From 0a8459693238a339de9705da4e26f6ffbb6a4ebc Mon Sep 17 00:00:00 2001 From: Gerd Hoffmann Date: Thu, 22 Aug 2019 11:06:43 +0200 Subject: fbdev: drop res_id parameter from remove_conflicting_pci_framebuffers Since commit b0e999c95581 ("fbdev: list all pci memory bars as conflicting apertures") the parameter was used for some sanity checks only, to make sure we detect any issues with the new approach to just list all memory bars as apertures. No issues turned up so far, so continue to cleanup: Drop the res_id parameter, drop the sanity checks. Also downgrade the logging from "info" level to "debug" level and update documentation. Signed-off-by: Gerd Hoffmann Reviewed-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/20190822090645.25410-2-kraxel@redhat.com --- include/linux/fb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 756706b666a1..41e0069eca0a 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -607,7 +607,7 @@ extern ssize_t fb_sys_write(struct fb_info *info, const char __user *buf, extern int register_framebuffer(struct fb_info *fb_info); extern void unregister_framebuffer(struct fb_info *fb_info); extern void unlink_framebuffer(struct fb_info *fb_info); -extern int remove_conflicting_pci_framebuffers(struct pci_dev *pdev, int res_id, +extern int remove_conflicting_pci_framebuffers(struct pci_dev *pdev, const char *name); extern int remove_conflicting_framebuffers(struct apertures_struct *a, const char *name, bool primary); -- cgit v1.2.3-71-gd317 From c88c8cd8265a9c7c2bf57350ab9c64d89c7b596b Mon Sep 17 00:00:00 2001 From: Mircea Caprioru Date: Mon, 2 Sep 2019 16:08:29 +0300 Subject: iio: adc: ad_sigma_delta: Export ad_sd_calibrate This patch exports the ad_sd_calibrate function in order to be able to call it from outside ad_sigma_delta. There are cases where the option to calibrate one channel at a time is necessary (ex. system calibration for zero scale and full scale). Signed-off-by: Mircea Caprioru Signed-off-by: Jonathan Cameron --- drivers/iio/adc/ad_sigma_delta.c | 3 ++- include/linux/iio/adc/ad_sigma_delta.h | 2 ++ 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c index 2640b75fb774..8ba90486c787 100644 --- a/drivers/iio/adc/ad_sigma_delta.c +++ b/drivers/iio/adc/ad_sigma_delta.c @@ -205,7 +205,7 @@ int ad_sd_reset(struct ad_sigma_delta *sigma_delta, } EXPORT_SYMBOL_GPL(ad_sd_reset); -static int ad_sd_calibrate(struct ad_sigma_delta *sigma_delta, +int ad_sd_calibrate(struct ad_sigma_delta *sigma_delta, unsigned int mode, unsigned int channel) { int ret; @@ -242,6 +242,7 @@ out: return ret; } +EXPORT_SYMBOL_GPL(ad_sd_calibrate); /** * ad_sd_calibrate_all() - Performs channel calibration diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index 7716fa0c9fce..8a4e25a7080c 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -119,6 +119,8 @@ int ad_sd_reset(struct ad_sigma_delta *sigma_delta, int ad_sigma_delta_single_conversion(struct iio_dev *indio_dev, const struct iio_chan_spec *chan, int *val); +int ad_sd_calibrate(struct ad_sigma_delta *sigma_delta, + unsigned int mode, unsigned int channel); int ad_sd_calibrate_all(struct ad_sigma_delta *sigma_delta, const struct ad_sd_calib_data *cd, unsigned int n); int ad_sd_init(struct ad_sigma_delta *sigma_delta, struct iio_dev *indio_dev, -- cgit v1.2.3-71-gd317 From ff92741270bf8b6e78aa885f166b68c7a67ab13a Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 30 Sep 2019 11:48:15 +0200 Subject: net: introduce name_node struct to be used in hashlist Introduce name_node structure to hold name of device and put it into hashlist instead of putting there struct net_device directly. Add a necessary infrastructure to manipulate the hashlist. This prepares the code to use the same hashlist for alternative names introduced later in this set. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 ++++- net/core/dev.c | 97 ++++++++++++++++++++++++++++++++++++++--------- 2 files changed, 87 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9eda1c31d1f7..e92bc5467256 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -925,6 +925,12 @@ struct dev_ifalias { struct devlink; struct tlsdev_ops; +struct netdev_name_node { + struct hlist_node hlist; + struct net_device *dev; + const char *name; +}; + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -1564,7 +1570,7 @@ enum netdev_priv_flags { * (i.e. as seen by users in the "Space.c" file). It is the name * of the interface. * - * @name_hlist: Device name hash chain, please keep it close to name[] + * @name_node: Name hashlist node * @ifalias: SNMP alias * @mem_end: Shared memory end * @mem_start: Shared memory start @@ -1774,7 +1780,7 @@ enum netdev_priv_flags { struct net_device { char name[IFNAMSIZ]; - struct hlist_node name_hlist; + struct netdev_name_node *name_node; struct dev_ifalias __rcu *ifalias; /* * I/O specific fields diff --git a/net/core/dev.c b/net/core/dev.c index 21a9c2987cbb..d2053d07c94a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -228,6 +228,67 @@ static inline void rps_unlock(struct softnet_data *sd) #endif } +static struct netdev_name_node *netdev_name_node_alloc(struct net_device *dev, + const char *name) +{ + struct netdev_name_node *name_node; + + name_node = kmalloc(sizeof(*name_node), GFP_KERNEL); + if (!name_node) + return NULL; + INIT_HLIST_NODE(&name_node->hlist); + name_node->dev = dev; + name_node->name = name; + return name_node; +} + +static struct netdev_name_node * +netdev_name_node_head_alloc(struct net_device *dev) +{ + return netdev_name_node_alloc(dev, dev->name); +} + +static void netdev_name_node_free(struct netdev_name_node *name_node) +{ + kfree(name_node); +} + +static void netdev_name_node_add(struct net *net, + struct netdev_name_node *name_node) +{ + hlist_add_head_rcu(&name_node->hlist, + dev_name_hash(net, name_node->name)); +} + +static void netdev_name_node_del(struct netdev_name_node *name_node) +{ + hlist_del_rcu(&name_node->hlist); +} + +static struct netdev_name_node *netdev_name_node_lookup(struct net *net, + const char *name) +{ + struct hlist_head *head = dev_name_hash(net, name); + struct netdev_name_node *name_node; + + hlist_for_each_entry(name_node, head, hlist) + if (!strcmp(name_node->name, name)) + return name_node; + return NULL; +} + +static struct netdev_name_node *netdev_name_node_lookup_rcu(struct net *net, + const char *name) +{ + struct hlist_head *head = dev_name_hash(net, name); + struct netdev_name_node *name_node; + + hlist_for_each_entry_rcu(name_node, head, hlist) + if (!strcmp(name_node->name, name)) + return name_node; + return NULL; +} + /* Device list insertion */ static void list_netdevice(struct net_device *dev) { @@ -237,7 +298,7 @@ static void list_netdevice(struct net_device *dev) write_lock_bh(&dev_base_lock); list_add_tail_rcu(&dev->dev_list, &net->dev_base_head); - hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name)); + netdev_name_node_add(net, dev->name_node); hlist_add_head_rcu(&dev->index_hlist, dev_index_hash(net, dev->ifindex)); write_unlock_bh(&dev_base_lock); @@ -255,7 +316,7 @@ static void unlist_netdevice(struct net_device *dev) /* Unlink dev from the device chain */ write_lock_bh(&dev_base_lock); list_del_rcu(&dev->dev_list); - hlist_del_rcu(&dev->name_hlist); + netdev_name_node_del(dev->name_node); hlist_del_rcu(&dev->index_hlist); write_unlock_bh(&dev_base_lock); @@ -733,14 +794,10 @@ EXPORT_SYMBOL_GPL(dev_fill_metadata_dst); struct net_device *__dev_get_by_name(struct net *net, const char *name) { - struct net_device *dev; - struct hlist_head *head = dev_name_hash(net, name); + struct netdev_name_node *node_name; - hlist_for_each_entry(dev, head, name_hlist) - if (!strncmp(dev->name, name, IFNAMSIZ)) - return dev; - - return NULL; + node_name = netdev_name_node_lookup(net, name); + return node_name ? node_name->dev : NULL; } EXPORT_SYMBOL(__dev_get_by_name); @@ -758,14 +815,10 @@ EXPORT_SYMBOL(__dev_get_by_name); struct net_device *dev_get_by_name_rcu(struct net *net, const char *name) { - struct net_device *dev; - struct hlist_head *head = dev_name_hash(net, name); - - hlist_for_each_entry_rcu(dev, head, name_hlist) - if (!strncmp(dev->name, name, IFNAMSIZ)) - return dev; + struct netdev_name_node *node_name; - return NULL; + node_name = netdev_name_node_lookup_rcu(net, name); + return node_name ? node_name->dev : NULL; } EXPORT_SYMBOL(dev_get_by_name_rcu); @@ -1232,13 +1285,13 @@ rollback: netdev_adjacent_rename_links(dev, oldname); write_lock_bh(&dev_base_lock); - hlist_del_rcu(&dev->name_hlist); + netdev_name_node_del(dev->name_node); write_unlock_bh(&dev_base_lock); synchronize_rcu(); write_lock_bh(&dev_base_lock); - hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name)); + netdev_name_node_add(net, dev->name_node); write_unlock_bh(&dev_base_lock); ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev); @@ -8264,6 +8317,8 @@ static void rollback_registered_many(struct list_head *head) dev_uc_flush(dev); dev_mc_flush(dev); + netdev_name_node_free(dev->name_node); + if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); @@ -8706,6 +8761,10 @@ int register_netdevice(struct net_device *dev) if (ret < 0) goto out; + dev->name_node = netdev_name_node_head_alloc(dev); + if (!dev->name_node) + goto out; + /* Init, if this function is available */ if (dev->netdev_ops->ndo_init) { ret = dev->netdev_ops->ndo_init(dev); @@ -8827,6 +8886,8 @@ out: return ret; err_uninit: + if (dev->name_node) + netdev_name_node_free(dev->name_node); if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); if (dev->priv_destructor) -- cgit v1.2.3-71-gd317 From 36fbf1e52bd3ff8a5cb604955eedfc9350c2e6cc Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 30 Sep 2019 11:48:16 +0200 Subject: net: rtnetlink: add linkprop commands to add and delete alternative ifnames Add two commands to add and delete list of link properties. Implement the first property type along - alternative ifnames. Each net device can have multiple alternative names. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++ include/uapi/linux/if.h | 1 + include/uapi/linux/if_link.h | 2 + include/uapi/linux/rtnetlink.h | 7 +++ net/core/dev.c | 58 ++++++++++++++++++++++- net/core/rtnetlink.c | 103 +++++++++++++++++++++++++++++++++++++++++ security/selinux/nlmsgtab.c | 4 +- 7 files changed, 177 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e92bc5467256..48cc71aae466 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -927,10 +927,14 @@ struct tlsdev_ops; struct netdev_name_node { struct hlist_node hlist; + struct list_head list; struct net_device *dev; const char *name; }; +int netdev_name_node_alt_create(struct net_device *dev, const char *name); +int netdev_name_node_alt_destroy(struct net_device *dev, const char *name); + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are diff --git a/include/uapi/linux/if.h b/include/uapi/linux/if.h index 7fea0fd7d6f5..4bf33344aab1 100644 --- a/include/uapi/linux/if.h +++ b/include/uapi/linux/if.h @@ -33,6 +33,7 @@ #define IFNAMSIZ 16 #endif /* __UAPI_DEF_IF_IFNAMSIZ */ #define IFALIASZ 256 +#define ALTIFNAMSIZ 128 #include /* For glibc compatibility. An empty enum does not compile. */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 4a8c02cafa9a..8aec8769d944 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -167,6 +167,8 @@ enum { IFLA_NEW_IFINDEX, IFLA_MIN_MTU, IFLA_MAX_MTU, + IFLA_PROP_LIST, + IFLA_ALT_IFNAME, /* Alternative ifname */ __IFLA_MAX }; diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index ce2a623abb75..1418a8362bb7 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -164,6 +164,13 @@ enum { RTM_GETNEXTHOP, #define RTM_GETNEXTHOP RTM_GETNEXTHOP + RTM_NEWLINKPROP = 108, +#define RTM_NEWLINKPROP RTM_NEWLINKPROP + RTM_DELLINKPROP, +#define RTM_DELLINKPROP RTM_DELLINKPROP + RTM_GETLINKPROP, +#define RTM_GETLINKPROP RTM_GETLINKPROP + __RTM_MAX, #define RTM_MAX (((__RTM_MAX + 3) & ~3) - 1) }; diff --git a/net/core/dev.c b/net/core/dev.c index d2053d07c94a..7a456c6a7ad8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -245,7 +245,13 @@ static struct netdev_name_node *netdev_name_node_alloc(struct net_device *dev, static struct netdev_name_node * netdev_name_node_head_alloc(struct net_device *dev) { - return netdev_name_node_alloc(dev, dev->name); + struct netdev_name_node *name_node; + + name_node = netdev_name_node_alloc(dev, dev->name); + if (!name_node) + return NULL; + INIT_LIST_HEAD(&name_node->list); + return name_node; } static void netdev_name_node_free(struct netdev_name_node *name_node) @@ -289,6 +295,55 @@ static struct netdev_name_node *netdev_name_node_lookup_rcu(struct net *net, return NULL; } +int netdev_name_node_alt_create(struct net_device *dev, const char *name) +{ + struct netdev_name_node *name_node; + struct net *net = dev_net(dev); + + name_node = netdev_name_node_lookup(net, name); + if (name_node) + return -EEXIST; + name_node = netdev_name_node_alloc(dev, name); + if (!name_node) + return -ENOMEM; + netdev_name_node_add(net, name_node); + /* The node that holds dev->name acts as a head of per-device list. */ + list_add_tail(&name_node->list, &dev->name_node->list); + + return 0; +} +EXPORT_SYMBOL(netdev_name_node_alt_create); + +static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node) +{ + list_del(&name_node->list); + netdev_name_node_del(name_node); + kfree(name_node->name); + netdev_name_node_free(name_node); +} + +int netdev_name_node_alt_destroy(struct net_device *dev, const char *name) +{ + struct netdev_name_node *name_node; + struct net *net = dev_net(dev); + + name_node = netdev_name_node_lookup(net, name); + if (!name_node) + return -ENOENT; + __netdev_name_node_alt_destroy(name_node); + + return 0; +} +EXPORT_SYMBOL(netdev_name_node_alt_destroy); + +static void netdev_name_node_alt_flush(struct net_device *dev) +{ + struct netdev_name_node *name_node, *tmp; + + list_for_each_entry_safe(name_node, tmp, &dev->name_node->list, list) + __netdev_name_node_alt_destroy(name_node); +} + /* Device list insertion */ static void list_netdevice(struct net_device *dev) { @@ -8317,6 +8372,7 @@ static void rollback_registered_many(struct list_head *head) dev_uc_flush(dev); dev_mc_flush(dev); + netdev_name_node_alt_flush(dev); netdev_name_node_free(dev->name_node); if (dev->netdev_ops->ndo_uninit) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 1ee6460f8275..e13646993d82 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1750,6 +1750,9 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_CARRIER_DOWN_COUNT] = { .type = NLA_U32 }, [IFLA_MIN_MTU] = { .type = NLA_U32 }, [IFLA_MAX_MTU] = { .type = NLA_U32 }, + [IFLA_PROP_LIST] = { .type = NLA_NESTED }, + [IFLA_ALT_IFNAME] = { .type = NLA_STRING, + .len = ALTIFNAMSIZ - 1 }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { @@ -3373,6 +3376,103 @@ out: return err; } +static int rtnl_alt_ifname(int cmd, struct net_device *dev, struct nlattr *attr, + bool *changed, struct netlink_ext_ack *extack) +{ + char *alt_ifname; + int err; + + err = nla_validate(attr, attr->nla_len, IFLA_MAX, ifla_policy, extack); + if (err) + return err; + + alt_ifname = nla_data(attr); + if (cmd == RTM_NEWLINKPROP) { + alt_ifname = kstrdup(alt_ifname, GFP_KERNEL); + if (!alt_ifname) + return -ENOMEM; + err = netdev_name_node_alt_create(dev, alt_ifname); + if (err) { + kfree(alt_ifname); + return err; + } + } else if (cmd == RTM_DELLINKPROP) { + err = netdev_name_node_alt_destroy(dev, alt_ifname); + if (err) + return err; + } else { + WARN_ON(1); + return 0; + } + + *changed = true; + return 0; +} + +static int rtnl_linkprop(int cmd, struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(skb->sk); + struct nlattr *tb[IFLA_MAX + 1]; + struct net_device *dev; + struct ifinfomsg *ifm; + bool changed = false; + struct nlattr *attr; + int err, rem; + + err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy, extack); + if (err) + return err; + + err = rtnl_ensure_unique_netns(tb, extack, true); + if (err) + return err; + + ifm = nlmsg_data(nlh); + if (ifm->ifi_index > 0) { + dev = __dev_get_by_index(net, ifm->ifi_index); + } else if (tb[IFLA_IFNAME]) { + char ifname[IFNAMSIZ]; + + nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); + dev = __dev_get_by_name(net, ifname); + } else { + return -EINVAL; + } + + if (!dev) + return -ENODEV; + + if (!tb[IFLA_PROP_LIST]) + return 0; + + nla_for_each_nested(attr, tb[IFLA_PROP_LIST], rem) { + switch (nla_type(attr)) { + case IFLA_ALT_IFNAME: + err = rtnl_alt_ifname(cmd, dev, attr, &changed, extack); + if (err) + return err; + break; + } + } + + if (changed) + netdev_state_change(dev); + return 0; +} + +static int rtnl_newlinkprop(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + return rtnl_linkprop(RTM_NEWLINKPROP, skb, nlh, extack); +} + +static int rtnl_dellinkprop(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + return rtnl_linkprop(RTM_DELLINKPROP, skb, nlh, extack); +} + static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); @@ -5331,6 +5431,9 @@ void __init rtnetlink_init(void) rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, 0); rtnl_register(PF_UNSPEC, RTM_GETNETCONF, NULL, rtnl_dump_all, 0); + rtnl_register(PF_UNSPEC, RTM_NEWLINKPROP, rtnl_newlinkprop, NULL, 0); + rtnl_register(PF_UNSPEC, RTM_DELLINKPROP, rtnl_dellinkprop, NULL, 0); + rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, 0); rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, 0); rtnl_register(PF_BRIDGE, RTM_GETNEIGH, rtnl_fdb_get, rtnl_fdb_dump, 0); diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c index 58345ba0528e..c97fdae8f71b 100644 --- a/security/selinux/nlmsgtab.c +++ b/security/selinux/nlmsgtab.c @@ -83,6 +83,8 @@ static const struct nlmsg_perm nlmsg_route_perms[] = { RTM_NEWNEXTHOP, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELNEXTHOP, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_GETNEXTHOP, NETLINK_ROUTE_SOCKET__NLMSG_READ }, + { RTM_NEWLINKPROP, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, + { RTM_DELLINKPROP, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, }; static const struct nlmsg_perm nlmsg_tcpdiag_perms[] = @@ -166,7 +168,7 @@ int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm) * structures at the top of this file with the new mappings * before updating the BUILD_BUG_ON() macro! */ - BUILD_BUG_ON(RTM_MAX != (RTM_NEWNEXTHOP + 3)); + BUILD_BUG_ON(RTM_MAX != (RTM_NEWLINKPROP + 3)); err = nlmsg_perm(nlmsg_type, perm, nlmsg_route_perms, sizeof(nlmsg_route_perms)); break; -- cgit v1.2.3-71-gd317 From a14b820316e84310b1bad3701a8d4c9159377633 Mon Sep 17 00:00:00 2001 From: Vivek Gautam Date: Thu, 18 Jul 2019 18:32:36 +0530 Subject: soc: qcom: llcc cleanup to get rid of sdm845 specific driver file A single file should suffice the need to program the llcc for various platforms. Get rid of sdm845 specific driver file to make way for a more generic driver. Signed-off-by: Vivek Gautam Signed-off-by: Bjorn Andersson --- drivers/soc/qcom/Kconfig | 14 ++---- drivers/soc/qcom/Makefile | 1 - drivers/soc/qcom/llcc-sdm845.c | 100 ------------------------------------- drivers/soc/qcom/llcc-slice.c | 60 +++++++++++++++++++--- include/linux/soc/qcom/llcc-qcom.h | 57 ++++++++------------- 5 files changed, 77 insertions(+), 155 deletions(-) delete mode 100644 drivers/soc/qcom/llcc-sdm845.c (limited to 'include/linux') diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig index 661e47acc354..c6df8b43fa6d 100644 --- a/drivers/soc/qcom/Kconfig +++ b/drivers/soc/qcom/Kconfig @@ -58,17 +58,9 @@ config QCOM_LLCC depends on ARCH_QCOM || COMPILE_TEST help Qualcomm Technologies, Inc. platform specific - Last Level Cache Controller(LLCC) driver. This provides interfaces - to clients that use the LLCC. Say yes here to enable LLCC slice - driver. - -config QCOM_SDM845_LLCC - tristate "Qualcomm Technologies, Inc. SDM845 LLCC driver" - depends on QCOM_LLCC - help - Say yes here to enable the LLCC driver for SDM845. This provides - data required to configure LLCC so that clients can start using the - LLCC slices. + Last Level Cache Controller(LLCC) driver for platforms such as, + SDM845. This provides interfaces to clients that use the LLCC. + Say yes here to enable LLCC slice driver. config QCOM_MDT_LOADER tristate diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile index 162788701a77..28d45b2e87e8 100644 --- a/drivers/soc/qcom/Makefile +++ b/drivers/soc/qcom/Makefile @@ -22,6 +22,5 @@ obj-$(CONFIG_QCOM_SOCINFO) += socinfo.o obj-$(CONFIG_QCOM_WCNSS_CTRL) += wcnss_ctrl.o obj-$(CONFIG_QCOM_APR) += apr.o obj-$(CONFIG_QCOM_LLCC) += llcc-slice.o -obj-$(CONFIG_QCOM_SDM845_LLCC) += llcc-sdm845.o obj-$(CONFIG_QCOM_RPMHPD) += rpmhpd.o obj-$(CONFIG_QCOM_RPMPD) += rpmpd.o diff --git a/drivers/soc/qcom/llcc-sdm845.c b/drivers/soc/qcom/llcc-sdm845.c deleted file mode 100644 index 86600d97c36d..000000000000 --- a/drivers/soc/qcom/llcc-sdm845.c +++ /dev/null @@ -1,100 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2017-2018, The Linux Foundation. All rights reserved. - * - */ - -#include -#include -#include -#include -#include - -/* - * SCT(System Cache Table) entry contains of the following members: - * usecase_id: Unique id for the client's use case - * slice_id: llcc slice id for each client - * max_cap: The maximum capacity of the cache slice provided in KB - * priority: Priority of the client used to select victim line for replacement - * fixed_size: Boolean indicating if the slice has a fixed capacity - * bonus_ways: Bonus ways are additional ways to be used for any slice, - * if client ends up using more than reserved cache ways. Bonus - * ways are allocated only if they are not reserved for some - * other client. - * res_ways: Reserved ways for the cache slice, the reserved ways cannot - * be used by any other client than the one its assigned to. - * cache_mode: Each slice operates as a cache, this controls the mode of the - * slice: normal or TCM(Tightly Coupled Memory) - * probe_target_ways: Determines what ways to probe for access hit. When - * configured to 1 only bonus and reserved ways are probed. - * When configured to 0 all ways in llcc are probed. - * dis_cap_alloc: Disable capacity based allocation for a client - * retain_on_pc: If this bit is set and client has maintained active vote - * then the ways assigned to this client are not flushed on power - * collapse. - * activate_on_init: Activate the slice immediately after the SCT is programmed - */ -#define SCT_ENTRY(uid, sid, mc, p, fs, bway, rway, cmod, ptw, dca, rp, a) \ - { \ - .usecase_id = uid, \ - .slice_id = sid, \ - .max_cap = mc, \ - .priority = p, \ - .fixed_size = fs, \ - .bonus_ways = bway, \ - .res_ways = rway, \ - .cache_mode = cmod, \ - .probe_target_ways = ptw, \ - .dis_cap_alloc = dca, \ - .retain_on_pc = rp, \ - .activate_on_init = a, \ - } - -static struct llcc_slice_config sdm845_data[] = { - SCT_ENTRY(LLCC_CPUSS, 1, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 1), - SCT_ENTRY(LLCC_VIDSC0, 2, 512, 2, 1, 0x0, 0x0f0, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_VIDSC1, 3, 512, 2, 1, 0x0, 0x0f0, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_ROTATOR, 4, 563, 2, 1, 0x0, 0x00e, 2, 0, 1, 1, 0), - SCT_ENTRY(LLCC_VOICE, 5, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_AUDIO, 6, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_MDMHPGRW, 7, 1024, 2, 0, 0xfc, 0xf00, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_MDM, 8, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_CMPT, 10, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_GPUHTW, 11, 512, 1, 1, 0xc, 0x0, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_GPU, 12, 2304, 1, 0, 0xff0, 0x2, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_MMUHWT, 13, 256, 2, 0, 0x0, 0x1, 0, 0, 1, 0, 1), - SCT_ENTRY(LLCC_CMPTDMA, 15, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_DISP, 16, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_VIDFW, 17, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_MDMHPFX, 20, 1024, 2, 1, 0x0, 0xf00, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_MDMPNG, 21, 1024, 0, 1, 0x1e, 0x0, 0, 0, 1, 1, 0), - SCT_ENTRY(LLCC_AUDHW, 22, 1024, 1, 1, 0xffc, 0x2, 0, 0, 1, 1, 0), -}; - -static int sdm845_qcom_llcc_remove(struct platform_device *pdev) -{ - return qcom_llcc_remove(pdev); -} - -static int sdm845_qcom_llcc_probe(struct platform_device *pdev) -{ - return qcom_llcc_probe(pdev, sdm845_data, ARRAY_SIZE(sdm845_data)); -} - -static const struct of_device_id sdm845_qcom_llcc_of_match[] = { - { .compatible = "qcom,sdm845-llcc", }, - { } -}; - -static struct platform_driver sdm845_qcom_llcc_driver = { - .driver = { - .name = "sdm845-llcc", - .of_match_table = sdm845_qcom_llcc_of_match, - }, - .probe = sdm845_qcom_llcc_probe, - .remove = sdm845_qcom_llcc_remove, -}; -module_platform_driver(sdm845_qcom_llcc_driver); - -MODULE_DESCRIPTION("QCOM sdm845 LLCC driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/soc/qcom/llcc-slice.c b/drivers/soc/qcom/llcc-slice.c index 9090ea12eaf3..574bb5bf20bc 100644 --- a/drivers/soc/qcom/llcc-slice.c +++ b/drivers/soc/qcom/llcc-slice.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Copyright (c) 2017-2018, The Linux Foundation. All rights reserved. + * Copyright (c) 2017-2019, The Linux Foundation. All rights reserved. * */ @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -46,6 +47,27 @@ #define BANK_OFFSET_STRIDE 0x80000 +static struct llcc_slice_config sdm845_data[] = { + { LLCC_CPUSS, 1, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 1 }, + { LLCC_VIDSC0, 2, 512, 2, 1, 0x0, 0x0f0, 0, 0, 1, 1, 0 }, + { LLCC_VIDSC1, 3, 512, 2, 1, 0x0, 0x0f0, 0, 0, 1, 1, 0 }, + { LLCC_ROTATOR, 4, 563, 2, 1, 0x0, 0x00e, 2, 0, 1, 1, 0 }, + { LLCC_VOICE, 5, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0 }, + { LLCC_AUDIO, 6, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0 }, + { LLCC_MDMHPGRW, 7, 1024, 2, 0, 0xfc, 0xf00, 0, 0, 1, 1, 0 }, + { LLCC_MDM, 8, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0 }, + { LLCC_CMPT, 10, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0 }, + { LLCC_GPUHTW, 11, 512, 1, 1, 0xc, 0x0, 0, 0, 1, 1, 0 }, + { LLCC_GPU, 12, 2304, 1, 0, 0xff0, 0x2, 0, 0, 1, 1, 0 }, + { LLCC_MMUHWT, 13, 256, 2, 0, 0x0, 0x1, 0, 0, 1, 0, 1 }, + { LLCC_CMPTDMA, 15, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0 }, + { LLCC_DISP, 16, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0 }, + { LLCC_VIDFW, 17, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 0 }, + { LLCC_MDMHPFX, 20, 1024, 2, 1, 0x0, 0xf00, 0, 0, 1, 1, 0 }, + { LLCC_MDMPNG, 21, 1024, 0, 1, 0x1e, 0x0, 0, 0, 1, 1, 0 }, + { LLCC_AUDHW, 22, 1024, 1, 1, 0xffc, 0x2, 0, 0, 1, 1, 0 }, +}; + static struct llcc_drv_data *drv_data = (void *) -EPROBE_DEFER; static const struct regmap_config llcc_regmap_config = { @@ -301,13 +323,12 @@ static int qcom_llcc_cfg_program(struct platform_device *pdev) return ret; } -int qcom_llcc_remove(struct platform_device *pdev) +static int qcom_llcc_remove(struct platform_device *pdev) { /* Set the global pointer to a error code to avoid referencing it */ drv_data = ERR_PTR(-ENODEV); return 0; } -EXPORT_SYMBOL_GPL(qcom_llcc_remove); static struct regmap *qcom_llcc_init_mmio(struct platform_device *pdev, const char *name) @@ -326,8 +347,8 @@ static struct regmap *qcom_llcc_init_mmio(struct platform_device *pdev, return devm_regmap_init_mmio(&pdev->dev, base, &llcc_regmap_config); } -int qcom_llcc_probe(struct platform_device *pdev, - const struct llcc_slice_config *llcc_cfg, u32 sz) +static int qcom_llcc_probe(struct platform_device *pdev, + const struct llcc_slice_config *llcc_cfg, u32 sz) { u32 num_banks; struct device *dev = &pdev->dev; @@ -407,6 +428,31 @@ err: drv_data = ERR_PTR(-ENODEV); return ret; } -EXPORT_SYMBOL_GPL(qcom_llcc_probe); + +static int sdm845_qcom_llcc_remove(struct platform_device *pdev) +{ + return qcom_llcc_remove(pdev); +} + +static int sdm845_qcom_llcc_probe(struct platform_device *pdev) +{ + return qcom_llcc_probe(pdev, sdm845_data, ARRAY_SIZE(sdm845_data)); +} + +static const struct of_device_id sdm845_qcom_llcc_of_match[] = { + { .compatible = "qcom,sdm845-llcc", }, + { } +}; + +static struct platform_driver sdm845_qcom_llcc_driver = { + .driver = { + .name = "sdm845-llcc", + .of_match_table = sdm845_qcom_llcc_of_match, + }, + .probe = sdm845_qcom_llcc_probe, + .remove = sdm845_qcom_llcc_remove, +}; +module_platform_driver(sdm845_qcom_llcc_driver); + +MODULE_DESCRIPTION("QCOM sdm845 LLCC driver"); MODULE_LICENSE("GPL v2"); -MODULE_DESCRIPTION("Qualcomm Last Level Cache Controller"); diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index eb71a50b8afc..d5cad6f7953c 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -39,18 +39,27 @@ struct llcc_slice_desc { /** * llcc_slice_config - Data associated with the llcc slice - * @usecase_id: usecase id for which the llcc slice is used - * @slice_id: llcc slice id assigned to each slice - * @max_cap: maximum capacity of the llcc slice - * @priority: priority of the llcc slice - * @fixed_size: whether the llcc slice can grow beyond its size - * @bonus_ways: bonus ways associated with llcc slice - * @res_ways: reserved ways associated with llcc slice - * @cache_mode: mode of the llcc slice - * @probe_target_ways: Probe only reserved and bonus ways on a cache miss - * @dis_cap_alloc: Disable capacity based allocation - * @retain_on_pc: Retain through power collapse - * @activate_on_init: activate the slice on init + * @usecase_id: Unique id for the client's use case + * @slice_id: llcc slice id for each client + * @max_cap: The maximum capacity of the cache slice provided in KB + * @priority: Priority of the client used to select victim line for replacement + * @fixed_size: Boolean indicating if the slice has a fixed capacity + * @bonus_ways: Bonus ways are additional ways to be used for any slice, + * if client ends up using more than reserved cache ways. Bonus + * ways are allocated only if they are not reserved for some + * other client. + * @res_ways: Reserved ways for the cache slice, the reserved ways cannot + * be used by any other client than the one its assigned to. + * @cache_mode: Each slice operates as a cache, this controls the mode of the + * slice: normal or TCM(Tightly Coupled Memory) + * @probe_target_ways: Determines what ways to probe for access hit. When + * configured to 1 only bonus and reserved ways are probed. + * When configured to 0 all ways in llcc are probed. + * @dis_cap_alloc: Disable capacity based allocation for a client + * @retain_on_pc: If this bit is set and client has maintained active vote + * then the ways assigned to this client are not flushed on power + * collapse. + * @activate_on_init: Activate the slice immediately after it is programmed */ struct llcc_slice_config { u32 usecase_id; @@ -154,20 +163,6 @@ int llcc_slice_activate(struct llcc_slice_desc *desc); */ int llcc_slice_deactivate(struct llcc_slice_desc *desc); -/** - * qcom_llcc_probe - program the sct table - * @pdev: platform device pointer - * @table: soc sct table - * @sz: Size of the config table - */ -int qcom_llcc_probe(struct platform_device *pdev, - const struct llcc_slice_config *table, u32 sz); - -/** - * qcom_llcc_remove - remove the sct table - * @pdev: Platform device pointer - */ -int qcom_llcc_remove(struct platform_device *pdev); #else static inline struct llcc_slice_desc *llcc_slice_getd(u32 uid) { @@ -197,16 +192,6 @@ static inline int llcc_slice_deactivate(struct llcc_slice_desc *desc) { return -EINVAL; } -static inline int qcom_llcc_probe(struct platform_device *pdev, - const struct llcc_slice_config *table, u32 sz) -{ - return -ENODEV; -} - -static inline int qcom_llcc_remove(struct platform_device *pdev) -{ - return -ENODEV; -} #endif #endif -- cgit v1.2.3-71-gd317 From 99356b03b431f9589bbaec2bc5bacceccb3dd99a Mon Sep 17 00:00:00 2001 From: Vivek Gautam Date: Thu, 18 Jul 2019 18:32:38 +0530 Subject: soc: qcom: Make llcc-qcom a generic driver This makes way for adding future llcc versions. Also pull out the llcc-qcom specific definitions from includes. Includes path now contains the only definitions that are to be exposed to other subsystems. Signed-off-by: Vivek Gautam Signed-off-by: Bjorn Andersson --- drivers/soc/qcom/llcc-qcom.c | 137 +++++++++++++++++++++++++++++++------ include/linux/soc/qcom/llcc-qcom.h | 89 ------------------------ 2 files changed, 116 insertions(+), 110 deletions(-) (limited to 'include/linux') diff --git a/drivers/soc/qcom/llcc-qcom.c b/drivers/soc/qcom/llcc-qcom.c index 574bb5bf20bc..98563ef0ac6b 100644 --- a/drivers/soc/qcom/llcc-qcom.c +++ b/drivers/soc/qcom/llcc-qcom.c @@ -47,6 +47,100 @@ #define BANK_OFFSET_STRIDE 0x80000 +/** + * llcc_slice_config - Data associated with the llcc slice + * @usecase_id: Unique id for the client's use case + * @slice_id: llcc slice id for each client + * @max_cap: The maximum capacity of the cache slice provided in KB + * @priority: Priority of the client used to select victim line for replacement + * @fixed_size: Boolean indicating if the slice has a fixed capacity + * @bonus_ways: Bonus ways are additional ways to be used for any slice, + * if client ends up using more than reserved cache ways. Bonus + * ways are allocated only if they are not reserved for some + * other client. + * @res_ways: Reserved ways for the cache slice, the reserved ways cannot + * be used by any other client than the one its assigned to. + * @cache_mode: Each slice operates as a cache, this controls the mode of the + * slice: normal or TCM(Tightly Coupled Memory) + * @probe_target_ways: Determines what ways to probe for access hit. When + * configured to 1 only bonus and reserved ways are probed. + * When configured to 0 all ways in llcc are probed. + * @dis_cap_alloc: Disable capacity based allocation for a client + * @retain_on_pc: If this bit is set and client has maintained active vote + * then the ways assigned to this client are not flushed on power + * collapse. + * @activate_on_init: Activate the slice immediately after it is programmed + */ +struct llcc_slice_config { + u32 usecase_id; + u32 slice_id; + u32 max_cap; + u32 priority; + bool fixed_size; + u32 bonus_ways; + u32 res_ways; + u32 cache_mode; + u32 probe_target_ways; + bool dis_cap_alloc; + bool retain_on_pc; + bool activate_on_init; +}; + +/** + * llcc_drv_data - Data associated with the llcc driver + * @regmap: regmap associated with the llcc device + * @bcast_regmap: regmap associated with llcc broadcast offset + * @cfg: pointer to the data structure for slice configuration + * @lock: mutex associated with each slice + * @cfg_size: size of the config data table + * @max_slices: max slices as read from device tree + * @num_banks: Number of llcc banks + * @bitmap: Bit map to track the active slice ids + * @offsets: Pointer to the bank offsets array + * @ecc_irq: interrupt for llcc cache error detection and reporting + */ +struct llcc_drv_data { + struct regmap *regmap; + struct regmap *bcast_regmap; + const struct llcc_slice_config *cfg; + struct mutex lock; + u32 cfg_size; + u32 max_slices; + u32 num_banks; + unsigned long *bitmap; + u32 *offsets; + int ecc_irq; +}; + +/** + * llcc_edac_reg_data - llcc edac registers data for each error type + * @name: Name of the error + * @synd_reg: Syndrome register address + * @count_status_reg: Status register address to read the error count + * @ways_status_reg: Status register address to read the error ways + * @reg_cnt: Number of registers + * @count_mask: Mask value to get the error count + * @ways_mask: Mask value to get the error ways + * @count_shift: Shift value to get the error count + * @ways_shift: Shift value to get the error ways + */ +struct llcc_edac_reg_data { + char *name; + u64 synd_reg; + u64 count_status_reg; + u64 ways_status_reg; + u32 reg_cnt; + u32 count_mask; + u32 ways_mask; + u8 count_shift; + u8 ways_shift; +}; + +struct qcom_llcc_config { + const struct llcc_slice_config *sct_data; + int size; +}; + static struct llcc_slice_config sdm845_data[] = { { LLCC_CPUSS, 1, 2816, 1, 0, 0xffc, 0x2, 0, 0, 1, 1, 1 }, { LLCC_VIDSC0, 2, 512, 2, 1, 0x0, 0x0f0, 0, 0, 1, 1, 0 }, @@ -68,6 +162,11 @@ static struct llcc_slice_config sdm845_data[] = { { LLCC_AUDHW, 22, 1024, 1, 1, 0xffc, 0x2, 0, 0, 1, 1, 0 }, }; +static const struct qcom_llcc_config sdm845_cfg = { + .sct_data = sdm845_data, + .size = ARRAY_SIZE(sdm845_data), +}; + static struct llcc_drv_data *drv_data = (void *) -EPROBE_DEFER; static const struct regmap_config llcc_regmap_config = { @@ -347,13 +446,15 @@ static struct regmap *qcom_llcc_init_mmio(struct platform_device *pdev, return devm_regmap_init_mmio(&pdev->dev, base, &llcc_regmap_config); } -static int qcom_llcc_probe(struct platform_device *pdev, - const struct llcc_slice_config *llcc_cfg, u32 sz) +static int qcom_llcc_probe(struct platform_device *pdev) { u32 num_banks; struct device *dev = &pdev->dev; int ret, i; struct platform_device *llcc_edac; + const struct qcom_llcc_config *cfg; + const struct llcc_slice_config *llcc_cfg; + u32 sz; drv_data = devm_kzalloc(dev, sizeof(*drv_data), GFP_KERNEL); if (!drv_data) { @@ -383,6 +484,10 @@ static int qcom_llcc_probe(struct platform_device *pdev, num_banks >>= LLCC_LB_CNT_SHIFT; drv_data->num_banks = num_banks; + cfg = of_device_get_match_data(&pdev->dev); + llcc_cfg = cfg->sct_data; + sz = cfg->size; + for (i = 0; i < sz; i++) if (llcc_cfg[i].slice_id > drv_data->max_slices) drv_data->max_slices = llcc_cfg[i].slice_id; @@ -429,30 +534,20 @@ err: return ret; } -static int sdm845_qcom_llcc_remove(struct platform_device *pdev) -{ - return qcom_llcc_remove(pdev); -} - -static int sdm845_qcom_llcc_probe(struct platform_device *pdev) -{ - return qcom_llcc_probe(pdev, sdm845_data, ARRAY_SIZE(sdm845_data)); -} - -static const struct of_device_id sdm845_qcom_llcc_of_match[] = { - { .compatible = "qcom,sdm845-llcc", }, +static const struct of_device_id qcom_llcc_of_match[] = { + { .compatible = "qcom,sdm845-llcc", .data = &sdm845_cfg }, { } }; -static struct platform_driver sdm845_qcom_llcc_driver = { +static struct platform_driver qcom_llcc_driver = { .driver = { - .name = "sdm845-llcc", - .of_match_table = sdm845_qcom_llcc_of_match, + .name = "qcom-llcc", + .of_match_table = qcom_llcc_of_match, }, - .probe = sdm845_qcom_llcc_probe, - .remove = sdm845_qcom_llcc_remove, + .probe = qcom_llcc_probe, + .remove = qcom_llcc_remove, }; -module_platform_driver(sdm845_qcom_llcc_driver); +module_platform_driver(qcom_llcc_driver); -MODULE_DESCRIPTION("QCOM sdm845 LLCC driver"); +MODULE_DESCRIPTION("Qualcomm Last Level Cache Controller"); MODULE_LICENSE("GPL v2"); diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index d5cad6f7953c..c0acdb28fde8 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -37,95 +37,6 @@ struct llcc_slice_desc { size_t slice_size; }; -/** - * llcc_slice_config - Data associated with the llcc slice - * @usecase_id: Unique id for the client's use case - * @slice_id: llcc slice id for each client - * @max_cap: The maximum capacity of the cache slice provided in KB - * @priority: Priority of the client used to select victim line for replacement - * @fixed_size: Boolean indicating if the slice has a fixed capacity - * @bonus_ways: Bonus ways are additional ways to be used for any slice, - * if client ends up using more than reserved cache ways. Bonus - * ways are allocated only if they are not reserved for some - * other client. - * @res_ways: Reserved ways for the cache slice, the reserved ways cannot - * be used by any other client than the one its assigned to. - * @cache_mode: Each slice operates as a cache, this controls the mode of the - * slice: normal or TCM(Tightly Coupled Memory) - * @probe_target_ways: Determines what ways to probe for access hit. When - * configured to 1 only bonus and reserved ways are probed. - * When configured to 0 all ways in llcc are probed. - * @dis_cap_alloc: Disable capacity based allocation for a client - * @retain_on_pc: If this bit is set and client has maintained active vote - * then the ways assigned to this client are not flushed on power - * collapse. - * @activate_on_init: Activate the slice immediately after it is programmed - */ -struct llcc_slice_config { - u32 usecase_id; - u32 slice_id; - u32 max_cap; - u32 priority; - bool fixed_size; - u32 bonus_ways; - u32 res_ways; - u32 cache_mode; - u32 probe_target_ways; - bool dis_cap_alloc; - bool retain_on_pc; - bool activate_on_init; -}; - -/** - * llcc_drv_data - Data associated with the llcc driver - * @regmap: regmap associated with the llcc device - * @bcast_regmap: regmap associated with llcc broadcast offset - * @cfg: pointer to the data structure for slice configuration - * @lock: mutex associated with each slice - * @cfg_size: size of the config data table - * @max_slices: max slices as read from device tree - * @num_banks: Number of llcc banks - * @bitmap: Bit map to track the active slice ids - * @offsets: Pointer to the bank offsets array - * @ecc_irq: interrupt for llcc cache error detection and reporting - */ -struct llcc_drv_data { - struct regmap *regmap; - struct regmap *bcast_regmap; - const struct llcc_slice_config *cfg; - struct mutex lock; - u32 cfg_size; - u32 max_slices; - u32 num_banks; - unsigned long *bitmap; - u32 *offsets; - int ecc_irq; -}; - -/** - * llcc_edac_reg_data - llcc edac registers data for each error type - * @name: Name of the error - * @synd_reg: Syndrome register address - * @count_status_reg: Status register address to read the error count - * @ways_status_reg: Status register address to read the error ways - * @reg_cnt: Number of registers - * @count_mask: Mask value to get the error count - * @ways_mask: Mask value to get the error ways - * @count_shift: Shift value to get the error count - * @ways_shift: Shift value to get the error ways - */ -struct llcc_edac_reg_data { - char *name; - u64 synd_reg; - u64 count_status_reg; - u64 ways_status_reg; - u32 reg_cnt; - u32 count_mask; - u32 ways_mask; - u8 count_shift; - u8 ways_shift; -}; - #if IS_ENABLED(CONFIG_QCOM_LLCC) /** * llcc_slice_getd - get llcc slice descriptor -- cgit v1.2.3-71-gd317 From afa0df5998131153ec3036f41e76ece33bf1334f Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 30 Sep 2019 10:15:09 +0200 Subject: net: push loops and nb calls into helper functions Push iterations over net namespaces and netdevices from register_netdevice_notifier() and unregister_netdevice_notifier() into helper functions. Along with that introduce continue_reverse macros to make the code a bit nicer allowing to get rid of "last" marks. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 ++ include/net/net_namespace.h | 3 +- net/core/dev.c | 89 +++++++++++++++++++++++++++++++-------------- 3 files changed, 66 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 48cc71aae466..7b183f724fc4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2574,6 +2574,9 @@ extern rwlock_t dev_base_lock; /* Device list lock */ list_for_each_entry_safe(d, n, &(net)->dev_base_head, dev_list) #define for_each_netdev_continue(net, d) \ list_for_each_entry_continue(d, &(net)->dev_base_head, dev_list) +#define for_each_netdev_continue_reverse(net, d) \ + list_for_each_entry_continue_reverse(d, &(net)->dev_base_head, \ + dev_list) #define for_each_netdev_continue_rcu(net, d) \ list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_in_bond_rcu(bond, slave) \ diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index f8712bbeb2e0..c5a98e03591d 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -317,7 +317,8 @@ static inline struct net *read_pnet(const possible_net_t *pnet) /* Protected by net_rwsem */ #define for_each_net(VAR) \ list_for_each_entry(VAR, &net_namespace_list, list) - +#define for_each_net_continue_reverse(VAR) \ + list_for_each_entry_continue_reverse(VAR, &net_namespace_list, list) #define for_each_net_rcu(VAR) \ list_for_each_entry_rcu(VAR, &net_namespace_list, list) diff --git a/net/core/dev.c b/net/core/dev.c index 7a456c6a7ad8..a8b70cb6c732 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1725,6 +1725,62 @@ static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val, return nb->notifier_call(nb, val, &info); } +static int call_netdevice_register_notifiers(struct notifier_block *nb, + struct net_device *dev) +{ + int err; + + err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev); + err = notifier_to_errno(err); + if (err) + return err; + + if (!(dev->flags & IFF_UP)) + return 0; + + call_netdevice_notifier(nb, NETDEV_UP, dev); + return 0; +} + +static void call_netdevice_unregister_notifiers(struct notifier_block *nb, + struct net_device *dev) +{ + if (dev->flags & IFF_UP) { + call_netdevice_notifier(nb, NETDEV_GOING_DOWN, + dev); + call_netdevice_notifier(nb, NETDEV_DOWN, dev); + } + call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev); +} + +static int call_netdevice_register_net_notifiers(struct notifier_block *nb, + struct net *net) +{ + struct net_device *dev; + int err; + + for_each_netdev(net, dev) { + err = call_netdevice_register_notifiers(nb, dev); + if (err) + goto rollback; + } + return 0; + +rollback: + for_each_netdev_continue_reverse(net, dev) + call_netdevice_unregister_notifiers(nb, dev); + return err; +} + +static void call_netdevice_unregister_net_notifiers(struct notifier_block *nb, + struct net *net) +{ + struct net_device *dev; + + for_each_netdev(net, dev) + call_netdevice_unregister_notifiers(nb, dev); +} + static int dev_boot_phase = 1; /** @@ -1743,8 +1799,6 @@ static int dev_boot_phase = 1; int register_netdevice_notifier(struct notifier_block *nb) { - struct net_device *dev; - struct net_device *last; struct net *net; int err; @@ -1757,17 +1811,9 @@ int register_netdevice_notifier(struct notifier_block *nb) if (dev_boot_phase) goto unlock; for_each_net(net) { - for_each_netdev(net, dev) { - err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev); - err = notifier_to_errno(err); - if (err) - goto rollback; - - if (!(dev->flags & IFF_UP)) - continue; - - call_netdevice_notifier(nb, NETDEV_UP, dev); - } + err = call_netdevice_register_net_notifiers(nb, net); + if (err) + goto rollback; } unlock: @@ -1776,22 +1822,9 @@ unlock: return err; rollback: - last = dev; - for_each_net(net) { - for_each_netdev(net, dev) { - if (dev == last) - goto outroll; - - if (dev->flags & IFF_UP) { - call_netdevice_notifier(nb, NETDEV_GOING_DOWN, - dev); - call_netdevice_notifier(nb, NETDEV_DOWN, dev); - } - call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev); - } - } + for_each_net_continue_reverse(net) + call_netdevice_unregister_net_notifiers(nb, net); -outroll: raw_notifier_chain_unregister(&netdev_chain, nb); goto unlock; } -- cgit v1.2.3-71-gd317 From a30c7b429f2dd980202c912fcb76442364937b4d Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 30 Sep 2019 10:15:10 +0200 Subject: net: introduce per-netns netdevice notifiers Often the code for example in drivers is interested in getting notifier call only from certain network namespace. In addition to the existing global netdevice notifier chain introduce per-netns chains and allow users to register to that. Eventually this would eliminate unnecessary overhead in case there are many netdevices in many network namespaces. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 ++ include/net/net_namespace.h | 3 ++ net/core/dev.c | 87 +++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 93 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7b183f724fc4..fe45b2c72315 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2504,6 +2504,9 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd); int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); +int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb); +int unregister_netdevice_notifier_net(struct net *net, + struct notifier_block *nb); struct netdev_notifier_info { struct net_device *dev; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index c5a98e03591d..5ac2bb16d4b3 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -36,6 +36,7 @@ #include #include #include +#include struct user_namespace; struct proc_dir_entry; @@ -96,6 +97,8 @@ struct net { struct list_head dev_base_head; struct hlist_head *dev_name_head; struct hlist_head *dev_index_head; + struct raw_notifier_head netdev_chain; + unsigned int dev_base_seq; /* protected by rtnl_mutex */ int ifindex; unsigned int dev_unreg_count; diff --git a/net/core/dev.c b/net/core/dev.c index a8b70cb6c732..c680225e0da8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1874,6 +1874,80 @@ unlock: } EXPORT_SYMBOL(unregister_netdevice_notifier); +/** + * register_netdevice_notifier_net - register a per-netns network notifier block + * @net: network namespace + * @nb: notifier + * + * Register a notifier to be called when network device events occur. + * The notifier passed is linked into the kernel structures and must + * not be reused until it has been unregistered. A negative errno code + * is returned on a failure. + * + * When registered all registration and up events are replayed + * to the new notifier to allow device to have a race free + * view of the network device list. + */ + +int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb) +{ + int err; + + rtnl_lock(); + err = raw_notifier_chain_register(&net->netdev_chain, nb); + if (err) + goto unlock; + if (dev_boot_phase) + goto unlock; + + err = call_netdevice_register_net_notifiers(nb, net); + if (err) + goto chain_unregister; + +unlock: + rtnl_unlock(); + return err; + +chain_unregister: + raw_notifier_chain_unregister(&netdev_chain, nb); + goto unlock; +} +EXPORT_SYMBOL(register_netdevice_notifier_net); + +/** + * unregister_netdevice_notifier_net - unregister a per-netns + * network notifier block + * @net: network namespace + * @nb: notifier + * + * Unregister a notifier previously registered by + * register_netdevice_notifier(). The notifier is unlinked into the + * kernel structures and may then be reused. A negative errno code + * is returned on a failure. + * + * After unregistering unregister and down device events are synthesized + * for all devices on the device list to the removed notifier to remove + * the need for special case cleanup code. + */ + +int unregister_netdevice_notifier_net(struct net *net, + struct notifier_block *nb) +{ + int err; + + rtnl_lock(); + err = raw_notifier_chain_unregister(&net->netdev_chain, nb); + if (err) + goto unlock; + + call_netdevice_unregister_net_notifiers(nb, net); + +unlock: + rtnl_unlock(); + return err; +} +EXPORT_SYMBOL(unregister_netdevice_notifier_net); + /** * call_netdevice_notifiers_info - call all network notifier blocks * @val: value passed unmodified to notifier function @@ -1886,7 +1960,18 @@ EXPORT_SYMBOL(unregister_netdevice_notifier); static int call_netdevice_notifiers_info(unsigned long val, struct netdev_notifier_info *info) { + struct net *net = dev_net(info->dev); + int ret; + ASSERT_RTNL(); + + /* Run per-netns notifier block chain first, then run the global one. + * Hopefully, one day, the global one is going to be removed after + * all notifier block registrators get converted to be per-netns. + */ + ret = raw_notifier_call_chain(&net->netdev_chain, val, info); + if (ret & NOTIFY_STOP_MASK) + return ret; return raw_notifier_call_chain(&netdev_chain, val, info); } @@ -9785,6 +9870,8 @@ static int __net_init netdev_init(struct net *net) if (net->dev_index_head == NULL) goto err_idx; + RAW_INIT_NOTIFIER_HEAD(&net->netdev_chain); + return 0; err_idx: -- cgit v1.2.3-71-gd317 From 2d2f116d69c127099553afe0d87cf9c0bbe2759e Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Thu, 12 Sep 2019 20:22:38 -0700 Subject: gpiolib: introduce devm_fwnode_gpiod_get_index() devm_fwnode_get_index_gpiod_from_child() is too long, besides the fwnode in question does not have to be a child of device node. Let's rename it to devm_fwnode_gpiod_get_index() and keep the old name for compatibility for now. Also let's add a devm_fwnode_gpiod_get() wrapper as majority of the callers need a single GPIO. Reviewed-by: Andy Shevchenko Signed-off-by: Dmitry Torokhov Reviewed-by: Mika Westerberg Link: https://lore.kernel.org/r/20190913032240.50333-2-dmitry.torokhov@gmail.com Signed-off-by: Linus Walleij --- drivers/gpio/gpiolib-devres.c | 19 +++++++++---------- include/linux/gpio/consumer.h | 41 +++++++++++++++++++++++++++++++---------- 2 files changed, 40 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpio/gpiolib-devres.c b/drivers/gpio/gpiolib-devres.c index 98e3c20d9730..9a0475c87f95 100644 --- a/drivers/gpio/gpiolib-devres.c +++ b/drivers/gpio/gpiolib-devres.c @@ -185,12 +185,11 @@ struct gpio_desc *devm_gpiod_get_from_of_node(struct device *dev, EXPORT_SYMBOL_GPL(devm_gpiod_get_from_of_node); /** - * devm_fwnode_get_index_gpiod_from_child - get a GPIO descriptor from a - * device's child node + * devm_fwnode_gpiod_get_index - get a GPIO descriptor from a given node * @dev: GPIO consumer + * @fwnode: firmware node containing GPIO reference * @con_id: function within the GPIO consumer * @index: index of the GPIO to obtain in the consumer - * @child: firmware node (child of @dev) * @flags: GPIO initialization flags * @label: label to attach to the requested GPIO * @@ -200,11 +199,11 @@ EXPORT_SYMBOL_GPL(devm_gpiod_get_from_of_node); * On successful request the GPIO pin is configured in accordance with * provided @flags. */ -struct gpio_desc *devm_fwnode_get_index_gpiod_from_child(struct device *dev, - const char *con_id, int index, - struct fwnode_handle *child, - enum gpiod_flags flags, - const char *label) +struct gpio_desc *devm_fwnode_gpiod_get_index(struct device *dev, + struct fwnode_handle *fwnode, + const char *con_id, int index, + enum gpiod_flags flags, + const char *label) { char prop_name[32]; /* 32 is max size of property name */ struct gpio_desc **dr; @@ -224,7 +223,7 @@ struct gpio_desc *devm_fwnode_get_index_gpiod_from_child(struct device *dev, snprintf(prop_name, sizeof(prop_name), "%s", gpio_suffixes[i]); - desc = fwnode_get_named_gpiod(child, prop_name, index, flags, + desc = fwnode_get_named_gpiod(fwnode, prop_name, index, flags, label); if (!IS_ERR(desc) || (PTR_ERR(desc) != -ENOENT)) break; @@ -239,7 +238,7 @@ struct gpio_desc *devm_fwnode_get_index_gpiod_from_child(struct device *dev, return desc; } -EXPORT_SYMBOL_GPL(devm_fwnode_get_index_gpiod_from_child); +EXPORT_SYMBOL_GPL(devm_fwnode_gpiod_get_index); /** * devm_gpiod_get_index_optional - Resource-managed gpiod_get_index_optional() diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index b70af921c614..dc0ddcd30515 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -176,11 +176,11 @@ struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode, const char *propname, int index, enum gpiod_flags dflags, const char *label); -struct gpio_desc *devm_fwnode_get_index_gpiod_from_child(struct device *dev, - const char *con_id, int index, - struct fwnode_handle *child, - enum gpiod_flags flags, - const char *label); +struct gpio_desc *devm_fwnode_gpiod_get_index(struct device *dev, + struct fwnode_handle *child, + const char *con_id, int index, + enum gpiod_flags flags, + const char *label); #else /* CONFIG_GPIOLIB */ @@ -531,6 +531,29 @@ struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode, return ERR_PTR(-ENOSYS); } +static inline +struct gpio_desc *devm_fwnode_gpiod_get_index(struct device *dev, + struct fwnode_handle *fwnode, + const char *con_id, int index, + enum gpiod_flags flags, + const char *label) +{ + return ERR_PTR(-ENOSYS); +} + +#endif /* CONFIG_GPIOLIB */ + +static inline +struct gpio_desc *devm_fwnode_gpiod_get(struct device *dev, + struct fwnode_handle *fwnode, + const char *con_id, + enum gpiod_flags flags, + const char *label) +{ + return devm_fwnode_gpiod_get_index(dev, fwnode, con_id, 0, + flags, label); +} + static inline struct gpio_desc *devm_fwnode_get_index_gpiod_from_child(struct device *dev, const char *con_id, int index, @@ -538,11 +561,10 @@ struct gpio_desc *devm_fwnode_get_index_gpiod_from_child(struct device *dev, enum gpiod_flags flags, const char *label) { - return ERR_PTR(-ENOSYS); + return devm_fwnode_gpiod_get_index(dev, child, con_id, index, + flags, label); } -#endif /* CONFIG_GPIOLIB */ - static inline struct gpio_desc *devm_fwnode_get_gpiod_from_child(struct device *dev, const char *con_id, @@ -550,8 +572,7 @@ struct gpio_desc *devm_fwnode_get_gpiod_from_child(struct device *dev, enum gpiod_flags flags, const char *label) { - return devm_fwnode_get_index_gpiod_from_child(dev, con_id, 0, child, - flags, label); + return devm_fwnode_gpiod_get_index(dev, child, con_id, 0, flags, label); } #if IS_ENABLED(CONFIG_GPIOLIB) && IS_ENABLED(CONFIG_OF_GPIO) -- cgit v1.2.3-71-gd317 From 13949fa9daa91a60c7cfef40755f7611cc2cf653 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Thu, 12 Sep 2019 20:22:39 -0700 Subject: gpiolib: introduce fwnode_gpiod_get_index() This introduces fwnode_gpiod_get_index() that iterates through common gpio suffixes when trying to locate a GPIO within a given firmware node. We also switch devm_fwnode_gpiod_get_index() to call fwnode_gpiod_get_index() instead of iterating through GPIO suffixes on its own. Reviewed-by: Andy Shevchenko Signed-off-by: Dmitry Torokhov Link: https://lore.kernel.org/r/20190913032240.50333-3-dmitry.torokhov@gmail.com Reviewed-by: Mika Westerberg Signed-off-by: Linus Walleij --- drivers/gpio/gpiolib-devres.c | 16 +-------------- drivers/gpio/gpiolib.c | 48 +++++++++++++++++++++++++++++++++++++++++++ include/linux/gpio/consumer.h | 13 ++++++++++++ 3 files changed, 62 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpio/gpiolib-devres.c b/drivers/gpio/gpiolib-devres.c index 9a0475c87f95..4421be09b960 100644 --- a/drivers/gpio/gpiolib-devres.c +++ b/drivers/gpio/gpiolib-devres.c @@ -205,29 +205,15 @@ struct gpio_desc *devm_fwnode_gpiod_get_index(struct device *dev, enum gpiod_flags flags, const char *label) { - char prop_name[32]; /* 32 is max size of property name */ struct gpio_desc **dr; struct gpio_desc *desc; - unsigned int i; dr = devres_alloc(devm_gpiod_release, sizeof(struct gpio_desc *), GFP_KERNEL); if (!dr) return ERR_PTR(-ENOMEM); - for (i = 0; i < ARRAY_SIZE(gpio_suffixes); i++) { - if (con_id) - snprintf(prop_name, sizeof(prop_name), "%s-%s", - con_id, gpio_suffixes[i]); - else - snprintf(prop_name, sizeof(prop_name), "%s", - gpio_suffixes[i]); - - desc = fwnode_get_named_gpiod(fwnode, prop_name, index, flags, - label); - if (!IS_ERR(desc) || (PTR_ERR(desc) != -ENOENT)) - break; - } + desc = fwnode_gpiod_get_index(fwnode, con_id, index, flags, label); if (IS_ERR(desc)) { devres_free(dr); return desc; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index bdbc1649eafa..2342deaace17 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -4324,6 +4324,54 @@ static int platform_gpio_count(struct device *dev, const char *con_id) return count; } +/** + * fwnode_gpiod_get_index - obtain a GPIO from firmware node + * @fwnode: handle of the firmware node + * @con_id: function within the GPIO consumer + * @index: index of the GPIO to obtain for the consumer + * @flags: GPIO initialization flags + * @label: label to attach to the requested GPIO + * + * This function can be used for drivers that get their configuration + * from opaque firmware. + * + * The function properly finds the corresponding GPIO using whatever is the + * underlying firmware interface and then makes sure that the GPIO + * descriptor is requested before it is returned to the caller. + * + * Returns: + * On successful request the GPIO pin is configured in accordance with + * provided @flags. + * + * In case of error an ERR_PTR() is returned. + */ +struct gpio_desc *fwnode_gpiod_get_index(struct fwnode_handle *fwnode, + const char *con_id, int index, + enum gpiod_flags flags, + const char *label) +{ + struct gpio_desc *desc; + char prop_name[32]; /* 32 is max size of property name */ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(gpio_suffixes); i++) { + if (con_id) + snprintf(prop_name, sizeof(prop_name), "%s-%s", + con_id, gpio_suffixes[i]); + else + snprintf(prop_name, sizeof(prop_name), "%s", + gpio_suffixes[i]); + + desc = fwnode_get_named_gpiod(fwnode, prop_name, index, flags, + label); + if (!IS_ERR(desc) || (PTR_ERR(desc) != -ENOENT)) + break; + } + + return desc; +} +EXPORT_SYMBOL_GPL(fwnode_gpiod_get_index); + /** * gpiod_count - return the number of GPIOs associated with a device / function * or -ENOENT if no GPIO has been assigned to the requested function diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index dc0ddcd30515..5215fdba6b9a 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -176,6 +176,10 @@ struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode, const char *propname, int index, enum gpiod_flags dflags, const char *label); +struct gpio_desc *fwnode_gpiod_get_index(struct fwnode_handle *fwnode, + const char *con_id, int index, + enum gpiod_flags flags, + const char *label); struct gpio_desc *devm_fwnode_gpiod_get_index(struct device *dev, struct fwnode_handle *child, const char *con_id, int index, @@ -531,6 +535,15 @@ struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode, return ERR_PTR(-ENOSYS); } +static inline +struct gpio_desc *fwnode_gpiod_get_index(struct fwnode_handle *fwnode, + const char *con_id, int index, + enum gpiod_flags flags, + const char *label) +{ + return ERR_PTR(-ENOSYS); +} + static inline struct gpio_desc *devm_fwnode_gpiod_get_index(struct device *dev, struct fwnode_handle *fwnode, -- cgit v1.2.3-71-gd317 From 8cde3c2153e8f57be884c0e73f18bc4de150e870 Mon Sep 17 00:00:00 2001 From: Carlo Caione Date: Wed, 31 Jul 2019 09:23:39 +0100 Subject: firmware: meson_sm: Rework driver as a proper platform driver The secure monitor driver is currently a frankenstein driver which is registered as a platform driver but its functionality goes through a global struct accessed by the consumer drivers using exported helper functions. Try to tidy up the driver moving the firmware struct into the driver data and make the consumer drivers referencing the secure-monitor using a new property in the DT. Currently only the nvmem driver is using this API so we can fix it in the same commit. Reviewed-by: Jerome Brunet Signed-off-by: Carlo Caione Signed-off-by: Kevin Hilman --- drivers/firmware/meson/meson_sm.c | 94 ++++++++++++++++++++++----------- drivers/nvmem/meson-efuse.c | 24 +++++++-- include/linux/firmware/meson/meson_sm.h | 15 +++--- 3 files changed, 94 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/meson/meson_sm.c b/drivers/firmware/meson/meson_sm.c index 772ca6726e7b..2e36a2aa274c 100644 --- a/drivers/firmware/meson/meson_sm.c +++ b/drivers/firmware/meson/meson_sm.c @@ -54,8 +54,6 @@ struct meson_sm_firmware { void __iomem *sm_shmem_out_base; }; -static struct meson_sm_firmware fw; - static u32 meson_sm_get_cmd(const struct meson_sm_chip *chip, unsigned int cmd_index) { @@ -90,6 +88,7 @@ static void __iomem *meson_sm_map_shmem(u32 cmd_shmem, unsigned int size) /** * meson_sm_call - generic SMC32 call to the secure-monitor * + * @fw: Pointer to secure-monitor firmware * @cmd_index: Index of the SMC32 function ID * @ret: Returned value * @arg0: SMC32 Argument 0 @@ -100,15 +99,15 @@ static void __iomem *meson_sm_map_shmem(u32 cmd_shmem, unsigned int size) * * Return: 0 on success, a negative value on error */ -int meson_sm_call(unsigned int cmd_index, u32 *ret, u32 arg0, - u32 arg1, u32 arg2, u32 arg3, u32 arg4) +int meson_sm_call(struct meson_sm_firmware *fw, unsigned int cmd_index, + u32 *ret, u32 arg0, u32 arg1, u32 arg2, u32 arg3, u32 arg4) { u32 cmd, lret; - if (!fw.chip) + if (!fw->chip) return -ENOENT; - cmd = meson_sm_get_cmd(fw.chip, cmd_index); + cmd = meson_sm_get_cmd(fw->chip, cmd_index); if (!cmd) return -EINVAL; @@ -124,6 +123,7 @@ EXPORT_SYMBOL(meson_sm_call); /** * meson_sm_call_read - retrieve data from secure-monitor * + * @fw: Pointer to secure-monitor firmware * @buffer: Buffer to store the retrieved data * @bsize: Size of the buffer * @cmd_index: Index of the SMC32 function ID @@ -137,22 +137,23 @@ EXPORT_SYMBOL(meson_sm_call); * When 0 is returned there is no guarantee about the amount of * data read and bsize bytes are copied in buffer. */ -int meson_sm_call_read(void *buffer, unsigned int bsize, unsigned int cmd_index, - u32 arg0, u32 arg1, u32 arg2, u32 arg3, u32 arg4) +int meson_sm_call_read(struct meson_sm_firmware *fw, void *buffer, + unsigned int bsize, unsigned int cmd_index, u32 arg0, + u32 arg1, u32 arg2, u32 arg3, u32 arg4) { u32 size; int ret; - if (!fw.chip) + if (!fw->chip) return -ENOENT; - if (!fw.chip->cmd_shmem_out_base) + if (!fw->chip->cmd_shmem_out_base) return -EINVAL; - if (bsize > fw.chip->shmem_size) + if (bsize > fw->chip->shmem_size) return -EINVAL; - if (meson_sm_call(cmd_index, &size, arg0, arg1, arg2, arg3, arg4) < 0) + if (meson_sm_call(fw, cmd_index, &size, arg0, arg1, arg2, arg3, arg4) < 0) return -EINVAL; if (size > bsize) @@ -164,7 +165,7 @@ int meson_sm_call_read(void *buffer, unsigned int bsize, unsigned int cmd_index, size = bsize; if (buffer) - memcpy(buffer, fw.sm_shmem_out_base, size); + memcpy(buffer, fw->sm_shmem_out_base, size); return ret; } @@ -173,6 +174,7 @@ EXPORT_SYMBOL(meson_sm_call_read); /** * meson_sm_call_write - send data to secure-monitor * + * @fw: Pointer to secure-monitor firmware * @buffer: Buffer containing data to send * @size: Size of the data to send * @cmd_index: Index of the SMC32 function ID @@ -184,23 +186,24 @@ EXPORT_SYMBOL(meson_sm_call_read); * * Return: size of sent data on success, a negative value on error */ -int meson_sm_call_write(void *buffer, unsigned int size, unsigned int cmd_index, - u32 arg0, u32 arg1, u32 arg2, u32 arg3, u32 arg4) +int meson_sm_call_write(struct meson_sm_firmware *fw, void *buffer, + unsigned int size, unsigned int cmd_index, u32 arg0, + u32 arg1, u32 arg2, u32 arg3, u32 arg4) { u32 written; - if (!fw.chip) + if (!fw->chip) return -ENOENT; - if (size > fw.chip->shmem_size) + if (size > fw->chip->shmem_size) return -EINVAL; - if (!fw.chip->cmd_shmem_in_base) + if (!fw->chip->cmd_shmem_in_base) return -EINVAL; - memcpy(fw.sm_shmem_in_base, buffer, size); + memcpy(fw->sm_shmem_in_base, buffer, size); - if (meson_sm_call(cmd_index, &written, arg0, arg1, arg2, arg3, arg4) < 0) + if (meson_sm_call(fw, cmd_index, &written, arg0, arg1, arg2, arg3, arg4) < 0) return -EINVAL; if (!written) @@ -210,6 +213,24 @@ int meson_sm_call_write(void *buffer, unsigned int size, unsigned int cmd_index, } EXPORT_SYMBOL(meson_sm_call_write); +/** + * meson_sm_get - get pointer to meson_sm_firmware structure. + * + * @sm_node: Pointer to the secure-monitor Device Tree node. + * + * Return: NULL is the secure-monitor device is not ready. + */ +struct meson_sm_firmware *meson_sm_get(struct device_node *sm_node) +{ + struct platform_device *pdev = of_find_device_by_node(sm_node); + + if (!pdev) + return NULL; + + return platform_get_drvdata(pdev); +} +EXPORT_SYMBOL_GPL(meson_sm_get); + #define SM_CHIP_ID_LENGTH 119 #define SM_CHIP_ID_OFFSET 4 #define SM_CHIP_ID_SIZE 12 @@ -217,14 +238,18 @@ EXPORT_SYMBOL(meson_sm_call_write); static ssize_t serial_show(struct device *dev, struct device_attribute *attr, char *buf) { + struct platform_device *pdev = to_platform_device(dev); + struct meson_sm_firmware *fw; uint8_t *id_buf; int ret; + fw = platform_get_drvdata(pdev); + id_buf = kmalloc(SM_CHIP_ID_LENGTH, GFP_KERNEL); if (!id_buf) return -ENOMEM; - ret = meson_sm_call_read(id_buf, SM_CHIP_ID_LENGTH, SM_GET_CHIP_ID, + ret = meson_sm_call_read(fw, id_buf, SM_CHIP_ID_LENGTH, SM_GET_CHIP_ID, 0, 0, 0, 0, 0); if (ret < 0) { kfree(id_buf); @@ -268,25 +293,34 @@ static const struct of_device_id meson_sm_ids[] = { static int __init meson_sm_probe(struct platform_device *pdev) { + struct device *dev = &pdev->dev; const struct meson_sm_chip *chip; + struct meson_sm_firmware *fw; + + fw = devm_kzalloc(dev, sizeof(*fw), GFP_KERNEL); + if (!fw) + return -ENOMEM; - chip = of_match_device(meson_sm_ids, &pdev->dev)->data; + chip = of_match_device(meson_sm_ids, dev)->data; if (chip->cmd_shmem_in_base) { - fw.sm_shmem_in_base = meson_sm_map_shmem(chip->cmd_shmem_in_base, - chip->shmem_size); - if (WARN_ON(!fw.sm_shmem_in_base)) + fw->sm_shmem_in_base = meson_sm_map_shmem(chip->cmd_shmem_in_base, + chip->shmem_size); + if (WARN_ON(!fw->sm_shmem_in_base)) goto out; } if (chip->cmd_shmem_out_base) { - fw.sm_shmem_out_base = meson_sm_map_shmem(chip->cmd_shmem_out_base, - chip->shmem_size); - if (WARN_ON(!fw.sm_shmem_out_base)) + fw->sm_shmem_out_base = meson_sm_map_shmem(chip->cmd_shmem_out_base, + chip->shmem_size); + if (WARN_ON(!fw->sm_shmem_out_base)) goto out_in_base; } - fw.chip = chip; + fw->chip = chip; + + platform_set_drvdata(pdev, fw); + pr_info("secure-monitor enabled\n"); if (sysfs_create_group(&pdev->dev.kobj, &meson_sm_sysfs_attr_group)) @@ -295,7 +329,7 @@ static int __init meson_sm_probe(struct platform_device *pdev) return 0; out_in_base: - iounmap(fw.sm_shmem_in_base); + iounmap(fw->sm_shmem_in_base); out: return -EINVAL; } diff --git a/drivers/nvmem/meson-efuse.c b/drivers/nvmem/meson-efuse.c index 39bd76306033..d6b533497ce1 100644 --- a/drivers/nvmem/meson-efuse.c +++ b/drivers/nvmem/meson-efuse.c @@ -17,14 +17,18 @@ static int meson_efuse_read(void *context, unsigned int offset, void *val, size_t bytes) { - return meson_sm_call_read((u8 *)val, bytes, SM_EFUSE_READ, offset, + struct meson_sm_firmware *fw = context; + + return meson_sm_call_read(fw, (u8 *)val, bytes, SM_EFUSE_READ, offset, bytes, 0, 0, 0); } static int meson_efuse_write(void *context, unsigned int offset, void *val, size_t bytes) { - return meson_sm_call_write((u8 *)val, bytes, SM_EFUSE_WRITE, offset, + struct meson_sm_firmware *fw = context; + + return meson_sm_call_write(fw, (u8 *)val, bytes, SM_EFUSE_WRITE, offset, bytes, 0, 0, 0); } @@ -37,12 +41,25 @@ MODULE_DEVICE_TABLE(of, meson_efuse_match); static int meson_efuse_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; + struct meson_sm_firmware *fw; + struct device_node *sm_np; struct nvmem_device *nvmem; struct nvmem_config *econfig; struct clk *clk; unsigned int size; int ret; + sm_np = of_parse_phandle(pdev->dev.of_node, "secure-monitor", 0); + if (!sm_np) { + dev_err(&pdev->dev, "no secure-monitor node\n"); + return -ENODEV; + } + + fw = meson_sm_get(sm_np); + of_node_put(sm_np); + if (!fw) + return -EPROBE_DEFER; + clk = devm_clk_get(dev, NULL); if (IS_ERR(clk)) { ret = PTR_ERR(clk); @@ -65,7 +82,7 @@ static int meson_efuse_probe(struct platform_device *pdev) return ret; } - if (meson_sm_call(SM_EFUSE_USER_MAX, &size, 0, 0, 0, 0, 0) < 0) { + if (meson_sm_call(fw, SM_EFUSE_USER_MAX, &size, 0, 0, 0, 0, 0) < 0) { dev_err(dev, "failed to get max user"); return -EINVAL; } @@ -81,6 +98,7 @@ static int meson_efuse_probe(struct platform_device *pdev) econfig->reg_read = meson_efuse_read; econfig->reg_write = meson_efuse_write; econfig->size = size; + econfig->priv = fw; nvmem = devm_nvmem_register(&pdev->dev, econfig); diff --git a/include/linux/firmware/meson/meson_sm.h b/include/linux/firmware/meson/meson_sm.h index 7613bf7c9442..6669e2a1d5fd 100644 --- a/include/linux/firmware/meson/meson_sm.h +++ b/include/linux/firmware/meson/meson_sm.h @@ -16,11 +16,14 @@ enum { struct meson_sm_firmware; -int meson_sm_call(unsigned int cmd_index, u32 *ret, u32 arg0, u32 arg1, - u32 arg2, u32 arg3, u32 arg4); -int meson_sm_call_write(void *buffer, unsigned int b_size, unsigned int cmd_index, - u32 arg0, u32 arg1, u32 arg2, u32 arg3, u32 arg4); -int meson_sm_call_read(void *buffer, unsigned int bsize, unsigned int cmd_index, - u32 arg0, u32 arg1, u32 arg2, u32 arg3, u32 arg4); +int meson_sm_call(struct meson_sm_firmware *fw, unsigned int cmd_index, + u32 *ret, u32 arg0, u32 arg1, u32 arg2, u32 arg3, u32 arg4); +int meson_sm_call_write(struct meson_sm_firmware *fw, void *buffer, + unsigned int b_size, unsigned int cmd_index, u32 arg0, + u32 arg1, u32 arg2, u32 arg3, u32 arg4); +int meson_sm_call_read(struct meson_sm_firmware *fw, void *buffer, + unsigned int bsize, unsigned int cmd_index, u32 arg0, + u32 arg1, u32 arg2, u32 arg3, u32 arg4); +struct meson_sm_firmware *meson_sm_get(struct device_node *firmware_node); #endif /* _MESON_SM_FW_H_ */ -- cgit v1.2.3-71-gd317 From 245d73698ed7abdc7e520dfa38048bb80ce89571 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 2 Oct 2019 16:41:58 -0700 Subject: audit: Report suspicious O_CREAT usage This renames the very specific audit_log_link_denied() to audit_log_path_denied() and adds the AUDIT_* type as an argument. This allows for the creation of the new AUDIT_ANOM_CREAT that can be used to report the fifo/regular file creation restrictions that were introduced in commit 30aba6656f61 ("namei: allow restricted O_CREAT of FIFOs and regular files"). Signed-off-by: Kees Cook Signed-off-by: Paul Moore --- fs/namei.c | 8 ++++++-- include/linux/audit.h | 5 +++-- include/uapi/linux/audit.h | 1 + kernel/audit.c | 11 ++++++----- 4 files changed, 16 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/fs/namei.c b/fs/namei.c index 671c3c1a3425..2dda552bcf7a 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -925,7 +925,7 @@ static inline int may_follow_link(struct nameidata *nd) return -ECHILD; audit_inode(nd->name, nd->stack[0].link.dentry, 0); - audit_log_link_denied("follow_link"); + audit_log_path_denied(AUDIT_ANOM_LINK, "follow_link"); return -EACCES; } @@ -993,7 +993,7 @@ static int may_linkat(struct path *link) if (safe_hardlink_source(inode) || inode_owner_or_capable(inode)) return 0; - audit_log_link_denied("linkat"); + audit_log_path_denied(AUDIT_ANOM_LINK, "linkat"); return -EPERM; } @@ -1031,6 +1031,10 @@ static int may_create_in_sticky(struct dentry * const dir, (dir->d_inode->i_mode & 0020 && ((sysctl_protected_fifos >= 2 && S_ISFIFO(inode->i_mode)) || (sysctl_protected_regular >= 2 && S_ISREG(inode->i_mode))))) { + const char *operation = S_ISFIFO(inode->i_mode) ? + "sticky_create_fifo" : + "sticky_create_regular"; + audit_log_path_denied(AUDIT_ANOM_CREAT, operation); return -EACCES; } return 0; diff --git a/include/linux/audit.h b/include/linux/audit.h index aee3dc9eb378..f9ceae57ca8d 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -156,7 +156,8 @@ extern void audit_log_d_path(struct audit_buffer *ab, const struct path *path); extern void audit_log_key(struct audit_buffer *ab, char *key); -extern void audit_log_link_denied(const char *operation); +extern void audit_log_path_denied(int type, + const char *operation); extern void audit_log_lost(const char *message); extern int audit_log_task_context(struct audit_buffer *ab); @@ -217,7 +218,7 @@ static inline void audit_log_d_path(struct audit_buffer *ab, { } static inline void audit_log_key(struct audit_buffer *ab, char *key) { } -static inline void audit_log_link_denied(const char *string) +static inline void audit_log_path_denied(int type, const char *operation) { } static inline int audit_log_task_context(struct audit_buffer *ab) { diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index c89c6495983d..3ad935527177 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -143,6 +143,7 @@ #define AUDIT_ANOM_PROMISCUOUS 1700 /* Device changed promiscuous mode */ #define AUDIT_ANOM_ABEND 1701 /* Process ended abnormally */ #define AUDIT_ANOM_LINK 1702 /* Suspicious use of file links */ +#define AUDIT_ANOM_CREAT 1703 /* Suspicious file creation */ #define AUDIT_INTEGRITY_DATA 1800 /* Data integrity verification */ #define AUDIT_INTEGRITY_METADATA 1801 /* Metadata integrity verification */ #define AUDIT_INTEGRITY_STATUS 1802 /* Integrity enable status */ diff --git a/kernel/audit.c b/kernel/audit.c index da8dc0db5bd3..d75485aa25ff 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -2155,18 +2155,19 @@ void audit_log_task_info(struct audit_buffer *ab) EXPORT_SYMBOL(audit_log_task_info); /** - * audit_log_link_denied - report a link restriction denial - * @operation: specific link operation + * audit_log_path_denied - report a path restriction denial + * @type: audit message type (AUDIT_ANOM_LINK, AUDIT_ANOM_CREAT, etc) + * @operation: specific operation name */ -void audit_log_link_denied(const char *operation) +void audit_log_path_denied(int type, const char *operation) { struct audit_buffer *ab; if (!audit_enabled || audit_dummy_context()) return; - /* Generate AUDIT_ANOM_LINK with subject, operation, outcome. */ - ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_ANOM_LINK); + /* Generate log with subject, operation, outcome. */ + ab = audit_log_start(audit_context(), GFP_KERNEL, type); if (!ab) return; audit_log_format(ab, "op=%s", operation); -- cgit v1.2.3-71-gd317 From 968a2978cb39a754750d35a47049781660682a31 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Wed, 2 Oct 2019 16:52:57 +0200 Subject: net: stmmac: Only enable enhanced addressing mode when needed Enhanced addressing mode is only required when more than 32 bits need to be addressed. Add a DMA configuration parameter to enable this mode only when needed. Signed-off-by: Thierry Reding Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c | 5 ++++- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 7 +++++++ include/linux/stmmac.h | 1 + 3 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c index 53c4a40d8386..19ef037393dd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c @@ -27,7 +27,10 @@ static void dwxgmac2_dma_init(void __iomem *ioaddr, if (dma_cfg->aal) value |= XGMAC_AAL; - writel(value | XGMAC_EAME, ioaddr + XGMAC_DMA_SYSBUS_MODE); + if (dma_cfg->eame) + value |= XGMAC_EAME; + + writel(value, ioaddr + XGMAC_DMA_SYSBUS_MODE); } static void dwxgmac2_dma_init_chan(void __iomem *ioaddr, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index d3232738fb25..2da1f77bb604 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4514,6 +4514,13 @@ int stmmac_dvr_probe(struct device *device, if (!ret) { dev_info(priv->device, "Using %d bits DMA width\n", priv->dma_cap.addr64); + + /* + * If more than 32 bits can be addressed, make sure to + * enable enhanced addressing mode. + */ + if (IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT)) + priv->plat->dma_cfg->eame = true; } else { ret = dma_set_mask_and_coherent(device, DMA_BIT_MASK(32)); if (ret) { diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index dc60d03c4b60..86f9464c3f5d 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -92,6 +92,7 @@ struct stmmac_dma_cfg { int fixed_burst; int mixed_burst; bool aal; + bool eame; }; #define AXI_BLEN 7 -- cgit v1.2.3-71-gd317 From 372a67c0c5ef63f55bd1eb480d9555328d8ec0f2 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Wed, 4 Sep 2019 14:11:20 -0700 Subject: driver core: Add fwnode_to_dev() to look up device from fwnode It's often useful to look up a device that corresponds to a fwnode. So add an API to do that irrespective of the bus on which the device has been added to. Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20190904211126.47518-2-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 7 +++++++ include/linux/fwnode.h | 2 ++ 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index 2db62d98e395..510fabf8918c 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2198,6 +2198,10 @@ int device_add(struct device *dev) BUS_NOTIFY_ADD_DEVICE, dev); kobject_uevent(&dev->kobj, KOBJ_ADD); + + if (dev->fwnode && !dev->fwnode->dev) + dev->fwnode->dev = dev; + bus_probe_device(dev); if (parent) klist_add_tail(&dev->p->knode_parent, @@ -2342,6 +2346,9 @@ void device_del(struct device *dev) kill_device(dev); device_unlock(dev); + if (dev->fwnode && dev->fwnode->dev == dev) + dev->fwnode->dev = NULL; + /* Notify clients of device removal. This call must come * before dpm_sysfs_remove(). */ diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index ababd6bc82f3..d8c6d231d577 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -17,6 +17,7 @@ struct device; struct fwnode_handle { struct fwnode_handle *secondary; const struct fwnode_operations *ops; + struct device *dev; }; /** @@ -123,5 +124,6 @@ struct fwnode_operations { if (fwnode_has_op(fwnode, op)) \ (fwnode)->ops->op(fwnode, ## __VA_ARGS__); \ } while (false) +#define get_dev_from_fwnode(fwnode) get_device((fwnode)->dev) #endif -- cgit v1.2.3-71-gd317 From e2ae9bcc4aaacda04edb75c4eea93384719efaa5 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Wed, 4 Sep 2019 14:11:21 -0700 Subject: driver core: Add support for linking devices during device addition The firmware corresponding to a device (dev.fwnode) might be able to provide functional dependency information between a device and its supplier and consumer devices. Tracking this functional dependency allows optimizing device probe order and informing a supplier when all its consumers have probed (and thereby actively managing their resources). The existing device links feature allows tracking and using supplier-consumer relationships. So, this patch adds the add_links() fwnode callback to allow firmware to create device links for each device as the device is added. However, when consumer devices are added, they might not have a supplier device to link to despite needing mandatory resources/functionality from one or more suppliers. A waiting_for_suppliers list is created to track such consumers and retry linking them when new devices get added. Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20190904211126.47518-3-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/device_link.rst | 3 +- drivers/base/core.c | 88 ++++++++++++++++++++++++++++++++ include/linux/device.h | 2 + include/linux/fwnode.h | 17 ++++++ 4 files changed, 109 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/Documentation/driver-api/device_link.rst b/Documentation/driver-api/device_link.rst index 1b5020ec6517..bc2d89af88ce 100644 --- a/Documentation/driver-api/device_link.rst +++ b/Documentation/driver-api/device_link.rst @@ -281,7 +281,8 @@ State machine :c:func:`driver_bound()`.) * Before a consumer device is probed, presence of supplier drivers is - verified by checking that links to suppliers are in ``DL_STATE_AVAILABLE`` + verified by checking the consumer device is not in the wait_for_suppliers + list and by checking that links to suppliers are in ``DL_STATE_AVAILABLE`` state. The state of the links is updated to ``DL_STATE_CONSUMER_PROBE``. (Call to :c:func:`device_links_check_suppliers()` from :c:func:`really_probe()`.) diff --git a/drivers/base/core.c b/drivers/base/core.c index 510fabf8918c..b3896da73b3d 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -44,6 +44,8 @@ early_param("sysfs.deprecated", sysfs_deprecated_setup); #endif /* Device links support. */ +static LIST_HEAD(wait_for_suppliers); +static DEFINE_MUTEX(wfs_lock); #ifdef CONFIG_SRCU static DEFINE_MUTEX(device_links_lock); @@ -430,6 +432,58 @@ struct device_link *device_link_add(struct device *consumer, } EXPORT_SYMBOL_GPL(device_link_add); +/** + * device_link_wait_for_supplier - Add device to wait_for_suppliers list + * @consumer: Consumer device + * + * Marks the @consumer device as waiting for suppliers to become available by + * adding it to the wait_for_suppliers list. The consumer device will never be + * probed until it's removed from the wait_for_suppliers list. + * + * The caller is responsible for adding the links to the supplier devices once + * they are available and removing the @consumer device from the + * wait_for_suppliers list once links to all the suppliers have been created. + * + * This function is NOT meant to be called from the probe function of the + * consumer but rather from code that creates/adds the consumer device. + */ +static void device_link_wait_for_supplier(struct device *consumer) +{ + mutex_lock(&wfs_lock); + list_add_tail(&consumer->links.needs_suppliers, &wait_for_suppliers); + mutex_unlock(&wfs_lock); +} + +/** + * device_link_add_missing_supplier_links - Add links from consumer devices to + * supplier devices, leaving any + * consumer with inactive suppliers on + * the wait_for_suppliers list + * + * Loops through all consumers waiting on suppliers and tries to add all their + * supplier links. If that succeeds, the consumer device is removed from + * wait_for_suppliers list. Otherwise, they are left in the wait_for_suppliers + * list. Devices left on the wait_for_suppliers list will not be probed. + * + * The fwnode add_links callback is expected to return 0 if it has found and + * added all the supplier links for the consumer device. It should return an + * error if it isn't able to do so. + * + * The caller of device_link_wait_for_supplier() is expected to call this once + * it's aware of potential suppliers becoming available. + */ +static void device_link_add_missing_supplier_links(void) +{ + struct device *dev, *tmp; + + mutex_lock(&wfs_lock); + list_for_each_entry_safe(dev, tmp, &wait_for_suppliers, + links.needs_suppliers) + if (!fwnode_call_int_op(dev->fwnode, add_links, dev)) + list_del_init(&dev->links.needs_suppliers); + mutex_unlock(&wfs_lock); +} + static void device_link_free(struct device_link *link) { while (refcount_dec_not_one(&link->rpm_active)) @@ -564,6 +618,17 @@ int device_links_check_suppliers(struct device *dev) struct device_link *link; int ret = 0; + /* + * Device waiting for supplier to become available is not allowed to + * probe. + */ + mutex_lock(&wfs_lock); + if (!list_empty(&dev->links.needs_suppliers)) { + mutex_unlock(&wfs_lock); + return -EPROBE_DEFER; + } + mutex_unlock(&wfs_lock); + device_links_write_lock(); list_for_each_entry(link, &dev->links.suppliers, c_node) { @@ -848,6 +913,10 @@ static void device_links_purge(struct device *dev) { struct device_link *link, *ln; + mutex_lock(&wfs_lock); + list_del(&dev->links.needs_suppliers); + mutex_unlock(&wfs_lock); + /* * Delete all of the remaining links from this device to any other * devices (either consumers or suppliers). @@ -1712,6 +1781,7 @@ void device_initialize(struct device *dev) #endif INIT_LIST_HEAD(&dev->links.consumers); INIT_LIST_HEAD(&dev->links.suppliers); + INIT_LIST_HEAD(&dev->links.needs_suppliers); dev->links.status = DL_DEV_NO_DRIVER; } EXPORT_SYMBOL_GPL(device_initialize); @@ -2202,6 +2272,24 @@ int device_add(struct device *dev) if (dev->fwnode && !dev->fwnode->dev) dev->fwnode->dev = dev; + /* + * Check if any of the other devices (consumers) have been waiting for + * this device (supplier) to be added so that they can create a device + * link to it. + * + * This needs to happen after device_pm_add() because device_link_add() + * requires the supplier be registered before it's called. + * + * But this also needs to happe before bus_probe_device() to make sure + * waiting consumers can link to it before the driver is bound to the + * device and the driver sync_state callback is called for this device. + */ + device_link_add_missing_supplier_links(); + + if (fwnode_has_op(dev->fwnode, add_links) + && fwnode_call_int_op(dev->fwnode, add_links, dev)) + device_link_wait_for_supplier(dev); + bus_probe_device(dev); if (parent) klist_add_tail(&dev->p->knode_parent, diff --git a/include/linux/device.h b/include/linux/device.h index 297239a08bb7..c6fb5b3431b7 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1135,11 +1135,13 @@ enum dl_dev_state { * struct dev_links_info - Device data related to device links. * @suppliers: List of links to supplier devices. * @consumers: List of links to consumer devices. + * @needs_suppliers: Hook to global list of devices waiting for suppliers. * @status: Driver status information. */ struct dev_links_info { struct list_head suppliers; struct list_head consumers; + struct list_head needs_suppliers; enum dl_dev_state status; }; diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index d8c6d231d577..6ae05b9ce359 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -66,6 +66,21 @@ struct fwnode_reference_args { * endpoint node. * @graph_get_port_parent: Return the parent node of a port node. * @graph_parse_endpoint: Parse endpoint for port and endpoint id. + * @add_links: Called after the device corresponding to the fwnode is added + * using device_add(). The function is expected to create device + * links to all the suppliers of the device that are available at + * the time this function is called. The function must NOT stop + * at the first failed device link if other unlinked supplier + * devices are present in the system. If some suppliers are not + * yet available, this function will be called again when other + * devices are added to allow creating device links to any newly + * available suppliers. + * + * Return 0 if device links have been successfully created to all + * the suppliers of this device or if the supplier information is + * not known. Return an error if and only if the supplier + * information is known but some of the suppliers are not yet + * available to create device links to. */ struct fwnode_operations { struct fwnode_handle *(*get)(struct fwnode_handle *fwnode); @@ -103,6 +118,8 @@ struct fwnode_operations { (*graph_get_port_parent)(struct fwnode_handle *fwnode); int (*graph_parse_endpoint)(const struct fwnode_handle *fwnode, struct fwnode_endpoint *endpoint); + int (*add_links)(const struct fwnode_handle *fwnode, + struct device *dev); }; #define fwnode_has_op(fwnode, op) \ -- cgit v1.2.3-71-gd317 From fc5a251d0fd7ca9038bab78a8c97932c8c6ca23b Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Wed, 4 Sep 2019 14:11:23 -0700 Subject: driver core: Add sync_state driver/bus callback This sync_state driver/bus callback is called once all the consumers of a supplier have probed successfully. This allows the supplier device's driver/bus to sync the supplier device's state to the software state with the guarantee that all the consumers are actively managing the resources provided by the supplier device. To maintain backwards compatibility and ease transition from existing frameworks and resource cleanup schemes, late_initcall_sync is the earliest when the sync_state callback might be called. There is no upper bound on the time by which the sync_state callback has to be called. This is because if a consumer device never probes, the supplier has to maintain its resources in the state left by the bootloader. For example, if the bootloader leaves the display backlight at a fixed voltage and the backlight driver is never probed, you don't want the backlight to ever be turned off after boot up. Also, when multiple devices are added after kernel init, some suppliers could be added before their consumer devices get added. In these instances, the supplier devices could get their sync_state callback called right after they probe because the consumers devices haven't had a chance to create device links to the suppliers. To handle this correctly, this change also provides APIs to pause/resume sync state callbacks so that when multiple devices are added, their sync_state callback evaluation can be postponed to happen after all of them are added. kbuild test robot reported missing documentation for device.state_synced Reported-by: kbuild test robot Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20190904211126.47518-5-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 72 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/device.h | 24 +++++++++++++++++ 2 files changed, 96 insertions(+) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index b3896da73b3d..acbf0b1414ab 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -46,6 +46,8 @@ early_param("sysfs.deprecated", sysfs_deprecated_setup); /* Device links support. */ static LIST_HEAD(wait_for_suppliers); static DEFINE_MUTEX(wfs_lock); +static LIST_HEAD(deferred_sync); +static unsigned int defer_sync_state_count = 1; #ifdef CONFIG_SRCU static DEFINE_MUTEX(device_links_lock); @@ -648,6 +650,69 @@ int device_links_check_suppliers(struct device *dev) return ret; } +static void __device_links_supplier_sync_state(struct device *dev) +{ + struct device_link *link; + + if (dev->state_synced) + return; + + list_for_each_entry(link, &dev->links.consumers, s_node) { + if (!(link->flags & DL_FLAG_MANAGED)) + continue; + if (link->status != DL_STATE_ACTIVE) + return; + } + + if (dev->bus->sync_state) + dev->bus->sync_state(dev); + else if (dev->driver && dev->driver->sync_state) + dev->driver->sync_state(dev); + + dev->state_synced = true; +} + +void device_links_supplier_sync_state_pause(void) +{ + device_links_write_lock(); + defer_sync_state_count++; + device_links_write_unlock(); +} + +void device_links_supplier_sync_state_resume(void) +{ + struct device *dev, *tmp; + + device_links_write_lock(); + if (!defer_sync_state_count) { + WARN(true, "Unmatched sync_state pause/resume!"); + goto out; + } + defer_sync_state_count--; + if (defer_sync_state_count) + goto out; + + list_for_each_entry_safe(dev, tmp, &deferred_sync, links.defer_sync) { + __device_links_supplier_sync_state(dev); + list_del_init(&dev->links.defer_sync); + } +out: + device_links_write_unlock(); +} + +static int sync_state_resume_initcall(void) +{ + device_links_supplier_sync_state_resume(); + return 0; +} +late_initcall(sync_state_resume_initcall); + +static void __device_links_supplier_defer_sync(struct device *sup) +{ + if (list_empty(&sup->links.defer_sync)) + list_add_tail(&sup->links.defer_sync, &deferred_sync); +} + /** * device_links_driver_bound - Update device links after probing its driver. * @dev: Device to update the links for. @@ -692,6 +757,11 @@ void device_links_driver_bound(struct device *dev) WARN_ON(link->status != DL_STATE_CONSUMER_PROBE); WRITE_ONCE(link->status, DL_STATE_ACTIVE); + + if (defer_sync_state_count) + __device_links_supplier_defer_sync(link->supplier); + else + __device_links_supplier_sync_state(link->supplier); } dev->links.status = DL_DEV_DRIVER_BOUND; @@ -808,6 +878,7 @@ void device_links_driver_cleanup(struct device *dev) WRITE_ONCE(link->status, DL_STATE_DORMANT); } + list_del_init(&dev->links.defer_sync); __device_links_no_driver(dev); device_links_write_unlock(); @@ -1782,6 +1853,7 @@ void device_initialize(struct device *dev) INIT_LIST_HEAD(&dev->links.consumers); INIT_LIST_HEAD(&dev->links.suppliers); INIT_LIST_HEAD(&dev->links.needs_suppliers); + INIT_LIST_HEAD(&dev->links.defer_sync); dev->links.status = DL_DEV_NO_DRIVER; } EXPORT_SYMBOL_GPL(device_initialize); diff --git a/include/linux/device.h b/include/linux/device.h index c6fb5b3431b7..6978bb471567 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -80,6 +80,13 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *); * that generate uevents to add the environment variables. * @probe: Called when a new device or driver add to this bus, and callback * the specific driver's probe to initial the matched device. + * @sync_state: Called to sync device state to software state after all the + * state tracking consumers linked to this device (present at + * the time of late_initcall) have successfully bound to a + * driver. If the device has no consumers, this function will + * be called at late_initcall_sync level. If the device has + * consumers that are never bound to a driver, this function + * will never get called until they do. * @remove: Called when a device removed from this bus. * @shutdown: Called at shut-down time to quiesce the device. * @@ -123,6 +130,7 @@ struct bus_type { int (*match)(struct device *dev, struct device_driver *drv); int (*uevent)(struct device *dev, struct kobj_uevent_env *env); int (*probe)(struct device *dev); + void (*sync_state)(struct device *dev); int (*remove)(struct device *dev); void (*shutdown)(struct device *dev); @@ -340,6 +348,13 @@ enum probe_type { * @probe: Called to query the existence of a specific device, * whether this driver can work with it, and bind the driver * to a specific device. + * @sync_state: Called to sync device state to software state after all the + * state tracking consumers linked to this device (present at + * the time of late_initcall) have successfully bound to a + * driver. If the device has no consumers, this function will + * be called at late_initcall_sync level. If the device has + * consumers that are never bound to a driver, this function + * will never get called until they do. * @remove: Called when the device is removed from the system to * unbind a device from this driver. * @shutdown: Called at shut-down time to quiesce the device. @@ -379,6 +394,7 @@ struct device_driver { const struct acpi_device_id *acpi_match_table; int (*probe) (struct device *dev); + void (*sync_state)(struct device *dev); int (*remove) (struct device *dev); void (*shutdown) (struct device *dev); int (*suspend) (struct device *dev, pm_message_t state); @@ -1136,12 +1152,14 @@ enum dl_dev_state { * @suppliers: List of links to supplier devices. * @consumers: List of links to consumer devices. * @needs_suppliers: Hook to global list of devices waiting for suppliers. + * @defer_sync: Hook to global list of devices that have deferred sync_state. * @status: Driver status information. */ struct dev_links_info { struct list_head suppliers; struct list_head consumers; struct list_head needs_suppliers; + struct list_head defer_sync; enum dl_dev_state status; }; @@ -1217,6 +1235,9 @@ struct dev_links_info { * @offline: Set after successful invocation of bus type's .offline(). * @of_node_reused: Set if the device-tree node is shared with an ancestor * device. + * @state_synced: The hardware state of this device has been synced to match + * the software state of this device by calling the driver/bus + * sync_state() callback. * @dma_coherent: this particular device is dma coherent, even if the * architecture supports non-coherent devices. * @@ -1313,6 +1334,7 @@ struct device { bool offline_disabled:1; bool offline:1; bool of_node_reused:1; + bool state_synced:1; #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) @@ -1655,6 +1677,8 @@ struct device_link *device_link_add(struct device *consumer, struct device *supplier, u32 flags); void device_link_del(struct device_link *link); void device_link_remove(void *consumer, struct device *supplier); +void device_links_supplier_sync_state_pause(void); +void device_links_supplier_sync_state_resume(void); #ifndef dev_fmt #define dev_fmt(fmt) fmt -- cgit v1.2.3-71-gd317 From 7c550daffe22a97282effa75fe7c1f6b83563ecb Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Oct 2019 11:49:27 +0200 Subject: net: fib_notifier: make FIB notifier per-netns Currently all users of FIB notifier only cares about events in init_net. Later in this patchset, users get interested in other namespaces too. However, for every registered block user is interested only about one namespace. Make the FIB notifier registration per-netns and avoid unnecessary calls of notifier block for other namespaces. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c | 7 +- .../net/ethernet/mellanox/mlxsw/spectrum_router.c | 9 +-- drivers/net/ethernet/rocker/rocker_main.c | 9 +-- drivers/net/netdevsim/fib.c | 8 +- include/linux/mroute_base.h | 10 +-- include/net/fib_notifier.h | 7 +- include/net/ip6_fib.h | 2 +- include/net/ip_fib.h | 2 +- net/core/fib_notifier.c | 87 ++++++++++------------ net/core/fib_rules.c | 7 +- net/ipv4/fib_notifier.c | 4 +- net/ipv4/fib_trie.c | 17 ++--- net/ipv4/ipmr_base.c | 4 +- net/ipv6/fib6_notifier.c | 4 +- net/ipv6/ip6_fib.c | 6 +- 15 files changed, 78 insertions(+), 105 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c index 5d20d615663e..fe0cc969cf94 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c @@ -248,9 +248,6 @@ static int mlx5_lag_fib_event(struct notifier_block *nb, struct net_device *fib_dev; struct fib_info *fi; - if (!net_eq(info->net, &init_net)) - return NOTIFY_DONE; - if (info->family != AF_INET) return NOTIFY_DONE; @@ -311,7 +308,7 @@ int mlx5_lag_mp_init(struct mlx5_lag *ldev) return 0; mp->fib_nb.notifier_call = mlx5_lag_fib_event; - err = register_fib_notifier(&mp->fib_nb, + err = register_fib_notifier(&init_net, &mp->fib_nb, mlx5_lag_fib_event_flush); if (err) mp->fib_nb.notifier_call = NULL; @@ -326,6 +323,6 @@ void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev) if (!mp->fib_nb.notifier_call) return; - unregister_fib_notifier(&mp->fib_nb); + unregister_fib_notifier(&init_net, &mp->fib_nb); mp->fib_nb.notifier_call = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index a330b369e899..d0db9ea71323 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -6213,7 +6213,7 @@ static int mlxsw_sp_router_fib_rule_event(unsigned long event, rule = fr_info->rule; /* Rule only affects locally generated traffic */ - if (rule->iifindex == info->net->loopback_dev->ifindex) + if (rule->iifindex == init_net.loopback_dev->ifindex) return 0; switch (info->family) { @@ -6250,8 +6250,7 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, struct mlxsw_sp_router *router; int err; - if (!net_eq(info->net, &init_net) || - (info->family != AF_INET && info->family != AF_INET6 && + if ((info->family != AF_INET && info->family != AF_INET6 && info->family != RTNL_FAMILY_IPMR && info->family != RTNL_FAMILY_IP6MR)) return NOTIFY_DONE; @@ -8155,7 +8154,7 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) goto err_dscp_init; mlxsw_sp->router->fib_nb.notifier_call = mlxsw_sp_router_fib_event; - err = register_fib_notifier(&mlxsw_sp->router->fib_nb, + err = register_fib_notifier(&init_net, &mlxsw_sp->router->fib_nb, mlxsw_sp_router_fib_dump_flush); if (err) goto err_register_fib_notifier; @@ -8195,7 +8194,7 @@ err_register_inetaddr_notifier: void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) { - unregister_fib_notifier(&mlxsw_sp->router->fib_nb); + unregister_fib_notifier(&init_net, &mlxsw_sp->router->fib_nb); unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb); mlxsw_sp_neigh_fini(mlxsw_sp); mlxsw_sp_vrs_fini(mlxsw_sp); diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index 786b158bd305..e54f6341a785 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -2189,9 +2189,6 @@ static int rocker_router_fib_event(struct notifier_block *nb, struct rocker_fib_event_work *fib_work; struct fib_notifier_info *info = ptr; - if (!net_eq(info->net, &init_net)) - return NOTIFY_DONE; - if (info->family != AF_INET) return NOTIFY_DONE; @@ -2994,7 +2991,7 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id) * the device, so no need to pass a callback. */ rocker->fib_nb.notifier_call = rocker_router_fib_event; - err = register_fib_notifier(&rocker->fib_nb, NULL); + err = register_fib_notifier(&init_net, &rocker->fib_nb, NULL); if (err) goto err_register_fib_notifier; @@ -3021,7 +3018,7 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id) err_register_switchdev_blocking_notifier: unregister_switchdev_notifier(&rocker_switchdev_notifier); err_register_switchdev_notifier: - unregister_fib_notifier(&rocker->fib_nb); + unregister_fib_notifier(&init_net, &rocker->fib_nb); err_register_fib_notifier: rocker_remove_ports(rocker); err_probe_ports: @@ -3057,7 +3054,7 @@ static void rocker_remove(struct pci_dev *pdev) unregister_switchdev_blocking_notifier(nb); unregister_switchdev_notifier(&rocker_switchdev_notifier); - unregister_fib_notifier(&rocker->fib_nb); + unregister_fib_notifier(&init_net, &rocker->fib_nb); rocker_remove_ports(rocker); rocker_write32(rocker, CONTROL, ROCKER_CONTROL_RESET); destroy_workqueue(rocker->rocker_owq); diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index 7de17e42d77a..01ee9cc54605 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -182,9 +182,6 @@ static int nsim_fib_event_nb(struct notifier_block *nb, unsigned long event, struct fib_notifier_info *info = ptr; int err = 0; - if (!net_eq(info->net, &init_net)) - return NOTIFY_DONE; - switch (event) { case FIB_EVENT_RULE_ADD: /* fall through */ case FIB_EVENT_RULE_DEL: @@ -258,7 +255,8 @@ struct nsim_fib_data *nsim_fib_create(struct devlink *devlink) data->ipv6.rules.max = (u64)-1; data->fib_nb.notifier_call = nsim_fib_event_nb; - err = register_fib_notifier(&data->fib_nb, nsim_fib_dump_inconsistent); + err = register_fib_notifier(&init_net, &data->fib_nb, + nsim_fib_dump_inconsistent); if (err) { pr_err("Failed to register fib notifier\n"); goto err_out; @@ -297,6 +295,6 @@ void nsim_fib_destroy(struct devlink *devlink, struct nsim_fib_data *data) NSIM_RESOURCE_IPV4_FIB_RULES); devlink_resource_occ_get_unregister(devlink, NSIM_RESOURCE_IPV4_FIB); - unregister_fib_notifier(&data->fib_nb); + unregister_fib_notifier(&init_net, &data->fib_nb); kfree(data); } diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index 34de06b426ef..0931631bbc13 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -47,7 +47,6 @@ struct vif_entry_notifier_info { }; static inline int mr_call_vif_notifier(struct notifier_block *nb, - struct net *net, unsigned short family, enum fib_event_type event_type, struct vif_device *vif, @@ -56,7 +55,6 @@ static inline int mr_call_vif_notifier(struct notifier_block *nb, struct vif_entry_notifier_info info = { .info = { .family = family, - .net = net, }, .dev = vif->dev, .vif_index = vif_index, @@ -64,7 +62,7 @@ static inline int mr_call_vif_notifier(struct notifier_block *nb, .tb_id = tb_id, }; - return call_fib_notifier(nb, net, event_type, &info.info); + return call_fib_notifier(nb, event_type, &info.info); } static inline int mr_call_vif_notifiers(struct net *net, @@ -77,7 +75,6 @@ static inline int mr_call_vif_notifiers(struct net *net, struct vif_entry_notifier_info info = { .info = { .family = family, - .net = net, }, .dev = vif->dev, .vif_index = vif_index, @@ -173,7 +170,6 @@ struct mfc_entry_notifier_info { }; static inline int mr_call_mfc_notifier(struct notifier_block *nb, - struct net *net, unsigned short family, enum fib_event_type event_type, struct mr_mfc *mfc, u32 tb_id) @@ -181,13 +177,12 @@ static inline int mr_call_mfc_notifier(struct notifier_block *nb, struct mfc_entry_notifier_info info = { .info = { .family = family, - .net = net, }, .mfc = mfc, .tb_id = tb_id }; - return call_fib_notifier(nb, net, event_type, &info.info); + return call_fib_notifier(nb, event_type, &info.info); } static inline int mr_call_mfc_notifiers(struct net *net, @@ -199,7 +194,6 @@ static inline int mr_call_mfc_notifiers(struct net *net, struct mfc_entry_notifier_info info = { .info = { .family = family, - .net = net, }, .mfc = mfc, .tb_id = tb_id diff --git a/include/net/fib_notifier.h b/include/net/fib_notifier.h index c49d7bfb5c30..23353f67b2b0 100644 --- a/include/net/fib_notifier.h +++ b/include/net/fib_notifier.h @@ -8,7 +8,6 @@ struct module; struct fib_notifier_info { - struct net *net; int family; struct netlink_ext_ack *extack; }; @@ -35,14 +34,14 @@ struct fib_notifier_ops { struct rcu_head rcu; }; -int call_fib_notifier(struct notifier_block *nb, struct net *net, +int call_fib_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info); int call_fib_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info); -int register_fib_notifier(struct notifier_block *nb, +int register_fib_notifier(struct net *net, struct notifier_block *nb, void (*cb)(struct notifier_block *nb)); -int unregister_fib_notifier(struct notifier_block *nb); +int unregister_fib_notifier(struct net *net, struct notifier_block *nb); struct fib_notifier_ops * fib_notifier_ops_register(const struct fib_notifier_ops *tmpl, struct net *net); void fib_notifier_ops_unregister(struct fib_notifier_ops *ops); diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 4b5656c71abc..14e9fca0e326 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -478,7 +478,7 @@ struct ipv6_route_iter { extern const struct seq_operations ipv6_route_seq_ops; -int call_fib6_notifier(struct notifier_block *nb, struct net *net, +int call_fib6_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info); int call_fib6_notifiers(struct net *net, enum fib_event_type event_type, diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index ab1ca9e238d2..a9df85304f40 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -219,7 +219,7 @@ struct fib_nh_notifier_info { struct fib_nh *fib_nh; }; -int call_fib4_notifier(struct notifier_block *nb, struct net *net, +int call_fib4_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info); int call_fib4_notifiers(struct net *net, enum fib_event_type event_type, diff --git a/net/core/fib_notifier.c b/net/core/fib_notifier.c index 470a606d5e8d..fbd029425638 100644 --- a/net/core/fib_notifier.c +++ b/net/core/fib_notifier.c @@ -12,17 +12,15 @@ static unsigned int fib_notifier_net_id; struct fib_notifier_net { struct list_head fib_notifier_ops; + struct atomic_notifier_head fib_chain; }; -static ATOMIC_NOTIFIER_HEAD(fib_chain); - -int call_fib_notifier(struct notifier_block *nb, struct net *net, +int call_fib_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info) { int err; - info->net = net; err = nb->notifier_call(nb, event_type, info); return notifier_to_errno(err); } @@ -31,35 +29,29 @@ EXPORT_SYMBOL(call_fib_notifier); int call_fib_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info) { + struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); int err; - info->net = net; - err = atomic_notifier_call_chain(&fib_chain, event_type, info); + err = atomic_notifier_call_chain(&fn_net->fib_chain, event_type, info); return notifier_to_errno(err); } EXPORT_SYMBOL(call_fib_notifiers); -static unsigned int fib_seq_sum(void) +static unsigned int fib_seq_sum(struct net *net) { - struct fib_notifier_net *fn_net; + struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); struct fib_notifier_ops *ops; unsigned int fib_seq = 0; - struct net *net; rtnl_lock(); - down_read(&net_rwsem); - for_each_net(net) { - fn_net = net_generic(net, fib_notifier_net_id); - rcu_read_lock(); - list_for_each_entry_rcu(ops, &fn_net->fib_notifier_ops, list) { - if (!try_module_get(ops->owner)) - continue; - fib_seq += ops->fib_seq_read(net); - module_put(ops->owner); - } - rcu_read_unlock(); + rcu_read_lock(); + list_for_each_entry_rcu(ops, &fn_net->fib_notifier_ops, list) { + if (!try_module_get(ops->owner)) + continue; + fib_seq += ops->fib_seq_read(net); + module_put(ops->owner); } - up_read(&net_rwsem); + rcu_read_unlock(); rtnl_unlock(); return fib_seq; @@ -69,68 +61,66 @@ static int fib_net_dump(struct net *net, struct notifier_block *nb) { struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); struct fib_notifier_ops *ops; + int err = 0; + rcu_read_lock(); list_for_each_entry_rcu(ops, &fn_net->fib_notifier_ops, list) { - int err; - if (!try_module_get(ops->owner)) continue; err = ops->fib_dump(net, nb); module_put(ops->owner); if (err) - return err; + goto unlock; } - return 0; +unlock: + rcu_read_unlock(); + + return err; } -static bool fib_dump_is_consistent(struct notifier_block *nb, +static bool fib_dump_is_consistent(struct net *net, struct notifier_block *nb, void (*cb)(struct notifier_block *nb), unsigned int fib_seq) { - atomic_notifier_chain_register(&fib_chain, nb); - if (fib_seq == fib_seq_sum()) + struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); + + atomic_notifier_chain_register(&fn_net->fib_chain, nb); + if (fib_seq == fib_seq_sum(net)) return true; - atomic_notifier_chain_unregister(&fib_chain, nb); + atomic_notifier_chain_unregister(&fn_net->fib_chain, nb); if (cb) cb(nb); return false; } #define FIB_DUMP_MAX_RETRIES 5 -int register_fib_notifier(struct notifier_block *nb, +int register_fib_notifier(struct net *net, struct notifier_block *nb, void (*cb)(struct notifier_block *nb)) { int retries = 0; int err; do { - unsigned int fib_seq = fib_seq_sum(); - struct net *net; - - rcu_read_lock(); - for_each_net_rcu(net) { - err = fib_net_dump(net, nb); - if (err) - goto err_fib_net_dump; - } - rcu_read_unlock(); - - if (fib_dump_is_consistent(nb, cb, fib_seq)) + unsigned int fib_seq = fib_seq_sum(net); + + err = fib_net_dump(net, nb); + if (err) + return err; + + if (fib_dump_is_consistent(net, nb, cb, fib_seq)) return 0; } while (++retries < FIB_DUMP_MAX_RETRIES); return -EBUSY; - -err_fib_net_dump: - rcu_read_unlock(); - return err; } EXPORT_SYMBOL(register_fib_notifier); -int unregister_fib_notifier(struct notifier_block *nb) +int unregister_fib_notifier(struct net *net, struct notifier_block *nb) { - return atomic_notifier_chain_unregister(&fib_chain, nb); + struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); + + return atomic_notifier_chain_unregister(&fn_net->fib_chain, nb); } EXPORT_SYMBOL(unregister_fib_notifier); @@ -181,6 +171,7 @@ static int __net_init fib_notifier_net_init(struct net *net) struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); INIT_LIST_HEAD(&fn_net->fib_notifier_ops); + ATOMIC_INIT_NOTIFIER_HEAD(&fn_net->fib_chain); return 0; } diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index dd220ce7ca7a..28cbf07102bc 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -321,7 +321,7 @@ out: } EXPORT_SYMBOL_GPL(fib_rules_lookup); -static int call_fib_rule_notifier(struct notifier_block *nb, struct net *net, +static int call_fib_rule_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_rule *rule, int family) { @@ -330,7 +330,7 @@ static int call_fib_rule_notifier(struct notifier_block *nb, struct net *net, .rule = rule, }; - return call_fib_notifier(nb, net, event_type, &info.info); + return call_fib_notifier(nb, event_type, &info.info); } static int call_fib_rule_notifiers(struct net *net, @@ -359,8 +359,7 @@ int fib_rules_dump(struct net *net, struct notifier_block *nb, int family) if (!ops) return -EAFNOSUPPORT; list_for_each_entry_rcu(rule, &ops->rules_list, list) - call_fib_rule_notifier(nb, net, FIB_EVENT_RULE_ADD, rule, - family); + call_fib_rule_notifier(nb, FIB_EVENT_RULE_ADD, rule, family); rules_ops_put(ops); return 0; diff --git a/net/ipv4/fib_notifier.c b/net/ipv4/fib_notifier.c index b804ccbdb241..1a128c1346fb 100644 --- a/net/ipv4/fib_notifier.c +++ b/net/ipv4/fib_notifier.c @@ -9,12 +9,12 @@ #include #include -int call_fib4_notifier(struct notifier_block *nb, struct net *net, +int call_fib4_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info) { info->family = AF_INET; - return call_fib_notifier(nb, net, event_type, info); + return call_fib_notifier(nb, event_type, info); } int call_fib4_notifiers(struct net *net, enum fib_event_type event_type, diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 1ab2fb6bb37d..5b600b2a2aa3 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -74,7 +74,7 @@ #include #include "fib_lookup.h" -static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net, +static int call_fib_entry_notifier(struct notifier_block *nb, enum fib_event_type event_type, u32 dst, int dst_len, struct fib_alias *fa) { @@ -86,7 +86,7 @@ static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net, .type = fa->fa_type, .tb_id = fa->tb_id, }; - return call_fib4_notifier(nb, net, event_type, &info.info); + return call_fib4_notifier(nb, event_type, &info.info); } static int call_fib_entry_notifiers(struct net *net, @@ -2015,8 +2015,8 @@ void fib_info_notify_update(struct net *net, struct nl_info *info) } } -static void fib_leaf_notify(struct net *net, struct key_vector *l, - struct fib_table *tb, struct notifier_block *nb) +static void fib_leaf_notify(struct key_vector *l, struct fib_table *tb, + struct notifier_block *nb) { struct fib_alias *fa; @@ -2032,20 +2032,19 @@ static void fib_leaf_notify(struct net *net, struct key_vector *l, if (tb->tb_id != fa->tb_id) continue; - call_fib_entry_notifier(nb, net, FIB_EVENT_ENTRY_ADD, l->key, + call_fib_entry_notifier(nb, FIB_EVENT_ENTRY_ADD, l->key, KEYLENGTH - fa->fa_slen, fa); } } -static void fib_table_notify(struct net *net, struct fib_table *tb, - struct notifier_block *nb) +static void fib_table_notify(struct fib_table *tb, struct notifier_block *nb) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *l, *tp = t->kv; t_key key = 0; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { - fib_leaf_notify(net, l, tb, nb); + fib_leaf_notify(l, tb, nb); key = l->key + 1; /* stop in case of wrap around */ @@ -2063,7 +2062,7 @@ void fib_notify(struct net *net, struct notifier_block *nb) struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist) - fib_table_notify(net, tb, nb); + fib_table_notify(tb, nb); } } diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index ea48bd15a575..4dcc3214e3cc 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -409,7 +409,7 @@ int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, if (!v->dev) continue; - mr_call_vif_notifier(nb, net, family, + mr_call_vif_notifier(nb, family, FIB_EVENT_VIF_ADD, v, vifi, mrt->id); } @@ -417,7 +417,7 @@ int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, /* Notify on table MFC entries */ list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) - mr_call_mfc_notifier(nb, net, family, + mr_call_mfc_notifier(nb, family, FIB_EVENT_ENTRY_ADD, mfc, mrt->id); } diff --git a/net/ipv6/fib6_notifier.c b/net/ipv6/fib6_notifier.c index 05f82baaa99e..4fe79296999a 100644 --- a/net/ipv6/fib6_notifier.c +++ b/net/ipv6/fib6_notifier.c @@ -7,12 +7,12 @@ #include #include -int call_fib6_notifier(struct notifier_block *nb, struct net *net, +int call_fib6_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info) { info->family = AF_INET6; - return call_fib_notifier(nb, net, event_type, info); + return call_fib_notifier(nb, event_type, info); } int call_fib6_notifiers(struct net *net, enum fib_event_type event_type, diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 6e2af411cd9c..f6fae48b2e18 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -357,7 +357,7 @@ unsigned int fib6_tables_seq_read(struct net *net) return fib_seq; } -static int call_fib6_entry_notifier(struct notifier_block *nb, struct net *net, +static int call_fib6_entry_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib6_info *rt) { @@ -365,7 +365,7 @@ static int call_fib6_entry_notifier(struct notifier_block *nb, struct net *net, .rt = rt, }; - return call_fib6_notifier(nb, net, event_type, &info.info); + return call_fib6_notifier(nb, event_type, &info.info); } int call_fib6_entry_notifiers(struct net *net, @@ -407,7 +407,7 @@ static void fib6_rt_dump(struct fib6_info *rt, struct fib6_dump_arg *arg) { if (rt == arg->net->ipv6.fib6_null_entry) return; - call_fib6_entry_notifier(arg->nb, arg->net, FIB_EVENT_ENTRY_ADD, rt); + call_fib6_entry_notifier(arg->nb, FIB_EVENT_ENTRY_ADD, rt); } static int fib6_node_dump(struct fib6_walker *w) -- cgit v1.2.3-71-gd317 From b7a595577ef3dc9add2b3e6d00869d017306bfbe Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Oct 2019 11:49:30 +0200 Subject: net: fib_notifier: propagate extack down to the notifier block callback Since errors are propagated all the way up to the caller, propagate possible extack of the caller all the way down to the notifier block callback. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c | 2 +- .../net/ethernet/mellanox/mlxsw/spectrum_router.c | 2 +- drivers/net/ethernet/rocker/rocker_main.c | 2 +- drivers/net/netdevsim/fib.c | 2 +- include/linux/mroute_base.h | 18 ++++++++++++------ include/net/fib_notifier.h | 6 ++++-- include/net/fib_rules.h | 3 ++- include/net/ip6_fib.h | 9 ++++++--- include/net/ip_fib.h | 9 ++++++--- net/core/fib_notifier.c | 10 ++++++---- net/core/fib_rules.c | 9 ++++++--- net/ipv4/fib_notifier.c | 7 ++++--- net/ipv4/fib_rules.c | 5 +++-- net/ipv4/fib_trie.c | 20 +++++++++++++------- net/ipv4/ipmr.c | 13 ++++++++----- net/ipv4/ipmr_base.c | 12 +++++++----- net/ipv6/fib6_notifier.c | 7 ++++--- net/ipv6/fib6_rules.c | 5 +++-- net/ipv6/ip6_fib.c | 12 +++++++++--- net/ipv6/ip6mr.c | 13 ++++++++----- 20 files changed, 105 insertions(+), 61 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c index fe0cc969cf94..13e2944b1274 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c @@ -309,7 +309,7 @@ int mlx5_lag_mp_init(struct mlx5_lag *ldev) mp->fib_nb.notifier_call = mlx5_lag_fib_event; err = register_fib_notifier(&init_net, &mp->fib_nb, - mlx5_lag_fib_event_flush); + mlx5_lag_fib_event_flush, NULL); if (err) mp->fib_nb.notifier_call = NULL; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 1eeff1d23b13..445e2daa54ac 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -8135,7 +8135,7 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) mlxsw_sp->router->fib_nb.notifier_call = mlxsw_sp_router_fib_event; err = register_fib_notifier(&init_net, &mlxsw_sp->router->fib_nb, - mlxsw_sp_router_fib_dump_flush); + mlxsw_sp_router_fib_dump_flush, NULL); if (err) goto err_register_fib_notifier; diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index e54f6341a785..bc4f951315da 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -2991,7 +2991,7 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id) * the device, so no need to pass a callback. */ rocker->fib_nb.notifier_call = rocker_router_fib_event; - err = register_fib_notifier(&init_net, &rocker->fib_nb, NULL); + err = register_fib_notifier(&init_net, &rocker->fib_nb, NULL, NULL); if (err) goto err_register_fib_notifier; diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index 01ee9cc54605..d2aeac0f4c2c 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -256,7 +256,7 @@ struct nsim_fib_data *nsim_fib_create(struct devlink *devlink) data->fib_nb.notifier_call = nsim_fib_event_nb; err = register_fib_notifier(&init_net, &data->fib_nb, - nsim_fib_dump_inconsistent); + nsim_fib_dump_inconsistent, NULL); if (err) { pr_err("Failed to register fib notifier\n"); goto err_out; diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index 0931631bbc13..8071148f29a6 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -50,11 +50,13 @@ static inline int mr_call_vif_notifier(struct notifier_block *nb, unsigned short family, enum fib_event_type event_type, struct vif_device *vif, - unsigned short vif_index, u32 tb_id) + unsigned short vif_index, u32 tb_id, + struct netlink_ext_ack *extack) { struct vif_entry_notifier_info info = { .info = { .family = family, + .extack = extack, }, .dev = vif->dev, .vif_index = vif_index, @@ -172,11 +174,13 @@ struct mfc_entry_notifier_info { static inline int mr_call_mfc_notifier(struct notifier_block *nb, unsigned short family, enum fib_event_type event_type, - struct mr_mfc *mfc, u32 tb_id) + struct mr_mfc *mfc, u32 tb_id, + struct netlink_ext_ack *extack) { struct mfc_entry_notifier_info info = { .info = { .family = family, + .extack = extack, }, .mfc = mfc, .tb_id = tb_id @@ -295,10 +299,11 @@ int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, int (*rules_dump)(struct net *net, - struct notifier_block *nb), + struct notifier_block *nb, + struct netlink_ext_ack *extack), struct mr_table *(*mr_iter)(struct net *net, struct mr_table *mrt), - rwlock_t *mrt_lock); + rwlock_t *mrt_lock, struct netlink_ext_ack *extack); #else static inline void vif_device_init(struct vif_device *v, struct net_device *dev, @@ -349,10 +354,11 @@ mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, static inline int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, int (*rules_dump)(struct net *net, - struct notifier_block *nb), + struct notifier_block *nb, + struct netlink_ext_ack *extack), struct mr_table *(*mr_iter)(struct net *net, struct mr_table *mrt), - rwlock_t *mrt_lock) + rwlock_t *mrt_lock, struct netlink_ext_ack *extack) { return -EINVAL; } diff --git a/include/net/fib_notifier.h b/include/net/fib_notifier.h index 23353f67b2b0..6d59221ff05a 100644 --- a/include/net/fib_notifier.h +++ b/include/net/fib_notifier.h @@ -29,7 +29,8 @@ struct fib_notifier_ops { int family; struct list_head list; unsigned int (*fib_seq_read)(struct net *net); - int (*fib_dump)(struct net *net, struct notifier_block *nb); + int (*fib_dump)(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack); struct module *owner; struct rcu_head rcu; }; @@ -40,7 +41,8 @@ int call_fib_notifier(struct notifier_block *nb, int call_fib_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info); int register_fib_notifier(struct net *net, struct notifier_block *nb, - void (*cb)(struct notifier_block *nb)); + void (*cb)(struct notifier_block *nb), + struct netlink_ext_ack *extack); int unregister_fib_notifier(struct net *net, struct notifier_block *nb); struct fib_notifier_ops * fib_notifier_ops_register(const struct fib_notifier_ops *tmpl, struct net *net); diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 20dcadd8eed9..54e227e6b06a 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -194,7 +194,8 @@ int fib_rules_lookup(struct fib_rules_ops *, struct flowi *, int flags, int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table, u32 flags); bool fib_rule_matchall(const struct fib_rule *rule); -int fib_rules_dump(struct net *net, struct notifier_block *nb, int family); +int fib_rules_dump(struct net *net, struct notifier_block *nb, int family, + struct netlink_ext_ack *extack); unsigned int fib_rules_seq_read(struct net *net, int family); int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 14e9fca0e326..5d1615463138 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -488,7 +488,8 @@ int __net_init fib6_notifier_init(struct net *net); void __net_exit fib6_notifier_exit(struct net *net); unsigned int fib6_tables_seq_read(struct net *net); -int fib6_tables_dump(struct net *net, struct notifier_block *nb); +int fib6_tables_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack); void fib6_update_sernum(struct net *net, struct fib6_info *rt); void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt); @@ -504,7 +505,8 @@ static inline bool fib6_metric_locked(struct fib6_info *f6i, int metric) int fib6_rules_init(void); void fib6_rules_cleanup(void); bool fib6_rule_default(const struct fib_rule *rule); -int fib6_rules_dump(struct net *net, struct notifier_block *nb); +int fib6_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack); unsigned int fib6_rules_seq_read(struct net *net); static inline bool fib6_rules_early_flow_dissect(struct net *net, @@ -537,7 +539,8 @@ static inline bool fib6_rule_default(const struct fib_rule *rule) { return true; } -static inline int fib6_rules_dump(struct net *net, struct notifier_block *nb) +static inline int fib6_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { return 0; } diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 05c1fd9c5e23..52b2406a5dfc 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -229,7 +229,8 @@ int __net_init fib4_notifier_init(struct net *net); void __net_exit fib4_notifier_exit(struct net *net); void fib_info_notify_update(struct net *net, struct nl_info *info); -int fib_notify(struct net *net, struct notifier_block *nb); +int fib_notify(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack); struct fib_table { struct hlist_node tb_hlist; @@ -315,7 +316,8 @@ static inline bool fib4_rule_default(const struct fib_rule *rule) return true; } -static inline int fib4_rules_dump(struct net *net, struct notifier_block *nb) +static inline int fib4_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { return 0; } @@ -377,7 +379,8 @@ out: } bool fib4_rule_default(const struct fib_rule *rule); -int fib4_rules_dump(struct net *net, struct notifier_block *nb); +int fib4_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack); unsigned int fib4_rules_seq_read(struct net *net); static inline bool fib4_rules_early_flow_dissect(struct net *net, diff --git a/net/core/fib_notifier.c b/net/core/fib_notifier.c index fbd029425638..fc96259807b6 100644 --- a/net/core/fib_notifier.c +++ b/net/core/fib_notifier.c @@ -57,7 +57,8 @@ static unsigned int fib_seq_sum(struct net *net) return fib_seq; } -static int fib_net_dump(struct net *net, struct notifier_block *nb) +static int fib_net_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); struct fib_notifier_ops *ops; @@ -67,7 +68,7 @@ static int fib_net_dump(struct net *net, struct notifier_block *nb) list_for_each_entry_rcu(ops, &fn_net->fib_notifier_ops, list) { if (!try_module_get(ops->owner)) continue; - err = ops->fib_dump(net, nb); + err = ops->fib_dump(net, nb, extack); module_put(ops->owner); if (err) goto unlock; @@ -96,7 +97,8 @@ static bool fib_dump_is_consistent(struct net *net, struct notifier_block *nb, #define FIB_DUMP_MAX_RETRIES 5 int register_fib_notifier(struct net *net, struct notifier_block *nb, - void (*cb)(struct notifier_block *nb)) + void (*cb)(struct notifier_block *nb), + struct netlink_ext_ack *extack) { int retries = 0; int err; @@ -104,7 +106,7 @@ int register_fib_notifier(struct net *net, struct notifier_block *nb, do { unsigned int fib_seq = fib_seq_sum(net); - err = fib_net_dump(net, nb); + err = fib_net_dump(net, nb, extack); if (err) return err; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 592d8aef90e3..3e7e15278c46 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -323,10 +323,12 @@ EXPORT_SYMBOL_GPL(fib_rules_lookup); static int call_fib_rule_notifier(struct notifier_block *nb, enum fib_event_type event_type, - struct fib_rule *rule, int family) + struct fib_rule *rule, int family, + struct netlink_ext_ack *extack) { struct fib_rule_notifier_info info = { .info.family = family, + .info.extack = extack, .rule = rule, }; @@ -350,7 +352,8 @@ static int call_fib_rule_notifiers(struct net *net, } /* Called with rcu_read_lock() */ -int fib_rules_dump(struct net *net, struct notifier_block *nb, int family) +int fib_rules_dump(struct net *net, struct notifier_block *nb, int family, + struct netlink_ext_ack *extack) { struct fib_rules_ops *ops; struct fib_rule *rule; @@ -361,7 +364,7 @@ int fib_rules_dump(struct net *net, struct notifier_block *nb, int family) return -EAFNOSUPPORT; list_for_each_entry_rcu(rule, &ops->rules_list, list) { err = call_fib_rule_notifier(nb, FIB_EVENT_RULE_ADD, - rule, family); + rule, family, extack); if (err) break; } diff --git a/net/ipv4/fib_notifier.c b/net/ipv4/fib_notifier.c index 0c57f68a9340..0c28bd469a68 100644 --- a/net/ipv4/fib_notifier.c +++ b/net/ipv4/fib_notifier.c @@ -34,15 +34,16 @@ static unsigned int fib4_seq_read(struct net *net) return net->ipv4.fib_seq + fib4_rules_seq_read(net); } -static int fib4_dump(struct net *net, struct notifier_block *nb) +static int fib4_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { int err; - err = fib4_rules_dump(net, nb); + err = fib4_rules_dump(net, nb, extack); if (err) return err; - return fib_notify(net, nb); + return fib_notify(net, nb, extack); } static const struct fib_notifier_ops fib4_notifier_ops_template = { diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index b43a7ba5c6a4..f99e3bac5cab 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -65,9 +65,10 @@ bool fib4_rule_default(const struct fib_rule *rule) } EXPORT_SYMBOL_GPL(fib4_rule_default); -int fib4_rules_dump(struct net *net, struct notifier_block *nb) +int fib4_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { - return fib_rules_dump(net, nb, AF_INET); + return fib_rules_dump(net, nb, AF_INET, extack); } unsigned int fib4_rules_seq_read(struct net *net) diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 568e59423773..b9df9c09b84e 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -76,9 +76,11 @@ static int call_fib_entry_notifier(struct notifier_block *nb, enum fib_event_type event_type, u32 dst, - int dst_len, struct fib_alias *fa) + int dst_len, struct fib_alias *fa, + struct netlink_ext_ack *extack) { struct fib_entry_notifier_info info = { + .info.extack = extack, .dst = dst, .dst_len = dst_len, .fi = fa->fa_info, @@ -2016,7 +2018,8 @@ void fib_info_notify_update(struct net *net, struct nl_info *info) } static int fib_leaf_notify(struct key_vector *l, struct fib_table *tb, - struct notifier_block *nb) + struct notifier_block *nb, + struct netlink_ext_ack *extack) { struct fib_alias *fa; int err; @@ -2034,14 +2037,16 @@ static int fib_leaf_notify(struct key_vector *l, struct fib_table *tb, continue; err = call_fib_entry_notifier(nb, FIB_EVENT_ENTRY_ADD, l->key, - KEYLENGTH - fa->fa_slen, fa); + KEYLENGTH - fa->fa_slen, + fa, extack); if (err) return err; } return 0; } -static int fib_table_notify(struct fib_table *tb, struct notifier_block *nb) +static int fib_table_notify(struct fib_table *tb, struct notifier_block *nb, + struct netlink_ext_ack *extack) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *l, *tp = t->kv; @@ -2049,7 +2054,7 @@ static int fib_table_notify(struct fib_table *tb, struct notifier_block *nb) int err; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { - err = fib_leaf_notify(l, tb, nb); + err = fib_leaf_notify(l, tb, nb, extack); if (err) return err; @@ -2061,7 +2066,8 @@ static int fib_table_notify(struct fib_table *tb, struct notifier_block *nb) return 0; } -int fib_notify(struct net *net, struct notifier_block *nb) +int fib_notify(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { unsigned int h; int err; @@ -2071,7 +2077,7 @@ int fib_notify(struct net *net, struct notifier_block *nb) struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist) { - err = fib_table_notify(tb, nb); + err = fib_table_notify(tb, nb, extack); if (err) return err; } diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 313470f6bb14..051f365b64d2 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -278,9 +278,10 @@ static void __net_exit ipmr_rules_exit(struct net *net) rtnl_unlock(); } -static int ipmr_rules_dump(struct net *net, struct notifier_block *nb) +static int ipmr_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { - return fib_rules_dump(net, nb, RTNL_FAMILY_IPMR); + return fib_rules_dump(net, nb, RTNL_FAMILY_IPMR, extack); } static unsigned int ipmr_rules_seq_read(struct net *net) @@ -336,7 +337,8 @@ static void __net_exit ipmr_rules_exit(struct net *net) rtnl_unlock(); } -static int ipmr_rules_dump(struct net *net, struct notifier_block *nb) +static int ipmr_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { return 0; } @@ -3040,10 +3042,11 @@ static unsigned int ipmr_seq_read(struct net *net) return net->ipv4.ipmr_seq + ipmr_rules_seq_read(net); } -static int ipmr_dump(struct net *net, struct notifier_block *nb) +static int ipmr_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { return mr_dump(net, nb, RTNL_FAMILY_IPMR, ipmr_rules_dump, - ipmr_mr_table_iter, &mrt_lock); + ipmr_mr_table_iter, &mrt_lock, extack); } static const struct fib_notifier_ops ipmr_notifier_ops_template = { diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index c4e23c2a0d5c..aa8738a91210 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -386,15 +386,17 @@ EXPORT_SYMBOL(mr_rtm_dumproute); int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, int (*rules_dump)(struct net *net, - struct notifier_block *nb), + struct notifier_block *nb, + struct netlink_ext_ack *extack), struct mr_table *(*mr_iter)(struct net *net, struct mr_table *mrt), - rwlock_t *mrt_lock) + rwlock_t *mrt_lock, + struct netlink_ext_ack *extack) { struct mr_table *mrt; int err; - err = rules_dump(net, nb); + err = rules_dump(net, nb, extack); if (err) return err; @@ -411,7 +413,7 @@ int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, err = mr_call_vif_notifier(nb, family, FIB_EVENT_VIF_ADD, - v, vifi, mrt->id); + v, vifi, mrt->id, extack); if (err) break; } @@ -424,7 +426,7 @@ int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) { err = mr_call_mfc_notifier(nb, family, FIB_EVENT_ENTRY_ADD, - mfc, mrt->id); + mfc, mrt->id, extack); if (err) return err; } diff --git a/net/ipv6/fib6_notifier.c b/net/ipv6/fib6_notifier.c index 4fe79296999a..f87ae33e1d01 100644 --- a/net/ipv6/fib6_notifier.c +++ b/net/ipv6/fib6_notifier.c @@ -27,15 +27,16 @@ static unsigned int fib6_seq_read(struct net *net) return fib6_tables_seq_read(net) + fib6_rules_seq_read(net); } -static int fib6_dump(struct net *net, struct notifier_block *nb) +static int fib6_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { int err; - err = fib6_rules_dump(net, nb); + err = fib6_rules_dump(net, nb, extack); if (err) return err; - return fib6_tables_dump(net, nb); + return fib6_tables_dump(net, nb, extack); } static const struct fib_notifier_ops fib6_notifier_ops_template = { diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index f9e8fe3ff0c5..fafe556d21e0 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -47,9 +47,10 @@ bool fib6_rule_default(const struct fib_rule *rule) } EXPORT_SYMBOL_GPL(fib6_rule_default); -int fib6_rules_dump(struct net *net, struct notifier_block *nb) +int fib6_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { - return fib_rules_dump(net, nb, AF_INET6); + return fib_rules_dump(net, nb, AF_INET6, extack); } unsigned int fib6_rules_seq_read(struct net *net) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 76124a909395..f66bc2af4e9d 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -359,9 +359,11 @@ unsigned int fib6_tables_seq_read(struct net *net) static int call_fib6_entry_notifier(struct notifier_block *nb, enum fib_event_type event_type, - struct fib6_info *rt) + struct fib6_info *rt, + struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { + .info.extack = extack, .rt = rt, }; @@ -401,13 +403,15 @@ int call_fib6_multipath_entry_notifiers(struct net *net, struct fib6_dump_arg { struct net *net; struct notifier_block *nb; + struct netlink_ext_ack *extack; }; static int fib6_rt_dump(struct fib6_info *rt, struct fib6_dump_arg *arg) { if (rt == arg->net->ipv6.fib6_null_entry) return 0; - return call_fib6_entry_notifier(arg->nb, FIB_EVENT_ENTRY_ADD, rt); + return call_fib6_entry_notifier(arg->nb, FIB_EVENT_ENTRY_ADD, + rt, arg->extack); } static int fib6_node_dump(struct fib6_walker *w) @@ -437,7 +441,8 @@ static int fib6_table_dump(struct net *net, struct fib6_table *tb, } /* Called with rcu_read_lock() */ -int fib6_tables_dump(struct net *net, struct notifier_block *nb) +int fib6_tables_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { struct fib6_dump_arg arg; struct fib6_walker *w; @@ -451,6 +456,7 @@ int fib6_tables_dump(struct net *net, struct notifier_block *nb) w->func = fib6_node_dump; arg.net = net; arg.nb = nb; + arg.extack = extack; w->args = &arg; for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 857a89ad4d6c..bfa49ff70531 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -265,9 +265,10 @@ static void __net_exit ip6mr_rules_exit(struct net *net) rtnl_unlock(); } -static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb) +static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { - return fib_rules_dump(net, nb, RTNL_FAMILY_IP6MR); + return fib_rules_dump(net, nb, RTNL_FAMILY_IP6MR, extack); } static unsigned int ip6mr_rules_seq_read(struct net *net) @@ -324,7 +325,8 @@ static void __net_exit ip6mr_rules_exit(struct net *net) rtnl_unlock(); } -static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb) +static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { return 0; } @@ -1256,10 +1258,11 @@ static unsigned int ip6mr_seq_read(struct net *net) return net->ipv6.ipmr_seq + ip6mr_rules_seq_read(net); } -static int ip6mr_dump(struct net *net, struct notifier_block *nb) +static int ip6mr_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { return mr_dump(net, nb, RTNL_FAMILY_IP6MR, ip6mr_rules_dump, - ip6mr_mr_table_iter, &mrt_lock); + ip6mr_mr_table_iter, &mrt_lock, extack); } static struct notifier_block ip6_mr_notifier = { -- cgit v1.2.3-71-gd317 From 894616f79200f74af6a0426fa20d986b1f45cd9b Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Wed, 2 Oct 2019 10:20:19 -0700 Subject: Input: add input_get_poll_interval() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some drivers need to be able to know the current polling interval for devices working in polling mode, let's allow them fetching it. Acked-By: Benjamin Tissoires Tested-by: Michal Vokáč Signed-off-by: Dmitry Torokhov --- drivers/input/input-poller.c | 9 +++++++++ include/linux/input.h | 1 + 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/drivers/input/input-poller.c b/drivers/input/input-poller.c index 1b3d28964bb2..7d6b4e8879f1 100644 --- a/drivers/input/input-poller.c +++ b/drivers/input/input-poller.c @@ -123,6 +123,15 @@ void input_set_max_poll_interval(struct input_dev *dev, unsigned int interval) } EXPORT_SYMBOL(input_set_max_poll_interval); +int input_get_poll_interval(struct input_dev *dev) +{ + if (!dev->poller) + return -EINVAL; + + return dev->poller->poll_interval; +} +EXPORT_SYMBOL(input_get_poll_interval); + /* SYSFS interface */ static ssize_t input_dev_get_poll_interval(struct device *dev, diff --git a/include/linux/input.h b/include/linux/input.h index 94f277cd806a..56f2fd32e609 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -383,6 +383,7 @@ int input_setup_polling(struct input_dev *dev, void input_set_poll_interval(struct input_dev *dev, unsigned int interval); void input_set_min_poll_interval(struct input_dev *dev, unsigned int interval); void input_set_max_poll_interval(struct input_dev *dev, unsigned int interval); +int input_get_poll_interval(struct input_dev *dev); int __must_check input_register_handler(struct input_handler *); void input_unregister_handler(struct input_handler *); -- cgit v1.2.3-71-gd317 From 01b4c39901e087ceebae2733857248de81476bd8 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 24 Jul 2019 15:22:59 +0200 Subject: nohz: Add TICK_DEP_BIT_RCU If a nohz_full CPU is looping in the kernel, the scheduling-clock tick might nevertheless remain disabled. In !PREEMPT kernels, this can prevent RCU's attempts to enlist the aid of that CPU's executions of cond_resched(), which can in turn result in an arbitrarily delayed grace period and thus an OOM. RCU therefore needs a way to enable a holdout nohz_full CPU's scheduler-clock interrupt. This commit therefore provides a new TICK_DEP_BIT_RCU value which RCU can pass to tick_dep_set_cpu() and friends to force on the scheduler-clock interrupt for a specified CPU or task. In some cases, rcutorture needs to turn on the scheduler-clock tick, so this commit also exports the relevant symbols to GPL-licensed modules. Signed-off-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney --- include/linux/tick.h | 7 ++++++- include/trace/events/timer.h | 3 ++- kernel/time/tick-sched.c | 7 +++++++ 3 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index f92a10b5e112..39eb44564058 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -108,7 +108,8 @@ enum tick_dep_bits { TICK_DEP_BIT_POSIX_TIMER = 0, TICK_DEP_BIT_PERF_EVENTS = 1, TICK_DEP_BIT_SCHED = 2, - TICK_DEP_BIT_CLOCK_UNSTABLE = 3 + TICK_DEP_BIT_CLOCK_UNSTABLE = 3, + TICK_DEP_BIT_RCU = 4 }; #define TICK_DEP_MASK_NONE 0 @@ -116,6 +117,7 @@ enum tick_dep_bits { #define TICK_DEP_MASK_PERF_EVENTS (1 << TICK_DEP_BIT_PERF_EVENTS) #define TICK_DEP_MASK_SCHED (1 << TICK_DEP_BIT_SCHED) #define TICK_DEP_MASK_CLOCK_UNSTABLE (1 << TICK_DEP_BIT_CLOCK_UNSTABLE) +#define TICK_DEP_MASK_RCU (1 << TICK_DEP_BIT_RCU) #ifdef CONFIG_NO_HZ_COMMON extern bool tick_nohz_enabled; @@ -268,6 +270,9 @@ static inline bool tick_nohz_full_enabled(void) { return false; } static inline bool tick_nohz_full_cpu(int cpu) { return false; } static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { } +static inline void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit) { } +static inline void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { } + static inline void tick_dep_set(enum tick_dep_bits bit) { } static inline void tick_dep_clear(enum tick_dep_bits bit) { } static inline void tick_dep_set_cpu(int cpu, enum tick_dep_bits bit) { } diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index b7a904825e7d..295517f109d7 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -367,7 +367,8 @@ TRACE_EVENT(itimer_expire, tick_dep_name(POSIX_TIMER) \ tick_dep_name(PERF_EVENTS) \ tick_dep_name(SCHED) \ - tick_dep_name_end(CLOCK_UNSTABLE) + tick_dep_name(CLOCK_UNSTABLE) \ + tick_dep_name_end(RCU) #undef tick_dep_name #undef tick_dep_mask_name diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 955851748dc3..d1b0a84b6112 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -198,6 +198,11 @@ static bool check_tick_dependency(atomic_t *dep) return true; } + if (val & TICK_DEP_MASK_RCU) { + trace_tick_stop(0, TICK_DEP_MASK_RCU); + return true; + } + return false; } @@ -324,6 +329,7 @@ void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit) preempt_enable(); } } +EXPORT_SYMBOL_GPL(tick_nohz_dep_set_cpu); void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { @@ -331,6 +337,7 @@ void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) atomic_andnot(BIT(bit), &ts->tick_dep_mask); } +EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_cpu); /* * Set a per-task tick dependency. Posix CPU timers need this in order to elapse -- cgit v1.2.3-71-gd317 From 366237e7b0833faa2d8da7a8d7d7da8c3ca802e5 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 10 Jul 2019 08:01:01 -0700 Subject: stop_machine: Provide RCU quiescent state in multi_cpu_stop() When multi_cpu_stop() loops waiting for other tasks, it can trigger an RCU CPU stall warning. This can be misleading because what is instead needed is information on whatever task is blocking multi_cpu_stop(). This commit therefore inserts an RCU quiescent state into the multi_cpu_stop() function's waitloop. Signed-off-by: Paul E. McKenney --- include/linux/rcutree.h | 1 + kernel/rcu/tree.c | 2 +- kernel/stop_machine.c | 1 + 3 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 18b1ed9864b0..c5147de885ec 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -37,6 +37,7 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier(void); bool rcu_eqs_special_set(int cpu); +void rcu_momentary_dyntick_idle(void); unsigned long get_state_synchronize_rcu(void); void cond_synchronize_rcu(unsigned long oldstate); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 238f93b4b0a4..a5c296d202ae 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -364,7 +364,7 @@ bool rcu_eqs_special_set(int cpu) * * The caller must have disabled interrupts and must not be idle. */ -static void __maybe_unused rcu_momentary_dyntick_idle(void) +void rcu_momentary_dyntick_idle(void) { int special; diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index c7031a22aa7b..34c4f117d8c7 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -233,6 +233,7 @@ static int multi_cpu_stop(void *data) */ touch_nmi_watchdog(); } + rcu_momentary_dyntick_idle(); } while (curstate != MULTI_STOP_EXIT); local_irq_restore(flags); -- cgit v1.2.3-71-gd317 From 79ba7ff5a9925f5c170f51ed7a96d1475eb6c27f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 4 Aug 2019 13:17:35 -0700 Subject: rcutorture: Emulate dyntick aspect of userspace nohz_full sojourn During an actual call_rcu() flood, there would be frequent trips to userspace (in-kernel call_rcu() floods must be otherwise housebroken). Userspace execution on nohz_full CPUs implies an RCU dyntick idle/not-idle transition pair, so this commit adds emulation of that pair. Signed-off-by: Paul E. McKenney --- include/linux/rcutiny.h | 1 + kernel/rcu/rcutorture.c | 11 +++++++++++ kernel/rcu/tree.c | 1 + 3 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 9bf1dfe7781f..37b6f0c2b79d 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -84,6 +84,7 @@ static inline void rcu_scheduler_starting(void) { } #endif /* #else #ifndef CONFIG_SRCU */ static inline void rcu_end_inkernel_boot(void) { } static inline bool rcu_is_watching(void) { return true; } +static inline void rcu_momentary_dyntick_idle(void) { } /* Avoid RCU read-side critical sections leaking across. */ static inline void rcu_all_qs(void) { barrier(); } diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index ab61f5c1353b..49ad88765ed2 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -1761,6 +1761,11 @@ static unsigned long rcu_torture_fwd_prog_cbfree(void) kfree(rfcp); freed++; rcu_torture_fwd_prog_cond_resched(freed); + if (tick_nohz_full_enabled()) { + local_irq_save(flags); + rcu_momentary_dyntick_idle(); + local_irq_restore(flags); + } } return freed; } @@ -1835,6 +1840,7 @@ static void rcu_torture_fwd_prog_nr(int *tested, int *tested_tries) static void rcu_torture_fwd_prog_cr(void) { unsigned long cver; + unsigned long flags; unsigned long gps; int i; long n_launders; @@ -1894,6 +1900,11 @@ static void rcu_torture_fwd_prog_cr(void) } cur_ops->call(&rfcp->rh, rcu_torture_fwd_cb_cr); rcu_torture_fwd_prog_cond_resched(n_launders + n_max_cbs); + if (tick_nohz_full_enabled()) { + local_irq_save(flags); + rcu_momentary_dyntick_idle(); + local_irq_restore(flags); + } } stoppedat = jiffies; n_launders_cb_snap = READ_ONCE(n_launders_cb); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 7c67ea561b36..66354ef776aa 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -375,6 +375,7 @@ void rcu_momentary_dyntick_idle(void) WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR)); rcu_preempt_deferred_qs(current); } +EXPORT_SYMBOL_GPL(rcu_momentary_dyntick_idle); /** * rcu_is_cpu_rrupt_from_idle - see if interrupted from idle -- cgit v1.2.3-71-gd317 From 507fd01d5333338753a1cc26322dfc9f856c109f Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Thu, 3 Oct 2019 11:29:12 +0200 Subject: drivers: move the early platform device support to arch/sh SuperH is the only user of the current implementation of early platform device support. We want to introduce a more robust approach to early probing. As the first step - move all the current early platform code to arch/sh. In order not to export internal drivers/base functions to arch code for this temporary solution - copy the two needed routines for driver matching from drivers/base/platform.c to arch/sh/drivers/platform_early.c. Also: call early_platform_cleanup() from subsys_initcall() so that it's called after all early devices are probed. Signed-off-by: Bartosz Golaszewski Cc: Rich Felker Link: https://lore.kernel.org/r/20191003092913.10731-2-brgl@bgdev.pl Signed-off-by: Greg Kroah-Hartman --- arch/sh/drivers/Makefile | 2 +- arch/sh/drivers/platform_early.c | 347 +++++++++++++++++++++++++++++++++ arch/sh/include/asm/platform_early.h | 61 ++++++ arch/sh/kernel/cpu/sh2/setup-sh7619.c | 1 + arch/sh/kernel/cpu/sh2a/setup-mxg.c | 1 + arch/sh/kernel/cpu/sh2a/setup-sh7201.c | 1 + arch/sh/kernel/cpu/sh2a/setup-sh7203.c | 1 + arch/sh/kernel/cpu/sh2a/setup-sh7206.c | 1 + arch/sh/kernel/cpu/sh2a/setup-sh7264.c | 1 + arch/sh/kernel/cpu/sh2a/setup-sh7269.c | 1 + arch/sh/kernel/cpu/sh3/setup-sh3.c | 1 + arch/sh/kernel/cpu/sh3/setup-sh7705.c | 1 + arch/sh/kernel/cpu/sh3/setup-sh770x.c | 1 + arch/sh/kernel/cpu/sh3/setup-sh7710.c | 1 + arch/sh/kernel/cpu/sh3/setup-sh7720.c | 1 + arch/sh/kernel/cpu/sh4/setup-sh4-202.c | 1 + arch/sh/kernel/cpu/sh4/setup-sh7750.c | 1 + arch/sh/kernel/cpu/sh4/setup-sh7760.c | 1 + arch/sh/kernel/cpu/sh4a/setup-sh7343.c | 1 + arch/sh/kernel/cpu/sh4a/setup-sh7366.c | 1 + arch/sh/kernel/cpu/sh4a/setup-sh7722.c | 1 + arch/sh/kernel/cpu/sh4a/setup-sh7723.c | 1 + arch/sh/kernel/cpu/sh4a/setup-sh7724.c | 1 + arch/sh/kernel/cpu/sh4a/setup-sh7734.c | 1 + arch/sh/kernel/cpu/sh4a/setup-sh7757.c | 1 + arch/sh/kernel/cpu/sh4a/setup-sh7763.c | 1 + arch/sh/kernel/cpu/sh4a/setup-sh7770.c | 1 + arch/sh/kernel/cpu/sh4a/setup-sh7780.c | 1 + arch/sh/kernel/cpu/sh4a/setup-sh7785.c | 1 + arch/sh/kernel/cpu/sh4a/setup-sh7786.c | 1 + arch/sh/kernel/cpu/sh4a/setup-shx3.c | 1 + arch/sh/kernel/cpu/sh5/setup-sh5.c | 1 + arch/sh/kernel/setup.c | 1 + arch/sh/kernel/time.c | 1 + drivers/base/platform.c | 288 --------------------------- drivers/clocksource/sh_cmt.c | 7 + drivers/clocksource/sh_mtu2.c | 7 + drivers/clocksource/sh_tmu.c | 8 + drivers/tty/serial/sh-sci.c | 7 +- include/linux/platform_device.h | 64 ++---- 40 files changed, 480 insertions(+), 342 deletions(-) create mode 100644 arch/sh/drivers/platform_early.c create mode 100644 arch/sh/include/asm/platform_early.h (limited to 'include/linux') diff --git a/arch/sh/drivers/Makefile b/arch/sh/drivers/Makefile index 3e93b434e604..56b0acace6e7 100644 --- a/arch/sh/drivers/Makefile +++ b/arch/sh/drivers/Makefile @@ -3,7 +3,7 @@ # Makefile for the Linux SuperH-specific device drivers. # -obj-y += dma/ +obj-y += dma/ platform_early.o obj-$(CONFIG_PCI) += pci/ obj-$(CONFIG_SUPERHYWAY) += superhyway/ diff --git a/arch/sh/drivers/platform_early.c b/arch/sh/drivers/platform_early.c new file mode 100644 index 000000000000..3dfe9f3541bb --- /dev/null +++ b/arch/sh/drivers/platform_early.c @@ -0,0 +1,347 @@ +// SPDX--License-Identifier: GPL-2.0 + +#include +#include +#include + +static __initdata LIST_HEAD(early_platform_driver_list); +static __initdata LIST_HEAD(early_platform_device_list); + +static const struct platform_device_id * +platform_match_id(const struct platform_device_id *id, + struct platform_device *pdev) +{ + while (id->name[0]) { + if (strcmp(pdev->name, id->name) == 0) { + pdev->id_entry = id; + return id; + } + id++; + } + return NULL; +} + +static int platform_match(struct device *dev, struct device_driver *drv) +{ + struct platform_device *pdev = to_platform_device(dev); + struct platform_driver *pdrv = to_platform_driver(drv); + + /* When driver_override is set, only bind to the matching driver */ + if (pdev->driver_override) + return !strcmp(pdev->driver_override, drv->name); + + /* Then try to match against the id table */ + if (pdrv->id_table) + return platform_match_id(pdrv->id_table, pdev) != NULL; + + /* fall-back to driver name match */ + return (strcmp(pdev->name, drv->name) == 0); +} + +#ifdef CONFIG_PM +static void device_pm_init_common(struct device *dev) +{ + if (!dev->power.early_init) { + spin_lock_init(&dev->power.lock); + dev->power.qos = NULL; + dev->power.early_init = true; + } +} + +static void pm_runtime_early_init(struct device *dev) +{ + dev->power.disable_depth = 1; + device_pm_init_common(dev); +} +#else +static void pm_runtime_early_init(struct device *dev) {} +#endif + +/** + * early_platform_driver_register - register early platform driver + * @epdrv: early_platform driver structure + * @buf: string passed from early_param() + * + * Helper function for early_platform_init() / early_platform_init_buffer() + */ +int __init early_platform_driver_register(struct early_platform_driver *epdrv, + char *buf) +{ + char *tmp; + int n; + + /* Simply add the driver to the end of the global list. + * Drivers will by default be put on the list in compiled-in order. + */ + if (!epdrv->list.next) { + INIT_LIST_HEAD(&epdrv->list); + list_add_tail(&epdrv->list, &early_platform_driver_list); + } + + /* If the user has specified device then make sure the driver + * gets prioritized. The driver of the last device specified on + * command line will be put first on the list. + */ + n = strlen(epdrv->pdrv->driver.name); + if (buf && !strncmp(buf, epdrv->pdrv->driver.name, n)) { + list_move(&epdrv->list, &early_platform_driver_list); + + /* Allow passing parameters after device name */ + if (buf[n] == '\0' || buf[n] == ',') + epdrv->requested_id = -1; + else { + epdrv->requested_id = simple_strtoul(&buf[n + 1], + &tmp, 10); + + if (buf[n] != '.' || (tmp == &buf[n + 1])) { + epdrv->requested_id = EARLY_PLATFORM_ID_ERROR; + n = 0; + } else + n += strcspn(&buf[n + 1], ",") + 1; + } + + if (buf[n] == ',') + n++; + + if (epdrv->bufsize) { + memcpy(epdrv->buffer, &buf[n], + min_t(int, epdrv->bufsize, strlen(&buf[n]) + 1)); + epdrv->buffer[epdrv->bufsize - 1] = '\0'; + } + } + + return 0; +} + +/** + * early_platform_add_devices - adds a number of early platform devices + * @devs: array of early platform devices to add + * @num: number of early platform devices in array + * + * Used by early architecture code to register early platform devices and + * their platform data. + */ +void __init early_platform_add_devices(struct platform_device **devs, int num) +{ + struct device *dev; + int i; + + /* simply add the devices to list */ + for (i = 0; i < num; i++) { + dev = &devs[i]->dev; + + if (!dev->devres_head.next) { + pm_runtime_early_init(dev); + INIT_LIST_HEAD(&dev->devres_head); + list_add_tail(&dev->devres_head, + &early_platform_device_list); + } + } +} + +/** + * early_platform_driver_register_all - register early platform drivers + * @class_str: string to identify early platform driver class + * + * Used by architecture code to register all early platform drivers + * for a certain class. If omitted then only early platform drivers + * with matching kernel command line class parameters will be registered. + */ +void __init early_platform_driver_register_all(char *class_str) +{ + /* The "class_str" parameter may or may not be present on the kernel + * command line. If it is present then there may be more than one + * matching parameter. + * + * Since we register our early platform drivers using early_param() + * we need to make sure that they also get registered in the case + * when the parameter is missing from the kernel command line. + * + * We use parse_early_options() to make sure the early_param() gets + * called at least once. The early_param() may be called more than + * once since the name of the preferred device may be specified on + * the kernel command line. early_platform_driver_register() handles + * this case for us. + */ + parse_early_options(class_str); +} + +/** + * early_platform_match - find early platform device matching driver + * @epdrv: early platform driver structure + * @id: id to match against + */ +static struct platform_device * __init +early_platform_match(struct early_platform_driver *epdrv, int id) +{ + struct platform_device *pd; + + list_for_each_entry(pd, &early_platform_device_list, dev.devres_head) + if (platform_match(&pd->dev, &epdrv->pdrv->driver)) + if (pd->id == id) + return pd; + + return NULL; +} + +/** + * early_platform_left - check if early platform driver has matching devices + * @epdrv: early platform driver structure + * @id: return true if id or above exists + */ +static int __init early_platform_left(struct early_platform_driver *epdrv, + int id) +{ + struct platform_device *pd; + + list_for_each_entry(pd, &early_platform_device_list, dev.devres_head) + if (platform_match(&pd->dev, &epdrv->pdrv->driver)) + if (pd->id >= id) + return 1; + + return 0; +} + +/** + * early_platform_driver_probe_id - probe drivers matching class_str and id + * @class_str: string to identify early platform driver class + * @id: id to match against + * @nr_probe: number of platform devices to successfully probe before exiting + */ +static int __init early_platform_driver_probe_id(char *class_str, + int id, + int nr_probe) +{ + struct early_platform_driver *epdrv; + struct platform_device *match; + int match_id; + int n = 0; + int left = 0; + + list_for_each_entry(epdrv, &early_platform_driver_list, list) { + /* only use drivers matching our class_str */ + if (strcmp(class_str, epdrv->class_str)) + continue; + + if (id == -2) { + match_id = epdrv->requested_id; + left = 1; + + } else { + match_id = id; + left += early_platform_left(epdrv, id); + + /* skip requested id */ + switch (epdrv->requested_id) { + case EARLY_PLATFORM_ID_ERROR: + case EARLY_PLATFORM_ID_UNSET: + break; + default: + if (epdrv->requested_id == id) + match_id = EARLY_PLATFORM_ID_UNSET; + } + } + + switch (match_id) { + case EARLY_PLATFORM_ID_ERROR: + pr_warn("%s: unable to parse %s parameter\n", + class_str, epdrv->pdrv->driver.name); + /* fall-through */ + case EARLY_PLATFORM_ID_UNSET: + match = NULL; + break; + default: + match = early_platform_match(epdrv, match_id); + } + + if (match) { + /* + * Set up a sensible init_name to enable + * dev_name() and others to be used before the + * rest of the driver core is initialized. + */ + if (!match->dev.init_name && slab_is_available()) { + if (match->id != -1) + match->dev.init_name = + kasprintf(GFP_KERNEL, "%s.%d", + match->name, + match->id); + else + match->dev.init_name = + kasprintf(GFP_KERNEL, "%s", + match->name); + + if (!match->dev.init_name) + return -ENOMEM; + } + + if (epdrv->pdrv->probe(match)) + pr_warn("%s: unable to probe %s early.\n", + class_str, match->name); + else + n++; + } + + if (n >= nr_probe) + break; + } + + if (left) + return n; + else + return -ENODEV; +} + +/** + * early_platform_driver_probe - probe a class of registered drivers + * @class_str: string to identify early platform driver class + * @nr_probe: number of platform devices to successfully probe before exiting + * @user_only: only probe user specified early platform devices + * + * Used by architecture code to probe registered early platform drivers + * within a certain class. For probe to happen a registered early platform + * device matching a registered early platform driver is needed. + */ +int __init early_platform_driver_probe(char *class_str, + int nr_probe, + int user_only) +{ + int k, n, i; + + n = 0; + for (i = -2; n < nr_probe; i++) { + k = early_platform_driver_probe_id(class_str, i, nr_probe - n); + + if (k < 0) + break; + + n += k; + + if (user_only) + break; + } + + return n; +} + +/** + * early_platform_cleanup - clean up early platform code + */ +static int __init early_platform_cleanup(void) +{ + struct platform_device *pd, *pd2; + + /* clean up the devres list used to chain devices */ + list_for_each_entry_safe(pd, pd2, &early_platform_device_list, + dev.devres_head) { + list_del(&pd->dev.devres_head); + memset(&pd->dev.devres_head, 0, sizeof(pd->dev.devres_head)); + } + + return 0; +} +/* + * This must happen once after all early devices are probed but before probing + * real platform devices. + */ +subsys_initcall(early_platform_cleanup); diff --git a/arch/sh/include/asm/platform_early.h b/arch/sh/include/asm/platform_early.h new file mode 100644 index 000000000000..4590ab757d5f --- /dev/null +++ b/arch/sh/include/asm/platform_early.h @@ -0,0 +1,61 @@ +/* SPDX--License-Identifier: GPL-2.0 */ + +#ifndef __PLATFORM_EARLY__ +#define __PLATFORM_EARLY__ + +#include +#include +#include +#include + +struct early_platform_driver { + const char *class_str; + struct platform_driver *pdrv; + struct list_head list; + int requested_id; + char *buffer; + int bufsize; +}; + +#define EARLY_PLATFORM_ID_UNSET -2 +#define EARLY_PLATFORM_ID_ERROR -3 + +extern int early_platform_driver_register(struct early_platform_driver *epdrv, + char *buf); +extern void early_platform_add_devices(struct platform_device **devs, int num); + +static inline int is_early_platform_device(struct platform_device *pdev) +{ + return !pdev->dev.driver; +} + +extern void early_platform_driver_register_all(char *class_str); +extern int early_platform_driver_probe(char *class_str, + int nr_probe, int user_only); + +#define early_platform_init(class_string, platdrv) \ + early_platform_init_buffer(class_string, platdrv, NULL, 0) + +#ifndef MODULE +#define early_platform_init_buffer(class_string, platdrv, buf, bufsiz) \ +static __initdata struct early_platform_driver early_driver = { \ + .class_str = class_string, \ + .buffer = buf, \ + .bufsize = bufsiz, \ + .pdrv = platdrv, \ + .requested_id = EARLY_PLATFORM_ID_UNSET, \ +}; \ +static int __init early_platform_driver_setup_func(char *buffer) \ +{ \ + return early_platform_driver_register(&early_driver, buffer); \ +} \ +early_param(class_string, early_platform_driver_setup_func) +#else /* MODULE */ +#define early_platform_init_buffer(class_string, platdrv, buf, bufsiz) \ +static inline char *early_platform_driver_setup_func(void) \ +{ \ + return bufsiz ? buf : NULL; \ +} +#endif /* MODULE */ + +#endif /* __PLATFORM_EARLY__ */ diff --git a/arch/sh/kernel/cpu/sh2/setup-sh7619.c b/arch/sh/kernel/cpu/sh2/setup-sh7619.c index f5b6841ef7e1..27d459e8a598 100644 --- a/arch/sh/kernel/cpu/sh2/setup-sh7619.c +++ b/arch/sh/kernel/cpu/sh2/setup-sh7619.c @@ -12,6 +12,7 @@ #include #include #include +#include enum { UNUSED = 0, diff --git a/arch/sh/kernel/cpu/sh2a/setup-mxg.c b/arch/sh/kernel/cpu/sh2a/setup-mxg.c index 52350ad0b0a2..8a19c5754978 100644 --- a/arch/sh/kernel/cpu/sh2a/setup-mxg.c +++ b/arch/sh/kernel/cpu/sh2a/setup-mxg.c @@ -9,6 +9,7 @@ #include #include #include +#include enum { UNUSED = 0, diff --git a/arch/sh/kernel/cpu/sh2a/setup-sh7201.c b/arch/sh/kernel/cpu/sh2a/setup-sh7201.c index b51ed761ae08..d975e4d404bd 100644 --- a/arch/sh/kernel/cpu/sh2a/setup-sh7201.c +++ b/arch/sh/kernel/cpu/sh2a/setup-sh7201.c @@ -11,6 +11,7 @@ #include #include #include +#include enum { UNUSED = 0, diff --git a/arch/sh/kernel/cpu/sh2a/setup-sh7203.c b/arch/sh/kernel/cpu/sh2a/setup-sh7203.c index 89b3e49fc250..318b8cd8d5b7 100644 --- a/arch/sh/kernel/cpu/sh2a/setup-sh7203.c +++ b/arch/sh/kernel/cpu/sh2a/setup-sh7203.c @@ -10,6 +10,7 @@ #include #include #include +#include enum { UNUSED = 0, diff --git a/arch/sh/kernel/cpu/sh2a/setup-sh7206.c b/arch/sh/kernel/cpu/sh2a/setup-sh7206.c index 36ff3a3139da..8e6fae60074a 100644 --- a/arch/sh/kernel/cpu/sh2a/setup-sh7206.c +++ b/arch/sh/kernel/cpu/sh2a/setup-sh7206.c @@ -11,6 +11,7 @@ #include #include #include +#include enum { UNUSED = 0, diff --git a/arch/sh/kernel/cpu/sh2a/setup-sh7264.c b/arch/sh/kernel/cpu/sh2a/setup-sh7264.c index d199618d877c..2d95c9b38330 100644 --- a/arch/sh/kernel/cpu/sh2a/setup-sh7264.c +++ b/arch/sh/kernel/cpu/sh2a/setup-sh7264.c @@ -11,6 +11,7 @@ #include #include #include +#include enum { UNUSED = 0, diff --git a/arch/sh/kernel/cpu/sh2a/setup-sh7269.c b/arch/sh/kernel/cpu/sh2a/setup-sh7269.c index 9095c960b455..ef4ff76cbe9e 100644 --- a/arch/sh/kernel/cpu/sh2a/setup-sh7269.c +++ b/arch/sh/kernel/cpu/sh2a/setup-sh7269.c @@ -12,6 +12,7 @@ #include #include #include +#include enum { UNUSED = 0, diff --git a/arch/sh/kernel/cpu/sh3/setup-sh3.c b/arch/sh/kernel/cpu/sh3/setup-sh3.c index 8058c01cf09d..cf2a3f09fee4 100644 --- a/arch/sh/kernel/cpu/sh3/setup-sh3.c +++ b/arch/sh/kernel/cpu/sh3/setup-sh3.c @@ -8,6 +8,7 @@ #include #include #include +#include /* All SH3 devices are equipped with IRQ0->5 (except sh7708) */ diff --git a/arch/sh/kernel/cpu/sh3/setup-sh7705.c b/arch/sh/kernel/cpu/sh3/setup-sh7705.c index e19d1ce7b6ad..9b34d1f4e797 100644 --- a/arch/sh/kernel/cpu/sh3/setup-sh7705.c +++ b/arch/sh/kernel/cpu/sh3/setup-sh7705.c @@ -14,6 +14,7 @@ #include #include #include +#include enum { UNUSED = 0, diff --git a/arch/sh/kernel/cpu/sh3/setup-sh770x.c b/arch/sh/kernel/cpu/sh3/setup-sh770x.c index 5c5144bee6bc..39f09504bd96 100644 --- a/arch/sh/kernel/cpu/sh3/setup-sh770x.c +++ b/arch/sh/kernel/cpu/sh3/setup-sh770x.c @@ -18,6 +18,7 @@ #include #include #include +#include enum { UNUSED = 0, diff --git a/arch/sh/kernel/cpu/sh3/setup-sh7710.c b/arch/sh/kernel/cpu/sh3/setup-sh7710.c index 4776e2495738..c006c8fcfa0f 100644 --- a/arch/sh/kernel/cpu/sh3/setup-sh7710.c +++ b/arch/sh/kernel/cpu/sh3/setup-sh7710.c @@ -13,6 +13,7 @@ #include #include #include +#include enum { UNUSED = 0, diff --git a/arch/sh/kernel/cpu/sh3/setup-sh7720.c b/arch/sh/kernel/cpu/sh3/setup-sh7720.c index 1d4c34e7b7db..cf2eec9f6abd 100644 --- a/arch/sh/kernel/cpu/sh3/setup-sh7720.c +++ b/arch/sh/kernel/cpu/sh3/setup-sh7720.c @@ -19,6 +19,7 @@ #include #include #include +#include #include static struct resource rtc_resources[] = { diff --git a/arch/sh/kernel/cpu/sh4/setup-sh4-202.c b/arch/sh/kernel/cpu/sh4/setup-sh4-202.c index a40ef35d101a..2480ce4a3b1e 100644 --- a/arch/sh/kernel/cpu/sh4/setup-sh4-202.c +++ b/arch/sh/kernel/cpu/sh4/setup-sh4-202.c @@ -12,6 +12,7 @@ #include #include #include +#include static struct plat_sci_port scif0_platform_data = { .scscr = SCSCR_REIE, diff --git a/arch/sh/kernel/cpu/sh4/setup-sh7750.c b/arch/sh/kernel/cpu/sh4/setup-sh7750.c index b37bda66a532..4592d660b942 100644 --- a/arch/sh/kernel/cpu/sh4/setup-sh7750.c +++ b/arch/sh/kernel/cpu/sh4/setup-sh7750.c @@ -13,6 +13,7 @@ #include #include #include +#include static struct resource rtc_resources[] = { [0] = { diff --git a/arch/sh/kernel/cpu/sh4/setup-sh7760.c b/arch/sh/kernel/cpu/sh4/setup-sh7760.c index 86845da85997..e64eb96e3589 100644 --- a/arch/sh/kernel/cpu/sh4/setup-sh7760.c +++ b/arch/sh/kernel/cpu/sh4/setup-sh7760.c @@ -11,6 +11,7 @@ #include #include #include +#include enum { UNUSED = 0, diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7343.c b/arch/sh/kernel/cpu/sh4a/setup-sh7343.c index a15e25690b5f..0fa56128bdca 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7343.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7343.c @@ -12,6 +12,7 @@ #include #include #include +#include /* Serial */ static struct plat_sci_port scif0_platform_data = { diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7366.c b/arch/sh/kernel/cpu/sh4a/setup-sh7366.c index 7bd2776441ba..9f2f75285ec3 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7366.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7366.c @@ -15,6 +15,7 @@ #include #include #include +#include static struct plat_sci_port scif0_platform_data = { .scscr = SCSCR_REIE, diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7722.c b/arch/sh/kernel/cpu/sh4a/setup-sh7722.c index 1ce65f88f060..8e5eaac789a7 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7722.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7722.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7723.c b/arch/sh/kernel/cpu/sh4a/setup-sh7723.c index edb649950662..b4b54aa0c267 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7723.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7723.c @@ -16,6 +16,7 @@ #include #include #include +#include #include /* Serial */ diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7724.c b/arch/sh/kernel/cpu/sh4a/setup-sh7724.c index 3e9825031d3d..ec237ab112cf 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7724.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7724.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7734.c b/arch/sh/kernel/cpu/sh4a/setup-sh7734.c index 06a91569697a..7ea9a8b43955 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7734.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7734.c @@ -18,6 +18,7 @@ #include #include #include +#include #include /* SCIF */ diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7757.c b/arch/sh/kernel/cpu/sh4a/setup-sh7757.c index 2501ce656511..922d9886be18 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7757.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7757.c @@ -19,6 +19,7 @@ #include #include #include +#include static struct plat_sci_port scif2_platform_data = { .scscr = SCSCR_REIE, diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7763.c b/arch/sh/kernel/cpu/sh4a/setup-sh7763.c index 419c5efe4a17..8725d4751baf 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7763.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7763.c @@ -14,6 +14,7 @@ #include #include #include +#include static struct plat_sci_port scif0_platform_data = { .scscr = SCSCR_REIE, diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7770.c b/arch/sh/kernel/cpu/sh4a/setup-sh7770.c index 5fb4cf9b58c6..035a0d4f2a2e 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7770.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7770.c @@ -11,6 +11,7 @@ #include #include #include +#include static struct plat_sci_port scif0_platform_data = { .scscr = SCSCR_REIE | SCSCR_TOIE, diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7780.c b/arch/sh/kernel/cpu/sh4a/setup-sh7780.c index ab7d6b715865..983be87cb7be 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7780.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7780.c @@ -13,6 +13,7 @@ #include #include #include +#include static struct plat_sci_port scif0_platform_data = { .scscr = SCSCR_REIE | SCSCR_CKE1, diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7785.c b/arch/sh/kernel/cpu/sh4a/setup-sh7785.c index a438da47285d..bb0cb710c16e 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7785.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7785.c @@ -14,6 +14,7 @@ #include #include #include +#include #include static struct plat_sci_port scif0_platform_data = { diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7786.c b/arch/sh/kernel/cpu/sh4a/setup-sh7786.c index d894165a0ef6..b5d94366eed3 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7786.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7786.c @@ -23,6 +23,7 @@ #include #include #include +#include static struct plat_sci_port scif0_platform_data = { .scscr = SCSCR_REIE | SCSCR_CKE1, diff --git a/arch/sh/kernel/cpu/sh4a/setup-shx3.c b/arch/sh/kernel/cpu/sh4a/setup-shx3.c index 14aa4552bc45..e82398d80b74 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-shx3.c +++ b/arch/sh/kernel/cpu/sh4a/setup-shx3.c @@ -14,6 +14,7 @@ #include #include #include +#include /* * This intentionally only registers SCIF ports 0, 1, and 3. SCIF 2 diff --git a/arch/sh/kernel/cpu/sh5/setup-sh5.c b/arch/sh/kernel/cpu/sh5/setup-sh5.c index 41c1673afc0b..584a6aeeca26 100644 --- a/arch/sh/kernel/cpu/sh5/setup-sh5.c +++ b/arch/sh/kernel/cpu/sh5/setup-sh5.c @@ -12,6 +12,7 @@ #include #include #include +#include static struct plat_sci_port scif0_platform_data = { .flags = UPF_IOREMAP, diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index 2c0e0f37a318..e535507851e1 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -44,6 +44,7 @@ #include #include #include +#include /* * Initialize loops_per_jiffy as 10000000 (1000MIPS). diff --git a/arch/sh/kernel/time.c b/arch/sh/kernel/time.c index e16b2cd269a3..8ad9fd5c4ff6 100644 --- a/arch/sh/kernel/time.c +++ b/arch/sh/kernel/time.c @@ -18,6 +18,7 @@ #include #include #include +#include static void __init sh_late_time_init(void) { diff --git a/drivers/base/platform.c b/drivers/base/platform.c index b6c6c7d97d5b..be1e67ee3af6 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -1264,8 +1264,6 @@ int __init platform_bus_init(void) { int error; - early_platform_cleanup(); - error = device_register(&platform_bus); if (error) { put_device(&platform_bus); @@ -1277,289 +1275,3 @@ int __init platform_bus_init(void) of_platform_register_reconfig_notifier(); return error; } - -static __initdata LIST_HEAD(early_platform_driver_list); -static __initdata LIST_HEAD(early_platform_device_list); - -/** - * early_platform_driver_register - register early platform driver - * @epdrv: early_platform driver structure - * @buf: string passed from early_param() - * - * Helper function for early_platform_init() / early_platform_init_buffer() - */ -int __init early_platform_driver_register(struct early_platform_driver *epdrv, - char *buf) -{ - char *tmp; - int n; - - /* Simply add the driver to the end of the global list. - * Drivers will by default be put on the list in compiled-in order. - */ - if (!epdrv->list.next) { - INIT_LIST_HEAD(&epdrv->list); - list_add_tail(&epdrv->list, &early_platform_driver_list); - } - - /* If the user has specified device then make sure the driver - * gets prioritized. The driver of the last device specified on - * command line will be put first on the list. - */ - n = strlen(epdrv->pdrv->driver.name); - if (buf && !strncmp(buf, epdrv->pdrv->driver.name, n)) { - list_move(&epdrv->list, &early_platform_driver_list); - - /* Allow passing parameters after device name */ - if (buf[n] == '\0' || buf[n] == ',') - epdrv->requested_id = -1; - else { - epdrv->requested_id = simple_strtoul(&buf[n + 1], - &tmp, 10); - - if (buf[n] != '.' || (tmp == &buf[n + 1])) { - epdrv->requested_id = EARLY_PLATFORM_ID_ERROR; - n = 0; - } else - n += strcspn(&buf[n + 1], ",") + 1; - } - - if (buf[n] == ',') - n++; - - if (epdrv->bufsize) { - memcpy(epdrv->buffer, &buf[n], - min_t(int, epdrv->bufsize, strlen(&buf[n]) + 1)); - epdrv->buffer[epdrv->bufsize - 1] = '\0'; - } - } - - return 0; -} - -/** - * early_platform_add_devices - adds a number of early platform devices - * @devs: array of early platform devices to add - * @num: number of early platform devices in array - * - * Used by early architecture code to register early platform devices and - * their platform data. - */ -void __init early_platform_add_devices(struct platform_device **devs, int num) -{ - struct device *dev; - int i; - - /* simply add the devices to list */ - for (i = 0; i < num; i++) { - dev = &devs[i]->dev; - - if (!dev->devres_head.next) { - pm_runtime_early_init(dev); - INIT_LIST_HEAD(&dev->devres_head); - list_add_tail(&dev->devres_head, - &early_platform_device_list); - } - } -} - -/** - * early_platform_driver_register_all - register early platform drivers - * @class_str: string to identify early platform driver class - * - * Used by architecture code to register all early platform drivers - * for a certain class. If omitted then only early platform drivers - * with matching kernel command line class parameters will be registered. - */ -void __init early_platform_driver_register_all(char *class_str) -{ - /* The "class_str" parameter may or may not be present on the kernel - * command line. If it is present then there may be more than one - * matching parameter. - * - * Since we register our early platform drivers using early_param() - * we need to make sure that they also get registered in the case - * when the parameter is missing from the kernel command line. - * - * We use parse_early_options() to make sure the early_param() gets - * called at least once. The early_param() may be called more than - * once since the name of the preferred device may be specified on - * the kernel command line. early_platform_driver_register() handles - * this case for us. - */ - parse_early_options(class_str); -} - -/** - * early_platform_match - find early platform device matching driver - * @epdrv: early platform driver structure - * @id: id to match against - */ -static struct platform_device * __init -early_platform_match(struct early_platform_driver *epdrv, int id) -{ - struct platform_device *pd; - - list_for_each_entry(pd, &early_platform_device_list, dev.devres_head) - if (platform_match(&pd->dev, &epdrv->pdrv->driver)) - if (pd->id == id) - return pd; - - return NULL; -} - -/** - * early_platform_left - check if early platform driver has matching devices - * @epdrv: early platform driver structure - * @id: return true if id or above exists - */ -static int __init early_platform_left(struct early_platform_driver *epdrv, - int id) -{ - struct platform_device *pd; - - list_for_each_entry(pd, &early_platform_device_list, dev.devres_head) - if (platform_match(&pd->dev, &epdrv->pdrv->driver)) - if (pd->id >= id) - return 1; - - return 0; -} - -/** - * early_platform_driver_probe_id - probe drivers matching class_str and id - * @class_str: string to identify early platform driver class - * @id: id to match against - * @nr_probe: number of platform devices to successfully probe before exiting - */ -static int __init early_platform_driver_probe_id(char *class_str, - int id, - int nr_probe) -{ - struct early_platform_driver *epdrv; - struct platform_device *match; - int match_id; - int n = 0; - int left = 0; - - list_for_each_entry(epdrv, &early_platform_driver_list, list) { - /* only use drivers matching our class_str */ - if (strcmp(class_str, epdrv->class_str)) - continue; - - if (id == -2) { - match_id = epdrv->requested_id; - left = 1; - - } else { - match_id = id; - left += early_platform_left(epdrv, id); - - /* skip requested id */ - switch (epdrv->requested_id) { - case EARLY_PLATFORM_ID_ERROR: - case EARLY_PLATFORM_ID_UNSET: - break; - default: - if (epdrv->requested_id == id) - match_id = EARLY_PLATFORM_ID_UNSET; - } - } - - switch (match_id) { - case EARLY_PLATFORM_ID_ERROR: - pr_warn("%s: unable to parse %s parameter\n", - class_str, epdrv->pdrv->driver.name); - /* fall-through */ - case EARLY_PLATFORM_ID_UNSET: - match = NULL; - break; - default: - match = early_platform_match(epdrv, match_id); - } - - if (match) { - /* - * Set up a sensible init_name to enable - * dev_name() and others to be used before the - * rest of the driver core is initialized. - */ - if (!match->dev.init_name && slab_is_available()) { - if (match->id != -1) - match->dev.init_name = - kasprintf(GFP_KERNEL, "%s.%d", - match->name, - match->id); - else - match->dev.init_name = - kasprintf(GFP_KERNEL, "%s", - match->name); - - if (!match->dev.init_name) - return -ENOMEM; - } - - if (epdrv->pdrv->probe(match)) - pr_warn("%s: unable to probe %s early.\n", - class_str, match->name); - else - n++; - } - - if (n >= nr_probe) - break; - } - - if (left) - return n; - else - return -ENODEV; -} - -/** - * early_platform_driver_probe - probe a class of registered drivers - * @class_str: string to identify early platform driver class - * @nr_probe: number of platform devices to successfully probe before exiting - * @user_only: only probe user specified early platform devices - * - * Used by architecture code to probe registered early platform drivers - * within a certain class. For probe to happen a registered early platform - * device matching a registered early platform driver is needed. - */ -int __init early_platform_driver_probe(char *class_str, - int nr_probe, - int user_only) -{ - int k, n, i; - - n = 0; - for (i = -2; n < nr_probe; i++) { - k = early_platform_driver_probe_id(class_str, i, nr_probe - n); - - if (k < 0) - break; - - n += k; - - if (user_only) - break; - } - - return n; -} - -/** - * early_platform_cleanup - clean up early platform code - */ -void __init early_platform_cleanup(void) -{ - struct platform_device *pd, *pd2; - - /* clean up the devres list used to chain devices */ - list_for_each_entry_safe(pd, pd2, &early_platform_device_list, - dev.devres_head) { - list_del(&pd->dev.devres_head); - memset(&pd->dev.devres_head, 0, sizeof(pd->dev.devres_head)); - } -} - diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c index ef773db080e9..3a185485300e 100644 --- a/drivers/clocksource/sh_cmt.c +++ b/drivers/clocksource/sh_cmt.c @@ -25,6 +25,10 @@ #include #include +#ifdef CONFIG_SUPERH +#include +#endif + struct sh_cmt_device; /* @@ -1109,7 +1113,10 @@ static void __exit sh_cmt_exit(void) platform_driver_unregister(&sh_cmt_device_driver); } +#ifdef CONFIG_SUPERH early_platform_init("earlytimer", &sh_cmt_device_driver); +#endif + subsys_initcall(sh_cmt_init); module_exit(sh_cmt_exit); diff --git a/drivers/clocksource/sh_mtu2.c b/drivers/clocksource/sh_mtu2.c index 354b27d14a19..d581060d33a2 100644 --- a/drivers/clocksource/sh_mtu2.c +++ b/drivers/clocksource/sh_mtu2.c @@ -23,6 +23,10 @@ #include #include +#ifdef CONFIG_SUPERH +#include +#endif + struct sh_mtu2_device; struct sh_mtu2_channel { @@ -511,7 +515,10 @@ static void __exit sh_mtu2_exit(void) platform_driver_unregister(&sh_mtu2_device_driver); } +#ifdef CONFIG_SUPERH early_platform_init("earlytimer", &sh_mtu2_device_driver); +#endif + subsys_initcall(sh_mtu2_init); module_exit(sh_mtu2_exit); diff --git a/drivers/clocksource/sh_tmu.c b/drivers/clocksource/sh_tmu.c index 8c4f3753b36e..50e30ead050e 100644 --- a/drivers/clocksource/sh_tmu.c +++ b/drivers/clocksource/sh_tmu.c @@ -24,6 +24,10 @@ #include #include +#ifdef CONFIG_SUPERH +#include +#endif + enum sh_tmu_model { SH_TMU, SH_TMU_SH3, @@ -615,6 +619,7 @@ static int sh_tmu_probe(struct platform_device *pdev) pm_runtime_idle(&pdev->dev); return ret; } + if (is_early_platform_device(pdev)) return 0; @@ -665,7 +670,10 @@ static void __exit sh_tmu_exit(void) platform_driver_unregister(&sh_tmu_device_driver); } +#ifdef CONFIG_SUPERH early_platform_init("earlytimer", &sh_tmu_device_driver); +#endif + subsys_initcall(sh_tmu_init); module_exit(sh_tmu_exit); diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 4e754a4850e6..2a645fd7f07b 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -54,6 +54,7 @@ #ifdef CONFIG_SUPERH #include +#include #endif #include "serial_mctrl_gpio.h" @@ -3086,6 +3087,7 @@ static struct console serial_console = { .data = &sci_uart_driver, }; +#ifdef CONFIG_SUPERH static struct console early_serial_console = { .name = "early_ttySC", .write = serial_console_write, @@ -3114,6 +3116,7 @@ static int sci_probe_earlyprintk(struct platform_device *pdev) register_console(&early_serial_console); return 0; } +#endif #define SCI_CONSOLE (&serial_console) @@ -3314,8 +3317,10 @@ static int sci_probe(struct platform_device *dev) * the special early probe. We don't have sufficient device state * to make it beyond this yet. */ +#ifdef CONFIG_SUPERH if (is_early_platform_device(dev)) return sci_probe_earlyprintk(dev); +#endif if (dev->dev.of_node) { p = sci_parse_dt(dev, &dev_id); @@ -3410,7 +3415,7 @@ static void __exit sci_exit(void) uart_unregister_driver(&sci_uart_driver); } -#ifdef CONFIG_SERIAL_SH_SCI_CONSOLE +#if defined(CONFIG_SUPERH) && defined(CONFIG_SERIAL_SH_SCI_CONSOLE) early_platform_init_buffer("earlyprintk", &sci_driver, early_serial_buf, ARRAY_SIZE(early_serial_buf)); #endif diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 1b5cec067533..85aa28a041a9 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -292,58 +292,6 @@ void platform_unregister_drivers(struct platform_driver * const *drivers, #define platform_register_drivers(drivers, count) \ __platform_register_drivers(drivers, count, THIS_MODULE) -/* early platform driver interface */ -struct early_platform_driver { - const char *class_str; - struct platform_driver *pdrv; - struct list_head list; - int requested_id; - char *buffer; - int bufsize; -}; - -#define EARLY_PLATFORM_ID_UNSET -2 -#define EARLY_PLATFORM_ID_ERROR -3 - -extern int early_platform_driver_register(struct early_platform_driver *epdrv, - char *buf); -extern void early_platform_add_devices(struct platform_device **devs, int num); - -static inline int is_early_platform_device(struct platform_device *pdev) -{ - return !pdev->dev.driver; -} - -extern void early_platform_driver_register_all(char *class_str); -extern int early_platform_driver_probe(char *class_str, - int nr_probe, int user_only); -extern void early_platform_cleanup(void); - -#define early_platform_init(class_string, platdrv) \ - early_platform_init_buffer(class_string, platdrv, NULL, 0) - -#ifndef MODULE -#define early_platform_init_buffer(class_string, platdrv, buf, bufsiz) \ -static __initdata struct early_platform_driver early_driver = { \ - .class_str = class_string, \ - .buffer = buf, \ - .bufsize = bufsiz, \ - .pdrv = platdrv, \ - .requested_id = EARLY_PLATFORM_ID_UNSET, \ -}; \ -static int __init early_platform_driver_setup_func(char *buffer) \ -{ \ - return early_platform_driver_register(&early_driver, buffer); \ -} \ -early_param(class_string, early_platform_driver_setup_func) -#else /* MODULE */ -#define early_platform_init_buffer(class_string, platdrv, buf, bufsiz) \ -static inline char *early_platform_driver_setup_func(void) \ -{ \ - return bufsiz ? buf : NULL; \ -} -#endif /* MODULE */ - #ifdef CONFIG_SUSPEND extern int platform_pm_suspend(struct device *dev); extern int platform_pm_resume(struct device *dev); @@ -378,4 +326,16 @@ extern int platform_dma_configure(struct device *dev); #define USE_PLATFORM_PM_SLEEP_OPS #endif +#ifndef CONFIG_SUPERH +/* + * REVISIT: This stub is needed for all non-SuperH users of early platform + * drivers. It should go away once we introduce the new platform_device-based + * early driver framework. + */ +static inline int is_early_platform_device(struct platform_device *pdev) +{ + return 0; +} +#endif /* CONFIG_SUPERH */ + #endif /* _PLATFORM_DEVICE_H_ */ -- cgit v1.2.3-71-gd317 From 201e91091b1d47047f55580b5474e1239f4d17aa Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Thu, 3 Oct 2019 11:29:13 +0200 Subject: sh: add the sh_ prefix to early platform symbols Old early platform device support is now sh-specific. Before moving on to implementing new early platform framework based on real platform devices, prefix all early platform symbols with 'sh_'. Signed-off-by: Bartosz Golaszewski Cc: Rich Felker Link: https://lore.kernel.org/r/20191003092913.10731-3-brgl@bgdev.pl Signed-off-by: Greg Kroah-Hartman --- arch/sh/drivers/platform_early.c | 66 +++++++++++++++++----------------- arch/sh/include/asm/platform_early.h | 30 ++++++++-------- arch/sh/kernel/cpu/sh2/setup-sh7619.c | 2 +- arch/sh/kernel/cpu/sh2a/setup-mxg.c | 2 +- arch/sh/kernel/cpu/sh2a/setup-sh7201.c | 2 +- arch/sh/kernel/cpu/sh2a/setup-sh7203.c | 2 +- arch/sh/kernel/cpu/sh2a/setup-sh7206.c | 2 +- arch/sh/kernel/cpu/sh2a/setup-sh7264.c | 2 +- arch/sh/kernel/cpu/sh2a/setup-sh7269.c | 2 +- arch/sh/kernel/cpu/sh3/setup-sh7705.c | 2 +- arch/sh/kernel/cpu/sh3/setup-sh770x.c | 2 +- arch/sh/kernel/cpu/sh3/setup-sh7710.c | 2 +- arch/sh/kernel/cpu/sh3/setup-sh7720.c | 2 +- arch/sh/kernel/cpu/sh4/setup-sh4-202.c | 2 +- arch/sh/kernel/cpu/sh4/setup-sh7750.c | 8 ++--- arch/sh/kernel/cpu/sh4/setup-sh7760.c | 2 +- arch/sh/kernel/cpu/sh4a/setup-sh7343.c | 2 +- arch/sh/kernel/cpu/sh4a/setup-sh7366.c | 2 +- arch/sh/kernel/cpu/sh4a/setup-sh7722.c | 2 +- arch/sh/kernel/cpu/sh4a/setup-sh7723.c | 2 +- arch/sh/kernel/cpu/sh4a/setup-sh7724.c | 2 +- arch/sh/kernel/cpu/sh4a/setup-sh7734.c | 2 +- arch/sh/kernel/cpu/sh4a/setup-sh7757.c | 2 +- arch/sh/kernel/cpu/sh4a/setup-sh7763.c | 2 +- arch/sh/kernel/cpu/sh4a/setup-sh7770.c | 2 +- arch/sh/kernel/cpu/sh4a/setup-sh7780.c | 2 +- arch/sh/kernel/cpu/sh4a/setup-sh7785.c | 2 +- arch/sh/kernel/cpu/sh4a/setup-sh7786.c | 2 +- arch/sh/kernel/cpu/sh4a/setup-shx3.c | 2 +- arch/sh/kernel/cpu/sh5/setup-sh5.c | 2 +- arch/sh/kernel/setup.c | 2 +- arch/sh/kernel/time.c | 4 +-- drivers/clocksource/sh_cmt.c | 6 ++-- drivers/clocksource/sh_mtu2.c | 6 ++-- drivers/clocksource/sh_tmu.c | 6 ++-- drivers/tty/serial/sh-sci.c | 4 +-- include/linux/platform_device.h | 2 +- 37 files changed, 94 insertions(+), 94 deletions(-) (limited to 'include/linux') diff --git a/arch/sh/drivers/platform_early.c b/arch/sh/drivers/platform_early.c index 3dfe9f3541bb..f6d148451dfc 100644 --- a/arch/sh/drivers/platform_early.c +++ b/arch/sh/drivers/platform_early.c @@ -4,8 +4,8 @@ #include #include -static __initdata LIST_HEAD(early_platform_driver_list); -static __initdata LIST_HEAD(early_platform_device_list); +static __initdata LIST_HEAD(sh_early_platform_driver_list); +static __initdata LIST_HEAD(sh_early_platform_device_list); static const struct platform_device_id * platform_match_id(const struct platform_device_id *id, @@ -58,13 +58,13 @@ static void pm_runtime_early_init(struct device *dev) {} #endif /** - * early_platform_driver_register - register early platform driver - * @epdrv: early_platform driver structure + * sh_early_platform_driver_register - register early platform driver + * @epdrv: sh_early_platform driver structure * @buf: string passed from early_param() * - * Helper function for early_platform_init() / early_platform_init_buffer() + * Helper function for sh_early_platform_init() / sh_early_platform_init_buffer() */ -int __init early_platform_driver_register(struct early_platform_driver *epdrv, +int __init sh_early_platform_driver_register(struct sh_early_platform_driver *epdrv, char *buf) { char *tmp; @@ -75,7 +75,7 @@ int __init early_platform_driver_register(struct early_platform_driver *epdrv, */ if (!epdrv->list.next) { INIT_LIST_HEAD(&epdrv->list); - list_add_tail(&epdrv->list, &early_platform_driver_list); + list_add_tail(&epdrv->list, &sh_early_platform_driver_list); } /* If the user has specified device then make sure the driver @@ -84,7 +84,7 @@ int __init early_platform_driver_register(struct early_platform_driver *epdrv, */ n = strlen(epdrv->pdrv->driver.name); if (buf && !strncmp(buf, epdrv->pdrv->driver.name, n)) { - list_move(&epdrv->list, &early_platform_driver_list); + list_move(&epdrv->list, &sh_early_platform_driver_list); /* Allow passing parameters after device name */ if (buf[n] == '\0' || buf[n] == ',') @@ -114,14 +114,14 @@ int __init early_platform_driver_register(struct early_platform_driver *epdrv, } /** - * early_platform_add_devices - adds a number of early platform devices + * sh_early_platform_add_devices - adds a number of early platform devices * @devs: array of early platform devices to add * @num: number of early platform devices in array * * Used by early architecture code to register early platform devices and * their platform data. */ -void __init early_platform_add_devices(struct platform_device **devs, int num) +void __init sh_early_platform_add_devices(struct platform_device **devs, int num) { struct device *dev; int i; @@ -134,20 +134,20 @@ void __init early_platform_add_devices(struct platform_device **devs, int num) pm_runtime_early_init(dev); INIT_LIST_HEAD(&dev->devres_head); list_add_tail(&dev->devres_head, - &early_platform_device_list); + &sh_early_platform_device_list); } } } /** - * early_platform_driver_register_all - register early platform drivers + * sh_early_platform_driver_register_all - register early platform drivers * @class_str: string to identify early platform driver class * * Used by architecture code to register all early platform drivers * for a certain class. If omitted then only early platform drivers * with matching kernel command line class parameters will be registered. */ -void __init early_platform_driver_register_all(char *class_str) +void __init sh_early_platform_driver_register_all(char *class_str) { /* The "class_str" parameter may or may not be present on the kernel * command line. If it is present then there may be more than one @@ -160,23 +160,23 @@ void __init early_platform_driver_register_all(char *class_str) * We use parse_early_options() to make sure the early_param() gets * called at least once. The early_param() may be called more than * once since the name of the preferred device may be specified on - * the kernel command line. early_platform_driver_register() handles + * the kernel command line. sh_early_platform_driver_register() handles * this case for us. */ parse_early_options(class_str); } /** - * early_platform_match - find early platform device matching driver + * sh_early_platform_match - find early platform device matching driver * @epdrv: early platform driver structure * @id: id to match against */ static struct platform_device * __init -early_platform_match(struct early_platform_driver *epdrv, int id) +sh_early_platform_match(struct sh_early_platform_driver *epdrv, int id) { struct platform_device *pd; - list_for_each_entry(pd, &early_platform_device_list, dev.devres_head) + list_for_each_entry(pd, &sh_early_platform_device_list, dev.devres_head) if (platform_match(&pd->dev, &epdrv->pdrv->driver)) if (pd->id == id) return pd; @@ -185,16 +185,16 @@ early_platform_match(struct early_platform_driver *epdrv, int id) } /** - * early_platform_left - check if early platform driver has matching devices + * sh_early_platform_left - check if early platform driver has matching devices * @epdrv: early platform driver structure * @id: return true if id or above exists */ -static int __init early_platform_left(struct early_platform_driver *epdrv, +static int __init sh_early_platform_left(struct sh_early_platform_driver *epdrv, int id) { struct platform_device *pd; - list_for_each_entry(pd, &early_platform_device_list, dev.devres_head) + list_for_each_entry(pd, &sh_early_platform_device_list, dev.devres_head) if (platform_match(&pd->dev, &epdrv->pdrv->driver)) if (pd->id >= id) return 1; @@ -203,22 +203,22 @@ static int __init early_platform_left(struct early_platform_driver *epdrv, } /** - * early_platform_driver_probe_id - probe drivers matching class_str and id + * sh_early_platform_driver_probe_id - probe drivers matching class_str and id * @class_str: string to identify early platform driver class * @id: id to match against * @nr_probe: number of platform devices to successfully probe before exiting */ -static int __init early_platform_driver_probe_id(char *class_str, +static int __init sh_early_platform_driver_probe_id(char *class_str, int id, int nr_probe) { - struct early_platform_driver *epdrv; + struct sh_early_platform_driver *epdrv; struct platform_device *match; int match_id; int n = 0; int left = 0; - list_for_each_entry(epdrv, &early_platform_driver_list, list) { + list_for_each_entry(epdrv, &sh_early_platform_driver_list, list) { /* only use drivers matching our class_str */ if (strcmp(class_str, epdrv->class_str)) continue; @@ -229,7 +229,7 @@ static int __init early_platform_driver_probe_id(char *class_str, } else { match_id = id; - left += early_platform_left(epdrv, id); + left += sh_early_platform_left(epdrv, id); /* skip requested id */ switch (epdrv->requested_id) { @@ -251,7 +251,7 @@ static int __init early_platform_driver_probe_id(char *class_str, match = NULL; break; default: - match = early_platform_match(epdrv, match_id); + match = sh_early_platform_match(epdrv, match_id); } if (match) { @@ -293,7 +293,7 @@ static int __init early_platform_driver_probe_id(char *class_str, } /** - * early_platform_driver_probe - probe a class of registered drivers + * sh_early_platform_driver_probe - probe a class of registered drivers * @class_str: string to identify early platform driver class * @nr_probe: number of platform devices to successfully probe before exiting * @user_only: only probe user specified early platform devices @@ -302,7 +302,7 @@ static int __init early_platform_driver_probe_id(char *class_str, * within a certain class. For probe to happen a registered early platform * device matching a registered early platform driver is needed. */ -int __init early_platform_driver_probe(char *class_str, +int __init sh_early_platform_driver_probe(char *class_str, int nr_probe, int user_only) { @@ -310,7 +310,7 @@ int __init early_platform_driver_probe(char *class_str, n = 0; for (i = -2; n < nr_probe; i++) { - k = early_platform_driver_probe_id(class_str, i, nr_probe - n); + k = sh_early_platform_driver_probe_id(class_str, i, nr_probe - n); if (k < 0) break; @@ -325,14 +325,14 @@ int __init early_platform_driver_probe(char *class_str, } /** - * early_platform_cleanup - clean up early platform code + * sh_early_platform_cleanup - clean up early platform code */ -static int __init early_platform_cleanup(void) +static int __init sh_early_platform_cleanup(void) { struct platform_device *pd, *pd2; /* clean up the devres list used to chain devices */ - list_for_each_entry_safe(pd, pd2, &early_platform_device_list, + list_for_each_entry_safe(pd, pd2, &sh_early_platform_device_list, dev.devres_head) { list_del(&pd->dev.devres_head); memset(&pd->dev.devres_head, 0, sizeof(pd->dev.devres_head)); @@ -344,4 +344,4 @@ static int __init early_platform_cleanup(void) * This must happen once after all early devices are probed but before probing * real platform devices. */ -subsys_initcall(early_platform_cleanup); +subsys_initcall(sh_early_platform_cleanup); diff --git a/arch/sh/include/asm/platform_early.h b/arch/sh/include/asm/platform_early.h index 4590ab757d5f..fc802137c37d 100644 --- a/arch/sh/include/asm/platform_early.h +++ b/arch/sh/include/asm/platform_early.h @@ -8,7 +8,7 @@ #include #include -struct early_platform_driver { +struct sh_early_platform_driver { const char *class_str; struct platform_driver *pdrv; struct list_head list; @@ -20,39 +20,39 @@ struct early_platform_driver { #define EARLY_PLATFORM_ID_UNSET -2 #define EARLY_PLATFORM_ID_ERROR -3 -extern int early_platform_driver_register(struct early_platform_driver *epdrv, +extern int sh_early_platform_driver_register(struct sh_early_platform_driver *epdrv, char *buf); -extern void early_platform_add_devices(struct platform_device **devs, int num); +extern void sh_early_platform_add_devices(struct platform_device **devs, int num); -static inline int is_early_platform_device(struct platform_device *pdev) +static inline int is_sh_early_platform_device(struct platform_device *pdev) { return !pdev->dev.driver; } -extern void early_platform_driver_register_all(char *class_str); -extern int early_platform_driver_probe(char *class_str, +extern void sh_early_platform_driver_register_all(char *class_str); +extern int sh_early_platform_driver_probe(char *class_str, int nr_probe, int user_only); -#define early_platform_init(class_string, platdrv) \ - early_platform_init_buffer(class_string, platdrv, NULL, 0) +#define sh_early_platform_init(class_string, platdrv) \ + sh_early_platform_init_buffer(class_string, platdrv, NULL, 0) #ifndef MODULE -#define early_platform_init_buffer(class_string, platdrv, buf, bufsiz) \ -static __initdata struct early_platform_driver early_driver = { \ +#define sh_early_platform_init_buffer(class_string, platdrv, buf, bufsiz) \ +static __initdata struct sh_early_platform_driver early_driver = { \ .class_str = class_string, \ .buffer = buf, \ .bufsize = bufsiz, \ .pdrv = platdrv, \ .requested_id = EARLY_PLATFORM_ID_UNSET, \ }; \ -static int __init early_platform_driver_setup_func(char *buffer) \ +static int __init sh_early_platform_driver_setup_func(char *buffer) \ { \ - return early_platform_driver_register(&early_driver, buffer); \ + return sh_early_platform_driver_register(&early_driver, buffer); \ } \ -early_param(class_string, early_platform_driver_setup_func) +early_param(class_string, sh_early_platform_driver_setup_func) #else /* MODULE */ -#define early_platform_init_buffer(class_string, platdrv, buf, bufsiz) \ -static inline char *early_platform_driver_setup_func(void) \ +#define sh_early_platform_init_buffer(class_string, platdrv, buf, bufsiz) \ +static inline char *sh_early_platform_driver_setup_func(void) \ { \ return bufsiz ? buf : NULL; \ } diff --git a/arch/sh/kernel/cpu/sh2/setup-sh7619.c b/arch/sh/kernel/cpu/sh2/setup-sh7619.c index 27d459e8a598..b1c877b6a420 100644 --- a/arch/sh/kernel/cpu/sh2/setup-sh7619.c +++ b/arch/sh/kernel/cpu/sh2/setup-sh7619.c @@ -200,6 +200,6 @@ void __init plat_early_device_setup(void) /* enable CMT clock */ __raw_writeb(__raw_readb(STBCR3) & ~0x10, STBCR3); - early_platform_add_devices(sh7619_early_devices, + sh_early_platform_add_devices(sh7619_early_devices, ARRAY_SIZE(sh7619_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh2a/setup-mxg.c b/arch/sh/kernel/cpu/sh2a/setup-mxg.c index 8a19c5754978..cefa07924c16 100644 --- a/arch/sh/kernel/cpu/sh2a/setup-mxg.c +++ b/arch/sh/kernel/cpu/sh2a/setup-mxg.c @@ -170,6 +170,6 @@ static struct platform_device *mxg_early_devices[] __initdata = { void __init plat_early_device_setup(void) { - early_platform_add_devices(mxg_early_devices, + sh_early_platform_add_devices(mxg_early_devices, ARRAY_SIZE(mxg_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh2a/setup-sh7201.c b/arch/sh/kernel/cpu/sh2a/setup-sh7201.c index d975e4d404bd..28f1bebf3405 100644 --- a/arch/sh/kernel/cpu/sh2a/setup-sh7201.c +++ b/arch/sh/kernel/cpu/sh2a/setup-sh7201.c @@ -413,6 +413,6 @@ void __init plat_early_device_setup(void) /* enable MTU2 clock */ __raw_writeb(__raw_readb(STBCR3) & ~0x20, STBCR3); - early_platform_add_devices(sh7201_early_devices, + sh_early_platform_add_devices(sh7201_early_devices, ARRAY_SIZE(sh7201_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh2a/setup-sh7203.c b/arch/sh/kernel/cpu/sh2a/setup-sh7203.c index 318b8cd8d5b7..4839f3aaeb4c 100644 --- a/arch/sh/kernel/cpu/sh2a/setup-sh7203.c +++ b/arch/sh/kernel/cpu/sh2a/setup-sh7203.c @@ -350,6 +350,6 @@ void __init plat_early_device_setup(void) /* enable MTU2 clock */ __raw_writeb(__raw_readb(STBCR3) & ~0x20, STBCR3); - early_platform_add_devices(sh7203_early_devices, + sh_early_platform_add_devices(sh7203_early_devices, ARRAY_SIZE(sh7203_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh2a/setup-sh7206.c b/arch/sh/kernel/cpu/sh2a/setup-sh7206.c index 8e6fae60074a..68add5af4cc5 100644 --- a/arch/sh/kernel/cpu/sh2a/setup-sh7206.c +++ b/arch/sh/kernel/cpu/sh2a/setup-sh7206.c @@ -286,6 +286,6 @@ void __init plat_early_device_setup(void) /* enable MTU2 clock */ __raw_writeb(__raw_readb(STBCR3) & ~0x20, STBCR3); - early_platform_add_devices(sh7206_early_devices, + sh_early_platform_add_devices(sh7206_early_devices, ARRAY_SIZE(sh7206_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh2a/setup-sh7264.c b/arch/sh/kernel/cpu/sh2a/setup-sh7264.c index 2d95c9b38330..8a1cb613dd2e 100644 --- a/arch/sh/kernel/cpu/sh2a/setup-sh7264.c +++ b/arch/sh/kernel/cpu/sh2a/setup-sh7264.c @@ -547,6 +547,6 @@ static struct platform_device *sh7264_early_devices[] __initdata = { void __init plat_early_device_setup(void) { - early_platform_add_devices(sh7264_early_devices, + sh_early_platform_add_devices(sh7264_early_devices, ARRAY_SIZE(sh7264_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh2a/setup-sh7269.c b/arch/sh/kernel/cpu/sh2a/setup-sh7269.c index ef4ff76cbe9e..8b1ef3028320 100644 --- a/arch/sh/kernel/cpu/sh2a/setup-sh7269.c +++ b/arch/sh/kernel/cpu/sh2a/setup-sh7269.c @@ -563,6 +563,6 @@ static struct platform_device *sh7269_early_devices[] __initdata = { void __init plat_early_device_setup(void) { - early_platform_add_devices(sh7269_early_devices, + sh_early_platform_add_devices(sh7269_early_devices, ARRAY_SIZE(sh7269_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh3/setup-sh7705.c b/arch/sh/kernel/cpu/sh3/setup-sh7705.c index 9b34d1f4e797..0544134b3f20 100644 --- a/arch/sh/kernel/cpu/sh3/setup-sh7705.c +++ b/arch/sh/kernel/cpu/sh3/setup-sh7705.c @@ -179,7 +179,7 @@ static struct platform_device *sh7705_early_devices[] __initdata = { void __init plat_early_device_setup(void) { - early_platform_add_devices(sh7705_early_devices, + sh_early_platform_add_devices(sh7705_early_devices, ARRAY_SIZE(sh7705_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh3/setup-sh770x.c b/arch/sh/kernel/cpu/sh3/setup-sh770x.c index 39f09504bd96..4947f57748bc 100644 --- a/arch/sh/kernel/cpu/sh3/setup-sh770x.c +++ b/arch/sh/kernel/cpu/sh3/setup-sh770x.c @@ -231,7 +231,7 @@ static struct platform_device *sh770x_early_devices[] __initdata = { void __init plat_early_device_setup(void) { - early_platform_add_devices(sh770x_early_devices, + sh_early_platform_add_devices(sh770x_early_devices, ARRAY_SIZE(sh770x_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh3/setup-sh7710.c b/arch/sh/kernel/cpu/sh3/setup-sh7710.c index c006c8fcfa0f..381910761579 100644 --- a/arch/sh/kernel/cpu/sh3/setup-sh7710.c +++ b/arch/sh/kernel/cpu/sh3/setup-sh7710.c @@ -178,7 +178,7 @@ static struct platform_device *sh7710_early_devices[] __initdata = { void __init plat_early_device_setup(void) { - early_platform_add_devices(sh7710_early_devices, + sh_early_platform_add_devices(sh7710_early_devices, ARRAY_SIZE(sh7710_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh3/setup-sh7720.c b/arch/sh/kernel/cpu/sh3/setup-sh7720.c index cf2eec9f6abd..425d067dae9b 100644 --- a/arch/sh/kernel/cpu/sh3/setup-sh7720.c +++ b/arch/sh/kernel/cpu/sh3/setup-sh7720.c @@ -212,7 +212,7 @@ static struct platform_device *sh7720_early_devices[] __initdata = { void __init plat_early_device_setup(void) { - early_platform_add_devices(sh7720_early_devices, + sh_early_platform_add_devices(sh7720_early_devices, ARRAY_SIZE(sh7720_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh4/setup-sh4-202.c b/arch/sh/kernel/cpu/sh4/setup-sh4-202.c index 2480ce4a3b1e..e6737f3d0df2 100644 --- a/arch/sh/kernel/cpu/sh4/setup-sh4-202.c +++ b/arch/sh/kernel/cpu/sh4/setup-sh4-202.c @@ -77,7 +77,7 @@ static struct platform_device *sh4202_early_devices[] __initdata = { void __init plat_early_device_setup(void) { - early_platform_add_devices(sh4202_early_devices, + sh_early_platform_add_devices(sh4202_early_devices, ARRAY_SIZE(sh4202_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh4/setup-sh7750.c b/arch/sh/kernel/cpu/sh4/setup-sh7750.c index 4592d660b942..19c8f1d69071 100644 --- a/arch/sh/kernel/cpu/sh4/setup-sh7750.c +++ b/arch/sh/kernel/cpu/sh4/setup-sh7750.c @@ -162,15 +162,15 @@ void __init plat_early_device_setup(void) if (mach_is_rts7751r2d()) { scif_platform_data.scscr |= SCSCR_CKE1; dev[0] = &scif_device; - early_platform_add_devices(dev, 1); + sh_early_platform_add_devices(dev, 1); } else { dev[0] = &sci_device; - early_platform_add_devices(dev, 1); + sh_early_platform_add_devices(dev, 1); dev[0] = &scif_device; - early_platform_add_devices(dev, 1); + sh_early_platform_add_devices(dev, 1); } - early_platform_add_devices(sh7750_early_devices, + sh_early_platform_add_devices(sh7750_early_devices, ARRAY_SIZE(sh7750_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh4/setup-sh7760.c b/arch/sh/kernel/cpu/sh4/setup-sh7760.c index e64eb96e3589..14212f5d803c 100644 --- a/arch/sh/kernel/cpu/sh4/setup-sh7760.c +++ b/arch/sh/kernel/cpu/sh4/setup-sh7760.c @@ -272,7 +272,7 @@ static struct platform_device *sh7760_early_devices[] __initdata = { void __init plat_early_device_setup(void) { - early_platform_add_devices(sh7760_early_devices, + sh_early_platform_add_devices(sh7760_early_devices, ARRAY_SIZE(sh7760_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7343.c b/arch/sh/kernel/cpu/sh4a/setup-sh7343.c index 0fa56128bdca..b6015188fab1 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7343.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7343.c @@ -297,7 +297,7 @@ static struct platform_device *sh7343_early_devices[] __initdata = { void __init plat_early_device_setup(void) { - early_platform_add_devices(sh7343_early_devices, + sh_early_platform_add_devices(sh7343_early_devices, ARRAY_SIZE(sh7343_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7366.c b/arch/sh/kernel/cpu/sh4a/setup-sh7366.c index 9f2f75285ec3..6676beef053e 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7366.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7366.c @@ -241,7 +241,7 @@ static struct platform_device *sh7366_early_devices[] __initdata = { void __init plat_early_device_setup(void) { - early_platform_add_devices(sh7366_early_devices, + sh_early_platform_add_devices(sh7366_early_devices, ARRAY_SIZE(sh7366_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7722.c b/arch/sh/kernel/cpu/sh4a/setup-sh7722.c index 8e5eaac789a7..0c6757ef63f4 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7722.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7722.c @@ -513,7 +513,7 @@ static struct platform_device *sh7722_early_devices[] __initdata = { void __init plat_early_device_setup(void) { - early_platform_add_devices(sh7722_early_devices, + sh_early_platform_add_devices(sh7722_early_devices, ARRAY_SIZE(sh7722_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7723.c b/arch/sh/kernel/cpu/sh4a/setup-sh7723.c index b4b54aa0c267..83ae1ad4a86e 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7723.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7723.c @@ -411,7 +411,7 @@ static struct platform_device *sh7723_early_devices[] __initdata = { void __init plat_early_device_setup(void) { - early_platform_add_devices(sh7723_early_devices, + sh_early_platform_add_devices(sh7723_early_devices, ARRAY_SIZE(sh7723_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7724.c b/arch/sh/kernel/cpu/sh4a/setup-sh7724.c index ec237ab112cf..0d990ab1ba2a 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7724.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7724.c @@ -831,7 +831,7 @@ static struct platform_device *sh7724_early_devices[] __initdata = { void __init plat_early_device_setup(void) { - early_platform_add_devices(sh7724_early_devices, + sh_early_platform_add_devices(sh7724_early_devices, ARRAY_SIZE(sh7724_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7734.c b/arch/sh/kernel/cpu/sh4a/setup-sh7734.c index 7ea9a8b43955..9911da794358 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7734.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7734.c @@ -281,7 +281,7 @@ static struct platform_device *sh7734_early_devices[] __initdata = { void __init plat_early_device_setup(void) { - early_platform_add_devices(sh7734_early_devices, + sh_early_platform_add_devices(sh7734_early_devices, ARRAY_SIZE(sh7734_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7757.c b/arch/sh/kernel/cpu/sh4a/setup-sh7757.c index 922d9886be18..67e330b7ea46 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7757.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7757.c @@ -768,7 +768,7 @@ static struct platform_device *sh7757_early_devices[] __initdata = { void __init plat_early_device_setup(void) { - early_platform_add_devices(sh7757_early_devices, + sh_early_platform_add_devices(sh7757_early_devices, ARRAY_SIZE(sh7757_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7763.c b/arch/sh/kernel/cpu/sh4a/setup-sh7763.c index 8725d4751baf..b0608664785f 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7763.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7763.c @@ -222,7 +222,7 @@ static struct platform_device *sh7763_early_devices[] __initdata = { void __init plat_early_device_setup(void) { - early_platform_add_devices(sh7763_early_devices, + sh_early_platform_add_devices(sh7763_early_devices, ARRAY_SIZE(sh7763_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7770.c b/arch/sh/kernel/cpu/sh4a/setup-sh7770.c index 035a0d4f2a2e..5efec6ceb04d 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7770.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7770.c @@ -317,7 +317,7 @@ static struct platform_device *sh7770_early_devices[] __initdata = { void __init plat_early_device_setup(void) { - early_platform_add_devices(sh7770_early_devices, + sh_early_platform_add_devices(sh7770_early_devices, ARRAY_SIZE(sh7770_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7780.c b/arch/sh/kernel/cpu/sh4a/setup-sh7780.c index 983be87cb7be..c818b788ecb0 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7780.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7780.c @@ -286,7 +286,7 @@ void __init plat_early_device_setup(void) scif1_platform_data.scscr &= ~SCSCR_CKE1; } - early_platform_add_devices(sh7780_early_devices, + sh_early_platform_add_devices(sh7780_early_devices, ARRAY_SIZE(sh7780_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7785.c b/arch/sh/kernel/cpu/sh4a/setup-sh7785.c index bb0cb710c16e..3b4a414d60a9 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7785.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7785.c @@ -354,7 +354,7 @@ static struct platform_device *sh7785_early_devices[] __initdata = { void __init plat_early_device_setup(void) { - early_platform_add_devices(sh7785_early_devices, + sh_early_platform_add_devices(sh7785_early_devices, ARRAY_SIZE(sh7785_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7786.c b/arch/sh/kernel/cpu/sh4a/setup-sh7786.c index b5d94366eed3..4b0db8259e3d 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7786.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7786.c @@ -835,6 +835,6 @@ arch_initcall(sh7786_devices_setup); void __init plat_early_device_setup(void) { - early_platform_add_devices(sh7786_early_devices, + sh_early_platform_add_devices(sh7786_early_devices, ARRAY_SIZE(sh7786_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh4a/setup-shx3.c b/arch/sh/kernel/cpu/sh4a/setup-shx3.c index e82398d80b74..7014d6d199b3 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-shx3.c +++ b/arch/sh/kernel/cpu/sh4a/setup-shx3.c @@ -153,7 +153,7 @@ arch_initcall(shx3_devices_setup); void __init plat_early_device_setup(void) { - early_platform_add_devices(shx3_early_devices, + sh_early_platform_add_devices(shx3_early_devices, ARRAY_SIZE(shx3_early_devices)); } diff --git a/arch/sh/kernel/cpu/sh5/setup-sh5.c b/arch/sh/kernel/cpu/sh5/setup-sh5.c index 584a6aeeca26..dc8476d67244 100644 --- a/arch/sh/kernel/cpu/sh5/setup-sh5.c +++ b/arch/sh/kernel/cpu/sh5/setup-sh5.c @@ -116,6 +116,6 @@ arch_initcall(sh5_devices_setup); void __init plat_early_device_setup(void) { - early_platform_add_devices(sh5_early_devices, + sh_early_platform_add_devices(sh5_early_devices, ARRAY_SIZE(sh5_early_devices)); } diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index e535507851e1..914174a125a4 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -329,7 +329,7 @@ void __init setup_arch(char **cmdline_p) sh_mv_setup(); /* Let earlyprintk output early console messages */ - early_platform_driver_probe("earlyprintk", 1, 1); + sh_early_platform_driver_probe("earlyprintk", 1, 1); #ifdef CONFIG_OF_FLATTREE #ifdef CONFIG_USE_BUILTIN_DTB diff --git a/arch/sh/kernel/time.c b/arch/sh/kernel/time.c index 8ad9fd5c4ff6..821a09cbd605 100644 --- a/arch/sh/kernel/time.c +++ b/arch/sh/kernel/time.c @@ -31,8 +31,8 @@ static void __init sh_late_time_init(void) * clocksource and the jiffies clocksource is used transparently * instead. No error handling is necessary here. */ - early_platform_driver_register_all("earlytimer"); - early_platform_driver_probe("earlytimer", 2, 0); + sh_early_platform_driver_register_all("earlytimer"); + sh_early_platform_driver_probe("earlytimer", 2, 0); } void __init time_init(void) diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c index 3a185485300e..9cde50cb3220 100644 --- a/drivers/clocksource/sh_cmt.c +++ b/drivers/clocksource/sh_cmt.c @@ -1056,7 +1056,7 @@ static int sh_cmt_probe(struct platform_device *pdev) struct sh_cmt_device *cmt = platform_get_drvdata(pdev); int ret; - if (!is_early_platform_device(pdev)) { + if (!is_sh_early_platform_device(pdev)) { pm_runtime_set_active(&pdev->dev); pm_runtime_enable(&pdev->dev); } @@ -1076,7 +1076,7 @@ static int sh_cmt_probe(struct platform_device *pdev) pm_runtime_idle(&pdev->dev); return ret; } - if (is_early_platform_device(pdev)) + if (is_sh_early_platform_device(pdev)) return 0; out: @@ -1114,7 +1114,7 @@ static void __exit sh_cmt_exit(void) } #ifdef CONFIG_SUPERH -early_platform_init("earlytimer", &sh_cmt_device_driver); +sh_early_platform_init("earlytimer", &sh_cmt_device_driver); #endif subsys_initcall(sh_cmt_init); diff --git a/drivers/clocksource/sh_mtu2.c b/drivers/clocksource/sh_mtu2.c index d581060d33a2..c40eef091a04 100644 --- a/drivers/clocksource/sh_mtu2.c +++ b/drivers/clocksource/sh_mtu2.c @@ -446,7 +446,7 @@ static int sh_mtu2_probe(struct platform_device *pdev) struct sh_mtu2_device *mtu = platform_get_drvdata(pdev); int ret; - if (!is_early_platform_device(pdev)) { + if (!is_sh_early_platform_device(pdev)) { pm_runtime_set_active(&pdev->dev); pm_runtime_enable(&pdev->dev); } @@ -466,7 +466,7 @@ static int sh_mtu2_probe(struct platform_device *pdev) pm_runtime_idle(&pdev->dev); return ret; } - if (is_early_platform_device(pdev)) + if (is_sh_early_platform_device(pdev)) return 0; out: @@ -516,7 +516,7 @@ static void __exit sh_mtu2_exit(void) } #ifdef CONFIG_SUPERH -early_platform_init("earlytimer", &sh_mtu2_device_driver); +sh_early_platform_init("earlytimer", &sh_mtu2_device_driver); #endif subsys_initcall(sh_mtu2_init); diff --git a/drivers/clocksource/sh_tmu.c b/drivers/clocksource/sh_tmu.c index 50e30ead050e..d49690d15536 100644 --- a/drivers/clocksource/sh_tmu.c +++ b/drivers/clocksource/sh_tmu.c @@ -599,7 +599,7 @@ static int sh_tmu_probe(struct platform_device *pdev) struct sh_tmu_device *tmu = platform_get_drvdata(pdev); int ret; - if (!is_early_platform_device(pdev)) { + if (!is_sh_early_platform_device(pdev)) { pm_runtime_set_active(&pdev->dev); pm_runtime_enable(&pdev->dev); } @@ -620,7 +620,7 @@ static int sh_tmu_probe(struct platform_device *pdev) return ret; } - if (is_early_platform_device(pdev)) + if (is_sh_early_platform_device(pdev)) return 0; out: @@ -671,7 +671,7 @@ static void __exit sh_tmu_exit(void) } #ifdef CONFIG_SUPERH -early_platform_init("earlytimer", &sh_tmu_device_driver); +sh_early_platform_init("earlytimer", &sh_tmu_device_driver); #endif subsys_initcall(sh_tmu_init); diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 2a645fd7f07b..970f1f86b945 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -3318,7 +3318,7 @@ static int sci_probe(struct platform_device *dev) * to make it beyond this yet. */ #ifdef CONFIG_SUPERH - if (is_early_platform_device(dev)) + if (is_sh_early_platform_device(dev)) return sci_probe_earlyprintk(dev); #endif @@ -3416,7 +3416,7 @@ static void __exit sci_exit(void) } #if defined(CONFIG_SUPERH) && defined(CONFIG_SERIAL_SH_SCI_CONSOLE) -early_platform_init_buffer("earlyprintk", &sci_driver, +sh_early_platform_init_buffer("earlyprintk", &sci_driver, early_serial_buf, ARRAY_SIZE(early_serial_buf)); #endif #ifdef CONFIG_SERIAL_SH_SCI_EARLYCON diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 85aa28a041a9..f086b6a1bc6b 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -332,7 +332,7 @@ extern int platform_dma_configure(struct device *dev); * drivers. It should go away once we introduce the new platform_device-based * early driver framework. */ -static inline int is_early_platform_device(struct platform_device *pdev) +static inline int is_sh_early_platform_device(struct platform_device *pdev) { return 0; } -- cgit v1.2.3-71-gd317 From b9df4fd7e99cb8bfd80c4143f3045d63b1754ad0 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sun, 6 Oct 2019 18:19:54 +0200 Subject: net: core: change return type of pskb_may_pull to bool This function de-facto returns a bool, so let's change the return type accordingly. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4351577b14d7..0a58402a166e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2261,12 +2261,12 @@ static inline void *pskb_pull(struct sk_buff *skb, unsigned int len) return unlikely(len > skb->len) ? NULL : __pskb_pull(skb, len); } -static inline int pskb_may_pull(struct sk_buff *skb, unsigned int len) +static inline bool pskb_may_pull(struct sk_buff *skb, unsigned int len) { if (likely(len <= skb_headlen(skb))) - return 1; + return true; if (unlikely(len > skb->len)) - return 0; + return false; return __pskb_pull_tail(skb, len - skb_headlen(skb)) != NULL; } -- cgit v1.2.3-71-gd317 From f00eaa38eb0c7185ffff51c5288d00af9032e354 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Mon, 7 Oct 2019 15:47:15 +0200 Subject: rtc: add a timestamp for year 0 A few RTCs handle dates from year 0 to year 9999. Add a timestamp even if years before 1970 will probably never be used. Link: https://lore.kernel.org/r/20191007134724.15505-1-alexandre.belloni@bootlin.com Signed-off-by: Alexandre Belloni --- include/linux/rtc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index df666cf29ef1..2680f9b2b119 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -160,6 +160,7 @@ struct rtc_device { #define to_rtc_device(d) container_of(d, struct rtc_device, dev) /* useful timestamps */ +#define RTC_TIMESTAMP_BEGIN_0000 -62167219200ULL /* 0000-01-01 00:00:00 */ #define RTC_TIMESTAMP_BEGIN_1900 -2208988800LL /* 1900-01-01 00:00:00 */ #define RTC_TIMESTAMP_BEGIN_2000 946684800LL /* 2000-01-01 00:00:00 */ #define RTC_TIMESTAMP_END_2063 2966371199LL /* 2063-12-31 23:59:59 */ -- cgit v1.2.3-71-gd317 From 163ab96b52ae2bb2d8f188cd29f0b570610f9007 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sun, 6 Oct 2019 21:09:27 -0700 Subject: net: sockmap: use bitmap for copy info Don't use bool array in struct sk_msg_sg, save 12 bytes. Signed-off-by: Jakub Kicinski Reviewed-by: Dirk van der Merwe Signed-off-by: David S. Miller --- include/linux/skmsg.h | 12 ++++++++---- net/core/filter.c | 4 ++-- 2 files changed, 10 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index e4b3fb4bb77c..fe80d537945d 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -28,13 +28,14 @@ struct sk_msg_sg { u32 end; u32 size; u32 copybreak; - bool copy[MAX_MSG_FRAGS]; + unsigned long copy; /* The extra element is used for chaining the front and sections when * the list becomes partitioned (e.g. end < start). The crypto APIs * require the chaining. */ struct scatterlist data[MAX_MSG_FRAGS + 1]; }; +static_assert(BITS_PER_LONG >= MAX_MSG_FRAGS); /* UAPI in filter.c depends on struct sk_msg_sg being first element. */ struct sk_msg { @@ -227,7 +228,7 @@ static inline void sk_msg_compute_data_pointers(struct sk_msg *msg) { struct scatterlist *sge = sk_msg_elem(msg, msg->sg.start); - if (msg->sg.copy[msg->sg.start]) { + if (test_bit(msg->sg.start, &msg->sg.copy)) { msg->data = NULL; msg->data_end = NULL; } else { @@ -246,7 +247,7 @@ static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page, sg_set_page(sge, page, len, offset); sg_unmark_end(sge); - msg->sg.copy[msg->sg.end] = true; + __set_bit(msg->sg.end, &msg->sg.copy); msg->sg.size += len; sk_msg_iter_next(msg, end); } @@ -254,7 +255,10 @@ static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page, static inline void sk_msg_sg_copy(struct sk_msg *msg, u32 i, bool copy_state) { do { - msg->sg.copy[i] = copy_state; + if (copy_state) + __set_bit(i, &msg->sg.copy); + else + __clear_bit(i, &msg->sg.copy); sk_msg_iter_var_next(i); if (i == msg->sg.end) break; diff --git a/net/core/filter.c b/net/core/filter.c index ed6563622ce3..46196e212413 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2245,7 +2245,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, * account for the headroom. */ bytes_sg_total = start - offset + bytes; - if (!msg->sg.copy[i] && bytes_sg_total <= len) + if (!test_bit(i, &msg->sg.copy) && bytes_sg_total <= len) goto out; /* At this point we need to linearize multiple scatterlist @@ -2450,7 +2450,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, /* Place newly allocated data buffer */ sk_mem_charge(msg->sk, len); msg->sg.size += len; - msg->sg.copy[new] = false; + __clear_bit(new, &msg->sg.copy); sg_set_page(&msg->sg.data[new], page, len + copy, 0); if (rsge.length) { get_page(sg_page(&rsge)); -- cgit v1.2.3-71-gd317 From 9566256518de0520c964bdf23140eac324b136af Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 30 Sep 2019 16:00:42 -0700 Subject: block: Remove request_queue.nr_queues Commit 897bb0c7f1ea ("blk-mq: Use proper cpumask iterator"; v4.6) removed the last use of request_queue.nr_queues from outside blk_mq_init_allocate_queue(). Remove this member variable to make struct request_queue smaller. This patch does not change any functionality. Cc: Christoph Hellwig Cc: Ming Lei Cc: Hannes Reinecke Cc: Johannes Thumshirn Signed-off-by: Bart Van Assche Signed-off-by: Jens Axboe --- block/blk-mq.c | 6 +++--- include/linux/blkdev.h | 1 - 2 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index ec791156e9cc..9d932939b576 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2876,9 +2876,9 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, /* init q->mq_kobj and sw queues' kobjects */ blk_mq_sysfs_init(q); - q->nr_queues = nr_hw_queues(set); - q->queue_hw_ctx = kcalloc_node(q->nr_queues, sizeof(*(q->queue_hw_ctx)), - GFP_KERNEL, set->numa_node); + q->queue_hw_ctx = kcalloc_node(nr_hw_queues(set), + sizeof(*(q->queue_hw_ctx)), GFP_KERNEL, + set->numa_node); if (!q->queue_hw_ctx) goto err_sys_init; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f3ea78b0c91c..d4051acb92a1 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -411,7 +411,6 @@ struct request_queue { /* sw queues */ struct blk_mq_ctx __percpu *queue_ctx; - unsigned int nr_queues; unsigned int queue_depth; -- cgit v1.2.3-71-gd317 From 7a18312c739aeace7c8ea448d39a0313d5ad5d5d Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 30 Sep 2019 16:00:45 -0700 Subject: block: Document all members of blk_mq_tag_set and bkl_mq_queue_map The meaning of several member variables of these two data structures is nontrivial. Hence document all member variables using the kernel-doc syntax. Cc: Christoph Hellwig Cc: Ming Lei Cc: Hannes Reinecke Cc: Johannes Thumshirn Signed-off-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 54 ++++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 43 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 0bf056de5cc3..a96b5cc957ab 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -76,6 +76,16 @@ struct blk_mq_hw_ctx { struct srcu_struct srcu[0]; }; +/** + * struct blk_mq_queue_map - ctx -> hctx mapping + * @mq_map: CPU ID to hardware queue index map. This is an array + * with nr_cpu_ids elements. Each element has a value in the range + * [@queue_offset, @queue_offset + @nr_queues). + * @nr_queues: Number of hardware queues to map CPU IDs onto. + * @queue_offset: First hardware queue to map onto. Used by the PCIe NVMe + * driver to map each hardware queue type (enum hctx_type) onto a distinct + * set of hardware queues. + */ struct blk_mq_queue_map { unsigned int *mq_map; unsigned int nr_queues; @@ -90,23 +100,45 @@ enum hctx_type { HCTX_MAX_TYPES, }; +/** + * struct blk_mq_tag_set - tag set that can be shared between request queues + * @map: One or more ctx -> hctx mappings. One map exists for each + * hardware queue type (enum hctx_type) that the driver wishes + * to support. There are no restrictions on maps being of the + * same size, and it's perfectly legal to share maps between + * types. + * @nr_maps: Number of elements in the @map array. A number in the range + * [1, HCTX_MAX_TYPES]. + * @ops: Pointers to functions that implement block driver behavior. + * @nr_hw_queues: Number of hardware queues supported by the block driver that + * owns this data structure. + * @queue_depth: Number of tags per hardware queue, reserved tags included. + * @reserved_tags: Number of tags to set aside for BLK_MQ_REQ_RESERVED tag + * allocations. + * @cmd_size: Number of additional bytes to allocate per request. The block + * driver owns these additional bytes. + * @numa_node: NUMA node the storage adapter has been connected to. + * @timeout: Request processing timeout in jiffies. + * @flags: Zero or more BLK_MQ_F_* flags. + * @driver_data: Pointer to data owned by the block driver that created this + * tag set. + * @tags: Tag sets. One tag set per hardware queue. Has @nr_hw_queues + * elements. + * @tag_list_lock: Serializes tag_list accesses. + * @tag_list: List of the request queues that use this tag set. See also + * request_queue.tag_set_list. + */ struct blk_mq_tag_set { - /* - * map[] holds ctx -> hctx mappings, one map exists for each type - * that the driver wishes to support. There are no restrictions - * on maps being of the same size, and it's perfectly legal to - * share maps between types. - */ struct blk_mq_queue_map map[HCTX_MAX_TYPES]; - unsigned int nr_maps; /* nr entries in map[] */ + unsigned int nr_maps; const struct blk_mq_ops *ops; - unsigned int nr_hw_queues; /* nr hw queues across maps */ - unsigned int queue_depth; /* max hw supported */ + unsigned int nr_hw_queues; + unsigned int queue_depth; unsigned int reserved_tags; - unsigned int cmd_size; /* per-request extra data */ + unsigned int cmd_size; int numa_node; unsigned int timeout; - unsigned int flags; /* BLK_MQ_F_* */ + unsigned int flags; void *driver_data; struct blk_mq_tags **tags; -- cgit v1.2.3-71-gd317 From 27a46989a82c71028f2ba15a3f2c8f30451fda33 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Mon, 30 Sep 2019 11:25:49 +0300 Subject: blk-mq: Inline status checkers blk_mq_request_completed() and blk_mq_request_started() are short, inline it. Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- block/blk-mq.c | 12 ------------ block/blk-mq.h | 9 --------- include/linux/blk-mq.h | 20 ++++++++++++++++++-- 3 files changed, 18 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index 9d932939b576..268a95e899b7 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -663,18 +663,6 @@ bool blk_mq_complete_request(struct request *rq) } EXPORT_SYMBOL(blk_mq_complete_request); -int blk_mq_request_started(struct request *rq) -{ - return blk_mq_rq_state(rq) != MQ_RQ_IDLE; -} -EXPORT_SYMBOL_GPL(blk_mq_request_started); - -int blk_mq_request_completed(struct request *rq) -{ - return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE; -} -EXPORT_SYMBOL_GPL(blk_mq_request_completed); - void blk_mq_start_request(struct request *rq) { struct request_queue *q = rq->q; diff --git a/block/blk-mq.h b/block/blk-mq.h index 32c62c64e6c2..eaaca8fc1c28 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -128,15 +128,6 @@ extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx); void blk_mq_release(struct request_queue *q); -/** - * blk_mq_rq_state() - read the current MQ_RQ_* state of a request - * @rq: target request. - */ -static inline enum mq_rq_state blk_mq_rq_state(struct request *rq) -{ - return READ_ONCE(rq->state); -} - static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q, unsigned int cpu) { diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index a96b5cc957ab..e0fce93ac127 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -333,9 +333,25 @@ static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag) return unique_tag & BLK_MQ_UNIQUE_TAG_MASK; } +/** + * blk_mq_rq_state() - read the current MQ_RQ_* state of a request + * @rq: target request. + */ +static inline enum mq_rq_state blk_mq_rq_state(struct request *rq) +{ + return READ_ONCE(rq->state); +} + +static inline int blk_mq_request_started(struct request *rq) +{ + return blk_mq_rq_state(rq) != MQ_RQ_IDLE; +} + +static inline int blk_mq_request_completed(struct request *rq) +{ + return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE; +} -int blk_mq_request_started(struct request *rq); -int blk_mq_request_completed(struct request *rq); void blk_mq_start_request(struct request *rq); void blk_mq_end_request(struct request *rq, blk_status_t error); void __blk_mq_end_request(struct request *rq, blk_status_t error); -- cgit v1.2.3-71-gd317 From b0a1614fb1f58520938968ebe1f4f11bcf34839e Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Fri, 23 Aug 2019 05:16:33 -0700 Subject: firmware: qcom: scm: add OCMEM lock/unlock interface Add support for the OCMEM lock/unlock interface that is needed by the On Chip MEMory (OCMEM) that is present on some Snapdragon devices. Signed-off-by: Rob Clark [masneyb@onstation.org: ported to latest kernel; minor reformatting.] Signed-off-by: Brian Masney Reviewed-by: Bjorn Andersson Tested-by: Gabriel Francisco Signed-off-by: Rob Clark --- drivers/firmware/qcom_scm-32.c | 35 +++++++++++++++++++++++++++++++++++ drivers/firmware/qcom_scm-64.c | 12 ++++++++++++ drivers/firmware/qcom_scm.c | 40 ++++++++++++++++++++++++++++++++++++++++ drivers/firmware/qcom_scm.h | 9 +++++++++ include/linux/qcom_scm.h | 15 +++++++++++++++ 5 files changed, 111 insertions(+) (limited to 'include/linux') diff --git a/drivers/firmware/qcom_scm-32.c b/drivers/firmware/qcom_scm-32.c index 215061c581e1..4c2514e5e249 100644 --- a/drivers/firmware/qcom_scm-32.c +++ b/drivers/firmware/qcom_scm-32.c @@ -442,6 +442,41 @@ int __qcom_scm_hdcp_req(struct device *dev, struct qcom_scm_hdcp_req *req, req, req_cnt * sizeof(*req), resp, sizeof(*resp)); } +int __qcom_scm_ocmem_lock(struct device *dev, u32 id, u32 offset, u32 size, + u32 mode) +{ + struct ocmem_tz_lock { + __le32 id; + __le32 offset; + __le32 size; + __le32 mode; + } request; + + request.id = cpu_to_le32(id); + request.offset = cpu_to_le32(offset); + request.size = cpu_to_le32(size); + request.mode = cpu_to_le32(mode); + + return qcom_scm_call(dev, QCOM_SCM_OCMEM_SVC, QCOM_SCM_OCMEM_LOCK_CMD, + &request, sizeof(request), NULL, 0); +} + +int __qcom_scm_ocmem_unlock(struct device *dev, u32 id, u32 offset, u32 size) +{ + struct ocmem_tz_unlock { + __le32 id; + __le32 offset; + __le32 size; + } request; + + request.id = cpu_to_le32(id); + request.offset = cpu_to_le32(offset); + request.size = cpu_to_le32(size); + + return qcom_scm_call(dev, QCOM_SCM_OCMEM_SVC, QCOM_SCM_OCMEM_UNLOCK_CMD, + &request, sizeof(request), NULL, 0); +} + void __qcom_scm_init(void) { } diff --git a/drivers/firmware/qcom_scm-64.c b/drivers/firmware/qcom_scm-64.c index 91d5ad7cf58b..c3a3d9874def 100644 --- a/drivers/firmware/qcom_scm-64.c +++ b/drivers/firmware/qcom_scm-64.c @@ -241,6 +241,18 @@ int __qcom_scm_hdcp_req(struct device *dev, struct qcom_scm_hdcp_req *req, return ret; } +int __qcom_scm_ocmem_lock(struct device *dev, uint32_t id, uint32_t offset, + uint32_t size, uint32_t mode) +{ + return -ENOTSUPP; +} + +int __qcom_scm_ocmem_unlock(struct device *dev, uint32_t id, uint32_t offset, + uint32_t size) +{ + return -ENOTSUPP; +} + void __qcom_scm_init(void) { u64 cmd; diff --git a/drivers/firmware/qcom_scm.c b/drivers/firmware/qcom_scm.c index 4802ab170fe5..7e285ff3961d 100644 --- a/drivers/firmware/qcom_scm.c +++ b/drivers/firmware/qcom_scm.c @@ -191,6 +191,46 @@ bool qcom_scm_pas_supported(u32 peripheral) } EXPORT_SYMBOL(qcom_scm_pas_supported); +/** + * qcom_scm_ocmem_lock_available() - is OCMEM lock/unlock interface available + */ +bool qcom_scm_ocmem_lock_available(void) +{ + return __qcom_scm_is_call_available(__scm->dev, QCOM_SCM_OCMEM_SVC, + QCOM_SCM_OCMEM_LOCK_CMD); +} +EXPORT_SYMBOL(qcom_scm_ocmem_lock_available); + +/** + * qcom_scm_ocmem_lock() - call OCMEM lock interface to assign an OCMEM + * region to the specified initiator + * + * @id: tz initiator id + * @offset: OCMEM offset + * @size: OCMEM size + * @mode: access mode (WIDE/NARROW) + */ +int qcom_scm_ocmem_lock(enum qcom_scm_ocmem_client id, u32 offset, u32 size, + u32 mode) +{ + return __qcom_scm_ocmem_lock(__scm->dev, id, offset, size, mode); +} +EXPORT_SYMBOL(qcom_scm_ocmem_lock); + +/** + * qcom_scm_ocmem_unlock() - call OCMEM unlock interface to release an OCMEM + * region from the specified initiator + * + * @id: tz initiator id + * @offset: OCMEM offset + * @size: OCMEM size + */ +int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id, u32 offset, u32 size) +{ + return __qcom_scm_ocmem_unlock(__scm->dev, id, offset, size); +} +EXPORT_SYMBOL(qcom_scm_ocmem_unlock); + /** * qcom_scm_pas_init_image() - Initialize peripheral authentication service * state machine for a given peripheral, using the diff --git a/drivers/firmware/qcom_scm.h b/drivers/firmware/qcom_scm.h index 99506bd873c0..ef293ee67ec1 100644 --- a/drivers/firmware/qcom_scm.h +++ b/drivers/firmware/qcom_scm.h @@ -42,6 +42,15 @@ extern int __qcom_scm_hdcp_req(struct device *dev, extern void __qcom_scm_init(void); +#define QCOM_SCM_OCMEM_SVC 0xf +#define QCOM_SCM_OCMEM_LOCK_CMD 0x1 +#define QCOM_SCM_OCMEM_UNLOCK_CMD 0x2 + +extern int __qcom_scm_ocmem_lock(struct device *dev, u32 id, u32 offset, + u32 size, u32 mode); +extern int __qcom_scm_ocmem_unlock(struct device *dev, u32 id, u32 offset, + u32 size); + #define QCOM_SCM_SVC_PIL 0x2 #define QCOM_SCM_PAS_INIT_IMAGE_CMD 0x1 #define QCOM_SCM_PAS_MEM_SETUP_CMD 0x2 diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index 2d5eff506e13..b49b734d662c 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -24,6 +24,16 @@ struct qcom_scm_vmperm { int perm; }; +enum qcom_scm_ocmem_client { + QCOM_SCM_OCMEM_UNUSED_ID = 0x0, + QCOM_SCM_OCMEM_GRAPHICS_ID, + QCOM_SCM_OCMEM_VIDEO_ID, + QCOM_SCM_OCMEM_LP_AUDIO_ID, + QCOM_SCM_OCMEM_SENSORS_ID, + QCOM_SCM_OCMEM_OTHER_OS_ID, + QCOM_SCM_OCMEM_DEBUG_ID, +}; + #define QCOM_SCM_VMID_HLOS 0x3 #define QCOM_SCM_VMID_MSS_MSA 0xF #define QCOM_SCM_VMID_WLAN 0x18 @@ -41,6 +51,11 @@ extern bool qcom_scm_is_available(void); extern bool qcom_scm_hdcp_available(void); extern int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, u32 *resp); +extern bool qcom_scm_ocmem_lock_available(void); +extern int qcom_scm_ocmem_lock(enum qcom_scm_ocmem_client id, u32 offset, + u32 size, u32 mode); +extern int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id, u32 offset, + u32 size); extern bool qcom_scm_pas_supported(u32 peripheral); extern int qcom_scm_pas_init_image(u32 peripheral, const void *metadata, size_t size); -- cgit v1.2.3-71-gd317 From 0434a4061471a9afc2b2061add496e58ba4bb92d Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Fri, 23 Aug 2019 05:16:34 -0700 Subject: firmware: qcom: scm: add support to restore secure config to qcm_scm-32 Add support to restore the secure configuration for qcm_scm-32.c. This is needed by the On Chip MEMory (OCMEM) that is present on some Snapdragon devices. Signed-off-by: Rob Clark [masneyb@onstation.org: ported to latest kernel; set ctx_bank_num to spare parameter.] Signed-off-by: Brian Masney Reviewed-by: Bjorn Andersson Tested-by: Gabriel Francisco Signed-off-by: Rob Clark --- drivers/firmware/qcom_scm-32.c | 17 ++++++++++++++++- drivers/firmware/qcom_scm.c | 13 +++++++++++++ include/linux/qcom_scm.h | 11 +++++++++++ 3 files changed, 40 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/firmware/qcom_scm-32.c b/drivers/firmware/qcom_scm-32.c index 4c2514e5e249..5d90b7f5ab5a 100644 --- a/drivers/firmware/qcom_scm-32.c +++ b/drivers/firmware/qcom_scm-32.c @@ -617,7 +617,22 @@ int __qcom_scm_assign_mem(struct device *dev, phys_addr_t mem_region, int __qcom_scm_restore_sec_cfg(struct device *dev, u32 device_id, u32 spare) { - return -ENODEV; + struct msm_scm_sec_cfg { + __le32 id; + __le32 ctx_bank_num; + } cfg; + int ret, scm_ret = 0; + + cfg.id = cpu_to_le32(device_id); + cfg.ctx_bank_num = cpu_to_le32(spare); + + ret = qcom_scm_call(dev, QCOM_SCM_SVC_MP, QCOM_SCM_RESTORE_SEC_CFG, + &cfg, sizeof(cfg), &scm_ret, sizeof(scm_ret)); + + if (ret || scm_ret) + return ret ? ret : -EINVAL; + + return 0; } int __qcom_scm_iommu_secure_ptbl_size(struct device *dev, u32 spare, diff --git a/drivers/firmware/qcom_scm.c b/drivers/firmware/qcom_scm.c index 7e285ff3961d..27c1d98a34e6 100644 --- a/drivers/firmware/qcom_scm.c +++ b/drivers/firmware/qcom_scm.c @@ -367,6 +367,19 @@ static const struct reset_control_ops qcom_scm_pas_reset_ops = { .deassert = qcom_scm_pas_reset_deassert, }; +/** + * qcom_scm_restore_sec_cfg_available() - Check if secure environment + * supports restore security config interface. + * + * Return true if restore-cfg interface is supported, false if not. + */ +bool qcom_scm_restore_sec_cfg_available(void) +{ + return __qcom_scm_is_call_available(__scm->dev, QCOM_SCM_SVC_MP, + QCOM_SCM_RESTORE_SEC_CFG); +} +EXPORT_SYMBOL(qcom_scm_restore_sec_cfg_available); + int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare) { return __qcom_scm_restore_sec_cfg(__scm->dev, device_id, spare); diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index b49b734d662c..04382e1798e4 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -34,6 +34,16 @@ enum qcom_scm_ocmem_client { QCOM_SCM_OCMEM_DEBUG_ID, }; +enum qcom_scm_sec_dev_id { + QCOM_SCM_MDSS_DEV_ID = 1, + QCOM_SCM_OCMEM_DEV_ID = 5, + QCOM_SCM_PCIE0_DEV_ID = 11, + QCOM_SCM_PCIE1_DEV_ID = 12, + QCOM_SCM_GFX_DEV_ID = 18, + QCOM_SCM_UFS_DEV_ID = 19, + QCOM_SCM_ICE_DEV_ID = 20, +}; + #define QCOM_SCM_VMID_HLOS 0x3 #define QCOM_SCM_VMID_MSS_MSA 0xF #define QCOM_SCM_VMID_WLAN 0x18 @@ -70,6 +80,7 @@ extern int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz, extern void qcom_scm_cpu_power_down(u32 flags); extern u32 qcom_scm_get_version(void); extern int qcom_scm_set_remote_state(u32 state, u32 id); +extern bool qcom_scm_restore_sec_cfg_available(void); extern int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare); extern int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size); extern int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare); -- cgit v1.2.3-71-gd317 From 8c2a2b8c2ff680b1d0f715cf1f320722b762f9dd Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Thu, 3 Oct 2019 11:52:29 +0200 Subject: nvmem: core: add nvmem_device_find nvmem_device_find provides a way to search for nvmem devices with the help of a match function simlair to bus_find_device. Reviewed-by: Srinivas Kandagatla Acked-by: Srinivas Kandagatla Signed-off-by: Thomas Bogendoerfer Signed-off-by: Paul Burton Cc: Jonathan Corbet Cc: Ralf Baechle Cc: James Hogan Cc: Lee Jones Cc: David S. Miller Cc: Alessandro Zummo Cc: Alexandre Belloni Cc: Greg Kroah-Hartman Cc: Jiri Slaby Cc: linux-doc@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-mips@vger.kernel.org Cc: netdev@vger.kernel.org Cc: linux-rtc@vger.kernel.org Cc: linux-serial@vger.kernel.org --- Documentation/driver-api/nvmem.rst | 2 ++ drivers/nvmem/core.c | 61 +++++++++++++++++--------------------- include/linux/nvmem-consumer.h | 9 ++++++ 3 files changed, 38 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/Documentation/driver-api/nvmem.rst b/Documentation/driver-api/nvmem.rst index d9d958d5c824..287e86819640 100644 --- a/Documentation/driver-api/nvmem.rst +++ b/Documentation/driver-api/nvmem.rst @@ -129,6 +129,8 @@ To facilitate such consumers NVMEM framework provides below apis:: struct nvmem_device *nvmem_device_get(struct device *dev, const char *name); struct nvmem_device *devm_nvmem_device_get(struct device *dev, const char *name); + struct nvmem_device *nvmem_device_find(void *data, + int (*match)(struct device *dev, const void *data)); void nvmem_device_put(struct nvmem_device *nvmem); int nvmem_device_read(struct nvmem_device *nvmem, unsigned int offset, size_t bytes, void *buf); diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 057d1ff87d5d..9f1ee9c766ec 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -76,33 +76,6 @@ static struct bus_type nvmem_bus_type = { .name = "nvmem", }; -static struct nvmem_device *of_nvmem_find(struct device_node *nvmem_np) -{ - struct device *d; - - if (!nvmem_np) - return NULL; - - d = bus_find_device_by_of_node(&nvmem_bus_type, nvmem_np); - - if (!d) - return NULL; - - return to_nvmem_device(d); -} - -static struct nvmem_device *nvmem_find(const char *name) -{ - struct device *d; - - d = bus_find_device_by_name(&nvmem_bus_type, NULL, name); - - if (!d) - return NULL; - - return to_nvmem_device(d); -} - static void nvmem_cell_drop(struct nvmem_cell *cell) { blocking_notifier_call_chain(&nvmem_notifier, NVMEM_CELL_REMOVE, cell); @@ -532,13 +505,16 @@ int devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem) } EXPORT_SYMBOL(devm_nvmem_unregister); -static struct nvmem_device *__nvmem_device_get(struct device_node *np, - const char *nvmem_name) +static struct nvmem_device *__nvmem_device_get(void *data, + int (*match)(struct device *dev, const void *data)) { struct nvmem_device *nvmem = NULL; + struct device *dev; mutex_lock(&nvmem_mutex); - nvmem = np ? of_nvmem_find(np) : nvmem_find(nvmem_name); + dev = bus_find_device(&nvmem_bus_type, NULL, data, match); + if (dev) + nvmem = to_nvmem_device(dev); mutex_unlock(&nvmem_mutex); if (!nvmem) return ERR_PTR(-EPROBE_DEFER); @@ -587,7 +563,7 @@ struct nvmem_device *of_nvmem_device_get(struct device_node *np, const char *id) if (!nvmem_np) return ERR_PTR(-ENOENT); - return __nvmem_device_get(nvmem_np, NULL); + return __nvmem_device_get(nvmem_np, device_match_of_node); } EXPORT_SYMBOL_GPL(of_nvmem_device_get); #endif @@ -613,10 +589,26 @@ struct nvmem_device *nvmem_device_get(struct device *dev, const char *dev_name) } - return __nvmem_device_get(NULL, dev_name); + return __nvmem_device_get((void *)dev_name, device_match_name); } EXPORT_SYMBOL_GPL(nvmem_device_get); +/** + * nvmem_device_find() - Find nvmem device with matching function + * + * @data: Data to pass to match function + * @match: Callback function to check device + * + * Return: ERR_PTR() on error or a valid pointer to a struct nvmem_device + * on success. + */ +struct nvmem_device *nvmem_device_find(void *data, + int (*match)(struct device *dev, const void *data)) +{ + return __nvmem_device_get(data, match); +} +EXPORT_SYMBOL_GPL(nvmem_device_find); + static int devm_nvmem_device_match(struct device *dev, void *res, void *data) { struct nvmem_device **nvmem = res; @@ -710,7 +702,8 @@ nvmem_cell_get_from_lookup(struct device *dev, const char *con_id) if ((strcmp(lookup->dev_id, dev_id) == 0) && (strcmp(lookup->con_id, con_id) == 0)) { /* This is the right entry. */ - nvmem = __nvmem_device_get(NULL, lookup->nvmem_name); + nvmem = __nvmem_device_get((void *)lookup->nvmem_name, + device_match_name); if (IS_ERR(nvmem)) { /* Provider may not be registered yet. */ cell = ERR_CAST(nvmem); @@ -780,7 +773,7 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, const char *id) if (!nvmem_np) return ERR_PTR(-EINVAL); - nvmem = __nvmem_device_get(nvmem_np, NULL); + nvmem = __nvmem_device_get(nvmem_np, device_match_of_node); of_node_put(nvmem_np); if (IS_ERR(nvmem)) return ERR_CAST(nvmem); diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 8f8be5b00060..02dc4aa992b2 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -89,6 +89,9 @@ void nvmem_del_cell_lookups(struct nvmem_cell_lookup *entries, int nvmem_register_notifier(struct notifier_block *nb); int nvmem_unregister_notifier(struct notifier_block *nb); +struct nvmem_device *nvmem_device_find(void *data, + int (*match)(struct device *dev, const void *data)); + #else static inline struct nvmem_cell *nvmem_cell_get(struct device *dev, @@ -204,6 +207,12 @@ static inline int nvmem_unregister_notifier(struct notifier_block *nb) return -EOPNOTSUPP; } +static inline struct nvmem_device *nvmem_device_find(void *data, + int (*match)(struct device *dev, const void *data)) +{ + return NULL; +} + #endif /* CONFIG_NVMEM */ #if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF) -- cgit v1.2.3-71-gd317 From b42faeee718ce13ef6eb99c24880b58deb54c8fa Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 5 Sep 2019 04:01:12 +0300 Subject: spi: Add a PTP system timestamp to the transfer structure SPI is one of the interfaces used to access devices which have a POSIX clock driver (real time clocks, 1588 timers etc). The fact that the SPI bus is slow is not what the main problem is, but rather the fact that drivers don't take a constant amount of time in transferring data over SPI. When there is a high delay in the readout of time, there will be uncertainty in the value that has been read out of the peripheral. When that delay is constant, the uncertainty can at least be approximated with a certain accuracy which is fine more often than not. Timing jitter occurs all over in the kernel code, and is mainly caused by having to let go of the CPU for various reasons such as preemption, servicing interrupts, going to sleep, etc. Another major reason is CPU dynamic frequency scaling. It turns out that the problem of retrieving time from a SPI peripheral with high accuracy can be solved by the use of "PTP system timestamping" - a mechanism to correlate the time when the device has snapshotted its internal time counter with the Linux system time at that same moment. This is sufficient for having a precise time measurement - it is not necessary for the whole SPI transfer to be transmitted "as fast as possible", or "as low-jitter as possible". The system has to be low-jitter for a very short amount of time to be effective. This patch introduces a PTP system timestamping mechanism in struct spi_transfer. This is to be used by SPI device drivers when they need to know the exact time at which the underlying device's time was snapshotted. More often than not, SPI peripherals have a very exact timing for when their SPI-to-interconnect bridge issues a transaction for snapshotting and reading the time register, and that will be dependent on when the SPI-to-interconnect bridge figures out that this is what it should do, aka as soon as it sees byte N of the SPI transfer. Since spi_device drivers are the ones who'd know best how the peripheral behaves in this regard, expose a mechanism in spi_transfer which allows them to specify which word (or word range) from the transfer should be timestamped. Add a default implementation of the PTP system timestamping in the SPI core. This is not going to be satisfactory performance-wise, but should at least increase the likelihood that SPI device drivers will use PTP system timestamping in the future. There are 3 entry points from the core towards the SPI controller drivers: - transfer_one: The driver is passed individual spi_transfers to execute. This is the easiest to timestamp. - transfer_one_message: The core passes the driver an entire spi_message (a potential batch of spi_transfers). The core puts the same pre and post timestamp to all transfers within a message. This is not ideal, but nothing better can be done by default anyway, since the core has no insight into how the driver batches the transfers. - transfer: Like transfer_one_message, but for unqueued drivers (i.e. the driver implements its own queue scheduling). Signed-off-by: Vladimir Oltean Link: https://lore.kernel.org/r/20190905010114.26718-3-olteanv@gmail.com Signed-off-by: Mark Brown --- drivers/spi/spi.c | 127 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/spi/spi.h | 61 +++++++++++++++++++++++ 2 files changed, 188 insertions(+) (limited to 'include/linux') diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index f9502dbbb5c1..9bb36c32cbf9 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1171,6 +1171,11 @@ static int spi_transfer_one_message(struct spi_controller *ctlr, spi_statistics_add_transfer_stats(statm, xfer, ctlr); spi_statistics_add_transfer_stats(stats, xfer, ctlr); + if (!ctlr->ptp_sts_supported) { + xfer->ptp_sts_word_pre = 0; + ptp_read_system_prets(xfer->ptp_sts); + } + if (xfer->tx_buf || xfer->rx_buf) { reinit_completion(&ctlr->xfer_completion); @@ -1197,6 +1202,11 @@ static int spi_transfer_one_message(struct spi_controller *ctlr, xfer->len); } + if (!ctlr->ptp_sts_supported) { + ptp_read_system_postts(xfer->ptp_sts); + xfer->ptp_sts_word_post = xfer->len; + } + trace_spi_transfer_stop(msg, xfer); if (msg->status != -EINPROGRESS) @@ -1265,6 +1275,7 @@ EXPORT_SYMBOL_GPL(spi_finalize_current_transfer); */ static void __spi_pump_messages(struct spi_controller *ctlr, bool in_kthread) { + struct spi_transfer *xfer; struct spi_message *msg; bool was_busy = false; unsigned long flags; @@ -1391,6 +1402,13 @@ static void __spi_pump_messages(struct spi_controller *ctlr, bool in_kthread) goto out; } + if (!ctlr->ptp_sts_supported && !ctlr->transfer_one) { + list_for_each_entry(xfer, &msg->transfers, transfer_list) { + xfer->ptp_sts_word_pre = 0; + ptp_read_system_prets(xfer->ptp_sts); + } + } + ret = ctlr->transfer_one_message(ctlr, msg); if (ret) { dev_err(&ctlr->dev, @@ -1418,6 +1436,99 @@ static void spi_pump_messages(struct kthread_work *work) __spi_pump_messages(ctlr, true); } +/** + * spi_take_timestamp_pre - helper for drivers to collect the beginning of the + * TX timestamp for the requested byte from the SPI + * transfer. The frequency with which this function + * must be called (once per word, once for the whole + * transfer, once per batch of words etc) is arbitrary + * as long as the @tx buffer offset is greater than or + * equal to the requested byte at the time of the + * call. The timestamp is only taken once, at the + * first such call. It is assumed that the driver + * advances its @tx buffer pointer monotonically. + * @ctlr: Pointer to the spi_controller structure of the driver + * @xfer: Pointer to the transfer being timestamped + * @tx: Pointer to the current word within the xfer->tx_buf that the driver is + * preparing to transmit right now. + * @irqs_off: If true, will disable IRQs and preemption for the duration of the + * transfer, for less jitter in time measurement. Only compatible + * with PIO drivers. If true, must follow up with + * spi_take_timestamp_post or otherwise system will crash. + * WARNING: for fully predictable results, the CPU frequency must + * also be under control (governor). + */ +void spi_take_timestamp_pre(struct spi_controller *ctlr, + struct spi_transfer *xfer, + const void *tx, bool irqs_off) +{ + u8 bytes_per_word = DIV_ROUND_UP(xfer->bits_per_word, 8); + + if (!xfer->ptp_sts) + return; + + if (xfer->timestamped_pre) + return; + + if (tx < (xfer->tx_buf + xfer->ptp_sts_word_pre * bytes_per_word)) + return; + + /* Capture the resolution of the timestamp */ + xfer->ptp_sts_word_pre = (tx - xfer->tx_buf) / bytes_per_word; + + xfer->timestamped_pre = true; + + if (irqs_off) { + local_irq_save(ctlr->irq_flags); + preempt_disable(); + } + + ptp_read_system_prets(xfer->ptp_sts); +} +EXPORT_SYMBOL_GPL(spi_take_timestamp_pre); + +/** + * spi_take_timestamp_post - helper for drivers to collect the end of the + * TX timestamp for the requested byte from the SPI + * transfer. Can be called with an arbitrary + * frequency: only the first call where @tx exceeds + * or is equal to the requested word will be + * timestamped. + * @ctlr: Pointer to the spi_controller structure of the driver + * @xfer: Pointer to the transfer being timestamped + * @tx: Pointer to the current word within the xfer->tx_buf that the driver has + * just transmitted. + * @irqs_off: If true, will re-enable IRQs and preemption for the local CPU. + */ +void spi_take_timestamp_post(struct spi_controller *ctlr, + struct spi_transfer *xfer, + const void *tx, bool irqs_off) +{ + u8 bytes_per_word = DIV_ROUND_UP(xfer->bits_per_word, 8); + + if (!xfer->ptp_sts) + return; + + if (xfer->timestamped_post) + return; + + if (tx < (xfer->tx_buf + xfer->ptp_sts_word_post * bytes_per_word)) + return; + + ptp_read_system_postts(xfer->ptp_sts); + + if (irqs_off) { + local_irq_restore(ctlr->irq_flags); + preempt_enable(); + } + + /* Capture the resolution of the timestamp */ + xfer->ptp_sts_word_post = (tx - xfer->tx_buf) / bytes_per_word; + + xfer->timestamped_post = true; +} +EXPORT_SYMBOL_GPL(spi_take_timestamp_post); + /** * spi_set_thread_rt - set the controller to pump at realtime priority * @ctlr: controller to boost priority of @@ -1503,6 +1614,7 @@ EXPORT_SYMBOL_GPL(spi_get_next_queued_message); */ void spi_finalize_current_message(struct spi_controller *ctlr) { + struct spi_transfer *xfer; struct spi_message *mesg; unsigned long flags; int ret; @@ -1511,6 +1623,13 @@ void spi_finalize_current_message(struct spi_controller *ctlr) mesg = ctlr->cur_msg; spin_unlock_irqrestore(&ctlr->queue_lock, flags); + if (!ctlr->ptp_sts_supported && !ctlr->transfer_one) { + list_for_each_entry(xfer, &mesg->transfers, transfer_list) { + ptp_read_system_postts(xfer->ptp_sts); + xfer->ptp_sts_word_post = xfer->len; + } + } + spi_unmap_msg(ctlr, mesg); if (ctlr->cur_msg_prepared && ctlr->unprepare_message) { @@ -3273,6 +3392,7 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message) static int __spi_async(struct spi_device *spi, struct spi_message *message) { struct spi_controller *ctlr = spi->controller; + struct spi_transfer *xfer; /* * Some controllers do not support doing regular SPI transfers. Return @@ -3288,6 +3408,13 @@ static int __spi_async(struct spi_device *spi, struct spi_message *message) trace_spi_message_submit(message); + if (!ctlr->ptp_sts_supported) { + list_for_each_entry(xfer, &message->transfers, transfer_list) { + xfer->ptp_sts_word_pre = 0; + ptp_read_system_prets(xfer->ptp_sts); + } + } + return ctlr->transfer(spi, message); } diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index af4f265d0f67..27f6b046cf92 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -13,6 +13,7 @@ #include #include #include +#include struct dma_chan; struct property_entry; @@ -409,6 +410,12 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @fw_translate_cs: If the boot firmware uses different numbering scheme * what Linux expects, this optional hook can be used to translate * between the two. + * @ptp_sts_supported: If the driver sets this to true, it must provide a + * time snapshot in @spi_transfer->ptp_sts as close as possible to the + * moment in time when @spi_transfer->ptp_sts_word_pre and + * @spi_transfer->ptp_sts_word_post were transmitted. + * If the driver does not set this, the SPI core takes the snapshot as + * close to the driver hand-over as possible. * * Each SPI controller can communicate with one or more @spi_device * children. These make a small bus, sharing MOSI, MISO and SCK signals @@ -604,6 +611,15 @@ struct spi_controller { void *dummy_tx; int (*fw_translate_cs)(struct spi_controller *ctlr, unsigned cs); + + /* + * Driver sets this field to indicate it is able to snapshot SPI + * transfers (needed e.g. for reading the time of POSIX clocks) + */ + bool ptp_sts_supported; + + /* Interrupt enable state during PTP system timestamping */ + unsigned long irq_flags; }; static inline void *spi_controller_get_devdata(struct spi_controller *ctlr) @@ -644,6 +660,14 @@ extern struct spi_message *spi_get_next_queued_message(struct spi_controller *ct extern void spi_finalize_current_message(struct spi_controller *ctlr); extern void spi_finalize_current_transfer(struct spi_controller *ctlr); +/* Helper calls for driver to timestamp transfer */ +void spi_take_timestamp_pre(struct spi_controller *ctlr, + struct spi_transfer *xfer, + const void *tx, bool irqs_off); +void spi_take_timestamp_post(struct spi_controller *ctlr, + struct spi_transfer *xfer, + const void *tx, bool irqs_off); + /* the spi driver core manages memory for the spi_controller classdev */ extern struct spi_controller *__spi_alloc_controller(struct device *host, unsigned int size, bool slave); @@ -753,6 +777,35 @@ extern void spi_res_release(struct spi_controller *ctlr, * @transfer_list: transfers are sequenced through @spi_message.transfers * @tx_sg: Scatterlist for transmit, currently not for client use * @rx_sg: Scatterlist for receive, currently not for client use + * @ptp_sts_word_pre: The word (subject to bits_per_word semantics) offset + * within @tx_buf for which the SPI device is requesting that the time + * snapshot for this transfer begins. Upon completing the SPI transfer, + * this value may have changed compared to what was requested, depending + * on the available snapshotting resolution (DMA transfer, + * @ptp_sts_supported is false, etc). + * @ptp_sts_word_post: See @ptp_sts_word_post. The two can be equal (meaning + * that a single byte should be snapshotted). + * If the core takes care of the timestamp (if @ptp_sts_supported is false + * for this controller), it will set @ptp_sts_word_pre to 0, and + * @ptp_sts_word_post to the length of the transfer. This is done + * purposefully (instead of setting to spi_transfer->len - 1) to denote + * that a transfer-level snapshot taken from within the driver may still + * be of higher quality. + * @ptp_sts: Pointer to a memory location held by the SPI slave device where a + * PTP system timestamp structure may lie. If drivers use PIO or their + * hardware has some sort of assist for retrieving exact transfer timing, + * they can (and should) assert @ptp_sts_supported and populate this + * structure using the ptp_read_system_*ts helper functions. + * The timestamp must represent the time at which the SPI slave device has + * processed the word, i.e. the "pre" timestamp should be taken before + * transmitting the "pre" word, and the "post" timestamp after receiving + * transmit confirmation from the controller for the "post" word. + * @timestamped_pre: Set by the SPI controller driver to denote it has acted + * upon the @ptp_sts request. Not set when the SPI core has taken care of + * the task. SPI device drivers are free to print a warning if this comes + * back unset and they need the better resolution. + * @timestamped_post: See above. The reason why both exist is that these + * booleans are also used to keep state in the core SPI logic. * * SPI transfers always write the same number of bytes as they read. * Protocol drivers should always provide @rx_buf and/or @tx_buf. @@ -842,6 +895,14 @@ struct spi_transfer { u32 effective_speed_hz; + unsigned int ptp_sts_word_pre; + unsigned int ptp_sts_word_post; + + struct ptp_system_timestamp *ptp_sts; + + bool timestamped_pre; + bool timestamped_post; + struct list_head transfer_list; }; -- cgit v1.2.3-71-gd317 From 4b7d4d453fc46769394e31d1cb19088f49897b59 Mon Sep 17 00:00:00 2001 From: Harish Kasiviswanathan Date: Thu, 16 May 2019 11:37:16 -0400 Subject: device_cgroup: Export devcgroup_check_permission For AMD compute (amdkfd) driver. All AMD compute devices are exported via single device node /dev/kfd. As a result devices cannot be controlled individually using device cgroup. AMD compute devices will rely on its graphics counterpart that exposes /dev/dri/renderN node for each device. For each task (based on its cgroup), KFD driver will check if /dev/dri/renderN node is accessible before exposing it. Signed-off-by: Harish Kasiviswanathan Acked-by: Tejun Heo Acked-by: Felix Kuehling Reviewed-by: Roman Gushchin Signed-off-by: Alex Deucher --- include/linux/device_cgroup.h | 19 ++++--------------- security/device_cgroup.c | 15 +++++++++++++-- 2 files changed, 17 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device_cgroup.h b/include/linux/device_cgroup.h index 8557efe096dc..fa35b52e0002 100644 --- a/include/linux/device_cgroup.h +++ b/include/linux/device_cgroup.h @@ -12,26 +12,15 @@ #define DEVCG_DEV_ALL 4 /* this represents all devices */ #ifdef CONFIG_CGROUP_DEVICE -extern int __devcgroup_check_permission(short type, u32 major, u32 minor, - short access); +int devcgroup_check_permission(short type, u32 major, u32 minor, + short access); #else -static inline int __devcgroup_check_permission(short type, u32 major, u32 minor, - short access) +static inline int devcgroup_check_permission(short type, u32 major, u32 minor, + short access) { return 0; } #endif #if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) -static inline int devcgroup_check_permission(short type, u32 major, u32 minor, - short access) -{ - int rc = BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access); - - if (rc) - return -EPERM; - - return __devcgroup_check_permission(type, major, minor, access); -} - static inline int devcgroup_inode_permission(struct inode *inode, int mask) { short type, access = 0; diff --git a/security/device_cgroup.c b/security/device_cgroup.c index 725674f3276d..7d0f8f7431ff 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -801,8 +801,8 @@ struct cgroup_subsys devices_cgrp_subsys = { * * returns 0 on success, -EPERM case the operation is not permitted */ -int __devcgroup_check_permission(short type, u32 major, u32 minor, - short access) +static int __devcgroup_check_permission(short type, u32 major, u32 minor, + short access) { struct dev_cgroup *dev_cgroup; bool rc; @@ -824,3 +824,14 @@ int __devcgroup_check_permission(short type, u32 major, u32 minor, return 0; } + +int devcgroup_check_permission(short type, u32 major, u32 minor, short access) +{ + int rc = BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access); + + if (rc) + return -EPERM; + + return __devcgroup_check_permission(type, major, minor, access); +} +EXPORT_SYMBOL(devcgroup_check_permission); -- cgit v1.2.3-71-gd317 From 2c3d0c9ffd24d9b4c62c5dfb2104695a614be28c Mon Sep 17 00:00:00 2001 From: Phil Reid Date: Thu, 19 Sep 2019 22:36:08 +0800 Subject: iio: core: Add optional symbolic label to device attributes If a label is defined in the device tree for this device add that to the device specific attributes. This is useful for userspace to be able to identify an individual device when multiple identical chips are present in the system. Tested-by: Michal Simek Signed-off-by: Phil Reid Signed-off-by: Jonathan Cameron --- drivers/iio/industrialio-core.c | 17 +++++++++++++++++ include/linux/iio/iio.h | 2 ++ 2 files changed, 19 insertions(+) (limited to 'include/linux') diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 524a686077ca..f72c2dc5f703 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -1238,6 +1238,16 @@ static ssize_t iio_show_dev_name(struct device *dev, static DEVICE_ATTR(name, S_IRUGO, iio_show_dev_name, NULL); +static ssize_t iio_show_dev_label(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct iio_dev *indio_dev = dev_to_iio_dev(dev); + return snprintf(buf, PAGE_SIZE, "%s\n", indio_dev->label); +} + +static DEVICE_ATTR(label, S_IRUGO, iio_show_dev_label, NULL); + static ssize_t iio_show_timestamp_clock(struct device *dev, struct device_attribute *attr, char *buf) @@ -1354,6 +1364,8 @@ static int iio_device_register_sysfs(struct iio_dev *indio_dev) if (indio_dev->name) attrcount++; + if (indio_dev->label) + attrcount++; if (clk) attrcount++; @@ -1376,6 +1388,8 @@ static int iio_device_register_sysfs(struct iio_dev *indio_dev) indio_dev->chan_attr_group.attrs[attrn++] = &p->dev_attr.attr; if (indio_dev->name) indio_dev->chan_attr_group.attrs[attrn++] = &dev_attr_name.attr; + if (indio_dev->label) + indio_dev->chan_attr_group.attrs[attrn++] = &dev_attr_label.attr; if (clk) indio_dev->chan_attr_group.attrs[attrn++] = clk; @@ -1647,6 +1661,9 @@ int __iio_device_register(struct iio_dev *indio_dev, struct module *this_mod) if (!indio_dev->dev.of_node && indio_dev->dev.parent) indio_dev->dev.of_node = indio_dev->dev.parent->of_node; + indio_dev->label = of_get_property(indio_dev->dev.of_node, "label", + NULL); + ret = iio_check_unique_scan_index(indio_dev); if (ret < 0) return ret; diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 8e132cf819e4..862ce0019eba 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -510,6 +510,7 @@ struct iio_buffer_setup_ops { * attributes * @chan_attr_group: [INTERN] group for all attrs in base directory * @name: [DRIVER] name of the device. + * @label: [DRIVER] unique name to identify which device this is * @info: [DRIVER] callbacks and constant info from driver * @clock_id: [INTERN] timestamping clock posix identifier * @info_exist_lock: [INTERN] lock to prevent use during removal @@ -553,6 +554,7 @@ struct iio_dev { struct list_head channel_attr_list; struct attribute_group chan_attr_group; const char *name; + const char *label; const struct iio_info *info; clockid_t clock_id; struct mutex info_exist_lock; -- cgit v1.2.3-71-gd317 From 017f77c050a3bc1f1ff877d1f265beeee26d7dea Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Thu, 3 Oct 2019 20:56:01 +0100 Subject: netfilter: ipset: add a coding-style fix to ip_set_ext_destroy. Use a local variable to hold comment in order to align the arguments of ip_set_comment_free properly. Signed-off-by: Jeremy Sowden Acked-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 9bc255a8461b..9fee4837d02c 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -269,9 +269,11 @@ ip_set_ext_destroy(struct ip_set *set, void *data) /* Check that the extension is enabled for the set and * call it's destroy function for its extension part in data. */ - if (SET_WITH_COMMENT(set)) - ip_set_extensions[IPSET_EXT_ID_COMMENT].destroy( - set, ext_comment(data, set)); + if (SET_WITH_COMMENT(set)) { + struct ip_set_comment *c = ext_comment(data, set); + + ip_set_extensions[IPSET_EXT_ID_COMMENT].destroy(set, c); + } } static inline int -- cgit v1.2.3-71-gd317 From 94177f6e11c74b6ca3bcf7f65d3d74f00bbd6a8c Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Thu, 3 Oct 2019 20:56:03 +0100 Subject: netfilter: ipset: move ip_set_comment functions from ip_set.h to ip_set_core.c. Most of the functions are only called from within ip_set_core.c. The exception is ip_set_init_comment. However, this is too complex to be a good candidate for a static inline function. Move it to ip_set_core.c, change its linkage to extern and export it, leaving a declaration in ip_set.h. ip_set_comment_free is only used as an extension destructor, so change its prototype to match and drop cast. Signed-off-by: Jeremy Sowden Acked-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 63 ++------------------------------ net/netfilter/ipset/ip_set_core.c | 66 +++++++++++++++++++++++++++++++++- 2 files changed, 67 insertions(+), 62 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 9fee4837d02c..985c9bb1ab65 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -521,67 +521,8 @@ ip_set_timeout_get(const unsigned long *timeout) return t == 0 ? 1 : t; } -static inline char* -ip_set_comment_uget(struct nlattr *tb) -{ - return nla_data(tb); -} - -/* Called from uadd only, protected by the set spinlock. - * The kadt functions don't use the comment extensions in any way. - */ -static inline void -ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, - const struct ip_set_ext *ext) -{ - struct ip_set_comment_rcu *c = rcu_dereference_protected(comment->c, 1); - size_t len = ext->comment ? strlen(ext->comment) : 0; - - if (unlikely(c)) { - set->ext_size -= sizeof(*c) + strlen(c->str) + 1; - kfree_rcu(c, rcu); - rcu_assign_pointer(comment->c, NULL); - } - if (!len) - return; - if (unlikely(len > IPSET_MAX_COMMENT_SIZE)) - len = IPSET_MAX_COMMENT_SIZE; - c = kmalloc(sizeof(*c) + len + 1, GFP_ATOMIC); - if (unlikely(!c)) - return; - strlcpy(c->str, ext->comment, len + 1); - set->ext_size += sizeof(*c) + strlen(c->str) + 1; - rcu_assign_pointer(comment->c, c); -} - -/* Used only when dumping a set, protected by rcu_read_lock() */ -static inline int -ip_set_put_comment(struct sk_buff *skb, const struct ip_set_comment *comment) -{ - struct ip_set_comment_rcu *c = rcu_dereference(comment->c); - - if (!c) - return 0; - return nla_put_string(skb, IPSET_ATTR_COMMENT, c->str); -} - -/* Called from uadd/udel, flush or the garbage collectors protected - * by the set spinlock. - * Called when the set is destroyed and when there can't be any user - * of the set data anymore. - */ -static inline void -ip_set_comment_free(struct ip_set *set, struct ip_set_comment *comment) -{ - struct ip_set_comment_rcu *c; - - c = rcu_dereference_protected(comment->c, 1); - if (unlikely(!c)) - return; - set->ext_size -= sizeof(*c) + strlen(c->str) + 1; - kfree_rcu(c, rcu); - rcu_assign_pointer(comment->c, NULL); -} +void ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, + const struct ip_set_ext *ext); static inline void ip_set_add_bytes(u64 bytes, struct ip_set_counter *counter) diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 04266295a750..73daea6d4bd5 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -325,6 +325,70 @@ ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr) } EXPORT_SYMBOL_GPL(ip_set_get_ipaddr6); +static char * +ip_set_comment_uget(struct nlattr *tb) +{ + return nla_data(tb); +} + +/* Called from uadd only, protected by the set spinlock. + * The kadt functions don't use the comment extensions in any way. + */ +void +ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, + const struct ip_set_ext *ext) +{ + struct ip_set_comment_rcu *c = rcu_dereference_protected(comment->c, 1); + size_t len = ext->comment ? strlen(ext->comment) : 0; + + if (unlikely(c)) { + set->ext_size -= sizeof(*c) + strlen(c->str) + 1; + kfree_rcu(c, rcu); + rcu_assign_pointer(comment->c, NULL); + } + if (!len) + return; + if (unlikely(len > IPSET_MAX_COMMENT_SIZE)) + len = IPSET_MAX_COMMENT_SIZE; + c = kmalloc(sizeof(*c) + len + 1, GFP_ATOMIC); + if (unlikely(!c)) + return; + strlcpy(c->str, ext->comment, len + 1); + set->ext_size += sizeof(*c) + strlen(c->str) + 1; + rcu_assign_pointer(comment->c, c); +} +EXPORT_SYMBOL_GPL(ip_set_init_comment); + +/* Used only when dumping a set, protected by rcu_read_lock() */ +static int +ip_set_put_comment(struct sk_buff *skb, const struct ip_set_comment *comment) +{ + struct ip_set_comment_rcu *c = rcu_dereference(comment->c); + + if (!c) + return 0; + return nla_put_string(skb, IPSET_ATTR_COMMENT, c->str); +} + +/* Called from uadd/udel, flush or the garbage collectors protected + * by the set spinlock. + * Called when the set is destroyed and when there can't be any user + * of the set data anymore. + */ +static void +ip_set_comment_free(struct ip_set *set, void *ptr) +{ + struct ip_set_comment *comment = ptr; + struct ip_set_comment_rcu *c; + + c = rcu_dereference_protected(comment->c, 1); + if (unlikely(!c)) + return; + set->ext_size -= sizeof(*c) + strlen(c->str) + 1; + kfree_rcu(c, rcu); + rcu_assign_pointer(comment->c, NULL); +} + typedef void (*destroyer)(struct ip_set *, void *); /* ipset data extension types, in size order */ @@ -351,7 +415,7 @@ const struct ip_set_ext_type ip_set_extensions[] = { .flag = IPSET_FLAG_WITH_COMMENT, .len = sizeof(struct ip_set_comment), .align = __alignof__(struct ip_set_comment), - .destroy = (destroyer) ip_set_comment_free, + .destroy = ip_set_comment_free, }, }; EXPORT_SYMBOL_GPL(ip_set_extensions); -- cgit v1.2.3-71-gd317 From 2398a97688f1aaca09d0a5a809f361e2abf5ff3c Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Thu, 3 Oct 2019 20:56:04 +0100 Subject: netfilter: ipset: move functions to ip_set_core.c. Several inline functions in ip_set.h are only called in ip_set_core.c: move them and remove inline function specifier. Signed-off-by: Jeremy Sowden Acked-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 102 --------------------------------- net/netfilter/ipset/ip_set_core.c | 102 +++++++++++++++++++++++++++++++++ 2 files changed, 102 insertions(+), 102 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 985c9bb1ab65..44f6de8a1733 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -508,86 +508,9 @@ ip_set_timeout_set(unsigned long *timeout, u32 value) *timeout = t; } -static inline u32 -ip_set_timeout_get(const unsigned long *timeout) -{ - u32 t; - - if (*timeout == IPSET_ELEM_PERMANENT) - return 0; - - t = jiffies_to_msecs(*timeout - jiffies)/MSEC_PER_SEC; - /* Zero value in userspace means no timeout */ - return t == 0 ? 1 : t; -} - void ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, const struct ip_set_ext *ext); -static inline void -ip_set_add_bytes(u64 bytes, struct ip_set_counter *counter) -{ - atomic64_add((long long)bytes, &(counter)->bytes); -} - -static inline void -ip_set_add_packets(u64 packets, struct ip_set_counter *counter) -{ - atomic64_add((long long)packets, &(counter)->packets); -} - -static inline u64 -ip_set_get_bytes(const struct ip_set_counter *counter) -{ - return (u64)atomic64_read(&(counter)->bytes); -} - -static inline u64 -ip_set_get_packets(const struct ip_set_counter *counter) -{ - return (u64)atomic64_read(&(counter)->packets); -} - -static inline bool -ip_set_match_counter(u64 counter, u64 match, u8 op) -{ - switch (op) { - case IPSET_COUNTER_NONE: - return true; - case IPSET_COUNTER_EQ: - return counter == match; - case IPSET_COUNTER_NE: - return counter != match; - case IPSET_COUNTER_LT: - return counter < match; - case IPSET_COUNTER_GT: - return counter > match; - } - return false; -} - -static inline void -ip_set_update_counter(struct ip_set_counter *counter, - const struct ip_set_ext *ext, u32 flags) -{ - if (ext->packets != ULLONG_MAX && - !(flags & IPSET_FLAG_SKIP_COUNTER_UPDATE)) { - ip_set_add_bytes(ext->bytes, counter); - ip_set_add_packets(ext->packets, counter); - } -} - -static inline bool -ip_set_put_counter(struct sk_buff *skb, const struct ip_set_counter *counter) -{ - return nla_put_net64(skb, IPSET_ATTR_BYTES, - cpu_to_be64(ip_set_get_bytes(counter)), - IPSET_ATTR_PAD) || - nla_put_net64(skb, IPSET_ATTR_PACKETS, - cpu_to_be64(ip_set_get_packets(counter)), - IPSET_ATTR_PAD); -} - static inline void ip_set_init_counter(struct ip_set_counter *counter, const struct ip_set_ext *ext) @@ -598,31 +521,6 @@ ip_set_init_counter(struct ip_set_counter *counter, atomic64_set(&(counter)->packets, (long long)(ext->packets)); } -static inline void -ip_set_get_skbinfo(struct ip_set_skbinfo *skbinfo, - const struct ip_set_ext *ext, - struct ip_set_ext *mext, u32 flags) -{ - mext->skbinfo = *skbinfo; -} - -static inline bool -ip_set_put_skbinfo(struct sk_buff *skb, const struct ip_set_skbinfo *skbinfo) -{ - /* Send nonzero parameters only */ - return ((skbinfo->skbmark || skbinfo->skbmarkmask) && - nla_put_net64(skb, IPSET_ATTR_SKBMARK, - cpu_to_be64((u64)skbinfo->skbmark << 32 | - skbinfo->skbmarkmask), - IPSET_ATTR_PAD)) || - (skbinfo->skbprio && - nla_put_net32(skb, IPSET_ATTR_SKBPRIO, - cpu_to_be32(skbinfo->skbprio))) || - (skbinfo->skbqueue && - nla_put_net16(skb, IPSET_ATTR_SKBQUEUE, - cpu_to_be16(skbinfo->skbqueue))); -} - static inline void ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo, const struct ip_set_ext *ext) diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 73daea6d4bd5..30bc7df2f4cf 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -325,6 +325,19 @@ ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr) } EXPORT_SYMBOL_GPL(ip_set_get_ipaddr6); +static u32 +ip_set_timeout_get(const unsigned long *timeout) +{ + u32 t; + + if (*timeout == IPSET_ELEM_PERMANENT) + return 0; + + t = jiffies_to_msecs(*timeout - jiffies) / MSEC_PER_SEC; + /* Zero value in userspace means no timeout */ + return t == 0 ? 1 : t; +} + static char * ip_set_comment_uget(struct nlattr *tb) { @@ -510,6 +523,46 @@ ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[], } EXPORT_SYMBOL_GPL(ip_set_get_extensions); +static u64 +ip_set_get_bytes(const struct ip_set_counter *counter) +{ + return (u64)atomic64_read(&(counter)->bytes); +} + +static u64 +ip_set_get_packets(const struct ip_set_counter *counter) +{ + return (u64)atomic64_read(&(counter)->packets); +} + +static bool +ip_set_put_counter(struct sk_buff *skb, const struct ip_set_counter *counter) +{ + return nla_put_net64(skb, IPSET_ATTR_BYTES, + cpu_to_be64(ip_set_get_bytes(counter)), + IPSET_ATTR_PAD) || + nla_put_net64(skb, IPSET_ATTR_PACKETS, + cpu_to_be64(ip_set_get_packets(counter)), + IPSET_ATTR_PAD); +} + +static bool +ip_set_put_skbinfo(struct sk_buff *skb, const struct ip_set_skbinfo *skbinfo) +{ + /* Send nonzero parameters only */ + return ((skbinfo->skbmark || skbinfo->skbmarkmask) && + nla_put_net64(skb, IPSET_ATTR_SKBMARK, + cpu_to_be64((u64)skbinfo->skbmark << 32 | + skbinfo->skbmarkmask), + IPSET_ATTR_PAD)) || + (skbinfo->skbprio && + nla_put_net32(skb, IPSET_ATTR_SKBPRIO, + cpu_to_be32(skbinfo->skbprio))) || + (skbinfo->skbqueue && + nla_put_net16(skb, IPSET_ATTR_SKBQUEUE, + cpu_to_be16(skbinfo->skbqueue))); +} + int ip_set_put_extensions(struct sk_buff *skb, const struct ip_set *set, const void *e, bool active) @@ -535,6 +588,55 @@ ip_set_put_extensions(struct sk_buff *skb, const struct ip_set *set, } EXPORT_SYMBOL_GPL(ip_set_put_extensions); +static bool +ip_set_match_counter(u64 counter, u64 match, u8 op) +{ + switch (op) { + case IPSET_COUNTER_NONE: + return true; + case IPSET_COUNTER_EQ: + return counter == match; + case IPSET_COUNTER_NE: + return counter != match; + case IPSET_COUNTER_LT: + return counter < match; + case IPSET_COUNTER_GT: + return counter > match; + } + return false; +} + +static void +ip_set_add_bytes(u64 bytes, struct ip_set_counter *counter) +{ + atomic64_add((long long)bytes, &(counter)->bytes); +} + +static void +ip_set_add_packets(u64 packets, struct ip_set_counter *counter) +{ + atomic64_add((long long)packets, &(counter)->packets); +} + +static void +ip_set_update_counter(struct ip_set_counter *counter, + const struct ip_set_ext *ext, u32 flags) +{ + if (ext->packets != ULLONG_MAX && + !(flags & IPSET_FLAG_SKIP_COUNTER_UPDATE)) { + ip_set_add_bytes(ext->bytes, counter); + ip_set_add_packets(ext->packets, counter); + } +} + +static void +ip_set_get_skbinfo(struct ip_set_skbinfo *skbinfo, + const struct ip_set_ext *ext, + struct ip_set_ext *mext, u32 flags) +{ + mext->skbinfo = *skbinfo; +} + bool ip_set_match_extensions(struct ip_set *set, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags, void *data) -- cgit v1.2.3-71-gd317 From 856391854ce73015fbe2b235f5886205aab166b0 Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Thu, 3 Oct 2019 20:56:05 +0100 Subject: netfilter: ipset: make ip_set_put_flags extern. ip_set_put_flags is rather large for a static inline function in a header-file. Move it to ip_set_core.c and export it. Signed-off-by: Jeremy Sowden Acked-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 23 +---------------------- net/netfilter/ipset/ip_set_core.c | 24 ++++++++++++++++++++++++ 2 files changed, 25 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 44f6de8a1733..4d8b1eaf7708 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -276,28 +276,7 @@ ip_set_ext_destroy(struct ip_set *set, void *data) } } -static inline int -ip_set_put_flags(struct sk_buff *skb, struct ip_set *set) -{ - u32 cadt_flags = 0; - - if (SET_WITH_TIMEOUT(set)) - if (unlikely(nla_put_net32(skb, IPSET_ATTR_TIMEOUT, - htonl(set->timeout)))) - return -EMSGSIZE; - if (SET_WITH_COUNTER(set)) - cadt_flags |= IPSET_FLAG_WITH_COUNTERS; - if (SET_WITH_COMMENT(set)) - cadt_flags |= IPSET_FLAG_WITH_COMMENT; - if (SET_WITH_SKBINFO(set)) - cadt_flags |= IPSET_FLAG_WITH_SKBINFO; - if (SET_WITH_FORCEADD(set)) - cadt_flags |= IPSET_FLAG_WITH_FORCEADD; - - if (!cadt_flags) - return 0; - return nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(cadt_flags)); -} +int ip_set_put_flags(struct sk_buff *skb, struct ip_set *set); /* Netlink CB args */ enum { diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 30bc7df2f4cf..35cf59e4004b 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1418,6 +1418,30 @@ static int ip_set_swap(struct net *net, struct sock *ctnl, struct sk_buff *skb, #define DUMP_TYPE(arg) (((u32)(arg)) & 0x0000FFFF) #define DUMP_FLAGS(arg) (((u32)(arg)) >> 16) +int +ip_set_put_flags(struct sk_buff *skb, struct ip_set *set) +{ + u32 cadt_flags = 0; + + if (SET_WITH_TIMEOUT(set)) + if (unlikely(nla_put_net32(skb, IPSET_ATTR_TIMEOUT, + htonl(set->timeout)))) + return -EMSGSIZE; + if (SET_WITH_COUNTER(set)) + cadt_flags |= IPSET_FLAG_WITH_COUNTERS; + if (SET_WITH_COMMENT(set)) + cadt_flags |= IPSET_FLAG_WITH_COMMENT; + if (SET_WITH_SKBINFO(set)) + cadt_flags |= IPSET_FLAG_WITH_SKBINFO; + if (SET_WITH_FORCEADD(set)) + cadt_flags |= IPSET_FLAG_WITH_FORCEADD; + + if (!cadt_flags) + return 0; + return nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(cadt_flags)); +} +EXPORT_SYMBOL_GPL(ip_set_put_flags); + static int ip_set_dump_done(struct netlink_callback *cb) { -- cgit v1.2.3-71-gd317 From 3fbd6c4513b5c27465a1dcf2e4286e6c3183bb1f Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Thu, 3 Oct 2019 20:56:06 +0100 Subject: netfilter: ipset: move function to ip_set_bitmap_ip.c. One inline function in ip_set_bitmap.h is only called in ip_set_bitmap_ip.c: move it and remove inline function specifier. Signed-off-by: Jeremy Sowden Acked-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set_bitmap.h | 14 -------------- net/netfilter/ipset/ip_set_bitmap_ip.c | 12 ++++++++++++ 2 files changed, 12 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set_bitmap.h b/include/linux/netfilter/ipset/ip_set_bitmap.h index 2dddbc6dcac7..fcc4d214a788 100644 --- a/include/linux/netfilter/ipset/ip_set_bitmap.h +++ b/include/linux/netfilter/ipset/ip_set_bitmap.h @@ -12,18 +12,4 @@ enum { IPSET_ADD_START_STORED_TIMEOUT, }; -/* Common functions */ - -static inline u32 -range_to_mask(u32 from, u32 to, u8 *bits) -{ - u32 mask = 0xFFFFFFFE; - - *bits = 32; - while (--(*bits) > 0 && mask && (to & mask) != from) - mask <<= 1; - - return mask; -} - #endif /* __IP_SET_BITMAP_H */ diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index c06172d5b017..abe8f77d7d23 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -237,6 +237,18 @@ init_map_ip(struct ip_set *set, struct bitmap_ip *map, return true; } +static u32 +range_to_mask(u32 from, u32 to, u8 *bits) +{ + u32 mask = 0xFFFFFFFE; + + *bits = 32; + while (--(*bits) > 0 && mask && (to & mask) != from) + mask <<= 1; + + return mask; +} + static int bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[], u32 flags) -- cgit v1.2.3-71-gd317 From f8615bf8a3dabd84bf844c6f888929495039d389 Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Thu, 3 Oct 2019 20:56:07 +0100 Subject: netfilter: ipset: move ip_set_get_ip_port() to ip_set_bitmap_port.c. ip_set_get_ip_port() is only used in ip_set_bitmap_port.c. Move it there and make it static. Signed-off-by: Jeremy Sowden Acked-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set_getport.h | 3 --- net/netfilter/ipset/ip_set_bitmap_port.c | 27 +++++++++++++++++++++++++ net/netfilter/ipset/ip_set_getport.c | 28 -------------------------- 3 files changed, 27 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set_getport.h b/include/linux/netfilter/ipset/ip_set_getport.h index d74cd112b88a..1ecaabd9a048 100644 --- a/include/linux/netfilter/ipset/ip_set_getport.h +++ b/include/linux/netfilter/ipset/ip_set_getport.h @@ -20,9 +20,6 @@ static inline bool ip_set_get_ip6_port(const struct sk_buff *skb, bool src, } #endif -extern bool ip_set_get_ip_port(const struct sk_buff *skb, u8 pf, bool src, - __be16 *port); - static inline bool ip_set_proto_with_ports(u8 proto) { switch (proto) { diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c index 72fede25469d..23d6095cb196 100644 --- a/net/netfilter/ipset/ip_set_bitmap_port.c +++ b/net/netfilter/ipset/ip_set_bitmap_port.c @@ -96,6 +96,33 @@ bitmap_port_do_head(struct sk_buff *skb, const struct bitmap_port *map) nla_put_net16(skb, IPSET_ATTR_PORT_TO, htons(map->last_port)); } +static bool +ip_set_get_ip_port(const struct sk_buff *skb, u8 pf, bool src, __be16 *port) +{ + bool ret; + u8 proto; + + switch (pf) { + case NFPROTO_IPV4: + ret = ip_set_get_ip4_port(skb, src, port, &proto); + break; + case NFPROTO_IPV6: + ret = ip_set_get_ip6_port(skb, src, port, &proto); + break; + default: + return false; + } + if (!ret) + return ret; + switch (proto) { + case IPPROTO_TCP: + case IPPROTO_UDP: + return true; + default: + return false; + } +} + static int bitmap_port_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, diff --git a/net/netfilter/ipset/ip_set_getport.c b/net/netfilter/ipset/ip_set_getport.c index 2b8f959574b4..36615eb3eae1 100644 --- a/net/netfilter/ipset/ip_set_getport.c +++ b/net/netfilter/ipset/ip_set_getport.c @@ -148,31 +148,3 @@ ip_set_get_ip6_port(const struct sk_buff *skb, bool src, } EXPORT_SYMBOL_GPL(ip_set_get_ip6_port); #endif - -bool -ip_set_get_ip_port(const struct sk_buff *skb, u8 pf, bool src, __be16 *port) -{ - bool ret; - u8 proto; - - switch (pf) { - case NFPROTO_IPV4: - ret = ip_set_get_ip4_port(skb, src, port, &proto); - break; - case NFPROTO_IPV6: - ret = ip_set_get_ip6_port(skb, src, port, &proto); - break; - default: - return false; - } - if (!ret) - return ret; - switch (proto) { - case IPPROTO_TCP: - case IPPROTO_UDP: - return true; - default: - return false; - } -} -EXPORT_SYMBOL_GPL(ip_set_get_ip_port); -- cgit v1.2.3-71-gd317 From 7d47433cf74f942a414171867d89c08640cfef45 Mon Sep 17 00:00:00 2001 From: Yamin Friedman Date: Mon, 7 Oct 2019 16:59:31 +0300 Subject: net/mlx5: Expose optimal performance scatter entries capability Expose maximum scatter entries per RDMA READ for optimal performance. Signed-off-by: Yamin Friedman Reviewed-by: Or Gerlitz Reviewed-by: Christoph Hellwig Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 138c50d5a353..c0bfb1d90dd2 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1153,7 +1153,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_srq[0x5]; u8 reserved_at_b0[0x10]; - u8 reserved_at_c0[0x8]; + u8 max_sgl_for_optimized_performance[0x8]; u8 log_max_cq_sz[0x8]; u8 reserved_at_d0[0xb]; u8 log_max_cq[0x5]; -- cgit v1.2.3-71-gd317 From 79591b7db21d255db158afaa48c557dcab631a1c Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 5 Sep 2019 04:01:12 +0300 Subject: spi: Add a PTP system timestamp to the transfer structure SPI is one of the interfaces used to access devices which have a POSIX clock driver (real time clocks, 1588 timers etc). The fact that the SPI bus is slow is not what the main problem is, but rather the fact that drivers don't take a constant amount of time in transferring data over SPI. When there is a high delay in the readout of time, there will be uncertainty in the value that has been read out of the peripheral. When that delay is constant, the uncertainty can at least be approximated with a certain accuracy which is fine more often than not. Timing jitter occurs all over in the kernel code, and is mainly caused by having to let go of the CPU for various reasons such as preemption, servicing interrupts, going to sleep, etc. Another major reason is CPU dynamic frequency scaling. It turns out that the problem of retrieving time from a SPI peripheral with high accuracy can be solved by the use of "PTP system timestamping" - a mechanism to correlate the time when the device has snapshotted its internal time counter with the Linux system time at that same moment. This is sufficient for having a precise time measurement - it is not necessary for the whole SPI transfer to be transmitted "as fast as possible", or "as low-jitter as possible". The system has to be low-jitter for a very short amount of time to be effective. This patch introduces a PTP system timestamping mechanism in struct spi_transfer. This is to be used by SPI device drivers when they need to know the exact time at which the underlying device's time was snapshotted. More often than not, SPI peripherals have a very exact timing for when their SPI-to-interconnect bridge issues a transaction for snapshotting and reading the time register, and that will be dependent on when the SPI-to-interconnect bridge figures out that this is what it should do, aka as soon as it sees byte N of the SPI transfer. Since spi_device drivers are the ones who'd know best how the peripheral behaves in this regard, expose a mechanism in spi_transfer which allows them to specify which word (or word range) from the transfer should be timestamped. Add a default implementation of the PTP system timestamping in the SPI core. This is not going to be satisfactory performance-wise, but should at least increase the likelihood that SPI device drivers will use PTP system timestamping in the future. There are 3 entry points from the core towards the SPI controller drivers: - transfer_one: The driver is passed individual spi_transfers to execute. This is the easiest to timestamp. - transfer_one_message: The core passes the driver an entire spi_message (a potential batch of spi_transfers). The core puts the same pre and post timestamp to all transfers within a message. This is not ideal, but nothing better can be done by default anyway, since the core has no insight into how the driver batches the transfers. - transfer: Like transfer_one_message, but for unqueued drivers (i.e. the driver implements its own queue scheduling). Signed-off-by: Vladimir Oltean Link: https://lore.kernel.org/r/20190905010114.26718-3-olteanv@gmail.com Signed-off-by: Mark Brown --- drivers/spi/spi.c | 127 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/spi/spi.h | 61 +++++++++++++++++++++++ 2 files changed, 188 insertions(+) (limited to 'include/linux') diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index f9502dbbb5c1..9bb36c32cbf9 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1171,6 +1171,11 @@ static int spi_transfer_one_message(struct spi_controller *ctlr, spi_statistics_add_transfer_stats(statm, xfer, ctlr); spi_statistics_add_transfer_stats(stats, xfer, ctlr); + if (!ctlr->ptp_sts_supported) { + xfer->ptp_sts_word_pre = 0; + ptp_read_system_prets(xfer->ptp_sts); + } + if (xfer->tx_buf || xfer->rx_buf) { reinit_completion(&ctlr->xfer_completion); @@ -1197,6 +1202,11 @@ static int spi_transfer_one_message(struct spi_controller *ctlr, xfer->len); } + if (!ctlr->ptp_sts_supported) { + ptp_read_system_postts(xfer->ptp_sts); + xfer->ptp_sts_word_post = xfer->len; + } + trace_spi_transfer_stop(msg, xfer); if (msg->status != -EINPROGRESS) @@ -1265,6 +1275,7 @@ EXPORT_SYMBOL_GPL(spi_finalize_current_transfer); */ static void __spi_pump_messages(struct spi_controller *ctlr, bool in_kthread) { + struct spi_transfer *xfer; struct spi_message *msg; bool was_busy = false; unsigned long flags; @@ -1391,6 +1402,13 @@ static void __spi_pump_messages(struct spi_controller *ctlr, bool in_kthread) goto out; } + if (!ctlr->ptp_sts_supported && !ctlr->transfer_one) { + list_for_each_entry(xfer, &msg->transfers, transfer_list) { + xfer->ptp_sts_word_pre = 0; + ptp_read_system_prets(xfer->ptp_sts); + } + } + ret = ctlr->transfer_one_message(ctlr, msg); if (ret) { dev_err(&ctlr->dev, @@ -1418,6 +1436,99 @@ static void spi_pump_messages(struct kthread_work *work) __spi_pump_messages(ctlr, true); } +/** + * spi_take_timestamp_pre - helper for drivers to collect the beginning of the + * TX timestamp for the requested byte from the SPI + * transfer. The frequency with which this function + * must be called (once per word, once for the whole + * transfer, once per batch of words etc) is arbitrary + * as long as the @tx buffer offset is greater than or + * equal to the requested byte at the time of the + * call. The timestamp is only taken once, at the + * first such call. It is assumed that the driver + * advances its @tx buffer pointer monotonically. + * @ctlr: Pointer to the spi_controller structure of the driver + * @xfer: Pointer to the transfer being timestamped + * @tx: Pointer to the current word within the xfer->tx_buf that the driver is + * preparing to transmit right now. + * @irqs_off: If true, will disable IRQs and preemption for the duration of the + * transfer, for less jitter in time measurement. Only compatible + * with PIO drivers. If true, must follow up with + * spi_take_timestamp_post or otherwise system will crash. + * WARNING: for fully predictable results, the CPU frequency must + * also be under control (governor). + */ +void spi_take_timestamp_pre(struct spi_controller *ctlr, + struct spi_transfer *xfer, + const void *tx, bool irqs_off) +{ + u8 bytes_per_word = DIV_ROUND_UP(xfer->bits_per_word, 8); + + if (!xfer->ptp_sts) + return; + + if (xfer->timestamped_pre) + return; + + if (tx < (xfer->tx_buf + xfer->ptp_sts_word_pre * bytes_per_word)) + return; + + /* Capture the resolution of the timestamp */ + xfer->ptp_sts_word_pre = (tx - xfer->tx_buf) / bytes_per_word; + + xfer->timestamped_pre = true; + + if (irqs_off) { + local_irq_save(ctlr->irq_flags); + preempt_disable(); + } + + ptp_read_system_prets(xfer->ptp_sts); +} +EXPORT_SYMBOL_GPL(spi_take_timestamp_pre); + +/** + * spi_take_timestamp_post - helper for drivers to collect the end of the + * TX timestamp for the requested byte from the SPI + * transfer. Can be called with an arbitrary + * frequency: only the first call where @tx exceeds + * or is equal to the requested word will be + * timestamped. + * @ctlr: Pointer to the spi_controller structure of the driver + * @xfer: Pointer to the transfer being timestamped + * @tx: Pointer to the current word within the xfer->tx_buf that the driver has + * just transmitted. + * @irqs_off: If true, will re-enable IRQs and preemption for the local CPU. + */ +void spi_take_timestamp_post(struct spi_controller *ctlr, + struct spi_transfer *xfer, + const void *tx, bool irqs_off) +{ + u8 bytes_per_word = DIV_ROUND_UP(xfer->bits_per_word, 8); + + if (!xfer->ptp_sts) + return; + + if (xfer->timestamped_post) + return; + + if (tx < (xfer->tx_buf + xfer->ptp_sts_word_post * bytes_per_word)) + return; + + ptp_read_system_postts(xfer->ptp_sts); + + if (irqs_off) { + local_irq_restore(ctlr->irq_flags); + preempt_enable(); + } + + /* Capture the resolution of the timestamp */ + xfer->ptp_sts_word_post = (tx - xfer->tx_buf) / bytes_per_word; + + xfer->timestamped_post = true; +} +EXPORT_SYMBOL_GPL(spi_take_timestamp_post); + /** * spi_set_thread_rt - set the controller to pump at realtime priority * @ctlr: controller to boost priority of @@ -1503,6 +1614,7 @@ EXPORT_SYMBOL_GPL(spi_get_next_queued_message); */ void spi_finalize_current_message(struct spi_controller *ctlr) { + struct spi_transfer *xfer; struct spi_message *mesg; unsigned long flags; int ret; @@ -1511,6 +1623,13 @@ void spi_finalize_current_message(struct spi_controller *ctlr) mesg = ctlr->cur_msg; spin_unlock_irqrestore(&ctlr->queue_lock, flags); + if (!ctlr->ptp_sts_supported && !ctlr->transfer_one) { + list_for_each_entry(xfer, &mesg->transfers, transfer_list) { + ptp_read_system_postts(xfer->ptp_sts); + xfer->ptp_sts_word_post = xfer->len; + } + } + spi_unmap_msg(ctlr, mesg); if (ctlr->cur_msg_prepared && ctlr->unprepare_message) { @@ -3273,6 +3392,7 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message) static int __spi_async(struct spi_device *spi, struct spi_message *message) { struct spi_controller *ctlr = spi->controller; + struct spi_transfer *xfer; /* * Some controllers do not support doing regular SPI transfers. Return @@ -3288,6 +3408,13 @@ static int __spi_async(struct spi_device *spi, struct spi_message *message) trace_spi_message_submit(message); + if (!ctlr->ptp_sts_supported) { + list_for_each_entry(xfer, &message->transfers, transfer_list) { + xfer->ptp_sts_word_pre = 0; + ptp_read_system_prets(xfer->ptp_sts); + } + } + return ctlr->transfer(spi, message); } diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index af4f265d0f67..27f6b046cf92 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -13,6 +13,7 @@ #include #include #include +#include struct dma_chan; struct property_entry; @@ -409,6 +410,12 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @fw_translate_cs: If the boot firmware uses different numbering scheme * what Linux expects, this optional hook can be used to translate * between the two. + * @ptp_sts_supported: If the driver sets this to true, it must provide a + * time snapshot in @spi_transfer->ptp_sts as close as possible to the + * moment in time when @spi_transfer->ptp_sts_word_pre and + * @spi_transfer->ptp_sts_word_post were transmitted. + * If the driver does not set this, the SPI core takes the snapshot as + * close to the driver hand-over as possible. * * Each SPI controller can communicate with one or more @spi_device * children. These make a small bus, sharing MOSI, MISO and SCK signals @@ -604,6 +611,15 @@ struct spi_controller { void *dummy_tx; int (*fw_translate_cs)(struct spi_controller *ctlr, unsigned cs); + + /* + * Driver sets this field to indicate it is able to snapshot SPI + * transfers (needed e.g. for reading the time of POSIX clocks) + */ + bool ptp_sts_supported; + + /* Interrupt enable state during PTP system timestamping */ + unsigned long irq_flags; }; static inline void *spi_controller_get_devdata(struct spi_controller *ctlr) @@ -644,6 +660,14 @@ extern struct spi_message *spi_get_next_queued_message(struct spi_controller *ct extern void spi_finalize_current_message(struct spi_controller *ctlr); extern void spi_finalize_current_transfer(struct spi_controller *ctlr); +/* Helper calls for driver to timestamp transfer */ +void spi_take_timestamp_pre(struct spi_controller *ctlr, + struct spi_transfer *xfer, + const void *tx, bool irqs_off); +void spi_take_timestamp_post(struct spi_controller *ctlr, + struct spi_transfer *xfer, + const void *tx, bool irqs_off); + /* the spi driver core manages memory for the spi_controller classdev */ extern struct spi_controller *__spi_alloc_controller(struct device *host, unsigned int size, bool slave); @@ -753,6 +777,35 @@ extern void spi_res_release(struct spi_controller *ctlr, * @transfer_list: transfers are sequenced through @spi_message.transfers * @tx_sg: Scatterlist for transmit, currently not for client use * @rx_sg: Scatterlist for receive, currently not for client use + * @ptp_sts_word_pre: The word (subject to bits_per_word semantics) offset + * within @tx_buf for which the SPI device is requesting that the time + * snapshot for this transfer begins. Upon completing the SPI transfer, + * this value may have changed compared to what was requested, depending + * on the available snapshotting resolution (DMA transfer, + * @ptp_sts_supported is false, etc). + * @ptp_sts_word_post: See @ptp_sts_word_post. The two can be equal (meaning + * that a single byte should be snapshotted). + * If the core takes care of the timestamp (if @ptp_sts_supported is false + * for this controller), it will set @ptp_sts_word_pre to 0, and + * @ptp_sts_word_post to the length of the transfer. This is done + * purposefully (instead of setting to spi_transfer->len - 1) to denote + * that a transfer-level snapshot taken from within the driver may still + * be of higher quality. + * @ptp_sts: Pointer to a memory location held by the SPI slave device where a + * PTP system timestamp structure may lie. If drivers use PIO or their + * hardware has some sort of assist for retrieving exact transfer timing, + * they can (and should) assert @ptp_sts_supported and populate this + * structure using the ptp_read_system_*ts helper functions. + * The timestamp must represent the time at which the SPI slave device has + * processed the word, i.e. the "pre" timestamp should be taken before + * transmitting the "pre" word, and the "post" timestamp after receiving + * transmit confirmation from the controller for the "post" word. + * @timestamped_pre: Set by the SPI controller driver to denote it has acted + * upon the @ptp_sts request. Not set when the SPI core has taken care of + * the task. SPI device drivers are free to print a warning if this comes + * back unset and they need the better resolution. + * @timestamped_post: See above. The reason why both exist is that these + * booleans are also used to keep state in the core SPI logic. * * SPI transfers always write the same number of bytes as they read. * Protocol drivers should always provide @rx_buf and/or @tx_buf. @@ -842,6 +895,14 @@ struct spi_transfer { u32 effective_speed_hz; + unsigned int ptp_sts_word_pre; + unsigned int ptp_sts_word_post; + + struct ptp_system_timestamp *ptp_sts; + + bool timestamped_pre; + bool timestamped_post; + struct list_head transfer_list; }; -- cgit v1.2.3-71-gd317 From 3a9ac959ba2825a3a6235bc909d369cc30386e9e Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 5 Sep 2019 11:44:24 +0100 Subject: of: Remove unused of_find_matching_node_by_address() of_find_matching_node_by_address() is unused, so remove it. Cc: Robin Murphy Reviewed-by: Geert Uytterhoeven Reviewed-by: Christoph Hellwig Tested-by: Nicolas Saenz Julienne Reviewed-by: Nicolas Saenz Julienne Signed-off-by: Rob Herring --- drivers/of/address.c | 19 ------------------- include/linux/of_address.h | 12 ------------ 2 files changed, 31 deletions(-) (limited to 'include/linux') diff --git a/drivers/of/address.c b/drivers/of/address.c index 978427a9d5e6..0c3cf515c510 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -826,25 +826,6 @@ int of_address_to_resource(struct device_node *dev, int index, } EXPORT_SYMBOL_GPL(of_address_to_resource); -struct device_node *of_find_matching_node_by_address(struct device_node *from, - const struct of_device_id *matches, - u64 base_address) -{ - struct device_node *dn = of_find_matching_node(from, matches); - struct resource res; - - while (dn) { - if (!of_address_to_resource(dn, 0, &res) && - res.start == base_address) - return dn; - - dn = of_find_matching_node(dn, matches); - } - - return NULL; -} - - /** * of_iomap - Maps the memory mapped IO for a given device_node * @device: the device whose io range will be mapped diff --git a/include/linux/of_address.h b/include/linux/of_address.h index 30e40fb6936b..e317f375374a 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -33,10 +33,6 @@ extern u64 of_translate_dma_address(struct device_node *dev, extern u64 of_translate_address(struct device_node *np, const __be32 *addr); extern int of_address_to_resource(struct device_node *dev, int index, struct resource *r); -extern struct device_node *of_find_matching_node_by_address( - struct device_node *from, - const struct of_device_id *matches, - u64 base_address); extern void __iomem *of_iomap(struct device_node *device, int index); void __iomem *of_io_request_and_map(struct device_node *device, int index, const char *name); @@ -71,14 +67,6 @@ static inline u64 of_translate_address(struct device_node *np, return OF_BAD_ADDR; } -static inline struct device_node *of_find_matching_node_by_address( - struct device_node *from, - const struct of_device_id *matches, - u64 base_address) -{ - return NULL; -} - static inline const __be32 *of_get_address(struct device_node *dev, int index, u64 *size, unsigned int *flags) { -- cgit v1.2.3-71-gd317 From 6e6faf63744333373db8bc64aea52dab86cbf0bc Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 5 Sep 2019 11:53:27 +0100 Subject: of: Make of_dma_get_range() private of_dma_get_range() is only used within the DT core code, so remove the export and move the header declaration to the private header. Cc: Robin Murphy Reviewed-by: Geert Uytterhoeven Tested-by: Nicolas Saenz Julienne Reviewed-by: Nicolas Saenz Julienne Reviewed-by: Christoph Hellwig Signed-off-by: Rob Herring --- drivers/of/address.c | 1 - drivers/of/of_private.h | 11 +++++++++++ include/linux/of_address.h | 8 -------- 3 files changed, 11 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/of/address.c b/drivers/of/address.c index 0c3cf515c510..8e354d12fb04 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -972,7 +972,6 @@ out: return ret; } -EXPORT_SYMBOL_GPL(of_dma_get_range); /** * of_dma_is_coherent - Check if device is coherent diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h index 24786818e32e..f8c58615c393 100644 --- a/drivers/of/of_private.h +++ b/drivers/of/of_private.h @@ -158,4 +158,15 @@ extern void __of_sysfs_remove_bin_file(struct device_node *np, #define for_each_transaction_entry_reverse(_oft, _te) \ list_for_each_entry_reverse(_te, &(_oft)->te_list, node) +#ifdef CONFIG_OF_ADDRESS +extern int of_dma_get_range(struct device_node *np, u64 *dma_addr, + u64 *paddr, u64 *size); +#else +static inline int of_dma_get_range(struct device_node *np, u64 *dma_addr, + u64 *paddr, u64 *size) +{ + return -ENODEV; +} +#endif + #endif /* _LINUX_OF_PRIVATE_H */ diff --git a/include/linux/of_address.h b/include/linux/of_address.h index e317f375374a..ddda3936039c 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -51,8 +51,6 @@ extern int of_pci_dma_range_parser_init(struct of_pci_range_parser *parser, extern struct of_pci_range *of_pci_range_parser_one( struct of_pci_range_parser *parser, struct of_pci_range *range); -extern int of_dma_get_range(struct device_node *np, u64 *dma_addr, - u64 *paddr, u64 *size); extern bool of_dma_is_coherent(struct device_node *np); #else /* CONFIG_OF_ADDRESS */ static inline void __iomem *of_io_request_and_map(struct device_node *device, @@ -92,12 +90,6 @@ static inline struct of_pci_range *of_pci_range_parser_one( return NULL; } -static inline int of_dma_get_range(struct device_node *np, u64 *dma_addr, - u64 *paddr, u64 *size) -{ - return -ENODEV; -} - static inline bool of_dma_is_coherent(struct device_node *np) { return false; -- cgit v1.2.3-71-gd317 From 645c138636de3d6d6ed7d92edec39298fd6873d7 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 5 Sep 2019 10:47:26 +0100 Subject: of/address: Fix of_pci_range_parser_one translation of DMA addresses of_pci_range_parser_one() has a bug when parsing dma-ranges. When it translates the parent address (aka cpu address in the code), 'ranges' is always being used. This happens to work because most users are just 1:1 translation. Cc: Robin Murphy Tested-by: Nicolas Saenz Julienne Reviewed-by: Nicolas Saenz Julienne Signed-off-by: Rob Herring --- drivers/of/address.c | 15 ++++++++++++--- include/linux/of_address.h | 1 + 2 files changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/of/address.c b/drivers/of/address.c index 1c291bd6bce2..5ce69d026584 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -243,6 +243,7 @@ static int parser_init(struct of_pci_range_parser *parser, parser->node = node; parser->pna = of_n_addr_cells(node); parser->np = parser->pna + na + ns; + parser->dma = !strcmp(name, "dma-ranges"); parser->range = of_get_property(node, name, &rlen); if (parser->range == NULL) @@ -281,7 +282,11 @@ struct of_pci_range *of_pci_range_parser_one(struct of_pci_range_parser *parser, range->pci_space = be32_to_cpup(parser->range); range->flags = of_bus_pci_get_flags(parser->range); range->pci_addr = of_read_number(parser->range + 1, ns); - range->cpu_addr = of_translate_address(parser->node, + if (parser->dma) + range->cpu_addr = of_translate_dma_address(parser->node, + parser->range + na); + else + range->cpu_addr = of_translate_address(parser->node, parser->range + na); range->size = of_read_number(parser->range + parser->pna + na, ns); @@ -294,8 +299,12 @@ struct of_pci_range *of_pci_range_parser_one(struct of_pci_range_parser *parser, flags = of_bus_pci_get_flags(parser->range); pci_addr = of_read_number(parser->range + 1, ns); - cpu_addr = of_translate_address(parser->node, - parser->range + na); + if (parser->dma) + cpu_addr = of_translate_dma_address(parser->node, + parser->range + na); + else + cpu_addr = of_translate_address(parser->node, + parser->range + na); size = of_read_number(parser->range + parser->pna + na, ns); if (flags != range->flags) diff --git a/include/linux/of_address.h b/include/linux/of_address.h index ddda3936039c..eac7ab109df4 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -12,6 +12,7 @@ struct of_pci_range_parser { const __be32 *end; int np; int pna; + bool dma; }; struct of_pci_range { -- cgit v1.2.3-71-gd317 From 89da2ba947b1080199f4a6413686569a75fc2e7d Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Tue, 8 Oct 2019 15:16:14 +0800 Subject: soc: qcom: Fix llcc-qcom definitions to include commit 99356b03b431 ("soc: qcom: Make llcc-qcom a generic driver") move these out of llcc-qcom.h, make the building fails: drivers/edac/qcom_edac.c:86:40: error: array type has incomplete element type struct llcc_edac_reg_data static const struct llcc_edac_reg_data edac_reg_data[] = { ^~~~~~~~~~~~~ drivers/edac/qcom_edac.c:87:3: error: array index in non-array initializer [LLCC_DRAM_CE] = { ^~~~~~~~~~~~ drivers/edac/qcom_edac.c:87:3: note: (near initialization for edac_reg_data) drivers/edac/qcom_edac.c:88:3: error: field name not in record or union initializer .name = "DRAM Single-bit", ... drivers/edac/qcom_edac.c:169:51: warning: struct llcc_drv_data declared inside parameter list will not be visible outside of this definition or declaration qcom_llcc_clear_error_status(int err_type, struct llcc_drv_data *drv) ^~~~~~~~~~~~~ This patch move the needed definitions back to include. Reported-by: Hulk Robot Fixes: 99356b03b431 ("soc: qcom: Make llcc-qcom a generic driver") Signed-off-by: YueHaibing Signed-off-by: Bjorn Andersson --- drivers/soc/qcom/llcc-qcom.c | 50 -------------------------------------- include/linux/soc/qcom/llcc-qcom.h | 50 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 50 insertions(+), 50 deletions(-) (limited to 'include/linux') diff --git a/drivers/soc/qcom/llcc-qcom.c b/drivers/soc/qcom/llcc-qcom.c index 98563ef0ac6b..436067367db4 100644 --- a/drivers/soc/qcom/llcc-qcom.c +++ b/drivers/soc/qcom/llcc-qcom.c @@ -86,56 +86,6 @@ struct llcc_slice_config { bool activate_on_init; }; -/** - * llcc_drv_data - Data associated with the llcc driver - * @regmap: regmap associated with the llcc device - * @bcast_regmap: regmap associated with llcc broadcast offset - * @cfg: pointer to the data structure for slice configuration - * @lock: mutex associated with each slice - * @cfg_size: size of the config data table - * @max_slices: max slices as read from device tree - * @num_banks: Number of llcc banks - * @bitmap: Bit map to track the active slice ids - * @offsets: Pointer to the bank offsets array - * @ecc_irq: interrupt for llcc cache error detection and reporting - */ -struct llcc_drv_data { - struct regmap *regmap; - struct regmap *bcast_regmap; - const struct llcc_slice_config *cfg; - struct mutex lock; - u32 cfg_size; - u32 max_slices; - u32 num_banks; - unsigned long *bitmap; - u32 *offsets; - int ecc_irq; -}; - -/** - * llcc_edac_reg_data - llcc edac registers data for each error type - * @name: Name of the error - * @synd_reg: Syndrome register address - * @count_status_reg: Status register address to read the error count - * @ways_status_reg: Status register address to read the error ways - * @reg_cnt: Number of registers - * @count_mask: Mask value to get the error count - * @ways_mask: Mask value to get the error ways - * @count_shift: Shift value to get the error count - * @ways_shift: Shift value to get the error ways - */ -struct llcc_edac_reg_data { - char *name; - u64 synd_reg; - u64 count_status_reg; - u64 ways_status_reg; - u32 reg_cnt; - u32 count_mask; - u32 ways_mask; - u8 count_shift; - u8 ways_shift; -}; - struct qcom_llcc_config { const struct llcc_slice_config *sct_data; int size; diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index c0acdb28fde8..90b864655822 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -37,6 +37,56 @@ struct llcc_slice_desc { size_t slice_size; }; +/** + * llcc_edac_reg_data - llcc edac registers data for each error type + * @name: Name of the error + * @synd_reg: Syndrome register address + * @count_status_reg: Status register address to read the error count + * @ways_status_reg: Status register address to read the error ways + * @reg_cnt: Number of registers + * @count_mask: Mask value to get the error count + * @ways_mask: Mask value to get the error ways + * @count_shift: Shift value to get the error count + * @ways_shift: Shift value to get the error ways + */ +struct llcc_edac_reg_data { + char *name; + u64 synd_reg; + u64 count_status_reg; + u64 ways_status_reg; + u32 reg_cnt; + u32 count_mask; + u32 ways_mask; + u8 count_shift; + u8 ways_shift; +}; + +/** + * llcc_drv_data - Data associated with the llcc driver + * @regmap: regmap associated with the llcc device + * @bcast_regmap: regmap associated with llcc broadcast offset + * @cfg: pointer to the data structure for slice configuration + * @lock: mutex associated with each slice + * @cfg_size: size of the config data table + * @max_slices: max slices as read from device tree + * @num_banks: Number of llcc banks + * @bitmap: Bit map to track the active slice ids + * @offsets: Pointer to the bank offsets array + * @ecc_irq: interrupt for llcc cache error detection and reporting + */ +struct llcc_drv_data { + struct regmap *regmap; + struct regmap *bcast_regmap; + const struct llcc_slice_config *cfg; + struct mutex lock; + u32 cfg_size; + u32 max_slices; + u32 num_banks; + unsigned long *bitmap; + u32 *offsets; + int ecc_irq; +}; + #if IS_ENABLED(CONFIG_QCOM_LLCC) /** * llcc_slice_getd - get llcc slice descriptor -- cgit v1.2.3-71-gd317 From bacb7e1855969bba78b32302453d2cc8ba0bc403 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 8 Oct 2019 14:20:34 -0700 Subject: Revert "tun: call dev_get_valid_name() before register_netdevice()" This reverts commit 0ad646c81b2182f7fa67ec0c8c825e0ee165696d. As noticed by Jakub, this is no longer needed after commit 11fc7d5a0a2d ("tun: fix memory leak in error path") This no longer exports dev_get_valid_name() for the exclusive use of tun driver. Suggested-by: Jakub Kicinski Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- drivers/net/tun.c | 3 --- include/linux/netdevice.h | 3 --- net/core/dev.c | 5 ++--- 3 files changed, 2 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 1e541b08b136..0413d182d782 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -2788,9 +2788,6 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) if (!dev) return -ENOMEM; - err = dev_get_valid_name(net, dev, name); - if (err < 0) - goto err_free_dev; dev_net_set(dev, net); dev->rtnl_link_ops = &tun_link_ops; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fe45b2c72315..3207e0b9ec4e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4113,9 +4113,6 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *), unsigned int txqs, unsigned int rxqs); -int dev_get_valid_name(struct net *net, struct net_device *dev, - const char *name); - #define alloc_netdev(sizeof_priv, name, name_assign_type, setup) \ alloc_netdev_mqs(sizeof_priv, name, name_assign_type, setup, 1, 1) diff --git a/net/core/dev.c b/net/core/dev.c index 7d05e042c6ba..8bc3dce71fc0 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1249,8 +1249,8 @@ int dev_alloc_name(struct net_device *dev, const char *name) } EXPORT_SYMBOL(dev_alloc_name); -int dev_get_valid_name(struct net *net, struct net_device *dev, - const char *name) +static int dev_get_valid_name(struct net *net, struct net_device *dev, + const char *name) { BUG_ON(!net); @@ -1266,7 +1266,6 @@ int dev_get_valid_name(struct net *net, struct net_device *dev, return 0; } -EXPORT_SYMBOL(dev_get_valid_name); /** * dev_change_name - change name of a device -- cgit v1.2.3-71-gd317 From f83eeb1a01689b2691f6f56629ac9f66de8d41c2 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 3 Oct 2019 18:17:44 +0200 Subject: sched/cputime: Rename vtime_account_system() to vtime_account_kernel() vtime_account_system() decides if we need to account the time to the system (__vtime_account_system()) or to the guest (vtime_account_guest()). So this function is a misnomer as we are on a higher level than "system". All we know when we call that function is that we are accounting kernel cputime. Whether it belongs to guest or system time is a lower level detail. Rename this function to vtime_account_kernel(). This will clarify things and avoid too many underscored vtime_account_system() versions. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Wanpeng Li Cc: Yauheni Kaliuta Link: https://lkml.kernel.org/r/20191003161745.28464-2-frederic@kernel.org Signed-off-by: Ingo Molnar --- arch/ia64/kernel/time.c | 4 ++-- arch/powerpc/kernel/time.c | 6 +++--- arch/s390/kernel/vtime.c | 4 ++-- include/linux/context_tracking.h | 4 ++-- include/linux/vtime.h | 6 +++--- kernel/sched/cputime.c | 18 +++++++++--------- 6 files changed, 21 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index 1e95d32c8877..91b4024c9351 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -132,7 +132,7 @@ static __u64 vtime_delta(struct task_struct *tsk) return delta_stime; } -void vtime_account_system(struct task_struct *tsk) +void vtime_account_kernel(struct task_struct *tsk) { struct thread_info *ti = task_thread_info(tsk); __u64 stime = vtime_delta(tsk); @@ -146,7 +146,7 @@ void vtime_account_system(struct task_struct *tsk) else ti->stime += stime; } -EXPORT_SYMBOL_GPL(vtime_account_system); +EXPORT_SYMBOL_GPL(vtime_account_kernel); void vtime_account_idle(struct task_struct *tsk) { diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 694522308cd5..84827da01d45 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -338,7 +338,7 @@ static unsigned long vtime_delta(struct task_struct *tsk, return stime; } -void vtime_account_system(struct task_struct *tsk) +void vtime_account_kernel(struct task_struct *tsk) { unsigned long stime, stime_scaled, steal_time; struct cpu_accounting_data *acct = get_accounting(tsk); @@ -366,7 +366,7 @@ void vtime_account_system(struct task_struct *tsk) #endif } } -EXPORT_SYMBOL_GPL(vtime_account_system); +EXPORT_SYMBOL_GPL(vtime_account_kernel); void vtime_account_idle(struct task_struct *tsk) { @@ -395,7 +395,7 @@ static void vtime_flush_scaled(struct task_struct *tsk, /* * Account the whole cputime accumulated in the paca * Must be called with interrupts disabled. - * Assumes that vtime_account_system/idle() has been called + * Assumes that vtime_account_kernel/idle() has been called * recently (i.e. since the last entry from usermode) so that * get_paca()->user_time_scaled is up to date. */ diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index c475ca49cfc6..8df10d3c8f6c 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -247,9 +247,9 @@ void vtime_account_irq_enter(struct task_struct *tsk) } EXPORT_SYMBOL_GPL(vtime_account_irq_enter); -void vtime_account_system(struct task_struct *tsk) +void vtime_account_kernel(struct task_struct *tsk) __attribute__((alias("vtime_account_irq_enter"))); -EXPORT_SYMBOL_GPL(vtime_account_system); +EXPORT_SYMBOL_GPL(vtime_account_kernel); /* * Sorted add to a list. List is linear searched until first bigger diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index d05609ad329d..558a209c247d 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -141,7 +141,7 @@ static inline void guest_enter_irqoff(void) * to assume that it's the stime pending cputime * to flush. */ - vtime_account_system(current); + vtime_account_kernel(current); current->flags |= PF_VCPU; rcu_virt_note_context_switch(smp_processor_id()); } @@ -149,7 +149,7 @@ static inline void guest_enter_irqoff(void) static inline void guest_exit_irqoff(void) { /* Flush the guest cputime we spent on the guest */ - vtime_account_system(current); + vtime_account_kernel(current); current->flags &= ~PF_VCPU; } #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ diff --git a/include/linux/vtime.h b/include/linux/vtime.h index a26ed10a4eac..2fd247f90408 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -57,13 +57,13 @@ static inline void vtime_task_switch(struct task_struct *prev) } #endif /* __ARCH_HAS_VTIME_TASK_SWITCH */ -extern void vtime_account_system(struct task_struct *tsk); +extern void vtime_account_kernel(struct task_struct *tsk); extern void vtime_account_idle(struct task_struct *tsk); #else /* !CONFIG_VIRT_CPU_ACCOUNTING */ static inline void vtime_task_switch(struct task_struct *prev) { } -static inline void vtime_account_system(struct task_struct *tsk) { } +static inline void vtime_account_kernel(struct task_struct *tsk) { } #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN @@ -86,7 +86,7 @@ extern void vtime_account_irq_enter(struct task_struct *tsk); static inline void vtime_account_irq_exit(struct task_struct *tsk) { /* On hard|softirq exit we always account to hard|softirq cputime */ - vtime_account_system(tsk); + vtime_account_kernel(tsk); } extern void vtime_flush(struct task_struct *tsk); #else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 46ed4e1383e2..b45932e27857 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -412,7 +412,7 @@ void vtime_common_task_switch(struct task_struct *prev) if (is_idle_task(prev)) vtime_account_idle(prev); else - vtime_account_system(prev); + vtime_account_kernel(prev); vtime_flush(prev); arch_vtime_task_switch(prev); @@ -425,7 +425,7 @@ void vtime_common_task_switch(struct task_struct *prev) /* * Archs that account the whole time spent in the idle task * (outside irq) as idle time can rely on this and just implement - * vtime_account_system() and vtime_account_idle(). Archs that + * vtime_account_kernel() and vtime_account_idle(). Archs that * have other meaning of the idle time (s390 only includes the * time spent by the CPU when it's in low power mode) must override * vtime_account(). @@ -436,7 +436,7 @@ void vtime_account_irq_enter(struct task_struct *tsk) if (!in_interrupt() && is_idle_task(tsk)) vtime_account_idle(tsk); else - vtime_account_system(tsk); + vtime_account_kernel(tsk); } EXPORT_SYMBOL_GPL(vtime_account_irq_enter); #endif /* __ARCH_HAS_VTIME_ACCOUNT */ @@ -711,8 +711,8 @@ static u64 get_vtime_delta(struct vtime *vtime) return delta - other; } -static void __vtime_account_system(struct task_struct *tsk, - struct vtime *vtime) +static void vtime_account_system(struct task_struct *tsk, + struct vtime *vtime) { vtime->stime += get_vtime_delta(vtime); if (vtime->stime >= TICK_NSEC) { @@ -731,7 +731,7 @@ static void vtime_account_guest(struct task_struct *tsk, } } -void vtime_account_system(struct task_struct *tsk) +void vtime_account_kernel(struct task_struct *tsk) { struct vtime *vtime = &tsk->vtime; @@ -743,7 +743,7 @@ void vtime_account_system(struct task_struct *tsk) if (tsk->flags & PF_VCPU) vtime_account_guest(tsk, vtime); else - __vtime_account_system(tsk, vtime); + vtime_account_system(tsk, vtime); write_seqcount_end(&vtime->seqcount); } @@ -752,7 +752,7 @@ void vtime_user_enter(struct task_struct *tsk) struct vtime *vtime = &tsk->vtime; write_seqcount_begin(&vtime->seqcount); - __vtime_account_system(tsk, vtime); + vtime_account_system(tsk, vtime); vtime->state = VTIME_USER; write_seqcount_end(&vtime->seqcount); } @@ -782,7 +782,7 @@ void vtime_guest_enter(struct task_struct *tsk) * that can thus safely catch up with a tickless delta. */ write_seqcount_begin(&vtime->seqcount); - __vtime_account_system(tsk, vtime); + vtime_account_system(tsk, vtime); tsk->flags |= PF_VCPU; write_seqcount_end(&vtime->seqcount); } -- cgit v1.2.3-71-gd317 From 8d495477d62e4397207f22a432fcaa86d9f2bc2d Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 3 Oct 2019 18:17:45 +0200 Subject: sched/cputime: Spare a seqcount lock/unlock cycle on context switch On context switch we are locking the vtime seqcount of the scheduling-out task twice: * On vtime_task_switch_common(), when we flush the pending vtime through vtime_account_system() * On arch_vtime_task_switch() to reset the vtime state. This is pointless as these actions can be performed without the need to unlock/lock in the middle. The reason these steps are separated is to consolidate a very small amount of common code between CONFIG_VIRT_CPU_ACCOUNTING_GEN and CONFIG_VIRT_CPU_ACCOUNTING_NATIVE. Performance in this fast path is definitely a priority over artificial code factorization so split the task switch code between GEN and NATIVE and mutualize the parts than can run under a single seqcount locked block. As a side effect, vtime_account_idle() becomes included in the seqcount protection. This happens to be a welcome preparation in order to properly support kcpustat under vtime in the future and fetch CPUTIME_IDLE without race. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Wanpeng Li Cc: Yauheni Kaliuta Link: https://lkml.kernel.org/r/20191003161745.28464-3-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/vtime.h | 32 ++++++++++++++++---------------- kernel/sched/cputime.c | 30 +++++++++++++++++++----------- 2 files changed, 35 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vtime.h b/include/linux/vtime.h index 2fd247f90408..d9160ab3667a 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -14,8 +14,12 @@ struct task_struct; * vtime_accounting_cpu_enabled() definitions/declarations */ #if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) + static inline bool vtime_accounting_cpu_enabled(void) { return true; } +extern void vtime_task_switch(struct task_struct *prev); + #elif defined(CONFIG_VIRT_CPU_ACCOUNTING_GEN) + /* * Checks if vtime is enabled on some CPU. Cputime readers want to be careful * in that case and compute the tickless cputime. @@ -36,33 +40,29 @@ static inline bool vtime_accounting_cpu_enabled(void) return false; } + +extern void vtime_task_switch_generic(struct task_struct *prev); + +static inline void vtime_task_switch(struct task_struct *prev) +{ + if (vtime_accounting_cpu_enabled()) + vtime_task_switch_generic(prev); +} + #else /* !CONFIG_VIRT_CPU_ACCOUNTING */ + static inline bool vtime_accounting_cpu_enabled(void) { return false; } -#endif +static inline void vtime_task_switch(struct task_struct *prev) { } +#endif /* * Common vtime APIs */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING - -#ifdef __ARCH_HAS_VTIME_TASK_SWITCH -extern void vtime_task_switch(struct task_struct *prev); -#else -extern void vtime_common_task_switch(struct task_struct *prev); -static inline void vtime_task_switch(struct task_struct *prev) -{ - if (vtime_accounting_cpu_enabled()) - vtime_common_task_switch(prev); -} -#endif /* __ARCH_HAS_VTIME_TASK_SWITCH */ - extern void vtime_account_kernel(struct task_struct *tsk); extern void vtime_account_idle(struct task_struct *tsk); - #else /* !CONFIG_VIRT_CPU_ACCOUNTING */ - -static inline void vtime_task_switch(struct task_struct *prev) { } static inline void vtime_account_kernel(struct task_struct *tsk) { } #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index b45932e27857..cef23c211f41 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -405,9 +405,10 @@ static inline void irqtime_account_process_tick(struct task_struct *p, int user_ /* * Use precise platform statistics if available: */ -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE + # ifndef __ARCH_HAS_VTIME_TASK_SWITCH -void vtime_common_task_switch(struct task_struct *prev) +void vtime_task_switch(struct task_struct *prev) { if (is_idle_task(prev)) vtime_account_idle(prev); @@ -418,10 +419,7 @@ void vtime_common_task_switch(struct task_struct *prev) arch_vtime_task_switch(prev); } # endif -#endif /* CONFIG_VIRT_CPU_ACCOUNTING */ - -#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE /* * Archs that account the whole time spent in the idle task * (outside irq) as idle time can rely on this and just implement @@ -731,6 +729,16 @@ static void vtime_account_guest(struct task_struct *tsk, } } +static void __vtime_account_kernel(struct task_struct *tsk, + struct vtime *vtime) +{ + /* We might have scheduled out from guest path */ + if (tsk->flags & PF_VCPU) + vtime_account_guest(tsk, vtime); + else + vtime_account_system(tsk, vtime); +} + void vtime_account_kernel(struct task_struct *tsk) { struct vtime *vtime = &tsk->vtime; @@ -739,11 +747,7 @@ void vtime_account_kernel(struct task_struct *tsk) return; write_seqcount_begin(&vtime->seqcount); - /* We might have scheduled out from guest path */ - if (tsk->flags & PF_VCPU) - vtime_account_guest(tsk, vtime); - else - vtime_account_system(tsk, vtime); + __vtime_account_kernel(tsk, vtime); write_seqcount_end(&vtime->seqcount); } @@ -804,11 +808,15 @@ void vtime_account_idle(struct task_struct *tsk) account_idle_time(get_vtime_delta(&tsk->vtime)); } -void arch_vtime_task_switch(struct task_struct *prev) +void vtime_task_switch_generic(struct task_struct *prev) { struct vtime *vtime = &prev->vtime; write_seqcount_begin(&vtime->seqcount); + if (is_idle_task(prev)) + vtime_account_idle(prev); + else + __vtime_account_kernel(prev, vtime); vtime->state = VTIME_INACTIVE; write_seqcount_end(&vtime->seqcount); -- cgit v1.2.3-71-gd317 From 5facae4f3549b5cf7c0e10ec312a65ffd43b5726 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 19 Sep 2019 12:09:40 -0400 Subject: locking/lockdep: Remove unused @nested argument from lock_release() Since the following commit: b4adfe8e05f1 ("locking/lockdep: Remove unused argument in __lock_release") @nested is no longer used in lock_release(), so remove it from all lock_release() calls and friends. Signed-off-by: Qian Cai Signed-off-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Acked-by: Daniel Vetter Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: airlied@linux.ie Cc: akpm@linux-foundation.org Cc: alexander.levin@microsoft.com Cc: daniel@iogearbox.net Cc: davem@davemloft.net Cc: dri-devel@lists.freedesktop.org Cc: duyuyang@gmail.com Cc: gregkh@linuxfoundation.org Cc: hannes@cmpxchg.org Cc: intel-gfx@lists.freedesktop.org Cc: jack@suse.com Cc: jlbec@evilplan.or Cc: joonas.lahtinen@linux.intel.com Cc: joseph.qi@linux.alibaba.com Cc: jslaby@suse.com Cc: juri.lelli@redhat.com Cc: maarten.lankhorst@linux.intel.com Cc: mark@fasheh.com Cc: mhocko@kernel.org Cc: mripard@kernel.org Cc: ocfs2-devel@oss.oracle.com Cc: rodrigo.vivi@intel.com Cc: sean@poorly.run Cc: st@kernel.org Cc: tj@kernel.org Cc: tytso@mit.edu Cc: vdavydov.dev@gmail.com Cc: vincent.guittot@linaro.org Cc: viro@zeniv.linux.org.uk Link: https://lkml.kernel.org/r/1568909380-32199-1-git-send-email-cai@lca.pw Signed-off-by: Ingo Molnar --- drivers/gpu/drm/drm_connector.c | 2 +- drivers/gpu/drm/i915/gem/i915_gem_shrinker.c | 6 +++--- drivers/gpu/drm/i915/gt/intel_engine_pm.c | 2 +- drivers/gpu/drm/i915/i915_request.c | 2 +- drivers/tty/tty_ldsem.c | 8 ++++---- fs/dcache.c | 2 +- fs/jbd2/transaction.c | 4 ++-- fs/kernfs/dir.c | 4 ++-- fs/ocfs2/dlmglue.c | 2 +- include/linux/jbd2.h | 2 +- include/linux/lockdep.h | 21 ++++++++++----------- include/linux/percpu-rwsem.h | 4 ++-- include/linux/rcupdate.h | 2 +- include/linux/rwlock_api_smp.h | 16 ++++++++-------- include/linux/seqlock.h | 4 ++-- include/linux/spinlock_api_smp.h | 8 ++++---- include/linux/ww_mutex.h | 2 +- include/net/sock.h | 2 +- kernel/bpf/stackmap.c | 2 +- kernel/cpu.c | 2 +- kernel/locking/lockdep.c | 3 +-- kernel/locking/mutex.c | 4 ++-- kernel/locking/rtmutex.c | 6 +++--- kernel/locking/rwsem.c | 10 +++++----- kernel/printk/printk.c | 10 +++++----- kernel/sched/core.c | 2 +- lib/locking-selftest.c | 24 ++++++++++++------------ mm/memcontrol.c | 2 +- net/core/sock.c | 2 +- tools/lib/lockdep/include/liblockdep/common.h | 3 +-- tools/lib/lockdep/include/liblockdep/mutex.h | 2 +- tools/lib/lockdep/include/liblockdep/rwlock.h | 2 +- tools/lib/lockdep/preload.c | 16 ++++++++-------- 33 files changed, 90 insertions(+), 93 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index 4c766624b20d..4a8b2e5c2af6 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -719,7 +719,7 @@ void drm_connector_list_iter_end(struct drm_connector_list_iter *iter) __drm_connector_put_safe(iter->conn); spin_unlock_irqrestore(&config->connector_list_lock, flags); } - lock_release(&connector_list_iter_dep_map, 0, _RET_IP_); + lock_release(&connector_list_iter_dep_map, _RET_IP_); } EXPORT_SYMBOL(drm_connector_list_iter_end); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c index edd21d14e64f..1a51b3598d63 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c @@ -509,14 +509,14 @@ void i915_gem_shrinker_taints_mutex(struct drm_i915_private *i915, I915_MM_SHRINKER, 0, _RET_IP_); mutex_acquire(&mutex->dep_map, 0, 0, _RET_IP_); - mutex_release(&mutex->dep_map, 0, _RET_IP_); + mutex_release(&mutex->dep_map, _RET_IP_); - mutex_release(&i915->drm.struct_mutex.dep_map, 0, _RET_IP_); + mutex_release(&i915->drm.struct_mutex.dep_map, _RET_IP_); fs_reclaim_release(GFP_KERNEL); if (unlock) - mutex_release(&i915->drm.struct_mutex.dep_map, 0, _RET_IP_); + mutex_release(&i915->drm.struct_mutex.dep_map, _RET_IP_); } #define obj_to_i915(obj__) to_i915((obj__)->base.dev) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c index 65b5ca74b394..7f647243b3b9 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c @@ -52,7 +52,7 @@ static inline unsigned long __timeline_mark_lock(struct intel_context *ce) static inline void __timeline_mark_unlock(struct intel_context *ce, unsigned long flags) { - mutex_release(&ce->timeline->mutex.dep_map, 0, _THIS_IP_); + mutex_release(&ce->timeline->mutex.dep_map, _THIS_IP_); local_irq_restore(flags); } diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index a53777dd371c..e1f1be4d0531 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1456,7 +1456,7 @@ long i915_request_wait(struct i915_request *rq, dma_fence_remove_callback(&rq->fence, &wait.cb); out: - mutex_release(&rq->engine->gt->reset.mutex.dep_map, 0, _THIS_IP_); + mutex_release(&rq->engine->gt->reset.mutex.dep_map, _THIS_IP_); trace_i915_request_wait_end(rq); return timeout; } diff --git a/drivers/tty/tty_ldsem.c b/drivers/tty/tty_ldsem.c index 60ff236a3d63..ce8291053af3 100644 --- a/drivers/tty/tty_ldsem.c +++ b/drivers/tty/tty_ldsem.c @@ -303,7 +303,7 @@ static int __ldsem_down_read_nested(struct ld_semaphore *sem, if (count <= 0) { lock_contended(&sem->dep_map, _RET_IP_); if (!down_read_failed(sem, count, timeout)) { - rwsem_release(&sem->dep_map, 1, _RET_IP_); + rwsem_release(&sem->dep_map, _RET_IP_); return 0; } } @@ -322,7 +322,7 @@ static int __ldsem_down_write_nested(struct ld_semaphore *sem, if ((count & LDSEM_ACTIVE_MASK) != LDSEM_ACTIVE_BIAS) { lock_contended(&sem->dep_map, _RET_IP_); if (!down_write_failed(sem, count, timeout)) { - rwsem_release(&sem->dep_map, 1, _RET_IP_); + rwsem_release(&sem->dep_map, _RET_IP_); return 0; } } @@ -390,7 +390,7 @@ void ldsem_up_read(struct ld_semaphore *sem) { long count; - rwsem_release(&sem->dep_map, 1, _RET_IP_); + rwsem_release(&sem->dep_map, _RET_IP_); count = atomic_long_add_return(-LDSEM_READ_BIAS, &sem->count); if (count < 0 && (count & LDSEM_ACTIVE_MASK) == 0) @@ -404,7 +404,7 @@ void ldsem_up_write(struct ld_semaphore *sem) { long count; - rwsem_release(&sem->dep_map, 1, _RET_IP_); + rwsem_release(&sem->dep_map, _RET_IP_); count = atomic_long_add_return(-LDSEM_WRITE_BIAS, &sem->count); if (count < 0) diff --git a/fs/dcache.c b/fs/dcache.c index e88cf0554e65..f7931b682a0d 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1319,7 +1319,7 @@ resume: if (!list_empty(&dentry->d_subdirs)) { spin_unlock(&this_parent->d_lock); - spin_release(&dentry->d_lock.dep_map, 1, _RET_IP_); + spin_release(&dentry->d_lock.dep_map, _RET_IP_); this_parent = dentry; spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_); goto repeat; diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index bee8498d7792..b25ebdcabfa3 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -713,7 +713,7 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, gfp_t gfp_mask) if (need_to_start) jbd2_log_start_commit(journal, tid); - rwsem_release(&journal->j_trans_commit_map, 1, _THIS_IP_); + rwsem_release(&journal->j_trans_commit_map, _THIS_IP_); handle->h_buffer_credits = nblocks; /* * Restore the original nofs context because the journal restart @@ -1848,7 +1848,7 @@ int jbd2_journal_stop(handle_t *handle) wake_up(&journal->j_wait_transaction_locked); } - rwsem_release(&journal->j_trans_commit_map, 1, _THIS_IP_); + rwsem_release(&journal->j_trans_commit_map, _THIS_IP_); if (wait_for_commit) err = jbd2_log_wait_commit(journal, tid); diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 6ebae6bbe6a5..c45b82feac9a 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -438,7 +438,7 @@ void kernfs_put_active(struct kernfs_node *kn) return; if (kernfs_lockdep(kn)) - rwsem_release(&kn->dep_map, 1, _RET_IP_); + rwsem_release(&kn->dep_map, _RET_IP_); v = atomic_dec_return(&kn->active); if (likely(v != KN_DEACTIVATED_BIAS)) return; @@ -476,7 +476,7 @@ static void kernfs_drain(struct kernfs_node *kn) if (kernfs_lockdep(kn)) { lock_acquired(&kn->dep_map, _RET_IP_); - rwsem_release(&kn->dep_map, 1, _RET_IP_); + rwsem_release(&kn->dep_map, _RET_IP_); } kernfs_drain_open_files(kn); diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 6e774c5ea13b..1c4c51f3df60 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -1687,7 +1687,7 @@ static void __ocfs2_cluster_unlock(struct ocfs2_super *osb, spin_unlock_irqrestore(&lockres->l_lock, flags); #ifdef CONFIG_DEBUG_LOCK_ALLOC if (lockres->l_lockdep_map.key != NULL) - rwsem_release(&lockres->l_lockdep_map, 1, caller_ip); + rwsem_release(&lockres->l_lockdep_map, caller_ip); #endif } diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 603fbc4e2f70..564793c24d12 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1170,7 +1170,7 @@ struct journal_s #define jbd2_might_wait_for_commit(j) \ do { \ rwsem_acquire(&j->j_trans_commit_map, 0, 0, _THIS_IP_); \ - rwsem_release(&j->j_trans_commit_map, 1, _THIS_IP_); \ + rwsem_release(&j->j_trans_commit_map, _THIS_IP_); \ } while (0) /* journal feature predicate functions */ diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index b8a835fd611b..c50d01ef1414 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -349,8 +349,7 @@ extern void lock_acquire(struct lockdep_map *lock, unsigned int subclass, int trylock, int read, int check, struct lockdep_map *nest_lock, unsigned long ip); -extern void lock_release(struct lockdep_map *lock, int nested, - unsigned long ip); +extern void lock_release(struct lockdep_map *lock, unsigned long ip); /* * Same "read" as for lock_acquire(), except -1 means any. @@ -428,7 +427,7 @@ static inline void lockdep_set_selftest_task(struct task_struct *task) } # define lock_acquire(l, s, t, r, c, n, i) do { } while (0) -# define lock_release(l, n, i) do { } while (0) +# define lock_release(l, i) do { } while (0) # define lock_downgrade(l, i) do { } while (0) # define lock_set_class(l, n, k, s, i) do { } while (0) # define lock_set_subclass(l, s, i) do { } while (0) @@ -591,42 +590,42 @@ static inline void print_irqtrace_events(struct task_struct *curr) #define spin_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define spin_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) -#define spin_release(l, n, i) lock_release(l, n, i) +#define spin_release(l, i) lock_release(l, i) #define rwlock_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define rwlock_acquire_read(l, s, t, i) lock_acquire_shared_recursive(l, s, t, NULL, i) -#define rwlock_release(l, n, i) lock_release(l, n, i) +#define rwlock_release(l, i) lock_release(l, i) #define seqcount_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define seqcount_acquire_read(l, s, t, i) lock_acquire_shared_recursive(l, s, t, NULL, i) -#define seqcount_release(l, n, i) lock_release(l, n, i) +#define seqcount_release(l, i) lock_release(l, i) #define mutex_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define mutex_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) -#define mutex_release(l, n, i) lock_release(l, n, i) +#define mutex_release(l, i) lock_release(l, i) #define rwsem_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define rwsem_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) #define rwsem_acquire_read(l, s, t, i) lock_acquire_shared(l, s, t, NULL, i) -#define rwsem_release(l, n, i) lock_release(l, n, i) +#define rwsem_release(l, i) lock_release(l, i) #define lock_map_acquire(l) lock_acquire_exclusive(l, 0, 0, NULL, _THIS_IP_) #define lock_map_acquire_read(l) lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_) #define lock_map_acquire_tryread(l) lock_acquire_shared_recursive(l, 0, 1, NULL, _THIS_IP_) -#define lock_map_release(l) lock_release(l, 1, _THIS_IP_) +#define lock_map_release(l) lock_release(l, _THIS_IP_) #ifdef CONFIG_PROVE_LOCKING # define might_lock(lock) \ do { \ typecheck(struct lockdep_map *, &(lock)->dep_map); \ lock_acquire(&(lock)->dep_map, 0, 0, 0, 1, NULL, _THIS_IP_); \ - lock_release(&(lock)->dep_map, 0, _THIS_IP_); \ + lock_release(&(lock)->dep_map, _THIS_IP_); \ } while (0) # define might_lock_read(lock) \ do { \ typecheck(struct lockdep_map *, &(lock)->dep_map); \ lock_acquire(&(lock)->dep_map, 0, 0, 1, 1, NULL, _THIS_IP_); \ - lock_release(&(lock)->dep_map, 0, _THIS_IP_); \ + lock_release(&(lock)->dep_map, _THIS_IP_); \ } while (0) #define lockdep_assert_irqs_enabled() do { \ diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h index 3998cdf9cd14..ad2ca2a89d5b 100644 --- a/include/linux/percpu-rwsem.h +++ b/include/linux/percpu-rwsem.h @@ -93,7 +93,7 @@ static inline void percpu_up_read(struct percpu_rw_semaphore *sem) __percpu_up_read(sem); /* Unconditional memory barrier */ preempt_enable(); - rwsem_release(&sem->rw_sem.dep_map, 1, _RET_IP_); + rwsem_release(&sem->rw_sem.dep_map, _RET_IP_); } extern void percpu_down_write(struct percpu_rw_semaphore *); @@ -118,7 +118,7 @@ extern void percpu_free_rwsem(struct percpu_rw_semaphore *); static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem, bool read, unsigned long ip) { - lock_release(&sem->rw_sem.dep_map, 1, ip); + lock_release(&sem->rw_sem.dep_map, ip); #ifdef CONFIG_RWSEM_SPIN_ON_OWNER if (!read) atomic_long_set(&sem->rw_sem.owner, RWSEM_OWNER_UNKNOWN); diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 75a2eded7aa2..269b31eab3d6 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -210,7 +210,7 @@ static inline void rcu_lock_acquire(struct lockdep_map *map) static inline void rcu_lock_release(struct lockdep_map *map) { - lock_release(map, 1, _THIS_IP_); + lock_release(map, _THIS_IP_); } extern struct lockdep_map rcu_lock_map; diff --git a/include/linux/rwlock_api_smp.h b/include/linux/rwlock_api_smp.h index 86ebb4bf9c6e..abfb53ab11be 100644 --- a/include/linux/rwlock_api_smp.h +++ b/include/linux/rwlock_api_smp.h @@ -215,14 +215,14 @@ static inline void __raw_write_lock(rwlock_t *lock) static inline void __raw_write_unlock(rwlock_t *lock) { - rwlock_release(&lock->dep_map, 1, _RET_IP_); + rwlock_release(&lock->dep_map, _RET_IP_); do_raw_write_unlock(lock); preempt_enable(); } static inline void __raw_read_unlock(rwlock_t *lock) { - rwlock_release(&lock->dep_map, 1, _RET_IP_); + rwlock_release(&lock->dep_map, _RET_IP_); do_raw_read_unlock(lock); preempt_enable(); } @@ -230,7 +230,7 @@ static inline void __raw_read_unlock(rwlock_t *lock) static inline void __raw_read_unlock_irqrestore(rwlock_t *lock, unsigned long flags) { - rwlock_release(&lock->dep_map, 1, _RET_IP_); + rwlock_release(&lock->dep_map, _RET_IP_); do_raw_read_unlock(lock); local_irq_restore(flags); preempt_enable(); @@ -238,7 +238,7 @@ __raw_read_unlock_irqrestore(rwlock_t *lock, unsigned long flags) static inline void __raw_read_unlock_irq(rwlock_t *lock) { - rwlock_release(&lock->dep_map, 1, _RET_IP_); + rwlock_release(&lock->dep_map, _RET_IP_); do_raw_read_unlock(lock); local_irq_enable(); preempt_enable(); @@ -246,7 +246,7 @@ static inline void __raw_read_unlock_irq(rwlock_t *lock) static inline void __raw_read_unlock_bh(rwlock_t *lock) { - rwlock_release(&lock->dep_map, 1, _RET_IP_); + rwlock_release(&lock->dep_map, _RET_IP_); do_raw_read_unlock(lock); __local_bh_enable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET); } @@ -254,7 +254,7 @@ static inline void __raw_read_unlock_bh(rwlock_t *lock) static inline void __raw_write_unlock_irqrestore(rwlock_t *lock, unsigned long flags) { - rwlock_release(&lock->dep_map, 1, _RET_IP_); + rwlock_release(&lock->dep_map, _RET_IP_); do_raw_write_unlock(lock); local_irq_restore(flags); preempt_enable(); @@ -262,7 +262,7 @@ static inline void __raw_write_unlock_irqrestore(rwlock_t *lock, static inline void __raw_write_unlock_irq(rwlock_t *lock) { - rwlock_release(&lock->dep_map, 1, _RET_IP_); + rwlock_release(&lock->dep_map, _RET_IP_); do_raw_write_unlock(lock); local_irq_enable(); preempt_enable(); @@ -270,7 +270,7 @@ static inline void __raw_write_unlock_irq(rwlock_t *lock) static inline void __raw_write_unlock_bh(rwlock_t *lock) { - rwlock_release(&lock->dep_map, 1, _RET_IP_); + rwlock_release(&lock->dep_map, _RET_IP_); do_raw_write_unlock(lock); __local_bh_enable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET); } diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index bcf4cf26b8c8..0491d963d47e 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -79,7 +79,7 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) local_irq_save(flags); seqcount_acquire_read(&l->dep_map, 0, 0, _RET_IP_); - seqcount_release(&l->dep_map, 1, _RET_IP_); + seqcount_release(&l->dep_map, _RET_IP_); local_irq_restore(flags); } @@ -384,7 +384,7 @@ static inline void write_seqcount_begin(seqcount_t *s) static inline void write_seqcount_end(seqcount_t *s) { - seqcount_release(&s->dep_map, 1, _RET_IP_); + seqcount_release(&s->dep_map, _RET_IP_); raw_write_seqcount_end(s); } diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h index b762eaba4cdf..19a9be9d97ee 100644 --- a/include/linux/spinlock_api_smp.h +++ b/include/linux/spinlock_api_smp.h @@ -147,7 +147,7 @@ static inline void __raw_spin_lock(raw_spinlock_t *lock) static inline void __raw_spin_unlock(raw_spinlock_t *lock) { - spin_release(&lock->dep_map, 1, _RET_IP_); + spin_release(&lock->dep_map, _RET_IP_); do_raw_spin_unlock(lock); preempt_enable(); } @@ -155,7 +155,7 @@ static inline void __raw_spin_unlock(raw_spinlock_t *lock) static inline void __raw_spin_unlock_irqrestore(raw_spinlock_t *lock, unsigned long flags) { - spin_release(&lock->dep_map, 1, _RET_IP_); + spin_release(&lock->dep_map, _RET_IP_); do_raw_spin_unlock(lock); local_irq_restore(flags); preempt_enable(); @@ -163,7 +163,7 @@ static inline void __raw_spin_unlock_irqrestore(raw_spinlock_t *lock, static inline void __raw_spin_unlock_irq(raw_spinlock_t *lock) { - spin_release(&lock->dep_map, 1, _RET_IP_); + spin_release(&lock->dep_map, _RET_IP_); do_raw_spin_unlock(lock); local_irq_enable(); preempt_enable(); @@ -171,7 +171,7 @@ static inline void __raw_spin_unlock_irq(raw_spinlock_t *lock) static inline void __raw_spin_unlock_bh(raw_spinlock_t *lock) { - spin_release(&lock->dep_map, 1, _RET_IP_); + spin_release(&lock->dep_map, _RET_IP_); do_raw_spin_unlock(lock); __local_bh_enable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET); } diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index 3af7c0e03be5..d7554252404c 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -182,7 +182,7 @@ static inline void ww_acquire_done(struct ww_acquire_ctx *ctx) static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx) { #ifdef CONFIG_DEBUG_MUTEXES - mutex_release(&ctx->dep_map, 0, _THIS_IP_); + mutex_release(&ctx->dep_map, _THIS_IP_); DEBUG_LOCKS_WARN_ON(ctx->acquired); if (!IS_ENABLED(CONFIG_PROVE_LOCKING)) diff --git a/include/net/sock.h b/include/net/sock.h index 2c53f1a1d905..e46db0c846d2 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1484,7 +1484,7 @@ static inline void sock_release_ownership(struct sock *sk) sk->sk_lock.owned = 0; /* The sk_lock has mutex_unlock() semantics: */ - mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_); + mutex_release(&sk->sk_lock.dep_map, _RET_IP_); } } diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 052580c33d26..dcfe2d37ad15 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -338,7 +338,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, * up_read_non_owner(). The rwsem_release() is called * here to release the lock from lockdep's perspective. */ - rwsem_release(¤t->mm->mmap_sem.dep_map, 1, _RET_IP_); + rwsem_release(¤t->mm->mmap_sem.dep_map, _RET_IP_); } } diff --git a/kernel/cpu.c b/kernel/cpu.c index fc28e17940e0..68f85627d909 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -336,7 +336,7 @@ static void lockdep_acquire_cpus_lock(void) static void lockdep_release_cpus_lock(void) { - rwsem_release(&cpu_hotplug_lock.rw_sem.dep_map, 1, _THIS_IP_); + rwsem_release(&cpu_hotplug_lock.rw_sem.dep_map, _THIS_IP_); } /* diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 233459c03b5a..8123518f9045 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -4491,8 +4491,7 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, } EXPORT_SYMBOL_GPL(lock_acquire); -void lock_release(struct lockdep_map *lock, int nested, - unsigned long ip) +void lock_release(struct lockdep_map *lock, unsigned long ip) { unsigned long flags; diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 468a9b8422e3..5352ce50a97e 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -1091,7 +1091,7 @@ err: err_early_kill: spin_unlock(&lock->wait_lock); debug_mutex_free_waiter(&waiter); - mutex_release(&lock->dep_map, 1, ip); + mutex_release(&lock->dep_map, ip); preempt_enable(); return ret; } @@ -1225,7 +1225,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne DEFINE_WAKE_Q(wake_q); unsigned long owner; - mutex_release(&lock->dep_map, 1, ip); + mutex_release(&lock->dep_map, ip); /* * Release the lock before (potentially) taking the spinlock such that diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 2874bf556162..851bbb10819d 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1517,7 +1517,7 @@ int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock) mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); ret = rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock); if (ret) - mutex_release(&lock->dep_map, 1, _RET_IP_); + mutex_release(&lock->dep_map, _RET_IP_); return ret; } @@ -1561,7 +1561,7 @@ rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout) RT_MUTEX_MIN_CHAINWALK, rt_mutex_slowlock); if (ret) - mutex_release(&lock->dep_map, 1, _RET_IP_); + mutex_release(&lock->dep_map, _RET_IP_); return ret; } @@ -1600,7 +1600,7 @@ EXPORT_SYMBOL_GPL(rt_mutex_trylock); */ void __sched rt_mutex_unlock(struct rt_mutex *lock) { - mutex_release(&lock->dep_map, 1, _RET_IP_); + mutex_release(&lock->dep_map, _RET_IP_); rt_mutex_fastunlock(lock, rt_mutex_slowunlock); } EXPORT_SYMBOL_GPL(rt_mutex_unlock); diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index eef04551eae7..44e68761f432 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -1504,7 +1504,7 @@ int __sched down_read_killable(struct rw_semaphore *sem) rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_); if (LOCK_CONTENDED_RETURN(sem, __down_read_trylock, __down_read_killable)) { - rwsem_release(&sem->dep_map, 1, _RET_IP_); + rwsem_release(&sem->dep_map, _RET_IP_); return -EINTR; } @@ -1546,7 +1546,7 @@ int __sched down_write_killable(struct rw_semaphore *sem) if (LOCK_CONTENDED_RETURN(sem, __down_write_trylock, __down_write_killable)) { - rwsem_release(&sem->dep_map, 1, _RET_IP_); + rwsem_release(&sem->dep_map, _RET_IP_); return -EINTR; } @@ -1573,7 +1573,7 @@ EXPORT_SYMBOL(down_write_trylock); */ void up_read(struct rw_semaphore *sem) { - rwsem_release(&sem->dep_map, 1, _RET_IP_); + rwsem_release(&sem->dep_map, _RET_IP_); __up_read(sem); } EXPORT_SYMBOL(up_read); @@ -1583,7 +1583,7 @@ EXPORT_SYMBOL(up_read); */ void up_write(struct rw_semaphore *sem) { - rwsem_release(&sem->dep_map, 1, _RET_IP_); + rwsem_release(&sem->dep_map, _RET_IP_); __up_write(sem); } EXPORT_SYMBOL(up_write); @@ -1639,7 +1639,7 @@ int __sched down_write_killable_nested(struct rw_semaphore *sem, int subclass) if (LOCK_CONTENDED_RETURN(sem, __down_write_trylock, __down_write_killable)) { - rwsem_release(&sem->dep_map, 1, _RET_IP_); + rwsem_release(&sem->dep_map, _RET_IP_); return -EINTR; } diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index ca65327a6de8..c8be5a0f5259 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -248,7 +248,7 @@ static void __up_console_sem(unsigned long ip) { unsigned long flags; - mutex_release(&console_lock_dep_map, 1, ip); + mutex_release(&console_lock_dep_map, ip); printk_safe_enter_irqsave(flags); up(&console_sem); @@ -1679,20 +1679,20 @@ static int console_lock_spinning_disable_and_check(void) raw_spin_unlock(&console_owner_lock); if (!waiter) { - spin_release(&console_owner_dep_map, 1, _THIS_IP_); + spin_release(&console_owner_dep_map, _THIS_IP_); return 0; } /* The waiter is now free to continue */ WRITE_ONCE(console_waiter, false); - spin_release(&console_owner_dep_map, 1, _THIS_IP_); + spin_release(&console_owner_dep_map, _THIS_IP_); /* * Hand off console_lock to waiter. The waiter will perform * the up(). After this, the waiter is the console_lock owner. */ - mutex_release(&console_lock_dep_map, 1, _THIS_IP_); + mutex_release(&console_lock_dep_map, _THIS_IP_); return 1; } @@ -1746,7 +1746,7 @@ static int console_trylock_spinning(void) /* Owner will clear console_waiter on hand off */ while (READ_ONCE(console_waiter)) cpu_relax(); - spin_release(&console_owner_dep_map, 1, _THIS_IP_); + spin_release(&console_owner_dep_map, _THIS_IP_); printk_safe_exit_irqrestore(flags); /* diff --git a/kernel/sched/core.c b/kernel/sched/core.c index dd05a378631a..eb42b71faab9 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3105,7 +3105,7 @@ prepare_lock_switch(struct rq *rq, struct task_struct *next, struct rq_flags *rf * do an early lockdep release here: */ rq_unpin_lock(rq, rf); - spin_release(&rq->lock.dep_map, 1, _THIS_IP_); + spin_release(&rq->lock.dep_map, _THIS_IP_); #ifdef CONFIG_DEBUG_SPINLOCK /* this is a valid case when another task releases the spinlock */ rq->lock.owner = next; diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c index a1705545e6ac..14f44f59e733 100644 --- a/lib/locking-selftest.c +++ b/lib/locking-selftest.c @@ -1475,7 +1475,7 @@ static void ww_test_edeadlk_normal(void) mutex_lock(&o2.base); o2.ctx = &t2; - mutex_release(&o2.base.dep_map, 1, _THIS_IP_); + mutex_release(&o2.base.dep_map, _THIS_IP_); WWAI(&t); t2 = t; @@ -1500,7 +1500,7 @@ static void ww_test_edeadlk_normal_slow(void) int ret; mutex_lock(&o2.base); - mutex_release(&o2.base.dep_map, 1, _THIS_IP_); + mutex_release(&o2.base.dep_map, _THIS_IP_); o2.ctx = &t2; WWAI(&t); @@ -1527,7 +1527,7 @@ static void ww_test_edeadlk_no_unlock(void) mutex_lock(&o2.base); o2.ctx = &t2; - mutex_release(&o2.base.dep_map, 1, _THIS_IP_); + mutex_release(&o2.base.dep_map, _THIS_IP_); WWAI(&t); t2 = t; @@ -1551,7 +1551,7 @@ static void ww_test_edeadlk_no_unlock_slow(void) int ret; mutex_lock(&o2.base); - mutex_release(&o2.base.dep_map, 1, _THIS_IP_); + mutex_release(&o2.base.dep_map, _THIS_IP_); o2.ctx = &t2; WWAI(&t); @@ -1576,7 +1576,7 @@ static void ww_test_edeadlk_acquire_more(void) int ret; mutex_lock(&o2.base); - mutex_release(&o2.base.dep_map, 1, _THIS_IP_); + mutex_release(&o2.base.dep_map, _THIS_IP_); o2.ctx = &t2; WWAI(&t); @@ -1597,7 +1597,7 @@ static void ww_test_edeadlk_acquire_more_slow(void) int ret; mutex_lock(&o2.base); - mutex_release(&o2.base.dep_map, 1, _THIS_IP_); + mutex_release(&o2.base.dep_map, _THIS_IP_); o2.ctx = &t2; WWAI(&t); @@ -1618,11 +1618,11 @@ static void ww_test_edeadlk_acquire_more_edeadlk(void) int ret; mutex_lock(&o2.base); - mutex_release(&o2.base.dep_map, 1, _THIS_IP_); + mutex_release(&o2.base.dep_map, _THIS_IP_); o2.ctx = &t2; mutex_lock(&o3.base); - mutex_release(&o3.base.dep_map, 1, _THIS_IP_); + mutex_release(&o3.base.dep_map, _THIS_IP_); o3.ctx = &t2; WWAI(&t); @@ -1644,11 +1644,11 @@ static void ww_test_edeadlk_acquire_more_edeadlk_slow(void) int ret; mutex_lock(&o2.base); - mutex_release(&o2.base.dep_map, 1, _THIS_IP_); + mutex_release(&o2.base.dep_map, _THIS_IP_); o2.ctx = &t2; mutex_lock(&o3.base); - mutex_release(&o3.base.dep_map, 1, _THIS_IP_); + mutex_release(&o3.base.dep_map, _THIS_IP_); o3.ctx = &t2; WWAI(&t); @@ -1669,7 +1669,7 @@ static void ww_test_edeadlk_acquire_wrong(void) int ret; mutex_lock(&o2.base); - mutex_release(&o2.base.dep_map, 1, _THIS_IP_); + mutex_release(&o2.base.dep_map, _THIS_IP_); o2.ctx = &t2; WWAI(&t); @@ -1694,7 +1694,7 @@ static void ww_test_edeadlk_acquire_wrong_slow(void) int ret; mutex_lock(&o2.base); - mutex_release(&o2.base.dep_map, 1, _THIS_IP_); + mutex_release(&o2.base.dep_map, _THIS_IP_); o2.ctx = &t2; WWAI(&t); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index bdac56009a38..12233463e39e 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1800,7 +1800,7 @@ static void mem_cgroup_oom_unlock(struct mem_cgroup *memcg) struct mem_cgroup *iter; spin_lock(&memcg_oom_lock); - mutex_release(&memcg_oom_lock_dep_map, 1, _RET_IP_); + mutex_release(&memcg_oom_lock_dep_map, _RET_IP_); for_each_mem_cgroup_tree(iter, memcg) iter->oom_lock = false; spin_unlock(&memcg_oom_lock); diff --git a/net/core/sock.c b/net/core/sock.c index fac2b4d80de5..50b930364cb0 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -521,7 +521,7 @@ int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, rc = sk_backlog_rcv(sk, skb); - mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_); + mutex_release(&sk->sk_lock.dep_map, _RET_IP_); } else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) { bh_unlock_sock(sk); atomic_inc(&sk->sk_drops); diff --git a/tools/lib/lockdep/include/liblockdep/common.h b/tools/lib/lockdep/include/liblockdep/common.h index a81d91d4fc78..a6d7ee5f18ba 100644 --- a/tools/lib/lockdep/include/liblockdep/common.h +++ b/tools/lib/lockdep/include/liblockdep/common.h @@ -42,8 +42,7 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name, void lock_acquire(struct lockdep_map *lock, unsigned int subclass, int trylock, int read, int check, struct lockdep_map *nest_lock, unsigned long ip); -void lock_release(struct lockdep_map *lock, int nested, - unsigned long ip); +void lock_release(struct lockdep_map *lock, unsigned long ip); void lockdep_reset_lock(struct lockdep_map *lock); void lockdep_register_key(struct lock_class_key *key); void lockdep_unregister_key(struct lock_class_key *key); diff --git a/tools/lib/lockdep/include/liblockdep/mutex.h b/tools/lib/lockdep/include/liblockdep/mutex.h index 783dd0df06f9..bd106b82759b 100644 --- a/tools/lib/lockdep/include/liblockdep/mutex.h +++ b/tools/lib/lockdep/include/liblockdep/mutex.h @@ -42,7 +42,7 @@ static inline int liblockdep_pthread_mutex_lock(liblockdep_pthread_mutex_t *lock static inline int liblockdep_pthread_mutex_unlock(liblockdep_pthread_mutex_t *lock) { - lock_release(&lock->dep_map, 0, (unsigned long)_RET_IP_); + lock_release(&lock->dep_map, (unsigned long)_RET_IP_); return pthread_mutex_unlock(&lock->mutex); } diff --git a/tools/lib/lockdep/include/liblockdep/rwlock.h b/tools/lib/lockdep/include/liblockdep/rwlock.h index 365762e3a1ea..6d5d2932bf4d 100644 --- a/tools/lib/lockdep/include/liblockdep/rwlock.h +++ b/tools/lib/lockdep/include/liblockdep/rwlock.h @@ -44,7 +44,7 @@ static inline int liblockdep_pthread_rwlock_rdlock(liblockdep_pthread_rwlock_t * static inline int liblockdep_pthread_rwlock_unlock(liblockdep_pthread_rwlock_t *lock) { - lock_release(&lock->dep_map, 0, (unsigned long)_RET_IP_); + lock_release(&lock->dep_map, (unsigned long)_RET_IP_); return pthread_rwlock_unlock(&lock->rwlock); } diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c index 76245d16196d..8f1adbe887b2 100644 --- a/tools/lib/lockdep/preload.c +++ b/tools/lib/lockdep/preload.c @@ -270,7 +270,7 @@ int pthread_mutex_lock(pthread_mutex_t *mutex) */ r = ll_pthread_mutex_lock(mutex); if (r) - lock_release(&__get_lock(mutex)->dep_map, 0, (unsigned long)_RET_IP_); + lock_release(&__get_lock(mutex)->dep_map, (unsigned long)_RET_IP_); return r; } @@ -284,7 +284,7 @@ int pthread_mutex_trylock(pthread_mutex_t *mutex) lock_acquire(&__get_lock(mutex)->dep_map, 0, 1, 0, 1, NULL, (unsigned long)_RET_IP_); r = ll_pthread_mutex_trylock(mutex); if (r) - lock_release(&__get_lock(mutex)->dep_map, 0, (unsigned long)_RET_IP_); + lock_release(&__get_lock(mutex)->dep_map, (unsigned long)_RET_IP_); return r; } @@ -295,7 +295,7 @@ int pthread_mutex_unlock(pthread_mutex_t *mutex) try_init_preload(); - lock_release(&__get_lock(mutex)->dep_map, 0, (unsigned long)_RET_IP_); + lock_release(&__get_lock(mutex)->dep_map, (unsigned long)_RET_IP_); /* * Just like taking a lock, only in reverse! * @@ -355,7 +355,7 @@ int pthread_rwlock_rdlock(pthread_rwlock_t *rwlock) lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 2, 1, NULL, (unsigned long)_RET_IP_); r = ll_pthread_rwlock_rdlock(rwlock); if (r) - lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_); + lock_release(&__get_lock(rwlock)->dep_map, (unsigned long)_RET_IP_); return r; } @@ -369,7 +369,7 @@ int pthread_rwlock_tryrdlock(pthread_rwlock_t *rwlock) lock_acquire(&__get_lock(rwlock)->dep_map, 0, 1, 2, 1, NULL, (unsigned long)_RET_IP_); r = ll_pthread_rwlock_tryrdlock(rwlock); if (r) - lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_); + lock_release(&__get_lock(rwlock)->dep_map, (unsigned long)_RET_IP_); return r; } @@ -383,7 +383,7 @@ int pthread_rwlock_trywrlock(pthread_rwlock_t *rwlock) lock_acquire(&__get_lock(rwlock)->dep_map, 0, 1, 0, 1, NULL, (unsigned long)_RET_IP_); r = ll_pthread_rwlock_trywrlock(rwlock); if (r) - lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_); + lock_release(&__get_lock(rwlock)->dep_map, (unsigned long)_RET_IP_); return r; } @@ -397,7 +397,7 @@ int pthread_rwlock_wrlock(pthread_rwlock_t *rwlock) lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_); r = ll_pthread_rwlock_wrlock(rwlock); if (r) - lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_); + lock_release(&__get_lock(rwlock)->dep_map, (unsigned long)_RET_IP_); return r; } @@ -408,7 +408,7 @@ int pthread_rwlock_unlock(pthread_rwlock_t *rwlock) init_preload(); - lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_); + lock_release(&__get_lock(rwlock)->dep_map, (unsigned long)_RET_IP_); r = ll_pthread_rwlock_unlock(rwlock); if (r) lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_); -- cgit v1.2.3-71-gd317 From d30cd83f68535ca21412b1abe8684438690c1c2b Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Wed, 9 Oct 2019 08:55:38 -0700 Subject: soc: ti: omap-prm: add support for denying idle for reset clockdomain TI SoCs hardware reset signals require the parent clockdomain to be in force wakeup mode while de-asserting the reset, otherwise it may never complete. To support this, add pdata hooks to control the clockdomain directly. Signed-off-by: Tero Kristo Reviewed-by: Tony Lindgren Signed-off-by: Santosh Shilimkar --- drivers/soc/ti/omap_prm.c | 36 ++++++++++++++++++++++++++++++++++-- include/linux/platform_data/ti-prm.h | 21 +++++++++++++++++++++ 2 files changed, 55 insertions(+), 2 deletions(-) create mode 100644 include/linux/platform_data/ti-prm.h (limited to 'include/linux') diff --git a/drivers/soc/ti/omap_prm.c b/drivers/soc/ti/omap_prm.c index a3ffb19e402f..09985da8f6d0 100644 --- a/drivers/soc/ti/omap_prm.c +++ b/drivers/soc/ti/omap_prm.c @@ -16,6 +16,8 @@ #include #include +#include + struct omap_rst_map { s8 rst; s8 st; @@ -24,6 +26,7 @@ struct omap_rst_map { struct omap_prm_data { u32 base; const char *name; + const char *clkdm_name; u16 rstctrl; u16 rstst; const struct omap_rst_map *rstmap; @@ -40,6 +43,8 @@ struct omap_reset_data { struct omap_prm *prm; u32 mask; spinlock_t lock; + struct clockdomain *clkdm; + struct device *dev; }; #define to_omap_reset_data(p) container_of((p), struct omap_reset_data, rcdev) @@ -49,6 +54,7 @@ struct omap_reset_data { #define OMAP_PRM_HAS_RSTCTRL BIT(0) #define OMAP_PRM_HAS_RSTST BIT(1) +#define OMAP_PRM_HAS_NO_CLKDM BIT(2) #define OMAP_PRM_HAS_RESETS (OMAP_PRM_HAS_RSTCTRL | OMAP_PRM_HAS_RSTST) @@ -133,6 +139,8 @@ static int omap_reset_deassert(struct reset_controller_dev *rcdev, int st_bit; bool has_rstst; unsigned long flags; + struct ti_prm_platform_data *pdata = dev_get_platdata(reset->dev); + int ret = 0; has_rstst = reset->prm->data->rstst || (reset->prm->data->flags & OMAP_PRM_HAS_RSTST); @@ -145,6 +153,9 @@ static int omap_reset_deassert(struct reset_controller_dev *rcdev, writel_relaxed(v, reset->prm->base + reset->prm->data->rstst); } + if (reset->clkdm) + pdata->clkdm_deny_idle(reset->clkdm); + /* de-assert the reset control line */ spin_lock_irqsave(&reset->lock, flags); v = readl_relaxed(reset->prm->base + reset->prm->data->rstctrl); @@ -153,7 +164,7 @@ static int omap_reset_deassert(struct reset_controller_dev *rcdev, spin_unlock_irqrestore(&reset->lock, flags); if (!has_rstst) - return 0; + goto exit; /* wait for the status to be set */ ret = readl_relaxed_poll_timeout(reset->prm->base + @@ -164,7 +175,11 @@ static int omap_reset_deassert(struct reset_controller_dev *rcdev, pr_err("%s: timedout waiting for %s:%lu\n", __func__, reset->prm->data->name, id); - return 0; +exit: + if (reset->clkdm) + pdata->clkdm_allow_idle(reset->clkdm); + + return ret; } static const struct reset_control_ops omap_reset_ops = { @@ -189,6 +204,8 @@ static int omap_prm_reset_init(struct platform_device *pdev, { struct omap_reset_data *reset; const struct omap_rst_map *map; + struct ti_prm_platform_data *pdata = dev_get_platdata(&pdev->dev); + char buf[32]; /* * Check if we have controllable resets. If either rstctrl is non-zero @@ -198,6 +215,11 @@ static int omap_prm_reset_init(struct platform_device *pdev, if (!prm->data->rstctrl && !(prm->data->flags & OMAP_PRM_HAS_RSTCTRL)) return 0; + /* Check if we have the pdata callbacks in place */ + if (!pdata || !pdata->clkdm_lookup || !pdata->clkdm_deny_idle || + !pdata->clkdm_allow_idle) + return -EINVAL; + map = prm->data->rstmap; if (!map) return -EINVAL; @@ -212,10 +234,20 @@ static int omap_prm_reset_init(struct platform_device *pdev, reset->rcdev.nr_resets = OMAP_MAX_RESETS; reset->rcdev.of_xlate = omap_prm_reset_xlate; reset->rcdev.of_reset_n_cells = 1; + reset->dev = &pdev->dev; spin_lock_init(&reset->lock); reset->prm = prm; + sprintf(buf, "%s_clkdm", prm->data->clkdm_name ? prm->data->clkdm_name : + prm->data->name); + + if (!(prm->data->flags & OMAP_PRM_HAS_NO_CLKDM)) { + reset->clkdm = pdata->clkdm_lookup(buf); + if (!reset->clkdm) + return -EINVAL; + } + while (map->rst >= 0) { reset->mask |= BIT(map->rst); map++; diff --git a/include/linux/platform_data/ti-prm.h b/include/linux/platform_data/ti-prm.h new file mode 100644 index 000000000000..28154c3226c2 --- /dev/null +++ b/include/linux/platform_data/ti-prm.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * TI PRM (Power & Reset Manager) platform data + * + * Copyright (C) 2019 Texas Instruments, Inc. + * + * Tero Kristo + */ + +#ifndef _LINUX_PLATFORM_DATA_TI_PRM_H +#define _LINUX_PLATFORM_DATA_TI_PRM_H + +struct clockdomain; + +struct ti_prm_platform_data { + void (*clkdm_deny_idle)(struct clockdomain *clkdm); + void (*clkdm_allow_idle)(struct clockdomain *clkdm); + struct clockdomain * (*clkdm_lookup)(const char *name); +}; + +#endif /* _LINUX_PLATFORM_DATA_TI_PRM_H */ -- cgit v1.2.3-71-gd317 From f9bdad8ca8a40270576dd8751ac225febaa87f93 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Mon, 29 Oct 2018 13:23:40 -0400 Subject: NFS NFSD: defining nl4_servers structure needed by both These structures are needed by COPY_NOTIFY on the client and needed by the nfsd as well Reviewed-by: Jeff Layton Signed-off-by: Olga Kornievskaia --- include/linux/nfs4.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index fd59904a282c..5810e248c1bd 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -16,6 +16,7 @@ #include #include #include +#include enum nfs4_acl_whotype { NFS4_ACL_WHO_NAMED = 0, @@ -674,4 +675,27 @@ struct nfs4_op_map { } u; }; +struct nfs42_netaddr { + char netid[RPCBIND_MAXNETIDLEN]; + char addr[RPCBIND_MAXUADDRLEN + 1]; + u32 netid_len; + u32 addr_len; +}; + +enum netloc_type4 { + NL4_NAME = 1, + NL4_URL = 2, + NL4_NETADDR = 3, +}; + +struct nl4_server { + enum netloc_type4 nl4_type; + union { + struct { /* NL4_NAME, NL4_URL */ + int nl4_str_sz; + char nl4_str[NFS4_OPAQUE_LIMIT + 1]; + }; + struct nfs42_netaddr nl4_addr; /* NL4_NETADDR */ + } u; +}; #endif -- cgit v1.2.3-71-gd317 From 0491567b51efeca807da1125a1a0d5193875e286 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Tue, 4 Jun 2019 16:14:30 -0400 Subject: NFS: add COPY_NOTIFY operation Try using the delegation stateid, then the open stateid. Only NL4_NETATTR, No support for NL4_NAME and NL4_URL. Allow only one source server address to be returned for now. To distinguish between same server copy offload ("intra") and a copy between different server ("inter"), do a check of server owner identity and also make sure server is capable of doing a copy offload. Signed-off-by: Andy Adamson Signed-off-by: Olga Kornievskaia --- fs/nfs/nfs42.h | 12 ++++ fs/nfs/nfs42proc.c | 91 ++++++++++++++++++++++++ fs/nfs/nfs42xdr.c | 178 ++++++++++++++++++++++++++++++++++++++++++++++ fs/nfs/nfs4_fs.h | 2 + fs/nfs/nfs4client.c | 2 +- fs/nfs/nfs4file.c | 20 +++++- fs/nfs/nfs4proc.c | 1 + fs/nfs/nfs4xdr.c | 1 + include/linux/nfs4.h | 1 + include/linux/nfs_fs_sb.h | 1 + include/linux/nfs_xdr.h | 16 +++++ 11 files changed, 323 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h index 901cca7542f9..4995731a6714 100644 --- a/fs/nfs/nfs42.h +++ b/fs/nfs/nfs42.h @@ -13,6 +13,7 @@ #define PNFS_LAYOUTSTATS_MAXDEV (4) /* nfs4.2proc.c */ +#ifdef CONFIG_NFS_V4_2 int nfs42_proc_allocate(struct file *, loff_t, loff_t); ssize_t nfs42_proc_copy(struct file *, loff_t, struct file *, loff_t, size_t); int nfs42_proc_deallocate(struct file *, loff_t, loff_t); @@ -23,5 +24,16 @@ int nfs42_proc_clone(struct file *, struct file *, loff_t, loff_t, loff_t); int nfs42_proc_layouterror(struct pnfs_layout_segment *lseg, const struct nfs42_layout_error *errors, size_t n); +int nfs42_proc_copy_notify(struct file *, struct file *, + struct nfs42_copy_notify_res *); +static inline bool nfs42_files_from_same_server(struct file *in, + struct file *out) +{ + struct nfs_client *c_in = (NFS_SERVER(file_inode(in)))->nfs_client; + struct nfs_client *c_out = (NFS_SERVER(file_inode(out)))->nfs_client; + return nfs4_check_serverowner_major_id(c_in->cl_serverowner, + c_out->cl_serverowner); +} +#endif /* CONFIG_NFS_V4_2 */ #endif /* __LINUX_FS_NFS_NFS4_2_H */ diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 5196bfa7894d..6317dd89cf43 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -3,6 +3,7 @@ * Copyright (c) 2014 Anna Schumaker */ #include +#include #include #include #include @@ -15,10 +16,30 @@ #include "pnfs.h" #include "nfs4session.h" #include "internal.h" +#include "delegation.h" #define NFSDBG_FACILITY NFSDBG_PROC static int nfs42_do_offload_cancel_async(struct file *dst, nfs4_stateid *std); +static void nfs42_set_netaddr(struct file *filep, struct nfs42_netaddr *naddr) +{ + struct nfs_client *clp = (NFS_SERVER(file_inode(filep)))->nfs_client; + unsigned short port = 2049; + + rcu_read_lock(); + naddr->netid_len = scnprintf(naddr->netid, + sizeof(naddr->netid), "%s", + rpc_peeraddr2str(clp->cl_rpcclient, + RPC_DISPLAY_NETID)); + naddr->addr_len = scnprintf(naddr->addr, + sizeof(naddr->addr), + "%s.%u.%u", + rpc_peeraddr2str(clp->cl_rpcclient, + RPC_DISPLAY_ADDR), + port >> 8, port & 255); + rcu_read_unlock(); +} + static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, struct nfs_lock_context *lock, loff_t offset, loff_t len) { @@ -459,6 +480,76 @@ static int nfs42_do_offload_cancel_async(struct file *dst, return status; } +int _nfs42_proc_copy_notify(struct file *src, struct file *dst, + struct nfs42_copy_notify_args *args, + struct nfs42_copy_notify_res *res) +{ + struct nfs_server *src_server = NFS_SERVER(file_inode(src)); + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COPY_NOTIFY], + .rpc_argp = args, + .rpc_resp = res, + }; + int status; + struct nfs_open_context *ctx; + struct nfs_lock_context *l_ctx; + + ctx = get_nfs_open_context(nfs_file_open_context(src)); + l_ctx = nfs_get_lock_context(ctx); + if (IS_ERR(l_ctx)) + return PTR_ERR(l_ctx); + + status = nfs4_set_rw_stateid(&args->cna_src_stateid, ctx, l_ctx, + FMODE_READ); + nfs_put_lock_context(l_ctx); + if (status) + return status; + + status = nfs4_call_sync(src_server->client, src_server, &msg, + &args->cna_seq_args, &res->cnr_seq_res, 0); + if (status == -ENOTSUPP) + src_server->caps &= ~NFS_CAP_COPY_NOTIFY; + + put_nfs_open_context(nfs_file_open_context(src)); + return status; +} + +int nfs42_proc_copy_notify(struct file *src, struct file *dst, + struct nfs42_copy_notify_res *res) +{ + struct nfs_server *src_server = NFS_SERVER(file_inode(src)); + struct nfs42_copy_notify_args *args; + struct nfs4_exception exception = { + .inode = file_inode(src), + }; + int status; + + if (!(src_server->caps & NFS_CAP_COPY_NOTIFY)) + return -EOPNOTSUPP; + + args = kzalloc(sizeof(struct nfs42_copy_notify_args), GFP_NOFS); + if (args == NULL) + return -ENOMEM; + + args->cna_src_fh = NFS_FH(file_inode(src)), + args->cna_dst.nl4_type = NL4_NETADDR; + nfs42_set_netaddr(dst, &args->cna_dst.u.nl4_addr); + exception.stateid = &args->cna_src_stateid; + + do { + status = _nfs42_proc_copy_notify(src, dst, args, res); + if (status == -ENOTSUPP) { + status = -EOPNOTSUPP; + goto out; + } + status = nfs4_handle_exception(src_server, status, &exception); + } while (exception.retry); + +out: + kfree(args); + return status; +} + static loff_t _nfs42_proc_llseek(struct file *filep, struct nfs_lock_context *lock, loff_t offset, int whence) { diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index aed865a84629..ccabc0cd93dd 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -29,6 +29,16 @@ #define encode_offload_cancel_maxsz (op_encode_hdr_maxsz + \ XDR_QUADLEN(NFS4_STATEID_SIZE)) #define decode_offload_cancel_maxsz (op_decode_hdr_maxsz) +#define encode_copy_notify_maxsz (op_encode_hdr_maxsz + \ + XDR_QUADLEN(NFS4_STATEID_SIZE) + \ + 1 + /* nl4_type */ \ + 1 + XDR_QUADLEN(NFS4_OPAQUE_LIMIT)) +#define decode_copy_notify_maxsz (op_decode_hdr_maxsz + \ + 3 + /* cnr_lease_time */\ + XDR_QUADLEN(NFS4_STATEID_SIZE) + \ + 1 + /* Support 1 cnr_source_server */\ + 1 + /* nl4_type */ \ + 1 + XDR_QUADLEN(NFS4_OPAQUE_LIMIT)) #define encode_deallocate_maxsz (op_encode_hdr_maxsz + \ encode_fallocate_maxsz) #define decode_deallocate_maxsz (op_decode_hdr_maxsz) @@ -99,6 +109,12 @@ decode_sequence_maxsz + \ decode_putfh_maxsz + \ decode_offload_cancel_maxsz) +#define NFS4_enc_copy_notify_sz (compound_encode_hdr_maxsz + \ + encode_putfh_maxsz + \ + encode_copy_notify_maxsz) +#define NFS4_dec_copy_notify_sz (compound_decode_hdr_maxsz + \ + decode_putfh_maxsz + \ + decode_copy_notify_maxsz) #define NFS4_enc_deallocate_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ @@ -166,6 +182,26 @@ static void encode_allocate(struct xdr_stream *xdr, encode_fallocate(xdr, args); } +static void encode_nl4_server(struct xdr_stream *xdr, + const struct nl4_server *ns) +{ + encode_uint32(xdr, ns->nl4_type); + switch (ns->nl4_type) { + case NL4_NAME: + case NL4_URL: + encode_string(xdr, ns->u.nl4_str_sz, ns->u.nl4_str); + break; + case NL4_NETADDR: + encode_string(xdr, ns->u.nl4_addr.netid_len, + ns->u.nl4_addr.netid); + encode_string(xdr, ns->u.nl4_addr.addr_len, + ns->u.nl4_addr.addr); + break; + default: + WARN_ON_ONCE(1); + } +} + static void encode_copy(struct xdr_stream *xdr, const struct nfs42_copy_args *args, struct compound_hdr *hdr) @@ -191,6 +227,15 @@ static void encode_offload_cancel(struct xdr_stream *xdr, encode_nfs4_stateid(xdr, &args->osa_stateid); } +static void encode_copy_notify(struct xdr_stream *xdr, + const struct nfs42_copy_notify_args *args, + struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_COPY_NOTIFY, decode_copy_notify_maxsz, hdr); + encode_nfs4_stateid(xdr, &args->cna_src_stateid); + encode_nl4_server(xdr, &args->cna_dst); +} + static void encode_deallocate(struct xdr_stream *xdr, const struct nfs42_falloc_args *args, struct compound_hdr *hdr) @@ -354,6 +399,25 @@ static void nfs4_xdr_enc_offload_cancel(struct rpc_rqst *req, encode_nops(&hdr); } +/* + * Encode COPY_NOTIFY request + */ +static void nfs4_xdr_enc_copy_notify(struct rpc_rqst *req, + struct xdr_stream *xdr, + const void *data) +{ + const struct nfs42_copy_notify_args *args = data; + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->cna_seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->cna_seq_args, &hdr); + encode_putfh(xdr, args->cna_src_fh, &hdr); + encode_copy_notify(xdr, args, &hdr); + encode_nops(&hdr); +} + /* * Encode DEALLOCATE request */ @@ -490,6 +554,58 @@ static int decode_write_response(struct xdr_stream *xdr, return decode_verifier(xdr, &res->verifier.verifier); } +static int decode_nl4_server(struct xdr_stream *xdr, struct nl4_server *ns) +{ + struct nfs42_netaddr *naddr; + uint32_t dummy; + char *dummy_str; + __be32 *p; + int status; + + /* nl_type */ + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + return -EIO; + ns->nl4_type = be32_to_cpup(p); + switch (ns->nl4_type) { + case NL4_NAME: + case NL4_URL: + status = decode_opaque_inline(xdr, &dummy, &dummy_str); + if (unlikely(status)) + return status; + if (unlikely(dummy > NFS4_OPAQUE_LIMIT)) + return -EIO; + memcpy(&ns->u.nl4_str, dummy_str, dummy); + ns->u.nl4_str_sz = dummy; + break; + case NL4_NETADDR: + naddr = &ns->u.nl4_addr; + + /* netid string */ + status = decode_opaque_inline(xdr, &dummy, &dummy_str); + if (unlikely(status)) + return status; + if (unlikely(dummy > RPCBIND_MAXNETIDLEN)) + return -EIO; + naddr->netid_len = dummy; + memcpy(naddr->netid, dummy_str, naddr->netid_len); + + /* uaddr string */ + status = decode_opaque_inline(xdr, &dummy, &dummy_str); + if (unlikely(status)) + return status; + if (unlikely(dummy > RPCBIND_MAXUADDRLEN)) + return -EIO; + naddr->addr_len = dummy; + memcpy(naddr->addr, dummy_str, naddr->addr_len); + break; + default: + WARN_ON_ONCE(1); + return -EIO; + } + return 0; +} + static int decode_copy_requirements(struct xdr_stream *xdr, struct nfs42_copy_res *res) { __be32 *p; @@ -529,6 +645,42 @@ static int decode_offload_cancel(struct xdr_stream *xdr, return decode_op_hdr(xdr, OP_OFFLOAD_CANCEL); } +static int decode_copy_notify(struct xdr_stream *xdr, + struct nfs42_copy_notify_res *res) +{ + __be32 *p; + int status, count; + + status = decode_op_hdr(xdr, OP_COPY_NOTIFY); + if (status) + return status; + /* cnr_lease_time */ + p = xdr_inline_decode(xdr, 12); + if (unlikely(!p)) + return -EIO; + p = xdr_decode_hyper(p, &res->cnr_lease_time.seconds); + res->cnr_lease_time.nseconds = be32_to_cpup(p); + + status = decode_opaque_fixed(xdr, &res->cnr_stateid, NFS4_STATEID_SIZE); + if (unlikely(status)) + return -EIO; + + /* number of source addresses */ + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + return -EIO; + + count = be32_to_cpup(p); + if (count > 1) + pr_warn("NFS: %s: nsvr %d > Supported. Use first servers\n", + __func__, count); + + status = decode_nl4_server(xdr, &res->cnr_src); + if (unlikely(status)) + return -EIO; + return 0; +} + static int decode_deallocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res) { return decode_op_hdr(xdr, OP_DEALLOCATE); @@ -656,6 +808,32 @@ out: return status; } +/* + * Decode COPY_NOTIFY response + */ +static int nfs4_xdr_dec_copy_notify(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + void *data) +{ + struct nfs42_copy_notify_res *res = data; + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->cnr_seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_copy_notify(xdr, res); + +out: + return status; +} + /* * Decode DEALLOCATE request */ diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 16b2e5cc3e94..8e590b424d75 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -457,6 +457,8 @@ int nfs41_discover_server_trunking(struct nfs_client *clp, struct nfs_client **, const struct cred *); extern void nfs4_schedule_session_recovery(struct nfs4_session *, int); extern void nfs41_notify_server(struct nfs_client *); +bool nfs4_check_serverowner_major_id(struct nfs41_server_owner *o1, + struct nfs41_server_owner *o2); #else static inline void nfs4_schedule_session_recovery(struct nfs4_session *session, int err) { diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index da6204025a2d..54aaf553d009 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -629,7 +629,7 @@ out: /* * Returns true if the server major ids match */ -static bool +bool nfs4_check_serverowner_major_id(struct nfs41_server_owner *o1, struct nfs41_server_owner *o2) { diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 339663d04bf8..686a6c4071e3 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -133,6 +133,9 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t count, unsigned int flags) { + struct nfs42_copy_notify_res *cn_resp = NULL; + ssize_t ret; + /* Only offload copy if superblock is the same */ if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) return -EXDEV; @@ -140,7 +143,22 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in, return -EOPNOTSUPP; if (file_inode(file_in) == file_inode(file_out)) return -EOPNOTSUPP; - return nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count); + if (!nfs42_files_from_same_server(file_in, file_out)) { + cn_resp = kzalloc(sizeof(struct nfs42_copy_notify_res), + GFP_NOFS); + if (unlikely(cn_resp == NULL)) + return -ENOMEM; + + ret = nfs42_proc_copy_notify(file_in, file_out, cn_resp); + if (ret) { + ret = -EOPNOTSUPP; + goto out; + } + } + ret = nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count); +out: + kfree(cn_resp); + return ret; } static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in, diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 11eafcfc490b..505045b47670 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -9899,6 +9899,7 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = { | NFS_CAP_ALLOCATE | NFS_CAP_COPY | NFS_CAP_OFFLOAD_CANCEL + | NFS_CAP_COPY_NOTIFY | NFS_CAP_DEALLOCATE | NFS_CAP_SEEK | NFS_CAP_LAYOUTSTATS diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index ab07db0f07cd..2f9315de3d7d 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -7581,6 +7581,7 @@ const struct rpc_procinfo nfs4_procedures[] = { PROC42(CLONE, enc_clone, dec_clone), PROC42(COPY, enc_copy, dec_copy), PROC42(OFFLOAD_CANCEL, enc_offload_cancel, dec_offload_cancel), + PROC42(COPY_NOTIFY, enc_copy_notify, dec_copy_notify), PROC(LOOKUPP, enc_lookupp, dec_lookupp), PROC42(LAYOUTERROR, enc_layouterror, dec_layouterror), }; diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 5810e248c1bd..5e7a5261af4e 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -537,6 +537,7 @@ enum { NFSPROC4_CLNT_CLONE, NFSPROC4_CLNT_COPY, NFSPROC4_CLNT_OFFLOAD_CANCEL, + NFSPROC4_CLNT_COPY_NOTIFY, NFSPROC4_CLNT_LOOKUPP, NFSPROC4_CLNT_LAYOUTERROR, diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index a87fe854f008..e1c8748e1e82 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -276,5 +276,6 @@ struct nfs_server { #define NFS_CAP_COPY (1U << 24) #define NFS_CAP_OFFLOAD_CANCEL (1U << 25) #define NFS_CAP_LAYOUTERROR (1U << 26) +#define NFS_CAP_COPY_NOTIFY (1U << 27) #endif diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 9b8324ec08f3..0a7af40026d7 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1463,6 +1463,22 @@ struct nfs42_offload_status_res { int osr_status; }; +struct nfs42_copy_notify_args { + struct nfs4_sequence_args cna_seq_args; + + struct nfs_fh *cna_src_fh; + nfs4_stateid cna_src_stateid; + struct nl4_server cna_dst; +}; + +struct nfs42_copy_notify_res { + struct nfs4_sequence_res cnr_seq_res; + + struct nfstime4 cnr_lease_time; + nfs4_stateid cnr_stateid; + struct nl4_server cnr_src; +}; + struct nfs42_seek_args { struct nfs4_sequence_args seq_args; -- cgit v1.2.3-71-gd317 From 1d38f3f0d70008671f4dc055697ff3c3bb44a284 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Tue, 4 Jun 2019 11:54:18 -0400 Subject: NFS: add ca_source_server<> to COPY Support only one source server address: the same address that the client and source server use. Signed-off-by: Andy Adamson Signed-off-by: Olga Kornievskaia --- fs/nfs/nfs42.h | 3 ++- fs/nfs/nfs42proc.c | 26 +++++++++++++++++--------- fs/nfs/nfs42xdr.c | 12 ++++++++++-- fs/nfs/nfs4file.c | 7 ++++++- include/linux/nfs_xdr.h | 1 + 5 files changed, 36 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h index 4995731a6714..02e3810cd889 100644 --- a/fs/nfs/nfs42.h +++ b/fs/nfs/nfs42.h @@ -15,7 +15,8 @@ /* nfs4.2proc.c */ #ifdef CONFIG_NFS_V4_2 int nfs42_proc_allocate(struct file *, loff_t, loff_t); -ssize_t nfs42_proc_copy(struct file *, loff_t, struct file *, loff_t, size_t); +ssize_t nfs42_proc_copy(struct file *, loff_t, struct file *, loff_t, size_t, + struct nl4_server *, nfs4_stateid *); int nfs42_proc_deallocate(struct file *, loff_t, loff_t); loff_t nfs42_proc_llseek(struct file *, loff_t, int); int nfs42_proc_layoutstats_generic(struct nfs_server *, diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 6317dd89cf43..e34ade844737 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -243,7 +243,9 @@ static ssize_t _nfs42_proc_copy(struct file *src, struct file *dst, struct nfs_lock_context *dst_lock, struct nfs42_copy_args *args, - struct nfs42_copy_res *res) + struct nfs42_copy_res *res, + struct nl4_server *nss, + nfs4_stateid *cnr_stateid) { struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COPY], @@ -257,11 +259,15 @@ static ssize_t _nfs42_proc_copy(struct file *src, size_t count = args->count; ssize_t status; - status = nfs4_set_rw_stateid(&args->src_stateid, src_lock->open_context, - src_lock, FMODE_READ); - if (status) - return status; - + if (nss) { + args->cp_src = nss; + nfs4_stateid_copy(&args->src_stateid, cnr_stateid); + } else { + status = nfs4_set_rw_stateid(&args->src_stateid, + src_lock->open_context, src_lock, FMODE_READ); + if (status) + return status; + } status = nfs_filemap_write_and_wait_range(file_inode(src)->i_mapping, pos_src, pos_src + (loff_t)count - 1); if (status) @@ -325,8 +331,9 @@ out: } ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src, - struct file *dst, loff_t pos_dst, - size_t count) + struct file *dst, loff_t pos_dst, size_t count, + struct nl4_server *nss, + nfs4_stateid *cnr_stateid) { struct nfs_server *server = NFS_SERVER(file_inode(dst)); struct nfs_lock_context *src_lock; @@ -368,7 +375,8 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src, inode_lock(file_inode(dst)); err = _nfs42_proc_copy(src, src_lock, dst, dst_lock, - &args, &res); + &args, &res, + nss, cnr_stateid); inode_unlock(file_inode(dst)); if (err >= 0) diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index ccabc0cd93dd..c03f3246d6c5 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -21,7 +21,10 @@ #define encode_copy_maxsz (op_encode_hdr_maxsz + \ XDR_QUADLEN(NFS4_STATEID_SIZE) + \ XDR_QUADLEN(NFS4_STATEID_SIZE) + \ - 2 + 2 + 2 + 1 + 1 + 1) + 2 + 2 + 2 + 1 + 1 + 1 +\ + 1 + /* One cnr_source_server */\ + 1 + /* nl4_type */ \ + 1 + XDR_QUADLEN(NFS4_OPAQUE_LIMIT)) #define decode_copy_maxsz (op_decode_hdr_maxsz + \ NFS42_WRITE_RES_SIZE + \ 1 /* cr_consecutive */ + \ @@ -216,7 +219,12 @@ static void encode_copy(struct xdr_stream *xdr, encode_uint32(xdr, 1); /* consecutive = true */ encode_uint32(xdr, args->sync); - encode_uint32(xdr, 0); /* src server list */ + if (args->cp_src == NULL) { /* intra-ssc */ + encode_uint32(xdr, 0); /* no src server list */ + return; + } + encode_uint32(xdr, 1); /* supporting 1 server */ + encode_nl4_server(xdr, args->cp_src); } static void encode_offload_cancel(struct xdr_stream *xdr, diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 686a6c4071e3..b68b41be6d9f 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -134,6 +134,8 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in, size_t count, unsigned int flags) { struct nfs42_copy_notify_res *cn_resp = NULL; + struct nl4_server *nss = NULL; + nfs4_stateid *cnrs = NULL; ssize_t ret; /* Only offload copy if superblock is the same */ @@ -154,8 +156,11 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in, ret = -EOPNOTSUPP; goto out; } + nss = &cn_resp->cnr_src; + cnrs = &cn_resp->cnr_stateid; } - ret = nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count); + ret = nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count, + nss, cnrs); out: kfree(cn_resp); return ret; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 0a7af40026d7..008facac8a30 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1435,6 +1435,7 @@ struct nfs42_copy_args { u64 count; bool sync; + struct nl4_server *cp_src; }; struct nfs42_write_res { -- cgit v1.2.3-71-gd317 From 0e65a32c8a569db363048e17a708b1a0913adbef Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Fri, 14 Jun 2019 14:38:40 -0400 Subject: NFS: handle source server reboot When the source server reboots after a server-to-server copy was issued, we need to retry the copy from COPY_NOTIFY. We need to detect that the source server rebooted and there is a copy waiting on a destination server and wake it up. Signed-off-by: Olga Kornievskaia --- fs/nfs/nfs42proc.c | 68 ++++++++++++++++++++++++++++++++++---------------- fs/nfs/nfs4_fs.h | 1 + fs/nfs/nfs4file.c | 3 +++ fs/nfs/nfs4state.c | 26 +++++++++++++++---- include/linux/nfs_fs.h | 4 ++- 5 files changed, 75 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 5d833f5748e9..9c7feacb0358 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -153,22 +153,26 @@ out_unlock: } static int handle_async_copy(struct nfs42_copy_res *res, - struct nfs_server *server, + struct nfs_server *dst_server, + struct nfs_server *src_server, struct file *src, struct file *dst, - nfs4_stateid *src_stateid) + nfs4_stateid *src_stateid, + bool *restart) { struct nfs4_copy_state *copy, *tmp_copy; int status = NFS4_OK; bool found_pending = false; - struct nfs_open_context *ctx = nfs_file_open_context(dst); + struct nfs_open_context *dst_ctx = nfs_file_open_context(dst); + struct nfs_open_context *src_ctx = nfs_file_open_context(src); copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_NOFS); if (!copy) return -ENOMEM; - spin_lock(&server->nfs_client->cl_lock); - list_for_each_entry(tmp_copy, &server->nfs_client->pending_cb_stateids, + spin_lock(&dst_server->nfs_client->cl_lock); + list_for_each_entry(tmp_copy, + &dst_server->nfs_client->pending_cb_stateids, copies) { if (memcmp(&res->write_res.stateid, &tmp_copy->stateid, NFS4_STATEID_SIZE)) @@ -178,7 +182,7 @@ static int handle_async_copy(struct nfs42_copy_res *res, break; } if (found_pending) { - spin_unlock(&server->nfs_client->cl_lock); + spin_unlock(&dst_server->nfs_client->cl_lock); kfree(copy); copy = tmp_copy; goto out; @@ -186,19 +190,32 @@ static int handle_async_copy(struct nfs42_copy_res *res, memcpy(©->stateid, &res->write_res.stateid, NFS4_STATEID_SIZE); init_completion(©->completion); - copy->parent_state = ctx->state; + copy->parent_dst_state = dst_ctx->state; + copy->parent_src_state = src_ctx->state; + + list_add_tail(©->copies, &dst_server->ss_copies); + spin_unlock(&dst_server->nfs_client->cl_lock); - list_add_tail(©->copies, &server->ss_copies); - spin_unlock(&server->nfs_client->cl_lock); + if (dst_server != src_server) { + spin_lock(&src_server->nfs_client->cl_lock); + list_add_tail(©->src_copies, &src_server->ss_copies); + spin_unlock(&src_server->nfs_client->cl_lock); + } status = wait_for_completion_interruptible(©->completion); - spin_lock(&server->nfs_client->cl_lock); + spin_lock(&dst_server->nfs_client->cl_lock); list_del_init(©->copies); - spin_unlock(&server->nfs_client->cl_lock); + spin_unlock(&dst_server->nfs_client->cl_lock); + if (dst_server != src_server) { + spin_lock(&src_server->nfs_client->cl_lock); + list_del_init(©->src_copies); + spin_unlock(&src_server->nfs_client->cl_lock); + } if (status == -ERESTARTSYS) { goto out_cancel; - } else if (copy->flags) { + } else if (copy->flags || copy->error == NFS4ERR_PARTNER_NO_AUTH) { status = -EAGAIN; + *restart = true; goto out_cancel; } out: @@ -247,7 +264,8 @@ static ssize_t _nfs42_proc_copy(struct file *src, struct nfs42_copy_args *args, struct nfs42_copy_res *res, struct nl4_server *nss, - nfs4_stateid *cnr_stateid) + nfs4_stateid *cnr_stateid, + bool *restart) { struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COPY], @@ -255,7 +273,9 @@ static ssize_t _nfs42_proc_copy(struct file *src, .rpc_resp = res, }; struct inode *dst_inode = file_inode(dst); - struct nfs_server *server = NFS_SERVER(dst_inode); + struct inode *src_inode = file_inode(src); + struct nfs_server *dst_server = NFS_SERVER(dst_inode); + struct nfs_server *src_server = NFS_SERVER(src_inode); loff_t pos_src = args->src_pos; loff_t pos_dst = args->dst_pos; size_t count = args->count; @@ -291,13 +311,15 @@ static ssize_t _nfs42_proc_copy(struct file *src, if (!res->commit_res.verf) return -ENOMEM; } + set_bit(NFS_CLNT_SRC_SSC_COPY_STATE, + &src_lock->open_context->state->flags); set_bit(NFS_CLNT_DST_SSC_COPY_STATE, &dst_lock->open_context->state->flags); - status = nfs4_call_sync(server->client, server, &msg, + status = nfs4_call_sync(dst_server->client, dst_server, &msg, &args->seq_args, &res->seq_res, 0); if (status == -ENOTSUPP) - server->caps &= ~NFS_CAP_COPY; + dst_server->caps &= ~NFS_CAP_COPY; if (status) goto out; @@ -309,8 +331,8 @@ static ssize_t _nfs42_proc_copy(struct file *src, } if (!res->synchronous) { - status = handle_async_copy(res, server, src, dst, - &args->src_stateid); + status = handle_async_copy(res, dst_server, src_server, src, + dst, &args->src_stateid, restart); if (status) return status; } @@ -358,6 +380,7 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src, .stateid = &args.dst_stateid, }; ssize_t err, err2; + bool restart = false; src_lock = nfs_get_lock_context(nfs_file_open_context(src)); if (IS_ERR(src_lock)) @@ -378,7 +401,7 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src, err = _nfs42_proc_copy(src, src_lock, dst, dst_lock, &args, &res, - nss, cnr_stateid); + nss, cnr_stateid, &restart); inode_unlock(file_inode(dst)); if (err >= 0) @@ -388,8 +411,11 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src, err = -EOPNOTSUPP; break; } else if (err == -EAGAIN) { - dst_exception.retry = 1; - continue; + if (!restart) { + dst_exception.retry = 1; + continue; + } + break; } else if (err == -NFS4ERR_OFFLOAD_NO_REQS && !args.sync) { args.sync = true; dst_exception.retry = 1; diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 814674f073a1..2122748f6f7c 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -168,6 +168,7 @@ enum { NFS_STATE_CHANGE_WAIT, /* A state changing operation is outstanding */ #ifdef CONFIG_NFS_V4_2 NFS_CLNT_DST_SSC_COPY_STATE, /* dst server open state on client*/ + NFS_CLNT_SRC_SSC_COPY_STATE, /* src server open state on client*/ NFS_SRV_SSC_COPY_STATE, /* ssc state on the dst server */ #endif /* CONFIG_NFS_V4_2 */ }; diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index a932fc9ca9c4..2af30b7f5bfd 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -146,6 +146,7 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in, return -EOPNOTSUPP; if (file_inode(file_in) == file_inode(file_out)) return -EOPNOTSUPP; +retry: if (!nfs42_files_from_same_server(file_in, file_out)) { cn_resp = kzalloc(sizeof(struct nfs42_copy_notify_res), GFP_NOFS); @@ -164,6 +165,8 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in, nss, cnrs); out: kfree(cn_resp); + if (ret == -EAGAIN) + goto retry; return ret; } diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index c45b3007e2af..e799fbe9ac58 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1556,16 +1556,32 @@ static void nfs42_complete_copies(struct nfs4_state_owner *sp, struct nfs4_state { struct nfs4_copy_state *copy; - if (!test_bit(NFS_CLNT_DST_SSC_COPY_STATE, &state->flags)) + if (!test_bit(NFS_CLNT_DST_SSC_COPY_STATE, &state->flags) && + !test_bit(NFS_CLNT_SRC_SSC_COPY_STATE, &state->flags)) return; spin_lock(&sp->so_server->nfs_client->cl_lock); list_for_each_entry(copy, &sp->so_server->ss_copies, copies) { - if (!nfs4_stateid_match_other(&state->stateid, ©->parent_state->stateid)) - continue; + if ((test_bit(NFS_CLNT_DST_SSC_COPY_STATE, &state->flags) && + !nfs4_stateid_match_other(&state->stateid, + ©->parent_dst_state->stateid))) + continue; copy->flags = 1; - complete(©->completion); - break; + if (test_and_clear_bit(NFS_CLNT_DST_SSC_COPY_STATE, + &state->flags)) { + clear_bit(NFS_CLNT_SRC_SSC_COPY_STATE, &state->flags); + complete(©->completion); + } + } + list_for_each_entry(copy, &sp->so_server->ss_copies, src_copies) { + if ((test_bit(NFS_CLNT_SRC_SSC_COPY_STATE, &state->flags) && + !nfs4_stateid_match_other(&state->stateid, + ©->parent_src_state->stateid))) + continue; + copy->flags = 1; + if (test_and_clear_bit(NFS_CLNT_DST_SSC_COPY_STATE, + &state->flags)) + complete(©->completion); } spin_unlock(&sp->so_server->nfs_client->cl_lock); } diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 570a60c2f4f4..c06b1fd130f3 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -189,13 +189,15 @@ struct nfs_inode { struct nfs4_copy_state { struct list_head copies; + struct list_head src_copies; nfs4_stateid stateid; struct completion completion; uint64_t count; struct nfs_writeverf verf; int error; int flags; - struct nfs4_state *parent_state; + struct nfs4_state *parent_src_state; + struct nfs4_state *parent_dst_state; }; /* -- cgit v1.2.3-71-gd317 From 0d3c8501e32e19c9bdfc65e5d4e17e7772729332 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Tue, 8 Oct 2019 10:13:55 -0700 Subject: Input: pixcir_i2c_ts - move definitions into a single file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit All the defined symbols from linux/platform_data/pixcir_i2c_ts.h are only used by the pixcir_i2c_ts driver, so move all the definitions locally and get rid of the pixcir_i2c_ts.h file. Signed-off-by: Fabio Estevam Reviewed-by: Roger Quadros Tested-by: Michal Vokáč Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/pixcir_i2c_ts.c | 60 ++++++++++++++++++++++++++- include/linux/platform_data/pixcir_i2c_ts.h | 64 ----------------------------- 2 files changed, 59 insertions(+), 65 deletions(-) delete mode 100644 include/linux/platform_data/pixcir_i2c_ts.h (limited to 'include/linux') diff --git a/drivers/input/touchscreen/pixcir_i2c_ts.c b/drivers/input/touchscreen/pixcir_i2c_ts.c index 4561d65e7a1e..acc9504aa35b 100644 --- a/drivers/input/touchscreen/pixcir_i2c_ts.c +++ b/drivers/input/touchscreen/pixcir_i2c_ts.c @@ -15,11 +15,69 @@ #include #include #include -#include #include #define PIXCIR_MAX_SLOTS 5 /* Max fingers supported by driver */ +/* + * Register map + */ +#define PIXCIR_REG_POWER_MODE 51 +#define PIXCIR_REG_INT_MODE 52 + +/* + * Power modes: + * active: max scan speed + * idle: lower scan speed with automatic transition to active on touch + * halt: datasheet says sleep but this is more like halt as the chip + * clocks are cut and it can only be brought out of this mode + * using the RESET pin. + */ +enum pixcir_power_mode { + PIXCIR_POWER_ACTIVE, + PIXCIR_POWER_IDLE, + PIXCIR_POWER_HALT, +}; + +#define PIXCIR_POWER_MODE_MASK 0x03 +#define PIXCIR_POWER_ALLOW_IDLE (1UL << 2) + +/* + * Interrupt modes: + * periodical: interrupt is asserted periodicaly + * diff coordinates: interrupt is asserted when coordinates change + * level on touch: interrupt level asserted during touch + * pulse on touch: interrupt pulse asserted during touch + * + */ +enum pixcir_int_mode { + PIXCIR_INT_PERIODICAL, + PIXCIR_INT_DIFF_COORD, + PIXCIR_INT_LEVEL_TOUCH, + PIXCIR_INT_PULSE_TOUCH, +}; + +#define PIXCIR_INT_MODE_MASK 0x03 +#define PIXCIR_INT_ENABLE (1UL << 3) +#define PIXCIR_INT_POL_HIGH (1UL << 2) + +/** + * struct pixcir_irc_chip_data - chip related data + * @max_fingers: Max number of fingers reported simultaneously by h/w + * @has_hw_ids: Hardware supports finger tracking IDs + * + */ +struct pixcir_i2c_chip_data { + u8 max_fingers; + bool has_hw_ids; +}; + +struct pixcir_ts_platform_data { + int x_max; + int y_max; + struct pixcir_i2c_chip_data chip; +}; + struct pixcir_i2c_ts_data { struct i2c_client *client; struct input_dev *input; diff --git a/include/linux/platform_data/pixcir_i2c_ts.h b/include/linux/platform_data/pixcir_i2c_ts.h deleted file mode 100644 index 4ab3cd6f1cc2..000000000000 --- a/include/linux/platform_data/pixcir_i2c_ts.h +++ /dev/null @@ -1,64 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _PIXCIR_I2C_TS_H -#define _PIXCIR_I2C_TS_H - -/* - * Register map - */ -#define PIXCIR_REG_POWER_MODE 51 -#define PIXCIR_REG_INT_MODE 52 - -/* - * Power modes: - * active: max scan speed - * idle: lower scan speed with automatic transition to active on touch - * halt: datasheet says sleep but this is more like halt as the chip - * clocks are cut and it can only be brought out of this mode - * using the RESET pin. - */ -enum pixcir_power_mode { - PIXCIR_POWER_ACTIVE, - PIXCIR_POWER_IDLE, - PIXCIR_POWER_HALT, -}; - -#define PIXCIR_POWER_MODE_MASK 0x03 -#define PIXCIR_POWER_ALLOW_IDLE (1UL << 2) - -/* - * Interrupt modes: - * periodical: interrupt is asserted periodicaly - * diff coordinates: interrupt is asserted when coordinates change - * level on touch: interrupt level asserted during touch - * pulse on touch: interrupt pulse asserted druing touch - * - */ -enum pixcir_int_mode { - PIXCIR_INT_PERIODICAL, - PIXCIR_INT_DIFF_COORD, - PIXCIR_INT_LEVEL_TOUCH, - PIXCIR_INT_PULSE_TOUCH, -}; - -#define PIXCIR_INT_MODE_MASK 0x03 -#define PIXCIR_INT_ENABLE (1UL << 3) -#define PIXCIR_INT_POL_HIGH (1UL << 2) - -/** - * struct pixcir_irc_chip_data - chip related data - * @max_fingers: Max number of fingers reported simultaneously by h/w - * @has_hw_ids: Hardware supports finger tracking IDs - * - */ -struct pixcir_i2c_chip_data { - u8 max_fingers; - bool has_hw_ids; -}; - -struct pixcir_ts_platform_data { - int x_max; - int y_max; - struct pixcir_i2c_chip_data chip; -}; - -#endif -- cgit v1.2.3-71-gd317 From 690a6ca7df3de7b90546bc10a620d1ac8ccaa1a1 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 8 Oct 2019 21:03:14 -0700 Subject: DIM: fix dim.h kernel-doc and headers Lots of fixes to kernel-doc in structs, enums, and functions. Also add header files that are being used but not yet #included. Signed-off-by: Randy Dunlap Cc: Yamin Friedman Cc: Tal Gilboa Cc: Saeed Mahameed Cc: Doug Ledford Cc: Jason Gunthorpe Cc: linux-rdma@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Jakub Kicinski --- include/linux/dim.h | 63 ++++++++++++++++++++++++++++------------------------- 1 file changed, 33 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dim.h b/include/linux/dim.h index 9fa4b3f88c39..b698266d0035 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -4,22 +4,26 @@ #ifndef DIM_H #define DIM_H +#include +#include #include +#include +#include -/** +/* * Number of events between DIM iterations. * Causes a moderation of the algorithm run. */ #define DIM_NEVENTS 64 -/** +/* * Is a difference between values justifies taking an action. * We consider 10% difference as significant. */ #define IS_SIGNIFICANT_DIFF(val, ref) \ (((100UL * abs((val) - (ref))) / (ref)) > 10) -/** +/* * Calculate the gap between two values. * Take wrap-around and variable size into consideration. */ @@ -27,12 +31,13 @@ & (BIT_ULL(bits) - 1)) /** - * Structure for CQ moderation values. + * struct dim_cq_moder - Structure for CQ moderation values. * Used for communications between DIM and its consumer. * * @usec: CQ timer suggestion (by DIM) * @pkts: CQ packet counter suggestion (by DIM) - * @cq_period_mode: CQ priod count mode (from CQE/EQE) + * @comps: Completion counter + * @cq_period_mode: CQ period count mode (from CQE/EQE) */ struct dim_cq_moder { u16 usec; @@ -42,13 +47,14 @@ struct dim_cq_moder { }; /** - * Structure for DIM sample data. + * struct dim_sample - Structure for DIM sample data. * Used for communications between DIM and its consumer. * * @time: Sample timestamp * @pkt_ctr: Number of packets * @byte_ctr: Number of bytes * @event_ctr: Number of events + * @comp_ctr: Current completion counter */ struct dim_sample { ktime_t time; @@ -59,12 +65,14 @@ struct dim_sample { }; /** - * Structure for DIM stats. + * struct dim_stats - Structure for DIM stats. * Used for holding current measured rates. * * @ppms: Packets per msec * @bpms: Bytes per msec * @epms: Events per msec + * @cpms: Completions per msec + * @cpe_ratio: Ratio of completions to events */ struct dim_stats { int ppms; /* packets per msec */ @@ -75,12 +83,13 @@ struct dim_stats { }; /** - * Main structure for dynamic interrupt moderation (DIM). + * struct dim - Main structure for dynamic interrupt moderation (DIM). * Used for holding all information about a specific DIM instance. * * @state: Algorithm state (see below) * @prev_stats: Measured rates from previous iteration (for comparison) * @start_sample: Sampled data at start of current iteration + * @measuring_sample: A &dim_sample that is used to update the current events * @work: Work to perform on action required * @priv: A pointer to the struct that points to dim * @profile_ix: Current moderation profile @@ -106,24 +115,21 @@ struct dim { }; /** - * enum dim_cq_period_mode - * - * These are the modes for CQ period count. + * enum dim_cq_period_mode - Modes for CQ period count * * @DIM_CQ_PERIOD_MODE_START_FROM_EQE: Start counting from EQE * @DIM_CQ_PERIOD_MODE_START_FROM_CQE: Start counting from CQE (implies timer reset) * @DIM_CQ_PERIOD_NUM_MODES: Number of modes */ -enum { +enum dim_cq_period_mode { DIM_CQ_PERIOD_MODE_START_FROM_EQE = 0x0, DIM_CQ_PERIOD_MODE_START_FROM_CQE = 0x1, DIM_CQ_PERIOD_NUM_MODES }; /** - * enum dim_state + * enum dim_state - DIM algorithm states * - * These are the DIM algorithm states. * These will determine if the algorithm is in a valid state to start an iteration. * * @DIM_START_MEASURE: This is the first iteration (also after applying a new profile) @@ -131,16 +137,15 @@ enum { * need to perform an action * @DIM_APPLY_NEW_PROFILE: DIM consumer is currently applying a profile - no need to measure */ -enum { +enum dim_state { DIM_START_MEASURE, DIM_MEASURE_IN_PROGRESS, DIM_APPLY_NEW_PROFILE, }; /** - * enum dim_tune_state + * enum dim_tune_state - DIM algorithm tune states * - * These are the DIM algorithm tune states. * These will determine which action the algorithm should perform. * * @DIM_PARKING_ON_TOP: Algorithm found a local top point - exit on significant difference @@ -148,7 +153,7 @@ enum { * @DIM_GOING_RIGHT: Algorithm is currently trying higher moderation levels * @DIM_GOING_LEFT: Algorithm is currently trying lower moderation levels */ -enum { +enum dim_tune_state { DIM_PARKING_ON_TOP, DIM_PARKING_TIRED, DIM_GOING_RIGHT, @@ -156,25 +161,23 @@ enum { }; /** - * enum dim_stats_state + * enum dim_stats_state - DIM algorithm statistics states * - * These are the DIM algorithm statistics states. * These will determine the verdict of current iteration. * * @DIM_STATS_WORSE: Current iteration shows worse performance than before - * @DIM_STATS_WORSE: Current iteration shows same performance than before - * @DIM_STATS_WORSE: Current iteration shows better performance than before + * @DIM_STATS_SAME: Current iteration shows same performance than before + * @DIM_STATS_BETTER: Current iteration shows better performance than before */ -enum { +enum dim_stats_state { DIM_STATS_WORSE, DIM_STATS_SAME, DIM_STATS_BETTER, }; /** - * enum dim_step_result + * enum dim_step_result - DIM algorithm step results * - * These are the DIM algorithm step results. * These describe the result of a step. * * @DIM_STEPPED: Performed a regular step @@ -182,7 +185,7 @@ enum { * tired parking * @DIM_ON_EDGE: Stepped to the most left/right profile */ -enum { +enum dim_step_result { DIM_STEPPED, DIM_TOO_TIRED, DIM_ON_EDGE, @@ -199,7 +202,7 @@ enum { bool dim_on_top(struct dim *dim); /** - * dim_turn - change profile alterning direction + * dim_turn - change profile altering direction * @dim: DIM context * * Go left if we were going right and vice-versa. @@ -238,7 +241,7 @@ void dim_calc_stats(struct dim_sample *start, struct dim_sample *end, struct dim_stats *curr_stats); /** - * dim_update_sample - set a sample's fields with give values + * dim_update_sample - set a sample's fields with given values * @event_ctr: number of events to set * @packets: number of packets to set * @bytes: number of bytes to set @@ -304,8 +307,8 @@ struct dim_cq_moder net_dim_get_def_tx_moderation(u8 cq_period_mode); * @end_sample: Current data measurement * * Called by the consumer. - * This is the main logic of the algorithm, where data is processed in order to decide on next - * required action. + * This is the main logic of the algorithm, where data is processed in order + * to decide on next required action. */ void net_dim(struct dim *dim, struct dim_sample end_sample); -- cgit v1.2.3-71-gd317 From c31e73121f4c1ec45a3e523ac6ce3ce6dafdcec1 Mon Sep 17 00:00:00 2001 From: Murali Nalajala Date: Mon, 7 Oct 2019 13:37:42 -0700 Subject: base: soc: Handle custom soc information sysfs entries Soc framework exposed sysfs entries are not sufficient for some of the h/w platforms. Currently there is no interface where soc drivers can expose further information about their SoCs via soc framework. This change address this limitation where clients can pass their custom entries as attribute group and soc framework would expose them as sysfs properties. Signed-off-by: Murali Nalajala Reviewed-by: Bjorn Andersson Reviewed-by: Stephen Boyd Link: https://lore.kernel.org/r/1570480662-25252-1-git-send-email-mnalajal@codeaurora.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/soc.c | 30 +++++++++++++++++------------- include/linux/sys_soc.h | 1 + 2 files changed, 18 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/soc.c b/drivers/base/soc.c index 7c0c5ca5953d..4af11a423475 100644 --- a/drivers/base/soc.c +++ b/drivers/base/soc.c @@ -104,15 +104,12 @@ static const struct attribute_group soc_attr_group = { .is_visible = soc_attribute_mode, }; -static const struct attribute_group *soc_attr_groups[] = { - &soc_attr_group, - NULL, -}; - static void soc_release(struct device *dev) { struct soc_device *soc_dev = container_of(dev, struct soc_device, dev); + ida_simple_remove(&soc_ida, soc_dev->soc_dev_num); + kfree(soc_dev->dev.groups); kfree(soc_dev); } @@ -121,6 +118,7 @@ static struct soc_device_attribute *early_soc_dev_attr; struct soc_device *soc_device_register(struct soc_device_attribute *soc_dev_attr) { struct soc_device *soc_dev; + const struct attribute_group **soc_attr_groups; int ret; if (!soc_bus_type.p) { @@ -136,10 +134,18 @@ struct soc_device *soc_device_register(struct soc_device_attribute *soc_dev_attr goto out1; } + soc_attr_groups = kcalloc(3, sizeof(*soc_attr_groups), GFP_KERNEL); + if (!soc_attr_groups) { + ret = -ENOMEM; + goto out2; + } + soc_attr_groups[0] = &soc_attr_group; + soc_attr_groups[1] = soc_dev_attr->custom_attr_group; + /* Fetch a unique (reclaimable) SOC ID. */ ret = ida_simple_get(&soc_ida, 0, 0, GFP_KERNEL); if (ret < 0) - goto out2; + goto out3; soc_dev->soc_dev_num = ret; soc_dev->attr = soc_dev_attr; @@ -150,15 +156,15 @@ struct soc_device *soc_device_register(struct soc_device_attribute *soc_dev_attr dev_set_name(&soc_dev->dev, "soc%d", soc_dev->soc_dev_num); ret = device_register(&soc_dev->dev); - if (ret) - goto out3; + if (ret) { + put_device(&soc_dev->dev); + return ERR_PTR(ret); + } return soc_dev; out3: - ida_simple_remove(&soc_ida, soc_dev->soc_dev_num); - put_device(&soc_dev->dev); - soc_dev = NULL; + kfree(soc_attr_groups); out2: kfree(soc_dev); out1: @@ -169,8 +175,6 @@ EXPORT_SYMBOL_GPL(soc_device_register); /* Ensure soc_dev->attr is freed prior to calling soc_device_unregister. */ void soc_device_unregister(struct soc_device *soc_dev) { - ida_simple_remove(&soc_ida, soc_dev->soc_dev_num); - device_unregister(&soc_dev->dev); early_soc_dev_attr = NULL; } diff --git a/include/linux/sys_soc.h b/include/linux/sys_soc.h index 48ceea867dd6..d9b3cf0f410c 100644 --- a/include/linux/sys_soc.h +++ b/include/linux/sys_soc.h @@ -15,6 +15,7 @@ struct soc_device_attribute { const char *serial_number; const char *soc_id; const void *data; + const struct attribute_group *custom_attr_group; }; /** -- cgit v1.2.3-71-gd317 From 977da0738f3ba3569b883ed6209c300bfcb695d4 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 30 Sep 2019 14:14:35 +0200 Subject: crypto: inside-secure - Remove #ifdef checks When both PCI and OF are disabled, no drivers are registered, and we get some unused-function warnings: drivers/crypto/inside-secure/safexcel.c:1221:13: error: unused function 'safexcel_unregister_algorithms' [-Werror,-Wunused-function] static void safexcel_unregister_algorithms(struct safexcel_crypto_priv *priv) drivers/crypto/inside-secure/safexcel.c:1307:12: error: unused function 'safexcel_probe_generic' [-Werror,-Wunused-function] static int safexcel_probe_generic(void *pdev, drivers/crypto/inside-secure/safexcel.c:1531:13: error: unused function 'safexcel_hw_reset_rings' [-Werror,-Wunused-function] static void safexcel_hw_reset_rings(struct safexcel_crypto_priv *priv) It's better to make the compiler see what is going on and remove such ifdef checks completely. In case of PCI, this is trivial since pci_register_driver() is defined to an empty function that makes the compiler subsequently drop all unused code silently. The global pcireg_rc/ofreg_rc variables are not actually needed here since the driver registration does not fail in ways that would make it helpful. For CONFIG_OF, an IS_ENABLED() check is still required, since platform drivers can exist both with and without it. A little change to linux/pci.h is needed to ensure that pcim_enable_device() is visible to the driver. Moving the declaration outside of ifdef would be sufficient here, but for consistency with the rest of the file, adding an inline helper is probably best. Fixes: 212ef6f29e5b ("crypto: inside-secure - Fix unused variable warning when CONFIG_PCI=n") Signed-off-by: Arnd Bergmann Acked-by: Bjorn Helgaas # pci.h Signed-off-by: Herbert Xu --- drivers/crypto/inside-secure/safexcel.c | 49 ++++++++------------------------- include/linux/pci.h | 1 + 2 files changed, 13 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c index cd7dcd8986f5..5342ba61b02e 100644 --- a/drivers/crypto/inside-secure/safexcel.c +++ b/drivers/crypto/inside-secure/safexcel.c @@ -1671,7 +1671,6 @@ static void safexcel_hw_reset_rings(struct safexcel_crypto_priv *priv) } } -#if IS_ENABLED(CONFIG_OF) /* for Device Tree platform driver */ static int safexcel_probe(struct platform_device *pdev) @@ -1790,9 +1789,7 @@ static struct platform_driver crypto_safexcel = { .of_match_table = safexcel_of_match_table, }, }; -#endif -#if IS_ENABLED(CONFIG_PCI) /* PCIE devices - i.e. Inside Secure development boards */ static int safexcel_pci_probe(struct pci_dev *pdev, @@ -1913,54 +1910,32 @@ static struct pci_driver safexcel_pci_driver = { .probe = safexcel_pci_probe, .remove = safexcel_pci_remove, }; -#endif - -/* Unfortunately, we have to resort to global variables here */ -#if IS_ENABLED(CONFIG_PCI) -int pcireg_rc = -EINVAL; /* Default safe value */ -#endif -#if IS_ENABLED(CONFIG_OF) -int ofreg_rc = -EINVAL; /* Default safe value */ -#endif static int __init safexcel_init(void) { -#if IS_ENABLED(CONFIG_PCI) + int ret; + /* Register PCI driver */ - pcireg_rc = pci_register_driver(&safexcel_pci_driver); -#endif + ret = pci_register_driver(&safexcel_pci_driver); -#if IS_ENABLED(CONFIG_OF) /* Register platform driver */ - ofreg_rc = platform_driver_register(&crypto_safexcel); - #if IS_ENABLED(CONFIG_PCI) - /* Return success if either PCI or OF registered OK */ - return pcireg_rc ? ofreg_rc : 0; - #else - return ofreg_rc; - #endif -#else - #if IS_ENABLED(CONFIG_PCI) - return pcireg_rc; - #else - return -EINVAL; - #endif -#endif + if (IS_ENABLED(CONFIG_OF) && !ret) { + ret = platform_driver_register(&crypto_safexcel); + if (ret) + pci_unregister_driver(&safexcel_pci_driver); + } + + return ret; } static void __exit safexcel_exit(void) { -#if IS_ENABLED(CONFIG_OF) /* Unregister platform driver */ - if (!ofreg_rc) + if (IS_ENABLED(CONFIG_OF)) platform_driver_unregister(&crypto_safexcel); -#endif -#if IS_ENABLED(CONFIG_PCI) /* Unregister PCI driver if successfully registered before */ - if (!pcireg_rc) - pci_unregister_driver(&safexcel_pci_driver); -#endif + pci_unregister_driver(&safexcel_pci_driver); } module_init(safexcel_init); diff --git a/include/linux/pci.h b/include/linux/pci.h index f9088c89a534..1a6cf19eac2d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1686,6 +1686,7 @@ static inline struct pci_dev *pci_get_class(unsigned int class, static inline void pci_set_master(struct pci_dev *dev) { } static inline int pci_enable_device(struct pci_dev *dev) { return -EIO; } static inline void pci_disable_device(struct pci_dev *dev) { } +static inline int pcim_enable_device(struct pci_dev *pdev) { return -EIO; } static inline int pci_assign_resource(struct pci_dev *dev, int i) { return -EBUSY; } static inline int __pci_register_driver(struct pci_driver *drv, -- cgit v1.2.3-71-gd317 From fefad9ef58ffc228f7b78b667c2aea8267503350 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 24 Sep 2019 08:44:20 +0200 Subject: seccomp: simplify secure_computing() Afaict, the struct seccomp_data argument to secure_computing() is unused by all current callers. So let's remove it. The argument was added in [1]. It was added because having the arch supply the syscall arguments used to be faster than having it done by secure_computing() (cf. Andy's comment in [2]). This is not true anymore though. /* References */ [1]: 2f275de5d1ed ("seccomp: Add a seccomp_data parameter secure_computing()") [2]: https://lore.kernel.org/r/CALCETrU_fs_At-hTpr231kpaAd0z7xJN4ku-DvzhRU6cvcJA_w@mail.gmail.com Signed-off-by: Christian Brauner Cc: Andy Lutomirski Cc: Thomas Gleixner Cc: Will Drewry Cc: Oleg Nesterov Cc: linux-arm-kernel@lists.infradead.org Cc: linux-parisc@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: linux-um@lists.infradead.org Cc: x86@kernel.org Acked-by: Borislav Petkov Acked-by: Andy Lutomirski Link: https://lore.kernel.org/r/20190924064420.6353-1-christian.brauner@ubuntu.com Signed-off-by: Kees Cook --- arch/arm/kernel/ptrace.c | 2 +- arch/arm64/kernel/ptrace.c | 2 +- arch/parisc/kernel/ptrace.c | 2 +- arch/s390/kernel/ptrace.c | 2 +- arch/um/kernel/skas/syscall.c | 2 +- arch/x86/entry/vsyscall/vsyscall_64.c | 2 +- include/linux/seccomp.h | 6 +++--- 7 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c index 324352787aea..b606cded90cd 100644 --- a/arch/arm/kernel/ptrace.c +++ b/arch/arm/kernel/ptrace.c @@ -923,7 +923,7 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs, int scno) /* Do seccomp after ptrace; syscall may have changed. */ #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER - if (secure_computing(NULL) == -1) + if (secure_computing() == -1) return -1; #else /* XXX: remove this once OABI gets fixed */ diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 21176d02e21a..6771c399d40c 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1816,7 +1816,7 @@ int syscall_trace_enter(struct pt_regs *regs) } /* Do the secure computing after ptrace; failures should be fast. */ - if (secure_computing(NULL) == -1) + if (secure_computing() == -1) return -1; if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c index 9f6ff7bc06f9..f8c07dcbfb49 100644 --- a/arch/parisc/kernel/ptrace.c +++ b/arch/parisc/kernel/ptrace.c @@ -342,7 +342,7 @@ long do_syscall_trace_enter(struct pt_regs *regs) } /* Do the secure computing check after ptrace. */ - if (secure_computing(NULL) == -1) + if (secure_computing() == -1) return -1; #ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index ad71132374f0..58faa12542a1 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -856,7 +856,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) } /* Do the secure computing check after ptrace. */ - if (secure_computing(NULL)) { + if (secure_computing()) { /* seccomp failures shouldn't expose any additional code. */ return -1; } diff --git a/arch/um/kernel/skas/syscall.c b/arch/um/kernel/skas/syscall.c index f574b1856bc6..40d90dddf3f1 100644 --- a/arch/um/kernel/skas/syscall.c +++ b/arch/um/kernel/skas/syscall.c @@ -35,7 +35,7 @@ void handle_syscall(struct uml_pt_regs *r) goto out; /* Do the seccomp check after ptrace; failures should be fast. */ - if (secure_computing(NULL) == -1) + if (secure_computing() == -1) goto out; syscall = UPT_SYSCALL_NR(r); diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index e7c596dea947..b10cbf71a8cc 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -222,7 +222,7 @@ bool emulate_vsyscall(unsigned long error_code, */ regs->orig_ax = syscall_nr; regs->ax = -ENOSYS; - tmp = secure_computing(NULL); + tmp = secure_computing(); if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) { warn_bad_vsyscall(KERN_DEBUG, regs, "seccomp tried to change syscall nr or ip"); diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 84868d37b35d..03583b6d1416 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -33,10 +33,10 @@ struct seccomp { #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER extern int __secure_computing(const struct seccomp_data *sd); -static inline int secure_computing(const struct seccomp_data *sd) +static inline int secure_computing(void) { if (unlikely(test_thread_flag(TIF_SECCOMP))) - return __secure_computing(sd); + return __secure_computing(NULL); return 0; } #else @@ -59,7 +59,7 @@ struct seccomp { }; struct seccomp_filter { }; #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER -static inline int secure_computing(struct seccomp_data *sd) { return 0; } +static inline int secure_computing(void) { return 0; } #else static inline void secure_computing_strict(int this_syscall) { return; } #endif -- cgit v1.2.3-71-gd317 From 56c9aa07942434490890ac35bba99026e66cb949 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Thu, 3 Oct 2019 15:32:09 +0300 Subject: software node: Make argument to to_software_node const to_software_node() does not need to modify the fwnode_handle it operates on; therefore make it const. This allows passing a const fwnode_handle to to_software_node(). Signed-off-by: Sakari Ailus Reviewed-by: Andy Shevchenko Reviewed-by: Heikki Krogerus Signed-off-by: Rafael J. Wysocki --- drivers/base/swnode.c | 4 ++-- include/linux/property.h | 3 ++- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c index d5b4905e2adb..9cde143201f5 100644 --- a/drivers/base/swnode.c +++ b/drivers/base/swnode.c @@ -71,9 +71,9 @@ software_node_to_swnode(const struct software_node *node) return swnode; } -const struct software_node *to_software_node(struct fwnode_handle *fwnode) +const struct software_node *to_software_node(const struct fwnode_handle *fwnode) { - struct swnode *swnode = to_swnode(fwnode); + const struct swnode *swnode = to_swnode(fwnode); return swnode ? swnode->node : NULL; } diff --git a/include/linux/property.h b/include/linux/property.h index 9b3d4ca3a73a..87d795a1e2d6 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -418,7 +418,8 @@ struct software_node { }; bool is_software_node(const struct fwnode_handle *fwnode); -const struct software_node *to_software_node(struct fwnode_handle *fwnode); +const struct software_node * +to_software_node(const struct fwnode_handle *fwnode); struct fwnode_handle *software_node_fwnode(const struct software_node *node); const struct software_node * -- cgit v1.2.3-71-gd317 From 87e5e95db31a27d117fbb4a5d464f44adb4c2ee2 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Thu, 3 Oct 2019 15:32:11 +0300 Subject: device property: Add functions for accessing node's parents Add two convenience functions for accessing node's parents: fwnode_count_parents() returns the number of parent nodes a given node has. fwnode_get_nth_parent() returns node's parent at a given distance from the node itself. Signed-off-by: Sakari Ailus Reviewed-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- drivers/base/property.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/property.h | 3 +++ 2 files changed, 49 insertions(+) (limited to 'include/linux') diff --git a/drivers/base/property.c b/drivers/base/property.c index 3d9dffbe9637..f2e555e68b56 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -590,6 +590,52 @@ struct fwnode_handle *fwnode_get_next_parent(struct fwnode_handle *fwnode) } EXPORT_SYMBOL_GPL(fwnode_get_next_parent); +/** + * fwnode_count_parents - Return the number of parents a node has + * @fwnode: The node the parents of which are to be counted + * + * Returns the number of parents a node has. + */ +unsigned int fwnode_count_parents(const struct fwnode_handle *fwnode) +{ + struct fwnode_handle *__fwnode; + unsigned int count; + + __fwnode = fwnode_get_parent(fwnode); + + for (count = 0; __fwnode; count++) + __fwnode = fwnode_get_next_parent(__fwnode); + + return count; +} +EXPORT_SYMBOL_GPL(fwnode_count_parents); + +/** + * fwnode_get_nth_parent - Return an nth parent of a node + * @fwnode: The node the parent of which is requested + * @depth: Distance of the parent from the node + * + * Returns the nth parent of a node. If there is no parent at the requested + * @depth, %NULL is returned. If @depth is 0, the functionality is equivalent to + * fwnode_handle_get(). For @depth == 1, it is fwnode_get_parent() and so on. + * + * The caller is responsible for calling fwnode_handle_put() for the returned + * node. + */ +struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwnode, + unsigned int depth) +{ + unsigned int i; + + fwnode_handle_get(fwnode); + + for (i = 0; i < depth && fwnode; i++) + fwnode = fwnode_get_next_parent(fwnode); + + return fwnode; +} +EXPORT_SYMBOL_GPL(fwnode_get_nth_parent); + /** * fwnode_get_next_child_node - Return the next child node handle for a node * @fwnode: Firmware node to find the next child node for. diff --git a/include/linux/property.h b/include/linux/property.h index 87d795a1e2d6..ea27c5811e1b 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -83,6 +83,9 @@ struct fwnode_handle *fwnode_find_reference(const struct fwnode_handle *fwnode, struct fwnode_handle *fwnode_get_parent(const struct fwnode_handle *fwnode); struct fwnode_handle *fwnode_get_next_parent( struct fwnode_handle *fwnode); +unsigned int fwnode_count_parents(const struct fwnode_handle *fwn); +struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwn, + unsigned int depth); struct fwnode_handle *fwnode_get_next_child_node( const struct fwnode_handle *fwnode, struct fwnode_handle *child); struct fwnode_handle *fwnode_get_next_available_child_node( -- cgit v1.2.3-71-gd317 From bc0500c1e43d95cca5352d2345fb0769f314ba22 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Thu, 3 Oct 2019 15:32:12 +0300 Subject: device property: Add fwnode_get_name for returning the name of a node The fwnode framework did not have means to obtain the name of a node. Add that now, in form of the fwnode_get_name() function and a corresponding get_name fwnode op. OF and ACPI support is included. Signed-off-by: Sakari Ailus Acked-by: Rob Herring (for OF) Reviewed-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- drivers/acpi/property.c | 26 ++++++++++++++++++++++++++ drivers/base/property.c | 11 +++++++++++ drivers/base/swnode.c | 12 ++++++++++++ drivers/of/property.c | 6 ++++++ include/linux/fwnode.h | 2 ++ include/linux/property.h | 1 + 6 files changed, 58 insertions(+) (limited to 'include/linux') diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c index 3eacf474e1e3..a501c1c584b5 100644 --- a/drivers/acpi/property.c +++ b/drivers/acpi/property.c @@ -1317,6 +1317,31 @@ acpi_fwnode_get_reference_args(const struct fwnode_handle *fwnode, args_count, args); } +static const char *acpi_fwnode_get_name(const struct fwnode_handle *fwnode) +{ + const struct acpi_device *adev; + struct fwnode_handle *parent; + + /* Is this the root node? */ + parent = fwnode_get_parent(fwnode); + if (!parent) + return "\\"; + + fwnode_handle_put(parent); + + if (is_acpi_data_node(fwnode)) { + const struct acpi_data_node *dn = to_acpi_data_node(fwnode); + + return dn->name; + } + + adev = to_acpi_device_node(fwnode); + if (WARN_ON(!adev)) + return NULL; + + return acpi_device_bid(adev); +} + static struct fwnode_handle * acpi_fwnode_get_parent(struct fwnode_handle *fwnode) { @@ -1357,6 +1382,7 @@ acpi_fwnode_device_get_match_data(const struct fwnode_handle *fwnode, .get_parent = acpi_node_get_parent, \ .get_next_child_node = acpi_get_next_subnode, \ .get_named_child_node = acpi_fwnode_get_named_child_node, \ + .get_name = acpi_fwnode_get_name, \ .get_reference_args = acpi_fwnode_get_reference_args, \ .graph_get_next_endpoint = \ acpi_graph_get_next_endpoint, \ diff --git a/drivers/base/property.c b/drivers/base/property.c index f2e555e68b56..9b5ec88e72d8 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -556,6 +556,17 @@ int device_add_properties(struct device *dev, } EXPORT_SYMBOL_GPL(device_add_properties); +/** + * fwnode_get_name - Return the name of a node + * @fwnode: The firmware node + * + * Returns a pointer to the node name. + */ +const char *fwnode_get_name(const struct fwnode_handle *fwnode) +{ + return fwnode_call_ptr_op(fwnode, get_name); +} + /** * fwnode_get_parent - Return parent firwmare node * @fwnode: Firmware whose parent is retrieved diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c index 9cde143201f5..eacca6a6626b 100644 --- a/drivers/base/swnode.c +++ b/drivers/base/swnode.c @@ -515,6 +515,17 @@ static int software_node_read_string_array(const struct fwnode_handle *fwnode, propname, val, nval); } +static const char * +software_node_get_name(const struct fwnode_handle *fwnode) +{ + const struct swnode *swnode = to_swnode(fwnode); + + if (!swnode) + return "(null)"; + + return kobject_name(&swnode->kobj); +} + static struct fwnode_handle * software_node_get_parent(const struct fwnode_handle *fwnode) { @@ -615,6 +626,7 @@ static const struct fwnode_operations software_node_ops = { .property_present = software_node_property_present, .property_read_int_array = software_node_read_int_array, .property_read_string_array = software_node_read_string_array, + .get_name = software_node_get_name, .get_parent = software_node_get_parent, .get_next_child_node = software_node_get_next_child, .get_named_child_node = software_node_get_named_child_node, diff --git a/drivers/of/property.c b/drivers/of/property.c index d7fa75e31f22..5bed634551ea 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -872,6 +872,11 @@ of_fwnode_property_read_string_array(const struct fwnode_handle *fwnode, of_property_count_strings(node, propname); } +static const char *of_fwnode_get_name(const struct fwnode_handle *fwnode) +{ + return kbasename(to_of_node(fwnode)->full_name); +} + static struct fwnode_handle * of_fwnode_get_parent(const struct fwnode_handle *fwnode) { @@ -993,6 +998,7 @@ const struct fwnode_operations of_fwnode_ops = { .property_present = of_fwnode_property_present, .property_read_int_array = of_fwnode_property_read_int_array, .property_read_string_array = of_fwnode_property_read_string_array, + .get_name = of_fwnode_get_name, .get_parent = of_fwnode_get_parent, .get_next_child_node = of_fwnode_get_next_child_node, .get_named_child_node = of_fwnode_get_named_child_node, diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index ababd6bc82f3..2bbf55739a57 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -56,6 +56,7 @@ struct fwnode_reference_args { * otherwise. * @property_read_string_array: Read an array of string properties. Return zero * on success, a negative error code otherwise. + * @get_name: Return the name of an fwnode. * @get_parent: Return the parent of an fwnode. * @get_next_child_node: Return the next child node in an iteration. * @get_named_child_node: Return a child node with a given name. @@ -82,6 +83,7 @@ struct fwnode_operations { (*property_read_string_array)(const struct fwnode_handle *fwnode_handle, const char *propname, const char **val, size_t nval); + const char *(*get_name)(const struct fwnode_handle *fwnode); struct fwnode_handle *(*get_parent)(const struct fwnode_handle *fwnode); struct fwnode_handle * (*get_next_child_node)(const struct fwnode_handle *fwnode, diff --git a/include/linux/property.h b/include/linux/property.h index ea27c5811e1b..afa84c47bf16 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -80,6 +80,7 @@ struct fwnode_handle *fwnode_find_reference(const struct fwnode_handle *fwnode, const char *name, unsigned int index); +const char *fwnode_get_name(const struct fwnode_handle *fwnode); struct fwnode_handle *fwnode_get_parent(const struct fwnode_handle *fwnode); struct fwnode_handle *fwnode_get_next_parent( struct fwnode_handle *fwnode); -- cgit v1.2.3-71-gd317 From e7e242bccb209b5f73455b33928b8680cc6e3319 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Thu, 3 Oct 2019 15:32:13 +0300 Subject: device property: Add a function to obtain a node's prefix The prefix is used for printing purpose before a node, and it also works as a separator between two nodes. Signed-off-by: Sakari Ailus Acked-by: Rob Herring (for OF) Reviewed-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- drivers/acpi/property.c | 22 ++++++++++++++++++++++ drivers/base/property.c | 12 ++++++++++++ drivers/base/swnode.c | 22 ++++++++++++++++++++++ drivers/of/property.c | 10 ++++++++++ include/linux/fwnode.h | 2 ++ include/linux/property.h | 1 + 6 files changed, 69 insertions(+) (limited to 'include/linux') diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c index a501c1c584b5..e601c4511a8b 100644 --- a/drivers/acpi/property.c +++ b/drivers/acpi/property.c @@ -1342,6 +1342,27 @@ static const char *acpi_fwnode_get_name(const struct fwnode_handle *fwnode) return acpi_device_bid(adev); } +static const char * +acpi_fwnode_get_name_prefix(const struct fwnode_handle *fwnode) +{ + struct fwnode_handle *parent; + + /* Is this the root node? */ + parent = fwnode_get_parent(fwnode); + if (!parent) + return ""; + + /* Is this 2nd node from the root? */ + parent = fwnode_get_next_parent(parent); + if (!parent) + return ""; + + fwnode_handle_put(parent); + + /* ACPI device or data node. */ + return "."; +} + static struct fwnode_handle * acpi_fwnode_get_parent(struct fwnode_handle *fwnode) { @@ -1383,6 +1404,7 @@ acpi_fwnode_device_get_match_data(const struct fwnode_handle *fwnode, .get_next_child_node = acpi_get_next_subnode, \ .get_named_child_node = acpi_fwnode_get_named_child_node, \ .get_name = acpi_fwnode_get_name, \ + .get_name_prefix = acpi_fwnode_get_name_prefix, \ .get_reference_args = acpi_fwnode_get_reference_args, \ .graph_get_next_endpoint = \ acpi_graph_get_next_endpoint, \ diff --git a/drivers/base/property.c b/drivers/base/property.c index 9b5ec88e72d8..511f6d7acdfe 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -567,6 +567,18 @@ const char *fwnode_get_name(const struct fwnode_handle *fwnode) return fwnode_call_ptr_op(fwnode, get_name); } +/** + * fwnode_get_name_prefix - Return the prefix of node for printing purposes + * @fwnode: The firmware node + * + * Returns the prefix of a node, intended to be printed right before the node. + * The prefix works also as a separator between the nodes. + */ +const char *fwnode_get_name_prefix(const struct fwnode_handle *fwnode) +{ + return fwnode_call_ptr_op(fwnode, get_name_prefix); +} + /** * fwnode_get_parent - Return parent firwmare node * @fwnode: Firmware whose parent is retrieved diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c index eacca6a6626b..12ca439bab30 100644 --- a/drivers/base/swnode.c +++ b/drivers/base/swnode.c @@ -526,6 +526,27 @@ software_node_get_name(const struct fwnode_handle *fwnode) return kobject_name(&swnode->kobj); } +static const char * +software_node_get_name_prefix(const struct fwnode_handle *fwnode) +{ + struct fwnode_handle *parent; + const char *prefix; + + parent = fwnode_get_parent(fwnode); + if (!parent) + return ""; + + /* Figure out the prefix from the parents. */ + while (is_software_node(parent)) + parent = fwnode_get_next_parent(parent); + + prefix = fwnode_get_name_prefix(parent); + fwnode_handle_put(parent); + + /* Guess something if prefix was NULL. */ + return prefix ?: "/"; +} + static struct fwnode_handle * software_node_get_parent(const struct fwnode_handle *fwnode) { @@ -627,6 +648,7 @@ static const struct fwnode_operations software_node_ops = { .property_read_int_array = software_node_read_int_array, .property_read_string_array = software_node_read_string_array, .get_name = software_node_get_name, + .get_name_prefix = software_node_get_name_prefix, .get_parent = software_node_get_parent, .get_next_child_node = software_node_get_next_child, .get_named_child_node = software_node_get_named_child_node, diff --git a/drivers/of/property.c b/drivers/of/property.c index 5bed634551ea..e8202f61a5d9 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -877,6 +877,15 @@ static const char *of_fwnode_get_name(const struct fwnode_handle *fwnode) return kbasename(to_of_node(fwnode)->full_name); } +static const char *of_fwnode_get_name_prefix(const struct fwnode_handle *fwnode) +{ + /* Root needs no prefix here (its name is "/"). */ + if (!to_of_node(fwnode)->parent) + return ""; + + return "/"; +} + static struct fwnode_handle * of_fwnode_get_parent(const struct fwnode_handle *fwnode) { @@ -999,6 +1008,7 @@ const struct fwnode_operations of_fwnode_ops = { .property_read_int_array = of_fwnode_property_read_int_array, .property_read_string_array = of_fwnode_property_read_string_array, .get_name = of_fwnode_get_name, + .get_name_prefix = of_fwnode_get_name_prefix, .get_parent = of_fwnode_get_parent, .get_next_child_node = of_fwnode_get_next_child_node, .get_named_child_node = of_fwnode_get_named_child_node, diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 2bbf55739a57..a5673c4674cf 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -57,6 +57,7 @@ struct fwnode_reference_args { * @property_read_string_array: Read an array of string properties. Return zero * on success, a negative error code otherwise. * @get_name: Return the name of an fwnode. + * @get_name_prefix: Get a prefix for a node (for printing purposes). * @get_parent: Return the parent of an fwnode. * @get_next_child_node: Return the next child node in an iteration. * @get_named_child_node: Return a child node with a given name. @@ -84,6 +85,7 @@ struct fwnode_operations { const char *propname, const char **val, size_t nval); const char *(*get_name)(const struct fwnode_handle *fwnode); + const char *(*get_name_prefix)(const struct fwnode_handle *fwnode); struct fwnode_handle *(*get_parent)(const struct fwnode_handle *fwnode); struct fwnode_handle * (*get_next_child_node)(const struct fwnode_handle *fwnode, diff --git a/include/linux/property.h b/include/linux/property.h index afa84c47bf16..054661109661 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -81,6 +81,7 @@ struct fwnode_handle *fwnode_find_reference(const struct fwnode_handle *fwnode, unsigned int index); const char *fwnode_get_name(const struct fwnode_handle *fwnode); +const char *fwnode_get_name_prefix(const struct fwnode_handle *fwnode); struct fwnode_handle *fwnode_get_parent(const struct fwnode_handle *fwnode); struct fwnode_handle *fwnode_get_next_parent( struct fwnode_handle *fwnode); -- cgit v1.2.3-71-gd317 From 8ed61d36050c57d9eba09511f53d683fd63b04d1 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Tue, 8 Oct 2019 16:26:06 +0300 Subject: device property: Fix the description of struct fwnode_operations Adding description for the device_is_available member which was missing, and fixing the description of the member property_read_int_array. Signed-off-by: Heikki Krogerus Reviewed-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- include/linux/fwnode.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index a5673c4674cf..9d9dc444d787 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -49,11 +49,11 @@ struct fwnode_reference_args { * struct fwnode_operations - Operations for fwnode interface * @get: Get a reference to an fwnode. * @put: Put a reference to an fwnode. + * @device_is_available: Return true if the device is available. * @device_get_match_data: Return the device driver match data. * @property_present: Return true if a property is present. - * @property_read_integer_array: Read an array of integer properties. Return - * zero on success, a negative error code - * otherwise. + * @property_read_int_array: Read an array of integer properties. Return zero on + * success, a negative error code otherwise. * @property_read_string_array: Read an array of string properties. Return zero * on success, a negative error code otherwise. * @get_name: Return the name of an fwnode. -- cgit v1.2.3-71-gd317 From 84a081f60db63aaae3665118203506aa09a7f94f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 11 Oct 2019 11:11:40 -0700 Subject: bpf: Align struct bpf_prog_stats Do not risk spanning these small structures on two cache lines. Signed-off-by: Eric Dumazet Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20191011181140.2898-1-edumazet@google.com --- include/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5b9d22338606..282e28bf41ec 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -363,7 +363,7 @@ struct bpf_prog_stats { u64 cnt; u64 nsecs; struct u64_stats_sync syncp; -}; +} __aligned(2 * sizeof(u64)); struct bpf_prog_aux { atomic_t refcnt; -- cgit v1.2.3-71-gd317 From 6b7fe77c334ae59fed9500140e08f4f896b36871 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 9 Aug 2019 14:22:40 +0100 Subject: arm/arm64: smccc/psci: add arm_smccc_1_1_get_conduit() SMCCC callers are currently amassing a collection of enums for the SMCCC conduit, and are having to dig into the PSCI driver's internals in order to figure out what to do. Let's clean this up, with common SMCCC_CONDUIT_* definitions, and an arm_smccc_1_1_get_conduit() helper that abstracts the PSCI driver's internal state. We can kill off the PSCI_CONDUIT_* definitions once we've migrated users over to the new interface. Signed-off-by: Mark Rutland Acked-by: Lorenzo Pieralisi Acked-by: Will Deacon Signed-off-by: Catalin Marinas --- drivers/firmware/psci/psci.c | 15 +++++++++++++++ include/linux/arm-smccc.h | 16 ++++++++++++++++ 2 files changed, 31 insertions(+) (limited to 'include/linux') diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c index 84f4ff351c62..eb797081d159 100644 --- a/drivers/firmware/psci/psci.c +++ b/drivers/firmware/psci/psci.c @@ -57,6 +57,21 @@ struct psci_operations psci_ops = { .smccc_version = SMCCC_VERSION_1_0, }; +enum arm_smccc_conduit arm_smccc_1_1_get_conduit(void) +{ + if (psci_ops.smccc_version < SMCCC_VERSION_1_1) + return SMCCC_CONDUIT_NONE; + + switch (psci_ops.conduit) { + case PSCI_CONDUIT_SMC: + return SMCCC_CONDUIT_SMC; + case PSCI_CONDUIT_HVC: + return SMCCC_CONDUIT_HVC; + default: + return SMCCC_CONDUIT_NONE; + } +} + typedef unsigned long (psci_fn)(unsigned long, unsigned long, unsigned long, unsigned long); static psci_fn *invoke_psci_fn; diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 080012a6f025..df01a8579034 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -80,6 +80,22 @@ #include #include + +enum arm_smccc_conduit { + SMCCC_CONDUIT_NONE, + SMCCC_CONDUIT_SMC, + SMCCC_CONDUIT_HVC, +}; + +/** + * arm_smccc_1_1_get_conduit() + * + * Returns the conduit to be used for SMCCCv1.1 or later. + * + * When SMCCCv1.1 is not present, returns SMCCC_CONDUIT_NONE. + */ +enum arm_smccc_conduit arm_smccc_1_1_get_conduit(void); + /** * struct arm_smccc_res - Result from SMC/HVC call * @a0-a3 result values from registers 0 to 3 -- cgit v1.2.3-71-gd317 From a5520eac4d2dafb7a48c1b0f1c486afcebd6fe0d Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 9 Aug 2019 14:22:43 +0100 Subject: firmware/psci: use common SMCCC_CONDUIT_* Now that we have common SMCCC_CONDUIT_* definitions, migrate the PSCI code over to them, and kill off the old PSCI_CONDUIT_* definitions. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Acked-by: Lorenzo Pieralisi Acked-by: Will Deacon Signed-off-by: Catalin Marinas --- drivers/firmware/psci/psci.c | 25 +++++++++---------------- include/linux/psci.h | 9 ++------- 2 files changed, 11 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c index eb797081d159..b3b6c15e7b36 100644 --- a/drivers/firmware/psci/psci.c +++ b/drivers/firmware/psci/psci.c @@ -53,7 +53,7 @@ bool psci_tos_resident_on(int cpu) } struct psci_operations psci_ops = { - .conduit = PSCI_CONDUIT_NONE, + .conduit = SMCCC_CONDUIT_NONE, .smccc_version = SMCCC_VERSION_1_0, }; @@ -62,14 +62,7 @@ enum arm_smccc_conduit arm_smccc_1_1_get_conduit(void) if (psci_ops.smccc_version < SMCCC_VERSION_1_1) return SMCCC_CONDUIT_NONE; - switch (psci_ops.conduit) { - case PSCI_CONDUIT_SMC: - return SMCCC_CONDUIT_SMC; - case PSCI_CONDUIT_HVC: - return SMCCC_CONDUIT_HVC; - default: - return SMCCC_CONDUIT_NONE; - } + return psci_ops.conduit; } typedef unsigned long (psci_fn)(unsigned long, unsigned long, @@ -227,13 +220,13 @@ static unsigned long psci_migrate_info_up_cpu(void) 0, 0, 0); } -static void set_conduit(enum psci_conduit conduit) +static void set_conduit(enum arm_smccc_conduit conduit) { switch (conduit) { - case PSCI_CONDUIT_HVC: + case SMCCC_CONDUIT_HVC: invoke_psci_fn = __invoke_psci_fn_hvc; break; - case PSCI_CONDUIT_SMC: + case SMCCC_CONDUIT_SMC: invoke_psci_fn = __invoke_psci_fn_smc; break; default: @@ -255,9 +248,9 @@ static int get_set_conduit_method(struct device_node *np) } if (!strcmp("hvc", method)) { - set_conduit(PSCI_CONDUIT_HVC); + set_conduit(SMCCC_CONDUIT_HVC); } else if (!strcmp("smc", method)) { - set_conduit(PSCI_CONDUIT_SMC); + set_conduit(SMCCC_CONDUIT_SMC); } else { pr_warn("invalid \"method\" property: %s\n", method); return -EINVAL; @@ -598,9 +591,9 @@ int __init psci_acpi_init(void) pr_info("probing for conduit method from ACPI.\n"); if (acpi_psci_use_hvc()) - set_conduit(PSCI_CONDUIT_HVC); + set_conduit(SMCCC_CONDUIT_HVC); else - set_conduit(PSCI_CONDUIT_SMC); + set_conduit(SMCCC_CONDUIT_SMC); return psci_probe(); } diff --git a/include/linux/psci.h b/include/linux/psci.h index e2bacc6fd2f2..ebe0a881d13d 100644 --- a/include/linux/psci.h +++ b/include/linux/psci.h @@ -7,6 +7,7 @@ #ifndef __LINUX_PSCI_H #define __LINUX_PSCI_H +#include #include #include @@ -18,12 +19,6 @@ bool psci_tos_resident_on(int cpu); int psci_cpu_suspend_enter(u32 state); bool psci_power_state_is_valid(u32 state); -enum psci_conduit { - PSCI_CONDUIT_NONE, - PSCI_CONDUIT_SMC, - PSCI_CONDUIT_HVC, -}; - enum smccc_version { SMCCC_VERSION_1_0, SMCCC_VERSION_1_1, @@ -38,7 +33,7 @@ struct psci_operations { int (*affinity_info)(unsigned long target_affinity, unsigned long lowest_affinity_level); int (*migrate_info_type)(void); - enum psci_conduit conduit; + enum arm_smccc_conduit conduit; enum smccc_version smccc_version; }; -- cgit v1.2.3-71-gd317 From e6ea46511b1ae8c4491904c79411fcd29139af14 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 9 Aug 2019 14:22:44 +0100 Subject: firmware: arm_sdei: use common SMCCC_CONDUIT_* Now that we have common definitions for SMCCC conduits, move the SDEI code over to them, and remove the SDEI-specific definitions. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Acked-by: Lorenzo Pieralisi Acked-by: James Morse Acked-by: Will Deacon Signed-off-by: Catalin Marinas --- arch/arm64/kernel/sdei.c | 3 ++- drivers/firmware/arm_sdei.c | 12 ++++++------ include/linux/arm_sdei.h | 6 ------ 3 files changed, 8 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c index ea94cf8f9dc6..d6259dac62b6 100644 --- a/arch/arm64/kernel/sdei.c +++ b/arch/arm64/kernel/sdei.c @@ -2,6 +2,7 @@ // Copyright (C) 2017 Arm Ltd. #define pr_fmt(fmt) "sdei: " fmt +#include #include #include #include @@ -161,7 +162,7 @@ unsigned long sdei_arch_get_entry_point(int conduit) return 0; } - sdei_exit_mode = (conduit == CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC; + sdei_exit_mode = (conduit == SMCCC_CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC; #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 if (arm64_kernel_unmapped_at_el0()) { diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c index 9cd70d1a5622..a479023fa036 100644 --- a/drivers/firmware/arm_sdei.c +++ b/drivers/firmware/arm_sdei.c @@ -967,29 +967,29 @@ static int sdei_get_conduit(struct platform_device *pdev) if (np) { if (of_property_read_string(np, "method", &method)) { pr_warn("missing \"method\" property\n"); - return CONDUIT_INVALID; + return SMCCC_CONDUIT_NONE; } if (!strcmp("hvc", method)) { sdei_firmware_call = &sdei_smccc_hvc; - return CONDUIT_HVC; + return SMCCC_CONDUIT_HVC; } else if (!strcmp("smc", method)) { sdei_firmware_call = &sdei_smccc_smc; - return CONDUIT_SMC; + return SMCCC_CONDUIT_SMC; } pr_warn("invalid \"method\" property: %s\n", method); } else if (IS_ENABLED(CONFIG_ACPI) && !acpi_disabled) { if (acpi_psci_use_hvc()) { sdei_firmware_call = &sdei_smccc_hvc; - return CONDUIT_HVC; + return SMCCC_CONDUIT_HVC; } else { sdei_firmware_call = &sdei_smccc_smc; - return CONDUIT_SMC; + return SMCCC_CONDUIT_SMC; } } - return CONDUIT_INVALID; + return SMCCC_CONDUIT_NONE; } static int sdei_probe(struct platform_device *pdev) diff --git a/include/linux/arm_sdei.h b/include/linux/arm_sdei.h index 3305ea7f9dc7..0a241c5c911d 100644 --- a/include/linux/arm_sdei.h +++ b/include/linux/arm_sdei.h @@ -5,12 +5,6 @@ #include -enum sdei_conduit_types { - CONDUIT_INVALID = 0, - CONDUIT_SMC, - CONDUIT_HVC, -}; - #include #ifdef CONFIG_ARM_SDE_INTERFACE -- cgit v1.2.3-71-gd317 From 734f9246e791d8da278957b2c326d7709b2a97c0 Mon Sep 17 00:00:00 2001 From: Nicolas Saenz Julienne Date: Wed, 11 Sep 2019 20:25:46 +0200 Subject: mm: refresh ZONE_DMA and ZONE_DMA32 comments in 'enum zone_type' These zones usage has evolved with time and the comments were outdated. This joins both ZONE_DMA and ZONE_DMA32 explanation and gives up to date examples on how they are used on different architectures. Signed-off-by: Nicolas Saenz Julienne Reviewed-by: Christoph Hellwig Reviewed-by: Catalin Marinas Signed-off-by: Catalin Marinas --- include/linux/mmzone.h | 45 ++++++++++++++++++++++++++------------------- 1 file changed, 26 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index bda20282746b..b0a36d1580b6 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -359,33 +359,40 @@ struct per_cpu_nodestat { #endif /* !__GENERATING_BOUNDS.H */ enum zone_type { -#ifdef CONFIG_ZONE_DMA /* - * ZONE_DMA is used when there are devices that are not able - * to do DMA to all of addressable memory (ZONE_NORMAL). Then we - * carve out the portion of memory that is needed for these devices. - * The range is arch specific. + * ZONE_DMA and ZONE_DMA32 are used when there are peripherals not able + * to DMA to all of the addressable memory (ZONE_NORMAL). + * On architectures where this area covers the whole 32 bit address + * space ZONE_DMA32 is used. ZONE_DMA is left for the ones with smaller + * DMA addressing constraints. This distinction is important as a 32bit + * DMA mask is assumed when ZONE_DMA32 is defined. Some 64-bit + * platforms may need both zones as they support peripherals with + * different DMA addressing limitations. + * + * Some examples: + * + * - i386 and x86_64 have a fixed 16M ZONE_DMA and ZONE_DMA32 for the + * rest of the lower 4G. + * + * - arm only uses ZONE_DMA, the size, up to 4G, may vary depending on + * the specific device. + * + * - arm64 has a fixed 1G ZONE_DMA and ZONE_DMA32 for the rest of the + * lower 4G. * - * Some examples + * - powerpc only uses ZONE_DMA, the size, up to 2G, may vary + * depending on the specific device. * - * Architecture Limit - * --------------------------- - * parisc, ia64, sparc <4G - * s390, powerpc <2G - * arm Various - * alpha Unlimited or 0-16MB. + * - s390 uses ZONE_DMA fixed to the lower 2G. * - * i386, x86_64 and multiple other arches - * <16M. + * - ia64 and riscv only use ZONE_DMA32. + * + * - parisc uses neither. */ +#ifdef CONFIG_ZONE_DMA ZONE_DMA, #endif #ifdef CONFIG_ZONE_DMA32 - /* - * x86_64 needs two ZONE_DMAs because it supports devices that are - * only able to do DMA to the lower 16M but also 32 bit devices that - * can only do DMA areas below 4G. - */ ZONE_DMA32, #endif /* -- cgit v1.2.3-71-gd317 From 9655ac4aca20d654769b8f0d6a5be34b7ce7bad1 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 11 Oct 2019 15:29:24 +0200 Subject: debugfs: remove return value of debugfs_create_u8() No one checks the return value of debugfs_create_u8(), as it's not needed, so make the return value void, so that no one tries to do so in the future. Signed-off-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20191011132931.1186197-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- Documentation/filesystems/debugfs.txt | 4 ++-- fs/debugfs/file.c | 15 +++------------ include/linux/debugfs.h | 12 ++++-------- 3 files changed, 9 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/debugfs.txt b/Documentation/filesystems/debugfs.txt index 9e27c843d00e..c146f18eb8ac 100644 --- a/Documentation/filesystems/debugfs.txt +++ b/Documentation/filesystems/debugfs.txt @@ -68,8 +68,8 @@ actually necessary; the debugfs code provides a number of helper functions for simple situations. Files containing a single integer value can be created with any of: - struct dentry *debugfs_create_u8(const char *name, umode_t mode, - struct dentry *parent, u8 *value); + void debugfs_create_u8(const char *name, umode_t mode, + struct dentry *parent, u8 *value); struct dentry *debugfs_create_u16(const char *name, umode_t mode, struct dentry *parent, u16 *value); struct dentry *debugfs_create_u32(const char *name, umode_t mode, diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 87846aad594b..2d5d9a0a6f57 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -420,20 +420,11 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_u8_wo, NULL, debugfs_u8_set, "%llu\n"); * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. - * - * This function will return a pointer to a dentry if it succeeds. This - * pointer must be passed to the debugfs_remove() function when the file is - * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be - * returned. - * - * If debugfs is not enabled in the kernel, the value %ERR_PTR(-ENODEV) will - * be returned. */ -struct dentry *debugfs_create_u8(const char *name, umode_t mode, - struct dentry *parent, u8 *value) +void debugfs_create_u8(const char *name, umode_t mode, struct dentry *parent, + u8 *value) { - return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u8, + debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u8, &fops_u8_ro, &fops_u8_wo); } EXPORT_SYMBOL_GPL(debugfs_create_u8); diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 58424eb3b329..8e071f599245 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -97,8 +97,8 @@ ssize_t debugfs_attr_write(struct file *file, const char __user *buf, struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, struct dentry *new_dir, const char *new_name); -struct dentry *debugfs_create_u8(const char *name, umode_t mode, - struct dentry *parent, u8 *value); +void debugfs_create_u8(const char *name, umode_t mode, struct dentry *parent, + u8 *value); struct dentry *debugfs_create_u16(const char *name, umode_t mode, struct dentry *parent, u16 *value); struct dentry *debugfs_create_u32(const char *name, umode_t mode, @@ -244,12 +244,8 @@ static inline struct dentry *debugfs_rename(struct dentry *old_dir, struct dentr return ERR_PTR(-ENODEV); } -static inline struct dentry *debugfs_create_u8(const char *name, umode_t mode, - struct dentry *parent, - u8 *value) -{ - return ERR_PTR(-ENODEV); -} +static inline void debugfs_create_u8(const char *name, umode_t mode, + struct dentry *parent, u8 *value) { } static inline struct dentry *debugfs_create_u16(const char *name, umode_t mode, struct dentry *parent, -- cgit v1.2.3-71-gd317 From 313f5dbba41d905d59c820bb2d91ee6c661aff99 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 11 Oct 2019 15:29:25 +0200 Subject: debugfs: remove return value of debugfs_create_u16() No one checks the return value of debugfs_create_u16(), as it's not needed, so make the return value void, so that no one tries to do so in the future. Signed-off-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20191011132931.1186197-2-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- Documentation/filesystems/debugfs.txt | 4 ++-- fs/debugfs/file.c | 15 +++------------ include/linux/debugfs.h | 12 ++++-------- 3 files changed, 9 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/debugfs.txt b/Documentation/filesystems/debugfs.txt index c146f18eb8ac..6abcf41fbd37 100644 --- a/Documentation/filesystems/debugfs.txt +++ b/Documentation/filesystems/debugfs.txt @@ -70,8 +70,8 @@ created with any of: void debugfs_create_u8(const char *name, umode_t mode, struct dentry *parent, u8 *value); - struct dentry *debugfs_create_u16(const char *name, umode_t mode, - struct dentry *parent, u16 *value); + void debugfs_create_u16(const char *name, umode_t mode, + struct dentry *parent, u16 *value); struct dentry *debugfs_create_u32(const char *name, umode_t mode, struct dentry *parent, u32 *value); struct dentry *debugfs_create_u64(const char *name, umode_t mode, diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 2d5d9a0a6f57..8091a7ef3589 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -456,20 +456,11 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_u16_wo, NULL, debugfs_u16_set, "%llu\n"); * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. - * - * This function will return a pointer to a dentry if it succeeds. This - * pointer must be passed to the debugfs_remove() function when the file is - * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be - * returned. - * - * If debugfs is not enabled in the kernel, the value %ERR_PTR(-ENODEV) will - * be returned. */ -struct dentry *debugfs_create_u16(const char *name, umode_t mode, - struct dentry *parent, u16 *value) +void debugfs_create_u16(const char *name, umode_t mode, struct dentry *parent, + u16 *value) { - return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u16, + debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u16, &fops_u16_ro, &fops_u16_wo); } EXPORT_SYMBOL_GPL(debugfs_create_u16); diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 8e071f599245..c83a33a76b6c 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -99,8 +99,8 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, void debugfs_create_u8(const char *name, umode_t mode, struct dentry *parent, u8 *value); -struct dentry *debugfs_create_u16(const char *name, umode_t mode, - struct dentry *parent, u16 *value); +void debugfs_create_u16(const char *name, umode_t mode, struct dentry *parent, + u16 *value); struct dentry *debugfs_create_u32(const char *name, umode_t mode, struct dentry *parent, u32 *value); struct dentry *debugfs_create_u64(const char *name, umode_t mode, @@ -247,12 +247,8 @@ static inline struct dentry *debugfs_rename(struct dentry *old_dir, struct dentr static inline void debugfs_create_u8(const char *name, umode_t mode, struct dentry *parent, u8 *value) { } -static inline struct dentry *debugfs_create_u16(const char *name, umode_t mode, - struct dentry *parent, - u16 *value) -{ - return ERR_PTR(-ENODEV); -} +static inline void debugfs_create_u16(const char *name, umode_t mode, + struct dentry *parent, u16 *value) { } static inline struct dentry *debugfs_create_u32(const char *name, umode_t mode, struct dentry *parent, -- cgit v1.2.3-71-gd317 From ad26221fb9e64e69e32a2caf58dba067ca4e815e Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 11 Oct 2019 15:29:26 +0200 Subject: debugfs: remove return value of debugfs_create_u64() No one checks the return value of debugfs_create_u64(), as it's not needed, so make the return value void, so that no one tries to do so in the future. Signed-off-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20191011132931.1186197-3-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- Documentation/filesystems/debugfs.txt | 4 ++-- fs/debugfs/file.c | 15 +++------------ include/linux/debugfs.h | 12 ++++-------- 3 files changed, 9 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/debugfs.txt b/Documentation/filesystems/debugfs.txt index 6abcf41fbd37..1b299ae4904d 100644 --- a/Documentation/filesystems/debugfs.txt +++ b/Documentation/filesystems/debugfs.txt @@ -74,8 +74,8 @@ created with any of: struct dentry *parent, u16 *value); struct dentry *debugfs_create_u32(const char *name, umode_t mode, struct dentry *parent, u32 *value); - struct dentry *debugfs_create_u64(const char *name, umode_t mode, - struct dentry *parent, u64 *value); + void debugfs_create_u64(const char *name, umode_t mode, + struct dentry *parent, u64 *value); These files support both reading and writing the given value; if a specific file should not be written to, simply set the mode bits accordingly. The diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 8091a7ef3589..4c8912d7d34c 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -538,20 +538,11 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n"); * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. - * - * This function will return a pointer to a dentry if it succeeds. This - * pointer must be passed to the debugfs_remove() function when the file is - * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be - * returned. - * - * If debugfs is not enabled in the kernel, the value %ERR_PTR(-ENODEV) will - * be returned. */ -struct dentry *debugfs_create_u64(const char *name, umode_t mode, - struct dentry *parent, u64 *value) +void debugfs_create_u64(const char *name, umode_t mode, struct dentry *parent, + u64 *value) { - return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u64, + debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u64, &fops_u64_ro, &fops_u64_wo); } EXPORT_SYMBOL_GPL(debugfs_create_u64); diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index c83a33a76b6c..b3bed4d61733 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -103,8 +103,8 @@ void debugfs_create_u16(const char *name, umode_t mode, struct dentry *parent, u16 *value); struct dentry *debugfs_create_u32(const char *name, umode_t mode, struct dentry *parent, u32 *value); -struct dentry *debugfs_create_u64(const char *name, umode_t mode, - struct dentry *parent, u64 *value); +void debugfs_create_u64(const char *name, umode_t mode, struct dentry *parent, + u64 *value); struct dentry *debugfs_create_ulong(const char *name, umode_t mode, struct dentry *parent, unsigned long *value); struct dentry *debugfs_create_x8(const char *name, umode_t mode, @@ -257,12 +257,8 @@ static inline struct dentry *debugfs_create_u32(const char *name, umode_t mode, return ERR_PTR(-ENODEV); } -static inline struct dentry *debugfs_create_u64(const char *name, umode_t mode, - struct dentry *parent, - u64 *value) -{ - return ERR_PTR(-ENODEV); -} +static inline void debugfs_create_u64(const char *name, umode_t mode, + struct dentry *parent, u64 *value) { } static inline struct dentry *debugfs_create_ulong(const char *name, umode_t mode, -- cgit v1.2.3-71-gd317 From 8e5802635f0f9f7329ec8ffdec15479946c99fb1 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 11 Oct 2019 15:29:27 +0200 Subject: debugfs: remove return value of debugfs_create_size_t() No one checks the return value of debugfs_create_size_t(), as it's not needed, so make the return value void, so that no one tries to do so in the future. Signed-off-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20191011132931.1186197-4-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- Documentation/filesystems/debugfs.txt | 5 ++--- fs/debugfs/file.c | 9 ++++----- include/linux/debugfs.h | 13 +++++-------- 3 files changed, 11 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/debugfs.txt b/Documentation/filesystems/debugfs.txt index 1b299ae4904d..55a5da08c71c 100644 --- a/Documentation/filesystems/debugfs.txt +++ b/Documentation/filesystems/debugfs.txt @@ -96,9 +96,8 @@ value to be exported. Some types can have different widths on different architectures, though, complicating the situation somewhat. There is a function meant to help out in one special case: - struct dentry *debugfs_create_size_t(const char *name, umode_t mode, - struct dentry *parent, - size_t *value); + void debugfs_create_size_t(const char *name, umode_t mode, + struct dentry *parent, size_t *value); As might be expected, this function will create a debugfs file to represent a variable of type size_t. diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 4c8912d7d34c..dfeda13023b3 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -721,12 +721,11 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_size_t_wo, NULL, debugfs_size_t_set, "%llu\n"); * @value: a pointer to the variable that the file should read to and write * from. */ -struct dentry *debugfs_create_size_t(const char *name, umode_t mode, - struct dentry *parent, size_t *value) +void debugfs_create_size_t(const char *name, umode_t mode, + struct dentry *parent, size_t *value) { - return debugfs_create_mode_unsafe(name, mode, parent, value, - &fops_size_t, &fops_size_t_ro, - &fops_size_t_wo); + debugfs_create_mode_unsafe(name, mode, parent, value, &fops_size_t, + &fops_size_t_ro, &fops_size_t_wo); } EXPORT_SYMBOL_GPL(debugfs_create_size_t); diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index b3bed4d61733..1d859bc657bd 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -115,8 +115,8 @@ struct dentry *debugfs_create_x32(const char *name, umode_t mode, struct dentry *parent, u32 *value); struct dentry *debugfs_create_x64(const char *name, umode_t mode, struct dentry *parent, u64 *value); -struct dentry *debugfs_create_size_t(const char *name, umode_t mode, - struct dentry *parent, size_t *value); +void debugfs_create_size_t(const char *name, umode_t mode, + struct dentry *parent, size_t *value); struct dentry *debugfs_create_atomic_t(const char *name, umode_t mode, struct dentry *parent, atomic_t *value); struct dentry *debugfs_create_bool(const char *name, umode_t mode, @@ -296,12 +296,9 @@ static inline struct dentry *debugfs_create_x64(const char *name, umode_t mode, return ERR_PTR(-ENODEV); } -static inline struct dentry *debugfs_create_size_t(const char *name, umode_t mode, - struct dentry *parent, - size_t *value) -{ - return ERR_PTR(-ENODEV); -} +static inline void debugfs_create_size_t(const char *name, umode_t mode, + struct dentry *parent, size_t *value) +{ } static inline struct dentry *debugfs_create_atomic_t(const char *name, umode_t mode, struct dentry *parent, atomic_t *value) -- cgit v1.2.3-71-gd317 From c9c13ba428ef90a9b408a6cdf874e14ab5754516 Mon Sep 17 00:00:00 2001 From: Denis Efremov Date: Sat, 28 Sep 2019 02:43:08 +0300 Subject: PCI: Add PCI_STD_NUM_BARS for the number of standard BARs Code that iterates over all standard PCI BARs typically uses PCI_STD_RESOURCE_END. However, that requires the unusual test "i <= PCI_STD_RESOURCE_END" rather than something the typical "i < PCI_STD_NUM_BARS". Add a definition for PCI_STD_NUM_BARS and change loops to use the more idiomatic C style to help avoid fencepost errors. Link: https://lore.kernel.org/r/20190927234026.23342-1-efremov@linux.com Link: https://lore.kernel.org/r/20190927234308.23935-1-efremov@linux.com Link: https://lore.kernel.org/r/20190916204158.6889-3-efremov@linux.com Signed-off-by: Denis Efremov Signed-off-by: Bjorn Helgaas Acked-by: Sebastian Ott # arch/s390/ Acked-by: Bartlomiej Zolnierkiewicz # video/fbdev/ Acked-by: Gustavo Pimentel # pci/controller/dwc/ Acked-by: Jack Wang # scsi/pm8001/ Acked-by: Martin K. Petersen # scsi/pm8001/ Acked-by: Ulf Hansson # memstick/ --- arch/alpha/kernel/pci-sysfs.c | 8 +++--- arch/s390/include/asm/pci.h | 5 +--- arch/s390/include/asm/pci_clp.h | 6 ++--- arch/s390/pci/pci.c | 16 ++++++------ arch/s390/pci/pci_clp.c | 6 ++--- arch/x86/pci/common.c | 2 +- arch/x86/pci/intel_mid_pci.c | 2 +- drivers/ata/pata_atp867x.c | 2 +- drivers/ata/sata_nv.c | 2 +- drivers/memstick/host/jmb38x_ms.c | 2 +- drivers/misc/pci_endpoint_test.c | 8 +++--- drivers/net/ethernet/intel/e1000/e1000.h | 1 - drivers/net/ethernet/intel/e1000/e1000_main.c | 2 +- drivers/net/ethernet/intel/ixgb/ixgb.h | 1 - drivers/net/ethernet/intel/ixgb/ixgb_main.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c | 4 +-- drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c | 2 +- drivers/pci/controller/dwc/pci-dra7xx.c | 2 +- drivers/pci/controller/dwc/pci-layerscape-ep.c | 2 +- drivers/pci/controller/dwc/pcie-artpec6.c | 2 +- drivers/pci/controller/dwc/pcie-designware-plat.c | 2 +- drivers/pci/controller/dwc/pcie-designware.h | 2 +- drivers/pci/controller/pci-hyperv.c | 10 +++---- drivers/pci/endpoint/functions/pci-epf-test.c | 10 +++---- drivers/pci/pci-sysfs.c | 4 +-- drivers/pci/pci.c | 13 ++++----- drivers/pci/proc.c | 4 +-- drivers/pci/quirks.c | 4 +-- drivers/rapidio/devices/tsi721.c | 2 +- drivers/scsi/pm8001/pm8001_hwi.c | 2 +- drivers/scsi/pm8001/pm8001_init.c | 2 +- drivers/staging/gasket/gasket_constants.h | 3 --- drivers/staging/gasket/gasket_core.c | 12 ++++----- drivers/staging/gasket/gasket_core.h | 4 +-- drivers/tty/serial/8250/8250_pci.c | 8 +++--- drivers/usb/core/hcd-pci.c | 2 +- drivers/usb/host/pci-quirks.c | 2 +- drivers/vfio/pci/vfio_pci.c | 11 +++++--- drivers/vfio/pci/vfio_pci_config.c | 32 ++++++++++++----------- drivers/vfio/pci/vfio_pci_private.h | 4 +-- drivers/video/fbdev/core/fbmem.c | 4 +-- drivers/video/fbdev/efifb.c | 2 +- include/linux/pci-epc.h | 2 +- include/linux/pci.h | 2 +- include/uapi/linux/pci_regs.h | 1 + lib/devres.c | 2 +- 46 files changed, 110 insertions(+), 113 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/kernel/pci-sysfs.c b/arch/alpha/kernel/pci-sysfs.c index f94c732fedeb..0021580d79ad 100644 --- a/arch/alpha/kernel/pci-sysfs.c +++ b/arch/alpha/kernel/pci-sysfs.c @@ -71,10 +71,10 @@ static int pci_mmap_resource(struct kobject *kobj, struct pci_bus_region bar; int i; - for (i = 0; i < PCI_ROM_RESOURCE; i++) + for (i = 0; i < PCI_STD_NUM_BARS; i++) if (res == &pdev->resource[i]) break; - if (i >= PCI_ROM_RESOURCE) + if (i >= PCI_STD_NUM_BARS) return -ENODEV; if (res->flags & IORESOURCE_MEM && iomem_is_exclusive(res->start)) @@ -115,7 +115,7 @@ void pci_remove_resource_files(struct pci_dev *pdev) { int i; - for (i = 0; i < PCI_ROM_RESOURCE; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { struct bin_attribute *res_attr; res_attr = pdev->res_attr[i]; @@ -232,7 +232,7 @@ int pci_create_resource_files(struct pci_dev *pdev) int retval; /* Expose the PCI resources from this device as files */ - for (i = 0; i < PCI_ROM_RESOURCE; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { /* skip empty resources */ if (!pci_resource_len(pdev, i)) diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index a2399eff84ca..3a06c264ea53 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -2,9 +2,6 @@ #ifndef __ASM_S390_PCI_H #define __ASM_S390_PCI_H -/* must be set before including pci_clp.h */ -#define PCI_BAR_COUNT 6 - #include #include #include @@ -138,7 +135,7 @@ struct zpci_dev { char res_name[16]; bool mio_capable; - struct zpci_bar_struct bars[PCI_BAR_COUNT]; + struct zpci_bar_struct bars[PCI_STD_NUM_BARS]; u64 start_dma; /* Start of available DMA addresses */ u64 end_dma; /* End of available DMA addresses */ diff --git a/arch/s390/include/asm/pci_clp.h b/arch/s390/include/asm/pci_clp.h index 50359172cc48..bd2cb4ea7d93 100644 --- a/arch/s390/include/asm/pci_clp.h +++ b/arch/s390/include/asm/pci_clp.h @@ -77,7 +77,7 @@ struct mio_info { struct { u64 wb; u64 wt; - } addr[PCI_BAR_COUNT]; + } addr[PCI_STD_NUM_BARS]; u32 reserved[6]; } __packed; @@ -98,9 +98,9 @@ struct clp_rsp_query_pci { u16 util_str_avail : 1; /* utility string available? */ u16 pfgid : 8; /* pci function group id */ u32 fid; /* pci function id */ - u8 bar_size[PCI_BAR_COUNT]; + u8 bar_size[PCI_STD_NUM_BARS]; u16 pchid; - __le32 bar[PCI_BAR_COUNT]; + __le32 bar[PCI_STD_NUM_BARS]; u8 pfip[CLP_PFIP_NR_SEGMENTS]; /* pci function internal path */ u32 : 16; u8 fmb_len; diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index c7fea9bea8cb..7b4c2acf05a8 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -43,7 +43,7 @@ static DECLARE_BITMAP(zpci_domain, ZPCI_NR_DEVICES); static DEFINE_SPINLOCK(zpci_domain_lock); #define ZPCI_IOMAP_ENTRIES \ - min(((unsigned long) ZPCI_NR_DEVICES * PCI_BAR_COUNT / 2), \ + min(((unsigned long) ZPCI_NR_DEVICES * PCI_STD_NUM_BARS / 2), \ ZPCI_IOMAP_MAX_ENTRIES) static DEFINE_SPINLOCK(zpci_iomap_lock); @@ -294,7 +294,7 @@ static void __iomem *pci_iomap_range_mio(struct pci_dev *pdev, int bar, void __iomem *pci_iomap_range(struct pci_dev *pdev, int bar, unsigned long offset, unsigned long max) { - if (!pci_resource_len(pdev, bar) || bar >= PCI_BAR_COUNT) + if (bar >= PCI_STD_NUM_BARS || !pci_resource_len(pdev, bar)) return NULL; if (static_branch_likely(&have_mio)) @@ -324,7 +324,7 @@ static void __iomem *pci_iomap_wc_range_mio(struct pci_dev *pdev, int bar, void __iomem *pci_iomap_wc_range(struct pci_dev *pdev, int bar, unsigned long offset, unsigned long max) { - if (!pci_resource_len(pdev, bar) || bar >= PCI_BAR_COUNT) + if (bar >= PCI_STD_NUM_BARS || !pci_resource_len(pdev, bar)) return NULL; if (static_branch_likely(&have_mio)) @@ -416,7 +416,7 @@ static void zpci_map_resources(struct pci_dev *pdev) resource_size_t len; int i; - for (i = 0; i < PCI_BAR_COUNT; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { len = pci_resource_len(pdev, i); if (!len) continue; @@ -451,7 +451,7 @@ static void zpci_unmap_resources(struct pci_dev *pdev) if (zpci_use_mio(zdev)) return; - for (i = 0; i < PCI_BAR_COUNT; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { len = pci_resource_len(pdev, i); if (!len) continue; @@ -514,7 +514,7 @@ static int zpci_setup_bus_resources(struct zpci_dev *zdev, snprintf(zdev->res_name, sizeof(zdev->res_name), "PCI Bus %04x:%02x", zdev->domain, ZPCI_BUS_NR); - for (i = 0; i < PCI_BAR_COUNT; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (!zdev->bars[i].size) continue; entry = zpci_alloc_iomap(zdev); @@ -551,7 +551,7 @@ static void zpci_cleanup_bus_resources(struct zpci_dev *zdev) { int i; - for (i = 0; i < PCI_BAR_COUNT; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (!zdev->bars[i].size || !zdev->bars[i].res) continue; @@ -573,7 +573,7 @@ int pcibios_add_device(struct pci_dev *pdev) pdev->dev.dma_ops = &s390_pci_dma_ops; zpci_map_resources(pdev); - for (i = 0; i < PCI_BAR_COUNT; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { res = &pdev->resource[i]; if (res->parent || !res->flags) continue; diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index 9bdff4defef1..8b729b5f2972 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -145,7 +145,7 @@ static int clp_store_query_pci_fn(struct zpci_dev *zdev, { int i; - for (i = 0; i < PCI_BAR_COUNT; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { zdev->bars[i].val = le32_to_cpu(response->bar[i]); zdev->bars[i].size = response->bar_size[i]; } @@ -164,8 +164,8 @@ static int clp_store_query_pci_fn(struct zpci_dev *zdev, sizeof(zdev->util_str)); } zdev->mio_capable = response->mio_addr_avail; - for (i = 0; i < PCI_BAR_COUNT; i++) { - if (!(response->mio.valid & (1 << (PCI_BAR_COUNT - i - 1)))) + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + if (!(response->mio.valid & (1 << (PCI_STD_NUM_BARS - i - 1)))) continue; zdev->bars[i].mio_wb = (void __iomem *) response->mio.addr[i].wb; diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 9acab6ac28f5..1e59df041456 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -135,7 +135,7 @@ static void pcibios_fixup_device_resources(struct pci_dev *dev) * resource so the kernel doesn't attempt to assign * it later on in pci_assign_unassigned_resources */ - for (bar = 0; bar <= PCI_STD_RESOURCE_END; bar++) { + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) { bar_r = &dev->resource[bar]; if (bar_r->start == 0 && bar_r->end != 0) { bar_r->flags = 0; diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 43867bc85368..00c62115f39c 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -382,7 +382,7 @@ static void pci_fixed_bar_fixup(struct pci_dev *dev) PCI_DEVFN(2, 2) == dev->devfn) return; - for (i = 0; i < PCI_ROM_RESOURCE; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { pci_read_config_dword(dev, offset + 8 + (i * 4), &size); dev->resource[i].end = dev->resource[i].start + size - 1; dev->resource[i].flags |= IORESOURCE_PCI_FIXED; diff --git a/drivers/ata/pata_atp867x.c b/drivers/ata/pata_atp867x.c index cfd0cf2cbca6..e01a3a6e4d46 100644 --- a/drivers/ata/pata_atp867x.c +++ b/drivers/ata/pata_atp867x.c @@ -422,7 +422,7 @@ static int atp867x_ata_pci_sff_init_host(struct ata_host *host) #ifdef ATP867X_DEBUG atp867x_check_res(pdev); - for (i = 0; i < PCI_ROM_RESOURCE; i++) + for (i = 0; i < PCI_STD_NUM_BARS; i++) printk(KERN_DEBUG "ATP867X: iomap[%d]=0x%llx\n", i, (unsigned long long)(host->iomap[i])); #endif diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c index 56946012d113..6f261fbae8c2 100644 --- a/drivers/ata/sata_nv.c +++ b/drivers/ata/sata_nv.c @@ -2325,7 +2325,7 @@ static int nv_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) // Make sure this is a SATA controller by counting the number of bars // (NVIDIA SATA controllers will always have six bars). Otherwise, // it's an IDE controller and we ignore it. - for (bar = 0; bar < 6; bar++) + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) if (pci_resource_start(pdev, bar) == 0) return -ENODEV; diff --git a/drivers/memstick/host/jmb38x_ms.c b/drivers/memstick/host/jmb38x_ms.c index 32747425297d..fd281c1d39b1 100644 --- a/drivers/memstick/host/jmb38x_ms.c +++ b/drivers/memstick/host/jmb38x_ms.c @@ -848,7 +848,7 @@ static int jmb38x_ms_count_slots(struct pci_dev *pdev) { int cnt, rc = 0; - for (cnt = 0; cnt < PCI_ROM_RESOURCE; ++cnt) { + for (cnt = 0; cnt < PCI_STD_NUM_BARS; ++cnt) { if (!(IORESOURCE_MEM & pci_resource_flags(pdev, cnt))) break; diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c index 6e208a060a58..a5e317073d95 100644 --- a/drivers/misc/pci_endpoint_test.c +++ b/drivers/misc/pci_endpoint_test.c @@ -94,7 +94,7 @@ enum pci_barno { struct pci_endpoint_test { struct pci_dev *pdev; void __iomem *base; - void __iomem *bar[6]; + void __iomem *bar[PCI_STD_NUM_BARS]; struct completion irq_raised; int last_irq; int num_irqs; @@ -687,7 +687,7 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev, if (!pci_endpoint_test_request_irq(test)) goto err_disable_irq; - for (bar = BAR_0; bar <= BAR_5; bar++) { + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) { if (pci_resource_flags(pdev, bar) & IORESOURCE_MEM) { base = pci_ioremap_bar(pdev, bar); if (!base) { @@ -740,7 +740,7 @@ err_ida_remove: ida_simple_remove(&pci_endpoint_test_ida, id); err_iounmap: - for (bar = BAR_0; bar <= BAR_5; bar++) { + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) { if (test->bar[bar]) pci_iounmap(pdev, test->bar[bar]); } @@ -771,7 +771,7 @@ static void pci_endpoint_test_remove(struct pci_dev *pdev) misc_deregister(&test->miscdev); kfree(misc_device->name); ida_simple_remove(&pci_endpoint_test_ida, id); - for (bar = BAR_0; bar <= BAR_5; bar++) { + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) { if (test->bar[bar]) pci_iounmap(pdev, test->bar[bar]); } diff --git a/drivers/net/ethernet/intel/e1000/e1000.h b/drivers/net/ethernet/intel/e1000/e1000.h index c40729b2c184..7fad2f24dcad 100644 --- a/drivers/net/ethernet/intel/e1000/e1000.h +++ b/drivers/net/ethernet/intel/e1000/e1000.h @@ -45,7 +45,6 @@ #define BAR_0 0 #define BAR_1 1 -#define BAR_5 5 #define INTEL_E1000_ETHERNET_DEVICE(device_id) {\ PCI_DEVICE(PCI_VENDOR_ID_INTEL, device_id)} diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 86493fea56e4..78db33694494 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -977,7 +977,7 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_ioremap; if (adapter->need_ioport) { - for (i = BAR_1; i <= BAR_5; i++) { + for (i = BAR_1; i < PCI_STD_NUM_BARS; i++) { if (pci_resource_len(pdev, i) == 0) continue; if (pci_resource_flags(pdev, i) & IORESOURCE_IO) { diff --git a/drivers/net/ethernet/intel/ixgb/ixgb.h b/drivers/net/ethernet/intel/ixgb/ixgb.h index e85271b68410..681d44cc9784 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb.h +++ b/drivers/net/ethernet/intel/ixgb/ixgb.h @@ -42,7 +42,6 @@ #define BAR_0 0 #define BAR_1 1 -#define BAR_5 5 struct ixgb_adapter; #include "ixgb_hw.h" diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c index 0940a0da16f2..3d8c051dd327 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c @@ -412,7 +412,7 @@ ixgb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_ioremap; } - for (i = BAR_1; i <= BAR_5; i++) { + for (i = BAR_1; i < PCI_STD_NUM_BARS; i++) { if (pci_resource_len(pdev, i) == 0) continue; if (pci_resource_flags(pdev, i) & IORESOURCE_IO) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index 292045f4581f..8237dbc3e991 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -489,7 +489,7 @@ static int stmmac_pci_probe(struct pci_dev *pdev, } /* Get the base address of device */ - for (i = 0; i <= PCI_STD_RESOURCE_END; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (pci_resource_len(pdev, i) == 0) continue; ret = pcim_iomap_regions(pdev, BIT(i), pci_name(pdev)); @@ -532,7 +532,7 @@ static void stmmac_pci_remove(struct pci_dev *pdev) if (priv->plat->stmmac_clk) clk_unregister_fixed_rate(priv->plat->stmmac_clk); - for (i = 0; i <= PCI_STD_RESOURCE_END; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (pci_resource_len(pdev, i) == 0) continue; pcim_iounmap_regions(pdev, BIT(i)); diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c index 386bafe74c3f..fa8604d7b797 100644 --- a/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-pci.c @@ -34,7 +34,7 @@ static int xlgmac_probe(struct pci_dev *pcidev, const struct pci_device_id *id) return ret; } - for (i = 0; i <= PCI_STD_RESOURCE_END; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (pci_resource_len(pcidev, i) == 0) continue; ret = pcim_iomap_regions(pcidev, BIT(i), XLGMAC_DRV_NAME); diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c index 4234ddb4722f..b20651cea09f 100644 --- a/drivers/pci/controller/dwc/pci-dra7xx.c +++ b/drivers/pci/controller/dwc/pci-dra7xx.c @@ -353,7 +353,7 @@ static void dra7xx_pcie_ep_init(struct dw_pcie_ep *ep) struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pci); enum pci_barno bar; - for (bar = BAR_0; bar <= BAR_5; bar++) + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) dw_pcie_ep_reset_bar(pci, bar); dra7xx_pcie_enable_wrapper_interrupts(dra7xx); diff --git a/drivers/pci/controller/dwc/pci-layerscape-ep.c b/drivers/pci/controller/dwc/pci-layerscape-ep.c index ca9aa4501e7e..0d151cead1b7 100644 --- a/drivers/pci/controller/dwc/pci-layerscape-ep.c +++ b/drivers/pci/controller/dwc/pci-layerscape-ep.c @@ -58,7 +58,7 @@ static void ls_pcie_ep_init(struct dw_pcie_ep *ep) struct dw_pcie *pci = to_dw_pcie_from_ep(ep); enum pci_barno bar; - for (bar = BAR_0; bar <= BAR_5; bar++) + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) dw_pcie_ep_reset_bar(pci, bar); } diff --git a/drivers/pci/controller/dwc/pcie-artpec6.c b/drivers/pci/controller/dwc/pcie-artpec6.c index d00252bd8fae..9e2482bd7b6d 100644 --- a/drivers/pci/controller/dwc/pcie-artpec6.c +++ b/drivers/pci/controller/dwc/pcie-artpec6.c @@ -422,7 +422,7 @@ static void artpec6_pcie_ep_init(struct dw_pcie_ep *ep) artpec6_pcie_wait_for_phy(artpec6_pcie); artpec6_pcie_set_nfts(artpec6_pcie); - for (bar = BAR_0; bar <= BAR_5; bar++) + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) dw_pcie_ep_reset_bar(pci, bar); } diff --git a/drivers/pci/controller/dwc/pcie-designware-plat.c b/drivers/pci/controller/dwc/pcie-designware-plat.c index b58fdcbc664b..73646b677aff 100644 --- a/drivers/pci/controller/dwc/pcie-designware-plat.c +++ b/drivers/pci/controller/dwc/pcie-designware-plat.c @@ -70,7 +70,7 @@ static void dw_plat_pcie_ep_init(struct dw_pcie_ep *ep) struct dw_pcie *pci = to_dw_pcie_from_ep(ep); enum pci_barno bar; - for (bar = BAR_0; bar <= BAR_5; bar++) + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) dw_pcie_ep_reset_bar(pci, bar); } diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h index 5a18e94e52c8..5accdd6bc388 100644 --- a/drivers/pci/controller/dwc/pcie-designware.h +++ b/drivers/pci/controller/dwc/pcie-designware.h @@ -214,7 +214,7 @@ struct dw_pcie_ep { phys_addr_t phys_base; size_t addr_size; size_t page_size; - u8 bar_to_atu[6]; + u8 bar_to_atu[PCI_STD_NUM_BARS]; phys_addr_t *outbound_addr; unsigned long *ib_window_map; unsigned long *ob_window_map; diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index f1f300218fab..ad40e848d564 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -307,7 +307,7 @@ struct pci_bus_relations { struct pci_q_res_req_response { struct vmpacket_descriptor hdr; s32 status; /* negative values are failures */ - u32 probed_bar[6]; + u32 probed_bar[PCI_STD_NUM_BARS]; } __packed; struct pci_set_power { @@ -539,7 +539,7 @@ struct hv_pci_dev { * What would be observed if one wrote 0xFFFFFFFF to a BAR and then * read it back, for each of the BAR offsets within config space. */ - u32 probed_bar[6]; + u32 probed_bar[PCI_STD_NUM_BARS]; }; struct hv_pci_compl { @@ -1610,7 +1610,7 @@ static void survey_child_resources(struct hv_pcibus_device *hbus) * so it's sufficient to just add them up without tracking alignment. */ list_for_each_entry(hpdev, &hbus->children, list_entry) { - for (i = 0; i < 6; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (hpdev->probed_bar[i] & PCI_BASE_ADDRESS_SPACE_IO) dev_err(&hbus->hdev->device, "There's an I/O BAR in this list!\n"); @@ -1684,7 +1684,7 @@ static void prepopulate_bars(struct hv_pcibus_device *hbus) /* Pick addresses for the BARs. */ do { list_for_each_entry(hpdev, &hbus->children, list_entry) { - for (i = 0; i < 6; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { bar_val = hpdev->probed_bar[i]; if (bar_val == 0) continue; @@ -1841,7 +1841,7 @@ static void q_resource_requirements(void *context, struct pci_response *resp, "query resource requirements failed: %x\n", resp->status); } else { - for (i = 0; i < 6; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { completion->hpdev->probed_bar[i] = q_res_req->probed_bar[i]; } diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c index 1cfe3687a211..5d74f81ddfe4 100644 --- a/drivers/pci/endpoint/functions/pci-epf-test.c +++ b/drivers/pci/endpoint/functions/pci-epf-test.c @@ -44,7 +44,7 @@ static struct workqueue_struct *kpcitest_workqueue; struct pci_epf_test { - void *reg[6]; + void *reg[PCI_STD_NUM_BARS]; struct pci_epf *epf; enum pci_barno test_reg_bar; struct delayed_work cmd_handler; @@ -377,7 +377,7 @@ static void pci_epf_test_unbind(struct pci_epf *epf) cancel_delayed_work(&epf_test->cmd_handler); pci_epc_stop(epc); - for (bar = BAR_0; bar <= BAR_5; bar++) { + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) { epf_bar = &epf->bar[bar]; if (epf_test->reg[bar]) { @@ -400,7 +400,7 @@ static int pci_epf_test_set_bar(struct pci_epf *epf) epc_features = epf_test->epc_features; - for (bar = BAR_0; bar <= BAR_5; bar += add) { + for (bar = 0; bar < PCI_STD_NUM_BARS; bar += add) { epf_bar = &epf->bar[bar]; /* * pci_epc_set_bar() sets PCI_BASE_ADDRESS_MEM_TYPE_64 @@ -450,7 +450,7 @@ static int pci_epf_test_alloc_space(struct pci_epf *epf) } epf_test->reg[test_reg_bar] = base; - for (bar = BAR_0; bar <= BAR_5; bar += add) { + for (bar = 0; bar < PCI_STD_NUM_BARS; bar += add) { epf_bar = &epf->bar[bar]; add = (epf_bar->flags & PCI_BASE_ADDRESS_MEM_TYPE_64) ? 2 : 1; @@ -478,7 +478,7 @@ static void pci_epf_configure_bar(struct pci_epf *epf, bool bar_fixed_64bit; int i; - for (i = BAR_0; i <= BAR_5; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { epf_bar = &epf->bar[i]; bar_fixed_64bit = !!(epc_features->bar_fixed_64bit & (1 << i)); if (bar_fixed_64bit) diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 793412954529..07bd84c50238 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -1122,7 +1122,7 @@ static void pci_remove_resource_files(struct pci_dev *pdev) { int i; - for (i = 0; i < PCI_ROM_RESOURCE; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { struct bin_attribute *res_attr; res_attr = pdev->res_attr[i]; @@ -1193,7 +1193,7 @@ static int pci_create_resource_files(struct pci_dev *pdev) int retval; /* Expose the PCI resources from this device as files */ - for (i = 0; i < PCI_ROM_RESOURCE; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { /* skip empty resources */ if (!pci_resource_len(pdev, i)) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index e7982af9a5d8..184765f12848 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -674,7 +674,7 @@ struct resource *pci_find_resource(struct pci_dev *dev, struct resource *res) { int i; - for (i = 0; i < PCI_ROM_RESOURCE; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { struct resource *r = &dev->resource[i]; if (r->start && resource_contains(r, res)) @@ -3768,7 +3768,7 @@ void pci_release_selected_regions(struct pci_dev *pdev, int bars) { int i; - for (i = 0; i < 6; i++) + for (i = 0; i < PCI_STD_NUM_BARS; i++) if (bars & (1 << i)) pci_release_region(pdev, i); } @@ -3779,7 +3779,7 @@ static int __pci_request_selected_regions(struct pci_dev *pdev, int bars, { int i; - for (i = 0; i < 6; i++) + for (i = 0; i < PCI_STD_NUM_BARS; i++) if (bars & (1 << i)) if (__pci_request_region(pdev, i, res_name, excl)) goto err_out; @@ -3827,7 +3827,7 @@ EXPORT_SYMBOL(pci_request_selected_regions_exclusive); void pci_release_regions(struct pci_dev *pdev) { - pci_release_selected_regions(pdev, (1 << 6) - 1); + pci_release_selected_regions(pdev, (1 << PCI_STD_NUM_BARS) - 1); } EXPORT_SYMBOL(pci_release_regions); @@ -3846,7 +3846,8 @@ EXPORT_SYMBOL(pci_release_regions); */ int pci_request_regions(struct pci_dev *pdev, const char *res_name) { - return pci_request_selected_regions(pdev, ((1 << 6) - 1), res_name); + return pci_request_selected_regions(pdev, + ((1 << PCI_STD_NUM_BARS) - 1), res_name); } EXPORT_SYMBOL(pci_request_regions); @@ -3868,7 +3869,7 @@ EXPORT_SYMBOL(pci_request_regions); int pci_request_regions_exclusive(struct pci_dev *pdev, const char *res_name) { return pci_request_selected_regions_exclusive(pdev, - ((1 << 6) - 1), res_name); + ((1 << PCI_STD_NUM_BARS) - 1), res_name); } EXPORT_SYMBOL(pci_request_regions_exclusive); diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c index 5495537c60c2..6ef74bf5013f 100644 --- a/drivers/pci/proc.c +++ b/drivers/pci/proc.c @@ -258,13 +258,13 @@ static int proc_bus_pci_mmap(struct file *file, struct vm_area_struct *vma) } /* Make sure the caller is mapping a real resource for this device */ - for (i = 0; i < PCI_ROM_RESOURCE; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (dev->resource[i].flags & res_bit && pci_mmap_fits(dev, i, vma, PCI_MMAP_PROCFS)) break; } - if (i >= PCI_ROM_RESOURCE) + if (i >= PCI_STD_NUM_BARS) return -ENODEV; if (fpriv->mmap_state == pci_mmap_mem && diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 320255e5e8f8..5d5e6f2f7837 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -474,7 +474,7 @@ static void quirk_extend_bar_to_page(struct pci_dev *dev) { int i; - for (i = 0; i <= PCI_STD_RESOURCE_END; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { struct resource *r = &dev->resource[i]; if (r->flags & IORESOURCE_MEM && resource_size(r) < PAGE_SIZE) { @@ -1809,7 +1809,7 @@ static void quirk_alder_ioapic(struct pci_dev *pdev) * The next five BARs all seem to be rubbish, so just clean * them out. */ - for (i = 1; i < 6; i++) + for (i = 1; i < PCI_STD_NUM_BARS; i++) memset(&pdev->resource[i], 0, sizeof(pdev->resource[i])); } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_EESSC, quirk_alder_ioapic); diff --git a/drivers/rapidio/devices/tsi721.c b/drivers/rapidio/devices/tsi721.c index 125a173bed45..4dd31dd9feea 100644 --- a/drivers/rapidio/devices/tsi721.c +++ b/drivers/rapidio/devices/tsi721.c @@ -2755,7 +2755,7 @@ static int tsi721_probe(struct pci_dev *pdev, { int i; - for (i = 0; i <= PCI_STD_RESOURCE_END; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { tsi_debug(INIT, &pdev->dev, "res%d %pR", i, &pdev->resource[i]); } diff --git a/drivers/scsi/pm8001/pm8001_hwi.c b/drivers/scsi/pm8001/pm8001_hwi.c index 68a8217032d0..1a3661d6be06 100644 --- a/drivers/scsi/pm8001/pm8001_hwi.c +++ b/drivers/scsi/pm8001/pm8001_hwi.c @@ -1186,7 +1186,7 @@ static void pm8001_hw_chip_rst(struct pm8001_hba_info *pm8001_ha) void pm8001_chip_iounmap(struct pm8001_hba_info *pm8001_ha) { s8 bar, logical = 0; - for (bar = 0; bar < 6; bar++) { + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) { /* ** logical BARs for SPC: ** bar 0 and 1 - logical BAR0 diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c index 3374f553c617..aca913490eb5 100644 --- a/drivers/scsi/pm8001/pm8001_init.c +++ b/drivers/scsi/pm8001/pm8001_init.c @@ -401,7 +401,7 @@ static int pm8001_ioremap(struct pm8001_hba_info *pm8001_ha) pdev = pm8001_ha->pdev; /* map pci mem (PMC pci base 0-3)*/ - for (bar = 0; bar < 6; bar++) { + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) { /* ** logical BARs for SPC: ** bar 0 and 1 - logical BAR0 diff --git a/drivers/staging/gasket/gasket_constants.h b/drivers/staging/gasket/gasket_constants.h index 50d87c7b178c..9ea9c8833f27 100644 --- a/drivers/staging/gasket/gasket_constants.h +++ b/drivers/staging/gasket/gasket_constants.h @@ -13,9 +13,6 @@ /* The maximum devices per each type. */ #define GASKET_DEV_MAX 256 -/* The number of supported (and possible) PCI BARs. */ -#define GASKET_NUM_BARS 6 - /* The number of supported Gasket page tables per device. */ #define GASKET_MAX_NUM_PAGE_TABLES 1 diff --git a/drivers/staging/gasket/gasket_core.c b/drivers/staging/gasket/gasket_core.c index 13179f063a61..cd8be80d2076 100644 --- a/drivers/staging/gasket/gasket_core.c +++ b/drivers/staging/gasket/gasket_core.c @@ -371,7 +371,7 @@ static int gasket_setup_pci(struct pci_dev *pci_dev, { int i, mapped_bars, ret; - for (i = 0; i < GASKET_NUM_BARS; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { ret = gasket_map_pci_bar(gasket_dev, i); if (ret) { mapped_bars = i; @@ -393,7 +393,7 @@ static void gasket_cleanup_pci(struct gasket_dev *gasket_dev) { int i; - for (i = 0; i < GASKET_NUM_BARS; i++) + for (i = 0; i < PCI_STD_NUM_BARS; i++) gasket_unmap_pci_bar(gasket_dev, i); } @@ -493,7 +493,7 @@ static ssize_t gasket_sysfs_data_show(struct device *device, (enum gasket_sysfs_attribute_type)gasket_attr->data.attr_type; switch (sysfs_type) { case ATTR_BAR_OFFSETS: - for (i = 0; i < GASKET_NUM_BARS; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { bar_desc = &driver_desc->bar_descriptions[i]; if (bar_desc->size == 0) continue; @@ -505,7 +505,7 @@ static ssize_t gasket_sysfs_data_show(struct device *device, } break; case ATTR_BAR_SIZES: - for (i = 0; i < GASKET_NUM_BARS; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { bar_desc = &driver_desc->bar_descriptions[i]; if (bar_desc->size == 0) continue; @@ -556,7 +556,7 @@ static ssize_t gasket_sysfs_data_show(struct device *device, ret = snprintf(buf, PAGE_SIZE, "%d\n", gasket_dev->reset_count); break; case ATTR_USER_MEM_RANGES: - for (i = 0; i < GASKET_NUM_BARS; ++i) { + for (i = 0; i < PCI_STD_NUM_BARS; ++i) { current_written = gasket_write_mappable_regions(buf, driver_desc, i); @@ -736,7 +736,7 @@ static int gasket_get_bar_index(const struct gasket_dev *gasket_dev, const struct gasket_driver_desc *driver_desc; driver_desc = gasket_dev->internal_desc->driver_desc; - for (i = 0; i < GASKET_NUM_BARS; ++i) { + for (i = 0; i < PCI_STD_NUM_BARS; ++i) { struct gasket_bar_desc bar_desc = driver_desc->bar_descriptions[i]; diff --git a/drivers/staging/gasket/gasket_core.h b/drivers/staging/gasket/gasket_core.h index be44ac1e3118..c417acadb0d5 100644 --- a/drivers/staging/gasket/gasket_core.h +++ b/drivers/staging/gasket/gasket_core.h @@ -268,7 +268,7 @@ struct gasket_dev { char kobj_name[GASKET_NAME_MAX]; /* Virtual address of mapped BAR memory range. */ - struct gasket_bar_data bar_data[GASKET_NUM_BARS]; + struct gasket_bar_data bar_data[PCI_STD_NUM_BARS]; /* Coherent buffer. */ struct gasket_coherent_buffer coherent_buffer; @@ -369,7 +369,7 @@ struct gasket_driver_desc { /* Set of 6 bar descriptions that describe all PCIe bars. * Note that BUS/AXI devices (i.e. non PCI devices) use those. */ - struct gasket_bar_desc bar_descriptions[GASKET_NUM_BARS]; + struct gasket_bar_desc bar_descriptions[PCI_STD_NUM_BARS]; /* * Coherent buffer description. diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 6adbadd6a56a..0b8784cd6d71 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -48,8 +48,6 @@ struct f815xxa_data { int idx; }; -#define PCI_NUM_BAR_RESOURCES 6 - struct serial_private { struct pci_dev *dev; unsigned int nr; @@ -89,7 +87,7 @@ setup_port(struct serial_private *priv, struct uart_8250_port *port, { struct pci_dev *dev = priv->dev; - if (bar >= PCI_NUM_BAR_RESOURCES) + if (bar >= PCI_STD_NUM_BARS) return -EINVAL; if (pci_resource_flags(dev, bar) & IORESOURCE_MEM) { @@ -4060,7 +4058,7 @@ serial_pci_guess_board(struct pci_dev *dev, struct pciserial_board *board) return -ENODEV; num_iomem = num_port = 0; - for (i = 0; i < PCI_NUM_BAR_RESOURCES; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (pci_resource_flags(dev, i) & IORESOURCE_IO) { num_port++; if (first_port == -1) @@ -4088,7 +4086,7 @@ serial_pci_guess_board(struct pci_dev *dev, struct pciserial_board *board) */ first_port = -1; num_port = 0; - for (i = 0; i < PCI_NUM_BAR_RESOURCES; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (pci_resource_flags(dev, i) & IORESOURCE_IO && pci_resource_len(dev, i) == 8 && (first_port == -1 || (first_port + num_port) == i)) { diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c index 9e26b0143a59..9ae2a7a93df2 100644 --- a/drivers/usb/core/hcd-pci.c +++ b/drivers/usb/core/hcd-pci.c @@ -234,7 +234,7 @@ int usb_hcd_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) /* UHCI */ int region; - for (region = 0; region < PCI_ROM_RESOURCE; region++) { + for (region = 0; region < PCI_STD_NUM_BARS; region++) { if (!(pci_resource_flags(dev, region) & IORESOURCE_IO)) continue; diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index f6d04491df60..6c7f0a876b96 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -728,7 +728,7 @@ static void quirk_usb_handoff_uhci(struct pci_dev *pdev) if (!pio_enabled(pdev)) return; - for (i = 0; i < PCI_ROM_RESOURCE; i++) + for (i = 0; i < PCI_STD_NUM_BARS; i++) if ((pci_resource_flags(pdev, i) & IORESOURCE_IO)) { base = pci_resource_start(pdev, i); break; diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 02206162eaa9..379a02c36e37 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -110,13 +110,15 @@ static inline bool vfio_pci_is_vga(struct pci_dev *pdev) static void vfio_pci_probe_mmaps(struct vfio_pci_device *vdev) { struct resource *res; - int bar; + int i; struct vfio_pci_dummy_resource *dummy_res; INIT_LIST_HEAD(&vdev->dummy_resources_list); - for (bar = PCI_STD_RESOURCES; bar <= PCI_STD_RESOURCE_END; bar++) { - res = vdev->pdev->resource + bar; + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + int bar = i + PCI_STD_RESOURCES; + + res = &vdev->pdev->resource[bar]; if (!IS_ENABLED(CONFIG_VFIO_PCI_MMAP)) goto no_mmap; @@ -399,7 +401,8 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev) vfio_config_free(vdev); - for (bar = PCI_STD_RESOURCES; bar <= PCI_STD_RESOURCE_END; bar++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + bar = i + PCI_STD_RESOURCES; if (!vdev->barmap[bar]) continue; pci_iounmap(pdev, vdev->barmap[bar]); diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index f0891bd8444c..90c0b80f8acf 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -450,30 +450,32 @@ static void vfio_bar_fixup(struct vfio_pci_device *vdev) { struct pci_dev *pdev = vdev->pdev; int i; - __le32 *bar; + __le32 *vbar; u64 mask; - bar = (__le32 *)&vdev->vconfig[PCI_BASE_ADDRESS_0]; + vbar = (__le32 *)&vdev->vconfig[PCI_BASE_ADDRESS_0]; - for (i = PCI_STD_RESOURCES; i <= PCI_STD_RESOURCE_END; i++, bar++) { - if (!pci_resource_start(pdev, i)) { - *bar = 0; /* Unmapped by host = unimplemented to user */ + for (i = 0; i < PCI_STD_NUM_BARS; i++, vbar++) { + int bar = i + PCI_STD_RESOURCES; + + if (!pci_resource_start(pdev, bar)) { + *vbar = 0; /* Unmapped by host = unimplemented to user */ continue; } - mask = ~(pci_resource_len(pdev, i) - 1); + mask = ~(pci_resource_len(pdev, bar) - 1); - *bar &= cpu_to_le32((u32)mask); - *bar |= vfio_generate_bar_flags(pdev, i); + *vbar &= cpu_to_le32((u32)mask); + *vbar |= vfio_generate_bar_flags(pdev, bar); - if (*bar & cpu_to_le32(PCI_BASE_ADDRESS_MEM_TYPE_64)) { - bar++; - *bar &= cpu_to_le32((u32)(mask >> 32)); + if (*vbar & cpu_to_le32(PCI_BASE_ADDRESS_MEM_TYPE_64)) { + vbar++; + *vbar &= cpu_to_le32((u32)(mask >> 32)); i++; } } - bar = (__le32 *)&vdev->vconfig[PCI_ROM_ADDRESS]; + vbar = (__le32 *)&vdev->vconfig[PCI_ROM_ADDRESS]; /* * NB. REGION_INFO will have reported zero size if we weren't able @@ -483,14 +485,14 @@ static void vfio_bar_fixup(struct vfio_pci_device *vdev) if (pci_resource_start(pdev, PCI_ROM_RESOURCE)) { mask = ~(pci_resource_len(pdev, PCI_ROM_RESOURCE) - 1); mask |= PCI_ROM_ADDRESS_ENABLE; - *bar &= cpu_to_le32((u32)mask); + *vbar &= cpu_to_le32((u32)mask); } else if (pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW) { mask = ~(0x20000 - 1); mask |= PCI_ROM_ADDRESS_ENABLE; - *bar &= cpu_to_le32((u32)mask); + *vbar &= cpu_to_le32((u32)mask); } else - *bar = 0; + *vbar = 0; vdev->bardirty = false; } diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h index ee6ee91718a4..8a2c7607d513 100644 --- a/drivers/vfio/pci/vfio_pci_private.h +++ b/drivers/vfio/pci/vfio_pci_private.h @@ -86,8 +86,8 @@ struct vfio_pci_reflck { struct vfio_pci_device { struct pci_dev *pdev; - void __iomem *barmap[PCI_STD_RESOURCE_END + 1]; - bool bar_mmap_supported[PCI_STD_RESOURCE_END + 1]; + void __iomem *barmap[PCI_STD_NUM_BARS]; + bool bar_mmap_supported[PCI_STD_NUM_BARS]; u8 *pci_config_map; u8 *vconfig; struct perm_bits *msi_perm; diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index e6a1c805064f..19af5626a317 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1774,7 +1774,7 @@ int remove_conflicting_pci_framebuffers(struct pci_dev *pdev, int res_id, const int err, idx, bar; bool res_id_found = false; - for (idx = 0, bar = 0; bar < PCI_ROM_RESOURCE; bar++) { + for (idx = 0, bar = 0; bar < PCI_STD_NUM_BARS; bar++) { if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM)) continue; idx++; @@ -1784,7 +1784,7 @@ int remove_conflicting_pci_framebuffers(struct pci_dev *pdev, int res_id, const if (!ap) return -ENOMEM; - for (idx = 0, bar = 0; bar < PCI_ROM_RESOURCE; bar++) { + for (idx = 0, bar = 0; bar < PCI_STD_NUM_BARS; bar++) { if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM)) continue; ap->ranges[idx].base = pci_resource_start(pdev, bar); diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c index 51d97ec4f58f..1caa3726cb45 100644 --- a/drivers/video/fbdev/efifb.c +++ b/drivers/video/fbdev/efifb.c @@ -653,7 +653,7 @@ static void efifb_fixup_resources(struct pci_dev *dev) if (!base) return; - for (i = 0; i <= PCI_STD_RESOURCE_END; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { struct resource *res = &dev->resource[i]; if (!(res->flags & IORESOURCE_MEM)) diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index f641badc2c61..56f1846b9d39 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -117,7 +117,7 @@ struct pci_epc_features { unsigned int msix_capable : 1; u8 reserved_bar; u8 bar_fixed_64bit; - u64 bar_fixed_size[BAR_5 + 1]; + u64 bar_fixed_size[PCI_STD_NUM_BARS]; size_t align; }; diff --git a/include/linux/pci.h b/include/linux/pci.h index f9088c89a534..4cc739616148 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -82,7 +82,7 @@ enum pci_mmap_state { enum { /* #0-5: standard PCI resources */ PCI_STD_RESOURCES, - PCI_STD_RESOURCE_END = 5, + PCI_STD_RESOURCE_END = PCI_STD_RESOURCES + PCI_STD_NUM_BARS - 1, /* #6: expansion ROM resource */ PCI_ROM_RESOURCE, diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 29d6e93fd15e..43cf74eba29d 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -34,6 +34,7 @@ * of which the first 64 bytes are standardized as follows: */ #define PCI_STD_HEADER_SIZEOF 64 +#define PCI_STD_NUM_BARS 6 /* Number of standard BARs */ #define PCI_VENDOR_ID 0x00 /* 16 bits */ #define PCI_DEVICE_ID 0x02 /* 16 bits */ #define PCI_COMMAND 0x04 /* 16 bits */ diff --git a/lib/devres.c b/lib/devres.c index 6a0e9bd6524a..ab75d73122b8 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -262,7 +262,7 @@ EXPORT_SYMBOL(devm_ioport_unmap); /* * PCI iomap devres */ -#define PCIM_IOMAP_MAX PCI_ROM_RESOURCE +#define PCIM_IOMAP_MAX PCI_STD_NUM_BARS struct pcim_iomap_devres { void __iomem *table[PCIM_IOMAP_MAX]; -- cgit v1.2.3-71-gd317 From 9e420d7f125f51ab1eda37497b08c4fad9efe4a8 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Fri, 11 Oct 2019 17:05:43 +0200 Subject: rts: ds1685: remove not needed fields from private struct A few of the fields in struct ds1685_priv aren't needed at all, so we can remove it. Signed-off-by: Thomas Bogendoerfer Acked-by: Joshua Kinard Link: https://lore.kernel.org/r/20191011150546.9186-1-tbogendoerfer@suse.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ds1685.c | 3 --- include/linux/rtc/ds1685.h | 3 --- 2 files changed, 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/rtc/rtc-ds1685.c b/drivers/rtc/rtc-ds1685.c index 184e4a3e2bef..51f568473de8 100644 --- a/drivers/rtc/rtc-ds1685.c +++ b/drivers/rtc/rtc-ds1685.c @@ -1086,12 +1086,10 @@ ds1685_rtc_probe(struct platform_device *pdev) * Set the base address for the rtc, and ioremap its * registers. */ - rtc->baseaddr = res->start; rtc->regs = devm_ioremap(&pdev->dev, res->start, rtc->size); if (!rtc->regs) return -ENOMEM; } - rtc->alloc_io_resources = pdata->alloc_io_resources; /* Get the register step size. */ if (pdata->regstep > 0) @@ -1271,7 +1269,6 @@ ds1685_rtc_probe(struct platform_device *pdev) /* See if the platform doesn't support UIE. */ if (pdata->uie_unsupported) rtc_dev->uie_unsupported = 1; - rtc->uie_unsupported = pdata->uie_unsupported; rtc->dev = rtc_dev; diff --git a/include/linux/rtc/ds1685.h b/include/linux/rtc/ds1685.h index 43aec568ba7c..b9671d00d964 100644 --- a/include/linux/rtc/ds1685.h +++ b/include/linux/rtc/ds1685.h @@ -43,13 +43,10 @@ struct ds1685_priv { struct rtc_device *dev; void __iomem *regs; u32 regstep; - resource_size_t baseaddr; size_t size; int irq_num; bool bcd_mode; bool no_irq; - bool uie_unsupported; - bool alloc_io_resources; u8 (*read)(struct ds1685_priv *, int); void (*write)(struct ds1685_priv *, int, u8); void (*prepare_poweroff)(void); -- cgit v1.2.3-71-gd317 From af818031f4637b0e8d106fcc9023f1c22c44e13a Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Fri, 11 Oct 2019 17:05:44 +0200 Subject: rtc: ds1685: use devm_platform_ioremap_resource helper Simplify ioremapping of registers by using devm_platform_ioremap_resource. Signed-off-by: Thomas Bogendoerfer Acked-by: Joshua Kinard Link: https://lore.kernel.org/r/20191011150546.9186-2-tbogendoerfer@suse.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ds1685.c | 23 +++-------------------- include/linux/rtc/ds1685.h | 1 - 2 files changed, 3 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/drivers/rtc/rtc-ds1685.c b/drivers/rtc/rtc-ds1685.c index 51f568473de8..349a8d1caca1 100644 --- a/drivers/rtc/rtc-ds1685.c +++ b/drivers/rtc/rtc-ds1685.c @@ -1040,7 +1040,6 @@ static int ds1685_rtc_probe(struct platform_device *pdev) { struct rtc_device *rtc_dev; - struct resource *res; struct ds1685_priv *rtc; struct ds1685_rtc_platform_data *pdata; u8 ctrla, ctrlb, hours; @@ -1070,25 +1069,9 @@ ds1685_rtc_probe(struct platform_device *pdev) * that sits behind the IOC3 PCI metadevice. */ if (pdata->alloc_io_resources) { - /* Get the platform resources. */ - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) - return -ENXIO; - rtc->size = resource_size(res); - - /* Request a memory region. */ - /* XXX: mmio-only for now. */ - if (!devm_request_mem_region(&pdev->dev, res->start, rtc->size, - pdev->name)) - return -EBUSY; - - /* - * Set the base address for the rtc, and ioremap its - * registers. - */ - rtc->regs = devm_ioremap(&pdev->dev, res->start, rtc->size); - if (!rtc->regs) - return -ENOMEM; + rtc->regs = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(rtc->regs)) + return PTR_ERR(rtc->regs); } /* Get the register step size. */ diff --git a/include/linux/rtc/ds1685.h b/include/linux/rtc/ds1685.h index b9671d00d964..101c7adc05a2 100644 --- a/include/linux/rtc/ds1685.h +++ b/include/linux/rtc/ds1685.h @@ -43,7 +43,6 @@ struct ds1685_priv { struct rtc_device *dev; void __iomem *regs; u32 regstep; - size_t size; int irq_num; bool bcd_mode; bool no_irq; -- cgit v1.2.3-71-gd317 From 781ca2de89bae1b1d2c96df9ef33e9a324415995 Mon Sep 17 00:00:00 2001 From: Tom Murphy Date: Sun, 8 Sep 2019 09:56:38 -0700 Subject: iommu: Add gfp parameter to iommu_ops::map Add a gfp_t parameter to the iommu_ops::map function. Remove the needless locking in the AMD iommu driver. The iommu_ops::map function (or the iommu_map function which calls it) was always supposed to be sleepable (according to Joerg's comment in this thread: https://lore.kernel.org/patchwork/patch/977520/ ) and so should probably have had a "might_sleep()" since it was written. However currently the dma-iommu api can call iommu_map in an atomic context, which it shouldn't do. This doesn't cause any problems because any iommu driver which uses the dma-iommu api uses gfp_atomic in it's iommu_ops::map function. But doing this wastes the memory allocators atomic pools. Signed-off-by: Tom Murphy Reviewed-by: Robin Murphy Reviewed-by: Christoph Hellwig Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 3 ++- drivers/iommu/arm-smmu-v3.c | 2 +- drivers/iommu/arm-smmu.c | 2 +- drivers/iommu/dma-iommu.c | 6 +++--- drivers/iommu/exynos-iommu.c | 2 +- drivers/iommu/intel-iommu.c | 2 +- drivers/iommu/iommu.c | 43 ++++++++++++++++++++++++++++++++++++------ drivers/iommu/ipmmu-vmsa.c | 2 +- drivers/iommu/msm_iommu.c | 2 +- drivers/iommu/mtk_iommu.c | 2 +- drivers/iommu/mtk_iommu_v1.c | 2 +- drivers/iommu/omap-iommu.c | 2 +- drivers/iommu/qcom_iommu.c | 2 +- drivers/iommu/rockchip-iommu.c | 2 +- drivers/iommu/s390-iommu.c | 2 +- drivers/iommu/tegra-gart.c | 2 +- drivers/iommu/tegra-smmu.c | 2 +- drivers/iommu/virtio-iommu.c | 2 +- include/linux/iommu.h | 21 ++++++++++++++++++++- 19 files changed, 77 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 97ca4ed4ce0c..1444757f0ff9 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -3106,7 +3106,8 @@ static int amd_iommu_attach_device(struct iommu_domain *dom, } static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova, - phys_addr_t paddr, size_t page_size, int iommu_prot) + phys_addr_t paddr, size_t page_size, int iommu_prot, + gfp_t gfp) { struct protection_domain *domain = to_pdomain(dom); int prot = 0; diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 8da93e730d6f..f1bdaaa8c5de 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -2448,7 +2448,7 @@ out_unlock: } static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops; diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index b18aac4c105e..e85bc0e8d564 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -1159,7 +1159,7 @@ rpm_put: } static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops; struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu; diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index f321279baf9e..cc3bf5cf0a90 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -476,7 +476,7 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys, if (!iova) return DMA_MAPPING_ERROR; - if (iommu_map(domain, iova, phys - iova_off, size, prot)) { + if (iommu_map_atomic(domain, iova, phys - iova_off, size, prot)) { iommu_dma_free_iova(cookie, iova, size); return DMA_MAPPING_ERROR; } @@ -611,7 +611,7 @@ static void *iommu_dma_alloc_remap(struct device *dev, size_t size, arch_dma_prep_coherent(sg_page(sg), sg->length); } - if (iommu_map_sg(domain, iova, sgt.sgl, sgt.orig_nents, ioprot) + if (iommu_map_sg_atomic(domain, iova, sgt.sgl, sgt.orig_nents, ioprot) < size) goto out_free_sg; @@ -871,7 +871,7 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, * We'll leave any physical concatenation to the IOMMU driver's * implementation - it knows better than we do. */ - if (iommu_map_sg(domain, iova, sg, nents, prot) < iova_len) + if (iommu_map_sg_atomic(domain, iova, sg, nents, prot) < iova_len) goto out_free_iova; return __finalise_sg(dev, sg, nents, iova); diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index 9c94e16fb127..186ff5cc975c 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -1073,7 +1073,7 @@ static int lv2set_page(sysmmu_pte_t *pent, phys_addr_t paddr, size_t size, */ static int exynos_iommu_map(struct iommu_domain *iommu_domain, unsigned long l_iova, phys_addr_t paddr, size_t size, - int prot) + int prot, gfp_t gfp) { struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain); sysmmu_pte_t *entry; diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 3f974919d3bd..615495aa613e 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -5432,7 +5432,7 @@ static void intel_iommu_aux_detach_device(struct iommu_domain *domain, static int intel_iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t hpa, - size_t size, int iommu_prot) + size_t size, int iommu_prot, gfp_t gfp) { struct dmar_domain *dmar_domain = to_dmar_domain(domain); u64 max_addr; diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index d658c7c6a2ab..f8853dbf1c4e 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1854,8 +1854,8 @@ static size_t iommu_pgsize(struct iommu_domain *domain, return pgsize; } -int iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) +int __iommu_map(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { const struct iommu_ops *ops = domain->ops; unsigned long orig_iova = iova; @@ -1892,8 +1892,8 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova, pr_debug("mapping: iova 0x%lx pa %pa pgsize 0x%zx\n", iova, &paddr, pgsize); + ret = ops->map(domain, iova, paddr, pgsize, prot, gfp); - ret = ops->map(domain, iova, paddr, pgsize, prot); if (ret) break; @@ -1913,8 +1913,22 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova, return ret; } + +int iommu_map(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot) +{ + might_sleep(); + return __iommu_map(domain, iova, paddr, size, prot, GFP_KERNEL); +} EXPORT_SYMBOL_GPL(iommu_map); +int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot) +{ + return __iommu_map(domain, iova, paddr, size, prot, GFP_ATOMIC); +} +EXPORT_SYMBOL_GPL(iommu_map_atomic); + static size_t __iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size, struct iommu_iotlb_gather *iotlb_gather) @@ -1991,8 +2005,9 @@ size_t iommu_unmap_fast(struct iommu_domain *domain, } EXPORT_SYMBOL_GPL(iommu_unmap_fast); -size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, - struct scatterlist *sg, unsigned int nents, int prot) +size_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova, + struct scatterlist *sg, unsigned int nents, int prot, + gfp_t gfp) { size_t len = 0, mapped = 0; phys_addr_t start; @@ -2003,7 +2018,9 @@ size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, phys_addr_t s_phys = sg_phys(sg); if (len && s_phys != start + len) { - ret = iommu_map(domain, iova + mapped, start, len, prot); + ret = __iommu_map(domain, iova + mapped, start, + len, prot, gfp); + if (ret) goto out_err; @@ -2031,8 +2048,22 @@ out_err: return 0; } + +size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, + struct scatterlist *sg, unsigned int nents, int prot) +{ + might_sleep(); + return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_KERNEL); +} EXPORT_SYMBOL_GPL(iommu_map_sg); +size_t iommu_map_sg_atomic(struct iommu_domain *domain, unsigned long iova, + struct scatterlist *sg, unsigned int nents, int prot) +{ + return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_ATOMIC); +} +EXPORT_SYMBOL_GPL(iommu_map_sg_atomic); + int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr, phys_addr_t paddr, u64 size, int prot) { diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index 9da8309f7170..35f3edaba0e2 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -724,7 +724,7 @@ static void ipmmu_detach_device(struct iommu_domain *io_domain, } static int ipmmu_map(struct iommu_domain *io_domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain); diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index be99d408cf35..93f14bca26ee 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -504,7 +504,7 @@ fail: } static int msm_iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t pa, size_t len, int prot) + phys_addr_t pa, size_t len, int prot, gfp_t gfp) { struct msm_priv *priv = to_msm_priv(domain); unsigned long flags; diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 67a483c1a935..556beaa110b3 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -412,7 +412,7 @@ static void mtk_iommu_detach_device(struct iommu_domain *domain, } static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct mtk_iommu_domain *dom = to_mtk_domain(domain); struct mtk_iommu_data *data = mtk_iommu_get_m4u_data(); diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index b5efd6dac953..e93b94ecac45 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -295,7 +295,7 @@ static void mtk_iommu_detach_device(struct iommu_domain *domain, } static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct mtk_iommu_domain *dom = to_mtk_domain(domain); unsigned int page_num = size >> MT2701_IOMMU_PAGE_SHIFT; diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index 09c6e1c680db..be551cc34be4 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -1339,7 +1339,7 @@ static u32 iotlb_init_entry(struct iotlb_entry *e, u32 da, u32 pa, int pgsz) } static int omap_iommu_map(struct iommu_domain *domain, unsigned long da, - phys_addr_t pa, size_t bytes, int prot) + phys_addr_t pa, size_t bytes, int prot, gfp_t gfp) { struct omap_iommu_domain *omap_domain = to_omap_domain(domain); struct device *dev = omap_domain->dev; diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c index c31e7bc4ccbe..6ad5f934f00f 100644 --- a/drivers/iommu/qcom_iommu.c +++ b/drivers/iommu/qcom_iommu.c @@ -423,7 +423,7 @@ static void qcom_iommu_detach_dev(struct iommu_domain *domain, struct device *de } static int qcom_iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { int ret; unsigned long flags; diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index 26290f310f90..a4f6425fd12d 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -757,7 +757,7 @@ unwind: } static int rk_iommu_map(struct iommu_domain *domain, unsigned long _iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct rk_iommu_domain *rk_domain = to_rk_domain(domain); unsigned long flags; diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c index 3b0b18e23187..1137f3ddcb85 100644 --- a/drivers/iommu/s390-iommu.c +++ b/drivers/iommu/s390-iommu.c @@ -265,7 +265,7 @@ undo_cpu_trans: } static int s390_iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct s390_domain *s390_domain = to_s390_domain(domain); int flags = ZPCI_PTE_VALID, rc = 0; diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c index 3924f7c05544..3fb7ba72507d 100644 --- a/drivers/iommu/tegra-gart.c +++ b/drivers/iommu/tegra-gart.c @@ -178,7 +178,7 @@ static inline int __gart_iommu_map(struct gart_device *gart, unsigned long iova, } static int gart_iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t pa, size_t bytes, int prot) + phys_addr_t pa, size_t bytes, int prot, gfp_t gfp) { struct gart_device *gart = gart_handle; int ret; diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index 7293fc3f796d..99f85fb5a704 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -650,7 +650,7 @@ static void tegra_smmu_set_pte(struct tegra_smmu_as *as, unsigned long iova, } static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { struct tegra_smmu_as *as = to_smmu_as(domain); dma_addr_t pte_dma; diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index 3ea9d7682999..2ebcf4bae0c6 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -713,7 +713,7 @@ static int viommu_attach_dev(struct iommu_domain *domain, struct device *dev) } static int viommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { int ret; u32 flags; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 29bac5345563..6ca3fb2873d7 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -256,7 +256,7 @@ struct iommu_ops { int (*attach_dev)(struct iommu_domain *domain, struct device *dev); void (*detach_dev)(struct iommu_domain *domain, struct device *dev); int (*map)(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot); + phys_addr_t paddr, size_t size, int prot, gfp_t gfp); size_t (*unmap)(struct iommu_domain *domain, unsigned long iova, size_t size, struct iommu_iotlb_gather *iotlb_gather); void (*flush_iotlb_all)(struct iommu_domain *domain); @@ -421,6 +421,8 @@ extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern struct iommu_domain *iommu_get_dma_domain(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot); +extern int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot); extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size); extern size_t iommu_unmap_fast(struct iommu_domain *domain, @@ -428,6 +430,9 @@ extern size_t iommu_unmap_fast(struct iommu_domain *domain, struct iommu_iotlb_gather *iotlb_gather); extern size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, struct scatterlist *sg,unsigned int nents, int prot); +extern size_t iommu_map_sg_atomic(struct iommu_domain *domain, + unsigned long iova, struct scatterlist *sg, + unsigned int nents, int prot); extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova); extern void iommu_set_fault_handler(struct iommu_domain *domain, iommu_fault_handler_t handler, void *token); @@ -662,6 +667,13 @@ static inline int iommu_map(struct iommu_domain *domain, unsigned long iova, return -ENODEV; } +static inline int iommu_map_atomic(struct iommu_domain *domain, + unsigned long iova, phys_addr_t paddr, + size_t size, int prot) +{ + return -ENODEV; +} + static inline size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) { @@ -682,6 +694,13 @@ static inline size_t iommu_map_sg(struct iommu_domain *domain, return 0; } +static inline size_t iommu_map_sg_atomic(struct iommu_domain *domain, + unsigned long iova, struct scatterlist *sg, + unsigned int nents, int prot) +{ + return 0; +} + static inline void iommu_flush_tlb_all(struct iommu_domain *domain) { } -- cgit v1.2.3-71-gd317 From 35009c807488ccd5a01cbf102033695e52794b68 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 1 Oct 2019 17:27:22 +0300 Subject: ACPI / utils: Introduce acpi_dev_hid_uid_match() helper There are users outside of ACPI realm which reimplementing the comparator function to check if the given device matches to given HID and UID. For better utilization, introduce a helper for everyone to use. Signed-off-by: Andy Shevchenko Reviewed-by: Mika Westerberg Signed-off-by: Rafael J. Wysocki --- drivers/acpi/utils.c | 25 +++++++++++++++++++++++++ include/acpi/acpi_bus.h | 2 ++ include/linux/acpi.h | 8 ++++++++ 3 files changed, 35 insertions(+) (limited to 'include/linux') diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c index dbd1c4cfd7d1..804ac0df58ec 100644 --- a/drivers/acpi/utils.c +++ b/drivers/acpi/utils.c @@ -701,6 +701,31 @@ bool acpi_check_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 funcs) } EXPORT_SYMBOL(acpi_check_dsm); +/** + * acpi_dev_hid_uid_match - Match device by supplied HID and UID + * @adev: ACPI device to match. + * @hid2: Hardware ID of the device. + * @uid2: Unique ID of the device, pass NULL to not check _UID. + * + * Matches HID and UID in @adev with given @hid2 and @uid2. + * Returns true if matches. + */ +bool acpi_dev_hid_uid_match(struct acpi_device *adev, + const char *hid2, const char *uid2) +{ + const char *hid1 = acpi_device_hid(adev); + const char *uid1 = acpi_device_uid(adev); + + if (strcmp(hid1, hid2)) + return false; + + if (!uid2) + return true; + + return uid1 && !strcmp(uid1, uid2); +} +EXPORT_SYMBOL(acpi_dev_hid_uid_match); + /** * acpi_dev_found - Detect presence of a given ACPI device in the namespace. * @hid: Hardware ID of the device. diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 3f6fddeb7519..0c23fd0548d1 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -680,6 +680,8 @@ static inline bool acpi_device_can_poweroff(struct acpi_device *adev) adev->power.states[ACPI_STATE_D3_HOT].flags.explicit_set); } +bool acpi_dev_hid_uid_match(struct acpi_device *adev, const char *hid2, const char *uid2); + struct acpi_device * acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv); diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 8b4e516bac00..0f37a7d5fa77 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -678,6 +678,14 @@ static inline bool acpi_dev_present(const char *hid, const char *uid, s64 hrv) return false; } +struct acpi_device; + +static inline bool +acpi_dev_hid_uid_match(struct acpi_device *adev, const char *hid2, const char *uid2) +{ + return false; +} + static inline struct acpi_device * acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv) { -- cgit v1.2.3-71-gd317 From b2c98153f45fc17b9fcb241000f2d131ddea6030 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 26 Sep 2019 13:51:30 +0300 Subject: spi: introduce spi_delay struct as "value + unit" & spi_delay_exec() There are plenty of delays that have been introduced in SPI core. Most of them are in micro-seconds, some need to be in nano-seconds, and some in clock-cycles. For some of these delays (related to transfers & CS timing) it may make sense to have a `spi_delay` struct that abstracts these a bit. The important element of these delays [for unification] seems to be the `unit` of the delay. It looks like micro-seconds is good enough for most people, but every-once in a while, some delays seem to require other units of measurement. This change adds the `spi_delay` struct & a `spi_delay_exec()` function that processes a `spi_delay` object/struct to execute the delay. It's a copy of the `cs_change_delay` mechanism, but without the default for 10 uS. The clock-cycle delay unit is a bit special, as it needs to be bound to an `spi_transfer` object to execute. Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20190926105147.7839-3-alexandru.ardelean@analog.com Signed-off-by: Mark Brown --- drivers/spi/spi.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/spi/spi.h | 18 ++++++++++++++--- 2 files changed, 66 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 7ba981cdb86b..7499a4efbaba 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1106,6 +1106,57 @@ static void _spi_transfer_delay_ns(u32 ns) } } +static int _spi_delay_to_ns(struct spi_delay *_delay, struct spi_transfer *xfer) +{ + u32 delay = _delay->value; + u32 unit = _delay->unit; + u32 hz; + + if (!delay) + return 0; + + switch (unit) { + case SPI_DELAY_UNIT_USECS: + delay *= 1000; + break; + case SPI_DELAY_UNIT_NSECS: /* nothing to do here */ + break; + case SPI_DELAY_UNIT_SCK: + /* clock cycles need to be obtained from spi_transfer */ + if (!xfer) + return -EINVAL; + /* if there is no effective speed know, then approximate + * by underestimating with half the requested hz + */ + hz = xfer->effective_speed_hz ?: xfer->speed_hz / 2; + if (!hz) + return -EINVAL; + delay *= DIV_ROUND_UP(1000000000, hz); + break; + default: + return -EINVAL; + } + + return delay; +} + +int spi_delay_exec(struct spi_delay *_delay, struct spi_transfer *xfer) +{ + int delay; + + if (!_delay) + return -EINVAL; + + delay = _spi_delay_to_ns(_delay, xfer); + if (delay < 0) + return delay; + + _spi_transfer_delay_ns(delay); + + return 0; +} +EXPORT_SYMBOL_GPL(spi_delay_exec); + static void _spi_transfer_cs_change_delay(struct spi_message *msg, struct spi_transfer *xfer) { diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 27f6b046cf92..8f643de3197b 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -90,6 +90,21 @@ void spi_statistics_add_transfer_stats(struct spi_statistics *stats, #define SPI_STATISTICS_INCREMENT_FIELD(stats, field) \ SPI_STATISTICS_ADD_TO_FIELD(stats, field, 1) +/** + * struct spi_delay - SPI delay information + * @value: Value for the delay + * @unit: Unit for the delay + */ +struct spi_delay { +#define SPI_DELAY_UNIT_USECS 0 +#define SPI_DELAY_UNIT_NSECS 1 +#define SPI_DELAY_UNIT_SCK 2 + u16 value; + u8 unit; +}; + +extern int spi_delay_exec(struct spi_delay *_delay, struct spi_transfer *xfer); + /** * struct spi_device - Controller side proxy for an SPI slave device * @dev: Driver model representation of the device. @@ -887,9 +902,6 @@ struct spi_transfer { u16 delay_usecs; u16 cs_change_delay; u8 cs_change_delay_unit; -#define SPI_DELAY_UNIT_USECS 0 -#define SPI_DELAY_UNIT_NSECS 1 -#define SPI_DELAY_UNIT_SCK 2 u32 speed_hz; u16 word_delay; -- cgit v1.2.3-71-gd317 From 329f0dac4cad9fa4b1439a88180d91bcb5c4eaf8 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 26 Sep 2019 13:51:31 +0300 Subject: spi: make `cs_change_delay` the first user of the `spi_delay` logic Since the logic for `spi_delay` struct + `spi_delay_exec()` has been copied from the `cs_change_delay` logic, it's natural to make this delay, the first user. The `cs_change_delay` logic requires that the default remain 10 uS, in case it is unspecified/unconfigured. So, there is some special handling needed to do that. The ADIS library is one of the few users of the new `cs_change_delay` parameter for an spi_transfer. The introduction of the `spi_delay` struct, requires that the users of of `cs_change_delay` get an update. This change also updates the ADIS library. Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20190926105147.7839-4-alexandru.ardelean@analog.com Signed-off-by: Mark Brown --- drivers/iio/imu/adis.c | 24 ++++++++++++------------ drivers/spi/spi.c | 28 +++++++--------------------- include/linux/spi/spi.h | 4 +--- 3 files changed, 20 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/imu/adis.c b/drivers/iio/imu/adis.c index 1631c255deab..2cd2cc2316c6 100644 --- a/drivers/iio/imu/adis.c +++ b/drivers/iio/imu/adis.c @@ -39,24 +39,24 @@ int adis_write_reg(struct adis *adis, unsigned int reg, .len = 2, .cs_change = 1, .delay_usecs = adis->data->write_delay, - .cs_change_delay = adis->data->cs_change_delay, - .cs_change_delay_unit = SPI_DELAY_UNIT_USECS, + .cs_change_delay.value = adis->data->cs_change_delay, + .cs_change_delay.unit = SPI_DELAY_UNIT_USECS, }, { .tx_buf = adis->tx + 2, .bits_per_word = 8, .len = 2, .cs_change = 1, .delay_usecs = adis->data->write_delay, - .cs_change_delay = adis->data->cs_change_delay, - .cs_change_delay_unit = SPI_DELAY_UNIT_USECS, + .cs_change_delay.value = adis->data->cs_change_delay, + .cs_change_delay.unit = SPI_DELAY_UNIT_USECS, }, { .tx_buf = adis->tx + 4, .bits_per_word = 8, .len = 2, .cs_change = 1, .delay_usecs = adis->data->write_delay, - .cs_change_delay = adis->data->cs_change_delay, - .cs_change_delay_unit = SPI_DELAY_UNIT_USECS, + .cs_change_delay.value = adis->data->cs_change_delay, + .cs_change_delay.unit = SPI_DELAY_UNIT_USECS, }, { .tx_buf = adis->tx + 6, .bits_per_word = 8, @@ -139,16 +139,16 @@ int adis_read_reg(struct adis *adis, unsigned int reg, .len = 2, .cs_change = 1, .delay_usecs = adis->data->write_delay, - .cs_change_delay = adis->data->cs_change_delay, - .cs_change_delay_unit = SPI_DELAY_UNIT_USECS, + .cs_change_delay.value = adis->data->cs_change_delay, + .cs_change_delay.unit = SPI_DELAY_UNIT_USECS, }, { .tx_buf = adis->tx + 2, .bits_per_word = 8, .len = 2, .cs_change = 1, .delay_usecs = adis->data->read_delay, - .cs_change_delay = adis->data->cs_change_delay, - .cs_change_delay_unit = SPI_DELAY_UNIT_USECS, + .cs_change_delay.value = adis->data->cs_change_delay, + .cs_change_delay.unit = SPI_DELAY_UNIT_USECS, }, { .tx_buf = adis->tx + 4, .rx_buf = adis->rx, @@ -156,8 +156,8 @@ int adis_read_reg(struct adis *adis, unsigned int reg, .len = 2, .cs_change = 1, .delay_usecs = adis->data->read_delay, - .cs_change_delay = adis->data->cs_change_delay, - .cs_change_delay_unit = SPI_DELAY_UNIT_USECS, + .cs_change_delay.value = adis->data->cs_change_delay, + .cs_change_delay.unit = SPI_DELAY_UNIT_USECS, }, { .rx_buf = adis->rx + 2, .bits_per_word = 8, diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 7499a4efbaba..b69c14082c52 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1160,9 +1160,9 @@ EXPORT_SYMBOL_GPL(spi_delay_exec); static void _spi_transfer_cs_change_delay(struct spi_message *msg, struct spi_transfer *xfer) { - u32 delay = xfer->cs_change_delay; - u32 unit = xfer->cs_change_delay_unit; - u32 hz; + u32 delay = xfer->cs_change_delay.value; + u32 unit = xfer->cs_change_delay.unit; + int ret; /* return early on "fast" mode - for everything but USECS */ if (!delay) { @@ -1171,27 +1171,13 @@ static void _spi_transfer_cs_change_delay(struct spi_message *msg, return; } - switch (unit) { - case SPI_DELAY_UNIT_USECS: - delay *= 1000; - break; - case SPI_DELAY_UNIT_NSECS: /* nothing to do here */ - break; - case SPI_DELAY_UNIT_SCK: - /* if there is no effective speed know, then approximate - * by underestimating with half the requested hz - */ - hz = xfer->effective_speed_hz ?: xfer->speed_hz / 2; - delay *= DIV_ROUND_UP(1000000000, hz); - break; - default: + ret = spi_delay_exec(&xfer->cs_change_delay, xfer); + if (ret) { dev_err_once(&msg->spi->dev, "Use of unsupported delay unit %i, using default of 10us\n", - xfer->cs_change_delay_unit); - delay = 10000; + unit); + _spi_transfer_delay_ns(10000); } - /* now sleep for the requested amount of time */ - _spi_transfer_delay_ns(delay); } /* diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 8f643de3197b..7670be934643 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -778,7 +778,6 @@ extern void spi_res_release(struct spi_controller *ctlr, * @cs_change: affects chipselect after this transfer completes * @cs_change_delay: delay between cs deassert and assert when * @cs_change is set and @spi_transfer is not the last in @spi_message - * @cs_change_delay_unit: unit of cs_change_delay * @delay_usecs: microseconds to delay after this transfer before * (optionally) changing the chipselect status, then starting * the next transfer or completing this @spi_message. @@ -900,8 +899,7 @@ struct spi_transfer { u8 bits_per_word; u8 word_delay_usecs; u16 delay_usecs; - u16 cs_change_delay; - u8 cs_change_delay_unit; + struct spi_delay cs_change_delay; u32 speed_hz; u16 word_delay; -- cgit v1.2.3-71-gd317 From 84593a131c3af21d686d05c4b4432290a415d399 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 26 Sep 2019 13:51:32 +0300 Subject: spi: sprd: convert transfer word delay to spi_delay struct The Spreadtrum SPI driver is the only user of the `word_delay` field in the `spi_transfer` struct. This change converts the field to use the `spi_delay` struct. This also enforces the users to specify the delay unit to be `SPI_DELAY_UNIT_SCK`. Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20190926105147.7839-5-alexandru.ardelean@analog.com Signed-off-by: Mark Brown --- drivers/spi/spi-sprd.c | 15 ++++++++++++--- include/linux/spi/spi.h | 4 ++-- 2 files changed, 14 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/spi/spi-sprd.c b/drivers/spi/spi-sprd.c index 8c9021b7f7a9..2ee1feb41681 100644 --- a/drivers/spi/spi-sprd.c +++ b/drivers/spi/spi-sprd.c @@ -669,11 +669,15 @@ static void sprd_spi_set_speed(struct sprd_spi *ss, u32 speed_hz) writel_relaxed(clk_div, ss->base + SPRD_SPI_CLKD); } -static void sprd_spi_init_hw(struct sprd_spi *ss, struct spi_transfer *t) +static int sprd_spi_init_hw(struct sprd_spi *ss, struct spi_transfer *t) { + struct spi_delay *d = &t->word_delay; u16 word_delay, interval; u32 val; + if (d->unit != SPI_DELAY_UNIT_SCK) + return -EINVAL; + val = readl_relaxed(ss->base + SPRD_SPI_CTL7); val &= ~(SPRD_SPI_SCK_REV | SPRD_SPI_NG_TX | SPRD_SPI_NG_RX); /* Set default chip selection, clock phase and clock polarity */ @@ -686,7 +690,7 @@ static void sprd_spi_init_hw(struct sprd_spi *ss, struct spi_transfer *t) * formula as below per datasheet: * interval time (source clock cycles) = interval * 4 + 10. */ - word_delay = clamp_t(u16, t->word_delay, SPRD_SPI_MIN_DELAY_CYCLE, + word_delay = clamp_t(u16, d->value, SPRD_SPI_MIN_DELAY_CYCLE, SPRD_SPI_MAX_DELAY_CYCLE); interval = DIV_ROUND_UP(word_delay - 10, 4); ss->word_delay = interval * 4 + 10; @@ -711,6 +715,8 @@ static void sprd_spi_init_hw(struct sprd_spi *ss, struct spi_transfer *t) val &= ~SPRD_SPI_DATA_LINE2_EN; writel_relaxed(val, ss->base + SPRD_SPI_CTL7); + + return 0; } static int sprd_spi_setup_transfer(struct spi_device *sdev, @@ -719,13 +725,16 @@ static int sprd_spi_setup_transfer(struct spi_device *sdev, struct sprd_spi *ss = spi_controller_get_devdata(sdev->controller); u8 bits_per_word = t->bits_per_word; u32 val, mode = 0; + int ret; ss->len = t->len; ss->tx_buf = t->tx_buf; ss->rx_buf = t->rx_buf; ss->hw_mode = sdev->mode; - sprd_spi_init_hw(ss, t); + ret = sprd_spi_init_hw(ss, t); + if (ret) + return ret; /* Set tansfer speed and valid bits */ sprd_spi_set_speed(ss, t->speed_hz); diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 7670be934643..6cb67ad53ffa 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -783,7 +783,7 @@ extern void spi_res_release(struct spi_controller *ctlr, * the next transfer or completing this @spi_message. * @word_delay_usecs: microseconds to inter word delay after each word size * (set by bits_per_word) transmission. - * @word_delay: clock cycles to inter word delay after each word size + * @word_delay: inter word delay to be introduced after each word size * (set by bits_per_word) transmission. * @effective_speed_hz: the effective SCK-speed that was used to * transfer this transfer. Set to 0 if the spi bus driver does @@ -900,8 +900,8 @@ struct spi_transfer { u8 word_delay_usecs; u16 delay_usecs; struct spi_delay cs_change_delay; + struct spi_delay word_delay; u32 speed_hz; - u16 word_delay; u32 effective_speed_hz; -- cgit v1.2.3-71-gd317 From 6c613f68aabf33385c01e949204ac5ed30887161 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 26 Sep 2019 13:51:35 +0300 Subject: spi: core,atmel: convert `word_delay_usecs` -> `word_delay` for spi_device This change does a conversion from the `word_delay_usecs` -> `word_delay` for the `spi_device` struct. This allows users to specify inter-word delays in other unit types (nano-seconds or clock cycles), depending on how users want. The Atmel SPI driver is the only current user of the `word_delay_usecs` field (from the `spi_device` struct). So, it needed a slight conversion to use the `word_delay` as an `spi_delay` struct. In SPI core, the only required mechanism is to update the `word_delay` information per `spi_transfer`. This requires a bit more logic than before, because it needs that both delays be converted to a common unit (nano-seconds) for comparison. Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20190926105147.7839-8-alexandru.ardelean@analog.com Signed-off-by: Mark Brown --- drivers/spi/spi-atmel.c | 26 ++++++++++++++++++++++++-- drivers/spi/spi.c | 24 ++++++++++++++++++++++-- include/linux/spi/spi.h | 7 ++----- 3 files changed, 48 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c index 3ed5e663da6f..1471b049f99a 100644 --- a/drivers/spi/spi-atmel.c +++ b/drivers/spi/spi-atmel.c @@ -1149,12 +1149,31 @@ atmel_spi_pdc_interrupt(int irq, void *dev_id) return ret; } +static int atmel_word_delay_csr(struct spi_device *spi, struct atmel_spi *as) +{ + struct spi_delay *delay = &spi->word_delay; + u32 value = delay->value; + + switch (delay->unit) { + case SPI_DELAY_UNIT_NSECS: + value /= 1000; + break; + case SPI_DELAY_UNIT_USECS: + break; + default: + return -EINVAL; + } + + return (as->spi_clk / 1000000 * value) >> 5; +} + static int atmel_spi_setup(struct spi_device *spi) { struct atmel_spi *as; struct atmel_spi_device *asd; u32 csr; unsigned int bits = spi->bits_per_word; + int word_delay_csr; as = spi_master_get_devdata(spi->master); @@ -1178,11 +1197,14 @@ static int atmel_spi_setup(struct spi_device *spi) */ csr |= SPI_BF(DLYBS, 0); + word_delay_csr = atmel_word_delay_csr(spi, as); + if (word_delay_csr < 0) + return word_delay_csr; + /* DLYBCT adds delays between words. This is useful for slow devices * that need a bit of time to setup the next transfer. */ - csr |= SPI_BF(DLYBCT, - (as->spi_clk / 1000000 * spi->word_delay_usecs) >> 5); + csr |= SPI_BF(DLYBCT, word_delay_csr); asd = spi->controller_state; if (!asd) { diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index b69c14082c52..307e440dd92d 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -3281,6 +3281,26 @@ void spi_set_cs_timing(struct spi_device *spi, u8 setup, u8 hold, } EXPORT_SYMBOL_GPL(spi_set_cs_timing); +static int _spi_xfer_word_delay_update(struct spi_transfer *xfer, + struct spi_device *spi) +{ + int delay1, delay2; + + delay1 = _spi_delay_to_ns(&xfer->word_delay, xfer); + if (delay1 < 0) + return delay1; + + delay2 = _spi_delay_to_ns(&spi->word_delay, xfer); + if (delay2 < 0) + return delay2; + + if (delay1 < delay2) + memcpy(&xfer->word_delay, &spi->word_delay, + sizeof(xfer->word_delay)); + + return 0; +} + static int __spi_validate(struct spi_device *spi, struct spi_message *message) { struct spi_controller *ctlr = spi->controller; @@ -3416,8 +3436,8 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message) return -EINVAL; } - if (xfer->word_delay_usecs < spi->word_delay_usecs) - xfer->word_delay_usecs = spi->word_delay_usecs; + if (_spi_xfer_word_delay_update(xfer, spi)) + return -EINVAL; } message->status = -EINPROGRESS; diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 6cb67ad53ffa..ebeb272aeb0f 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -139,7 +139,7 @@ extern int spi_delay_exec(struct spi_delay *_delay, struct spi_transfer *xfer); * the spi_master. * @cs_gpiod: gpio descriptor of the chipselect line (optional, NULL when * not using a GPIO line) - * @word_delay_usecs: microsecond delay to be inserted between consecutive + * @word_delay: delay to be inserted between consecutive * words of a transfer * * @statistics: statistics for the spi_device @@ -189,7 +189,7 @@ struct spi_device { const char *driver_override; int cs_gpio; /* LEGACY: chip select gpio */ struct gpio_desc *cs_gpiod; /* chip select gpio desc */ - uint8_t word_delay_usecs; /* inter-word delay */ + struct spi_delay word_delay; /* inter-word delay */ /* the statistics */ struct spi_statistics statistics; @@ -781,8 +781,6 @@ extern void spi_res_release(struct spi_controller *ctlr, * @delay_usecs: microseconds to delay after this transfer before * (optionally) changing the chipselect status, then starting * the next transfer or completing this @spi_message. - * @word_delay_usecs: microseconds to inter word delay after each word size - * (set by bits_per_word) transmission. * @word_delay: inter word delay to be introduced after each word size * (set by bits_per_word) transmission. * @effective_speed_hz: the effective SCK-speed that was used to @@ -897,7 +895,6 @@ struct spi_transfer { #define SPI_NBITS_DUAL 0x02 /* 2bits transfer */ #define SPI_NBITS_QUAD 0x04 /* 4bits transfer */ u8 bits_per_word; - u8 word_delay_usecs; u16 delay_usecs; struct spi_delay cs_change_delay; struct spi_delay word_delay; -- cgit v1.2.3-71-gd317 From bebcfd272df648542c458d28fbd6a8f9428b5310 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 26 Sep 2019 13:51:36 +0300 Subject: spi: introduce `delay` field for `spi_transfer` + spi_transfer_delay_exec() The change introduces the `delay` field to the `spi_transfer` struct as an `struct spi_delay` type. This intends to eventually replace `delay_usecs`. But, since there are many users of `delay_usecs`, this needs some intermediate work. A helper called `spi_transfer_delay_exec()` is also added, which maintains backwards compatibility with `delay_usecs`, by assigning the value to `delay` if non-zero. This should maintain backwards compatibility with current users of `udelay_usecs`. Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20190926105147.7839-9-alexandru.ardelean@analog.com Signed-off-by: Mark Brown --- drivers/spi/spi.c | 6 +++--- include/linux/spi/spi.h | 18 ++++++++++++++++++ 2 files changed, 21 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 307e440dd92d..2e448078a117 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1248,8 +1248,7 @@ static int spi_transfer_one_message(struct spi_controller *ctlr, if (msg->status != -EINPROGRESS) goto out; - if (xfer->delay_usecs) - _spi_transfer_delay_ns(xfer->delay_usecs * 1000); + spi_transfer_delay_exec(xfer); if (xfer->cs_change) { if (list_is_last(&xfer->transfer_list, @@ -3026,10 +3025,11 @@ struct spi_replaced_transfers *spi_replace_transfers( /* add to list */ list_add(&xfer->transfer_list, rxfer->replaced_after); - /* clear cs_change and delay_usecs for all but the last */ + /* clear cs_change and delay for all but the last */ if (i) { xfer->cs_change = false; xfer->delay_usecs = 0; + xfer->delay.value = 0; } } diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index ebeb272aeb0f..fe5b85df2c79 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -778,6 +778,9 @@ extern void spi_res_release(struct spi_controller *ctlr, * @cs_change: affects chipselect after this transfer completes * @cs_change_delay: delay between cs deassert and assert when * @cs_change is set and @spi_transfer is not the last in @spi_message + * @delay: delay to be introduced after this transfer before + * (optionally) changing the chipselect status, then starting + * the next transfer or completing this @spi_message. * @delay_usecs: microseconds to delay after this transfer before * (optionally) changing the chipselect status, then starting * the next transfer or completing this @spi_message. @@ -896,6 +899,7 @@ struct spi_transfer { #define SPI_NBITS_QUAD 0x04 /* 4bits transfer */ u8 bits_per_word; u16 delay_usecs; + struct spi_delay delay; struct spi_delay cs_change_delay; struct spi_delay word_delay; u32 speed_hz; @@ -1003,6 +1007,20 @@ spi_transfer_del(struct spi_transfer *t) list_del(&t->transfer_list); } +static inline int +spi_transfer_delay_exec(struct spi_transfer *t) +{ + struct spi_delay d; + + if (t->delay_usecs) { + d.value = t->delay_usecs; + d.unit = SPI_DELAY_UNIT_USECS; + return spi_delay_exec(&d, NULL); + } + + return spi_delay_exec(&t->delay, t); +} + /** * spi_message_init_with_transfers - Initialize spi_message and append transfers * @m: spi_message to be initialized -- cgit v1.2.3-71-gd317 From 8105936684681195d9073880b06a123b2e316811 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 26 Sep 2019 13:51:42 +0300 Subject: spi: tegra114: change format for `spi_set_cs_timing()` function The initial version of `spi_set_cs_timing()` was implemented with consideration only for clock-cycles as delay. For cases like `CS setup` time, it's sometimes needed that micro-seconds (or nano-seconds) are required, or sometimes even longer delays, for cases where the device needs a little longer to start transferring that after CS is asserted. Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20190926105147.7839-15-alexandru.ardelean@analog.com Signed-off-by: Mark Brown --- drivers/spi/spi-tegra114.c | 22 ++++++++++++++++++++-- drivers/spi/spi.c | 16 ++++++++++------ include/linux/spi/spi.h | 9 ++++++--- 3 files changed, 36 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/spi/spi-tegra114.c b/drivers/spi/spi-tegra114.c index 8133dc49d34f..e6a450d9b4f0 100644 --- a/drivers/spi/spi-tegra114.c +++ b/drivers/spi/spi-tegra114.c @@ -723,15 +723,31 @@ static void tegra_spi_deinit_dma_param(struct tegra_spi_data *tspi, dma_release_channel(dma_chan); } -static void tegra_spi_set_hw_cs_timing(struct spi_device *spi, u8 setup_dly, - u8 hold_dly, u8 inactive_dly) +static int tegra_spi_set_hw_cs_timing(struct spi_device *spi, + struct spi_delay *setup, + struct spi_delay *hold, + struct spi_delay *inactive) { struct tegra_spi_data *tspi = spi_master_get_devdata(spi->master); + u8 setup_dly, hold_dly, inactive_dly; u32 setup_hold; u32 spi_cs_timing; u32 inactive_cycles; u8 cs_state; + if ((setup && setup->unit != SPI_DELAY_UNIT_SCK) || + (hold && hold->unit != SPI_DELAY_UNIT_SCK) || + (inactive && inactive->unit != SPI_DELAY_UNIT_SCK)) { + dev_err(&spi->dev, + "Invalid delay unit %d, should be SPI_DELAY_UNIT_SCK\n", + SPI_DELAY_UNIT_SCK); + return -EINVAL; + } + + setup_dly = setup ? setup->value : 0; + hold_dly = hold ? hold->value : 0; + inactive_dly = inactive ? inactive->value : 0; + setup_dly = min_t(u8, setup_dly, MAX_SETUP_HOLD_CYCLES); hold_dly = min_t(u8, hold_dly, MAX_SETUP_HOLD_CYCLES); if (setup_dly && hold_dly) { @@ -758,6 +774,8 @@ static void tegra_spi_set_hw_cs_timing(struct spi_device *spi, u8 setup_dly, tspi->spi_cs_timing2 = spi_cs_timing; tegra_spi_writel(tspi, spi_cs_timing, SPI_CS_TIMING2); } + + return 0; } static u32 tegra_spi_setup_transfer_one(struct spi_device *spi, diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 2e448078a117..6beeb363515c 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -3269,15 +3269,19 @@ EXPORT_SYMBOL_GPL(spi_setup); /** * spi_set_cs_timing - configure CS setup, hold, and inactive delays * @spi: the device that requires specific CS timing configuration - * @setup: CS setup time in terms of clock count - * @hold: CS hold time in terms of clock count - * @inactive_dly: CS inactive delay between transfers in terms of clock count + * @setup: CS setup time specified via @spi_delay + * @hold: CS hold time specified via @spi_delay + * @inactive: CS inactive delay between transfers specified via @spi_delay + * + * Return: zero on success, else a negative error code. */ -void spi_set_cs_timing(struct spi_device *spi, u8 setup, u8 hold, - u8 inactive_dly) +int spi_set_cs_timing(struct spi_device *spi, struct spi_delay *setup, + struct spi_delay *hold, struct spi_delay *inactive) { if (spi->controller->set_cs_timing) - spi->controller->set_cs_timing(spi, setup, hold, inactive_dly); + return spi->controller->set_cs_timing(spi, setup, hold, + inactive); + return -ENOTSUPP; } EXPORT_SYMBOL_GPL(spi_set_cs_timing); diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index fe5b85df2c79..f9b4ba2db08d 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -524,8 +524,8 @@ struct spi_controller { * to configure specific CS timing through spi_set_cs_timing() after * spi_setup(). */ - void (*set_cs_timing)(struct spi_device *spi, u8 setup_clk_cycles, - u8 hold_clk_cycles, u8 inactive_clk_cycles); + int (*set_cs_timing)(struct spi_device *spi, struct spi_delay *setup, + struct spi_delay *hold, struct spi_delay *inactive); /* bidirectional bulk transfers * @@ -1068,7 +1068,10 @@ static inline void spi_message_free(struct spi_message *m) kfree(m); } -extern void spi_set_cs_timing(struct spi_device *spi, u8 setup, u8 hold, u8 inactive_dly); +extern int spi_set_cs_timing(struct spi_device *spi, + struct spi_delay *setup, + struct spi_delay *hold, + struct spi_delay *inactive); extern int spi_setup(struct spi_device *spi); extern int spi_async(struct spi_device *spi, struct spi_message *message); -- cgit v1.2.3-71-gd317 From 25093bdeb6bcae728e12e3795261dbd3677060a9 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 26 Sep 2019 13:51:43 +0300 Subject: spi: implement SW control for CS times This change implements CS control for setup, hold & inactive delays. The `cs_setup` delay is completely new, and can help with cases where asserting the CS, also brings the device out of power-sleep, where there needs to be a longer (than usual), before transferring data. The `cs_hold` time can overlap with the `delay` (or `delay_usecs`) from an SPI transfer. The main difference is that `cs_hold` implies that CS will be de-asserted. The `cs_inactive` delay does not have a clear use-case yet. It has been implemented mostly because the `spi_set_cs_timing()` function implements it. To some degree, this could overlap or replace `cs_change_delay`, but this will require more consideration/investigation in the future. All these delays have been added to the `spi_controller` struct, as they would typically be configured by calling `spi_set_cs_timing()` after an `spi_setup()` call. Software-mode for CS control, implies that the `set_cs_timing()` hook has not been provided for the `spi_controller` object. Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20190926105147.7839-16-alexandru.ardelean@analog.com Signed-off-by: Mark Brown --- drivers/spi/spi.c | 45 ++++++++++++++++++++++++++++++++++++++++++++- include/linux/spi/spi.h | 5 +++++ 2 files changed, 49 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 6beeb363515c..21628b0728f1 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -775,6 +775,15 @@ int spi_register_board_info(struct spi_board_info const *info, unsigned n) static void spi_set_cs(struct spi_device *spi, bool enable) { + bool enable1 = enable; + + if (!spi->controller->set_cs_timing) { + if (enable1) + spi_delay_exec(&spi->controller->cs_setup, NULL); + else + spi_delay_exec(&spi->controller->cs_hold, NULL); + } + if (spi->mode & SPI_CS_HIGH) enable = !enable; @@ -800,6 +809,11 @@ static void spi_set_cs(struct spi_device *spi, bool enable) } else if (spi->controller->set_cs) { spi->controller->set_cs(spi, !enable); } + + if (!spi->controller->set_cs_timing) { + if (!enable1) + spi_delay_exec(&spi->controller->cs_inactive, NULL); + } } #ifdef CONFIG_HAS_DMA @@ -3278,10 +3292,39 @@ EXPORT_SYMBOL_GPL(spi_setup); int spi_set_cs_timing(struct spi_device *spi, struct spi_delay *setup, struct spi_delay *hold, struct spi_delay *inactive) { + size_t len; + if (spi->controller->set_cs_timing) return spi->controller->set_cs_timing(spi, setup, hold, inactive); - return -ENOTSUPP; + + if ((setup && setup->unit == SPI_DELAY_UNIT_SCK) || + (hold && hold->unit == SPI_DELAY_UNIT_SCK) || + (inactive && inactive->unit == SPI_DELAY_UNIT_SCK)) { + dev_err(&spi->dev, + "Clock-cycle delays for CS not supported in SW mode\n"); + return -ENOTSUPP; + } + + len = sizeof(struct spi_delay); + + /* copy delays to controller */ + if (setup) + memcpy(&spi->controller->cs_setup, setup, len); + else + memset(&spi->controller->cs_setup, 0, len); + + if (hold) + memcpy(&spi->controller->cs_hold, hold, len); + else + memset(&spi->controller->cs_hold, 0, len); + + if (inactive) + memcpy(&spi->controller->cs_inactive, inactive, len); + else + memset(&spi->controller->cs_inactive, 0, len); + + return 0; } EXPORT_SYMBOL_GPL(spi_set_cs_timing); diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index f9b4ba2db08d..cfd87b18f077 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -609,6 +609,11 @@ struct spi_controller { /* Optimized handlers for SPI memory-like operations. */ const struct spi_controller_mem_ops *mem_ops; + /* CS delays */ + struct spi_delay cs_setup; + struct spi_delay cs_hold; + struct spi_delay cs_inactive; + /* gpio chip select */ int *cs_gpios; struct gpio_desc **cs_gpiods; -- cgit v1.2.3-71-gd317 From 3984d39b0e41ac4de8b4530ae3911ccf52ed4bbf Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 26 Sep 2019 13:51:44 +0300 Subject: spi: spi-fsl-espi: convert transfer delay to `spi_delay` format The way the max delay is computed for this controller, it looks like it is searching for the max delay from an SPI message a using that. No idea if this is valid. But this change should support both `delay_usecs` and the new `delay` data which is of `spi_delay` type. Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20190926105147.7839-17-alexandru.ardelean@analog.com Signed-off-by: Mark Brown --- drivers/spi/spi-fsl-espi.c | 16 +++++++++++++--- drivers/spi/spi.c | 9 +++++---- include/linux/spi/spi.h | 1 + 3 files changed, 19 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/spi/spi-fsl-espi.c b/drivers/spi/spi-fsl-espi.c index f20326714b9d..f72daf66f3f3 100644 --- a/drivers/spi/spi-fsl-espi.c +++ b/drivers/spi/spi-fsl-espi.c @@ -437,6 +437,7 @@ static int fsl_espi_do_one_msg(struct spi_master *master, struct spi_message *m) { unsigned int delay_usecs = 0, rx_nbits = 0; + unsigned int delay_nsecs = 0, delay_nsecs1 = 0; struct spi_transfer *t, trans = {}; int ret; @@ -445,8 +446,16 @@ static int fsl_espi_do_one_msg(struct spi_master *master, goto out; list_for_each_entry(t, &m->transfers, transfer_list) { - if (t->delay_usecs > delay_usecs) - delay_usecs = t->delay_usecs; + if (t->delay_usecs) { + if (t->delay_usecs > delay_usecs) { + delay_usecs = t->delay_usecs; + delay_nsecs = delay_usecs * 1000; + } + } else { + delay_nsecs1 = spi_delay_to_ns(&t->delay, t); + if (delay_nsecs1 > delay_nsecs) + delay_nsecs = delay_nsecs1; + } if (t->rx_nbits > rx_nbits) rx_nbits = t->rx_nbits; } @@ -457,7 +466,8 @@ static int fsl_espi_do_one_msg(struct spi_master *master, trans.len = m->frame_length; trans.speed_hz = t->speed_hz; trans.bits_per_word = t->bits_per_word; - trans.delay_usecs = delay_usecs; + trans.delay.value = delay_nsecs; + trans.delay.unit = SPI_DELAY_UNIT_NSECS; trans.rx_nbits = rx_nbits; if (trans.len) diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 21628b0728f1..5414a10afd65 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1120,7 +1120,7 @@ static void _spi_transfer_delay_ns(u32 ns) } } -static int _spi_delay_to_ns(struct spi_delay *_delay, struct spi_transfer *xfer) +int spi_delay_to_ns(struct spi_delay *_delay, struct spi_transfer *xfer) { u32 delay = _delay->value; u32 unit = _delay->unit; @@ -1153,6 +1153,7 @@ static int _spi_delay_to_ns(struct spi_delay *_delay, struct spi_transfer *xfer) return delay; } +EXPORT_SYMBOL_GPL(spi_delay_to_ns); int spi_delay_exec(struct spi_delay *_delay, struct spi_transfer *xfer) { @@ -1161,7 +1162,7 @@ int spi_delay_exec(struct spi_delay *_delay, struct spi_transfer *xfer) if (!_delay) return -EINVAL; - delay = _spi_delay_to_ns(_delay, xfer); + delay = spi_delay_to_ns(_delay, xfer); if (delay < 0) return delay; @@ -3333,11 +3334,11 @@ static int _spi_xfer_word_delay_update(struct spi_transfer *xfer, { int delay1, delay2; - delay1 = _spi_delay_to_ns(&xfer->word_delay, xfer); + delay1 = spi_delay_to_ns(&xfer->word_delay, xfer); if (delay1 < 0) return delay1; - delay2 = _spi_delay_to_ns(&spi->word_delay, xfer); + delay2 = spi_delay_to_ns(&spi->word_delay, xfer); if (delay2 < 0) return delay2; diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index cfd87b18f077..c40d6af2bf07 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -103,6 +103,7 @@ struct spi_delay { u8 unit; }; +extern int spi_delay_to_ns(struct spi_delay *_delay, struct spi_transfer *xfer); extern int spi_delay_exec(struct spi_delay *_delay, struct spi_transfer *xfer); /** -- cgit v1.2.3-71-gd317 From f226650494c6aa87526d12135b7de8b8c074f3de Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 2 Oct 2019 10:06:12 +0100 Subject: arm64: Relax ICC_PMR_EL1 accesses when ICC_CTLR_EL1.PMHE is clear The GICv3 architecture specification is incredibly misleading when it comes to PMR and the requirement for a DSB. It turns out that this DSB is only required if the CPU interface sends an Upstream Control message to the redistributor in order to update the RD's view of PMR. This message is only sent when ICC_CTLR_EL1.PMHE is set, which isn't the case in Linux. It can still be set from EL3, so some special care is required. But the upshot is that in the (hopefuly large) majority of the cases, we can drop the DSB altogether. This relies on a new static key being set if the boot CPU has PMHE set. The drawback is that this static key has to be exported to modules. Cc: Will Deacon Cc: James Morse Cc: Julien Thierry Cc: Suzuki K Poulose Signed-off-by: Marc Zyngier Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/barrier.h | 12 ++++++++++++ arch/arm64/include/asm/daifflags.h | 3 ++- arch/arm64/include/asm/irqflags.h | 19 ++++++++++--------- arch/arm64/include/asm/kvm_host.h | 3 +-- arch/arm64/kernel/entry.S | 6 ++++-- arch/arm64/kvm/hyp/switch.c | 4 ++-- drivers/irqchip/irq-gic-v3.c | 20 ++++++++++++++++++++ include/linux/irqchip/arm-gic-v3.h | 2 ++ 8 files changed, 53 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index e0e2b1946f42..7d9cc5ec4971 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -29,6 +29,18 @@ SB_BARRIER_INSN"nop\n", \ ARM64_HAS_SB)) +#ifdef CONFIG_ARM64_PSEUDO_NMI +#define pmr_sync() \ + do { \ + extern struct static_key_false gic_pmr_sync; \ + \ + if (static_branch_unlikely(&gic_pmr_sync)) \ + dsb(sy); \ + } while(0) +#else +#define pmr_sync() do {} while (0) +#endif + #define mb() dsb(sy) #define rmb() dsb(ld) #define wmb() dsb(st) diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h index 063c964af705..53cd5fab79a8 100644 --- a/arch/arm64/include/asm/daifflags.h +++ b/arch/arm64/include/asm/daifflags.h @@ -8,6 +8,7 @@ #include #include +#include #include #define DAIF_PROCCTX 0 @@ -65,7 +66,7 @@ static inline void local_daif_restore(unsigned long flags) if (system_uses_irq_prio_masking()) { gic_write_pmr(GIC_PRIO_IRQON); - dsb(sy); + pmr_sync(); } } else if (system_uses_irq_prio_masking()) { u64 pmr; diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h index 1a59f0ed1ae3..aa4b6521ef14 100644 --- a/arch/arm64/include/asm/irqflags.h +++ b/arch/arm64/include/asm/irqflags.h @@ -6,6 +6,7 @@ #define __ASM_IRQFLAGS_H #include +#include #include #include @@ -34,14 +35,14 @@ static inline void arch_local_irq_enable(void) } asm volatile(ALTERNATIVE( - "msr daifclr, #2 // arch_local_irq_enable\n" - "nop", - __msr_s(SYS_ICC_PMR_EL1, "%0") - "dsb sy", + "msr daifclr, #2 // arch_local_irq_enable", + __msr_s(SYS_ICC_PMR_EL1, "%0"), ARM64_HAS_IRQ_PRIO_MASKING) : : "r" ((unsigned long) GIC_PRIO_IRQON) : "memory"); + + pmr_sync(); } static inline void arch_local_irq_disable(void) @@ -116,14 +117,14 @@ static inline unsigned long arch_local_irq_save(void) static inline void arch_local_irq_restore(unsigned long flags) { asm volatile(ALTERNATIVE( - "msr daif, %0\n" - "nop", - __msr_s(SYS_ICC_PMR_EL1, "%0") - "dsb sy", - ARM64_HAS_IRQ_PRIO_MASKING) + "msr daif, %0", + __msr_s(SYS_ICC_PMR_EL1, "%0"), + ARM64_HAS_IRQ_PRIO_MASKING) : : "r" (flags) : "memory"); + + pmr_sync(); } #endif /* __ASM_IRQFLAGS_H */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index f656169db8c3..5ecb091c8576 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -600,8 +600,7 @@ static inline void kvm_arm_vhe_guest_enter(void) * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU. */ - if (system_uses_irq_prio_masking()) - dsb(sy); + pmr_sync(); } static inline void kvm_arm_vhe_guest_exit(void) diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index e304fe04b098..0a44f21bf087 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -269,8 +269,10 @@ alternative_else_nop_endif alternative_if ARM64_HAS_IRQ_PRIO_MASKING ldr x20, [sp, #S_PMR_SAVE] msr_s SYS_ICC_PMR_EL1, x20 - /* Ensure priority change is seen by redistributor */ - dsb sy + mrs_s x21, SYS_ICC_CTLR_EL1 + tbz x21, #6, .L__skip_pmr_sync\@ // Check for ICC_CTLR_EL1.PMHE + dsb sy // Ensure priority change is seen by redistributor +.L__skip_pmr_sync\@: alternative_else_nop_endif ldp x21, x22, [sp, #S_PC] // load ELR, SPSR diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index 3d3815020e36..402f18664f25 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -12,7 +12,7 @@ #include -#include +#include #include #include #include @@ -592,7 +592,7 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) */ if (system_uses_irq_prio_masking()) { gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); - dsb(sy); + pmr_sync(); } vcpu = kern_hyp_va(vcpu); diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 422664ac5f53..0abc5a13adaa 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -87,6 +87,15 @@ static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key); */ static DEFINE_STATIC_KEY_FALSE(supports_pseudo_nmis); +/* + * Global static key controlling whether an update to PMR allowing more + * interrupts requires to be propagated to the redistributor (DSB SY). + * And this needs to be exported for modules to be able to enable + * interrupts... + */ +DEFINE_STATIC_KEY_FALSE(gic_pmr_sync); +EXPORT_SYMBOL(gic_pmr_sync); + /* ppi_nmi_refs[n] == number of cpus having ppi[n + 16] set as NMI */ static refcount_t *ppi_nmi_refs; @@ -1502,6 +1511,17 @@ static void gic_enable_nmi_support(void) for (i = 0; i < gic_data.ppi_nr; i++) refcount_set(&ppi_nmi_refs[i], 0); + /* + * Linux itself doesn't use 1:N distribution, so has no need to + * set PMHE. The only reason to have it set is if EL3 requires it + * (and we can't change it). + */ + if (gic_read_ctlr() & ICC_CTLR_EL1_PMHE_MASK) + static_branch_enable(&gic_pmr_sync); + + pr_info("%s ICC_PMR_EL1 synchronisation\n", + static_branch_unlikely(&gic_pmr_sync) ? "Forcing" : "Relaxing"); + static_branch_enable(&supports_pseudo_nmis); if (static_branch_likely(&supports_deactivate_key)) diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 5cc10cf7cb3e..a0bde9e12efa 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -487,6 +487,8 @@ #define ICC_CTLR_EL1_EOImode_MASK (1 << ICC_CTLR_EL1_EOImode_SHIFT) #define ICC_CTLR_EL1_CBPR_SHIFT 0 #define ICC_CTLR_EL1_CBPR_MASK (1 << ICC_CTLR_EL1_CBPR_SHIFT) +#define ICC_CTLR_EL1_PMHE_SHIFT 6 +#define ICC_CTLR_EL1_PMHE_MASK (1 << ICC_CTLR_EL1_PMHE_SHIFT) #define ICC_CTLR_EL1_PRI_BITS_SHIFT 8 #define ICC_CTLR_EL1_PRI_BITS_MASK (0x7 << ICC_CTLR_EL1_PRI_BITS_SHIFT) #define ICC_CTLR_EL1_ID_BITS_SHIFT 11 -- cgit v1.2.3-71-gd317 From 4c7c171f85b261f91270d405b7c7390aa6ddfb60 Mon Sep 17 00:00:00 2001 From: Yi L Liu Date: Wed, 2 Oct 2019 12:42:40 -0700 Subject: iommu: Introduce cache_invalidate API In any virtualization use case, when the first translation stage is "owned" by the guest OS, the host IOMMU driver has no knowledge of caching structure updates unless the guest invalidation activities are trapped by the virtualizer and passed down to the host. Since the invalidation data can be obtained from user space and will be written into physical IOMMU, we must allow security check at various layers. Therefore, generic invalidation data format are proposed here, model specific IOMMU drivers need to convert them into their own format. Signed-off-by: Yi L Liu Signed-off-by: Jacob Pan Signed-off-by: Ashok Raj Signed-off-by: Eric Auger Signed-off-by: Jean-Philippe Brucker Reviewed-by: Jean-Philippe Brucker Reviewed-by: Eric Auger Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 10 +++++ include/linux/iommu.h | 14 ++++++ include/uapi/linux/iommu.h | 110 +++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 134 insertions(+) (limited to 'include/linux') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index d658c7c6a2ab..6ca9d28c08bb 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1665,6 +1665,16 @@ out_unlock: } EXPORT_SYMBOL_GPL(iommu_attach_device); +int iommu_cache_invalidate(struct iommu_domain *domain, struct device *dev, + struct iommu_cache_invalidate_info *inv_info) +{ + if (unlikely(!domain->ops->cache_invalidate)) + return -ENODEV; + + return domain->ops->cache_invalidate(domain, dev, inv_info); +} +EXPORT_SYMBOL_GPL(iommu_cache_invalidate); + static void __iommu_detach_device(struct iommu_domain *domain, struct device *dev) { diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 29bac5345563..9b22055e6f85 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -244,6 +244,7 @@ struct iommu_iotlb_gather { * @sva_unbind: Unbind process address space from device * @sva_get_pasid: Get PASID associated to a SVA handle * @page_response: handle page request response + * @cache_invalidate: invalidate translation caches * @pgsize_bitmap: bitmap of all possible supported page sizes */ struct iommu_ops { @@ -306,6 +307,8 @@ struct iommu_ops { int (*page_response)(struct device *dev, struct iommu_fault_event *evt, struct iommu_page_response *msg); + int (*cache_invalidate)(struct iommu_domain *domain, struct device *dev, + struct iommu_cache_invalidate_info *inv_info); unsigned long pgsize_bitmap; }; @@ -417,6 +420,9 @@ extern int iommu_attach_device(struct iommu_domain *domain, struct device *dev); extern void iommu_detach_device(struct iommu_domain *domain, struct device *dev); +extern int iommu_cache_invalidate(struct iommu_domain *domain, + struct device *dev, + struct iommu_cache_invalidate_info *inv_info); extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern struct iommu_domain *iommu_get_dma_domain(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, @@ -1005,6 +1011,14 @@ static inline int iommu_sva_get_pasid(struct iommu_sva *handle) return IOMMU_PASID_INVALID; } +static inline int +iommu_cache_invalidate(struct iommu_domain *domain, + struct device *dev, + struct iommu_cache_invalidate_info *inv_info) +{ + return -ENODEV; +} + #endif /* CONFIG_IOMMU_API */ #ifdef CONFIG_IOMMU_DEBUGFS diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h index fc00c5d4741b..f3e96214df8e 100644 --- a/include/uapi/linux/iommu.h +++ b/include/uapi/linux/iommu.h @@ -152,4 +152,114 @@ struct iommu_page_response { __u32 code; }; +/* defines the granularity of the invalidation */ +enum iommu_inv_granularity { + IOMMU_INV_GRANU_DOMAIN, /* domain-selective invalidation */ + IOMMU_INV_GRANU_PASID, /* PASID-selective invalidation */ + IOMMU_INV_GRANU_ADDR, /* page-selective invalidation */ + IOMMU_INV_GRANU_NR, /* number of invalidation granularities */ +}; + +/** + * struct iommu_inv_addr_info - Address Selective Invalidation Structure + * + * @flags: indicates the granularity of the address-selective invalidation + * - If the PASID bit is set, the @pasid field is populated and the invalidation + * relates to cache entries tagged with this PASID and matching the address + * range. + * - If ARCHID bit is set, @archid is populated and the invalidation relates + * to cache entries tagged with this architecture specific ID and matching + * the address range. + * - Both PASID and ARCHID can be set as they may tag different caches. + * - If neither PASID or ARCHID is set, global addr invalidation applies. + * - The LEAF flag indicates whether only the leaf PTE caching needs to be + * invalidated and other paging structure caches can be preserved. + * @pasid: process address space ID + * @archid: architecture-specific ID + * @addr: first stage/level input address + * @granule_size: page/block size of the mapping in bytes + * @nb_granules: number of contiguous granules to be invalidated + */ +struct iommu_inv_addr_info { +#define IOMMU_INV_ADDR_FLAGS_PASID (1 << 0) +#define IOMMU_INV_ADDR_FLAGS_ARCHID (1 << 1) +#define IOMMU_INV_ADDR_FLAGS_LEAF (1 << 2) + __u32 flags; + __u32 archid; + __u64 pasid; + __u64 addr; + __u64 granule_size; + __u64 nb_granules; +}; + +/** + * struct iommu_inv_pasid_info - PASID Selective Invalidation Structure + * + * @flags: indicates the granularity of the PASID-selective invalidation + * - If the PASID bit is set, the @pasid field is populated and the invalidation + * relates to cache entries tagged with this PASID and matching the address + * range. + * - If the ARCHID bit is set, the @archid is populated and the invalidation + * relates to cache entries tagged with this architecture specific ID and + * matching the address range. + * - Both PASID and ARCHID can be set as they may tag different caches. + * - At least one of PASID or ARCHID must be set. + * @pasid: process address space ID + * @archid: architecture-specific ID + */ +struct iommu_inv_pasid_info { +#define IOMMU_INV_PASID_FLAGS_PASID (1 << 0) +#define IOMMU_INV_PASID_FLAGS_ARCHID (1 << 1) + __u32 flags; + __u32 archid; + __u64 pasid; +}; + +/** + * struct iommu_cache_invalidate_info - First level/stage invalidation + * information + * @version: API version of this structure + * @cache: bitfield that allows to select which caches to invalidate + * @granularity: defines the lowest granularity used for the invalidation: + * domain > PASID > addr + * @padding: reserved for future use (should be zero) + * @pasid_info: invalidation data when @granularity is %IOMMU_INV_GRANU_PASID + * @addr_info: invalidation data when @granularity is %IOMMU_INV_GRANU_ADDR + * + * Not all the combinations of cache/granularity are valid: + * + * +--------------+---------------+---------------+---------------+ + * | type / | DEV_IOTLB | IOTLB | PASID | + * | granularity | | | cache | + * +==============+===============+===============+===============+ + * | DOMAIN | N/A | Y | Y | + * +--------------+---------------+---------------+---------------+ + * | PASID | Y | Y | Y | + * +--------------+---------------+---------------+---------------+ + * | ADDR | Y | Y | N/A | + * +--------------+---------------+---------------+---------------+ + * + * Invalidations by %IOMMU_INV_GRANU_DOMAIN don't take any argument other than + * @version and @cache. + * + * If multiple cache types are invalidated simultaneously, they all + * must support the used granularity. + */ +struct iommu_cache_invalidate_info { +#define IOMMU_CACHE_INVALIDATE_INFO_VERSION_1 1 + __u32 version; +/* IOMMU paging structure cache */ +#define IOMMU_CACHE_INV_TYPE_IOTLB (1 << 0) /* IOMMU IOTLB */ +#define IOMMU_CACHE_INV_TYPE_DEV_IOTLB (1 << 1) /* Device IOTLB */ +#define IOMMU_CACHE_INV_TYPE_PASID (1 << 2) /* PASID cache */ +#define IOMMU_CACHE_INV_TYPE_NR (3) + __u8 cache; + __u8 granularity; + __u8 padding[2]; + union { + struct iommu_inv_pasid_info pasid_info; + struct iommu_inv_addr_info addr_info; + }; +}; + #endif /* _UAPI_IOMMU_H */ -- cgit v1.2.3-71-gd317 From fa83433c92e340822a056a610a4fa2063a3db304 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Wed, 2 Oct 2019 12:42:41 -0700 Subject: iommu: Add I/O ASID allocator Some devices might support multiple DMA address spaces, in particular those that have the PCI PASID feature. PASID (Process Address Space ID) allows to share process address spaces with devices (SVA), partition a device into VM-assignable entities (VFIO mdev) or simply provide multiple DMA address space to kernel drivers. Add a global PASID allocator usable by different drivers at the same time. Name it I/O ASID to avoid confusion with ASIDs allocated by arch code, which are usually a separate ID space. The IOASID space is global. Each device can have its own PASID space, but by convention the IOMMU ended up having a global PASID space, so that with SVA, each mm_struct is associated to a single PASID. The allocator is primarily used by IOMMU subsystem but in rare occasions drivers would like to allocate PASIDs for devices that aren't managed by an IOMMU, using the same ID space as IOMMU. Signed-off-by: Jean-Philippe Brucker Signed-off-by: Jacob Pan Reviewed-by: Jean-Philippe Brucker Reviewed-by: Eric Auger Signed-off-by: Joerg Roedel --- drivers/iommu/Kconfig | 4 ++ drivers/iommu/Makefile | 1 + drivers/iommu/ioasid.c | 151 +++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/ioasid.h | 48 ++++++++++++++++ 4 files changed, 204 insertions(+) create mode 100644 drivers/iommu/ioasid.c create mode 100644 include/linux/ioasid.h (limited to 'include/linux') diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index e3842eabcfdd..fd50ddffffbf 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -3,6 +3,10 @@ config IOMMU_IOVA tristate +# The IOASID library may also be used by non-IOMMU_API users +config IOASID + tristate + # IOMMU_API always gets selected by whoever wants it. config IOMMU_API bool diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index 4f405f926e73..35d17094fe3b 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -7,6 +7,7 @@ obj-$(CONFIG_IOMMU_DMA) += dma-iommu.o obj-$(CONFIG_IOMMU_IO_PGTABLE) += io-pgtable.o obj-$(CONFIG_IOMMU_IO_PGTABLE_ARMV7S) += io-pgtable-arm-v7s.o obj-$(CONFIG_IOMMU_IO_PGTABLE_LPAE) += io-pgtable-arm.o +obj-$(CONFIG_IOASID) += ioasid.o obj-$(CONFIG_IOMMU_IOVA) += iova.o obj-$(CONFIG_OF_IOMMU) += of_iommu.o obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o diff --git a/drivers/iommu/ioasid.c b/drivers/iommu/ioasid.c new file mode 100644 index 000000000000..aadf500c281c --- /dev/null +++ b/drivers/iommu/ioasid.c @@ -0,0 +1,151 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * I/O Address Space ID allocator. There is one global IOASID space, split into + * subsets. Users create a subset with DECLARE_IOASID_SET, then allocate and + * free IOASIDs with ioasid_alloc and ioasid_free. + */ +#include +#include +#include +#include +#include + +struct ioasid_data { + ioasid_t id; + struct ioasid_set *set; + void *private; + struct rcu_head rcu; +}; + +static DEFINE_XARRAY_ALLOC(ioasid_xa); + +/** + * ioasid_set_data - Set private data for an allocated ioasid + * @ioasid: the ID to set data + * @data: the private data + * + * For IOASID that is already allocated, private data can be set + * via this API. Future lookup can be done via ioasid_find. + */ +int ioasid_set_data(ioasid_t ioasid, void *data) +{ + struct ioasid_data *ioasid_data; + int ret = 0; + + xa_lock(&ioasid_xa); + ioasid_data = xa_load(&ioasid_xa, ioasid); + if (ioasid_data) + rcu_assign_pointer(ioasid_data->private, data); + else + ret = -ENOENT; + xa_unlock(&ioasid_xa); + + /* + * Wait for readers to stop accessing the old private data, so the + * caller can free it. + */ + if (!ret) + synchronize_rcu(); + + return ret; +} +EXPORT_SYMBOL_GPL(ioasid_set_data); + +/** + * ioasid_alloc - Allocate an IOASID + * @set: the IOASID set + * @min: the minimum ID (inclusive) + * @max: the maximum ID (inclusive) + * @private: data private to the caller + * + * Allocate an ID between @min and @max. The @private pointer is stored + * internally and can be retrieved with ioasid_find(). + * + * Return: the allocated ID on success, or %INVALID_IOASID on failure. + */ +ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max, + void *private) +{ + struct ioasid_data *data; + ioasid_t id; + + data = kzalloc(sizeof(*data), GFP_ATOMIC); + if (!data) + return INVALID_IOASID; + + data->set = set; + data->private = private; + + if (xa_alloc(&ioasid_xa, &id, data, XA_LIMIT(min, max), GFP_KERNEL)) { + pr_err("Failed to alloc ioasid from %d to %d\n", min, max); + goto exit_free; + } + data->id = id; + + return id; +exit_free: + kfree(data); + return INVALID_IOASID; +} +EXPORT_SYMBOL_GPL(ioasid_alloc); + +/** + * ioasid_free - Free an IOASID + * @ioasid: the ID to remove + */ +void ioasid_free(ioasid_t ioasid) +{ + struct ioasid_data *ioasid_data; + + ioasid_data = xa_erase(&ioasid_xa, ioasid); + + kfree_rcu(ioasid_data, rcu); +} +EXPORT_SYMBOL_GPL(ioasid_free); + +/** + * ioasid_find - Find IOASID data + * @set: the IOASID set + * @ioasid: the IOASID to find + * @getter: function to call on the found object + * + * The optional getter function allows to take a reference to the found object + * under the rcu lock. The function can also check if the object is still valid: + * if @getter returns false, then the object is invalid and NULL is returned. + * + * If the IOASID exists, return the private pointer passed to ioasid_alloc. + * Private data can be NULL if not set. Return an error if the IOASID is not + * found, or if @set is not NULL and the IOASID does not belong to the set. + */ +void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, + bool (*getter)(void *)) +{ + void *priv; + struct ioasid_data *ioasid_data; + + rcu_read_lock(); + ioasid_data = xa_load(&ioasid_xa, ioasid); + if (!ioasid_data) { + priv = ERR_PTR(-ENOENT); + goto unlock; + } + if (set && ioasid_data->set != set) { + /* data found but does not belong to the set */ + priv = ERR_PTR(-EACCES); + goto unlock; + } + /* Now IOASID and its set is verified, we can return the private data */ + priv = rcu_dereference(ioasid_data->private); + if (getter && !getter(priv)) + priv = NULL; +unlock: + rcu_read_unlock(); + + return priv; +} +EXPORT_SYMBOL_GPL(ioasid_find); + +MODULE_AUTHOR("Jean-Philippe Brucker "); +MODULE_AUTHOR("Jacob Pan "); +MODULE_DESCRIPTION("IO Address Space ID (IOASID) allocator"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/ioasid.h b/include/linux/ioasid.h new file mode 100644 index 000000000000..17337a13f06e --- /dev/null +++ b/include/linux/ioasid.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_IOASID_H +#define __LINUX_IOASID_H + +#include +#include + +#define INVALID_IOASID ((ioasid_t)-1) +typedef unsigned int ioasid_t; + +struct ioasid_set { + int dummy; +}; + +#define DECLARE_IOASID_SET(name) struct ioasid_set name = { 0 } + +#if IS_ENABLED(CONFIG_IOASID) +ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max, + void *private); +void ioasid_free(ioasid_t ioasid); +void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, + bool (*getter)(void *)); +int ioasid_set_data(ioasid_t ioasid, void *data); + +#else /* !CONFIG_IOASID */ +static inline ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, + ioasid_t max, void *private) +{ + return INVALID_IOASID; +} + +static inline void ioasid_free(ioasid_t ioasid) +{ +} + +static inline void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, + bool (*getter)(void *)) +{ + return NULL; +} + +static inline int ioasid_set_data(ioasid_t ioasid, void *data) +{ + return -ENOTSUPP; +} + +#endif /* CONFIG_IOASID */ +#endif /* __LINUX_IOASID_H */ -- cgit v1.2.3-71-gd317 From e5c0bd7f2206cd288029edb6afbfde93c73b4048 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Wed, 2 Oct 2019 12:42:42 -0700 Subject: iommu/ioasid: Add custom allocators IOASID allocation may rely on platform specific methods. One use case is that when running in the guest, in order to obtain system wide global IOASIDs, emulated allocation interface is needed to communicate with the host. Here we call these platform specific allocators custom allocators. Custom IOASID allocators can be registered at runtime and take precedence over the default XArray allocator. They have these attributes: - provides platform specific alloc()/free() functions with private data. - allocation results lookup are not provided by the allocator, lookup request must be done by the IOASID framework by its own XArray. - allocators can be unregistered at runtime, either fallback to the next custom allocator or to the default allocator. - custom allocators can share the same set of alloc()/free() helpers, in this case they also share the same IOASID space, thus the same XArray. - switching between allocators requires all outstanding IOASIDs to be freed unless the two allocators share the same alloc()/free() helpers. Signed-off-by: Jean-Philippe Brucker Signed-off-by: Jacob Pan Link: https://lkml.org/lkml/2019/4/26/462 Reviewed-by: Jean-Philippe Brucker Reviewed-by: Eric Auger Signed-off-by: Joerg Roedel --- drivers/iommu/ioasid.c | 289 +++++++++++++++++++++++++++++++++++++++++++++++-- include/linux/ioasid.h | 28 +++++ 2 files changed, 308 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/ioasid.c b/drivers/iommu/ioasid.c index aadf500c281c..0f8dd377aada 100644 --- a/drivers/iommu/ioasid.c +++ b/drivers/iommu/ioasid.c @@ -17,7 +17,245 @@ struct ioasid_data { struct rcu_head rcu; }; -static DEFINE_XARRAY_ALLOC(ioasid_xa); +/* + * struct ioasid_allocator_data - Internal data structure to hold information + * about an allocator. There are two types of allocators: + * + * - Default allocator always has its own XArray to track the IOASIDs allocated. + * - Custom allocators may share allocation helpers with different private data. + * Custom allocators that share the same helper functions also share the same + * XArray. + * Rules: + * 1. Default allocator is always available, not dynamically registered. This is + * to prevent race conditions with early boot code that want to register + * custom allocators or allocate IOASIDs. + * 2. Custom allocators take precedence over the default allocator. + * 3. When all custom allocators sharing the same helper functions are + * unregistered (e.g. due to hotplug), all outstanding IOASIDs must be + * freed. Otherwise, outstanding IOASIDs will be lost and orphaned. + * 4. When switching between custom allocators sharing the same helper + * functions, outstanding IOASIDs are preserved. + * 5. When switching between custom allocator and default allocator, all IOASIDs + * must be freed to ensure unadulterated space for the new allocator. + * + * @ops: allocator helper functions and its data + * @list: registered custom allocators + * @slist: allocators share the same ops but different data + * @flags: attributes of the allocator + * @xa: xarray holds the IOASID space + * @rcu: used for kfree_rcu when unregistering allocator + */ +struct ioasid_allocator_data { + struct ioasid_allocator_ops *ops; + struct list_head list; + struct list_head slist; +#define IOASID_ALLOCATOR_CUSTOM BIT(0) /* Needs framework to track results */ + unsigned long flags; + struct xarray xa; + struct rcu_head rcu; +}; + +static DEFINE_SPINLOCK(ioasid_allocator_lock); +static LIST_HEAD(allocators_list); + +static ioasid_t default_alloc(ioasid_t min, ioasid_t max, void *opaque); +static void default_free(ioasid_t ioasid, void *opaque); + +static struct ioasid_allocator_ops default_ops = { + .alloc = default_alloc, + .free = default_free, +}; + +static struct ioasid_allocator_data default_allocator = { + .ops = &default_ops, + .flags = 0, + .xa = XARRAY_INIT(ioasid_xa, XA_FLAGS_ALLOC), +}; + +static struct ioasid_allocator_data *active_allocator = &default_allocator; + +static ioasid_t default_alloc(ioasid_t min, ioasid_t max, void *opaque) +{ + ioasid_t id; + + if (xa_alloc(&default_allocator.xa, &id, opaque, XA_LIMIT(min, max), GFP_ATOMIC)) { + pr_err("Failed to alloc ioasid from %d to %d\n", min, max); + return INVALID_IOASID; + } + + return id; +} + +static void default_free(ioasid_t ioasid, void *opaque) +{ + struct ioasid_data *ioasid_data; + + ioasid_data = xa_erase(&default_allocator.xa, ioasid); + kfree_rcu(ioasid_data, rcu); +} + +/* Allocate and initialize a new custom allocator with its helper functions */ +static struct ioasid_allocator_data *ioasid_alloc_allocator(struct ioasid_allocator_ops *ops) +{ + struct ioasid_allocator_data *ia_data; + + ia_data = kzalloc(sizeof(*ia_data), GFP_ATOMIC); + if (!ia_data) + return NULL; + + xa_init_flags(&ia_data->xa, XA_FLAGS_ALLOC); + INIT_LIST_HEAD(&ia_data->slist); + ia_data->flags |= IOASID_ALLOCATOR_CUSTOM; + ia_data->ops = ops; + + /* For tracking custom allocators that share the same ops */ + list_add_tail(&ops->list, &ia_data->slist); + + return ia_data; +} + +static bool use_same_ops(struct ioasid_allocator_ops *a, struct ioasid_allocator_ops *b) +{ + return (a->free == b->free) && (a->alloc == b->alloc); +} + +/** + * ioasid_register_allocator - register a custom allocator + * @ops: the custom allocator ops to be registered + * + * Custom allocators take precedence over the default xarray based allocator. + * Private data associated with the IOASID allocated by the custom allocators + * are managed by IOASID framework similar to data stored in xa by default + * allocator. + * + * There can be multiple allocators registered but only one is active. In case + * of runtime removal of a custom allocator, the next one is activated based + * on the registration ordering. + * + * Multiple allocators can share the same alloc() function, in this case the + * IOASID space is shared. + */ +int ioasid_register_allocator(struct ioasid_allocator_ops *ops) +{ + struct ioasid_allocator_data *ia_data; + struct ioasid_allocator_data *pallocator; + int ret = 0; + + spin_lock(&ioasid_allocator_lock); + + ia_data = ioasid_alloc_allocator(ops); + if (!ia_data) { + ret = -ENOMEM; + goto out_unlock; + } + + /* + * No particular preference, we activate the first one and keep + * the later registered allocators in a list in case the first one gets + * removed due to hotplug. + */ + if (list_empty(&allocators_list)) { + WARN_ON(active_allocator != &default_allocator); + /* Use this new allocator if default is not active */ + if (xa_empty(&active_allocator->xa)) { + rcu_assign_pointer(active_allocator, ia_data); + list_add_tail(&ia_data->list, &allocators_list); + goto out_unlock; + } + pr_warn("Default allocator active with outstanding IOASID\n"); + ret = -EAGAIN; + goto out_free; + } + + /* Check if the allocator is already registered */ + list_for_each_entry(pallocator, &allocators_list, list) { + if (pallocator->ops == ops) { + pr_err("IOASID allocator already registered\n"); + ret = -EEXIST; + goto out_free; + } else if (use_same_ops(pallocator->ops, ops)) { + /* + * If the new allocator shares the same ops, + * then they will share the same IOASID space. + * We should put them under the same xarray. + */ + list_add_tail(&ops->list, &pallocator->slist); + goto out_free; + } + } + list_add_tail(&ia_data->list, &allocators_list); + + spin_unlock(&ioasid_allocator_lock); + return 0; +out_free: + kfree(ia_data); +out_unlock: + spin_unlock(&ioasid_allocator_lock); + return ret; +} +EXPORT_SYMBOL_GPL(ioasid_register_allocator); + +/** + * ioasid_unregister_allocator - Remove a custom IOASID allocator ops + * @ops: the custom allocator to be removed + * + * Remove an allocator from the list, activate the next allocator in + * the order it was registered. Or revert to default allocator if all + * custom allocators are unregistered without outstanding IOASIDs. + */ +void ioasid_unregister_allocator(struct ioasid_allocator_ops *ops) +{ + struct ioasid_allocator_data *pallocator; + struct ioasid_allocator_ops *sops; + + spin_lock(&ioasid_allocator_lock); + if (list_empty(&allocators_list)) { + pr_warn("No custom IOASID allocators active!\n"); + goto exit_unlock; + } + + list_for_each_entry(pallocator, &allocators_list, list) { + if (!use_same_ops(pallocator->ops, ops)) + continue; + + if (list_is_singular(&pallocator->slist)) { + /* No shared helper functions */ + list_del(&pallocator->list); + /* + * All IOASIDs should have been freed before + * the last allocator that shares the same ops + * is unregistered. + */ + WARN_ON(!xa_empty(&pallocator->xa)); + if (list_empty(&allocators_list)) { + pr_info("No custom IOASID allocators, switch to default.\n"); + rcu_assign_pointer(active_allocator, &default_allocator); + } else if (pallocator == active_allocator) { + rcu_assign_pointer(active_allocator, + list_first_entry(&allocators_list, + struct ioasid_allocator_data, list)); + pr_info("IOASID allocator changed"); + } + kfree_rcu(pallocator, rcu); + break; + } + /* + * Find the matching shared ops to delete, + * but keep outstanding IOASIDs + */ + list_for_each_entry(sops, &pallocator->slist, list) { + if (sops == ops) { + list_del(&ops->list); + break; + } + } + break; + } + +exit_unlock: + spin_unlock(&ioasid_allocator_lock); +} +EXPORT_SYMBOL_GPL(ioasid_unregister_allocator); /** * ioasid_set_data - Set private data for an allocated ioasid @@ -32,13 +270,13 @@ int ioasid_set_data(ioasid_t ioasid, void *data) struct ioasid_data *ioasid_data; int ret = 0; - xa_lock(&ioasid_xa); - ioasid_data = xa_load(&ioasid_xa, ioasid); + spin_lock(&ioasid_allocator_lock); + ioasid_data = xa_load(&active_allocator->xa, ioasid); if (ioasid_data) rcu_assign_pointer(ioasid_data->private, data); else ret = -ENOENT; - xa_unlock(&ioasid_xa); + spin_unlock(&ioasid_allocator_lock); /* * Wait for readers to stop accessing the old private data, so the @@ -67,6 +305,7 @@ ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max, void *private) { struct ioasid_data *data; + void *adata; ioasid_t id; data = kzalloc(sizeof(*data), GFP_ATOMIC); @@ -76,14 +315,31 @@ ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max, data->set = set; data->private = private; - if (xa_alloc(&ioasid_xa, &id, data, XA_LIMIT(min, max), GFP_KERNEL)) { - pr_err("Failed to alloc ioasid from %d to %d\n", min, max); + /* + * Custom allocator needs allocator data to perform platform specific + * operations. + */ + spin_lock(&ioasid_allocator_lock); + adata = active_allocator->flags & IOASID_ALLOCATOR_CUSTOM ? active_allocator->ops->pdata : data; + id = active_allocator->ops->alloc(min, max, adata); + if (id == INVALID_IOASID) { + pr_err("Failed ASID allocation %lu\n", active_allocator->flags); + goto exit_free; + } + + if ((active_allocator->flags & IOASID_ALLOCATOR_CUSTOM) && + xa_alloc(&active_allocator->xa, &id, data, XA_LIMIT(id, id), GFP_ATOMIC)) { + /* Custom allocator needs framework to store and track allocation results */ + pr_err("Failed to alloc ioasid from %d\n", id); + active_allocator->ops->free(id, active_allocator->ops->pdata); goto exit_free; } data->id = id; + spin_unlock(&ioasid_allocator_lock); return id; exit_free: + spin_unlock(&ioasid_allocator_lock); kfree(data); return INVALID_IOASID; } @@ -97,9 +353,22 @@ void ioasid_free(ioasid_t ioasid) { struct ioasid_data *ioasid_data; - ioasid_data = xa_erase(&ioasid_xa, ioasid); + spin_lock(&ioasid_allocator_lock); + ioasid_data = xa_load(&active_allocator->xa, ioasid); + if (!ioasid_data) { + pr_err("Trying to free unknown IOASID %u\n", ioasid); + goto exit_unlock; + } - kfree_rcu(ioasid_data, rcu); + active_allocator->ops->free(ioasid, active_allocator->ops->pdata); + /* Custom allocator needs additional steps to free the xa element */ + if (active_allocator->flags & IOASID_ALLOCATOR_CUSTOM) { + ioasid_data = xa_erase(&active_allocator->xa, ioasid); + kfree_rcu(ioasid_data, rcu); + } + +exit_unlock: + spin_unlock(&ioasid_allocator_lock); } EXPORT_SYMBOL_GPL(ioasid_free); @@ -122,9 +391,11 @@ void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, { void *priv; struct ioasid_data *ioasid_data; + struct ioasid_allocator_data *idata; rcu_read_lock(); - ioasid_data = xa_load(&ioasid_xa, ioasid); + idata = rcu_dereference(active_allocator); + ioasid_data = xa_load(&idata->xa, ioasid); if (!ioasid_data) { priv = ERR_PTR(-ENOENT); goto unlock; diff --git a/include/linux/ioasid.h b/include/linux/ioasid.h index 17337a13f06e..6f000d7a0ddc 100644 --- a/include/linux/ioasid.h +++ b/include/linux/ioasid.h @@ -7,11 +7,28 @@ #define INVALID_IOASID ((ioasid_t)-1) typedef unsigned int ioasid_t; +typedef ioasid_t (*ioasid_alloc_fn_t)(ioasid_t min, ioasid_t max, void *data); +typedef void (*ioasid_free_fn_t)(ioasid_t ioasid, void *data); struct ioasid_set { int dummy; }; +/** + * struct ioasid_allocator_ops - IOASID allocator helper functions and data + * + * @alloc: helper function to allocate IOASID + * @free: helper function to free IOASID + * @list: for tracking ops that share helper functions but not data + * @pdata: data belong to the allocator, provided when calling alloc() + */ +struct ioasid_allocator_ops { + ioasid_alloc_fn_t alloc; + ioasid_free_fn_t free; + struct list_head list; + void *pdata; +}; + #define DECLARE_IOASID_SET(name) struct ioasid_set name = { 0 } #if IS_ENABLED(CONFIG_IOASID) @@ -20,6 +37,8 @@ ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max, void ioasid_free(ioasid_t ioasid); void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, bool (*getter)(void *)); +int ioasid_register_allocator(struct ioasid_allocator_ops *allocator); +void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator); int ioasid_set_data(ioasid_t ioasid, void *data); #else /* !CONFIG_IOASID */ @@ -39,6 +58,15 @@ static inline void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, return NULL; } +static inline int ioasid_register_allocator(struct ioasid_allocator_ops *allocator) +{ + return -ENOTSUPP; +} + +static inline void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator) +{ +} + static inline int ioasid_set_data(ioasid_t ioasid, void *data) { return -ENOTSUPP; -- cgit v1.2.3-71-gd317 From 808be0aae53a3675337fad9cde616e086bdc8287 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Wed, 2 Oct 2019 12:42:43 -0700 Subject: iommu: Introduce guest PASID bind function Guest shared virtual address (SVA) may require host to shadow guest PASID tables. Guest PASID can also be allocated from the host via enlightened interfaces. In this case, guest needs to bind the guest mm, i.e. cr3 in guest physical address to the actual PASID table in the host IOMMU. Nesting will be turned on such that guest virtual address can go through a two level translation: - 1st level translates GVA to GPA - 2nd level translates GPA to HPA This patch introduces APIs to bind guest PASID data to the assigned device entry in the physical IOMMU. See the diagram below for usage explanation. .-------------. .---------------------------. | vIOMMU | | Guest process mm, FL only | | | '---------------------------' .----------------/ | PASID Entry |--- PASID cache flush - '-------------' | | | V | | GP '-------------' Guest ------| Shadow |----------------------- GP->HP* --------- v v | Host v .-------------. .----------------------. | pIOMMU | | Bind FL for GVA-GPA | | | '----------------------' .----------------/ | | PASID Entry | V (Nested xlate) '----------------\.---------------------. | | |Set SL to GPA-HPA | | | '---------------------' '-------------' Where: - FL = First level/stage one page tables - SL = Second level/stage two page tables - GP = Guest PASID - HP = Host PASID * Conversion needed if non-identity GP-HP mapping option is chosen. Signed-off-by: Jacob Pan Signed-off-by: Liu Yi L Reviewed-by: Jean-Philippe Brucker Reviewed-by: Jean-Philippe Brucker Reviewed-by: Eric Auger Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 20 ++++++++++++++++ include/linux/iommu.h | 22 +++++++++++++++++ include/uapi/linux/iommu.h | 59 ++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 101 insertions(+) (limited to 'include/linux') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 6ca9d28c08bb..4486c4e6830a 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1675,6 +1675,26 @@ int iommu_cache_invalidate(struct iommu_domain *domain, struct device *dev, } EXPORT_SYMBOL_GPL(iommu_cache_invalidate); +int iommu_sva_bind_gpasid(struct iommu_domain *domain, + struct device *dev, struct iommu_gpasid_bind_data *data) +{ + if (unlikely(!domain->ops->sva_bind_gpasid)) + return -ENODEV; + + return domain->ops->sva_bind_gpasid(domain, dev, data); +} +EXPORT_SYMBOL_GPL(iommu_sva_bind_gpasid); + +int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev, + ioasid_t pasid) +{ + if (unlikely(!domain->ops->sva_unbind_gpasid)) + return -ENODEV; + + return domain->ops->sva_unbind_gpasid(dev, pasid); +} +EXPORT_SYMBOL_GPL(iommu_sva_unbind_gpasid); + static void __iommu_detach_device(struct iommu_domain *domain, struct device *dev) { diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 9b22055e6f85..f8959f759e41 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #define IOMMU_READ (1 << 0) @@ -246,6 +247,8 @@ struct iommu_iotlb_gather { * @page_response: handle page request response * @cache_invalidate: invalidate translation caches * @pgsize_bitmap: bitmap of all possible supported page sizes + * @sva_bind_gpasid: bind guest pasid and mm + * @sva_unbind_gpasid: unbind guest pasid and mm */ struct iommu_ops { bool (*capable)(enum iommu_cap); @@ -309,6 +312,10 @@ struct iommu_ops { struct iommu_page_response *msg); int (*cache_invalidate)(struct iommu_domain *domain, struct device *dev, struct iommu_cache_invalidate_info *inv_info); + int (*sva_bind_gpasid)(struct iommu_domain *domain, + struct device *dev, struct iommu_gpasid_bind_data *data); + + int (*sva_unbind_gpasid)(struct device *dev, int pasid); unsigned long pgsize_bitmap; }; @@ -423,6 +430,10 @@ extern void iommu_detach_device(struct iommu_domain *domain, extern int iommu_cache_invalidate(struct iommu_domain *domain, struct device *dev, struct iommu_cache_invalidate_info *inv_info); +extern int iommu_sva_bind_gpasid(struct iommu_domain *domain, + struct device *dev, struct iommu_gpasid_bind_data *data); +extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain, + struct device *dev, ioasid_t pasid); extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern struct iommu_domain *iommu_get_dma_domain(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, @@ -1018,6 +1029,17 @@ iommu_cache_invalidate(struct iommu_domain *domain, { return -ENODEV; } +static inline int iommu_sva_bind_gpasid(struct iommu_domain *domain, + struct device *dev, struct iommu_gpasid_bind_data *data) +{ + return -ENODEV; +} + +static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain, + struct device *dev, int pasid) +{ + return -ENODEV; +} #endif /* CONFIG_IOMMU_API */ diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h index f3e96214df8e..4ad3496e5c43 100644 --- a/include/uapi/linux/iommu.h +++ b/include/uapi/linux/iommu.h @@ -262,4 +262,63 @@ struct iommu_cache_invalidate_info { }; }; +/** + * struct iommu_gpasid_bind_data_vtd - Intel VT-d specific data on device and guest + * SVA binding. + * + * @flags: VT-d PASID table entry attributes + * @pat: Page attribute table data to compute effective memory type + * @emt: Extended memory type + * + * Only guest vIOMMU selectable and effective options are passed down to + * the host IOMMU. + */ +struct iommu_gpasid_bind_data_vtd { +#define IOMMU_SVA_VTD_GPASID_SRE (1 << 0) /* supervisor request */ +#define IOMMU_SVA_VTD_GPASID_EAFE (1 << 1) /* extended access enable */ +#define IOMMU_SVA_VTD_GPASID_PCD (1 << 2) /* page-level cache disable */ +#define IOMMU_SVA_VTD_GPASID_PWT (1 << 3) /* page-level write through */ +#define IOMMU_SVA_VTD_GPASID_EMTE (1 << 4) /* extended mem type enable */ +#define IOMMU_SVA_VTD_GPASID_CD (1 << 5) /* PASID-level cache disable */ + __u64 flags; + __u32 pat; + __u32 emt; +}; + +/** + * struct iommu_gpasid_bind_data - Information about device and guest PASID binding + * @version: Version of this data structure + * @format: PASID table entry format + * @flags: Additional information on guest bind request + * @gpgd: Guest page directory base of the guest mm to bind + * @hpasid: Process address space ID used for the guest mm in host IOMMU + * @gpasid: Process address space ID used for the guest mm in guest IOMMU + * @addr_width: Guest virtual address width + * @padding: Reserved for future use (should be zero) + * @vtd: Intel VT-d specific data + * + * Guest to host PASID mapping can be an identity or non-identity, where guest + * has its own PASID space. For non-identify mapping, guest to host PASID lookup + * is needed when VM programs guest PASID into an assigned device. VMM may + * trap such PASID programming then request host IOMMU driver to convert guest + * PASID to host PASID based on this bind data. + */ +struct iommu_gpasid_bind_data { +#define IOMMU_GPASID_BIND_VERSION_1 1 + __u32 version; +#define IOMMU_PASID_FORMAT_INTEL_VTD 1 + __u32 format; +#define IOMMU_SVA_GPASID_VAL (1 << 0) /* guest PASID valid */ + __u64 flags; + __u64 gpgd; + __u64 hpasid; + __u64 gpasid; + __u32 addr_width; + __u8 padding[12]; + /* Vendor specific data */ + union { + struct iommu_gpasid_bind_data_vtd vtd; + }; +}; + #endif /* _UAPI_IOMMU_H */ -- cgit v1.2.3-71-gd317 From 13ef954445df4fd1d7c003a500ec5ce49573e14b Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 15 Oct 2019 08:43:42 -0700 Subject: iomap: Allow forcing of waiting for running DIO in iomap_dio_rw() Filesystems do not support doing IO as asynchronous in some cases. For example in case of unaligned writes or in case file size needs to be extended (e.g. for ext4). Instead of forcing filesystem to wait for AIO in such cases, add argument to iomap_dio_rw() which makes the function wait for IO completion. This also results in executing iomap_dio_complete() inline in iomap_dio_rw() providing its return value to the caller as for ordinary sync IO. Signed-off-by: Jan Kara Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/gfs2/file.c | 6 ++++-- fs/iomap/direct-io.c | 7 +++++-- fs/xfs/xfs_file.c | 5 +++-- include/linux/iomap.h | 3 ++- 4 files changed, 14 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 997b326247e2..f0caee2b7c00 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -732,7 +732,8 @@ static ssize_t gfs2_file_direct_read(struct kiocb *iocb, struct iov_iter *to) if (ret) goto out_uninit; - ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL); + ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL, + is_sync_kiocb(iocb)); gfs2_glock_dq(&gh); out_uninit: @@ -767,7 +768,8 @@ static ssize_t gfs2_file_direct_write(struct kiocb *iocb, struct iov_iter *from) if (offset + len > i_size_read(&ip->i_inode)) goto out; - ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL); + ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL, + is_sync_kiocb(iocb)); out: gfs2_glock_dq(&gh); diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 1fc28c2da279..da124cee1783 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -392,7 +392,8 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length, */ ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, - const struct iomap_ops *ops, const struct iomap_dio_ops *dops) + const struct iomap_ops *ops, const struct iomap_dio_ops *dops, + bool wait_for_completion) { struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = file_inode(iocb->ki_filp); @@ -400,7 +401,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, loff_t pos = iocb->ki_pos, start = pos; loff_t end = iocb->ki_pos + count - 1, ret = 0; unsigned int flags = IOMAP_DIRECT; - bool wait_for_completion = is_sync_kiocb(iocb); struct blk_plug plug; struct iomap_dio *dio; @@ -409,6 +409,9 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (!count) return 0; + if (WARN_ON(is_sync_kiocb(iocb) && !wait_for_completion)) + return -EIO; + dio = kmalloc(sizeof(*dio), GFP_KERNEL); if (!dio) return -ENOMEM; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 1ffb179f35d2..0739ba72a82e 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -188,7 +188,7 @@ xfs_file_dio_aio_read( file_accessed(iocb->ki_filp); xfs_ilock(ip, XFS_IOLOCK_SHARED); - ret = iomap_dio_rw(iocb, to, &xfs_iomap_ops, NULL); + ret = iomap_dio_rw(iocb, to, &xfs_iomap_ops, NULL, is_sync_kiocb(iocb)); xfs_iunlock(ip, XFS_IOLOCK_SHARED); return ret; @@ -547,7 +547,8 @@ xfs_file_dio_aio_write( } trace_xfs_file_direct_write(ip, count, iocb->ki_pos); - ret = iomap_dio_rw(iocb, from, &xfs_iomap_ops, &xfs_dio_write_ops); + ret = iomap_dio_rw(iocb, from, &xfs_iomap_ops, &xfs_dio_write_ops, + is_sync_kiocb(iocb)); /* * If unaligned, this is the only IO in-flight. If it has not yet diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 7aa5d6117936..76b14cb729dc 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -195,7 +195,8 @@ struct iomap_dio_ops { }; ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, - const struct iomap_ops *ops, const struct iomap_dio_ops *dops); + const struct iomap_ops *ops, const struct iomap_dio_ops *dops, + bool wait_for_completion); int iomap_dio_iopoll(struct kiocb *kiocb, bool spin); #ifdef CONFIG_SWAP -- cgit v1.2.3-71-gd317 From aff5d0552da4055da3faa27ee4252e48bb1f5821 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sat, 5 Oct 2019 14:04:36 +0200 Subject: PCI/ASPM: Add L1 PM substate support to pci_disable_link_state() Add support for disabling states L1.1 and L1.2 to pci_disable_link_state(). Allow separate control of ASPM and PCI PM L1 substates. Link: https://lore.kernel.org/r/d81f8036-c236-6463-48e7-ebcdcda85bba@gmail.com Signed-off-by: Heiner Kallweit Signed-off-by: Bjorn Helgaas --- drivers/pci/pcie/aspm.c | 11 ++++++++++- include/linux/pci.h | 10 +++++++--- 2 files changed, 17 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index f5c7138a34aa..f8572a523a15 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -1094,7 +1094,16 @@ static int __pci_disable_link_state(struct pci_dev *pdev, int state, bool sem) if (state & PCIE_LINK_STATE_L0S) link->aspm_disable |= ASPM_STATE_L0S; if (state & PCIE_LINK_STATE_L1) - link->aspm_disable |= ASPM_STATE_L1; + /* L1 PM substates require L1 */ + link->aspm_disable |= ASPM_STATE_L1 | ASPM_STATE_L1SS; + if (state & PCIE_LINK_STATE_L1_1) + link->aspm_disable |= ASPM_STATE_L1_1; + if (state & PCIE_LINK_STATE_L1_2) + link->aspm_disable |= ASPM_STATE_L1_2; + if (state & PCIE_LINK_STATE_L1_1_PCIPM) + link->aspm_disable |= ASPM_STATE_L1_1_PCIPM; + if (state & PCIE_LINK_STATE_L1_2_PCIPM) + link->aspm_disable |= ASPM_STATE_L1_2_PCIPM; pcie_config_aspm_link(link, policy_to_aspm_state(link)); if (state & PCIE_LINK_STATE_CLKPM) { diff --git a/include/linux/pci.h b/include/linux/pci.h index f9088c89a534..9dc5bee14ae9 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1544,9 +1544,13 @@ extern bool pcie_ports_native; #define pcie_ports_native false #endif -#define PCIE_LINK_STATE_L0S 1 -#define PCIE_LINK_STATE_L1 2 -#define PCIE_LINK_STATE_CLKPM 4 +#define PCIE_LINK_STATE_L0S BIT(0) +#define PCIE_LINK_STATE_L1 BIT(1) +#define PCIE_LINK_STATE_CLKPM BIT(2) +#define PCIE_LINK_STATE_L1_1 BIT(3) +#define PCIE_LINK_STATE_L1_2 BIT(4) +#define PCIE_LINK_STATE_L1_1_PCIPM BIT(5) +#define PCIE_LINK_STATE_L1_2_PCIPM BIT(6) #ifdef CONFIG_PCIEASPM int pci_disable_link_state(struct pci_dev *pdev, int state); -- cgit v1.2.3-71-gd317 From b7a73b33bb39575848df66c4bff09cd281652882 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Sun, 6 Oct 2019 15:22:04 +0200 Subject: iio: imu: st_lsm6dsx: add wakeup_source in st_sensors_platform_data Add the possibility to enable/disable wakeup source through st_sensors_platform_data and not only through device tree Signed-off-by: Lorenzo Bianconi Signed-off-by: Jonathan Cameron --- drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c | 6 ++++-- include/linux/platform_data/st_sensors_pdata.h | 2 ++ 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c index c0df2615ed74..5be372d5f407 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c @@ -2099,7 +2099,9 @@ static int st_lsm6dsx_irq_setup(struct st_lsm6dsx_hw *hw) int st_lsm6dsx_probe(struct device *dev, int irq, int hw_id, struct regmap *regmap) { + struct st_sensors_platform_data *pdata = dev->platform_data; const struct st_lsm6dsx_shub_settings *hub_settings; + struct device_node *np = dev->of_node; struct st_lsm6dsx_hw *hw; const char *name = NULL; int i, err; @@ -2162,8 +2164,8 @@ int st_lsm6dsx_probe(struct device *dev, int irq, int hw_id, return err; } - if (dev->of_node && - of_property_read_bool(dev->of_node, "wakeup-source")) + if ((np && of_property_read_bool(np, "wakeup-source")) || + (pdata && pdata->wakeup_source)) device_init_wakeup(dev, true); return 0; diff --git a/include/linux/platform_data/st_sensors_pdata.h b/include/linux/platform_data/st_sensors_pdata.h index 30929c22227d..e40b28ca892e 100644 --- a/include/linux/platform_data/st_sensors_pdata.h +++ b/include/linux/platform_data/st_sensors_pdata.h @@ -18,12 +18,14 @@ * @open_drain: set the interrupt line to be open drain if possible. * @spi_3wire: enable spi-3wire mode. * @pullups: enable/disable i2c controller pullup resistors. + * @wakeup_source: enable/disable device as wakeup generator. */ struct st_sensors_platform_data { u8 drdy_int_pin; bool open_drain; bool spi_3wire; bool pullups; + bool wakeup_source; }; #endif /* ST_SENSORS_PDATA_H */ -- cgit v1.2.3-71-gd317 From 8cbb8a9374a271099bacdc890fb16d374261332b Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 9 Oct 2019 14:54:01 -0500 Subject: PCI/ATS: Move pci_prg_resp_pasid_required() to CONFIG_PCI_PRI pci_prg_resp_pasid_required() returns the value of the "PRG Response PASID Required" bit from the PRI capability, but the interface was previously defined under #ifdef CONFIG_PCI_PASID. Move it from CONFIG_PCI_PASID to CONFIG_PCI_PRI so it's with the other PRI-related things. Signed-off-by: Bjorn Helgaas Reviewed-by: Kuppuswamy Sathyanarayanan Reviewed-by: Joerg Roedel --- drivers/pci/ats.c | 55 ++++++++++++++++++++++--------------------------- include/linux/pci-ats.h | 11 +++++----- 2 files changed, 30 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c index e18499243f84..0d06177252c7 100644 --- a/drivers/pci/ats.c +++ b/drivers/pci/ats.c @@ -280,6 +280,31 @@ int pci_reset_pri(struct pci_dev *pdev) return 0; } EXPORT_SYMBOL_GPL(pci_reset_pri); + +/** + * pci_prg_resp_pasid_required - Return PRG Response PASID Required bit + * status. + * @pdev: PCI device structure + * + * Returns 1 if PASID is required in PRG Response Message, 0 otherwise. + */ +int pci_prg_resp_pasid_required(struct pci_dev *pdev) +{ + u16 status; + int pos; + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI); + if (!pos) + return 0; + + pci_read_config_word(pdev, pos + PCI_PRI_STATUS, &status); + + if (status & PCI_PRI_STATUS_PASID) + return 1; + + return 0; +} +EXPORT_SYMBOL_GPL(pci_prg_resp_pasid_required); #endif /* CONFIG_PCI_PRI */ #ifdef CONFIG_PCI_PASID @@ -395,36 +420,6 @@ int pci_pasid_features(struct pci_dev *pdev) } EXPORT_SYMBOL_GPL(pci_pasid_features); -/** - * pci_prg_resp_pasid_required - Return PRG Response PASID Required bit - * status. - * @pdev: PCI device structure - * - * Returns 1 if PASID is required in PRG Response Message, 0 otherwise. - * - * Even though the PRG response PASID status is read from PRI Status - * Register, since this API will mainly be used by PASID users, this - * function is defined within #ifdef CONFIG_PCI_PASID instead of - * CONFIG_PCI_PRI. - */ -int pci_prg_resp_pasid_required(struct pci_dev *pdev) -{ - u16 status; - int pos; - - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI); - if (!pos) - return 0; - - pci_read_config_word(pdev, pos + PCI_PRI_STATUS, &status); - - if (status & PCI_PRI_STATUS_PASID) - return 1; - - return 0; -} -EXPORT_SYMBOL_GPL(pci_prg_resp_pasid_required); - #define PASID_NUMBER_SHIFT 8 #define PASID_NUMBER_MASK (0x1f << PASID_NUMBER_SHIFT) /** diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h index 1ebb88e7c184..a7a2b3d94fcc 100644 --- a/include/linux/pci-ats.h +++ b/include/linux/pci-ats.h @@ -10,6 +10,7 @@ int pci_enable_pri(struct pci_dev *pdev, u32 reqs); void pci_disable_pri(struct pci_dev *pdev); void pci_restore_pri_state(struct pci_dev *pdev); int pci_reset_pri(struct pci_dev *pdev); +int pci_prg_resp_pasid_required(struct pci_dev *pdev); #else /* CONFIG_PCI_PRI */ @@ -31,6 +32,10 @@ static inline int pci_reset_pri(struct pci_dev *pdev) return -ENODEV; } +static inline int pci_prg_resp_pasid_required(struct pci_dev *pdev) +{ + return 0; +} #endif /* CONFIG_PCI_PRI */ #ifdef CONFIG_PCI_PASID @@ -40,7 +45,6 @@ void pci_disable_pasid(struct pci_dev *pdev); void pci_restore_pasid_state(struct pci_dev *pdev); int pci_pasid_features(struct pci_dev *pdev); int pci_max_pasids(struct pci_dev *pdev); -int pci_prg_resp_pasid_required(struct pci_dev *pdev); #else /* CONFIG_PCI_PASID */ @@ -66,11 +70,6 @@ static inline int pci_max_pasids(struct pci_dev *pdev) { return -EINVAL; } - -static inline int pci_prg_resp_pasid_required(struct pci_dev *pdev) -{ - return 0; -} #endif /* CONFIG_PCI_PASID */ -- cgit v1.2.3-71-gd317 From 3ad62192097443e8c3a8e244475bacaecb894d4e Mon Sep 17 00:00:00 2001 From: Kuppuswamy Sathyanarayanan Date: Thu, 5 Sep 2019 14:31:44 -0500 Subject: PCI/ATS: Disable PF/VF ATS service independently Previously we didn't disable the PF ATS until all associated VFs had disabled it. But per PCIe spec r5.0, sec 9.3.7.8, the ATS Capability in VFs and associated PFs may be enabled independently. Leaving ATS enabled in the PF unnecessarily may have power and performance impacts. Remove this dependency logic in the ATS enable/disable code. [bhelgaas: commit log] Suggested-by: Ashok Raj Link: https://lore.kernel.org/r/8163ab8fa66afd2cba514ae95d29ab12104781aa.1567029860.git.sathyanarayanan.kuppuswamy@linux.intel.com Link: https://lore.kernel.org/r/20190905193146.90250-4-helgaas@kernel.org Signed-off-by: Kuppuswamy Sathyanarayanan Signed-off-by: Bjorn Helgaas Cc: Ashok Raj Cc: Keith Busch --- drivers/pci/ats.c | 11 ----------- include/linux/pci.h | 1 - 2 files changed, 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c index fb5cfd27dd3c..a708ed4146ca 100644 --- a/drivers/pci/ats.c +++ b/drivers/pci/ats.c @@ -60,8 +60,6 @@ int pci_enable_ats(struct pci_dev *dev, int ps) pdev = pci_physfn(dev); if (pdev->ats_stu != ps) return -EINVAL; - - atomic_inc(&pdev->ats_ref_cnt); /* count enabled VFs */ } else { dev->ats_stu = ps; ctrl |= PCI_ATS_CTRL_STU(dev->ats_stu - PCI_ATS_MIN_STU); @@ -79,20 +77,11 @@ EXPORT_SYMBOL_GPL(pci_enable_ats); */ void pci_disable_ats(struct pci_dev *dev) { - struct pci_dev *pdev; u16 ctrl; if (WARN_ON(!dev->ats_enabled)) return; - if (atomic_read(&dev->ats_ref_cnt)) - return; /* VFs still enabled */ - - if (dev->is_virtfn) { - pdev = pci_physfn(dev); - atomic_dec(&pdev->ats_ref_cnt); - } - pci_read_config_word(dev, dev->ats_cap + PCI_ATS_CTRL, &ctrl); ctrl &= ~PCI_ATS_CTRL_ENABLE; pci_write_config_word(dev, dev->ats_cap + PCI_ATS_CTRL, ctrl); diff --git a/include/linux/pci.h b/include/linux/pci.h index f9088c89a534..c028883c8460 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -452,7 +452,6 @@ struct pci_dev { }; u16 ats_cap; /* ATS Capability offset */ u8 ats_stu; /* ATS Smallest Translation Unit */ - atomic_t ats_ref_cnt; /* Number of VFs with ATS enabled */ #endif #ifdef CONFIG_PCI_PRI u32 pri_reqs_alloc; /* Number of PRI requests allocated */ -- cgit v1.2.3-71-gd317 From c065190bbcd4fb54ce9c5fd34fcad71acf2a0ea4 Mon Sep 17 00:00:00 2001 From: Kuppuswamy Sathyanarayanan Date: Thu, 5 Sep 2019 14:31:45 -0500 Subject: PCI/ATS: Cache PRI Capability offset Previously each PRI interface searched for the PRI Capability. Cache the capability offset the first time we use it instead of searching each time. [bhelgaas: commit log, reorder patch to later, call pci_pri_init() from pci_init_capabilities()] Link: https://lore.kernel.org/r/0c5495d376faf6dbb8eb2165204c474438aaae65.156 7029860.git.sathyanarayanan.kuppuswamy@linux.intel.com Link: https://lore.kernel.org/r/20190905193146.90250-5-helgaas@kernel.org Signed-off-by: Kuppuswamy Sathyanarayanan Signed-off-by: Bjorn Helgaas --- drivers/pci/ats.c | 51 ++++++++++++++++++++++++++------------------------- drivers/pci/pci.h | 6 ++++++ drivers/pci/probe.c | 3 +++ include/linux/pci.h | 1 + 4 files changed, 36 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c index a708ed4146ca..c97e862b538a 100644 --- a/drivers/pci/ats.c +++ b/drivers/pci/ats.c @@ -159,6 +159,11 @@ int pci_ats_page_aligned(struct pci_dev *pdev) EXPORT_SYMBOL_GPL(pci_ats_page_aligned); #ifdef CONFIG_PCI_PRI +void pci_pri_init(struct pci_dev *pdev) +{ + pdev->pri_cap = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI); +} + /** * pci_enable_pri - Enable PRI capability * @ pdev: PCI device structure @@ -169,7 +174,7 @@ int pci_enable_pri(struct pci_dev *pdev, u32 reqs) { u16 control, status; u32 max_requests; - int pos; + int pri = pdev->pri_cap; /* * VFs must not implement the PRI Capability. If their PF @@ -185,21 +190,20 @@ int pci_enable_pri(struct pci_dev *pdev, u32 reqs) if (WARN_ON(pdev->pri_enabled)) return -EBUSY; - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI); - if (!pos) + if (!pri) return -EINVAL; - pci_read_config_word(pdev, pos + PCI_PRI_STATUS, &status); + pci_read_config_word(pdev, pri + PCI_PRI_STATUS, &status); if (!(status & PCI_PRI_STATUS_STOPPED)) return -EBUSY; - pci_read_config_dword(pdev, pos + PCI_PRI_MAX_REQ, &max_requests); + pci_read_config_dword(pdev, pri + PCI_PRI_MAX_REQ, &max_requests); reqs = min(max_requests, reqs); pdev->pri_reqs_alloc = reqs; - pci_write_config_dword(pdev, pos + PCI_PRI_ALLOC_REQ, reqs); + pci_write_config_dword(pdev, pri + PCI_PRI_ALLOC_REQ, reqs); control = PCI_PRI_CTRL_ENABLE; - pci_write_config_word(pdev, pos + PCI_PRI_CTRL, control); + pci_write_config_word(pdev, pri + PCI_PRI_CTRL, control); pdev->pri_enabled = 1; @@ -216,7 +220,7 @@ EXPORT_SYMBOL_GPL(pci_enable_pri); void pci_disable_pri(struct pci_dev *pdev) { u16 control; - int pos; + int pri = pdev->pri_cap; /* VFs share the PF PRI */ if (pdev->is_virtfn) @@ -225,13 +229,12 @@ void pci_disable_pri(struct pci_dev *pdev) if (WARN_ON(!pdev->pri_enabled)) return; - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI); - if (!pos) + if (!pri) return; - pci_read_config_word(pdev, pos + PCI_PRI_CTRL, &control); + pci_read_config_word(pdev, pri + PCI_PRI_CTRL, &control); control &= ~PCI_PRI_CTRL_ENABLE; - pci_write_config_word(pdev, pos + PCI_PRI_CTRL, control); + pci_write_config_word(pdev, pri + PCI_PRI_CTRL, control); pdev->pri_enabled = 0; } @@ -245,7 +248,7 @@ void pci_restore_pri_state(struct pci_dev *pdev) { u16 control = PCI_PRI_CTRL_ENABLE; u32 reqs = pdev->pri_reqs_alloc; - int pos; + int pri = pdev->pri_cap; if (pdev->is_virtfn) return; @@ -253,12 +256,11 @@ void pci_restore_pri_state(struct pci_dev *pdev) if (!pdev->pri_enabled) return; - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI); - if (!pos) + if (!pri) return; - pci_write_config_dword(pdev, pos + PCI_PRI_ALLOC_REQ, reqs); - pci_write_config_word(pdev, pos + PCI_PRI_CTRL, control); + pci_write_config_dword(pdev, pri + PCI_PRI_ALLOC_REQ, reqs); + pci_write_config_word(pdev, pri + PCI_PRI_CTRL, control); } EXPORT_SYMBOL_GPL(pci_restore_pri_state); @@ -272,7 +274,7 @@ EXPORT_SYMBOL_GPL(pci_restore_pri_state); int pci_reset_pri(struct pci_dev *pdev) { u16 control; - int pos; + int pri = pdev->pri_cap; if (pdev->is_virtfn) return 0; @@ -280,12 +282,11 @@ int pci_reset_pri(struct pci_dev *pdev) if (WARN_ON(pdev->pri_enabled)) return -EBUSY; - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI); - if (!pos) + if (!pri) return -EINVAL; control = PCI_PRI_CTRL_RESET; - pci_write_config_word(pdev, pos + PCI_PRI_CTRL, control); + pci_write_config_word(pdev, pri + PCI_PRI_CTRL, control); return 0; } @@ -301,16 +302,16 @@ EXPORT_SYMBOL_GPL(pci_reset_pri); int pci_prg_resp_pasid_required(struct pci_dev *pdev) { u16 status; - int pos; + int pri; if (pdev->is_virtfn) pdev = pci_physfn(pdev); - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI); - if (!pos) + pri = pdev->pri_cap; + if (!pri) return 0; - pci_read_config_word(pdev, pos + PCI_PRI_STATUS, &status); + pci_read_config_word(pdev, pri + PCI_PRI_STATUS, &status); if (status & PCI_PRI_STATUS_PASID) return 1; diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 3f6947ee3324..aa08cd35bf87 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -456,6 +456,12 @@ static inline void pci_ats_init(struct pci_dev *d) { } static inline void pci_restore_ats_state(struct pci_dev *dev) { } #endif /* CONFIG_PCI_ATS */ +#ifdef CONFIG_PCI_PRI +void pci_pri_init(struct pci_dev *dev); +#else +static inline void pci_pri_init(struct pci_dev *dev) { } +#endif + #ifdef CONFIG_PCI_IOV int pci_iov_init(struct pci_dev *dev); void pci_iov_release(struct pci_dev *dev); diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 3d5271a7a849..d145165c799c 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2324,6 +2324,9 @@ static void pci_init_capabilities(struct pci_dev *dev) /* Address Translation Services */ pci_ats_init(dev); + /* Page Request Interface */ + pci_pri_init(dev); + /* Enable ACS P2P upstream forwarding */ pci_enable_acs(dev); diff --git a/include/linux/pci.h b/include/linux/pci.h index c028883c8460..e7770d990c46 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -454,6 +454,7 @@ struct pci_dev { u8 ats_stu; /* ATS Smallest Translation Unit */ #endif #ifdef CONFIG_PCI_PRI + u16 pri_cap; /* PRI Capability offset */ u32 pri_reqs_alloc; /* Number of PRI requests allocated */ #endif #ifdef CONFIG_PCI_PASID -- cgit v1.2.3-71-gd317 From 751035b8dc061ae434c3311bac9cd6d0e5e00f94 Mon Sep 17 00:00:00 2001 From: Kuppuswamy Sathyanarayanan Date: Thu, 5 Sep 2019 14:31:46 -0500 Subject: PCI/ATS: Cache PASID Capability offset Previously each PASID interface searched for the PASID Capability. Cache the capability offset the first time we use it instead of searching each time. [bhelgaas: commit log, reorder patch to later, call pci_pasid_init() from pci_init_capabilities()] Link: https://lore.kernel.org/r/4957778959fa34eab3e8b3065d1951989c61cb0f.1567029860.git.sathyanarayanan.kuppuswamy@linux.intel.com Link: https://lore.kernel.org/r/20190905193146.90250-6-helgaas@kernel.org Signed-off-by: Kuppuswamy Sathyanarayanan Signed-off-by: Bjorn Helgaas --- drivers/pci/ats.c | 42 +++++++++++++++++++++--------------------- drivers/pci/pci.h | 6 ++++++ drivers/pci/probe.c | 3 +++ include/linux/pci.h | 1 + 4 files changed, 31 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c index c97e862b538a..d5ac808cae21 100644 --- a/drivers/pci/ats.c +++ b/drivers/pci/ats.c @@ -322,6 +322,11 @@ EXPORT_SYMBOL_GPL(pci_prg_resp_pasid_required); #endif /* CONFIG_PCI_PRI */ #ifdef CONFIG_PCI_PASID +void pci_pasid_init(struct pci_dev *pdev) +{ + pdev->pasid_cap = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PASID); +} + /** * pci_enable_pasid - Enable the PASID capability * @pdev: PCI device structure @@ -334,7 +339,7 @@ EXPORT_SYMBOL_GPL(pci_prg_resp_pasid_required); int pci_enable_pasid(struct pci_dev *pdev, int features) { u16 control, supported; - int pos; + int pasid = pdev->pasid_cap; /* * VFs must not implement the PASID Capability, but if a PF @@ -352,11 +357,10 @@ int pci_enable_pasid(struct pci_dev *pdev, int features) if (!pdev->eetlp_prefix_path) return -EINVAL; - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PASID); - if (!pos) + if (!pasid) return -EINVAL; - pci_read_config_word(pdev, pos + PCI_PASID_CAP, &supported); + pci_read_config_word(pdev, pasid + PCI_PASID_CAP, &supported); supported &= PCI_PASID_CAP_EXEC | PCI_PASID_CAP_PRIV; /* User wants to enable anything unsupported? */ @@ -366,7 +370,7 @@ int pci_enable_pasid(struct pci_dev *pdev, int features) control = PCI_PASID_CTRL_ENABLE | features; pdev->pasid_features = features; - pci_write_config_word(pdev, pos + PCI_PASID_CTRL, control); + pci_write_config_word(pdev, pasid + PCI_PASID_CTRL, control); pdev->pasid_enabled = 1; @@ -381,7 +385,7 @@ EXPORT_SYMBOL_GPL(pci_enable_pasid); void pci_disable_pasid(struct pci_dev *pdev) { u16 control = 0; - int pos; + int pasid = pdev->pasid_cap; /* VFs share the PF PASID configuration */ if (pdev->is_virtfn) @@ -390,11 +394,10 @@ void pci_disable_pasid(struct pci_dev *pdev) if (WARN_ON(!pdev->pasid_enabled)) return; - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PASID); - if (!pos) + if (!pasid) return; - pci_write_config_word(pdev, pos + PCI_PASID_CTRL, control); + pci_write_config_word(pdev, pasid + PCI_PASID_CTRL, control); pdev->pasid_enabled = 0; } @@ -407,7 +410,7 @@ EXPORT_SYMBOL_GPL(pci_disable_pasid); void pci_restore_pasid_state(struct pci_dev *pdev) { u16 control; - int pos; + int pasid = pdev->pasid_cap; if (pdev->is_virtfn) return; @@ -415,12 +418,11 @@ void pci_restore_pasid_state(struct pci_dev *pdev) if (!pdev->pasid_enabled) return; - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PASID); - if (!pos) + if (!pasid) return; control = PCI_PASID_CTRL_ENABLE | pdev->pasid_features; - pci_write_config_word(pdev, pos + PCI_PASID_CTRL, control); + pci_write_config_word(pdev, pasid + PCI_PASID_CTRL, control); } EXPORT_SYMBOL_GPL(pci_restore_pasid_state); @@ -437,16 +439,15 @@ EXPORT_SYMBOL_GPL(pci_restore_pasid_state); int pci_pasid_features(struct pci_dev *pdev) { u16 supported; - int pos; + int pasid = pdev->pasid_cap; if (pdev->is_virtfn) pdev = pci_physfn(pdev); - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PASID); - if (!pos) + if (!pasid) return -EINVAL; - pci_read_config_word(pdev, pos + PCI_PASID_CAP, &supported); + pci_read_config_word(pdev, pasid + PCI_PASID_CAP, &supported); supported &= PCI_PASID_CAP_EXEC | PCI_PASID_CAP_PRIV; @@ -466,16 +467,15 @@ EXPORT_SYMBOL_GPL(pci_pasid_features); int pci_max_pasids(struct pci_dev *pdev) { u16 supported; - int pos; + int pasid = pdev->pasid_cap; if (pdev->is_virtfn) pdev = pci_physfn(pdev); - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PASID); - if (!pos) + if (!pasid) return -EINVAL; - pci_read_config_word(pdev, pos + PCI_PASID_CAP, &supported); + pci_read_config_word(pdev, pasid + PCI_PASID_CAP, &supported); supported = (supported & PASID_NUMBER_MASK) >> PASID_NUMBER_SHIFT; diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index aa08cd35bf87..ae84d28ba03a 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -462,6 +462,12 @@ void pci_pri_init(struct pci_dev *dev); static inline void pci_pri_init(struct pci_dev *dev) { } #endif +#ifdef CONFIG_PCI_PASID +void pci_pasid_init(struct pci_dev *dev); +#else +static inline void pci_pasid_init(struct pci_dev *dev) { } +#endif + #ifdef CONFIG_PCI_IOV int pci_iov_init(struct pci_dev *dev); void pci_iov_release(struct pci_dev *dev); diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index d145165c799c..df2b77866f3b 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2327,6 +2327,9 @@ static void pci_init_capabilities(struct pci_dev *dev) /* Page Request Interface */ pci_pri_init(dev); + /* Process Address Space ID */ + pci_pasid_init(dev); + /* Enable ACS P2P upstream forwarding */ pci_enable_acs(dev); diff --git a/include/linux/pci.h b/include/linux/pci.h index e7770d990c46..6542100bd2dd 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -458,6 +458,7 @@ struct pci_dev { u32 pri_reqs_alloc; /* Number of PRI requests allocated */ #endif #ifdef CONFIG_PCI_PASID + u16 pasid_cap; /* PASID Capability offset */ u16 pasid_features; #endif #ifdef CONFIG_PCI_P2PDMA -- cgit v1.2.3-71-gd317 From e5adf79a1d8086aefa56f48eeb08f8fe4e054a3d Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 9 Oct 2019 16:07:51 -0500 Subject: PCI/ATS: Cache PRI PRG Response PASID Required bit The PRG Response PASID Required bit in the PRI Capability is read-only. Read it once when we enumerate the device and cache the value so we don't need to read it again. Based-on-patch-by: Kuppuswamy Sathyanarayanan Signed-off-by: Bjorn Helgaas --- drivers/pci/ats.c | 23 ++++++++++------------- include/linux/pci.h | 1 + 2 files changed, 11 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c index d5ac808cae21..76ae518d55f4 100644 --- a/drivers/pci/ats.c +++ b/drivers/pci/ats.c @@ -161,7 +161,16 @@ EXPORT_SYMBOL_GPL(pci_ats_page_aligned); #ifdef CONFIG_PCI_PRI void pci_pri_init(struct pci_dev *pdev) { + u16 status; + pdev->pri_cap = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI); + + if (!pdev->pri_cap) + return; + + pci_read_config_word(pdev, pdev->pri_cap + PCI_PRI_STATUS, &status); + if (status & PCI_PRI_STATUS_PASID) + pdev->pasid_required = 1; } /** @@ -301,22 +310,10 @@ EXPORT_SYMBOL_GPL(pci_reset_pri); */ int pci_prg_resp_pasid_required(struct pci_dev *pdev) { - u16 status; - int pri; - if (pdev->is_virtfn) pdev = pci_physfn(pdev); - pri = pdev->pri_cap; - if (!pri) - return 0; - - pci_read_config_word(pdev, pri + PCI_PRI_STATUS, &status); - - if (status & PCI_PRI_STATUS_PASID) - return 1; - - return 0; + return pdev->pasid_required; } EXPORT_SYMBOL_GPL(pci_prg_resp_pasid_required); #endif /* CONFIG_PCI_PRI */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 6542100bd2dd..64d35e730fab 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -456,6 +456,7 @@ struct pci_dev { #ifdef CONFIG_PCI_PRI u16 pri_cap; /* PRI Capability offset */ u32 pri_reqs_alloc; /* Number of PRI requests allocated */ + unsigned int pasid_required:1; /* PRG Response PASID Required */ #endif #ifdef CONFIG_PCI_PASID u16 pasid_cap; /* PASID Capability offset */ -- cgit v1.2.3-71-gd317 From b24d5c2098596a41cf187af41287777a2e0dd753 Mon Sep 17 00:00:00 2001 From: Krzysztof Wilczynski Date: Sat, 14 Sep 2019 23:30:32 +0200 Subject: PCI/ATS: Consolidate ATS declarations in linux/pci-ats.h Move ATS function prototypes from include/linux/pci.h to include/linux/pci-ats.h as the ATS, PRI, and PASID interfaces are related and are used only by the IOMMU drivers. This effectively reverts ff9bee895c4d ("PCI: Move ATS declarations to linux/pci.h so they're all together"). Also, remove surplus forward declaration of struct pci_ats from include/linux/pci.h, as it is no longer needed, since struct pci_ats was embedded directly into struct pci_dev by d544d75ac96a ("PCI: Embed ATS info directly into struct pci_dev"). No functional changes intended. Link: https://lore.kernel.org/r/20190914213032.22314-1-kw@linux.com Signed-off-by: Krzysztof Wilczynski Signed-off-by: Bjorn Helgaas --- include/linux/pci-ats.h | 75 ++++++++++++++++++------------------------------- include/linux/pci.h | 14 --------- 2 files changed, 28 insertions(+), 61 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h index a7a2b3d94fcc..67de3a9499bb 100644 --- a/include/linux/pci-ats.h +++ b/include/linux/pci-ats.h @@ -4,73 +4,54 @@ #include -#ifdef CONFIG_PCI_PRI +#ifdef CONFIG_PCI_ATS +/* Address Translation Service */ +int pci_enable_ats(struct pci_dev *dev, int ps); +void pci_disable_ats(struct pci_dev *dev); +int pci_ats_queue_depth(struct pci_dev *dev); +int pci_ats_page_aligned(struct pci_dev *dev); +#else /* CONFIG_PCI_ATS */ +static inline int pci_enable_ats(struct pci_dev *d, int ps) +{ return -ENODEV; } +static inline void pci_disable_ats(struct pci_dev *d) { } +static inline int pci_ats_queue_depth(struct pci_dev *d) +{ return -ENODEV; } +static inline int pci_ats_page_aligned(struct pci_dev *dev) +{ return 0; } +#endif /* CONFIG_PCI_ATS */ +#ifdef CONFIG_PCI_PRI int pci_enable_pri(struct pci_dev *pdev, u32 reqs); void pci_disable_pri(struct pci_dev *pdev); void pci_restore_pri_state(struct pci_dev *pdev); int pci_reset_pri(struct pci_dev *pdev); int pci_prg_resp_pasid_required(struct pci_dev *pdev); - #else /* CONFIG_PCI_PRI */ - static inline int pci_enable_pri(struct pci_dev *pdev, u32 reqs) -{ - return -ENODEV; -} - -static inline void pci_disable_pri(struct pci_dev *pdev) -{ -} - -static inline void pci_restore_pri_state(struct pci_dev *pdev) -{ -} - +{ return -ENODEV; } +static inline void pci_disable_pri(struct pci_dev *pdev) { } +static inline void pci_restore_pri_state(struct pci_dev *pdev) { } static inline int pci_reset_pri(struct pci_dev *pdev) -{ - return -ENODEV; -} - +{ return -ENODEV; } static inline int pci_prg_resp_pasid_required(struct pci_dev *pdev) -{ - return 0; -} +{ return 0; } #endif /* CONFIG_PCI_PRI */ #ifdef CONFIG_PCI_PASID - int pci_enable_pasid(struct pci_dev *pdev, int features); void pci_disable_pasid(struct pci_dev *pdev); void pci_restore_pasid_state(struct pci_dev *pdev); int pci_pasid_features(struct pci_dev *pdev); int pci_max_pasids(struct pci_dev *pdev); - -#else /* CONFIG_PCI_PASID */ - +#else /* CONFIG_PCI_PASID */ static inline int pci_enable_pasid(struct pci_dev *pdev, int features) -{ - return -EINVAL; -} - -static inline void pci_disable_pasid(struct pci_dev *pdev) -{ -} - -static inline void pci_restore_pasid_state(struct pci_dev *pdev) -{ -} - +{ return -EINVAL; } +static inline void pci_disable_pasid(struct pci_dev *pdev) { } +static inline void pci_restore_pasid_state(struct pci_dev *pdev) { } static inline int pci_pasid_features(struct pci_dev *pdev) -{ - return -EINVAL; -} - +{ return -EINVAL; } static inline int pci_max_pasids(struct pci_dev *pdev) -{ - return -EINVAL; -} +{ return -EINVAL; } #endif /* CONFIG_PCI_PASID */ - -#endif /* LINUX_PCI_ATS_H*/ +#endif /* LINUX_PCI_ATS_H */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 64d35e730fab..9fc22f48055e 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -284,7 +284,6 @@ struct irq_affinity; struct pcie_link_state; struct pci_vpd; struct pci_sriov; -struct pci_ats; struct pci_p2pdma; /* The pci_dev structure describes PCI devices */ @@ -1778,19 +1777,6 @@ pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, NULL); } -#ifdef CONFIG_PCI_ATS -/* Address Translation Service */ -int pci_enable_ats(struct pci_dev *dev, int ps); -void pci_disable_ats(struct pci_dev *dev); -int pci_ats_queue_depth(struct pci_dev *dev); -int pci_ats_page_aligned(struct pci_dev *dev); -#else -static inline int pci_enable_ats(struct pci_dev *d, int ps) { return -ENODEV; } -static inline void pci_disable_ats(struct pci_dev *d) { } -static inline int pci_ats_queue_depth(struct pci_dev *d) { return -ENODEV; } -static inline int pci_ats_page_aligned(struct pci_dev *dev) { return 0; } -#endif - /* Include architecture-dependent settings and functions */ #include -- cgit v1.2.3-71-gd317 From c6e9aefbf9db818d60818aa5540d78c1da289aae Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 9 Oct 2019 16:27:30 -0500 Subject: PCI/ATS: Remove unused PRI and PASID stubs The following functions are only used by amd_iommu.c and intel-iommu.c (when CONFIG_INTEL_IOMMU_SVM is enabled). CONFIG_PCI_PRI and CONFIG_PCI_PASID are always defined in those cases, so there's no need for the stubs. pci_enable_pri() pci_disable_pri() pci_reset_pri() pci_prg_resp_pasid_required() pci_enable_pasid() pci_disable_pasid() Remove the unused stubs. Signed-off-by: Bjorn Helgaas Reviewed-by: Kuppuswamy Sathyanarayanan Reviewed-by: Joerg Roedel --- include/linux/pci-ats.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h index 67de3a9499bb..963c11f7c56b 100644 --- a/include/linux/pci-ats.h +++ b/include/linux/pci-ats.h @@ -27,14 +27,7 @@ void pci_restore_pri_state(struct pci_dev *pdev); int pci_reset_pri(struct pci_dev *pdev); int pci_prg_resp_pasid_required(struct pci_dev *pdev); #else /* CONFIG_PCI_PRI */ -static inline int pci_enable_pri(struct pci_dev *pdev, u32 reqs) -{ return -ENODEV; } -static inline void pci_disable_pri(struct pci_dev *pdev) { } static inline void pci_restore_pri_state(struct pci_dev *pdev) { } -static inline int pci_reset_pri(struct pci_dev *pdev) -{ return -ENODEV; } -static inline int pci_prg_resp_pasid_required(struct pci_dev *pdev) -{ return 0; } #endif /* CONFIG_PCI_PRI */ #ifdef CONFIG_PCI_PASID @@ -44,9 +37,6 @@ void pci_restore_pasid_state(struct pci_dev *pdev); int pci_pasid_features(struct pci_dev *pdev); int pci_max_pasids(struct pci_dev *pdev); #else /* CONFIG_PCI_PASID */ -static inline int pci_enable_pasid(struct pci_dev *pdev, int features) -{ return -EINVAL; } -static inline void pci_disable_pasid(struct pci_dev *pdev) { } static inline void pci_restore_pasid_state(struct pci_dev *pdev) { } static inline int pci_pasid_features(struct pci_dev *pdev) { return -EINVAL; } -- cgit v1.2.3-71-gd317 From fef2dd8b3966517172514ea5a89104ba7745678b Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 9 Oct 2019 16:47:15 -0500 Subject: PCI/ATS: Make pci_restore_pri_state(), pci_restore_pasid_state() private These interfaces: void pci_restore_pri_state(struct pci_dev *pdev); void pci_restore_pasid_state(struct pci_dev *pdev); are only used in drivers/pci and do not need to be seen by the rest of the kernel. Most them to drivers/pci/pci.h so they're private to the PCI subsystem. Signed-off-by: Bjorn Helgaas Reviewed-by: Joerg Roedel --- drivers/pci/pci.h | 4 ++++ include/linux/pci-ats.h | 5 ----- 2 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index ae84d28ba03a..e6b46d2b9846 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -458,14 +458,18 @@ static inline void pci_restore_ats_state(struct pci_dev *dev) { } #ifdef CONFIG_PCI_PRI void pci_pri_init(struct pci_dev *dev); +void pci_restore_pri_state(struct pci_dev *pdev); #else static inline void pci_pri_init(struct pci_dev *dev) { } +static inline void pci_restore_pri_state(struct pci_dev *pdev) { } #endif #ifdef CONFIG_PCI_PASID void pci_pasid_init(struct pci_dev *dev); +void pci_restore_pasid_state(struct pci_dev *pdev); #else static inline void pci_pasid_init(struct pci_dev *dev) { } +static inline void pci_restore_pasid_state(struct pci_dev *pdev) { } #endif #ifdef CONFIG_PCI_IOV diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h index 963c11f7c56b..5d62e78946a3 100644 --- a/include/linux/pci-ats.h +++ b/include/linux/pci-ats.h @@ -23,21 +23,16 @@ static inline int pci_ats_page_aligned(struct pci_dev *dev) #ifdef CONFIG_PCI_PRI int pci_enable_pri(struct pci_dev *pdev, u32 reqs); void pci_disable_pri(struct pci_dev *pdev); -void pci_restore_pri_state(struct pci_dev *pdev); int pci_reset_pri(struct pci_dev *pdev); int pci_prg_resp_pasid_required(struct pci_dev *pdev); -#else /* CONFIG_PCI_PRI */ -static inline void pci_restore_pri_state(struct pci_dev *pdev) { } #endif /* CONFIG_PCI_PRI */ #ifdef CONFIG_PCI_PASID int pci_enable_pasid(struct pci_dev *pdev, int features); void pci_disable_pasid(struct pci_dev *pdev); -void pci_restore_pasid_state(struct pci_dev *pdev); int pci_pasid_features(struct pci_dev *pdev); int pci_max_pasids(struct pci_dev *pdev); #else /* CONFIG_PCI_PASID */ -static inline void pci_restore_pasid_state(struct pci_dev *pdev) { } static inline int pci_pasid_features(struct pci_dev *pdev) { return -EINVAL; } static inline int pci_max_pasids(struct pci_dev *pdev) -- cgit v1.2.3-71-gd317 From 554032cdfbf4491f38241a3f6b27459408d90df3 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 15 Oct 2019 11:28:46 +0100 Subject: net: phylink: use more linkmode_* Use more linkmode_* helpers rather than open-coding the bitmap operations. Signed-off-by: Russell King Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 7 ++----- include/linux/linkmode.h | 6 ++++++ 2 files changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index a5a57ca94c1a..8e53ed90da3c 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -117,9 +117,7 @@ static int phylink_is_empty_linkmode(const unsigned long *linkmode) phylink_set(tmp, Pause); phylink_set(tmp, Asym_Pause); - bitmap_andnot(tmp, linkmode, tmp, __ETHTOOL_LINK_MODE_MASK_NBITS); - - return linkmode_empty(tmp); + return linkmode_subset(linkmode, tmp); } static const char *phylink_an_mode_str(unsigned int mode) @@ -1728,8 +1726,7 @@ static int phylink_sfp_module_insert(void *upstream, if (phy_interface_mode_is_8023z(iface) && pl->phydev) return -EINVAL; - changed = !bitmap_equal(pl->supported, support, - __ETHTOOL_LINK_MODE_MASK_NBITS); + changed = !linkmode_equal(pl->supported, support); if (changed) { linkmode_copy(pl->supported, support); linkmode_copy(pl->link_config.advertising, config.advertising); diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index a99c58866860..fe740031339d 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -82,4 +82,10 @@ static inline int linkmode_equal(const unsigned long *src1, return bitmap_equal(src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); } +static inline int linkmode_subset(const unsigned long *src1, + const unsigned long *src2) +{ + return bitmap_subset(src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + #endif /* __LINKMODE_H */ -- cgit v1.2.3-71-gd317 From 299b610117a4145dfe15963f0ea037ab319ce531 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Mon, 14 Oct 2019 23:46:21 +0200 Subject: rtc: ds1685: add indirect access method and remove plat_read/plat_write SGI Octane (IP30) doesn't have RTC register directly mapped into CPU address space, but accesses RTC registers with an address and data register. This is now supported by additional access functions, which are selected by a new field in platform data. Removed plat_read/plat_write since there is no user and their usage could introduce lifetime issue, when functions are placed in different modules. Signed-off-by: Thomas Bogendoerfer Acked-by: Joshua Kinard Reviewed-by: Joshua Kinard Link: https://lore.kernel.org/r/20191014214621.25257-1-tbogendoerfer@suse.de Signed-off-by: Alexandre Belloni --- arch/mips/sgi-ip32/ip32-platform.c | 2 +- drivers/rtc/rtc-ds1685.c | 78 +++++++++++++++++++++++++------------- include/linux/rtc/ds1685.h | 8 ++-- 3 files changed, 58 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/arch/mips/sgi-ip32/ip32-platform.c b/arch/mips/sgi-ip32/ip32-platform.c index 5a2a82148d8d..c3909bd8dd1a 100644 --- a/arch/mips/sgi-ip32/ip32-platform.c +++ b/arch/mips/sgi-ip32/ip32-platform.c @@ -115,7 +115,7 @@ ip32_rtc_platform_data[] = { .bcd_mode = true, .no_irq = false, .uie_unsupported = false, - .alloc_io_resources = true, + .access_type = ds1685_reg_direct, .plat_prepare_poweroff = ip32_prepare_poweroff, }, }; diff --git a/drivers/rtc/rtc-ds1685.c b/drivers/rtc/rtc-ds1685.c index 349a8d1caca1..98d06b3ee913 100644 --- a/drivers/rtc/rtc-ds1685.c +++ b/drivers/rtc/rtc-ds1685.c @@ -31,7 +31,10 @@ /* ----------------------------------------------------------------------- */ -/* Standard read/write functions if platform does not provide overrides */ +/* + * Standard read/write + * all registers are mapped in CPU address space + */ /** * ds1685_read - read a value from an rtc register. @@ -59,6 +62,35 @@ ds1685_write(struct ds1685_priv *rtc, int reg, u8 value) } /* ----------------------------------------------------------------------- */ +/* + * Indirect read/write functions + * access happens via address and data register mapped in CPU address space + */ + +/** + * ds1685_indirect_read - read a value from an rtc register. + * @rtc: pointer to the ds1685 rtc structure. + * @reg: the register address to read. + */ +static u8 +ds1685_indirect_read(struct ds1685_priv *rtc, int reg) +{ + writeb(reg, rtc->regs); + return readb(rtc->data); +} + +/** + * ds1685_indirect_write - write a value to an rtc register. + * @rtc: pointer to the ds1685 rtc structure. + * @reg: the register address to write. + * @value: value to write to the register. + */ +static void +ds1685_indirect_write(struct ds1685_priv *rtc, int reg, u8 value) +{ + writeb(reg, rtc->regs); + writeb(value, rtc->data); +} /* ----------------------------------------------------------------------- */ /* Inlined functions */ @@ -1062,42 +1094,36 @@ ds1685_rtc_probe(struct platform_device *pdev) if (!rtc) return -ENOMEM; - /* - * Allocate/setup any IORESOURCE_MEM resources, if required. Not all - * platforms put the RTC in an easy-access place. Like the SGI Octane, - * which attaches the RTC to a "ByteBus", hooked to a SuperIO chip - * that sits behind the IOC3 PCI metadevice. - */ - if (pdata->alloc_io_resources) { + /* Setup resources and access functions */ + switch (pdata->access_type) { + case ds1685_reg_direct: + rtc->regs = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(rtc->regs)) + return PTR_ERR(rtc->regs); + rtc->read = ds1685_read; + rtc->write = ds1685_write; + break; + case ds1685_reg_indirect: rtc->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(rtc->regs)) return PTR_ERR(rtc->regs); + rtc->data = devm_platform_ioremap_resource(pdev, 1); + if (IS_ERR(rtc->data)) + return PTR_ERR(rtc->data); + rtc->read = ds1685_indirect_read; + rtc->write = ds1685_indirect_write; + break; } + if (!rtc->read || !rtc->write) + return -ENXIO; + /* Get the register step size. */ if (pdata->regstep > 0) rtc->regstep = pdata->regstep; else rtc->regstep = 1; - /* Platform read function, else default if mmio setup */ - if (pdata->plat_read) - rtc->read = pdata->plat_read; - else - if (pdata->alloc_io_resources) - rtc->read = ds1685_read; - else - return -ENXIO; - - /* Platform write function, else default if mmio setup */ - if (pdata->plat_write) - rtc->write = pdata->plat_write; - else - if (pdata->alloc_io_resources) - rtc->write = ds1685_write; - else - return -ENXIO; - /* Platform pre-shutdown function, if defined. */ if (pdata->plat_prepare_poweroff) rtc->prepare_poweroff = pdata->plat_prepare_poweroff; diff --git a/include/linux/rtc/ds1685.h b/include/linux/rtc/ds1685.h index 101c7adc05a2..67ee9d20cc5a 100644 --- a/include/linux/rtc/ds1685.h +++ b/include/linux/rtc/ds1685.h @@ -42,6 +42,7 @@ struct ds1685_priv { struct rtc_device *dev; void __iomem *regs; + void __iomem *data; u32 regstep; int irq_num; bool bcd_mode; @@ -70,12 +71,13 @@ struct ds1685_rtc_platform_data { const bool bcd_mode; const bool no_irq; const bool uie_unsupported; - const bool alloc_io_resources; - u8 (*plat_read)(struct ds1685_priv *, int); - void (*plat_write)(struct ds1685_priv *, int, u8); void (*plat_prepare_poweroff)(void); void (*plat_wake_alarm)(void); void (*plat_post_ram_clear)(void); + enum { + ds1685_reg_direct, + ds1685_reg_indirect + } access_type; }; -- cgit v1.2.3-71-gd317 From e502ff8606b32df4f9f2435ab00278312db125b3 Mon Sep 17 00:00:00 2001 From: Tejas Patel Date: Mon, 26 Aug 2019 13:30:44 -0700 Subject: soc: xilinx: Set CAP_UNUSABLE requirement for versal while powering down domain For "0" requirement which is used to inform firmware that device is not required currently by master, Versal PLM (Platform Loader and Manager) which runs on Platform Management Controller and is responsible platform management of devices that disables clock, power it down and reset the device. genpd_power_off() is being called during runtime suspend also. So, if any device goes to runtime suspend state during resumes it needs to be re-initialized again. It is possible that drivers do not reinitialize device upon resume from runtime suspend every time ans so dont want it to be powered down or get reset during runtime suspend. In Versal PLM new PM_CAP_UNUSABLE capability is added, which disables clock only and avoids power down and reset during runtime suspend. Power and reset will be gated with core suspend.So, this patch sets CAPABILITY_UNUSABLE requirement during gpd_power_off() if platform is other than zynqmp. Signed-off-by: Tejas Patel Signed-off-by: Jolly Shah Signed-off-by: Michal Simek --- drivers/soc/xilinx/zynqmp_pm_domains.c | 10 ++++++++-- include/linux/firmware/xlnx-zynqmp.h | 3 ++- 2 files changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/soc/xilinx/zynqmp_pm_domains.c b/drivers/soc/xilinx/zynqmp_pm_domains.c index 600f57cf0c2e..23d90cb12ba9 100644 --- a/drivers/soc/xilinx/zynqmp_pm_domains.c +++ b/drivers/soc/xilinx/zynqmp_pm_domains.c @@ -2,7 +2,7 @@ /* * ZynqMP Generic PM domain support * - * Copyright (C) 2015-2018 Xilinx, Inc. + * Copyright (C) 2015-2019 Xilinx, Inc. * * Davorin Mista * Jolly Shah @@ -25,6 +25,8 @@ static const struct zynqmp_eemi_ops *eemi_ops; +static int min_capability; + /** * struct zynqmp_pm_domain - Wrapper around struct generic_pm_domain * @gpd: Generic power domain @@ -106,7 +108,7 @@ static int zynqmp_gpd_power_off(struct generic_pm_domain *domain) int ret; struct pm_domain_data *pdd, *tmp; struct zynqmp_pm_domain *pd; - u32 capabilities = 0; + u32 capabilities = min_capability; bool may_wakeup; if (!eemi_ops->set_requirement) @@ -283,6 +285,10 @@ static int zynqmp_gpd_probe(struct platform_device *pdev) if (!domains) return -ENOMEM; + if (!of_device_is_compatible(dev->parent->of_node, + "xlnx,zynqmp-firmware")) + min_capability = ZYNQMP_PM_CAPABILITY_UNUSABLE; + for (i = 0; i < ZYNQMP_NUM_DOMAINS; i++, pd++) { pd->node_id = 0; pd->gpd.name = kasprintf(GFP_KERNEL, "domain%d", i); diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 778abbbc7d94..adb14bcedca2 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -2,7 +2,7 @@ /* * Xilinx Zynq MPSoC Firmware layer * - * Copyright (C) 2014-2018 Xilinx + * Copyright (C) 2014-2019 Xilinx * * Michal Simek * Davorin Mista @@ -46,6 +46,7 @@ #define ZYNQMP_PM_CAPABILITY_ACCESS 0x1U #define ZYNQMP_PM_CAPABILITY_CONTEXT 0x2U #define ZYNQMP_PM_CAPABILITY_WAKEUP 0x4U +#define ZYNQMP_PM_CAPABILITY_UNUSABLE 0x8U /* * Firmware FPGA Manager flags -- cgit v1.2.3-71-gd317 From e40d38f28c10e3010b2828f2c737b50fb81bda8f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 11 Oct 2019 15:29:29 +0200 Subject: debugfs: remove return value of debugfs_create_x16() No one checks the return value of debugfs_create_x16(), as it's not needed, so make the return value void, so that no one tries to do so in the future. Link: https://lore.kernel.org/r/20191011132931.1186197-6-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- Documentation/filesystems/debugfs.txt | 4 ++-- fs/debugfs/file.c | 6 +++--- include/linux/debugfs.h | 12 ++++-------- 3 files changed, 9 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/debugfs.txt b/Documentation/filesystems/debugfs.txt index 55a5da08c71c..4967f77a62a0 100644 --- a/Documentation/filesystems/debugfs.txt +++ b/Documentation/filesystems/debugfs.txt @@ -84,8 +84,8 @@ the following functions can be used instead: struct dentry *debugfs_create_x8(const char *name, umode_t mode, struct dentry *parent, u8 *value); - struct dentry *debugfs_create_x16(const char *name, umode_t mode, - struct dentry *parent, u16 *value); + void debugfs_create_x16(const char *name, umode_t mode, + struct dentry *parent, u16 *value); struct dentry *debugfs_create_x32(const char *name, umode_t mode, struct dentry *parent, u32 *value); struct dentry *debugfs_create_x64(const char *name, umode_t mode, diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index dfeda13023b3..cc6c76702e65 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -651,10 +651,10 @@ EXPORT_SYMBOL_GPL(debugfs_create_x8); * @value: a pointer to the variable that the file should read to and write * from. */ -struct dentry *debugfs_create_x16(const char *name, umode_t mode, - struct dentry *parent, u16 *value) +void debugfs_create_x16(const char *name, umode_t mode, struct dentry *parent, + u16 *value) { - return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x16, + debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x16, &fops_x16_ro, &fops_x16_wo); } EXPORT_SYMBOL_GPL(debugfs_create_x16); diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 1d859bc657bd..e742081c6844 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -109,8 +109,8 @@ struct dentry *debugfs_create_ulong(const char *name, umode_t mode, struct dentry *parent, unsigned long *value); struct dentry *debugfs_create_x8(const char *name, umode_t mode, struct dentry *parent, u8 *value); -struct dentry *debugfs_create_x16(const char *name, umode_t mode, - struct dentry *parent, u16 *value); +void debugfs_create_x16(const char *name, umode_t mode, struct dentry *parent, + u16 *value); struct dentry *debugfs_create_x32(const char *name, umode_t mode, struct dentry *parent, u32 *value); struct dentry *debugfs_create_x64(const char *name, umode_t mode, @@ -275,12 +275,8 @@ static inline struct dentry *debugfs_create_x8(const char *name, umode_t mode, return ERR_PTR(-ENODEV); } -static inline struct dentry *debugfs_create_x16(const char *name, umode_t mode, - struct dentry *parent, - u16 *value) -{ - return ERR_PTR(-ENODEV); -} +static inline void debugfs_create_x16(const char *name, umode_t mode, + struct dentry *parent, u16 *value) { } static inline struct dentry *debugfs_create_x32(const char *name, umode_t mode, struct dentry *parent, -- cgit v1.2.3-71-gd317 From f5cb0a7e64f41b6f1c5cacc64a476962f5e97f91 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 11 Oct 2019 15:29:30 +0200 Subject: debugfs: remove return value of debugfs_create_x32() No one checks the return value of debugfs_create_x32(), as it's not needed, so make the return value void, so that no one tries to do so in the future. Link: https://lore.kernel.org/r/20191011132931.1186197-7-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- Documentation/filesystems/debugfs.txt | 4 ++-- fs/debugfs/file.c | 6 +++--- include/linux/debugfs.h | 12 ++++-------- 3 files changed, 9 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/debugfs.txt b/Documentation/filesystems/debugfs.txt index 4967f77a62a0..94b8f9a0cb5e 100644 --- a/Documentation/filesystems/debugfs.txt +++ b/Documentation/filesystems/debugfs.txt @@ -86,8 +86,8 @@ the following functions can be used instead: struct dentry *parent, u8 *value); void debugfs_create_x16(const char *name, umode_t mode, struct dentry *parent, u16 *value); - struct dentry *debugfs_create_x32(const char *name, umode_t mode, - struct dentry *parent, u32 *value); + void debugfs_create_x32(const char *name, umode_t mode, + struct dentry *parent, u32 *value); struct dentry *debugfs_create_x64(const char *name, umode_t mode, struct dentry *parent, u64 *value); diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index cc6c76702e65..9c906251b3c6 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -669,10 +669,10 @@ EXPORT_SYMBOL_GPL(debugfs_create_x16); * @value: a pointer to the variable that the file should read to and write * from. */ -struct dentry *debugfs_create_x32(const char *name, umode_t mode, - struct dentry *parent, u32 *value) +void debugfs_create_x32(const char *name, umode_t mode, struct dentry *parent, + u32 *value) { - return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x32, + debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x32, &fops_x32_ro, &fops_x32_wo); } EXPORT_SYMBOL_GPL(debugfs_create_x32); diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index e742081c6844..89d0b02f82f5 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -111,8 +111,8 @@ struct dentry *debugfs_create_x8(const char *name, umode_t mode, struct dentry *parent, u8 *value); void debugfs_create_x16(const char *name, umode_t mode, struct dentry *parent, u16 *value); -struct dentry *debugfs_create_x32(const char *name, umode_t mode, - struct dentry *parent, u32 *value); +void debugfs_create_x32(const char *name, umode_t mode, struct dentry *parent, + u32 *value); struct dentry *debugfs_create_x64(const char *name, umode_t mode, struct dentry *parent, u64 *value); void debugfs_create_size_t(const char *name, umode_t mode, @@ -278,12 +278,8 @@ static inline struct dentry *debugfs_create_x8(const char *name, umode_t mode, static inline void debugfs_create_x16(const char *name, umode_t mode, struct dentry *parent, u16 *value) { } -static inline struct dentry *debugfs_create_x32(const char *name, umode_t mode, - struct dentry *parent, - u32 *value) -{ - return ERR_PTR(-ENODEV); -} +static inline void debugfs_create_x32(const char *name, umode_t mode, + struct dentry *parent, u32 *value) { } static inline struct dentry *debugfs_create_x64(const char *name, umode_t mode, struct dentry *parent, -- cgit v1.2.3-71-gd317 From 0864c408fb1e5b02d817cc8cd5b794d4cb491d50 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 11 Oct 2019 15:29:31 +0200 Subject: debugfs: remove return value of debugfs_create_x64() No one checks the return value of debugfs_create_x64(), as it's not needed, so make the return value void, so that no one tries to do so in the future. Link: https://lore.kernel.org/r/20191011132931.1186197-8-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- Documentation/filesystems/debugfs.txt | 4 ++-- fs/debugfs/file.c | 6 +++--- include/linux/debugfs.h | 12 ++++-------- 3 files changed, 9 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/debugfs.txt b/Documentation/filesystems/debugfs.txt index 94b8f9a0cb5e..9e705026ac10 100644 --- a/Documentation/filesystems/debugfs.txt +++ b/Documentation/filesystems/debugfs.txt @@ -88,8 +88,8 @@ the following functions can be used instead: struct dentry *parent, u16 *value); void debugfs_create_x32(const char *name, umode_t mode, struct dentry *parent, u32 *value); - struct dentry *debugfs_create_x64(const char *name, umode_t mode, - struct dentry *parent, u64 *value); + void debugfs_create_x64(const char *name, umode_t mode, + struct dentry *parent, u64 *value); These functions are useful as long as the developer knows the size of the value to be exported. Some types can have different widths on different diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 9c906251b3c6..3ff736f22eb6 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -687,10 +687,10 @@ EXPORT_SYMBOL_GPL(debugfs_create_x32); * @value: a pointer to the variable that the file should read to and write * from. */ -struct dentry *debugfs_create_x64(const char *name, umode_t mode, - struct dentry *parent, u64 *value) +void debugfs_create_x64(const char *name, umode_t mode, struct dentry *parent, + u64 *value) { - return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x64, + debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x64, &fops_x64_ro, &fops_x64_wo); } EXPORT_SYMBOL_GPL(debugfs_create_x64); diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 89d0b02f82f5..33690949b45d 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -113,8 +113,8 @@ void debugfs_create_x16(const char *name, umode_t mode, struct dentry *parent, u16 *value); void debugfs_create_x32(const char *name, umode_t mode, struct dentry *parent, u32 *value); -struct dentry *debugfs_create_x64(const char *name, umode_t mode, - struct dentry *parent, u64 *value); +void debugfs_create_x64(const char *name, umode_t mode, struct dentry *parent, + u64 *value); void debugfs_create_size_t(const char *name, umode_t mode, struct dentry *parent, size_t *value); struct dentry *debugfs_create_atomic_t(const char *name, umode_t mode, @@ -281,12 +281,8 @@ static inline void debugfs_create_x16(const char *name, umode_t mode, static inline void debugfs_create_x32(const char *name, umode_t mode, struct dentry *parent, u32 *value) { } -static inline struct dentry *debugfs_create_x64(const char *name, umode_t mode, - struct dentry *parent, - u64 *value) -{ - return ERR_PTR(-ENODEV); -} +static inline void debugfs_create_x64(const char *name, umode_t mode, + struct dentry *parent, u64 *value) { } static inline void debugfs_create_size_t(const char *name, umode_t mode, struct dentry *parent, size_t *value) -- cgit v1.2.3-71-gd317 From 2203cbf2c8b58a1e3bef98c47531d431d11639a0 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 15 Oct 2019 11:38:39 +0100 Subject: net: sfp: move fwnode parsing into sfp-bus layer Rather than parsing the sfp firmware node in phylink, parse it in the sfp-bus code, so we can re-use this code for PHYs without having to duplicate the parsing. Signed-off-by: Russell King Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 21 +++++---------- drivers/net/phy/sfp-bus.c | 65 ++++++++++++++++++++++++++++++----------------- include/linux/sfp.h | 10 ++++---- 3 files changed, 53 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 8e53ed90da3c..4c5e8b4f8d80 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -548,26 +548,17 @@ static const struct sfp_upstream_ops sfp_phylink_ops; static int phylink_register_sfp(struct phylink *pl, struct fwnode_handle *fwnode) { - struct fwnode_reference_args ref; + struct sfp_bus *bus; int ret; - if (!fwnode) - return 0; - - ret = fwnode_property_get_reference_args(fwnode, "sfp", NULL, - 0, 0, &ref); - if (ret < 0) { - if (ret == -ENOENT) - return 0; - - phylink_err(pl, "unable to parse \"sfp\" node: %d\n", - ret); + bus = sfp_register_upstream_node(fwnode, pl, &sfp_phylink_ops); + if (IS_ERR(bus)) { + ret = PTR_ERR(bus); + phylink_err(pl, "unable to attach SFP bus: %d\n", ret); return ret; } - pl->sfp_bus = sfp_register_upstream(ref.fwnode, pl, &sfp_phylink_ops); - if (!pl->sfp_bus) - return -ENOMEM; + pl->sfp_bus = bus; return 0; } diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index b23fc41896ef..d037aab6a71d 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -4,6 +4,7 @@ #include #include #include +#include #include #include @@ -445,45 +446,63 @@ static void sfp_upstream_clear(struct sfp_bus *bus) } /** - * sfp_register_upstream() - Register the neighbouring device - * @fwnode: firmware node for the SFP bus + * sfp_register_upstream_node() - parse and register the neighbouring device + * @fwnode: firmware node for the parent device (MAC or PHY) * @upstream: the upstream private data * @ops: the upstream's &struct sfp_upstream_ops * - * Register the upstream device (eg, PHY) with the SFP bus. MAC drivers - * should use phylink, which will call this function for them. Returns - * a pointer to the allocated &struct sfp_bus. + * Parse the parent device's firmware node for a SFP bus, and register the + * SFP bus using sfp_register_upstream(). * - * On error, returns %NULL. + * Returns: on success, a pointer to the sfp_bus structure, + * %NULL if no SFP is specified, + * on failure, an error pointer value: + * corresponding to the errors detailed for + * fwnode_property_get_reference_args(). + * %-ENOMEM if we failed to allocate the bus. + * an error from the upstream's connect_phy() method. */ -struct sfp_bus *sfp_register_upstream(struct fwnode_handle *fwnode, - void *upstream, - const struct sfp_upstream_ops *ops) +struct sfp_bus *sfp_register_upstream_node(struct fwnode_handle *fwnode, + void *upstream, + const struct sfp_upstream_ops *ops) { - struct sfp_bus *bus = sfp_bus_get(fwnode); - int ret = 0; + struct fwnode_reference_args ref; + struct sfp_bus *bus; + int ret; - if (bus) { - rtnl_lock(); - bus->upstream_ops = ops; - bus->upstream = upstream; + ret = fwnode_property_get_reference_args(fwnode, "sfp", NULL, + 0, 0, &ref); + if (ret == -ENOENT) + return NULL; + else if (ret < 0) + return ERR_PTR(ret); - if (bus->sfp) { - ret = sfp_register_bus(bus); - if (ret) - sfp_upstream_clear(bus); - } - rtnl_unlock(); + bus = sfp_bus_get(ref.fwnode); + fwnode_handle_put(ref.fwnode); + if (!bus) + return ERR_PTR(-ENOMEM); + + rtnl_lock(); + bus->upstream_ops = ops; + bus->upstream = upstream; + + if (bus->sfp) { + ret = sfp_register_bus(bus); + if (ret) + sfp_upstream_clear(bus); + } else { + ret = 0; } + rtnl_unlock(); if (ret) { sfp_bus_put(bus); - bus = NULL; + bus = ERR_PTR(ret); } return bus; } -EXPORT_SYMBOL_GPL(sfp_register_upstream); +EXPORT_SYMBOL_GPL(sfp_register_upstream_node); /** * sfp_unregister_upstream() - Unregister sfp bus diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 1c35428e98bc..355a08a76fd4 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -508,9 +508,9 @@ int sfp_get_module_eeprom(struct sfp_bus *bus, struct ethtool_eeprom *ee, u8 *data); void sfp_upstream_start(struct sfp_bus *bus); void sfp_upstream_stop(struct sfp_bus *bus); -struct sfp_bus *sfp_register_upstream(struct fwnode_handle *fwnode, - void *upstream, - const struct sfp_upstream_ops *ops); +struct sfp_bus *sfp_register_upstream_node(struct fwnode_handle *fwnode, + void *upstream, + const struct sfp_upstream_ops *ops); void sfp_unregister_upstream(struct sfp_bus *bus); #else static inline int sfp_parse_port(struct sfp_bus *bus, @@ -553,11 +553,11 @@ static inline void sfp_upstream_stop(struct sfp_bus *bus) { } -static inline struct sfp_bus *sfp_register_upstream( +static inline struct sfp_bus *sfp_register_upstream_node( struct fwnode_handle *fwnode, void *upstream, const struct sfp_upstream_ops *ops) { - return (struct sfp_bus *)-1; + return NULL; } static inline void sfp_unregister_upstream(struct sfp_bus *bus) -- cgit v1.2.3-71-gd317 From ca58fbe06c54795f00db79e447f94c2028d30124 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 11 Oct 2019 00:30:37 +0200 Subject: netfilter: add and use nf_hook_slow_list() At this time, NF_HOOK_LIST() macro will iterate the list and then calls nf_hook() for each individual skb. This makes it so the entire list is passed into the netfilter core. The advantage is that we only need to fetch the rule blob once per list instead of per-skb. NF_HOOK_LIST now only works for ipv4 and ipv6, as those are the only callers. v2: use skb_list_del_init() instead of list_del (Edward Cree) Signed-off-by: Florian Westphal Acked-by: Edward Cree Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 41 +++++++++++++++++++++++++++++++---------- net/netfilter/core.c | 20 ++++++++++++++++++++ 2 files changed, 51 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 77ebb61faf48..eb312e7ca36e 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -199,6 +199,8 @@ extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, const struct nf_hook_entries *e, unsigned int i); +void nf_hook_slow_list(struct list_head *head, struct nf_hook_state *state, + const struct nf_hook_entries *e); /** * nf_hook - call a netfilter hook * @@ -311,17 +313,36 @@ NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct list_head *head, struct net_device *in, struct net_device *out, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { - struct sk_buff *skb, *next; - struct list_head sublist; - - INIT_LIST_HEAD(&sublist); - list_for_each_entry_safe(skb, next, head, list) { - list_del(&skb->list); - if (nf_hook(pf, hook, net, sk, skb, in, out, okfn) == 1) - list_add_tail(&skb->list, &sublist); + struct nf_hook_entries *hook_head = NULL; + +#ifdef CONFIG_JUMP_LABEL + if (__builtin_constant_p(pf) && + __builtin_constant_p(hook) && + !static_key_false(&nf_hooks_needed[pf][hook])) + return; +#endif + + rcu_read_lock(); + switch (pf) { + case NFPROTO_IPV4: + hook_head = rcu_dereference(net->nf.hooks_ipv4[hook]); + break; + case NFPROTO_IPV6: + hook_head = rcu_dereference(net->nf.hooks_ipv6[hook]); + break; + default: + WARN_ON_ONCE(1); + break; } - /* Put passed packets back on main list */ - list_splice(&sublist, head); + + if (hook_head) { + struct nf_hook_state state; + + nf_hook_state_init(&state, hook, pf, in, out, sk, net, okfn); + + nf_hook_slow_list(head, &state, hook_head); + } + rcu_read_unlock(); } /* Call setsockopt() */ diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 5d5bdf450091..78f046ec506f 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -536,6 +536,26 @@ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, } EXPORT_SYMBOL(nf_hook_slow); +void nf_hook_slow_list(struct list_head *head, struct nf_hook_state *state, + const struct nf_hook_entries *e) +{ + struct sk_buff *skb, *next; + struct list_head sublist; + int ret; + + INIT_LIST_HEAD(&sublist); + + list_for_each_entry_safe(skb, next, head, list) { + skb_list_del_init(skb); + ret = nf_hook_slow(skb, state, e, 0); + if (ret == 1) + list_add_tail(&skb->list, &sublist); + } + /* Put passed packets back on main list */ + list_splice(&sublist, head); +} +EXPORT_SYMBOL(nf_hook_slow_list); + /* This needs to be compiled in any case to avoid dependencies between the * nfnetlink_queue code and nf_conntrack. */ -- cgit v1.2.3-71-gd317 From 92df01e3601fe29eb3727a82705eafa6209053f5 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Fri, 11 Oct 2019 12:15:20 -0700 Subject: driver: core: Improve documentation for fwnode_operations.add_links() The add_links() ops shouldn't return on the first failed device link add. It needs to continue trying to add device links to other suppliers that are available. The documentation didn't explain WHY this behavior is necessary. So, update the documentation with an example that explains why this is necessary. Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20191011191521.179614-3-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fwnode.h | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 6ae05b9ce359..97223e2410bd 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -71,8 +71,25 @@ struct fwnode_reference_args { * links to all the suppliers of the device that are available at * the time this function is called. The function must NOT stop * at the first failed device link if other unlinked supplier - * devices are present in the system. If some suppliers are not - * yet available, this function will be called again when other + * devices are present in the system. This is necessary for the + * driver/bus sync_state() callbacks to work correctly. + * + * For example, say Device-C depends on suppliers Device-S1 and + * Device-S2 and the dependency is listed in that order in the + * firmware. Say, S1 gets populated from the firmware after + * late_initcall_sync(). Say S2 is populated and probed way + * before that in device_initcall(). When C is populated, if this + * add_links() function doesn't continue past a "failed linking to + * S1" and continue linking C to S2, then S2 will get a + * sync_state() callback before C is probed. This is because from + * the perspective of S2, C was never a consumer when its + * sync_state() evaluation is done. To avoid this, the add_links() + * function has to go through all available suppliers of the + * device (that corresponds to this fwnode) and link to them + * before returning. + * + * If some suppliers are not yet available (indicated by an error + * return value), this function will be called again when other * devices are added to allow creating device links to any newly * available suppliers. * -- cgit v1.2.3-71-gd317 From 3d6d8da48d0b214d65ea0227d47228abc75d7c88 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 17 Oct 2019 12:18:28 +0200 Subject: pidfd: check pid has attached task in fdinfo Currently, when a task is dead we still print the pid it used to use in the fdinfo files of its pidfds. This doesn't make much sense since the pid may have already been reused. So verify that the task is still alive by introducing the pid_has_task() helper which will be used by other callers in follow-up patches. If the task is not alive anymore, we will print -1. This allows us to differentiate between a task not being present in a given pid namespace - in which case we already print 0 - and a task having been reaped. Note that this uses PIDTYPE_PID for the check. Technically, we could've checked PIDTYPE_TGID since pidfds currently only refer to thread-group leaders but if they won't anymore in the future then this check becomes problematic without it being immediately obvious to non-experts imho. If a thread is created via clone(CLONE_THREAD) than struct pid has a single non-empty list pid->tasks[PIDTYPE_PID] and this pid can't be used as a PIDTYPE_TGID meaning pid->tasks[PIDTYPE_TGID] will return NULL even though the thread-group leader might still be very much alive. So checking PIDTYPE_PID is fine and is easier to maintain should we ever allow pidfds to refer to threads. Cc: Jann Horn Cc: Christian Kellner Cc: linux-api@vger.kernel.org Signed-off-by: Christian Brauner Reviewed-by: Oleg Nesterov Link: https://lore.kernel.org/r/20191017101832.5985-1-christian.brauner@ubuntu.com --- include/linux/pid.h | 4 ++++ kernel/fork.c | 17 +++++++++++------ 2 files changed, 15 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index 9645b1194c98..034e3cd60dc0 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -85,6 +85,10 @@ static inline struct pid *get_pid(struct pid *pid) extern void put_pid(struct pid *pid); extern struct task_struct *pid_task(struct pid *pid, enum pid_type); +static inline bool pid_has_task(struct pid *pid, enum pid_type type) +{ + return !hlist_empty(&pid->tasks[type]); +} extern struct task_struct *get_pid_task(struct pid *pid, enum pid_type); extern struct pid *get_task_pid(struct task_struct *task, enum pid_type type); diff --git a/kernel/fork.c b/kernel/fork.c index 782986962d47..ffa314838b43 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1732,15 +1732,20 @@ static int pidfd_release(struct inode *inode, struct file *file) */ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) { - struct pid_namespace *ns = proc_pid_ns(file_inode(m->file)); struct pid *pid = f->private_data; - pid_t nr = pid_nr_ns(pid, ns); + struct pid_namespace *ns; + pid_t nr = -1; - seq_put_decimal_ull(m, "Pid:\t", nr); + if (likely(pid_has_task(pid, PIDTYPE_PID))) { + ns = proc_pid_ns(file_inode(m->file)); + nr = pid_nr_ns(pid, ns); + } + + seq_put_decimal_ll(m, "Pid:\t", nr); #ifdef CONFIG_PID_NS - seq_put_decimal_ull(m, "\nNSpid:\t", nr); - if (nr) { + seq_put_decimal_ll(m, "\nNSpid:\t", nr); + if (nr > 0) { int i; /* If nr is non-zero it means that 'pid' is valid and that @@ -1749,7 +1754,7 @@ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) * Start at one below the already printed level. */ for (i = ns->level + 1; i <= pid->level; i++) - seq_put_decimal_ull(m, "\t", pid->numbers[i].nr); + seq_put_decimal_ll(m, "\t", pid->numbers[i].nr); } #endif seq_putc(m, '\n'); -- cgit v1.2.3-71-gd317 From 57f5677e535ba24b8926a7125be2ef8d7f09323c Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 15 Oct 2019 21:07:05 +0200 Subject: printf: add support for printing symbolic error names MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It has been suggested several times to extend vsnprintf() to be able to convert the numeric value of ENOSPC to print "ENOSPC". This implements that as a %p extension: With %pe, one can do if (IS_ERR(foo)) { pr_err("Sorry, can't do that: %pe\n", foo); return PTR_ERR(foo); } instead of what is seen in quite a few places in the kernel: if (IS_ERR(foo)) { pr_err("Sorry, can't do that: %ld\n", PTR_ERR(foo)); return PTR_ERR(foo); } If the value passed to %pe is an ERR_PTR, but the library function errname() added here doesn't know about the value, the value is simply printed in decimal. If the value passed to %pe is not an ERR_PTR, we treat it as an ordinary %p and thus print the hashed value (passing non-ERR_PTR values to %pe indicates a bug in the caller, but we can't do much about that). With my embedded hat on, and because it's not very invasive to do, I've made it possible to remove this. The errname() function and associated lookup tables take up about 3K. For most, that's probably quite acceptable and a price worth paying for more readable dmesg (once this starts getting used), while for those that disable printk() it's of very little use - I don't see a procfs/sysfs/seq_printf() file reasonably making use of this - and they clearly want to squeeze vmlinux as much as possible. Hence the default y if PRINTK. The symbols to include have been found by massaging the output of find arch include -iname 'errno*.h' | xargs grep -E 'define\s*E' In the cases where some common aliasing exists (e.g. EAGAIN=EWOULDBLOCK on all platforms, EDEADLOCK=EDEADLK on most), I've moved the more popular one (in terms of 'git grep -w Efoo | wc) to the bottom so that one takes precedence. Link: http://lkml.kernel.org/r/20191015190706.15989-1-linux@rasmusvillemoes.dk To: "Jonathan Corbet" To: linux-kernel@vger.kernel.org Cc: "Andy Shevchenko" Cc: "Andrew Morton" Cc: "Joe Perches" Cc: linux-doc@vger.kernel.org Signed-off-by: Rasmus Villemoes Acked-by: Uwe Kleine-König Reviewed-by: Petr Mladek [andy.shevchenko@gmail.com: use abs()] Acked-by: Andy Shevchenko Signed-off-by: Petr Mladek --- Documentation/core-api/printk-formats.rst | 12 ++ include/linux/errname.h | 16 +++ lib/Kconfig.debug | 9 ++ lib/Makefile | 1 + lib/errname.c | 223 ++++++++++++++++++++++++++++++ lib/test_printf.c | 21 +++ lib/vsprintf.c | 27 ++++ 7 files changed, 309 insertions(+) create mode 100644 include/linux/errname.h create mode 100644 lib/errname.c (limited to 'include/linux') diff --git a/Documentation/core-api/printk-formats.rst b/Documentation/core-api/printk-formats.rst index 75d2bbe9813f..dffd5c0b24f8 100644 --- a/Documentation/core-api/printk-formats.rst +++ b/Documentation/core-api/printk-formats.rst @@ -79,6 +79,18 @@ has the added benefit of providing a unique identifier. On 64-bit machines the first 32 bits are zeroed. The kernel will print ``(ptrval)`` until it gathers enough entropy. If you *really* want the address see %px below. +Error Pointers +-------------- + +:: + + %pe -ENOSPC + +For printing error pointers (i.e. a pointer for which IS_ERR() is true) +as a symbolic error name. Error values for which no symbolic name is +known are printed in decimal, while a non-ERR_PTR passed as the +argument to %pe gets treated as ordinary %p. + Symbols/Function Pointers ------------------------- diff --git a/include/linux/errname.h b/include/linux/errname.h new file mode 100644 index 000000000000..e8576ad90cb7 --- /dev/null +++ b/include/linux/errname.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_ERRNAME_H +#define _LINUX_ERRNAME_H + +#include + +#ifdef CONFIG_SYMBOLIC_ERRNAME +const char *errname(int err); +#else +static inline const char *errname(int err) +{ + return NULL; +} +#endif + +#endif /* _LINUX_ERRNAME_H */ diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 06d9c9d70385..4934b69c7b39 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -164,6 +164,15 @@ config DYNAMIC_DEBUG See Documentation/admin-guide/dynamic-debug-howto.rst for additional information. +config SYMBOLIC_ERRNAME + bool "Support symbolic error names in printf" + default y if PRINTK + help + If you say Y here, the kernel's printf implementation will + be able to print symbolic error names such as ENOSPC instead + of the number 28. It makes the kernel image slightly larger + (about 3KB), but can make the kernel logs easier to read. + endmenu # "printk and dmesg options" menu "Compile-time checks and compiler options" diff --git a/lib/Makefile b/lib/Makefile index d3daedf93c5a..907759f28916 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -183,6 +183,7 @@ lib-$(CONFIG_GENERIC_BUG) += bug.o obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o obj-$(CONFIG_DYNAMIC_DEBUG) += dynamic_debug.o +obj-$(CONFIG_SYMBOLIC_ERRNAME) += errname.o obj-$(CONFIG_NLATTR) += nlattr.o diff --git a/lib/errname.c b/lib/errname.c new file mode 100644 index 000000000000..0c4d3e66170e --- /dev/null +++ b/lib/errname.c @@ -0,0 +1,223 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include + +/* + * Ensure these tables do not accidentally become gigantic if some + * huge errno makes it in. On most architectures, the first table will + * only have about 140 entries, but mips and parisc have more sparsely + * allocated errnos (with EHWPOISON = 257 on parisc, and EDQUOT = 1133 + * on mips), so this wastes a bit of space on those - though we + * special case the EDQUOT case. + */ +#define E(err) [err + BUILD_BUG_ON_ZERO(err <= 0 || err > 300)] = "-" #err +static const char *names_0[] = { + E(E2BIG), + E(EACCES), + E(EADDRINUSE), + E(EADDRNOTAVAIL), + E(EADV), + E(EAFNOSUPPORT), + E(EALREADY), + E(EBADE), + E(EBADF), + E(EBADFD), + E(EBADMSG), + E(EBADR), + E(EBADRQC), + E(EBADSLT), + E(EBFONT), + E(EBUSY), +#ifdef ECANCELLED + E(ECANCELLED), +#endif + E(ECHILD), + E(ECHRNG), + E(ECOMM), + E(ECONNABORTED), + E(ECONNRESET), + E(EDEADLOCK), + E(EDESTADDRREQ), + E(EDOM), + E(EDOTDOT), +#ifndef CONFIG_MIPS + E(EDQUOT), +#endif + E(EEXIST), + E(EFAULT), + E(EFBIG), + E(EHOSTDOWN), + E(EHOSTUNREACH), + E(EHWPOISON), + E(EIDRM), + E(EILSEQ), +#ifdef EINIT + E(EINIT), +#endif + E(EINPROGRESS), + E(EINTR), + E(EINVAL), + E(EIO), + E(EISCONN), + E(EISDIR), + E(EISNAM), + E(EKEYEXPIRED), + E(EKEYREJECTED), + E(EKEYREVOKED), + E(EL2HLT), + E(EL2NSYNC), + E(EL3HLT), + E(EL3RST), + E(ELIBACC), + E(ELIBBAD), + E(ELIBEXEC), + E(ELIBMAX), + E(ELIBSCN), + E(ELNRNG), + E(ELOOP), + E(EMEDIUMTYPE), + E(EMFILE), + E(EMLINK), + E(EMSGSIZE), + E(EMULTIHOP), + E(ENAMETOOLONG), + E(ENAVAIL), + E(ENETDOWN), + E(ENETRESET), + E(ENETUNREACH), + E(ENFILE), + E(ENOANO), + E(ENOBUFS), + E(ENOCSI), + E(ENODATA), + E(ENODEV), + E(ENOENT), + E(ENOEXEC), + E(ENOKEY), + E(ENOLCK), + E(ENOLINK), + E(ENOMEDIUM), + E(ENOMEM), + E(ENOMSG), + E(ENONET), + E(ENOPKG), + E(ENOPROTOOPT), + E(ENOSPC), + E(ENOSR), + E(ENOSTR), +#ifdef ENOSYM + E(ENOSYM), +#endif + E(ENOSYS), + E(ENOTBLK), + E(ENOTCONN), + E(ENOTDIR), + E(ENOTEMPTY), + E(ENOTNAM), + E(ENOTRECOVERABLE), + E(ENOTSOCK), + E(ENOTTY), + E(ENOTUNIQ), + E(ENXIO), + E(EOPNOTSUPP), + E(EOVERFLOW), + E(EOWNERDEAD), + E(EPERM), + E(EPFNOSUPPORT), + E(EPIPE), +#ifdef EPROCLIM + E(EPROCLIM), +#endif + E(EPROTO), + E(EPROTONOSUPPORT), + E(EPROTOTYPE), + E(ERANGE), + E(EREMCHG), +#ifdef EREMDEV + E(EREMDEV), +#endif + E(EREMOTE), + E(EREMOTEIO), +#ifdef EREMOTERELEASE + E(EREMOTERELEASE), +#endif + E(ERESTART), + E(ERFKILL), + E(EROFS), +#ifdef ERREMOTE + E(ERREMOTE), +#endif + E(ESHUTDOWN), + E(ESOCKTNOSUPPORT), + E(ESPIPE), + E(ESRCH), + E(ESRMNT), + E(ESTALE), + E(ESTRPIPE), + E(ETIME), + E(ETIMEDOUT), + E(ETOOMANYREFS), + E(ETXTBSY), + E(EUCLEAN), + E(EUNATCH), + E(EUSERS), + E(EXDEV), + E(EXFULL), + + E(ECANCELED), /* ECANCELLED */ + E(EAGAIN), /* EWOULDBLOCK */ + E(ECONNREFUSED), /* EREFUSED */ + E(EDEADLK), /* EDEADLOCK */ +}; +#undef E + +#define E(err) [err - 512 + BUILD_BUG_ON_ZERO(err < 512 || err > 550)] = "-" #err +static const char *names_512[] = { + E(ERESTARTSYS), + E(ERESTARTNOINTR), + E(ERESTARTNOHAND), + E(ENOIOCTLCMD), + E(ERESTART_RESTARTBLOCK), + E(EPROBE_DEFER), + E(EOPENSTALE), + E(ENOPARAM), + + E(EBADHANDLE), + E(ENOTSYNC), + E(EBADCOOKIE), + E(ENOTSUPP), + E(ETOOSMALL), + E(ESERVERFAULT), + E(EBADTYPE), + E(EJUKEBOX), + E(EIOCBQUEUED), + E(ERECALLCONFLICT), +}; +#undef E + +static const char *__errname(unsigned err) +{ + if (err < ARRAY_SIZE(names_0)) + return names_0[err]; + if (err >= 512 && err - 512 < ARRAY_SIZE(names_512)) + return names_512[err - 512]; + /* But why? */ + if (IS_ENABLED(CONFIG_MIPS) && err == EDQUOT) /* 1133 */ + return "-EDQUOT"; + return NULL; +} + +/* + * errname(EIO) -> "EIO" + * errname(-EIO) -> "-EIO" + */ +const char *errname(int err) +{ + const char *name = __errname(abs(err)); + if (!name) + return NULL; + + return err > 0 ? name + 1 : name; +} diff --git a/lib/test_printf.c b/lib/test_printf.c index 5d94cbff2120..030daeb4fe21 100644 --- a/lib/test_printf.c +++ b/lib/test_printf.c @@ -593,6 +593,26 @@ flags(void) kfree(cmp_buffer); } +static void __init +errptr(void) +{ + test("-1234", "%pe", ERR_PTR(-1234)); + + /* Check that %pe with a non-ERR_PTR gets treated as ordinary %p. */ + BUILD_BUG_ON(IS_ERR(PTR)); + test_hashed("%pe", PTR); + +#ifdef CONFIG_SYMBOLIC_ERRNAME + test("(-ENOTSOCK)", "(%pe)", ERR_PTR(-ENOTSOCK)); + test("(-EAGAIN)", "(%pe)", ERR_PTR(-EAGAIN)); + BUILD_BUG_ON(EAGAIN != EWOULDBLOCK); + test("(-EAGAIN)", "(%pe)", ERR_PTR(-EWOULDBLOCK)); + test("[-EIO ]", "[%-8pe]", ERR_PTR(-EIO)); + test("[ -EIO]", "[%8pe]", ERR_PTR(-EIO)); + test("-EPROBE_DEFER", "%pe", ERR_PTR(-EPROBE_DEFER)); +#endif +} + static void __init test_pointer(void) { @@ -615,6 +635,7 @@ test_pointer(void) bitmap(); netdev_features(); flags(); + errptr(); } static void __init selftest(void) diff --git a/lib/vsprintf.c b/lib/vsprintf.c index e78017a3e1bd..b54d252b398e 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -21,6 +21,7 @@ #include #include #include +#include #include /* for KSYM_SYMBOL_LEN */ #include #include @@ -613,6 +614,25 @@ static char *string_nocheck(char *buf, char *end, const char *s, return widen_string(buf, len, end, spec); } +static char *err_ptr(char *buf, char *end, void *ptr, + struct printf_spec spec) +{ + int err = PTR_ERR(ptr); + const char *sym = errname(err); + + if (sym) + return string_nocheck(buf, end, sym, spec); + + /* + * Somebody passed ERR_PTR(-1234) or some other non-existing + * Efoo - or perhaps CONFIG_SYMBOLIC_ERRNAME=n. Fall back to + * printing it as its decimal representation. + */ + spec.flags |= SIGN; + spec.base = 10; + return number(buf, end, err, spec); +} + /* Be careful: error messages must fit into the given buffer. */ static char *error_string(char *buf, char *end, const char *s, struct printf_spec spec) @@ -2187,6 +2207,11 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr, return kobject_string(buf, end, ptr, spec, fmt); case 'x': return pointer_string(buf, end, ptr, spec); + case 'e': + /* %pe with a non-ERR_PTR gets treated as plain %p */ + if (!IS_ERR(ptr)) + break; + return err_ptr(buf, end, ptr, spec); } /* default is to _not_ leak addresses, hash before printing */ @@ -2823,6 +2848,7 @@ int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args) case 'f': case 'x': case 'K': + case 'e': save_arg(void *); break; default: @@ -2999,6 +3025,7 @@ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf) case 'f': case 'x': case 'K': + case 'e': process = true; break; default: -- cgit v1.2.3-71-gd317 From 32adcaa010fa85e09296a6a606ad07348ef349ed Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Thu, 8 Aug 2019 15:47:24 +0200 Subject: ARM: mmp: move cputype.h to include/linux/soc/ Let's move cputype.h away from mach-mmp/ so that the drivers outside that directory are able to tell the precise silicon revision. The MMP3 USB OTG PHY driver needs this. Signed-off-by: Lubomir Rintel --- MAINTAINERS | 1 + arch/arm/mach-mmp/common.c | 2 +- arch/arm/mach-mmp/cputype.h | 85 ----------------------------------------- arch/arm/mach-mmp/devices.c | 2 +- arch/arm/mach-mmp/mmp2.c | 2 +- arch/arm/mach-mmp/pm-mmp2.c | 2 +- arch/arm/mach-mmp/pm-pxa910.c | 2 +- arch/arm/mach-mmp/pxa168.c | 2 +- arch/arm/mach-mmp/pxa910.c | 2 +- arch/arm/mach-mmp/time.c | 2 +- include/Kbuild | 1 + include/linux/soc/mmp/cputype.h | 85 +++++++++++++++++++++++++++++++++++++++++ 12 files changed, 95 insertions(+), 93 deletions(-) delete mode 100644 arch/arm/mach-mmp/cputype.h create mode 100644 include/linux/soc/mmp/cputype.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 296de2b51c83..85f64ade294d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10908,6 +10908,7 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Odd Fixes F: arch/arm/boot/dts/mmp* F: arch/arm/mach-mmp/ +F: linux/soc/mmp/ MMU GATHER AND TLB INVALIDATION M: Will Deacon diff --git a/arch/arm/mach-mmp/common.c b/arch/arm/mach-mmp/common.c index 24c689a01ecb..e94349d4726c 100644 --- a/arch/arm/mach-mmp/common.c +++ b/arch/arm/mach-mmp/common.c @@ -13,7 +13,7 @@ #include #include #include "addr-map.h" -#include "cputype.h" +#include #include "common.h" diff --git a/arch/arm/mach-mmp/cputype.h b/arch/arm/mach-mmp/cputype.h deleted file mode 100644 index c3ec88983e94..000000000000 --- a/arch/arm/mach-mmp/cputype.h +++ /dev/null @@ -1,85 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_MACH_CPUTYPE_H -#define __ASM_MACH_CPUTYPE_H - -#include - -/* - * CPU Stepping CPU_ID CHIP_ID - * - * PXA168 S0 0x56158400 0x0000C910 - * PXA168 A0 0x56158400 0x00A0A168 - * PXA910 Y1 0x56158400 0x00F2C920 - * PXA910 A0 0x56158400 0x00F2C910 - * PXA910 A1 0x56158400 0x00A0C910 - * PXA920 Y0 0x56158400 0x00F2C920 - * PXA920 A0 0x56158400 0x00A0C920 - * PXA920 A1 0x56158400 0x00A1C920 - * MMP2 Z0 0x560f5811 0x00F00410 - * MMP2 Z1 0x560f5811 0x00E00410 - * MMP2 A0 0x560f5811 0x00A0A610 - * MMP3 A0 0x562f5842 0x00A02128 - * MMP3 B0 0x562f5842 0x00B02128 - */ - -extern unsigned int mmp_chip_id; - -#ifdef CONFIG_CPU_PXA168 -static inline int cpu_is_pxa168(void) -{ - return (((read_cpuid_id() >> 8) & 0xff) == 0x84) && - ((mmp_chip_id & 0xfff) == 0x168); -} -#else -#define cpu_is_pxa168() (0) -#endif - -/* cpu_is_pxa910() is shared on both pxa910 and pxa920 */ -#ifdef CONFIG_CPU_PXA910 -static inline int cpu_is_pxa910(void) -{ - return (((read_cpuid_id() >> 8) & 0xff) == 0x84) && - (((mmp_chip_id & 0xfff) == 0x910) || - ((mmp_chip_id & 0xfff) == 0x920)); -} -#else -#define cpu_is_pxa910() (0) -#endif - -#if defined(CONFIG_CPU_MMP2) || defined(CONFIG_MACH_MMP2_DT) -static inline int cpu_is_mmp2(void) -{ - return (((read_cpuid_id() >> 8) & 0xff) == 0x58) && - (((mmp_chip_id & 0xfff) == 0x410) || - ((mmp_chip_id & 0xfff) == 0x610)); -} -#else -#define cpu_is_mmp2() (0) -#endif - -#ifdef CONFIG_MACH_MMP3_DT -static inline int cpu_is_mmp3(void) -{ - return (((read_cpuid_id() >> 8) & 0xff) == 0x58) && - ((mmp_chip_id & 0xffff) == 0x2128); -} - -static inline int cpu_is_mmp3_a0(void) -{ - return (cpu_is_mmp3() && - ((mmp_chip_id & 0x00ff0000) == 0x00a00000)); -} - -static inline int cpu_is_mmp3_b0(void) -{ - return (cpu_is_mmp3() && - ((mmp_chip_id & 0x00ff0000) == 0x00b00000)); -} - -#else -#define cpu_is_mmp3() (0) -#define cpu_is_mmp3_a0() (0) -#define cpu_is_mmp3_b0() (0) -#endif - -#endif /* __ASM_MACH_CPUTYPE_H */ diff --git a/arch/arm/mach-mmp/devices.c b/arch/arm/mach-mmp/devices.c index 130c1a603ba2..18bee66a671f 100644 --- a/arch/arm/mach-mmp/devices.c +++ b/arch/arm/mach-mmp/devices.c @@ -11,7 +11,7 @@ #include #include "irqs.h" #include "devices.h" -#include "cputype.h" +#include #include "regs-usb.h" int __init pxa_register_device(struct pxa_device_desc *desc, diff --git a/arch/arm/mach-mmp/mmp2.c b/arch/arm/mach-mmp/mmp2.c index 18ea3e1a26e6..bbc4c2274de3 100644 --- a/arch/arm/mach-mmp/mmp2.c +++ b/arch/arm/mach-mmp/mmp2.c @@ -20,7 +20,7 @@ #include #include "addr-map.h" #include "regs-apbc.h" -#include "cputype.h" +#include #include "irqs.h" #include "mfp.h" #include "devices.h" diff --git a/arch/arm/mach-mmp/pm-mmp2.c b/arch/arm/mach-mmp/pm-mmp2.c index 2923dd5732a6..2d86381e152d 100644 --- a/arch/arm/mach-mmp/pm-mmp2.c +++ b/arch/arm/mach-mmp/pm-mmp2.c @@ -17,7 +17,7 @@ #include #include -#include "cputype.h" +#include #include "addr-map.h" #include "pm-mmp2.h" #include "regs-icu.h" diff --git a/arch/arm/mach-mmp/pm-pxa910.c b/arch/arm/mach-mmp/pm-pxa910.c index 58535ce206dc..69ebe18ff209 100644 --- a/arch/arm/mach-mmp/pm-pxa910.c +++ b/arch/arm/mach-mmp/pm-pxa910.c @@ -18,7 +18,7 @@ #include #include -#include "cputype.h" +#include #include "addr-map.h" #include "pm-pxa910.h" #include "regs-icu.h" diff --git a/arch/arm/mach-mmp/pxa168.c b/arch/arm/mach-mmp/pxa168.c index 6e0277488967..b642e900727a 100644 --- a/arch/arm/mach-mmp/pxa168.c +++ b/arch/arm/mach-mmp/pxa168.c @@ -21,7 +21,7 @@ #include "addr-map.h" #include "clock.h" #include "common.h" -#include "cputype.h" +#include #include "devices.h" #include "irqs.h" #include "mfp.h" diff --git a/arch/arm/mach-mmp/pxa910.c b/arch/arm/mach-mmp/pxa910.c index cba31c758dea..b19a069d9fab 100644 --- a/arch/arm/mach-mmp/pxa910.c +++ b/arch/arm/mach-mmp/pxa910.c @@ -18,7 +18,7 @@ #include #include "addr-map.h" #include "regs-apbc.h" -#include "cputype.h" +#include #include "irqs.h" #include "mfp.h" #include "devices.h" diff --git a/arch/arm/mach-mmp/time.c b/arch/arm/mach-mmp/time.c index 8f4cacbf640e..110dcb3314d1 100644 --- a/arch/arm/mach-mmp/time.c +++ b/arch/arm/mach-mmp/time.c @@ -33,7 +33,7 @@ #include "regs-timers.h" #include "regs-apbc.h" #include "irqs.h" -#include "cputype.h" +#include #include "clock.h" #define TIMERS_VIRT_BASE TIMERS1_VIRT_BASE diff --git a/include/Kbuild b/include/Kbuild index ffba79483cc5..5a01ab62f61e 100644 --- a/include/Kbuild +++ b/include/Kbuild @@ -633,6 +633,7 @@ header-test- += linux/soc/amlogic/meson-canvas.h header-test- += linux/soc/brcmstb/brcmstb.h header-test- += linux/soc/ixp4xx/npe.h header-test- += linux/soc/mediatek/infracfg.h +header-test- += linux/soc/mmp/cputype.h header-test- += linux/soc/qcom/smd-rpm.h header-test- += linux/soc/qcom/smem.h header-test- += linux/soc/qcom/smem_state.h diff --git a/include/linux/soc/mmp/cputype.h b/include/linux/soc/mmp/cputype.h new file mode 100644 index 000000000000..c3ec88983e94 --- /dev/null +++ b/include/linux/soc/mmp/cputype.h @@ -0,0 +1,85 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_MACH_CPUTYPE_H +#define __ASM_MACH_CPUTYPE_H + +#include + +/* + * CPU Stepping CPU_ID CHIP_ID + * + * PXA168 S0 0x56158400 0x0000C910 + * PXA168 A0 0x56158400 0x00A0A168 + * PXA910 Y1 0x56158400 0x00F2C920 + * PXA910 A0 0x56158400 0x00F2C910 + * PXA910 A1 0x56158400 0x00A0C910 + * PXA920 Y0 0x56158400 0x00F2C920 + * PXA920 A0 0x56158400 0x00A0C920 + * PXA920 A1 0x56158400 0x00A1C920 + * MMP2 Z0 0x560f5811 0x00F00410 + * MMP2 Z1 0x560f5811 0x00E00410 + * MMP2 A0 0x560f5811 0x00A0A610 + * MMP3 A0 0x562f5842 0x00A02128 + * MMP3 B0 0x562f5842 0x00B02128 + */ + +extern unsigned int mmp_chip_id; + +#ifdef CONFIG_CPU_PXA168 +static inline int cpu_is_pxa168(void) +{ + return (((read_cpuid_id() >> 8) & 0xff) == 0x84) && + ((mmp_chip_id & 0xfff) == 0x168); +} +#else +#define cpu_is_pxa168() (0) +#endif + +/* cpu_is_pxa910() is shared on both pxa910 and pxa920 */ +#ifdef CONFIG_CPU_PXA910 +static inline int cpu_is_pxa910(void) +{ + return (((read_cpuid_id() >> 8) & 0xff) == 0x84) && + (((mmp_chip_id & 0xfff) == 0x910) || + ((mmp_chip_id & 0xfff) == 0x920)); +} +#else +#define cpu_is_pxa910() (0) +#endif + +#if defined(CONFIG_CPU_MMP2) || defined(CONFIG_MACH_MMP2_DT) +static inline int cpu_is_mmp2(void) +{ + return (((read_cpuid_id() >> 8) & 0xff) == 0x58) && + (((mmp_chip_id & 0xfff) == 0x410) || + ((mmp_chip_id & 0xfff) == 0x610)); +} +#else +#define cpu_is_mmp2() (0) +#endif + +#ifdef CONFIG_MACH_MMP3_DT +static inline int cpu_is_mmp3(void) +{ + return (((read_cpuid_id() >> 8) & 0xff) == 0x58) && + ((mmp_chip_id & 0xffff) == 0x2128); +} + +static inline int cpu_is_mmp3_a0(void) +{ + return (cpu_is_mmp3() && + ((mmp_chip_id & 0x00ff0000) == 0x00a00000)); +} + +static inline int cpu_is_mmp3_b0(void) +{ + return (cpu_is_mmp3() && + ((mmp_chip_id & 0x00ff0000) == 0x00b00000)); +} + +#else +#define cpu_is_mmp3() (0) +#define cpu_is_mmp3_a0() (0) +#define cpu_is_mmp3_b0() (0) +#endif + +#endif /* __ASM_MACH_CPUTYPE_H */ -- cgit v1.2.3-71-gd317 From 7c6a469e3416fa23568c2395a3faa7dd6e376dcb Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 15 Oct 2019 20:24:56 -0700 Subject: bpf: Add typecast to bpf helpers to help BTF generation When pahole converts dwarf to btf it emits only used types. Wrap existing bpf helper functions into typedef and use it in typecast to make gcc emits this type into dwarf. Then pahole will convert it to btf. The "btf_#name_of_helper" types will be used to figure out types of arguments of bpf helpers. The generated code before and after is the same. Only dwarf and btf sections are different. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: John Fastabend Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20191016032505.2089704-3-ast@kernel.org --- include/linux/filter.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 2ce57645f3cd..d3d51d7aff2c 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -464,10 +464,11 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) #define BPF_CALL_x(x, name, ...) \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ + typedef u64 (*btf_##name)(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)); \ u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)) \ { \ - return ____##name(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\ + return ((btf_##name)____##name)(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\ } \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)) -- cgit v1.2.3-71-gd317 From 8580ac9404f6240668a026785d7d8856f0530409 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 15 Oct 2019 20:24:57 -0700 Subject: bpf: Process in-kernel BTF If in-kernel BTF exists parse it and prepare 'struct btf *btf_vmlinux' for further use by the verifier. In-kernel BTF is trusted just like kallsyms and other build artifacts embedded into vmlinux. Yet run this BTF image through BTF verifier to make sure that it is valid and it wasn't mangled during the build. If in-kernel BTF is incorrect it means either gcc or pahole or kernel are buggy. In such case disallow loading BPF programs. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20191016032505.2089704-4-ast@kernel.org --- include/linux/bpf_verifier.h | 4 ++- include/linux/btf.h | 1 + kernel/bpf/btf.c | 71 +++++++++++++++++++++++++++++++++++++++++++- kernel/bpf/verifier.c | 20 +++++++++++++ 4 files changed, 94 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 26a6d58ca78c..713efae62e96 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -330,10 +330,12 @@ static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log) #define BPF_LOG_STATS 4 #define BPF_LOG_LEVEL (BPF_LOG_LEVEL1 | BPF_LOG_LEVEL2) #define BPF_LOG_MASK (BPF_LOG_LEVEL | BPF_LOG_STATS) +#define BPF_LOG_KERNEL (BPF_LOG_MASK + 1) /* kernel internal flag */ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) { - return log->level && log->ubuf && !bpf_verifier_log_full(log); + return (log->level && log->ubuf && !bpf_verifier_log_full(log)) || + log->level == BPF_LOG_KERNEL; } #define BPF_MAX_SUBPROGS 256 diff --git a/include/linux/btf.h b/include/linux/btf.h index 64cdf2a23d42..55d43bc856be 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -56,6 +56,7 @@ bool btf_type_is_void(const struct btf_type *t); #ifdef CONFIG_BPF_SYSCALL const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); const char *btf_name_by_offset(const struct btf *btf, u32 offset); +struct btf *btf_parse_vmlinux(void); #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 29c7c06c6bd6..ddeab1e8d21e 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -698,6 +698,13 @@ __printf(4, 5) static void __btf_verifier_log_type(struct btf_verifier_env *env, if (!bpf_verifier_log_needed(log)) return; + /* btf verifier prints all types it is processing via + * btf_verifier_log_type(..., fmt = NULL). + * Skip those prints for in-kernel BTF verification. + */ + if (log->level == BPF_LOG_KERNEL && !fmt) + return; + __btf_verifier_log(log, "[%u] %s %s%s", env->log_type_id, btf_kind_str[kind], @@ -735,6 +742,8 @@ static void btf_verifier_log_member(struct btf_verifier_env *env, if (!bpf_verifier_log_needed(log)) return; + if (log->level == BPF_LOG_KERNEL && !fmt) + return; /* The CHECK_META phase already did a btf dump. * * If member is logged again, it must hit an error in @@ -777,6 +786,8 @@ static void btf_verifier_log_vsi(struct btf_verifier_env *env, if (!bpf_verifier_log_needed(log)) return; + if (log->level == BPF_LOG_KERNEL && !fmt) + return; if (env->phase != CHECK_META) btf_verifier_log_type(env, datasec_type, NULL); @@ -802,6 +813,8 @@ static void btf_verifier_log_hdr(struct btf_verifier_env *env, if (!bpf_verifier_log_needed(log)) return; + if (log->level == BPF_LOG_KERNEL) + return; hdr = &btf->hdr; __btf_verifier_log(log, "magic: 0x%x\n", hdr->magic); __btf_verifier_log(log, "version: %u\n", hdr->version); @@ -2405,7 +2418,8 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env, return -EINVAL; } - + if (env->log.level == BPF_LOG_KERNEL) + continue; btf_verifier_log(env, "\t%s val=%d\n", __btf_name_by_offset(btf, enums[i].name_off), enums[i].val); @@ -3367,6 +3381,61 @@ errout: return ERR_PTR(err); } +extern char __weak _binary__btf_vmlinux_bin_start[]; +extern char __weak _binary__btf_vmlinux_bin_end[]; + +struct btf *btf_parse_vmlinux(void) +{ + struct btf_verifier_env *env = NULL; + struct bpf_verifier_log *log; + struct btf *btf = NULL; + int err; + + env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN); + if (!env) + return ERR_PTR(-ENOMEM); + + log = &env->log; + log->level = BPF_LOG_KERNEL; + + btf = kzalloc(sizeof(*btf), GFP_KERNEL | __GFP_NOWARN); + if (!btf) { + err = -ENOMEM; + goto errout; + } + env->btf = btf; + + btf->data = _binary__btf_vmlinux_bin_start; + btf->data_size = _binary__btf_vmlinux_bin_end - + _binary__btf_vmlinux_bin_start; + + err = btf_parse_hdr(env); + if (err) + goto errout; + + btf->nohdr_data = btf->data + btf->hdr.hdr_len; + + err = btf_parse_str_sec(env); + if (err) + goto errout; + + err = btf_check_all_metas(env); + if (err) + goto errout; + + btf_verifier_env_free(env); + refcount_set(&btf->refcnt, 1); + return btf; + +errout: + btf_verifier_env_free(env); + if (btf) { + kvfree(btf->types); + kfree(btf); + } + return ERR_PTR(err); +} + void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, struct seq_file *m) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d3446f018b9a..466b3b19de4d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -207,6 +207,8 @@ struct bpf_call_arg_meta { int func_id; }; +struct btf *btf_vmlinux; + static DEFINE_MUTEX(bpf_verifier_lock); static const struct bpf_line_info * @@ -243,6 +245,10 @@ void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, n = min(log->len_total - log->len_used - 1, n); log->kbuf[n] = '\0'; + if (log->level == BPF_LOG_KERNEL) { + pr_err("BPF:%s\n", log->kbuf); + return; + } if (!copy_to_user(log->ubuf + log->len_used, log->kbuf, n + 1)) log->len_used += n; else @@ -9294,6 +9300,13 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, env->ops = bpf_verifier_ops[env->prog->type]; is_priv = capable(CAP_SYS_ADMIN); + if (!btf_vmlinux && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) { + mutex_lock(&bpf_verifier_lock); + if (!btf_vmlinux) + btf_vmlinux = btf_parse_vmlinux(); + mutex_unlock(&bpf_verifier_lock); + } + /* grab the mutex to protect few globals used by verifier */ if (!is_priv) mutex_lock(&bpf_verifier_lock); @@ -9313,6 +9326,13 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, goto err_unlock; } + if (IS_ERR(btf_vmlinux)) { + /* Either gcc or pahole or kernel are broken. */ + verbose(env, "in-kernel BTF is malformed\n"); + ret = PTR_ERR(btf_vmlinux); + goto err_unlock; + } + env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT); if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) env->strict_alignment = true; -- cgit v1.2.3-71-gd317 From ccfe29eb29c2edcea6552072ef00ff4117f53e83 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 15 Oct 2019 20:24:58 -0700 Subject: bpf: Add attach_btf_id attribute to program load Add attach_btf_id attribute to prog_load command. It's similar to existing expected_attach_type attribute which is used in several cgroup based program types. Unfortunately expected_attach_type is ignored for tracing programs and cannot be reused for new purpose. Hence introduce attach_btf_id to verify bpf programs against given in-kernel BTF type id at load time. It is strictly checked to be valid for raw_tp programs only. In a later patches it will become: btf_id == 0 semantics of existing raw_tp progs. btd_id > 0 raw_tp with BTF and additional type safety. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20191016032505.2089704-5-ast@kernel.org --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 1 + kernel/bpf/syscall.c | 18 ++++++++++++++---- tools/include/uapi/linux/bpf.h | 1 + 4 files changed, 17 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 282e28bf41ec..f916380675dd 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -375,6 +375,7 @@ struct bpf_prog_aux { u32 id; u32 func_cnt; /* used by non-func prog as the number of func progs */ u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */ + u32 attach_btf_id; /* in-kernel BTF type id to attach to */ bool verifier_zext; /* Zero extensions has been inserted by verifier. */ bool offload_requested; struct bpf_prog **func; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a65c3b0c6935..3bb2cd1de341 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -420,6 +420,7 @@ union bpf_attr { __u32 line_info_rec_size; /* userspace bpf_line_info size */ __aligned_u64 line_info; /* line info */ __u32 line_info_cnt; /* number of bpf_line_info records */ + __u32 attach_btf_id; /* in-kernel BTF type id to attach to */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 82eabd4e38ad..b56c482c9760 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -23,6 +23,7 @@ #include #include #include +#include #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ @@ -1565,8 +1566,9 @@ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr) } static int -bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type, - enum bpf_attach_type expected_attach_type) +bpf_prog_load_check_attach(enum bpf_prog_type prog_type, + enum bpf_attach_type expected_attach_type, + u32 btf_id) { switch (prog_type) { case BPF_PROG_TYPE_CGROUP_SOCK: @@ -1608,13 +1610,19 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type, default: return -EINVAL; } + case BPF_PROG_TYPE_RAW_TRACEPOINT: + if (btf_id > BTF_MAX_TYPE) + return -EINVAL; + return 0; default: + if (btf_id) + return -EINVAL; return 0; } } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD line_info_cnt +#define BPF_PROG_LOAD_LAST_FIELD attach_btf_id static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) { @@ -1656,7 +1664,8 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) return -EPERM; bpf_prog_load_fixup_attach_type(attr); - if (bpf_prog_load_check_attach_type(type, attr->expected_attach_type)) + if (bpf_prog_load_check_attach(type, attr->expected_attach_type, + attr->attach_btf_id)) return -EINVAL; /* plain bpf_prog allocation */ @@ -1665,6 +1674,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) return -ENOMEM; prog->expected_attach_type = attr->expected_attach_type; + prog->aux->attach_btf_id = attr->attach_btf_id; prog->aux->offload_requested = !!attr->prog_ifindex; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index a65c3b0c6935..3bb2cd1de341 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -420,6 +420,7 @@ union bpf_attr { __u32 line_info_rec_size; /* userspace bpf_line_info size */ __aligned_u64 line_info; /* line info */ __u32 line_info_cnt; /* number of bpf_line_info records */ + __u32 attach_btf_id; /* in-kernel BTF type id to attach to */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ -- cgit v1.2.3-71-gd317 From 9e15db66136a14cde3f35691f1d839d950118826 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 15 Oct 2019 20:25:00 -0700 Subject: bpf: Implement accurate raw_tp context access via BTF libbpf analyzes bpf C program, searches in-kernel BTF for given type name and stores it into expected_attach_type. The kernel verifier expects this btf_id to point to something like: typedef void (*btf_trace_kfree_skb)(void *, struct sk_buff *skb, void *loc); which represents signature of raw_tracepoint "kfree_skb". Then btf_ctx_access() matches ctx+0 access in bpf program with 'skb' and 'ctx+8' access with 'loc' arguments of "kfree_skb" tracepoint. In first case it passes btf_id of 'struct sk_buff *' back to the verifier core and 'void *' in second case. Then the verifier tracks PTR_TO_BTF_ID as any other pointer type. Like PTR_TO_SOCKET points to 'struct bpf_sock', PTR_TO_TCP_SOCK points to 'struct bpf_tcp_sock', and so on. PTR_TO_BTF_ID points to in-kernel structs. If 1234 is btf_id of 'struct sk_buff' in vmlinux's BTF then PTR_TO_BTF_ID#1234 points to one of in kernel skbs. When PTR_TO_BTF_ID#1234 is dereferenced (like r2 = *(u64 *)r1 + 32) the btf_struct_access() checks which field of 'struct sk_buff' is at offset 32. Checks that size of access matches type definition of the field and continues to track the dereferenced type. If that field was a pointer to 'struct net_device' the r2's type will be PTR_TO_BTF_ID#456. Where 456 is btf_id of 'struct net_device' in vmlinux's BTF. Such verifier analysis prevents "cheating" in BPF C program. The program cannot cast arbitrary pointer to 'struct sk_buff *' and access it. C compiler would allow type cast, of course, but the verifier will notice type mismatch based on BPF assembly and in-kernel BTF. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20191016032505.2089704-7-ast@kernel.org --- include/linux/bpf.h | 17 +++- include/linux/bpf_verifier.h | 4 + kernel/bpf/btf.c | 190 +++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/verifier.c | 88 +++++++++++++++++++- kernel/trace/bpf_trace.c | 2 +- 5 files changed, 296 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f916380675dd..028555fcd10d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -16,6 +16,7 @@ #include struct bpf_verifier_env; +struct bpf_verifier_log; struct perf_event; struct bpf_prog; struct bpf_map; @@ -281,6 +282,7 @@ enum bpf_reg_type { PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */ PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */ PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */ + PTR_TO_BTF_ID, /* reg points to kernel struct */ }; /* The information passed from prog-specific *_is_valid_access @@ -288,7 +290,11 @@ enum bpf_reg_type { */ struct bpf_insn_access_aux { enum bpf_reg_type reg_type; - int ctx_field_size; + union { + int ctx_field_size; + u32 btf_id; + }; + struct bpf_verifier_log *log; /* for verbose logs */ }; static inline void @@ -483,6 +489,7 @@ struct bpf_event_entry { bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); int bpf_prog_calc_tag(struct bpf_prog *fp); +const char *kernel_type_name(u32 btf_type_id); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); @@ -748,6 +755,14 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); +bool btf_ctx_access(int off, int size, enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info); +int btf_struct_access(struct bpf_verifier_log *log, + const struct btf_type *t, int off, int size, + enum bpf_access_type atype, + u32 *next_btf_id); + #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 713efae62e96..6e7284ea1468 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -52,6 +52,8 @@ struct bpf_reg_state { */ struct bpf_map *map_ptr; + u32 btf_id; /* for PTR_TO_BTF_ID */ + /* Max size from any of the above. */ unsigned long raw; }; @@ -399,6 +401,8 @@ __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, va_list args); __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, const char *fmt, ...); +__printf(2, 3) void bpf_log(struct bpf_verifier_log *log, + const char *fmt, ...); static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env) { diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index ddeab1e8d21e..271d27cd427f 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3436,6 +3436,196 @@ errout: return ERR_PTR(err); } +extern struct btf *btf_vmlinux; + +bool btf_ctx_access(int off, int size, enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + struct bpf_verifier_log *log = info->log; + u32 btf_id = prog->aux->attach_btf_id; + const struct btf_param *args; + const struct btf_type *t; + const char prefix[] = "btf_trace_"; + const char *tname; + u32 nr_args, arg; + + if (!btf_id) + return true; + + if (IS_ERR(btf_vmlinux)) { + bpf_log(log, "btf_vmlinux is malformed\n"); + return false; + } + + t = btf_type_by_id(btf_vmlinux, btf_id); + if (!t || BTF_INFO_KIND(t->info) != BTF_KIND_TYPEDEF) { + bpf_log(log, "btf_id is invalid\n"); + return false; + } + + tname = __btf_name_by_offset(btf_vmlinux, t->name_off); + if (strncmp(prefix, tname, sizeof(prefix) - 1)) { + bpf_log(log, "btf_id points to wrong type name %s\n", tname); + return false; + } + tname += sizeof(prefix) - 1; + + t = btf_type_by_id(btf_vmlinux, t->type); + if (!btf_type_is_ptr(t)) + return false; + t = btf_type_by_id(btf_vmlinux, t->type); + if (!btf_type_is_func_proto(t)) + return false; + + if (off % 8) { + bpf_log(log, "raw_tp '%s' offset %d is not multiple of 8\n", + tname, off); + return false; + } + arg = off / 8; + args = (const struct btf_param *)(t + 1); + /* skip first 'void *__data' argument in btf_trace_##name typedef */ + args++; + nr_args = btf_type_vlen(t) - 1; + if (arg >= nr_args) { + bpf_log(log, "raw_tp '%s' doesn't have %d-th argument\n", + tname, arg); + return false; + } + + t = btf_type_by_id(btf_vmlinux, args[arg].type); + /* skip modifiers */ + while (btf_type_is_modifier(t)) + t = btf_type_by_id(btf_vmlinux, t->type); + if (btf_type_is_int(t)) + /* accessing a scalar */ + return true; + if (!btf_type_is_ptr(t)) { + bpf_log(log, + "raw_tp '%s' arg%d '%s' has type %s. Only pointer access is allowed\n", + tname, arg, + __btf_name_by_offset(btf_vmlinux, t->name_off), + btf_kind_str[BTF_INFO_KIND(t->info)]); + return false; + } + if (t->type == 0) + /* This is a pointer to void. + * It is the same as scalar from the verifier safety pov. + * No further pointer walking is allowed. + */ + return true; + + /* this is a pointer to another type */ + info->reg_type = PTR_TO_BTF_ID; + info->btf_id = t->type; + + t = btf_type_by_id(btf_vmlinux, t->type); + /* skip modifiers */ + while (btf_type_is_modifier(t)) + t = btf_type_by_id(btf_vmlinux, t->type); + if (!btf_type_is_struct(t)) { + bpf_log(log, + "raw_tp '%s' arg%d type %s is not a struct\n", + tname, arg, btf_kind_str[BTF_INFO_KIND(t->info)]); + return false; + } + bpf_log(log, "raw_tp '%s' arg%d has btf_id %d type %s '%s'\n", + tname, arg, info->btf_id, btf_kind_str[BTF_INFO_KIND(t->info)], + __btf_name_by_offset(btf_vmlinux, t->name_off)); + return true; +} + +int btf_struct_access(struct bpf_verifier_log *log, + const struct btf_type *t, int off, int size, + enum bpf_access_type atype, + u32 *next_btf_id) +{ + const struct btf_member *member; + const struct btf_type *mtype; + const char *tname, *mname; + int i, moff = 0, msize; + +again: + tname = __btf_name_by_offset(btf_vmlinux, t->name_off); + if (!btf_type_is_struct(t)) { + bpf_log(log, "Type '%s' is not a struct", tname); + return -EINVAL; + } + + for_each_member(i, t, member) { + /* offset of the field in bits */ + moff = btf_member_bit_offset(t, member); + + if (btf_member_bitfield_size(t, member)) + /* bitfields are not supported yet */ + continue; + + if (off + size <= moff / 8) + /* won't find anything, field is already too far */ + break; + + /* type of the field */ + mtype = btf_type_by_id(btf_vmlinux, member->type); + mname = __btf_name_by_offset(btf_vmlinux, member->name_off); + + /* skip modifiers */ + while (btf_type_is_modifier(mtype)) + mtype = btf_type_by_id(btf_vmlinux, mtype->type); + + if (btf_type_is_array(mtype)) + /* array deref is not supported yet */ + continue; + + if (!btf_type_has_size(mtype) && !btf_type_is_ptr(mtype)) { + bpf_log(log, "field %s doesn't have size\n", mname); + return -EFAULT; + } + if (btf_type_is_ptr(mtype)) + msize = 8; + else + msize = mtype->size; + if (off >= moff / 8 + msize) + /* no overlap with member, keep iterating */ + continue; + /* the 'off' we're looking for is either equal to start + * of this field or inside of this struct + */ + if (btf_type_is_struct(mtype)) { + /* our field must be inside that union or struct */ + t = mtype; + + /* adjust offset we're looking for */ + off -= moff / 8; + goto again; + } + if (msize != size) { + /* field access size doesn't match */ + bpf_log(log, + "cannot access %d bytes in struct %s field %s that has size %d\n", + size, tname, mname, msize); + return -EACCES; + } + + if (btf_type_is_ptr(mtype)) { + const struct btf_type *stype; + + stype = btf_type_by_id(btf_vmlinux, mtype->type); + /* skip modifiers */ + while (btf_type_is_modifier(stype)) + stype = btf_type_by_id(btf_vmlinux, stype->type); + if (btf_type_is_struct(stype)) { + *next_btf_id = mtype->type; + return PTR_TO_BTF_ID; + } + } + /* all other fields are treated as scalars */ + return SCALAR_VALUE; + } + bpf_log(log, "struct %s doesn't have field at offset %d\n", tname, off); + return -EINVAL; +} + void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, struct seq_file *m) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 466b3b19de4d..42a463e09761 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -286,6 +286,19 @@ __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...) va_end(args); } +__printf(2, 3) void bpf_log(struct bpf_verifier_log *log, + const char *fmt, ...) +{ + va_list args; + + if (!bpf_verifier_log_needed(log)) + return; + + va_start(args, fmt); + bpf_verifier_vlog(log, fmt, args); + va_end(args); +} + static const char *ltrim(const char *s) { while (isspace(*s)) @@ -406,6 +419,7 @@ static const char * const reg_type_str[] = { [PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null", [PTR_TO_TP_BUFFER] = "tp_buffer", [PTR_TO_XDP_SOCK] = "xdp_sock", + [PTR_TO_BTF_ID] = "ptr_", }; static char slot_type_char[] = { @@ -436,6 +450,12 @@ static struct bpf_func_state *func(struct bpf_verifier_env *env, return cur->frame[reg->frameno]; } +const char *kernel_type_name(u32 id) +{ + return btf_name_by_offset(btf_vmlinux, + btf_type_by_id(btf_vmlinux, id)->name_off); +} + static void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_state *state) { @@ -460,6 +480,8 @@ static void print_verifier_state(struct bpf_verifier_env *env, /* reg->off should be 0 for SCALAR_VALUE */ verbose(env, "%lld", reg->var_off.value + reg->off); } else { + if (t == PTR_TO_BTF_ID) + verbose(env, "%s", kernel_type_name(reg->btf_id)); verbose(env, "(id=%d", reg->id); if (reg_type_may_be_refcounted_or_null(t)) verbose(env, ",ref_obj_id=%d", reg->ref_obj_id); @@ -2337,10 +2359,12 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, /* check access to 'struct bpf_context' fields. Supports fixed offsets only */ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size, - enum bpf_access_type t, enum bpf_reg_type *reg_type) + enum bpf_access_type t, enum bpf_reg_type *reg_type, + u32 *btf_id) { struct bpf_insn_access_aux info = { .reg_type = *reg_type, + .log = &env->log, }; if (env->ops->is_valid_access && @@ -2354,7 +2378,10 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, */ *reg_type = info.reg_type; - env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; + if (*reg_type == PTR_TO_BTF_ID) + *btf_id = info.btf_id; + else + env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; /* remember the offset of last byte accessed in ctx */ if (env->prog->aux->max_ctx_offset < off + size) env->prog->aux->max_ctx_offset = off + size; @@ -2780,6 +2807,53 @@ static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val) return 0; } +static int check_ptr_to_btf_access(struct bpf_verifier_env *env, + struct bpf_reg_state *regs, + int regno, int off, int size, + enum bpf_access_type atype, + int value_regno) +{ + struct bpf_reg_state *reg = regs + regno; + const struct btf_type *t = btf_type_by_id(btf_vmlinux, reg->btf_id); + const char *tname = btf_name_by_offset(btf_vmlinux, t->name_off); + u32 btf_id; + int ret; + + if (atype != BPF_READ) { + verbose(env, "only read is supported\n"); + return -EACCES; + } + + if (off < 0) { + verbose(env, + "R%d is ptr_%s invalid negative access: off=%d\n", + regno, tname, off); + return -EACCES; + } + if (!tnum_is_const(reg->var_off) || reg->var_off.value) { + char tn_buf[48]; + + tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); + verbose(env, + "R%d is ptr_%s invalid variable offset: off=%d, var_off=%s\n", + regno, tname, off, tn_buf); + return -EACCES; + } + + ret = btf_struct_access(&env->log, t, off, size, atype, &btf_id); + if (ret < 0) + return ret; + + if (ret == SCALAR_VALUE) { + mark_reg_unknown(env, regs, value_regno); + return 0; + } + mark_reg_known_zero(env, regs, value_regno); + regs[value_regno].type = PTR_TO_BTF_ID; + regs[value_regno].btf_id = btf_id; + return 0; +} + /* check whether memory at (regno + off) is accessible for t = (read | write) * if t==write, value_regno is a register which value is stored into memory * if t==read, value_regno is a register which will receive the value from memory @@ -2840,6 +2914,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn } } else if (reg->type == PTR_TO_CTX) { enum bpf_reg_type reg_type = SCALAR_VALUE; + u32 btf_id = 0; if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { @@ -2851,7 +2926,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (err < 0) return err; - err = check_ctx_access(env, insn_idx, off, size, t, ®_type); + err = check_ctx_access(env, insn_idx, off, size, t, ®_type, &btf_id); + if (err) + verbose_linfo(env, insn_idx, "; "); if (!err && t == BPF_READ && value_regno >= 0) { /* ctx access returns either a scalar, or a * PTR_TO_PACKET[_META,_END]. In the latter @@ -2870,6 +2947,8 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn * a sub-register. */ regs[value_regno].subreg_def = DEF_NOT_SUBREG; + if (reg_type == PTR_TO_BTF_ID) + regs[value_regno].btf_id = btf_id; } regs[value_regno].type = reg_type; } @@ -2929,6 +3008,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn err = check_tp_buffer_access(env, reg, regno, off, size); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); + } else if (reg->type == PTR_TO_BTF_ID) { + err = check_ptr_to_btf_access(env, regs, regno, off, size, t, + value_regno); } else { verbose(env, "R%d invalid mem access '%s'\n", regno, reg_type_str[reg->type]); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 44bd08f2443b..6221e8c6ecc3 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1074,7 +1074,7 @@ static bool raw_tp_prog_is_valid_access(int off, int size, return false; if (off % size != 0) return false; - return true; + return btf_ctx_access(off, size, type, prog, info); } const struct bpf_verifier_ops raw_tracepoint_verifier_ops = { -- cgit v1.2.3-71-gd317 From 2a02759ef5f8a34792df22b41d5e10658fd7bbd3 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 15 Oct 2019 20:25:02 -0700 Subject: bpf: Add support for BTF pointers to interpreter Pointer to BTF object is a pointer to kernel object or NULL. The memory access in the interpreter has to be done via probe_kernel_read to avoid page faults. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20191016032505.2089704-9-ast@kernel.org --- include/linux/filter.h | 3 +++ kernel/bpf/core.c | 19 +++++++++++++++++++ kernel/bpf/verifier.c | 8 ++++++++ 3 files changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index d3d51d7aff2c..22ebea2e64ea 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -65,6 +65,9 @@ struct ctl_table_header; /* unused opcode to mark special call to bpf_tail_call() helper */ #define BPF_TAIL_CALL 0xf0 +/* unused opcode to mark special load instruction. Same as BPF_ABS */ +#define BPF_PROBE_MEM 0x20 + /* unused opcode to mark call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0 diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 66088a9e9b9e..8a765bbd33f0 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1291,6 +1291,11 @@ bool bpf_opcode_in_insntable(u8 code) } #ifndef CONFIG_BPF_JIT_ALWAYS_ON +u64 __weak bpf_probe_read(void * dst, u32 size, const void * unsafe_ptr) +{ + memset(dst, 0, size); + return -EFAULT; +} /** * __bpf_prog_run - run eBPF program on a given context * @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers @@ -1310,6 +1315,10 @@ static u64 __no_fgcse ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u6 /* Non-UAPI available opcodes. */ [BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS, [BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL, + [BPF_LDX | BPF_PROBE_MEM | BPF_B] = &&LDX_PROBE_MEM_B, + [BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H, + [BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W, + [BPF_LDX | BPF_PROBE_MEM | BPF_DW] = &&LDX_PROBE_MEM_DW, }; #undef BPF_INSN_3_LBL #undef BPF_INSN_2_LBL @@ -1542,6 +1551,16 @@ out: LDST(W, u32) LDST(DW, u64) #undef LDST +#define LDX_PROBE(SIZEOP, SIZE) \ + LDX_PROBE_MEM_##SIZEOP: \ + bpf_probe_read(&DST, SIZE, (const void *)(long) SRC); \ + CONT; + LDX_PROBE(B, 1) + LDX_PROBE(H, 2) + LDX_PROBE(W, 4) + LDX_PROBE(DW, 8) +#undef LDX_PROBE + STX_XADD_W: /* lock xadd *(u32 *)(dst_reg + off16) += src_reg */ atomic_add((u32) SRC, (atomic_t *)(unsigned long) (DST + insn->off)); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 42a463e09761..c4b6a2cfcd47 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -7581,6 +7581,7 @@ static bool reg_type_mismatch_ok(enum bpf_reg_type type) case PTR_TO_TCP_SOCK: case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: + case PTR_TO_BTF_ID: return false; default: return true; @@ -8722,6 +8723,13 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) case PTR_TO_XDP_SOCK: convert_ctx_access = bpf_xdp_sock_convert_ctx_access; break; + case PTR_TO_BTF_ID: + if (type == BPF_WRITE) { + verbose(env, "Writes through BTF pointers are not allowed\n"); + return -EINVAL; + } + insn->code = BPF_LDX | BPF_PROBE_MEM | BPF_SIZE((insn)->code); + continue; default: continue; } -- cgit v1.2.3-71-gd317 From 3dec541b2e632d630fe7142ed44f0b3702ef1f8c Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 15 Oct 2019 20:25:03 -0700 Subject: bpf: Add support for BTF pointers to x86 JIT Pointer to BTF object is a pointer to kernel object or NULL. Such pointers can only be used by BPF_LDX instructions. The verifier changed their opcode from LDX|MEM|size to LDX|PROBE_MEM|size to make JITing easier. The number of entries in extable is the number of BPF_LDX insns that access kernel memory via "pointer to BTF type". Only these load instructions can fault. Since x86 extable is relative it has to be allocated in the same memory region as JITed code. Allocate it prior to last pass of JITing and let the last pass populate it. Pointer to extable in bpf_prog_aux is necessary to make page fault handling fast. Page fault handling is done in two steps: 1. bpf_prog_kallsyms_find() finds BPF program that page faulted. It's done by walking rb tree. 2. then extable for given bpf program is binary searched. This process is similar to how page faulting is done for kernel modules. The exception handler skips over faulting x86 instruction and initializes destination register with zero. This mimics exact behavior of bpf_probe_read (when probe_kernel_read faults dest is zeroed). JITs for other architectures can add support in similar way. Until then they will reject unknown opcode and fallback to interpreter. Since extable should be aligned and placed near JITed code make bpf_jit_binary_alloc() return 4 byte aligned image offset, so that extable aligning formula in bpf_int_jit_compile() doesn't need to rely on internal implementation of bpf_jit_binary_alloc(). On x86 gcc defaults to 16-byte alignment for regular kernel functions due to better performance. JITed code may be aligned to 16 in the future, but it will use 4 in the meantime. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20191016032505.2089704-10-ast@kernel.org --- arch/x86/net/bpf_jit_comp.c | 97 +++++++++++++++++++++++++++++++++++++++++++-- include/linux/bpf.h | 3 ++ include/linux/extable.h | 10 +++++ kernel/bpf/core.c | 20 +++++++++- kernel/bpf/verifier.c | 1 + kernel/extable.c | 2 + 6 files changed, 128 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 3ad2ba1ad855..8cd23d8309bf 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -9,7 +9,7 @@ #include #include #include - +#include #include #include @@ -123,6 +123,19 @@ static const int reg2hex[] = { [AUX_REG] = 3, /* R11 temp register */ }; +static const int reg2pt_regs[] = { + [BPF_REG_0] = offsetof(struct pt_regs, ax), + [BPF_REG_1] = offsetof(struct pt_regs, di), + [BPF_REG_2] = offsetof(struct pt_regs, si), + [BPF_REG_3] = offsetof(struct pt_regs, dx), + [BPF_REG_4] = offsetof(struct pt_regs, cx), + [BPF_REG_5] = offsetof(struct pt_regs, r8), + [BPF_REG_6] = offsetof(struct pt_regs, bx), + [BPF_REG_7] = offsetof(struct pt_regs, r13), + [BPF_REG_8] = offsetof(struct pt_regs, r14), + [BPF_REG_9] = offsetof(struct pt_regs, r15), +}; + /* * is_ereg() == true if BPF register 'reg' maps to x86-64 r8..r15 * which need extra byte of encoding. @@ -377,6 +390,19 @@ static void emit_mov_reg(u8 **pprog, bool is64, u32 dst_reg, u32 src_reg) *pprog = prog; } + +static bool ex_handler_bpf(const struct exception_table_entry *x, + struct pt_regs *regs, int trapnr, + unsigned long error_code, unsigned long fault_addr) +{ + u32 reg = x->fixup >> 8; + + /* jump over faulting load and clear dest register */ + *(unsigned long *)((void *)regs + reg) = 0; + regs->ip += x->fixup & 0xff; + return true; +} + static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, int oldproglen, struct jit_context *ctx) { @@ -384,7 +410,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, int insn_cnt = bpf_prog->len; bool seen_exit = false; u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY]; - int i, cnt = 0; + int i, cnt = 0, excnt = 0; int proglen = 0; u8 *prog = temp; @@ -778,14 +804,17 @@ stx: if (is_imm8(insn->off)) /* LDX: dst_reg = *(u8*)(src_reg + off) */ case BPF_LDX | BPF_MEM | BPF_B: + case BPF_LDX | BPF_PROBE_MEM | BPF_B: /* Emit 'movzx rax, byte ptr [rax + off]' */ EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB6); goto ldx; case BPF_LDX | BPF_MEM | BPF_H: + case BPF_LDX | BPF_PROBE_MEM | BPF_H: /* Emit 'movzx rax, word ptr [rax + off]' */ EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB7); goto ldx; case BPF_LDX | BPF_MEM | BPF_W: + case BPF_LDX | BPF_PROBE_MEM | BPF_W: /* Emit 'mov eax, dword ptr [rax+0x14]' */ if (is_ereg(dst_reg) || is_ereg(src_reg)) EMIT2(add_2mod(0x40, src_reg, dst_reg), 0x8B); @@ -793,6 +822,7 @@ stx: if (is_imm8(insn->off)) EMIT1(0x8B); goto ldx; case BPF_LDX | BPF_MEM | BPF_DW: + case BPF_LDX | BPF_PROBE_MEM | BPF_DW: /* Emit 'mov rax, qword ptr [rax+0x14]' */ EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x8B); ldx: /* @@ -805,6 +835,48 @@ ldx: /* else EMIT1_off32(add_2reg(0x80, src_reg, dst_reg), insn->off); + if (BPF_MODE(insn->code) == BPF_PROBE_MEM) { + struct exception_table_entry *ex; + u8 *_insn = image + proglen; + s64 delta; + + if (!bpf_prog->aux->extable) + break; + + if (excnt >= bpf_prog->aux->num_exentries) { + pr_err("ex gen bug\n"); + return -EFAULT; + } + ex = &bpf_prog->aux->extable[excnt++]; + + delta = _insn - (u8 *)&ex->insn; + if (!is_simm32(delta)) { + pr_err("extable->insn doesn't fit into 32-bit\n"); + return -EFAULT; + } + ex->insn = delta; + + delta = (u8 *)ex_handler_bpf - (u8 *)&ex->handler; + if (!is_simm32(delta)) { + pr_err("extable->handler doesn't fit into 32-bit\n"); + return -EFAULT; + } + ex->handler = delta; + + if (dst_reg > BPF_REG_9) { + pr_err("verifier error\n"); + return -EFAULT; + } + /* + * Compute size of x86 insn and its target dest x86 register. + * ex_handler_bpf() will use lower 8 bits to adjust + * pt_regs->ip to jump over this x86 instruction + * and upper bits to figure out which pt_regs to zero out. + * End result: x86 insn "mov rbx, qword ptr [rax+0x14]" + * of 4 bytes will be ignored and rbx will be zero inited. + */ + ex->fixup = (prog - temp) | (reg2pt_regs[dst_reg] << 8); + } break; /* STX XADD: lock *(u32*)(dst_reg + off) += src_reg */ @@ -1058,6 +1130,11 @@ emit_jmp: addrs[i] = proglen; prog = temp; } + + if (image && excnt != bpf_prog->aux->num_exentries) { + pr_err("extable is not populated\n"); + return -EFAULT; + } return proglen; } @@ -1158,12 +1235,24 @@ out_image: break; } if (proglen == oldproglen) { - header = bpf_jit_binary_alloc(proglen, &image, - 1, jit_fill_hole); + /* + * The number of entries in extable is the number of BPF_LDX + * insns that access kernel memory via "pointer to BTF type". + * The verifier changed their opcode from LDX|MEM|size + * to LDX|PROBE_MEM|size to make JITing easier. + */ + u32 align = __alignof__(struct exception_table_entry); + u32 extable_size = prog->aux->num_exentries * + sizeof(struct exception_table_entry); + + /* allocate module memory for x86 insns and extable */ + header = bpf_jit_binary_alloc(roundup(proglen, align) + extable_size, + &image, align, jit_fill_hole); if (!header) { prog = orig_prog; goto out_addrs; } + prog->aux->extable = (void *) image + roundup(proglen, align); } oldproglen = proglen; cond_resched(); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 028555fcd10d..a7330d75bb94 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -24,6 +24,7 @@ struct sock; struct seq_file; struct btf; struct btf_type; +struct exception_table_entry; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; @@ -423,6 +424,8 @@ struct bpf_prog_aux { * main prog always has linfo_idx == 0 */ u32 linfo_idx; + u32 num_exentries; + struct exception_table_entry *extable; struct bpf_prog_stats __percpu *stats; union { struct work_struct work; diff --git a/include/linux/extable.h b/include/linux/extable.h index 81ecfaa83ad3..4ab9e78f313b 100644 --- a/include/linux/extable.h +++ b/include/linux/extable.h @@ -33,4 +33,14 @@ search_module_extables(unsigned long addr) } #endif /*CONFIG_MODULES*/ +#ifdef CONFIG_BPF_JIT +const struct exception_table_entry *search_bpf_extables(unsigned long addr); +#else +static inline const struct exception_table_entry * +search_bpf_extables(unsigned long addr) +{ + return NULL; +} +#endif + #endif /* _LINUX_EXTABLE_H */ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 8a765bbd33f0..673f5d40a93e 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -30,7 +30,7 @@ #include #include #include - +#include #include /* Registers */ @@ -712,6 +712,24 @@ bool is_bpf_text_address(unsigned long addr) return ret; } +const struct exception_table_entry *search_bpf_extables(unsigned long addr) +{ + const struct exception_table_entry *e = NULL; + struct bpf_prog *prog; + + rcu_read_lock(); + prog = bpf_prog_kallsyms_find(addr); + if (!prog) + goto out; + if (!prog->aux->num_exentries) + goto out; + + e = search_extable(prog->aux->extable, prog->aux->num_exentries, addr); +out: + rcu_read_unlock(); + return e; +} + int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c4b6a2cfcd47..fba9ef6a831b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8729,6 +8729,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) return -EINVAL; } insn->code = BPF_LDX | BPF_PROBE_MEM | BPF_SIZE((insn)->code); + env->prog->aux->num_exentries++; continue; default: continue; diff --git a/kernel/extable.c b/kernel/extable.c index f6c9406eec7d..f6920a11e28a 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -56,6 +56,8 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr) e = search_kernel_exception_table(addr); if (!e) e = search_module_extables(addr); + if (!e) + e = search_bpf_extables(addr); return e; } -- cgit v1.2.3-71-gd317 From a7658e1a4164ce2b9eb4a11aadbba38586e93bd6 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 15 Oct 2019 20:25:04 -0700 Subject: bpf: Check types of arguments passed into helpers Introduce new helper that reuses existing skb perf_event output implementation, but can be called from raw_tracepoint programs that receive 'struct sk_buff *' as tracepoint argument or can walk other kernel data structures to skb pointer. In order to do that teach verifier to resolve true C types of bpf helpers into in-kernel BTF ids. The type of kernel pointer passed by raw tracepoint into bpf program will be tracked by the verifier all the way until it's passed into helper function. For example: kfree_skb() kernel function calls trace_kfree_skb(skb, loc); bpf programs receives that skb pointer and may eventually pass it into bpf_skb_output() bpf helper which in-kernel is implemented via bpf_skb_event_output() kernel function. Its first argument in the kernel is 'struct sk_buff *'. The verifier makes sure that types match all the way. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20191016032505.2089704-11-ast@kernel.org --- include/linux/bpf.h | 18 +++++++---- include/uapi/linux/bpf.h | 27 ++++++++++++++++- kernel/bpf/btf.c | 68 ++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/verifier.c | 44 +++++++++++++++++---------- kernel/trace/bpf_trace.c | 4 +++ net/core/filter.c | 15 +++++++++- tools/include/uapi/linux/bpf.h | 27 ++++++++++++++++- 7 files changed, 180 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a7330d75bb94..2c2c29b49845 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -213,6 +213,7 @@ enum bpf_arg_type { ARG_PTR_TO_INT, /* pointer to int */ ARG_PTR_TO_LONG, /* pointer to long */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ + ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */ }; /* type of values returned from helper functions */ @@ -235,11 +236,17 @@ struct bpf_func_proto { bool gpl_only; bool pkt_access; enum bpf_return_type ret_type; - enum bpf_arg_type arg1_type; - enum bpf_arg_type arg2_type; - enum bpf_arg_type arg3_type; - enum bpf_arg_type arg4_type; - enum bpf_arg_type arg5_type; + union { + struct { + enum bpf_arg_type arg1_type; + enum bpf_arg_type arg2_type; + enum bpf_arg_type arg3_type; + enum bpf_arg_type arg4_type; + enum bpf_arg_type arg5_type; + }; + enum bpf_arg_type arg_type[5]; + }; + u32 *btf_id; /* BTF ids of arguments */ }; /* bpf_context is intentionally undefined structure. Pointer to bpf_context is @@ -765,6 +772,7 @@ int btf_struct_access(struct bpf_verifier_log *log, const struct btf_type *t, int off, int size, enum bpf_access_type atype, u32 *next_btf_id); +u32 btf_resolve_helper_id(struct bpf_verifier_log *log, void *, int); #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 3bb2cd1de341..4af8b0819a32 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2751,6 +2751,30 @@ union bpf_attr { * **-EOPNOTSUPP** kernel configuration does not enable SYN cookies * * **-EPROTONOSUPPORT** IP packet version is not 4 or 6 + * + * int bpf_skb_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * Description + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * *ctx* is a pointer to in-kernel struct sk_buff. + * + * This helper is similar to **bpf_perf_event_output**\ () but + * restricted to raw_tracepoint bpf programs. + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2863,7 +2887,8 @@ union bpf_attr { FN(sk_storage_get), \ FN(sk_storage_delete), \ FN(send_signal), \ - FN(tcp_gen_syncookie), + FN(tcp_gen_syncookie), \ + FN(skb_output), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 271d27cd427f..f7557af39756 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3626,6 +3626,74 @@ again: return -EINVAL; } +u32 btf_resolve_helper_id(struct bpf_verifier_log *log, void *fn, int arg) +{ + char fnname[KSYM_SYMBOL_LEN + 4] = "btf_"; + const struct btf_param *args; + const struct btf_type *t; + const char *tname, *sym; + u32 btf_id, i; + + if (IS_ERR(btf_vmlinux)) { + bpf_log(log, "btf_vmlinux is malformed\n"); + return -EINVAL; + } + + sym = kallsyms_lookup((long)fn, NULL, NULL, NULL, fnname + 4); + if (!sym) { + bpf_log(log, "kernel doesn't have kallsyms\n"); + return -EFAULT; + } + + for (i = 1; i <= btf_vmlinux->nr_types; i++) { + t = btf_type_by_id(btf_vmlinux, i); + if (BTF_INFO_KIND(t->info) != BTF_KIND_TYPEDEF) + continue; + tname = __btf_name_by_offset(btf_vmlinux, t->name_off); + if (!strcmp(tname, fnname)) + break; + } + if (i > btf_vmlinux->nr_types) { + bpf_log(log, "helper %s type is not found\n", fnname); + return -ENOENT; + } + + t = btf_type_by_id(btf_vmlinux, t->type); + if (!btf_type_is_ptr(t)) + return -EFAULT; + t = btf_type_by_id(btf_vmlinux, t->type); + if (!btf_type_is_func_proto(t)) + return -EFAULT; + + args = (const struct btf_param *)(t + 1); + if (arg >= btf_type_vlen(t)) { + bpf_log(log, "bpf helper %s doesn't have %d-th argument\n", + fnname, arg); + return -EINVAL; + } + + t = btf_type_by_id(btf_vmlinux, args[arg].type); + if (!btf_type_is_ptr(t) || !t->type) { + /* anything but the pointer to struct is a helper config bug */ + bpf_log(log, "ARG_PTR_TO_BTF is misconfigured\n"); + return -EFAULT; + } + btf_id = t->type; + t = btf_type_by_id(btf_vmlinux, t->type); + /* skip modifiers */ + while (btf_type_is_modifier(t)) { + btf_id = t->type; + t = btf_type_by_id(btf_vmlinux, t->type); + } + if (!btf_type_is_struct(t)) { + bpf_log(log, "ARG_PTR_TO_BTF is not a struct\n"); + return -EFAULT; + } + bpf_log(log, "helper %s arg%d has btf_id %d struct %s\n", fnname + 4, + arg, btf_id, __btf_name_by_offset(btf_vmlinux, t->name_off)); + return btf_id; +} + void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, struct seq_file *m) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index fba9ef6a831b..556e82f8869b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -205,6 +205,7 @@ struct bpf_call_arg_meta { u64 msize_umax_value; int ref_obj_id; int func_id; + u32 btf_id; }; struct btf *btf_vmlinux; @@ -3439,6 +3440,22 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, expected_type = PTR_TO_SOCKET; if (type != expected_type) goto err_type; + } else if (arg_type == ARG_PTR_TO_BTF_ID) { + expected_type = PTR_TO_BTF_ID; + if (type != expected_type) + goto err_type; + if (reg->btf_id != meta->btf_id) { + verbose(env, "Helper has type %s got %s in R%d\n", + kernel_type_name(meta->btf_id), + kernel_type_name(reg->btf_id), regno); + + return -EACCES; + } + if (!tnum_is_const(reg->var_off) || reg->var_off.value || reg->off) { + verbose(env, "R%d is a pointer to in-kernel struct with non-zero offset\n", + regno); + return -EACCES; + } } else if (arg_type == ARG_PTR_TO_SPIN_LOCK) { if (meta->func_id == BPF_FUNC_spin_lock) { if (process_spin_lock(env, regno, true)) @@ -3586,6 +3603,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_MAP_TYPE_PERF_EVENT_ARRAY: if (func_id != BPF_FUNC_perf_event_read && func_id != BPF_FUNC_perf_event_output && + func_id != BPF_FUNC_skb_output && func_id != BPF_FUNC_perf_event_read_value) goto error; break; @@ -3673,6 +3691,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_FUNC_perf_event_read: case BPF_FUNC_perf_event_output: case BPF_FUNC_perf_event_read_value: + case BPF_FUNC_skb_output: if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) goto error; break; @@ -4127,21 +4146,16 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn meta.func_id = func_id; /* check args */ - err = check_func_arg(env, BPF_REG_1, fn->arg1_type, &meta); - if (err) - return err; - err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &meta); - if (err) - return err; - err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &meta); - if (err) - return err; - err = check_func_arg(env, BPF_REG_4, fn->arg4_type, &meta); - if (err) - return err; - err = check_func_arg(env, BPF_REG_5, fn->arg5_type, &meta); - if (err) - return err; + for (i = 0; i < 5; i++) { + if (fn->arg_type[i] == ARG_PTR_TO_BTF_ID) { + if (!fn->btf_id[i]) + fn->btf_id[i] = btf_resolve_helper_id(&env->log, fn->func, i); + meta.btf_id = fn->btf_id[i]; + } + err = check_func_arg(env, BPF_REG_1 + i, fn->arg_type[i], &meta); + if (err) + return err; + } err = record_func_map(env, &meta, func_id, insn_idx); if (err) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 6221e8c6ecc3..52f7e9d8c29b 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -995,6 +995,8 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = { .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; +extern const struct bpf_func_proto bpf_skb_output_proto; + BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args, struct bpf_map *, map, u64, flags) { @@ -1053,6 +1055,8 @@ raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_perf_event_output_proto_raw_tp; + case BPF_FUNC_skb_output: + return &bpf_skb_output_proto; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_raw_tp; case BPF_FUNC_get_stack: diff --git a/net/core/filter.c b/net/core/filter.c index 46196e212413..728ba6203c1f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3798,7 +3798,7 @@ BPF_CALL_5(bpf_skb_event_output, struct sk_buff *, skb, struct bpf_map *, map, if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK))) return -EINVAL; - if (unlikely(skb_size > skb->len)) + if (unlikely(!skb || skb_size > skb->len)) return -EFAULT; return bpf_event_output(map, flags, meta, meta_size, skb, skb_size, @@ -3816,6 +3816,19 @@ static const struct bpf_func_proto bpf_skb_event_output_proto = { .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; +static u32 bpf_skb_output_btf_ids[5]; +const struct bpf_func_proto bpf_skb_output_proto = { + .func = bpf_skb_event_output, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_MEM, + .arg5_type = ARG_CONST_SIZE_OR_ZERO, + .btf_id = bpf_skb_output_btf_ids, +}; + static unsigned short bpf_tunnel_key_af(u64 flags) { return flags & BPF_F_TUNINFO_IPV6 ? AF_INET6 : AF_INET; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 3bb2cd1de341..4af8b0819a32 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2751,6 +2751,30 @@ union bpf_attr { * **-EOPNOTSUPP** kernel configuration does not enable SYN cookies * * **-EPROTONOSUPPORT** IP packet version is not 4 or 6 + * + * int bpf_skb_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * Description + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * *ctx* is a pointer to in-kernel struct sk_buff. + * + * This helper is similar to **bpf_perf_event_output**\ () but + * restricted to raw_tracepoint bpf programs. + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2863,7 +2887,8 @@ union bpf_attr { FN(sk_storage_get), \ FN(sk_storage_delete), \ FN(send_signal), \ - FN(tcp_gen_syncookie), + FN(tcp_gen_syncookie), \ + FN(skb_output), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call -- cgit v1.2.3-71-gd317 From 825dbc6ff7a3a063ea91be7d94af940080b0c991 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Tue, 15 Oct 2019 11:26:15 +0100 Subject: percpu: add __percpu to SHIFT_PERCPU_PTR The SHIFT_PERCPU_PTR() returns a pointer used by a number of functions that expect the pointer to be __percpu annotated (sparse address space 3). Adding __percpu to this makes the following sparse warnings go away. Note, this then creates the problem the __percup is marked as noderef, which may need removing for some of the internal functions, or to remove other warnings. mm/vmstat.c:385:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:385:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:385:13: got signed char * mm/vmstat.c:385:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:385:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:385:13: got signed char * mm/vmstat.c:385:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:385:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:385:13: got signed char * mm/vmstat.c:385:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:385:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:385:13: got signed char * mm/vmstat.c:401:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:401:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:401:13: got signed char * mm/vmstat.c:401:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:401:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:401:13: got signed char * mm/vmstat.c:401:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:401:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:401:13: got signed char * mm/vmstat.c:401:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:401:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:401:13: got signed char * mm/vmstat.c:429:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:429:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:429:13: got signed char * mm/vmstat.c:429:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:429:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:429:13: got signed char * mm/vmstat.c:429:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:429:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:429:13: got signed char * mm/vmstat.c:429:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:429:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:429:13: got signed char * mm/vmstat.c:445:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:445:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:445:13: got signed char * mm/vmstat.c:445:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:445:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:445:13: got signed char * mm/vmstat.c:445:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:445:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:445:13: got signed char * mm/vmstat.c:445:13: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:445:13: expected signed char [noderef] [usertype] *__p mm/vmstat.c:445:13: got signed char * mm/vmstat.c:763:29: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:763:29: expected signed char [noderef] *__p mm/vmstat.c:763:29: got signed char * mm/vmstat.c:763:29: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:763:29: expected signed char [noderef] *__p mm/vmstat.c:763:29: got signed char * mm/vmstat.c:763:29: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:763:29: expected signed char [noderef] *__p mm/vmstat.c:763:29: got signed char * mm/vmstat.c:763:29: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:763:29: expected signed char [noderef] *__p mm/vmstat.c:763:29: got signed char * mm/vmstat.c:825:29: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:825:29: expected signed char [noderef] *__p mm/vmstat.c:825:29: got signed char * mm/vmstat.c:825:29: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:825:29: expected signed char [noderef] *__p mm/vmstat.c:825:29: got signed char * mm/vmstat.c:825:29: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:825:29: expected signed char [noderef] *__p mm/vmstat.c:825:29: got signed char * mm/vmstat.c:825:29: warning: incorrect type in initializer (different address spaces) mm/vmstat.c:825:29: expected signed char [noderef] *__p mm/vmstat.c:825:29: got signed char * Signed-off-by: Ben Dooks Signed-off-by: Dennis Zhou --- include/linux/percpu-defs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index a6fabd865211..a49b6c702598 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -229,7 +229,7 @@ do { \ * pointer value. The weird cast keeps both GCC and sparse happy. */ #define SHIFT_PERCPU_PTR(__p, __offset) \ - RELOC_HIDE((typeof(*(__p)) __kernel __force *)(__p), (__offset)) + RELOC_HIDE((typeof(*(__p)) __kernel __percpu __force *)(__p), (__offset)) #define per_cpu_ptr(ptr, cpu) \ ({ \ -- cgit v1.2.3-71-gd317 From da97e18458fb42d7c00fac5fd1c56a3896ec666e Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Mon, 14 Oct 2019 13:03:08 -0400 Subject: perf_event: Add support for LSM and SELinux checks In current mainline, the degree of access to perf_event_open(2) system call depends on the perf_event_paranoid sysctl. This has a number of limitations: 1. The sysctl is only a single value. Many types of accesses are controlled based on the single value thus making the control very limited and coarse grained. 2. The sysctl is global, so if the sysctl is changed, then that means all processes get access to perf_event_open(2) opening the door to security issues. This patch adds LSM and SELinux access checking which will be used in Android to access perf_event_open(2) for the purposes of attaching BPF programs to tracepoints, perf profiling and other operations from userspace. These operations are intended for production systems. 5 new LSM hooks are added: 1. perf_event_open: This controls access during the perf_event_open(2) syscall itself. The hook is called from all the places that the perf_event_paranoid sysctl is checked to keep it consistent with the systctl. The hook gets passed a 'type' argument which controls CPU, kernel and tracepoint accesses (in this context, CPU, kernel and tracepoint have the same semantics as the perf_event_paranoid sysctl). Additionally, I added an 'open' type which is similar to perf_event_paranoid sysctl == 3 patch carried in Android and several other distros but was rejected in mainline [1] in 2016. 2. perf_event_alloc: This allocates a new security object for the event which stores the current SID within the event. It will be useful when the perf event's FD is passed through IPC to another process which may try to read the FD. Appropriate security checks will limit access. 3. perf_event_free: Called when the event is closed. 4. perf_event_read: Called from the read(2) and mmap(2) syscalls for the event. 5. perf_event_write: Called from the ioctl(2) syscalls for the event. [1] https://lwn.net/Articles/696240/ Since Peter had suggest LSM hooks in 2016 [1], I am adding his Suggested-by tag below. To use this patch, we set the perf_event_paranoid sysctl to -1 and then apply selinux checking as appropriate (default deny everything, and then add policy rules to give access to domains that need it). In the future we can remove the perf_event_paranoid sysctl altogether. Suggested-by: Peter Zijlstra Co-developed-by: Peter Zijlstra Signed-off-by: Joel Fernandes (Google) Signed-off-by: Peter Zijlstra (Intel) Acked-by: James Morris Cc: Arnaldo Carvalho de Melo Cc: rostedt@goodmis.org Cc: Yonghong Song Cc: Kees Cook Cc: Ingo Molnar Cc: Alexei Starovoitov Cc: jeffv@google.com Cc: Jiri Olsa Cc: Daniel Borkmann Cc: primiano@google.com Cc: Song Liu Cc: rsavitski@google.com Cc: Namhyung Kim Cc: Matthew Garrett Link: https://lkml.kernel.org/r/20191014170308.70668-1-joel@joelfernandes.org --- arch/powerpc/perf/core-book3s.c | 18 +++++----- arch/x86/events/intel/bts.c | 8 +++-- arch/x86/events/intel/core.c | 5 +-- arch/x86/events/intel/p4.c | 5 +-- include/linux/lsm_hooks.h | 15 ++++++++ include/linux/perf_event.h | 36 ++++++++++++++++--- include/linux/security.h | 38 +++++++++++++++++++- kernel/events/core.c | 57 ++++++++++++++++++++++++------ kernel/trace/trace_event_perf.c | 15 +++++--- security/security.c | 27 +++++++++++++++ security/selinux/hooks.c | 69 +++++++++++++++++++++++++++++++++++++ security/selinux/include/classmap.h | 2 ++ security/selinux/include/objsec.h | 6 +++- 13 files changed, 261 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index ca92e01d0bd1..48604625ab31 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -96,7 +96,7 @@ static inline unsigned long perf_ip_adjust(struct pt_regs *regs) { return 0; } -static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp) { } +static inline void perf_get_data_addr(struct perf_event *event, struct pt_regs *regs, u64 *addrp) { } static inline u32 perf_get_misc_flags(struct pt_regs *regs) { return 0; @@ -127,7 +127,7 @@ static unsigned long ebb_switch_in(bool ebb, struct cpu_hw_events *cpuhw) static inline void power_pmu_bhrb_enable(struct perf_event *event) {} static inline void power_pmu_bhrb_disable(struct perf_event *event) {} static void power_pmu_sched_task(struct perf_event_context *ctx, bool sched_in) {} -static inline void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) {} +static inline void power_pmu_bhrb_read(struct perf_event *event, struct cpu_hw_events *cpuhw) {} static void pmao_restore_workaround(bool ebb) { } #endif /* CONFIG_PPC32 */ @@ -179,7 +179,7 @@ static inline unsigned long perf_ip_adjust(struct pt_regs *regs) * pointed to by SIAR; this is indicated by the [POWER6_]MMCRA_SDSYNC, the * [POWER7P_]MMCRA_SDAR_VALID bit in MMCRA, or the SDAR_VALID bit in SIER. */ -static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp) +static inline void perf_get_data_addr(struct perf_event *event, struct pt_regs *regs, u64 *addrp) { unsigned long mmcra = regs->dsisr; bool sdar_valid; @@ -204,8 +204,7 @@ static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp) if (!(mmcra & MMCRA_SAMPLE_ENABLE) || sdar_valid) *addrp = mfspr(SPRN_SDAR); - if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN) && - is_kernel_addr(mfspr(SPRN_SDAR))) + if (is_kernel_addr(mfspr(SPRN_SDAR)) && perf_allow_kernel(&event->attr) != 0) *addrp = 0; } @@ -444,7 +443,7 @@ static __u64 power_pmu_bhrb_to(u64 addr) } /* Processing BHRB entries */ -static void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) +static void power_pmu_bhrb_read(struct perf_event *event, struct cpu_hw_events *cpuhw) { u64 val; u64 addr; @@ -472,8 +471,7 @@ static void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) * exporting it to userspace (avoid exposure of regions * where we could have speculative execution) */ - if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN) && - is_kernel_addr(addr)) + if (is_kernel_addr(addr) && perf_allow_kernel(&event->attr) != 0) continue; /* Branches are read most recent first (ie. mfbhrb 0 is @@ -2087,12 +2085,12 @@ static void record_and_restart(struct perf_event *event, unsigned long val, if (event->attr.sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR)) - perf_get_data_addr(regs, &data.addr); + perf_get_data_addr(event, regs, &data.addr); if (event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK) { struct cpu_hw_events *cpuhw; cpuhw = this_cpu_ptr(&cpu_hw_events); - power_pmu_bhrb_read(cpuhw); + power_pmu_bhrb_read(event, cpuhw); data.br_stack = &cpuhw->bhrb_stack; } diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index 5ee3fed881d3..38de4a7f6752 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -549,9 +549,11 @@ static int bts_event_init(struct perf_event *event) * Note that the default paranoia setting permits unprivileged * users to profile the kernel. */ - if (event->attr.exclude_kernel && perf_paranoid_kernel() && - !capable(CAP_SYS_ADMIN)) - return -EACCES; + if (event->attr.exclude_kernel) { + ret = perf_allow_kernel(&event->attr); + if (ret) + return ret; + } if (x86_add_exclusive(x86_lbr_exclusive_bts)) return -EBUSY; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index fcef678c3423..bbf6588d47ee 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3315,8 +3315,9 @@ static int intel_pmu_hw_config(struct perf_event *event) if (x86_pmu.version < 3) return -EINVAL; - if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN)) - return -EACCES; + ret = perf_allow_cpu(&event->attr); + if (ret) + return ret; event->hw.config |= ARCH_PERFMON_EVENTSEL_ANY; diff --git a/arch/x86/events/intel/p4.c b/arch/x86/events/intel/p4.c index dee579efb2b2..a4cc66005ce8 100644 --- a/arch/x86/events/intel/p4.c +++ b/arch/x86/events/intel/p4.c @@ -776,8 +776,9 @@ static int p4_validate_raw_event(struct perf_event *event) * the user needs special permissions to be able to use it */ if (p4_ht_active() && p4_event_bind_map[v].shared) { - if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN)) - return -EACCES; + v = perf_allow_cpu(&event->attr); + if (v) + return v; } /* ESCR EventMask bits may be invalid */ diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index a3763247547c..20d8cf194fb7 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1818,6 +1818,14 @@ union security_list_options { void (*bpf_prog_free_security)(struct bpf_prog_aux *aux); #endif /* CONFIG_BPF_SYSCALL */ int (*locked_down)(enum lockdown_reason what); +#ifdef CONFIG_PERF_EVENTS + int (*perf_event_open)(struct perf_event_attr *attr, int type); + int (*perf_event_alloc)(struct perf_event *event); + void (*perf_event_free)(struct perf_event *event); + int (*perf_event_read)(struct perf_event *event); + int (*perf_event_write)(struct perf_event *event); + +#endif }; struct security_hook_heads { @@ -2060,6 +2068,13 @@ struct security_hook_heads { struct hlist_head bpf_prog_free_security; #endif /* CONFIG_BPF_SYSCALL */ struct hlist_head locked_down; +#ifdef CONFIG_PERF_EVENTS + struct hlist_head perf_event_open; + struct hlist_head perf_event_alloc; + struct hlist_head perf_event_free; + struct hlist_head perf_event_read; + struct hlist_head perf_event_write; +#endif } __randomize_layout; /* diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 61448c19a132..587ae4d002f5 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -56,6 +56,7 @@ struct perf_guest_info_callbacks { #include #include #include +#include #include struct perf_callchain_entry { @@ -721,6 +722,9 @@ struct perf_event { struct perf_cgroup *cgrp; /* cgroup event is attach to */ #endif +#ifdef CONFIG_SECURITY + void *security; +#endif struct list_head sb_list; #endif /* CONFIG_PERF_EVENTS */ }; @@ -1241,19 +1245,41 @@ extern int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, int perf_event_max_stack_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); -static inline bool perf_paranoid_tracepoint_raw(void) +/* Access to perf_event_open(2) syscall. */ +#define PERF_SECURITY_OPEN 0 + +/* Finer grained perf_event_open(2) access control. */ +#define PERF_SECURITY_CPU 1 +#define PERF_SECURITY_KERNEL 2 +#define PERF_SECURITY_TRACEPOINT 3 + +static inline int perf_is_paranoid(void) { return sysctl_perf_event_paranoid > -1; } -static inline bool perf_paranoid_cpu(void) +static inline int perf_allow_kernel(struct perf_event_attr *attr) { - return sysctl_perf_event_paranoid > 0; + if (sysctl_perf_event_paranoid > 1 && !capable(CAP_SYS_ADMIN)) + return -EACCES; + + return security_perf_event_open(attr, PERF_SECURITY_KERNEL); } -static inline bool perf_paranoid_kernel(void) +static inline int perf_allow_cpu(struct perf_event_attr *attr) { - return sysctl_perf_event_paranoid > 1; + if (sysctl_perf_event_paranoid > 0 && !capable(CAP_SYS_ADMIN)) + return -EACCES; + + return security_perf_event_open(attr, PERF_SECURITY_CPU); +} + +static inline int perf_allow_tracepoint(struct perf_event_attr *attr) +{ + if (sysctl_perf_event_paranoid > -1 && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + return security_perf_event_open(attr, PERF_SECURITY_TRACEPOINT); } extern void perf_event_init(void); diff --git a/include/linux/security.h b/include/linux/security.h index a8d59d612d27..4df79ffdc3a0 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1894,5 +1894,41 @@ static inline void security_bpf_prog_free(struct bpf_prog_aux *aux) #endif /* CONFIG_SECURITY */ #endif /* CONFIG_BPF_SYSCALL */ -#endif /* ! __LINUX_SECURITY_H */ +#ifdef CONFIG_PERF_EVENTS +struct perf_event_attr; + +#ifdef CONFIG_SECURITY +extern int security_perf_event_open(struct perf_event_attr *attr, int type); +extern int security_perf_event_alloc(struct perf_event *event); +extern void security_perf_event_free(struct perf_event *event); +extern int security_perf_event_read(struct perf_event *event); +extern int security_perf_event_write(struct perf_event *event); +#else +static inline int security_perf_event_open(struct perf_event_attr *attr, + int type) +{ + return 0; +} + +static inline int security_perf_event_alloc(struct perf_event *event) +{ + return 0; +} + +static inline void security_perf_event_free(struct perf_event *event) +{ +} + +static inline int security_perf_event_read(struct perf_event *event) +{ + return 0; +} +static inline int security_perf_event_write(struct perf_event *event) +{ + return 0; +} +#endif /* CONFIG_SECURITY */ +#endif /* CONFIG_PERF_EVENTS */ + +#endif /* ! __LINUX_SECURITY_H */ diff --git a/kernel/events/core.c b/kernel/events/core.c index 9ec0b0bfddbd..f9a5d4356562 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4229,8 +4229,9 @@ find_get_context(struct pmu *pmu, struct task_struct *task, if (!task) { /* Must be root to operate on a CPU event: */ - if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN)) - return ERR_PTR(-EACCES); + err = perf_allow_cpu(&event->attr); + if (err) + return ERR_PTR(err); cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu); ctx = &cpuctx->ctx; @@ -4539,6 +4540,8 @@ static void _free_event(struct perf_event *event) unaccount_event(event); + security_perf_event_free(event); + if (event->rb) { /* * Can happen when we close an event with re-directed output. @@ -4992,6 +4995,10 @@ perf_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) struct perf_event_context *ctx; int ret; + ret = security_perf_event_read(event); + if (ret) + return ret; + ctx = perf_event_ctx_lock(event); ret = __perf_read(event, buf, count); perf_event_ctx_unlock(event, ctx); @@ -5256,6 +5263,11 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg) struct perf_event_context *ctx; long ret; + /* Treat ioctl like writes as it is likely a mutating operation. */ + ret = security_perf_event_write(event); + if (ret) + return ret; + ctx = perf_event_ctx_lock(event); ret = _perf_ioctl(event, cmd, arg); perf_event_ctx_unlock(event, ctx); @@ -5719,6 +5731,10 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) if (!(vma->vm_flags & VM_SHARED)) return -EINVAL; + ret = security_perf_event_read(event); + if (ret) + return ret; + vma_size = vma->vm_end - vma->vm_start; if (vma->vm_pgoff == 0) { @@ -5844,7 +5860,7 @@ accounting: lock_limit >>= PAGE_SHIFT; locked = atomic64_read(&vma->vm_mm->pinned_vm) + extra; - if ((locked > lock_limit) && perf_paranoid_tracepoint_raw() && + if ((locked > lock_limit) && perf_is_paranoid() && !capable(CAP_IPC_LOCK)) { ret = -EPERM; goto unlock; @@ -10578,11 +10594,20 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, } } + err = security_perf_event_alloc(event); + if (err) + goto err_callchain_buffer; + /* symmetric to unaccount_event() in _free_event() */ account_event(event); return event; +err_callchain_buffer: + if (!event->parent) { + if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) + put_callchain_buffers(); + } err_addr_filters: kfree(event->addr_filter_ranges); @@ -10671,9 +10696,11 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr, attr->branch_sample_type = mask; } /* privileged levels capture (kernel, hv): check permissions */ - if ((mask & PERF_SAMPLE_BRANCH_PERM_PLM) - && perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN)) - return -EACCES; + if (mask & PERF_SAMPLE_BRANCH_PERM_PLM) { + ret = perf_allow_kernel(attr); + if (ret) + return ret; + } } if (attr->sample_type & PERF_SAMPLE_REGS_USER) { @@ -10886,13 +10913,19 @@ SYSCALL_DEFINE5(perf_event_open, if (flags & ~PERF_FLAG_ALL) return -EINVAL; + /* Do we allow access to perf_event_open(2) ? */ + err = security_perf_event_open(&attr, PERF_SECURITY_OPEN); + if (err) + return err; + err = perf_copy_attr(attr_uptr, &attr); if (err) return err; if (!attr.exclude_kernel) { - if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN)) - return -EACCES; + err = perf_allow_kernel(&attr); + if (err) + return err; } if (attr.namespaces) { @@ -10909,9 +10942,11 @@ SYSCALL_DEFINE5(perf_event_open, } /* Only privileged users can get physical addresses */ - if ((attr.sample_type & PERF_SAMPLE_PHYS_ADDR) && - perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN)) - return -EACCES; + if ((attr.sample_type & PERF_SAMPLE_PHYS_ADDR)) { + err = perf_allow_kernel(&attr); + if (err) + return err; + } err = security_locked_down(LOCKDOWN_PERF); if (err && (attr.sample_type & PERF_SAMPLE_REGS_INTR)) diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 0892e38ed6fb..0917fee6ee7c 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -8,6 +8,7 @@ #include #include +#include #include "trace.h" #include "trace_probe.h" @@ -26,8 +27,10 @@ static int total_ref_count; static int perf_trace_event_perm(struct trace_event_call *tp_event, struct perf_event *p_event) { + int ret; + if (tp_event->perf_perm) { - int ret = tp_event->perf_perm(tp_event, p_event); + ret = tp_event->perf_perm(tp_event, p_event); if (ret) return ret; } @@ -46,8 +49,9 @@ static int perf_trace_event_perm(struct trace_event_call *tp_event, /* The ftrace function trace is allowed only for root. */ if (ftrace_event_is_function(tp_event)) { - if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN)) - return -EPERM; + ret = perf_allow_tracepoint(&p_event->attr); + if (ret) + return ret; if (!is_sampling_event(p_event)) return 0; @@ -82,8 +86,9 @@ static int perf_trace_event_perm(struct trace_event_call *tp_event, * ...otherwise raw tracepoint data can be a severe data leak, * only allow root to have these. */ - if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN)) - return -EPERM; + ret = perf_allow_tracepoint(&p_event->attr); + if (ret) + return ret; return 0; } diff --git a/security/security.c b/security/security.c index 1bc000f834e2..cd2d18d2d279 100644 --- a/security/security.c +++ b/security/security.c @@ -2404,3 +2404,30 @@ int security_locked_down(enum lockdown_reason what) return call_int_hook(locked_down, 0, what); } EXPORT_SYMBOL(security_locked_down); + +#ifdef CONFIG_PERF_EVENTS +int security_perf_event_open(struct perf_event_attr *attr, int type) +{ + return call_int_hook(perf_event_open, 0, attr, type); +} + +int security_perf_event_alloc(struct perf_event *event) +{ + return call_int_hook(perf_event_alloc, 0, event); +} + +void security_perf_event_free(struct perf_event *event) +{ + call_void_hook(perf_event_free, event); +} + +int security_perf_event_read(struct perf_event *event) +{ + return call_int_hook(perf_event_read, 0, event); +} + +int security_perf_event_write(struct perf_event *event) +{ + return call_int_hook(perf_event_write, 0, event); +} +#endif /* CONFIG_PERF_EVENTS */ diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 9625b99e677f..28eb05490d59 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -6795,6 +6795,67 @@ struct lsm_blob_sizes selinux_blob_sizes __lsm_ro_after_init = { .lbs_msg_msg = sizeof(struct msg_security_struct), }; +#ifdef CONFIG_PERF_EVENTS +static int selinux_perf_event_open(struct perf_event_attr *attr, int type) +{ + u32 requested, sid = current_sid(); + + if (type == PERF_SECURITY_OPEN) + requested = PERF_EVENT__OPEN; + else if (type == PERF_SECURITY_CPU) + requested = PERF_EVENT__CPU; + else if (type == PERF_SECURITY_KERNEL) + requested = PERF_EVENT__KERNEL; + else if (type == PERF_SECURITY_TRACEPOINT) + requested = PERF_EVENT__TRACEPOINT; + else + return -EINVAL; + + return avc_has_perm(&selinux_state, sid, sid, SECCLASS_PERF_EVENT, + requested, NULL); +} + +static int selinux_perf_event_alloc(struct perf_event *event) +{ + struct perf_event_security_struct *perfsec; + + perfsec = kzalloc(sizeof(*perfsec), GFP_KERNEL); + if (!perfsec) + return -ENOMEM; + + perfsec->sid = current_sid(); + event->security = perfsec; + + return 0; +} + +static void selinux_perf_event_free(struct perf_event *event) +{ + struct perf_event_security_struct *perfsec = event->security; + + event->security = NULL; + kfree(perfsec); +} + +static int selinux_perf_event_read(struct perf_event *event) +{ + struct perf_event_security_struct *perfsec = event->security; + u32 sid = current_sid(); + + return avc_has_perm(&selinux_state, sid, perfsec->sid, + SECCLASS_PERF_EVENT, PERF_EVENT__READ, NULL); +} + +static int selinux_perf_event_write(struct perf_event *event) +{ + struct perf_event_security_struct *perfsec = event->security; + u32 sid = current_sid(); + + return avc_has_perm(&selinux_state, sid, perfsec->sid, + SECCLASS_PERF_EVENT, PERF_EVENT__WRITE, NULL); +} +#endif + static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(binder_set_context_mgr, selinux_binder_set_context_mgr), LSM_HOOK_INIT(binder_transaction, selinux_binder_transaction), @@ -7030,6 +7091,14 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(bpf_map_free_security, selinux_bpf_map_free), LSM_HOOK_INIT(bpf_prog_free_security, selinux_bpf_prog_free), #endif + +#ifdef CONFIG_PERF_EVENTS + LSM_HOOK_INIT(perf_event_open, selinux_perf_event_open), + LSM_HOOK_INIT(perf_event_alloc, selinux_perf_event_alloc), + LSM_HOOK_INIT(perf_event_free, selinux_perf_event_free), + LSM_HOOK_INIT(perf_event_read, selinux_perf_event_read), + LSM_HOOK_INIT(perf_event_write, selinux_perf_event_write), +#endif }; static __init int selinux_init(void) diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h index 32e9b03be3dd..7db24855e12d 100644 --- a/security/selinux/include/classmap.h +++ b/security/selinux/include/classmap.h @@ -244,6 +244,8 @@ struct security_class_mapping secclass_map[] = { {"map_create", "map_read", "map_write", "prog_load", "prog_run"} }, { "xdp_socket", { COMMON_SOCK_PERMS, NULL } }, + { "perf_event", + {"open", "cpu", "kernel", "tracepoint", "read", "write"} }, { NULL } }; diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h index 586b7abd0aa7..a4a86cbcfb0a 100644 --- a/security/selinux/include/objsec.h +++ b/security/selinux/include/objsec.h @@ -141,7 +141,11 @@ struct pkey_security_struct { }; struct bpf_security_struct { - u32 sid; /*SID of bpf obj creater*/ + u32 sid; /* SID of bpf obj creator */ +}; + +struct perf_event_security_struct { + u32 sid; /* SID of perf_event obj creator */ }; extern struct lsm_blob_sizes selinux_blob_sizes; -- cgit v1.2.3-71-gd317 From 7684e2c4384d5d1f884b01ab8bff2369e4db0bff Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Thu, 17 Oct 2019 13:12:01 -0700 Subject: iomap: iomap that extends beyond EOF should be marked dirty When doing a direct IO that spans the current EOF, and there are written blocks beyond EOF that extend beyond the current write, the only metadata update that needs to be done is a file size extension. However, we don't mark such iomaps as IOMAP_F_DIRTY to indicate that there is IO completion metadata updates required, and hence we may fail to correctly sync file size extensions made in IO completion when O_DSYNC writes are being used and the hardware supports FUA. Hence when setting IOMAP_F_DIRTY, we need to also take into account whether the iomap spans the current EOF. If it does, then we need to mark it dirty so that IO completion will call generic_write_sync() to flush the inode size update to stable storage correctly. Fixes: 3460cac1ca76 ("iomap: Use FUA for pure data O_DSYNC DIO writes") Signed-off-by: Dave Chinner Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong [darrick: removed the ext4 part; they'll handle it separately] Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_iomap.c | 7 +++++++ include/linux/iomap.h | 2 ++ 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index f780e223b118..32993c2acbd9 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1049,6 +1049,13 @@ xfs_file_iomap_begin( trace_xfs_iomap_alloc(ip, offset, length, XFS_DATA_FORK, &imap); out_finish: + /* + * Writes that span EOF might trigger an IO size update on completion, + * so consider them to be dirty for the purposes of O_DSYNC even if + * there is no other metadata changes pending or have been made here. + */ + if ((flags & IOMAP_WRITE) && offset + length > i_size_read(inode)) + iomap->flags |= IOMAP_F_DIRTY; return xfs_bmbt_to_iomap(ip, iomap, &imap, shared); out_found: diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 76b14cb729dc..4b25ad6b5edd 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -32,6 +32,8 @@ struct vm_fault; * * IOMAP_F_DIRTY indicates the inode has uncommitted metadata needed to access * written data and requires fdatasync to commit them to persistent storage. + * This needs to take into account metadata changes that *may* be made at IO + * completion, such as file size updates from direct IO. */ #define IOMAP_F_NEW 0x01 /* blocks have been newly allocated */ #define IOMAP_F_DIRTY 0x02 /* uncommitted metadata */ -- cgit v1.2.3-71-gd317 From ffedeeb780dc554eff3d3b16e6a462a26a41d7ec Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 11 Oct 2019 13:50:41 +0200 Subject: linkage: Introduce new macros for assembler symbols Introduce new C macros for annotations of functions and data in assembly. There is a long-standing mess in macros like ENTRY, END, ENDPROC and similar. They are used in different manners and sometimes incorrectly. So introduce macros with clear use to annotate assembly as follows: a) Support macros for the ones below SYM_T_FUNC -- type used by assembler to mark functions SYM_T_OBJECT -- type used by assembler to mark data SYM_T_NONE -- type used by assembler to mark entries of unknown type They are defined as STT_FUNC, STT_OBJECT, and STT_NOTYPE respectively. According to the gas manual, this is the most portable way. I am not sure about other assemblers, so this can be switched back to %function and %object if this turns into a problem. Architectures can also override them by something like ", @function" if they need. SYM_A_ALIGN, SYM_A_NONE -- align the symbol? SYM_L_GLOBAL, SYM_L_WEAK, SYM_L_LOCAL -- linkage of symbols b) Mostly internal annotations, used by the ones below SYM_ENTRY -- use only if you have to (for non-paired symbols) SYM_START -- use only if you have to (for paired symbols) SYM_END -- use only if you have to (for paired symbols) c) Annotations for code SYM_INNER_LABEL_ALIGN -- only for labels in the middle of code SYM_INNER_LABEL -- only for labels in the middle of code SYM_FUNC_START_LOCAL_ALIAS -- use where there are two local names for one function SYM_FUNC_START_ALIAS -- use where there are two global names for one function SYM_FUNC_END_ALIAS -- the end of LOCAL_ALIASed or ALIASed function SYM_FUNC_START -- use for global functions SYM_FUNC_START_NOALIGN -- use for global functions, w/o alignment SYM_FUNC_START_LOCAL -- use for local functions SYM_FUNC_START_LOCAL_NOALIGN -- use for local functions, w/o alignment SYM_FUNC_START_WEAK -- use for weak functions SYM_FUNC_START_WEAK_NOALIGN -- use for weak functions, w/o alignment SYM_FUNC_END -- the end of SYM_FUNC_START_LOCAL, SYM_FUNC_START, SYM_FUNC_START_WEAK, ... For functions with special (non-C) calling conventions: SYM_CODE_START -- use for non-C (special) functions SYM_CODE_START_NOALIGN -- use for non-C (special) functions, w/o alignment SYM_CODE_START_LOCAL -- use for local non-C (special) functions SYM_CODE_START_LOCAL_NOALIGN -- use for local non-C (special) functions, w/o alignment SYM_CODE_END -- the end of SYM_CODE_START_LOCAL or SYM_CODE_START d) For data SYM_DATA_START -- global data symbol SYM_DATA_START_LOCAL -- local data symbol SYM_DATA_END -- the end of the SYM_DATA_START symbol SYM_DATA_END_LABEL -- the labeled end of SYM_DATA_START symbol SYM_DATA -- start+end wrapper around simple global data SYM_DATA_LOCAL -- start+end wrapper around simple local data ========== The macros allow to pair starts and ends of functions and mark functions correctly in the output ELF objects. All users of the old macros in x86 are converted to use these in further patches. Signed-off-by: Jiri Slaby Signed-off-by: Borislav Petkov Acked-by: Rafael J. Wysocki Cc: Andrew Morton Cc: Andrey Ryabinin Cc: Boris Ostrovsky Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Len Brown Cc: Linus Torvalds Cc: linux-arch@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-pm@vger.kernel.org Cc: Mark Rutland Cc: Pavel Machek Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Cc: x86-ml Cc: xen-devel@lists.xenproject.org Link: https://lkml.kernel.org/r/20191011115108.12392-2-jslaby@suse.cz --- Documentation/asm-annotations.rst | 216 +++++++++++++++++++++++++++++++++ Documentation/index.rst | 8 ++ arch/x86/include/asm/linkage.h | 10 +- include/linux/linkage.h | 245 ++++++++++++++++++++++++++++++++++++-- 4 files changed, 468 insertions(+), 11 deletions(-) create mode 100644 Documentation/asm-annotations.rst (limited to 'include/linux') diff --git a/Documentation/asm-annotations.rst b/Documentation/asm-annotations.rst new file mode 100644 index 000000000000..29ccd6e61fe5 --- /dev/null +++ b/Documentation/asm-annotations.rst @@ -0,0 +1,216 @@ +Assembler Annotations +===================== + +Copyright (c) 2017-2019 Jiri Slaby + +This document describes the new macros for annotation of data and code in +assembly. In particular, it contains information about ``SYM_FUNC_START``, +``SYM_FUNC_END``, ``SYM_CODE_START``, and similar. + +Rationale +--------- +Some code like entries, trampolines, or boot code needs to be written in +assembly. The same as in C, such code is grouped into functions and +accompanied with data. Standard assemblers do not force users into precisely +marking these pieces as code, data, or even specifying their length. +Nevertheless, assemblers provide developers with such annotations to aid +debuggers throughout assembly. On top of that, developers also want to mark +some functions as *global* in order to be visible outside of their translation +units. + +Over time, the Linux kernel has adopted macros from various projects (like +``binutils``) to facilitate such annotations. So for historic reasons, +developers have been using ``ENTRY``, ``END``, ``ENDPROC``, and other +annotations in assembly. Due to the lack of their documentation, the macros +are used in rather wrong contexts at some locations. Clearly, ``ENTRY`` was +intended to denote the beginning of global symbols (be it data or code). +``END`` used to mark the end of data or end of special functions with +*non-standard* calling convention. In contrast, ``ENDPROC`` should annotate +only ends of *standard* functions. + +When these macros are used correctly, they help assemblers generate a nice +object with both sizes and types set correctly. For example, the result of +``arch/x86/lib/putuser.S``:: + + Num: Value Size Type Bind Vis Ndx Name + 25: 0000000000000000 33 FUNC GLOBAL DEFAULT 1 __put_user_1 + 29: 0000000000000030 37 FUNC GLOBAL DEFAULT 1 __put_user_2 + 32: 0000000000000060 36 FUNC GLOBAL DEFAULT 1 __put_user_4 + 35: 0000000000000090 37 FUNC GLOBAL DEFAULT 1 __put_user_8 + +This is not only important for debugging purposes. When there are properly +annotated objects like this, tools can be run on them to generate more useful +information. In particular, on properly annotated objects, ``objtool`` can be +run to check and fix the object if needed. Currently, ``objtool`` can report +missing frame pointer setup/destruction in functions. It can also +automatically generate annotations for :doc:`ORC unwinder ` +for most code. Both of these are especially important to support reliable +stack traces which are in turn necessary for :doc:`Kernel live patching +`. + +Caveat and Discussion +--------------------- +As one might realize, there were only three macros previously. That is indeed +insufficient to cover all the combinations of cases: + +* standard/non-standard function +* code/data +* global/local symbol + +There was a discussion_ and instead of extending the current ``ENTRY/END*`` +macros, it was decided that brand new macros should be introduced instead:: + + So how about using macro names that actually show the purpose, instead + of importing all the crappy, historic, essentially randomly chosen + debug symbol macro names from the binutils and older kernels? + +.. _discussion: https://lkml.kernel.org/r/20170217104757.28588-1-jslaby@suse.cz + +Macros Description +------------------ + +The new macros are prefixed with the ``SYM_`` prefix and can be divided into +three main groups: + +1. ``SYM_FUNC_*`` -- to annotate C-like functions. This means functions with + standard C calling conventions, i.e. the stack contains a return address at + the predefined place and a return from the function can happen in a + standard way. When frame pointers are enabled, save/restore of frame + pointer shall happen at the start/end of a function, respectively, too. + + Checking tools like ``objtool`` should ensure such marked functions conform + to these rules. The tools can also easily annotate these functions with + debugging information (like *ORC data*) automatically. + +2. ``SYM_CODE_*`` -- special functions called with special stack. Be it + interrupt handlers with special stack content, trampolines, or startup + functions. + + Checking tools mostly ignore checking of these functions. But some debug + information still can be generated automatically. For correct debug data, + this code needs hints like ``UNWIND_HINT_REGS`` provided by developers. + +3. ``SYM_DATA*`` -- obviously data belonging to ``.data`` sections and not to + ``.text``. Data do not contain instructions, so they have to be treated + specially by the tools: they should not treat the bytes as instructions, + nor assign any debug information to them. + +Instruction Macros +~~~~~~~~~~~~~~~~~~ +This section covers ``SYM_FUNC_*`` and ``SYM_CODE_*`` enumerated above. + +* ``SYM_FUNC_START`` and ``SYM_FUNC_START_LOCAL`` are supposed to be **the + most frequent markings**. They are used for functions with standard calling + conventions -- global and local. Like in C, they both align the functions to + architecture specific ``__ALIGN`` bytes. There are also ``_NOALIGN`` variants + for special cases where developers do not want this implicit alignment. + + ``SYM_FUNC_START_WEAK`` and ``SYM_FUNC_START_WEAK_NOALIGN`` markings are + also offered as an assembler counterpart to the *weak* attribute known from + C. + + All of these **shall** be coupled with ``SYM_FUNC_END``. First, it marks + the sequence of instructions as a function and computes its size to the + generated object file. Second, it also eases checking and processing such + object files as the tools can trivially find exact function boundaries. + + So in most cases, developers should write something like in the following + example, having some asm instructions in between the macros, of course:: + + SYM_FUNC_START(function_hook) + ... asm insns ... + SYM_FUNC_END(function_hook) + + In fact, this kind of annotation corresponds to the now deprecated ``ENTRY`` + and ``ENDPROC`` macros. + +* ``SYM_FUNC_START_ALIAS`` and ``SYM_FUNC_START_LOCAL_ALIAS`` serve for those + who decided to have two or more names for one function. The typical use is:: + + SYM_FUNC_START_ALIAS(__memset) + SYM_FUNC_START(memset) + ... asm insns ... + SYM_FUNC_END(memset) + SYM_FUNC_END_ALIAS(__memset) + + In this example, one can call ``__memset`` or ``memset`` with the same + result, except the debug information for the instructions is generated to + the object file only once -- for the non-``ALIAS`` case. + +* ``SYM_CODE_START`` and ``SYM_CODE_START_LOCAL`` should be used only in + special cases -- if you know what you are doing. This is used exclusively + for interrupt handlers and similar where the calling convention is not the C + one. ``_NOALIGN`` variants exist too. The use is the same as for the ``FUNC`` + category above:: + + SYM_CODE_START_LOCAL(bad_put_user) + ... asm insns ... + SYM_CODE_END(bad_put_user) + + Again, every ``SYM_CODE_START*`` **shall** be coupled by ``SYM_CODE_END``. + + To some extent, this category corresponds to deprecated ``ENTRY`` and + ``END``. Except ``END`` had several other meanings too. + +* ``SYM_INNER_LABEL*`` is used to denote a label inside some + ``SYM_{CODE,FUNC}_START`` and ``SYM_{CODE,FUNC}_END``. They are very similar + to C labels, except they can be made global. An example of use:: + + SYM_CODE_START(ftrace_caller) + /* save_mcount_regs fills in first two parameters */ + ... + + SYM_INNER_LABEL(ftrace_caller_op_ptr, SYM_L_GLOBAL) + /* Load the ftrace_ops into the 3rd parameter */ + ... + + SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) + call ftrace_stub + ... + retq + SYM_CODE_END(ftrace_caller) + +Data Macros +~~~~~~~~~~~ +Similar to instructions, there is a couple of macros to describe data in the +assembly. + +* ``SYM_DATA_START`` and ``SYM_DATA_START_LOCAL`` mark the start of some data + and shall be used in conjunction with either ``SYM_DATA_END``, or + ``SYM_DATA_END_LABEL``. The latter adds also a label to the end, so that + people can use ``lstack`` and (local) ``lstack_end`` in the following + example:: + + SYM_DATA_START_LOCAL(lstack) + .skip 4096 + SYM_DATA_END_LABEL(lstack, SYM_L_LOCAL, lstack_end) + +* ``SYM_DATA`` and ``SYM_DATA_LOCAL`` are variants for simple, mostly one-line + data:: + + SYM_DATA(HEAP, .long rm_heap) + SYM_DATA(heap_end, .long rm_stack) + + In the end, they expand to ``SYM_DATA_START`` with ``SYM_DATA_END`` + internally. + +Support Macros +~~~~~~~~~~~~~~ +All the above reduce themselves to some invocation of ``SYM_START``, +``SYM_END``, or ``SYM_ENTRY`` at last. Normally, developers should avoid using +these. + +Further, in the above examples, one could see ``SYM_L_LOCAL``. There are also +``SYM_L_GLOBAL`` and ``SYM_L_WEAK``. All are intended to denote linkage of a +symbol marked by them. They are used either in ``_LABEL`` variants of the +earlier macros, or in ``SYM_START``. + + +Overriding Macros +~~~~~~~~~~~~~~~~~ +Architecture can also override any of the macros in their own +``asm/linkage.h``, including macros specifying the type of a symbol +(``SYM_T_FUNC``, ``SYM_T_OBJECT``, and ``SYM_T_NONE``). As every macro +described in this file is surrounded by ``#ifdef`` + ``#endif``, it is enough +to define the macros differently in the aforementioned architecture-dependent +header. diff --git a/Documentation/index.rst b/Documentation/index.rst index b843e313d2f2..2ceab197246f 100644 --- a/Documentation/index.rst +++ b/Documentation/index.rst @@ -135,6 +135,14 @@ needed). mic/index scheduler/index +Architecture-agnostic documentation +----------------------------------- + +.. toctree:: + :maxdepth: 2 + + asm-annotations + Architecture-specific documentation ----------------------------------- diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 14caa9d9fb7f..e07188e8d763 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -13,9 +13,13 @@ #ifdef __ASSEMBLY__ -#define GLOBAL(name) \ - .globl name; \ - name: +/* + * GLOBAL is DEPRECATED + * + * use SYM_DATA_START, SYM_FUNC_START, SYM_INNER_LABEL, SYM_CODE_START, or + * similar + */ +#define GLOBAL(name) SYM_ENTRY(name, SYM_L_GLOBAL, SYM_A_NONE) #if defined(CONFIG_X86_64) || defined(CONFIG_X86_ALIGNMENT_16) #define __ALIGN .p2align 4, 0x90 diff --git a/include/linux/linkage.h b/include/linux/linkage.h index 7e020782ade2..f3ae8f3dea2c 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -75,32 +75,58 @@ #ifdef __ASSEMBLY__ +/* SYM_T_FUNC -- type used by assembler to mark functions */ +#ifndef SYM_T_FUNC +#define SYM_T_FUNC STT_FUNC +#endif + +/* SYM_T_OBJECT -- type used by assembler to mark data */ +#ifndef SYM_T_OBJECT +#define SYM_T_OBJECT STT_OBJECT +#endif + +/* SYM_T_NONE -- type used by assembler to mark entries of unknown type */ +#ifndef SYM_T_NONE +#define SYM_T_NONE STT_NOTYPE +#endif + +/* SYM_A_* -- align the symbol? */ +#define SYM_A_ALIGN ALIGN +#define SYM_A_NONE /* nothing */ + +/* SYM_L_* -- linkage of symbols */ +#define SYM_L_GLOBAL(name) .globl name +#define SYM_L_WEAK(name) .weak name +#define SYM_L_LOCAL(name) /* nothing */ + #ifndef LINKER_SCRIPT #define ALIGN __ALIGN #define ALIGN_STR __ALIGN_STR +/* === DEPRECATED annotations === */ + #ifndef GLOBAL +/* deprecated, use SYM_DATA*, SYM_ENTRY, or similar */ #define GLOBAL(name) \ .globl name ASM_NL \ name: #endif #ifndef ENTRY +/* deprecated, use SYM_FUNC_START */ #define ENTRY(name) \ - .globl name ASM_NL \ - ALIGN ASM_NL \ - name: + SYM_FUNC_START(name) #endif #endif /* LINKER_SCRIPT */ #ifndef WEAK +/* deprecated, use SYM_FUNC_START_WEAK* */ #define WEAK(name) \ - .weak name ASM_NL \ - ALIGN ASM_NL \ - name: + SYM_FUNC_START_WEAK(name) #endif #ifndef END +/* deprecated, use SYM_FUNC_END, SYM_DATA_END, or SYM_END */ #define END(name) \ .size name, .-name #endif @@ -110,11 +136,214 @@ * static analysis tools such as stack depth analyzer. */ #ifndef ENDPROC +/* deprecated, use SYM_FUNC_END */ #define ENDPROC(name) \ - .type name, @function ASM_NL \ - END(name) + SYM_FUNC_END(name) +#endif + +/* === generic annotations === */ + +/* SYM_ENTRY -- use only if you have to for non-paired symbols */ +#ifndef SYM_ENTRY +#define SYM_ENTRY(name, linkage, align...) \ + linkage(name) ASM_NL \ + align ASM_NL \ + name: +#endif + +/* SYM_START -- use only if you have to */ +#ifndef SYM_START +#define SYM_START(name, linkage, align...) \ + SYM_ENTRY(name, linkage, align) +#endif + +/* SYM_END -- use only if you have to */ +#ifndef SYM_END +#define SYM_END(name, sym_type) \ + .type name sym_type ASM_NL \ + .size name, .-name +#endif + +/* === code annotations === */ + +/* + * FUNC -- C-like functions (proper stack frame etc.) + * CODE -- non-C code (e.g. irq handlers with different, special stack etc.) + * + * Objtool validates stack for FUNC, but not for CODE. + * Objtool generates debug info for both FUNC & CODE, but needs special + * annotations for each CODE's start (to describe the actual stack frame). + * + * ALIAS -- does not generate debug info -- the aliased function will + */ + +/* SYM_INNER_LABEL_ALIGN -- only for labels in the middle of code */ +#ifndef SYM_INNER_LABEL_ALIGN +#define SYM_INNER_LABEL_ALIGN(name, linkage) \ + .type name SYM_T_NONE ASM_NL \ + SYM_ENTRY(name, linkage, SYM_A_ALIGN) +#endif + +/* SYM_INNER_LABEL -- only for labels in the middle of code */ +#ifndef SYM_INNER_LABEL +#define SYM_INNER_LABEL(name, linkage) \ + .type name SYM_T_NONE ASM_NL \ + SYM_ENTRY(name, linkage, SYM_A_NONE) +#endif + +/* + * SYM_FUNC_START_LOCAL_ALIAS -- use where there are two local names for one + * function + */ +#ifndef SYM_FUNC_START_LOCAL_ALIAS +#define SYM_FUNC_START_LOCAL_ALIAS(name) \ + SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN) +#endif + +/* + * SYM_FUNC_START_ALIAS -- use where there are two global names for one + * function + */ +#ifndef SYM_FUNC_START_ALIAS +#define SYM_FUNC_START_ALIAS(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) +#endif + +/* SYM_FUNC_START -- use for global functions */ +#ifndef SYM_FUNC_START +/* + * The same as SYM_FUNC_START_ALIAS, but we will need to distinguish these two + * later. + */ +#define SYM_FUNC_START(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) +#endif + +/* SYM_FUNC_START_NOALIGN -- use for global functions, w/o alignment */ +#ifndef SYM_FUNC_START_NOALIGN +#define SYM_FUNC_START_NOALIGN(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_NONE) +#endif + +/* SYM_FUNC_START_LOCAL -- use for local functions */ +#ifndef SYM_FUNC_START_LOCAL +/* the same as SYM_FUNC_START_LOCAL_ALIAS, see comment near SYM_FUNC_START */ +#define SYM_FUNC_START_LOCAL(name) \ + SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN) #endif +/* SYM_FUNC_START_LOCAL_NOALIGN -- use for local functions, w/o alignment */ +#ifndef SYM_FUNC_START_LOCAL_NOALIGN +#define SYM_FUNC_START_LOCAL_NOALIGN(name) \ + SYM_START(name, SYM_L_LOCAL, SYM_A_NONE) #endif +/* SYM_FUNC_START_WEAK -- use for weak functions */ +#ifndef SYM_FUNC_START_WEAK +#define SYM_FUNC_START_WEAK(name) \ + SYM_START(name, SYM_L_WEAK, SYM_A_ALIGN) #endif + +/* SYM_FUNC_START_WEAK_NOALIGN -- use for weak functions, w/o alignment */ +#ifndef SYM_FUNC_START_WEAK_NOALIGN +#define SYM_FUNC_START_WEAK_NOALIGN(name) \ + SYM_START(name, SYM_L_WEAK, SYM_A_NONE) +#endif + +/* SYM_FUNC_END_ALIAS -- the end of LOCAL_ALIASed or ALIASed function */ +#ifndef SYM_FUNC_END_ALIAS +#define SYM_FUNC_END_ALIAS(name) \ + SYM_END(name, SYM_T_FUNC) +#endif + +/* + * SYM_FUNC_END -- the end of SYM_FUNC_START_LOCAL, SYM_FUNC_START, + * SYM_FUNC_START_WEAK, ... + */ +#ifndef SYM_FUNC_END +/* the same as SYM_FUNC_END_ALIAS, see comment near SYM_FUNC_START */ +#define SYM_FUNC_END(name) \ + SYM_END(name, SYM_T_FUNC) +#endif + +/* SYM_CODE_START -- use for non-C (special) functions */ +#ifndef SYM_CODE_START +#define SYM_CODE_START(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) +#endif + +/* SYM_CODE_START_NOALIGN -- use for non-C (special) functions, w/o alignment */ +#ifndef SYM_CODE_START_NOALIGN +#define SYM_CODE_START_NOALIGN(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_NONE) +#endif + +/* SYM_CODE_START_LOCAL -- use for local non-C (special) functions */ +#ifndef SYM_CODE_START_LOCAL +#define SYM_CODE_START_LOCAL(name) \ + SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN) +#endif + +/* + * SYM_CODE_START_LOCAL_NOALIGN -- use for local non-C (special) functions, + * w/o alignment + */ +#ifndef SYM_CODE_START_LOCAL_NOALIGN +#define SYM_CODE_START_LOCAL_NOALIGN(name) \ + SYM_START(name, SYM_L_LOCAL, SYM_A_NONE) +#endif + +/* SYM_CODE_END -- the end of SYM_CODE_START_LOCAL, SYM_CODE_START, ... */ +#ifndef SYM_CODE_END +#define SYM_CODE_END(name) \ + SYM_END(name, SYM_T_NONE) +#endif + +/* === data annotations === */ + +/* SYM_DATA_START -- global data symbol */ +#ifndef SYM_DATA_START +#define SYM_DATA_START(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_NONE) +#endif + +/* SYM_DATA_START -- local data symbol */ +#ifndef SYM_DATA_START_LOCAL +#define SYM_DATA_START_LOCAL(name) \ + SYM_START(name, SYM_L_LOCAL, SYM_A_NONE) +#endif + +/* SYM_DATA_END -- the end of SYM_DATA_START symbol */ +#ifndef SYM_DATA_END +#define SYM_DATA_END(name) \ + SYM_END(name, SYM_T_OBJECT) +#endif + +/* SYM_DATA_END_LABEL -- the labeled end of SYM_DATA_START symbol */ +#ifndef SYM_DATA_END_LABEL +#define SYM_DATA_END_LABEL(name, linkage, label) \ + linkage(label) ASM_NL \ + .type label SYM_T_OBJECT ASM_NL \ + label: \ + SYM_END(name, SYM_T_OBJECT) +#endif + +/* SYM_DATA -- start+end wrapper around simple global data */ +#ifndef SYM_DATA +#define SYM_DATA(name, data...) \ + SYM_DATA_START(name) ASM_NL \ + data ASM_NL \ + SYM_DATA_END(name) +#endif + +/* SYM_DATA_LOCAL -- start+end wrapper around simple local data */ +#ifndef SYM_DATA_LOCAL +#define SYM_DATA_LOCAL(name, data...) \ + SYM_DATA_START_LOCAL(name) ASM_NL \ + data ASM_NL \ + SYM_DATA_END(name) +#endif + +#endif /* __ASSEMBLY__ */ + +#endif /* _LINUX_LINKAGE_H */ -- cgit v1.2.3-71-gd317 From b4edca150106a68d05eaf823d665a355ff19e28b Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 11 Oct 2019 13:50:59 +0200 Subject: x86/asm: Remove the last GLOBAL user and remove the macro Convert the remaining 32bit users and remove the GLOBAL macro finally. In particular, this means to use SYM_ENTRY for the singlestepping hack region. Exclude the global definition of GLOBAL from x86 too. Signed-off-by: Jiri Slaby Signed-off-by: Borislav Petkov Cc: Andrew Morton Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: linux-arch@vger.kernel.org Cc: Mark Rutland Cc: "Rafael J. Wysocki" Cc: Thomas Gleixner Cc: Will Deacon Cc: x86-ml Link: https://lkml.kernel.org/r/20191011115108.12392-20-jslaby@suse.cz --- arch/x86/entry/entry_32.S | 4 ++-- arch/x86/include/asm/linkage.h | 8 -------- include/linux/linkage.h | 2 ++ 3 files changed, 4 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index f37ff583cecb..4900a6a5e125 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -832,7 +832,7 @@ SYM_INNER_LABEL_ALIGN(resume_userspace, SYM_L_LOCAL) jmp restore_all SYM_CODE_END(ret_from_exception) -GLOBAL(__begin_SYSENTER_singlestep_region) +SYM_ENTRY(__begin_SYSENTER_singlestep_region, SYM_L_GLOBAL, SYM_A_NONE) /* * All code from here through __end_SYSENTER_singlestep_region is subject * to being single-stepped if a user program sets TF and executes SYSENTER. @@ -1011,7 +1011,7 @@ ENTRY(entry_SYSENTER_32) pushl $X86_EFLAGS_FIXED popfl jmp .Lsysenter_flags_fixed -GLOBAL(__end_SYSENTER_singlestep_region) +SYM_ENTRY(__end_SYSENTER_singlestep_region, SYM_L_GLOBAL, SYM_A_NONE) ENDPROC(entry_SYSENTER_32) /* diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index e07188e8d763..365111789cc6 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -13,14 +13,6 @@ #ifdef __ASSEMBLY__ -/* - * GLOBAL is DEPRECATED - * - * use SYM_DATA_START, SYM_FUNC_START, SYM_INNER_LABEL, SYM_CODE_START, or - * similar - */ -#define GLOBAL(name) SYM_ENTRY(name, SYM_L_GLOBAL, SYM_A_NONE) - #if defined(CONFIG_X86_64) || defined(CONFIG_X86_ALIGNMENT_16) #define __ALIGN .p2align 4, 0x90 #define __ALIGN_STR __stringify(__ALIGN) diff --git a/include/linux/linkage.h b/include/linux/linkage.h index f3ae8f3dea2c..cb1108dde385 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -105,12 +105,14 @@ /* === DEPRECATED annotations === */ +#ifndef CONFIG_X86 #ifndef GLOBAL /* deprecated, use SYM_DATA*, SYM_ENTRY, or similar */ #define GLOBAL(name) \ .globl name ASM_NL \ name: #endif +#endif #ifndef ENTRY /* deprecated, use SYM_FUNC_START */ -- cgit v1.2.3-71-gd317 From 6dcc5627f6aec4cb1d1494d06a48d8061db06a04 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 11 Oct 2019 13:51:04 +0200 Subject: x86/asm: Change all ENTRY+ENDPROC to SYM_FUNC_* MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These are all functions which are invoked from elsewhere, so annotate them as global using the new SYM_FUNC_START and their ENDPROC's by SYM_FUNC_END. Make sure ENTRY/ENDPROC is not defined on X86_64, given these were the last users. Signed-off-by: Jiri Slaby Signed-off-by: Borislav Petkov Reviewed-by: Rafael J. Wysocki [hibernate] Reviewed-by: Boris Ostrovsky [xen bits] Acked-by: Herbert Xu [crypto] Cc: Allison Randal Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Andy Shevchenko Cc: Ard Biesheuvel Cc: Armijn Hemel Cc: Cao jin Cc: Darren Hart Cc: Dave Hansen Cc: "David S. Miller" Cc: Enrico Weigelt Cc: Greg Kroah-Hartman Cc: Herbert Xu Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jim Mattson Cc: Joerg Roedel Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Kate Stewart Cc: "Kirill A. Shutemov" Cc: kvm ML Cc: Len Brown Cc: linux-arch@vger.kernel.org Cc: linux-crypto@vger.kernel.org Cc: linux-efi Cc: linux-efi@vger.kernel.org Cc: linux-pm@vger.kernel.org Cc: Mark Rutland Cc: Matt Fleming Cc: Paolo Bonzini Cc: Pavel Machek Cc: Peter Zijlstra Cc: platform-driver-x86@vger.kernel.org Cc: "Radim Krčmář" Cc: Sean Christopherson Cc: Stefano Stabellini Cc: "Steven Rostedt (VMware)" Cc: Thomas Gleixner Cc: Vitaly Kuznetsov Cc: Wanpeng Li Cc: Wei Huang Cc: x86-ml Cc: xen-devel@lists.xenproject.org Cc: Xiaoyao Li Link: https://lkml.kernel.org/r/20191011115108.12392-25-jslaby@suse.cz --- arch/x86/boot/compressed/efi_thunk_64.S | 4 +- arch/x86/boot/compressed/head_64.S | 16 ++++---- arch/x86/boot/compressed/mem_encrypt.S | 8 ++-- arch/x86/crypto/aegis128-aesni-asm.S | 28 ++++++------- arch/x86/crypto/aes_ctrby8_avx-x86_64.S | 12 +++--- arch/x86/crypto/aesni-intel_asm.S | 60 ++++++++++++++-------------- arch/x86/crypto/aesni-intel_avx-x86_64.S | 32 +++++++-------- arch/x86/crypto/blowfish-x86_64-asm_64.S | 16 ++++---- arch/x86/crypto/camellia-aesni-avx-asm_64.S | 24 +++++------ arch/x86/crypto/camellia-aesni-avx2-asm_64.S | 24 +++++------ arch/x86/crypto/camellia-x86_64-asm_64.S | 16 ++++---- arch/x86/crypto/cast5-avx-x86_64-asm_64.S | 16 ++++---- arch/x86/crypto/cast6-avx-x86_64-asm_64.S | 24 +++++------ arch/x86/crypto/chacha-avx2-x86_64.S | 12 +++--- arch/x86/crypto/chacha-avx512vl-x86_64.S | 12 +++--- arch/x86/crypto/chacha-ssse3-x86_64.S | 12 +++--- arch/x86/crypto/crc32-pclmul_asm.S | 4 +- arch/x86/crypto/crc32c-pcl-intel-asm_64.S | 4 +- arch/x86/crypto/crct10dif-pcl-asm_64.S | 4 +- arch/x86/crypto/des3_ede-asm_64.S | 8 ++-- arch/x86/crypto/ghash-clmulni-intel_asm.S | 8 ++-- arch/x86/crypto/nh-avx2-x86_64.S | 4 +- arch/x86/crypto/nh-sse2-x86_64.S | 4 +- arch/x86/crypto/poly1305-avx2-x86_64.S | 4 +- arch/x86/crypto/poly1305-sse2-x86_64.S | 8 ++-- arch/x86/crypto/serpent-avx-x86_64-asm_64.S | 24 +++++------ arch/x86/crypto/serpent-avx2-asm_64.S | 24 +++++------ arch/x86/crypto/serpent-sse2-x86_64-asm_64.S | 8 ++-- arch/x86/crypto/sha1_avx2_x86_64_asm.S | 4 +- arch/x86/crypto/sha1_ni_asm.S | 4 +- arch/x86/crypto/sha1_ssse3_asm.S | 4 +- arch/x86/crypto/sha256-avx-asm.S | 4 +- arch/x86/crypto/sha256-avx2-asm.S | 4 +- arch/x86/crypto/sha256-ssse3-asm.S | 4 +- arch/x86/crypto/sha256_ni_asm.S | 4 +- arch/x86/crypto/sha512-avx-asm.S | 4 +- arch/x86/crypto/sha512-avx2-asm.S | 4 +- arch/x86/crypto/sha512-ssse3-asm.S | 4 +- arch/x86/crypto/twofish-avx-x86_64-asm_64.S | 24 +++++------ arch/x86/crypto/twofish-x86_64-asm_64-3way.S | 8 ++-- arch/x86/crypto/twofish-x86_64-asm_64.S | 8 ++-- arch/x86/entry/entry_64.S | 10 ++--- arch/x86/entry/entry_64_compat.S | 4 +- arch/x86/kernel/acpi/wakeup_64.S | 8 ++-- arch/x86/kernel/ftrace_64.S | 20 +++++----- arch/x86/kernel/irqflags.S | 8 ++-- arch/x86/kvm/vmx/vmenter.S | 12 +++--- arch/x86/lib/checksum_32.S | 8 ++-- arch/x86/lib/clear_page_64.S | 12 +++--- arch/x86/lib/cmpxchg16b_emu.S | 4 +- arch/x86/lib/cmpxchg8b_emu.S | 4 +- arch/x86/lib/copy_page_64.S | 4 +- arch/x86/lib/copy_user_64.S | 16 ++++---- arch/x86/lib/csum-copy_64.S | 4 +- arch/x86/lib/getuser.S | 16 ++++---- arch/x86/lib/hweight.S | 8 ++-- arch/x86/lib/iomap_copy_64.S | 4 +- arch/x86/lib/memcpy_64.S | 4 +- arch/x86/lib/memmove_64.S | 4 +- arch/x86/lib/memset_64.S | 4 +- arch/x86/lib/msr-reg.S | 8 ++-- arch/x86/lib/putuser.S | 16 ++++---- arch/x86/lib/retpoline.S | 4 +- arch/x86/mm/mem_encrypt_boot.S | 8 ++-- arch/x86/platform/efi/efi_stub_64.S | 4 +- arch/x86/platform/efi/efi_thunk_64.S | 4 +- arch/x86/power/hibernate_asm_64.S | 8 ++-- arch/x86/xen/xen-asm.S | 28 ++++++------- arch/x86/xen/xen-asm_64.S | 16 ++++---- include/linux/linkage.h | 4 ++ 70 files changed, 379 insertions(+), 375 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/boot/compressed/efi_thunk_64.S b/arch/x86/boot/compressed/efi_thunk_64.S index 31312070db22..593913692d16 100644 --- a/arch/x86/boot/compressed/efi_thunk_64.S +++ b/arch/x86/boot/compressed/efi_thunk_64.S @@ -23,7 +23,7 @@ .code64 .text -ENTRY(efi64_thunk) +SYM_FUNC_START(efi64_thunk) push %rbp push %rbx @@ -97,7 +97,7 @@ ENTRY(efi64_thunk) pop %rbx pop %rbp ret -ENDPROC(efi64_thunk) +SYM_FUNC_END(efi64_thunk) SYM_FUNC_START_LOCAL(efi_exit32) movq func_rt_ptr(%rip), %rax diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 55800467ce5c..58a512e33d8d 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -45,7 +45,7 @@ __HEAD .code32 -ENTRY(startup_32) +SYM_FUNC_START(startup_32) /* * 32bit entry is 0 and it is ABI so immutable! * If we come here directly from a bootloader, @@ -222,11 +222,11 @@ ENTRY(startup_32) /* Jump from 32bit compatibility mode into 64bit mode. */ lret -ENDPROC(startup_32) +SYM_FUNC_END(startup_32) #ifdef CONFIG_EFI_MIXED .org 0x190 -ENTRY(efi32_stub_entry) +SYM_FUNC_START(efi32_stub_entry) add $0x4, %esp /* Discard return address */ popl %ecx popl %edx @@ -245,7 +245,7 @@ ENTRY(efi32_stub_entry) movl %eax, efi_config(%ebp) jmp startup_32 -ENDPROC(efi32_stub_entry) +SYM_FUNC_END(efi32_stub_entry) #endif .code64 @@ -447,7 +447,7 @@ SYM_CODE_END(startup_64) #ifdef CONFIG_EFI_STUB /* The entry point for the PE/COFF executable is efi_pe_entry. */ -ENTRY(efi_pe_entry) +SYM_FUNC_START(efi_pe_entry) movq %rcx, efi64_config(%rip) /* Handle */ movq %rdx, efi64_config+8(%rip) /* EFI System table pointer */ @@ -496,10 +496,10 @@ fail: movl BP_code32_start(%esi), %eax leaq startup_64(%rax), %rax jmp *%rax -ENDPROC(efi_pe_entry) +SYM_FUNC_END(efi_pe_entry) .org 0x390 -ENTRY(efi64_stub_entry) +SYM_FUNC_START(efi64_stub_entry) movq %rdi, efi64_config(%rip) /* Handle */ movq %rsi, efi64_config+8(%rip) /* EFI System table pointer */ @@ -508,7 +508,7 @@ ENTRY(efi64_stub_entry) movq %rdx, %rsi jmp handover_entry -ENDPROC(efi64_stub_entry) +SYM_FUNC_END(efi64_stub_entry) #endif .text diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S index 28d703cad310..dd07e7b41b11 100644 --- a/arch/x86/boot/compressed/mem_encrypt.S +++ b/arch/x86/boot/compressed/mem_encrypt.S @@ -15,7 +15,7 @@ .text .code32 -ENTRY(get_sev_encryption_bit) +SYM_FUNC_START(get_sev_encryption_bit) xor %eax, %eax #ifdef CONFIG_AMD_MEM_ENCRYPT @@ -65,10 +65,10 @@ ENTRY(get_sev_encryption_bit) #endif /* CONFIG_AMD_MEM_ENCRYPT */ ret -ENDPROC(get_sev_encryption_bit) +SYM_FUNC_END(get_sev_encryption_bit) .code64 -ENTRY(set_sev_encryption_mask) +SYM_FUNC_START(set_sev_encryption_mask) #ifdef CONFIG_AMD_MEM_ENCRYPT push %rbp push %rdx @@ -90,7 +90,7 @@ ENTRY(set_sev_encryption_mask) xor %rax, %rax ret -ENDPROC(set_sev_encryption_mask) +SYM_FUNC_END(set_sev_encryption_mask) .data diff --git a/arch/x86/crypto/aegis128-aesni-asm.S b/arch/x86/crypto/aegis128-aesni-asm.S index b7026fdef4ff..51d46d93efbc 100644 --- a/arch/x86/crypto/aegis128-aesni-asm.S +++ b/arch/x86/crypto/aegis128-aesni-asm.S @@ -186,7 +186,7 @@ SYM_FUNC_END(__store_partial) /* * void crypto_aegis128_aesni_init(void *state, const void *key, const void *iv); */ -ENTRY(crypto_aegis128_aesni_init) +SYM_FUNC_START(crypto_aegis128_aesni_init) FRAME_BEGIN /* load IV: */ @@ -226,13 +226,13 @@ ENTRY(crypto_aegis128_aesni_init) FRAME_END ret -ENDPROC(crypto_aegis128_aesni_init) +SYM_FUNC_END(crypto_aegis128_aesni_init) /* * void crypto_aegis128_aesni_ad(void *state, unsigned int length, * const void *data); */ -ENTRY(crypto_aegis128_aesni_ad) +SYM_FUNC_START(crypto_aegis128_aesni_ad) FRAME_BEGIN cmp $0x10, LEN @@ -378,7 +378,7 @@ ENTRY(crypto_aegis128_aesni_ad) .Lad_out: FRAME_END ret -ENDPROC(crypto_aegis128_aesni_ad) +SYM_FUNC_END(crypto_aegis128_aesni_ad) .macro encrypt_block a s0 s1 s2 s3 s4 i movdq\a (\i * 0x10)(SRC), MSG @@ -402,7 +402,7 @@ ENDPROC(crypto_aegis128_aesni_ad) * void crypto_aegis128_aesni_enc(void *state, unsigned int length, * const void *src, void *dst); */ -ENTRY(crypto_aegis128_aesni_enc) +SYM_FUNC_START(crypto_aegis128_aesni_enc) FRAME_BEGIN cmp $0x10, LEN @@ -493,13 +493,13 @@ ENTRY(crypto_aegis128_aesni_enc) .Lenc_out: FRAME_END ret -ENDPROC(crypto_aegis128_aesni_enc) +SYM_FUNC_END(crypto_aegis128_aesni_enc) /* * void crypto_aegis128_aesni_enc_tail(void *state, unsigned int length, * const void *src, void *dst); */ -ENTRY(crypto_aegis128_aesni_enc_tail) +SYM_FUNC_START(crypto_aegis128_aesni_enc_tail) FRAME_BEGIN /* load the state: */ @@ -533,7 +533,7 @@ ENTRY(crypto_aegis128_aesni_enc_tail) FRAME_END ret -ENDPROC(crypto_aegis128_aesni_enc_tail) +SYM_FUNC_END(crypto_aegis128_aesni_enc_tail) .macro decrypt_block a s0 s1 s2 s3 s4 i movdq\a (\i * 0x10)(SRC), MSG @@ -556,7 +556,7 @@ ENDPROC(crypto_aegis128_aesni_enc_tail) * void crypto_aegis128_aesni_dec(void *state, unsigned int length, * const void *src, void *dst); */ -ENTRY(crypto_aegis128_aesni_dec) +SYM_FUNC_START(crypto_aegis128_aesni_dec) FRAME_BEGIN cmp $0x10, LEN @@ -647,13 +647,13 @@ ENTRY(crypto_aegis128_aesni_dec) .Ldec_out: FRAME_END ret -ENDPROC(crypto_aegis128_aesni_dec) +SYM_FUNC_END(crypto_aegis128_aesni_dec) /* * void crypto_aegis128_aesni_dec_tail(void *state, unsigned int length, * const void *src, void *dst); */ -ENTRY(crypto_aegis128_aesni_dec_tail) +SYM_FUNC_START(crypto_aegis128_aesni_dec_tail) FRAME_BEGIN /* load the state: */ @@ -697,13 +697,13 @@ ENTRY(crypto_aegis128_aesni_dec_tail) FRAME_END ret -ENDPROC(crypto_aegis128_aesni_dec_tail) +SYM_FUNC_END(crypto_aegis128_aesni_dec_tail) /* * void crypto_aegis128_aesni_final(void *state, void *tag_xor, * u64 assoclen, u64 cryptlen); */ -ENTRY(crypto_aegis128_aesni_final) +SYM_FUNC_START(crypto_aegis128_aesni_final) FRAME_BEGIN /* load the state: */ @@ -744,4 +744,4 @@ ENTRY(crypto_aegis128_aesni_final) FRAME_END ret -ENDPROC(crypto_aegis128_aesni_final) +SYM_FUNC_END(crypto_aegis128_aesni_final) diff --git a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S index 5f6a5af9c489..ec437db1fa54 100644 --- a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S +++ b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S @@ -544,11 +544,11 @@ ddq_add_8: * aes_ctr_enc_128_avx_by8(void *in, void *iv, void *keys, void *out, * unsigned int num_bytes) */ -ENTRY(aes_ctr_enc_128_avx_by8) +SYM_FUNC_START(aes_ctr_enc_128_avx_by8) /* call the aes main loop */ do_aes_ctrmain KEY_128 -ENDPROC(aes_ctr_enc_128_avx_by8) +SYM_FUNC_END(aes_ctr_enc_128_avx_by8) /* * routine to do AES192 CTR enc/decrypt "by8" @@ -557,11 +557,11 @@ ENDPROC(aes_ctr_enc_128_avx_by8) * aes_ctr_enc_192_avx_by8(void *in, void *iv, void *keys, void *out, * unsigned int num_bytes) */ -ENTRY(aes_ctr_enc_192_avx_by8) +SYM_FUNC_START(aes_ctr_enc_192_avx_by8) /* call the aes main loop */ do_aes_ctrmain KEY_192 -ENDPROC(aes_ctr_enc_192_avx_by8) +SYM_FUNC_END(aes_ctr_enc_192_avx_by8) /* * routine to do AES256 CTR enc/decrypt "by8" @@ -570,8 +570,8 @@ ENDPROC(aes_ctr_enc_192_avx_by8) * aes_ctr_enc_256_avx_by8(void *in, void *iv, void *keys, void *out, * unsigned int num_bytes) */ -ENTRY(aes_ctr_enc_256_avx_by8) +SYM_FUNC_START(aes_ctr_enc_256_avx_by8) /* call the aes main loop */ do_aes_ctrmain KEY_256 -ENDPROC(aes_ctr_enc_256_avx_by8) +SYM_FUNC_END(aes_ctr_enc_256_avx_by8) diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index 9d8d5f2296e1..d28503f99f58 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -1592,7 +1592,7 @@ _esb_loop_\@: * poly = x^128 + x^127 + x^126 + x^121 + 1 * *****************************************************************************/ -ENTRY(aesni_gcm_dec) +SYM_FUNC_START(aesni_gcm_dec) FUNC_SAVE GCM_INIT %arg6, arg7, arg8, arg9 @@ -1600,7 +1600,7 @@ ENTRY(aesni_gcm_dec) GCM_COMPLETE arg10, arg11 FUNC_RESTORE ret -ENDPROC(aesni_gcm_dec) +SYM_FUNC_END(aesni_gcm_dec) /***************************************************************************** @@ -1680,7 +1680,7 @@ ENDPROC(aesni_gcm_dec) * * poly = x^128 + x^127 + x^126 + x^121 + 1 ***************************************************************************/ -ENTRY(aesni_gcm_enc) +SYM_FUNC_START(aesni_gcm_enc) FUNC_SAVE GCM_INIT %arg6, arg7, arg8, arg9 @@ -1689,7 +1689,7 @@ ENTRY(aesni_gcm_enc) GCM_COMPLETE arg10, arg11 FUNC_RESTORE ret -ENDPROC(aesni_gcm_enc) +SYM_FUNC_END(aesni_gcm_enc) /***************************************************************************** * void aesni_gcm_init(void *aes_ctx, // AES Key schedule. Starts on a 16 byte boundary. @@ -1702,12 +1702,12 @@ ENDPROC(aesni_gcm_enc) * const u8 *aad, // Additional Authentication Data (AAD) * u64 aad_len) // Length of AAD in bytes. */ -ENTRY(aesni_gcm_init) +SYM_FUNC_START(aesni_gcm_init) FUNC_SAVE GCM_INIT %arg3, %arg4,%arg5, %arg6 FUNC_RESTORE ret -ENDPROC(aesni_gcm_init) +SYM_FUNC_END(aesni_gcm_init) /***************************************************************************** * void aesni_gcm_enc_update(void *aes_ctx, // AES Key schedule. Starts on a 16 byte boundary. @@ -1717,12 +1717,12 @@ ENDPROC(aesni_gcm_init) * const u8 *in, // Plaintext input * u64 plaintext_len, // Length of data in bytes for encryption. */ -ENTRY(aesni_gcm_enc_update) +SYM_FUNC_START(aesni_gcm_enc_update) FUNC_SAVE GCM_ENC_DEC enc FUNC_RESTORE ret -ENDPROC(aesni_gcm_enc_update) +SYM_FUNC_END(aesni_gcm_enc_update) /***************************************************************************** * void aesni_gcm_dec_update(void *aes_ctx, // AES Key schedule. Starts on a 16 byte boundary. @@ -1732,12 +1732,12 @@ ENDPROC(aesni_gcm_enc_update) * const u8 *in, // Plaintext input * u64 plaintext_len, // Length of data in bytes for encryption. */ -ENTRY(aesni_gcm_dec_update) +SYM_FUNC_START(aesni_gcm_dec_update) FUNC_SAVE GCM_ENC_DEC dec FUNC_RESTORE ret -ENDPROC(aesni_gcm_dec_update) +SYM_FUNC_END(aesni_gcm_dec_update) /***************************************************************************** * void aesni_gcm_finalize(void *aes_ctx, // AES Key schedule. Starts on a 16 byte boundary. @@ -1747,12 +1747,12 @@ ENDPROC(aesni_gcm_dec_update) * u64 auth_tag_len); // Authenticated Tag Length in bytes. Valid values are 16 (most likely), * // 12 or 8. */ -ENTRY(aesni_gcm_finalize) +SYM_FUNC_START(aesni_gcm_finalize) FUNC_SAVE GCM_COMPLETE %arg3 %arg4 FUNC_RESTORE ret -ENDPROC(aesni_gcm_finalize) +SYM_FUNC_END(aesni_gcm_finalize) #endif @@ -1830,7 +1830,7 @@ SYM_FUNC_END(_key_expansion_256b) * int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key, * unsigned int key_len) */ -ENTRY(aesni_set_key) +SYM_FUNC_START(aesni_set_key) FRAME_BEGIN #ifndef __x86_64__ pushl KEYP @@ -1939,12 +1939,12 @@ ENTRY(aesni_set_key) #endif FRAME_END ret -ENDPROC(aesni_set_key) +SYM_FUNC_END(aesni_set_key) /* * void aesni_enc(struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src) */ -ENTRY(aesni_enc) +SYM_FUNC_START(aesni_enc) FRAME_BEGIN #ifndef __x86_64__ pushl KEYP @@ -1963,7 +1963,7 @@ ENTRY(aesni_enc) #endif FRAME_END ret -ENDPROC(aesni_enc) +SYM_FUNC_END(aesni_enc) /* * _aesni_enc1: internal ABI @@ -2133,7 +2133,7 @@ SYM_FUNC_END(_aesni_enc4) /* * void aesni_dec (struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src) */ -ENTRY(aesni_dec) +SYM_FUNC_START(aesni_dec) FRAME_BEGIN #ifndef __x86_64__ pushl KEYP @@ -2153,7 +2153,7 @@ ENTRY(aesni_dec) #endif FRAME_END ret -ENDPROC(aesni_dec) +SYM_FUNC_END(aesni_dec) /* * _aesni_dec1: internal ABI @@ -2324,7 +2324,7 @@ SYM_FUNC_END(_aesni_dec4) * void aesni_ecb_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, * size_t len) */ -ENTRY(aesni_ecb_enc) +SYM_FUNC_START(aesni_ecb_enc) FRAME_BEGIN #ifndef __x86_64__ pushl LEN @@ -2378,13 +2378,13 @@ ENTRY(aesni_ecb_enc) #endif FRAME_END ret -ENDPROC(aesni_ecb_enc) +SYM_FUNC_END(aesni_ecb_enc) /* * void aesni_ecb_dec(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, * size_t len); */ -ENTRY(aesni_ecb_dec) +SYM_FUNC_START(aesni_ecb_dec) FRAME_BEGIN #ifndef __x86_64__ pushl LEN @@ -2439,13 +2439,13 @@ ENTRY(aesni_ecb_dec) #endif FRAME_END ret -ENDPROC(aesni_ecb_dec) +SYM_FUNC_END(aesni_ecb_dec) /* * void aesni_cbc_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, * size_t len, u8 *iv) */ -ENTRY(aesni_cbc_enc) +SYM_FUNC_START(aesni_cbc_enc) FRAME_BEGIN #ifndef __x86_64__ pushl IVP @@ -2483,13 +2483,13 @@ ENTRY(aesni_cbc_enc) #endif FRAME_END ret -ENDPROC(aesni_cbc_enc) +SYM_FUNC_END(aesni_cbc_enc) /* * void aesni_cbc_dec(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, * size_t len, u8 *iv) */ -ENTRY(aesni_cbc_dec) +SYM_FUNC_START(aesni_cbc_dec) FRAME_BEGIN #ifndef __x86_64__ pushl IVP @@ -2576,7 +2576,7 @@ ENTRY(aesni_cbc_dec) #endif FRAME_END ret -ENDPROC(aesni_cbc_dec) +SYM_FUNC_END(aesni_cbc_dec) #ifdef __x86_64__ .pushsection .rodata @@ -2638,7 +2638,7 @@ SYM_FUNC_END(_aesni_inc) * void aesni_ctr_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, * size_t len, u8 *iv) */ -ENTRY(aesni_ctr_enc) +SYM_FUNC_START(aesni_ctr_enc) FRAME_BEGIN cmp $16, LEN jb .Lctr_enc_just_ret @@ -2695,7 +2695,7 @@ ENTRY(aesni_ctr_enc) .Lctr_enc_just_ret: FRAME_END ret -ENDPROC(aesni_ctr_enc) +SYM_FUNC_END(aesni_ctr_enc) /* * _aesni_gf128mul_x_ble: internal ABI @@ -2719,7 +2719,7 @@ ENDPROC(aesni_ctr_enc) * void aesni_xts_crypt8(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, * bool enc, u8 *iv) */ -ENTRY(aesni_xts_crypt8) +SYM_FUNC_START(aesni_xts_crypt8) FRAME_BEGIN cmpb $0, %cl movl $0, %ecx @@ -2823,6 +2823,6 @@ ENTRY(aesni_xts_crypt8) FRAME_END ret -ENDPROC(aesni_xts_crypt8) +SYM_FUNC_END(aesni_xts_crypt8) #endif diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S index 91c039ab5699..bfa1c0b3e5b4 100644 --- a/arch/x86/crypto/aesni-intel_avx-x86_64.S +++ b/arch/x86/crypto/aesni-intel_avx-x86_64.S @@ -1775,12 +1775,12 @@ _initial_blocks_done\@: # const u8 *aad, /* Additional Authentication Data (AAD)*/ # u64 aad_len) /* Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 Bytes */ ############################################################# -ENTRY(aesni_gcm_init_avx_gen2) +SYM_FUNC_START(aesni_gcm_init_avx_gen2) FUNC_SAVE INIT GHASH_MUL_AVX, PRECOMPUTE_AVX FUNC_RESTORE ret -ENDPROC(aesni_gcm_init_avx_gen2) +SYM_FUNC_END(aesni_gcm_init_avx_gen2) ############################################################################### #void aesni_gcm_enc_update_avx_gen2( @@ -1790,7 +1790,7 @@ ENDPROC(aesni_gcm_init_avx_gen2) # const u8 *in, /* Plaintext input */ # u64 plaintext_len) /* Length of data in Bytes for encryption. */ ############################################################################### -ENTRY(aesni_gcm_enc_update_avx_gen2) +SYM_FUNC_START(aesni_gcm_enc_update_avx_gen2) FUNC_SAVE mov keysize, %eax cmp $32, %eax @@ -1809,7 +1809,7 @@ key_256_enc_update: GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, ENC, 13 FUNC_RESTORE ret -ENDPROC(aesni_gcm_enc_update_avx_gen2) +SYM_FUNC_END(aesni_gcm_enc_update_avx_gen2) ############################################################################### #void aesni_gcm_dec_update_avx_gen2( @@ -1819,7 +1819,7 @@ ENDPROC(aesni_gcm_enc_update_avx_gen2) # const u8 *in, /* Ciphertext input */ # u64 plaintext_len) /* Length of data in Bytes for encryption. */ ############################################################################### -ENTRY(aesni_gcm_dec_update_avx_gen2) +SYM_FUNC_START(aesni_gcm_dec_update_avx_gen2) FUNC_SAVE mov keysize,%eax cmp $32, %eax @@ -1838,7 +1838,7 @@ key_256_dec_update: GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, DEC, 13 FUNC_RESTORE ret -ENDPROC(aesni_gcm_dec_update_avx_gen2) +SYM_FUNC_END(aesni_gcm_dec_update_avx_gen2) ############################################################################### #void aesni_gcm_finalize_avx_gen2( @@ -1848,7 +1848,7 @@ ENDPROC(aesni_gcm_dec_update_avx_gen2) # u64 auth_tag_len)# /* Authenticated Tag Length in bytes. # Valid values are 16 (most likely), 12 or 8. */ ############################################################################### -ENTRY(aesni_gcm_finalize_avx_gen2) +SYM_FUNC_START(aesni_gcm_finalize_avx_gen2) FUNC_SAVE mov keysize,%eax cmp $32, %eax @@ -1867,7 +1867,7 @@ key_256_finalize: GCM_COMPLETE GHASH_MUL_AVX, 13, arg3, arg4 FUNC_RESTORE ret -ENDPROC(aesni_gcm_finalize_avx_gen2) +SYM_FUNC_END(aesni_gcm_finalize_avx_gen2) #endif /* CONFIG_AS_AVX */ @@ -2746,12 +2746,12 @@ _initial_blocks_done\@: # const u8 *aad, /* Additional Authentication Data (AAD)*/ # u64 aad_len) /* Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 Bytes */ ############################################################# -ENTRY(aesni_gcm_init_avx_gen4) +SYM_FUNC_START(aesni_gcm_init_avx_gen4) FUNC_SAVE INIT GHASH_MUL_AVX2, PRECOMPUTE_AVX2 FUNC_RESTORE ret -ENDPROC(aesni_gcm_init_avx_gen4) +SYM_FUNC_END(aesni_gcm_init_avx_gen4) ############################################################################### #void aesni_gcm_enc_avx_gen4( @@ -2761,7 +2761,7 @@ ENDPROC(aesni_gcm_init_avx_gen4) # const u8 *in, /* Plaintext input */ # u64 plaintext_len) /* Length of data in Bytes for encryption. */ ############################################################################### -ENTRY(aesni_gcm_enc_update_avx_gen4) +SYM_FUNC_START(aesni_gcm_enc_update_avx_gen4) FUNC_SAVE mov keysize,%eax cmp $32, %eax @@ -2780,7 +2780,7 @@ key_256_enc_update4: GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, ENC, 13 FUNC_RESTORE ret -ENDPROC(aesni_gcm_enc_update_avx_gen4) +SYM_FUNC_END(aesni_gcm_enc_update_avx_gen4) ############################################################################### #void aesni_gcm_dec_update_avx_gen4( @@ -2790,7 +2790,7 @@ ENDPROC(aesni_gcm_enc_update_avx_gen4) # const u8 *in, /* Ciphertext input */ # u64 plaintext_len) /* Length of data in Bytes for encryption. */ ############################################################################### -ENTRY(aesni_gcm_dec_update_avx_gen4) +SYM_FUNC_START(aesni_gcm_dec_update_avx_gen4) FUNC_SAVE mov keysize,%eax cmp $32, %eax @@ -2809,7 +2809,7 @@ key_256_dec_update4: GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, DEC, 13 FUNC_RESTORE ret -ENDPROC(aesni_gcm_dec_update_avx_gen4) +SYM_FUNC_END(aesni_gcm_dec_update_avx_gen4) ############################################################################### #void aesni_gcm_finalize_avx_gen4( @@ -2819,7 +2819,7 @@ ENDPROC(aesni_gcm_dec_update_avx_gen4) # u64 auth_tag_len)# /* Authenticated Tag Length in bytes. # Valid values are 16 (most likely), 12 or 8. */ ############################################################################### -ENTRY(aesni_gcm_finalize_avx_gen4) +SYM_FUNC_START(aesni_gcm_finalize_avx_gen4) FUNC_SAVE mov keysize,%eax cmp $32, %eax @@ -2838,6 +2838,6 @@ key_256_finalize4: GCM_COMPLETE GHASH_MUL_AVX2, 13, arg3, arg4 FUNC_RESTORE ret -ENDPROC(aesni_gcm_finalize_avx_gen4) +SYM_FUNC_END(aesni_gcm_finalize_avx_gen4) #endif /* CONFIG_AS_AVX2 */ diff --git a/arch/x86/crypto/blowfish-x86_64-asm_64.S b/arch/x86/crypto/blowfish-x86_64-asm_64.S index 330db7a48af8..4222ac6d6584 100644 --- a/arch/x86/crypto/blowfish-x86_64-asm_64.S +++ b/arch/x86/crypto/blowfish-x86_64-asm_64.S @@ -103,7 +103,7 @@ bswapq RX0; \ xorq RX0, (RIO); -ENTRY(__blowfish_enc_blk) +SYM_FUNC_START(__blowfish_enc_blk) /* input: * %rdi: ctx * %rsi: dst @@ -139,9 +139,9 @@ ENTRY(__blowfish_enc_blk) .L__enc_xor: xor_block(); ret; -ENDPROC(__blowfish_enc_blk) +SYM_FUNC_END(__blowfish_enc_blk) -ENTRY(blowfish_dec_blk) +SYM_FUNC_START(blowfish_dec_blk) /* input: * %rdi: ctx * %rsi: dst @@ -171,7 +171,7 @@ ENTRY(blowfish_dec_blk) movq %r11, %r12; ret; -ENDPROC(blowfish_dec_blk) +SYM_FUNC_END(blowfish_dec_blk) /********************************************************************** 4-way blowfish, four blocks parallel @@ -283,7 +283,7 @@ ENDPROC(blowfish_dec_blk) bswapq RX3; \ xorq RX3, 24(RIO); -ENTRY(__blowfish_enc_blk_4way) +SYM_FUNC_START(__blowfish_enc_blk_4way) /* input: * %rdi: ctx * %rsi: dst @@ -330,9 +330,9 @@ ENTRY(__blowfish_enc_blk_4way) popq %rbx; popq %r12; ret; -ENDPROC(__blowfish_enc_blk_4way) +SYM_FUNC_END(__blowfish_enc_blk_4way) -ENTRY(blowfish_dec_blk_4way) +SYM_FUNC_START(blowfish_dec_blk_4way) /* input: * %rdi: ctx * %rsi: dst @@ -365,4 +365,4 @@ ENTRY(blowfish_dec_blk_4way) popq %r12; ret; -ENDPROC(blowfish_dec_blk_4way) +SYM_FUNC_END(blowfish_dec_blk_4way) diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S index f4408ca55fdb..d01ddd73de65 100644 --- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S +++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S @@ -893,7 +893,7 @@ SYM_FUNC_START_LOCAL(__camellia_dec_blk16) jmp .Ldec_max24; SYM_FUNC_END(__camellia_dec_blk16) -ENTRY(camellia_ecb_enc_16way) +SYM_FUNC_START(camellia_ecb_enc_16way) /* input: * %rdi: ctx, CTX * %rsi: dst (16 blocks) @@ -916,9 +916,9 @@ ENTRY(camellia_ecb_enc_16way) FRAME_END ret; -ENDPROC(camellia_ecb_enc_16way) +SYM_FUNC_END(camellia_ecb_enc_16way) -ENTRY(camellia_ecb_dec_16way) +SYM_FUNC_START(camellia_ecb_dec_16way) /* input: * %rdi: ctx, CTX * %rsi: dst (16 blocks) @@ -946,9 +946,9 @@ ENTRY(camellia_ecb_dec_16way) FRAME_END ret; -ENDPROC(camellia_ecb_dec_16way) +SYM_FUNC_END(camellia_ecb_dec_16way) -ENTRY(camellia_cbc_dec_16way) +SYM_FUNC_START(camellia_cbc_dec_16way) /* input: * %rdi: ctx, CTX * %rsi: dst (16 blocks) @@ -997,7 +997,7 @@ ENTRY(camellia_cbc_dec_16way) FRAME_END ret; -ENDPROC(camellia_cbc_dec_16way) +SYM_FUNC_END(camellia_cbc_dec_16way) #define inc_le128(x, minus_one, tmp) \ vpcmpeqq minus_one, x, tmp; \ @@ -1005,7 +1005,7 @@ ENDPROC(camellia_cbc_dec_16way) vpslldq $8, tmp, tmp; \ vpsubq tmp, x, x; -ENTRY(camellia_ctr_16way) +SYM_FUNC_START(camellia_ctr_16way) /* input: * %rdi: ctx, CTX * %rsi: dst (16 blocks) @@ -1110,7 +1110,7 @@ ENTRY(camellia_ctr_16way) FRAME_END ret; -ENDPROC(camellia_ctr_16way) +SYM_FUNC_END(camellia_ctr_16way) #define gf128mul_x_ble(iv, mask, tmp) \ vpsrad $31, iv, tmp; \ @@ -1256,7 +1256,7 @@ SYM_FUNC_START_LOCAL(camellia_xts_crypt_16way) ret; SYM_FUNC_END(camellia_xts_crypt_16way) -ENTRY(camellia_xts_enc_16way) +SYM_FUNC_START(camellia_xts_enc_16way) /* input: * %rdi: ctx, CTX * %rsi: dst (16 blocks) @@ -1268,9 +1268,9 @@ ENTRY(camellia_xts_enc_16way) leaq __camellia_enc_blk16, %r9; jmp camellia_xts_crypt_16way; -ENDPROC(camellia_xts_enc_16way) +SYM_FUNC_END(camellia_xts_enc_16way) -ENTRY(camellia_xts_dec_16way) +SYM_FUNC_START(camellia_xts_dec_16way) /* input: * %rdi: ctx, CTX * %rsi: dst (16 blocks) @@ -1286,4 +1286,4 @@ ENTRY(camellia_xts_dec_16way) leaq __camellia_dec_blk16, %r9; jmp camellia_xts_crypt_16way; -ENDPROC(camellia_xts_dec_16way) +SYM_FUNC_END(camellia_xts_dec_16way) diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S index 72ae3edd0997..563ef6e83cdd 100644 --- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S +++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S @@ -931,7 +931,7 @@ SYM_FUNC_START_LOCAL(__camellia_dec_blk32) jmp .Ldec_max24; SYM_FUNC_END(__camellia_dec_blk32) -ENTRY(camellia_ecb_enc_32way) +SYM_FUNC_START(camellia_ecb_enc_32way) /* input: * %rdi: ctx, CTX * %rsi: dst (32 blocks) @@ -958,9 +958,9 @@ ENTRY(camellia_ecb_enc_32way) FRAME_END ret; -ENDPROC(camellia_ecb_enc_32way) +SYM_FUNC_END(camellia_ecb_enc_32way) -ENTRY(camellia_ecb_dec_32way) +SYM_FUNC_START(camellia_ecb_dec_32way) /* input: * %rdi: ctx, CTX * %rsi: dst (32 blocks) @@ -992,9 +992,9 @@ ENTRY(camellia_ecb_dec_32way) FRAME_END ret; -ENDPROC(camellia_ecb_dec_32way) +SYM_FUNC_END(camellia_ecb_dec_32way) -ENTRY(camellia_cbc_dec_32way) +SYM_FUNC_START(camellia_cbc_dec_32way) /* input: * %rdi: ctx, CTX * %rsi: dst (32 blocks) @@ -1060,7 +1060,7 @@ ENTRY(camellia_cbc_dec_32way) FRAME_END ret; -ENDPROC(camellia_cbc_dec_32way) +SYM_FUNC_END(camellia_cbc_dec_32way) #define inc_le128(x, minus_one, tmp) \ vpcmpeqq minus_one, x, tmp; \ @@ -1076,7 +1076,7 @@ ENDPROC(camellia_cbc_dec_32way) vpslldq $8, tmp1, tmp1; \ vpsubq tmp1, x, x; -ENTRY(camellia_ctr_32way) +SYM_FUNC_START(camellia_ctr_32way) /* input: * %rdi: ctx, CTX * %rsi: dst (32 blocks) @@ -1200,7 +1200,7 @@ ENTRY(camellia_ctr_32way) FRAME_END ret; -ENDPROC(camellia_ctr_32way) +SYM_FUNC_END(camellia_ctr_32way) #define gf128mul_x_ble(iv, mask, tmp) \ vpsrad $31, iv, tmp; \ @@ -1369,7 +1369,7 @@ SYM_FUNC_START_LOCAL(camellia_xts_crypt_32way) ret; SYM_FUNC_END(camellia_xts_crypt_32way) -ENTRY(camellia_xts_enc_32way) +SYM_FUNC_START(camellia_xts_enc_32way) /* input: * %rdi: ctx, CTX * %rsi: dst (32 blocks) @@ -1382,9 +1382,9 @@ ENTRY(camellia_xts_enc_32way) leaq __camellia_enc_blk32, %r9; jmp camellia_xts_crypt_32way; -ENDPROC(camellia_xts_enc_32way) +SYM_FUNC_END(camellia_xts_enc_32way) -ENTRY(camellia_xts_dec_32way) +SYM_FUNC_START(camellia_xts_dec_32way) /* input: * %rdi: ctx, CTX * %rsi: dst (32 blocks) @@ -1400,4 +1400,4 @@ ENTRY(camellia_xts_dec_32way) leaq __camellia_dec_blk32, %r9; jmp camellia_xts_crypt_32way; -ENDPROC(camellia_xts_dec_32way) +SYM_FUNC_END(camellia_xts_dec_32way) diff --git a/arch/x86/crypto/camellia-x86_64-asm_64.S b/arch/x86/crypto/camellia-x86_64-asm_64.S index 23528bc18fc6..1372e6408850 100644 --- a/arch/x86/crypto/camellia-x86_64-asm_64.S +++ b/arch/x86/crypto/camellia-x86_64-asm_64.S @@ -175,7 +175,7 @@ bswapq RAB0; \ movq RAB0, 4*2(RIO); -ENTRY(__camellia_enc_blk) +SYM_FUNC_START(__camellia_enc_blk) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -220,9 +220,9 @@ ENTRY(__camellia_enc_blk) movq RR12, %r12; ret; -ENDPROC(__camellia_enc_blk) +SYM_FUNC_END(__camellia_enc_blk) -ENTRY(camellia_dec_blk) +SYM_FUNC_START(camellia_dec_blk) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -258,7 +258,7 @@ ENTRY(camellia_dec_blk) movq RR12, %r12; ret; -ENDPROC(camellia_dec_blk) +SYM_FUNC_END(camellia_dec_blk) /********************************************************************** 2-way camellia @@ -409,7 +409,7 @@ ENDPROC(camellia_dec_blk) bswapq RAB1; \ movq RAB1, 12*2(RIO); -ENTRY(__camellia_enc_blk_2way) +SYM_FUNC_START(__camellia_enc_blk_2way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -456,9 +456,9 @@ ENTRY(__camellia_enc_blk_2way) movq RR12, %r12; popq %rbx; ret; -ENDPROC(__camellia_enc_blk_2way) +SYM_FUNC_END(__camellia_enc_blk_2way) -ENTRY(camellia_dec_blk_2way) +SYM_FUNC_START(camellia_dec_blk_2way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -496,4 +496,4 @@ ENTRY(camellia_dec_blk_2way) movq RR12, %r12; movq RXOR, %rbx; ret; -ENDPROC(camellia_dec_blk_2way) +SYM_FUNC_END(camellia_dec_blk_2way) diff --git a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S index ef86c6a966de..8a6181b08b59 100644 --- a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S @@ -359,7 +359,7 @@ SYM_FUNC_START_LOCAL(__cast5_dec_blk16) jmp .L__dec_tail; SYM_FUNC_END(__cast5_dec_blk16) -ENTRY(cast5_ecb_enc_16way) +SYM_FUNC_START(cast5_ecb_enc_16way) /* input: * %rdi: ctx * %rsi: dst @@ -394,9 +394,9 @@ ENTRY(cast5_ecb_enc_16way) popq %r15; FRAME_END ret; -ENDPROC(cast5_ecb_enc_16way) +SYM_FUNC_END(cast5_ecb_enc_16way) -ENTRY(cast5_ecb_dec_16way) +SYM_FUNC_START(cast5_ecb_dec_16way) /* input: * %rdi: ctx * %rsi: dst @@ -432,9 +432,9 @@ ENTRY(cast5_ecb_dec_16way) popq %r15; FRAME_END ret; -ENDPROC(cast5_ecb_dec_16way) +SYM_FUNC_END(cast5_ecb_dec_16way) -ENTRY(cast5_cbc_dec_16way) +SYM_FUNC_START(cast5_cbc_dec_16way) /* input: * %rdi: ctx * %rsi: dst @@ -484,9 +484,9 @@ ENTRY(cast5_cbc_dec_16way) popq %r12; FRAME_END ret; -ENDPROC(cast5_cbc_dec_16way) +SYM_FUNC_END(cast5_cbc_dec_16way) -ENTRY(cast5_ctr_16way) +SYM_FUNC_START(cast5_ctr_16way) /* input: * %rdi: ctx * %rsi: dst @@ -560,4 +560,4 @@ ENTRY(cast5_ctr_16way) popq %r12; FRAME_END ret; -ENDPROC(cast5_ctr_16way) +SYM_FUNC_END(cast5_ctr_16way) diff --git a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S index b080a7454e70..932a3ce32a88 100644 --- a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S @@ -341,7 +341,7 @@ SYM_FUNC_START_LOCAL(__cast6_dec_blk8) ret; SYM_FUNC_END(__cast6_dec_blk8) -ENTRY(cast6_ecb_enc_8way) +SYM_FUNC_START(cast6_ecb_enc_8way) /* input: * %rdi: ctx * %rsi: dst @@ -362,9 +362,9 @@ ENTRY(cast6_ecb_enc_8way) popq %r15; FRAME_END ret; -ENDPROC(cast6_ecb_enc_8way) +SYM_FUNC_END(cast6_ecb_enc_8way) -ENTRY(cast6_ecb_dec_8way) +SYM_FUNC_START(cast6_ecb_dec_8way) /* input: * %rdi: ctx * %rsi: dst @@ -385,9 +385,9 @@ ENTRY(cast6_ecb_dec_8way) popq %r15; FRAME_END ret; -ENDPROC(cast6_ecb_dec_8way) +SYM_FUNC_END(cast6_ecb_dec_8way) -ENTRY(cast6_cbc_dec_8way) +SYM_FUNC_START(cast6_cbc_dec_8way) /* input: * %rdi: ctx * %rsi: dst @@ -411,9 +411,9 @@ ENTRY(cast6_cbc_dec_8way) popq %r12; FRAME_END ret; -ENDPROC(cast6_cbc_dec_8way) +SYM_FUNC_END(cast6_cbc_dec_8way) -ENTRY(cast6_ctr_8way) +SYM_FUNC_START(cast6_ctr_8way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -439,9 +439,9 @@ ENTRY(cast6_ctr_8way) popq %r12; FRAME_END ret; -ENDPROC(cast6_ctr_8way) +SYM_FUNC_END(cast6_ctr_8way) -ENTRY(cast6_xts_enc_8way) +SYM_FUNC_START(cast6_xts_enc_8way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -466,9 +466,9 @@ ENTRY(cast6_xts_enc_8way) popq %r15; FRAME_END ret; -ENDPROC(cast6_xts_enc_8way) +SYM_FUNC_END(cast6_xts_enc_8way) -ENTRY(cast6_xts_dec_8way) +SYM_FUNC_START(cast6_xts_dec_8way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -493,4 +493,4 @@ ENTRY(cast6_xts_dec_8way) popq %r15; FRAME_END ret; -ENDPROC(cast6_xts_dec_8way) +SYM_FUNC_END(cast6_xts_dec_8way) diff --git a/arch/x86/crypto/chacha-avx2-x86_64.S b/arch/x86/crypto/chacha-avx2-x86_64.S index 831e4434fc20..ee9a40ab4109 100644 --- a/arch/x86/crypto/chacha-avx2-x86_64.S +++ b/arch/x86/crypto/chacha-avx2-x86_64.S @@ -34,7 +34,7 @@ CTR4BL: .octa 0x00000000000000000000000000000002 .text -ENTRY(chacha_2block_xor_avx2) +SYM_FUNC_START(chacha_2block_xor_avx2) # %rdi: Input state matrix, s # %rsi: up to 2 data blocks output, o # %rdx: up to 2 data blocks input, i @@ -224,9 +224,9 @@ ENTRY(chacha_2block_xor_avx2) lea -8(%r10),%rsp jmp .Ldone2 -ENDPROC(chacha_2block_xor_avx2) +SYM_FUNC_END(chacha_2block_xor_avx2) -ENTRY(chacha_4block_xor_avx2) +SYM_FUNC_START(chacha_4block_xor_avx2) # %rdi: Input state matrix, s # %rsi: up to 4 data blocks output, o # %rdx: up to 4 data blocks input, i @@ -529,9 +529,9 @@ ENTRY(chacha_4block_xor_avx2) lea -8(%r10),%rsp jmp .Ldone4 -ENDPROC(chacha_4block_xor_avx2) +SYM_FUNC_END(chacha_4block_xor_avx2) -ENTRY(chacha_8block_xor_avx2) +SYM_FUNC_START(chacha_8block_xor_avx2) # %rdi: Input state matrix, s # %rsi: up to 8 data blocks output, o # %rdx: up to 8 data blocks input, i @@ -1018,4 +1018,4 @@ ENTRY(chacha_8block_xor_avx2) jmp .Ldone8 -ENDPROC(chacha_8block_xor_avx2) +SYM_FUNC_END(chacha_8block_xor_avx2) diff --git a/arch/x86/crypto/chacha-avx512vl-x86_64.S b/arch/x86/crypto/chacha-avx512vl-x86_64.S index 848f9c75fd4f..bb193fde123a 100644 --- a/arch/x86/crypto/chacha-avx512vl-x86_64.S +++ b/arch/x86/crypto/chacha-avx512vl-x86_64.S @@ -24,7 +24,7 @@ CTR8BL: .octa 0x00000003000000020000000100000000 .text -ENTRY(chacha_2block_xor_avx512vl) +SYM_FUNC_START(chacha_2block_xor_avx512vl) # %rdi: Input state matrix, s # %rsi: up to 2 data blocks output, o # %rdx: up to 2 data blocks input, i @@ -187,9 +187,9 @@ ENTRY(chacha_2block_xor_avx512vl) jmp .Ldone2 -ENDPROC(chacha_2block_xor_avx512vl) +SYM_FUNC_END(chacha_2block_xor_avx512vl) -ENTRY(chacha_4block_xor_avx512vl) +SYM_FUNC_START(chacha_4block_xor_avx512vl) # %rdi: Input state matrix, s # %rsi: up to 4 data blocks output, o # %rdx: up to 4 data blocks input, i @@ -453,9 +453,9 @@ ENTRY(chacha_4block_xor_avx512vl) jmp .Ldone4 -ENDPROC(chacha_4block_xor_avx512vl) +SYM_FUNC_END(chacha_4block_xor_avx512vl) -ENTRY(chacha_8block_xor_avx512vl) +SYM_FUNC_START(chacha_8block_xor_avx512vl) # %rdi: Input state matrix, s # %rsi: up to 8 data blocks output, o # %rdx: up to 8 data blocks input, i @@ -833,4 +833,4 @@ ENTRY(chacha_8block_xor_avx512vl) jmp .Ldone8 -ENDPROC(chacha_8block_xor_avx512vl) +SYM_FUNC_END(chacha_8block_xor_avx512vl) diff --git a/arch/x86/crypto/chacha-ssse3-x86_64.S b/arch/x86/crypto/chacha-ssse3-x86_64.S index 361d2bfc253c..a38ab2512a6f 100644 --- a/arch/x86/crypto/chacha-ssse3-x86_64.S +++ b/arch/x86/crypto/chacha-ssse3-x86_64.S @@ -111,7 +111,7 @@ SYM_FUNC_START_LOCAL(chacha_permute) ret SYM_FUNC_END(chacha_permute) -ENTRY(chacha_block_xor_ssse3) +SYM_FUNC_START(chacha_block_xor_ssse3) # %rdi: Input state matrix, s # %rsi: up to 1 data block output, o # %rdx: up to 1 data block input, i @@ -197,9 +197,9 @@ ENTRY(chacha_block_xor_ssse3) lea -8(%r10),%rsp jmp .Ldone -ENDPROC(chacha_block_xor_ssse3) +SYM_FUNC_END(chacha_block_xor_ssse3) -ENTRY(hchacha_block_ssse3) +SYM_FUNC_START(hchacha_block_ssse3) # %rdi: Input state matrix, s # %rsi: output (8 32-bit words) # %edx: nrounds @@ -218,9 +218,9 @@ ENTRY(hchacha_block_ssse3) FRAME_END ret -ENDPROC(hchacha_block_ssse3) +SYM_FUNC_END(hchacha_block_ssse3) -ENTRY(chacha_4block_xor_ssse3) +SYM_FUNC_START(chacha_4block_xor_ssse3) # %rdi: Input state matrix, s # %rsi: up to 4 data blocks output, o # %rdx: up to 4 data blocks input, i @@ -788,4 +788,4 @@ ENTRY(chacha_4block_xor_ssse3) jmp .Ldone4 -ENDPROC(chacha_4block_xor_ssse3) +SYM_FUNC_END(chacha_4block_xor_ssse3) diff --git a/arch/x86/crypto/crc32-pclmul_asm.S b/arch/x86/crypto/crc32-pclmul_asm.S index 1c099dc08cc3..9fd28ff65bc2 100644 --- a/arch/x86/crypto/crc32-pclmul_asm.S +++ b/arch/x86/crypto/crc32-pclmul_asm.S @@ -103,7 +103,7 @@ * size_t len, uint crc32) */ -ENTRY(crc32_pclmul_le_16) /* buffer and buffer size are 16 bytes aligned */ +SYM_FUNC_START(crc32_pclmul_le_16) /* buffer and buffer size are 16 bytes aligned */ movdqa (BUF), %xmm1 movdqa 0x10(BUF), %xmm2 movdqa 0x20(BUF), %xmm3 @@ -238,4 +238,4 @@ fold_64: PEXTRD 0x01, %xmm1, %eax ret -ENDPROC(crc32_pclmul_le_16) +SYM_FUNC_END(crc32_pclmul_le_16) diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S index d9b734d0c8cc..0e6690e3618c 100644 --- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S +++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S @@ -74,7 +74,7 @@ # unsigned int crc_pcl(u8 *buffer, int len, unsigned int crc_init); .text -ENTRY(crc_pcl) +SYM_FUNC_START(crc_pcl) #define bufp %rdi #define bufp_dw %edi #define bufp_w %di @@ -311,7 +311,7 @@ do_return: popq %rdi popq %rbx ret -ENDPROC(crc_pcl) +SYM_FUNC_END(crc_pcl) .section .rodata, "a", @progbits ################################################################ diff --git a/arch/x86/crypto/crct10dif-pcl-asm_64.S b/arch/x86/crypto/crct10dif-pcl-asm_64.S index 3d873e67749d..b2533d63030e 100644 --- a/arch/x86/crypto/crct10dif-pcl-asm_64.S +++ b/arch/x86/crypto/crct10dif-pcl-asm_64.S @@ -95,7 +95,7 @@ # Assumes len >= 16. # .align 16 -ENTRY(crc_t10dif_pcl) +SYM_FUNC_START(crc_t10dif_pcl) movdqa .Lbswap_mask(%rip), BSWAP_MASK @@ -280,7 +280,7 @@ ENTRY(crc_t10dif_pcl) jge .Lfold_16_bytes_loop # 32 <= len <= 255 add $16, len jmp .Lhandle_partial_segment # 17 <= len <= 31 -ENDPROC(crc_t10dif_pcl) +SYM_FUNC_END(crc_t10dif_pcl) .section .rodata, "a", @progbits .align 16 diff --git a/arch/x86/crypto/des3_ede-asm_64.S b/arch/x86/crypto/des3_ede-asm_64.S index 7fca43099a5f..fac0fdc3f25d 100644 --- a/arch/x86/crypto/des3_ede-asm_64.S +++ b/arch/x86/crypto/des3_ede-asm_64.S @@ -162,7 +162,7 @@ movl left##d, (io); \ movl right##d, 4(io); -ENTRY(des3_ede_x86_64_crypt_blk) +SYM_FUNC_START(des3_ede_x86_64_crypt_blk) /* input: * %rdi: round keys, CTX * %rsi: dst @@ -244,7 +244,7 @@ ENTRY(des3_ede_x86_64_crypt_blk) popq %rbx; ret; -ENDPROC(des3_ede_x86_64_crypt_blk) +SYM_FUNC_END(des3_ede_x86_64_crypt_blk) /*********************************************************************** * 3-way 3DES @@ -418,7 +418,7 @@ ENDPROC(des3_ede_x86_64_crypt_blk) #define __movq(src, dst) \ movq src, dst; -ENTRY(des3_ede_x86_64_crypt_blk_3way) +SYM_FUNC_START(des3_ede_x86_64_crypt_blk_3way) /* input: * %rdi: ctx, round keys * %rsi: dst (3 blocks) @@ -529,7 +529,7 @@ ENTRY(des3_ede_x86_64_crypt_blk_3way) popq %rbx; ret; -ENDPROC(des3_ede_x86_64_crypt_blk_3way) +SYM_FUNC_END(des3_ede_x86_64_crypt_blk_3way) .section .rodata, "a", @progbits .align 16 diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S index e81da25a33ca..bb9735fbb865 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_asm.S +++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S @@ -90,7 +90,7 @@ SYM_FUNC_START_LOCAL(__clmul_gf128mul_ble) SYM_FUNC_END(__clmul_gf128mul_ble) /* void clmul_ghash_mul(char *dst, const u128 *shash) */ -ENTRY(clmul_ghash_mul) +SYM_FUNC_START(clmul_ghash_mul) FRAME_BEGIN movups (%rdi), DATA movups (%rsi), SHASH @@ -101,13 +101,13 @@ ENTRY(clmul_ghash_mul) movups DATA, (%rdi) FRAME_END ret -ENDPROC(clmul_ghash_mul) +SYM_FUNC_END(clmul_ghash_mul) /* * void clmul_ghash_update(char *dst, const char *src, unsigned int srclen, * const u128 *shash); */ -ENTRY(clmul_ghash_update) +SYM_FUNC_START(clmul_ghash_update) FRAME_BEGIN cmp $16, %rdx jb .Lupdate_just_ret # check length @@ -130,4 +130,4 @@ ENTRY(clmul_ghash_update) .Lupdate_just_ret: FRAME_END ret -ENDPROC(clmul_ghash_update) +SYM_FUNC_END(clmul_ghash_update) diff --git a/arch/x86/crypto/nh-avx2-x86_64.S b/arch/x86/crypto/nh-avx2-x86_64.S index f7946ea1b704..b22c7b936272 100644 --- a/arch/x86/crypto/nh-avx2-x86_64.S +++ b/arch/x86/crypto/nh-avx2-x86_64.S @@ -69,7 +69,7 @@ * * It's guaranteed that message_len % 16 == 0. */ -ENTRY(nh_avx2) +SYM_FUNC_START(nh_avx2) vmovdqu 0x00(KEY), K0 vmovdqu 0x10(KEY), K1 @@ -154,4 +154,4 @@ ENTRY(nh_avx2) vpaddq T4, T0, T0 vmovdqu T0, (HASH) ret -ENDPROC(nh_avx2) +SYM_FUNC_END(nh_avx2) diff --git a/arch/x86/crypto/nh-sse2-x86_64.S b/arch/x86/crypto/nh-sse2-x86_64.S index 51f52d4ab4bb..d7ae22dd6683 100644 --- a/arch/x86/crypto/nh-sse2-x86_64.S +++ b/arch/x86/crypto/nh-sse2-x86_64.S @@ -71,7 +71,7 @@ * * It's guaranteed that message_len % 16 == 0. */ -ENTRY(nh_sse2) +SYM_FUNC_START(nh_sse2) movdqu 0x00(KEY), K0 movdqu 0x10(KEY), K1 @@ -120,4 +120,4 @@ ENTRY(nh_sse2) movdqu T0, 0x00(HASH) movdqu T1, 0x10(HASH) ret -ENDPROC(nh_sse2) +SYM_FUNC_END(nh_sse2) diff --git a/arch/x86/crypto/poly1305-avx2-x86_64.S b/arch/x86/crypto/poly1305-avx2-x86_64.S index 8b341bc29d41..d6063feda9da 100644 --- a/arch/x86/crypto/poly1305-avx2-x86_64.S +++ b/arch/x86/crypto/poly1305-avx2-x86_64.S @@ -79,7 +79,7 @@ ORMASK: .octa 0x00000000010000000000000001000000 #define d3 %r12 #define d4 %r13 -ENTRY(poly1305_4block_avx2) +SYM_FUNC_START(poly1305_4block_avx2) # %rdi: Accumulator h[5] # %rsi: 64 byte input block m # %rdx: Poly1305 key r[5] @@ -387,4 +387,4 @@ ENTRY(poly1305_4block_avx2) pop %r12 pop %rbx ret -ENDPROC(poly1305_4block_avx2) +SYM_FUNC_END(poly1305_4block_avx2) diff --git a/arch/x86/crypto/poly1305-sse2-x86_64.S b/arch/x86/crypto/poly1305-sse2-x86_64.S index 5578f846e622..d8ea29b96640 100644 --- a/arch/x86/crypto/poly1305-sse2-x86_64.S +++ b/arch/x86/crypto/poly1305-sse2-x86_64.S @@ -46,7 +46,7 @@ ORMASK: .octa 0x00000000010000000000000001000000 #define d3 %r11 #define d4 %r12 -ENTRY(poly1305_block_sse2) +SYM_FUNC_START(poly1305_block_sse2) # %rdi: Accumulator h[5] # %rsi: 16 byte input block m # %rdx: Poly1305 key r[5] @@ -276,7 +276,7 @@ ENTRY(poly1305_block_sse2) pop %r12 pop %rbx ret -ENDPROC(poly1305_block_sse2) +SYM_FUNC_END(poly1305_block_sse2) #define u0 0x00(%r8) @@ -301,7 +301,7 @@ ENDPROC(poly1305_block_sse2) #undef d0 #define d0 %r13 -ENTRY(poly1305_2block_sse2) +SYM_FUNC_START(poly1305_2block_sse2) # %rdi: Accumulator h[5] # %rsi: 16 byte input block m # %rdx: Poly1305 key r[5] @@ -587,4 +587,4 @@ ENTRY(poly1305_2block_sse2) pop %r12 pop %rbx ret -ENDPROC(poly1305_2block_sse2) +SYM_FUNC_END(poly1305_2block_sse2) diff --git a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S index a098aa015784..ba9e4c1e7f5c 100644 --- a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S @@ -662,7 +662,7 @@ SYM_FUNC_START_LOCAL(__serpent_dec_blk8_avx) ret; SYM_FUNC_END(__serpent_dec_blk8_avx) -ENTRY(serpent_ecb_enc_8way_avx) +SYM_FUNC_START(serpent_ecb_enc_8way_avx) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -678,9 +678,9 @@ ENTRY(serpent_ecb_enc_8way_avx) FRAME_END ret; -ENDPROC(serpent_ecb_enc_8way_avx) +SYM_FUNC_END(serpent_ecb_enc_8way_avx) -ENTRY(serpent_ecb_dec_8way_avx) +SYM_FUNC_START(serpent_ecb_dec_8way_avx) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -696,9 +696,9 @@ ENTRY(serpent_ecb_dec_8way_avx) FRAME_END ret; -ENDPROC(serpent_ecb_dec_8way_avx) +SYM_FUNC_END(serpent_ecb_dec_8way_avx) -ENTRY(serpent_cbc_dec_8way_avx) +SYM_FUNC_START(serpent_cbc_dec_8way_avx) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -714,9 +714,9 @@ ENTRY(serpent_cbc_dec_8way_avx) FRAME_END ret; -ENDPROC(serpent_cbc_dec_8way_avx) +SYM_FUNC_END(serpent_cbc_dec_8way_avx) -ENTRY(serpent_ctr_8way_avx) +SYM_FUNC_START(serpent_ctr_8way_avx) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -734,9 +734,9 @@ ENTRY(serpent_ctr_8way_avx) FRAME_END ret; -ENDPROC(serpent_ctr_8way_avx) +SYM_FUNC_END(serpent_ctr_8way_avx) -ENTRY(serpent_xts_enc_8way_avx) +SYM_FUNC_START(serpent_xts_enc_8way_avx) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -756,9 +756,9 @@ ENTRY(serpent_xts_enc_8way_avx) FRAME_END ret; -ENDPROC(serpent_xts_enc_8way_avx) +SYM_FUNC_END(serpent_xts_enc_8way_avx) -ENTRY(serpent_xts_dec_8way_avx) +SYM_FUNC_START(serpent_xts_dec_8way_avx) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -778,4 +778,4 @@ ENTRY(serpent_xts_dec_8way_avx) FRAME_END ret; -ENDPROC(serpent_xts_dec_8way_avx) +SYM_FUNC_END(serpent_xts_dec_8way_avx) diff --git a/arch/x86/crypto/serpent-avx2-asm_64.S b/arch/x86/crypto/serpent-avx2-asm_64.S index 6149ba80b4d1..c9648aeae705 100644 --- a/arch/x86/crypto/serpent-avx2-asm_64.S +++ b/arch/x86/crypto/serpent-avx2-asm_64.S @@ -668,7 +668,7 @@ SYM_FUNC_START_LOCAL(__serpent_dec_blk16) ret; SYM_FUNC_END(__serpent_dec_blk16) -ENTRY(serpent_ecb_enc_16way) +SYM_FUNC_START(serpent_ecb_enc_16way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -688,9 +688,9 @@ ENTRY(serpent_ecb_enc_16way) FRAME_END ret; -ENDPROC(serpent_ecb_enc_16way) +SYM_FUNC_END(serpent_ecb_enc_16way) -ENTRY(serpent_ecb_dec_16way) +SYM_FUNC_START(serpent_ecb_dec_16way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -710,9 +710,9 @@ ENTRY(serpent_ecb_dec_16way) FRAME_END ret; -ENDPROC(serpent_ecb_dec_16way) +SYM_FUNC_END(serpent_ecb_dec_16way) -ENTRY(serpent_cbc_dec_16way) +SYM_FUNC_START(serpent_cbc_dec_16way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -733,9 +733,9 @@ ENTRY(serpent_cbc_dec_16way) FRAME_END ret; -ENDPROC(serpent_cbc_dec_16way) +SYM_FUNC_END(serpent_cbc_dec_16way) -ENTRY(serpent_ctr_16way) +SYM_FUNC_START(serpent_ctr_16way) /* input: * %rdi: ctx, CTX * %rsi: dst (16 blocks) @@ -758,9 +758,9 @@ ENTRY(serpent_ctr_16way) FRAME_END ret; -ENDPROC(serpent_ctr_16way) +SYM_FUNC_END(serpent_ctr_16way) -ENTRY(serpent_xts_enc_16way) +SYM_FUNC_START(serpent_xts_enc_16way) /* input: * %rdi: ctx, CTX * %rsi: dst (16 blocks) @@ -784,9 +784,9 @@ ENTRY(serpent_xts_enc_16way) FRAME_END ret; -ENDPROC(serpent_xts_enc_16way) +SYM_FUNC_END(serpent_xts_enc_16way) -ENTRY(serpent_xts_dec_16way) +SYM_FUNC_START(serpent_xts_dec_16way) /* input: * %rdi: ctx, CTX * %rsi: dst (16 blocks) @@ -810,4 +810,4 @@ ENTRY(serpent_xts_dec_16way) FRAME_END ret; -ENDPROC(serpent_xts_dec_16way) +SYM_FUNC_END(serpent_xts_dec_16way) diff --git a/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S b/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S index 5e0b3a3e97af..efb6dc17dc90 100644 --- a/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S +++ b/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S @@ -619,7 +619,7 @@ pxor t0, x3; \ movdqu x3, (3*4*4)(out); -ENTRY(__serpent_enc_blk_8way) +SYM_FUNC_START(__serpent_enc_blk_8way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -682,9 +682,9 @@ ENTRY(__serpent_enc_blk_8way) xor_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2); ret; -ENDPROC(__serpent_enc_blk_8way) +SYM_FUNC_END(__serpent_enc_blk_8way) -ENTRY(serpent_dec_blk_8way) +SYM_FUNC_START(serpent_dec_blk_8way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -736,4 +736,4 @@ ENTRY(serpent_dec_blk_8way) write_blocks(%rax, RC2, RD2, RB2, RE2, RK0, RK1, RK2); ret; -ENDPROC(serpent_dec_blk_8way) +SYM_FUNC_END(serpent_dec_blk_8way) diff --git a/arch/x86/crypto/sha1_avx2_x86_64_asm.S b/arch/x86/crypto/sha1_avx2_x86_64_asm.S index 9f712a7dfd79..6decc85ef7b7 100644 --- a/arch/x86/crypto/sha1_avx2_x86_64_asm.S +++ b/arch/x86/crypto/sha1_avx2_x86_64_asm.S @@ -634,7 +634,7 @@ _loop3: * param: function's name */ .macro SHA1_VECTOR_ASM name - ENTRY(\name) + SYM_FUNC_START(\name) push %rbx push %r12 @@ -676,7 +676,7 @@ _loop3: ret - ENDPROC(\name) + SYM_FUNC_END(\name) .endm .section .rodata diff --git a/arch/x86/crypto/sha1_ni_asm.S b/arch/x86/crypto/sha1_ni_asm.S index ebbdba72ae07..11efe3a45a1f 100644 --- a/arch/x86/crypto/sha1_ni_asm.S +++ b/arch/x86/crypto/sha1_ni_asm.S @@ -95,7 +95,7 @@ */ .text .align 32 -ENTRY(sha1_ni_transform) +SYM_FUNC_START(sha1_ni_transform) mov %rsp, RSPSAVE sub $FRAME_SIZE, %rsp and $~0xF, %rsp @@ -291,7 +291,7 @@ ENTRY(sha1_ni_transform) mov RSPSAVE, %rsp ret -ENDPROC(sha1_ni_transform) +SYM_FUNC_END(sha1_ni_transform) .section .rodata.cst16.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 16 .align 16 diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S index 99c5b8c4dc38..5d03c1173690 100644 --- a/arch/x86/crypto/sha1_ssse3_asm.S +++ b/arch/x86/crypto/sha1_ssse3_asm.S @@ -67,7 +67,7 @@ * param: function's name */ .macro SHA1_VECTOR_ASM name - ENTRY(\name) + SYM_FUNC_START(\name) push %rbx push %r12 @@ -101,7 +101,7 @@ pop %rbx ret - ENDPROC(\name) + SYM_FUNC_END(\name) .endm /* diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/crypto/sha256-avx-asm.S index 001bbcf93c79..22e14c8dd2e4 100644 --- a/arch/x86/crypto/sha256-avx-asm.S +++ b/arch/x86/crypto/sha256-avx-asm.S @@ -347,7 +347,7 @@ a = TMP_ ## arg 3 : Num blocks ######################################################################## .text -ENTRY(sha256_transform_avx) +SYM_FUNC_START(sha256_transform_avx) .align 32 pushq %rbx pushq %r12 @@ -460,7 +460,7 @@ done_hash: popq %r12 popq %rbx ret -ENDPROC(sha256_transform_avx) +SYM_FUNC_END(sha256_transform_avx) .section .rodata.cst256.K256, "aM", @progbits, 256 .align 64 diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S index 1420db15dcdd..519b551ad576 100644 --- a/arch/x86/crypto/sha256-avx2-asm.S +++ b/arch/x86/crypto/sha256-avx2-asm.S @@ -526,7 +526,7 @@ STACK_SIZE = _RSP + _RSP_SIZE ## arg 3 : Num blocks ######################################################################## .text -ENTRY(sha256_transform_rorx) +SYM_FUNC_START(sha256_transform_rorx) .align 32 pushq %rbx pushq %r12 @@ -713,7 +713,7 @@ done_hash: popq %r12 popq %rbx ret -ENDPROC(sha256_transform_rorx) +SYM_FUNC_END(sha256_transform_rorx) .section .rodata.cst512.K256, "aM", @progbits, 512 .align 64 diff --git a/arch/x86/crypto/sha256-ssse3-asm.S b/arch/x86/crypto/sha256-ssse3-asm.S index c6c05ed2c16a..69cc2f91dc4c 100644 --- a/arch/x86/crypto/sha256-ssse3-asm.S +++ b/arch/x86/crypto/sha256-ssse3-asm.S @@ -353,7 +353,7 @@ a = TMP_ ## arg 3 : Num blocks ######################################################################## .text -ENTRY(sha256_transform_ssse3) +SYM_FUNC_START(sha256_transform_ssse3) .align 32 pushq %rbx pushq %r12 @@ -471,7 +471,7 @@ done_hash: popq %rbx ret -ENDPROC(sha256_transform_ssse3) +SYM_FUNC_END(sha256_transform_ssse3) .section .rodata.cst256.K256, "aM", @progbits, 256 .align 64 diff --git a/arch/x86/crypto/sha256_ni_asm.S b/arch/x86/crypto/sha256_ni_asm.S index fb58f58ecfbc..7abade04a3a3 100644 --- a/arch/x86/crypto/sha256_ni_asm.S +++ b/arch/x86/crypto/sha256_ni_asm.S @@ -97,7 +97,7 @@ .text .align 32 -ENTRY(sha256_ni_transform) +SYM_FUNC_START(sha256_ni_transform) shl $6, NUM_BLKS /* convert to bytes */ jz .Ldone_hash @@ -327,7 +327,7 @@ ENTRY(sha256_ni_transform) .Ldone_hash: ret -ENDPROC(sha256_ni_transform) +SYM_FUNC_END(sha256_ni_transform) .section .rodata.cst256.K256, "aM", @progbits, 256 .align 64 diff --git a/arch/x86/crypto/sha512-avx-asm.S b/arch/x86/crypto/sha512-avx-asm.S index 39235fefe6f7..3704ddd7e5d5 100644 --- a/arch/x86/crypto/sha512-avx-asm.S +++ b/arch/x86/crypto/sha512-avx-asm.S @@ -277,7 +277,7 @@ frame_size = frame_GPRSAVE + GPRSAVE_SIZE # message blocks. # L is the message length in SHA512 blocks ######################################################################## -ENTRY(sha512_transform_avx) +SYM_FUNC_START(sha512_transform_avx) cmp $0, msglen je nowork @@ -365,7 +365,7 @@ updateblock: nowork: ret -ENDPROC(sha512_transform_avx) +SYM_FUNC_END(sha512_transform_avx) ######################################################################## ### Binary Data diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S index b16d56005162..80d830e7ee09 100644 --- a/arch/x86/crypto/sha512-avx2-asm.S +++ b/arch/x86/crypto/sha512-avx2-asm.S @@ -569,7 +569,7 @@ frame_size = frame_GPRSAVE + GPRSAVE_SIZE # message blocks. # L is the message length in SHA512 blocks ######################################################################## -ENTRY(sha512_transform_rorx) +SYM_FUNC_START(sha512_transform_rorx) # Allocate Stack Space mov %rsp, %rax sub $frame_size, %rsp @@ -682,7 +682,7 @@ done_hash: # Restore Stack Pointer mov frame_RSPSAVE(%rsp), %rsp ret -ENDPROC(sha512_transform_rorx) +SYM_FUNC_END(sha512_transform_rorx) ######################################################################## ### Binary Data diff --git a/arch/x86/crypto/sha512-ssse3-asm.S b/arch/x86/crypto/sha512-ssse3-asm.S index 66bbd9058a90..838f984e95d9 100644 --- a/arch/x86/crypto/sha512-ssse3-asm.S +++ b/arch/x86/crypto/sha512-ssse3-asm.S @@ -275,7 +275,7 @@ frame_size = frame_GPRSAVE + GPRSAVE_SIZE # message blocks. # L is the message length in SHA512 blocks. ######################################################################## -ENTRY(sha512_transform_ssse3) +SYM_FUNC_START(sha512_transform_ssse3) cmp $0, msglen je nowork @@ -364,7 +364,7 @@ updateblock: nowork: ret -ENDPROC(sha512_transform_ssse3) +SYM_FUNC_END(sha512_transform_ssse3) ######################################################################## ### Binary Data diff --git a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S index 588f0a2f63ab..a5151393bb2f 100644 --- a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S @@ -315,7 +315,7 @@ SYM_FUNC_START_LOCAL(__twofish_dec_blk8) ret; SYM_FUNC_END(__twofish_dec_blk8) -ENTRY(twofish_ecb_enc_8way) +SYM_FUNC_START(twofish_ecb_enc_8way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -333,9 +333,9 @@ ENTRY(twofish_ecb_enc_8way) FRAME_END ret; -ENDPROC(twofish_ecb_enc_8way) +SYM_FUNC_END(twofish_ecb_enc_8way) -ENTRY(twofish_ecb_dec_8way) +SYM_FUNC_START(twofish_ecb_dec_8way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -353,9 +353,9 @@ ENTRY(twofish_ecb_dec_8way) FRAME_END ret; -ENDPROC(twofish_ecb_dec_8way) +SYM_FUNC_END(twofish_ecb_dec_8way) -ENTRY(twofish_cbc_dec_8way) +SYM_FUNC_START(twofish_cbc_dec_8way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -378,9 +378,9 @@ ENTRY(twofish_cbc_dec_8way) FRAME_END ret; -ENDPROC(twofish_cbc_dec_8way) +SYM_FUNC_END(twofish_cbc_dec_8way) -ENTRY(twofish_ctr_8way) +SYM_FUNC_START(twofish_ctr_8way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -405,9 +405,9 @@ ENTRY(twofish_ctr_8way) FRAME_END ret; -ENDPROC(twofish_ctr_8way) +SYM_FUNC_END(twofish_ctr_8way) -ENTRY(twofish_xts_enc_8way) +SYM_FUNC_START(twofish_xts_enc_8way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -429,9 +429,9 @@ ENTRY(twofish_xts_enc_8way) FRAME_END ret; -ENDPROC(twofish_xts_enc_8way) +SYM_FUNC_END(twofish_xts_enc_8way) -ENTRY(twofish_xts_dec_8way) +SYM_FUNC_START(twofish_xts_dec_8way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -453,4 +453,4 @@ ENTRY(twofish_xts_dec_8way) FRAME_END ret; -ENDPROC(twofish_xts_dec_8way) +SYM_FUNC_END(twofish_xts_dec_8way) diff --git a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S index e495e07c7f1b..fc23552afe37 100644 --- a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S +++ b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S @@ -220,7 +220,7 @@ rorq $32, RAB2; \ outunpack3(mov, RIO, 2, RAB, 2); -ENTRY(__twofish_enc_blk_3way) +SYM_FUNC_START(__twofish_enc_blk_3way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -267,9 +267,9 @@ ENTRY(__twofish_enc_blk_3way) popq %r12; popq %r13; ret; -ENDPROC(__twofish_enc_blk_3way) +SYM_FUNC_END(__twofish_enc_blk_3way) -ENTRY(twofish_dec_blk_3way) +SYM_FUNC_START(twofish_dec_blk_3way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -302,4 +302,4 @@ ENTRY(twofish_dec_blk_3way) popq %r12; popq %r13; ret; -ENDPROC(twofish_dec_blk_3way) +SYM_FUNC_END(twofish_dec_blk_3way) diff --git a/arch/x86/crypto/twofish-x86_64-asm_64.S b/arch/x86/crypto/twofish-x86_64-asm_64.S index ecef2cb9f43f..d2e56232494a 100644 --- a/arch/x86/crypto/twofish-x86_64-asm_64.S +++ b/arch/x86/crypto/twofish-x86_64-asm_64.S @@ -202,7 +202,7 @@ xor %r8d, d ## D;\ ror $1, d ## D; -ENTRY(twofish_enc_blk) +SYM_FUNC_START(twofish_enc_blk) pushq R1 /* %rdi contains the ctx address */ @@ -253,9 +253,9 @@ ENTRY(twofish_enc_blk) popq R1 movl $1,%eax ret -ENDPROC(twofish_enc_blk) +SYM_FUNC_END(twofish_enc_blk) -ENTRY(twofish_dec_blk) +SYM_FUNC_START(twofish_dec_blk) pushq R1 /* %rdi contains the ctx address */ @@ -305,4 +305,4 @@ ENTRY(twofish_dec_blk) popq R1 movl $1,%eax ret -ENDPROC(twofish_dec_blk) +SYM_FUNC_END(twofish_dec_blk) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 13e4fe378e5a..d58c01239457 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -15,7 +15,7 @@ * at the top of the kernel process stack. * * Some macro usage: - * - ENTRY/END: Define functions in the symbol table. + * - SYM_FUNC_START/END:Define functions in the symbol table. * - TRACE_IRQ_*: Trace hardirq state for lock debugging. * - idtentry: Define exception entry points. */ @@ -1040,7 +1040,7 @@ idtentry simd_coprocessor_error do_simd_coprocessor_error has_error_code=0 * Reload gs selector with exception handling * edi: new selector */ -ENTRY(native_load_gs_index) +SYM_FUNC_START(native_load_gs_index) FRAME_BEGIN pushfq DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI) @@ -1054,7 +1054,7 @@ ENTRY(native_load_gs_index) popfq FRAME_END ret -ENDPROC(native_load_gs_index) +SYM_FUNC_END(native_load_gs_index) EXPORT_SYMBOL(native_load_gs_index) _ASM_EXTABLE(.Lgs_change, .Lbad_gs) @@ -1075,7 +1075,7 @@ SYM_CODE_END(.Lbad_gs) .previous /* Call softirq on interrupt stack. Interrupts are off. */ -ENTRY(do_softirq_own_stack) +SYM_FUNC_START(do_softirq_own_stack) pushq %rbp mov %rsp, %rbp ENTER_IRQ_STACK regs=0 old_rsp=%r11 @@ -1083,7 +1083,7 @@ ENTRY(do_softirq_own_stack) LEAVE_IRQ_STACK regs=0 leaveq ret -ENDPROC(do_softirq_own_stack) +SYM_FUNC_END(do_softirq_own_stack) #ifdef CONFIG_XEN_PV idtentry hypervisor_callback xen_do_hypervisor_callback has_error_code=0 diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index da296435676e..f1d3ccae5dd5 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -46,7 +46,7 @@ * ebp user stack * 0(%ebp) arg6 */ -ENTRY(entry_SYSENTER_compat) +SYM_FUNC_START(entry_SYSENTER_compat) /* Interrupts are off on entry. */ SWAPGS @@ -147,7 +147,7 @@ ENTRY(entry_SYSENTER_compat) popfq jmp .Lsysenter_flags_fixed SYM_INNER_LABEL(__end_entry_SYSENTER_compat, SYM_L_GLOBAL) -ENDPROC(entry_SYSENTER_compat) +SYM_FUNC_END(entry_SYSENTER_compat) /* * 32-bit SYSCALL entry. diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index 462a20f386e0..c8daa92f38dc 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -14,7 +14,7 @@ /* * Hooray, we are in Long 64-bit mode (but still running in low memory) */ -ENTRY(wakeup_long64) +SYM_FUNC_START(wakeup_long64) movq saved_magic, %rax movq $0x123456789abcdef0, %rdx cmpq %rdx, %rax @@ -40,9 +40,9 @@ ENTRY(wakeup_long64) movq saved_rip, %rax jmp *%rax -ENDPROC(wakeup_long64) +SYM_FUNC_END(wakeup_long64) -ENTRY(do_suspend_lowlevel) +SYM_FUNC_START(do_suspend_lowlevel) FRAME_BEGIN subq $8, %rsp xorl %eax, %eax @@ -125,7 +125,7 @@ ENTRY(do_suspend_lowlevel) addq $8, %rsp FRAME_END jmp restore_processor_state -ENDPROC(do_suspend_lowlevel) +SYM_FUNC_END(do_suspend_lowlevel) .data saved_rbp: .quad 0 diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 60f894b018e0..16deae706950 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -132,11 +132,11 @@ EXPORT_SYMBOL(__fentry__) #ifdef CONFIG_DYNAMIC_FTRACE -ENTRY(function_hook) +SYM_FUNC_START(function_hook) retq -ENDPROC(function_hook) +SYM_FUNC_END(function_hook) -ENTRY(ftrace_caller) +SYM_FUNC_START(ftrace_caller) /* save_mcount_regs fills in first two parameters */ save_mcount_regs @@ -170,9 +170,9 @@ SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) */ WEAK(ftrace_stub) retq -ENDPROC(ftrace_caller) +SYM_FUNC_END(ftrace_caller) -ENTRY(ftrace_regs_caller) +SYM_FUNC_START(ftrace_regs_caller) /* Save the current flags before any operations that can change them */ pushfq @@ -243,12 +243,12 @@ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL) jmp ftrace_epilogue -ENDPROC(ftrace_regs_caller) +SYM_FUNC_END(ftrace_regs_caller) #else /* ! CONFIG_DYNAMIC_FTRACE */ -ENTRY(function_hook) +SYM_FUNC_START(function_hook) cmpq $ftrace_stub, ftrace_trace_function jnz trace @@ -279,11 +279,11 @@ trace: restore_mcount_regs jmp fgraph_trace -ENDPROC(function_hook) +SYM_FUNC_END(function_hook) #endif /* CONFIG_DYNAMIC_FTRACE */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER -ENTRY(ftrace_graph_caller) +SYM_FUNC_START(ftrace_graph_caller) /* Saves rbp into %rdx and fills first parameter */ save_mcount_regs @@ -294,7 +294,7 @@ ENTRY(ftrace_graph_caller) restore_mcount_regs retq -ENDPROC(ftrace_graph_caller) +SYM_FUNC_END(ftrace_graph_caller) SYM_CODE_START(return_to_handler) UNWIND_HINT_EMPTY diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S index ddeeaac8adda..0db0375235b4 100644 --- a/arch/x86/kernel/irqflags.S +++ b/arch/x86/kernel/irqflags.S @@ -7,20 +7,20 @@ /* * unsigned long native_save_fl(void) */ -ENTRY(native_save_fl) +SYM_FUNC_START(native_save_fl) pushf pop %_ASM_AX ret -ENDPROC(native_save_fl) +SYM_FUNC_END(native_save_fl) EXPORT_SYMBOL(native_save_fl) /* * void native_restore_fl(unsigned long flags) * %eax/%rdi: flags */ -ENTRY(native_restore_fl) +SYM_FUNC_START(native_restore_fl) push %_ASM_ARG1 popf ret -ENDPROC(native_restore_fl) +SYM_FUNC_END(native_restore_fl) EXPORT_SYMBOL(native_restore_fl) diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 751a384c2eb0..81ada2ce99e7 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -43,7 +43,7 @@ * they VM-Fail, whereas a successful VM-Enter + VM-Exit will jump * to vmx_vmexit. */ -ENTRY(vmx_vmenter) +SYM_FUNC_START(vmx_vmenter) /* EFLAGS.ZF is set if VMCS.LAUNCHED == 0 */ je 2f @@ -65,7 +65,7 @@ ENTRY(vmx_vmenter) _ASM_EXTABLE(1b, 5b) _ASM_EXTABLE(2b, 5b) -ENDPROC(vmx_vmenter) +SYM_FUNC_END(vmx_vmenter) /** * vmx_vmexit - Handle a VMX VM-Exit @@ -77,7 +77,7 @@ ENDPROC(vmx_vmenter) * here after hardware loads the host's state, i.e. this is the destination * referred to by VMCS.HOST_RIP. */ -ENTRY(vmx_vmexit) +SYM_FUNC_START(vmx_vmexit) #ifdef CONFIG_RETPOLINE ALTERNATIVE "jmp .Lvmexit_skip_rsb", "", X86_FEATURE_RETPOLINE /* Preserve guest's RAX, it's used to stuff the RSB. */ @@ -90,7 +90,7 @@ ENTRY(vmx_vmexit) .Lvmexit_skip_rsb: #endif ret -ENDPROC(vmx_vmexit) +SYM_FUNC_END(vmx_vmexit) /** * __vmx_vcpu_run - Run a vCPU via a transition to VMX guest mode @@ -101,7 +101,7 @@ ENDPROC(vmx_vmexit) * Returns: * 0 on VM-Exit, 1 on VM-Fail */ -ENTRY(__vmx_vcpu_run) +SYM_FUNC_START(__vmx_vcpu_run) push %_ASM_BP mov %_ASM_SP, %_ASM_BP #ifdef CONFIG_X86_64 @@ -233,4 +233,4 @@ ENTRY(__vmx_vcpu_run) /* VM-Fail. Out-of-line to avoid a taken Jcc after VM-Exit. */ 2: mov $1, %eax jmp 1b -ENDPROC(__vmx_vcpu_run) +SYM_FUNC_END(__vmx_vcpu_run) diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S index 4df90c9ea383..74256bd193da 100644 --- a/arch/x86/lib/checksum_32.S +++ b/arch/x86/lib/checksum_32.S @@ -280,7 +280,7 @@ unsigned int csum_partial_copy_generic (const char *src, char *dst, #define ARGBASE 16 #define FP 12 -ENTRY(csum_partial_copy_generic) +SYM_FUNC_START(csum_partial_copy_generic) subl $4,%esp pushl %edi pushl %esi @@ -398,7 +398,7 @@ DST( movb %cl, (%edi) ) popl %edi popl %ecx # equivalent to addl $4,%esp ret -ENDPROC(csum_partial_copy_generic) +SYM_FUNC_END(csum_partial_copy_generic) #else @@ -416,7 +416,7 @@ ENDPROC(csum_partial_copy_generic) #define ARGBASE 12 -ENTRY(csum_partial_copy_generic) +SYM_FUNC_START(csum_partial_copy_generic) pushl %ebx pushl %edi pushl %esi @@ -483,7 +483,7 @@ DST( movb %dl, (%edi) ) popl %edi popl %ebx ret -ENDPROC(csum_partial_copy_generic) +SYM_FUNC_END(csum_partial_copy_generic) #undef ROUND #undef ROUND1 diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S index 75a5a4515fa7..c4c7dd115953 100644 --- a/arch/x86/lib/clear_page_64.S +++ b/arch/x86/lib/clear_page_64.S @@ -13,15 +13,15 @@ * Zero a page. * %rdi - page */ -ENTRY(clear_page_rep) +SYM_FUNC_START(clear_page_rep) movl $4096/8,%ecx xorl %eax,%eax rep stosq ret -ENDPROC(clear_page_rep) +SYM_FUNC_END(clear_page_rep) EXPORT_SYMBOL_GPL(clear_page_rep) -ENTRY(clear_page_orig) +SYM_FUNC_START(clear_page_orig) xorl %eax,%eax movl $4096/64,%ecx .p2align 4 @@ -40,13 +40,13 @@ ENTRY(clear_page_orig) jnz .Lloop nop ret -ENDPROC(clear_page_orig) +SYM_FUNC_END(clear_page_orig) EXPORT_SYMBOL_GPL(clear_page_orig) -ENTRY(clear_page_erms) +SYM_FUNC_START(clear_page_erms) movl $4096,%ecx xorl %eax,%eax rep stosb ret -ENDPROC(clear_page_erms) +SYM_FUNC_END(clear_page_erms) EXPORT_SYMBOL_GPL(clear_page_erms) diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S index d63185698a23..3542502faa3b 100644 --- a/arch/x86/lib/cmpxchg16b_emu.S +++ b/arch/x86/lib/cmpxchg16b_emu.S @@ -13,7 +13,7 @@ * %rcx : high 64 bits of new value * %al : Operation successful */ -ENTRY(this_cpu_cmpxchg16b_emu) +SYM_FUNC_START(this_cpu_cmpxchg16b_emu) # # Emulate 'cmpxchg16b %gs:(%rsi)' except we return the result in %al not @@ -44,4 +44,4 @@ ENTRY(this_cpu_cmpxchg16b_emu) xor %al,%al ret -ENDPROC(this_cpu_cmpxchg16b_emu) +SYM_FUNC_END(this_cpu_cmpxchg16b_emu) diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S index 691d80e97488..ca01ed6029f4 100644 --- a/arch/x86/lib/cmpxchg8b_emu.S +++ b/arch/x86/lib/cmpxchg8b_emu.S @@ -13,7 +13,7 @@ * %ebx : low 32 bits of new value * %ecx : high 32 bits of new value */ -ENTRY(cmpxchg8b_emu) +SYM_FUNC_START(cmpxchg8b_emu) # # Emulate 'cmpxchg8b (%esi)' on UP except we don't @@ -42,5 +42,5 @@ ENTRY(cmpxchg8b_emu) popfl ret -ENDPROC(cmpxchg8b_emu) +SYM_FUNC_END(cmpxchg8b_emu) EXPORT_SYMBOL(cmpxchg8b_emu) diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S index f505870bd93b..2402d4c489d2 100644 --- a/arch/x86/lib/copy_page_64.S +++ b/arch/x86/lib/copy_page_64.S @@ -13,12 +13,12 @@ * prefetch distance based on SMP/UP. */ ALIGN -ENTRY(copy_page) +SYM_FUNC_START(copy_page) ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD movl $4096/8, %ecx rep movsq ret -ENDPROC(copy_page) +SYM_FUNC_END(copy_page) EXPORT_SYMBOL(copy_page) SYM_FUNC_START_LOCAL(copy_page_regs) diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 4a12b3c120bf..816f128a6d52 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -53,7 +53,7 @@ * Output: * eax uncopied bytes or 0 if successful. */ -ENTRY(copy_user_generic_unrolled) +SYM_FUNC_START(copy_user_generic_unrolled) ASM_STAC cmpl $8,%edx jb 20f /* less then 8 bytes, go to byte copy loop */ @@ -136,7 +136,7 @@ ENTRY(copy_user_generic_unrolled) _ASM_EXTABLE_UA(19b, 40b) _ASM_EXTABLE_UA(21b, 50b) _ASM_EXTABLE_UA(22b, 50b) -ENDPROC(copy_user_generic_unrolled) +SYM_FUNC_END(copy_user_generic_unrolled) EXPORT_SYMBOL(copy_user_generic_unrolled) /* Some CPUs run faster using the string copy instructions. @@ -157,7 +157,7 @@ EXPORT_SYMBOL(copy_user_generic_unrolled) * Output: * eax uncopied bytes or 0 if successful. */ -ENTRY(copy_user_generic_string) +SYM_FUNC_START(copy_user_generic_string) ASM_STAC cmpl $8,%edx jb 2f /* less than 8 bytes, go to byte copy loop */ @@ -182,7 +182,7 @@ ENTRY(copy_user_generic_string) _ASM_EXTABLE_UA(1b, 11b) _ASM_EXTABLE_UA(3b, 12b) -ENDPROC(copy_user_generic_string) +SYM_FUNC_END(copy_user_generic_string) EXPORT_SYMBOL(copy_user_generic_string) /* @@ -197,7 +197,7 @@ EXPORT_SYMBOL(copy_user_generic_string) * Output: * eax uncopied bytes or 0 if successful. */ -ENTRY(copy_user_enhanced_fast_string) +SYM_FUNC_START(copy_user_enhanced_fast_string) ASM_STAC cmpl $64,%edx jb .L_copy_short_string /* less then 64 bytes, avoid the costly 'rep' */ @@ -214,7 +214,7 @@ ENTRY(copy_user_enhanced_fast_string) .previous _ASM_EXTABLE_UA(1b, 12b) -ENDPROC(copy_user_enhanced_fast_string) +SYM_FUNC_END(copy_user_enhanced_fast_string) EXPORT_SYMBOL(copy_user_enhanced_fast_string) /* @@ -249,7 +249,7 @@ SYM_CODE_END(.Lcopy_user_handle_tail) * - Require 8-byte alignment when size is 8 bytes or larger. * - Require 4-byte alignment when size is 4 bytes. */ -ENTRY(__copy_user_nocache) +SYM_FUNC_START(__copy_user_nocache) ASM_STAC /* If size is less than 8 bytes, go to 4-byte copy */ @@ -388,5 +388,5 @@ ENTRY(__copy_user_nocache) _ASM_EXTABLE_UA(31b, .L_fixup_4b_copy) _ASM_EXTABLE_UA(40b, .L_fixup_1b_copy) _ASM_EXTABLE_UA(41b, .L_fixup_1b_copy) -ENDPROC(__copy_user_nocache) +SYM_FUNC_END(__copy_user_nocache) EXPORT_SYMBOL(__copy_user_nocache) diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S index a4a379e79259..3394a8ff7fd0 100644 --- a/arch/x86/lib/csum-copy_64.S +++ b/arch/x86/lib/csum-copy_64.S @@ -49,7 +49,7 @@ .endm -ENTRY(csum_partial_copy_generic) +SYM_FUNC_START(csum_partial_copy_generic) cmpl $3*64, %edx jle .Lignore @@ -225,4 +225,4 @@ ENTRY(csum_partial_copy_generic) jz .Lende movl $-EFAULT, (%rax) jmp .Lende -ENDPROC(csum_partial_copy_generic) +SYM_FUNC_END(csum_partial_copy_generic) diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index f9f59eb85635..c8a85b512796 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -36,7 +36,7 @@ #include .text -ENTRY(__get_user_1) +SYM_FUNC_START(__get_user_1) mov PER_CPU_VAR(current_task), %_ASM_DX cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user @@ -47,10 +47,10 @@ ENTRY(__get_user_1) xor %eax,%eax ASM_CLAC ret -ENDPROC(__get_user_1) +SYM_FUNC_END(__get_user_1) EXPORT_SYMBOL(__get_user_1) -ENTRY(__get_user_2) +SYM_FUNC_START(__get_user_2) add $1,%_ASM_AX jc bad_get_user mov PER_CPU_VAR(current_task), %_ASM_DX @@ -63,10 +63,10 @@ ENTRY(__get_user_2) xor %eax,%eax ASM_CLAC ret -ENDPROC(__get_user_2) +SYM_FUNC_END(__get_user_2) EXPORT_SYMBOL(__get_user_2) -ENTRY(__get_user_4) +SYM_FUNC_START(__get_user_4) add $3,%_ASM_AX jc bad_get_user mov PER_CPU_VAR(current_task), %_ASM_DX @@ -79,10 +79,10 @@ ENTRY(__get_user_4) xor %eax,%eax ASM_CLAC ret -ENDPROC(__get_user_4) +SYM_FUNC_END(__get_user_4) EXPORT_SYMBOL(__get_user_4) -ENTRY(__get_user_8) +SYM_FUNC_START(__get_user_8) #ifdef CONFIG_X86_64 add $7,%_ASM_AX jc bad_get_user @@ -111,7 +111,7 @@ ENTRY(__get_user_8) ASM_CLAC ret #endif -ENDPROC(__get_user_8) +SYM_FUNC_END(__get_user_8) EXPORT_SYMBOL(__get_user_8) diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S index a14f9939c365..dbf8cc97b7f5 100644 --- a/arch/x86/lib/hweight.S +++ b/arch/x86/lib/hweight.S @@ -8,7 +8,7 @@ * unsigned int __sw_hweight32(unsigned int w) * %rdi: w */ -ENTRY(__sw_hweight32) +SYM_FUNC_START(__sw_hweight32) #ifdef CONFIG_X86_64 movl %edi, %eax # w @@ -33,10 +33,10 @@ ENTRY(__sw_hweight32) shrl $24, %eax # w = w_tmp >> 24 __ASM_SIZE(pop,) %__ASM_REG(dx) ret -ENDPROC(__sw_hweight32) +SYM_FUNC_END(__sw_hweight32) EXPORT_SYMBOL(__sw_hweight32) -ENTRY(__sw_hweight64) +SYM_FUNC_START(__sw_hweight64) #ifdef CONFIG_X86_64 pushq %rdi pushq %rdx @@ -79,5 +79,5 @@ ENTRY(__sw_hweight64) popl %ecx ret #endif -ENDPROC(__sw_hweight64) +SYM_FUNC_END(__sw_hweight64) EXPORT_SYMBOL(__sw_hweight64) diff --git a/arch/x86/lib/iomap_copy_64.S b/arch/x86/lib/iomap_copy_64.S index a9bdf0805be0..cb5a1964506b 100644 --- a/arch/x86/lib/iomap_copy_64.S +++ b/arch/x86/lib/iomap_copy_64.S @@ -8,8 +8,8 @@ /* * override generic version in lib/iomap_copy.c */ -ENTRY(__iowrite32_copy) +SYM_FUNC_START(__iowrite32_copy) movl %edx,%ecx rep movsd ret -ENDPROC(__iowrite32_copy) +SYM_FUNC_END(__iowrite32_copy) diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 3265b21e86c0..56b243b14c3a 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -193,7 +193,7 @@ MCSAFE_TEST_CTL * Note that we only catch machine checks when reading the source addresses. * Writes to target are posted and don't generate machine checks. */ -ENTRY(__memcpy_mcsafe) +SYM_FUNC_START(__memcpy_mcsafe) cmpl $8, %edx /* Less than 8 bytes? Go to byte copy loop */ jb .L_no_whole_words @@ -260,7 +260,7 @@ ENTRY(__memcpy_mcsafe) xorl %eax, %eax .L_done: ret -ENDPROC(__memcpy_mcsafe) +SYM_FUNC_END(__memcpy_mcsafe) EXPORT_SYMBOL_GPL(__memcpy_mcsafe) .section .fixup, "ax" diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S index 50c1648311b3..337830d7a59c 100644 --- a/arch/x86/lib/memmove_64.S +++ b/arch/x86/lib/memmove_64.S @@ -27,7 +27,7 @@ .weak memmove SYM_FUNC_START_ALIAS(memmove) -ENTRY(__memmove) +SYM_FUNC_START(__memmove) /* Handle more 32 bytes in loop */ mov %rdi, %rax @@ -207,7 +207,7 @@ ENTRY(__memmove) movb %r11b, (%rdi) 13: retq -ENDPROC(__memmove) +SYM_FUNC_END(__memmove) SYM_FUNC_END_ALIAS(memmove) EXPORT_SYMBOL(__memmove) EXPORT_SYMBOL(memmove) diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S index 564abf9ecedb..9ff15ee404a4 100644 --- a/arch/x86/lib/memset_64.S +++ b/arch/x86/lib/memset_64.S @@ -20,7 +20,7 @@ * rax original destination */ SYM_FUNC_START_ALIAS(memset) -ENTRY(__memset) +SYM_FUNC_START(__memset) /* * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended * to use it when possible. If not available, use fast string instructions. @@ -43,7 +43,7 @@ ENTRY(__memset) rep stosb movq %r9,%rax ret -ENDPROC(__memset) +SYM_FUNC_END(__memset) SYM_FUNC_END_ALIAS(memset) EXPORT_SYMBOL(memset) EXPORT_SYMBOL(__memset) diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S index ed33cbab3958..a2b9caa5274c 100644 --- a/arch/x86/lib/msr-reg.S +++ b/arch/x86/lib/msr-reg.S @@ -12,7 +12,7 @@ * */ .macro op_safe_regs op -ENTRY(\op\()_safe_regs) +SYM_FUNC_START(\op\()_safe_regs) pushq %rbx pushq %r12 movq %rdi, %r10 /* Save pointer */ @@ -41,13 +41,13 @@ ENTRY(\op\()_safe_regs) jmp 2b _ASM_EXTABLE(1b, 3b) -ENDPROC(\op\()_safe_regs) +SYM_FUNC_END(\op\()_safe_regs) .endm #else /* X86_32 */ .macro op_safe_regs op -ENTRY(\op\()_safe_regs) +SYM_FUNC_START(\op\()_safe_regs) pushl %ebx pushl %ebp pushl %esi @@ -83,7 +83,7 @@ ENTRY(\op\()_safe_regs) jmp 2b _ASM_EXTABLE(1b, 3b) -ENDPROC(\op\()_safe_regs) +SYM_FUNC_END(\op\()_safe_regs) .endm #endif diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S index a9391d772c81..7c7c92db8497 100644 --- a/arch/x86/lib/putuser.S +++ b/arch/x86/lib/putuser.S @@ -34,7 +34,7 @@ #define ENTER mov PER_CPU_VAR(current_task), %_ASM_BX .text -ENTRY(__put_user_1) +SYM_FUNC_START(__put_user_1) ENTER cmp TASK_addr_limit(%_ASM_BX),%_ASM_CX jae .Lbad_put_user @@ -43,10 +43,10 @@ ENTRY(__put_user_1) xor %eax,%eax ASM_CLAC ret -ENDPROC(__put_user_1) +SYM_FUNC_END(__put_user_1) EXPORT_SYMBOL(__put_user_1) -ENTRY(__put_user_2) +SYM_FUNC_START(__put_user_2) ENTER mov TASK_addr_limit(%_ASM_BX),%_ASM_BX sub $1,%_ASM_BX @@ -57,10 +57,10 @@ ENTRY(__put_user_2) xor %eax,%eax ASM_CLAC ret -ENDPROC(__put_user_2) +SYM_FUNC_END(__put_user_2) EXPORT_SYMBOL(__put_user_2) -ENTRY(__put_user_4) +SYM_FUNC_START(__put_user_4) ENTER mov TASK_addr_limit(%_ASM_BX),%_ASM_BX sub $3,%_ASM_BX @@ -71,10 +71,10 @@ ENTRY(__put_user_4) xor %eax,%eax ASM_CLAC ret -ENDPROC(__put_user_4) +SYM_FUNC_END(__put_user_4) EXPORT_SYMBOL(__put_user_4) -ENTRY(__put_user_8) +SYM_FUNC_START(__put_user_8) ENTER mov TASK_addr_limit(%_ASM_BX),%_ASM_BX sub $7,%_ASM_BX @@ -88,7 +88,7 @@ ENTRY(__put_user_8) xor %eax,%eax ASM_CLAC RET -ENDPROC(__put_user_8) +SYM_FUNC_END(__put_user_8) EXPORT_SYMBOL(__put_user_8) SYM_CODE_START_LOCAL(.Lbad_put_user_clac) diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index c909961e678a..363ec132df7e 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -11,11 +11,11 @@ .macro THUNK reg .section .text.__x86.indirect_thunk -ENTRY(__x86_indirect_thunk_\reg) +SYM_FUNC_START(__x86_indirect_thunk_\reg) CFI_STARTPROC JMP_NOSPEC %\reg CFI_ENDPROC -ENDPROC(__x86_indirect_thunk_\reg) +SYM_FUNC_END(__x86_indirect_thunk_\reg) .endm /* diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S index 6d71481a1e70..106ead05bbe3 100644 --- a/arch/x86/mm/mem_encrypt_boot.S +++ b/arch/x86/mm/mem_encrypt_boot.S @@ -16,7 +16,7 @@ .text .code64 -ENTRY(sme_encrypt_execute) +SYM_FUNC_START(sme_encrypt_execute) /* * Entry parameters: @@ -66,9 +66,9 @@ ENTRY(sme_encrypt_execute) pop %rbp ret -ENDPROC(sme_encrypt_execute) +SYM_FUNC_END(sme_encrypt_execute) -ENTRY(__enc_copy) +SYM_FUNC_START(__enc_copy) /* * Routine used to encrypt memory in place. * This routine must be run outside of the kernel proper since @@ -153,4 +153,4 @@ ENTRY(__enc_copy) ret .L__enc_copy_end: -ENDPROC(__enc_copy) +SYM_FUNC_END(__enc_copy) diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S index 74628ec78f29..b1d2313fe3bf 100644 --- a/arch/x86/platform/efi/efi_stub_64.S +++ b/arch/x86/platform/efi/efi_stub_64.S @@ -39,7 +39,7 @@ mov %rsi, %cr0; \ mov (%rsp), %rsp -ENTRY(efi_call) +SYM_FUNC_START(efi_call) pushq %rbp movq %rsp, %rbp SAVE_XMM @@ -55,4 +55,4 @@ ENTRY(efi_call) RESTORE_XMM popq %rbp ret -ENDPROC(efi_call) +SYM_FUNC_END(efi_call) diff --git a/arch/x86/platform/efi/efi_thunk_64.S b/arch/x86/platform/efi/efi_thunk_64.S index d677a7eb2d0a..3189f1394701 100644 --- a/arch/x86/platform/efi/efi_thunk_64.S +++ b/arch/x86/platform/efi/efi_thunk_64.S @@ -25,7 +25,7 @@ .text .code64 -ENTRY(efi64_thunk) +SYM_FUNC_START(efi64_thunk) push %rbp push %rbx @@ -60,7 +60,7 @@ ENTRY(efi64_thunk) pop %rbx pop %rbp retq -ENDPROC(efi64_thunk) +SYM_FUNC_END(efi64_thunk) /* * We run this function from the 1:1 mapping. diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S index 4057cd5af7e2..7918b8415f13 100644 --- a/arch/x86/power/hibernate_asm_64.S +++ b/arch/x86/power/hibernate_asm_64.S @@ -22,7 +22,7 @@ #include #include -ENTRY(swsusp_arch_suspend) +SYM_FUNC_START(swsusp_arch_suspend) movq $saved_context, %rax movq %rsp, pt_regs_sp(%rax) movq %rbp, pt_regs_bp(%rax) @@ -50,7 +50,7 @@ ENTRY(swsusp_arch_suspend) call swsusp_save FRAME_END ret -ENDPROC(swsusp_arch_suspend) +SYM_FUNC_END(swsusp_arch_suspend) SYM_CODE_START(restore_image) /* prepare to jump to the image kernel */ @@ -102,7 +102,7 @@ SYM_CODE_END(core_restore_code) /* code below belongs to the image kernel */ .align PAGE_SIZE -ENTRY(restore_registers) +SYM_FUNC_START(restore_registers) /* go back to the original page tables */ movq %r9, %cr3 @@ -144,4 +144,4 @@ ENTRY(restore_registers) movq %rax, in_suspend(%rip) ret -ENDPROC(restore_registers) +SYM_FUNC_END(restore_registers) diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index be104eef80be..508fe204520b 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -19,7 +19,7 @@ * event status with one and operation. If there are pending events, * then enter the hypervisor to get them handled. */ -ENTRY(xen_irq_enable_direct) +SYM_FUNC_START(xen_irq_enable_direct) FRAME_BEGIN /* Unmask events */ movb $0, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask @@ -38,17 +38,17 @@ ENTRY(xen_irq_enable_direct) 1: FRAME_END ret - ENDPROC(xen_irq_enable_direct) +SYM_FUNC_END(xen_irq_enable_direct) /* * Disabling events is simply a matter of making the event mask * non-zero. */ -ENTRY(xen_irq_disable_direct) +SYM_FUNC_START(xen_irq_disable_direct) movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask ret -ENDPROC(xen_irq_disable_direct) +SYM_FUNC_END(xen_irq_disable_direct) /* * (xen_)save_fl is used to get the current interrupt enable status. @@ -59,12 +59,12 @@ ENDPROC(xen_irq_disable_direct) * undefined. We need to toggle the state of the bit, because Xen and * x86 use opposite senses (mask vs enable). */ -ENTRY(xen_save_fl_direct) +SYM_FUNC_START(xen_save_fl_direct) testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask setz %ah addb %ah, %ah ret - ENDPROC(xen_save_fl_direct) +SYM_FUNC_END(xen_save_fl_direct) /* @@ -74,7 +74,7 @@ ENTRY(xen_save_fl_direct) * interrupt mask state, it checks for unmasked pending events and * enters the hypervisor to get them delivered if so. */ -ENTRY(xen_restore_fl_direct) +SYM_FUNC_START(xen_restore_fl_direct) FRAME_BEGIN #ifdef CONFIG_X86_64 testw $X86_EFLAGS_IF, %di @@ -95,14 +95,14 @@ ENTRY(xen_restore_fl_direct) 1: FRAME_END ret - ENDPROC(xen_restore_fl_direct) +SYM_FUNC_END(xen_restore_fl_direct) /* * Force an event check by making a hypercall, but preserve regs * before making the call. */ -ENTRY(check_events) +SYM_FUNC_START(check_events) FRAME_BEGIN #ifdef CONFIG_X86_32 push %eax @@ -135,19 +135,19 @@ ENTRY(check_events) #endif FRAME_END ret -ENDPROC(check_events) +SYM_FUNC_END(check_events) -ENTRY(xen_read_cr2) +SYM_FUNC_START(xen_read_cr2) FRAME_BEGIN _ASM_MOV PER_CPU_VAR(xen_vcpu), %_ASM_AX _ASM_MOV XEN_vcpu_info_arch_cr2(%_ASM_AX), %_ASM_AX FRAME_END ret - ENDPROC(xen_read_cr2); +SYM_FUNC_END(xen_read_cr2); -ENTRY(xen_read_cr2_direct) +SYM_FUNC_START(xen_read_cr2_direct) FRAME_BEGIN _ASM_MOV PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_arch_cr2, %_ASM_AX FRAME_END ret - ENDPROC(xen_read_cr2_direct); +SYM_FUNC_END(xen_read_cr2_direct); diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S index 0060120f51dd..0a0fd168683a 100644 --- a/arch/x86/xen/xen-asm_64.S +++ b/arch/x86/xen/xen-asm_64.S @@ -126,7 +126,7 @@ SYM_CODE_END(xen_sysret64) */ /* Normal 64-bit system call target */ -ENTRY(xen_syscall_target) +SYM_FUNC_START(xen_syscall_target) popq %rcx popq %r11 @@ -139,12 +139,12 @@ ENTRY(xen_syscall_target) movq $__USER_CS, 1*8(%rsp) jmp entry_SYSCALL_64_after_hwframe -ENDPROC(xen_syscall_target) +SYM_FUNC_END(xen_syscall_target) #ifdef CONFIG_IA32_EMULATION /* 32-bit compat syscall target */ -ENTRY(xen_syscall32_target) +SYM_FUNC_START(xen_syscall32_target) popq %rcx popq %r11 @@ -157,25 +157,25 @@ ENTRY(xen_syscall32_target) movq $__USER32_CS, 1*8(%rsp) jmp entry_SYSCALL_compat_after_hwframe -ENDPROC(xen_syscall32_target) +SYM_FUNC_END(xen_syscall32_target) /* 32-bit compat sysenter target */ -ENTRY(xen_sysenter_target) +SYM_FUNC_START(xen_sysenter_target) mov 0*8(%rsp), %rcx mov 1*8(%rsp), %r11 mov 5*8(%rsp), %rsp jmp entry_SYSENTER_compat -ENDPROC(xen_sysenter_target) +SYM_FUNC_END(xen_sysenter_target) #else /* !CONFIG_IA32_EMULATION */ SYM_FUNC_START_ALIAS(xen_syscall32_target) -ENTRY(xen_sysenter_target) +SYM_FUNC_START(xen_sysenter_target) lea 16(%rsp), %rsp /* strip %rcx, %r11 */ mov $-ENOSYS, %rax pushq $0 jmp hypercall_iret -ENDPROC(xen_sysenter_target) +SYM_FUNC_END(xen_sysenter_target) SYM_FUNC_END_ALIAS(xen_syscall32_target) #endif /* CONFIG_IA32_EMULATION */ diff --git a/include/linux/linkage.h b/include/linux/linkage.h index cb1108dde385..19f3d796ab5b 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -114,11 +114,13 @@ #endif #endif +#ifndef CONFIG_X86_64 #ifndef ENTRY /* deprecated, use SYM_FUNC_START */ #define ENTRY(name) \ SYM_FUNC_START(name) #endif +#endif /* CONFIG_X86_64 */ #endif /* LINKER_SCRIPT */ #ifndef WEAK @@ -133,6 +135,7 @@ .size name, .-name #endif +#ifndef CONFIG_X86_64 /* If symbol 'name' is treated as a subroutine (gets called, and returns) * then please use ENDPROC to mark 'name' as STT_FUNC for the benefit of * static analysis tools such as stack depth analyzer. @@ -142,6 +145,7 @@ #define ENDPROC(name) \ SYM_FUNC_END(name) #endif +#endif /* CONFIG_X86_64 */ /* === generic annotations === */ -- cgit v1.2.3-71-gd317 From 5e63306f1629527799e34a9814dd8035df6ca854 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 11 Oct 2019 13:51:06 +0200 Subject: x86/asm/32: Change all ENTRY+END to SYM_CODE_* Change all assembly code which is marked using END (and not ENDPROC) to appropriate new markings SYM_CODE_START and SYM_CODE_END. And since the last user of END on X86 is gone now, make sure that END is not defined there. Signed-off-by: Jiri Slaby Signed-off-by: Borislav Petkov Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Boris Ostrovsky Cc: Herbert Xu Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Josh Poimboeuf Cc: linux-arch@vger.kernel.org Cc: Mark Rutland Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: "Steven Rostedt (VMware)" Cc: Thomas Gleixner Cc: x86-ml Link: https://lkml.kernel.org/r/20191011115108.12392-27-jslaby@suse.cz --- arch/x86/entry/entry_32.S | 104 ++++++++++++++++++++++---------------------- arch/x86/kernel/ftrace_32.S | 8 ++-- include/linux/linkage.h | 2 + 3 files changed, 58 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 64fe7aa50ad2..0ecc12fcfc05 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -709,7 +709,7 @@ * %eax: prev task * %edx: next task */ -ENTRY(__switch_to_asm) +SYM_CODE_START(__switch_to_asm) /* * Save callee-saved registers * This must match the order in struct inactive_task_frame @@ -748,7 +748,7 @@ ENTRY(__switch_to_asm) popl %ebp jmp __switch_to -END(__switch_to_asm) +SYM_CODE_END(__switch_to_asm) /* * The unwinder expects the last frame on the stack to always be at the same @@ -774,7 +774,7 @@ ENDPROC(schedule_tail_wrapper) * ebx: kernel thread func (NULL for user thread) * edi: kernel thread arg */ -ENTRY(ret_from_fork) +SYM_CODE_START(ret_from_fork) call schedule_tail_wrapper testl %ebx, %ebx @@ -797,7 +797,7 @@ ENTRY(ret_from_fork) */ movl $0, PT_EAX(%esp) jmp 2b -END(ret_from_fork) +SYM_CODE_END(ret_from_fork) /* * Return to user mode is not as complex as all this looks, @@ -1161,7 +1161,7 @@ ENDPROC(entry_INT80_32) * We pack 1 stub into every 8-byte block. */ .align 8 -ENTRY(irq_entries_start) +SYM_CODE_START(irq_entries_start) vector=FIRST_EXTERNAL_VECTOR .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR) pushl $(~vector+0x80) /* Note: always in signed byte range */ @@ -1169,11 +1169,11 @@ ENTRY(irq_entries_start) jmp common_interrupt .align 8 .endr -END(irq_entries_start) +SYM_CODE_END(irq_entries_start) #ifdef CONFIG_X86_LOCAL_APIC .align 8 -ENTRY(spurious_entries_start) +SYM_CODE_START(spurious_entries_start) vector=FIRST_SYSTEM_VECTOR .rept (NR_VECTORS - FIRST_SYSTEM_VECTOR) pushl $(~vector+0x80) /* Note: always in signed byte range */ @@ -1181,7 +1181,7 @@ ENTRY(spurious_entries_start) jmp common_spurious .align 8 .endr -END(spurious_entries_start) +SYM_CODE_END(spurious_entries_start) SYM_CODE_START_LOCAL(common_spurious) ASM_CLAC @@ -1230,14 +1230,14 @@ ENDPROC(name) /* The include is where all of the SMP etc. interrupts come from */ #include -ENTRY(coprocessor_error) +SYM_CODE_START(coprocessor_error) ASM_CLAC pushl $0 pushl $do_coprocessor_error jmp common_exception -END(coprocessor_error) +SYM_CODE_END(coprocessor_error) -ENTRY(simd_coprocessor_error) +SYM_CODE_START(simd_coprocessor_error) ASM_CLAC pushl $0 #ifdef CONFIG_X86_INVD_BUG @@ -1249,96 +1249,96 @@ ENTRY(simd_coprocessor_error) pushl $do_simd_coprocessor_error #endif jmp common_exception -END(simd_coprocessor_error) +SYM_CODE_END(simd_coprocessor_error) -ENTRY(device_not_available) +SYM_CODE_START(device_not_available) ASM_CLAC pushl $-1 # mark this as an int pushl $do_device_not_available jmp common_exception -END(device_not_available) +SYM_CODE_END(device_not_available) #ifdef CONFIG_PARAVIRT -ENTRY(native_iret) +SYM_CODE_START(native_iret) iret _ASM_EXTABLE(native_iret, iret_exc) -END(native_iret) +SYM_CODE_END(native_iret) #endif -ENTRY(overflow) +SYM_CODE_START(overflow) ASM_CLAC pushl $0 pushl $do_overflow jmp common_exception -END(overflow) +SYM_CODE_END(overflow) -ENTRY(bounds) +SYM_CODE_START(bounds) ASM_CLAC pushl $0 pushl $do_bounds jmp common_exception -END(bounds) +SYM_CODE_END(bounds) -ENTRY(invalid_op) +SYM_CODE_START(invalid_op) ASM_CLAC pushl $0 pushl $do_invalid_op jmp common_exception -END(invalid_op) +SYM_CODE_END(invalid_op) -ENTRY(coprocessor_segment_overrun) +SYM_CODE_START(coprocessor_segment_overrun) ASM_CLAC pushl $0 pushl $do_coprocessor_segment_overrun jmp common_exception -END(coprocessor_segment_overrun) +SYM_CODE_END(coprocessor_segment_overrun) -ENTRY(invalid_TSS) +SYM_CODE_START(invalid_TSS) ASM_CLAC pushl $do_invalid_TSS jmp common_exception -END(invalid_TSS) +SYM_CODE_END(invalid_TSS) -ENTRY(segment_not_present) +SYM_CODE_START(segment_not_present) ASM_CLAC pushl $do_segment_not_present jmp common_exception -END(segment_not_present) +SYM_CODE_END(segment_not_present) -ENTRY(stack_segment) +SYM_CODE_START(stack_segment) ASM_CLAC pushl $do_stack_segment jmp common_exception -END(stack_segment) +SYM_CODE_END(stack_segment) -ENTRY(alignment_check) +SYM_CODE_START(alignment_check) ASM_CLAC pushl $do_alignment_check jmp common_exception -END(alignment_check) +SYM_CODE_END(alignment_check) -ENTRY(divide_error) +SYM_CODE_START(divide_error) ASM_CLAC pushl $0 # no error code pushl $do_divide_error jmp common_exception -END(divide_error) +SYM_CODE_END(divide_error) #ifdef CONFIG_X86_MCE -ENTRY(machine_check) +SYM_CODE_START(machine_check) ASM_CLAC pushl $0 pushl machine_check_vector jmp common_exception -END(machine_check) +SYM_CODE_END(machine_check) #endif -ENTRY(spurious_interrupt_bug) +SYM_CODE_START(spurious_interrupt_bug) ASM_CLAC pushl $0 pushl $do_spurious_interrupt_bug jmp common_exception -END(spurious_interrupt_bug) +SYM_CODE_END(spurious_interrupt_bug) #ifdef CONFIG_XEN_PV ENTRY(xen_hypervisor_callback) @@ -1442,11 +1442,11 @@ BUILD_INTERRUPT3(hv_stimer0_callback_vector, HYPERV_STIMER0_VECTOR, #endif /* CONFIG_HYPERV */ -ENTRY(page_fault) +SYM_CODE_START(page_fault) ASM_CLAC pushl $do_page_fault jmp common_exception_read_cr2 -END(page_fault) +SYM_CODE_END(page_fault) SYM_CODE_START_LOCAL_NOALIGN(common_exception_read_cr2) /* the function address is in %gs's slot on the stack */ @@ -1495,7 +1495,7 @@ SYM_CODE_START_LOCAL_NOALIGN(common_exception) jmp ret_from_exception SYM_CODE_END(common_exception) -ENTRY(debug) +SYM_CODE_START(debug) /* * Entry from sysenter is now handled in common_exception */ @@ -1503,7 +1503,7 @@ ENTRY(debug) pushl $-1 # mark this as an int pushl $do_debug jmp common_exception -END(debug) +SYM_CODE_END(debug) /* * NMI is doubly nasty. It can happen on the first instruction of @@ -1512,7 +1512,7 @@ END(debug) * switched stacks. We handle both conditions by simply checking whether we * interrupted kernel code running on the SYSENTER stack. */ -ENTRY(nmi) +SYM_CODE_START(nmi) ASM_CLAC #ifdef CONFIG_X86_ESPFIX32 @@ -1577,9 +1577,9 @@ ENTRY(nmi) lss 12+4(%esp), %esp # back to espfix stack jmp .Lirq_return #endif -END(nmi) +SYM_CODE_END(nmi) -ENTRY(int3) +SYM_CODE_START(int3) ASM_CLAC pushl $-1 # mark this as an int @@ -1590,22 +1590,22 @@ ENTRY(int3) movl %esp, %eax # pt_regs pointer call do_int3 jmp ret_from_exception -END(int3) +SYM_CODE_END(int3) -ENTRY(general_protection) +SYM_CODE_START(general_protection) pushl $do_general_protection jmp common_exception -END(general_protection) +SYM_CODE_END(general_protection) #ifdef CONFIG_KVM_GUEST -ENTRY(async_page_fault) +SYM_CODE_START(async_page_fault) ASM_CLAC pushl $do_async_page_fault jmp common_exception_read_cr2 -END(async_page_fault) +SYM_CODE_END(async_page_fault) #endif -ENTRY(rewind_stack_do_exit) +SYM_CODE_START(rewind_stack_do_exit) /* Prevent any naive code from trying to unwind to our caller. */ xorl %ebp, %ebp @@ -1614,4 +1614,4 @@ ENTRY(rewind_stack_do_exit) call do_exit 1: jmp 1b -END(rewind_stack_do_exit) +SYM_CODE_END(rewind_stack_do_exit) diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S index a43ed4c0402d..b4f495bbd5a1 100644 --- a/arch/x86/kernel/ftrace_32.S +++ b/arch/x86/kernel/ftrace_32.S @@ -25,7 +25,7 @@ SYM_FUNC_START(function_hook) ret SYM_FUNC_END(function_hook) -ENTRY(ftrace_caller) +SYM_CODE_START(ftrace_caller) #ifdef CONFIG_FRAME_POINTER /* @@ -87,7 +87,7 @@ ftrace_graph_call: /* This is weak to keep gas from relaxing the jumps */ WEAK(ftrace_stub) ret -END(ftrace_caller) +SYM_CODE_END(ftrace_caller) SYM_CODE_START(ftrace_regs_caller) /* @@ -166,7 +166,7 @@ SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL) SYM_CODE_END(ftrace_regs_caller) #ifdef CONFIG_FUNCTION_GRAPH_TRACER -ENTRY(ftrace_graph_caller) +SYM_CODE_START(ftrace_graph_caller) pushl %eax pushl %ecx pushl %edx @@ -180,7 +180,7 @@ ENTRY(ftrace_graph_caller) popl %ecx popl %eax ret -END(ftrace_graph_caller) +SYM_CODE_END(ftrace_graph_caller) .globl return_to_handler return_to_handler: diff --git a/include/linux/linkage.h b/include/linux/linkage.h index 19f3d796ab5b..5ffcf72c8f87 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -129,11 +129,13 @@ SYM_FUNC_START_WEAK(name) #endif +#ifndef CONFIG_X86 #ifndef END /* deprecated, use SYM_FUNC_END, SYM_DATA_END, or SYM_END */ #define END(name) \ .size name, .-name #endif +#endif /* CONFIG_X86 */ #ifndef CONFIG_X86_64 /* If symbol 'name' is treated as a subroutine (gets called, and returns) -- cgit v1.2.3-71-gd317 From 6d685e5318e51b843ca50adeca50dc6300bf2cbb Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 11 Oct 2019 13:51:07 +0200 Subject: x86/asm/32: Change all ENTRY+ENDPROC to SYM_FUNC_* These are all functions which are invoked from elsewhere, so annotate them as global using the new SYM_FUNC_START and their ENDPROC's by SYM_FUNC_END. Now, ENTRY/ENDPROC can be forced to be undefined on X86, so do so. Signed-off-by: Jiri Slaby Signed-off-by: Borislav Petkov Cc: Allison Randal Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Andy Shevchenko Cc: Ard Biesheuvel Cc: Bill Metzenthen Cc: Boris Ostrovsky Cc: Darren Hart Cc: "David S. Miller" Cc: Greg Kroah-Hartman Cc: Herbert Xu Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: linux-arch@vger.kernel.org Cc: linux-crypto@vger.kernel.org Cc: linux-efi Cc: linux-efi@vger.kernel.org Cc: linux-pm@vger.kernel.org Cc: Mark Rutland Cc: Matt Fleming Cc: Pavel Machek Cc: platform-driver-x86@vger.kernel.org Cc: "Rafael J. Wysocki" Cc: Thomas Gleixner Cc: Will Deacon Cc: x86-ml Link: https://lkml.kernel.org/r/20191011115108.12392-28-jslaby@suse.cz --- arch/x86/boot/compressed/efi_stub_32.S | 4 ++-- arch/x86/boot/compressed/head_32.S | 12 +++++------ arch/x86/crypto/serpent-sse2-i586-asm_32.S | 8 ++++---- arch/x86/crypto/twofish-i586-asm_32.S | 8 ++++---- arch/x86/entry/entry_32.S | 24 +++++++++++----------- arch/x86/kernel/head_32.S | 16 +++++++-------- arch/x86/lib/atomic64_386_32.S | 4 ++-- arch/x86/lib/atomic64_cx8_32.S | 32 +++++++++++++++--------------- arch/x86/lib/checksum_32.S | 8 ++++---- arch/x86/math-emu/div_Xsig.S | 4 ++-- arch/x86/math-emu/div_small.S | 4 ++-- arch/x86/math-emu/mul_Xsig.S | 12 +++++------ arch/x86/math-emu/polynom_Xsig.S | 4 ++-- arch/x86/math-emu/reg_norm.S | 8 ++++---- arch/x86/math-emu/reg_round.S | 4 ++-- arch/x86/math-emu/reg_u_add.S | 4 ++-- arch/x86/math-emu/reg_u_div.S | 4 ++-- arch/x86/math-emu/reg_u_mul.S | 4 ++-- arch/x86/math-emu/reg_u_sub.S | 4 ++-- arch/x86/math-emu/round_Xsig.S | 8 ++++---- arch/x86/math-emu/shr_Xsig.S | 4 ++-- arch/x86/math-emu/wm_shrx.S | 8 ++++---- arch/x86/math-emu/wm_sqrt.S | 4 ++-- arch/x86/platform/efi/efi_stub_32.S | 4 ++-- arch/x86/power/hibernate_asm_32.S | 8 ++++---- include/linux/linkage.h | 8 ++------ 26 files changed, 104 insertions(+), 108 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/boot/compressed/efi_stub_32.S b/arch/x86/boot/compressed/efi_stub_32.S index 257e341fd2c8..ed6c351d34ed 100644 --- a/arch/x86/boot/compressed/efi_stub_32.S +++ b/arch/x86/boot/compressed/efi_stub_32.S @@ -24,7 +24,7 @@ */ .text -ENTRY(efi_call_phys) +SYM_FUNC_START(efi_call_phys) /* * 0. The function can only be called in Linux kernel. So CS has been * set to 0x0010, DS and SS have been set to 0x0018. In EFI, I found @@ -77,7 +77,7 @@ ENTRY(efi_call_phys) movl saved_return_addr(%edx), %ecx pushl %ecx ret -ENDPROC(efi_call_phys) +SYM_FUNC_END(efi_call_phys) .previous .data diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index f9e2a80bd699..f2dfd6d083ef 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -61,7 +61,7 @@ .hidden _egot __HEAD -ENTRY(startup_32) +SYM_FUNC_START(startup_32) cld /* * Test KEEP_SEGMENTS flag to see if the bootloader is asking @@ -142,14 +142,14 @@ ENTRY(startup_32) */ leal .Lrelocated(%ebx), %eax jmp *%eax -ENDPROC(startup_32) +SYM_FUNC_END(startup_32) #ifdef CONFIG_EFI_STUB /* * We don't need the return address, so set up the stack so efi_main() can find * its arguments. */ -ENTRY(efi_pe_entry) +SYM_FUNC_START(efi_pe_entry) add $0x4, %esp call 1f @@ -174,9 +174,9 @@ ENTRY(efi_pe_entry) pushl %eax pushl %ecx jmp 2f /* Skip efi_config initialization */ -ENDPROC(efi_pe_entry) +SYM_FUNC_END(efi_pe_entry) -ENTRY(efi32_stub_entry) +SYM_FUNC_START(efi32_stub_entry) add $0x4, %esp popl %ecx popl %edx @@ -205,7 +205,7 @@ fail: movl BP_code32_start(%esi), %eax leal startup_32(%eax), %eax jmp *%eax -ENDPROC(efi32_stub_entry) +SYM_FUNC_END(efi32_stub_entry) #endif .text diff --git a/arch/x86/crypto/serpent-sse2-i586-asm_32.S b/arch/x86/crypto/serpent-sse2-i586-asm_32.S index e5c4a4690ca9..6379b99cb722 100644 --- a/arch/x86/crypto/serpent-sse2-i586-asm_32.S +++ b/arch/x86/crypto/serpent-sse2-i586-asm_32.S @@ -497,7 +497,7 @@ pxor t0, x3; \ movdqu x3, (3*4*4)(out); -ENTRY(__serpent_enc_blk_4way) +SYM_FUNC_START(__serpent_enc_blk_4way) /* input: * arg_ctx(%esp): ctx, CTX * arg_dst(%esp): dst @@ -559,9 +559,9 @@ ENTRY(__serpent_enc_blk_4way) xor_blocks(%eax, RA, RB, RC, RD, RT0, RT1, RE); ret; -ENDPROC(__serpent_enc_blk_4way) +SYM_FUNC_END(__serpent_enc_blk_4way) -ENTRY(serpent_dec_blk_4way) +SYM_FUNC_START(serpent_dec_blk_4way) /* input: * arg_ctx(%esp): ctx, CTX * arg_dst(%esp): dst @@ -613,4 +613,4 @@ ENTRY(serpent_dec_blk_4way) write_blocks(%eax, RC, RD, RB, RE, RT0, RT1, RA); ret; -ENDPROC(serpent_dec_blk_4way) +SYM_FUNC_END(serpent_dec_blk_4way) diff --git a/arch/x86/crypto/twofish-i586-asm_32.S b/arch/x86/crypto/twofish-i586-asm_32.S index 290cc4e9a6fe..a6f09e4f2e46 100644 --- a/arch/x86/crypto/twofish-i586-asm_32.S +++ b/arch/x86/crypto/twofish-i586-asm_32.S @@ -207,7 +207,7 @@ xor %esi, d ## D;\ ror $1, d ## D; -ENTRY(twofish_enc_blk) +SYM_FUNC_START(twofish_enc_blk) push %ebp /* save registers according to calling convention*/ push %ebx push %esi @@ -261,9 +261,9 @@ ENTRY(twofish_enc_blk) pop %ebp mov $1, %eax ret -ENDPROC(twofish_enc_blk) +SYM_FUNC_END(twofish_enc_blk) -ENTRY(twofish_dec_blk) +SYM_FUNC_START(twofish_dec_blk) push %ebp /* save registers according to calling convention*/ push %ebx push %esi @@ -318,4 +318,4 @@ ENTRY(twofish_dec_blk) pop %ebp mov $1, %eax ret -ENDPROC(twofish_dec_blk) +SYM_FUNC_END(twofish_dec_blk) diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 0ecc12fcfc05..a987b62fc591 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -757,7 +757,7 @@ SYM_CODE_END(__switch_to_asm) * asmlinkage function so its argument has to be pushed on the stack. This * wrapper creates a proper "end of stack" frame header before the call. */ -ENTRY(schedule_tail_wrapper) +SYM_FUNC_START(schedule_tail_wrapper) FRAME_BEGIN pushl %eax @@ -766,7 +766,7 @@ ENTRY(schedule_tail_wrapper) FRAME_END ret -ENDPROC(schedule_tail_wrapper) +SYM_FUNC_END(schedule_tail_wrapper) /* * A newly forked process directly context switches into this address. * @@ -885,7 +885,7 @@ SYM_CODE_END(xen_sysenter_target) * ebp user stack * 0(%ebp) arg6 */ -ENTRY(entry_SYSENTER_32) +SYM_FUNC_START(entry_SYSENTER_32) /* * On entry-stack with all userspace-regs live - save and * restore eflags and %eax to use it as scratch-reg for the cr3 @@ -1013,7 +1013,7 @@ ENTRY(entry_SYSENTER_32) popfl jmp .Lsysenter_flags_fixed SYM_ENTRY(__end_SYSENTER_singlestep_region, SYM_L_GLOBAL, SYM_A_NONE) -ENDPROC(entry_SYSENTER_32) +SYM_FUNC_END(entry_SYSENTER_32) /* * 32-bit legacy system call entry. @@ -1043,7 +1043,7 @@ ENDPROC(entry_SYSENTER_32) * edi arg5 * ebp arg6 */ -ENTRY(entry_INT80_32) +SYM_FUNC_START(entry_INT80_32) ASM_CLAC pushl %eax /* pt_regs->orig_ax */ @@ -1120,7 +1120,7 @@ SYM_CODE_START(iret_exc) SYM_CODE_END(iret_exc) .previous _ASM_EXTABLE(.Lirq_return, iret_exc) -ENDPROC(entry_INT80_32) +SYM_FUNC_END(entry_INT80_32) .macro FIXUP_ESPFIX_STACK /* @@ -1213,7 +1213,7 @@ SYM_CODE_START_LOCAL(common_interrupt) SYM_CODE_END(common_interrupt) #define BUILD_INTERRUPT3(name, nr, fn) \ -ENTRY(name) \ +SYM_FUNC_START(name) \ ASM_CLAC; \ pushl $~(nr); \ SAVE_ALL switch_stacks=1; \ @@ -1222,7 +1222,7 @@ ENTRY(name) \ movl %esp, %eax; \ call fn; \ jmp ret_from_intr; \ -ENDPROC(name) +SYM_FUNC_END(name) #define BUILD_INTERRUPT(name, nr) \ BUILD_INTERRUPT3(name, nr, smp_##name); \ @@ -1341,7 +1341,7 @@ SYM_CODE_START(spurious_interrupt_bug) SYM_CODE_END(spurious_interrupt_bug) #ifdef CONFIG_XEN_PV -ENTRY(xen_hypervisor_callback) +SYM_FUNC_START(xen_hypervisor_callback) pushl $-1 /* orig_ax = -1 => not a system call */ SAVE_ALL ENCODE_FRAME_POINTER @@ -1369,7 +1369,7 @@ SYM_INNER_LABEL_ALIGN(xen_do_upcall, SYM_L_GLOBAL) call xen_maybe_preempt_hcall #endif jmp ret_from_intr -ENDPROC(xen_hypervisor_callback) +SYM_FUNC_END(xen_hypervisor_callback) /* * Hypervisor uses this for application faults while it executes. @@ -1383,7 +1383,7 @@ ENDPROC(xen_hypervisor_callback) * to pop the stack frame we end up in an infinite loop of failsafe callbacks. * We distinguish between categories by maintaining a status value in EAX. */ -ENTRY(xen_failsafe_callback) +SYM_FUNC_START(xen_failsafe_callback) pushl %eax movl $1, %eax 1: mov 4(%esp), %ds @@ -1420,7 +1420,7 @@ ENTRY(xen_failsafe_callback) _ASM_EXTABLE(2b, 7b) _ASM_EXTABLE(3b, 8b) _ASM_EXTABLE(4b, 9b) -ENDPROC(xen_failsafe_callback) +SYM_FUNC_END(xen_failsafe_callback) #endif /* CONFIG_XEN_PV */ #ifdef CONFIG_XEN_PVHVM diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 7029bbaccc41..ea24aa5465fd 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -180,12 +180,12 @@ SYM_CODE_END(startup_32) * up already except stack. We just set up stack here. Then call * start_secondary(). */ -ENTRY(start_cpu0) +SYM_FUNC_START(start_cpu0) movl initial_stack, %ecx movl %ecx, %esp call *(initial_code) 1: jmp 1b -ENDPROC(start_cpu0) +SYM_FUNC_END(start_cpu0) #endif /* @@ -196,7 +196,7 @@ ENDPROC(start_cpu0) * If cpu hotplug is not supported then this code can go in init section * which will be freed later */ -ENTRY(startup_32_smp) +SYM_FUNC_START(startup_32_smp) cld movl $(__BOOT_DS),%eax movl %eax,%ds @@ -363,7 +363,7 @@ ENTRY(startup_32_smp) call *(initial_code) 1: jmp 1b -ENDPROC(startup_32_smp) +SYM_FUNC_END(startup_32_smp) #include "verify_cpu.S" @@ -393,7 +393,7 @@ setup_once: andl $0,setup_once_ref /* Once is enough, thanks */ ret -ENTRY(early_idt_handler_array) +SYM_FUNC_START(early_idt_handler_array) # 36(%esp) %eflags # 32(%esp) %cs # 28(%esp) %eip @@ -408,7 +408,7 @@ ENTRY(early_idt_handler_array) i = i + 1 .fill early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc .endr -ENDPROC(early_idt_handler_array) +SYM_FUNC_END(early_idt_handler_array) SYM_CODE_START_LOCAL(early_idt_handler_common) /* @@ -464,7 +464,7 @@ SYM_CODE_START_LOCAL(early_idt_handler_common) SYM_CODE_END(early_idt_handler_common) /* This is the default interrupt "handler" :-) */ -ENTRY(early_ignore_irq) +SYM_FUNC_START(early_ignore_irq) cld #ifdef CONFIG_PRINTK pushl %eax @@ -499,7 +499,7 @@ ENTRY(early_ignore_irq) hlt_loop: hlt jmp hlt_loop -ENDPROC(early_ignore_irq) +SYM_FUNC_END(early_ignore_irq) __INITDATA .align 4 diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S index e0788bade5ab..3b6544111ac9 100644 --- a/arch/x86/lib/atomic64_386_32.S +++ b/arch/x86/lib/atomic64_386_32.S @@ -20,10 +20,10 @@ #define BEGIN(op) \ .macro endp; \ -ENDPROC(atomic64_##op##_386); \ +SYM_FUNC_END(atomic64_##op##_386); \ .purgem endp; \ .endm; \ -ENTRY(atomic64_##op##_386); \ +SYM_FUNC_START(atomic64_##op##_386); \ LOCK v; #define ENDP endp diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S index 843d978ee341..1c5c81c16b06 100644 --- a/arch/x86/lib/atomic64_cx8_32.S +++ b/arch/x86/lib/atomic64_cx8_32.S @@ -16,12 +16,12 @@ cmpxchg8b (\reg) .endm -ENTRY(atomic64_read_cx8) +SYM_FUNC_START(atomic64_read_cx8) read64 %ecx ret -ENDPROC(atomic64_read_cx8) +SYM_FUNC_END(atomic64_read_cx8) -ENTRY(atomic64_set_cx8) +SYM_FUNC_START(atomic64_set_cx8) 1: /* we don't need LOCK_PREFIX since aligned 64-bit writes * are atomic on 586 and newer */ @@ -29,19 +29,19 @@ ENTRY(atomic64_set_cx8) jne 1b ret -ENDPROC(atomic64_set_cx8) +SYM_FUNC_END(atomic64_set_cx8) -ENTRY(atomic64_xchg_cx8) +SYM_FUNC_START(atomic64_xchg_cx8) 1: LOCK_PREFIX cmpxchg8b (%esi) jne 1b ret -ENDPROC(atomic64_xchg_cx8) +SYM_FUNC_END(atomic64_xchg_cx8) .macro addsub_return func ins insc -ENTRY(atomic64_\func\()_return_cx8) +SYM_FUNC_START(atomic64_\func\()_return_cx8) pushl %ebp pushl %ebx pushl %esi @@ -69,14 +69,14 @@ ENTRY(atomic64_\func\()_return_cx8) popl %ebx popl %ebp ret -ENDPROC(atomic64_\func\()_return_cx8) +SYM_FUNC_END(atomic64_\func\()_return_cx8) .endm addsub_return add add adc addsub_return sub sub sbb .macro incdec_return func ins insc -ENTRY(atomic64_\func\()_return_cx8) +SYM_FUNC_START(atomic64_\func\()_return_cx8) pushl %ebx read64 %esi @@ -94,13 +94,13 @@ ENTRY(atomic64_\func\()_return_cx8) movl %ecx, %edx popl %ebx ret -ENDPROC(atomic64_\func\()_return_cx8) +SYM_FUNC_END(atomic64_\func\()_return_cx8) .endm incdec_return inc add adc incdec_return dec sub sbb -ENTRY(atomic64_dec_if_positive_cx8) +SYM_FUNC_START(atomic64_dec_if_positive_cx8) pushl %ebx read64 %esi @@ -119,9 +119,9 @@ ENTRY(atomic64_dec_if_positive_cx8) movl %ecx, %edx popl %ebx ret -ENDPROC(atomic64_dec_if_positive_cx8) +SYM_FUNC_END(atomic64_dec_if_positive_cx8) -ENTRY(atomic64_add_unless_cx8) +SYM_FUNC_START(atomic64_add_unless_cx8) pushl %ebp pushl %ebx /* these just push these two parameters on the stack */ @@ -155,9 +155,9 @@ ENTRY(atomic64_add_unless_cx8) jne 2b xorl %eax, %eax jmp 3b -ENDPROC(atomic64_add_unless_cx8) +SYM_FUNC_END(atomic64_add_unless_cx8) -ENTRY(atomic64_inc_not_zero_cx8) +SYM_FUNC_START(atomic64_inc_not_zero_cx8) pushl %ebx read64 %esi @@ -177,4 +177,4 @@ ENTRY(atomic64_inc_not_zero_cx8) 3: popl %ebx ret -ENDPROC(atomic64_inc_not_zero_cx8) +SYM_FUNC_END(atomic64_inc_not_zero_cx8) diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S index 74256bd193da..4742e8fa7ee7 100644 --- a/arch/x86/lib/checksum_32.S +++ b/arch/x86/lib/checksum_32.S @@ -46,7 +46,7 @@ unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum) * Fortunately, it is easy to convert 2-byte alignment to 4-byte * alignment for the unrolled loop. */ -ENTRY(csum_partial) +SYM_FUNC_START(csum_partial) pushl %esi pushl %ebx movl 20(%esp),%eax # Function arg: unsigned int sum @@ -128,13 +128,13 @@ ENTRY(csum_partial) popl %ebx popl %esi ret -ENDPROC(csum_partial) +SYM_FUNC_END(csum_partial) #else /* Version for PentiumII/PPro */ -ENTRY(csum_partial) +SYM_FUNC_START(csum_partial) pushl %esi pushl %ebx movl 20(%esp),%eax # Function arg: unsigned int sum @@ -246,7 +246,7 @@ ENTRY(csum_partial) popl %ebx popl %esi ret -ENDPROC(csum_partial) +SYM_FUNC_END(csum_partial) #endif EXPORT_SYMBOL(csum_partial) diff --git a/arch/x86/math-emu/div_Xsig.S b/arch/x86/math-emu/div_Xsig.S index ee08449d20fd..951da2ad54bb 100644 --- a/arch/x86/math-emu/div_Xsig.S +++ b/arch/x86/math-emu/div_Xsig.S @@ -75,7 +75,7 @@ FPU_result_1: .text -ENTRY(div_Xsig) +SYM_FUNC_START(div_Xsig) pushl %ebp movl %esp,%ebp #ifndef NON_REENTRANT_FPU @@ -364,4 +364,4 @@ L_bugged_2: pop %ebx jmp L_exit #endif /* PARANOID */ -ENDPROC(div_Xsig) +SYM_FUNC_END(div_Xsig) diff --git a/arch/x86/math-emu/div_small.S b/arch/x86/math-emu/div_small.S index 8f5025c80ee0..d047d1816abe 100644 --- a/arch/x86/math-emu/div_small.S +++ b/arch/x86/math-emu/div_small.S @@ -19,7 +19,7 @@ #include "fpu_emu.h" .text -ENTRY(FPU_div_small) +SYM_FUNC_START(FPU_div_small) pushl %ebp movl %esp,%ebp @@ -45,4 +45,4 @@ ENTRY(FPU_div_small) leave ret -ENDPROC(FPU_div_small) +SYM_FUNC_END(FPU_div_small) diff --git a/arch/x86/math-emu/mul_Xsig.S b/arch/x86/math-emu/mul_Xsig.S index 3e489122a2b0..4afc7b1fa6e9 100644 --- a/arch/x86/math-emu/mul_Xsig.S +++ b/arch/x86/math-emu/mul_Xsig.S @@ -25,7 +25,7 @@ #include "fpu_emu.h" .text -ENTRY(mul32_Xsig) +SYM_FUNC_START(mul32_Xsig) pushl %ebp movl %esp,%ebp subl $16,%esp @@ -63,10 +63,10 @@ ENTRY(mul32_Xsig) popl %esi leave ret -ENDPROC(mul32_Xsig) +SYM_FUNC_END(mul32_Xsig) -ENTRY(mul64_Xsig) +SYM_FUNC_START(mul64_Xsig) pushl %ebp movl %esp,%ebp subl $16,%esp @@ -116,11 +116,11 @@ ENTRY(mul64_Xsig) popl %esi leave ret -ENDPROC(mul64_Xsig) +SYM_FUNC_END(mul64_Xsig) -ENTRY(mul_Xsig_Xsig) +SYM_FUNC_START(mul_Xsig_Xsig) pushl %ebp movl %esp,%ebp subl $16,%esp @@ -176,4 +176,4 @@ ENTRY(mul_Xsig_Xsig) popl %esi leave ret -ENDPROC(mul_Xsig_Xsig) +SYM_FUNC_END(mul_Xsig_Xsig) diff --git a/arch/x86/math-emu/polynom_Xsig.S b/arch/x86/math-emu/polynom_Xsig.S index 604f0b2d17e8..702315eecb86 100644 --- a/arch/x86/math-emu/polynom_Xsig.S +++ b/arch/x86/math-emu/polynom_Xsig.S @@ -37,7 +37,7 @@ #define OVERFLOWED -16(%ebp) /* addition overflow flag */ .text -ENTRY(polynomial_Xsig) +SYM_FUNC_START(polynomial_Xsig) pushl %ebp movl %esp,%ebp subl $32,%esp @@ -134,4 +134,4 @@ L_accum_done: popl %esi leave ret -ENDPROC(polynomial_Xsig) +SYM_FUNC_END(polynomial_Xsig) diff --git a/arch/x86/math-emu/reg_norm.S b/arch/x86/math-emu/reg_norm.S index 7f6b4392a15d..cad1d60b1e84 100644 --- a/arch/x86/math-emu/reg_norm.S +++ b/arch/x86/math-emu/reg_norm.S @@ -22,7 +22,7 @@ .text -ENTRY(FPU_normalize) +SYM_FUNC_START(FPU_normalize) pushl %ebp movl %esp,%ebp pushl %ebx @@ -95,12 +95,12 @@ L_overflow: call arith_overflow pop %ebx jmp L_exit -ENDPROC(FPU_normalize) +SYM_FUNC_END(FPU_normalize) /* Normalise without reporting underflow or overflow */ -ENTRY(FPU_normalize_nuo) +SYM_FUNC_START(FPU_normalize_nuo) pushl %ebp movl %esp,%ebp pushl %ebx @@ -147,4 +147,4 @@ L_exit_nuo_zero: popl %ebx leave ret -ENDPROC(FPU_normalize_nuo) +SYM_FUNC_END(FPU_normalize_nuo) diff --git a/arch/x86/math-emu/reg_round.S b/arch/x86/math-emu/reg_round.S index 04563421ee7d..11a1f798451b 100644 --- a/arch/x86/math-emu/reg_round.S +++ b/arch/x86/math-emu/reg_round.S @@ -109,7 +109,7 @@ FPU_denormal: .globl fpu_Arith_exit /* Entry point when called from C */ -ENTRY(FPU_round) +SYM_FUNC_START(FPU_round) pushl %ebp movl %esp,%ebp pushl %esi @@ -708,4 +708,4 @@ L_exception_exit: jmp fpu_reg_round_special_exit #endif /* PARANOID */ -ENDPROC(FPU_round) +SYM_FUNC_END(FPU_round) diff --git a/arch/x86/math-emu/reg_u_add.S b/arch/x86/math-emu/reg_u_add.S index 50fe9f8c893c..9c9e2c810afe 100644 --- a/arch/x86/math-emu/reg_u_add.S +++ b/arch/x86/math-emu/reg_u_add.S @@ -32,7 +32,7 @@ #include "control_w.h" .text -ENTRY(FPU_u_add) +SYM_FUNC_START(FPU_u_add) pushl %ebp movl %esp,%ebp pushl %esi @@ -166,4 +166,4 @@ L_exit: leave ret #endif /* PARANOID */ -ENDPROC(FPU_u_add) +SYM_FUNC_END(FPU_u_add) diff --git a/arch/x86/math-emu/reg_u_div.S b/arch/x86/math-emu/reg_u_div.S index 94d545e118e4..e2fb5c2644c5 100644 --- a/arch/x86/math-emu/reg_u_div.S +++ b/arch/x86/math-emu/reg_u_div.S @@ -75,7 +75,7 @@ FPU_ovfl_flag: #define DEST PARAM3 .text -ENTRY(FPU_u_div) +SYM_FUNC_START(FPU_u_div) pushl %ebp movl %esp,%ebp #ifndef NON_REENTRANT_FPU @@ -471,4 +471,4 @@ L_exit: ret #endif /* PARANOID */ -ENDPROC(FPU_u_div) +SYM_FUNC_END(FPU_u_div) diff --git a/arch/x86/math-emu/reg_u_mul.S b/arch/x86/math-emu/reg_u_mul.S index 21cde47fb3e5..0c779c87ac5b 100644 --- a/arch/x86/math-emu/reg_u_mul.S +++ b/arch/x86/math-emu/reg_u_mul.S @@ -45,7 +45,7 @@ FPU_accum_1: .text -ENTRY(FPU_u_mul) +SYM_FUNC_START(FPU_u_mul) pushl %ebp movl %esp,%ebp #ifndef NON_REENTRANT_FPU @@ -147,4 +147,4 @@ L_exit: ret #endif /* PARANOID */ -ENDPROC(FPU_u_mul) +SYM_FUNC_END(FPU_u_mul) diff --git a/arch/x86/math-emu/reg_u_sub.S b/arch/x86/math-emu/reg_u_sub.S index f05dea7dec38..e9bb7c248649 100644 --- a/arch/x86/math-emu/reg_u_sub.S +++ b/arch/x86/math-emu/reg_u_sub.S @@ -33,7 +33,7 @@ #include "control_w.h" .text -ENTRY(FPU_u_sub) +SYM_FUNC_START(FPU_u_sub) pushl %ebp movl %esp,%ebp pushl %esi @@ -271,4 +271,4 @@ L_exit: popl %esi leave ret -ENDPROC(FPU_u_sub) +SYM_FUNC_END(FPU_u_sub) diff --git a/arch/x86/math-emu/round_Xsig.S b/arch/x86/math-emu/round_Xsig.S index 226a51e991f1..d9d7de8dbd7b 100644 --- a/arch/x86/math-emu/round_Xsig.S +++ b/arch/x86/math-emu/round_Xsig.S @@ -23,7 +23,7 @@ .text -ENTRY(round_Xsig) +SYM_FUNC_START(round_Xsig) pushl %ebp movl %esp,%ebp pushl %ebx /* Reserve some space */ @@ -79,11 +79,11 @@ L_exit: popl %ebx leave ret -ENDPROC(round_Xsig) +SYM_FUNC_END(round_Xsig) -ENTRY(norm_Xsig) +SYM_FUNC_START(norm_Xsig) pushl %ebp movl %esp,%ebp pushl %ebx /* Reserve some space */ @@ -139,4 +139,4 @@ L_n_exit: popl %ebx leave ret -ENDPROC(norm_Xsig) +SYM_FUNC_END(norm_Xsig) diff --git a/arch/x86/math-emu/shr_Xsig.S b/arch/x86/math-emu/shr_Xsig.S index 96f4779aa9c1..726af985f758 100644 --- a/arch/x86/math-emu/shr_Xsig.S +++ b/arch/x86/math-emu/shr_Xsig.S @@ -22,7 +22,7 @@ #include "fpu_emu.h" .text -ENTRY(shr_Xsig) +SYM_FUNC_START(shr_Xsig) push %ebp movl %esp,%ebp pushl %esi @@ -86,4 +86,4 @@ L_more_than_95: popl %esi leave ret -ENDPROC(shr_Xsig) +SYM_FUNC_END(shr_Xsig) diff --git a/arch/x86/math-emu/wm_shrx.S b/arch/x86/math-emu/wm_shrx.S index d588874eb6fb..4fc89174caf0 100644 --- a/arch/x86/math-emu/wm_shrx.S +++ b/arch/x86/math-emu/wm_shrx.S @@ -33,7 +33,7 @@ | Results returned in the 64 bit arg and eax. | +---------------------------------------------------------------------------*/ -ENTRY(FPU_shrx) +SYM_FUNC_START(FPU_shrx) push %ebp movl %esp,%ebp pushl %esi @@ -93,7 +93,7 @@ L_more_than_95: popl %esi leave ret -ENDPROC(FPU_shrx) +SYM_FUNC_END(FPU_shrx) /*---------------------------------------------------------------------------+ @@ -112,7 +112,7 @@ ENDPROC(FPU_shrx) | part which has been shifted out of the arg. | | Results returned in the 64 bit arg and eax. | +---------------------------------------------------------------------------*/ -ENTRY(FPU_shrxs) +SYM_FUNC_START(FPU_shrxs) push %ebp movl %esp,%ebp pushl %esi @@ -204,4 +204,4 @@ Ls_more_than_95: popl %esi leave ret -ENDPROC(FPU_shrxs) +SYM_FUNC_END(FPU_shrxs) diff --git a/arch/x86/math-emu/wm_sqrt.S b/arch/x86/math-emu/wm_sqrt.S index f031c0e19356..3b2b58164ec1 100644 --- a/arch/x86/math-emu/wm_sqrt.S +++ b/arch/x86/math-emu/wm_sqrt.S @@ -75,7 +75,7 @@ FPU_fsqrt_arg_0: .text -ENTRY(wm_sqrt) +SYM_FUNC_START(wm_sqrt) pushl %ebp movl %esp,%ebp #ifndef NON_REENTRANT_FPU @@ -469,4 +469,4 @@ sqrt_more_prec_large: /* Our estimate is too large */ movl $0x7fffff00,%eax jmp sqrt_round_result -ENDPROC(wm_sqrt) +SYM_FUNC_END(wm_sqrt) diff --git a/arch/x86/platform/efi/efi_stub_32.S b/arch/x86/platform/efi/efi_stub_32.S index ab2e91e76894..eed8b5b441f8 100644 --- a/arch/x86/platform/efi/efi_stub_32.S +++ b/arch/x86/platform/efi/efi_stub_32.S @@ -22,7 +22,7 @@ */ .text -ENTRY(efi_call_phys) +SYM_FUNC_START(efi_call_phys) /* * 0. The function can only be called in Linux kernel. So CS has been * set to 0x0010, DS and SS have been set to 0x0018. In EFI, I found @@ -114,7 +114,7 @@ ENTRY(efi_call_phys) movl (%edx), %ecx pushl %ecx ret -ENDPROC(efi_call_phys) +SYM_FUNC_END(efi_call_phys) .previous .data diff --git a/arch/x86/power/hibernate_asm_32.S b/arch/x86/power/hibernate_asm_32.S index a19ed3d23185..8786653ad3c0 100644 --- a/arch/x86/power/hibernate_asm_32.S +++ b/arch/x86/power/hibernate_asm_32.S @@ -16,7 +16,7 @@ .text -ENTRY(swsusp_arch_suspend) +SYM_FUNC_START(swsusp_arch_suspend) movl %esp, saved_context_esp movl %ebx, saved_context_ebx movl %ebp, saved_context_ebp @@ -33,7 +33,7 @@ ENTRY(swsusp_arch_suspend) call swsusp_save FRAME_END ret -ENDPROC(swsusp_arch_suspend) +SYM_FUNC_END(swsusp_arch_suspend) SYM_CODE_START(restore_image) /* prepare to jump to the image kernel */ @@ -82,7 +82,7 @@ SYM_CODE_END(core_restore_code) /* code below belongs to the image kernel */ .align PAGE_SIZE -ENTRY(restore_registers) +SYM_FUNC_START(restore_registers) /* go back to the original page tables */ movl %ebp, %cr3 movl mmu_cr4_features, %ecx @@ -109,4 +109,4 @@ ENTRY(restore_registers) movl %eax, in_suspend ret -ENDPROC(restore_registers) +SYM_FUNC_END(restore_registers) diff --git a/include/linux/linkage.h b/include/linux/linkage.h index 5ffcf72c8f87..331a2306312c 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -112,15 +112,13 @@ .globl name ASM_NL \ name: #endif -#endif -#ifndef CONFIG_X86_64 #ifndef ENTRY /* deprecated, use SYM_FUNC_START */ #define ENTRY(name) \ SYM_FUNC_START(name) #endif -#endif /* CONFIG_X86_64 */ +#endif /* CONFIG_X86 */ #endif /* LINKER_SCRIPT */ #ifndef WEAK @@ -135,9 +133,7 @@ #define END(name) \ .size name, .-name #endif -#endif /* CONFIG_X86 */ -#ifndef CONFIG_X86_64 /* If symbol 'name' is treated as a subroutine (gets called, and returns) * then please use ENDPROC to mark 'name' as STT_FUNC for the benefit of * static analysis tools such as stack depth analyzer. @@ -147,7 +143,7 @@ #define ENDPROC(name) \ SYM_FUNC_END(name) #endif -#endif /* CONFIG_X86_64 */ +#endif /* CONFIG_X86 */ /* === generic annotations === */ -- cgit v1.2.3-71-gd317 From 13fbe784ef6e58d0267a6e183f90ce7826d7d885 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 11 Oct 2019 13:51:08 +0200 Subject: x86/asm: Replace WEAK uses by SYM_INNER_LABEL_ALIGN Use the new SYM_INNER_LABEL_ALIGN for WEAK entries in the middle of x86 assembly functions. And make sure WEAK is not defined for x86 anymore as these were the last users. Signed-off-by: Jiri Slaby Signed-off-by: Borislav Petkov Cc: Andrey Ryabinin Cc: Boris Ostrovsky Cc: Herbert Xu Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Josh Poimboeuf Cc: linux-arch@vger.kernel.org Cc: Mark Rutland Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: "Steven Rostedt (VMware)" Cc: Thomas Gleixner Cc: x86-ml Link: https://lkml.kernel.org/r/20191011115108.12392-29-jslaby@suse.cz --- arch/x86/kernel/ftrace_32.S | 2 +- arch/x86/kernel/ftrace_64.S | 2 +- arch/x86/kernel/head_32.S | 2 +- include/linux/linkage.h | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S index b4f495bbd5a1..8ed1f5d371f0 100644 --- a/arch/x86/kernel/ftrace_32.S +++ b/arch/x86/kernel/ftrace_32.S @@ -85,7 +85,7 @@ ftrace_graph_call: #endif /* This is weak to keep gas from relaxing the jumps */ -WEAK(ftrace_stub) +SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK) ret SYM_CODE_END(ftrace_caller) diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 16deae706950..69c8d1b9119e 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -168,7 +168,7 @@ SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) * This is weak to keep gas from relaxing the jumps. * It is also used to copy the retq for trampolines. */ -WEAK(ftrace_stub) +SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK) retq SYM_FUNC_END(ftrace_caller) diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index ea24aa5465fd..3fe7d2008b7a 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -156,7 +156,7 @@ SYM_CODE_START(startup_32) jmp *%eax .Lbad_subarch: -WEAK(xen_entry) +SYM_INNER_LABEL_ALIGN(xen_entry, SYM_L_WEAK) /* Unknown implementation; there's really nothing we can do at this point. */ ud2a diff --git a/include/linux/linkage.h b/include/linux/linkage.h index 331a2306312c..9280209d1f62 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -121,13 +121,13 @@ #endif /* CONFIG_X86 */ #endif /* LINKER_SCRIPT */ +#ifndef CONFIG_X86 #ifndef WEAK /* deprecated, use SYM_FUNC_START_WEAK* */ #define WEAK(name) \ SYM_FUNC_START_WEAK(name) #endif -#ifndef CONFIG_X86 #ifndef END /* deprecated, use SYM_FUNC_END, SYM_DATA_END, or SYM_END */ #define END(name) \ -- cgit v1.2.3-71-gd317 From 036beb0e85f8772acb635c30df573876103b0c21 Mon Sep 17 00:00:00 2001 From: Tzung-Bi Shih Date: Mon, 14 Oct 2019 18:20:13 +0800 Subject: platform/chrome: cros_ec: remove unused EC feature Remove unused EC_FEATURE_AUDIO_CODEC. Signed-off-by: Tzung-Bi Shih Acked-By: Benson Leung Link: https://lore.kernel.org/r/20191014180059.01.I374c311eaca0d47944a37b07acbe48fdb74f734d@changeid Signed-off-by: Mark Brown --- include/linux/platform_data/cros_ec_commands.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 98415686cbfa..43b8f7dae4cc 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -1277,8 +1277,6 @@ enum ec_feature_code { * MOTIONSENSE_CMD_TABLET_MODE_LID_ANGLE. */ EC_FEATURE_REFINED_TABLET_MODE_HYSTERESIS = 37, - /* EC supports audio codec. */ - EC_FEATURE_AUDIO_CODEC = 38, /* The MCU is a System Companion Processor (SCP). */ EC_FEATURE_SCP = 39, /* The MCU is an Integrated Sensor Hub */ -- cgit v1.2.3-71-gd317 From 727f1c71c780789aeb8f3da2596c65ae008d5d6c Mon Sep 17 00:00:00 2001 From: Tzung-Bi Shih Date: Mon, 14 Oct 2019 18:20:14 +0800 Subject: ASoC: cros_ec_codec: refactor I2S RX Refactor by the following items: - reformat copyright declaration - use more specific name "i2s rx" - use verbose symbol names to separate namespaces - make some short functions inline - remove unused TDM-related code Signed-off-by: Tzung-Bi Shih Acked-By: Benson Leung Link: https://lore.kernel.org/r/20191014180059.02.I43373b9a66dbb70196b3f216b3aa86111c410836@changeid Signed-off-by: Mark Brown --- drivers/platform/chrome/cros_ec_trace.c | 2 +- include/linux/platform_data/cros_ec_commands.h | 120 +++--- sound/soc/codecs/cros_ec_codec.c | 502 ++++++++++--------------- 3 files changed, 251 insertions(+), 373 deletions(-) (limited to 'include/linux') diff --git a/drivers/platform/chrome/cros_ec_trace.c b/drivers/platform/chrome/cros_ec_trace.c index 6f80ff4532ae..901850004b2b 100644 --- a/drivers/platform/chrome/cros_ec_trace.c +++ b/drivers/platform/chrome/cros_ec_trace.c @@ -98,7 +98,7 @@ TRACE_SYMBOL(EC_CMD_SB_READ_BLOCK), \ TRACE_SYMBOL(EC_CMD_SB_WRITE_BLOCK), \ TRACE_SYMBOL(EC_CMD_BATTERY_VENDOR_PARAM), \ - TRACE_SYMBOL(EC_CMD_CODEC_I2S), \ + TRACE_SYMBOL(EC_CMD_EC_CODEC_I2S_RX), \ TRACE_SYMBOL(EC_CMD_REBOOT_EC), \ TRACE_SYMBOL(EC_CMD_GET_PANIC_INFO), \ TRACE_SYMBOL(EC_CMD_ACPI_READ), \ diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 43b8f7dae4cc..261ac83bd007 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -4466,92 +4466,74 @@ enum mkbp_cec_event { /*****************************************************************************/ -/* Commands for I2S recording on audio codec. */ - -#define EC_CMD_CODEC_I2S 0x00BC -#define EC_WOV_I2S_SAMPLE_RATE 48000 - -enum ec_codec_i2s_subcmd { - EC_CODEC_SET_SAMPLE_DEPTH = 0x0, - EC_CODEC_SET_GAIN = 0x1, - EC_CODEC_GET_GAIN = 0x2, - EC_CODEC_I2S_ENABLE = 0x3, - EC_CODEC_I2S_SET_CONFIG = 0x4, - EC_CODEC_I2S_SET_TDM_CONFIG = 0x5, - EC_CODEC_I2S_SET_BCLK = 0x6, - EC_CODEC_I2S_SUBCMD_COUNT = 0x7, +/* Commands for I2S RX on audio codec. */ + +#define EC_CMD_EC_CODEC_I2S_RX 0x00BC + +enum ec_codec_i2s_rx_subcmd { + EC_CODEC_I2S_RX_ENABLE = 0x0, + EC_CODEC_I2S_RX_DISABLE = 0x1, + EC_CODEC_I2S_RX_SET_GAIN = 0x2, + EC_CODEC_I2S_RX_GET_GAIN = 0x3, + EC_CODEC_I2S_RX_SET_SAMPLE_DEPTH = 0x4, + EC_CODEC_I2S_RX_SET_DAIFMT = 0x5, + EC_CODEC_I2S_RX_SET_BCLK = 0x6, + EC_CODEC_I2S_RX_SUBCMD_COUNT, }; -enum ec_sample_depth_value { - EC_CODEC_SAMPLE_DEPTH_16 = 0, - EC_CODEC_SAMPLE_DEPTH_24 = 1, +enum ec_codec_i2s_rx_sample_depth { + EC_CODEC_I2S_RX_SAMPLE_DEPTH_16 = 0x0, + EC_CODEC_I2S_RX_SAMPLE_DEPTH_24 = 0x1, + EC_CODEC_I2S_RX_SAMPLE_DEPTH_COUNT, }; -enum ec_i2s_config { - EC_DAI_FMT_I2S = 0, - EC_DAI_FMT_RIGHT_J = 1, - EC_DAI_FMT_LEFT_J = 2, - EC_DAI_FMT_PCM_A = 3, - EC_DAI_FMT_PCM_B = 4, - EC_DAI_FMT_PCM_TDM = 5, +enum ec_codec_i2s_rx_daifmt { + EC_CODEC_I2S_RX_DAIFMT_I2S = 0x0, + EC_CODEC_I2S_RX_DAIFMT_RIGHT_J = 0x1, + EC_CODEC_I2S_RX_DAIFMT_LEFT_J = 0x2, + EC_CODEC_I2S_RX_DAIFMT_COUNT, }; -/* - * For subcommand EC_CODEC_GET_GAIN. - */ -struct __ec_align1 ec_codec_i2s_gain { +struct __ec_align1 ec_param_ec_codec_i2s_rx_set_sample_depth { + uint8_t depth; + uint8_t reserved[3]; +}; + +struct __ec_align1 ec_param_ec_codec_i2s_rx_set_gain { uint8_t left; uint8_t right; + uint8_t reserved[2]; }; -struct __ec_todo_unpacked ec_param_codec_i2s_tdm { - int16_t ch0_delay; /* 0 to 496 */ - int16_t ch1_delay; /* -1 to 496 */ - uint8_t adjacent_to_ch0; - uint8_t adjacent_to_ch1; +struct __ec_align1 ec_param_ec_codec_i2s_rx_set_daifmt { + uint8_t daifmt; + uint8_t reserved[3]; }; -struct __ec_todo_packed ec_param_codec_i2s { - /* enum ec_codec_i2s_subcmd */ - uint8_t cmd; - union { - /* - * EC_CODEC_SET_SAMPLE_DEPTH - * Value should be one of ec_sample_depth_value. - */ - uint8_t depth; - - /* - * EC_CODEC_SET_GAIN - * Value should be 0~43 for both channels. - */ - struct ec_codec_i2s_gain gain; - - /* - * EC_CODEC_I2S_ENABLE - * 1 to enable, 0 to disable. - */ - uint8_t i2s_enable; - - /* - * EC_CODEC_I2S_SET_CONFIG - * Value should be one of ec_i2s_config. - */ - uint8_t i2s_config; +struct __ec_align4 ec_param_ec_codec_i2s_rx_set_bclk { + uint32_t bclk; +}; - /* - * EC_CODEC_I2S_SET_TDM_CONFIG - * Value should be one of ec_i2s_config. - */ - struct ec_param_codec_i2s_tdm tdm_param; +struct __ec_align4 ec_param_ec_codec_i2s_rx { + uint8_t cmd; /* enum ec_codec_i2s_rx_subcmd */ + uint8_t reserved[3]; - /* - * EC_CODEC_I2S_SET_BCLK - */ - uint32_t bclk; + union { + struct ec_param_ec_codec_i2s_rx_set_sample_depth + set_sample_depth_param; + struct ec_param_ec_codec_i2s_rx_set_gain + set_gain_param; + struct ec_param_ec_codec_i2s_rx_set_daifmt + set_daifmt_param; + struct ec_param_ec_codec_i2s_rx_set_bclk + set_bclk_param; }; }; +struct __ec_align1 ec_response_ec_codec_i2s_rx_get_gain { + uint8_t left; + uint8_t right; +}; /*****************************************************************************/ /* System commands */ diff --git a/sound/soc/codecs/cros_ec_codec.c b/sound/soc/codecs/cros_ec_codec.c index 3c1bd24a1057..179fa77291cd 100644 --- a/sound/soc/codecs/cros_ec_codec.c +++ b/sound/soc/codecs/cros_ec_codec.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Driver for ChromeOS Embedded Controller codec. + * Copyright 2019 Google, Inc. + * + * ChromeOS Embedded Controller codec driver. * * This driver uses the cros-ec interface to communicate with the ChromeOS * EC for audio function. @@ -18,403 +20,297 @@ #include #include -#define DRV_NAME "cros-ec-codec" - -/** - * struct cros_ec_codec_data - ChromeOS EC codec driver data. - * @dev: Device structure used in sysfs. - * @ec_device: cros_ec_device structure to talk to the physical device. - * @component: Pointer to the component. - * @max_dmic_gain: Maximum gain in dB supported by EC codec. - */ -struct cros_ec_codec_data { +struct cros_ec_codec_priv { struct device *dev; struct cros_ec_device *ec_device; - struct snd_soc_component *component; - unsigned int max_dmic_gain; }; -static const DECLARE_TLV_DB_SCALE(ec_mic_gain_tlv, 0, 100, 0); - -static int ec_command_get_gain(struct snd_soc_component *component, - struct ec_param_codec_i2s *param, - struct ec_codec_i2s_gain *resp) +static int send_ec_host_command(struct cros_ec_device *ec_dev, uint32_t cmd, + uint8_t *out, size_t outsize, + uint8_t *in, size_t insize) { - struct cros_ec_codec_data *codec_data = - snd_soc_component_get_drvdata(component); - struct cros_ec_device *ec_device = codec_data->ec_device; - u8 buffer[sizeof(struct cros_ec_command) + - max(sizeof(struct ec_param_codec_i2s), - sizeof(struct ec_codec_i2s_gain))]; - struct cros_ec_command *msg = (struct cros_ec_command *)&buffer; int ret; + struct cros_ec_command *msg; + + msg = kmalloc(sizeof(*msg) + max(outsize, insize), GFP_KERNEL); + if (!msg) + return -ENOMEM; msg->version = 0; - msg->command = EC_CMD_CODEC_I2S; - msg->outsize = sizeof(struct ec_param_codec_i2s); - msg->insize = sizeof(struct ec_codec_i2s_gain); + msg->command = cmd; + msg->outsize = outsize; + msg->insize = insize; + + if (outsize) + memcpy(msg->data, out, outsize); - memcpy(msg->data, param, msg->outsize); + ret = cros_ec_cmd_xfer_status(ec_dev, msg); + if (ret < 0) + goto error; - ret = cros_ec_cmd_xfer_status(ec_device, msg); - if (ret > 0) - memcpy(resp, msg->data, msg->insize); + if (insize) + memcpy(in, msg->data, insize); + ret = 0; +error: + kfree(msg); return ret; } -/* - * Wrapper for EC command without response. - */ -static int ec_command_no_resp(struct snd_soc_component *component, - struct ec_param_codec_i2s *param) +static int dmic_get_gain(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) { - struct cros_ec_codec_data *codec_data = + struct snd_soc_component *component = + snd_soc_kcontrol_component(kcontrol); + struct cros_ec_codec_priv *priv = snd_soc_component_get_drvdata(component); - struct cros_ec_device *ec_device = codec_data->ec_device; - u8 buffer[sizeof(struct cros_ec_command) + - sizeof(struct ec_param_codec_i2s)]; - struct cros_ec_command *msg = (struct cros_ec_command *)&buffer; - - msg->version = 0; - msg->command = EC_CMD_CODEC_I2S; - msg->outsize = sizeof(struct ec_param_codec_i2s); - msg->insize = 0; - - memcpy(msg->data, param, msg->outsize); - - return cros_ec_cmd_xfer_status(ec_device, msg); -} - -static int set_i2s_config(struct snd_soc_component *component, - enum ec_i2s_config i2s_config) -{ - struct ec_param_codec_i2s param; + struct ec_param_ec_codec_i2s_rx p; + struct ec_response_ec_codec_i2s_rx_get_gain r; + int ret; - dev_dbg(component->dev, "%s set I2S format to %u\n", __func__, - i2s_config); + p.cmd = EC_CODEC_I2S_RX_GET_GAIN; + ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_I2S_RX, + (uint8_t *)&p, sizeof(p), + (uint8_t *)&r, sizeof(r)); + if (ret < 0) + return ret; - param.cmd = EC_CODEC_I2S_SET_CONFIG; - param.i2s_config = i2s_config; + ucontrol->value.integer.value[0] = r.left; + ucontrol->value.integer.value[1] = r.right; - return ec_command_no_resp(component, ¶m); + return 0; } -static int cros_ec_i2s_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt) +static int dmic_put_gain(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) { - struct snd_soc_component *component = dai->component; - enum ec_i2s_config i2s_config; - - switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) { - case SND_SOC_DAIFMT_CBS_CFS: - break; - default: - return -EINVAL; - } - - switch (fmt & SND_SOC_DAIFMT_INV_MASK) { - case SND_SOC_DAIFMT_NB_NF: - break; - default: - return -EINVAL; - } - - switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) { - case SND_SOC_DAIFMT_I2S: - i2s_config = EC_DAI_FMT_I2S; - break; - - case SND_SOC_DAIFMT_RIGHT_J: - i2s_config = EC_DAI_FMT_RIGHT_J; - break; - - case SND_SOC_DAIFMT_LEFT_J: - i2s_config = EC_DAI_FMT_LEFT_J; - break; - - case SND_SOC_DAIFMT_DSP_A: - i2s_config = EC_DAI_FMT_PCM_A; - break; - - case SND_SOC_DAIFMT_DSP_B: - i2s_config = EC_DAI_FMT_PCM_B; - break; + struct snd_soc_component *component = + snd_soc_kcontrol_component(kcontrol); + struct cros_ec_codec_priv *priv = + snd_soc_component_get_drvdata(component); + struct soc_mixer_control *control = + (struct soc_mixer_control *)kcontrol->private_value; + int max_dmic_gain = control->max; + int left = ucontrol->value.integer.value[0]; + int right = ucontrol->value.integer.value[1]; + struct ec_param_ec_codec_i2s_rx p; - default: + if (left > max_dmic_gain || right > max_dmic_gain) return -EINVAL; - } - return set_i2s_config(component, i2s_config); -} - -static int set_i2s_sample_depth(struct snd_soc_component *component, - enum ec_sample_depth_value depth) -{ - struct ec_param_codec_i2s param; - - dev_dbg(component->dev, "%s set depth to %u\n", __func__, depth); - - param.cmd = EC_CODEC_SET_SAMPLE_DEPTH; - param.depth = depth; + dev_dbg(component->dev, "set mic gain to %u, %u\n", left, right); - return ec_command_no_resp(component, ¶m); + p.cmd = EC_CODEC_I2S_RX_SET_GAIN; + p.set_gain_param.left = left; + p.set_gain_param.right = right; + return send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_I2S_RX, + (uint8_t *)&p, sizeof(p), NULL, 0); } -static int set_i2s_bclk(struct snd_soc_component *component, uint32_t bclk) -{ - struct ec_param_codec_i2s param; - - dev_dbg(component->dev, "%s set i2s bclk to %u\n", __func__, bclk); +static const DECLARE_TLV_DB_SCALE(dmic_gain_tlv, 0, 100, 0); - param.cmd = EC_CODEC_I2S_SET_BCLK; - param.bclk = bclk; +enum { + DMIC_CTL_GAIN = 0, +}; - return ec_command_no_resp(component, ¶m); -} +static struct snd_kcontrol_new dmic_controls[] = { + [DMIC_CTL_GAIN] = + SOC_DOUBLE_EXT_TLV("EC Mic Gain", SND_SOC_NOPM, SND_SOC_NOPM, + 0, 0, 0, dmic_get_gain, dmic_put_gain, + dmic_gain_tlv), +}; -static int cros_ec_i2s_hw_params(struct snd_pcm_substream *substream, - struct snd_pcm_hw_params *params, - struct snd_soc_dai *dai) +static int i2s_rx_hw_params(struct snd_pcm_substream *substream, + struct snd_pcm_hw_params *params, + struct snd_soc_dai *dai) { struct snd_soc_component *component = dai->component; - unsigned int rate, bclk; + struct cros_ec_codec_priv *priv = + snd_soc_component_get_drvdata(component); + struct ec_param_ec_codec_i2s_rx p; + enum ec_codec_i2s_rx_sample_depth depth; int ret; - rate = params_rate(params); - if (rate != 48000) + if (params_rate(params) != 48000) return -EINVAL; switch (params_format(params)) { case SNDRV_PCM_FORMAT_S16_LE: - ret = set_i2s_sample_depth(component, EC_CODEC_SAMPLE_DEPTH_16); + depth = EC_CODEC_I2S_RX_SAMPLE_DEPTH_16; break; case SNDRV_PCM_FORMAT_S24_LE: - ret = set_i2s_sample_depth(component, EC_CODEC_SAMPLE_DEPTH_24); + depth = EC_CODEC_I2S_RX_SAMPLE_DEPTH_24; break; default: return -EINVAL; } - if (ret < 0) - return ret; - - bclk = snd_soc_params_to_bclk(params); - return set_i2s_bclk(component, bclk); -} -static const struct snd_soc_dai_ops cros_ec_i2s_dai_ops = { - .hw_params = cros_ec_i2s_hw_params, - .set_fmt = cros_ec_i2s_set_dai_fmt, -}; + dev_dbg(component->dev, "set depth to %u\n", depth); -static struct snd_soc_dai_driver cros_ec_dai[] = { - { - .name = "cros_ec_codec I2S", - .id = 0, - .capture = { - .stream_name = "I2S Capture", - .channels_min = 2, - .channels_max = 2, - .rates = SNDRV_PCM_RATE_48000, - .formats = SNDRV_PCM_FMTBIT_S16_LE | - SNDRV_PCM_FMTBIT_S24_LE, - }, - .ops = &cros_ec_i2s_dai_ops, - } -}; - -static int get_ec_mic_gain(struct snd_soc_component *component, - u8 *left, u8 *right) -{ - struct ec_param_codec_i2s param; - struct ec_codec_i2s_gain resp; - int ret; - - param.cmd = EC_CODEC_GET_GAIN; - - ret = ec_command_get_gain(component, ¶m, &resp); + p.cmd = EC_CODEC_I2S_RX_SET_SAMPLE_DEPTH; + p.set_sample_depth_param.depth = depth; + ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_I2S_RX, + (uint8_t *)&p, sizeof(p), NULL, 0); if (ret < 0) return ret; - *left = resp.left; - *right = resp.right; - - return 0; -} - -static int mic_gain_get(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - struct snd_soc_component *component = - snd_soc_kcontrol_component(kcontrol); - u8 left, right; - int ret; - - ret = get_ec_mic_gain(component, &left, &right); - if (ret) - return ret; - - ucontrol->value.integer.value[0] = left; - ucontrol->value.integer.value[1] = right; - - return 0; -} - -static int set_ec_mic_gain(struct snd_soc_component *component, - u8 left, u8 right) -{ - struct ec_param_codec_i2s param; - - dev_dbg(component->dev, "%s set mic gain to %u, %u\n", - __func__, left, right); + dev_dbg(component->dev, "set bclk to %u\n", + snd_soc_params_to_bclk(params)); - param.cmd = EC_CODEC_SET_GAIN; - param.gain.left = left; - param.gain.right = right; - - return ec_command_no_resp(component, ¶m); + p.cmd = EC_CODEC_I2S_RX_SET_BCLK; + p.set_bclk_param.bclk = snd_soc_params_to_bclk(params); + return send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_I2S_RX, + (uint8_t *)&p, sizeof(p), NULL, 0); } -static int mic_gain_put(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) +static int i2s_rx_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) { - struct snd_soc_component *component = - snd_soc_kcontrol_component(kcontrol); - struct cros_ec_codec_data *codec_data = + struct snd_soc_component *component = dai->component; + struct cros_ec_codec_priv *priv = snd_soc_component_get_drvdata(component); - int left = ucontrol->value.integer.value[0]; - int right = ucontrol->value.integer.value[1]; - unsigned int max_dmic_gain = codec_data->max_dmic_gain; + struct ec_param_ec_codec_i2s_rx p; + enum ec_codec_i2s_rx_daifmt daifmt; - if (left > max_dmic_gain || right > max_dmic_gain) + switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) { + case SND_SOC_DAIFMT_CBS_CFS: + break; + default: return -EINVAL; + } - return set_ec_mic_gain(component, (u8)left, (u8)right); -} - -static struct snd_kcontrol_new mic_gain_control = - SOC_DOUBLE_EXT_TLV("EC Mic Gain", SND_SOC_NOPM, SND_SOC_NOPM, 0, 0, 0, - mic_gain_get, mic_gain_put, ec_mic_gain_tlv); - -static int enable_i2s(struct snd_soc_component *component, int enable) -{ - struct ec_param_codec_i2s param; + switch (fmt & SND_SOC_DAIFMT_INV_MASK) { + case SND_SOC_DAIFMT_NB_NF: + break; + default: + return -EINVAL; + } - dev_dbg(component->dev, "%s set i2s to %u\n", __func__, enable); + switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) { + case SND_SOC_DAIFMT_I2S: + daifmt = EC_CODEC_I2S_RX_DAIFMT_I2S; + break; + case SND_SOC_DAIFMT_RIGHT_J: + daifmt = EC_CODEC_I2S_RX_DAIFMT_RIGHT_J; + break; + case SND_SOC_DAIFMT_LEFT_J: + daifmt = EC_CODEC_I2S_RX_DAIFMT_LEFT_J; + break; + default: + return -EINVAL; + } - param.cmd = EC_CODEC_I2S_ENABLE; - param.i2s_enable = enable; + dev_dbg(component->dev, "set format to %u\n", daifmt); - return ec_command_no_resp(component, ¶m); + p.cmd = EC_CODEC_I2S_RX_SET_DAIFMT; + p.set_daifmt_param.daifmt = daifmt; + return send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_I2S_RX, + (uint8_t *)&p, sizeof(p), NULL, 0); } -static int cros_ec_i2s_enable_event(struct snd_soc_dapm_widget *w, - struct snd_kcontrol *kcontrol, int event) +static const struct snd_soc_dai_ops i2s_rx_dai_ops = { + .hw_params = i2s_rx_hw_params, + .set_fmt = i2s_rx_set_fmt, +}; + +static int i2s_rx_event(struct snd_soc_dapm_widget *w, + struct snd_kcontrol *kcontrol, int event) { struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm); + struct cros_ec_codec_priv *priv = + snd_soc_component_get_drvdata(component); + struct ec_param_ec_codec_i2s_rx p; switch (event) { case SND_SOC_DAPM_PRE_PMU: - dev_dbg(component->dev, - "%s got SND_SOC_DAPM_PRE_PMU event\n", __func__); - return enable_i2s(component, 1); - + dev_dbg(component->dev, "enable I2S RX\n"); + p.cmd = EC_CODEC_I2S_RX_ENABLE; + break; case SND_SOC_DAPM_PRE_PMD: - dev_dbg(component->dev, - "%s got SND_SOC_DAPM_PRE_PMD event\n", __func__); - return enable_i2s(component, 0); + dev_dbg(component->dev, "disable I2S RX\n"); + p.cmd = EC_CODEC_I2S_RX_DISABLE; + break; + default: + return 0; } - return 0; + return send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_I2S_RX, + (uint8_t *)&p, sizeof(p), NULL, 0); } -/* - * The goal of this DAPM route is to turn on/off I2S using EC - * host command when capture stream is started/stopped. - */ -static const struct snd_soc_dapm_widget cros_ec_codec_dapm_widgets[] = { +static struct snd_soc_dapm_widget i2s_rx_dapm_widgets[] = { SND_SOC_DAPM_INPUT("DMIC"), - - /* - * Control EC to enable/disable I2S. - */ - SND_SOC_DAPM_SUPPLY("I2S Enable", SND_SOC_NOPM, - 0, 0, cros_ec_i2s_enable_event, + SND_SOC_DAPM_SUPPLY("I2S RX Enable", SND_SOC_NOPM, 0, 0, i2s_rx_event, SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_PRE_PMD), + SND_SOC_DAPM_AIF_OUT("I2S RX", "I2S Capture", 0, SND_SOC_NOPM, 0, 0), +}; - SND_SOC_DAPM_AIF_OUT("I2STX", "I2S Capture", 0, SND_SOC_NOPM, 0, 0), +static struct snd_soc_dapm_route i2s_rx_dapm_routes[] = { + {"I2S RX", NULL, "DMIC"}, + {"I2S RX", NULL, "I2S RX Enable"}, }; -static const struct snd_soc_dapm_route cros_ec_codec_dapm_routes[] = { - { "I2STX", NULL, "DMIC" }, - { "I2STX", NULL, "I2S Enable" }, +static struct snd_soc_dai_driver i2s_rx_dai_driver = { + .name = "EC Codec I2S RX", + .capture = { + .stream_name = "I2S Capture", + .channels_min = 2, + .channels_max = 2, + .rates = SNDRV_PCM_RATE_48000, + .formats = SNDRV_PCM_FMTBIT_S16_LE | + SNDRV_PCM_FMTBIT_S24_LE, + }, + .ops = &i2s_rx_dai_ops, }; -/* - * Read maximum gain from device property and set it to mixer control. - */ -static int cros_ec_set_gain_range(struct device *dev) +static int i2s_rx_probe(struct snd_soc_component *component) { + struct cros_ec_codec_priv *priv = + snd_soc_component_get_drvdata(component); + struct device *dev = priv->dev; + int ret, val; struct soc_mixer_control *control; - struct cros_ec_codec_data *codec_data = dev_get_drvdata(dev); - int rc; - rc = device_property_read_u32(dev, "max-dmic-gain", - &codec_data->max_dmic_gain); - if (rc) - return rc; + ret = device_property_read_u32(dev, "max-dmic-gain", &val); + if (ret) { + dev_err(dev, "Failed to read 'max-dmic-gain'\n"); + return ret; + } control = (struct soc_mixer_control *) - mic_gain_control.private_value; - control->max = codec_data->max_dmic_gain; - control->platform_max = codec_data->max_dmic_gain; + dmic_controls[DMIC_CTL_GAIN].private_value; + control->max = val; + control->platform_max = val; - return 0; -} - -static int cros_ec_codec_probe(struct snd_soc_component *component) -{ - int rc; - - struct cros_ec_codec_data *codec_data = - snd_soc_component_get_drvdata(component); - - rc = cros_ec_set_gain_range(codec_data->dev); - if (rc) - return rc; - - return snd_soc_add_component_controls(component, &mic_gain_control, 1); + return snd_soc_add_component_controls(component, + &dmic_controls[DMIC_CTL_GAIN], 1); } -static const struct snd_soc_component_driver cros_ec_component_driver = { - .probe = cros_ec_codec_probe, - .dapm_widgets = cros_ec_codec_dapm_widgets, - .num_dapm_widgets = ARRAY_SIZE(cros_ec_codec_dapm_widgets), - .dapm_routes = cros_ec_codec_dapm_routes, - .num_dapm_routes = ARRAY_SIZE(cros_ec_codec_dapm_routes), +static const struct snd_soc_component_driver i2s_rx_component_driver = { + .probe = i2s_rx_probe, + .dapm_widgets = i2s_rx_dapm_widgets, + .num_dapm_widgets = ARRAY_SIZE(i2s_rx_dapm_widgets), + .dapm_routes = i2s_rx_dapm_routes, + .num_dapm_routes = ARRAY_SIZE(i2s_rx_dapm_routes), }; -/* - * Platform device and platform driver fro cros-ec-codec. - */ -static int cros_ec_codec_platform_probe(struct platform_device *pd) +static int cros_ec_codec_platform_probe(struct platform_device *pdev) { - struct device *dev = &pd->dev; - struct cros_ec_device *ec_device = dev_get_drvdata(pd->dev.parent); - struct cros_ec_codec_data *codec_data; + struct device *dev = &pdev->dev; + struct cros_ec_device *ec_device = dev_get_drvdata(pdev->dev.parent); + struct cros_ec_codec_priv *priv; - codec_data = devm_kzalloc(dev, sizeof(struct cros_ec_codec_data), - GFP_KERNEL); - if (!codec_data) + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) return -ENOMEM; - codec_data->dev = dev; - codec_data->ec_device = ec_device; + priv->dev = dev; + priv->ec_device = ec_device; - platform_set_drvdata(pd, codec_data); + platform_set_drvdata(pdev, priv); - return devm_snd_soc_register_component(dev, &cros_ec_component_driver, - cros_ec_dai, ARRAY_SIZE(cros_ec_dai)); + return devm_snd_soc_register_component(dev, &i2s_rx_component_driver, + &i2s_rx_dai_driver, 1); } #ifdef CONFIG_OF @@ -427,7 +323,7 @@ MODULE_DEVICE_TABLE(of, cros_ec_codec_of_match); static struct platform_driver cros_ec_codec_platform_driver = { .driver = { - .name = DRV_NAME, + .name = "cros-ec-codec", .of_match_table = of_match_ptr(cros_ec_codec_of_match), }, .probe = cros_ec_codec_platform_probe, @@ -438,4 +334,4 @@ module_platform_driver(cros_ec_codec_platform_driver); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("ChromeOS EC codec driver"); MODULE_AUTHOR("Cheng-Yi Chiang "); -MODULE_ALIAS("platform:" DRV_NAME); +MODULE_ALIAS("platform:cros-ec-codec"); -- cgit v1.2.3-71-gd317 From 8f731d4c92c2ef9434d4d7f84882c6429754164b Mon Sep 17 00:00:00 2001 From: Tzung-Bi Shih Date: Mon, 14 Oct 2019 18:20:15 +0800 Subject: ASoC: cros_ec_codec: extract DMIC EC command from I2S RX Extract DMIC EC command from I2S RX. Setting and getting microphone gains is common features. Signed-off-by: Tzung-Bi Shih Acked-By: Benson Leung Link: https://lore.kernel.org/r/20191014180059.03.I93d9c65964f3c30f85a36d228e31150ff1917706@changeid Signed-off-by: Mark Brown --- drivers/platform/chrome/cros_ec_trace.c | 1 + include/linux/platform_data/cros_ec_commands.h | 49 ++++++++++++++++------ sound/soc/codecs/cros_ec_codec.c | 57 ++++++++++++++------------ 3 files changed, 68 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/drivers/platform/chrome/cros_ec_trace.c b/drivers/platform/chrome/cros_ec_trace.c index 901850004b2b..e73bb6a8b00e 100644 --- a/drivers/platform/chrome/cros_ec_trace.c +++ b/drivers/platform/chrome/cros_ec_trace.c @@ -98,6 +98,7 @@ TRACE_SYMBOL(EC_CMD_SB_READ_BLOCK), \ TRACE_SYMBOL(EC_CMD_SB_WRITE_BLOCK), \ TRACE_SYMBOL(EC_CMD_BATTERY_VENDOR_PARAM), \ + TRACE_SYMBOL(EC_CMD_EC_CODEC_DMIC), \ TRACE_SYMBOL(EC_CMD_EC_CODEC_I2S_RX), \ TRACE_SYMBOL(EC_CMD_REBOOT_EC), \ TRACE_SYMBOL(EC_CMD_GET_PANIC_INFO), \ diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 261ac83bd007..58e460c015ef 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -4466,18 +4466,48 @@ enum mkbp_cec_event { /*****************************************************************************/ +/* Commands for DMIC on audio codec. */ +#define EC_CMD_EC_CODEC_DMIC 0x00BC + +enum ec_codec_dmic_subcmd { + EC_CODEC_DMIC_SET_GAIN = 0x0, + EC_CODEC_DMIC_GET_GAIN = 0x1, + EC_CODEC_DMIC_SUBCMD_COUNT, +}; + +struct __ec_align1 ec_param_ec_codec_dmic_set_gain { + uint8_t left; + uint8_t right; + uint8_t reserved[2]; +}; + +struct __ec_align4 ec_param_ec_codec_dmic { + uint8_t cmd; /* enum ec_codec_dmic_subcmd */ + uint8_t reserved[3]; + + union { + struct ec_param_ec_codec_dmic_set_gain + set_gain_param; + }; +}; + +struct __ec_align1 ec_response_ec_codec_dmic_get_gain { + uint8_t left; + uint8_t right; +}; + +/*****************************************************************************/ + /* Commands for I2S RX on audio codec. */ -#define EC_CMD_EC_CODEC_I2S_RX 0x00BC +#define EC_CMD_EC_CODEC_I2S_RX 0x00BD enum ec_codec_i2s_rx_subcmd { EC_CODEC_I2S_RX_ENABLE = 0x0, EC_CODEC_I2S_RX_DISABLE = 0x1, - EC_CODEC_I2S_RX_SET_GAIN = 0x2, - EC_CODEC_I2S_RX_GET_GAIN = 0x3, - EC_CODEC_I2S_RX_SET_SAMPLE_DEPTH = 0x4, - EC_CODEC_I2S_RX_SET_DAIFMT = 0x5, - EC_CODEC_I2S_RX_SET_BCLK = 0x6, + EC_CODEC_I2S_RX_SET_SAMPLE_DEPTH = 0x2, + EC_CODEC_I2S_RX_SET_DAIFMT = 0x3, + EC_CODEC_I2S_RX_SET_BCLK = 0x4, EC_CODEC_I2S_RX_SUBCMD_COUNT, }; @@ -4521,8 +4551,6 @@ struct __ec_align4 ec_param_ec_codec_i2s_rx { union { struct ec_param_ec_codec_i2s_rx_set_sample_depth set_sample_depth_param; - struct ec_param_ec_codec_i2s_rx_set_gain - set_gain_param; struct ec_param_ec_codec_i2s_rx_set_daifmt set_daifmt_param; struct ec_param_ec_codec_i2s_rx_set_bclk @@ -4530,11 +4558,6 @@ struct __ec_align4 ec_param_ec_codec_i2s_rx { }; }; -struct __ec_align1 ec_response_ec_codec_i2s_rx_get_gain { - uint8_t left; - uint8_t right; -}; - /*****************************************************************************/ /* System commands */ diff --git a/sound/soc/codecs/cros_ec_codec.c b/sound/soc/codecs/cros_ec_codec.c index 179fa77291cd..c19c7fe42e2e 100644 --- a/sound/soc/codecs/cros_ec_codec.c +++ b/sound/soc/codecs/cros_ec_codec.c @@ -64,12 +64,12 @@ static int dmic_get_gain(struct snd_kcontrol *kcontrol, snd_soc_kcontrol_component(kcontrol); struct cros_ec_codec_priv *priv = snd_soc_component_get_drvdata(component); - struct ec_param_ec_codec_i2s_rx p; - struct ec_response_ec_codec_i2s_rx_get_gain r; + struct ec_param_ec_codec_dmic p; + struct ec_response_ec_codec_dmic_get_gain r; int ret; - p.cmd = EC_CODEC_I2S_RX_GET_GAIN; - ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_I2S_RX, + p.cmd = EC_CODEC_DMIC_GET_GAIN; + ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_DMIC, (uint8_t *)&p, sizeof(p), (uint8_t *)&r, sizeof(r)); if (ret < 0) @@ -93,17 +93,17 @@ static int dmic_put_gain(struct snd_kcontrol *kcontrol, int max_dmic_gain = control->max; int left = ucontrol->value.integer.value[0]; int right = ucontrol->value.integer.value[1]; - struct ec_param_ec_codec_i2s_rx p; + struct ec_param_ec_codec_dmic p; if (left > max_dmic_gain || right > max_dmic_gain) return -EINVAL; dev_dbg(component->dev, "set mic gain to %u, %u\n", left, right); - p.cmd = EC_CODEC_I2S_RX_SET_GAIN; + p.cmd = EC_CODEC_DMIC_SET_GAIN; p.set_gain_param.left = left; p.set_gain_param.right = right; - return send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_I2S_RX, + return send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_DMIC, (uint8_t *)&p, sizeof(p), NULL, 0); } @@ -120,6 +120,29 @@ static struct snd_kcontrol_new dmic_controls[] = { dmic_gain_tlv), }; +static int dmic_probe(struct snd_soc_component *component) +{ + struct cros_ec_codec_priv *priv = + snd_soc_component_get_drvdata(component); + struct device *dev = priv->dev; + int ret, val; + struct soc_mixer_control *control; + + ret = device_property_read_u32(dev, "max-dmic-gain", &val); + if (ret) { + dev_err(dev, "Failed to read 'max-dmic-gain'\n"); + return ret; + } + + control = (struct soc_mixer_control *) + dmic_controls[DMIC_CTL_GAIN].private_value; + control->max = val; + control->platform_max = val; + + return snd_soc_add_component_controls(component, + &dmic_controls[DMIC_CTL_GAIN], 1); +} + static int i2s_rx_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params, struct snd_soc_dai *dai) @@ -265,25 +288,7 @@ static struct snd_soc_dai_driver i2s_rx_dai_driver = { static int i2s_rx_probe(struct snd_soc_component *component) { - struct cros_ec_codec_priv *priv = - snd_soc_component_get_drvdata(component); - struct device *dev = priv->dev; - int ret, val; - struct soc_mixer_control *control; - - ret = device_property_read_u32(dev, "max-dmic-gain", &val); - if (ret) { - dev_err(dev, "Failed to read 'max-dmic-gain'\n"); - return ret; - } - - control = (struct soc_mixer_control *) - dmic_controls[DMIC_CTL_GAIN].private_value; - control->max = val; - control->platform_max = val; - - return snd_soc_add_component_controls(component, - &dmic_controls[DMIC_CTL_GAIN], 1); + return dmic_probe(component); } static const struct snd_soc_component_driver i2s_rx_component_driver = { -- cgit v1.2.3-71-gd317 From 104c6f8f7ff859ddd53b69c4af11e83f2971f0c4 Mon Sep 17 00:00:00 2001 From: Tzung-Bi Shih Date: Thu, 17 Oct 2019 22:00:09 +0800 Subject: platform/chrome: cros_ec: add common commands for EC codec Add the following common commands: - GET_CAPABILITIES - GET_SHM_ADDR - SET_SHM_ADDR Acked-by: Benson Leung Signed-off-by: Tzung-Bi Shih Link: https://lore.kernel.org/r/20191017213539.04.Idc3c6e1cd94b70bf010249928d4a93c6c90495b7@changeid Signed-off-by: Mark Brown --- drivers/platform/chrome/cros_ec_trace.c | 1 + include/linux/platform_data/cros_ec_commands.h | 64 +++++++++++++++++++++++++- 2 files changed, 63 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/platform/chrome/cros_ec_trace.c b/drivers/platform/chrome/cros_ec_trace.c index e73bb6a8b00e..2ea0d4e0d54d 100644 --- a/drivers/platform/chrome/cros_ec_trace.c +++ b/drivers/platform/chrome/cros_ec_trace.c @@ -98,6 +98,7 @@ TRACE_SYMBOL(EC_CMD_SB_READ_BLOCK), \ TRACE_SYMBOL(EC_CMD_SB_WRITE_BLOCK), \ TRACE_SYMBOL(EC_CMD_BATTERY_VENDOR_PARAM), \ + TRACE_SYMBOL(EC_CMD_EC_CODEC), \ TRACE_SYMBOL(EC_CMD_EC_CODEC_DMIC), \ TRACE_SYMBOL(EC_CMD_EC_CODEC_I2S_RX), \ TRACE_SYMBOL(EC_CMD_REBOOT_EC), \ diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 58e460c015ef..3ca0fa9e92a7 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -4466,8 +4466,68 @@ enum mkbp_cec_event { /*****************************************************************************/ +/* Commands for audio codec. */ +#define EC_CMD_EC_CODEC 0x00BC + +enum ec_codec_subcmd { + EC_CODEC_GET_CAPABILITIES = 0x0, + EC_CODEC_GET_SHM_ADDR = 0x1, + EC_CODEC_SET_SHM_ADDR = 0x2, + EC_CODEC_SUBCMD_COUNT, +}; + +enum ec_codec_cap { + EC_CODEC_CAP_LAST = 32, +}; + +enum ec_codec_shm_id { + EC_CODEC_SHM_ID_LAST, +}; + +enum ec_codec_shm_type { + EC_CODEC_SHM_TYPE_EC_RAM = 0x0, + EC_CODEC_SHM_TYPE_SYSTEM_RAM = 0x1, +}; + +struct __ec_align1 ec_param_ec_codec_get_shm_addr { + uint8_t shm_id; + uint8_t reserved[3]; +}; + +struct __ec_align4 ec_param_ec_codec_set_shm_addr { + uint64_t phys_addr; + uint32_t len; + uint8_t shm_id; + uint8_t reserved[3]; +}; + +struct __ec_align4 ec_param_ec_codec { + uint8_t cmd; /* enum ec_codec_subcmd */ + uint8_t reserved[3]; + + union { + struct ec_param_ec_codec_get_shm_addr + get_shm_addr_param; + struct ec_param_ec_codec_set_shm_addr + set_shm_addr_param; + }; +}; + +struct __ec_align4 ec_response_ec_codec_get_capabilities { + uint32_t capabilities; +}; + +struct __ec_align4 ec_response_ec_codec_get_shm_addr { + uint64_t phys_addr; + uint32_t len; + uint8_t type; + uint8_t reserved[3]; +}; + +/*****************************************************************************/ + /* Commands for DMIC on audio codec. */ -#define EC_CMD_EC_CODEC_DMIC 0x00BC +#define EC_CMD_EC_CODEC_DMIC 0x00BD enum ec_codec_dmic_subcmd { EC_CODEC_DMIC_SET_GAIN = 0x0, @@ -4500,7 +4560,7 @@ struct __ec_align1 ec_response_ec_codec_dmic_get_gain { /* Commands for I2S RX on audio codec. */ -#define EC_CMD_EC_CODEC_I2S_RX 0x00BD +#define EC_CMD_EC_CODEC_I2S_RX 0x00BE enum ec_codec_i2s_rx_subcmd { EC_CODEC_I2S_RX_ENABLE = 0x0, -- cgit v1.2.3-71-gd317 From f3e82ad43ca538a7e0db0f310e26c5e75db6ba18 Mon Sep 17 00:00:00 2001 From: Tzung-Bi Shih Date: Thu, 17 Oct 2019 22:00:10 +0800 Subject: ASoC: cros_ec_codec: read max DMIC gain from EC codec Read max DMIC gain from EC codec instead of DTS. Also removes the dt-binding of max-dmic-gain. Acked-by: Rob Herring Acked-by: Benson Leung Signed-off-by: Tzung-Bi Shih Link: https://lore.kernel.org/r/20191017213539.05.Id4657c864d544634f2b5c1c9b34fa8232ecba44d@changeid Signed-off-by: Mark Brown --- .../bindings/sound/google,cros-ec-codec.txt | 4 +- include/linux/platform_data/cros_ec_commands.h | 43 ++++++++++++++---- sound/soc/codecs/cros_ec_codec.c | 53 ++++++++++++++++------ 3 files changed, 73 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/Documentation/devicetree/bindings/sound/google,cros-ec-codec.txt b/Documentation/devicetree/bindings/sound/google,cros-ec-codec.txt index 1084f7f22eea..0ce9fafc78e2 100644 --- a/Documentation/devicetree/bindings/sound/google,cros-ec-codec.txt +++ b/Documentation/devicetree/bindings/sound/google,cros-ec-codec.txt @@ -1,4 +1,4 @@ -* Audio codec controlled by ChromeOS EC +Audio codec controlled by ChromeOS EC Google's ChromeOS EC codec is a digital mic codec provided by the Embedded Controller (EC) and is controlled via a host-command interface. @@ -9,7 +9,6 @@ Documentation/devicetree/bindings/mfd/cros-ec.txt). Required properties: - compatible: Must contain "google,cros-ec-codec" - #sound-dai-cells: Should be 1. The cell specifies number of DAIs. -- max-dmic-gain: A number for maximum gain in dB on digital microphone. Example: @@ -21,6 +20,5 @@ cros-ec@0 { cros_ec_codec: ec-codec { compatible = "google,cros-ec-codec"; #sound-dai-cells = <1>; - max-dmic-gain = <43>; }; }; diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 3ca0fa9e92a7..21db0d4d4025 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -4530,30 +4530,53 @@ struct __ec_align4 ec_response_ec_codec_get_shm_addr { #define EC_CMD_EC_CODEC_DMIC 0x00BD enum ec_codec_dmic_subcmd { - EC_CODEC_DMIC_SET_GAIN = 0x0, - EC_CODEC_DMIC_GET_GAIN = 0x1, + EC_CODEC_DMIC_GET_MAX_GAIN = 0x0, + EC_CODEC_DMIC_SET_GAIN_IDX = 0x1, + EC_CODEC_DMIC_GET_GAIN_IDX = 0x2, EC_CODEC_DMIC_SUBCMD_COUNT, }; -struct __ec_align1 ec_param_ec_codec_dmic_set_gain { - uint8_t left; - uint8_t right; +enum ec_codec_dmic_channel { + EC_CODEC_DMIC_CHANNEL_0 = 0x0, + EC_CODEC_DMIC_CHANNEL_1 = 0x1, + EC_CODEC_DMIC_CHANNEL_2 = 0x2, + EC_CODEC_DMIC_CHANNEL_3 = 0x3, + EC_CODEC_DMIC_CHANNEL_4 = 0x4, + EC_CODEC_DMIC_CHANNEL_5 = 0x5, + EC_CODEC_DMIC_CHANNEL_6 = 0x6, + EC_CODEC_DMIC_CHANNEL_7 = 0x7, + EC_CODEC_DMIC_CHANNEL_COUNT, +}; + +struct __ec_align1 ec_param_ec_codec_dmic_set_gain_idx { + uint8_t channel; /* enum ec_codec_dmic_channel */ + uint8_t gain; uint8_t reserved[2]; }; +struct __ec_align1 ec_param_ec_codec_dmic_get_gain_idx { + uint8_t channel; /* enum ec_codec_dmic_channel */ + uint8_t reserved[3]; +}; + struct __ec_align4 ec_param_ec_codec_dmic { uint8_t cmd; /* enum ec_codec_dmic_subcmd */ uint8_t reserved[3]; union { - struct ec_param_ec_codec_dmic_set_gain - set_gain_param; + struct ec_param_ec_codec_dmic_set_gain_idx + set_gain_idx_param; + struct ec_param_ec_codec_dmic_get_gain_idx + get_gain_idx_param; }; }; -struct __ec_align1 ec_response_ec_codec_dmic_get_gain { - uint8_t left; - uint8_t right; +struct __ec_align1 ec_response_ec_codec_dmic_get_max_gain { + uint8_t max_gain; +}; + +struct __ec_align1 ec_response_ec_codec_dmic_get_gain_idx { + uint8_t gain; }; /*****************************************************************************/ diff --git a/sound/soc/codecs/cros_ec_codec.c b/sound/soc/codecs/cros_ec_codec.c index c19c7fe42e2e..3d4f9e82d6e9 100644 --- a/sound/soc/codecs/cros_ec_codec.c +++ b/sound/soc/codecs/cros_ec_codec.c @@ -65,18 +65,26 @@ static int dmic_get_gain(struct snd_kcontrol *kcontrol, struct cros_ec_codec_priv *priv = snd_soc_component_get_drvdata(component); struct ec_param_ec_codec_dmic p; - struct ec_response_ec_codec_dmic_get_gain r; + struct ec_response_ec_codec_dmic_get_gain_idx r; int ret; - p.cmd = EC_CODEC_DMIC_GET_GAIN; + p.cmd = EC_CODEC_DMIC_GET_GAIN_IDX; + p.get_gain_idx_param.channel = EC_CODEC_DMIC_CHANNEL_0; ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_DMIC, (uint8_t *)&p, sizeof(p), (uint8_t *)&r, sizeof(r)); if (ret < 0) return ret; + ucontrol->value.integer.value[0] = r.gain; - ucontrol->value.integer.value[0] = r.left; - ucontrol->value.integer.value[1] = r.right; + p.cmd = EC_CODEC_DMIC_GET_GAIN_IDX; + p.get_gain_idx_param.channel = EC_CODEC_DMIC_CHANNEL_1; + ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_DMIC, + (uint8_t *)&p, sizeof(p), + (uint8_t *)&r, sizeof(r)); + if (ret < 0) + return ret; + ucontrol->value.integer.value[1] = r.gain; return 0; } @@ -94,15 +102,24 @@ static int dmic_put_gain(struct snd_kcontrol *kcontrol, int left = ucontrol->value.integer.value[0]; int right = ucontrol->value.integer.value[1]; struct ec_param_ec_codec_dmic p; + int ret; if (left > max_dmic_gain || right > max_dmic_gain) return -EINVAL; dev_dbg(component->dev, "set mic gain to %u, %u\n", left, right); - p.cmd = EC_CODEC_DMIC_SET_GAIN; - p.set_gain_param.left = left; - p.set_gain_param.right = right; + p.cmd = EC_CODEC_DMIC_SET_GAIN_IDX; + p.set_gain_idx_param.channel = EC_CODEC_DMIC_CHANNEL_0; + p.set_gain_idx_param.gain = left; + ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_DMIC, + (uint8_t *)&p, sizeof(p), NULL, 0); + if (ret < 0) + return ret; + + p.cmd = EC_CODEC_DMIC_SET_GAIN_IDX; + p.set_gain_idx_param.channel = EC_CODEC_DMIC_CHANNEL_1; + p.set_gain_idx_param.gain = right; return send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_DMIC, (uint8_t *)&p, sizeof(p), NULL, 0); } @@ -125,19 +142,27 @@ static int dmic_probe(struct snd_soc_component *component) struct cros_ec_codec_priv *priv = snd_soc_component_get_drvdata(component); struct device *dev = priv->dev; - int ret, val; struct soc_mixer_control *control; + struct ec_param_ec_codec_dmic p; + struct ec_response_ec_codec_dmic_get_max_gain r; + int ret; - ret = device_property_read_u32(dev, "max-dmic-gain", &val); - if (ret) { - dev_err(dev, "Failed to read 'max-dmic-gain'\n"); - return ret; + p.cmd = EC_CODEC_DMIC_GET_MAX_GAIN; + + ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_DMIC, + (uint8_t *)&p, sizeof(p), + (uint8_t *)&r, sizeof(r)); + if (ret < 0) { + dev_warn(dev, "get_max_gain() unsupported\n"); + return 0; } + dev_dbg(dev, "max gain = %d\n", r.max_gain); + control = (struct soc_mixer_control *) dmic_controls[DMIC_CTL_GAIN].private_value; - control->max = val; - control->platform_max = val; + control->max = r.max_gain; + control->platform_max = r.max_gain; return snd_soc_add_component_controls(component, &dmic_controls[DMIC_CTL_GAIN], 1); -- cgit v1.2.3-71-gd317 From 4f3d957718e7f0ac2b033dbf48c7cddecd0a8dd3 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 18 Oct 2019 13:54:25 +0300 Subject: spi: pxa2xx: No need to keep pointer to platform device There is no need to keep a pointer to the platform device. Currently there are no users of it directly, and if there will be in the future we may restore it from pointer to the struct device. Convert all users at the same time. Cc: Russell King Cc: Jaroslav Kysela Cc: Takashi Iwai Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20191018105429.82782-1-andriy.shevchenko@linux.intel.com Signed-off-by: Mark Brown --- arch/arm/plat-pxa/ssp.c | 4 ++-- drivers/spi/spi-pxa2xx.c | 2 +- include/linux/pxa2xx_ssp.h | 2 +- sound/soc/pxa/mmp-sspa.c | 2 +- sound/soc/pxa/pxa-ssp.c | 10 +++++----- 5 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/plat-pxa/ssp.c b/arch/arm/plat-pxa/ssp.c index 9a6e4923bd69..563440315acd 100644 --- a/arch/arm/plat-pxa/ssp.c +++ b/arch/arm/plat-pxa/ssp.c @@ -89,7 +89,7 @@ void pxa_ssp_free(struct ssp_device *ssp) ssp->use_count--; ssp->label = NULL; } else - dev_err(&ssp->pdev->dev, "device already free\n"); + dev_err(ssp->dev, "device already free\n"); mutex_unlock(&ssp_lock); } EXPORT_SYMBOL(pxa_ssp_free); @@ -118,7 +118,7 @@ static int pxa_ssp_probe(struct platform_device *pdev) if (ssp == NULL) return -ENOMEM; - ssp->pdev = pdev; + ssp->dev = dev; ssp->clk = devm_clk_get(dev, NULL); if (IS_ERR(ssp->clk)) diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index bb6a14d1ab0f..59d1406a9c96 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -1567,7 +1567,7 @@ pxa2xx_spi_init_pdata(struct platform_device *pdev) ssp->clk = devm_clk_get(&pdev->dev, NULL); ssp->irq = platform_get_irq(pdev, 0); ssp->type = type; - ssp->pdev = pdev; + ssp->dev = &pdev->dev; ssp->port_id = pxa2xx_spi_get_port_id(adev); pdata->is_slave = of_property_read_bool(pdev->dev.of_node, "spi-slave"); diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index a5d1837e4f35..6facf27865f9 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -206,7 +206,7 @@ enum pxa_ssp_type { }; struct ssp_device { - struct platform_device *pdev; + struct device *dev; struct list_head node; struct clk *clk; diff --git a/sound/soc/pxa/mmp-sspa.c b/sound/soc/pxa/mmp-sspa.c index e3e5425b5c62..e701637a9ae9 100644 --- a/sound/soc/pxa/mmp-sspa.c +++ b/sound/soc/pxa/mmp-sspa.c @@ -177,7 +177,7 @@ static int mmp_sspa_set_dai_fmt(struct snd_soc_dai *cpu_dai, /* we can only change the settings if the port is not in use */ if ((mmp_sspa_read_reg(sspa, SSPA_TXSP) & SSPA_SP_S_EN) || (mmp_sspa_read_reg(sspa, SSPA_RXSP) & SSPA_SP_S_EN)) { - dev_err(&sspa->pdev->dev, + dev_err(sspa->dev, "can't change hardware dai format: stream is in use\n"); return -EINVAL; } diff --git a/sound/soc/pxa/pxa-ssp.c b/sound/soc/pxa/pxa-ssp.c index 5fdd1a24c232..6c5201431f6e 100644 --- a/sound/soc/pxa/pxa-ssp.c +++ b/sound/soc/pxa/pxa-ssp.c @@ -52,11 +52,11 @@ struct ssp_priv { static void dump_registers(struct ssp_device *ssp) { - dev_dbg(&ssp->pdev->dev, "SSCR0 0x%08x SSCR1 0x%08x SSTO 0x%08x\n", + dev_dbg(ssp->dev, "SSCR0 0x%08x SSCR1 0x%08x SSTO 0x%08x\n", pxa_ssp_read_reg(ssp, SSCR0), pxa_ssp_read_reg(ssp, SSCR1), pxa_ssp_read_reg(ssp, SSTO)); - dev_dbg(&ssp->pdev->dev, "SSPSP 0x%08x SSSR 0x%08x SSACD 0x%08x\n", + dev_dbg(ssp->dev, "SSPSP 0x%08x SSSR 0x%08x SSACD 0x%08x\n", pxa_ssp_read_reg(ssp, SSPSP), pxa_ssp_read_reg(ssp, SSSR), pxa_ssp_read_reg(ssp, SSACD)); } @@ -223,7 +223,7 @@ static int pxa_ssp_set_dai_sysclk(struct snd_soc_dai *cpu_dai, clk_id = PXA_SSP_CLK_EXT; } - dev_dbg(&ssp->pdev->dev, + dev_dbg(ssp->dev, "pxa_ssp_set_dai_sysclk id: %d, clk_id %d, freq %u\n", cpu_dai->id, clk_id, freq); @@ -316,7 +316,7 @@ static int pxa_ssp_set_pll(struct ssp_priv *priv, unsigned int freq) ssacd |= (0x6 << 4); - dev_dbg(&ssp->pdev->dev, + dev_dbg(ssp->dev, "Using SSACDD %x to supply %uHz\n", val, freq); break; @@ -687,7 +687,7 @@ static int pxa_ssp_hw_params(struct snd_pcm_substream *substream, * - complain loudly and fail if they've not been set up yet. */ if ((sscr0 & SSCR0_MOD) && !ttsa) { - dev_err(&ssp->pdev->dev, "No TDM timeslot configured\n"); + dev_err(ssp->dev, "No TDM timeslot configured\n"); return -EINVAL; } -- cgit v1.2.3-71-gd317 From a77fc11156893bd0332a1fb6e314e6268abf720b Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 11 Oct 2019 09:18:05 +0200 Subject: mfd: Switch the AB8500 GPADC to IIO The AB8500 GPADC driver is indeed a "general purpose ADC" driver, and while the IIO subsystem did not exist when the driver was first merged, it is never too late to clean things up and move it to the right place. Nowadays IIO provides the right abstractions and interfaces to do generic ADC work in the kernel. We have to cut a bunch of debugfs luggage to make this transition swift, but all these files to is read out the raw values of the ADC and the IIO subsystem already has a standard sysfs ABI for doing exactly this: no debugfs is needed. Acked-by: Lee Jones Signed-off-by: Linus Walleij Signed-off-by: Jonathan Cameron --- drivers/mfd/Kconfig | 7 - drivers/mfd/Makefile | 1 - drivers/mfd/ab8500-debugfs.c | 715 -------------------- drivers/mfd/ab8500-gpadc.c | 1075 ------------------------------- include/linux/mfd/abx500/ab8500-gpadc.h | 75 --- 5 files changed, 1873 deletions(-) delete mode 100644 drivers/mfd/ab8500-gpadc.c delete mode 100644 include/linux/mfd/abx500/ab8500-gpadc.h (limited to 'include/linux') diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index ae24d3ea68ea..420900852166 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -1210,13 +1210,6 @@ config AB8500_DEBUG Select this option if you want debug information using the debug filesystem, debugfs. -config AB8500_GPADC - bool "ST-Ericsson AB8500 GPADC driver" - depends on AB8500_CORE && REGULATOR_AB8500 - default y - help - AB8500 GPADC driver used to convert Acc and battery/ac/usb voltage - config MFD_DB8500_PRCMU bool "ST-Ericsson DB8500 Power Reset Control Management Unit" depends on UX500_SOC_DB8500 diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index c1067ea46204..aed99f08739f 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -177,7 +177,6 @@ obj-$(CONFIG_ABX500_CORE) += abx500-core.o obj-$(CONFIG_AB3100_CORE) += ab3100-core.o obj-$(CONFIG_AB3100_OTP) += ab3100-otp.o obj-$(CONFIG_AB8500_DEBUG) += ab8500-debugfs.o -obj-$(CONFIG_AB8500_GPADC) += ab8500-gpadc.o obj-$(CONFIG_MFD_DB8500_PRCMU) += db8500-prcmu.o # ab8500-core need to come after db8500-prcmu (which provides the channel) obj-$(CONFIG_AB8500_CORE) += ab8500-core.o ab8500-sysctrl.o diff --git a/drivers/mfd/ab8500-debugfs.c b/drivers/mfd/ab8500-debugfs.c index f4e26b6e5362..1a9a3414d4fa 100644 --- a/drivers/mfd/ab8500-debugfs.c +++ b/drivers/mfd/ab8500-debugfs.c @@ -84,7 +84,6 @@ #include #include -#include #ifdef CONFIG_DEBUG_FS #include @@ -103,11 +102,6 @@ static int num_irqs; static struct device_attribute **dev_attr; static char **event_name; -static u8 avg_sample = SAMPLE_16; -static u8 trig_edge = RISING_EDGE; -static u8 conv_type = ADC_SW; -static u8 trig_timer; - /** * struct ab8500_reg_range * @first: the first address of the range @@ -152,7 +146,6 @@ static struct hwreg_cfg hwreg_cfg = { }; #define AB8500_NAME_STRING "ab8500" -#define AB8500_ADC_NAME_STRING "gpadc" #define AB8500_NUM_BANKS AB8500_DEBUG_FIELD_LAST #define AB8500_REV_REG 0x80 @@ -1646,633 +1639,6 @@ report_write_failure: DEFINE_SHOW_ATTRIBUTE(ab8500_modem); -static int ab8500_gpadc_bat_ctrl_show(struct seq_file *s, void *p) -{ - int bat_ctrl_raw; - int bat_ctrl_convert; - struct ab8500_gpadc *gpadc; - - gpadc = ab8500_gpadc_get("ab8500-gpadc.0"); - bat_ctrl_raw = ab8500_gpadc_read_raw(gpadc, BAT_CTRL, - avg_sample, trig_edge, trig_timer, conv_type); - bat_ctrl_convert = ab8500_gpadc_ad_to_voltage(gpadc, - BAT_CTRL, bat_ctrl_raw); - - seq_printf(s, "%d,0x%X\n", bat_ctrl_convert, bat_ctrl_raw); - - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(ab8500_gpadc_bat_ctrl); - -static int ab8500_gpadc_btemp_ball_show(struct seq_file *s, void *p) -{ - int btemp_ball_raw; - int btemp_ball_convert; - struct ab8500_gpadc *gpadc; - - gpadc = ab8500_gpadc_get("ab8500-gpadc.0"); - btemp_ball_raw = ab8500_gpadc_read_raw(gpadc, BTEMP_BALL, - avg_sample, trig_edge, trig_timer, conv_type); - btemp_ball_convert = ab8500_gpadc_ad_to_voltage(gpadc, BTEMP_BALL, - btemp_ball_raw); - - seq_printf(s, "%d,0x%X\n", btemp_ball_convert, btemp_ball_raw); - - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(ab8500_gpadc_btemp_ball); - -static int ab8500_gpadc_main_charger_v_show(struct seq_file *s, void *p) -{ - int main_charger_v_raw; - int main_charger_v_convert; - struct ab8500_gpadc *gpadc; - - gpadc = ab8500_gpadc_get("ab8500-gpadc.0"); - main_charger_v_raw = ab8500_gpadc_read_raw(gpadc, MAIN_CHARGER_V, - avg_sample, trig_edge, trig_timer, conv_type); - main_charger_v_convert = ab8500_gpadc_ad_to_voltage(gpadc, - MAIN_CHARGER_V, main_charger_v_raw); - - seq_printf(s, "%d,0x%X\n", main_charger_v_convert, main_charger_v_raw); - - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(ab8500_gpadc_main_charger_v); - -static int ab8500_gpadc_acc_detect1_show(struct seq_file *s, void *p) -{ - int acc_detect1_raw; - int acc_detect1_convert; - struct ab8500_gpadc *gpadc; - - gpadc = ab8500_gpadc_get("ab8500-gpadc.0"); - acc_detect1_raw = ab8500_gpadc_read_raw(gpadc, ACC_DETECT1, - avg_sample, trig_edge, trig_timer, conv_type); - acc_detect1_convert = ab8500_gpadc_ad_to_voltage(gpadc, ACC_DETECT1, - acc_detect1_raw); - - seq_printf(s, "%d,0x%X\n", acc_detect1_convert, acc_detect1_raw); - - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(ab8500_gpadc_acc_detect1); - -static int ab8500_gpadc_acc_detect2_show(struct seq_file *s, void *p) -{ - int acc_detect2_raw; - int acc_detect2_convert; - struct ab8500_gpadc *gpadc; - - gpadc = ab8500_gpadc_get("ab8500-gpadc.0"); - acc_detect2_raw = ab8500_gpadc_read_raw(gpadc, ACC_DETECT2, - avg_sample, trig_edge, trig_timer, conv_type); - acc_detect2_convert = ab8500_gpadc_ad_to_voltage(gpadc, - ACC_DETECT2, acc_detect2_raw); - - seq_printf(s, "%d,0x%X\n", acc_detect2_convert, acc_detect2_raw); - - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(ab8500_gpadc_acc_detect2); - -static int ab8500_gpadc_aux1_show(struct seq_file *s, void *p) -{ - int aux1_raw; - int aux1_convert; - struct ab8500_gpadc *gpadc; - - gpadc = ab8500_gpadc_get("ab8500-gpadc.0"); - aux1_raw = ab8500_gpadc_read_raw(gpadc, ADC_AUX1, - avg_sample, trig_edge, trig_timer, conv_type); - aux1_convert = ab8500_gpadc_ad_to_voltage(gpadc, ADC_AUX1, - aux1_raw); - - seq_printf(s, "%d,0x%X\n", aux1_convert, aux1_raw); - - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(ab8500_gpadc_aux1); - -static int ab8500_gpadc_aux2_show(struct seq_file *s, void *p) -{ - int aux2_raw; - int aux2_convert; - struct ab8500_gpadc *gpadc; - - gpadc = ab8500_gpadc_get("ab8500-gpadc.0"); - aux2_raw = ab8500_gpadc_read_raw(gpadc, ADC_AUX2, - avg_sample, trig_edge, trig_timer, conv_type); - aux2_convert = ab8500_gpadc_ad_to_voltage(gpadc, ADC_AUX2, - aux2_raw); - - seq_printf(s, "%d,0x%X\n", aux2_convert, aux2_raw); - - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(ab8500_gpadc_aux2); - -static int ab8500_gpadc_main_bat_v_show(struct seq_file *s, void *p) -{ - int main_bat_v_raw; - int main_bat_v_convert; - struct ab8500_gpadc *gpadc; - - gpadc = ab8500_gpadc_get("ab8500-gpadc.0"); - main_bat_v_raw = ab8500_gpadc_read_raw(gpadc, MAIN_BAT_V, - avg_sample, trig_edge, trig_timer, conv_type); - main_bat_v_convert = ab8500_gpadc_ad_to_voltage(gpadc, MAIN_BAT_V, - main_bat_v_raw); - - seq_printf(s, "%d,0x%X\n", main_bat_v_convert, main_bat_v_raw); - - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(ab8500_gpadc_main_bat_v); - -static int ab8500_gpadc_vbus_v_show(struct seq_file *s, void *p) -{ - int vbus_v_raw; - int vbus_v_convert; - struct ab8500_gpadc *gpadc; - - gpadc = ab8500_gpadc_get("ab8500-gpadc.0"); - vbus_v_raw = ab8500_gpadc_read_raw(gpadc, VBUS_V, - avg_sample, trig_edge, trig_timer, conv_type); - vbus_v_convert = ab8500_gpadc_ad_to_voltage(gpadc, VBUS_V, - vbus_v_raw); - - seq_printf(s, "%d,0x%X\n", vbus_v_convert, vbus_v_raw); - - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(ab8500_gpadc_vbus_v); - -static int ab8500_gpadc_main_charger_c_show(struct seq_file *s, void *p) -{ - int main_charger_c_raw; - int main_charger_c_convert; - struct ab8500_gpadc *gpadc; - - gpadc = ab8500_gpadc_get("ab8500-gpadc.0"); - main_charger_c_raw = ab8500_gpadc_read_raw(gpadc, MAIN_CHARGER_C, - avg_sample, trig_edge, trig_timer, conv_type); - main_charger_c_convert = ab8500_gpadc_ad_to_voltage(gpadc, - MAIN_CHARGER_C, main_charger_c_raw); - - seq_printf(s, "%d,0x%X\n", main_charger_c_convert, main_charger_c_raw); - - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(ab8500_gpadc_main_charger_c); - -static int ab8500_gpadc_usb_charger_c_show(struct seq_file *s, void *p) -{ - int usb_charger_c_raw; - int usb_charger_c_convert; - struct ab8500_gpadc *gpadc; - - gpadc = ab8500_gpadc_get("ab8500-gpadc.0"); - usb_charger_c_raw = ab8500_gpadc_read_raw(gpadc, USB_CHARGER_C, - avg_sample, trig_edge, trig_timer, conv_type); - usb_charger_c_convert = ab8500_gpadc_ad_to_voltage(gpadc, - USB_CHARGER_C, usb_charger_c_raw); - - seq_printf(s, "%d,0x%X\n", usb_charger_c_convert, usb_charger_c_raw); - - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(ab8500_gpadc_usb_charger_c); - -static int ab8500_gpadc_bk_bat_v_show(struct seq_file *s, void *p) -{ - int bk_bat_v_raw; - int bk_bat_v_convert; - struct ab8500_gpadc *gpadc; - - gpadc = ab8500_gpadc_get("ab8500-gpadc.0"); - bk_bat_v_raw = ab8500_gpadc_read_raw(gpadc, BK_BAT_V, - avg_sample, trig_edge, trig_timer, conv_type); - bk_bat_v_convert = ab8500_gpadc_ad_to_voltage(gpadc, - BK_BAT_V, bk_bat_v_raw); - - seq_printf(s, "%d,0x%X\n", bk_bat_v_convert, bk_bat_v_raw); - - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(ab8500_gpadc_bk_bat_v); - -static int ab8500_gpadc_die_temp_show(struct seq_file *s, void *p) -{ - int die_temp_raw; - int die_temp_convert; - struct ab8500_gpadc *gpadc; - - gpadc = ab8500_gpadc_get("ab8500-gpadc.0"); - die_temp_raw = ab8500_gpadc_read_raw(gpadc, DIE_TEMP, - avg_sample, trig_edge, trig_timer, conv_type); - die_temp_convert = ab8500_gpadc_ad_to_voltage(gpadc, DIE_TEMP, - die_temp_raw); - - seq_printf(s, "%d,0x%X\n", die_temp_convert, die_temp_raw); - - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(ab8500_gpadc_die_temp); - -static int ab8500_gpadc_usb_id_show(struct seq_file *s, void *p) -{ - int usb_id_raw; - int usb_id_convert; - struct ab8500_gpadc *gpadc; - - gpadc = ab8500_gpadc_get("ab8500-gpadc.0"); - usb_id_raw = ab8500_gpadc_read_raw(gpadc, USB_ID, - avg_sample, trig_edge, trig_timer, conv_type); - usb_id_convert = ab8500_gpadc_ad_to_voltage(gpadc, USB_ID, - usb_id_raw); - - seq_printf(s, "%d,0x%X\n", usb_id_convert, usb_id_raw); - - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(ab8500_gpadc_usb_id); - -static int ab8540_gpadc_xtal_temp_show(struct seq_file *s, void *p) -{ - int xtal_temp_raw; - int xtal_temp_convert; - struct ab8500_gpadc *gpadc; - - gpadc = ab8500_gpadc_get("ab8500-gpadc.0"); - xtal_temp_raw = ab8500_gpadc_read_raw(gpadc, XTAL_TEMP, - avg_sample, trig_edge, trig_timer, conv_type); - xtal_temp_convert = ab8500_gpadc_ad_to_voltage(gpadc, XTAL_TEMP, - xtal_temp_raw); - - seq_printf(s, "%d,0x%X\n", xtal_temp_convert, xtal_temp_raw); - - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(ab8540_gpadc_xtal_temp); - -static int ab8540_gpadc_vbat_true_meas_show(struct seq_file *s, void *p) -{ - int vbat_true_meas_raw; - int vbat_true_meas_convert; - struct ab8500_gpadc *gpadc; - - gpadc = ab8500_gpadc_get("ab8500-gpadc.0"); - vbat_true_meas_raw = ab8500_gpadc_read_raw(gpadc, VBAT_TRUE_MEAS, - avg_sample, trig_edge, trig_timer, conv_type); - vbat_true_meas_convert = - ab8500_gpadc_ad_to_voltage(gpadc, VBAT_TRUE_MEAS, - vbat_true_meas_raw); - - seq_printf(s, "%d,0x%X\n", vbat_true_meas_convert, vbat_true_meas_raw); - - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(ab8540_gpadc_vbat_true_meas); - -static int ab8540_gpadc_bat_ctrl_and_ibat_show(struct seq_file *s, void *p) -{ - int bat_ctrl_raw; - int bat_ctrl_convert; - int ibat_raw; - int ibat_convert; - struct ab8500_gpadc *gpadc; - - gpadc = ab8500_gpadc_get("ab8500-gpadc.0"); - bat_ctrl_raw = ab8500_gpadc_double_read_raw(gpadc, BAT_CTRL_AND_IBAT, - avg_sample, trig_edge, trig_timer, conv_type, &ibat_raw); - - bat_ctrl_convert = ab8500_gpadc_ad_to_voltage(gpadc, BAT_CTRL, - bat_ctrl_raw); - ibat_convert = ab8500_gpadc_ad_to_voltage(gpadc, IBAT_VIRTUAL_CHANNEL, - ibat_raw); - - seq_printf(s, - "%d,0x%X\n" - "%d,0x%X\n", - bat_ctrl_convert, bat_ctrl_raw, - ibat_convert, ibat_raw); - - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(ab8540_gpadc_bat_ctrl_and_ibat); - -static int ab8540_gpadc_vbat_meas_and_ibat_show(struct seq_file *s, void *p) -{ - int vbat_meas_raw; - int vbat_meas_convert; - int ibat_raw; - int ibat_convert; - struct ab8500_gpadc *gpadc; - - gpadc = ab8500_gpadc_get("ab8500-gpadc.0"); - vbat_meas_raw = ab8500_gpadc_double_read_raw(gpadc, VBAT_MEAS_AND_IBAT, - avg_sample, trig_edge, trig_timer, conv_type, &ibat_raw); - vbat_meas_convert = ab8500_gpadc_ad_to_voltage(gpadc, MAIN_BAT_V, - vbat_meas_raw); - ibat_convert = ab8500_gpadc_ad_to_voltage(gpadc, IBAT_VIRTUAL_CHANNEL, - ibat_raw); - - seq_printf(s, - "%d,0x%X\n" - "%d,0x%X\n", - vbat_meas_convert, vbat_meas_raw, - ibat_convert, ibat_raw); - - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(ab8540_gpadc_vbat_meas_and_ibat); - -static int ab8540_gpadc_vbat_true_meas_and_ibat_show(struct seq_file *s, void *p) -{ - int vbat_true_meas_raw; - int vbat_true_meas_convert; - int ibat_raw; - int ibat_convert; - struct ab8500_gpadc *gpadc; - - gpadc = ab8500_gpadc_get("ab8500-gpadc.0"); - vbat_true_meas_raw = ab8500_gpadc_double_read_raw(gpadc, - VBAT_TRUE_MEAS_AND_IBAT, avg_sample, trig_edge, - trig_timer, conv_type, &ibat_raw); - vbat_true_meas_convert = ab8500_gpadc_ad_to_voltage(gpadc, - VBAT_TRUE_MEAS, vbat_true_meas_raw); - ibat_convert = ab8500_gpadc_ad_to_voltage(gpadc, IBAT_VIRTUAL_CHANNEL, - ibat_raw); - - seq_printf(s, - "%d,0x%X\n" - "%d,0x%X\n", - vbat_true_meas_convert, vbat_true_meas_raw, - ibat_convert, ibat_raw); - - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(ab8540_gpadc_vbat_true_meas_and_ibat); - -static int ab8540_gpadc_bat_temp_and_ibat_show(struct seq_file *s, void *p) -{ - int bat_temp_raw; - int bat_temp_convert; - int ibat_raw; - int ibat_convert; - struct ab8500_gpadc *gpadc; - - gpadc = ab8500_gpadc_get("ab8500-gpadc.0"); - bat_temp_raw = ab8500_gpadc_double_read_raw(gpadc, BAT_TEMP_AND_IBAT, - avg_sample, trig_edge, trig_timer, conv_type, &ibat_raw); - bat_temp_convert = ab8500_gpadc_ad_to_voltage(gpadc, BTEMP_BALL, - bat_temp_raw); - ibat_convert = ab8500_gpadc_ad_to_voltage(gpadc, IBAT_VIRTUAL_CHANNEL, - ibat_raw); - - seq_printf(s, - "%d,0x%X\n" - "%d,0x%X\n", - bat_temp_convert, bat_temp_raw, - ibat_convert, ibat_raw); - - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(ab8540_gpadc_bat_temp_and_ibat); - -static int ab8540_gpadc_otp_calib_show(struct seq_file *s, void *p) -{ - struct ab8500_gpadc *gpadc; - u16 vmain_l, vmain_h, btemp_l, btemp_h; - u16 vbat_l, vbat_h, ibat_l, ibat_h; - - gpadc = ab8500_gpadc_get("ab8500-gpadc.0"); - ab8540_gpadc_get_otp(gpadc, &vmain_l, &vmain_h, &btemp_l, &btemp_h, - &vbat_l, &vbat_h, &ibat_l, &ibat_h); - seq_printf(s, - "VMAIN_L:0x%X\n" - "VMAIN_H:0x%X\n" - "BTEMP_L:0x%X\n" - "BTEMP_H:0x%X\n" - "VBAT_L:0x%X\n" - "VBAT_H:0x%X\n" - "IBAT_L:0x%X\n" - "IBAT_H:0x%X\n", - vmain_l, vmain_h, btemp_l, btemp_h, - vbat_l, vbat_h, ibat_l, ibat_h); - - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(ab8540_gpadc_otp_calib); - -static int ab8500_gpadc_avg_sample_print(struct seq_file *s, void *p) -{ - seq_printf(s, "%d\n", avg_sample); - - return 0; -} - -static int ab8500_gpadc_avg_sample_open(struct inode *inode, struct file *file) -{ - return single_open(file, ab8500_gpadc_avg_sample_print, - inode->i_private); -} - -static ssize_t ab8500_gpadc_avg_sample_write(struct file *file, - const char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct device *dev = ((struct seq_file *)(file->private_data))->private; - unsigned long user_avg_sample; - int err; - - err = kstrtoul_from_user(user_buf, count, 0, &user_avg_sample); - if (err) - return err; - - if ((user_avg_sample == SAMPLE_1) || (user_avg_sample == SAMPLE_4) - || (user_avg_sample == SAMPLE_8) - || (user_avg_sample == SAMPLE_16)) { - avg_sample = (u8) user_avg_sample; - } else { - dev_err(dev, - "debugfs err input: should be egal to 1, 4, 8 or 16\n"); - return -EINVAL; - } - - return count; -} - -static const struct file_operations ab8500_gpadc_avg_sample_fops = { - .open = ab8500_gpadc_avg_sample_open, - .read = seq_read, - .write = ab8500_gpadc_avg_sample_write, - .llseek = seq_lseek, - .release = single_release, - .owner = THIS_MODULE, -}; - -static int ab8500_gpadc_trig_edge_print(struct seq_file *s, void *p) -{ - seq_printf(s, "%d\n", trig_edge); - - return 0; -} - -static int ab8500_gpadc_trig_edge_open(struct inode *inode, struct file *file) -{ - return single_open(file, ab8500_gpadc_trig_edge_print, - inode->i_private); -} - -static ssize_t ab8500_gpadc_trig_edge_write(struct file *file, - const char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct device *dev = ((struct seq_file *)(file->private_data))->private; - unsigned long user_trig_edge; - int err; - - err = kstrtoul_from_user(user_buf, count, 0, &user_trig_edge); - if (err) - return err; - - if ((user_trig_edge == RISING_EDGE) - || (user_trig_edge == FALLING_EDGE)) { - trig_edge = (u8) user_trig_edge; - } else { - dev_err(dev, "Wrong input:\n" - "Enter 0. Rising edge\n" - "Enter 1. Falling edge\n"); - return -EINVAL; - } - - return count; -} - -static const struct file_operations ab8500_gpadc_trig_edge_fops = { - .open = ab8500_gpadc_trig_edge_open, - .read = seq_read, - .write = ab8500_gpadc_trig_edge_write, - .llseek = seq_lseek, - .release = single_release, - .owner = THIS_MODULE, -}; - -static int ab8500_gpadc_trig_timer_print(struct seq_file *s, void *p) -{ - seq_printf(s, "%d\n", trig_timer); - - return 0; -} - -static int ab8500_gpadc_trig_timer_open(struct inode *inode, struct file *file) -{ - return single_open(file, ab8500_gpadc_trig_timer_print, - inode->i_private); -} - -static ssize_t ab8500_gpadc_trig_timer_write(struct file *file, - const char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct device *dev = ((struct seq_file *)(file->private_data))->private; - unsigned long user_trig_timer; - int err; - - err = kstrtoul_from_user(user_buf, count, 0, &user_trig_timer); - if (err) - return err; - - if (user_trig_timer & ~0xFF) { - dev_err(dev, - "debugfs error input: should be between 0 to 255\n"); - return -EINVAL; - } - - trig_timer = (u8) user_trig_timer; - - return count; -} - -static const struct file_operations ab8500_gpadc_trig_timer_fops = { - .open = ab8500_gpadc_trig_timer_open, - .read = seq_read, - .write = ab8500_gpadc_trig_timer_write, - .llseek = seq_lseek, - .release = single_release, - .owner = THIS_MODULE, -}; - -static int ab8500_gpadc_conv_type_print(struct seq_file *s, void *p) -{ - seq_printf(s, "%d\n", conv_type); - - return 0; -} - -static int ab8500_gpadc_conv_type_open(struct inode *inode, struct file *file) -{ - return single_open(file, ab8500_gpadc_conv_type_print, - inode->i_private); -} - -static ssize_t ab8500_gpadc_conv_type_write(struct file *file, - const char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct device *dev = ((struct seq_file *)(file->private_data))->private; - unsigned long user_conv_type; - int err; - - err = kstrtoul_from_user(user_buf, count, 0, &user_conv_type); - if (err) - return err; - - if ((user_conv_type == ADC_SW) - || (user_conv_type == ADC_HW)) { - conv_type = (u8) user_conv_type; - } else { - dev_err(dev, "Wrong input:\n" - "Enter 0. ADC SW conversion\n" - "Enter 1. ADC HW conversion\n"); - return -EINVAL; - } - - return count; -} - -static const struct file_operations ab8500_gpadc_conv_type_fops = { - .open = ab8500_gpadc_conv_type_open, - .read = seq_read, - .write = ab8500_gpadc_conv_type_write, - .llseek = seq_lseek, - .release = single_release, - .owner = THIS_MODULE, -}; - /* * return length of an ASCII numerical value, 0 is string is not a * numerical value. @@ -2647,7 +2013,6 @@ static const struct file_operations ab8500_hwreg_fops = { static int ab8500_debug_probe(struct platform_device *plf) { struct dentry *ab8500_dir; - struct dentry *ab8500_gpadc_dir; struct ab8500 *ab8500; struct resource *res; @@ -2689,9 +2054,6 @@ static int ab8500_debug_probe(struct platform_device *plf) ab8500_dir = debugfs_create_dir(AB8500_NAME_STRING, NULL); - ab8500_gpadc_dir = debugfs_create_dir(AB8500_ADC_NAME_STRING, - ab8500_dir); - debugfs_create_file("all-bank-registers", S_IRUGO, ab8500_dir, &plf->dev, &ab8500_bank_registers_fops); debugfs_create_file("all-banks", S_IRUGO, ab8500_dir, @@ -2727,83 +2089,6 @@ static int ab8500_debug_probe(struct platform_device *plf) &plf->dev, &ab8500_hwreg_fops); debugfs_create_file("all-modem-registers", (S_IRUGO | S_IWUSR | S_IWGRP), ab8500_dir, &plf->dev, &ab8500_modem_fops); - debugfs_create_file("bat_ctrl", (S_IRUGO | S_IWUSR | S_IWGRP), - ab8500_gpadc_dir, &plf->dev, - &ab8500_gpadc_bat_ctrl_fops); - debugfs_create_file("btemp_ball", (S_IRUGO | S_IWUSR | S_IWGRP), - ab8500_gpadc_dir, &plf->dev, - &ab8500_gpadc_btemp_ball_fops); - debugfs_create_file("main_charger_v", (S_IRUGO | S_IWUSR | S_IWGRP), - ab8500_gpadc_dir, &plf->dev, - &ab8500_gpadc_main_charger_v_fops); - debugfs_create_file("acc_detect1", (S_IRUGO | S_IWUSR | S_IWGRP), - ab8500_gpadc_dir, &plf->dev, - &ab8500_gpadc_acc_detect1_fops); - debugfs_create_file("acc_detect2", (S_IRUGO | S_IWUSR | S_IWGRP), - ab8500_gpadc_dir, &plf->dev, - &ab8500_gpadc_acc_detect2_fops); - debugfs_create_file("adc_aux1", (S_IRUGO | S_IWUSR | S_IWGRP), - ab8500_gpadc_dir, &plf->dev, - &ab8500_gpadc_aux1_fops); - debugfs_create_file("adc_aux2", (S_IRUGO | S_IWUSR | S_IWGRP), - ab8500_gpadc_dir, &plf->dev, - &ab8500_gpadc_aux2_fops); - debugfs_create_file("main_bat_v", (S_IRUGO | S_IWUSR | S_IWGRP), - ab8500_gpadc_dir, &plf->dev, - &ab8500_gpadc_main_bat_v_fops); - debugfs_create_file("vbus_v", (S_IRUGO | S_IWUSR | S_IWGRP), - ab8500_gpadc_dir, &plf->dev, - &ab8500_gpadc_vbus_v_fops); - debugfs_create_file("main_charger_c", (S_IRUGO | S_IWUSR | S_IWGRP), - ab8500_gpadc_dir, &plf->dev, - &ab8500_gpadc_main_charger_c_fops); - debugfs_create_file("usb_charger_c", (S_IRUGO | S_IWUSR | S_IWGRP), - ab8500_gpadc_dir, &plf->dev, - &ab8500_gpadc_usb_charger_c_fops); - debugfs_create_file("bk_bat_v", (S_IRUGO | S_IWUSR | S_IWGRP), - ab8500_gpadc_dir, &plf->dev, - &ab8500_gpadc_bk_bat_v_fops); - debugfs_create_file("die_temp", (S_IRUGO | S_IWUSR | S_IWGRP), - ab8500_gpadc_dir, &plf->dev, - &ab8500_gpadc_die_temp_fops); - debugfs_create_file("usb_id", (S_IRUGO | S_IWUSR | S_IWGRP), - ab8500_gpadc_dir, &plf->dev, - &ab8500_gpadc_usb_id_fops); - if (is_ab8540(ab8500)) { - debugfs_create_file("xtal_temp", (S_IRUGO | S_IWUSR | S_IWGRP), - ab8500_gpadc_dir, &plf->dev, - &ab8540_gpadc_xtal_temp_fops); - debugfs_create_file("vbattruemeas", (S_IRUGO | S_IWUSR | S_IWGRP), - ab8500_gpadc_dir, &plf->dev, - &ab8540_gpadc_vbat_true_meas_fops); - debugfs_create_file("batctrl_and_ibat", (S_IRUGO | S_IWUGO), - ab8500_gpadc_dir, &plf->dev, - &ab8540_gpadc_bat_ctrl_and_ibat_fops); - debugfs_create_file("vbatmeas_and_ibat", (S_IRUGO | S_IWUGO), - ab8500_gpadc_dir, &plf->dev, - &ab8540_gpadc_vbat_meas_and_ibat_fops); - debugfs_create_file("vbattruemeas_and_ibat", (S_IRUGO | S_IWUGO), - ab8500_gpadc_dir, &plf->dev, - &ab8540_gpadc_vbat_true_meas_and_ibat_fops); - debugfs_create_file("battemp_and_ibat", (S_IRUGO | S_IWUGO), - ab8500_gpadc_dir, &plf->dev, - &ab8540_gpadc_bat_temp_and_ibat_fops); - debugfs_create_file("otp_calib", (S_IRUGO | S_IWUSR | S_IWGRP), - ab8500_gpadc_dir, &plf->dev, - &ab8540_gpadc_otp_calib_fops); - } - debugfs_create_file("avg_sample", (S_IRUGO | S_IWUSR | S_IWGRP), - ab8500_gpadc_dir, &plf->dev, - &ab8500_gpadc_avg_sample_fops); - debugfs_create_file("trig_edge", (S_IRUGO | S_IWUSR | S_IWGRP), - ab8500_gpadc_dir, &plf->dev, - &ab8500_gpadc_trig_edge_fops); - debugfs_create_file("trig_timer", (S_IRUGO | S_IWUSR | S_IWGRP), - ab8500_gpadc_dir, &plf->dev, - &ab8500_gpadc_trig_timer_fops); - debugfs_create_file("conv_type", (S_IRUGO | S_IWUSR | S_IWGRP), - ab8500_gpadc_dir, &plf->dev, - &ab8500_gpadc_conv_type_fops); return 0; } diff --git a/drivers/mfd/ab8500-gpadc.c b/drivers/mfd/ab8500-gpadc.c deleted file mode 100644 index 005f9ee34cd1..000000000000 --- a/drivers/mfd/ab8500-gpadc.c +++ /dev/null @@ -1,1075 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) ST-Ericsson SA 2010 - * - * Author: Arun R Murthy - * Author: Daniel Willerud - * Author: Johan Palsson - * Author: M'boumba Cedric Madianga - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -/* - * GPADC register offsets - * Bank : 0x0A - */ -#define AB8500_GPADC_CTRL1_REG 0x00 -#define AB8500_GPADC_CTRL2_REG 0x01 -#define AB8500_GPADC_CTRL3_REG 0x02 -#define AB8500_GPADC_AUTO_TIMER_REG 0x03 -#define AB8500_GPADC_STAT_REG 0x04 -#define AB8500_GPADC_MANDATAL_REG 0x05 -#define AB8500_GPADC_MANDATAH_REG 0x06 -#define AB8500_GPADC_AUTODATAL_REG 0x07 -#define AB8500_GPADC_AUTODATAH_REG 0x08 -#define AB8500_GPADC_MUX_CTRL_REG 0x09 -#define AB8540_GPADC_MANDATA2L_REG 0x09 -#define AB8540_GPADC_MANDATA2H_REG 0x0A -#define AB8540_GPADC_APEAAX_REG 0x10 -#define AB8540_GPADC_APEAAT_REG 0x11 -#define AB8540_GPADC_APEAAM_REG 0x12 -#define AB8540_GPADC_APEAAH_REG 0x13 -#define AB8540_GPADC_APEAAL_REG 0x14 - -/* - * OTP register offsets - * Bank : 0x15 - */ -#define AB8500_GPADC_CAL_1 0x0F -#define AB8500_GPADC_CAL_2 0x10 -#define AB8500_GPADC_CAL_3 0x11 -#define AB8500_GPADC_CAL_4 0x12 -#define AB8500_GPADC_CAL_5 0x13 -#define AB8500_GPADC_CAL_6 0x14 -#define AB8500_GPADC_CAL_7 0x15 -/* New calibration for 8540 */ -#define AB8540_GPADC_OTP4_REG_7 0x38 -#define AB8540_GPADC_OTP4_REG_6 0x39 -#define AB8540_GPADC_OTP4_REG_5 0x3A - -/* gpadc constants */ -#define EN_VINTCORE12 0x04 -#define EN_VTVOUT 0x02 -#define EN_GPADC 0x01 -#define DIS_GPADC 0x00 -#define AVG_1 0x00 -#define AVG_4 0x20 -#define AVG_8 0x40 -#define AVG_16 0x60 -#define ADC_SW_CONV 0x04 -#define EN_ICHAR 0x80 -#define BTEMP_PULL_UP 0x08 -#define EN_BUF 0x40 -#define DIS_ZERO 0x00 -#define GPADC_BUSY 0x01 -#define EN_FALLING 0x10 -#define EN_TRIG_EDGE 0x02 -#define EN_VBIAS_XTAL_TEMP 0x02 - -/* GPADC constants from AB8500 spec, UM0836 */ -#define ADC_RESOLUTION 1024 -#define ADC_CH_BTEMP_MIN 0 -#define ADC_CH_BTEMP_MAX 1350 -#define ADC_CH_DIETEMP_MIN 0 -#define ADC_CH_DIETEMP_MAX 1350 -#define ADC_CH_CHG_V_MIN 0 -#define ADC_CH_CHG_V_MAX 20030 -#define ADC_CH_ACCDET2_MIN 0 -#define ADC_CH_ACCDET2_MAX 2500 -#define ADC_CH_VBAT_MIN 2300 -#define ADC_CH_VBAT_MAX 4800 -#define ADC_CH_CHG_I_MIN 0 -#define ADC_CH_CHG_I_MAX 1500 -#define ADC_CH_BKBAT_MIN 0 -#define ADC_CH_BKBAT_MAX 3200 - -/* GPADC constants from AB8540 spec */ -#define ADC_CH_IBAT_MIN (-6000) /* mA range measured by ADC for ibat */ -#define ADC_CH_IBAT_MAX 6000 -#define ADC_CH_IBAT_MIN_V (-60) /* mV range measured by ADC for ibat */ -#define ADC_CH_IBAT_MAX_V 60 -#define IBAT_VDROP_L (-56) /* mV */ -#define IBAT_VDROP_H 56 - -/* This is used to not lose precision when dividing to get gain and offset */ -#define CALIB_SCALE 1000 -/* - * Number of bits shift used to not lose precision - * when dividing to get ibat gain. - */ -#define CALIB_SHIFT_IBAT 20 - -/* Time in ms before disabling regulator */ -#define GPADC_AUDOSUSPEND_DELAY 1 - -#define CONVERSION_TIME 500 /* ms */ - -enum cal_channels { - ADC_INPUT_VMAIN = 0, - ADC_INPUT_BTEMP, - ADC_INPUT_VBAT, - ADC_INPUT_IBAT, - NBR_CAL_INPUTS, -}; - -/** - * struct adc_cal_data - Table for storing gain and offset for the calibrated - * ADC channels - * @gain: Gain of the ADC channel - * @offset: Offset of the ADC channel - */ -struct adc_cal_data { - s64 gain; - s64 offset; - u16 otp_calib_hi; - u16 otp_calib_lo; -}; - -/** - * struct ab8500_gpadc - AB8500 GPADC device information - * @dev: pointer to the struct device - * @node: a list of AB8500 GPADCs, hence prepared for - reentrance - * @parent: pointer to the struct ab8500 - * @ab8500_gpadc_complete: pointer to the struct completion, to indicate - * the completion of gpadc conversion - * @ab8500_gpadc_lock: structure of type mutex - * @regu: pointer to the struct regulator - * @irq_sw: interrupt number that is used by gpadc for Sw - * conversion - * @irq_hw: interrupt number that is used by gpadc for Hw - * conversion - * @cal_data array of ADC calibration data structs - */ -struct ab8500_gpadc { - struct device *dev; - struct list_head node; - struct ab8500 *parent; - struct completion ab8500_gpadc_complete; - struct mutex ab8500_gpadc_lock; - struct regulator *regu; - int irq_sw; - int irq_hw; - struct adc_cal_data cal_data[NBR_CAL_INPUTS]; -}; - -static LIST_HEAD(ab8500_gpadc_list); - -/** - * ab8500_gpadc_get() - returns a reference to the primary AB8500 GPADC - * (i.e. the first GPADC in the instance list) - */ -struct ab8500_gpadc *ab8500_gpadc_get(char *name) -{ - struct ab8500_gpadc *gpadc; - - list_for_each_entry(gpadc, &ab8500_gpadc_list, node) { - if (!strcmp(name, dev_name(gpadc->dev))) - return gpadc; - } - - return ERR_PTR(-ENOENT); -} -EXPORT_SYMBOL(ab8500_gpadc_get); - -/** - * ab8500_gpadc_ad_to_voltage() - Convert a raw ADC value to a voltage - */ -int ab8500_gpadc_ad_to_voltage(struct ab8500_gpadc *gpadc, u8 channel, - int ad_value) -{ - int res; - - switch (channel) { - case MAIN_CHARGER_V: - /* For some reason we don't have calibrated data */ - if (!gpadc->cal_data[ADC_INPUT_VMAIN].gain) { - res = ADC_CH_CHG_V_MIN + (ADC_CH_CHG_V_MAX - - ADC_CH_CHG_V_MIN) * ad_value / - ADC_RESOLUTION; - break; - } - /* Here we can use the calibrated data */ - res = (int) (ad_value * gpadc->cal_data[ADC_INPUT_VMAIN].gain + - gpadc->cal_data[ADC_INPUT_VMAIN].offset) / CALIB_SCALE; - break; - - case XTAL_TEMP: - case BAT_CTRL: - case BTEMP_BALL: - case ACC_DETECT1: - case ADC_AUX1: - case ADC_AUX2: - /* For some reason we don't have calibrated data */ - if (!gpadc->cal_data[ADC_INPUT_BTEMP].gain) { - res = ADC_CH_BTEMP_MIN + (ADC_CH_BTEMP_MAX - - ADC_CH_BTEMP_MIN) * ad_value / - ADC_RESOLUTION; - break; - } - /* Here we can use the calibrated data */ - res = (int) (ad_value * gpadc->cal_data[ADC_INPUT_BTEMP].gain + - gpadc->cal_data[ADC_INPUT_BTEMP].offset) / CALIB_SCALE; - break; - - case MAIN_BAT_V: - case VBAT_TRUE_MEAS: - /* For some reason we don't have calibrated data */ - if (!gpadc->cal_data[ADC_INPUT_VBAT].gain) { - res = ADC_CH_VBAT_MIN + (ADC_CH_VBAT_MAX - - ADC_CH_VBAT_MIN) * ad_value / - ADC_RESOLUTION; - break; - } - /* Here we can use the calibrated data */ - res = (int) (ad_value * gpadc->cal_data[ADC_INPUT_VBAT].gain + - gpadc->cal_data[ADC_INPUT_VBAT].offset) / CALIB_SCALE; - break; - - case DIE_TEMP: - res = ADC_CH_DIETEMP_MIN + - (ADC_CH_DIETEMP_MAX - ADC_CH_DIETEMP_MIN) * ad_value / - ADC_RESOLUTION; - break; - - case ACC_DETECT2: - res = ADC_CH_ACCDET2_MIN + - (ADC_CH_ACCDET2_MAX - ADC_CH_ACCDET2_MIN) * ad_value / - ADC_RESOLUTION; - break; - - case VBUS_V: - res = ADC_CH_CHG_V_MIN + - (ADC_CH_CHG_V_MAX - ADC_CH_CHG_V_MIN) * ad_value / - ADC_RESOLUTION; - break; - - case MAIN_CHARGER_C: - case USB_CHARGER_C: - res = ADC_CH_CHG_I_MIN + - (ADC_CH_CHG_I_MAX - ADC_CH_CHG_I_MIN) * ad_value / - ADC_RESOLUTION; - break; - - case BK_BAT_V: - res = ADC_CH_BKBAT_MIN + - (ADC_CH_BKBAT_MAX - ADC_CH_BKBAT_MIN) * ad_value / - ADC_RESOLUTION; - break; - - case IBAT_VIRTUAL_CHANNEL: - /* For some reason we don't have calibrated data */ - if (!gpadc->cal_data[ADC_INPUT_IBAT].gain) { - res = ADC_CH_IBAT_MIN + (ADC_CH_IBAT_MAX - - ADC_CH_IBAT_MIN) * ad_value / - ADC_RESOLUTION; - break; - } - /* Here we can use the calibrated data */ - res = (int) (ad_value * gpadc->cal_data[ADC_INPUT_IBAT].gain + - gpadc->cal_data[ADC_INPUT_IBAT].offset) - >> CALIB_SHIFT_IBAT; - break; - - default: - dev_err(gpadc->dev, - "unknown channel, not possible to convert\n"); - res = -EINVAL; - break; - - } - return res; -} -EXPORT_SYMBOL(ab8500_gpadc_ad_to_voltage); - -/** - * ab8500_gpadc_sw_hw_convert() - gpadc conversion - * @channel: analog channel to be converted to digital data - * @avg_sample: number of ADC sample to average - * @trig_egde: selected ADC trig edge - * @trig_timer: selected ADC trigger delay timer - * @conv_type: selected conversion type (HW or SW conversion) - * - * This function converts the selected analog i/p to digital - * data. - */ -int ab8500_gpadc_sw_hw_convert(struct ab8500_gpadc *gpadc, u8 channel, - u8 avg_sample, u8 trig_edge, u8 trig_timer, u8 conv_type) -{ - int ad_value; - int voltage; - - ad_value = ab8500_gpadc_read_raw(gpadc, channel, avg_sample, - trig_edge, trig_timer, conv_type); - - /* On failure retry a second time */ - if (ad_value < 0) - ad_value = ab8500_gpadc_read_raw(gpadc, channel, avg_sample, - trig_edge, trig_timer, conv_type); - if (ad_value < 0) { - dev_err(gpadc->dev, "GPADC raw value failed ch: %d\n", - channel); - return ad_value; - } - - voltage = ab8500_gpadc_ad_to_voltage(gpadc, channel, ad_value); - if (voltage < 0) - dev_err(gpadc->dev, - "GPADC to voltage conversion failed ch: %d AD: 0x%x\n", - channel, ad_value); - - return voltage; -} -EXPORT_SYMBOL(ab8500_gpadc_sw_hw_convert); - -/** - * ab8500_gpadc_read_raw() - gpadc read - * @channel: analog channel to be read - * @avg_sample: number of ADC sample to average - * @trig_edge: selected trig edge - * @trig_timer: selected ADC trigger delay timer - * @conv_type: selected conversion type (HW or SW conversion) - * - * This function obtains the raw ADC value for an hardware conversion, - * this then needs to be converted by calling ab8500_gpadc_ad_to_voltage() - */ -int ab8500_gpadc_read_raw(struct ab8500_gpadc *gpadc, u8 channel, - u8 avg_sample, u8 trig_edge, u8 trig_timer, u8 conv_type) -{ - return ab8500_gpadc_double_read_raw(gpadc, channel, avg_sample, - trig_edge, trig_timer, conv_type, - NULL); -} - -int ab8500_gpadc_double_read_raw(struct ab8500_gpadc *gpadc, u8 channel, - u8 avg_sample, u8 trig_edge, u8 trig_timer, u8 conv_type, - int *ibat) -{ - int ret; - int looplimit = 0; - unsigned long completion_timeout; - u8 val, low_data, high_data, low_data2, high_data2; - u8 val_reg1 = 0; - unsigned int delay_min = 0; - unsigned int delay_max = 0; - u8 data_low_addr, data_high_addr; - - if (!gpadc) - return -ENODEV; - - /* check if convertion is supported */ - if ((gpadc->irq_sw < 0) && (conv_type == ADC_SW)) - return -ENOTSUPP; - if ((gpadc->irq_hw < 0) && (conv_type == ADC_HW)) - return -ENOTSUPP; - - mutex_lock(&gpadc->ab8500_gpadc_lock); - /* Enable VTVout LDO this is required for GPADC */ - pm_runtime_get_sync(gpadc->dev); - - /* Check if ADC is not busy, lock and proceed */ - do { - ret = abx500_get_register_interruptible(gpadc->dev, - AB8500_GPADC, AB8500_GPADC_STAT_REG, &val); - if (ret < 0) - goto out; - if (!(val & GPADC_BUSY)) - break; - msleep(20); - } while (++looplimit < 10); - if (looplimit >= 10 && (val & GPADC_BUSY)) { - dev_err(gpadc->dev, "gpadc_conversion: GPADC busy"); - ret = -EINVAL; - goto out; - } - - /* Enable GPADC */ - val_reg1 |= EN_GPADC; - - /* Select the channel source and set average samples */ - switch (avg_sample) { - case SAMPLE_1: - val = channel | AVG_1; - break; - case SAMPLE_4: - val = channel | AVG_4; - break; - case SAMPLE_8: - val = channel | AVG_8; - break; - default: - val = channel | AVG_16; - break; - } - - if (conv_type == ADC_HW) { - ret = abx500_set_register_interruptible(gpadc->dev, - AB8500_GPADC, AB8500_GPADC_CTRL3_REG, val); - val_reg1 |= EN_TRIG_EDGE; - if (trig_edge) - val_reg1 |= EN_FALLING; - } else - ret = abx500_set_register_interruptible(gpadc->dev, - AB8500_GPADC, AB8500_GPADC_CTRL2_REG, val); - if (ret < 0) { - dev_err(gpadc->dev, - "gpadc_conversion: set avg samples failed\n"); - goto out; - } - - /* - * Enable ADC, buffering, select rising edge and enable ADC path - * charging current sense if it needed, ABB 3.0 needs some special - * treatment too. - */ - switch (channel) { - case MAIN_CHARGER_C: - case USB_CHARGER_C: - val_reg1 |= EN_BUF | EN_ICHAR; - break; - case BTEMP_BALL: - if (!is_ab8500_2p0_or_earlier(gpadc->parent)) { - val_reg1 |= EN_BUF | BTEMP_PULL_UP; - /* - * Delay might be needed for ABB8500 cut 3.0, if not, - * remove when hardware will be availible - */ - delay_min = 1000; /* Delay in micro seconds */ - delay_max = 10000; /* large range optimises sleepmode */ - break; - } - /* Intentional fallthrough */ - default: - val_reg1 |= EN_BUF; - break; - } - - /* Write configuration to register */ - ret = abx500_set_register_interruptible(gpadc->dev, - AB8500_GPADC, AB8500_GPADC_CTRL1_REG, val_reg1); - if (ret < 0) { - dev_err(gpadc->dev, - "gpadc_conversion: set Control register failed\n"); - goto out; - } - - if (delay_min != 0) - usleep_range(delay_min, delay_max); - - if (conv_type == ADC_HW) { - /* Set trigger delay timer */ - ret = abx500_set_register_interruptible(gpadc->dev, - AB8500_GPADC, AB8500_GPADC_AUTO_TIMER_REG, trig_timer); - if (ret < 0) { - dev_err(gpadc->dev, - "gpadc_conversion: trig timer failed\n"); - goto out; - } - completion_timeout = 2 * HZ; - data_low_addr = AB8500_GPADC_AUTODATAL_REG; - data_high_addr = AB8500_GPADC_AUTODATAH_REG; - } else { - /* Start SW conversion */ - ret = abx500_mask_and_set_register_interruptible(gpadc->dev, - AB8500_GPADC, AB8500_GPADC_CTRL1_REG, - ADC_SW_CONV, ADC_SW_CONV); - if (ret < 0) { - dev_err(gpadc->dev, - "gpadc_conversion: start s/w conv failed\n"); - goto out; - } - completion_timeout = msecs_to_jiffies(CONVERSION_TIME); - data_low_addr = AB8500_GPADC_MANDATAL_REG; - data_high_addr = AB8500_GPADC_MANDATAH_REG; - } - - /* wait for completion of conversion */ - if (!wait_for_completion_timeout(&gpadc->ab8500_gpadc_complete, - completion_timeout)) { - dev_err(gpadc->dev, - "timeout didn't receive GPADC conv interrupt\n"); - ret = -EINVAL; - goto out; - } - - /* Read the converted RAW data */ - ret = abx500_get_register_interruptible(gpadc->dev, - AB8500_GPADC, data_low_addr, &low_data); - if (ret < 0) { - dev_err(gpadc->dev, "gpadc_conversion: read low data failed\n"); - goto out; - } - - ret = abx500_get_register_interruptible(gpadc->dev, - AB8500_GPADC, data_high_addr, &high_data); - if (ret < 0) { - dev_err(gpadc->dev, "gpadc_conversion: read high data failed\n"); - goto out; - } - - /* Check if double convertion is required */ - if ((channel == BAT_CTRL_AND_IBAT) || - (channel == VBAT_MEAS_AND_IBAT) || - (channel == VBAT_TRUE_MEAS_AND_IBAT) || - (channel == BAT_TEMP_AND_IBAT)) { - - if (conv_type == ADC_HW) { - /* not supported */ - ret = -ENOTSUPP; - dev_err(gpadc->dev, - "gpadc_conversion: only SW double conversion supported\n"); - goto out; - } else { - /* Read the converted RAW data 2 */ - ret = abx500_get_register_interruptible(gpadc->dev, - AB8500_GPADC, AB8540_GPADC_MANDATA2L_REG, - &low_data2); - if (ret < 0) { - dev_err(gpadc->dev, - "gpadc_conversion: read sw low data 2 failed\n"); - goto out; - } - - ret = abx500_get_register_interruptible(gpadc->dev, - AB8500_GPADC, AB8540_GPADC_MANDATA2H_REG, - &high_data2); - if (ret < 0) { - dev_err(gpadc->dev, - "gpadc_conversion: read sw high data 2 failed\n"); - goto out; - } - if (ibat != NULL) { - *ibat = (high_data2 << 8) | low_data2; - } else { - dev_warn(gpadc->dev, - "gpadc_conversion: ibat not stored\n"); - } - - } - } - - /* Disable GPADC */ - ret = abx500_set_register_interruptible(gpadc->dev, AB8500_GPADC, - AB8500_GPADC_CTRL1_REG, DIS_GPADC); - if (ret < 0) { - dev_err(gpadc->dev, "gpadc_conversion: disable gpadc failed\n"); - goto out; - } - - /* Disable VTVout LDO this is required for GPADC */ - pm_runtime_mark_last_busy(gpadc->dev); - pm_runtime_put_autosuspend(gpadc->dev); - - mutex_unlock(&gpadc->ab8500_gpadc_lock); - - return (high_data << 8) | low_data; - -out: - /* - * It has shown to be needed to turn off the GPADC if an error occurs, - * otherwise we might have problem when waiting for the busy bit in the - * GPADC status register to go low. In V1.1 there wait_for_completion - * seems to timeout when waiting for an interrupt.. Not seen in V2.0 - */ - (void) abx500_set_register_interruptible(gpadc->dev, AB8500_GPADC, - AB8500_GPADC_CTRL1_REG, DIS_GPADC); - pm_runtime_put(gpadc->dev); - mutex_unlock(&gpadc->ab8500_gpadc_lock); - dev_err(gpadc->dev, - "gpadc_conversion: Failed to AD convert channel %d\n", channel); - return ret; -} -EXPORT_SYMBOL(ab8500_gpadc_read_raw); - -/** - * ab8500_bm_gpadcconvend_handler() - isr for gpadc conversion completion - * @irq: irq number - * @data: pointer to the data passed during request irq - * - * This is a interrupt service routine for gpadc conversion completion. - * Notifies the gpadc completion is completed and the converted raw value - * can be read from the registers. - * Returns IRQ status(IRQ_HANDLED) - */ -static irqreturn_t ab8500_bm_gpadcconvend_handler(int irq, void *_gpadc) -{ - struct ab8500_gpadc *gpadc = _gpadc; - - complete(&gpadc->ab8500_gpadc_complete); - - return IRQ_HANDLED; -} - -static int otp_cal_regs[] = { - AB8500_GPADC_CAL_1, - AB8500_GPADC_CAL_2, - AB8500_GPADC_CAL_3, - AB8500_GPADC_CAL_4, - AB8500_GPADC_CAL_5, - AB8500_GPADC_CAL_6, - AB8500_GPADC_CAL_7, -}; - -static int otp4_cal_regs[] = { - AB8540_GPADC_OTP4_REG_7, - AB8540_GPADC_OTP4_REG_6, - AB8540_GPADC_OTP4_REG_5, -}; - -static void ab8500_gpadc_read_calibration_data(struct ab8500_gpadc *gpadc) -{ - int i; - int ret[ARRAY_SIZE(otp_cal_regs)]; - u8 gpadc_cal[ARRAY_SIZE(otp_cal_regs)]; - int ret_otp4[ARRAY_SIZE(otp4_cal_regs)]; - u8 gpadc_otp4[ARRAY_SIZE(otp4_cal_regs)]; - int vmain_high, vmain_low; - int btemp_high, btemp_low; - int vbat_high, vbat_low; - int ibat_high, ibat_low; - s64 V_gain, V_offset, V2A_gain, V2A_offset; - struct ab8500 *ab8500; - - ab8500 = gpadc->parent; - - /* First we read all OTP registers and store the error code */ - for (i = 0; i < ARRAY_SIZE(otp_cal_regs); i++) { - ret[i] = abx500_get_register_interruptible(gpadc->dev, - AB8500_OTP_EMUL, otp_cal_regs[i], &gpadc_cal[i]); - if (ret[i] < 0) - dev_err(gpadc->dev, "%s: read otp reg 0x%02x failed\n", - __func__, otp_cal_regs[i]); - } - - /* - * The ADC calibration data is stored in OTP registers. - * The layout of the calibration data is outlined below and a more - * detailed description can be found in UM0836 - * - * vm_h/l = vmain_high/low - * bt_h/l = btemp_high/low - * vb_h/l = vbat_high/low - * - * Data bits 8500/9540: - * | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 - * |.......|.......|.......|.......|.......|.......|.......|....... - * | | vm_h9 | vm_h8 - * |.......|.......|.......|.......|.......|.......|.......|....... - * | | vm_h7 | vm_h6 | vm_h5 | vm_h4 | vm_h3 | vm_h2 - * |.......|.......|.......|.......|.......|.......|.......|....... - * | vm_h1 | vm_h0 | vm_l4 | vm_l3 | vm_l2 | vm_l1 | vm_l0 | bt_h9 - * |.......|.......|.......|.......|.......|.......|.......|....... - * | bt_h8 | bt_h7 | bt_h6 | bt_h5 | bt_h4 | bt_h3 | bt_h2 | bt_h1 - * |.......|.......|.......|.......|.......|.......|.......|....... - * | bt_h0 | bt_l4 | bt_l3 | bt_l2 | bt_l1 | bt_l0 | vb_h9 | vb_h8 - * |.......|.......|.......|.......|.......|.......|.......|....... - * | vb_h7 | vb_h6 | vb_h5 | vb_h4 | vb_h3 | vb_h2 | vb_h1 | vb_h0 - * |.......|.......|.......|.......|.......|.......|.......|....... - * | vb_l5 | vb_l4 | vb_l3 | vb_l2 | vb_l1 | vb_l0 | - * |.......|.......|.......|.......|.......|.......|.......|....... - * - * Data bits 8540: - * OTP2 - * | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 - * |.......|.......|.......|.......|.......|.......|.......|....... - * | - * |.......|.......|.......|.......|.......|.......|.......|....... - * | vm_h9 | vm_h8 | vm_h7 | vm_h6 | vm_h5 | vm_h4 | vm_h3 | vm_h2 - * |.......|.......|.......|.......|.......|.......|.......|....... - * | vm_h1 | vm_h0 | vm_l4 | vm_l3 | vm_l2 | vm_l1 | vm_l0 | bt_h9 - * |.......|.......|.......|.......|.......|.......|.......|....... - * | bt_h8 | bt_h7 | bt_h6 | bt_h5 | bt_h4 | bt_h3 | bt_h2 | bt_h1 - * |.......|.......|.......|.......|.......|.......|.......|....... - * | bt_h0 | bt_l4 | bt_l3 | bt_l2 | bt_l1 | bt_l0 | vb_h9 | vb_h8 - * |.......|.......|.......|.......|.......|.......|.......|....... - * | vb_h7 | vb_h6 | vb_h5 | vb_h4 | vb_h3 | vb_h2 | vb_h1 | vb_h0 - * |.......|.......|.......|.......|.......|.......|.......|....... - * | vb_l5 | vb_l4 | vb_l3 | vb_l2 | vb_l1 | vb_l0 | - * |.......|.......|.......|.......|.......|.......|.......|....... - * - * Data bits 8540: - * OTP4 - * | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 - * |.......|.......|.......|.......|.......|.......|.......|....... - * | | ib_h9 | ib_h8 | ib_h7 - * |.......|.......|.......|.......|.......|.......|.......|....... - * | ib_h6 | ib_h5 | ib_h4 | ib_h3 | ib_h2 | ib_h1 | ib_h0 | ib_l5 - * |.......|.......|.......|.......|.......|.......|.......|....... - * | ib_l4 | ib_l3 | ib_l2 | ib_l1 | ib_l0 | - * - * - * Ideal output ADC codes corresponding to injected input voltages - * during manufacturing is: - * - * vmain_high: Vin = 19500mV / ADC ideal code = 997 - * vmain_low: Vin = 315mV / ADC ideal code = 16 - * btemp_high: Vin = 1300mV / ADC ideal code = 985 - * btemp_low: Vin = 21mV / ADC ideal code = 16 - * vbat_high: Vin = 4700mV / ADC ideal code = 982 - * vbat_low: Vin = 2380mV / ADC ideal code = 33 - */ - - if (is_ab8540(ab8500)) { - /* Calculate gain and offset for VMAIN if all reads succeeded*/ - if (!(ret[1] < 0 || ret[2] < 0)) { - vmain_high = (((gpadc_cal[1] & 0xFF) << 2) | - ((gpadc_cal[2] & 0xC0) >> 6)); - vmain_low = ((gpadc_cal[2] & 0x3E) >> 1); - - gpadc->cal_data[ADC_INPUT_VMAIN].otp_calib_hi = - (u16)vmain_high; - gpadc->cal_data[ADC_INPUT_VMAIN].otp_calib_lo = - (u16)vmain_low; - - gpadc->cal_data[ADC_INPUT_VMAIN].gain = CALIB_SCALE * - (19500 - 315) / (vmain_high - vmain_low); - gpadc->cal_data[ADC_INPUT_VMAIN].offset = CALIB_SCALE * - 19500 - (CALIB_SCALE * (19500 - 315) / - (vmain_high - vmain_low)) * vmain_high; - } else { - gpadc->cal_data[ADC_INPUT_VMAIN].gain = 0; - } - - /* Read IBAT calibration Data */ - for (i = 0; i < ARRAY_SIZE(otp4_cal_regs); i++) { - ret_otp4[i] = abx500_get_register_interruptible( - gpadc->dev, AB8500_OTP_EMUL, - otp4_cal_regs[i], &gpadc_otp4[i]); - if (ret_otp4[i] < 0) - dev_err(gpadc->dev, - "%s: read otp4 reg 0x%02x failed\n", - __func__, otp4_cal_regs[i]); - } - - /* Calculate gain and offset for IBAT if all reads succeeded */ - if (!(ret_otp4[0] < 0 || ret_otp4[1] < 0 || ret_otp4[2] < 0)) { - ibat_high = (((gpadc_otp4[0] & 0x07) << 7) | - ((gpadc_otp4[1] & 0xFE) >> 1)); - ibat_low = (((gpadc_otp4[1] & 0x01) << 5) | - ((gpadc_otp4[2] & 0xF8) >> 3)); - - gpadc->cal_data[ADC_INPUT_IBAT].otp_calib_hi = - (u16)ibat_high; - gpadc->cal_data[ADC_INPUT_IBAT].otp_calib_lo = - (u16)ibat_low; - - V_gain = ((IBAT_VDROP_H - IBAT_VDROP_L) - << CALIB_SHIFT_IBAT) / (ibat_high - ibat_low); - - V_offset = (IBAT_VDROP_H << CALIB_SHIFT_IBAT) - - (((IBAT_VDROP_H - IBAT_VDROP_L) << - CALIB_SHIFT_IBAT) / (ibat_high - ibat_low)) - * ibat_high; - /* - * Result obtained is in mV (at a scale factor), - * we need to calculate gain and offset to get mA - */ - V2A_gain = (ADC_CH_IBAT_MAX - ADC_CH_IBAT_MIN)/ - (ADC_CH_IBAT_MAX_V - ADC_CH_IBAT_MIN_V); - V2A_offset = ((ADC_CH_IBAT_MAX_V * ADC_CH_IBAT_MIN - - ADC_CH_IBAT_MAX * ADC_CH_IBAT_MIN_V) - << CALIB_SHIFT_IBAT) - / (ADC_CH_IBAT_MAX_V - ADC_CH_IBAT_MIN_V); - - gpadc->cal_data[ADC_INPUT_IBAT].gain = - V_gain * V2A_gain; - gpadc->cal_data[ADC_INPUT_IBAT].offset = - V_offset * V2A_gain + V2A_offset; - } else { - gpadc->cal_data[ADC_INPUT_IBAT].gain = 0; - } - - dev_dbg(gpadc->dev, "IBAT gain %llu offset %llu\n", - gpadc->cal_data[ADC_INPUT_IBAT].gain, - gpadc->cal_data[ADC_INPUT_IBAT].offset); - } else { - /* Calculate gain and offset for VMAIN if all reads succeeded */ - if (!(ret[0] < 0 || ret[1] < 0 || ret[2] < 0)) { - vmain_high = (((gpadc_cal[0] & 0x03) << 8) | - ((gpadc_cal[1] & 0x3F) << 2) | - ((gpadc_cal[2] & 0xC0) >> 6)); - vmain_low = ((gpadc_cal[2] & 0x3E) >> 1); - - gpadc->cal_data[ADC_INPUT_VMAIN].otp_calib_hi = - (u16)vmain_high; - gpadc->cal_data[ADC_INPUT_VMAIN].otp_calib_lo = - (u16)vmain_low; - - gpadc->cal_data[ADC_INPUT_VMAIN].gain = CALIB_SCALE * - (19500 - 315) / (vmain_high - vmain_low); - - gpadc->cal_data[ADC_INPUT_VMAIN].offset = CALIB_SCALE * - 19500 - (CALIB_SCALE * (19500 - 315) / - (vmain_high - vmain_low)) * vmain_high; - } else { - gpadc->cal_data[ADC_INPUT_VMAIN].gain = 0; - } - } - - /* Calculate gain and offset for BTEMP if all reads succeeded */ - if (!(ret[2] < 0 || ret[3] < 0 || ret[4] < 0)) { - btemp_high = (((gpadc_cal[2] & 0x01) << 9) | - (gpadc_cal[3] << 1) | ((gpadc_cal[4] & 0x80) >> 7)); - btemp_low = ((gpadc_cal[4] & 0x7C) >> 2); - - gpadc->cal_data[ADC_INPUT_BTEMP].otp_calib_hi = (u16)btemp_high; - gpadc->cal_data[ADC_INPUT_BTEMP].otp_calib_lo = (u16)btemp_low; - - gpadc->cal_data[ADC_INPUT_BTEMP].gain = - CALIB_SCALE * (1300 - 21) / (btemp_high - btemp_low); - gpadc->cal_data[ADC_INPUT_BTEMP].offset = CALIB_SCALE * 1300 - - (CALIB_SCALE * (1300 - 21) / (btemp_high - btemp_low)) - * btemp_high; - } else { - gpadc->cal_data[ADC_INPUT_BTEMP].gain = 0; - } - - /* Calculate gain and offset for VBAT if all reads succeeded */ - if (!(ret[4] < 0 || ret[5] < 0 || ret[6] < 0)) { - vbat_high = (((gpadc_cal[4] & 0x03) << 8) | gpadc_cal[5]); - vbat_low = ((gpadc_cal[6] & 0xFC) >> 2); - - gpadc->cal_data[ADC_INPUT_VBAT].otp_calib_hi = (u16)vbat_high; - gpadc->cal_data[ADC_INPUT_VBAT].otp_calib_lo = (u16)vbat_low; - - gpadc->cal_data[ADC_INPUT_VBAT].gain = CALIB_SCALE * - (4700 - 2380) / (vbat_high - vbat_low); - gpadc->cal_data[ADC_INPUT_VBAT].offset = CALIB_SCALE * 4700 - - (CALIB_SCALE * (4700 - 2380) / - (vbat_high - vbat_low)) * vbat_high; - } else { - gpadc->cal_data[ADC_INPUT_VBAT].gain = 0; - } - - dev_dbg(gpadc->dev, "VMAIN gain %llu offset %llu\n", - gpadc->cal_data[ADC_INPUT_VMAIN].gain, - gpadc->cal_data[ADC_INPUT_VMAIN].offset); - - dev_dbg(gpadc->dev, "BTEMP gain %llu offset %llu\n", - gpadc->cal_data[ADC_INPUT_BTEMP].gain, - gpadc->cal_data[ADC_INPUT_BTEMP].offset); - - dev_dbg(gpadc->dev, "VBAT gain %llu offset %llu\n", - gpadc->cal_data[ADC_INPUT_VBAT].gain, - gpadc->cal_data[ADC_INPUT_VBAT].offset); -} - -#ifdef CONFIG_PM -static int ab8500_gpadc_runtime_suspend(struct device *dev) -{ - struct ab8500_gpadc *gpadc = dev_get_drvdata(dev); - - regulator_disable(gpadc->regu); - return 0; -} - -static int ab8500_gpadc_runtime_resume(struct device *dev) -{ - struct ab8500_gpadc *gpadc = dev_get_drvdata(dev); - int ret; - - ret = regulator_enable(gpadc->regu); - if (ret) - dev_err(dev, "Failed to enable vtvout LDO: %d\n", ret); - return ret; -} -#endif - -#ifdef CONFIG_PM_SLEEP -static int ab8500_gpadc_suspend(struct device *dev) -{ - struct ab8500_gpadc *gpadc = dev_get_drvdata(dev); - - mutex_lock(&gpadc->ab8500_gpadc_lock); - - pm_runtime_get_sync(dev); - - regulator_disable(gpadc->regu); - return 0; -} - -static int ab8500_gpadc_resume(struct device *dev) -{ - struct ab8500_gpadc *gpadc = dev_get_drvdata(dev); - int ret; - - ret = regulator_enable(gpadc->regu); - if (ret) - dev_err(dev, "Failed to enable vtvout LDO: %d\n", ret); - - pm_runtime_mark_last_busy(gpadc->dev); - pm_runtime_put_autosuspend(gpadc->dev); - - mutex_unlock(&gpadc->ab8500_gpadc_lock); - return ret; -} -#endif - -static int ab8500_gpadc_probe(struct platform_device *pdev) -{ - int ret = 0; - struct ab8500_gpadc *gpadc; - - gpadc = devm_kzalloc(&pdev->dev, - sizeof(struct ab8500_gpadc), GFP_KERNEL); - if (!gpadc) - return -ENOMEM; - - gpadc->irq_sw = platform_get_irq_byname(pdev, "SW_CONV_END"); - if (gpadc->irq_sw < 0) - dev_err(gpadc->dev, "failed to get platform sw_conv_end irq\n"); - - gpadc->irq_hw = platform_get_irq_byname(pdev, "HW_CONV_END"); - if (gpadc->irq_hw < 0) - dev_err(gpadc->dev, "failed to get platform hw_conv_end irq\n"); - - gpadc->dev = &pdev->dev; - gpadc->parent = dev_get_drvdata(pdev->dev.parent); - mutex_init(&gpadc->ab8500_gpadc_lock); - - /* Initialize completion used to notify completion of conversion */ - init_completion(&gpadc->ab8500_gpadc_complete); - - /* Register interrupts */ - if (gpadc->irq_sw >= 0) { - ret = request_threaded_irq(gpadc->irq_sw, NULL, - ab8500_bm_gpadcconvend_handler, - IRQF_NO_SUSPEND | IRQF_SHARED | IRQF_ONESHOT, - "ab8500-gpadc-sw", - gpadc); - if (ret < 0) { - dev_err(gpadc->dev, - "Failed to register interrupt irq: %d\n", - gpadc->irq_sw); - goto fail; - } - } - - if (gpadc->irq_hw >= 0) { - ret = request_threaded_irq(gpadc->irq_hw, NULL, - ab8500_bm_gpadcconvend_handler, - IRQF_NO_SUSPEND | IRQF_SHARED | IRQF_ONESHOT, - "ab8500-gpadc-hw", - gpadc); - if (ret < 0) { - dev_err(gpadc->dev, - "Failed to register interrupt irq: %d\n", - gpadc->irq_hw); - goto fail_irq; - } - } - - /* VTVout LDO used to power up ab8500-GPADC */ - gpadc->regu = devm_regulator_get(&pdev->dev, "vddadc"); - if (IS_ERR(gpadc->regu)) { - ret = PTR_ERR(gpadc->regu); - dev_err(gpadc->dev, "failed to get vtvout LDO\n"); - goto fail_irq; - } - - platform_set_drvdata(pdev, gpadc); - - ret = regulator_enable(gpadc->regu); - if (ret) { - dev_err(gpadc->dev, "Failed to enable vtvout LDO: %d\n", ret); - goto fail_enable; - } - - pm_runtime_set_autosuspend_delay(gpadc->dev, GPADC_AUDOSUSPEND_DELAY); - pm_runtime_use_autosuspend(gpadc->dev); - pm_runtime_set_active(gpadc->dev); - pm_runtime_enable(gpadc->dev); - - ab8500_gpadc_read_calibration_data(gpadc); - list_add_tail(&gpadc->node, &ab8500_gpadc_list); - dev_dbg(gpadc->dev, "probe success\n"); - - return 0; - -fail_enable: -fail_irq: - free_irq(gpadc->irq_sw, gpadc); - free_irq(gpadc->irq_hw, gpadc); -fail: - return ret; -} - -static int ab8500_gpadc_remove(struct platform_device *pdev) -{ - struct ab8500_gpadc *gpadc = platform_get_drvdata(pdev); - - /* remove this gpadc entry from the list */ - list_del(&gpadc->node); - /* remove interrupt - completion of Sw ADC conversion */ - if (gpadc->irq_sw >= 0) - free_irq(gpadc->irq_sw, gpadc); - if (gpadc->irq_hw >= 0) - free_irq(gpadc->irq_hw, gpadc); - - pm_runtime_get_sync(gpadc->dev); - pm_runtime_disable(gpadc->dev); - - regulator_disable(gpadc->regu); - - pm_runtime_set_suspended(gpadc->dev); - - pm_runtime_put_noidle(gpadc->dev); - - return 0; -} - -static const struct dev_pm_ops ab8500_gpadc_pm_ops = { - SET_RUNTIME_PM_OPS(ab8500_gpadc_runtime_suspend, - ab8500_gpadc_runtime_resume, - NULL) - SET_SYSTEM_SLEEP_PM_OPS(ab8500_gpadc_suspend, - ab8500_gpadc_resume) - -}; - -static struct platform_driver ab8500_gpadc_driver = { - .probe = ab8500_gpadc_probe, - .remove = ab8500_gpadc_remove, - .driver = { - .name = "ab8500-gpadc", - .pm = &ab8500_gpadc_pm_ops, - }, -}; - -static int __init ab8500_gpadc_init(void) -{ - return platform_driver_register(&ab8500_gpadc_driver); -} -subsys_initcall_sync(ab8500_gpadc_init); - -/** - * ab8540_gpadc_get_otp() - returns OTP values - * - */ -void ab8540_gpadc_get_otp(struct ab8500_gpadc *gpadc, - u16 *vmain_l, u16 *vmain_h, u16 *btemp_l, u16 *btemp_h, - u16 *vbat_l, u16 *vbat_h, u16 *ibat_l, u16 *ibat_h) -{ - *vmain_l = gpadc->cal_data[ADC_INPUT_VMAIN].otp_calib_lo; - *vmain_h = gpadc->cal_data[ADC_INPUT_VMAIN].otp_calib_hi; - *btemp_l = gpadc->cal_data[ADC_INPUT_BTEMP].otp_calib_lo; - *btemp_h = gpadc->cal_data[ADC_INPUT_BTEMP].otp_calib_hi; - *vbat_l = gpadc->cal_data[ADC_INPUT_VBAT].otp_calib_lo; - *vbat_h = gpadc->cal_data[ADC_INPUT_VBAT].otp_calib_hi; - *ibat_l = gpadc->cal_data[ADC_INPUT_IBAT].otp_calib_lo; - *ibat_h = gpadc->cal_data[ADC_INPUT_IBAT].otp_calib_hi; -} diff --git a/include/linux/mfd/abx500/ab8500-gpadc.h b/include/linux/mfd/abx500/ab8500-gpadc.h deleted file mode 100644 index 836c944abe2e..000000000000 --- a/include/linux/mfd/abx500/ab8500-gpadc.h +++ /dev/null @@ -1,75 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2010 ST-Ericsson SA - * - * Author: Arun R Murthy - * Author: Daniel Willerud - * Author: M'boumba Cedric Madianga - */ - -#ifndef _AB8500_GPADC_H -#define _AB8500_GPADC_H - -/* GPADC source: From datasheet(ADCSwSel[4:0] in GPADCCtrl2 - * and ADCHwSel[4:0] in GPADCCtrl3 ) */ -#define BAT_CTRL 0x01 -#define BTEMP_BALL 0x02 -#define MAIN_CHARGER_V 0x03 -#define ACC_DETECT1 0x04 -#define ACC_DETECT2 0x05 -#define ADC_AUX1 0x06 -#define ADC_AUX2 0x07 -#define MAIN_BAT_V 0x08 -#define VBUS_V 0x09 -#define MAIN_CHARGER_C 0x0A -#define USB_CHARGER_C 0x0B -#define BK_BAT_V 0x0C -#define DIE_TEMP 0x0D -#define USB_ID 0x0E -#define XTAL_TEMP 0x12 -#define VBAT_TRUE_MEAS 0x13 -#define BAT_CTRL_AND_IBAT 0x1C -#define VBAT_MEAS_AND_IBAT 0x1D -#define VBAT_TRUE_MEAS_AND_IBAT 0x1E -#define BAT_TEMP_AND_IBAT 0x1F - -/* Virtual channel used only for ibat convertion to ampere - * Battery current conversion (ibat) cannot be requested as a single conversion - * but it is always in combination with other input requests - */ -#define IBAT_VIRTUAL_CHANNEL 0xFF - -#define SAMPLE_1 1 -#define SAMPLE_4 4 -#define SAMPLE_8 8 -#define SAMPLE_16 16 -#define RISING_EDGE 0 -#define FALLING_EDGE 1 - -/* Arbitrary ADC conversion type constants */ -#define ADC_SW 0 -#define ADC_HW 1 - -struct ab8500_gpadc; - -struct ab8500_gpadc *ab8500_gpadc_get(char *name); -int ab8500_gpadc_sw_hw_convert(struct ab8500_gpadc *gpadc, u8 channel, - u8 avg_sample, u8 trig_edge, u8 trig_timer, u8 conv_type); -static inline int ab8500_gpadc_convert(struct ab8500_gpadc *gpadc, u8 channel) -{ - return ab8500_gpadc_sw_hw_convert(gpadc, channel, - SAMPLE_16, 0, 0, ADC_SW); -} - -int ab8500_gpadc_read_raw(struct ab8500_gpadc *gpadc, u8 channel, - u8 avg_sample, u8 trig_edge, u8 trig_timer, u8 conv_type); -int ab8500_gpadc_double_read_raw(struct ab8500_gpadc *gpadc, u8 channel, - u8 avg_sample, u8 trig_edge, u8 trig_timer, u8 conv_type, - int *ibat); -int ab8500_gpadc_ad_to_voltage(struct ab8500_gpadc *gpadc, - u8 channel, int ad_value); -void ab8540_gpadc_get_otp(struct ab8500_gpadc *gpadc, - u16 *vmain_l, u16 *vmain_h, u16 *btemp_l, u16 *btemp_h, - u16 *vbat_l, u16 *vbat_h, u16 *ibat_l, u16 *ibat_h); - -#endif /* _AB8500_GPADC_H */ -- cgit v1.2.3-71-gd317 From d49e6ee2d6c2b654c5eeb9aa1c4986cd1bec2582 Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Sun, 6 Oct 2019 16:03:09 -0400 Subject: counter: Simplify the count_read and count_write callbacks The count_read and count_write callbacks are simplified to pass val as unsigned long rather than as an opaque data structure. The opaque counter_count_read_value and counter_count_write_value structures, counter_count_value_type enum, and relevant counter_count_read_value_set and counter_count_write_value_get functions, are removed as they are no longer used. Cc: Patrick Havelange Acked-by: Fabrice Gasnier Acked-by: David Lechner Signed-off-by: William Breathitt Gray Signed-off-by: Jonathan Cameron --- drivers/counter/104-quad-8.c | 33 ++++-------- drivers/counter/counter.c | 101 ++++++------------------------------ drivers/counter/ftm-quaddec.c | 14 ++--- drivers/counter/stm32-lptimer-cnt.c | 5 +- drivers/counter/stm32-timer-cnt.c | 17 ++---- drivers/counter/ti-eqep.c | 19 +++---- include/linux/counter.h | 74 ++++---------------------- 7 files changed, 51 insertions(+), 212 deletions(-) (limited to 'include/linux') diff --git a/drivers/counter/104-quad-8.c b/drivers/counter/104-quad-8.c index 00b113f4b958..17e67a84777d 100644 --- a/drivers/counter/104-quad-8.c +++ b/drivers/counter/104-quad-8.c @@ -562,11 +562,10 @@ static const struct iio_chan_spec quad8_channels[] = { }; static int quad8_signal_read(struct counter_device *counter, - struct counter_signal *signal, struct counter_signal_read_value *val) + struct counter_signal *signal, enum counter_signal_value *val) { const struct quad8_iio *const priv = counter->priv; unsigned int state; - enum counter_signal_level level; /* Only Index signal levels can be read */ if (signal->id < 16) @@ -575,22 +574,19 @@ static int quad8_signal_read(struct counter_device *counter, state = inb(priv->base + QUAD8_REG_INDEX_INPUT_LEVELS) & BIT(signal->id - 16); - level = (state) ? COUNTER_SIGNAL_LEVEL_HIGH : COUNTER_SIGNAL_LEVEL_LOW; - - counter_signal_read_value_set(val, COUNTER_SIGNAL_LEVEL, &level); + *val = (state) ? COUNTER_SIGNAL_HIGH : COUNTER_SIGNAL_LOW; return 0; } static int quad8_count_read(struct counter_device *counter, - struct counter_count *count, struct counter_count_read_value *val) + struct counter_count *count, unsigned long *val) { const struct quad8_iio *const priv = counter->priv; const int base_offset = priv->base + 2 * count->id; unsigned int flags; unsigned int borrow; unsigned int carry; - unsigned long position; int i; flags = inb(base_offset + 1); @@ -598,36 +594,27 @@ static int quad8_count_read(struct counter_device *counter, carry = !!(flags & QUAD8_FLAG_CT); /* Borrow XOR Carry effectively doubles count range */ - position = (unsigned long)(borrow ^ carry) << 24; + *val = (unsigned long)(borrow ^ carry) << 24; /* Reset Byte Pointer; transfer Counter to Output Latch */ outb(QUAD8_CTR_RLD | QUAD8_RLD_RESET_BP | QUAD8_RLD_CNTR_OUT, base_offset + 1); for (i = 0; i < 3; i++) - position |= (unsigned long)inb(base_offset) << (8 * i); - - counter_count_read_value_set(val, COUNTER_COUNT_POSITION, &position); + *val |= (unsigned long)inb(base_offset) << (8 * i); return 0; } static int quad8_count_write(struct counter_device *counter, - struct counter_count *count, struct counter_count_write_value *val) + struct counter_count *count, unsigned long val) { const struct quad8_iio *const priv = counter->priv; const int base_offset = priv->base + 2 * count->id; - int err; - unsigned long position; int i; - err = counter_count_write_value_get(&position, COUNTER_COUNT_POSITION, - val); - if (err) - return err; - /* Only 24-bit values are supported */ - if (position > 0xFFFFFF) + if (val > 0xFFFFFF) return -EINVAL; /* Reset Byte Pointer */ @@ -635,7 +622,7 @@ static int quad8_count_write(struct counter_device *counter, /* Counter can only be set via Preset Register */ for (i = 0; i < 3; i++) - outb(position >> (8 * i), base_offset); + outb(val >> (8 * i), base_offset); /* Transfer Preset Register to Counter */ outb(QUAD8_CTR_RLD | QUAD8_RLD_PRESET_CNTR, base_offset + 1); @@ -644,9 +631,9 @@ static int quad8_count_write(struct counter_device *counter, outb(QUAD8_CTR_RLD | QUAD8_RLD_RESET_BP, base_offset + 1); /* Set Preset Register back to original value */ - position = priv->preset[count->id]; + val = priv->preset[count->id]; for (i = 0; i < 3; i++) - outb(position >> (8 * i), base_offset); + outb(val >> (8 * i), base_offset); /* Reset Borrow, Carry, Compare, and Sign flags */ outb(QUAD8_CTR_RLD | QUAD8_RLD_RESET_FLAGS, base_offset + 1); diff --git a/drivers/counter/counter.c b/drivers/counter/counter.c index 106bc7180cd8..6a683d086008 100644 --- a/drivers/counter/counter.c +++ b/drivers/counter/counter.c @@ -220,86 +220,6 @@ ssize_t counter_device_enum_available_read(struct counter_device *counter, } EXPORT_SYMBOL_GPL(counter_device_enum_available_read); -static const char *const counter_signal_level_str[] = { - [COUNTER_SIGNAL_LEVEL_LOW] = "low", - [COUNTER_SIGNAL_LEVEL_HIGH] = "high" -}; - -/** - * counter_signal_read_value_set - set counter_signal_read_value data - * @val: counter_signal_read_value structure to set - * @type: property Signal data represents - * @data: Signal data - * - * This function sets an opaque counter_signal_read_value structure with the - * provided Signal data. - */ -void counter_signal_read_value_set(struct counter_signal_read_value *const val, - const enum counter_signal_value_type type, - void *const data) -{ - if (type == COUNTER_SIGNAL_LEVEL) - val->len = sprintf(val->buf, "%s\n", - counter_signal_level_str[*(enum counter_signal_level *)data]); - else - val->len = 0; -} -EXPORT_SYMBOL_GPL(counter_signal_read_value_set); - -/** - * counter_count_read_value_set - set counter_count_read_value data - * @val: counter_count_read_value structure to set - * @type: property Count data represents - * @data: Count data - * - * This function sets an opaque counter_count_read_value structure with the - * provided Count data. - */ -void counter_count_read_value_set(struct counter_count_read_value *const val, - const enum counter_count_value_type type, - void *const data) -{ - switch (type) { - case COUNTER_COUNT_POSITION: - val->len = sprintf(val->buf, "%lu\n", *(unsigned long *)data); - break; - default: - val->len = 0; - } -} -EXPORT_SYMBOL_GPL(counter_count_read_value_set); - -/** - * counter_count_write_value_get - get counter_count_write_value data - * @data: Count data - * @type: property Count data represents - * @val: counter_count_write_value structure containing data - * - * This function extracts Count data from the provided opaque - * counter_count_write_value structure and stores it at the address provided by - * @data. - * - * RETURNS: - * 0 on success, negative error number on failure. - */ -int counter_count_write_value_get(void *const data, - const enum counter_count_value_type type, - const struct counter_count_write_value *const val) -{ - int err; - - switch (type) { - case COUNTER_COUNT_POSITION: - err = kstrtoul(val->buf, 0, data); - if (err) - return err; - break; - } - - return 0; -} -EXPORT_SYMBOL_GPL(counter_count_write_value_get); - struct counter_attr_parm { struct counter_device_attr_group *group; const char *prefix; @@ -369,6 +289,11 @@ struct counter_signal_unit { struct counter_signal *signal; }; +static const char *const counter_signal_value_str[] = { + [COUNTER_SIGNAL_LOW] = "low", + [COUNTER_SIGNAL_HIGH] = "high" +}; + static ssize_t counter_signal_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -377,13 +302,13 @@ static ssize_t counter_signal_show(struct device *dev, const struct counter_signal_unit *const component = devattr->component; struct counter_signal *const signal = component->signal; int err; - struct counter_signal_read_value val = { .buf = buf }; + enum counter_signal_value val; err = counter->ops->signal_read(counter, signal, &val); if (err) return err; - return val.len; + return sprintf(buf, "%s\n", counter_signal_value_str[val]); } struct counter_name_unit { @@ -788,13 +713,13 @@ static ssize_t counter_count_show(struct device *dev, const struct counter_count_unit *const component = devattr->component; struct counter_count *const count = component->count; int err; - struct counter_count_read_value val = { .buf = buf }; + unsigned long val; err = counter->ops->count_read(counter, count, &val); if (err) return err; - return val.len; + return sprintf(buf, "%lu\n", val); } static ssize_t counter_count_store(struct device *dev, @@ -806,9 +731,13 @@ static ssize_t counter_count_store(struct device *dev, const struct counter_count_unit *const component = devattr->component; struct counter_count *const count = component->count; int err; - struct counter_count_write_value val = { .buf = buf }; + unsigned long val; + + err = kstrtoul(buf, 0, &val); + if (err) + return err; - err = counter->ops->count_write(counter, count, &val); + err = counter->ops->count_write(counter, count, val); if (err) return err; diff --git a/drivers/counter/ftm-quaddec.c b/drivers/counter/ftm-quaddec.c index 4046aa9f9234..c2b3fdfd8b77 100644 --- a/drivers/counter/ftm-quaddec.c +++ b/drivers/counter/ftm-quaddec.c @@ -178,31 +178,25 @@ static const enum counter_count_function ftm_quaddec_count_functions[] = { static int ftm_quaddec_count_read(struct counter_device *counter, struct counter_count *count, - struct counter_count_read_value *val) + unsigned long *val) { struct ftm_quaddec *const ftm = counter->priv; uint32_t cntval; ftm_read(ftm, FTM_CNT, &cntval); - counter_count_read_value_set(val, COUNTER_COUNT_POSITION, &cntval); + *val = cntval; return 0; } static int ftm_quaddec_count_write(struct counter_device *counter, struct counter_count *count, - struct counter_count_write_value *val) + const unsigned long val) { struct ftm_quaddec *const ftm = counter->priv; - u32 cnt; - int err; - err = counter_count_write_value_get(&cnt, COUNTER_COUNT_POSITION, val); - if (err) - return err; - - if (cnt != 0) { + if (val != 0) { dev_warn(&ftm->pdev->dev, "Can only accept '0' as new counter value\n"); return -EINVAL; } diff --git a/drivers/counter/stm32-lptimer-cnt.c b/drivers/counter/stm32-lptimer-cnt.c index 28b63645c411..8e276eb655f5 100644 --- a/drivers/counter/stm32-lptimer-cnt.c +++ b/drivers/counter/stm32-lptimer-cnt.c @@ -377,8 +377,7 @@ static enum counter_synapse_action stm32_lptim_cnt_synapse_actions[] = { }; static int stm32_lptim_cnt_read(struct counter_device *counter, - struct counter_count *count, - struct counter_count_read_value *val) + struct counter_count *count, unsigned long *val) { struct stm32_lptim_cnt *const priv = counter->priv; u32 cnt; @@ -388,7 +387,7 @@ static int stm32_lptim_cnt_read(struct counter_device *counter, if (ret) return ret; - counter_count_read_value_set(val, COUNTER_COUNT_POSITION, &cnt); + *val = cnt; return 0; } diff --git a/drivers/counter/stm32-timer-cnt.c b/drivers/counter/stm32-timer-cnt.c index b61135b63ee8..3eafccec3beb 100644 --- a/drivers/counter/stm32-timer-cnt.c +++ b/drivers/counter/stm32-timer-cnt.c @@ -48,34 +48,27 @@ static enum counter_count_function stm32_count_functions[] = { }; static int stm32_count_read(struct counter_device *counter, - struct counter_count *count, - struct counter_count_read_value *val) + struct counter_count *count, unsigned long *val) { struct stm32_timer_cnt *const priv = counter->priv; u32 cnt; regmap_read(priv->regmap, TIM_CNT, &cnt); - counter_count_read_value_set(val, COUNTER_COUNT_POSITION, &cnt); + *val = cnt; return 0; } static int stm32_count_write(struct counter_device *counter, struct counter_count *count, - struct counter_count_write_value *val) + const unsigned long val) { struct stm32_timer_cnt *const priv = counter->priv; - u32 cnt; - int err; - - err = counter_count_write_value_get(&cnt, COUNTER_COUNT_POSITION, val); - if (err) - return err; - if (cnt > priv->ceiling) + if (val > priv->ceiling) return -EINVAL; - return regmap_write(priv->regmap, TIM_CNT, cnt); + return regmap_write(priv->regmap, TIM_CNT, val); } static int stm32_count_function_get(struct counter_device *counter, diff --git a/drivers/counter/ti-eqep.c b/drivers/counter/ti-eqep.c index 4b3ef2449c06..1ff07faef27f 100644 --- a/drivers/counter/ti-eqep.c +++ b/drivers/counter/ti-eqep.c @@ -93,35 +93,28 @@ struct ti_eqep_cnt { }; static int ti_eqep_count_read(struct counter_device *counter, - struct counter_count *count, - struct counter_count_read_value *val) + struct counter_count *count, unsigned long *val) { struct ti_eqep_cnt *priv = counter->priv; u32 cnt; regmap_read(priv->regmap32, QPOSCNT, &cnt); - counter_count_read_value_set(val, COUNTER_COUNT_POSITION, &cnt); + *val = cnt; return 0; } static int ti_eqep_count_write(struct counter_device *counter, - struct counter_count *count, - struct counter_count_write_value *val) + struct counter_count *count, unsigned long val) { struct ti_eqep_cnt *priv = counter->priv; - u32 cnt, max; - int err; - - err = counter_count_write_value_get(&cnt, COUNTER_COUNT_POSITION, val); - if (err) - return err; + u32 max; regmap_read(priv->regmap32, QPOSMAX, &max); - if (cnt > max) + if (val > max) return -EINVAL; - return regmap_write(priv->regmap32, QPOSCNT, cnt); + return regmap_write(priv->regmap32, QPOSCNT, val); } static int ti_eqep_function_get(struct counter_device *counter, diff --git a/include/linux/counter.h b/include/linux/counter.h index a061cdcdef7c..32fb4d8cc3fd 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -290,53 +290,22 @@ struct counter_device_state { const struct attribute_group **groups; }; -/** - * struct counter_signal_read_value - Opaque Signal read value - * @buf: string representation of Signal read value - * @len: length of string in @buf - */ -struct counter_signal_read_value { - char *buf; - size_t len; -}; - -/** - * struct counter_count_read_value - Opaque Count read value - * @buf: string representation of Count read value - * @len: length of string in @buf - */ -struct counter_count_read_value { - char *buf; - size_t len; -}; - -/** - * struct counter_count_write_value - Opaque Count write value - * @buf: string representation of Count write value - */ -struct counter_count_write_value { - const char *buf; +enum counter_signal_value { + COUNTER_SIGNAL_LOW = 0, + COUNTER_SIGNAL_HIGH }; /** * struct counter_ops - Callbacks from driver * @signal_read: optional read callback for Signal attribute. The read * value of the respective Signal should be passed back via - * the val parameter. val points to an opaque type which - * should be set only by calling the - * counter_signal_read_value_set function from within the - * signal_read callback. + * the val parameter. * @count_read: optional read callback for Count attribute. The read * value of the respective Count should be passed back via - * the val parameter. val points to an opaque type which - * should be set only by calling the - * counter_count_read_value_set function from within the - * count_read callback. + * the val parameter. * @count_write: optional write callback for Count attribute. The write * value for the respective Count is passed in via the val - * parameter. val points to an opaque type which should be - * accessed only by calling the - * counter_count_write_value_get function. + * parameter. * @function_get: function to get the current count function mode. Returns * 0 on success and negative error code on error. The index * of the respective Count's returned function mode should @@ -355,13 +324,11 @@ struct counter_count_write_value { struct counter_ops { int (*signal_read)(struct counter_device *counter, struct counter_signal *signal, - struct counter_signal_read_value *val); + enum counter_signal_value *val); int (*count_read)(struct counter_device *counter, - struct counter_count *count, - struct counter_count_read_value *val); + struct counter_count *count, unsigned long *val); int (*count_write)(struct counter_device *counter, - struct counter_count *count, - struct counter_count_write_value *val); + struct counter_count *count, unsigned long val); int (*function_get)(struct counter_device *counter, struct counter_count *count, size_t *function); int (*function_set)(struct counter_device *counter, @@ -477,29 +444,6 @@ struct counter_device { void *priv; }; -enum counter_signal_level { - COUNTER_SIGNAL_LEVEL_LOW = 0, - COUNTER_SIGNAL_LEVEL_HIGH -}; - -enum counter_signal_value_type { - COUNTER_SIGNAL_LEVEL = 0 -}; - -enum counter_count_value_type { - COUNTER_COUNT_POSITION = 0, -}; - -void counter_signal_read_value_set(struct counter_signal_read_value *const val, - const enum counter_signal_value_type type, - void *const data); -void counter_count_read_value_set(struct counter_count_read_value *const val, - const enum counter_count_value_type type, - void *const data); -int counter_count_write_value_get(void *const data, - const enum counter_count_value_type type, - const struct counter_count_write_value *const val); - int counter_register(struct counter_device *const counter); void counter_unregister(struct counter_device *const counter); int devm_counter_register(struct device *dev, -- cgit v1.2.3-71-gd317 From c5d550fb6e126a73247d4a98d6314a84f4805b98 Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Sun, 6 Oct 2019 16:03:11 -0400 Subject: counter: Fix typo in action_get description The action_get callback returns a Synapse's action mode. Signed-off-by: William Breathitt Gray Signed-off-by: Jonathan Cameron --- include/linux/counter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/counter.h b/include/linux/counter.h index 32fb4d8cc3fd..9dbd5df4cd34 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -315,7 +315,7 @@ enum counter_signal_value { * Count's functions_list array. * @action_get: function to get the current action mode. Returns 0 on * success and negative error code on error. The index of - * the respective Signal's returned action mode should be + * the respective Synapse's returned action mode should be * passed back via the action parameter. * @action_set: function to set the action mode. action is the index of * the requested action mode from the respective Synapse's -- cgit v1.2.3-71-gd317 From af65d1ad416bc6e069ccb9e649faeda224248f96 Mon Sep 17 00:00:00 2001 From: "Patel, Mayurkumar" Date: Fri, 18 Oct 2019 16:52:21 +0000 Subject: PCI/AER: Save AER Capability for suspend/resume Previously we did not save and restore the AER configuration on suspend/resume, so the configuration may be lost after resume. Save the AER configuration during suspend and restore it during resume. [bhelgaas: commit log] Link: https://lore.kernel.org/r/92EBB4272BF81E4089A7126EC1E7B28492C3B007@IRSMSX101.ger.corp.intel.com Signed-off-by: Mayurkumar Patel Signed-off-by: Kuppuswamy Sathyanarayanan Signed-off-by: Bjorn Helgaas Reviewed-by: Andy Shevchenko --- drivers/pci/access.c | 2 +- drivers/pci/pci.c | 2 ++ drivers/pci/pci.h | 1 + drivers/pci/pcie/aer.c | 62 ++++++++++++++++++++++++++++++++++++++++++++++++-- include/linux/aer.h | 4 ++++ 5 files changed, 68 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/access.c b/drivers/pci/access.c index 2fccb5762c76..79c4a2ef269a 100644 --- a/drivers/pci/access.c +++ b/drivers/pci/access.c @@ -355,7 +355,7 @@ static inline bool pcie_cap_has_sltctl(const struct pci_dev *dev) pcie_caps_reg(dev) & PCI_EXP_FLAGS_SLOT; } -static inline bool pcie_cap_has_rtctl(const struct pci_dev *dev) +bool pcie_cap_has_rtctl(const struct pci_dev *dev) { int type = pci_pcie_type(dev); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index e7982af9a5d8..d02636540ca1 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1361,6 +1361,7 @@ int pci_save_state(struct pci_dev *dev) pci_save_ltr_state(dev); pci_save_dpc_state(dev); + pci_save_aer_state(dev); return pci_save_vc_state(dev); } EXPORT_SYMBOL(pci_save_state); @@ -1474,6 +1475,7 @@ void pci_restore_state(struct pci_dev *dev) pci_restore_dpc_state(dev); pci_cleanup_aer_error_status_regs(dev); + pci_restore_aer_state(dev); pci_restore_config_space(dev); diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 3f6947ee3324..b96988f90315 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -12,6 +12,7 @@ extern const unsigned char pcie_link_speed[]; extern bool pci_early_dump; bool pcie_cap_has_lnkctl(const struct pci_dev *dev); +bool pcie_cap_has_rtctl(const struct pci_dev *dev); /* Functions internal to the PCI core code */ diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index b45bc47d04fe..443512882be4 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -448,12 +448,70 @@ int pci_cleanup_aer_error_status_regs(struct pci_dev *dev) return 0; } +void pci_save_aer_state(struct pci_dev *dev) +{ + struct pci_cap_saved_state *save_state; + u32 *cap; + int pos; + + pos = dev->aer_cap; + if (!pos) + return; + + save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_ERR); + if (!save_state) + return; + + cap = &save_state->cap.data[0]; + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, cap++); + pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, cap++); + pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK, cap++); + pci_read_config_dword(dev, pos + PCI_ERR_CAP, cap++); + if (pcie_cap_has_rtctl(dev)) + pci_read_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, cap++); +} + +void pci_restore_aer_state(struct pci_dev *dev) +{ + struct pci_cap_saved_state *save_state; + u32 *cap; + int pos; + + pos = dev->aer_cap; + if (!pos) + return; + + save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_ERR); + if (!save_state) + return; + + cap = &save_state->cap.data[0]; + pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, *cap++); + pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, *cap++); + pci_write_config_dword(dev, pos + PCI_ERR_COR_MASK, *cap++); + pci_write_config_dword(dev, pos + PCI_ERR_CAP, *cap++); + if (pcie_cap_has_rtctl(dev)) + pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, *cap++); +} + void pci_aer_init(struct pci_dev *dev) { + int n; + dev->aer_cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); + if (!dev->aer_cap) + return; - if (dev->aer_cap) - dev->aer_stats = kzalloc(sizeof(struct aer_stats), GFP_KERNEL); + dev->aer_stats = kzalloc(sizeof(struct aer_stats), GFP_KERNEL); + + /* + * We save/restore PCI_ERR_UNCOR_MASK, PCI_ERR_UNCOR_SEVER, + * PCI_ERR_COR_MASK, and PCI_ERR_CAP. Root and Root Complex Event + * Collectors also implement PCI_ERR_ROOT_COMMAND (PCIe r5.0, sec + * 7.8.4). + */ + n = pcie_cap_has_rtctl(dev) ? 5 : 4; + pci_add_ext_cap_save_buffer(dev, PCI_EXT_CAP_ID_ERR, sizeof(u32) * n); pci_cleanup_aer_error_status_regs(dev); } diff --git a/include/linux/aer.h b/include/linux/aer.h index 514bffa11dbb..fa19e01f418a 100644 --- a/include/linux/aer.h +++ b/include/linux/aer.h @@ -46,6 +46,8 @@ int pci_enable_pcie_error_reporting(struct pci_dev *dev); int pci_disable_pcie_error_reporting(struct pci_dev *dev); int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev); int pci_cleanup_aer_error_status_regs(struct pci_dev *dev); +void pci_save_aer_state(struct pci_dev *dev); +void pci_restore_aer_state(struct pci_dev *dev); #else static inline int pci_enable_pcie_error_reporting(struct pci_dev *dev) { @@ -63,6 +65,8 @@ static inline int pci_cleanup_aer_error_status_regs(struct pci_dev *dev) { return -EINVAL; } +static inline void pci_save_aer_state(struct pci_dev *dev) {} +static inline void pci_restore_aer_state(struct pci_dev *dev) {} #endif void cper_print_aer(struct pci_dev *dev, int aer_severity, -- cgit v1.2.3-71-gd317 From ae79d5588a04aec9dc4b0c6df700d131447306e0 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 19 Oct 2019 09:15:27 +0200 Subject: perf/core: Fix !CONFIG_PERF_EVENTS build warnings and failures sparc64 runs into this warning: include/linux/security.h:1913:52: warning: 'struct perf_event' declared inside parameter list will not be visible outside of this definition or declaration which is escalated to a build error in some of the .c files due to -Werror. Fix it via a forward declaration, like we do for perf_event_attr, the stub inlines don't actually need to know the structure of this struct. Fixes: da97e18458fb: ("perf_event: Add support for LSM and SELinux checks") Cc: "Joel Fernandes (Google)" Cc: linux-kernel@vger.kernel.org Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Alexander Shishkin Cc: Mark Rutland Cc: Namhyung Kim Signed-off-by: Ingo Molnar --- include/linux/security.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 4df79ffdc3a0..0a86bfea64d0 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1896,6 +1896,7 @@ static inline void security_bpf_prog_free(struct bpf_prog_aux *aux) #ifdef CONFIG_PERF_EVENTS struct perf_event_attr; +struct perf_event; #ifdef CONFIG_SECURITY extern int security_perf_event_open(struct perf_event_attr *attr, int type); -- cgit v1.2.3-71-gd317 From 8d6ac1cec7251a74c2d2f21e72b842c000206811 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Wed, 16 Oct 2019 22:16:22 +0200 Subject: rtc: add timestamp for end of 2199 Some RTCs handle date up to 2199. Link: https://lore.kernel.org/r/20191016201626.31309-1-alexandre.belloni@bootlin.com Signed-off-by: Alexandre Belloni --- include/linux/rtc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 2680f9b2b119..e86a9f307b82 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -165,6 +165,7 @@ struct rtc_device { #define RTC_TIMESTAMP_BEGIN_2000 946684800LL /* 2000-01-01 00:00:00 */ #define RTC_TIMESTAMP_END_2063 2966371199LL /* 2063-12-31 23:59:59 */ #define RTC_TIMESTAMP_END_2099 4102444799LL /* 2099-12-31 23:59:59 */ +#define RTC_TIMESTAMP_END_2199 7258118399LL /* 2199-12-31 23:59:59 */ #define RTC_TIMESTAMP_END_9999 253402300799LL /* 9999-12-31 23:59:59 */ extern struct rtc_device *devm_rtc_device_register(struct device *dev, -- cgit v1.2.3-71-gd317 From ae4866884338259318be94fa8f88015cced07000 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Sat, 19 Oct 2019 22:50:34 +0200 Subject: rtc: introduce lock helpers Introduce rtc_lock and rtc_unlock to shorten the code when locking and unlocking ops_lock from drivers. Link: https://lore.kernel.org/r/20191019205034.6382-1-alexandre.belloni@bootlin.com Signed-off-by: Alexandre Belloni --- include/linux/rtc.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index e86a9f307b82..4e9d3c71addb 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -159,6 +159,9 @@ struct rtc_device { }; #define to_rtc_device(d) container_of(d, struct rtc_device, dev) +#define rtc_lock(d) mutex_lock(&d->ops_lock) +#define rtc_unlock(d) mutex_unlock(&d->ops_lock) + /* useful timestamps */ #define RTC_TIMESTAMP_BEGIN_0000 -62167219200ULL /* 0000-01-01 00:00:00 */ #define RTC_TIMESTAMP_BEGIN_1900 -2208988800LL /* 1900-01-01 00:00:00 */ -- cgit v1.2.3-71-gd317 From 535bbe6a1f94dfc3e23cf1c9687459de7f3d2271 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Mon, 16 Sep 2019 14:23:44 -0500 Subject: soundwire: remove DAI_ID_RANGE definitions There is no reason to reserve a range of DAI IDs for SoundWire. This is not scalable and it's better to let the ASoC core allocate the dai->id when registering a component. Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20190916192348.467-3-pierre-louis.bossart@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/intel.c | 2 -- include/linux/soundwire/sdw.h | 3 --- 2 files changed, 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index bcc5077b2814..9d578dafa292 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -873,8 +873,6 @@ static int intel_create_dai(struct sdw_cdns *cdns, dais[i].capture.formats = SNDRV_PCM_FMTBIT_S16_LE; } - dais[i].id = SDW_DAI_ID_RANGE_START + i; - if (pcm) dais[i].ops = &intel_pcm_dai_ops; else diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index ea787201c3ac..688b40e65c89 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -40,9 +40,6 @@ struct sdw_slave; #define SDW_VALID_PORT_RANGE(n) ((n) <= 14 && (n) >= 1) -#define SDW_DAI_ID_RANGE_START 100 -#define SDW_DAI_ID_RANGE_END 200 - enum { SDW_PORT_DIRN_SINK = 0, SDW_PORT_DIRN_SOURCE, -- cgit v1.2.3-71-gd317 From b6bc07d4360dbf766e551f18e43c67fff6784955 Mon Sep 17 00:00:00 2001 From: Tzung-Bi Shih Date: Sat, 19 Oct 2019 15:02:51 +0800 Subject: ASoC: cros_ec_codec: support WoV 1. Get EC codec's capabilities. 2. Get and set SHM address if any. 3. Transmit language model to EC codec if needed. 4. Start to read audio data from EC codec if receives host event. Signed-off-by: Tzung-Bi Shih Acked-by: Enric Balletbo i Serra Link: https://lore.kernel.org/r/20191019143504.1.I5388b69a7a9c551078fed216a77440cee6dedf49@changeid Signed-off-by: Mark Brown --- drivers/platform/chrome/cros_ec_trace.c | 1 + include/linux/platform_data/cros_ec_commands.h | 69 +++ sound/soc/codecs/Kconfig | 2 + sound/soc/codecs/cros_ec_codec.c | 700 ++++++++++++++++++++++++- 4 files changed, 770 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/platform/chrome/cros_ec_trace.c b/drivers/platform/chrome/cros_ec_trace.c index 2ea0d4e0d54d..5af1d66d9eca 100644 --- a/drivers/platform/chrome/cros_ec_trace.c +++ b/drivers/platform/chrome/cros_ec_trace.c @@ -101,6 +101,7 @@ TRACE_SYMBOL(EC_CMD_EC_CODEC), \ TRACE_SYMBOL(EC_CMD_EC_CODEC_DMIC), \ TRACE_SYMBOL(EC_CMD_EC_CODEC_I2S_RX), \ + TRACE_SYMBOL(EC_CMD_EC_CODEC_WOV), \ TRACE_SYMBOL(EC_CMD_REBOOT_EC), \ TRACE_SYMBOL(EC_CMD_GET_PANIC_INFO), \ TRACE_SYMBOL(EC_CMD_ACPI_READ), \ diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 21db0d4d4025..69210881ebac 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -556,6 +556,9 @@ enum host_event_code { /* Keyboard recovery combo with hardware reinitialization */ EC_HOST_EVENT_KEYBOARD_RECOVERY_HW_REINIT = 30, + /* WoV */ + EC_HOST_EVENT_WOV = 31, + /* * The high bit of the event mask is not used as a host event code. If * it reads back as set, then the entire event mask should be @@ -4477,10 +4480,14 @@ enum ec_codec_subcmd { }; enum ec_codec_cap { + EC_CODEC_CAP_WOV_AUDIO_SHM = 0, + EC_CODEC_CAP_WOV_LANG_SHM = 1, EC_CODEC_CAP_LAST = 32, }; enum ec_codec_shm_id { + EC_CODEC_SHM_ID_WOV_AUDIO = 0x0, + EC_CODEC_SHM_ID_WOV_LANG = 0x1, EC_CODEC_SHM_ID_LAST, }; @@ -4641,6 +4648,68 @@ struct __ec_align4 ec_param_ec_codec_i2s_rx { }; }; +/*****************************************************************************/ +/* Commands for WoV on audio codec. */ + +#define EC_CMD_EC_CODEC_WOV 0x00BF + +enum ec_codec_wov_subcmd { + EC_CODEC_WOV_SET_LANG = 0x0, + EC_CODEC_WOV_SET_LANG_SHM = 0x1, + EC_CODEC_WOV_GET_LANG = 0x2, + EC_CODEC_WOV_ENABLE = 0x3, + EC_CODEC_WOV_DISABLE = 0x4, + EC_CODEC_WOV_READ_AUDIO = 0x5, + EC_CODEC_WOV_READ_AUDIO_SHM = 0x6, + EC_CODEC_WOV_SUBCMD_COUNT, +}; + +/* + * @hash is SHA256 of the whole language model. + * @total_len indicates the length of whole language model. + * @offset is the cursor from the beginning of the model. + * @buf is the packet buffer. + * @len denotes how many bytes in the buf. + */ +struct __ec_align4 ec_param_ec_codec_wov_set_lang { + uint8_t hash[32]; + uint32_t total_len; + uint32_t offset; + uint8_t buf[128]; + uint32_t len; +}; + +struct __ec_align4 ec_param_ec_codec_wov_set_lang_shm { + uint8_t hash[32]; + uint32_t total_len; +}; + +struct __ec_align4 ec_param_ec_codec_wov { + uint8_t cmd; /* enum ec_codec_wov_subcmd */ + uint8_t reserved[3]; + + union { + struct ec_param_ec_codec_wov_set_lang + set_lang_param; + struct ec_param_ec_codec_wov_set_lang_shm + set_lang_shm_param; + }; +}; + +struct __ec_align4 ec_response_ec_codec_wov_get_lang { + uint8_t hash[32]; +}; + +struct __ec_align4 ec_response_ec_codec_wov_read_audio { + uint8_t buf[128]; + uint32_t len; +}; + +struct __ec_align4 ec_response_ec_codec_wov_read_audio_shm { + uint32_t offset; + uint32_t len; +}; + /*****************************************************************************/ /* System commands */ diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig index 5a706102db04..1a4b084cc90d 100644 --- a/sound/soc/codecs/Kconfig +++ b/sound/soc/codecs/Kconfig @@ -509,6 +509,8 @@ config SND_SOC_CQ0093VC config SND_SOC_CROS_EC_CODEC tristate "codec driver for ChromeOS EC" depends on CROS_EC + select CRYPTO + select CRYPTO_SHA256 help If you say yes here you will get support for the ChromeOS Embedded Controller's Audio Codec. diff --git a/sound/soc/codecs/cros_ec_codec.c b/sound/soc/codecs/cros_ec_codec.c index 3d4f9e82d6e9..dd14caf9091a 100644 --- a/sound/soc/codecs/cros_ec_codec.c +++ b/sound/soc/codecs/cros_ec_codec.c @@ -8,10 +8,16 @@ * EC for audio function. */ +#include +#include #include #include +#include +#include #include #include +#include +#include #include #include #include @@ -23,8 +29,45 @@ struct cros_ec_codec_priv { struct device *dev; struct cros_ec_device *ec_device; + + /* common */ + uint32_t ec_capabilities; + + uint64_t ec_shm_addr; + uint32_t ec_shm_len; + + uint64_t ap_shm_phys_addr; + uint32_t ap_shm_len; + uint64_t ap_shm_addr; + uint64_t ap_shm_last_alloc; + + /* DMIC */ + atomic_t dmic_probed; + + /* WoV */ + bool wov_enabled; + uint8_t *wov_audio_shm_p; + uint32_t wov_audio_shm_len; + uint8_t wov_audio_shm_type; + uint8_t *wov_lang_shm_p; + uint32_t wov_lang_shm_len; + uint8_t wov_lang_shm_type; + + struct mutex wov_dma_lock; + uint8_t wov_buf[64000]; + uint32_t wov_rp, wov_wp; + size_t wov_dma_offset; + bool wov_burst_read; + struct snd_pcm_substream *wov_substream; + struct delayed_work wov_copy_work; + struct notifier_block wov_notifier; }; +static int ec_codec_capable(struct cros_ec_codec_priv *priv, uint8_t cap) +{ + return priv->ec_capabilities & BIT(cap); +} + static int send_ec_host_command(struct cros_ec_device *ec_dev, uint32_t cmd, uint8_t *out, size_t outsize, uint8_t *in, size_t insize) @@ -57,6 +100,41 @@ error: return ret; } +static int calculate_sha256(struct cros_ec_codec_priv *priv, + uint8_t *buf, uint32_t size, uint8_t *digest) +{ + struct crypto_shash *tfm; + + tfm = crypto_alloc_shash("sha256", CRYPTO_ALG_TYPE_SHASH, 0); + if (IS_ERR(tfm)) { + dev_err(priv->dev, "can't alloc shash\n"); + return PTR_ERR(tfm); + } + + { + SHASH_DESC_ON_STACK(desc, tfm); + + desc->tfm = tfm; + + crypto_shash_digest(desc, buf, size, digest); + shash_desc_zero(desc); + } + + crypto_free_shash(tfm); + +#ifdef DEBUG + { + char digest_str[65]; + + bin2hex(digest_str, digest, 32); + digest_str[64] = 0; + dev_dbg(priv->dev, "hash=%s\n", digest_str); + } +#endif + + return 0; +} + static int dmic_get_gain(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { @@ -147,6 +225,9 @@ static int dmic_probe(struct snd_soc_component *component) struct ec_response_ec_codec_dmic_get_max_gain r; int ret; + if (!atomic_add_unless(&priv->dmic_probed, 1, 1)) + return 0; + p.cmd = EC_CODEC_DMIC_GET_MAX_GAIN; ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_DMIC, @@ -324,23 +405,638 @@ static const struct snd_soc_component_driver i2s_rx_component_driver = { .num_dapm_routes = ARRAY_SIZE(i2s_rx_dapm_routes), }; +static void *wov_map_shm(struct cros_ec_codec_priv *priv, + uint8_t shm_id, uint32_t *len, uint8_t *type) +{ + struct ec_param_ec_codec p; + struct ec_response_ec_codec_get_shm_addr r; + uint32_t req, offset; + + p.cmd = EC_CODEC_GET_SHM_ADDR; + p.get_shm_addr_param.shm_id = shm_id; + if (send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC, + (uint8_t *)&p, sizeof(p), + (uint8_t *)&r, sizeof(r)) < 0) { + dev_err(priv->dev, "failed to EC_CODEC_GET_SHM_ADDR\n"); + return NULL; + } + + dev_dbg(priv->dev, "phys_addr=%#llx, len=%#x\n", r.phys_addr, r.len); + + *len = r.len; + *type = r.type; + + switch (r.type) { + case EC_CODEC_SHM_TYPE_EC_RAM: + return (void __force *)devm_ioremap_wc(priv->dev, + r.phys_addr + priv->ec_shm_addr, r.len); + case EC_CODEC_SHM_TYPE_SYSTEM_RAM: + if (r.phys_addr) { + dev_err(priv->dev, "unknown status\n"); + return NULL; + } + + req = round_up(r.len, PAGE_SIZE); + dev_dbg(priv->dev, "round up from %u to %u\n", r.len, req); + + if (priv->ap_shm_last_alloc + req > + priv->ap_shm_phys_addr + priv->ap_shm_len) { + dev_err(priv->dev, "insufficient space for AP SHM\n"); + return NULL; + } + + dev_dbg(priv->dev, "alloc AP SHM addr=%#llx, len=%#x\n", + priv->ap_shm_last_alloc, req); + + p.cmd = EC_CODEC_SET_SHM_ADDR; + p.set_shm_addr_param.phys_addr = priv->ap_shm_last_alloc; + p.set_shm_addr_param.len = req; + p.set_shm_addr_param.shm_id = shm_id; + if (send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC, + (uint8_t *)&p, sizeof(p), + NULL, 0) < 0) { + dev_err(priv->dev, "failed to EC_CODEC_SET_SHM_ADDR\n"); + return NULL; + } + + /* + * Note: EC codec only requests for `r.len' but we allocate + * round up PAGE_SIZE `req'. + */ + offset = priv->ap_shm_last_alloc - priv->ap_shm_phys_addr; + priv->ap_shm_last_alloc += req; + + return (void *)(uintptr_t)(priv->ap_shm_addr + offset); + default: + return NULL; + } +} + +static bool wov_queue_full(struct cros_ec_codec_priv *priv) +{ + return ((priv->wov_wp + 1) % sizeof(priv->wov_buf)) == priv->wov_rp; +} + +static size_t wov_queue_size(struct cros_ec_codec_priv *priv) +{ + if (priv->wov_wp >= priv->wov_rp) + return priv->wov_wp - priv->wov_rp; + else + return sizeof(priv->wov_buf) - priv->wov_rp + priv->wov_wp; +} + +static void wov_queue_dequeue(struct cros_ec_codec_priv *priv, size_t len) +{ + struct snd_pcm_runtime *runtime = priv->wov_substream->runtime; + size_t req; + + while (len) { + req = min(len, runtime->dma_bytes - priv->wov_dma_offset); + if (priv->wov_wp >= priv->wov_rp) + req = min(req, (size_t)priv->wov_wp - priv->wov_rp); + else + req = min(req, sizeof(priv->wov_buf) - priv->wov_rp); + + memcpy(runtime->dma_area + priv->wov_dma_offset, + priv->wov_buf + priv->wov_rp, req); + + priv->wov_dma_offset += req; + if (priv->wov_dma_offset == runtime->dma_bytes) + priv->wov_dma_offset = 0; + + priv->wov_rp += req; + if (priv->wov_rp == sizeof(priv->wov_buf)) + priv->wov_rp = 0; + + len -= req; + } + + snd_pcm_period_elapsed(priv->wov_substream); +} + +static void wov_queue_try_dequeue(struct cros_ec_codec_priv *priv) +{ + size_t period_bytes = snd_pcm_lib_period_bytes(priv->wov_substream); + + while (period_bytes && wov_queue_size(priv) >= period_bytes) { + wov_queue_dequeue(priv, period_bytes); + period_bytes = snd_pcm_lib_period_bytes(priv->wov_substream); + } +} + +static void wov_queue_enqueue(struct cros_ec_codec_priv *priv, + uint8_t *addr, size_t len, bool iomem) +{ + size_t req; + + while (len) { + if (wov_queue_full(priv)) { + wov_queue_try_dequeue(priv); + + if (wov_queue_full(priv)) { + dev_err(priv->dev, "overrun detected\n"); + return; + } + } + + if (priv->wov_wp >= priv->wov_rp) + req = sizeof(priv->wov_buf) - priv->wov_wp; + else + /* Note: waste 1-byte to differentiate full and empty */ + req = priv->wov_rp - priv->wov_wp - 1; + req = min(req, len); + + if (iomem) + memcpy_fromio(priv->wov_buf + priv->wov_wp, + (void __force __iomem *)addr, req); + else + memcpy(priv->wov_buf + priv->wov_wp, addr, req); + + priv->wov_wp += req; + if (priv->wov_wp == sizeof(priv->wov_buf)) + priv->wov_wp = 0; + + addr += req; + len -= req; + } + + wov_queue_try_dequeue(priv); +} + +static int wov_read_audio_shm(struct cros_ec_codec_priv *priv) +{ + struct ec_param_ec_codec_wov p; + struct ec_response_ec_codec_wov_read_audio_shm r; + int ret; + + p.cmd = EC_CODEC_WOV_READ_AUDIO_SHM; + ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_WOV, + (uint8_t *)&p, sizeof(p), + (uint8_t *)&r, sizeof(r)); + if (ret) { + dev_err(priv->dev, "failed to EC_CODEC_WOV_READ_AUDIO_SHM\n"); + return ret; + } + + if (!r.len) + dev_dbg(priv->dev, "no data, sleep\n"); + else + wov_queue_enqueue(priv, priv->wov_audio_shm_p + r.offset, r.len, + priv->wov_audio_shm_type == EC_CODEC_SHM_TYPE_EC_RAM); + return -EAGAIN; +} + +static int wov_read_audio(struct cros_ec_codec_priv *priv) +{ + struct ec_param_ec_codec_wov p; + struct ec_response_ec_codec_wov_read_audio r; + int remain = priv->wov_burst_read ? 16000 : 320; + int ret; + + while (remain >= 0) { + p.cmd = EC_CODEC_WOV_READ_AUDIO; + ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_WOV, + (uint8_t *)&p, sizeof(p), + (uint8_t *)&r, sizeof(r)); + if (ret) { + dev_err(priv->dev, + "failed to EC_CODEC_WOV_READ_AUDIO\n"); + return ret; + } + + if (!r.len) { + dev_dbg(priv->dev, "no data, sleep\n"); + priv->wov_burst_read = false; + break; + } + + wov_queue_enqueue(priv, r.buf, r.len, false); + remain -= r.len; + } + + return -EAGAIN; +} + +static void wov_copy_work(struct work_struct *w) +{ + struct cros_ec_codec_priv *priv = + container_of(w, struct cros_ec_codec_priv, wov_copy_work.work); + int ret; + + mutex_lock(&priv->wov_dma_lock); + if (!priv->wov_substream) { + dev_warn(priv->dev, "no pcm substream\n"); + goto leave; + } + + if (ec_codec_capable(priv, EC_CODEC_CAP_WOV_AUDIO_SHM)) + ret = wov_read_audio_shm(priv); + else + ret = wov_read_audio(priv); + + if (ret == -EAGAIN) + schedule_delayed_work(&priv->wov_copy_work, + msecs_to_jiffies(10)); + else if (ret) + dev_err(priv->dev, "failed to read audio data\n"); +leave: + mutex_unlock(&priv->wov_dma_lock); +} + +static int wov_enable_get(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *c = snd_soc_kcontrol_component(kcontrol); + struct cros_ec_codec_priv *priv = snd_soc_component_get_drvdata(c); + + ucontrol->value.integer.value[0] = priv->wov_enabled; + return 0; +} + +static int wov_enable_put(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *c = snd_soc_kcontrol_component(kcontrol); + struct cros_ec_codec_priv *priv = snd_soc_component_get_drvdata(c); + int enabled = ucontrol->value.integer.value[0]; + struct ec_param_ec_codec_wov p; + int ret; + + if (priv->wov_enabled != enabled) { + if (enabled) + p.cmd = EC_CODEC_WOV_ENABLE; + else + p.cmd = EC_CODEC_WOV_DISABLE; + + ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_WOV, + (uint8_t *)&p, sizeof(p), NULL, 0); + if (ret) { + dev_err(priv->dev, "failed to %s wov\n", + enabled ? "enable" : "disable"); + return ret; + } + + priv->wov_enabled = enabled; + } + + return 0; +} + +static int wov_set_lang_shm(struct cros_ec_codec_priv *priv, + uint8_t *buf, size_t size, uint8_t *digest) +{ + struct ec_param_ec_codec_wov p; + struct ec_param_ec_codec_wov_set_lang_shm *pp = &p.set_lang_shm_param; + int ret; + + if (size > priv->wov_lang_shm_len) { + dev_err(priv->dev, "no enough SHM size: %d\n", + priv->wov_lang_shm_len); + return -EIO; + } + + switch (priv->wov_lang_shm_type) { + case EC_CODEC_SHM_TYPE_EC_RAM: + memcpy_toio((void __force __iomem *)priv->wov_lang_shm_p, + buf, size); + memset_io((void __force __iomem *)priv->wov_lang_shm_p + size, + 0, priv->wov_lang_shm_len - size); + break; + case EC_CODEC_SHM_TYPE_SYSTEM_RAM: + memcpy(priv->wov_lang_shm_p, buf, size); + memset(priv->wov_lang_shm_p + size, 0, + priv->wov_lang_shm_len - size); + + /* make sure write to memory before calling host command */ + wmb(); + break; + } + + p.cmd = EC_CODEC_WOV_SET_LANG_SHM; + memcpy(pp->hash, digest, SHA256_DIGEST_SIZE); + pp->total_len = size; + ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_WOV, + (uint8_t *)&p, sizeof(p), NULL, 0); + if (ret) { + dev_err(priv->dev, "failed to EC_CODEC_WOV_SET_LANG_SHM\n"); + return ret; + } + + return 0; +} + +static int wov_set_lang(struct cros_ec_codec_priv *priv, + uint8_t *buf, size_t size, uint8_t *digest) +{ + struct ec_param_ec_codec_wov p; + struct ec_param_ec_codec_wov_set_lang *pp = &p.set_lang_param; + size_t i, req; + int ret; + + for (i = 0; i < size; i += req) { + req = min(size - i, ARRAY_SIZE(pp->buf)); + + p.cmd = EC_CODEC_WOV_SET_LANG; + memcpy(pp->hash, digest, SHA256_DIGEST_SIZE); + pp->total_len = size; + pp->offset = i; + memcpy(pp->buf, buf + i, req); + pp->len = req; + ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_WOV, + (uint8_t *)&p, sizeof(p), NULL, 0); + if (ret) { + dev_err(priv->dev, "failed to EC_CODEC_WOV_SET_LANG\n"); + return ret; + } + } + + return 0; +} + +static int wov_hotword_model_put(struct snd_kcontrol *kcontrol, + const unsigned int __user *bytes, + unsigned int size) +{ + struct snd_soc_component *component = snd_kcontrol_chip(kcontrol); + struct cros_ec_codec_priv *priv = + snd_soc_component_get_drvdata(component); + struct ec_param_ec_codec_wov p; + struct ec_response_ec_codec_wov_get_lang r; + uint8_t digest[SHA256_DIGEST_SIZE]; + uint8_t *buf; + int ret; + + /* Skips the TLV header. */ + bytes += 2; + size -= 8; + + dev_dbg(priv->dev, "%s: size=%d\n", __func__, size); + + buf = memdup_user(bytes, size); + if (IS_ERR(buf)) + return PTR_ERR(buf); + + ret = calculate_sha256(priv, buf, size, digest); + if (ret) + goto leave; + + p.cmd = EC_CODEC_WOV_GET_LANG; + ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC_WOV, + (uint8_t *)&p, sizeof(p), + (uint8_t *)&r, sizeof(r)); + if (ret) + goto leave; + + if (memcmp(digest, r.hash, SHA256_DIGEST_SIZE) == 0) { + dev_dbg(priv->dev, "not updated"); + goto leave; + } + + if (ec_codec_capable(priv, EC_CODEC_CAP_WOV_LANG_SHM)) + ret = wov_set_lang_shm(priv, buf, size, digest); + else + ret = wov_set_lang(priv, buf, size, digest); + +leave: + kfree(buf); + return ret; +} + +static struct snd_kcontrol_new wov_controls[] = { + SOC_SINGLE_BOOL_EXT("Wake-on-Voice Switch", 0, + wov_enable_get, wov_enable_put), + SND_SOC_BYTES_TLV("Hotword Model", 0x11000, NULL, + wov_hotword_model_put), +}; + +static struct snd_soc_dai_driver wov_dai_driver = { + .name = "Wake on Voice", + .capture = { + .stream_name = "WoV Capture", + .channels_min = 1, + .channels_max = 1, + .rates = SNDRV_PCM_RATE_16000, + .formats = SNDRV_PCM_FMTBIT_S16_LE, + }, +}; + +static int wov_host_event(struct notifier_block *nb, + unsigned long queued_during_suspend, void *notify) +{ + struct cros_ec_codec_priv *priv = + container_of(nb, struct cros_ec_codec_priv, wov_notifier); + u32 host_event; + + dev_dbg(priv->dev, "%s\n", __func__); + + host_event = cros_ec_get_host_event(priv->ec_device); + if (host_event & EC_HOST_EVENT_MASK(EC_HOST_EVENT_WOV)) { + schedule_delayed_work(&priv->wov_copy_work, 0); + return NOTIFY_OK; + } else { + return NOTIFY_DONE; + } +} + +static int wov_probe(struct snd_soc_component *component) +{ + struct cros_ec_codec_priv *priv = + snd_soc_component_get_drvdata(component); + int ret; + + mutex_init(&priv->wov_dma_lock); + INIT_DELAYED_WORK(&priv->wov_copy_work, wov_copy_work); + + priv->wov_notifier.notifier_call = wov_host_event; + ret = blocking_notifier_chain_register( + &priv->ec_device->event_notifier, &priv->wov_notifier); + if (ret) + return ret; + + if (ec_codec_capable(priv, EC_CODEC_CAP_WOV_LANG_SHM)) { + priv->wov_lang_shm_p = wov_map_shm(priv, + EC_CODEC_SHM_ID_WOV_LANG, + &priv->wov_lang_shm_len, + &priv->wov_lang_shm_type); + if (!priv->wov_lang_shm_p) + return -EFAULT; + } + + if (ec_codec_capable(priv, EC_CODEC_CAP_WOV_AUDIO_SHM)) { + priv->wov_audio_shm_p = wov_map_shm(priv, + EC_CODEC_SHM_ID_WOV_AUDIO, + &priv->wov_audio_shm_len, + &priv->wov_audio_shm_type); + if (!priv->wov_audio_shm_p) + return -EFAULT; + } + + return dmic_probe(component); +} + +static void wov_remove(struct snd_soc_component *component) +{ + struct cros_ec_codec_priv *priv = + snd_soc_component_get_drvdata(component); + + blocking_notifier_chain_unregister( + &priv->ec_device->event_notifier, &priv->wov_notifier); +} + +static int wov_pcm_open(struct snd_soc_component *component, + struct snd_pcm_substream *substream) +{ + static const struct snd_pcm_hardware hw_param = { + .info = SNDRV_PCM_INFO_MMAP | + SNDRV_PCM_INFO_INTERLEAVED | + SNDRV_PCM_INFO_MMAP_VALID, + .formats = SNDRV_PCM_FMTBIT_S16_LE, + .rates = SNDRV_PCM_RATE_16000, + .channels_min = 1, + .channels_max = 1, + .period_bytes_min = PAGE_SIZE, + .period_bytes_max = 0x20000 / 8, + .periods_min = 8, + .periods_max = 8, + .buffer_bytes_max = 0x20000, + }; + + return snd_soc_set_runtime_hwparams(substream, &hw_param); +} + +static int wov_pcm_hw_params(struct snd_soc_component *component, + struct snd_pcm_substream *substream, + struct snd_pcm_hw_params *hw_params) +{ + struct cros_ec_codec_priv *priv = + snd_soc_component_get_drvdata(component); + + mutex_lock(&priv->wov_dma_lock); + priv->wov_substream = substream; + priv->wov_rp = priv->wov_wp = 0; + priv->wov_dma_offset = 0; + priv->wov_burst_read = true; + mutex_unlock(&priv->wov_dma_lock); + + return snd_pcm_lib_alloc_vmalloc_buffer(substream, + params_buffer_bytes(hw_params)); +} + +static int wov_pcm_hw_free(struct snd_soc_component *component, + struct snd_pcm_substream *substream) +{ + struct cros_ec_codec_priv *priv = + snd_soc_component_get_drvdata(component); + + mutex_lock(&priv->wov_dma_lock); + wov_queue_dequeue(priv, wov_queue_size(priv)); + priv->wov_substream = NULL; + mutex_unlock(&priv->wov_dma_lock); + + cancel_delayed_work_sync(&priv->wov_copy_work); + + return snd_pcm_lib_free_vmalloc_buffer(substream); +} + +static snd_pcm_uframes_t wov_pcm_pointer(struct snd_soc_component *component, + struct snd_pcm_substream *substream) +{ + struct snd_pcm_runtime *runtime = substream->runtime; + struct cros_ec_codec_priv *priv = + snd_soc_component_get_drvdata(component); + + return bytes_to_frames(runtime, priv->wov_dma_offset); +} + +static struct page *wov_pcm_page(struct snd_soc_component *component, + struct snd_pcm_substream *substream, + unsigned long offset) +{ + return snd_pcm_lib_get_vmalloc_page(substream, offset); +} + +static const struct snd_soc_component_driver wov_component_driver = { + .probe = wov_probe, + .remove = wov_remove, + .controls = wov_controls, + .num_controls = ARRAY_SIZE(wov_controls), + .open = wov_pcm_open, + .hw_params = wov_pcm_hw_params, + .hw_free = wov_pcm_hw_free, + .pointer = wov_pcm_pointer, + .page = wov_pcm_page, +}; + static int cros_ec_codec_platform_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct cros_ec_device *ec_device = dev_get_drvdata(pdev->dev.parent); struct cros_ec_codec_priv *priv; + struct ec_param_ec_codec p; + struct ec_response_ec_codec_get_capabilities r; + int ret; +#ifdef CONFIG_OF + struct device_node *node; + struct resource res; + u64 ec_shm_size; + const __be32 *regaddr_p; +#endif priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; +#ifdef CONFIG_OF + regaddr_p = of_get_address(dev->of_node, 0, &ec_shm_size, NULL); + if (regaddr_p) { + priv->ec_shm_addr = of_read_number(regaddr_p, 2); + priv->ec_shm_len = ec_shm_size; + + dev_dbg(dev, "ec_shm_addr=%#llx len=%#x\n", + priv->ec_shm_addr, priv->ec_shm_len); + } + + node = of_parse_phandle(dev->of_node, "memory-region", 0); + if (node) { + ret = of_address_to_resource(node, 0, &res); + if (!ret) { + priv->ap_shm_phys_addr = res.start; + priv->ap_shm_len = resource_size(&res); + priv->ap_shm_addr = + (uint64_t)(uintptr_t)devm_ioremap_wc( + dev, priv->ap_shm_phys_addr, + priv->ap_shm_len); + priv->ap_shm_last_alloc = priv->ap_shm_phys_addr; + + dev_dbg(dev, "ap_shm_phys_addr=%#llx len=%#x\n", + priv->ap_shm_phys_addr, priv->ap_shm_len); + } + } +#endif + priv->dev = dev; priv->ec_device = ec_device; + atomic_set(&priv->dmic_probed, 0); + + p.cmd = EC_CODEC_GET_CAPABILITIES; + ret = send_ec_host_command(priv->ec_device, EC_CMD_EC_CODEC, + (uint8_t *)&p, sizeof(p), + (uint8_t *)&r, sizeof(r)); + if (ret) { + dev_err(dev, "failed to EC_CODEC_GET_CAPABILITIES\n"); + return ret; + } + priv->ec_capabilities = r.capabilities; platform_set_drvdata(pdev, priv); - return devm_snd_soc_register_component(dev, &i2s_rx_component_driver, - &i2s_rx_dai_driver, 1); + ret = devm_snd_soc_register_component(dev, &i2s_rx_component_driver, + &i2s_rx_dai_driver, 1); + if (ret) + return ret; + + return devm_snd_soc_register_component(dev, &wov_component_driver, + &wov_dai_driver, 1); } #ifdef CONFIG_OF -- cgit v1.2.3-71-gd317 From 52525b7a3cf82adec5c6cf0ecbd23ff228badc94 Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Fri, 18 Oct 2019 15:38:47 +0800 Subject: PCI: Add a helper to check Power Resource Requirements _PR3 existence A driver may want to know the existence of _PR3, to choose different runtime suspend behavior. A user will be add in next patch. This is mostly the same as nouveau_pr3_present(). Signed-off-by: Kai-Heng Feng Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20191018073848.14590-1-kai.heng.feng@canonical.com Signed-off-by: Takashi Iwai --- drivers/pci/pci.c | 18 ++++++++++++++++++ include/linux/pci.h | 2 ++ 2 files changed, 20 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index e7982af9a5d8..1df99d9e350e 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -5856,6 +5856,24 @@ int pci_set_vga_state(struct pci_dev *dev, bool decode, return 0; } +#ifdef CONFIG_ACPI +bool pci_pr3_present(struct pci_dev *pdev) +{ + struct acpi_device *adev; + + if (acpi_disabled) + return false; + + adev = ACPI_COMPANION(&pdev->dev); + if (!adev) + return false; + + return adev->power.flags.power_resources && + acpi_has_method(adev->handle, "_PR3"); +} +EXPORT_SYMBOL_GPL(pci_pr3_present); +#endif + /** * pci_add_dma_alias - Add a DMA devfn alias for a device * @dev: the PCI device for which alias is added diff --git a/include/linux/pci.h b/include/linux/pci.h index f9088c89a534..1d15c5d49cdd 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2310,9 +2310,11 @@ struct irq_domain *pci_host_bridge_acpi_msi_domain(struct pci_bus *bus); void pci_msi_register_fwnode_provider(struct fwnode_handle *(*fn)(struct device *)); +bool pci_pr3_present(struct pci_dev *pdev); #else static inline struct irq_domain * pci_host_bridge_acpi_msi_domain(struct pci_bus *bus) { return NULL; } +static bool pci_pr3_present(struct pci_dev *pdev) { return false; } #endif #ifdef CONFIG_EEH -- cgit v1.2.3-71-gd317 From d8ede917f5cd472e344be636d62b8e1f10bdae5e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 9 Aug 2019 14:42:28 +0200 Subject: jbd2: Remove jbd_trylock_bh_state() No users. Signed-off-by: Thomas Gleixner Reviewed-by: Jan Kara Cc: linux-ext4@vger.kernel.org Cc: "Theodore Ts'o" Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20190809124233.13277-3-jack@suse.cz Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 603fbc4e2f70..7fb4d98e2adb 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -347,11 +347,6 @@ static inline void jbd_lock_bh_state(struct buffer_head *bh) bit_spin_lock(BH_State, &bh->b_state); } -static inline int jbd_trylock_bh_state(struct buffer_head *bh) -{ - return bit_spin_trylock(BH_State, &bh->b_state); -} - static inline int jbd_is_locked_bh_state(struct buffer_head *bh) { return bit_spin_is_locked(BH_State, &bh->b_state); -- cgit v1.2.3-71-gd317 From 93108ebb848df8d4948d51db14714a14c4e81111 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 9 Aug 2019 14:42:29 +0200 Subject: jbd2: Move dropping of jh reference out of un/re-filing functions __jbd2_journal_unfile_buffer() and __jbd2_journal_refile_buffer() drop transaction's jh reference when they remove jh from a transaction. This will be however inconvenient once we move state lock into journal_head itself as we still need to unlock it and we'd need to grab jh reference just for that. Move dropping of jh reference out of these functions into the few callers. Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20190809124233.13277-4-jack@suse.cz Signed-off-by: Theodore Ts'o --- fs/jbd2/commit.c | 5 ++++- fs/jbd2/transaction.c | 23 +++++++++++++++-------- include/linux/jbd2.h | 2 +- 3 files changed, 20 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 132fb92098c7..a0a191f3df77 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -918,6 +918,7 @@ restart_loop: transaction_t *cp_transaction; struct buffer_head *bh; int try_to_free = 0; + bool drop_ref; jh = commit_transaction->t_forget; spin_unlock(&journal->j_list_lock); @@ -1022,8 +1023,10 @@ restart_loop: try_to_free = 1; } JBUFFER_TRACE(jh, "refile or unfile buffer"); - __jbd2_journal_refile_buffer(jh); + drop_ref = __jbd2_journal_refile_buffer(jh); jbd_unlock_bh_state(bh); + if (drop_ref) + jbd2_journal_put_journal_head(jh); if (try_to_free) release_buffer_page(bh); /* Drops bh reference */ else diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 2273b1067d3a..620113068e03 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1598,6 +1598,7 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh) __jbd2_journal_file_buffer(jh, transaction, BJ_Forget); } else { __jbd2_journal_unfile_buffer(jh); + jbd2_journal_put_journal_head(jh); if (!buffer_jbd(bh)) { spin_unlock(&journal->j_list_lock); goto not_jbd; @@ -1971,17 +1972,15 @@ static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh) } /* - * Remove buffer from all transactions. + * Remove buffer from all transactions. The caller is responsible for dropping + * the jh reference that belonged to the transaction. * * Called with bh_state lock and j_list_lock - * - * jh and bh may be already freed when this function returns. */ static void __jbd2_journal_unfile_buffer(struct journal_head *jh) { __jbd2_journal_temp_unlink_buffer(jh); jh->b_transaction = NULL; - jbd2_journal_put_journal_head(jh); } void jbd2_journal_unfile_buffer(journal_t *journal, struct journal_head *jh) @@ -1995,6 +1994,7 @@ void jbd2_journal_unfile_buffer(journal_t *journal, struct journal_head *jh) __jbd2_journal_unfile_buffer(jh); spin_unlock(&journal->j_list_lock); jbd_unlock_bh_state(bh); + jbd2_journal_put_journal_head(jh); __brelse(bh); } @@ -2133,6 +2133,7 @@ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction) } else { JBUFFER_TRACE(jh, "on running transaction"); __jbd2_journal_unfile_buffer(jh); + jbd2_journal_put_journal_head(jh); } return may_free; } @@ -2496,9 +2497,11 @@ void jbd2_journal_file_buffer(struct journal_head *jh, * Called under j_list_lock * Called under jbd_lock_bh_state(jh2bh(jh)) * - * jh and bh may be already free when this function returns + * When this function returns true, there's no next transaction to refile to + * and the caller has to drop jh reference through + * jbd2_journal_put_journal_head(). */ -void __jbd2_journal_refile_buffer(struct journal_head *jh) +bool __jbd2_journal_refile_buffer(struct journal_head *jh) { int was_dirty, jlist; struct buffer_head *bh = jh2bh(jh); @@ -2510,7 +2513,7 @@ void __jbd2_journal_refile_buffer(struct journal_head *jh) /* If the buffer is now unused, just drop it. */ if (jh->b_next_transaction == NULL) { __jbd2_journal_unfile_buffer(jh); - return; + return true; } /* @@ -2538,6 +2541,7 @@ void __jbd2_journal_refile_buffer(struct journal_head *jh) if (was_dirty) set_buffer_jbddirty(bh); + return false; } /* @@ -2549,15 +2553,18 @@ void __jbd2_journal_refile_buffer(struct journal_head *jh) void jbd2_journal_refile_buffer(journal_t *journal, struct journal_head *jh) { struct buffer_head *bh = jh2bh(jh); + bool drop; /* Get reference so that buffer cannot be freed before we unlock it */ get_bh(bh); jbd_lock_bh_state(bh); spin_lock(&journal->j_list_lock); - __jbd2_journal_refile_buffer(jh); + drop = __jbd2_journal_refile_buffer(jh); jbd_unlock_bh_state(bh); spin_unlock(&journal->j_list_lock); __brelse(bh); + if (drop) + jbd2_journal_put_journal_head(jh); } /* diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 7fb4d98e2adb..d0c77478d49d 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1252,7 +1252,7 @@ JBD2_FEATURE_INCOMPAT_FUNCS(csum3, CSUM_V3) /* Filing buffers */ extern void jbd2_journal_unfile_buffer(journal_t *, struct journal_head *); -extern void __jbd2_journal_refile_buffer(struct journal_head *); +extern bool __jbd2_journal_refile_buffer(struct journal_head *); extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *); extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); extern void __journal_free_buffer(struct journal_head *bh); -- cgit v1.2.3-71-gd317 From 464170647b5648bb81f3615567485fcb9a685bed Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 9 Aug 2019 14:42:32 +0200 Subject: jbd2: Make state lock a spinlock Bit-spinlocks are problematic on PREEMPT_RT if functions which might sleep on RT, e.g. spin_lock(), alloc/free(), are invoked inside the lock held region because bit spinlocks disable preemption even on RT. A first attempt was to replace state lock with a spinlock placed in struct buffer_head and make the locking conditional on PREEMPT_RT and DEBUG_BIT_SPINLOCKS. Jan pointed out that there is a 4 byte hole in struct journal_head where a regular spinlock fits in and he would not object to convert the state lock to a spinlock unconditionally. Aside of solving the RT problem, this also gains lockdep coverage for the journal head state lock (bit-spinlocks are not covered by lockdep as it's hard to fit a lockdep map into a single bit). The trivial change would have been to convert the jbd_*lock_bh_state() inlines, but that comes with the downside that these functions take a buffer head pointer which needs to be converted to a journal head pointer which adds another level of indirection. As almost all functions which use this lock have a journal head pointer readily available, it makes more sense to remove the lock helper inlines and write out spin_*lock() at all call sites. Fixup all locking comments as well. Suggested-by: Jan Kara Signed-off-by: Thomas Gleixner Signed-off-by: Jan Kara Cc: "Theodore Ts'o" Cc: Mark Fasheh Cc: Joseph Qi Cc: Joel Becker Cc: Jan Kara Cc: linux-ext4@vger.kernel.org Link: https://lore.kernel.org/r/20190809124233.13277-7-jack@suse.cz Signed-off-by: Theodore Ts'o --- fs/jbd2/commit.c | 8 ++-- fs/jbd2/journal.c | 10 +++-- fs/jbd2/transaction.c | 100 ++++++++++++++++++++----------------------- fs/ocfs2/suballoc.c | 19 ++++---- include/linux/jbd2.h | 20 +-------- include/linux/journal-head.h | 21 ++++++--- 6 files changed, 84 insertions(+), 94 deletions(-) (limited to 'include/linux') diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index a0a191f3df77..8e1ff875de43 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -482,10 +482,10 @@ void jbd2_journal_commit_transaction(journal_t *journal) if (jh->b_committed_data) { struct buffer_head *bh = jh2bh(jh); - jbd_lock_bh_state(bh); + spin_lock(&jh->b_state_lock); jbd2_free(jh->b_committed_data, bh->b_size); jh->b_committed_data = NULL; - jbd_unlock_bh_state(bh); + spin_unlock(&jh->b_state_lock); } jbd2_journal_refile_buffer(journal, jh); } @@ -928,7 +928,7 @@ restart_loop: * done with it. */ get_bh(bh); - jbd_lock_bh_state(bh); + spin_lock(&jh->b_state_lock); J_ASSERT_JH(jh, jh->b_transaction == commit_transaction); /* @@ -1024,7 +1024,7 @@ restart_loop: } JBUFFER_TRACE(jh, "refile or unfile buffer"); drop_ref = __jbd2_journal_refile_buffer(jh); - jbd_unlock_bh_state(bh); + spin_unlock(&jh->b_state_lock); if (drop_ref) jbd2_journal_put_journal_head(jh); if (try_to_free) diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 1c58859aa592..5d4192f05879 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -363,7 +363,7 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction, /* keep subsequent assertions sane */ atomic_set(&new_bh->b_count, 1); - jbd_lock_bh_state(bh_in); + spin_lock(&jh_in->b_state_lock); repeat: /* * If a new transaction has already done a buffer copy-out, then @@ -405,13 +405,13 @@ repeat: if (need_copy_out && !done_copy_out) { char *tmp; - jbd_unlock_bh_state(bh_in); + spin_unlock(&jh_in->b_state_lock); tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS); if (!tmp) { brelse(new_bh); return -ENOMEM; } - jbd_lock_bh_state(bh_in); + spin_lock(&jh_in->b_state_lock); if (jh_in->b_frozen_data) { jbd2_free(tmp, bh_in->b_size); goto repeat; @@ -464,7 +464,7 @@ repeat: __jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow); spin_unlock(&journal->j_list_lock); set_buffer_shadow(bh_in); - jbd_unlock_bh_state(bh_in); + spin_unlock(&jh_in->b_state_lock); return do_escape | (done_copy_out << 1); } @@ -2410,6 +2410,8 @@ static struct journal_head *journal_alloc_journal_head(void) ret = kmem_cache_zalloc(jbd2_journal_head_cache, GFP_NOFS | __GFP_NOFAIL); } + if (ret) + spin_lock_init(&ret->b_state_lock); return ret; } diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index f2af4afc690a..7c11afe60532 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -879,7 +879,7 @@ repeat: start_lock = jiffies; lock_buffer(bh); - jbd_lock_bh_state(bh); + spin_lock(&jh->b_state_lock); /* If it takes too long to lock the buffer, trace it */ time_lock = jbd2_time_diff(start_lock, jiffies); @@ -929,7 +929,7 @@ repeat: error = -EROFS; if (is_handle_aborted(handle)) { - jbd_unlock_bh_state(bh); + spin_unlock(&jh->b_state_lock); goto out; } error = 0; @@ -993,7 +993,7 @@ repeat: */ if (buffer_shadow(bh)) { JBUFFER_TRACE(jh, "on shadow: sleep"); - jbd_unlock_bh_state(bh); + spin_unlock(&jh->b_state_lock); wait_on_bit_io(&bh->b_state, BH_Shadow, TASK_UNINTERRUPTIBLE); goto repeat; } @@ -1014,7 +1014,7 @@ repeat: JBUFFER_TRACE(jh, "generate frozen data"); if (!frozen_buffer) { JBUFFER_TRACE(jh, "allocate memory for buffer"); - jbd_unlock_bh_state(bh); + spin_unlock(&jh->b_state_lock); frozen_buffer = jbd2_alloc(jh2bh(jh)->b_size, GFP_NOFS | __GFP_NOFAIL); goto repeat; @@ -1033,7 +1033,7 @@ attach_next: jh->b_next_transaction = transaction; done: - jbd_unlock_bh_state(bh); + spin_unlock(&jh->b_state_lock); /* * If we are about to journal a buffer, then any revoke pending on it is @@ -1172,7 +1172,7 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh) * that case: the transaction must have deleted the buffer for it to be * reused here. */ - jbd_lock_bh_state(bh); + spin_lock(&jh->b_state_lock); J_ASSERT_JH(jh, (jh->b_transaction == transaction || jh->b_transaction == NULL || (jh->b_transaction == journal->j_committing_transaction && @@ -1207,7 +1207,7 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh) jh->b_next_transaction = transaction; spin_unlock(&journal->j_list_lock); } - jbd_unlock_bh_state(bh); + spin_unlock(&jh->b_state_lock); /* * akpm: I added this. ext3_alloc_branch can pick up new indirect @@ -1275,13 +1275,13 @@ repeat: committed_data = jbd2_alloc(jh2bh(jh)->b_size, GFP_NOFS|__GFP_NOFAIL); - jbd_lock_bh_state(bh); + spin_lock(&jh->b_state_lock); if (!jh->b_committed_data) { /* Copy out the current buffer contents into the * preserved, committed copy. */ JBUFFER_TRACE(jh, "generate b_committed data"); if (!committed_data) { - jbd_unlock_bh_state(bh); + spin_unlock(&jh->b_state_lock); goto repeat; } @@ -1289,7 +1289,7 @@ repeat: committed_data = NULL; memcpy(jh->b_committed_data, bh->b_data, bh->b_size); } - jbd_unlock_bh_state(bh); + spin_unlock(&jh->b_state_lock); out: jbd2_journal_put_journal_head(jh); if (unlikely(committed_data)) @@ -1390,16 +1390,16 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) */ if (jh->b_transaction != transaction && jh->b_next_transaction != transaction) { - jbd_lock_bh_state(bh); + spin_lock(&jh->b_state_lock); J_ASSERT_JH(jh, jh->b_transaction == transaction || jh->b_next_transaction == transaction); - jbd_unlock_bh_state(bh); + spin_unlock(&jh->b_state_lock); } if (jh->b_modified == 1) { /* If it's in our transaction it must be in BJ_Metadata list. */ if (jh->b_transaction == transaction && jh->b_jlist != BJ_Metadata) { - jbd_lock_bh_state(bh); + spin_lock(&jh->b_state_lock); if (jh->b_transaction == transaction && jh->b_jlist != BJ_Metadata) pr_err("JBD2: assertion failure: h_type=%u " @@ -1409,13 +1409,13 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) jh->b_jlist); J_ASSERT_JH(jh, jh->b_transaction != transaction || jh->b_jlist == BJ_Metadata); - jbd_unlock_bh_state(bh); + spin_unlock(&jh->b_state_lock); } goto out; } journal = transaction->t_journal; - jbd_lock_bh_state(bh); + spin_lock(&jh->b_state_lock); if (jh->b_modified == 0) { /* @@ -1501,7 +1501,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) __jbd2_journal_file_buffer(jh, transaction, BJ_Metadata); spin_unlock(&journal->j_list_lock); out_unlock_bh: - jbd_unlock_bh_state(bh); + spin_unlock(&jh->b_state_lock); out: JBUFFER_TRACE(jh, "exit"); return ret; @@ -1539,11 +1539,13 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh) BUFFER_TRACE(bh, "entry"); - jbd_lock_bh_state(bh); + jh = jbd2_journal_grab_journal_head(bh); + if (!jh) { + __bforget(bh); + return 0; + } - if (!buffer_jbd(bh)) - goto not_jbd; - jh = bh2jh(bh); + spin_lock(&jh->b_state_lock); /* Critical error: attempting to delete a bitmap buffer, maybe? * Don't do any jbd operations, and return an error. */ @@ -1664,18 +1666,14 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh) spin_unlock(&journal->j_list_lock); } drop: - jbd_unlock_bh_state(bh); __brelse(bh); + spin_unlock(&jh->b_state_lock); + jbd2_journal_put_journal_head(jh); if (drop_reserve) { /* no need to reserve log space for this block -bzzz */ handle->h_buffer_credits++; } return err; - -not_jbd: - jbd_unlock_bh_state(bh); - __bforget(bh); - goto drop; } /** @@ -1874,7 +1872,7 @@ free_and_exit: * * j_list_lock is held. * - * jbd_lock_bh_state(jh2bh(jh)) is held. + * jh->b_state_lock is held. */ static inline void @@ -1898,7 +1896,7 @@ __blist_add_buffer(struct journal_head **list, struct journal_head *jh) * * Called with j_list_lock held, and the journal may not be locked. * - * jbd_lock_bh_state(jh2bh(jh)) is held. + * jh->b_state_lock is held. */ static inline void @@ -1930,7 +1928,7 @@ static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh) transaction_t *transaction; struct buffer_head *bh = jh2bh(jh); - J_ASSERT_JH(jh, jbd_is_locked_bh_state(bh)); + lockdep_assert_held(&jh->b_state_lock); transaction = jh->b_transaction; if (transaction) assert_spin_locked(&transaction->t_journal->j_list_lock); @@ -1984,11 +1982,11 @@ void jbd2_journal_unfile_buffer(journal_t *journal, struct journal_head *jh) /* Get reference so that buffer cannot be freed before we unlock it */ get_bh(bh); - jbd_lock_bh_state(bh); + spin_lock(&jh->b_state_lock); spin_lock(&journal->j_list_lock); __jbd2_journal_unfile_buffer(jh); spin_unlock(&journal->j_list_lock); - jbd_unlock_bh_state(bh); + spin_unlock(&jh->b_state_lock); jbd2_journal_put_journal_head(jh); __brelse(bh); } @@ -1996,7 +1994,7 @@ void jbd2_journal_unfile_buffer(journal_t *journal, struct journal_head *jh) /* * Called from jbd2_journal_try_to_free_buffers(). * - * Called under jbd_lock_bh_state(bh) + * Called under jh->b_state_lock */ static void __journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh) @@ -2083,10 +2081,10 @@ int jbd2_journal_try_to_free_buffers(journal_t *journal, if (!jh) continue; - jbd_lock_bh_state(bh); + spin_lock(&jh->b_state_lock); __journal_try_to_free_buffer(journal, bh); + spin_unlock(&jh->b_state_lock); jbd2_journal_put_journal_head(jh); - jbd_unlock_bh_state(bh); if (buffer_jbd(bh)) goto busy; } while ((bh = bh->b_this_page) != head); @@ -2107,7 +2105,7 @@ busy: * * Called under j_list_lock. * - * Called under jbd_lock_bh_state(bh). + * Called under jh->b_state_lock. */ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction) { @@ -2201,7 +2199,7 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh, /* OK, we have data buffer in journaled mode */ write_lock(&journal->j_state_lock); - jbd_lock_bh_state(bh); + spin_lock(&jh->b_state_lock); spin_lock(&journal->j_list_lock); /* @@ -2282,10 +2280,10 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh, * for commit and try again. */ if (partial_page) { - jbd2_journal_put_journal_head(jh); spin_unlock(&journal->j_list_lock); - jbd_unlock_bh_state(bh); + spin_unlock(&jh->b_state_lock); write_unlock(&journal->j_state_lock); + jbd2_journal_put_journal_head(jh); return -EBUSY; } /* @@ -2297,10 +2295,10 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh, set_buffer_freed(bh); if (journal->j_running_transaction && buffer_jbddirty(bh)) jh->b_next_transaction = journal->j_running_transaction; - jbd2_journal_put_journal_head(jh); spin_unlock(&journal->j_list_lock); - jbd_unlock_bh_state(bh); + spin_unlock(&jh->b_state_lock); write_unlock(&journal->j_state_lock); + jbd2_journal_put_journal_head(jh); return 0; } else { /* Good, the buffer belongs to the running transaction. @@ -2324,10 +2322,10 @@ zap_buffer: * here. */ jh->b_modified = 0; - jbd2_journal_put_journal_head(jh); spin_unlock(&journal->j_list_lock); - jbd_unlock_bh_state(bh); + spin_unlock(&jh->b_state_lock); write_unlock(&journal->j_state_lock); + jbd2_journal_put_journal_head(jh); zap_buffer_unlocked: clear_buffer_dirty(bh); J_ASSERT_BH(bh, !buffer_jbddirty(bh)); @@ -2414,7 +2412,7 @@ void __jbd2_journal_file_buffer(struct journal_head *jh, int was_dirty = 0; struct buffer_head *bh = jh2bh(jh); - J_ASSERT_JH(jh, jbd_is_locked_bh_state(bh)); + lockdep_assert_held(&jh->b_state_lock); assert_spin_locked(&transaction->t_journal->j_list_lock); J_ASSERT_JH(jh, jh->b_jlist < BJ_Types); @@ -2476,11 +2474,11 @@ void __jbd2_journal_file_buffer(struct journal_head *jh, void jbd2_journal_file_buffer(struct journal_head *jh, transaction_t *transaction, int jlist) { - jbd_lock_bh_state(jh2bh(jh)); + spin_lock(&jh->b_state_lock); spin_lock(&transaction->t_journal->j_list_lock); __jbd2_journal_file_buffer(jh, transaction, jlist); spin_unlock(&transaction->t_journal->j_list_lock); - jbd_unlock_bh_state(jh2bh(jh)); + spin_unlock(&jh->b_state_lock); } /* @@ -2490,7 +2488,7 @@ void jbd2_journal_file_buffer(struct journal_head *jh, * buffer on that transaction's metadata list. * * Called under j_list_lock - * Called under jbd_lock_bh_state(jh2bh(jh)) + * Called under jh->b_state_lock * * When this function returns true, there's no next transaction to refile to * and the caller has to drop jh reference through @@ -2501,7 +2499,7 @@ bool __jbd2_journal_refile_buffer(struct journal_head *jh) int was_dirty, jlist; struct buffer_head *bh = jh2bh(jh); - J_ASSERT_JH(jh, jbd_is_locked_bh_state(bh)); + lockdep_assert_held(&jh->b_state_lock); if (jh->b_transaction) assert_spin_locked(&jh->b_transaction->t_journal->j_list_lock); @@ -2547,17 +2545,13 @@ bool __jbd2_journal_refile_buffer(struct journal_head *jh) */ void jbd2_journal_refile_buffer(journal_t *journal, struct journal_head *jh) { - struct buffer_head *bh = jh2bh(jh); bool drop; - /* Get reference so that buffer cannot be freed before we unlock it */ - get_bh(bh); - jbd_lock_bh_state(bh); + spin_lock(&jh->b_state_lock); spin_lock(&journal->j_list_lock); drop = __jbd2_journal_refile_buffer(jh); - jbd_unlock_bh_state(bh); + spin_unlock(&jh->b_state_lock); spin_unlock(&journal->j_list_lock); - __brelse(bh); if (drop) jbd2_journal_put_journal_head(jh); } diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 69c21a3843af..4180c3ef0a68 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -1252,6 +1252,7 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh, int nr) { struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data; + struct journal_head *jh; int ret; if (ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap)) @@ -1260,13 +1261,14 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh, if (!buffer_jbd(bg_bh)) return 1; - jbd_lock_bh_state(bg_bh); - bg = (struct ocfs2_group_desc *) bh2jh(bg_bh)->b_committed_data; + jh = bh2jh(bg_bh); + spin_lock(&jh->b_state_lock); + bg = (struct ocfs2_group_desc *) jh->b_committed_data; if (bg) ret = !ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap); else ret = 1; - jbd_unlock_bh_state(bg_bh); + spin_unlock(&jh->b_state_lock); return ret; } @@ -2387,6 +2389,7 @@ static int ocfs2_block_group_clear_bits(handle_t *handle, int status; unsigned int tmp; struct ocfs2_group_desc *undo_bg = NULL; + struct journal_head *jh; /* The caller got this descriptor from * ocfs2_read_group_descriptor(). Any corruption is a code bug. */ @@ -2405,10 +2408,10 @@ static int ocfs2_block_group_clear_bits(handle_t *handle, goto bail; } + jh = bh2jh(group_bh); if (undo_fn) { - jbd_lock_bh_state(group_bh); - undo_bg = (struct ocfs2_group_desc *) - bh2jh(group_bh)->b_committed_data; + spin_lock(&jh->b_state_lock); + undo_bg = (struct ocfs2_group_desc *) jh->b_committed_data; BUG_ON(!undo_bg); } @@ -2423,7 +2426,7 @@ static int ocfs2_block_group_clear_bits(handle_t *handle, le16_add_cpu(&bg->bg_free_bits_count, num_bits); if (le16_to_cpu(bg->bg_free_bits_count) > le16_to_cpu(bg->bg_bits)) { if (undo_fn) - jbd_unlock_bh_state(group_bh); + spin_unlock(&jh->b_state_lock); return ocfs2_error(alloc_inode->i_sb, "Group descriptor # %llu has bit count %u but claims %u are freed. num_bits %d\n", (unsigned long long)le64_to_cpu(bg->bg_blkno), le16_to_cpu(bg->bg_bits), @@ -2432,7 +2435,7 @@ static int ocfs2_block_group_clear_bits(handle_t *handle, } if (undo_fn) - jbd_unlock_bh_state(group_bh); + spin_unlock(&jh->b_state_lock); ocfs2_journal_dirty(handle, group_bh); bail: diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index d0c77478d49d..9cafbc9a76d9 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -313,7 +313,6 @@ enum jbd_state_bits { BH_Revoked, /* Has been revoked from the log */ BH_RevokeValid, /* Revoked flag is valid */ BH_JBDDirty, /* Is dirty but journaled */ - BH_State, /* Pins most journal_head state */ BH_JournalHead, /* Pins bh->b_private and jh->b_bh */ BH_Shadow, /* IO on shadow buffer is running */ BH_Verified, /* Metadata block has been verified ok */ @@ -342,21 +341,6 @@ static inline struct journal_head *bh2jh(struct buffer_head *bh) return bh->b_private; } -static inline void jbd_lock_bh_state(struct buffer_head *bh) -{ - bit_spin_lock(BH_State, &bh->b_state); -} - -static inline int jbd_is_locked_bh_state(struct buffer_head *bh) -{ - return bit_spin_is_locked(BH_State, &bh->b_state); -} - -static inline void jbd_unlock_bh_state(struct buffer_head *bh) -{ - bit_spin_unlock(BH_State, &bh->b_state); -} - static inline void jbd_lock_bh_journal_head(struct buffer_head *bh) { bit_spin_lock(BH_JournalHead, &bh->b_state); @@ -551,9 +535,9 @@ struct transaction_chp_stats_s { * ->jbd_lock_bh_journal_head() (This is "innermost") * * j_state_lock - * ->jbd_lock_bh_state() + * ->b_state_lock * - * jbd_lock_bh_state() + * b_state_lock * ->j_list_lock * * j_state_lock diff --git a/include/linux/journal-head.h b/include/linux/journal-head.h index 9fb870524314..75bc56109031 100644 --- a/include/linux/journal-head.h +++ b/include/linux/journal-head.h @@ -11,6 +11,8 @@ #ifndef JOURNAL_HEAD_H_INCLUDED #define JOURNAL_HEAD_H_INCLUDED +#include + typedef unsigned int tid_t; /* Unique transaction ID */ typedef struct transaction_s transaction_t; /* Compound transaction type */ @@ -23,6 +25,11 @@ struct journal_head { */ struct buffer_head *b_bh; + /* + * Protect the buffer head state + */ + spinlock_t b_state_lock; + /* * Reference count - see description in journal.c * [jbd_lock_bh_journal_head()] @@ -30,7 +37,7 @@ struct journal_head { int b_jcount; /* - * Journalling list for this buffer [jbd_lock_bh_state()] + * Journalling list for this buffer [b_state_lock] * NOTE: We *cannot* combine this with b_modified into a bitfield * as gcc would then (which the C standard allows but which is * very unuseful) make 64-bit accesses to the bitfield and clobber @@ -41,20 +48,20 @@ struct journal_head { /* * This flag signals the buffer has been modified by * the currently running transaction - * [jbd_lock_bh_state()] + * [b_state_lock] */ unsigned b_modified; /* * Copy of the buffer data frozen for writing to the log. - * [jbd_lock_bh_state()] + * [b_state_lock] */ char *b_frozen_data; /* * Pointer to a saved copy of the buffer containing no uncommitted * deallocation references, so that allocations can avoid overwriting - * uncommitted deletes. [jbd_lock_bh_state()] + * uncommitted deletes. [b_state_lock] */ char *b_committed_data; @@ -63,7 +70,7 @@ struct journal_head { * metadata: either the running transaction or the committing * transaction (if there is one). Only applies to buffers on a * transaction's data or metadata journaling list. - * [j_list_lock] [jbd_lock_bh_state()] + * [j_list_lock] [b_state_lock] * Either of these locks is enough for reading, both are needed for * changes. */ @@ -73,13 +80,13 @@ struct journal_head { * Pointer to the running compound transaction which is currently * modifying the buffer's metadata, if there was already a transaction * committing it when the new transaction touched it. - * [t_list_lock] [jbd_lock_bh_state()] + * [t_list_lock] [b_state_lock] */ transaction_t *b_next_transaction; /* * Doubly-linked list of buffers on a transaction's data, metadata or - * forget queue. [t_list_lock] [jbd_lock_bh_state()] + * forget queue. [t_list_lock] [b_state_lock] */ struct journal_head *b_tnext, *b_tprev; -- cgit v1.2.3-71-gd317 From 46b4bff6572b0552b1ee062043621e4b252638d8 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 21 Oct 2019 16:25:20 +0200 Subject: PCI: Fix missing inline for pci_pr3_present() The inline prefix was missing in the dummy function pci_pr3_present() definition. Fix it. Reported-by: kbuild test robot Fixes: 52525b7a3cf8 ("PCI: Add a helper to check Power Resource Requirements _PR3 existence") Link: https://lore.kernel.org/r/201910212111.qHm6OcWx%lkp@intel.com Signed-off-by: Takashi Iwai --- include/linux/pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 1d15c5d49cdd..be529d311122 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2314,7 +2314,7 @@ bool pci_pr3_present(struct pci_dev *pdev); #else static inline struct irq_domain * pci_host_bridge_acpi_msi_domain(struct pci_bus *bus) { return NULL; } -static bool pci_pr3_present(struct pci_dev *pdev) { return false; } +static inline bool pci_pr3_present(struct pci_dev *pdev) { return false; } #endif #ifdef CONFIG_EEH -- cgit v1.2.3-71-gd317 From 27938fd8ba78b4c7f9a2385b7b52cca19ab891b8 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Fri, 4 Oct 2019 15:32:07 +0200 Subject: pwm: Update comment on struct pwm_ops::apply MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 71523d1812ac (pwm: Ensure pwm_apply_state() doesn't modify the state argument) updated the kernel-doc for pwm_apply_state(), but not for the ->apply callback in the pwm_ops struct. Signed-off-by: Rasmus Villemoes Reviewed-by: Uwe Kleine-König Reviewed-by: Bjorn Andersson Signed-off-by: Thierry Reding --- include/linux/pwm.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index b2c9c460947d..0ef808d925bb 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -243,10 +243,7 @@ pwm_set_relative_duty_cycle(struct pwm_state *state, unsigned int duty_cycle, * @request: optional hook for requesting a PWM * @free: optional hook for freeing a PWM * @capture: capture and report PWM signal - * @apply: atomically apply a new PWM config. The state argument - * should be adjusted with the real hardware config (if the - * approximate the period or duty_cycle value, state should - * reflect it) + * @apply: atomically apply a new PWM config * @get_state: get the current PWM state. This function is only * called once per PWM device when the PWM chip is * registered. -- cgit v1.2.3-71-gd317 From 8e53622594f5530b5a86094464937dda47fc6e3b Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Wed, 16 Oct 2019 12:42:40 +0200 Subject: pwm: stm32: Remove clutter from ternary operator Remove usage of the ternary operator to assign values for register fields. Instead, parameterize the register and field offset macros and pass the index to them. This removes clutter and improves readability. Signed-off-by: Thierry Reding --- drivers/pwm/pwm-stm32.c | 21 +++++++++------------ include/linux/mfd/stm32-timers.h | 12 ++++-------- 2 files changed, 13 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c index c5f51a33ee1b..7a2be0453824 100644 --- a/drivers/pwm/pwm-stm32.c +++ b/drivers/pwm/pwm-stm32.c @@ -493,20 +493,17 @@ static const struct pwm_ops stm32pwm_ops = { static int stm32_pwm_set_breakinput(struct stm32_pwm *priv, int index, int level, int filter) { - u32 bke = (index == 0) ? TIM_BDTR_BKE : TIM_BDTR_BK2E; - int shift = (index == 0) ? TIM_BDTR_BKF_SHIFT : TIM_BDTR_BK2F_SHIFT; - u32 mask = (index == 0) ? TIM_BDTR_BKE | TIM_BDTR_BKP | TIM_BDTR_BKF - : TIM_BDTR_BK2E | TIM_BDTR_BK2P | TIM_BDTR_BK2F; - u32 bdtr = bke; + u32 shift = TIM_BDTR_BKF_SHIFT(index); + u32 bke = TIM_BDTR_BKE(index); + u32 bkp = TIM_BDTR_BKP(index); + u32 bkf = TIM_BDTR_BKF(index); + u32 mask = bkf | bkp | bke; + u32 bdtr; - /* - * The both bits could be set since only one will be wrote - * due to mask value. - */ - if (level) - bdtr |= TIM_BDTR_BKP | TIM_BDTR_BK2P; + bdtr = (filter & TIM_BDTR_BKF_MASK) << shift | bke; - bdtr |= (filter & TIM_BDTR_BKF_MASK) << shift; + if (level) + bdtr |= bkp; regmap_update_bits(priv->regmap, TIM_BDTR, mask, bdtr); diff --git a/include/linux/mfd/stm32-timers.h b/include/linux/mfd/stm32-timers.h index 067d14655c28..f8db83aedb2b 100644 --- a/include/linux/mfd/stm32-timers.h +++ b/include/linux/mfd/stm32-timers.h @@ -70,14 +70,11 @@ #define TIM_CCER_CC4E BIT(12) /* Capt/Comp 4 out Ena */ #define TIM_CCER_CC4P BIT(13) /* Capt/Comp 4 Polarity */ #define TIM_CCER_CCXE (BIT(0) | BIT(4) | BIT(8) | BIT(12)) -#define TIM_BDTR_BKE BIT(12) /* Break input enable */ -#define TIM_BDTR_BKP BIT(13) /* Break input polarity */ +#define TIM_BDTR_BKE(x) BIT(12 + (x) * 12) /* Break input enable */ +#define TIM_BDTR_BKP(x) BIT(13 + (x) * 12) /* Break input polarity */ #define TIM_BDTR_AOE BIT(14) /* Automatic Output Enable */ #define TIM_BDTR_MOE BIT(15) /* Main Output Enable */ -#define TIM_BDTR_BKF (BIT(16) | BIT(17) | BIT(18) | BIT(19)) -#define TIM_BDTR_BK2F (BIT(20) | BIT(21) | BIT(22) | BIT(23)) -#define TIM_BDTR_BK2E BIT(24) /* Break 2 input enable */ -#define TIM_BDTR_BK2P BIT(25) /* Break 2 input polarity */ +#define TIM_BDTR_BKF(x) (0xf << (16 + (x) * 4)) #define TIM_DCR_DBA GENMASK(4, 0) /* DMA base addr */ #define TIM_DCR_DBL GENMASK(12, 8) /* DMA burst len */ @@ -87,8 +84,7 @@ #define TIM_CR2_MMS2_SHIFT 20 #define TIM_SMCR_TS_SHIFT 4 #define TIM_BDTR_BKF_MASK 0xF -#define TIM_BDTR_BKF_SHIFT 16 -#define TIM_BDTR_BK2F_SHIFT 20 +#define TIM_BDTR_BKF_SHIFT(x) (16 + (x) * 4) enum stm32_timers_dmas { STM32_TIMERS_DMA_CH1, -- cgit v1.2.3-71-gd317 From 598ecfbaa742aca0dcdbbea25681406f95cc0b63 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 17 Oct 2019 13:12:15 -0700 Subject: iomap: lift the xfs writeback code to iomap Take the xfs writeback code and move it to fs/iomap. A new structure with three methods is added as the abstraction from the generic writeback code to the file system. These methods are used to map blocks, submit an ioend, and cancel a page that encountered an error before it was added to an ioend. Signed-off-by: Christoph Hellwig [darrick: rename ->submit_ioend to ->prepare_ioend to clarify what it does] Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/iomap/buffered-io.c | 551 +++++++++++++++++++++++++++++++++++++++++- fs/iomap/trace.h | 1 + fs/xfs/xfs_aops.c | 639 +++++-------------------------------------------- fs/xfs/xfs_aops.h | 17 -- fs/xfs/xfs_super.c | 11 +- fs/xfs/xfs_trace.h | 39 --- include/linux/iomap.h | 59 +++++ 7 files changed, 669 insertions(+), 648 deletions(-) (limited to 'include/linux') diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 55e514899b8c..41e1828a0bb3 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2010 Red Hat, Inc. - * Copyright (c) 2016-2018 Christoph Hellwig. + * Copyright (C) 2016-2019 Christoph Hellwig. */ #include #include @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -20,6 +21,8 @@ #include "../internal.h" +static struct bio_set iomap_ioend_bioset; + static struct iomap_page * iomap_page_create(struct inode *inode, struct page *page) { @@ -1088,3 +1091,549 @@ out_unlock: return block_page_mkwrite_return(ret); } EXPORT_SYMBOL_GPL(iomap_page_mkwrite); + +static void +iomap_finish_page_writeback(struct inode *inode, struct bio_vec *bvec, + int error) +{ + struct iomap_page *iop = to_iomap_page(bvec->bv_page); + + if (error) { + SetPageError(bvec->bv_page); + mapping_set_error(inode->i_mapping, -EIO); + } + + WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE && !iop); + WARN_ON_ONCE(iop && atomic_read(&iop->write_count) <= 0); + + if (!iop || atomic_dec_and_test(&iop->write_count)) + end_page_writeback(bvec->bv_page); +} + +/* + * We're now finished for good with this ioend structure. Update the page + * state, release holds on bios, and finally free up memory. Do not use the + * ioend after this. + */ +static void +iomap_finish_ioend(struct iomap_ioend *ioend, int error) +{ + struct inode *inode = ioend->io_inode; + struct bio *bio = &ioend->io_inline_bio; + struct bio *last = ioend->io_bio, *next; + u64 start = bio->bi_iter.bi_sector; + bool quiet = bio_flagged(bio, BIO_QUIET); + + for (bio = &ioend->io_inline_bio; bio; bio = next) { + struct bio_vec *bv; + struct bvec_iter_all iter_all; + + /* + * For the last bio, bi_private points to the ioend, so we + * need to explicitly end the iteration here. + */ + if (bio == last) + next = NULL; + else + next = bio->bi_private; + + /* walk each page on bio, ending page IO on them */ + bio_for_each_segment_all(bv, bio, iter_all) + iomap_finish_page_writeback(inode, bv, error); + bio_put(bio); + } + + if (unlikely(error && !quiet)) { + printk_ratelimited(KERN_ERR + "%s: writeback error on sector %llu", + inode->i_sb->s_id, start); + } +} + +void +iomap_finish_ioends(struct iomap_ioend *ioend, int error) +{ + struct list_head tmp; + + list_replace_init(&ioend->io_list, &tmp); + iomap_finish_ioend(ioend, error); + + while (!list_empty(&tmp)) { + ioend = list_first_entry(&tmp, struct iomap_ioend, io_list); + list_del_init(&ioend->io_list); + iomap_finish_ioend(ioend, error); + } +} +EXPORT_SYMBOL_GPL(iomap_finish_ioends); + +/* + * We can merge two adjacent ioends if they have the same set of work to do. + */ +static bool +iomap_ioend_can_merge(struct iomap_ioend *ioend, struct iomap_ioend *next) +{ + if (ioend->io_bio->bi_status != next->io_bio->bi_status) + return false; + if ((ioend->io_flags & IOMAP_F_SHARED) ^ + (next->io_flags & IOMAP_F_SHARED)) + return false; + if ((ioend->io_type == IOMAP_UNWRITTEN) ^ + (next->io_type == IOMAP_UNWRITTEN)) + return false; + if (ioend->io_offset + ioend->io_size != next->io_offset) + return false; + return true; +} + +void +iomap_ioend_try_merge(struct iomap_ioend *ioend, struct list_head *more_ioends, + void (*merge_private)(struct iomap_ioend *ioend, + struct iomap_ioend *next)) +{ + struct iomap_ioend *next; + + INIT_LIST_HEAD(&ioend->io_list); + + while ((next = list_first_entry_or_null(more_ioends, struct iomap_ioend, + io_list))) { + if (!iomap_ioend_can_merge(ioend, next)) + break; + list_move_tail(&next->io_list, &ioend->io_list); + ioend->io_size += next->io_size; + if (next->io_private && merge_private) + merge_private(ioend, next); + } +} +EXPORT_SYMBOL_GPL(iomap_ioend_try_merge); + +static int +iomap_ioend_compare(void *priv, struct list_head *a, struct list_head *b) +{ + struct iomap_ioend *ia, *ib; + + ia = container_of(a, struct iomap_ioend, io_list); + ib = container_of(b, struct iomap_ioend, io_list); + if (ia->io_offset < ib->io_offset) + return -1; + else if (ia->io_offset > ib->io_offset) + return 1; + return 0; +} + +void +iomap_sort_ioends(struct list_head *ioend_list) +{ + list_sort(NULL, ioend_list, iomap_ioend_compare); +} +EXPORT_SYMBOL_GPL(iomap_sort_ioends); + +static void iomap_writepage_end_bio(struct bio *bio) +{ + struct iomap_ioend *ioend = bio->bi_private; + + iomap_finish_ioend(ioend, blk_status_to_errno(bio->bi_status)); +} + +/* + * Submit the final bio for an ioend. + * + * If @error is non-zero, it means that we have a situation where some part of + * the submission process has failed after we have marked paged for writeback + * and unlocked them. In this situation, we need to fail the bio instead of + * submitting it. This typically only happens on a filesystem shutdown. + */ +static int +iomap_submit_ioend(struct iomap_writepage_ctx *wpc, struct iomap_ioend *ioend, + int error) +{ + ioend->io_bio->bi_private = ioend; + ioend->io_bio->bi_end_io = iomap_writepage_end_bio; + + if (wpc->ops->prepare_ioend) + error = wpc->ops->prepare_ioend(ioend, error); + if (error) { + /* + * If we are failing the IO now, just mark the ioend with an + * error and finish it. This will run IO completion immediately + * as there is only one reference to the ioend at this point in + * time. + */ + ioend->io_bio->bi_status = errno_to_blk_status(error); + bio_endio(ioend->io_bio); + return error; + } + + submit_bio(ioend->io_bio); + return 0; +} + +static struct iomap_ioend * +iomap_alloc_ioend(struct inode *inode, struct iomap_writepage_ctx *wpc, + loff_t offset, sector_t sector, struct writeback_control *wbc) +{ + struct iomap_ioend *ioend; + struct bio *bio; + + bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &iomap_ioend_bioset); + bio_set_dev(bio, wpc->iomap.bdev); + bio->bi_iter.bi_sector = sector; + bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc); + bio->bi_write_hint = inode->i_write_hint; + wbc_init_bio(wbc, bio); + + ioend = container_of(bio, struct iomap_ioend, io_inline_bio); + INIT_LIST_HEAD(&ioend->io_list); + ioend->io_type = wpc->iomap.type; + ioend->io_flags = wpc->iomap.flags; + ioend->io_inode = inode; + ioend->io_size = 0; + ioend->io_offset = offset; + ioend->io_private = NULL; + ioend->io_bio = bio; + return ioend; +} + +/* + * Allocate a new bio, and chain the old bio to the new one. + * + * Note that we have to do perform the chaining in this unintuitive order + * so that the bi_private linkage is set up in the right direction for the + * traversal in iomap_finish_ioend(). + */ +static struct bio * +iomap_chain_bio(struct bio *prev) +{ + struct bio *new; + + new = bio_alloc(GFP_NOFS, BIO_MAX_PAGES); + bio_copy_dev(new, prev);/* also copies over blkcg information */ + new->bi_iter.bi_sector = bio_end_sector(prev); + new->bi_opf = prev->bi_opf; + new->bi_write_hint = prev->bi_write_hint; + + bio_chain(prev, new); + bio_get(prev); /* for iomap_finish_ioend */ + submit_bio(prev); + return new; +} + +static bool +iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t offset, + sector_t sector) +{ + if ((wpc->iomap.flags & IOMAP_F_SHARED) != + (wpc->ioend->io_flags & IOMAP_F_SHARED)) + return false; + if (wpc->iomap.type != wpc->ioend->io_type) + return false; + if (offset != wpc->ioend->io_offset + wpc->ioend->io_size) + return false; + if (sector != bio_end_sector(wpc->ioend->io_bio)) + return false; + return true; +} + +/* + * Test to see if we have an existing ioend structure that we could append to + * first, otherwise finish off the current ioend and start another. + */ +static void +iomap_add_to_ioend(struct inode *inode, loff_t offset, struct page *page, + struct iomap_page *iop, struct iomap_writepage_ctx *wpc, + struct writeback_control *wbc, struct list_head *iolist) +{ + sector_t sector = iomap_sector(&wpc->iomap, offset); + unsigned len = i_blocksize(inode); + unsigned poff = offset & (PAGE_SIZE - 1); + bool merged, same_page = false; + + if (!wpc->ioend || !iomap_can_add_to_ioend(wpc, offset, sector)) { + if (wpc->ioend) + list_add(&wpc->ioend->io_list, iolist); + wpc->ioend = iomap_alloc_ioend(inode, wpc, offset, sector, wbc); + } + + merged = __bio_try_merge_page(wpc->ioend->io_bio, page, len, poff, + &same_page); + if (iop && !same_page) + atomic_inc(&iop->write_count); + + if (!merged) { + if (bio_full(wpc->ioend->io_bio, len)) { + wpc->ioend->io_bio = + iomap_chain_bio(wpc->ioend->io_bio); + } + bio_add_page(wpc->ioend->io_bio, page, len, poff); + } + + wpc->ioend->io_size += len; + wbc_account_cgroup_owner(wbc, page, len); +} + +/* + * We implement an immediate ioend submission policy here to avoid needing to + * chain multiple ioends and hence nest mempool allocations which can violate + * forward progress guarantees we need to provide. The current ioend we are + * adding blocks to is cached on the writepage context, and if the new block + * does not append to the cached ioend it will create a new ioend and cache that + * instead. + * + * If a new ioend is created and cached, the old ioend is returned and queued + * locally for submission once the entire page is processed or an error has been + * detected. While ioends are submitted immediately after they are completed, + * batching optimisations are provided by higher level block plugging. + * + * At the end of a writeback pass, there will be a cached ioend remaining on the + * writepage context that the caller will need to submit. + */ +static int +iomap_writepage_map(struct iomap_writepage_ctx *wpc, + struct writeback_control *wbc, struct inode *inode, + struct page *page, u64 end_offset) +{ + struct iomap_page *iop = to_iomap_page(page); + struct iomap_ioend *ioend, *next; + unsigned len = i_blocksize(inode); + u64 file_offset; /* file offset of page */ + int error = 0, count = 0, i; + LIST_HEAD(submit_list); + + WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE && !iop); + WARN_ON_ONCE(iop && atomic_read(&iop->write_count) != 0); + + /* + * Walk through the page to find areas to write back. If we run off the + * end of the current map or find the current map invalid, grab a new + * one. + */ + for (i = 0, file_offset = page_offset(page); + i < (PAGE_SIZE >> inode->i_blkbits) && file_offset < end_offset; + i++, file_offset += len) { + if (iop && !test_bit(i, iop->uptodate)) + continue; + + error = wpc->ops->map_blocks(wpc, inode, file_offset); + if (error) + break; + if (wpc->iomap.type == IOMAP_HOLE) + continue; + iomap_add_to_ioend(inode, file_offset, page, iop, wpc, wbc, + &submit_list); + count++; + } + + WARN_ON_ONCE(!wpc->ioend && !list_empty(&submit_list)); + WARN_ON_ONCE(!PageLocked(page)); + WARN_ON_ONCE(PageWriteback(page)); + + /* + * We cannot cancel the ioend directly here on error. We may have + * already set other pages under writeback and hence we have to run I/O + * completion to mark the error state of the pages under writeback + * appropriately. + */ + if (unlikely(error)) { + if (!count) { + /* + * If the current page hasn't been added to ioend, it + * won't be affected by I/O completions and we must + * discard and unlock it right here. + */ + if (wpc->ops->discard_page) + wpc->ops->discard_page(page); + ClearPageUptodate(page); + unlock_page(page); + goto done; + } + + /* + * If the page was not fully cleaned, we need to ensure that the + * higher layers come back to it correctly. That means we need + * to keep the page dirty, and for WB_SYNC_ALL writeback we need + * to ensure the PAGECACHE_TAG_TOWRITE index mark is not removed + * so another attempt to write this page in this writeback sweep + * will be made. + */ + set_page_writeback_keepwrite(page); + } else { + clear_page_dirty_for_io(page); + set_page_writeback(page); + } + + unlock_page(page); + + /* + * Preserve the original error if there was one, otherwise catch + * submission errors here and propagate into subsequent ioend + * submissions. + */ + list_for_each_entry_safe(ioend, next, &submit_list, io_list) { + int error2; + + list_del_init(&ioend->io_list); + error2 = iomap_submit_ioend(wpc, ioend, error); + if (error2 && !error) + error = error2; + } + + /* + * We can end up here with no error and nothing to write only if we race + * with a partial page truncate on a sub-page block sized filesystem. + */ + if (!count) + end_page_writeback(page); +done: + mapping_set_error(page->mapping, error); + return error; +} + +/* + * Write out a dirty page. + * + * For delalloc space on the page we need to allocate space and flush it. + * For unwritten space on the page we need to start the conversion to + * regular allocated space. + */ +static int +iomap_do_writepage(struct page *page, struct writeback_control *wbc, void *data) +{ + struct iomap_writepage_ctx *wpc = data; + struct inode *inode = page->mapping->host; + pgoff_t end_index; + u64 end_offset; + loff_t offset; + + trace_iomap_writepage(inode, page, 0, 0); + + /* + * Refuse to write the page out if we are called from reclaim context. + * + * This avoids stack overflows when called from deeply used stacks in + * random callers for direct reclaim or memcg reclaim. We explicitly + * allow reclaim from kswapd as the stack usage there is relatively low. + * + * This should never happen except in the case of a VM regression so + * warn about it. + */ + if (WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) == + PF_MEMALLOC)) + goto redirty; + + /* + * Given that we do not allow direct reclaim to call us, we should + * never be called in a recursive filesystem reclaim context. + */ + if (WARN_ON_ONCE(current->flags & PF_MEMALLOC_NOFS)) + goto redirty; + + /* + * Is this page beyond the end of the file? + * + * The page index is less than the end_index, adjust the end_offset + * to the highest offset that this page should represent. + * ----------------------------------------------------- + * | file mapping | | + * ----------------------------------------------------- + * | Page ... | Page N-2 | Page N-1 | Page N | | + * ^--------------------------------^----------|-------- + * | desired writeback range | see else | + * ---------------------------------^------------------| + */ + offset = i_size_read(inode); + end_index = offset >> PAGE_SHIFT; + if (page->index < end_index) + end_offset = (loff_t)(page->index + 1) << PAGE_SHIFT; + else { + /* + * Check whether the page to write out is beyond or straddles + * i_size or not. + * ------------------------------------------------------- + * | file mapping | | + * ------------------------------------------------------- + * | Page ... | Page N-2 | Page N-1 | Page N | Beyond | + * ^--------------------------------^-----------|--------- + * | | Straddles | + * ---------------------------------^-----------|--------| + */ + unsigned offset_into_page = offset & (PAGE_SIZE - 1); + + /* + * Skip the page if it is fully outside i_size, e.g. due to a + * truncate operation that is in progress. We must redirty the + * page so that reclaim stops reclaiming it. Otherwise + * iomap_vm_releasepage() is called on it and gets confused. + * + * Note that the end_index is unsigned long, it would overflow + * if the given offset is greater than 16TB on 32-bit system + * and if we do check the page is fully outside i_size or not + * via "if (page->index >= end_index + 1)" as "end_index + 1" + * will be evaluated to 0. Hence this page will be redirtied + * and be written out repeatedly which would result in an + * infinite loop, the user program that perform this operation + * will hang. Instead, we can verify this situation by checking + * if the page to write is totally beyond the i_size or if it's + * offset is just equal to the EOF. + */ + if (page->index > end_index || + (page->index == end_index && offset_into_page == 0)) + goto redirty; + + /* + * The page straddles i_size. It must be zeroed out on each + * and every writepage invocation because it may be mmapped. + * "A file is mapped in multiples of the page size. For a file + * that is not a multiple of the page size, the remaining + * memory is zeroed when mapped, and writes to that region are + * not written out to the file." + */ + zero_user_segment(page, offset_into_page, PAGE_SIZE); + + /* Adjust the end_offset to the end of file */ + end_offset = offset; + } + + return iomap_writepage_map(wpc, wbc, inode, page, end_offset); + +redirty: + redirty_page_for_writepage(wbc, page); + unlock_page(page); + return 0; +} + +int +iomap_writepage(struct page *page, struct writeback_control *wbc, + struct iomap_writepage_ctx *wpc, + const struct iomap_writeback_ops *ops) +{ + int ret; + + wpc->ops = ops; + ret = iomap_do_writepage(page, wbc, wpc); + if (!wpc->ioend) + return ret; + return iomap_submit_ioend(wpc, wpc->ioend, ret); +} +EXPORT_SYMBOL_GPL(iomap_writepage); + +int +iomap_writepages(struct address_space *mapping, struct writeback_control *wbc, + struct iomap_writepage_ctx *wpc, + const struct iomap_writeback_ops *ops) +{ + int ret; + + wpc->ops = ops; + ret = write_cache_pages(mapping, wbc, iomap_do_writepage, wpc); + if (!wpc->ioend) + return ret; + return iomap_submit_ioend(wpc, wpc->ioend, ret); +} +EXPORT_SYMBOL_GPL(iomap_writepages); + +static int __init iomap_init(void) +{ + return bioset_init(&iomap_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE), + offsetof(struct iomap_ioend, io_inline_bio), + BIOSET_NEED_BVECS); +} +fs_initcall(iomap_init); diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h index 63a98ad01b0f..4ca1aa2f3f6e 100644 --- a/fs/iomap/trace.h +++ b/fs/iomap/trace.h @@ -76,6 +76,7 @@ DEFINE_EVENT(iomap_page_class, name, \ TP_PROTO(struct inode *inode, struct page *page, unsigned long off, \ unsigned int len), \ TP_ARGS(inode, page, off, len)) +DEFINE_PAGE_EVENT(iomap_writepage); DEFINE_PAGE_EVENT(iomap_releasepage); DEFINE_PAGE_EVENT(iomap_invalidatepage); diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index f08563e2bd9f..5936507c6f50 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -18,16 +18,18 @@ #include "xfs_bmap_util.h" #include "xfs_reflink.h" -/* - * structure owned by writepages passed to individual writepage calls - */ struct xfs_writepage_ctx { - struct iomap iomap; + struct iomap_writepage_ctx ctx; unsigned int data_seq; unsigned int cow_seq; - struct xfs_ioend *ioend; }; +static inline struct xfs_writepage_ctx * +XFS_WPC(struct iomap_writepage_ctx *ctx) +{ + return container_of(ctx, struct xfs_writepage_ctx, ctx); +} + struct block_device * xfs_find_bdev_for_inode( struct inode *inode) @@ -54,87 +56,10 @@ xfs_find_daxdev_for_inode( return mp->m_ddev_targp->bt_daxdev; } -static void -xfs_finish_page_writeback( - struct inode *inode, - struct bio_vec *bvec, - int error) -{ - struct iomap_page *iop = to_iomap_page(bvec->bv_page); - - if (error) { - SetPageError(bvec->bv_page); - mapping_set_error(inode->i_mapping, -EIO); - } - - ASSERT(iop || i_blocksize(inode) == PAGE_SIZE); - ASSERT(!iop || atomic_read(&iop->write_count) > 0); - - if (!iop || atomic_dec_and_test(&iop->write_count)) - end_page_writeback(bvec->bv_page); -} - -/* - * We're now finished for good with this ioend structure. Update the page - * state, release holds on bios, and finally free up memory. Do not use the - * ioend after this. - */ -STATIC void -xfs_destroy_ioend( - struct xfs_ioend *ioend, - int error) -{ - struct inode *inode = ioend->io_inode; - struct bio *bio = &ioend->io_inline_bio; - struct bio *last = ioend->io_bio, *next; - u64 start = bio->bi_iter.bi_sector; - bool quiet = bio_flagged(bio, BIO_QUIET); - - for (bio = &ioend->io_inline_bio; bio; bio = next) { - struct bio_vec *bvec; - struct bvec_iter_all iter_all; - - /* - * For the last bio, bi_private points to the ioend, so we - * need to explicitly end the iteration here. - */ - if (bio == last) - next = NULL; - else - next = bio->bi_private; - - /* walk each page on bio, ending page IO on them */ - bio_for_each_segment_all(bvec, bio, iter_all) - xfs_finish_page_writeback(inode, bvec, error); - bio_put(bio); - } - - if (unlikely(error && !quiet)) { - xfs_err_ratelimited(XFS_I(inode)->i_mount, - "writeback error on sector %llu", start); - } -} - -static void -xfs_destroy_ioends( - struct xfs_ioend *ioend, - int error) -{ - struct list_head tmp; - - list_replace_init(&ioend->io_list, &tmp); - xfs_destroy_ioend(ioend, error); - while ((ioend = list_first_entry_or_null(&tmp, struct xfs_ioend, - io_list))) { - list_del_init(&ioend->io_list); - xfs_destroy_ioend(ioend, error); - } -} - /* * Fast and loose check if this write could update the on-disk inode size. */ -static inline bool xfs_ioend_is_append(struct xfs_ioend *ioend) +static inline bool xfs_ioend_is_append(struct iomap_ioend *ioend) { return ioend->io_offset + ioend->io_size > XFS_I(ioend->io_inode)->i_d.di_size; @@ -142,7 +67,7 @@ static inline bool xfs_ioend_is_append(struct xfs_ioend *ioend) STATIC int xfs_setfilesize_trans_alloc( - struct xfs_ioend *ioend) + struct iomap_ioend *ioend) { struct xfs_mount *mp = XFS_I(ioend->io_inode)->i_mount; struct xfs_trans *tp; @@ -215,7 +140,7 @@ xfs_setfilesize( STATIC int xfs_setfilesize_ioend( - struct xfs_ioend *ioend, + struct iomap_ioend *ioend, int error) { struct xfs_inode *ip = XFS_I(ioend->io_inode); @@ -243,7 +168,7 @@ xfs_setfilesize_ioend( */ STATIC void xfs_end_ioend( - struct xfs_ioend *ioend) + struct iomap_ioend *ioend) { struct xfs_inode *ip = XFS_I(ioend->io_inode); xfs_off_t offset = ioend->io_offset; @@ -289,31 +214,10 @@ xfs_end_ioend( done: if (ioend->io_private) error = xfs_setfilesize_ioend(ioend, error); - xfs_destroy_ioends(ioend, error); + iomap_finish_ioends(ioend, error); memalloc_nofs_restore(nofs_flag); } -/* - * We can merge two adjacent ioends if they have the same set of work to do. - */ -static bool -xfs_ioend_can_merge( - struct xfs_ioend *ioend, - struct xfs_ioend *next) -{ - if (ioend->io_bio->bi_status != next->io_bio->bi_status) - return false; - if ((ioend->io_flags & IOMAP_F_SHARED) ^ - (next->io_flags & IOMAP_F_SHARED)) - return false; - if ((ioend->io_type == IOMAP_UNWRITTEN) ^ - (next->io_type == IOMAP_UNWRITTEN)) - return false; - if (ioend->io_offset + ioend->io_size != next->io_offset) - return false; - return true; -} - /* * If the to be merged ioend has a preallocated transaction for file * size updates we need to ensure the ioend it is merged into also @@ -322,8 +226,8 @@ xfs_ioend_can_merge( */ static void xfs_ioend_merge_private( - struct xfs_ioend *ioend, - struct xfs_ioend *next) + struct iomap_ioend *ioend, + struct iomap_ioend *next) { if (!ioend->io_private) { ioend->io_private = next->io_private; @@ -333,53 +237,6 @@ xfs_ioend_merge_private( } } -/* Try to merge adjacent completions. */ -STATIC void -xfs_ioend_try_merge( - struct xfs_ioend *ioend, - struct list_head *more_ioends) -{ - struct xfs_ioend *next; - - INIT_LIST_HEAD(&ioend->io_list); - - while ((next = list_first_entry_or_null(more_ioends, struct xfs_ioend, - io_list))) { - if (!xfs_ioend_can_merge(ioend, next)) - break; - list_move_tail(&next->io_list, &ioend->io_list); - ioend->io_size += next->io_size; - if (next->io_private) - xfs_ioend_merge_private(ioend, next); - } -} - -/* list_sort compare function for ioends */ -static int -xfs_ioend_compare( - void *priv, - struct list_head *a, - struct list_head *b) -{ - struct xfs_ioend *ia; - struct xfs_ioend *ib; - - ia = container_of(a, struct xfs_ioend, io_list); - ib = container_of(b, struct xfs_ioend, io_list); - if (ia->io_offset < ib->io_offset) - return -1; - else if (ia->io_offset > ib->io_offset) - return 1; - return 0; -} - -static void -xfs_sort_ioends( - struct list_head *ioend_list) -{ - list_sort(NULL, ioend_list, xfs_ioend_compare); -} - /* Finish all pending io completions. */ void xfs_end_io( @@ -387,7 +244,7 @@ xfs_end_io( { struct xfs_inode *ip = container_of(work, struct xfs_inode, i_ioend_work); - struct xfs_ioend *ioend; + struct iomap_ioend *ioend; struct list_head tmp; unsigned long flags; @@ -395,16 +252,16 @@ xfs_end_io( list_replace_init(&ip->i_ioend_list, &tmp); spin_unlock_irqrestore(&ip->i_ioend_lock, flags); - xfs_sort_ioends(&tmp); - while ((ioend = list_first_entry_or_null(&tmp, struct xfs_ioend, + iomap_sort_ioends(&tmp); + while ((ioend = list_first_entry_or_null(&tmp, struct iomap_ioend, io_list))) { list_del_init(&ioend->io_list); - xfs_ioend_try_merge(ioend, &tmp); + iomap_ioend_try_merge(ioend, &tmp, xfs_ioend_merge_private); xfs_end_ioend(ioend); } } -static inline bool xfs_ioend_needs_workqueue(struct xfs_ioend *ioend) +static inline bool xfs_ioend_needs_workqueue(struct iomap_ioend *ioend) { return ioend->io_private || ioend->io_type == IOMAP_UNWRITTEN || @@ -415,20 +272,18 @@ STATIC void xfs_end_bio( struct bio *bio) { - struct xfs_ioend *ioend = bio->bi_private; + struct iomap_ioend *ioend = bio->bi_private; struct xfs_inode *ip = XFS_I(ioend->io_inode); - struct xfs_mount *mp = ip->i_mount; unsigned long flags; - if (xfs_ioend_needs_workqueue(ioend)) { - spin_lock_irqsave(&ip->i_ioend_lock, flags); - if (list_empty(&ip->i_ioend_list)) - WARN_ON_ONCE(!queue_work(mp->m_unwritten_workqueue, - &ip->i_ioend_work)); - list_add_tail(&ioend->io_list, &ip->i_ioend_list); - spin_unlock_irqrestore(&ip->i_ioend_lock, flags); - } else - xfs_destroy_ioend(ioend, blk_status_to_errno(bio->bi_status)); + ASSERT(xfs_ioend_needs_workqueue(ioend)); + + spin_lock_irqsave(&ip->i_ioend_lock, flags); + if (list_empty(&ip->i_ioend_list)) + WARN_ON_ONCE(!queue_work(ip->i_mount->m_unwritten_workqueue, + &ip->i_ioend_work)); + list_add_tail(&ioend->io_list, &ip->i_ioend_list); + spin_unlock_irqrestore(&ip->i_ioend_lock, flags); } /* @@ -437,7 +292,7 @@ xfs_end_bio( */ static bool xfs_imap_valid( - struct xfs_writepage_ctx *wpc, + struct iomap_writepage_ctx *wpc, struct xfs_inode *ip, loff_t offset) { @@ -459,10 +314,10 @@ xfs_imap_valid( * checked (and found nothing at this offset) could have added * overlapping blocks. */ - if (wpc->data_seq != READ_ONCE(ip->i_df.if_seq)) + if (XFS_WPC(wpc)->data_seq != READ_ONCE(ip->i_df.if_seq)) return false; if (xfs_inode_has_cow_data(ip) && - wpc->cow_seq != READ_ONCE(ip->i_cowfp->if_seq)) + XFS_WPC(wpc)->cow_seq != READ_ONCE(ip->i_cowfp->if_seq)) return false; return true; } @@ -477,12 +332,18 @@ xfs_imap_valid( */ static int xfs_convert_blocks( - struct xfs_writepage_ctx *wpc, + struct iomap_writepage_ctx *wpc, struct xfs_inode *ip, int whichfork, loff_t offset) { int error; + unsigned *seq; + + if (whichfork == XFS_COW_FORK) + seq = &XFS_WPC(wpc)->cow_seq; + else + seq = &XFS_WPC(wpc)->data_seq; /* * Attempt to allocate whatever delalloc extent currently backs offset @@ -492,8 +353,7 @@ xfs_convert_blocks( */ do { error = xfs_bmapi_convert_delalloc(ip, whichfork, offset, - &wpc->iomap, whichfork == XFS_COW_FORK ? - &wpc->cow_seq : &wpc->data_seq); + &wpc->iomap, seq); if (error) return error; } while (wpc->iomap.offset + wpc->iomap.length <= offset); @@ -501,9 +361,9 @@ xfs_convert_blocks( return 0; } -STATIC int +static int xfs_map_blocks( - struct xfs_writepage_ctx *wpc, + struct iomap_writepage_ctx *wpc, struct inode *inode, loff_t offset) { @@ -559,7 +419,7 @@ retry: xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &imap)) cow_fsb = imap.br_startoff; if (cow_fsb != NULLFILEOFF && cow_fsb <= offset_fsb) { - wpc->cow_seq = READ_ONCE(ip->i_cowfp->if_seq); + XFS_WPC(wpc)->cow_seq = READ_ONCE(ip->i_cowfp->if_seq); xfs_iunlock(ip, XFS_ILOCK_SHARED); whichfork = XFS_COW_FORK; @@ -582,7 +442,7 @@ retry: */ if (!xfs_iext_lookup_extent(ip, &ip->i_df, offset_fsb, &icur, &imap)) imap.br_startoff = end_fsb; /* fake a hole past EOF */ - wpc->data_seq = READ_ONCE(ip->i_df.if_seq); + XFS_WPC(wpc)->data_seq = READ_ONCE(ip->i_df.if_seq); xfs_iunlock(ip, XFS_ILOCK_SHARED); /* landed in a hole or beyond EOF? */ @@ -645,24 +505,9 @@ allocate_blocks: return 0; } -/* - * Submit the bio for an ioend. We are passed an ioend with a bio attached to - * it, and we submit that bio. The ioend may be used for multiple bio - * submissions, so we only want to allocate an append transaction for the ioend - * once. In the case of multiple bio submission, each bio will take an IO - * reference to the ioend to ensure that the ioend completion is only done once - * all bios have been submitted and the ioend is really done. - * - * If @status is non-zero, it means that we have a situation where some part of - * the submission process has failed after we have marked paged for writeback - * and unlocked them. In this situation, we need to fail the bio and ioend - * rather than submit it to IO. This typically only happens on a filesystem - * shutdown. - */ -STATIC int -xfs_submit_ioend( - struct writeback_control *wbc, - struct xfs_ioend *ioend, +static int +xfs_prepare_ioend( + struct iomap_ioend *ioend, int status) { unsigned int nofs_flag; @@ -690,137 +535,9 @@ xfs_submit_ioend( memalloc_nofs_restore(nofs_flag); - ioend->io_bio->bi_private = ioend; - ioend->io_bio->bi_end_io = xfs_end_bio; - - /* - * If we are failing the IO now, just mark the ioend with an - * error and finish it. This will run IO completion immediately - * as there is only one reference to the ioend at this point in - * time. - */ - if (status) { - ioend->io_bio->bi_status = errno_to_blk_status(status); - bio_endio(ioend->io_bio); - return status; - } - - submit_bio(ioend->io_bio); - return 0; -} - -static struct xfs_ioend * -xfs_alloc_ioend( - struct inode *inode, - struct xfs_writepage_ctx *wpc, - xfs_off_t offset, - sector_t sector, - struct writeback_control *wbc) -{ - struct xfs_ioend *ioend; - struct bio *bio; - - bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &xfs_ioend_bioset); - bio_set_dev(bio, wpc->iomap.bdev); - bio->bi_iter.bi_sector = sector; - bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc); - bio->bi_write_hint = inode->i_write_hint; - wbc_init_bio(wbc, bio); - - ioend = container_of(bio, struct xfs_ioend, io_inline_bio); - INIT_LIST_HEAD(&ioend->io_list); - ioend->io_type = wpc->iomap.type; - ioend->io_flags = wpc->iomap.flags; - ioend->io_inode = inode; - ioend->io_size = 0; - ioend->io_offset = offset; - ioend->io_private = NULL; - ioend->io_bio = bio; - return ioend; -} - -/* - * Allocate a new bio, and chain the old bio to the new one. - * - * Note that we have to do perform the chaining in this unintuitive order - * so that the bi_private linkage is set up in the right direction for the - * traversal in xfs_destroy_ioend(). - */ -static struct bio * -xfs_chain_bio( - struct bio *prev) -{ - struct bio *new; - - new = bio_alloc(GFP_NOFS, BIO_MAX_PAGES); - bio_copy_dev(new, prev);/* also copies over blkcg information */ - new->bi_iter.bi_sector = bio_end_sector(prev); - new->bi_opf = prev->bi_opf; - new->bi_write_hint = prev->bi_write_hint; - - bio_chain(prev, new); - bio_get(prev); /* for xfs_destroy_ioend */ - submit_bio(prev); - return new; -} - -static bool -xfs_can_add_to_ioend( - struct xfs_writepage_ctx *wpc, - xfs_off_t offset, - sector_t sector) -{ - if ((wpc->iomap.flags & IOMAP_F_SHARED) != - (wpc->ioend->io_flags & IOMAP_F_SHARED)) - return false; - if (wpc->iomap.type != wpc->ioend->io_type) - return false; - if (offset != wpc->ioend->io_offset + wpc->ioend->io_size) - return false; - if (sector != bio_end_sector(wpc->ioend->io_bio)) - return false; - return true; -} - -/* - * Test to see if we have an existing ioend structure that we could append to - * first, otherwise finish off the current ioend and start another. - */ -STATIC void -xfs_add_to_ioend( - struct inode *inode, - xfs_off_t offset, - struct page *page, - struct iomap_page *iop, - struct xfs_writepage_ctx *wpc, - struct writeback_control *wbc, - struct list_head *iolist) -{ - sector_t sector = iomap_sector(&wpc->iomap, offset); - unsigned len = i_blocksize(inode); - unsigned poff = offset & (PAGE_SIZE - 1); - bool merged, same_page = false; - - if (!wpc->ioend || !xfs_can_add_to_ioend(wpc, offset, sector)) { - if (wpc->ioend) - list_add(&wpc->ioend->io_list, iolist); - wpc->ioend = xfs_alloc_ioend(inode, wpc, offset, sector, wbc); - } - - merged = __bio_try_merge_page(wpc->ioend->io_bio, page, len, poff, - &same_page); - - if (iop && !same_page) - atomic_inc(&iop->write_count); - - if (!merged) { - if (bio_full(wpc->ioend->io_bio, len)) - wpc->ioend->io_bio = xfs_chain_bio(wpc->ioend->io_bio); - bio_add_page(wpc->ioend->io_bio, page, len, poff); - } - - wpc->ioend->io_size += len; - wbc_account_cgroup_owner(wbc, page, len); + if (xfs_ioend_needs_workqueue(ioend)) + ioend->io_bio->bi_end_io = xfs_end_bio; + return status; } /* @@ -834,8 +551,8 @@ xfs_add_to_ioend( * transaction as there is no space left for block reservation (typically why we * see a ENOSPC in writeback). */ -STATIC void -xfs_aops_discard_page( +static void +xfs_discard_page( struct page *page) { struct inode *inode = page->mapping->host; @@ -860,243 +577,11 @@ out_invalidate: iomap_invalidatepage(page, 0, PAGE_SIZE); } -/* - * We implement an immediate ioend submission policy here to avoid needing to - * chain multiple ioends and hence nest mempool allocations which can violate - * forward progress guarantees we need to provide. The current ioend we are - * adding blocks to is cached on the writepage context, and if the new block - * does not append to the cached ioend it will create a new ioend and cache that - * instead. - * - * If a new ioend is created and cached, the old ioend is returned and queued - * locally for submission once the entire page is processed or an error has been - * detected. While ioends are submitted immediately after they are completed, - * batching optimisations are provided by higher level block plugging. - * - * At the end of a writeback pass, there will be a cached ioend remaining on the - * writepage context that the caller will need to submit. - */ -static int -xfs_writepage_map( - struct xfs_writepage_ctx *wpc, - struct writeback_control *wbc, - struct inode *inode, - struct page *page, - uint64_t end_offset) -{ - LIST_HEAD(submit_list); - struct iomap_page *iop = to_iomap_page(page); - unsigned len = i_blocksize(inode); - struct xfs_ioend *ioend, *next; - uint64_t file_offset; /* file offset of page */ - int error = 0, count = 0, i; - - ASSERT(iop || i_blocksize(inode) == PAGE_SIZE); - ASSERT(!iop || atomic_read(&iop->write_count) == 0); - - /* - * Walk through the page to find areas to write back. If we run off the - * end of the current map or find the current map invalid, grab a new - * one. - */ - for (i = 0, file_offset = page_offset(page); - i < (PAGE_SIZE >> inode->i_blkbits) && file_offset < end_offset; - i++, file_offset += len) { - if (iop && !test_bit(i, iop->uptodate)) - continue; - - error = xfs_map_blocks(wpc, inode, file_offset); - if (error) - break; - if (wpc->iomap.type == IOMAP_HOLE) - continue; - xfs_add_to_ioend(inode, file_offset, page, iop, wpc, wbc, - &submit_list); - count++; - } - - ASSERT(wpc->ioend || list_empty(&submit_list)); - ASSERT(PageLocked(page)); - ASSERT(!PageWriteback(page)); - - /* - * On error, we have to fail the ioend here because we may have set - * pages under writeback, we have to make sure we run IO completion to - * mark the error state of the IO appropriately, so we can't cancel the - * ioend directly here. That means we have to mark this page as under - * writeback if we included any blocks from it in the ioend chain so - * that completion treats it correctly. - * - * If we didn't include the page in the ioend, the on error we can - * simply discard and unlock it as there are no other users of the page - * now. The caller will still need to trigger submission of outstanding - * ioends on the writepage context so they are treated correctly on - * error. - */ - if (unlikely(error)) { - if (!count) { - xfs_aops_discard_page(page); - ClearPageUptodate(page); - unlock_page(page); - goto done; - } - - /* - * If the page was not fully cleaned, we need to ensure that the - * higher layers come back to it correctly. That means we need - * to keep the page dirty, and for WB_SYNC_ALL writeback we need - * to ensure the PAGECACHE_TAG_TOWRITE index mark is not removed - * so another attempt to write this page in this writeback sweep - * will be made. - */ - set_page_writeback_keepwrite(page); - } else { - clear_page_dirty_for_io(page); - set_page_writeback(page); - } - - unlock_page(page); - - /* - * Preserve the original error if there was one, otherwise catch - * submission errors here and propagate into subsequent ioend - * submissions. - */ - list_for_each_entry_safe(ioend, next, &submit_list, io_list) { - int error2; - - list_del_init(&ioend->io_list); - error2 = xfs_submit_ioend(wbc, ioend, error); - if (error2 && !error) - error = error2; - } - - /* - * We can end up here with no error and nothing to write only if we race - * with a partial page truncate on a sub-page block sized filesystem. - */ - if (!count) - end_page_writeback(page); -done: - mapping_set_error(page->mapping, error); - return error; -} - -/* - * Write out a dirty page. - * - * For delalloc space on the page we need to allocate space and flush it. - * For unwritten space on the page we need to start the conversion to - * regular allocated space. - */ -STATIC int -xfs_do_writepage( - struct page *page, - struct writeback_control *wbc, - void *data) -{ - struct xfs_writepage_ctx *wpc = data; - struct inode *inode = page->mapping->host; - loff_t offset; - uint64_t end_offset; - pgoff_t end_index; - - trace_xfs_writepage(inode, page, 0, 0); - - /* - * Refuse to write the page out if we are called from reclaim context. - * - * This avoids stack overflows when called from deeply used stacks in - * random callers for direct reclaim or memcg reclaim. We explicitly - * allow reclaim from kswapd as the stack usage there is relatively low. - * - * This should never happen except in the case of a VM regression so - * warn about it. - */ - if (WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) == - PF_MEMALLOC)) - goto redirty; - - /* - * Given that we do not allow direct reclaim to call us, we should - * never be called while in a filesystem transaction. - */ - if (WARN_ON_ONCE(current->flags & PF_MEMALLOC_NOFS)) - goto redirty; - - /* - * Is this page beyond the end of the file? - * - * The page index is less than the end_index, adjust the end_offset - * to the highest offset that this page should represent. - * ----------------------------------------------------- - * | file mapping | | - * ----------------------------------------------------- - * | Page ... | Page N-2 | Page N-1 | Page N | | - * ^--------------------------------^----------|-------- - * | desired writeback range | see else | - * ---------------------------------^------------------| - */ - offset = i_size_read(inode); - end_index = offset >> PAGE_SHIFT; - if (page->index < end_index) - end_offset = (xfs_off_t)(page->index + 1) << PAGE_SHIFT; - else { - /* - * Check whether the page to write out is beyond or straddles - * i_size or not. - * ------------------------------------------------------- - * | file mapping | | - * ------------------------------------------------------- - * | Page ... | Page N-2 | Page N-1 | Page N | Beyond | - * ^--------------------------------^-----------|--------- - * | | Straddles | - * ---------------------------------^-----------|--------| - */ - unsigned offset_into_page = offset & (PAGE_SIZE - 1); - - /* - * Skip the page if it is fully outside i_size, e.g. due to a - * truncate operation that is in progress. We must redirty the - * page so that reclaim stops reclaiming it. Otherwise - * xfs_vm_releasepage() is called on it and gets confused. - * - * Note that the end_index is unsigned long, it would overflow - * if the given offset is greater than 16TB on 32-bit system - * and if we do check the page is fully outside i_size or not - * via "if (page->index >= end_index + 1)" as "end_index + 1" - * will be evaluated to 0. Hence this page will be redirtied - * and be written out repeatedly which would result in an - * infinite loop, the user program that perform this operation - * will hang. Instead, we can verify this situation by checking - * if the page to write is totally beyond the i_size or if it's - * offset is just equal to the EOF. - */ - if (page->index > end_index || - (page->index == end_index && offset_into_page == 0)) - goto redirty; - - /* - * The page straddles i_size. It must be zeroed out on each - * and every writepage invocation because it may be mmapped. - * "A file is mapped in multiples of the page size. For a file - * that is not a multiple of the page size, the remaining - * memory is zeroed when mapped, and writes to that region are - * not written out to the file." - */ - zero_user_segment(page, offset_into_page, PAGE_SIZE); - - /* Adjust the end_offset to the end of file */ - end_offset = offset; - } - - return xfs_writepage_map(wpc, wbc, inode, page, end_offset); - -redirty: - redirty_page_for_writepage(wbc, page); - unlock_page(page); - return 0; -} +static const struct iomap_writeback_ops xfs_writeback_ops = { + .map_blocks = xfs_map_blocks, + .prepare_ioend = xfs_prepare_ioend, + .discard_page = xfs_discard_page, +}; STATIC int xfs_vm_writepage( @@ -1104,12 +589,8 @@ xfs_vm_writepage( struct writeback_control *wbc) { struct xfs_writepage_ctx wpc = { }; - int ret; - ret = xfs_do_writepage(page, wbc, &wpc); - if (wpc.ioend) - ret = xfs_submit_ioend(wbc, wpc.ioend, ret); - return ret; + return iomap_writepage(page, wbc, &wpc.ctx, &xfs_writeback_ops); } STATIC int @@ -1118,13 +599,9 @@ xfs_vm_writepages( struct writeback_control *wbc) { struct xfs_writepage_ctx wpc = { }; - int ret; xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED); - ret = write_cache_pages(mapping, wbc, xfs_do_writepage, &wpc); - if (wpc.ioend) - ret = xfs_submit_ioend(wbc, wpc.ioend, ret); - return ret; + return iomap_writepages(mapping, wbc, &wpc.ctx, &xfs_writeback_ops); } STATIC int diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h index 4a0226cdad4f..687b11f34fa2 100644 --- a/fs/xfs/xfs_aops.h +++ b/fs/xfs/xfs_aops.h @@ -6,23 +6,6 @@ #ifndef __XFS_AOPS_H__ #define __XFS_AOPS_H__ -extern struct bio_set xfs_ioend_bioset; - -/* - * Structure for buffered I/O completions. - */ -struct xfs_ioend { - struct list_head io_list; /* next ioend in chain */ - u16 io_type; - u16 io_flags; /* IOMAP_F_* */ - struct inode *io_inode; /* file being written to */ - size_t io_size; /* size of the extent */ - xfs_off_t io_offset; /* offset in the file */ - void *io_private; /* file system private data */ - struct bio *io_bio; /* bio being built */ - struct bio io_inline_bio; /* MUST BE LAST! */ -}; - extern const struct address_space_operations xfs_address_space_operations; extern const struct address_space_operations xfs_dax_aops; diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 8d1df9f8be07..0a8cf6b87a21 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -40,7 +40,6 @@ #include static const struct super_operations xfs_super_operations; -struct bio_set xfs_ioend_bioset; static struct kset *xfs_kset; /* top-level xfs sysfs dir */ #ifdef DEBUG @@ -1853,15 +1852,10 @@ MODULE_ALIAS_FS("xfs"); STATIC int __init xfs_init_zones(void) { - if (bioset_init(&xfs_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE), - offsetof(struct xfs_ioend, io_inline_bio), - BIOSET_NEED_BVECS)) - goto out; - xfs_log_ticket_zone = kmem_zone_init(sizeof(xlog_ticket_t), "xfs_log_ticket"); if (!xfs_log_ticket_zone) - goto out_free_ioend_bioset; + goto out; xfs_bmap_free_item_zone = kmem_zone_init( sizeof(struct xfs_extent_free_item), @@ -1996,8 +1990,6 @@ xfs_init_zones(void) kmem_zone_destroy(xfs_bmap_free_item_zone); out_destroy_log_ticket_zone: kmem_zone_destroy(xfs_log_ticket_zone); - out_free_ioend_bioset: - bioset_exit(&xfs_ioend_bioset); out: return -ENOMEM; } @@ -2028,7 +2020,6 @@ xfs_destroy_zones(void) kmem_zone_destroy(xfs_btree_cur_zone); kmem_zone_destroy(xfs_bmap_free_item_zone); kmem_zone_destroy(xfs_log_ticket_zone); - bioset_exit(&xfs_ioend_bioset); } STATIC int __init diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index eae4b29c174e..cbb23d7a3554 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -1158,45 +1158,6 @@ DEFINE_RW_EVENT(xfs_file_buffered_write); DEFINE_RW_EVENT(xfs_file_direct_write); DEFINE_RW_EVENT(xfs_file_dax_write); -DECLARE_EVENT_CLASS(xfs_page_class, - TP_PROTO(struct inode *inode, struct page *page, unsigned long off, - unsigned int len), - TP_ARGS(inode, page, off, len), - TP_STRUCT__entry( - __field(dev_t, dev) - __field(xfs_ino_t, ino) - __field(pgoff_t, pgoff) - __field(loff_t, size) - __field(unsigned long, offset) - __field(unsigned int, length) - ), - TP_fast_assign( - __entry->dev = inode->i_sb->s_dev; - __entry->ino = XFS_I(inode)->i_ino; - __entry->pgoff = page_offset(page); - __entry->size = i_size_read(inode); - __entry->offset = off; - __entry->length = len; - ), - TP_printk("dev %d:%d ino 0x%llx pgoff 0x%lx size 0x%llx offset %lx " - "length %x", - MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->ino, - __entry->pgoff, - __entry->size, - __entry->offset, - __entry->length) -) - -#define DEFINE_PAGE_EVENT(name) \ -DEFINE_EVENT(xfs_page_class, name, \ - TP_PROTO(struct inode *inode, struct page *page, unsigned long off, \ - unsigned int len), \ - TP_ARGS(inode, page, off, len)) -DEFINE_PAGE_EVENT(xfs_writepage); -DEFINE_PAGE_EVENT(xfs_releasepage); -DEFINE_PAGE_EVENT(xfs_invalidatepage); - DECLARE_EVENT_CLASS(xfs_imap_class, TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count, int whichfork, struct xfs_bmbt_irec *irec), diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 4b25ad6b5edd..6e00bb843c7f 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -4,6 +4,7 @@ #include #include +#include #include #include #include @@ -12,6 +13,7 @@ struct address_space; struct fiemap_extent_info; struct inode; +struct iomap_writepage_ctx; struct iov_iter; struct kiocb; struct page; @@ -185,6 +187,63 @@ loff_t iomap_seek_data(struct inode *inode, loff_t offset, sector_t iomap_bmap(struct address_space *mapping, sector_t bno, const struct iomap_ops *ops); +/* + * Structure for writeback I/O completions. + */ +struct iomap_ioend { + struct list_head io_list; /* next ioend in chain */ + u16 io_type; + u16 io_flags; /* IOMAP_F_* */ + struct inode *io_inode; /* file being written to */ + size_t io_size; /* size of the extent */ + loff_t io_offset; /* offset in the file */ + void *io_private; /* file system private data */ + struct bio *io_bio; /* bio being built */ + struct bio io_inline_bio; /* MUST BE LAST! */ +}; + +struct iomap_writeback_ops { + /* + * Required, maps the blocks so that writeback can be performed on + * the range starting at offset. + */ + int (*map_blocks)(struct iomap_writepage_ctx *wpc, struct inode *inode, + loff_t offset); + + /* + * Optional, allows the file systems to perform actions just before + * submitting the bio and/or override the bio end_io handler for complex + * operations like copy on write extent manipulation or unwritten extent + * conversions. + */ + int (*prepare_ioend)(struct iomap_ioend *ioend, int status); + + /* + * Optional, allows the file system to discard state on a page where + * we failed to submit any I/O. + */ + void (*discard_page)(struct page *page); +}; + +struct iomap_writepage_ctx { + struct iomap iomap; + struct iomap_ioend *ioend; + const struct iomap_writeback_ops *ops; +}; + +void iomap_finish_ioends(struct iomap_ioend *ioend, int error); +void iomap_ioend_try_merge(struct iomap_ioend *ioend, + struct list_head *more_ioends, + void (*merge_private)(struct iomap_ioend *ioend, + struct iomap_ioend *next)); +void iomap_sort_ioends(struct list_head *ioend_list); +int iomap_writepage(struct page *page, struct writeback_control *wbc, + struct iomap_writepage_ctx *wpc, + const struct iomap_writeback_ops *ops); +int iomap_writepages(struct address_space *mapping, + struct writeback_control *wbc, struct iomap_writepage_ctx *wpc, + const struct iomap_writeback_ops *ops); + /* * Flags for direct I/O ->end_io: */ -- cgit v1.2.3-71-gd317 From ab08b01ec0a205d9c98e712eb504c850a51e6fdb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 17 Oct 2019 13:12:19 -0700 Subject: iomap: move struct iomap_page out of iomap.h Now that all the writepage code is in the iomap code there is no need to keep this structure public. Signed-off-by: Christoph Hellwig Reviewed-by: Dave Chinner Reviewed-by: Carlos Maiolino Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/iomap/buffered-io.c | 17 +++++++++++++++++ include/linux/iomap.h | 17 ----------------- 2 files changed, 17 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 901c1a799238..b5ff54fddf1f 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -21,6 +21,23 @@ #include "../internal.h" +/* + * Structure allocated for each page when block size < PAGE_SIZE to track + * sub-page uptodate status and I/O completions. + */ +struct iomap_page { + atomic_t read_count; + atomic_t write_count; + DECLARE_BITMAP(uptodate, PAGE_SIZE / 512); +}; + +static inline struct iomap_page *to_iomap_page(struct page *page) +{ + if (page_has_private(page)) + return (struct iomap_page *)page_private(page); + return NULL; +} + static struct bio_set iomap_ioend_bioset; static struct iomap_page * diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 6e00bb843c7f..0f741eebf3a7 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -136,23 +136,6 @@ loff_t iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags, const struct iomap_ops *ops, void *data, iomap_actor_t actor); -/* - * Structure allocate for each page when block size < PAGE_SIZE to track - * sub-page uptodate status and I/O completions. - */ -struct iomap_page { - atomic_t read_count; - atomic_t write_count; - DECLARE_BITMAP(uptodate, PAGE_SIZE / 512); -}; - -static inline struct iomap_page *to_iomap_page(struct page *page) -{ - if (page_has_private(page)) - return (struct iomap_page *)page_private(page); - return NULL; -} - ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops); int iomap_readpage(struct page *page, const struct iomap_ops *ops); -- cgit v1.2.3-71-gd317 From 65a60e8687c1c8f69aae3e77eafbf4a54b9f99e7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 18 Oct 2019 16:40:17 -0700 Subject: iomap: better document the IOMAP_F_* flags The documentation for IOMAP_F_* is a bit disorganized, and doesn't mention the fact that most flags are set by the file system and consumed by the iomap core, while IOMAP_F_SIZE_CHANGED is set by the core and consumed by the file system. Signed-off-by: Christoph Hellwig Reviewed-by: Allison Collins Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/iomap.h | 31 +++++++++++++++++++++++-------- 1 file changed, 23 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 0f741eebf3a7..8016700e6121 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -30,23 +30,38 @@ struct vm_fault; #define IOMAP_INLINE 0x05 /* data inline in the inode */ /* - * Flags for all iomap mappings: + * Flags reported by the file system from iomap_begin: + * + * IOMAP_F_NEW indicates that the blocks have been newly allocated and need + * zeroing for areas that no data is copied to. * * IOMAP_F_DIRTY indicates the inode has uncommitted metadata needed to access * written data and requires fdatasync to commit them to persistent storage. * This needs to take into account metadata changes that *may* be made at IO * completion, such as file size updates from direct IO. + * + * IOMAP_F_SHARED indicates that the blocks are shared, and will need to be + * unshared as part a write. + * + * IOMAP_F_MERGED indicates that the iomap contains the merge of multiple block + * mappings. + * + * IOMAP_F_BUFFER_HEAD indicates that the file system requires the use of + * buffer heads for this mapping. */ -#define IOMAP_F_NEW 0x01 /* blocks have been newly allocated */ -#define IOMAP_F_DIRTY 0x02 /* uncommitted metadata */ -#define IOMAP_F_BUFFER_HEAD 0x04 /* file system requires buffer heads */ -#define IOMAP_F_SIZE_CHANGED 0x08 /* file size has changed */ +#define IOMAP_F_NEW 0x01 +#define IOMAP_F_DIRTY 0x02 +#define IOMAP_F_SHARED 0x04 +#define IOMAP_F_MERGED 0x08 +#define IOMAP_F_BUFFER_HEAD 0x10 /* - * Flags that only need to be reported for IOMAP_REPORT requests: + * Flags set by the core iomap code during operations: + * + * IOMAP_F_SIZE_CHANGED indicates to the iomap_end method that the file size + * has changed as the result of this write operation. */ -#define IOMAP_F_MERGED 0x10 /* contains multiple blocks/extents */ -#define IOMAP_F_SHARED 0x20 /* block shared with another file */ +#define IOMAP_F_SIZE_CHANGED 0x100 /* * Flags from 0x1000 up are for file system specific usage: -- cgit v1.2.3-71-gd317 From 3590c4d8979bcc364e2ded95ab3966b4e436b7bf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 18 Oct 2019 16:41:34 -0700 Subject: iomap: ignore non-shared or non-data blocks in xfs_file_dirty xfs_file_dirty is used to unshare reflink blocks. Rename the function to xfs_file_unshare to better document that purpose, and skip iomaps that are not shared and don't need zeroing. This will allow to simplify the caller. Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/iomap/buffered-io.c | 15 +++++++++++---- fs/xfs/xfs_reflink.c | 2 +- include/linux/iomap.h | 2 +- 3 files changed, 13 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 8f9b54db3811..30df87ac8349 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -887,12 +887,19 @@ __iomap_read_page(struct inode *inode, loff_t offset) } static loff_t -iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data, +iomap_unshare_actor(struct inode *inode, loff_t pos, loff_t length, void *data, struct iomap *iomap) { long status = 0; ssize_t written = 0; + /* don't bother with blocks that are not shared to start with */ + if (!(iomap->flags & IOMAP_F_SHARED)) + return length; + /* don't bother with holes or unwritten extents */ + if (iomap->type == IOMAP_HOLE || iomap->type == IOMAP_UNWRITTEN) + return length; + do { struct page *page, *rpage; unsigned long offset; /* Offset into pagecache page */ @@ -932,14 +939,14 @@ iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data, } int -iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len, +iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, const struct iomap_ops *ops) { loff_t ret; while (len) { ret = iomap_apply(inode, pos, len, IOMAP_WRITE, ops, NULL, - iomap_dirty_actor); + iomap_unshare_actor); if (ret <= 0) return ret; pos += ret; @@ -948,7 +955,7 @@ iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len, return 0; } -EXPORT_SYMBOL_GPL(iomap_file_dirty); +EXPORT_SYMBOL_GPL(iomap_file_unshare); static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset, unsigned bytes, struct iomap *iomap) diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 0f08153b4994..a9634110c783 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1442,7 +1442,7 @@ xfs_reflink_dirty_extents( flen = XFS_FSB_TO_B(mp, rlen); if (fpos + flen > isize) flen = isize - fpos; - error = iomap_file_dirty(VFS_I(ip), fpos, flen, + error = iomap_file_unshare(VFS_I(ip), fpos, flen, &xfs_iomap_ops); xfs_ilock(ip, XFS_ILOCK_EXCL); if (error) diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 8016700e6121..1623851ade90 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -168,7 +168,7 @@ int iomap_migrate_page(struct address_space *mapping, struct page *newpage, #else #define iomap_migrate_page NULL #endif -int iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len, +int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, const struct iomap_ops *ops); int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, const struct iomap_ops *ops); -- cgit v1.2.3-71-gd317 From eb81cf9d0e18d438e27339e0d1a49d3ac8644674 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 18 Oct 2019 16:43:08 -0700 Subject: iomap: renumber IOMAP_HOLE to 0 Instead of keeping a separate unnamed state for uninitialized iomaps, renumber IOMAP_HOLE to zero so that an uninitialized iomap is treated as a hole. Suggested-by: Darrick J. Wong Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/iomap.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 1623851ade90..53e6e2275d3d 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -23,11 +23,11 @@ struct vm_fault; /* * Types of block ranges for iomap mappings: */ -#define IOMAP_HOLE 0x01 /* no blocks allocated, need allocation */ -#define IOMAP_DELALLOC 0x02 /* delayed allocation blocks */ -#define IOMAP_MAPPED 0x03 /* blocks allocated at @addr */ -#define IOMAP_UNWRITTEN 0x04 /* blocks allocated at @addr in unwritten state */ -#define IOMAP_INLINE 0x05 /* data inline in the inode */ +#define IOMAP_HOLE 0 /* no blocks allocated, need allocation */ +#define IOMAP_DELALLOC 1 /* delayed allocation blocks */ +#define IOMAP_MAPPED 2 /* blocks allocated at @addr */ +#define IOMAP_UNWRITTEN 3 /* blocks allocated at @addr in unwritten state */ +#define IOMAP_INLINE 4 /* data inline in the inode */ /* * Flags reported by the file system from iomap_begin: -- cgit v1.2.3-71-gd317 From c039b99792726346ad46ff17c5a5bcb77a5edac4 Mon Sep 17 00:00:00 2001 From: Goldwyn Rodrigues Date: Fri, 18 Oct 2019 16:44:10 -0700 Subject: iomap: use a srcmap for a read-modify-write I/O The srcmap is used to identify where the read is to be performed from. It is passed to ->iomap_begin, which can fill it in if we need to read data for partially written blocks from a different location than the write target. The srcmap is only supported for buffered writes so far. Signed-off-by: Goldwyn Rodrigues [hch: merged two patches, removed the IOMAP_F_COW flag, use iomap as srcmap if not set, adjust length down to srcmap end as well] Signed-off-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong Acked-by: Goldwyn Rodrigues --- fs/dax.c | 13 ++++++---- fs/ext2/inode.c | 2 +- fs/ext4/inode.c | 2 +- fs/gfs2/bmap.c | 3 ++- fs/iomap/apply.c | 25 ++++++++++++++----- fs/iomap/buffered-io.c | 65 +++++++++++++++++++++++++++----------------------- fs/iomap/direct-io.c | 2 +- fs/iomap/fiemap.c | 4 ++-- fs/iomap/seek.c | 4 ++-- fs/iomap/swapfile.c | 3 ++- fs/xfs/xfs_iomap.c | 9 ++++--- include/linux/iomap.h | 5 ++-- 12 files changed, 82 insertions(+), 55 deletions(-) (limited to 'include/linux') diff --git a/fs/dax.c b/fs/dax.c index 6bf81f931de3..68eef98cd9c4 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1090,7 +1090,7 @@ EXPORT_SYMBOL_GPL(__dax_zero_page_range); static loff_t dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data, - struct iomap *iomap) + struct iomap *iomap, struct iomap *srcmap) { struct block_device *bdev = iomap->bdev; struct dax_device *dax_dev = iomap->dax_dev; @@ -1247,7 +1247,8 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp, struct inode *inode = mapping->host; unsigned long vaddr = vmf->address; loff_t pos = (loff_t)vmf->pgoff << PAGE_SHIFT; - struct iomap iomap = { 0 }; + struct iomap iomap = { .type = IOMAP_HOLE }; + struct iomap srcmap = { .type = IOMAP_HOLE }; unsigned flags = IOMAP_FAULT; int error, major = 0; bool write = vmf->flags & FAULT_FLAG_WRITE; @@ -1292,7 +1293,7 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp, * the file system block size to be equal the page size, which means * that we never have to deal with more than a single extent here. */ - error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap); + error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap, &srcmap); if (iomap_errp) *iomap_errp = error; if (error) { @@ -1471,7 +1472,8 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp, unsigned int iomap_flags = (write ? IOMAP_WRITE : 0) | IOMAP_FAULT; struct inode *inode = mapping->host; vm_fault_t result = VM_FAULT_FALLBACK; - struct iomap iomap = { 0 }; + struct iomap iomap = { .type = IOMAP_HOLE }; + struct iomap srcmap = { .type = IOMAP_HOLE }; pgoff_t max_pgoff; void *entry; loff_t pos; @@ -1546,7 +1548,8 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp, * to look up our filesystem block. */ pos = (loff_t)xas.xa_index << PAGE_SHIFT; - error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap); + error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap, + &srcmap); if (error) goto unlock_entry; diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 7004ce581a32..467c13ff6b40 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -801,7 +801,7 @@ int ext2_get_block(struct inode *inode, sector_t iblock, #ifdef CONFIG_FS_DAX static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length, - unsigned flags, struct iomap *iomap) + unsigned flags, struct iomap *iomap, struct iomap *srcmap) { unsigned int blkbits = inode->i_blkbits; unsigned long first_block = offset >> blkbits; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 516faa280ced..abaaf7d96ca4 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3407,7 +3407,7 @@ static bool ext4_inode_datasync_dirty(struct inode *inode) } static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length, - unsigned flags, struct iomap *iomap) + unsigned flags, struct iomap *iomap, struct iomap *srcmap) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); unsigned int blkbits = inode->i_blkbits; diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index f63df54a08c6..516103248272 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1149,7 +1149,8 @@ static inline bool gfs2_iomap_need_write_lock(unsigned flags) } static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length, - unsigned flags, struct iomap *iomap) + unsigned flags, struct iomap *iomap, + struct iomap *srcmap) { struct gfs2_inode *ip = GFS2_I(inode); struct metapath mp = { .mp_aheight = 1, }; diff --git a/fs/iomap/apply.c b/fs/iomap/apply.c index 54c02aecf3cd..484dd8eda861 100644 --- a/fs/iomap/apply.c +++ b/fs/iomap/apply.c @@ -23,8 +23,10 @@ loff_t iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags, const struct iomap_ops *ops, void *data, iomap_actor_t actor) { - struct iomap iomap = { 0 }; + struct iomap iomap = { .type = IOMAP_HOLE }; + struct iomap srcmap = { .type = IOMAP_HOLE }; loff_t written = 0, ret; + u64 end; /* * Need to map a range from start position for length bytes. This can @@ -38,7 +40,7 @@ iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags, * expose transient stale data. If the reserve fails, we can safely * back out at this point as there is nothing to undo. */ - ret = ops->iomap_begin(inode, pos, length, flags, &iomap); + ret = ops->iomap_begin(inode, pos, length, flags, &iomap, &srcmap); if (ret) return ret; if (WARN_ON(iomap.offset > pos)) @@ -50,15 +52,26 @@ iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags, * Cut down the length to the one actually provided by the filesystem, * as it might not be able to give us the whole size that we requested. */ - if (iomap.offset + iomap.length < pos + length) - length = iomap.offset + iomap.length - pos; + end = iomap.offset + iomap.length; + if (srcmap.type != IOMAP_HOLE) + end = min(end, srcmap.offset + srcmap.length); + if (pos + length > end) + length = end - pos; /* - * Now that we have guaranteed that the space allocation will succeed. + * Now that we have guaranteed that the space allocation will succeed, * we can do the copy-in page by page without having to worry about * failures exposing transient data. + * + * To support COW operations, we read in data for partially blocks from + * the srcmap if the file system filled it in. In that case we the + * length needs to be limited to the earlier of the ends of the iomaps. + * If the file system did not provide a srcmap we pass in the normal + * iomap into the actors so that they don't need to have special + * handling for the two cases. */ - written = actor(inode, pos, length, data, &iomap); + written = actor(inode, pos, length, data, &iomap, + srcmap.type != IOMAP_HOLE ? &srcmap : &iomap); /* * Now the data has been copied, commit the range we've copied. This diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index b61076823544..c62e807956b6 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -234,7 +234,7 @@ static inline bool iomap_block_needs_zeroing(struct inode *inode, static loff_t iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, - struct iomap *iomap) + struct iomap *iomap, struct iomap *srcmap) { struct iomap_readpage_ctx *ctx = data; struct page *page = ctx->cur_page; @@ -382,7 +382,7 @@ iomap_next_page(struct inode *inode, struct list_head *pages, loff_t pos, static loff_t iomap_readpages_actor(struct inode *inode, loff_t pos, loff_t length, - void *data, struct iomap *iomap) + void *data, struct iomap *iomap, struct iomap *srcmap) { struct iomap_readpage_ctx *ctx = data; loff_t done, ret; @@ -402,7 +402,7 @@ iomap_readpages_actor(struct inode *inode, loff_t pos, loff_t length, ctx->cur_page_in_bio = false; } ret = iomap_readpage_actor(inode, pos + done, length - done, - ctx, iomap); + ctx, iomap, srcmap); } return done; @@ -582,7 +582,7 @@ iomap_read_page_sync(loff_t block_start, struct page *page, unsigned poff, static int __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, int flags, - struct page *page, struct iomap *iomap) + struct page *page, struct iomap *srcmap) { struct iomap_page *iop = iomap_page_create(inode, page); loff_t block_size = i_blocksize(inode); @@ -605,7 +605,7 @@ __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, int flags, (to <= poff || to >= poff + plen)) continue; - if (iomap_block_needs_zeroing(inode, iomap, block_start)) { + if (iomap_block_needs_zeroing(inode, srcmap, block_start)) { if (WARN_ON_ONCE(flags & IOMAP_WRITE_F_UNSHARE)) return -EIO; zero_user_segments(page, poff, from, to, poff + plen); @@ -614,7 +614,7 @@ __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, int flags, } status = iomap_read_page_sync(block_start, page, poff, plen, - iomap); + srcmap); if (status) return status; } while ((block_start += plen) < block_end); @@ -624,13 +624,15 @@ __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, int flags, static int iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags, - struct page **pagep, struct iomap *iomap) + struct page **pagep, struct iomap *iomap, struct iomap *srcmap) { const struct iomap_page_ops *page_ops = iomap->page_ops; struct page *page; int status = 0; BUG_ON(pos + len > iomap->offset + iomap->length); + if (srcmap != iomap) + BUG_ON(pos + len > srcmap->offset + srcmap->length); if (fatal_signal_pending(current)) return -EINTR; @@ -648,13 +650,13 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags, goto out_no_page; } - if (iomap->type == IOMAP_INLINE) - iomap_read_inline_data(inode, page, iomap); + if (srcmap->type == IOMAP_INLINE) + iomap_read_inline_data(inode, page, srcmap); else if (iomap->flags & IOMAP_F_BUFFER_HEAD) - status = __block_write_begin_int(page, pos, len, NULL, iomap); + status = __block_write_begin_int(page, pos, len, NULL, srcmap); else status = __iomap_write_begin(inode, pos, len, flags, page, - iomap); + srcmap); if (unlikely(status)) goto out_unlock; @@ -740,16 +742,16 @@ iomap_write_end_inline(struct inode *inode, struct page *page, } static int -iomap_write_end(struct inode *inode, loff_t pos, unsigned len, - unsigned copied, struct page *page, struct iomap *iomap) +iomap_write_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied, + struct page *page, struct iomap *iomap, struct iomap *srcmap) { const struct iomap_page_ops *page_ops = iomap->page_ops; loff_t old_size = inode->i_size; int ret; - if (iomap->type == IOMAP_INLINE) { + if (srcmap->type == IOMAP_INLINE) { ret = iomap_write_end_inline(inode, page, iomap, pos, copied); - } else if (iomap->flags & IOMAP_F_BUFFER_HEAD) { + } else if (srcmap->flags & IOMAP_F_BUFFER_HEAD) { ret = block_write_end(NULL, inode->i_mapping, pos, len, copied, page, NULL); } else { @@ -780,7 +782,7 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len, static loff_t iomap_write_actor(struct inode *inode, loff_t pos, loff_t length, void *data, - struct iomap *iomap) + struct iomap *iomap, struct iomap *srcmap) { struct iov_iter *i = data; long status = 0; @@ -814,7 +816,8 @@ again: break; } - status = iomap_write_begin(inode, pos, bytes, 0, &page, iomap); + status = iomap_write_begin(inode, pos, bytes, 0, &page, iomap, + srcmap); if (unlikely(status)) break; @@ -825,8 +828,8 @@ again: flush_dcache_page(page); - status = iomap_write_end(inode, pos, bytes, copied, page, - iomap); + status = iomap_write_end(inode, pos, bytes, copied, page, iomap, + srcmap); if (unlikely(status < 0)) break; copied = status; @@ -879,7 +882,7 @@ EXPORT_SYMBOL_GPL(iomap_file_buffered_write); static loff_t iomap_unshare_actor(struct inode *inode, loff_t pos, loff_t length, void *data, - struct iomap *iomap) + struct iomap *iomap, struct iomap *srcmap) { long status = 0; ssize_t written = 0; @@ -888,7 +891,7 @@ iomap_unshare_actor(struct inode *inode, loff_t pos, loff_t length, void *data, if (!(iomap->flags & IOMAP_F_SHARED)) return length; /* don't bother with holes or unwritten extents */ - if (iomap->type == IOMAP_HOLE || iomap->type == IOMAP_UNWRITTEN) + if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) return length; do { @@ -897,11 +900,12 @@ iomap_unshare_actor(struct inode *inode, loff_t pos, loff_t length, void *data, struct page *page; status = iomap_write_begin(inode, pos, bytes, - IOMAP_WRITE_F_UNSHARE, &page, iomap); + IOMAP_WRITE_F_UNSHARE, &page, iomap, srcmap); if (unlikely(status)) return status; - status = iomap_write_end(inode, pos, bytes, bytes, page, iomap); + status = iomap_write_end(inode, pos, bytes, bytes, page, iomap, + srcmap); if (unlikely(status <= 0)) { if (WARN_ON_ONCE(status == 0)) return -EIO; @@ -940,19 +944,19 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, EXPORT_SYMBOL_GPL(iomap_file_unshare); static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset, - unsigned bytes, struct iomap *iomap) + unsigned bytes, struct iomap *iomap, struct iomap *srcmap) { struct page *page; int status; - status = iomap_write_begin(inode, pos, bytes, 0, &page, iomap); + status = iomap_write_begin(inode, pos, bytes, 0, &page, iomap, srcmap); if (status) return status; zero_user(page, offset, bytes); mark_page_accessed(page); - return iomap_write_end(inode, pos, bytes, bytes, page, iomap); + return iomap_write_end(inode, pos, bytes, bytes, page, iomap, srcmap); } static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes, @@ -964,14 +968,14 @@ static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes, static loff_t iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count, - void *data, struct iomap *iomap) + void *data, struct iomap *iomap, struct iomap *srcmap) { bool *did_zero = data; loff_t written = 0; int status; /* already zeroed? we're done. */ - if (iomap->type == IOMAP_HOLE || iomap->type == IOMAP_UNWRITTEN) + if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) return count; do { @@ -983,7 +987,8 @@ iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count, if (IS_DAX(inode)) status = iomap_dax_zero(pos, offset, bytes, iomap); else - status = iomap_zero(inode, pos, offset, bytes, iomap); + status = iomap_zero(inode, pos, offset, bytes, iomap, + srcmap); if (status < 0) return status; @@ -1033,7 +1038,7 @@ EXPORT_SYMBOL_GPL(iomap_truncate_page); static loff_t iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length, - void *data, struct iomap *iomap) + void *data, struct iomap *iomap, struct iomap *srcmap) { struct page *page = data; int ret; diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index da124cee1783..49bf9780e3ed 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -358,7 +358,7 @@ iomap_dio_inline_actor(struct inode *inode, loff_t pos, loff_t length, static loff_t iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length, - void *data, struct iomap *iomap) + void *data, struct iomap *iomap, struct iomap *srcmap) { struct iomap_dio *dio = data; diff --git a/fs/iomap/fiemap.c b/fs/iomap/fiemap.c index f26fdd36e383..690ef2d7c6c8 100644 --- a/fs/iomap/fiemap.c +++ b/fs/iomap/fiemap.c @@ -44,7 +44,7 @@ static int iomap_to_fiemap(struct fiemap_extent_info *fi, static loff_t iomap_fiemap_actor(struct inode *inode, loff_t pos, loff_t length, void *data, - struct iomap *iomap) + struct iomap *iomap, struct iomap *srcmap) { struct fiemap_ctx *ctx = data; loff_t ret = length; @@ -111,7 +111,7 @@ EXPORT_SYMBOL_GPL(iomap_fiemap); static loff_t iomap_bmap_actor(struct inode *inode, loff_t pos, loff_t length, - void *data, struct iomap *iomap) + void *data, struct iomap *iomap, struct iomap *srcmap) { sector_t *bno = data, addr; diff --git a/fs/iomap/seek.c b/fs/iomap/seek.c index c04bad4b2b43..89f61d93c0bc 100644 --- a/fs/iomap/seek.c +++ b/fs/iomap/seek.c @@ -119,7 +119,7 @@ out: static loff_t iomap_seek_hole_actor(struct inode *inode, loff_t offset, loff_t length, - void *data, struct iomap *iomap) + void *data, struct iomap *iomap, struct iomap *srcmap) { switch (iomap->type) { case IOMAP_UNWRITTEN: @@ -165,7 +165,7 @@ EXPORT_SYMBOL_GPL(iomap_seek_hole); static loff_t iomap_seek_data_actor(struct inode *inode, loff_t offset, loff_t length, - void *data, struct iomap *iomap) + void *data, struct iomap *iomap, struct iomap *srcmap) { switch (iomap->type) { case IOMAP_HOLE: diff --git a/fs/iomap/swapfile.c b/fs/iomap/swapfile.c index 152a230f668d..a648dbf6991e 100644 --- a/fs/iomap/swapfile.c +++ b/fs/iomap/swapfile.c @@ -76,7 +76,8 @@ static int iomap_swapfile_add_extent(struct iomap_swapfile_info *isi) * distinction between written and unwritten extents. */ static loff_t iomap_swapfile_activate_actor(struct inode *inode, loff_t pos, - loff_t count, void *data, struct iomap *iomap) + loff_t count, void *data, struct iomap *iomap, + struct iomap *srcmap) { struct iomap_swapfile_info *isi = data; int error; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index f7b8b1329ddd..95719e161286 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -928,7 +928,8 @@ xfs_file_iomap_begin( loff_t offset, loff_t length, unsigned flags, - struct iomap *iomap) + struct iomap *iomap, + struct iomap *srcmap) { struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; @@ -1161,7 +1162,8 @@ xfs_seek_iomap_begin( loff_t offset, loff_t length, unsigned flags, - struct iomap *iomap) + struct iomap *iomap, + struct iomap *srcmap) { struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; @@ -1247,7 +1249,8 @@ xfs_xattr_iomap_begin( loff_t offset, loff_t length, unsigned flags, - struct iomap *iomap) + struct iomap *iomap, + struct iomap *srcmap) { struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 53e6e2275d3d..8b09463dae0d 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -129,7 +129,8 @@ struct iomap_ops { * The actual length is returned in iomap->length. */ int (*iomap_begin)(struct inode *inode, loff_t pos, loff_t length, - unsigned flags, struct iomap *iomap); + unsigned flags, struct iomap *iomap, + struct iomap *srcmap); /* * Commit and/or unreserve space previous allocated using iomap_begin. @@ -145,7 +146,7 @@ struct iomap_ops { * Main iomap iterator function. */ typedef loff_t (*iomap_actor_t)(struct inode *inode, loff_t pos, loff_t len, - void *data, struct iomap *iomap); + void *data, struct iomap *iomap, struct iomap *srcmap); loff_t iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags, const struct iomap_ops *ops, void *data, -- cgit v1.2.3-71-gd317 From b48c1a45a190898103cec28771efc399fd65a05a Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 21 Oct 2019 16:28:16 +0100 Subject: KVM: arm64: Implement PV_TIME_FEATURES call This provides a mechanism for querying which paravirtualized time features are available in this hypervisor. Also add the header file which defines the ABI for the paravirtualized time features we're about to add. Signed-off-by: Steven Price Signed-off-by: Marc Zyngier --- arch/arm/include/asm/kvm_host.h | 6 ++++++ arch/arm64/include/asm/kvm_host.h | 2 ++ arch/arm64/include/asm/pvclock-abi.h | 17 +++++++++++++++++ arch/arm64/kvm/Makefile | 1 + include/linux/arm-smccc.h | 14 ++++++++++++++ virt/kvm/arm/hypercalls.c | 8 +++++++- virt/kvm/arm/pvtime.c | 20 ++++++++++++++++++++ 7 files changed, 67 insertions(+), 1 deletion(-) create mode 100644 arch/arm64/include/asm/pvclock-abi.h create mode 100644 virt/kvm/arm/pvtime.c (limited to 'include/linux') diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 8a37c8e89777..5a0c3569ebde 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -7,6 +7,7 @@ #ifndef __ARM_KVM_HOST_H__ #define __ARM_KVM_HOST_H__ +#include #include #include #include @@ -323,6 +324,11 @@ static inline int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext) int kvm_perf_init(void); int kvm_perf_teardown(void); +static inline long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu) +{ + return SMCCC_RET_NOT_SUPPORTED; +} + void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot); struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr); diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index f656169db8c3..93b46d9526d0 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -478,6 +478,8 @@ void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run, int kvm_perf_init(void); int kvm_perf_teardown(void); +long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu); + void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 syndrome); struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr); diff --git a/arch/arm64/include/asm/pvclock-abi.h b/arch/arm64/include/asm/pvclock-abi.h new file mode 100644 index 000000000000..c4f1c0a0789c --- /dev/null +++ b/arch/arm64/include/asm/pvclock-abi.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019 Arm Ltd. */ + +#ifndef __ASM_PVCLOCK_ABI_H +#define __ASM_PVCLOCK_ABI_H + +/* The below structure is defined in ARM DEN0057A */ + +struct pvclock_vcpu_stolen_time { + __le32 revision; + __le32 attributes; + __le64 stolen_time; + /* Structure must be 64 byte aligned, pad to that size */ + u8 padding[48]; +} __packed; + +#endif diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 73dce4d47d47..5ffbdc39e780 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -14,6 +14,7 @@ kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/e kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arm.o $(KVM)/arm/mmu.o $(KVM)/arm/mmio.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/psci.o $(KVM)/arm/perf.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hypercalls.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/pvtime.o kvm-$(CONFIG_KVM_ARM_HOST) += inject_fault.o regmap.o va_layout.o kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index df01a8579034..92e0046ce7a7 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -45,6 +45,7 @@ #define ARM_SMCCC_OWNER_SIP 2 #define ARM_SMCCC_OWNER_OEM 3 #define ARM_SMCCC_OWNER_STANDARD 4 +#define ARM_SMCCC_OWNER_STANDARD_HYP 5 #define ARM_SMCCC_OWNER_TRUSTED_APP 48 #define ARM_SMCCC_OWNER_TRUSTED_APP_END 49 #define ARM_SMCCC_OWNER_TRUSTED_OS 50 @@ -318,5 +319,18 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, #define SMCCC_RET_NOT_SUPPORTED -1 #define SMCCC_RET_NOT_REQUIRED -2 +/* Paravirtualised time calls (defined by ARM DEN0057A) */ +#define ARM_SMCCC_HV_PV_TIME_FEATURES \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_STANDARD_HYP, \ + 0x20) + +#define ARM_SMCCC_HV_PV_TIME_ST \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_STANDARD_HYP, \ + 0x21) + #endif /*__ASSEMBLY__*/ #endif /*__LINUX_ARM_SMCCC_H*/ diff --git a/virt/kvm/arm/hypercalls.c b/virt/kvm/arm/hypercalls.c index f875241bd030..97ea8b133e77 100644 --- a/virt/kvm/arm/hypercalls.c +++ b/virt/kvm/arm/hypercalls.c @@ -12,7 +12,7 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) { u32 func_id = smccc_get_function(vcpu); - u32 val = SMCCC_RET_NOT_SUPPORTED; + long val = SMCCC_RET_NOT_SUPPORTED; u32 feature; switch (func_id) { @@ -48,8 +48,14 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) break; } break; + case ARM_SMCCC_HV_PV_TIME_FEATURES: + val = SMCCC_RET_SUCCESS; + break; } break; + case ARM_SMCCC_HV_PV_TIME_FEATURES: + val = kvm_hypercall_pv_features(vcpu); + break; default: return kvm_psci_call(vcpu); } diff --git a/virt/kvm/arm/pvtime.c b/virt/kvm/arm/pvtime.c new file mode 100644 index 000000000000..9fc69fc2d683 --- /dev/null +++ b/virt/kvm/arm/pvtime.c @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2019 Arm Ltd. + +#include + +#include + +long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu) +{ + u32 feature = smccc_get_arg1(vcpu); + long val = SMCCC_RET_NOT_SUPPORTED; + + switch (feature) { + case ARM_SMCCC_HV_PV_TIME_FEATURES: + val = SMCCC_RET_SUCCESS; + break; + } + + return val; +} -- cgit v1.2.3-71-gd317 From cac0f1b7285eaaf9a186c618c3a7304d82ed5493 Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 21 Oct 2019 16:28:17 +0100 Subject: KVM: Implement kvm_put_guest() kvm_put_guest() is analogous to put_user() - it writes a single value to the guest physical address. The implementation is built upon put_user() and so it has the same single copy atomic properties. Signed-off-by: Steven Price Signed-off-by: Marc Zyngier --- include/linux/kvm_host.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 719fc3e15ea4..9907e45f8875 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -746,6 +746,28 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, unsigned long len); int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, gpa_t gpa, unsigned long len); + +#define __kvm_put_guest(kvm, gfn, offset, value, type) \ +({ \ + unsigned long __addr = gfn_to_hva(kvm, gfn); \ + type __user *__uaddr = (type __user *)(__addr + offset); \ + int __ret = -EFAULT; \ + \ + if (!kvm_is_error_hva(__addr)) \ + __ret = put_user(value, __uaddr); \ + if (!__ret) \ + mark_page_dirty(kvm, gfn); \ + __ret; \ +}) + +#define kvm_put_guest(kvm, gpa, value, type) \ +({ \ + gpa_t __gpa = gpa; \ + struct kvm *__kvm = kvm; \ + __kvm_put_guest(__kvm, __gpa >> PAGE_SHIFT, \ + offset_in_page(__gpa), (value), type); \ +}) + int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len); int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len); struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); -- cgit v1.2.3-71-gd317 From 8564d6372a7d8a6d440441b8ed8020f97f744450 Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 21 Oct 2019 16:28:18 +0100 Subject: KVM: arm64: Support stolen time reporting via shared structure Implement the service call for configuring a shared structure between a VCPU and the hypervisor in which the hypervisor can write the time stolen from the VCPU's execution time by other tasks on the host. User space allocates memory which is placed at an IPA also chosen by user space. The hypervisor then updates the shared structure using kvm_put_guest() to ensure single copy atomicity of the 64-bit value reporting the stolen time in nanoseconds. Whenever stolen time is enabled by the guest, the stolen time counter is reset. The stolen time itself is retrieved from the sched_info structure maintained by the Linux scheduler code. We enable SCHEDSTATS when selecting KVM Kconfig to ensure this value is meaningful. Signed-off-by: Steven Price Signed-off-by: Marc Zyngier --- arch/arm/include/asm/kvm_host.h | 19 ++++++++++++++ arch/arm64/include/asm/kvm_host.h | 20 +++++++++++++++ arch/arm64/kvm/Kconfig | 1 + include/linux/kvm_types.h | 2 ++ virt/kvm/arm/arm.c | 11 +++++++++ virt/kvm/arm/hypercalls.c | 6 +++++ virt/kvm/arm/pvtime.c | 52 +++++++++++++++++++++++++++++++++++++++ 7 files changed, 111 insertions(+) (limited to 'include/linux') diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 5a0c3569ebde..5a077f85813f 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -39,6 +39,7 @@ KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_IRQ_PENDING KVM_ARCH_REQ(1) #define KVM_REQ_VCPU_RESET KVM_ARCH_REQ(2) +#define KVM_REQ_RECORD_STEAL KVM_ARCH_REQ(3) DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); @@ -329,6 +330,24 @@ static inline long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu) return SMCCC_RET_NOT_SUPPORTED; } +static inline gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu) +{ + return GPA_INVALID; +} + +static inline void kvm_update_stolen_time(struct kvm_vcpu *vcpu) +{ +} + +static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch) +{ +} + +static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch) +{ + return false; +} + void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot); struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr); diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 93b46d9526d0..75ef37f79633 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -44,6 +44,7 @@ KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_IRQ_PENDING KVM_ARCH_REQ(1) #define KVM_REQ_VCPU_RESET KVM_ARCH_REQ(2) +#define KVM_REQ_RECORD_STEAL KVM_ARCH_REQ(3) DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); @@ -338,6 +339,13 @@ struct kvm_vcpu_arch { /* True when deferrable sysregs are loaded on the physical CPU, * see kvm_vcpu_load_sysregs and kvm_vcpu_put_sysregs. */ bool sysregs_loaded_on_cpu; + + /* Guest PV state */ + struct { + u64 steal; + u64 last_steal; + gpa_t base; + } steal; }; /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */ @@ -479,6 +487,18 @@ int kvm_perf_init(void); int kvm_perf_teardown(void); long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu); +gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu); +void kvm_update_stolen_time(struct kvm_vcpu *vcpu); + +static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch) +{ + vcpu_arch->steal.base = GPA_INVALID; +} + +static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch) +{ + return (vcpu_arch->steal.base != GPA_INVALID); +} void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 syndrome); diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index a67121d419a2..d8b88e40d223 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -39,6 +39,7 @@ config KVM select IRQ_BYPASS_MANAGER select HAVE_KVM_IRQ_BYPASS select HAVE_KVM_VCPU_RUN_PID_CHANGE + select SCHEDSTATS ---help--- Support hosting virtualized guest machines. We don't support KVM with 16K page tables yet, due to the multiple diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index bde5374ae021..1c88e69db3d9 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -35,6 +35,8 @@ typedef unsigned long gva_t; typedef u64 gpa_t; typedef u64 gfn_t; +#define GPA_INVALID (~(gpa_t)0) + typedef unsigned long hva_t; typedef u64 hpa_t; typedef u64 hfn_t; diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 86c6aa1cb58e..2aba375dfd13 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -40,6 +40,10 @@ #include #include +#include +#include +#include + #ifdef REQUIRES_VIRT __asm__(".arch_extension virt"); #endif @@ -351,6 +355,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) kvm_arm_reset_debug_ptr(vcpu); + kvm_arm_pvtime_vcpu_init(&vcpu->arch); + return kvm_vgic_vcpu_init(vcpu); } @@ -380,6 +386,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_vcpu_load_sysregs(vcpu); kvm_arch_vcpu_load_fp(vcpu); kvm_vcpu_pmu_restore_guest(vcpu); + if (kvm_arm_is_pvtime_enabled(&vcpu->arch)) + kvm_make_request(KVM_REQ_RECORD_STEAL, vcpu); if (single_task_running()) vcpu_clear_wfe_traps(vcpu); @@ -645,6 +653,9 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu) * that a VCPU sees new virtual interrupts. */ kvm_check_request(KVM_REQ_IRQ_PENDING, vcpu); + + if (kvm_check_request(KVM_REQ_RECORD_STEAL, vcpu)) + kvm_update_stolen_time(vcpu); } } diff --git a/virt/kvm/arm/hypercalls.c b/virt/kvm/arm/hypercalls.c index 97ea8b133e77..550dfa3e53cd 100644 --- a/virt/kvm/arm/hypercalls.c +++ b/virt/kvm/arm/hypercalls.c @@ -14,6 +14,7 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) u32 func_id = smccc_get_function(vcpu); long val = SMCCC_RET_NOT_SUPPORTED; u32 feature; + gpa_t gpa; switch (func_id) { case ARM_SMCCC_VERSION_FUNC_ID: @@ -56,6 +57,11 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) case ARM_SMCCC_HV_PV_TIME_FEATURES: val = kvm_hypercall_pv_features(vcpu); break; + case ARM_SMCCC_HV_PV_TIME_ST: + gpa = kvm_init_stolen_time(vcpu); + if (gpa != GPA_INVALID) + val = gpa; + break; default: return kvm_psci_call(vcpu); } diff --git a/virt/kvm/arm/pvtime.c b/virt/kvm/arm/pvtime.c index 9fc69fc2d683..b90b3a7bea85 100644 --- a/virt/kvm/arm/pvtime.c +++ b/virt/kvm/arm/pvtime.c @@ -3,8 +3,35 @@ #include +#include + #include +void kvm_update_stolen_time(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + u64 steal; + __le64 steal_le; + u64 offset; + int idx; + u64 base = vcpu->arch.steal.base; + + if (base == GPA_INVALID) + return; + + /* Let's do the local bookkeeping */ + steal = vcpu->arch.steal.steal; + steal += current->sched_info.run_delay - vcpu->arch.steal.last_steal; + vcpu->arch.steal.last_steal = current->sched_info.run_delay; + vcpu->arch.steal.steal = steal; + + steal_le = cpu_to_le64(steal); + idx = srcu_read_lock(&kvm->srcu); + offset = offsetof(struct pvclock_vcpu_stolen_time, stolen_time); + kvm_put_guest(kvm, base + offset, steal_le, u64); + srcu_read_unlock(&kvm->srcu, idx); +} + long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu) { u32 feature = smccc_get_arg1(vcpu); @@ -12,9 +39,34 @@ long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu) switch (feature) { case ARM_SMCCC_HV_PV_TIME_FEATURES: + case ARM_SMCCC_HV_PV_TIME_ST: val = SMCCC_RET_SUCCESS; break; } return val; } + +gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu) +{ + struct pvclock_vcpu_stolen_time init_values = {}; + struct kvm *kvm = vcpu->kvm; + u64 base = vcpu->arch.steal.base; + int idx; + + if (base == GPA_INVALID) + return base; + + /* + * Start counting stolen time from the time the guest requests + * the feature enabled. + */ + vcpu->arch.steal.steal = 0; + vcpu->arch.steal.last_steal = current->sched_info.run_delay; + + idx = srcu_read_lock(&kvm->srcu); + kvm_write_guest(kvm, base, &init_values, sizeof(init_values)); + srcu_read_unlock(&kvm->srcu, idx); + + return base; +} -- cgit v1.2.3-71-gd317 From 8538cb22bbce5a988671b68baf0b0f9e86ca1e87 Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 21 Oct 2019 16:28:19 +0100 Subject: KVM: Allow kvm_device_ops to be const Currently a kvm_device_ops structure cannot be const without triggering compiler warnings. However the structure doesn't need to be written to and, by marking it const, it can be read-only in memory. Add some more const keywords to allow this. Reviewed-by: Andrew Jones Signed-off-by: Steven Price Signed-off-by: Marc Zyngier --- include/linux/kvm_host.h | 4 ++-- virt/kvm/kvm_main.c | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9907e45f8875..7a26d5513471 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1262,7 +1262,7 @@ extern unsigned int halt_poll_ns_grow_start; extern unsigned int halt_poll_ns_shrink; struct kvm_device { - struct kvm_device_ops *ops; + const struct kvm_device_ops *ops; struct kvm *kvm; void *private; struct list_head vm_node; @@ -1315,7 +1315,7 @@ struct kvm_device_ops { void kvm_device_get(struct kvm_device *dev); void kvm_device_put(struct kvm_device *dev); struct kvm_device *kvm_device_from_filp(struct file *filp); -int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type); +int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type); void kvm_unregister_device_ops(u32 type); extern struct kvm_device_ops kvm_mpic_ops; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index fd68fbe0a75d..66a977472a1c 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3046,14 +3046,14 @@ struct kvm_device *kvm_device_from_filp(struct file *filp) return filp->private_data; } -static struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = { +static const struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = { #ifdef CONFIG_KVM_MPIC [KVM_DEV_TYPE_FSL_MPIC_20] = &kvm_mpic_ops, [KVM_DEV_TYPE_FSL_MPIC_42] = &kvm_mpic_ops, #endif }; -int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type) +int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type) { if (type >= ARRAY_SIZE(kvm_device_ops_table)) return -ENOSPC; @@ -3074,7 +3074,7 @@ void kvm_unregister_device_ops(u32 type) static int kvm_ioctl_create_device(struct kvm *kvm, struct kvm_create_device *cd) { - struct kvm_device_ops *ops = NULL; + const struct kvm_device_ops *ops = NULL; struct kvm_device *dev; bool test = cd->flags & KVM_CREATE_DEVICE_TEST; int type; -- cgit v1.2.3-71-gd317 From 541625ac47ce9d0835efaee0fcbaa251b0000a37 Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 21 Oct 2019 16:28:21 +0100 Subject: arm/arm64: Provide a wrapper for SMCCC 1.1 calls SMCCC 1.1 calls may use either HVC or SMC depending on the PSCI conduit. Rather than coding this in every call site, provide a macro which uses the correct instruction. The macro also handles the case where no conduit is configured/available returning a not supported error in res, along with returning the conduit used for the call. This allow us to remove some duplicated code and will be useful later when adding paravirtualized time hypervisor calls. Signed-off-by: Steven Price Acked-by: Will Deacon Signed-off-by: Marc Zyngier --- include/linux/arm-smccc.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) (limited to 'include/linux') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 92e0046ce7a7..59494df0f55b 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -319,6 +319,51 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, #define SMCCC_RET_NOT_SUPPORTED -1 #define SMCCC_RET_NOT_REQUIRED -2 +/* + * Like arm_smccc_1_1* but always returns SMCCC_RET_NOT_SUPPORTED. + * Used when the SMCCC conduit is not defined. The empty asm statement + * avoids compiler warnings about unused variables. + */ +#define __fail_smccc_1_1(...) \ + do { \ + __declare_args(__count_args(__VA_ARGS__), __VA_ARGS__); \ + asm ("" __constraints(__count_args(__VA_ARGS__))); \ + if (___res) \ + ___res->a0 = SMCCC_RET_NOT_SUPPORTED; \ + } while (0) + +/* + * arm_smccc_1_1_invoke() - make an SMCCC v1.1 compliant call + * + * This is a variadic macro taking one to eight source arguments, and + * an optional return structure. + * + * @a0-a7: arguments passed in registers 0 to 7 + * @res: result values from registers 0 to 3 + * + * This macro will make either an HVC call or an SMC call depending on the + * current SMCCC conduit. If no valid conduit is available then -1 + * (SMCCC_RET_NOT_SUPPORTED) is returned in @res.a0 (if supplied). + * + * The return value also provides the conduit that was used. + */ +#define arm_smccc_1_1_invoke(...) ({ \ + int method = arm_smccc_1_1_get_conduit(); \ + switch (method) { \ + case SMCCC_CONDUIT_HVC: \ + arm_smccc_1_1_hvc(__VA_ARGS__); \ + break; \ + case SMCCC_CONDUIT_SMC: \ + arm_smccc_1_1_smc(__VA_ARGS__); \ + break; \ + default: \ + __fail_smccc_1_1(__VA_ARGS__); \ + method = SMCCC_CONDUIT_NONE; \ + break; \ + } \ + method; \ + }) + /* Paravirtualised time calls (defined by ARM DEN0057A) */ #define ARM_SMCCC_HV_PV_TIME_FEATURES \ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ -- cgit v1.2.3-71-gd317 From e0685fa228fdaf386f82ac0d64b2d6f3e0ddd588 Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 21 Oct 2019 16:28:23 +0100 Subject: arm64: Retrieve stolen time as paravirtualized guest Enable paravirtualization features when running under a hypervisor supporting the PV_TIME_ST hypercall. For each (v)CPU, we ask the hypervisor for the location of a shared page which the hypervisor will use to report stolen time to us. We set pv_time_ops to the stolen time function which simply reads the stolen value from the shared page for a VCPU. We guarantee single-copy atomicity using READ_ONCE which means we can also read the stolen time for another VCPU than the currently running one while it is potentially being updated by the hypervisor. Signed-off-by: Steven Price Signed-off-by: Marc Zyngier --- Documentation/admin-guide/kernel-parameters.txt | 6 +- arch/arm64/include/asm/paravirt.h | 9 +- arch/arm64/kernel/paravirt.c | 140 ++++++++++++++++++++++++ arch/arm64/kernel/time.c | 3 + include/linux/cpuhotplug.h | 1 + 5 files changed, 155 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index a84a83f8881e..19f465530e86 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3083,9 +3083,9 @@ [X86,PV_OPS] Disable paravirtualized VMware scheduler clock and use the default one. - no-steal-acc [X86,KVM] Disable paravirtualized steal time accounting. - steal time is computed, but won't influence scheduler - behaviour + no-steal-acc [X86,KVM,ARM64] Disable paravirtualized steal time + accounting. steal time is computed, but won't + influence scheduler behaviour nolapic [X86-32,APIC] Do not enable or use the local APIC. diff --git a/arch/arm64/include/asm/paravirt.h b/arch/arm64/include/asm/paravirt.h index 799d9dd6f7cc..cf3a0fd7c1a7 100644 --- a/arch/arm64/include/asm/paravirt.h +++ b/arch/arm64/include/asm/paravirt.h @@ -21,6 +21,13 @@ static inline u64 paravirt_steal_clock(int cpu) { return pv_ops.time.steal_clock(cpu); } -#endif + +int __init pv_time_init(void); + +#else + +#define pv_time_init() do {} while (0) + +#endif // CONFIG_PARAVIRT #endif diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c index 4cfed91fe256..1ef702b0be2d 100644 --- a/arch/arm64/kernel/paravirt.c +++ b/arch/arm64/kernel/paravirt.c @@ -6,13 +6,153 @@ * Author: Stefano Stabellini */ +#define pr_fmt(fmt) "arm-pv: " fmt + +#include +#include #include +#include #include +#include +#include +#include +#include #include + #include +#include +#include struct static_key paravirt_steal_enabled; struct static_key paravirt_steal_rq_enabled; struct paravirt_patch_template pv_ops; EXPORT_SYMBOL_GPL(pv_ops); + +struct pv_time_stolen_time_region { + struct pvclock_vcpu_stolen_time *kaddr; +}; + +static DEFINE_PER_CPU(struct pv_time_stolen_time_region, stolen_time_region); + +static bool steal_acc = true; +static int __init parse_no_stealacc(char *arg) +{ + steal_acc = false; + return 0; +} + +early_param("no-steal-acc", parse_no_stealacc); + +/* return stolen time in ns by asking the hypervisor */ +static u64 pv_steal_clock(int cpu) +{ + struct pv_time_stolen_time_region *reg; + + reg = per_cpu_ptr(&stolen_time_region, cpu); + if (!reg->kaddr) { + pr_warn_once("stolen time enabled but not configured for cpu %d\n", + cpu); + return 0; + } + + return le64_to_cpu(READ_ONCE(reg->kaddr->stolen_time)); +} + +static int stolen_time_dying_cpu(unsigned int cpu) +{ + struct pv_time_stolen_time_region *reg; + + reg = this_cpu_ptr(&stolen_time_region); + if (!reg->kaddr) + return 0; + + memunmap(reg->kaddr); + memset(reg, 0, sizeof(*reg)); + + return 0; +} + +static int init_stolen_time_cpu(unsigned int cpu) +{ + struct pv_time_stolen_time_region *reg; + struct arm_smccc_res res; + + reg = this_cpu_ptr(&stolen_time_region); + + arm_smccc_1_1_invoke(ARM_SMCCC_HV_PV_TIME_ST, &res); + + if (res.a0 == SMCCC_RET_NOT_SUPPORTED) + return -EINVAL; + + reg->kaddr = memremap(res.a0, + sizeof(struct pvclock_vcpu_stolen_time), + MEMREMAP_WB); + + if (!reg->kaddr) { + pr_warn("Failed to map stolen time data structure\n"); + return -ENOMEM; + } + + if (le32_to_cpu(reg->kaddr->revision) != 0 || + le32_to_cpu(reg->kaddr->attributes) != 0) { + pr_warn_once("Unexpected revision or attributes in stolen time data\n"); + return -ENXIO; + } + + return 0; +} + +static int pv_time_init_stolen_time(void) +{ + int ret; + + ret = cpuhp_setup_state(CPUHP_AP_ARM_KVMPV_STARTING, + "hypervisor/arm/pvtime:starting", + init_stolen_time_cpu, stolen_time_dying_cpu); + if (ret < 0) + return ret; + return 0; +} + +static bool has_pv_steal_clock(void) +{ + struct arm_smccc_res res; + + /* To detect the presence of PV time support we require SMCCC 1.1+ */ + if (psci_ops.smccc_version < SMCCC_VERSION_1_1) + return false; + + arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, + ARM_SMCCC_HV_PV_TIME_FEATURES, &res); + + if (res.a0 != SMCCC_RET_SUCCESS) + return false; + + arm_smccc_1_1_invoke(ARM_SMCCC_HV_PV_TIME_FEATURES, + ARM_SMCCC_HV_PV_TIME_ST, &res); + + return (res.a0 == SMCCC_RET_SUCCESS); +} + +int __init pv_time_init(void) +{ + int ret; + + if (!has_pv_steal_clock()) + return 0; + + ret = pv_time_init_stolen_time(); + if (ret) + return ret; + + pv_ops.time.steal_clock = pv_steal_clock; + + static_key_slow_inc(¶virt_steal_enabled); + if (steal_acc) + static_key_slow_inc(¶virt_steal_rq_enabled); + + pr_info("using stolen time PV\n"); + + return 0; +} diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c index 0b2946414dc9..73f06d4b3aae 100644 --- a/arch/arm64/kernel/time.c +++ b/arch/arm64/kernel/time.c @@ -30,6 +30,7 @@ #include #include +#include unsigned long profile_pc(struct pt_regs *regs) { @@ -65,4 +66,6 @@ void __init time_init(void) /* Calibrate the delay loop directly */ lpj_fine = arch_timer_rate / HZ; + + pv_time_init(); } diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 068793a619ca..89d75edb5750 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -136,6 +136,7 @@ enum cpuhp_state { /* Must be the last timer callback */ CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_ARM_XEN_STARTING, + CPUHP_AP_ARM_KVMPV_STARTING, CPUHP_AP_ARM_CORESIGHT_STARTING, CPUHP_AP_ARM64_ISNDEP_STARTING, CPUHP_AP_SMPCFD_DYING, -- cgit v1.2.3-71-gd317 From 1565bdad59e97f31cfc7b065bc0fc77e9549e62d Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 9 Oct 2019 16:34:17 -0700 Subject: fscrypt: remove struct fscrypt_ctx Now that ext4 and f2fs implement their own post-read workflow that supports both fscrypt and fsverity, the fscrypt-only workflow based around struct fscrypt_ctx is no longer used. So remove the unused code. This is based on a patch from Chandan Rajendra's "Consolidate FS read I/O callbacks code" patchset, but rebased onto the latest kernel, folded __fscrypt_decrypt_bio() into fscrypt_decrypt_bio(), cleaned up fscrypt_initialize(), and updated the commit message. Originally-from: Chandan Rajendra Signed-off-by: Eric Biggers --- fs/crypto/bio.c | 29 +----------- fs/crypto/crypto.c | 110 ++++---------------------------------------- fs/crypto/fscrypt_private.h | 2 - include/linux/fscrypt.h | 32 ------------- 4 files changed, 10 insertions(+), 163 deletions(-) (limited to 'include/linux') diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c index 82da2510721f..1f4b8a277060 100644 --- a/fs/crypto/bio.c +++ b/fs/crypto/bio.c @@ -26,7 +26,7 @@ #include #include "fscrypt_private.h" -static void __fscrypt_decrypt_bio(struct bio *bio, bool done) +void fscrypt_decrypt_bio(struct bio *bio) { struct bio_vec *bv; struct bvec_iter_all iter_all; @@ -37,37 +37,10 @@ static void __fscrypt_decrypt_bio(struct bio *bio, bool done) bv->bv_offset); if (ret) SetPageError(page); - else if (done) - SetPageUptodate(page); - if (done) - unlock_page(page); } } - -void fscrypt_decrypt_bio(struct bio *bio) -{ - __fscrypt_decrypt_bio(bio, false); -} EXPORT_SYMBOL(fscrypt_decrypt_bio); -static void completion_pages(struct work_struct *work) -{ - struct fscrypt_ctx *ctx = container_of(work, struct fscrypt_ctx, work); - struct bio *bio = ctx->bio; - - __fscrypt_decrypt_bio(bio, true); - fscrypt_release_ctx(ctx); - bio_put(bio); -} - -void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, struct bio *bio) -{ - INIT_WORK(&ctx->work, completion_pages); - ctx->bio = bio; - fscrypt_enqueue_decrypt_work(&ctx->work); -} -EXPORT_SYMBOL(fscrypt_enqueue_decrypt_bio); - int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, sector_t pblk, unsigned int len) { diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c index 6bc3e4f1e657..ced8ad9f2d01 100644 --- a/fs/crypto/crypto.c +++ b/fs/crypto/crypto.c @@ -31,24 +31,16 @@ #include "fscrypt_private.h" static unsigned int num_prealloc_crypto_pages = 32; -static unsigned int num_prealloc_crypto_ctxs = 128; module_param(num_prealloc_crypto_pages, uint, 0444); MODULE_PARM_DESC(num_prealloc_crypto_pages, "Number of crypto pages to preallocate"); -module_param(num_prealloc_crypto_ctxs, uint, 0444); -MODULE_PARM_DESC(num_prealloc_crypto_ctxs, - "Number of crypto contexts to preallocate"); static mempool_t *fscrypt_bounce_page_pool = NULL; -static LIST_HEAD(fscrypt_free_ctxs); -static DEFINE_SPINLOCK(fscrypt_ctx_lock); - static struct workqueue_struct *fscrypt_read_workqueue; static DEFINE_MUTEX(fscrypt_init_mutex); -static struct kmem_cache *fscrypt_ctx_cachep; struct kmem_cache *fscrypt_info_cachep; void fscrypt_enqueue_decrypt_work(struct work_struct *work) @@ -57,62 +49,6 @@ void fscrypt_enqueue_decrypt_work(struct work_struct *work) } EXPORT_SYMBOL(fscrypt_enqueue_decrypt_work); -/** - * fscrypt_release_ctx() - Release a decryption context - * @ctx: The decryption context to release. - * - * If the decryption context was allocated from the pre-allocated pool, return - * it to that pool. Else, free it. - */ -void fscrypt_release_ctx(struct fscrypt_ctx *ctx) -{ - unsigned long flags; - - if (ctx->flags & FS_CTX_REQUIRES_FREE_ENCRYPT_FL) { - kmem_cache_free(fscrypt_ctx_cachep, ctx); - } else { - spin_lock_irqsave(&fscrypt_ctx_lock, flags); - list_add(&ctx->free_list, &fscrypt_free_ctxs); - spin_unlock_irqrestore(&fscrypt_ctx_lock, flags); - } -} -EXPORT_SYMBOL(fscrypt_release_ctx); - -/** - * fscrypt_get_ctx() - Get a decryption context - * @gfp_flags: The gfp flag for memory allocation - * - * Allocate and initialize a decryption context. - * - * Return: A new decryption context on success; an ERR_PTR() otherwise. - */ -struct fscrypt_ctx *fscrypt_get_ctx(gfp_t gfp_flags) -{ - struct fscrypt_ctx *ctx; - unsigned long flags; - - /* - * First try getting a ctx from the free list so that we don't have to - * call into the slab allocator. - */ - spin_lock_irqsave(&fscrypt_ctx_lock, flags); - ctx = list_first_entry_or_null(&fscrypt_free_ctxs, - struct fscrypt_ctx, free_list); - if (ctx) - list_del(&ctx->free_list); - spin_unlock_irqrestore(&fscrypt_ctx_lock, flags); - if (!ctx) { - ctx = kmem_cache_zalloc(fscrypt_ctx_cachep, gfp_flags); - if (!ctx) - return ERR_PTR(-ENOMEM); - ctx->flags |= FS_CTX_REQUIRES_FREE_ENCRYPT_FL; - } else { - ctx->flags &= ~FS_CTX_REQUIRES_FREE_ENCRYPT_FL; - } - return ctx; -} -EXPORT_SYMBOL(fscrypt_get_ctx); - struct page *fscrypt_alloc_bounce_page(gfp_t gfp_flags) { return mempool_alloc(fscrypt_bounce_page_pool, gfp_flags); @@ -392,17 +328,6 @@ const struct dentry_operations fscrypt_d_ops = { .d_revalidate = fscrypt_d_revalidate, }; -static void fscrypt_destroy(void) -{ - struct fscrypt_ctx *pos, *n; - - list_for_each_entry_safe(pos, n, &fscrypt_free_ctxs, free_list) - kmem_cache_free(fscrypt_ctx_cachep, pos); - INIT_LIST_HEAD(&fscrypt_free_ctxs); - mempool_destroy(fscrypt_bounce_page_pool); - fscrypt_bounce_page_pool = NULL; -} - /** * fscrypt_initialize() - allocate major buffers for fs encryption. * @cop_flags: fscrypt operations flags @@ -410,11 +335,11 @@ static void fscrypt_destroy(void) * We only call this when we start accessing encrypted files, since it * results in memory getting allocated that wouldn't otherwise be used. * - * Return: Zero on success, non-zero otherwise. + * Return: 0 on success; -errno on failure */ int fscrypt_initialize(unsigned int cop_flags) { - int i, res = -ENOMEM; + int err = 0; /* No need to allocate a bounce page pool if this FS won't use it. */ if (cop_flags & FS_CFLG_OWN_PAGES) @@ -422,29 +347,18 @@ int fscrypt_initialize(unsigned int cop_flags) mutex_lock(&fscrypt_init_mutex); if (fscrypt_bounce_page_pool) - goto already_initialized; - - for (i = 0; i < num_prealloc_crypto_ctxs; i++) { - struct fscrypt_ctx *ctx; - - ctx = kmem_cache_zalloc(fscrypt_ctx_cachep, GFP_NOFS); - if (!ctx) - goto fail; - list_add(&ctx->free_list, &fscrypt_free_ctxs); - } + goto out_unlock; + err = -ENOMEM; fscrypt_bounce_page_pool = mempool_create_page_pool(num_prealloc_crypto_pages, 0); if (!fscrypt_bounce_page_pool) - goto fail; + goto out_unlock; -already_initialized: - mutex_unlock(&fscrypt_init_mutex); - return 0; -fail: - fscrypt_destroy(); + err = 0; +out_unlock: mutex_unlock(&fscrypt_init_mutex); - return res; + return err; } void fscrypt_msg(const struct inode *inode, const char *level, @@ -490,13 +404,9 @@ static int __init fscrypt_init(void) if (!fscrypt_read_workqueue) goto fail; - fscrypt_ctx_cachep = KMEM_CACHE(fscrypt_ctx, SLAB_RECLAIM_ACCOUNT); - if (!fscrypt_ctx_cachep) - goto fail_free_queue; - fscrypt_info_cachep = KMEM_CACHE(fscrypt_info, SLAB_RECLAIM_ACCOUNT); if (!fscrypt_info_cachep) - goto fail_free_ctx; + goto fail_free_queue; err = fscrypt_init_keyring(); if (err) @@ -506,8 +416,6 @@ static int __init fscrypt_init(void) fail_free_info: kmem_cache_destroy(fscrypt_info_cachep); -fail_free_ctx: - kmem_cache_destroy(fscrypt_ctx_cachep); fail_free_queue: destroy_workqueue(fscrypt_read_workqueue); fail: diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index 76c64297ce18..dacf8fcbac3b 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -203,8 +203,6 @@ typedef enum { FS_ENCRYPT, } fscrypt_direction_t; -#define FS_CTX_REQUIRES_FREE_ENCRYPT_FL 0x00000001 - static inline bool fscrypt_valid_enc_modes(u32 contents_mode, u32 filenames_mode) { diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index f622f7460ed8..04f5ed628445 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -20,7 +20,6 @@ #define FS_CRYPTO_BLOCK_SIZE 16 -struct fscrypt_ctx; struct fscrypt_info; struct fscrypt_str { @@ -64,18 +63,6 @@ struct fscrypt_operations { unsigned int max_namelen; }; -/* Decryption work */ -struct fscrypt_ctx { - union { - struct { - struct bio *bio; - struct work_struct work; - }; - struct list_head free_list; /* Free list */ - }; - u8 flags; /* Flags */ -}; - static inline bool fscrypt_has_encryption_key(const struct inode *inode) { /* pairs with cmpxchg_release() in fscrypt_get_encryption_info() */ @@ -102,8 +89,6 @@ static inline void fscrypt_handle_d_move(struct dentry *dentry) /* crypto.c */ extern void fscrypt_enqueue_decrypt_work(struct work_struct *); -extern struct fscrypt_ctx *fscrypt_get_ctx(gfp_t); -extern void fscrypt_release_ctx(struct fscrypt_ctx *); extern struct page *fscrypt_encrypt_pagecache_blocks(struct page *page, unsigned int len, @@ -244,8 +229,6 @@ static inline bool fscrypt_match_name(const struct fscrypt_name *fname, /* bio.c */ extern void fscrypt_decrypt_bio(struct bio *); -extern void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, - struct bio *bio); extern int fscrypt_zeroout_range(const struct inode *, pgoff_t, sector_t, unsigned int); @@ -295,16 +278,6 @@ static inline void fscrypt_enqueue_decrypt_work(struct work_struct *work) { } -static inline struct fscrypt_ctx *fscrypt_get_ctx(gfp_t gfp_flags) -{ - return ERR_PTR(-EOPNOTSUPP); -} - -static inline void fscrypt_release_ctx(struct fscrypt_ctx *ctx) -{ - return; -} - static inline struct page *fscrypt_encrypt_pagecache_blocks(struct page *page, unsigned int len, unsigned int offs, @@ -484,11 +457,6 @@ static inline void fscrypt_decrypt_bio(struct bio *bio) { } -static inline void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, - struct bio *bio) -{ -} - static inline int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, sector_t pblk, unsigned int len) { -- cgit v1.2.3-71-gd317 From a362687404edc5d73a4fc281af3b2b1542ef194e Mon Sep 17 00:00:00 2001 From: Olof Johansson Date: Mon, 21 Oct 2019 18:52:24 -0700 Subject: soc: mmp: guard include of asm/cputype.h with CONFIG_ARM{,64} Since this driver is enabled for COMPILE_TEST, it avoids build error on x86 allmodconfig: In file included from /build/drivers/phy/marvell/phy-mmp3-usb.c:12: /build/include/linux/soc/mmp/cputype.h:5:10: fatal error: asm/cputype.h: No such file or directory Link: https://lore.kernel.org/r/20191022015658.14624-1-olof@lixom.net Signed-off-by: Olof Johansson --- include/linux/soc/mmp/cputype.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/mmp/cputype.h b/include/linux/soc/mmp/cputype.h index c3ec88983e94..221790761e8e 100644 --- a/include/linux/soc/mmp/cputype.h +++ b/include/linux/soc/mmp/cputype.h @@ -2,7 +2,9 @@ #ifndef __ASM_MACH_CPUTYPE_H #define __ASM_MACH_CPUTYPE_H +#if defined(CONFIG_ARM) || defined(CONFIG_ARM64) #include +#endif /* * CPU Stepping CPU_ID CHIP_ID -- cgit v1.2.3-71-gd317 From 771fdcf8d3d04e77ae0f0dc1018144206a61d216 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Wed, 16 Oct 2019 16:57:53 +0200 Subject: PM / OPP: Support adjusting OPP voltages at runtime On some SoCs the Adaptive Voltage Scaling (AVS) technique is employed to optimize the operating voltage of a device. At a given frequency, the hardware monitors dynamic factors and either makes a suggestion for how much to adjust a voltage for the current frequency, or it automatically adjusts the voltage without software intervention. Add an API to the OPP library for the former case, so that AVS type devices can update the voltages for an OPP when the hardware determines the voltage should change. The assumption is that drivers like CPUfreq or devfreq will register for the OPP notifiers and adjust the voltage according to suggestions that AVS makes. This patch is derived from [1] submitted by Stephen. [1] https://lore.kernel.org/patchwork/patch/599279/ Signed-off-by: Stephen Boyd Signed-off-by: Roger Lu [s.nawrocki@samsung.com: added handling of OPP min/max voltage] Signed-off-by: Sylwester Nawrocki Signed-off-by: Viresh Kumar --- drivers/opp/core.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/pm_opp.h | 13 ++++++++++ 2 files changed, 82 insertions(+) (limited to 'include/linux') diff --git a/drivers/opp/core.c b/drivers/opp/core.c index 3b7ffd0234e9..f38b3be85072 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -2112,6 +2112,75 @@ put_table: return r; } +/** + * dev_pm_opp_adjust_voltage() - helper to change the voltage of an OPP + * @dev: device for which we do this operation + * @freq: OPP frequency to adjust voltage of + * @u_volt: new OPP target voltage + * @u_volt_min: new OPP min voltage + * @u_volt_max: new OPP max voltage + * + * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the + * copy operation, returns 0 if no modifcation was done OR modification was + * successful. + */ +int dev_pm_opp_adjust_voltage(struct device *dev, unsigned long freq, + unsigned long u_volt, unsigned long u_volt_min, + unsigned long u_volt_max) + +{ + struct opp_table *opp_table; + struct dev_pm_opp *tmp_opp, *opp = ERR_PTR(-ENODEV); + int r = 0; + + /* Find the opp_table */ + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + r = PTR_ERR(opp_table); + dev_warn(dev, "%s: Device OPP not found (%d)\n", __func__, r); + return r; + } + + mutex_lock(&opp_table->lock); + + /* Do we have the frequency? */ + list_for_each_entry(tmp_opp, &opp_table->opp_list, node) { + if (tmp_opp->rate == freq) { + opp = tmp_opp; + break; + } + } + + if (IS_ERR(opp)) { + r = PTR_ERR(opp); + goto adjust_unlock; + } + + /* Is update really needed? */ + if (opp->supplies->u_volt == u_volt) + goto adjust_unlock; + + opp->supplies->u_volt = u_volt; + opp->supplies->u_volt_min = u_volt_min; + opp->supplies->u_volt_max = u_volt_max; + + dev_pm_opp_get(opp); + mutex_unlock(&opp_table->lock); + + /* Notify the voltage change of the OPP */ + blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_ADJUST_VOLTAGE, + opp); + + dev_pm_opp_put(opp); + goto adjust_put_table; + +adjust_unlock: + mutex_unlock(&opp_table->lock); +adjust_put_table: + dev_pm_opp_put_opp_table(opp_table); + return r; +} + /** * dev_pm_opp_enable() - Enable a specific OPP * @dev: device for which we do this operation diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index b8197ab014f2..747861816f4f 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -22,6 +22,7 @@ struct opp_table; enum dev_pm_opp_event { OPP_EVENT_ADD, OPP_EVENT_REMOVE, OPP_EVENT_ENABLE, OPP_EVENT_DISABLE, + OPP_EVENT_ADJUST_VOLTAGE, }; /** @@ -113,6 +114,10 @@ int dev_pm_opp_add(struct device *dev, unsigned long freq, void dev_pm_opp_remove(struct device *dev, unsigned long freq); void dev_pm_opp_remove_all_dynamic(struct device *dev); +int dev_pm_opp_adjust_voltage(struct device *dev, unsigned long freq, + unsigned long u_volt, unsigned long u_volt_min, + unsigned long u_volt_max); + int dev_pm_opp_enable(struct device *dev, unsigned long freq); int dev_pm_opp_disable(struct device *dev, unsigned long freq); @@ -242,6 +247,14 @@ static inline void dev_pm_opp_remove_all_dynamic(struct device *dev) { } +static inline int +dev_pm_opp_adjust_voltage(struct device *dev, unsigned long freq, + unsigned long u_volt, unsigned long u_volt_min, + unsigned long u_volt_max) +{ + return 0; +} + static inline int dev_pm_opp_enable(struct device *dev, unsigned long freq) { return 0; -- cgit v1.2.3-71-gd317 From 78958563d8023db0c6d03a2fe2a64d79b47b4349 Mon Sep 17 00:00:00 2001 From: Aaron Lewis Date: Mon, 21 Oct 2019 16:30:22 -0700 Subject: KVM: x86: Remove unneeded kvm_vcpu variable, guest_xcr0_loaded The kvm_vcpu variable, guest_xcr0_loaded, is a waste of an 'int' and a conditional branch. VMX and SVM are the only users, and both unconditionally pair kvm_load_guest_xcr0() with kvm_put_guest_xcr0() making this check unnecessary. Without this variable, the predicates in kvm_load_guest_xcr0 and kvm_put_guest_xcr0 should match. Suggested-by: Sean Christopherson Reviewed-by: Jim Mattson Signed-off-by: Aaron Lewis Change-Id: I7b1eb9b62969d7bbb2850f27e42f863421641b23 Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 16 +++++----------- include/linux/kvm_host.h | 1 - 2 files changed, 5 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 38131c834091..7141f81141a2 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -811,22 +811,16 @@ EXPORT_SYMBOL_GPL(kvm_lmsw); void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) { if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) && - !vcpu->guest_xcr0_loaded) { - /* kvm_set_xcr() also depends on this */ - if (vcpu->arch.xcr0 != host_xcr0) - xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0); - vcpu->guest_xcr0_loaded = 1; - } + vcpu->arch.xcr0 != host_xcr0) + xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0); } EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0); void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) { - if (vcpu->guest_xcr0_loaded) { - if (vcpu->arch.xcr0 != host_xcr0) - xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0); - vcpu->guest_xcr0_loaded = 0; - } + if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) && + vcpu->arch.xcr0 != host_xcr0) + xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0); } EXPORT_SYMBOL_GPL(kvm_put_guest_xcr0); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 719fc3e15ea4..d2017302996c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -278,7 +278,6 @@ struct kvm_vcpu { struct mutex mutex; struct kvm_run *run; - int guest_xcr0_loaded; struct swait_queue_head wq; struct pid __rcu *pid; int sigset_active; -- cgit v1.2.3-71-gd317 From 149487bdacde32f5a9a344a49533ae0772fb9db7 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 21 Oct 2019 15:58:42 -0700 Subject: KVM: Add separate helper for putting borrowed reference to kvm Add a new helper, kvm_put_kvm_no_destroy(), to handle putting a borrowed reference[*] to the VM when installing a new file descriptor fails. KVM expects the refcount to remain valid in this case, as the in-progress ioctl() has an explicit reference to the VM. The primary motiviation for the helper is to document that the 'kvm' pointer is still valid after putting the borrowed reference, e.g. to document that doing mutex(&kvm->lock) immediately after putting a ref to kvm isn't broken. [*] When exposing a new object to userspace via a file descriptor, e.g. a new vcpu, KVM grabs a reference to itself (the VM) prior to making the object visible to userspace to avoid prematurely freeing the VM in the scenario where userspace immediately closes file descriptor. Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/powerpc/kvm/book3s_64_mmu_hv.c | 2 +- arch/powerpc/kvm/book3s_64_vio.c | 2 +- include/linux/kvm_host.h | 1 + virt/kvm/kvm_main.c | 16 ++++++++++++++-- 4 files changed, 17 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 9a75f0e1933b..68678e31c84c 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -2000,7 +2000,7 @@ int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *ghf) ret = anon_inode_getfd("kvm-htab", &kvm_htab_fops, ctx, rwflag | O_CLOEXEC); if (ret < 0) { kfree(ctx); - kvm_put_kvm(kvm); + kvm_put_kvm_no_destroy(kvm); return ret; } diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index 5834db0a54c6..883a66e76638 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -317,7 +317,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, if (ret >= 0) list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables); else - kvm_put_kvm(kvm); + kvm_put_kvm_no_destroy(kvm); mutex_unlock(&kvm->lock); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index d2017302996c..a817e446c9aa 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -621,6 +621,7 @@ void kvm_exit(void); void kvm_get_kvm(struct kvm *kvm); void kvm_put_kvm(struct kvm *kvm); +void kvm_put_kvm_no_destroy(struct kvm *kvm); static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id) { diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 67ef3f2e19e8..b8534c6b8cf6 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -772,6 +772,18 @@ void kvm_put_kvm(struct kvm *kvm) } EXPORT_SYMBOL_GPL(kvm_put_kvm); +/* + * Used to put a reference that was taken on behalf of an object associated + * with a user-visible file descriptor, e.g. a vcpu or device, if installation + * of the new file descriptor fails and the reference cannot be transferred to + * its final owner. In such cases, the caller is still actively using @kvm and + * will fail miserably if the refcount unexpectedly hits zero. + */ +void kvm_put_kvm_no_destroy(struct kvm *kvm) +{ + WARN_ON(refcount_dec_and_test(&kvm->users_count)); +} +EXPORT_SYMBOL_GPL(kvm_put_kvm_no_destroy); static int kvm_vm_release(struct inode *inode, struct file *filp) { @@ -2679,7 +2691,7 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) kvm_get_kvm(kvm); r = create_vcpu_fd(vcpu); if (r < 0) { - kvm_put_kvm(kvm); + kvm_put_kvm_no_destroy(kvm); goto unlock_vcpu_destroy; } @@ -3117,7 +3129,7 @@ static int kvm_ioctl_create_device(struct kvm *kvm, kvm_get_kvm(kvm); ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC); if (ret < 0) { - kvm_put_kvm(kvm); + kvm_put_kvm_no_destroy(kvm); mutex_lock(&kvm->lock); list_del(&dev->vm_node); mutex_unlock(&kvm->lock); -- cgit v1.2.3-71-gd317 From cbb79863fc3175ed5ac506465948b02a893a8235 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Mon, 14 Oct 2019 10:35:56 -0500 Subject: ipmi: Don't allow device module unload when in use If something has the IPMI driver open, don't allow the device module to be unloaded. Before it would unload and the user would get errors on use. This change is made on user request, and it makes it consistent with the I2C driver, which has the same behavior. It does change things a little bit with respect to kernel users. If the ACPI or IPMI watchdog (or any other kernel user) has created a user, then the device module cannot be unloaded. Before it could be unloaded, This does not affect hot-plug. If the device goes away (it's on something removable that is removed or is hot-removed via sysfs) then it still behaves as it did before. Reported-by: tony camuso Signed-off-by: Corey Minyard Tested-by: tony camuso --- drivers/char/ipmi/ipmi_msghandler.c | 23 ++++++++++++++++------- include/linux/ipmi_smi.h | 12 ++++++++---- 2 files changed, 24 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index 2aab80e19ae0..3c8a559506e8 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -448,6 +448,8 @@ enum ipmi_stat_indexes { #define IPMI_IPMB_NUM_SEQ 64 struct ipmi_smi { + struct module *owner; + /* What interface number are we? */ int intf_num; @@ -1220,6 +1222,11 @@ int ipmi_create_user(unsigned int if_num, if (rv) goto out_kfree; + if (!try_module_get(intf->owner)) { + rv = -ENODEV; + goto out_kfree; + } + /* Note that each existing user holds a refcount to the interface. */ kref_get(&intf->refcount); @@ -1349,6 +1356,7 @@ static void _ipmi_destroy_user(struct ipmi_user *user) } kref_put(&intf->refcount, intf_free); + module_put(intf->owner); } int ipmi_destroy_user(struct ipmi_user *user) @@ -2459,7 +2467,7 @@ static int __get_device_id(struct ipmi_smi *intf, struct bmc_device *bmc) * been recently fetched, this will just use the cached data. Otherwise * it will run a new fetch. * - * Except for the first time this is called (in ipmi_register_smi()), + * Except for the first time this is called (in ipmi_add_smi()), * this will always return good data; */ static int __bmc_get_device_id(struct ipmi_smi *intf, struct bmc_device *bmc, @@ -3377,10 +3385,11 @@ static void redo_bmc_reg(struct work_struct *work) kref_put(&intf->refcount, intf_free); } -int ipmi_register_smi(const struct ipmi_smi_handlers *handlers, - void *send_info, - struct device *si_dev, - unsigned char slave_addr) +int ipmi_add_smi(struct module *owner, + const struct ipmi_smi_handlers *handlers, + void *send_info, + struct device *si_dev, + unsigned char slave_addr) { int i, j; int rv; @@ -3406,7 +3415,7 @@ int ipmi_register_smi(const struct ipmi_smi_handlers *handlers, return rv; } - + intf->owner = owner; intf->bmc = &intf->tmp_bmc; INIT_LIST_HEAD(&intf->bmc->intfs); mutex_init(&intf->bmc->dyn_mutex); @@ -3514,7 +3523,7 @@ int ipmi_register_smi(const struct ipmi_smi_handlers *handlers, return rv; } -EXPORT_SYMBOL(ipmi_register_smi); +EXPORT_SYMBOL(ipmi_add_smi); static void deliver_smi_err_response(struct ipmi_smi *intf, struct ipmi_smi_msg *msg, diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h index 4dc66157d872..deec18b8944a 100644 --- a/include/linux/ipmi_smi.h +++ b/include/linux/ipmi_smi.h @@ -224,10 +224,14 @@ static inline int ipmi_demangle_device_id(uint8_t netfn, uint8_t cmd, * is called, and the lower layer must get the interface from that * call. */ -int ipmi_register_smi(const struct ipmi_smi_handlers *handlers, - void *send_info, - struct device *dev, - unsigned char slave_addr); +int ipmi_add_smi(struct module *owner, + const struct ipmi_smi_handlers *handlers, + void *send_info, + struct device *dev, + unsigned char slave_addr); + +#define ipmi_register_smi(handlers, send_info, dev, slave_addr) \ + ipmi_add_smi(THIS_MODULE, handlers, send_info, dev, slave_addr) /* * Remove a low-level interface from the IPMI driver. This will -- cgit v1.2.3-71-gd317 From 4b97ba73dcdc24fd968cbeb970ae57212e2c1c73 Mon Sep 17 00:00:00 2001 From: Jethro Beekman Date: Wed, 4 Sep 2019 01:15:24 +0000 Subject: mtd: spi-nor: intel-spi: add support for Intel Cannon Lake SPI flash Now that SPI flash controllers without a software sequencer are supported, it's trivial to add support for CNL and its PCI ID. Values from https://www.intel.com/content/dam/www/public/us/en/documents/datasheets/300-series-chipset-pch-datasheet-vol-2.pdf Signed-off-by: Jethro Beekman Reviewed-by: Mika Westerberg Signed-off-by: Tudor Ambarus --- drivers/mtd/spi-nor/intel-spi-pci.c | 5 +++++ drivers/mtd/spi-nor/intel-spi.c | 11 +++++++++++ include/linux/platform_data/intel-spi.h | 1 + 3 files changed, 17 insertions(+) (limited to 'include/linux') diff --git a/drivers/mtd/spi-nor/intel-spi-pci.c b/drivers/mtd/spi-nor/intel-spi-pci.c index 3cda8e7a68f8..581d154796c1 100644 --- a/drivers/mtd/spi-nor/intel-spi-pci.c +++ b/drivers/mtd/spi-nor/intel-spi-pci.c @@ -20,6 +20,10 @@ static const struct intel_spi_boardinfo bxt_info = { .type = INTEL_SPI_BXT, }; +static const struct intel_spi_boardinfo cnl_info = { + .type = INTEL_SPI_CNL, +}; + static int intel_spi_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { @@ -68,6 +72,7 @@ static const struct pci_device_id intel_spi_pci_ids[] = { { PCI_VDEVICE(INTEL, 0xa0a4), (unsigned long)&bxt_info }, { PCI_VDEVICE(INTEL, 0xa1a4), (unsigned long)&bxt_info }, { PCI_VDEVICE(INTEL, 0xa224), (unsigned long)&bxt_info }, + { PCI_VDEVICE(INTEL, 0xa324), (unsigned long)&cnl_info }, { }, }; MODULE_DEVICE_TABLE(pci, intel_spi_pci_ids); diff --git a/drivers/mtd/spi-nor/intel-spi.c b/drivers/mtd/spi-nor/intel-spi.c index a85af3b65f2f..8420528dbaa8 100644 --- a/drivers/mtd/spi-nor/intel-spi.c +++ b/drivers/mtd/spi-nor/intel-spi.c @@ -108,6 +108,10 @@ #define BXT_FREG_NUM 12 #define BXT_PR_NUM 6 +#define CNL_PR 0x84 +#define CNL_FREG_NUM 6 +#define CNL_PR_NUM 5 + #define LVSCC 0xc4 #define UVSCC 0xc8 #define ERASE_OPCODE_SHIFT 8 @@ -344,6 +348,13 @@ static int intel_spi_init(struct intel_spi *ispi) ispi->erase_64k = true; break; + case INTEL_SPI_CNL: + ispi->sregs = NULL; + ispi->pregs = ispi->base + CNL_PR; + ispi->nregions = CNL_FREG_NUM; + ispi->pr_num = CNL_PR_NUM; + break; + default: return -EINVAL; } diff --git a/include/linux/platform_data/intel-spi.h b/include/linux/platform_data/intel-spi.h index ebb4f332588b..7f53a5c6f35e 100644 --- a/include/linux/platform_data/intel-spi.h +++ b/include/linux/platform_data/intel-spi.h @@ -13,6 +13,7 @@ enum intel_spi_type { INTEL_SPI_BYT = 1, INTEL_SPI_LPT, INTEL_SPI_BXT, + INTEL_SPI_CNL, }; /** -- cgit v1.2.3-71-gd317 From 45397787536434648495f7b02a7e669ab8ae12f3 Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Tue, 24 Sep 2019 07:45:53 +0000 Subject: mtd: spi-nor: Introduce 'struct spi_nor_controller_ops' Move all SPI NOR controller driver specific ops in a dedicated structure. 'struct spi_nor' becomes lighter. Use size_t for lengths in 'int (*write_reg)()' and 'int (*read_reg)()'. Rename wite/read_buf to buf, the name of the functions are suggestive enough. Constify buf in int (*write_reg). Comply with these changes in the SPI NOR controller drivers. Suggested-by: Boris Brezillon Signed-off-by: Tudor Ambarus Reviewed-by: Boris Brezillon --- drivers/mtd/spi-nor/aspeed-smc.c | 23 ++++++----- drivers/mtd/spi-nor/cadence-quadspi.c | 39 ++++++++++-------- drivers/mtd/spi-nor/hisi-sfc.c | 22 +++++----- drivers/mtd/spi-nor/intel-spi.c | 24 ++++++----- drivers/mtd/spi-nor/mtk-quadspi.c | 25 +++++++----- drivers/mtd/spi-nor/nxp-spifi.c | 23 +++++++---- drivers/mtd/spi-nor/spi-nor.c | 76 ++++++++++++++++++++--------------- include/linux/mtd/spi-nor.h | 51 +++++++++++++---------- 8 files changed, 166 insertions(+), 117 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/spi-nor/aspeed-smc.c b/drivers/mtd/spi-nor/aspeed-smc.c index 009c1da8574c..2b7cabbb680c 100644 --- a/drivers/mtd/spi-nor/aspeed-smc.c +++ b/drivers/mtd/spi-nor/aspeed-smc.c @@ -320,7 +320,8 @@ static void aspeed_smc_unprep(struct spi_nor *nor, enum spi_nor_ops ops) mutex_unlock(&chip->controller->mutex); } -static int aspeed_smc_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) +static int aspeed_smc_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, + size_t len) { struct aspeed_smc_chip *chip = nor->priv; @@ -331,8 +332,8 @@ static int aspeed_smc_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) return 0; } -static int aspeed_smc_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, - int len) +static int aspeed_smc_write_reg(struct spi_nor *nor, u8 opcode, const u8 *buf, + size_t len) { struct aspeed_smc_chip *chip = nor->priv; @@ -746,6 +747,15 @@ static int aspeed_smc_chip_setup_finish(struct aspeed_smc_chip *chip) return 0; } +static const struct spi_nor_controller_ops aspeed_smc_controller_ops = { + .prepare = aspeed_smc_prep, + .unprepare = aspeed_smc_unprep, + .read_reg = aspeed_smc_read_reg, + .write_reg = aspeed_smc_write_reg, + .read = aspeed_smc_read_user, + .write = aspeed_smc_write_user, +}; + static int aspeed_smc_setup_flash(struct aspeed_smc_controller *controller, struct device_node *np, struct resource *r) { @@ -805,12 +815,7 @@ static int aspeed_smc_setup_flash(struct aspeed_smc_controller *controller, nor->dev = dev; nor->priv = chip; spi_nor_set_flash_node(nor, child); - nor->read = aspeed_smc_read_user; - nor->write = aspeed_smc_write_user; - nor->read_reg = aspeed_smc_read_reg; - nor->write_reg = aspeed_smc_write_reg; - nor->prepare = aspeed_smc_prep; - nor->unprepare = aspeed_smc_unprep; + nor->controller_ops = &aspeed_smc_controller_ops; ret = aspeed_smc_chip_setup_init(chip, r); if (ret) diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c index 7bef63947b29..ebda612641a4 100644 --- a/drivers/mtd/spi-nor/cadence-quadspi.c +++ b/drivers/mtd/spi-nor/cadence-quadspi.c @@ -356,18 +356,19 @@ static int cqspi_exec_flash_cmd(struct cqspi_st *cqspi, unsigned int reg) static int cqspi_command_read(struct spi_nor *nor, const u8 *txbuf, const unsigned n_tx, - u8 *rxbuf, const unsigned n_rx) + u8 *rxbuf, size_t n_rx) { struct cqspi_flash_pdata *f_pdata = nor->priv; struct cqspi_st *cqspi = f_pdata->cqspi; void __iomem *reg_base = cqspi->iobase; unsigned int rdreg; unsigned int reg; - unsigned int read_len; + size_t read_len; int status; if (!n_rx || n_rx > CQSPI_STIG_DATA_LEN_MAX || !rxbuf) { - dev_err(nor->dev, "Invalid input argument, len %d rxbuf 0x%p\n", + dev_err(nor->dev, + "Invalid input argument, len %zu rxbuf 0x%p\n", n_rx, rxbuf); return -EINVAL; } @@ -404,19 +405,19 @@ static int cqspi_command_read(struct spi_nor *nor, } static int cqspi_command_write(struct spi_nor *nor, const u8 opcode, - const u8 *txbuf, const unsigned n_tx) + const u8 *txbuf, size_t n_tx) { struct cqspi_flash_pdata *f_pdata = nor->priv; struct cqspi_st *cqspi = f_pdata->cqspi; void __iomem *reg_base = cqspi->iobase; unsigned int reg; unsigned int data; - u32 write_len; + size_t write_len; int ret; if (n_tx > CQSPI_STIG_DATA_LEN_MAX || (n_tx && !txbuf)) { dev_err(nor->dev, - "Invalid input argument, cmdlen %d txbuf 0x%p\n", + "Invalid input argument, cmdlen %zu txbuf 0x%p\n", n_tx, txbuf); return -EINVAL; } @@ -1050,7 +1051,7 @@ static int cqspi_erase(struct spi_nor *nor, loff_t offs) return ret; /* Send write enable, then erase commands. */ - ret = nor->write_reg(nor, SPINOR_OP_WREN, NULL, 0); + ret = nor->controller_ops->write_reg(nor, SPINOR_OP_WREN, NULL, 0); if (ret) return ret; @@ -1080,7 +1081,7 @@ static void cqspi_unprep(struct spi_nor *nor, enum spi_nor_ops ops) mutex_unlock(&cqspi->bus_mutex); } -static int cqspi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) +static int cqspi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, size_t len) { int ret; @@ -1091,7 +1092,8 @@ static int cqspi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) return ret; } -static int cqspi_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) +static int cqspi_write_reg(struct spi_nor *nor, u8 opcode, const u8 *buf, + size_t len) { int ret; @@ -1216,6 +1218,16 @@ static void cqspi_request_mmap_dma(struct cqspi_st *cqspi) init_completion(&cqspi->rx_dma_complete); } +static const struct spi_nor_controller_ops cqspi_controller_ops = { + .prepare = cqspi_prep, + .unprepare = cqspi_unprep, + .read_reg = cqspi_read_reg, + .write_reg = cqspi_write_reg, + .read = cqspi_read, + .write = cqspi_write, + .erase = cqspi_erase, +}; + static int cqspi_setup_flash(struct cqspi_st *cqspi, struct device_node *np) { struct platform_device *pdev = cqspi->pdev; @@ -1265,14 +1277,7 @@ static int cqspi_setup_flash(struct cqspi_st *cqspi, struct device_node *np) nor->dev = dev; spi_nor_set_flash_node(nor, np); nor->priv = f_pdata; - - nor->read_reg = cqspi_read_reg; - nor->write_reg = cqspi_write_reg; - nor->read = cqspi_read; - nor->write = cqspi_write; - nor->erase = cqspi_erase; - nor->prepare = cqspi_prep; - nor->unprepare = cqspi_unprep; + nor->controller_ops = &cqspi_controller_ops; mtd->name = devm_kasprintf(dev, GFP_KERNEL, "%s.%d", dev_name(dev), cs); diff --git a/drivers/mtd/spi-nor/hisi-sfc.c b/drivers/mtd/spi-nor/hisi-sfc.c index c99ed9cdbf9c..a1258216f89d 100644 --- a/drivers/mtd/spi-nor/hisi-sfc.c +++ b/drivers/mtd/spi-nor/hisi-sfc.c @@ -177,7 +177,7 @@ static void hisi_spi_nor_unprep(struct spi_nor *nor, enum spi_nor_ops ops) } static int hisi_spi_nor_op_reg(struct spi_nor *nor, - u8 opcode, int len, u8 optype) + u8 opcode, size_t len, u8 optype) { struct hifmc_priv *priv = nor->priv; struct hifmc_host *host = priv->host; @@ -200,7 +200,7 @@ static int hisi_spi_nor_op_reg(struct spi_nor *nor, } static int hisi_spi_nor_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, - int len) + size_t len) { struct hifmc_priv *priv = nor->priv; struct hifmc_host *host = priv->host; @@ -215,7 +215,7 @@ static int hisi_spi_nor_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, } static int hisi_spi_nor_write_reg(struct spi_nor *nor, u8 opcode, - u8 *buf, int len) + const u8 *buf, size_t len) { struct hifmc_priv *priv = nor->priv; struct hifmc_host *host = priv->host; @@ -311,6 +311,15 @@ static ssize_t hisi_spi_nor_write(struct spi_nor *nor, loff_t to, return len; } +static const struct spi_nor_controller_ops hisi_controller_ops = { + .prepare = hisi_spi_nor_prep, + .unprepare = hisi_spi_nor_unprep, + .read_reg = hisi_spi_nor_read_reg, + .write_reg = hisi_spi_nor_write_reg, + .read = hisi_spi_nor_read, + .write = hisi_spi_nor_write, +}; + /** * Get spi flash device information and register it as a mtd device. */ @@ -357,13 +366,8 @@ static int hisi_spi_nor_register(struct device_node *np, } priv->host = host; nor->priv = priv; + nor->controller_ops = &hisi_controller_ops; - nor->prepare = hisi_spi_nor_prep; - nor->unprepare = hisi_spi_nor_unprep; - nor->read_reg = hisi_spi_nor_read_reg; - nor->write_reg = hisi_spi_nor_write_reg; - nor->read = hisi_spi_nor_read; - nor->write = hisi_spi_nor_write; ret = spi_nor_scan(nor, NULL, &hwcaps); if (ret) return ret; diff --git a/drivers/mtd/spi-nor/intel-spi.c b/drivers/mtd/spi-nor/intel-spi.c index 8420528dbaa8..61d2a0ad2131 100644 --- a/drivers/mtd/spi-nor/intel-spi.c +++ b/drivers/mtd/spi-nor/intel-spi.c @@ -446,7 +446,7 @@ static int intel_spi_opcode_index(struct intel_spi *ispi, u8 opcode, int optype) return 0; } -static int intel_spi_hw_cycle(struct intel_spi *ispi, u8 opcode, int len) +static int intel_spi_hw_cycle(struct intel_spi *ispi, u8 opcode, size_t len) { u32 val, status; int ret; @@ -489,7 +489,7 @@ static int intel_spi_hw_cycle(struct intel_spi *ispi, u8 opcode, int len) return 0; } -static int intel_spi_sw_cycle(struct intel_spi *ispi, u8 opcode, int len, +static int intel_spi_sw_cycle(struct intel_spi *ispi, u8 opcode, size_t len, int optype) { u32 val = 0, status; @@ -555,7 +555,8 @@ static int intel_spi_sw_cycle(struct intel_spi *ispi, u8 opcode, int len, return 0; } -static int intel_spi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) +static int intel_spi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, + size_t len) { struct intel_spi *ispi = nor->priv; int ret; @@ -575,7 +576,8 @@ static int intel_spi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) return intel_spi_read_block(ispi, buf, len); } -static int intel_spi_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) +static int intel_spi_write_reg(struct spi_nor *nor, u8 opcode, const u8 *buf, + size_t len) { struct intel_spi *ispi = nor->priv; int ret; @@ -884,6 +886,14 @@ static void intel_spi_fill_partition(struct intel_spi *ispi, } } +static const struct spi_nor_controller_ops intel_spi_controller_ops = { + .read_reg = intel_spi_read_reg, + .write_reg = intel_spi_write_reg, + .read = intel_spi_read, + .write = intel_spi_write, + .erase = intel_spi_erase, +}; + struct intel_spi *intel_spi_probe(struct device *dev, struct resource *mem, const struct intel_spi_boardinfo *info) { @@ -917,11 +927,7 @@ struct intel_spi *intel_spi_probe(struct device *dev, ispi->nor.dev = ispi->dev; ispi->nor.priv = ispi; - ispi->nor.read_reg = intel_spi_read_reg; - ispi->nor.write_reg = intel_spi_write_reg; - ispi->nor.read = intel_spi_read; - ispi->nor.write = intel_spi_write; - ispi->nor.erase = intel_spi_erase; + ispi->nor.controller_ops = &intel_spi_controller_ops; ret = spi_nor_scan(&ispi->nor, NULL, &hwcaps); if (ret) { diff --git a/drivers/mtd/spi-nor/mtk-quadspi.c b/drivers/mtd/spi-nor/mtk-quadspi.c index 34db01ab6cab..b1691680d174 100644 --- a/drivers/mtd/spi-nor/mtk-quadspi.c +++ b/drivers/mtd/spi-nor/mtk-quadspi.c @@ -151,9 +151,9 @@ static int mtk_nor_execute_cmd(struct mtk_nor *mtk_nor, u8 cmdval) } static int mtk_nor_do_tx_rx(struct mtk_nor *mtk_nor, u8 op, - u8 *tx, int txlen, u8 *rx, int rxlen) + const u8 *tx, size_t txlen, u8 *rx, size_t rxlen) { - int len = 1 + txlen + rxlen; + size_t len = 1 + txlen + rxlen; int i, ret, idx; if (len > MTK_NOR_MAX_SHIFT) @@ -193,7 +193,7 @@ static int mtk_nor_do_tx_rx(struct mtk_nor *mtk_nor, u8 op, } /* Do a WRSR (Write Status Register) command */ -static int mtk_nor_wr_sr(struct mtk_nor *mtk_nor, u8 sr) +static int mtk_nor_wr_sr(struct mtk_nor *mtk_nor, const u8 sr) { writeb(sr, mtk_nor->base + MTK_NOR_PRGDATA5_REG); writeb(8, mtk_nor->base + MTK_NOR_CNT_REG); @@ -354,7 +354,7 @@ static ssize_t mtk_nor_write(struct spi_nor *nor, loff_t to, size_t len, return len; } -static int mtk_nor_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) +static int mtk_nor_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, size_t len) { int ret; struct mtk_nor *mtk_nor = nor->priv; @@ -376,8 +376,8 @@ static int mtk_nor_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) return ret; } -static int mtk_nor_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, - int len) +static int mtk_nor_write_reg(struct spi_nor *nor, u8 opcode, const u8 *buf, + size_t len) { int ret; struct mtk_nor *mtk_nor = nor->priv; @@ -419,6 +419,13 @@ static int mtk_nor_enable_clk(struct mtk_nor *mtk_nor) return 0; } +static const struct spi_nor_controller_ops mtk_controller_ops = { + .read_reg = mtk_nor_read_reg, + .write_reg = mtk_nor_write_reg, + .read = mtk_nor_read, + .write = mtk_nor_write, +}; + static int mtk_nor_init(struct mtk_nor *mtk_nor, struct device_node *flash_node) { @@ -438,12 +445,8 @@ static int mtk_nor_init(struct mtk_nor *mtk_nor, nor->dev = mtk_nor->dev; nor->priv = mtk_nor; spi_nor_set_flash_node(nor, flash_node); + nor->controller_ops = &mtk_controller_ops; - /* fill the hooks to spi nor */ - nor->read = mtk_nor_read; - nor->read_reg = mtk_nor_read_reg; - nor->write = mtk_nor_write; - nor->write_reg = mtk_nor_write_reg; nor->mtd.name = "mtk_nor"; /* initialized with NULL */ ret = spi_nor_scan(nor, NULL, &hwcaps); diff --git a/drivers/mtd/spi-nor/nxp-spifi.c b/drivers/mtd/spi-nor/nxp-spifi.c index 4a871587392b..9a5b1a7c636a 100644 --- a/drivers/mtd/spi-nor/nxp-spifi.c +++ b/drivers/mtd/spi-nor/nxp-spifi.c @@ -123,7 +123,8 @@ static int nxp_spifi_set_memory_mode_on(struct nxp_spifi *spifi) return ret; } -static int nxp_spifi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) +static int nxp_spifi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, + size_t len) { struct nxp_spifi *spifi = nor->priv; u32 cmd; @@ -145,7 +146,8 @@ static int nxp_spifi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) return nxp_spifi_wait_for_cmd(spifi); } -static int nxp_spifi_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) +static int nxp_spifi_write_reg(struct spi_nor *nor, u8 opcode, const u8 *buf, + size_t len) { struct nxp_spifi *spifi = nor->priv; u32 cmd; @@ -263,9 +265,18 @@ static int nxp_spifi_setup_memory_cmd(struct nxp_spifi *spifi) static void nxp_spifi_dummy_id_read(struct spi_nor *nor) { u8 id[SPI_NOR_MAX_ID_LEN]; - nor->read_reg(nor, SPINOR_OP_RDID, id, SPI_NOR_MAX_ID_LEN); + nor->controller_ops->read_reg(nor, SPINOR_OP_RDID, id, + SPI_NOR_MAX_ID_LEN); } +static const struct spi_nor_controller_ops nxp_spifi_controller_ops = { + .read_reg = nxp_spifi_read_reg, + .write_reg = nxp_spifi_write_reg, + .read = nxp_spifi_read, + .write = nxp_spifi_write, + .erase = nxp_spifi_erase, +}; + static int nxp_spifi_setup_flash(struct nxp_spifi *spifi, struct device_node *np) { @@ -332,11 +343,7 @@ static int nxp_spifi_setup_flash(struct nxp_spifi *spifi, spifi->nor.dev = spifi->dev; spi_nor_set_flash_node(&spifi->nor, np); spifi->nor.priv = spifi; - spifi->nor.read = nxp_spifi_read; - spifi->nor.write = nxp_spifi_write; - spifi->nor.erase = nxp_spifi_erase; - spifi->nor.read_reg = nxp_spifi_read_reg; - spifi->nor.write_reg = nxp_spifi_write_reg; + spifi->nor.controller_ops = &nxp_spifi_controller_ops; /* * The first read on a hard reset isn't reliable so do a diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 013102792166..a6f9f833c862 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -338,7 +338,7 @@ static ssize_t spi_nor_read_data(struct spi_nor *nor, loff_t from, size_t len, if (nor->spimem) return spi_nor_spimem_read_data(nor, from, len, buf); - return nor->read(nor, from, len, buf); + return nor->controller_ops->read(nor, from, len, buf); } /** @@ -385,7 +385,7 @@ static ssize_t spi_nor_write_data(struct spi_nor *nor, loff_t to, size_t len, if (nor->spimem) return spi_nor_spimem_write_data(nor, to, len, buf); - return nor->write(nor, to, len, buf); + return nor->controller_ops->write(nor, to, len, buf); } /* @@ -406,7 +406,8 @@ static int read_sr(struct spi_nor *nor) ret = spi_mem_exec_op(nor->spimem, &op); } else { - ret = nor->read_reg(nor, SPINOR_OP_RDSR, nor->bouncebuf, 1); + ret = nor->controller_ops->read_reg(nor, SPINOR_OP_RDSR, + nor->bouncebuf, 1); } if (ret < 0) { @@ -435,7 +436,8 @@ static int read_fsr(struct spi_nor *nor) ret = spi_mem_exec_op(nor->spimem, &op); } else { - ret = nor->read_reg(nor, SPINOR_OP_RDFSR, nor->bouncebuf, 1); + ret = nor->controller_ops->read_reg(nor, SPINOR_OP_RDFSR, + nor->bouncebuf, 1); } if (ret < 0) { @@ -464,7 +466,8 @@ static int read_cr(struct spi_nor *nor) ret = spi_mem_exec_op(nor->spimem, &op); } else { - ret = nor->read_reg(nor, SPINOR_OP_RDCR, nor->bouncebuf, 1); + ret = nor->controller_ops->read_reg(nor, SPINOR_OP_RDCR, + nor->bouncebuf, 1); } if (ret < 0) { @@ -492,7 +495,8 @@ static int write_sr(struct spi_nor *nor, u8 val) return spi_mem_exec_op(nor->spimem, &op); } - return nor->write_reg(nor, SPINOR_OP_WRSR, nor->bouncebuf, 1); + return nor->controller_ops->write_reg(nor, SPINOR_OP_WRSR, + nor->bouncebuf, 1); } /* @@ -511,7 +515,7 @@ static int write_enable(struct spi_nor *nor) return spi_mem_exec_op(nor->spimem, &op); } - return nor->write_reg(nor, SPINOR_OP_WREN, NULL, 0); + return nor->controller_ops->write_reg(nor, SPINOR_OP_WREN, NULL, 0); } /* @@ -529,7 +533,7 @@ static int write_disable(struct spi_nor *nor) return spi_mem_exec_op(nor->spimem, &op); } - return nor->write_reg(nor, SPINOR_OP_WRDI, NULL, 0); + return nor->controller_ops->write_reg(nor, SPINOR_OP_WRDI, NULL, 0); } static struct spi_nor *mtd_to_spi_nor(struct mtd_info *mtd) @@ -631,8 +635,9 @@ static int macronix_set_4byte(struct spi_nor *nor, bool enable) return spi_mem_exec_op(nor->spimem, &op); } - return nor->write_reg(nor, enable ? SPINOR_OP_EN4B : SPINOR_OP_EX4B, - NULL, 0); + return nor->controller_ops->write_reg(nor, enable ? SPINOR_OP_EN4B : + SPINOR_OP_EX4B, + NULL, 0); } static int st_micron_set_4byte(struct spi_nor *nor, bool enable) @@ -660,7 +665,8 @@ static int spansion_set_4byte(struct spi_nor *nor, bool enable) return spi_mem_exec_op(nor->spimem, &op); } - return nor->write_reg(nor, SPINOR_OP_BRWR, nor->bouncebuf, 1); + return nor->controller_ops->write_reg(nor, SPINOR_OP_BRWR, + nor->bouncebuf, 1); } static int spi_nor_write_ear(struct spi_nor *nor, u8 ear) @@ -677,7 +683,8 @@ static int spi_nor_write_ear(struct spi_nor *nor, u8 ear) return spi_mem_exec_op(nor->spimem, &op); } - return nor->write_reg(nor, SPINOR_OP_WREAR, nor->bouncebuf, 1); + return nor->controller_ops->write_reg(nor, SPINOR_OP_WREAR, + nor->bouncebuf, 1); } static int winbond_set_4byte(struct spi_nor *nor, bool enable) @@ -712,7 +719,7 @@ static int spi_nor_xread_sr(struct spi_nor *nor, u8 *sr) return spi_mem_exec_op(nor->spimem, &op); } - return nor->read_reg(nor, SPINOR_OP_XRDSR, sr, 1); + return nor->controller_ops->read_reg(nor, SPINOR_OP_XRDSR, sr, 1); } static int s3an_sr_ready(struct spi_nor *nor) @@ -740,7 +747,7 @@ static int spi_nor_clear_sr(struct spi_nor *nor) return spi_mem_exec_op(nor->spimem, &op); } - return nor->write_reg(nor, SPINOR_OP_CLSR, NULL, 0); + return nor->controller_ops->write_reg(nor, SPINOR_OP_CLSR, NULL, 0); } static int spi_nor_sr_ready(struct spi_nor *nor) @@ -774,7 +781,7 @@ static int spi_nor_clear_fsr(struct spi_nor *nor) return spi_mem_exec_op(nor->spimem, &op); } - return nor->write_reg(nor, SPINOR_OP_CLFSR, NULL, 0); + return nor->controller_ops->write_reg(nor, SPINOR_OP_CLFSR, NULL, 0); } static int spi_nor_fsr_ready(struct spi_nor *nor) @@ -871,7 +878,8 @@ static int erase_chip(struct spi_nor *nor) return spi_mem_exec_op(nor->spimem, &op); } - return nor->write_reg(nor, SPINOR_OP_CHIP_ERASE, NULL, 0); + return nor->controller_ops->write_reg(nor, SPINOR_OP_CHIP_ERASE, + NULL, 0); } static int spi_nor_lock_and_prep(struct spi_nor *nor, enum spi_nor_ops ops) @@ -880,10 +888,9 @@ static int spi_nor_lock_and_prep(struct spi_nor *nor, enum spi_nor_ops ops) mutex_lock(&nor->lock); - if (nor->prepare) { - ret = nor->prepare(nor, ops); + if (nor->controller_ops && nor->controller_ops->prepare) { + ret = nor->controller_ops->prepare(nor, ops); if (ret) { - dev_err(nor->dev, "failed in the preparation.\n"); mutex_unlock(&nor->lock); return ret; } @@ -893,8 +900,8 @@ static int spi_nor_lock_and_prep(struct spi_nor *nor, enum spi_nor_ops ops) static void spi_nor_unlock_and_unprep(struct spi_nor *nor, enum spi_nor_ops ops) { - if (nor->unprepare) - nor->unprepare(nor, ops); + if (nor->controller_ops && nor->controller_ops->unprepare) + nor->controller_ops->unprepare(nor, ops); mutex_unlock(&nor->lock); } @@ -935,8 +942,8 @@ static int spi_nor_erase_sector(struct spi_nor *nor, u32 addr) addr = spi_nor_convert_addr(nor, addr); - if (nor->erase) - return nor->erase(nor, addr); + if (nor->controller_ops && nor->controller_ops->erase) + return nor->controller_ops->erase(nor, addr); if (nor->spimem) { struct spi_mem_op op = @@ -957,8 +964,8 @@ static int spi_nor_erase_sector(struct spi_nor *nor, u32 addr) addr >>= 8; } - return nor->write_reg(nor, nor->erase_opcode, nor->bouncebuf, - nor->addr_width); + return nor->controller_ops->write_reg(nor, nor->erase_opcode, + nor->bouncebuf, nor->addr_width); } /** @@ -1678,7 +1685,8 @@ static int write_sr_cr(struct spi_nor *nor, u8 *sr_cr) ret = spi_mem_exec_op(nor->spimem, &op); } else { - ret = nor->write_reg(nor, SPINOR_OP_WRSR, sr_cr, 2); + ret = nor->controller_ops->write_reg(nor, SPINOR_OP_WRSR, + sr_cr, 2); } if (ret < 0) { @@ -1873,7 +1881,7 @@ static int spi_nor_write_sr2(struct spi_nor *nor, u8 *sr2) return spi_mem_exec_op(nor->spimem, &op); } - return nor->write_reg(nor, SPINOR_OP_WRSR2, sr2, 1); + return nor->controller_ops->write_reg(nor, SPINOR_OP_WRSR2, sr2, 1); } static int spi_nor_read_sr2(struct spi_nor *nor, u8 *sr2) @@ -1888,7 +1896,7 @@ static int spi_nor_read_sr2(struct spi_nor *nor, u8 *sr2) return spi_mem_exec_op(nor->spimem, &op); } - return nor->read_reg(nor, SPINOR_OP_RDSR2, sr2, 1); + return nor->controller_ops->read_reg(nor, SPINOR_OP_RDSR2, sr2, 1); } /** @@ -2522,8 +2530,8 @@ static const struct flash_info *spi_nor_read_id(struct spi_nor *nor) tmp = spi_mem_exec_op(nor->spimem, &op); } else { - tmp = nor->read_reg(nor, SPINOR_OP_RDID, id, - SPI_NOR_MAX_ID_LEN); + tmp = nor->controller_ops->read_reg(nor, SPINOR_OP_RDID, id, + SPI_NOR_MAX_ID_LEN); } if (tmp < 0) { dev_err(nor->dev, "error %d reading JEDEC ID\n", tmp); @@ -2724,9 +2732,11 @@ write_err: static int spi_nor_check(struct spi_nor *nor) { if (!nor->dev || - (!nor->spimem && - (!nor->read || !nor->write || !nor->read_reg || - !nor->write_reg))) { + (!nor->spimem && nor->controller_ops && + (!nor->controller_ops->read || + !nor->controller_ops->write || + !nor->controller_ops->read_reg || + !nor->controller_ops->write_reg))) { pr_err("spi-nor: please fill all the necessary fields!\n"); return -EINVAL; } diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index fc0b4b19c900..d1d736d3c8ab 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -465,6 +465,34 @@ enum spi_nor_pp_command_index { /* Forward declaration that will be used in 'struct spi_nor_flash_parameter' */ struct spi_nor; +/** + * struct spi_nor_controller_ops - SPI NOR controller driver specific + * operations. + * @prepare: [OPTIONAL] do some preparations for the + * read/write/erase/lock/unlock operations. + * @unprepare: [OPTIONAL] do some post work after the + * read/write/erase/lock/unlock operations. + * @read_reg: read out the register. + * @write_reg: write data to the register. + * @read: read data from the SPI NOR. + * @write: write data to the SPI NOR. + * @erase: erase a sector of the SPI NOR at the offset @offs; if + * not provided by the driver, spi-nor will send the erase + * opcode via write_reg(). + */ +struct spi_nor_controller_ops { + int (*prepare)(struct spi_nor *nor, enum spi_nor_ops ops); + void (*unprepare)(struct spi_nor *nor, enum spi_nor_ops ops); + int (*read_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, size_t len); + int (*write_reg)(struct spi_nor *nor, u8 opcode, const u8 *buf, + size_t len); + + ssize_t (*read)(struct spi_nor *nor, loff_t from, size_t len, u8 *buf); + ssize_t (*write)(struct spi_nor *nor, loff_t to, size_t len, + const u8 *buf); + int (*erase)(struct spi_nor *nor, loff_t offs); +}; + /** * struct spi_nor_locking_ops - SPI NOR locking methods * @lock: lock a region of the SPI NOR. @@ -549,17 +577,7 @@ struct flash_info; * @read_proto: the SPI protocol for read operations * @write_proto: the SPI protocol for write operations * @reg_proto the SPI protocol for read_reg/write_reg/erase operations - * @prepare: [OPTIONAL] do some preparations for the - * read/write/erase/lock/unlock operations - * @unprepare: [OPTIONAL] do some post work after the - * read/write/erase/lock/unlock operations - * @read_reg: [DRIVER-SPECIFIC] read out the register - * @write_reg: [DRIVER-SPECIFIC] write data to the register - * @read: [DRIVER-SPECIFIC] read data from the SPI NOR - * @write: [DRIVER-SPECIFIC] write data to the SPI NOR - * @erase: [DRIVER-SPECIFIC] erase a sector of the SPI NOR - * at the offset @offs; if not provided by the driver, - * spi-nor will send the erase opcode via write_reg() + * @controller_ops: SPI NOR controller driver specific operations. * @clear_sr_bp: [FLASH-SPECIFIC] clears the Block Protection Bits from * the SPI NOR Status Register. * @params: [FLASH-SPECIFIC] SPI-NOR flash parameters and settings. @@ -588,16 +606,7 @@ struct spi_nor { bool sst_write_second; u32 flags; - int (*prepare)(struct spi_nor *nor, enum spi_nor_ops ops); - void (*unprepare)(struct spi_nor *nor, enum spi_nor_ops ops); - int (*read_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, int len); - int (*write_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, int len); - - ssize_t (*read)(struct spi_nor *nor, loff_t from, - size_t len, u_char *read_buf); - ssize_t (*write)(struct spi_nor *nor, loff_t to, - size_t len, const u_char *write_buf); - int (*erase)(struct spi_nor *nor, loff_t offs); + const struct spi_nor_controller_ops *controller_ops; int (*clear_sr_bp)(struct spi_nor *nor); struct spi_nor_flash_parameter params; -- cgit v1.2.3-71-gd317 From 90767cdfea89c3ac7012035d66633b9ba839091a Mon Sep 17 00:00:00 2001 From: Nagarjuna Kristam Date: Fri, 18 Oct 2019 15:08:08 +0530 Subject: phy: tegra: xusb: Add vbus override support on Tegra210 Tegra XUSB device control driver needs to control vbus override during its operations, add API for the support. Signed-off-by: Nagarjuna Kristam Acked-by: Thierry Reding Signed-off-by: Kishon Vijay Abraham I --- drivers/phy/tegra/xusb-tegra210.c | 58 +++++++++++++++++++++++++++++++++++++++ drivers/phy/tegra/xusb.c | 22 +++++++++++++++ drivers/phy/tegra/xusb.h | 2 ++ include/linux/phy/tegra/xusb.h | 4 ++- 4 files changed, 85 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/phy/tegra/xusb-tegra210.c b/drivers/phy/tegra/xusb-tegra210.c index 12e5a46c1de3..394913bb2f20 100644 --- a/drivers/phy/tegra/xusb-tegra210.c +++ b/drivers/phy/tegra/xusb-tegra210.c @@ -65,6 +65,10 @@ #define XUSB_PADCTL_USB3_PAD_MUX_PCIE_IDDQ_DISABLE(x) (1 << (1 + (x))) #define XUSB_PADCTL_USB3_PAD_MUX_SATA_IDDQ_DISABLE(x) (1 << (8 + (x))) +#define XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPADX_CTL0(x) (0x080 + (x) * 0x40) +#define XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPAD_CTL0_ZIP (1 << 18) +#define XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPAD_CTL0_ZIN (1 << 22) + #define XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPADX_CTL1(x) (0x084 + (x) * 0x40) #define XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPAD_CTL1_VREG_LEV_SHIFT 7 #define XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPAD_CTL1_VREG_LEV_MASK 0x3 @@ -227,6 +231,12 @@ #define XUSB_PADCTL_UPHY_USB3_PADX_ECTL6(x) (0xa74 + (x) * 0x40) #define XUSB_PADCTL_UPHY_USB3_PAD_ECTL6_RX_EQ_CTRL_H_VAL 0xfcf01368 +#define XUSB_PADCTL_USB2_VBUS_ID 0xc60 +#define XUSB_PADCTL_USB2_VBUS_ID_OVERRIDE_VBUS_ON (1 << 14) +#define XUSB_PADCTL_USB2_VBUS_ID_OVERRIDE_SHIFT 18 +#define XUSB_PADCTL_USB2_VBUS_ID_OVERRIDE_MASK 0xf +#define XUSB_PADCTL_USB2_VBUS_ID_OVERRIDE_FLOATING 8 + struct tegra210_xusb_fuse_calibration { u32 hs_curr_level[4]; u32 hs_term_range_adj; @@ -2013,6 +2023,52 @@ static const struct tegra_xusb_port_ops tegra210_usb3_port_ops = { .map = tegra210_usb3_port_map, }; +static int tegra210_xusb_padctl_vbus_override(struct tegra_xusb_padctl *padctl, + bool status) +{ + u32 value; + + dev_dbg(padctl->dev, "%s vbus override\n", status ? "set" : "clear"); + + value = padctl_readl(padctl, XUSB_PADCTL_USB2_VBUS_ID); + + if (status) { + value |= XUSB_PADCTL_USB2_VBUS_ID_OVERRIDE_VBUS_ON; + value &= ~(XUSB_PADCTL_USB2_VBUS_ID_OVERRIDE_MASK << + XUSB_PADCTL_USB2_VBUS_ID_OVERRIDE_SHIFT); + value |= XUSB_PADCTL_USB2_VBUS_ID_OVERRIDE_FLOATING << + XUSB_PADCTL_USB2_VBUS_ID_OVERRIDE_SHIFT; + } else { + value &= ~XUSB_PADCTL_USB2_VBUS_ID_OVERRIDE_VBUS_ON; + } + + padctl_writel(padctl, value, XUSB_PADCTL_USB2_VBUS_ID); + + return 0; +} + +static int tegra210_utmi_port_reset(struct phy *phy) +{ + struct tegra_xusb_padctl *padctl; + struct tegra_xusb_lane *lane; + u32 value; + + lane = phy_get_drvdata(phy); + padctl = lane->pad->padctl; + + value = padctl_readl(padctl, + XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPADX_CTL0(lane->index)); + + if ((value & XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPAD_CTL0_ZIP) || + (value & XUSB_PADCTL_USB2_BATTERY_CHRG_OTGPAD_CTL0_ZIN)) { + tegra210_xusb_padctl_vbus_override(padctl, false); + tegra210_xusb_padctl_vbus_override(padctl, true); + return 1; + } + + return 0; +} + static int tegra210_xusb_read_fuse_calibration(struct tegra210_xusb_fuse_calibration *fuse) { @@ -2075,6 +2131,8 @@ static const struct tegra_xusb_padctl_ops tegra210_xusb_padctl_ops = { .remove = tegra210_xusb_padctl_remove, .usb3_set_lfps_detect = tegra210_usb3_set_lfps_detect, .hsic_set_idle = tegra210_hsic_set_idle, + .vbus_override = tegra210_xusb_padctl_vbus_override, + .utmi_port_reset = tegra210_utmi_port_reset, }; static const char * const tegra210_xusb_padctl_supply_names[] = { diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c index b4b217e2ad49..bf4b00853438 100644 --- a/drivers/phy/tegra/xusb.c +++ b/drivers/phy/tegra/xusb.c @@ -1121,6 +1121,28 @@ int tegra_xusb_padctl_usb3_set_lfps_detect(struct tegra_xusb_padctl *padctl, } EXPORT_SYMBOL_GPL(tegra_xusb_padctl_usb3_set_lfps_detect); +int tegra_xusb_padctl_set_vbus_override(struct tegra_xusb_padctl *padctl, + bool val) +{ + if (padctl->soc->ops->vbus_override) + return padctl->soc->ops->vbus_override(padctl, val); + + return -ENOTSUPP; +} +EXPORT_SYMBOL_GPL(tegra_xusb_padctl_set_vbus_override); + +int tegra_phy_xusb_utmi_port_reset(struct phy *phy) +{ + struct tegra_xusb_lane *lane = phy_get_drvdata(phy); + struct tegra_xusb_padctl *padctl = lane->pad->padctl; + + if (padctl->soc->ops->utmi_port_reset) + return padctl->soc->ops->utmi_port_reset(phy); + + return -ENOTSUPP; +} +EXPORT_SYMBOL_GPL(tegra_phy_xusb_utmi_port_reset); + MODULE_AUTHOR("Thierry Reding "); MODULE_DESCRIPTION("Tegra XUSB Pad Controller driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/phy/tegra/xusb.h b/drivers/phy/tegra/xusb.h index bd91832a0843..da94fcce6307 100644 --- a/drivers/phy/tegra/xusb.h +++ b/drivers/phy/tegra/xusb.h @@ -373,6 +373,8 @@ struct tegra_xusb_padctl_ops { unsigned int index, bool idle); int (*usb3_set_lfps_detect)(struct tegra_xusb_padctl *padctl, unsigned int index, bool enable); + int (*vbus_override)(struct tegra_xusb_padctl *padctl, bool set); + int (*utmi_port_reset)(struct phy *phy); }; struct tegra_xusb_padctl_soc { diff --git a/include/linux/phy/tegra/xusb.h b/include/linux/phy/tegra/xusb.h index ee59562c8354..1235865e7e2c 100644 --- a/include/linux/phy/tegra/xusb.h +++ b/include/linux/phy/tegra/xusb.h @@ -18,5 +18,7 @@ int tegra_xusb_padctl_hsic_set_idle(struct tegra_xusb_padctl *padctl, unsigned int port, bool idle); int tegra_xusb_padctl_usb3_set_lfps_detect(struct tegra_xusb_padctl *padctl, unsigned int port, bool enable); - +int tegra_xusb_padctl_set_vbus_override(struct tegra_xusb_padctl *padctl, + bool val); +int tegra_phy_xusb_utmi_port_reset(struct phy *phy); #endif /* PHY_TEGRA_XUSB_H */ -- cgit v1.2.3-71-gd317 From 2952db0fd51b0890f728df94ac563c21407f4f43 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 11 Sep 2018 16:55:03 +0200 Subject: compat_ioctl: add compat_ptr_ioctl() Many drivers have ioctl() handlers that are completely compatible between 32-bit and 64-bit architectures, except for the argument that is passed down from user space and may have to be passed through compat_ptr() in order to become a valid 64-bit pointer. Using ".compat_ptr = compat_ptr_ioctl" in file operations should let us simplify a lot of those drivers to avoid #ifdef checks, and convert additional drivers that don't have proper compat handling yet. On most architectures, the compat_ptr_ioctl() just passes all arguments to the corresponding ->ioctl handler. The exception is arch/s390, where compat_ptr() clears the top bit of a 32-bit pointer value, so user space pointers to the second 2GB alias the first 2GB, as is the case for native 32-bit s390 user space. The compat_ptr_ioctl() function must therefore be used only with ioctl functions that either ignore the argument or pass a pointer to a compatible data type. If any ioctl command handled by fops->unlocked_ioctl passes a plain integer instead of a pointer, or any of the passed data types is incompatible between 32-bit and 64-bit architectures, a proper handler is required instead of compat_ptr_ioctl. Signed-off-by: Arnd Bergmann --- v3: add a better description v2: use compat_ptr_ioctl instead of generic_compat_ioctl_ptrarg, as suggested by Al Viro --- fs/ioctl.c | 35 +++++++++++++++++++++++++++++++++++ include/linux/fs.h | 7 +++++++ 2 files changed, 42 insertions(+) (limited to 'include/linux') diff --git a/fs/ioctl.c b/fs/ioctl.c index fef3a6bf7c78..3118da0de158 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include @@ -719,3 +720,37 @@ SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { return ksys_ioctl(fd, cmd, arg); } + +#ifdef CONFIG_COMPAT +/** + * compat_ptr_ioctl - generic implementation of .compat_ioctl file operation + * + * This is not normally called as a function, but instead set in struct + * file_operations as + * + * .compat_ioctl = compat_ptr_ioctl, + * + * On most architectures, the compat_ptr_ioctl() just passes all arguments + * to the corresponding ->ioctl handler. The exception is arch/s390, where + * compat_ptr() clears the top bit of a 32-bit pointer value, so user space + * pointers to the second 2GB alias the first 2GB, as is the case for + * native 32-bit s390 user space. + * + * The compat_ptr_ioctl() function must therefore be used only with ioctl + * functions that either ignore the argument or pass a pointer to a + * compatible data type. + * + * If any ioctl command handled by fops->unlocked_ioctl passes a plain + * integer instead of a pointer, or any of the passed data types + * is incompatible between 32-bit and 64-bit architectures, a proper + * handler is required instead of compat_ptr_ioctl. + */ +long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + if (!file->f_op->unlocked_ioctl) + return -ENOIOCTLCMD; + + return file->f_op->unlocked_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); +} +EXPORT_SYMBOL(compat_ptr_ioctl); +#endif diff --git a/include/linux/fs.h b/include/linux/fs.h index e0d909d35763..0b4d8fc79e0f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1727,6 +1727,13 @@ int vfs_mkobj(struct dentry *, umode_t, extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); +#ifdef CONFIG_COMPAT +extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, + unsigned long arg); +#else +#define compat_ptr_ioctl NULL +#endif + /* * VFS file helper functions. */ -- cgit v1.2.3-71-gd317 From 011da44bc5b6520d00b42c584a4fefc85f7b332b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 21 Apr 2019 19:24:03 -0400 Subject: compat: move FS_IOC_RESVSP_32 handling to fs/ioctl.c ... and lose the ridiculous games with compat_alloc_user_space() there. Signed-off-by: Al Viro Signed-off-by: Arnd Bergmann --- fs/compat_ioctl.c | 35 ----------------------------------- fs/ioctl.c | 29 +++++++++++++++++++++++++++++ include/linux/falloc.h | 20 ++++++++++++++++++++ 3 files changed, 49 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index 46e8a8f8b6f1..ce995d4fa1f4 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -467,41 +467,6 @@ static int rtc_ioctl(struct file *file, return -ENOIOCTLCMD; } -/* on ia32 l_start is on a 32-bit boundary */ -#if defined(CONFIG_X86_64) -struct space_resv_32 { - __s16 l_type; - __s16 l_whence; - __s64 l_start __attribute__((packed)); - /* len == 0 means until end of file */ - __s64 l_len __attribute__((packed)); - __s32 l_sysid; - __u32 l_pid; - __s32 l_pad[4]; /* reserve area */ -}; - -#define FS_IOC_RESVSP_32 _IOW ('X', 40, struct space_resv_32) -#define FS_IOC_RESVSP64_32 _IOW ('X', 42, struct space_resv_32) - -/* just account for different alignment */ -static int compat_ioctl_preallocate(struct file *file, - struct space_resv_32 __user *p32) -{ - struct space_resv __user *p = compat_alloc_user_space(sizeof(*p)); - - if (copy_in_user(&p->l_type, &p32->l_type, sizeof(s16)) || - copy_in_user(&p->l_whence, &p32->l_whence, sizeof(s16)) || - copy_in_user(&p->l_start, &p32->l_start, sizeof(s64)) || - copy_in_user(&p->l_len, &p32->l_len, sizeof(s64)) || - copy_in_user(&p->l_sysid, &p32->l_sysid, sizeof(s32)) || - copy_in_user(&p->l_pid, &p32->l_pid, sizeof(u32)) || - copy_in_user(&p->l_pad, &p32->l_pad, 4*sizeof(u32))) - return -EFAULT; - - return ioctl_preallocate(file, p); -} -#endif - /* * simple reversible transform to make our table more evenly * distributed after sorting. diff --git a/fs/ioctl.c b/fs/ioctl.c index e14bd85f3bc6..812061ba667a 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -491,6 +491,35 @@ int ioctl_preallocate(struct file *filp, void __user *argp) return vfs_fallocate(filp, FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len); } +/* on ia32 l_start is on a 32-bit boundary */ +#if defined CONFIG_COMPAT && defined(CONFIG_X86_64) +/* just account for different alignment */ +int compat_ioctl_preallocate(struct file *file, + struct space_resv_32 __user *argp) +{ + struct inode *inode = file_inode(file); + struct space_resv_32 sr; + + if (copy_from_user(&sr, argp, sizeof(sr))) + return -EFAULT; + + switch (sr.l_whence) { + case SEEK_SET: + break; + case SEEK_CUR: + sr.l_start += file->f_pos; + break; + case SEEK_END: + sr.l_start += i_size_read(inode); + break; + default: + return -EINVAL; + } + + return vfs_fallocate(file, FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len); +} +#endif + static int file_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { diff --git a/include/linux/falloc.h b/include/linux/falloc.h index 674d59f4d6ce..fc61fdb9d1e9 100644 --- a/include/linux/falloc.h +++ b/include/linux/falloc.h @@ -29,4 +29,24 @@ struct space_resv { FALLOC_FL_INSERT_RANGE | \ FALLOC_FL_UNSHARE_RANGE) +/* on ia32 l_start is on a 32-bit boundary */ +#if defined(CONFIG_X86_64) +struct space_resv_32 { + __s16 l_type; + __s16 l_whence; + __s64 l_start __attribute__((packed)); + /* len == 0 means until end of file */ + __s64 l_len __attribute__((packed)); + __s32 l_sysid; + __u32 l_pid; + __s32 l_pad[4]; /* reserve area */ +}; + +#define FS_IOC_RESVSP_32 _IOW ('X', 40, struct space_resv_32) +#define FS_IOC_RESVSP64_32 _IOW ('X', 42, struct space_resv_32) + +int compat_ioctl_preallocate(struct file *, struct space_resv_32 __user *); + +#endif + #endif /* _FALLOC_H_ */ -- cgit v1.2.3-71-gd317 From 1207045da5a7c94344e0ea9a9e7495985eef499a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 7 Sep 2018 16:49:43 +0200 Subject: compat_ioctl: move tape handling into drivers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit MTIOCPOS and MTIOCGET are incompatible between 32-bit and 64-bit user space, and traditionally have been translated in fs/compat_ioctl.c. To get rid of that translation handler, move a corresponding implementation into each of the four drivers implementing those commands. The interesting part of that is now in a new linux/mtio.h header that wraps the existing uapi/linux/mtio.h header and provides an abstraction to let drivers handle both cases easily. Using an in_compat_syscall() check, the caller does not have to keep track of whether this was called through .unlocked_ioctl() or .compat_ioctl(). Acked-by: Heiko Carstens Cc: "Kai Mäkisara" Cc: linux-scsi@vger.kernel.org Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: "David S. Miller" Signed-off-by: Arnd Bergmann --- drivers/ide/ide-tape.c | 27 ++++++++++++---- drivers/s390/char/tape_char.c | 41 +++++++++--------------- drivers/scsi/st.c | 28 +++++++++++------ fs/compat_ioctl.c | 73 ------------------------------------------- include/linux/mtio.h | 60 +++++++++++++++++++++++++++++++++++ 5 files changed, 114 insertions(+), 115 deletions(-) create mode 100644 include/linux/mtio.h (limited to 'include/linux') diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c index db1a65f4b490..3e7482695f77 100644 --- a/drivers/ide/ide-tape.c +++ b/drivers/ide/ide-tape.c @@ -19,6 +19,7 @@ #define IDETAPE_VERSION "1.20" +#include #include #include #include @@ -1407,14 +1408,10 @@ static long do_idetape_chrdev_ioctl(struct file *file, if (tape->drv_write_prot) mtget.mt_gstat |= GMT_WR_PROT(0xffffffff); - if (copy_to_user(argp, &mtget, sizeof(struct mtget))) - return -EFAULT; - return 0; + return put_user_mtget(argp, &mtget); case MTIOCPOS: mtpos.mt_blkno = position / tape->user_bs_factor - block_offset; - if (copy_to_user(argp, &mtpos, sizeof(struct mtpos))) - return -EFAULT; - return 0; + return put_user_mtpos(argp, &mtpos); default: if (tape->chrdev_dir == IDETAPE_DIR_READ) ide_tape_discard_merge_buffer(drive, 1); @@ -1432,6 +1429,22 @@ static long idetape_chrdev_ioctl(struct file *file, return ret; } +static long idetape_chrdev_compat_ioctl(struct file *file, + unsigned int cmd, unsigned long arg) +{ + long ret; + + if (cmd == MTIOCPOS32) + cmd = MTIOCPOS; + else if (cmd == MTIOCGET32) + cmd = MTIOCGET; + + mutex_lock(&ide_tape_mutex); + ret = do_idetape_chrdev_ioctl(file, cmd, arg); + mutex_unlock(&ide_tape_mutex); + return ret; +} + /* * Do a mode sense page 0 with block descriptor and if it succeeds set the tape * block size with the reported value. @@ -1886,6 +1899,8 @@ static const struct file_operations idetape_fops = { .read = idetape_chrdev_read, .write = idetape_chrdev_write, .unlocked_ioctl = idetape_chrdev_ioctl, + .compat_ioctl = IS_ENABLED(CONFIG_COMPAT) ? + idetape_chrdev_compat_ioctl : NULL, .open = idetape_chrdev_open, .release = idetape_chrdev_release, .llseek = noop_llseek, diff --git a/drivers/s390/char/tape_char.c b/drivers/s390/char/tape_char.c index ea4253939555..8abb42923307 100644 --- a/drivers/s390/char/tape_char.c +++ b/drivers/s390/char/tape_char.c @@ -341,14 +341,14 @@ tapechar_release(struct inode *inode, struct file *filp) */ static int __tapechar_ioctl(struct tape_device *device, - unsigned int no, unsigned long data) + unsigned int no, void __user *data) { int rc; if (no == MTIOCTOP) { struct mtop op; - if (copy_from_user(&op, (char __user *) data, sizeof(op)) != 0) + if (copy_from_user(&op, data, sizeof(op)) != 0) return -EFAULT; if (op.mt_count < 0) return -EINVAL; @@ -392,9 +392,7 @@ __tapechar_ioctl(struct tape_device *device, if (rc < 0) return rc; pos.mt_blkno = rc; - if (copy_to_user((char __user *) data, &pos, sizeof(pos)) != 0) - return -EFAULT; - return 0; + return put_user_mtpos(data, &pos); } if (no == MTIOCGET) { /* MTIOCGET: query the tape drive status. */ @@ -424,15 +422,12 @@ __tapechar_ioctl(struct tape_device *device, get.mt_blkno = rc; } - if (copy_to_user((char __user *) data, &get, sizeof(get)) != 0) - return -EFAULT; - - return 0; + return put_user_mtget(data, &get); } /* Try the discipline ioctl function. */ if (device->discipline->ioctl_fn == NULL) return -EINVAL; - return device->discipline->ioctl_fn(device, no, data); + return device->discipline->ioctl_fn(device, no, (unsigned long)data); } static long @@ -445,7 +440,7 @@ tapechar_ioctl(struct file *filp, unsigned int no, unsigned long data) device = (struct tape_device *) filp->private_data; mutex_lock(&device->mutex); - rc = __tapechar_ioctl(device, no, data); + rc = __tapechar_ioctl(device, no, (void __user *)data); mutex_unlock(&device->mutex); return rc; } @@ -455,23 +450,17 @@ static long tapechar_compat_ioctl(struct file *filp, unsigned int no, unsigned long data) { struct tape_device *device = filp->private_data; - int rval = -ENOIOCTLCMD; - unsigned long argp; + long rc; - /* The 'arg' argument of any ioctl function may only be used for - * pointers because of the compat pointer conversion. - * Consider this when adding new ioctls. - */ - argp = (unsigned long) compat_ptr(data); - if (device->discipline->ioctl_fn) { - mutex_lock(&device->mutex); - rval = device->discipline->ioctl_fn(device, no, argp); - mutex_unlock(&device->mutex); - if (rval == -EINVAL) - rval = -ENOIOCTLCMD; - } + if (no == MTIOCPOS32) + no = MTIOCPOS; + else if (no == MTIOCGET32) + no = MTIOCGET; - return rval; + mutex_lock(&device->mutex); + rc = __tapechar_ioctl(device, no, compat_ptr(data)); + mutex_unlock(&device->mutex); + return rc; } #endif /* CONFIG_COMPAT */ diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index e3266a64a477..9e3fff2de83e 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -22,6 +22,7 @@ static const char *verstr = "20160209"; #include +#include #include #include #include @@ -3800,14 +3801,11 @@ static long st_ioctl(struct file *file, unsigned int cmd_in, unsigned long arg) if (STp->cleaning_req) mt_status.mt_gstat |= GMT_CLN(0xffffffff); - i = copy_to_user(p, &mt_status, sizeof(struct mtget)); - if (i) { - retval = (-EFAULT); + retval = put_user_mtget(p, &mt_status); + if (retval) goto out; - } STp->recover_reg = 0; /* Clear after read */ - retval = 0; goto out; } /* End of MTIOCGET */ if (cmd_type == _IOC_TYPE(MTIOCPOS) && cmd_nr == _IOC_NR(MTIOCPOS)) { @@ -3821,9 +3819,7 @@ static long st_ioctl(struct file *file, unsigned int cmd_in, unsigned long arg) goto out; } mt_pos.mt_blkno = blk; - i = copy_to_user(p, &mt_pos, sizeof(struct mtpos)); - if (i) - retval = (-EFAULT); + retval = put_user_mtpos(p, &mt_pos); goto out; } mutex_unlock(&STp->lock); @@ -3857,14 +3853,26 @@ static long st_ioctl(struct file *file, unsigned int cmd_in, unsigned long arg) } #ifdef CONFIG_COMPAT -static long st_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +static long st_compat_ioctl(struct file *file, unsigned int cmd_in, unsigned long arg) { + void __user *p = compat_ptr(arg); struct scsi_tape *STp = file->private_data; struct scsi_device *sdev = STp->device; int ret = -ENOIOCTLCMD; + + /* argument conversion is handled using put_user_mtpos/put_user_mtget */ + switch (cmd_in) { + case MTIOCTOP: + return st_ioctl(file, MTIOCTOP, (unsigned long)p); + case MTIOCPOS32: + return st_ioctl(file, MTIOCPOS, (unsigned long)p); + case MTIOCGET32: + return st_ioctl(file, MTIOCGET, (unsigned long)p); + } + if (sdev->host->hostt->compat_ioctl) { - ret = sdev->host->hostt->compat_ioctl(sdev, cmd, (void __user *)arg); + ret = sdev->host->hostt->compat_ioctl(sdev, cmd_in, (void __user *)arg); } return ret; diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index 47da220f95b1..b65eef3d4787 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -27,7 +27,6 @@ #include #include #include -#include #include #include #include @@ -361,73 +360,6 @@ static int ppp_scompress(struct file *file, unsigned int cmd, return do_ioctl(file, PPPIOCSCOMPRESS, (unsigned long) odata); } -#ifdef CONFIG_BLOCK -struct mtget32 { - compat_long_t mt_type; - compat_long_t mt_resid; - compat_long_t mt_dsreg; - compat_long_t mt_gstat; - compat_long_t mt_erreg; - compat_daddr_t mt_fileno; - compat_daddr_t mt_blkno; -}; -#define MTIOCGET32 _IOR('m', 2, struct mtget32) - -struct mtpos32 { - compat_long_t mt_blkno; -}; -#define MTIOCPOS32 _IOR('m', 3, struct mtpos32) - -static int mt_ioctl_trans(struct file *file, - unsigned int cmd, void __user *argp) -{ - /* NULL initialization to make gcc shut up */ - struct mtget __user *get = NULL; - struct mtget32 __user *umget32; - struct mtpos __user *pos = NULL; - struct mtpos32 __user *upos32; - unsigned long kcmd; - void *karg; - int err = 0; - - switch(cmd) { - case MTIOCPOS32: - kcmd = MTIOCPOS; - pos = compat_alloc_user_space(sizeof(*pos)); - karg = pos; - break; - default: /* MTIOCGET32 */ - kcmd = MTIOCGET; - get = compat_alloc_user_space(sizeof(*get)); - karg = get; - break; - } - if (karg == NULL) - return -EFAULT; - err = do_ioctl(file, kcmd, (unsigned long)karg); - if (err) - return err; - switch (cmd) { - case MTIOCPOS32: - upos32 = argp; - err = convert_in_user(&pos->mt_blkno, &upos32->mt_blkno); - break; - case MTIOCGET32: - umget32 = argp; - err = convert_in_user(&get->mt_type, &umget32->mt_type); - err |= convert_in_user(&get->mt_resid, &umget32->mt_resid); - err |= convert_in_user(&get->mt_dsreg, &umget32->mt_dsreg); - err |= convert_in_user(&get->mt_gstat, &umget32->mt_gstat); - err |= convert_in_user(&get->mt_erreg, &umget32->mt_erreg); - err |= convert_in_user(&get->mt_fileno, &umget32->mt_fileno); - err |= convert_in_user(&get->mt_blkno, &umget32->mt_blkno); - break; - } - return err ? -EFAULT: 0; -} - -#endif /* CONFIG_BLOCK */ - /* Bluetooth ioctls */ #define HCIUARTSETPROTO _IOW('U', 200, int) #define HCIUARTGETPROTO _IOR('U', 201, int) @@ -479,8 +411,6 @@ IGNORE_IOCTL(VT_GETMODE) */ COMPATIBLE_IOCTL(_IOR('p', 20, int[7])) /* RTCGET */ COMPATIBLE_IOCTL(_IOW('p', 21, int[7])) /* RTCSET */ -/* Little m */ -COMPATIBLE_IOCTL(MTIOCTOP) #ifdef CONFIG_BLOCK /* md calls this on random blockdevs */ IGNORE_IOCTL(RAID_VERSION) @@ -846,9 +776,6 @@ static long do_ioctl_trans(unsigned int cmd, return sg_ioctl_trans(file, cmd, argp); case SG_GET_REQUEST_TABLE: return sg_grt_trans(file, cmd, argp); - case MTIOCGET32: - case MTIOCPOS32: - return mt_ioctl_trans(file, cmd, argp); #endif } diff --git a/include/linux/mtio.h b/include/linux/mtio.h new file mode 100644 index 000000000000..67d03156f2c2 --- /dev/null +++ b/include/linux/mtio.h @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_MTIO_COMPAT_H +#define _LINUX_MTIO_COMPAT_H + +#include +#include +#include + +/* + * helper functions for implementing compat ioctls on the four tape + * drivers: we define the 32-bit layout of each incompatible structure, + * plus a wrapper function to copy it to user space in either format. + */ + +struct mtget32 { + s32 mt_type; + s32 mt_resid; + s32 mt_dsreg; + s32 mt_gstat; + s32 mt_erreg; + s32 mt_fileno; + s32 mt_blkno; +}; +#define MTIOCGET32 _IOR('m', 2, struct mtget32) + +struct mtpos32 { + s32 mt_blkno; +}; +#define MTIOCPOS32 _IOR('m', 3, struct mtpos32) + +static inline int put_user_mtget(void __user *u, struct mtget *k) +{ + struct mtget32 k32 = { + .mt_type = k->mt_type, + .mt_resid = k->mt_resid, + .mt_dsreg = k->mt_dsreg, + .mt_gstat = k->mt_gstat, + .mt_erreg = k->mt_erreg, + .mt_fileno = k->mt_fileno, + .mt_blkno = k->mt_blkno, + }; + int ret; + + if (in_compat_syscall()) + ret = copy_to_user(u, &k32, sizeof(k32)); + else + ret = copy_to_user(u, k, sizeof(*k)); + + return ret ? -EFAULT : 0; +} + +static inline int put_user_mtpos(void __user *u, struct mtpos *k) +{ + if (in_compat_syscall()) + return put_user(k->mt_blkno, (u32 __user *)u); + else + return put_user(k->mt_blkno, (long __user *)u); +} + +#endif -- cgit v1.2.3-71-gd317 From 98aaaec4a150c39219a8aaa68c3adc6eed443ea8 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 14 Mar 2019 17:45:18 +0100 Subject: compat_ioctl: reimplement SG_IO handling There are two code locations that implement the SG_IO ioctl: the old sg.c driver, and the generic scsi_ioctl helper that is in turn used by multiple drivers. To eradicate the old compat_ioctl conversion handler for the SG_IO command, I implement a readable pair of put_sg_io_hdr() /get_sg_io_hdr() helper functions that can be used for both compat and native mode, and then I call this from both drivers. For the iovec handling, there is already a compat_import_iovec() function that can simply be called in place of import_iovec(). To avoid having to pass the compat/native state through multiple indirections, I mark the SG_IO command itself as compatible in fs/compat_ioctl.c and use in_compat_syscall() to figure out where we are called from. As a side-effect of this, the sg.c driver now also accepts the 32-bit sg_io_hdr format in compat mode using the read/write interface, not just ioctl. This should improve compatiblity with old 32-bit binaries, but it would break if any application intentionally passes the 64-bit data structure in compat mode here. Steffen Maier helped debug an issue in an earlier version of this patch. Cc: Steffen Maier Cc: linux-scsi@vger.kernel.org Cc: Doug Gilbert Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Signed-off-by: Arnd Bergmann --- block/scsi_ioctl.c | 132 +++++++++++++++++++++++++++++++++++++++++-- drivers/scsi/sg.c | 19 ++++--- fs/compat_ioctl.c | 148 +------------------------------------------------ include/linux/blkdev.h | 2 + lib/iov_iter.c | 1 + 5 files changed, 143 insertions(+), 159 deletions(-) (limited to 'include/linux') diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index f5e0ad65e86a..650bade5ea5a 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -2,6 +2,7 @@ /* * Copyright (C) 2001 Jens Axboe */ +#include #include #include #include @@ -327,7 +328,14 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk, struct iov_iter i; struct iovec *iov = NULL; - ret = import_iovec(rq_data_dir(rq), +#ifdef CONFIG_COMPAT + if (in_compat_syscall()) + ret = compat_import_iovec(rq_data_dir(rq), + hdr->dxferp, hdr->iovec_count, + 0, &iov, &i); + else +#endif + ret = import_iovec(rq_data_dir(rq), hdr->dxferp, hdr->iovec_count, 0, &iov, &i); if (ret < 0) @@ -542,6 +550,122 @@ static inline int blk_send_start_stop(struct request_queue *q, return __blk_send_generic(q, bd_disk, GPCMD_START_STOP_UNIT, data); } +#ifdef CONFIG_COMPAT +struct compat_sg_io_hdr { + compat_int_t interface_id; /* [i] 'S' for SCSI generic (required) */ + compat_int_t dxfer_direction; /* [i] data transfer direction */ + unsigned char cmd_len; /* [i] SCSI command length ( <= 16 bytes) */ + unsigned char mx_sb_len; /* [i] max length to write to sbp */ + unsigned short iovec_count; /* [i] 0 implies no scatter gather */ + compat_uint_t dxfer_len; /* [i] byte count of data transfer */ + compat_uint_t dxferp; /* [i], [*io] points to data transfer memory + or scatter gather list */ + compat_uptr_t cmdp; /* [i], [*i] points to command to perform */ + compat_uptr_t sbp; /* [i], [*o] points to sense_buffer memory */ + compat_uint_t timeout; /* [i] MAX_UINT->no timeout (unit: millisec) */ + compat_uint_t flags; /* [i] 0 -> default, see SG_FLAG... */ + compat_int_t pack_id; /* [i->o] unused internally (normally) */ + compat_uptr_t usr_ptr; /* [i->o] unused internally */ + unsigned char status; /* [o] scsi status */ + unsigned char masked_status; /* [o] shifted, masked scsi status */ + unsigned char msg_status; /* [o] messaging level data (optional) */ + unsigned char sb_len_wr; /* [o] byte count actually written to sbp */ + unsigned short host_status; /* [o] errors from host adapter */ + unsigned short driver_status; /* [o] errors from software driver */ + compat_int_t resid; /* [o] dxfer_len - actual_transferred */ + compat_uint_t duration; /* [o] time taken by cmd (unit: millisec) */ + compat_uint_t info; /* [o] auxiliary information */ +}; +#endif + +int put_sg_io_hdr(const struct sg_io_hdr *hdr, void __user *argp) +{ +#ifdef CONFIG_COMPAT + if (in_compat_syscall()) { + struct compat_sg_io_hdr hdr32 = { + .interface_id = hdr->interface_id, + .dxfer_direction = hdr->dxfer_direction, + .cmd_len = hdr->cmd_len, + .mx_sb_len = hdr->mx_sb_len, + .iovec_count = hdr->iovec_count, + .dxfer_len = hdr->dxfer_len, + .dxferp = (uintptr_t)hdr->dxferp, + .cmdp = (uintptr_t)hdr->cmdp, + .sbp = (uintptr_t)hdr->sbp, + .timeout = hdr->timeout, + .flags = hdr->flags, + .pack_id = hdr->pack_id, + .usr_ptr = (uintptr_t)hdr->usr_ptr, + .status = hdr->status, + .masked_status = hdr->masked_status, + .msg_status = hdr->msg_status, + .sb_len_wr = hdr->sb_len_wr, + .host_status = hdr->host_status, + .driver_status = hdr->driver_status, + .resid = hdr->resid, + .duration = hdr->duration, + .info = hdr->info, + }; + + if (copy_to_user(argp, &hdr32, sizeof(hdr32))) + return -EFAULT; + + return 0; + } +#endif + + if (copy_to_user(argp, hdr, sizeof(*hdr))) + return -EFAULT; + + return 0; +} +EXPORT_SYMBOL(put_sg_io_hdr); + +int get_sg_io_hdr(struct sg_io_hdr *hdr, const void __user *argp) +{ +#ifdef CONFIG_COMPAT + struct compat_sg_io_hdr hdr32; + + if (in_compat_syscall()) { + if (copy_from_user(&hdr32, argp, sizeof(hdr32))) + return -EFAULT; + + *hdr = (struct sg_io_hdr) { + .interface_id = hdr32.interface_id, + .dxfer_direction = hdr32.dxfer_direction, + .cmd_len = hdr32.cmd_len, + .mx_sb_len = hdr32.mx_sb_len, + .iovec_count = hdr32.iovec_count, + .dxfer_len = hdr32.dxfer_len, + .dxferp = compat_ptr(hdr32.dxferp), + .cmdp = compat_ptr(hdr32.cmdp), + .sbp = compat_ptr(hdr32.sbp), + .timeout = hdr32.timeout, + .flags = hdr32.flags, + .pack_id = hdr32.pack_id, + .usr_ptr = compat_ptr(hdr32.usr_ptr), + .status = hdr32.status, + .masked_status = hdr32.masked_status, + .msg_status = hdr32.msg_status, + .sb_len_wr = hdr32.sb_len_wr, + .host_status = hdr32.host_status, + .driver_status = hdr32.driver_status, + .resid = hdr32.resid, + .duration = hdr32.duration, + .info = hdr32.info, + }; + + return 0; + } +#endif + + if (copy_from_user(hdr, argp, sizeof(*hdr))) + return -EFAULT; + + return 0; +} +EXPORT_SYMBOL(get_sg_io_hdr); + int scsi_cmd_ioctl(struct request_queue *q, struct gendisk *bd_disk, fmode_t mode, unsigned int cmd, void __user *arg) { @@ -581,14 +705,14 @@ int scsi_cmd_ioctl(struct request_queue *q, struct gendisk *bd_disk, fmode_t mod case SG_IO: { struct sg_io_hdr hdr; - err = -EFAULT; - if (copy_from_user(&hdr, arg, sizeof(hdr))) + err = get_sg_io_hdr(&hdr, arg); + if (err) break; err = sg_io(q, bd_disk, &hdr, mode); if (err == -EFAULT) break; - if (copy_to_user(arg, &hdr, sizeof(hdr))) + if (put_sg_io_hdr(&hdr, arg)) err = -EFAULT; break; } diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index cce757506383..8ae096af2667 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -447,8 +447,7 @@ sg_read(struct file *filp, char __user *buf, size_t count, loff_t * ppos) retval = -ENOMEM; goto free_old_hdr; } - retval =__copy_from_user - (new_hdr, buf, SZ_SG_IO_HDR); + retval = get_sg_io_hdr(new_hdr, buf); req_pack_id = new_hdr->pack_id; kfree(new_hdr); if (retval) { @@ -589,10 +588,7 @@ sg_new_read(Sg_fd * sfp, char __user *buf, size_t count, Sg_request * srp) } if (hp->masked_status || hp->host_status || hp->driver_status) hp->info |= SG_INFO_CHECK; - if (copy_to_user(buf, hp, SZ_SG_IO_HDR)) { - err = -EFAULT; - goto err_out; - } + err = put_sg_io_hdr(hp, buf); err_out: err2 = sg_finish_rem_req(srp); sg_remove_request(sfp, srp); @@ -735,7 +731,7 @@ sg_new_write(Sg_fd *sfp, struct file *file, const char __user *buf, } srp->sg_io_owned = sg_io_owned; hp = &srp->header; - if (__copy_from_user(hp, buf, SZ_SG_IO_HDR)) { + if (get_sg_io_hdr(hp, buf)) { sg_remove_request(sfp, srp); return -EFAULT; } @@ -1797,7 +1793,14 @@ sg_start_req(Sg_request *srp, unsigned char *cmd) struct iovec *iov = NULL; struct iov_iter i; - res = import_iovec(rw, hp->dxferp, iov_count, 0, &iov, &i); +#ifdef CONFIG_COMPAT + if (in_compat_syscall()) + res = compat_import_iovec(rw, hp->dxferp, iov_count, + 0, &iov, &i); + else +#endif + res = import_iovec(rw, hp->dxferp, iov_count, + 0, &iov, &i); if (res < 0) return res; diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index 10ba2d9e20bc..f279e77df256 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -64,151 +64,6 @@ static int do_ioctl(struct file *file, unsigned int cmd, unsigned long arg) } #ifdef CONFIG_BLOCK -typedef struct sg_io_hdr32 { - compat_int_t interface_id; /* [i] 'S' for SCSI generic (required) */ - compat_int_t dxfer_direction; /* [i] data transfer direction */ - unsigned char cmd_len; /* [i] SCSI command length ( <= 16 bytes) */ - unsigned char mx_sb_len; /* [i] max length to write to sbp */ - unsigned short iovec_count; /* [i] 0 implies no scatter gather */ - compat_uint_t dxfer_len; /* [i] byte count of data transfer */ - compat_uint_t dxferp; /* [i], [*io] points to data transfer memory - or scatter gather list */ - compat_uptr_t cmdp; /* [i], [*i] points to command to perform */ - compat_uptr_t sbp; /* [i], [*o] points to sense_buffer memory */ - compat_uint_t timeout; /* [i] MAX_UINT->no timeout (unit: millisec) */ - compat_uint_t flags; /* [i] 0 -> default, see SG_FLAG... */ - compat_int_t pack_id; /* [i->o] unused internally (normally) */ - compat_uptr_t usr_ptr; /* [i->o] unused internally */ - unsigned char status; /* [o] scsi status */ - unsigned char masked_status; /* [o] shifted, masked scsi status */ - unsigned char msg_status; /* [o] messaging level data (optional) */ - unsigned char sb_len_wr; /* [o] byte count actually written to sbp */ - unsigned short host_status; /* [o] errors from host adapter */ - unsigned short driver_status; /* [o] errors from software driver */ - compat_int_t resid; /* [o] dxfer_len - actual_transferred */ - compat_uint_t duration; /* [o] time taken by cmd (unit: millisec) */ - compat_uint_t info; /* [o] auxiliary information */ -} sg_io_hdr32_t; /* 64 bytes long (on sparc32) */ - -typedef struct sg_iovec32 { - compat_uint_t iov_base; - compat_uint_t iov_len; -} sg_iovec32_t; - -static int sg_build_iovec(sg_io_hdr_t __user *sgio, void __user *dxferp, u16 iovec_count) -{ - sg_iovec_t __user *iov = (sg_iovec_t __user *) (sgio + 1); - sg_iovec32_t __user *iov32 = dxferp; - int i; - - for (i = 0; i < iovec_count; i++) { - u32 base, len; - - if (get_user(base, &iov32[i].iov_base) || - get_user(len, &iov32[i].iov_len) || - put_user(compat_ptr(base), &iov[i].iov_base) || - put_user(len, &iov[i].iov_len)) - return -EFAULT; - } - - if (put_user(iov, &sgio->dxferp)) - return -EFAULT; - return 0; -} - -static int sg_ioctl_trans(struct file *file, unsigned int cmd, - sg_io_hdr32_t __user *sgio32) -{ - sg_io_hdr_t __user *sgio; - u16 iovec_count; - u32 data; - void __user *dxferp; - int err; - int interface_id; - - if (get_user(interface_id, &sgio32->interface_id)) - return -EFAULT; - if (interface_id != 'S') - return do_ioctl(file, cmd, (unsigned long)sgio32); - - if (get_user(iovec_count, &sgio32->iovec_count)) - return -EFAULT; - - { - void __user *top = compat_alloc_user_space(0); - void __user *new = compat_alloc_user_space(sizeof(sg_io_hdr_t) + - (iovec_count * sizeof(sg_iovec_t))); - if (new > top) - return -EINVAL; - - sgio = new; - } - - /* Ok, now construct. */ - if (copy_in_user(&sgio->interface_id, &sgio32->interface_id, - (2 * sizeof(int)) + - (2 * sizeof(unsigned char)) + - (1 * sizeof(unsigned short)) + - (1 * sizeof(unsigned int)))) - return -EFAULT; - - if (get_user(data, &sgio32->dxferp)) - return -EFAULT; - dxferp = compat_ptr(data); - if (iovec_count) { - if (sg_build_iovec(sgio, dxferp, iovec_count)) - return -EFAULT; - } else { - if (put_user(dxferp, &sgio->dxferp)) - return -EFAULT; - } - - { - unsigned char __user *cmdp; - unsigned char __user *sbp; - - if (get_user(data, &sgio32->cmdp)) - return -EFAULT; - cmdp = compat_ptr(data); - - if (get_user(data, &sgio32->sbp)) - return -EFAULT; - sbp = compat_ptr(data); - - if (put_user(cmdp, &sgio->cmdp) || - put_user(sbp, &sgio->sbp)) - return -EFAULT; - } - - if (copy_in_user(&sgio->timeout, &sgio32->timeout, - 3 * sizeof(int))) - return -EFAULT; - - if (get_user(data, &sgio32->usr_ptr)) - return -EFAULT; - if (put_user(compat_ptr(data), &sgio->usr_ptr)) - return -EFAULT; - - err = do_ioctl(file, cmd, (unsigned long) sgio); - - if (err >= 0) { - void __user *datap; - - if (copy_in_user(&sgio32->pack_id, &sgio->pack_id, - sizeof(int)) || - get_user(datap, &sgio->usr_ptr) || - put_user((u32)(unsigned long)datap, - &sgio32->usr_ptr) || - copy_in_user(&sgio32->status, &sgio->status, - (4 * sizeof(unsigned char)) + - (2 * sizeof(unsigned short)) + - (3 * sizeof(int)))) - err = -EFAULT; - } - - return err; -} - struct compat_sg_req_info { /* used by SG_GET_REQUEST_TABLE ioctl() */ char req_state; char orphan; @@ -358,6 +213,7 @@ COMPATIBLE_IOCTL(SCSI_IOCTL_GET_PCI) #endif #ifdef CONFIG_BLOCK /* SG stuff */ +COMPATIBLE_IOCTL(SG_IO) COMPATIBLE_IOCTL(SG_SET_TIMEOUT) COMPATIBLE_IOCTL(SG_GET_TIMEOUT) COMPATIBLE_IOCTL(SG_EMULATED_HOST) @@ -435,8 +291,6 @@ static long do_ioctl_trans(unsigned int cmd, case PPPIOCSACTIVE32: return ppp_sock_fprog_ioctl_trans(file, cmd, argp); #ifdef CONFIG_BLOCK - case SG_IO: - return sg_ioctl_trans(file, cmd, argp); case SG_GET_REQUEST_TABLE: return sg_grt_trans(file, cmd, argp); #endif diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f3ea78b0c91c..2c8cd22b176b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -870,6 +870,8 @@ extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t, unsigned int, void __user *); extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t, struct scsi_ioctl_command __user *); +extern int get_sg_io_hdr(struct sg_io_hdr *hdr, const void __user *argp); +extern int put_sg_io_hdr(const struct sg_io_hdr *hdr, void __user *argp); extern int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags); extern void blk_queue_exit(struct request_queue *q); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 639d5e7014c1..ffb52f2c0ef4 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1678,6 +1678,7 @@ ssize_t compat_import_iovec(int type, *iov = p == *iov ? NULL : p; return n; } +EXPORT_SYMBOL(compat_import_iovec); #endif int import_single_range(int rw, void __user *buf, size_t len, -- cgit v1.2.3-71-gd317 From ce4dd4429b3c7e4506870796f3b8b06d707d2928 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 16 Oct 2019 15:13:41 +0100 Subject: Remove the nr_exclusive argument from __wake_up_sync_key() Remove the nr_exclusive argument from __wake_up_sync_key() and derived functions as everything seems to set it to 1. Note also that if it wasn't set to 1, it would clear WF_SYNC anyway. Signed-off-by: David Howells Acked-by: Peter Zijlstra (Intel) --- include/linux/wait.h | 8 ++++---- kernel/exit.c | 2 +- kernel/sched/wait.c | 14 ++++---------- 3 files changed, 9 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index 3eb7cae8206c..bb7676d396cd 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -201,9 +201,9 @@ void __wake_up(struct wait_queue_head *wq_head, unsigned int mode, int nr, void void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked_key_bookmark(struct wait_queue_head *wq_head, unsigned int mode, void *key, wait_queue_entry_t *bookmark); -void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, int nr, void *key); +void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr); -void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode, int nr); +void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode); #define wake_up(x) __wake_up(x, TASK_NORMAL, 1, NULL) #define wake_up_nr(x, nr) __wake_up(x, TASK_NORMAL, nr, NULL) @@ -214,7 +214,7 @@ void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode, int nr); #define wake_up_interruptible(x) __wake_up(x, TASK_INTERRUPTIBLE, 1, NULL) #define wake_up_interruptible_nr(x, nr) __wake_up(x, TASK_INTERRUPTIBLE, nr, NULL) #define wake_up_interruptible_all(x) __wake_up(x, TASK_INTERRUPTIBLE, 0, NULL) -#define wake_up_interruptible_sync(x) __wake_up_sync((x), TASK_INTERRUPTIBLE, 1) +#define wake_up_interruptible_sync(x) __wake_up_sync((x), TASK_INTERRUPTIBLE) /* * Wakeup macros to be used to report events to the targets. @@ -228,7 +228,7 @@ void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode, int nr); #define wake_up_interruptible_poll(x, m) \ __wake_up(x, TASK_INTERRUPTIBLE, 1, poll_to_key(m)) #define wake_up_interruptible_sync_poll(x, m) \ - __wake_up_sync_key((x), TASK_INTERRUPTIBLE, 1, poll_to_key(m)) + __wake_up_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m)) #define ___wait_cond_timeout(condition) \ ({ \ diff --git a/kernel/exit.c b/kernel/exit.c index a46a50d67002..a1ff25ef050e 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1435,7 +1435,7 @@ static int child_wait_callback(wait_queue_entry_t *wait, unsigned mode, void __wake_up_parent(struct task_struct *p, struct task_struct *parent) { __wake_up_sync_key(&parent->signal->wait_chldexit, - TASK_INTERRUPTIBLE, 1, p); + TASK_INTERRUPTIBLE, p); } static long do_wait(struct wait_opts *wo) diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index c1e566a114ca..b4b52361dab7 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -169,7 +169,6 @@ EXPORT_SYMBOL_GPL(__wake_up_locked_key_bookmark); * __wake_up_sync_key - wake up threads blocked on a waitqueue. * @wq_head: the waitqueue * @mode: which threads - * @nr_exclusive: how many wake-one or wake-many threads to wake up * @key: opaque value to be passed to wakeup targets * * The sync wakeup differs that the waker knows that it will schedule @@ -183,26 +182,21 @@ EXPORT_SYMBOL_GPL(__wake_up_locked_key_bookmark); * accessing the task state. */ void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, - int nr_exclusive, void *key) + void *key) { - int wake_flags = 1; /* XXX WF_SYNC */ - if (unlikely(!wq_head)) return; - if (unlikely(nr_exclusive != 1)) - wake_flags = 0; - - __wake_up_common_lock(wq_head, mode, nr_exclusive, wake_flags, key); + __wake_up_common_lock(wq_head, mode, 1, WF_SYNC, key); } EXPORT_SYMBOL_GPL(__wake_up_sync_key); /* * __wake_up_sync - see __wake_up_sync_key() */ -void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive) +void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode) { - __wake_up_sync_key(wq_head, mode, nr_exclusive, NULL); + __wake_up_sync_key(wq_head, mode, NULL); } EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ -- cgit v1.2.3-71-gd317 From a3470c1829c0c856a19c10af58f8e7792ae27d7a Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Wed, 23 Oct 2019 10:00:46 +0300 Subject: spi: document CS setup, hold & inactive times in header This change documents the CS setup, host & inactive times. They were omitted when the fields were added, and were caught by one of the build bots. Fixes: 25093bdeb6bc ("spi: implement SW control for CS times") Reported-by: kbuild test robot Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20191023070046.12478-1-alexandru.ardelean@analog.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index c40d6af2bf07..98fe8663033a 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -407,6 +407,11 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * controller has native support for memory like operations. * @unprepare_message: undo any work done by prepare_message(). * @slave_abort: abort the ongoing transfer request on an SPI slave controller + * @cs_setup: delay to be introduced by the controller after CS is asserted + * @cs_hold: delay to be introduced by the controller before CS is deasserted + * @cs_inactive: delay to be introduced by the controller after CS is + * deasserted. If @cs_change_delay is used from @spi_transfer, then the + * two delays will be added up. * @cs_gpios: LEGACY: array of GPIO descs to use as chip select lines; one per * CS number. Any individual value may be -ENOENT for CS lines that * are not GPIOs (driven by the SPI controller itself). Use the cs_gpiods -- cgit v1.2.3-71-gd317 From fa6e98cee558622565c97924e922b97340aeabd8 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Tue, 22 Oct 2019 11:31:07 -0700 Subject: net: phy: add support for clause 37 auto-negotiation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds support for clause 37 1000Base-X auto-negotiation. Signed-off-by: Heiner Kallweit Signed-off-by: Tao Ren Tested-by: René van Dorst Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 139 +++++++++++++++++++++++++++++++++++++++++++ include/linux/phy.h | 4 ++ 2 files changed, 143 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index f1f60bd4865a..fa71998fea51 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1607,6 +1607,40 @@ static int genphy_config_advert(struct phy_device *phydev) return changed; } +/** + * genphy_c37_config_advert - sanitize and advertise auto-negotiation parameters + * @phydev: target phy_device struct + * + * Description: Writes MII_ADVERTISE with the appropriate values, + * after sanitizing the values to make sure we only advertise + * what is supported. Returns < 0 on error, 0 if the PHY's advertisement + * hasn't changed, and > 0 if it has changed. This function is intended + * for Clause 37 1000Base-X mode. + */ +static int genphy_c37_config_advert(struct phy_device *phydev) +{ + u16 adv = 0; + + /* Only allow advertising what this PHY supports */ + linkmode_and(phydev->advertising, phydev->advertising, + phydev->supported); + + if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT, + phydev->advertising)) + adv |= ADVERTISE_1000XFULL; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, + phydev->advertising)) + adv |= ADVERTISE_1000XPAUSE; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, + phydev->advertising)) + adv |= ADVERTISE_1000XPSE_ASYM; + + return phy_modify_changed(phydev, MII_ADVERTISE, + ADVERTISE_1000XFULL | ADVERTISE_1000XPAUSE | + ADVERTISE_1000XHALF | ADVERTISE_1000XPSE_ASYM, + adv); +} + /** * genphy_config_eee_advert - disable unwanted eee mode advertisement * @phydev: target phy_device struct @@ -1715,6 +1749,54 @@ int __genphy_config_aneg(struct phy_device *phydev, bool changed) } EXPORT_SYMBOL(__genphy_config_aneg); +/** + * genphy_c37_config_aneg - restart auto-negotiation or write BMCR + * @phydev: target phy_device struct + * + * Description: If auto-negotiation is enabled, we configure the + * advertising, and then restart auto-negotiation. If it is not + * enabled, then we write the BMCR. This function is intended + * for use with Clause 37 1000Base-X mode. + */ +int genphy_c37_config_aneg(struct phy_device *phydev) +{ + int err, changed; + + if (phydev->autoneg != AUTONEG_ENABLE) + return genphy_setup_forced(phydev); + + err = phy_modify(phydev, MII_BMCR, BMCR_SPEED1000 | BMCR_SPEED100, + BMCR_SPEED1000); + if (err) + return err; + + changed = genphy_c37_config_advert(phydev); + if (changed < 0) /* error */ + return changed; + + if (!changed) { + /* Advertisement hasn't changed, but maybe aneg was never on to + * begin with? Or maybe phy was isolated? + */ + int ctl = phy_read(phydev, MII_BMCR); + + if (ctl < 0) + return ctl; + + if (!(ctl & BMCR_ANENABLE) || (ctl & BMCR_ISOLATE)) + changed = 1; /* do restart aneg */ + } + + /* Only restart aneg if we are advertising something different + * than we were before. + */ + if (changed > 0) + return genphy_restart_aneg(phydev); + + return 0; +} +EXPORT_SYMBOL(genphy_c37_config_aneg); + /** * genphy_aneg_done - return auto-negotiation status * @phydev: target phy_device struct @@ -1886,6 +1968,63 @@ int genphy_read_status(struct phy_device *phydev) } EXPORT_SYMBOL(genphy_read_status); +/** + * genphy_c37_read_status - check the link status and update current link state + * @phydev: target phy_device struct + * + * Description: Check the link, then figure out the current state + * by comparing what we advertise with what the link partner + * advertises. This function is for Clause 37 1000Base-X mode. + */ +int genphy_c37_read_status(struct phy_device *phydev) +{ + int lpa, err, old_link = phydev->link; + + /* Update the link, but return if there was an error */ + err = genphy_update_link(phydev); + if (err) + return err; + + /* why bother the PHY if nothing can have changed */ + if (phydev->autoneg == AUTONEG_ENABLE && old_link && phydev->link) + return 0; + + phydev->duplex = DUPLEX_UNKNOWN; + phydev->pause = 0; + phydev->asym_pause = 0; + + if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) { + lpa = phy_read(phydev, MII_LPA); + if (lpa < 0) + return lpa; + + linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + phydev->lp_advertising, lpa & LPA_LPACK); + linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT, + phydev->lp_advertising, lpa & LPA_1000XFULL); + linkmode_mod_bit(ETHTOOL_LINK_MODE_Pause_BIT, + phydev->lp_advertising, lpa & LPA_1000XPAUSE); + linkmode_mod_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, + phydev->lp_advertising, + lpa & LPA_1000XPAUSE_ASYM); + + phy_resolve_aneg_linkmode(phydev); + } else if (phydev->autoneg == AUTONEG_DISABLE) { + int bmcr = phy_read(phydev, MII_BMCR); + + if (bmcr < 0) + return bmcr; + + if (bmcr & BMCR_FULLDPLX) + phydev->duplex = DUPLEX_FULL; + else + phydev->duplex = DUPLEX_HALF; + } + + return 0; +} +EXPORT_SYMBOL(genphy_c37_read_status); + /** * genphy_soft_reset - software reset the PHY via BMCR_RESET bit * @phydev: target phy_device struct diff --git a/include/linux/phy.h b/include/linux/phy.h index 9a0e981df502..78436d58ce7c 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1106,6 +1106,10 @@ int genphy_read_mmd_unsupported(struct phy_device *phdev, int devad, int genphy_write_mmd_unsupported(struct phy_device *phdev, int devnum, u16 regnum, u16 val); +/* Clause 37 */ +int genphy_c37_config_aneg(struct phy_device *phydev); +int genphy_c37_read_status(struct phy_device *phydev); + /* Clause 45 PHY */ int genphy_c45_restart_aneg(struct phy_device *phydev); int genphy_c45_check_and_restart_aneg(struct phy_device *phydev, bool restart); -- cgit v1.2.3-71-gd317 From b9bcb95315febd09419ab870ddc7cb98a393f9d0 Mon Sep 17 00:00:00 2001 From: Tao Ren Date: Tue, 22 Oct 2019 11:31:08 -0700 Subject: net: phy: broadcom: add 1000Base-X support for BCM54616S The BCM54616S PHY cannot work properly in RGMII->1000Base-X mode, mainly because genphy functions are designed for copper links, and 1000Base-X (clause 37) auto negotiation needs to be handled differently. This patch enables 1000Base-X support for BCM54616S by customizing 3 driver callbacks, and it's verified to be working on Facebook CMM BMC platform (RGMII->1000Base-KX): - probe: probe callback detects PHY's operation mode based on INTERF_SEL[1:0] pins and 1000X/100FX selection bit in SerDES 100-FX Control register. - config_aneg: calls genphy_c37_config_aneg when the PHY is running in 1000Base-X mode; otherwise, genphy_config_aneg will be called. - read_status: calls genphy_c37_read_status when the PHY is running in 1000Base-X mode; otherwise, genphy_read_status will be called. Note: BCM54616S PHY can also be configured in RGMII->100Base-FX mode, and 100Base-FX support is not available as of now. Signed-off-by: Tao Ren Acked-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/broadcom.c | 57 ++++++++++++++++++++++++++++++++++++++++++---- include/linux/brcmphy.h | 10 ++++++-- 2 files changed, 61 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index 4313c74b4fd8..7d68b28bb893 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -359,9 +359,9 @@ static int bcm5482_config_init(struct phy_device *phydev) /* * Select 1000BASE-X register set (primary SerDes) */ - reg = bcm_phy_read_shadow(phydev, BCM5482_SHD_MODE); - bcm_phy_write_shadow(phydev, BCM5482_SHD_MODE, - reg | BCM5482_SHD_MODE_1000BX); + reg = bcm_phy_read_shadow(phydev, BCM54XX_SHD_MODE); + bcm_phy_write_shadow(phydev, BCM54XX_SHD_MODE, + reg | BCM54XX_SHD_MODE_1000BX); /* * LED1=ACTIVITYLED, LED3=LINKSPD[2] @@ -427,12 +427,47 @@ static int bcm5481_config_aneg(struct phy_device *phydev) return ret; } +static int bcm54616s_probe(struct phy_device *phydev) +{ + int val, intf_sel; + + val = bcm_phy_read_shadow(phydev, BCM54XX_SHD_MODE); + if (val < 0) + return val; + + /* The PHY is strapped in RGMII-fiber mode when INTERF_SEL[1:0] + * is 01b, and the link between PHY and its link partner can be + * either 1000Base-X or 100Base-FX. + * RGMII-1000Base-X is properly supported, but RGMII-100Base-FX + * support is still missing as of now. + */ + intf_sel = (val & BCM54XX_SHD_INTF_SEL_MASK) >> 1; + if (intf_sel == 1) { + val = bcm_phy_read_shadow(phydev, BCM54616S_SHD_100FX_CTRL); + if (val < 0) + return val; + + /* Bit 0 of the SerDes 100-FX Control register, when set + * to 1, sets the MII/RGMII -> 100BASE-FX configuration. + * When this bit is set to 0, it sets the GMII/RGMII -> + * 1000BASE-X configuration. + */ + if (!(val & BCM54616S_100FX_MODE)) + phydev->dev_flags |= PHY_BCM_FLAGS_MODE_1000BX; + } + + return 0; +} + static int bcm54616s_config_aneg(struct phy_device *phydev) { int ret; /* Aneg firsly. */ - ret = genphy_config_aneg(phydev); + if (phydev->dev_flags & PHY_BCM_FLAGS_MODE_1000BX) + ret = genphy_c37_config_aneg(phydev); + else + ret = genphy_config_aneg(phydev); /* Then we can set up the delay. */ bcm54xx_config_clock_delay(phydev); @@ -440,6 +475,18 @@ static int bcm54616s_config_aneg(struct phy_device *phydev) return ret; } +static int bcm54616s_read_status(struct phy_device *phydev) +{ + int err; + + if (phydev->dev_flags & PHY_BCM_FLAGS_MODE_1000BX) + err = genphy_c37_read_status(phydev); + else + err = genphy_read_status(phydev); + + return err; +} + static int brcm_phy_setbits(struct phy_device *phydev, int reg, int set) { int val; @@ -631,6 +678,8 @@ static struct phy_driver broadcom_drivers[] = { .config_aneg = bcm54616s_config_aneg, .ack_interrupt = bcm_phy_ack_intr, .config_intr = bcm_phy_config_intr, + .read_status = bcm54616s_read_status, + .probe = bcm54616s_probe, }, { .phy_id = PHY_ID_BCM5464, .phy_id_mask = 0xfffffff0, diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 6db2d9a6e503..b475e7f20d28 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -200,9 +200,15 @@ #define BCM5482_SHD_SSD 0x14 /* 10100: Secondary SerDes control */ #define BCM5482_SHD_SSD_LEDM 0x0008 /* SSD LED Mode enable */ #define BCM5482_SHD_SSD_EN 0x0001 /* SSD enable */ -#define BCM5482_SHD_MODE 0x1f /* 11111: Mode Control Register */ -#define BCM5482_SHD_MODE_1000BX 0x0001 /* Enable 1000BASE-X registers */ +/* 10011: SerDes 100-FX Control Register */ +#define BCM54616S_SHD_100FX_CTRL 0x13 +#define BCM54616S_100FX_MODE BIT(0) /* 100-FX SerDes Enable */ + +/* 11111: Mode Control Register */ +#define BCM54XX_SHD_MODE 0x1f +#define BCM54XX_SHD_INTF_SEL_MASK GENMASK(2, 1) /* INTERF_SEL[1:0] */ +#define BCM54XX_SHD_MODE_1000BX BIT(0) /* Enable 1000-X registers */ /* * EXPANSION SHADOW ACCESS REGISTERS. (PHY REG 0x15, 0x16, and 0x17) -- cgit v1.2.3-71-gd317 From 15fd552d186cb0df34b9d36a07dd6677c4da56bc Mon Sep 17 00:00:00 2001 From: Christian König Date: Tue, 3 Jul 2018 16:42:26 +0200 Subject: dma-buf: change DMA-buf locking convention v3 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch is a stripped down version of the locking changes necessary to support dynamic DMA-buf handling. It adds a dynamic flag for both importers as well as exporters so that drivers can choose if they want the reservation object locked or unlocked during mapping of attachments. For compatibility between drivers we cache the DMA-buf mapping during attaching an importer as soon as exporter/importer disagree on the dynamic handling. Issues and solutions we considered: - We can't change all existing drivers, and existing improters have strong opinions about which locks they're holding while calling dma_buf_attachment_map/unmap. Exporters also have strong opinions about which locks they can acquire in their ->map/unmap callbacks, levaing no room for change. The solution to avoid this was to move the actual map/unmap out from this call, into the attach/detach callbacks, and cache the mapping. This works because drivers don't call attach/detach from deep within their code callchains (like deep in memory management code called from cs/execbuf ioctl), but directly from the fd2handle implementation. - The caching has some troubles on some soc drivers, which set other modes than DMA_BIDIRECTIONAL. We can't have 2 incompatible mappings, and we can't re-create the mapping at _map time due to the above locking fun. We very carefuly step around that by only caching at attach time if the dynamic mode between importer/expoert mismatches. - There's been quite some discussion on dma-buf mappings which need active cache management, which would all break down when caching, plus we don't have explicit flush operations on the attachment side. The solution to this was to shrug and keep the current discrepancy between what the dma-buf docs claim and what implementations do, with the hope that the begin/end_cpu_access hooks are good enough and that all necessary flushing to keep device mappings consistent will be done there. v2: cleanup set_name merge, improve kerneldoc v3: update commit message, kerneldoc and cleanup _debug_show() Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/336788/ --- drivers/dma-buf/dma-buf.c | 118 +++++++++++++++++++++++++++++++++++++++------- include/linux/dma-buf.h | 63 ++++++++++++++++++++++--- 2 files changed, 158 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 433d91d710e4..0573879a222a 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -45,10 +45,10 @@ static char *dmabuffs_dname(struct dentry *dentry, char *buffer, int buflen) size_t ret = 0; dmabuf = dentry->d_fsdata; - mutex_lock(&dmabuf->lock); + dma_resv_lock(dmabuf->resv, NULL); if (dmabuf->name) ret = strlcpy(name, dmabuf->name, DMA_BUF_NAME_LEN); - mutex_unlock(&dmabuf->lock); + dma_resv_unlock(dmabuf->resv); return dynamic_dname(dentry, buffer, buflen, "/%s:%s", dentry->d_name.name, ret > 0 ? name : ""); @@ -334,7 +334,7 @@ static long dma_buf_set_name(struct dma_buf *dmabuf, const char __user *buf) if (IS_ERR(name)) return PTR_ERR(name); - mutex_lock(&dmabuf->lock); + dma_resv_lock(dmabuf->resv, NULL); if (!list_empty(&dmabuf->attachments)) { ret = -EBUSY; kfree(name); @@ -344,7 +344,7 @@ static long dma_buf_set_name(struct dma_buf *dmabuf, const char __user *buf) dmabuf->name = name; out_unlock: - mutex_unlock(&dmabuf->lock); + dma_resv_unlock(dmabuf->resv); return ret; } @@ -403,10 +403,10 @@ static void dma_buf_show_fdinfo(struct seq_file *m, struct file *file) /* Don't count the temporary reference taken inside procfs seq_show */ seq_printf(m, "count:\t%ld\n", file_count(dmabuf->file) - 1); seq_printf(m, "exp_name:\t%s\n", dmabuf->exp_name); - mutex_lock(&dmabuf->lock); + dma_resv_lock(dmabuf->resv, NULL); if (dmabuf->name) seq_printf(m, "name:\t%s\n", dmabuf->name); - mutex_unlock(&dmabuf->lock); + dma_resv_unlock(dmabuf->resv); } static const struct file_operations dma_buf_fops = { @@ -525,6 +525,10 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) return ERR_PTR(-EINVAL); } + if (WARN_ON(exp_info->ops->cache_sgt_mapping && + exp_info->ops->dynamic_mapping)) + return ERR_PTR(-EINVAL); + if (!try_module_get(exp_info->owner)) return ERR_PTR(-ENOENT); @@ -645,10 +649,11 @@ void dma_buf_put(struct dma_buf *dmabuf) EXPORT_SYMBOL_GPL(dma_buf_put); /** - * dma_buf_attach - Add the device to dma_buf's attachments list; optionally, + * dma_buf_dynamic_attach - Add the device to dma_buf's attachments list; optionally, * calls attach() of dma_buf_ops to allow device-specific attach functionality - * @dmabuf: [in] buffer to attach device to. - * @dev: [in] device to be attached. + * @dmabuf: [in] buffer to attach device to. + * @dev: [in] device to be attached. + * @dynamic_mapping: [in] calling convention for map/unmap * * Returns struct dma_buf_attachment pointer for this attachment. Attachments * must be cleaned up by calling dma_buf_detach(). @@ -662,8 +667,9 @@ EXPORT_SYMBOL_GPL(dma_buf_put); * accessible to @dev, and cannot be moved to a more suitable place. This is * indicated with the error code -EBUSY. */ -struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, - struct device *dev) +struct dma_buf_attachment * +dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev, + bool dynamic_mapping) { struct dma_buf_attachment *attach; int ret; @@ -677,6 +683,7 @@ struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, attach->dev = dev; attach->dmabuf = dmabuf; + attach->dynamic_mapping = dynamic_mapping; mutex_lock(&dmabuf->lock); @@ -685,16 +692,64 @@ struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, if (ret) goto err_attach; } + dma_resv_lock(dmabuf->resv, NULL); list_add(&attach->node, &dmabuf->attachments); + dma_resv_unlock(dmabuf->resv); mutex_unlock(&dmabuf->lock); + /* When either the importer or the exporter can't handle dynamic + * mappings we cache the mapping here to avoid issues with the + * reservation object lock. + */ + if (dma_buf_attachment_is_dynamic(attach) != + dma_buf_is_dynamic(dmabuf)) { + struct sg_table *sgt; + + if (dma_buf_is_dynamic(attach->dmabuf)) + dma_resv_lock(attach->dmabuf->resv, NULL); + + sgt = dmabuf->ops->map_dma_buf(attach, DMA_BIDIRECTIONAL); + if (!sgt) + sgt = ERR_PTR(-ENOMEM); + if (IS_ERR(sgt)) { + ret = PTR_ERR(sgt); + goto err_unlock; + } + if (dma_buf_is_dynamic(attach->dmabuf)) + dma_resv_unlock(attach->dmabuf->resv); + attach->sgt = sgt; + attach->dir = DMA_BIDIRECTIONAL; + } + return attach; err_attach: kfree(attach); mutex_unlock(&dmabuf->lock); return ERR_PTR(ret); + +err_unlock: + if (dma_buf_is_dynamic(attach->dmabuf)) + dma_resv_unlock(attach->dmabuf->resv); + + dma_buf_detach(dmabuf, attach); + return ERR_PTR(ret); +} +EXPORT_SYMBOL_GPL(dma_buf_dynamic_attach); + +/** + * dma_buf_attach - Wrapper for dma_buf_dynamic_attach + * @dmabuf: [in] buffer to attach device to. + * @dev: [in] device to be attached. + * + * Wrapper to call dma_buf_dynamic_attach() for drivers which still use a static + * mapping. + */ +struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, + struct device *dev) +{ + return dma_buf_dynamic_attach(dmabuf, dev, false); } EXPORT_SYMBOL_GPL(dma_buf_attach); @@ -711,11 +766,20 @@ void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach) if (WARN_ON(!dmabuf || !attach)) return; - if (attach->sgt) + if (attach->sgt) { + if (dma_buf_is_dynamic(attach->dmabuf)) + dma_resv_lock(attach->dmabuf->resv, NULL); + dmabuf->ops->unmap_dma_buf(attach, attach->sgt, attach->dir); + if (dma_buf_is_dynamic(attach->dmabuf)) + dma_resv_unlock(attach->dmabuf->resv); + } + mutex_lock(&dmabuf->lock); + dma_resv_lock(dmabuf->resv, NULL); list_del(&attach->node); + dma_resv_unlock(dmabuf->resv); if (dmabuf->ops->detach) dmabuf->ops->detach(dmabuf, attach); @@ -749,6 +813,9 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach, if (WARN_ON(!attach || !attach->dmabuf)) return ERR_PTR(-EINVAL); + if (dma_buf_attachment_is_dynamic(attach)) + dma_resv_assert_held(attach->dmabuf->resv); + if (attach->sgt) { /* * Two mappings with different directions for the same @@ -761,6 +828,9 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach, return attach->sgt; } + if (dma_buf_is_dynamic(attach->dmabuf)) + dma_resv_assert_held(attach->dmabuf->resv); + sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction); if (!sg_table) sg_table = ERR_PTR(-ENOMEM); @@ -793,9 +863,15 @@ void dma_buf_unmap_attachment(struct dma_buf_attachment *attach, if (WARN_ON(!attach || !attach->dmabuf || !sg_table)) return; + if (dma_buf_attachment_is_dynamic(attach)) + dma_resv_assert_held(attach->dmabuf->resv); + if (attach->sgt == sg_table) return; + if (dma_buf_is_dynamic(attach->dmabuf)) + dma_resv_assert_held(attach->dmabuf->resv); + attach->dmabuf->ops->unmap_dma_buf(attach, sg_table, direction); } EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment); @@ -1171,13 +1247,14 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused) "size", "flags", "mode", "count", "ino"); list_for_each_entry(buf_obj, &db_list.head, list_node) { + ret = mutex_lock_interruptible(&buf_obj->lock); + if (ret) + goto error_unlock_list; - if (ret) { - seq_puts(s, - "\tERROR locking buffer object: skipping\n"); - continue; - } + ret = dma_resv_lock_interruptible(buf_obj->resv, NULL); + if (ret) + goto error_unlock_buf; seq_printf(s, "%08zu\t%08x\t%08x\t%08ld\t%s\t%08lu\t%s\n", buf_obj->size, @@ -1223,6 +1300,7 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused) seq_printf(s, "\t%s\n", dev_name(attach_obj->dev)); attach_count++; } + dma_resv_unlock(buf_obj->resv); seq_printf(s, "Total %d devices attached\n\n", attach_count); @@ -1236,6 +1314,12 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused) mutex_unlock(&db_list.lock); return 0; + +error_unlock_buf: + mutex_unlock(&buf_obj->lock); +error_unlock_list: + mutex_unlock(&db_list.lock); + return ret; } DEFINE_SHOW_ATTRIBUTE(dma_buf_debug); diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index ec212cb27fdc..af73f835c51c 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -42,6 +42,18 @@ struct dma_buf_ops { */ bool cache_sgt_mapping; + /** + * @dynamic_mapping: + * + * If true the framework makes sure that the map/unmap_dma_buf + * callbacks are always called with the dma_resv object locked. + * + * If false the framework makes sure that the map/unmap_dma_buf + * callbacks are always called without the dma_resv object locked. + * Mutual exclusive with @cache_sgt_mapping. + */ + bool dynamic_mapping; + /** * @attach: * @@ -109,6 +121,9 @@ struct dma_buf_ops { * any other kind of sharing that the exporter might wish to make * available to buffer-users. * + * This is always called with the dmabuf->resv object locked when + * the dynamic_mapping flag is true. + * * Returns: * * A &sg_table scatter list of or the backing storage of the DMA buffer, @@ -267,14 +282,16 @@ struct dma_buf_ops { * struct dma_buf - shared buffer object * @size: size of the buffer * @file: file pointer used for sharing buffers across, and for refcounting. - * @attachments: list of dma_buf_attachment that denotes all devices attached. + * @attachments: list of dma_buf_attachment that denotes all devices attached, + * protected by dma_resv lock. * @ops: dma_buf_ops associated with this buffer object. * @lock: used internally to serialize list manipulation, attach/detach and - * vmap/unmap, and accesses to name + * vmap/unmap * @vmapping_counter: used internally to refcnt the vmaps * @vmap_ptr: the current vmap ptr if vmapping_counter > 0 * @exp_name: name of the exporter; useful for debugging. - * @name: userspace-provided name; useful for accounting and debugging. + * @name: userspace-provided name; useful for accounting and debugging, + * protected by @resv. * @owner: pointer to exporter module; used for refcounting when exporter is a * kernel module. * @list_node: node for dma_buf accounting and debugging. @@ -323,10 +340,12 @@ struct dma_buf { * struct dma_buf_attachment - holds device-buffer attachment data * @dmabuf: buffer for this attachment. * @dev: device attached to the buffer. - * @node: list of dma_buf_attachment. + * @node: list of dma_buf_attachment, protected by dma_resv lock of the dmabuf. * @sgt: cached mapping. * @dir: direction of cached mapping. * @priv: exporter specific attachment data. + * @dynamic_mapping: true if dma_buf_map/unmap_attachment() is called with the + * dma_resv lock held. * * This structure holds the attachment information between the dma_buf buffer * and its user device(s). The list contains one attachment struct per device @@ -343,6 +362,7 @@ struct dma_buf_attachment { struct list_head node; struct sg_table *sgt; enum dma_data_direction dir; + bool dynamic_mapping; void *priv; }; @@ -394,10 +414,40 @@ static inline void get_dma_buf(struct dma_buf *dmabuf) get_file(dmabuf->file); } +/** + * dma_buf_is_dynamic - check if a DMA-buf uses dynamic mappings. + * @dmabuf: the DMA-buf to check + * + * Returns true if a DMA-buf exporter wants to be called with the dma_resv + * locked for the map/unmap callbacks, false if it doesn't wants to be called + * with the lock held. + */ +static inline bool dma_buf_is_dynamic(struct dma_buf *dmabuf) +{ + return dmabuf->ops->dynamic_mapping; +} + +/** + * dma_buf_attachment_is_dynamic - check if a DMA-buf attachment uses dynamic + * mappinsg + * @attach: the DMA-buf attachment to check + * + * Returns true if a DMA-buf importer wants to call the map/unmap functions with + * the dma_resv lock held. + */ +static inline bool +dma_buf_attachment_is_dynamic(struct dma_buf_attachment *attach) +{ + return attach->dynamic_mapping; +} + struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, - struct device *dev); + struct device *dev); +struct dma_buf_attachment * +dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev, + bool dynamic_mapping); void dma_buf_detach(struct dma_buf *dmabuf, - struct dma_buf_attachment *dmabuf_attach); + struct dma_buf_attachment *attach); struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info); @@ -409,6 +459,7 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *, enum dma_data_direction); void dma_buf_unmap_attachment(struct dma_buf_attachment *, struct sg_table *, enum dma_data_direction); +void dma_buf_move_notify(struct dma_buf *dma_buf); int dma_buf_begin_cpu_access(struct dma_buf *dma_buf, enum dma_data_direction dir); int dma_buf_end_cpu_access(struct dma_buf *dma_buf, -- cgit v1.2.3-71-gd317 From c512995ce9dc653111d782b130e600802da52b5f Mon Sep 17 00:00:00 2001 From: Josef Friedl Date: Tue, 10 Sep 2019 09:04:41 +0200 Subject: rtc: mt6397: move some common definitions into rtc.h move code to separate header-file to reuse definitions later in poweroff-driver (drivers/power/reset/mt6323-poweroff.c) Suggested-by: Frank Wunderlich Signed-off-by: Josef Friedl Signed-off-by: Frank Wunderlich Acked-by: Alexandre Belloni Signed-off-by: Lee Jones --- drivers/rtc/rtc-mt6397.c | 55 +------------------------------- include/linux/mfd/mt6397/rtc.h | 71 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 72 insertions(+), 54 deletions(-) create mode 100644 include/linux/mfd/mt6397/rtc.h (limited to 'include/linux') diff --git a/drivers/rtc/rtc-mt6397.c b/drivers/rtc/rtc-mt6397.c index 704229eb0cac..5f76c83e3e9a 100644 --- a/drivers/rtc/rtc-mt6397.c +++ b/drivers/rtc/rtc-mt6397.c @@ -9,60 +9,7 @@ #include #include #include -#include -#include -#include -#include -#include -#include - -#define RTC_BBPU 0x0000 -#define RTC_BBPU_CBUSY BIT(6) - -#define RTC_WRTGR 0x003c - -#define RTC_IRQ_STA 0x0002 -#define RTC_IRQ_STA_AL BIT(0) -#define RTC_IRQ_STA_LP BIT(3) - -#define RTC_IRQ_EN 0x0004 -#define RTC_IRQ_EN_AL BIT(0) -#define RTC_IRQ_EN_ONESHOT BIT(2) -#define RTC_IRQ_EN_LP BIT(3) -#define RTC_IRQ_EN_ONESHOT_AL (RTC_IRQ_EN_ONESHOT | RTC_IRQ_EN_AL) - -#define RTC_AL_MASK 0x0008 -#define RTC_AL_MASK_DOW BIT(4) - -#define RTC_TC_SEC 0x000a -/* Min, Hour, Dom... register offset to RTC_TC_SEC */ -#define RTC_OFFSET_SEC 0 -#define RTC_OFFSET_MIN 1 -#define RTC_OFFSET_HOUR 2 -#define RTC_OFFSET_DOM 3 -#define RTC_OFFSET_DOW 4 -#define RTC_OFFSET_MTH 5 -#define RTC_OFFSET_YEAR 6 -#define RTC_OFFSET_COUNT 7 - -#define RTC_AL_SEC 0x0018 - -#define RTC_PDN2 0x002e -#define RTC_PDN2_PWRON_ALARM BIT(4) - -#define RTC_MIN_YEAR 1968 -#define RTC_BASE_YEAR 1900 -#define RTC_NUM_YEARS 128 -#define RTC_MIN_YEAR_OFFSET (RTC_MIN_YEAR - RTC_BASE_YEAR) - -struct mt6397_rtc { - struct device *dev; - struct rtc_device *rtc_dev; - struct mutex lock; - struct regmap *regmap; - int irq; - u32 addr_base; -}; +#include static int mtk_rtc_write_trigger(struct mt6397_rtc *rtc) { diff --git a/include/linux/mfd/mt6397/rtc.h b/include/linux/mfd/mt6397/rtc.h new file mode 100644 index 000000000000..f84b9163c0ee --- /dev/null +++ b/include/linux/mfd/mt6397/rtc.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2014-2019 MediaTek Inc. + * + * Author: Tianping.Fang + * Sean Wang + */ + +#ifndef _LINUX_MFD_MT6397_RTC_H_ +#define _LINUX_MFD_MT6397_RTC_H_ + +#include +#include +#include +#include + +#define RTC_BBPU 0x0000 +#define RTC_BBPU_CBUSY BIT(6) +#define RTC_BBPU_KEY (0x43 << 8) + +#define RTC_WRTGR 0x003c + +#define RTC_IRQ_STA 0x0002 +#define RTC_IRQ_STA_AL BIT(0) +#define RTC_IRQ_STA_LP BIT(3) + +#define RTC_IRQ_EN 0x0004 +#define RTC_IRQ_EN_AL BIT(0) +#define RTC_IRQ_EN_ONESHOT BIT(2) +#define RTC_IRQ_EN_LP BIT(3) +#define RTC_IRQ_EN_ONESHOT_AL (RTC_IRQ_EN_ONESHOT | RTC_IRQ_EN_AL) + +#define RTC_AL_MASK 0x0008 +#define RTC_AL_MASK_DOW BIT(4) + +#define RTC_TC_SEC 0x000a +/* Min, Hour, Dom... register offset to RTC_TC_SEC */ +#define RTC_OFFSET_SEC 0 +#define RTC_OFFSET_MIN 1 +#define RTC_OFFSET_HOUR 2 +#define RTC_OFFSET_DOM 3 +#define RTC_OFFSET_DOW 4 +#define RTC_OFFSET_MTH 5 +#define RTC_OFFSET_YEAR 6 +#define RTC_OFFSET_COUNT 7 + +#define RTC_AL_SEC 0x0018 + +#define RTC_PDN2 0x002e +#define RTC_PDN2_PWRON_ALARM BIT(4) + +#define RTC_MIN_YEAR 1968 +#define RTC_BASE_YEAR 1900 +#define RTC_NUM_YEARS 128 +#define RTC_MIN_YEAR_OFFSET (RTC_MIN_YEAR - RTC_BASE_YEAR) + +#define MTK_RTC_POLL_DELAY_US 10 +#define MTK_RTC_POLL_TIMEOUT (jiffies_to_usecs(HZ)) + +struct mt6397_rtc { + struct device *dev; + struct rtc_device *rtc_dev; + + /* Protect register access from multiple tasks */ + struct mutex lock; + struct regmap *regmap; + int irq; + u32 addr_base; +}; + +#endif /* _LINUX_MFD_MT6397_RTC_H_ */ -- cgit v1.2.3-71-gd317 From a48108c0c20f02485b8cc3ca83652a55a0f5e47f Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Tue, 22 Oct 2019 16:51:37 +0200 Subject: reset: improve of_xlate documentation Mention of_reset_simple_xlate as the default if of_xlate is not set. Signed-off-by: Philipp Zabel --- drivers/reset/core.c | 6 ++++-- include/linux/reset-controller.h | 3 ++- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/reset/core.c b/drivers/reset/core.c index 2badff33a0db..329c78599a02 100644 --- a/drivers/reset/core.c +++ b/drivers/reset/core.c @@ -78,8 +78,10 @@ static const char *rcdev_name(struct reset_controller_dev *rcdev) * @reset_spec: reset line specifier as found in the device tree * @flags: a flags pointer to fill in (optional) * - * This simple translation function should be used for reset controllers - * with 1:1 mapping, where reset lines can be indexed by number without gaps. + * This static translation function is used by default if of_xlate in + * :c:type:`reset_controller_dev` is not set. It is useful for all reset + * controllers with 1:1 mapping, where reset lines can be indexed by number + * without gaps. */ static int of_reset_simple_xlate(struct reset_controller_dev *rcdev, const struct of_phandle_args *reset_spec) diff --git a/include/linux/reset-controller.h b/include/linux/reset-controller.h index 9326d671b6e6..8d35753d419e 100644 --- a/include/linux/reset-controller.h +++ b/include/linux/reset-controller.h @@ -62,7 +62,8 @@ struct reset_control_lookup { * @of_node: corresponding device tree node as phandle target * @of_reset_n_cells: number of cells in reset line specifiers * @of_xlate: translation function to translate from specifier as found in the - * device tree to id as given to the reset control ops + * device tree to id as given to the reset control ops, defaults + * to :c:func:`of_reset_simple_xlate`. * @nr_resets: number of reset controls in this reset controller device */ struct reset_controller_dev { -- cgit v1.2.3-71-gd317 From c2ffa00ad6152ad54940f942fc316b9c83d5e6f9 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Tue, 22 Oct 2019 16:53:25 +0200 Subject: reset: document (devm_)reset_control_get_optional variants Add kerneldoc comments for the optional reset_control_get variants. Signed-off-by: Philipp Zabel --- include/linux/reset.h | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) (limited to 'include/linux') diff --git a/include/linux/reset.h b/include/linux/reset.h index e7793fc0fa93..bf7c7f188406 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -203,12 +203,34 @@ static inline struct reset_control *reset_control_get_shared( return __reset_control_get(dev, id, 0, true, false, false); } +/** + * reset_control_get_optional_exclusive - optional reset_control_get_exclusive() + * @dev: device to be reset by the controller + * @id: reset line name + * + * Optional variant of reset_control_get_exclusive(). If the requested reset + * is not specified in the device tree, this function returns NULL instead of + * an error. + * + * See reset_control_get_exclusive() for more information. + */ static inline struct reset_control *reset_control_get_optional_exclusive( struct device *dev, const char *id) { return __reset_control_get(dev, id, 0, false, true, true); } +/** + * reset_control_get_optional_shared - optional reset_control_get_shared() + * @dev: device to be reset by the controller + * @id: reset line name + * + * Optional variant of reset_control_get_shared(). If the requested reset + * is not specified in the device tree, this function returns NULL instead of + * an error. + * + * See reset_control_get_shared() for more information. + */ static inline struct reset_control *reset_control_get_optional_shared( struct device *dev, const char *id) { @@ -354,12 +376,36 @@ static inline struct reset_control *devm_reset_control_get_shared( return __devm_reset_control_get(dev, id, 0, true, false, false); } +/** + * devm_reset_control_get_optional_exclusive - resource managed + * reset_control_get_optional_exclusive() + * @dev: device to be reset by the controller + * @id: reset line name + * + * Managed reset_control_get_optional_exclusive(). For reset controllers + * returned from this function, reset_control_put() is called automatically on + * driver detach. + * + * See reset_control_get_optional_exclusive() for more information. + */ static inline struct reset_control *devm_reset_control_get_optional_exclusive( struct device *dev, const char *id) { return __devm_reset_control_get(dev, id, 0, false, true, true); } +/** + * devm_reset_control_get_optional_shared - resource managed + * reset_control_get_optional_shared() + * @dev: device to be reset by the controller + * @id: reset line name + * + * Managed reset_control_get_optional_shared(). For reset controllers returned + * from this function, reset_control_put() is called automatically on driver + * detach. + * + * See reset_control_get_optional_shared() for more information. + */ static inline struct reset_control *devm_reset_control_get_optional_shared( struct device *dev, const char *id) { -- cgit v1.2.3-71-gd317 From b84dfe1af54053e0aedb14cd26307859aa1df35f Mon Sep 17 00:00:00 2001 From: Eugen Hristev Date: Wed, 23 Oct 2019 12:40:14 +0000 Subject: i2c: add support for filters optional properties i2c-digital-filter-width-ns: This optional timing property specifies the width of the spikes on the i2c lines (in ns) that can be filtered out by built-in digital filters which are embedded in some i2c controllers. i2c-analog-filter-cutoff-frequency: This optional timing property specifies the cutoff frequency of a low-pass analog filter built-in i2c controllers. This low pass filter is used to filter out high frequency noise on the i2c lines. Specified in Hz. Include these properties in the timings structure and read them as integers. Signed-off-by: Eugen Hristev Acked-by: Ludovic Desroches Reviewed-by: Peter Rosin Signed-off-by: Wolfram Sang --- drivers/i2c/i2c-core-base.c | 6 ++++++ include/linux/i2c.h | 6 ++++++ 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 5f6a4985f2bc..6a5183cffdfc 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -1656,6 +1656,12 @@ void i2c_parse_fw_timings(struct device *dev, struct i2c_timings *t, bool use_de t->sda_fall_ns = t->scl_fall_ns; device_property_read_u32(dev, "i2c-sda-hold-time-ns", &t->sda_hold_ns); + + device_property_read_u32(dev, "i2c-digital-filter-width-ns", + &t->digital_filter_width_ns); + + device_property_read_u32(dev, "i2c-analog-filter-cutoff-frequency", + &t->analog_filter_cutoff_freq_hz); } EXPORT_SYMBOL_GPL(i2c_parse_fw_timings); diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 1361637c369d..aaf57d9b41db 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -575,6 +575,10 @@ struct i2c_lock_operations { * @scl_int_delay_ns: time IP core additionally needs to setup SCL in ns * @sda_fall_ns: time SDA signal takes to fall in ns; t(f) in the I2C specification * @sda_hold_ns: time IP core additionally needs to hold SDA in ns + * @digital_filter_width_ns: width in ns of spikes on i2c lines that the IP core + * digital filter can filter out + * @analog_filter_cutoff_freq_hz: threshold frequency for the low pass IP core + * analog filter */ struct i2c_timings { u32 bus_freq_hz; @@ -583,6 +587,8 @@ struct i2c_timings { u32 scl_int_delay_ns; u32 sda_fall_ns; u32 sda_hold_ns; + u32 digital_filter_width_ns; + u32 analog_filter_cutoff_freq_hz; }; /** -- cgit v1.2.3-71-gd317 From 26ed19adbab16410460bd8b90ccc7430229a0b4a Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 18 Jun 2019 01:21:23 +0900 Subject: libfdt: reduce the number of headers included from libfdt_env.h Currently, libfdt_env.h includes just for INT_MAX. pulls in a lots of broat. Thanks to commit 54d50897d544 ("linux/kernel.h: split *_MAX and *_MIN macros into "), can be replaced with . This saves including dozens of headers. Signed-off-by: Masahiro Yamada Signed-off-by: Rob Herring --- include/linux/libfdt_env.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libfdt_env.h b/include/linux/libfdt_env.h index edb0f0c30904..2231eb855e8f 100644 --- a/include/linux/libfdt_env.h +++ b/include/linux/libfdt_env.h @@ -2,7 +2,7 @@ #ifndef LIBFDT_ENV_H #define LIBFDT_ENV_H -#include /* For INT_MAX */ +#include /* For INT_MAX */ #include #include -- cgit v1.2.3-71-gd317 From 3820729160440158a014add69cc0d371061a96b2 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 24 Oct 2019 17:18:11 -0700 Subject: bpf: Prepare btf_ctx_access for non raw_tp use case This patch makes a few changes to btf_ctx_access() to prepare it for non raw_tp use case where the attach_btf_id is not necessary a BTF_KIND_TYPEDEF. It moves the "btf_trace_" prefix check and typedef-follow logic to a new function "check_attach_btf_id()" which is called only once during bpf_check(). btf_ctx_access() only operates on a BTF_KIND_FUNC_PROTO type now. That should also be more efficient since it is done only one instead of every-time check_ctx_access() is called. "check_attach_btf_id()" needs to find the func_proto type from the attach_btf_id. It needs to store the result into the newly added prog->aux->attach_func_proto. func_proto btf type has no name, so a proper name should be stored into "attach_func_name" also. v2: - Move the "btf_trace_" check to an earlier verifier phase (Alexei) Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20191025001811.1718491-1-kafai@fb.com --- include/linux/bpf.h | 5 ++++ include/linux/btf.h | 31 ++++++++++++++++++++ kernel/bpf/btf.c | 73 +++++++++--------------------------------------- kernel/bpf/syscall.c | 4 +-- kernel/bpf/verifier.c | 52 +++++++++++++++++++++++++++++++++- kernel/trace/bpf_trace.c | 2 ++ 6 files changed, 103 insertions(+), 64 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2c2c29b49845..171be30fe0ae 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -392,6 +392,11 @@ struct bpf_prog_aux { u32 attach_btf_id; /* in-kernel BTF type id to attach to */ bool verifier_zext; /* Zero extensions has been inserted by verifier. */ bool offload_requested; + bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ + /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ + const struct btf_type *attach_func_proto; + /* function name for valid attach_btf_id */ + const char *attach_func_name; struct bpf_prog **func; void *jit_data; /* JIT specific data. arch dependent */ struct latch_tree_node ksym_tnode; diff --git a/include/linux/btf.h b/include/linux/btf.h index 55d43bc856be..9dee00859c5f 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -5,6 +5,7 @@ #define _LINUX_BTF_H 1 #include +#include struct btf; struct btf_member; @@ -53,6 +54,36 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t); bool btf_type_is_void(const struct btf_type *t); +static inline bool btf_type_is_ptr(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_PTR; +} + +static inline bool btf_type_is_int(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_INT; +} + +static inline bool btf_type_is_enum(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM; +} + +static inline bool btf_type_is_typedef(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF; +} + +static inline bool btf_type_is_func(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC; +} + +static inline bool btf_type_is_func_proto(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC_PROTO; +} + #ifdef CONFIG_BPF_SYSCALL const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); const char *btf_name_by_offset(const struct btf *btf, u32 offset); diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index f7557af39756..128d89601d73 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -336,16 +336,6 @@ static bool btf_type_is_fwd(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_FWD; } -static bool btf_type_is_func(const struct btf_type *t) -{ - return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC; -} - -static bool btf_type_is_func_proto(const struct btf_type *t) -{ - return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC_PROTO; -} - static bool btf_type_nosize(const struct btf_type *t) { return btf_type_is_void(t) || btf_type_is_fwd(t) || @@ -377,16 +367,6 @@ static bool btf_type_is_array(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY; } -static bool btf_type_is_ptr(const struct btf_type *t) -{ - return BTF_INFO_KIND(t->info) == BTF_KIND_PTR; -} - -static bool btf_type_is_int(const struct btf_type *t) -{ - return BTF_INFO_KIND(t->info) == BTF_KIND_INT; -} - static bool btf_type_is_var(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_VAR; @@ -3442,54 +3422,27 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { + const struct btf_type *t = prog->aux->attach_func_proto; + const char *tname = prog->aux->attach_func_name; struct bpf_verifier_log *log = info->log; - u32 btf_id = prog->aux->attach_btf_id; const struct btf_param *args; - const struct btf_type *t; - const char prefix[] = "btf_trace_"; - const char *tname; u32 nr_args, arg; - if (!btf_id) - return true; - - if (IS_ERR(btf_vmlinux)) { - bpf_log(log, "btf_vmlinux is malformed\n"); - return false; - } - - t = btf_type_by_id(btf_vmlinux, btf_id); - if (!t || BTF_INFO_KIND(t->info) != BTF_KIND_TYPEDEF) { - bpf_log(log, "btf_id is invalid\n"); - return false; - } - - tname = __btf_name_by_offset(btf_vmlinux, t->name_off); - if (strncmp(prefix, tname, sizeof(prefix) - 1)) { - bpf_log(log, "btf_id points to wrong type name %s\n", tname); - return false; - } - tname += sizeof(prefix) - 1; - - t = btf_type_by_id(btf_vmlinux, t->type); - if (!btf_type_is_ptr(t)) - return false; - t = btf_type_by_id(btf_vmlinux, t->type); - if (!btf_type_is_func_proto(t)) - return false; - if (off % 8) { - bpf_log(log, "raw_tp '%s' offset %d is not multiple of 8\n", + bpf_log(log, "func '%s' offset %d is not multiple of 8\n", tname, off); return false; } arg = off / 8; args = (const struct btf_param *)(t + 1); - /* skip first 'void *__data' argument in btf_trace_##name typedef */ - args++; - nr_args = btf_type_vlen(t) - 1; + nr_args = btf_type_vlen(t); + if (prog->aux->attach_btf_trace) { + /* skip first 'void *__data' argument in btf_trace_##name typedef */ + args++; + nr_args--; + } if (arg >= nr_args) { - bpf_log(log, "raw_tp '%s' doesn't have %d-th argument\n", + bpf_log(log, "func '%s' doesn't have %d-th argument\n", tname, arg); return false; } @@ -3503,7 +3456,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, return true; if (!btf_type_is_ptr(t)) { bpf_log(log, - "raw_tp '%s' arg%d '%s' has type %s. Only pointer access is allowed\n", + "func '%s' arg%d '%s' has type %s. Only pointer access is allowed\n", tname, arg, __btf_name_by_offset(btf_vmlinux, t->name_off), btf_kind_str[BTF_INFO_KIND(t->info)]); @@ -3526,11 +3479,11 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, t = btf_type_by_id(btf_vmlinux, t->type); if (!btf_type_is_struct(t)) { bpf_log(log, - "raw_tp '%s' arg%d type %s is not a struct\n", + "func '%s' arg%d type %s is not a struct\n", tname, arg, btf_kind_str[BTF_INFO_KIND(t->info)]); return false; } - bpf_log(log, "raw_tp '%s' arg%d has btf_id %d type %s '%s'\n", + bpf_log(log, "func '%s' arg%d has btf_id %d type %s '%s'\n", tname, arg, info->btf_id, btf_kind_str[BTF_INFO_KIND(t->info)], __btf_name_by_offset(btf_vmlinux, t->name_off)); return true; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 16ea3c0db4f6..ff5225759553 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1848,9 +1848,7 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) goto out_put_prog; } /* raw_tp name is taken from type name instead */ - tp_name = kernel_type_name(prog->aux->attach_btf_id); - /* skip the prefix */ - tp_name += sizeof("btf_trace_") - 1; + tp_name = prog->aux->attach_func_name; } else { if (strncpy_from_user(buf, u64_to_user_ptr(attr->raw_tracepoint.name), diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 556e82f8869b..c59778c0fc4d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -9372,6 +9372,52 @@ static void print_verification_stats(struct bpf_verifier_env *env) env->peak_states, env->longest_mark_read_walk); } +static int check_attach_btf_id(struct bpf_verifier_env *env) +{ + struct bpf_prog *prog = env->prog; + u32 btf_id = prog->aux->attach_btf_id; + const struct btf_type *t; + const char *tname; + + if (prog->type == BPF_PROG_TYPE_RAW_TRACEPOINT && btf_id) { + const char prefix[] = "btf_trace_"; + + t = btf_type_by_id(btf_vmlinux, btf_id); + if (!t) { + verbose(env, "attach_btf_id %u is invalid\n", btf_id); + return -EINVAL; + } + if (!btf_type_is_typedef(t)) { + verbose(env, "attach_btf_id %u is not a typedef\n", + btf_id); + return -EINVAL; + } + tname = btf_name_by_offset(btf_vmlinux, t->name_off); + if (!tname || strncmp(prefix, tname, sizeof(prefix) - 1)) { + verbose(env, "attach_btf_id %u points to wrong type name %s\n", + btf_id, tname); + return -EINVAL; + } + tname += sizeof(prefix) - 1; + t = btf_type_by_id(btf_vmlinux, t->type); + if (!btf_type_is_ptr(t)) + /* should never happen in valid vmlinux build */ + return -EINVAL; + t = btf_type_by_id(btf_vmlinux, t->type); + if (!btf_type_is_func_proto(t)) + /* should never happen in valid vmlinux build */ + return -EINVAL; + + /* remember two read only pointers that are valid for + * the life time of the kernel + */ + prog->aux->attach_func_name = tname; + prog->aux->attach_func_proto = t; + prog->aux->attach_btf_trace = true; + } + return 0; +} + int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, union bpf_attr __user *uattr) { @@ -9435,9 +9481,13 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, /* Either gcc or pahole or kernel are broken. */ verbose(env, "in-kernel BTF is malformed\n"); ret = PTR_ERR(btf_vmlinux); - goto err_unlock; + goto skip_full_check; } + ret = check_attach_btf_id(env); + if (ret) + goto skip_full_check; + env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT); if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) env->strict_alignment = true; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index c3240898cc44..571c25d60710 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1080,6 +1080,8 @@ static bool raw_tp_prog_is_valid_access(int off, int size, return false; if (off % size != 0) return false; + if (!prog->aux->attach_btf_id) + return true; return btf_ctx_access(off, size, type, prog, info); } -- cgit v1.2.3-71-gd317 From a69b0e855d3fd278ff6f09a23e1edf929538e304 Mon Sep 17 00:00:00 2001 From: "Andrew F. Davis" Date: Mon, 21 Oct 2019 19:03:06 +0000 Subject: dma-buf: Add dma-buf heaps framework This framework allows a unified userspace interface for dma-buf exporters, allowing userland to allocate specific types of memory for use in dma-buf sharing. Each heap is given its own device node, which a user can allocate a dma-buf fd from using the DMA_HEAP_IOC_ALLOC. This code is an evoluiton of the Android ION implementation, and a big thanks is due to its authors/maintainers over time for their effort: Rebecca Schultz Zavin, Colin Cross, Benjamin Gaignard, Laura Abbott, and many other contributors! Cc: Laura Abbott Cc: Benjamin Gaignard Cc: Sumit Semwal Cc: Liam Mark Cc: Pratik Patel Cc: Brian Starkey Cc: Vincent Donnefort Cc: Sudipto Paul Cc: Andrew F. Davis Cc: Christoph Hellwig Cc: Chenbo Feng Cc: Alistair Strachan Cc: Hridya Valsaraju Cc: Hillf Danton Cc: dri-devel@lists.freedesktop.org Reviewed-by: Benjamin Gaignard Reviewed-by: Brian Starkey Acked-by: Laura Abbott Tested-by: Ayan Kumar Halder Signed-off-by: Andrew F. Davis Signed-off-by: John Stultz Signed-off-by: Sumit Semwal Link: https://patchwork.freedesktop.org/patch/msgid/20191021190310.85221-2-john.stultz@linaro.org --- MAINTAINERS | 18 +++ drivers/dma-buf/Kconfig | 9 ++ drivers/dma-buf/Makefile | 1 + drivers/dma-buf/dma-heap.c | 269 ++++++++++++++++++++++++++++++++++++++++++ include/linux/dma-heap.h | 59 +++++++++ include/uapi/linux/dma-heap.h | 55 +++++++++ 6 files changed, 411 insertions(+) create mode 100644 drivers/dma-buf/dma-heap.c create mode 100644 include/linux/dma-heap.h create mode 100644 include/uapi/linux/dma-heap.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index b63c291ad029..5f39067caa7c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4942,6 +4942,24 @@ F: include/linux/*fence.h F: Documentation/driver-api/dma-buf.rst T: git git://anongit.freedesktop.org/drm/drm-misc +DMA-BUF HEAPS FRAMEWORK +M: Sumit Semwal +R: Andrew F. Davis +R: Benjamin Gaignard +R: Liam Mark +R: Laura Abbott +R: Brian Starkey +R: John Stultz +S: Maintained +L: linux-media@vger.kernel.org +L: dri-devel@lists.freedesktop.org +L: linaro-mm-sig@lists.linaro.org (moderated for non-subscribers) +F: include/uapi/linux/dma-heap.h +F: include/linux/dma-heap.h +F: drivers/dma-buf/dma-heap.c +F: drivers/dma-buf/heaps/* +T: git git://anongit.freedesktop.org/drm/drm-misc + DMA GENERIC OFFLOAD ENGINE SUBSYSTEM M: Vinod Koul L: dmaengine@vger.kernel.org diff --git a/drivers/dma-buf/Kconfig b/drivers/dma-buf/Kconfig index a23b6752d11a..bffa58fc3e6e 100644 --- a/drivers/dma-buf/Kconfig +++ b/drivers/dma-buf/Kconfig @@ -44,4 +44,13 @@ config DMABUF_SELFTESTS default n depends on DMA_SHARED_BUFFER +menuconfig DMABUF_HEAPS + bool "DMA-BUF Userland Memory Heaps" + select DMA_SHARED_BUFFER + help + Choose this option to enable the DMA-BUF userland memory heaps. + This options creates per heap chardevs in /dev/dma_heap/ which + allows userspace to allocate dma-bufs that can be shared + between drivers. + endmenu diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile index 03479da06422..caee5eb3d351 100644 --- a/drivers/dma-buf/Makefile +++ b/drivers/dma-buf/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only obj-y := dma-buf.o dma-fence.o dma-fence-array.o dma-fence-chain.o \ dma-resv.o seqno-fence.o +obj-$(CONFIG_DMABUF_HEAPS) += dma-heap.o obj-$(CONFIG_SYNC_FILE) += sync_file.o obj-$(CONFIG_SW_SYNC) += sw_sync.o sync_debug.o obj-$(CONFIG_UDMABUF) += udmabuf.o diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c new file mode 100644 index 000000000000..9a41b73e54b4 --- /dev/null +++ b/drivers/dma-buf/dma-heap.c @@ -0,0 +1,269 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Framework for userspace DMA-BUF allocations + * + * Copyright (C) 2011 Google, Inc. + * Copyright (C) 2019 Linaro Ltd. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define DEVNAME "dma_heap" + +#define NUM_HEAP_MINORS 128 + +/** + * struct dma_heap - represents a dmabuf heap in the system + * @name: used for debugging/device-node name + * @ops: ops struct for this heap + * @minor minor number of this heap device + * @heap_devt heap device node + * @heap_cdev heap char device + * + * Represents a heap of memory from which buffers can be made. + */ +struct dma_heap { + const char *name; + const struct dma_heap_ops *ops; + void *priv; + unsigned int minor; + dev_t heap_devt; + struct list_head list; + struct cdev heap_cdev; +}; + +static LIST_HEAD(heap_list); +static DEFINE_MUTEX(heap_list_lock); +static dev_t dma_heap_devt; +static struct class *dma_heap_class; +static DEFINE_XARRAY_ALLOC(dma_heap_minors); + +static int dma_heap_buffer_alloc(struct dma_heap *heap, size_t len, + unsigned int fd_flags, + unsigned int heap_flags) +{ + /* + * Allocations from all heaps have to begin + * and end on page boundaries. + */ + len = PAGE_ALIGN(len); + if (!len) + return -EINVAL; + + return heap->ops->allocate(heap, len, fd_flags, heap_flags); +} + +static int dma_heap_open(struct inode *inode, struct file *file) +{ + struct dma_heap *heap; + + heap = xa_load(&dma_heap_minors, iminor(inode)); + if (!heap) { + pr_err("dma_heap: minor %d unknown.\n", iminor(inode)); + return -ENODEV; + } + + /* instance data as context */ + file->private_data = heap; + nonseekable_open(inode, file); + + return 0; +} + +static long dma_heap_ioctl_allocate(struct file *file, unsigned long arg) +{ + struct dma_heap_allocation_data heap_allocation; + struct dma_heap *heap = file->private_data; + int fd; + + if (copy_from_user(&heap_allocation, (void __user *)arg, + sizeof(heap_allocation))) + return -EFAULT; + + if (heap_allocation.fd || + heap_allocation.reserved0 || + heap_allocation.reserved1) { + pr_warn_once("dma_heap: ioctl data not valid\n"); + return -EINVAL; + } + + if (heap_allocation.fd_flags & ~DMA_HEAP_VALID_FD_FLAGS) { + pr_warn_once("dma_heap: fd_flags has invalid or unsupported flags set\n"); + return -EINVAL; + } + + if (heap_allocation.heap_flags & ~DMA_HEAP_VALID_HEAP_FLAGS) { + pr_warn_once("dma_heap: heap flags has invalid or unsupported flags set\n"); + return -EINVAL; + } + + fd = dma_heap_buffer_alloc(heap, heap_allocation.len, + heap_allocation.fd_flags, + heap_allocation.heap_flags); + if (fd < 0) + return fd; + + heap_allocation.fd = fd; + + if (copy_to_user((void __user *)arg, &heap_allocation, + sizeof(heap_allocation))) { + ksys_close(fd); + return -EFAULT; + } + + return 0; +} + +static long dma_heap_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + int ret = 0; + + switch (cmd) { + case DMA_HEAP_IOC_ALLOC: + ret = dma_heap_ioctl_allocate(file, arg); + break; + default: + return -ENOTTY; + } + + return ret; +} + +static const struct file_operations dma_heap_fops = { + .owner = THIS_MODULE, + .open = dma_heap_open, + .unlocked_ioctl = dma_heap_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = dma_heap_ioctl, +#endif +}; + +/** + * dma_heap_get_drvdata() - get per-subdriver data for the heap + * @heap: DMA-Heap to retrieve private data for + * + * Returns: + * The per-subdriver data for the heap. + */ +void *dma_heap_get_drvdata(struct dma_heap *heap) +{ + return heap->priv; +} + +struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info) +{ + struct dma_heap *heap, *h, *err_ret; + struct device *dev_ret; + int ret; + + if (!exp_info->name || !strcmp(exp_info->name, "")) { + pr_err("dma_heap: Cannot add heap without a name\n"); + return ERR_PTR(-EINVAL); + } + + if (!exp_info->ops || !exp_info->ops->allocate) { + pr_err("dma_heap: Cannot add heap with invalid ops struct\n"); + return ERR_PTR(-EINVAL); + } + + /* check the name is unique */ + mutex_lock(&heap_list_lock); + list_for_each_entry(h, &heap_list, list) { + if (!strcmp(h->name, exp_info->name)) { + mutex_unlock(&heap_list_lock); + pr_err("dma_heap: Already registered heap named %s\n", + exp_info->name); + return ERR_PTR(-EINVAL); + } + } + mutex_unlock(&heap_list_lock); + + heap = kzalloc(sizeof(*heap), GFP_KERNEL); + if (!heap) + return ERR_PTR(-ENOMEM); + + heap->name = exp_info->name; + heap->ops = exp_info->ops; + heap->priv = exp_info->priv; + + /* Find unused minor number */ + ret = xa_alloc(&dma_heap_minors, &heap->minor, heap, + XA_LIMIT(0, NUM_HEAP_MINORS - 1), GFP_KERNEL); + if (ret < 0) { + pr_err("dma_heap: Unable to get minor number for heap\n"); + err_ret = ERR_PTR(ret); + goto err0; + } + + /* Create device */ + heap->heap_devt = MKDEV(MAJOR(dma_heap_devt), heap->minor); + + cdev_init(&heap->heap_cdev, &dma_heap_fops); + ret = cdev_add(&heap->heap_cdev, heap->heap_devt, 1); + if (ret < 0) { + pr_err("dma_heap: Unable to add char device\n"); + err_ret = ERR_PTR(ret); + goto err1; + } + + dev_ret = device_create(dma_heap_class, + NULL, + heap->heap_devt, + NULL, + heap->name); + if (IS_ERR(dev_ret)) { + pr_err("dma_heap: Unable to create device\n"); + err_ret = ERR_CAST(dev_ret); + goto err2; + } + /* Add heap to the list */ + mutex_lock(&heap_list_lock); + list_add(&heap->list, &heap_list); + mutex_unlock(&heap_list_lock); + + return heap; + +err2: + cdev_del(&heap->heap_cdev); +err1: + xa_erase(&dma_heap_minors, heap->minor); +err0: + kfree(heap); + return err_ret; +} + +static char *dma_heap_devnode(struct device *dev, umode_t *mode) +{ + return kasprintf(GFP_KERNEL, "dma_heap/%s", dev_name(dev)); +} + +static int dma_heap_init(void) +{ + int ret; + + ret = alloc_chrdev_region(&dma_heap_devt, 0, NUM_HEAP_MINORS, DEVNAME); + if (ret) + return ret; + + dma_heap_class = class_create(THIS_MODULE, DEVNAME); + if (IS_ERR(dma_heap_class)) { + unregister_chrdev_region(dma_heap_devt, NUM_HEAP_MINORS); + return PTR_ERR(dma_heap_class); + } + dma_heap_class->devnode = dma_heap_devnode; + + return 0; +} +subsys_initcall(dma_heap_init); diff --git a/include/linux/dma-heap.h b/include/linux/dma-heap.h new file mode 100644 index 000000000000..454e354d1ffb --- /dev/null +++ b/include/linux/dma-heap.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * DMABUF Heaps Allocation Infrastructure + * + * Copyright (C) 2011 Google, Inc. + * Copyright (C) 2019 Linaro Ltd. + */ + +#ifndef _DMA_HEAPS_H +#define _DMA_HEAPS_H + +#include +#include + +struct dma_heap; + +/** + * struct dma_heap_ops - ops to operate on a given heap + * @allocate: allocate dmabuf and return fd + * + * allocate returns dmabuf fd on success, -errno on error. + */ +struct dma_heap_ops { + int (*allocate)(struct dma_heap *heap, + unsigned long len, + unsigned long fd_flags, + unsigned long heap_flags); +}; + +/** + * struct dma_heap_export_info - information needed to export a new dmabuf heap + * @name: used for debugging/device-node name + * @ops: ops struct for this heap + * @priv: heap exporter private data + * + * Information needed to export a new dmabuf heap. + */ +struct dma_heap_export_info { + const char *name; + const struct dma_heap_ops *ops; + void *priv; +}; + +/** + * dma_heap_get_drvdata() - get per-heap driver data + * @heap: DMA-Heap to retrieve private data for + * + * Returns: + * The per-heap data for the heap. + */ +void *dma_heap_get_drvdata(struct dma_heap *heap); + +/** + * dma_heap_add - adds a heap to dmabuf heaps + * @exp_info: information needed to register this heap + */ +struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info); + +#endif /* _DMA_HEAPS_H */ diff --git a/include/uapi/linux/dma-heap.h b/include/uapi/linux/dma-heap.h new file mode 100644 index 000000000000..6ce5cc68d238 --- /dev/null +++ b/include/uapi/linux/dma-heap.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * DMABUF Heaps Userspace API + * + * Copyright (C) 2011 Google, Inc. + * Copyright (C) 2019 Linaro Ltd. + */ +#ifndef _UAPI_LINUX_DMABUF_POOL_H +#define _UAPI_LINUX_DMABUF_POOL_H + +#include +#include + +/** + * DOC: DMABUF Heaps Userspace API + */ + +/* Valid FD_FLAGS are O_CLOEXEC, O_RDONLY, O_WRONLY, O_RDWR */ +#define DMA_HEAP_VALID_FD_FLAGS (O_CLOEXEC | O_ACCMODE) + +/* Currently no heap flags */ +#define DMA_HEAP_VALID_HEAP_FLAGS (0) + +/** + * struct dma_heap_allocation_data - metadata passed from userspace for + * allocations + * @len: size of the allocation + * @fd: will be populated with a fd which provdes the + * handle to the allocated dma-buf + * @fd_flags: file descriptor flags used when allocating + * @heap_flags: flags passed to heap + * + * Provided by userspace as an argument to the ioctl + */ +struct dma_heap_allocation_data { + __u64 len; + __u32 fd; + __u32 fd_flags; + __u64 heap_flags; + __u32 reserved0; + __u32 reserved1; +}; + +#define DMA_HEAP_IOC_MAGIC 'H' + +/** + * DOC: DMA_HEAP_IOC_ALLOC - allocate memory from pool + * + * Takes an dma_heap_allocation_data struct and returns it with the fd field + * populated with the dmabuf handle of the allocation. + */ +#define DMA_HEAP_IOC_ALLOC _IOWR(DMA_HEAP_IOC_MAGIC, 0, \ + struct dma_heap_allocation_data) + +#endif /* _UAPI_LINUX_DMABUF_POOL_H */ -- cgit v1.2.3-71-gd317 From 5153faac18d293fc7abb19ff7034683fbcd82dc7 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 24 Oct 2019 12:03:51 -0700 Subject: cgroup: remove cgroup_enable_task_cg_lists() optimization cgroup_enable_task_cg_lists() is used to lazyily initialize task cgroup associations on the first use to reduce fork / exit overheads on systems which don't use cgroup. Unfortunately, locking around it has never been actually correct and its value is dubious given how the vast majority of systems use cgroup right away from boot. This patch removes the optimization. For now, replace the cg_list based branches with WARN_ON_ONCE()'s to be on the safe side. We can simplify the logic further in the future. Signed-off-by: Tejun Heo Reported-by: Oleg Nesterov Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 1 - kernel/cgroup/cgroup.c | 184 +++++++++++-------------------------------------- kernel/cgroup/cpuset.c | 2 - 3 files changed, 39 insertions(+), 148 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 3ba3e6da13a6..f6b048902d6c 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -150,7 +150,6 @@ struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp); -void cgroup_enable_task_cg_lists(void); void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, struct css_task_iter *it); struct task_struct *css_task_iter_next(struct css_task_iter *it); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 8b1c4fd47a7a..cf32c0c7a45d 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1883,65 +1883,6 @@ static int cgroup_reconfigure(struct fs_context *fc) return 0; } -/* - * To reduce the fork() overhead for systems that are not actually using - * their cgroups capability, we don't maintain the lists running through - * each css_set to its tasks until we see the list actually used - in other - * words after the first mount. - */ -static bool use_task_css_set_links __read_mostly; - -void cgroup_enable_task_cg_lists(void) -{ - struct task_struct *p, *g; - - /* - * We need tasklist_lock because RCU is not safe against - * while_each_thread(). Besides, a forking task that has passed - * cgroup_post_fork() without seeing use_task_css_set_links = 1 - * is not guaranteed to have its child immediately visible in the - * tasklist if we walk through it with RCU. - */ - read_lock(&tasklist_lock); - spin_lock_irq(&css_set_lock); - - if (use_task_css_set_links) - goto out_unlock; - - use_task_css_set_links = true; - - do_each_thread(g, p) { - WARN_ON_ONCE(!list_empty(&p->cg_list) || - task_css_set(p) != &init_css_set); - - /* - * We should check if the process is exiting, otherwise - * it will race with cgroup_exit() in that the list - * entry won't be deleted though the process has exited. - * Do it while holding siglock so that we don't end up - * racing against cgroup_exit(). - * - * Interrupts were already disabled while acquiring - * the css_set_lock, so we do not need to disable it - * again when acquiring the sighand->siglock here. - */ - spin_lock(&p->sighand->siglock); - if (!(p->flags & PF_EXITING)) { - struct css_set *cset = task_css_set(p); - - if (!css_set_populated(cset)) - css_set_update_populated(cset, true); - list_add_tail(&p->cg_list, &cset->tasks); - get_css_set(cset); - cset->nr_tasks++; - } - spin_unlock(&p->sighand->siglock); - } while_each_thread(g, p); -out_unlock: - spin_unlock_irq(&css_set_lock); - read_unlock(&tasklist_lock); -} - static void init_cgroup_housekeeping(struct cgroup *cgrp) { struct cgroup_subsys *ss; @@ -2187,13 +2128,6 @@ static int cgroup_init_fs_context(struct fs_context *fc) if (!ctx) return -ENOMEM; - /* - * The first time anyone tries to mount a cgroup, enable the list - * linking each css_set to its tasks and fix up all existing tasks. - */ - if (!use_task_css_set_links) - cgroup_enable_task_cg_lists(); - ctx->ns = current->nsproxy->cgroup_ns; get_cgroup_ns(ctx->ns); fc->fs_private = &ctx->kfc; @@ -2371,9 +2305,8 @@ static void cgroup_migrate_add_task(struct task_struct *task, if (task->flags & PF_EXITING) return; - /* leave @task alone if post_fork() hasn't linked it yet */ - if (list_empty(&task->cg_list)) - return; + /* cgroup_threadgroup_rwsem protects racing against forks */ + WARN_ON_ONCE(list_empty(&task->cg_list)); cset = task_css_set(task); if (!cset->mg_src_cgrp) @@ -4586,9 +4519,6 @@ repeat: void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, struct css_task_iter *it) { - /* no one should try to iterate before mounting cgroups */ - WARN_ON_ONCE(!use_task_css_set_links); - memset(it, 0, sizeof(*it)); spin_lock_irq(&css_set_lock); @@ -6022,62 +5952,38 @@ void cgroup_cancel_fork(struct task_struct *child) void cgroup_post_fork(struct task_struct *child) { struct cgroup_subsys *ss; + struct css_set *cset; int i; + spin_lock_irq(&css_set_lock); + + WARN_ON_ONCE(!list_empty(&child->cg_list)); + cset = task_css_set(current); /* current is @child's parent */ + get_css_set(cset); + cset->nr_tasks++; + css_set_move_task(child, NULL, cset, false); + /* - * This may race against cgroup_enable_task_cg_lists(). As that - * function sets use_task_css_set_links before grabbing - * tasklist_lock and we just went through tasklist_lock to add - * @child, it's guaranteed that either we see the set - * use_task_css_set_links or cgroup_enable_task_cg_lists() sees - * @child during its iteration. - * - * If we won the race, @child is associated with %current's - * css_set. Grabbing css_set_lock guarantees both that the - * association is stable, and, on completion of the parent's - * migration, @child is visible in the source of migration or - * already in the destination cgroup. This guarantee is necessary - * when implementing operations which need to migrate all tasks of - * a cgroup to another. - * - * Note that if we lose to cgroup_enable_task_cg_lists(), @child - * will remain in init_css_set. This is safe because all tasks are - * in the init_css_set before cg_links is enabled and there's no - * operation which transfers all tasks out of init_css_set. + * If the cgroup has to be frozen, the new task has too. Let's set + * the JOBCTL_TRAP_FREEZE jobctl bit to get the task into the + * frozen state. */ - if (use_task_css_set_links) { - struct css_set *cset; - - spin_lock_irq(&css_set_lock); - cset = task_css_set(current); /* current is @child's parent */ - if (list_empty(&child->cg_list)) { - get_css_set(cset); - cset->nr_tasks++; - css_set_move_task(child, NULL, cset, false); - } + if (unlikely(cgroup_task_freeze(child))) { + spin_lock(&child->sighand->siglock); + WARN_ON_ONCE(child->frozen); + child->jobctl |= JOBCTL_TRAP_FREEZE; + spin_unlock(&child->sighand->siglock); /* - * If the cgroup has to be frozen, the new task has too. - * Let's set the JOBCTL_TRAP_FREEZE jobctl bit to get - * the task into the frozen state. + * Calling cgroup_update_frozen() isn't required here, + * because it will be called anyway a bit later from + * do_freezer_trap(). So we avoid cgroup's transient switch + * from the frozen state and back. */ - if (unlikely(cgroup_task_freeze(child))) { - spin_lock(&child->sighand->siglock); - WARN_ON_ONCE(child->frozen); - child->jobctl |= JOBCTL_TRAP_FREEZE; - spin_unlock(&child->sighand->siglock); - - /* - * Calling cgroup_update_frozen() isn't required here, - * because it will be called anyway a bit later - * from do_freezer_trap(). So we avoid cgroup's - * transient switch from the frozen state and back. - */ - } - - spin_unlock_irq(&css_set_lock); } + spin_unlock_irq(&css_set_lock); + /* * Call ss->fork(). This must happen after @child is linked on * css_set; otherwise, @child might change state between ->fork() @@ -6101,29 +6007,19 @@ void cgroup_exit(struct task_struct *tsk) struct css_set *cset; int i; - /* - * Unlink from @tsk from its css_set. As migration path can't race - * with us (thanks to cgroup_threadgroup_rwsem), we can check css_set - * and cg_list without synchronization. - */ - cset = task_css_set(tsk); + spin_lock_irq(&css_set_lock); - if (!list_empty(&tsk->cg_list)) { - spin_lock_irq(&css_set_lock); - css_set_move_task(tsk, cset, NULL, false); - list_add_tail(&tsk->cg_list, &cset->dying_tasks); - cset->nr_tasks--; + WARN_ON_ONCE(list_empty(&tsk->cg_list)); + cset = task_css_set(tsk); + css_set_move_task(tsk, cset, NULL, false); + list_add_tail(&tsk->cg_list, &cset->dying_tasks); + cset->nr_tasks--; - WARN_ON_ONCE(cgroup_task_frozen(tsk)); - if (unlikely(cgroup_task_freeze(tsk))) - cgroup_update_frozen(task_dfl_cgroup(tsk)); + WARN_ON_ONCE(cgroup_task_frozen(tsk)); + if (unlikely(cgroup_task_freeze(tsk))) + cgroup_update_frozen(task_dfl_cgroup(tsk)); - spin_unlock_irq(&css_set_lock); - } else { - /* Take reference to avoid freeing init_css_set in cgroup_free, - * see cgroup_fork(). */ - get_css_set(cset); - } + spin_unlock_irq(&css_set_lock); /* see cgroup_post_fork() for details */ do_each_subsys_mask(ss, i, have_exit_callback) { @@ -6140,12 +6036,10 @@ void cgroup_release(struct task_struct *task) ss->release(task); } while_each_subsys_mask(); - if (use_task_css_set_links) { - spin_lock_irq(&css_set_lock); - css_set_skip_task_iters(task_css_set(task), task); - list_del_init(&task->cg_list); - spin_unlock_irq(&css_set_lock); - } + spin_lock_irq(&css_set_lock); + css_set_skip_task_iters(task_css_set(task), task); + list_del_init(&task->cg_list); + spin_unlock_irq(&css_set_lock); } void cgroup_free(struct task_struct *task) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index c52bc91f882b..faff8f99e8f2 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -928,8 +928,6 @@ static void rebuild_root_domains(void) lockdep_assert_cpus_held(); lockdep_assert_held(&sched_domains_mutex); - cgroup_enable_task_cg_lists(); - rcu_read_lock(); /* -- cgit v1.2.3-71-gd317 From 993e4cdebb5a53bc87f21cdd34d1dc42225de43d Mon Sep 17 00:00:00 2001 From: David Sterba Date: Thu, 24 Oct 2019 19:31:10 +0200 Subject: block: reorder bio::__bi_remaining for better packing Simple reordering of __bi_remaining can reduce bio size by 8 bytes that are now wasted on padding (measured on x86_64): struct bio { struct bio * bi_next; /* 0 8 */ struct gendisk * bi_disk; /* 8 8 */ unsigned int bi_opf; /* 16 4 */ short unsigned int bi_flags; /* 20 2 */ short unsigned int bi_ioprio; /* 22 2 */ short unsigned int bi_write_hint; /* 24 2 */ blk_status_t bi_status; /* 26 1 */ u8 bi_partno; /* 27 1 */ /* XXX 4 bytes hole, try to pack */ struct bvec_iter bi_iter; /* 32 24 */ /* XXX last struct has 4 bytes of padding */ atomic_t __bi_remaining; /* 56 4 */ /* XXX 4 bytes hole, try to pack */ [...] /* size: 104, cachelines: 2, members: 19 */ /* sum members: 96, holes: 2, sum holes: 8 */ /* paddings: 1, sum paddings: 4 */ /* last cacheline: 40 bytes */ }; Now becomes: struct bio { struct bio * bi_next; /* 0 8 */ struct gendisk * bi_disk; /* 8 8 */ unsigned int bi_opf; /* 16 4 */ short unsigned int bi_flags; /* 20 2 */ short unsigned int bi_ioprio; /* 22 2 */ short unsigned int bi_write_hint; /* 24 2 */ blk_status_t bi_status; /* 26 1 */ u8 bi_partno; /* 27 1 */ atomic_t __bi_remaining; /* 28 4 */ struct bvec_iter bi_iter; /* 32 24 */ /* XXX last struct has 4 bytes of padding */ [...] /* size: 96, cachelines: 2, members: 19 */ /* paddings: 1, sum paddings: 4 */ /* last cacheline: 32 bytes */ }; Signed-off-by: David Sterba Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index d688b96d1d63..1e7eeec16458 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -153,10 +153,10 @@ struct bio { unsigned short bi_write_hint; blk_status_t bi_status; u8 bi_partno; + atomic_t __bi_remaining; struct bvec_iter bi_iter; - atomic_t __bi_remaining; bio_end_io_t *bi_end_io; void *bi_private; -- cgit v1.2.3-71-gd317 From d386732bc142c63b9f676fed098bc06f91ee964a Mon Sep 17 00:00:00 2001 From: André Almeida Date: Mon, 21 Oct 2019 21:07:24 -0300 Subject: blk-mq: fill header with kernel-doc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Insert documentation for structs, enums and functions at header file. Format existing and new comments at struct blk_mq_ops as kernel-doc comments. Reviewed-by: Bart Van Assche Signed-off-by: André Almeida Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 225 ++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 185 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index e0fce93ac127..4919d22e1aff 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -10,74 +10,171 @@ struct blk_mq_tags; struct blk_flush_queue; /** - * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware block device + * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware + * block device */ struct blk_mq_hw_ctx { struct { + /** @lock: Protects the dispatch list. */ spinlock_t lock; + /** + * @dispatch: Used for requests that are ready to be + * dispatched to the hardware but for some reason (e.g. lack of + * resources) could not be sent to the hardware. As soon as the + * driver can send new requests, requests at this list will + * be sent first for a fairer dispatch. + */ struct list_head dispatch; - unsigned long state; /* BLK_MQ_S_* flags */ + /** + * @state: BLK_MQ_S_* flags. Defines the state of the hw + * queue (active, scheduled to restart, stopped). + */ + unsigned long state; } ____cacheline_aligned_in_smp; + /** + * @run_work: Used for scheduling a hardware queue run at a later time. + */ struct delayed_work run_work; + /** @cpumask: Map of available CPUs where this hctx can run. */ cpumask_var_t cpumask; + /** + * @next_cpu: Used by blk_mq_hctx_next_cpu() for round-robin CPU + * selection from @cpumask. + */ int next_cpu; + /** + * @next_cpu_batch: Counter of how many works left in the batch before + * changing to the next CPU. + */ int next_cpu_batch; - unsigned long flags; /* BLK_MQ_F_* flags */ + /** @flags: BLK_MQ_F_* flags. Defines the behaviour of the queue. */ + unsigned long flags; + /** + * @sched_data: Pointer owned by the IO scheduler attached to a request + * queue. It's up to the IO scheduler how to use this pointer. + */ void *sched_data; + /** + * @queue: Pointer to the request queue that owns this hardware context. + */ struct request_queue *queue; + /** @fq: Queue of requests that need to perform a flush operation. */ struct blk_flush_queue *fq; + /** + * @driver_data: Pointer to data owned by the block driver that created + * this hctx + */ void *driver_data; + /** + * @ctx_map: Bitmap for each software queue. If bit is on, there is a + * pending request in that software queue. + */ struct sbitmap ctx_map; + /** + * @dispatch_from: Software queue to be used when no scheduler was + * selected. + */ struct blk_mq_ctx *dispatch_from; + /** + * @dispatch_busy: Number used by blk_mq_update_dispatch_busy() to + * decide if the hw_queue is busy using Exponential Weighted Moving + * Average algorithm. + */ unsigned int dispatch_busy; + /** @type: HCTX_TYPE_* flags. Type of hardware queue. */ unsigned short type; + /** @nr_ctx: Number of software queues. */ unsigned short nr_ctx; + /** @ctxs: Array of software queues. */ struct blk_mq_ctx **ctxs; + /** @dispatch_wait_lock: Lock for dispatch_wait queue. */ spinlock_t dispatch_wait_lock; + /** + * @dispatch_wait: Waitqueue to put requests when there is no tag + * available at the moment, to wait for another try in the future. + */ wait_queue_entry_t dispatch_wait; + + /** + * @wait_index: Index of next available dispatch_wait queue to insert + * requests. + */ atomic_t wait_index; + /** + * @tags: Tags owned by the block driver. A tag at this set is only + * assigned when a request is dispatched from a hardware queue. + */ struct blk_mq_tags *tags; + /** + * @sched_tags: Tags owned by I/O scheduler. If there is an I/O + * scheduler associated with a request queue, a tag is assigned when + * that request is allocated. Else, this member is not used. + */ struct blk_mq_tags *sched_tags; + /** @queued: Number of queued requests. */ unsigned long queued; + /** @run: Number of dispatched requests. */ unsigned long run; #define BLK_MQ_MAX_DISPATCH_ORDER 7 + /** @dispatched: Number of dispatch requests by queue. */ unsigned long dispatched[BLK_MQ_MAX_DISPATCH_ORDER]; + /** @numa_node: NUMA node the storage adapter has been connected to. */ unsigned int numa_node; + /** @queue_num: Index of this hardware queue. */ unsigned int queue_num; + /** + * @nr_active: Number of active requests. Only used when a tag set is + * shared across request queues. + */ atomic_t nr_active; + /** @cpuhp_dead: List to store request if some CPU die. */ struct hlist_node cpuhp_dead; + /** @kobj: Kernel object for sysfs. */ struct kobject kobj; + /** @poll_considered: Count times blk_poll() was called. */ unsigned long poll_considered; + /** @poll_invoked: Count how many requests blk_poll() polled. */ unsigned long poll_invoked; + /** @poll_success: Count how many polled requests were completed. */ unsigned long poll_success; #ifdef CONFIG_BLK_DEBUG_FS + /** + * @debugfs_dir: debugfs directory for this hardware queue. Named + * as cpu. + */ struct dentry *debugfs_dir; + /** @sched_debugfs_dir: debugfs directory for the scheduler. */ struct dentry *sched_debugfs_dir; #endif + /** @hctx_list: List of all hardware queues. */ struct list_head hctx_list; - /* Must be the last member - see also blk_mq_hw_ctx_size(). */ + /** + * @srcu: Sleepable RCU. Use as lock when type of the hardware queue is + * blocking (BLK_MQ_F_BLOCKING). Must be the last member - see also + * blk_mq_hw_ctx_size(). + */ struct srcu_struct srcu[0]; }; /** - * struct blk_mq_queue_map - ctx -> hctx mapping + * struct blk_mq_queue_map - Map software queues to hardware queues * @mq_map: CPU ID to hardware queue index map. This is an array * with nr_cpu_ids elements. Each element has a value in the range * [@queue_offset, @queue_offset + @nr_queues). @@ -92,10 +189,17 @@ struct blk_mq_queue_map { unsigned int queue_offset; }; +/** + * enum hctx_type - Type of hardware queue + * @HCTX_TYPE_DEFAULT: All I/O not otherwise accounted for. + * @HCTX_TYPE_READ: Just for READ I/O. + * @HCTX_TYPE_POLL: Polled I/O of any kind. + * @HCTX_MAX_TYPES: Number of types of hctx. + */ enum hctx_type { - HCTX_TYPE_DEFAULT, /* all I/O not otherwise accounted for */ - HCTX_TYPE_READ, /* just for READ I/O */ - HCTX_TYPE_POLL, /* polled I/O of any kind */ + HCTX_TYPE_DEFAULT, + HCTX_TYPE_READ, + HCTX_TYPE_POLL, HCTX_MAX_TYPES, }; @@ -147,6 +251,12 @@ struct blk_mq_tag_set { struct list_head tag_list; }; +/** + * struct blk_mq_queue_data - Data about a request inserted in a queue + * + * @rq: Request pointer. + * @last: If it is the last request in the queue. + */ struct blk_mq_queue_data { struct request *rq; bool last; @@ -174,81 +284,101 @@ typedef bool (busy_fn)(struct request_queue *); typedef void (complete_fn)(struct request *); typedef void (cleanup_rq_fn)(struct request *); - +/** + * struct blk_mq_ops - Callback functions that implements block driver + * behaviour. + */ struct blk_mq_ops { - /* - * Queue request + /** + * @queue_rq: Queue a new request from block IO. */ queue_rq_fn *queue_rq; - /* - * If a driver uses bd->last to judge when to submit requests to - * hardware, it must define this function. In case of errors that - * make us stop issuing further requests, this hook serves the + /** + * @commit_rqs: If a driver uses bd->last to judge when to submit + * requests to hardware, it must define this function. In case of errors + * that make us stop issuing further requests, this hook serves the * purpose of kicking the hardware (which the last request otherwise * would have done). */ commit_rqs_fn *commit_rqs; - /* - * Reserve budget before queue request, once .queue_rq is + /** + * @get_budget: Reserve budget before queue request, once .queue_rq is * run, it is driver's responsibility to release the * reserved budget. Also we have to handle failure case * of .get_budget for avoiding I/O deadlock. */ get_budget_fn *get_budget; + /** + * @put_budget: Release the reserved budget. + */ put_budget_fn *put_budget; - /* - * Called on request timeout + /** + * @timeout: Called on request timeout. */ timeout_fn *timeout; - /* - * Called to poll for completion of a specific tag. + /** + * @poll: Called to poll for completion of a specific tag. */ poll_fn *poll; + /** + * @complete: Mark the request as complete. + */ complete_fn *complete; - /* - * Called when the block layer side of a hardware queue has been - * set up, allowing the driver to allocate/init matching structures. - * Ditto for exit/teardown. + /** + * @init_hctx: Called when the block layer side of a hardware queue has + * been set up, allowing the driver to allocate/init matching + * structures. */ init_hctx_fn *init_hctx; + /** + * @exit_hctx: Ditto for exit/teardown. + */ exit_hctx_fn *exit_hctx; - /* - * Called for every command allocated by the block layer to allow - * the driver to set up driver specific data. + /** + * @init_request: Called for every command allocated by the block layer + * to allow the driver to set up driver specific data. * * Tag greater than or equal to queue_depth is for setting up * flush request. - * - * Ditto for exit/teardown. */ init_request_fn *init_request; + /** + * @exit_request: Ditto for exit/teardown. + */ exit_request_fn *exit_request; - /* Called from inside blk_get_request() */ + + /** + * @initialize_rq_fn: Called from inside blk_get_request(). + */ void (*initialize_rq_fn)(struct request *rq); - /* - * Called before freeing one request which isn't completed yet, - * and usually for freeing the driver private data + /** + * @cleanup_rq: Called before freeing one request which isn't completed + * yet, and usually for freeing the driver private data. */ cleanup_rq_fn *cleanup_rq; - /* - * If set, returns whether or not this queue currently is busy + /** + * @busy: If set, returns whether or not this queue currently is busy. */ busy_fn *busy; + /** + * @map_queues: This allows drivers specify their own queue mapping by + * overriding the setup-time function that builds the mq_map. + */ map_queues_fn *map_queues; #ifdef CONFIG_BLK_DEBUG_FS - /* - * Used by the debugfs implementation to show driver-specific + /** + * @show_rq: Used by the debugfs implementation to show driver-specific * information about a request. */ void (*show_rq)(struct seq_file *m, struct request *rq); @@ -391,14 +521,29 @@ void blk_mq_quiesce_queue_nowait(struct request_queue *q); unsigned int blk_mq_rq_cpu(struct request *rq); -/* +/** + * blk_mq_rq_from_pdu - cast a PDU to a request + * @pdu: the PDU (Protocol Data Unit) to be casted + * + * Return: request + * * Driver command data is immediately after the request. So subtract request - * size to get back to the original request, add request size to get the PDU. + * size to get back to the original request. */ static inline struct request *blk_mq_rq_from_pdu(void *pdu) { return pdu - sizeof(struct request); } + +/** + * blk_mq_rq_to_pdu - cast a request to a PDU + * @rq: the request to be casted + * + * Return: pointer to the PDU + * + * Driver command data is immediately after the request. So add request to get + * the PDU. + */ static inline void *blk_mq_rq_to_pdu(struct request *rq) { return rq + 1; -- cgit v1.2.3-71-gd317 From 480274787d7e3458bc5a7cfbbbe07033984ad711 Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Wed, 23 Oct 2019 11:09:26 -0400 Subject: tcp: add TCP_INFO status for failed client TFO The TCPI_OPT_SYN_DATA bit as part of tcpi_options currently reports whether or not data-in-SYN was ack'd on both the client and server side. We'd like to gather more information on the client-side in the failure case in order to indicate the reason for the failure. This can be useful for not only debugging TFO, but also for creating TFO socket policies. For example, if a middle box removes the TFO option or drops a data-in-SYN, we can can detect this case, and turn off TFO for these connections saving the extra retransmits. The newly added tcpi_fastopen_client_fail status is 2 bits and has the following 4 states: 1) TFO_STATUS_UNSPEC Catch-all state which includes when TFO is disabled via black hole detection, which is indicated via LINUX_MIB_TCPFASTOPENBLACKHOLE. 2) TFO_COOKIE_UNAVAILABLE If TFO_CLIENT_NO_COOKIE mode is off, this state indicates that no cookie is available in the cache. 3) TFO_DATA_NOT_ACKED Data was sent with SYN, we received a SYN/ACK but it did not cover the data portion. Cookie is not accepted by server because the cookie may be invalid or the server may be overloaded. 4) TFO_SYN_RETRANSMITTED Data was sent with SYN, we received a SYN/ACK which did not cover the data after at least 1 additional SYN was sent (without data). It may be the case that a middle-box is dropping data-in-SYN packets. Thus, it would be more efficient to not use TFO on this connection to avoid extra retransmits during connection establishment. These new fields do not cover all the cases where TFO may fail, but other failures, such as SYN/ACK + data being dropped, will result in the connection not becoming established. And a connection blackhole after session establishment shows up as a stalled connection. Signed-off-by: Jason Baron Cc: Eric Dumazet Cc: Neal Cardwell Cc: Christoph Paasch Cc: Yuchung Cheng Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 +- include/uapi/linux/tcp.h | 10 +++++++++- net/ipv4/tcp.c | 2 ++ net/ipv4/tcp_fastopen.c | 5 ++++- net/ipv4/tcp_input.c | 4 ++++ 5 files changed, 20 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 668e25a76d69..ca6f01531e64 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -223,7 +223,7 @@ struct tcp_sock { fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */ fastopen_no_cookie:1, /* Allow send/recv SYN+data without a cookie */ is_sack_reneg:1, /* in recovery from loss with SACK reneg? */ - unused:2; + fastopen_client_fail:2; /* reason why fastopen failed */ u8 nonagle : 4,/* Disable Nagle algorithm? */ thin_lto : 1,/* Use linear timeouts for thin streams */ recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */ diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 81e697978e8b..74af1f759cee 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -155,6 +155,14 @@ enum { TCP_QUEUES_NR, }; +/* why fastopen failed from client perspective */ +enum tcp_fastopen_client_fail { + TFO_STATUS_UNSPEC, /* catch-all */ + TFO_COOKIE_UNAVAILABLE, /* if not in TFO_CLIENT_NO_COOKIE mode */ + TFO_DATA_NOT_ACKED, /* SYN-ACK did not ack SYN data */ + TFO_SYN_RETRANSMITTED, /* SYN-ACK did not ack SYN data after timeout */ +}; + /* for TCP_INFO socket option */ #define TCPI_OPT_TIMESTAMPS 1 #define TCPI_OPT_SACK 2 @@ -211,7 +219,7 @@ struct tcp_info { __u8 tcpi_backoff; __u8 tcpi_options; __u8 tcpi_snd_wscale : 4, tcpi_rcv_wscale : 4; - __u8 tcpi_delivery_rate_app_limited:1; + __u8 tcpi_delivery_rate_app_limited:1, tcpi_fastopen_client_fail:2; __u32 tcpi_rto; __u32 tcpi_ato; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 9d69e1da93f2..8fc1e8b6d408 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2666,6 +2666,7 @@ int tcp_disconnect(struct sock *sk, int flags) /* Clean up fastopen related fields */ tcp_free_fastopen_req(tp); inet->defer_connect = 0; + tp->fastopen_client_fail = 0; WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); @@ -3305,6 +3306,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_reord_seen = tp->reord_seen; info->tcpi_rcv_ooopack = tp->rcv_ooopack; info->tcpi_snd_wnd = tp->snd_wnd; + info->tcpi_fastopen_client_fail = tp->fastopen_client_fail; unlock_sock_fast(sk, slow); } EXPORT_SYMBOL_GPL(tcp_get_info); diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index a915ade0c818..19ad9586c720 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -422,7 +422,10 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, cookie->len = -1; return true; } - return cookie->len > 0; + if (cookie->len > 0) + return true; + tcp_sk(sk)->fastopen_client_fail = TFO_COOKIE_UNAVAILABLE; + return false; } /* This function checks if we want to defer sending SYN until the first diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a2e52ad7cdab..88b987ca9ebb 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5814,6 +5814,10 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, tcp_fastopen_cache_set(sk, mss, cookie, syn_drop, try_exp); if (data) { /* Retransmit unacked data in SYN */ + if (tp->total_retrans) + tp->fastopen_client_fail = TFO_SYN_RETRANSMITTED; + else + tp->fastopen_client_fail = TFO_DATA_NOT_ACKED; skb_rbtree_walk_from(data) { if (__tcp_retransmit_skb(sk, data, 1)) break; -- cgit v1.2.3-71-gd317 From caccddcfc4b4de75930df2e8f7fd0c66556b13ff Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Mon, 18 Jun 2018 14:01:51 +0200 Subject: gpu: host1x: Request channels for clients, not devices A struct device doesn't carry much information that a channel might be interested in, but the client very much does. Request channels for the clients rather than their parent devices and store a pointer to them in order to have that information available when needed. Signed-off-by: Thierry Reding --- drivers/gpu/drm/tegra/gr2d.c | 2 +- drivers/gpu/drm/tegra/gr3d.c | 2 +- drivers/gpu/drm/tegra/vic.c | 2 +- drivers/gpu/host1x/channel.c | 13 +++++++------ drivers/gpu/host1x/channel.h | 1 + include/linux/host1x.h | 2 +- 6 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/tegra/gr2d.c b/drivers/gpu/drm/tegra/gr2d.c index 641299cc85b8..3cbb4a029c41 100644 --- a/drivers/gpu/drm/tegra/gr2d.c +++ b/drivers/gpu/drm/tegra/gr2d.c @@ -40,7 +40,7 @@ static int gr2d_init(struct host1x_client *client) struct gr2d *gr2d = to_gr2d(drm); int err; - gr2d->channel = host1x_channel_request(client->dev); + gr2d->channel = host1x_channel_request(client); if (!gr2d->channel) return -ENOMEM; diff --git a/drivers/gpu/drm/tegra/gr3d.c b/drivers/gpu/drm/tegra/gr3d.c index 8b9a35b1cbb3..87a386134cc4 100644 --- a/drivers/gpu/drm/tegra/gr3d.c +++ b/drivers/gpu/drm/tegra/gr3d.c @@ -49,7 +49,7 @@ static int gr3d_init(struct host1x_client *client) struct gr3d *gr3d = to_gr3d(drm); int err; - gr3d->channel = host1x_channel_request(client->dev); + gr3d->channel = host1x_channel_request(client); if (!gr3d->channel) return -ENOMEM; diff --git a/drivers/gpu/drm/tegra/vic.c b/drivers/gpu/drm/tegra/vic.c index cd0399fd8c63..c97a61c877af 100644 --- a/drivers/gpu/drm/tegra/vic.c +++ b/drivers/gpu/drm/tegra/vic.c @@ -198,7 +198,7 @@ static int vic_init(struct host1x_client *client) vic->domain = tegra->domain; } - vic->channel = host1x_channel_request(client->dev); + vic->channel = host1x_channel_request(client); if (!vic->channel) { err = -ENOMEM; goto detach; diff --git a/drivers/gpu/host1x/channel.c b/drivers/gpu/host1x/channel.c index 1436295aa450..4cd212bb570d 100644 --- a/drivers/gpu/host1x/channel.c +++ b/drivers/gpu/host1x/channel.c @@ -115,14 +115,14 @@ static struct host1x_channel *acquire_unused_channel(struct host1x *host) /** * host1x_channel_request() - Allocate a channel - * @device: Host1x unit this channel will be used to send commands to + * @client: Host1x client this channel will be used to send commands to * - * Allocates a new host1x channel for @device. May return NULL if CDMA + * Allocates a new host1x channel for @client. May return NULL if CDMA * initialization fails. */ -struct host1x_channel *host1x_channel_request(struct device *dev) +struct host1x_channel *host1x_channel_request(struct host1x_client *client) { - struct host1x *host = dev_get_drvdata(dev->parent); + struct host1x *host = dev_get_drvdata(client->dev->parent); struct host1x_channel_list *chlist = &host->channel_list; struct host1x_channel *channel; int err; @@ -133,7 +133,8 @@ struct host1x_channel *host1x_channel_request(struct device *dev) kref_init(&channel->refcount); mutex_init(&channel->submitlock); - channel->dev = dev; + channel->client = client; + channel->dev = client->dev; err = host1x_hw_channel_init(host, channel, channel->id); if (err < 0) @@ -148,7 +149,7 @@ struct host1x_channel *host1x_channel_request(struct device *dev) fail: clear_bit(channel->id, chlist->allocated_channels); - dev_err(dev, "failed to initialize channel\n"); + dev_err(client->dev, "failed to initialize channel\n"); return NULL; } diff --git a/drivers/gpu/host1x/channel.h b/drivers/gpu/host1x/channel.h index 4fd694834f74..39044ff6c3aa 100644 --- a/drivers/gpu/host1x/channel.h +++ b/drivers/gpu/host1x/channel.h @@ -26,6 +26,7 @@ struct host1x_channel { unsigned int id; struct mutex submitlock; void __iomem *regs; + struct host1x_client *client; struct device *dev; struct host1x_cdma cdma; }; diff --git a/include/linux/host1x.h b/include/linux/host1x.h index e6eea45e1154..4396cd566a33 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -158,7 +158,7 @@ u32 host1x_syncpt_base_id(struct host1x_syncpt_base *base); struct host1x_channel; struct host1x_job; -struct host1x_channel *host1x_channel_request(struct device *dev); +struct host1x_channel *host1x_channel_request(struct host1x_client *client); struct host1x_channel *host1x_channel_get(struct host1x_channel *channel); void host1x_channel_put(struct host1x_channel *channel); int host1x_job_submit(struct host1x_job *job); -- cgit v1.2.3-71-gd317 From aacdf19849734d1be5e407932228ae101ba5b92f Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 8 Feb 2019 14:35:13 +0100 Subject: drm/tegra: Move IOMMU group into host1x client Handling of the IOMMU group attachment is common to all clients, so move the group into the client to simplify code. Signed-off-by: Thierry Reding --- drivers/gpu/drm/tegra/dc.c | 9 ++++----- drivers/gpu/drm/tegra/dc.h | 2 -- drivers/gpu/drm/tegra/drm.c | 22 +++++++++++----------- drivers/gpu/drm/tegra/drm.h | 6 ++---- drivers/gpu/drm/tegra/gr2d.c | 10 ++++------ drivers/gpu/drm/tegra/gr3d.c | 10 ++++------ drivers/gpu/drm/tegra/vic.c | 10 ++++------ include/linux/host1x.h | 3 +++ 8 files changed, 32 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c index f7f7984bb749..3ac535bd99ca 100644 --- a/drivers/gpu/drm/tegra/dc.c +++ b/drivers/gpu/drm/tegra/dc.c @@ -2014,9 +2014,8 @@ static int tegra_dc_init(struct host1x_client *client) if (!dc->syncpt) dev_warn(dc->dev, "failed to allocate syncpoint\n"); - dc->group = host1x_client_iommu_attach(client, true); - if (IS_ERR(dc->group)) { - err = PTR_ERR(dc->group); + err = host1x_client_iommu_attach(client, true); + if (err < 0) { dev_err(client->dev, "failed to attach to domain: %d\n", err); return err; } @@ -2089,7 +2088,7 @@ cleanup: if (!IS_ERR(primary)) drm_plane_cleanup(primary); - host1x_client_iommu_detach(client, dc->group); + host1x_client_iommu_detach(client); host1x_syncpt_free(dc->syncpt); return err; @@ -2114,7 +2113,7 @@ static int tegra_dc_exit(struct host1x_client *client) return err; } - host1x_client_iommu_detach(client, dc->group); + host1x_client_iommu_detach(client); host1x_syncpt_free(dc->syncpt); return 0; diff --git a/drivers/gpu/drm/tegra/dc.h b/drivers/gpu/drm/tegra/dc.h index 0c4d17851f47..3d8ddccd758f 100644 --- a/drivers/gpu/drm/tegra/dc.h +++ b/drivers/gpu/drm/tegra/dc.h @@ -90,8 +90,6 @@ struct tegra_dc { struct drm_info_list *debugfs_files; const struct tegra_dc_soc_info *soc; - - struct iommu_group *group; }; static inline struct tegra_dc * diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index 498d22a65616..b74362cb63eb 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -1068,8 +1068,7 @@ int tegra_drm_unregister_client(struct tegra_drm *tegra, return 0; } -struct iommu_group *host1x_client_iommu_attach(struct host1x_client *client, - bool shared) +int host1x_client_iommu_attach(struct host1x_client *client, bool shared) { struct drm_device *drm = dev_get_drvdata(client->parent); struct tegra_drm *tegra = drm->dev_private; @@ -1080,7 +1079,7 @@ struct iommu_group *host1x_client_iommu_attach(struct host1x_client *client, group = iommu_group_get(client->dev); if (!group) { dev_err(client->dev, "failed to get IOMMU group\n"); - return ERR_PTR(-ENODEV); + return -ENODEV; } if (!shared || (shared && (group != tegra->group))) { @@ -1095,7 +1094,7 @@ struct iommu_group *host1x_client_iommu_attach(struct host1x_client *client, err = iommu_attach_group(tegra->domain, group); if (err < 0) { iommu_group_put(group); - return ERR_PTR(err); + return err; } if (shared && !tegra->group) @@ -1103,22 +1102,23 @@ struct iommu_group *host1x_client_iommu_attach(struct host1x_client *client, } } - return group; + client->group = group; + + return 0; } -void host1x_client_iommu_detach(struct host1x_client *client, - struct iommu_group *group) +void host1x_client_iommu_detach(struct host1x_client *client) { struct drm_device *drm = dev_get_drvdata(client->parent); struct tegra_drm *tegra = drm->dev_private; - if (group) { - if (group == tegra->group) { - iommu_detach_group(tegra->domain, group); + if (client->group) { + if (client->group == tegra->group) { + iommu_detach_group(tegra->domain, client->group); tegra->group = NULL; } - iommu_group_put(group); + iommu_group_put(client->group); } } diff --git a/drivers/gpu/drm/tegra/drm.h b/drivers/gpu/drm/tegra/drm.h index 29911eff9ceb..6a06d636e930 100644 --- a/drivers/gpu/drm/tegra/drm.h +++ b/drivers/gpu/drm/tegra/drm.h @@ -100,10 +100,8 @@ int tegra_drm_register_client(struct tegra_drm *tegra, struct tegra_drm_client *client); int tegra_drm_unregister_client(struct tegra_drm *tegra, struct tegra_drm_client *client); -struct iommu_group *host1x_client_iommu_attach(struct host1x_client *client, - bool shared); -void host1x_client_iommu_detach(struct host1x_client *client, - struct iommu_group *group); +int host1x_client_iommu_attach(struct host1x_client *client, bool shared); +void host1x_client_iommu_detach(struct host1x_client *client); int tegra_drm_init(struct tegra_drm *tegra, struct drm_device *drm); int tegra_drm_exit(struct tegra_drm *tegra); diff --git a/drivers/gpu/drm/tegra/gr2d.c b/drivers/gpu/drm/tegra/gr2d.c index 3cbb4a029c41..5d5af9a05c18 100644 --- a/drivers/gpu/drm/tegra/gr2d.c +++ b/drivers/gpu/drm/tegra/gr2d.c @@ -17,7 +17,6 @@ struct gr2d_soc { }; struct gr2d { - struct iommu_group *group; struct tegra_drm_client client; struct host1x_channel *channel; struct clk *clk; @@ -51,9 +50,8 @@ static int gr2d_init(struct host1x_client *client) goto put; } - gr2d->group = host1x_client_iommu_attach(client, false); - if (IS_ERR(gr2d->group)) { - err = PTR_ERR(gr2d->group); + err = host1x_client_iommu_attach(client, false); + if (err < 0) { dev_err(client->dev, "failed to attach to domain: %d\n", err); goto free; } @@ -67,7 +65,7 @@ static int gr2d_init(struct host1x_client *client) return 0; detach: - host1x_client_iommu_detach(client, gr2d->group); + host1x_client_iommu_detach(client); free: host1x_syncpt_free(client->syncpts[0]); put: @@ -87,7 +85,7 @@ static int gr2d_exit(struct host1x_client *client) if (err < 0) return err; - host1x_client_iommu_detach(client, gr2d->group); + host1x_client_iommu_detach(client); host1x_syncpt_free(client->syncpts[0]); host1x_channel_put(gr2d->channel); diff --git a/drivers/gpu/drm/tegra/gr3d.c b/drivers/gpu/drm/tegra/gr3d.c index 87a386134cc4..c249a6bd8d51 100644 --- a/drivers/gpu/drm/tegra/gr3d.c +++ b/drivers/gpu/drm/tegra/gr3d.c @@ -23,7 +23,6 @@ struct gr3d_soc { }; struct gr3d { - struct iommu_group *group; struct tegra_drm_client client; struct host1x_channel *channel; struct clk *clk_secondary; @@ -60,9 +59,8 @@ static int gr3d_init(struct host1x_client *client) goto put; } - gr3d->group = host1x_client_iommu_attach(client, false); - if (IS_ERR(gr3d->group)) { - err = PTR_ERR(gr3d->group); + err = host1x_client_iommu_attach(client, false); + if (err < 0) { dev_err(client->dev, "failed to attach to domain: %d\n", err); goto free; } @@ -76,7 +74,7 @@ static int gr3d_init(struct host1x_client *client) return 0; detach: - host1x_client_iommu_detach(client, gr3d->group); + host1x_client_iommu_detach(client); free: host1x_syncpt_free(client->syncpts[0]); put: @@ -95,7 +93,7 @@ static int gr3d_exit(struct host1x_client *client) if (err < 0) return err; - host1x_client_iommu_detach(client, gr3d->group); + host1x_client_iommu_detach(client); host1x_syncpt_free(client->syncpts[0]); host1x_channel_put(gr3d->channel); diff --git a/drivers/gpu/drm/tegra/vic.c b/drivers/gpu/drm/tegra/vic.c index e4b17c7ce708..d34b1ada422c 100644 --- a/drivers/gpu/drm/tegra/vic.c +++ b/drivers/gpu/drm/tegra/vic.c @@ -34,7 +34,6 @@ struct vic { void __iomem *regs; struct tegra_drm_client client; struct host1x_channel *channel; - struct iommu_group *group; struct device *dev; struct clk *clk; struct reset_control *rst; @@ -188,9 +187,8 @@ static int vic_init(struct host1x_client *client) struct vic *vic = to_vic(drm); int err; - vic->group = host1x_client_iommu_attach(client, false); - if (IS_ERR(vic->group)) { - err = PTR_ERR(vic->group); + err = host1x_client_iommu_attach(client, false); + if (err < 0) { dev_err(vic->dev, "failed to attach to domain: %d\n", err); return err; } @@ -224,7 +222,7 @@ free_syncpt: free_channel: host1x_channel_put(vic->channel); detach: - host1x_client_iommu_detach(client, vic->group); + host1x_client_iommu_detach(client); return err; } @@ -246,7 +244,7 @@ static int vic_exit(struct host1x_client *client) host1x_syncpt_free(client->syncpts[0]); host1x_channel_put(vic->channel); - host1x_client_iommu_detach(client, vic->group); + host1x_client_iommu_detach(client); return 0; } diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 4396cd566a33..df6e613ba715 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -18,6 +18,7 @@ enum host1x_class { }; struct host1x_client; +struct iommu_group; /** * struct host1x_client_ops - host1x client operations @@ -34,6 +35,7 @@ struct host1x_client_ops { * @list: list node for the host1x client * @parent: pointer to struct device representing the host1x controller * @dev: pointer to struct device backing this host1x client + * @group: IOMMU group that this client is a member of * @ops: host1x client operations * @class: host1x class represented by this client * @channel: host1x channel associated with this client @@ -44,6 +46,7 @@ struct host1x_client { struct list_head list; struct device *parent; struct device *dev; + struct iommu_group *group; const struct host1x_client_ops *ops; -- cgit v1.2.3-71-gd317 From 69393cb03ccdf29f3b452d3482ef918469d1c098 Mon Sep 17 00:00:00 2001 From: "Christopher M. Riedl" Date: Sat, 7 Sep 2019 01:11:24 -0500 Subject: powerpc/xmon: Restrict when kernel is locked down Xmon should be either fully or partially disabled depending on the kernel lockdown state. Put xmon into read-only mode for lockdown=integrity and prevent user entry into xmon when lockdown=confidentiality. Xmon checks the lockdown state on every attempted entry: (1) during early xmon'ing (2) when triggered via sysrq (3) when toggled via debugfs (4) when triggered via a previously enabled breakpoint The following lockdown state transitions are handled: (1) lockdown=none -> lockdown=integrity set xmon read-only mode (2) lockdown=none -> lockdown=confidentiality clear all breakpoints, set xmon read-only mode, prevent user re-entry into xmon (3) lockdown=integrity -> lockdown=confidentiality clear all breakpoints, set xmon read-only mode, prevent user re-entry into xmon Suggested-by: Andrew Donnellan Signed-off-by: Christopher M. Riedl Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20190907061124.1947-3-cmr@informatik.wtf --- arch/powerpc/xmon/xmon.c | 103 ++++++++++++++++++++++++++++++++++--------- include/linux/security.h | 2 + security/lockdown/lockdown.c | 2 + 3 files changed, 86 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 0a0d84261678..0a438b51dbb5 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include @@ -187,6 +188,8 @@ static void dump_tlb_44x(void); static void dump_tlb_book3e(void); #endif +static void clear_all_bpt(void); + #ifdef CONFIG_PPC64 #define REG "%.16lx" #else @@ -283,10 +286,38 @@ Commands:\n\ " U show uptime information\n" " ? help\n" " # n limit output to n lines per page (for dp, dpa, dl)\n" -" zr reboot\n\ - zh halt\n" +" zr reboot\n" +" zh halt\n" ; +#ifdef CONFIG_SECURITY +static bool xmon_is_locked_down(void) +{ + static bool lockdown; + + if (!lockdown) { + lockdown = !!security_locked_down(LOCKDOWN_XMON_RW); + if (lockdown) { + printf("xmon: Disabled due to kernel lockdown\n"); + xmon_is_ro = true; + } + } + + if (!xmon_is_ro) { + xmon_is_ro = !!security_locked_down(LOCKDOWN_XMON_WR); + if (xmon_is_ro) + printf("xmon: Read-only due to kernel lockdown\n"); + } + + return lockdown; +} +#else /* CONFIG_SECURITY */ +static inline bool xmon_is_locked_down(void) +{ + return false; +} +#endif + static struct pt_regs *xmon_regs; static inline void sync(void) @@ -438,7 +469,10 @@ static bool wait_for_other_cpus(int ncpus) return false; } -#endif /* CONFIG_SMP */ +#else /* CONFIG_SMP */ +static inline void get_output_lock(void) {} +static inline void release_output_lock(void) {} +#endif static inline int unrecoverable_excp(struct pt_regs *regs) { @@ -455,6 +489,7 @@ static int xmon_core(struct pt_regs *regs, int fromipi) int cmd = 0; struct bpt *bp; long recurse_jmp[JMP_BUF_LEN]; + bool locked_down; unsigned long offset; unsigned long flags; #ifdef CONFIG_SMP @@ -465,6 +500,8 @@ static int xmon_core(struct pt_regs *regs, int fromipi) local_irq_save(flags); hard_irq_disable(); + locked_down = xmon_is_locked_down(); + if (!fromipi) { tracing_enabled = tracing_is_on(); tracing_off(); @@ -518,7 +555,8 @@ static int xmon_core(struct pt_regs *regs, int fromipi) if (!fromipi) { get_output_lock(); - excprint(regs); + if (!locked_down) + excprint(regs); if (bp) { printf("cpu 0x%x stopped at breakpoint 0x%tx (", cpu, BP_NUM(bp)); @@ -570,10 +608,14 @@ static int xmon_core(struct pt_regs *regs, int fromipi) } remove_bpts(); disable_surveillance(); - /* for breakpoint or single step, print the current instr. */ - if (bp || TRAP(regs) == 0xd00) - ppc_inst_dump(regs->nip, 1, 0); - printf("enter ? for help\n"); + + if (!locked_down) { + /* for breakpoint or single step, print curr insn */ + if (bp || TRAP(regs) == 0xd00) + ppc_inst_dump(regs->nip, 1, 0); + printf("enter ? for help\n"); + } + mb(); xmon_gate = 1; barrier(); @@ -597,8 +639,9 @@ static int xmon_core(struct pt_regs *regs, int fromipi) spin_cpu_relax(); touch_nmi_watchdog(); } else { - cmd = cmds(regs); - if (cmd != 0) { + if (!locked_down) + cmd = cmds(regs); + if (locked_down || cmd != 0) { /* exiting xmon */ insert_bpts(); xmon_gate = 0; @@ -635,13 +678,16 @@ static int xmon_core(struct pt_regs *regs, int fromipi) "can't continue\n"); remove_bpts(); disable_surveillance(); - /* for breakpoint or single step, print the current instr. */ - if (bp || TRAP(regs) == 0xd00) - ppc_inst_dump(regs->nip, 1, 0); - printf("enter ? for help\n"); + if (!locked_down) { + /* for breakpoint or single step, print current insn */ + if (bp || TRAP(regs) == 0xd00) + ppc_inst_dump(regs->nip, 1, 0); + printf("enter ? for help\n"); + } } - cmd = cmds(regs); + if (!locked_down) + cmd = cmds(regs); insert_bpts(); in_xmon = 0; @@ -670,7 +716,10 @@ static int xmon_core(struct pt_regs *regs, int fromipi) } } #endif - insert_cpu_bpts(); + if (locked_down) + clear_all_bpt(); + else + insert_cpu_bpts(); touch_nmi_watchdog(); local_irq_restore(flags); @@ -3768,6 +3817,11 @@ static void xmon_init(int enable) #ifdef CONFIG_MAGIC_SYSRQ static void sysrq_handle_xmon(int key) { + if (xmon_is_locked_down()) { + clear_all_bpt(); + xmon_init(0); + return; + } /* ensure xmon is enabled */ xmon_init(1); debugger(get_irq_regs()); @@ -3789,7 +3843,6 @@ static int __init setup_xmon_sysrq(void) device_initcall(setup_xmon_sysrq); #endif /* CONFIG_MAGIC_SYSRQ */ -#ifdef CONFIG_DEBUG_FS static void clear_all_bpt(void) { int i; @@ -3807,18 +3860,22 @@ static void clear_all_bpt(void) iabr = NULL; dabr.enabled = 0; } - - printf("xmon: All breakpoints cleared\n"); } +#ifdef CONFIG_DEBUG_FS static int xmon_dbgfs_set(void *data, u64 val) { xmon_on = !!val; xmon_init(xmon_on); /* make sure all breakpoints removed when disabling */ - if (!xmon_on) + if (!xmon_on) { clear_all_bpt(); + get_output_lock(); + printf("xmon: All breakpoints cleared\n"); + release_output_lock(); + } + return 0; } @@ -3844,7 +3901,11 @@ static int xmon_early __initdata; static int __init early_parse_xmon(char *p) { - if (!p || strncmp(p, "early", 5) == 0) { + if (xmon_is_locked_down()) { + xmon_init(0); + xmon_early = 0; + xmon_on = 0; + } else if (!p || strncmp(p, "early", 5) == 0) { /* just "xmon" is equivalent to "xmon=early" */ xmon_init(1); xmon_early = 1; diff --git a/include/linux/security.h b/include/linux/security.h index a8d59d612d27..79567eacb834 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -116,12 +116,14 @@ enum lockdown_reason { LOCKDOWN_MODULE_PARAMETERS, LOCKDOWN_MMIOTRACE, LOCKDOWN_DEBUGFS, + LOCKDOWN_XMON_WR, LOCKDOWN_INTEGRITY_MAX, LOCKDOWN_KCORE, LOCKDOWN_KPROBES, LOCKDOWN_BPF_READ, LOCKDOWN_PERF, LOCKDOWN_TRACEFS, + LOCKDOWN_XMON_RW, LOCKDOWN_CONFIDENTIALITY_MAX, }; diff --git a/security/lockdown/lockdown.c b/security/lockdown/lockdown.c index 8a10b43daf74..c1a9e5f3a19d 100644 --- a/security/lockdown/lockdown.c +++ b/security/lockdown/lockdown.c @@ -31,12 +31,14 @@ static const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1] = { [LOCKDOWN_MODULE_PARAMETERS] = "unsafe module parameters", [LOCKDOWN_MMIOTRACE] = "unsafe mmio", [LOCKDOWN_DEBUGFS] = "debugfs access", + [LOCKDOWN_XMON_WR] = "xmon write access", [LOCKDOWN_INTEGRITY_MAX] = "integrity", [LOCKDOWN_KCORE] = "/proc/kcore access", [LOCKDOWN_KPROBES] = "use of kprobes", [LOCKDOWN_BPF_READ] = "use of bpf to read kernel RAM", [LOCKDOWN_PERF] = "unsafe use of perf", [LOCKDOWN_TRACEFS] = "use of tracefs", + [LOCKDOWN_XMON_RW] = "xmon read and write access", [LOCKDOWN_CONFIDENTIALITY_MAX] = "confidentiality", }; -- cgit v1.2.3-71-gd317 From fc1adfe306b71e094df636012f8c0fed971cad45 Mon Sep 17 00:00:00 2001 From: Alexey Budankov Date: Wed, 23 Oct 2019 10:11:04 +0300 Subject: perf/core, perf/x86: Introduce swap_task_ctx() method at 'struct pmu' Declare swap_task_ctx() methods at the generic and x86 specific pmu types to bridge calls to platform specific PMU code on optimized context switch path between equivalent task perf event contexts. Signed-off-by: Alexey Budankov Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Ian Rogers Cc: Jiri Olsa Cc: Kan Liang Cc: Linus Torvalds Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Song Liu Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Link: https://lkml.kernel.org/r/9a0aa84a-f062-9b64-3133-373658550c4b@linux.intel.com Signed-off-by: Ingo Molnar --- arch/x86/events/perf_event.h | 8 ++++++++ include/linux/perf_event.h | 9 +++++++++ 2 files changed, 17 insertions(+) (limited to 'include/linux') diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index ecacfbf4ebc1..5384317eaa16 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -682,6 +682,14 @@ struct x86_pmu { */ atomic_t lbr_exclusive[x86_lbr_exclusive_max]; + /* + * perf task context (i.e. struct perf_event_context::task_ctx_data) + * switch helper to bridge calls from perf/core to perf/x86. + * See struct pmu::swap_task_ctx() usage for examples; + */ + void (*swap_task_ctx)(struct perf_event_context *prev, + struct perf_event_context *next); + /* * AMD bits */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 4f77b22d47be..011dcbdbccc2 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -410,6 +410,15 @@ struct pmu { */ size_t task_ctx_size; + /* + * PMU specific parts of task perf event context (i.e. ctx->task_ctx_data) + * can be synchronized using this function. See Intel LBR callstack support + * implementation and Perf core context switch handling callbacks for usage + * examples. + */ + void (*swap_task_ctx) (struct perf_event_context *prev, + struct perf_event_context *next); + /* optional */ /* * Set up pmu-private data structures for an AUX area -- cgit v1.2.3-71-gd317 From 837a6e7f5cdb5e411c6187729e12962c2705160d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Oct 2019 22:26:02 -0700 Subject: fs: add generic UNRESVSP and ZERO_RANGE ioctl handlers These use the same scheme as the pre-existing mapping of the XFS RESVP ioctls to ->falloc, so just extend it and remove the XFS implementation. Signed-off-by: Christoph Hellwig [darrick: fix compile error on s390] Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/compat_ioctl.c | 31 ++++++++++++++++++---- fs/ioctl.c | 12 ++++++--- fs/xfs/xfs_ioctl.c | 72 +++++++++----------------------------------------- fs/xfs/xfs_ioctl.h | 1 - fs/xfs/xfs_ioctl32.c | 7 ++--- include/linux/falloc.h | 3 +++ include/linux/fs.h | 2 +- 7 files changed, 53 insertions(+), 75 deletions(-) (limited to 'include/linux') diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index a7ec2d3dff92..62e530814cef 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -480,11 +480,14 @@ struct space_resv_32 { __s32 l_pad[4]; /* reserve area */ }; -#define FS_IOC_RESVSP_32 _IOW ('X', 40, struct space_resv_32) +#define FS_IOC_RESVSP_32 _IOW ('X', 40, struct space_resv_32) +#define FS_IOC_UNRESVSP_32 _IOW ('X', 41, struct space_resv_32) #define FS_IOC_RESVSP64_32 _IOW ('X', 42, struct space_resv_32) +#define FS_IOC_UNRESVSP64_32 _IOW ('X', 43, struct space_resv_32) +#define FS_IOC_ZERO_RANGE_32 _IOW ('X', 57, struct space_resv_32) /* just account for different alignment */ -static int compat_ioctl_preallocate(struct file *file, +static int compat_ioctl_preallocate(struct file *file, int mode, struct space_resv_32 __user *p32) { struct space_resv __user *p = compat_alloc_user_space(sizeof(*p)); @@ -498,7 +501,7 @@ static int compat_ioctl_preallocate(struct file *file, copy_in_user(&p->l_pad, &p32->l_pad, 4*sizeof(u32))) return -EFAULT; - return ioctl_preallocate(file, p); + return ioctl_preallocate(file, mode, p); } #endif @@ -1022,12 +1025,30 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, #if defined(CONFIG_IA64) || defined(CONFIG_X86_64) case FS_IOC_RESVSP_32: case FS_IOC_RESVSP64_32: - error = compat_ioctl_preallocate(f.file, compat_ptr(arg)); + error = compat_ioctl_preallocate(f.file, 0, compat_ptr(arg)); + goto out_fput; + case FS_IOC_UNRESVSP_32: + case FS_IOC_UNRESVSP64_32: + error = compat_ioctl_preallocate(f.file, FALLOC_FL_PUNCH_HOLE, + compat_ptr(arg)); + goto out_fput; + case FS_IOC_ZERO_RANGE_32: + error = compat_ioctl_preallocate(f.file, FALLOC_FL_ZERO_RANGE, + compat_ptr(arg)); goto out_fput; #else case FS_IOC_RESVSP: case FS_IOC_RESVSP64: - error = ioctl_preallocate(f.file, compat_ptr(arg)); + error = ioctl_preallocate(f.file, 0, compat_ptr(arg)); + goto out_fput; + case FS_IOC_UNRESVSP: + case FS_IOC_UNRESVSP64: + error = ioctl_preallocate(f.file, FALLOC_FL_PUNCH_HOLE, + compat_ptr(arg)); + goto out_fput; + case FS_IOC_ZERO_RANGE: + error = ioctl_preallocate(f.file, FALLOC_FL_ZERO_RANGE, + compat_ptr(arg)); goto out_fput; #endif diff --git a/fs/ioctl.c b/fs/ioctl.c index fef3a6bf7c78..55c7cfb0e599 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -466,7 +466,7 @@ EXPORT_SYMBOL(generic_block_fiemap); * Only the l_start, l_len and l_whence fields of the 'struct space_resv' * are used here, rest are ignored. */ -int ioctl_preallocate(struct file *filp, void __user *argp) +int ioctl_preallocate(struct file *filp, int mode, void __user *argp) { struct inode *inode = file_inode(filp); struct space_resv sr; @@ -487,7 +487,8 @@ int ioctl_preallocate(struct file *filp, void __user *argp) return -EINVAL; } - return vfs_fallocate(filp, FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len); + return vfs_fallocate(filp, mode | FALLOC_FL_KEEP_SIZE, sr.l_start, + sr.l_len); } static int file_ioctl(struct file *filp, unsigned int cmd, @@ -503,7 +504,12 @@ static int file_ioctl(struct file *filp, unsigned int cmd, return put_user(i_size_read(inode) - filp->f_pos, p); case FS_IOC_RESVSP: case FS_IOC_RESVSP64: - return ioctl_preallocate(filp, p); + return ioctl_preallocate(filp, 0, p); + case FS_IOC_UNRESVSP: + case FS_IOC_UNRESVSP64: + return ioctl_preallocate(filp, FALLOC_FL_PUNCH_HOLE, p); + case FS_IOC_ZERO_RANGE: + return ioctl_preallocate(filp, FALLOC_FL_ZERO_RANGE, p); } return vfs_ioctl(filp, cmd, arg); diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 2f26417405a5..e897d5363d01 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -588,13 +588,12 @@ xfs_attrmulti_by_handle( int xfs_ioc_space( struct file *filp, - unsigned int cmd, xfs_flock64_t *bf) { struct inode *inode = file_inode(filp); struct xfs_inode *ip = XFS_I(inode); struct iattr iattr; - enum xfs_prealloc_flags flags = 0; + enum xfs_prealloc_flags flags = XFS_PREALLOC_CLEAR; uint iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL; int error; @@ -635,65 +634,21 @@ xfs_ioc_space( goto out_unlock; } - /* - * length of <= 0 for resv/unresv/zero is invalid. length for - * alloc/free is ignored completely and we have no idea what userspace - * might have set it to, so set it to zero to allow range - * checks to pass. - */ - switch (cmd) { - case XFS_IOC_ZERO_RANGE: - case XFS_IOC_UNRESVSP: - case XFS_IOC_UNRESVSP64: - if (bf->l_len <= 0) { - error = -EINVAL; - goto out_unlock; - } - break; - default: - bf->l_len = 0; - break; - } - - if (bf->l_start < 0 || - bf->l_start > inode->i_sb->s_maxbytes || - bf->l_start + bf->l_len < 0 || - bf->l_start + bf->l_len >= inode->i_sb->s_maxbytes) { + if (bf->l_start < 0 || bf->l_start > inode->i_sb->s_maxbytes) { error = -EINVAL; goto out_unlock; } - switch (cmd) { - case XFS_IOC_ZERO_RANGE: - flags |= XFS_PREALLOC_SET; - error = xfs_zero_file_space(ip, bf->l_start, bf->l_len); - break; - case XFS_IOC_UNRESVSP: - case XFS_IOC_UNRESVSP64: - error = xfs_free_file_space(ip, bf->l_start, bf->l_len); - break; - case XFS_IOC_ALLOCSP: - case XFS_IOC_ALLOCSP64: - case XFS_IOC_FREESP: - case XFS_IOC_FREESP64: - flags |= XFS_PREALLOC_CLEAR; - if (bf->l_start > XFS_ISIZE(ip)) { - error = xfs_alloc_file_space(ip, XFS_ISIZE(ip), - bf->l_start - XFS_ISIZE(ip), 0); - if (error) - goto out_unlock; - } - - iattr.ia_valid = ATTR_SIZE; - iattr.ia_size = bf->l_start; - - error = xfs_vn_setattr_size(file_dentry(filp), &iattr); - break; - default: - ASSERT(0); - error = -EINVAL; + if (bf->l_start > XFS_ISIZE(ip)) { + error = xfs_alloc_file_space(ip, XFS_ISIZE(ip), + bf->l_start - XFS_ISIZE(ip), 0); + if (error) + goto out_unlock; } + iattr.ia_valid = ATTR_SIZE; + iattr.ia_size = bf->l_start; + error = xfs_vn_setattr_size(file_dentry(filp), &iattr); if (error) goto out_unlock; @@ -2113,16 +2068,13 @@ xfs_file_ioctl( return xfs_ioc_setlabel(filp, mp, arg); case XFS_IOC_ALLOCSP: case XFS_IOC_FREESP: - case XFS_IOC_UNRESVSP: case XFS_IOC_ALLOCSP64: - case XFS_IOC_FREESP64: - case XFS_IOC_UNRESVSP64: - case XFS_IOC_ZERO_RANGE: { + case XFS_IOC_FREESP64: { xfs_flock64_t bf; if (copy_from_user(&bf, arg, sizeof(bf))) return -EFAULT; - return xfs_ioc_space(filp, cmd, &bf); + return xfs_ioc_space(filp, &bf); } case XFS_IOC_DIOINFO: { struct xfs_buftarg *target = xfs_inode_buftarg(ip); diff --git a/fs/xfs/xfs_ioctl.h b/fs/xfs/xfs_ioctl.h index 654c0bb1bcf8..25ef178cbb74 100644 --- a/fs/xfs/xfs_ioctl.h +++ b/fs/xfs/xfs_ioctl.h @@ -9,7 +9,6 @@ extern int xfs_ioc_space( struct file *filp, - unsigned int cmd, xfs_flock64_t *bf); int diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c index 257b7caf7fed..3c0d518e1039 100644 --- a/fs/xfs/xfs_ioctl32.c +++ b/fs/xfs/xfs_ioctl32.c @@ -557,16 +557,13 @@ xfs_file_compat_ioctl( case XFS_IOC_ALLOCSP_32: case XFS_IOC_FREESP_32: case XFS_IOC_ALLOCSP64_32: - case XFS_IOC_FREESP64_32: - case XFS_IOC_RESVSP64_32: - case XFS_IOC_UNRESVSP64_32: - case XFS_IOC_ZERO_RANGE_32: { + case XFS_IOC_FREESP64_32: { struct xfs_flock64 bf; if (xfs_compat_flock64_copyin(&bf, arg)) return -EFAULT; cmd = _NATIVE_IOC(cmd, struct xfs_flock64); - return xfs_ioc_space(filp, cmd, &bf); + return xfs_ioc_space(filp, &bf); } case XFS_IOC_FSGEOMETRY_V1_32: return xfs_compat_ioc_fsgeometry_v1(mp, arg); diff --git a/include/linux/falloc.h b/include/linux/falloc.h index 674d59f4d6ce..f5c73f0ec22d 100644 --- a/include/linux/falloc.h +++ b/include/linux/falloc.h @@ -20,7 +20,10 @@ struct space_resv { }; #define FS_IOC_RESVSP _IOW('X', 40, struct space_resv) +#define FS_IOC_UNRESVSP _IOW('X', 41, struct space_resv) #define FS_IOC_RESVSP64 _IOW('X', 42, struct space_resv) +#define FS_IOC_UNRESVSP64 _IOW('X', 43, struct space_resv) +#define FS_IOC_ZERO_RANGE _IOW('X', 57, struct space_resv) #define FALLOC_FL_SUPPORTED_MASK (FALLOC_FL_KEEP_SIZE | \ FALLOC_FL_PUNCH_HOLE | \ diff --git a/include/linux/fs.h b/include/linux/fs.h index e0d909d35763..2b5692207c1d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2547,7 +2547,7 @@ extern int finish_no_open(struct file *file, struct dentry *dentry); /* fs/ioctl.c */ -extern int ioctl_preallocate(struct file *filp, void __user *argp); +extern int ioctl_preallocate(struct file *filp, int mode, void __user *argp); /* fs/dcache.c */ extern void __init vfs_caches_init_early(void); -- cgit v1.2.3-71-gd317 From c3a6cf19e695c8b0a9bf8b5933f863e12d878b7c Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 18 Oct 2019 10:31:43 +0100 Subject: export: avoid code duplication in include/linux/export.h include/linux/export.h has lots of code duplication between EXPORT_SYMBOL and EXPORT_SYMBOL_NS. To improve the maintainability and readability, unify the implementation. When the symbol has no namespace, pass the empty string "" to the 'ns' parameter. The drawback of this change is, it grows the code size. When the symbol has no namespace, sym->namespace was previously NULL, but it is now an empty string "". So, it increases 1 byte for every no namespace EXPORT_SYMBOL. A typical kernel configuration has 10K exported symbols, so it increases 10KB in rough estimation. I did not come up with a good idea to refactor it without increasing the code size. I am not sure how big a deal it is, but at least include/linux/export.h looks nicer. Reviewed-by: Greg Kroah-Hartman Signed-off-by: Masahiro Yamada [maennich: rebase on top of 3 fixes for the namespace feature] Signed-off-by: Matthias Maennich Signed-off-by: Jessica Yu --- include/linux/export.h | 91 ++++++++++++++++---------------------------------- kernel/module.c | 2 +- 2 files changed, 29 insertions(+), 64 deletions(-) (limited to 'include/linux') diff --git a/include/linux/export.h b/include/linux/export.h index 941d075f03d6..201262793369 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -46,7 +46,7 @@ extern struct module __this_module; * absolute relocations that require runtime processing on relocatable * kernels. */ -#define __KSYMTAB_ENTRY_NS(sym, sec) \ +#define __KSYMTAB_ENTRY(sym, sec) \ __ADDRESSABLE(sym) \ asm(" .section \"___ksymtab" sec "+" #sym "\", \"a\" \n" \ " .balign 4 \n" \ @@ -56,33 +56,17 @@ extern struct module __this_module; " .long __kstrtabns_" #sym "- . \n" \ " .previous \n") -#define __KSYMTAB_ENTRY(sym, sec) \ - __ADDRESSABLE(sym) \ - asm(" .section \"___ksymtab" sec "+" #sym "\", \"a\" \n" \ - " .balign 4 \n" \ - "__ksymtab_" #sym ": \n" \ - " .long " #sym "- . \n" \ - " .long __kstrtab_" #sym "- . \n" \ - " .long 0 \n" \ - " .previous \n") - struct kernel_symbol { int value_offset; int name_offset; int namespace_offset; }; #else -#define __KSYMTAB_ENTRY_NS(sym, sec) \ - static const struct kernel_symbol __ksymtab_##sym \ - __attribute__((section("___ksymtab" sec "+" #sym), used)) \ - __aligned(sizeof(void *)) \ - = { (unsigned long)&sym, __kstrtab_##sym, __kstrtabns_##sym } - #define __KSYMTAB_ENTRY(sym, sec) \ static const struct kernel_symbol __ksymtab_##sym \ __attribute__((section("___ksymtab" sec "+" #sym), used)) \ __aligned(sizeof(void *)) \ - = { (unsigned long)&sym, __kstrtab_##sym, NULL } + = { (unsigned long)&sym, __kstrtab_##sym, __kstrtabns_##sym } struct kernel_symbol { unsigned long value; @@ -93,28 +77,20 @@ struct kernel_symbol { #ifdef __GENKSYMS__ -#define ___EXPORT_SYMBOL(sym,sec) __GENKSYMS_EXPORT_SYMBOL(sym) -#define ___EXPORT_SYMBOL_NS(sym,sec,ns) __GENKSYMS_EXPORT_SYMBOL(sym) +#define ___EXPORT_SYMBOL(sym, sec, ns) __GENKSYMS_EXPORT_SYMBOL(sym) #else -#define ___export_symbol_common(sym, sec) \ +/* For every exported symbol, place a struct in the __ksymtab section */ +#define ___EXPORT_SYMBOL(sym, sec, ns) \ extern typeof(sym) sym; \ __CRC_SYMBOL(sym, sec); \ static const char __kstrtab_##sym[] \ __attribute__((section("__ksymtab_strings"), used, aligned(1))) \ - = #sym \ - -/* For every exported symbol, place a struct in the __ksymtab section */ -#define ___EXPORT_SYMBOL_NS(sym, sec, ns) \ - ___export_symbol_common(sym, sec); \ + = #sym; \ static const char __kstrtabns_##sym[] \ __attribute__((section("__ksymtab_strings"), used, aligned(1))) \ - = #ns; \ - __KSYMTAB_ENTRY_NS(sym, sec) - -#define ___EXPORT_SYMBOL(sym, sec) \ - ___export_symbol_common(sym, sec); \ + = ns; \ __KSYMTAB_ENTRY(sym, sec) #endif @@ -126,8 +102,7 @@ struct kernel_symbol { * be reused in other execution contexts such as the UEFI stub or the * decompressor. */ -#define __EXPORT_SYMBOL_NS(sym, sec, ns) -#define __EXPORT_SYMBOL(sym, sec) +#define __EXPORT_SYMBOL(sym, sec, ns) #elif defined(CONFIG_TRIM_UNUSED_KSYMS) @@ -143,48 +118,38 @@ struct kernel_symbol { #define __ksym_marker(sym) \ static int __ksym_marker_##sym[0] __section(".discard.ksym") __used -#define __EXPORT_SYMBOL(sym, sec) \ - __ksym_marker(sym); \ - __cond_export_sym(sym, sec, __is_defined(__KSYM_##sym)) -#define __cond_export_sym(sym, sec, conf) \ - ___cond_export_sym(sym, sec, conf) -#define ___cond_export_sym(sym, sec, enabled) \ - __cond_export_sym_##enabled(sym, sec) -#define __cond_export_sym_1(sym, sec) ___EXPORT_SYMBOL(sym, sec) -#define __cond_export_sym_0(sym, sec) /* nothing */ - -#define __EXPORT_SYMBOL_NS(sym, sec, ns) \ +#define __EXPORT_SYMBOL(sym, sec, ns) \ __ksym_marker(sym); \ - __cond_export_ns_sym(sym, sec, ns, __is_defined(__KSYM_##sym)) -#define __cond_export_ns_sym(sym, sec, ns, conf) \ - ___cond_export_ns_sym(sym, sec, ns, conf) -#define ___cond_export_ns_sym(sym, sec, ns, enabled) \ - __cond_export_ns_sym_##enabled(sym, sec, ns) -#define __cond_export_ns_sym_1(sym, sec, ns) ___EXPORT_SYMBOL_NS(sym, sec, ns) -#define __cond_export_ns_sym_0(sym, sec, ns) /* nothing */ + __cond_export_sym(sym, sec, ns, __is_defined(__KSYM_##sym)) +#define __cond_export_sym(sym, sec, ns, conf) \ + ___cond_export_sym(sym, sec, ns, conf) +#define ___cond_export_sym(sym, sec, ns, enabled) \ + __cond_export_sym_##enabled(sym, sec, ns) +#define __cond_export_sym_1(sym, sec, ns) ___EXPORT_SYMBOL(sym, sec, ns) +#define __cond_export_sym_0(sym, sec, ns) /* nothing */ #else -#define __EXPORT_SYMBOL_NS(sym,sec,ns) ___EXPORT_SYMBOL_NS(sym,sec,ns) -#define __EXPORT_SYMBOL(sym,sec) ___EXPORT_SYMBOL(sym,sec) +#define __EXPORT_SYMBOL(sym, sec, ns) ___EXPORT_SYMBOL(sym, sec, ns) #endif /* CONFIG_MODULES */ #ifdef DEFAULT_SYMBOL_NAMESPACE -#undef __EXPORT_SYMBOL -#define __EXPORT_SYMBOL(sym, sec) \ - __EXPORT_SYMBOL_NS(sym, sec, DEFAULT_SYMBOL_NAMESPACE) +#include +#define _EXPORT_SYMBOL(sym, sec) __EXPORT_SYMBOL(sym, sec, __stringify(DEFAULT_SYMBOL_NAMESPACE)) +#else +#define _EXPORT_SYMBOL(sym, sec) __EXPORT_SYMBOL(sym, sec, "") #endif -#define EXPORT_SYMBOL(sym) __EXPORT_SYMBOL(sym, "") -#define EXPORT_SYMBOL_GPL(sym) __EXPORT_SYMBOL(sym, "_gpl") -#define EXPORT_SYMBOL_GPL_FUTURE(sym) __EXPORT_SYMBOL(sym, "_gpl_future") -#define EXPORT_SYMBOL_NS(sym, ns) __EXPORT_SYMBOL_NS(sym, "", ns) -#define EXPORT_SYMBOL_NS_GPL(sym, ns) __EXPORT_SYMBOL_NS(sym, "_gpl", ns) +#define EXPORT_SYMBOL(sym) _EXPORT_SYMBOL(sym, "") +#define EXPORT_SYMBOL_GPL(sym) _EXPORT_SYMBOL(sym, "_gpl") +#define EXPORT_SYMBOL_GPL_FUTURE(sym) _EXPORT_SYMBOL(sym, "_gpl_future") +#define EXPORT_SYMBOL_NS(sym, ns) __EXPORT_SYMBOL(sym, "", #ns) +#define EXPORT_SYMBOL_NS_GPL(sym, ns) __EXPORT_SYMBOL(sym, "_gpl", #ns) #ifdef CONFIG_UNUSED_SYMBOLS -#define EXPORT_UNUSED_SYMBOL(sym) __EXPORT_SYMBOL(sym, "_unused") -#define EXPORT_UNUSED_SYMBOL_GPL(sym) __EXPORT_SYMBOL(sym, "_unused_gpl") +#define EXPORT_UNUSED_SYMBOL(sym) _EXPORT_SYMBOL(sym, "_unused") +#define EXPORT_UNUSED_SYMBOL_GPL(sym) _EXPORT_SYMBOL(sym, "_unused_gpl") #else #define EXPORT_UNUSED_SYMBOL(sym) #define EXPORT_UNUSED_SYMBOL_GPL(sym) diff --git a/kernel/module.c b/kernel/module.c index ff2d7359a418..26c13173da3d 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1400,7 +1400,7 @@ static int verify_namespace_is_imported(const struct load_info *info, char *imported_namespace; namespace = kernel_symbol_namespace(sym); - if (namespace) { + if (namespace && namespace[0]) { imported_namespace = get_modinfo(info, "import_ns"); while (imported_namespace) { if (strcmp(namespace, imported_namespace) == 0) -- cgit v1.2.3-71-gd317 From 8e01d9a396e6db153d94a6004e6473d9ff251a6a Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sun, 27 Oct 2019 14:41:59 +0000 Subject: KVM: arm64: vgic-v4: Move the GICv4 residency flow to be driven by vcpu_load/put When the VHE code was reworked, a lot of the vgic stuff was moved around, but the GICv4 residency code did stay untouched, meaning that we come in and out of residency on each flush/sync, which is obviously suboptimal. To address this, let's move things around a bit: - Residency entry (flush) moves to vcpu_load - Residency exit (sync) moves to vcpu_put - On blocking (entry to WFI), we "put" - On unblocking (exit from WFI), we "load" Because these can nest (load/block/put/load/unblock/put, for example), we now have per-VPE tracking of the residency state. Additionally, vgic_v4_put gains a "need doorbell" parameter, which only gets set to true when blocking because of a WFI. This allows a finer control of the doorbell, which now also gets disabled as soon as it gets signaled. Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20191027144234.8395-2-maz@kernel.org --- drivers/irqchip/irq-gic-v4.c | 7 ++++- include/kvm/arm_vgic.h | 4 +-- include/linux/irqchip/arm-gic-v4.h | 2 ++ virt/kvm/arm/arm.c | 12 ++++++--- virt/kvm/arm/vgic/vgic-v3.c | 4 +++ virt/kvm/arm/vgic/vgic-v4.c | 55 ++++++++++++++++++-------------------- virt/kvm/arm/vgic/vgic.c | 4 --- virt/kvm/arm/vgic/vgic.h | 2 -- 8 files changed, 48 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/drivers/irqchip/irq-gic-v4.c b/drivers/irqchip/irq-gic-v4.c index 563e87ed0766..45969927cc81 100644 --- a/drivers/irqchip/irq-gic-v4.c +++ b/drivers/irqchip/irq-gic-v4.c @@ -141,12 +141,17 @@ static int its_send_vpe_cmd(struct its_vpe *vpe, struct its_cmd_info *info) int its_schedule_vpe(struct its_vpe *vpe, bool on) { struct its_cmd_info info; + int ret; WARN_ON(preemptible()); info.cmd_type = on ? SCHEDULE_VPE : DESCHEDULE_VPE; - return its_send_vpe_cmd(vpe, &info); + ret = its_send_vpe_cmd(vpe, &info); + if (!ret) + vpe->resident = on; + + return ret; } int its_invall_vpe(struct its_vpe *vpe) diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index af4f09c02bf1..4dc58d7a0010 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -396,7 +396,7 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int irq, int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int irq, struct kvm_kernel_irq_routing_entry *irq_entry); -void kvm_vgic_v4_enable_doorbell(struct kvm_vcpu *vcpu); -void kvm_vgic_v4_disable_doorbell(struct kvm_vcpu *vcpu); +int vgic_v4_load(struct kvm_vcpu *vcpu); +int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db); #endif /* __KVM_ARM_VGIC_H */ diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h index e6b155713b47..ab1396afe08a 100644 --- a/include/linux/irqchip/arm-gic-v4.h +++ b/include/linux/irqchip/arm-gic-v4.h @@ -35,6 +35,8 @@ struct its_vpe { /* Doorbell interrupt */ int irq; irq_hw_number_t vpe_db_lpi; + /* VPE resident */ + bool resident; /* VPE proxy mapping */ int vpe_proxy_event; /* diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 86c6aa1cb58e..bd2afcf9a13f 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -322,20 +322,24 @@ void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) /* * If we're about to block (most likely because we've just hit a * WFI), we need to sync back the state of the GIC CPU interface - * so that we have the lastest PMR and group enables. This ensures + * so that we have the latest PMR and group enables. This ensures * that kvm_arch_vcpu_runnable has up-to-date data to decide * whether we have pending interrupts. + * + * For the same reason, we want to tell GICv4 that we need + * doorbells to be signalled, should an interrupt become pending. */ preempt_disable(); kvm_vgic_vmcr_sync(vcpu); + vgic_v4_put(vcpu, true); preempt_enable(); - - kvm_vgic_v4_enable_doorbell(vcpu); } void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) { - kvm_vgic_v4_disable_doorbell(vcpu); + preempt_disable(); + vgic_v4_load(vcpu); + preempt_enable(); } int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index 8d69f007dd0c..48307a9eb1d8 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -664,6 +664,8 @@ void vgic_v3_load(struct kvm_vcpu *vcpu) if (has_vhe()) __vgic_v3_activate_traps(vcpu); + + WARN_ON(vgic_v4_load(vcpu)); } void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu) @@ -676,6 +678,8 @@ void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu) void vgic_v3_put(struct kvm_vcpu *vcpu) { + WARN_ON(vgic_v4_put(vcpu, false)); + vgic_v3_vmcr_sync(vcpu); kvm_call_hyp(__vgic_v3_save_aprs, vcpu); diff --git a/virt/kvm/arm/vgic/vgic-v4.c b/virt/kvm/arm/vgic/vgic-v4.c index 477af6aebb97..7e1f3202968a 100644 --- a/virt/kvm/arm/vgic/vgic-v4.c +++ b/virt/kvm/arm/vgic/vgic-v4.c @@ -85,6 +85,10 @@ static irqreturn_t vgic_v4_doorbell_handler(int irq, void *info) { struct kvm_vcpu *vcpu = info; + /* We got the message, no need to fire again */ + if (!irqd_irq_disabled(&irq_to_desc(irq)->irq_data)) + disable_irq_nosync(irq); + vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last = true; kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); kvm_vcpu_kick(vcpu); @@ -192,20 +196,30 @@ void vgic_v4_teardown(struct kvm *kvm) its_vm->vpes = NULL; } -int vgic_v4_sync_hwstate(struct kvm_vcpu *vcpu) +int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db) { - if (!vgic_supports_direct_msis(vcpu->kvm)) + struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; + struct irq_desc *desc = irq_to_desc(vpe->irq); + + if (!vgic_supports_direct_msis(vcpu->kvm) || !vpe->resident) return 0; - return its_schedule_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe, false); + /* + * If blocking, a doorbell is required. Undo the nested + * disable_irq() calls... + */ + while (need_db && irqd_irq_disabled(&desc->irq_data)) + enable_irq(vpe->irq); + + return its_schedule_vpe(vpe, false); } -int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu) +int vgic_v4_load(struct kvm_vcpu *vcpu) { - int irq = vcpu->arch.vgic_cpu.vgic_v3.its_vpe.irq; + struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; int err; - if (!vgic_supports_direct_msis(vcpu->kvm)) + if (!vgic_supports_direct_msis(vcpu->kvm) || vpe->resident) return 0; /* @@ -214,11 +228,14 @@ int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu) * doc in drivers/irqchip/irq-gic-v4.c to understand how this * turns into a VMOVP command at the ITS level. */ - err = irq_set_affinity(irq, cpumask_of(smp_processor_id())); + err = irq_set_affinity(vpe->irq, cpumask_of(smp_processor_id())); if (err) return err; - err = its_schedule_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe, true); + /* Disabled the doorbell, as we're about to enter the guest */ + disable_irq_nosync(vpe->irq); + + err = its_schedule_vpe(vpe, true); if (err) return err; @@ -226,9 +243,7 @@ int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu) * Now that the VPE is resident, let's get rid of a potential * doorbell interrupt that would still be pending. */ - err = irq_set_irqchip_state(irq, IRQCHIP_STATE_PENDING, false); - - return err; + return irq_set_irqchip_state(vpe->irq, IRQCHIP_STATE_PENDING, false); } static struct vgic_its *vgic_get_its(struct kvm *kvm, @@ -335,21 +350,3 @@ out: mutex_unlock(&its->its_lock); return ret; } - -void kvm_vgic_v4_enable_doorbell(struct kvm_vcpu *vcpu) -{ - if (vgic_supports_direct_msis(vcpu->kvm)) { - int irq = vcpu->arch.vgic_cpu.vgic_v3.its_vpe.irq; - if (irq) - enable_irq(irq); - } -} - -void kvm_vgic_v4_disable_doorbell(struct kvm_vcpu *vcpu) -{ - if (vgic_supports_direct_msis(vcpu->kvm)) { - int irq = vcpu->arch.vgic_cpu.vgic_v3.its_vpe.irq; - if (irq) - disable_irq(irq); - } -} diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c index 45a870cb63f5..99b02ca730a8 100644 --- a/virt/kvm/arm/vgic/vgic.c +++ b/virt/kvm/arm/vgic/vgic.c @@ -857,8 +857,6 @@ void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - WARN_ON(vgic_v4_sync_hwstate(vcpu)); - /* An empty ap_list_head implies used_lrs == 0 */ if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head)) return; @@ -882,8 +880,6 @@ static inline void vgic_restore_state(struct kvm_vcpu *vcpu) /* Flush our emulation state into the GIC hardware before entering the guest. */ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) { - WARN_ON(vgic_v4_flush_hwstate(vcpu)); - /* * If there are no virtual interrupts active or pending for this * VCPU, then there is no work to do and we can bail out without diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index 83066a81b16a..c7fefd6b1c80 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -316,7 +316,5 @@ void vgic_its_invalidate_cache(struct kvm *kvm); bool vgic_supports_direct_msis(struct kvm *kvm); int vgic_v4_init(struct kvm *kvm); void vgic_v4_teardown(struct kvm *kvm); -int vgic_v4_sync_hwstate(struct kvm_vcpu *vcpu); -int vgic_v4_flush_hwstate(struct kvm_vcpu *vcpu); #endif -- cgit v1.2.3-71-gd317 From 74bddb3682f60df16ba24be335c94de348ba1b07 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 9 Oct 2019 13:09:24 -0300 Subject: RDMA/mlx5: Delete struct mlx5_priv->mkey_table No users are left, delete it. Link: https://lore.kernel.org/r/20191009160934.3143-5-jgg@ziepe.ca Reviewed-by: Artemy Kovalyov Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/mr.c | 9 --------- drivers/net/ethernet/mellanox/mlx5/core/main.c | 4 ---- drivers/net/ethernet/mellanox/mlx5/core/mr.c | 28 +------------------------- include/linux/mlx5/driver.h | 4 ---- 4 files changed, 1 insertion(+), 44 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 60b12dc53004..fd94838a8845 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -90,8 +90,6 @@ static void reg_mr_callback(int status, struct mlx5_async_work *context) struct mlx5_cache_ent *ent = &cache->ent[c]; u8 key; unsigned long flags; - struct xarray *mkeys = &dev->mdev->priv.mkey_table; - int err; spin_lock_irqsave(&ent->lock, flags); ent->pending--; @@ -118,13 +116,6 @@ static void reg_mr_callback(int status, struct mlx5_async_work *context) ent->size++; spin_unlock_irqrestore(&ent->lock, flags); - xa_lock_irqsave(mkeys, flags); - err = xa_err(__xa_store(mkeys, mlx5_base_mkey(mr->mmkey.key), - &mr->mmkey, GFP_ATOMIC)); - xa_unlock_irqrestore(mkeys, flags); - if (err) - pr_err("Error inserting to mkey tree. 0x%x\n", -err); - if (!completion_done(&ent->compl)) complete(&ent->compl); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index e47dd7c1b909..d10051f39b9c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -837,8 +837,6 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) mlx5_init_qp_table(dev); - mlx5_init_mkey_table(dev); - mlx5_init_reserved_gids(dev); mlx5_init_clock(dev); @@ -896,7 +894,6 @@ err_rl_cleanup: err_tables_cleanup: mlx5_geneve_destroy(dev->geneve); mlx5_vxlan_destroy(dev->vxlan); - mlx5_cleanup_mkey_table(dev); mlx5_cleanup_qp_table(dev); mlx5_cq_debugfs_cleanup(dev); mlx5_events_cleanup(dev); @@ -924,7 +921,6 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev) mlx5_vxlan_destroy(dev->vxlan); mlx5_cleanup_clock(dev); mlx5_cleanup_reserved_gids(dev); - mlx5_cleanup_mkey_table(dev); mlx5_cleanup_qp_table(dev); mlx5_cq_debugfs_cleanup(dev); mlx5_events_cleanup(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c index c501bf2a0252..42cc3c7ac5b6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c @@ -36,16 +36,6 @@ #include #include "mlx5_core.h" -void mlx5_init_mkey_table(struct mlx5_core_dev *dev) -{ - xa_init_flags(&dev->priv.mkey_table, XA_FLAGS_LOCK_IRQ); -} - -void mlx5_cleanup_mkey_table(struct mlx5_core_dev *dev) -{ - WARN_ON(!xa_empty(&dev->priv.mkey_table)); -} - int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey, struct mlx5_async_ctx *async_ctx, u32 *in, @@ -54,7 +44,6 @@ int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev, struct mlx5_async_work *context) { u32 lout[MLX5_ST_SZ_DW(create_mkey_out)] = {0}; - struct xarray *mkeys = &dev->priv.mkey_table; u32 mkey_index; void *mkc; int err; @@ -84,16 +73,7 @@ int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev, mlx5_core_dbg(dev, "out 0x%x, key 0x%x, mkey 0x%x\n", mkey_index, key, mkey->key); - - err = xa_err(xa_store_irq(mkeys, mlx5_base_mkey(mkey->key), mkey, - GFP_KERNEL)); - if (err) { - mlx5_core_warn(dev, "failed xarray insert of mkey 0x%x, %d\n", - mlx5_base_mkey(mkey->key), err); - mlx5_core_destroy_mkey(dev, mkey); - } - - return err; + return 0; } EXPORT_SYMBOL(mlx5_core_create_mkey_cb); @@ -111,12 +91,6 @@ int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, { u32 out[MLX5_ST_SZ_DW(destroy_mkey_out)] = {0}; u32 in[MLX5_ST_SZ_DW(destroy_mkey_in)] = {0}; - struct xarray *mkeys = &dev->priv.mkey_table; - unsigned long flags; - - xa_lock_irqsave(mkeys, flags); - __xa_erase(mkeys, mlx5_base_mkey(mkey->key)); - xa_unlock_irqrestore(mkeys, flags); MLX5_SET(destroy_mkey_in, in, opcode, MLX5_CMD_OP_DESTROY_MKEY); MLX5_SET(destroy_mkey_in, in, mkey_index, mlx5_mkey_to_idx(mkey->key)); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 3e80f03a387f..8288b62b8f37 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -556,8 +556,6 @@ struct mlx5_priv { struct dentry *cmdif_debugfs; /* end: qp staff */ - struct xarray mkey_table; - /* start: alloc staff */ /* protect buffer alocation according to numa node */ struct mutex alloc_mutex; @@ -942,8 +940,6 @@ struct mlx5_cmd_mailbox *mlx5_alloc_cmd_mailbox_chain(struct mlx5_core_dev *dev, gfp_t flags, int npages); void mlx5_free_cmd_mailbox_chain(struct mlx5_core_dev *dev, struct mlx5_cmd_mailbox *head); -void mlx5_init_mkey_table(struct mlx5_core_dev *dev); -void mlx5_cleanup_mkey_table(struct mlx5_core_dev *dev); int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey, struct mlx5_async_ctx *async_ctx, u32 *in, -- cgit v1.2.3-71-gd317 From 802f4a827f139f2581b3c50c69d20f8bf4c24af1 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 16 Oct 2019 04:56:47 +0200 Subject: sched/vtime: Record CPU under seqcount for kcpustat needs In order to compute the kcpustat delta on a nohz CPU, we'll need to fetch the task running on that target. Checking that its vtime state snapshot actually refers to the relevant target involves recording that CPU under the seqcount locked on task switch. This is a step toward making kcpustat moving forward on full nohz CPUs. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Cc: Jacek Anaszewski Cc: Linus Torvalds Cc: Pavel Machek Cc: Peter Zijlstra Cc: Rafael J . Wysocki Cc: Rik van Riel Cc: Thomas Gleixner Cc: Viresh Kumar Cc: Wanpeng Li Cc: Yauheni Kaliuta Link: https://lkml.kernel.org/r/20191016025700.31277-2-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 + kernel/sched/cputime.c | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2c2e56bd8913..d5d07335a97b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -259,6 +259,7 @@ struct vtime { seqcount_t seqcount; unsigned long long starttime; enum vtime_state state; + unsigned int cpu; u64 utime; u64 stime; u64 gtime; diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index cef23c211f41..40f581692254 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -818,6 +818,7 @@ void vtime_task_switch_generic(struct task_struct *prev) else __vtime_account_kernel(prev, vtime); vtime->state = VTIME_INACTIVE; + vtime->cpu = -1; write_seqcount_end(&vtime->seqcount); vtime = ¤t->vtime; @@ -825,6 +826,7 @@ void vtime_task_switch_generic(struct task_struct *prev) write_seqcount_begin(&vtime->seqcount); vtime->state = VTIME_SYS; vtime->starttime = sched_clock(); + vtime->cpu = smp_processor_id(); write_seqcount_end(&vtime->seqcount); } @@ -837,6 +839,7 @@ void vtime_init_idle(struct task_struct *t, int cpu) write_seqcount_begin(&vtime->seqcount); vtime->state = VTIME_SYS; vtime->starttime = sched_clock(); + vtime->cpu = cpu; write_seqcount_end(&vtime->seqcount); local_irq_restore(flags); } -- cgit v1.2.3-71-gd317 From 14faf6fcac4ba33f8fd8d9b2d0278010a9eb1742 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 16 Oct 2019 04:56:48 +0200 Subject: sched/cputime: Add vtime idle task state Record idle as a VTIME state instead of guessing it from VTIME_SYS and is_idle_task(). This is going to simplify the cputime read side especially as its state machine is going to further expand in order to fully support kcpustat on nohz_full. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Cc: Jacek Anaszewski Cc: Linus Torvalds Cc: Pavel Machek Cc: Peter Zijlstra Cc: Rafael J . Wysocki Cc: Rik van Riel Cc: Thomas Gleixner Cc: Viresh Kumar Cc: Wanpeng Li Cc: Yauheni Kaliuta Link: https://lkml.kernel.org/r/20191016025700.31277-3-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 6 ++++-- kernel/sched/cputime.c | 13 ++++++++----- 2 files changed, 12 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index d5d07335a97b..4ae19be2c126 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -249,10 +249,12 @@ struct prev_cputime { enum vtime_state { /* Task is sleeping or running in a CPU with VTIME inactive: */ VTIME_INACTIVE = 0, - /* Task runs in userspace in a CPU with VTIME active: */ - VTIME_USER, + /* Task is idle */ + VTIME_IDLE, /* Task runs in kernelspace in a CPU with VTIME active: */ VTIME_SYS, + /* Task runs in userspace in a CPU with VTIME active: */ + VTIME_USER, }; struct vtime { diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 40f581692254..2e885e870aa1 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -813,7 +813,7 @@ void vtime_task_switch_generic(struct task_struct *prev) struct vtime *vtime = &prev->vtime; write_seqcount_begin(&vtime->seqcount); - if (is_idle_task(prev)) + if (vtime->state == VTIME_IDLE) vtime_account_idle(prev); else __vtime_account_kernel(prev, vtime); @@ -824,7 +824,10 @@ void vtime_task_switch_generic(struct task_struct *prev) vtime = ¤t->vtime; write_seqcount_begin(&vtime->seqcount); - vtime->state = VTIME_SYS; + if (is_idle_task(current)) + vtime->state = VTIME_IDLE; + else + vtime->state = VTIME_SYS; vtime->starttime = sched_clock(); vtime->cpu = smp_processor_id(); write_seqcount_end(&vtime->seqcount); @@ -837,7 +840,7 @@ void vtime_init_idle(struct task_struct *t, int cpu) local_irq_save(flags); write_seqcount_begin(&vtime->seqcount); - vtime->state = VTIME_SYS; + vtime->state = VTIME_IDLE; vtime->starttime = sched_clock(); vtime->cpu = cpu; write_seqcount_end(&vtime->seqcount); @@ -888,8 +891,8 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) *utime = t->utime; *stime = t->stime; - /* Task is sleeping, nothing to add */ - if (vtime->state == VTIME_INACTIVE || is_idle_task(t)) + /* Task is sleeping or idle, nothing to add */ + if (vtime->state < VTIME_SYS) continue; delta = vtime_delta(vtime); -- cgit v1.2.3-71-gd317 From e6d5bf3e321ca664d12eb00ceb40bd58987ce8a1 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 16 Oct 2019 04:56:49 +0200 Subject: sched/cputime: Add vtime guest task state Record guest as a VTIME state instead of guessing it from VTIME_SYS and PF_VCPU. This is going to simplify the cputime read side especially as its state machine is going to further expand in order to fully support kcpustat on nohz_full. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Cc: Jacek Anaszewski Cc: Linus Torvalds Cc: Pavel Machek Cc: Peter Zijlstra Cc: Rafael J . Wysocki Cc: Rik van Riel Cc: Thomas Gleixner Cc: Viresh Kumar Cc: Wanpeng Li Cc: Yauheni Kaliuta Link: https://lkml.kernel.org/r/20191016025700.31277-4-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 ++ kernel/sched/cputime.c | 18 +++++++++++------- 2 files changed, 13 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4ae19be2c126..988c4da00c31 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -255,6 +255,8 @@ enum vtime_state { VTIME_SYS, /* Task runs in userspace in a CPU with VTIME active: */ VTIME_USER, + /* Task runs as guests in a CPU with VTIME active: */ + VTIME_GUEST, }; struct vtime { diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 2e885e870aa1..34086afc3518 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -733,7 +733,7 @@ static void __vtime_account_kernel(struct task_struct *tsk, struct vtime *vtime) { /* We might have scheduled out from guest path */ - if (tsk->flags & PF_VCPU) + if (vtime->state == VTIME_GUEST) vtime_account_guest(tsk, vtime); else vtime_account_system(tsk, vtime); @@ -788,6 +788,7 @@ void vtime_guest_enter(struct task_struct *tsk) write_seqcount_begin(&vtime->seqcount); vtime_account_system(tsk, vtime); tsk->flags |= PF_VCPU; + vtime->state = VTIME_GUEST; write_seqcount_end(&vtime->seqcount); } EXPORT_SYMBOL_GPL(vtime_guest_enter); @@ -799,6 +800,7 @@ void vtime_guest_exit(struct task_struct *tsk) write_seqcount_begin(&vtime->seqcount); vtime_account_guest(tsk, vtime); tsk->flags &= ~PF_VCPU; + vtime->state = VTIME_SYS; write_seqcount_end(&vtime->seqcount); } EXPORT_SYMBOL_GPL(vtime_guest_exit); @@ -826,6 +828,8 @@ void vtime_task_switch_generic(struct task_struct *prev) write_seqcount_begin(&vtime->seqcount); if (is_idle_task(current)) vtime->state = VTIME_IDLE; + else if (current->flags & PF_VCPU) + vtime->state = VTIME_GUEST; else vtime->state = VTIME_SYS; vtime->starttime = sched_clock(); @@ -860,7 +864,7 @@ u64 task_gtime(struct task_struct *t) seq = read_seqcount_begin(&vtime->seqcount); gtime = t->gtime; - if (vtime->state == VTIME_SYS && t->flags & PF_VCPU) + if (vtime->state == VTIME_GUEST) gtime += vtime->gtime + vtime_delta(vtime); } while (read_seqcount_retry(&vtime->seqcount, seq)); @@ -898,13 +902,13 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) delta = vtime_delta(vtime); /* - * Task runs either in user or kernel space, add pending nohz time to - * the right place. + * Task runs either in user (including guest) or kernel space, + * add pending nohz time to the right place. */ - if (vtime->state == VTIME_USER || t->flags & PF_VCPU) - *utime += vtime->utime + delta; - else if (vtime->state == VTIME_SYS) + if (vtime->state == VTIME_SYS) *stime += vtime->stime + delta; + else + *utime += vtime->utime + delta; } while (read_seqcount_retry(&vtime->seqcount, seq)); } #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ -- cgit v1.2.3-71-gd317 From 0ca167c056ea3d637b7959e6e94010fa526b9b8c Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 16 Oct 2019 04:56:50 +0200 Subject: context_tracking: Remove context_tracking_active() This function is a leftover from old removal or rename. We can drop it. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Cc: Jacek Anaszewski Cc: Linus Torvalds Cc: Pavel Machek Cc: Peter Zijlstra Cc: Rafael J . Wysocki Cc: Rik van Riel Cc: Thomas Gleixner Cc: Viresh Kumar Cc: Wanpeng Li Cc: Yauheni Kaliuta Link: https://lkml.kernel.org/r/20191016025700.31277-5-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/context_tracking_state.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index f128dc3be0df..f4633c2c29a5 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -42,7 +42,6 @@ static inline bool context_tracking_in_user(void) } #else static inline bool context_tracking_in_user(void) { return false; } -static inline bool context_tracking_active(void) { return false; } static inline bool context_tracking_is_enabled(void) { return false; } static inline bool context_tracking_cpu_is_enabled(void) { return false; } #endif /* CONFIG_CONTEXT_TRACKING */ -- cgit v1.2.3-71-gd317 From 74c578759f15cb5a0d0107759bdad671d7b52ab9 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 16 Oct 2019 04:56:51 +0200 Subject: context_tracking: Rename context_tracking_is_enabled() => context_tracking_enabled() Remove the superfluous "is" in the middle of the name. We want to standardize the naming so that it can be expanded through suffixes: context_tracking_enabled() context_tracking_enabled_cpu() context_tracking_enabled_this_cpu() Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Cc: Jacek Anaszewski Cc: Linus Torvalds Cc: Pavel Machek Cc: Peter Zijlstra Cc: Rafael J . Wysocki Cc: Rik van Riel Cc: Thomas Gleixner Cc: Viresh Kumar Cc: Wanpeng Li Cc: Yauheni Kaliuta Link: https://lkml.kernel.org/r/20191016025700.31277-6-frederic@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/entry/calling.h | 2 +- include/linux/context_tracking.h | 20 ++++++++++---------- include/linux/context_tracking_state.h | 8 ++++---- include/linux/tick.h | 2 +- include/linux/vtime.h | 2 +- kernel/context_tracking.c | 6 +++--- 6 files changed, 20 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 515c0ceeb4a3..0789e13ece90 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -354,7 +354,7 @@ For 32-bit we have the following conventions - kernel is built with .macro CALL_enter_from_user_mode #ifdef CONFIG_CONTEXT_TRACKING #ifdef CONFIG_JUMP_LABEL - STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_enabled, def=0 + STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_key, def=0 #endif call enter_from_user_mode .Lafter_call_\@: diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 558a209c247d..f1601bac08dc 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -22,26 +22,26 @@ extern void context_tracking_user_exit(void); static inline void user_enter(void) { - if (context_tracking_is_enabled()) + if (context_tracking_enabled()) context_tracking_enter(CONTEXT_USER); } static inline void user_exit(void) { - if (context_tracking_is_enabled()) + if (context_tracking_enabled()) context_tracking_exit(CONTEXT_USER); } /* Called with interrupts disabled. */ static inline void user_enter_irqoff(void) { - if (context_tracking_is_enabled()) + if (context_tracking_enabled()) __context_tracking_enter(CONTEXT_USER); } static inline void user_exit_irqoff(void) { - if (context_tracking_is_enabled()) + if (context_tracking_enabled()) __context_tracking_exit(CONTEXT_USER); } @@ -49,7 +49,7 @@ static inline enum ctx_state exception_enter(void) { enum ctx_state prev_ctx; - if (!context_tracking_is_enabled()) + if (!context_tracking_enabled()) return 0; prev_ctx = this_cpu_read(context_tracking.state); @@ -61,7 +61,7 @@ static inline enum ctx_state exception_enter(void) static inline void exception_exit(enum ctx_state prev_ctx) { - if (context_tracking_is_enabled()) { + if (context_tracking_enabled()) { if (prev_ctx != CONTEXT_KERNEL) context_tracking_enter(prev_ctx); } @@ -77,7 +77,7 @@ static inline void exception_exit(enum ctx_state prev_ctx) */ static inline enum ctx_state ct_state(void) { - return context_tracking_is_enabled() ? + return context_tracking_enabled() ? this_cpu_read(context_tracking.state) : CONTEXT_DISABLED; } #else @@ -90,7 +90,7 @@ static inline void exception_exit(enum ctx_state prev_ctx) { } static inline enum ctx_state ct_state(void) { return CONTEXT_DISABLED; } #endif /* !CONFIG_CONTEXT_TRACKING */ -#define CT_WARN_ON(cond) WARN_ON(context_tracking_is_enabled() && (cond)) +#define CT_WARN_ON(cond) WARN_ON(context_tracking_enabled() && (cond)) #ifdef CONFIG_CONTEXT_TRACKING_FORCE extern void context_tracking_init(void); @@ -108,7 +108,7 @@ static inline void guest_enter_irqoff(void) else current->flags |= PF_VCPU; - if (context_tracking_is_enabled()) + if (context_tracking_enabled()) __context_tracking_enter(CONTEXT_GUEST); /* KVM does not hold any references to rcu protected data when it @@ -124,7 +124,7 @@ static inline void guest_enter_irqoff(void) static inline void guest_exit_irqoff(void) { - if (context_tracking_is_enabled()) + if (context_tracking_enabled()) __context_tracking_exit(CONTEXT_GUEST); if (vtime_accounting_cpu_enabled()) diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index f4633c2c29a5..91250bdf2060 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -23,12 +23,12 @@ struct context_tracking { }; #ifdef CONFIG_CONTEXT_TRACKING -extern struct static_key_false context_tracking_enabled; +extern struct static_key_false context_tracking_key; DECLARE_PER_CPU(struct context_tracking, context_tracking); -static inline bool context_tracking_is_enabled(void) +static inline bool context_tracking_enabled(void) { - return static_branch_unlikely(&context_tracking_enabled); + return static_branch_unlikely(&context_tracking_key); } static inline bool context_tracking_cpu_is_enabled(void) @@ -42,7 +42,7 @@ static inline bool context_tracking_in_user(void) } #else static inline bool context_tracking_in_user(void) { return false; } -static inline bool context_tracking_is_enabled(void) { return false; } +static inline bool context_tracking_enabled(void) { return false; } static inline bool context_tracking_cpu_is_enabled(void) { return false; } #endif /* CONFIG_CONTEXT_TRACKING */ diff --git a/include/linux/tick.h b/include/linux/tick.h index f92a10b5e112..7e050a356cc5 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -174,7 +174,7 @@ extern cpumask_var_t tick_nohz_full_mask; static inline bool tick_nohz_full_enabled(void) { - if (!context_tracking_is_enabled()) + if (!context_tracking_enabled()) return false; return tick_nohz_full_running; diff --git a/include/linux/vtime.h b/include/linux/vtime.h index d9160ab3667a..0fc7f11f7aa4 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -28,7 +28,7 @@ extern void vtime_task_switch(struct task_struct *prev); */ static inline bool vtime_accounting_enabled(void) { - return context_tracking_is_enabled(); + return context_tracking_enabled(); } static inline bool vtime_accounting_cpu_enabled(void) diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index be01a4d627c9..0296b4bda8f1 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -25,8 +25,8 @@ #define CREATE_TRACE_POINTS #include -DEFINE_STATIC_KEY_FALSE(context_tracking_enabled); -EXPORT_SYMBOL_GPL(context_tracking_enabled); +DEFINE_STATIC_KEY_FALSE(context_tracking_key); +EXPORT_SYMBOL_GPL(context_tracking_key); DEFINE_PER_CPU(struct context_tracking, context_tracking); EXPORT_SYMBOL_GPL(context_tracking); @@ -192,7 +192,7 @@ void __init context_tracking_cpu_set(int cpu) if (!per_cpu(context_tracking.active, cpu)) { per_cpu(context_tracking.active, cpu) = true; - static_branch_inc(&context_tracking_enabled); + static_branch_inc(&context_tracking_key); } if (initialized) -- cgit v1.2.3-71-gd317 From 84e0dacd0c347e9ee2531052013babd84683245f Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 16 Oct 2019 04:56:52 +0200 Subject: context_tracking: Rename context_tracking_is_cpu_enabled() to context_tracking_enabled_this_cpu() Standardize the naming on top of the context_tracking_enabled_*() base. Also make it clear we are checking the context tracking state of the *current* CPU with this function. We'll need to add an API to check that state on remote CPUs as well, so we must disambiguate the naming. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Cc: Jacek Anaszewski Cc: Linus Torvalds Cc: Pavel Machek Cc: Peter Zijlstra Cc: Rafael J . Wysocki Cc: Rik van Riel Cc: Thomas Gleixner Cc: Viresh Kumar Cc: Wanpeng Li Cc: Yauheni Kaliuta Link: https://lkml.kernel.org/r/20191016025700.31277-7-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/context_tracking.h | 2 +- include/linux/context_tracking_state.h | 4 ++-- include/linux/vtime.h | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index f1601bac08dc..c9065ad518a7 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -118,7 +118,7 @@ static inline void guest_enter_irqoff(void) * one time slice). Lets treat guest mode as quiescent state, just like * we do with user-mode execution. */ - if (!context_tracking_cpu_is_enabled()) + if (!context_tracking_enabled_this_cpu()) rcu_virt_note_context_switch(smp_processor_id()); } diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index 91250bdf2060..08f125f6b31b 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -31,7 +31,7 @@ static inline bool context_tracking_enabled(void) return static_branch_unlikely(&context_tracking_key); } -static inline bool context_tracking_cpu_is_enabled(void) +static inline bool context_tracking_enabled_this_cpu(void) { return __this_cpu_read(context_tracking.active); } @@ -43,7 +43,7 @@ static inline bool context_tracking_in_user(void) #else static inline bool context_tracking_in_user(void) { return false; } static inline bool context_tracking_enabled(void) { return false; } -static inline bool context_tracking_cpu_is_enabled(void) { return false; } +static inline bool context_tracking_enabled_this_cpu(void) { return false; } #endif /* CONFIG_CONTEXT_TRACKING */ #endif diff --git a/include/linux/vtime.h b/include/linux/vtime.h index 0fc7f11f7aa4..54e91511250b 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -34,7 +34,7 @@ static inline bool vtime_accounting_enabled(void) static inline bool vtime_accounting_cpu_enabled(void) { if (vtime_accounting_enabled()) { - if (context_tracking_cpu_is_enabled()) + if (context_tracking_enabled_this_cpu()) return true; } -- cgit v1.2.3-71-gd317 From 097f2541c6e51e0c1cdb1e6d46ef08a624336518 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 16 Oct 2019 04:56:53 +0200 Subject: context_tracking: Introduce context_tracking_enabled_cpu() This allows us to check if a remote CPU runs context tracking (ie: is nohz_full). We'll need that to reliably support "nice" accounting on kcpustat. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Cc: Jacek Anaszewski Cc: Linus Torvalds Cc: Pavel Machek Cc: Peter Zijlstra Cc: Rafael J . Wysocki Cc: Rik van Riel Cc: Thomas Gleixner Cc: Viresh Kumar Cc: Wanpeng Li Cc: Yauheni Kaliuta Link: https://lkml.kernel.org/r/20191016025700.31277-8-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/context_tracking_state.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index 08f125f6b31b..587717705727 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -31,6 +31,11 @@ static inline bool context_tracking_enabled(void) return static_branch_unlikely(&context_tracking_key); } +static inline bool context_tracking_enabled_cpu(int cpu) +{ + return per_cpu(context_tracking.active, cpu); +} + static inline bool context_tracking_enabled_this_cpu(void) { return __this_cpu_read(context_tracking.active); @@ -43,6 +48,7 @@ static inline bool context_tracking_in_user(void) #else static inline bool context_tracking_in_user(void) { return false; } static inline bool context_tracking_enabled(void) { return false; } +static inline bool context_tracking_enabled_cpu(int cpu) { return false; } static inline bool context_tracking_enabled_this_cpu(void) { return false; } #endif /* CONFIG_CONTEXT_TRACKING */ -- cgit v1.2.3-71-gd317 From e44fcb4b7a299602fb300b82a546c0b8a50d9d90 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 16 Oct 2019 04:56:54 +0200 Subject: sched/vtime: Rename vtime_accounting_cpu_enabled() to vtime_accounting_enabled_this_cpu() Standardize the naming on top of the vtime_accounting_enabled_*() base. Also make it clear we are checking the vtime state of the *current* CPU with this function. We'll need to add an API to check that state on remote CPUs as well, so we must disambiguate the naming. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Cc: Jacek Anaszewski Cc: Linus Torvalds Cc: Pavel Machek Cc: Peter Zijlstra Cc: Rafael J . Wysocki Cc: Rik van Riel Cc: Thomas Gleixner Cc: Viresh Kumar Cc: Wanpeng Li Cc: Yauheni Kaliuta Link: https://lkml.kernel.org/r/20191016025700.31277-9-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/context_tracking.h | 4 ++-- include/linux/vtime.h | 10 +++++----- kernel/sched/cputime.c | 2 +- kernel/time/tick-sched.c | 2 +- 4 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index c9065ad518a7..64ec82851aa3 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -103,7 +103,7 @@ static inline void context_tracking_init(void) { } /* must be called with irqs disabled */ static inline void guest_enter_irqoff(void) { - if (vtime_accounting_cpu_enabled()) + if (vtime_accounting_enabled_this_cpu()) vtime_guest_enter(current); else current->flags |= PF_VCPU; @@ -127,7 +127,7 @@ static inline void guest_exit_irqoff(void) if (context_tracking_enabled()) __context_tracking_exit(CONTEXT_GUEST); - if (vtime_accounting_cpu_enabled()) + if (vtime_accounting_enabled_this_cpu()) vtime_guest_exit(current); else current->flags &= ~PF_VCPU; diff --git a/include/linux/vtime.h b/include/linux/vtime.h index 54e91511250b..eb2e7a19054b 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -11,11 +11,11 @@ struct task_struct; /* - * vtime_accounting_cpu_enabled() definitions/declarations + * vtime_accounting_enabled_this_cpu() definitions/declarations */ #if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) -static inline bool vtime_accounting_cpu_enabled(void) { return true; } +static inline bool vtime_accounting_enabled_this_cpu(void) { return true; } extern void vtime_task_switch(struct task_struct *prev); #elif defined(CONFIG_VIRT_CPU_ACCOUNTING_GEN) @@ -31,7 +31,7 @@ static inline bool vtime_accounting_enabled(void) return context_tracking_enabled(); } -static inline bool vtime_accounting_cpu_enabled(void) +static inline bool vtime_accounting_enabled_this_cpu(void) { if (vtime_accounting_enabled()) { if (context_tracking_enabled_this_cpu()) @@ -45,13 +45,13 @@ extern void vtime_task_switch_generic(struct task_struct *prev); static inline void vtime_task_switch(struct task_struct *prev) { - if (vtime_accounting_cpu_enabled()) + if (vtime_accounting_enabled_this_cpu()) vtime_task_switch_generic(prev); } #else /* !CONFIG_VIRT_CPU_ACCOUNTING */ -static inline bool vtime_accounting_cpu_enabled(void) { return false; } +static inline bool vtime_accounting_enabled_this_cpu(void) { return false; } static inline void vtime_task_switch(struct task_struct *prev) { } #endif diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 34086afc3518..b931a19df093 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -475,7 +475,7 @@ void account_process_tick(struct task_struct *p, int user_tick) u64 cputime, steal; struct rq *rq = this_rq(); - if (vtime_accounting_cpu_enabled()) + if (vtime_accounting_enabled_this_cpu()) return; if (sched_clock_irqtime) { diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 955851748dc3..c2748232f607 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -1119,7 +1119,7 @@ static void tick_nohz_account_idle_ticks(struct tick_sched *ts) #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE unsigned long ticks; - if (vtime_accounting_cpu_enabled()) + if (vtime_accounting_enabled_this_cpu()) return; /* * We stopped the tick in idle. Update process times would miss the -- cgit v1.2.3-71-gd317 From 9adbb9dd4c4eb45e1129fc73d8de69ca72350f81 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 16 Oct 2019 04:56:55 +0200 Subject: sched/vtime: Introduce vtime_accounting_enabled_cpu() This allows us to check if a remote CPU runs vtime accounting (ie: is nohz_full). We'll need that to reliably support reading kcpustat on nohz_full CPUs. Also simplify a bit the condition in the local flavoured function while at it. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Cc: Jacek Anaszewski Cc: Linus Torvalds Cc: Pavel Machek Cc: Peter Zijlstra Cc: Rafael J . Wysocki Cc: Rik van Riel Cc: Thomas Gleixner Cc: Viresh Kumar Cc: Wanpeng Li Cc: Yauheni Kaliuta Link: https://lkml.kernel.org/r/20191016025700.31277-10-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/vtime.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vtime.h b/include/linux/vtime.h index eb2e7a19054b..e2733bf33541 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -31,14 +31,14 @@ static inline bool vtime_accounting_enabled(void) return context_tracking_enabled(); } -static inline bool vtime_accounting_enabled_this_cpu(void) +static inline bool vtime_accounting_enabled_cpu(int cpu) { - if (vtime_accounting_enabled()) { - if (context_tracking_enabled_this_cpu()) - return true; - } + return (vtime_accounting_enabled() && context_tracking_enabled_cpu(cpu)); +} - return false; +static inline bool vtime_accounting_enabled_this_cpu(void) +{ + return (vtime_accounting_enabled() && context_tracking_enabled_this_cpu()); } extern void vtime_task_switch_generic(struct task_struct *prev); @@ -51,6 +51,7 @@ static inline void vtime_task_switch(struct task_struct *prev) #else /* !CONFIG_VIRT_CPU_ACCOUNTING */ +static inline bool vtime_accounting_enabled_cpu(int cpu) {return false; } static inline bool vtime_accounting_enabled_this_cpu(void) { return false; } static inline void vtime_task_switch(struct task_struct *prev) { } -- cgit v1.2.3-71-gd317 From 023e9deb51c9e1aafacbd421e55beadcb8e87f53 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 16 Oct 2019 04:56:56 +0200 Subject: context_tracking: Check static key on context_tracking_enabled_*cpu() guest_enter() doesn't call context_tracking_enabled() before calling context_tracking_enabled_this_cpu(). Therefore the guest code doesn't benefit from the static key on the fast path. Just make sure that context_tracking_enabled_*cpu() functions check the static key by themselves to propagate the optimization. Reported-by: Peter Zijlstra Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Cc: Jacek Anaszewski Cc: Linus Torvalds Cc: Pavel Machek Cc: Rafael J . Wysocki Cc: Rik van Riel Cc: Thomas Gleixner Cc: Viresh Kumar Cc: Wanpeng Li Cc: Yauheni Kaliuta Link: https://lkml.kernel.org/r/20191016025700.31277-11-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/context_tracking_state.h | 4 ++-- include/linux/vtime.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index 587717705727..e7fe6678b7ad 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -33,12 +33,12 @@ static inline bool context_tracking_enabled(void) static inline bool context_tracking_enabled_cpu(int cpu) { - return per_cpu(context_tracking.active, cpu); + return context_tracking_enabled() && per_cpu(context_tracking.active, cpu); } static inline bool context_tracking_enabled_this_cpu(void) { - return __this_cpu_read(context_tracking.active); + return context_tracking_enabled() && __this_cpu_read(context_tracking.active); } static inline bool context_tracking_in_user(void) diff --git a/include/linux/vtime.h b/include/linux/vtime.h index e2733bf33541..2cdeca062db3 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -33,12 +33,12 @@ static inline bool vtime_accounting_enabled(void) static inline bool vtime_accounting_enabled_cpu(int cpu) { - return (vtime_accounting_enabled() && context_tracking_enabled_cpu(cpu)); + return context_tracking_enabled_cpu(cpu); } static inline bool vtime_accounting_enabled_this_cpu(void) { - return (vtime_accounting_enabled() && context_tracking_enabled_this_cpu()); + return context_tracking_enabled_this_cpu(); } extern void vtime_task_switch_generic(struct task_struct *prev); -- cgit v1.2.3-71-gd317 From 64eea63c19a2c386a96638f4e54a1355510709e3 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 25 Oct 2019 04:03:03 +0200 Subject: sched/kcpustat: Introduce vtime-aware kcpustat accessor for CPUTIME_SYSTEM Kcpustat is not correctly supported on nohz_full CPUs. The tick doesn't fire and the cputime therefore doesn't move forward. The issue has shown up after the vanishing of the remaining 1Hz which has made the stall visible. We are solving that with checking the task running on a CPU through RCU and reading its vtime delta that we add to the raw kcpustat values. We make sure that we fetch a coherent raw-kcpustat/vtime-delta couple sequence while checking that the CPU referred by the target vtime is the correct one, under the locked vtime seqcount. Only CPUTIME_SYSTEM is handled here as a start because it's the trivial case. User and guest time will require more preparation work to correctly handle niceness. Reported-by: Yauheni Kaliuta Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: Wanpeng Li Link: https://lkml.kernel.org/r/20191025020303.19342-1-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/kernel_stat.h | 11 ++++++ kernel/sched/cputime.c | 82 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 93 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 7ee2bb43b251..79781196eb25 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -78,6 +78,17 @@ static inline unsigned int kstat_cpu_irqs_sum(unsigned int cpu) return kstat_cpu(cpu).irqs_sum; } +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +extern u64 kcpustat_field(struct kernel_cpustat *kcpustat, + enum cpu_usage_stat usage, int cpu); +#else +static inline u64 kcpustat_field(struct kernel_cpustat *kcpustat, + enum cpu_usage_stat usage, int cpu) +{ + return kcpustat->cpustat[usage]; +} +#endif + extern void account_user_time(struct task_struct *, u64); extern void account_guest_time(struct task_struct *, u64); extern void account_system_time(struct task_struct *, int, u64); diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index b931a19df093..e0cd20693ef5 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -911,4 +911,86 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) *utime += vtime->utime + delta; } while (read_seqcount_retry(&vtime->seqcount, seq)); } + +static int kcpustat_field_vtime(u64 *cpustat, + struct vtime *vtime, + enum cpu_usage_stat usage, + int cpu, u64 *val) +{ + unsigned int seq; + int err; + + do { + seq = read_seqcount_begin(&vtime->seqcount); + + /* + * We raced against context switch, fetch the + * kcpustat task again. + */ + if (vtime->cpu != cpu && vtime->cpu != -1) + return -EAGAIN; + + /* + * Two possible things here: + * 1) We are seeing the scheduling out task (prev) or any past one. + * 2) We are seeing the scheduling in task (next) but it hasn't + * passed though vtime_task_switch() yet so the pending + * cputime of the prev task may not be flushed yet. + * + * Case 1) is ok but 2) is not. So wait for a safe VTIME state. + */ + if (vtime->state == VTIME_INACTIVE) + return -EAGAIN; + + err = 0; + + *val = cpustat[usage]; + + if (vtime->state == VTIME_SYS) + *val += vtime->stime + vtime_delta(vtime); + + } while (read_seqcount_retry(&vtime->seqcount, seq)); + + return 0; +} + +u64 kcpustat_field(struct kernel_cpustat *kcpustat, + enum cpu_usage_stat usage, int cpu) +{ + u64 *cpustat = kcpustat->cpustat; + struct rq *rq; + u64 val; + int err; + + if (!vtime_accounting_enabled_cpu(cpu)) + return cpustat[usage]; + + /* Only support sys vtime for now */ + if (usage != CPUTIME_SYSTEM) + return cpustat[usage]; + + rq = cpu_rq(cpu); + + for (;;) { + struct task_struct *curr; + struct vtime *vtime; + + rcu_read_lock(); + curr = rcu_dereference(rq->curr); + if (WARN_ON_ONCE(!curr)) { + rcu_read_unlock(); + return cpustat[usage]; + } + + vtime = &curr->vtime; + err = kcpustat_field_vtime(cpustat, vtime, usage, cpu, &val); + rcu_read_unlock(); + + if (!err) + return val; + + cpu_relax(); + } +} +EXPORT_SYMBOL_GPL(kcpustat_field); #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ -- cgit v1.2.3-71-gd317 From 494f8b10d832456a96be4ee7317425f6936cabc8 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 28 Oct 2019 11:32:32 -0500 Subject: resource: Add a resource_list_first_type helper A common pattern is looping over a resource_list just to get a matching entry with a specific type. Add resource_list_first_type() helper which implements this. Signed-off-by: Rob Herring Signed-off-by: Lorenzo Pieralisi --- include/linux/resource_ext.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/resource_ext.h b/include/linux/resource_ext.h index 06da59b23b79..ff0339df56af 100644 --- a/include/linux/resource_ext.h +++ b/include/linux/resource_ext.h @@ -66,4 +66,16 @@ resource_list_destroy_entry(struct resource_entry *entry) #define resource_list_for_each_entry_safe(entry, tmp, list) \ list_for_each_entry_safe((entry), (tmp), (list), node) +static inline struct resource_entry * +resource_list_first_type(struct list_head *list, unsigned long type) +{ + struct resource_entry *entry; + + resource_list_for_each_entry(entry, list) { + if (resource_type(entry->res) == type) + return entry; + } + return NULL; +} + #endif /* _LINUX_RESOURCE_EXT_H */ -- cgit v1.2.3-71-gd317 From f7907e57aea2adcd0b57ebcca410e125412ab680 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Tue, 29 Oct 2019 01:21:31 +0000 Subject: regulator: fixed: add off-on-delay Depends on board design, the gpio controlling regulator may connects with a big capacitance. When need off, it takes some time to let the regulator to be truly off. If not add enough delay, the regulator might have always been on, so introduce off-on-delay to handle such case. Signed-off-by: Peng Fan Link: https://lore.kernel.org/r/1572311875-22880-3-git-send-email-peng.fan@nxp.com Signed-off-by: Mark Brown --- drivers/regulator/fixed.c | 2 ++ include/linux/regulator/fixed.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/drivers/regulator/fixed.c b/drivers/regulator/fixed.c index f81533070058..bc0bbd99e98d 100644 --- a/drivers/regulator/fixed.c +++ b/drivers/regulator/fixed.c @@ -123,6 +123,7 @@ of_get_fixed_voltage_config(struct device *dev, config->enabled_at_boot = true; of_property_read_u32(np, "startup-delay-us", &config->startup_delay); + of_property_read_u32(np, "off-on-delay-us", &config->off_on_delay); if (of_find_property(np, "vin-supply", NULL)) config->input_supply = "vin"; @@ -189,6 +190,7 @@ static int reg_fixed_voltage_probe(struct platform_device *pdev) } drvdata->desc.enable_time = config->startup_delay; + drvdata->desc.off_on_delay = config->off_on_delay; if (config->input_supply) { drvdata->desc.supply_name = devm_kstrdup(&pdev->dev, diff --git a/include/linux/regulator/fixed.h b/include/linux/regulator/fixed.h index d44ce5f18a56..55319943fcc5 100644 --- a/include/linux/regulator/fixed.h +++ b/include/linux/regulator/fixed.h @@ -36,6 +36,7 @@ struct fixed_voltage_config { const char *input_supply; int microvolts; unsigned startup_delay; + unsigned int off_on_delay; unsigned enabled_at_boot:1; struct regulator_init_data *init_data; }; -- cgit v1.2.3-71-gd317 From 80327ce3d4edaa9abde1c6e1a1785572c7de3750 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Mon, 28 Oct 2019 13:37:09 +0100 Subject: gpu: host1x: Overhaul host1x_bo_{pin,unpin}() API The host1x_bo_pin() and host1x_bo_unpin() APIs are used to pin and unpin buffers during host1x job submission. Pinning currently returns the SG table and the DMA address (an IOVA if an IOMMU is used or a physical address if no IOMMU is used) of the buffer. The DMA address is only used for buffers that are relocated, whereas the host1x driver will map gather buffers into its own IOVA space so that they can be processed by the CDMA engine. This approach has a couple of issues. On one hand it's not very useful to return a DMA address for the buffer if host1x doesn't need it. On the other hand, returning the SG table of the buffer is suboptimal because a single SG table cannot be shared for multiple mappings, because the DMA address is stored within the SG table, and the DMA address may be different for different devices. Subsequent patches will move the host1x driver over to the DMA API which doesn't work with a single shared SG table. Fix this by returning a new SG table each time a buffer is pinned. This allows the buffer to be referenced by multiple jobs for different engines. Change the prototypes of host1x_bo_pin() and host1x_bo_unpin() to take a struct device *, specifying the device for which the buffer should be pinned. This is required in order to be able to properly construct the SG table. While at it, make host1x_bo_pin() return the SG table because that allows us to return an ERR_PTR()-encoded error code if we need to, or return NULL to signal that we don't need the SG table to be remapped and can simply use the DMA address as-is. At the same time, returning the DMA address is made optional because in the example of command buffers, host1x doesn't need to know the DMA address since it will have to create its own mapping anyway. Signed-off-by: Thierry Reding --- drivers/gpu/drm/tegra/gem.c | 34 ++++++++++++++++++++++++++++++---- drivers/gpu/host1x/job.c | 15 ++++++++++++--- include/linux/host1x.h | 17 ++++++++++------- 3 files changed, 52 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c index d2f88cc3134f..564ef60f67c2 100644 --- a/drivers/gpu/drm/tegra/gem.c +++ b/drivers/gpu/drm/tegra/gem.c @@ -27,17 +27,43 @@ static void tegra_bo_put(struct host1x_bo *bo) drm_gem_object_put_unlocked(&obj->gem); } -static dma_addr_t tegra_bo_pin(struct host1x_bo *bo, struct sg_table **sgt) +static struct sg_table *tegra_bo_pin(struct device *dev, struct host1x_bo *bo, + dma_addr_t *phys) { struct tegra_bo *obj = host1x_to_tegra_bo(bo); + struct sg_table *sgt; + int err; + + if (phys) + *phys = obj->iova; - *sgt = obj->sgt; + sgt = kzalloc(sizeof(*sgt), GFP_KERNEL); + if (!sgt) + return ERR_PTR(-ENOMEM); - return obj->iova; + if (obj->pages) { + err = sg_alloc_table_from_pages(sgt, obj->pages, obj->num_pages, + 0, obj->gem.size, GFP_KERNEL); + if (err < 0) + goto free; + } else { + err = dma_get_sgtable(dev, sgt, obj->vaddr, obj->iova, + obj->gem.size); + if (err < 0) + goto free; + } + + return sgt; + +free: + kfree(sgt); + return ERR_PTR(err); } -static void tegra_bo_unpin(struct host1x_bo *bo, struct sg_table *sgt) +static void tegra_bo_unpin(struct device *dev, struct sg_table *sgt) { + sg_free_table(sgt); + kfree(sgt); } static void *tegra_bo_mmap(struct host1x_bo *bo) diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c index eaa5c3352c13..90dd592fdfca 100644 --- a/drivers/gpu/host1x/job.c +++ b/drivers/gpu/host1x/job.c @@ -99,6 +99,7 @@ EXPORT_SYMBOL(host1x_job_add_gather); static unsigned int pin_job(struct host1x *host, struct host1x_job *job) { + struct device *dev = job->client->dev; unsigned int i; int err; @@ -115,7 +116,11 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job) goto unpin; } - phys_addr = host1x_bo_pin(reloc->target.bo, &sgt); + sgt = host1x_bo_pin(dev, reloc->target.bo, &phys_addr); + if (IS_ERR(sgt)) { + err = PTR_ERR(sgt); + goto unpin; + } job->addr_phys[job->num_unpins] = phys_addr; job->unpins[job->num_unpins].bo = reloc->target.bo; @@ -139,7 +144,11 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job) goto unpin; } - phys_addr = host1x_bo_pin(g->bo, &sgt); + sgt = host1x_bo_pin(host->dev, g->bo, &phys_addr); + if (IS_ERR(sgt)) { + err = PTR_ERR(sgt); + goto unpin; + } if (!IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL) && host->domain) { for_each_sg(sgt->sgl, sg, sgt->nents, j) @@ -566,7 +575,7 @@ void host1x_job_unpin(struct host1x_job *job) iova_pfn(&host->iova, job->addr_phys[i])); } - host1x_bo_unpin(unpin->bo, unpin->sgt); + host1x_bo_unpin(host->dev, unpin->bo, unpin->sgt); host1x_bo_put(unpin->bo); } diff --git a/include/linux/host1x.h b/include/linux/host1x.h index df6e613ba715..1ba23a6a2021 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -67,8 +67,9 @@ struct sg_table; struct host1x_bo_ops { struct host1x_bo *(*get)(struct host1x_bo *bo); void (*put)(struct host1x_bo *bo); - dma_addr_t (*pin)(struct host1x_bo *bo, struct sg_table **sgt); - void (*unpin)(struct host1x_bo *bo, struct sg_table *sgt); + struct sg_table *(*pin)(struct device *dev, struct host1x_bo *bo, + dma_addr_t *phys); + void (*unpin)(struct device *dev, struct sg_table *sgt); void *(*mmap)(struct host1x_bo *bo); void (*munmap)(struct host1x_bo *bo, void *addr); void *(*kmap)(struct host1x_bo *bo, unsigned int pagenum); @@ -95,15 +96,17 @@ static inline void host1x_bo_put(struct host1x_bo *bo) bo->ops->put(bo); } -static inline dma_addr_t host1x_bo_pin(struct host1x_bo *bo, - struct sg_table **sgt) +static inline struct sg_table *host1x_bo_pin(struct device *dev, + struct host1x_bo *bo, + dma_addr_t *phys) { - return bo->ops->pin(bo, sgt); + return bo->ops->pin(dev, bo, phys); } -static inline void host1x_bo_unpin(struct host1x_bo *bo, struct sg_table *sgt) +static inline void host1x_bo_unpin(struct device *dev, struct host1x_bo *bo, + struct sg_table *sgt) { - bo->ops->unpin(bo, sgt); + bo->ops->unpin(dev, sgt); } static inline void *host1x_bo_mmap(struct host1x_bo *bo) -- cgit v1.2.3-71-gd317 From ab4f81bfc2a8d429130182f8ea3f29a8b1754931 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Mon, 28 Oct 2019 13:37:11 +0100 Subject: gpu: host1x: Add direction flags to relocations Add direction flags to host1x relocations performed during job pinning. These flags indicate the kinds of accesses that hardware is allowed to perform on the relocated buffers. Signed-off-by: Thierry Reding --- drivers/gpu/drm/tegra/drm.c | 2 ++ include/linux/host1x.h | 4 ++++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index 9a1c1694604a..efc8a27b9e6a 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -149,6 +149,8 @@ static int host1x_reloc_copy_from_user(struct host1x_reloc *dest, if (err < 0) return err; + dest->flags = HOST1X_RELOC_READ | HOST1X_RELOC_WRITE; + dest->cmdbuf.bo = host1x_bo_lookup(file, cmdbuf); if (!dest->cmdbuf.bo) return -ENOENT; diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 1ba23a6a2021..6f8d772591ba 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -173,6 +173,9 @@ int host1x_job_submit(struct host1x_job *job); * host1x job */ +#define HOST1X_RELOC_READ (1 << 0) +#define HOST1X_RELOC_WRITE (1 << 1) + struct host1x_reloc { struct { struct host1x_bo *bo; @@ -183,6 +186,7 @@ struct host1x_reloc { unsigned long offset; } target; unsigned long shift; + unsigned long flags; }; struct host1x_job { -- cgit v1.2.3-71-gd317 From 771b53d033e8663abdf59704806aa856b236dcdb Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 22 Oct 2019 10:25:58 -0600 Subject: io-wq: small threadpool implementation for io_uring This adds support for io-wq, a smaller and specialized thread pool implementation. This is meant to replace workqueues for io_uring. Among the reasons for this addition are: - We can assign memory context smarter and more persistently if we manage the life time of threads. - We can drop various work-arounds we have in io_uring, like the async_list. - We can implement hashed work insertion, to manage concurrency of buffered writes without needing a) an extra workqueue, or b) needlessly making the concurrency of said workqueue very low which hurts performance of multiple buffered file writers. - We can implement cancel through signals, for cancelling interruptible work like read/write (or send/recv) to/from sockets. - We need the above cancel for being able to assign and use file tables from a process. - We can implement a more thorough cancel operation in general. - We need it to move towards a syslet/threadlet model for even faster async execution. For that we need to take ownership of the used threads. This list is just off the top of my head. Performance should be the same, or better, at least that's what I've seen in my testing. io-wq supports basic NUMA functionality, setting up a pool per node. io-wq hooks up to the scheduler schedule in/out just like workqueue and uses that to drive the need for more/less workers. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Jens Axboe --- fs/Kconfig | 3 + fs/Makefile | 1 + fs/io-wq.c | 825 ++++++++++++++++++++++++++++++++++++++++++++++++++ fs/io-wq.h | 55 ++++ include/linux/sched.h | 1 + kernel/sched/core.c | 16 +- 6 files changed, 897 insertions(+), 4 deletions(-) create mode 100644 fs/io-wq.c create mode 100644 fs/io-wq.h (limited to 'include/linux') diff --git a/fs/Kconfig b/fs/Kconfig index 2501e6f1f965..7b623e9fc1b0 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -322,4 +322,7 @@ source "fs/nls/Kconfig" source "fs/dlm/Kconfig" source "fs/unicode/Kconfig" +config IO_WQ + bool + endmenu diff --git a/fs/Makefile b/fs/Makefile index 14231b4cf383..1148c555c4d3 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -32,6 +32,7 @@ obj-$(CONFIG_EVENTFD) += eventfd.o obj-$(CONFIG_USERFAULTFD) += userfaultfd.o obj-$(CONFIG_AIO) += aio.o obj-$(CONFIG_IO_URING) += io_uring.o +obj-$(CONFIG_IO_WQ) += io-wq.o obj-$(CONFIG_FS_DAX) += dax.o obj-$(CONFIG_FS_ENCRYPTION) += crypto/ obj-$(CONFIG_FS_VERITY) += verity/ diff --git a/fs/io-wq.c b/fs/io-wq.c new file mode 100644 index 000000000000..37863879e987 --- /dev/null +++ b/fs/io-wq.c @@ -0,0 +1,825 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Basic worker thread pool for io_uring + * + * Copyright (C) 2019 Jens Axboe + * + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "io-wq.h" + +#define WORKER_IDLE_TIMEOUT (5 * HZ) + +enum { + IO_WORKER_F_UP = 1, /* up and active */ + IO_WORKER_F_RUNNING = 2, /* account as running */ + IO_WORKER_F_FREE = 4, /* worker on free list */ + IO_WORKER_F_EXITING = 8, /* worker exiting */ + IO_WORKER_F_FIXED = 16, /* static idle worker */ +}; + +enum { + IO_WQ_BIT_EXIT = 0, /* wq exiting */ + IO_WQ_BIT_CANCEL = 1, /* cancel work on list */ +}; + +enum { + IO_WQE_FLAG_STALLED = 1, /* stalled on hash */ +}; + +/* + * One for each thread in a wqe pool + */ +struct io_worker { + refcount_t ref; + unsigned flags; + struct hlist_nulls_node nulls_node; + struct task_struct *task; + wait_queue_head_t wait; + struct io_wqe *wqe; + struct io_wq_work *cur_work; + + struct rcu_head rcu; + struct mm_struct *mm; +}; + +struct io_wq_nulls_list { + struct hlist_nulls_head head; + unsigned long nulls; +}; + +#if BITS_PER_LONG == 64 +#define IO_WQ_HASH_ORDER 6 +#else +#define IO_WQ_HASH_ORDER 5 +#endif + +/* + * Per-node worker thread pool + */ +struct io_wqe { + struct { + spinlock_t lock; + struct list_head work_list; + unsigned long hash_map; + unsigned flags; + } ____cacheline_aligned_in_smp; + + int node; + unsigned nr_workers; + unsigned max_workers; + atomic_t nr_running; + + struct io_wq_nulls_list free_list; + struct io_wq_nulls_list busy_list; + + struct io_wq *wq; +}; + +/* + * Per io_wq state + */ +struct io_wq { + struct io_wqe **wqes; + unsigned long state; + unsigned nr_wqes; + + struct task_struct *manager; + struct mm_struct *mm; + refcount_t refs; + struct completion done; +}; + +static void io_wq_free_worker(struct rcu_head *head) +{ + struct io_worker *worker = container_of(head, struct io_worker, rcu); + + kfree(worker); +} + +static bool io_worker_get(struct io_worker *worker) +{ + return refcount_inc_not_zero(&worker->ref); +} + +static void io_worker_release(struct io_worker *worker) +{ + if (refcount_dec_and_test(&worker->ref)) + wake_up_process(worker->task); +} + +/* + * Note: drops the wqe->lock if returning true! The caller must re-acquire + * the lock in that case. Some callers need to restart handling if this + * happens, so we can't just re-acquire the lock on behalf of the caller. + */ +static bool __io_worker_unuse(struct io_wqe *wqe, struct io_worker *worker) +{ + /* + * If we have an active mm, we need to drop the wq lock before unusing + * it. If we do, return true and let the caller retry the idle loop. + */ + if (worker->mm) { + __acquire(&wqe->lock); + spin_unlock_irq(&wqe->lock); + __set_current_state(TASK_RUNNING); + set_fs(KERNEL_DS); + unuse_mm(worker->mm); + mmput(worker->mm); + worker->mm = NULL; + return true; + } + + return false; +} + +static void io_worker_exit(struct io_worker *worker) +{ + struct io_wqe *wqe = worker->wqe; + bool all_done = false; + + /* + * If we're not at zero, someone else is holding a brief reference + * to the worker. Wait for that to go away. + */ + set_current_state(TASK_INTERRUPTIBLE); + if (!refcount_dec_and_test(&worker->ref)) + schedule(); + __set_current_state(TASK_RUNNING); + + preempt_disable(); + current->flags &= ~PF_IO_WORKER; + if (worker->flags & IO_WORKER_F_RUNNING) + atomic_dec(&wqe->nr_running); + worker->flags = 0; + preempt_enable(); + + spin_lock_irq(&wqe->lock); + hlist_nulls_del_rcu(&worker->nulls_node); + if (__io_worker_unuse(wqe, worker)) { + __release(&wqe->lock); + spin_lock_irq(&wqe->lock); + } + wqe->nr_workers--; + all_done = !wqe->nr_workers; + spin_unlock_irq(&wqe->lock); + + /* all workers gone, wq exit can proceed */ + if (all_done && refcount_dec_and_test(&wqe->wq->refs)) + complete(&wqe->wq->done); + + call_rcu(&worker->rcu, io_wq_free_worker); +} + +static void io_worker_start(struct io_wqe *wqe, struct io_worker *worker) +{ + allow_kernel_signal(SIGINT); + + current->flags |= PF_IO_WORKER; + + worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING); + atomic_inc(&wqe->nr_running); +} + +/* + * Worker will start processing some work. Move it to the busy list, if + * it's currently on the freelist + */ +static void __io_worker_busy(struct io_wqe *wqe, struct io_worker *worker, + struct io_wq_work *work) + __must_hold(wqe->lock) +{ + if (worker->flags & IO_WORKER_F_FREE) { + worker->flags &= ~IO_WORKER_F_FREE; + hlist_nulls_del_init_rcu(&worker->nulls_node); + hlist_nulls_add_head_rcu(&worker->nulls_node, + &wqe->busy_list.head); + } + worker->cur_work = work; +} + +/* + * No work, worker going to sleep. Move to freelist, and unuse mm if we + * have one attached. Dropping the mm may potentially sleep, so we drop + * the lock in that case and return success. Since the caller has to + * retry the loop in that case (we changed task state), we don't regrab + * the lock if we return success. + */ +static bool __io_worker_idle(struct io_wqe *wqe, struct io_worker *worker) + __must_hold(wqe->lock) +{ + if (!(worker->flags & IO_WORKER_F_FREE)) { + worker->flags |= IO_WORKER_F_FREE; + hlist_nulls_del_init_rcu(&worker->nulls_node); + hlist_nulls_add_head_rcu(&worker->nulls_node, + &wqe->free_list.head); + } + + return __io_worker_unuse(wqe, worker); +} + +static struct io_wq_work *io_get_next_work(struct io_wqe *wqe, unsigned *hash) + __must_hold(wqe->lock) +{ + struct io_wq_work *work; + + list_for_each_entry(work, &wqe->work_list, list) { + /* not hashed, can run anytime */ + if (!(work->flags & IO_WQ_WORK_HASHED)) { + list_del(&work->list); + return work; + } + + /* hashed, can run if not already running */ + *hash = work->flags >> IO_WQ_HASH_SHIFT; + if (!(wqe->hash_map & BIT_ULL(*hash))) { + wqe->hash_map |= BIT_ULL(*hash); + list_del(&work->list); + return work; + } + } + + return NULL; +} + +static void io_worker_handle_work(struct io_worker *worker) + __releases(wqe->lock) +{ + struct io_wq_work *work, *old_work; + struct io_wqe *wqe = worker->wqe; + struct io_wq *wq = wqe->wq; + + do { + unsigned hash = -1U; + + /* + * Signals are either sent to cancel specific work, or to just + * cancel all work items. For the former, ->cur_work must + * match. ->cur_work is NULL at this point, since we haven't + * assigned any work, so it's safe to flush signals for that + * case. For the latter case of cancelling all work, the caller + * wil have set IO_WQ_BIT_CANCEL. + */ + if (signal_pending(current)) + flush_signals(current); + + /* + * If we got some work, mark us as busy. If we didn't, but + * the list isn't empty, it means we stalled on hashed work. + * Mark us stalled so we don't keep looking for work when we + * can't make progress, any work completion or insertion will + * clear the stalled flag. + */ + work = io_get_next_work(wqe, &hash); + if (work) + __io_worker_busy(wqe, worker, work); + else if (!list_empty(&wqe->work_list)) + wqe->flags |= IO_WQE_FLAG_STALLED; + + spin_unlock_irq(&wqe->lock); + if (!work) + break; +next: + if ((work->flags & IO_WQ_WORK_NEEDS_USER) && !worker->mm && + wq->mm && mmget_not_zero(wq->mm)) { + use_mm(wq->mm); + set_fs(USER_DS); + worker->mm = wq->mm; + } + if (test_bit(IO_WQ_BIT_CANCEL, &wq->state)) + work->flags |= IO_WQ_WORK_CANCEL; + if (worker->mm) + work->flags |= IO_WQ_WORK_HAS_MM; + + old_work = work; + work->func(&work); + + spin_lock_irq(&wqe->lock); + worker->cur_work = NULL; + if (hash != -1U) { + wqe->hash_map &= ~BIT_ULL(hash); + wqe->flags &= ~IO_WQE_FLAG_STALLED; + } + if (work && work != old_work) { + spin_unlock_irq(&wqe->lock); + /* dependent work not hashed */ + hash = -1U; + goto next; + } + } while (1); +} + +static inline bool io_wqe_run_queue(struct io_wqe *wqe) + __must_hold(wqe->lock) +{ + if (!list_empty_careful(&wqe->work_list) && + !(wqe->flags & IO_WQE_FLAG_STALLED)) + return true; + return false; +} + +static int io_wqe_worker(void *data) +{ + struct io_worker *worker = data; + struct io_wqe *wqe = worker->wqe; + struct io_wq *wq = wqe->wq; + DEFINE_WAIT(wait); + + io_worker_start(wqe, worker); + + while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) { + prepare_to_wait(&worker->wait, &wait, TASK_INTERRUPTIBLE); + + spin_lock_irq(&wqe->lock); + if (io_wqe_run_queue(wqe)) { + __set_current_state(TASK_RUNNING); + io_worker_handle_work(worker); + continue; + } + /* drops the lock on success, retry */ + if (__io_worker_idle(wqe, worker)) { + __release(&wqe->lock); + continue; + } + spin_unlock_irq(&wqe->lock); + if (signal_pending(current)) + flush_signals(current); + if (schedule_timeout(WORKER_IDLE_TIMEOUT)) + continue; + /* timed out, exit unless we're the fixed worker */ + if (test_bit(IO_WQ_BIT_EXIT, &wq->state) || + !(worker->flags & IO_WORKER_F_FIXED)) + break; + } + + finish_wait(&worker->wait, &wait); + + if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) { + spin_lock_irq(&wqe->lock); + if (!list_empty(&wqe->work_list)) + io_worker_handle_work(worker); + else + spin_unlock_irq(&wqe->lock); + } + + io_worker_exit(worker); + return 0; +} + +/* + * Check head of free list for an available worker. If one isn't available, + * caller must wake up the wq manager to create one. + */ +static bool io_wqe_activate_free_worker(struct io_wqe *wqe) + __must_hold(RCU) +{ + struct hlist_nulls_node *n; + struct io_worker *worker; + + n = rcu_dereference(hlist_nulls_first_rcu(&wqe->free_list.head)); + if (is_a_nulls(n)) + return false; + + worker = hlist_nulls_entry(n, struct io_worker, nulls_node); + if (io_worker_get(worker)) { + wake_up(&worker->wait); + io_worker_release(worker); + return true; + } + + return false; +} + +/* + * We need a worker. If we find a free one, we're good. If not, and we're + * below the max number of workers, wake up the manager to create one. + */ +static void io_wqe_wake_worker(struct io_wqe *wqe) +{ + bool ret; + + rcu_read_lock(); + ret = io_wqe_activate_free_worker(wqe); + rcu_read_unlock(); + + if (!ret && wqe->nr_workers < wqe->max_workers) + wake_up_process(wqe->wq->manager); +} + +/* + * Called when a worker is scheduled in. Mark us as currently running. + */ +void io_wq_worker_running(struct task_struct *tsk) +{ + struct io_worker *worker = kthread_data(tsk); + struct io_wqe *wqe = worker->wqe; + + if (!(worker->flags & IO_WORKER_F_UP)) + return; + if (worker->flags & IO_WORKER_F_RUNNING) + return; + worker->flags |= IO_WORKER_F_RUNNING; + atomic_inc(&wqe->nr_running); +} + +/* + * Called when worker is going to sleep. If there are no workers currently + * running and we have work pending, wake up a free one or have the manager + * set one up. + */ +void io_wq_worker_sleeping(struct task_struct *tsk) +{ + struct io_worker *worker = kthread_data(tsk); + struct io_wqe *wqe = worker->wqe; + + if (!(worker->flags & IO_WORKER_F_UP)) + return; + if (!(worker->flags & IO_WORKER_F_RUNNING)) + return; + + worker->flags &= ~IO_WORKER_F_RUNNING; + + spin_lock_irq(&wqe->lock); + if (atomic_dec_and_test(&wqe->nr_running) && io_wqe_run_queue(wqe)) + io_wqe_wake_worker(wqe); + spin_unlock_irq(&wqe->lock); +} + +static void create_io_worker(struct io_wq *wq, struct io_wqe *wqe) +{ + struct io_worker *worker; + + worker = kcalloc_node(1, sizeof(*worker), GFP_KERNEL, wqe->node); + if (!worker) + return; + + refcount_set(&worker->ref, 1); + worker->nulls_node.pprev = NULL; + init_waitqueue_head(&worker->wait); + worker->wqe = wqe; + + worker->task = kthread_create_on_node(io_wqe_worker, worker, wqe->node, + "io_wqe_worker-%d", wqe->node); + if (IS_ERR(worker->task)) { + kfree(worker); + return; + } + + spin_lock_irq(&wqe->lock); + hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list.head); + worker->flags |= IO_WORKER_F_FREE; + if (!wqe->nr_workers) + worker->flags |= IO_WORKER_F_FIXED; + wqe->nr_workers++; + spin_unlock_irq(&wqe->lock); + + wake_up_process(worker->task); +} + +static inline bool io_wqe_need_new_worker(struct io_wqe *wqe) + __must_hold(wqe->lock) +{ + if (!wqe->nr_workers) + return true; + if (hlist_nulls_empty(&wqe->free_list.head) && + wqe->nr_workers < wqe->max_workers && io_wqe_run_queue(wqe)) + return true; + + return false; +} + +/* + * Manager thread. Tasked with creating new workers, if we need them. + */ +static int io_wq_manager(void *data) +{ + struct io_wq *wq = data; + + while (!kthread_should_stop()) { + int i; + + for (i = 0; i < wq->nr_wqes; i++) { + struct io_wqe *wqe = wq->wqes[i]; + bool fork_worker = false; + + spin_lock_irq(&wqe->lock); + fork_worker = io_wqe_need_new_worker(wqe); + spin_unlock_irq(&wqe->lock); + if (fork_worker) + create_io_worker(wq, wqe); + } + set_current_state(TASK_INTERRUPTIBLE); + schedule_timeout(HZ); + } + + return 0; +} + +static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work) +{ + unsigned long flags; + + spin_lock_irqsave(&wqe->lock, flags); + list_add_tail(&work->list, &wqe->work_list); + wqe->flags &= ~IO_WQE_FLAG_STALLED; + spin_unlock_irqrestore(&wqe->lock, flags); + + if (!atomic_read(&wqe->nr_running)) + io_wqe_wake_worker(wqe); +} + +void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work) +{ + struct io_wqe *wqe = wq->wqes[numa_node_id()]; + + io_wqe_enqueue(wqe, work); +} + +/* + * Enqueue work, hashed by some key. Work items that hash to the same value + * will not be done in parallel. Used to limit concurrent writes, generally + * hashed by inode. + */ +void io_wq_enqueue_hashed(struct io_wq *wq, struct io_wq_work *work, void *val) +{ + struct io_wqe *wqe = wq->wqes[numa_node_id()]; + unsigned bit; + + + bit = hash_ptr(val, IO_WQ_HASH_ORDER); + work->flags |= (IO_WQ_WORK_HASHED | (bit << IO_WQ_HASH_SHIFT)); + io_wqe_enqueue(wqe, work); +} + +static bool io_wqe_worker_send_sig(struct io_worker *worker, void *data) +{ + send_sig(SIGINT, worker->task, 1); + return false; +} + +/* + * Iterate the passed in list and call the specific function for each + * worker that isn't exiting + */ +static bool io_wq_for_each_worker(struct io_wqe *wqe, + struct io_wq_nulls_list *list, + bool (*func)(struct io_worker *, void *), + void *data) +{ + struct hlist_nulls_node *n; + struct io_worker *worker; + bool ret = false; + +restart: + hlist_nulls_for_each_entry_rcu(worker, n, &list->head, nulls_node) { + if (io_worker_get(worker)) { + ret = func(worker, data); + io_worker_release(worker); + if (ret) + break; + } + } + if (!ret && get_nulls_value(n) != list->nulls) + goto restart; + return ret; +} + +void io_wq_cancel_all(struct io_wq *wq) +{ + int i; + + set_bit(IO_WQ_BIT_CANCEL, &wq->state); + + /* + * Browse both lists, as there's a gap between handing work off + * to a worker and the worker putting itself on the busy_list + */ + rcu_read_lock(); + for (i = 0; i < wq->nr_wqes; i++) { + struct io_wqe *wqe = wq->wqes[i]; + + io_wq_for_each_worker(wqe, &wqe->busy_list, + io_wqe_worker_send_sig, NULL); + io_wq_for_each_worker(wqe, &wqe->free_list, + io_wqe_worker_send_sig, NULL); + } + rcu_read_unlock(); +} + +static bool io_wq_worker_cancel(struct io_worker *worker, void *data) +{ + struct io_wq_work *work = data; + + if (worker->cur_work == work) { + send_sig(SIGINT, worker->task, 1); + return true; + } + + return false; +} + +static enum io_wq_cancel io_wqe_cancel_work(struct io_wqe *wqe, + struct io_wq_work *cwork) +{ + struct io_wq_work *work; + bool found = false; + + cwork->flags |= IO_WQ_WORK_CANCEL; + + /* + * First check pending list, if we're lucky we can just remove it + * from there. CANCEL_OK means that the work is returned as-new, + * no completion will be posted for it. + */ + spin_lock_irq(&wqe->lock); + list_for_each_entry(work, &wqe->work_list, list) { + if (work == cwork) { + list_del(&work->list); + found = true; + break; + } + } + spin_unlock_irq(&wqe->lock); + + if (found) { + work->flags |= IO_WQ_WORK_CANCEL; + work->func(&work); + return IO_WQ_CANCEL_OK; + } + + /* + * Now check if a free (going busy) or busy worker has the work + * currently running. If we find it there, we'll return CANCEL_RUNNING + * as an indication that we attempte to signal cancellation. The + * completion will run normally in this case. + */ + rcu_read_lock(); + found = io_wq_for_each_worker(wqe, &wqe->free_list, io_wq_worker_cancel, + cwork); + if (found) + goto done; + + found = io_wq_for_each_worker(wqe, &wqe->busy_list, io_wq_worker_cancel, + cwork); +done: + rcu_read_unlock(); + return found ? IO_WQ_CANCEL_RUNNING : IO_WQ_CANCEL_NOTFOUND; +} + +enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork) +{ + enum io_wq_cancel ret = IO_WQ_CANCEL_NOTFOUND; + int i; + + for (i = 0; i < wq->nr_wqes; i++) { + struct io_wqe *wqe = wq->wqes[i]; + + ret = io_wqe_cancel_work(wqe, cwork); + if (ret != IO_WQ_CANCEL_NOTFOUND) + break; + } + + return ret; +} + +struct io_wq_flush_data { + struct io_wq_work work; + struct completion done; +}; + +static void io_wq_flush_func(struct io_wq_work **workptr) +{ + struct io_wq_work *work = *workptr; + struct io_wq_flush_data *data; + + data = container_of(work, struct io_wq_flush_data, work); + complete(&data->done); +} + +/* + * Doesn't wait for previously queued work to finish. When this completes, + * it just means that previously queued work was started. + */ +void io_wq_flush(struct io_wq *wq) +{ + struct io_wq_flush_data data; + int i; + + for (i = 0; i < wq->nr_wqes; i++) { + struct io_wqe *wqe = wq->wqes[i]; + + init_completion(&data.done); + INIT_IO_WORK(&data.work, io_wq_flush_func); + io_wqe_enqueue(wqe, &data.work); + wait_for_completion(&data.done); + } +} + +struct io_wq *io_wq_create(unsigned concurrency, struct mm_struct *mm) +{ + int ret = -ENOMEM, i, node; + struct io_wq *wq; + + wq = kcalloc(1, sizeof(*wq), GFP_KERNEL); + if (!wq) + return ERR_PTR(-ENOMEM); + + wq->nr_wqes = num_online_nodes(); + wq->wqes = kcalloc(wq->nr_wqes, sizeof(struct io_wqe *), GFP_KERNEL); + if (!wq->wqes) { + kfree(wq); + return ERR_PTR(-ENOMEM); + } + + i = 0; + refcount_set(&wq->refs, wq->nr_wqes); + for_each_online_node(node) { + struct io_wqe *wqe; + + wqe = kcalloc_node(1, sizeof(struct io_wqe), GFP_KERNEL, node); + if (!wqe) + break; + wq->wqes[i] = wqe; + wqe->node = node; + wqe->max_workers = concurrency; + wqe->node = node; + wqe->wq = wq; + spin_lock_init(&wqe->lock); + INIT_LIST_HEAD(&wqe->work_list); + INIT_HLIST_NULLS_HEAD(&wqe->free_list.head, 0); + wqe->free_list.nulls = 0; + INIT_HLIST_NULLS_HEAD(&wqe->busy_list.head, 1); + wqe->busy_list.nulls = 1; + atomic_set(&wqe->nr_running, 0); + + i++; + } + + init_completion(&wq->done); + + if (i != wq->nr_wqes) + goto err; + + /* caller must have already done mmgrab() on this mm */ + wq->mm = mm; + + wq->manager = kthread_create(io_wq_manager, wq, "io_wq_manager"); + if (!IS_ERR(wq->manager)) { + wake_up_process(wq->manager); + return wq; + } + + ret = PTR_ERR(wq->manager); + wq->manager = NULL; +err: + complete(&wq->done); + io_wq_destroy(wq); + return ERR_PTR(ret); +} + +static bool io_wq_worker_wake(struct io_worker *worker, void *data) +{ + wake_up_process(worker->task); + return false; +} + +void io_wq_destroy(struct io_wq *wq) +{ + int i; + + if (wq->manager) { + set_bit(IO_WQ_BIT_EXIT, &wq->state); + kthread_stop(wq->manager); + } + + rcu_read_lock(); + for (i = 0; i < wq->nr_wqes; i++) { + struct io_wqe *wqe = wq->wqes[i]; + + if (!wqe) + continue; + io_wq_for_each_worker(wqe, &wqe->free_list, io_wq_worker_wake, + NULL); + io_wq_for_each_worker(wqe, &wqe->busy_list, io_wq_worker_wake, + NULL); + } + rcu_read_unlock(); + + wait_for_completion(&wq->done); + + for (i = 0; i < wq->nr_wqes; i++) + kfree(wq->wqes[i]); + kfree(wq->wqes); + kfree(wq); +} diff --git a/fs/io-wq.h b/fs/io-wq.h new file mode 100644 index 000000000000..be8f22c8937b --- /dev/null +++ b/fs/io-wq.h @@ -0,0 +1,55 @@ +#ifndef INTERNAL_IO_WQ_H +#define INTERNAL_IO_WQ_H + +struct io_wq; + +enum { + IO_WQ_WORK_CANCEL = 1, + IO_WQ_WORK_HAS_MM = 2, + IO_WQ_WORK_HASHED = 4, + IO_WQ_WORK_NEEDS_USER = 8, + + IO_WQ_HASH_SHIFT = 24, /* upper 8 bits are used for hash key */ +}; + +enum io_wq_cancel { + IO_WQ_CANCEL_OK, /* cancelled before started */ + IO_WQ_CANCEL_RUNNING, /* found, running, and attempted cancelled */ + IO_WQ_CANCEL_NOTFOUND, /* work not found */ +}; + +struct io_wq_work { + struct list_head list; + void (*func)(struct io_wq_work **); + unsigned flags; +}; + +#define INIT_IO_WORK(work, _func) \ + do { \ + (work)->func = _func; \ + (work)->flags = 0; \ + } while (0) \ + +struct io_wq *io_wq_create(unsigned concurrency, struct mm_struct *mm); +void io_wq_destroy(struct io_wq *wq); + +void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work); +void io_wq_enqueue_hashed(struct io_wq *wq, struct io_wq_work *work, void *val); +void io_wq_flush(struct io_wq *wq); + +void io_wq_cancel_all(struct io_wq *wq); +enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork); + +#if defined(CONFIG_IO_WQ) +extern void io_wq_worker_sleeping(struct task_struct *); +extern void io_wq_worker_running(struct task_struct *); +#else +static inline void io_wq_worker_sleeping(struct task_struct *tsk) +{ +} +static inline void io_wq_worker_running(struct task_struct *tsk) +{ +} +#endif + +#endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 67a1d86981a9..6666e25606b7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1468,6 +1468,7 @@ extern struct pid *cad_pid; #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMALLOC_NOCMA 0x10000000 /* All allocation request will have _GFP_MOVABLE cleared */ +#define PF_IO_WORKER 0x20000000 /* Task is an IO worker */ #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index dd05a378631a..a95a2f05f3b5 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -16,6 +16,7 @@ #include #include "../workqueue_internal.h" +#include "../../fs/io-wq.h" #include "../smpboot.h" #include "pelt.h" @@ -4103,9 +4104,12 @@ static inline void sched_submit_work(struct task_struct *tsk) * we disable preemption to avoid it calling schedule() again * in the possible wakeup of a kworker. */ - if (tsk->flags & PF_WQ_WORKER) { + if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) { preempt_disable(); - wq_worker_sleeping(tsk); + if (tsk->flags & PF_WQ_WORKER) + wq_worker_sleeping(tsk); + else + io_wq_worker_sleeping(tsk); preempt_enable_no_resched(); } @@ -4122,8 +4126,12 @@ static inline void sched_submit_work(struct task_struct *tsk) static void sched_update_worker(struct task_struct *tsk) { - if (tsk->flags & PF_WQ_WORKER) - wq_worker_running(tsk); + if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) { + if (tsk->flags & PF_WQ_WORKER) + wq_worker_running(tsk); + else + io_wq_worker_running(tsk); + } } asmlinkage __visible void __sched schedule(void) -- cgit v1.2.3-71-gd317 From de2ea4b64b75a79ed9cdf9bf30e0e197901084e4 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 17 Oct 2019 14:41:29 -0600 Subject: net: add __sys_accept4_file() helper This is identical to __sys_accept4(), except it takes a struct file instead of an fd, and it also allows passing in extra file->f_flags flags. The latter is done to support masking in O_NONBLOCK without manipulating the original file flags. No functional changes in this patch. Cc: netdev@vger.kernel.org Acked-by: David S. Miller Signed-off-by: Jens Axboe --- include/linux/socket.h | 3 +++ net/socket.c | 65 +++++++++++++++++++++++++++++++------------------- 2 files changed, 44 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index fc0bed59fc84..dd061f741bc1 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -392,6 +392,9 @@ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, extern int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, struct sockaddr __user *addr, int addr_len); +extern int __sys_accept4_file(struct file *file, unsigned file_flags, + struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags); extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_socket(int family, int type, int protocol); diff --git a/net/socket.c b/net/socket.c index 6a9ab7a8b1d2..40ab39f6c5d8 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1690,24 +1690,13 @@ SYSCALL_DEFINE2(listen, int, fd, int, backlog) return __sys_listen(fd, backlog); } -/* - * For accept, we attempt to create a new socket, set up the link - * with the client, wake up the client, then return the new - * connected fd. We collect the address of the connector in kernel - * space and move it to user at the very end. This is unclean because - * we open the socket then return an error. - * - * 1003.1g adds the ability to recvmsg() to query connection pending - * status to recvmsg. We need to add that support in a way thats - * clean when we restructure accept also. - */ - -int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, - int __user *upeer_addrlen, int flags) +int __sys_accept4_file(struct file *file, unsigned file_flags, + struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags) { struct socket *sock, *newsock; struct file *newfile; - int err, len, newfd, fput_needed; + int err, len, newfd; struct sockaddr_storage address; if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) @@ -1716,14 +1705,14 @@ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; - sock = sockfd_lookup_light(fd, &err, &fput_needed); + sock = sock_from_file(file, &err); if (!sock) goto out; err = -ENFILE; newsock = sock_alloc(); if (!newsock) - goto out_put; + goto out; newsock->type = sock->type; newsock->ops = sock->ops; @@ -1738,20 +1727,21 @@ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, if (unlikely(newfd < 0)) { err = newfd; sock_release(newsock); - goto out_put; + goto out; } newfile = sock_alloc_file(newsock, flags, sock->sk->sk_prot_creator->name); if (IS_ERR(newfile)) { err = PTR_ERR(newfile); put_unused_fd(newfd); - goto out_put; + goto out; } err = security_socket_accept(sock, newsock); if (err) goto out_fd; - err = sock->ops->accept(sock, newsock, sock->file->f_flags, false); + err = sock->ops->accept(sock, newsock, sock->file->f_flags | file_flags, + false); if (err < 0) goto out_fd; @@ -1772,15 +1762,42 @@ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, fd_install(newfd, newfile); err = newfd; - -out_put: - fput_light(sock->file, fput_needed); out: return err; out_fd: fput(newfile); put_unused_fd(newfd); - goto out_put; + goto out; + +} + +/* + * For accept, we attempt to create a new socket, set up the link + * with the client, wake up the client, then return the new + * connected fd. We collect the address of the connector in kernel + * space and move it to user at the very end. This is unclean because + * we open the socket then return an error. + * + * 1003.1g adds the ability to recvmsg() to query connection pending + * status to recvmsg. We need to add that support in a way thats + * clean when we restructure accept also. + */ + +int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags) +{ + int ret = -EBADF; + struct fd f; + + f = fdget(fd); + if (f.file) { + ret = __sys_accept4_file(f.file, 0, upeer_sockaddr, + upeer_addrlen, flags); + if (f.flags) + fput(f.file); + } + + return ret; } SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, -- cgit v1.2.3-71-gd317 From b4941adb24c0676f77ddc25e6d7836b8245c47fc Mon Sep 17 00:00:00 2001 From: Ran Wang Date: Thu, 24 Oct 2019 17:26:42 +0800 Subject: PM: wakeup: Add routine to help fetch wakeup source object. Some user might want to go through all registered wakeup sources and doing things accordingly. For example, SoC PM driver might need to do HW programming to prevent powering down specific IP which wakeup source depending on. So add this API to help walk through all registered wakeup source objects on that list and return them one by one. Signed-off-by: Ran Wang Tested-by: Leonard Crestez Reviewed-by: Rafael J. Wysocki Signed-off-by: Li Yang --- drivers/base/power/wakeup.c | 54 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/pm_wakeup.h | 9 ++++++++ 2 files changed, 63 insertions(+) (limited to 'include/linux') diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index 5817b51d2b15..70a9edb5f525 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -247,6 +247,60 @@ void wakeup_source_unregister(struct wakeup_source *ws) } EXPORT_SYMBOL_GPL(wakeup_source_unregister); +/** + * wakeup_sources_read_lock - Lock wakeup source list for read. + * + * Returns an index of srcu lock for struct wakeup_srcu. + * This index must be passed to the matching wakeup_sources_read_unlock(). + */ +int wakeup_sources_read_lock(void) +{ + return srcu_read_lock(&wakeup_srcu); +} +EXPORT_SYMBOL_GPL(wakeup_sources_read_lock); + +/** + * wakeup_sources_read_unlock - Unlock wakeup source list. + * @idx: return value from corresponding wakeup_sources_read_lock() + */ +void wakeup_sources_read_unlock(int idx) +{ + srcu_read_unlock(&wakeup_srcu, idx); +} +EXPORT_SYMBOL_GPL(wakeup_sources_read_unlock); + +/** + * wakeup_sources_walk_start - Begin a walk on wakeup source list + * + * Returns first object of the list of wakeup sources. + * + * Note that to be safe, wakeup sources list needs to be locked by calling + * wakeup_source_read_lock() for this. + */ +struct wakeup_source *wakeup_sources_walk_start(void) +{ + struct list_head *ws_head = &wakeup_sources; + + return list_entry_rcu(ws_head->next, struct wakeup_source, entry); +} +EXPORT_SYMBOL_GPL(wakeup_sources_walk_start); + +/** + * wakeup_sources_walk_next - Get next wakeup source from the list + * @ws: Previous wakeup source object + * + * Note that to be safe, wakeup sources list needs to be locked by calling + * wakeup_source_read_lock() for this. + */ +struct wakeup_source *wakeup_sources_walk_next(struct wakeup_source *ws) +{ + struct list_head *ws_head = &wakeup_sources; + + return list_next_or_null_rcu(ws_head, &ws->entry, + struct wakeup_source, entry); +} +EXPORT_SYMBOL_GPL(wakeup_sources_walk_next); + /** * device_wakeup_attach - Attach a wakeup source object to a device object. * @dev: Device to handle. diff --git a/include/linux/pm_wakeup.h b/include/linux/pm_wakeup.h index 661efa029c96..aa3da6611533 100644 --- a/include/linux/pm_wakeup.h +++ b/include/linux/pm_wakeup.h @@ -63,6 +63,11 @@ struct wakeup_source { bool autosleep_enabled:1; }; +#define for_each_wakeup_source(ws) \ + for ((ws) = wakeup_sources_walk_start(); \ + (ws); \ + (ws) = wakeup_sources_walk_next((ws))) + #ifdef CONFIG_PM_SLEEP /* @@ -92,6 +97,10 @@ extern void wakeup_source_remove(struct wakeup_source *ws); extern struct wakeup_source *wakeup_source_register(struct device *dev, const char *name); extern void wakeup_source_unregister(struct wakeup_source *ws); +extern int wakeup_sources_read_lock(void); +extern void wakeup_sources_read_unlock(int idx); +extern struct wakeup_source *wakeup_sources_walk_start(void); +extern struct wakeup_source *wakeup_sources_walk_next(struct wakeup_source *ws); extern int device_wakeup_enable(struct device *dev); extern int device_wakeup_disable(struct device *dev); extern void device_set_wakeup_capable(struct device *dev, bool capable); -- cgit v1.2.3-71-gd317 From 8e6af017f4b1da9cdd2b55ce83853df8e167b4d3 Mon Sep 17 00:00:00 2001 From: Ethan Hansen <1ethanhansen@gmail.com> Date: Fri, 2 Aug 2019 13:37:58 -0700 Subject: rcu: Remove unused function hlist_bl_del_init_rcu() The function hlist_bl_del_init_rcu() is declared in rculist_bl.h, but never used. This commit therefore removes it. Signed-off-by: Ethan Hansen <1ethanhansen@gmail.com> Signed-off-by: Paul E. McKenney --- include/linux/rculist_bl.h | 28 ---------------------------- 1 file changed, 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rculist_bl.h b/include/linux/rculist_bl.h index 66e73ec1aa99..0b952d06eb0b 100644 --- a/include/linux/rculist_bl.h +++ b/include/linux/rculist_bl.h @@ -24,34 +24,6 @@ static inline struct hlist_bl_node *hlist_bl_first_rcu(struct hlist_bl_head *h) ((unsigned long)rcu_dereference_check(h->first, hlist_bl_is_locked(h)) & ~LIST_BL_LOCKMASK); } -/** - * hlist_bl_del_init_rcu - deletes entry from hash list with re-initialization - * @n: the element to delete from the hash list. - * - * Note: hlist_bl_unhashed() on the node returns true after this. It is - * useful for RCU based read lockfree traversal if the writer side - * must know if the list entry is still hashed or already unhashed. - * - * In particular, it means that we can not poison the forward pointers - * that may still be used for walking the hash list and we can only - * zero the pprev pointer so list_unhashed() will return true after - * this. - * - * The caller must take whatever precautions are necessary (such as - * holding appropriate locks) to avoid racing with another - * list-mutation primitive, such as hlist_bl_add_head_rcu() or - * hlist_bl_del_rcu(), running on this same list. However, it is - * perfectly legal to run concurrently with the _rcu list-traversal - * primitives, such as hlist_bl_for_each_entry_rcu(). - */ -static inline void hlist_bl_del_init_rcu(struct hlist_bl_node *n) -{ - if (!hlist_bl_unhashed(n)) { - __hlist_bl_del(n); - n->pprev = NULL; - } -} - /** * hlist_bl_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. -- cgit v1.2.3-71-gd317 From a63fc6b75cca984c71f095282e0227a390ba88f3 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 23 Sep 2019 15:05:11 -0700 Subject: rcu: Upgrade rcu_swap_protected() to rcu_replace_pointer() Although the rcu_swap_protected() macro follows the example of swap(), the interactions with RCU make its update of its argument somewhat counter-intuitive. This commit therefore introduces an rcu_replace_pointer() that returns the old value of the RCU pointer instead of doing the argument update. Once all the uses of rcu_swap_protected() are updated to instead use rcu_replace_pointer(), rcu_swap_protected() will be removed. Link: https://lore.kernel.org/lkml/CAHk-=wiAsJLw1egFEE=Z7-GGtM6wcvtyytXZA1+BHqta4gg6Hw@mail.gmail.com/ Reported-by: Linus Torvalds [ paulmck: From rcu_replace() to rcu_replace_pointer() per Ingo Molnar. ] Signed-off-by: Paul E. McKenney Cc: Bart Van Assche Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: Johannes Thumshirn Cc: Shane M Seymour Cc: Martin K. Petersen --- include/linux/rcupdate.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 75a2eded7aa2..185dd9736863 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -382,6 +382,24 @@ do { \ smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \ } while (0) +/** + * rcu_replace_pointer() - replace an RCU pointer, returning its old value + * @rcu_ptr: RCU pointer, whose old value is returned + * @ptr: regular pointer + * @c: the lockdep conditions under which the dereference will take place + * + * Perform a replacement, where @rcu_ptr is an RCU-annotated + * pointer and @c is the lockdep argument that is passed to the + * rcu_dereference_protected() call used to read that pointer. The old + * value of @rcu_ptr is returned, and @rcu_ptr is set to @ptr. + */ +#define rcu_replace_pointer(rcu_ptr, ptr, c) \ +({ \ + typeof(ptr) __tmp = rcu_dereference_protected((rcu_ptr), (c)); \ + rcu_assign_pointer((rcu_ptr), (ptr)); \ + __tmp; \ +}) + /** * rcu_swap_protected() - swap an RCU and a regular pointer * @rcu_ptr: RCU pointer -- cgit v1.2.3-71-gd317 From a445e940ea686fc60475564009821010eb213be3 Mon Sep 17 00:00:00 2001 From: Vladimir Murzin Date: Wed, 30 Oct 2019 10:13:13 +0000 Subject: dma-mapping: fix handling of dma-ranges for reserved memory (again) Daniele reported that issue previously fixed in c41f9ea998f3 ("drivers: dma-coherent: Account dma_pfn_offset when used with device tree") reappear shortly after 43fc509c3efb ("dma-coherent: introduce interface for default DMA pool") where fix was accidentally dropped. Lets put fix back in place and respect dma-ranges for reserved memory. Fixes: 43fc509c3efb ("dma-coherent: introduce interface for default DMA pool") Reported-by: Daniele Alessandrelli Tested-by: Daniele Alessandrelli Tested-by: Alexandre Torgue Signed-off-by: Vladimir Murzin Signed-off-by: Christoph Hellwig --- arch/arm/mm/dma-mapping-nommu.c | 2 +- include/linux/dma-mapping.h | 4 ++-- kernel/dma/coherent.c | 16 +++++++++------- 3 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c index db9247898300..287ef898a55e 100644 --- a/arch/arm/mm/dma-mapping-nommu.c +++ b/arch/arm/mm/dma-mapping-nommu.c @@ -35,7 +35,7 @@ static void *arm_nommu_dma_alloc(struct device *dev, size_t size, unsigned long attrs) { - void *ret = dma_alloc_from_global_coherent(size, dma_handle); + void *ret = dma_alloc_from_global_coherent(dev, size, dma_handle); /* * dma_alloc_from_global_coherent() may fail because: diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 4a1c4fca475a..10918c55003f 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -162,7 +162,7 @@ int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr); int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, size_t size, int *ret); -void *dma_alloc_from_global_coherent(ssize_t size, dma_addr_t *dma_handle); +void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size, dma_addr_t *dma_handle); int dma_release_from_global_coherent(int order, void *vaddr); int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *cpu_addr, size_t size, int *ret); @@ -172,7 +172,7 @@ int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *cpu_addr, #define dma_release_from_dev_coherent(dev, order, vaddr) (0) #define dma_mmap_from_dev_coherent(dev, vma, vaddr, order, ret) (0) -static inline void *dma_alloc_from_global_coherent(ssize_t size, +static inline void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size, dma_addr_t *dma_handle) { return NULL; diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c index 545e3869b0e3..551b0eb7028a 100644 --- a/kernel/dma/coherent.c +++ b/kernel/dma/coherent.c @@ -123,8 +123,9 @@ int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, return ret; } -static void *__dma_alloc_from_coherent(struct dma_coherent_mem *mem, - ssize_t size, dma_addr_t *dma_handle) +static void *__dma_alloc_from_coherent(struct device *dev, + struct dma_coherent_mem *mem, + ssize_t size, dma_addr_t *dma_handle) { int order = get_order(size); unsigned long flags; @@ -143,7 +144,7 @@ static void *__dma_alloc_from_coherent(struct dma_coherent_mem *mem, /* * Memory was found in the coherent area. */ - *dma_handle = mem->device_base + (pageno << PAGE_SHIFT); + *dma_handle = dma_get_device_base(dev, mem) + (pageno << PAGE_SHIFT); ret = mem->virt_base + (pageno << PAGE_SHIFT); spin_unlock_irqrestore(&mem->spinlock, flags); memset(ret, 0, size); @@ -175,17 +176,18 @@ int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size, if (!mem) return 0; - *ret = __dma_alloc_from_coherent(mem, size, dma_handle); + *ret = __dma_alloc_from_coherent(dev, mem, size, dma_handle); return 1; } -void *dma_alloc_from_global_coherent(ssize_t size, dma_addr_t *dma_handle) +void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size, + dma_addr_t *dma_handle) { if (!dma_coherent_default_memory) return NULL; - return __dma_alloc_from_coherent(dma_coherent_default_memory, size, - dma_handle); + return __dma_alloc_from_coherent(dev, dma_coherent_default_memory, size, + dma_handle); } static int __dma_release_from_coherent(struct dma_coherent_mem *mem, -- cgit v1.2.3-71-gd317 From 4544b9f25e70eae9f70a243de0cc802aa5c8cb69 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 29 Oct 2019 14:34:22 -0700 Subject: dma-mapping: Add vmap checks to dma_map_single() As we've seen from USB and other areas[1], we need to always do runtime checks for DMA operating on memory regions that might be remapped. This adds vmap checks (similar to those already in USB but missing in other places) into dma_map_single() so all callers benefit from the checking. [1] https://git.kernel.org/linus/3840c5b78803b2b6cc1ff820100a74a092c40cbb Suggested-by: Laura Abbott Signed-off-by: Kees Cook [hch: fixed the printk message] Signed-off-by: Christoph Hellwig --- include/linux/dma-mapping.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 10918c55003f..4d450672b7d6 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -583,6 +583,10 @@ static inline unsigned long dma_get_merge_boundary(struct device *dev) static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr, size_t size, enum dma_data_direction dir, unsigned long attrs) { + /* DMA must never operate on areas that might be remapped. */ + if (dev_WARN_ONCE(dev, is_vmalloc_addr(ptr), + "rejecting DMA map of vmalloc memory\n")) + return DMA_MAPPING_ERROR; debug_dma_map_single(dev, ptr, size); return dma_map_page_attrs(dev, virt_to_page(ptr), offset_in_page(ptr), size, dir, attrs); -- cgit v1.2.3-71-gd317 From fae7d7d5f374eadbb0b5dd31b39162e7176e9c3d Mon Sep 17 00:00:00 2001 From: Sean Paul Date: Wed, 30 Oct 2019 16:29:54 -0400 Subject: Revert "dma-buf: Add dma-buf heaps framework" This reverts commit a69b0e855d3fd278ff6f09a23e1edf929538e304. This patchset doesn't meet the UAPI requirements set out in [1] for the DRM subsystem. Once the userspace component is reviewed and ready for merge we can try again. [1]- https://01.org/linuxgraphics/gfx-docs/drm/gpu/drm-uapi.html#open-source-userspace-requirements Fixes: a69b0e855d3f ("dma-buf: Add dma-buf heaps framework") Cc: Laura Abbott Cc: Benjamin Gaignard Cc: Sumit Semwal Cc: Liam Mark Cc: Pratik Patel Cc: Brian Starkey Cc: Vincent Donnefort Cc: Sudipto Paul Cc: Andrew F. Davis Cc: Christoph Hellwig Cc: Chenbo Feng Cc: Alistair Strachan Cc: Hridya Valsaraju Cc: Hillf Danton Cc: dri-devel@lists.freedesktop.org Cc: Brian Starkey Cc: John Stultz Cc: Mauro Carvalho Chehab Cc: "David S. Miller" Cc: Greg Kroah-Hartman Cc: Rob Herring Cc: Jonathan Cameron Cc: "Paul E. McKenney" Cc: Sean Paul Cc: "Andrew F. Davis" Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Acked-by: David Airlie Signed-off-by: Sean Paul Link: https://patchwork.freedesktop.org/patch/msgid/20191030203003.101156-6-sean@poorly.run --- MAINTAINERS | 18 --- drivers/dma-buf/Kconfig | 9 -- drivers/dma-buf/Makefile | 1 - drivers/dma-buf/dma-heap.c | 269 ------------------------------------------ include/linux/dma-heap.h | 59 --------- include/uapi/linux/dma-heap.h | 55 --------- 6 files changed, 411 deletions(-) delete mode 100644 drivers/dma-buf/dma-heap.c delete mode 100644 include/linux/dma-heap.h delete mode 100644 include/uapi/linux/dma-heap.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 5f39067caa7c..b63c291ad029 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4942,24 +4942,6 @@ F: include/linux/*fence.h F: Documentation/driver-api/dma-buf.rst T: git git://anongit.freedesktop.org/drm/drm-misc -DMA-BUF HEAPS FRAMEWORK -M: Sumit Semwal -R: Andrew F. Davis -R: Benjamin Gaignard -R: Liam Mark -R: Laura Abbott -R: Brian Starkey -R: John Stultz -S: Maintained -L: linux-media@vger.kernel.org -L: dri-devel@lists.freedesktop.org -L: linaro-mm-sig@lists.linaro.org (moderated for non-subscribers) -F: include/uapi/linux/dma-heap.h -F: include/linux/dma-heap.h -F: drivers/dma-buf/dma-heap.c -F: drivers/dma-buf/heaps/* -T: git git://anongit.freedesktop.org/drm/drm-misc - DMA GENERIC OFFLOAD ENGINE SUBSYSTEM M: Vinod Koul L: dmaengine@vger.kernel.org diff --git a/drivers/dma-buf/Kconfig b/drivers/dma-buf/Kconfig index bffa58fc3e6e..a23b6752d11a 100644 --- a/drivers/dma-buf/Kconfig +++ b/drivers/dma-buf/Kconfig @@ -44,13 +44,4 @@ config DMABUF_SELFTESTS default n depends on DMA_SHARED_BUFFER -menuconfig DMABUF_HEAPS - bool "DMA-BUF Userland Memory Heaps" - select DMA_SHARED_BUFFER - help - Choose this option to enable the DMA-BUF userland memory heaps. - This options creates per heap chardevs in /dev/dma_heap/ which - allows userspace to allocate dma-bufs that can be shared - between drivers. - endmenu diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile index caee5eb3d351..03479da06422 100644 --- a/drivers/dma-buf/Makefile +++ b/drivers/dma-buf/Makefile @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only obj-y := dma-buf.o dma-fence.o dma-fence-array.o dma-fence-chain.o \ dma-resv.o seqno-fence.o -obj-$(CONFIG_DMABUF_HEAPS) += dma-heap.o obj-$(CONFIG_SYNC_FILE) += sync_file.o obj-$(CONFIG_SW_SYNC) += sw_sync.o sync_debug.o obj-$(CONFIG_UDMABUF) += udmabuf.o diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c deleted file mode 100644 index 9a41b73e54b4..000000000000 --- a/drivers/dma-buf/dma-heap.c +++ /dev/null @@ -1,269 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Framework for userspace DMA-BUF allocations - * - * Copyright (C) 2011 Google, Inc. - * Copyright (C) 2019 Linaro Ltd. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define DEVNAME "dma_heap" - -#define NUM_HEAP_MINORS 128 - -/** - * struct dma_heap - represents a dmabuf heap in the system - * @name: used for debugging/device-node name - * @ops: ops struct for this heap - * @minor minor number of this heap device - * @heap_devt heap device node - * @heap_cdev heap char device - * - * Represents a heap of memory from which buffers can be made. - */ -struct dma_heap { - const char *name; - const struct dma_heap_ops *ops; - void *priv; - unsigned int minor; - dev_t heap_devt; - struct list_head list; - struct cdev heap_cdev; -}; - -static LIST_HEAD(heap_list); -static DEFINE_MUTEX(heap_list_lock); -static dev_t dma_heap_devt; -static struct class *dma_heap_class; -static DEFINE_XARRAY_ALLOC(dma_heap_minors); - -static int dma_heap_buffer_alloc(struct dma_heap *heap, size_t len, - unsigned int fd_flags, - unsigned int heap_flags) -{ - /* - * Allocations from all heaps have to begin - * and end on page boundaries. - */ - len = PAGE_ALIGN(len); - if (!len) - return -EINVAL; - - return heap->ops->allocate(heap, len, fd_flags, heap_flags); -} - -static int dma_heap_open(struct inode *inode, struct file *file) -{ - struct dma_heap *heap; - - heap = xa_load(&dma_heap_minors, iminor(inode)); - if (!heap) { - pr_err("dma_heap: minor %d unknown.\n", iminor(inode)); - return -ENODEV; - } - - /* instance data as context */ - file->private_data = heap; - nonseekable_open(inode, file); - - return 0; -} - -static long dma_heap_ioctl_allocate(struct file *file, unsigned long arg) -{ - struct dma_heap_allocation_data heap_allocation; - struct dma_heap *heap = file->private_data; - int fd; - - if (copy_from_user(&heap_allocation, (void __user *)arg, - sizeof(heap_allocation))) - return -EFAULT; - - if (heap_allocation.fd || - heap_allocation.reserved0 || - heap_allocation.reserved1) { - pr_warn_once("dma_heap: ioctl data not valid\n"); - return -EINVAL; - } - - if (heap_allocation.fd_flags & ~DMA_HEAP_VALID_FD_FLAGS) { - pr_warn_once("dma_heap: fd_flags has invalid or unsupported flags set\n"); - return -EINVAL; - } - - if (heap_allocation.heap_flags & ~DMA_HEAP_VALID_HEAP_FLAGS) { - pr_warn_once("dma_heap: heap flags has invalid or unsupported flags set\n"); - return -EINVAL; - } - - fd = dma_heap_buffer_alloc(heap, heap_allocation.len, - heap_allocation.fd_flags, - heap_allocation.heap_flags); - if (fd < 0) - return fd; - - heap_allocation.fd = fd; - - if (copy_to_user((void __user *)arg, &heap_allocation, - sizeof(heap_allocation))) { - ksys_close(fd); - return -EFAULT; - } - - return 0; -} - -static long dma_heap_ioctl(struct file *file, unsigned int cmd, - unsigned long arg) -{ - int ret = 0; - - switch (cmd) { - case DMA_HEAP_IOC_ALLOC: - ret = dma_heap_ioctl_allocate(file, arg); - break; - default: - return -ENOTTY; - } - - return ret; -} - -static const struct file_operations dma_heap_fops = { - .owner = THIS_MODULE, - .open = dma_heap_open, - .unlocked_ioctl = dma_heap_ioctl, -#ifdef CONFIG_COMPAT - .compat_ioctl = dma_heap_ioctl, -#endif -}; - -/** - * dma_heap_get_drvdata() - get per-subdriver data for the heap - * @heap: DMA-Heap to retrieve private data for - * - * Returns: - * The per-subdriver data for the heap. - */ -void *dma_heap_get_drvdata(struct dma_heap *heap) -{ - return heap->priv; -} - -struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info) -{ - struct dma_heap *heap, *h, *err_ret; - struct device *dev_ret; - int ret; - - if (!exp_info->name || !strcmp(exp_info->name, "")) { - pr_err("dma_heap: Cannot add heap without a name\n"); - return ERR_PTR(-EINVAL); - } - - if (!exp_info->ops || !exp_info->ops->allocate) { - pr_err("dma_heap: Cannot add heap with invalid ops struct\n"); - return ERR_PTR(-EINVAL); - } - - /* check the name is unique */ - mutex_lock(&heap_list_lock); - list_for_each_entry(h, &heap_list, list) { - if (!strcmp(h->name, exp_info->name)) { - mutex_unlock(&heap_list_lock); - pr_err("dma_heap: Already registered heap named %s\n", - exp_info->name); - return ERR_PTR(-EINVAL); - } - } - mutex_unlock(&heap_list_lock); - - heap = kzalloc(sizeof(*heap), GFP_KERNEL); - if (!heap) - return ERR_PTR(-ENOMEM); - - heap->name = exp_info->name; - heap->ops = exp_info->ops; - heap->priv = exp_info->priv; - - /* Find unused minor number */ - ret = xa_alloc(&dma_heap_minors, &heap->minor, heap, - XA_LIMIT(0, NUM_HEAP_MINORS - 1), GFP_KERNEL); - if (ret < 0) { - pr_err("dma_heap: Unable to get minor number for heap\n"); - err_ret = ERR_PTR(ret); - goto err0; - } - - /* Create device */ - heap->heap_devt = MKDEV(MAJOR(dma_heap_devt), heap->minor); - - cdev_init(&heap->heap_cdev, &dma_heap_fops); - ret = cdev_add(&heap->heap_cdev, heap->heap_devt, 1); - if (ret < 0) { - pr_err("dma_heap: Unable to add char device\n"); - err_ret = ERR_PTR(ret); - goto err1; - } - - dev_ret = device_create(dma_heap_class, - NULL, - heap->heap_devt, - NULL, - heap->name); - if (IS_ERR(dev_ret)) { - pr_err("dma_heap: Unable to create device\n"); - err_ret = ERR_CAST(dev_ret); - goto err2; - } - /* Add heap to the list */ - mutex_lock(&heap_list_lock); - list_add(&heap->list, &heap_list); - mutex_unlock(&heap_list_lock); - - return heap; - -err2: - cdev_del(&heap->heap_cdev); -err1: - xa_erase(&dma_heap_minors, heap->minor); -err0: - kfree(heap); - return err_ret; -} - -static char *dma_heap_devnode(struct device *dev, umode_t *mode) -{ - return kasprintf(GFP_KERNEL, "dma_heap/%s", dev_name(dev)); -} - -static int dma_heap_init(void) -{ - int ret; - - ret = alloc_chrdev_region(&dma_heap_devt, 0, NUM_HEAP_MINORS, DEVNAME); - if (ret) - return ret; - - dma_heap_class = class_create(THIS_MODULE, DEVNAME); - if (IS_ERR(dma_heap_class)) { - unregister_chrdev_region(dma_heap_devt, NUM_HEAP_MINORS); - return PTR_ERR(dma_heap_class); - } - dma_heap_class->devnode = dma_heap_devnode; - - return 0; -} -subsys_initcall(dma_heap_init); diff --git a/include/linux/dma-heap.h b/include/linux/dma-heap.h deleted file mode 100644 index 454e354d1ffb..000000000000 --- a/include/linux/dma-heap.h +++ /dev/null @@ -1,59 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * DMABUF Heaps Allocation Infrastructure - * - * Copyright (C) 2011 Google, Inc. - * Copyright (C) 2019 Linaro Ltd. - */ - -#ifndef _DMA_HEAPS_H -#define _DMA_HEAPS_H - -#include -#include - -struct dma_heap; - -/** - * struct dma_heap_ops - ops to operate on a given heap - * @allocate: allocate dmabuf and return fd - * - * allocate returns dmabuf fd on success, -errno on error. - */ -struct dma_heap_ops { - int (*allocate)(struct dma_heap *heap, - unsigned long len, - unsigned long fd_flags, - unsigned long heap_flags); -}; - -/** - * struct dma_heap_export_info - information needed to export a new dmabuf heap - * @name: used for debugging/device-node name - * @ops: ops struct for this heap - * @priv: heap exporter private data - * - * Information needed to export a new dmabuf heap. - */ -struct dma_heap_export_info { - const char *name; - const struct dma_heap_ops *ops; - void *priv; -}; - -/** - * dma_heap_get_drvdata() - get per-heap driver data - * @heap: DMA-Heap to retrieve private data for - * - * Returns: - * The per-heap data for the heap. - */ -void *dma_heap_get_drvdata(struct dma_heap *heap); - -/** - * dma_heap_add - adds a heap to dmabuf heaps - * @exp_info: information needed to register this heap - */ -struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info); - -#endif /* _DMA_HEAPS_H */ diff --git a/include/uapi/linux/dma-heap.h b/include/uapi/linux/dma-heap.h deleted file mode 100644 index 6ce5cc68d238..000000000000 --- a/include/uapi/linux/dma-heap.h +++ /dev/null @@ -1,55 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * DMABUF Heaps Userspace API - * - * Copyright (C) 2011 Google, Inc. - * Copyright (C) 2019 Linaro Ltd. - */ -#ifndef _UAPI_LINUX_DMABUF_POOL_H -#define _UAPI_LINUX_DMABUF_POOL_H - -#include -#include - -/** - * DOC: DMABUF Heaps Userspace API - */ - -/* Valid FD_FLAGS are O_CLOEXEC, O_RDONLY, O_WRONLY, O_RDWR */ -#define DMA_HEAP_VALID_FD_FLAGS (O_CLOEXEC | O_ACCMODE) - -/* Currently no heap flags */ -#define DMA_HEAP_VALID_HEAP_FLAGS (0) - -/** - * struct dma_heap_allocation_data - metadata passed from userspace for - * allocations - * @len: size of the allocation - * @fd: will be populated with a fd which provdes the - * handle to the allocated dma-buf - * @fd_flags: file descriptor flags used when allocating - * @heap_flags: flags passed to heap - * - * Provided by userspace as an argument to the ioctl - */ -struct dma_heap_allocation_data { - __u64 len; - __u32 fd; - __u32 fd_flags; - __u64 heap_flags; - __u32 reserved0; - __u32 reserved1; -}; - -#define DMA_HEAP_IOC_MAGIC 'H' - -/** - * DOC: DMA_HEAP_IOC_ALLOC - allocate memory from pool - * - * Takes an dma_heap_allocation_data struct and returns it with the fd field - * populated with the dmabuf handle of the allocation. - */ -#define DMA_HEAP_IOC_ALLOC _IOWR(DMA_HEAP_IOC_MAGIC, 0, \ - struct dma_heap_allocation_data) - -#endif /* _UAPI_LINUX_DMABUF_POOL_H */ -- cgit v1.2.3-71-gd317 From 711b2bfba748b5adf8ad837b490b393197279203 Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Thu, 24 Oct 2019 00:38:49 +0200 Subject: phy: add PHY_MODE_LVDS There are combo phys out there that can be switched between doing dsi and lvds. So add a mode definition for it. Signed-off-by: Heiko Stuebner Signed-off-by: Kishon Vijay Abraham I --- include/linux/phy/phy.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index 15032f145063..56d3a100006a 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -38,7 +38,8 @@ enum phy_mode { PHY_MODE_PCIE, PHY_MODE_ETHERNET, PHY_MODE_MIPI_DPHY, - PHY_MODE_SATA + PHY_MODE_SATA, + PHY_MODE_LVDS, }; /** -- cgit v1.2.3-71-gd317 From 22a6564f716b0746b5a05add3f9f37549f89244e Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Thu, 12 Sep 2019 16:26:05 +0300 Subject: clk: ti: clkctrl: convert to use bit helper macros instead of bitops This improves the readibility of the code slightly, and makes modifying the flags bit simpler. Signed-off-by: Tero Kristo --- drivers/clk/ti/clkctrl.c | 8 ++++---- include/linux/clk/ti.h | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/clk/ti/clkctrl.c b/drivers/clk/ti/clkctrl.c index a914df2e9e1b..d904a9a7626a 100644 --- a/drivers/clk/ti/clkctrl.c +++ b/drivers/clk/ti/clkctrl.c @@ -24,7 +24,7 @@ #include #include "clock.h" -#define NO_IDLEST 0x1 +#define NO_IDLEST 0 #define OMAP4_MODULEMODE_MASK 0x3 @@ -158,7 +158,7 @@ static int _omap4_clkctrl_clk_enable(struct clk_hw *hw) ti_clk_ll_ops->clk_writel(val, &clk->enable_reg); - if (clk->flags & NO_IDLEST) + if (test_bit(NO_IDLEST, &clk->flags)) return 0; /* Wait until module is enabled */ @@ -187,7 +187,7 @@ static void _omap4_clkctrl_clk_disable(struct clk_hw *hw) ti_clk_ll_ops->clk_writel(val, &clk->enable_reg); - if (clk->flags & NO_IDLEST) + if (test_bit(NO_IDLEST, &clk->flags)) goto exit; /* Wait until module is disabled */ @@ -596,7 +596,7 @@ static void __init _ti_omap4_clkctrl_setup(struct device_node *node) if (reg_data->flags & CLKF_HW_SUP) hw->enable_bit = MODULEMODE_HWCTRL; if (reg_data->flags & CLKF_NO_IDLEST) - hw->flags |= NO_IDLEST; + set_bit(NO_IDLEST, &hw->flags); if (reg_data->clkdm_name) hw->clkdm_name = reg_data->clkdm_name; diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index 1e8ef96555ce..bb2c5af9082a 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -153,7 +153,7 @@ struct clk_hw_omap { u8 fixed_div; struct clk_omap_reg enable_reg; u8 enable_bit; - u8 flags; + unsigned long flags; struct clk_omap_reg clksel_reg; struct dpll_data *dpll_data; const char *clkdm_name; -- cgit v1.2.3-71-gd317 From 2209b72d41993c13de220b82c830b482925322b9 Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Thu, 12 Sep 2019 16:26:06 +0300 Subject: clk: ti: clkctrl: add new exported API for checking standby info Standby status is provided for certain clkctrl clocks to see if the given module has entered standby or not. This is mostly needed by remoteproc code to see if the remoteproc has entered standby and the clock can be turned off safely. Signed-off-by: Tero Kristo --- drivers/clk/ti/clkctrl.c | 33 +++++++++++++++++++++++++++++++++ include/linux/clk/ti.h | 1 + 2 files changed, 34 insertions(+) (limited to 'include/linux') diff --git a/drivers/clk/ti/clkctrl.c b/drivers/clk/ti/clkctrl.c index d904a9a7626a..d6cb41b55800 100644 --- a/drivers/clk/ti/clkctrl.c +++ b/drivers/clk/ti/clkctrl.c @@ -34,6 +34,9 @@ #define OMAP4_IDLEST_MASK (0x3 << 16) #define OMAP4_IDLEST_SHIFT 16 +#define OMAP4_STBYST_MASK BIT(18) +#define OMAP4_STBYST_SHIFT 18 + #define CLKCTRL_IDLEST_FUNCTIONAL 0x0 #define CLKCTRL_IDLEST_INTERFACE_IDLE 0x2 #define CLKCTRL_IDLEST_DISABLED 0x3 @@ -647,3 +650,33 @@ cleanup: } CLK_OF_DECLARE(ti_omap4_clkctrl_clock, "ti,clkctrl", _ti_omap4_clkctrl_setup); + +/** + * ti_clk_is_in_standby - Check if clkctrl clock is in standby or not + * @clk: clock to check standby status for + * + * Finds whether the provided clock is in standby mode or not. Returns + * true if the provided clock is a clkctrl type clock and it is in standby, + * false otherwise. + */ +bool ti_clk_is_in_standby(struct clk *clk) +{ + struct clk_hw *hw; + struct clk_hw_omap *hwclk; + u32 val; + + hw = __clk_get_hw(clk); + + if (!omap2_clk_is_hw_omap(hw)) + return false; + + hwclk = to_clk_hw_omap(hw); + + val = ti_clk_ll_ops->clk_readl(&hwclk->enable_reg); + + if (val & OMAP4_STBYST_MASK) + return true; + + return false; +} +EXPORT_SYMBOL_GPL(ti_clk_is_in_standby); diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index bb2c5af9082a..c62f6fa6763d 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -298,6 +298,7 @@ struct ti_clk_features { void ti_clk_setup_features(struct ti_clk_features *features); const struct ti_clk_features *ti_clk_get_features(void); +bool ti_clk_is_in_standby(struct clk *clk); int omap3_noncore_dpll_save_context(struct clk_hw *hw); void omap3_noncore_dpll_restore_context(struct clk_hw *hw); -- cgit v1.2.3-71-gd317 From f1b9509c2fb0ef4db8d22dac9aef8e856a5d81f6 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 30 Oct 2019 15:32:11 -0700 Subject: bpf: Replace prog_raw_tp+btf_id with prog_tracing The bpf program type raw_tp together with 'expected_attach_type' was the most appropriate api to indicate BTF-enabled raw_tp programs. But during development it became apparent that 'expected_attach_type' cannot be used and new 'attach_btf_id' field had to be introduced. Which means that the information is duplicated in two fields where one of them is ignored. Clean it up by introducing new program type where both 'expected_attach_type' and 'attach_btf_id' fields have specific meaning. In the future 'expected_attach_type' will be extended with other attach points that have similar semantics to raw_tp. This patch is replacing BTF-enabled BPF_PROG_TYPE_RAW_TRACEPOINT with prog_type = BPF_RPOG_TYPE_TRACING expected_attach_type = BPF_TRACE_RAW_TP attach_btf_id = btf_id of raw tracepoint inside the kernel Future patches will add expected_attach_type = BPF_TRACE_FENTRY or BPF_TRACE_FEXIT where programs have the same input context and the same helpers, but different attach points. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20191030223212.953010-2-ast@kernel.org --- include/linux/bpf.h | 5 +++++ include/linux/bpf_types.h | 1 + include/uapi/linux/bpf.h | 2 ++ kernel/bpf/syscall.c | 6 +++--- kernel/bpf/verifier.c | 34 ++++++++++++++++++++++++---------- kernel/trace/bpf_trace.c | 44 ++++++++++++++++++++++++++++++++++++-------- 6 files changed, 71 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 171be30fe0ae..80158cff44bd 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -373,6 +373,11 @@ enum bpf_cgroup_storage_type { #define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX +/* The longest tracepoint has 12 args. + * See include/trace/bpf_probe.h + */ +#define MAX_BPF_FUNC_ARGS 12 + struct bpf_prog_stats { u64 cnt; u64 nsecs; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 36a9c2325176..de14872b01ba 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -26,6 +26,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint) BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event) BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint) BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable) +BPF_PROG_TYPE(BPF_PROG_TYPE_TRACING, tracing) #endif #ifdef CONFIG_CGROUP_BPF BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4af8b0819a32..a6bf19dabaab 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -173,6 +173,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_CGROUP_SYSCTL, BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, BPF_PROG_TYPE_CGROUP_SOCKOPT, + BPF_PROG_TYPE_TRACING, }; enum bpf_attach_type { @@ -199,6 +200,7 @@ enum bpf_attach_type { BPF_CGROUP_UDP6_RECVMSG, BPF_CGROUP_GETSOCKOPT, BPF_CGROUP_SETSOCKOPT, + BPF_TRACE_RAW_TP, __MAX_BPF_ATTACH_TYPE }; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index ff5225759553..985d01ced196 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1571,7 +1571,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, u32 btf_id) { switch (prog_type) { - case BPF_PROG_TYPE_RAW_TRACEPOINT: + case BPF_PROG_TYPE_TRACING: if (btf_id > BTF_MAX_TYPE) return -EINVAL; break; @@ -1833,13 +1833,13 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) return PTR_ERR(prog); if (prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT && + prog->type != BPF_PROG_TYPE_TRACING && prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE) { err = -EINVAL; goto out_put_prog; } - if (prog->type == BPF_PROG_TYPE_RAW_TRACEPOINT && - prog->aux->attach_btf_id) { + if (prog->type == BPF_PROG_TYPE_TRACING) { if (attr->raw_tracepoint.name) { /* raw_tp name should not be specified in raw_tp * programs that were verified via in-kernel BTF info diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6b0de04f8b91..2f2374967b36 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -9381,24 +9381,36 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog; u32 btf_id = prog->aux->attach_btf_id; + const char prefix[] = "btf_trace_"; const struct btf_type *t; const char *tname; - if (prog->type == BPF_PROG_TYPE_RAW_TRACEPOINT && btf_id) { - const char prefix[] = "btf_trace_"; + if (prog->type != BPF_PROG_TYPE_TRACING) + return 0; - t = btf_type_by_id(btf_vmlinux, btf_id); - if (!t) { - verbose(env, "attach_btf_id %u is invalid\n", btf_id); - return -EINVAL; - } + if (!btf_id) { + verbose(env, "Tracing programs must provide btf_id\n"); + return -EINVAL; + } + t = btf_type_by_id(btf_vmlinux, btf_id); + if (!t) { + verbose(env, "attach_btf_id %u is invalid\n", btf_id); + return -EINVAL; + } + tname = btf_name_by_offset(btf_vmlinux, t->name_off); + if (!tname) { + verbose(env, "attach_btf_id %u doesn't have a name\n", btf_id); + return -EINVAL; + } + + switch (prog->expected_attach_type) { + case BPF_TRACE_RAW_TP: if (!btf_type_is_typedef(t)) { verbose(env, "attach_btf_id %u is not a typedef\n", btf_id); return -EINVAL; } - tname = btf_name_by_offset(btf_vmlinux, t->name_off); - if (!tname || strncmp(prefix, tname, sizeof(prefix) - 1)) { + if (strncmp(prefix, tname, sizeof(prefix) - 1)) { verbose(env, "attach_btf_id %u points to wrong type name %s\n", btf_id, tname); return -EINVAL; @@ -9419,8 +9431,10 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) prog->aux->attach_func_name = tname; prog->aux->attach_func_proto = t; prog->aux->attach_btf_trace = true; + return 0; + default: + return -EINVAL; } - return 0; } int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 571c25d60710..f50bf19f7a05 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1055,10 +1055,6 @@ raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_perf_event_output_proto_raw_tp; -#ifdef CONFIG_NET - case BPF_FUNC_skb_output: - return &bpf_skb_output_proto; -#endif case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_raw_tp; case BPF_FUNC_get_stack: @@ -1068,20 +1064,44 @@ raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) } } +static const struct bpf_func_proto * +tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + switch (func_id) { +#ifdef CONFIG_NET + case BPF_FUNC_skb_output: + return &bpf_skb_output_proto; +#endif + default: + return raw_tp_prog_func_proto(func_id, prog); + } +} + static bool raw_tp_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { - /* largest tracepoint in the kernel has 12 args */ - if (off < 0 || off >= sizeof(__u64) * 12) + if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS) + return false; + if (type != BPF_READ) + return false; + if (off % size != 0) + return false; + return true; +} + +static bool tracing_prog_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS) return false; if (type != BPF_READ) return false; if (off % size != 0) return false; - if (!prog->aux->attach_btf_id) - return true; return btf_ctx_access(off, size, type, prog, info); } @@ -1093,6 +1113,14 @@ const struct bpf_verifier_ops raw_tracepoint_verifier_ops = { const struct bpf_prog_ops raw_tracepoint_prog_ops = { }; +const struct bpf_verifier_ops tracing_verifier_ops = { + .get_func_proto = tracing_prog_func_proto, + .is_valid_access = tracing_prog_is_valid_access, +}; + +const struct bpf_prog_ops tracing_prog_ops = { +}; + static bool raw_tp_writable_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, -- cgit v1.2.3-71-gd317 From f94df9890e98f2090c6a8d70c795134863b70201 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 24 Sep 2019 16:07:45 +0100 Subject: Add wake_up_interruptible_sync_poll_locked() Add a wakeup call for a case whereby the caller already has the waitqueue spinlock held. This can be used by pipes to alter the ring buffer indices and issue a wakeup under the same spinlock. Signed-off-by: David Howells Acked-by: Peter Zijlstra (Intel) --- include/linux/wait.h | 3 +++ kernel/sched/wait.c | 23 +++++++++++++++++++++++ 2 files changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index bb7676d396cd..3283c8d02137 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -202,6 +202,7 @@ void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, vo void __wake_up_locked_key_bookmark(struct wait_queue_head *wq_head, unsigned int mode, void *key, wait_queue_entry_t *bookmark); void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); +void __wake_up_locked_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr); void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode); @@ -229,6 +230,8 @@ void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode); __wake_up(x, TASK_INTERRUPTIBLE, 1, poll_to_key(m)) #define wake_up_interruptible_sync_poll(x, m) \ __wake_up_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m)) +#define wake_up_interruptible_sync_poll_locked(x, m) \ + __wake_up_locked_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m)) #define ___wait_cond_timeout(condition) \ ({ \ diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index b4b52361dab7..ba059fbfc53a 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -191,6 +191,29 @@ void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, } EXPORT_SYMBOL_GPL(__wake_up_sync_key); +/** + * __wake_up_locked_sync_key - wake up a thread blocked on a locked waitqueue. + * @wq_head: the waitqueue + * @mode: which threads + * @key: opaque value to be passed to wakeup targets + * + * The sync wakeup differs in that the waker knows that it will schedule + * away soon, so while the target thread will be woken up, it will not + * be migrated to another CPU - ie. the two threads are 'synchronized' + * with each other. This can prevent needless bouncing between CPUs. + * + * On UP it can prevent extra preemption. + * + * If this function wakes up a task, it executes a full memory barrier before + * accessing the task state. + */ +void __wake_up_locked_sync_key(struct wait_queue_head *wq_head, + unsigned int mode, void *key) +{ + __wake_up_common(wq_head, mode, 1, WF_SYNC, key, NULL); +} +EXPORT_SYMBOL_GPL(__wake_up_locked_sync_key); + /* * __wake_up_sync - see __wake_up_sync_key() */ -- cgit v1.2.3-71-gd317 From 8cefc107ca54c8b06438b7dc9cc08bc0a11d5b98 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 15 Nov 2019 13:30:32 +0000 Subject: pipe: Use head and tail pointers for the ring, not cursor and length Convert pipes to use head and tail pointers for the buffer ring rather than pointer and length as the latter requires two atomic ops to update (or a combined op) whereas the former only requires one. (1) The head pointer is the point at which production occurs and points to the slot in which the next buffer will be placed. This is equivalent to pipe->curbuf + pipe->nrbufs. The head pointer belongs to the write-side. (2) The tail pointer is the point at which consumption occurs. It points to the next slot to be consumed. This is equivalent to pipe->curbuf. The tail pointer belongs to the read-side. (3) head and tail are allowed to run to UINT_MAX and wrap naturally. They are only masked off when the array is being accessed, e.g.: pipe->bufs[head & mask] This means that it is not necessary to have a dead slot in the ring as head == tail isn't ambiguous. (4) The ring is empty if "head == tail". A helper, pipe_empty(), is provided for this. (5) The occupancy of the ring is "head - tail". A helper, pipe_occupancy(), is provided for this. (6) The number of free slots in the ring is "pipe->ring_size - occupancy". A helper, pipe_space_for_user() is provided to indicate how many slots userspace may use. (7) The ring is full if "head - tail >= pipe->ring_size". A helper, pipe_full(), is provided for this. Signed-off-by: David Howells --- drivers/char/virtio_console.c | 16 ++- fs/fuse/dev.c | 31 +++-- fs/pipe.c | 170 ++++++++++++++------------ fs/splice.c | 190 +++++++++++++++++------------ include/linux/pipe_fs_i.h | 60 +++++++++- include/linux/uio.h | 4 +- lib/iov_iter.c | 269 ++++++++++++++++++++++++------------------ 7 files changed, 448 insertions(+), 292 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 7270e7b69262..de35c56b3d96 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -919,6 +919,7 @@ static ssize_t port_fops_splice_write(struct pipe_inode_info *pipe, .pos = *ppos, .u.data = &sgl, }; + unsigned int occupancy; /* * Rproc_serial does not yet support splice. To support splice @@ -929,21 +930,18 @@ static ssize_t port_fops_splice_write(struct pipe_inode_info *pipe, if (is_rproc_serial(port->out_vq->vdev)) return -EINVAL; - /* - * pipe->nrbufs == 0 means there are no data to transfer, - * so this returns just 0 for no data. - */ pipe_lock(pipe); - if (!pipe->nrbufs) { - ret = 0; + ret = 0; + if (pipe_empty(pipe->head, pipe->tail)) goto error_out; - } ret = wait_port_writable(port, filp->f_flags & O_NONBLOCK); if (ret < 0) goto error_out; - buf = alloc_buf(port->portdev->vdev, 0, pipe->nrbufs); + occupancy = pipe_occupancy(pipe->head, pipe->tail); + buf = alloc_buf(port->portdev->vdev, 0, occupancy); + if (!buf) { ret = -ENOMEM; goto error_out; @@ -951,7 +949,7 @@ static ssize_t port_fops_splice_write(struct pipe_inode_info *pipe, sgl.n = 0; sgl.len = 0; - sgl.size = pipe->nrbufs; + sgl.size = occupancy; sgl.sg = buf->sg; sg_init_table(sgl.sg, sgl.size); ret = __splice_from_pipe(pipe, &sd, pipe_to_sg); diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index dadd617d826c..c56011f95a87 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -703,7 +703,7 @@ static int fuse_copy_fill(struct fuse_copy_state *cs) cs->pipebufs++; cs->nr_segs--; } else { - if (cs->nr_segs == cs->pipe->buffers) + if (cs->nr_segs >= cs->pipe->ring_size) return -EIO; page = alloc_page(GFP_HIGHUSER); @@ -879,7 +879,7 @@ static int fuse_ref_page(struct fuse_copy_state *cs, struct page *page, struct pipe_buffer *buf; int err; - if (cs->nr_segs == cs->pipe->buffers) + if (cs->nr_segs >= cs->pipe->ring_size) return -EIO; err = unlock_request(cs->req); @@ -1341,7 +1341,7 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos, if (!fud) return -EPERM; - bufs = kvmalloc_array(pipe->buffers, sizeof(struct pipe_buffer), + bufs = kvmalloc_array(pipe->ring_size, sizeof(struct pipe_buffer), GFP_KERNEL); if (!bufs) return -ENOMEM; @@ -1353,7 +1353,7 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos, if (ret < 0) goto out; - if (pipe->nrbufs + cs.nr_segs > pipe->buffers) { + if (pipe_occupancy(pipe->head, pipe->tail) + cs.nr_segs > pipe->ring_size) { ret = -EIO; goto out; } @@ -1935,6 +1935,7 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags) { + unsigned int head, tail, mask, count; unsigned nbuf; unsigned idx; struct pipe_buffer *bufs; @@ -1949,8 +1950,12 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, pipe_lock(pipe); - bufs = kvmalloc_array(pipe->nrbufs, sizeof(struct pipe_buffer), - GFP_KERNEL); + head = pipe->head; + tail = pipe->tail; + mask = pipe->ring_size - 1; + count = head - tail; + + bufs = kvmalloc_array(count, sizeof(struct pipe_buffer), GFP_KERNEL); if (!bufs) { pipe_unlock(pipe); return -ENOMEM; @@ -1958,8 +1963,8 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, nbuf = 0; rem = 0; - for (idx = 0; idx < pipe->nrbufs && rem < len; idx++) - rem += pipe->bufs[(pipe->curbuf + idx) & (pipe->buffers - 1)].len; + for (idx = tail; idx < head && rem < len; idx++) + rem += pipe->bufs[idx & mask].len; ret = -EINVAL; if (rem < len) @@ -1970,16 +1975,16 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, struct pipe_buffer *ibuf; struct pipe_buffer *obuf; - BUG_ON(nbuf >= pipe->buffers); - BUG_ON(!pipe->nrbufs); - ibuf = &pipe->bufs[pipe->curbuf]; + BUG_ON(nbuf >= pipe->ring_size); + BUG_ON(tail == head); + ibuf = &pipe->bufs[tail & mask]; obuf = &bufs[nbuf]; if (rem >= ibuf->len) { *obuf = *ibuf; ibuf->ops = NULL; - pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1); - pipe->nrbufs--; + tail++; + pipe->tail = tail; } else { if (!pipe_buf_get(pipe, ibuf)) goto out_free; diff --git a/fs/pipe.c b/fs/pipe.c index 8a2ab2f974bd..e9b361cb093e 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -43,10 +43,12 @@ unsigned long pipe_user_pages_hard; unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR; /* - * We use a start+len construction, which provides full use of the - * allocated memory. - * -- Florian Coosmann (FGC) - * + * We use head and tail indices that aren't masked off, except at the point of + * dereference, but rather they're allowed to wrap naturally. This means there + * isn't a dead spot in the buffer, but the ring has to be a power of two and + * <= 2^31. + * -- David Howells 2019-09-23. + * * Reads with count = 0 should always return 0. * -- Julian Bradfield 1999-06-07. * @@ -285,10 +287,12 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) ret = 0; __pipe_lock(pipe); for (;;) { - int bufs = pipe->nrbufs; - if (bufs) { - int curbuf = pipe->curbuf; - struct pipe_buffer *buf = pipe->bufs + curbuf; + unsigned int head = pipe->head; + unsigned int tail = pipe->tail; + unsigned int mask = pipe->ring_size - 1; + + if (!pipe_empty(head, tail)) { + struct pipe_buffer *buf = &pipe->bufs[tail & mask]; size_t chars = buf->len; size_t written; int error; @@ -321,17 +325,17 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) if (!buf->len) { pipe_buf_release(pipe, buf); - curbuf = (curbuf + 1) & (pipe->buffers - 1); - pipe->curbuf = curbuf; - pipe->nrbufs = --bufs; + tail++; + pipe->tail = tail; do_wakeup = 1; } total_len -= chars; if (!total_len) break; /* common path: read succeeded */ + if (!pipe_empty(head, tail)) /* More to do? */ + continue; } - if (bufs) /* More to do? */ - continue; + if (!pipe->writers) break; if (!pipe->waiting_writers) { @@ -380,6 +384,7 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) { struct file *filp = iocb->ki_filp; struct pipe_inode_info *pipe = filp->private_data; + unsigned int head, tail, max_usage, mask; ssize_t ret = 0; int do_wakeup = 0; size_t total_len = iov_iter_count(from); @@ -397,12 +402,15 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) goto out; } + tail = pipe->tail; + head = pipe->head; + max_usage = pipe->ring_size; + mask = pipe->ring_size - 1; + /* We try to merge small writes */ chars = total_len & (PAGE_SIZE-1); /* size of the last buffer */ - if (pipe->nrbufs && chars != 0) { - int lastbuf = (pipe->curbuf + pipe->nrbufs - 1) & - (pipe->buffers - 1); - struct pipe_buffer *buf = pipe->bufs + lastbuf; + if (!pipe_empty(head, tail) && chars != 0) { + struct pipe_buffer *buf = &pipe->bufs[(head - 1) & mask]; int offset = buf->offset + buf->len; if (pipe_buf_can_merge(buf) && offset + chars <= PAGE_SIZE) { @@ -423,18 +431,16 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) } for (;;) { - int bufs; - if (!pipe->readers) { send_sig(SIGPIPE, current, 0); if (!ret) ret = -EPIPE; break; } - bufs = pipe->nrbufs; - if (bufs < pipe->buffers) { - int newbuf = (pipe->curbuf + bufs) & (pipe->buffers-1); - struct pipe_buffer *buf = pipe->bufs + newbuf; + + tail = pipe->tail; + if (!pipe_full(head, tail, max_usage)) { + struct pipe_buffer *buf = &pipe->bufs[head & mask]; struct page *page = pipe->tmp_page; int copied; @@ -470,14 +476,19 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) buf->ops = &packet_pipe_buf_ops; buf->flags = PIPE_BUF_FLAG_PACKET; } - pipe->nrbufs = ++bufs; + + head++; + pipe->head = head; pipe->tmp_page = NULL; if (!iov_iter_count(from)) break; } - if (bufs < pipe->buffers) + + if (!pipe_full(head, tail, max_usage)) continue; + + /* Wait for buffer space to become available. */ if (filp->f_flags & O_NONBLOCK) { if (!ret) ret = -EAGAIN; @@ -515,17 +526,19 @@ out: static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct pipe_inode_info *pipe = filp->private_data; - int count, buf, nrbufs; + int count, head, tail, mask; switch (cmd) { case FIONREAD: __pipe_lock(pipe); count = 0; - buf = pipe->curbuf; - nrbufs = pipe->nrbufs; - while (--nrbufs >= 0) { - count += pipe->bufs[buf].len; - buf = (buf+1) & (pipe->buffers - 1); + head = pipe->head; + tail = pipe->tail; + mask = pipe->ring_size - 1; + + while (tail != head) { + count += pipe->bufs[tail & mask].len; + tail++; } __pipe_unlock(pipe); @@ -541,21 +554,25 @@ pipe_poll(struct file *filp, poll_table *wait) { __poll_t mask; struct pipe_inode_info *pipe = filp->private_data; - int nrbufs; + unsigned int head = READ_ONCE(pipe->head); + unsigned int tail = READ_ONCE(pipe->tail); poll_wait(filp, &pipe->wait, wait); + BUG_ON(pipe_occupancy(head, tail) > pipe->ring_size); + /* Reading only -- no need for acquiring the semaphore. */ - nrbufs = pipe->nrbufs; mask = 0; if (filp->f_mode & FMODE_READ) { - mask = (nrbufs > 0) ? EPOLLIN | EPOLLRDNORM : 0; + if (!pipe_empty(head, tail)) + mask |= EPOLLIN | EPOLLRDNORM; if (!pipe->writers && filp->f_version != pipe->w_counter) mask |= EPOLLHUP; } if (filp->f_mode & FMODE_WRITE) { - mask |= (nrbufs < pipe->buffers) ? EPOLLOUT | EPOLLWRNORM : 0; + if (!pipe_full(head, tail, pipe->ring_size)) + mask |= EPOLLOUT | EPOLLWRNORM; /* * Most Unices do not set EPOLLERR for FIFOs but on Linux they * behave exactly like pipes for poll(). @@ -679,7 +696,7 @@ struct pipe_inode_info *alloc_pipe_info(void) if (pipe->bufs) { init_waitqueue_head(&pipe->wait); pipe->r_counter = pipe->w_counter = 1; - pipe->buffers = pipe_bufs; + pipe->ring_size = pipe_bufs; pipe->user = user; mutex_init(&pipe->mutex); return pipe; @@ -697,9 +714,9 @@ void free_pipe_info(struct pipe_inode_info *pipe) { int i; - (void) account_pipe_buffers(pipe->user, pipe->buffers, 0); + (void) account_pipe_buffers(pipe->user, pipe->ring_size, 0); free_uid(pipe->user); - for (i = 0; i < pipe->buffers; i++) { + for (i = 0; i < pipe->ring_size; i++) { struct pipe_buffer *buf = pipe->bufs + i; if (buf->ops) pipe_buf_release(pipe, buf); @@ -880,7 +897,7 @@ SYSCALL_DEFINE1(pipe, int __user *, fildes) static int wait_for_partner(struct pipe_inode_info *pipe, unsigned int *cnt) { - int cur = *cnt; + int cur = *cnt; while (cur == *cnt) { pipe_wait(pipe); @@ -955,7 +972,7 @@ static int fifo_open(struct inode *inode, struct file *filp) } } break; - + case FMODE_WRITE: /* * O_WRONLY @@ -975,7 +992,7 @@ static int fifo_open(struct inode *inode, struct file *filp) goto err_wr; } break; - + case FMODE_READ | FMODE_WRITE: /* * O_RDWR @@ -1054,14 +1071,14 @@ unsigned int round_pipe_size(unsigned long size) static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) { struct pipe_buffer *bufs; - unsigned int size, nr_pages; + unsigned int size, nr_slots, head, tail, mask, n; unsigned long user_bufs; long ret = 0; size = round_pipe_size(arg); - nr_pages = size >> PAGE_SHIFT; + nr_slots = size >> PAGE_SHIFT; - if (!nr_pages) + if (!nr_slots) return -EINVAL; /* @@ -1071,13 +1088,13 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) * Decreasing the pipe capacity is always permitted, even * if the user is currently over a limit. */ - if (nr_pages > pipe->buffers && + if (nr_slots > pipe->ring_size && size > pipe_max_size && !capable(CAP_SYS_RESOURCE)) return -EPERM; - user_bufs = account_pipe_buffers(pipe->user, pipe->buffers, nr_pages); + user_bufs = account_pipe_buffers(pipe->user, pipe->ring_size, nr_slots); - if (nr_pages > pipe->buffers && + if (nr_slots > pipe->ring_size && (too_many_pipe_buffers_hard(user_bufs) || too_many_pipe_buffers_soft(user_bufs)) && is_unprivileged_user()) { @@ -1086,17 +1103,21 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) } /* - * We can shrink the pipe, if arg >= pipe->nrbufs. Since we don't - * expect a lot of shrink+grow operations, just free and allocate - * again like we would do for growing. If the pipe currently + * We can shrink the pipe, if arg is greater than the ring occupancy. + * Since we don't expect a lot of shrink+grow operations, just free and + * allocate again like we would do for growing. If the pipe currently * contains more buffers than arg, then return busy. */ - if (nr_pages < pipe->nrbufs) { + mask = pipe->ring_size - 1; + head = pipe->head; + tail = pipe->tail; + n = pipe_occupancy(pipe->head, pipe->tail); + if (nr_slots < n) { ret = -EBUSY; goto out_revert_acct; } - bufs = kcalloc(nr_pages, sizeof(*bufs), + bufs = kcalloc(nr_slots, sizeof(*bufs), GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (unlikely(!bufs)) { ret = -ENOMEM; @@ -1105,33 +1126,36 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) /* * The pipe array wraps around, so just start the new one at zero - * and adjust the indexes. + * and adjust the indices. */ - if (pipe->nrbufs) { - unsigned int tail; - unsigned int head; - - tail = pipe->curbuf + pipe->nrbufs; - if (tail < pipe->buffers) - tail = 0; - else - tail &= (pipe->buffers - 1); - - head = pipe->nrbufs - tail; - if (head) - memcpy(bufs, pipe->bufs + pipe->curbuf, head * sizeof(struct pipe_buffer)); - if (tail) - memcpy(bufs + head, pipe->bufs, tail * sizeof(struct pipe_buffer)); + if (n > 0) { + unsigned int h = head & mask; + unsigned int t = tail & mask; + if (h > t) { + memcpy(bufs, pipe->bufs + t, + n * sizeof(struct pipe_buffer)); + } else { + unsigned int tsize = pipe->ring_size - t; + if (h > 0) + memcpy(bufs + tsize, pipe->bufs, + h * sizeof(struct pipe_buffer)); + memcpy(bufs, pipe->bufs + t, + tsize * sizeof(struct pipe_buffer)); + } } - pipe->curbuf = 0; + head = n; + tail = 0; + kfree(pipe->bufs); pipe->bufs = bufs; - pipe->buffers = nr_pages; - return nr_pages * PAGE_SIZE; + pipe->ring_size = nr_slots; + pipe->tail = tail; + pipe->head = head; + return pipe->ring_size * PAGE_SIZE; out_revert_acct: - (void) account_pipe_buffers(pipe->user, nr_pages, pipe->buffers); + (void) account_pipe_buffers(pipe->user, nr_slots, pipe->ring_size); return ret; } @@ -1161,7 +1185,7 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg) ret = pipe_set_size(pipe, arg); break; case F_GETPIPE_SZ: - ret = pipe->buffers * PAGE_SIZE; + ret = pipe->ring_size * PAGE_SIZE; break; default: ret = -EINVAL; diff --git a/fs/splice.c b/fs/splice.c index 98412721f056..22b0a47a35c0 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -185,6 +185,9 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) { unsigned int spd_pages = spd->nr_pages; + unsigned int tail = pipe->tail; + unsigned int head = pipe->head; + unsigned int mask = pipe->ring_size - 1; int ret = 0, page_nr = 0; if (!spd_pages) @@ -196,9 +199,8 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe, goto out; } - while (pipe->nrbufs < pipe->buffers) { - int newbuf = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1); - struct pipe_buffer *buf = pipe->bufs + newbuf; + while (!pipe_full(head, tail, pipe->ring_size)) { + struct pipe_buffer *buf = &pipe->bufs[head & mask]; buf->page = spd->pages[page_nr]; buf->offset = spd->partial[page_nr].offset; @@ -207,7 +209,8 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe, buf->ops = spd->ops; buf->flags = 0; - pipe->nrbufs++; + head++; + pipe->head = head; page_nr++; ret += buf->len; @@ -228,17 +231,19 @@ EXPORT_SYMBOL_GPL(splice_to_pipe); ssize_t add_to_pipe(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { + unsigned int head = pipe->head; + unsigned int tail = pipe->tail; + unsigned int mask = pipe->ring_size - 1; int ret; if (unlikely(!pipe->readers)) { send_sig(SIGPIPE, current, 0); ret = -EPIPE; - } else if (pipe->nrbufs == pipe->buffers) { + } else if (pipe_full(head, tail, pipe->ring_size)) { ret = -EAGAIN; } else { - int newbuf = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1); - pipe->bufs[newbuf] = *buf; - pipe->nrbufs++; + pipe->bufs[head & mask] = *buf; + pipe->head = head + 1; return buf->len; } pipe_buf_release(pipe, buf); @@ -252,14 +257,14 @@ EXPORT_SYMBOL(add_to_pipe); */ int splice_grow_spd(const struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) { - unsigned int buffers = READ_ONCE(pipe->buffers); + unsigned int max_usage = READ_ONCE(pipe->ring_size); - spd->nr_pages_max = buffers; - if (buffers <= PIPE_DEF_BUFFERS) + spd->nr_pages_max = max_usage; + if (max_usage <= PIPE_DEF_BUFFERS) return 0; - spd->pages = kmalloc_array(buffers, sizeof(struct page *), GFP_KERNEL); - spd->partial = kmalloc_array(buffers, sizeof(struct partial_page), + spd->pages = kmalloc_array(max_usage, sizeof(struct page *), GFP_KERNEL); + spd->partial = kmalloc_array(max_usage, sizeof(struct partial_page), GFP_KERNEL); if (spd->pages && spd->partial) @@ -298,10 +303,11 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos, { struct iov_iter to; struct kiocb kiocb; - int idx, ret; + unsigned int i_head; + int ret; iov_iter_pipe(&to, READ, pipe, len); - idx = to.idx; + i_head = to.head; init_sync_kiocb(&kiocb, in); kiocb.ki_pos = *ppos; ret = call_read_iter(in, &kiocb, &to); @@ -309,7 +315,7 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos, *ppos = kiocb.ki_pos; file_accessed(in); } else if (ret < 0) { - to.idx = idx; + to.head = i_head; to.iov_offset = 0; iov_iter_advance(&to, 0); /* to free what was emitted */ /* @@ -370,11 +376,12 @@ static ssize_t default_file_splice_read(struct file *in, loff_t *ppos, struct iov_iter to; struct page **pages; unsigned int nr_pages; + unsigned int mask; size_t offset, base, copied = 0; ssize_t res; int i; - if (pipe->nrbufs == pipe->buffers) + if (pipe_full(pipe->head, pipe->tail, pipe->ring_size)) return -EAGAIN; /* @@ -400,8 +407,9 @@ static ssize_t default_file_splice_read(struct file *in, loff_t *ppos, } } - pipe->bufs[to.idx].offset = offset; - pipe->bufs[to.idx].len -= offset; + mask = pipe->ring_size - 1; + pipe->bufs[to.head & mask].offset = offset; + pipe->bufs[to.head & mask].len -= offset; for (i = 0; i < nr_pages; i++) { size_t this_len = min_t(size_t, len, PAGE_SIZE - offset); @@ -443,7 +451,8 @@ static int pipe_to_sendpage(struct pipe_inode_info *pipe, more = (sd->flags & SPLICE_F_MORE) ? MSG_MORE : 0; - if (sd->len < sd->total_len && pipe->nrbufs > 1) + if (sd->len < sd->total_len && + pipe_occupancy(pipe->head, pipe->tail) > 1) more |= MSG_SENDPAGE_NOTLAST; return file->f_op->sendpage(file, buf->page, buf->offset, @@ -481,10 +490,13 @@ static void wakeup_pipe_writers(struct pipe_inode_info *pipe) static int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_desc *sd, splice_actor *actor) { + unsigned int head = pipe->head; + unsigned int tail = pipe->tail; + unsigned int mask = pipe->ring_size - 1; int ret; - while (pipe->nrbufs) { - struct pipe_buffer *buf = pipe->bufs + pipe->curbuf; + while (!pipe_empty(tail, head)) { + struct pipe_buffer *buf = &pipe->bufs[tail & mask]; sd->len = buf->len; if (sd->len > sd->total_len) @@ -511,8 +523,8 @@ static int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_des if (!buf->len) { pipe_buf_release(pipe, buf); - pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1); - pipe->nrbufs--; + tail++; + pipe->tail = tail; if (pipe->files) sd->need_wakeup = true; } @@ -543,7 +555,7 @@ static int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_des if (signal_pending(current)) return -ERESTARTSYS; - while (!pipe->nrbufs) { + while (pipe_empty(pipe->head, pipe->tail)) { if (!pipe->writers) return 0; @@ -686,7 +698,7 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, .pos = *ppos, .u.file = out, }; - int nbufs = pipe->buffers; + int nbufs = pipe->ring_size; struct bio_vec *array = kcalloc(nbufs, sizeof(struct bio_vec), GFP_KERNEL); ssize_t ret; @@ -699,16 +711,19 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, splice_from_pipe_begin(&sd); while (sd.total_len) { struct iov_iter from; + unsigned int head = pipe->head; + unsigned int tail = pipe->tail; + unsigned int mask = pipe->ring_size - 1; size_t left; - int n, idx; + int n; ret = splice_from_pipe_next(pipe, &sd); if (ret <= 0) break; - if (unlikely(nbufs < pipe->buffers)) { + if (unlikely(nbufs < pipe->ring_size)) { kfree(array); - nbufs = pipe->buffers; + nbufs = pipe->ring_size; array = kcalloc(nbufs, sizeof(struct bio_vec), GFP_KERNEL); if (!array) { @@ -719,16 +734,13 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, /* build the vector */ left = sd.total_len; - for (n = 0, idx = pipe->curbuf; left && n < pipe->nrbufs; n++, idx++) { - struct pipe_buffer *buf = pipe->bufs + idx; + for (n = 0; !pipe_empty(head, tail) && left && n < nbufs; tail++, n++) { + struct pipe_buffer *buf = &pipe->bufs[tail & mask]; size_t this_len = buf->len; if (this_len > left) this_len = left; - if (idx == pipe->buffers - 1) - idx = -1; - ret = pipe_buf_confirm(pipe, buf); if (unlikely(ret)) { if (ret == -ENODATA) @@ -752,14 +764,15 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, *ppos = sd.pos; /* dismiss the fully eaten buffers, adjust the partial one */ + tail = pipe->tail; while (ret) { - struct pipe_buffer *buf = pipe->bufs + pipe->curbuf; + struct pipe_buffer *buf = &pipe->bufs[tail & mask]; if (ret >= buf->len) { ret -= buf->len; buf->len = 0; pipe_buf_release(pipe, buf); - pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1); - pipe->nrbufs--; + tail++; + pipe->tail = tail; if (pipe->files) sd.need_wakeup = true; } else { @@ -942,15 +955,17 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd, sd->flags &= ~SPLICE_F_NONBLOCK; more = sd->flags & SPLICE_F_MORE; - WARN_ON_ONCE(pipe->nrbufs != 0); + WARN_ON_ONCE(!pipe_empty(pipe->head, pipe->tail)); while (len) { + unsigned int p_space; size_t read_len; loff_t pos = sd->pos, prev_pos = pos; /* Don't try to read more the pipe has space for. */ - read_len = min_t(size_t, len, - (pipe->buffers - pipe->nrbufs) << PAGE_SHIFT); + p_space = pipe->ring_size - + pipe_occupancy(pipe->head, pipe->tail); + read_len = min_t(size_t, len, p_space << PAGE_SHIFT); ret = do_splice_to(in, &pos, pipe, read_len, flags); if (unlikely(ret <= 0)) goto out_release; @@ -989,7 +1004,7 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd, } done: - pipe->nrbufs = pipe->curbuf = 0; + pipe->tail = pipe->head = 0; file_accessed(in); return bytes; @@ -998,8 +1013,8 @@ out_release: * If we did an incomplete transfer we must release * the pipe buffers in question: */ - for (i = 0; i < pipe->buffers; i++) { - struct pipe_buffer *buf = pipe->bufs + i; + for (i = 0; i < pipe->ring_size; i++) { + struct pipe_buffer *buf = &pipe->bufs[i]; if (buf->ops) pipe_buf_release(pipe, buf); @@ -1075,7 +1090,7 @@ static int wait_for_space(struct pipe_inode_info *pipe, unsigned flags) send_sig(SIGPIPE, current, 0); return -EPIPE; } - if (pipe->nrbufs != pipe->buffers) + if (!pipe_full(pipe->head, pipe->tail, pipe->ring_size)) return 0; if (flags & SPLICE_F_NONBLOCK) return -EAGAIN; @@ -1442,16 +1457,16 @@ static int ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags) int ret; /* - * Check ->nrbufs without the inode lock first. This function + * Check the pipe occupancy without the inode lock first. This function * is speculative anyways, so missing one is ok. */ - if (pipe->nrbufs) + if (!pipe_empty(pipe->head, pipe->tail)) return 0; ret = 0; pipe_lock(pipe); - while (!pipe->nrbufs) { + while (pipe_empty(pipe->head, pipe->tail)) { if (signal_pending(current)) { ret = -ERESTARTSYS; break; @@ -1480,16 +1495,16 @@ static int opipe_prep(struct pipe_inode_info *pipe, unsigned int flags) int ret; /* - * Check ->nrbufs without the inode lock first. This function + * Check pipe occupancy without the inode lock first. This function * is speculative anyways, so missing one is ok. */ - if (pipe->nrbufs < pipe->buffers) + if (pipe_full(pipe->head, pipe->tail, pipe->ring_size)) return 0; ret = 0; pipe_lock(pipe); - while (pipe->nrbufs >= pipe->buffers) { + while (pipe_full(pipe->head, pipe->tail, pipe->ring_size)) { if (!pipe->readers) { send_sig(SIGPIPE, current, 0); ret = -EPIPE; @@ -1520,7 +1535,10 @@ static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe, size_t len, unsigned int flags) { struct pipe_buffer *ibuf, *obuf; - int ret = 0, nbuf; + unsigned int i_head, o_head; + unsigned int i_tail, o_tail; + unsigned int i_mask, o_mask; + int ret = 0; bool input_wakeup = false; @@ -1540,7 +1558,14 @@ retry: */ pipe_double_lock(ipipe, opipe); + i_tail = ipipe->tail; + i_mask = ipipe->ring_size - 1; + o_head = opipe->head; + o_mask = opipe->ring_size - 1; + do { + size_t o_len; + if (!opipe->readers) { send_sig(SIGPIPE, current, 0); if (!ret) @@ -1548,14 +1573,18 @@ retry: break; } - if (!ipipe->nrbufs && !ipipe->writers) + i_head = ipipe->head; + o_tail = opipe->tail; + + if (pipe_empty(i_head, i_tail) && !ipipe->writers) break; /* * Cannot make any progress, because either the input * pipe is empty or the output pipe is full. */ - if (!ipipe->nrbufs || opipe->nrbufs >= opipe->buffers) { + if (pipe_empty(i_head, i_tail) || + pipe_full(o_head, o_tail, opipe->ring_size)) { /* Already processed some buffers, break */ if (ret) break; @@ -1575,9 +1604,8 @@ retry: goto retry; } - ibuf = ipipe->bufs + ipipe->curbuf; - nbuf = (opipe->curbuf + opipe->nrbufs) & (opipe->buffers - 1); - obuf = opipe->bufs + nbuf; + ibuf = &ipipe->bufs[i_tail & i_mask]; + obuf = &opipe->bufs[o_head & o_mask]; if (len >= ibuf->len) { /* @@ -1585,10 +1613,12 @@ retry: */ *obuf = *ibuf; ibuf->ops = NULL; - opipe->nrbufs++; - ipipe->curbuf = (ipipe->curbuf + 1) & (ipipe->buffers - 1); - ipipe->nrbufs--; + i_tail++; + ipipe->tail = i_tail; input_wakeup = true; + o_len = obuf->len; + o_head++; + opipe->head = o_head; } else { /* * Get a reference to this pipe buffer, @@ -1610,12 +1640,14 @@ retry: pipe_buf_mark_unmergeable(obuf); obuf->len = len; - opipe->nrbufs++; - ibuf->offset += obuf->len; - ibuf->len -= obuf->len; + ibuf->offset += len; + ibuf->len -= len; + o_len = len; + o_head++; + opipe->head = o_head; } - ret += obuf->len; - len -= obuf->len; + ret += o_len; + len -= o_len; } while (len); pipe_unlock(ipipe); @@ -1641,7 +1673,10 @@ static int link_pipe(struct pipe_inode_info *ipipe, size_t len, unsigned int flags) { struct pipe_buffer *ibuf, *obuf; - int ret = 0, i = 0, nbuf; + unsigned int i_head, o_head; + unsigned int i_tail, o_tail; + unsigned int i_mask, o_mask; + int ret = 0; /* * Potential ABBA deadlock, work around it by ordering lock @@ -1650,6 +1685,11 @@ static int link_pipe(struct pipe_inode_info *ipipe, */ pipe_double_lock(ipipe, opipe); + i_tail = ipipe->tail; + i_mask = ipipe->ring_size - 1; + o_head = opipe->head; + o_mask = opipe->ring_size - 1; + do { if (!opipe->readers) { send_sig(SIGPIPE, current, 0); @@ -1658,15 +1698,19 @@ static int link_pipe(struct pipe_inode_info *ipipe, break; } + i_head = ipipe->head; + o_tail = opipe->tail; + /* - * If we have iterated all input buffers or ran out of + * If we have iterated all input buffers or run out of * output room, break. */ - if (i >= ipipe->nrbufs || opipe->nrbufs >= opipe->buffers) + if (pipe_empty(i_head, i_tail) || + pipe_full(o_head, o_tail, opipe->ring_size)) break; - ibuf = ipipe->bufs + ((ipipe->curbuf + i) & (ipipe->buffers-1)); - nbuf = (opipe->curbuf + opipe->nrbufs) & (opipe->buffers - 1); + ibuf = &ipipe->bufs[i_tail & i_mask]; + obuf = &opipe->bufs[o_head & o_mask]; /* * Get a reference to this pipe buffer, @@ -1678,7 +1722,6 @@ static int link_pipe(struct pipe_inode_info *ipipe, break; } - obuf = opipe->bufs + nbuf; *obuf = *ibuf; /* @@ -1691,11 +1734,12 @@ static int link_pipe(struct pipe_inode_info *ipipe, if (obuf->len > len) obuf->len = len; - - opipe->nrbufs++; ret += obuf->len; len -= obuf->len; - i++; + + o_head++; + opipe->head = o_head; + i_tail++; } while (len); /* diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 5c626fdc10db..96158ca80456 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -30,9 +30,9 @@ struct pipe_buffer { * struct pipe_inode_info - a linux kernel pipe * @mutex: mutex protecting the whole thing * @wait: reader/writer wait point in case of empty/full pipe - * @nrbufs: the number of non-empty pipe buffers in this pipe - * @buffers: total number of buffers (should be a power of 2) - * @curbuf: the current pipe buffer entry + * @head: The point of buffer production + * @tail: The point of buffer consumption + * @ring_size: total number of buffers (should be a power of 2) * @tmp_page: cached released page * @readers: number of current readers of this pipe * @writers: number of current writers of this pipe @@ -48,7 +48,9 @@ struct pipe_buffer { struct pipe_inode_info { struct mutex mutex; wait_queue_head_t wait; - unsigned int nrbufs, curbuf, buffers; + unsigned int head; + unsigned int tail; + unsigned int ring_size; unsigned int readers; unsigned int writers; unsigned int files; @@ -104,6 +106,56 @@ struct pipe_buf_operations { bool (*get)(struct pipe_inode_info *, struct pipe_buffer *); }; +/** + * pipe_empty - Return true if the pipe is empty + * @head: The pipe ring head pointer + * @tail: The pipe ring tail pointer + */ +static inline bool pipe_empty(unsigned int head, unsigned int tail) +{ + return head == tail; +} + +/** + * pipe_occupancy - Return number of slots used in the pipe + * @head: The pipe ring head pointer + * @tail: The pipe ring tail pointer + */ +static inline unsigned int pipe_occupancy(unsigned int head, unsigned int tail) +{ + return head - tail; +} + +/** + * pipe_full - Return true if the pipe is full + * @head: The pipe ring head pointer + * @tail: The pipe ring tail pointer + * @limit: The maximum amount of slots available. + */ +static inline bool pipe_full(unsigned int head, unsigned int tail, + unsigned int limit) +{ + return pipe_occupancy(head, tail) >= limit; +} + +/** + * pipe_space_for_user - Return number of slots available to userspace + * @head: The pipe ring head pointer + * @tail: The pipe ring tail pointer + * @pipe: The pipe info structure + */ +static inline unsigned int pipe_space_for_user(unsigned int head, unsigned int tail, + struct pipe_inode_info *pipe) +{ + unsigned int p_occupancy, p_space; + + p_occupancy = pipe_occupancy(head, tail); + if (p_occupancy >= pipe->ring_size) + return 0; + p_space = pipe->ring_size - p_occupancy; + return p_space; +} + /** * pipe_buf_get - get a reference to a pipe_buffer * @pipe: the pipe that the buffer belongs to diff --git a/include/linux/uio.h b/include/linux/uio.h index ab5f523bc0df..9576fd8158d7 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -45,8 +45,8 @@ struct iov_iter { union { unsigned long nr_segs; struct { - int idx; - int start_idx; + unsigned int head; + unsigned int start_head; }; }; }; diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 639d5e7014c1..957f8828378a 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -325,28 +325,33 @@ done: static bool sanity(const struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; - int idx = i->idx; - int next = pipe->curbuf + pipe->nrbufs; + unsigned int p_head = pipe->head; + unsigned int p_tail = pipe->tail; + unsigned int p_mask = pipe->ring_size - 1; + unsigned int p_occupancy = pipe_occupancy(p_head, p_tail); + unsigned int i_head = i->head; + unsigned int idx; + if (i->iov_offset) { struct pipe_buffer *p; - if (unlikely(!pipe->nrbufs)) + if (unlikely(p_occupancy == 0)) goto Bad; // pipe must be non-empty - if (unlikely(idx != ((next - 1) & (pipe->buffers - 1)))) + if (unlikely(i_head != p_head - 1)) goto Bad; // must be at the last buffer... - p = &pipe->bufs[idx]; + p = &pipe->bufs[i_head & p_mask]; if (unlikely(p->offset + p->len != i->iov_offset)) goto Bad; // ... at the end of segment } else { - if (idx != (next & (pipe->buffers - 1))) + if (i_head != p_head) goto Bad; // must be right after the last buffer } return true; Bad: - printk(KERN_ERR "idx = %d, offset = %zd\n", i->idx, i->iov_offset); - printk(KERN_ERR "curbuf = %d, nrbufs = %d, buffers = %d\n", - pipe->curbuf, pipe->nrbufs, pipe->buffers); - for (idx = 0; idx < pipe->buffers; idx++) + printk(KERN_ERR "idx = %d, offset = %zd\n", i_head, i->iov_offset); + printk(KERN_ERR "head = %d, tail = %d, buffers = %d\n", + p_head, p_tail, pipe->ring_size); + for (idx = 0; idx < pipe->ring_size; idx++) printk(KERN_ERR "[%p %p %d %d]\n", pipe->bufs[idx].ops, pipe->bufs[idx].page, @@ -359,18 +364,15 @@ Bad: #define sanity(i) true #endif -static inline int next_idx(int idx, struct pipe_inode_info *pipe) -{ - return (idx + 1) & (pipe->buffers - 1); -} - static size_t copy_page_to_iter_pipe(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; struct pipe_buffer *buf; + unsigned int p_tail = pipe->tail; + unsigned int p_mask = pipe->ring_size - 1; + unsigned int i_head = i->head; size_t off; - int idx; if (unlikely(bytes > i->count)) bytes = i->count; @@ -382,8 +384,7 @@ static size_t copy_page_to_iter_pipe(struct page *page, size_t offset, size_t by return 0; off = i->iov_offset; - idx = i->idx; - buf = &pipe->bufs[idx]; + buf = &pipe->bufs[i_head & p_mask]; if (off) { if (offset == off && buf->page == page) { /* merge with the last one */ @@ -391,18 +392,21 @@ static size_t copy_page_to_iter_pipe(struct page *page, size_t offset, size_t by i->iov_offset += bytes; goto out; } - idx = next_idx(idx, pipe); - buf = &pipe->bufs[idx]; + i_head++; + buf = &pipe->bufs[i_head & p_mask]; } - if (idx == pipe->curbuf && pipe->nrbufs) + if (pipe_full(i_head, p_tail, pipe->ring_size)) return 0; - pipe->nrbufs++; + buf->ops = &page_cache_pipe_buf_ops; - get_page(buf->page = page); + get_page(page); + buf->page = page; buf->offset = offset; buf->len = bytes; + + pipe->head = i_head + 1; i->iov_offset = offset + bytes; - i->idx = idx; + i->head = i_head; out: i->count -= bytes; return bytes; @@ -480,24 +484,30 @@ static inline bool allocated(struct pipe_buffer *buf) return buf->ops == &default_pipe_buf_ops; } -static inline void data_start(const struct iov_iter *i, int *idxp, size_t *offp) +static inline void data_start(const struct iov_iter *i, + unsigned int *iter_headp, size_t *offp) { + unsigned int p_mask = i->pipe->ring_size - 1; + unsigned int iter_head = i->head; size_t off = i->iov_offset; - int idx = i->idx; - if (off && (!allocated(&i->pipe->bufs[idx]) || off == PAGE_SIZE)) { - idx = next_idx(idx, i->pipe); + + if (off && (!allocated(&i->pipe->bufs[iter_head & p_mask]) || + off == PAGE_SIZE)) { + iter_head++; off = 0; } - *idxp = idx; + *iter_headp = iter_head; *offp = off; } static size_t push_pipe(struct iov_iter *i, size_t size, - int *idxp, size_t *offp) + int *iter_headp, size_t *offp) { struct pipe_inode_info *pipe = i->pipe; + unsigned int p_tail = pipe->tail; + unsigned int p_mask = pipe->ring_size - 1; + unsigned int iter_head; size_t off; - int idx; ssize_t left; if (unlikely(size > i->count)) @@ -506,33 +516,34 @@ static size_t push_pipe(struct iov_iter *i, size_t size, return 0; left = size; - data_start(i, &idx, &off); - *idxp = idx; + data_start(i, &iter_head, &off); + *iter_headp = iter_head; *offp = off; if (off) { left -= PAGE_SIZE - off; if (left <= 0) { - pipe->bufs[idx].len += size; + pipe->bufs[iter_head & p_mask].len += size; return size; } - pipe->bufs[idx].len = PAGE_SIZE; - idx = next_idx(idx, pipe); + pipe->bufs[iter_head & p_mask].len = PAGE_SIZE; + iter_head++; } - while (idx != pipe->curbuf || !pipe->nrbufs) { + while (!pipe_full(iter_head, p_tail, pipe->ring_size)) { + struct pipe_buffer *buf = &pipe->bufs[iter_head & p_mask]; struct page *page = alloc_page(GFP_USER); if (!page) break; - pipe->nrbufs++; - pipe->bufs[idx].ops = &default_pipe_buf_ops; - pipe->bufs[idx].page = page; - pipe->bufs[idx].offset = 0; - if (left <= PAGE_SIZE) { - pipe->bufs[idx].len = left; + + buf->ops = &default_pipe_buf_ops; + buf->page = page; + buf->offset = 0; + buf->len = min_t(ssize_t, left, PAGE_SIZE); + left -= buf->len; + iter_head++; + pipe->head = iter_head; + + if (left == 0) return size; - } - pipe->bufs[idx].len = PAGE_SIZE; - left -= PAGE_SIZE; - idx = next_idx(idx, pipe); } return size - left; } @@ -541,23 +552,26 @@ static size_t copy_pipe_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; + unsigned int p_mask = pipe->ring_size - 1; + unsigned int i_head; size_t n, off; - int idx; if (!sanity(i)) return 0; - bytes = n = push_pipe(i, bytes, &idx, &off); + bytes = n = push_pipe(i, bytes, &i_head, &off); if (unlikely(!n)) return 0; - for ( ; n; idx = next_idx(idx, pipe), off = 0) { + do { size_t chunk = min_t(size_t, n, PAGE_SIZE - off); - memcpy_to_page(pipe->bufs[idx].page, off, addr, chunk); - i->idx = idx; + memcpy_to_page(pipe->bufs[i_head & p_mask].page, off, addr, chunk); + i->head = i_head; i->iov_offset = off + chunk; n -= chunk; addr += chunk; - } + off = 0; + i_head++; + } while (n); i->count -= bytes; return bytes; } @@ -573,28 +587,31 @@ static size_t csum_and_copy_to_pipe_iter(const void *addr, size_t bytes, __wsum *csum, struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; + unsigned int p_mask = pipe->ring_size - 1; + unsigned int i_head; size_t n, r; size_t off = 0; __wsum sum = *csum; - int idx; if (!sanity(i)) return 0; - bytes = n = push_pipe(i, bytes, &idx, &r); + bytes = n = push_pipe(i, bytes, &i_head, &r); if (unlikely(!n)) return 0; - for ( ; n; idx = next_idx(idx, pipe), r = 0) { + do { size_t chunk = min_t(size_t, n, PAGE_SIZE - r); - char *p = kmap_atomic(pipe->bufs[idx].page); + char *p = kmap_atomic(pipe->bufs[i_head & p_mask].page); sum = csum_and_memcpy(p + r, addr, chunk, sum, off); kunmap_atomic(p); - i->idx = idx; + i->head = i_head; i->iov_offset = r + chunk; n -= chunk; off += chunk; addr += chunk; - } + r = 0; + i_head++; + } while (n); i->count -= bytes; *csum = sum; return bytes; @@ -645,29 +662,32 @@ static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; + unsigned int p_mask = pipe->ring_size - 1; + unsigned int i_head; size_t n, off, xfer = 0; - int idx; if (!sanity(i)) return 0; - bytes = n = push_pipe(i, bytes, &idx, &off); + bytes = n = push_pipe(i, bytes, &i_head, &off); if (unlikely(!n)) return 0; - for ( ; n; idx = next_idx(idx, pipe), off = 0) { + do { size_t chunk = min_t(size_t, n, PAGE_SIZE - off); unsigned long rem; - rem = memcpy_mcsafe_to_page(pipe->bufs[idx].page, off, addr, - chunk); - i->idx = idx; + rem = memcpy_mcsafe_to_page(pipe->bufs[i_head & p_mask].page, + off, addr, chunk); + i->head = i_head; i->iov_offset = off + chunk - rem; xfer += chunk - rem; if (rem) break; n -= chunk; addr += chunk; - } + off = 0; + i_head++; + } while (n); i->count -= xfer; return xfer; } @@ -925,23 +945,26 @@ EXPORT_SYMBOL(copy_page_from_iter); static size_t pipe_zero(size_t bytes, struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; + unsigned int p_mask = pipe->ring_size - 1; + unsigned int i_head; size_t n, off; - int idx; if (!sanity(i)) return 0; - bytes = n = push_pipe(i, bytes, &idx, &off); + bytes = n = push_pipe(i, bytes, &i_head, &off); if (unlikely(!n)) return 0; - for ( ; n; idx = next_idx(idx, pipe), off = 0) { + do { size_t chunk = min_t(size_t, n, PAGE_SIZE - off); - memzero_page(pipe->bufs[idx].page, off, chunk); - i->idx = idx; + memzero_page(pipe->bufs[i_head & p_mask].page, off, chunk); + i->head = i_head; i->iov_offset = off + chunk; n -= chunk; - } + off = 0; + i_head++; + } while (n); i->count -= bytes; return bytes; } @@ -987,20 +1010,26 @@ EXPORT_SYMBOL(iov_iter_copy_from_user_atomic); static inline void pipe_truncate(struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; - if (pipe->nrbufs) { + unsigned int p_tail = pipe->tail; + unsigned int p_head = pipe->head; + unsigned int p_mask = pipe->ring_size - 1; + + if (!pipe_empty(p_head, p_tail)) { + struct pipe_buffer *buf; + unsigned int i_head = i->head; size_t off = i->iov_offset; - int idx = i->idx; - int nrbufs = (idx - pipe->curbuf) & (pipe->buffers - 1); + if (off) { - pipe->bufs[idx].len = off - pipe->bufs[idx].offset; - idx = next_idx(idx, pipe); - nrbufs++; + buf = &pipe->bufs[i_head & p_mask]; + buf->len = off - buf->offset; + i_head++; } - while (pipe->nrbufs > nrbufs) { - pipe_buf_release(pipe, &pipe->bufs[idx]); - idx = next_idx(idx, pipe); - pipe->nrbufs--; + while (p_head != i_head) { + p_head--; + pipe_buf_release(pipe, &pipe->bufs[p_head & p_mask]); } + + pipe->head = p_head; } } @@ -1011,18 +1040,20 @@ static void pipe_advance(struct iov_iter *i, size_t size) size = i->count; if (size) { struct pipe_buffer *buf; + unsigned int p_mask = pipe->ring_size - 1; + unsigned int i_head = i->head; size_t off = i->iov_offset, left = size; - int idx = i->idx; + if (off) /* make it relative to the beginning of buffer */ - left += off - pipe->bufs[idx].offset; + left += off - pipe->bufs[i_head & p_mask].offset; while (1) { - buf = &pipe->bufs[idx]; + buf = &pipe->bufs[i_head & p_mask]; if (left <= buf->len) break; left -= buf->len; - idx = next_idx(idx, pipe); + i_head++; } - i->idx = idx; + i->head = i_head; i->iov_offset = buf->offset + left; } i->count -= size; @@ -1053,25 +1084,27 @@ void iov_iter_revert(struct iov_iter *i, size_t unroll) i->count += unroll; if (unlikely(iov_iter_is_pipe(i))) { struct pipe_inode_info *pipe = i->pipe; - int idx = i->idx; + unsigned int p_mask = pipe->ring_size - 1; + unsigned int i_head = i->head; size_t off = i->iov_offset; while (1) { - size_t n = off - pipe->bufs[idx].offset; + struct pipe_buffer *b = &pipe->bufs[i_head & p_mask]; + size_t n = off - b->offset; if (unroll < n) { off -= unroll; break; } unroll -= n; - if (!unroll && idx == i->start_idx) { + if (!unroll && i_head == i->start_head) { off = 0; break; } - if (!idx--) - idx = pipe->buffers - 1; - off = pipe->bufs[idx].offset + pipe->bufs[idx].len; + i_head--; + b = &pipe->bufs[i_head & p_mask]; + off = b->offset + b->len; } i->iov_offset = off; - i->idx = idx; + i->head = i_head; pipe_truncate(i); return; } @@ -1159,13 +1192,13 @@ void iov_iter_pipe(struct iov_iter *i, unsigned int direction, size_t count) { BUG_ON(direction != READ); - WARN_ON(pipe->nrbufs == pipe->buffers); + WARN_ON(pipe_full(pipe->head, pipe->tail, pipe->ring_size)); i->type = ITER_PIPE | READ; i->pipe = pipe; - i->idx = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1); + i->head = pipe->head; i->iov_offset = 0; i->count = count; - i->start_idx = i->idx; + i->start_head = i->head; } EXPORT_SYMBOL(iov_iter_pipe); @@ -1189,11 +1222,12 @@ EXPORT_SYMBOL(iov_iter_discard); unsigned long iov_iter_alignment(const struct iov_iter *i) { + unsigned int p_mask = i->pipe->ring_size - 1; unsigned long res = 0; size_t size = i->count; if (unlikely(iov_iter_is_pipe(i))) { - if (size && i->iov_offset && allocated(&i->pipe->bufs[i->idx])) + if (size && i->iov_offset && allocated(&i->pipe->bufs[i->head & p_mask])) return size | i->iov_offset; return size; } @@ -1231,19 +1265,20 @@ EXPORT_SYMBOL(iov_iter_gap_alignment); static inline ssize_t __pipe_get_pages(struct iov_iter *i, size_t maxsize, struct page **pages, - int idx, + int iter_head, size_t *start) { struct pipe_inode_info *pipe = i->pipe; - ssize_t n = push_pipe(i, maxsize, &idx, start); + unsigned int p_mask = pipe->ring_size - 1; + ssize_t n = push_pipe(i, maxsize, &iter_head, start); if (!n) return -EFAULT; maxsize = n; n += *start; while (n > 0) { - get_page(*pages++ = pipe->bufs[idx].page); - idx = next_idx(idx, pipe); + get_page(*pages++ = pipe->bufs[iter_head & p_mask].page); + iter_head++; n -= PAGE_SIZE; } @@ -1254,9 +1289,8 @@ static ssize_t pipe_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start) { - unsigned npages; + unsigned int iter_head, npages; size_t capacity; - int idx; if (!maxsize) return 0; @@ -1264,12 +1298,12 @@ static ssize_t pipe_get_pages(struct iov_iter *i, if (!sanity(i)) return -EFAULT; - data_start(i, &idx, start); - /* some of this one + all after this one */ - npages = ((i->pipe->curbuf - idx - 1) & (i->pipe->buffers - 1)) + 1; - capacity = min(npages,maxpages) * PAGE_SIZE - *start; + data_start(i, &iter_head, start); + /* Amount of free space: some of this one + all after this one */ + npages = pipe_space_for_user(iter_head, i->pipe->tail, i->pipe); + capacity = min(npages, maxpages) * PAGE_SIZE - *start; - return __pipe_get_pages(i, min(maxsize, capacity), pages, idx, start); + return __pipe_get_pages(i, min(maxsize, capacity), pages, iter_head, start); } ssize_t iov_iter_get_pages(struct iov_iter *i, @@ -1323,9 +1357,8 @@ static ssize_t pipe_get_pages_alloc(struct iov_iter *i, size_t *start) { struct page **p; + unsigned int iter_head, npages; ssize_t n; - int idx; - int npages; if (!maxsize) return 0; @@ -1333,9 +1366,9 @@ static ssize_t pipe_get_pages_alloc(struct iov_iter *i, if (!sanity(i)) return -EFAULT; - data_start(i, &idx, start); - /* some of this one + all after this one */ - npages = ((i->pipe->curbuf - idx - 1) & (i->pipe->buffers - 1)) + 1; + data_start(i, &iter_head, start); + /* Amount of free space: some of this one + all after this one */ + npages = pipe_space_for_user(iter_head, i->pipe->tail, i->pipe); n = npages * PAGE_SIZE - *start; if (maxsize > n) maxsize = n; @@ -1344,7 +1377,7 @@ static ssize_t pipe_get_pages_alloc(struct iov_iter *i, p = get_pages_array(npages); if (!p) return -ENOMEM; - n = __pipe_get_pages(i, maxsize, p, idx, start); + n = __pipe_get_pages(i, maxsize, p, iter_head, start); if (n > 0) *pages = p; else @@ -1560,15 +1593,15 @@ int iov_iter_npages(const struct iov_iter *i, int maxpages) if (unlikely(iov_iter_is_pipe(i))) { struct pipe_inode_info *pipe = i->pipe; + unsigned int iter_head; size_t off; - int idx; if (!sanity(i)) return 0; - data_start(i, &idx, &off); + data_start(i, &iter_head, &off); /* some of this one + all after this one */ - npages = ((pipe->curbuf - idx - 1) & (pipe->buffers - 1)) + 1; + npages = pipe_space_for_user(iter_head, pipe->tail, pipe); if (npages >= maxpages) return maxpages; } else iterate_all_kinds(i, size, v, ({ -- cgit v1.2.3-71-gd317 From 246880958ac93989c97c73ae1e60b78b4c4c88c5 Mon Sep 17 00:00:00 2001 From: Vikas Gupta Date: Thu, 31 Oct 2019 15:38:50 +0530 Subject: firmware: broadcom: add OP-TEE based BNXT f/w manager This driver registers on TEE bus to interact with OP-TEE based BNXT firmware management modules Cc: Jakub Kicinski Reported-by: kbuild test robot Signed-off-by: Vikas Gupta Signed-off-by: Sheetal Tigadoli Signed-off-by: David S. Miller --- drivers/firmware/broadcom/Kconfig | 8 + drivers/firmware/broadcom/Makefile | 1 + drivers/firmware/broadcom/tee_bnxt_fw.c | 279 ++++++++++++++++++++++++++ include/linux/firmware/broadcom/tee_bnxt_fw.h | 14 ++ 4 files changed, 302 insertions(+) create mode 100644 drivers/firmware/broadcom/tee_bnxt_fw.c create mode 100644 include/linux/firmware/broadcom/tee_bnxt_fw.h (limited to 'include/linux') diff --git a/drivers/firmware/broadcom/Kconfig b/drivers/firmware/broadcom/Kconfig index d03ed8e43ad7..8e3d355a637a 100644 --- a/drivers/firmware/broadcom/Kconfig +++ b/drivers/firmware/broadcom/Kconfig @@ -22,3 +22,11 @@ config BCM47XX_SPROM In case of SoC devices SPROM content is stored on a flash used by bootloader firmware CFE. This driver provides method to ssb and bcma drivers to read SPROM on SoC. + +config TEE_BNXT_FW + tristate "Broadcom BNXT firmware manager" + depends on (ARCH_BCM_IPROC && OPTEE) || (COMPILE_TEST && TEE) + default ARCH_BCM_IPROC + help + This module help to manage firmware on Broadcom BNXT device. The module + registers on tee bus and invoke calls to manage firmware on BNXT device. diff --git a/drivers/firmware/broadcom/Makefile b/drivers/firmware/broadcom/Makefile index 72c7fdc20c77..17c5061c47a7 100644 --- a/drivers/firmware/broadcom/Makefile +++ b/drivers/firmware/broadcom/Makefile @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_BCM47XX_NVRAM) += bcm47xx_nvram.o obj-$(CONFIG_BCM47XX_SPROM) += bcm47xx_sprom.o +obj-$(CONFIG_TEE_BNXT_FW) += tee_bnxt_fw.o diff --git a/drivers/firmware/broadcom/tee_bnxt_fw.c b/drivers/firmware/broadcom/tee_bnxt_fw.c new file mode 100644 index 000000000000..5b7ef89eb701 --- /dev/null +++ b/drivers/firmware/broadcom/tee_bnxt_fw.c @@ -0,0 +1,279 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2019 Broadcom. + */ + +#include +#include +#include +#include +#include +#include + +#include + +#define MAX_SHM_MEM_SZ SZ_4M + +#define MAX_TEE_PARAM_ARRY_MEMB 4 + +enum ta_cmd { + /* + * TA_CMD_BNXT_FASTBOOT - boot bnxt device by copying f/w into sram + * + * param[0] unused + * param[1] unused + * param[2] unused + * param[3] unused + * + * Result: + * TEE_SUCCESS - Invoke command success + * TEE_ERROR_ITEM_NOT_FOUND - Corrupt f/w image found on memory + */ + TA_CMD_BNXT_FASTBOOT = 0, + + /* + * TA_CMD_BNXT_COPY_COREDUMP - copy the core dump into shm + * + * param[0] (inout memref) - Coredump buffer memory reference + * param[1] (in value) - value.a: offset, data to be copied from + * value.b: size of data to be copied + * param[2] unused + * param[3] unused + * + * Result: + * TEE_SUCCESS - Invoke command success + * TEE_ERROR_BAD_PARAMETERS - Incorrect input param + * TEE_ERROR_ITEM_NOT_FOUND - Corrupt core dump + */ + TA_CMD_BNXT_COPY_COREDUMP = 3, +}; + +/** + * struct tee_bnxt_fw_private - OP-TEE bnxt private data + * @dev: OP-TEE based bnxt device. + * @ctx: OP-TEE context handler. + * @session_id: TA session identifier. + */ +struct tee_bnxt_fw_private { + struct device *dev; + struct tee_context *ctx; + u32 session_id; + struct tee_shm *fw_shm_pool; +}; + +static struct tee_bnxt_fw_private pvt_data; + +static void prepare_args(int cmd, + struct tee_ioctl_invoke_arg *arg, + struct tee_param *param) +{ + memset(arg, 0, sizeof(*arg)); + memset(param, 0, MAX_TEE_PARAM_ARRY_MEMB * sizeof(*param)); + + arg->func = cmd; + arg->session = pvt_data.session_id; + arg->num_params = MAX_TEE_PARAM_ARRY_MEMB; + + /* Fill invoke cmd params */ + switch (cmd) { + case TA_CMD_BNXT_COPY_COREDUMP: + param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT; + param[0].u.memref.shm = pvt_data.fw_shm_pool; + param[0].u.memref.size = MAX_SHM_MEM_SZ; + param[0].u.memref.shm_offs = 0; + param[1].attr = TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INPUT; + break; + case TA_CMD_BNXT_FASTBOOT: + default: + /* Nothing to do */ + break; + } +} + +/** + * tee_bnxt_fw_load() - Load the bnxt firmware + * Uses an OP-TEE call to start a secure + * boot process. + * Returns 0 on success, negative errno otherwise. + */ +int tee_bnxt_fw_load(void) +{ + int ret = 0; + struct tee_ioctl_invoke_arg arg; + struct tee_param param[MAX_TEE_PARAM_ARRY_MEMB]; + + if (!pvt_data.ctx) + return -ENODEV; + + prepare_args(TA_CMD_BNXT_FASTBOOT, &arg, param); + + ret = tee_client_invoke_func(pvt_data.ctx, &arg, param); + if (ret < 0 || arg.ret != 0) { + dev_err(pvt_data.dev, + "TA_CMD_BNXT_FASTBOOT invoke failed TEE err: %x, ret:%x\n", + arg.ret, ret); + return -EINVAL; + } + + return 0; +} +EXPORT_SYMBOL(tee_bnxt_fw_load); + +/** + * tee_bnxt_copy_coredump() - Copy coredump from the allocated memory + * Uses an OP-TEE call to copy coredump + * @buf: destination buffer where core dump is copied into + * @offset: offset from the base address of core dump area + * @size: size of the dump + * + * Returns 0 on success, negative errno otherwise. + */ +int tee_bnxt_copy_coredump(void *buf, u32 offset, u32 size) +{ + struct tee_ioctl_invoke_arg arg; + struct tee_param param[MAX_TEE_PARAM_ARRY_MEMB]; + void *core_data; + u32 rbytes = size; + u32 nbytes = 0; + int ret = 0; + + if (!pvt_data.ctx) + return -ENODEV; + + prepare_args(TA_CMD_BNXT_COPY_COREDUMP, &arg, param); + + while (rbytes) { + nbytes = rbytes; + + nbytes = min_t(u32, rbytes, param[0].u.memref.size); + + /* Fill additional invoke cmd params */ + param[1].u.value.a = offset; + param[1].u.value.b = nbytes; + + ret = tee_client_invoke_func(pvt_data.ctx, &arg, param); + if (ret < 0 || arg.ret != 0) { + dev_err(pvt_data.dev, + "TA_CMD_BNXT_COPY_COREDUMP invoke failed TEE err: %x, ret:%x\n", + arg.ret, ret); + return -EINVAL; + } + + core_data = tee_shm_get_va(pvt_data.fw_shm_pool, 0); + if (IS_ERR(core_data)) { + dev_err(pvt_data.dev, "tee_shm_get_va failed\n"); + return PTR_ERR(core_data); + } + + memcpy(buf, core_data, nbytes); + + rbytes -= nbytes; + buf += nbytes; + offset += nbytes; + } + + return 0; +} +EXPORT_SYMBOL(tee_bnxt_copy_coredump); + +static int optee_ctx_match(struct tee_ioctl_version_data *ver, const void *data) +{ + return (ver->impl_id == TEE_IMPL_ID_OPTEE); +} + +static int tee_bnxt_fw_probe(struct device *dev) +{ + struct tee_client_device *bnxt_device = to_tee_client_device(dev); + int ret, err = -ENODEV; + struct tee_ioctl_open_session_arg sess_arg; + struct tee_shm *fw_shm_pool; + + memset(&sess_arg, 0, sizeof(sess_arg)); + + /* Open context with TEE driver */ + pvt_data.ctx = tee_client_open_context(NULL, optee_ctx_match, NULL, + NULL); + if (IS_ERR(pvt_data.ctx)) + return -ENODEV; + + /* Open session with Bnxt load Trusted App */ + memcpy(sess_arg.uuid, bnxt_device->id.uuid.b, TEE_IOCTL_UUID_LEN); + sess_arg.clnt_login = TEE_IOCTL_LOGIN_PUBLIC; + sess_arg.num_params = 0; + + ret = tee_client_open_session(pvt_data.ctx, &sess_arg, NULL); + if (ret < 0 || sess_arg.ret != 0) { + dev_err(dev, "tee_client_open_session failed, err: %x\n", + sess_arg.ret); + err = -EINVAL; + goto out_ctx; + } + pvt_data.session_id = sess_arg.session; + + pvt_data.dev = dev; + + fw_shm_pool = tee_shm_alloc(pvt_data.ctx, MAX_SHM_MEM_SZ, + TEE_SHM_MAPPED | TEE_SHM_DMA_BUF); + if (IS_ERR(fw_shm_pool)) { + tee_client_close_context(pvt_data.ctx); + dev_err(pvt_data.dev, "tee_shm_alloc failed\n"); + err = PTR_ERR(fw_shm_pool); + goto out_sess; + } + + pvt_data.fw_shm_pool = fw_shm_pool; + + return 0; + +out_sess: + tee_client_close_session(pvt_data.ctx, pvt_data.session_id); +out_ctx: + tee_client_close_context(pvt_data.ctx); + + return err; +} + +static int tee_bnxt_fw_remove(struct device *dev) +{ + tee_shm_free(pvt_data.fw_shm_pool); + tee_client_close_session(pvt_data.ctx, pvt_data.session_id); + tee_client_close_context(pvt_data.ctx); + pvt_data.ctx = NULL; + + return 0; +} + +static const struct tee_client_device_id tee_bnxt_fw_id_table[] = { + {UUID_INIT(0x6272636D, 0x2019, 0x0716, + 0x42, 0x43, 0x4D, 0x5F, 0x53, 0x43, 0x48, 0x49)}, + {} +}; + +MODULE_DEVICE_TABLE(tee, tee_bnxt_fw_id_table); + +static struct tee_client_driver tee_bnxt_fw_driver = { + .id_table = tee_bnxt_fw_id_table, + .driver = { + .name = KBUILD_MODNAME, + .bus = &tee_bus_type, + .probe = tee_bnxt_fw_probe, + .remove = tee_bnxt_fw_remove, + }, +}; + +static int __init tee_bnxt_fw_mod_init(void) +{ + return driver_register(&tee_bnxt_fw_driver.driver); +} + +static void __exit tee_bnxt_fw_mod_exit(void) +{ + driver_unregister(&tee_bnxt_fw_driver.driver); +} + +module_init(tee_bnxt_fw_mod_init); +module_exit(tee_bnxt_fw_mod_exit); + +MODULE_AUTHOR("Vikas Gupta "); +MODULE_DESCRIPTION("Broadcom bnxt firmware manager"); +MODULE_LICENSE("GPL v2"); diff --git a/include/linux/firmware/broadcom/tee_bnxt_fw.h b/include/linux/firmware/broadcom/tee_bnxt_fw.h new file mode 100644 index 000000000000..f24c82d6ef73 --- /dev/null +++ b/include/linux/firmware/broadcom/tee_bnxt_fw.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: BSD-2-Clause */ +/* + * Copyright 2019 Broadcom. + */ + +#ifndef _BROADCOM_TEE_BNXT_FW_H +#define _BROADCOM_TEE_BNXT_FW_H + +#include + +int tee_bnxt_fw_load(void); +int tee_bnxt_copy_coredump(void *buf, u32 offset, u32 size); + +#endif /* _BROADCOM_TEE_BNXT_FW_H */ -- cgit v1.2.3-71-gd317 From df4bb5d128e2c44848aeb36b7ceceba3ac85080d Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Thu, 31 Oct 2019 10:39:20 +0000 Subject: quota: Check that quota is not dirty before release There is a race window where quota was redirted once we drop dq_list_lock inside dqput(), but before we grab dquot->dq_lock inside dquot_release() TASK1 TASK2 (chowner) ->dqput() we_slept: spin_lock(&dq_list_lock) if (dquot_dirty(dquot)) { spin_unlock(&dq_list_lock); dquot->dq_sb->dq_op->write_dquot(dquot); goto we_slept if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) { spin_unlock(&dq_list_lock); dquot->dq_sb->dq_op->release_dquot(dquot); dqget() mark_dquot_dirty() dqput() goto we_slept; } So dquot dirty quota will be released by TASK1, but on next we_sleept loop we detect this and call ->write_dquot() for it. XFSTEST: https://github.com/dmonakhov/xfstests/commit/440a80d4cbb39e9234df4d7240aee1d551c36107 Link: https://lore.kernel.org/r/20191031103920.3919-2-dmonakhov@openvz.org CC: stable@vger.kernel.org Signed-off-by: Dmitry Monakhov Signed-off-by: Jan Kara --- fs/ocfs2/quota_global.c | 2 +- fs/quota/dquot.c | 2 +- include/linux/quotaops.h | 10 ++++++++++ 3 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index 7a922190a8c7..eda83487c9ec 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -728,7 +728,7 @@ static int ocfs2_release_dquot(struct dquot *dquot) mutex_lock(&dquot->dq_lock); /* Check whether we are not racing with some other dqget() */ - if (atomic_read(&dquot->dq_count) > 1) + if (dquot_is_busy(dquot)) goto out; /* Running from downconvert thread? Postpone quota processing to wq */ if (current == osb->dc_task) { diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index b492b9ea829a..72d24a5451bb 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -497,7 +497,7 @@ int dquot_release(struct dquot *dquot) mutex_lock(&dquot->dq_lock); /* Check whether we are not racing with some other dqget() */ - if (atomic_read(&dquot->dq_count) > 1) + if (dquot_is_busy(dquot)) goto out_dqlock; if (dqopt->ops[dquot->dq_id.type]->release_dqblk) { ret = dqopt->ops[dquot->dq_id.type]->release_dqblk(dquot); diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 185d94829701..91e0b7624053 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -54,6 +54,16 @@ static inline struct dquot *dqgrab(struct dquot *dquot) atomic_inc(&dquot->dq_count); return dquot; } + +static inline bool dquot_is_busy(struct dquot *dquot) +{ + if (test_bit(DQ_MOD_B, &dquot->dq_flags)) + return true; + if (atomic_read(&dquot->dq_count) > 1) + return true; + return false; +} + void dqput(struct dquot *dquot); int dquot_scan_active(struct super_block *sb, int (*fn)(struct dquot *dquot, unsigned long priv), -- cgit v1.2.3-71-gd317 From 1ac210d128ef6e92698dd3aa4e2e03e831bc9906 Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Thu, 31 Oct 2019 01:18:29 +0200 Subject: bus: fsl-mc: add the fsl_mc_get_endpoint function Using the newly added fsl_mc_get_endpoint function a fsl-mc driver can find its associated endpoint (another object at the other link of a MC firmware link). The API will be used in the following patch in order to discover the connected DPMAC object of a DPNI. Also, the fsl_mc_device_lookup function is made available to the entire fsl-mc bus driver and not just for the dprc driver. Signed-off-by: Ioana Ciornei Signed-off-by: David S. Miller --- drivers/bus/fsl-mc/dprc-driver.c | 6 ++--- drivers/bus/fsl-mc/dprc.c | 53 +++++++++++++++++++++++++++++++++++++ drivers/bus/fsl-mc/fsl-mc-bus.c | 33 +++++++++++++++++++++++ drivers/bus/fsl-mc/fsl-mc-private.h | 42 +++++++++++++++++++++++++++++ include/linux/fsl/mc.h | 2 ++ 5 files changed, 132 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/bus/fsl-mc/dprc-driver.c b/drivers/bus/fsl-mc/dprc-driver.c index 52c7e15143d6..c8b1c3842c1a 100644 --- a/drivers/bus/fsl-mc/dprc-driver.c +++ b/drivers/bus/fsl-mc/dprc-driver.c @@ -104,10 +104,8 @@ static int __fsl_mc_device_match(struct device *dev, void *data) return fsl_mc_device_match(mc_dev, obj_desc); } -static struct fsl_mc_device *fsl_mc_device_lookup(struct fsl_mc_obj_desc - *obj_desc, - struct fsl_mc_device - *mc_bus_dev) +struct fsl_mc_device *fsl_mc_device_lookup(struct fsl_mc_obj_desc *obj_desc, + struct fsl_mc_device *mc_bus_dev) { struct device *dev; diff --git a/drivers/bus/fsl-mc/dprc.c b/drivers/bus/fsl-mc/dprc.c index 0fe3f52ae0de..602f030d84eb 100644 --- a/drivers/bus/fsl-mc/dprc.c +++ b/drivers/bus/fsl-mc/dprc.c @@ -554,3 +554,56 @@ int dprc_get_container_id(struct fsl_mc_io *mc_io, return 0; } + +/** + * dprc_get_connection() - Get connected endpoint and link status if connection + * exists. + * @mc_io: Pointer to MC portal's I/O object + * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_' + * @token: Token of DPRC object + * @endpoint1: Endpoint 1 configuration parameters + * @endpoint2: Returned endpoint 2 configuration parameters + * @state: Returned link state: + * 1 - link is up; + * 0 - link is down; + * -1 - no connection (endpoint2 information is irrelevant) + * + * Return: '0' on Success; -ENOTCONN if connection does not exist. + */ +int dprc_get_connection(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token, + const struct dprc_endpoint *endpoint1, + struct dprc_endpoint *endpoint2, + int *state) +{ + struct dprc_cmd_get_connection *cmd_params; + struct dprc_rsp_get_connection *rsp_params; + struct fsl_mc_command cmd = { 0 }; + int err, i; + + /* prepare command */ + cmd.header = mc_encode_cmd_header(DPRC_CMDID_GET_CONNECTION, + cmd_flags, + token); + cmd_params = (struct dprc_cmd_get_connection *)cmd.params; + cmd_params->ep1_id = cpu_to_le32(endpoint1->id); + cmd_params->ep1_interface_id = cpu_to_le16(endpoint1->if_id); + for (i = 0; i < 16; i++) + cmd_params->ep1_type[i] = endpoint1->type[i]; + + /* send command to mc */ + err = mc_send_command(mc_io, &cmd); + if (err) + return -ENOTCONN; + + /* retrieve response parameters */ + rsp_params = (struct dprc_rsp_get_connection *)cmd.params; + endpoint2->id = le32_to_cpu(rsp_params->ep2_id); + endpoint2->if_id = le16_to_cpu(rsp_params->ep2_interface_id); + *state = le32_to_cpu(rsp_params->state); + for (i = 0; i < 16; i++) + endpoint2->type[i] = rsp_params->ep2_type[i]; + + return 0; +} diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c index bb3c2fc7c5ba..a07cc19becdb 100644 --- a/drivers/bus/fsl-mc/fsl-mc-bus.c +++ b/drivers/bus/fsl-mc/fsl-mc-bus.c @@ -712,6 +712,39 @@ void fsl_mc_device_remove(struct fsl_mc_device *mc_dev) } EXPORT_SYMBOL_GPL(fsl_mc_device_remove); +struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev) +{ + struct fsl_mc_device *mc_bus_dev, *endpoint; + struct fsl_mc_obj_desc endpoint_desc = { 0 }; + struct dprc_endpoint endpoint1 = { 0 }; + struct dprc_endpoint endpoint2 = { 0 }; + int state, err; + + mc_bus_dev = to_fsl_mc_device(mc_dev->dev.parent); + strcpy(endpoint1.type, mc_dev->obj_desc.type); + endpoint1.id = mc_dev->obj_desc.id; + + err = dprc_get_connection(mc_bus_dev->mc_io, 0, + mc_bus_dev->mc_handle, + &endpoint1, &endpoint2, + &state); + + if (err == -ENOTCONN || state == -1) + return ERR_PTR(-ENOTCONN); + + if (err < 0) { + dev_err(&mc_bus_dev->dev, "dprc_get_connection() = %d\n", err); + return ERR_PTR(err); + } + + strcpy(endpoint_desc.type, endpoint2.type); + endpoint_desc.id = endpoint2.id; + endpoint = fsl_mc_device_lookup(&endpoint_desc, mc_bus_dev); + + return endpoint; +} +EXPORT_SYMBOL_GPL(fsl_mc_get_endpoint); + static int parse_mc_ranges(struct device *dev, int *paddr_cells, int *mc_addr_cells, diff --git a/drivers/bus/fsl-mc/fsl-mc-private.h b/drivers/bus/fsl-mc/fsl-mc-private.h index 020fcc04ec8b..21ca8c756ee7 100644 --- a/drivers/bus/fsl-mc/fsl-mc-private.h +++ b/drivers/bus/fsl-mc/fsl-mc-private.h @@ -105,6 +105,8 @@ int dpmcp_reset(struct fsl_mc_io *mc_io, #define DPRC_CMDID_GET_OBJ_REG_V2 DPRC_CMD_V2(0x15E) #define DPRC_CMDID_SET_OBJ_IRQ DPRC_CMD(0x15F) +#define DPRC_CMDID_GET_CONNECTION DPRC_CMD(0x16C) + struct dprc_cmd_open { __le32 container_id; }; @@ -228,6 +230,22 @@ struct dprc_cmd_set_obj_irq { u8 obj_type[16]; }; +struct dprc_cmd_get_connection { + __le32 ep1_id; + __le16 ep1_interface_id; + u8 pad[2]; + u8 ep1_type[16]; +}; + +struct dprc_rsp_get_connection { + __le64 pad[3]; + __le32 ep2_id; + __le16 ep2_interface_id; + __le16 pad1; + u8 ep2_type[16]; + __le32 state; +}; + /* * DPRC API for managing and querying DPAA resources */ @@ -392,6 +410,27 @@ int dprc_get_container_id(struct fsl_mc_io *mc_io, u32 cmd_flags, int *container_id); +/** + * struct dprc_endpoint - Endpoint description for link connect/disconnect + * operations + * @type: Endpoint object type: NULL terminated string + * @id: Endpoint object ID + * @if_id: Interface ID; should be set for endpoints with multiple + * interfaces ("dpsw", "dpdmux"); for others, always set to 0 + */ +struct dprc_endpoint { + char type[16]; + int id; + u16 if_id; +}; + +int dprc_get_connection(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token, + const struct dprc_endpoint *endpoint1, + struct dprc_endpoint *endpoint2, + int *state); + /* * Data Path Buffer Pool (DPBP) API */ @@ -574,4 +613,7 @@ void fsl_destroy_mc_io(struct fsl_mc_io *mc_io); bool fsl_mc_is_root_dprc(struct device *dev); +struct fsl_mc_device *fsl_mc_device_lookup(struct fsl_mc_obj_desc *obj_desc, + struct fsl_mc_device *mc_bus_dev); + #endif /* _FSL_MC_PRIVATE_H_ */ diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index 975553a9f75d..54d9436600c7 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -403,6 +403,8 @@ int __must_check fsl_mc_allocate_irqs(struct fsl_mc_device *mc_dev); void fsl_mc_free_irqs(struct fsl_mc_device *mc_dev); +struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev); + extern struct bus_type fsl_mc_bus_type; extern struct device_type fsl_mc_bus_dprc_type; -- cgit v1.2.3-71-gd317 From cec0cb8a28f9060367099beeafd0dbdb76fdfae2 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 25 Oct 2019 12:41:10 -0700 Subject: crypto: skcipher - remove crypto_has_ablkcipher() crypto_has_ablkcipher() has no users, and it does the same thing as crypto_has_skcipher() anyway. So remove it. This also removes the last user of crypto_skcipher_type() and crypto_skcipher_mask(), so remove those too. Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- Documentation/crypto/api-skcipher.rst | 2 +- include/linux/crypto.h | 31 ------------------------------- 2 files changed, 1 insertion(+), 32 deletions(-) (limited to 'include/linux') diff --git a/Documentation/crypto/api-skcipher.rst b/Documentation/crypto/api-skcipher.rst index 20ba08dddf2e..55e0851f6fed 100644 --- a/Documentation/crypto/api-skcipher.rst +++ b/Documentation/crypto/api-skcipher.rst @@ -41,7 +41,7 @@ Asynchronous Block Cipher API - Deprecated :doc: Asynchronous Block Cipher API .. kernel-doc:: include/linux/crypto.h - :functions: crypto_free_ablkcipher crypto_has_ablkcipher crypto_ablkcipher_ivsize crypto_ablkcipher_blocksize crypto_ablkcipher_setkey crypto_ablkcipher_reqtfm crypto_ablkcipher_encrypt crypto_ablkcipher_decrypt + :functions: crypto_free_ablkcipher crypto_ablkcipher_ivsize crypto_ablkcipher_blocksize crypto_ablkcipher_setkey crypto_ablkcipher_reqtfm crypto_ablkcipher_encrypt crypto_ablkcipher_decrypt Asynchronous Cipher Request Handle - Deprecated ----------------------------------------------- diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 19ea3a371d7b..b7855743f7e3 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -900,20 +900,6 @@ static inline struct crypto_ablkcipher *__crypto_ablkcipher_cast( return (struct crypto_ablkcipher *)tfm; } -static inline u32 crypto_skcipher_type(u32 type) -{ - type &= ~CRYPTO_ALG_TYPE_MASK; - type |= CRYPTO_ALG_TYPE_BLKCIPHER; - return type; -} - -static inline u32 crypto_skcipher_mask(u32 mask) -{ - mask &= ~CRYPTO_ALG_TYPE_MASK; - mask |= CRYPTO_ALG_TYPE_BLKCIPHER_MASK; - return mask; -} - /** * DOC: Asynchronous Block Cipher API * @@ -959,23 +945,6 @@ static inline void crypto_free_ablkcipher(struct crypto_ablkcipher *tfm) crypto_free_tfm(crypto_ablkcipher_tfm(tfm)); } -/** - * crypto_has_ablkcipher() - Search for the availability of an ablkcipher. - * @alg_name: is the cra_name / name or cra_driver_name / driver name of the - * ablkcipher - * @type: specifies the type of the cipher - * @mask: specifies the mask for the cipher - * - * Return: true when the ablkcipher is known to the kernel crypto API; false - * otherwise - */ -static inline int crypto_has_ablkcipher(const char *alg_name, u32 type, - u32 mask) -{ - return crypto_has_alg(alg_name, crypto_skcipher_type(type), - crypto_skcipher_mask(mask)); -} - static inline struct ablkcipher_tfm *crypto_ablkcipher_crt( struct crypto_ablkcipher *tfm) { -- cgit v1.2.3-71-gd317 From c65058b7587fd3d001c57a50285477be521f5350 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 25 Oct 2019 12:41:12 -0700 Subject: crypto: skcipher - remove the "blkcipher" algorithm type Now that all "blkcipher" algorithms have been converted to "skcipher", remove the blkcipher algorithm type. The skcipher (symmetric key cipher) algorithm type was introduced a few years ago to replace both blkcipher and ablkcipher (synchronous and asynchronous block cipher). The advantages of skcipher include: - A much less confusing name, since none of these algorithm types have ever actually been for raw block ciphers, but rather for all length-preserving encryption modes including block cipher modes of operation, stream ciphers, and other length-preserving modes. - It unified blkcipher and ablkcipher into a single algorithm type which supports both synchronous and asynchronous implementations. Note, blkcipher already operated only on scatterlists, so the fact that skcipher does too isn't a regression in functionality. - Better type safety by using struct skcipher_alg, struct crypto_skcipher, etc. instead of crypto_alg, crypto_tfm, etc. - It sometimes simplifies the implementations of algorithms. Also, the blkcipher API was no longer being tested. Signed-off-by: Eric Biggers Signed-off-by: Herbert Xu --- Documentation/crypto/api-skcipher.rst | 11 +- Documentation/crypto/architecture.rst | 2 - Documentation/crypto/devel-algos.rst | 27 +- crypto/Makefile | 1 - crypto/api.c | 2 +- crypto/blkcipher.c | 548 ---------------------------------- crypto/cryptd.c | 2 +- crypto/crypto_user_stat.c | 4 - crypto/essiv.c | 6 +- crypto/skcipher.c | 107 +------ include/crypto/algapi.h | 74 ----- include/crypto/internal/skcipher.h | 12 - include/crypto/skcipher.h | 8 - include/linux/crypto.h | 395 +----------------------- net/xfrm/xfrm_algo.c | 4 +- 15 files changed, 22 insertions(+), 1181 deletions(-) delete mode 100644 crypto/blkcipher.c (limited to 'include/linux') diff --git a/Documentation/crypto/api-skcipher.rst b/Documentation/crypto/api-skcipher.rst index 55e0851f6fed..56274109ee56 100644 --- a/Documentation/crypto/api-skcipher.rst +++ b/Documentation/crypto/api-skcipher.rst @@ -5,7 +5,7 @@ Block Cipher Algorithm Definitions :doc: Block Cipher Algorithm Definitions .. kernel-doc:: include/linux/crypto.h - :functions: crypto_alg ablkcipher_alg blkcipher_alg cipher_alg compress_alg + :functions: crypto_alg ablkcipher_alg cipher_alg compress_alg Symmetric Key Cipher API ------------------------ @@ -51,12 +51,3 @@ Asynchronous Cipher Request Handle - Deprecated .. kernel-doc:: include/linux/crypto.h :functions: crypto_ablkcipher_reqsize ablkcipher_request_set_tfm ablkcipher_request_alloc ablkcipher_request_free ablkcipher_request_set_callback ablkcipher_request_set_crypt - -Synchronous Block Cipher API - Deprecated ------------------------------------------ - -.. kernel-doc:: include/linux/crypto.h - :doc: Synchronous Block Cipher API - -.. kernel-doc:: include/linux/crypto.h - :functions: crypto_alloc_blkcipher crypto_free_blkcipher crypto_has_blkcipher crypto_blkcipher_name crypto_blkcipher_ivsize crypto_blkcipher_blocksize crypto_blkcipher_setkey crypto_blkcipher_encrypt crypto_blkcipher_encrypt_iv crypto_blkcipher_decrypt crypto_blkcipher_decrypt_iv crypto_blkcipher_set_iv crypto_blkcipher_get_iv diff --git a/Documentation/crypto/architecture.rst b/Documentation/crypto/architecture.rst index 3eae1ae7f798..da90bb006ab0 100644 --- a/Documentation/crypto/architecture.rst +++ b/Documentation/crypto/architecture.rst @@ -201,8 +201,6 @@ the aforementioned cipher types: - CRYPTO_ALG_TYPE_AEAD Authenticated Encryption with Associated Data (MAC) -- CRYPTO_ALG_TYPE_BLKCIPHER Synchronous multi-block cipher - - CRYPTO_ALG_TYPE_ABLKCIPHER Asynchronous multi-block cipher - CRYPTO_ALG_TYPE_KPP Key-agreement Protocol Primitive (KPP) such as diff --git a/Documentation/crypto/devel-algos.rst b/Documentation/crypto/devel-algos.rst index c45c6f400dbd..f9d288015acc 100644 --- a/Documentation/crypto/devel-algos.rst +++ b/Documentation/crypto/devel-algos.rst @@ -128,25 +128,20 @@ process requests that are unaligned. This implies, however, additional overhead as the kernel crypto API needs to perform the realignment of the data which may imply moving of data. -Cipher Definition With struct blkcipher_alg and ablkcipher_alg -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Cipher Definition With struct skcipher_alg +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -Struct blkcipher_alg defines a synchronous block cipher whereas struct -ablkcipher_alg defines an asynchronous block cipher. +Struct skcipher_alg defines a multi-block cipher, or more generally, a +length-preserving symmetric cipher algorithm. -Please refer to the single block cipher description for schematics of -the block cipher usage. +Scatterlist handling +~~~~~~~~~~~~~~~~~~~~ -Specifics Of Asynchronous Multi-Block Cipher -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - -There are a couple of specifics to the asynchronous interface. - -First of all, some of the drivers will want to use the Generic -ScatterWalk in case the hardware needs to be fed separate chunks of the -scatterlist which contains the plaintext and will contain the -ciphertext. Please refer to the ScatterWalk interface offered by the -Linux kernel scatter / gather list implementation. +Some drivers will want to use the Generic ScatterWalk in case the +hardware needs to be fed separate chunks of the scatterlist which +contains the plaintext and will contain the ciphertext. Please refer +to the ScatterWalk interface offered by the Linux kernel scatter / +gather list implementation. Hashing [HASH] -------------- diff --git a/crypto/Makefile b/crypto/Makefile index 8de52cff3069..66b56ec37dd4 100644 --- a/crypto/Makefile +++ b/crypto/Makefile @@ -16,7 +16,6 @@ obj-$(CONFIG_CRYPTO_ALGAPI2) += crypto_algapi.o obj-$(CONFIG_CRYPTO_AEAD2) += aead.o crypto_blkcipher-y := ablkcipher.o -crypto_blkcipher-y += blkcipher.o crypto_blkcipher-y += skcipher.o obj-$(CONFIG_CRYPTO_BLKCIPHER2) += crypto_blkcipher.o obj-$(CONFIG_CRYPTO_SEQIV) += seqiv.o diff --git a/crypto/api.c b/crypto/api.c index d8ba54142620..3e1f9e95095a 100644 --- a/crypto/api.c +++ b/crypto/api.c @@ -406,7 +406,7 @@ EXPORT_SYMBOL_GPL(__crypto_alloc_tfm); * * The returned transform is of a non-determinate type. Most people * should use one of the more specific allocation functions such as - * crypto_alloc_blkcipher. + * crypto_alloc_skcipher(). * * In case of error the return value is an error pointer. */ diff --git a/crypto/blkcipher.c b/crypto/blkcipher.c deleted file mode 100644 index 48a33817de11..000000000000 --- a/crypto/blkcipher.c +++ /dev/null @@ -1,548 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Block chaining cipher operations. - * - * Generic encrypt/decrypt wrapper for ciphers, handles operations across - * multiple page boundaries by using temporary blocks. In user context, - * the kernel is given a chance to schedule us once per page. - * - * Copyright (c) 2006 Herbert Xu - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "internal.h" - -enum { - BLKCIPHER_WALK_PHYS = 1 << 0, - BLKCIPHER_WALK_SLOW = 1 << 1, - BLKCIPHER_WALK_COPY = 1 << 2, - BLKCIPHER_WALK_DIFF = 1 << 3, -}; - -static int blkcipher_walk_next(struct blkcipher_desc *desc, - struct blkcipher_walk *walk); -static int blkcipher_walk_first(struct blkcipher_desc *desc, - struct blkcipher_walk *walk); - -static inline void blkcipher_map_src(struct blkcipher_walk *walk) -{ - walk->src.virt.addr = scatterwalk_map(&walk->in); -} - -static inline void blkcipher_map_dst(struct blkcipher_walk *walk) -{ - walk->dst.virt.addr = scatterwalk_map(&walk->out); -} - -static inline void blkcipher_unmap_src(struct blkcipher_walk *walk) -{ - scatterwalk_unmap(walk->src.virt.addr); -} - -static inline void blkcipher_unmap_dst(struct blkcipher_walk *walk) -{ - scatterwalk_unmap(walk->dst.virt.addr); -} - -/* Get a spot of the specified length that does not straddle a page. - * The caller needs to ensure that there is enough space for this operation. - */ -static inline u8 *blkcipher_get_spot(u8 *start, unsigned int len) -{ - u8 *end_page = (u8 *)(((unsigned long)(start + len - 1)) & PAGE_MASK); - return max(start, end_page); -} - -static inline void blkcipher_done_slow(struct blkcipher_walk *walk, - unsigned int bsize) -{ - u8 *addr; - - addr = (u8 *)ALIGN((unsigned long)walk->buffer, walk->alignmask + 1); - addr = blkcipher_get_spot(addr, bsize); - scatterwalk_copychunks(addr, &walk->out, bsize, 1); -} - -static inline void blkcipher_done_fast(struct blkcipher_walk *walk, - unsigned int n) -{ - if (walk->flags & BLKCIPHER_WALK_COPY) { - blkcipher_map_dst(walk); - memcpy(walk->dst.virt.addr, walk->page, n); - blkcipher_unmap_dst(walk); - } else if (!(walk->flags & BLKCIPHER_WALK_PHYS)) { - if (walk->flags & BLKCIPHER_WALK_DIFF) - blkcipher_unmap_dst(walk); - blkcipher_unmap_src(walk); - } - - scatterwalk_advance(&walk->in, n); - scatterwalk_advance(&walk->out, n); -} - -int blkcipher_walk_done(struct blkcipher_desc *desc, - struct blkcipher_walk *walk, int err) -{ - unsigned int n; /* bytes processed */ - bool more; - - if (unlikely(err < 0)) - goto finish; - - n = walk->nbytes - err; - walk->total -= n; - more = (walk->total != 0); - - if (likely(!(walk->flags & BLKCIPHER_WALK_SLOW))) { - blkcipher_done_fast(walk, n); - } else { - if (WARN_ON(err)) { - /* unexpected case; didn't process all bytes */ - err = -EINVAL; - goto finish; - } - blkcipher_done_slow(walk, n); - } - - scatterwalk_done(&walk->in, 0, more); - scatterwalk_done(&walk->out, 1, more); - - if (more) { - crypto_yield(desc->flags); - return blkcipher_walk_next(desc, walk); - } - err = 0; -finish: - walk->nbytes = 0; - if (walk->iv != desc->info) - memcpy(desc->info, walk->iv, walk->ivsize); - if (walk->buffer != walk->page) - kfree(walk->buffer); - if (walk->page) - free_page((unsigned long)walk->page); - return err; -} -EXPORT_SYMBOL_GPL(blkcipher_walk_done); - -static inline int blkcipher_next_slow(struct blkcipher_desc *desc, - struct blkcipher_walk *walk, - unsigned int bsize, - unsigned int alignmask) -{ - unsigned int n; - unsigned aligned_bsize = ALIGN(bsize, alignmask + 1); - - if (walk->buffer) - goto ok; - - walk->buffer = walk->page; - if (walk->buffer) - goto ok; - - n = aligned_bsize * 3 - (alignmask + 1) + - (alignmask & ~(crypto_tfm_ctx_alignment() - 1)); - walk->buffer = kmalloc(n, GFP_ATOMIC); - if (!walk->buffer) - return blkcipher_walk_done(desc, walk, -ENOMEM); - -ok: - walk->dst.virt.addr = (u8 *)ALIGN((unsigned long)walk->buffer, - alignmask + 1); - walk->dst.virt.addr = blkcipher_get_spot(walk->dst.virt.addr, bsize); - walk->src.virt.addr = blkcipher_get_spot(walk->dst.virt.addr + - aligned_bsize, bsize); - - scatterwalk_copychunks(walk->src.virt.addr, &walk->in, bsize, 0); - - walk->nbytes = bsize; - walk->flags |= BLKCIPHER_WALK_SLOW; - - return 0; -} - -static inline int blkcipher_next_copy(struct blkcipher_walk *walk) -{ - u8 *tmp = walk->page; - - blkcipher_map_src(walk); - memcpy(tmp, walk->src.virt.addr, walk->nbytes); - blkcipher_unmap_src(walk); - - walk->src.virt.addr = tmp; - walk->dst.virt.addr = tmp; - - return 0; -} - -static inline int blkcipher_next_fast(struct blkcipher_desc *desc, - struct blkcipher_walk *walk) -{ - unsigned long diff; - - walk->src.phys.page = scatterwalk_page(&walk->in); - walk->src.phys.offset = offset_in_page(walk->in.offset); - walk->dst.phys.page = scatterwalk_page(&walk->out); - walk->dst.phys.offset = offset_in_page(walk->out.offset); - - if (walk->flags & BLKCIPHER_WALK_PHYS) - return 0; - - diff = walk->src.phys.offset - walk->dst.phys.offset; - diff |= walk->src.virt.page - walk->dst.virt.page; - - blkcipher_map_src(walk); - walk->dst.virt.addr = walk->src.virt.addr; - - if (diff) { - walk->flags |= BLKCIPHER_WALK_DIFF; - blkcipher_map_dst(walk); - } - - return 0; -} - -static int blkcipher_walk_next(struct blkcipher_desc *desc, - struct blkcipher_walk *walk) -{ - unsigned int bsize; - unsigned int n; - int err; - - n = walk->total; - if (unlikely(n < walk->cipher_blocksize)) { - desc->flags |= CRYPTO_TFM_RES_BAD_BLOCK_LEN; - return blkcipher_walk_done(desc, walk, -EINVAL); - } - - bsize = min(walk->walk_blocksize, n); - - walk->flags &= ~(BLKCIPHER_WALK_SLOW | BLKCIPHER_WALK_COPY | - BLKCIPHER_WALK_DIFF); - if (!scatterwalk_aligned(&walk->in, walk->alignmask) || - !scatterwalk_aligned(&walk->out, walk->alignmask)) { - walk->flags |= BLKCIPHER_WALK_COPY; - if (!walk->page) { - walk->page = (void *)__get_free_page(GFP_ATOMIC); - if (!walk->page) - n = 0; - } - } - - n = scatterwalk_clamp(&walk->in, n); - n = scatterwalk_clamp(&walk->out, n); - - if (unlikely(n < bsize)) { - err = blkcipher_next_slow(desc, walk, bsize, walk->alignmask); - goto set_phys_lowmem; - } - - walk->nbytes = n; - if (walk->flags & BLKCIPHER_WALK_COPY) { - err = blkcipher_next_copy(walk); - goto set_phys_lowmem; - } - - return blkcipher_next_fast(desc, walk); - -set_phys_lowmem: - if (walk->flags & BLKCIPHER_WALK_PHYS) { - walk->src.phys.page = virt_to_page(walk->src.virt.addr); - walk->dst.phys.page = virt_to_page(walk->dst.virt.addr); - walk->src.phys.offset &= PAGE_SIZE - 1; - walk->dst.phys.offset &= PAGE_SIZE - 1; - } - return err; -} - -static inline int blkcipher_copy_iv(struct blkcipher_walk *walk) -{ - unsigned bs = walk->walk_blocksize; - unsigned aligned_bs = ALIGN(bs, walk->alignmask + 1); - unsigned int size = aligned_bs * 2 + - walk->ivsize + max(aligned_bs, walk->ivsize) - - (walk->alignmask + 1); - u8 *iv; - - size += walk->alignmask & ~(crypto_tfm_ctx_alignment() - 1); - walk->buffer = kmalloc(size, GFP_ATOMIC); - if (!walk->buffer) - return -ENOMEM; - - iv = (u8 *)ALIGN((unsigned long)walk->buffer, walk->alignmask + 1); - iv = blkcipher_get_spot(iv, bs) + aligned_bs; - iv = blkcipher_get_spot(iv, bs) + aligned_bs; - iv = blkcipher_get_spot(iv, walk->ivsize); - - walk->iv = memcpy(iv, walk->iv, walk->ivsize); - return 0; -} - -int blkcipher_walk_virt(struct blkcipher_desc *desc, - struct blkcipher_walk *walk) -{ - walk->flags &= ~BLKCIPHER_WALK_PHYS; - walk->walk_blocksize = crypto_blkcipher_blocksize(desc->tfm); - walk->cipher_blocksize = walk->walk_blocksize; - walk->ivsize = crypto_blkcipher_ivsize(desc->tfm); - walk->alignmask = crypto_blkcipher_alignmask(desc->tfm); - return blkcipher_walk_first(desc, walk); -} -EXPORT_SYMBOL_GPL(blkcipher_walk_virt); - -int blkcipher_walk_phys(struct blkcipher_desc *desc, - struct blkcipher_walk *walk) -{ - walk->flags |= BLKCIPHER_WALK_PHYS; - walk->walk_blocksize = crypto_blkcipher_blocksize(desc->tfm); - walk->cipher_blocksize = walk->walk_blocksize; - walk->ivsize = crypto_blkcipher_ivsize(desc->tfm); - walk->alignmask = crypto_blkcipher_alignmask(desc->tfm); - return blkcipher_walk_first(desc, walk); -} -EXPORT_SYMBOL_GPL(blkcipher_walk_phys); - -static int blkcipher_walk_first(struct blkcipher_desc *desc, - struct blkcipher_walk *walk) -{ - if (WARN_ON_ONCE(in_irq())) - return -EDEADLK; - - walk->iv = desc->info; - walk->nbytes = walk->total; - if (unlikely(!walk->total)) - return 0; - - walk->buffer = NULL; - if (unlikely(((unsigned long)walk->iv & walk->alignmask))) { - int err = blkcipher_copy_iv(walk); - if (err) - return err; - } - - scatterwalk_start(&walk->in, walk->in.sg); - scatterwalk_start(&walk->out, walk->out.sg); - walk->page = NULL; - - return blkcipher_walk_next(desc, walk); -} - -int blkcipher_walk_virt_block(struct blkcipher_desc *desc, - struct blkcipher_walk *walk, - unsigned int blocksize) -{ - walk->flags &= ~BLKCIPHER_WALK_PHYS; - walk->walk_blocksize = blocksize; - walk->cipher_blocksize = crypto_blkcipher_blocksize(desc->tfm); - walk->ivsize = crypto_blkcipher_ivsize(desc->tfm); - walk->alignmask = crypto_blkcipher_alignmask(desc->tfm); - return blkcipher_walk_first(desc, walk); -} -EXPORT_SYMBOL_GPL(blkcipher_walk_virt_block); - -int blkcipher_aead_walk_virt_block(struct blkcipher_desc *desc, - struct blkcipher_walk *walk, - struct crypto_aead *tfm, - unsigned int blocksize) -{ - walk->flags &= ~BLKCIPHER_WALK_PHYS; - walk->walk_blocksize = blocksize; - walk->cipher_blocksize = crypto_aead_blocksize(tfm); - walk->ivsize = crypto_aead_ivsize(tfm); - walk->alignmask = crypto_aead_alignmask(tfm); - return blkcipher_walk_first(desc, walk); -} -EXPORT_SYMBOL_GPL(blkcipher_aead_walk_virt_block); - -static int setkey_unaligned(struct crypto_tfm *tfm, const u8 *key, - unsigned int keylen) -{ - struct blkcipher_alg *cipher = &tfm->__crt_alg->cra_blkcipher; - unsigned long alignmask = crypto_tfm_alg_alignmask(tfm); - int ret; - u8 *buffer, *alignbuffer; - unsigned long absize; - - absize = keylen + alignmask; - buffer = kmalloc(absize, GFP_ATOMIC); - if (!buffer) - return -ENOMEM; - - alignbuffer = (u8 *)ALIGN((unsigned long)buffer, alignmask + 1); - memcpy(alignbuffer, key, keylen); - ret = cipher->setkey(tfm, alignbuffer, keylen); - memset(alignbuffer, 0, keylen); - kfree(buffer); - return ret; -} - -static int setkey(struct crypto_tfm *tfm, const u8 *key, unsigned int keylen) -{ - struct blkcipher_alg *cipher = &tfm->__crt_alg->cra_blkcipher; - unsigned long alignmask = crypto_tfm_alg_alignmask(tfm); - - if (keylen < cipher->min_keysize || keylen > cipher->max_keysize) { - tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN; - return -EINVAL; - } - - if ((unsigned long)key & alignmask) - return setkey_unaligned(tfm, key, keylen); - - return cipher->setkey(tfm, key, keylen); -} - -static int async_setkey(struct crypto_ablkcipher *tfm, const u8 *key, - unsigned int keylen) -{ - return setkey(crypto_ablkcipher_tfm(tfm), key, keylen); -} - -static int async_encrypt(struct ablkcipher_request *req) -{ - struct crypto_tfm *tfm = req->base.tfm; - struct blkcipher_alg *alg = &tfm->__crt_alg->cra_blkcipher; - struct blkcipher_desc desc = { - .tfm = __crypto_blkcipher_cast(tfm), - .info = req->info, - .flags = req->base.flags, - }; - - - return alg->encrypt(&desc, req->dst, req->src, req->nbytes); -} - -static int async_decrypt(struct ablkcipher_request *req) -{ - struct crypto_tfm *tfm = req->base.tfm; - struct blkcipher_alg *alg = &tfm->__crt_alg->cra_blkcipher; - struct blkcipher_desc desc = { - .tfm = __crypto_blkcipher_cast(tfm), - .info = req->info, - .flags = req->base.flags, - }; - - return alg->decrypt(&desc, req->dst, req->src, req->nbytes); -} - -static unsigned int crypto_blkcipher_ctxsize(struct crypto_alg *alg, u32 type, - u32 mask) -{ - struct blkcipher_alg *cipher = &alg->cra_blkcipher; - unsigned int len = alg->cra_ctxsize; - - if ((mask & CRYPTO_ALG_TYPE_MASK) == CRYPTO_ALG_TYPE_MASK && - cipher->ivsize) { - len = ALIGN(len, (unsigned long)alg->cra_alignmask + 1); - len += cipher->ivsize; - } - - return len; -} - -static int crypto_init_blkcipher_ops_async(struct crypto_tfm *tfm) -{ - struct ablkcipher_tfm *crt = &tfm->crt_ablkcipher; - struct blkcipher_alg *alg = &tfm->__crt_alg->cra_blkcipher; - - crt->setkey = async_setkey; - crt->encrypt = async_encrypt; - crt->decrypt = async_decrypt; - crt->base = __crypto_ablkcipher_cast(tfm); - crt->ivsize = alg->ivsize; - - return 0; -} - -static int crypto_init_blkcipher_ops_sync(struct crypto_tfm *tfm) -{ - struct blkcipher_tfm *crt = &tfm->crt_blkcipher; - struct blkcipher_alg *alg = &tfm->__crt_alg->cra_blkcipher; - unsigned long align = crypto_tfm_alg_alignmask(tfm) + 1; - unsigned long addr; - - crt->setkey = setkey; - crt->encrypt = alg->encrypt; - crt->decrypt = alg->decrypt; - - addr = (unsigned long)crypto_tfm_ctx(tfm); - addr = ALIGN(addr, align); - addr += ALIGN(tfm->__crt_alg->cra_ctxsize, align); - crt->iv = (void *)addr; - - return 0; -} - -static int crypto_init_blkcipher_ops(struct crypto_tfm *tfm, u32 type, u32 mask) -{ - struct blkcipher_alg *alg = &tfm->__crt_alg->cra_blkcipher; - - if (alg->ivsize > PAGE_SIZE / 8) - return -EINVAL; - - if ((mask & CRYPTO_ALG_TYPE_MASK) == CRYPTO_ALG_TYPE_MASK) - return crypto_init_blkcipher_ops_sync(tfm); - else - return crypto_init_blkcipher_ops_async(tfm); -} - -#ifdef CONFIG_NET -static int crypto_blkcipher_report(struct sk_buff *skb, struct crypto_alg *alg) -{ - struct crypto_report_blkcipher rblkcipher; - - memset(&rblkcipher, 0, sizeof(rblkcipher)); - - strscpy(rblkcipher.type, "blkcipher", sizeof(rblkcipher.type)); - strscpy(rblkcipher.geniv, "", sizeof(rblkcipher.geniv)); - - rblkcipher.blocksize = alg->cra_blocksize; - rblkcipher.min_keysize = alg->cra_blkcipher.min_keysize; - rblkcipher.max_keysize = alg->cra_blkcipher.max_keysize; - rblkcipher.ivsize = alg->cra_blkcipher.ivsize; - - return nla_put(skb, CRYPTOCFGA_REPORT_BLKCIPHER, - sizeof(rblkcipher), &rblkcipher); -} -#else -static int crypto_blkcipher_report(struct sk_buff *skb, struct crypto_alg *alg) -{ - return -ENOSYS; -} -#endif - -static void crypto_blkcipher_show(struct seq_file *m, struct crypto_alg *alg) - __maybe_unused; -static void crypto_blkcipher_show(struct seq_file *m, struct crypto_alg *alg) -{ - seq_printf(m, "type : blkcipher\n"); - seq_printf(m, "blocksize : %u\n", alg->cra_blocksize); - seq_printf(m, "min keysize : %u\n", alg->cra_blkcipher.min_keysize); - seq_printf(m, "max keysize : %u\n", alg->cra_blkcipher.max_keysize); - seq_printf(m, "ivsize : %u\n", alg->cra_blkcipher.ivsize); - seq_printf(m, "geniv : \n"); -} - -const struct crypto_type crypto_blkcipher_type = { - .ctxsize = crypto_blkcipher_ctxsize, - .init = crypto_init_blkcipher_ops, -#ifdef CONFIG_PROC_FS - .show = crypto_blkcipher_show, -#endif - .report = crypto_blkcipher_report, -}; -EXPORT_SYMBOL_GPL(crypto_blkcipher_type); - -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("Generic block chaining cipher type"); diff --git a/crypto/cryptd.c b/crypto/cryptd.c index 927760b316a4..2c6649b10923 100644 --- a/crypto/cryptd.c +++ b/crypto/cryptd.c @@ -919,7 +919,7 @@ static int cryptd_create(struct crypto_template *tmpl, struct rtattr **tb) return PTR_ERR(algt); switch (algt->type & algt->mask & CRYPTO_ALG_TYPE_MASK) { - case CRYPTO_ALG_TYPE_BLKCIPHER: + case CRYPTO_ALG_TYPE_SKCIPHER: return cryptd_create_skcipher(tmpl, tb, &queue); case CRYPTO_ALG_TYPE_HASH: return cryptd_create_hash(tmpl, tb, &queue); diff --git a/crypto/crypto_user_stat.c b/crypto/crypto_user_stat.c index 1be95432fa23..154884bf9275 100644 --- a/crypto/crypto_user_stat.c +++ b/crypto/crypto_user_stat.c @@ -213,10 +213,6 @@ static int crypto_reportstat_one(struct crypto_alg *alg, if (crypto_report_cipher(skb, alg)) goto nla_put_failure; break; - case CRYPTO_ALG_TYPE_BLKCIPHER: - if (crypto_report_cipher(skb, alg)) - goto nla_put_failure; - break; case CRYPTO_ALG_TYPE_CIPHER: if (crypto_report_cipher(skb, alg)) goto nla_put_failure; diff --git a/crypto/essiv.c b/crypto/essiv.c index a8befc8fb06e..fc248de88590 100644 --- a/crypto/essiv.c +++ b/crypto/essiv.c @@ -486,7 +486,7 @@ static int essiv_create(struct crypto_template *tmpl, struct rtattr **tb) type = algt->type & algt->mask; switch (type) { - case CRYPTO_ALG_TYPE_BLKCIPHER: + case CRYPTO_ALG_TYPE_SKCIPHER: skcipher_inst = kzalloc(sizeof(*skcipher_inst) + sizeof(*ictx), GFP_KERNEL); if (!skcipher_inst) @@ -586,7 +586,7 @@ static int essiv_create(struct crypto_template *tmpl, struct rtattr **tb) base->cra_alignmask = block_base->cra_alignmask; base->cra_priority = block_base->cra_priority; - if (type == CRYPTO_ALG_TYPE_BLKCIPHER) { + if (type == CRYPTO_ALG_TYPE_SKCIPHER) { skcipher_inst->alg.setkey = essiv_skcipher_setkey; skcipher_inst->alg.encrypt = essiv_skcipher_encrypt; skcipher_inst->alg.decrypt = essiv_skcipher_decrypt; @@ -628,7 +628,7 @@ static int essiv_create(struct crypto_template *tmpl, struct rtattr **tb) out_free_hash: crypto_mod_put(_hash_alg); out_drop_skcipher: - if (type == CRYPTO_ALG_TYPE_BLKCIPHER) + if (type == CRYPTO_ALG_TYPE_SKCIPHER) crypto_drop_skcipher(&ictx->u.skcipher_spawn); else crypto_drop_aead(&ictx->u.aead_spawn); diff --git a/crypto/skcipher.c b/crypto/skcipher.c index 490a3f4b5102..1ce8fbb85f95 100644 --- a/crypto/skcipher.c +++ b/crypto/skcipher.c @@ -580,9 +580,6 @@ EXPORT_SYMBOL_GPL(skcipher_walk_aead_decrypt); static unsigned int crypto_skcipher_extsize(struct crypto_alg *alg) { - if (alg->cra_type == &crypto_blkcipher_type) - return sizeof(struct crypto_blkcipher *); - if (alg->cra_type == &crypto_ablkcipher_type) return sizeof(struct crypto_ablkcipher *); @@ -595,105 +592,6 @@ static void skcipher_set_needkey(struct crypto_skcipher *tfm) crypto_skcipher_set_flags(tfm, CRYPTO_TFM_NEED_KEY); } -static int skcipher_setkey_blkcipher(struct crypto_skcipher *tfm, - const u8 *key, unsigned int keylen) -{ - struct crypto_blkcipher **ctx = crypto_skcipher_ctx(tfm); - struct crypto_blkcipher *blkcipher = *ctx; - int err; - - crypto_blkcipher_clear_flags(blkcipher, ~0); - crypto_blkcipher_set_flags(blkcipher, crypto_skcipher_get_flags(tfm) & - CRYPTO_TFM_REQ_MASK); - err = crypto_blkcipher_setkey(blkcipher, key, keylen); - crypto_skcipher_set_flags(tfm, crypto_blkcipher_get_flags(blkcipher) & - CRYPTO_TFM_RES_MASK); - if (unlikely(err)) { - skcipher_set_needkey(tfm); - return err; - } - - crypto_skcipher_clear_flags(tfm, CRYPTO_TFM_NEED_KEY); - return 0; -} - -static int skcipher_crypt_blkcipher(struct skcipher_request *req, - int (*crypt)(struct blkcipher_desc *, - struct scatterlist *, - struct scatterlist *, - unsigned int)) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct crypto_blkcipher **ctx = crypto_skcipher_ctx(tfm); - struct blkcipher_desc desc = { - .tfm = *ctx, - .info = req->iv, - .flags = req->base.flags, - }; - - - return crypt(&desc, req->dst, req->src, req->cryptlen); -} - -static int skcipher_encrypt_blkcipher(struct skcipher_request *req) -{ - struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req); - struct crypto_tfm *tfm = crypto_skcipher_tfm(skcipher); - struct blkcipher_alg *alg = &tfm->__crt_alg->cra_blkcipher; - - return skcipher_crypt_blkcipher(req, alg->encrypt); -} - -static int skcipher_decrypt_blkcipher(struct skcipher_request *req) -{ - struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req); - struct crypto_tfm *tfm = crypto_skcipher_tfm(skcipher); - struct blkcipher_alg *alg = &tfm->__crt_alg->cra_blkcipher; - - return skcipher_crypt_blkcipher(req, alg->decrypt); -} - -static void crypto_exit_skcipher_ops_blkcipher(struct crypto_tfm *tfm) -{ - struct crypto_blkcipher **ctx = crypto_tfm_ctx(tfm); - - crypto_free_blkcipher(*ctx); -} - -static int crypto_init_skcipher_ops_blkcipher(struct crypto_tfm *tfm) -{ - struct crypto_alg *calg = tfm->__crt_alg; - struct crypto_skcipher *skcipher = __crypto_skcipher_cast(tfm); - struct crypto_blkcipher **ctx = crypto_tfm_ctx(tfm); - struct crypto_blkcipher *blkcipher; - struct crypto_tfm *btfm; - - if (!crypto_mod_get(calg)) - return -EAGAIN; - - btfm = __crypto_alloc_tfm(calg, CRYPTO_ALG_TYPE_BLKCIPHER, - CRYPTO_ALG_TYPE_MASK); - if (IS_ERR(btfm)) { - crypto_mod_put(calg); - return PTR_ERR(btfm); - } - - blkcipher = __crypto_blkcipher_cast(btfm); - *ctx = blkcipher; - tfm->exit = crypto_exit_skcipher_ops_blkcipher; - - skcipher->setkey = skcipher_setkey_blkcipher; - skcipher->encrypt = skcipher_encrypt_blkcipher; - skcipher->decrypt = skcipher_decrypt_blkcipher; - - skcipher->ivsize = crypto_blkcipher_ivsize(blkcipher); - skcipher->keysize = calg->cra_blkcipher.max_keysize; - - skcipher_set_needkey(skcipher); - - return 0; -} - static int skcipher_setkey_ablkcipher(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) { @@ -888,9 +786,6 @@ static int crypto_skcipher_init_tfm(struct crypto_tfm *tfm) struct crypto_skcipher *skcipher = __crypto_skcipher_cast(tfm); struct skcipher_alg *alg = crypto_skcipher_alg(skcipher); - if (tfm->__crt_alg->cra_type == &crypto_blkcipher_type) - return crypto_init_skcipher_ops_blkcipher(tfm); - if (tfm->__crt_alg->cra_type == &crypto_ablkcipher_type) return crypto_init_skcipher_ops_ablkcipher(tfm); @@ -973,7 +868,7 @@ static const struct crypto_type crypto_skcipher_type = { #endif .report = crypto_skcipher_report, .maskclear = ~CRYPTO_ALG_TYPE_MASK, - .maskset = CRYPTO_ALG_TYPE_BLKCIPHER_MASK, + .maskset = CRYPTO_ALG_TYPE_MASK, .type = CRYPTO_ALG_TYPE_SKCIPHER, .tfmsize = offsetof(struct crypto_skcipher, base), }; diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h index e5bd302f2c49..cadc5257c612 100644 --- a/include/crypto/algapi.h +++ b/include/crypto/algapi.h @@ -85,36 +85,6 @@ struct scatter_walk { unsigned int offset; }; -struct blkcipher_walk { - union { - struct { - struct page *page; - unsigned long offset; - } phys; - - struct { - u8 *page; - u8 *addr; - } virt; - } src, dst; - - struct scatter_walk in; - unsigned int nbytes; - - struct scatter_walk out; - unsigned int total; - - void *page; - u8 *buffer; - u8 *iv; - unsigned int ivsize; - - int flags; - unsigned int walk_blocksize; - unsigned int cipher_blocksize; - unsigned int alignmask; -}; - struct ablkcipher_walk { struct { struct page *page; @@ -133,7 +103,6 @@ struct ablkcipher_walk { }; extern const struct crypto_type crypto_ablkcipher_type; -extern const struct crypto_type crypto_blkcipher_type; void crypto_mod_put(struct crypto_alg *alg); @@ -233,20 +202,6 @@ static inline void crypto_xor_cpy(u8 *dst, const u8 *src1, const u8 *src2, } } -int blkcipher_walk_done(struct blkcipher_desc *desc, - struct blkcipher_walk *walk, int err); -int blkcipher_walk_virt(struct blkcipher_desc *desc, - struct blkcipher_walk *walk); -int blkcipher_walk_phys(struct blkcipher_desc *desc, - struct blkcipher_walk *walk); -int blkcipher_walk_virt_block(struct blkcipher_desc *desc, - struct blkcipher_walk *walk, - unsigned int blocksize); -int blkcipher_aead_walk_virt_block(struct blkcipher_desc *desc, - struct blkcipher_walk *walk, - struct crypto_aead *tfm, - unsigned int blocksize); - int ablkcipher_walk_done(struct ablkcipher_request *req, struct ablkcipher_walk *walk, int err); int ablkcipher_walk_phys(struct ablkcipher_request *req, @@ -286,25 +241,6 @@ static inline void *crypto_ablkcipher_ctx_aligned(struct crypto_ablkcipher *tfm) return crypto_tfm_ctx_aligned(&tfm->base); } -static inline struct crypto_blkcipher *crypto_spawn_blkcipher( - struct crypto_spawn *spawn) -{ - u32 type = CRYPTO_ALG_TYPE_BLKCIPHER; - u32 mask = CRYPTO_ALG_TYPE_MASK; - - return __crypto_blkcipher_cast(crypto_spawn_tfm(spawn, type, mask)); -} - -static inline void *crypto_blkcipher_ctx(struct crypto_blkcipher *tfm) -{ - return crypto_tfm_ctx(&tfm->base); -} - -static inline void *crypto_blkcipher_ctx_aligned(struct crypto_blkcipher *tfm) -{ - return crypto_tfm_ctx_aligned(&tfm->base); -} - static inline struct crypto_cipher *crypto_spawn_cipher( struct crypto_spawn *spawn) { @@ -319,16 +255,6 @@ static inline struct cipher_alg *crypto_cipher_alg(struct crypto_cipher *tfm) return &crypto_cipher_tfm(tfm)->__crt_alg->cra_cipher; } -static inline void blkcipher_walk_init(struct blkcipher_walk *walk, - struct scatterlist *dst, - struct scatterlist *src, - unsigned int nbytes) -{ - walk->in.sg = src; - walk->out.sg = dst; - walk->total = nbytes; -} - static inline void ablkcipher_walk_init(struct ablkcipher_walk *walk, struct scatterlist *dst, struct scatterlist *src, diff --git a/include/crypto/internal/skcipher.h b/include/crypto/internal/skcipher.h index 3175dfeaed2c..454e898d5f5f 100644 --- a/include/crypto/internal/skcipher.h +++ b/include/crypto/internal/skcipher.h @@ -182,10 +182,6 @@ static inline u32 skcipher_request_flags(struct skcipher_request *req) static inline unsigned int crypto_skcipher_alg_min_keysize( struct skcipher_alg *alg) { - if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) == - CRYPTO_ALG_TYPE_BLKCIPHER) - return alg->base.cra_blkcipher.min_keysize; - if (alg->base.cra_ablkcipher.encrypt) return alg->base.cra_ablkcipher.min_keysize; @@ -195,10 +191,6 @@ static inline unsigned int crypto_skcipher_alg_min_keysize( static inline unsigned int crypto_skcipher_alg_max_keysize( struct skcipher_alg *alg) { - if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) == - CRYPTO_ALG_TYPE_BLKCIPHER) - return alg->base.cra_blkcipher.max_keysize; - if (alg->base.cra_ablkcipher.encrypt) return alg->base.cra_ablkcipher.max_keysize; @@ -208,10 +200,6 @@ static inline unsigned int crypto_skcipher_alg_max_keysize( static inline unsigned int crypto_skcipher_alg_walksize( struct skcipher_alg *alg) { - if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) == - CRYPTO_ALG_TYPE_BLKCIPHER) - return alg->base.cra_blocksize; - if (alg->base.cra_ablkcipher.encrypt) return alg->base.cra_blocksize; diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h index e34993f5d190..8c5a31e810da 100644 --- a/include/crypto/skcipher.h +++ b/include/crypto/skcipher.h @@ -241,10 +241,6 @@ static inline struct skcipher_alg *crypto_skcipher_alg( static inline unsigned int crypto_skcipher_alg_ivsize(struct skcipher_alg *alg) { - if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) == - CRYPTO_ALG_TYPE_BLKCIPHER) - return alg->base.cra_blkcipher.ivsize; - if (alg->base.cra_ablkcipher.encrypt) return alg->base.cra_ablkcipher.ivsize; @@ -290,10 +286,6 @@ static inline unsigned int crypto_skcipher_blocksize( static inline unsigned int crypto_skcipher_alg_chunksize( struct skcipher_alg *alg) { - if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) == - CRYPTO_ALG_TYPE_BLKCIPHER) - return alg->base.cra_blocksize; - if (alg->base.cra_ablkcipher.encrypt) return alg->base.cra_blocksize; diff --git a/include/linux/crypto.h b/include/linux/crypto.h index b7855743f7e3..e9f2c6b5d800 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -41,7 +41,6 @@ #define CRYPTO_ALG_TYPE_CIPHER 0x00000001 #define CRYPTO_ALG_TYPE_COMPRESS 0x00000002 #define CRYPTO_ALG_TYPE_AEAD 0x00000003 -#define CRYPTO_ALG_TYPE_BLKCIPHER 0x00000004 #define CRYPTO_ALG_TYPE_ABLKCIPHER 0x00000005 #define CRYPTO_ALG_TYPE_SKCIPHER 0x00000005 #define CRYPTO_ALG_TYPE_KPP 0x00000008 @@ -55,7 +54,6 @@ #define CRYPTO_ALG_TYPE_HASH_MASK 0x0000000e #define CRYPTO_ALG_TYPE_AHASH_MASK 0x0000000e -#define CRYPTO_ALG_TYPE_BLKCIPHER_MASK 0x0000000c #define CRYPTO_ALG_TYPE_ACOMPRESS_MASK 0x0000000e #define CRYPTO_ALG_LARVAL 0x00000010 @@ -141,7 +139,6 @@ struct scatterlist; struct crypto_ablkcipher; struct crypto_async_request; -struct crypto_blkcipher; struct crypto_tfm; struct crypto_type; @@ -176,12 +173,6 @@ struct ablkcipher_request { void *__ctx[] CRYPTO_MINALIGN_ATTR; }; -struct blkcipher_desc { - struct crypto_blkcipher *tfm; - void *info; - u32 flags; -}; - /** * DOC: Block Cipher Algorithm Definitions * @@ -240,32 +231,6 @@ struct ablkcipher_alg { unsigned int ivsize; }; -/** - * struct blkcipher_alg - synchronous block cipher definition - * @min_keysize: see struct ablkcipher_alg - * @max_keysize: see struct ablkcipher_alg - * @setkey: see struct ablkcipher_alg - * @encrypt: see struct ablkcipher_alg - * @decrypt: see struct ablkcipher_alg - * @ivsize: see struct ablkcipher_alg - * - * All fields except @ivsize are mandatory and must be filled. - */ -struct blkcipher_alg { - int (*setkey)(struct crypto_tfm *tfm, const u8 *key, - unsigned int keylen); - int (*encrypt)(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes); - int (*decrypt)(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes); - - unsigned int min_keysize; - unsigned int max_keysize; - unsigned int ivsize; -}; - /** * struct cipher_alg - single-block symmetric ciphers definition * @cia_min_keysize: Minimum key size supported by the transformation. This is @@ -451,7 +416,6 @@ struct crypto_istat_rng { #endif /* CONFIG_CRYPTO_STATS */ #define cra_ablkcipher cra_u.ablkcipher -#define cra_blkcipher cra_u.blkcipher #define cra_cipher cra_u.cipher #define cra_compress cra_u.compress @@ -499,9 +463,8 @@ struct crypto_istat_rng { * transformation algorithm. * @cra_type: Type of the cryptographic transformation. This is a pointer to * struct crypto_type, which implements callbacks common for all - * transformation types. There are multiple options: - * &crypto_blkcipher_type, &crypto_ablkcipher_type, - * &crypto_ahash_type, &crypto_rng_type. + * transformation types. There are multiple options, such as + * &crypto_skcipher_type, &crypto_ahash_type, &crypto_rng_type. * This field might be empty. In that case, there are no common * callbacks. This is the case for: cipher, compress, shash. * @cra_u: Callbacks implementing the transformation. This is a union of @@ -522,8 +485,6 @@ struct crypto_istat_rng { * @cra_init. * @cra_u.ablkcipher: Union member which contains an asynchronous block cipher * definition. See @struct @ablkcipher_alg. - * @cra_u.blkcipher: Union member which contains a synchronous block cipher - * definition See @struct @blkcipher_alg. * @cra_u.cipher: Union member which contains a single-block symmetric cipher * definition. See @struct @cipher_alg. * @cra_u.compress: Union member which contains a (de)compression algorithm. @@ -566,7 +527,6 @@ struct crypto_alg { union { struct ablkcipher_alg ablkcipher; - struct blkcipher_alg blkcipher; struct cipher_alg cipher; struct compress_alg compress; } cra_u; @@ -727,16 +687,6 @@ struct ablkcipher_tfm { unsigned int reqsize; }; -struct blkcipher_tfm { - void *iv; - int (*setkey)(struct crypto_tfm *tfm, const u8 *key, - unsigned int keylen); - int (*encrypt)(struct blkcipher_desc *desc, struct scatterlist *dst, - struct scatterlist *src, unsigned int nbytes); - int (*decrypt)(struct blkcipher_desc *desc, struct scatterlist *dst, - struct scatterlist *src, unsigned int nbytes); -}; - struct cipher_tfm { int (*cit_setkey)(struct crypto_tfm *tfm, const u8 *key, unsigned int keylen); @@ -754,7 +704,6 @@ struct compress_tfm { }; #define crt_ablkcipher crt_u.ablkcipher -#define crt_blkcipher crt_u.blkcipher #define crt_cipher crt_u.cipher #define crt_compress crt_u.compress @@ -764,7 +713,6 @@ struct crypto_tfm { union { struct ablkcipher_tfm ablkcipher; - struct blkcipher_tfm blkcipher; struct cipher_tfm cipher; struct compress_tfm compress; } crt_u; @@ -780,10 +728,6 @@ struct crypto_ablkcipher { struct crypto_tfm base; }; -struct crypto_blkcipher { - struct crypto_tfm base; -}; - struct crypto_cipher { struct crypto_tfm base; }; @@ -1232,341 +1176,6 @@ static inline void ablkcipher_request_set_crypt( req->info = iv; } -/** - * DOC: Synchronous Block Cipher API - * - * The synchronous block cipher API is used with the ciphers of type - * CRYPTO_ALG_TYPE_BLKCIPHER (listed as type "blkcipher" in /proc/crypto) - * - * Synchronous calls, have a context in the tfm. But since a single tfm can be - * used in multiple calls and in parallel, this info should not be changeable - * (unless a lock is used). This applies, for example, to the symmetric key. - * However, the IV is changeable, so there is an iv field in blkcipher_tfm - * structure for synchronous blkcipher api. So, its the only state info that can - * be kept for synchronous calls without using a big lock across a tfm. - * - * The block cipher API allows the use of a complete cipher, i.e. a cipher - * consisting of a template (a block chaining mode) and a single block cipher - * primitive (e.g. AES). - * - * The plaintext data buffer and the ciphertext data buffer are pointed to - * by using scatter/gather lists. The cipher operation is performed - * on all segments of the provided scatter/gather lists. - * - * The kernel crypto API supports a cipher operation "in-place" which means that - * the caller may provide the same scatter/gather list for the plaintext and - * cipher text. After the completion of the cipher operation, the plaintext - * data is replaced with the ciphertext data in case of an encryption and vice - * versa for a decryption. The caller must ensure that the scatter/gather lists - * for the output data point to sufficiently large buffers, i.e. multiples of - * the block size of the cipher. - */ - -static inline struct crypto_blkcipher *__crypto_blkcipher_cast( - struct crypto_tfm *tfm) -{ - return (struct crypto_blkcipher *)tfm; -} - -static inline struct crypto_blkcipher *crypto_blkcipher_cast( - struct crypto_tfm *tfm) -{ - BUG_ON(crypto_tfm_alg_type(tfm) != CRYPTO_ALG_TYPE_BLKCIPHER); - return __crypto_blkcipher_cast(tfm); -} - -/** - * crypto_alloc_blkcipher() - allocate synchronous block cipher handle - * @alg_name: is the cra_name / name or cra_driver_name / driver name of the - * blkcipher cipher - * @type: specifies the type of the cipher - * @mask: specifies the mask for the cipher - * - * Allocate a cipher handle for a block cipher. The returned struct - * crypto_blkcipher is the cipher handle that is required for any subsequent - * API invocation for that block cipher. - * - * Return: allocated cipher handle in case of success; IS_ERR() is true in case - * of an error, PTR_ERR() returns the error code. - */ -static inline struct crypto_blkcipher *crypto_alloc_blkcipher( - const char *alg_name, u32 type, u32 mask) -{ - type &= ~CRYPTO_ALG_TYPE_MASK; - type |= CRYPTO_ALG_TYPE_BLKCIPHER; - mask |= CRYPTO_ALG_TYPE_MASK; - - return __crypto_blkcipher_cast(crypto_alloc_base(alg_name, type, mask)); -} - -static inline struct crypto_tfm *crypto_blkcipher_tfm( - struct crypto_blkcipher *tfm) -{ - return &tfm->base; -} - -/** - * crypto_free_blkcipher() - zeroize and free the block cipher handle - * @tfm: cipher handle to be freed - */ -static inline void crypto_free_blkcipher(struct crypto_blkcipher *tfm) -{ - crypto_free_tfm(crypto_blkcipher_tfm(tfm)); -} - -/** - * crypto_has_blkcipher() - Search for the availability of a block cipher - * @alg_name: is the cra_name / name or cra_driver_name / driver name of the - * block cipher - * @type: specifies the type of the cipher - * @mask: specifies the mask for the cipher - * - * Return: true when the block cipher is known to the kernel crypto API; false - * otherwise - */ -static inline int crypto_has_blkcipher(const char *alg_name, u32 type, u32 mask) -{ - type &= ~CRYPTO_ALG_TYPE_MASK; - type |= CRYPTO_ALG_TYPE_BLKCIPHER; - mask |= CRYPTO_ALG_TYPE_MASK; - - return crypto_has_alg(alg_name, type, mask); -} - -/** - * crypto_blkcipher_name() - return the name / cra_name from the cipher handle - * @tfm: cipher handle - * - * Return: The character string holding the name of the cipher - */ -static inline const char *crypto_blkcipher_name(struct crypto_blkcipher *tfm) -{ - return crypto_tfm_alg_name(crypto_blkcipher_tfm(tfm)); -} - -static inline struct blkcipher_tfm *crypto_blkcipher_crt( - struct crypto_blkcipher *tfm) -{ - return &crypto_blkcipher_tfm(tfm)->crt_blkcipher; -} - -static inline struct blkcipher_alg *crypto_blkcipher_alg( - struct crypto_blkcipher *tfm) -{ - return &crypto_blkcipher_tfm(tfm)->__crt_alg->cra_blkcipher; -} - -/** - * crypto_blkcipher_ivsize() - obtain IV size - * @tfm: cipher handle - * - * The size of the IV for the block cipher referenced by the cipher handle is - * returned. This IV size may be zero if the cipher does not need an IV. - * - * Return: IV size in bytes - */ -static inline unsigned int crypto_blkcipher_ivsize(struct crypto_blkcipher *tfm) -{ - return crypto_blkcipher_alg(tfm)->ivsize; -} - -/** - * crypto_blkcipher_blocksize() - obtain block size of cipher - * @tfm: cipher handle - * - * The block size for the block cipher referenced with the cipher handle is - * returned. The caller may use that information to allocate appropriate - * memory for the data returned by the encryption or decryption operation. - * - * Return: block size of cipher - */ -static inline unsigned int crypto_blkcipher_blocksize( - struct crypto_blkcipher *tfm) -{ - return crypto_tfm_alg_blocksize(crypto_blkcipher_tfm(tfm)); -} - -static inline unsigned int crypto_blkcipher_alignmask( - struct crypto_blkcipher *tfm) -{ - return crypto_tfm_alg_alignmask(crypto_blkcipher_tfm(tfm)); -} - -static inline u32 crypto_blkcipher_get_flags(struct crypto_blkcipher *tfm) -{ - return crypto_tfm_get_flags(crypto_blkcipher_tfm(tfm)); -} - -static inline void crypto_blkcipher_set_flags(struct crypto_blkcipher *tfm, - u32 flags) -{ - crypto_tfm_set_flags(crypto_blkcipher_tfm(tfm), flags); -} - -static inline void crypto_blkcipher_clear_flags(struct crypto_blkcipher *tfm, - u32 flags) -{ - crypto_tfm_clear_flags(crypto_blkcipher_tfm(tfm), flags); -} - -/** - * crypto_blkcipher_setkey() - set key for cipher - * @tfm: cipher handle - * @key: buffer holding the key - * @keylen: length of the key in bytes - * - * The caller provided key is set for the block cipher referenced by the cipher - * handle. - * - * Note, the key length determines the cipher type. Many block ciphers implement - * different cipher modes depending on the key size, such as AES-128 vs AES-192 - * vs. AES-256. When providing a 16 byte key for an AES cipher handle, AES-128 - * is performed. - * - * Return: 0 if the setting of the key was successful; < 0 if an error occurred - */ -static inline int crypto_blkcipher_setkey(struct crypto_blkcipher *tfm, - const u8 *key, unsigned int keylen) -{ - return crypto_blkcipher_crt(tfm)->setkey(crypto_blkcipher_tfm(tfm), - key, keylen); -} - -/** - * crypto_blkcipher_encrypt() - encrypt plaintext - * @desc: reference to the block cipher handle with meta data - * @dst: scatter/gather list that is filled by the cipher operation with the - * ciphertext - * @src: scatter/gather list that holds the plaintext - * @nbytes: number of bytes of the plaintext to encrypt. - * - * Encrypt plaintext data using the IV set by the caller with a preceding - * call of crypto_blkcipher_set_iv. - * - * The blkcipher_desc data structure must be filled by the caller and can - * reside on the stack. The caller must fill desc as follows: desc.tfm is filled - * with the block cipher handle; desc.flags is filled with either - * CRYPTO_TFM_REQ_MAY_SLEEP or 0. - * - * Return: 0 if the cipher operation was successful; < 0 if an error occurred - */ -static inline int crypto_blkcipher_encrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, - struct scatterlist *src, - unsigned int nbytes) -{ - desc->info = crypto_blkcipher_crt(desc->tfm)->iv; - return crypto_blkcipher_crt(desc->tfm)->encrypt(desc, dst, src, nbytes); -} - -/** - * crypto_blkcipher_encrypt_iv() - encrypt plaintext with dedicated IV - * @desc: reference to the block cipher handle with meta data - * @dst: scatter/gather list that is filled by the cipher operation with the - * ciphertext - * @src: scatter/gather list that holds the plaintext - * @nbytes: number of bytes of the plaintext to encrypt. - * - * Encrypt plaintext data with the use of an IV that is solely used for this - * cipher operation. Any previously set IV is not used. - * - * The blkcipher_desc data structure must be filled by the caller and can - * reside on the stack. The caller must fill desc as follows: desc.tfm is filled - * with the block cipher handle; desc.info is filled with the IV to be used for - * the current operation; desc.flags is filled with either - * CRYPTO_TFM_REQ_MAY_SLEEP or 0. - * - * Return: 0 if the cipher operation was successful; < 0 if an error occurred - */ -static inline int crypto_blkcipher_encrypt_iv(struct blkcipher_desc *desc, - struct scatterlist *dst, - struct scatterlist *src, - unsigned int nbytes) -{ - return crypto_blkcipher_crt(desc->tfm)->encrypt(desc, dst, src, nbytes); -} - -/** - * crypto_blkcipher_decrypt() - decrypt ciphertext - * @desc: reference to the block cipher handle with meta data - * @dst: scatter/gather list that is filled by the cipher operation with the - * plaintext - * @src: scatter/gather list that holds the ciphertext - * @nbytes: number of bytes of the ciphertext to decrypt. - * - * Decrypt ciphertext data using the IV set by the caller with a preceding - * call of crypto_blkcipher_set_iv. - * - * The blkcipher_desc data structure must be filled by the caller as documented - * for the crypto_blkcipher_encrypt call above. - * - * Return: 0 if the cipher operation was successful; < 0 if an error occurred - * - */ -static inline int crypto_blkcipher_decrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, - struct scatterlist *src, - unsigned int nbytes) -{ - desc->info = crypto_blkcipher_crt(desc->tfm)->iv; - return crypto_blkcipher_crt(desc->tfm)->decrypt(desc, dst, src, nbytes); -} - -/** - * crypto_blkcipher_decrypt_iv() - decrypt ciphertext with dedicated IV - * @desc: reference to the block cipher handle with meta data - * @dst: scatter/gather list that is filled by the cipher operation with the - * plaintext - * @src: scatter/gather list that holds the ciphertext - * @nbytes: number of bytes of the ciphertext to decrypt. - * - * Decrypt ciphertext data with the use of an IV that is solely used for this - * cipher operation. Any previously set IV is not used. - * - * The blkcipher_desc data structure must be filled by the caller as documented - * for the crypto_blkcipher_encrypt_iv call above. - * - * Return: 0 if the cipher operation was successful; < 0 if an error occurred - */ -static inline int crypto_blkcipher_decrypt_iv(struct blkcipher_desc *desc, - struct scatterlist *dst, - struct scatterlist *src, - unsigned int nbytes) -{ - return crypto_blkcipher_crt(desc->tfm)->decrypt(desc, dst, src, nbytes); -} - -/** - * crypto_blkcipher_set_iv() - set IV for cipher - * @tfm: cipher handle - * @src: buffer holding the IV - * @len: length of the IV in bytes - * - * The caller provided IV is set for the block cipher referenced by the cipher - * handle. - */ -static inline void crypto_blkcipher_set_iv(struct crypto_blkcipher *tfm, - const u8 *src, unsigned int len) -{ - memcpy(crypto_blkcipher_crt(tfm)->iv, src, len); -} - -/** - * crypto_blkcipher_get_iv() - obtain IV from cipher - * @tfm: cipher handle - * @dst: buffer filled with the IV - * @len: length of the buffer dst - * - * The caller can obtain the IV set for the block cipher referenced by the - * cipher handle and store it into the user-provided buffer. If the buffer - * has an insufficient space, the IV is truncated to fit the buffer. - */ -static inline void crypto_blkcipher_get_iv(struct crypto_blkcipher *tfm, - u8 *dst, unsigned int len) -{ - memcpy(dst, crypto_blkcipher_crt(tfm)->iv, len); -} - /** * DOC: Single Block Cipher API * diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c index 32a378e7011f..4dae3ab8d030 100644 --- a/net/xfrm/xfrm_algo.c +++ b/net/xfrm/xfrm_algo.c @@ -626,8 +626,8 @@ static const struct xfrm_algo_list xfrm_aalg_list = { static const struct xfrm_algo_list xfrm_ealg_list = { .algs = ealg_list, .entries = ARRAY_SIZE(ealg_list), - .type = CRYPTO_ALG_TYPE_BLKCIPHER, - .mask = CRYPTO_ALG_TYPE_BLKCIPHER_MASK, + .type = CRYPTO_ALG_TYPE_SKCIPHER, + .mask = CRYPTO_ALG_TYPE_MASK, }; static const struct xfrm_algo_list xfrm_calg_list = { -- cgit v1.2.3-71-gd317 From 8b5369ea580964dbc982781bfb9fb93459fc5e8d Mon Sep 17 00:00:00 2001 From: Nicolas Saenz Julienne Date: Mon, 14 Oct 2019 20:31:03 +0200 Subject: dma/direct: turn ARCH_ZONE_DMA_BITS into a variable Some architectures, notably ARM, are interested in tweaking this depending on their runtime DMA addressing limitations. Acked-by: Christoph Hellwig Signed-off-by: Nicolas Saenz Julienne Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/page.h | 2 -- arch/arm64/mm/init.c | 9 +++++++-- arch/powerpc/include/asm/page.h | 9 --------- arch/powerpc/mm/mem.c | 20 +++++++++++++++----- arch/s390/include/asm/page.h | 2 -- arch/s390/mm/init.c | 1 + include/linux/dma-direct.h | 2 ++ kernel/dma/direct.c | 13 ++++++------- 8 files changed, 31 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h index 7b8c98830101..d39ddb258a04 100644 --- a/arch/arm64/include/asm/page.h +++ b/arch/arm64/include/asm/page.h @@ -38,6 +38,4 @@ extern int pfn_valid(unsigned long); #include -#define ARCH_ZONE_DMA_BITS 30 - #endif diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 39fc69873b18..35f27b839101 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -41,6 +42,8 @@ #include #include +#define ARM64_ZONE_DMA_BITS 30 + /* * We need to be able to catch inadvertent references to memstart_addr * that occur (potentially in generic code) before arm64_memblock_init() @@ -440,8 +443,10 @@ void __init arm64_memblock_init(void) early_init_fdt_scan_reserved_mem(); - if (IS_ENABLED(CONFIG_ZONE_DMA)) - arm64_dma_phys_limit = max_zone_phys(ARCH_ZONE_DMA_BITS); + if (IS_ENABLED(CONFIG_ZONE_DMA)) { + zone_dma_bits = ARM64_ZONE_DMA_BITS; + arm64_dma_phys_limit = max_zone_phys(ARM64_ZONE_DMA_BITS); + } if (IS_ENABLED(CONFIG_ZONE_DMA32)) arm64_dma32_phys_limit = max_zone_phys(32); diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index c8bb14ff4713..f6c562acc3f8 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -329,13 +329,4 @@ struct vm_area_struct; #endif /* __ASSEMBLY__ */ #include -/* - * Allow 30-bit DMA for very limited Broadcom wifi chips on many powerbooks. - */ -#ifdef CONFIG_PPC32 -#define ARCH_ZONE_DMA_BITS 30 -#else -#define ARCH_ZONE_DMA_BITS 31 -#endif - #endif /* _ASM_POWERPC_PAGE_H */ diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index be941d382c8d..c95b7fe9f298 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include @@ -201,10 +202,10 @@ static int __init mark_nonram_nosave(void) * everything else. GFP_DMA32 page allocations automatically fall back to * ZONE_DMA. * - * By using 31-bit unconditionally, we can exploit ARCH_ZONE_DMA_BITS to - * inform the generic DMA mapping code. 32-bit only devices (if not handled - * by an IOMMU anyway) will take a first dip into ZONE_NORMAL and get - * otherwise served by ZONE_DMA. + * By using 31-bit unconditionally, we can exploit zone_dma_bits to inform the + * generic DMA mapping code. 32-bit only devices (if not handled by an IOMMU + * anyway) will take a first dip into ZONE_NORMAL and get otherwise served by + * ZONE_DMA. */ static unsigned long max_zone_pfns[MAX_NR_ZONES]; @@ -237,9 +238,18 @@ void __init paging_init(void) printk(KERN_DEBUG "Memory hole size: %ldMB\n", (long int)((top_of_ram - total_ram) >> 20)); + /* + * Allow 30-bit DMA for very limited Broadcom wifi chips on many + * powerbooks. + */ + if (IS_ENABLED(CONFIG_PPC32)) + zone_dma_bits = 30; + else + zone_dma_bits = 31; + #ifdef CONFIG_ZONE_DMA max_zone_pfns[ZONE_DMA] = min(max_low_pfn, - 1UL << (ARCH_ZONE_DMA_BITS - PAGE_SHIFT)); + 1UL << (zone_dma_bits - PAGE_SHIFT)); #endif max_zone_pfns[ZONE_NORMAL] = max_low_pfn; #ifdef CONFIG_HIGHMEM diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index 823578c6b9e2..a4d38092530a 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -177,8 +177,6 @@ static inline int devmem_is_allowed(unsigned long pfn) #define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) -#define ARCH_ZONE_DMA_BITS 31 - #include #include diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index a124f19f7b3c..f0ce22220565 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -118,6 +118,7 @@ void __init paging_init(void) sparse_memory_present_with_active_regions(MAX_NUMNODES); sparse_init(); + zone_dma_bits = 31; memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); max_zone_pfns[ZONE_DMA] = PFN_DOWN(MAX_DMA_ADDRESS); max_zone_pfns[ZONE_NORMAL] = max_low_pfn; diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index adf993a3bd58..d03af3605460 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -5,6 +5,8 @@ #include #include +extern unsigned int zone_dma_bits; + #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA #include #else diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 8402b29c280f..0b67c04e531b 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -16,12 +16,11 @@ #include /* - * Most architectures use ZONE_DMA for the first 16 Megabytes, but - * some use it for entirely different regions: + * Most architectures use ZONE_DMA for the first 16 Megabytes, but some use it + * it for entirely different regions. In that case the arch code needs to + * override the variable below for dma-direct to work properly. */ -#ifndef ARCH_ZONE_DMA_BITS -#define ARCH_ZONE_DMA_BITS 24 -#endif +unsigned int zone_dma_bits __ro_after_init = 24; static void report_addr(struct device *dev, dma_addr_t dma_addr, size_t size) { @@ -69,7 +68,7 @@ static gfp_t __dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, * Note that GFP_DMA32 and GFP_DMA are no ops without the corresponding * zones. */ - if (*phys_mask <= DMA_BIT_MASK(ARCH_ZONE_DMA_BITS)) + if (*phys_mask <= DMA_BIT_MASK(zone_dma_bits)) return GFP_DMA; if (*phys_mask <= DMA_BIT_MASK(32)) return GFP_DMA32; @@ -395,7 +394,7 @@ int dma_direct_supported(struct device *dev, u64 mask) u64 min_mask; if (IS_ENABLED(CONFIG_ZONE_DMA)) - min_mask = DMA_BIT_MASK(ARCH_ZONE_DMA_BITS); + min_mask = DMA_BIT_MASK(zone_dma_bits); else min_mask = DMA_BIT_MASK(32); -- cgit v1.2.3-71-gd317 From 73727f4dafa2df107e85753c5ab703a1f344e1f1 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Wed, 30 Oct 2019 16:43:10 +0100 Subject: livepatch: Basic API to track system state changes This is another step how to help maintaining more livepatches. One big help was the atomic replace and cumulative livepatches. These livepatches replace the already installed ones. Therefore it should be enough when each cumulative livepatch is consistent. The problems might come with shadow variables and callbacks. They might change the system behavior or state so that it is no longer safe to go back and use an older livepatch or the original kernel code. Also, a new livepatch must be able to detect changes which were made by the already installed livepatches. This is where the livepatch system state tracking gets useful. It allows to: - find whether a system state has already been modified by previous livepatches - store data needed to manipulate and restore the system state The information about the manipulated system states is stored in an array of struct klp_state. It can be searched by two new functions klp_get_state() and klp_get_prev_state(). The dependencies are going to be solved by a version field added later. The only important information is that it will be allowed to modify the same state by more non-cumulative livepatches. It is similar to allowing to modify the same function several times. The livepatch author is responsible for preventing incompatible changes. Link: http://lkml.kernel.org/r/20191030154313.13263-3-pmladek@suse.com To: Jiri Kosina Cc: Kamalesh Babulal Cc: Nicolai Stange Cc: live-patching@vger.kernel.org Cc: linux-kernel@vger.kernel.org Acked-by: Miroslav Benes Acked-by: Joe Lawrence Acked-by: Josh Poimboeuf Signed-off-by: Petr Mladek --- include/linux/livepatch.h | 15 +++++++++ kernel/livepatch/Makefile | 2 +- kernel/livepatch/state.c | 83 +++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 99 insertions(+), 1 deletion(-) create mode 100644 kernel/livepatch/state.c (limited to 'include/linux') diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 273400814020..726947338fd5 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -130,10 +130,21 @@ struct klp_object { bool patched; }; +/** + * struct klp_state - state of the system modified by the livepatch + * @id: system state identifier (non-zero) + * @data: custom data + */ +struct klp_state { + unsigned long id; + void *data; +}; + /** * struct klp_patch - patch structure for live patching * @mod: reference to the live patch module * @objs: object entries for kernel objects to be patched + * @states: system states that can get modified * @replace: replace all actively used patches * @list: list node for global list of actively used patches * @kobj: kobject for sysfs resources @@ -147,6 +158,7 @@ struct klp_patch { /* external */ struct module *mod; struct klp_object *objs; + struct klp_state *states; bool replace; /* internal */ @@ -217,6 +229,9 @@ void *klp_shadow_get_or_alloc(void *obj, unsigned long id, void klp_shadow_free(void *obj, unsigned long id, klp_shadow_dtor_t dtor); void klp_shadow_free_all(unsigned long id, klp_shadow_dtor_t dtor); +struct klp_state *klp_get_state(struct klp_patch *patch, unsigned long id); +struct klp_state *klp_get_prev_state(unsigned long id); + #else /* !CONFIG_LIVEPATCH */ static inline int klp_module_coming(struct module *mod) { return 0; } diff --git a/kernel/livepatch/Makefile b/kernel/livepatch/Makefile index cf9b5bcdb952..cf03d4bdfc66 100644 --- a/kernel/livepatch/Makefile +++ b/kernel/livepatch/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_LIVEPATCH) += livepatch.o -livepatch-objs := core.o patch.o shadow.o transition.o +livepatch-objs := core.o patch.o shadow.o state.o transition.o diff --git a/kernel/livepatch/state.c b/kernel/livepatch/state.c new file mode 100644 index 000000000000..6ab15b642c0a --- /dev/null +++ b/kernel/livepatch/state.c @@ -0,0 +1,83 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * system_state.c - State of the system modified by livepatches + * + * Copyright (C) 2019 SUSE + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include "core.h" +#include "transition.h" + +#define klp_for_each_state(patch, state) \ + for (state = patch->states; state && state->id; state++) + +/** + * klp_get_state() - get information about system state modified by + * the given patch + * @patch: livepatch that modifies the given system state + * @id: custom identifier of the modified system state + * + * Checks whether the given patch modifies the given system state. + * + * The function can be called either from pre/post (un)patch + * callbacks or from the kernel code added by the livepatch. + * + * Return: pointer to struct klp_state when found, otherwise NULL. + */ +struct klp_state *klp_get_state(struct klp_patch *patch, unsigned long id) +{ + struct klp_state *state; + + klp_for_each_state(patch, state) { + if (state->id == id) + return state; + } + + return NULL; +} +EXPORT_SYMBOL_GPL(klp_get_state); + +/** + * klp_get_prev_state() - get information about system state modified by + * the already installed livepatches + * @id: custom identifier of the modified system state + * + * Checks whether already installed livepatches modify the given + * system state. + * + * The same system state can be modified by more non-cumulative + * livepatches. It is expected that the latest livepatch has + * the most up-to-date information. + * + * The function can be called only during transition when a new + * livepatch is being enabled or when such a transition is reverted. + * It is typically called only from from pre/post (un)patch + * callbacks. + * + * Return: pointer to the latest struct klp_state from already + * installed livepatches, NULL when not found. + */ +struct klp_state *klp_get_prev_state(unsigned long id) +{ + struct klp_patch *patch; + struct klp_state *state, *last_state = NULL; + + if (WARN_ON_ONCE(!klp_transition_patch)) + return NULL; + + klp_for_each_patch(patch) { + if (patch == klp_transition_patch) + goto out; + + state = klp_get_state(patch, id); + if (state) + last_state = state; + } + +out: + return last_state; +} +EXPORT_SYMBOL_GPL(klp_get_prev_state); -- cgit v1.2.3-71-gd317 From 92c9abf5e57500ea7dc59a55273aa7850b631bda Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Wed, 30 Oct 2019 16:43:11 +0100 Subject: livepatch: Allow to distinguish different version of system state changes The atomic replace runs pre/post (un)install callbacks only from the new livepatch. There are several reasons for this: + Simplicity: clear ordering of operations, no interactions between old and new callbacks. + Reliability: only new livepatch knows what changes can already be made by older livepatches and how to take over the state. + Testing: the atomic replace can be properly tested only when a newer livepatch is available. It might be too late to fix unwanted effect of callbacks from older livepatches. It might happen that an older change is not enough and the same system state has to be modified another way. Different changes need to get distinguished by a version number added to struct klp_state. The version can also be used to prevent loading incompatible livepatches. The check is done when the livepatch is enabled. The rules are: + Any completely new system state modification is allowed. + System state modifications with the same or higher version are allowed for already modified system states. + Cumulative livepatches must handle all system state modifications from already installed livepatches. + Non-cumulative livepatches are allowed to touch already modified system states. Link: http://lkml.kernel.org/r/20191030154313.13263-4-pmladek@suse.com To: Jiri Kosina Cc: Kamalesh Babulal Cc: Nicolai Stange Cc: live-patching@vger.kernel.org Cc: linux-kernel@vger.kernel.org Acked-by: Miroslav Benes Acked-by: Joe Lawrence Acked-by: Josh Poimboeuf Signed-off-by: Petr Mladek --- include/linux/livepatch.h | 2 ++ kernel/livepatch/core.c | 8 ++++++++ kernel/livepatch/state.c | 36 ++++++++++++++++++++++++++++++++++++ kernel/livepatch/state.h | 9 +++++++++ 4 files changed, 55 insertions(+) create mode 100644 kernel/livepatch/state.h (limited to 'include/linux') diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 726947338fd5..e894e74905f3 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -133,10 +133,12 @@ struct klp_object { /** * struct klp_state - state of the system modified by the livepatch * @id: system state identifier (non-zero) + * @version: version of the change * @data: custom data */ struct klp_state { unsigned long id; + unsigned int version; void *data; }; diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 1e1d87ead55c..c3512e7e0801 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -22,6 +22,7 @@ #include #include "core.h" #include "patch.h" +#include "state.h" #include "transition.h" /* @@ -1009,6 +1010,13 @@ int klp_enable_patch(struct klp_patch *patch) mutex_lock(&klp_mutex); + if (!klp_is_patch_compatible(patch)) { + pr_err("Livepatch patch (%s) is not compatible with the already installed livepatches.\n", + patch->mod->name); + mutex_unlock(&klp_mutex); + return -EINVAL; + } + ret = klp_init_patch_early(patch); if (ret) { mutex_unlock(&klp_mutex); diff --git a/kernel/livepatch/state.c b/kernel/livepatch/state.c index 6ab15b642c0a..7ee19476de9d 100644 --- a/kernel/livepatch/state.c +++ b/kernel/livepatch/state.c @@ -9,6 +9,7 @@ #include #include "core.h" +#include "state.h" #include "transition.h" #define klp_for_each_state(patch, state) \ @@ -81,3 +82,38 @@ out: return last_state; } EXPORT_SYMBOL_GPL(klp_get_prev_state); + +/* Check if the patch is able to deal with the existing system state. */ +static bool klp_is_state_compatible(struct klp_patch *patch, + struct klp_state *old_state) +{ + struct klp_state *state; + + state = klp_get_state(patch, old_state->id); + + /* A cumulative livepatch must handle all already modified states. */ + if (!state) + return !patch->replace; + + return state->version >= old_state->version; +} + +/* + * Check that the new livepatch will not break the existing system states. + * Cumulative patches must handle all already modified states. + * Non-cumulative patches can touch already modified states. + */ +bool klp_is_patch_compatible(struct klp_patch *patch) +{ + struct klp_patch *old_patch; + struct klp_state *old_state; + + klp_for_each_patch(old_patch) { + klp_for_each_state(old_patch, old_state) { + if (!klp_is_state_compatible(patch, old_state)) + return false; + } + } + + return true; +} diff --git a/kernel/livepatch/state.h b/kernel/livepatch/state.h new file mode 100644 index 000000000000..49d9c16e8762 --- /dev/null +++ b/kernel/livepatch/state.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LIVEPATCH_STATE_H +#define _LIVEPATCH_STATE_H + +#include + +bool klp_is_patch_compatible(struct klp_patch *patch); + +#endif /* _LIVEPATCH_STATE_H */ -- cgit v1.2.3-71-gd317 From 626fb735a43ddcb7b2c58c27cb03b098acc03339 Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 30 Oct 2019 00:59:30 +0800 Subject: blk-mq: Make blk_mq_run_hw_queue() return void Since commit 97889f9ac24f ("blk-mq: remove synchronize_rcu() from blk_mq_del_queue_tag_set()"), the return value of blk_mq_run_hw_queue() is never checked, so make it return void, which very marginally simplifies the code. Reviewed-by: Bob Liu Signed-off-by: John Garry Signed-off-by: Jens Axboe --- block/blk-mq.c | 8 ++------ include/linux/blk-mq.h | 2 +- 2 files changed, 3 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index c0f3357a2050..5c9adcaa27ac 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1457,7 +1457,7 @@ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs) } EXPORT_SYMBOL(blk_mq_delay_run_hw_queue); -bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) +void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) { int srcu_idx; bool need_run; @@ -1475,12 +1475,8 @@ bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) blk_mq_hctx_has_pending(hctx); hctx_unlock(hctx, srcu_idx); - if (need_run) { + if (need_run) __blk_mq_delay_run_hw_queue(hctx, async, 0); - return true; - } - - return false; } EXPORT_SYMBOL(blk_mq_run_hw_queue); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 4919d22e1aff..dc03e059fdff 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -502,7 +502,7 @@ void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); void blk_mq_quiesce_queue(struct request_queue *q); void blk_mq_unquiesce_queue(struct request_queue *q); void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); -bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); +void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_run_hw_queues(struct request_queue *q, bool async); void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv); -- cgit v1.2.3-71-gd317 From 25937580a5065d6fbd92d9c8ebd47145ad80052e Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 31 Oct 2019 10:59:44 +0100 Subject: ata: define AC_ERR_OK Since we will return enum ata_completion_errors from qc_prep in the next patch, let's define AC_ERR_OK to mark the OK status. Signed-off-by: Jiri Slaby Cc: Jens Axboe Cc: linux-ide@vger.kernel.org Signed-off-by: Jens Axboe --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 207e7ee764ce..b63ce4ebcd66 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -484,6 +484,7 @@ enum hsm_task_states { }; enum ata_completion_errors { + AC_ERR_OK = 0, /* no error */ AC_ERR_DEV = (1 << 0), /* device reported error */ AC_ERR_HSM = (1 << 1), /* host state machine violation */ AC_ERR_TIMEOUT = (1 << 2), /* timeout */ -- cgit v1.2.3-71-gd317 From 95364f36701e62dd50eee91e1303187fd1a9f567 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 31 Oct 2019 10:59:45 +0100 Subject: ata: make qc_prep return ata_completion_errors In case a driver wants to return an error from qc_prep, return enum ata_completion_errors. sata_mv is one of those drivers -- see the next patch. Other drivers return the newly defined AC_ERR_OK. [v2] use enum ata_completion_errors and AC_ERR_OK. Signed-off-by: Jiri Slaby Cc: Jens Axboe Cc: linux-ide@vger.kernel.org Signed-off-by: Jens Axboe --- Documentation/driver-api/libata.rst | 2 +- drivers/ata/acard-ahci.c | 6 ++++-- drivers/ata/libahci.c | 6 ++++-- drivers/ata/libata-core.c | 9 +++++++-- drivers/ata/libata-sff.c | 12 ++++++++---- drivers/ata/pata_macio.c | 6 ++++-- drivers/ata/pata_pxa.c | 8 +++++--- drivers/ata/pdc_adma.c | 7 ++++--- drivers/ata/sata_fsl.c | 4 +++- drivers/ata/sata_inic162x.c | 4 +++- drivers/ata/sata_mv.c | 26 +++++++++++++++----------- drivers/ata/sata_nv.c | 18 +++++++++++------- drivers/ata/sata_promise.c | 6 ++++-- drivers/ata/sata_qstor.c | 8 +++++--- drivers/ata/sata_rcar.c | 6 ++++-- drivers/ata/sata_sil.c | 8 +++++--- drivers/ata/sata_sil24.c | 6 ++++-- drivers/ata/sata_sx4.c | 6 ++++-- include/linux/libata.h | 12 ++++++------ 19 files changed, 101 insertions(+), 59 deletions(-) (limited to 'include/linux') diff --git a/Documentation/driver-api/libata.rst b/Documentation/driver-api/libata.rst index c2ee38098e85..207f0d24de69 100644 --- a/Documentation/driver-api/libata.rst +++ b/Documentation/driver-api/libata.rst @@ -250,7 +250,7 @@ High-level taskfile hooks :: - void (*qc_prep) (struct ata_queued_cmd *qc); + enum ata_completion_errors (*qc_prep) (struct ata_queued_cmd *qc); int (*qc_issue) (struct ata_queued_cmd *qc); diff --git a/drivers/ata/acard-ahci.c b/drivers/ata/acard-ahci.c index 753985c01517..46dc54d18f0b 100644 --- a/drivers/ata/acard-ahci.c +++ b/drivers/ata/acard-ahci.c @@ -56,7 +56,7 @@ struct acard_sg { __le32 size; /* bit 31 (EOT) max==0x10000 (64k) */ }; -static void acard_ahci_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors acard_ahci_qc_prep(struct ata_queued_cmd *qc); static bool acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc); static int acard_ahci_port_start(struct ata_port *ap); static int acard_ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); @@ -210,7 +210,7 @@ static unsigned int acard_ahci_fill_sg(struct ata_queued_cmd *qc, void *cmd_tbl) return si; } -static void acard_ahci_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors acard_ahci_qc_prep(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct ahci_port_priv *pp = ap->private_data; @@ -248,6 +248,8 @@ static void acard_ahci_qc_prep(struct ata_queued_cmd *qc) opts |= AHCI_CMD_ATAPI | AHCI_CMD_PREFETCH; ahci_fill_cmd_slot(pp, qc->hw_tag, opts); + + return AC_ERR_OK; } static bool acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc) diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index bff369d9a1a7..ea5bf5f4cbed 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -57,7 +57,7 @@ static int ahci_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val); static bool ahci_qc_fill_rtf(struct ata_queued_cmd *qc); static int ahci_port_start(struct ata_port *ap); static void ahci_port_stop(struct ata_port *ap); -static void ahci_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors ahci_qc_prep(struct ata_queued_cmd *qc); static int ahci_pmp_qc_defer(struct ata_queued_cmd *qc); static void ahci_freeze(struct ata_port *ap); static void ahci_thaw(struct ata_port *ap); @@ -1624,7 +1624,7 @@ static int ahci_pmp_qc_defer(struct ata_queued_cmd *qc) return sata_pmp_qc_defer_cmd_switch(qc); } -static void ahci_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors ahci_qc_prep(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct ahci_port_priv *pp = ap->private_data; @@ -1660,6 +1660,8 @@ static void ahci_qc_prep(struct ata_queued_cmd *qc) opts |= AHCI_CMD_ATAPI | AHCI_CMD_PREFETCH; ahci_fill_cmd_slot(pp, qc->hw_tag, opts); + + return AC_ERR_OK; } static void ahci_fbs_dec_intr(struct ata_port *ap) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 74c9b3032d46..e9017c570bc5 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4980,7 +4980,10 @@ int ata_std_qc_defer(struct ata_queued_cmd *qc) return ATA_DEFER_LINK; } -void ata_noop_qc_prep(struct ata_queued_cmd *qc) { } +enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc) +{ + return AC_ERR_OK; +} /** * ata_sg_init - Associate command with scatter-gather table. @@ -5443,7 +5446,9 @@ void ata_qc_issue(struct ata_queued_cmd *qc) return; } - ap->ops->qc_prep(qc); + qc->err_mask |= ap->ops->qc_prep(qc); + if (unlikely(qc->err_mask)) + goto err; trace_ata_qc_issue(qc); qc->err_mask |= ap->ops->qc_issue(qc); if (unlikely(qc->err_mask)) diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index 4ed682da52ae..038db94216a9 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -2679,12 +2679,14 @@ static void ata_bmdma_fill_sg_dumb(struct ata_queued_cmd *qc) * LOCKING: * spin_lock_irqsave(host lock) */ -void ata_bmdma_qc_prep(struct ata_queued_cmd *qc) +enum ata_completion_errors ata_bmdma_qc_prep(struct ata_queued_cmd *qc) { if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; ata_bmdma_fill_sg(qc); + + return AC_ERR_OK; } EXPORT_SYMBOL_GPL(ata_bmdma_qc_prep); @@ -2697,12 +2699,14 @@ EXPORT_SYMBOL_GPL(ata_bmdma_qc_prep); * LOCKING: * spin_lock_irqsave(host lock) */ -void ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc) +enum ata_completion_errors ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc) { if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; ata_bmdma_fill_sg_dumb(qc); + + return AC_ERR_OK; } EXPORT_SYMBOL_GPL(ata_bmdma_dumb_qc_prep); diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c index 57f2ec71cfc3..1bfd0154dad5 100644 --- a/drivers/ata/pata_macio.c +++ b/drivers/ata/pata_macio.c @@ -510,7 +510,7 @@ static int pata_macio_cable_detect(struct ata_port *ap) return ATA_CBL_PATA40; } -static void pata_macio_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors pata_macio_qc_prep(struct ata_queued_cmd *qc) { unsigned int write = (qc->tf.flags & ATA_TFLAG_WRITE); struct ata_port *ap = qc->ap; @@ -523,7 +523,7 @@ static void pata_macio_qc_prep(struct ata_queued_cmd *qc) __func__, qc, qc->flags, write, qc->dev->devno); if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; table = (struct dbdma_cmd *) priv->dma_table_cpu; @@ -568,6 +568,8 @@ static void pata_macio_qc_prep(struct ata_queued_cmd *qc) table->command = cpu_to_le16(DBDMA_STOP); dev_dbgdma(priv->dev, "%s: %d DMA list entries\n", __func__, pi); + + return AC_ERR_OK; } diff --git a/drivers/ata/pata_pxa.c b/drivers/ata/pata_pxa.c index 4afcb8e63e21..41430f79663c 100644 --- a/drivers/ata/pata_pxa.c +++ b/drivers/ata/pata_pxa.c @@ -44,25 +44,27 @@ static void pxa_ata_dma_irq(void *d) /* * Prepare taskfile for submission. */ -static void pxa_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors pxa_qc_prep(struct ata_queued_cmd *qc) { struct pata_pxa_data *pd = qc->ap->private_data; struct dma_async_tx_descriptor *tx; enum dma_transfer_direction dir; if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; dir = (qc->dma_dir == DMA_TO_DEVICE ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM); tx = dmaengine_prep_slave_sg(pd->dma_chan, qc->sg, qc->n_elem, dir, DMA_PREP_INTERRUPT); if (!tx) { ata_dev_err(qc->dev, "prep_slave_sg() failed\n"); - return; + return AC_ERR_OK; } tx->callback = pxa_ata_dma_irq; tx->callback_param = pd; pd->dma_cookie = dmaengine_submit(tx); + + return AC_ERR_OK; } /* diff --git a/drivers/ata/pdc_adma.c b/drivers/ata/pdc_adma.c index cb490531b62e..5db55e1e2a61 100644 --- a/drivers/ata/pdc_adma.c +++ b/drivers/ata/pdc_adma.c @@ -116,7 +116,7 @@ static int adma_ata_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); static int adma_port_start(struct ata_port *ap); static void adma_port_stop(struct ata_port *ap); -static void adma_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors adma_qc_prep(struct ata_queued_cmd *qc); static unsigned int adma_qc_issue(struct ata_queued_cmd *qc); static int adma_check_atapi_dma(struct ata_queued_cmd *qc); static void adma_freeze(struct ata_port *ap); @@ -295,7 +295,7 @@ static int adma_fill_sg(struct ata_queued_cmd *qc) return i; } -static void adma_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors adma_qc_prep(struct ata_queued_cmd *qc) { struct adma_port_priv *pp = qc->ap->private_data; u8 *buf = pp->pkt; @@ -306,7 +306,7 @@ static void adma_qc_prep(struct ata_queued_cmd *qc) adma_enter_reg_mode(qc->ap); if (qc->tf.protocol != ATA_PROT_DMA) - return; + return AC_ERR_OK; buf[i++] = 0; /* Response flags */ buf[i++] = 0; /* reserved */ @@ -371,6 +371,7 @@ static void adma_qc_prep(struct ata_queued_cmd *qc) printk("%s\n", obuf); } #endif + return AC_ERR_OK; } static inline void adma_packet_start(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index 8e9cb198fcd1..9239615d8a04 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -502,7 +502,7 @@ static unsigned int sata_fsl_fill_sg(struct ata_queued_cmd *qc, void *cmd_desc, return num_prde; } -static void sata_fsl_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors sata_fsl_qc_prep(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct sata_fsl_port_priv *pp = ap->private_data; @@ -548,6 +548,8 @@ static void sata_fsl_qc_prep(struct ata_queued_cmd *qc) VPRINTK("SATA FSL : xx_qc_prep, di = 0x%x, ttl = %d, num_prde = %d\n", desc_info, ttl_dwords, num_prde); + + return AC_ERR_OK; } static unsigned int sata_fsl_qc_issue(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_inic162x.c b/drivers/ata/sata_inic162x.c index 7f99e23bff88..a6b76cc12a66 100644 --- a/drivers/ata/sata_inic162x.c +++ b/drivers/ata/sata_inic162x.c @@ -478,7 +478,7 @@ static void inic_fill_sg(struct inic_prd *prd, struct ata_queued_cmd *qc) prd[-1].flags |= PRD_END; } -static void inic_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors inic_qc_prep(struct ata_queued_cmd *qc) { struct inic_port_priv *pp = qc->ap->private_data; struct inic_pkt *pkt = pp->pkt; @@ -538,6 +538,8 @@ static void inic_qc_prep(struct ata_queued_cmd *qc) inic_fill_sg(prd, qc); pp->cpb_tbl[0] = pp->pkt_dma; + + return AC_ERR_OK; } static unsigned int inic_qc_issue(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index ad385a113391..5d5c8936a590 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -592,8 +592,8 @@ static int mv5_scr_write(struct ata_link *link, unsigned int sc_reg_in, u32 val) static int mv_port_start(struct ata_port *ap); static void mv_port_stop(struct ata_port *ap); static int mv_qc_defer(struct ata_queued_cmd *qc); -static void mv_qc_prep(struct ata_queued_cmd *qc); -static void mv_qc_prep_iie(struct ata_queued_cmd *qc); +static enum ata_completion_errors mv_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors mv_qc_prep_iie(struct ata_queued_cmd *qc); static unsigned int mv_qc_issue(struct ata_queued_cmd *qc); static int mv_hardreset(struct ata_link *link, unsigned int *class, unsigned long deadline); @@ -2031,7 +2031,7 @@ static void mv_rw_multi_errata_sata24(struct ata_queued_cmd *qc) * LOCKING: * Inherited from caller. */ -static void mv_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors mv_qc_prep(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct mv_port_priv *pp = ap->private_data; @@ -2043,15 +2043,15 @@ static void mv_qc_prep(struct ata_queued_cmd *qc) switch (tf->protocol) { case ATA_PROT_DMA: if (tf->command == ATA_CMD_DSM) - return; + return AC_ERR_OK; /* fall-thru */ case ATA_PROT_NCQ: break; /* continue below */ case ATA_PROT_PIO: mv_rw_multi_errata_sata24(qc); - return; + return AC_ERR_OK; default: - return; + return AC_ERR_OK; } /* Fill in command request block @@ -2116,8 +2116,10 @@ static void mv_qc_prep(struct ata_queued_cmd *qc) mv_crqb_pack_cmd(cw++, tf->command, ATA_REG_CMD, 1); /* last */ if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; mv_fill_sg(qc); + + return AC_ERR_OK; } /** @@ -2132,7 +2134,7 @@ static void mv_qc_prep(struct ata_queued_cmd *qc) * LOCKING: * Inherited from caller. */ -static void mv_qc_prep_iie(struct ata_queued_cmd *qc) +static enum ata_completion_errors mv_qc_prep_iie(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct mv_port_priv *pp = ap->private_data; @@ -2143,9 +2145,9 @@ static void mv_qc_prep_iie(struct ata_queued_cmd *qc) if ((tf->protocol != ATA_PROT_DMA) && (tf->protocol != ATA_PROT_NCQ)) - return; + return AC_ERR_OK; if (tf->command == ATA_CMD_DSM) - return; /* use bmdma for this */ + return AC_ERR_OK; /* use bmdma for this */ /* Fill in Gen IIE command request block */ if (!(tf->flags & ATA_TFLAG_WRITE)) @@ -2186,8 +2188,10 @@ static void mv_qc_prep_iie(struct ata_queued_cmd *qc) ); if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; mv_fill_sg(qc); + + return AC_ERR_OK; } /** diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c index 56946012d113..65ec8dff1c51 100644 --- a/drivers/ata/sata_nv.c +++ b/drivers/ata/sata_nv.c @@ -297,7 +297,7 @@ static void nv_ck804_freeze(struct ata_port *ap); static void nv_ck804_thaw(struct ata_port *ap); static int nv_adma_slave_config(struct scsi_device *sdev); static int nv_adma_check_atapi_dma(struct ata_queued_cmd *qc); -static void nv_adma_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors nv_adma_qc_prep(struct ata_queued_cmd *qc); static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc); static irqreturn_t nv_adma_interrupt(int irq, void *dev_instance); static void nv_adma_irq_clear(struct ata_port *ap); @@ -319,7 +319,7 @@ static void nv_mcp55_freeze(struct ata_port *ap); static void nv_swncq_error_handler(struct ata_port *ap); static int nv_swncq_slave_config(struct scsi_device *sdev); static int nv_swncq_port_start(struct ata_port *ap); -static void nv_swncq_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors nv_swncq_qc_prep(struct ata_queued_cmd *qc); static void nv_swncq_fill_sg(struct ata_queued_cmd *qc); static unsigned int nv_swncq_qc_issue(struct ata_queued_cmd *qc); static void nv_swncq_irq_clear(struct ata_port *ap, u16 fis); @@ -1344,7 +1344,7 @@ static int nv_adma_use_reg_mode(struct ata_queued_cmd *qc) return 1; } -static void nv_adma_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors nv_adma_qc_prep(struct ata_queued_cmd *qc) { struct nv_adma_port_priv *pp = qc->ap->private_data; struct nv_adma_cpb *cpb = &pp->cpb[qc->hw_tag]; @@ -1356,7 +1356,7 @@ static void nv_adma_qc_prep(struct ata_queued_cmd *qc) (qc->flags & ATA_QCFLAG_DMAMAP)); nv_adma_register_mode(qc->ap); ata_bmdma_qc_prep(qc); - return; + return AC_ERR_OK; } cpb->resp_flags = NV_CPB_RESP_DONE; @@ -1388,6 +1388,8 @@ static void nv_adma_qc_prep(struct ata_queued_cmd *qc) cpb->ctl_flags = ctl_flags; wmb(); cpb->resp_flags = 0; + + return AC_ERR_OK; } static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc) @@ -1950,17 +1952,19 @@ static int nv_swncq_port_start(struct ata_port *ap) return 0; } -static void nv_swncq_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors nv_swncq_qc_prep(struct ata_queued_cmd *qc) { if (qc->tf.protocol != ATA_PROT_NCQ) { ata_bmdma_qc_prep(qc); - return; + return AC_ERR_OK; } if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; nv_swncq_fill_sg(qc); + + return AC_ERR_OK; } static void nv_swncq_fill_sg(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_promise.c b/drivers/ata/sata_promise.c index 5fd464765ddc..c451d7d1c817 100644 --- a/drivers/ata/sata_promise.c +++ b/drivers/ata/sata_promise.c @@ -139,7 +139,7 @@ static int pdc_sata_scr_write(struct ata_link *link, unsigned int sc_reg, u32 va static int pdc_ata_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); static int pdc_common_port_start(struct ata_port *ap); static int pdc_sata_port_start(struct ata_port *ap); -static void pdc_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors pdc_qc_prep(struct ata_queued_cmd *qc); static void pdc_tf_load_mmio(struct ata_port *ap, const struct ata_taskfile *tf); static void pdc_exec_command_mmio(struct ata_port *ap, const struct ata_taskfile *tf); static int pdc_check_atapi_dma(struct ata_queued_cmd *qc); @@ -633,7 +633,7 @@ static void pdc_fill_sg(struct ata_queued_cmd *qc) prd[idx - 1].flags_len |= cpu_to_le32(ATA_PRD_EOT); } -static void pdc_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors pdc_qc_prep(struct ata_queued_cmd *qc) { struct pdc_port_priv *pp = qc->ap->private_data; unsigned int i; @@ -665,6 +665,8 @@ static void pdc_qc_prep(struct ata_queued_cmd *qc) default: break; } + + return AC_ERR_OK; } static int pdc_is_sataii_tx4(unsigned long flags) diff --git a/drivers/ata/sata_qstor.c b/drivers/ata/sata_qstor.c index c53c5a47204d..ef00ab644afb 100644 --- a/drivers/ata/sata_qstor.c +++ b/drivers/ata/sata_qstor.c @@ -100,7 +100,7 @@ static int qs_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val); static int qs_ata_init_one(struct pci_dev *pdev, const struct pci_device_id *ent); static int qs_port_start(struct ata_port *ap); static void qs_host_stop(struct ata_host *host); -static void qs_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors qs_qc_prep(struct ata_queued_cmd *qc); static unsigned int qs_qc_issue(struct ata_queued_cmd *qc); static int qs_check_atapi_dma(struct ata_queued_cmd *qc); static void qs_freeze(struct ata_port *ap); @@ -260,7 +260,7 @@ static unsigned int qs_fill_sg(struct ata_queued_cmd *qc) return si; } -static void qs_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors qs_qc_prep(struct ata_queued_cmd *qc) { struct qs_port_priv *pp = qc->ap->private_data; u8 dflags = QS_DF_PORD, *buf = pp->pkt; @@ -272,7 +272,7 @@ static void qs_qc_prep(struct ata_queued_cmd *qc) qs_enter_reg_mode(qc->ap); if (qc->tf.protocol != ATA_PROT_DMA) - return; + return AC_ERR_OK; nelem = qs_fill_sg(qc); @@ -295,6 +295,8 @@ static void qs_qc_prep(struct ata_queued_cmd *qc) /* frame information structure (FIS) */ ata_tf_to_fis(&qc->tf, 0, 1, &buf[32]); + + return AC_ERR_OK; } static inline void qs_packet_start(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c index 3495e1733a8e..980aacdbcf3b 100644 --- a/drivers/ata/sata_rcar.c +++ b/drivers/ata/sata_rcar.c @@ -550,12 +550,14 @@ static void sata_rcar_bmdma_fill_sg(struct ata_queued_cmd *qc) prd[si - 1].addr |= cpu_to_le32(SATA_RCAR_DTEND); } -static void sata_rcar_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors sata_rcar_qc_prep(struct ata_queued_cmd *qc) { if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; sata_rcar_bmdma_fill_sg(qc); + + return AC_ERR_OK; } static void sata_rcar_bmdma_setup(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c index e6fbae2f645a..75321f1ceba5 100644 --- a/drivers/ata/sata_sil.c +++ b/drivers/ata/sata_sil.c @@ -103,7 +103,7 @@ static void sil_dev_config(struct ata_device *dev); static int sil_scr_read(struct ata_link *link, unsigned int sc_reg, u32 *val); static int sil_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val); static int sil_set_mode(struct ata_link *link, struct ata_device **r_failed); -static void sil_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors sil_qc_prep(struct ata_queued_cmd *qc); static void sil_bmdma_setup(struct ata_queued_cmd *qc); static void sil_bmdma_start(struct ata_queued_cmd *qc); static void sil_bmdma_stop(struct ata_queued_cmd *qc); @@ -317,12 +317,14 @@ static void sil_fill_sg(struct ata_queued_cmd *qc) last_prd->flags_len |= cpu_to_le32(ATA_PRD_EOT); } -static void sil_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors sil_qc_prep(struct ata_queued_cmd *qc) { if (!(qc->flags & ATA_QCFLAG_DMAMAP)) - return; + return AC_ERR_OK; sil_fill_sg(qc); + + return AC_ERR_OK; } static unsigned char sil_get_device_cache_line(struct pci_dev *pdev) diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c index 7bef82de53ca..560070d4f1d0 100644 --- a/drivers/ata/sata_sil24.c +++ b/drivers/ata/sata_sil24.c @@ -326,7 +326,7 @@ static void sil24_dev_config(struct ata_device *dev); static int sil24_scr_read(struct ata_link *link, unsigned sc_reg, u32 *val); static int sil24_scr_write(struct ata_link *link, unsigned sc_reg, u32 val); static int sil24_qc_defer(struct ata_queued_cmd *qc); -static void sil24_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors sil24_qc_prep(struct ata_queued_cmd *qc); static unsigned int sil24_qc_issue(struct ata_queued_cmd *qc); static bool sil24_qc_fill_rtf(struct ata_queued_cmd *qc); static void sil24_pmp_attach(struct ata_port *ap); @@ -830,7 +830,7 @@ static int sil24_qc_defer(struct ata_queued_cmd *qc) return ata_std_qc_defer(qc); } -static void sil24_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors sil24_qc_prep(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct sil24_port_priv *pp = ap->private_data; @@ -874,6 +874,8 @@ static void sil24_qc_prep(struct ata_queued_cmd *qc) if (qc->flags & ATA_QCFLAG_DMAMAP) sil24_fill_sg(qc, sge); + + return AC_ERR_OK; } static unsigned int sil24_qc_issue(struct ata_queued_cmd *qc) diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c index 2277ba0c9c7f..2c7b30c5ea3d 100644 --- a/drivers/ata/sata_sx4.c +++ b/drivers/ata/sata_sx4.c @@ -202,7 +202,7 @@ static void pdc_error_handler(struct ata_port *ap); static void pdc_freeze(struct ata_port *ap); static void pdc_thaw(struct ata_port *ap); static int pdc_port_start(struct ata_port *ap); -static void pdc20621_qc_prep(struct ata_queued_cmd *qc); +static enum ata_completion_errors pdc20621_qc_prep(struct ata_queued_cmd *qc); static void pdc_tf_load_mmio(struct ata_port *ap, const struct ata_taskfile *tf); static void pdc_exec_command_mmio(struct ata_port *ap, const struct ata_taskfile *tf); static unsigned int pdc20621_dimm_init(struct ata_host *host); @@ -530,7 +530,7 @@ static void pdc20621_nodata_prep(struct ata_queued_cmd *qc) VPRINTK("ata pkt buf ofs %u, mmio copied\n", i); } -static void pdc20621_qc_prep(struct ata_queued_cmd *qc) +static enum ata_completion_errors pdc20621_qc_prep(struct ata_queued_cmd *qc) { switch (qc->tf.protocol) { case ATA_PROT_DMA: @@ -542,6 +542,8 @@ static void pdc20621_qc_prep(struct ata_queued_cmd *qc) default: break; } + + return AC_ERR_OK; } static void __pdc20621_push_hdma(struct ata_queued_cmd *qc, diff --git a/include/linux/libata.h b/include/linux/libata.h index b63ce4ebcd66..d3bbfddf616a 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -892,9 +892,9 @@ struct ata_port_operations { /* * Command execution */ - int (*qc_defer)(struct ata_queued_cmd *qc); - int (*check_atapi_dma)(struct ata_queued_cmd *qc); - void (*qc_prep)(struct ata_queued_cmd *qc); + int (*qc_defer)(struct ata_queued_cmd *qc); + int (*check_atapi_dma)(struct ata_queued_cmd *qc); + enum ata_completion_errors (*qc_prep)(struct ata_queued_cmd *qc); unsigned int (*qc_issue)(struct ata_queued_cmd *qc); bool (*qc_fill_rtf)(struct ata_queued_cmd *qc); @@ -1162,7 +1162,7 @@ extern int ata_xfer_mode2shift(unsigned long xfer_mode); extern const char *ata_mode_string(unsigned long xfer_mask); extern unsigned long ata_id_xfermask(const u16 *id); extern int ata_std_qc_defer(struct ata_queued_cmd *qc); -extern void ata_noop_qc_prep(struct ata_queued_cmd *qc); +extern enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc); extern void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg, unsigned int n_elem); extern unsigned int ata_dev_classify(const struct ata_taskfile *tf); @@ -1894,9 +1894,9 @@ extern const struct ata_port_operations ata_bmdma_port_ops; .sg_tablesize = LIBATA_MAX_PRD, \ .dma_boundary = ATA_DMA_BOUNDARY -extern void ata_bmdma_qc_prep(struct ata_queued_cmd *qc); +extern enum ata_completion_errors ata_bmdma_qc_prep(struct ata_queued_cmd *qc); extern unsigned int ata_bmdma_qc_issue(struct ata_queued_cmd *qc); -extern void ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc); +extern enum ata_completion_errors ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc); extern unsigned int ata_bmdma_port_intr(struct ata_port *ap, struct ata_queued_cmd *qc); extern irqreturn_t ata_bmdma_interrupt(int irq, void *dev_instance); -- cgit v1.2.3-71-gd317 From e53a9d26cf80565cfb7172fc52a0dfac73613a0f Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Mon, 28 Oct 2019 23:35:30 +0000 Subject: IB/mlx5: Introduce and use mlx5_core_is_vf() Instead of deciding a given device is virtual function or not based on a device is PF or not, use already defined MLX5_COREDEV_VF by introducing an helper API mlx5_core_is_vf(). This enables to clearly identify PF, VF and non virtual functions. Signed-off-by: Parav Pandit Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/main.c | 2 +- include/linux/mlx5/driver.h | 5 +++++ 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 831539419c30..8343a740c91e 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -1031,7 +1031,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, if (MLX5_CAP_GEN(mdev, cd)) props->device_cap_flags |= IB_DEVICE_CROSS_CHANNEL; - if (!mlx5_core_is_pf(mdev)) + if (mlx5_core_is_vf(mdev)) props->device_cap_flags |= IB_DEVICE_VIRTUAL_FUNCTION; if (mlx5_ib_port_link_layer(ibdev, 1) == diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 3e80f03a387f..7b4801e96feb 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1121,6 +1121,11 @@ static inline bool mlx5_core_is_pf(const struct mlx5_core_dev *dev) return dev->coredev_type == MLX5_COREDEV_PF; } +static inline bool mlx5_core_is_vf(const struct mlx5_core_dev *dev) +{ + return dev->coredev_type == MLX5_COREDEV_VF; +} + static inline bool mlx5_core_is_ecpf(struct mlx5_core_dev *dev) { return dev->caps.embedded_cpu; -- cgit v1.2.3-71-gd317 From d817991cc7486ab83f6c7188b0bc80eebee872f6 Mon Sep 17 00:00:00 2001 From: Björn Töpel Date: Fri, 1 Nov 2019 12:03:46 +0100 Subject: xsk: Restructure/inline XSKMAP lookup/redirect/flush MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In this commit the XSKMAP entry lookup function used by the XDP redirect code is moved from the xskmap.c file to the xdp_sock.h header, so the lookup can be inlined from, e.g., the bpf_xdp_redirect_map() function. Further the __xsk_map_redirect() and __xsk_map_flush() is moved to the xsk.c, which lets the compiler inline the xsk_rcv() and xsk_flush() functions. Finally, all the XDP socket functions were moved from linux/bpf.h to net/xdp_sock.h, where most of the XDP sockets functions are anyway. This yields a ~2% performance boost for the xdpsock "rx_drop" scenario. Signed-off-by: Björn Töpel Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20191101110346.15004-4-bjorn.topel@gmail.com --- include/linux/bpf.h | 25 ------------------------- include/net/xdp_sock.h | 51 ++++++++++++++++++++++++++++++++++++++------------ kernel/bpf/xskmap.c | 48 ----------------------------------------------- net/xdp/xsk.c | 33 ++++++++++++++++++++++++++++++-- 4 files changed, 70 insertions(+), 87 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 80158cff44bd..7c7f518811a6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1009,31 +1009,6 @@ static inline int sock_map_get_from_fd(const union bpf_attr *attr, } #endif -#if defined(CONFIG_XDP_SOCKETS) -struct xdp_sock; -struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key); -int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, - struct xdp_sock *xs); -void __xsk_map_flush(struct bpf_map *map); -#else -struct xdp_sock; -static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, - u32 key) -{ - return NULL; -} - -static inline int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, - struct xdp_sock *xs) -{ - return -EOPNOTSUPP; -} - -static inline void __xsk_map_flush(struct bpf_map *map) -{ -} -#endif - #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) void bpf_sk_reuseport_detach(struct sock *sk); int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index c9398ce7960f..e3780e4b74e1 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -69,7 +69,14 @@ struct xdp_umem { /* Nodes are linked in the struct xdp_sock map_list field, and used to * track which maps a certain socket reside in. */ -struct xsk_map; + +struct xsk_map { + struct bpf_map map; + struct list_head __percpu *flush_list; + spinlock_t lock; /* Synchronize map updates */ + struct xdp_sock *xsk_map[]; +}; + struct xsk_map_node { struct list_head node; struct xsk_map *map; @@ -109,8 +116,6 @@ struct xdp_sock { struct xdp_buff; #ifdef CONFIG_XDP_SOCKETS int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp); -int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp); -void xsk_flush(struct xdp_sock *xs); bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs); /* Used from netdev driver */ bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt); @@ -134,6 +139,22 @@ void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, struct xdp_sock **map_entry); int xsk_map_inc(struct xsk_map *map); void xsk_map_put(struct xsk_map *map); +int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, + struct xdp_sock *xs); +void __xsk_map_flush(struct bpf_map *map); + +static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, + u32 key) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + struct xdp_sock *xs; + + if (key >= map->max_entries) + return NULL; + + xs = READ_ONCE(m->xsk_map[key]); + return xs; +} static inline u64 xsk_umem_extract_addr(u64 addr) { @@ -224,15 +245,6 @@ static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) return -ENOTSUPP; } -static inline int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) -{ - return -ENOTSUPP; -} - -static inline void xsk_flush(struct xdp_sock *xs) -{ -} - static inline bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs) { return false; @@ -357,6 +369,21 @@ static inline u64 xsk_umem_adjust_offset(struct xdp_umem *umem, u64 handle, return 0; } +static inline int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, + struct xdp_sock *xs) +{ + return -EOPNOTSUPP; +} + +static inline void __xsk_map_flush(struct bpf_map *map) +{ +} + +static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, + u32 key) +{ + return NULL; +} #endif /* CONFIG_XDP_SOCKETS */ #endif /* _LINUX_XDP_SOCK_H */ diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c index 554939f78b83..da16c30868f3 100644 --- a/kernel/bpf/xskmap.c +++ b/kernel/bpf/xskmap.c @@ -9,13 +9,6 @@ #include #include -struct xsk_map { - struct bpf_map map; - struct list_head __percpu *flush_list; - spinlock_t lock; /* Synchronize map updates */ - struct xdp_sock *xsk_map[]; -}; - int xsk_map_inc(struct xsk_map *map) { struct bpf_map *m = &map->map; @@ -151,18 +144,6 @@ static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key) return 0; } -struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key) -{ - struct xsk_map *m = container_of(map, struct xsk_map, map); - struct xdp_sock *xs; - - if (key >= map->max_entries) - return NULL; - - xs = READ_ONCE(m->xsk_map[key]); - return xs; -} - static u32 xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { const int ret = BPF_REG_0, mp = BPF_REG_1, index = BPF_REG_2; @@ -179,35 +160,6 @@ static u32 xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) return insn - insn_buf; } -int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, - struct xdp_sock *xs) -{ - struct xsk_map *m = container_of(map, struct xsk_map, map); - struct list_head *flush_list = this_cpu_ptr(m->flush_list); - int err; - - err = xsk_rcv(xs, xdp); - if (err) - return err; - - if (!xs->flush_node.prev) - list_add(&xs->flush_node, flush_list); - - return 0; -} - -void __xsk_map_flush(struct bpf_map *map) -{ - struct xsk_map *m = container_of(map, struct xsk_map, map); - struct list_head *flush_list = this_cpu_ptr(m->flush_list); - struct xdp_sock *xs, *tmp; - - list_for_each_entry_safe(xs, tmp, flush_list, flush_node) { - xsk_flush(xs); - __list_del_clearprev(&xs->flush_node); - } -} - static void *xsk_map_lookup_elem(struct bpf_map *map, void *key) { WARN_ON_ONCE(!rcu_read_lock_held()); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 9044073fbf22..6040bc2b0088 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -196,7 +196,7 @@ static bool xsk_is_bound(struct xdp_sock *xs) return false; } -int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) +static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) { u32 len; @@ -212,7 +212,7 @@ int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) __xsk_rcv_zc(xs, xdp, len) : __xsk_rcv(xs, xdp, len); } -void xsk_flush(struct xdp_sock *xs) +static void xsk_flush(struct xdp_sock *xs) { xskq_produce_flush_desc(xs->rx); xs->sk.sk_data_ready(&xs->sk); @@ -264,6 +264,35 @@ out_unlock: return err; } +int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, + struct xdp_sock *xs) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + struct list_head *flush_list = this_cpu_ptr(m->flush_list); + int err; + + err = xsk_rcv(xs, xdp); + if (err) + return err; + + if (!xs->flush_node.prev) + list_add(&xs->flush_node, flush_list); + + return 0; +} + +void __xsk_map_flush(struct bpf_map *map) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + struct list_head *flush_list = this_cpu_ptr(m->flush_list); + struct xdp_sock *xs, *tmp; + + list_for_each_entry_safe(xs, tmp, flush_list, flush_node) { + xsk_flush(xs); + __list_del_clearprev(&xs->flush_node); + } +} + void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries) { xskq_produce_flush_addr_n(umem->cq, nb_entries); -- cgit v1.2.3-71-gd317 From 05ef983e0d65a31b370a4e1b93c1efd490ae778f Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Mon, 28 Oct 2019 15:00:22 -0700 Subject: driver core: Add device link support for SYNC_STATE_ONLY flag Parent devices might need to create "proxy" device links from themselves to supplier devices to make sure the supplier devices don't get a sync_state() before the child consumer devices get a chance to add device links to the supplier devices. However, the parent device has no real dependency on the supplier device and probing, suspend/resume or runtime PM don't need to be affected by the supplier device. To capture these cases, create a SYNC_STATE_ONLY device link flag that only affects sync_state() behavior and doesn't affect probing, suspend/resume or runtime PM. Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20191028220027.251605-2-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 50 +++++++++++++++++++++++++++++++++++++++++--------- include/linux/device.h | 2 ++ 2 files changed, 43 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index 7ea665a97da2..17ed054c4132 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -131,6 +131,9 @@ static int device_is_dependent(struct device *dev, void *target) return ret; list_for_each_entry(link, &dev->links.consumers, s_node) { + if (link->flags == (DL_FLAG_SYNC_STATE_ONLY | DL_FLAG_MANAGED)) + continue; + if (link->consumer == target) return 1; @@ -200,8 +203,11 @@ static int device_reorder_to_tail(struct device *dev, void *not_used) device_pm_move_last(dev); device_for_each_child(dev, NULL, device_reorder_to_tail); - list_for_each_entry(link, &dev->links.consumers, s_node) + list_for_each_entry(link, &dev->links.consumers, s_node) { + if (link->flags == (DL_FLAG_SYNC_STATE_ONLY | DL_FLAG_MANAGED)) + continue; device_reorder_to_tail(link->consumer, NULL); + } return 0; } @@ -228,7 +234,8 @@ void device_pm_move_to_tail(struct device *dev) #define DL_MANAGED_LINK_FLAGS (DL_FLAG_AUTOREMOVE_CONSUMER | \ DL_FLAG_AUTOREMOVE_SUPPLIER | \ - DL_FLAG_AUTOPROBE_CONSUMER) + DL_FLAG_AUTOPROBE_CONSUMER | \ + DL_FLAG_SYNC_STATE_ONLY) #define DL_ADD_VALID_FLAGS (DL_MANAGED_LINK_FLAGS | DL_FLAG_STATELESS | \ DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE) @@ -296,6 +303,8 @@ struct device_link *device_link_add(struct device *consumer, if (!consumer || !supplier || flags & ~DL_ADD_VALID_FLAGS || (flags & DL_FLAG_STATELESS && flags & DL_MANAGED_LINK_FLAGS) || + (flags & DL_FLAG_SYNC_STATE_ONLY && + flags != DL_FLAG_SYNC_STATE_ONLY) || (flags & DL_FLAG_AUTOPROBE_CONSUMER && flags & (DL_FLAG_AUTOREMOVE_CONSUMER | DL_FLAG_AUTOREMOVE_SUPPLIER))) @@ -316,11 +325,14 @@ struct device_link *device_link_add(struct device *consumer, /* * If the supplier has not been fully registered yet or there is a - * reverse dependency between the consumer and the supplier already in - * the graph, return NULL. + * reverse (non-SYNC_STATE_ONLY) dependency between the consumer and + * the supplier already in the graph, return NULL. If the link is a + * SYNC_STATE_ONLY link, we don't check for reverse dependencies + * because it only affects sync_state() callbacks. */ if (!device_pm_initialized(supplier) - || device_is_dependent(consumer, supplier)) { + || (!(flags & DL_FLAG_SYNC_STATE_ONLY) && + device_is_dependent(consumer, supplier))) { link = NULL; goto out; } @@ -347,9 +359,14 @@ struct device_link *device_link_add(struct device *consumer, } if (flags & DL_FLAG_STATELESS) { - link->flags |= DL_FLAG_STATELESS; kref_get(&link->kref); - goto out; + if (link->flags & DL_FLAG_SYNC_STATE_ONLY && + !(link->flags & DL_FLAG_STATELESS)) { + link->flags |= DL_FLAG_STATELESS; + goto reorder; + } else { + goto out; + } } /* @@ -371,6 +388,12 @@ struct device_link *device_link_add(struct device *consumer, link->flags |= DL_FLAG_MANAGED; device_link_init_status(link, consumer, supplier); } + if (link->flags & DL_FLAG_SYNC_STATE_ONLY && + !(flags & DL_FLAG_SYNC_STATE_ONLY)) { + link->flags &= ~DL_FLAG_SYNC_STATE_ONLY; + goto reorder; + } + goto out; } @@ -410,6 +433,13 @@ struct device_link *device_link_add(struct device *consumer, flags & DL_FLAG_PM_RUNTIME) pm_runtime_resume(supplier); + if (flags & DL_FLAG_SYNC_STATE_ONLY) { + dev_dbg(consumer, + "Linked as a sync state only consumer to %s\n", + dev_name(supplier)); + goto out; + } +reorder: /* * Move the consumer and all of the devices depending on it to the end * of dpm_list and the devices_kset list. @@ -635,7 +665,8 @@ int device_links_check_suppliers(struct device *dev) device_links_write_lock(); list_for_each_entry(link, &dev->links.suppliers, c_node) { - if (!(link->flags & DL_FLAG_MANAGED)) + if (!(link->flags & DL_FLAG_MANAGED) || + link->flags & DL_FLAG_SYNC_STATE_ONLY) continue; if (link->status != DL_STATE_AVAILABLE) { @@ -949,7 +980,8 @@ void device_links_unbind_consumers(struct device *dev) list_for_each_entry(link, &dev->links.consumers, s_node) { enum device_link_state status; - if (!(link->flags & DL_FLAG_MANAGED)) + if (!(link->flags & DL_FLAG_MANAGED) || + link->flags & DL_FLAG_SYNC_STATE_ONLY) continue; status = link->status; diff --git a/include/linux/device.h b/include/linux/device.h index 6978bb471567..82890e1b8f08 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1096,6 +1096,7 @@ enum device_link_state { * AUTOREMOVE_SUPPLIER: Remove the link automatically on supplier driver unbind. * AUTOPROBE_CONSUMER: Probe consumer driver automatically after supplier binds. * MANAGED: The core tracks presence of supplier/consumer drivers (internal). + * SYNC_STATE_ONLY: Link only affects sync_state() behavior. */ #define DL_FLAG_STATELESS BIT(0) #define DL_FLAG_AUTOREMOVE_CONSUMER BIT(1) @@ -1104,6 +1105,7 @@ enum device_link_state { #define DL_FLAG_AUTOREMOVE_SUPPLIER BIT(4) #define DL_FLAG_AUTOPROBE_CONSUMER BIT(5) #define DL_FLAG_MANAGED BIT(6) +#define DL_FLAG_SYNC_STATE_ONLY BIT(7) /** * struct device_link - Device link representation. -- cgit v1.2.3-71-gd317 From bcbbcfd57247f4c2976055995e5760fb576aae1e Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Mon, 28 Oct 2019 15:00:23 -0700 Subject: driver core: Allow a device to wait on optional suppliers Before this change, if a device is waiting on suppliers, it's assumed that all those suppliers are needed for the device to probe successfully. This change allows marking a devices as waiting only on optional suppliers. This allows a device to wait on suppliers (and link to them as soon as they are available) without preventing the device from being probed. Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20191028220027.251605-3-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 28 +++++++++++++++++++++++++--- include/linux/device.h | 3 +++ 2 files changed, 28 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index 17ed054c4132..48cd43a91ce6 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -480,13 +480,25 @@ EXPORT_SYMBOL_GPL(device_link_add); * This function is NOT meant to be called from the probe function of the * consumer but rather from code that creates/adds the consumer device. */ -static void device_link_wait_for_supplier(struct device *consumer) +static void device_link_wait_for_supplier(struct device *consumer, + bool need_for_probe) { mutex_lock(&wfs_lock); list_add_tail(&consumer->links.needs_suppliers, &wait_for_suppliers); + consumer->links.need_for_probe = need_for_probe; mutex_unlock(&wfs_lock); } +static void device_link_wait_for_mandatory_supplier(struct device *consumer) +{ + device_link_wait_for_supplier(consumer, true); +} + +static void device_link_wait_for_optional_supplier(struct device *consumer) +{ + device_link_wait_for_supplier(consumer, false); +} + /** * device_link_add_missing_supplier_links - Add links from consumer devices to * supplier devices, leaving any @@ -656,7 +668,8 @@ int device_links_check_suppliers(struct device *dev) * probe. */ mutex_lock(&wfs_lock); - if (!list_empty(&dev->links.needs_suppliers)) { + if (!list_empty(&dev->links.needs_suppliers) && + dev->links.need_for_probe) { mutex_unlock(&wfs_lock); return -EPROBE_DEFER; } @@ -760,6 +773,15 @@ void device_links_driver_bound(struct device *dev) { struct device_link *link; + /* + * If a device probes successfully, it's expected to have created all + * the device links it needs to or make new device links as it needs + * them. So, it no longer needs to wait on any suppliers. + */ + mutex_lock(&wfs_lock); + list_del_init(&dev->links.needs_suppliers); + mutex_unlock(&wfs_lock); + device_links_write_lock(); list_for_each_entry(link, &dev->links.consumers, s_node) { @@ -2393,7 +2415,7 @@ int device_add(struct device *dev) if (fwnode_has_op(dev->fwnode, add_links) && fwnode_call_int_op(dev->fwnode, add_links, dev)) - device_link_wait_for_supplier(dev); + device_link_wait_for_mandatory_supplier(dev, true); bus_probe_device(dev); if (parent) diff --git a/include/linux/device.h b/include/linux/device.h index 82890e1b8f08..d1bcc8f122f6 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1155,6 +1155,8 @@ enum dl_dev_state { * @consumers: List of links to consumer devices. * @needs_suppliers: Hook to global list of devices waiting for suppliers. * @defer_sync: Hook to global list of devices that have deferred sync_state. + * @need_for_probe: If needs_suppliers is on a list, this indicates if the + * suppliers are needed for probe or not. * @status: Driver status information. */ struct dev_links_info { @@ -1162,6 +1164,7 @@ struct dev_links_info { struct list_head consumers; struct list_head needs_suppliers; struct list_head defer_sync; + bool need_for_probe; enum dl_dev_state status; }; -- cgit v1.2.3-71-gd317 From 03324507e66c7664c754b1ef92c5c3be24c78aa2 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Mon, 28 Oct 2019 15:00:24 -0700 Subject: driver core: Allow fwnode_operations.add_links to differentiate errors When add_links() still has suppliers that it needs to link to in the future, this patch allows it to differentiate between suppliers that are needed for probing vs suppliers that are needed for sync_state() correctness. Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20191028220027.251605-4-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 12 ++++++++---- include/linux/fwnode.h | 13 +++++++++---- 2 files changed, 17 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index 48cd43a91ce6..e6d3e6d485da 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2297,7 +2297,7 @@ int device_add(struct device *dev) struct device *parent; struct kobject *kobj; struct class_interface *class_intf; - int error = -EINVAL; + int error = -EINVAL, fw_ret; struct kobject *glue_dir = NULL; dev = get_device(dev); @@ -2413,9 +2413,13 @@ int device_add(struct device *dev) */ device_link_add_missing_supplier_links(); - if (fwnode_has_op(dev->fwnode, add_links) - && fwnode_call_int_op(dev->fwnode, add_links, dev)) - device_link_wait_for_mandatory_supplier(dev, true); + if (fwnode_has_op(dev->fwnode, add_links)) { + fw_ret = fwnode_call_int_op(dev->fwnode, add_links, dev); + if (fw_ret == -ENODEV) + device_link_wait_for_mandatory_supplier(dev); + else if (fw_ret) + device_link_wait_for_optional_supplier(dev); + } bus_probe_device(dev); if (parent) diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 97223e2410bd..766ff9bb5876 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -94,10 +94,15 @@ struct fwnode_reference_args { * available suppliers. * * Return 0 if device links have been successfully created to all - * the suppliers of this device or if the supplier information is - * not known. Return an error if and only if the supplier - * information is known but some of the suppliers are not yet - * available to create device links to. + * the suppliers this device needs to create device links to or if + * the supplier information is not known. + * + * Return -ENODEV if and only if the suppliers needed for probing + * the device are not yet available to create device links to. + * + * Return -EAGAIN if there are suppliers that need to be linked to + * that are not yet available but none of those suppliers are + * necessary for probing this device. */ struct fwnode_operations { struct fwnode_handle *(*get)(struct fwnode_handle *fwnode); -- cgit v1.2.3-71-gd317 From c7c1168909410e692be6df17d0092363a00f33a9 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 11 Oct 2019 15:29:28 +0200 Subject: debugfs: remove return value of debugfs_create_x8() No one checks the return value of debugfs_create_x8(), as it's not needed, so make the return value void, so that no one tries to do so in the future. Link: https://lore.kernel.org/r/20191011132931.1186197-5-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- Documentation/filesystems/debugfs.txt | 4 ++-- fs/debugfs/file.c | 6 +++--- include/linux/debugfs.h | 12 ++++-------- 3 files changed, 9 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/debugfs.txt b/Documentation/filesystems/debugfs.txt index 9e705026ac10..1ec4a94b6e93 100644 --- a/Documentation/filesystems/debugfs.txt +++ b/Documentation/filesystems/debugfs.txt @@ -82,8 +82,8 @@ file should not be written to, simply set the mode bits accordingly. The values in these files are in decimal; if hexadecimal is more appropriate, the following functions can be used instead: - struct dentry *debugfs_create_x8(const char *name, umode_t mode, - struct dentry *parent, u8 *value); + void debugfs_create_x8(const char *name, umode_t mode, + struct dentry *parent, u8 *value); void debugfs_create_x16(const char *name, umode_t mode, struct dentry *parent, u16 *value); void debugfs_create_x32(const char *name, umode_t mode, diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 3ff736f22eb6..8aac1a9007c9 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -633,10 +633,10 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_x64_wo, NULL, debugfs_u64_set, "0x%016llx\n"); * @value: a pointer to the variable that the file should read to and write * from. */ -struct dentry *debugfs_create_x8(const char *name, umode_t mode, - struct dentry *parent, u8 *value) +void debugfs_create_x8(const char *name, umode_t mode, struct dentry *parent, + u8 *value) { - return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x8, + debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x8, &fops_x8_ro, &fops_x8_wo); } EXPORT_SYMBOL_GPL(debugfs_create_x8); diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 33690949b45d..c127c159d10a 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -107,8 +107,8 @@ void debugfs_create_u64(const char *name, umode_t mode, struct dentry *parent, u64 *value); struct dentry *debugfs_create_ulong(const char *name, umode_t mode, struct dentry *parent, unsigned long *value); -struct dentry *debugfs_create_x8(const char *name, umode_t mode, - struct dentry *parent, u8 *value); +void debugfs_create_x8(const char *name, umode_t mode, struct dentry *parent, + u8 *value); void debugfs_create_x16(const char *name, umode_t mode, struct dentry *parent, u16 *value); void debugfs_create_x32(const char *name, umode_t mode, struct dentry *parent, @@ -268,12 +268,8 @@ static inline struct dentry *debugfs_create_ulong(const char *name, return ERR_PTR(-ENODEV); } -static inline struct dentry *debugfs_create_x8(const char *name, umode_t mode, - struct dentry *parent, - u8 *value) -{ - return ERR_PTR(-ENODEV); -} +static inline void debugfs_create_x8(const char *name, umode_t mode, + struct dentry *parent, u8 *value) { } static inline void debugfs_create_x16(const char *name, umode_t mode, struct dentry *parent, u16 *value) { } -- cgit v1.2.3-71-gd317 From 1d1585ca0f48fe7ed95c3571f3e4a82b2b5045dc Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 2 Nov 2019 00:17:56 +0100 Subject: uaccess: Add non-pagefault user-space write function Commit 3d7081822f7f ("uaccess: Add non-pagefault user-space read functions") missed to add probe write function, therefore factor out a probe_write_common() helper with most logic of probe_kernel_write() except setting KERNEL_DS, and add a new probe_user_write() helper so it can be used from BPF side. Again, on some archs, the user address space and kernel address space can co-exist and be overlapping, so in such case, setting KERNEL_DS would mean that the given address is treated as being in kernel address space. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Cc: Masami Hiramatsu Link: https://lore.kernel.org/bpf/9df2542e68141bfa3addde631441ee45503856a8.1572649915.git.daniel@iogearbox.net --- include/linux/uaccess.h | 12 ++++++++++++ mm/maccess.c | 45 +++++++++++++++++++++++++++++++++++++++++---- 2 files changed, 53 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index d4ee6e942562..38555435a64a 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -337,6 +337,18 @@ extern long __probe_user_read(void *dst, const void __user *src, size_t size); extern long notrace probe_kernel_write(void *dst, const void *src, size_t size); extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size); +/* + * probe_user_write(): safely attempt to write to a location in user space + * @dst: address to write to + * @src: pointer to the data that shall be written + * @size: size of the data chunk + * + * Safely write to address @dst from the buffer at @src. If a kernel fault + * happens, handle that and return -EFAULT. + */ +extern long notrace probe_user_write(void __user *dst, const void *src, size_t size); +extern long notrace __probe_user_write(void __user *dst, const void *src, size_t size); + extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); extern long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr, long count); diff --git a/mm/maccess.c b/mm/maccess.c index d065736f6b87..2d3c3d01064c 100644 --- a/mm/maccess.c +++ b/mm/maccess.c @@ -18,6 +18,18 @@ probe_read_common(void *dst, const void __user *src, size_t size) return ret ? -EFAULT : 0; } +static __always_inline long +probe_write_common(void __user *dst, const void *src, size_t size) +{ + long ret; + + pagefault_disable(); + ret = __copy_to_user_inatomic(dst, src, size); + pagefault_enable(); + + return ret ? -EFAULT : 0; +} + /** * probe_kernel_read(): safely attempt to read from a kernel-space location * @dst: pointer to the buffer that shall take the data @@ -85,6 +97,7 @@ EXPORT_SYMBOL_GPL(probe_user_read); * Safely write to address @dst from the buffer at @src. If a kernel fault * happens, handle that and return -EFAULT. */ + long __weak probe_kernel_write(void *dst, const void *src, size_t size) __attribute__((alias("__probe_kernel_write"))); @@ -94,15 +107,39 @@ long __probe_kernel_write(void *dst, const void *src, size_t size) mm_segment_t old_fs = get_fs(); set_fs(KERNEL_DS); - pagefault_disable(); - ret = __copy_to_user_inatomic((__force void __user *)dst, src, size); - pagefault_enable(); + ret = probe_write_common((__force void __user *)dst, src, size); set_fs(old_fs); - return ret ? -EFAULT : 0; + return ret; } EXPORT_SYMBOL_GPL(probe_kernel_write); +/** + * probe_user_write(): safely attempt to write to a user-space location + * @dst: address to write to + * @src: pointer to the data that shall be written + * @size: size of the data chunk + * + * Safely write to address @dst from the buffer at @src. If a kernel fault + * happens, handle that and return -EFAULT. + */ + +long __weak probe_user_write(void __user *dst, const void *src, size_t size) + __attribute__((alias("__probe_user_write"))); + +long __probe_user_write(void __user *dst, const void *src, size_t size) +{ + long ret = -EFAULT; + mm_segment_t old_fs = get_fs(); + + set_fs(USER_DS); + if (access_ok(dst, size)) + ret = probe_write_common(dst, src, size); + set_fs(old_fs); + + return ret; +} +EXPORT_SYMBOL_GPL(probe_user_write); /** * strncpy_from_unsafe: - Copy a NUL terminated string from unsafe address. -- cgit v1.2.3-71-gd317 From 75a1a607bb7e6d918be3aca11ec2214a275392f4 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 2 Nov 2019 00:17:57 +0100 Subject: uaccess: Add strict non-pagefault kernel-space read function Add two new probe_kernel_read_strict() and strncpy_from_unsafe_strict() helpers which by default alias to the __probe_kernel_read() and the __strncpy_from_unsafe(), respectively, but can be overridden by archs which have non-overlapping address ranges for kernel space and user space in order to bail out with -EFAULT when attempting to probe user memory including non-canonical user access addresses [0]: 4-level page tables: user-space mem: 0x0000000000000000 - 0x00007fffffffffff non-canonical: 0x0000800000000000 - 0xffff7fffffffffff 5-level page tables: user-space mem: 0x0000000000000000 - 0x00ffffffffffffff non-canonical: 0x0100000000000000 - 0xfeffffffffffffff The idea is that these helpers are complementary to the probe_user_read() and strncpy_from_unsafe_user() which probe user-only memory. Both added helpers here do the same, but for kernel-only addresses. Both set of helpers are going to be used for BPF tracing. They also explicitly avoid throwing the splat for non-canonical user addresses from 00c42373d397 ("x86-64: add warning for non-canonical user access address dereferences"). For compat, the current probe_kernel_read() and strncpy_from_unsafe() are left as-is. [0] Documentation/x86/x86_64/mm.txt Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Cc: Linus Torvalds Cc: Masami Hiramatsu Cc: x86@kernel.org Link: https://lore.kernel.org/bpf/eefeefd769aa5a013531f491a71f0936779e916b.1572649915.git.daniel@iogearbox.net --- arch/x86/mm/Makefile | 2 +- arch/x86/mm/maccess.c | 43 +++++++++++++++++++++++++++++++++++++++++++ include/linux/uaccess.h | 4 ++++ mm/maccess.c | 25 ++++++++++++++++++++++++- 4 files changed, 72 insertions(+), 2 deletions(-) create mode 100644 arch/x86/mm/maccess.c (limited to 'include/linux') diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 84373dc9b341..bbc68a54795e 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -13,7 +13,7 @@ CFLAGS_REMOVE_mem_encrypt_identity.o = -pg endif obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ - pat.o pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o + pat.o pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o maccess.o # Make sure __phys_addr has no stackprotector nostackp := $(call cc-option, -fno-stack-protector) diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c new file mode 100644 index 000000000000..f5b85bdc0535 --- /dev/null +++ b/arch/x86/mm/maccess.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include + +#ifdef CONFIG_X86_64 +static __always_inline u64 canonical_address(u64 vaddr, u8 vaddr_bits) +{ + return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits); +} + +static __always_inline bool invalid_probe_range(u64 vaddr) +{ + /* + * Range covering the highest possible canonical userspace address + * as well as non-canonical address range. For the canonical range + * we also need to include the userspace guard page. + */ + return vaddr < TASK_SIZE_MAX + PAGE_SIZE || + canonical_address(vaddr, boot_cpu_data.x86_virt_bits) != vaddr; +} +#else +static __always_inline bool invalid_probe_range(u64 vaddr) +{ + return vaddr < TASK_SIZE_MAX; +} +#endif + +long probe_kernel_read_strict(void *dst, const void *src, size_t size) +{ + if (unlikely(invalid_probe_range((unsigned long)src))) + return -EFAULT; + + return __probe_kernel_read(dst, src, size); +} + +long strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr, long count) +{ + if (unlikely(invalid_probe_range((unsigned long)unsafe_addr))) + return -EFAULT; + + return __strncpy_from_unsafe(dst, unsafe_addr, count); +} diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 38555435a64a..67f016010aad 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -311,6 +311,7 @@ copy_struct_from_user(void *dst, size_t ksize, const void __user *src, * happens, handle that and return -EFAULT. */ extern long probe_kernel_read(void *dst, const void *src, size_t size); +extern long probe_kernel_read_strict(void *dst, const void *src, size_t size); extern long __probe_kernel_read(void *dst, const void *src, size_t size); /* @@ -350,6 +351,9 @@ extern long notrace probe_user_write(void __user *dst, const void *src, size_t s extern long notrace __probe_user_write(void __user *dst, const void *src, size_t size); extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); +extern long strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr, + long count); +extern long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); extern long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr, long count); extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count); diff --git a/mm/maccess.c b/mm/maccess.c index 2d3c3d01064c..3ca8d97e5010 100644 --- a/mm/maccess.c +++ b/mm/maccess.c @@ -43,11 +43,20 @@ probe_write_common(void __user *dst, const void *src, size_t size) * do_page_fault() doesn't attempt to take mmap_sem. This makes * probe_kernel_read() suitable for use within regions where the caller * already holds mmap_sem, or other locks which nest inside mmap_sem. + * + * probe_kernel_read_strict() is the same as probe_kernel_read() except for + * the case where architectures have non-overlapping user and kernel address + * ranges: probe_kernel_read_strict() will additionally return -EFAULT for + * probing memory on a user address range where probe_user_read() is supposed + * to be used instead. */ long __weak probe_kernel_read(void *dst, const void *src, size_t size) __attribute__((alias("__probe_kernel_read"))); +long __weak probe_kernel_read_strict(void *dst, const void *src, size_t size) + __attribute__((alias("__probe_kernel_read"))); + long __probe_kernel_read(void *dst, const void *src, size_t size) { long ret; @@ -157,8 +166,22 @@ EXPORT_SYMBOL_GPL(probe_user_write); * * If @count is smaller than the length of the string, copies @count-1 bytes, * sets the last byte of @dst buffer to NUL and returns @count. + * + * strncpy_from_unsafe_strict() is the same as strncpy_from_unsafe() except + * for the case where architectures have non-overlapping user and kernel address + * ranges: strncpy_from_unsafe_strict() will additionally return -EFAULT for + * probing memory on a user address range where strncpy_from_unsafe_user() is + * supposed to be used instead. */ -long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count) + +long __weak strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count) + __attribute__((alias("__strncpy_from_unsafe"))); + +long __weak strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr, + long count) + __attribute__((alias("__strncpy_from_unsafe"))); + +long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count) { mm_segment_t old_fs = get_fs(); const void *src = unsafe_addr; -- cgit v1.2.3-71-gd317 From c49cfc227e7f49e6011d6b955145814ce13424bc Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Fri, 1 Nov 2019 11:35:05 +0200 Subject: iio: imu: adis: assign value only if return code zero in read funcs The inline read functions in the ADIS library don't check the return value of the `adis_read_reg()` function and assign the value of `tmp` regardless. Fix this by checking if return value is zero and only then assigning the value of `tmp`. No known case of the callers of this function incorrectly using the value, but best to stop any potential risk here. Not suitable for stable due to no known actual bugs caused by this issue. Fixes: 57a1228a06b7a ("iio:imu:adis: Add support for 32bit registers") Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/imu/adis.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 4c53815bb729..92aae14593bf 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -129,7 +129,8 @@ static inline int adis_read_reg_16(struct adis *adis, unsigned int reg, int ret; ret = adis_read_reg(adis, reg, &tmp, 2); - *val = tmp; + if (ret == 0) + *val = tmp; return ret; } @@ -147,7 +148,8 @@ static inline int adis_read_reg_32(struct adis *adis, unsigned int reg, int ret; ret = adis_read_reg(adis, reg, &tmp, 4); - *val = tmp; + if (ret == 0) + *val = tmp; return ret; } -- cgit v1.2.3-71-gd317 From 9927c6fa3e1d941c9b89f807f5d0480390eb0471 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 16 Oct 2019 06:03:32 -0700 Subject: debugfs: remove return value of debugfs_create_atomic_t() No one checks the return value of debugfs_create_atomic_t(), as it's not needed, so make the return value void, so that no one tries to do so in the future. Link: https://lore.kernel.org/r/20191016130332.GA28240@kroah.com Signed-off-by: Greg Kroah-Hartman --- Documentation/filesystems/debugfs.txt | 4 ++-- fs/debugfs/file.c | 9 ++++----- include/linux/debugfs.h | 13 ++++++------- 3 files changed, 12 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/debugfs.txt b/Documentation/filesystems/debugfs.txt index 1ec4a94b6e93..ac6067a02f74 100644 --- a/Documentation/filesystems/debugfs.txt +++ b/Documentation/filesystems/debugfs.txt @@ -113,8 +113,8 @@ lower-case values, or 1 or 0. Any other input will be silently ignored. Also, atomic_t values can be placed in debugfs with: - struct dentry *debugfs_create_atomic_t(const char *name, umode_t mode, - struct dentry *parent, atomic_t *value) + void debugfs_create_atomic_t(const char *name, umode_t mode, + struct dentry *parent, atomic_t *value) A read of this file will get atomic_t values, and a write of this file will set atomic_t values. diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 8aac1a9007c9..dede25247b81 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -757,12 +757,11 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_atomic_t_wo, NULL, debugfs_atomic_t_set, * @value: a pointer to the variable that the file should read to and write * from. */ -struct dentry *debugfs_create_atomic_t(const char *name, umode_t mode, - struct dentry *parent, atomic_t *value) +void debugfs_create_atomic_t(const char *name, umode_t mode, + struct dentry *parent, atomic_t *value) { - return debugfs_create_mode_unsafe(name, mode, parent, value, - &fops_atomic_t, &fops_atomic_t_ro, - &fops_atomic_t_wo); + debugfs_create_mode_unsafe(name, mode, parent, value, &fops_atomic_t, + &fops_atomic_t_ro, &fops_atomic_t_wo); } EXPORT_SYMBOL_GPL(debugfs_create_atomic_t); diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index c127c159d10a..19231e618c16 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -117,8 +117,8 @@ void debugfs_create_x64(const char *name, umode_t mode, struct dentry *parent, u64 *value); void debugfs_create_size_t(const char *name, umode_t mode, struct dentry *parent, size_t *value); -struct dentry *debugfs_create_atomic_t(const char *name, umode_t mode, - struct dentry *parent, atomic_t *value); +void debugfs_create_atomic_t(const char *name, umode_t mode, + struct dentry *parent, atomic_t *value); struct dentry *debugfs_create_bool(const char *name, umode_t mode, struct dentry *parent, bool *value); @@ -284,11 +284,10 @@ static inline void debugfs_create_size_t(const char *name, umode_t mode, struct dentry *parent, size_t *value) { } -static inline struct dentry *debugfs_create_atomic_t(const char *name, umode_t mode, - struct dentry *parent, atomic_t *value) -{ - return ERR_PTR(-ENODEV); -} +static inline void debugfs_create_atomic_t(const char *name, umode_t mode, + struct dentry *parent, + atomic_t *value) +{ } static inline struct dentry *debugfs_create_bool(const char *name, umode_t mode, struct dentry *parent, -- cgit v1.2.3-71-gd317 From 11f70002213774ed233950f71ea8803fa3700aa3 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Sun, 29 Sep 2019 23:18:49 +0900 Subject: leds: remove PAGE_SIZE limit of /sys/class/leds//trigger Reading /sys/class/leds//trigger returns all available LED triggers. However, the size of this file is limited to PAGE_SIZE because of the limitation for sysfs attribute. Enabling LED CPU trigger on systems with thousands of CPUs easily hits PAGE_SIZE limit, and makes it impossible to see all available LED triggers and which trigger is currently activated. We work around it here by converting /sys/class/leds//trigger to binary attribute, which is not limited by length. This is _not_ good design, do not copy it. Signed-off-by: Akinobu Mita Cc: "Rafael J. Wysocki" Cc: Pavel Machek Cc: Dan Murphy A Reviewed-by: Greg Kroah-Hartman Signed-off-by: Pavel Machek --- drivers/leds/led-class.c | 8 ++-- drivers/leds/led-triggers.c | 90 ++++++++++++++++++++++++++++++++++----------- drivers/leds/leds.h | 6 +++ include/linux/leds.h | 5 --- 4 files changed, 78 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c index 647b1263c579..3f04334d59ee 100644 --- a/drivers/leds/led-class.c +++ b/drivers/leds/led-class.c @@ -74,13 +74,13 @@ static ssize_t max_brightness_show(struct device *dev, static DEVICE_ATTR_RO(max_brightness); #ifdef CONFIG_LEDS_TRIGGERS -static DEVICE_ATTR(trigger, 0644, led_trigger_show, led_trigger_store); -static struct attribute *led_trigger_attrs[] = { - &dev_attr_trigger.attr, +static BIN_ATTR(trigger, 0644, led_trigger_read, led_trigger_write, 0); +static struct bin_attribute *led_trigger_bin_attrs[] = { + &bin_attr_trigger, NULL, }; static const struct attribute_group led_trigger_group = { - .attrs = led_trigger_attrs, + .bin_attrs = led_trigger_bin_attrs, }; #endif diff --git a/drivers/leds/led-triggers.c b/drivers/leds/led-triggers.c index 23963e5cb5d6..79e30d2cb7a5 100644 --- a/drivers/leds/led-triggers.c +++ b/drivers/leds/led-triggers.c @@ -16,6 +16,7 @@ #include #include #include +#include #include "leds.h" /* @@ -26,9 +27,11 @@ LIST_HEAD(trigger_list); /* Used by LED Class */ -ssize_t led_trigger_store(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +ssize_t led_trigger_write(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, + loff_t pos, size_t count) { + struct device *dev = kobj_to_dev(kobj); struct led_classdev *led_cdev = dev_get_drvdata(dev); struct led_trigger *trig; int ret = count; @@ -64,39 +67,82 @@ unlock: mutex_unlock(&led_cdev->led_access); return ret; } -EXPORT_SYMBOL_GPL(led_trigger_store); +EXPORT_SYMBOL_GPL(led_trigger_write); -ssize_t led_trigger_show(struct device *dev, struct device_attribute *attr, - char *buf) +__printf(3, 4) +static int led_trigger_snprintf(char *buf, ssize_t size, const char *fmt, ...) +{ + va_list args; + int i; + + va_start(args, fmt); + if (size <= 0) + i = vsnprintf(NULL, 0, fmt, args); + else + i = vscnprintf(buf, size, fmt, args); + va_end(args); + + return i; +} + +static int led_trigger_format(char *buf, size_t size, + struct led_classdev *led_cdev) { - struct led_classdev *led_cdev = dev_get_drvdata(dev); struct led_trigger *trig; - int len = 0; + int len = led_trigger_snprintf(buf, size, "%s", + led_cdev->trigger ? "none" : "[none]"); + + list_for_each_entry(trig, &trigger_list, next_trig) { + bool hit = led_cdev->trigger && + !strcmp(led_cdev->trigger->name, trig->name); + + len += led_trigger_snprintf(buf + len, size - len, + " %s%s%s", hit ? "[" : "", + trig->name, hit ? "]" : ""); + } + + len += led_trigger_snprintf(buf + len, size - len, "\n"); + + return len; +} + +/* + * It was stupid to create 10000 cpu triggers, but we are stuck with it now. + * Don't make that mistake again. We work around it here by creating binary + * attribute, which is not limited by length. This is _not_ good design, do not + * copy it. + */ +ssize_t led_trigger_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, + loff_t pos, size_t count) +{ + struct device *dev = kobj_to_dev(kobj); + struct led_classdev *led_cdev = dev_get_drvdata(dev); + void *data; + int len; down_read(&triggers_list_lock); down_read(&led_cdev->trigger_lock); - if (!led_cdev->trigger) - len += scnprintf(buf+len, PAGE_SIZE - len, "[none] "); - else - len += scnprintf(buf+len, PAGE_SIZE - len, "none "); - - list_for_each_entry(trig, &trigger_list, next_trig) { - if (led_cdev->trigger && !strcmp(led_cdev->trigger->name, - trig->name)) - len += scnprintf(buf+len, PAGE_SIZE - len, "[%s] ", - trig->name); - else - len += scnprintf(buf+len, PAGE_SIZE - len, "%s ", - trig->name); + len = led_trigger_format(NULL, 0, led_cdev); + data = kvmalloc(len + 1, GFP_KERNEL); + if (!data) { + up_read(&led_cdev->trigger_lock); + up_read(&triggers_list_lock); + return -ENOMEM; } + len = led_trigger_format(data, len + 1, led_cdev); + up_read(&led_cdev->trigger_lock); up_read(&triggers_list_lock); - len += scnprintf(len+buf, PAGE_SIZE - len, "\n"); + len = memory_read_from_buffer(buf, count, &pos, data, len); + + kvfree(data); + return len; } -EXPORT_SYMBOL_GPL(led_trigger_show); +EXPORT_SYMBOL_GPL(led_trigger_read); /* Caller must ensure led_cdev->trigger_lock held */ int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig) diff --git a/drivers/leds/leds.h b/drivers/leds/leds.h index 0b577cece8f7..2d9eb48bbed9 100644 --- a/drivers/leds/leds.h +++ b/drivers/leds/leds.h @@ -23,6 +23,12 @@ void led_set_brightness_nopm(struct led_classdev *led_cdev, enum led_brightness value); void led_set_brightness_nosleep(struct led_classdev *led_cdev, enum led_brightness value); +ssize_t led_trigger_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, + loff_t pos, size_t count); +ssize_t led_trigger_write(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, + loff_t pos, size_t count); extern struct rw_semaphore leds_list_lock; extern struct list_head leds_list; diff --git a/include/linux/leds.h b/include/linux/leds.h index b8df71193329..0b6b6166e9ea 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -361,11 +361,6 @@ struct led_trigger { #define led_trigger_get_led(dev) ((struct led_classdev *)dev_get_drvdata((dev))) #define led_trigger_get_drvdata(dev) (led_get_trigger_data(led_trigger_get_led(dev))) -ssize_t led_trigger_store(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count); -ssize_t led_trigger_show(struct device *dev, struct device_attribute *attr, - char *buf); - /* Registration functions for complex triggers */ extern int led_trigger_register(struct led_trigger *trigger); extern void led_trigger_unregister(struct led_trigger *trigger); -- cgit v1.2.3-71-gd317 From 4a29f90e60df955f1b6e0dd836955f14a62dc103 Mon Sep 17 00:00:00 2001 From: Dan Murphy Date: Tue, 1 Oct 2019 13:04:36 -0500 Subject: leds: flash: Convert non extended registration to inline Convert the #define non-extended registration API to an inline function. Signed-off-by: Dan Murphy Signed-off-by: Pavel Machek --- include/linux/led-class-flash.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/led-class-flash.h b/include/linux/led-class-flash.h index 1e824963af17..7ff287a9e2a2 100644 --- a/include/linux/led-class-flash.h +++ b/include/linux/led-class-flash.h @@ -98,8 +98,11 @@ extern int led_classdev_flash_register_ext(struct device *parent, struct led_classdev_flash *fled_cdev, struct led_init_data *init_data); -#define led_classdev_flash_register(parent, fled_cdev) \ - led_classdev_flash_register_ext(parent, fled_cdev, NULL) +static inline int led_classdev_flash_register(struct device *parent, + struct led_classdev_flash *fled_cdev) +{ + return led_classdev_flash_register_ext(parent, fled_cdev, NULL); +} /** * led_classdev_flash_unregister - unregisters an object of led_classdev class -- cgit v1.2.3-71-gd317 From 57e5c31e53758aad96699e784a752ad944890b25 Mon Sep 17 00:00:00 2001 From: Dan Murphy Date: Wed, 2 Oct 2019 07:40:37 -0500 Subject: leds: flash: Remove extern from the header file extern is implied and is not needed in the header file. Remove the extern keyword and re-align the code. Signed-off-by: Dan Murphy Signed-off-by: Pavel Machek --- include/linux/led-class-flash.h | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/led-class-flash.h b/include/linux/led-class-flash.h index 7ff287a9e2a2..1bd83159fa4c 100644 --- a/include/linux/led-class-flash.h +++ b/include/linux/led-class-flash.h @@ -94,12 +94,12 @@ static inline struct led_classdev_flash *lcdev_to_flcdev( * * Returns: 0 on success or negative error value on failure */ -extern int led_classdev_flash_register_ext(struct device *parent, - struct led_classdev_flash *fled_cdev, - struct led_init_data *init_data); +int led_classdev_flash_register_ext(struct device *parent, + struct led_classdev_flash *fled_cdev, + struct led_init_data *init_data); static inline int led_classdev_flash_register(struct device *parent, - struct led_classdev_flash *fled_cdev) + struct led_classdev_flash *fled_cdev) { return led_classdev_flash_register_ext(parent, fled_cdev, NULL); } @@ -111,7 +111,7 @@ static inline int led_classdev_flash_register(struct device *parent, * * Unregister a previously registered via led_classdev_flash_register object */ -extern void led_classdev_flash_unregister(struct led_classdev_flash *fled_cdev); +void led_classdev_flash_unregister(struct led_classdev_flash *fled_cdev); /** * led_set_flash_strobe - setup flash strobe @@ -159,8 +159,8 @@ static inline int led_get_flash_strobe(struct led_classdev_flash *fled_cdev, * * Returns: 0 on success or negative error value on failure */ -extern int led_set_flash_brightness(struct led_classdev_flash *fled_cdev, - u32 brightness); +int led_set_flash_brightness(struct led_classdev_flash *fled_cdev, + u32 brightness); /** * led_update_flash_brightness - update flash LED brightness @@ -171,7 +171,7 @@ extern int led_set_flash_brightness(struct led_classdev_flash *fled_cdev, * * Returns: 0 on success or negative error value on failure */ -extern int led_update_flash_brightness(struct led_classdev_flash *fled_cdev); +int led_update_flash_brightness(struct led_classdev_flash *fled_cdev); /** * led_set_flash_timeout - set flash LED timeout @@ -182,8 +182,7 @@ extern int led_update_flash_brightness(struct led_classdev_flash *fled_cdev); * * Returns: 0 on success or negative error value on failure */ -extern int led_set_flash_timeout(struct led_classdev_flash *fled_cdev, - u32 timeout); +int led_set_flash_timeout(struct led_classdev_flash *fled_cdev, u32 timeout); /** * led_get_flash_fault - get the flash LED fault @@ -194,7 +193,6 @@ extern int led_set_flash_timeout(struct led_classdev_flash *fled_cdev, * * Returns: 0 on success or negative error value on failure */ -extern int led_get_flash_fault(struct led_classdev_flash *fled_cdev, - u32 *fault); +int led_get_flash_fault(struct led_classdev_flash *fled_cdev, u32 *fault); #endif /* __LINUX_FLASH_LEDS_H_INCLUDED */ -- cgit v1.2.3-71-gd317 From 20cdba9d9c165e475fcc5af97857b6fa7aec96a0 Mon Sep 17 00:00:00 2001 From: Dan Murphy Date: Wed, 2 Oct 2019 07:40:38 -0500 Subject: leds: flash: Add devm_* functions to the flash class Add the missing device managed API for registration and unregistration for the LED flash class. Signed-off-by: Dan Murphy Signed-off-by: Pavel Machek --- drivers/leds/led-class-flash.c | 50 +++++++++++++++++++++++++++++++++++++++++ include/linux/led-class-flash.h | 14 ++++++++++++ 2 files changed, 64 insertions(+) (limited to 'include/linux') diff --git a/drivers/leds/led-class-flash.c b/drivers/leds/led-class-flash.c index 60c3de5c6b9f..6eeb9effcf65 100644 --- a/drivers/leds/led-class-flash.c +++ b/drivers/leds/led-class-flash.c @@ -327,6 +327,56 @@ void led_classdev_flash_unregister(struct led_classdev_flash *fled_cdev) } EXPORT_SYMBOL_GPL(led_classdev_flash_unregister); +static void devm_led_classdev_flash_release(struct device *dev, void *res) +{ + led_classdev_flash_unregister(*(struct led_classdev_flash **)res); +} + +int devm_led_classdev_flash_register_ext(struct device *parent, + struct led_classdev_flash *fled_cdev, + struct led_init_data *init_data) +{ + struct led_classdev_flash **dr; + int ret; + + dr = devres_alloc(devm_led_classdev_flash_release, sizeof(*dr), + GFP_KERNEL); + if (!dr) + return -ENOMEM; + + ret = led_classdev_flash_register_ext(parent, fled_cdev, init_data); + if (ret) { + devres_free(dr); + return ret; + } + + *dr = fled_cdev; + devres_add(parent, dr); + + return 0; +} +EXPORT_SYMBOL_GPL(devm_led_classdev_flash_register_ext); + +static int devm_led_classdev_flash_match(struct device *dev, + void *res, void *data) +{ + struct led_classdev_flash **p = res; + + if (WARN_ON(!p || !*p)) + return 0; + + return *p == data; +} + +void devm_led_classdev_flash_unregister(struct device *dev, + struct led_classdev_flash *fled_cdev) +{ + WARN_ON(devres_release(dev, + devm_led_classdev_flash_release, + devm_led_classdev_flash_match, fled_cdev)); +} +EXPORT_SYMBOL_GPL(devm_led_classdev_flash_unregister); + static void led_clamp_align(struct led_flash_setting *s) { u32 v, offset; diff --git a/include/linux/led-class-flash.h b/include/linux/led-class-flash.h index 1bd83159fa4c..21a3358a1731 100644 --- a/include/linux/led-class-flash.h +++ b/include/linux/led-class-flash.h @@ -113,6 +113,20 @@ static inline int led_classdev_flash_register(struct device *parent, */ void led_classdev_flash_unregister(struct led_classdev_flash *fled_cdev); +int devm_led_classdev_flash_register_ext(struct device *parent, + struct led_classdev_flash *fled_cdev, + struct led_init_data *init_data); + + +static inline int devm_led_classdev_flash_register(struct device *parent, + struct led_classdev_flash *fled_cdev) +{ + return devm_led_classdev_flash_register_ext(parent, fled_cdev, NULL); +} + +void devm_led_classdev_flash_unregister(struct device *parent, + struct led_classdev_flash *fled_cdev); + /** * led_set_flash_strobe - setup flash strobe * @fled_cdev: the flash LED to set strobe on -- cgit v1.2.3-71-gd317 From ec28a8cfdce6306afcbf528e231a733010c82251 Mon Sep 17 00:00:00 2001 From: Dan Murphy Date: Wed, 2 Oct 2019 07:40:40 -0500 Subject: leds: core: Remove extern from header extern is implied and is not needed in the header file. Remove the extern keyword and re-align the code. Signed-off-by: Dan Murphy Signed-off-by: Pavel Machek --- include/linux/leds.h | 95 ++++++++++++++++++++++++---------------------------- 1 file changed, 44 insertions(+), 51 deletions(-) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index 0b6b6166e9ea..52e50183b963 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -161,7 +161,7 @@ struct led_classdev { * * Returns: 0 on success or negative error value on failure */ -extern int led_classdev_register_ext(struct device *parent, +int led_classdev_register_ext(struct device *parent, struct led_classdev *led_cdev, struct led_init_data *init_data); @@ -181,7 +181,7 @@ static inline int led_classdev_register(struct device *parent, return led_classdev_register_ext(parent, led_cdev, NULL); } -extern int devm_led_classdev_register_ext(struct device *parent, +int devm_led_classdev_register_ext(struct device *parent, struct led_classdev *led_cdev, struct led_init_data *init_data); @@ -190,11 +190,11 @@ static inline int devm_led_classdev_register(struct device *parent, { return devm_led_classdev_register_ext(parent, led_cdev, NULL); } -extern void led_classdev_unregister(struct led_classdev *led_cdev); -extern void devm_led_classdev_unregister(struct device *parent, - struct led_classdev *led_cdev); -extern void led_classdev_suspend(struct led_classdev *led_cdev); -extern void led_classdev_resume(struct led_classdev *led_cdev); +void led_classdev_unregister(struct led_classdev *led_cdev); +void devm_led_classdev_unregister(struct device *parent, + struct led_classdev *led_cdev); +void led_classdev_suspend(struct led_classdev *led_cdev); +void led_classdev_resume(struct led_classdev *led_cdev); /** * led_blink_set - set blinking with software fallback @@ -211,9 +211,8 @@ extern void led_classdev_resume(struct led_classdev *led_cdev); * led_cdev->brightness_set() will not stop the blinking, * use led_classdev_brightness_set() instead. */ -extern void led_blink_set(struct led_classdev *led_cdev, - unsigned long *delay_on, - unsigned long *delay_off); +void led_blink_set(struct led_classdev *led_cdev, unsigned long *delay_on, + unsigned long *delay_off); /** * led_blink_set_oneshot - do a oneshot software blink * @led_cdev: the LED to start blinking @@ -228,10 +227,9 @@ extern void led_blink_set(struct led_classdev *led_cdev, * If invert is set, led blinks for delay_off first, then for * delay_on and leave the led on after the on-off cycle. */ -extern void led_blink_set_oneshot(struct led_classdev *led_cdev, - unsigned long *delay_on, - unsigned long *delay_off, - int invert); +void led_blink_set_oneshot(struct led_classdev *led_cdev, + unsigned long *delay_on, unsigned long *delay_off, + int invert); /** * led_set_brightness - set LED brightness * @led_cdev: the LED to set @@ -241,8 +239,8 @@ extern void led_blink_set_oneshot(struct led_classdev *led_cdev, * software blink timer that implements blinking when the * hardware doesn't. This function is guaranteed not to sleep. */ -extern void led_set_brightness(struct led_classdev *led_cdev, - enum led_brightness brightness); +void led_set_brightness(struct led_classdev *led_cdev, + enum led_brightness brightness); /** * led_set_brightness_sync - set LED brightness synchronously @@ -255,8 +253,8 @@ extern void led_set_brightness(struct led_classdev *led_cdev, * * Returns: 0 on success or negative error value on failure */ -extern int led_set_brightness_sync(struct led_classdev *led_cdev, - enum led_brightness value); +int led_set_brightness_sync(struct led_classdev *led_cdev, + enum led_brightness value); /** * led_update_brightness - update LED brightness @@ -267,7 +265,7 @@ extern int led_set_brightness_sync(struct led_classdev *led_cdev, * * Returns: 0 on success or negative error value on failure */ -extern int led_update_brightness(struct led_classdev *led_cdev); +int led_update_brightness(struct led_classdev *led_cdev); /** * led_get_default_pattern - return default pattern @@ -279,8 +277,7 @@ extern int led_update_brightness(struct led_classdev *led_cdev); * Return: Allocated array of integers with default pattern from device tree * or NULL. Caller is responsible for kfree(). */ -extern u32 *led_get_default_pattern(struct led_classdev *led_cdev, - unsigned int *size); +u32 *led_get_default_pattern(struct led_classdev *led_cdev, unsigned int *size); /** * led_sysfs_disable - disable LED sysfs interface @@ -288,7 +285,7 @@ extern u32 *led_get_default_pattern(struct led_classdev *led_cdev, * * Disable the led_cdev's sysfs interface. */ -extern void led_sysfs_disable(struct led_classdev *led_cdev); +void led_sysfs_disable(struct led_classdev *led_cdev); /** * led_sysfs_enable - enable LED sysfs interface @@ -296,7 +293,7 @@ extern void led_sysfs_disable(struct led_classdev *led_cdev); * * Enable the led_cdev's sysfs interface. */ -extern void led_sysfs_enable(struct led_classdev *led_cdev); +void led_sysfs_enable(struct led_classdev *led_cdev); /** * led_compose_name - compose LED class device name @@ -311,8 +308,8 @@ extern void led_sysfs_enable(struct led_classdev *led_cdev); * * Returns: 0 on success or negative error value on failure */ -extern int led_compose_name(struct device *dev, struct led_init_data *init_data, - char *led_classdev_name); +int led_compose_name(struct device *dev, struct led_init_data *init_data, + char *led_classdev_name); /** * led_sysfs_is_disabled - check if LED sysfs interface is disabled @@ -362,27 +359,24 @@ struct led_trigger { #define led_trigger_get_drvdata(dev) (led_get_trigger_data(led_trigger_get_led(dev))) /* Registration functions for complex triggers */ -extern int led_trigger_register(struct led_trigger *trigger); -extern void led_trigger_unregister(struct led_trigger *trigger); -extern int devm_led_trigger_register(struct device *dev, +int led_trigger_register(struct led_trigger *trigger); +void led_trigger_unregister(struct led_trigger *trigger); +int devm_led_trigger_register(struct device *dev, struct led_trigger *trigger); -extern void led_trigger_register_simple(const char *name, +void led_trigger_register_simple(const char *name, struct led_trigger **trigger); -extern void led_trigger_unregister_simple(struct led_trigger *trigger); -extern void led_trigger_event(struct led_trigger *trigger, - enum led_brightness event); -extern void led_trigger_blink(struct led_trigger *trigger, - unsigned long *delay_on, - unsigned long *delay_off); -extern void led_trigger_blink_oneshot(struct led_trigger *trigger, - unsigned long *delay_on, - unsigned long *delay_off, - int invert); -extern void led_trigger_set_default(struct led_classdev *led_cdev); -extern int led_trigger_set(struct led_classdev *led_cdev, - struct led_trigger *trigger); -extern void led_trigger_remove(struct led_classdev *led_cdev); +void led_trigger_unregister_simple(struct led_trigger *trigger); +void led_trigger_event(struct led_trigger *trigger, enum led_brightness event); +void led_trigger_blink(struct led_trigger *trigger, unsigned long *delay_on, + unsigned long *delay_off); +void led_trigger_blink_oneshot(struct led_trigger *trigger, + unsigned long *delay_on, + unsigned long *delay_off, + int invert); +void led_trigger_set_default(struct led_classdev *led_cdev); +int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trigger); +void led_trigger_remove(struct led_classdev *led_cdev); static inline void led_set_trigger_data(struct led_classdev *led_cdev, void *trigger_data) @@ -410,8 +404,7 @@ static inline void *led_get_trigger_data(struct led_classdev *led_cdev) * This is meant to be used on triggers with statically * allocated name. */ -extern void led_trigger_rename_static(const char *name, - struct led_trigger *trig); +void led_trigger_rename_static(const char *name, struct led_trigger *trig); #define module_led_trigger(__led_trigger) \ module_driver(__led_trigger, led_trigger_register, \ @@ -453,20 +446,20 @@ static inline void *led_get_trigger_data(struct led_classdev *led_cdev) /* Trigger specific functions */ #ifdef CONFIG_LEDS_TRIGGER_DISK -extern void ledtrig_disk_activity(bool write); +void ledtrig_disk_activity(bool write); #else static inline void ledtrig_disk_activity(bool write) {} #endif #ifdef CONFIG_LEDS_TRIGGER_MTD -extern void ledtrig_mtd_activity(void); +void ledtrig_mtd_activity(void); #else static inline void ledtrig_mtd_activity(void) {} #endif #if defined(CONFIG_LEDS_TRIGGER_CAMERA) || defined(CONFIG_LEDS_TRIGGER_CAMERA_MODULE) -extern void ledtrig_flash_ctrl(bool on); -extern void ledtrig_torch_ctrl(bool on); +void ledtrig_flash_ctrl(bool on); +void ledtrig_torch_ctrl(bool on); #else static inline void ledtrig_flash_ctrl(bool on) {} static inline void ledtrig_torch_ctrl(bool on) {} @@ -546,7 +539,7 @@ enum cpu_led_event { CPU_LED_HALTED, /* Machine shutdown */ }; #ifdef CONFIG_LEDS_TRIGGER_CPU -extern void ledtrig_cpu(enum cpu_led_event evt); +void ledtrig_cpu(enum cpu_led_event evt); #else static inline void ledtrig_cpu(enum cpu_led_event evt) { @@ -555,7 +548,7 @@ static inline void ledtrig_cpu(enum cpu_led_event evt) #endif #ifdef CONFIG_LEDS_BRIGHTNESS_HW_CHANGED -extern void led_classdev_notify_brightness_hw_changed( +void led_classdev_notify_brightness_hw_changed( struct led_classdev *led_cdev, enum led_brightness brightness); #else static inline void led_classdev_notify_brightness_hw_changed( -- cgit v1.2.3-71-gd317 From 9cc93be7b0c91a87ef452457c706af62741249d7 Mon Sep 17 00:00:00 2001 From: Dan Murphy Date: Wed, 2 Oct 2019 07:40:42 -0500 Subject: leds: core: Fix leds.h structure documentation Update the leds.h structure documentation to define the correct arguments. Signed-off-by: Dan Murphy Signed-off-by: Pavel Machek --- include/linux/leds.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index 52e50183b963..242258f7d837 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -245,7 +245,7 @@ void led_set_brightness(struct led_classdev *led_cdev, /** * led_set_brightness_sync - set LED brightness synchronously * @led_cdev: the LED to set - * @brightness: the brightness to set it to + * @value: the brightness to set it to * * Set an LED's brightness immediately. This function will block * the caller for the time required for accessing device registers, @@ -298,8 +298,7 @@ void led_sysfs_enable(struct led_classdev *led_cdev); /** * led_compose_name - compose LED class device name * @dev: LED controller device object - * @child: child fwnode_handle describing a LED or a group of synchronized LEDs; - * it must be provided only for fwnode based LEDs + * @init_data: the LED class device initialization data * @led_classdev_name: composed LED class device name * * Create LED class device name basing on the provided init_data argument. -- cgit v1.2.3-71-gd317 From d3504757f3f049b553ba0eda8bd17cd1f2651285 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 25 Oct 2019 11:41:24 +0200 Subject: debugfs: Add debugfs_create_xul() for hexadecimal unsigned long The existing debugfs_create_ulong() function supports objects of type "unsigned long", which are 32-bit or 64-bit depending on the platform, in decimal form. To format objects in hexadecimal, various debugfs_create_x*() functions exist, but all of them take fixed-size types. Add a debugfs helper for "unsigned long" objects in hexadecimal format. This avoids the need for users to open-code the same, or introduce bugs when casting the value pointer to "u32 *" or "u64 *" to call debugfs_create_x{32,64}(). Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20191025094130.26033-2-geert+renesas@glider.be Signed-off-by: Greg Kroah-Hartman --- Documentation/filesystems/debugfs.txt | 5 ++++- include/linux/debugfs.h | 21 +++++++++++++++++++++ 2 files changed, 25 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/debugfs.txt b/Documentation/filesystems/debugfs.txt index 36dac49e859f..dc497b96fa4f 100644 --- a/Documentation/filesystems/debugfs.txt +++ b/Documentation/filesystems/debugfs.txt @@ -102,11 +102,14 @@ functions meant to help out in such special cases: As might be expected, this function will create a debugfs file to represent a variable of type size_t. -Similarly, there is a helper for variables of type unsigned long: +Similarly, there are helpers for variables of type unsigned long, in decimal +and hexadecimal: struct dentry *debugfs_create_ulong(const char *name, umode_t mode, struct dentry *parent, unsigned long *value); + void debugfs_create_xul(const char *name, umode_t mode, + struct dentry *parent, unsigned long *value); Boolean values can be placed in debugfs with: diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 19231e618c16..0e8f2e0cb91f 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -351,4 +351,25 @@ static inline ssize_t debugfs_write_file_bool(struct file *file, #endif +/** + * debugfs_create_xul - create a debugfs file that is used to read and write an + * unsigned long value, formatted in hexadecimal + * @name: a pointer to a string containing the name of the file to create. + * @mode: the permission that the file should have + * @parent: a pointer to the parent dentry for this file. This should be a + * directory dentry if set. If this parameter is %NULL, then the + * file will be created in the root of the debugfs filesystem. + * @value: a pointer to the variable that the file should read to and write + * from. + */ +static inline void debugfs_create_xul(const char *name, umode_t mode, + struct dentry *parent, + unsigned long *value) +{ + if (sizeof(*value) == sizeof(u32)) + debugfs_create_x32(name, mode, parent, (u32 *)value); + else + debugfs_create_x64(name, mode, parent, (u64 *)value); +} + #endif -- cgit v1.2.3-71-gd317 From e86d5a02874c1364c50e1b532481835b54173ed2 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 4 Oct 2019 16:38:56 -0400 Subject: NFS: Convert struct nfs_fattr to use struct timespec64 NFSv4 supports 64-bit times, so we should switch to using struct timespec64 when decoding attributes. Signed-off-by: Trond Myklebust --- fs/nfs/inode.c | 54 +++++++++++++++++++++++------------------------ fs/nfs/internal.h | 2 +- fs/nfs/nfs2xdr.c | 2 +- fs/nfs/nfs3xdr.c | 2 +- fs/nfs/nfs4xdr.c | 14 ++++++------ include/linux/nfs_fs_sb.h | 2 +- include/linux/nfs_xdr.h | 12 +++++------ 7 files changed, 44 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 2a03bfeec10a..b0b4b9f303fd 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -504,15 +504,15 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st nfsi->read_cache_jiffies = fattr->time_start; nfsi->attr_gencount = fattr->gencount; if (fattr->valid & NFS_ATTR_FATTR_ATIME) - inode->i_atime = timespec_to_timespec64(fattr->atime); + inode->i_atime = fattr->atime; else if (nfs_server_capable(inode, NFS_CAP_ATIME)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME); if (fattr->valid & NFS_ATTR_FATTR_MTIME) - inode->i_mtime = timespec_to_timespec64(fattr->mtime); + inode->i_mtime = fattr->mtime; else if (nfs_server_capable(inode, NFS_CAP_MTIME)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME); if (fattr->valid & NFS_ATTR_FATTR_CTIME) - inode->i_ctime = timespec_to_timespec64(fattr->ctime); + inode->i_ctime = fattr->ctime; else if (nfs_server_capable(inode, NFS_CAP_CTIME)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_CTIME); if (fattr->valid & NFS_ATTR_FATTR_CHANGE) @@ -698,7 +698,7 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, if ((attr->ia_valid & ATTR_GID) != 0) inode->i_gid = attr->ia_gid; if (fattr->valid & NFS_ATTR_FATTR_CTIME) - inode->i_ctime = timespec_to_timespec64(fattr->ctime); + inode->i_ctime = fattr->ctime; else nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME); @@ -709,14 +709,14 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_ATIME | NFS_INO_INVALID_CTIME); if (fattr->valid & NFS_ATTR_FATTR_ATIME) - inode->i_atime = timespec_to_timespec64(fattr->atime); + inode->i_atime = fattr->atime; else if (attr->ia_valid & ATTR_ATIME_SET) inode->i_atime = attr->ia_atime; else nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME); if (fattr->valid & NFS_ATTR_FATTR_CTIME) - inode->i_ctime = timespec_to_timespec64(fattr->ctime); + inode->i_ctime = fattr->ctime; else nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME); @@ -725,14 +725,14 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_MTIME | NFS_INO_INVALID_CTIME); if (fattr->valid & NFS_ATTR_FATTR_MTIME) - inode->i_mtime = timespec_to_timespec64(fattr->mtime); + inode->i_mtime = fattr->mtime; else if (attr->ia_valid & ATTR_MTIME_SET) inode->i_mtime = attr->ia_mtime; else nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME); if (fattr->valid & NFS_ATTR_FATTR_CTIME) - inode->i_ctime = timespec_to_timespec64(fattr->ctime); + inode->i_ctime = fattr->ctime; else nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME); @@ -1351,7 +1351,7 @@ static bool nfs_file_has_buffered_writers(struct nfs_inode *nfsi) static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr) { - struct timespec ts; + struct timespec64 ts; if ((fattr->valid & NFS_ATTR_FATTR_PRECHANGE) && (fattr->valid & NFS_ATTR_FATTR_CHANGE) @@ -1361,18 +1361,18 @@ static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); } /* If we have atomic WCC data, we may update some attributes */ - ts = timespec64_to_timespec(inode->i_ctime); + ts = inode->i_ctime; if ((fattr->valid & NFS_ATTR_FATTR_PRECTIME) && (fattr->valid & NFS_ATTR_FATTR_CTIME) - && timespec_equal(&ts, &fattr->pre_ctime)) { - inode->i_ctime = timespec_to_timespec64(fattr->ctime); + && timespec64_equal(&ts, &fattr->pre_ctime)) { + inode->i_ctime = fattr->ctime; } - ts = timespec64_to_timespec(inode->i_mtime); + ts = inode->i_mtime; if ((fattr->valid & NFS_ATTR_FATTR_PREMTIME) && (fattr->valid & NFS_ATTR_FATTR_MTIME) - && timespec_equal(&ts, &fattr->pre_mtime)) { - inode->i_mtime = timespec_to_timespec64(fattr->mtime); + && timespec64_equal(&ts, &fattr->pre_mtime)) { + inode->i_mtime = fattr->mtime; if (S_ISDIR(inode->i_mode)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); } @@ -1398,7 +1398,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat struct nfs_inode *nfsi = NFS_I(inode); loff_t cur_size, new_isize; unsigned long invalid = 0; - struct timespec ts; + struct timespec64 ts; if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ)) return 0; @@ -1425,12 +1425,12 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat invalid |= NFS_INO_INVALID_CHANGE | NFS_INO_REVAL_PAGECACHE; - ts = timespec64_to_timespec(inode->i_mtime); - if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec_equal(&ts, &fattr->mtime)) + ts = inode->i_mtime; + if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec64_equal(&ts, &fattr->mtime)) invalid |= NFS_INO_INVALID_MTIME; - ts = timespec64_to_timespec(inode->i_ctime); - if ((fattr->valid & NFS_ATTR_FATTR_CTIME) && !timespec_equal(&ts, &fattr->ctime)) + ts = inode->i_ctime; + if ((fattr->valid & NFS_ATTR_FATTR_CTIME) && !timespec64_equal(&ts, &fattr->ctime)) invalid |= NFS_INO_INVALID_CTIME; if (fattr->valid & NFS_ATTR_FATTR_SIZE) { @@ -1460,8 +1460,8 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat if ((fattr->valid & NFS_ATTR_FATTR_NLINK) && inode->i_nlink != fattr->nlink) invalid |= NFS_INO_INVALID_OTHER; - ts = timespec64_to_timespec(inode->i_atime); - if ((fattr->valid & NFS_ATTR_FATTR_ATIME) && !timespec_equal(&ts, &fattr->atime)) + ts = inode->i_atime; + if ((fattr->valid & NFS_ATTR_FATTR_ATIME) && !timespec64_equal(&ts, &fattr->atime)) invalid |= NFS_INO_INVALID_ATIME; if (invalid != 0) @@ -1733,12 +1733,12 @@ int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fa } if ((fattr->valid & NFS_ATTR_FATTR_CTIME) != 0 && (fattr->valid & NFS_ATTR_FATTR_PRECTIME) == 0) { - fattr->pre_ctime = timespec64_to_timespec(inode->i_ctime); + fattr->pre_ctime = inode->i_ctime; fattr->valid |= NFS_ATTR_FATTR_PRECTIME; } if ((fattr->valid & NFS_ATTR_FATTR_MTIME) != 0 && (fattr->valid & NFS_ATTR_FATTR_PREMTIME) == 0) { - fattr->pre_mtime = timespec64_to_timespec(inode->i_mtime); + fattr->pre_mtime = inode->i_mtime; fattr->valid |= NFS_ATTR_FATTR_PREMTIME; } if ((fattr->valid & NFS_ATTR_FATTR_SIZE) != 0 && @@ -1899,7 +1899,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) } if (fattr->valid & NFS_ATTR_FATTR_MTIME) { - inode->i_mtime = timespec_to_timespec64(fattr->mtime); + inode->i_mtime = fattr->mtime; } else if (server->caps & NFS_CAP_MTIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_MTIME @@ -1908,7 +1908,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) } if (fattr->valid & NFS_ATTR_FATTR_CTIME) { - inode->i_ctime = timespec_to_timespec64(fattr->ctime); + inode->i_ctime = fattr->ctime; } else if (server->caps & NFS_CAP_CTIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_CTIME @@ -1946,7 +1946,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) if (fattr->valid & NFS_ATTR_FATTR_ATIME) - inode->i_atime = timespec_to_timespec64(fattr->atime); + inode->i_atime = fattr->atime; else if (server->caps & NFS_CAP_ATIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATIME diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 447a3c17fa8e..24a65da58aa9 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -713,7 +713,7 @@ unsigned int nfs_page_array_len(unsigned int base, size_t len) * 1024*1024*1024. */ static inline -u64 nfs_timespec_to_change_attr(const struct timespec *ts) +u64 nfs_timespec_to_change_attr(const struct timespec64 *ts) { return ((u64)ts->tv_sec << 30) + ts->tv_nsec; } diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index cbc17a203248..d4e144712034 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -234,7 +234,7 @@ static __be32 *xdr_encode_current_server_time(__be32 *p, return p; } -static __be32 *xdr_decode_time(__be32 *p, struct timespec *timep) +static __be32 *xdr_decode_time(__be32 *p, struct timespec64 *timep) { timep->tv_sec = be32_to_cpup(p++); timep->tv_nsec = be32_to_cpup(p++) * NSEC_PER_USEC; diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 602767850b36..2a16bbda3937 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -463,7 +463,7 @@ static __be32 *xdr_encode_nfstime3(__be32 *p, const struct timespec *timep) return p; } -static __be32 *xdr_decode_nfstime3(__be32 *p, struct timespec *timep) +static __be32 *xdr_decode_nfstime3(__be32 *p, struct timespec64 *timep) { timep->tv_sec = be32_to_cpup(p++); timep->tv_nsec = be32_to_cpup(p++); diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index ab07db0f07cd..2af962810ed8 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -4065,17 +4065,17 @@ static int decode_attr_space_used(struct xdr_stream *xdr, uint32_t *bitmap, uint } static __be32 * -xdr_decode_nfstime4(__be32 *p, struct timespec *t) +xdr_decode_nfstime4(__be32 *p, struct timespec64 *t) { __u64 sec; p = xdr_decode_hyper(p, &sec); - t-> tv_sec = (time_t)sec; + t-> tv_sec = sec; t->tv_nsec = be32_to_cpup(p++); return p; } -static int decode_attr_time(struct xdr_stream *xdr, struct timespec *time) +static int decode_attr_time(struct xdr_stream *xdr, struct timespec64 *time) { __be32 *p; @@ -4086,7 +4086,7 @@ static int decode_attr_time(struct xdr_stream *xdr, struct timespec *time) return 0; } -static int decode_attr_time_access(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec *time) +static int decode_attr_time_access(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec64 *time) { int status = 0; @@ -4104,7 +4104,7 @@ static int decode_attr_time_access(struct xdr_stream *xdr, uint32_t *bitmap, str return status; } -static int decode_attr_time_metadata(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec *time) +static int decode_attr_time_metadata(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec64 *time) { int status = 0; @@ -4123,7 +4123,7 @@ static int decode_attr_time_metadata(struct xdr_stream *xdr, uint32_t *bitmap, s } static int decode_attr_time_delta(struct xdr_stream *xdr, uint32_t *bitmap, - struct timespec *time) + struct timespec64 *time) { int status = 0; @@ -4186,7 +4186,7 @@ static int decode_attr_security_label(struct xdr_stream *xdr, uint32_t *bitmap, return status; } -static int decode_attr_time_modify(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec *time) +static int decode_attr_time_modify(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec64 *time) { int status = 0; diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index a87fe854f008..47266870a235 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -171,7 +171,7 @@ struct nfs_server { struct nfs_fsid fsid; __u64 maxfilesize; /* maximum file size */ - struct timespec time_delta; /* smallest time granularity */ + struct timespec64 time_delta; /* smallest time granularity */ unsigned long mount_time; /* when this fs was mounted */ struct super_block *super; /* VFS super block */ dev_t s_dev; /* superblock dev numbers */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 9b8324ec08f3..db5c01001937 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -62,14 +62,14 @@ struct nfs_fattr { struct nfs_fsid fsid; __u64 fileid; __u64 mounted_on_fileid; - struct timespec atime; - struct timespec mtime; - struct timespec ctime; + struct timespec64 atime; + struct timespec64 mtime; + struct timespec64 ctime; __u64 change_attr; /* NFSv4 change attribute */ __u64 pre_change_attr;/* pre-op NFSv4 change attribute */ __u64 pre_size; /* pre_op_attr.size */ - struct timespec pre_mtime; /* pre_op_attr.mtime */ - struct timespec pre_ctime; /* pre_op_attr.ctime */ + struct timespec64 pre_mtime; /* pre_op_attr.mtime */ + struct timespec64 pre_ctime; /* pre_op_attr.ctime */ unsigned long time_start; unsigned long gencount; struct nfs4_string *owner_name; @@ -143,7 +143,7 @@ struct nfs_fsinfo { __u32 wtmult; /* writes should be multiple of this */ __u32 dtpref; /* pref. readdir transfer size */ __u64 maxfilesize; - struct timespec time_delta; /* server time granularity */ + struct timespec64 time_delta; /* server time granularity */ __u32 lease_time; /* in seconds */ __u32 nlayouttypes; /* number of layouttypes */ __u32 layouttype[NFS_MAX_LAYOUT_TYPES]; /* supported pnfs layout driver */ -- cgit v1.2.3-71-gd317 From 6430b323ae09f146dfc26e6d17c432bfc3d11452 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 4 Oct 2019 17:00:02 -0400 Subject: NFSv3: Clean up timespec encode Simplify the struct iattr timestamp encoding by skipping the step of an intermediate struct timespec. Signed-off-by: Trond Myklebust --- fs/nfs/nfs3xdr.c | 12 ++++-------- include/linux/nfs_xdr.h | 2 +- 2 files changed, 5 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 2a16bbda3937..927eb680f161 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -456,9 +456,9 @@ static void zero_nfs_fh3(struct nfs_fh *fh) * uint32 nseconds; * }; */ -static __be32 *xdr_encode_nfstime3(__be32 *p, const struct timespec *timep) +static __be32 *xdr_encode_nfstime3(__be32 *p, const struct timespec64 *timep) { - *p++ = cpu_to_be32(timep->tv_sec); + *p++ = cpu_to_be32((u32)timep->tv_sec); *p++ = cpu_to_be32(timep->tv_nsec); return p; } @@ -533,7 +533,6 @@ static __be32 *xdr_decode_nfstime3(__be32 *p, struct timespec64 *timep) static void encode_sattr3(struct xdr_stream *xdr, const struct iattr *attr, struct user_namespace *userns) { - struct timespec ts; u32 nbytes; __be32 *p; @@ -583,10 +582,8 @@ static void encode_sattr3(struct xdr_stream *xdr, const struct iattr *attr, *p++ = xdr_zero; if (attr->ia_valid & ATTR_ATIME_SET) { - struct timespec ts; *p++ = xdr_two; - ts = timespec64_to_timespec(attr->ia_atime); - p = xdr_encode_nfstime3(p, &ts); + p = xdr_encode_nfstime3(p, &attr->ia_atime); } else if (attr->ia_valid & ATTR_ATIME) { *p++ = xdr_one; } else @@ -594,8 +591,7 @@ static void encode_sattr3(struct xdr_stream *xdr, const struct iattr *attr, if (attr->ia_valid & ATTR_MTIME_SET) { *p++ = xdr_two; - ts = timespec64_to_timespec(attr->ia_mtime); - xdr_encode_nfstime3(p, &ts); + xdr_encode_nfstime3(p, &attr->ia_mtime); } else if (attr->ia_valid & ATTR_MTIME) { *p = xdr_one; } else diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index db5c01001937..22bc6613474e 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -869,7 +869,7 @@ struct nfs3_sattrargs { struct nfs_fh * fh; struct iattr * sattr; unsigned int guard; - struct timespec guardtime; + struct timespec64 guardtime; }; struct nfs3_diropargs { -- cgit v1.2.3-71-gd317 From 4b1b69cedf9de8c203101ea74510c07d428538f7 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 3 Oct 2019 14:08:43 -0400 Subject: NFS: Add a flag to tell nfs_client to set RPC_CLNT_CREATE_NOPING Add a flag to tell the nfs_client it should set RPC_CLNT_CREATE_NOPING when creating the rpc client. Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 2 ++ include/linux/nfs_fs_sb.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 30838304a0bf..fa7d92328c72 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -515,6 +515,8 @@ int nfs_create_rpc_client(struct nfs_client *clp, args.flags |= RPC_CLNT_CREATE_NONPRIVPORT; if (test_bit(NFS_CS_INFINITE_SLOTS, &clp->cl_flags)) args.flags |= RPC_CLNT_CREATE_INFINITE_SLOTS; + if (test_bit(NFS_CS_NOPING, &clp->cl_flags)) + args.flags |= RPC_CLNT_CREATE_NOPING; if (!IS_ERR(clp->cl_rpcclient)) return 0; diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 47266870a235..a50dd432475b 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -45,6 +45,7 @@ struct nfs_client { #define NFS_CS_INFINITE_SLOTS 3 /* - don't limit TCP slots */ #define NFS_CS_NO_RETRANS_TIMEOUT 4 /* - Disable retransmit timeouts */ #define NFS_CS_TSM_POSSIBLE 5 /* - Maybe state migration */ +#define NFS_CS_NOPING 6 /* - don't ping on connect */ struct sockaddr_storage cl_addr; /* server identifier */ size_t cl_addrlen; char * cl_hostname; /* hostname of server */ -- cgit v1.2.3-71-gd317 From 52f98f1a2ddd2bb561f2c7e3b19a81d816a63118 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 17 Oct 2019 09:49:45 -0400 Subject: NFS/pnfs: Separate NFSv3 DS and MDS traffic If a NFSv3 server is being used as both a DS and as a regular NFSv3 server, we may want to keep the IO traffic on a separate TCP connection, since it will typically have very different timeout characteristics. This patch therefore sets up a flag to separate the two modes of operation for the nfs_client. Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 6 ++++++ fs/nfs/nfs3client.c | 1 + include/linux/nfs_fs_sb.h | 1 + 3 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index fa7d92328c72..bd6575ee3b8e 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -312,6 +312,12 @@ again: /* Match nfsv4 minorversion */ if (clp->cl_minorversion != data->minorversion) continue; + + /* Match request for a dedicated DS */ + if (test_bit(NFS_CS_DS, &data->init_flags) != + test_bit(NFS_CS_DS, &clp->cl_flags)) + continue; + /* Match the full socket address */ if (!rpc_cmp_addr_port(sap, clap)) /* Match all xprt_switch full socket addresses */ diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c index 793fa4273edb..223904bc40a7 100644 --- a/fs/nfs/nfs3client.c +++ b/fs/nfs/nfs3client.c @@ -109,6 +109,7 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv, __set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags); __set_bit(NFS_CS_NOPING, &cl_init.init_flags); + __set_bit(NFS_CS_DS, &cl_init.init_flags); /* Use the MDS nfs_client cl_ipaddr. */ nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans); diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index a50dd432475b..69e80cef5a81 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -46,6 +46,7 @@ struct nfs_client { #define NFS_CS_NO_RETRANS_TIMEOUT 4 /* - Disable retransmit timeouts */ #define NFS_CS_TSM_POSSIBLE 5 /* - Maybe state migration */ #define NFS_CS_NOPING 6 /* - don't ping on connect */ +#define NFS_CS_DS 7 /* - Server is a DS */ struct sockaddr_storage cl_addr; /* server identifier */ size_t cl_addrlen; char * cl_hostname; /* hostname of server */ -- cgit v1.2.3-71-gd317 From e6237b6feb37582fbd6bd7a8336d1256a6b4b4f9 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 17 Oct 2019 11:13:54 -0400 Subject: NFSv4.1: Don't rebind to the same source port when reconnecting to the server NFSv2, v3 and NFSv4 servers often have duplicate replay caches that look at the source port when deciding whether or not an RPC call is a replay of a previous call. This requires clients to perform strange TCP gymnastics in order to ensure that when they reconnect to the server, they bind to the same source port. NFSv4.1 and NFSv4.2 have sessions that provide proper replay semantics, that do not look at the source port of the connection. This patch therefore ensures they can ignore the rebind requirement. Signed-off-by: Trond Myklebust --- fs/lockd/host.c | 3 ++- fs/nfs/client.c | 3 +++ fs/nfs/nfs4client.c | 5 ++++- include/linux/nfs_fs_sb.h | 1 + include/linux/sunrpc/clnt.h | 1 + include/linux/sunrpc/xprt.h | 3 ++- net/sunrpc/clnt.c | 7 ++++++- net/sunrpc/xprtsock.c | 2 +- 8 files changed, 20 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/lockd/host.c b/fs/lockd/host.c index 7d46fafdbbe5..0afb6d59bad0 100644 --- a/fs/lockd/host.c +++ b/fs/lockd/host.c @@ -464,7 +464,8 @@ nlm_bind_host(struct nlm_host *host) .version = host->h_version, .authflavor = RPC_AUTH_UNIX, .flags = (RPC_CLNT_CREATE_NOPING | - RPC_CLNT_CREATE_AUTOBIND), + RPC_CLNT_CREATE_AUTOBIND | + RPC_CLNT_CREATE_REUSEPORT), .cred = host->h_cred, }; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index bd6575ee3b8e..02110a30a49e 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -523,6 +523,8 @@ int nfs_create_rpc_client(struct nfs_client *clp, args.flags |= RPC_CLNT_CREATE_INFINITE_SLOTS; if (test_bit(NFS_CS_NOPING, &clp->cl_flags)) args.flags |= RPC_CLNT_CREATE_NOPING; + if (test_bit(NFS_CS_REUSEPORT, &clp->cl_flags)) + args.flags |= RPC_CLNT_CREATE_REUSEPORT; if (!IS_ERR(clp->cl_rpcclient)) return 0; @@ -670,6 +672,7 @@ static int nfs_init_server(struct nfs_server *server, .timeparms = &timeparms, .cred = server->cred, .nconnect = data->nfs_server.nconnect, + .init_flags = (1UL << NFS_CS_REUSEPORT), }; struct nfs_client *clp; int error; diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index ebc960dd89ff..abd5af77fe94 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -879,8 +879,11 @@ static int nfs4_set_client(struct nfs_server *server, }; struct nfs_client *clp; - if (minorversion > 0 && proto == XPRT_TRANSPORT_TCP) + if (minorversion == 0) + __set_bit(NFS_CS_REUSEPORT, &cl_init.init_flags); + else if (proto == XPRT_TRANSPORT_TCP) cl_init.nconnect = nconnect; + if (server->flags & NFS_MOUNT_NORESVPORT) __set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags); if (server->options & NFS_OPTION_MIGRATION) diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 69e80cef5a81..df61ff8981e8 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -47,6 +47,7 @@ struct nfs_client { #define NFS_CS_TSM_POSSIBLE 5 /* - Maybe state migration */ #define NFS_CS_NOPING 6 /* - don't ping on connect */ #define NFS_CS_DS 7 /* - Server is a DS */ +#define NFS_CS_REUSEPORT 8 /* - reuse src port on reconnect */ struct sockaddr_storage cl_addr; /* server identifier */ size_t cl_addrlen; char * cl_hostname; /* hostname of server */ diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index abc63bd1be2b..ec52e78d432b 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -149,6 +149,7 @@ struct rpc_add_xprt_test { #define RPC_CLNT_CREATE_NO_IDLE_TIMEOUT (1UL << 8) #define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT (1UL << 9) #define RPC_CLNT_CREATE_SOFTERR (1UL << 10) +#define RPC_CLNT_CREATE_REUSEPORT (1UL << 11) struct rpc_clnt *rpc_create(struct rpc_create_args *args); struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *, diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index d783e15ba898..ccd35cf4fc41 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -207,7 +207,8 @@ struct rpc_xprt { unsigned int min_reqs; /* min number of slots */ unsigned int num_reqs; /* total slots */ unsigned long state; /* transport state */ - unsigned char resvport : 1; /* use a reserved port */ + unsigned char resvport : 1, /* use a reserved port */ + reuseport : 1; /* reuse port on reconnect */ atomic_t swapper; /* we're swapping over this transport */ unsigned int bind_index; /* bind function index */ diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index f7f78566be46..5baf9b9be2e8 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -591,6 +591,9 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) xprt->resvport = 1; if (args->flags & RPC_CLNT_CREATE_NONPRIVPORT) xprt->resvport = 0; + xprt->reuseport = 0; + if (args->flags & RPC_CLNT_CREATE_REUSEPORT) + xprt->reuseport = 1; clnt = rpc_create_xprt(args, xprt); if (IS_ERR(clnt) || args->nconnect <= 1) @@ -2906,7 +2909,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt; unsigned long connect_timeout; unsigned long reconnect_timeout; - unsigned char resvport; + unsigned char resvport, reuseport; int ret = 0; rcu_read_lock(); @@ -2918,6 +2921,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, return -EAGAIN; } resvport = xprt->resvport; + reuseport = xprt->reuseport; connect_timeout = xprt->connect_timeout; reconnect_timeout = xprt->max_reconnect_timeout; rcu_read_unlock(); @@ -2928,6 +2932,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, goto out_put_switch; } xprt->resvport = resvport; + xprt->reuseport = reuseport; if (xprt->ops->set_connect_timeout != NULL) xprt->ops->set_connect_timeout(xprt, connect_timeout, diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 70e52f567b2a..98e2d40b2d6a 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1752,7 +1752,7 @@ static void xs_set_port(struct rpc_xprt *xprt, unsigned short port) static void xs_set_srcport(struct sock_xprt *transport, struct socket *sock) { - if (transport->srcport == 0) + if (transport->srcport == 0 && transport->xprt.reuseport) transport->srcport = xs_sock_getport(sock); } -- cgit v1.2.3-71-gd317 From c7d3d28360fdb3ed3a5aa0bab19315e0fdc994a1 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 1 Nov 2019 17:45:31 +0100 Subject: quota: Factor out setup of quota inode Factor out setting up of quota inode and eventual error cleanup from vfs_load_quota_inode(). This will simplify situation for filesystems that don't have any quota inodes. Signed-off-by: Jan Kara --- fs/quota/dquot.c | 108 +++++++++++++++++++++++++++++------------------ include/linux/quotaops.h | 2 + 2 files changed, 69 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 6e826b454082..9e8eb6e71675 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2299,28 +2299,60 @@ EXPORT_SYMBOL(dquot_quota_off); * Turn quotas on on a device */ -/* - * Helper function to turn quotas on when we already have the inode of - * quota file and no quota information is loaded. - */ -static int vfs_load_quota_inode(struct inode *inode, int type, int format_id, +static int vfs_setup_quota_inode(struct inode *inode, int type) +{ + struct super_block *sb = inode->i_sb; + struct quota_info *dqopt = sb_dqopt(sb); + + if (!S_ISREG(inode->i_mode)) + return -EACCES; + if (IS_RDONLY(inode)) + return -EROFS; + if (sb_has_quota_loaded(sb, type)) + return -EBUSY; + + dqopt->files[type] = igrab(inode); + if (!dqopt->files[type]) + return -EIO; + if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) { + /* We don't want quota and atime on quota files (deadlocks + * possible) Also nobody should write to the file - we use + * special IO operations which ignore the immutable bit. */ + inode_lock(inode); + inode->i_flags |= S_NOQUOTA; + inode_unlock(inode); + /* + * When S_NOQUOTA is set, remove dquot references as no more + * references can be added + */ + __dquot_drop(inode); + } + return 0; +} + +static void vfs_cleanup_quota_inode(struct super_block *sb, int type) +{ + struct quota_info *dqopt = sb_dqopt(sb); + struct inode *inode = dqopt->files[type]; + + if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) { + inode_lock(inode); + inode->i_flags &= ~S_NOQUOTA; + inode_unlock(inode); + } + dqopt->files[type] = NULL; + iput(inode); +} + +int dquot_load_quota_sb(struct super_block *sb, int type, int format_id, unsigned int flags) { struct quota_format_type *fmt = find_quota_format(format_id); - struct super_block *sb = inode->i_sb; struct quota_info *dqopt = sb_dqopt(sb); int error; if (!fmt) return -ESRCH; - if (!S_ISREG(inode->i_mode)) { - error = -EACCES; - goto out_fmt; - } - if (IS_RDONLY(inode)) { - error = -EROFS; - goto out_fmt; - } if (!sb->s_op->quota_write || !sb->s_op->quota_read || (type == PRJQUOTA && sb->dq_op->get_projid == NULL)) { error = -EINVAL; @@ -2352,27 +2384,9 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id, invalidate_bdev(sb->s_bdev); } - if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) { - /* We don't want quota and atime on quota files (deadlocks - * possible) Also nobody should write to the file - we use - * special IO operations which ignore the immutable bit. */ - inode_lock(inode); - inode->i_flags |= S_NOQUOTA; - inode_unlock(inode); - /* - * When S_NOQUOTA is set, remove dquot references as no more - * references can be added - */ - __dquot_drop(inode); - } - - error = -EIO; - dqopt->files[type] = igrab(inode); - if (!dqopt->files[type]) - goto out_file_flags; error = -EINVAL; if (!fmt->qf_ops->check_quota_file(sb, type)) - goto out_file_init; + goto out_fmt; dqopt->ops[type] = fmt->qf_ops; dqopt->info[type].dqi_format = fmt; @@ -2380,7 +2394,7 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id, INIT_LIST_HEAD(&dqopt->info[type].dqi_dirty_list); error = dqopt->ops[type]->read_file_info(sb, type); if (error < 0) - goto out_file_init; + goto out_fmt; if (dqopt->flags & DQUOT_QUOTA_SYS_FILE) { spin_lock(&dq_data_lock); dqopt->info[type].dqi_flags |= DQF_SYS_FILE; @@ -2395,18 +2409,30 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id, dquot_disable(sb, type, flags); return error; -out_file_init: - dqopt->files[type] = NULL; - iput(inode); -out_file_flags: - inode_lock(inode); - inode->i_flags &= ~S_NOQUOTA; - inode_unlock(inode); out_fmt: put_quota_format(fmt); return error; } +EXPORT_SYMBOL(dquot_load_quota_sb); + +/* + * Helper function to turn quotas on when we already have the inode of + * quota file and no quota information is loaded. + */ +static int vfs_load_quota_inode(struct inode *inode, int type, int format_id, + unsigned int flags) +{ + int err; + + err = vfs_setup_quota_inode(inode, type); + if (err < 0) + return err; + err = dquot_load_quota_sb(inode->i_sb, type, format_id, flags); + if (err < 0) + vfs_cleanup_quota_inode(inode->i_sb, type); + return err; +} /* Reenable quotas on remount RW */ int dquot_resume(struct super_block *sb, int type) diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 185d94829701..2625766bcfe7 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -89,6 +89,8 @@ int dquot_file_open(struct inode *inode, struct file *file); int dquot_enable(struct inode *inode, int type, int format_id, unsigned int flags); +int dquot_load_quota_sb(struct super_block *sb, int type, int format_id, + unsigned int flags); int dquot_quota_on(struct super_block *sb, int type, int format_id, const struct path *path); int dquot_quota_on_mount(struct super_block *sb, char *qf_name, -- cgit v1.2.3-71-gd317 From dc19432ae1c22d696f91edea11ae06c348b4e88a Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 1 Nov 2019 18:37:44 +0100 Subject: quota: Rename vfs_load_quota_inode() to dquot_load_quota_inode() Rename vfs_load_quota_inode() to dquot_load_quota_inode() to be consistent with naming of other functions used for enabling quota accounting from filesystems. Also export the function and add some sanity checks to assure filesystems are calling the function properly. Signed-off-by: Jan Kara --- fs/quota/dquot.c | 19 +++++++++++++------ include/linux/quotaops.h | 2 ++ 2 files changed, 15 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index ecdae91029ed..0ddcbce596f8 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2351,6 +2351,12 @@ int dquot_load_quota_sb(struct super_block *sb, int type, int format_id, struct quota_info *dqopt = sb_dqopt(sb); int error; + /* Just unsuspend quotas? */ + BUG_ON(flags & DQUOT_SUSPENDED); + /* s_umount should be held in exclusive mode */ + if (WARN_ON_ONCE(down_read_trylock(&sb->s_umount))) + up_read(&sb->s_umount); + if (!fmt) return -ESRCH; if (!sb->s_op->quota_write || !sb->s_op->quota_read || @@ -2417,10 +2423,10 @@ out_fmt: EXPORT_SYMBOL(dquot_load_quota_sb); /* - * Helper function to turn quotas on when we already have the inode of - * quota file and no quota information is loaded. + * More powerful function for turning on quotas on given quota inode allowing + * setting of individual quota flags */ -static int vfs_load_quota_inode(struct inode *inode, int type, int format_id, +int dquot_load_quota_inode(struct inode *inode, int type, int format_id, unsigned int flags) { int err; @@ -2433,6 +2439,7 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id, vfs_cleanup_quota_inode(inode->i_sb, type); return err; } +EXPORT_SYMBOL(dquot_load_quota_inode); /* Reenable quotas on remount RW */ int dquot_resume(struct super_block *sb, int type) @@ -2479,7 +2486,7 @@ int dquot_quota_on(struct super_block *sb, int type, int format_id, if (path->dentry->d_sb != sb) error = -EXDEV; else - error = vfs_load_quota_inode(d_inode(path->dentry), type, + error = dquot_load_quota_inode(d_inode(path->dentry), type, format_id, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); return error; @@ -2517,7 +2524,7 @@ int dquot_enable(struct inode *inode, int type, int format_id, return 0; } - return vfs_load_quota_inode(inode, type, format_id, flags); + return dquot_load_quota_inode(inode, type, format_id, flags); } EXPORT_SYMBOL(dquot_enable); @@ -2542,7 +2549,7 @@ int dquot_quota_on_mount(struct super_block *sb, char *qf_name, error = security_quota_on(dentry); if (!error) - error = vfs_load_quota_inode(d_inode(dentry), type, format_id, + error = dquot_load_quota_inode(d_inode(dentry), type, format_id, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); out: diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 2625766bcfe7..0ce9da5a1a93 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -91,6 +91,8 @@ int dquot_enable(struct inode *inode, int type, int format_id, unsigned int flags); int dquot_load_quota_sb(struct super_block *sb, int type, int format_id, unsigned int flags); +int dquot_load_quota_inode(struct inode *inode, int type, int format_id, + unsigned int flags); int dquot_quota_on(struct super_block *sb, int type, int format_id, const struct path *path); int dquot_quota_on_mount(struct super_block *sb, char *qf_name, -- cgit v1.2.3-71-gd317 From 069a9166369773627e51c5249cd7f9169aecd7fa Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 1 Nov 2019 18:57:56 +0100 Subject: quota: Drop dquot_enable() Now dquot_enable() has only two internal callers and both of them just need to update quota flags and don't need most of checks. Just drop dquot_enable() and fold necessary functionality into the two calling places. Signed-off-by: Jan Kara --- fs/quota/dquot.c | 61 +++++++++++++----------------------------------- include/linux/quotaops.h | 2 -- 2 files changed, 16 insertions(+), 47 deletions(-) (limited to 'include/linux') diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 0ddcbce596f8..3e4cf0d10955 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2493,41 +2493,6 @@ int dquot_quota_on(struct super_block *sb, int type, int format_id, } EXPORT_SYMBOL(dquot_quota_on); -/* - * More powerful function for turning on quotas allowing setting - * of individual quota flags - */ -int dquot_enable(struct inode *inode, int type, int format_id, - unsigned int flags) -{ - struct super_block *sb = inode->i_sb; - - /* Just unsuspend quotas? */ - BUG_ON(flags & DQUOT_SUSPENDED); - /* s_umount should be held in exclusive mode */ - if (WARN_ON_ONCE(down_read_trylock(&sb->s_umount))) - up_read(&sb->s_umount); - - if (!flags) - return 0; - /* Just updating flags needed? */ - if (sb_has_quota_loaded(sb, type)) { - if (flags & DQUOT_USAGE_ENABLED && - sb_has_quota_usage_enabled(sb, type)) - return -EBUSY; - if (flags & DQUOT_LIMITS_ENABLED && - sb_has_quota_limits_enabled(sb, type)) - return -EBUSY; - spin_lock(&dq_state_lock); - sb_dqopt(sb)->flags |= dquot_state_flag(flags, type); - spin_unlock(&dq_state_lock); - return 0; - } - - return dquot_load_quota_inode(inode, type, format_id, flags); -} -EXPORT_SYMBOL(dquot_enable); - /* * This function is used when filesystem needs to initialize quotas * during mount time. @@ -2574,13 +2539,17 @@ static int dquot_quota_enable(struct super_block *sb, unsigned int flags) if (!(flags & qtype_enforce_flag(type))) continue; /* Can't enforce without accounting */ - if (!sb_has_quota_usage_enabled(sb, type)) - return -EINVAL; - ret = dquot_enable(dqopt->files[type], type, - dqopt->info[type].dqi_fmt_id, - DQUOT_LIMITS_ENABLED); - if (ret < 0) + if (!sb_has_quota_usage_enabled(sb, type)) { + ret = -EINVAL; + goto out_err; + } + if (sb_has_quota_limits_enabled(sb, type)) { + ret = -EBUSY; goto out_err; + } + spin_lock(&dq_state_lock); + dqopt->flags |= dquot_state_flag(DQUOT_LIMITS_ENABLED, type); + spin_unlock(&dq_state_lock); } return 0; out_err: @@ -2630,10 +2599,12 @@ static int dquot_quota_disable(struct super_block *sb, unsigned int flags) out_err: /* Backout enforcement disabling we already did */ for (type--; type >= 0; type--) { - if (flags & qtype_enforce_flag(type)) - dquot_enable(dqopt->files[type], type, - dqopt->info[type].dqi_fmt_id, - DQUOT_LIMITS_ENABLED); + if (flags & qtype_enforce_flag(type)) { + spin_lock(&dq_state_lock); + dqopt->flags |= + dquot_state_flag(DQUOT_LIMITS_ENABLED, type); + spin_unlock(&dq_state_lock); + } } return ret; } diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 0ce9da5a1a93..6b8ebc8d715e 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -87,8 +87,6 @@ int dquot_mark_dquot_dirty(struct dquot *dquot); int dquot_file_open(struct inode *inode, struct file *file); -int dquot_enable(struct inode *inode, int type, int format_id, - unsigned int flags); int dquot_load_quota_sb(struct super_block *sb, int type, int format_id, unsigned int flags); int dquot_load_quota_inode(struct inode *inode, int type, int format_id, -- cgit v1.2.3-71-gd317 From c6919d5e0cd168a732034d8dc19fdc3dff683a2b Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Tue, 8 Oct 2019 15:25:59 +0300 Subject: usb: roles: Add usb_role_switch_find_by_fwnode() Simple wrapper function that searches USB role switches with class_find_device_by_fwnode(). Signed-off-by: Heikki Krogerus Reviewed-by: Hans de Goede Tested-by: Hans de Goede Link: https://lore.kernel.org/r/20191008122600.22340-2-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/roles/class.c | 21 +++++++++++++++++++++ include/linux/usb/role.h | 3 +++ 2 files changed, 24 insertions(+) (limited to 'include/linux') diff --git a/drivers/usb/roles/class.c b/drivers/usb/roles/class.c index 94b4e7db2b94..8273126ffdf4 100644 --- a/drivers/usb/roles/class.c +++ b/drivers/usb/roles/class.c @@ -175,6 +175,27 @@ void usb_role_switch_put(struct usb_role_switch *sw) } EXPORT_SYMBOL_GPL(usb_role_switch_put); +/** + * usb_role_switch_find_by_fwnode - Find USB role switch with its fwnode + * @fwnode: fwnode of the USB Role Switch + * + * Finds and returns role switch with @fwnode. The reference count for the + * found switch is incremented. + */ +struct usb_role_switch * +usb_role_switch_find_by_fwnode(const struct fwnode_handle *fwnode) +{ + struct device *dev; + + if (!fwnode) + return NULL; + + dev = class_find_device_by_fwnode(role_class, fwnode); + + return dev ? to_role_switch(dev) : NULL; +} +EXPORT_SYMBOL_GPL(usb_role_switch_find_by_fwnode); + static umode_t usb_role_switch_is_visible(struct kobject *kobj, struct attribute *attr, int n) { diff --git a/include/linux/usb/role.h b/include/linux/usb/role.h index 2d77f97df72d..efac3af83d6b 100644 --- a/include/linux/usb/role.h +++ b/include/linux/usb/role.h @@ -50,6 +50,9 @@ struct usb_role_switch *usb_role_switch_get(struct device *dev); struct usb_role_switch *fwnode_usb_role_switch_get(struct fwnode_handle *node); void usb_role_switch_put(struct usb_role_switch *sw); +struct usb_role_switch * +usb_role_switch_find_by_fwnode(const struct fwnode_handle *fwnode); + struct usb_role_switch * usb_role_switch_register(struct device *parent, const struct usb_role_switch_desc *desc); -- cgit v1.2.3-71-gd317 From 51f421c85c880dcb37df11e672b384eaa4444328 Mon Sep 17 00:00:00 2001 From: Revanth Rajashekar Date: Thu, 31 Oct 2019 10:13:21 -0600 Subject: block: sed-opal: Add support to read/write opal tables generically This feature gives the user RW access to any opal table with admin1 authority. The flags described in the new structure determines if the user wants to read/write the data. Flags are checked for valid values in order to allow future features to be added to the ioctl. The user can provide the desired table's UID. Also, the ioctl provides a size and offset field and internally will loop data accesses to return the full data block. Read overrun is prevented by the initiator's sec_send_recv() backend. The ioctl provides a private field with the intention to accommodate any future expansions to the ioctl. Reviewed-by: Scott Bauer Reviewed-by: Jon Derrick Signed-off-by: Revanth Rajashekar Signed-off-by: Jens Axboe --- block/opal_proto.h | 1 - block/sed-opal.c | 172 ++++++++++++++++++++++++++++++++++++++++++ include/linux/sed-opal.h | 1 + include/uapi/linux/sed-opal.h | 20 +++++ 4 files changed, 193 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/block/opal_proto.h b/block/opal_proto.h index 5532412d567c..710911864e1d 100644 --- a/block/opal_proto.h +++ b/block/opal_proto.h @@ -76,7 +76,6 @@ enum opal_response_token { * Derived from: TCG_Storage_Architecture_Core_Spec_v2.01_r1.00 * Section: 6.3 Assigned UIDs */ -#define OPAL_UID_LENGTH 8 #define OPAL_METHOD_LENGTH 8 #define OPAL_MSID_KEYLEN 15 #define OPAL_UID_LENGTH_HALF 4 diff --git a/block/sed-opal.c b/block/sed-opal.c index d6e2ec0d8a3a..1d5afaaf0826 100644 --- a/block/sed-opal.c +++ b/block/sed-opal.c @@ -1967,6 +1967,113 @@ static int get_msid_cpin_pin(struct opal_dev *dev, void *data) return 0; } +static int write_table_data(struct opal_dev *dev, void *data) +{ + struct opal_read_write_table *write_tbl = data; + + return generic_table_write_data(dev, write_tbl->data, write_tbl->offset, + write_tbl->size, write_tbl->table_uid); +} + +static int read_table_data_cont(struct opal_dev *dev) +{ + int err; + const char *data_read; + + err = parse_and_check_status(dev); + if (err) + return err; + + dev->prev_d_len = response_get_string(&dev->parsed, 1, &data_read); + dev->prev_data = (void *)data_read; + if (!dev->prev_data) { + pr_debug("%s: Couldn't read data from the table.\n", __func__); + return OPAL_INVAL_PARAM; + } + + return 0; +} + +/* + * IO_BUFFER_LENGTH = 2048 + * sizeof(header) = 56 + * No. of Token Bytes in the Response = 11 + * MAX size of data that can be carried in response buffer + * at a time is : 2048 - (56 + 11) = 1981 = 0x7BD. + */ +#define OPAL_MAX_READ_TABLE (0x7BD) + +static int read_table_data(struct opal_dev *dev, void *data) +{ + struct opal_read_write_table *read_tbl = data; + int err; + size_t off = 0, max_read_size = OPAL_MAX_READ_TABLE; + u64 table_len, len; + u64 offset = read_tbl->offset, read_size = read_tbl->size - 1; + u8 __user *dst; + + err = generic_get_table_info(dev, read_tbl->table_uid, OPAL_TABLE_ROWS); + if (err) { + pr_debug("Couldn't get the table size\n"); + return err; + } + + table_len = response_get_u64(&dev->parsed, 4); + + /* Check if the user is trying to read from the table limits */ + if (read_size > table_len || offset > table_len - read_size) { + pr_debug("Read size exceeds the Table size limits (%llu vs. %llu)\n", + offset + read_size, table_len); + return -EINVAL; + } + + while (off < read_size) { + err = cmd_start(dev, read_tbl->table_uid, opalmethod[OPAL_GET]); + + add_token_u8(&err, dev, OPAL_STARTLIST); + add_token_u8(&err, dev, OPAL_STARTNAME); + add_token_u8(&err, dev, OPAL_STARTROW); + add_token_u64(&err, dev, offset + off); /* start row value */ + add_token_u8(&err, dev, OPAL_ENDNAME); + + add_token_u8(&err, dev, OPAL_STARTNAME); + add_token_u8(&err, dev, OPAL_ENDROW); + + len = min(max_read_size, (size_t)(read_size - off)); + add_token_u64(&err, dev, offset + off + len); /* end row value + */ + add_token_u8(&err, dev, OPAL_ENDNAME); + add_token_u8(&err, dev, OPAL_ENDLIST); + + if (err) { + pr_debug("Error building read table data command.\n"); + break; + } + + err = finalize_and_send(dev, read_table_data_cont); + if (err) + break; + + /* len+1: This includes the NULL terminator at the end*/ + if (dev->prev_d_len > len + 1) { + err = -EOVERFLOW; + break; + } + + dst = (u8 __user *)(uintptr_t)read_tbl->data; + if (copy_to_user(dst + off, dev->prev_data, dev->prev_d_len)) { + pr_debug("Error copying data to userspace\n"); + err = -EFAULT; + break; + } + dev->prev_data = NULL; + + off += len; + } + + return err; +} + static int end_opal_session(struct opal_dev *dev, void *data) { int err = 0; @@ -2453,6 +2560,68 @@ bool opal_unlock_from_suspend(struct opal_dev *dev) } EXPORT_SYMBOL(opal_unlock_from_suspend); +static int opal_read_table(struct opal_dev *dev, + struct opal_read_write_table *rw_tbl) +{ + const struct opal_step read_table_steps[] = { + { start_admin1LSP_opal_session, &rw_tbl->key }, + { read_table_data, rw_tbl }, + { end_opal_session, } + }; + int ret = 0; + + if (!rw_tbl->size) + return ret; + + return execute_steps(dev, read_table_steps, + ARRAY_SIZE(read_table_steps)); +} + +static int opal_write_table(struct opal_dev *dev, + struct opal_read_write_table *rw_tbl) +{ + const struct opal_step write_table_steps[] = { + { start_admin1LSP_opal_session, &rw_tbl->key }, + { write_table_data, rw_tbl }, + { end_opal_session, } + }; + int ret = 0; + + if (!rw_tbl->size) + return ret; + + return execute_steps(dev, write_table_steps, + ARRAY_SIZE(write_table_steps)); +} + +static int opal_generic_read_write_table(struct opal_dev *dev, + struct opal_read_write_table *rw_tbl) +{ + int ret, bit_set; + + mutex_lock(&dev->dev_lock); + setup_opal_dev(dev); + + bit_set = fls64(rw_tbl->flags) - 1; + switch (bit_set) { + case OPAL_READ_TABLE: + ret = opal_read_table(dev, rw_tbl); + break; + case OPAL_WRITE_TABLE: + ret = opal_write_table(dev, rw_tbl); + break; + default: + pr_debug("Invalid bit set in the flag (%016llx).\n", + rw_tbl->flags); + ret = -EINVAL; + break; + } + + mutex_unlock(&dev->dev_lock); + + return ret; +} + int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg) { void *p; @@ -2515,6 +2684,9 @@ int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg) case IOC_OPAL_PSID_REVERT_TPR: ret = opal_reverttper(dev, p, true); break; + case IOC_OPAL_GENERIC_TABLE_RW: + ret = opal_generic_read_write_table(dev, p); + break; default: break; } diff --git a/include/linux/sed-opal.h b/include/linux/sed-opal.h index 53c28d750a45..1ac0d712a9c3 100644 --- a/include/linux/sed-opal.h +++ b/include/linux/sed-opal.h @@ -42,6 +42,7 @@ static inline bool is_sed_ioctl(unsigned int cmd) case IOC_OPAL_PSID_REVERT_TPR: case IOC_OPAL_MBR_DONE: case IOC_OPAL_WRITE_SHADOW_MBR: + case IOC_OPAL_GENERIC_TABLE_RW: return true; } return false; diff --git a/include/uapi/linux/sed-opal.h b/include/uapi/linux/sed-opal.h index c6d035fa1b6c..6f5af1a84213 100644 --- a/include/uapi/linux/sed-opal.h +++ b/include/uapi/linux/sed-opal.h @@ -113,6 +113,25 @@ struct opal_shadow_mbr { __u64 size; }; +/* Opal table operations */ +enum opal_table_ops { + OPAL_READ_TABLE, + OPAL_WRITE_TABLE, +}; + +#define OPAL_UID_LENGTH 8 +struct opal_read_write_table { + struct opal_key key; + const __u64 data; + const __u8 table_uid[OPAL_UID_LENGTH]; + __u64 offset; + __u64 size; +#define OPAL_TABLE_READ (1 << OPAL_READ_TABLE) +#define OPAL_TABLE_WRITE (1 << OPAL_WRITE_TABLE) + __u64 flags; + __u64 priv; +}; + #define IOC_OPAL_SAVE _IOW('p', 220, struct opal_lock_unlock) #define IOC_OPAL_LOCK_UNLOCK _IOW('p', 221, struct opal_lock_unlock) #define IOC_OPAL_TAKE_OWNERSHIP _IOW('p', 222, struct opal_key) @@ -128,5 +147,6 @@ struct opal_shadow_mbr { #define IOC_OPAL_PSID_REVERT_TPR _IOW('p', 232, struct opal_key) #define IOC_OPAL_MBR_DONE _IOW('p', 233, struct opal_mbr_done) #define IOC_OPAL_WRITE_SHADOW_MBR _IOW('p', 234, struct opal_shadow_mbr) +#define IOC_OPAL_GENERIC_TABLE_RW _IOW('p', 235, struct opal_read_write_table) #endif /* _UAPI_SED_OPAL_H */ -- cgit v1.2.3-71-gd317 From 7162431dcf72032835d369c8d7b51311df407938 Mon Sep 17 00:00:00 2001 From: Miroslav Benes Date: Wed, 16 Oct 2019 13:33:13 +0200 Subject: ftrace: Introduce PERMANENT ftrace_ops flag Livepatch uses ftrace for redirection to new patched functions. It means that if ftrace is disabled, all live patched functions are disabled as well. Toggling global 'ftrace_enabled' sysctl thus affect it directly. It is not a problem per se, because only administrator can set sysctl values, but it still may be surprising. Introduce PERMANENT ftrace_ops flag to amend this. If the FTRACE_OPS_FL_PERMANENT is set on any ftrace ops, the tracing cannot be disabled by disabling ftrace_enabled. Equally, a callback with the flag set cannot be registered if ftrace_enabled is disabled. Link: http://lkml.kernel.org/r/20191016113316.13415-2-mbenes@suse.cz Reviewed-by: Petr Mladek Reviewed-by: Kamalesh Babulal Signed-off-by: Miroslav Benes Signed-off-by: Steven Rostedt (VMware) --- Documentation/trace/ftrace-uses.rst | 8 ++++++++ Documentation/trace/ftrace.rst | 4 +++- include/linux/ftrace.h | 3 +++ kernel/livepatch/patch.c | 3 ++- kernel/trace/ftrace.c | 23 +++++++++++++++++++++-- 5 files changed, 37 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/Documentation/trace/ftrace-uses.rst b/Documentation/trace/ftrace-uses.rst index 1fbc69894eed..740bd0224d35 100644 --- a/Documentation/trace/ftrace-uses.rst +++ b/Documentation/trace/ftrace-uses.rst @@ -170,6 +170,14 @@ FTRACE_OPS_FL_RCU a callback may be executed and RCU synchronization will not protect it. +FTRACE_OPS_FL_PERMANENT + If this is set on any ftrace ops, then the tracing cannot disabled by + writing 0 to the proc sysctl ftrace_enabled. Equally, a callback with + the flag set cannot be registered if ftrace_enabled is 0. + + Livepatch uses it not to lose the function redirection, so the system + stays protected. + Filtering which functions to trace ================================== diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst index e3060eedb22d..d2b5657ed33e 100644 --- a/Documentation/trace/ftrace.rst +++ b/Documentation/trace/ftrace.rst @@ -2976,7 +2976,9 @@ Note, the proc sysctl ftrace_enable is a big on/off switch for the function tracer. By default it is enabled (when function tracing is enabled in the kernel). If it is disabled, all function tracing is disabled. This includes not only the function tracers for ftrace, but -also for any other uses (perf, kprobes, stack tracing, profiling, etc). +also for any other uses (perf, kprobes, stack tracing, profiling, etc). It +cannot be disabled if there is a callback with FTRACE_OPS_FL_PERMANENT set +registered. Please disable this with care. diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 8a8cb3c401b2..8385cafe4f9f 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -142,6 +142,8 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops); * PID - Is affected by set_ftrace_pid (allows filtering on those pids) * RCU - Set when the ops can only be called when RCU is watching. * TRACE_ARRAY - The ops->private points to a trace_array descriptor. + * PERMANENT - Set when the ops is permanent and should not be affected by + * ftrace_enabled. */ enum { FTRACE_OPS_FL_ENABLED = 1 << 0, @@ -160,6 +162,7 @@ enum { FTRACE_OPS_FL_PID = 1 << 13, FTRACE_OPS_FL_RCU = 1 << 14, FTRACE_OPS_FL_TRACE_ARRAY = 1 << 15, + FTRACE_OPS_FL_PERMANENT = 1 << 16, }; #ifdef CONFIG_DYNAMIC_FTRACE diff --git a/kernel/livepatch/patch.c b/kernel/livepatch/patch.c index bd43537702bd..b552cf2d85f8 100644 --- a/kernel/livepatch/patch.c +++ b/kernel/livepatch/patch.c @@ -196,7 +196,8 @@ static int klp_patch_func(struct klp_func *func) ops->fops.func = klp_ftrace_handler; ops->fops.flags = FTRACE_OPS_FL_SAVE_REGS | FTRACE_OPS_FL_DYNAMIC | - FTRACE_OPS_FL_IPMODIFY; + FTRACE_OPS_FL_IPMODIFY | + FTRACE_OPS_FL_PERMANENT; list_add(&ops->node, &klp_ops); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f296d89be757..89e9128652ef 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -326,6 +326,8 @@ int __register_ftrace_function(struct ftrace_ops *ops) if (ops->flags & FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED) ops->flags |= FTRACE_OPS_FL_SAVE_REGS; #endif + if (!ftrace_enabled && (ops->flags & FTRACE_OPS_FL_PERMANENT)) + return -EBUSY; if (!core_kernel_data((unsigned long)ops)) ops->flags |= FTRACE_OPS_FL_DYNAMIC; @@ -6754,6 +6756,18 @@ int unregister_ftrace_function(struct ftrace_ops *ops) } EXPORT_SYMBOL_GPL(unregister_ftrace_function); +static bool is_permanent_ops_registered(void) +{ + struct ftrace_ops *op; + + do_for_each_ftrace_op(op, ftrace_ops_list) { + if (op->flags & FTRACE_OPS_FL_PERMANENT) + return true; + } while_for_each_ftrace_op(op); + + return false; +} + int ftrace_enable_sysctl(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, @@ -6771,8 +6785,6 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled)) goto out; - last_ftrace_enabled = !!ftrace_enabled; - if (ftrace_enabled) { /* we are starting ftrace again */ @@ -6783,12 +6795,19 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, ftrace_startup_sysctl(); } else { + if (is_permanent_ops_registered()) { + ftrace_enabled = true; + ret = -EBUSY; + goto out; + } + /* stopping ftrace calls (just send to ftrace_stub) */ ftrace_trace_function = ftrace_stub; ftrace_shutdown_sysctl(); } + last_ftrace_enabled = !!ftrace_enabled; out: mutex_unlock(&ftrace_lock); return ret; -- cgit v1.2.3-71-gd317 From 8c127a42af89c39560a8c5bd5accadaaa5741f8c Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Mon, 4 Nov 2019 17:24:19 +0300 Subject: usb: typec: Introduce typec_get_drvdata() Leaving the private driver_data pointer of the port device to the port drivers. Signed-off-by: Heikki Krogerus Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20191104142435.29960-3-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/class.c | 11 +++++++++++ include/linux/usb/typec.h | 4 ++++ 2 files changed, 15 insertions(+) (limited to 'include/linux') diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c index 7749933ffce5..51154634c2c0 100644 --- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -1488,6 +1488,16 @@ EXPORT_SYMBOL_GPL(typec_set_mode); /* --------------------------------------- */ +/** + * typec_get_drvdata - Return private driver data pointer + * @port: USB Type-C port + */ +void *typec_get_drvdata(struct typec_port *port) +{ + return dev_get_drvdata(&port->dev); +} +EXPORT_SYMBOL_GPL(typec_get_drvdata); + /** * typec_port_register_altmode - Register USB Type-C Port Alternate Mode * @port: USB Type-C Port that supports the alternate mode @@ -1591,6 +1601,7 @@ struct typec_port *typec_register_port(struct device *parent, port->dev.fwnode = cap->fwnode; port->dev.type = &typec_port_dev_type; dev_set_name(&port->dev, "port%d", id); + dev_set_drvdata(&port->dev, cap->driver_data); port->cap = kmemdup(cap, sizeof(*cap), GFP_KERNEL); if (!port->cap) { diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index 7df4ecabc78a..8b90cd77331c 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -179,6 +179,7 @@ struct typec_partner_desc { * @sw: Cable plug orientation switch * @mux: Multiplexer switch for Alternate/Accessory Modes * @fwnode: Optional fwnode of the port + * @driver_data: Private pointer for driver specific info * @try_role: Set data role preference for DRP port * @dr_set: Set Data Role * @pr_set: Set Power Role @@ -198,6 +199,7 @@ struct typec_capability { struct typec_switch *sw; struct typec_mux *mux; struct fwnode_handle *fwnode; + void *driver_data; int (*try_role)(const struct typec_capability *, int role); @@ -241,6 +243,8 @@ int typec_set_orientation(struct typec_port *port, enum typec_orientation typec_get_orientation(struct typec_port *port); int typec_set_mode(struct typec_port *port, int mode); +void *typec_get_drvdata(struct typec_port *port); + int typec_find_port_power_role(const char *name); int typec_find_power_role(const char *name); int typec_find_port_data_role(const char *name); -- cgit v1.2.3-71-gd317 From 46310e4dade2bc3b574d540e421e3aa9f32cfd5f Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Mon, 4 Nov 2019 17:24:20 +0300 Subject: usb: typec: Separate the operations vector Introducing struct typec_operations which has the same callbacks as struct typec_capability. The old callbacks are kept for now, but after all users have been converted, they will be removed. Signed-off-by: Heikki Krogerus Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20191104142435.29960-4-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/class.c | 39 +++++++++++++++++++++++++++++---------- include/linux/usb/typec.h | 20 ++++++++++++++++++++ 2 files changed, 49 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c index 51154634c2c0..b934a006535a 100644 --- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -54,6 +54,7 @@ struct typec_port { const struct typec_capability *orig_cap; /* to be removed */ const struct typec_capability *cap; + const struct typec_operations *ops; }; #define to_typec_port(_dev_) container_of(_dev_, struct typec_port, dev) @@ -956,7 +957,7 @@ preferred_role_store(struct device *dev, struct device_attribute *attr, return -EOPNOTSUPP; } - if (!port->cap->try_role) { + if (!port->cap->try_role && (!port->ops || !port->ops->try_role)) { dev_dbg(dev, "Setting preferred role not supported\n"); return -EOPNOTSUPP; } @@ -969,7 +970,10 @@ preferred_role_store(struct device *dev, struct device_attribute *attr, return -EINVAL; } - ret = port->cap->try_role(port->orig_cap, role); + if (port->ops && port->ops->try_role) + ret = port->ops->try_role(port, role); + else + ret = port->cap->try_role(port->orig_cap, role); if (ret) return ret; @@ -1000,7 +1004,7 @@ static ssize_t data_role_store(struct device *dev, struct typec_port *port = to_typec_port(dev); int ret; - if (!port->cap->dr_set) { + if (!port->cap->dr_set && (!port->ops || !port->ops->dr_set)) { dev_dbg(dev, "data role swapping not supported\n"); return -EOPNOTSUPP; } @@ -1015,7 +1019,10 @@ static ssize_t data_role_store(struct device *dev, goto unlock_and_ret; } - ret = port->cap->dr_set(port->orig_cap, ret); + if (port->ops && port->ops->dr_set) + ret = port->ops->dr_set(port, ret); + else + ret = port->cap->dr_set(port->orig_cap, ret); if (ret) goto unlock_and_ret; @@ -1050,7 +1057,7 @@ static ssize_t power_role_store(struct device *dev, return -EOPNOTSUPP; } - if (!port->cap->pr_set) { + if (!port->cap->pr_set && (!port->ops || !port->ops->pr_set)) { dev_dbg(dev, "power role swapping not supported\n"); return -EOPNOTSUPP; } @@ -1072,7 +1079,10 @@ static ssize_t power_role_store(struct device *dev, goto unlock_and_ret; } - ret = port->cap->pr_set(port->orig_cap, ret); + if (port->ops && port->ops->dr_set) + ret = port->ops->pr_set(port, ret); + else + ret = port->cap->pr_set(port->orig_cap, ret); if (ret) goto unlock_and_ret; @@ -1103,7 +1113,8 @@ port_type_store(struct device *dev, struct device_attribute *attr, int ret; enum typec_port_type type; - if (!port->cap->port_type_set || port->cap->type != TYPEC_PORT_DRP) { + if (port->cap->type != TYPEC_PORT_DRP || (!port->cap->port_type_set && + (!port->ops || !port->ops->port_type_set))) { dev_dbg(dev, "changing port type not supported\n"); return -EOPNOTSUPP; } @@ -1120,7 +1131,10 @@ port_type_store(struct device *dev, struct device_attribute *attr, goto unlock_and_ret; } - ret = port->cap->port_type_set(port->orig_cap, type); + if (port->ops && port->ops->port_type_set) + ret = port->ops->port_type_set(port, type); + else + ret = port->cap->port_type_set(port->orig_cap, type); if (ret) goto unlock_and_ret; @@ -1176,7 +1190,7 @@ static ssize_t vconn_source_store(struct device *dev, return -EOPNOTSUPP; } - if (!port->cap->vconn_set) { + if (!port->cap->vconn_set && (!port->ops || !port->ops->vconn_set)) { dev_dbg(dev, "VCONN swapping not supported\n"); return -EOPNOTSUPP; } @@ -1185,7 +1199,11 @@ static ssize_t vconn_source_store(struct device *dev, if (ret) return ret; - ret = port->cap->vconn_set(port->orig_cap, (enum typec_role)source); + if (port->ops && port->ops->vconn_set) + ret = port->ops->vconn_set(port, (enum typec_role)source); + else + ret = port->cap->vconn_set(port->orig_cap, + (enum typec_role)source); if (ret) return ret; @@ -1591,6 +1609,7 @@ struct typec_port *typec_register_port(struct device *parent, mutex_init(&port->port_type_lock); port->id = id; + port->ops = cap->ops; port->orig_cap = cap; port->port_type = cap->type; port->prefer_role = cap->prefer_role; diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index 8b90cd77331c..c9bef128453b 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -168,6 +168,23 @@ struct typec_partner_desc { struct usb_pd_identity *identity; }; +/** + * struct typec_operations - USB Type-C Port Operations + * @try_role: Set data role preference for DRP port + * @dr_set: Set Data Role + * @pr_set: Set Power Role + * @vconn_set: Source VCONN + * @port_type_set: Set port type + */ +struct typec_operations { + int (*try_role)(struct typec_port *port, int role); + int (*dr_set)(struct typec_port *port, enum typec_data_role role); + int (*pr_set)(struct typec_port *port, enum typec_role role); + int (*vconn_set)(struct typec_port *port, enum typec_role role); + int (*port_type_set)(struct typec_port *port, + enum typec_port_type type); +}; + /* * struct typec_capability - USB Type-C Port Capabilities * @type: Supported power role of the port @@ -180,6 +197,7 @@ struct typec_partner_desc { * @mux: Multiplexer switch for Alternate/Accessory Modes * @fwnode: Optional fwnode of the port * @driver_data: Private pointer for driver specific info + * @ops: Port operations vector * @try_role: Set data role preference for DRP port * @dr_set: Set Data Role * @pr_set: Set Power Role @@ -201,6 +219,8 @@ struct typec_capability { struct fwnode_handle *fwnode; void *driver_data; + const struct typec_operations *ops; + int (*try_role)(const struct typec_capability *, int role); -- cgit v1.2.3-71-gd317 From 8c038ea8b65fc803cd35423b8a1ff7057dd52f8b Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Mon, 4 Nov 2019 17:24:25 +0300 Subject: usb: typec: Remove the callback members from struct typec_capability There are no more users for them. Signed-off-by: Heikki Krogerus Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20191104142435.29960-9-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/class.c | 40 +++++++++++----------------------------- include/linux/usb/typec.h | 17 ----------------- 2 files changed, 11 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c index b934a006535a..7ece6ca6e690 100644 --- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -52,7 +52,6 @@ struct typec_port { struct typec_switch *sw; struct typec_mux *mux; - const struct typec_capability *orig_cap; /* to be removed */ const struct typec_capability *cap; const struct typec_operations *ops; }; @@ -957,7 +956,7 @@ preferred_role_store(struct device *dev, struct device_attribute *attr, return -EOPNOTSUPP; } - if (!port->cap->try_role && (!port->ops || !port->ops->try_role)) { + if (!port->ops || !port->ops->try_role) { dev_dbg(dev, "Setting preferred role not supported\n"); return -EOPNOTSUPP; } @@ -970,10 +969,7 @@ preferred_role_store(struct device *dev, struct device_attribute *attr, return -EINVAL; } - if (port->ops && port->ops->try_role) - ret = port->ops->try_role(port, role); - else - ret = port->cap->try_role(port->orig_cap, role); + ret = port->ops->try_role(port, role); if (ret) return ret; @@ -1004,7 +1000,7 @@ static ssize_t data_role_store(struct device *dev, struct typec_port *port = to_typec_port(dev); int ret; - if (!port->cap->dr_set && (!port->ops || !port->ops->dr_set)) { + if (!port->ops || !port->ops->dr_set) { dev_dbg(dev, "data role swapping not supported\n"); return -EOPNOTSUPP; } @@ -1019,10 +1015,7 @@ static ssize_t data_role_store(struct device *dev, goto unlock_and_ret; } - if (port->ops && port->ops->dr_set) - ret = port->ops->dr_set(port, ret); - else - ret = port->cap->dr_set(port->orig_cap, ret); + ret = port->ops->dr_set(port, ret); if (ret) goto unlock_and_ret; @@ -1057,7 +1050,7 @@ static ssize_t power_role_store(struct device *dev, return -EOPNOTSUPP; } - if (!port->cap->pr_set && (!port->ops || !port->ops->pr_set)) { + if (!port->ops || !port->ops->pr_set) { dev_dbg(dev, "power role swapping not supported\n"); return -EOPNOTSUPP; } @@ -1079,10 +1072,7 @@ static ssize_t power_role_store(struct device *dev, goto unlock_and_ret; } - if (port->ops && port->ops->dr_set) - ret = port->ops->pr_set(port, ret); - else - ret = port->cap->pr_set(port->orig_cap, ret); + ret = port->ops->pr_set(port, ret); if (ret) goto unlock_and_ret; @@ -1113,8 +1103,8 @@ port_type_store(struct device *dev, struct device_attribute *attr, int ret; enum typec_port_type type; - if (port->cap->type != TYPEC_PORT_DRP || (!port->cap->port_type_set && - (!port->ops || !port->ops->port_type_set))) { + if (port->cap->type != TYPEC_PORT_DRP || + !port->ops || !port->ops->port_type_set) { dev_dbg(dev, "changing port type not supported\n"); return -EOPNOTSUPP; } @@ -1131,10 +1121,7 @@ port_type_store(struct device *dev, struct device_attribute *attr, goto unlock_and_ret; } - if (port->ops && port->ops->port_type_set) - ret = port->ops->port_type_set(port, type); - else - ret = port->cap->port_type_set(port->orig_cap, type); + ret = port->ops->port_type_set(port, type); if (ret) goto unlock_and_ret; @@ -1190,7 +1177,7 @@ static ssize_t vconn_source_store(struct device *dev, return -EOPNOTSUPP; } - if (!port->cap->vconn_set && (!port->ops || !port->ops->vconn_set)) { + if (!port->ops || !port->ops->vconn_set) { dev_dbg(dev, "VCONN swapping not supported\n"); return -EOPNOTSUPP; } @@ -1199,11 +1186,7 @@ static ssize_t vconn_source_store(struct device *dev, if (ret) return ret; - if (port->ops && port->ops->vconn_set) - ret = port->ops->vconn_set(port, (enum typec_role)source); - else - ret = port->cap->vconn_set(port->orig_cap, - (enum typec_role)source); + ret = port->ops->vconn_set(port, (enum typec_role)source); if (ret) return ret; @@ -1610,7 +1593,6 @@ struct typec_port *typec_register_port(struct device *parent, port->id = id; port->ops = cap->ops; - port->orig_cap = cap; port->port_type = cap->type; port->prefer_role = cap->prefer_role; diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index c9bef128453b..894798084319 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -198,11 +198,6 @@ struct typec_operations { * @fwnode: Optional fwnode of the port * @driver_data: Private pointer for driver specific info * @ops: Port operations vector - * @try_role: Set data role preference for DRP port - * @dr_set: Set Data Role - * @pr_set: Set Power Role - * @vconn_set: Set VCONN Role - * @port_type_set: Set port type * * Static capabilities of a single USB Type-C port. */ @@ -220,18 +215,6 @@ struct typec_capability { void *driver_data; const struct typec_operations *ops; - - int (*try_role)(const struct typec_capability *, - int role); - - int (*dr_set)(const struct typec_capability *, - enum typec_data_role); - int (*pr_set)(const struct typec_capability *, - enum typec_role); - int (*vconn_set)(const struct typec_capability *, - enum typec_role); - int (*port_type_set)(const struct typec_capability *, - enum typec_port_type); }; /* Specific to try_role(). Indicates the user want's to clear the preference. */ -- cgit v1.2.3-71-gd317 From 61d78ee29a0bf1078ebf5bbb2ccab7e7998d7410 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Mon, 4 Nov 2019 17:24:26 +0300 Subject: usb: typec: Remove unused members from struct typec_capability The members for the muxes are not used, so dropping them. Signed-off-by: Heikki Krogerus Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20191104142435.29960-10-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index 894798084319..0f52723a11bd 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -209,8 +209,6 @@ struct typec_capability { int prefer_role; enum typec_accessory accessory[TYPEC_MAX_ACCESSORY]; - struct typec_switch *sw; - struct typec_mux *mux; struct fwnode_handle *fwnode; void *driver_data; -- cgit v1.2.3-71-gd317 From 5eb0e0e4f90addc6b79ebf1cb4b06b56b09f09de Mon Sep 17 00:00:00 2001 From: Vivek Gautam Date: Fri, 20 Sep 2019 13:34:28 +0530 Subject: firmware/qcom_scm: Add scm call to handle smmu errata Qcom's smmu-500 needs to toggle wait-for-safe sequence to handle TLB invalidation sync's. Few firmwares allow doing that through SCM interface. Add API to toggle wait for safe from firmware through a SCM call. Signed-off-by: Vivek Gautam Reviewed-by: Bjorn Andersson Reviewed-by: Stephen Boyd Acked-by: Andy Gross Signed-off-by: Sai Prakash Ranjan Signed-off-by: Will Deacon --- drivers/firmware/qcom_scm-32.c | 5 +++++ drivers/firmware/qcom_scm-64.c | 13 +++++++++++++ drivers/firmware/qcom_scm.c | 6 ++++++ drivers/firmware/qcom_scm.h | 5 +++++ include/linux/qcom_scm.h | 2 ++ 5 files changed, 31 insertions(+) (limited to 'include/linux') diff --git a/drivers/firmware/qcom_scm-32.c b/drivers/firmware/qcom_scm-32.c index 215061c581e1..bee8729525ec 100644 --- a/drivers/firmware/qcom_scm-32.c +++ b/drivers/firmware/qcom_scm-32.c @@ -614,3 +614,8 @@ int __qcom_scm_io_writel(struct device *dev, phys_addr_t addr, unsigned int val) return qcom_scm_call_atomic2(QCOM_SCM_SVC_IO, QCOM_SCM_IO_WRITE, addr, val); } + +int __qcom_scm_qsmmu500_wait_safe_toggle(struct device *dev, bool enable) +{ + return -ENODEV; +} diff --git a/drivers/firmware/qcom_scm-64.c b/drivers/firmware/qcom_scm-64.c index 872155c67b2d..e1cd933ea9ae 100644 --- a/drivers/firmware/qcom_scm-64.c +++ b/drivers/firmware/qcom_scm-64.c @@ -552,3 +552,16 @@ int __qcom_scm_io_writel(struct device *dev, phys_addr_t addr, unsigned int val) return qcom_scm_call(dev, QCOM_SCM_SVC_IO, QCOM_SCM_IO_WRITE, &desc, &res); } + +int __qcom_scm_qsmmu500_wait_safe_toggle(struct device *dev, bool en) +{ + struct qcom_scm_desc desc = {0}; + struct arm_smccc_res res; + + desc.args[0] = QCOM_SCM_CONFIG_ERRATA1_CLIENT_ALL; + desc.args[1] = en; + desc.arginfo = QCOM_SCM_ARGS(2); + + return qcom_scm_call_atomic(dev, QCOM_SCM_SVC_SMMU_PROGRAM, + QCOM_SCM_CONFIG_ERRATA1, &desc, &res); +} diff --git a/drivers/firmware/qcom_scm.c b/drivers/firmware/qcom_scm.c index 4802ab170fe5..a729e05c21b8 100644 --- a/drivers/firmware/qcom_scm.c +++ b/drivers/firmware/qcom_scm.c @@ -345,6 +345,12 @@ int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare) } EXPORT_SYMBOL(qcom_scm_iommu_secure_ptbl_init); +int qcom_scm_qsmmu500_wait_safe_toggle(bool en) +{ + return __qcom_scm_qsmmu500_wait_safe_toggle(__scm->dev, en); +} +EXPORT_SYMBOL(qcom_scm_qsmmu500_wait_safe_toggle); + int qcom_scm_io_readl(phys_addr_t addr, unsigned int *val) { return __qcom_scm_io_readl(__scm->dev, addr, val); diff --git a/drivers/firmware/qcom_scm.h b/drivers/firmware/qcom_scm.h index 99506bd873c0..baee744dbcfe 100644 --- a/drivers/firmware/qcom_scm.h +++ b/drivers/firmware/qcom_scm.h @@ -91,10 +91,15 @@ extern int __qcom_scm_restore_sec_cfg(struct device *dev, u32 device_id, u32 spare); #define QCOM_SCM_IOMMU_SECURE_PTBL_SIZE 3 #define QCOM_SCM_IOMMU_SECURE_PTBL_INIT 4 +#define QCOM_SCM_SVC_SMMU_PROGRAM 0x15 +#define QCOM_SCM_CONFIG_ERRATA1 0x3 +#define QCOM_SCM_CONFIG_ERRATA1_CLIENT_ALL 0x2 extern int __qcom_scm_iommu_secure_ptbl_size(struct device *dev, u32 spare, size_t *size); extern int __qcom_scm_iommu_secure_ptbl_init(struct device *dev, u64 addr, u32 size, u32 spare); +extern int __qcom_scm_qsmmu500_wait_safe_toggle(struct device *dev, + bool enable); #define QCOM_MEM_PROT_ASSIGN_ID 0x16 extern int __qcom_scm_assign_mem(struct device *dev, phys_addr_t mem_region, size_t mem_sz, diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index 2d5eff506e13..ffd72b3b14ee 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -58,6 +58,7 @@ extern int qcom_scm_set_remote_state(u32 state, u32 id); extern int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare); extern int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size); extern int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare); +extern int qcom_scm_qsmmu500_wait_safe_toggle(bool en); extern int qcom_scm_io_readl(phys_addr_t addr, unsigned int *val); extern int qcom_scm_io_writel(phys_addr_t addr, unsigned int val); #else @@ -97,6 +98,7 @@ qcom_scm_set_remote_state(u32 state,u32 id) { return -ENODEV; } static inline int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare) { return -ENODEV; } static inline int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size) { return -ENODEV; } static inline int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare) { return -ENODEV; } +static inline int qcom_scm_qsmmu500_wait_safe_toggle(bool en) { return -ENODEV; } static inline int qcom_scm_io_readl(phys_addr_t addr, unsigned int *val) { return -ENODEV; } static inline int qcom_scm_io_writel(phys_addr_t addr, unsigned int val) { return -ENODEV; } #endif -- cgit v1.2.3-71-gd317 From f16583614222d015968541f2e50447c67c277f74 Mon Sep 17 00:00:00 2001 From: James Smart Date: Fri, 27 Sep 2019 14:51:34 -0700 Subject: nvme-fc: Sync nvme-fc header to FC-NVME-2 Sync the header to FC-NVME-2 r1.06 (T11-2019-00210-v001). Includes some minor mods where pre-release field names changed by the time the spec was released. Signed-off-by: James Smart Signed-off-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/nvme-fc.h | 182 ++++++++++++++++++++++++++++++++++++------------ 1 file changed, 137 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme-fc.h b/include/linux/nvme-fc.h index 067c9fea64fe..e8c30b39bb27 100644 --- a/include/linux/nvme-fc.h +++ b/include/linux/nvme-fc.h @@ -4,33 +4,60 @@ */ /* - * This file contains definitions relative to FC-NVME r1.14 (16-020vB). - * The fcnvme_lsdesc_cr_assoc_cmd struct reflects expected r1.16 content. + * This file contains definitions relative to FC-NVME-2 r1.06 + * (T11-2019-00210-v001). */ #ifndef _NVME_FC_H #define _NVME_FC_H 1 +#include -#define NVME_CMD_SCSI_ID 0xFD +#define NVME_CMD_FORMAT_ID 0xFD #define NVME_CMD_FC_ID FC_TYPE_NVME /* FC-NVME Cmd IU Flags */ -#define FCNVME_CMD_FLAGS_DIRMASK 0x03 -#define FCNVME_CMD_FLAGS_WRITE 0x01 -#define FCNVME_CMD_FLAGS_READ 0x02 +enum { + FCNVME_CMD_FLAGS_DIRMASK = 0x03, + FCNVME_CMD_FLAGS_WRITE = (1 << 0), + FCNVME_CMD_FLAGS_READ = (1 << 1), + + FCNVME_CMD_FLAGS_PICWP = (1 << 2), +}; + +enum { + FCNVME_CMD_CAT_MASK = 0x0F, + FCNVME_CMD_CAT_ADMINQ = 0x01, + FCNVME_CMD_CAT_CSSMASK = 0x07, + FCNVME_CMD_CAT_CSSFLAG = 0x08, +}; + +static inline __u8 fccmnd_set_cat_admin(__u8 rsv_cat) +{ + return (rsv_cat & ~FCNVME_CMD_CAT_MASK) | FCNVME_CMD_CAT_ADMINQ; +} + +static inline __u8 fccmnd_set_cat_css(__u8 rsv_cat, __u8 css) +{ + return (rsv_cat & ~FCNVME_CMD_CAT_MASK) | FCNVME_CMD_CAT_CSSFLAG | + (css & FCNVME_CMD_CAT_CSSMASK); +} struct nvme_fc_cmd_iu { - __u8 scsi_id; + __u8 format_id; __u8 fc_id; __be16 iu_len; - __u8 rsvd4[3]; + __u8 rsvd4[2]; + __u8 rsv_cat; __u8 flags; __be64 connection_id; __be32 csn; __be32 data_len; struct nvme_command sqe; - __be32 rsvd88[2]; + __u8 dps; + __u8 lbads; + __be16 ms; + __be32 rsvd92; }; #define NVME_FC_SIZEOF_ZEROS_RSP 12 @@ -38,11 +65,12 @@ struct nvme_fc_cmd_iu { enum { FCNVME_SC_SUCCESS = 0, FCNVME_SC_INVALID_FIELD = 1, - FCNVME_SC_INVALID_CONNID = 2, + /* reserved 2 */ + FCNVME_SC_ILL_CONN_PARAMS = 3, }; struct nvme_fc_ersp_iu { - __u8 status_code; + __u8 ersp_result; __u8 rsvd1; __be16 iu_len; __be32 rsn; @@ -53,14 +81,44 @@ struct nvme_fc_ersp_iu { }; -/* FC-NVME Link Services */ +#define FCNVME_NVME_SR_OPCODE 0x01 + +struct nvme_fc_nvme_sr_iu { + __u8 fc_id; + __u8 opcode; + __u8 rsvd2; + __u8 retry_rctl; + __be32 rsvd4; +}; + + +enum { + FCNVME_SRSTAT_ACC = 0x0, + FCNVME_SRSTAT_INV_FCID = 0x1, + /* reserved 0x2 */ + FCNVME_SRSTAT_LOGICAL_ERR = 0x3, + FCNVME_SRSTAT_INV_QUALIF = 0x4, + FCNVME_SRSTAT_UNABL2PERFORM = 0x9, +}; + +struct nvme_fc_nvme_sr_rsp_iu { + __u8 fc_id; + __u8 opcode; + __u8 rsvd2; + __u8 status; + __be32 rsvd4; +}; + + +/* FC-NVME Link Services - LS cmd values (w0 bits 31:24) */ enum { FCNVME_LS_RSVD = 0, FCNVME_LS_RJT = 1, FCNVME_LS_ACC = 2, - FCNVME_LS_CREATE_ASSOCIATION = 3, - FCNVME_LS_CREATE_CONNECTION = 4, - FCNVME_LS_DISCONNECT = 5, + FCNVME_LS_CREATE_ASSOCIATION = 3, /* Create Association */ + FCNVME_LS_CREATE_CONNECTION = 4, /* Create I/O Connection */ + FCNVME_LS_DISCONNECT_ASSOC = 5, /* Disconnect Association */ + FCNVME_LS_DISCONNECT_CONN = 6, /* Disconnect Connection */ }; /* FC-NVME Link Service Descriptors */ @@ -117,14 +175,17 @@ enum fcnvme_ls_rjt_reason { FCNVME_RJT_RC_UNSUP = 0x0b, /* command not supported */ - FCNVME_RJT_RC_INPROG = 0x0e, - /* command already in progress */ - FCNVME_RJT_RC_INV_ASSOC = 0x40, - /* Invalid Association ID*/ + /* Invalid Association ID */ FCNVME_RJT_RC_INV_CONN = 0x41, - /* Invalid Connection ID*/ + /* Invalid Connection ID */ + + FCNVME_RJT_RC_INV_PARAM = 0x42, + /* Invalid Parameters */ + + FCNVME_RJT_RC_INSUF_RES = 0x43, + /* Insufficient Resources */ FCNVME_RJT_RC_VENDOR = 0xff, /* vendor specific error */ @@ -138,14 +199,32 @@ enum fcnvme_ls_rjt_explan { FCNVME_RJT_EXP_OXID_RXID = 0x17, /* invalid OX_ID-RX_ID combination */ - FCNVME_RJT_EXP_INSUF_RES = 0x29, - /* insufficient resources */ - FCNVME_RJT_EXP_UNAB_DATA = 0x2a, /* unable to supply requested data */ FCNVME_RJT_EXP_INV_LEN = 0x2d, /* Invalid payload length */ + + FCNVME_RJT_EXP_INV_ERSP_RAT = 0x40, + /* Invalid NVMe_ERSP Ratio */ + + FCNVME_RJT_EXP_INV_CTLR_ID = 0x41, + /* Invalid Controller ID */ + + FCNVME_RJT_EXP_INV_QUEUE_ID = 0x42, + /* Invalid Queue ID */ + + FCNVME_RJT_EXP_INV_SQSIZE = 0x43, + /* Invalid Submission Queue Size */ + + FCNVME_RJT_EXP_INV_HOSTID = 0x44, + /* Invalid HOST ID */ + + FCNVME_RJT_EXP_INV_HOSTNQN = 0x45, + /* Invalid HOSTNQN */ + + FCNVME_RJT_EXP_INV_SUBNQN = 0x46, + /* Invalid SUBNQN */ }; /* FCNVME_LSDESC_RJT */ @@ -209,21 +288,11 @@ struct fcnvme_lsdesc_cr_conn_cmd { __be32 rsvd52; }; -/* Disconnect Scope Values */ -enum { - FCNVME_DISCONN_ASSOCIATION = 0, - FCNVME_DISCONN_CONNECTION = 1, -}; - /* FCNVME_LSDESC_DISCONN_CMD */ struct fcnvme_lsdesc_disconn_cmd { __be32 desc_tag; /* FCNVME_LSDESC_xxx */ __be32 desc_len; - u8 rsvd8[3]; - /* note: scope is really a 1 bit field */ - u8 scope; /* FCNVME_DISCONN_xxx */ - __be32 rsvd12; - __be64 id; + __be32 rsvd8[4]; }; /* FCNVME_LSDESC_CONN_ID */ @@ -242,9 +311,14 @@ struct fcnvme_lsdesc_assoc_id { /* r_ctl values */ enum { - FCNVME_RS_RCTL_DATA = 1, - FCNVME_RS_RCTL_XFER_RDY = 5, - FCNVME_RS_RCTL_RSP = 8, + FCNVME_RS_RCTL_CMND = 0x6, + FCNVME_RS_RCTL_DATA = 0x1, + FCNVME_RS_RCTL_CONF = 0x3, + FCNVME_RS_RCTL_SR = 0x9, + FCNVME_RS_RCTL_XFER_RDY = 0x5, + FCNVME_RS_RCTL_RSP = 0x7, + FCNVME_RS_RCTL_ERSP = 0x8, + FCNVME_RS_RCTL_SR_RSP = 0xA, }; @@ -264,7 +338,10 @@ struct fcnvme_ls_acc_hdr { struct fcnvme_ls_rqst_w0 w0; __be32 desc_list_len; struct fcnvme_lsdesc_rqst rqst; - /* Followed by cmd-specific ACC descriptors, see next definitions */ + /* + * Followed by cmd-specific ACCEPT descriptors, see xxx_acc + * definitions below + */ }; /* FCNVME_LS_CREATE_ASSOCIATION */ @@ -302,25 +379,39 @@ struct fcnvme_ls_cr_conn_acc { struct fcnvme_lsdesc_conn_id connectid; }; -/* FCNVME_LS_DISCONNECT */ -struct fcnvme_ls_disconnect_rqst { +/* FCNVME_LS_DISCONNECT_ASSOC */ +struct fcnvme_ls_disconnect_assoc_rqst { struct fcnvme_ls_rqst_w0 w0; __be32 desc_list_len; struct fcnvme_lsdesc_assoc_id associd; struct fcnvme_lsdesc_disconn_cmd discon_cmd; }; -struct fcnvme_ls_disconnect_acc { +struct fcnvme_ls_disconnect_assoc_acc { + struct fcnvme_ls_acc_hdr hdr; +}; + + +/* FCNVME_LS_DISCONNECT_CONN */ +struct fcnvme_ls_disconnect_conn_rqst { + struct fcnvme_ls_rqst_w0 w0; + __be32 desc_list_len; + struct fcnvme_lsdesc_assoc_id associd; + struct fcnvme_lsdesc_disconn_cmd connectid; +}; + +struct fcnvme_ls_disconnect_conn_acc { struct fcnvme_ls_acc_hdr hdr; }; /* - * Yet to be defined in FC-NVME: + * Default R_A_TOV is pulled in from fc_fs.h but needs conversion + * from ms to seconds for our use. */ -#define NVME_FC_CONNECT_TIMEOUT_SEC 2 /* 2 seconds */ -#define NVME_FC_LS_TIMEOUT_SEC 2 /* 2 seconds */ -#define NVME_FC_TGTOP_TIMEOUT_SEC 2 /* 2 seconds */ +#define FC_TWO_TIMES_R_A_TOV (2 * (FC_DEF_R_A_TOV / 1000)) +#define NVME_FC_LS_TIMEOUT_SEC FC_TWO_TIMES_R_A_TOV +#define NVME_FC_TGTOP_TIMEOUT_SEC FC_TWO_TIMES_R_A_TOV /* * TRADDR string must be of form "nn-<16hexdigits>:pn-<16hexdigits>" @@ -328,6 +419,7 @@ struct fcnvme_ls_disconnect_acc { * infront of the <16hexdigits>. Without is considered the "min" string * and with is considered the "max" string. The hexdigits may be upper * or lower case. + * Note: FC-NVME-2 standard requires a "0x" prefix. */ #define NVME_FC_TRADDR_NNLEN 3 /* "?n-" */ #define NVME_FC_TRADDR_OXNNLEN 5 /* "?n-0x" */ -- cgit v1.2.3-71-gd317 From 2dc3947b53f573e8a75ea9cbec5588df88ca502e Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Sun, 13 Oct 2019 19:57:35 +0300 Subject: nvme: introduce "Command Aborted By host" status code Fix the status code of canceled requests initiated by the host according to TP4028 (Status Code 0x371): "Command Aborted By host: The command was aborted as a result of host action (e.g., the host disconnected the Fabric connection)." Also in a multipath environment, unless otherwise specified, errors of this type (path related) should be retried using a different path, if one is available. Signed-off-by: Max Gurtovoy Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 2 +- drivers/nvme/host/multipath.c | 1 + include/linux/nvme.h | 1 + 3 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index fd7dea36c3b6..dfa122beb4cf 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -298,7 +298,7 @@ bool nvme_cancel_request(struct request *req, void *data, bool reserved) if (blk_mq_request_completed(req)) return true; - nvme_req(req)->status = NVME_SC_HOST_PATH_ERROR; + nvme_req(req)->status = NVME_SC_HOST_ABORTED_CMD; blk_mq_complete_request(req); return true; } diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 30de7efef003..103c04fa7746 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -95,6 +95,7 @@ void nvme_failover_req(struct request *req) } break; case NVME_SC_HOST_PATH_ERROR: + case NVME_SC_HOST_ABORTED_CMD: /* * Temporary transport disruption in talking to the controller. * Try to send on a new path. diff --git a/include/linux/nvme.h b/include/linux/nvme.h index f61d6906e59d..a260cd754f28 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -1368,6 +1368,7 @@ enum { NVME_SC_ANA_INACCESSIBLE = 0x302, NVME_SC_ANA_TRANSITION = 0x303, NVME_SC_HOST_PATH_ERROR = 0x370, + NVME_SC_HOST_ABORTED_CMD = 0x371, NVME_SC_CRD = 0x1800, NVME_SC_DNR = 0x4000, -- cgit v1.2.3-71-gd317 From 48c9e85b23464a7d1e3ebd70b79cc3a2d97d3222 Mon Sep 17 00:00:00 2001 From: Revanth Rajashekar Date: Mon, 14 Oct 2019 11:16:07 -0600 Subject: nvme: resync include/linux/nvme.h with nvmecli Update enumerations and structures in include/linux/nvme.h to resync with the nvmecli. All the updates are mentioned in the ratified NVMe 1.4 spec https://nvmexpress.org/wp-content/uploads/NVM-Express-1_4-2019.06.10-Ratified.pdf Reviewed-by: Christoph Hellwig Signed-off-by: Revanth Rajashekar Signed-off-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/nvme.h | 53 +++++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 50 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index a260cd754f28..3eca4f7d8510 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -107,8 +107,22 @@ enum { NVME_REG_AQA = 0x0024, /* Admin Queue Attributes */ NVME_REG_ASQ = 0x0028, /* Admin SQ Base Address */ NVME_REG_ACQ = 0x0030, /* Admin CQ Base Address */ - NVME_REG_CMBLOC = 0x0038, /* Controller Memory Buffer Location */ + NVME_REG_CMBLOC = 0x0038, /* Controller Memory Buffer Location */ NVME_REG_CMBSZ = 0x003c, /* Controller Memory Buffer Size */ + NVME_REG_BPINFO = 0x0040, /* Boot Partition Information */ + NVME_REG_BPRSEL = 0x0044, /* Boot Partition Read Select */ + NVME_REG_BPMBL = 0x0048, /* Boot Partition Memory Buffer + * Location + */ + NVME_REG_PMRCAP = 0x0e00, /* Persistent Memory Capabilities */ + NVME_REG_PMRCTL = 0x0e04, /* Persistent Memory Region Control */ + NVME_REG_PMRSTS = 0x0e08, /* Persistent Memory Region Status */ + NVME_REG_PMREBS = 0x0e0c, /* Persistent Memory Region Elasticity + * Buffer Size + */ + NVME_REG_PMRSWTP = 0x0e10, /* Persistent Memory Region Sustained + * Write Throughput + */ NVME_REG_DBS = 0x1000, /* SQ 0 Tail Doorbell */ }; @@ -295,6 +309,14 @@ enum { NVME_CTRL_OACS_DIRECTIVES = 1 << 5, NVME_CTRL_OACS_DBBUF_SUPP = 1 << 8, NVME_CTRL_LPA_CMD_EFFECTS_LOG = 1 << 1, + NVME_CTRL_CTRATT_128_ID = 1 << 0, + NVME_CTRL_CTRATT_NON_OP_PSP = 1 << 1, + NVME_CTRL_CTRATT_NVM_SETS = 1 << 2, + NVME_CTRL_CTRATT_READ_RECV_LVLS = 1 << 3, + NVME_CTRL_CTRATT_ENDURANCE_GROUPS = 1 << 4, + NVME_CTRL_CTRATT_PREDICTABLE_LAT = 1 << 5, + NVME_CTRL_CTRATT_NAMESPACE_GRANULARITY = 1 << 7, + NVME_CTRL_CTRATT_UUID_LIST = 1 << 9, }; struct nvme_lbaf { @@ -352,6 +374,9 @@ enum { NVME_ID_CNS_NS_PRESENT = 0x11, NVME_ID_CNS_CTRL_NS_LIST = 0x12, NVME_ID_CNS_CTRL_LIST = 0x13, + NVME_ID_CNS_SCNDRY_CTRL_LIST = 0x15, + NVME_ID_CNS_NS_GRANULARITY = 0x16, + NVME_ID_CNS_UUID_LIST = 0x17, }; enum { @@ -409,7 +434,8 @@ struct nvme_smart_log { __u8 avail_spare; __u8 spare_thresh; __u8 percent_used; - __u8 rsvd6[26]; + __u8 endu_grp_crit_warn_sumry; + __u8 rsvd7[25]; __u8 data_units_read[16]; __u8 data_units_written[16]; __u8 host_reads[16]; @@ -423,7 +449,11 @@ struct nvme_smart_log { __le32 warning_temp_time; __le32 critical_comp_time; __le16 temp_sensor[8]; - __u8 rsvd216[296]; + __le32 thm_temp1_trans_count; + __le32 thm_temp2_trans_count; + __le32 thm_temp1_total_time; + __le32 thm_temp2_total_time; + __u8 rsvd232[280]; }; struct nvme_fw_slot_info_log { @@ -440,6 +470,7 @@ enum { NVME_CMD_EFFECTS_NIC = 1 << 3, NVME_CMD_EFFECTS_CCC = 1 << 4, NVME_CMD_EFFECTS_CSE_MASK = 3 << 16, + NVME_CMD_EFFECTS_UUID_SEL = 1 << 19, }; struct nvme_effects_log { @@ -563,6 +594,7 @@ enum nvme_opcode { nvme_cmd_compare = 0x05, nvme_cmd_write_zeroes = 0x08, nvme_cmd_dsm = 0x09, + nvme_cmd_verify = 0x0c, nvme_cmd_resv_register = 0x0d, nvme_cmd_resv_report = 0x0e, nvme_cmd_resv_acquire = 0x11, @@ -806,10 +838,14 @@ enum nvme_admin_opcode { nvme_admin_ns_mgmt = 0x0d, nvme_admin_activate_fw = 0x10, nvme_admin_download_fw = 0x11, + nvme_admin_dev_self_test = 0x14, nvme_admin_ns_attach = 0x15, nvme_admin_keep_alive = 0x18, nvme_admin_directive_send = 0x19, nvme_admin_directive_recv = 0x1a, + nvme_admin_virtual_mgmt = 0x1c, + nvme_admin_nvme_mi_send = 0x1d, + nvme_admin_nvme_mi_recv = 0x1e, nvme_admin_dbbuf = 0x7C, nvme_admin_format_nvm = 0x80, nvme_admin_security_send = 0x81, @@ -873,6 +909,7 @@ enum { NVME_FEAT_PLM_CONFIG = 0x13, NVME_FEAT_PLM_WINDOW = 0x14, NVME_FEAT_HOST_BEHAVIOR = 0x16, + NVME_FEAT_SANITIZE = 0x17, NVME_FEAT_SW_PROGRESS = 0x80, NVME_FEAT_HOST_ID = 0x81, NVME_FEAT_RESV_MASK = 0x82, @@ -883,6 +920,10 @@ enum { NVME_LOG_FW_SLOT = 0x03, NVME_LOG_CHANGED_NS = 0x04, NVME_LOG_CMD_EFFECTS = 0x05, + NVME_LOG_DEVICE_SELF_TEST = 0x06, + NVME_LOG_TELEMETRY_HOST = 0x07, + NVME_LOG_TELEMETRY_CTRL = 0x08, + NVME_LOG_ENDURANCE_GROUP = 0x09, NVME_LOG_ANA = 0x0c, NVME_LOG_DISC = 0x70, NVME_LOG_RESERVATION = 0x80, @@ -1290,7 +1331,11 @@ enum { NVME_SC_SGL_INVALID_OFFSET = 0x16, NVME_SC_SGL_INVALID_SUBTYPE = 0x17, + NVME_SC_SANITIZE_FAILED = 0x1C, + NVME_SC_SANITIZE_IN_PROGRESS = 0x1D, + NVME_SC_NS_WRITE_PROTECTED = 0x20, + NVME_SC_CMD_INTERRUPTED = 0x21, NVME_SC_LBA_RANGE = 0x80, NVME_SC_CAP_EXCEEDED = 0x81, @@ -1328,6 +1373,8 @@ enum { NVME_SC_NS_NOT_ATTACHED = 0x11a, NVME_SC_THIN_PROV_NOT_SUPP = 0x11b, NVME_SC_CTRL_LIST_INVALID = 0x11c, + NVME_SC_BP_WRITE_PROHIBITED = 0x11e, + NVME_SC_PMR_SAN_PROHIBITED = 0x123, /* * I/O Command Set Specific - NVM commands: -- cgit v1.2.3-71-gd317 From 0c65b2b90d13c1deaee6449304dd367c5d4eb8ae Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Mon, 4 Nov 2019 02:40:33 +0100 Subject: net: of_get_phy_mode: Change API to solve int/unit warnings Before this change of_get_phy_mode() returned an enum, phy_interface_t. On error, -ENODEV etc, is returned. If the result of the function is stored in a variable of type phy_interface_t, and the compiler has decided to represent this as an unsigned int, comparision with -ENODEV etc, is a signed vs unsigned comparision. Fix this problem by changing the API. Make the function return an error, or 0 on success, and pass a pointer, of type phy_interface_t, where the phy mode should be stored. v2: Return with *interface set to PHY_INTERFACE_MODE_NA on error. Add error checks to all users of of_get_phy_mode() Fixup a few reverse christmas tree errors Fixup a few slightly malformed reverse christmas trees v3: Fix 0-day reported errors. Reported-by: Dan Carpenter Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/bcm_sf2.c | 7 ++++--- drivers/net/dsa/microchip/ksz_common.c | 7 ++++--- drivers/net/dsa/mt7530.c | 8 ++++++-- drivers/net/dsa/qca8k.c | 9 +++++---- drivers/net/dsa/sja1105/sja1105_main.c | 7 ++++--- drivers/net/ethernet/altera/altera_tse_main.c | 6 +++--- drivers/net/ethernet/arc/emac_arc.c | 15 ++++++++++----- drivers/net/ethernet/arc/emac_rockchip.c | 7 +++++-- drivers/net/ethernet/atheros/ag71xx.c | 5 ++--- drivers/net/ethernet/aurora/nb8800.c | 4 ++-- drivers/net/ethernet/aurora/nb8800.h | 2 +- drivers/net/ethernet/broadcom/bcmsysport.c | 4 ++-- drivers/net/ethernet/broadcom/genet/bcmmii.c | 8 ++++---- drivers/net/ethernet/cadence/macb_main.c | 7 ++++--- drivers/net/ethernet/faraday/ftgmac100.c | 6 +++--- drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c | 7 ++++--- drivers/net/ethernet/freescale/enetc/enetc_pf.c | 4 ++-- drivers/net/ethernet/freescale/fec_main.c | 7 ++++--- drivers/net/ethernet/freescale/fman/mac.c | 6 +++--- drivers/net/ethernet/freescale/gianfar.c | 7 ++++--- drivers/net/ethernet/hisilicon/hip04_eth.c | 7 +++---- drivers/net/ethernet/hisilicon/hix5hd2_gmac.c | 5 ++--- drivers/net/ethernet/ibm/emac/core.c | 5 +++-- drivers/net/ethernet/marvell/mv643xx_eth.c | 7 ++++--- drivers/net/ethernet/marvell/mvneta.c | 7 +++---- drivers/net/ethernet/marvell/pxa168_eth.c | 4 +++- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 8 ++++---- drivers/net/ethernet/mscc/ocelot_board.c | 12 ++++++------ drivers/net/ethernet/ni/nixge.c | 5 ++--- drivers/net/ethernet/renesas/ravb_main.c | 4 +++- drivers/net/ethernet/renesas/sh_eth.c | 7 ++++--- drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c | 5 ++++- drivers/net/ethernet/socionext/sni_ave.c | 6 +++--- drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c | 10 +++++++--- drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c | 5 +++-- drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c | 9 +++++---- drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c | 5 ++--- drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c | 4 ++-- drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c | 9 +++++++-- drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 7 ++++--- drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c | 8 ++++++-- drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 6 +++--- drivers/net/ethernet/ti/cpsw.c | 5 ++--- drivers/net/ethernet/ti/cpsw_priv.h | 2 +- drivers/net/ethernet/ti/netcp_ethss.c | 5 +++-- drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 6 ++---- drivers/of/of_mdio.c | 4 ++-- drivers/of/of_net.c | 16 +++++++++++----- include/linux/of_net.h | 7 +++++-- include/linux/stmmac.h | 3 ++- include/linux/sxgbe_platform.h | 4 +++- net/dsa/port.c | 13 +++++++------ net/dsa/slave.c | 7 ++++--- 53 files changed, 201 insertions(+), 149 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 9add84c79dd6..67125a5487e1 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -381,8 +381,9 @@ static void bcm_sf2_identify_ports(struct bcm_sf2_priv *priv, struct device_node *dn) { struct device_node *port; - int mode; unsigned int port_num; + phy_interface_t mode; + int err; priv->moca_port = -1; @@ -395,8 +396,8 @@ static void bcm_sf2_identify_ports(struct bcm_sf2_priv *priv, * has completed, since they might be turned off at that * time */ - mode = of_get_phy_mode(port); - if (mode < 0) + err = of_get_phy_mode(port, &mode); + if (err) continue; if (mode == PHY_INTERFACE_MODE_INTERNAL) diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 5d08e4430824..d8fda4a02640 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -422,6 +422,7 @@ EXPORT_SYMBOL(ksz_switch_alloc); int ksz_switch_register(struct ksz_device *dev, const struct ksz_dev_ops *ops) { + phy_interface_t interface; int ret; if (dev->pdata) @@ -456,9 +457,9 @@ int ksz_switch_register(struct ksz_device *dev, * device tree. */ if (dev->dev->of_node) { - ret = of_get_phy_mode(dev->dev->of_node); - if (ret >= 0) - dev->interface = ret; + ret = of_get_phy_mode(dev->dev->of_node, &interface); + if (ret == 0) + dev->interface = interface; dev->synclko_125 = of_property_read_bool(dev->dev->of_node, "microchip,synclko-125"); } diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index add9e4279176..ed1ec10ec62b 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1340,7 +1340,9 @@ mt7530_setup(struct dsa_switch *ds) if (!dsa_is_unused_port(ds, 5)) { priv->p5_intf_sel = P5_INTF_SEL_GMAC5; - interface = of_get_phy_mode(dsa_to_port(ds, 5)->dn); + ret = of_get_phy_mode(dsa_to_port(ds, 5)->dn, &interface); + if (ret && ret != -ENODEV) + return ret; } else { /* Scan the ethernet nodes. look for GMAC1, lookup used phy */ for_each_child_of_node(dn, mac_np) { @@ -1354,7 +1356,9 @@ mt7530_setup(struct dsa_switch *ds) phy_node = of_parse_phandle(mac_np, "phy-handle", 0); if (phy_node->parent == priv->dev->of_node->parent) { - interface = of_get_phy_mode(mac_np); + ret = of_get_phy_mode(mac_np, &interface); + if (ret && ret != -ENODEV) + return ret; id = of_mdio_parse_addr(ds->dev, phy_node); if (id == 0) priv->p5_intf_sel = P5_INTF_SEL_PHY_P0; diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index 36c6ed98f8e7..e548289df31e 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -639,7 +639,8 @@ static int qca8k_setup(struct dsa_switch *ds) { struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv; - int ret, i, phy_mode = -1; + phy_interface_t phy_mode = PHY_INTERFACE_MODE_NA; + int ret, i; u32 mask; /* Make sure that port 0 is the cpu port */ @@ -661,10 +662,10 @@ qca8k_setup(struct dsa_switch *ds) return ret; /* Initialize CPU port pad mode (xMII type, delays...) */ - phy_mode = of_get_phy_mode(dsa_to_port(ds, QCA8K_CPU_PORT)->dn); - if (phy_mode < 0) { + ret = of_get_phy_mode(dsa_to_port(ds, QCA8K_CPU_PORT)->dn, &phy_mode); + if (ret) { pr_err("Can't find phy-mode for master device\n"); - return phy_mode; + return ret; } ret = qca8k_set_pad_ctrl(priv, QCA8K_CPU_PORT, phy_mode); if (ret < 0) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 2ae84a9dea59..d5dfda335aa1 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -584,8 +584,9 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv, for_each_child_of_node(ports_node, child) { struct device_node *phy_node; - int phy_mode; + phy_interface_t phy_mode; u32 index; + int err; /* Get switch port number from DT */ if (of_property_read_u32(child, "reg", &index) < 0) { @@ -596,8 +597,8 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv, } /* Get PHY mode from DT */ - phy_mode = of_get_phy_mode(child); - if (phy_mode < 0) { + err = of_get_phy_mode(child, &phy_mode); + if (err) { dev_err(dev, "Failed to read phy-mode or " "phy-interface-type property for port %d\n", index); diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index bb032be7fe31..4cd53fc338b5 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -730,12 +730,12 @@ static int altera_tse_phy_get_addr_mdio_create(struct net_device *dev) { struct altera_tse_private *priv = netdev_priv(dev); struct device_node *np = priv->device->of_node; - int ret = 0; + int ret; - priv->phy_iface = of_get_phy_mode(np); + ret = of_get_phy_mode(np, &priv->phy_iface); /* Avoid get phy addr and create mdio if no phy is present */ - if (!priv->phy_iface) + if (ret) return 0; /* try to get PHY address from device tree, use PHY autodetection if diff --git a/drivers/net/ethernet/arc/emac_arc.c b/drivers/net/ethernet/arc/emac_arc.c index 78e52d217e56..539166112993 100644 --- a/drivers/net/ethernet/arc/emac_arc.c +++ b/drivers/net/ethernet/arc/emac_arc.c @@ -20,9 +20,10 @@ static int emac_arc_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct net_device *ndev; struct arc_emac_priv *priv; - int interface, err; + phy_interface_t interface; + struct net_device *ndev; + int err; if (!dev->of_node) return -ENODEV; @@ -37,9 +38,13 @@ static int emac_arc_probe(struct platform_device *pdev) priv->drv_name = DRV_NAME; priv->drv_version = DRV_VERSION; - interface = of_get_phy_mode(dev->of_node); - if (interface < 0) - interface = PHY_INTERFACE_MODE_MII; + err = of_get_phy_mode(dev->of_node, &interface); + if (err) { + if (err == -ENODEV) + interface = PHY_INTERFACE_MODE_MII; + else + goto out_netdev; + } priv->clk = devm_clk_get(dev, "hclk"); if (IS_ERR(priv->clk)) { diff --git a/drivers/net/ethernet/arc/emac_rockchip.c b/drivers/net/ethernet/arc/emac_rockchip.c index 664d664e0925..aae231c5224f 100644 --- a/drivers/net/ethernet/arc/emac_rockchip.c +++ b/drivers/net/ethernet/arc/emac_rockchip.c @@ -97,8 +97,9 @@ static int emac_rockchip_probe(struct platform_device *pdev) struct net_device *ndev; struct rockchip_priv_data *priv; const struct of_device_id *match; + phy_interface_t interface; u32 data; - int err, interface; + int err; if (!pdev->dev.of_node) return -ENODEV; @@ -114,7 +115,9 @@ static int emac_rockchip_probe(struct platform_device *pdev) priv->emac.drv_version = DRV_VERSION; priv->emac.set_mac_speed = emac_rockchip_set_mac_speed; - interface = of_get_phy_mode(dev->of_node); + err = of_get_phy_mode(dev->of_node, &interface); + if (err) + goto out_netdev; /* RK3036/RK3066/RK3188 SoCs only support RMII */ if (interface != PHY_INTERFACE_MODE_RMII) { diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index 1b1a09095c0d..8f5021091eee 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -1744,10 +1744,9 @@ static int ag71xx_probe(struct platform_device *pdev) eth_random_addr(ndev->dev_addr); } - ag->phy_if_mode = of_get_phy_mode(np); - if (ag->phy_if_mode < 0) { + err = of_get_phy_mode(np, ag->phy_if_mode); + if (err) { netif_err(ag, probe, ndev, "missing phy-mode property in DT\n"); - err = ag->phy_if_mode; goto err_free; } diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c index 37752d9514e7..30b455013bf3 100644 --- a/drivers/net/ethernet/aurora/nb8800.c +++ b/drivers/net/ethernet/aurora/nb8800.c @@ -1371,8 +1371,8 @@ static int nb8800_probe(struct platform_device *pdev) priv = netdev_priv(dev); priv->base = base; - priv->phy_mode = of_get_phy_mode(pdev->dev.of_node); - if (priv->phy_mode < 0) + ret = of_get_phy_mode(pdev->dev.of_node, &priv->phy_mode); + if (ret) priv->phy_mode = PHY_INTERFACE_MODE_RGMII; priv->clk = devm_clk_get(&pdev->dev, NULL); diff --git a/drivers/net/ethernet/aurora/nb8800.h b/drivers/net/ethernet/aurora/nb8800.h index aacc3cce2cc0..40941fb6065b 100644 --- a/drivers/net/ethernet/aurora/nb8800.h +++ b/drivers/net/ethernet/aurora/nb8800.h @@ -287,7 +287,7 @@ struct nb8800_priv { struct device_node *phy_node; /* PHY connection type from DT */ - int phy_mode; + phy_interface_t phy_mode; /* Current link status */ int speed; diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index a977a459bd20..825af709708e 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -2479,9 +2479,9 @@ static int bcm_sysport_probe(struct platform_device *pdev) priv->netdev = dev; priv->pdev = pdev; - priv->phy_interface = of_get_phy_mode(dn); + ret = of_get_phy_mode(dn, &priv->phy_interface); /* Default to GMII interface mode */ - if ((int)priv->phy_interface < 0) + if (ret) priv->phy_interface = PHY_INTERFACE_MODE_GMII; /* In the case of a fixed PHY, the DT node associated diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 17bb8d60a157..b797a7e59a53 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -436,7 +436,7 @@ static int bcmgenet_mii_of_init(struct bcmgenet_priv *priv) struct device_node *dn = priv->pdev->dev.of_node; struct device *kdev = &priv->pdev->dev; struct phy_device *phydev; - int phy_mode; + phy_interface_t phy_mode; int ret; /* Fetch the PHY phandle */ @@ -454,10 +454,10 @@ static int bcmgenet_mii_of_init(struct bcmgenet_priv *priv) } /* Get the link mode */ - phy_mode = of_get_phy_mode(dn); - if (phy_mode < 0) { + ret = of_get_phy_mode(dn, &phy_mode); + if (ret) { dev_err(kdev, "invalid PHY mode property\n"); - return phy_mode; + return ret; } priv->phy_interface = phy_mode; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 1e1b774e1953..b884cf7f339b 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -4182,6 +4182,7 @@ static int macb_probe(struct platform_device *pdev) unsigned int queue_mask, num_queues; bool native_io; struct phy_device *phydev; + phy_interface_t interface; struct net_device *dev; struct resource *regs; void __iomem *mem; @@ -4308,12 +4309,12 @@ static int macb_probe(struct platform_device *pdev) macb_get_hwaddr(bp); } - err = of_get_phy_mode(np); - if (err < 0) + err = of_get_phy_mode(np, &interface); + if (err) /* not found in DT, MII by default */ bp->phy_interface = PHY_INTERFACE_MODE_MII; else - bp->phy_interface = err; + bp->phy_interface = interface; /* IP specific init */ err = init(pdev); diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index da0c506349d1..a6f2063f1475 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1612,7 +1612,7 @@ static int ftgmac100_setup_mdio(struct net_device *netdev) { struct ftgmac100 *priv = netdev_priv(netdev); struct platform_device *pdev = to_platform_device(priv->dev); - int phy_intf = PHY_INTERFACE_MODE_RGMII; + phy_interface_t phy_intf = PHY_INTERFACE_MODE_RGMII; struct device_node *np = pdev->dev.of_node; int i, err = 0; u32 reg; @@ -1637,8 +1637,8 @@ static int ftgmac100_setup_mdio(struct net_device *netdev) /* Get PHY mode from device-tree */ if (np) { /* Default to RGMII. It's a gigabit part after all */ - phy_intf = of_get_phy_mode(np); - if (phy_intf < 0) + err = of_get_phy_mode(np, &phy_intf); + if (err) phy_intf = PHY_INTERFACE_MODE_RGMII; /* Aspeed only supports these. I don't know about other IP diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c index fea388d86f20..b713739f4804 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c @@ -44,10 +44,11 @@ static struct device_node *dpaa2_mac_get_node(u16 dpmac_id) static int dpaa2_mac_get_if_mode(struct device_node *node, struct dpmac_attr attr) { - int if_mode; + phy_interface_t if_mode; + int err; - if_mode = of_get_phy_mode(node); - if (if_mode >= 0) + err = of_get_phy_mode(node, &if_mode); + if (!err) return if_mode; if_mode = phy_mode(attr.eth_if); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index b73421c3e25b..7da79b816416 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -784,8 +784,8 @@ static int enetc_of_get_phy(struct enetc_ndev_priv *priv) } } - priv->if_mode = of_get_phy_mode(np); - if ((int)priv->if_mode < 0) { + err = of_get_phy_mode(np, &priv->if_mode); + if (err) { dev_err(priv->dev, "missing phy type\n"); of_node_put(priv->phy_node); if (of_phy_is_fixed_link(np)) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 7d37ba9f6819..d4d6c2e941f1 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3393,6 +3393,7 @@ fec_probe(struct platform_device *pdev) { struct fec_enet_private *fep; struct fec_platform_data *pdata; + phy_interface_t interface; struct net_device *ndev; int i, irq, ret = 0; const struct of_device_id *of_id; @@ -3465,15 +3466,15 @@ fec_probe(struct platform_device *pdev) } fep->phy_node = phy_node; - ret = of_get_phy_mode(pdev->dev.of_node); - if (ret < 0) { + ret = of_get_phy_mode(pdev->dev.of_node, &interface); + if (ret) { pdata = dev_get_platdata(&pdev->dev); if (pdata) fep->phy_interface = pdata->phy; else fep->phy_interface = PHY_INTERFACE_MODE_MII; } else { - fep->phy_interface = ret; + fep->phy_interface = interface; } fep->clk_ipg = devm_clk_get(&pdev->dev, "ipg"); diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c index 7ab8095db192..f0806ace1ae2 100644 --- a/drivers/net/ethernet/freescale/fman/mac.c +++ b/drivers/net/ethernet/freescale/fman/mac.c @@ -608,7 +608,7 @@ static int mac_probe(struct platform_device *_of_dev) const u8 *mac_addr; u32 val; u8 fman_id; - int phy_if; + phy_interface_t phy_if; dev = &_of_dev->dev; mac_node = dev->of_node; @@ -776,8 +776,8 @@ static int mac_probe(struct platform_device *_of_dev) } /* Get the PHY connection type */ - phy_if = of_get_phy_mode(mac_node); - if (phy_if < 0) { + err = of_get_phy_mode(mac_node, &phy_if); + if (err) { dev_warn(dev, "of_get_phy_mode() for %pOF failed. Defaulting to SGMII\n", mac_node); diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 51ad86417cb1..72868a28b621 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -641,6 +641,7 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev) const char *model; const void *mac_addr; int err = 0, i; + phy_interface_t interface; struct net_device *dev = NULL; struct gfar_private *priv = NULL; struct device_node *np = ofdev->dev.of_node; @@ -805,9 +806,9 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev) * rgmii-id really needs to be specified. Other types can be * detected by hardware */ - err = of_get_phy_mode(np); - if (err >= 0) - priv->interface = err; + err = of_get_phy_mode(np, &interface); + if (!err) + priv->interface = interface; else priv->interface = gfar_get_interface(dev); diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index 4606a7e4a6d1..3e9b6d543c77 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -211,7 +211,7 @@ struct hip04_priv { #if defined(CONFIG_HI13X1_GMAC) void __iomem *sysctrl_base; #endif - int phy_mode; + phy_interface_t phy_mode; int chan; unsigned int port; unsigned int group; @@ -961,10 +961,9 @@ static int hip04_mac_probe(struct platform_device *pdev) goto init_fail; } - priv->phy_mode = of_get_phy_mode(node); - if (priv->phy_mode < 0) { + ret = of_get_phy_mode(node, &priv->phy_mode); + if (ret) { dev_warn(d, "not find phy-mode\n"); - ret = -EINVAL; goto init_fail; } diff --git a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c index c41b19c760f8..247de9105d10 100644 --- a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c +++ b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c @@ -1193,10 +1193,9 @@ static int hix5hd2_dev_probe(struct platform_device *pdev) if (ret) goto err_free_mdio; - priv->phy_mode = of_get_phy_mode(node); - if ((int)priv->phy_mode < 0) { + ret = of_get_phy_mode(node, &priv->phy_mode); + if (ret) { netdev_err(ndev, "not find phy-mode\n"); - ret = -EINVAL; goto err_mdiobus; } diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index 9e43c9ace9c2..2e40425d8a34 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -2849,6 +2849,7 @@ static int emac_init_config(struct emac_instance *dev) { struct device_node *np = dev->ofdev->dev.of_node; const void *p; + int err; /* Read config from device-tree */ if (emac_read_uint_prop(np, "mal-device", &dev->mal_ph, 1)) @@ -2897,8 +2898,8 @@ static int emac_init_config(struct emac_instance *dev) dev->mal_burst_size = 256; /* PHY mode needs some decoding */ - dev->phy_mode = of_get_phy_mode(np); - if (dev->phy_mode < 0) + err = of_get_phy_mode(np, &dev->phy_mode); + if (err) dev->phy_mode = PHY_INTERFACE_MODE_NA; /* Check EMAC version */ diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 82ea55ae5053..d5b644131cff 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -2959,15 +2959,16 @@ static void set_params(struct mv643xx_eth_private *mp, static int get_phy_mode(struct mv643xx_eth_private *mp) { struct device *dev = mp->dev->dev.parent; - int iface = -1; + phy_interface_t iface; + int err; if (dev->of_node) - iface = of_get_phy_mode(dev->of_node); + err = of_get_phy_mode(dev->of_node, &iface); /* Historical default if unspecified. We could also read/write * the interface state in the PSC1 */ - if (iface < 0) + if (!dev->of_node || err) iface = PHY_INTERFACE_MODE_GMII; return iface; } diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 8f9df6efda61..274ac39c0f0f 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -4797,9 +4797,9 @@ static int mvneta_probe(struct platform_device *pdev) struct phy *comphy; const char *dt_mac_addr; char hw_mac_addr[ETH_ALEN]; + phy_interface_t phy_mode; const char *mac_from; int tx_csum_limit; - int phy_mode; int err; int cpu; @@ -4812,10 +4812,9 @@ static int mvneta_probe(struct platform_device *pdev) if (dev->irq == 0) return -EINVAL; - phy_mode = of_get_phy_mode(dn); - if (phy_mode < 0) { + err = of_get_phy_mode(dn, &phy_mode); + if (err) { dev_err(&pdev->dev, "incorrect phy-mode\n"); - err = -EINVAL; goto err_free_irq; } diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c index 51b77c2de400..3fb7ee3d4d13 100644 --- a/drivers/net/ethernet/marvell/pxa168_eth.c +++ b/drivers/net/ethernet/marvell/pxa168_eth.c @@ -1489,8 +1489,10 @@ static int pxa168_eth_probe(struct platform_device *pdev) goto err_netdev; } of_property_read_u32(np, "reg", &pep->phy_addr); - pep->phy_intf = of_get_phy_mode(pdev->dev.of_node); of_node_put(np); + err = of_get_phy_mode(pdev->dev.of_node, &pep->phy_intf); + if (err && err != -ENODEV) + goto err_netdev; } /* Hardware supports only 3 ports */ diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 703adb96429e..385a4ab9ec99 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -2758,9 +2758,10 @@ static const struct net_device_ops mtk_netdev_ops = { static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) { const __be32 *_id = of_get_property(np, "reg", NULL); + phy_interface_t phy_mode; struct phylink *phylink; - int phy_mode, id, err; struct mtk_mac *mac; + int id, err; if (!_id) { dev_err(eth->dev, "missing mac id\n"); @@ -2805,10 +2806,9 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) mac->hw_stats->reg_offset = id * MTK_STAT_OFFSET; /* phylink create */ - phy_mode = of_get_phy_mode(np); - if (phy_mode < 0) { + err = of_get_phy_mode(np, &phy_mode); + if (err) { dev_err(eth->dev, "incorrect phy-mode\n"); - err = -EINVAL; goto free_netdev; } diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c index aac115136720..723724bdc139 100644 --- a/drivers/net/ethernet/mscc/ocelot_board.c +++ b/drivers/net/ethernet/mscc/ocelot_board.c @@ -364,12 +364,12 @@ static int mscc_ocelot_probe(struct platform_device *pdev) for_each_available_child_of_node(ports, portnp) { struct device_node *phy_node; + phy_interface_t phy_mode; struct phy_device *phy; struct resource *res; struct phy *serdes; void __iomem *regs; char res_name[8]; - int phy_mode; u32 port; if (of_property_read_u32(portnp, "reg", &port)) @@ -398,11 +398,11 @@ static int mscc_ocelot_probe(struct platform_device *pdev) goto out_put_ports; } - phy_mode = of_get_phy_mode(portnp); - if (phy_mode < 0) - ocelot->ports[port]->phy_mode = PHY_INTERFACE_MODE_NA; - else - ocelot->ports[port]->phy_mode = phy_mode; + err = of_get_phy_mode(portnp, &phy_mode); + if (err && err != -ENODEV) + goto out_put_ports; + + ocelot->ports[port]->phy_mode = phy_mode; switch (ocelot->ports[port]->phy_mode) { case PHY_INTERFACE_MODE_NA: diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c index 2761f3a3ae50..49c7987c2abd 100644 --- a/drivers/net/ethernet/ni/nixge.c +++ b/drivers/net/ethernet/ni/nixge.c @@ -1346,10 +1346,9 @@ static int nixge_probe(struct platform_device *pdev) } } - priv->phy_mode = of_get_phy_mode(pdev->dev.of_node); - if ((int)priv->phy_mode < 0) { + err = of_get_phy_mode(pdev->dev.of_node, &priv->phy_mode); + if (err) { netdev_err(ndev, "not find \"phy-mode\" property\n"); - err = -EINVAL; goto unregister_mdio; } diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index de9aa8c47f1c..5ea14b5fbed8 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -2046,7 +2046,9 @@ static int ravb_probe(struct platform_device *pdev) spin_lock_init(&priv->lock); INIT_WORK(&priv->work, ravb_tx_timeout_work); - priv->phy_interface = of_get_phy_mode(np); + error = of_get_phy_mode(np, &priv->phy_interface); + if (error && error != -ENODEV) + goto out_release; priv->no_avb_link = of_property_read_bool(np, "renesas,no-ether-link"); priv->avb_link_active_low = diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 7ba35a0bdb29..e19b49c4013e 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -3183,6 +3183,7 @@ static struct sh_eth_plat_data *sh_eth_parse_dt(struct device *dev) { struct device_node *np = dev->of_node; struct sh_eth_plat_data *pdata; + phy_interface_t interface; const char *mac_addr; int ret; @@ -3190,10 +3191,10 @@ static struct sh_eth_plat_data *sh_eth_parse_dt(struct device *dev) if (!pdata) return NULL; - ret = of_get_phy_mode(np); - if (ret < 0) + ret = of_get_phy_mode(np, &interface); + if (ret) return NULL; - pdata->phy_interface = ret; + pdata->phy_interface = interface; mac_addr = of_get_mac_address(np); if (!IS_ERR(mac_addr)) diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c index 2412c87561e0..33f79402850d 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c @@ -30,12 +30,15 @@ static int sxgbe_probe_config_dt(struct platform_device *pdev, { struct device_node *np = pdev->dev.of_node; struct sxgbe_dma_cfg *dma_cfg; + int err; if (!np) return -ENODEV; *mac = of_get_mac_address(np); - plat->interface = of_get_phy_mode(np); + err = of_get_phy_mode(np, &plat->interface); + if (err && err != -ENODEV) + return err; plat->bus_id = of_alias_get_id(np, "ethernet"); if (plat->bus_id < 0) diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c index 6e984d5a729f..f7e927ad67fa 100644 --- a/drivers/net/ethernet/socionext/sni_ave.c +++ b/drivers/net/ethernet/socionext/sni_ave.c @@ -1565,10 +1565,10 @@ static int ave_probe(struct platform_device *pdev) return -EINVAL; np = dev->of_node; - phy_mode = of_get_phy_mode(np); - if ((int)phy_mode < 0) { + ret = of_get_phy_mode(np, &phy_mode); + if (ret) { dev_err(dev, "phy-mode not found\n"); - return -EINVAL; + return ret; } irq = platform_get_irq(pdev, 0); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c index 527f93320a5a..d0d2d0fc5f0a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c @@ -61,9 +61,10 @@ static void anarion_gmac_exit(struct platform_device *pdev, void *priv) static struct anarion_gmac *anarion_config_dt(struct platform_device *pdev) { - int phy_mode; - void __iomem *ctl_block; struct anarion_gmac *gmac; + phy_interface_t phy_mode; + void __iomem *ctl_block; + int err; ctl_block = devm_platform_ioremap_resource(pdev, 1); if (IS_ERR(ctl_block)) { @@ -78,7 +79,10 @@ static struct anarion_gmac *anarion_config_dt(struct platform_device *pdev) gmac->ctl_block = (uintptr_t)ctl_block; - phy_mode = of_get_phy_mode(pdev->dev.of_node); + err = of_get_phy_mode(pdev->dev.of_node, &phy_mode); + if (err) + return ERR_PTR(err); + switch (phy_mode) { case PHY_INTERFACE_MODE_RGMII: /* Fall through */ case PHY_INTERFACE_MODE_RGMII_ID /* Fall through */: diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c index 0d21082ceb93..6ae13dc19510 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c @@ -189,9 +189,10 @@ static int ipq806x_gmac_set_speed(struct ipq806x_gmac *gmac, unsigned int speed) static int ipq806x_gmac_of_parse(struct ipq806x_gmac *gmac) { struct device *dev = &gmac->pdev->dev; + int ret; - gmac->phy_mode = of_get_phy_mode(dev->of_node); - if ((int)gmac->phy_mode < 0) { + ret = of_get_phy_mode(dev->of_node, &gmac->phy_mode); + if (ret) { dev_err(dev, "missing phy mode property\n"); return -EINVAL; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c index cea7a0c7ce68..bdb80421acac 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c @@ -54,7 +54,7 @@ struct mediatek_dwmac_plat_data { struct device_node *np; struct regmap *peri_regmap; struct device *dev; - int phy_mode; + phy_interface_t phy_mode; bool rmii_rxc; }; @@ -243,6 +243,7 @@ static int mediatek_dwmac_config_dt(struct mediatek_dwmac_plat_data *plat) { struct mac_delay_struct *mac_delay = &plat->mac_delay; u32 tx_delay_ps, rx_delay_ps; + int err; plat->peri_regmap = syscon_regmap_lookup_by_phandle(plat->np, "mediatek,pericfg"); if (IS_ERR(plat->peri_regmap)) { @@ -250,10 +251,10 @@ static int mediatek_dwmac_config_dt(struct mediatek_dwmac_plat_data *plat) return PTR_ERR(plat->peri_regmap); } - plat->phy_mode = of_get_phy_mode(plat->np); - if (plat->phy_mode < 0) { + err = of_get_phy_mode(plat->np, &plat->phy_mode); + if (err) { dev_err(plat->dev, "not find phy-mode\n"); - return -EINVAL; + return err; } if (!of_property_read_u32(plat->np, "mediatek,tx-delay-ps", &tx_delay_ps)) { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c index 306da8f6b7d5..bd6c01004913 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c @@ -338,10 +338,9 @@ static int meson8b_dwmac_probe(struct platform_device *pdev) } dwmac->dev = &pdev->dev; - dwmac->phy_mode = of_get_phy_mode(pdev->dev.of_node); - if ((int)dwmac->phy_mode < 0) { + ret = of_get_phy_mode(pdev->dev.of_node, &dwmac->phy_mode); + if (ret) { dev_err(&pdev->dev, "missing phy-mode property\n"); - ret = -EINVAL; goto err_remove_config_dt; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index e2e469c37a4d..dc50ba13a746 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -37,7 +37,7 @@ struct rk_gmac_ops { struct rk_priv_data { struct platform_device *pdev; - int phy_iface; + phy_interface_t phy_iface; struct regulator *regulator; bool suspended; const struct rk_gmac_ops *ops; @@ -1224,7 +1224,7 @@ static struct rk_priv_data *rk_gmac_setup(struct platform_device *pdev, if (!bsp_priv) return ERR_PTR(-ENOMEM); - bsp_priv->phy_iface = of_get_phy_mode(dev->of_node); + of_get_phy_mode(dev->of_node, &bsp_priv->phy_iface); bsp_priv->ops = ops; bsp_priv->regulator = devm_regulator_get_optional(dev, "phy"); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c index e9fd661f7995..e1b63df6f96f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c @@ -116,7 +116,7 @@ #define ETH_PHY_SEL_MII 0x0 struct sti_dwmac { - int interface; /* MII interface */ + phy_interface_t interface; /* MII interface */ bool ext_phyclk; /* Clock from external PHY */ u32 tx_retime_src; /* TXCLK Retiming*/ struct clk *clk; /* PHY clock */ @@ -269,7 +269,12 @@ static int sti_dwmac_parse_data(struct sti_dwmac *dwmac, return err; } - dwmac->interface = of_get_phy_mode(np); + err = of_get_phy_mode(np, &dwmac->interface); + if (err && err != -ENODEV) { + dev_err(dev, "Can't get phy-mode\n"); + return err; + } + dwmac->regmap = regmap; dwmac->gmac_en = of_property_read_bool(np, "st,gmac_en"); dwmac->ext_phyclk = of_property_read_bool(np, "st,ext-phyclk"); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index ddcc191febdb..eefb06d918c8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -1105,6 +1105,7 @@ static int sun8i_dwmac_probe(struct platform_device *pdev) struct stmmac_resources stmmac_res; struct sunxi_priv_data *gmac; struct device *dev = &pdev->dev; + phy_interface_t interface; int ret; struct stmmac_priv *priv; struct net_device *ndev; @@ -1178,10 +1179,10 @@ static int sun8i_dwmac_probe(struct platform_device *pdev) return ret; } - ret = of_get_phy_mode(dev->of_node); - if (ret < 0) + ret = of_get_phy_mode(dev->of_node, &interface); + if (ret) return -EINVAL; - plat_dat->interface = ret; + plat_dat->interface = interface; /* platform data specifying hardware features and callbacks. * hardware features were copied from Allwinner drivers. diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c index a299da3971b4..26353ef616b8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c @@ -18,7 +18,7 @@ #include "stmmac_platform.h" struct sunxi_priv_data { - int interface; + phy_interface_t interface; int clk_enabled; struct clk *tx_clk; struct regulator *regulator; @@ -118,7 +118,11 @@ static int sun7i_gmac_probe(struct platform_device *pdev) goto err_remove_config_dt; } - gmac->interface = of_get_phy_mode(dev->of_node); + ret = of_get_phy_mode(dev->of_node, &gmac->interface); + if (ret && ret != -ENODEV) { + dev_err(dev, "Can't get phy-mode\n"); + goto err_remove_config_dt; + } gmac->tx_clk = devm_clk_get(dev, "allwinner_gmac_tx"); if (IS_ERR(gmac->tx_clk)) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 170c3a052b14..bedaff0c13bd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -412,9 +412,9 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) *mac = NULL; } - plat->phy_interface = of_get_phy_mode(np); - if (plat->phy_interface < 0) - return ERR_PTR(plat->phy_interface); + rc = of_get_phy_mode(np, &plat->phy_interface); + if (rc) + return ERR_PTR(rc); plat->interface = stmmac_of_get_mac_mode(np); if (plat->interface < 0) diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index f298d714efd6..329671e66fe4 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -2619,11 +2619,10 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, i); goto no_phy_slave; } - slave_data->phy_if = of_get_phy_mode(slave_node); - if (slave_data->phy_if < 0) { + ret = of_get_phy_mode(slave_node, &slave_data->phy_if); + if (ret) { dev_err(&pdev->dev, "Missing or malformed slave[%d] phy-mode property\n", i); - ret = slave_data->phy_if; goto err_node_put; } diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h index 362c5a986869..8bfa761fa552 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.h +++ b/drivers/net/ethernet/ti/cpsw_priv.h @@ -275,7 +275,7 @@ struct cpsw_slave_data { struct device_node *slave_node; struct device_node *phy_node; char phy_id[MII_BUS_ID_SIZE]; - int phy_if; + phy_interface_t phy_if; u8 mac_addr[ETH_ALEN]; u16 dual_emac_res_vlan; /* Reserved VLAN for DualEMAC */ struct phy *ifphy; diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index 2c1fac33136c..86a3f42a3dcc 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -2291,6 +2291,7 @@ static int gbe_slave_open(struct gbe_intf *gbe_intf) struct gbe_slave *slave = gbe_intf->slave; phy_interface_t phy_mode; bool has_phy = false; + int err; void (*hndlr)(struct net_device *) = gbe_adjust_link; @@ -2320,11 +2321,11 @@ static int gbe_slave_open(struct gbe_intf *gbe_intf) slave->phy_port_t = PORT_MII; } else if (slave->link_interface == RGMII_LINK_MAC_PHY) { has_phy = true; - phy_mode = of_get_phy_mode(slave->node); + err = of_get_phy_mode(slave->node, &phy_mode); /* if phy-mode is not present, default to * PHY_INTERFACE_MODE_RGMII */ - if (phy_mode < 0) + if (err) phy_mode = PHY_INTERFACE_MODE_RGMII; if (!phy_interface_mode_is_rgmii(phy_mode)) { diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 676006f32f91..867726d696e2 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1761,11 +1761,9 @@ static int axienet_probe(struct platform_device *pdev) goto free_netdev; } } else { - lp->phy_mode = of_get_phy_mode(pdev->dev.of_node); - if ((int)lp->phy_mode < 0) { - ret = -EINVAL; + ret = of_get_phy_mode(pdev->dev.of_node, &lp->phy_mode); + if (ret) goto free_netdev; - } } /* Find the DMA node, map the DMA registers, and decode the DMA IRQs */ diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index bd6129db6417..c6b87ce2b0cc 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -361,8 +361,8 @@ struct phy_device *of_phy_get_and_connect(struct net_device *dev, struct phy_device *phy; int ret; - iface = of_get_phy_mode(np); - if ((int)iface < 0) + ret = of_get_phy_mode(np, &iface); + if (ret) return NULL; if (of_phy_is_fixed_link(np)) { ret = of_phy_register_fixed_link(np); diff --git a/drivers/of/of_net.c b/drivers/of/of_net.c index b02734aff8c1..6e411821583e 100644 --- a/drivers/of/of_net.c +++ b/drivers/of/of_net.c @@ -15,16 +15,20 @@ /** * of_get_phy_mode - Get phy mode for given device_node * @np: Pointer to the given device_node + * @interface: Pointer to the result * * The function gets phy interface string from property 'phy-mode' or - * 'phy-connection-type', and return its index in phy_modes table, or errno in - * error case. + * 'phy-connection-type'. The index in phy_modes table is set in + * interface and 0 returned. In case of error interface is set to + * PHY_INTERFACE_MODE_NA and an errno is returned, e.g. -ENODEV. */ -int of_get_phy_mode(struct device_node *np) +int of_get_phy_mode(struct device_node *np, phy_interface_t *interface) { const char *pm; int err, i; + *interface = PHY_INTERFACE_MODE_NA; + err = of_property_read_string(np, "phy-mode", &pm); if (err < 0) err = of_property_read_string(np, "phy-connection-type", &pm); @@ -32,8 +36,10 @@ int of_get_phy_mode(struct device_node *np) return err; for (i = 0; i < PHY_INTERFACE_MODE_MAX; i++) - if (!strcasecmp(pm, phy_modes(i))) - return i; + if (!strcasecmp(pm, phy_modes(i))) { + *interface = i; + return 0; + } return -ENODEV; } diff --git a/include/linux/of_net.h b/include/linux/of_net.h index 6aeaea1775e6..71bbfcf3adcd 100644 --- a/include/linux/of_net.h +++ b/include/linux/of_net.h @@ -6,15 +6,18 @@ #ifndef __LINUX_OF_NET_H #define __LINUX_OF_NET_H +#include + #ifdef CONFIG_OF_NET #include struct net_device; -extern int of_get_phy_mode(struct device_node *np); +extern int of_get_phy_mode(struct device_node *np, phy_interface_t *interface); extern const void *of_get_mac_address(struct device_node *np); extern struct net_device *of_find_net_device_by_node(struct device_node *np); #else -static inline int of_get_phy_mode(struct device_node *np) +static inline int of_get_phy_mode(struct device_node *np, + phy_interface_t *interface) { return -ENODEV; } diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 86f9464c3f5d..d4bcd9387136 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -13,6 +13,7 @@ #define __STMMAC_PLATFORM_DATA #include +#include #define MTL_MAX_RX_QUEUES 8 #define MTL_MAX_TX_QUEUES 8 @@ -132,7 +133,7 @@ struct plat_stmmacenet_data { int bus_id; int phy_addr; int interface; - int phy_interface; + phy_interface_t phy_interface; struct stmmac_mdio_bus_data *mdio_bus_data; struct device_node *phy_node; struct device_node *phylink_node; diff --git a/include/linux/sxgbe_platform.h b/include/linux/sxgbe_platform.h index 267369110584..85ec745767bd 100644 --- a/include/linux/sxgbe_platform.h +++ b/include/linux/sxgbe_platform.h @@ -10,6 +10,8 @@ #ifndef __SXGBE_PLATFORM_H__ #define __SXGBE_PLATFORM_H__ +#include + /* MDC Clock Selection define*/ #define SXGBE_CSR_100_150M 0x0 /* MDC = clk_scr_i/62 */ #define SXGBE_CSR_150_250M 0x1 /* MDC = clk_scr_i/102 */ @@ -38,7 +40,7 @@ struct sxgbe_plat_data { char *phy_bus_name; int bus_id; int phy_addr; - int interface; + phy_interface_t interface; struct sxgbe_mdio_bus_data *mdio_bus_data; struct sxgbe_dma_cfg *dma_cfg; int clk_csr; diff --git a/net/dsa/port.c b/net/dsa/port.c index 9b54e5a76297..6e93c36bf0c0 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -561,7 +561,7 @@ static int dsa_port_fixed_link_register_of(struct dsa_port *dp) struct dsa_switch *ds = dp->ds; struct phy_device *phydev; int port = dp->index; - int mode; + phy_interface_t mode; int err; err = of_phy_register_fixed_link(dn); @@ -574,8 +574,8 @@ static int dsa_port_fixed_link_register_of(struct dsa_port *dp) phydev = of_phy_find_device(dn); - mode = of_get_phy_mode(dn); - if (mode < 0) + err = of_get_phy_mode(dn, &mode); + if (err) mode = PHY_INTERFACE_MODE_NA; phydev->interface = mode; @@ -593,10 +593,11 @@ static int dsa_port_phylink_register(struct dsa_port *dp) { struct dsa_switch *ds = dp->ds; struct device_node *port_dn = dp->dn; - int mode, err; + phy_interface_t mode; + int err; - mode = of_get_phy_mode(port_dn); - if (mode < 0) + err = of_get_phy_mode(port_dn, &mode); + if (err) mode = PHY_INTERFACE_MODE_NA; dp->pl_config.dev = ds->dev; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index d18761649754..78ffc87dc25e 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1313,11 +1313,12 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) struct dsa_port *dp = dsa_slave_to_port(slave_dev); struct device_node *port_dn = dp->dn; struct dsa_switch *ds = dp->ds; + phy_interface_t mode; u32 phy_flags = 0; - int mode, ret; + int ret; - mode = of_get_phy_mode(port_dn); - if (mode < 0) + ret = of_get_phy_mode(port_dn, &mode); + if (ret) mode = PHY_INTERFACE_MODE_NA; dp->pl_config.dev = &slave_dev->dev; -- cgit v1.2.3-71-gd317 From 205577ab6f7ade6185f764ed78fb6875dca40205 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Fri, 25 Oct 2019 19:08:36 +0100 Subject: iommu/io-pgtable-arm: Rationalise MAIR handling Between VMSAv8-64 and the various 32-bit formats, there is either one 64-bit MAIR or a pair of 32-bit MAIR0/MAIR1 or NMRR/PMRR registers. As such, keeping two 64-bit values in io_pgtable_cfg has always been overkill. Signed-off-by: Robin Murphy Signed-off-by: Will Deacon --- drivers/iommu/arm-smmu-v3.c | 2 +- drivers/iommu/arm-smmu.c | 4 ++-- drivers/iommu/io-pgtable-arm.c | 3 +-- drivers/iommu/ipmmu-vmsa.c | 2 +- drivers/iommu/qcom_iommu.c | 4 ++-- include/linux/io-pgtable.h | 2 +- 6 files changed, 8 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 8da93e730d6f..3f20e548f1ec 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -2172,7 +2172,7 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain, cfg->cd.asid = (u16)asid; cfg->cd.ttbr = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0]; cfg->cd.tcr = pgtbl_cfg->arm_lpae_s1_cfg.tcr; - cfg->cd.mair = pgtbl_cfg->arm_lpae_s1_cfg.mair[0]; + cfg->cd.mair = pgtbl_cfg->arm_lpae_s1_cfg.mair; return 0; out_free_asid: diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index a180665ea002..424ebf38cd09 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -552,8 +552,8 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain, cb->mair[0] = pgtbl_cfg->arm_v7s_cfg.prrr; cb->mair[1] = pgtbl_cfg->arm_v7s_cfg.nmrr; } else { - cb->mair[0] = pgtbl_cfg->arm_lpae_s1_cfg.mair[0]; - cb->mair[1] = pgtbl_cfg->arm_lpae_s1_cfg.mair[1]; + cb->mair[0] = pgtbl_cfg->arm_lpae_s1_cfg.mair; + cb->mair[1] = pgtbl_cfg->arm_lpae_s1_cfg.mair >> 32; } } } diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index fcb302704053..cd96442af44b 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -861,8 +861,7 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie) (ARM_LPAE_MAIR_ATTR_INC_OWBRWA << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_INC_OCACHE)); - cfg->arm_lpae_s1_cfg.mair[0] = reg; - cfg->arm_lpae_s1_cfg.mair[1] = 0; + cfg->arm_lpae_s1_cfg.mair = reg; /* Looking good; allocate a pgd */ data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data), diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index 9da8309f7170..e4da6efbda49 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -438,7 +438,7 @@ static void ipmmu_domain_setup_context(struct ipmmu_vmsa_domain *domain) /* MAIR0 */ ipmmu_ctx_write_root(domain, IMMAIR0, - domain->cfg.arm_lpae_s1_cfg.mair[0]); + domain->cfg.arm_lpae_s1_cfg.mair); /* IMBUSCR */ if (domain->mmu->features->setup_imbuscr) diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c index c31e7bc4ccbe..66e9b40e9275 100644 --- a/drivers/iommu/qcom_iommu.c +++ b/drivers/iommu/qcom_iommu.c @@ -284,9 +284,9 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain, /* MAIRs (stage-1 only) */ iommu_writel(ctx, ARM_SMMU_CB_S1_MAIR0, - pgtbl_cfg.arm_lpae_s1_cfg.mair[0]); + pgtbl_cfg.arm_lpae_s1_cfg.mair); iommu_writel(ctx, ARM_SMMU_CB_S1_MAIR1, - pgtbl_cfg.arm_lpae_s1_cfg.mair[1]); + pgtbl_cfg.arm_lpae_s1_cfg.mair >> 32); /* SCTLR */ reg = SCTLR_CFIE | SCTLR_CFRE | SCTLR_AFE | SCTLR_TRE | diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index ec7a13405f10..ee21eedafe98 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -102,7 +102,7 @@ struct io_pgtable_cfg { struct { u64 ttbr[2]; u64 tcr; - u64 mair[2]; + u64 mair; } arm_lpae_s1_cfg; struct { -- cgit v1.2.3-71-gd317 From f188b5e76aae9f713c73708d2ba57b65953ce207 Mon Sep 17 00:00:00 2001 From: Andrew Murray Date: Mon, 4 Nov 2019 11:12:38 -0700 Subject: coresight: etm4x: Save/restore state across CPU low power states Some hardware will ignore bit TRCPDCR.PU which is used to signal to hardware that power should not be removed from the trace unit. Let's mitigate against this by conditionally saving and restoring the trace unit state when the CPU enters low power states. This patchset introduces a firmware property named 'arm,coresight-loses-context-with-cpu' - when this is present the hardware state will be conditionally saved and restored. A module parameter 'pm_save_enable' is also introduced which can be configured to override the firmware property. This can be set to never allow save/restore or to conditionally allow it (only for self-hosted). The default value is determined by firmware. We avoid saving the hardware state when self-hosted coresight isn't in use to reduce PM latency - we can't determine this by reading the claim tags (TRCCLAIMCLR) as these are 'trace' registers which need power and clocking, something we can't easily provide in the PM context. Therefore we rely on the existing drvdata->mode internal state that is set when self-hosted coresight is used (and powered). Signed-off-by: Andrew Murray Reviewed-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20191104181251.26732-2-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-etm4x.c | 318 ++++++++++++++++++++++++++ drivers/hwtracing/coresight/coresight-etm4x.h | 64 ++++++ drivers/hwtracing/coresight/coresight.c | 6 + include/linux/coresight.h | 6 + 4 files changed, 394 insertions(+) (limited to 'include/linux') diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c index a128b5063f46..4cecabdd051b 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x.c +++ b/drivers/hwtracing/coresight/coresight-etm4x.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -26,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -37,6 +39,15 @@ static int boot_enable; module_param(boot_enable, int, 0444); MODULE_PARM_DESC(boot_enable, "Enable tracing on boot"); +#define PARAM_PM_SAVE_FIRMWARE 0 /* save self-hosted state as per firmware */ +#define PARAM_PM_SAVE_NEVER 1 /* never save any state */ +#define PARAM_PM_SAVE_SELF_HOSTED 2 /* save self-hosted state only */ + +static int pm_save_enable = PARAM_PM_SAVE_FIRMWARE; +module_param(pm_save_enable, int, 0444); +MODULE_PARM_DESC(pm_save_enable, + "Save/restore state on power down: 1 = never, 2 = self-hosted"); + /* The number of ETMv4 currently registered */ static int etm4_count; static struct etmv4_drvdata *etmdrvdata[NR_CPUS]; @@ -54,6 +65,14 @@ static void etm4_os_unlock(struct etmv4_drvdata *drvdata) isb(); } +static void etm4_os_lock(struct etmv4_drvdata *drvdata) +{ + /* Writing 0x1 to TRCOSLAR locks the trace registers */ + writel_relaxed(0x1, drvdata->base + TRCOSLAR); + drvdata->os_unlock = false; + isb(); +} + static bool etm4_arch_supported(u8 arch) { /* Mask out the minor version number */ @@ -1085,6 +1104,288 @@ static void etm4_init_trace_id(struct etmv4_drvdata *drvdata) drvdata->trcid = coresight_get_trace_id(drvdata->cpu); } +#ifdef CONFIG_CPU_PM +static int etm4_cpu_save(struct etmv4_drvdata *drvdata) +{ + int i, ret = 0; + struct etmv4_save_state *state; + struct device *etm_dev = &drvdata->csdev->dev; + + /* + * As recommended by 3.4.1 ("The procedure when powering down the PE") + * of ARM IHI 0064D + */ + dsb(sy); + isb(); + + CS_UNLOCK(drvdata->base); + + /* Lock the OS lock to disable trace and external debugger access */ + etm4_os_lock(drvdata); + + /* wait for TRCSTATR.PMSTABLE to go up */ + if (coresight_timeout(drvdata->base, TRCSTATR, + TRCSTATR_PMSTABLE_BIT, 1)) { + dev_err(etm_dev, + "timeout while waiting for PM Stable Status\n"); + etm4_os_unlock(drvdata); + ret = -EBUSY; + goto out; + } + + state = drvdata->save_state; + + state->trcprgctlr = readl(drvdata->base + TRCPRGCTLR); + state->trcprocselr = readl(drvdata->base + TRCPROCSELR); + state->trcconfigr = readl(drvdata->base + TRCCONFIGR); + state->trcauxctlr = readl(drvdata->base + TRCAUXCTLR); + state->trceventctl0r = readl(drvdata->base + TRCEVENTCTL0R); + state->trceventctl1r = readl(drvdata->base + TRCEVENTCTL1R); + state->trcstallctlr = readl(drvdata->base + TRCSTALLCTLR); + state->trctsctlr = readl(drvdata->base + TRCTSCTLR); + state->trcsyncpr = readl(drvdata->base + TRCSYNCPR); + state->trcccctlr = readl(drvdata->base + TRCCCCTLR); + state->trcbbctlr = readl(drvdata->base + TRCBBCTLR); + state->trctraceidr = readl(drvdata->base + TRCTRACEIDR); + state->trcqctlr = readl(drvdata->base + TRCQCTLR); + + state->trcvictlr = readl(drvdata->base + TRCVICTLR); + state->trcviiectlr = readl(drvdata->base + TRCVIIECTLR); + state->trcvissctlr = readl(drvdata->base + TRCVISSCTLR); + state->trcvipcssctlr = readl(drvdata->base + TRCVIPCSSCTLR); + state->trcvdctlr = readl(drvdata->base + TRCVDCTLR); + state->trcvdsacctlr = readl(drvdata->base + TRCVDSACCTLR); + state->trcvdarcctlr = readl(drvdata->base + TRCVDARCCTLR); + + for (i = 0; i < drvdata->nrseqstate; i++) + state->trcseqevr[i] = readl(drvdata->base + TRCSEQEVRn(i)); + + state->trcseqrstevr = readl(drvdata->base + TRCSEQRSTEVR); + state->trcseqstr = readl(drvdata->base + TRCSEQSTR); + state->trcextinselr = readl(drvdata->base + TRCEXTINSELR); + + for (i = 0; i < drvdata->nr_cntr; i++) { + state->trccntrldvr[i] = readl(drvdata->base + TRCCNTRLDVRn(i)); + state->trccntctlr[i] = readl(drvdata->base + TRCCNTCTLRn(i)); + state->trccntvr[i] = readl(drvdata->base + TRCCNTVRn(i)); + } + + for (i = 0; i < drvdata->nr_resource * 2; i++) + state->trcrsctlr[i] = readl(drvdata->base + TRCRSCTLRn(i)); + + for (i = 0; i < drvdata->nr_ss_cmp; i++) { + state->trcssccr[i] = readl(drvdata->base + TRCSSCCRn(i)); + state->trcsscsr[i] = readl(drvdata->base + TRCSSCSRn(i)); + state->trcsspcicr[i] = readl(drvdata->base + TRCSSPCICRn(i)); + } + + for (i = 0; i < drvdata->nr_addr_cmp * 2; i++) { + state->trcacvr[i] = readl(drvdata->base + TRCACVRn(i)); + state->trcacatr[i] = readl(drvdata->base + TRCACATRn(i)); + } + + /* + * Data trace stream is architecturally prohibited for A profile cores + * so we don't save (or later restore) trcdvcvr and trcdvcmr - As per + * section 1.3.4 ("Possible functional configurations of an ETMv4 trace + * unit") of ARM IHI 0064D. + */ + + for (i = 0; i < drvdata->numcidc; i++) + state->trccidcvr[i] = readl(drvdata->base + TRCCIDCVRn(i)); + + for (i = 0; i < drvdata->numvmidc; i++) + state->trcvmidcvr[i] = readl(drvdata->base + TRCVMIDCVRn(i)); + + state->trccidcctlr0 = readl(drvdata->base + TRCCIDCCTLR0); + state->trccidcctlr1 = readl(drvdata->base + TRCCIDCCTLR1); + + state->trcvmidcctlr0 = readl(drvdata->base + TRCVMIDCCTLR0); + state->trcvmidcctlr0 = readl(drvdata->base + TRCVMIDCCTLR1); + + state->trcclaimset = readl(drvdata->base + TRCCLAIMCLR); + + state->trcpdcr = readl(drvdata->base + TRCPDCR); + + /* wait for TRCSTATR.IDLE to go up */ + if (coresight_timeout(drvdata->base, TRCSTATR, TRCSTATR_IDLE_BIT, 1)) { + dev_err(etm_dev, + "timeout while waiting for Idle Trace Status\n"); + etm4_os_unlock(drvdata); + ret = -EBUSY; + goto out; + } + + drvdata->state_needs_restore = true; + + /* + * Power can be removed from the trace unit now. We do this to + * potentially save power on systems that respect the TRCPDCR_PU + * despite requesting software to save/restore state. + */ + writel_relaxed((state->trcpdcr & ~TRCPDCR_PU), + drvdata->base + TRCPDCR); + +out: + CS_LOCK(drvdata->base); + return ret; +} + +static void etm4_cpu_restore(struct etmv4_drvdata *drvdata) +{ + int i; + struct etmv4_save_state *state = drvdata->save_state; + + CS_UNLOCK(drvdata->base); + + writel_relaxed(state->trcclaimset, drvdata->base + TRCCLAIMSET); + + writel_relaxed(state->trcprgctlr, drvdata->base + TRCPRGCTLR); + writel_relaxed(state->trcprocselr, drvdata->base + TRCPROCSELR); + writel_relaxed(state->trcconfigr, drvdata->base + TRCCONFIGR); + writel_relaxed(state->trcauxctlr, drvdata->base + TRCAUXCTLR); + writel_relaxed(state->trceventctl0r, drvdata->base + TRCEVENTCTL0R); + writel_relaxed(state->trceventctl1r, drvdata->base + TRCEVENTCTL1R); + writel_relaxed(state->trcstallctlr, drvdata->base + TRCSTALLCTLR); + writel_relaxed(state->trctsctlr, drvdata->base + TRCTSCTLR); + writel_relaxed(state->trcsyncpr, drvdata->base + TRCSYNCPR); + writel_relaxed(state->trcccctlr, drvdata->base + TRCCCCTLR); + writel_relaxed(state->trcbbctlr, drvdata->base + TRCBBCTLR); + writel_relaxed(state->trctraceidr, drvdata->base + TRCTRACEIDR); + writel_relaxed(state->trcqctlr, drvdata->base + TRCQCTLR); + + writel_relaxed(state->trcvictlr, drvdata->base + TRCVICTLR); + writel_relaxed(state->trcviiectlr, drvdata->base + TRCVIIECTLR); + writel_relaxed(state->trcvissctlr, drvdata->base + TRCVISSCTLR); + writel_relaxed(state->trcvipcssctlr, drvdata->base + TRCVIPCSSCTLR); + writel_relaxed(state->trcvdctlr, drvdata->base + TRCVDCTLR); + writel_relaxed(state->trcvdsacctlr, drvdata->base + TRCVDSACCTLR); + writel_relaxed(state->trcvdarcctlr, drvdata->base + TRCVDARCCTLR); + + for (i = 0; i < drvdata->nrseqstate; i++) + writel_relaxed(state->trcseqevr[i], + drvdata->base + TRCSEQEVRn(i)); + + writel_relaxed(state->trcseqrstevr, drvdata->base + TRCSEQRSTEVR); + writel_relaxed(state->trcseqstr, drvdata->base + TRCSEQSTR); + writel_relaxed(state->trcextinselr, drvdata->base + TRCEXTINSELR); + + for (i = 0; i < drvdata->nr_cntr; i++) { + writel_relaxed(state->trccntrldvr[i], + drvdata->base + TRCCNTRLDVRn(i)); + writel_relaxed(state->trccntctlr[i], + drvdata->base + TRCCNTCTLRn(i)); + writel_relaxed(state->trccntvr[i], + drvdata->base + TRCCNTVRn(i)); + } + + for (i = 0; i < drvdata->nr_resource * 2; i++) + writel_relaxed(state->trcrsctlr[i], + drvdata->base + TRCRSCTLRn(i)); + + for (i = 0; i < drvdata->nr_ss_cmp; i++) { + writel_relaxed(state->trcssccr[i], + drvdata->base + TRCSSCCRn(i)); + writel_relaxed(state->trcsscsr[i], + drvdata->base + TRCSSCSRn(i)); + writel_relaxed(state->trcsspcicr[i], + drvdata->base + TRCSSPCICRn(i)); + } + + for (i = 0; i < drvdata->nr_addr_cmp * 2; i++) { + writel_relaxed(state->trcacvr[i], + drvdata->base + TRCACVRn(i)); + writel_relaxed(state->trcacatr[i], + drvdata->base + TRCACATRn(i)); + } + + for (i = 0; i < drvdata->numcidc; i++) + writel_relaxed(state->trccidcvr[i], + drvdata->base + TRCCIDCVRn(i)); + + for (i = 0; i < drvdata->numvmidc; i++) + writel_relaxed(state->trcvmidcvr[i], + drvdata->base + TRCVMIDCVRn(i)); + + writel_relaxed(state->trccidcctlr0, drvdata->base + TRCCIDCCTLR0); + writel_relaxed(state->trccidcctlr1, drvdata->base + TRCCIDCCTLR1); + + writel_relaxed(state->trcvmidcctlr0, drvdata->base + TRCVMIDCCTLR0); + writel_relaxed(state->trcvmidcctlr0, drvdata->base + TRCVMIDCCTLR1); + + writel_relaxed(state->trcclaimset, drvdata->base + TRCCLAIMSET); + + writel_relaxed(state->trcpdcr, drvdata->base + TRCPDCR); + + drvdata->state_needs_restore = false; + + /* + * As recommended by section 4.3.7 ("Synchronization when using the + * memory-mapped interface") of ARM IHI 0064D + */ + dsb(sy); + isb(); + + /* Unlock the OS lock to re-enable trace and external debug access */ + etm4_os_unlock(drvdata); + CS_LOCK(drvdata->base); +} + +static int etm4_cpu_pm_notify(struct notifier_block *nb, unsigned long cmd, + void *v) +{ + struct etmv4_drvdata *drvdata; + unsigned int cpu = smp_processor_id(); + + if (!etmdrvdata[cpu]) + return NOTIFY_OK; + + drvdata = etmdrvdata[cpu]; + + if (!drvdata->save_state) + return NOTIFY_OK; + + if (WARN_ON_ONCE(drvdata->cpu != cpu)) + return NOTIFY_BAD; + + switch (cmd) { + case CPU_PM_ENTER: + /* save the state if self-hosted coresight is in use */ + if (local_read(&drvdata->mode)) + if (etm4_cpu_save(drvdata)) + return NOTIFY_BAD; + break; + case CPU_PM_EXIT: + /* fallthrough */ + case CPU_PM_ENTER_FAILED: + if (drvdata->state_needs_restore) + etm4_cpu_restore(drvdata); + break; + default: + return NOTIFY_DONE; + } + + return NOTIFY_OK; +} + +static struct notifier_block etm4_cpu_pm_nb = { + .notifier_call = etm4_cpu_pm_notify, +}; + +static int etm4_cpu_pm_register(void) +{ + return cpu_pm_register_notifier(&etm4_cpu_pm_nb); +} + +static void etm4_cpu_pm_unregister(void) +{ + cpu_pm_unregister_notifier(&etm4_cpu_pm_nb); +} +#else +static int etm4_cpu_pm_register(void) { return 0; } +static void etm4_cpu_pm_unregister(void) { } +#endif + static int etm4_probe(struct amba_device *adev, const struct amba_id *id) { int ret; @@ -1101,6 +1402,17 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id) dev_set_drvdata(dev, drvdata); + if (pm_save_enable == PARAM_PM_SAVE_FIRMWARE) + pm_save_enable = coresight_loses_context_with_cpu(dev) ? + PARAM_PM_SAVE_SELF_HOSTED : PARAM_PM_SAVE_NEVER; + + if (pm_save_enable != PARAM_PM_SAVE_NEVER) { + drvdata->save_state = devm_kmalloc(dev, + sizeof(struct etmv4_save_state), GFP_KERNEL); + if (!drvdata->save_state) + return -ENOMEM; + } + /* Validity for the resource is already checked by the AMBA core */ base = devm_ioremap_resource(dev, res); if (IS_ERR(base)) @@ -1135,6 +1447,10 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id) if (ret < 0) goto err_arch_supported; hp_online = ret; + + ret = etm4_cpu_pm_register(); + if (ret) + goto err_arch_supported; } cpus_read_unlock(); @@ -1185,6 +1501,8 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id) err_arch_supported: if (--etm4_count == 0) { + etm4_cpu_pm_unregister(); + cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING); if (hp_online) cpuhp_remove_state_nocalls(hp_online); diff --git a/drivers/hwtracing/coresight/coresight-etm4x.h b/drivers/hwtracing/coresight/coresight-etm4x.h index 4523f10ddd0f..546d790cb01b 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x.h +++ b/drivers/hwtracing/coresight/coresight-etm4x.h @@ -175,6 +175,7 @@ ETM_MODE_EXCL_USER) #define TRCSTATR_IDLE_BIT 0 +#define TRCSTATR_PMSTABLE_BIT 1 #define ETM_DEFAULT_ADDR_COMP 0 /* PowerDown Control Register bits */ @@ -281,6 +282,65 @@ struct etmv4_config { u32 ext_inp; }; +/** + * struct etm4_save_state - state to be preserved when ETM is without power + */ +struct etmv4_save_state { + u32 trcprgctlr; + u32 trcprocselr; + u32 trcconfigr; + u32 trcauxctlr; + u32 trceventctl0r; + u32 trceventctl1r; + u32 trcstallctlr; + u32 trctsctlr; + u32 trcsyncpr; + u32 trcccctlr; + u32 trcbbctlr; + u32 trctraceidr; + u32 trcqctlr; + + u32 trcvictlr; + u32 trcviiectlr; + u32 trcvissctlr; + u32 trcvipcssctlr; + u32 trcvdctlr; + u32 trcvdsacctlr; + u32 trcvdarcctlr; + + u32 trcseqevr[ETM_MAX_SEQ_STATES]; + u32 trcseqrstevr; + u32 trcseqstr; + u32 trcextinselr; + u32 trccntrldvr[ETMv4_MAX_CNTR]; + u32 trccntctlr[ETMv4_MAX_CNTR]; + u32 trccntvr[ETMv4_MAX_CNTR]; + + u32 trcrsctlr[ETM_MAX_RES_SEL * 2]; + + u32 trcssccr[ETM_MAX_SS_CMP]; + u32 trcsscsr[ETM_MAX_SS_CMP]; + u32 trcsspcicr[ETM_MAX_SS_CMP]; + + u64 trcacvr[ETM_MAX_SINGLE_ADDR_CMP]; + u64 trcacatr[ETM_MAX_SINGLE_ADDR_CMP]; + u64 trccidcvr[ETMv4_MAX_CTXID_CMP]; + u32 trcvmidcvr[ETM_MAX_VMID_CMP]; + u32 trccidcctlr0; + u32 trccidcctlr1; + u32 trcvmidcctlr0; + u32 trcvmidcctlr1; + + u32 trcclaimset; + + u32 cntr_val[ETMv4_MAX_CNTR]; + u32 seq_state; + u32 vinst_ctrl; + u32 ss_status[ETM_MAX_SS_CMP]; + + u32 trcpdcr; +}; + /** * struct etm4_drvdata - specifics associated to an ETM component * @base: Memory mapped base address for this component. @@ -336,6 +396,8 @@ struct etmv4_config { * @atbtrig: If the implementation can support ATB triggers * @lpoverride: If the implementation can support low-power state over. * @config: structure holding configuration parameters. + * @save_state: State to be preserved across power loss + * @state_needs_restore: True when there is context to restore after PM exit */ struct etmv4_drvdata { void __iomem *base; @@ -381,6 +443,8 @@ struct etmv4_drvdata { bool atbtrig; bool lpoverride; struct etmv4_config config; + struct etmv4_save_state *save_state; + bool state_needs_restore; }; /* Address comparator access types */ diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c index 6453c67a4d01..e6ca899fea4e 100644 --- a/drivers/hwtracing/coresight/coresight.c +++ b/drivers/hwtracing/coresight/coresight.c @@ -1308,6 +1308,12 @@ static inline int coresight_search_device_idx(struct coresight_dev_list *dict, return -ENOENT; } +bool coresight_loses_context_with_cpu(struct device *dev) +{ + return fwnode_property_present(dev_fwnode(dev), + "arm,coresight-loses-context-with-cpu"); +} + /* * coresight_alloc_device_name - Get an index for a given device in the * device index list specific to a driver. An index is allocated for a diff --git a/include/linux/coresight.h b/include/linux/coresight.h index a2b68823717b..44e552de419c 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -285,6 +285,8 @@ extern void coresight_disclaim_device(void __iomem *base); extern void coresight_disclaim_device_unlocked(void __iomem *base); extern char *coresight_alloc_device_name(struct coresight_dev_list *devs, struct device *dev); + +extern bool coresight_loses_context_with_cpu(struct device *dev); #else static inline struct coresight_device * coresight_register(struct coresight_desc *desc) { return NULL; } @@ -307,6 +309,10 @@ static inline int coresight_claim_device(void __iomem *base) static inline void coresight_disclaim_device(void __iomem *base) {} static inline void coresight_disclaim_device_unlocked(void __iomem *base) {} +static inline bool coresight_loses_context_with_cpu(struct device *dev) +{ + return false; +} #endif extern int coresight_get_cpu(struct device *dev); -- cgit v1.2.3-71-gd317 From b8104fda1fff0882e43b7e98832a76d7e98eb3e9 Mon Sep 17 00:00:00 2001 From: John Garry Date: Tue, 5 Nov 2019 01:22:16 +0800 Subject: logic_pio: Define PIO_INDIRECT_SIZE for !CONFIG_INDIRECT_PIO With the goal of expanding the test coverage of the HiSi LPC driver to !ARM64, define a dummy PIO_INDIRECT_SIZE for !CONFIG_INDIRECT_PIO, which is required by the named driver. Signed-off-by: John Garry Signed-off-by: Wei Xu --- include/linux/logic_pio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/logic_pio.h b/include/linux/logic_pio.h index 88e1e6304a71..54945aa824b4 100644 --- a/include/linux/logic_pio.h +++ b/include/linux/logic_pio.h @@ -108,10 +108,10 @@ void logic_outsl(unsigned long addr, const void *buffer, unsigned int count); * area by redefining the macro below. */ #define PIO_INDIRECT_SIZE 0x4000 -#define MMIO_UPPER_LIMIT (IO_SPACE_LIMIT - PIO_INDIRECT_SIZE) #else -#define MMIO_UPPER_LIMIT IO_SPACE_LIMIT +#define PIO_INDIRECT_SIZE 0 #endif /* CONFIG_INDIRECT_PIO */ +#define MMIO_UPPER_LIMIT (IO_SPACE_LIMIT - PIO_INDIRECT_SIZE) struct logic_pio_hwaddr *find_io_range_by_fwnode(struct fwnode_handle *fwnode); unsigned long logic_pio_trans_hwaddr(struct fwnode_handle *fwnode, -- cgit v1.2.3-71-gd317 From add3efdd78b8a0478ce423bb9d4df6bd95e8b335 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 5 Nov 2019 17:44:07 +0100 Subject: jbd2: Fix possible overflow in jbd2_log_space_left() When number of free space in the journal is very low, the arithmetic in jbd2_log_space_left() could underflow resulting in very high number of free blocks and thus triggering assertion failure in transaction commit code complaining there's not enough space in the journal: J_ASSERT(journal->j_free > 1); Properly check for the low number of free blocks. CC: stable@vger.kernel.org Reviewed-by: Theodore Ts'o Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20191105164437.32602-1-jack@suse.cz Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 603fbc4e2f70..10e6049c0ba9 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1582,7 +1582,7 @@ static inline int jbd2_space_needed(journal_t *journal) static inline unsigned long jbd2_log_space_left(journal_t *journal) { /* Allow for rounding errors */ - unsigned long free = journal->j_free - 32; + long free = journal->j_free - 32; if (journal->j_committing_transaction) { unsigned long committing = atomic_read(&journal-> @@ -1591,7 +1591,7 @@ static inline unsigned long jbd2_log_space_left(journal_t *journal) /* Transaction + control blocks */ free -= committing + (committing >> JBD2_CONTROL_BLOCKS_SHIFT); } - return free; + return max_t(long, free, 0); } /* -- cgit v1.2.3-71-gd317 From 8670b2b8b029a6650d133486be9d2ace146fd29a Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Thu, 24 Oct 2019 19:40:42 +0200 Subject: rfkill: allocate static minor udev has a feature of creating /dev/ device-nodes if it finds a devnode: modalias. This allows for auto-loading of modules that provide the node. This requires to use a statically allocated minor number for misc character devices. However, rfkill uses dynamic minor numbers and prevents auto-loading of the module. So allocate the next static misc minor number and use it for rfkill. Signed-off-by: Marcel Holtmann Link: https://lore.kernel.org/r/20191024174042.19851-1-marcel@holtmann.org Signed-off-by: Greg Kroah-Hartman --- include/linux/miscdevice.h | 1 + net/rfkill/core.c | 9 +++++++-- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index 3247a3dc7934..b06b75776a32 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -57,6 +57,7 @@ #define UHID_MINOR 239 #define USERIO_MINOR 240 #define VHOST_VSOCK_MINOR 241 +#define RFKILL_MINOR 242 #define MISC_DYNAMIC_MINOR 255 struct device; diff --git a/net/rfkill/core.c b/net/rfkill/core.c index f9b08a6d8dbe..0bf9bf1ceb8f 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -1316,10 +1316,12 @@ static const struct file_operations rfkill_fops = { .llseek = no_llseek, }; +#define RFKILL_NAME "rfkill" + static struct miscdevice rfkill_miscdev = { - .name = "rfkill", .fops = &rfkill_fops, - .minor = MISC_DYNAMIC_MINOR, + .name = RFKILL_NAME, + .minor = RFKILL_MINOR, }; static int __init rfkill_init(void) @@ -1371,3 +1373,6 @@ static void __exit rfkill_exit(void) class_unregister(&rfkill_class); } module_exit(rfkill_exit); + +MODULE_ALIAS_MISCDEV(RFKILL_MINOR); +MODULE_ALIAS("devname:" RFKILL_NAME); -- cgit v1.2.3-71-gd317 From b873af620e58863b70ae9cf97f6fab4cf4c544af Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Tue, 22 Oct 2019 10:43:13 +0200 Subject: lib: devres: provide devm_ioremap_resource_wc() Provide a variant of devm_ioremap_resource() for write-combined ioremap. Signed-off-by: Bartosz Golaszewski Reviewed-by: Arnd Bergmann Link: https://lore.kernel.org/r/20191022084318.22256-4-brgl@bgdev.pl Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/driver-model/devres.rst | 1 + include/linux/device.h | 2 ++ lib/devres.c | 15 +++++++++++++++ 3 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/Documentation/driver-api/driver-model/devres.rst b/Documentation/driver-api/driver-model/devres.rst index 8e3087662daf..e605bb9df6e1 100644 --- a/Documentation/driver-api/driver-model/devres.rst +++ b/Documentation/driver-api/driver-model/devres.rst @@ -316,6 +316,7 @@ IOMAP devm_ioremap_nocache() devm_ioremap_wc() devm_ioremap_resource() : checks resource, requests memory region, ioremaps + devm_ioremap_resource_wc() devm_platform_ioremap_resource() : calls devm_ioremap_resource() for platform device devm_iounmap() pcim_iomap() diff --git a/include/linux/device.h b/include/linux/device.h index d1bcc8f122f6..f05c5b92e61f 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -962,6 +962,8 @@ extern void devm_free_pages(struct device *dev, unsigned long addr); void __iomem *devm_ioremap_resource(struct device *dev, const struct resource *res); +void __iomem *devm_ioremap_resource_wc(struct device *dev, + const struct resource *res); void __iomem *devm_of_iomap(struct device *dev, struct device_node *node, int index, diff --git a/lib/devres.c b/lib/devres.c index a14c727128c1..97fb44e5b4d6 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -169,6 +169,21 @@ void __iomem *devm_ioremap_resource(struct device *dev, } EXPORT_SYMBOL(devm_ioremap_resource); +/** + * devm_ioremap_resource_wc() - write-combined variant of + * devm_ioremap_resource() + * @dev: generic device to handle the resource for + * @res: resource to be handled + * + * Returns a pointer to the remapped memory or an ERR_PTR() encoded error code + * on failure. Usage example: + */ +void __iomem *devm_ioremap_resource_wc(struct device *dev, + const struct resource *res) +{ + return __devm_ioremap_resource(dev, res, DEVM_IOREMAP_WC); +} + /* * devm_of_iomap - Requests a resource and maps the memory mapped IO * for a given device_node managed by a given device -- cgit v1.2.3-71-gd317 From bb6243b4f73d29f8c8faf8f805a2042ac3973b71 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Tue, 22 Oct 2019 10:43:14 +0200 Subject: drivers: platform: provide devm_platform_ioremap_resource_wc() Provide a write-combined variant of devm_platform_ioremap_resource(). Signed-off-by: Bartosz Golaszewski Reviewed-by: Arnd Bergmann Link: https://lore.kernel.org/r/20191022084318.22256-5-brgl@bgdev.pl Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/driver-model/devres.rst | 1 + drivers/base/platform.c | 19 ++++++++++++++++++- include/linux/platform_device.h | 3 +++ 3 files changed, 22 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/Documentation/driver-api/driver-model/devres.rst b/Documentation/driver-api/driver-model/devres.rst index e605bb9df6e1..480b78ca3871 100644 --- a/Documentation/driver-api/driver-model/devres.rst +++ b/Documentation/driver-api/driver-model/devres.rst @@ -318,6 +318,7 @@ IOMAP devm_ioremap_resource() : checks resource, requests memory region, ioremaps devm_ioremap_resource_wc() devm_platform_ioremap_resource() : calls devm_ioremap_resource() for platform device + devm_platform_ioremap_resource_wc() devm_iounmap() pcim_iomap() pcim_iomap_regions() : do request_region() and iomap() on multiple BARs diff --git a/drivers/base/platform.c b/drivers/base/platform.c index e0ca682a756d..28eb71967f17 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -60,6 +60,7 @@ struct resource *platform_get_resource(struct platform_device *dev, } EXPORT_SYMBOL_GPL(platform_get_resource); +#ifdef CONFIG_HAS_IOMEM /** * devm_platform_ioremap_resource - call devm_ioremap_resource() for a platform * device @@ -68,7 +69,6 @@ EXPORT_SYMBOL_GPL(platform_get_resource); * resource management * @index: resource index */ -#ifdef CONFIG_HAS_IOMEM void __iomem *devm_platform_ioremap_resource(struct platform_device *pdev, unsigned int index) { @@ -78,6 +78,23 @@ void __iomem *devm_platform_ioremap_resource(struct platform_device *pdev, return devm_ioremap_resource(&pdev->dev, res); } EXPORT_SYMBOL_GPL(devm_platform_ioremap_resource); + +/** + * devm_platform_ioremap_resource_wc - write-combined variant of + * devm_platform_ioremap_resource() + * + * @pdev: platform device to use both for memory resource lookup as well as + * resource management + * @index: resource index + */ +void __iomem *devm_platform_ioremap_resource_wc(struct platform_device *pdev, + unsigned int index) +{ + struct resource *res; + + res = platform_get_resource(pdev, IORESOURCE_MEM, index); + return devm_ioremap_resource_wc(&pdev->dev, res); +} #endif /* CONFIG_HAS_IOMEM */ /** diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 51fb7fc28587..91fcdbbae89d 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -57,6 +57,9 @@ platform_find_device_by_driver(struct device *start, extern void __iomem * devm_platform_ioremap_resource(struct platform_device *pdev, unsigned int index); +extern void __iomem * +devm_platform_ioremap_resource_wc(struct platform_device *pdev, + unsigned int index); extern int platform_get_irq(struct platform_device *, unsigned int); extern int platform_get_irq_optional(struct platform_device *, unsigned int); extern int platform_irq_count(struct platform_device *); -- cgit v1.2.3-71-gd317 From c9c8641d3ebd79274af75f7df3e6a9c6cc8a66e9 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Tue, 22 Oct 2019 10:43:16 +0200 Subject: drivers: provide devm_platform_ioremap_resource_byname() Provide a variant of devm_platform_ioremap_resource() that allows to lookup resources from platform devices by name rather than by index. Signed-off-by: Bartosz Golaszewski Reviewed-by: Arnd Bergmann Link: https://lore.kernel.org/r/20191022084318.22256-7-brgl@bgdev.pl Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/driver-model/devres.rst | 1 + drivers/base/platform.c | 20 ++++++++++++++++++++ include/linux/platform_device.h | 3 +++ 3 files changed, 24 insertions(+) (limited to 'include/linux') diff --git a/Documentation/driver-api/driver-model/devres.rst b/Documentation/driver-api/driver-model/devres.rst index 480b78ca3871..4ab193319d8c 100644 --- a/Documentation/driver-api/driver-model/devres.rst +++ b/Documentation/driver-api/driver-model/devres.rst @@ -319,6 +319,7 @@ IOMAP devm_ioremap_resource_wc() devm_platform_ioremap_resource() : calls devm_ioremap_resource() for platform device devm_platform_ioremap_resource_wc() + devm_platform_ioremap_resource_byname() devm_iounmap() pcim_iomap() pcim_iomap_regions() : do request_region() and iomap() on multiple BARs diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 28eb71967f17..1b8a20466eef 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -95,6 +95,26 @@ void __iomem *devm_platform_ioremap_resource_wc(struct platform_device *pdev, res = platform_get_resource(pdev, IORESOURCE_MEM, index); return devm_ioremap_resource_wc(&pdev->dev, res); } + +/** + * devm_platform_ioremap_resource_byname - call devm_ioremap_resource for + * a platform device, retrieve the + * resource by name + * + * @pdev: platform device to use both for memory resource lookup as well as + * resource management + * @name: name of the resource + */ +void __iomem * +devm_platform_ioremap_resource_byname(struct platform_device *pdev, + const char *name) +{ + struct resource *res; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, name); + return devm_ioremap_resource(&pdev->dev, res); +} +EXPORT_SYMBOL_GPL(devm_platform_ioremap_resource_byname); #endif /* CONFIG_HAS_IOMEM */ /** diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 91fcdbbae89d..276a03c24691 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -60,6 +60,9 @@ devm_platform_ioremap_resource(struct platform_device *pdev, extern void __iomem * devm_platform_ioremap_resource_wc(struct platform_device *pdev, unsigned int index); +extern void __iomem * +devm_platform_ioremap_resource_byname(struct platform_device *pdev, + const char *name); extern int platform_get_irq(struct platform_device *, unsigned int); extern int platform_get_irq_optional(struct platform_device *, unsigned int); extern int platform_irq_count(struct platform_device *); -- cgit v1.2.3-71-gd317 From 9b8303fc6efa724bd6a90656434fbde2cc6ceb2c Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Tue, 29 Oct 2019 11:42:31 +0000 Subject: nvmem: core: fix nvmem_cell_write inline function nvmem_cell_write's buf argument uses different types based on the configuration of CONFIG_NVMEM. The function prototype for enabled NVMEM uses 'void *' type, but the static dummy function for disabled NVMEM uses 'const char *' instead. Fix the different behaviour by always expecting a 'void *' typed buf argument. Fixes: 7a78a7f7695b ("power: reset: nvmem-reboot-mode: use NVMEM as reboot mode write interface") Reported-by: kbuild test robot Cc: Han Nandor Cc: Srinivas Kandagatla Cc: linux-kernel@vger.kernel.org Signed-off-by: Sebastian Reichel Reviewed-By: Han Nandor Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20191029114240.14905-2-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-consumer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 8f8be5b00060..5c17cb733224 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -118,7 +118,7 @@ static inline void *nvmem_cell_read(struct nvmem_cell *cell, size_t *len) } static inline int nvmem_cell_write(struct nvmem_cell *cell, - const char *buf, size_t len) + void *buf, size_t len) { return -EOPNOTSUPP; } -- cgit v1.2.3-71-gd317 From 8adeac3be03d400f9c2391d52f85cd27bd188800 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Wed, 2 Oct 2019 14:03:41 -0500 Subject: dm stripe: use struct_size() in kmalloc() One of the more common cases of allocation size calculations is finding the size of a structure that has a zero-sized array at the end, along with memory for some number of elements for that array. For example: struct stripe_c { ... struct stripe stripe[0]; }; In this case alloc_context() and dm_array_too_big() are removed and replaced by the direct use of the struct_size() helper in kmalloc(). Notice that open-coded form is prone to type mistakes. This code was detected with the help of Coccinelle. Signed-off-by: Gustavo A. R. Silva Signed-off-by: Mike Snitzer --- drivers/md/dm-stripe.c | 15 +-------------- include/linux/device-mapper.h | 3 --- 2 files changed, 1 insertion(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index 8547d7594338..63bbcc20f49a 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -55,19 +55,6 @@ static void trigger_event(struct work_struct *work) dm_table_event(sc->ti->table); } -static inline struct stripe_c *alloc_context(unsigned int stripes) -{ - size_t len; - - if (dm_array_too_big(sizeof(struct stripe_c), sizeof(struct stripe), - stripes)) - return NULL; - - len = sizeof(struct stripe_c) + (sizeof(struct stripe) * stripes); - - return kmalloc(len, GFP_KERNEL); -} - /* * Parse a single pair */ @@ -142,7 +129,7 @@ static int stripe_ctr(struct dm_target *ti, unsigned int argc, char **argv) return -EINVAL; } - sc = alloc_context(stripes); + sc = kmalloc(struct_size(sc, stripe, stripes), GFP_KERNEL); if (!sc) { ti->error = "Memory allocation for striped context " "failed"; diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 399ad8632356..2e13826898b2 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -594,9 +594,6 @@ void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size); */ #define dm_round_up(n, sz) (dm_div_up((n), (sz)) * (sz)) -#define dm_array_too_big(fixed, obj, num) \ - ((num) > (UINT_MAX - (fixed)) / (obj)) - /* * Sector offset taken relative to the start of the target instead of * relative to the start of the device. -- cgit v1.2.3-71-gd317 From a9a8344ee1714f835ba394077e8c13d751e2f148 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 5 Nov 2019 17:44:17 +0100 Subject: ext4, jbd2: Provide accessor function for handle credits Provide accessor function to get number of credits available in a handle and use it from ext4. Later, computation of available credits won't be so straightforward. Reviewed-by: Theodore Ts'o Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20191105164437.32602-11-jack@suse.cz Signed-off-by: Theodore Ts'o --- fs/ext4/ext4_jbd2.c | 13 +++++++------ fs/ext4/ext4_jbd2.h | 7 ------- fs/ext4/xattr.c | 2 +- include/linux/jbd2.h | 6 ++++++ 4 files changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 2b98d893cda9..731bbfdbce5b 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -119,8 +119,8 @@ handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line, return ext4_get_nojournal(); sb = handle->h_journal->j_private; - trace_ext4_journal_start_reserved(sb, handle->h_buffer_credits, - _RET_IP_); + trace_ext4_journal_start_reserved(sb, + jbd2_handle_buffer_credits(handle), _RET_IP_); err = ext4_journal_check_start(sb); if (err < 0) { jbd2_journal_free_reserved(handle); @@ -138,10 +138,10 @@ int __ext4_journal_ensure_credits(handle_t *handle, int check_cred, { if (!ext4_handle_valid(handle)) return 0; - if (handle->h_buffer_credits >= check_cred) + if (jbd2_handle_buffer_credits(handle) >= check_cred) return 0; return ext4_journal_extend(handle, - extend_cred - handle->h_buffer_credits); + extend_cred - jbd2_handle_buffer_credits(handle)); } static void ext4_journal_abort_handle(const char *caller, unsigned int line, @@ -289,7 +289,7 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, handle->h_type, handle->h_line_no, handle->h_requested_credits, - handle->h_buffer_credits, err); + jbd2_handle_buffer_credits(handle), err); return err; } ext4_error_inode(inode, where, line, @@ -300,7 +300,8 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, handle->h_type, handle->h_line_no, handle->h_requested_credits, - handle->h_buffer_credits, err); + jbd2_handle_buffer_credits(handle), + err); } } else { if (inode) diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index 1920b976eef1..36aa72599646 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -288,13 +288,6 @@ static inline int ext4_handle_is_aborted(handle_t *handle) return 0; } -static inline int ext4_handle_has_enough_credits(handle_t *handle, int needed) -{ - if (ext4_handle_valid(handle) && handle->h_buffer_credits < needed) - return 0; - return 1; -} - #define ext4_journal_start_sb(sb, type, nblocks) \ __ext4_journal_start_sb((sb), __LINE__, (type), (nblocks), 0) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index b79d8ffd3e9b..48a9dbd27f43 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2314,7 +2314,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, flags & XATTR_CREATE); brelse(bh); - if (!ext4_handle_has_enough_credits(handle, credits)) { + if (jbd2_handle_buffer_credits(handle) < credits) { error = -ENOSPC; goto cleanup; } diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 10e6049c0ba9..727ff91d7f3e 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1645,6 +1645,12 @@ static inline tid_t jbd2_get_latest_transaction(journal_t *journal) return tid; } + +static inline int jbd2_handle_buffer_credits(handle_t *handle) +{ + return handle->h_buffer_credits; +} + #ifdef __KERNEL__ #define buffer_trace_init(bh) do {} while (0) -- cgit v1.2.3-71-gd317 From 9f356e5a4f12008fa0df8b6385fc0ab830416e72 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 5 Nov 2019 17:44:24 +0100 Subject: jbd2: Account descriptor blocks into t_outstanding_credits Currently, journal descriptor blocks were not accounted in transaction->t_outstanding_credits and we were just leaving some slack space in the journal for them (in jbd2_log_space_left() and jbd2_space_needed()). This is making proper accounting (and reservation we want to add) of descriptor blocks difficult so switch to accounting descriptor blocks in transaction->t_outstanding_credits and just reserve the same amount of credits in t_outstanding credits for journal descriptor blocks when creating transaction. Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20191105164437.32602-18-jack@suse.cz Signed-off-by: Theodore Ts'o --- fs/jbd2/commit.c | 6 ++++-- fs/jbd2/journal.c | 1 + fs/jbd2/transaction.c | 20 ++++++++++++-------- include/linux/jbd2.h | 22 +++++++--------------- 4 files changed, 24 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index b67e2d0cff88..9047f8e269d0 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -560,8 +560,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) stats.run.rs_logging = jiffies; stats.run.rs_flushing = jbd2_time_diff(stats.run.rs_flushing, stats.run.rs_logging); - stats.run.rs_blocks = - atomic_read(&commit_transaction->t_outstanding_credits); + stats.run.rs_blocks = commit_transaction->t_nr_buffers; stats.run.rs_blocks_logged = 0; J_ASSERT(commit_transaction->t_nr_buffers <= @@ -889,6 +888,9 @@ start_journal_io: if (err) jbd2_journal_abort(journal, err); + WARN_ON_ONCE( + atomic_read(&commit_transaction->t_outstanding_credits) < 0); + /* * Now disk caches for filesystem device are flushed so we are safe to * erase checkpointed transactions from the log by updating journal diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index cc11097f1176..22b14b3ca197 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -840,6 +840,7 @@ jbd2_journal_get_descriptor_buffer(transaction_t *transaction, int type) bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize); if (!bh) return NULL; + atomic_dec(&transaction->t_outstanding_credits); lock_buffer(bh); memset(bh->b_data, 0, journal->j_blocksize); header = (journal_header_t *)bh->b_data; diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index b30df011beaa..ed7cf9e62584 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -62,6 +62,17 @@ void jbd2_journal_free_transaction(transaction_t *transaction) kmem_cache_free(transaction_cache, transaction); } +/* + * We reserve t_outstanding_credits >> JBD2_CONTROL_BLOCKS_SHIFT for + * transaction descriptor blocks. + */ +#define JBD2_CONTROL_BLOCKS_SHIFT 5 + +static int jbd2_descriptor_blocks_per_trans(journal_t *journal) +{ + return journal->j_max_transaction_buffers >> JBD2_CONTROL_BLOCKS_SHIFT; +} + /* * jbd2_get_transaction: obtain a new transaction_t object. * @@ -88,6 +99,7 @@ static void jbd2_get_transaction(journal_t *journal, spin_lock_init(&transaction->t_handle_lock); atomic_set(&transaction->t_updates, 0); atomic_set(&transaction->t_outstanding_credits, + jbd2_descriptor_blocks_per_trans(journal) + atomic_read(&journal->j_reserved_credits)); atomic_set(&transaction->t_handle_count, 0); INIT_LIST_HEAD(&transaction->t_inode_list); @@ -634,14 +646,6 @@ int jbd2_journal_extend(handle_t *handle, int nblocks) goto unlock; } - if (wanted + (wanted >> JBD2_CONTROL_BLOCKS_SHIFT) > - jbd2_log_space_left(journal)) { - jbd_debug(3, "denied handle %p %d blocks: " - "insufficient log space\n", handle, nblocks); - atomic_sub(nblocks, &transaction->t_outstanding_credits); - goto unlock; - } - trace_jbd2_handle_extend(journal->j_fs_dev->bd_dev, transaction->t_tid, handle->h_type, handle->h_line_no, diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 727ff91d7f3e..bef4f74b1ea0 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -681,8 +681,10 @@ struct transaction_s atomic_t t_updates; /* - * Number of buffers reserved for use by all handles in this transaction - * handle but not yet modified. [none] + * Number of blocks reserved for this transaction in the journal. + * This is including all credits reserved when starting transaction + * handles as well as all journal descriptor blocks needed for this + * transaction. [none] */ atomic_t t_outstanding_credits; @@ -1560,20 +1562,13 @@ static inline int jbd2_journal_has_csum_v2or3(journal_t *journal) return journal->j_chksum_driver != NULL; } -/* - * We reserve t_outstanding_credits >> JBD2_CONTROL_BLOCKS_SHIFT for - * transaction control blocks. - */ -#define JBD2_CONTROL_BLOCKS_SHIFT 5 - /* * Return the minimum number of blocks which must be free in the journal * before a new transaction may be started. Must be called under j_state_lock. */ static inline int jbd2_space_needed(journal_t *journal) { - int nblocks = journal->j_max_transaction_buffers; - return nblocks + (nblocks >> JBD2_CONTROL_BLOCKS_SHIFT); + return journal->j_max_transaction_buffers; } /* @@ -1585,11 +1580,8 @@ static inline unsigned long jbd2_log_space_left(journal_t *journal) long free = journal->j_free - 32; if (journal->j_committing_transaction) { - unsigned long committing = atomic_read(&journal-> - j_committing_transaction->t_outstanding_credits); - - /* Transaction + control blocks */ - free -= committing + (committing >> JBD2_CONTROL_BLOCKS_SHIFT); + free -= atomic_read(&journal-> + j_committing_transaction->t_outstanding_credits); } return max_t(long, free, 0); } -- cgit v1.2.3-71-gd317 From 77444ac4f9537bc4211f928959d5231445e30c6e Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 5 Nov 2019 17:44:25 +0100 Subject: jbd2: Drop jbd2_space_needed() The function is now just a trivial wrapper returning journal->j_max_transaction_buffers. Drop it. Reviewed-by: Theodore Ts'o Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20191105164437.32602-19-jack@suse.cz Signed-off-by: Theodore Ts'o --- fs/jbd2/checkpoint.c | 2 +- fs/jbd2/transaction.c | 5 +++-- include/linux/jbd2.h | 9 --------- 3 files changed, 4 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index a1909066bde6..8fff6677a5da 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -110,7 +110,7 @@ void __jbd2_log_wait_for_space(journal_t *journal) int nblocks, space_left; /* assert_spin_locked(&journal->j_state_lock); */ - nblocks = jbd2_space_needed(journal); + nblocks = journal->j_max_transaction_buffers; while (jbd2_log_space_left(journal) < nblocks) { write_unlock(&journal->j_state_lock); mutex_lock_io(&journal->j_checkpoint_mutex); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index ed7cf9e62584..ba388da7e02b 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -270,12 +270,13 @@ static int add_transaction_credits(journal_t *journal, int blocks, * *before* starting to dirty potentially checkpointed buffers * in the new transaction. */ - if (jbd2_log_space_left(journal) < jbd2_space_needed(journal)) { + if (jbd2_log_space_left(journal) < journal->j_max_transaction_buffers) { atomic_sub(total, &t->t_outstanding_credits); read_unlock(&journal->j_state_lock); jbd2_might_wait_for_commit(journal); write_lock(&journal->j_state_lock); - if (jbd2_log_space_left(journal) < jbd2_space_needed(journal)) + if (jbd2_log_space_left(journal) < + journal->j_max_transaction_buffers) __jbd2_log_wait_for_space(journal); write_unlock(&journal->j_state_lock); return 1; diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index bef4f74b1ea0..1dd2703a8e26 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1562,15 +1562,6 @@ static inline int jbd2_journal_has_csum_v2or3(journal_t *journal) return journal->j_chksum_driver != NULL; } -/* - * Return the minimum number of blocks which must be free in the journal - * before a new transaction may be started. Must be called under j_state_lock. - */ -static inline int jbd2_space_needed(journal_t *journal) -{ - return journal->j_max_transaction_buffers; -} - /* * Return number of free blocks in the log. Must be called under j_state_lock. */ -- cgit v1.2.3-71-gd317 From fdc3ef882a5d59c1709a13b5486ae2b1632e12b6 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 5 Nov 2019 17:44:26 +0100 Subject: jbd2: Reserve space for revoke descriptor blocks Extend functions for starting, extending, and restarting transaction handles to take number of revoke records handle must be able to accommodate. These functions then make sure transaction has enough credits to be able to store resulting revoke descriptor blocks. Also revoke code tracks number of revoke records created by a handle to catch situation where some place didn't reserve enough space for revoke records. Similarly to standard transaction credits, space for unused reserved revoke records is released when the handle is stopped. On the ext4 side we currently take a simplistic approach of reserving space for 1024 revoke records for any transaction. This grows amount of credits reserved for each handle only by a few and is enough for any normal workload so that we don't hit warnings in jbd2. We will refine the logic in following commits. Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20191105164437.32602-20-jack@suse.cz Signed-off-by: Theodore Ts'o --- fs/ext4/ext4_jbd2.c | 2 +- fs/ext4/ext4_jbd2.h | 4 ++-- fs/jbd2/journal.c | 21 ++++++++++++++++++++ fs/jbd2/revoke.c | 6 ++++++ fs/jbd2/transaction.c | 54 ++++++++++++++++++++++++++++++++++++++++++++------- fs/ocfs2/journal.c | 4 ++-- include/linux/jbd2.h | 43 ++++++++++++++++++++++++++++++---------- 7 files changed, 112 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 731bbfdbce5b..b81190bee32d 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -78,7 +78,7 @@ handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line, journal = EXT4_SB(sb)->s_journal; if (!journal) return ext4_get_nojournal(); - return jbd2__journal_start(journal, blocks, rsv_blocks, GFP_NOFS, + return jbd2__journal_start(journal, blocks, rsv_blocks, 1024, GFP_NOFS, type, line); } diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index 36aa72599646..aca05e52e317 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -328,14 +328,14 @@ static inline handle_t *ext4_journal_current_handle(void) static inline int ext4_journal_extend(handle_t *handle, int nblocks) { if (ext4_handle_valid(handle)) - return jbd2_journal_extend(handle, nblocks); + return jbd2_journal_extend(handle, nblocks, 1024); return 0; } static inline int ext4_journal_restart(handle_t *handle, int nblocks) { if (ext4_handle_valid(handle)) - return jbd2_journal_restart(handle, nblocks); + return jbd2__journal_restart(handle, nblocks, 1024, GFP_NOFS); return 0; } diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 22b14b3ca197..eef809f61722 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1500,6 +1500,21 @@ void jbd2_journal_update_sb_errno(journal_t *journal) } EXPORT_SYMBOL(jbd2_journal_update_sb_errno); +static int journal_revoke_records_per_block(journal_t *journal) +{ + int record_size; + int space = journal->j_blocksize - sizeof(jbd2_journal_revoke_header_t); + + if (jbd2_has_feature_64bit(journal)) + record_size = 8; + else + record_size = 4; + + if (jbd2_journal_has_csum_v2or3(journal)) + space -= sizeof(struct jbd2_journal_block_tail); + return space / record_size; +} + /* * Read the superblock for a given journal, performing initial * validation of the format. @@ -1608,6 +1623,8 @@ static int journal_get_superblock(journal_t *journal) sizeof(sb->s_uuid)); } + journal->j_revoke_records_per_block = + journal_revoke_records_per_block(journal); set_buffer_verified(bh); return 0; @@ -1928,6 +1945,8 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat, sb->s_feature_ro_compat |= cpu_to_be32(ro); sb->s_feature_incompat |= cpu_to_be32(incompat); unlock_buffer(journal->j_sb_buffer); + journal->j_revoke_records_per_block = + journal_revoke_records_per_block(journal); return 1; #undef COMPAT_FEATURE_ON @@ -1958,6 +1977,8 @@ void jbd2_journal_clear_features(journal_t *journal, unsigned long compat, sb->s_feature_compat &= ~cpu_to_be32(compat); sb->s_feature_ro_compat &= ~cpu_to_be32(ro); sb->s_feature_incompat &= ~cpu_to_be32(incompat); + journal->j_revoke_records_per_block = + journal_revoke_records_per_block(journal); } EXPORT_SYMBOL(jbd2_journal_clear_features); diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c index f08073d7bbf5..fa608788b93d 100644 --- a/fs/jbd2/revoke.c +++ b/fs/jbd2/revoke.c @@ -371,6 +371,11 @@ int jbd2_journal_revoke(handle_t *handle, unsigned long long blocknr, } #endif + if (WARN_ON_ONCE(handle->h_revoke_credits <= 0)) { + if (!bh_in) + brelse(bh); + return -EIO; + } /* We really ought not ever to revoke twice in a row without first having the revoke cancelled: it's illegal to free a block twice without allocating it in between! */ @@ -391,6 +396,7 @@ int jbd2_journal_revoke(handle_t *handle, unsigned long long blocknr, __brelse(bh); } } + handle->h_revoke_credits--; jbd_debug(2, "insert revoke for block %llu, bh_in=%p\n",blocknr, bh_in); err = insert_revoke_hash(journal, blocknr, diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index ba388da7e02b..1c121afbcf8f 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -101,6 +101,7 @@ static void jbd2_get_transaction(journal_t *journal, atomic_set(&transaction->t_outstanding_credits, jbd2_descriptor_blocks_per_trans(journal) + atomic_read(&journal->j_reserved_credits)); + atomic_set(&transaction->t_outstanding_revokes, 0); atomic_set(&transaction->t_handle_count, 0); INIT_LIST_HEAD(&transaction->t_inode_list); INIT_LIST_HEAD(&transaction->t_private_list); @@ -418,6 +419,7 @@ repeat: update_t_max_wait(transaction, ts); handle->h_transaction = transaction; handle->h_requested_credits = blocks; + handle->h_revoke_credits_requested = handle->h_revoke_credits; handle->h_start_jiffies = jiffies; atomic_inc(&transaction->t_updates); atomic_inc(&transaction->t_handle_count); @@ -451,8 +453,8 @@ static handle_t *new_handle(int nblocks) } handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int rsv_blocks, - gfp_t gfp_mask, unsigned int type, - unsigned int line_no) + int revoke_records, gfp_t gfp_mask, + unsigned int type, unsigned int line_no) { handle_t *handle = journal_current_handle(); int err; @@ -466,6 +468,8 @@ handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int rsv_blocks, return handle; } + nblocks += DIV_ROUND_UP(revoke_records, + journal->j_revoke_records_per_block); handle = new_handle(nblocks); if (!handle) return ERR_PTR(-ENOMEM); @@ -481,6 +485,7 @@ handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int rsv_blocks, rsv_handle->h_journal = journal; handle->h_rsv_handle = rsv_handle; } + handle->h_revoke_credits = revoke_records; err = start_this_handle(journal, handle, gfp_mask); if (err < 0) { @@ -521,7 +526,7 @@ EXPORT_SYMBOL(jbd2__journal_start); */ handle_t *jbd2_journal_start(journal_t *journal, int nblocks) { - return jbd2__journal_start(journal, nblocks, 0, GFP_NOFS, 0, 0); + return jbd2__journal_start(journal, nblocks, 0, 0, GFP_NOFS, 0, 0); } EXPORT_SYMBOL(jbd2_journal_start); @@ -598,6 +603,7 @@ EXPORT_SYMBOL(jbd2_journal_start_reserved); * int jbd2_journal_extend() - extend buffer credits. * @handle: handle to 'extend' * @nblocks: nr blocks to try to extend by. + * @revoke_records: number of revoke records to try to extend by. * * Some transactions, such as large extends and truncates, can be done * atomically all at once or in several stages. The operation requests @@ -614,7 +620,7 @@ EXPORT_SYMBOL(jbd2_journal_start_reserved); * return code < 0 implies an error * return code > 0 implies normal transaction-full status. */ -int jbd2_journal_extend(handle_t *handle, int nblocks) +int jbd2_journal_extend(handle_t *handle, int nblocks, int revoke_records) { transaction_t *transaction = handle->h_transaction; journal_t *journal; @@ -636,6 +642,12 @@ int jbd2_journal_extend(handle_t *handle, int nblocks) goto error_out; } + nblocks += DIV_ROUND_UP( + handle->h_revoke_credits_requested + revoke_records, + journal->j_revoke_records_per_block) - + DIV_ROUND_UP( + handle->h_revoke_credits_requested, + journal->j_revoke_records_per_block); spin_lock(&transaction->t_handle_lock); wanted = atomic_add_return(nblocks, &transaction->t_outstanding_credits); @@ -655,6 +667,8 @@ int jbd2_journal_extend(handle_t *handle, int nblocks) handle->h_buffer_credits += nblocks; handle->h_requested_credits += nblocks; + handle->h_revoke_credits += revoke_records; + handle->h_revoke_credits_requested += revoke_records; result = 0; jbd_debug(3, "extended handle %p by %d\n", handle, nblocks); @@ -669,10 +683,31 @@ static void stop_this_handle(handle_t *handle) { transaction_t *transaction = handle->h_transaction; journal_t *journal = transaction->t_journal; + int revokes; J_ASSERT(journal_current_handle() == handle); J_ASSERT(atomic_read(&transaction->t_updates) > 0); current->journal_info = NULL; + /* + * Subtract necessary revoke descriptor blocks from handle credits. We + * take care to account only for revoke descriptor blocks the + * transaction will really need as large sequences of transactions with + * small numbers of revokes are relatively common. + */ + revokes = handle->h_revoke_credits_requested - handle->h_revoke_credits; + if (revokes) { + int t_revokes, revoke_descriptors; + int rr_per_blk = journal->j_revoke_records_per_block; + + WARN_ON_ONCE(DIV_ROUND_UP(revokes, rr_per_blk) + > handle->h_buffer_credits); + t_revokes = atomic_add_return(revokes, + &transaction->t_outstanding_revokes); + revoke_descriptors = + DIV_ROUND_UP(t_revokes, rr_per_blk) - + DIV_ROUND_UP(t_revokes - revokes, rr_per_blk); + handle->h_buffer_credits -= revoke_descriptors; + } atomic_sub(handle->h_buffer_credits, &transaction->t_outstanding_credits); if (handle->h_rsv_handle) @@ -692,6 +727,7 @@ static void stop_this_handle(handle_t *handle) * int jbd2_journal_restart() - restart a handle . * @handle: handle to restart * @nblocks: nr credits requested + * @revoke_records: number of revoke record credits requested * @gfp_mask: memory allocation flags (for start_this_handle) * * Restart a handle for a multi-transaction filesystem @@ -704,7 +740,8 @@ static void stop_this_handle(handle_t *handle) * credits. We preserve reserved handle if there's any attached to the * passed in handle. */ -int jbd2__journal_restart(handle_t *handle, int nblocks, gfp_t gfp_mask) +int jbd2__journal_restart(handle_t *handle, int nblocks, int revoke_records, + gfp_t gfp_mask) { transaction_t *transaction = handle->h_transaction; journal_t *journal; @@ -735,7 +772,10 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, gfp_t gfp_mask) read_unlock(&journal->j_state_lock); if (need_to_start) jbd2_log_start_commit(journal, tid); - handle->h_buffer_credits = nblocks; + handle->h_buffer_credits = nblocks + + DIV_ROUND_UP(revoke_records, + journal->j_revoke_records_per_block); + handle->h_revoke_credits = revoke_records; return start_this_handle(journal, handle, gfp_mask); } EXPORT_SYMBOL(jbd2__journal_restart); @@ -743,7 +783,7 @@ EXPORT_SYMBOL(jbd2__journal_restart); int jbd2_journal_restart(handle_t *handle, int nblocks) { - return jbd2__journal_restart(handle, nblocks, GFP_NOFS); + return jbd2__journal_restart(handle, nblocks, 0, GFP_NOFS); } EXPORT_SYMBOL(jbd2_journal_restart); diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 019aaf2a3f8a..a032f0297dad 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -426,7 +426,7 @@ int ocfs2_extend_trans(handle_t *handle, int nblocks) #ifdef CONFIG_OCFS2_DEBUG_FS status = 1; #else - status = jbd2_journal_extend(handle, nblocks); + status = jbd2_journal_extend(handle, nblocks, 0); if (status < 0) { mlog_errno(status); goto bail; @@ -466,7 +466,7 @@ int ocfs2_allocate_extend_trans(handle_t *handle, int thresh) if (old_nblks < thresh) return 0; - status = jbd2_journal_extend(handle, OCFS2_MAX_TRANS_DATA); + status = jbd2_journal_extend(handle, OCFS2_MAX_TRANS_DATA, 0); if (status < 0) { mlog_errno(status); goto bail; diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 1dd2703a8e26..2a3d5f50e7a1 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -478,6 +478,7 @@ struct jbd2_revoke_table_s; * @h_journal: Which journal handle belongs to - used iff h_reserved set. * @h_rsv_handle: Handle reserved for finishing the logical operation. * @h_buffer_credits: Number of remaining buffers we are allowed to dirty. + * @h_revoke_credits: Number of remaining revoke records available for handle * @h_ref: Reference count on this handle. * @h_err: Field for caller's use to track errors through large fs operations. * @h_sync: Flag for sync-on-close. @@ -488,6 +489,7 @@ struct jbd2_revoke_table_s; * @h_line_no: For handle statistics. * @h_start_jiffies: Handle Start time. * @h_requested_credits: Holds @h_buffer_credits after handle is started. + * @h_revoke_credits_requested: Holds @h_revoke_credits after handle is started. * @saved_alloc_context: Saved context while transaction is open. **/ @@ -505,6 +507,8 @@ struct jbd2_journal_handle handle_t *h_rsv_handle; int h_buffer_credits; + int h_revoke_credits; + int h_revoke_credits_requested; int h_ref; int h_err; @@ -688,6 +692,17 @@ struct transaction_s */ atomic_t t_outstanding_credits; + /* + * Number of revoke records for this transaction added by already + * stopped handles. [none] + */ + atomic_t t_outstanding_revokes; + + /* + * How many handles used this transaction? [none] + */ + atomic_t t_handle_count; + /* * Forward and backward links for the circular list of all transactions * awaiting checkpoint. [j_list_lock] @@ -705,11 +720,6 @@ struct transaction_s */ ktime_t t_start_time; - /* - * How many handles used this transaction? [none] - */ - atomic_t t_handle_count; - /* * This transaction is being forced and some process is * waiting for it to finish. @@ -1026,6 +1036,13 @@ struct journal_s */ int j_max_transaction_buffers; + /** + * @j_revoke_records_per_block: + * + * Number of revoke records that fit in one descriptor block. + */ + int j_revoke_records_per_block; + /** * @j_commit_interval: * @@ -1360,14 +1377,16 @@ static inline handle_t *journal_current_handle(void) extern handle_t *jbd2_journal_start(journal_t *, int nblocks); extern handle_t *jbd2__journal_start(journal_t *, int blocks, int rsv_blocks, - gfp_t gfp_mask, unsigned int type, - unsigned int line_no); + int revoke_records, gfp_t gfp_mask, + unsigned int type, unsigned int line_no); extern int jbd2_journal_restart(handle_t *, int nblocks); -extern int jbd2__journal_restart(handle_t *, int nblocks, gfp_t gfp_mask); +extern int jbd2__journal_restart(handle_t *, int nblocks, + int revoke_records, gfp_t gfp_mask); extern int jbd2_journal_start_reserved(handle_t *handle, unsigned int type, unsigned int line_no); extern void jbd2_journal_free_reserved(handle_t *handle); -extern int jbd2_journal_extend (handle_t *, int nblocks); +extern int jbd2_journal_extend(handle_t *handle, int nblocks, + int revoke_records); extern int jbd2_journal_get_write_access(handle_t *, struct buffer_head *); extern int jbd2_journal_get_create_access (handle_t *, struct buffer_head *); extern int jbd2_journal_get_undo_access(handle_t *, struct buffer_head *); @@ -1631,7 +1650,11 @@ static inline tid_t jbd2_get_latest_transaction(journal_t *journal) static inline int jbd2_handle_buffer_credits(handle_t *handle) { - return handle->h_buffer_credits; + journal_t *journal = handle->h_transaction->t_journal; + + return handle->h_buffer_credits - + DIV_ROUND_UP(handle->h_revoke_credits_requested, + journal->j_revoke_records_per_block); } #ifdef __KERNEL__ -- cgit v1.2.3-71-gd317 From 933f1c1e0b75bbc29730eef07c9e196c6dfd37e5 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 5 Nov 2019 17:44:27 +0100 Subject: jbd2: Rename h_buffer_credits to h_total_credits The credit counter now contains both buffer and revoke descriptor block credits. Rename to counter to h_total_credits to reflect that. No functional change. Reviewed-by: Theodore Ts'o Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20191105164437.32602-21-jack@suse.cz Signed-off-by: Theodore Ts'o --- fs/jbd2/transaction.c | 30 +++++++++++++++--------------- include/linux/jbd2.h | 9 +++++---- 2 files changed, 20 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 1c121afbcf8f..10fd802fd222 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -313,12 +313,12 @@ static int start_this_handle(journal_t *journal, handle_t *handle, gfp_t gfp_mask) { transaction_t *transaction, *new_transaction = NULL; - int blocks = handle->h_buffer_credits; + int blocks = handle->h_total_credits; int rsv_blocks = 0; unsigned long ts = jiffies; if (handle->h_rsv_handle) - rsv_blocks = handle->h_rsv_handle->h_buffer_credits; + rsv_blocks = handle->h_rsv_handle->h_total_credits; /* * Limit the number of reserved credits to 1/2 of maximum transaction @@ -446,7 +446,7 @@ static handle_t *new_handle(int nblocks) handle_t *handle = jbd2_alloc_handle(GFP_NOFS); if (!handle) return NULL; - handle->h_buffer_credits = nblocks; + handle->h_total_credits = nblocks; handle->h_ref = 1; return handle; @@ -535,7 +535,7 @@ static void __jbd2_journal_unreserve_handle(handle_t *handle) journal_t *journal = handle->h_journal; WARN_ON(!handle->h_reserved); - sub_reserved_credits(journal, handle->h_buffer_credits); + sub_reserved_credits(journal, handle->h_total_credits); } void jbd2_journal_free_reserved(handle_t *handle) @@ -594,7 +594,7 @@ int jbd2_journal_start_reserved(handle_t *handle, unsigned int type, handle->h_line_no = line_no; trace_jbd2_handle_start(journal->j_fs_dev->bd_dev, handle->h_transaction->t_tid, type, - line_no, handle->h_buffer_credits); + line_no, handle->h_total_credits); return 0; } EXPORT_SYMBOL(jbd2_journal_start_reserved); @@ -662,10 +662,10 @@ int jbd2_journal_extend(handle_t *handle, int nblocks, int revoke_records) trace_jbd2_handle_extend(journal->j_fs_dev->bd_dev, transaction->t_tid, handle->h_type, handle->h_line_no, - handle->h_buffer_credits, + handle->h_total_credits, nblocks); - handle->h_buffer_credits += nblocks; + handle->h_total_credits += nblocks; handle->h_requested_credits += nblocks; handle->h_revoke_credits += revoke_records; handle->h_revoke_credits_requested += revoke_records; @@ -700,15 +700,15 @@ static void stop_this_handle(handle_t *handle) int rr_per_blk = journal->j_revoke_records_per_block; WARN_ON_ONCE(DIV_ROUND_UP(revokes, rr_per_blk) - > handle->h_buffer_credits); + > handle->h_total_credits); t_revokes = atomic_add_return(revokes, &transaction->t_outstanding_revokes); revoke_descriptors = DIV_ROUND_UP(t_revokes, rr_per_blk) - DIV_ROUND_UP(t_revokes - revokes, rr_per_blk); - handle->h_buffer_credits -= revoke_descriptors; + handle->h_total_credits -= revoke_descriptors; } - atomic_sub(handle->h_buffer_credits, + atomic_sub(handle->h_total_credits, &transaction->t_outstanding_credits); if (handle->h_rsv_handle) __jbd2_journal_unreserve_handle(handle->h_rsv_handle); @@ -772,7 +772,7 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, int revoke_records, read_unlock(&journal->j_state_lock); if (need_to_start) jbd2_log_start_commit(journal, tid); - handle->h_buffer_credits = nblocks + + handle->h_total_credits = nblocks + DIV_ROUND_UP(revoke_records, journal->j_revoke_records_per_block); handle->h_revoke_credits = revoke_records; @@ -1477,12 +1477,12 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) * of the transaction. This needs to be done * once a transaction -bzzz */ - if (handle->h_buffer_credits <= 0) { + if (handle->h_total_credits <= 0) { ret = -ENOSPC; goto out_unlock_bh; } jh->b_modified = 1; - handle->h_buffer_credits--; + handle->h_total_credits--; } /* @@ -1726,7 +1726,7 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh) drop: if (drop_reserve) { /* no need to reserve log space for this block -bzzz */ - handle->h_buffer_credits++; + handle->h_total_credits++; } return err; @@ -1787,7 +1787,7 @@ int jbd2_journal_stop(handle_t *handle) jiffies - handle->h_start_jiffies, handle->h_sync, handle->h_requested_credits, (handle->h_requested_credits - - handle->h_buffer_credits)); + handle->h_total_credits)); /* * Implement synchronous transaction batching. If the handle diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 2a3d5f50e7a1..3115eeb44039 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -477,7 +477,8 @@ struct jbd2_revoke_table_s; * @h_transaction: Which compound transaction is this update a part of? * @h_journal: Which journal handle belongs to - used iff h_reserved set. * @h_rsv_handle: Handle reserved for finishing the logical operation. - * @h_buffer_credits: Number of remaining buffers we are allowed to dirty. + * @h_total_credits: Number of remaining buffers we are allowed to add to + journal. These are dirty buffers and revoke descriptor blocks. * @h_revoke_credits: Number of remaining revoke records available for handle * @h_ref: Reference count on this handle. * @h_err: Field for caller's use to track errors through large fs operations. @@ -488,7 +489,7 @@ struct jbd2_revoke_table_s; * @h_type: For handle statistics. * @h_line_no: For handle statistics. * @h_start_jiffies: Handle Start time. - * @h_requested_credits: Holds @h_buffer_credits after handle is started. + * @h_requested_credits: Holds @h_total_credits after handle is started. * @h_revoke_credits_requested: Holds @h_revoke_credits after handle is started. * @saved_alloc_context: Saved context while transaction is open. **/ @@ -506,7 +507,7 @@ struct jbd2_journal_handle }; handle_t *h_rsv_handle; - int h_buffer_credits; + int h_total_credits; int h_revoke_credits; int h_revoke_credits_requested; int h_ref; @@ -1652,7 +1653,7 @@ static inline int jbd2_handle_buffer_credits(handle_t *handle) { journal_t *journal = handle->h_transaction->t_journal; - return handle->h_buffer_credits - + return handle->h_total_credits - DIV_ROUND_UP(handle->h_revoke_credits_requested, journal->j_revoke_records_per_block); } -- cgit v1.2.3-71-gd317 From 15122464d525f684a61806d28597050cdcef0f32 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Sat, 2 Nov 2019 01:12:03 +0100 Subject: icmp: add helpers to recognize ICMP error packets Add two helper functions, one for IPv4 and one for IPv6, to recognize the ICMP packets which are error responses. This packets are special because they have as payload the original header of the packet which generated it (RFC 792 says at least 8 bytes, but Linux actually includes much more than that). Signed-off-by: Matteo Croce Signed-off-by: David S. Miller --- include/linux/icmp.h | 15 +++++++++++++++ include/linux/icmpv6.h | 14 ++++++++++++++ 2 files changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/icmp.h b/include/linux/icmp.h index 2d8aaf7d4b9e..81ca84ce3119 100644 --- a/include/linux/icmp.h +++ b/include/linux/icmp.h @@ -20,4 +20,19 @@ static inline struct icmphdr *icmp_hdr(const struct sk_buff *skb) { return (struct icmphdr *)skb_transport_header(skb); } + +static inline bool icmp_is_err(int type) +{ + switch (type) { + case ICMP_DEST_UNREACH: + case ICMP_SOURCE_QUENCH: + case ICMP_REDIRECT: + case ICMP_TIME_EXCEEDED: + case ICMP_PARAMETERPROB: + return true; + } + + return false; +} + #endif /* _LINUX_ICMP_H */ diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index a8f888976137..ef1cbb5f454f 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -46,4 +46,18 @@ extern void icmpv6_flow_init(struct sock *sk, const struct in6_addr *saddr, const struct in6_addr *daddr, int oif); + +static inline bool icmpv6_is_err(int type) +{ + switch (type) { + case ICMPV6_DEST_UNREACH: + case ICMPV6_PKT_TOOBIG: + case ICMPV6_TIME_EXCEED: + case ICMPV6_PARAMPROB: + return true; + } + + return false; +} + #endif -- cgit v1.2.3-71-gd317 From a00351687f8a05773c1c57be80a5bbca68fa9ae8 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Wed, 23 Oct 2019 13:02:19 -0700 Subject: software node: remove DEV_PROP_MAX This definition is not used anywhere, let's remove it. Suggested-by: Andy Shevchenko Reviewed-by: Andy Shevchenko Signed-off-by: Dmitry Torokhov Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index 054661109661..0a075fbde57e 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -22,7 +22,6 @@ enum dev_prop_type { DEV_PROP_U32, DEV_PROP_U64, DEV_PROP_STRING, - DEV_PROP_MAX, }; enum dev_dma_attr { -- cgit v1.2.3-71-gd317 From 1741cfacfa9ba047b3f2244fbe6e865602e70ddb Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Wed, 23 Oct 2019 13:02:20 -0700 Subject: software node: introduce PROPERTY_ENTRY_XXX_ARRAY_LEN() Sometimes we want to initialize property entry array from a regular pointer, when we can't determine length automatically via ARRAY_SIZE. Let's introduce PROPERTY_ENTRY_XXX_ARRAY_LEN macros that take explicit "len" argument. Reviewed-by: Andy Shevchenko Signed-off-by: Dmitry Torokhov Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 45 ++++++++++++++++++++++++++++----------------- 1 file changed, 28 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index 0a075fbde57e..fad2e83a207c 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -261,33 +261,44 @@ struct property_entry { * and structs. */ -#define PROPERTY_ENTRY_INTEGER_ARRAY(_name_, _type_, _Type_, _val_) \ +#define PROPERTY_ENTRY_ARRAY_LEN(_name_, _type_, _Type_, _val_, _len_) \ (struct property_entry) { \ .name = _name_, \ - .length = ARRAY_SIZE(_val_) * sizeof(_type_), \ + .length = (_len_) * sizeof(_type_), \ .is_array = true, \ .type = DEV_PROP_##_Type_, \ { .pointer = { ._type_##_data = _val_ } }, \ } -#define PROPERTY_ENTRY_U8_ARRAY(_name_, _val_) \ - PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u8, U8, _val_) -#define PROPERTY_ENTRY_U16_ARRAY(_name_, _val_) \ - PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u16, U16, _val_) -#define PROPERTY_ENTRY_U32_ARRAY(_name_, _val_) \ - PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u32, U32, _val_) -#define PROPERTY_ENTRY_U64_ARRAY(_name_, _val_) \ - PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u64, U64, _val_) +#define PROPERTY_ENTRY_U8_ARRAY_LEN(_name_, _val_, _len_) \ + PROPERTY_ENTRY_ARRAY_LEN(_name_, u8, U8, _val_, _len_) +#define PROPERTY_ENTRY_U16_ARRAY_LEN(_name_, _val_, _len_) \ + PROPERTY_ENTRY_ARRAY_LEN(_name_, u16, U16, _val_, _len_) +#define PROPERTY_ENTRY_U32_ARRAY_LEN(_name_, _val_, _len_) \ + PROPERTY_ENTRY_ARRAY_LEN(_name_, u32, U32, _val_, _len_) +#define PROPERTY_ENTRY_U64_ARRAY_LEN(_name_, _val_, _len_) \ + PROPERTY_ENTRY_ARRAY_LEN(_name_, u64, U64, _val_, _len_) -#define PROPERTY_ENTRY_STRING_ARRAY(_name_, _val_) \ -(struct property_entry) { \ - .name = _name_, \ - .length = ARRAY_SIZE(_val_) * sizeof(const char *), \ - .is_array = true, \ - .type = DEV_PROP_STRING, \ - { .pointer = { .str = _val_ } }, \ +#define PROPERTY_ENTRY_STRING_ARRAY_LEN(_name_, _val_, _len_) \ +(struct property_entry) { \ + .name = _name_, \ + .length = (_len_) * sizeof(const char *), \ + .is_array = true, \ + .type = DEV_PROP_STRING, \ + { .pointer = { .str = _val_ } }, \ } +#define PROPERTY_ENTRY_U8_ARRAY(_name_, _val_) \ + PROPERTY_ENTRY_U8_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_)) +#define PROPERTY_ENTRY_U16_ARRAY(_name_, _val_) \ + PROPERTY_ENTRY_U16_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_)) +#define PROPERTY_ENTRY_U32_ARRAY(_name_, _val_) \ + PROPERTY_ENTRY_U32_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_)) +#define PROPERTY_ENTRY_U64_ARRAY(_name_, _val_) \ + PROPERTY_ENTRY_U64_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_)) +#define PROPERTY_ENTRY_STRING_ARRAY(_name_, _val_) \ + PROPERTY_ENTRY_STRING_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_)) + #define PROPERTY_ENTRY_INTEGER(_name_, _type_, _Type_, _val_) \ (struct property_entry) { \ .name = _name_, \ -- cgit v1.2.3-71-gd317 From b871160fbc61d8cd43440b3903d402e90e28e321 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Wed, 23 Oct 2019 13:02:22 -0700 Subject: software node: mark internal macros with double underscores Let's mark PROPERTY_ENTRY_* macros that are internal with double leading underscores so users are not tempted to use them. Signed-off-by: Dmitry Torokhov Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index fad2e83a207c..d6019bacd848 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -261,7 +261,7 @@ struct property_entry { * and structs. */ -#define PROPERTY_ENTRY_ARRAY_LEN(_name_, _type_, _Type_, _val_, _len_) \ +#define __PROPERTY_ENTRY_ARRAY_LEN(_name_, _type_, _Type_, _val_, _len_)\ (struct property_entry) { \ .name = _name_, \ .length = (_len_) * sizeof(_type_), \ @@ -271,13 +271,13 @@ struct property_entry { } #define PROPERTY_ENTRY_U8_ARRAY_LEN(_name_, _val_, _len_) \ - PROPERTY_ENTRY_ARRAY_LEN(_name_, u8, U8, _val_, _len_) + __PROPERTY_ENTRY_ARRAY_LEN(_name_, u8, U8, _val_, _len_) #define PROPERTY_ENTRY_U16_ARRAY_LEN(_name_, _val_, _len_) \ - PROPERTY_ENTRY_ARRAY_LEN(_name_, u16, U16, _val_, _len_) + __PROPERTY_ENTRY_ARRAY_LEN(_name_, u16, U16, _val_, _len_) #define PROPERTY_ENTRY_U32_ARRAY_LEN(_name_, _val_, _len_) \ - PROPERTY_ENTRY_ARRAY_LEN(_name_, u32, U32, _val_, _len_) + __PROPERTY_ENTRY_ARRAY_LEN(_name_, u32, U32, _val_, _len_) #define PROPERTY_ENTRY_U64_ARRAY_LEN(_name_, _val_, _len_) \ - PROPERTY_ENTRY_ARRAY_LEN(_name_, u64, U64, _val_, _len_) + __PROPERTY_ENTRY_ARRAY_LEN(_name_, u64, U64, _val_, _len_) #define PROPERTY_ENTRY_STRING_ARRAY_LEN(_name_, _val_, _len_) \ (struct property_entry) { \ @@ -299,7 +299,7 @@ struct property_entry { #define PROPERTY_ENTRY_STRING_ARRAY(_name_, _val_) \ PROPERTY_ENTRY_STRING_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_)) -#define PROPERTY_ENTRY_INTEGER(_name_, _type_, _Type_, _val_) \ +#define __PROPERTY_ENTRY_INTEGER(_name_, _type_, _Type_, _val_) \ (struct property_entry) { \ .name = _name_, \ .length = sizeof(_type_), \ @@ -308,13 +308,13 @@ struct property_entry { } #define PROPERTY_ENTRY_U8(_name_, _val_) \ - PROPERTY_ENTRY_INTEGER(_name_, u8, U8, _val_) + __PROPERTY_ENTRY_INTEGER(_name_, u8, U8, _val_) #define PROPERTY_ENTRY_U16(_name_, _val_) \ - PROPERTY_ENTRY_INTEGER(_name_, u16, U16, _val_) + __PROPERTY_ENTRY_INTEGER(_name_, u16, U16, _val_) #define PROPERTY_ENTRY_U32(_name_, _val_) \ - PROPERTY_ENTRY_INTEGER(_name_, u32, U32, _val_) + __PROPERTY_ENTRY_INTEGER(_name_, u32, U32, _val_) #define PROPERTY_ENTRY_U64(_name_, _val_) \ - PROPERTY_ENTRY_INTEGER(_name_, u64, U64, _val_) + __PROPERTY_ENTRY_INTEGER(_name_, u64, U64, _val_) #define PROPERTY_ENTRY_STRING(_name_, _val_) \ (struct property_entry) { \ -- cgit v1.2.3-71-gd317 From 1f74d70ff21249670eb68c1344e0687aa909861d Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Wed, 23 Oct 2019 13:02:24 -0700 Subject: software node: get rid of property_set_pointer() Instead of explicitly setting values of integer types when copying property entries lets just copy entire value union when processing non-array values. For value arrays we no longer use union of pointers, but rather a single void pointer, which allows us to remove property_set_pointer(). In property_get_pointer() we do not need to handle each data type separately, we can simply return either the pointer or pointer to values union. We are not losing anything from removing typed pointer union because the upper layers do their accesses through void pointers anyway, and we trust the "type" of the property when interpret the data. We rely on users of property entries on using PROPERTY_ENTRY_XXX() macros to properly initialize entries instead of poking in the instances directly. Signed-off-by: Dmitry Torokhov Signed-off-by: Rafael J. Wysocki --- drivers/base/swnode.c | 90 ++++++++++-------------------------------------- include/linux/property.h | 12 ++----- 2 files changed, 22 insertions(+), 80 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c index f41692e0f63b..fd667a73a201 100644 --- a/drivers/base/swnode.c +++ b/drivers/base/swnode.c @@ -103,71 +103,15 @@ property_entry_get(const struct property_entry *prop, const char *name) return NULL; } -static void -property_set_pointer(struct property_entry *prop, const void *pointer) -{ - switch (prop->type) { - case DEV_PROP_U8: - if (prop->is_array) - prop->pointer.u8_data = pointer; - else - prop->value.u8_data = *((u8 *)pointer); - break; - case DEV_PROP_U16: - if (prop->is_array) - prop->pointer.u16_data = pointer; - else - prop->value.u16_data = *((u16 *)pointer); - break; - case DEV_PROP_U32: - if (prop->is_array) - prop->pointer.u32_data = pointer; - else - prop->value.u32_data = *((u32 *)pointer); - break; - case DEV_PROP_U64: - if (prop->is_array) - prop->pointer.u64_data = pointer; - else - prop->value.u64_data = *((u64 *)pointer); - break; - case DEV_PROP_STRING: - if (prop->is_array) - prop->pointer.str = pointer; - else - prop->value.str = pointer; - break; - default: - break; - } -} - static const void *property_get_pointer(const struct property_entry *prop) { - switch (prop->type) { - case DEV_PROP_U8: - if (prop->is_array) - return prop->pointer.u8_data; - return &prop->value.u8_data; - case DEV_PROP_U16: - if (prop->is_array) - return prop->pointer.u16_data; - return &prop->value.u16_data; - case DEV_PROP_U32: - if (prop->is_array) - return prop->pointer.u32_data; - return &prop->value.u32_data; - case DEV_PROP_U64: - if (prop->is_array) - return prop->pointer.u64_data; - return &prop->value.u64_data; - case DEV_PROP_STRING: - if (prop->is_array) - return prop->pointer.str; - return &prop->value.str; - default: + if (!prop->length) return NULL; - } + + if (prop->is_array) + return prop->pointer; + + return &prop->value; } static const void *property_entry_find(const struct property_entry *props, @@ -322,13 +266,15 @@ static int property_entry_read_string_array(const struct property_entry *props, static void property_entry_free_data(const struct property_entry *p) { const void *pointer = property_get_pointer(p); + const char * const *src_str; size_t i, nval; if (p->is_array) { - if (p->type == DEV_PROP_STRING && p->pointer.str) { + if (p->type == DEV_PROP_STRING && p->pointer) { + src_str = p->pointer; nval = p->length / sizeof(const char *); for (i = 0; i < nval; i++) - kfree(p->pointer.str[i]); + kfree(src_str[i]); } kfree(pointer); } else if (p->type == DEV_PROP_STRING) { @@ -341,6 +287,7 @@ static const char * const * property_copy_string_array(const struct property_entry *src) { const char **d; + const char * const *src_str = src->pointer; size_t nval = src->length / sizeof(*d); int i; @@ -349,8 +296,8 @@ property_copy_string_array(const struct property_entry *src) return NULL; for (i = 0; i < nval; i++) { - d[i] = kstrdup(src->pointer.str[i], GFP_KERNEL); - if (!d[i] && src->pointer.str[i]) { + d[i] = kstrdup(src_str[i], GFP_KERNEL); + if (!d[i] && src_str[i]) { while (--i >= 0) kfree(d[i]); kfree(d); @@ -380,20 +327,21 @@ static int property_entry_copy_data(struct property_entry *dst, if (!new) return -ENOMEM; } + + dst->is_array = true; + dst->pointer = new; } else if (src->type == DEV_PROP_STRING) { new = kstrdup(src->value.str, GFP_KERNEL); if (!new && src->value.str) return -ENOMEM; + + dst->value.str = new; } else { - new = pointer; + dst->value = src->value; } dst->length = src->length; - dst->is_array = src->is_array; dst->type = src->type; - - property_set_pointer(dst, new); - dst->name = kstrdup(src->name, GFP_KERNEL); if (!dst->name) goto out_free_data; diff --git a/include/linux/property.h b/include/linux/property.h index d6019bacd848..12eff7cbb395 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -238,13 +238,7 @@ struct property_entry { bool is_array; enum dev_prop_type type; union { - union { - const u8 *u8_data; - const u16 *u16_data; - const u32 *u32_data; - const u64 *u64_data; - const char * const *str; - } pointer; + const void *pointer; union { u8 u8_data; u16 u16_data; @@ -267,7 +261,7 @@ struct property_entry { .length = (_len_) * sizeof(_type_), \ .is_array = true, \ .type = DEV_PROP_##_Type_, \ - { .pointer = { ._type_##_data = _val_ } }, \ + { .pointer = _val_ }, \ } #define PROPERTY_ENTRY_U8_ARRAY_LEN(_name_, _val_, _len_) \ @@ -285,7 +279,7 @@ struct property_entry { .length = (_len_) * sizeof(const char *), \ .is_array = true, \ .type = DEV_PROP_STRING, \ - { .pointer = { .str = _val_ } }, \ + { .pointer = _val_ }, \ } #define PROPERTY_ENTRY_U8_ARRAY(_name_, _val_) \ -- cgit v1.2.3-71-gd317 From daeba9bf62e6d03667915899af48471cdf26fde4 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Wed, 23 Oct 2019 13:02:26 -0700 Subject: software node: unify PROPERTY_ENTRY_XXX macros We can unify string properties initializer macros with integer initializers. Signed-off-by: Dmitry Torokhov Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 64 ++++++++++++++++++++---------------------------- 1 file changed, 27 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index 12eff7cbb395..48335288c2a9 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -250,37 +250,33 @@ struct property_entry { }; /* - * Note: the below four initializers for the anonymous union are carefully + * Note: the below initializers for the anonymous union are carefully * crafted to avoid gcc-4.4.4's problems with initialization of anon unions * and structs. */ -#define __PROPERTY_ENTRY_ARRAY_LEN(_name_, _type_, _Type_, _val_, _len_)\ +#define __PROPERTY_ENTRY_ELEMENT_SIZE(_elem_) \ + sizeof(((struct property_entry *)NULL)->value._elem_) + +#define __PROPERTY_ENTRY_ARRAY_LEN(_name_, _elem_, _Type_, _val_, _len_)\ (struct property_entry) { \ .name = _name_, \ - .length = (_len_) * sizeof(_type_), \ + .length = (_len_) * __PROPERTY_ENTRY_ELEMENT_SIZE(_elem_), \ .is_array = true, \ .type = DEV_PROP_##_Type_, \ { .pointer = _val_ }, \ } #define PROPERTY_ENTRY_U8_ARRAY_LEN(_name_, _val_, _len_) \ - __PROPERTY_ENTRY_ARRAY_LEN(_name_, u8, U8, _val_, _len_) + __PROPERTY_ENTRY_ARRAY_LEN(_name_, u8_data, U8, _val_, _len_) #define PROPERTY_ENTRY_U16_ARRAY_LEN(_name_, _val_, _len_) \ - __PROPERTY_ENTRY_ARRAY_LEN(_name_, u16, U16, _val_, _len_) + __PROPERTY_ENTRY_ARRAY_LEN(_name_, u16_data, U16, _val_, _len_) #define PROPERTY_ENTRY_U32_ARRAY_LEN(_name_, _val_, _len_) \ - __PROPERTY_ENTRY_ARRAY_LEN(_name_, u32, U32, _val_, _len_) + __PROPERTY_ENTRY_ARRAY_LEN(_name_, u32_data, U32, _val_, _len_) #define PROPERTY_ENTRY_U64_ARRAY_LEN(_name_, _val_, _len_) \ - __PROPERTY_ENTRY_ARRAY_LEN(_name_, u64, U64, _val_, _len_) - + __PROPERTY_ENTRY_ARRAY_LEN(_name_, u64_data, U64, _val_, _len_) #define PROPERTY_ENTRY_STRING_ARRAY_LEN(_name_, _val_, _len_) \ -(struct property_entry) { \ - .name = _name_, \ - .length = (_len_) * sizeof(const char *), \ - .is_array = true, \ - .type = DEV_PROP_STRING, \ - { .pointer = _val_ }, \ -} + __PROPERTY_ENTRY_ARRAY_LEN(_name_, str, STRING, _val_, _len_) #define PROPERTY_ENTRY_U8_ARRAY(_name_, _val_) \ PROPERTY_ENTRY_U8_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_)) @@ -293,30 +289,24 @@ struct property_entry { #define PROPERTY_ENTRY_STRING_ARRAY(_name_, _val_) \ PROPERTY_ENTRY_STRING_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_)) -#define __PROPERTY_ENTRY_INTEGER(_name_, _type_, _Type_, _val_) \ -(struct property_entry) { \ - .name = _name_, \ - .length = sizeof(_type_), \ - .type = DEV_PROP_##_Type_, \ - { .value = { ._type_##_data = _val_ } }, \ +#define __PROPERTY_ENTRY_ELEMENT(_name_, _elem_, _Type_, _val_) \ +(struct property_entry) { \ + .name = _name_, \ + .length = __PROPERTY_ENTRY_ELEMENT_SIZE(_elem_), \ + .type = DEV_PROP_##_Type_, \ + { .value = { ._elem_ = _val_ } }, \ } -#define PROPERTY_ENTRY_U8(_name_, _val_) \ - __PROPERTY_ENTRY_INTEGER(_name_, u8, U8, _val_) -#define PROPERTY_ENTRY_U16(_name_, _val_) \ - __PROPERTY_ENTRY_INTEGER(_name_, u16, U16, _val_) -#define PROPERTY_ENTRY_U32(_name_, _val_) \ - __PROPERTY_ENTRY_INTEGER(_name_, u32, U32, _val_) -#define PROPERTY_ENTRY_U64(_name_, _val_) \ - __PROPERTY_ENTRY_INTEGER(_name_, u64, U64, _val_) - -#define PROPERTY_ENTRY_STRING(_name_, _val_) \ -(struct property_entry) { \ - .name = _name_, \ - .length = sizeof(const char *), \ - .type = DEV_PROP_STRING, \ - { .value = { .str = _val_ } }, \ -} +#define PROPERTY_ENTRY_U8(_name_, _val_) \ + __PROPERTY_ENTRY_ELEMENT(_name_, u8_data, U8, _val_) +#define PROPERTY_ENTRY_U16(_name_, _val_) \ + __PROPERTY_ENTRY_ELEMENT(_name_, u16_data, U16, _val_) +#define PROPERTY_ENTRY_U32(_name_, _val_) \ + __PROPERTY_ENTRY_ELEMENT(_name_, u32_data, U32, _val_) +#define PROPERTY_ENTRY_U64(_name_, _val_) \ + __PROPERTY_ENTRY_ELEMENT(_name_, u64_data, U64, _val_) +#define PROPERTY_ENTRY_STRING(_name_, _val_) \ + __PROPERTY_ENTRY_ELEMENT(_name_, str, STRING, _val_) #define PROPERTY_ENTRY_BOOL(_name_) \ (struct property_entry) { \ -- cgit v1.2.3-71-gd317 From ea81bae46032022656d45d4a395f1bf3b96697f0 Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Tue, 1 Oct 2019 10:37:33 +0200 Subject: mm: Remove BUG_ON mmap_sem not held from xxx_trans_huge_lock() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The caller needs to make sure that the vma is not torn down during the lock operation and can also use the i_mmap_rwsem for file-backed vmas. Remove the BUG_ON. We could, as an alternative, add a test that either vma->vm_mm->mmap_sem or vma->vm_file->f_mapping->i_mmap_rwsem are held. Cc: Andrew Morton Cc: Matthew Wilcox Cc: Will Deacon Cc: Peter Zijlstra Cc: Rik van Riel Cc: Minchan Kim Cc: Michal Hocko Cc: Huang Ying Cc: Jérôme Glisse Cc: Kirill A. Shutemov Signed-off-by: Thomas Hellstrom Acked-by: Kirill A. Shutemov --- include/linux/huge_mm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 93d5cf0bc716..0b84e13e88e2 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -216,7 +216,6 @@ static inline int is_swap_pmd(pmd_t pmd) static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { - VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma); if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) return __pmd_trans_huge_lock(pmd, vma); else @@ -225,7 +224,6 @@ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma) { - VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma); if (pud_trans_huge(*pud) || pud_devmap(*pud)) return __pud_trans_huge_lock(pud, vma); else -- cgit v1.2.3-71-gd317 From ecaad8aca20432fa60821282d8ff479629c9f7b9 Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Tue, 1 Oct 2019 11:17:34 +0200 Subject: mm: Add a walk_page_mapping() function to the pagewalk code MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For users that want to travers all page table entries pointing into a region of a struct address_space mapping, introduce a walk_page_mapping() function. The walk_page_mapping() function will be initially be used for dirty- tracking in virtual graphics drivers. Cc: Andrew Morton Cc: Matthew Wilcox Cc: Will Deacon Cc: Peter Zijlstra Cc: Rik van Riel Cc: Minchan Kim Cc: Michal Hocko Cc: Huang Ying Cc: Jérôme Glisse Cc: Kirill A. Shutemov Signed-off-by: Thomas Hellstrom Reviewed-by: Andrew Morton --- include/linux/pagewalk.h | 9 +++++ mm/pagewalk.c | 94 +++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 102 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index bddd9759bab9..6ec82e92c87f 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -24,6 +24,9 @@ struct mm_walk; * "do page table walk over the current vma", returning * a negative value means "abort current page table walk * right now" and returning 1 means "skip the current vma" + * @pre_vma: if set, called before starting walk on a non-null vma. + * @post_vma: if set, called after a walk on a non-null vma, provided + * that @pre_vma and the vma walk succeeded. */ struct mm_walk_ops { int (*pud_entry)(pud_t *pud, unsigned long addr, @@ -39,6 +42,9 @@ struct mm_walk_ops { struct mm_walk *walk); int (*test_walk)(unsigned long addr, unsigned long next, struct mm_walk *walk); + int (*pre_vma)(unsigned long start, unsigned long end, + struct mm_walk *walk); + void (*post_vma)(struct mm_walk *walk); }; /** @@ -62,5 +68,8 @@ int walk_page_range(struct mm_struct *mm, unsigned long start, void *private); int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops, void *private); +int walk_page_mapping(struct address_space *mapping, pgoff_t first_index, + pgoff_t nr, const struct mm_walk_ops *ops, + void *private); #endif /* _LINUX_PAGEWALK_H */ diff --git a/mm/pagewalk.c b/mm/pagewalk.c index c5fa42cab14f..ea0b9e606ad1 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -254,13 +254,23 @@ static int __walk_page_range(unsigned long start, unsigned long end, { int err = 0; struct vm_area_struct *vma = walk->vma; + const struct mm_walk_ops *ops = walk->ops; + + if (vma && ops->pre_vma) { + err = ops->pre_vma(start, end, walk); + if (err) + return err; + } if (vma && is_vm_hugetlb_page(vma)) { - if (walk->ops->hugetlb_entry) + if (ops->hugetlb_entry) err = walk_hugetlb_range(start, end, walk); } else err = walk_pgd_range(start, end, walk); + if (vma && ops->post_vma) + ops->post_vma(walk); + return err; } @@ -291,6 +301,11 @@ static int __walk_page_range(unsigned long start, unsigned long end, * its vm_flags. walk_page_test() and @ops->test_walk() are used for this * purpose. * + * If operations need to be staged before and committed after a vma is walked, + * there are two callbacks, pre_vma() and post_vma(). Note that post_vma(), + * since it is intended to handle commit-type operations, can't return any + * errors. + * * struct mm_walk keeps current values of some common data like vma and pmd, * which are useful for the access from callbacks. If you want to pass some * caller-specific data to callbacks, @private should be helpful. @@ -377,3 +392,80 @@ int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops, return err; return __walk_page_range(vma->vm_start, vma->vm_end, &walk); } + +/** + * walk_page_mapping - walk all memory areas mapped into a struct address_space. + * @mapping: Pointer to the struct address_space + * @first_index: First page offset in the address_space + * @nr: Number of incremental page offsets to cover + * @ops: operation to call during the walk + * @private: private data for callbacks' usage + * + * This function walks all memory areas mapped into a struct address_space. + * The walk is limited to only the given page-size index range, but if + * the index boundaries cross a huge page-table entry, that entry will be + * included. + * + * Also see walk_page_range() for additional information. + * + * Locking: + * This function can't require that the struct mm_struct::mmap_sem is held, + * since @mapping may be mapped by multiple processes. Instead + * @mapping->i_mmap_rwsem must be held. This might have implications in the + * callbacks, and it's up tho the caller to ensure that the + * struct mm_struct::mmap_sem is not needed. + * + * Also this means that a caller can't rely on the struct + * vm_area_struct::vm_flags to be constant across a call, + * except for immutable flags. Callers requiring this shouldn't use + * this function. + * + * Return: 0 on success, negative error code on failure, positive number on + * caller defined premature termination. + */ +int walk_page_mapping(struct address_space *mapping, pgoff_t first_index, + pgoff_t nr, const struct mm_walk_ops *ops, + void *private) +{ + struct mm_walk walk = { + .ops = ops, + .private = private, + }; + struct vm_area_struct *vma; + pgoff_t vba, vea, cba, cea; + unsigned long start_addr, end_addr; + int err = 0; + + lockdep_assert_held(&mapping->i_mmap_rwsem); + vma_interval_tree_foreach(vma, &mapping->i_mmap, first_index, + first_index + nr - 1) { + /* Clip to the vma */ + vba = vma->vm_pgoff; + vea = vba + vma_pages(vma); + cba = first_index; + cba = max(cba, vba); + cea = first_index + nr; + cea = min(cea, vea); + + start_addr = ((cba - vba) << PAGE_SHIFT) + vma->vm_start; + end_addr = ((cea - vba) << PAGE_SHIFT) + vma->vm_start; + if (start_addr >= end_addr) + continue; + + walk.vma = vma; + walk.mm = vma->vm_mm; + + err = walk_page_test(vma->vm_start, vma->vm_end, &walk); + if (err > 0) { + err = 0; + break; + } else if (err < 0) + break; + + err = __walk_page_range(start_addr, end_addr, &walk); + if (err) + break; + } + + return err; +} -- cgit v1.2.3-71-gd317 From c5acad84cf1e33ca1a50984952e1c5b2caa0e13f Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Tue, 19 Mar 2019 13:12:30 +0100 Subject: mm: Add write-protect and clean utilities for address space ranges MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add two utilities to 1) write-protect and 2) clean all ptes pointing into a range of an address space. The utilities are intended to aid in tracking dirty pages (either driver-allocated system memory or pci device memory). The write-protect utility should be used in conjunction with page_mkwrite() and pfn_mkwrite() to trigger write page-faults on page accesses. Typically one would want to use this on sparse accesses into large memory regions. The clean utility should be used to utilize hardware dirtying functionality and avoid the overhead of page-faults, typically on large accesses into small memory regions. Cc: Andrew Morton Cc: Matthew Wilcox Cc: Will Deacon Cc: Peter Zijlstra Cc: Rik van Riel Cc: Minchan Kim Cc: Michal Hocko Cc: Huang Ying Cc: Jérôme Glisse Cc: Kirill A. Shutemov Signed-off-by: Thomas Hellstrom Acked-by: Andrew Morton --- include/linux/mm.h | 13 +- mm/Kconfig | 3 + mm/Makefile | 1 + mm/mapping_dirty_helpers.c | 315 +++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 331 insertions(+), 1 deletion(-) create mode 100644 mm/mapping_dirty_helpers.c (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index cc292273e6ba..4bc93477375e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2637,7 +2637,6 @@ typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data); extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); - #ifdef CONFIG_PAGE_POISONING extern bool page_poisoning_enabled(void); extern void kernel_poison_pages(struct page *page, int numpages, int enable); @@ -2878,5 +2877,17 @@ static inline int pages_identical(struct page *page1, struct page *page2) return !memcmp_pages(page1, page2); } +#ifdef CONFIG_MAPPING_DIRTY_HELPERS +unsigned long clean_record_shared_mapping_range(struct address_space *mapping, + pgoff_t first_index, pgoff_t nr, + pgoff_t bitmap_pgoff, + unsigned long *bitmap, + pgoff_t *start, + pgoff_t *end); + +unsigned long wp_shared_mapping_range(struct address_space *mapping, + pgoff_t first_index, pgoff_t nr); +#endif + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ diff --git a/mm/Kconfig b/mm/Kconfig index a5dae9a7eb51..550f7aceb679 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -736,4 +736,7 @@ config ARCH_HAS_PTE_SPECIAL config ARCH_HAS_HUGEPD bool +config MAPPING_DIRTY_HELPERS + bool + endmenu diff --git a/mm/Makefile b/mm/Makefile index d996846697ef..1937cc251883 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -107,3 +107,4 @@ obj-$(CONFIG_PERCPU_STATS) += percpu-stats.o obj-$(CONFIG_ZONE_DEVICE) += memremap.o obj-$(CONFIG_HMM_MIRROR) += hmm.o obj-$(CONFIG_MEMFD_CREATE) += memfd.o +obj-$(CONFIG_MAPPING_DIRTY_HELPERS) += mapping_dirty_helpers.o diff --git a/mm/mapping_dirty_helpers.c b/mm/mapping_dirty_helpers.c new file mode 100644 index 000000000000..71070dda9643 --- /dev/null +++ b/mm/mapping_dirty_helpers.c @@ -0,0 +1,315 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include + +/** + * struct wp_walk - Private struct for pagetable walk callbacks + * @range: Range for mmu notifiers + * @tlbflush_start: Address of first modified pte + * @tlbflush_end: Address of last modified pte + 1 + * @total: Total number of modified ptes + */ +struct wp_walk { + struct mmu_notifier_range range; + unsigned long tlbflush_start; + unsigned long tlbflush_end; + unsigned long total; +}; + +/** + * wp_pte - Write-protect a pte + * @pte: Pointer to the pte + * @addr: The virtual page address + * @walk: pagetable walk callback argument + * + * The function write-protects a pte and records the range in + * virtual address space of touched ptes for efficient range TLB flushes. + */ +static int wp_pte(pte_t *pte, unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + struct wp_walk *wpwalk = walk->private; + pte_t ptent = *pte; + + if (pte_write(ptent)) { + pte_t old_pte = ptep_modify_prot_start(walk->vma, addr, pte); + + ptent = pte_wrprotect(old_pte); + ptep_modify_prot_commit(walk->vma, addr, pte, old_pte, ptent); + wpwalk->total++; + wpwalk->tlbflush_start = min(wpwalk->tlbflush_start, addr); + wpwalk->tlbflush_end = max(wpwalk->tlbflush_end, + addr + PAGE_SIZE); + } + + return 0; +} + +/** + * struct clean_walk - Private struct for the clean_record_pte function. + * @base: struct wp_walk we derive from + * @bitmap_pgoff: Address_space Page offset of the first bit in @bitmap + * @bitmap: Bitmap with one bit for each page offset in the address_space range + * covered. + * @start: Address_space page offset of first modified pte relative + * to @bitmap_pgoff + * @end: Address_space page offset of last modified pte relative + * to @bitmap_pgoff + */ +struct clean_walk { + struct wp_walk base; + pgoff_t bitmap_pgoff; + unsigned long *bitmap; + pgoff_t start; + pgoff_t end; +}; + +#define to_clean_walk(_wpwalk) container_of(_wpwalk, struct clean_walk, base) + +/** + * clean_record_pte - Clean a pte and record its address space offset in a + * bitmap + * @pte: Pointer to the pte + * @addr: The virtual page address + * @walk: pagetable walk callback argument + * + * The function cleans a pte and records the range in + * virtual address space of touched ptes for efficient TLB flushes. + * It also records dirty ptes in a bitmap representing page offsets + * in the address_space, as well as the first and last of the bits + * touched. + */ +static int clean_record_pte(pte_t *pte, unsigned long addr, + unsigned long end, struct mm_walk *walk) +{ + struct wp_walk *wpwalk = walk->private; + struct clean_walk *cwalk = to_clean_walk(wpwalk); + pte_t ptent = *pte; + + if (pte_dirty(ptent)) { + pgoff_t pgoff = ((addr - walk->vma->vm_start) >> PAGE_SHIFT) + + walk->vma->vm_pgoff - cwalk->bitmap_pgoff; + pte_t old_pte = ptep_modify_prot_start(walk->vma, addr, pte); + + ptent = pte_mkclean(old_pte); + ptep_modify_prot_commit(walk->vma, addr, pte, old_pte, ptent); + + wpwalk->total++; + wpwalk->tlbflush_start = min(wpwalk->tlbflush_start, addr); + wpwalk->tlbflush_end = max(wpwalk->tlbflush_end, + addr + PAGE_SIZE); + + __set_bit(pgoff, cwalk->bitmap); + cwalk->start = min(cwalk->start, pgoff); + cwalk->end = max(cwalk->end, pgoff + 1); + } + + return 0; +} + +/* wp_clean_pmd_entry - The pagewalk pmd callback. */ +static int wp_clean_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + /* Dirty-tracking should be handled on the pte level */ + pmd_t pmdval = pmd_read_atomic(pmd); + + if (pmd_trans_huge(pmdval) || pmd_devmap(pmdval)) + WARN_ON(pmd_write(pmdval) || pmd_dirty(pmdval)); + + return 0; +} + +/* wp_clean_pud_entry - The pagewalk pud callback. */ +static int wp_clean_pud_entry(pud_t *pud, unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + /* Dirty-tracking should be handled on the pte level */ + pud_t pudval = READ_ONCE(*pud); + + if (pud_trans_huge(pudval) || pud_devmap(pudval)) + WARN_ON(pud_write(pudval) || pud_dirty(pudval)); + + return 0; +} + +/* + * wp_clean_pre_vma - The pagewalk pre_vma callback. + * + * The pre_vma callback performs the cache flush, stages the tlb flush + * and calls the necessary mmu notifiers. + */ +static int wp_clean_pre_vma(unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + struct wp_walk *wpwalk = walk->private; + + wpwalk->tlbflush_start = end; + wpwalk->tlbflush_end = start; + + mmu_notifier_range_init(&wpwalk->range, MMU_NOTIFY_PROTECTION_PAGE, 0, + walk->vma, walk->mm, start, end); + mmu_notifier_invalidate_range_start(&wpwalk->range); + flush_cache_range(walk->vma, start, end); + + /* + * We're not using tlb_gather_mmu() since typically + * only a small subrange of PTEs are affected, whereas + * tlb_gather_mmu() records the full range. + */ + inc_tlb_flush_pending(walk->mm); + + return 0; +} + +/* + * wp_clean_post_vma - The pagewalk post_vma callback. + * + * The post_vma callback performs the tlb flush and calls necessary mmu + * notifiers. + */ +static void wp_clean_post_vma(struct mm_walk *walk) +{ + struct wp_walk *wpwalk = walk->private; + + if (mm_tlb_flush_nested(walk->mm)) + flush_tlb_range(walk->vma, wpwalk->range.start, + wpwalk->range.end); + else if (wpwalk->tlbflush_end > wpwalk->tlbflush_start) + flush_tlb_range(walk->vma, wpwalk->tlbflush_start, + wpwalk->tlbflush_end); + + mmu_notifier_invalidate_range_end(&wpwalk->range); + dec_tlb_flush_pending(walk->mm); +} + +/* + * wp_clean_test_walk - The pagewalk test_walk callback. + * + * Won't perform dirty-tracking on COW, read-only or HUGETLB vmas. + */ +static int wp_clean_test_walk(unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + unsigned long vm_flags = READ_ONCE(walk->vma->vm_flags); + + /* Skip non-applicable VMAs */ + if ((vm_flags & (VM_SHARED | VM_MAYWRITE | VM_HUGETLB)) != + (VM_SHARED | VM_MAYWRITE)) + return 1; + + return 0; +} + +static const struct mm_walk_ops clean_walk_ops = { + .pte_entry = clean_record_pte, + .pmd_entry = wp_clean_pmd_entry, + .pud_entry = wp_clean_pud_entry, + .test_walk = wp_clean_test_walk, + .pre_vma = wp_clean_pre_vma, + .post_vma = wp_clean_post_vma +}; + +static const struct mm_walk_ops wp_walk_ops = { + .pte_entry = wp_pte, + .pmd_entry = wp_clean_pmd_entry, + .pud_entry = wp_clean_pud_entry, + .test_walk = wp_clean_test_walk, + .pre_vma = wp_clean_pre_vma, + .post_vma = wp_clean_post_vma +}; + +/** + * wp_shared_mapping_range - Write-protect all ptes in an address space range + * @mapping: The address_space we want to write protect + * @first_index: The first page offset in the range + * @nr: Number of incremental page offsets to cover + * + * Note: This function currently skips transhuge page-table entries, since + * it's intended for dirty-tracking on the PTE level. It will warn on + * encountering transhuge write-enabled entries, though, and can easily be + * extended to handle them as well. + * + * Return: The number of ptes actually write-protected. Note that + * already write-protected ptes are not counted. + */ +unsigned long wp_shared_mapping_range(struct address_space *mapping, + pgoff_t first_index, pgoff_t nr) +{ + struct wp_walk wpwalk = { .total = 0 }; + + i_mmap_lock_read(mapping); + WARN_ON(walk_page_mapping(mapping, first_index, nr, &wp_walk_ops, + &wpwalk)); + i_mmap_unlock_read(mapping); + + return wpwalk.total; +} +EXPORT_SYMBOL_GPL(wp_shared_mapping_range); + +/** + * clean_record_shared_mapping_range - Clean and record all ptes in an + * address space range + * @mapping: The address_space we want to clean + * @first_index: The first page offset in the range + * @nr: Number of incremental page offsets to cover + * @bitmap_pgoff: The page offset of the first bit in @bitmap + * @bitmap: Pointer to a bitmap of at least @nr bits. The bitmap needs to + * cover the whole range @first_index..@first_index + @nr. + * @start: Pointer to number of the first set bit in @bitmap. + * is modified as new bits are set by the function. + * @end: Pointer to the number of the last set bit in @bitmap. + * none set. The value is modified as new bits are set by the function. + * + * Note: When this function returns there is no guarantee that a CPU has + * not already dirtied new ptes. However it will not clean any ptes not + * reported in the bitmap. The guarantees are as follows: + * a) All ptes dirty when the function starts executing will end up recorded + * in the bitmap. + * b) All ptes dirtied after that will either remain dirty, be recorded in the + * bitmap or both. + * + * If a caller needs to make sure all dirty ptes are picked up and none + * additional are added, it first needs to write-protect the address-space + * range and make sure new writers are blocked in page_mkwrite() or + * pfn_mkwrite(). And then after a TLB flush following the write-protection + * pick up all dirty bits. + * + * Note: This function currently skips transhuge page-table entries, since + * it's intended for dirty-tracking on the PTE level. It will warn on + * encountering transhuge dirty entries, though, and can easily be extended + * to handle them as well. + * + * Return: The number of dirty ptes actually cleaned. + */ +unsigned long clean_record_shared_mapping_range(struct address_space *mapping, + pgoff_t first_index, pgoff_t nr, + pgoff_t bitmap_pgoff, + unsigned long *bitmap, + pgoff_t *start, + pgoff_t *end) +{ + bool none_set = (*start >= *end); + struct clean_walk cwalk = { + .base = { .total = 0 }, + .bitmap_pgoff = bitmap_pgoff, + .bitmap = bitmap, + .start = none_set ? nr : *start, + .end = none_set ? 0 : *end, + }; + + i_mmap_lock_read(mapping); + WARN_ON(walk_page_mapping(mapping, first_index, nr, &clean_walk_ops, + &cwalk.base)); + i_mmap_unlock_read(mapping); + + *start = cwalk.start; + *end = cwalk.end; + + return cwalk.base.total; +} +EXPORT_SYMBOL_GPL(clean_record_shared_mapping_range); -- cgit v1.2.3-71-gd317 From 99e98d3fb1008ef7416e16a1fd355cb73a253502 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 4 Nov 2019 12:16:17 +0100 Subject: cpuidle: Consolidate disabled state checks There are two reasons why CPU idle states may be disabled: either because the driver has disabled them or because they have been disabled by user space via sysfs. In the former case, the state's "disabled" flag is set once during the initialization of the driver and it is never cleared later (it is read-only effectively). In the latter case, the "disable" field of the given state's cpuidle_state_usage struct is set and it may be changed via sysfs. Thus checking whether or not an idle state has been disabled involves reading these two flags every time. In order to avoid the additional check of the state's "disabled" flag (which is effectively read-only anyway), use the value of it at the init time to set a (new) flag in the "disable" field of that state's cpuidle_state_usage structure and use the sysfs interface to manipulate another (new) flag in it. This way the state is disabled whenever the "disable" field of its cpuidle_state_usage structure is nonzero, whatever the reason, and it is the only place to look into to check whether or not the state has been disabled. Signed-off-by: Rafael J. Wysocki Acked-by: Daniel Lezcano Acked-by: Peter Zijlstra (Intel) --- drivers/cpuidle/cpuidle-powernv.c | 7 ++---- drivers/cpuidle/cpuidle.c | 24 ++++++++++-------- drivers/cpuidle/governors/ladder.c | 4 +-- drivers/cpuidle/governors/menu.c | 8 +++--- drivers/cpuidle/governors/teo.c | 5 ++-- drivers/cpuidle/sysfs.c | 51 ++++++++++++++++++++++---------------- include/linux/cpuidle.h | 3 +++ 7 files changed, 54 insertions(+), 48 deletions(-) (limited to 'include/linux') diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c index 84b1ebe212b3..1b299e801f74 100644 --- a/drivers/cpuidle/cpuidle-powernv.c +++ b/drivers/cpuidle/cpuidle-powernv.c @@ -56,13 +56,10 @@ static u64 get_snooze_timeout(struct cpuidle_device *dev, return default_snooze_timeout; for (i = index + 1; i < drv->state_count; i++) { - struct cpuidle_state *s = &drv->states[i]; - struct cpuidle_state_usage *su = &dev->states_usage[i]; - - if (s->disabled || su->disable) + if (dev->states_usage[i].disable) continue; - return s->target_residency * tb_ticks_per_usec; + return drv->states[i].target_residency * tb_ticks_per_usec; } return default_snooze_timeout; diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 0895b988fa92..44ae39f2b47a 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -84,12 +84,12 @@ static int find_deepest_state(struct cpuidle_driver *drv, for (i = 1; i < drv->state_count; i++) { struct cpuidle_state *s = &drv->states[i]; - struct cpuidle_state_usage *su = &dev->states_usage[i]; - if (s->disabled || su->disable || s->exit_latency <= latency_req - || s->exit_latency > max_latency - || (s->flags & forbidden_flags) - || (s2idle && !s->enter_s2idle)) + if (dev->states_usage[i].disable || + s->exit_latency <= latency_req || + s->exit_latency > max_latency || + (s->flags & forbidden_flags) || + (s2idle && !s->enter_s2idle)) continue; latency_req = s->exit_latency; @@ -265,8 +265,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, if (diff < drv->states[entered_state].target_residency) { for (i = entered_state - 1; i >= 0; i--) { - if (drv->states[i].disabled || - dev->states_usage[i].disable) + if (dev->states_usage[i].disable) continue; /* Shallower states are enabled, so update. */ @@ -275,8 +274,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, } } else if (diff > delay) { for (i = entered_state + 1; i < drv->state_count; i++) { - if (drv->states[i].disabled || - dev->states_usage[i].disable) + if (dev->states_usage[i].disable) continue; /* @@ -380,7 +378,7 @@ u64 cpuidle_poll_time(struct cpuidle_driver *drv, limit_ns = TICK_NSEC; for (i = 1; i < drv->state_count; i++) { - if (drv->states[i].disabled || dev->states_usage[i].disable) + if (dev->states_usage[i].disable) continue; limit_ns = (u64)drv->states[i].target_residency * NSEC_PER_USEC; @@ -567,12 +565,16 @@ static void __cpuidle_device_init(struct cpuidle_device *dev) */ static int __cpuidle_register_device(struct cpuidle_device *dev) { - int ret; struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); + int i, ret; if (!try_module_get(drv->owner)) return -EINVAL; + for (i = 0; i < drv->state_count; i++) + if (drv->states[i].disabled) + dev->states_usage[i].disable |= CPUIDLE_STATE_DISABLED_BY_DRIVER; + per_cpu(cpuidle_devices, dev->cpu) = dev; list_add(&dev->device_list, &cpuidle_detected_devices); diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c index 428eeb832fe7..b0126b8c32fe 100644 --- a/drivers/cpuidle/governors/ladder.c +++ b/drivers/cpuidle/governors/ladder.c @@ -84,7 +84,6 @@ static int ladder_select_state(struct cpuidle_driver *drv, /* consider promotion */ if (last_idx < drv->state_count - 1 && - !drv->states[last_idx + 1].disabled && !dev->states_usage[last_idx + 1].disable && last_residency > last_state->threshold.promotion_time && drv->states[last_idx + 1].exit_latency <= latency_req) { @@ -98,8 +97,7 @@ static int ladder_select_state(struct cpuidle_driver *drv, /* consider demotion */ if (last_idx > first_idx && - (drv->states[last_idx].disabled || - dev->states_usage[last_idx].disable || + (dev->states_usage[last_idx].disable || drv->states[last_idx].exit_latency > latency_req)) { int i; diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index e5a5d0c8d66b..38b2b72102a8 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -298,7 +298,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, if (unlikely(drv->state_count <= 1 || latency_req == 0) || ((data->next_timer_us < drv->states[1].target_residency || latency_req < drv->states[1].exit_latency) && - !drv->states[0].disabled && !dev->states_usage[0].disable)) { + !dev->states_usage[0].disable)) { /* * In this case state[0] will be used no matter what, so return * it right away and keep the tick running if state[0] is a @@ -349,9 +349,8 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, idx = -1; for (i = 0; i < drv->state_count; i++) { struct cpuidle_state *s = &drv->states[i]; - struct cpuidle_state_usage *su = &dev->states_usage[i]; - if (s->disabled || su->disable) + if (dev->states_usage[i].disable) continue; if (idx == -1) @@ -422,8 +421,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * tick, so try to correct that. */ for (i = idx - 1; i >= 0; i--) { - if (drv->states[i].disabled || - dev->states_usage[i].disable) + if (dev->states_usage[i].disable) continue; idx = i; diff --git a/drivers/cpuidle/governors/teo.c b/drivers/cpuidle/governors/teo.c index b9b9156618e6..702d560eb347 100644 --- a/drivers/cpuidle/governors/teo.c +++ b/drivers/cpuidle/governors/teo.c @@ -212,7 +212,7 @@ static int teo_find_shallower_state(struct cpuidle_driver *drv, int i; for (i = state_idx - 1; i >= 0; i--) { - if (drv->states[i].disabled || dev->states_usage[i].disable) + if (dev->states_usage[i].disable) continue; state_idx = i; @@ -256,9 +256,8 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, for (i = 0; i < drv->state_count; i++) { struct cpuidle_state *s = &drv->states[i]; - struct cpuidle_state_usage *su = &dev->states_usage[i]; - if (s->disabled || su->disable) { + if (dev->states_usage[i].disable) { /* * Ignore disabled states with target residencies beyond * the anticipated idle duration. diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c index 2bb2683b493c..9f3755ac8f87 100644 --- a/drivers/cpuidle/sysfs.c +++ b/drivers/cpuidle/sysfs.c @@ -255,25 +255,6 @@ static ssize_t show_state_##_name(struct cpuidle_state *state, \ return sprintf(buf, "%u\n", state->_name);\ } -#define define_store_state_ull_function(_name) \ -static ssize_t store_state_##_name(struct cpuidle_state *state, \ - struct cpuidle_state_usage *state_usage, \ - const char *buf, size_t size) \ -{ \ - unsigned long long value; \ - int err; \ - if (!capable(CAP_SYS_ADMIN)) \ - return -EPERM; \ - err = kstrtoull(buf, 0, &value); \ - if (err) \ - return err; \ - if (value) \ - state_usage->_name = 1; \ - else \ - state_usage->_name = 0; \ - return size; \ -} - #define define_show_state_ull_function(_name) \ static ssize_t show_state_##_name(struct cpuidle_state *state, \ struct cpuidle_state_usage *state_usage, \ @@ -299,11 +280,39 @@ define_show_state_ull_function(usage) define_show_state_ull_function(time) define_show_state_str_function(name) define_show_state_str_function(desc) -define_show_state_ull_function(disable) -define_store_state_ull_function(disable) define_show_state_ull_function(above) define_show_state_ull_function(below) +static ssize_t show_state_disable(struct cpuidle_state *state, + struct cpuidle_state_usage *state_usage, + char *buf) +{ + return sprintf(buf, "%llu\n", + state_usage->disable & CPUIDLE_STATE_DISABLED_BY_USER); +} + +static ssize_t store_state_disable(struct cpuidle_state *state, + struct cpuidle_state_usage *state_usage, + const char *buf, size_t size) +{ + unsigned int value; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + err = kstrtouint(buf, 0, &value); + if (err) + return err; + + if (value) + state_usage->disable |= CPUIDLE_STATE_DISABLED_BY_USER; + else + state_usage->disable &= ~CPUIDLE_STATE_DISABLED_BY_USER; + + return size; +} + define_one_state_ro(name, show_state_name); define_one_state_ro(desc, show_state_desc); define_one_state_ro(latency, show_state_exit_latency); diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 4b6b5bea8f79..d23a3b1ddcf6 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -29,6 +29,9 @@ struct cpuidle_driver; * CPUIDLE DEVICE INTERFACE * ****************************/ +#define CPUIDLE_STATE_DISABLED_BY_USER BIT(0) +#define CPUIDLE_STATE_DISABLED_BY_DRIVER BIT(1) + struct cpuidle_state_usage { unsigned long long disable; unsigned long long usage; -- cgit v1.2.3-71-gd317 From 634d811c619b0dbe16dc890a53d2c978e9d055d5 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 5 Nov 2019 14:59:02 -0500 Subject: nfsv4: Move NFSPROC4_CLNT_COPY_NOTIFY to end of list We shouldn't insert things into the NFSPROC4_CLNT enums, since that causes the nfsstat array to be reordered. Signed-off-by: Trond Myklebust --- include/linux/nfs4.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 5e7a5261af4e..82d8fb422092 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -537,10 +537,11 @@ enum { NFSPROC4_CLNT_CLONE, NFSPROC4_CLNT_COPY, NFSPROC4_CLNT_OFFLOAD_CANCEL, - NFSPROC4_CLNT_COPY_NOTIFY, NFSPROC4_CLNT_LOOKUPP, NFSPROC4_CLNT_LAYOUTERROR, + + NFSPROC4_CLNT_COPY_NOTIFY, }; /* nfs41 types */ -- cgit v1.2.3-71-gd317 From fbf6c73c5b264c25484fa9f449b5546569fe11f0 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 16 Oct 2019 17:51:10 +0100 Subject: ftrace: add ftrace_init_nop() Architectures may need to perform special initialization of ftrace callsites, and today they do so by special-casing ftrace_make_nop() when the expected branch address is MCOUNT_ADDR. In some cases (e.g. for patchable-function-entry), we don't have an mcount-like symbol and don't want a synthetic MCOUNT_ADDR, but we may need to perform some initialization of callsites. To make it possible to separate initialization from runtime modification, and to handle cases without an mcount-like symbol, this patch adds an optional ftrace_init_nop() function that architectures can implement, which does not pass a branch address. Where an architecture does not provide ftrace_init_nop(), we will fall back to the existing behaviour of calling ftrace_make_nop() with MCOUNT_ADDR. At the same time, ftrace_code_disable() is renamed to ftrace_nop_initialize() to make it clearer that it is intended to intialize a callsite into a disabled state, and is not for disabling a callsite that has been runtime enabled. The kerneldoc description of rec arguments is updated to cover non-mcount callsites. Signed-off-by: Mark Rutland Reviewed-by: Amit Daniel Kachhap Reviewed-by: Ard Biesheuvel Reviewed-by: Miroslav Benes Reviewed-by: Steven Rostedt (VMware) Reviewed-by: Torsten Duwe Tested-by: Amit Daniel Kachhap Tested-by: Sven Schnelle Tested-by: Torsten Duwe Cc: Ingo Molnar --- include/linux/ftrace.h | 35 ++++++++++++++++++++++++++++++++--- kernel/trace/ftrace.c | 6 +++--- 2 files changed, 35 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 8a8cb3c401b2..9867d90d635e 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -499,7 +499,7 @@ static inline int ftrace_disable_ftrace_graph_caller(void) { return 0; } /** * ftrace_make_nop - convert code into nop * @mod: module structure if called by module load initialization - * @rec: the mcount call site record + * @rec: the call site record (e.g. mcount/fentry) * @addr: the address that the call site should be calling * * This is a very sensitive operation and great care needs @@ -520,9 +520,38 @@ static inline int ftrace_disable_ftrace_graph_caller(void) { return 0; } extern int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr); + +/** + * ftrace_init_nop - initialize a nop call site + * @mod: module structure if called by module load initialization + * @rec: the call site record (e.g. mcount/fentry) + * + * This is a very sensitive operation and great care needs + * to be taken by the arch. The operation should carefully + * read the location, check to see if what is read is indeed + * what we expect it to be, and then on success of the compare, + * it should write to the location. + * + * The code segment at @rec->ip should contain the contents created by + * the compiler + * + * Return must be: + * 0 on success + * -EFAULT on error reading the location + * -EINVAL on a failed compare of the contents + * -EPERM on error writing to the location + * Any other value will be considered a failure. + */ +#ifndef ftrace_init_nop +static inline int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) +{ + return ftrace_make_nop(mod, rec, MCOUNT_ADDR); +} +#endif + /** * ftrace_make_call - convert a nop call site into a call to addr - * @rec: the mcount call site record + * @rec: the call site record (e.g. mcount/fentry) * @addr: the address that the call site should call * * This is a very sensitive operation and great care needs @@ -545,7 +574,7 @@ extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr); #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS /** * ftrace_modify_call - convert from one addr to another (no nop) - * @rec: the mcount call site record + * @rec: the call site record (e.g. mcount/fentry) * @old_addr: the address expected to be currently called to * @addr: the address to change to * diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f296d89be757..5259d4dea675 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2494,14 +2494,14 @@ struct dyn_ftrace *ftrace_rec_iter_record(struct ftrace_rec_iter *iter) } static int -ftrace_code_disable(struct module *mod, struct dyn_ftrace *rec) +ftrace_nop_initialize(struct module *mod, struct dyn_ftrace *rec) { int ret; if (unlikely(ftrace_disabled)) return 0; - ret = ftrace_make_nop(mod, rec, MCOUNT_ADDR); + ret = ftrace_init_nop(mod, rec); if (ret) { ftrace_bug_type = FTRACE_BUG_INIT; ftrace_bug(ret, rec); @@ -2943,7 +2943,7 @@ static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs) * to the NOP instructions. */ if (!__is_defined(CC_USING_NOP_MCOUNT) && - !ftrace_code_disable(mod, p)) + !ftrace_nop_initialize(mod, p)) break; update_cnt++; -- cgit v1.2.3-71-gd317 From a1326b17ac03a9012cb3d01e434aacb4d67a416c Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 16 Oct 2019 18:17:11 +0100 Subject: module/ftrace: handle patchable-function-entry When using patchable-function-entry, the compiler will record the callsites into a section named "__patchable_function_entries" rather than "__mcount_loc". Let's abstract this difference behind a new FTRACE_CALLSITE_SECTION, so that architectures don't have to handle this explicitly (e.g. with custom module linker scripts). As parisc currently handles this explicitly, it is fixed up accordingly, with its custom linker script removed. Since FTRACE_CALLSITE_SECTION is only defined when DYNAMIC_FTRACE is selected, the parisc module loading code is updated to only use the definition in that case. When DYNAMIC_FTRACE is not selected, modules shouldn't have this section, so this removes some redundant work in that case. To make sure that this is keep up-to-date for modules and the main kernel, a comment is added to vmlinux.lds.h, with the existing ifdeffery simplified for legibility. I built parisc generic-{32,64}bit_defconfig with DYNAMIC_FTRACE enabled, and verified that the section made it into the .ko files for modules. Signed-off-by: Mark Rutland Acked-by: Helge Deller Acked-by: Steven Rostedt (VMware) Reviewed-by: Ard Biesheuvel Reviewed-by: Torsten Duwe Tested-by: Amit Daniel Kachhap Tested-by: Sven Schnelle Tested-by: Torsten Duwe Cc: Ingo Molnar Cc: James E.J. Bottomley Cc: Jessica Yu Cc: linux-parisc@vger.kernel.org --- arch/parisc/Makefile | 1 - arch/parisc/kernel/module.c | 10 +++++++--- arch/parisc/kernel/module.lds | 7 ------- include/asm-generic/vmlinux.lds.h | 14 +++++++------- include/linux/ftrace.h | 5 +++++ kernel/module.c | 2 +- 6 files changed, 20 insertions(+), 19 deletions(-) delete mode 100644 arch/parisc/kernel/module.lds (limited to 'include/linux') diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile index 36b834f1c933..dca8f2de8cf5 100644 --- a/arch/parisc/Makefile +++ b/arch/parisc/Makefile @@ -60,7 +60,6 @@ KBUILD_CFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY=1 \ -DFTRACE_PATCHABLE_FUNCTION_SIZE=$(NOP_COUNT) CC_FLAGS_FTRACE := -fpatchable-function-entry=$(NOP_COUNT),$(shell echo $$(($(NOP_COUNT)-1))) -KBUILD_LDS_MODULE += $(srctree)/arch/parisc/kernel/module.lds endif OBJCOPY_FLAGS =-O binary -R .note -R .comment -S diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c index ac5f34993b53..1c50093e2ebe 100644 --- a/arch/parisc/kernel/module.c +++ b/arch/parisc/kernel/module.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include #include @@ -862,7 +863,7 @@ int module_finalize(const Elf_Ehdr *hdr, const char *strtab = NULL; const Elf_Shdr *s; char *secstrings; - int err, symindex = -1; + int symindex = -1; Elf_Sym *newptr, *oldptr; Elf_Shdr *symhdr = NULL; #ifdef DEBUG @@ -946,11 +947,13 @@ int module_finalize(const Elf_Ehdr *hdr, /* patch .altinstructions */ apply_alternatives(aseg, aseg + s->sh_size, me->name); +#ifdef CONFIG_DYNAMIC_FTRACE /* For 32 bit kernels we're compiling modules with * -ffunction-sections so we must relocate the addresses in the - *__mcount_loc section. + * ftrace callsite section. */ - if (symindex != -1 && !strcmp(secname, "__mcount_loc")) { + if (symindex != -1 && !strcmp(secname, FTRACE_CALLSITE_SECTION)) { + int err; if (s->sh_type == SHT_REL) err = apply_relocate((Elf_Shdr *)sechdrs, strtab, symindex, @@ -962,6 +965,7 @@ int module_finalize(const Elf_Ehdr *hdr, if (err) return err; } +#endif } return 0; } diff --git a/arch/parisc/kernel/module.lds b/arch/parisc/kernel/module.lds deleted file mode 100644 index 1a9a92aca5c8..000000000000 --- a/arch/parisc/kernel/module.lds +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -SECTIONS { - __mcount_loc : { - *(__patchable_function_entries) - } -} diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index dae64600ccbf..a9c4e4721434 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -110,17 +110,17 @@ #endif #ifdef CONFIG_FTRACE_MCOUNT_RECORD -#ifdef CC_USING_PATCHABLE_FUNCTION_ENTRY -#define MCOUNT_REC() . = ALIGN(8); \ - __start_mcount_loc = .; \ - KEEP(*(__patchable_function_entries)) \ - __stop_mcount_loc = .; -#else +/* + * The ftrace call sites are logged to a section whose name depends on the + * compiler option used. A given kernel image will only use one, AKA + * FTRACE_CALLSITE_SECTION. We capture all of them here to avoid header + * dependencies for FTRACE_CALLSITE_SECTION's definition. + */ #define MCOUNT_REC() . = ALIGN(8); \ __start_mcount_loc = .; \ KEEP(*(__mcount_loc)) \ + KEEP(*(__patchable_function_entries)) \ __stop_mcount_loc = .; -#endif #else #define MCOUNT_REC() #endif diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 9867d90d635e..9141f2263286 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -738,6 +738,11 @@ static inline unsigned long get_lock_parent_ip(void) #ifdef CONFIG_FTRACE_MCOUNT_RECORD extern void ftrace_init(void); +#ifdef CC_USING_PATCHABLE_FUNCTION_ENTRY +#define FTRACE_CALLSITE_SECTION "__patchable_function_entries" +#else +#define FTRACE_CALLSITE_SECTION "__mcount_loc" +#endif #else static inline void ftrace_init(void) { } #endif diff --git a/kernel/module.c b/kernel/module.c index ff2d7359a418..acf7962936c4 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3222,7 +3222,7 @@ static int find_module_sections(struct module *mod, struct load_info *info) #endif #ifdef CONFIG_FTRACE_MCOUNT_RECORD /* sechdrs[0].sh_size is always zero */ - mod->ftrace_callsites = section_objs(info, "__mcount_loc", + mod->ftrace_callsites = section_objs(info, FTRACE_CALLSITE_SECTION, sizeof(*mod->ftrace_callsites), &mod->num_ftrace_callsites); #endif -- cgit v1.2.3-71-gd317 From b103fb7653fff09e7a6fb6ba9398a41584e7ae36 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 24 Oct 2019 14:54:36 -0700 Subject: fscrypt: add support for IV_INO_LBLK_64 policies Inline encryption hardware compliant with the UFS v2.1 standard or with the upcoming version of the eMMC standard has the following properties: (1) Per I/O request, the encryption key is specified by a previously loaded keyslot. There might be only a small number of keyslots. (2) Per I/O request, the starting IV is specified by a 64-bit "data unit number" (DUN). IV bits 64-127 are assumed to be 0. The hardware automatically increments the DUN for each "data unit" of configurable size in the request, e.g. for each filesystem block. Property (1) makes it inefficient to use the traditional fscrypt per-file keys. Property (2) precludes the use of the existing DIRECT_KEY fscrypt policy flag, which needs at least 192 IV bits. Therefore, add a new fscrypt policy flag IV_INO_LBLK_64 which causes the encryption to modified as follows: - The encryption keys are derived from the master key, encryption mode number, and filesystem UUID. - The IVs are chosen as (inode_number << 32) | file_logical_block_num. For filenames encryption, file_logical_block_num is 0. Since the file nonces aren't used in the key derivation, many files may share the same encryption key. This is much more efficient on the target hardware. Including the inode number in the IVs and mixing the filesystem UUID into the keys ensures that data in different files is nevertheless still encrypted differently. Additionally, limiting the inode and block numbers to 32 bits and placing the block number in the low bits maintains compatibility with the 64-bit DUN convention (property (2) above). Since this scheme assumes that inode numbers are stable (which may preclude filesystem shrinking) and that inode and file logical block numbers are at most 32-bit, IV_INO_LBLK_64 will only be allowed on filesystems that meet these constraints. These are acceptable limitations for the cases where this format would actually be used. Note that IV_INO_LBLK_64 is an on-disk format, not an implementation. This patch just adds support for it using the existing filesystem layer encryption. A later patch will add support for inline encryption. Reviewed-by: Paul Crowley Co-developed-by: Satya Tangirala Signed-off-by: Satya Tangirala Signed-off-by: Eric Biggers --- Documentation/filesystems/fscrypt.rst | 63 +++++++++++++++++++++++------------ fs/crypto/crypto.c | 10 ++++-- fs/crypto/fscrypt_private.h | 16 +++++++-- fs/crypto/keyring.c | 6 ++-- fs/crypto/keysetup.c | 45 +++++++++++++++++++------ fs/crypto/policy.c | 41 ++++++++++++++++++++++- include/linux/fscrypt.h | 3 ++ include/uapi/linux/fscrypt.h | 3 +- 8 files changed, 146 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst index 6ec459be3de1..471a511c7508 100644 --- a/Documentation/filesystems/fscrypt.rst +++ b/Documentation/filesystems/fscrypt.rst @@ -256,13 +256,8 @@ alternative master keys or to support rotating master keys. Instead, the master keys may be wrapped in userspace, e.g. as is done by the `fscrypt `_ tool. -Including the inode number in the IVs was considered. However, it was -rejected as it would have prevented ext4 filesystems from being -resized, and by itself still wouldn't have been sufficient to prevent -the same key from being directly reused for both XTS and CTS-CBC. - -DIRECT_KEY and per-mode keys ----------------------------- +DIRECT_KEY policies +------------------- The Adiantum encryption mode (see `Encryption modes and usage`_) is suitable for both contents and filenames encryption, and it accepts @@ -285,6 +280,21 @@ IV. Moreover: key derived using the KDF. Users may use the same master key for other v2 encryption policies. +IV_INO_LBLK_64 policies +----------------------- + +When FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64 is set in the fscrypt policy, +the encryption keys are derived from the master key, encryption mode +number, and filesystem UUID. This normally results in all files +protected by the same master key sharing a single contents encryption +key and a single filenames encryption key. To still encrypt different +files' data differently, inode numbers are included in the IVs. +Consequently, shrinking the filesystem may not be allowed. + +This format is optimized for use with inline encryption hardware +compliant with the UFS or eMMC standards, which support only 64 IV +bits per I/O request and may have only a small number of keyslots. + Key identifiers --------------- @@ -342,10 +352,16 @@ a little endian number, except that: is encrypted with AES-256 where the AES-256 key is the SHA-256 hash of the file's data encryption key. -- In the "direct key" configuration (FSCRYPT_POLICY_FLAG_DIRECT_KEY - set in the fscrypt_policy), the file's nonce is also appended to the - IV. Currently this is only allowed with the Adiantum encryption - mode. +- With `DIRECT_KEY policies`_, the file's nonce is appended to the IV. + Currently this is only allowed with the Adiantum encryption mode. + +- With `IV_INO_LBLK_64 policies`_, the logical block number is limited + to 32 bits and is placed in bits 0-31 of the IV. The inode number + (which is also limited to 32 bits) is placed in bits 32-63. + +Note that because file logical block numbers are included in the IVs, +filesystems must enforce that blocks are never shifted around within +encrypted files, e.g. via "collapse range" or "insert range". Filenames encryption -------------------- @@ -355,10 +371,10 @@ the requirements to retain support for efficient directory lookups and filenames of up to 255 bytes, the same IV is used for every filename in a directory. -However, each encrypted directory still uses a unique key; or -alternatively (for the "direct key" configuration) has the file's -nonce included in the IVs. Thus, IV reuse is limited to within a -single directory. +However, each encrypted directory still uses a unique key, or +alternatively has the file's nonce (for `DIRECT_KEY policies`_) or +inode number (for `IV_INO_LBLK_64 policies`_) included in the IVs. +Thus, IV reuse is limited to within a single directory. With CTS-CBC, the IV reuse means that when the plaintext filenames share a common prefix at least as long as the cipher block size (16 @@ -432,12 +448,15 @@ This structure must be initialized as follows: (1) for ``contents_encryption_mode`` and FSCRYPT_MODE_AES_256_CTS (4) for ``filenames_encryption_mode``. -- ``flags`` must contain a value from ```` which - identifies the amount of NUL-padding to use when encrypting - filenames. If unsure, use FSCRYPT_POLICY_FLAGS_PAD_32 (0x3). - Additionally, if the encryption modes are both - FSCRYPT_MODE_ADIANTUM, this can contain - FSCRYPT_POLICY_FLAG_DIRECT_KEY; see `DIRECT_KEY and per-mode keys`_. +- ``flags`` contains optional flags from ````: + + - FSCRYPT_POLICY_FLAGS_PAD_*: The amount of NUL padding to use when + encrypting filenames. If unsure, use FSCRYPT_POLICY_FLAGS_PAD_32 + (0x3). + - FSCRYPT_POLICY_FLAG_DIRECT_KEY: See `DIRECT_KEY policies`_. + - FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64: See `IV_INO_LBLK_64 + policies`_. This is mutually exclusive with DIRECT_KEY and is not + supported on v1 policies. - For v2 encryption policies, ``__reserved`` must be zeroed. @@ -1090,7 +1109,7 @@ policy structs (see `Setting an encryption policy`_), except that the context structs also contain a nonce. The nonce is randomly generated by the kernel and is used as KDF input or as a tweak to cause different files to be encrypted differently; see `Per-file keys`_ and -`DIRECT_KEY and per-mode keys`_. +`DIRECT_KEY policies`_. Data path changes ----------------- diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c index ced8ad9f2d01..3719efa546c6 100644 --- a/fs/crypto/crypto.c +++ b/fs/crypto/crypto.c @@ -73,11 +73,17 @@ EXPORT_SYMBOL(fscrypt_free_bounce_page); void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num, const struct fscrypt_info *ci) { + u8 flags = fscrypt_policy_flags(&ci->ci_policy); + memset(iv, 0, ci->ci_mode->ivsize); - iv->lblk_num = cpu_to_le64(lblk_num); - if (fscrypt_is_direct_key_policy(&ci->ci_policy)) + if (flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) { + WARN_ON_ONCE((u32)lblk_num != lblk_num); + lblk_num |= (u64)ci->ci_inode->i_ino << 32; + } else if (flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) { memcpy(iv->nonce, ci->ci_nonce, FS_KEY_DERIVATION_NONCE_SIZE); + } + iv->lblk_num = cpu_to_le64(lblk_num); } /* Encrypt or decrypt a single filesystem block of file contents */ diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index d9a3e8614049..130b50e5a011 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -163,6 +163,9 @@ struct fscrypt_info { /* The actual crypto transform used for encryption and decryption */ struct crypto_skcipher *ci_ctfm; + /* True if the key should be freed when this fscrypt_info is freed */ + bool ci_owns_key; + /* * Encryption mode used for this inode. It corresponds to either the * contents or filenames encryption mode, depending on the inode type. @@ -281,7 +284,8 @@ extern int fscrypt_init_hkdf(struct fscrypt_hkdf *hkdf, const u8 *master_key, */ #define HKDF_CONTEXT_KEY_IDENTIFIER 1 #define HKDF_CONTEXT_PER_FILE_KEY 2 -#define HKDF_CONTEXT_PER_MODE_KEY 3 +#define HKDF_CONTEXT_DIRECT_KEY 3 +#define HKDF_CONTEXT_IV_INO_LBLK_64_KEY 4 extern int fscrypt_hkdf_expand(struct fscrypt_hkdf *hkdf, u8 context, const u8 *info, unsigned int infolen, @@ -378,8 +382,14 @@ struct fscrypt_master_key { struct list_head mk_decrypted_inodes; spinlock_t mk_decrypted_inodes_lock; - /* Per-mode tfms for DIRECT_KEY policies, allocated on-demand */ - struct crypto_skcipher *mk_mode_keys[__FSCRYPT_MODE_MAX + 1]; + /* Crypto API transforms for DIRECT_KEY policies, allocated on-demand */ + struct crypto_skcipher *mk_direct_tfms[__FSCRYPT_MODE_MAX + 1]; + + /* + * Crypto API transforms for filesystem-layer implementation of + * IV_INO_LBLK_64 policies, allocated on-demand. + */ + struct crypto_skcipher *mk_iv_ino_lblk_64_tfms[__FSCRYPT_MODE_MAX + 1]; } __randomize_layout; diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c index c34fa7c61b43..040df1f5e1c8 100644 --- a/fs/crypto/keyring.c +++ b/fs/crypto/keyring.c @@ -43,8 +43,10 @@ static void free_master_key(struct fscrypt_master_key *mk) wipe_master_key_secret(&mk->mk_secret); - for (i = 0; i < ARRAY_SIZE(mk->mk_mode_keys); i++) - crypto_free_skcipher(mk->mk_mode_keys[i]); + for (i = 0; i <= __FSCRYPT_MODE_MAX; i++) { + crypto_free_skcipher(mk->mk_direct_tfms[i]); + crypto_free_skcipher(mk->mk_iv_ino_lblk_64_tfms[i]); + } key_put(mk->mk_users); kzfree(mk); diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index 28bc2da9be3c..f577bb6613f9 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -114,40 +114,54 @@ int fscrypt_set_derived_key(struct fscrypt_info *ci, const u8 *derived_key) return PTR_ERR(tfm); ci->ci_ctfm = tfm; + ci->ci_owns_key = true; return 0; } static int setup_per_mode_key(struct fscrypt_info *ci, - struct fscrypt_master_key *mk) + struct fscrypt_master_key *mk, + struct crypto_skcipher **tfms, + u8 hkdf_context, bool include_fs_uuid) { + const struct inode *inode = ci->ci_inode; + const struct super_block *sb = inode->i_sb; struct fscrypt_mode *mode = ci->ci_mode; u8 mode_num = mode - available_modes; struct crypto_skcipher *tfm, *prev_tfm; u8 mode_key[FSCRYPT_MAX_KEY_SIZE]; + u8 hkdf_info[sizeof(mode_num) + sizeof(sb->s_uuid)]; + unsigned int hkdf_infolen = 0; int err; - if (WARN_ON(mode_num >= ARRAY_SIZE(mk->mk_mode_keys))) + if (WARN_ON(mode_num > __FSCRYPT_MODE_MAX)) return -EINVAL; /* pairs with cmpxchg() below */ - tfm = READ_ONCE(mk->mk_mode_keys[mode_num]); + tfm = READ_ONCE(tfms[mode_num]); if (likely(tfm != NULL)) goto done; BUILD_BUG_ON(sizeof(mode_num) != 1); + BUILD_BUG_ON(sizeof(sb->s_uuid) != 16); + BUILD_BUG_ON(sizeof(hkdf_info) != 17); + hkdf_info[hkdf_infolen++] = mode_num; + if (include_fs_uuid) { + memcpy(&hkdf_info[hkdf_infolen], &sb->s_uuid, + sizeof(sb->s_uuid)); + hkdf_infolen += sizeof(sb->s_uuid); + } err = fscrypt_hkdf_expand(&mk->mk_secret.hkdf, - HKDF_CONTEXT_PER_MODE_KEY, - &mode_num, sizeof(mode_num), + hkdf_context, hkdf_info, hkdf_infolen, mode_key, mode->keysize); if (err) return err; - tfm = fscrypt_allocate_skcipher(mode, mode_key, ci->ci_inode); + tfm = fscrypt_allocate_skcipher(mode, mode_key, inode); memzero_explicit(mode_key, mode->keysize); if (IS_ERR(tfm)) return PTR_ERR(tfm); /* pairs with READ_ONCE() above */ - prev_tfm = cmpxchg(&mk->mk_mode_keys[mode_num], NULL, tfm); + prev_tfm = cmpxchg(&tfms[mode_num], NULL, tfm); if (prev_tfm != NULL) { crypto_free_skcipher(tfm); tfm = prev_tfm; @@ -178,7 +192,19 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_info *ci, ci->ci_mode->friendly_name); return -EINVAL; } - return setup_per_mode_key(ci, mk); + return setup_per_mode_key(ci, mk, mk->mk_direct_tfms, + HKDF_CONTEXT_DIRECT_KEY, false); + } else if (ci->ci_policy.v2.flags & + FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) { + /* + * IV_INO_LBLK_64: encryption keys are derived from (master_key, + * mode_num, filesystem_uuid), and inode number is included in + * the IVs. This format is optimized for use with inline + * encryption hardware compliant with the UFS or eMMC standards. + */ + return setup_per_mode_key(ci, mk, mk->mk_iv_ino_lblk_64_tfms, + HKDF_CONTEXT_IV_INO_LBLK_64_KEY, + true); } err = fscrypt_hkdf_expand(&mk->mk_secret.hkdf, @@ -302,8 +328,7 @@ static void put_crypt_info(struct fscrypt_info *ci) if (ci->ci_direct_key) fscrypt_put_direct_key(ci->ci_direct_key); - else if (ci->ci_ctfm != NULL && - !fscrypt_is_direct_key_policy(&ci->ci_policy)) + else if (ci->ci_owns_key) crypto_free_skcipher(ci->ci_ctfm); key = ci->ci_master_key; diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index 4072ba644595..96f528071bed 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -29,6 +29,40 @@ bool fscrypt_policies_equal(const union fscrypt_policy *policy1, return !memcmp(policy1, policy2, fscrypt_policy_size(policy1)); } +static bool supported_iv_ino_lblk_64_policy( + const struct fscrypt_policy_v2 *policy, + const struct inode *inode) +{ + struct super_block *sb = inode->i_sb; + int ino_bits = 64, lblk_bits = 64; + + if (policy->flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) { + fscrypt_warn(inode, + "The DIRECT_KEY and IV_INO_LBLK_64 flags are mutually exclusive"); + return false; + } + /* + * It's unsafe to include inode numbers in the IVs if the filesystem can + * potentially renumber inodes, e.g. via filesystem shrinking. + */ + if (!sb->s_cop->has_stable_inodes || + !sb->s_cop->has_stable_inodes(sb)) { + fscrypt_warn(inode, + "Can't use IV_INO_LBLK_64 policy on filesystem '%s' because it doesn't have stable inode numbers", + sb->s_id); + return false; + } + if (sb->s_cop->get_ino_and_lblk_bits) + sb->s_cop->get_ino_and_lblk_bits(sb, &ino_bits, &lblk_bits); + if (ino_bits > 32 || lblk_bits > 32) { + fscrypt_warn(inode, + "Can't use IV_INO_LBLK_64 policy on filesystem '%s' because it doesn't use 32-bit inode and block numbers", + sb->s_id); + return false; + } + return true; +} + /** * fscrypt_supported_policy - check whether an encryption policy is supported * @@ -55,7 +89,8 @@ bool fscrypt_supported_policy(const union fscrypt_policy *policy_u, return false; } - if (policy->flags & ~FSCRYPT_POLICY_FLAGS_VALID) { + if (policy->flags & ~(FSCRYPT_POLICY_FLAGS_PAD_MASK | + FSCRYPT_POLICY_FLAG_DIRECT_KEY)) { fscrypt_warn(inode, "Unsupported encryption flags (0x%02x)", policy->flags); @@ -83,6 +118,10 @@ bool fscrypt_supported_policy(const union fscrypt_policy *policy_u, return false; } + if ((policy->flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) && + !supported_iv_ino_lblk_64_policy(policy, inode)) + return false; + if (memchr_inv(policy->__reserved, 0, sizeof(policy->__reserved))) { fscrypt_warn(inode, diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 04f5ed628445..1a7bffe78ed5 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -61,6 +61,9 @@ struct fscrypt_operations { bool (*dummy_context)(struct inode *); bool (*empty_dir)(struct inode *); unsigned int max_namelen; + bool (*has_stable_inodes)(struct super_block *sb); + void (*get_ino_and_lblk_bits)(struct super_block *sb, + int *ino_bits_ret, int *lblk_bits_ret); }; static inline bool fscrypt_has_encryption_key(const struct inode *inode) diff --git a/include/uapi/linux/fscrypt.h b/include/uapi/linux/fscrypt.h index 39ccfe9311c3..1beb174ad950 100644 --- a/include/uapi/linux/fscrypt.h +++ b/include/uapi/linux/fscrypt.h @@ -17,7 +17,8 @@ #define FSCRYPT_POLICY_FLAGS_PAD_32 0x03 #define FSCRYPT_POLICY_FLAGS_PAD_MASK 0x03 #define FSCRYPT_POLICY_FLAG_DIRECT_KEY 0x04 -#define FSCRYPT_POLICY_FLAGS_VALID 0x07 +#define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64 0x08 +#define FSCRYPT_POLICY_FLAGS_VALID 0x0F /* Encryption algorithms */ #define FSCRYPT_MODE_AES_256_XTS 1 -- cgit v1.2.3-71-gd317 From 1bb5ec2eec48dcab1d8ae3707e4a388da6a9c9dc Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 6 Nov 2019 12:49:57 -0800 Subject: cgroup: use cgroup->last_bstat instead of cgroup->bstat_pending for consistency cgroup->bstat_pending is used to determine the base stat delta to propagate to the parent. While correct, this is different from how percpu delta is determined for no good reason and the inconsistency makes the code more difficult to understand. This patch makes parent propagation delta calculation use the same method as percpu to global propagation. * cgroup_base_stat_accumulate() is renamed to cgroup_base_stat_add() and cgroup_base_stat_sub() is added. * percpu propagation calculation is updated to use the above helpers. * cgroup->bstat_pending is replaced with cgroup->last_bstat and updated to use the same calculation as percpu propagation. Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 2 +- kernel/cgroup/rstat.c | 46 ++++++++++++++++++++++++--------------------- 2 files changed, 26 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 430e219e3aba..4904b1ebd1ff 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -458,7 +458,7 @@ struct cgroup { struct list_head rstat_css_list; /* cgroup basic resource statistics */ - struct cgroup_base_stat pending_bstat; /* pending from children */ + struct cgroup_base_stat last_bstat; struct cgroup_base_stat bstat; struct prev_cputime prev_cputime; /* for printing out cputime */ diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index ca19b4c8acf5..b48b22d4deb6 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -304,44 +304,48 @@ void __init cgroup_rstat_boot(void) * Functions for cgroup basic resource statistics implemented on top of * rstat. */ -static void cgroup_base_stat_accumulate(struct cgroup_base_stat *dst_bstat, - struct cgroup_base_stat *src_bstat) +static void cgroup_base_stat_add(struct cgroup_base_stat *dst_bstat, + struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime += src_bstat->cputime.utime; dst_bstat->cputime.stime += src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime; } +static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat, + struct cgroup_base_stat *src_bstat) +{ + dst_bstat->cputime.utime -= src_bstat->cputime.utime; + dst_bstat->cputime.stime -= src_bstat->cputime.stime; + dst_bstat->cputime.sum_exec_runtime -= src_bstat->cputime.sum_exec_runtime; +} + static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu) { struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); - struct task_cputime *last_cputime = &rstatc->last_bstat.cputime; - struct task_cputime cputime; - struct cgroup_base_stat delta; + struct cgroup_base_stat cur, delta; unsigned seq; /* fetch the current per-cpu values */ do { seq = __u64_stats_fetch_begin(&rstatc->bsync); - cputime = rstatc->bstat.cputime; + cur.cputime = rstatc->bstat.cputime; } while (__u64_stats_fetch_retry(&rstatc->bsync, seq)); - /* calculate the delta to propgate */ - delta.cputime.utime = cputime.utime - last_cputime->utime; - delta.cputime.stime = cputime.stime - last_cputime->stime; - delta.cputime.sum_exec_runtime = cputime.sum_exec_runtime - - last_cputime->sum_exec_runtime; - *last_cputime = cputime; - - /* transfer the pending stat into delta */ - cgroup_base_stat_accumulate(&delta, &cgrp->pending_bstat); - memset(&cgrp->pending_bstat, 0, sizeof(cgrp->pending_bstat)); - - /* propagate delta into the global stat and the parent's pending */ - cgroup_base_stat_accumulate(&cgrp->bstat, &delta); - if (parent) - cgroup_base_stat_accumulate(&parent->pending_bstat, &delta); + /* propagate percpu delta to global */ + delta = cur; + cgroup_base_stat_sub(&delta, &rstatc->last_bstat); + cgroup_base_stat_add(&cgrp->bstat, &delta); + cgroup_base_stat_add(&rstatc->last_bstat, &delta); + + /* propagate global delta to parent */ + if (parent) { + delta = cgrp->bstat; + cgroup_base_stat_sub(&delta, &cgrp->last_bstat); + cgroup_base_stat_add(&parent->bstat, &delta); + cgroup_base_stat_add(&cgrp->last_bstat, &delta); + } } static struct cgroup_rstat_cpu * -- cgit v1.2.3-71-gd317 From 56144737e67329c9aaed15f942d46a6302e2e3d8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 6 Nov 2019 09:48:04 -0800 Subject: hrtimer: Annotate lockless access to timer->state syzbot reported various data-race caused by hrtimer_is_queued() reading timer->state. A READ_ONCE() is required there to silence the warning. Also add the corresponding WRITE_ONCE() when timer->state is set. In remove_hrtimer() the hrtimer_is_queued() helper is open coded to avoid loading timer->state twice. KCSAN reported these cases: BUG: KCSAN: data-race in __remove_hrtimer / tcp_pacing_check write to 0xffff8880b2a7d388 of 1 bytes by interrupt on cpu 0: __remove_hrtimer+0x52/0x130 kernel/time/hrtimer.c:991 __run_hrtimer kernel/time/hrtimer.c:1496 [inline] __hrtimer_run_queues+0x250/0x600 kernel/time/hrtimer.c:1576 hrtimer_run_softirq+0x10e/0x150 kernel/time/hrtimer.c:1593 __do_softirq+0x115/0x33f kernel/softirq.c:292 run_ksoftirqd+0x46/0x60 kernel/softirq.c:603 smpboot_thread_fn+0x37d/0x4a0 kernel/smpboot.c:165 kthread+0x1d4/0x200 drivers/block/aoe/aoecmd.c:1253 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:352 read to 0xffff8880b2a7d388 of 1 bytes by task 24652 on cpu 1: tcp_pacing_check net/ipv4/tcp_output.c:2235 [inline] tcp_pacing_check+0xba/0x130 net/ipv4/tcp_output.c:2225 tcp_xmit_retransmit_queue+0x32c/0x5a0 net/ipv4/tcp_output.c:3044 tcp_xmit_recovery+0x7c/0x120 net/ipv4/tcp_input.c:3558 tcp_ack+0x17b6/0x3170 net/ipv4/tcp_input.c:3717 tcp_rcv_established+0x37e/0xf50 net/ipv4/tcp_input.c:5696 tcp_v4_do_rcv+0x381/0x4e0 net/ipv4/tcp_ipv4.c:1561 sk_backlog_rcv include/net/sock.h:945 [inline] __release_sock+0x135/0x1e0 net/core/sock.c:2435 release_sock+0x61/0x160 net/core/sock.c:2951 sk_stream_wait_memory+0x3d7/0x7c0 net/core/stream.c:145 tcp_sendmsg_locked+0xb47/0x1f30 net/ipv4/tcp.c:1393 tcp_sendmsg+0x39/0x60 net/ipv4/tcp.c:1434 inet_sendmsg+0x6d/0x90 net/ipv4/af_inet.c:807 sock_sendmsg_nosec net/socket.c:637 [inline] sock_sendmsg+0x9f/0xc0 net/socket.c:657 BUG: KCSAN: data-race in __remove_hrtimer / __tcp_ack_snd_check write to 0xffff8880a3a65588 of 1 bytes by interrupt on cpu 0: __remove_hrtimer+0x52/0x130 kernel/time/hrtimer.c:991 __run_hrtimer kernel/time/hrtimer.c:1496 [inline] __hrtimer_run_queues+0x250/0x600 kernel/time/hrtimer.c:1576 hrtimer_run_softirq+0x10e/0x150 kernel/time/hrtimer.c:1593 __do_softirq+0x115/0x33f kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0xbb/0xe0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0xe6/0x280 arch/x86/kernel/apic/apic.c:1137 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830 read to 0xffff8880a3a65588 of 1 bytes by task 22891 on cpu 1: __tcp_ack_snd_check+0x415/0x4f0 net/ipv4/tcp_input.c:5265 tcp_ack_snd_check net/ipv4/tcp_input.c:5287 [inline] tcp_rcv_established+0x750/0xf50 net/ipv4/tcp_input.c:5708 tcp_v4_do_rcv+0x381/0x4e0 net/ipv4/tcp_ipv4.c:1561 sk_backlog_rcv include/net/sock.h:945 [inline] __release_sock+0x135/0x1e0 net/core/sock.c:2435 release_sock+0x61/0x160 net/core/sock.c:2951 sk_stream_wait_memory+0x3d7/0x7c0 net/core/stream.c:145 tcp_sendmsg_locked+0xb47/0x1f30 net/ipv4/tcp.c:1393 tcp_sendmsg+0x39/0x60 net/ipv4/tcp.c:1434 inet_sendmsg+0x6d/0x90 net/ipv4/af_inet.c:807 sock_sendmsg_nosec net/socket.c:637 [inline] sock_sendmsg+0x9f/0xc0 net/socket.c:657 __sys_sendto+0x21f/0x320 net/socket.c:1952 __do_sys_sendto net/socket.c:1964 [inline] __se_sys_sendto net/socket.c:1960 [inline] __x64_sys_sendto+0x89/0xb0 net/socket.c:1960 do_syscall_64+0xcc/0x370 arch/x86/entry/common.c:290 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 24652 Comm: syz-executor.3 Not tainted 5.4.0-rc3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 [ tglx: Added comments ] Reported-by: syzbot Signed-off-by: Eric Dumazet Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20191106174804.74723-1-edumazet@google.com --- include/linux/hrtimer.h | 14 ++++++++++---- kernel/time/hrtimer.c | 11 +++++++---- 2 files changed, 17 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 1b9a51a1bccb..1f98b52118f0 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -456,12 +456,18 @@ extern u64 hrtimer_next_event_without(const struct hrtimer *exclude); extern bool hrtimer_active(const struct hrtimer *timer); -/* - * Helper function to check, whether the timer is on one of the queues +/** + * hrtimer_is_queued = check, whether the timer is on one of the queues + * @timer: Timer to check + * + * Returns: True if the timer is queued, false otherwise + * + * The function can be used lockless, but it gives only a current snapshot. */ -static inline int hrtimer_is_queued(struct hrtimer *timer) +static inline bool hrtimer_is_queued(struct hrtimer *timer) { - return timer->state & HRTIMER_STATE_ENQUEUED; + /* The READ_ONCE pairs with the update functions of timer->state */ + return !!(READ_ONCE(timer->state) & HRTIMER_STATE_ENQUEUED); } /* diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 65605530ee34..7f31932216a1 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -966,7 +966,8 @@ static int enqueue_hrtimer(struct hrtimer *timer, base->cpu_base->active_bases |= 1 << base->index; - timer->state = HRTIMER_STATE_ENQUEUED; + /* Pairs with the lockless read in hrtimer_is_queued() */ + WRITE_ONCE(timer->state, HRTIMER_STATE_ENQUEUED); return timerqueue_add(&base->active, &timer->node); } @@ -988,7 +989,8 @@ static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_cpu_base *cpu_base = base->cpu_base; u8 state = timer->state; - timer->state = newstate; + /* Pairs with the lockless read in hrtimer_is_queued() */ + WRITE_ONCE(timer->state, newstate); if (!(state & HRTIMER_STATE_ENQUEUED)) return; @@ -1013,8 +1015,9 @@ static void __remove_hrtimer(struct hrtimer *timer, static inline int remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart) { - if (hrtimer_is_queued(timer)) { - u8 state = timer->state; + u8 state = timer->state; + + if (state & HRTIMER_STATE_ENQUEUED) { int reprogram; /* -- cgit v1.2.3-71-gd317 From f96c8e50152814d05a4002b8c03a80366a27afa3 Mon Sep 17 00:00:00 2001 From: Amit Kucheria Date: Mon, 21 Oct 2019 17:45:10 +0530 Subject: thermal: Remove netlink support There are no users of netlink messages for thermal inside the kernel. Remove the code and adjust the documentation. Signed-off-by: Amit Kucheria Acked-by: Viresh Kumar Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/8ff02cf62186c7a54fff325fad40a2e9ca3affa6.1571656014.git.amit.kucheria@linaro.org --- Documentation/driver-api/thermal/sysfs-api.rst | 26 ++----- drivers/thermal/thermal_core.c | 101 +------------------------ include/linux/thermal.h | 11 --- 3 files changed, 7 insertions(+), 131 deletions(-) (limited to 'include/linux') diff --git a/Documentation/driver-api/thermal/sysfs-api.rst b/Documentation/driver-api/thermal/sysfs-api.rst index fab2c9b36d08..b40b1f839148 100644 --- a/Documentation/driver-api/thermal/sysfs-api.rst +++ b/Documentation/driver-api/thermal/sysfs-api.rst @@ -725,24 +725,10 @@ method, the sys I/F structure will be built like this:: |---temp1_input: 37000 |---temp1_crit: 100000 -4. Event Notification +4. Export Symbol APIs ===================== -The framework includes a simple notification mechanism, in the form of a -netlink event. Netlink socket initialization is done during the _init_ -of the framework. Drivers which intend to use the notification mechanism -just need to call thermal_generate_netlink_event() with two arguments viz -(originator, event). The originator is a pointer to struct thermal_zone_device -from where the event has been originated. An integer which represents the -thermal zone device will be used in the message to identify the zone. The -event will be one of:{THERMAL_AUX0, THERMAL_AUX1, THERMAL_CRITICAL, -THERMAL_DEV_FAULT}. Notification can be sent when the current temperature -crosses any of the configured thresholds. - -5. Export Symbol APIs -===================== - -5.1. get_tz_trend +4.1. get_tz_trend ----------------- This function returns the trend of a thermal zone, i.e the rate of change @@ -751,14 +737,14 @@ are supposed to implement the callback. If they don't, the thermal framework calculated the trend by comparing the previous and the current temperature values. -5.2. get_thermal_instance +4.2. get_thermal_instance ------------------------- This function returns the thermal_instance corresponding to a given {thermal_zone, cooling_device, trip_point} combination. Returns NULL if such an instance does not exist. -5.3. thermal_notify_framework +4.3. thermal_notify_framework ----------------------------- This function handles the trip events from sensor drivers. It starts @@ -768,14 +754,14 @@ and does actual throttling for other trip points i.e ACTIVE and PASSIVE. The throttling policy is based on the configured platform data; if no platform data is provided, this uses the step_wise throttling policy. -5.4. thermal_cdev_update +4.4. thermal_cdev_update ------------------------ This function serves as an arbitrator to set the state of a cooling device. It sets the cooling device to the deepest cooling state if possible. -6. thermal_emergency_poweroff +5. thermal_emergency_poweroff ============================= On an event of critical trip temperature crossing. Thermal framework diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index d4481cc8958f..cced0638b686 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -19,8 +19,6 @@ #include #include #include -#include -#include #include #define CREATE_TRACE_POINTS @@ -1464,97 +1462,6 @@ exit: } EXPORT_SYMBOL_GPL(thermal_zone_get_zone_by_name); -#ifdef CONFIG_NET -static const struct genl_multicast_group thermal_event_mcgrps[] = { - { .name = THERMAL_GENL_MCAST_GROUP_NAME, }, -}; - -static struct genl_family thermal_event_genl_family __ro_after_init = { - .module = THIS_MODULE, - .name = THERMAL_GENL_FAMILY_NAME, - .version = THERMAL_GENL_VERSION, - .maxattr = THERMAL_GENL_ATTR_MAX, - .mcgrps = thermal_event_mcgrps, - .n_mcgrps = ARRAY_SIZE(thermal_event_mcgrps), -}; - -int thermal_generate_netlink_event(struct thermal_zone_device *tz, - enum events event) -{ - struct sk_buff *skb; - struct nlattr *attr; - struct thermal_genl_event *thermal_event; - void *msg_header; - int size; - int result; - static unsigned int thermal_event_seqnum; - - if (!tz) - return -EINVAL; - - /* allocate memory */ - size = nla_total_size(sizeof(struct thermal_genl_event)) + - nla_total_size(0); - - skb = genlmsg_new(size, GFP_ATOMIC); - if (!skb) - return -ENOMEM; - - /* add the genetlink message header */ - msg_header = genlmsg_put(skb, 0, thermal_event_seqnum++, - &thermal_event_genl_family, 0, - THERMAL_GENL_CMD_EVENT); - if (!msg_header) { - nlmsg_free(skb); - return -ENOMEM; - } - - /* fill the data */ - attr = nla_reserve(skb, THERMAL_GENL_ATTR_EVENT, - sizeof(struct thermal_genl_event)); - - if (!attr) { - nlmsg_free(skb); - return -EINVAL; - } - - thermal_event = nla_data(attr); - if (!thermal_event) { - nlmsg_free(skb); - return -EINVAL; - } - - memset(thermal_event, 0, sizeof(struct thermal_genl_event)); - - thermal_event->orig = tz->id; - thermal_event->event = event; - - /* send multicast genetlink message */ - genlmsg_end(skb, msg_header); - - result = genlmsg_multicast(&thermal_event_genl_family, skb, 0, - 0, GFP_ATOMIC); - if (result) - dev_err(&tz->device, "Failed to send netlink event:%d", result); - - return result; -} -EXPORT_SYMBOL_GPL(thermal_generate_netlink_event); - -static int __init genetlink_init(void) -{ - return genl_register_family(&thermal_event_genl_family); -} - -static void genetlink_exit(void) -{ - genl_unregister_family(&thermal_event_genl_family); -} -#else /* !CONFIG_NET */ -static inline int genetlink_init(void) { return 0; } -static inline void genetlink_exit(void) {} -#endif /* !CONFIG_NET */ - static int thermal_pm_notify(struct notifier_block *nb, unsigned long mode, void *_unused) { @@ -1607,13 +1514,9 @@ static int __init thermal_init(void) if (result) goto unregister_governors; - result = genetlink_init(); - if (result) - goto unregister_class; - result = of_parse_thermal_zones(); if (result) - goto exit_netlink; + goto unregister_class; result = register_pm_notifier(&thermal_pm_nb); if (result) @@ -1622,8 +1525,6 @@ static int __init thermal_init(void) return 0; -exit_netlink: - genetlink_exit(); unregister_class: class_unregister(&thermal_class); unregister_governors: diff --git a/include/linux/thermal.h b/include/linux/thermal.h index e45659c75920..d9111aebb97d 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -544,15 +544,4 @@ static inline void thermal_notify_framework(struct thermal_zone_device *tz, { } #endif /* CONFIG_THERMAL */ -#if defined(CONFIG_NET) && IS_ENABLED(CONFIG_THERMAL) -extern int thermal_generate_netlink_event(struct thermal_zone_device *tz, - enum events event); -#else -static inline int thermal_generate_netlink_event(struct thermal_zone_device *tz, - enum events event) -{ - return 0; -} -#endif - #endif /* __THERMAL_H__ */ -- cgit v1.2.3-71-gd317 From f5bf3c06730c1bd85a3c064357de433736facc5a Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 30 Oct 2019 10:10:36 +0100 Subject: thermal: cpu_cooling: Remove pointless dependency on CONFIG_OF The option CONFIG_CPU_THERMAL depends on CONFIG_OF in the Kconfig. It it pointless to check if CONFIG_OF is set in the header file as this is always true if CONFIG_CPU_THERMAL is true. Remove it. Signed-off-by: Daniel Lezcano Acked-by: Viresh Kumar Reviewed-by: Amit Kucheria Link: https://lore.kernel.org/r/20191030091038.678-1-daniel.lezcano@linaro.org --- include/linux/cpu_cooling.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index bae54bb7c048..72d1c9c5e538 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -47,7 +47,7 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev) } #endif /* CONFIG_CPU_THERMAL */ -#if defined(CONFIG_THERMAL_OF) && defined(CONFIG_CPU_THERMAL) +#ifdef CONFIG_CPU_THERMAL /** * of_cpufreq_cooling_register - create cpufreq cooling device based on DT. * @policy: cpufreq policy. @@ -60,6 +60,6 @@ of_cpufreq_cooling_register(struct cpufreq_policy *policy) { return NULL; } -#endif /* defined(CONFIG_THERMAL_OF) && defined(CONFIG_CPU_THERMAL) */ +#endif /* CONFIG_CPU_THERMAL */ #endif /* __CPU_COOLING_H__ */ -- cgit v1.2.3-71-gd317 From 0cac7559f1b67aa29879ead6b6b6a856d963905f Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 30 Oct 2019 10:10:37 +0100 Subject: thermal: cpu_cooling: Reorder the header file As the conditions are simplified and unified, it is useless to have different blocks of definitions under the same compiler condition, let's merge the blocks. There is no functional change. Signed-off-by: Daniel Lezcano Acked-by: Viresh Kumar Reviewed-by: Amit Kucheria Link: https://lore.kernel.org/r/20191030091038.678-2-daniel.lezcano@linaro.org --- include/linux/cpu_cooling.h | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index 72d1c9c5e538..b74732535e4b 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -33,6 +33,13 @@ cpufreq_cooling_register(struct cpufreq_policy *policy); */ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev); +/** + * of_cpufreq_cooling_register - create cpufreq cooling device based on DT. + * @policy: cpufreq policy. + */ +struct thermal_cooling_device * +of_cpufreq_cooling_register(struct cpufreq_policy *policy); + #else /* !CONFIG_CPU_THERMAL */ static inline struct thermal_cooling_device * cpufreq_cooling_register(struct cpufreq_policy *policy) @@ -45,16 +52,7 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev) { return; } -#endif /* CONFIG_CPU_THERMAL */ -#ifdef CONFIG_CPU_THERMAL -/** - * of_cpufreq_cooling_register - create cpufreq cooling device based on DT. - * @policy: cpufreq policy. - */ -struct thermal_cooling_device * -of_cpufreq_cooling_register(struct cpufreq_policy *policy); -#else static inline struct thermal_cooling_device * of_cpufreq_cooling_register(struct cpufreq_policy *policy) { -- cgit v1.2.3-71-gd317 From 27a47e422ef3cb09f6a428e2b05eb79079506875 Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Wed, 30 Oct 2019 15:14:49 +0000 Subject: PM / EM: Declare EM data types unconditionally The structs representing capacity states and performance domains of an Energy Model are currently only defined for CONFIG_ENERGY_MODEL=y. That makes it hard for code outside PM_EM to manipulate those structures without a lot of ifdefery or stubbed accessors. So, move the declaration of the two structs outside of the CONFIG_ENERGY_MODEL ifdef. The client code (e.g. EAS or thermal) always checks the return of em_cpu_get() before using it, so the exising code is still safe to use as-is. Reported-by: kbuild test robot Signed-off-by: Quentin Perret Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20191030151451.7961-3-qperret@google.com --- include/linux/energy_model.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 73f8c3cb9588..d249b88a4d5a 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -9,7 +9,6 @@ #include #include -#ifdef CONFIG_ENERGY_MODEL /** * em_cap_state - Capacity state of a performance domain * @frequency: The CPU frequency in KHz, for consistency with CPUFreq @@ -40,6 +39,7 @@ struct em_perf_domain { unsigned long cpus[0]; }; +#ifdef CONFIG_ENERGY_MODEL #define EM_CPU_MAX_POWER 0xFFFF struct em_data_callback { @@ -160,7 +160,6 @@ static inline int em_pd_nr_cap_states(struct em_perf_domain *pd) } #else -struct em_perf_domain {}; struct em_data_callback {}; #define EM_DATA_CB(_active_power_cb) { } -- cgit v1.2.3-71-gd317 From 9208b1e77d6e8e9776f34f46ef4079ecac9c3c25 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Wed, 6 Nov 2019 10:51:47 +0200 Subject: gpio: Add definition for GPIO direction At least for me it is difficult to remember the meaning of GPIO direction values. Define GPIO_LINE_DIRECTION_IN and GPIO_LINE_DIRECTION_OUT so that occasional GPIO contributors would not need to always check the meaning of hard coded values 1 and 0. Signed-off-by: Matti Vaittinen Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 5dd9c982e2cb..cc9ade4552d9 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -22,6 +22,9 @@ enum gpio_lookup_flags; struct gpio_chip; +#define GPIO_LINE_DIRECTION_IN 1 +#define GPIO_LINE_DIRECTION_OUT 0 + /** * struct gpio_irq_chip - GPIO interrupt controller */ -- cgit v1.2.3-71-gd317 From 0d95981438c3bdb53cc99b0fb656d24d7a80e1f3 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Wed, 6 Nov 2019 08:06:13 +0100 Subject: x86: efi/random: Invoke EFI_RNG_PROTOCOL to seed the UEFI RNG table Invoke the EFI_RNG_PROTOCOL protocol in the context of the x86 EFI stub, same as is done on arm/arm64 since commit 568bc4e87033 ("efi/arm*/libstub: Invoke EFI_RNG_PROTOCOL to seed the UEFI RNG table"). Within the stub, a Linux-specific RNG seed UEFI config table will be seeded. The EFI routines in the core kernel will pick that up later, yet still early during boot, to seed the kernel entropy pool. If CONFIG_RANDOM_TRUST_BOOTLOADER, entropy is credited for this seed. Signed-off-by: Dominik Brodowski Signed-off-by: Ard Biesheuvel --- arch/x86/boot/compressed/eboot.c | 3 +++ drivers/firmware/efi/libstub/Makefile | 5 +++-- drivers/firmware/efi/libstub/efistub.h | 2 -- include/linux/efi.h | 2 ++ 4 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 82bc60c8acb2..68945c5700bf 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -782,6 +782,9 @@ efi_main(struct efi_config *c, struct boot_params *boot_params) /* Ask the firmware to clear memory on unclean shutdown */ efi_enable_reset_attack_mitigation(sys_table); + + efi_random_get_seed(sys_table); + efi_retrieve_tpm2_eventlog(sys_table); setup_graphics(boot_params); diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index ee0661ddb25b..c35f893897e1 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -38,7 +38,8 @@ OBJECT_FILES_NON_STANDARD := y # Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. KCOV_INSTRUMENT := n -lib-y := efi-stub-helper.o gop.o secureboot.o tpm.o +lib-y := efi-stub-helper.o gop.o secureboot.o tpm.o \ + random.o # include the stub's generic dependencies from lib/ when building for ARM/arm64 arm-deps-y := fdt_rw.c fdt_ro.c fdt_wip.c fdt.c fdt_empty_tree.c fdt_sw.c @@ -47,7 +48,7 @@ arm-deps-$(CONFIG_ARM64) += sort.c $(obj)/lib-%.o: $(srctree)/lib/%.c FORCE $(call if_changed_rule,cc_o_c) -lib-$(CONFIG_EFI_ARMSTUB) += arm-stub.o fdt.o string.o random.o \ +lib-$(CONFIG_EFI_ARMSTUB) += arm-stub.o fdt.o string.o \ $(patsubst %.c,lib-%.o,$(arm-deps-y)) lib-$(CONFIG_ARM) += arm32-stub.o diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index 7f1556fd867d..05739ae013c8 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -63,8 +63,6 @@ efi_status_t efi_random_alloc(efi_system_table_t *sys_table_arg, efi_status_t check_platform_features(efi_system_table_t *sys_table_arg); -efi_status_t efi_random_get_seed(efi_system_table_t *sys_table_arg); - void *get_efi_config_table(efi_system_table_t *sys_table, efi_guid_t guid); /* Helper macros for the usual case of using simple C variables: */ diff --git a/include/linux/efi.h b/include/linux/efi.h index d87acf62958e..028efa7a9f3b 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1645,6 +1645,8 @@ static inline void efi_enable_reset_attack_mitigation(efi_system_table_t *sys_table_arg) { } #endif +efi_status_t efi_random_get_seed(efi_system_table_t *sys_table_arg); + void efi_retrieve_tpm2_eventlog(efi_system_table_t *sys_table); /* -- cgit v1.2.3-71-gd317 From dd5ddd3c7a8c7ac382a82d15757f0ca3ab2b2dbc Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 24 Oct 2019 16:57:39 +0100 Subject: iommu/io-pgtable-arm: Rename IOMMU_QCOM_SYS_CACHE and improve doc The 'IOMMU_QCOM_SYS_CACHE' IOMMU protection flag is exposed to all users of the IOMMU API. Despite its name, the idea behind it isn't especially tied to Qualcomm implementations and could conceivably be used by other systems. Rename it to 'IOMMU_SYS_CACHE_ONLY' and update the comment to describe a bit better the idea behind it. Cc: Robin Murphy Cc: "Isaac J. Manjarres" Signed-off-by: Will Deacon --- drivers/iommu/io-pgtable-arm.c | 2 +- include/linux/iommu.h | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index cd96442af44b..bdf47f745268 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -455,7 +455,7 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data, else if (prot & IOMMU_CACHE) pte |= (ARM_LPAE_MAIR_ATTR_IDX_CACHE << ARM_LPAE_PTE_ATTRINDX_SHIFT); - else if (prot & IOMMU_QCOM_SYS_CACHE) + else if (prot & IOMMU_SYS_CACHE_ONLY) pte |= (ARM_LPAE_MAIR_ATTR_IDX_INC_OCACHE << ARM_LPAE_PTE_ATTRINDX_SHIFT); } diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 29bac5345563..a86bd21d08a9 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -31,11 +31,11 @@ */ #define IOMMU_PRIV (1 << 5) /* - * Non-coherent masters on few Qualcomm SoCs can use this page protection flag - * to set correct cacheability attributes to use an outer level of cache - - * last level cache, aka system cache. + * Non-coherent masters can use this page protection flag to set cacheable + * memory attributes for only a transparent outer level of cache, also known as + * the last-level or system cache. */ -#define IOMMU_QCOM_SYS_CACHE (1 << 6) +#define IOMMU_SYS_CACHE_ONLY (1 << 6) struct iommu_ops; struct iommu_group; -- cgit v1.2.3-71-gd317 From 99c4f70df3a6446c56ca817c2d0f9c12d85d4e7c Mon Sep 17 00:00:00 2001 From: Stephan Gerhold Date: Wed, 6 Nov 2019 18:31:24 +0100 Subject: regulator: ab8500: Remove AB8505 USB regulator The USB regulator was removed for AB8500 in commit 41a06aa738ad ("regulator: ab8500: Remove USB regulator"). It was then added for AB8505 in commit 547f384f33db ("regulator: ab8500: add support for ab8505"). However, there was never an entry added for it in ab8505_regulator_match. This causes all regulators after it to be initialized with the wrong device tree data, eventually leading to an out-of-bounds array read. Given that it is not used anywhere in the kernel, it seems likely that similar arguments against supporting it exist for AB8505 (it is controlled by hardware). Therefore, simply remove it like for AB8500 instead of adding an entry in ab8505_regulator_match. Fixes: 547f384f33db ("regulator: ab8500: add support for ab8505") Cc: Linus Walleij Signed-off-by: Stephan Gerhold Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20191106173125.14496-1-stephan@gerhold.net Signed-off-by: Mark Brown --- drivers/regulator/ab8500.c | 17 ----------------- include/linux/regulator/ab8500.h | 1 - 2 files changed, 18 deletions(-) (limited to 'include/linux') diff --git a/drivers/regulator/ab8500.c b/drivers/regulator/ab8500.c index efb2f01a9101..f60e1b26c2d2 100644 --- a/drivers/regulator/ab8500.c +++ b/drivers/regulator/ab8500.c @@ -953,23 +953,6 @@ static struct ab8500_regulator_info .update_val_idle = 0x82, .update_val_normal = 0x02, }, - [AB8505_LDO_USB] = { - .desc = { - .name = "LDO-USB", - .ops = &ab8500_regulator_mode_ops, - .type = REGULATOR_VOLTAGE, - .id = AB8505_LDO_USB, - .owner = THIS_MODULE, - .n_voltages = 1, - .volt_table = fixed_3300000_voltage, - }, - .update_bank = 0x03, - .update_reg = 0x82, - .update_mask = 0x03, - .update_val = 0x01, - .update_val_idle = 0x03, - .update_val_normal = 0x01, - }, [AB8505_LDO_AUDIO] = { .desc = { .name = "LDO-AUDIO", diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h index 7cf8f797e13a..505e94a6e3e8 100644 --- a/include/linux/regulator/ab8500.h +++ b/include/linux/regulator/ab8500.h @@ -37,7 +37,6 @@ enum ab8505_regulator_id { AB8505_LDO_AUX6, AB8505_LDO_INTCORE, AB8505_LDO_ADC, - AB8505_LDO_USB, AB8505_LDO_AUDIO, AB8505_LDO_ANAMIC1, AB8505_LDO_ANAMIC2, -- cgit v1.2.3-71-gd317 From 458ea3ad033fc86e291712ce50cbe60c3428cf30 Mon Sep 17 00:00:00 2001 From: Stephan Gerhold Date: Wed, 6 Nov 2019 18:31:25 +0100 Subject: regulator: ab8500: Remove SYSCLKREQ from enum ab8505_regulator_id Those regulators are not actually supported by the AB8500 regulator driver. There is no ab8500_regulator_info for them and no entry in ab8505_regulator_match. As such, they cannot be registered successfully, and looking them up in ab8505_regulator_match causes an out-of-bounds array read. Fixes: 547f384f33db ("regulator: ab8500: add support for ab8505") Cc: Linus Walleij Signed-off-by: Stephan Gerhold Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20191106173125.14496-2-stephan@gerhold.net Signed-off-by: Mark Brown --- include/linux/regulator/ab8500.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h index 505e94a6e3e8..3ab1ddf151a2 100644 --- a/include/linux/regulator/ab8500.h +++ b/include/linux/regulator/ab8500.h @@ -42,8 +42,6 @@ enum ab8505_regulator_id { AB8505_LDO_ANAMIC2, AB8505_LDO_AUX8, AB8505_LDO_ANA, - AB8505_SYSCLKREQ_2, - AB8505_SYSCLKREQ_4, AB8505_NUM_REGULATORS, }; -- cgit v1.2.3-71-gd317 From 6c1b1da58f8c7a697a88ae35afeba196fc7b701e Mon Sep 17 00:00:00 2001 From: Ajay Joshi Date: Sun, 27 Oct 2019 23:05:45 +0900 Subject: block: add zone open, close and finish operations MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Zoned block devices (ZBC and ZAC devices) allow an explicit control over the condition (state) of zones. The operations allowed are: * Open a zone: Transition to open condition to indicate that a zone will actively be written * Close a zone: Transition to closed condition to release the drive resources used for writing to a zone * Finish a zone: Transition an open or closed zone to the full condition to prevent write operations To enable this control for in-kernel zoned block device users, define the new request operations REQ_OP_ZONE_OPEN, REQ_OP_ZONE_CLOSE and REQ_OP_ZONE_FINISH as well as the generic function blkdev_zone_mgmt() for submitting these operations on a range of zones. This results in blkdev_reset_zones() removal and replacement with this new zone magement function. Users of blkdev_reset_zones() (f2fs and dm-zoned) are updated accordingly. Contains contributions from Matias Bjorling, Hans Holmberg, Dmitry Fomichev, Keith Busch, Damien Le Moal and Christoph Hellwig. Reviewed-by: Javier González Reviewed-by: Christoph Hellwig Signed-off-by: Ajay Joshi Signed-off-by: Matias Bjorling Signed-off-by: Hans Holmberg Signed-off-by: Dmitry Fomichev Signed-off-by: Keith Busch Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- block/blk-core.c | 12 +++++++++--- block/blk-zoned.c | 35 +++++++++++++++++++++-------------- drivers/md/dm-zoned-metadata.c | 6 +++--- fs/f2fs/segment.c | 3 ++- include/linux/blk_types.h | 25 +++++++++++++++++++++++++ include/linux/blkdev.h | 5 +++-- 6 files changed, 63 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index ae506ac2dd48..f0d82227a2fc 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -132,6 +132,9 @@ static const char *const blk_op_name[] = { REQ_OP_NAME(SECURE_ERASE), REQ_OP_NAME(ZONE_RESET), REQ_OP_NAME(ZONE_RESET_ALL), + REQ_OP_NAME(ZONE_OPEN), + REQ_OP_NAME(ZONE_CLOSE), + REQ_OP_NAME(ZONE_FINISH), REQ_OP_NAME(WRITE_SAME), REQ_OP_NAME(WRITE_ZEROES), REQ_OP_NAME(SCSI_IN), @@ -849,10 +852,10 @@ static inline int blk_partition_remap(struct bio *bio) goto out; /* - * Zone reset does not include bi_size so bio_sectors() is always 0. - * Include a test for the reset op code and perform the remap if needed. + * Zone management bios do not have a sector count but they do have + * a start sector filled out and need to be remapped. */ - if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET) { + if (bio_sectors(bio) || op_is_zone_mgmt(bio_op(bio))) { if (bio_check_eod(bio, part_nr_sects_read(p))) goto out; bio->bi_iter.bi_sector += p->start_sect; @@ -936,6 +939,9 @@ generic_make_request_checks(struct bio *bio) goto not_supported; break; case REQ_OP_ZONE_RESET: + case REQ_OP_ZONE_OPEN: + case REQ_OP_ZONE_CLOSE: + case REQ_OP_ZONE_FINISH: if (!blk_queue_is_zoned(q)) goto not_supported; break; diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 14785011e798..dab34dc48fb6 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -221,23 +221,27 @@ static inline bool blkdev_allow_reset_all_zones(struct block_device *bdev, } /** - * blkdev_reset_zones - Reset zones write pointer + * blkdev_zone_mgmt - Execute a zone management operation on a range of zones * @bdev: Target block device - * @sector: Start sector of the first zone to reset - * @nr_sectors: Number of sectors, at least the length of one zone + * @op: Operation to be performed on the zones + * @sector: Start sector of the first zone to operate on + * @nr_sectors: Number of sectors, should be at least the length of one zone and + * must be zone size aligned. * @gfp_mask: Memory allocation flags (for bio_alloc) * * Description: - * Reset the write pointer of the zones contained in the range + * Perform the specified operation on the range of zones specified by * @sector..@sector+@nr_sectors. Specifying the entire disk sector range * is valid, but the specified range should not contain conventional zones. + * The operation to execute on each zone can be a zone reset, open, close + * or finish request. */ -int blkdev_reset_zones(struct block_device *bdev, - sector_t sector, sector_t nr_sectors, - gfp_t gfp_mask) +int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op, + sector_t sector, sector_t nr_sectors, + gfp_t gfp_mask) { struct request_queue *q = bdev_get_queue(bdev); - sector_t zone_sectors; + sector_t zone_sectors = blk_queue_zone_sectors(q); sector_t end_sector = sector + nr_sectors; struct bio *bio = NULL; int ret; @@ -248,12 +252,14 @@ int blkdev_reset_zones(struct block_device *bdev, if (bdev_read_only(bdev)) return -EPERM; + if (!op_is_zone_mgmt(op)) + return -EOPNOTSUPP; + if (!nr_sectors || end_sector > bdev->bd_part->nr_sects) /* Out of range */ return -EINVAL; /* Check alignment (handle eventual smaller last zone) */ - zone_sectors = blk_queue_zone_sectors(q); if (sector & (zone_sectors - 1)) return -EINVAL; @@ -269,12 +275,13 @@ int blkdev_reset_zones(struct block_device *bdev, * Special case for the zone reset operation that reset all * zones, this is useful for applications like mkfs. */ - if (blkdev_allow_reset_all_zones(bdev, sector, nr_sectors)) { + if (op == REQ_OP_ZONE_RESET && + blkdev_allow_reset_all_zones(bdev, sector, nr_sectors)) { bio->bi_opf = REQ_OP_ZONE_RESET_ALL; break; } - bio->bi_opf = REQ_OP_ZONE_RESET; + bio->bi_opf = op; bio->bi_iter.bi_sector = sector; sector += zone_sectors; @@ -287,7 +294,7 @@ int blkdev_reset_zones(struct block_device *bdev, return ret; } -EXPORT_SYMBOL_GPL(blkdev_reset_zones); +EXPORT_SYMBOL_GPL(blkdev_zone_mgmt); /* * BLKREPORTZONE ioctl processing. @@ -379,8 +386,8 @@ int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode, if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range))) return -EFAULT; - return blkdev_reset_zones(bdev, zrange.sector, zrange.nr_sectors, - GFP_KERNEL); + return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET, + zrange.sector, zrange.nr_sectors, GFP_KERNEL); } static inline unsigned long *blk_alloc_zone_bitmap(int node, diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c index 595a73110e17..feb4718ce6a6 100644 --- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -1312,9 +1312,9 @@ static int dmz_reset_zone(struct dmz_metadata *zmd, struct dm_zone *zone) if (!dmz_is_empty(zone) || dmz_seq_write_err(zone)) { struct dmz_dev *dev = zmd->dev; - ret = blkdev_reset_zones(dev->bdev, - dmz_start_sect(zmd, zone), - dev->zone_nr_sectors, GFP_NOIO); + ret = blkdev_zone_mgmt(dev->bdev, REQ_OP_ZONE_RESET, + dmz_start_sect(zmd, zone), + dev->zone_nr_sectors, GFP_NOIO); if (ret) { dmz_dev_err(dev, "Reset zone %u failed %d", dmz_id(zmd, zone), ret); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 808709581481..2c997f94a3b2 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1771,7 +1771,8 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi, return -EIO; } trace_f2fs_issue_reset_zone(bdev, blkstart); - return blkdev_reset_zones(bdev, sector, nr_sects, GFP_NOFS); + return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET, + sector, nr_sects, GFP_NOFS); } /* For conventional zones, use regular discard if supported */ diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 1e7eeec16458..23a2fd534817 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -290,6 +290,12 @@ enum req_opf { REQ_OP_ZONE_RESET_ALL = 8, /* write the zero filled sector many times */ REQ_OP_WRITE_ZEROES = 9, + /* Open a zone */ + REQ_OP_ZONE_OPEN = 10, + /* Close a zone */ + REQ_OP_ZONE_CLOSE = 11, + /* Transition a zone to full */ + REQ_OP_ZONE_FINISH = 12, /* SCSI passthrough using struct scsi_request */ REQ_OP_SCSI_IN = 32, @@ -417,6 +423,25 @@ static inline bool op_is_discard(unsigned int op) return (op & REQ_OP_MASK) == REQ_OP_DISCARD; } +/* + * Check if a bio or request operation is a zone management operation, with + * the exception of REQ_OP_ZONE_RESET_ALL which is treated as a special case + * due to its different handling in the block layer and device response in + * case of command failure. + */ +static inline bool op_is_zone_mgmt(enum req_opf op) +{ + switch (op & REQ_OP_MASK) { + case REQ_OP_ZONE_RESET: + case REQ_OP_ZONE_OPEN: + case REQ_OP_ZONE_CLOSE: + case REQ_OP_ZONE_FINISH: + return true; + default: + return false; + } +} + static inline int op_stat_group(unsigned int op) { if (op_is_discard(op)) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d4051acb92a1..9cfafff86f66 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -360,8 +360,9 @@ extern unsigned int blkdev_nr_zones(struct block_device *bdev); extern int blkdev_report_zones(struct block_device *bdev, sector_t sector, struct blk_zone *zones, unsigned int *nr_zones); -extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors, - sector_t nr_sectors, gfp_t gfp_mask); +extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op, + sector_t sectors, sector_t nr_sectors, + gfp_t gfp_mask); extern int blk_revalidate_disk_zones(struct gendisk *disk); extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, -- cgit v1.2.3-71-gd317 From e876df1fe0ad1b191284ee6ed2db7960bd322d00 Mon Sep 17 00:00:00 2001 From: Ajay Joshi Date: Sun, 27 Oct 2019 23:05:46 +0900 Subject: block: add zone open, close and finish ioctl support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce three new ioctl commands BLKOPENZONE, BLKCLOSEZONE and BLKFINISHZONE to allow applications to control the condition of zones on a zoned block device through the execution of the REQ_OP_ZONE_OPEN, REQ_OP_ZONE_CLOSE and REQ_OP_ZONE_FINISH operations. Contains contributions from Matias Bjorling, Hans Holmberg, Dmitry Fomichev, Keith Busch, Damien Le Moal and Christoph Hellwig. Reviewed-by: Javier González Reviewed-by: Christoph Hellwig Signed-off-by: Ajay Joshi Signed-off-by: Matias Bjorling Signed-off-by: Hans Holmberg Signed-off-by: Dmitry Fomichev Signed-off-by: Keith Busch Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- block/blk-zoned.c | 28 +++++++++++++++++++++++----- block/ioctl.c | 5 ++++- include/linux/blkdev.h | 10 +++++----- include/uapi/linux/blkzoned.h | 17 ++++++++++++++--- 4 files changed, 46 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/block/blk-zoned.c b/block/blk-zoned.c index dab34dc48fb6..481eaf7d04d4 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -357,15 +357,16 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, } /* - * BLKRESETZONE ioctl processing. + * BLKRESETZONE, BLKOPENZONE, BLKCLOSEZONE and BLKFINISHZONE ioctl processing. * Called from blkdev_ioctl. */ -int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode, - unsigned int cmd, unsigned long arg) +int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; struct request_queue *q; struct blk_zone_range zrange; + enum req_opf op; if (!argp) return -EINVAL; @@ -386,8 +387,25 @@ int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode, if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range))) return -EFAULT; - return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET, - zrange.sector, zrange.nr_sectors, GFP_KERNEL); + switch (cmd) { + case BLKRESETZONE: + op = REQ_OP_ZONE_RESET; + break; + case BLKOPENZONE: + op = REQ_OP_ZONE_OPEN; + break; + case BLKCLOSEZONE: + op = REQ_OP_ZONE_CLOSE; + break; + case BLKFINISHZONE: + op = REQ_OP_ZONE_FINISH; + break; + default: + return -ENOTTY; + } + + return blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors, + GFP_KERNEL); } static inline unsigned long *blk_alloc_zone_bitmap(int node, diff --git a/block/ioctl.c b/block/ioctl.c index 15a0eb80ada9..8756efb1419e 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -532,7 +532,10 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, case BLKREPORTZONE: return blkdev_report_zones_ioctl(bdev, mode, cmd, arg); case BLKRESETZONE: - return blkdev_reset_zones_ioctl(bdev, mode, cmd, arg); + case BLKOPENZONE: + case BLKCLOSEZONE: + case BLKFINISHZONE: + return blkdev_zone_mgmt_ioctl(bdev, mode, cmd, arg); case BLKGETZONESZ: return put_uint(arg, bdev_zone_sectors(bdev)); case BLKGETNRZONES: diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9cfafff86f66..6a4f7abbdcf7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -367,8 +367,8 @@ extern int blk_revalidate_disk_zones(struct gendisk *disk); extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg); -extern int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode, - unsigned int cmd, unsigned long arg); +extern int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg); #else /* CONFIG_BLK_DEV_ZONED */ @@ -389,9 +389,9 @@ static inline int blkdev_report_zones_ioctl(struct block_device *bdev, return -ENOTTY; } -static inline int blkdev_reset_zones_ioctl(struct block_device *bdev, - fmode_t mode, unsigned int cmd, - unsigned long arg) +static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev, + fmode_t mode, unsigned int cmd, + unsigned long arg) { return -ENOTTY; } diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h index 498eec813494..0cdef67135f0 100644 --- a/include/uapi/linux/blkzoned.h +++ b/include/uapi/linux/blkzoned.h @@ -120,9 +120,11 @@ struct blk_zone_report { }; /** - * struct blk_zone_range - BLKRESETZONE ioctl request - * @sector: starting sector of the first zone to issue reset write pointer - * @nr_sectors: Total number of sectors of 1 or more zones to reset + * struct blk_zone_range - BLKRESETZONE/BLKOPENZONE/ + * BLKCLOSEZONE/BLKFINISHZONE ioctl + * requests + * @sector: Starting sector of the first zone to operate on. + * @nr_sectors: Total number of sectors of all zones to operate on. */ struct blk_zone_range { __u64 sector; @@ -139,10 +141,19 @@ struct blk_zone_range { * sector range. The sector range must be zone aligned. * @BLKGETZONESZ: Get the device zone size in number of 512 B sectors. * @BLKGETNRZONES: Get the total number of zones of the device. + * @BLKOPENZONE: Open the zones in the specified sector range. + * The 512 B sector range must be zone aligned. + * @BLKCLOSEZONE: Close the zones in the specified sector range. + * The 512 B sector range must be zone aligned. + * @BLKFINISHZONE: Mark the zones as full in the specified sector range. + * The 512 B sector range must be zone aligned. */ #define BLKREPORTZONE _IOWR(0x12, 130, struct blk_zone_report) #define BLKRESETZONE _IOW(0x12, 131, struct blk_zone_range) #define BLKGETZONESZ _IOR(0x12, 132, __u32) #define BLKGETNRZONES _IOR(0x12, 133, __u32) +#define BLKOPENZONE _IOW(0x12, 134, struct blk_zone_range) +#define BLKCLOSEZONE _IOW(0x12, 135, struct blk_zone_range) +#define BLKFINISHZONE _IOW(0x12, 136, struct blk_zone_range) #endif /* _UAPI_BLKZONED_H */ -- cgit v1.2.3-71-gd317 From e2854a1054ab171a2c5cad6e9b7f0c580bab409d Mon Sep 17 00:00:00 2001 From: Zhenzhong Duan Date: Mon, 4 Nov 2019 17:09:37 +0800 Subject: moduleparam: fix parameter description mismatch The first parameter of module_param is @name, but @value is used in description. Fix it. Fixes: 546970bc6afc ("param: add kerneldoc to moduleparam.h") Signed-off-by: Zhenzhong Duan Signed-off-by: Jessica Yu --- include/linux/moduleparam.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index 5ba250d9172a..e5c3e23919b8 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -100,11 +100,11 @@ struct kparam_array /** * module_param - typesafe helper for a module/cmdline parameter - * @value: the variable to alter, and exposed parameter name. + * @name: the variable to alter, and exposed parameter name. * @type: the type of the parameter * @perm: visibility in sysfs. * - * @value becomes the module parameter, or (prefixed by KBUILD_MODNAME and a + * @name becomes the module parameter, or (prefixed by KBUILD_MODNAME and a * ".") the kernel commandline parameter. Note that - is changed to _, so * the user can use "foo-bar=1" even for variable "foo_bar". * -- cgit v1.2.3-71-gd317 From fe3e5e65c06edb1c56e64e567f053e243142001f Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 6 Nov 2019 17:43:00 -0800 Subject: efi: Enumerate EFI_MEMORY_SP UEFI 2.8 defines an EFI_MEMORY_SP attribute bit to augment the interpretation of the EFI Memory Types as "reserved for a specific purpose". The intent of this bit is to allow the OS to identify precious or scarce memory resources and optionally manage it separately from EfiConventionalMemory. As defined older OSes that do not know about this attribute are permitted to ignore it and the memory will be handled according to the OS default policy for the given memory type. In other words, this "specific purpose" hint is deliberately weaker than EfiReservedMemoryType in that the system continues to operate if the OS takes no action on the attribute. The risk of taking no action is potentially unwanted / unmovable kernel allocations from the designated resource that prevent the full realization of the "specific purpose". For example, consider a system with a high-bandwidth memory pool. Older kernels are permitted to boot and consume that memory as conventional "System-RAM" newer kernels may arrange for that memory to be set aside (soft reserved) by the system administrator for a dedicated high-bandwidth memory aware application to consume. Specifically, this mechanism allows for the elimination of scenarios where platform firmware tries to game OS policy by lying about ACPI SLIT values, i.e. claiming that a precious memory resource has a high distance to trigger the OS to avoid it by default. This reservation hint allows platform-firmware to instead tell the truth about performance characteristics by indicate to OS memory management to put immovable allocations elsewhere. Implement simple detection of the bit for EFI memory table dumps and save the kernel policy for a follow-on change. Reviewed-by: Ard Biesheuvel Reviewed-by: Dave Hansen Signed-off-by: Dan Williams Acked-by: Thomas Gleixner Signed-off-by: Rafael J. Wysocki --- drivers/firmware/efi/efi.c | 5 +++-- include/linux/efi.h | 1 + 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index e98bbf8e56d9..f8f8e273d809 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -842,15 +842,16 @@ char * __init efi_md_typeattr_format(char *buf, size_t size, if (attr & ~(EFI_MEMORY_UC | EFI_MEMORY_WC | EFI_MEMORY_WT | EFI_MEMORY_WB | EFI_MEMORY_UCE | EFI_MEMORY_RO | EFI_MEMORY_WP | EFI_MEMORY_RP | EFI_MEMORY_XP | - EFI_MEMORY_NV | + EFI_MEMORY_NV | EFI_MEMORY_SP | EFI_MEMORY_RUNTIME | EFI_MEMORY_MORE_RELIABLE)) snprintf(pos, size, "|attr=0x%016llx]", (unsigned long long)attr); else snprintf(pos, size, - "|%3s|%2s|%2s|%2s|%2s|%2s|%2s|%3s|%2s|%2s|%2s|%2s]", + "|%3s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%3s|%2s|%2s|%2s|%2s]", attr & EFI_MEMORY_RUNTIME ? "RUN" : "", attr & EFI_MEMORY_MORE_RELIABLE ? "MR" : "", + attr & EFI_MEMORY_SP ? "SP" : "", attr & EFI_MEMORY_NV ? "NV" : "", attr & EFI_MEMORY_XP ? "XP" : "", attr & EFI_MEMORY_RP ? "RP" : "", diff --git a/include/linux/efi.h b/include/linux/efi.h index d87acf62958e..78c75992b313 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -112,6 +112,7 @@ typedef struct { #define EFI_MEMORY_MORE_RELIABLE \ ((u64)0x0000000000010000ULL) /* higher reliability */ #define EFI_MEMORY_RO ((u64)0x0000000000020000ULL) /* read-only */ +#define EFI_MEMORY_SP ((u64)0x0000000000040000ULL) /* soft reserved */ #define EFI_MEMORY_RUNTIME ((u64)0x8000000000000000ULL) /* range requires runtime mapping */ #define EFI_MEMORY_DESCRIPTOR_VERSION 1 -- cgit v1.2.3-71-gd317 From 6950e31b35fdf4588cbbdec1813091bb02cf8871 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 6 Nov 2019 17:43:05 -0800 Subject: x86/efi: Push EFI_MEMMAP check into leaf routines In preparation for adding another EFI_MEMMAP dependent call that needs to occur before e820__memblock_setup() fixup the existing efi calls to check for EFI_MEMMAP internally. This ends up being cleaner than the alternative of checking EFI_MEMMAP multiple times in setup_arch(). Reviewed-by: Dave Hansen Reviewed-by: Ard Biesheuvel Signed-off-by: Dan Williams Acked-by: Thomas Gleixner Signed-off-by: Rafael J. Wysocki --- arch/x86/include/asm/efi.h | 9 ++++++++- arch/x86/kernel/setup.c | 18 ++++++++---------- arch/x86/platform/efi/efi.c | 3 +++ arch/x86/platform/efi/quirks.c | 3 +++ drivers/firmware/efi/esrt.c | 3 +++ drivers/firmware/efi/fake_mem.c | 2 +- include/linux/efi.h | 1 - 7 files changed, 26 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 43a82e59c59d..45f853bce869 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -140,7 +140,6 @@ extern void efi_delete_dummy_variable(void); extern void efi_switch_mm(struct mm_struct *mm); extern void efi_recover_from_page_fault(unsigned long phys_addr); extern void efi_free_boot_services(void); -extern void efi_reserve_boot_services(void); struct efi_setup_data { u64 fw_vendor; @@ -244,6 +243,8 @@ static inline bool efi_is_64bit(void) extern bool efi_reboot_required(void); extern bool efi_is_table_address(unsigned long phys_addr); +extern void efi_find_mirror(void); +extern void efi_reserve_boot_services(void); #else static inline void parse_efi_setup(u64 phys_addr, u32 data_len) {} static inline bool efi_reboot_required(void) @@ -254,6 +255,12 @@ static inline bool efi_is_table_address(unsigned long phys_addr) { return false; } +static inline void efi_find_mirror(void) +{ +} +static inline void efi_reserve_boot_services(void) +{ +} #endif /* CONFIG_EFI */ #endif /* _ASM_X86_EFI_H */ diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 77ea96b794bd..1c4b866bc184 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1122,17 +1122,15 @@ void __init setup_arch(char **cmdline_p) reserve_bios_regions(); - if (efi_enabled(EFI_MEMMAP)) { - efi_fake_memmap(); - efi_find_mirror(); - efi_esrt_init(); + efi_fake_memmap(); + efi_find_mirror(); + efi_esrt_init(); - /* - * The EFI specification says that boot service code won't be - * called after ExitBootServices(). This is, in fact, a lie. - */ - efi_reserve_boot_services(); - } + /* + * The EFI specification says that boot service code won't be + * called after ExitBootServices(). This is, in fact, a lie. + */ + efi_reserve_boot_services(); /* preallocate 4k for mptable mpc */ e820__memblock_alloc_reserved_mpc_new(); diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 425e025341db..e6e41b118d68 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -128,6 +128,9 @@ void __init efi_find_mirror(void) efi_memory_desc_t *md; u64 mirror_size = 0, total_size = 0; + if (!efi_enabled(EFI_MEMMAP)) + return; + for_each_efi_memory_desc(md) { unsigned long long start = md->phys_addr; unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 3b9fd679cea9..7675cf754d90 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -320,6 +320,9 @@ void __init efi_reserve_boot_services(void) { efi_memory_desc_t *md; + if (!efi_enabled(EFI_MEMMAP)) + return; + for_each_efi_memory_desc(md) { u64 start = md->phys_addr; u64 size = md->num_pages << EFI_PAGE_SHIFT; diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c index d6dd5f503fa2..2762e0662bf4 100644 --- a/drivers/firmware/efi/esrt.c +++ b/drivers/firmware/efi/esrt.c @@ -246,6 +246,9 @@ void __init efi_esrt_init(void) int rc; phys_addr_t end; + if (!efi_enabled(EFI_MEMMAP)) + return; + pr_debug("esrt-init: loading.\n"); if (!esrt_table_exists()) return; diff --git a/drivers/firmware/efi/fake_mem.c b/drivers/firmware/efi/fake_mem.c index 9501edc0fcfb..526b45331d96 100644 --- a/drivers/firmware/efi/fake_mem.c +++ b/drivers/firmware/efi/fake_mem.c @@ -44,7 +44,7 @@ void __init efi_fake_memmap(void) void *new_memmap; int i; - if (!nr_fake_mem) + if (!efi_enabled(EFI_MEMMAP) || !nr_fake_mem) return; /* count up the number of EFI memory descriptor */ diff --git a/include/linux/efi.h b/include/linux/efi.h index 78c75992b313..44c85b559e15 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1045,7 +1045,6 @@ extern void efi_enter_virtual_mode (void); /* switch EFI to virtual mode, if pos extern efi_status_t efi_query_variable_store(u32 attributes, unsigned long size, bool nonblocking); -extern void efi_find_mirror(void); #else static inline efi_status_t efi_query_variable_store(u32 attributes, -- cgit v1.2.3-71-gd317 From b617c5266eedbef2ccbb90931bb9175faa4ae0bc Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 6 Nov 2019 17:43:11 -0800 Subject: efi: Common enable/disable infrastructure for EFI soft reservation UEFI 2.8 defines an EFI_MEMORY_SP attribute bit to augment the interpretation of the EFI Memory Types as "reserved for a specific purpose". The proposed Linux behavior for specific purpose memory is that it is reserved for direct-access (device-dax) by default and not available for any kernel usage, not even as an OOM fallback. Later, through udev scripts or another init mechanism, these device-dax claimed ranges can be reconfigured and hot-added to the available System-RAM with a unique node identifier. This device-dax management scheme implements "soft" in the "soft reserved" designation by allowing some or all of the reservation to be recovered as typical memory. This policy can be disabled at compile-time with CONFIG_EFI_SOFT_RESERVE=n, or runtime with efi=nosoftreserve. As for this patch, define the common helpers to determine if the EFI_MEMORY_SP attribute should be honored. The determination needs to be made early to prevent the kernel from being loaded into soft-reserved memory, or otherwise allowing early allocations to land there. Follow-on changes are needed per architecture to leverage these helpers in their respective mem-init paths. Reviewed-by: Ard Biesheuvel Signed-off-by: Dan Williams Acked-by: Thomas Gleixner Signed-off-by: Rafael J. Wysocki --- Documentation/admin-guide/kernel-parameters.txt | 9 ++++++++- drivers/firmware/efi/Kconfig | 21 +++++++++++++++++++++ drivers/firmware/efi/efi.c | 8 ++++++++ drivers/firmware/efi/libstub/efi-stub-helper.c | 19 +++++++++++++++++++ include/linux/efi.h | 14 ++++++++++++++ 5 files changed, 70 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index a84a83f8881e..2359dc56d82c 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1168,7 +1168,8 @@ Format: {"off" | "on" | "skip[mbr]"} efi= [EFI] - Format: { "old_map", "nochunk", "noruntime", "debug" } + Format: { "old_map", "nochunk", "noruntime", "debug", + "nosoftreserve" } old_map [X86-64]: switch to the old ioremap-based EFI runtime services mapping. 32-bit still uses this one by default. @@ -1177,6 +1178,12 @@ firmware implementations. noruntime : disable EFI runtime services support debug: enable misc debug output + nosoftreserve: The EFI_MEMORY_SP (Specific Purpose) + attribute may cause the kernel to reserve the + memory range for a memory mapping driver to + claim. Specify efi=nosoftreserve to disable this + reservation and treat the memory by its base type + (i.e. EFI_CONVENTIONAL_MEMORY / "System RAM"). efi_no_storage_paranoia [EFI; X86] Using this parameter you can use more than 50% of diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig index b248870a9806..bcc378c19ebe 100644 --- a/drivers/firmware/efi/Kconfig +++ b/drivers/firmware/efi/Kconfig @@ -75,6 +75,27 @@ config EFI_MAX_FAKE_MEM Ranges can be set up to this value using comma-separated list. The default value is 8. +config EFI_SOFT_RESERVE + bool "Reserve EFI Specific Purpose Memory" + depends on EFI && EFI_STUB && ACPI_HMAT + default ACPI_HMAT + help + On systems that have mixed performance classes of memory EFI + may indicate specific purpose memory with an attribute (See + EFI_MEMORY_SP in UEFI 2.8). A memory range tagged with this + attribute may have unique performance characteristics compared + to the system's general purpose "System RAM" pool. On the + expectation that such memory has application specific usage, + and its base EFI memory type is "conventional" answer Y to + arrange for the kernel to reserve it as a "Soft Reserved" + resource, and set aside for direct-access (device-dax) by + default. The memory range can later be optionally assigned to + the page allocator by system administrator policy via the + device-dax kmem facility. Say N to have the kernel treat this + memory as "System RAM" by default. + + If unsure, say Y. + config EFI_PARAMS_FROM_FDT bool help diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index f8f8e273d809..e1cb915b45c6 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -81,6 +81,11 @@ bool efi_runtime_disabled(void) return disable_runtime; } +bool __pure __efi_soft_reserve_enabled(void) +{ + return !efi_enabled(EFI_MEM_NO_SOFT_RESERVE); +} + static int __init parse_efi_cmdline(char *str) { if (!str) { @@ -94,6 +99,9 @@ static int __init parse_efi_cmdline(char *str) if (parse_option_str(str, "noruntime")) disable_runtime = true; + if (parse_option_str(str, "nosoftreserve")) + set_bit(EFI_MEM_NO_SOFT_RESERVE, &efi.flags); + return 0; } early_param("efi", parse_efi_cmdline); diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index 35dbc2791c97..e02579907f2e 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -32,6 +32,7 @@ static unsigned long __chunk_size = EFI_READ_CHUNK_SIZE; static int __section(.data) __nokaslr; static int __section(.data) __quiet; static int __section(.data) __novamap; +static bool __section(.data) efi_nosoftreserve; int __pure nokaslr(void) { @@ -45,6 +46,10 @@ int __pure novamap(void) { return __novamap; } +bool __pure __efi_soft_reserve_enabled(void) +{ + return !efi_nosoftreserve; +} #define EFI_MMAP_NR_SLACK_SLOTS 8 @@ -211,6 +216,10 @@ again: if (desc->type != EFI_CONVENTIONAL_MEMORY) continue; + if (efi_soft_reserve_enabled() && + (desc->attribute & EFI_MEMORY_SP)) + continue; + if (desc->num_pages < nr_pages) continue; @@ -305,6 +314,10 @@ efi_status_t efi_low_alloc_above(efi_system_table_t *sys_table_arg, if (desc->type != EFI_CONVENTIONAL_MEMORY) continue; + if (efi_soft_reserve_enabled() && + (desc->attribute & EFI_MEMORY_SP)) + continue; + if (desc->num_pages < nr_pages) continue; @@ -484,6 +497,12 @@ efi_status_t efi_parse_options(char const *cmdline) __novamap = 1; } + if (IS_ENABLED(CONFIG_EFI_SOFT_RESERVE) && + !strncmp(str, "nosoftreserve", 7)) { + str += strlen("nosoftreserve"); + efi_nosoftreserve = 1; + } + /* Group words together, delimited by "," */ while (*str && *str != ' ' && *str != ',') str++; diff --git a/include/linux/efi.h b/include/linux/efi.h index 44c85b559e15..88654910ce29 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1202,6 +1202,7 @@ extern int __init efi_setup_pcdp_console(char *); #define EFI_DBG 8 /* Print additional debug info at runtime */ #define EFI_NX_PE_DATA 9 /* Can runtime data regions be mapped non-executable? */ #define EFI_MEM_ATTR 10 /* Did firmware publish an EFI_MEMORY_ATTRIBUTES table? */ +#define EFI_MEM_NO_SOFT_RESERVE 11 /* Is the kernel configured to ignore soft reservations? */ #ifdef CONFIG_EFI /* @@ -1212,6 +1213,14 @@ static inline bool efi_enabled(int feature) return test_bit(feature, &efi.flags) != 0; } extern void efi_reboot(enum reboot_mode reboot_mode, const char *__unused); + +bool __pure __efi_soft_reserve_enabled(void); + +static inline bool __pure efi_soft_reserve_enabled(void) +{ + return IS_ENABLED(CONFIG_EFI_SOFT_RESERVE) + && __efi_soft_reserve_enabled(); +} #else static inline bool efi_enabled(int feature) { @@ -1225,6 +1234,11 @@ efi_capsule_pending(int *reset_type) { return false; } + +static inline bool efi_soft_reserve_enabled(void) +{ + return false; +} #endif extern int efi_status_to_err(efi_status_t status); -- cgit v1.2.3-71-gd317 From 262b45ae3ab4bf8e2caf1fcfd0d8307897519630 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 6 Nov 2019 17:43:16 -0800 Subject: x86/efi: EFI soft reservation to E820 enumeration UEFI 2.8 defines an EFI_MEMORY_SP attribute bit to augment the interpretation of the EFI Memory Types as "reserved for a specific purpose". The proposed Linux behavior for specific purpose memory is that it is reserved for direct-access (device-dax) by default and not available for any kernel usage, not even as an OOM fallback. Later, through udev scripts or another init mechanism, these device-dax claimed ranges can be reconfigured and hot-added to the available System-RAM with a unique node identifier. This device-dax management scheme implements "soft" in the "soft reserved" designation by allowing some or all of the reservation to be recovered as typical memory. This policy can be disabled at compile-time with CONFIG_EFI_SOFT_RESERVE=n, or runtime with efi=nosoftreserve. This patch introduces 2 new concepts at once given the entanglement between early boot enumeration relative to memory that can optionally be reserved from the kernel page allocator by default. The new concepts are: - E820_TYPE_SOFT_RESERVED: Upon detecting the EFI_MEMORY_SP attribute on EFI_CONVENTIONAL memory, update the E820 map with this new type. Only perform this classification if the CONFIG_EFI_SOFT_RESERVE=y policy is enabled, otherwise treat it as typical ram. - IORES_DESC_SOFT_RESERVED: Add a new I/O resource descriptor for a device driver to search iomem resources for application specific memory. Teach the iomem code to identify such ranges as "Soft Reserved". Note that the comment for do_add_efi_memmap() needed refreshing since it seemed to imply that the efi map might overflow the e820 table, but that is not an issue as of commit 7b6e4ba3cb1f "x86/boot/e820: Clean up the E820_X_MAX definition" that removed the 128 entry limit for e820__range_add(). A follow-on change integrates parsing of the ACPI HMAT to identify the node and sub-range boundaries of EFI_MEMORY_SP designated memory. For now, just identify and reserve memory of this type. Acked-by: Ard Biesheuvel Reported-by: kbuild test robot Reviewed-by: Dave Hansen Signed-off-by: Dan Williams Acked-by: Thomas Gleixner Signed-off-by: Rafael J. Wysocki --- arch/x86/boot/compressed/eboot.c | 6 ++++- arch/x86/boot/compressed/kaslr.c | 4 ++++ arch/x86/include/asm/e820/types.h | 8 +++++++ arch/x86/kernel/e820.c | 12 ++++++++-- arch/x86/platform/efi/efi.c | 49 +++++++++++++++++++++++++++++++++++---- include/linux/ioport.h | 1 + 6 files changed, 73 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 82bc60c8acb2..f2db8c5e4b06 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -554,7 +554,11 @@ setup_e820(struct boot_params *params, struct setup_data *e820ext, u32 e820ext_s case EFI_BOOT_SERVICES_CODE: case EFI_BOOT_SERVICES_DATA: case EFI_CONVENTIONAL_MEMORY: - e820_type = E820_TYPE_RAM; + if (efi_soft_reserve_enabled() && + (d->attribute & EFI_MEMORY_SP)) + e820_type = E820_TYPE_SOFT_RESERVED; + else + e820_type = E820_TYPE_RAM; break; case EFI_ACPI_MEMORY_NVS: diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 2e53c056ba20..ff6fa81949cd 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -760,6 +760,10 @@ process_efi_entries(unsigned long minimum, unsigned long image_size) if (md->type != EFI_CONVENTIONAL_MEMORY) continue; + if (efi_soft_reserve_enabled() && + (md->attribute & EFI_MEMORY_SP)) + continue; + if (efi_mirror_found && !(md->attribute & EFI_MEMORY_MORE_RELIABLE)) continue; diff --git a/arch/x86/include/asm/e820/types.h b/arch/x86/include/asm/e820/types.h index c3aa4b5e49e2..314f75d886d0 100644 --- a/arch/x86/include/asm/e820/types.h +++ b/arch/x86/include/asm/e820/types.h @@ -28,6 +28,14 @@ enum e820_type { */ E820_TYPE_PRAM = 12, + /* + * Special-purpose memory is indicated to the system via the + * EFI_MEMORY_SP attribute. Define an e820 translation of this + * memory type for the purpose of reserving this range and + * marking it with the IORES_DESC_SOFT_RESERVED designation. + */ + E820_TYPE_SOFT_RESERVED = 0xefffffff, + /* * Reserved RAM used by the kernel itself if * CONFIG_INTEL_TXT=y is enabled, memory of this type diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 7da2bcd2b8eb..9976106b57ec 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -190,6 +190,7 @@ static void __init e820_print_type(enum e820_type type) case E820_TYPE_RAM: /* Fall through: */ case E820_TYPE_RESERVED_KERN: pr_cont("usable"); break; case E820_TYPE_RESERVED: pr_cont("reserved"); break; + case E820_TYPE_SOFT_RESERVED: pr_cont("soft reserved"); break; case E820_TYPE_ACPI: pr_cont("ACPI data"); break; case E820_TYPE_NVS: pr_cont("ACPI NVS"); break; case E820_TYPE_UNUSABLE: pr_cont("unusable"); break; @@ -1037,6 +1038,7 @@ static const char *__init e820_type_to_string(struct e820_entry *entry) case E820_TYPE_PRAM: return "Persistent Memory (legacy)"; case E820_TYPE_PMEM: return "Persistent Memory"; case E820_TYPE_RESERVED: return "Reserved"; + case E820_TYPE_SOFT_RESERVED: return "Soft Reserved"; default: return "Unknown E820 type"; } } @@ -1052,6 +1054,7 @@ static unsigned long __init e820_type_to_iomem_type(struct e820_entry *entry) case E820_TYPE_PRAM: /* Fall-through: */ case E820_TYPE_PMEM: /* Fall-through: */ case E820_TYPE_RESERVED: /* Fall-through: */ + case E820_TYPE_SOFT_RESERVED: /* Fall-through: */ default: return IORESOURCE_MEM; } } @@ -1064,6 +1067,7 @@ static unsigned long __init e820_type_to_iores_desc(struct e820_entry *entry) case E820_TYPE_PMEM: return IORES_DESC_PERSISTENT_MEMORY; case E820_TYPE_PRAM: return IORES_DESC_PERSISTENT_MEMORY_LEGACY; case E820_TYPE_RESERVED: return IORES_DESC_RESERVED; + case E820_TYPE_SOFT_RESERVED: return IORES_DESC_SOFT_RESERVED; case E820_TYPE_RESERVED_KERN: /* Fall-through: */ case E820_TYPE_RAM: /* Fall-through: */ case E820_TYPE_UNUSABLE: /* Fall-through: */ @@ -1078,11 +1082,12 @@ static bool __init do_mark_busy(enum e820_type type, struct resource *res) return true; /* - * Treat persistent memory like device memory, i.e. reserve it - * for exclusive use of a driver + * Treat persistent memory and other special memory ranges like + * device memory, i.e. reserve it for exclusive use of a driver */ switch (type) { case E820_TYPE_RESERVED: + case E820_TYPE_SOFT_RESERVED: case E820_TYPE_PRAM: case E820_TYPE_PMEM: return false; @@ -1285,6 +1290,9 @@ void __init e820__memblock_setup(void) if (end != (resource_size_t)end) continue; + if (entry->type == E820_TYPE_SOFT_RESERVED) + memblock_reserve(entry->addr, entry->size); + if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN) continue; diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index e6e41b118d68..8609dccea096 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -148,14 +148,18 @@ void __init efi_find_mirror(void) /* * Tell the kernel about the EFI memory map. This might include - * more than the max 128 entries that can fit in the e820 legacy - * (zeropage) memory map. + * more than the max 128 entries that can fit in the passed in e820 + * legacy (zeropage) memory map, but the kernel's e820 table can hold + * E820_MAX_ENTRIES. */ static void __init do_add_efi_memmap(void) { efi_memory_desc_t *md; + if (!efi_enabled(EFI_MEMMAP)) + return; + for_each_efi_memory_desc(md) { unsigned long long start = md->phys_addr; unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; @@ -167,7 +171,10 @@ static void __init do_add_efi_memmap(void) case EFI_BOOT_SERVICES_CODE: case EFI_BOOT_SERVICES_DATA: case EFI_CONVENTIONAL_MEMORY: - if (md->attribute & EFI_MEMORY_WB) + if (efi_soft_reserve_enabled() + && (md->attribute & EFI_MEMORY_SP)) + e820_type = E820_TYPE_SOFT_RESERVED; + else if (md->attribute & EFI_MEMORY_WB) e820_type = E820_TYPE_RAM; else e820_type = E820_TYPE_RESERVED; @@ -193,11 +200,36 @@ static void __init do_add_efi_memmap(void) e820_type = E820_TYPE_RESERVED; break; } + e820__range_add(start, size, e820_type); } e820__update_table(e820_table); } +/* + * Given add_efi_memmap defaults to 0 and there there is no alternative + * e820 mechanism for soft-reserved memory, import the full EFI memory + * map if soft reservations are present and enabled. Otherwise, the + * mechanism to disable the kernel's consideration of EFI_MEMORY_SP is + * the efi=nosoftreserve option. + */ +static bool do_efi_soft_reserve(void) +{ + efi_memory_desc_t *md; + + if (!efi_enabled(EFI_MEMMAP)) + return false; + + if (!efi_soft_reserve_enabled()) + return false; + + for_each_efi_memory_desc(md) + if (md->type == EFI_CONVENTIONAL_MEMORY && + (md->attribute & EFI_MEMORY_SP)) + return true; + return false; +} + int __init efi_memblock_x86_reserve_range(void) { struct efi_info *e = &boot_params.efi_info; @@ -227,7 +259,7 @@ int __init efi_memblock_x86_reserve_range(void) if (rv) return rv; - if (add_efi_memmap) + if (add_efi_memmap || do_efi_soft_reserve()) do_add_efi_memmap(); WARN(efi.memmap.desc_version != 1, @@ -781,6 +813,15 @@ static bool should_map_region(efi_memory_desc_t *md) if (IS_ENABLED(CONFIG_X86_32)) return false; + /* + * EFI specific purpose memory may be reserved by default + * depending on kernel config and boot options. + */ + if (md->type == EFI_CONVENTIONAL_MEMORY && + efi_soft_reserve_enabled() && + (md->attribute & EFI_MEMORY_SP)) + return false; + /* * Map all of RAM so that we can access arguments in the 1:1 * mapping when making EFI runtime calls. diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 7bddddfc76d6..a9b9170b5dd2 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -134,6 +134,7 @@ enum { IORES_DESC_PERSISTENT_MEMORY_LEGACY = 5, IORES_DESC_DEVICE_PRIVATE_MEMORY = 6, IORES_DESC_RESERVED = 7, + IORES_DESC_SOFT_RESERVED = 8, }; /* -- cgit v1.2.3-71-gd317 From 33dd70752cd76f4d883a165a674f13121a4155ed Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 6 Nov 2019 17:43:31 -0800 Subject: lib: Uplevel the pmem "region" ida to a global allocator In preparation for handling platform differentiated memory types beyond persistent memory, uplevel the "region" identifier to a global number space. This enables a device-dax instance to be registered to any memory type with guaranteed unique names. Signed-off-by: Dan Williams Acked-by: Thomas Gleixner Signed-off-by: Rafael J. Wysocki --- drivers/nvdimm/Kconfig | 1 + drivers/nvdimm/core.c | 1 - drivers/nvdimm/nd-core.h | 1 - drivers/nvdimm/region_devs.c | 13 ++++--------- include/linux/memregion.h | 19 +++++++++++++++++++ lib/Kconfig | 3 +++ lib/Makefile | 1 + lib/memregion.c | 18 ++++++++++++++++++ 8 files changed, 46 insertions(+), 11 deletions(-) create mode 100644 include/linux/memregion.h create mode 100644 lib/memregion.c (limited to 'include/linux') diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig index 36af7af6b7cf..b7d1eb38b27d 100644 --- a/drivers/nvdimm/Kconfig +++ b/drivers/nvdimm/Kconfig @@ -4,6 +4,7 @@ menuconfig LIBNVDIMM depends on PHYS_ADDR_T_64BIT depends on HAS_IOMEM depends on BLK_DEV + select MEMREGION help Generic support for non-volatile memory devices including ACPI-6-NFIT defined resources. On platforms that define an diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c index 9204f1e9fd14..e592c4964674 100644 --- a/drivers/nvdimm/core.c +++ b/drivers/nvdimm/core.c @@ -455,7 +455,6 @@ static __exit void libnvdimm_exit(void) nd_region_exit(); nvdimm_exit(); nvdimm_bus_exit(); - nd_region_devs_exit(); nvdimm_devs_exit(); } diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h index 25fa121104d0..aa059439fca0 100644 --- a/drivers/nvdimm/nd-core.h +++ b/drivers/nvdimm/nd-core.h @@ -114,7 +114,6 @@ struct nvdimm_bus *walk_to_nvdimm_bus(struct device *nd_dev); int __init nvdimm_bus_init(void); void nvdimm_bus_exit(void); void nvdimm_devs_exit(void); -void nd_region_devs_exit(void); struct nd_region; void nd_region_advance_seeds(struct nd_region *nd_region, struct device *dev); void nd_region_create_ns_seed(struct nd_region *nd_region); diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index ef423ba1a711..fbf34cf688f4 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -3,6 +3,7 @@ * Copyright(c) 2013-2015 Intel Corporation. All rights reserved. */ #include +#include #include #include #include @@ -19,7 +20,6 @@ */ #include -static DEFINE_IDA(region_ida); static DEFINE_PER_CPU(int, flush_idx); static int nvdimm_map_flush(struct device *dev, struct nvdimm *nvdimm, int dimm, @@ -133,7 +133,7 @@ static void nd_region_release(struct device *dev) put_device(&nvdimm->dev); } free_percpu(nd_region->lane); - ida_simple_remove(®ion_ida, nd_region->id); + memregion_free(nd_region->id); if (is_nd_blk(dev)) kfree(to_nd_blk_region(dev)); else @@ -985,7 +985,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus, if (!region_buf) return NULL; - nd_region->id = ida_simple_get(®ion_ida, 0, 0, GFP_KERNEL); + nd_region->id = memregion_alloc(GFP_KERNEL); if (nd_region->id < 0) goto err_id; @@ -1044,7 +1044,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus, return nd_region; err_percpu: - ida_simple_remove(®ion_ida, nd_region->id); + memregion_free(nd_region->id); err_id: kfree(region_buf); return NULL; @@ -1216,8 +1216,3 @@ int nd_region_conflict(struct nd_region *nd_region, resource_size_t start, return device_for_each_child(&nvdimm_bus->dev, &ctx, region_conflict); } - -void __exit nd_region_devs_exit(void) -{ - ida_destroy(®ion_ida); -} diff --git a/include/linux/memregion.h b/include/linux/memregion.h new file mode 100644 index 000000000000..7de7c0a1444e --- /dev/null +++ b/include/linux/memregion.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _MEMREGION_H_ +#define _MEMREGION_H_ +#include +#include + +#ifdef CONFIG_MEMREGION +int memregion_alloc(gfp_t gfp); +void memregion_free(int id); +#else +static inline int memregion_alloc(gfp_t gfp) +{ + return -ENOMEM; +} +void memregion_free(int id) +{ +} +#endif +#endif /* _MEMREGION_H_ */ diff --git a/lib/Kconfig b/lib/Kconfig index 183f92a297ca..0dc043ac271d 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -606,6 +606,9 @@ config ARCH_NO_SG_CHAIN config ARCH_HAS_PMEM_API bool +config MEMREGION + bool + # use memcpy to implement user copies for nommu architectures config UACCESS_MEMCPY bool diff --git a/lib/Makefile b/lib/Makefile index c5892807e06f..2fb7b47018f1 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -212,6 +212,7 @@ obj-$(CONFIG_GENERIC_NET_UTILS) += net_utils.o obj-$(CONFIG_SG_SPLIT) += sg_split.o obj-$(CONFIG_SG_POOL) += sg_pool.o +obj-$(CONFIG_MEMREGION) += memregion.o obj-$(CONFIG_STMP_DEVICE) += stmp_device.o obj-$(CONFIG_IRQ_POLL) += irq_poll.o diff --git a/lib/memregion.c b/lib/memregion.c new file mode 100644 index 000000000000..77c85b5251da --- /dev/null +++ b/lib/memregion.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* identifiers for device / performance-differentiated memory regions */ +#include +#include + +static DEFINE_IDA(memregion_ids); + +int memregion_alloc(gfp_t gfp) +{ + return ida_alloc(&memregion_ids, gfp); +} +EXPORT_SYMBOL(memregion_alloc); + +void memregion_free(int id) +{ + ida_free(&memregion_ids, id); +} +EXPORT_SYMBOL(memregion_free); -- cgit v1.2.3-71-gd317 From a6c7f4c6aea5f4ca6056b06cec7ebd79f8c23e33 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 6 Nov 2019 17:43:43 -0800 Subject: device-dax: Add a driver for "hmem" devices Platform firmware like EFI/ACPI may publish "hmem" platform devices. Such a device is a performance differentiated memory range likely reserved for an application specific use case. The driver gives access to 100% of the capacity via a device-dax mmap instance by default. However, if over-subscription and other kernel memory management is desired the resulting dax device can be assigned to the core-mm via the kmem driver. This consumes "hmem" devices the producer of "hmem" devices is saved for a follow-on patch so that it can reference the new CONFIG_DEV_DAX_HMEM symbol to gate performing the enumeration work. Reported-by: kbuild test robot Reviewed-by: Dave Hansen Signed-off-by: Dan Williams Acked-by: Thomas Gleixner Signed-off-by: Rafael J. Wysocki --- drivers/dax/Kconfig | 27 ++++++++++++++++++----- drivers/dax/Makefile | 2 ++ drivers/dax/hmem.c | 56 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/memregion.h | 4 ++++ 4 files changed, 84 insertions(+), 5 deletions(-) create mode 100644 drivers/dax/hmem.c (limited to 'include/linux') diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig index f33c73e4af41..3b6c06f07326 100644 --- a/drivers/dax/Kconfig +++ b/drivers/dax/Kconfig @@ -32,19 +32,36 @@ config DEV_DAX_PMEM Say M if unsure +config DEV_DAX_HMEM + tristate "HMEM DAX: direct access to 'specific purpose' memory" + depends on EFI_SOFT_RESERVE + default DEV_DAX + help + EFI 2.8 platforms, and others, may advertise 'specific purpose' + memory. For example, a high bandwidth memory pool. The + indication from platform firmware is meant to reserve the + memory from typical usage by default. This driver creates + device-dax instances for these memory ranges, and that also + enables the possibility to assign them to the DEV_DAX_KMEM + driver to override the reservation and add them to kernel + "System RAM" pool. + + Say M if unsure. + config DEV_DAX_KMEM tristate "KMEM DAX: volatile-use of persistent memory" default DEV_DAX depends on DEV_DAX depends on MEMORY_HOTPLUG # for add_memory() and friends help - Support access to persistent memory as if it were RAM. This - allows easier use of persistent memory by unmodified - applications. + Support access to persistent, or other performance + differentiated memory as if it were System RAM. This allows + easier use of persistent memory by unmodified applications, or + adds core kernel memory services to heterogeneous memory types + (HMEM) marked "reserved" by platform firmware. To use this feature, a DAX device must be unbound from the - device_dax driver (PMEM DAX) and bound to this kmem driver - on each boot. + device_dax driver and bound to this kmem driver on each boot. Say N if unsure. diff --git a/drivers/dax/Makefile b/drivers/dax/Makefile index 81f7d54dadfb..80065b38b3c4 100644 --- a/drivers/dax/Makefile +++ b/drivers/dax/Makefile @@ -2,9 +2,11 @@ obj-$(CONFIG_DAX) += dax.o obj-$(CONFIG_DEV_DAX) += device_dax.o obj-$(CONFIG_DEV_DAX_KMEM) += kmem.o +obj-$(CONFIG_DEV_DAX_HMEM) += dax_hmem.o dax-y := super.o dax-y += bus.o device_dax-y := device.o +dax_hmem-y := hmem.o obj-y += pmem/ diff --git a/drivers/dax/hmem.c b/drivers/dax/hmem.c new file mode 100644 index 000000000000..fe7214daf62e --- /dev/null +++ b/drivers/dax/hmem.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include "bus.h" + +static int dax_hmem_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct dev_pagemap pgmap = { }; + struct dax_region *dax_region; + struct memregion_info *mri; + struct dev_dax *dev_dax; + struct resource *res; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) + return -ENOMEM; + + mri = dev->platform_data; + memcpy(&pgmap.res, res, sizeof(*res)); + + dax_region = alloc_dax_region(dev, pdev->id, res, mri->target_node, + PMD_SIZE, PFN_DEV|PFN_MAP); + if (!dax_region) + return -ENOMEM; + + dev_dax = devm_create_dev_dax(dax_region, 0, &pgmap); + if (IS_ERR(dev_dax)) + return PTR_ERR(dev_dax); + + /* child dev_dax instances now own the lifetime of the dax_region */ + dax_region_put(dax_region); + return 0; +} + +static int dax_hmem_remove(struct platform_device *pdev) +{ + /* devm handles teardown */ + return 0; +} + +static struct platform_driver dax_hmem_driver = { + .probe = dax_hmem_probe, + .remove = dax_hmem_remove, + .driver = { + .name = "hmem", + }, +}; + +module_platform_driver(dax_hmem_driver); + +MODULE_ALIAS("platform:hmem*"); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Intel Corporation"); diff --git a/include/linux/memregion.h b/include/linux/memregion.h index 7de7c0a1444e..e11595256cac 100644 --- a/include/linux/memregion.h +++ b/include/linux/memregion.h @@ -4,6 +4,10 @@ #include #include +struct memregion_info { + int target_node; +}; + #ifdef CONFIG_MEMREGION int memregion_alloc(gfp_t gfp); void memregion_free(int id); -- cgit v1.2.3-71-gd317 From acaade1af3587132e7ea585f470a95261e14f60c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 29 Oct 2019 09:57:09 +0100 Subject: dma-direct: remove __dma_direct_free_pages We can just call dma_free_contiguous directly instead of wrapping it. Signed-off-by: Christoph Hellwig Reviewed-by: Max Filippov --- include/linux/dma-direct.h | 1 - kernel/dma/direct.c | 11 +++-------- kernel/dma/remap.c | 4 ++-- 3 files changed, 5 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index adf993a3bd58..dec3b3bb121d 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -68,6 +68,5 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs); struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); -void __dma_direct_free_pages(struct device *dev, size_t size, struct page *page); int dma_direct_supported(struct device *dev, u64 mask); #endif /* _LINUX_DMA_DIRECT_H */ diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 8402b29c280f..a7a2739fb747 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -153,7 +153,7 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, * so log an error and fail. */ dev_info(dev, "Rejecting highmem page from CMA.\n"); - __dma_direct_free_pages(dev, size, page); + dma_free_contiguous(dev, page, size); return NULL; } @@ -175,11 +175,6 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, return ret; } -void __dma_direct_free_pages(struct device *dev, size_t size, struct page *page) -{ - dma_free_contiguous(dev, page, size); -} - void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs) { @@ -188,7 +183,7 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) && !force_dma_unencrypted(dev)) { /* cpu_addr is a struct page cookie, not a kernel address */ - __dma_direct_free_pages(dev, size, cpu_addr); + dma_free_contiguous(dev, cpu_addr, size); return; } @@ -198,7 +193,7 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, if (IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) && dma_alloc_need_uncached(dev, attrs)) cpu_addr = cached_kernel_address(cpu_addr); - __dma_direct_free_pages(dev, size, virt_to_page(cpu_addr)); + dma_free_contiguous(dev, virt_to_page(cpu_addr), size); } void *dma_direct_alloc(struct device *dev, size_t size, diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c index c00b9258fa6a..fb1e50c2d48a 100644 --- a/kernel/dma/remap.c +++ b/kernel/dma/remap.c @@ -238,7 +238,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, dma_pgprot(dev, PAGE_KERNEL, attrs), __builtin_return_address(0)); if (!ret) { - __dma_direct_free_pages(dev, size, page); + dma_free_contiguous(dev, page, size); return ret; } @@ -256,7 +256,7 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr, struct page *page = pfn_to_page(__phys_to_pfn(phys)); vunmap(vaddr); - __dma_direct_free_pages(dev, size, page); + dma_free_contiguous(dev, page, size); } } -- cgit v1.2.3-71-gd317 From 4e1003aa56a7d60ddb048e43a7a51368fcfe36af Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 29 Oct 2019 09:57:32 +0100 Subject: dma-direct: remove the dma_handle argument to __dma_direct_alloc_pages The argument isn't used anywhere, so stop passing it. Signed-off-by: Christoph Hellwig Reviewed-by: Max Filippov --- include/linux/dma-direct.h | 2 +- kernel/dma/direct.c | 4 ++-- kernel/dma/remap.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index dec3b3bb121d..ff3d5edc44b9 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -67,6 +67,6 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs); struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); + gfp_t gfp, unsigned long attrs); int dma_direct_supported(struct device *dev, u64 mask); #endif /* _LINUX_DMA_DIRECT_H */ diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index a7a2739fb747..724c282dd943 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -83,7 +83,7 @@ static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size) } struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) + gfp_t gfp, unsigned long attrs) { size_t alloc_size = PAGE_ALIGN(size); int node = dev_to_node(dev); @@ -131,7 +131,7 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, struct page *page; void *ret; - page = __dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs); + page = __dma_direct_alloc_pages(dev, size, gfp, attrs); if (!page) return NULL; diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c index fb1e50c2d48a..90d5ce77c189 100644 --- a/kernel/dma/remap.c +++ b/kernel/dma/remap.c @@ -226,7 +226,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, goto done; } - page = __dma_direct_alloc_pages(dev, size, dma_handle, flags, attrs); + page = __dma_direct_alloc_pages(dev, size, flags, attrs); if (!page) return NULL; -- cgit v1.2.3-71-gd317 From 8a80d5d6638b7d58480a83aef49d587de63d4cbb Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 7 Nov 2019 11:18:02 -0800 Subject: blk-cgroup: remove now unused blkg_print_stat_{bytes|ios}_recursive() These don't have users anymore. Remove them. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 83 ---------------------------------------------- include/linux/blk-cgroup.h | 5 --- 2 files changed, 88 deletions(-) (limited to 'include/linux') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 1eb8895be4c6..e7e93377e320 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -615,89 +615,6 @@ u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, } EXPORT_SYMBOL_GPL(blkg_prfill_rwstat); -static u64 blkg_prfill_rwstat_field(struct seq_file *sf, - struct blkg_policy_data *pd, int off) -{ - struct blkg_rwstat_sample rwstat = { }; - - blkg_rwstat_read((void *)pd->blkg + off, &rwstat); - return __blkg_prfill_rwstat(sf, pd, &rwstat); -} - -/** - * blkg_print_stat_bytes - seq_show callback for blkg->stat_bytes - * @sf: seq_file to print to - * @v: unused - * - * To be used as cftype->seq_show to print blkg->stat_bytes. - * cftype->private must be set to the blkcg_policy. - */ -int blkg_print_stat_bytes(struct seq_file *sf, void *v) -{ - blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), - blkg_prfill_rwstat_field, (void *)seq_cft(sf)->private, - offsetof(struct blkcg_gq, stat_bytes), true); - return 0; -} -EXPORT_SYMBOL_GPL(blkg_print_stat_bytes); - -/** - * blkg_print_stat_bytes - seq_show callback for blkg->stat_ios - * @sf: seq_file to print to - * @v: unused - * - * To be used as cftype->seq_show to print blkg->stat_ios. cftype->private - * must be set to the blkcg_policy. - */ -int blkg_print_stat_ios(struct seq_file *sf, void *v) -{ - blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), - blkg_prfill_rwstat_field, (void *)seq_cft(sf)->private, - offsetof(struct blkcg_gq, stat_ios), true); - return 0; -} -EXPORT_SYMBOL_GPL(blkg_print_stat_ios); - -static u64 blkg_prfill_rwstat_field_recursive(struct seq_file *sf, - struct blkg_policy_data *pd, - int off) -{ - struct blkg_rwstat_sample rwstat; - - blkg_rwstat_recursive_sum(pd->blkg, NULL, off, &rwstat); - return __blkg_prfill_rwstat(sf, pd, &rwstat); -} - -/** - * blkg_print_stat_bytes_recursive - recursive version of blkg_print_stat_bytes - * @sf: seq_file to print to - * @v: unused - */ -int blkg_print_stat_bytes_recursive(struct seq_file *sf, void *v) -{ - blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), - blkg_prfill_rwstat_field_recursive, - (void *)seq_cft(sf)->private, - offsetof(struct blkcg_gq, stat_bytes), true); - return 0; -} -EXPORT_SYMBOL_GPL(blkg_print_stat_bytes_recursive); - -/** - * blkg_print_stat_ios_recursive - recursive version of blkg_print_stat_ios - * @sf: seq_file to print to - * @v: unused - */ -int blkg_print_stat_ios_recursive(struct seq_file *sf, void *v) -{ - blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), - blkg_prfill_rwstat_field_recursive, - (void *)seq_cft(sf)->private, - offsetof(struct blkcg_gq, stat_ios), true); - return 0; -} -EXPORT_SYMBOL_GPL(blkg_print_stat_ios_recursive); - /** * blkg_rwstat_recursive_sum - collect hierarchical blkg_rwstat * @blkg: blkg of interest diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index bed9e43f9426..914ce55fa8c2 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -220,11 +220,6 @@ u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, const struct blkg_rwstat_sample *rwstat); u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, int off); -int blkg_print_stat_bytes(struct seq_file *sf, void *v); -int blkg_print_stat_ios(struct seq_file *sf, void *v); -int blkg_print_stat_bytes_recursive(struct seq_file *sf, void *v); -int blkg_print_stat_ios_recursive(struct seq_file *sf, void *v); - void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol, int off, struct blkg_rwstat_sample *sum); -- cgit v1.2.3-71-gd317 From f73316482977ac401ac37245c9df48079d4e11f3 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 7 Nov 2019 11:18:03 -0800 Subject: blk-cgroup: reimplement basic IO stats using cgroup rstat blk-cgroup has been using blkg_rwstat to track basic IO stats. Unfortunately, reading recursive stats scales badly as itinvolves walking all descendants. On systems with a huge number of cgroups (dead or alive), this can lead to substantial CPU cost when reading IO stats. This patch reimplements basic IO stats using cgroup rstat which uses more memory but makes recursive stat reading O(# descendants which have been active since last reading) instead of O(# descendants). * blk-cgroup core no longer uses sync/async stats. Introduce new stat enums - BLKG_IOSTAT_{READ|WRITE|DISCARD}. * Add blkg_iostat[_set] which encapsulates byte and io stats, last values for propagation delta calculation and u64_stats_sync for correctness on 32bit archs. * Update the new percpu stat counters directly and implement blkcg_rstat_flush() to implement propagation. * blkg_print_stat() can now bring the stats up to date by calling cgroup_rstat_flush() and print them instead of directly summing up all descendants. * It now allocates 96 bytes per cpu. It used to be 40 bytes. Signed-off-by: Tejun Heo Cc: Dan Schatzberg Cc: Daniel Xu Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 124 ++++++++++++++++++++++++++++++++++++--------- include/linux/blk-cgroup.h | 48 ++++++++++++++++-- 2 files changed, 142 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index e7e93377e320..b3429be62057 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -80,8 +80,7 @@ static void blkg_free(struct blkcg_gq *blkg) if (blkg->pd[i]) blkcg_policy[i]->pd_free_fn(blkg->pd[i]); - blkg_rwstat_exit(&blkg->stat_ios); - blkg_rwstat_exit(&blkg->stat_bytes); + free_percpu(blkg->iostat_cpu); percpu_ref_exit(&blkg->refcnt); kfree(blkg); } @@ -146,7 +145,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q, gfp_t gfp_mask) { struct blkcg_gq *blkg; - int i; + int i, cpu; /* alloc and init base part */ blkg = kzalloc_node(sizeof(*blkg), gfp_mask, q->node); @@ -156,8 +155,8 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q, if (percpu_ref_init(&blkg->refcnt, blkg_release, 0, gfp_mask)) goto err_free; - if (blkg_rwstat_init(&blkg->stat_bytes, gfp_mask) || - blkg_rwstat_init(&blkg->stat_ios, gfp_mask)) + blkg->iostat_cpu = alloc_percpu_gfp(struct blkg_iostat_set, gfp_mask); + if (!blkg->iostat_cpu) goto err_free; blkg->q = q; @@ -167,6 +166,10 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q, INIT_WORK(&blkg->async_bio_work, blkg_async_bio_workfn); blkg->blkcg = blkcg; + u64_stats_init(&blkg->iostat.sync); + for_each_possible_cpu(cpu) + u64_stats_init(&per_cpu_ptr(blkg->iostat_cpu, cpu)->sync); + for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; struct blkg_policy_data *pd; @@ -393,7 +396,6 @@ struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, static void blkg_destroy(struct blkcg_gq *blkg) { struct blkcg *blkcg = blkg->blkcg; - struct blkcg_gq *parent = blkg->parent; int i; lockdep_assert_held(&blkg->q->queue_lock); @@ -410,11 +412,6 @@ static void blkg_destroy(struct blkcg_gq *blkg) pol->pd_offline_fn(blkg->pd[i]); } - if (parent) { - blkg_rwstat_add_aux(&parent->stat_bytes, &blkg->stat_bytes); - blkg_rwstat_add_aux(&parent->stat_ios, &blkg->stat_ios); - } - blkg->online = false; radix_tree_delete(&blkcg->blkg_tree, blkg->q->id); @@ -464,7 +461,7 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css, { struct blkcg *blkcg = css_to_blkcg(css); struct blkcg_gq *blkg; - int i; + int i, cpu; mutex_lock(&blkcg_pol_mutex); spin_lock_irq(&blkcg->lock); @@ -475,8 +472,12 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css, * anyway. If you get hit by a race, retry. */ hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { - blkg_rwstat_reset(&blkg->stat_bytes); - blkg_rwstat_reset(&blkg->stat_ios); + for_each_possible_cpu(cpu) { + struct blkg_iostat_set *bis = + per_cpu_ptr(blkg->iostat_cpu, cpu); + memset(bis, 0, sizeof(*bis)); + } + memset(&blkg->iostat, 0, sizeof(blkg->iostat)); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; @@ -840,16 +841,18 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); struct blkcg_gq *blkg; + cgroup_rstat_flush(blkcg->css.cgroup); rcu_read_lock(); hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { + struct blkg_iostat_set *bis = &blkg->iostat; const char *dname; char *buf; - struct blkg_rwstat_sample rwstat; u64 rbytes, wbytes, rios, wios, dbytes, dios; size_t size = seq_get_buf(sf, &buf), off = 0; int i; bool has_stats = false; + unsigned seq; spin_lock_irq(&blkg->q->queue_lock); @@ -868,17 +871,16 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) */ off += scnprintf(buf+off, size-off, "%s ", dname); - blkg_rwstat_recursive_sum(blkg, NULL, - offsetof(struct blkcg_gq, stat_bytes), &rwstat); - rbytes = rwstat.cnt[BLKG_RWSTAT_READ]; - wbytes = rwstat.cnt[BLKG_RWSTAT_WRITE]; - dbytes = rwstat.cnt[BLKG_RWSTAT_DISCARD]; + do { + seq = u64_stats_fetch_begin(&bis->sync); - blkg_rwstat_recursive_sum(blkg, NULL, - offsetof(struct blkcg_gq, stat_ios), &rwstat); - rios = rwstat.cnt[BLKG_RWSTAT_READ]; - wios = rwstat.cnt[BLKG_RWSTAT_WRITE]; - dios = rwstat.cnt[BLKG_RWSTAT_DISCARD]; + rbytes = bis->cur.bytes[BLKG_IOSTAT_READ]; + wbytes = bis->cur.bytes[BLKG_IOSTAT_WRITE]; + dbytes = bis->cur.bytes[BLKG_IOSTAT_DISCARD]; + rios = bis->cur.ios[BLKG_IOSTAT_READ]; + wios = bis->cur.ios[BLKG_IOSTAT_WRITE]; + dios = bis->cur.ios[BLKG_IOSTAT_DISCARD]; + } while (u64_stats_fetch_retry(&bis->sync, seq)); if (rbytes || wbytes || rios || wios) { has_stats = true; @@ -1214,6 +1216,77 @@ static int blkcg_can_attach(struct cgroup_taskset *tset) return ret; } +static void blkg_iostat_set(struct blkg_iostat *dst, struct blkg_iostat *src) +{ + int i; + + for (i = 0; i < BLKG_IOSTAT_NR; i++) { + dst->bytes[i] = src->bytes[i]; + dst->ios[i] = src->ios[i]; + } +} + +static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src) +{ + int i; + + for (i = 0; i < BLKG_IOSTAT_NR; i++) { + dst->bytes[i] += src->bytes[i]; + dst->ios[i] += src->ios[i]; + } +} + +static void blkg_iostat_sub(struct blkg_iostat *dst, struct blkg_iostat *src) +{ + int i; + + for (i = 0; i < BLKG_IOSTAT_NR; i++) { + dst->bytes[i] -= src->bytes[i]; + dst->ios[i] -= src->ios[i]; + } +} + +static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) +{ + struct blkcg *blkcg = css_to_blkcg(css); + struct blkcg_gq *blkg; + + rcu_read_lock(); + + hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { + struct blkcg_gq *parent = blkg->parent; + struct blkg_iostat_set *bisc = per_cpu_ptr(blkg->iostat_cpu, cpu); + struct blkg_iostat cur, delta; + unsigned seq; + + /* fetch the current per-cpu values */ + do { + seq = u64_stats_fetch_begin(&bisc->sync); + blkg_iostat_set(&cur, &bisc->cur); + } while (u64_stats_fetch_retry(&bisc->sync, seq)); + + /* propagate percpu delta to global */ + u64_stats_update_begin(&blkg->iostat.sync); + blkg_iostat_set(&delta, &cur); + blkg_iostat_sub(&delta, &bisc->last); + blkg_iostat_add(&blkg->iostat.cur, &delta); + blkg_iostat_add(&bisc->last, &delta); + u64_stats_update_end(&blkg->iostat.sync); + + /* propagate global delta to parent */ + if (parent) { + u64_stats_update_begin(&parent->iostat.sync); + blkg_iostat_set(&delta, &blkg->iostat.cur); + blkg_iostat_sub(&delta, &blkg->iostat.last); + blkg_iostat_add(&parent->iostat.cur, &delta); + blkg_iostat_add(&blkg->iostat.last, &delta); + u64_stats_update_end(&parent->iostat.sync); + } + } + + rcu_read_unlock(); +} + static void blkcg_bind(struct cgroup_subsys_state *root_css) { int i; @@ -1246,6 +1319,7 @@ struct cgroup_subsys io_cgrp_subsys = { .css_offline = blkcg_css_offline, .css_free = blkcg_css_free, .can_attach = blkcg_can_attach, + .css_rstat_flush = blkcg_rstat_flush, .bind = blkcg_bind, .dfl_cftypes = blkcg_files, .legacy_cftypes = blkcg_legacy_files, diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 914ce55fa8c2..867ab391e409 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -15,7 +15,9 @@ */ #include +#include #include +#include #include #include #include @@ -31,6 +33,14 @@ #ifdef CONFIG_BLK_CGROUP +enum blkg_iostat_type { + BLKG_IOSTAT_READ, + BLKG_IOSTAT_WRITE, + BLKG_IOSTAT_DISCARD, + + BLKG_IOSTAT_NR, +}; + enum blkg_rwstat_type { BLKG_RWSTAT_READ, BLKG_RWSTAT_WRITE, @@ -61,6 +71,17 @@ struct blkcg { #endif }; +struct blkg_iostat { + u64 bytes[BLKG_IOSTAT_NR]; + u64 ios[BLKG_IOSTAT_NR]; +}; + +struct blkg_iostat_set { + struct u64_stats_sync sync; + struct blkg_iostat cur; + struct blkg_iostat last; +}; + /* * blkg_[rw]stat->aux_cnt is excluded for local stats but included for * recursive. Used to carry stats of dead children. @@ -127,8 +148,8 @@ struct blkcg_gq { /* is this blkg online? protected by both blkcg and q locks */ bool online; - struct blkg_rwstat stat_bytes; - struct blkg_rwstat stat_ios; + struct blkg_iostat_set __percpu *iostat_cpu; + struct blkg_iostat_set iostat; struct blkg_policy_data *pd[BLKCG_MAX_POLS]; @@ -740,15 +761,32 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, throtl = blk_throtl_bio(q, blkg, bio); if (!throtl) { + struct blkg_iostat_set *bis; + int rwd, cpu; + + if (op_is_discard(bio->bi_opf)) + rwd = BLKG_IOSTAT_DISCARD; + else if (op_is_write(bio->bi_opf)) + rwd = BLKG_IOSTAT_WRITE; + else + rwd = BLKG_IOSTAT_READ; + + cpu = get_cpu(); + bis = per_cpu_ptr(blkg->iostat_cpu, cpu); + u64_stats_update_begin(&bis->sync); + /* * If the bio is flagged with BIO_QUEUE_ENTERED it means this * is a split bio and we would have already accounted for the * size of the bio. */ if (!bio_flagged(bio, BIO_QUEUE_ENTERED)) - blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf, - bio->bi_iter.bi_size); - blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1); + bis->cur.bytes[rwd] += bio->bi_iter.bi_size; + bis->cur.ios[rwd]++; + + u64_stats_update_end(&bis->sync); + cgroup_rstat_updated(blkg->blkcg->css.cgroup, cpu); + put_cpu(); } blkcg_bio_issue_init(bio); -- cgit v1.2.3-71-gd317 From 1d156646e0d8ec390e5d5ac288137df02d4207be Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 7 Nov 2019 11:18:04 -0800 Subject: blk-cgroup: separate out blkg_rwstat under CONFIG_BLK_CGROUP_RWSTAT blkg_rwstat is now only used by bfq-iosched and blk-throtl when on cgroup1. Let's move it into its own files and gate it behind a config option. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- block/Kconfig | 4 ++ block/Kconfig.iosched | 1 + block/Makefile | 1 + block/bfq-iosched.h | 2 + block/blk-cgroup-rwstat.c | 129 ++++++++++++++++++++++++++++++++++++ block/blk-cgroup-rwstat.h | 149 ++++++++++++++++++++++++++++++++++++++++++ block/blk-cgroup.c | 97 --------------------------- block/blk-throttle.c | 1 + include/linux/blk-cgroup.h | 159 --------------------------------------------- 9 files changed, 287 insertions(+), 256 deletions(-) create mode 100644 block/blk-cgroup-rwstat.c create mode 100644 block/blk-cgroup-rwstat.h (limited to 'include/linux') diff --git a/block/Kconfig b/block/Kconfig index 41c0917ce622..c23094a14a2b 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -32,6 +32,9 @@ config BLK_RQ_ALLOC_TIME config BLK_SCSI_REQUEST bool +config BLK_CGROUP_RWSTAT + bool + config BLK_DEV_BSG bool "Block layer SG support v4" default y @@ -86,6 +89,7 @@ config BLK_DEV_ZONED config BLK_DEV_THROTTLING bool "Block layer bio throttling support" depends on BLK_CGROUP=y + select BLK_CGROUP_RWSTAT ---help--- Block layer bio throttling support. It can be used to limit the IO rate to a device. IO rate policies are per cgroup and diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched index b89310a022ad..7df14133adc8 100644 --- a/block/Kconfig.iosched +++ b/block/Kconfig.iosched @@ -31,6 +31,7 @@ config IOSCHED_BFQ config BFQ_GROUP_IOSCHED bool "BFQ hierarchical scheduling support" depends on IOSCHED_BFQ && BLK_CGROUP + select BLK_CGROUP_RWSTAT ---help--- Enable hierarchical scheduling in BFQ, using the blkio diff --git a/block/Makefile b/block/Makefile index 9ef57ace90d4..205a5f2fef17 100644 --- a/block/Makefile +++ b/block/Makefile @@ -16,6 +16,7 @@ obj-$(CONFIG_BLK_SCSI_REQUEST) += scsi_ioctl.o obj-$(CONFIG_BLK_DEV_BSG) += bsg.o obj-$(CONFIG_BLK_DEV_BSGLIB) += bsg-lib.o obj-$(CONFIG_BLK_CGROUP) += blk-cgroup.o +obj-$(CONFIG_BLK_CGROUP_RWSTAT) += blk-cgroup-rwstat.o obj-$(CONFIG_BLK_DEV_THROTTLING) += blk-throttle.o obj-$(CONFIG_BLK_CGROUP_IOLATENCY) += blk-iolatency.o obj-$(CONFIG_BLK_CGROUP_IOCOST) += blk-iocost.o diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index 2676c06218f1..9c82c1f35716 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -10,6 +10,8 @@ #include #include +#include "blk-cgroup-rwstat.h" + #define BFQ_IOPRIO_CLASSES 3 #define BFQ_CL_IDLE_TIMEOUT (HZ/5) diff --git a/block/blk-cgroup-rwstat.c b/block/blk-cgroup-rwstat.c new file mode 100644 index 000000000000..85d5790ac49b --- /dev/null +++ b/block/blk-cgroup-rwstat.c @@ -0,0 +1,129 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Legacy blkg rwstat helpers enabled by CONFIG_BLK_CGROUP_RWSTAT. + * Do not use in new code. + */ +#include "blk-cgroup-rwstat.h" + +int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp) +{ + int i, ret; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) { + ret = percpu_counter_init(&rwstat->cpu_cnt[i], 0, gfp); + if (ret) { + while (--i >= 0) + percpu_counter_destroy(&rwstat->cpu_cnt[i]); + return ret; + } + atomic64_set(&rwstat->aux_cnt[i], 0); + } + return 0; +} +EXPORT_SYMBOL_GPL(blkg_rwstat_init); + +void blkg_rwstat_exit(struct blkg_rwstat *rwstat) +{ + int i; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + percpu_counter_destroy(&rwstat->cpu_cnt[i]); +} +EXPORT_SYMBOL_GPL(blkg_rwstat_exit); + +/** + * __blkg_prfill_rwstat - prfill helper for a blkg_rwstat + * @sf: seq_file to print to + * @pd: policy private data of interest + * @rwstat: rwstat to print + * + * Print @rwstat to @sf for the device assocaited with @pd. + */ +u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, + const struct blkg_rwstat_sample *rwstat) +{ + static const char *rwstr[] = { + [BLKG_RWSTAT_READ] = "Read", + [BLKG_RWSTAT_WRITE] = "Write", + [BLKG_RWSTAT_SYNC] = "Sync", + [BLKG_RWSTAT_ASYNC] = "Async", + [BLKG_RWSTAT_DISCARD] = "Discard", + }; + const char *dname = blkg_dev_name(pd->blkg); + u64 v; + int i; + + if (!dname) + return 0; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + seq_printf(sf, "%s %s %llu\n", dname, rwstr[i], + rwstat->cnt[i]); + + v = rwstat->cnt[BLKG_RWSTAT_READ] + + rwstat->cnt[BLKG_RWSTAT_WRITE] + + rwstat->cnt[BLKG_RWSTAT_DISCARD]; + seq_printf(sf, "%s Total %llu\n", dname, v); + return v; +} +EXPORT_SYMBOL_GPL(__blkg_prfill_rwstat); + +/** + * blkg_prfill_rwstat - prfill callback for blkg_rwstat + * @sf: seq_file to print to + * @pd: policy private data of interest + * @off: offset to the blkg_rwstat in @pd + * + * prfill callback for printing a blkg_rwstat. + */ +u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, + int off) +{ + struct blkg_rwstat_sample rwstat = { }; + + blkg_rwstat_read((void *)pd + off, &rwstat); + return __blkg_prfill_rwstat(sf, pd, &rwstat); +} +EXPORT_SYMBOL_GPL(blkg_prfill_rwstat); + +/** + * blkg_rwstat_recursive_sum - collect hierarchical blkg_rwstat + * @blkg: blkg of interest + * @pol: blkcg_policy which contains the blkg_rwstat + * @off: offset to the blkg_rwstat in blkg_policy_data or @blkg + * @sum: blkg_rwstat_sample structure containing the results + * + * Collect the blkg_rwstat specified by @blkg, @pol and @off and all its + * online descendants and their aux counts. The caller must be holding the + * queue lock for online tests. + * + * If @pol is NULL, blkg_rwstat is at @off bytes into @blkg; otherwise, it + * is at @off bytes into @blkg's blkg_policy_data of the policy. + */ +void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol, + int off, struct blkg_rwstat_sample *sum) +{ + struct blkcg_gq *pos_blkg; + struct cgroup_subsys_state *pos_css; + unsigned int i; + + lockdep_assert_held(&blkg->q->queue_lock); + + rcu_read_lock(); + blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) { + struct blkg_rwstat *rwstat; + + if (!pos_blkg->online) + continue; + + if (pol) + rwstat = (void *)blkg_to_pd(pos_blkg, pol) + off; + else + rwstat = (void *)pos_blkg + off; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + sum->cnt[i] = blkg_rwstat_read_counter(rwstat, i); + } + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(blkg_rwstat_recursive_sum); diff --git a/block/blk-cgroup-rwstat.h b/block/blk-cgroup-rwstat.h new file mode 100644 index 000000000000..ee746919c41f --- /dev/null +++ b/block/blk-cgroup-rwstat.h @@ -0,0 +1,149 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Legacy blkg rwstat helpers enabled by CONFIG_BLK_CGROUP_RWSTAT. + * Do not use in new code. + */ +#ifndef _BLK_CGROUP_RWSTAT_H +#define _BLK_CGROUP_RWSTAT_H + +#include + +enum blkg_rwstat_type { + BLKG_RWSTAT_READ, + BLKG_RWSTAT_WRITE, + BLKG_RWSTAT_SYNC, + BLKG_RWSTAT_ASYNC, + BLKG_RWSTAT_DISCARD, + + BLKG_RWSTAT_NR, + BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR, +}; + +/* + * blkg_[rw]stat->aux_cnt is excluded for local stats but included for + * recursive. Used to carry stats of dead children. + */ +struct blkg_rwstat { + struct percpu_counter cpu_cnt[BLKG_RWSTAT_NR]; + atomic64_t aux_cnt[BLKG_RWSTAT_NR]; +}; + +struct blkg_rwstat_sample { + u64 cnt[BLKG_RWSTAT_NR]; +}; + +static inline u64 blkg_rwstat_read_counter(struct blkg_rwstat *rwstat, + unsigned int idx) +{ + return atomic64_read(&rwstat->aux_cnt[idx]) + + percpu_counter_sum_positive(&rwstat->cpu_cnt[idx]); +} + +int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp); +void blkg_rwstat_exit(struct blkg_rwstat *rwstat); +u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, + const struct blkg_rwstat_sample *rwstat); +u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, + int off); +void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol, + int off, struct blkg_rwstat_sample *sum); + + +/** + * blkg_rwstat_add - add a value to a blkg_rwstat + * @rwstat: target blkg_rwstat + * @op: REQ_OP and flags + * @val: value to add + * + * Add @val to @rwstat. The counters are chosen according to @rw. The + * caller is responsible for synchronizing calls to this function. + */ +static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat, + unsigned int op, uint64_t val) +{ + struct percpu_counter *cnt; + + if (op_is_discard(op)) + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_DISCARD]; + else if (op_is_write(op)) + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE]; + else + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ]; + + percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH); + + if (op_is_sync(op)) + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC]; + else + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC]; + + percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH); +} + +/** + * blkg_rwstat_read - read the current values of a blkg_rwstat + * @rwstat: blkg_rwstat to read + * + * Read the current snapshot of @rwstat and return it in the aux counts. + */ +static inline void blkg_rwstat_read(struct blkg_rwstat *rwstat, + struct blkg_rwstat_sample *result) +{ + int i; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + result->cnt[i] = + percpu_counter_sum_positive(&rwstat->cpu_cnt[i]); +} + +/** + * blkg_rwstat_total - read the total count of a blkg_rwstat + * @rwstat: blkg_rwstat to read + * + * Return the total count of @rwstat regardless of the IO direction. This + * function can be called without synchronization and takes care of u64 + * atomicity. + */ +static inline uint64_t blkg_rwstat_total(struct blkg_rwstat *rwstat) +{ + struct blkg_rwstat_sample tmp = { }; + + blkg_rwstat_read(rwstat, &tmp); + return tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE]; +} + +/** + * blkg_rwstat_reset - reset a blkg_rwstat + * @rwstat: blkg_rwstat to reset + */ +static inline void blkg_rwstat_reset(struct blkg_rwstat *rwstat) +{ + int i; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) { + percpu_counter_set(&rwstat->cpu_cnt[i], 0); + atomic64_set(&rwstat->aux_cnt[i], 0); + } +} + +/** + * blkg_rwstat_add_aux - add a blkg_rwstat into another's aux count + * @to: the destination blkg_rwstat + * @from: the source + * + * Add @from's count including the aux one to @to's aux count. + */ +static inline void blkg_rwstat_add_aux(struct blkg_rwstat *to, + struct blkg_rwstat *from) +{ + u64 sum[BLKG_RWSTAT_NR]; + int i; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + sum[i] = percpu_counter_sum_positive(&from->cpu_cnt[i]); + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + atomic64_add(sum[i] + atomic64_read(&from->aux_cnt[i]), + &to->aux_cnt[i]); +} +#endif /* _BLK_CGROUP_RWSTAT_H */ diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index b3429be62057..708dea92dac8 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -561,103 +561,6 @@ u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v) } EXPORT_SYMBOL_GPL(__blkg_prfill_u64); -/** - * __blkg_prfill_rwstat - prfill helper for a blkg_rwstat - * @sf: seq_file to print to - * @pd: policy private data of interest - * @rwstat: rwstat to print - * - * Print @rwstat to @sf for the device assocaited with @pd. - */ -u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, - const struct blkg_rwstat_sample *rwstat) -{ - static const char *rwstr[] = { - [BLKG_RWSTAT_READ] = "Read", - [BLKG_RWSTAT_WRITE] = "Write", - [BLKG_RWSTAT_SYNC] = "Sync", - [BLKG_RWSTAT_ASYNC] = "Async", - [BLKG_RWSTAT_DISCARD] = "Discard", - }; - const char *dname = blkg_dev_name(pd->blkg); - u64 v; - int i; - - if (!dname) - return 0; - - for (i = 0; i < BLKG_RWSTAT_NR; i++) - seq_printf(sf, "%s %s %llu\n", dname, rwstr[i], - rwstat->cnt[i]); - - v = rwstat->cnt[BLKG_RWSTAT_READ] + - rwstat->cnt[BLKG_RWSTAT_WRITE] + - rwstat->cnt[BLKG_RWSTAT_DISCARD]; - seq_printf(sf, "%s Total %llu\n", dname, v); - return v; -} -EXPORT_SYMBOL_GPL(__blkg_prfill_rwstat); - -/** - * blkg_prfill_rwstat - prfill callback for blkg_rwstat - * @sf: seq_file to print to - * @pd: policy private data of interest - * @off: offset to the blkg_rwstat in @pd - * - * prfill callback for printing a blkg_rwstat. - */ -u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, - int off) -{ - struct blkg_rwstat_sample rwstat = { }; - - blkg_rwstat_read((void *)pd + off, &rwstat); - return __blkg_prfill_rwstat(sf, pd, &rwstat); -} -EXPORT_SYMBOL_GPL(blkg_prfill_rwstat); - -/** - * blkg_rwstat_recursive_sum - collect hierarchical blkg_rwstat - * @blkg: blkg of interest - * @pol: blkcg_policy which contains the blkg_rwstat - * @off: offset to the blkg_rwstat in blkg_policy_data or @blkg - * @sum: blkg_rwstat_sample structure containing the results - * - * Collect the blkg_rwstat specified by @blkg, @pol and @off and all its - * online descendants and their aux counts. The caller must be holding the - * queue lock for online tests. - * - * If @pol is NULL, blkg_rwstat is at @off bytes into @blkg; otherwise, it - * is at @off bytes into @blkg's blkg_policy_data of the policy. - */ -void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol, - int off, struct blkg_rwstat_sample *sum) -{ - struct blkcg_gq *pos_blkg; - struct cgroup_subsys_state *pos_css; - unsigned int i; - - lockdep_assert_held(&blkg->q->queue_lock); - - rcu_read_lock(); - blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) { - struct blkg_rwstat *rwstat; - - if (!pos_blkg->online) - continue; - - if (pol) - rwstat = (void *)blkg_to_pd(pos_blkg, pol) + off; - else - rwstat = (void *)pos_blkg + off; - - for (i = 0; i < BLKG_RWSTAT_NR; i++) - sum->cnt[i] = blkg_rwstat_read_counter(rwstat, i); - } - rcu_read_unlock(); -} -EXPORT_SYMBOL_GPL(blkg_rwstat_recursive_sum); - /* Performs queue bypass and policy enabled checks then looks up blkg. */ static struct blkcg_gq *blkg_lookup_check(struct blkcg *blkcg, const struct blkcg_policy *pol, diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 2d0fc73d9781..98233c9c65a8 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -12,6 +12,7 @@ #include #include #include "blk.h" +#include "blk-cgroup-rwstat.h" /* Max dispatch from a group in 1 round */ static int throtl_grp_quantum = 8; diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 867ab391e409..48a66738143d 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -41,17 +41,6 @@ enum blkg_iostat_type { BLKG_IOSTAT_NR, }; -enum blkg_rwstat_type { - BLKG_RWSTAT_READ, - BLKG_RWSTAT_WRITE, - BLKG_RWSTAT_SYNC, - BLKG_RWSTAT_ASYNC, - BLKG_RWSTAT_DISCARD, - - BLKG_RWSTAT_NR, - BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR, -}; - struct blkcg_gq; struct blkcg { @@ -82,19 +71,6 @@ struct blkg_iostat_set { struct blkg_iostat last; }; -/* - * blkg_[rw]stat->aux_cnt is excluded for local stats but included for - * recursive. Used to carry stats of dead children. - */ -struct blkg_rwstat { - struct percpu_counter cpu_cnt[BLKG_RWSTAT_NR]; - atomic64_t aux_cnt[BLKG_RWSTAT_NR]; -}; - -struct blkg_rwstat_sample { - u64 cnt[BLKG_RWSTAT_NR]; -}; - /* * A blkcg_gq (blkg) is association between a block cgroup (blkcg) and a * request_queue (q). This is used by blkcg policies which need to track @@ -223,13 +199,6 @@ int blkcg_activate_policy(struct request_queue *q, void blkcg_deactivate_policy(struct request_queue *q, const struct blkcg_policy *pol); -static inline u64 blkg_rwstat_read_counter(struct blkg_rwstat *rwstat, - unsigned int idx) -{ - return atomic64_read(&rwstat->aux_cnt[idx]) + - percpu_counter_sum_positive(&rwstat->cpu_cnt[idx]); -} - const char *blkg_dev_name(struct blkcg_gq *blkg); void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, u64 (*prfill)(struct seq_file *, @@ -237,12 +206,6 @@ void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, const struct blkcg_policy *pol, int data, bool show_total); u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v); -u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, - const struct blkg_rwstat_sample *rwstat); -u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, - int off); -void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol, - int off, struct blkg_rwstat_sample *sum); struct blkg_conf_ctx { struct gendisk *disk; @@ -594,128 +557,6 @@ static inline void blkg_put(struct blkcg_gq *blkg) if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ (p_blkg)->q, false))) -static inline int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp) -{ - int i, ret; - - for (i = 0; i < BLKG_RWSTAT_NR; i++) { - ret = percpu_counter_init(&rwstat->cpu_cnt[i], 0, gfp); - if (ret) { - while (--i >= 0) - percpu_counter_destroy(&rwstat->cpu_cnt[i]); - return ret; - } - atomic64_set(&rwstat->aux_cnt[i], 0); - } - return 0; -} - -static inline void blkg_rwstat_exit(struct blkg_rwstat *rwstat) -{ - int i; - - for (i = 0; i < BLKG_RWSTAT_NR; i++) - percpu_counter_destroy(&rwstat->cpu_cnt[i]); -} - -/** - * blkg_rwstat_add - add a value to a blkg_rwstat - * @rwstat: target blkg_rwstat - * @op: REQ_OP and flags - * @val: value to add - * - * Add @val to @rwstat. The counters are chosen according to @rw. The - * caller is responsible for synchronizing calls to this function. - */ -static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat, - unsigned int op, uint64_t val) -{ - struct percpu_counter *cnt; - - if (op_is_discard(op)) - cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_DISCARD]; - else if (op_is_write(op)) - cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE]; - else - cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ]; - - percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH); - - if (op_is_sync(op)) - cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC]; - else - cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC]; - - percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH); -} - -/** - * blkg_rwstat_read - read the current values of a blkg_rwstat - * @rwstat: blkg_rwstat to read - * - * Read the current snapshot of @rwstat and return it in the aux counts. - */ -static inline void blkg_rwstat_read(struct blkg_rwstat *rwstat, - struct blkg_rwstat_sample *result) -{ - int i; - - for (i = 0; i < BLKG_RWSTAT_NR; i++) - result->cnt[i] = - percpu_counter_sum_positive(&rwstat->cpu_cnt[i]); -} - -/** - * blkg_rwstat_total - read the total count of a blkg_rwstat - * @rwstat: blkg_rwstat to read - * - * Return the total count of @rwstat regardless of the IO direction. This - * function can be called without synchronization and takes care of u64 - * atomicity. - */ -static inline uint64_t blkg_rwstat_total(struct blkg_rwstat *rwstat) -{ - struct blkg_rwstat_sample tmp = { }; - - blkg_rwstat_read(rwstat, &tmp); - return tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE]; -} - -/** - * blkg_rwstat_reset - reset a blkg_rwstat - * @rwstat: blkg_rwstat to reset - */ -static inline void blkg_rwstat_reset(struct blkg_rwstat *rwstat) -{ - int i; - - for (i = 0; i < BLKG_RWSTAT_NR; i++) { - percpu_counter_set(&rwstat->cpu_cnt[i], 0); - atomic64_set(&rwstat->aux_cnt[i], 0); - } -} - -/** - * blkg_rwstat_add_aux - add a blkg_rwstat into another's aux count - * @to: the destination blkg_rwstat - * @from: the source - * - * Add @from's count including the aux one to @to's aux count. - */ -static inline void blkg_rwstat_add_aux(struct blkg_rwstat *to, - struct blkg_rwstat *from) -{ - u64 sum[BLKG_RWSTAT_NR]; - int i; - - for (i = 0; i < BLKG_RWSTAT_NR; i++) - sum[i] = percpu_counter_sum_positive(&from->cpu_cnt[i]); - - for (i = 0; i < BLKG_RWSTAT_NR; i++) - atomic64_add(sum[i] + atomic64_read(&from->aux_cnt[i]), - &to->aux_cnt[i]); -} - #ifdef CONFIG_BLK_DEV_THROTTLING extern bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, struct bio *bio); -- cgit v1.2.3-71-gd317 From dbbf98392af6e2cf3673908c1388ca1ae915c8bb Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Fri, 6 Sep 2019 15:06:41 +0000 Subject: memory: atmel-ebi: move NUM_CS definition inside EBI driver The total number of EBI CS lines is described by the EBI controller and not by the Matrix. Move the definition for the number of CS inside EBI driver. Signed-off-by: Tudor Ambarus Link: https://lore.kernel.org/r/20190906150632.19039-1-tudor.ambarus@microchip.com Signed-off-by: Alexandre Belloni --- drivers/memory/atmel-ebi.c | 6 ++++-- include/linux/mfd/syscon/atmel-matrix.h | 1 - 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/memory/atmel-ebi.c b/drivers/memory/atmel-ebi.c index 0322df9dc249..8515196c2b03 100644 --- a/drivers/memory/atmel-ebi.c +++ b/drivers/memory/atmel-ebi.c @@ -19,6 +19,8 @@ #include #include +#define AT91_EBI_NUM_CS 8 + struct atmel_ebi_dev_config { int cs; struct atmel_smc_cs_conf smcconf; @@ -314,7 +316,7 @@ static int atmel_ebi_dev_setup(struct atmel_ebi *ebi, struct device_node *np, if (ret) return ret; - if (cs >= AT91_MATRIX_EBI_NUM_CS || + if (cs >= AT91_EBI_NUM_CS || !(ebi->caps->available_cs & BIT(cs))) { dev_err(dev, "invalid reg property in %pOF\n", np); return -EINVAL; @@ -344,7 +346,7 @@ static int atmel_ebi_dev_setup(struct atmel_ebi *ebi, struct device_node *np, apply = true; i = 0; - for_each_set_bit(cs, &cslines, AT91_MATRIX_EBI_NUM_CS) { + for_each_set_bit(cs, &cslines, AT91_EBI_NUM_CS) { ebid->configs[i].cs = cs; if (apply) { diff --git a/include/linux/mfd/syscon/atmel-matrix.h b/include/linux/mfd/syscon/atmel-matrix.h index f61cd127a852..20c25665216a 100644 --- a/include/linux/mfd/syscon/atmel-matrix.h +++ b/include/linux/mfd/syscon/atmel-matrix.h @@ -106,7 +106,6 @@ #define AT91_MATRIX_DDR_IOSR BIT(18) #define AT91_MATRIX_NFD0_SELECT BIT(24) #define AT91_MATRIX_DDR_MP_EN BIT(25) -#define AT91_MATRIX_EBI_NUM_CS 8 #define AT91_MATRIX_USBPUCR_PUON BIT(30) -- cgit v1.2.3-71-gd317 From de7d5084d82794a8e83afb994fcb07f82da3cd7b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 Nov 2019 16:27:14 -0800 Subject: net: provide dev_lstats_read() helper Many network drivers use hand-coded implementation of the same thing, let's factorize things so that u64_stats_t adoption is done once. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/loopback.c | 24 +++++++++++++++++------- include/linux/netdevice.h | 2 ++ 2 files changed, 19 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index 14545a8797a8..92336ac4c5e6 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -99,13 +99,13 @@ static netdev_tx_t loopback_xmit(struct sk_buff *skb, return NETDEV_TX_OK; } -static void loopback_get_stats64(struct net_device *dev, - struct rtnl_link_stats64 *stats) +void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes) { - u64 bytes = 0; - u64 packets = 0; int i; + *packets = 0; + *bytes = 0; + for_each_possible_cpu(i) { const struct pcpu_lstats *lb_stats; u64 tbytes, tpackets; @@ -114,12 +114,22 @@ static void loopback_get_stats64(struct net_device *dev, lb_stats = per_cpu_ptr(dev->lstats, i); do { start = u64_stats_fetch_begin_irq(&lb_stats->syncp); - tbytes = lb_stats->bytes; tpackets = lb_stats->packets; + tbytes = lb_stats->bytes; } while (u64_stats_fetch_retry_irq(&lb_stats->syncp, start)); - bytes += tbytes; - packets += tpackets; + *bytes += tbytes; + *packets += tpackets; } +} +EXPORT_SYMBOL(dev_lstats_read); + +static void loopback_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *stats) +{ + u64 packets, bytes; + + dev_lstats_read(dev, &packets, &bytes); + stats->rx_packets = packets; stats->tx_packets = packets; stats->rx_bytes = bytes; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1f140a6b66df..75561992c31f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2401,6 +2401,8 @@ struct pcpu_lstats { struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); +void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes); + #define __netdev_alloc_pcpu_stats(type, gfp) \ ({ \ typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\ -- cgit v1.2.3-71-gd317 From dd5382a08157756510aa8d7269c662eccde775cb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 Nov 2019 16:27:15 -0800 Subject: net: provide dev_lstats_add() helper Many network drivers need it and hand-coded the same function. In order to ease u64_stats_t adoption, it is time to factorize. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/loopback.c | 12 ++---------- include/linux/netdevice.h | 10 ++++++++++ 2 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index 92336ac4c5e6..47ad2478b9f3 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -68,7 +68,6 @@ EXPORT_SYMBOL(blackhole_netdev); static netdev_tx_t loopback_xmit(struct sk_buff *skb, struct net_device *dev) { - struct pcpu_lstats *lb_stats; int len; skb_tx_timestamp(skb); @@ -85,16 +84,9 @@ static netdev_tx_t loopback_xmit(struct sk_buff *skb, skb->protocol = eth_type_trans(skb, dev); - /* it's OK to use per_cpu_ptr() because BHs are off */ - lb_stats = this_cpu_ptr(dev->lstats); - len = skb->len; - if (likely(netif_rx(skb) == NET_RX_SUCCESS)) { - u64_stats_update_begin(&lb_stats->syncp); - lb_stats->bytes += len; - lb_stats->packets++; - u64_stats_update_end(&lb_stats->syncp); - } + if (likely(netif_rx(skb) == NET_RX_SUCCESS)) + dev_lstats_add(dev, len); return NETDEV_TX_OK; } diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 75561992c31f..461a36220cf4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2403,6 +2403,16 @@ struct pcpu_lstats { void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes); +static inline void dev_lstats_add(struct net_device *dev, unsigned int len) +{ + struct pcpu_lstats *lstats = this_cpu_ptr(dev->lstats); + + u64_stats_update_begin(&lstats->syncp); + lstats->bytes += len; + lstats->packets++; + u64_stats_update_end(&lstats->syncp); +} + #define __netdev_alloc_pcpu_stats(type, gfp) \ ({ \ typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\ -- cgit v1.2.3-71-gd317 From 316580b69d0a7aeeee5063af47438b626bc47cbd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 Nov 2019 16:27:20 -0800 Subject: u64_stats: provide u64_stats_t type On 64bit arches, struct u64_stats_sync is empty and provides no help against load/store tearing. Using READ_ONCE()/WRITE_ONCE() would be needed. But the update side would be slightly more expensive. local64_t was defined so that we could use regular adds in a manner which is atomic wrt IRQs. However the u64_stats infra means we do not have to use local64_t on 32bit arches since the syncp provides the needed protection. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/u64_stats_sync.h | 51 ++++++++++++++++++++++++++++++++++++++---- 1 file changed, 47 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index a27604f99ed0..9de5c10293f5 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -40,8 +40,8 @@ * spin_lock_bh(...) or other synchronization to get exclusive access * ... * u64_stats_update_begin(&stats->syncp); - * stats->bytes64 += len; // non atomic operation - * stats->packets64++; // non atomic operation + * u64_stats_add(&stats->bytes64, len); // non atomic operation + * u64_stats_inc(&stats->packets64); // non atomic operation * u64_stats_update_end(&stats->syncp); * * While a consumer (reader) should use following template to get consistent @@ -52,8 +52,8 @@ * * do { * start = u64_stats_fetch_begin(&stats->syncp); - * tbytes = stats->bytes64; // non atomic operation - * tpackets = stats->packets64; // non atomic operation + * tbytes = u64_stats_read(&stats->bytes64); // non atomic operation + * tpackets = u64_stats_read(&stats->packets64); // non atomic operation * } while (u64_stats_fetch_retry(&stats->syncp, start)); * * @@ -68,6 +68,49 @@ struct u64_stats_sync { #endif }; +#if BITS_PER_LONG == 64 +#include + +typedef struct { + local64_t v; +} u64_stats_t ; + +static inline u64 u64_stats_read(const u64_stats_t *p) +{ + return local64_read(&p->v); +} + +static inline void u64_stats_add(u64_stats_t *p, unsigned long val) +{ + local64_add(val, &p->v); +} + +static inline void u64_stats_inc(u64_stats_t *p) +{ + local64_inc(&p->v); +} + +#else + +typedef struct { + u64 v; +} u64_stats_t; + +static inline u64 u64_stats_read(const u64_stats_t *p) +{ + return p->v; +} + +static inline void u64_stats_add(u64_stats_t *p, unsigned long val) +{ + p->v += val; +} + +static inline void u64_stats_inc(u64_stats_t *p) +{ + p->v++; +} +#endif static inline void u64_stats_init(struct u64_stats_sync *syncp) { -- cgit v1.2.3-71-gd317 From fd2f4737870eb866537fbbffa2b59414b9b0c0a2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 Nov 2019 16:27:22 -0800 Subject: net: use u64_stats_t in struct pcpu_lstats In order to fix the data-race found by KCSAN, we can use the new u64_stats_t type and its accessors instead of plain u64 fields. This will still generate optimal code for both 32 and 64 bit platforms. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/loopback.c | 4 ++-- include/linux/netdevice.h | 8 ++++---- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index 47ad2478b9f3..a1c77cc00416 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -106,8 +106,8 @@ void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes) lb_stats = per_cpu_ptr(dev->lstats, i); do { start = u64_stats_fetch_begin_irq(&lb_stats->syncp); - tpackets = lb_stats->packets; - tbytes = lb_stats->bytes; + tpackets = u64_stats_read(&lb_stats->packets); + tbytes = u64_stats_read(&lb_stats->bytes); } while (u64_stats_fetch_retry_irq(&lb_stats->syncp, start)); *bytes += tbytes; *packets += tpackets; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 461a36220cf4..f857f01234f7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2396,8 +2396,8 @@ struct pcpu_sw_netstats { } __aligned(4 * sizeof(u64)); struct pcpu_lstats { - u64 packets; - u64 bytes; + u64_stats_t packets; + u64_stats_t bytes; struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); @@ -2408,8 +2408,8 @@ static inline void dev_lstats_add(struct net_device *dev, unsigned int len) struct pcpu_lstats *lstats = this_cpu_ptr(dev->lstats); u64_stats_update_begin(&lstats->syncp); - lstats->bytes += len; - lstats->packets++; + u64_stats_add(&lstats->bytes, len); + u64_stats_inc(&lstats->packets); u64_stats_update_end(&lstats->syncp); } -- cgit v1.2.3-71-gd317 From f8cc62ca3e660ae3fdaee533b1d554297cd2ae82 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 Nov 2019 18:49:43 -0800 Subject: net: add a READ_ONCE() in skb_peek_tail() skb_peek_tail() can be used without protection of a lock, as spotted by KCSAN [1] In order to avoid load-stearing, add a READ_ONCE() Note that the corresponding WRITE_ONCE() are already there. [1] BUG: KCSAN: data-race in sk_wait_data / skb_queue_tail read to 0xffff8880b36a4118 of 8 bytes by task 20426 on cpu 1: skb_peek_tail include/linux/skbuff.h:1784 [inline] sk_wait_data+0x15b/0x250 net/core/sock.c:2477 kcm_wait_data+0x112/0x1f0 net/kcm/kcmsock.c:1103 kcm_recvmsg+0xac/0x320 net/kcm/kcmsock.c:1130 sock_recvmsg_nosec net/socket.c:871 [inline] sock_recvmsg net/socket.c:889 [inline] sock_recvmsg+0x92/0xb0 net/socket.c:885 ___sys_recvmsg+0x1a0/0x3e0 net/socket.c:2480 do_recvmmsg+0x19a/0x5c0 net/socket.c:2601 __sys_recvmmsg+0x1ef/0x200 net/socket.c:2680 __do_sys_recvmmsg net/socket.c:2703 [inline] __se_sys_recvmmsg net/socket.c:2696 [inline] __x64_sys_recvmmsg+0x89/0xb0 net/socket.c:2696 do_syscall_64+0xcc/0x370 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x44/0xa9 write to 0xffff8880b36a4118 of 8 bytes by task 451 on cpu 0: __skb_insert include/linux/skbuff.h:1852 [inline] __skb_queue_before include/linux/skbuff.h:1958 [inline] __skb_queue_tail include/linux/skbuff.h:1991 [inline] skb_queue_tail+0x7e/0xc0 net/core/skbuff.c:3145 kcm_queue_rcv_skb+0x202/0x310 net/kcm/kcmsock.c:206 kcm_rcv_strparser+0x74/0x4b0 net/kcm/kcmsock.c:370 __strp_recv+0x348/0xf50 net/strparser/strparser.c:309 strp_recv+0x84/0xa0 net/strparser/strparser.c:343 tcp_read_sock+0x174/0x5c0 net/ipv4/tcp.c:1639 strp_read_sock+0xd4/0x140 net/strparser/strparser.c:366 do_strp_work net/strparser/strparser.c:414 [inline] strp_work+0x9a/0xe0 net/strparser/strparser.c:423 process_one_work+0x3d4/0x890 kernel/workqueue.c:2269 worker_thread+0xa0/0x800 kernel/workqueue.c:2415 kthread+0x1d4/0x200 drivers/block/aoe/aoecmd.c:1253 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:352 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 451 Comm: kworker/u4:3 Not tainted 5.4.0-rc3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: kstrp strp_work Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 53238ac725a3..dfe02b658829 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1795,7 +1795,7 @@ static inline struct sk_buff *skb_peek_next(struct sk_buff *skb, */ static inline struct sk_buff *skb_peek_tail(const struct sk_buff_head *list_) { - struct sk_buff *skb = list_->prev; + struct sk_buff *skb = READ_ONCE(list_->prev); if (skb == (struct sk_buff *)list_) skb = NULL; @@ -1861,7 +1861,9 @@ static inline void __skb_insert(struct sk_buff *newsk, struct sk_buff *prev, struct sk_buff *next, struct sk_buff_head *list) { - /* see skb_queue_empty_lockless() for the opposite READ_ONCE() */ + /* See skb_queue_empty_lockless() and skb_peek_tail() + * for the opposite READ_ONCE() + */ WRITE_ONCE(newsk->next, next); WRITE_ONCE(newsk->prev, prev); WRITE_ONCE(next->prev, newsk); -- cgit v1.2.3-71-gd317 From 5bd90b0989731520f2cdcfbbe467f1271f3cc803 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 7 Nov 2019 16:04:11 +0000 Subject: KVM: vgic-v4: Track the number of VLPIs per vcpu In order to find out whether a vcpu is likely to be the target of VLPIs (and to further optimize the way we deal with those), let's track the number of VLPIs a vcpu can receive. This gets implemented with an atomic variable that gets incremented or decremented on map, unmap and move of a VLPI. Signed-off-by: Marc Zyngier Reviewed-by: Zenghui Yu Reviewed-by: Christoffer Dall Link: https://lore.kernel.org/r/20191107160412.30301-2-maz@kernel.org --- include/linux/irqchip/arm-gic-v4.h | 2 ++ virt/kvm/arm/vgic/vgic-init.c | 1 + virt/kvm/arm/vgic/vgic-its.c | 3 +++ virt/kvm/arm/vgic/vgic-v4.c | 2 ++ 4 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h index ab1396afe08a..5dbcfc65f21e 100644 --- a/include/linux/irqchip/arm-gic-v4.h +++ b/include/linux/irqchip/arm-gic-v4.h @@ -32,6 +32,8 @@ struct its_vm { struct its_vpe { struct page *vpt_page; struct its_vm *its_vm; + /* per-vPE VLPI tracking */ + atomic_t vlpi_count; /* Doorbell interrupt */ int irq; irq_hw_number_t vpe_db_lpi; diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c index 6f50c429196d..b3c5de48064c 100644 --- a/virt/kvm/arm/vgic/vgic-init.c +++ b/virt/kvm/arm/vgic/vgic-init.c @@ -203,6 +203,7 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) INIT_LIST_HEAD(&vgic_cpu->ap_list_head); raw_spin_lock_init(&vgic_cpu->ap_list_lock); + atomic_set(&vgic_cpu->vgic_v3.its_vpe.vlpi_count, 0); /* * Enable and configure all SGIs to be edge-triggered and diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index 2be6b66b3856..98c7360d9fb7 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -360,7 +360,10 @@ static int update_affinity(struct vgic_irq *irq, struct kvm_vcpu *vcpu) if (ret) return ret; + if (map.vpe) + atomic_dec(&map.vpe->vlpi_count); map.vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; + atomic_inc(&map.vpe->vlpi_count); ret = its_map_vlpi(irq->host_irq, &map); } diff --git a/virt/kvm/arm/vgic/vgic-v4.c b/virt/kvm/arm/vgic/vgic-v4.c index 0965fb0c427a..46f875589c47 100644 --- a/virt/kvm/arm/vgic/vgic-v4.c +++ b/virt/kvm/arm/vgic/vgic-v4.c @@ -309,6 +309,7 @@ int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq, irq->hw = true; irq->host_irq = virq; + atomic_inc(&map.vpe->vlpi_count); out: mutex_unlock(&its->its_lock); @@ -342,6 +343,7 @@ int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int virq, WARN_ON(!(irq->hw && irq->host_irq == virq)); if (irq->hw) { + atomic_dec(&irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count); irq->hw = false; ret = its_unmap_vlpi(virq); } -- cgit v1.2.3-71-gd317 From bc9ad9e40dbc4c8874e806345df393a9cfeadad3 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Wed, 6 Nov 2019 09:33:02 +0000 Subject: EDAC: Replace EDAC_DIMM_PTR() macro with edac_get_dimm() function The EDAC_DIMM_PTR() macro takes 3 arguments from struct mem_ctl_info. Clean up this interface to only pass the mci struct and replace this macro with a new function edac_get_dimm(). Also introduce an edac_get_dimm_by_index() function for later use. This allows it to get a DIMM pointer only by a given index. This can be useful if the DIMM's position within the layers of the memory controller or the exact size of the layers are unknown. Small style changes made for some hunks after applying the semantic patch. Semantic patch used: @@ expression mci, a, b,c; @@ -EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, a, b, c) +edac_get_dimm(mci, a, b, c) [ bp: Touchups. ] Signed-off-by: Robert Richter Signed-off-by: Borislav Petkov Reviewed-by: Mauro Carvalho Chehab Cc: "linux-edac@vger.kernel.org" Cc: James Morse Cc: Jason Baron Cc: Qiuxu Zhuo Cc: Tero Kristo Cc: Tony Luck Link: https://lkml.kernel.org/r/20191106093239.25517-2-rrichter@marvell.com --- drivers/edac/ghes_edac.c | 7 +--- drivers/edac/i10nm_base.c | 3 +- drivers/edac/i3200_edac.c | 3 +- drivers/edac/i5000_edac.c | 5 +-- drivers/edac/i5100_edac.c | 3 +- drivers/edac/i5400_edac.c | 3 +- drivers/edac/i7300_edac.c | 3 +- drivers/edac/i7core_edac.c | 3 +- drivers/edac/ie31200_edac.c | 7 +--- drivers/edac/pnd2_edac.c | 4 +- drivers/edac/sb_edac.c | 2 +- drivers/edac/skx_base.c | 3 +- drivers/edac/ti_edac.c | 2 +- include/linux/edac.h | 89 +++++++++++++++++++++++++++++---------------- 14 files changed, 74 insertions(+), 63 deletions(-) (limited to 'include/linux') diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c index f6f6a688c009..2275d6bf6bc5 100644 --- a/drivers/edac/ghes_edac.c +++ b/drivers/edac/ghes_edac.c @@ -106,9 +106,7 @@ static void ghes_edac_dmidecode(const struct dmi_header *dh, void *arg) if (dh->type == DMI_ENTRY_MEM_DEVICE) { struct memdev_dmi_entry *entry = (struct memdev_dmi_entry *)dh; - struct dimm_info *dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, - mci->n_layers, - dimm_fill->count, 0, 0); + struct dimm_info *dimm = edac_get_dimm(mci, dimm_fill->count, 0, 0); u16 rdr_mask = BIT(7) | BIT(13); if (entry->size == 0xffff) { @@ -544,8 +542,7 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev) dimm_fill.mci = mci; dmi_walk(ghes_edac_dmidecode, &dimm_fill); } else { - struct dimm_info *dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, - mci->n_layers, 0, 0, 0); + struct dimm_info *dimm = edac_get_dimm(mci, 0, 0, 0); dimm->nr_pages = 1; dimm->grain = 128; diff --git a/drivers/edac/i10nm_base.c b/drivers/edac/i10nm_base.c index c370d5457e6b..059eccf0582b 100644 --- a/drivers/edac/i10nm_base.c +++ b/drivers/edac/i10nm_base.c @@ -154,8 +154,7 @@ static int i10nm_get_dimm_config(struct mem_ctl_info *mci) ndimms = 0; for (j = 0; j < I10NM_NUM_DIMMS; j++) { - dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, - mci->n_layers, i, j, 0); + dimm = edac_get_dimm(mci, i, j, 0); mtr = I10NM_GET_DIMMMTR(imc, i, j); mcddrtcfg = I10NM_GET_MCDDRTCFG(imc, i, j); edac_dbg(1, "dimmmtr 0x%x mcddrtcfg 0x%x (mc%d ch%d dimm%d)\n", diff --git a/drivers/edac/i3200_edac.c b/drivers/edac/i3200_edac.c index 299b441647cd..432b375a4075 100644 --- a/drivers/edac/i3200_edac.c +++ b/drivers/edac/i3200_edac.c @@ -392,8 +392,7 @@ static int i3200_probe1(struct pci_dev *pdev, int dev_idx) unsigned long nr_pages; for (j = 0; j < nr_channels; j++) { - struct dimm_info *dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, - mci->n_layers, i, j, 0); + struct dimm_info *dimm = edac_get_dimm(mci, i, j, 0); nr_pages = drb_to_nr_pages(drbs, stacked, j, i); if (nr_pages == 0) diff --git a/drivers/edac/i5000_edac.c b/drivers/edac/i5000_edac.c index 078a7351bf05..1a6f69c859ab 100644 --- a/drivers/edac/i5000_edac.c +++ b/drivers/edac/i5000_edac.c @@ -1275,9 +1275,8 @@ static int i5000_init_csrows(struct mem_ctl_info *mci) if (!MTR_DIMMS_PRESENT(mtr)) continue; - dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, - channel / MAX_BRANCHES, - channel % MAX_BRANCHES, slot); + dimm = edac_get_dimm(mci, channel / MAX_BRANCHES, + channel % MAX_BRANCHES, slot); csrow_megs = pvt->dimm_info[slot][channel].megabytes; dimm->grain = 8; diff --git a/drivers/edac/i5100_edac.c b/drivers/edac/i5100_edac.c index 12bebecb203b..134586753311 100644 --- a/drivers/edac/i5100_edac.c +++ b/drivers/edac/i5100_edac.c @@ -858,8 +858,7 @@ static void i5100_init_csrows(struct mem_ctl_info *mci) if (!npages) continue; - dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, - chan, rank, 0); + dimm = edac_get_dimm(mci, chan, rank, 0); dimm->nr_pages = npages; dimm->grain = 32; diff --git a/drivers/edac/i5400_edac.c b/drivers/edac/i5400_edac.c index 8c86c6fd7da7..f131c05ade9f 100644 --- a/drivers/edac/i5400_edac.c +++ b/drivers/edac/i5400_edac.c @@ -1187,8 +1187,7 @@ static int i5400_init_dimms(struct mem_ctl_info *mci) if (!MTR_DIMMS_PRESENT(mtr)) continue; - dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, - channel / 2, channel % 2, slot); + dimm = edac_get_dimm(mci, channel / 2, channel % 2, slot); size_mb = pvt->dimm_info[slot][channel].megabytes; diff --git a/drivers/edac/i7300_edac.c b/drivers/edac/i7300_edac.c index 447d357c7a67..2e9bbe56cde9 100644 --- a/drivers/edac/i7300_edac.c +++ b/drivers/edac/i7300_edac.c @@ -794,8 +794,7 @@ static int i7300_init_csrows(struct mem_ctl_info *mci) for (ch = 0; ch < max_channel; ch++) { int channel = to_channel(ch, branch); - dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, - mci->n_layers, branch, ch, slot); + dimm = edac_get_dimm(mci, branch, ch, slot); dinfo = &pvt->dimm_info[slot][channel]; diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c index a71cca6eeb33..b3135b208f9a 100644 --- a/drivers/edac/i7core_edac.c +++ b/drivers/edac/i7core_edac.c @@ -585,8 +585,7 @@ static int get_dimm_config(struct mem_ctl_info *mci) if (!DIMM_PRESENT(dimm_dod[j])) continue; - dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, - i, j, 0); + dimm = edac_get_dimm(mci, i, j, 0); banks = numbank(MC_DOD_NUMBANK(dimm_dod[j])); ranks = numrank(MC_DOD_NUMRANK(dimm_dod[j])); rows = numrow(MC_DOD_NUMROW(dimm_dod[j])); diff --git a/drivers/edac/ie31200_edac.c b/drivers/edac/ie31200_edac.c index d26300f9cb07..4f65073f230b 100644 --- a/drivers/edac/ie31200_edac.c +++ b/drivers/edac/ie31200_edac.c @@ -490,9 +490,7 @@ static int ie31200_probe1(struct pci_dev *pdev, int dev_idx) if (dimm_info[j][i].dual_rank) { nr_pages = nr_pages / 2; - dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, - mci->n_layers, (i * 2) + 1, - j, 0); + dimm = edac_get_dimm(mci, (i * 2) + 1, j, 0); dimm->nr_pages = nr_pages; edac_dbg(0, "set nr pages: 0x%lx\n", nr_pages); dimm->grain = 8; /* just a guess */ @@ -503,8 +501,7 @@ static int ie31200_probe1(struct pci_dev *pdev, int dev_idx) dimm->dtype = DEV_UNKNOWN; dimm->edac_mode = EDAC_UNKNOWN; } - dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, - mci->n_layers, i * 2, j, 0); + dimm = edac_get_dimm(mci, i * 2, j, 0); dimm->nr_pages = nr_pages; edac_dbg(0, "set nr pages: 0x%lx\n", nr_pages); dimm->grain = 8; /* same guess */ diff --git a/drivers/edac/pnd2_edac.c b/drivers/edac/pnd2_edac.c index b1193be1ef1d..933f7722b893 100644 --- a/drivers/edac/pnd2_edac.c +++ b/drivers/edac/pnd2_edac.c @@ -1231,7 +1231,7 @@ static void apl_get_dimm_config(struct mem_ctl_info *mci) if (!(chan_mask & BIT(i))) continue; - dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, i, 0, 0); + dimm = edac_get_dimm(mci, i, 0, 0); if (!dimm) { edac_dbg(0, "No allocated DIMM for channel %d\n", i); continue; @@ -1311,7 +1311,7 @@ static void dnv_get_dimm_config(struct mem_ctl_info *mci) if (!ranks_of_dimm[j]) continue; - dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, i, j, 0); + dimm = edac_get_dimm(mci, i, j, 0); if (!dimm) { edac_dbg(0, "No allocated DIMM for channel %d DIMM %d\n", i, j); continue; diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index a2fd39d330d6..4957e8ee1879 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -1621,7 +1621,7 @@ static int __populate_dimms(struct mem_ctl_info *mci, } for (j = 0; j < max_dimms_per_channel; j++) { - dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, i, j, 0); + dimm = edac_get_dimm(mci, i, j, 0); if (pvt->info.type == KNIGHTS_LANDING) { pci_read_config_dword(pvt->knl.pci_channel[i], knl_mtr_reg, &mtr); diff --git a/drivers/edac/skx_base.c b/drivers/edac/skx_base.c index a8853e724d1f..83545b4facb7 100644 --- a/drivers/edac/skx_base.c +++ b/drivers/edac/skx_base.c @@ -189,8 +189,7 @@ static int skx_get_dimm_config(struct mem_ctl_info *mci) pci_read_config_dword(imc->chan[i].cdev, 0x8C, &amap); pci_read_config_dword(imc->chan[i].cdev, 0x400, &mcddrtcfg); for (j = 0; j < SKX_NUM_DIMMS; j++) { - dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, - mci->n_layers, i, j, 0); + dimm = edac_get_dimm(mci, i, j, 0); pci_read_config_dword(imc->chan[i].cdev, 0x80 + 4 * j, &mtr); if (IS_DIMM_PRESENT(mtr)) { diff --git a/drivers/edac/ti_edac.c b/drivers/edac/ti_edac.c index 6ac26d1b929f..8be3e89a510e 100644 --- a/drivers/edac/ti_edac.c +++ b/drivers/edac/ti_edac.c @@ -135,7 +135,7 @@ static void ti_edac_setup_dimm(struct mem_ctl_info *mci, u32 type) u32 val; u32 memsize; - dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, 0, 0, 0); + dimm = edac_get_dimm(mci, 0, 0, 0); val = ti_edac_readl(edac, EMIF_SDRAM_CONFIG); diff --git a/include/linux/edac.h b/include/linux/edac.h index c19483b90079..280d109b9d05 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -403,37 +403,6 @@ struct edac_mc_layer { __i; \ }) -/** - * EDAC_DIMM_PTR - Macro responsible to get a pointer inside a pointer array - * for the element given by [layer0,layer1,layer2] position - * - * @layers: a struct edac_mc_layer array, describing how many elements - * were allocated for each layer - * @var: name of the var where we want to get the pointer - * (like mci->dimms) - * @nlayers: Number of layers at the @layers array - * @layer0: layer0 position - * @layer1: layer1 position. Unused if n_layers < 2 - * @layer2: layer2 position. Unused if n_layers < 3 - * - * For 1 layer, this macro returns "var[layer0]"; - * - * For 2 layers, this macro is similar to allocate a bi-dimensional array - * and to return "var[layer0][layer1]"; - * - * For 3 layers, this macro is similar to allocate a tri-dimensional array - * and to return "var[layer0][layer1][layer2]"; - */ -#define EDAC_DIMM_PTR(layers, var, nlayers, layer0, layer1, layer2) ({ \ - typeof(*var) __p; \ - int ___i = EDAC_DIMM_OFF(layers, nlayers, layer0, layer1, layer2); \ - if (___i < 0) \ - __p = NULL; \ - else \ - __p = (var)[___i]; \ - __p; \ -}) - struct dimm_info { struct device dev; @@ -669,4 +638,60 @@ struct mem_ctl_info { bool fake_inject_ue; u16 fake_inject_count; }; -#endif + +/** + * edac_get_dimm_by_index - Get DIMM info at @index from a memory + * controller + * + * @mci: MC descriptor struct mem_ctl_info + * @index: index in the memory controller's DIMM array + * + * Returns a struct dimm_info * or NULL on failure. + */ +static inline struct dimm_info * +edac_get_dimm_by_index(struct mem_ctl_info *mci, int index) +{ + if (index < 0 || index >= mci->tot_dimms) + return NULL; + + return mci->dimms[index]; +} + +/** + * edac_get_dimm - Get DIMM info from a memory controller given by + * [layer0,layer1,layer2] position + * + * @mci: MC descriptor struct mem_ctl_info + * @layer0: layer0 position + * @layer1: layer1 position. Unused if n_layers < 2 + * @layer2: layer2 position. Unused if n_layers < 3 + * + * For 1 layer, this function returns "dimms[layer0]"; + * + * For 2 layers, this function is similar to allocating a two-dimensional + * array and returning "dimms[layer0][layer1]"; + * + * For 3 layers, this function is similar to allocating a tri-dimensional + * array and returning "dimms[layer0][layer1][layer2]"; + */ +static inline struct dimm_info *edac_get_dimm(struct mem_ctl_info *mci, + int layer0, int layer1, int layer2) +{ + int index; + + if (layer0 < 0 + || (mci->n_layers > 1 && layer1 < 0) + || (mci->n_layers > 2 && layer2 < 0)) + return NULL; + + index = layer0; + + if (mci->n_layers > 1) + index = index * mci->layers[1].size + layer1; + + if (mci->n_layers > 2) + index = index * mci->layers[2].size + layer2; + + return edac_get_dimm_by_index(mci, index); +} +#endif /* _LINUX_EDAC_H_ */ -- cgit v1.2.3-71-gd317 From 977b1ce7c117905b3138dc727ed25f8af2ba2902 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Wed, 6 Nov 2019 09:33:04 +0000 Subject: EDAC: Remove EDAC_DIMM_OFF() macro The EDAC_DIMM_OFF() macro takes 5 arguments to get the DIMM's index. Simplify this by storing the index in struct dimm_info to avoid its calculation and remove the EDAC_DIMM_OFF() macro. The index can be directly used then. Another advantage is that edac_mc_alloc() could be used even if the exact size of the layers is unknown. Only the number of DIMMs would be needed. Rename iterator variable to idx, while at it. The name is more handy, esp. when searching for it in the code. Signed-off-by: Robert Richter Signed-off-by: Borislav Petkov Reviewed-by: Mauro Carvalho Chehab Cc: "linux-edac@vger.kernel.org" Cc: James Morse Cc: Tony Luck Link: https://lkml.kernel.org/r/20191106093239.25517-3-rrichter@marvell.com --- drivers/edac/edac_mc.c | 28 +++++++++++++-------------- drivers/edac/edac_mc_sysfs.c | 20 ++++---------------- include/linux/edac.h | 45 ++++---------------------------------------- 3 files changed, 21 insertions(+), 72 deletions(-) (limited to 'include/linux') diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index e6fd079783bd..cb5356411251 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -314,25 +314,27 @@ struct mem_ctl_info *edac_mc_alloc(unsigned int mc_num, struct dimm_info *dimm; u32 *ce_per_layer[EDAC_MAX_LAYERS], *ue_per_layer[EDAC_MAX_LAYERS]; unsigned int pos[EDAC_MAX_LAYERS]; - unsigned int size, tot_dimms = 1, count = 1; + unsigned int idx, size, tot_dimms = 1, count = 1; unsigned int tot_csrows = 1, tot_channels = 1, tot_errcount = 0; void *pvt, *p, *ptr = NULL; - int i, j, row, chn, n, len, off; + int i, j, row, chn, n, len; bool per_rank = false; BUG_ON(n_layers > EDAC_MAX_LAYERS || n_layers == 0); + /* * Calculate the total amount of dimms and csrows/cschannels while * in the old API emulation mode */ - for (i = 0; i < n_layers; i++) { - tot_dimms *= layers[i].size; - if (layers[i].is_virt_csrow) - tot_csrows *= layers[i].size; + for (idx = 0; idx < n_layers; idx++) { + tot_dimms *= layers[idx].size; + + if (layers[idx].is_virt_csrow) + tot_csrows *= layers[idx].size; else - tot_channels *= layers[i].size; + tot_channels *= layers[idx].size; - if (layers[i].type == EDAC_MC_LAYER_CHIP_SELECT) + if (layers[idx].type == EDAC_MC_LAYER_CHIP_SELECT) per_rank = true; } @@ -425,19 +427,15 @@ struct mem_ctl_info *edac_mc_alloc(unsigned int mc_num, memset(&pos, 0, sizeof(pos)); row = 0; chn = 0; - for (i = 0; i < tot_dimms; i++) { + for (idx = 0; idx < tot_dimms; idx++) { chan = mci->csrows[row]->channels[chn]; - off = EDAC_DIMM_OFF(layer, n_layers, pos[0], pos[1], pos[2]); - if (off < 0 || off >= tot_dimms) { - edac_mc_printk(mci, KERN_ERR, "EDAC core bug: EDAC_DIMM_OFF is trying to do an illegal data access\n"); - goto error; - } dimm = kzalloc(sizeof(**mci->dimms), GFP_KERNEL); if (!dimm) goto error; - mci->dimms[off] = dimm; + mci->dimms[idx] = dimm; dimm->mci = mci; + dimm->idx = idx; /* * Copy DIMM location and initialize it. diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index 32d016f1ecd1..91e4c8f155af 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -557,14 +557,8 @@ static ssize_t dimmdev_ce_count_show(struct device *dev, { struct dimm_info *dimm = to_dimm(dev); u32 count; - int off; - - off = EDAC_DIMM_OFF(dimm->mci->layers, - dimm->mci->n_layers, - dimm->location[0], - dimm->location[1], - dimm->location[2]); - count = dimm->mci->ce_per_layer[dimm->mci->n_layers-1][off]; + + count = dimm->mci->ce_per_layer[dimm->mci->n_layers-1][dimm->idx]; return sprintf(data, "%u\n", count); } @@ -574,14 +568,8 @@ static ssize_t dimmdev_ue_count_show(struct device *dev, { struct dimm_info *dimm = to_dimm(dev); u32 count; - int off; - - off = EDAC_DIMM_OFF(dimm->mci->layers, - dimm->mci->n_layers, - dimm->location[0], - dimm->location[1], - dimm->location[2]); - count = dimm->mci->ue_per_layer[dimm->mci->n_layers-1][off]; + + count = dimm->mci->ue_per_layer[dimm->mci->n_layers-1][dimm->idx]; return sprintf(data, "%u\n", count); } diff --git a/include/linux/edac.h b/include/linux/edac.h index 280d109b9d05..f4ebb14bc406 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -362,47 +362,6 @@ struct edac_mc_layer { */ #define EDAC_MAX_LAYERS 3 -/** - * EDAC_DIMM_OFF - Macro responsible to get a pointer offset inside a pointer - * array for the element given by [layer0,layer1,layer2] - * position - * - * @layers: a struct edac_mc_layer array, describing how many elements - * were allocated for each layer - * @nlayers: Number of layers at the @layers array - * @layer0: layer0 position - * @layer1: layer1 position. Unused if n_layers < 2 - * @layer2: layer2 position. Unused if n_layers < 3 - * - * For 1 layer, this macro returns "var[layer0] - var"; - * - * For 2 layers, this macro is similar to allocate a bi-dimensional array - * and to return "var[layer0][layer1] - var"; - * - * For 3 layers, this macro is similar to allocate a tri-dimensional array - * and to return "var[layer0][layer1][layer2] - var". - * - * A loop could be used here to make it more generic, but, as we only have - * 3 layers, this is a little faster. - * - * By design, layers can never be 0 or more than 3. If that ever happens, - * a NULL is returned, causing an OOPS during the memory allocation routine, - * with would point to the developer that he's doing something wrong. - */ -#define EDAC_DIMM_OFF(layers, nlayers, layer0, layer1, layer2) ({ \ - int __i; \ - if ((nlayers) == 1) \ - __i = layer0; \ - else if ((nlayers) == 2) \ - __i = (layer1) + ((layers[1]).size * (layer0)); \ - else if ((nlayers) == 3) \ - __i = (layer2) + ((layers[2]).size * ((layer1) + \ - ((layers[1]).size * (layer0)))); \ - else \ - __i = -EINVAL; \ - __i; \ -}) - struct dimm_info { struct device dev; @@ -412,6 +371,7 @@ struct dimm_info { unsigned int location[EDAC_MAX_LAYERS]; struct mem_ctl_info *mci; /* the parent */ + unsigned int idx; /* index within the parent dimm array */ u32 grain; /* granularity of reported error in bytes */ enum dev_type dtype; /* memory device type */ @@ -654,6 +614,9 @@ edac_get_dimm_by_index(struct mem_ctl_info *mci, int index) if (index < 0 || index >= mci->tot_dimms) return NULL; + if (WARN_ON_ONCE(mci->dimms[index]->idx != index)) + return NULL; + return mci->dimms[index]; } -- cgit v1.2.3-71-gd317 From 5bd54539788b3b3a415e84204cc89f918658d56d Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 22 Oct 2019 18:48:06 -0500 Subject: soundwire: remove bitfield for unique_id, use u8 There is no good reason why the unique_id needs to be stored as 4 bits. The code will work without changes with a u8 since all values are already filtered while parsing the ACPI tables and Slave devID registers. Use u8 representation. This will allow us to encode a "IGNORE_UNIQUE_ID" value to account for firmware/BIOS creativity. Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20191022234808.17432-2-pierre-louis.bossart@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 688b40e65c89..28745b9ba279 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -403,6 +403,8 @@ int sdw_slave_read_prop(struct sdw_slave *slave); * SDW Slave Structures and APIs */ +#define SDW_IGNORED_UNIQUE_ID 0xFF + /** * struct sdw_slave_id - Slave ID * @mfg_id: MIPI Manufacturer ID @@ -418,7 +420,7 @@ struct sdw_slave_id { __u16 mfg_id; __u16 part_id; __u8 class_id; - __u8 unique_id:4; + __u8 unique_id; __u8 sdw_version:4; }; -- cgit v1.2.3-71-gd317 From 727b3668b730634228fc65c336c2a7a080e02885 Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 8 Nov 2019 17:39:29 +0000 Subject: net: sfp: rework upstream interface The current upstream interface is an all-or-nothing, which is sub-optimal for future changes, as it doesn't allow the upstream driver to prepare for the SFP module becoming available, as it is at boot. Switch to a find-sfp-bus, add-upstream, del-upstream, put-sfp-bus interface structure instead, which allows the upstream driver to prepare for a module being available as soon as add-upstream is called. Signed-off-by: Russell King Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 10 +++--- drivers/net/phy/sfp-bus.c | 92 +++++++++++++++++++++++++++++++++-------------- include/linux/sfp.h | 25 ++++++++----- 3 files changed, 88 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index f16d9e92a81a..e3fbc8e93317 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -567,7 +567,7 @@ static int phylink_register_sfp(struct phylink *pl, struct sfp_bus *bus; int ret; - bus = sfp_register_upstream_node(fwnode, pl, &sfp_phylink_ops); + bus = sfp_bus_find_fwnode(fwnode); if (IS_ERR(bus)) { ret = PTR_ERR(bus); phylink_err(pl, "unable to attach SFP bus: %d\n", ret); @@ -576,7 +576,10 @@ static int phylink_register_sfp(struct phylink *pl, pl->sfp_bus = bus; - return 0; + ret = sfp_bus_add_upstream(bus, pl, &sfp_phylink_ops); + sfp_bus_put(bus); + + return ret; } /** @@ -670,8 +673,7 @@ EXPORT_SYMBOL_GPL(phylink_create); */ void phylink_destroy(struct phylink *pl) { - if (pl->sfp_bus) - sfp_unregister_upstream(pl->sfp_bus); + sfp_bus_del_upstream(pl->sfp_bus); if (pl->link_gpio) gpiod_put(pl->link_gpio); diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index d037aab6a71d..715d45214e18 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -329,10 +329,19 @@ static void sfp_bus_release(struct kref *kref) kfree(bus); } -static void sfp_bus_put(struct sfp_bus *bus) +/** + * sfp_bus_put() - put a reference on the &struct sfp_bus + * bus: the &struct sfp_bus found via sfp_bus_find_fwnode() + * + * Put a reference on the &struct sfp_bus and free the underlying structure + * if this was the last reference. + */ +void sfp_bus_put(struct sfp_bus *bus) { - kref_put_mutex(&bus->kref, sfp_bus_release, &sfp_mutex); + if (bus) + kref_put_mutex(&bus->kref, sfp_bus_release, &sfp_mutex); } +EXPORT_SYMBOL_GPL(sfp_bus_put); static int sfp_register_bus(struct sfp_bus *bus) { @@ -348,11 +357,11 @@ static int sfp_register_bus(struct sfp_bus *bus) return ret; } } + bus->registered = true; bus->socket_ops->attach(bus->sfp); if (bus->started) bus->socket_ops->start(bus->sfp); bus->upstream_ops->attach(bus->upstream, bus); - bus->registered = true; return 0; } @@ -446,13 +455,12 @@ static void sfp_upstream_clear(struct sfp_bus *bus) } /** - * sfp_register_upstream_node() - parse and register the neighbouring device + * sfp_bus_find_fwnode() - parse and locate the SFP bus from fwnode * @fwnode: firmware node for the parent device (MAC or PHY) - * @upstream: the upstream private data - * @ops: the upstream's &struct sfp_upstream_ops * - * Parse the parent device's firmware node for a SFP bus, and register the - * SFP bus using sfp_register_upstream(). + * Parse the parent device's firmware node for a SFP bus, and locate + * the sfp_bus structure, incrementing its reference count. This must + * be put via sfp_bus_put() when done. * * Returns: on success, a pointer to the sfp_bus structure, * %NULL if no SFP is specified, @@ -462,9 +470,7 @@ static void sfp_upstream_clear(struct sfp_bus *bus) * %-ENOMEM if we failed to allocate the bus. * an error from the upstream's connect_phy() method. */ -struct sfp_bus *sfp_register_upstream_node(struct fwnode_handle *fwnode, - void *upstream, - const struct sfp_upstream_ops *ops) +struct sfp_bus *sfp_bus_find_fwnode(struct fwnode_handle *fwnode) { struct fwnode_reference_args ref; struct sfp_bus *bus; @@ -482,7 +488,39 @@ struct sfp_bus *sfp_register_upstream_node(struct fwnode_handle *fwnode, if (!bus) return ERR_PTR(-ENOMEM); + return bus; +} +EXPORT_SYMBOL_GPL(sfp_bus_find_fwnode); + +/** + * sfp_bus_add_upstream() - parse and register the neighbouring device + * @bus: the &struct sfp_bus found via sfp_bus_find_fwnode() + * @upstream: the upstream private data + * @ops: the upstream's &struct sfp_upstream_ops + * + * Add upstream driver for the SFP bus, and if the bus is complete, register + * the SFP bus using sfp_register_upstream(). This takes a reference on the + * bus, so it is safe to put the bus after this call. + * + * Returns: on success, a pointer to the sfp_bus structure, + * %NULL if no SFP is specified, + * on failure, an error pointer value: + * corresponding to the errors detailed for + * fwnode_property_get_reference_args(). + * %-ENOMEM if we failed to allocate the bus. + * an error from the upstream's connect_phy() method. + */ +int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, + const struct sfp_upstream_ops *ops) +{ + int ret; + + /* If no bus, return success */ + if (!bus) + return 0; + rtnl_lock(); + kref_get(&bus->kref); bus->upstream_ops = ops; bus->upstream = upstream; @@ -495,33 +533,33 @@ struct sfp_bus *sfp_register_upstream_node(struct fwnode_handle *fwnode, } rtnl_unlock(); - if (ret) { + if (ret) sfp_bus_put(bus); - bus = ERR_PTR(ret); - } - return bus; + return ret; } -EXPORT_SYMBOL_GPL(sfp_register_upstream_node); +EXPORT_SYMBOL_GPL(sfp_bus_add_upstream); /** - * sfp_unregister_upstream() - Unregister sfp bus + * sfp_bus_del_upstream() - Delete a sfp bus * @bus: a pointer to the &struct sfp_bus structure for the sfp module * - * Unregister a previously registered upstream connection for the SFP - * module. @bus is returned from sfp_register_upstream(). + * Delete a previously registered upstream connection for the SFP + * module. @bus should have been added by sfp_bus_add_upstream(). */ -void sfp_unregister_upstream(struct sfp_bus *bus) +void sfp_bus_del_upstream(struct sfp_bus *bus) { - rtnl_lock(); - if (bus->sfp) - sfp_unregister_bus(bus); - sfp_upstream_clear(bus); - rtnl_unlock(); + if (bus) { + rtnl_lock(); + if (bus->sfp) + sfp_unregister_bus(bus); + sfp_upstream_clear(bus); + rtnl_unlock(); - sfp_bus_put(bus); + sfp_bus_put(bus); + } } -EXPORT_SYMBOL_GPL(sfp_unregister_upstream); +EXPORT_SYMBOL_GPL(sfp_bus_del_upstream); /* Socket driver entry points */ int sfp_add_phy(struct sfp_bus *bus, struct phy_device *phydev) diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 355a08a76fd4..c8464de7cff5 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -508,10 +508,11 @@ int sfp_get_module_eeprom(struct sfp_bus *bus, struct ethtool_eeprom *ee, u8 *data); void sfp_upstream_start(struct sfp_bus *bus); void sfp_upstream_stop(struct sfp_bus *bus); -struct sfp_bus *sfp_register_upstream_node(struct fwnode_handle *fwnode, - void *upstream, - const struct sfp_upstream_ops *ops); -void sfp_unregister_upstream(struct sfp_bus *bus); +void sfp_bus_put(struct sfp_bus *bus); +struct sfp_bus *sfp_bus_find_fwnode(struct fwnode_handle *fwnode); +int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, + const struct sfp_upstream_ops *ops); +void sfp_bus_del_upstream(struct sfp_bus *bus); #else static inline int sfp_parse_port(struct sfp_bus *bus, const struct sfp_eeprom_id *id, @@ -553,14 +554,22 @@ static inline void sfp_upstream_stop(struct sfp_bus *bus) { } -static inline struct sfp_bus *sfp_register_upstream_node( - struct fwnode_handle *fwnode, void *upstream, - const struct sfp_upstream_ops *ops) +static inline void sfp_bus_put(struct sfp_bus *bus) +{ +} + +static inline struct sfp_bus *sfp_bus_find_fwnode(struct fwnode_handle *fwnode) { return NULL; } -static inline void sfp_unregister_upstream(struct sfp_bus *bus) +static int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, + const struct sfp_upstream_ops *ops) +{ + return 0; +} + +static inline void sfp_bus_del_upstream(struct sfp_bus *bus) { } #endif -- cgit v1.2.3-71-gd317 From c498afaf7df87f44e7cb383c135baec52b5259be Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Wed, 6 Nov 2019 09:33:07 +0000 Subject: EDAC: Introduce an mci_for_each_dimm() iterator Introduce an mci_for_each_dimm() iterator. It returns a pointer to a struct dimm_info. This makes the declaration and use of an index obsolete and avoids access to internal data of struct mci (direct array access etc). [ bp: push the struct dimm_info *dimm; declaration into the CONFIG_EDAC_DEBUG block. ] Signed-off-by: Robert Richter Signed-off-by: Borislav Petkov Reviewed-by: Mauro Carvalho Chehab Cc: "linux-edac@vger.kernel.org" Cc: James Morse Cc: Tony Luck Link: https://lkml.kernel.org/r/20191106093239.25517-4-rrichter@marvell.com --- drivers/edac/edac_mc.c | 19 +++++++++++-------- drivers/edac/edac_mc_sysfs.c | 29 ++++++++++++----------------- drivers/edac/ghes_edac.c | 9 +++++---- drivers/edac/i5100_edac.c | 13 +++++-------- include/linux/edac.h | 7 +++++++ 5 files changed, 40 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index cb5356411251..88e24ece3e1e 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -145,15 +145,18 @@ static void edac_mc_dump_channel(struct rank_info *chan) edac_dbg(4, " channel->dimm = %p\n", chan->dimm); } -static void edac_mc_dump_dimm(struct dimm_info *dimm, int number) +static void edac_mc_dump_dimm(struct dimm_info *dimm) { char location[80]; + if (!dimm->nr_pages) + return; + edac_dimm_info_location(dimm, location, sizeof(location)); edac_dbg(4, "%s%i: %smapped as virtual row %d, chan %d\n", dimm->mci->csbased ? "rank" : "dimm", - number, location, dimm->csrow, dimm->cschannel); + dimm->idx, location, dimm->csrow, dimm->cschannel); edac_dbg(4, " dimm = %p\n", dimm); edac_dbg(4, " dimm->label = '%s'\n", dimm->label); edac_dbg(4, " dimm->nr_pages = 0x%x\n", dimm->nr_pages); @@ -712,6 +715,7 @@ int edac_mc_add_mc_with_groups(struct mem_ctl_info *mci, edac_mc_dump_mci(mci); if (edac_debug_level >= 4) { + struct dimm_info *dimm; int i; for (i = 0; i < mci->nr_csrows; i++) { @@ -728,9 +732,9 @@ int edac_mc_add_mc_with_groups(struct mem_ctl_info *mci, if (csrow->channels[j]->dimm->nr_pages) edac_mc_dump_channel(csrow->channels[j]); } - for (i = 0; i < mci->tot_dimms; i++) - if (mci->dimms[i]->nr_pages) - edac_mc_dump_dimm(mci->dimms[i], i); + + mci_for_each_dimm(mci, dimm) + edac_mc_dump_dimm(dimm); } #endif mutex_lock(&mem_ctls_mutex); @@ -1088,6 +1092,7 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type, const char *msg, const char *other_detail) { + struct dimm_info *dimm; char *p; int row = -1, chan = -1; int pos[EDAC_MAX_LAYERS] = { top_layer, mid_layer, low_layer }; @@ -1148,9 +1153,7 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type, p = e->label; *p = '\0'; - for (i = 0; i < mci->tot_dimms; i++) { - struct dimm_info *dimm = mci->dimms[i]; - + mci_for_each_dimm(mci, dimm) { if (top_layer >= 0 && top_layer != dimm->location[0]) continue; if (mid_layer >= 0 && mid_layer != dimm->location[1]) diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index 91e4c8f155af..0367554e7437 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -621,8 +621,7 @@ static const struct device_type dimm_attr_type = { /* Create a DIMM object under specifed memory controller device */ static int edac_create_dimm_object(struct mem_ctl_info *mci, - struct dimm_info *dimm, - int index) + struct dimm_info *dimm) { int err; dimm->mci = mci; @@ -632,9 +631,9 @@ static int edac_create_dimm_object(struct mem_ctl_info *mci, dimm->dev.parent = &mci->dev; if (mci->csbased) - dev_set_name(&dimm->dev, "rank%d", index); + dev_set_name(&dimm->dev, "rank%d", dimm->idx); else - dev_set_name(&dimm->dev, "dimm%d", index); + dev_set_name(&dimm->dev, "dimm%d", dimm->idx); dev_set_drvdata(&dimm->dev, dimm); pm_runtime_forbid(&mci->dev); @@ -916,7 +915,8 @@ static const struct device_type mci_attr_type = { int edac_create_sysfs_mci_device(struct mem_ctl_info *mci, const struct attribute_group **groups) { - int i, err; + struct dimm_info *dimm; + int err; /* get the /sys/devices/system/edac subsys reference */ mci->dev.type = &mci_attr_type; @@ -940,13 +940,12 @@ int edac_create_sysfs_mci_device(struct mem_ctl_info *mci, /* * Create the dimm/rank devices */ - for (i = 0; i < mci->tot_dimms; i++) { - struct dimm_info *dimm = mci->dimms[i]; + mci_for_each_dimm(mci, dimm) { /* Only expose populated DIMMs */ if (!dimm->nr_pages) continue; - err = edac_create_dimm_object(mci, dimm, i); + err = edac_create_dimm_object(mci, dimm); if (err) goto fail_unregister_dimm; } @@ -961,12 +960,9 @@ int edac_create_sysfs_mci_device(struct mem_ctl_info *mci, return 0; fail_unregister_dimm: - for (i--; i >= 0; i--) { - struct dimm_info *dimm = mci->dimms[i]; - if (!dimm->nr_pages) - continue; - - device_unregister(&dimm->dev); + mci_for_each_dimm(mci, dimm) { + if (device_is_registered(&dimm->dev)) + device_unregister(&dimm->dev); } device_unregister(&mci->dev); @@ -978,7 +974,7 @@ fail_unregister_dimm: */ void edac_remove_sysfs_mci_device(struct mem_ctl_info *mci) { - int i; + struct dimm_info *dimm; edac_dbg(0, "\n"); @@ -989,8 +985,7 @@ void edac_remove_sysfs_mci_device(struct mem_ctl_info *mci) edac_delete_csrow_objects(mci); #endif - for (i = 0; i < mci->tot_dimms; i++) { - struct dimm_info *dimm = mci->dimms[i]; + mci_for_each_dimm(mci, dimm) { if (dimm->nr_pages == 0) continue; edac_dbg(1, "unregistering device %s\n", dev_name(&dimm->dev)); diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c index 2275d6bf6bc5..fbc8b1de3ddd 100644 --- a/drivers/edac/ghes_edac.c +++ b/drivers/edac/ghes_edac.c @@ -90,12 +90,13 @@ static void ghes_edac_count_dimms(const struct dmi_header *dh, void *arg) static int get_dimm_smbios_index(struct mem_ctl_info *mci, u16 handle) { - int i; + struct dimm_info *dimm; - for (i = 0; i < mci->tot_dimms; i++) { - if (mci->dimms[i]->smbios_handle == handle) - return i; + mci_for_each_dimm(mci, dimm) { + if (dimm->smbios_handle == handle) + return dimm->idx; } + return -1; } diff --git a/drivers/edac/i5100_edac.c b/drivers/edac/i5100_edac.c index 134586753311..0ddc41e47a96 100644 --- a/drivers/edac/i5100_edac.c +++ b/drivers/edac/i5100_edac.c @@ -846,20 +846,17 @@ static void i5100_init_interleaving(struct pci_dev *pdev, static void i5100_init_csrows(struct mem_ctl_info *mci) { - int i; struct i5100_priv *priv = mci->pvt_info; + struct dimm_info *dimm; - for (i = 0; i < mci->tot_dimms; i++) { - struct dimm_info *dimm; - const unsigned long npages = i5100_npages(mci, i); - const unsigned int chan = i5100_csrow_to_chan(mci, i); - const unsigned int rank = i5100_csrow_to_rank(mci, i); + mci_for_each_dimm(mci, dimm) { + const unsigned long npages = i5100_npages(mci, dimm->idx); + const unsigned int chan = i5100_csrow_to_chan(mci, dimm->idx); + const unsigned int rank = i5100_csrow_to_rank(mci, dimm->idx); if (!npages) continue; - dimm = edac_get_dimm(mci, chan, rank, 0); - dimm->nr_pages = npages; dimm->grain = 32; dimm->dtype = (priv->mtr[chan][rank].width == 4) ? diff --git a/include/linux/edac.h b/include/linux/edac.h index f4ebb14bc406..31f99d48b024 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -599,6 +599,13 @@ struct mem_ctl_info { u16 fake_inject_count; }; +#define mci_for_each_dimm(mci, dimm) \ + for ((dimm) = (mci)->dimms[0]; \ + (dimm); \ + (dimm) = (dimm)->idx + 1 < (mci)->tot_dimms \ + ? (mci)->dimms[(dimm)->idx + 1] \ + : NULL) + /** * edac_get_dimm_by_index - Get DIMM info at @index from a memory * controller -- cgit v1.2.3-71-gd317 From 98edb865bd3ee2a67e51e0d947208f3a2129a460 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Wed, 6 Nov 2019 09:33:18 +0000 Subject: EDAC: Remove misleading comment in struct edac_raw_error_desc There never has been such function edac_raw_error_desc_clean() and in function ghes_edac_report_mem_error() the whole struct is zero'ed including the string arrays. Remove that comment. Signed-off-by: Robert Richter Signed-off-by: Borislav Petkov Reviewed-by: Mauro Carvalho Chehab Cc: "linux-edac@vger.kernel.org" Cc: James Morse Cc: Tony Luck Link: https://lkml.kernel.org/r/20191106093239.25517-9-rrichter@marvell.com --- include/linux/edac.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index 31f99d48b024..cc31b9742684 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -457,15 +457,10 @@ struct errcount_attribute_data { * (typically, a memory controller error) */ struct edac_raw_error_desc { - /* - * NOTE: everything before grain won't be cleaned by - * edac_raw_error_desc_clean() - */ char location[LOCATION_SIZE]; char label[(EDAC_MC_LABEL_LEN + 1 + sizeof(OTHER_LABEL)) * EDAC_MAX_LABELS]; long grain; - /* the vars below and grain will be cleaned on every new error report */ u16 error_count; int top_layer; int mid_layer; -- cgit v1.2.3-71-gd317 From ffedbf0cba153c91a0da5d1280a5e639664c5ab3 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 8 Nov 2019 16:57:59 +0000 Subject: irqchip/gic-v3-its: Kill its->ite_size and use TYPER copy instead Now that we have a copy of TYPER in the ITS structure, rely on this to provide the same service as its->ite_size, which gets axed. Errata workarounds are now updating the cached fields instead of requiring a separate field in the ITS structure. Signed-off-by: Marc Zyngier Reviewed-by: Zenghui Yu Link: https://lore.kernel.org/r/20191027144234.8395-6-maz@kernel.org Link: https://lore.kernel.org/r/20191108165805.3071-6-maz@kernel.org --- drivers/irqchip/irq-gic-v3-its.c | 8 ++++---- include/linux/irqchip/arm-gic-v3.h | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 5bb3eacbbde4..c3a1e47e7836 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -6,6 +6,7 @@ #include #include +#include #include #include #include @@ -108,7 +109,6 @@ struct its_node { struct list_head its_device_list; u64 flags; unsigned long list_nr; - u32 ite_size; u32 device_ids; int numa_node; unsigned int msi_domain_flags; @@ -2453,7 +2453,7 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id, * sized as a power of two (and you need at least one bit...). */ nr_ites = max(2, nvecs); - sz = nr_ites * its->ite_size; + sz = nr_ites * (FIELD_GET(GITS_TYPER_ITT_ENTRY_SIZE, its->typer) + 1); sz = max(sz, ITS_ITT_ALIGN) + ITS_ITT_ALIGN - 1; itt = kzalloc_node(sz, GFP_KERNEL, its->numa_node); if (alloc_lpis) { @@ -3268,7 +3268,8 @@ static bool __maybe_unused its_enable_quirk_qdf2400_e0065(void *data) struct its_node *its = data; /* On QDF2400, the size of the ITE is 16Bytes */ - its->ite_size = 16; + its->typer &= ~GITS_TYPER_ITT_ENTRY_SIZE; + its->typer |= FIELD_PREP(GITS_TYPER_ITT_ENTRY_SIZE, 16 - 1); return true; } @@ -3637,7 +3638,6 @@ static int __init its_probe_one(struct resource *res, its->typer = typer; its->base = its_base; its->phys_base = res->start; - its->ite_size = GITS_TYPER_ITT_ENTRY_SIZE(typer); its->device_ids = GITS_TYPER_DEVBITS(typer); if (is_v4(its)) { if (!(typer & GITS_TYPER_VMOVP)) { diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 5cc10cf7cb3e..4bce7a904075 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -334,7 +334,7 @@ #define GITS_TYPER_PLPIS (1UL << 0) #define GITS_TYPER_VLPIS (1UL << 1) #define GITS_TYPER_ITT_ENTRY_SIZE_SHIFT 4 -#define GITS_TYPER_ITT_ENTRY_SIZE(r) ((((r) >> GITS_TYPER_ITT_ENTRY_SIZE_SHIFT) & 0xf) + 1) +#define GITS_TYPER_ITT_ENTRY_SIZE GENMASK_ULL(7, 4) #define GITS_TYPER_IDBITS_SHIFT 8 #define GITS_TYPER_DEVBITS_SHIFT 13 #define GITS_TYPER_DEVBITS(r) ((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1) -- cgit v1.2.3-71-gd317 From 576a83429757999f220f36f206044af2b9026672 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 8 Nov 2019 16:58:00 +0000 Subject: irqchip/gic-v3-its: Kill its->device_ids and use TYPER copy instead Now that we have a copy of TYPER in the ITS structure, rely on this to provide the same service as its->device_ids, which gets axed. Errata workarounds are now updating the cached fields instead of requiring a separate field in the ITS structure. Signed-off-by: Marc Zyngier Reviewed-by: Zenghui Yu Link: https://lore.kernel.org/r/20191027144234.8395-7-maz@kernel.org Link: https://lore.kernel.org/r/20191108165805.3071-7-maz@kernel.org --- drivers/irqchip/irq-gic-v3-its.c | 24 +++++++++++++----------- include/linux/irqchip/arm-gic-v3.h | 2 +- 2 files changed, 14 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index c3a1e47e7836..e8aeb07e1cb0 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -109,7 +109,6 @@ struct its_node { struct list_head its_device_list; u64 flags; unsigned long list_nr; - u32 device_ids; int numa_node; unsigned int msi_domain_flags; u32 pre_its_base; /* for Socionext Synquacer */ @@ -117,6 +116,7 @@ struct its_node { }; #define is_v4(its) (!!((its)->typer & GITS_TYPER_VLPIS)) +#define device_ids(its) (FIELD_GET(GITS_TYPER_DEVBITS, (its)->typer) + 1) #define ITS_ITT_ALIGN SZ_256 @@ -1956,9 +1956,9 @@ static bool its_parse_indirect_baser(struct its_node *its, if (new_order >= MAX_ORDER) { new_order = MAX_ORDER - 1; ids = ilog2(PAGE_ORDER_TO_SIZE(new_order) / (int)esz); - pr_warn("ITS@%pa: %s Table too large, reduce ids %u->%u\n", + pr_warn("ITS@%pa: %s Table too large, reduce ids %llu->%u\n", &its->phys_base, its_base_type_string[type], - its->device_ids, ids); + device_ids(its), ids); } *order = new_order; @@ -2004,7 +2004,7 @@ static int its_alloc_tables(struct its_node *its) case GITS_BASER_TYPE_DEVICE: indirect = its_parse_indirect_baser(its, baser, psz, &order, - its->device_ids); + device_ids(its)); break; case GITS_BASER_TYPE_VCPU: @@ -2395,7 +2395,7 @@ static bool its_alloc_device_table(struct its_node *its, u32 dev_id) /* Don't allow device id that exceeds ITS hardware limit */ if (!baser) - return (ilog2(dev_id) < its->device_ids); + return (ilog2(dev_id) < device_ids(its)); return its_alloc_table_entry(its, baser, dev_id); } @@ -3247,8 +3247,9 @@ static bool __maybe_unused its_enable_quirk_cavium_22375(void *data) { struct its_node *its = data; - /* erratum 22375: only alloc 8MB table size */ - its->device_ids = 0x14; /* 20 bits, 8MB */ + /* erratum 22375: only alloc 8MB table size (20 bits) */ + its->typer &= ~GITS_TYPER_DEVBITS; + its->typer |= FIELD_PREP(GITS_TYPER_DEVBITS, 20 - 1); its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_22375; return true; @@ -3303,8 +3304,10 @@ static bool __maybe_unused its_enable_quirk_socionext_synquacer(void *data) its->get_msi_base = its_irq_get_msi_base_pre_its; ids = ilog2(pre_its_window[1]) - 2; - if (its->device_ids > ids) - its->device_ids = ids; + if (device_ids(its) > ids) { + its->typer &= ~GITS_TYPER_DEVBITS; + its->typer |= FIELD_PREP(GITS_TYPER_DEVBITS, ids - 1); + } /* the pre-ITS breaks isolation, so disable MSI remapping */ its->msi_domain_flags &= ~IRQ_DOMAIN_FLAG_MSI_REMAP; @@ -3537,7 +3540,7 @@ static int its_init_vpe_domain(void) } /* Use the last possible DevID */ - devid = GENMASK(its->device_ids - 1, 0); + devid = GENMASK(device_ids(its) - 1, 0); vpe_proxy.dev = its_create_device(its, devid, entries, false); if (!vpe_proxy.dev) { kfree(vpe_proxy.vpes); @@ -3638,7 +3641,6 @@ static int __init its_probe_one(struct resource *res, its->typer = typer; its->base = its_base; its->phys_base = res->start; - its->device_ids = GITS_TYPER_DEVBITS(typer); if (is_v4(its)) { if (!(typer & GITS_TYPER_VMOVP)) { err = its_compute_its_list_map(res, its_base); diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 4bce7a904075..b6514e8893bf 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -337,7 +337,7 @@ #define GITS_TYPER_ITT_ENTRY_SIZE GENMASK_ULL(7, 4) #define GITS_TYPER_IDBITS_SHIFT 8 #define GITS_TYPER_DEVBITS_SHIFT 13 -#define GITS_TYPER_DEVBITS(r) ((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1) +#define GITS_TYPER_DEVBITS GENMASK_ULL(17, 13) #define GITS_TYPER_PTA (1UL << 19) #define GITS_TYPER_HCC_SHIFT 24 #define GITS_TYPER_HCC(r) (((r) >> GITS_TYPER_HCC_SHIFT) & 0xff) -- cgit v1.2.3-71-gd317 From 20b44b4de61f2887694981e8cae74fe1bf58f950 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Wed, 2 Oct 2019 19:25:21 +0800 Subject: irqchip: ingenic: Drop redundant irq_suspend / irq_resume functions The same behaviour can be obtained by using the IRQCHIP_MASK_ON_SUSPEND flag on the IRQ chip. Signed-off-by: Paul Cercueil Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/1570015525-27018-2-git-send-email-zhouyanjie@zoho.com --- drivers/irqchip/irq-ingenic.c | 24 +----------------------- include/linux/irqchip/ingenic.h | 14 -------------- 2 files changed, 1 insertion(+), 37 deletions(-) delete mode 100644 include/linux/irqchip/ingenic.h (limited to 'include/linux') diff --git a/drivers/irqchip/irq-ingenic.c b/drivers/irqchip/irq-ingenic.c index f126255b3260..06fa810e89bb 100644 --- a/drivers/irqchip/irq-ingenic.c +++ b/drivers/irqchip/irq-ingenic.c @@ -10,7 +10,6 @@ #include #include #include -#include #include #include #include @@ -50,26 +49,6 @@ static irqreturn_t intc_cascade(int irq, void *data) return IRQ_HANDLED; } -static void intc_irq_set_mask(struct irq_chip_generic *gc, uint32_t mask) -{ - struct irq_chip_regs *regs = &gc->chip_types->regs; - - writel(mask, gc->reg_base + regs->enable); - writel(~mask, gc->reg_base + regs->disable); -} - -void ingenic_intc_irq_suspend(struct irq_data *data) -{ - struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data); - intc_irq_set_mask(gc, gc->wake_active); -} - -void ingenic_intc_irq_resume(struct irq_data *data) -{ - struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data); - intc_irq_set_mask(gc, gc->mask_cache); -} - static struct irqaction intc_cascade_action = { .handler = intc_cascade, .name = "SoC intc cascade interrupt", @@ -127,8 +106,7 @@ static int __init ingenic_intc_of_init(struct device_node *node, ct->chip.irq_mask = irq_gc_mask_disable_reg; ct->chip.irq_mask_ack = irq_gc_mask_disable_reg; ct->chip.irq_set_wake = irq_gc_set_wake; - ct->chip.irq_suspend = ingenic_intc_irq_suspend; - ct->chip.irq_resume = ingenic_intc_irq_resume; + ct->chip.flags = IRQCHIP_MASK_ON_SUSPEND; irq_setup_generic_chip(gc, IRQ_MSK(32), 0, 0, IRQ_NOPROBE | IRQ_LEVEL); diff --git a/include/linux/irqchip/ingenic.h b/include/linux/irqchip/ingenic.h deleted file mode 100644 index 146558853ad4..000000000000 --- a/include/linux/irqchip/ingenic.h +++ /dev/null @@ -1,14 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (C) 2010, Lars-Peter Clausen - */ - -#ifndef __LINUX_IRQCHIP_INGENIC_H__ -#define __LINUX_IRQCHIP_INGENIC_H__ - -#include - -extern void ingenic_intc_irq_suspend(struct irq_data *data); -extern void ingenic_intc_irq_resume(struct irq_data *data); - -#endif -- cgit v1.2.3-71-gd317 From 25cb20a212a1f989385dfe23230817e69c62bee5 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Wed, 16 Oct 2019 16:57:53 +0200 Subject: PM / OPP: Support adjusting OPP voltages at runtime On some SoCs the Adaptive Voltage Scaling (AVS) technique is employed to optimize the operating voltage of a device. At a given frequency, the hardware monitors dynamic factors and either makes a suggestion for how much to adjust a voltage for the current frequency, or it automatically adjusts the voltage without software intervention. Add an API to the OPP library for the former case, so that AVS type devices can update the voltages for an OPP when the hardware determines the voltage should change. The assumption is that drivers like CPUfreq or devfreq will register for the OPP notifiers and adjust the voltage according to suggestions that AVS makes. This patch is derived from [1] submitted by Stephen. [1] https://lore.kernel.org/patchwork/patch/599279/ Signed-off-by: Stephen Boyd [Roger Lu: Changed to rcu less implementation] Signed-off-by: Roger Lu [s.nawrocki@samsung.com: added handling of OPP min/max voltage] Signed-off-by: Sylwester Nawrocki Signed-off-by: Viresh Kumar --- drivers/opp/core.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/pm_opp.h | 13 ++++++++++ 2 files changed, 82 insertions(+) (limited to 'include/linux') diff --git a/drivers/opp/core.c b/drivers/opp/core.c index 9ff0538ee83a..be7a7d332332 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -2102,6 +2102,75 @@ put_table: return r; } +/** + * dev_pm_opp_adjust_voltage() - helper to change the voltage of an OPP + * @dev: device for which we do this operation + * @freq: OPP frequency to adjust voltage of + * @u_volt: new OPP target voltage + * @u_volt_min: new OPP min voltage + * @u_volt_max: new OPP max voltage + * + * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the + * copy operation, returns 0 if no modifcation was done OR modification was + * successful. + */ +int dev_pm_opp_adjust_voltage(struct device *dev, unsigned long freq, + unsigned long u_volt, unsigned long u_volt_min, + unsigned long u_volt_max) + +{ + struct opp_table *opp_table; + struct dev_pm_opp *tmp_opp, *opp = ERR_PTR(-ENODEV); + int r = 0; + + /* Find the opp_table */ + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) { + r = PTR_ERR(opp_table); + dev_warn(dev, "%s: Device OPP not found (%d)\n", __func__, r); + return r; + } + + mutex_lock(&opp_table->lock); + + /* Do we have the frequency? */ + list_for_each_entry(tmp_opp, &opp_table->opp_list, node) { + if (tmp_opp->rate == freq) { + opp = tmp_opp; + break; + } + } + + if (IS_ERR(opp)) { + r = PTR_ERR(opp); + goto adjust_unlock; + } + + /* Is update really needed? */ + if (opp->supplies->u_volt == u_volt) + goto adjust_unlock; + + opp->supplies->u_volt = u_volt; + opp->supplies->u_volt_min = u_volt_min; + opp->supplies->u_volt_max = u_volt_max; + + dev_pm_opp_get(opp); + mutex_unlock(&opp_table->lock); + + /* Notify the voltage change of the OPP */ + blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_ADJUST_VOLTAGE, + opp); + + dev_pm_opp_put(opp); + goto adjust_put_table; + +adjust_unlock: + mutex_unlock(&opp_table->lock); +adjust_put_table: + dev_pm_opp_put_opp_table(opp_table); + return r; +} + /** * dev_pm_opp_enable() - Enable a specific OPP * @dev: device for which we do this operation diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index b8197ab014f2..747861816f4f 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -22,6 +22,7 @@ struct opp_table; enum dev_pm_opp_event { OPP_EVENT_ADD, OPP_EVENT_REMOVE, OPP_EVENT_ENABLE, OPP_EVENT_DISABLE, + OPP_EVENT_ADJUST_VOLTAGE, }; /** @@ -113,6 +114,10 @@ int dev_pm_opp_add(struct device *dev, unsigned long freq, void dev_pm_opp_remove(struct device *dev, unsigned long freq); void dev_pm_opp_remove_all_dynamic(struct device *dev); +int dev_pm_opp_adjust_voltage(struct device *dev, unsigned long freq, + unsigned long u_volt, unsigned long u_volt_min, + unsigned long u_volt_max); + int dev_pm_opp_enable(struct device *dev, unsigned long freq); int dev_pm_opp_disable(struct device *dev, unsigned long freq); @@ -242,6 +247,14 @@ static inline void dev_pm_opp_remove_all_dynamic(struct device *dev) { } +static inline int +dev_pm_opp_adjust_voltage(struct device *dev, unsigned long freq, + unsigned long u_volt, unsigned long u_volt_min, + unsigned long u_volt_max) +{ + return 0; +} + static inline int dev_pm_opp_enable(struct device *dev, unsigned long freq) { return 0; -- cgit v1.2.3-71-gd317 From 39d1e3340c73e8f7eb1d6a8cae561c255ca7b1b0 Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Thu, 7 Nov 2019 08:41:51 +0000 Subject: mtd: spi-nor: Fix clearing of QE bit on lock()/unlock() Make sure that when doing a lock() or an unlock() operation we don't clear the QE bit from Status Register 2. JESD216 revB or later offers information about the *default* Status Register commands to use (see BFPT DWORDS[15], bits 22:20). In this standard, Status Register 1 refers to the first data byte transferred on a Read Status (05h) or Write Status (01h) command. Status register 2 refers to the byte read using instruction 35h. Status register 2 is the second byte transferred in a Write Status (01h) command. Industry naming and definitions of these Status Registers may differ. The definitions are described in JESD216B, BFPT DWORDS[15], bits 22:20. There are cases in which writing only one byte to the Status Register 1 has the side-effect of clearing Status Register 2 and implicitly the Quad Enable bit. This side-effect is hit just by the BFPT_DWORD15_QER_SR2_BIT1_BUGGY and BFPT_DWORD15_QER_SR2_BIT1 cases. Suggested-by: Boris Brezillon Signed-off-by: Tudor Ambarus Reviewed-by: Vignesh Raghavendra --- drivers/mtd/spi-nor/spi-nor.c | 120 ++++++++++++++++++++++++++++++++++++++++-- include/linux/mtd/spi-nor.h | 3 ++ 2 files changed, 118 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 9960e09136ce..d696334f25f0 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -959,12 +959,19 @@ static int spi_nor_write_sr(struct spi_nor *nor, const u8 *sr, size_t len) return spi_nor_wait_till_ready(nor); } -/* Write status register and ensure bits in mask match written values */ -static int spi_nor_write_sr_and_check(struct spi_nor *nor, u8 status_new) +/** + * spi_nor_write_sr1_and_check() - Write one byte to the Status Register 1 and + * ensure that the byte written match the received value. + * @nor: pointer to a 'struct spi_nor'. + * @sr1: byte value to be written to the Status Register. + * + * Return: 0 on success, -errno otherwise. + */ +static int spi_nor_write_sr1_and_check(struct spi_nor *nor, u8 sr1) { int ret; - nor->bouncebuf[0] = status_new; + nor->bouncebuf[0] = sr1; ret = spi_nor_write_sr(nor, nor->bouncebuf, 1); if (ret) @@ -974,14 +981,96 @@ static int spi_nor_write_sr_and_check(struct spi_nor *nor, u8 status_new) if (ret) return ret; - if (nor->bouncebuf[0] != status_new) { - dev_dbg(nor->dev, "SR: read back test failed\n"); + if (nor->bouncebuf[0] != sr1) { + dev_dbg(nor->dev, "SR1: read back test failed\n"); + return -EIO; + } + + return 0; +} + +/** + * spi_nor_write_16bit_sr_and_check() - Write the Status Register 1 and the + * Status Register 2 in one shot. Ensure that the byte written in the Status + * Register 1 match the received value, and that the 16-bit Write did not + * affect what was already in the Status Register 2. + * @nor: pointer to a 'struct spi_nor'. + * @sr1: byte value to be written to the Status Register 1. + * + * Return: 0 on success, -errno otherwise. + */ +static int spi_nor_write_16bit_sr_and_check(struct spi_nor *nor, u8 sr1) +{ + int ret; + u8 *sr_cr = nor->bouncebuf; + u8 cr_written; + + /* Make sure we don't overwrite the contents of Status Register 2. */ + if (!(nor->flags & SNOR_F_NO_READ_CR)) { + ret = spi_nor_read_cr(nor, &sr_cr[1]); + if (ret) + return ret; + } else if (nor->params.quad_enable) { + /* + * If the Status Register 2 Read command (35h) is not + * supported, we should at least be sure we don't + * change the value of the SR2 Quad Enable bit. + * + * We can safely assume that when the Quad Enable method is + * set, the value of the QE bit is one, as a consequence of the + * nor->params.quad_enable() call. + * + * We can safely assume that the Quad Enable bit is present in + * the Status Register 2 at BIT(1). According to the JESD216 + * revB standard, BFPT DWORDS[15], bits 22:20, the 16-bit + * Write Status (01h) command is available just for the cases + * in which the QE bit is described in SR2 at BIT(1). + */ + sr_cr[1] = CR_QUAD_EN_SPAN; + } else { + sr_cr[1] = 0; + } + + sr_cr[0] = sr1; + + ret = spi_nor_write_sr(nor, sr_cr, 2); + if (ret) + return ret; + + if (nor->flags & SNOR_F_NO_READ_CR) + return 0; + + cr_written = sr_cr[1]; + + ret = spi_nor_read_cr(nor, &sr_cr[1]); + if (ret) + return ret; + + if (cr_written != sr_cr[1]) { + dev_dbg(nor->dev, "CR: read back test failed\n"); return -EIO; } return 0; } +/** + * spi_nor_write_sr_and_check() - Write the Status Register 1 and ensure that + * the byte written match the received value without affecting other bits in the + * Status Register 1 and 2. + * @nor: pointer to a 'struct spi_nor'. + * @sr1: byte value to be written to the Status Register. + * + * Return: 0 on success, -errno otherwise. + */ +static int spi_nor_write_sr_and_check(struct spi_nor *nor, u8 sr1) +{ + if (nor->flags & SNOR_F_HAS_16BIT_SR) + return spi_nor_write_16bit_sr_and_check(nor, sr1); + + return spi_nor_write_sr1_and_check(nor, sr1); +} + /** * spi_nor_write_sr2() - Write the Status Register 2 using the * SPINOR_OP_WRSR2 (3eh) command. @@ -3634,19 +3723,38 @@ static int spi_nor_parse_bfpt(struct spi_nor *nor, break; case BFPT_DWORD15_QER_SR2_BIT1_BUGGY: + /* + * Writing only one byte to the Status Register has the + * side-effect of clearing Status Register 2. + */ case BFPT_DWORD15_QER_SR2_BIT1_NO_RD: + /* + * Read Configuration Register (35h) instruction is not + * supported. + */ + nor->flags |= SNOR_F_HAS_16BIT_SR | SNOR_F_NO_READ_CR; params->quad_enable = spansion_no_read_cr_quad_enable; break; case BFPT_DWORD15_QER_SR1_BIT6: + nor->flags &= ~SNOR_F_HAS_16BIT_SR; params->quad_enable = macronix_quad_enable; break; case BFPT_DWORD15_QER_SR2_BIT7: + nor->flags &= ~SNOR_F_HAS_16BIT_SR; params->quad_enable = sr2_bit7_quad_enable; break; case BFPT_DWORD15_QER_SR2_BIT1: + /* + * JESD216 rev B or later does not specify if writing only one + * byte to the Status Register clears or not the Status + * Register 2, so let's be cautious and keep the default + * assumption of a 16-bit Write Status (01h) command. + */ + nor->flags |= SNOR_F_HAS_16BIT_SR; + params->quad_enable = spansion_read_cr_quad_enable; break; @@ -4613,6 +4721,8 @@ static void spi_nor_info_init_params(struct spi_nor *nor) params->quad_enable = spansion_read_cr_quad_enable; params->set_4byte = spansion_set_4byte; params->setup = spi_nor_default_setup; + /* Default to 16-bit Write Status (01h) Command */ + nor->flags |= SNOR_F_HAS_16BIT_SR; /* Set SPI NOR sizes. */ params->size = (u64)info->sector_size * info->n_sectors; diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index d1d736d3c8ab..d6ec55cc6d97 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -243,6 +243,9 @@ enum spi_nor_option_flags { SNOR_F_4B_OPCODES = BIT(6), SNOR_F_HAS_4BAIT = BIT(7), SNOR_F_HAS_LOCK = BIT(8), + SNOR_F_HAS_16BIT_SR = BIT(9), + SNOR_F_NO_READ_CR = BIT(10), + }; /** -- cgit v1.2.3-71-gd317 From 3e0930f109e76922ea1742a9c8c1cc16f052ad45 Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Thu, 7 Nov 2019 08:41:55 +0000 Subject: mtd: spi-nor: Rework the disabling of block write protection spi_nor_unlock() unlocks blocks of memory or the entire flash memory array, if requested. clear_sr_bp() unlocks the entire flash memory array at boot time. This calls for some unification, clear_sr_bp() is just an optimization for the case when the unlock request covers the entire flash size. Get rid of clear_sr_bp() and introduce spi_nor_unlock_all(), which is just a call to spi_nor_unlock() for the entire flash memory array. This fixes a bug that was present in spi_nor_spansion_clear_sr_bp(). When the QE bit was zero, we used the Write Status (01h) command with one data byte, which might cleared the Status Register 2. We now always use the Write Status (01h) command with two data bytes when SNOR_F_HAS_16BIT_SR is set, to avoid clearing the Status Register 2. The SNOR_F_NO_READ_CR case is treated as well. When the flash doesn't support the CR Read command, we make an assumption about the value of the QE bit. In spi_nor_init(), call spi_nor_quad_enable() first, then spi_nor_unlock_all(), so that at the spi_nor_unlock_all() time we can be sure the QE bit has value one, because of the previous call to spi_nor_quad_enable(). Get rid of the MFR handling and implement specific manufacturer default_init() fixup hooks. Note that this changes a bit the logic for the SNOR_MFR_ATMEL, SNOR_MFR_INTEL and SNOR_MFR_SST cases. Before this patch, the Atmel, Intel and SST chips did not set the locking ops, but unlocked the entire flash at boot time, while now they are setting the locking ops to stm_locking_ops. This should work, since the disable of the block protection at the boot time used the same Status Register bits to unlock the flash, as in the stm_locking_ops case. Suggested-by: Boris Brezillon Signed-off-by: Tudor Ambarus Reviewed-by: Vignesh Raghavendra --- drivers/mtd/spi-nor/spi-nor.c | 140 +++++++++++++++--------------------------- include/linux/mtd/spi-nor.h | 3 - 2 files changed, 50 insertions(+), 93 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index d696334f25f0..06aac894ee6d 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -2185,74 +2185,6 @@ static int sr2_bit7_quad_enable(struct spi_nor *nor) return 0; } -/** - * spi_nor_clear_sr_bp() - clear the Status Register Block Protection bits. - * @nor: pointer to a 'struct spi_nor' - * - * Read-modify-write function that clears the Block Protection bits from the - * Status Register without affecting other bits. - * - * Return: 0 on success, -errno otherwise. - */ -static int spi_nor_clear_sr_bp(struct spi_nor *nor) -{ - int ret; - u8 mask = SR_BP2 | SR_BP1 | SR_BP0; - - ret = spi_nor_read_sr(nor, nor->bouncebuf); - if (ret) - return ret; - - nor->bouncebuf[0] &= ~mask; - - return spi_nor_write_sr(nor, nor->bouncebuf, 1); -} - -/** - * spi_nor_spansion_clear_sr_bp() - clear the Status Register Block Protection - * bits on spansion flashes. - * @nor: pointer to a 'struct spi_nor' - * - * Read-modify-write function that clears the Block Protection bits from the - * Status Register without affecting other bits. The function is tightly - * coupled with the spansion_read_cr_quad_enable() function. Both assume that - * the Write Register with 16 bits, together with the Read Configuration - * Register (35h) instructions are supported. - * - * Return: 0 on success, -errno otherwise. - */ -static int spi_nor_spansion_clear_sr_bp(struct spi_nor *nor) -{ - int ret; - u8 mask = SR_BP2 | SR_BP1 | SR_BP0; - u8 *sr_cr = nor->bouncebuf; - - /* Check current Quad Enable bit value. */ - ret = spi_nor_read_cr(nor, &sr_cr[1]); - if (ret) - return ret; - - /* - * When the configuration register Quad Enable bit is one, only the - * Write Status (01h) command with two data bytes may be used. - */ - if (sr_cr[1] & CR_QUAD_EN_SPAN) { - ret = spi_nor_read_sr(nor, sr_cr); - if (ret) - return ret; - - sr_cr[0] &= ~mask; - - return spi_nor_write_sr(nor, sr_cr, 2); - } - - /* - * If the Quad Enable bit is zero, use the Write Status (01h) command - * with one data byte. - */ - return spi_nor_clear_sr_bp(nor); -} - /* Used when the "_ext_id" is two bytes at most */ #define INFO(_jedec_id, _ext_id, _sector_size, _n_sectors, _flags) \ .id = { \ @@ -4634,12 +4566,27 @@ static int spi_nor_setup(struct spi_nor *nor, return nor->params.setup(nor, hwcaps); } +static void atmel_set_default_init(struct spi_nor *nor) +{ + nor->flags |= SNOR_F_HAS_LOCK; +} + +static void intel_set_default_init(struct spi_nor *nor) +{ + nor->flags |= SNOR_F_HAS_LOCK; +} + static void macronix_set_default_init(struct spi_nor *nor) { nor->params.quad_enable = macronix_quad_enable; nor->params.set_4byte = macronix_set_4byte; } +static void sst_set_default_init(struct spi_nor *nor) +{ + nor->flags |= SNOR_F_HAS_LOCK; +} + static void st_micron_set_default_init(struct spi_nor *nor) { nor->flags |= SNOR_F_HAS_LOCK; @@ -4661,6 +4608,14 @@ static void spi_nor_manufacturer_init_params(struct spi_nor *nor) { /* Init flash parameters based on MFR */ switch (JEDEC_MFR(nor->info)) { + case SNOR_MFR_ATMEL: + atmel_set_default_init(nor); + break; + + case SNOR_MFR_INTEL: + intel_set_default_init(nor); + break; + case SNOR_MFR_MACRONIX: macronix_set_default_init(nor); break; @@ -4670,6 +4625,10 @@ static void spi_nor_manufacturer_init_params(struct spi_nor *nor) st_micron_set_default_init(nor); break; + case SNOR_MFR_SST: + sst_set_default_init(nor); + break; + case SNOR_MFR_WINBOND: winbond_set_default_init(nor); break; @@ -4930,21 +4889,26 @@ static int spi_nor_quad_enable(struct spi_nor *nor) return nor->params.quad_enable(nor); } -static int spi_nor_init(struct spi_nor *nor) +/** + * spi_nor_unlock_all() - Unlocks the entire flash memory array. + * @nor: pointer to a 'struct spi_nor'. + * + * Some SPI NOR flashes are write protected by default after a power-on reset + * cycle, in order to avoid inadvertent writes during power-up. Backward + * compatibility imposes to unlock the entire flash memory array at power-up + * by default. + */ +static int spi_nor_unlock_all(struct spi_nor *nor) { - int err; + if (nor->flags & SNOR_F_HAS_LOCK) + return spi_nor_unlock(&nor->mtd, 0, nor->params.size); - if (nor->clear_sr_bp) { - if (nor->params.quad_enable == spansion_read_cr_quad_enable) - nor->clear_sr_bp = spi_nor_spansion_clear_sr_bp; + return 0; +} - err = nor->clear_sr_bp(nor); - if (err) { - dev_dbg(nor->dev, - "fail to clear block protection bits\n"); - return err; - } - } +static int spi_nor_init(struct spi_nor *nor) +{ + int err; err = spi_nor_quad_enable(nor); if (err) { @@ -4952,6 +4916,12 @@ static int spi_nor_init(struct spi_nor *nor) return err; } + err = spi_nor_unlock_all(nor); + if (err) { + dev_dbg(nor->dev, "Failed to unlock the entire flash memory array\n"); + return err; + } + if (nor->addr_width == 4 && !(nor->flags & SNOR_F_4B_OPCODES)) { /* * If the RESET# pin isn't hooked up properly, or the system @@ -5134,16 +5104,6 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, if (info->flags & SPI_NOR_HAS_LOCK) nor->flags |= SNOR_F_HAS_LOCK; - /* - * Atmel, SST, Intel/Numonyx, and others serial NOR tend to power up - * with the software protection bits set. - */ - if (JEDEC_MFR(nor->info) == SNOR_MFR_ATMEL || - JEDEC_MFR(nor->info) == SNOR_MFR_INTEL || - JEDEC_MFR(nor->info) == SNOR_MFR_SST || - nor->info->flags & SPI_NOR_HAS_LOCK) - nor->clear_sr_bp = spi_nor_clear_sr_bp; - /* Init flash parameters based on flash_info struct and SFDP */ spi_nor_init_params(nor); diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index d6ec55cc6d97..11daecc5a83d 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -581,8 +581,6 @@ struct flash_info; * @write_proto: the SPI protocol for write operations * @reg_proto the SPI protocol for read_reg/write_reg/erase operations * @controller_ops: SPI NOR controller driver specific operations. - * @clear_sr_bp: [FLASH-SPECIFIC] clears the Block Protection Bits from - * the SPI NOR Status Register. * @params: [FLASH-SPECIFIC] SPI-NOR flash parameters and settings. * The structure includes legacy flash parameters and * settings that can be overwritten by the spi_nor_fixups @@ -611,7 +609,6 @@ struct spi_nor { const struct spi_nor_controller_ops *controller_ops; - int (*clear_sr_bp)(struct spi_nor *nor); struct spi_nor_flash_parameter params; void *priv; -- cgit v1.2.3-71-gd317 From bb2dc7f46ad897ba1c2d8ae773c77601ba240932 Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Thu, 7 Nov 2019 08:42:01 +0000 Subject: mtd: spi-nor: Rename CR_QUAD_EN_SPAN to SR2_QUAD_EN_BIT1 JEDEC Basic Flash Parameter Table, 15th DWORD, bits 22:20, refers to this bit as "bit 1 of the status register 2". Rename the macro accordingly. Signed-off-by: Tudor Ambarus Reviewed-by: Vignesh Raghavendra --- drivers/mtd/spi-nor/spi-nor.c | 8 ++++---- include/linux/mtd/spi-nor.h | 4 +--- 2 files changed, 5 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index d33ad56d3b67..8c59b5220e2a 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -1026,7 +1026,7 @@ static int spi_nor_write_16bit_sr_and_check(struct spi_nor *nor, u8 sr1) * Write Status (01h) command is available just for the cases * in which the QE bit is described in SR2 at BIT(1). */ - sr_cr[1] = CR_QUAD_EN_SPAN; + sr_cr[1] = SR2_QUAD_EN_BIT1; } else { sr_cr[1] = 0; } @@ -2074,7 +2074,7 @@ static int spansion_no_read_cr_quad_enable(struct spi_nor *nor) if (ret) return ret; - sr_cr[1] = CR_QUAD_EN_SPAN; + sr_cr[1] = SR2_QUAD_EN_BIT1; ret = spi_nor_write_sr(nor, sr_cr, 2); if (ret) @@ -2118,10 +2118,10 @@ static int spansion_read_cr_quad_enable(struct spi_nor *nor) if (ret) return ret; - if (sr_cr[1] & CR_QUAD_EN_SPAN) + if (sr_cr[1] & SR2_QUAD_EN_BIT1) return 0; - sr_cr[1] |= CR_QUAD_EN_SPAN; + sr_cr[1] |= SR2_QUAD_EN_BIT1; /* Keep the current value of the Status Register. */ ret = spi_nor_read_sr(nor, sr_cr); diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 11daecc5a83d..364309845de0 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -144,10 +144,8 @@ #define FSR_P_ERR BIT(4) /* Program operation status */ #define FSR_PT_ERR BIT(1) /* Protection error bit */ -/* Configuration Register bits. */ -#define CR_QUAD_EN_SPAN BIT(1) /* Spansion Quad I/O */ - /* Status Register 2 bits. */ +#define SR2_QUAD_EN_BIT1 BIT(1) #define SR2_QUAD_EN_BIT7 BIT(7) /* Supported SPI protocols */ -- cgit v1.2.3-71-gd317 From 658488ed2108f5772572c5a17c3f31ed6e554edc Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Thu, 7 Nov 2019 08:42:09 +0000 Subject: mtd: spi-nor: Rename Quad Enable methods Rename macronix_quad_enable() to a generic name: spi_nor_sr1_bit6_quad_enable(). Prepend "spi_nor_" to "sr2_bit7_quad_enable". All SPI NOR generic methods should be prepended by "spi_nor_". Signed-off-by: Tudor Ambarus Reviewed-by: Vignesh Raghavendra --- drivers/mtd/spi-nor/spi-nor.c | 25 ++++++++++++------------- include/linux/mtd/spi-nor.h | 2 +- 2 files changed, 13 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 16fb3c7d0daf..824649eecd59 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -2078,16 +2078,15 @@ static int spi_nor_is_locked(struct mtd_info *mtd, loff_t ofs, uint64_t len) } /** - * macronix_quad_enable() - set QE bit in Status Register. + * spi_nor_sr1_bit6_quad_enable() - Set the Quad Enable BIT(6) in the Status + * Register 1. * @nor: pointer to a 'struct spi_nor' * - * Set the Quad Enable (QE) bit in the Status Register. - * - * bit 6 of the Status Register is the QE bit for Macronix like QSPI memories. + * Bit 6 of the Status Register 1 is the QE bit for Macronix like QSPI memories. * * Return: 0 on success, -errno otherwise. */ -static int macronix_quad_enable(struct spi_nor *nor) +static int spi_nor_sr1_bit6_quad_enable(struct spi_nor *nor) { int ret; @@ -2095,10 +2094,10 @@ static int macronix_quad_enable(struct spi_nor *nor) if (ret) return ret; - if (nor->bouncebuf[0] & SR_QUAD_EN_MX) + if (nor->bouncebuf[0] & SR1_QUAD_EN_BIT6) return 0; - nor->bouncebuf[0] |= SR_QUAD_EN_MX; + nor->bouncebuf[0] |= SR1_QUAD_EN_BIT6; return spi_nor_write_sr1_and_check(nor, nor->bouncebuf[0]); } @@ -2130,7 +2129,7 @@ static int spi_nor_sr2_bit1_quad_enable(struct spi_nor *nor) } /** - * sr2_bit7_quad_enable() - set QE bit in Status Register 2. + * spi_nor_sr2_bit7_quad_enable() - set QE bit in Status Register 2. * @nor: pointer to a 'struct spi_nor' * * Set the Quad Enable (QE) bit in the Status Register 2. @@ -2141,7 +2140,7 @@ static int spi_nor_sr2_bit1_quad_enable(struct spi_nor *nor) * * Return: 0 on success, -errno otherwise. */ -static int sr2_bit7_quad_enable(struct spi_nor *nor) +static int spi_nor_sr2_bit7_quad_enable(struct spi_nor *nor) { u8 *sr2 = nor->bouncebuf; int ret; @@ -2281,7 +2280,7 @@ static void gd25q256_default_init(struct spi_nor *nor) * indicate the quad_enable method for this case, we need * to set it in the default_init fixup hook. */ - nor->params.quad_enable = macronix_quad_enable; + nor->params.quad_enable = spi_nor_sr1_bit6_quad_enable; } static struct spi_nor_fixups gd25q256_fixups = { @@ -3661,12 +3660,12 @@ static int spi_nor_parse_bfpt(struct spi_nor *nor, case BFPT_DWORD15_QER_SR1_BIT6: nor->flags &= ~SNOR_F_HAS_16BIT_SR; - params->quad_enable = macronix_quad_enable; + params->quad_enable = spi_nor_sr1_bit6_quad_enable; break; case BFPT_DWORD15_QER_SR2_BIT7: nor->flags &= ~SNOR_F_HAS_16BIT_SR; - params->quad_enable = sr2_bit7_quad_enable; + params->quad_enable = spi_nor_sr2_bit7_quad_enable; break; case BFPT_DWORD15_QER_SR2_BIT1: @@ -4569,7 +4568,7 @@ static void intel_set_default_init(struct spi_nor *nor) static void macronix_set_default_init(struct spi_nor *nor) { - nor->params.quad_enable = macronix_quad_enable; + nor->params.quad_enable = spi_nor_sr1_bit6_quad_enable; nor->params.set_4byte = macronix_set_4byte; } diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 364309845de0..9eae35c60bce 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -133,7 +133,7 @@ #define SR_E_ERR BIT(5) #define SR_P_ERR BIT(6) -#define SR_QUAD_EN_MX BIT(6) /* Macronix Quad I/O */ +#define SR1_QUAD_EN_BIT6 BIT(6) /* Enhanced Volatile Configuration Register bits */ #define EVCR_QUAD_EN_MICRON BIT(7) /* Micron Quad I/O */ -- cgit v1.2.3-71-gd317 From 153bedbac2ebd475e1c7c2d2fa0c042f5525927d Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 8 Nov 2019 17:08:55 +0100 Subject: irq_work: Convert flags to atomic_t We need to convert flags to atomic_t in order to later fix an ordering issue on atomic_cmpxchg() failure. This will allow us to use atomic_fetch_or(). Also clarify the nature of those flags. [ mingo: Converted two more usage site the original patch missed. ] Signed-off-by: Frederic Weisbecker Cc: Linus Torvalds Cc: Paul E . McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20191108160858.31665-2-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/irq_work.h | 10 +++++++--- kernel/bpf/stackmap.c | 2 +- kernel/irq_work.c | 18 +++++++++--------- kernel/printk/printk.c | 2 +- kernel/trace/bpf_trace.c | 2 +- 5 files changed, 19 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index b11fcdfd0770..02da997ad12c 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -22,7 +22,7 @@ #define IRQ_WORK_CLAIMED (IRQ_WORK_PENDING | IRQ_WORK_BUSY) struct irq_work { - unsigned long flags; + atomic_t flags; struct llist_node llnode; void (*func)(struct irq_work *); }; @@ -30,11 +30,15 @@ struct irq_work { static inline void init_irq_work(struct irq_work *work, void (*func)(struct irq_work *)) { - work->flags = 0; + atomic_set(&work->flags, 0); work->func = func; } -#define DEFINE_IRQ_WORK(name, _f) struct irq_work name = { .func = (_f), } +#define DEFINE_IRQ_WORK(name, _f) struct irq_work name = { \ + .flags = ATOMIC_INIT(0), \ + .func = (_f) \ +} + bool irq_work_queue(struct irq_work *work); bool irq_work_queue_on(struct irq_work *work, int cpu); diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 052580c33d26..4d31284095e2 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -289,7 +289,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, if (in_nmi()) { work = this_cpu_ptr(&up_read_work); - if (work->irq_work.flags & IRQ_WORK_BUSY) + if (atomic_read(&work->irq_work.flags) & IRQ_WORK_BUSY) /* cannot queue more up_read, fallback */ irq_work_busy = true; } diff --git a/kernel/irq_work.c b/kernel/irq_work.c index d42acaf81886..df0dbf4d859b 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -29,16 +29,16 @@ static DEFINE_PER_CPU(struct llist_head, lazy_list); */ static bool irq_work_claim(struct irq_work *work) { - unsigned long flags, oflags, nflags; + int flags, oflags, nflags; /* * Start with our best wish as a premise but only trust any * flag value after cmpxchg() result. */ - flags = work->flags & ~IRQ_WORK_PENDING; + flags = atomic_read(&work->flags) & ~IRQ_WORK_PENDING; for (;;) { nflags = flags | IRQ_WORK_CLAIMED; - oflags = cmpxchg(&work->flags, flags, nflags); + oflags = atomic_cmpxchg(&work->flags, flags, nflags); if (oflags == flags) break; if (oflags & IRQ_WORK_PENDING) @@ -61,7 +61,7 @@ void __weak arch_irq_work_raise(void) static void __irq_work_queue_local(struct irq_work *work) { /* If the work is "lazy", handle it from next tick if any */ - if (work->flags & IRQ_WORK_LAZY) { + if (atomic_read(&work->flags) & IRQ_WORK_LAZY) { if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) && tick_nohz_tick_stopped()) arch_irq_work_raise(); @@ -143,7 +143,7 @@ static void irq_work_run_list(struct llist_head *list) { struct irq_work *work, *tmp; struct llist_node *llnode; - unsigned long flags; + int flags; BUG_ON(!irqs_disabled()); @@ -159,15 +159,15 @@ static void irq_work_run_list(struct llist_head *list) * to claim that work don't rely on us to handle their data * while we are in the middle of the func. */ - flags = work->flags & ~IRQ_WORK_PENDING; - xchg(&work->flags, flags); + flags = atomic_read(&work->flags) & ~IRQ_WORK_PENDING; + atomic_xchg(&work->flags, flags); work->func(work); /* * Clear the BUSY bit and return to the free state if * no-one else claimed it meanwhile. */ - (void)cmpxchg(&work->flags, flags, flags & ~IRQ_WORK_BUSY); + (void)atomic_cmpxchg(&work->flags, flags, flags & ~IRQ_WORK_BUSY); } } @@ -199,7 +199,7 @@ void irq_work_sync(struct irq_work *work) { lockdep_assert_irqs_enabled(); - while (work->flags & IRQ_WORK_BUSY) + while (atomic_read(&work->flags) & IRQ_WORK_BUSY) cpu_relax(); } EXPORT_SYMBOL_GPL(irq_work_sync); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index ca65327a6de8..865727373a3b 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2961,7 +2961,7 @@ static void wake_up_klogd_work_func(struct irq_work *irq_work) static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = { .func = wake_up_klogd_work_func, - .flags = IRQ_WORK_LAZY, + .flags = ATOMIC_INIT(IRQ_WORK_LAZY), }; void wake_up_klogd(void) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 44bd08f2443b..ff467a4e2639 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -660,7 +660,7 @@ BPF_CALL_1(bpf_send_signal, u32, sig) return -EINVAL; work = this_cpu_ptr(&send_signal_work); - if (work->irq_work.flags & IRQ_WORK_BUSY) + if (atomic_read(&work->irq_work.flags) & IRQ_WORK_BUSY) return -EBUSY; /* Add the current task, which is the target of sending signal, -- cgit v1.2.3-71-gd317 From e537654b7039aacfe8ae629d49655c0e5692ad44 Mon Sep 17 00:00:00 2001 From: Tuowen Zhao Date: Wed, 16 Oct 2019 15:06:28 -0600 Subject: lib: devres: add a helper function for ioremap_uc Implement a resource managed strongly uncachable ioremap function. Cc: # v4.19+ Tested-by: AceLan Kao Signed-off-by: Tuowen Zhao Acked-by: Mika Westerberg Acked-by: Andy Shevchenko Acked-by: Luis Chamberlain Signed-off-by: Lee Jones --- include/linux/io.h | 2 ++ lib/devres.c | 19 +++++++++++++++++++ 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/io.h b/include/linux/io.h index accac822336a..a59834bc0a11 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -64,6 +64,8 @@ static inline void devm_ioport_unmap(struct device *dev, void __iomem *addr) void __iomem *devm_ioremap(struct device *dev, resource_size_t offset, resource_size_t size); +void __iomem *devm_ioremap_uc(struct device *dev, resource_size_t offset, + resource_size_t size); void __iomem *devm_ioremap_nocache(struct device *dev, resource_size_t offset, resource_size_t size); void __iomem *devm_ioremap_wc(struct device *dev, resource_size_t offset, diff --git a/lib/devres.c b/lib/devres.c index 6a0e9bd6524a..17624d35e82d 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -9,6 +9,7 @@ enum devm_ioremap_type { DEVM_IOREMAP = 0, DEVM_IOREMAP_NC, + DEVM_IOREMAP_UC, DEVM_IOREMAP_WC, }; @@ -39,6 +40,9 @@ static void __iomem *__devm_ioremap(struct device *dev, resource_size_t offset, case DEVM_IOREMAP_NC: addr = ioremap_nocache(offset, size); break; + case DEVM_IOREMAP_UC: + addr = ioremap_uc(offset, size); + break; case DEVM_IOREMAP_WC: addr = ioremap_wc(offset, size); break; @@ -68,6 +72,21 @@ void __iomem *devm_ioremap(struct device *dev, resource_size_t offset, } EXPORT_SYMBOL(devm_ioremap); +/** + * devm_ioremap_uc - Managed ioremap_uc() + * @dev: Generic device to remap IO address for + * @offset: Resource address to map + * @size: Size of map + * + * Managed ioremap_uc(). Map is automatically unmapped on driver detach. + */ +void __iomem *devm_ioremap_uc(struct device *dev, resource_size_t offset, + resource_size_t size) +{ + return __devm_ioremap(dev, offset, size, DEVM_IOREMAP_UC); +} +EXPORT_SYMBOL_GPL(devm_ioremap_uc); + /** * devm_ioremap_nocache - Managed ioremap_nocache() * @dev: Generic device to remap IO address for -- cgit v1.2.3-71-gd317 From 37ef8c2c15bdc1322b160e38986c187de2b877b2 Mon Sep 17 00:00:00 2001 From: Daniel Schultz Date: Tue, 17 Sep 2019 10:12:53 +0200 Subject: mfd: rk808: Fix RK818 ID template The Rockchip PMIC driver can automatically detect connected component versions by reading the ID_MSB and ID_LSB registers. The probe function will always fail with RK818 PMICs because the ID_MSK is 0xFFF0 and the RK818 template ID is 0x8181. This patch changes this value to 0x8180. Fixes: 9d6105e19f61 ("mfd: rk808: Fix up the chip id get failed") Cc: stable@vger.kernel.org Cc: Elaine Zhang Cc: Joseph Chen Signed-off-by: Daniel Schultz Signed-off-by: Heiko Stuebner Signed-off-by: Lee Jones --- include/linux/mfd/rk808.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rk808.h b/include/linux/mfd/rk808.h index 7cfd2b0504df..a59bf323f713 100644 --- a/include/linux/mfd/rk808.h +++ b/include/linux/mfd/rk808.h @@ -610,7 +610,7 @@ enum { RK808_ID = 0x0000, RK809_ID = 0x8090, RK817_ID = 0x8170, - RK818_ID = 0x8181, + RK818_ID = 0x8180, }; struct rk808 { -- cgit v1.2.3-71-gd317 From 393f05f1d4651f7e4661a8739c381300dd9e39dc Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Tue, 9 Feb 2016 14:08:27 +0000 Subject: mfd: Provide MACRO to declare commonly defined MFD cell attributes Signed-off-by: Lee Jones Acked-by: Laxman Dewangan Tested-by: Laxman Dewangan --- include/linux/mfd/core.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index b43fc5773ad7..9a97e0932592 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -12,6 +12,35 @@ #include +#define MFD_RES_SIZE(arr) (sizeof(arr) / sizeof(struct resource)) + +#define MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, _compat, _match)\ + { \ + .name = (_name), \ + .resources = (_res), \ + .num_resources = MFD_RES_SIZE((_res)), \ + .platform_data = (_pdata), \ + .pdata_size = (_pdsize), \ + .of_compatible = (_compat), \ + .acpi_match = (_match), \ + .id = (_id), \ + } + +#define OF_MFD_CELL(_name, _res, _pdata, _pdsize,_id, _compat) \ + MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, _compat, NULL) \ + +#define ACPI_MFD_CELL(_name, _res, _pdata, _pdsize, _id, _match) \ + MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, NULL, _match) \ + +#define MFD_CELL_BASIC(_name, _res, _pdata, _pdsize, _id) \ + MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, NULL, NULL) \ + +#define MFD_CELL_RES(_name, _res) \ + MFD_CELL_ALL(_name, _res, NULL, 0, 0, NULL, NULL) \ + +#define MFD_CELL_NAME(_name) \ + MFD_CELL_ALL(_name, NULL, NULL, 0, 0, NULL, NULL) \ + struct irq_domain; struct property_entry; -- cgit v1.2.3-71-gd317 From 7f0e60c751dc7252276230c7f8def447ffc0af4e Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Wed, 2 Oct 2019 16:43:18 +0200 Subject: mfd: max77620: Do not allocate IRQs upfront regmap_add_irq_chip() will try to allocate all of the IRQ descriptors upfront if passed a non-zero irq_base parameter. However, the intention is to allocate IRQ descriptors on an as-needed basis if possible. Pass 0 instead of -1 to fix that use-case. Signed-off-by: Thierry Reding Signed-off-by: Lee Jones --- drivers/mfd/max77620.c | 5 ++--- include/linux/mfd/max77620.h | 1 - 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/max77620.c b/drivers/mfd/max77620.c index a851ff473a44..c7ed5c353553 100644 --- a/drivers/mfd/max77620.c +++ b/drivers/mfd/max77620.c @@ -507,7 +507,6 @@ static int max77620_probe(struct i2c_client *client, i2c_set_clientdata(client, chip); chip->dev = &client->dev; - chip->irq_base = -1; chip->chip_irq = client->irq; chip->chip_id = (enum max77620_chip_id)id->driver_data; @@ -545,8 +544,8 @@ static int max77620_probe(struct i2c_client *client, max77620_top_irq_chip.irq_drv_data = chip; ret = devm_regmap_add_irq_chip(chip->dev, chip->rmap, client->irq, - IRQF_ONESHOT | IRQF_SHARED, - chip->irq_base, &max77620_top_irq_chip, + IRQF_ONESHOT | IRQF_SHARED, 0, + &max77620_top_irq_chip, &chip->top_irq_data); if (ret < 0) { dev_err(chip->dev, "Failed to add regmap irq: %d\n", ret); diff --git a/include/linux/mfd/max77620.h b/include/linux/mfd/max77620.h index 12ba157cb83f..f552ef5b1100 100644 --- a/include/linux/mfd/max77620.h +++ b/include/linux/mfd/max77620.h @@ -329,7 +329,6 @@ struct max77620_chip { struct regmap *rmap; int chip_irq; - int irq_base; /* chip id */ enum max77620_chip_id chip_id; -- cgit v1.2.3-71-gd317 From cbfdc839ea913250bd38528408addf44b27e9e5f Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Sun, 13 Oct 2019 10:30:15 +0100 Subject: mfd: twl: Endian fixups in i2c write and read wrappers Use a local variable to ensure correct endian types for intermediate results. Identified by sparse when building the IIO driver. Signed-off-by: Jonathan Cameron Signed-off-by: Lee Jones --- include/linux/mfd/twl.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/twl.h b/include/linux/mfd/twl.h index 44aff52a5002..089e8942223a 100644 --- a/include/linux/mfd/twl.h +++ b/include/linux/mfd/twl.h @@ -181,14 +181,18 @@ static inline int twl_i2c_read_u8(u8 mod_no, u8 *val, u8 reg) { } static inline int twl_i2c_write_u16(u8 mod_no, u16 val, u8 reg) { - val = cpu_to_le16(val); - return twl_i2c_write(mod_no, (u8*) &val, reg, 2); + __le16 value; + + value = cpu_to_le16(val); + return twl_i2c_write(mod_no, (u8 *) &value, reg, 2); } static inline int twl_i2c_read_u16(u8 mod_no, u16 *val, u8 reg) { int ret; - ret = twl_i2c_read(mod_no, (u8*) val, reg, 2); - *val = le16_to_cpu(*val); + __le16 value; + + ret = twl_i2c_read(mod_no, (u8 *) &value, reg, 2); + *val = le16_to_cpu(value); return ret; } -- cgit v1.2.3-71-gd317 From 28eafe9162b6a8b7d0266889d55567ba5a7809d5 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Mon, 21 Oct 2019 14:58:11 +0100 Subject: mfd: wm8998: Remove some unused registers Save a few bytes by removing some registers from the driver that are not currently used and not intended to be used at any point in the future. Signed-off-by: Charles Keepax Signed-off-by: Lee Jones --- drivers/mfd/wm8998-tables.c | 12 ------------ include/linux/mfd/arizona/registers.h | 7 ------- 2 files changed, 19 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/wm8998-tables.c b/drivers/mfd/wm8998-tables.c index ebf0eadd2075..9b34a6d76094 100644 --- a/drivers/mfd/wm8998-tables.c +++ b/drivers/mfd/wm8998-tables.c @@ -806,12 +806,6 @@ static const struct reg_default wm8998_reg_default[] = { { 0x00000EF3, 0x0000 }, /* R3827 - ISRC 2 CTRL 1 */ { 0x00000EF4, 0x0001 }, /* R3828 - ISRC 2 CTRL 2 */ { 0x00000EF5, 0x0000 }, /* R3829 - ISRC 2 CTRL 3 */ - { 0x00001700, 0x0000 }, /* R5888 - FRF_COEFF_1 */ - { 0x00001701, 0x0000 }, /* R5889 - FRF_COEFF_2 */ - { 0x00001702, 0x0000 }, /* R5890 - FRF_COEFF_3 */ - { 0x00001703, 0x0000 }, /* R5891 - FRF_COEFF_4 */ - { 0x00001704, 0x0000 }, /* R5892 - DAC_COMP_1 */ - { 0x00001705, 0x0000 }, /* R5893 - DAC_COMP_2 */ }; static bool wm8998_readable_register(struct device *dev, unsigned int reg) @@ -1492,12 +1486,6 @@ static bool wm8998_readable_register(struct device *dev, unsigned int reg) case ARIZONA_ISRC_2_CTRL_1: case ARIZONA_ISRC_2_CTRL_2: case ARIZONA_ISRC_2_CTRL_3: - case ARIZONA_FRF_COEFF_1: - case ARIZONA_FRF_COEFF_2: - case ARIZONA_FRF_COEFF_3: - case ARIZONA_FRF_COEFF_4: - case ARIZONA_V2_DAC_COMP_1: - case ARIZONA_V2_DAC_COMP_2: return true; default: return false; diff --git a/include/linux/mfd/arizona/registers.h b/include/linux/mfd/arizona/registers.h index bb1a2530ae27..49e24d1de8d4 100644 --- a/include/linux/mfd/arizona/registers.h +++ b/include/linux/mfd/arizona/registers.h @@ -1186,13 +1186,6 @@ #define ARIZONA_DSP4_SCRATCH_1 0x1441 #define ARIZONA_DSP4_SCRATCH_2 0x1442 #define ARIZONA_DSP4_SCRATCH_3 0x1443 -#define ARIZONA_FRF_COEFF_1 0x1700 -#define ARIZONA_FRF_COEFF_2 0x1701 -#define ARIZONA_FRF_COEFF_3 0x1702 -#define ARIZONA_FRF_COEFF_4 0x1703 -#define ARIZONA_V2_DAC_COMP_1 0x1704 -#define ARIZONA_V2_DAC_COMP_2 0x1705 - /* * Field Definitions. -- cgit v1.2.3-71-gd317 From 1e624fce3a1ca03fcea167cc43399d0073472edc Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Mon, 21 Oct 2019 14:58:13 +0100 Subject: mfd: madera: Add support for requesting the supply clocks Add the ability to get the clock for each clock input pin of the chip and enable MCLK2 since that is expected to be a permanently enabled 32kHz clock. Signed-off-by: Charles Keepax Signed-off-by: Lee Jones --- drivers/mfd/madera-core.c | 27 ++++++++++++++++++++++++++- include/linux/mfd/madera/core.h | 11 +++++++++++ 2 files changed, 37 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/mfd/madera-core.c b/drivers/mfd/madera-core.c index 29540cbf7593..a8cfadc1fc01 100644 --- a/drivers/mfd/madera-core.c +++ b/drivers/mfd/madera-core.c @@ -450,6 +450,21 @@ int madera_dev_init(struct madera *madera) sizeof(madera->pdata)); } + madera->mclk[MADERA_MCLK1].id = "mclk1"; + madera->mclk[MADERA_MCLK2].id = "mclk2"; + madera->mclk[MADERA_MCLK3].id = "mclk3"; + + ret = devm_clk_bulk_get_optional(madera->dev, ARRAY_SIZE(madera->mclk), + madera->mclk); + if (ret) { + dev_err(madera->dev, "Failed to get clocks: %d\n", ret); + return ret; + } + + /* Not using devm_clk_get to prevent breakage of existing DTs */ + if (!madera->mclk[MADERA_MCLK2].clk) + dev_warn(madera->dev, "Missing MCLK2, requires 32kHz clock\n"); + ret = madera_get_reset_gpio(madera); if (ret) return ret; @@ -660,13 +675,19 @@ int madera_dev_init(struct madera *madera) } /* Init 32k clock sourced from MCLK2 */ + ret = clk_prepare_enable(madera->mclk[MADERA_MCLK2].clk); + if (ret) { + dev_err(madera->dev, "Failed to enable 32k clock: %d\n", ret); + goto err_reset; + } + ret = regmap_update_bits(madera->regmap, MADERA_CLOCK_32K_1, MADERA_CLK_32K_ENA_MASK | MADERA_CLK_32K_SRC_MASK, MADERA_CLK_32K_ENA | MADERA_32KZ_MCLK2); if (ret) { dev_err(madera->dev, "Failed to init 32k clock: %d\n", ret); - goto err_reset; + goto err_clock; } pm_runtime_set_active(madera->dev); @@ -687,6 +708,8 @@ int madera_dev_init(struct madera *madera) err_pm_runtime: pm_runtime_disable(madera->dev); +err_clock: + clk_disable_unprepare(madera->mclk[MADERA_MCLK2].clk); err_reset: madera_enable_hard_reset(madera); regulator_disable(madera->dcvdd); @@ -713,6 +736,8 @@ int madera_dev_exit(struct madera *madera) */ pm_runtime_disable(madera->dev); + clk_disable_unprepare(madera->mclk[MADERA_MCLK2].clk); + regulator_disable(madera->dcvdd); regulator_put(madera->dcvdd); diff --git a/include/linux/mfd/madera/core.h b/include/linux/mfd/madera/core.h index 7ffa696cce7c..ad2c138105d4 100644 --- a/include/linux/mfd/madera/core.h +++ b/include/linux/mfd/madera/core.h @@ -8,6 +8,7 @@ #ifndef MADERA_CORE_H #define MADERA_CORE_H +#include #include #include #include @@ -29,6 +30,13 @@ enum madera_type { CS42L92 = 9, }; +enum { + MADERA_MCLK1, + MADERA_MCLK2, + MADERA_MCLK3, + MADERA_NUM_MCLK +}; + #define MADERA_MAX_CORE_SUPPLIES 2 #define MADERA_MAX_GPIOS 40 @@ -155,6 +163,7 @@ struct snd_soc_dapm_context; * @irq_dev: the irqchip child driver device * @irq_data: pointer to irqchip data for the child irqchip driver * @irq: host irq number from SPI or I2C configuration + * @mclk: Structure holding clock supplies * @out_clamp: indicates output clamp state for each analogue output * @out_shorted: indicates short circuit state for each analogue output * @hp_ena: bitflags of enable state for the headphone outputs @@ -184,6 +193,8 @@ struct madera { struct regmap_irq_chip_data *irq_data; int irq; + struct clk_bulk_data mclk[MADERA_NUM_MCLK]; + unsigned int num_micbias; unsigned int num_childbias[MADERA_MAX_MICBIAS]; -- cgit v1.2.3-71-gd317 From ead1c83ddd7613d9e61368dc686d014e37955192 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Fri, 18 Oct 2019 13:31:39 +0100 Subject: mfd: mfd-core: Remove mfd_clone_cell() Providing a subsystem-level API helper seems over-kill just to save a few lines of C-code. Previous commits saw us convert mfd_clone_cell()'s only user over to use a more traditional style of MFD child-device registration. Now we can remove the superfluous helper from the MFD API. Signed-off-by: Lee Jones Reviewed-by: Daniel Thompson --- drivers/mfd/mfd-core.c | 33 --------------------------------- include/linux/mfd/core.h | 18 ------------------ 2 files changed, 51 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c index 96d02b6f06fd..e38e411ca775 100644 --- a/drivers/mfd/mfd-core.c +++ b/drivers/mfd/mfd-core.c @@ -392,38 +392,5 @@ int devm_mfd_add_devices(struct device *dev, int id, } EXPORT_SYMBOL(devm_mfd_add_devices); -int mfd_clone_cell(const char *cell, const char **clones, size_t n_clones) -{ - struct mfd_cell cell_entry; - struct device *dev; - struct platform_device *pdev; - int i; - - /* fetch the parent cell's device (should already be registered!) */ - dev = bus_find_device_by_name(&platform_bus_type, NULL, cell); - if (!dev) { - printk(KERN_ERR "failed to find device for cell %s\n", cell); - return -ENODEV; - } - pdev = to_platform_device(dev); - memcpy(&cell_entry, mfd_get_cell(pdev), sizeof(cell_entry)); - - WARN_ON(!cell_entry.enable); - - for (i = 0; i < n_clones; i++) { - cell_entry.name = clones[i]; - /* don't give up if a single call fails; just report error */ - if (mfd_add_device(pdev->dev.parent, -1, &cell_entry, - cell_entry.usage_count, NULL, 0, NULL)) - dev_err(dev, "failed to create platform device '%s'\n", - clones[i]); - } - - put_device(dev); - - return 0; -} -EXPORT_SYMBOL(mfd_clone_cell); - MODULE_LICENSE("GPL"); MODULE_AUTHOR("Ian Molton, Dmitry Baryshkov"); diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index 9a97e0932592..63ac3cc86608 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -115,24 +115,6 @@ struct mfd_cell { extern int mfd_cell_enable(struct platform_device *pdev); extern int mfd_cell_disable(struct platform_device *pdev); -/* - * "Clone" multiple platform devices for a single cell. This is to be used - * for devices that have multiple users of a cell. For example, if an mfd - * driver wants the cell "foo" to be used by a GPIO driver, an MTD driver, - * and a platform driver, the following bit of code would be use after first - * calling mfd_add_devices(): - * - * const char *fclones[] = { "foo-gpio", "foo-mtd" }; - * err = mfd_clone_cells("foo", fclones, ARRAY_SIZE(fclones)); - * - * Each driver (MTD, GPIO, and platform driver) would then register - * platform_drivers for "foo-mtd", "foo-gpio", and "foo", respectively. - * The cell's .enable/.disable hooks should be used to deal with hardware - * resource contention. - */ -extern int mfd_clone_cell(const char *cell, const char **clones, - size_t n_clones); - /* * Given a platform device that's been created by mfd_add_devices(), fetch * the mfd_cell that created it. -- cgit v1.2.3-71-gd317 From 5a47c0fbd276b7f57bd38f153e8b15784b2f6f22 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Mon, 21 Oct 2019 10:47:37 +0100 Subject: mfd: mfd-core: Remove usage counting for .{en,dis}able() call-backs The MFD implementation for reference counting was complex and unnecessary. There was only one bona fide user which has now been converted to handle the process in a different way. Any future resource protection, shared enablement functions should be handed by the parent device, rather than through the MFD subsystem API. Signed-off-by: Lee Jones Reviewed-by: Daniel Thompson Reviewed-by: Mark Brown --- drivers/mfd/mfd-core.c | 57 ++++++++---------------------------------------- include/linux/mfd/core.h | 2 -- 2 files changed, 9 insertions(+), 50 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c index e38e411ca775..2535dd3605c0 100644 --- a/drivers/mfd/mfd-core.c +++ b/drivers/mfd/mfd-core.c @@ -26,53 +26,31 @@ static struct device_type mfd_dev_type = { int mfd_cell_enable(struct platform_device *pdev) { const struct mfd_cell *cell = mfd_get_cell(pdev); - int err = 0; if (!cell->enable) { dev_dbg(&pdev->dev, "No .enable() call-back registered\n"); return 0; } - /* only call enable hook if the cell wasn't previously enabled */ - if (atomic_inc_return(cell->usage_count) == 1) - err = cell->enable(pdev); - - /* if the enable hook failed, decrement counter to allow retries */ - if (err) - atomic_dec(cell->usage_count); - - return err; + return cell->enable(pdev); } EXPORT_SYMBOL(mfd_cell_enable); int mfd_cell_disable(struct platform_device *pdev) { const struct mfd_cell *cell = mfd_get_cell(pdev); - int err = 0; if (!cell->disable) { dev_dbg(&pdev->dev, "No .disable() call-back registered\n"); return 0; } - /* only disable if no other clients are using it */ - if (atomic_dec_return(cell->usage_count) == 0) - err = cell->disable(pdev); - - /* if the disable hook failed, increment to allow retries */ - if (err) - atomic_inc(cell->usage_count); - - /* sanity check; did someone call disable too many times? */ - WARN_ON(atomic_read(cell->usage_count) < 0); - - return err; + return cell->disable(pdev); } EXPORT_SYMBOL(mfd_cell_disable); static int mfd_platform_add_cell(struct platform_device *pdev, - const struct mfd_cell *cell, - atomic_t *usage_count) + const struct mfd_cell *cell) { if (!cell) return 0; @@ -81,7 +59,6 @@ static int mfd_platform_add_cell(struct platform_device *pdev, if (!pdev->mfd_cell) return -ENOMEM; - pdev->mfd_cell->usage_count = usage_count; return 0; } @@ -144,7 +121,7 @@ static inline void mfd_acpi_add_device(const struct mfd_cell *cell, #endif static int mfd_add_device(struct device *parent, int id, - const struct mfd_cell *cell, atomic_t *usage_count, + const struct mfd_cell *cell, struct resource *mem_base, int irq_base, struct irq_domain *domain) { @@ -206,7 +183,7 @@ static int mfd_add_device(struct device *parent, int id, goto fail_alias; } - ret = mfd_platform_add_cell(pdev, cell, usage_count); + ret = mfd_platform_add_cell(pdev, cell); if (ret) goto fail_alias; @@ -296,16 +273,9 @@ int mfd_add_devices(struct device *parent, int id, { int i; int ret; - atomic_t *cnts; - - /* initialize reference counting for all cells */ - cnts = kcalloc(n_devs, sizeof(*cnts), GFP_KERNEL); - if (!cnts) - return -ENOMEM; for (i = 0; i < n_devs; i++) { - atomic_set(&cnts[i], 0); - ret = mfd_add_device(parent, id, cells + i, cnts + i, mem_base, + ret = mfd_add_device(parent, id, cells + i, mem_base, irq_base, domain); if (ret) goto fail; @@ -316,17 +286,15 @@ int mfd_add_devices(struct device *parent, int id, fail: if (i) mfd_remove_devices(parent); - else - kfree(cnts); + return ret; } EXPORT_SYMBOL(mfd_add_devices); -static int mfd_remove_devices_fn(struct device *dev, void *c) +static int mfd_remove_devices_fn(struct device *dev, void *data) { struct platform_device *pdev; const struct mfd_cell *cell; - atomic_t **usage_count = c; if (dev->type != &mfd_dev_type) return 0; @@ -337,20 +305,13 @@ static int mfd_remove_devices_fn(struct device *dev, void *c) regulator_bulk_unregister_supply_alias(dev, cell->parent_supplies, cell->num_parent_supplies); - /* find the base address of usage_count pointers (for freeing) */ - if (!*usage_count || (cell->usage_count < *usage_count)) - *usage_count = cell->usage_count; - platform_device_unregister(pdev); return 0; } void mfd_remove_devices(struct device *parent) { - atomic_t *cnts = NULL; - - device_for_each_child_reverse(parent, &cnts, mfd_remove_devices_fn); - kfree(cnts); + device_for_each_child_reverse(parent, NULL, mfd_remove_devices_fn); } EXPORT_SYMBOL(mfd_remove_devices); diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index 63ac3cc86608..d01d1299e49d 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -59,8 +59,6 @@ struct mfd_cell { const char *name; int id; - /* refcounting for multiple drivers to use a single cell */ - atomic_t *usage_count; int (*enable)(struct platform_device *dev); int (*disable)(struct platform_device *dev); -- cgit v1.2.3-71-gd317 From 22fb3ad0cc5f578398953ddcab9c8239a08caccd Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sat, 26 Oct 2019 23:47:32 +0200 Subject: mfd: db8500-prcmu: Support U8420-sysclk firmware There is a distinct version of the Ux500 U8420 variant with "sysclk", as can be seen from the vendor code that didn't make it upstream, this firmware lacks the ULPPLL (ultra-low power phase locked loop) which in effect means that the timer clock is instead wired to the 32768 Hz always-on clock. This has some repercussions when enabling the timer clock as the code as it stands will disable the timer clock on these platforms (lacking the so-called "doze mode") and obtaining the wrong rate of the timer clock. The timer frequency is of course needed very early in the boot, and as a consequence, we need to shuffle around the early PRCMU init code: whereas in the past we did not need to look up the PRCMU firmware version in the early init, but now we need to know the version before the core system timers are registered so we restructure the platform callbacks to the PRCMU so as not to take any arguments and instead look up the resources it needs directly from the device tree when initializing. As we do not yet support any platforms using this firmware it is not a regression, but as PostmarketOS is starting to support products with this firmware we need to fix this up. The low rate of 32kHz also makes the MTU timer unsuitable as delay timer but this needs to be fixed in a separate patch. Signed-off-by: Linus Walleij Reviewed-by: Stephan Gerhold Acked-by: Olof Johansson Signed-off-by: Lee Jones --- arch/arm/mach-ux500/cpu-db8500.c | 2 +- drivers/mfd/db8500-prcmu.c | 63 +++++++++++++++++++++++++++------------- include/linux/mfd/db8500-prcmu.h | 4 +-- include/linux/mfd/dbx500-prcmu.h | 7 +++-- 4 files changed, 50 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c index 3875027ef8fc..e929aaa744c0 100644 --- a/arch/arm/mach-ux500/cpu-db8500.c +++ b/arch/arm/mach-ux500/cpu-db8500.c @@ -84,6 +84,7 @@ static void __init ux500_init_irq(void) struct resource r; irqchip_init(); + prcmu_early_init(); np = of_find_compatible_node(NULL, NULL, "stericsson,db8500-prcmu"); of_address_to_resource(np, 0, &r); of_node_put(np); @@ -91,7 +92,6 @@ static void __init ux500_init_irq(void) pr_err("could not find PRCMU base resource\n"); return; } - prcmu_early_init(r.start, r.end-r.start); ux500_pm_init(r.start, r.end-r.start); /* Unlock before init */ diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c index 3972f910dd23..57ac58b4b5f3 100644 --- a/drivers/mfd/db8500-prcmu.c +++ b/drivers/mfd/db8500-prcmu.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -668,6 +669,14 @@ struct prcmu_fw_version *prcmu_get_fw_version(void) return fw_info.valid ? &fw_info.version : NULL; } +static bool prcmu_is_ulppll_disabled(void) +{ + struct prcmu_fw_version *ver; + + ver = prcmu_get_fw_version(); + return ver && ver->project == PRCMU_FW_PROJECT_U8420_SYSCLK; +} + bool prcmu_has_arm_maxopp(void) { return (readb(tcdm_base + PRCM_AVS_VARM_MAX_OPP) & @@ -1308,10 +1317,23 @@ static int request_sysclk(bool enable) static int request_timclk(bool enable) { - u32 val = (PRCM_TCR_DOZE_MODE | PRCM_TCR_TENSEL_MASK); + u32 val; + + /* + * On the U8420_CLKSEL firmware, the ULP (Ultra Low Power) + * PLL is disabled so we cannot use doze mode, this will + * stop the clock on this firmware. + */ + if (prcmu_is_ulppll_disabled()) + val = 0; + else + val = (PRCM_TCR_DOZE_MODE | PRCM_TCR_TENSEL_MASK); if (!enable) - val |= PRCM_TCR_STOP_TIMERS; + val |= PRCM_TCR_STOP_TIMERS | + PRCM_TCR_DOZE_MODE | + PRCM_TCR_TENSEL_MASK; + writel(val, PRCM_TCR); return 0; @@ -1615,7 +1637,8 @@ unsigned long prcmu_clock_rate(u8 clock) if (clock < PRCMU_NUM_REG_CLOCKS) return clock_rate(clock); else if (clock == PRCMU_TIMCLK) - return ROOT_CLOCK_RATE / 16; + return prcmu_is_ulppll_disabled() ? + 32768 : ROOT_CLOCK_RATE / 16; else if (clock == PRCMU_SYSCLK) return ROOT_CLOCK_RATE; else if (clock == PRCMU_PLLSOC0) @@ -2646,6 +2669,8 @@ static char *fw_project_name(u32 project) return "U8520 MBL"; case PRCMU_FW_PROJECT_U8420: return "U8420"; + case PRCMU_FW_PROJECT_U8420_SYSCLK: + return "U8420-sysclk"; case PRCMU_FW_PROJECT_U9540: return "U9540"; case PRCMU_FW_PROJECT_A9420: @@ -2693,27 +2718,18 @@ static int db8500_irq_init(struct device_node *np) return 0; } -static void dbx500_fw_version_init(struct platform_device *pdev, - u32 version_offset) +static void dbx500_fw_version_init(struct device_node *np) { - struct resource *res; void __iomem *tcpm_base; u32 version; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, - "prcmu-tcpm"); - if (!res) { - dev_err(&pdev->dev, - "Error: no prcmu tcpm memory region provided\n"); - return; - } - tcpm_base = ioremap(res->start, resource_size(res)); + tcpm_base = of_iomap(np, 1); if (!tcpm_base) { - dev_err(&pdev->dev, "no prcmu tcpm mem region provided\n"); + pr_err("no prcmu tcpm mem region provided\n"); return; } - version = readl(tcpm_base + version_offset); + version = readl(tcpm_base + DB8500_PRCMU_FW_VERSION_OFFSET); fw_info.version.project = (version & 0xFF); fw_info.version.api_version = (version >> 8) & 0xFF; fw_info.version.func_version = (version >> 16) & 0xFF; @@ -2731,7 +2747,7 @@ static void dbx500_fw_version_init(struct platform_device *pdev, iounmap(tcpm_base); } -void __init db8500_prcmu_early_init(u32 phy_base, u32 size) +void __init db8500_prcmu_early_init(void) { /* * This is a temporary remap to bring up the clocks. It is @@ -2740,9 +2756,17 @@ void __init db8500_prcmu_early_init(u32 phy_base, u32 size) * clock driver can probe independently. An early initcall will * still be needed, but it can be diverted into drivers/clk/ux500. */ - prcmu_base = ioremap(phy_base, size); - if (!prcmu_base) + struct device_node *np; + + np = of_find_compatible_node(NULL, NULL, "stericsson,db8500-prcmu"); + prcmu_base = of_iomap(np, 0); + if (!prcmu_base) { + of_node_put(np); pr_err("%s: ioremap() of prcmu registers failed!\n", __func__); + return; + } + dbx500_fw_version_init(np); + of_node_put(np); spin_lock_init(&mb0_transfer.lock); spin_lock_init(&mb0_transfer.dbb_irqs_lock); @@ -3084,7 +3108,6 @@ static int db8500_prcmu_probe(struct platform_device *pdev) return -ENOMEM; } init_prcm_registers(); - dbx500_fw_version_init(pdev, DB8500_PRCMU_FW_VERSION_OFFSET); res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "prcmu-tcdm"); if (!res) { dev_err(&pdev->dev, "no prcmu tcdm region provided\n"); diff --git a/include/linux/mfd/db8500-prcmu.h b/include/linux/mfd/db8500-prcmu.h index 813710aa2cfd..1fc75d2b4a38 100644 --- a/include/linux/mfd/db8500-prcmu.h +++ b/include/linux/mfd/db8500-prcmu.h @@ -489,7 +489,7 @@ struct prcmu_auto_pm_config { #ifdef CONFIG_MFD_DB8500_PRCMU -void db8500_prcmu_early_init(u32 phy_base, u32 size); +void db8500_prcmu_early_init(void); int prcmu_set_rc_a2p(enum romcode_write); enum romcode_read prcmu_get_rc_p2a(void); enum ap_pwrst prcmu_get_xp70_current_state(void); @@ -546,7 +546,7 @@ void db8500_prcmu_write_masked(unsigned int reg, u32 mask, u32 value); #else /* !CONFIG_MFD_DB8500_PRCMU */ -static inline void db8500_prcmu_early_init(u32 phy_base, u32 size) {} +static inline void db8500_prcmu_early_init(void) {} static inline int prcmu_set_rc_a2p(enum romcode_write code) { diff --git a/include/linux/mfd/dbx500-prcmu.h b/include/linux/mfd/dbx500-prcmu.h index 238401a50d0b..e2571040c7e8 100644 --- a/include/linux/mfd/dbx500-prcmu.h +++ b/include/linux/mfd/dbx500-prcmu.h @@ -190,6 +190,7 @@ enum ddr_pwrst { #define PRCMU_FW_PROJECT_U8500_MBL2 12 /* Customer specific */ #define PRCMU_FW_PROJECT_U8520 13 #define PRCMU_FW_PROJECT_U8420 14 +#define PRCMU_FW_PROJECT_U8420_SYSCLK 17 #define PRCMU_FW_PROJECT_A9420 20 /* [32..63] 9540 and derivatives */ #define PRCMU_FW_PROJECT_U9540 32 @@ -211,9 +212,9 @@ struct prcmu_fw_version { #if defined(CONFIG_UX500_SOC_DB8500) -static inline void prcmu_early_init(u32 phy_base, u32 size) +static inline void prcmu_early_init(void) { - return db8500_prcmu_early_init(phy_base, size); + return db8500_prcmu_early_init(); } static inline int prcmu_set_power_state(u8 state, bool keep_ulp_clk, @@ -401,7 +402,7 @@ static inline int prcmu_config_a9wdog(u8 num, bool sleep_auto_off) } #else -static inline void prcmu_early_init(u32 phy_base, u32 size) {} +static inline void prcmu_early_init(void) {} static inline int prcmu_set_power_state(u8 state, bool keep_ulp_clk, bool keep_ap_pll) -- cgit v1.2.3-71-gd317 From 34dc0ea6bc960f1f57b2148f01a3f4da23f87013 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 29 Oct 2019 11:01:37 +0100 Subject: dma-direct: provide mmap and get_sgtable method overrides For dma-direct we know that the DMA address is an encoding of the physical address that we can trivially decode. Use that fact to provide implementations that do not need the arch_dma_coherent_to_pfn architecture hook. Note that we still can only support mmap of non-coherent memory only if the architecture provides a way to set an uncached bit in the page tables. This must be true for architectures that use the generic remap helpers, but other architectures can also manually select it. Signed-off-by: Christoph Hellwig Reviewed-by: Max Filippov --- arch/arc/Kconfig | 1 - arch/arm/Kconfig | 1 - arch/arm/mm/dma-mapping.c | 6 ---- arch/arm64/Kconfig | 1 - arch/ia64/Kconfig | 2 +- arch/ia64/kernel/dma-mapping.c | 6 ---- arch/microblaze/Kconfig | 1 - arch/mips/Kconfig | 4 +-- arch/mips/mm/dma-noncoherent.c | 6 ---- arch/powerpc/platforms/Kconfig.cputype | 1 - include/linux/dma-direct.h | 7 ++++ include/linux/dma-noncoherent.h | 2 -- kernel/dma/Kconfig | 12 +++++-- kernel/dma/direct.c | 59 ++++++++++++++++++++++++++++++++++ kernel/dma/mapping.c | 45 ++++---------------------- kernel/dma/remap.c | 6 ---- 16 files changed, 85 insertions(+), 75 deletions(-) (limited to 'include/linux') diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 8383155c8c82..4d7b671c8ff4 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -6,7 +6,6 @@ config ARC def_bool y select ARC_TIMERS - select ARCH_HAS_DMA_COHERENT_TO_PFN select ARCH_HAS_DMA_PREP_COHERENT select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SETUP_DMA_OPS diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 8a50efb559f3..80e795aacd3a 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -7,7 +7,6 @@ config ARM select ARCH_HAS_BINFMT_FLAT select ARCH_HAS_DEBUG_VIRTUAL if MMU select ARCH_HAS_DEVMEM_IS_ALLOWED - select ARCH_HAS_DMA_COHERENT_TO_PFN if SWIOTLB select ARCH_HAS_DMA_WRITE_COMBINE if !ARM_DMA_MEM_BUFFERABLE select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FORTIFY_SOURCE diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 7d042d5c43e3..f3cbeba7f9cb 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -2346,12 +2346,6 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, size, dir); } -long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, - dma_addr_t dma_addr) -{ - return dma_to_pfn(dev, dma_addr); -} - void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 3f047afb982c..57606307fe34 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -12,7 +12,6 @@ config ARM64 select ARCH_CLOCKSOURCE_DATA select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEVMEM_IS_ALLOWED - select ARCH_HAS_DMA_COHERENT_TO_PFN select ARCH_HAS_DMA_PREP_COHERENT select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_FAST_MULTIPLIER diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 16714477eef4..bab7cd878464 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -33,7 +33,7 @@ config IA64 select HAVE_ARCH_TRACEHOOK select HAVE_MEMBLOCK_NODE_MAP select HAVE_VIRT_CPU_ACCOUNTING - select ARCH_HAS_DMA_COHERENT_TO_PFN + select DMA_NONCOHERENT_MMAP select ARCH_HAS_SYNC_DMA_FOR_CPU select VIRT_TO_BUS select GENERIC_IRQ_PROBE diff --git a/arch/ia64/kernel/dma-mapping.c b/arch/ia64/kernel/dma-mapping.c index 4a3262795890..09ef9ce9988d 100644 --- a/arch/ia64/kernel/dma-mapping.c +++ b/arch/ia64/kernel/dma-mapping.c @@ -19,9 +19,3 @@ void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, { dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs); } - -long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, - dma_addr_t dma_addr) -{ - return page_to_pfn(virt_to_page(cpu_addr)); -} diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index c9c4be822456..261c26df1c9f 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -4,7 +4,6 @@ config MICROBLAZE select ARCH_32BIT_OFF_T select ARCH_NO_SWAP select ARCH_HAS_BINFMT_FLAT if !MMU - select ARCH_HAS_DMA_COHERENT_TO_PFN if MMU select ARCH_HAS_DMA_PREP_COHERENT select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_SYNC_DMA_FOR_CPU diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index a0bd9bdb5f83..248d39b8a160 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -1134,9 +1134,9 @@ config DMA_NONCOHERENT select ARCH_HAS_DMA_WRITE_COMBINE select ARCH_HAS_SYNC_DMA_FOR_DEVICE select ARCH_HAS_UNCACHED_SEGMENT - select NEED_DMA_MAP_STATE - select ARCH_HAS_DMA_COHERENT_TO_PFN + select DMA_NONCOHERENT_MMAP select DMA_NONCOHERENT_CACHE_SYNC + select NEED_DMA_MAP_STATE config SYS_HAS_EARLY_PRINTK bool diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c index 1d4d57dd9acf..fcf6d3eaac66 100644 --- a/arch/mips/mm/dma-noncoherent.c +++ b/arch/mips/mm/dma-noncoherent.c @@ -59,12 +59,6 @@ void *cached_kernel_address(void *addr) return __va(addr) - UNCAC_BASE; } -long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, - dma_addr_t dma_addr) -{ - return page_to_pfn(virt_to_page(cached_kernel_address(cpu_addr))); -} - static inline void dma_sync_virt(void *addr, size_t size, enum dma_data_direction dir) { diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 12543e53fa96..303752f97c19 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -459,7 +459,6 @@ config NOT_COHERENT_CACHE bool depends on 4xx || PPC_8xx || E200 || PPC_MPC512x || \ GAMECUBE_COMMON || AMIGAONE - select ARCH_HAS_DMA_COHERENT_TO_PFN select ARCH_HAS_DMA_PREP_COHERENT select ARCH_HAS_SYNC_DMA_FOR_DEVICE select ARCH_HAS_SYNC_DMA_FOR_CPU diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index ff3d5edc44b9..bcd953fb1f5a 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -68,5 +68,12 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs); struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, gfp_t gfp, unsigned long attrs); +int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs); +bool dma_direct_can_mmap(struct device *dev); +int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs); int dma_direct_supported(struct device *dev, u64 mask); #endif /* _LINUX_DMA_DIRECT_H */ diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h index dd3de6d88fc0..e30fca1f1b12 100644 --- a/include/linux/dma-noncoherent.h +++ b/include/linux/dma-noncoherent.h @@ -41,8 +41,6 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs); -long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, - dma_addr_t dma_addr); #ifdef CONFIG_MMU /* diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index 73c5c2b8e824..4c103a24e380 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -51,9 +51,6 @@ config ARCH_HAS_SYNC_DMA_FOR_CPU_ALL config ARCH_HAS_DMA_PREP_COHERENT bool -config ARCH_HAS_DMA_COHERENT_TO_PFN - bool - config ARCH_HAS_FORCE_DMA_UNENCRYPTED bool @@ -68,9 +65,18 @@ config SWIOTLB bool select NEED_DMA_MAP_STATE +# +# Should be selected if we can mmap non-coherent mappings to userspace. +# The only thing that is really required is a way to set an uncached bit +# in the pagetables +# +config DMA_NONCOHERENT_MMAP + bool + config DMA_REMAP depends on MMU select GENERIC_ALLOCATOR + select DMA_NONCOHERENT_MMAP bool config DMA_DIRECT_REMAP diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 724c282dd943..58beaa9ddd27 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -43,6 +43,12 @@ static inline dma_addr_t phys_to_dma_direct(struct device *dev, return phys_to_dma(dev, phys); } +static inline struct page *dma_direct_to_page(struct device *dev, + dma_addr_t dma_addr) +{ + return pfn_to_page(PHYS_PFN(dma_to_phys(dev, dma_addr))); +} + u64 dma_direct_get_required_mask(struct device *dev) { u64 max_dma = phys_to_dma_direct(dev, (max_pfn - 1) << PAGE_SHIFT); @@ -379,6 +385,59 @@ dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr, } EXPORT_SYMBOL(dma_direct_map_resource); +int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs) +{ + struct page *page = dma_direct_to_page(dev, dma_addr); + int ret; + + ret = sg_alloc_table(sgt, 1, GFP_KERNEL); + if (!ret) + sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0); + return ret; +} + +#ifdef CONFIG_MMU +bool dma_direct_can_mmap(struct device *dev) +{ + return dev_is_dma_coherent(dev) || + IS_ENABLED(CONFIG_DMA_NONCOHERENT_MMAP); +} + +int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs) +{ + unsigned long user_count = vma_pages(vma); + unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; + unsigned long pfn = PHYS_PFN(dma_to_phys(dev, dma_addr)); + int ret = -ENXIO; + + vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs); + + if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret)) + return ret; + + if (vma->vm_pgoff >= count || user_count > count - vma->vm_pgoff) + return -ENXIO; + return remap_pfn_range(vma, vma->vm_start, pfn + vma->vm_pgoff, + user_count << PAGE_SHIFT, vma->vm_page_prot); +} +#else /* CONFIG_MMU */ +bool dma_direct_can_mmap(struct device *dev) +{ + return false; +} + +int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs) +{ + return -ENXIO; +} +#endif /* CONFIG_MMU */ + /* * Because 32-bit DMA masks are so common we expect every architecture to be * able to satisfy them - either by not supporting more physical memory, or by diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index d9334f31a5af..12ff766ec1fa 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -112,24 +112,9 @@ int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs) { - struct page *page; + struct page *page = virt_to_page(cpu_addr); int ret; - if (!dev_is_dma_coherent(dev)) { - unsigned long pfn; - - if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_COHERENT_TO_PFN)) - return -ENXIO; - - /* If the PFN is not valid, we do not have a struct page */ - pfn = arch_dma_coherent_to_pfn(dev, cpu_addr, dma_addr); - if (!pfn_valid(pfn)) - return -ENXIO; - page = pfn_to_page(pfn); - } else { - page = virt_to_page(cpu_addr); - } - ret = sg_alloc_table(sgt, 1, GFP_KERNEL); if (!ret) sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0); @@ -154,7 +139,7 @@ int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, const struct dma_map_ops *ops = get_dma_ops(dev); if (dma_is_direct(ops)) - return dma_common_get_sgtable(dev, sgt, cpu_addr, dma_addr, + return dma_direct_get_sgtable(dev, sgt, cpu_addr, dma_addr, size, attrs); if (!ops->get_sgtable) return -ENXIO; @@ -192,7 +177,6 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, unsigned long user_count = vma_pages(vma); unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; unsigned long off = vma->vm_pgoff; - unsigned long pfn; int ret = -ENXIO; vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs); @@ -203,19 +187,8 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, if (off >= count || user_count > count - off) return -ENXIO; - if (!dev_is_dma_coherent(dev)) { - if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_COHERENT_TO_PFN)) - return -ENXIO; - - /* If the PFN is not valid, we do not have a struct page */ - pfn = arch_dma_coherent_to_pfn(dev, cpu_addr, dma_addr); - if (!pfn_valid(pfn)) - return -ENXIO; - } else { - pfn = page_to_pfn(virt_to_page(cpu_addr)); - } - - return remap_pfn_range(vma, vma->vm_start, pfn + vma->vm_pgoff, + return remap_pfn_range(vma, vma->vm_start, + page_to_pfn(virt_to_page(cpu_addr)) + vma->vm_pgoff, user_count << PAGE_SHIFT, vma->vm_page_prot); #else return -ENXIO; @@ -233,12 +206,8 @@ bool dma_can_mmap(struct device *dev) { const struct dma_map_ops *ops = get_dma_ops(dev); - if (dma_is_direct(ops)) { - return IS_ENABLED(CONFIG_MMU) && - (dev_is_dma_coherent(dev) || - IS_ENABLED(CONFIG_ARCH_HAS_DMA_COHERENT_TO_PFN)); - } - + if (dma_is_direct(ops)) + return dma_direct_can_mmap(dev); return ops->mmap != NULL; } EXPORT_SYMBOL_GPL(dma_can_mmap); @@ -263,7 +232,7 @@ int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, const struct dma_map_ops *ops = get_dma_ops(dev); if (dma_is_direct(ops)) - return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size, + return dma_direct_mmap(dev, vma, cpu_addr, dma_addr, size, attrs); if (!ops->mmap) return -ENXIO; diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c index 90d5ce77c189..3c49499ee6b0 100644 --- a/kernel/dma/remap.c +++ b/kernel/dma/remap.c @@ -259,10 +259,4 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr, dma_free_contiguous(dev, page, size); } } - -long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, - dma_addr_t dma_addr) -{ - return __phys_to_pfn(dma_to_phys(dev, dma_addr)); -} #endif /* CONFIG_DMA_DIRECT_REMAP */ -- cgit v1.2.3-71-gd317 From b12d66278dd627cbe1ea7c000aa4715aaf8830c8 Mon Sep 17 00:00:00 2001 From: Nicolas Saenz Julienne Date: Thu, 7 Nov 2019 16:06:44 +0100 Subject: dma-direct: check for overflows on 32 bit DMA addresses As seen on the new Raspberry Pi 4 and sta2x11's DMA implementation it is possible for a device configured with 32 bit DMA addresses and a partial DMA mapping located at the end of the address space to overflow. It happens when a higher physical address, not DMAable, is translated to it's DMA counterpart. For example the Raspberry Pi 4, configurable up to 4 GB of memory, has an interconnect capable of addressing the lower 1 GB of physical memory with a DMA offset of 0xc0000000. It transpires that, any attempt to translate physical addresses higher than the first GB will result in an overflow which dma_capable() can't detect as it only checks for addresses bigger then the maximum allowed DMA address. Fix this by verifying in dma_capable() if the DMA address range provided is at any point lower than the minimum possible DMA address on the bus. Signed-off-by: Nicolas Saenz Julienne Signed-off-by: Christoph Hellwig --- include/linux/dma-direct.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index bcd953fb1f5a..6db863c3eb93 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -3,8 +3,11 @@ #define _LINUX_DMA_DIRECT_H 1 #include +#include /* for min_low_pfn */ #include +static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr); + #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA #include #else @@ -24,11 +27,16 @@ static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dev_addr) static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) { + dma_addr_t end = addr + size - 1; + if (!dev->dma_mask) return false; - return addr + size - 1 <= - min_not_zero(*dev->dma_mask, dev->bus_dma_mask); + if (!IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) && + min(addr, end) < phys_to_dma(dev, PFN_PHYS(min_low_pfn))) + return false; + + return end <= min_not_zero(*dev->dma_mask, dev->bus_dma_mask); } #endif /* !CONFIG_ARCH_HAS_PHYS_TO_DMA */ -- cgit v1.2.3-71-gd317 From 6fcbcec9cfc7b3c6a2c1f1a23ebacedff7073e0a Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Sun, 10 Nov 2019 12:49:06 +0300 Subject: fs/quota: handle overflows of sysctl fs.quota.* and report as unsigned long Quota statistics counted as 64-bit per-cpu counter. Reading sums per-cpu fractions as signed 64-bit int, filters negative values and then reports lower half as signed 32-bit int. Result may looks like: fs.quota.allocated_dquots = 22327 fs.quota.cache_hits = -489852115 fs.quota.drops = -487288718 fs.quota.free_dquots = 22083 fs.quota.lookups = -486883485 fs.quota.reads = 22327 fs.quota.syncs = 335064 fs.quota.writes = 3088689 Values bigger than 2^31-1 reported as negative. All counters except "allocated_dquots" and "free_dquots" are monotonic, thus they should be reported as is without filtering negative values. Kernel doesn't have generic helper for 64-bit sysctl yet, let's use at least unsigned long. Link: https://lore.kernel.org/r/157337934693.2078.9842146413181153727.stgit@buzz Signed-off-by: Konstantin Khlebnikov Signed-off-by: Jan Kara --- fs/quota/dquot.c | 29 +++++++++++++++++------------ include/linux/quota.h | 2 +- 2 files changed, 18 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 54a6626c2e9b..4639d53e96a3 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2848,68 +2848,73 @@ EXPORT_SYMBOL(dquot_quotactl_sysfile_ops); static int do_proc_dqstats(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - unsigned int type = (int *)table->data - dqstats.stat; + unsigned int type = (unsigned long *)table->data - dqstats.stat; + s64 value = percpu_counter_sum(&dqstats.counter[type]); + + /* Filter negative values for non-monotonic counters */ + if (value < 0 && (type == DQST_ALLOC_DQUOTS || + type == DQST_FREE_DQUOTS)) + value = 0; /* Update global table */ - dqstats.stat[type] = - percpu_counter_sum_positive(&dqstats.counter[type]); - return proc_dointvec(table, write, buffer, lenp, ppos); + dqstats.stat[type] = value; + return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } static struct ctl_table fs_dqstats_table[] = { { .procname = "lookups", .data = &dqstats.stat[DQST_LOOKUPS], - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "drops", .data = &dqstats.stat[DQST_DROPS], - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "reads", .data = &dqstats.stat[DQST_READS], - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "writes", .data = &dqstats.stat[DQST_WRITES], - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "cache_hits", .data = &dqstats.stat[DQST_CACHE_HITS], - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "allocated_dquots", .data = &dqstats.stat[DQST_ALLOC_DQUOTS], - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "free_dquots", .data = &dqstats.stat[DQST_FREE_DQUOTS], - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "syncs", .data = &dqstats.stat[DQST_SYNCS], - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, diff --git a/include/linux/quota.h b/include/linux/quota.h index f32dd270b8e3..27aab84fcbaa 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -263,7 +263,7 @@ enum { }; struct dqstats { - int stat[_DQST_DQSTAT_LAST]; + unsigned long stat[_DQST_DQSTAT_LAST]; struct percpu_counter counter[_DQST_DQSTAT_LAST]; }; -- cgit v1.2.3-71-gd317 From 2e7ec69d645210ea8a94cbb91799f57f62418bca Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Tue, 22 Oct 2019 10:36:28 +0200 Subject: backlight: gpio: Remove unused fields from platform data Remove the platform data fields that nobody uses. Signed-off-by: Bartosz Golaszewski Reviewed-by: Andy Shevchenko Reviewed-by: Linus Walleij Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones --- include/linux/platform_data/gpio_backlight.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio_backlight.h b/include/linux/platform_data/gpio_backlight.h index 34179d600360..1a8b5b1946fe 100644 --- a/include/linux/platform_data/gpio_backlight.h +++ b/include/linux/platform_data/gpio_backlight.h @@ -9,9 +9,6 @@ struct device; struct gpio_backlight_platform_data { struct device *fbdev; - int gpio; - int def_value; - const char *name; }; #endif -- cgit v1.2.3-71-gd317 From d9b86cc48283112f06738d45031b88bd3f9ecb92 Mon Sep 17 00:00:00 2001 From: Sowjanya Komatineni Date: Fri, 16 Aug 2019 12:41:52 -0700 Subject: clk: Add API to get index of the clock parent This patch adds a new clk_hw_get_parent_index() function that can be used to retrieve the index of a given clock's parent. This can be useful for restoring a clock on system resume. Reviewed-by: Thierry Reding Reviewed-by: Dmitry Osipenko Signed-off-by: Sowjanya Komatineni Signed-off-by: Thierry Reding --- drivers/clk/clk.c | 18 ++++++++++++++++++ include/linux/clk-provider.h | 1 + 2 files changed, 19 insertions(+) (limited to 'include/linux') diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 1c677d7f7f53..f8ed6e613436 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -1674,6 +1674,24 @@ static int clk_fetch_parent_index(struct clk_core *core, return i; } +/** + * clk_hw_get_parent_index - return the index of the parent clock + * @hw: clk_hw associated with the clk being consumed + * + * Fetches and returns the index of parent clock. Returns -EINVAL if the given + * clock does not have a current parent. + */ +int clk_hw_get_parent_index(struct clk_hw *hw) +{ + struct clk_hw *parent = clk_hw_get_parent(hw); + + if (WARN_ON(parent == NULL)) + return -EINVAL; + + return clk_fetch_parent_index(hw->core, parent->core); +} +EXPORT_SYMBOL_GPL(clk_hw_get_parent_index); + /* * Update the orphan status of @core and all its children. */ diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 2fdfe8061363..caf4b9df16eb 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -818,6 +818,7 @@ unsigned int clk_hw_get_num_parents(const struct clk_hw *hw); struct clk_hw *clk_hw_get_parent(const struct clk_hw *hw); struct clk_hw *clk_hw_get_parent_by_index(const struct clk_hw *hw, unsigned int index); +int clk_hw_get_parent_index(struct clk_hw *hw); int clk_hw_set_parent(struct clk_hw *hw, struct clk_hw *new_parent); unsigned int __clk_get_enable_count(struct clk *clk); unsigned long clk_hw_get_rate(const struct clk_hw *hw); -- cgit v1.2.3-71-gd317 From ed1a2459e20c0dfc9d184230c480ace439bececb Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Mon, 12 Aug 2019 00:00:29 +0300 Subject: clk: tegra: Add Tegra20/30 EMC clock implementation A proper External Memory Controller clock rounding and parent selection functionality is required by the EMC drivers, it is not available using the generic clock implementation because only the Memory Controller driver is aware of what clock rates are actually available for a particular device. EMC drivers will have to register a Tegra-specific CLK-API callback which will perform rounding of a requested rate. EMC clock users won't be able to request EMC clock by getting -EPROBE_DEFER until EMC driver is probed and the callback is set up. The functionality is somewhat similar to the clk-emc.c which serves Tegra124+ SoCs. The later HW generations support more parent clock sources and the HW configuration / integration with the EMC drivers differs a tad from the older gens, hence it's not really worth to try to squash everything into a single source file. Acked-by: Peter De Schrijver Signed-off-by: Dmitry Osipenko Acked-by: Stephen Boyd Signed-off-by: Thierry Reding --- drivers/clk/tegra/Makefile | 2 + drivers/clk/tegra/clk-tegra20-emc.c | 293 ++++++++++++++++++++++++++++++++++++ drivers/clk/tegra/clk-tegra20.c | 55 ++----- drivers/clk/tegra/clk-tegra30.c | 38 +++-- drivers/clk/tegra/clk.h | 3 + include/linux/clk/tegra.h | 11 ++ 6 files changed, 350 insertions(+), 52 deletions(-) create mode 100644 drivers/clk/tegra/clk-tegra20-emc.c (limited to 'include/linux') diff --git a/drivers/clk/tegra/Makefile b/drivers/clk/tegra/Makefile index 4812e45c2214..df966ca06788 100644 --- a/drivers/clk/tegra/Makefile +++ b/drivers/clk/tegra/Makefile @@ -17,7 +17,9 @@ obj-y += clk-tegra-fixed.o obj-y += clk-tegra-super-gen4.o obj-$(CONFIG_TEGRA_CLK_EMC) += clk-emc.o obj-$(CONFIG_ARCH_TEGRA_2x_SOC) += clk-tegra20.o +obj-$(CONFIG_ARCH_TEGRA_2x_SOC) += clk-tegra20-emc.o obj-$(CONFIG_ARCH_TEGRA_3x_SOC) += clk-tegra30.o +obj-$(CONFIG_ARCH_TEGRA_3x_SOC) += clk-tegra20-emc.o obj-$(CONFIG_ARCH_TEGRA_114_SOC) += clk-tegra114.o obj-$(CONFIG_ARCH_TEGRA_124_SOC) += clk-tegra124.o obj-$(CONFIG_TEGRA_CLK_DFLL) += clk-tegra124-dfll-fcpu.o diff --git a/drivers/clk/tegra/clk-tegra20-emc.c b/drivers/clk/tegra/clk-tegra20-emc.c new file mode 100644 index 000000000000..03bf0009a33c --- /dev/null +++ b/drivers/clk/tegra/clk-tegra20-emc.c @@ -0,0 +1,293 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Based on drivers/clk/tegra/clk-emc.c + * Copyright (c) 2014, NVIDIA CORPORATION. All rights reserved. + * + * Author: Dmitry Osipenko + * Copyright (C) 2019 GRATE-DRIVER project + */ + +#define pr_fmt(fmt) "tegra-emc-clk: " fmt + +#include +#include +#include +#include +#include +#include +#include + +#include "clk.h" + +#define CLK_SOURCE_EMC_2X_CLK_DIVISOR_MASK GENMASK(7, 0) +#define CLK_SOURCE_EMC_2X_CLK_SRC_MASK GENMASK(31, 30) +#define CLK_SOURCE_EMC_2X_CLK_SRC_SHIFT 30 + +#define MC_EMC_SAME_FREQ BIT(16) +#define USE_PLLM_UD BIT(29) + +#define EMC_SRC_PLL_M 0 +#define EMC_SRC_PLL_C 1 +#define EMC_SRC_PLL_P 2 +#define EMC_SRC_CLK_M 3 + +static const char * const emc_parent_clk_names[] = { + "pll_m", "pll_c", "pll_p", "clk_m", +}; + +struct tegra_clk_emc { + struct clk_hw hw; + void __iomem *reg; + bool mc_same_freq; + bool want_low_jitter; + + tegra20_clk_emc_round_cb *round_cb; + void *cb_arg; +}; + +static inline struct tegra_clk_emc *to_tegra_clk_emc(struct clk_hw *hw) +{ + return container_of(hw, struct tegra_clk_emc, hw); +} + +static unsigned long emc_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct tegra_clk_emc *emc = to_tegra_clk_emc(hw); + u32 val, div; + + val = readl_relaxed(emc->reg); + div = val & CLK_SOURCE_EMC_2X_CLK_DIVISOR_MASK; + + return DIV_ROUND_UP(parent_rate * 2, div + 2); +} + +static u8 emc_get_parent(struct clk_hw *hw) +{ + struct tegra_clk_emc *emc = to_tegra_clk_emc(hw); + + return readl_relaxed(emc->reg) >> CLK_SOURCE_EMC_2X_CLK_SRC_SHIFT; +} + +static int emc_set_parent(struct clk_hw *hw, u8 index) +{ + struct tegra_clk_emc *emc = to_tegra_clk_emc(hw); + u32 val, div; + + val = readl_relaxed(emc->reg); + val &= ~CLK_SOURCE_EMC_2X_CLK_SRC_MASK; + val |= index << CLK_SOURCE_EMC_2X_CLK_SRC_SHIFT; + + div = val & CLK_SOURCE_EMC_2X_CLK_DIVISOR_MASK; + + if (index == EMC_SRC_PLL_M && div == 0 && emc->want_low_jitter) + val |= USE_PLLM_UD; + else + val &= ~USE_PLLM_UD; + + if (emc->mc_same_freq) + val |= MC_EMC_SAME_FREQ; + else + val &= ~MC_EMC_SAME_FREQ; + + writel_relaxed(val, emc->reg); + + fence_udelay(1, emc->reg); + + return 0; +} + +static int emc_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct tegra_clk_emc *emc = to_tegra_clk_emc(hw); + unsigned int index; + u32 val, div; + + div = div_frac_get(rate, parent_rate, 8, 1, 0); + + val = readl_relaxed(emc->reg); + val &= ~CLK_SOURCE_EMC_2X_CLK_DIVISOR_MASK; + val |= div; + + index = val >> CLK_SOURCE_EMC_2X_CLK_SRC_SHIFT; + + if (index == EMC_SRC_PLL_M && div == 0 && emc->want_low_jitter) + val |= USE_PLLM_UD; + else + val &= ~USE_PLLM_UD; + + if (emc->mc_same_freq) + val |= MC_EMC_SAME_FREQ; + else + val &= ~MC_EMC_SAME_FREQ; + + writel_relaxed(val, emc->reg); + + fence_udelay(1, emc->reg); + + return 0; +} + +static int emc_set_rate_and_parent(struct clk_hw *hw, + unsigned long rate, + unsigned long parent_rate, + u8 index) +{ + struct tegra_clk_emc *emc = to_tegra_clk_emc(hw); + u32 val, div; + + div = div_frac_get(rate, parent_rate, 8, 1, 0); + + val = readl_relaxed(emc->reg); + + val &= ~CLK_SOURCE_EMC_2X_CLK_SRC_MASK; + val |= index << CLK_SOURCE_EMC_2X_CLK_SRC_SHIFT; + + val &= ~CLK_SOURCE_EMC_2X_CLK_DIVISOR_MASK; + val |= div; + + if (index == EMC_SRC_PLL_M && div == 0 && emc->want_low_jitter) + val |= USE_PLLM_UD; + else + val &= ~USE_PLLM_UD; + + if (emc->mc_same_freq) + val |= MC_EMC_SAME_FREQ; + else + val &= ~MC_EMC_SAME_FREQ; + + writel_relaxed(val, emc->reg); + + fence_udelay(1, emc->reg); + + return 0; +} + +static int emc_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) +{ + struct tegra_clk_emc *emc = to_tegra_clk_emc(hw); + struct clk_hw *parent_hw; + unsigned long divided_rate; + unsigned long parent_rate; + unsigned int i; + long emc_rate; + int div; + + emc_rate = emc->round_cb(req->rate, req->min_rate, req->max_rate, + emc->cb_arg); + if (emc_rate < 0) + return emc_rate; + + for (i = 0; i < ARRAY_SIZE(emc_parent_clk_names); i++) { + parent_hw = clk_hw_get_parent_by_index(hw, i); + + if (req->best_parent_hw == parent_hw) + parent_rate = req->best_parent_rate; + else + parent_rate = clk_hw_get_rate(parent_hw); + + if (emc_rate > parent_rate) + continue; + + div = div_frac_get(emc_rate, parent_rate, 8, 1, 0); + divided_rate = DIV_ROUND_UP(parent_rate * 2, div + 2); + + if (divided_rate != emc_rate) + continue; + + req->best_parent_rate = parent_rate; + req->best_parent_hw = parent_hw; + req->rate = emc_rate; + break; + } + + if (i == ARRAY_SIZE(emc_parent_clk_names)) { + pr_err_once("can't find parent for rate %lu emc_rate %lu\n", + req->rate, emc_rate); + return -EINVAL; + } + + return 0; +} + +static const struct clk_ops tegra_clk_emc_ops = { + .recalc_rate = emc_recalc_rate, + .get_parent = emc_get_parent, + .set_parent = emc_set_parent, + .set_rate = emc_set_rate, + .set_rate_and_parent = emc_set_rate_and_parent, + .determine_rate = emc_determine_rate, +}; + +void tegra20_clk_set_emc_round_callback(tegra20_clk_emc_round_cb *round_cb, + void *cb_arg) +{ + struct clk *clk = __clk_lookup("emc"); + struct tegra_clk_emc *emc; + struct clk_hw *hw; + + if (clk) { + hw = __clk_get_hw(clk); + emc = to_tegra_clk_emc(hw); + + emc->round_cb = round_cb; + emc->cb_arg = cb_arg; + } +} + +bool tegra20_clk_emc_driver_available(struct clk_hw *emc_hw) +{ + return to_tegra_clk_emc(emc_hw)->round_cb != NULL; +} + +struct clk *tegra20_clk_register_emc(void __iomem *ioaddr, bool low_jitter) +{ + struct tegra_clk_emc *emc; + struct clk_init_data init; + struct clk *clk; + + emc = kzalloc(sizeof(*emc), GFP_KERNEL); + if (!emc) + return NULL; + + /* + * EMC stands for External Memory Controller. + * + * We don't want EMC clock to be disabled ever by gating its + * parent and whatnot because system is busted immediately in that + * case, hence the clock is marked as critical. + */ + init.name = "emc"; + init.ops = &tegra_clk_emc_ops; + init.flags = CLK_IS_CRITICAL; + init.parent_names = emc_parent_clk_names; + init.num_parents = ARRAY_SIZE(emc_parent_clk_names); + + emc->reg = ioaddr; + emc->hw.init = &init; + emc->want_low_jitter = low_jitter; + + clk = clk_register(NULL, &emc->hw); + if (IS_ERR(clk)) { + kfree(emc); + return NULL; + } + + return clk; +} + +int tegra20_clk_prepare_emc_mc_same_freq(struct clk *emc_clk, bool same) +{ + struct tegra_clk_emc *emc; + struct clk_hw *hw; + + if (!emc_clk) + return -EINVAL; + + hw = __clk_get_hw(emc_clk); + emc = to_tegra_clk_emc(hw); + emc->mc_same_freq = same; + + return 0; +} diff --git a/drivers/clk/tegra/clk-tegra20.c b/drivers/clk/tegra/clk-tegra20.c index bcd871134f45..cceefbd67a3b 100644 --- a/drivers/clk/tegra/clk-tegra20.c +++ b/drivers/clk/tegra/clk-tegra20.c @@ -130,8 +130,6 @@ static struct cpu_clk_suspend_context { static void __iomem *clk_base; static void __iomem *pmc_base; -static DEFINE_SPINLOCK(emc_lock); - #define TEGRA_INIT_DATA_MUX(_name, _parents, _offset, \ _clk_num, _gate_flags, _clk_id) \ TEGRA_INIT_DATA(_name, NULL, NULL, _parents, _offset, \ @@ -760,7 +758,6 @@ static const char *pwm_parents[] = { "pll_p", "pll_c", "audio", "clk_m", static const char *mux_pllpcm_clkm[] = { "pll_p", "pll_c", "pll_m", "clk_m" }; static const char *mux_pllpdc_clkm[] = { "pll_p", "pll_d_out0", "pll_c", "clk_m" }; -static const char *mux_pllmcp_clkm[] = { "pll_m", "pll_c", "pll_p", "clk_m" }; static struct tegra_periph_init_data tegra_periph_clk_list[] = { TEGRA_INIT_DATA_MUX("i2s1", i2s1_parents, CLK_SOURCE_I2S1, 11, TEGRA_PERIPH_ON_APB, TEGRA20_CLK_I2S1), @@ -787,41 +784,6 @@ static struct tegra_periph_init_data tegra_periph_nodiv_clk_list[] = { TEGRA_INIT_DATA_NODIV("disp2", mux_pllpdc_clkm, CLK_SOURCE_DISP2, 30, 2, 26, 0, TEGRA20_CLK_DISP2), }; -static void __init tegra20_emc_clk_init(void) -{ - const u32 use_pllm_ud = BIT(29); - struct clk *clk; - u32 emc_reg; - - clk = clk_register_mux(NULL, "emc_mux", mux_pllmcp_clkm, - ARRAY_SIZE(mux_pllmcp_clkm), - CLK_SET_RATE_NO_REPARENT, - clk_base + CLK_SOURCE_EMC, - 30, 2, 0, &emc_lock); - - clk = tegra_clk_register_mc("mc", "emc_mux", clk_base + CLK_SOURCE_EMC, - &emc_lock); - clks[TEGRA20_CLK_MC] = clk; - - /* un-divided pll_m_out0 is currently unsupported */ - emc_reg = readl_relaxed(clk_base + CLK_SOURCE_EMC); - if (emc_reg & use_pllm_ud) { - pr_err("%s: un-divided PllM_out0 used as clock source\n", - __func__); - return; - } - - /* - * Note that 'emc_mux' source and 'emc' rate shouldn't be changed at - * the same time due to a HW bug, this won't happen because we're - * defining 'emc_mux' and 'emc' as distinct clocks. - */ - clk = tegra_clk_register_divider("emc", "emc_mux", - clk_base + CLK_SOURCE_EMC, CLK_IS_CRITICAL, - TEGRA_DIVIDER_INT, 0, 8, 1, &emc_lock); - clks[TEGRA20_CLK_EMC] = clk; -} - static void __init tegra20_periph_clk_init(void) { struct tegra_periph_init_data *data; @@ -835,7 +797,13 @@ static void __init tegra20_periph_clk_init(void) clks[TEGRA20_CLK_AC97] = clk; /* emc */ - tegra20_emc_clk_init(); + clk = tegra20_clk_register_emc(clk_base + CLK_SOURCE_EMC, false); + + clks[TEGRA20_CLK_EMC] = clk; + + clk = tegra_clk_register_mc("mc", "emc", clk_base + CLK_SOURCE_EMC, + NULL); + clks[TEGRA20_CLK_MC] = clk; /* dsi */ clk = tegra_clk_register_periph_gate("dsi", "pll_d", 0, clk_base, 0, @@ -1115,6 +1083,8 @@ static struct clk *tegra20_clk_src_onecell_get(struct of_phandle_args *clkspec, if (IS_ERR(clk)) return clk; + hw = __clk_get_hw(clk); + /* * Tegra20 CDEV1 and CDEV2 clocks are a bit special case, their parent * clock is created by the pinctrl driver. It is possible for clk user @@ -1124,13 +1094,16 @@ static struct clk *tegra20_clk_src_onecell_get(struct of_phandle_args *clkspec, */ if (clkspec->args[0] == TEGRA20_CLK_CDEV1 || clkspec->args[0] == TEGRA20_CLK_CDEV2) { - hw = __clk_get_hw(clk); - parent_hw = clk_hw_get_parent(hw); if (!parent_hw) return ERR_PTR(-EPROBE_DEFER); } + if (clkspec->args[0] == TEGRA20_CLK_EMC) { + if (!tegra20_clk_emc_driver_available(hw)) + return ERR_PTR(-EPROBE_DEFER); + } + return clk; } diff --git a/drivers/clk/tegra/clk-tegra30.c b/drivers/clk/tegra/clk-tegra30.c index 7b4c6a488527..95b0e4a16dd5 100644 --- a/drivers/clk/tegra/clk-tegra30.c +++ b/drivers/clk/tegra/clk-tegra30.c @@ -151,7 +151,6 @@ static unsigned long input_freq; static DEFINE_SPINLOCK(cml_lock); static DEFINE_SPINLOCK(pll_d_lock); -static DEFINE_SPINLOCK(emc_lock); #define TEGRA_INIT_DATA_MUX(_name, _parents, _offset, \ _clk_num, _gate_flags, _clk_id) \ @@ -808,7 +807,7 @@ static struct tegra_clk tegra30_clks[tegra_clk_max] __initdata = { [tegra_clk_pll_a] = { .dt_id = TEGRA30_CLK_PLL_A, .present = true }, [tegra_clk_pll_a_out0] = { .dt_id = TEGRA30_CLK_PLL_A_OUT0, .present = true }, [tegra_clk_cec] = { .dt_id = TEGRA30_CLK_CEC, .present = true }, - [tegra_clk_emc] = { .dt_id = TEGRA30_CLK_EMC, .present = true }, + [tegra_clk_emc] = { .dt_id = TEGRA30_CLK_EMC, .present = false }, }; static const char *pll_e_parents[] = { "pll_ref", "pll_p" }; @@ -995,7 +994,6 @@ static void __init tegra30_super_clk_init(void) static const char *mux_pllacp_clkm[] = { "pll_a_out0", "unused", "pll_p", "clk_m" }; static const char *mux_pllpcm_clkm[] = { "pll_p", "pll_c", "pll_m", "clk_m" }; -static const char *mux_pllmcp_clkm[] = { "pll_m", "pll_c", "pll_p", "clk_m" }; static const char *spdif_out_parents[] = { "pll_a_out0", "spdif_2x", "pll_p", "clk_m" }; static const char *mux_pllmcpa[] = { "pll_m", "pll_c", "pll_p", "pll_a_out0" }; @@ -1044,14 +1042,12 @@ static void __init tegra30_periph_clk_init(void) clks[TEGRA30_CLK_AFI] = clk; /* emc */ - clk = clk_register_mux(NULL, "emc_mux", mux_pllmcp_clkm, - ARRAY_SIZE(mux_pllmcp_clkm), - CLK_SET_RATE_NO_REPARENT, - clk_base + CLK_SOURCE_EMC, - 30, 2, 0, &emc_lock); + clk = tegra20_clk_register_emc(clk_base + CLK_SOURCE_EMC, true); + + clks[TEGRA30_CLK_EMC] = clk; - clk = tegra_clk_register_mc("mc", "emc_mux", clk_base + CLK_SOURCE_EMC, - &emc_lock); + clk = tegra_clk_register_mc("mc", "emc", clk_base + CLK_SOURCE_EMC, + NULL); clks[TEGRA30_CLK_MC] = clk; /* cml0 */ @@ -1302,6 +1298,26 @@ static struct tegra_audio_clk_info tegra30_audio_plls[] = { { "pll_a", &pll_a_params, tegra_clk_pll_a, "pll_p_out1" }, }; +static struct clk *tegra30_clk_src_onecell_get(struct of_phandle_args *clkspec, + void *data) +{ + struct clk_hw *hw; + struct clk *clk; + + clk = of_clk_src_onecell_get(clkspec, data); + if (IS_ERR(clk)) + return clk; + + hw = __clk_get_hw(clk); + + if (clkspec->args[0] == TEGRA30_CLK_EMC) { + if (!tegra20_clk_emc_driver_available(hw)) + return ERR_PTR(-EPROBE_DEFER); + } + + return clk; +} + static void __init tegra30_clock_init(struct device_node *np) { struct device_node *node; @@ -1345,7 +1361,7 @@ static void __init tegra30_clock_init(struct device_node *np) tegra_init_dup_clks(tegra_clk_duplicates, clks, TEGRA30_CLK_CLK_MAX); - tegra_add_of_provider(np, of_clk_src_onecell_get); + tegra_add_of_provider(np, tegra30_clk_src_onecell_get); tegra_register_devclks(devclks, ARRAY_SIZE(devclks)); tegra_clk_apply_init_table = tegra30_clock_apply_init_table; diff --git a/drivers/clk/tegra/clk.h b/drivers/clk/tegra/clk.h index 905bf1096558..20b3ee123050 100644 --- a/drivers/clk/tegra/clk.h +++ b/drivers/clk/tegra/clk.h @@ -838,4 +838,7 @@ int div_frac_get(unsigned long rate, unsigned parent_rate, u8 width, udelay(delay); \ } while (0) +bool tegra20_clk_emc_driver_available(struct clk_hw *emc_hw); +struct clk *tegra20_clk_register_emc(void __iomem *ioaddr, bool low_jitter); + #endif /* TEGRA_CLK_H */ diff --git a/include/linux/clk/tegra.h b/include/linux/clk/tegra.h index b8aef62cc3f5..6a7cbc3cfadc 100644 --- a/include/linux/clk/tegra.h +++ b/include/linux/clk/tegra.h @@ -119,4 +119,15 @@ extern void tegra210_put_utmipll_in_iddq(void); extern void tegra210_put_utmipll_out_iddq(void); extern int tegra210_clk_handle_mbist_war(unsigned int id); +struct clk; + +typedef long (tegra20_clk_emc_round_cb)(unsigned long rate, + unsigned long min_rate, + unsigned long max_rate, + void *arg); + +void tegra20_clk_set_emc_round_callback(tegra20_clk_emc_round_cb *round_cb, + void *cb_arg); +int tegra20_clk_prepare_emc_mc_same_freq(struct clk *emc_clk, bool same); + #endif /* __LINUX_CLK_TEGRA_H_ */ -- cgit v1.2.3-71-gd317 From 5699d160550b1e480c920f8182bd4b73b8c9ae43 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Tue, 15 Oct 2019 20:00:06 +0300 Subject: clk: tegra: Add missing stubs for the case of !CONFIG_PM_SLEEP The new CPUIDLE driver uses the Tegra's CLK API and that driver won't strictly depend on CONFIG_PM_SLEEP, hence add the required stubs in order to allow compiling of the new driver with the CONFIG_PM_SLEEP=n. Signed-off-by: Dmitry Osipenko Signed-off-by: Thierry Reding --- include/linux/clk/tegra.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/tegra.h b/include/linux/clk/tegra.h index 6a7cbc3cfadc..2b1b35240074 100644 --- a/include/linux/clk/tegra.h +++ b/include/linux/clk/tegra.h @@ -108,6 +108,19 @@ static inline void tegra_cpu_clock_resume(void) tegra_cpu_car_ops->resume(); } +#else +static inline bool tegra_cpu_rail_off_ready(void) +{ + return false; +} + +static inline void tegra_cpu_clock_suspend(void) +{ +} + +static inline void tegra_cpu_clock_resume(void) +{ +} #endif extern void tegra210_xusb_pll_hw_control_enable(void); -- cgit v1.2.3-71-gd317 From 6c3a44ed3c553c324845744f30bcd1d3b07d61fd Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Sun, 10 Nov 2019 09:27:44 -0800 Subject: iommu/vt-d: Turn off translations at shutdown The intel-iommu driver assumes that the iommu state is cleaned up at the start of the new kernel. But, when we try to kexec boot something other than the Linux kernel, the cleanup cannot be relied upon. Hence, cleanup before we go down for reboot. Keeping the cleanup at initialization also, in case BIOS leaves the IOMMU enabled. I considered turning off iommu only during kexec reboot, but a clean shutdown seems always a good idea. But if someone wants to make it conditional, such as VMM live update, we can do that. There doesn't seem to be such a condition at this time. Tested that before, the info message 'DMAR: Translation was enabled for but we are not in kdump mode' would be reported for each iommu. The message will not appear when the DMA-remapping is not enabled on entry to the kernel. Signed-off-by: Deepa Dinamani Acked-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/dmar.c | 5 ++++- drivers/iommu/intel-iommu.c | 20 ++++++++++++++++++++ include/linux/dmar.h | 2 ++ 3 files changed, 26 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index eecd6a421667..3acfa6a25fa2 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -895,8 +895,11 @@ int __init detect_intel_iommu(void) } #ifdef CONFIG_X86 - if (!ret) + if (!ret) { x86_init.iommu.iommu_init = intel_iommu_init; + x86_platform.iommu_shutdown = intel_iommu_shutdown; + } + #endif if (dmar_tbl) { diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index f168cd8ee570..10ee8fa4b1b8 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -4762,6 +4762,26 @@ static void intel_disable_iommus(void) iommu_disable_translation(iommu); } +void intel_iommu_shutdown(void) +{ + struct dmar_drhd_unit *drhd; + struct intel_iommu *iommu = NULL; + + if (no_iommu || dmar_disabled) + return; + + down_write(&dmar_global_lock); + + /* Disable PMRs explicitly here. */ + for_each_iommu(iommu, drhd) + iommu_disable_protect_mem_regions(iommu); + + /* Make sure the IOMMUs are switched off */ + intel_disable_iommus(); + + up_write(&dmar_global_lock); +} + static inline struct intel_iommu *dev_to_intel_iommu(struct device *dev) { struct iommu_device *iommu_dev = dev_to_iommu_device(dev); diff --git a/include/linux/dmar.h b/include/linux/dmar.h index a7cf3599d9a1..f64ca27dc210 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -129,6 +129,7 @@ static inline int dmar_res_noop(struct acpi_dmar_header *hdr, void *arg) #ifdef CONFIG_INTEL_IOMMU extern int iommu_detected, no_iommu; extern int intel_iommu_init(void); +extern void intel_iommu_shutdown(void); extern int dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg); extern int dmar_parse_one_atsr(struct acpi_dmar_header *header, void *arg); extern int dmar_check_one_atsr(struct acpi_dmar_header *hdr, void *arg); @@ -137,6 +138,7 @@ extern int dmar_iommu_hotplug(struct dmar_drhd_unit *dmaru, bool insert); extern int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info); #else /* !CONFIG_INTEL_IOMMU: */ static inline int intel_iommu_init(void) { return -ENODEV; } +static inline void intel_iommu_shutdown(void) { } #define dmar_parse_one_rmrr dmar_res_noop #define dmar_parse_one_atsr dmar_res_noop -- cgit v1.2.3-71-gd317 From 83cba933a6db1dd4d7ac85170f99461fbc339eff Mon Sep 17 00:00:00 2001 From: Sagar Shrikant Kadam Date: Tue, 22 Oct 2019 17:22:19 +0000 Subject: mtd: spi-nor: Set default Quad Enable method for ISSI flashes Set the default Quad Enable method for ISSI flashes. Used for ISSI flashes (IS25WP256D-JMLE) that do not support SFDP tables and can not determine the Quad Enable method by parsing BFPT. Based on code originally written by Wesley Terpstra and/or Palmer Dabbelt https://github.com/riscv/riscv-linux/commit/c94e267766d62bc9a669611c3d0c8ed5ea26569b Signed-off-by: Sagar Shrikant Kadam [tudor.ambarus@microchip.com: - rebase, split and adapt for latest spi-nor/next, - use PMC CFI ID for ISSI. According to JEP106BA, "Programmable Micro Corp" changed its name to Integrated Silicon Solution (ISSI)] Signed-off-by: Tudor Ambarus Reviewed-by: Vignesh Raghavendra --- drivers/mtd/spi-nor/spi-nor.c | 9 +++++++++ include/linux/mtd/spi-nor.h | 1 + 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index f7c6dcb6faaa..f4afe123e9dc 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -4577,6 +4577,11 @@ static void intel_set_default_init(struct spi_nor *nor) nor->flags |= SNOR_F_HAS_LOCK; } +static void issi_set_default_init(struct spi_nor *nor) +{ + nor->params.quad_enable = spi_nor_sr1_bit6_quad_enable; +} + static void macronix_set_default_init(struct spi_nor *nor) { nor->params.quad_enable = spi_nor_sr1_bit6_quad_enable; @@ -4617,6 +4622,10 @@ static void spi_nor_manufacturer_init_params(struct spi_nor *nor) intel_set_default_init(nor); break; + case SNOR_MFR_ISSI: + issi_set_default_init(nor); + break; + case SNOR_MFR_MACRONIX: macronix_set_default_init(nor); break; diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 9eae35c60bce..5a4623fc586b 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -22,6 +22,7 @@ #define SNOR_MFR_INTEL CFI_MFR_INTEL #define SNOR_MFR_ST CFI_MFR_ST /* ST Micro */ #define SNOR_MFR_MICRON CFI_MFR_MICRON /* Micron */ +#define SNOR_MFR_ISSI CFI_MFR_PMC #define SNOR_MFR_MACRONIX CFI_MFR_MACRONIX #define SNOR_MFR_SPANSION CFI_MFR_AMD #define SNOR_MFR_SST CFI_MFR_SST -- cgit v1.2.3-71-gd317 From cc9defcbb8fae52810f7795b039223edae51ef95 Mon Sep 17 00:00:00 2001 From: Michael Guralnik Date: Fri, 8 Nov 2019 23:45:24 +0000 Subject: net/mlx5: Handle "enable_roce" devlink param Register "enable_roce" param, default value is RoCE enabled. Current configuration is stored on mlx5_core_dev and exposed to user through the cmode runtime devlink param. Changing configuration requires changing the cmode driverinit devlink param and calling devlink reload. Signed-off-by: Michael Guralnik Acked-by: Jiri Pirko Signed-off-by: Saeed Mahameed --- .../networking/device_drivers/mellanox/mlx5.rst | 21 +++++++++++++++++++++ Documentation/networking/devlink-params-mlx5.txt | 5 +++++ drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 22 ++++++++++++++++++++++ include/linux/mlx5/driver.h | 11 +++++++++++ 4 files changed, 59 insertions(+) (limited to 'include/linux') diff --git a/Documentation/networking/device_drivers/mellanox/mlx5.rst b/Documentation/networking/device_drivers/mellanox/mlx5.rst index d071c6b49e1f..7599dceba9f1 100644 --- a/Documentation/networking/device_drivers/mellanox/mlx5.rst +++ b/Documentation/networking/device_drivers/mellanox/mlx5.rst @@ -154,6 +154,27 @@ User command examples: values: cmode runtime value smfs +enable_roce: RoCE enablement state +---------------------------------- +RoCE enablement state controls driver support for RoCE traffic. +When RoCE is disabled, there is no gid table, only raw ethernet QPs are supported and traffic on the well known UDP RoCE port is handled as raw ethernet traffic. + +To change RoCE enablement state a user must change the driverinit cmode value and run devlink reload. + +User command examples: + +- Disable RoCE:: + + $ devlink dev param set pci/0000:06:00.0 name enable_roce value false cmode driverinit + $ devlink dev reload pci/0000:06:00.0 + +- Read RoCE enablement state:: + + $ devlink dev param show pci/0000:06:00.0 name enable_roce + pci/0000:06:00.0: + name enable_roce type generic + values: + cmode driverinit value true Devlink health reporters ======================== diff --git a/Documentation/networking/devlink-params-mlx5.txt b/Documentation/networking/devlink-params-mlx5.txt index 8c0b82d655dc..5071467118bd 100644 --- a/Documentation/networking/devlink-params-mlx5.txt +++ b/Documentation/networking/devlink-params-mlx5.txt @@ -10,3 +10,8 @@ flow_steering_mode [DEVICE, DRIVER-SPECIFIC] without firmware intervention. Type: String Configuration mode: runtime + +enable_roce [DEVICE, GENERIC] + Enable handling of RoCE traffic in the device. + Defaultly enabled. + Configuration mode: driverinit diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index 381925c90d94..b2c26388edb1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -177,12 +177,29 @@ enum mlx5_devlink_param_id { MLX5_DEVLINK_PARAM_FLOW_STEERING_MODE, }; +static int mlx5_devlink_enable_roce_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + bool new_state = val.vbool; + + if (new_state && !MLX5_CAP_GEN(dev, roce)) { + NL_SET_ERR_MSG_MOD(extack, "Device doesn't support RoCE"); + return -EOPNOTSUPP; + } + + return 0; +} + static const struct devlink_param mlx5_devlink_params[] = { DEVLINK_PARAM_DRIVER(MLX5_DEVLINK_PARAM_FLOW_STEERING_MODE, "flow_steering_mode", DEVLINK_PARAM_TYPE_STRING, BIT(DEVLINK_PARAM_CMODE_RUNTIME), mlx5_devlink_fs_mode_get, mlx5_devlink_fs_mode_set, mlx5_devlink_fs_mode_validate), + DEVLINK_PARAM_GENERIC(ENABLE_ROCE, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), + NULL, NULL, mlx5_devlink_enable_roce_validate), }; static void mlx5_devlink_set_params_init_values(struct devlink *devlink) @@ -197,6 +214,11 @@ static void mlx5_devlink_set_params_init_values(struct devlink *devlink) devlink_param_driverinit_value_set(devlink, MLX5_DEVLINK_PARAM_FLOW_STEERING_MODE, value); + + value.vbool = MLX5_CAP_GEN(dev, roce); + devlink_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, + value); } int mlx5_devlink_register(struct devlink *devlink, struct device *dev) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 7b4801e96feb..1884513aac90 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1191,4 +1191,15 @@ enum { MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32, }; +static inline bool mlx5_is_roce_enabled(struct mlx5_core_dev *dev) +{ + struct devlink *devlink = priv_to_devlink(dev); + union devlink_param_value val; + + devlink_param_driverinit_value_get(devlink, + DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, + &val); + return val.vbool; +} + #endif /* MLX5_DRIVER_H */ -- cgit v1.2.3-71-gd317 From 7be5f90f689af5abb6b16755e212f76ed97a20dd Mon Sep 17 00:00:00 2001 From: Patrick Williams Date: Tue, 1 Oct 2019 11:00:00 -0500 Subject: i2c: pxa: remove unused i2c-slave APIs With the i2c-pxa driver migrated to the standard i2c-slave APIs, the custom APIs and structures are no longer needed or used. Remove them. Signed-off-by: Patrick Williams Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-pxa.c | 1 - include/linux/i2c-pxa.h | 18 ------------------ include/linux/platform_data/i2c-pxa.h | 4 ---- 3 files changed, 23 deletions(-) delete mode 100644 include/linux/i2c-pxa.h (limited to 'include/linux') diff --git a/drivers/i2c/busses/i2c-pxa.c b/drivers/i2c/busses/i2c-pxa.c index c811646e809f..466e4f681d7a 100644 --- a/drivers/i2c/busses/i2c-pxa.c +++ b/drivers/i2c/busses/i2c-pxa.c @@ -25,7 +25,6 @@ #include #include #include -#include #include #include #include diff --git a/include/linux/i2c-pxa.h b/include/linux/i2c-pxa.h deleted file mode 100644 index a897e2b507b6..000000000000 --- a/include/linux/i2c-pxa.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_I2C_ALGO_PXA_H -#define _LINUX_I2C_ALGO_PXA_H - -typedef enum i2c_slave_event_e { - I2C_SLAVE_EVENT_START_READ, - I2C_SLAVE_EVENT_START_WRITE, - I2C_SLAVE_EVENT_STOP -} i2c_slave_event_t; - -struct i2c_slave_client { - void *data; - void (*event)(void *ptr, i2c_slave_event_t event); - int (*read) (void *ptr); - void (*write)(void *ptr, unsigned int val); -}; - -#endif /* _LINUX_I2C_ALGO_PXA_H */ diff --git a/include/linux/platform_data/i2c-pxa.h b/include/linux/platform_data/i2c-pxa.h index cb290092599c..6a9b28399b39 100644 --- a/include/linux/platform_data/i2c-pxa.h +++ b/include/linux/platform_data/i2c-pxa.h @@ -55,11 +55,7 @@ */ #define I2C_ISR_INIT 0x7FF /* status register init */ -struct i2c_slave_client; - struct i2c_pxa_platform_data { - unsigned int slave_addr; - struct i2c_slave_client *slave; unsigned int class; unsigned int use_pio :1; unsigned int fast_mode :1; -- cgit v1.2.3-71-gd317 From c1d51f684c72b5eb2aecbbd47be3a2977a2dc903 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 7 Nov 2019 15:25:12 +0100 Subject: cpuidle: Use nanoseconds as the unit of time Currently, the cpuidle subsystem uses microseconds as the unit of time which (among other things) causes the idle loop to incur some integer division overhead for no clear benefit. In order to allow cpuidle to measure time in nanoseconds, add two new fields, exit_latency_ns and target_residency_ns, to represent the exit latency and target residency of an idle state in nanoseconds, respectively, to struct cpuidle_state and initialize them with the help of the corresponding values in microseconds provided by drivers. Additionally, change cpuidle_governor_latency_req() to return the idle state exit latency constraint in nanoseconds. Also meeasure idle state residency (last_residency_ns in struct cpuidle_device and time_ns in struct cpuidle_driver) in nanoseconds and update the cpuidle core and governors accordingly. However, the menu governor still computes typical intervals in microseconds to avoid integer overflows. Signed-off-by: Rafael J. Wysocki Acked-by: Peter Zijlstra (Intel) Acked-by: Doug Smythies Tested-by: Doug Smythies --- drivers/cpuidle/cpuidle.c | 36 +++++----- drivers/cpuidle/driver.c | 29 ++++++--- drivers/cpuidle/governor.c | 7 +- drivers/cpuidle/governors/haltpoll.c | 7 +- drivers/cpuidle/governors/ladder.c | 25 +++---- drivers/cpuidle/governors/menu.c | 123 ++++++++++++++++------------------- drivers/cpuidle/governors/teo.c | 76 ++++++++++------------ drivers/cpuidle/poll_state.c | 2 + drivers/cpuidle/sysfs.c | 20 +++++- include/linux/cpuidle.h | 8 ++- kernel/sched/idle.c | 2 +- 11 files changed, 174 insertions(+), 161 deletions(-) (limited to 'include/linux') diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 44ae39f2b47a..bf9b030cd7e1 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -75,24 +75,24 @@ int cpuidle_play_dead(void) static int find_deepest_state(struct cpuidle_driver *drv, struct cpuidle_device *dev, - unsigned int max_latency, + u64 max_latency_ns, unsigned int forbidden_flags, bool s2idle) { - unsigned int latency_req = 0; + u64 latency_req = 0; int i, ret = 0; for (i = 1; i < drv->state_count; i++) { struct cpuidle_state *s = &drv->states[i]; if (dev->states_usage[i].disable || - s->exit_latency <= latency_req || - s->exit_latency > max_latency || + s->exit_latency_ns <= latency_req || + s->exit_latency_ns > max_latency_ns || (s->flags & forbidden_flags) || (s2idle && !s->enter_s2idle)) continue; - latency_req = s->exit_latency; + latency_req = s->exit_latency_ns; ret = i; } return ret; @@ -124,7 +124,7 @@ void cpuidle_use_deepest_state(bool enable) int cpuidle_find_deepest_state(struct cpuidle_driver *drv, struct cpuidle_device *dev) { - return find_deepest_state(drv, dev, UINT_MAX, 0, false); + return find_deepest_state(drv, dev, U64_MAX, 0, false); } #ifdef CONFIG_SUSPEND @@ -180,7 +180,7 @@ int cpuidle_enter_s2idle(struct cpuidle_driver *drv, struct cpuidle_device *dev) * that interrupts won't be enabled when it exits and allows the tick to * be frozen safely. */ - index = find_deepest_state(drv, dev, UINT_MAX, 0, true); + index = find_deepest_state(drv, dev, U64_MAX, 0, true); if (index > 0) enter_s2idle_proper(drv, dev, index); @@ -209,7 +209,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, * CPU as a broadcast timer, this call may fail if it is not available. */ if (broadcast && tick_broadcast_enter()) { - index = find_deepest_state(drv, dev, target_state->exit_latency, + index = find_deepest_state(drv, dev, target_state->exit_latency_ns, CPUIDLE_FLAG_TIMER_STOP, false); if (index < 0) { default_idle_call(); @@ -247,7 +247,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, local_irq_enable(); if (entered_state >= 0) { - s64 diff, delay = drv->states[entered_state].exit_latency; + s64 diff, delay = drv->states[entered_state].exit_latency_ns; int i; /* @@ -255,15 +255,13 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, * This can be moved to within driver enter routine, * but that results in multiple copies of same code. */ - diff = ktime_us_delta(time_end, time_start); - if (diff > INT_MAX) - diff = INT_MAX; + diff = ktime_sub(time_end, time_start); - dev->last_residency = (int)diff; - dev->states_usage[entered_state].time += dev->last_residency; + dev->last_residency_ns = diff; + dev->states_usage[entered_state].time_ns += diff; dev->states_usage[entered_state].usage++; - if (diff < drv->states[entered_state].target_residency) { + if (diff < drv->states[entered_state].target_residency_ns) { for (i = entered_state - 1; i >= 0; i--) { if (dev->states_usage[i].disable) continue; @@ -281,14 +279,14 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, * Update if a deeper state would have been a * better match for the observed idle duration. */ - if (diff - delay >= drv->states[i].target_residency) + if (diff - delay >= drv->states[i].target_residency_ns) dev->states_usage[entered_state].below++; break; } } } else { - dev->last_residency = 0; + dev->last_residency_ns = 0; } return entered_state; @@ -381,7 +379,7 @@ u64 cpuidle_poll_time(struct cpuidle_driver *drv, if (dev->states_usage[i].disable) continue; - limit_ns = (u64)drv->states[i].target_residency * NSEC_PER_USEC; + limit_ns = (u64)drv->states[i].target_residency_ns; } dev->poll_limit_ns = limit_ns; @@ -552,7 +550,7 @@ static void __cpuidle_unregister_device(struct cpuidle_device *dev) static void __cpuidle_device_init(struct cpuidle_device *dev) { memset(dev->states_usage, 0, sizeof(dev->states_usage)); - dev->last_residency = 0; + dev->last_residency_ns = 0; dev->next_hrtimer = 0; } diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c index 9db154224999..fcaf8b2bab96 100644 --- a/drivers/cpuidle/driver.c +++ b/drivers/cpuidle/driver.c @@ -165,16 +165,27 @@ static void __cpuidle_driver_init(struct cpuidle_driver *drv) if (!drv->cpumask) drv->cpumask = (struct cpumask *)cpu_possible_mask; - /* - * Look for the timer stop flag in the different states, so that we know - * if the broadcast timer has to be set up. The loop is in the reverse - * order, because usually one of the deeper states have this flag set. - */ - for (i = drv->state_count - 1; i >= 0 ; i--) { - if (drv->states[i].flags & CPUIDLE_FLAG_TIMER_STOP) { + for (i = 0; i < drv->state_count; i++) { + struct cpuidle_state *s = &drv->states[i]; + + /* + * Look for the timer stop flag in the different states and if + * it is found, indicate that the broadcast timer has to be set + * up. + */ + if (s->flags & CPUIDLE_FLAG_TIMER_STOP) drv->bctimer = 1; - break; - } + + /* + * The core will use the target residency and exit latency + * values in nanoseconds, but allow drivers to provide them in + * microseconds too. + */ + if (s->target_residency > 0) + s->target_residency_ns = s->target_residency * NSEC_PER_USEC; + + if (s->exit_latency > 0) + s->exit_latency_ns = s->exit_latency * NSEC_PER_USEC; } } diff --git a/drivers/cpuidle/governor.c b/drivers/cpuidle/governor.c index e9801f26c732..e48271e117a3 100644 --- a/drivers/cpuidle/governor.c +++ b/drivers/cpuidle/governor.c @@ -107,11 +107,14 @@ int cpuidle_register_governor(struct cpuidle_governor *gov) * cpuidle_governor_latency_req - Compute a latency constraint for CPU * @cpu: Target CPU */ -int cpuidle_governor_latency_req(unsigned int cpu) +s64 cpuidle_governor_latency_req(unsigned int cpu) { int global_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY); struct device *device = get_cpu_device(cpu); int device_req = dev_pm_qos_raw_resume_latency(device); - return device_req < global_req ? device_req : global_req; + if (device_req > global_req) + device_req = global_req; + + return (s64)device_req * NSEC_PER_USEC; } diff --git a/drivers/cpuidle/governors/haltpoll.c b/drivers/cpuidle/governors/haltpoll.c index 7a703d2e0064..cb2a96eafc02 100644 --- a/drivers/cpuidle/governors/haltpoll.c +++ b/drivers/cpuidle/governors/haltpoll.c @@ -49,7 +49,7 @@ static int haltpoll_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, bool *stop_tick) { - int latency_req = cpuidle_governor_latency_req(dev->cpu); + s64 latency_req = cpuidle_governor_latency_req(dev->cpu); if (!drv->state_count || latency_req == 0) { *stop_tick = false; @@ -75,10 +75,9 @@ static int haltpoll_select(struct cpuidle_driver *drv, return 0; } -static void adjust_poll_limit(struct cpuidle_device *dev, unsigned int block_us) +static void adjust_poll_limit(struct cpuidle_device *dev, u64 block_ns) { unsigned int val; - u64 block_ns = block_us*NSEC_PER_USEC; /* Grow cpu_halt_poll_us if * cpu_halt_poll_us < block_ns < guest_halt_poll_us @@ -115,7 +114,7 @@ static void haltpoll_reflect(struct cpuidle_device *dev, int index) dev->last_state_idx = index; if (index != 0) - adjust_poll_limit(dev, dev->last_residency); + adjust_poll_limit(dev, dev->last_residency_ns); } /** diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c index b0126b8c32fe..8e9058c4ea63 100644 --- a/drivers/cpuidle/governors/ladder.c +++ b/drivers/cpuidle/governors/ladder.c @@ -27,8 +27,8 @@ struct ladder_device_state { struct { u32 promotion_count; u32 demotion_count; - u32 promotion_time; - u32 demotion_time; + u64 promotion_time_ns; + u64 demotion_time_ns; } threshold; struct { int promotion_count; @@ -68,9 +68,10 @@ static int ladder_select_state(struct cpuidle_driver *drv, { struct ladder_device *ldev = this_cpu_ptr(&ladder_devices); struct ladder_device_state *last_state; - int last_residency, last_idx = dev->last_state_idx; + int last_idx = dev->last_state_idx; int first_idx = drv->states[0].flags & CPUIDLE_FLAG_POLLING ? 1 : 0; - int latency_req = cpuidle_governor_latency_req(dev->cpu); + s64 latency_req = cpuidle_governor_latency_req(dev->cpu); + s64 last_residency; /* Special case when user has set very strict latency requirement */ if (unlikely(latency_req == 0)) { @@ -80,13 +81,13 @@ static int ladder_select_state(struct cpuidle_driver *drv, last_state = &ldev->states[last_idx]; - last_residency = dev->last_residency - drv->states[last_idx].exit_latency; + last_residency = dev->last_residency_ns - drv->states[last_idx].exit_latency_ns; /* consider promotion */ if (last_idx < drv->state_count - 1 && !dev->states_usage[last_idx + 1].disable && - last_residency > last_state->threshold.promotion_time && - drv->states[last_idx + 1].exit_latency <= latency_req) { + last_residency > last_state->threshold.promotion_time_ns && + drv->states[last_idx + 1].exit_latency_ns <= latency_req) { last_state->stats.promotion_count++; last_state->stats.demotion_count = 0; if (last_state->stats.promotion_count >= last_state->threshold.promotion_count) { @@ -98,11 +99,11 @@ static int ladder_select_state(struct cpuidle_driver *drv, /* consider demotion */ if (last_idx > first_idx && (dev->states_usage[last_idx].disable || - drv->states[last_idx].exit_latency > latency_req)) { + drv->states[last_idx].exit_latency_ns > latency_req)) { int i; for (i = last_idx - 1; i > first_idx; i--) { - if (drv->states[i].exit_latency <= latency_req) + if (drv->states[i].exit_latency_ns <= latency_req) break; } ladder_do_selection(dev, ldev, last_idx, i); @@ -110,7 +111,7 @@ static int ladder_select_state(struct cpuidle_driver *drv, } if (last_idx > first_idx && - last_residency < last_state->threshold.demotion_time) { + last_residency < last_state->threshold.demotion_time_ns) { last_state->stats.demotion_count++; last_state->stats.promotion_count = 0; if (last_state->stats.demotion_count >= last_state->threshold.demotion_count) { @@ -150,9 +151,9 @@ static int ladder_enable_device(struct cpuidle_driver *drv, lstate->threshold.demotion_count = DEMOTION_COUNT; if (i < drv->state_count - 1) - lstate->threshold.promotion_time = state->exit_latency; + lstate->threshold.promotion_time_ns = state->exit_latency_ns; if (i > first_idx) - lstate->threshold.demotion_time = state->exit_latency; + lstate->threshold.demotion_time_ns = state->exit_latency_ns; } return 0; diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index 38b2b72102a8..b0a7ad566081 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -19,22 +19,12 @@ #include #include -/* - * Please note when changing the tuning values: - * If (MAX_INTERESTING-1) * RESOLUTION > UINT_MAX, the result of - * a scaling operation multiplication may overflow on 32 bit platforms. - * In that case, #define RESOLUTION as ULL to get 64 bit result: - * #define RESOLUTION 1024ULL - * - * The default values do not overflow. - */ #define BUCKETS 12 #define INTERVAL_SHIFT 3 #define INTERVALS (1UL << INTERVAL_SHIFT) #define RESOLUTION 1024 #define DECAY 8 -#define MAX_INTERESTING 50000 - +#define MAX_INTERESTING (50000 * NSEC_PER_USEC) /* * Concepts and ideas behind the menu governor @@ -120,14 +110,14 @@ struct menu_device { int needs_update; int tick_wakeup; - unsigned int next_timer_us; + u64 next_timer_ns; unsigned int bucket; unsigned int correction_factor[BUCKETS]; unsigned int intervals[INTERVALS]; int interval_ptr; }; -static inline int which_bucket(unsigned int duration, unsigned long nr_iowaiters) +static inline int which_bucket(u64 duration_ns, unsigned long nr_iowaiters) { int bucket = 0; @@ -140,15 +130,15 @@ static inline int which_bucket(unsigned int duration, unsigned long nr_iowaiters if (nr_iowaiters) bucket = BUCKETS/2; - if (duration < 10) + if (duration_ns < 10ULL * NSEC_PER_USEC) return bucket; - if (duration < 100) + if (duration_ns < 100ULL * NSEC_PER_USEC) return bucket + 1; - if (duration < 1000) + if (duration_ns < 1000ULL * NSEC_PER_USEC) return bucket + 2; - if (duration < 10000) + if (duration_ns < 10000ULL * NSEC_PER_USEC) return bucket + 3; - if (duration < 100000) + if (duration_ns < 100000ULL * NSEC_PER_USEC) return bucket + 4; return bucket + 5; } @@ -276,13 +266,13 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, bool *stop_tick) { struct menu_device *data = this_cpu_ptr(&menu_devices); - int latency_req = cpuidle_governor_latency_req(dev->cpu); - int i; - int idx; - unsigned int interactivity_req; + s64 latency_req = cpuidle_governor_latency_req(dev->cpu); unsigned int predicted_us; + u64 predicted_ns; + u64 interactivity_req; unsigned long nr_iowaiters; ktime_t delta_next; + int i, idx; if (data->needs_update) { menu_update(drv, dev); @@ -290,14 +280,14 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, } /* determine the expected residency time, round up */ - data->next_timer_us = ktime_to_us(tick_nohz_get_sleep_length(&delta_next)); + data->next_timer_ns = tick_nohz_get_sleep_length(&delta_next); nr_iowaiters = nr_iowait_cpu(dev->cpu); - data->bucket = which_bucket(data->next_timer_us, nr_iowaiters); + data->bucket = which_bucket(data->next_timer_ns, nr_iowaiters); if (unlikely(drv->state_count <= 1 || latency_req == 0) || - ((data->next_timer_us < drv->states[1].target_residency || - latency_req < drv->states[1].exit_latency) && + ((data->next_timer_ns < drv->states[1].target_residency_ns || + latency_req < drv->states[1].exit_latency_ns) && !dev->states_usage[0].disable)) { /* * In this case state[0] will be used no matter what, so return @@ -308,18 +298,15 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, return 0; } - /* - * Force the result of multiplication to be 64 bits even if both - * operands are 32 bits. - * Make sure to round up for half microseconds. - */ - predicted_us = DIV_ROUND_CLOSEST_ULL((uint64_t)data->next_timer_us * - data->correction_factor[data->bucket], - RESOLUTION * DECAY); - /* - * Use the lowest expected idle interval to pick the idle state. - */ - predicted_us = min(predicted_us, get_typical_interval(data, predicted_us)); + /* Round up the result for half microseconds. */ + predicted_us = div_u64(data->next_timer_ns * + data->correction_factor[data->bucket] + + (RESOLUTION * DECAY * NSEC_PER_USEC) / 2, + RESOLUTION * DECAY * NSEC_PER_USEC); + /* Use the lowest expected idle interval to pick the idle state. */ + predicted_ns = (u64)min(predicted_us, + get_typical_interval(data, predicted_us)) * + NSEC_PER_USEC; if (tick_nohz_tick_stopped()) { /* @@ -330,14 +317,15 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * the known time till the closest timer event for the idle * state selection. */ - if (predicted_us < TICK_USEC) - predicted_us = ktime_to_us(delta_next); + if (predicted_ns < TICK_NSEC) + predicted_ns = delta_next; } else { /* * Use the performance multiplier and the user-configurable * latency_req to determine the maximum exit latency. */ - interactivity_req = predicted_us / performance_multiplier(nr_iowaiters); + interactivity_req = div64_u64(predicted_ns, + performance_multiplier(nr_iowaiters)); if (latency_req > interactivity_req) latency_req = interactivity_req; } @@ -356,19 +344,19 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, if (idx == -1) idx = i; /* first enabled state */ - if (s->target_residency > predicted_us) { + if (s->target_residency_ns > predicted_ns) { /* * Use a physical idle state, not busy polling, unless * a timer is going to trigger soon enough. */ if ((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) && - s->exit_latency <= latency_req && - s->target_residency <= data->next_timer_us) { - predicted_us = s->target_residency; + s->exit_latency_ns <= latency_req && + s->target_residency_ns <= data->next_timer_ns) { + predicted_ns = s->target_residency_ns; idx = i; break; } - if (predicted_us < TICK_USEC) + if (predicted_ns < TICK_NSEC) break; if (!tick_nohz_tick_stopped()) { @@ -378,7 +366,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * tick in that case and let the governor run * again in the next iteration of the loop. */ - predicted_us = drv->states[idx].target_residency; + predicted_ns = drv->states[idx].target_residency_ns; break; } @@ -388,13 +376,13 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * closest timer event, select this one to avoid getting * stuck in the shallow one for too long. */ - if (drv->states[idx].target_residency < TICK_USEC && - s->target_residency <= ktime_to_us(delta_next)) + if (drv->states[idx].target_residency_ns < TICK_NSEC && + s->target_residency_ns <= delta_next) idx = i; return idx; } - if (s->exit_latency > latency_req) + if (s->exit_latency_ns > latency_req) break; idx = i; @@ -408,12 +396,10 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * expected idle duration is shorter than the tick period length. */ if (((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) || - predicted_us < TICK_USEC) && !tick_nohz_tick_stopped()) { - unsigned int delta_next_us = ktime_to_us(delta_next); - + predicted_ns < TICK_NSEC) && !tick_nohz_tick_stopped()) { *stop_tick = false; - if (idx > 0 && drv->states[idx].target_residency > delta_next_us) { + if (idx > 0 && drv->states[idx].target_residency_ns > delta_next) { /* * The tick is not going to be stopped and the target * residency of the state to be returned is not within @@ -425,7 +411,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, continue; idx = i; - if (drv->states[i].target_residency <= delta_next_us) + if (drv->states[i].target_residency_ns <= delta_next) break; } } @@ -461,7 +447,7 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) struct menu_device *data = this_cpu_ptr(&menu_devices); int last_idx = dev->last_state_idx; struct cpuidle_state *target = &drv->states[last_idx]; - unsigned int measured_us; + u64 measured_ns; unsigned int new_factor; /* @@ -479,7 +465,7 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) * assume the state was never reached and the exit latency is 0. */ - if (data->tick_wakeup && data->next_timer_us > TICK_USEC) { + if (data->tick_wakeup && data->next_timer_ns > TICK_NSEC) { /* * The nohz code said that there wouldn't be any events within * the tick boundary (if the tick was stopped), but the idle @@ -489,7 +475,7 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) * have been idle long (but not forever) to help the idle * duration predictor do a better job next time. */ - measured_us = 9 * MAX_INTERESTING / 10; + measured_ns = 9 * MAX_INTERESTING / 10; } else if ((drv->states[last_idx].flags & CPUIDLE_FLAG_POLLING) && dev->poll_time_limit) { /* @@ -499,28 +485,29 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) * the CPU might have been woken up from idle by the next timer. * Assume that to be the case. */ - measured_us = data->next_timer_us; + measured_ns = data->next_timer_ns; } else { /* measured value */ - measured_us = dev->last_residency; + measured_ns = dev->last_residency_ns; /* Deduct exit latency */ - if (measured_us > 2 * target->exit_latency) - measured_us -= target->exit_latency; + if (measured_ns > 2 * target->exit_latency_ns) + measured_ns -= target->exit_latency_ns; else - measured_us /= 2; + measured_ns /= 2; } /* Make sure our coefficients do not exceed unity */ - if (measured_us > data->next_timer_us) - measured_us = data->next_timer_us; + if (measured_ns > data->next_timer_ns) + measured_ns = data->next_timer_ns; /* Update our correction ratio */ new_factor = data->correction_factor[data->bucket]; new_factor -= new_factor / DECAY; - if (data->next_timer_us > 0 && measured_us < MAX_INTERESTING) - new_factor += RESOLUTION * measured_us / data->next_timer_us; + if (data->next_timer_ns > 0 && measured_ns < MAX_INTERESTING) + new_factor += div64_u64(RESOLUTION * measured_ns, + data->next_timer_ns); else /* * we were idle so long that we count it as a perfect @@ -540,7 +527,7 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) data->correction_factor[data->bucket] = new_factor; /* update the repeating-pattern data */ - data->intervals[data->interval_ptr++] = measured_us; + data->intervals[data->interval_ptr++] = ktime_to_us(measured_ns); if (data->interval_ptr >= INTERVALS) data->interval_ptr = 0; } diff --git a/drivers/cpuidle/governors/teo.c b/drivers/cpuidle/governors/teo.c index 702d560eb347..ecbcfaefb0cd 100644 --- a/drivers/cpuidle/governors/teo.c +++ b/drivers/cpuidle/governors/teo.c @@ -104,7 +104,7 @@ struct teo_cpu { u64 sleep_length_ns; struct teo_idle_state states[CPUIDLE_STATE_MAX]; int interval_idx; - unsigned int intervals[INTERVALS]; + u64 intervals[INTERVALS]; }; static DEFINE_PER_CPU(struct teo_cpu, teo_cpus); @@ -117,9 +117,8 @@ static DEFINE_PER_CPU(struct teo_cpu, teo_cpus); static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) { struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu); - unsigned int sleep_length_us = ktime_to_us(cpu_data->sleep_length_ns); int i, idx_hit = -1, idx_timer = -1; - unsigned int measured_us; + u64 measured_ns; if (cpu_data->time_span_ns >= cpu_data->sleep_length_ns) { /* @@ -127,23 +126,21 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) * enough to the closest timer event expected at the idle state * selection time to be discarded. */ - measured_us = UINT_MAX; + measured_ns = U64_MAX; } else { - unsigned int lat; + u64 lat_ns = drv->states[dev->last_state_idx].exit_latency_ns; - lat = drv->states[dev->last_state_idx].exit_latency; - - measured_us = ktime_to_us(cpu_data->time_span_ns); + measured_ns = cpu_data->time_span_ns; /* * The delay between the wakeup and the first instruction * executed by the CPU is not likely to be worst-case every * time, so take 1/2 of the exit latency as a very rough * approximation of the average of it. */ - if (measured_us >= lat) - measured_us -= lat / 2; + if (measured_ns >= lat_ns) + measured_ns -= lat_ns / 2; else - measured_us /= 2; + measured_ns /= 2; } /* @@ -155,9 +152,9 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) cpu_data->states[i].early_hits -= early_hits >> DECAY_SHIFT; - if (drv->states[i].target_residency <= sleep_length_us) { + if (drv->states[i].target_residency_ns <= cpu_data->sleep_length_ns) { idx_timer = i; - if (drv->states[i].target_residency <= measured_us) + if (drv->states[i].target_residency_ns <= measured_ns) idx_hit = i; } } @@ -193,7 +190,7 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) * Save idle duration values corresponding to non-timer wakeups for * pattern detection. */ - cpu_data->intervals[cpu_data->interval_idx++] = measured_us; + cpu_data->intervals[cpu_data->interval_idx++] = measured_ns; if (cpu_data->interval_idx > INTERVALS) cpu_data->interval_idx = 0; } @@ -203,11 +200,11 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) * @drv: cpuidle driver containing state data. * @dev: Target CPU. * @state_idx: Index of the capping idle state. - * @duration_us: Idle duration value to match. + * @duration_ns: Idle duration value to match. */ static int teo_find_shallower_state(struct cpuidle_driver *drv, struct cpuidle_device *dev, int state_idx, - unsigned int duration_us) + u64 duration_ns) { int i; @@ -216,7 +213,7 @@ static int teo_find_shallower_state(struct cpuidle_driver *drv, continue; state_idx = i; - if (drv->states[i].target_residency <= duration_us) + if (drv->states[i].target_residency_ns <= duration_ns) break; } return state_idx; @@ -232,8 +229,9 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, bool *stop_tick) { struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu); - int latency_req = cpuidle_governor_latency_req(dev->cpu); - unsigned int duration_us, hits, misses, early_hits; + s64 latency_req = cpuidle_governor_latency_req(dev->cpu); + u64 duration_ns; + unsigned int hits, misses, early_hits; int max_early_idx, constraint_idx, idx, i; ktime_t delta_tick; @@ -244,8 +242,8 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, cpu_data->time_span_ns = local_clock(); - cpu_data->sleep_length_ns = tick_nohz_get_sleep_length(&delta_tick); - duration_us = ktime_to_us(cpu_data->sleep_length_ns); + duration_ns = tick_nohz_get_sleep_length(&delta_tick); + cpu_data->sleep_length_ns = duration_ns; hits = 0; misses = 0; @@ -262,7 +260,7 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * Ignore disabled states with target residencies beyond * the anticipated idle duration. */ - if (s->target_residency > duration_us) + if (s->target_residency_ns > duration_ns) continue; /* @@ -301,7 +299,7 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * shallow for that role. */ if (!(tick_nohz_tick_stopped() && - drv->states[idx].target_residency < TICK_USEC)) { + drv->states[idx].target_residency_ns < TICK_NSEC)) { early_hits = cpu_data->states[i].early_hits; max_early_idx = idx; } @@ -315,10 +313,10 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, misses = cpu_data->states[i].misses; } - if (s->target_residency > duration_us) + if (s->target_residency_ns > duration_ns) break; - if (s->exit_latency > latency_req && constraint_idx > i) + if (s->exit_latency_ns > latency_req && constraint_idx > i) constraint_idx = i; idx = i; @@ -327,7 +325,7 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, if (early_hits < cpu_data->states[i].early_hits && !(tick_nohz_tick_stopped() && - drv->states[i].target_residency < TICK_USEC)) { + drv->states[i].target_residency_ns < TICK_NSEC)) { early_hits = cpu_data->states[i].early_hits; max_early_idx = i; } @@ -343,7 +341,7 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, */ if (hits <= misses && max_early_idx >= 0) { idx = max_early_idx; - duration_us = drv->states[idx].target_residency; + duration_ns = drv->states[idx].target_residency_ns; } /* @@ -364,9 +362,9 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * the current expected idle duration value. */ for (i = 0; i < INTERVALS; i++) { - unsigned int val = cpu_data->intervals[i]; + u64 val = cpu_data->intervals[i]; - if (val >= duration_us) + if (val >= duration_ns) continue; count++; @@ -378,17 +376,17 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * values are in the interesting range. */ if (count > INTERVALS / 2) { - unsigned int avg_us = div64_u64(sum, count); + u64 avg_ns = div64_u64(sum, count); /* * Avoid spending too much time in an idle state that * would be too shallow. */ - if (!(tick_nohz_tick_stopped() && avg_us < TICK_USEC)) { - duration_us = avg_us; - if (drv->states[idx].target_residency > avg_us) + if (!(tick_nohz_tick_stopped() && avg_ns < TICK_NSEC)) { + duration_ns = avg_ns; + if (drv->states[idx].target_residency_ns > avg_ns) idx = teo_find_shallower_state(drv, dev, - idx, avg_us); + idx, avg_ns); } } } @@ -398,9 +396,7 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * expected idle duration is shorter than the tick period length. */ if (((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) || - duration_us < TICK_USEC) && !tick_nohz_tick_stopped()) { - unsigned int delta_tick_us = ktime_to_us(delta_tick); - + duration_ns < TICK_NSEC) && !tick_nohz_tick_stopped()) { *stop_tick = false; /* @@ -409,8 +405,8 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * till the closest timer including the tick, try to correct * that. */ - if (idx > 0 && drv->states[idx].target_residency > delta_tick_us) - idx = teo_find_shallower_state(drv, dev, idx, delta_tick_us); + if (idx > 0 && drv->states[idx].target_residency_ns > delta_tick) + idx = teo_find_shallower_state(drv, dev, idx, delta_tick); } return idx; @@ -454,7 +450,7 @@ static int teo_enable_device(struct cpuidle_driver *drv, memset(cpu_data, 0, sizeof(*cpu_data)); for (i = 0; i < INTERVALS; i++) - cpu_data->intervals[i] = UINT_MAX; + cpu_data->intervals[i] = U64_MAX; return 0; } diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c index c8fa5f41dfc4..9f1ace9c53da 100644 --- a/drivers/cpuidle/poll_state.c +++ b/drivers/cpuidle/poll_state.c @@ -49,6 +49,8 @@ void cpuidle_poll_state_init(struct cpuidle_driver *drv) snprintf(state->desc, CPUIDLE_DESC_LEN, "CPUIDLE CORE POLL IDLE"); state->exit_latency = 0; state->target_residency = 0; + state->exit_latency_ns = 0; + state->target_residency_ns = 0; state->power_usage = -1; state->enter = poll_idle; state->disabled = false; diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c index 9f3755ac8f87..38ef770be90d 100644 --- a/drivers/cpuidle/sysfs.c +++ b/drivers/cpuidle/sysfs.c @@ -273,16 +273,30 @@ static ssize_t show_state_##_name(struct cpuidle_state *state, \ return sprintf(buf, "%s\n", state->_name);\ } -define_show_state_function(exit_latency) -define_show_state_function(target_residency) +#define define_show_state_time_function(_name) \ +static ssize_t show_state_##_name(struct cpuidle_state *state, \ + struct cpuidle_state_usage *state_usage, \ + char *buf) \ +{ \ + return sprintf(buf, "%llu\n", ktime_to_us(state->_name##_ns)); \ +} + +define_show_state_time_function(exit_latency) +define_show_state_time_function(target_residency) define_show_state_function(power_usage) define_show_state_ull_function(usage) -define_show_state_ull_function(time) define_show_state_str_function(name) define_show_state_str_function(desc) define_show_state_ull_function(above) define_show_state_ull_function(below) +static ssize_t show_state_time(struct cpuidle_state *state, + struct cpuidle_state_usage *state_usage, + char *buf) +{ + return sprintf(buf, "%llu\n", ktime_to_us(state_usage->time_ns)); +} + static ssize_t show_state_disable(struct cpuidle_state *state, struct cpuidle_state_usage *state_usage, char *buf) diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index d23a3b1ddcf6..22602747f468 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -35,7 +35,7 @@ struct cpuidle_driver; struct cpuidle_state_usage { unsigned long long disable; unsigned long long usage; - unsigned long long time; /* in US */ + u64 time_ns; unsigned long long above; /* Number of times it's been too deep */ unsigned long long below; /* Number of times it's been too shallow */ #ifdef CONFIG_SUSPEND @@ -48,6 +48,8 @@ struct cpuidle_state { char name[CPUIDLE_NAME_LEN]; char desc[CPUIDLE_DESC_LEN]; + u64 exit_latency_ns; + u64 target_residency_ns; unsigned int flags; unsigned int exit_latency; /* in US */ int power_usage; /* in mW */ @@ -89,7 +91,7 @@ struct cpuidle_device { ktime_t next_hrtimer; int last_state_idx; - int last_residency; + u64 last_residency_ns; u64 poll_limit_ns; struct cpuidle_state_usage states_usage[CPUIDLE_STATE_MAX]; struct cpuidle_state_kobj *kobjs[CPUIDLE_STATE_MAX]; @@ -263,7 +265,7 @@ struct cpuidle_governor { #ifdef CONFIG_CPU_IDLE extern int cpuidle_register_governor(struct cpuidle_governor *gov); -extern int cpuidle_governor_latency_req(unsigned int cpu); +extern s64 cpuidle_governor_latency_req(unsigned int cpu); #else static inline int cpuidle_register_governor(struct cpuidle_governor *gov) {return 0;} diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 8dad5aa600ea..1aa260702b38 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -104,7 +104,7 @@ static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev, * update no idle residency and return. */ if (current_clr_polling_and_test()) { - dev->last_residency = 0; + dev->last_residency_ns = 0; local_irq_enable(); return -EBUSY; } -- cgit v1.2.3-71-gd317 From 50ec88120ea16cf8b9aabf8422c364166ce3ee17 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 8 Oct 2019 19:20:39 +0300 Subject: can: mcp251x: get rid of legacy platform data Instead of using legacy platform data, switch to use device properties. For clock frequency we are using well established clock-frequency property. Users, two for now, are also converted here. Cc: Daniel Mack Cc: Haojian Zhuang Cc: Robert Jarzmik Cc: Russell King Signed-off-by: Andy Shevchenko Signed-off-by: Marc Kleine-Budde --- arch/arm/mach-pxa/icontrol.c | 9 +++++---- arch/arm/mach-pxa/zeus.c | 9 +++++---- drivers/net/can/spi/mcp251x.c | 9 ++++----- include/linux/can/platform/mcp251x.h | 22 ---------------------- 4 files changed, 14 insertions(+), 35 deletions(-) delete mode 100644 include/linux/can/platform/mcp251x.h (limited to 'include/linux') diff --git a/arch/arm/mach-pxa/icontrol.c b/arch/arm/mach-pxa/icontrol.c index 865b10344ea2..0474a4b1394d 100644 --- a/arch/arm/mach-pxa/icontrol.c +++ b/arch/arm/mach-pxa/icontrol.c @@ -12,6 +12,7 @@ #include #include +#include #include #include @@ -22,7 +23,6 @@ #include #include -#include #include #include "generic.h" @@ -69,8 +69,9 @@ static struct pxa2xx_spi_chip mcp251x_chip_info4 = { .gpio_cs = ICONTROL_MCP251x_nCS4 }; -static struct mcp251x_platform_data mcp251x_info = { - .oscillator_frequency = 16E6, +static const struct property_entry mcp251x_properties[] = { + PROPERTY_ENTRY_U32("clock-frequency", 16000000), + {} }; static struct spi_board_info mcp251x_board_info[] = { @@ -79,7 +80,7 @@ static struct spi_board_info mcp251x_board_info[] = { .max_speed_hz = 6500000, .bus_num = 3, .chip_select = 0, - .platform_data = &mcp251x_info, + .properties = mcp251x_properties, .controller_data = &mcp251x_chip_info1, .irq = PXA_GPIO_TO_IRQ(ICONTROL_MCP251x_nIRQ1) }, diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c index da113c8eefbf..b27fc7ac9cea 100644 --- a/arch/arm/mach-pxa/zeus.c +++ b/arch/arm/mach-pxa/zeus.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -27,7 +28,6 @@ #include #include #include -#include #include #include @@ -428,14 +428,15 @@ static struct gpiod_lookup_table can_regulator_gpiod_table = { }, }; -static struct mcp251x_platform_data zeus_mcp2515_pdata = { - .oscillator_frequency = 16*1000*1000, +static const struct property_entry mcp251x_properties[] = { + PROPERTY_ENTRY_U32("clock-frequency", 16000000), + {} }; static struct spi_board_info zeus_spi_board_info[] = { [0] = { .modalias = "mcp2515", - .platform_data = &zeus_mcp2515_pdata, + .properties = mcp251x_properties, .irq = PXA_GPIO_TO_IRQ(ZEUS_CAN_GPIO), .max_speed_hz = 1*1000*1000, .bus_num = 3, diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index bb20a9b75cc6..ee2e97da4e1d 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -22,7 +22,6 @@ #include #include #include -#include #include #include #include @@ -986,19 +985,19 @@ MODULE_DEVICE_TABLE(spi, mcp251x_id_table); static int mcp251x_can_probe(struct spi_device *spi) { const void *match = device_get_match_data(&spi->dev); - struct mcp251x_platform_data *pdata = dev_get_platdata(&spi->dev); struct net_device *net; struct mcp251x_priv *priv; struct clk *clk; - int freq, ret; + u32 freq; + int ret; clk = devm_clk_get_optional(&spi->dev, NULL); if (IS_ERR(clk)) return PTR_ERR(clk); freq = clk_get_rate(clk); - if (freq == 0 && pdata) - freq = pdata->oscillator_frequency; + if (freq == 0) + device_property_read_u32(&spi->dev, "clock-frequency", &freq); /* Sanity check */ if (freq < 1000000 || freq > 25000000) diff --git a/include/linux/can/platform/mcp251x.h b/include/linux/can/platform/mcp251x.h deleted file mode 100644 index 9e5ac27fb6c1..000000000000 --- a/include/linux/can/platform/mcp251x.h +++ /dev/null @@ -1,22 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _CAN_PLATFORM_MCP251X_H -#define _CAN_PLATFORM_MCP251X_H - -/* - * - * CAN bus driver for Microchip 251x CAN Controller with SPI Interface - * - */ - -#include - -/* - * struct mcp251x_platform_data - MCP251X SPI CAN controller platform data - * @oscillator_frequency: - oscillator frequency in Hz - */ - -struct mcp251x_platform_data { - unsigned long oscillator_frequency; -}; - -#endif /* !_CAN_PLATFORM_MCP251X_H */ -- cgit v1.2.3-71-gd317 From 61d2350615c2c42f7af65d9a575f5dbf9738a10e Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 7 Oct 2019 13:36:58 +0200 Subject: can: rx-offload: can_rx_offload_reset(): remove no-op function This patch removes the function can_rx_offload_reset(), as it does nothing. If we ever need this function, add it back again. Signed-off-by: Marc Kleine-Budde --- drivers/net/can/rx-offload.c | 7 ------- include/linux/can/rx-offload.h | 1 - 2 files changed, 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/can/rx-offload.c b/drivers/net/can/rx-offload.c index 412a8cec5d18..8d120a3750fa 100644 --- a/drivers/net/can/rx-offload.c +++ b/drivers/net/can/rx-offload.c @@ -348,7 +348,6 @@ static int can_rx_offload_init_queue(struct net_device *dev, offload->skb_queue_len_max *= 4; skb_queue_head_init(&offload->skb_queue); - can_rx_offload_reset(offload); netif_napi_add(dev, &offload->napi, can_rx_offload_napi_poll, weight); dev_dbg(dev->dev.parent, "%s: skb_queue_len_max=%d\n", @@ -390,7 +389,6 @@ EXPORT_SYMBOL_GPL(can_rx_offload_add_fifo); void can_rx_offload_enable(struct can_rx_offload *offload) { - can_rx_offload_reset(offload); napi_enable(&offload->napi); } EXPORT_SYMBOL_GPL(can_rx_offload_enable); @@ -401,8 +399,3 @@ void can_rx_offload_del(struct can_rx_offload *offload) skb_queue_purge(&offload->skb_queue); } EXPORT_SYMBOL_GPL(can_rx_offload_del); - -void can_rx_offload_reset(struct can_rx_offload *offload) -{ -} -EXPORT_SYMBOL_GPL(can_rx_offload_reset); diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index 01219f2902bf..fc75e9a7ad2f 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -44,7 +44,6 @@ unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload, unsigned int idx, u32 timestamp); int can_rx_offload_queue_tail(struct can_rx_offload *offload, struct sk_buff *skb); -void can_rx_offload_reset(struct can_rx_offload *offload); void can_rx_offload_del(struct can_rx_offload *offload); void can_rx_offload_enable(struct can_rx_offload *offload); -- cgit v1.2.3-71-gd317 From 4e9c9484b085dbba60b299182dd490eaeb84d18a Mon Sep 17 00:00:00 2001 From: Joakim Zhang Date: Fri, 12 Jul 2019 08:02:38 +0000 Subject: can: rx-offload: Prepare for CAN FD support The skbs for classic CAN and CAN FD frames are allocated with seperate functions: alloc_can_skb() and alloc_canfd_skb(). In order to support CAN FD frames via the rx-offload helper, the driver itself has to allocate the skb (depending whether it received a classic CAN or CAN FD frame), as the rx-offload helper cannot know which kind of CAN frame the driver has received. This patch moves the allocation of the skb into the struct can_rx_offload::mailbox_read callbacks of the the flexcan and ti_hecc driver and adjusts the rx-offload helper accordingly. Signed-off-by: Joakim Zhang Signed-off-by: Marc Kleine-Budde --- drivers/net/can/flexcan.c | 27 +++++++++++----- drivers/net/can/rx-offload.c | 70 ++++++++++-------------------------------- drivers/net/can/ti_hecc.c | 26 ++++++++++++---- include/linux/can/rx-offload.h | 6 ++-- 4 files changed, 60 insertions(+), 69 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index 57f9a2f51085..1a8198163b80 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -783,16 +783,23 @@ static inline struct flexcan_priv *rx_offload_to_priv(struct can_rx_offload *off return container_of(offload, struct flexcan_priv, offload); } -static unsigned int flexcan_mailbox_read(struct can_rx_offload *offload, - struct can_frame *cf, - u32 *timestamp, unsigned int n) +static struct sk_buff *flexcan_mailbox_read(struct can_rx_offload *offload, + unsigned int n, u32 *timestamp, + bool drop) { struct flexcan_priv *priv = rx_offload_to_priv(offload); struct flexcan_regs __iomem *regs = priv->regs; struct flexcan_mb __iomem *mb; + struct sk_buff *skb; + struct can_frame *cf; u32 reg_ctrl, reg_id, reg_iflag1; int i; + if (unlikely(drop)) { + skb = ERR_PTR(-ENOBUFS); + goto mark_as_read; + } + mb = flexcan_get_mb(priv, n); if (priv->devtype_data->quirks & FLEXCAN_QUIRK_USE_OFF_TIMESTAMP) { @@ -806,7 +813,7 @@ static unsigned int flexcan_mailbox_read(struct can_rx_offload *offload, code = reg_ctrl & FLEXCAN_MB_CODE_MASK; if ((code != FLEXCAN_MB_CODE_RX_FULL) && (code != FLEXCAN_MB_CODE_RX_OVERRUN)) - return 0; + return NULL; if (code == FLEXCAN_MB_CODE_RX_OVERRUN) { /* This MB was overrun, we lost data */ @@ -816,11 +823,17 @@ static unsigned int flexcan_mailbox_read(struct can_rx_offload *offload, } else { reg_iflag1 = priv->read(®s->iflag1); if (!(reg_iflag1 & FLEXCAN_IFLAG_RX_FIFO_AVAILABLE)) - return 0; + return NULL; reg_ctrl = priv->read(&mb->can_ctrl); } + skb = alloc_can_skb(offload->dev, &cf); + if (!skb) { + skb = ERR_PTR(-ENOMEM); + goto mark_as_read; + } + /* increase timstamp to full 32 bit */ *timestamp = reg_ctrl << 16; @@ -839,7 +852,7 @@ static unsigned int flexcan_mailbox_read(struct can_rx_offload *offload, *(__be32 *)(cf->data + i) = data; } - /* mark as read */ + mark_as_read: if (priv->devtype_data->quirks & FLEXCAN_QUIRK_USE_OFF_TIMESTAMP) { /* Clear IRQ */ if (n < 32) @@ -856,7 +869,7 @@ static unsigned int flexcan_mailbox_read(struct can_rx_offload *offload, */ priv->read(®s->timer); - return 1; + return skb; } diff --git a/drivers/net/can/rx-offload.c b/drivers/net/can/rx-offload.c index 8d120a3750fa..e8328910a234 100644 --- a/drivers/net/can/rx-offload.c +++ b/drivers/net/can/rx-offload.c @@ -139,71 +139,35 @@ static int can_rx_offload_compare(struct sk_buff *a, struct sk_buff *b) static struct sk_buff * can_rx_offload_offload_one(struct can_rx_offload *offload, unsigned int n) { - struct sk_buff *skb = NULL, *skb_error = NULL; + struct sk_buff *skb; struct can_rx_offload_cb *cb; - struct can_frame *cf; - int ret; - - if (likely(skb_queue_len(&offload->skb_queue) < - offload->skb_queue_len_max)) { - skb = alloc_can_skb(offload->dev, &cf); - if (unlikely(!skb)) - skb_error = ERR_PTR(-ENOMEM); /* skb alloc failed */ - } else { - skb_error = ERR_PTR(-ENOBUFS); /* skb_queue is full */ - } - - /* If queue is full or skb not available, drop by reading into - * overflow buffer. - */ - if (unlikely(skb_error)) { - struct can_frame cf_overflow; - u32 timestamp; - - ret = offload->mailbox_read(offload, &cf_overflow, - ×tamp, n); - - /* Mailbox was empty. */ - if (unlikely(!ret)) - return NULL; - - /* Mailbox has been read and we're dropping it or - * there was a problem reading the mailbox. - * - * Increment error counters in any case. - */ - offload->dev->stats.rx_dropped++; - offload->dev->stats.rx_fifo_errors++; - - /* There was a problem reading the mailbox, propagate - * error value. - */ - if (unlikely(ret < 0)) - return ERR_PTR(ret); - - return skb_error; - } + bool drop = false; + u32 timestamp; - cb = can_rx_offload_get_cb(skb); - ret = offload->mailbox_read(offload, cf, &cb->timestamp, n); + /* If queue is full drop frame */ + if (unlikely(skb_queue_len(&offload->skb_queue) > + offload->skb_queue_len_max)) + drop = true; + skb = offload->mailbox_read(offload, n, ×tamp, drop); /* Mailbox was empty. */ - if (unlikely(!ret)) { - kfree_skb(skb); + if (unlikely(!skb)) return NULL; - } - - /* There was a problem reading the mailbox, propagate error value. */ - if (unlikely(ret < 0)) { - kfree_skb(skb); + /* There was a problem reading the mailbox, propagate + * error value. + */ + if (unlikely(IS_ERR(skb))) { offload->dev->stats.rx_dropped++; offload->dev->stats.rx_fifo_errors++; - return ERR_PTR(ret); + return skb; } /* Mailbox was read. */ + cb = can_rx_offload_get_cb(skb); + cb->timestamp = timestamp; + return skb; } diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c index 31ad364a89bb..94b1491b569f 100644 --- a/drivers/net/can/ti_hecc.c +++ b/drivers/net/can/ti_hecc.c @@ -535,15 +535,28 @@ struct ti_hecc_priv *rx_offload_to_priv(struct can_rx_offload *offload) return container_of(offload, struct ti_hecc_priv, offload); } -static unsigned int ti_hecc_mailbox_read(struct can_rx_offload *offload, - struct can_frame *cf, - u32 *timestamp, unsigned int mbxno) +static struct sk_buff *ti_hecc_mailbox_read(struct can_rx_offload *offload, + unsigned int mbxno, u32 *timestamp, + bool drop) { struct ti_hecc_priv *priv = rx_offload_to_priv(offload); + struct sk_buff *skb; + struct can_frame *cf; u32 data, mbx_mask; - int ret = 1; mbx_mask = BIT(mbxno); + + if (unlikely(drop)) { + skb = ERR_PTR(-ENOBUFS); + goto mark_as_read; + } + + skb = alloc_can_skb(offload->dev, &cf); + if (unlikely(!skb)) { + skb = ERR_PTR(-ENOMEM); + goto mark_as_read; + } + data = hecc_read_mbx(priv, mbxno, HECC_CANMID); if (data & HECC_CANMID_IDE) cf->can_id = (data & CAN_EFF_MASK) | CAN_EFF_FLAG; @@ -578,11 +591,12 @@ static unsigned int ti_hecc_mailbox_read(struct can_rx_offload *offload, */ if (unlikely(mbxno == HECC_RX_LAST_MBOX && hecc_read(priv, HECC_CANRML) & mbx_mask)) - ret = -ENOBUFS; + skb = ERR_PTR(-ENOBUFS); + mark_as_read: hecc_write(priv, HECC_CANRMP, mbx_mask); - return ret; + return skb; } static int ti_hecc_error(struct net_device *ndev, int int_status, diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index fc75e9a7ad2f..1b78a0cfb615 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -15,9 +15,9 @@ struct can_rx_offload { struct net_device *dev; - unsigned int (*mailbox_read)(struct can_rx_offload *offload, - struct can_frame *cf, - u32 *timestamp, unsigned int mb); + struct sk_buff *(*mailbox_read)(struct can_rx_offload *offload, + unsigned int mb, u32 *timestamp, + bool drop); struct sk_buff_head skb_queue; u32 skb_queue_len_max; -- cgit v1.2.3-71-gd317 From 4238fad366a660cbc6499ca1ea4be42bd4d1ac5b Mon Sep 17 00:00:00 2001 From: Nayna Jain Date: Wed, 30 Oct 2019 23:31:27 -0400 Subject: powerpc/ima: Add support to initialize ima policy rules PowerNV systems use a Linux-based bootloader, which rely on the IMA subsystem to enforce different secure boot modes. Since the verification policy may differ based on the secure boot mode of the system, the policies must be defined at runtime. This patch implements arch-specific support to define IMA policy rules based on the runtime secure boot mode of the system. This patch provides arch-specific IMA policies if PPC_SECURE_BOOT config is enabled. Signed-off-by: Nayna Jain Signed-off-by: Mimi Zohar Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/1572492694-6520-3-git-send-email-zohar@linux.ibm.com --- arch/powerpc/Kconfig | 1 + arch/powerpc/kernel/Makefile | 2 +- arch/powerpc/kernel/ima_arch.c | 43 ++++++++++++++++++++++++++++++++++++++++++ include/linux/ima.h | 3 ++- 4 files changed, 47 insertions(+), 2 deletions(-) create mode 100644 arch/powerpc/kernel/ima_arch.c (limited to 'include/linux') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 56ea0019b616..c795039bdc73 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -938,6 +938,7 @@ config PPC_SECURE_BOOT prompt "Enable secure boot support" bool depends on PPC_POWERNV + depends on IMA_ARCH_POLICY help Systems with firmware secure boot enabled need to define security policies to extend secure boot to the OS. This config allows a user diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index e2a54fa240ac..e8eb2955b7d5 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -161,7 +161,7 @@ ifneq ($(CONFIG_PPC_POWERNV)$(CONFIG_PPC_SVM),) obj-y += ucall.o endif -obj-$(CONFIG_PPC_SECURE_BOOT) += secure_boot.o +obj-$(CONFIG_PPC_SECURE_BOOT) += secure_boot.o ima_arch.o # Disable GCOV, KCOV & sanitizers in odd or sensitive code GCOV_PROFILE_prom_init.o := n diff --git a/arch/powerpc/kernel/ima_arch.c b/arch/powerpc/kernel/ima_arch.c new file mode 100644 index 000000000000..d88913dc0da7 --- /dev/null +++ b/arch/powerpc/kernel/ima_arch.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 IBM Corporation + * Author: Nayna Jain + */ + +#include +#include + +bool arch_ima_get_secureboot(void) +{ + return is_ppc_secureboot_enabled(); +} + +/* + * The "secure_rules" are enabled only on "secureboot" enabled systems. + * These rules verify the file signatures against known good values. + * The "appraise_type=imasig|modsig" option allows the known good signature + * to be stored as an xattr or as an appended signature. + * + * To avoid duplicate signature verification as much as possible, the IMA + * policy rule for module appraisal is added only if CONFIG_MODULE_SIG_FORCE + * is not enabled. + */ +static const char *const secure_rules[] = { + "appraise func=KEXEC_KERNEL_CHECK appraise_type=imasig|modsig", +#ifndef CONFIG_MODULE_SIG_FORCE + "appraise func=MODULE_CHECK appraise_type=imasig|modsig", +#endif + NULL +}; + +/* + * Returns the relevant IMA arch-specific policies based on the system secure + * boot state. + */ +const char *const *arch_get_ima_policy(void) +{ + if (is_ppc_secureboot_enabled()) + return secure_rules; + + return NULL; +} diff --git a/include/linux/ima.h b/include/linux/ima.h index 1c37f17f7203..6d904754d858 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -29,7 +29,8 @@ extern void ima_kexec_cmdline(const void *buf, int size); extern void ima_add_kexec_buffer(struct kimage *image); #endif -#if (defined(CONFIG_X86) && defined(CONFIG_EFI)) || defined(CONFIG_S390) +#if (defined(CONFIG_X86) && defined(CONFIG_EFI)) || defined(CONFIG_S390) \ + || defined(CONFIG_PPC_SECURE_BOOT) extern bool arch_ima_get_secureboot(void); extern const char * const *arch_get_ima_policy(void); #else -- cgit v1.2.3-71-gd317 From 39a963b457b5c6cbbdc70441c9d496e39d151582 Mon Sep 17 00:00:00 2001 From: Nayna Jain Date: Tue, 1 Oct 2019 19:37:18 -0400 Subject: sysfs: Fixes __BIN_ATTR_WO() macro This patch fixes the size and write parameter for the macro __BIN_ATTR_WO(). Fixes: 7f905761e15a8 ("sysfs: add BIN_ATTR_WO() macro") Signed-off-by: Nayna Jain Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/1569973038-2710-1-git-send-email-nayna@linux.ibm.com --- include/linux/sysfs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 5420817ed317..fa7ee503fb76 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -196,9 +196,9 @@ struct bin_attribute { .size = _size, \ } -#define __BIN_ATTR_WO(_name) { \ +#define __BIN_ATTR_WO(_name, _size) { \ .attr = { .name = __stringify(_name), .mode = 0200 }, \ - .store = _name##_store, \ + .write = _name##_write, \ .size = _size, \ } -- cgit v1.2.3-71-gd317 From 3bbc53f4ae1686b501d92d4a5fd400f4958c8a98 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 7 Nov 2019 10:19:24 +0100 Subject: hrtimer: Remove the comment about not used HRTIMER_SOFTIRQ The softirq `HRTIMER_SOFTIRQ' was not used since commit c6eb3f70d448 ("hrtimer: Get rid of hrtimer softirq"). But it got used again, beginning with commit 5da70160462e ("hrtimer: Implement support for softirq based hrtimers"), which did not remove the comment. Remove it now. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20191107091924.13410-1-bigeasy@linutronix.de --- include/linux/interrupt.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 89fc59dab57d..963c3c695784 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -520,8 +520,7 @@ enum IRQ_POLL_SOFTIRQ, TASKLET_SOFTIRQ, SCHED_SOFTIRQ, - HRTIMER_SOFTIRQ, /* Unused, but kept as tools rely on the - numbering. Sigh! */ + HRTIMER_SOFTIRQ, RCU_SOFTIRQ, /* Preferable RCU should always be the last softirq */ NR_SOFTIRQS -- cgit v1.2.3-71-gd317 From e23f568aa63f64cd6b355094224cc9356c0f696b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 4 Nov 2019 15:54:29 -0800 Subject: kernfs: fix ino wrap-around detection When the 32bit ino wraps around, kernfs increments the generation number to distinguish reused ino instances. The wrap-around detection tests whether the allocated ino is lower than what the cursor but the cursor is pointing to the next ino to allocate so the condition never triggers. Fix it by remembering the last ino and comparing against that. Signed-off-by: Tejun Heo Reviewed-by: Greg Kroah-Hartman Fixes: 4a3ef68acacf ("kernfs: implement i_generation") Cc: Namhyung Kim Cc: stable@vger.kernel.org # v4.14+ --- fs/kernfs/dir.c | 5 ++--- include/linux/kernfs.h | 1 + 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 6ebae6bbe6a5..7d4af6cea2a6 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -622,7 +622,6 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, { struct kernfs_node *kn; u32 gen; - int cursor; int ret; name = kstrdup_const(name, GFP_KERNEL); @@ -635,11 +634,11 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, idr_preload(GFP_KERNEL); spin_lock(&kernfs_idr_lock); - cursor = idr_get_cursor(&root->ino_idr); ret = idr_alloc_cyclic(&root->ino_idr, kn, 1, 0, GFP_ATOMIC); - if (ret >= 0 && ret < cursor) + if (ret >= 0 && ret < root->last_ino) root->next_generation++; gen = root->next_generation; + root->last_ino = ret; spin_unlock(&kernfs_idr_lock); idr_preload_end(); if (ret < 0) diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 936b61bd504e..f797ccc650e7 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -187,6 +187,7 @@ struct kernfs_root { /* private fields, do not use outside kernfs proper */ struct idr ino_idr; + u32 last_ino; u32 next_generation; struct kernfs_syscall_ops *syscall_ops; -- cgit v1.2.3-71-gd317 From 67c0496e87d193b8356d2af49ab95e8a1b954b3c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 4 Nov 2019 15:54:30 -0800 Subject: kernfs: convert kernfs_node->id from union kernfs_node_id to u64 kernfs_node->id is currently a union kernfs_node_id which represents either a 32bit (ino, gen) pair or u64 value. I can't see much value in the usage of the union - all that's needed is a 64bit ID which the current code is already limited to. Using a union makes the code unnecessarily complicated and prevents using 64bit ino without adding practical benefits. This patch drops union kernfs_node_id and makes kernfs_node->id a u64. ino is stored in the lower 32bits and gen upper. Accessors - kernfs[_id]_ino() and kernfs[_id]_gen() - are added to retrieve the ino and gen. This simplifies ID handling less cumbersome and will allow using 64bit inos on supported archs. This patch doesn't make any functional changes. Signed-off-by: Tejun Heo Reviewed-by: Greg Kroah-Hartman Cc: Namhyung Kim Cc: Jens Axboe Cc: Alexei Starovoitov --- fs/kernfs/dir.c | 10 +++--- fs/kernfs/file.c | 4 +-- fs/kernfs/inode.c | 4 +-- fs/kernfs/mount.c | 7 ++--- include/linux/cgroup.h | 17 +++++----- include/linux/kernfs.h | 45 ++++++++++++++++----------- include/trace/events/writeback.h | 4 +-- kernel/bpf/helpers.c | 2 +- kernel/bpf/local_storage.c | 2 +- kernel/cgroup/cgroup.c | 3 +- kernel/trace/blktrace.c | 67 +++++++++++++++++++--------------------- net/core/filter.c | 4 +-- 12 files changed, 85 insertions(+), 84 deletions(-) (limited to 'include/linux') diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index beabb585a7d8..c67afb591e5b 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -532,7 +532,7 @@ void kernfs_put(struct kernfs_node *kn) kmem_cache_free(kernfs_iattrs_cache, kn->iattr); } spin_lock(&kernfs_idr_lock); - idr_remove(&root->ino_idr, kn->id.ino); + idr_remove(&root->ino_idr, kernfs_ino(kn)); spin_unlock(&kernfs_idr_lock); kmem_cache_free(kernfs_node_cache, kn); @@ -639,8 +639,8 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, idr_preload_end(); if (ret < 0) goto err_out2; - kn->id.ino = ret; - kn->id.generation = gen; + + kn->id = (u64)gen << 32 | ret; atomic_set(&kn->count, 1); atomic_set(&kn->active, KN_DEACTIVATED_BIAS); @@ -671,7 +671,7 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, return kn; err_out3: - idr_remove(&root->ino_idr, kn->id.ino); + idr_remove(&root->ino_idr, kernfs_ino(kn)); err_out2: kmem_cache_free(kernfs_node_cache, kn); err_out1: @@ -1656,7 +1656,7 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx) const char *name = pos->name; unsigned int type = dt_type(pos); int len = strlen(name); - ino_t ino = pos->id.ino; + ino_t ino = kernfs_ino(pos); ctx->pos = pos->hash; file->private_data = pos; diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index e8c792b49616..34366db3620d 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -892,7 +892,7 @@ repeat: * have the matching @file available. Look up the inodes * and generate the events manually. */ - inode = ilookup(info->sb, kn->id.ino); + inode = ilookup(info->sb, kernfs_ino(kn)); if (!inode) continue; @@ -901,7 +901,7 @@ repeat: if (parent) { struct inode *p_inode; - p_inode = ilookup(info->sb, parent->id.ino); + p_inode = ilookup(info->sb, kernfs_ino(parent)); if (p_inode) { fsnotify(p_inode, FS_MODIFY | FS_EVENT_ON_CHILD, inode, FSNOTIFY_EVENT_INODE, &name, 0); diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index f3eaa8869f42..eac277c63d42 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -201,7 +201,7 @@ static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode) inode->i_private = kn; inode->i_mapping->a_ops = &kernfs_aops; inode->i_op = &kernfs_iops; - inode->i_generation = kn->id.generation; + inode->i_generation = kernfs_gen(kn); set_default_inode_attr(inode, kn->mode); kernfs_refresh_inode(kn, inode); @@ -247,7 +247,7 @@ struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn) { struct inode *inode; - inode = iget_locked(sb, kn->id.ino); + inode = iget_locked(sb, kernfs_ino(kn)); if (inode && (inode->i_state & I_NEW)) kernfs_init_inode(kn, inode); diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index 067b7c380056..f05d5d6f926d 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -57,15 +57,14 @@ const struct super_operations kernfs_sops = { * Similar to kernfs_fh_get_inode, this one gets kernfs node from inode * number and generation */ -struct kernfs_node *kernfs_get_node_by_id(struct kernfs_root *root, - const union kernfs_node_id *id) +struct kernfs_node *kernfs_get_node_by_id(struct kernfs_root *root, u64 id) { struct kernfs_node *kn; - kn = kernfs_find_and_get_node_by_ino(root, id->ino); + kn = kernfs_find_and_get_node_by_ino(root, kernfs_id_ino(id)); if (!kn) return NULL; - if (kn->id.generation != id->generation) { + if (kernfs_gen(kn) != kernfs_id_gen(id)) { kernfs_put(kn); return NULL; } diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index f6b048902d6c..815fff49d555 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -616,7 +616,7 @@ static inline bool cgroup_is_populated(struct cgroup *cgrp) /* returns ino associated with a cgroup */ static inline ino_t cgroup_ino(struct cgroup *cgrp) { - return cgrp->kn->id.ino; + return kernfs_ino(cgrp->kn); } /* cft/css accessors for cftype->write() operation */ @@ -687,13 +687,12 @@ static inline void cgroup_kthread_ready(void) current->no_cgroup_migration = 0; } -static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp) +static inline u64 cgroup_get_kernfs_id(struct cgroup *cgrp) { - return &cgrp->kn->id; + return cgrp->kn->id; } -void cgroup_path_from_kernfs_id(const union kernfs_node_id *id, - char *buf, size_t buflen); +void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen); #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; @@ -718,9 +717,9 @@ static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } static inline void cgroup_init_kthreadd(void) {} static inline void cgroup_kthread_ready(void) {} -static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp) +static inline union u64 cgroup_get_kernfs_id(struct cgroup *cgrp) { - return NULL; + return 0; } static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) @@ -739,8 +738,8 @@ static inline bool task_under_cgroup_hierarchy(struct task_struct *task, return true; } -static inline void cgroup_path_from_kernfs_id(const union kernfs_node_id *id, - char *buf, size_t buflen) {} +static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) +{} #endif /* !CONFIG_CGROUPS */ #ifdef CONFIG_CGROUPS diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index f797ccc650e7..b2fc5c8ef6d9 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -104,21 +104,6 @@ struct kernfs_elem_attr { struct kernfs_node *notify_next; /* for kernfs_notify() */ }; -/* represent a kernfs node */ -union kernfs_node_id { - struct { - /* - * blktrace will export this struct as a simplified 'struct - * fid' (which is a big data struction), so userspace can use - * it to find kernfs node. The layout must match the first two - * fields of 'struct fid' exactly. - */ - u32 ino; - u32 generation; - }; - u64 id; -}; - /* * kernfs_node - the building block of kernfs hierarchy. Each and every * kernfs node is represented by single kernfs_node. Most fields are @@ -155,7 +140,12 @@ struct kernfs_node { void *priv; - union kernfs_node_id id; + /* + * 64bit unique ID. Lower 32bits carry the inode number and lower + * generation. + */ + u64 id; + unsigned short flags; umode_t mode; struct kernfs_iattrs *iattr; @@ -292,6 +282,26 @@ static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn) return kn->flags & KERNFS_TYPE_MASK; } +static inline ino_t kernfs_id_ino(u64 id) +{ + return (u32)id; +} + +static inline u32 kernfs_id_gen(u64 id) +{ + return id >> 32; +} + +static inline ino_t kernfs_ino(struct kernfs_node *kn) +{ + return kernfs_id_ino(kn->id); +} + +static inline ino_t kernfs_gen(struct kernfs_node *kn) +{ + return kernfs_id_gen(kn->id); +} + /** * kernfs_enable_ns - enable namespace under a directory * @kn: directory of interest, should be empty @@ -383,8 +393,7 @@ void kernfs_kill_sb(struct super_block *sb); void kernfs_init(void); -struct kernfs_node *kernfs_get_node_by_id(struct kernfs_root *root, - const union kernfs_node_id *id); +struct kernfs_node *kernfs_get_node_by_id(struct kernfs_root *root, u64 id); #else /* CONFIG_KERNFS */ static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn) diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 95e50677476b..b4f0ffe1817e 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -152,7 +152,7 @@ DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode, static inline ino_t __trace_wb_assign_cgroup(struct bdi_writeback *wb) { - return wb->memcg_css->cgroup->kn->id.ino; + return cgroup_ino(wb->memcg_css->cgroup); } static inline ino_t __trace_wbc_assign_cgroup(struct writeback_control *wbc) @@ -260,7 +260,7 @@ TRACE_EVENT(track_foreign_dirty, __entry->ino = inode ? inode->i_ino : 0; __entry->memcg_id = wb->memcg_css->id; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); - __entry->page_cgroup_ino = page->mem_cgroup->css.cgroup->kn->id.ino; + __entry->page_cgroup_ino = cgroup_ino(page->mem_cgroup->css.cgroup); ), TP_printk("bdi %s[%llu]: ino=%lu memcg_id=%u cgroup_ino=%lu page_cgroup_ino=%lu", diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 5e28718928ca..912e761cd17a 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -317,7 +317,7 @@ BPF_CALL_0(bpf_get_current_cgroup_id) { struct cgroup *cgrp = task_dfl_cgroup(current); - return cgrp->kn->id.id; + return cgrp->kn->id; } const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index addd6fdceec8..5d867f6d7204 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -569,7 +569,7 @@ void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, return; storage->key.attach_type = type; - storage->key.cgroup_inode_id = cgroup->kn->id.id; + storage->key.cgroup_inode_id = cgroup->kn->id; map = storage->map; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index cf32c0c7a45d..c6bd1a5a1977 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5786,8 +5786,7 @@ static int __init cgroup_wq_init(void) } core_initcall(cgroup_wq_init); -void cgroup_path_from_kernfs_id(const union kernfs_node_id *id, - char *buf, size_t buflen) +void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) { struct kernfs_node *kn; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 2d6e93ab0478..a986d2e74ca2 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -64,8 +64,7 @@ static void blk_unregister_tracepoints(void); * Send out a notify message. */ static void trace_note(struct blk_trace *bt, pid_t pid, int action, - const void *data, size_t len, - union kernfs_node_id *cgid) + const void *data, size_t len, u64 cgid) { struct blk_io_trace *t; struct ring_buffer_event *event = NULL; @@ -73,7 +72,7 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action, int pc = 0; int cpu = smp_processor_id(); bool blk_tracer = blk_tracer_enabled; - ssize_t cgid_len = cgid ? sizeof(*cgid) : 0; + ssize_t cgid_len = cgid ? sizeof(cgid) : 0; if (blk_tracer) { buffer = blk_tr->trace_buffer.buffer; @@ -100,8 +99,8 @@ record_it: t->pid = pid; t->cpu = cpu; t->pdu_len = len + cgid_len; - if (cgid) - memcpy((void *)t + sizeof(*t), cgid, cgid_len); + if (cgid_len) + memcpy((void *)t + sizeof(*t), &cgid, cgid_len); memcpy((void *) t + sizeof(*t) + cgid_len, data, len); if (blk_tracer) @@ -122,7 +121,7 @@ static void trace_note_tsk(struct task_struct *tsk) spin_lock_irqsave(&running_trace_lock, flags); list_for_each_entry(bt, &running_trace_list, running_list) { trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm, - sizeof(tsk->comm), NULL); + sizeof(tsk->comm), 0); } spin_unlock_irqrestore(&running_trace_lock, flags); } @@ -139,7 +138,7 @@ static void trace_note_time(struct blk_trace *bt) words[1] = now.tv_nsec; local_irq_save(flags); - trace_note(bt, 0, BLK_TN_TIMESTAMP, words, sizeof(words), NULL); + trace_note(bt, 0, BLK_TN_TIMESTAMP, words, sizeof(words), 0); local_irq_restore(flags); } @@ -172,9 +171,9 @@ void __trace_note_message(struct blk_trace *bt, struct blkcg *blkcg, blkcg = NULL; #ifdef CONFIG_BLK_CGROUP trace_note(bt, 0, BLK_TN_MESSAGE, buf, n, - blkcg ? cgroup_get_kernfs_id(blkcg->css.cgroup) : NULL); + blkcg ? cgroup_get_kernfs_id(blkcg->css.cgroup) : 0); #else - trace_note(bt, 0, BLK_TN_MESSAGE, buf, n, NULL); + trace_note(bt, 0, BLK_TN_MESSAGE, buf, n, 0); #endif local_irq_restore(flags); } @@ -212,7 +211,7 @@ static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ), */ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, int op, int op_flags, u32 what, int error, int pdu_len, - void *pdu_data, union kernfs_node_id *cgid) + void *pdu_data, u64 cgid) { struct task_struct *tsk = current; struct ring_buffer_event *event = NULL; @@ -223,7 +222,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, pid_t pid; int cpu, pc = 0; bool blk_tracer = blk_tracer_enabled; - ssize_t cgid_len = cgid ? sizeof(*cgid) : 0; + ssize_t cgid_len = cgid ? sizeof(cgid) : 0; if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer)) return; @@ -294,7 +293,7 @@ record_it: t->pdu_len = pdu_len + cgid_len; if (cgid_len) - memcpy((void *)t + sizeof(*t), cgid, cgid_len); + memcpy((void *)t + sizeof(*t), &cgid, cgid_len); if (pdu_len) memcpy((void *)t + sizeof(*t) + cgid_len, pdu_data, pdu_len); @@ -751,31 +750,29 @@ void blk_trace_shutdown(struct request_queue *q) } #ifdef CONFIG_BLK_CGROUP -static union kernfs_node_id * -blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) +static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) { struct blk_trace *bt = q->blk_trace; if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) - return NULL; + return 0; if (!bio->bi_blkg) - return NULL; + return 0; return cgroup_get_kernfs_id(bio_blkcg(bio)->css.cgroup); } #else -static union kernfs_node_id * -blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) +u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) { - return NULL; + return 0; } #endif -static union kernfs_node_id * +static u64 blk_trace_request_get_cgid(struct request_queue *q, struct request *rq) { if (!rq->bio) - return NULL; + return 0; /* Use the first bio */ return blk_trace_bio_get_cgid(q, rq->bio); } @@ -797,8 +794,7 @@ blk_trace_request_get_cgid(struct request_queue *q, struct request *rq) * **/ static void blk_add_trace_rq(struct request *rq, int error, - unsigned int nr_bytes, u32 what, - union kernfs_node_id *cgid) + unsigned int nr_bytes, u32 what, u64 cgid) { struct blk_trace *bt = rq->q->blk_trace; @@ -913,7 +909,7 @@ static void blk_add_trace_getrq(void *ignore, if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_GETRQ, 0, 0, - NULL, NULL); + NULL, 0); } } @@ -929,7 +925,7 @@ static void blk_add_trace_sleeprq(void *ignore, if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_SLEEPRQ, - 0, 0, NULL, NULL); + 0, 0, NULL, 0); } } @@ -938,7 +934,7 @@ static void blk_add_trace_plug(void *ignore, struct request_queue *q) struct blk_trace *bt = q->blk_trace; if (bt) - __blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, NULL); + __blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, 0); } static void blk_add_trace_unplug(void *ignore, struct request_queue *q, @@ -955,7 +951,7 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q, else what = BLK_TA_UNPLUG_TIMER; - __blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, NULL); + __blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, 0); } } @@ -1172,19 +1168,17 @@ const struct blk_io_trace *te_blk_io_trace(const struct trace_entry *ent) static inline const void *pdu_start(const struct trace_entry *ent, bool has_cg) { - return (void *)(te_blk_io_trace(ent) + 1) + - (has_cg ? sizeof(union kernfs_node_id) : 0); + return (void *)(te_blk_io_trace(ent) + 1) + (has_cg ? sizeof(u64) : 0); } -static inline const void *cgid_start(const struct trace_entry *ent) +static inline u64 t_cgid(const struct trace_entry *ent) { - return (void *)(te_blk_io_trace(ent) + 1); + return *(u64 *)(te_blk_io_trace(ent) + 1); } static inline int pdu_real_len(const struct trace_entry *ent, bool has_cg) { - return te_blk_io_trace(ent)->pdu_len - - (has_cg ? sizeof(union kernfs_node_id) : 0); + return te_blk_io_trace(ent)->pdu_len - (has_cg ? sizeof(u64) : 0); } static inline u32 t_action(const struct trace_entry *ent) @@ -1257,7 +1251,7 @@ static void blk_log_action(struct trace_iterator *iter, const char *act, fill_rwbs(rwbs, t); if (has_cg) { - const union kernfs_node_id *id = cgid_start(iter->ent); + u64 id = t_cgid(iter->ent); if (blk_tracer_flags.val & TRACE_BLK_OPT_CGNAME) { char blkcg_name_buf[NAME_MAX + 1] = "<...>"; @@ -1269,9 +1263,10 @@ static void blk_log_action(struct trace_iterator *iter, const char *act, blkcg_name_buf, act, rwbs); } else trace_seq_printf(&iter->seq, - "%3d,%-3d %x,%-x %2s %3s ", + "%3d,%-3d %lx,%-x %2s %3s ", MAJOR(t->device), MINOR(t->device), - id->ino, id->generation, act, rwbs); + kernfs_id_ino(id), kernfs_id_gen(id), + act, rwbs); } else trace_seq_printf(&iter->seq, "%3d,%-3d %2s %3s ", MAJOR(t->device), MINOR(t->device), act, rwbs); diff --git a/net/core/filter.c b/net/core/filter.c index ed6563622ce3..b360a7beb6fc 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4089,7 +4089,7 @@ BPF_CALL_1(bpf_skb_cgroup_id, const struct sk_buff *, skb) return 0; cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - return cgrp->kn->id.id; + return cgrp->kn->id; } static const struct bpf_func_proto bpf_skb_cgroup_id_proto = { @@ -4114,7 +4114,7 @@ BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int, if (!ancestor) return 0; - return ancestor->kn->id.id; + return ancestor->kn->id; } static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = { -- cgit v1.2.3-71-gd317 From fe0f726c9fb626b1092a9ea3bf75f57f2eed676e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 4 Nov 2019 15:54:30 -0800 Subject: kernfs: combine ino/id lookup functions into kernfs_find_and_get_node_by_id() kernfs_find_and_get_node_by_ino() looks the kernfs_node matching the specified ino. On top of that, kernfs_get_node_by_id() and kernfs_fh_get_inode() implement full ID matching by testing the rest of ID. On surface, confusingly, the two are slightly different in that the latter uses 0 gen as wildcard while the former doesn't - does it mean that the latter can't uniquely identify inodes w/ 0 gen? In practice, this is a distinction without a difference because generation number starts at 1. There are no actual IDs with 0 gen, so it can always safely used as wildcard. Let's simplify the code by renaming kernfs_find_and_get_node_by_ino() to kernfs_find_and_get_node_by_id(), moving all lookup logics into it, and removing now unnecessary kernfs_get_node_by_id(). Signed-off-by: Tejun Heo Reviewed-by: Greg Kroah-Hartman --- fs/kernfs/dir.c | 17 +++++++++++++---- fs/kernfs/kernfs-internal.h | 2 -- fs/kernfs/mount.c | 26 ++------------------------ include/linux/kernfs.h | 3 ++- kernel/cgroup/cgroup.c | 2 +- 5 files changed, 18 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index c67afb591e5b..5dcf19d4adbc 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -696,17 +696,22 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, } /* - * kernfs_find_and_get_node_by_ino - get kernfs_node from inode number + * kernfs_find_and_get_node_by_id - get kernfs_node from node id * @root: the kernfs root - * @ino: inode number + * @id: the target node id + * + * @id's lower 32bits encode ino and upper gen. If the gen portion is + * zero, all generations are matched. * * RETURNS: * NULL on failure. Return a kernfs node with reference counter incremented */ -struct kernfs_node *kernfs_find_and_get_node_by_ino(struct kernfs_root *root, - unsigned int ino) +struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root, + u64 id) { struct kernfs_node *kn; + ino_t ino = kernfs_id_ino(id); + u32 gen = kernfs_id_gen(id); spin_lock(&kernfs_idr_lock); @@ -714,6 +719,10 @@ struct kernfs_node *kernfs_find_and_get_node_by_ino(struct kernfs_root *root, if (!kn) goto err_unlock; + /* 0 matches all generations */ + if (unlikely(gen && kernfs_gen(kn) != gen)) + goto err_unlock; + /* * ACTIVATED is protected with kernfs_mutex but it was clear when * @kn was added to idr and we just wanna see it set. No need to diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index 02ce570a9a3c..2f3c51d55261 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -109,8 +109,6 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, unsigned flags); -struct kernfs_node *kernfs_find_and_get_node_by_ino(struct kernfs_root *root, - unsigned int ino); /* * file.c diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index f05d5d6f926d..8aed2cccd002 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -53,24 +53,6 @@ const struct super_operations kernfs_sops = { .show_path = kernfs_sop_show_path, }; -/* - * Similar to kernfs_fh_get_inode, this one gets kernfs node from inode - * number and generation - */ -struct kernfs_node *kernfs_get_node_by_id(struct kernfs_root *root, u64 id) -{ - struct kernfs_node *kn; - - kn = kernfs_find_and_get_node_by_ino(root, kernfs_id_ino(id)); - if (!kn) - return NULL; - if (kernfs_gen(kn) != kernfs_id_gen(id)) { - kernfs_put(kn); - return NULL; - } - return kn; -} - static struct inode *kernfs_fh_get_inode(struct super_block *sb, u64 ino, u32 generation) { @@ -81,7 +63,8 @@ static struct inode *kernfs_fh_get_inode(struct super_block *sb, if (ino == 0) return ERR_PTR(-ESTALE); - kn = kernfs_find_and_get_node_by_ino(info->root, ino); + kn = kernfs_find_and_get_node_by_id(info->root, + ino | ((u64)generation << 32)); if (!kn) return ERR_PTR(-ESTALE); inode = kernfs_get_inode(sb, kn); @@ -89,11 +72,6 @@ static struct inode *kernfs_fh_get_inode(struct super_block *sb, if (!inode) return ERR_PTR(-ESTALE); - if (generation && inode->i_generation != generation) { - /* we didn't find the right inode.. */ - iput(inode); - return ERR_PTR(-ESTALE); - } return inode; } diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index b2fc5c8ef6d9..38267cc9420c 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -393,7 +393,8 @@ void kernfs_kill_sb(struct super_block *sb); void kernfs_init(void); -struct kernfs_node *kernfs_get_node_by_id(struct kernfs_root *root, u64 id); +struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root, + u64 id); #else /* CONFIG_KERNFS */ static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index c6bd1a5a1977..b5dcbee5aa6c 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5790,7 +5790,7 @@ void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) { struct kernfs_node *kn; - kn = kernfs_get_node_by_id(cgrp_dfl_root.kf_root, id); + kn = kernfs_find_and_get_node_by_id(cgrp_dfl_root.kf_root, id); if (!kn) return; kernfs_path(kn, buf, buflen); -- cgit v1.2.3-71-gd317 From 33c5ac9175195c36a0b7005aaf503a2e81f117a1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 4 Nov 2019 15:54:30 -0800 Subject: kernfs: implement custom exportfs ops and fid type The current kernfs exportfs implementation uses the generic_fh_*() helpers and FILEID_INO32_GEN[_PARENT] which limits ino to 32bits. Let's implement custom exportfs operations and fid type to remove the restriction. * FILEID_KERNFS is a single u64 value whose content is kernfs_node->id. This is the only native fid type. * For backward compatibility with blk_log_action() path which exposes (ino,gen) pairs which userland assembles into FILEID_INO32_GEN keys, combine the generic keys into 64bit IDs in the same order. Signed-off-by: Tejun Heo Reviewed-by: Greg Kroah-Hartman Cc: Namhyung Kim --- fs/kernfs/mount.c | 77 ++++++++++++++++++++++++++++++++++++++---------- include/linux/exportfs.h | 5 ++++ 2 files changed, 66 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index 8aed2cccd002..37a1e5df117a 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -53,40 +53,84 @@ const struct super_operations kernfs_sops = { .show_path = kernfs_sop_show_path, }; -static struct inode *kernfs_fh_get_inode(struct super_block *sb, - u64 ino, u32 generation) +static int kernfs_encode_fh(struct inode *inode, __u32 *fh, int *max_len, + struct inode *parent) +{ + struct kernfs_node *kn = inode->i_private; + + if (*max_len < 2) { + *max_len = 2; + return FILEID_INVALID; + } + + *max_len = 2; + *(u64 *)fh = kn->id; + return FILEID_KERNFS; +} + +static struct dentry *__kernfs_fh_to_dentry(struct super_block *sb, + struct fid *fid, int fh_len, + int fh_type, bool get_parent) { struct kernfs_super_info *info = kernfs_info(sb); - struct inode *inode; struct kernfs_node *kn; + struct inode *inode; + u64 id; - if (ino == 0) - return ERR_PTR(-ESTALE); + if (fh_len < 2) + return NULL; + + switch (fh_type) { + case FILEID_KERNFS: + id = *(u64 *)fid; + break; + case FILEID_INO32_GEN: + case FILEID_INO32_GEN_PARENT: + /* + * blk_log_action() exposes (ino,gen) pair without type and + * userland can call us with generic fid constructed from + * them. Combine it back to ID. See blk_log_action(). + */ + id = ((u64)fid->i32.gen << 32) | fid->i32.ino; + break; + default: + return NULL; + } - kn = kernfs_find_and_get_node_by_id(info->root, - ino | ((u64)generation << 32)); + kn = kernfs_find_and_get_node_by_id(info->root, id); if (!kn) return ERR_PTR(-ESTALE); + + if (get_parent) { + struct kernfs_node *parent; + + parent = kernfs_get_parent(kn); + kernfs_put(kn); + kn = parent; + if (!kn) + return ERR_PTR(-ESTALE); + } + inode = kernfs_get_inode(sb, kn); kernfs_put(kn); if (!inode) return ERR_PTR(-ESTALE); - return inode; + return d_obtain_alias(inode); } -static struct dentry *kernfs_fh_to_dentry(struct super_block *sb, struct fid *fid, - int fh_len, int fh_type) +static struct dentry *kernfs_fh_to_dentry(struct super_block *sb, + struct fid *fid, int fh_len, + int fh_type) { - return generic_fh_to_dentry(sb, fid, fh_len, fh_type, - kernfs_fh_get_inode); + return __kernfs_fh_to_dentry(sb, fid, fh_len, fh_type, false); } -static struct dentry *kernfs_fh_to_parent(struct super_block *sb, struct fid *fid, - int fh_len, int fh_type) +static struct dentry *kernfs_fh_to_parent(struct super_block *sb, + struct fid *fid, int fh_len, + int fh_type) { - return generic_fh_to_parent(sb, fid, fh_len, fh_type, - kernfs_fh_get_inode); + return __kernfs_fh_to_dentry(sb, fid, fh_len, fh_type, true); } static struct dentry *kernfs_get_parent_dentry(struct dentry *child) @@ -97,6 +141,7 @@ static struct dentry *kernfs_get_parent_dentry(struct dentry *child) } static const struct export_operations kernfs_export_ops = { + .encode_fh = kernfs_encode_fh, .fh_to_dentry = kernfs_fh_to_dentry, .fh_to_parent = kernfs_fh_to_parent, .get_parent = kernfs_get_parent_dentry, diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index cf6571fc9c01..d896b8657085 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -104,6 +104,11 @@ enum fid_type { */ FILEID_LUSTRE = 0x97, + /* + * 64 bit unique kernfs id + */ + FILEID_KERNFS = 0xfe, + /* * Filesystems must not use 0xff file ID. */ -- cgit v1.2.3-71-gd317 From 40430452fd5da1509177ac597b394614cd3a121f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 4 Nov 2019 15:54:30 -0800 Subject: kernfs: use 64bit inos if ino_t is 64bit Each kernfs_node is identified with a 64bit ID. The low 32bit is exposed as ino and the high gen. While this already allows using inos as keys by looking up with wildcard generation number of 0, it's adding unnecessary complications for 64bit ino archs which can directly use kernfs_node IDs as inos to uniquely identify each cgroup instance. This patch exposes IDs directly as inos on 64bit ino archs. The conversion is mostly straight-forward. * 32bit ino archs behave the same as before. 64bit ino archs now use the whole 64bit ID as ino and the generation number is fixed at 1. * 64bit inos still use the same idr allocator which gurantees that the lower 32bits identify the current live instance uniquely and the high 32bits are incremented whenever the low bits wrap. As the upper 32bits are no longer used as gen and we don't wanna start ino allocation with 33rd bit set, the initial value for highbits allocation is changed to 0 on 64bit ino archs. * blktrace exposes two 32bit numbers - (INO,GEN) pair - to identify the issuing cgroup. Userland builds FILEID_INO32_GEN fids from these numbers to look up the cgroups. To remain compatible with the behavior, always output (LOW32,HIGH32) which will be constructed back to the original 64bit ID by __kernfs_fh_to_dentry(). Signed-off-by: Tejun Heo Reviewed-by: Greg Kroah-Hartman Cc: Namhyung Kim --- fs/kernfs/dir.c | 42 +++++++++++++++++++++++++++++------------- fs/kernfs/mount.c | 7 ++++--- include/linux/kernfs.h | 20 ++++++++++++++------ kernel/trace/blktrace.c | 21 +++++++++++++++++---- 4 files changed, 64 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 5dcf19d4adbc..b2d9f79c4a7c 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -532,7 +532,7 @@ void kernfs_put(struct kernfs_node *kn) kmem_cache_free(kernfs_iattrs_cache, kn->iattr); } spin_lock(&kernfs_idr_lock); - idr_remove(&root->ino_idr, kernfs_ino(kn)); + idr_remove(&root->ino_idr, (u32)kernfs_ino(kn)); spin_unlock(&kernfs_idr_lock); kmem_cache_free(kernfs_node_cache, kn); @@ -617,7 +617,7 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, unsigned flags) { struct kernfs_node *kn; - u32 gen; + u32 id_highbits; int ret; name = kstrdup_const(name, GFP_KERNEL); @@ -631,16 +631,16 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, idr_preload(GFP_KERNEL); spin_lock(&kernfs_idr_lock); ret = idr_alloc_cyclic(&root->ino_idr, kn, 1, 0, GFP_ATOMIC); - if (ret >= 0 && ret < root->last_ino) - root->next_generation++; - gen = root->next_generation; - root->last_ino = ret; + if (ret >= 0 && ret < root->last_id_lowbits) + root->id_highbits++; + id_highbits = root->id_highbits; + root->last_id_lowbits = ret; spin_unlock(&kernfs_idr_lock); idr_preload_end(); if (ret < 0) goto err_out2; - kn->id = (u64)gen << 32 | ret; + kn->id = (u64)id_highbits << 32 | ret; atomic_set(&kn->count, 1); atomic_set(&kn->active, KN_DEACTIVATED_BIAS); @@ -671,7 +671,7 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, return kn; err_out3: - idr_remove(&root->ino_idr, kernfs_ino(kn)); + idr_remove(&root->ino_idr, (u32)kernfs_ino(kn)); err_out2: kmem_cache_free(kernfs_node_cache, kn); err_out1: @@ -715,13 +715,19 @@ struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root, spin_lock(&kernfs_idr_lock); - kn = idr_find(&root->ino_idr, ino); + kn = idr_find(&root->ino_idr, (u32)ino); if (!kn) goto err_unlock; - /* 0 matches all generations */ - if (unlikely(gen && kernfs_gen(kn) != gen)) - goto err_unlock; + if (sizeof(ino_t) >= sizeof(u64)) { + /* we looked up with the low 32bits, compare the whole */ + if (kernfs_ino(kn) != ino) + goto err_unlock; + } else { + /* 0 matches all generations */ + if (unlikely(gen && kernfs_gen(kn) != gen)) + goto err_unlock; + } /* * ACTIVATED is protected with kernfs_mutex but it was clear when @@ -949,7 +955,17 @@ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, idr_init(&root->ino_idr); INIT_LIST_HEAD(&root->supers); - root->next_generation = 1; + + /* + * On 64bit ino setups, id is ino. On 32bit, low 32bits are ino. + * High bits generation. The starting value for both ino and + * genenration is 1. Initialize upper 32bit allocation + * accordingly. + */ + if (sizeof(ino_t) >= sizeof(u64)) + root->id_highbits = 0; + else + root->id_highbits = 1; kn = __kernfs_new_node(root, NULL, "", S_IFDIR | S_IRUGO | S_IXUGO, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index 37a1e5df117a..4d31503abaee 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -87,9 +87,10 @@ static struct dentry *__kernfs_fh_to_dentry(struct super_block *sb, case FILEID_INO32_GEN: case FILEID_INO32_GEN_PARENT: /* - * blk_log_action() exposes (ino,gen) pair without type and - * userland can call us with generic fid constructed from - * them. Combine it back to ID. See blk_log_action(). + * blk_log_action() exposes "LOW32,HIGH32" pair without + * type and userland can call us with generic fid + * constructed from them. Combine it back to ID. See + * blk_log_action(). */ id = ((u64)fid->i32.gen << 32) | fid->i32.ino; break; diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 38267cc9420c..dded2e5a9f42 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -141,8 +141,8 @@ struct kernfs_node { void *priv; /* - * 64bit unique ID. Lower 32bits carry the inode number and lower - * generation. + * 64bit unique ID. On 64bit ino setups, id is the ino. On 32bit, + * the low 32bits are ino and upper generation. */ u64 id; @@ -177,8 +177,8 @@ struct kernfs_root { /* private fields, do not use outside kernfs proper */ struct idr ino_idr; - u32 last_ino; - u32 next_generation; + u32 last_id_lowbits; + u32 id_highbits; struct kernfs_syscall_ops *syscall_ops; /* list of kernfs_super_info of this root, protected by kernfs_mutex */ @@ -284,12 +284,20 @@ static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn) static inline ino_t kernfs_id_ino(u64 id) { - return (u32)id; + /* id is ino if ino_t is 64bit; otherwise, low 32bits */ + if (sizeof(ino_t) >= sizeof(u64)) + return id; + else + return (u32)id; } static inline u32 kernfs_id_gen(u64 id) { - return id >> 32; + /* gen is fixed at 1 if ino_t is 64bit; otherwise, high 32bits */ + if (sizeof(ino_t) >= sizeof(u64)) + return 1; + else + return id >> 32; } static inline ino_t kernfs_ino(struct kernfs_node *kn) diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index a986d2e74ca2..a7dac5b63f3f 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -1261,12 +1261,25 @@ static void blk_log_action(struct trace_iterator *iter, const char *act, trace_seq_printf(&iter->seq, "%3d,%-3d %s %2s %3s ", MAJOR(t->device), MINOR(t->device), blkcg_name_buf, act, rwbs); - } else + } else { + /* + * The cgid portion used to be "INO,GEN". Userland + * builds a FILEID_INO32_GEN fid out of them and + * opens the cgroup using open_by_handle_at(2). + * While 32bit ino setups are still the same, 64bit + * ones now use the 64bit ino as the whole ID and + * no longer use generation. + * + * Regarldess of the content, always output + * "LOW32,HIGH32" so that FILEID_INO32_GEN fid can + * be mapped back to @id on both 64 and 32bit ino + * setups. See __kernfs_fh_to_dentry(). + */ trace_seq_printf(&iter->seq, - "%3d,%-3d %lx,%-x %2s %3s ", + "%3d,%-3d %llx,%-llx %2s %3s ", MAJOR(t->device), MINOR(t->device), - kernfs_id_ino(id), kernfs_id_gen(id), - act, rwbs); + id & U32_MAX, id >> 32, act, rwbs); + } } else trace_seq_printf(&iter->seq, "%3d,%-3d %2s %3s ", MAJOR(t->device), MINOR(t->device), act, rwbs); -- cgit v1.2.3-71-gd317 From 743210386c0354a2f8ef3d697353c7d8477fa81d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 4 Nov 2019 15:54:30 -0800 Subject: cgroup: use cgrp->kn->id as the cgroup ID cgroup ID is currently allocated using a dedicated per-hierarchy idr and used internally and exposed through tracepoints and bpf. This is confusing because there are tracepoints and other interfaces which use the cgroupfs ino as IDs. The preceding changes made kn->id exposed as ino as 64bit ino on supported archs or ino+gen (low 32bits as ino, high gen). There's no reason for cgroup to use different IDs. The kernfs IDs are unique and userland can easily discover them and map them back to paths using standard file operations. This patch replaces cgroup IDs with kernfs IDs. * cgroup_id() is added and all cgroup ID users are converted to use it. * kernfs_node creation is moved to earlier during cgroup init so that cgroup_id() is available during init. * While at it, s/cgroup/cgrp/ in psi helpers for consistency. * Fallback ID value is changed to 1 to be consistent with root cgroup ID. Signed-off-by: Tejun Heo Reviewed-by: Greg Kroah-Hartman Cc: Namhyung Kim --- include/linux/cgroup-defs.h | 17 ++-------- include/linux/cgroup.h | 17 ++++------ include/trace/events/cgroup.h | 6 ++-- kernel/bpf/helpers.c | 2 +- kernel/bpf/local_storage.c | 2 +- kernel/cgroup/cgroup.c | 76 ++++++++++++++----------------------------- kernel/trace/blktrace.c | 4 +-- net/core/filter.c | 4 +-- 8 files changed, 43 insertions(+), 85 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 4904b1ebd1ff..63097cb243cb 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -354,16 +354,6 @@ struct cgroup { unsigned long flags; /* "unsigned long" so bitops work */ - /* - * idr allocated in-hierarchy ID. - * - * ID 0 is not used, the ID of the root cgroup is always 1, and a - * new cgroup will be assigned with a smallest available ID. - * - * Allocating/Removing ID must be protected by cgroup_mutex. - */ - int id; - /* * The depth this cgroup is at. The root is at depth zero and each * step down the hierarchy increments the level. This along with @@ -488,7 +478,7 @@ struct cgroup { struct cgroup_freezer_state freezer; /* ids of the ancestors at each level including self */ - int ancestor_ids[]; + u64 ancestor_ids[]; }; /* @@ -509,7 +499,7 @@ struct cgroup_root { struct cgroup cgrp; /* for cgrp->ancestor_ids[0] */ - int cgrp_ancestor_id_storage; + u64 cgrp_ancestor_id_storage; /* Number of cgroups in the hierarchy, used only for /proc/cgroups */ atomic_t nr_cgrps; @@ -520,9 +510,6 @@ struct cgroup_root { /* Hierarchy-specific flags */ unsigned int flags; - /* IDs for cgroups in this hierarchy */ - struct idr cgroup_idr; - /* The path to use for release notifications. */ char release_agent_path[PATH_MAX]; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 815fff49d555..d7ddebd0cdec 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -304,6 +304,11 @@ void css_task_iter_end(struct css_task_iter *it); * Inline functions. */ +static inline u64 cgroup_id(struct cgroup *cgrp) +{ + return cgrp->kn->id; +} + /** * css_get - obtain a reference on the specified css * @css: target css @@ -565,7 +570,7 @@ static inline bool cgroup_is_descendant(struct cgroup *cgrp, { if (cgrp->root != ancestor->root || cgrp->level < ancestor->level) return false; - return cgrp->ancestor_ids[ancestor->level] == ancestor->id; + return cgrp->ancestor_ids[ancestor->level] == cgroup_id(ancestor); } /** @@ -687,17 +692,13 @@ static inline void cgroup_kthread_ready(void) current->no_cgroup_migration = 0; } -static inline u64 cgroup_get_kernfs_id(struct cgroup *cgrp) -{ - return cgrp->kn->id; -} - void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen); #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; struct cgroup; +static inline u64 cgroup_id(struct cgroup *cgrp) { return 1; } static inline void css_get(struct cgroup_subsys_state *css) {} static inline void css_put(struct cgroup_subsys_state *css) {} static inline int cgroup_attach_task_all(struct task_struct *from, @@ -717,10 +718,6 @@ static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } static inline void cgroup_init_kthreadd(void) {} static inline void cgroup_kthread_ready(void) {} -static inline union u64 cgroup_get_kernfs_id(struct cgroup *cgrp) -{ - return 0; -} static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) { diff --git a/include/trace/events/cgroup.h b/include/trace/events/cgroup.h index a566cc521476..7f42a3de59e6 100644 --- a/include/trace/events/cgroup.h +++ b/include/trace/events/cgroup.h @@ -66,7 +66,7 @@ DECLARE_EVENT_CLASS(cgroup, TP_fast_assign( __entry->root = cgrp->root->hierarchy_id; - __entry->id = cgrp->id; + __entry->id = cgroup_id(cgrp); __entry->level = cgrp->level; __assign_str(path, path); ), @@ -135,7 +135,7 @@ DECLARE_EVENT_CLASS(cgroup_migrate, TP_fast_assign( __entry->dst_root = dst_cgrp->root->hierarchy_id; - __entry->dst_id = dst_cgrp->id; + __entry->dst_id = cgroup_id(dst_cgrp); __entry->dst_level = dst_cgrp->level; __assign_str(dst_path, path); __entry->pid = task->pid; @@ -179,7 +179,7 @@ DECLARE_EVENT_CLASS(cgroup_event, TP_fast_assign( __entry->root = cgrp->root->hierarchy_id; - __entry->id = cgrp->id; + __entry->id = cgroup_id(cgrp); __entry->level = cgrp->level; __assign_str(path, path); __entry->val = val; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 912e761cd17a..cada974c9f4e 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -317,7 +317,7 @@ BPF_CALL_0(bpf_get_current_cgroup_id) { struct cgroup *cgrp = task_dfl_cgroup(current); - return cgrp->kn->id; + return cgroup_id(cgrp); } const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 5d867f6d7204..2ba750725cb2 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -569,7 +569,7 @@ void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, return; storage->key.attach_type = type; - storage->key.cgroup_inode_id = cgroup->kn->id; + storage->key.cgroup_inode_id = cgroup_id(cgroup); map = storage->map; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index b5dcbee5aa6c..c12dcf7dc432 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1308,10 +1308,7 @@ static void cgroup_exit_root_id(struct cgroup_root *root) void cgroup_free_root(struct cgroup_root *root) { - if (root) { - idr_destroy(&root->cgroup_idr); - kfree(root); - } + kfree(root); } static void cgroup_destroy_root(struct cgroup_root *root) @@ -1917,7 +1914,6 @@ void init_cgroup_root(struct cgroup_fs_context *ctx) atomic_set(&root->nr_cgrps, 1); cgrp->root = root; init_cgroup_housekeeping(cgrp); - idr_init(&root->cgroup_idr); root->flags = ctx->flags; if (ctx->release_agent) @@ -1938,12 +1934,6 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) lockdep_assert_held(&cgroup_mutex); - ret = cgroup_idr_alloc(&root->cgroup_idr, root_cgrp, 1, 2, GFP_KERNEL); - if (ret < 0) - goto out; - root_cgrp->id = ret; - root_cgrp->ancestor_ids[0] = ret; - ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release, 0, GFP_KERNEL); if (ret) @@ -1976,6 +1966,8 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) goto exit_root_id; } root_cgrp->kn = root->kf_root->kn; + WARN_ON_ONCE(cgroup_id(root_cgrp) != 1); + root_cgrp->ancestor_ids[0] = cgroup_id(root_cgrp); ret = css_populate_dir(&root_cgrp->self); if (ret) @@ -3552,22 +3544,22 @@ static int cpu_stat_show(struct seq_file *seq, void *v) #ifdef CONFIG_PSI static int cgroup_io_pressure_show(struct seq_file *seq, void *v) { - struct cgroup *cgroup = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup->id == 1 ? &psi_system : &cgroup->psi; + struct cgroup *cgrp = seq_css(seq)->cgroup; + struct psi_group *psi = cgroup_id(cgrp) == 1 ? &psi_system : &cgrp->psi; return psi_show(seq, psi, PSI_IO); } static int cgroup_memory_pressure_show(struct seq_file *seq, void *v) { - struct cgroup *cgroup = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup->id == 1 ? &psi_system : &cgroup->psi; + struct cgroup *cgrp = seq_css(seq)->cgroup; + struct psi_group *psi = cgroup_id(cgrp) == 1 ? &psi_system : &cgrp->psi; return psi_show(seq, psi, PSI_MEM); } static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) { - struct cgroup *cgroup = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup->id == 1 ? &psi_system : &cgroup->psi; + struct cgroup *cgrp = seq_css(seq)->cgroup; + struct psi_group *psi = cgroup_id(cgrp) == 1 ? &psi_system : &cgrp->psi; return psi_show(seq, psi, PSI_CPU); } @@ -4987,9 +4979,6 @@ static void css_release_work_fn(struct work_struct *work) tcgrp->nr_dying_descendants--; spin_unlock_irq(&css_set_lock); - cgroup_idr_remove(&cgrp->root->cgroup_idr, cgrp->id); - cgrp->id = -1; - /* * There are two control paths which try to determine * cgroup from dentry without going through kernfs - @@ -5154,10 +5143,12 @@ err_free_css: * it isn't associated with its kernfs_node and doesn't have the control * mask applied. */ -static struct cgroup *cgroup_create(struct cgroup *parent) +static struct cgroup *cgroup_create(struct cgroup *parent, const char *name, + umode_t mode) { struct cgroup_root *root = parent->root; struct cgroup *cgrp, *tcgrp; + struct kernfs_node *kn; int level = parent->level + 1; int ret; @@ -5177,15 +5168,13 @@ static struct cgroup *cgroup_create(struct cgroup *parent) goto out_cancel_ref; } - /* - * Temporarily set the pointer to NULL, so idr_find() won't return - * a half-baked cgroup. - */ - cgrp->id = cgroup_idr_alloc(&root->cgroup_idr, NULL, 2, 0, GFP_KERNEL); - if (cgrp->id < 0) { - ret = -ENOMEM; + /* create the directory */ + kn = kernfs_create_dir(parent->kn, name, mode, cgrp); + if (IS_ERR(kn)) { + ret = PTR_ERR(kn); goto out_stat_exit; } + cgrp->kn = kn; init_cgroup_housekeeping(cgrp); @@ -5195,7 +5184,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent) ret = psi_cgroup_alloc(cgrp); if (ret) - goto out_idr_free; + goto out_kernfs_remove; ret = cgroup_bpf_inherit(cgrp); if (ret) @@ -5219,7 +5208,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent) spin_lock_irq(&css_set_lock); for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) { - cgrp->ancestor_ids[tcgrp->level] = tcgrp->id; + cgrp->ancestor_ids[tcgrp->level] = cgroup_id(tcgrp); if (tcgrp != cgrp) { tcgrp->nr_descendants++; @@ -5248,12 +5237,6 @@ static struct cgroup *cgroup_create(struct cgroup *parent) atomic_inc(&root->nr_cgrps); cgroup_get_live(parent); - /* - * @cgrp is now fully operational. If something fails after this - * point, it'll be released via the normal destruction path. - */ - cgroup_idr_replace(&root->cgroup_idr, cgrp, cgrp->id); - /* * On the default hierarchy, a child doesn't automatically inherit * subtree_control from the parent. Each is configured manually. @@ -5267,8 +5250,8 @@ static struct cgroup *cgroup_create(struct cgroup *parent) out_psi_free: psi_cgroup_free(cgrp); -out_idr_free: - cgroup_idr_remove(&root->cgroup_idr, cgrp->id); +out_kernfs_remove: + kernfs_remove(cgrp->kn); out_stat_exit: if (cgroup_on_dfl(parent)) cgroup_rstat_exit(cgrp); @@ -5305,7 +5288,6 @@ fail: int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode) { struct cgroup *parent, *cgrp; - struct kernfs_node *kn; int ret; /* do not accept '\n' to prevent making /proc//cgroup unparsable */ @@ -5321,27 +5303,19 @@ int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode) goto out_unlock; } - cgrp = cgroup_create(parent); + cgrp = cgroup_create(parent, name, mode); if (IS_ERR(cgrp)) { ret = PTR_ERR(cgrp); goto out_unlock; } - /* create the directory */ - kn = kernfs_create_dir(parent->kn, name, mode, cgrp); - if (IS_ERR(kn)) { - ret = PTR_ERR(kn); - goto out_destroy; - } - cgrp->kn = kn; - /* * This extra ref will be put in cgroup_free_fn() and guarantees * that @cgrp->kn is always accessible. */ - kernfs_get(kn); + kernfs_get(cgrp->kn); - ret = cgroup_kn_set_ugid(kn); + ret = cgroup_kn_set_ugid(cgrp->kn); if (ret) goto out_destroy; @@ -5356,7 +5330,7 @@ int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode) TRACE_CGROUP_PATH(mkdir, cgrp); /* let's create and online css's */ - kernfs_activate(kn); + kernfs_activate(cgrp->kn); ret = 0; goto out_unlock; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index a7dac5b63f3f..475e29498bca 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -171,7 +171,7 @@ void __trace_note_message(struct blk_trace *bt, struct blkcg *blkcg, blkcg = NULL; #ifdef CONFIG_BLK_CGROUP trace_note(bt, 0, BLK_TN_MESSAGE, buf, n, - blkcg ? cgroup_get_kernfs_id(blkcg->css.cgroup) : 0); + blkcg ? cgroup_id(blkcg->css.cgroup) : 1); #else trace_note(bt, 0, BLK_TN_MESSAGE, buf, n, 0); #endif @@ -759,7 +759,7 @@ static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) if (!bio->bi_blkg) return 0; - return cgroup_get_kernfs_id(bio_blkcg(bio)->css.cgroup); + return cgroup_id(bio_blkcg(bio)->css.cgroup); } #else u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) diff --git a/net/core/filter.c b/net/core/filter.c index b360a7beb6fc..caef7c74cad5 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4089,7 +4089,7 @@ BPF_CALL_1(bpf_skb_cgroup_id, const struct sk_buff *, skb) return 0; cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - return cgrp->kn->id; + return cgroup_id(cgrp); } static const struct bpf_func_proto bpf_skb_cgroup_id_proto = { @@ -4114,7 +4114,7 @@ BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int, if (!ancestor) return 0; - return ancestor->kn->id; + return cgroup_id(ancestor); } static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = { -- cgit v1.2.3-71-gd317 From d05a0201969045f4c488f7cf1d024089949a68b6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Nov 2019 16:34:22 +0100 Subject: sunrpc: remove __KERNEL__ ifdefs Remove the __KERNEL__ ifdefs from the non-UAPI sunrpc headers, as those can't be included from user space programs. Signed-off-by: Christoph Hellwig Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/auth.h | 3 --- include/linux/sunrpc/auth_gss.h | 2 -- include/linux/sunrpc/clnt.h | 3 --- include/linux/sunrpc/gss_api.h | 2 -- include/linux/sunrpc/gss_err.h | 3 --- include/linux/sunrpc/msg_prot.h | 3 --- include/linux/sunrpc/rpc_pipe_fs.h | 3 --- include/linux/sunrpc/svcauth.h | 4 ---- include/linux/sunrpc/svcauth_gss.h | 2 -- include/linux/sunrpc/xdr.h | 3 --- include/linux/sunrpc/xprt.h | 4 ---- include/linux/sunrpc/xprtsock.h | 4 ---- 12 files changed, 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 5f9076fdb090..e9ec742796e7 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -10,8 +10,6 @@ #ifndef _LINUX_SUNRPC_AUTH_H #define _LINUX_SUNRPC_AUTH_H -#ifdef __KERNEL__ - #include #include #include @@ -194,5 +192,4 @@ struct rpc_cred *get_rpccred(struct rpc_cred *cred) return NULL; } -#endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_AUTH_H */ diff --git a/include/linux/sunrpc/auth_gss.h b/include/linux/sunrpc/auth_gss.h index 30427b729070..43e481aa347a 100644 --- a/include/linux/sunrpc/auth_gss.h +++ b/include/linux/sunrpc/auth_gss.h @@ -13,7 +13,6 @@ #ifndef _LINUX_SUNRPC_AUTH_GSS_H #define _LINUX_SUNRPC_AUTH_GSS_H -#ifdef __KERNEL__ #include #include #include @@ -90,6 +89,5 @@ struct gss_cred { unsigned long gc_upcall_timestamp; }; -#endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_AUTH_GSS_H */ diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index abc63bd1be2b..64bffcb7142b 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -109,8 +109,6 @@ struct rpc_procinfo { const char * p_name; /* name of procedure */ }; -#ifdef __KERNEL__ - struct rpc_create_args { struct net *net; int protocol; @@ -237,5 +235,4 @@ static inline int rpc_reply_expected(struct rpc_task *task) (task->tk_msg.rpc_proc->p_decode != NULL); } -#endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_CLNT_H */ diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h index 5ac5db4d295f..bd691e08be3b 100644 --- a/include/linux/sunrpc/gss_api.h +++ b/include/linux/sunrpc/gss_api.h @@ -13,7 +13,6 @@ #ifndef _LINUX_SUNRPC_GSS_API_H #define _LINUX_SUNRPC_GSS_API_H -#ifdef __KERNEL__ #include #include #include @@ -160,6 +159,5 @@ struct gss_api_mech * gss_mech_get(struct gss_api_mech *); * corresponding call to gss_mech_put. */ void gss_mech_put(struct gss_api_mech *); -#endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_GSS_API_H */ diff --git a/include/linux/sunrpc/gss_err.h b/include/linux/sunrpc/gss_err.h index a6807867bd21..b73c329c83f2 100644 --- a/include/linux/sunrpc/gss_err.h +++ b/include/linux/sunrpc/gss_err.h @@ -34,8 +34,6 @@ #ifndef _LINUX_SUNRPC_GSS_ERR_H #define _LINUX_SUNRPC_GSS_ERR_H -#ifdef __KERNEL__ - typedef unsigned int OM_uint32; /* @@ -163,5 +161,4 @@ typedef unsigned int OM_uint32; /* XXXX This is a necessary evil until the spec is fixed */ #define GSS_S_CRED_UNAVAIL GSS_S_FAILURE -#endif /* __KERNEL__ */ #endif /* __LINUX_SUNRPC_GSS_ERR_H */ diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h index 4722b28ec36a..bea40d9f03a1 100644 --- a/include/linux/sunrpc/msg_prot.h +++ b/include/linux/sunrpc/msg_prot.h @@ -8,8 +8,6 @@ #ifndef _LINUX_SUNRPC_MSGPROT_H_ #define _LINUX_SUNRPC_MSGPROT_H_ -#ifdef __KERNEL__ /* user programs should get these from the rpc header files */ - #define RPC_VERSION 2 /* size of an XDR encoding unit in bytes, i.e. 32bit */ @@ -217,5 +215,4 @@ typedef __be32 rpc_fraghdr; /* Assume INET6_ADDRSTRLEN will always be larger than INET_ADDRSTRLEN... */ #define RPCBIND_MAXUADDRLEN RPCBIND_MAXUADDR6LEN -#endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_MSGPROT_H_ */ diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h index e90b9bd99ded..cd188a527d16 100644 --- a/include/linux/sunrpc/rpc_pipe_fs.h +++ b/include/linux/sunrpc/rpc_pipe_fs.h @@ -2,8 +2,6 @@ #ifndef _LINUX_SUNRPC_RPC_PIPE_FS_H #define _LINUX_SUNRPC_RPC_PIPE_FS_H -#ifdef __KERNEL__ - #include struct rpc_pipe_dir_head { @@ -133,4 +131,3 @@ extern void unregister_rpc_pipefs(void); extern bool gssd_running(struct net *net); #endif -#endif diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h index 3e53a6e2ada7..b0003866a249 100644 --- a/include/linux/sunrpc/svcauth.h +++ b/include/linux/sunrpc/svcauth.h @@ -10,8 +10,6 @@ #ifndef _LINUX_SUNRPC_SVCAUTH_H_ #define _LINUX_SUNRPC_SVCAUTH_H_ -#ifdef __KERNEL__ - #include #include #include @@ -185,6 +183,4 @@ static inline unsigned long hash_mem(char const *buf, int length, int bits) return full_name_hash(NULL, buf, length) >> (32 - bits); } -#endif /* __KERNEL__ */ - #endif /* _LINUX_SUNRPC_SVCAUTH_H_ */ diff --git a/include/linux/sunrpc/svcauth_gss.h b/include/linux/sunrpc/svcauth_gss.h index a4528b26c8aa..ca39a388dc22 100644 --- a/include/linux/sunrpc/svcauth_gss.h +++ b/include/linux/sunrpc/svcauth_gss.h @@ -9,7 +9,6 @@ #ifndef _LINUX_SUNRPC_SVCAUTH_GSS_H #define _LINUX_SUNRPC_SVCAUTH_GSS_H -#ifdef __KERNEL__ #include #include #include @@ -24,5 +23,4 @@ void gss_svc_shutdown_net(struct net *net); int svcauth_gss_register_pseudoflavor(u32 pseudoflavor, char * name); u32 svcauth_gss_flavor(struct auth_domain *dom); -#endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_SVCAUTH_GSS_H */ diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index f33e5013bdfb..b41f34977995 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -11,8 +11,6 @@ #ifndef _SUNRPC_XDR_H_ #define _SUNRPC_XDR_H_ -#ifdef __KERNEL__ - #include #include #include @@ -552,6 +550,5 @@ xdr_stream_decode_uint32_array(struct xdr_stream *xdr, *array = be32_to_cpup(p); return retval; } -#endif /* __KERNEL__ */ #endif /* _SUNRPC_XDR_H_ */ diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index d783e15ba898..874205227778 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -19,8 +19,6 @@ #include #include -#ifdef __KERNEL__ - #define RPC_MIN_SLOT_TABLE (2U) #define RPC_DEF_SLOT_TABLE (16U) #define RPC_MAX_SLOT_TABLE_LIMIT (65536U) @@ -505,6 +503,4 @@ static inline void xprt_inject_disconnect(struct rpc_xprt *xprt) } #endif -#endif /* __KERNEL__*/ - #endif /* _LINUX_SUNRPC_XPRT_H */ diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 7638dbe7bc50..30acd67d1627 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -8,8 +8,6 @@ #ifndef _LINUX_SUNRPC_XPRTSOCK_H #define _LINUX_SUNRPC_XPRTSOCK_H -#ifdef __KERNEL__ - int init_socket_xprt(void); void cleanup_socket_xprt(void); @@ -90,6 +88,4 @@ struct sock_xprt { #define XPRT_SOCK_WAKE_PENDING (6) #define XPRT_SOCK_WAKE_DISCONNECT (7) -#endif /* __KERNEL__ */ - #endif /* _LINUX_SUNRPC_XPRTSOCK_H */ -- cgit v1.2.3-71-gd317 From fb7dd0a1ba8690527c2394c6c55f909aa87d8f44 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Nov 2019 16:34:23 +0100 Subject: lockd: remove __KERNEL__ ifdefs Remove the __KERNEL__ ifdefs from the non-UAPI sunrpc headers, as those can't be included from user space programs. Signed-off-by: Christoph Hellwig Signed-off-by: J. Bruce Fields --- include/linux/lockd/debug.h | 4 ---- include/linux/lockd/lockd.h | 4 ---- 2 files changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockd/debug.h b/include/linux/lockd/debug.h index e536c579827f..eede2ab5246f 100644 --- a/include/linux/lockd/debug.h +++ b/include/linux/lockd/debug.h @@ -10,8 +10,6 @@ #ifndef LINUX_LOCKD_DEBUG_H #define LINUX_LOCKD_DEBUG_H -#ifdef __KERNEL__ - #include /* @@ -25,8 +23,6 @@ # define ifdebug(flag) if (0) #endif -#endif /* __KERNEL__ */ - /* * Debug flags */ diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index d294dde9e546..666f5f310a04 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -10,8 +10,6 @@ #ifndef LINUX_LOCKD_LOCKD_H #define LINUX_LOCKD_LOCKD_H -#ifdef __KERNEL__ - #include #include #include @@ -373,6 +371,4 @@ static inline int nlm_compare_locks(const struct file_lock *fl1, extern const struct lock_manager_operations nlmsvc_lock_operations; -#endif /* __KERNEL__ */ - #endif /* LINUX_LOCKD_LOCKD_H */ -- cgit v1.2.3-71-gd317 From 6c0867022352027409f5a9fee1d3c6923f9e083e Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 12 Nov 2019 11:35:00 +0000 Subject: net: sfp: fix sfp_bus_add_upstream() warning When building with SFP disabled, the stub for sfp_bus_add_upstream() missed "inline". Add it. Fixes: 727b3668b730 ("net: sfp: rework upstream interface") Signed-off-by: Russell King Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/sfp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sfp.h b/include/linux/sfp.h index c8464de7cff5..3b35efd85bb1 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -563,8 +563,8 @@ static inline struct sfp_bus *sfp_bus_find_fwnode(struct fwnode_handle *fwnode) return NULL; } -static int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, - const struct sfp_upstream_ops *ops) +static inline int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, + const struct sfp_upstream_ops *ops) { return 0; } -- cgit v1.2.3-71-gd317 From 15d0b22c01e6320241fe4d570e02de2935b842bf Mon Sep 17 00:00:00 2001 From: Jerry Snitselaar Date: Mon, 2 Sep 2019 07:27:34 -0700 Subject: tpm: provide a way to override the chip returned durations Patch adds method ->update_durations to override returned durations in case TPM chip misbehaves for TPM 1.2 drivers. Cc: Peter Huewe Cc: Jason Gunthorpe Signed-off-by: Alexey Klimov Signed-off-by: Jerry Snitselaar Reviewed-by: Jarkko Sakkinen Tested-by: Jarkko Sakkinen (!update_durations path) Signed-off-by: Jarkko Sakkinen --- drivers/char/tpm/tpm1-cmd.c | 15 +++++++++++++++ include/linux/tpm.h | 2 ++ 2 files changed, 17 insertions(+) (limited to 'include/linux') diff --git a/drivers/char/tpm/tpm1-cmd.c b/drivers/char/tpm/tpm1-cmd.c index 149e953ca369..ca7158fa6e6c 100644 --- a/drivers/char/tpm/tpm1-cmd.c +++ b/drivers/char/tpm/tpm1-cmd.c @@ -343,6 +343,7 @@ int tpm1_get_timeouts(struct tpm_chip *chip) { cap_t cap; unsigned long timeout_old[4], timeout_chip[4], timeout_eff[4]; + unsigned long durations[3]; ssize_t rc; rc = tpm1_getcap(chip, TPM_CAP_PROP_TIS_TIMEOUT, &cap, NULL, @@ -427,6 +428,20 @@ int tpm1_get_timeouts(struct tpm_chip *chip) usecs_to_jiffies(be32_to_cpu(cap.duration.tpm_long)); chip->duration[TPM_LONG_LONG] = 0; /* not used under 1.2 */ + /* + * Provide the ability for vendor overrides of duration values in case + * of misreporting. + */ + if (chip->ops->update_durations) + chip->ops->update_durations(chip, durations); + + if (chip->duration_adjusted) { + dev_info(&chip->dev, HW_ERR "Adjusting reported durations."); + chip->duration[TPM_SHORT] = durations[0]; + chip->duration[TPM_MEDIUM] = durations[1]; + chip->duration[TPM_LONG] = durations[2]; + } + /* The Broadcom BCM0102 chipset in a Dell Latitude D820 gets the above * value wrong and apparently reports msecs rather than usecs. So we * fix up the resulting too-small TPM_SHORT value to make things work. diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 53c0ea9ec9df..bb1d1ac7081d 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -67,6 +67,8 @@ struct tpm_class_ops { u8 (*status) (struct tpm_chip *chip); void (*update_timeouts)(struct tpm_chip *chip, unsigned long *timeout_cap); + void (*update_durations)(struct tpm_chip *chip, + unsigned long *duration_cap); int (*go_idle)(struct tpm_chip *chip); int (*cmd_ready)(struct tpm_chip *chip); int (*request_locality)(struct tpm_chip *chip, int loc); -- cgit v1.2.3-71-gd317 From 74edff2d74c64ca5977a57efb5c238c8f5318ba9 Mon Sep 17 00:00:00 2001 From: Sumit Garg Date: Wed, 16 Oct 2019 10:44:52 +0530 Subject: tpm: Move tpm_buf code to include/linux/ Move tpm_buf code to common include/linux/tpm.h header so that it can be reused via other subsystems like trusted keys etc. Also rename trusted keys and asymmetric keys usage of TPM 1.x buffer implementation to tpm1_buf to avoid any compilation errors. Suggested-by: Jarkko Sakkinen Signed-off-by: Sumit Garg Reviewed-by: Jerry Snitselaar Reviewed-by: Jarkko Sakkinen Tested-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- crypto/asymmetric_keys/asym_tpm.c | 12 +-- drivers/char/tpm/tpm.h | 212 -------------------------------------- include/keys/trusted.h | 12 +-- include/linux/tpm.h | 212 ++++++++++++++++++++++++++++++++++++++ security/keys/trusted.c | 12 +-- 5 files changed, 230 insertions(+), 230 deletions(-) (limited to 'include/linux') diff --git a/crypto/asymmetric_keys/asym_tpm.c b/crypto/asymmetric_keys/asym_tpm.c index 76d2ce3a1b5b..b88968dcee70 100644 --- a/crypto/asymmetric_keys/asym_tpm.c +++ b/crypto/asymmetric_keys/asym_tpm.c @@ -31,7 +31,7 @@ /* * Load a TPM key from the blob provided by userspace */ -static int tpm_loadkey2(struct tpm_buf *tb, +static int tpm_loadkey2(struct tpm1_buf *tb, uint32_t keyhandle, unsigned char *keyauth, const unsigned char *keyblob, int keybloblen, uint32_t *newhandle) @@ -99,7 +99,7 @@ static int tpm_loadkey2(struct tpm_buf *tb, /* * Execute the FlushSpecific TPM command */ -static int tpm_flushspecific(struct tpm_buf *tb, uint32_t handle) +static int tpm_flushspecific(struct tpm1_buf *tb, uint32_t handle) { INIT_BUF(tb); store16(tb, TPM_TAG_RQU_COMMAND); @@ -115,7 +115,7 @@ static int tpm_flushspecific(struct tpm_buf *tb, uint32_t handle) * Decrypt a blob provided by userspace using a specific key handle. * The handle is a well known handle or previously loaded by e.g. LoadKey2 */ -static int tpm_unbind(struct tpm_buf *tb, +static int tpm_unbind(struct tpm1_buf *tb, uint32_t keyhandle, unsigned char *keyauth, const unsigned char *blob, uint32_t bloblen, void *out, uint32_t outlen) @@ -201,7 +201,7 @@ static int tpm_unbind(struct tpm_buf *tb, * up to key_length_in_bytes - 11 and not be limited to size 20 like the * TPM_SS_RSASSAPKCS1v15_SHA1 signature scheme. */ -static int tpm_sign(struct tpm_buf *tb, +static int tpm_sign(struct tpm1_buf *tb, uint32_t keyhandle, unsigned char *keyauth, const unsigned char *blob, uint32_t bloblen, void *out, uint32_t outlen) @@ -519,7 +519,7 @@ static int tpm_key_decrypt(struct tpm_key *tk, struct kernel_pkey_params *params, const void *in, void *out) { - struct tpm_buf *tb; + struct tpm1_buf *tb; uint32_t keyhandle; uint8_t srkauth[SHA1_DIGEST_SIZE]; uint8_t keyauth[SHA1_DIGEST_SIZE]; @@ -643,7 +643,7 @@ static int tpm_key_sign(struct tpm_key *tk, struct kernel_pkey_params *params, const void *in, void *out) { - struct tpm_buf *tb; + struct tpm1_buf *tb; uint32_t keyhandle; uint8_t srkauth[SHA1_DIGEST_SIZE]; uint8_t keyauth[SHA1_DIGEST_SIZE]; diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h index 0d1fd37d6218..b174cf46410c 100644 --- a/drivers/char/tpm/tpm.h +++ b/drivers/char/tpm/tpm.h @@ -25,7 +25,6 @@ #include #include #include -#include #include #ifdef CONFIG_X86 @@ -58,124 +57,6 @@ enum tpm_addr { #define TPM_ERR_DISABLED 0x7 #define TPM_ERR_INVALID_POSTINIT 38 -#define TPM_HEADER_SIZE 10 - -enum tpm2_const { - TPM2_PLATFORM_PCR = 24, - TPM2_PCR_SELECT_MIN = ((TPM2_PLATFORM_PCR + 7) / 8), -}; - -enum tpm2_timeouts { - TPM2_TIMEOUT_A = 750, - TPM2_TIMEOUT_B = 2000, - TPM2_TIMEOUT_C = 200, - TPM2_TIMEOUT_D = 30, - TPM2_DURATION_SHORT = 20, - TPM2_DURATION_MEDIUM = 750, - TPM2_DURATION_LONG = 2000, - TPM2_DURATION_LONG_LONG = 300000, - TPM2_DURATION_DEFAULT = 120000, -}; - -enum tpm2_structures { - TPM2_ST_NO_SESSIONS = 0x8001, - TPM2_ST_SESSIONS = 0x8002, -}; - -/* Indicates from what layer of the software stack the error comes from */ -#define TSS2_RC_LAYER_SHIFT 16 -#define TSS2_RESMGR_TPM_RC_LAYER (11 << TSS2_RC_LAYER_SHIFT) - -enum tpm2_return_codes { - TPM2_RC_SUCCESS = 0x0000, - TPM2_RC_HASH = 0x0083, /* RC_FMT1 */ - TPM2_RC_HANDLE = 0x008B, - TPM2_RC_INITIALIZE = 0x0100, /* RC_VER1 */ - TPM2_RC_FAILURE = 0x0101, - TPM2_RC_DISABLED = 0x0120, - TPM2_RC_COMMAND_CODE = 0x0143, - TPM2_RC_TESTING = 0x090A, /* RC_WARN */ - TPM2_RC_REFERENCE_H0 = 0x0910, - TPM2_RC_RETRY = 0x0922, -}; - -enum tpm2_command_codes { - TPM2_CC_FIRST = 0x011F, - TPM2_CC_HIERARCHY_CONTROL = 0x0121, - TPM2_CC_HIERARCHY_CHANGE_AUTH = 0x0129, - TPM2_CC_CREATE_PRIMARY = 0x0131, - TPM2_CC_SEQUENCE_COMPLETE = 0x013E, - TPM2_CC_SELF_TEST = 0x0143, - TPM2_CC_STARTUP = 0x0144, - TPM2_CC_SHUTDOWN = 0x0145, - TPM2_CC_NV_READ = 0x014E, - TPM2_CC_CREATE = 0x0153, - TPM2_CC_LOAD = 0x0157, - TPM2_CC_SEQUENCE_UPDATE = 0x015C, - TPM2_CC_UNSEAL = 0x015E, - TPM2_CC_CONTEXT_LOAD = 0x0161, - TPM2_CC_CONTEXT_SAVE = 0x0162, - TPM2_CC_FLUSH_CONTEXT = 0x0165, - TPM2_CC_VERIFY_SIGNATURE = 0x0177, - TPM2_CC_GET_CAPABILITY = 0x017A, - TPM2_CC_GET_RANDOM = 0x017B, - TPM2_CC_PCR_READ = 0x017E, - TPM2_CC_PCR_EXTEND = 0x0182, - TPM2_CC_EVENT_SEQUENCE_COMPLETE = 0x0185, - TPM2_CC_HASH_SEQUENCE_START = 0x0186, - TPM2_CC_CREATE_LOADED = 0x0191, - TPM2_CC_LAST = 0x0193, /* Spec 1.36 */ -}; - -enum tpm2_permanent_handles { - TPM2_RS_PW = 0x40000009, -}; - -enum tpm2_capabilities { - TPM2_CAP_HANDLES = 1, - TPM2_CAP_COMMANDS = 2, - TPM2_CAP_PCRS = 5, - TPM2_CAP_TPM_PROPERTIES = 6, -}; - -enum tpm2_properties { - TPM_PT_TOTAL_COMMANDS = 0x0129, -}; - -enum tpm2_startup_types { - TPM2_SU_CLEAR = 0x0000, - TPM2_SU_STATE = 0x0001, -}; - -enum tpm2_cc_attrs { - TPM2_CC_ATTR_CHANDLES = 25, - TPM2_CC_ATTR_RHANDLE = 28, -}; - -#define TPM_VID_INTEL 0x8086 -#define TPM_VID_WINBOND 0x1050 -#define TPM_VID_STM 0x104A - -enum tpm_chip_flags { - TPM_CHIP_FLAG_TPM2 = BIT(1), - TPM_CHIP_FLAG_IRQ = BIT(2), - TPM_CHIP_FLAG_VIRTUAL = BIT(3), - TPM_CHIP_FLAG_HAVE_TIMEOUTS = BIT(4), - TPM_CHIP_FLAG_ALWAYS_POWERED = BIT(5), - TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED = BIT(6), -}; - -#define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) - -struct tpm_header { - __be16 tag; - __be32 length; - union { - __be32 ordinal; - __be32 return_code; - }; -} __packed; - #define TPM_TAG_RQU_COMMAND 193 struct stclear_flags_t { @@ -272,99 +153,6 @@ enum tpm_sub_capabilities { * compiler warnings about stack frame size. */ #define TPM_MAX_RNG_DATA 128 -/* A string buffer type for constructing TPM commands. This is based on the - * ideas of string buffer code in security/keys/trusted.h but is heap based - * in order to keep the stack usage minimal. - */ - -enum tpm_buf_flags { - TPM_BUF_OVERFLOW = BIT(0), -}; - -struct tpm_buf { - unsigned int flags; - u8 *data; -}; - -static inline void tpm_buf_reset(struct tpm_buf *buf, u16 tag, u32 ordinal) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - - head->tag = cpu_to_be16(tag); - head->length = cpu_to_be32(sizeof(*head)); - head->ordinal = cpu_to_be32(ordinal); -} - -static inline int tpm_buf_init(struct tpm_buf *buf, u16 tag, u32 ordinal) -{ - buf->data = (u8 *)__get_free_page(GFP_KERNEL); - if (!buf->data) - return -ENOMEM; - - buf->flags = 0; - tpm_buf_reset(buf, tag, ordinal); - return 0; -} - -static inline void tpm_buf_destroy(struct tpm_buf *buf) -{ - free_page((unsigned long)buf->data); -} - -static inline u32 tpm_buf_length(struct tpm_buf *buf) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - - return be32_to_cpu(head->length); -} - -static inline u16 tpm_buf_tag(struct tpm_buf *buf) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - - return be16_to_cpu(head->tag); -} - -static inline void tpm_buf_append(struct tpm_buf *buf, - const unsigned char *new_data, - unsigned int new_len) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - u32 len = tpm_buf_length(buf); - - /* Return silently if overflow has already happened. */ - if (buf->flags & TPM_BUF_OVERFLOW) - return; - - if ((len + new_len) > PAGE_SIZE) { - WARN(1, "tpm_buf: overflow\n"); - buf->flags |= TPM_BUF_OVERFLOW; - return; - } - - memcpy(&buf->data[len], new_data, new_len); - head->length = cpu_to_be32(len + new_len); -} - -static inline void tpm_buf_append_u8(struct tpm_buf *buf, const u8 value) -{ - tpm_buf_append(buf, &value, 1); -} - -static inline void tpm_buf_append_u16(struct tpm_buf *buf, const u16 value) -{ - __be16 value2 = cpu_to_be16(value); - - tpm_buf_append(buf, (u8 *) &value2, 2); -} - -static inline void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value) -{ - __be32 value2 = cpu_to_be32(value); - - tpm_buf_append(buf, (u8 *) &value2, 4); -} - extern struct class *tpm_class; extern struct class *tpmrm_class; extern dev_t tpm_devt; diff --git a/include/keys/trusted.h b/include/keys/trusted.h index 0071298b9b28..841ae111c976 100644 --- a/include/keys/trusted.h +++ b/include/keys/trusted.h @@ -17,7 +17,7 @@ #define LOAD32N(buffer, offset) (*(uint32_t *)&buffer[offset]) #define LOAD16(buffer, offset) (ntohs(*(uint16_t *)&buffer[offset])) -struct tpm_buf { +struct tpm1_buf { int len; unsigned char data[MAX_BUF_SIZE]; }; @@ -46,7 +46,7 @@ int TSS_checkhmac1(unsigned char *buffer, unsigned int keylen, ...); int trusted_tpm_send(unsigned char *cmd, size_t buflen); -int oiap(struct tpm_buf *tb, uint32_t *handle, unsigned char *nonce); +int oiap(struct tpm1_buf *tb, uint32_t *handle, unsigned char *nonce); #define TPM_DEBUG 0 @@ -110,24 +110,24 @@ static inline void dump_tpm_buf(unsigned char *buf) } #endif -static inline void store8(struct tpm_buf *buf, const unsigned char value) +static inline void store8(struct tpm1_buf *buf, const unsigned char value) { buf->data[buf->len++] = value; } -static inline void store16(struct tpm_buf *buf, const uint16_t value) +static inline void store16(struct tpm1_buf *buf, const uint16_t value) { *(uint16_t *) & buf->data[buf->len] = htons(value); buf->len += sizeof value; } -static inline void store32(struct tpm_buf *buf, const uint32_t value) +static inline void store32(struct tpm1_buf *buf, const uint32_t value) { *(uint32_t *) & buf->data[buf->len] = htonl(value); buf->len += sizeof value; } -static inline void storebytes(struct tpm_buf *buf, const unsigned char *in, +static inline void storebytes(struct tpm1_buf *buf, const unsigned char *in, const int len) { memcpy(buf->data + buf->len, in, len); diff --git a/include/linux/tpm.h b/include/linux/tpm.h index bb1d1ac7081d..c78119fcac7f 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -21,6 +21,7 @@ #include #include #include +#include #include #define TPM_DIGEST_SIZE 20 /* Max TPM v1.2 PCR size */ @@ -163,6 +164,217 @@ struct tpm_chip { int locality; }; +#define TPM_HEADER_SIZE 10 + +enum tpm2_const { + TPM2_PLATFORM_PCR = 24, + TPM2_PCR_SELECT_MIN = ((TPM2_PLATFORM_PCR + 7) / 8), +}; + +enum tpm2_timeouts { + TPM2_TIMEOUT_A = 750, + TPM2_TIMEOUT_B = 2000, + TPM2_TIMEOUT_C = 200, + TPM2_TIMEOUT_D = 30, + TPM2_DURATION_SHORT = 20, + TPM2_DURATION_MEDIUM = 750, + TPM2_DURATION_LONG = 2000, + TPM2_DURATION_LONG_LONG = 300000, + TPM2_DURATION_DEFAULT = 120000, +}; + +enum tpm2_structures { + TPM2_ST_NO_SESSIONS = 0x8001, + TPM2_ST_SESSIONS = 0x8002, +}; + +/* Indicates from what layer of the software stack the error comes from */ +#define TSS2_RC_LAYER_SHIFT 16 +#define TSS2_RESMGR_TPM_RC_LAYER (11 << TSS2_RC_LAYER_SHIFT) + +enum tpm2_return_codes { + TPM2_RC_SUCCESS = 0x0000, + TPM2_RC_HASH = 0x0083, /* RC_FMT1 */ + TPM2_RC_HANDLE = 0x008B, + TPM2_RC_INITIALIZE = 0x0100, /* RC_VER1 */ + TPM2_RC_FAILURE = 0x0101, + TPM2_RC_DISABLED = 0x0120, + TPM2_RC_COMMAND_CODE = 0x0143, + TPM2_RC_TESTING = 0x090A, /* RC_WARN */ + TPM2_RC_REFERENCE_H0 = 0x0910, + TPM2_RC_RETRY = 0x0922, +}; + +enum tpm2_command_codes { + TPM2_CC_FIRST = 0x011F, + TPM2_CC_HIERARCHY_CONTROL = 0x0121, + TPM2_CC_HIERARCHY_CHANGE_AUTH = 0x0129, + TPM2_CC_CREATE_PRIMARY = 0x0131, + TPM2_CC_SEQUENCE_COMPLETE = 0x013E, + TPM2_CC_SELF_TEST = 0x0143, + TPM2_CC_STARTUP = 0x0144, + TPM2_CC_SHUTDOWN = 0x0145, + TPM2_CC_NV_READ = 0x014E, + TPM2_CC_CREATE = 0x0153, + TPM2_CC_LOAD = 0x0157, + TPM2_CC_SEQUENCE_UPDATE = 0x015C, + TPM2_CC_UNSEAL = 0x015E, + TPM2_CC_CONTEXT_LOAD = 0x0161, + TPM2_CC_CONTEXT_SAVE = 0x0162, + TPM2_CC_FLUSH_CONTEXT = 0x0165, + TPM2_CC_VERIFY_SIGNATURE = 0x0177, + TPM2_CC_GET_CAPABILITY = 0x017A, + TPM2_CC_GET_RANDOM = 0x017B, + TPM2_CC_PCR_READ = 0x017E, + TPM2_CC_PCR_EXTEND = 0x0182, + TPM2_CC_EVENT_SEQUENCE_COMPLETE = 0x0185, + TPM2_CC_HASH_SEQUENCE_START = 0x0186, + TPM2_CC_CREATE_LOADED = 0x0191, + TPM2_CC_LAST = 0x0193, /* Spec 1.36 */ +}; + +enum tpm2_permanent_handles { + TPM2_RS_PW = 0x40000009, +}; + +enum tpm2_capabilities { + TPM2_CAP_HANDLES = 1, + TPM2_CAP_COMMANDS = 2, + TPM2_CAP_PCRS = 5, + TPM2_CAP_TPM_PROPERTIES = 6, +}; + +enum tpm2_properties { + TPM_PT_TOTAL_COMMANDS = 0x0129, +}; + +enum tpm2_startup_types { + TPM2_SU_CLEAR = 0x0000, + TPM2_SU_STATE = 0x0001, +}; + +enum tpm2_cc_attrs { + TPM2_CC_ATTR_CHANDLES = 25, + TPM2_CC_ATTR_RHANDLE = 28, +}; + +#define TPM_VID_INTEL 0x8086 +#define TPM_VID_WINBOND 0x1050 +#define TPM_VID_STM 0x104A + +enum tpm_chip_flags { + TPM_CHIP_FLAG_TPM2 = BIT(1), + TPM_CHIP_FLAG_IRQ = BIT(2), + TPM_CHIP_FLAG_VIRTUAL = BIT(3), + TPM_CHIP_FLAG_HAVE_TIMEOUTS = BIT(4), + TPM_CHIP_FLAG_ALWAYS_POWERED = BIT(5), + TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED = BIT(6), +}; + +#define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) + +struct tpm_header { + __be16 tag; + __be32 length; + union { + __be32 ordinal; + __be32 return_code; + }; +} __packed; + +/* A string buffer type for constructing TPM commands. This is based on the + * ideas of string buffer code in security/keys/trusted.h but is heap based + * in order to keep the stack usage minimal. + */ + +enum tpm_buf_flags { + TPM_BUF_OVERFLOW = BIT(0), +}; + +struct tpm_buf { + unsigned int flags; + u8 *data; +}; + +static inline void tpm_buf_reset(struct tpm_buf *buf, u16 tag, u32 ordinal) +{ + struct tpm_header *head = (struct tpm_header *)buf->data; + + head->tag = cpu_to_be16(tag); + head->length = cpu_to_be32(sizeof(*head)); + head->ordinal = cpu_to_be32(ordinal); +} + +static inline int tpm_buf_init(struct tpm_buf *buf, u16 tag, u32 ordinal) +{ + buf->data = (u8 *)__get_free_page(GFP_KERNEL); + if (!buf->data) + return -ENOMEM; + + buf->flags = 0; + tpm_buf_reset(buf, tag, ordinal); + return 0; +} + +static inline void tpm_buf_destroy(struct tpm_buf *buf) +{ + free_page((unsigned long)buf->data); +} + +static inline u32 tpm_buf_length(struct tpm_buf *buf) +{ + struct tpm_header *head = (struct tpm_header *)buf->data; + + return be32_to_cpu(head->length); +} + +static inline u16 tpm_buf_tag(struct tpm_buf *buf) +{ + struct tpm_header *head = (struct tpm_header *)buf->data; + + return be16_to_cpu(head->tag); +} + +static inline void tpm_buf_append(struct tpm_buf *buf, + const unsigned char *new_data, + unsigned int new_len) +{ + struct tpm_header *head = (struct tpm_header *)buf->data; + u32 len = tpm_buf_length(buf); + + /* Return silently if overflow has already happened. */ + if (buf->flags & TPM_BUF_OVERFLOW) + return; + + if ((len + new_len) > PAGE_SIZE) { + WARN(1, "tpm_buf: overflow\n"); + buf->flags |= TPM_BUF_OVERFLOW; + return; + } + + memcpy(&buf->data[len], new_data, new_len); + head->length = cpu_to_be32(len + new_len); +} + +static inline void tpm_buf_append_u8(struct tpm_buf *buf, const u8 value) +{ + tpm_buf_append(buf, &value, 1); +} + +static inline void tpm_buf_append_u16(struct tpm_buf *buf, const u16 value) +{ + __be16 value2 = cpu_to_be16(value); + + tpm_buf_append(buf, (u8 *) &value2, 2); +} + +static inline void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value) +{ + __be32 value2 = cpu_to_be32(value); + + tpm_buf_append(buf, (u8 *) &value2, 4); +} + #if defined(CONFIG_TCG_TPM) || defined(CONFIG_TCG_TPM_MODULE) extern int tpm_is_tpm2(struct tpm_chip *chip); diff --git a/security/keys/trusted.c b/security/keys/trusted.c index 1fbd77816610..4cfae208848e 100644 --- a/security/keys/trusted.c +++ b/security/keys/trusted.c @@ -395,7 +395,7 @@ static int pcrlock(const int pcrnum) /* * Create an object specific authorisation protocol (OSAP) session */ -static int osap(struct tpm_buf *tb, struct osapsess *s, +static int osap(struct tpm1_buf *tb, struct osapsess *s, const unsigned char *key, uint16_t type, uint32_t handle) { unsigned char enonce[TPM_NONCE_SIZE]; @@ -430,7 +430,7 @@ static int osap(struct tpm_buf *tb, struct osapsess *s, /* * Create an object independent authorisation protocol (oiap) session */ -int oiap(struct tpm_buf *tb, uint32_t *handle, unsigned char *nonce) +int oiap(struct tpm1_buf *tb, uint32_t *handle, unsigned char *nonce) { int ret; @@ -464,7 +464,7 @@ struct tpm_digests { * Have the TPM seal(encrypt) the trusted key, possibly based on * Platform Configuration Registers (PCRs). AUTH1 for sealing key. */ -static int tpm_seal(struct tpm_buf *tb, uint16_t keytype, +static int tpm_seal(struct tpm1_buf *tb, uint16_t keytype, uint32_t keyhandle, const unsigned char *keyauth, const unsigned char *data, uint32_t datalen, unsigned char *blob, uint32_t *bloblen, @@ -579,7 +579,7 @@ out: /* * use the AUTH2_COMMAND form of unseal, to authorize both key and blob */ -static int tpm_unseal(struct tpm_buf *tb, +static int tpm_unseal(struct tpm1_buf *tb, uint32_t keyhandle, const unsigned char *keyauth, const unsigned char *blob, int bloblen, const unsigned char *blobauth, @@ -670,7 +670,7 @@ static int tpm_unseal(struct tpm_buf *tb, static int key_seal(struct trusted_key_payload *p, struct trusted_key_options *o) { - struct tpm_buf *tb; + struct tpm1_buf *tb; int ret; tb = kzalloc(sizeof *tb, GFP_KERNEL); @@ -696,7 +696,7 @@ static int key_seal(struct trusted_key_payload *p, static int key_unseal(struct trusted_key_payload *p, struct trusted_key_options *o) { - struct tpm_buf *tb; + struct tpm1_buf *tb; int ret; tb = kzalloc(sizeof *tb, GFP_KERNEL); -- cgit v1.2.3-71-gd317 From 2e19e10131a08dc65079c755fb6e8af936bfedbd Mon Sep 17 00:00:00 2001 From: Sumit Garg Date: Wed, 16 Oct 2019 10:44:55 +0530 Subject: KEYS: trusted: Move TPM2 trusted keys code Move TPM2 trusted keys code to trusted keys subsystem. The reason being it's better to consolidate all the trusted keys code to a single location so that it can be maintained sanely. Also, utilize existing tpm_send() exported API which wraps the internal tpm_transmit_cmd() API. Suggested-by: Jarkko Sakkinen Signed-off-by: Sumit Garg Reviewed-by: Jarkko Sakkinen Tested-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- drivers/char/tpm/tpm-interface.c | 56 ------ drivers/char/tpm/tpm.h | 11 -- drivers/char/tpm/tpm2-cmd.c | 307 ----------------------------- include/keys/trusted_tpm.h | 7 + include/linux/tpm.h | 36 ++-- security/keys/trusted-keys/Makefile | 1 + security/keys/trusted-keys/trusted_tpm1.c | 4 +- security/keys/trusted-keys/trusted_tpm2.c | 314 ++++++++++++++++++++++++++++++ 8 files changed, 342 insertions(+), 394 deletions(-) create mode 100644 security/keys/trusted-keys/trusted_tpm2.c (limited to 'include/linux') diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index 7f105490604c..a438b1206fcb 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -459,62 +459,6 @@ int tpm_get_random(struct tpm_chip *chip, u8 *out, size_t max) } EXPORT_SYMBOL_GPL(tpm_get_random); -/** - * tpm_seal_trusted() - seal a trusted key payload - * @chip: a &struct tpm_chip instance, %NULL for the default chip - * @options: authentication values and other options - * @payload: the key data in clear and encrypted form - * - * Note: only TPM 2.0 chip are supported. TPM 1.x implementation is located in - * the keyring subsystem. - * - * Return: same as with tpm_transmit_cmd() - */ -int tpm_seal_trusted(struct tpm_chip *chip, struct trusted_key_payload *payload, - struct trusted_key_options *options) -{ - int rc; - - chip = tpm_find_get_ops(chip); - if (!chip || !(chip->flags & TPM_CHIP_FLAG_TPM2)) - return -ENODEV; - - rc = tpm2_seal_trusted(chip, payload, options); - - tpm_put_ops(chip); - return rc; -} -EXPORT_SYMBOL_GPL(tpm_seal_trusted); - -/** - * tpm_unseal_trusted() - unseal a trusted key - * @chip: a &struct tpm_chip instance, %NULL for the default chip - * @options: authentication values and other options - * @payload: the key data in clear and encrypted form - * - * Note: only TPM 2.0 chip are supported. TPM 1.x implementation is located in - * the keyring subsystem. - * - * Return: same as with tpm_transmit_cmd() - */ -int tpm_unseal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options) -{ - int rc; - - chip = tpm_find_get_ops(chip); - if (!chip || !(chip->flags & TPM_CHIP_FLAG_TPM2)) - return -ENODEV; - - rc = tpm2_unseal_trusted(chip, payload, options); - - tpm_put_ops(chip); - - return rc; -} -EXPORT_SYMBOL_GPL(tpm_unseal_trusted); - static int __init tpm_init(void) { int rc; diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h index b174cf46410c..b9e1547be6b5 100644 --- a/drivers/char/tpm/tpm.h +++ b/drivers/char/tpm/tpm.h @@ -212,11 +212,6 @@ static inline void tpm_add_ppi(struct tpm_chip *chip) } #endif -static inline u32 tpm2_rc_value(u32 rc) -{ - return (rc & BIT(7)) ? rc & 0xff : rc; -} - int tpm2_get_timeouts(struct tpm_chip *chip); int tpm2_pcr_read(struct tpm_chip *chip, u32 pcr_idx, struct tpm_digest *digest, u16 *digest_size_ptr); @@ -224,12 +219,6 @@ int tpm2_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, struct tpm_digest *digests); int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max); void tpm2_flush_context(struct tpm_chip *chip, u32 handle); -int tpm2_seal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options); -int tpm2_unseal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options); ssize_t tpm2_get_tpm_pt(struct tpm_chip *chip, u32 property_id, u32 *value, const char *desc); diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index 5817dfe5c5d2..fdb457704aa7 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -13,20 +13,6 @@ #include "tpm.h" #include -#include - -enum tpm2_object_attributes { - TPM2_OA_USER_WITH_AUTH = BIT(6), -}; - -enum tpm2_session_attributes { - TPM2_SA_CONTINUE_SESSION = BIT(0), -}; - -struct tpm2_hash { - unsigned int crypto_id; - unsigned int tpm_id; -}; static struct tpm2_hash tpm2_hash_map[] = { {HASH_ALGO_SHA1, TPM_ALG_SHA1}, @@ -377,299 +363,6 @@ void tpm2_flush_context(struct tpm_chip *chip, u32 handle) tpm_buf_destroy(&buf); } -/** - * tpm_buf_append_auth() - append TPMS_AUTH_COMMAND to the buffer. - * - * @buf: an allocated tpm_buf instance - * @session_handle: session handle - * @nonce: the session nonce, may be NULL if not used - * @nonce_len: the session nonce length, may be 0 if not used - * @attributes: the session attributes - * @hmac: the session HMAC or password, may be NULL if not used - * @hmac_len: the session HMAC or password length, maybe 0 if not used - */ -static void tpm2_buf_append_auth(struct tpm_buf *buf, u32 session_handle, - const u8 *nonce, u16 nonce_len, - u8 attributes, - const u8 *hmac, u16 hmac_len) -{ - tpm_buf_append_u32(buf, 9 + nonce_len + hmac_len); - tpm_buf_append_u32(buf, session_handle); - tpm_buf_append_u16(buf, nonce_len); - - if (nonce && nonce_len) - tpm_buf_append(buf, nonce, nonce_len); - - tpm_buf_append_u8(buf, attributes); - tpm_buf_append_u16(buf, hmac_len); - - if (hmac && hmac_len) - tpm_buf_append(buf, hmac, hmac_len); -} - -/** - * tpm2_seal_trusted() - seal the payload of a trusted key - * - * @chip: TPM chip to use - * @payload: the key data in clear and encrypted form - * @options: authentication values and other options - * - * Return: < 0 on error and 0 on success. - */ -int tpm2_seal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options) -{ - unsigned int blob_len; - struct tpm_buf buf; - u32 hash; - int i; - int rc; - - for (i = 0; i < ARRAY_SIZE(tpm2_hash_map); i++) { - if (options->hash == tpm2_hash_map[i].crypto_id) { - hash = tpm2_hash_map[i].tpm_id; - break; - } - } - - if (i == ARRAY_SIZE(tpm2_hash_map)) - return -EINVAL; - - rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_CREATE); - if (rc) - return rc; - - tpm_buf_append_u32(&buf, options->keyhandle); - tpm2_buf_append_auth(&buf, TPM2_RS_PW, - NULL /* nonce */, 0, - 0 /* session_attributes */, - options->keyauth /* hmac */, - TPM_DIGEST_SIZE); - - /* sensitive */ - tpm_buf_append_u16(&buf, 4 + TPM_DIGEST_SIZE + payload->key_len + 1); - - tpm_buf_append_u16(&buf, TPM_DIGEST_SIZE); - tpm_buf_append(&buf, options->blobauth, TPM_DIGEST_SIZE); - tpm_buf_append_u16(&buf, payload->key_len + 1); - tpm_buf_append(&buf, payload->key, payload->key_len); - tpm_buf_append_u8(&buf, payload->migratable); - - /* public */ - tpm_buf_append_u16(&buf, 14 + options->policydigest_len); - tpm_buf_append_u16(&buf, TPM_ALG_KEYEDHASH); - tpm_buf_append_u16(&buf, hash); - - /* policy */ - if (options->policydigest_len) { - tpm_buf_append_u32(&buf, 0); - tpm_buf_append_u16(&buf, options->policydigest_len); - tpm_buf_append(&buf, options->policydigest, - options->policydigest_len); - } else { - tpm_buf_append_u32(&buf, TPM2_OA_USER_WITH_AUTH); - tpm_buf_append_u16(&buf, 0); - } - - /* public parameters */ - tpm_buf_append_u16(&buf, TPM_ALG_NULL); - tpm_buf_append_u16(&buf, 0); - - /* outside info */ - tpm_buf_append_u16(&buf, 0); - - /* creation PCR */ - tpm_buf_append_u32(&buf, 0); - - if (buf.flags & TPM_BUF_OVERFLOW) { - rc = -E2BIG; - goto out; - } - - rc = tpm_transmit_cmd(chip, &buf, 4, "sealing data"); - if (rc) - goto out; - - blob_len = be32_to_cpup((__be32 *) &buf.data[TPM_HEADER_SIZE]); - if (blob_len > MAX_BLOB_SIZE) { - rc = -E2BIG; - goto out; - } - if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + 4 + blob_len) { - rc = -EFAULT; - goto out; - } - - memcpy(payload->blob, &buf.data[TPM_HEADER_SIZE + 4], blob_len); - payload->blob_len = blob_len; - -out: - tpm_buf_destroy(&buf); - - if (rc > 0) { - if (tpm2_rc_value(rc) == TPM2_RC_HASH) - rc = -EINVAL; - else - rc = -EPERM; - } - - return rc; -} - -/** - * tpm2_load_cmd() - execute a TPM2_Load command - * - * @chip: TPM chip to use - * @payload: the key data in clear and encrypted form - * @options: authentication values and other options - * @blob_handle: returned blob handle - * - * Return: 0 on success. - * -E2BIG on wrong payload size. - * -EPERM on tpm error status. - * < 0 error from tpm_transmit_cmd. - */ -static int tpm2_load_cmd(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options, - u32 *blob_handle) -{ - struct tpm_buf buf; - unsigned int private_len; - unsigned int public_len; - unsigned int blob_len; - int rc; - - private_len = be16_to_cpup((__be16 *) &payload->blob[0]); - if (private_len > (payload->blob_len - 2)) - return -E2BIG; - - public_len = be16_to_cpup((__be16 *) &payload->blob[2 + private_len]); - blob_len = private_len + public_len + 4; - if (blob_len > payload->blob_len) - return -E2BIG; - - rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_LOAD); - if (rc) - return rc; - - tpm_buf_append_u32(&buf, options->keyhandle); - tpm2_buf_append_auth(&buf, TPM2_RS_PW, - NULL /* nonce */, 0, - 0 /* session_attributes */, - options->keyauth /* hmac */, - TPM_DIGEST_SIZE); - - tpm_buf_append(&buf, payload->blob, blob_len); - - if (buf.flags & TPM_BUF_OVERFLOW) { - rc = -E2BIG; - goto out; - } - - rc = tpm_transmit_cmd(chip, &buf, 4, "loading blob"); - if (!rc) - *blob_handle = be32_to_cpup( - (__be32 *) &buf.data[TPM_HEADER_SIZE]); - -out: - tpm_buf_destroy(&buf); - - if (rc > 0) - rc = -EPERM; - - return rc; -} - -/** - * tpm2_unseal_cmd() - execute a TPM2_Unload command - * - * @chip: TPM chip to use - * @payload: the key data in clear and encrypted form - * @options: authentication values and other options - * @blob_handle: blob handle - * - * Return: 0 on success - * -EPERM on tpm error status - * < 0 error from tpm_transmit_cmd - */ -static int tpm2_unseal_cmd(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options, - u32 blob_handle) -{ - struct tpm_buf buf; - u16 data_len; - u8 *data; - int rc; - - rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_UNSEAL); - if (rc) - return rc; - - tpm_buf_append_u32(&buf, blob_handle); - tpm2_buf_append_auth(&buf, - options->policyhandle ? - options->policyhandle : TPM2_RS_PW, - NULL /* nonce */, 0, - TPM2_SA_CONTINUE_SESSION, - options->blobauth /* hmac */, - TPM_DIGEST_SIZE); - - rc = tpm_transmit_cmd(chip, &buf, 6, "unsealing"); - if (rc > 0) - rc = -EPERM; - - if (!rc) { - data_len = be16_to_cpup( - (__be16 *) &buf.data[TPM_HEADER_SIZE + 4]); - if (data_len < MIN_KEY_SIZE || data_len > MAX_KEY_SIZE + 1) { - rc = -EFAULT; - goto out; - } - - if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + 6 + data_len) { - rc = -EFAULT; - goto out; - } - data = &buf.data[TPM_HEADER_SIZE + 6]; - - memcpy(payload->key, data, data_len - 1); - payload->key_len = data_len - 1; - payload->migratable = data[data_len - 1]; - } - -out: - tpm_buf_destroy(&buf); - return rc; -} - -/** - * tpm2_unseal_trusted() - unseal the payload of a trusted key - * - * @chip: TPM chip to use - * @payload: the key data in clear and encrypted form - * @options: authentication values and other options - * - * Return: Same as with tpm_transmit_cmd. - */ -int tpm2_unseal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options) -{ - u32 blob_handle; - int rc; - - rc = tpm2_load_cmd(chip, payload, options, &blob_handle); - if (rc) - return rc; - - rc = tpm2_unseal_cmd(chip, payload, options, blob_handle); - tpm2_flush_context(chip, blob_handle); - return rc; -} - struct tpm2_get_cap_out { u8 more_data; __be32 subcap_id; diff --git a/include/keys/trusted_tpm.h b/include/keys/trusted_tpm.h index 7b9d7b450a9e..a56d8e1298f2 100644 --- a/include/keys/trusted_tpm.h +++ b/include/keys/trusted_tpm.h @@ -40,6 +40,13 @@ int TSS_checkhmac1(unsigned char *buffer, int trusted_tpm_send(unsigned char *cmd, size_t buflen); int oiap(struct tpm_buf *tb, uint32_t *handle, unsigned char *nonce); +int tpm2_seal_trusted(struct tpm_chip *chip, + struct trusted_key_payload *payload, + struct trusted_key_options *options); +int tpm2_unseal_trusted(struct tpm_chip *chip, + struct trusted_key_payload *payload, + struct trusted_key_options *options); + #define TPM_DEBUG 0 #if TPM_DEBUG diff --git a/include/linux/tpm.h b/include/linux/tpm.h index c78119fcac7f..0d6e949ba315 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -296,6 +296,19 @@ struct tpm_buf { u8 *data; }; +enum tpm2_object_attributes { + TPM2_OA_USER_WITH_AUTH = BIT(6), +}; + +enum tpm2_session_attributes { + TPM2_SA_CONTINUE_SESSION = BIT(0), +}; + +struct tpm2_hash { + unsigned int crypto_id; + unsigned int tpm_id; +}; + static inline void tpm_buf_reset(struct tpm_buf *buf, u16 tag, u32 ordinal) { struct tpm_header *head = (struct tpm_header *)buf->data; @@ -375,6 +388,11 @@ static inline void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value) tpm_buf_append(buf, (u8 *) &value2, 4); } +static inline u32 tpm2_rc_value(u32 rc) +{ + return (rc & BIT(7)) ? rc & 0xff : rc; +} + #if defined(CONFIG_TCG_TPM) || defined(CONFIG_TCG_TPM_MODULE) extern int tpm_is_tpm2(struct tpm_chip *chip); @@ -384,12 +402,6 @@ extern int tpm_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, struct tpm_digest *digests); extern int tpm_send(struct tpm_chip *chip, void *cmd, size_t buflen); extern int tpm_get_random(struct tpm_chip *chip, u8 *data, size_t max); -extern int tpm_seal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options); -extern int tpm_unseal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options); extern struct tpm_chip *tpm_default_chip(void); #else static inline int tpm_is_tpm2(struct tpm_chip *chip) @@ -418,18 +430,6 @@ static inline int tpm_get_random(struct tpm_chip *chip, u8 *data, size_t max) return -ENODEV; } -static inline int tpm_seal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options) -{ - return -ENODEV; -} -static inline int tpm_unseal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options) -{ - return -ENODEV; -} static inline struct tpm_chip *tpm_default_chip(void) { return NULL; diff --git a/security/keys/trusted-keys/Makefile b/security/keys/trusted-keys/Makefile index 1a24680edc6a..7b73cebbb378 100644 --- a/security/keys/trusted-keys/Makefile +++ b/security/keys/trusted-keys/Makefile @@ -5,3 +5,4 @@ obj-$(CONFIG_TRUSTED_KEYS) += trusted.o trusted-y += trusted_tpm1.o +trusted-y += trusted_tpm2.o diff --git a/security/keys/trusted-keys/trusted_tpm1.c b/security/keys/trusted-keys/trusted_tpm1.c index e3155fd08f5b..eb5074e46323 100644 --- a/security/keys/trusted-keys/trusted_tpm1.c +++ b/security/keys/trusted-keys/trusted_tpm1.c @@ -1004,7 +1004,7 @@ static int trusted_instantiate(struct key *key, switch (key_cmd) { case Opt_load: if (tpm2) - ret = tpm_unseal_trusted(chip, payload, options); + ret = tpm2_unseal_trusted(chip, payload, options); else ret = key_unseal(payload, options); dump_payload(payload); @@ -1020,7 +1020,7 @@ static int trusted_instantiate(struct key *key, goto out; } if (tpm2) - ret = tpm_seal_trusted(chip, payload, options); + ret = tpm2_seal_trusted(chip, payload, options); else ret = key_seal(payload, options); if (ret < 0) diff --git a/security/keys/trusted-keys/trusted_tpm2.c b/security/keys/trusted-keys/trusted_tpm2.c new file mode 100644 index 000000000000..a9810ac2776f --- /dev/null +++ b/security/keys/trusted-keys/trusted_tpm2.c @@ -0,0 +1,314 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2004 IBM Corporation + * Copyright (C) 2014 Intel Corporation + */ + +#include +#include +#include +#include + +#include +#include + +static struct tpm2_hash tpm2_hash_map[] = { + {HASH_ALGO_SHA1, TPM_ALG_SHA1}, + {HASH_ALGO_SHA256, TPM_ALG_SHA256}, + {HASH_ALGO_SHA384, TPM_ALG_SHA384}, + {HASH_ALGO_SHA512, TPM_ALG_SHA512}, + {HASH_ALGO_SM3_256, TPM_ALG_SM3_256}, +}; + +/** + * tpm_buf_append_auth() - append TPMS_AUTH_COMMAND to the buffer. + * + * @buf: an allocated tpm_buf instance + * @session_handle: session handle + * @nonce: the session nonce, may be NULL if not used + * @nonce_len: the session nonce length, may be 0 if not used + * @attributes: the session attributes + * @hmac: the session HMAC or password, may be NULL if not used + * @hmac_len: the session HMAC or password length, maybe 0 if not used + */ +static void tpm2_buf_append_auth(struct tpm_buf *buf, u32 session_handle, + const u8 *nonce, u16 nonce_len, + u8 attributes, + const u8 *hmac, u16 hmac_len) +{ + tpm_buf_append_u32(buf, 9 + nonce_len + hmac_len); + tpm_buf_append_u32(buf, session_handle); + tpm_buf_append_u16(buf, nonce_len); + + if (nonce && nonce_len) + tpm_buf_append(buf, nonce, nonce_len); + + tpm_buf_append_u8(buf, attributes); + tpm_buf_append_u16(buf, hmac_len); + + if (hmac && hmac_len) + tpm_buf_append(buf, hmac, hmac_len); +} + +/** + * tpm2_seal_trusted() - seal the payload of a trusted key + * + * @chip: TPM chip to use + * @payload: the key data in clear and encrypted form + * @options: authentication values and other options + * + * Return: < 0 on error and 0 on success. + */ +int tpm2_seal_trusted(struct tpm_chip *chip, + struct trusted_key_payload *payload, + struct trusted_key_options *options) +{ + unsigned int blob_len; + struct tpm_buf buf; + u32 hash; + int i; + int rc; + + for (i = 0; i < ARRAY_SIZE(tpm2_hash_map); i++) { + if (options->hash == tpm2_hash_map[i].crypto_id) { + hash = tpm2_hash_map[i].tpm_id; + break; + } + } + + if (i == ARRAY_SIZE(tpm2_hash_map)) + return -EINVAL; + + rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_CREATE); + if (rc) + return rc; + + tpm_buf_append_u32(&buf, options->keyhandle); + tpm2_buf_append_auth(&buf, TPM2_RS_PW, + NULL /* nonce */, 0, + 0 /* session_attributes */, + options->keyauth /* hmac */, + TPM_DIGEST_SIZE); + + /* sensitive */ + tpm_buf_append_u16(&buf, 4 + TPM_DIGEST_SIZE + payload->key_len + 1); + + tpm_buf_append_u16(&buf, TPM_DIGEST_SIZE); + tpm_buf_append(&buf, options->blobauth, TPM_DIGEST_SIZE); + tpm_buf_append_u16(&buf, payload->key_len + 1); + tpm_buf_append(&buf, payload->key, payload->key_len); + tpm_buf_append_u8(&buf, payload->migratable); + + /* public */ + tpm_buf_append_u16(&buf, 14 + options->policydigest_len); + tpm_buf_append_u16(&buf, TPM_ALG_KEYEDHASH); + tpm_buf_append_u16(&buf, hash); + + /* policy */ + if (options->policydigest_len) { + tpm_buf_append_u32(&buf, 0); + tpm_buf_append_u16(&buf, options->policydigest_len); + tpm_buf_append(&buf, options->policydigest, + options->policydigest_len); + } else { + tpm_buf_append_u32(&buf, TPM2_OA_USER_WITH_AUTH); + tpm_buf_append_u16(&buf, 0); + } + + /* public parameters */ + tpm_buf_append_u16(&buf, TPM_ALG_NULL); + tpm_buf_append_u16(&buf, 0); + + /* outside info */ + tpm_buf_append_u16(&buf, 0); + + /* creation PCR */ + tpm_buf_append_u32(&buf, 0); + + if (buf.flags & TPM_BUF_OVERFLOW) { + rc = -E2BIG; + goto out; + } + + rc = tpm_send(chip, buf.data, tpm_buf_length(&buf)); + if (rc) + goto out; + + blob_len = be32_to_cpup((__be32 *) &buf.data[TPM_HEADER_SIZE]); + if (blob_len > MAX_BLOB_SIZE) { + rc = -E2BIG; + goto out; + } + if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + 4 + blob_len) { + rc = -EFAULT; + goto out; + } + + memcpy(payload->blob, &buf.data[TPM_HEADER_SIZE + 4], blob_len); + payload->blob_len = blob_len; + +out: + tpm_buf_destroy(&buf); + + if (rc > 0) { + if (tpm2_rc_value(rc) == TPM2_RC_HASH) + rc = -EINVAL; + else + rc = -EPERM; + } + + return rc; +} + +/** + * tpm2_load_cmd() - execute a TPM2_Load command + * + * @chip: TPM chip to use + * @payload: the key data in clear and encrypted form + * @options: authentication values and other options + * @blob_handle: returned blob handle + * + * Return: 0 on success. + * -E2BIG on wrong payload size. + * -EPERM on tpm error status. + * < 0 error from tpm_send. + */ +static int tpm2_load_cmd(struct tpm_chip *chip, + struct trusted_key_payload *payload, + struct trusted_key_options *options, + u32 *blob_handle) +{ + struct tpm_buf buf; + unsigned int private_len; + unsigned int public_len; + unsigned int blob_len; + int rc; + + private_len = be16_to_cpup((__be16 *) &payload->blob[0]); + if (private_len > (payload->blob_len - 2)) + return -E2BIG; + + public_len = be16_to_cpup((__be16 *) &payload->blob[2 + private_len]); + blob_len = private_len + public_len + 4; + if (blob_len > payload->blob_len) + return -E2BIG; + + rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_LOAD); + if (rc) + return rc; + + tpm_buf_append_u32(&buf, options->keyhandle); + tpm2_buf_append_auth(&buf, TPM2_RS_PW, + NULL /* nonce */, 0, + 0 /* session_attributes */, + options->keyauth /* hmac */, + TPM_DIGEST_SIZE); + + tpm_buf_append(&buf, payload->blob, blob_len); + + if (buf.flags & TPM_BUF_OVERFLOW) { + rc = -E2BIG; + goto out; + } + + rc = tpm_send(chip, buf.data, tpm_buf_length(&buf)); + if (!rc) + *blob_handle = be32_to_cpup( + (__be32 *) &buf.data[TPM_HEADER_SIZE]); + +out: + tpm_buf_destroy(&buf); + + if (rc > 0) + rc = -EPERM; + + return rc; +} + +/** + * tpm2_unseal_cmd() - execute a TPM2_Unload command + * + * @chip: TPM chip to use + * @payload: the key data in clear and encrypted form + * @options: authentication values and other options + * @blob_handle: blob handle + * + * Return: 0 on success + * -EPERM on tpm error status + * < 0 error from tpm_send + */ +static int tpm2_unseal_cmd(struct tpm_chip *chip, + struct trusted_key_payload *payload, + struct trusted_key_options *options, + u32 blob_handle) +{ + struct tpm_buf buf; + u16 data_len; + u8 *data; + int rc; + + rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_UNSEAL); + if (rc) + return rc; + + tpm_buf_append_u32(&buf, blob_handle); + tpm2_buf_append_auth(&buf, + options->policyhandle ? + options->policyhandle : TPM2_RS_PW, + NULL /* nonce */, 0, + TPM2_SA_CONTINUE_SESSION, + options->blobauth /* hmac */, + TPM_DIGEST_SIZE); + + rc = tpm_send(chip, buf.data, tpm_buf_length(&buf)); + if (rc > 0) + rc = -EPERM; + + if (!rc) { + data_len = be16_to_cpup( + (__be16 *) &buf.data[TPM_HEADER_SIZE + 4]); + if (data_len < MIN_KEY_SIZE || data_len > MAX_KEY_SIZE + 1) { + rc = -EFAULT; + goto out; + } + + if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + 6 + data_len) { + rc = -EFAULT; + goto out; + } + data = &buf.data[TPM_HEADER_SIZE + 6]; + + memcpy(payload->key, data, data_len - 1); + payload->key_len = data_len - 1; + payload->migratable = data[data_len - 1]; + } + +out: + tpm_buf_destroy(&buf); + return rc; +} + +/** + * tpm2_unseal_trusted() - unseal the payload of a trusted key + * + * @chip: TPM chip to use + * @payload: the key data in clear and encrypted form + * @options: authentication values and other options + * + * Return: Same as with tpm_send. + */ +int tpm2_unseal_trusted(struct tpm_chip *chip, + struct trusted_key_payload *payload, + struct trusted_key_options *options) +{ + u32 blob_handle; + int rc; + + rc = tpm2_load_cmd(chip, payload, options, &blob_handle); + if (rc) + return rc; + + rc = tpm2_unseal_cmd(chip, payload, options, blob_handle); + + return rc; +} -- cgit v1.2.3-71-gd317 From 56f434f40f059eb3769d50b9c244a850096c3d6f Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 12 Nov 2019 16:22:18 -0400 Subject: mm/mmu_notifier: define the header pre-processor parts even if disabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Now that we have KERNEL_HEADER_TEST all headers are generally compile tested, so relying on makefile tricks to avoid compiling code that depends on CONFIG_MMU_NOTIFIER is more annoying. Instead follow the usual pattern and provide most of the header with only the functions stubbed out when CONFIG_MMU_NOTIFIER is disabled. This ensures code compiles no matter what the config setting is. While here, struct mmu_notifier_mm is private to mmu_notifier.c, move it. Link: https://lore.kernel.org/r/20191112202231.3856-2-jgg@ziepe.ca Reviewed-by: Jérôme Glisse Tested-by: Ralph Campbell Reviewed-by: John Hubbard Reviewed-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe --- include/linux/mmu_notifier.h | 46 ++++++++++++++++---------------------------- mm/mmu_notifier.c | 13 +++++++++++++ 2 files changed, 30 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 1bd8e6a09a3c..12bd603d318c 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -7,8 +7,9 @@ #include #include +struct mmu_notifier_mm; struct mmu_notifier; -struct mmu_notifier_ops; +struct mmu_notifier_range; /** * enum mmu_notifier_event - reason for the mmu notifier callback @@ -40,36 +41,8 @@ enum mmu_notifier_event { MMU_NOTIFY_SOFT_DIRTY, }; -#ifdef CONFIG_MMU_NOTIFIER - -#ifdef CONFIG_LOCKDEP -extern struct lockdep_map __mmu_notifier_invalidate_range_start_map; -#endif - -/* - * The mmu notifier_mm structure is allocated and installed in - * mm->mmu_notifier_mm inside the mm_take_all_locks() protected - * critical section and it's released only when mm_count reaches zero - * in mmdrop(). - */ -struct mmu_notifier_mm { - /* all mmu notifiers registerd in this mm are queued in this list */ - struct hlist_head list; - /* to serialize the list modifications and hlist_unhashed */ - spinlock_t lock; -}; - #define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0) -struct mmu_notifier_range { - struct vm_area_struct *vma; - struct mm_struct *mm; - unsigned long start; - unsigned long end; - unsigned flags; - enum mmu_notifier_event event; -}; - struct mmu_notifier_ops { /* * Called either by mmu_notifier_unregister or when the mm is @@ -249,6 +222,21 @@ struct mmu_notifier { unsigned int users; }; +#ifdef CONFIG_MMU_NOTIFIER + +#ifdef CONFIG_LOCKDEP +extern struct lockdep_map __mmu_notifier_invalidate_range_start_map; +#endif + +struct mmu_notifier_range { + struct vm_area_struct *vma; + struct mm_struct *mm; + unsigned long start; + unsigned long end; + unsigned flags; + enum mmu_notifier_event event; +}; + static inline int mm_has_notifiers(struct mm_struct *mm) { return unlikely(mm->mmu_notifier_mm); diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 7fde88695f35..367670cfd02b 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -27,6 +27,19 @@ struct lockdep_map __mmu_notifier_invalidate_range_start_map = { }; #endif +/* + * The mmu notifier_mm structure is allocated and installed in + * mm->mmu_notifier_mm inside the mm_take_all_locks() protected + * critical section and it's released only when mm_count reaches zero + * in mmdrop(). + */ +struct mmu_notifier_mm { + /* all mmu notifiers registered in this mm are queued in this list */ + struct hlist_head list; + /* to serialize the list modifications and hlist_unhashed */ + spinlock_t lock; +}; + /* * This function can't run concurrently against mmu_notifier_register * because mm->mm_users > 0 during mmu_notifier_register and exit_mmap -- cgit v1.2.3-71-gd317 From d41003513e61dd9d4974cb441d30b63650b85654 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 11 Nov 2019 11:39:30 +0900 Subject: block: rework zone reporting Avoid the need to allocate a potentially large array of struct blk_zone in the block layer by switching the ->report_zones method interface to a callback model. Now the caller simply supplies a callback that is executed on each reported zone, and private data for it. Signed-off-by: Christoph Hellwig Signed-off-by: Shin'ichiro Kawasaki Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Mike Snitzer Signed-off-by: Jens Axboe --- block/blk-zoned.c | 253 ++++++++++++++++------------------------- drivers/block/null_blk.h | 2 +- drivers/block/null_blk_zoned.c | 31 +++-- drivers/md/dm-flakey.c | 18 +-- drivers/md/dm-linear.c | 20 ++-- drivers/md/dm-zoned-metadata.c | 131 ++++++++------------- drivers/md/dm.c | 121 +++++++++----------- drivers/scsi/sd.h | 4 +- drivers/scsi/sd_zbc.c | 106 ++++++++--------- fs/f2fs/super.c | 51 +++------ include/linux/blkdev.h | 15 ++- include/linux/device-mapper.h | 24 +++- 12 files changed, 329 insertions(+), 447 deletions(-) (limited to 'include/linux') diff --git a/block/blk-zoned.c b/block/blk-zoned.c index ae665e490858..6fad6f3f6980 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -101,44 +101,35 @@ EXPORT_SYMBOL_GPL(blkdev_nr_zones); * blkdev_report_zones - Get zones information * @bdev: Target block device * @sector: Sector from which to report zones - * @zones: Array of zone structures where to return the zones information - * @nr_zones: Number of zone structures in the zone array + * @nr_zones: Maximum number of zones to report + * @cb: Callback function called for each reported zone + * @data: Private data for the callback * * Description: - * Get zone information starting from the zone containing @sector. - * The number of zone information reported may be less than the number - * requested by @nr_zones. The number of zones actually reported is - * returned in @nr_zones. - * The caller must use memalloc_noXX_save/restore() calls to control - * memory allocations done within this function (zone array and command - * buffer allocation by the device driver). + * Get zone information starting from the zone containing @sector for at most + * @nr_zones, and call @cb for each zone reported by the device. + * To report all zones in a device starting from @sector, the BLK_ALL_ZONES + * constant can be passed to @nr_zones. + * Returns the number of zones reported by the device, or a negative errno + * value in case of failure. + * + * Note: The caller must use memalloc_noXX_save/restore() calls to control + * memory allocations done within this function. */ int blkdev_report_zones(struct block_device *bdev, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones) + unsigned int nr_zones, report_zones_cb cb, void *data) { - struct request_queue *q = bdev_get_queue(bdev); struct gendisk *disk = bdev->bd_disk; sector_t capacity = get_capacity(disk); - if (!blk_queue_is_zoned(q)) - return -EOPNOTSUPP; - - /* - * A block device that advertized itself as zoned must have a - * report_zones method. If it does not have one defined, the device - * driver has a bug. So warn about that. - */ - if (WARN_ON_ONCE(!disk->fops->report_zones)) + if (!blk_queue_is_zoned(bdev_get_queue(bdev)) || + WARN_ON_ONCE(!disk->fops->report_zones)) return -EOPNOTSUPP; - if (!*nr_zones || sector >= capacity) { - *nr_zones = 0; + if (!nr_zones || sector >= capacity) return 0; - } - *nr_zones = min(*nr_zones, __blkdev_nr_zones(q, capacity - sector)); - - return disk->fops->report_zones(disk, sector, zones, nr_zones); + return disk->fops->report_zones(disk, sector, nr_zones, cb, data); } EXPORT_SYMBOL_GPL(blkdev_report_zones); @@ -232,6 +223,20 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op, } EXPORT_SYMBOL_GPL(blkdev_zone_mgmt); +struct zone_report_args { + struct blk_zone __user *zones; +}; + +static int blkdev_copy_zone_to_user(struct blk_zone *zone, unsigned int idx, + void *data) +{ + struct zone_report_args *args = data; + + if (copy_to_user(&args->zones[idx], zone, sizeof(struct blk_zone))) + return -EFAULT; + return 0; +} + /* * BLKREPORTZONE ioctl processing. * Called from blkdev_ioctl. @@ -240,9 +245,9 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; + struct zone_report_args args; struct request_queue *q; struct blk_zone_report rep; - struct blk_zone *zones; int ret; if (!argp) @@ -264,32 +269,16 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, if (!rep.nr_zones) return -EINVAL; - rep.nr_zones = min(blkdev_nr_zones(bdev), rep.nr_zones); - - zones = kvmalloc_array(rep.nr_zones, sizeof(struct blk_zone), - GFP_KERNEL | __GFP_ZERO); - if (!zones) - return -ENOMEM; - - ret = blkdev_report_zones(bdev, rep.sector, zones, &rep.nr_zones); - if (ret) - goto out; - - if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report))) { - ret = -EFAULT; - goto out; - } - - if (rep.nr_zones) { - if (copy_to_user(argp + sizeof(struct blk_zone_report), zones, - sizeof(struct blk_zone) * rep.nr_zones)) - ret = -EFAULT; - } + args.zones = argp + sizeof(struct blk_zone_report); + ret = blkdev_report_zones(bdev, rep.sector, rep.nr_zones, + blkdev_copy_zone_to_user, &args); + if (ret < 0) + return ret; - out: - kvfree(zones); - - return ret; + rep.nr_zones = ret; + if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report))) + return -EFAULT; + return 0; } /* @@ -351,31 +340,6 @@ static inline unsigned long *blk_alloc_zone_bitmap(int node, GFP_NOIO, node); } -/* - * Allocate an array of struct blk_zone to get nr_zones zone information. - * The allocated array may be smaller than nr_zones. - */ -static struct blk_zone *blk_alloc_zones(unsigned int *nr_zones) -{ - struct blk_zone *zones; - size_t nrz = min(*nr_zones, BLK_ZONED_REPORT_MAX_ZONES); - - /* - * GFP_KERNEL here is meaningless as the caller task context has - * the PF_MEMALLOC_NOIO flag set in blk_revalidate_disk_zones() - * with memalloc_noio_save(). - */ - zones = kvcalloc(nrz, sizeof(struct blk_zone), GFP_KERNEL); - if (!zones) { - *nr_zones = 0; - return NULL; - } - - *nr_zones = nrz; - - return zones; -} - void blk_queue_free_zone_bitmaps(struct request_queue *q) { kfree(q->seq_zones_bitmap); @@ -384,12 +348,21 @@ void blk_queue_free_zone_bitmaps(struct request_queue *q) q->seq_zones_wlock = NULL; } +struct blk_revalidate_zone_args { + struct gendisk *disk; + unsigned long *seq_zones_bitmap; + unsigned long *seq_zones_wlock; + sector_t sector; +}; + /* * Helper function to check the validity of zones of a zoned block device. */ -static bool blk_zone_valid(struct gendisk *disk, struct blk_zone *zone, - sector_t *sector) +static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx, + void *data) { + struct blk_revalidate_zone_args *args = data; + struct gendisk *disk = args->disk; struct request_queue *q = disk->queue; sector_t zone_sectors = blk_queue_zone_sectors(q); sector_t capacity = get_capacity(disk); @@ -409,14 +382,14 @@ static bool blk_zone_valid(struct gendisk *disk, struct blk_zone *zone, zone->len > zone_sectors) { pr_warn("%s: Invalid zoned device with larger last zone size\n", disk->disk_name); - return false; + return -ENODEV; } /* Check for holes in the zone report */ - if (zone->start != *sector) { + if (zone->start != args->sector) { pr_warn("%s: Zone gap at sectors %llu..%llu\n", - disk->disk_name, *sector, zone->start); - return false; + disk->disk_name, args->sector, zone->start); + return -ENODEV; } /* Check zone type */ @@ -428,12 +401,38 @@ static bool blk_zone_valid(struct gendisk *disk, struct blk_zone *zone, default: pr_warn("%s: Invalid zone type 0x%x at sectors %llu\n", disk->disk_name, (int)zone->type, zone->start); - return false; + return -ENODEV; } - *sector += zone->len; + if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) + set_bit(idx, args->seq_zones_bitmap); - return true; + args->sector += zone->len; + return 0; +} + +static int blk_update_zone_info(struct gendisk *disk, unsigned int nr_zones, + struct blk_revalidate_zone_args *args) +{ + /* + * Ensure that all memory allocations in this context are done as + * if GFP_NOIO was specified. + */ + unsigned int noio_flag = memalloc_noio_save(); + struct request_queue *q = disk->queue; + int ret; + + args->seq_zones_wlock = blk_alloc_zone_bitmap(q->node, nr_zones); + if (!args->seq_zones_wlock) + return -ENOMEM; + args->seq_zones_bitmap = blk_alloc_zone_bitmap(q->node, nr_zones); + if (!args->seq_zones_bitmap) + return -ENOMEM; + + ret = disk->fops->report_zones(disk, 0, nr_zones, + blk_revalidate_zone_cb, args); + memalloc_noio_restore(noio_flag); + return ret; } /** @@ -449,11 +448,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk) { struct request_queue *q = disk->queue; unsigned int nr_zones = __blkdev_nr_zones(q, get_capacity(disk)); - unsigned long *seq_zones_wlock = NULL, *seq_zones_bitmap = NULL; - unsigned int i, rep_nr_zones = 0, z = 0, nrz; - struct blk_zone *zones = NULL; - unsigned int noio_flag; - sector_t sector = 0; + struct blk_revalidate_zone_args args = { .disk = disk }; int ret = 0; if (WARN_ON_ONCE(!blk_queue_is_zoned(q))) @@ -468,82 +463,28 @@ int blk_revalidate_disk_zones(struct gendisk *disk) return 0; } - /* - * Ensure that all memory allocations in this context are done as - * if GFP_NOIO was specified. - */ - noio_flag = memalloc_noio_save(); - - if (!nr_zones) - goto update; - - /* Allocate bitmaps */ - ret = -ENOMEM; - seq_zones_wlock = blk_alloc_zone_bitmap(q->node, nr_zones); - if (!seq_zones_wlock) - goto out; - seq_zones_bitmap = blk_alloc_zone_bitmap(q->node, nr_zones); - if (!seq_zones_bitmap) - goto out; - - /* - * Get zone information to check the zones and initialize - * seq_zones_bitmap. - */ - rep_nr_zones = nr_zones; - zones = blk_alloc_zones(&rep_nr_zones); - if (!zones) - goto out; - - while (z < nr_zones) { - nrz = min(nr_zones - z, rep_nr_zones); - ret = disk->fops->report_zones(disk, sector, zones, &nrz); - if (ret) - goto out; - if (!nrz) - break; - for (i = 0; i < nrz; i++) { - if (!blk_zone_valid(disk, &zones[i], §or)) { - ret = -ENODEV; - goto out; - } - if (zones[i].type != BLK_ZONE_TYPE_CONVENTIONAL) - set_bit(z, seq_zones_bitmap); - z++; - } - } - - if (WARN_ON(z != nr_zones)) { - ret = -EIO; - goto out; - } + if (nr_zones) + ret = blk_update_zone_info(disk, nr_zones, &args); -update: /* * Install the new bitmaps, making sure the queue is stopped and * all I/Os are completed (i.e. a scheduler is not referencing the * bitmaps). */ blk_mq_freeze_queue(q); - q->nr_zones = nr_zones; - swap(q->seq_zones_wlock, seq_zones_wlock); - swap(q->seq_zones_bitmap, seq_zones_bitmap); - blk_mq_unfreeze_queue(q); - -out: - memalloc_noio_restore(noio_flag); - - kvfree(zones); - kfree(seq_zones_wlock); - kfree(seq_zones_bitmap); - - if (ret) { + if (ret >= 0) { + q->nr_zones = nr_zones; + swap(q->seq_zones_wlock, args.seq_zones_wlock); + swap(q->seq_zones_bitmap, args.seq_zones_bitmap); + ret = 0; + } else { pr_warn("%s: failed to revalidate zones\n", disk->disk_name); - blk_mq_freeze_queue(q); blk_queue_free_zone_bitmaps(q); - blk_mq_unfreeze_queue(q); } + blk_mq_unfreeze_queue(q); + kfree(args.seq_zones_wlock); + kfree(args.seq_zones_bitmap); return ret; } EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones); diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h index 9bf56fbab091..bc837862b767 100644 --- a/drivers/block/null_blk.h +++ b/drivers/block/null_blk.h @@ -92,7 +92,7 @@ struct nullb { int null_zone_init(struct nullb_device *dev); void null_zone_exit(struct nullb_device *dev); int null_report_zones(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones); + unsigned int nr_zones, report_zones_cb cb, void *data); blk_status_t null_handle_zoned(struct nullb_cmd *cmd, enum req_opf op, sector_t sector, sector_t nr_sectors); diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c index 00696f16664b..d4d88b581822 100644 --- a/drivers/block/null_blk_zoned.c +++ b/drivers/block/null_blk_zoned.c @@ -67,21 +67,34 @@ void null_zone_exit(struct nullb_device *dev) } int null_report_zones(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones) + unsigned int nr_zones, report_zones_cb cb, void *data) { struct nullb *nullb = disk->private_data; struct nullb_device *dev = nullb->dev; - unsigned int zno, nrz = 0; + unsigned int first_zone, i; + struct blk_zone zone; + int error; - zno = null_zone_no(dev, sector); - if (zno < dev->nr_zones) { - nrz = min_t(unsigned int, *nr_zones, dev->nr_zones - zno); - memcpy(zones, &dev->zones[zno], nrz * sizeof(struct blk_zone)); - } + first_zone = null_zone_no(dev, sector); + if (first_zone >= dev->nr_zones) + return 0; - *nr_zones = nrz; + nr_zones = min(nr_zones, dev->nr_zones - first_zone); + for (i = 0; i < nr_zones; i++) { + /* + * Stacked DM target drivers will remap the zone information by + * modifying the zone information passed to the report callback. + * So use a local copy to avoid corruption of the device zone + * array. + */ + memcpy(&zone, &dev->zones[first_zone + i], + sizeof(struct blk_zone)); + error = cb(&zone, i, data); + if (error) + return error; + } - return 0; + return nr_zones; } size_t null_zone_valid_read_len(struct nullb *nullb, diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 76587e9af0ef..a2cc9e45cbba 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -459,21 +459,15 @@ static int flakey_prepare_ioctl(struct dm_target *ti, struct block_device **bdev } #ifdef CONFIG_BLK_DEV_ZONED -static int flakey_report_zones(struct dm_target *ti, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones) +static int flakey_report_zones(struct dm_target *ti, + struct dm_report_zones_args *args, unsigned int nr_zones) { struct flakey_c *fc = ti->private; - int ret; + sector_t sector = flakey_map_sector(ti, args->next_sector); - /* Do report and remap it */ - ret = blkdev_report_zones(fc->dev->bdev, flakey_map_sector(ti, sector), - zones, nr_zones); - if (ret != 0) - return ret; - - if (*nr_zones) - dm_remap_zone_report(ti, fc->start, zones, nr_zones); - return 0; + args->start = fc->start; + return blkdev_report_zones(fc->dev->bdev, sector, nr_zones, + dm_report_zones_cb, args); } #endif diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 97acafd48c85..8d07fdf63a47 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -136,21 +136,15 @@ static int linear_prepare_ioctl(struct dm_target *ti, struct block_device **bdev } #ifdef CONFIG_BLK_DEV_ZONED -static int linear_report_zones(struct dm_target *ti, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones) +static int linear_report_zones(struct dm_target *ti, + struct dm_report_zones_args *args, unsigned int nr_zones) { - struct linear_c *lc = (struct linear_c *) ti->private; - int ret; - - /* Do report and remap it */ - ret = blkdev_report_zones(lc->dev->bdev, linear_map_sector(ti, sector), - zones, nr_zones); - if (ret != 0) - return ret; + struct linear_c *lc = ti->private; + sector_t sector = linear_map_sector(ti, args->next_sector); - if (*nr_zones) - dm_remap_zone_report(ti, lc->start, zones, nr_zones); - return 0; + args->start = lc->start; + return blkdev_report_zones(lc->dev->bdev, sector, nr_zones, + dm_report_zones_cb, args); } #endif diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c index feb4718ce6a6..069e4675da6b 100644 --- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -1080,9 +1080,10 @@ static int dmz_load_sb(struct dmz_metadata *zmd) /* * Initialize a zone descriptor. */ -static int dmz_init_zone(struct dmz_metadata *zmd, struct dm_zone *zone, - struct blk_zone *blkz) +static int dmz_init_zone(struct blk_zone *blkz, unsigned int idx, void *data) { + struct dmz_metadata *zmd = data; + struct dm_zone *zone = &zmd->zones[idx]; struct dmz_dev *dev = zmd->dev; /* Ignore the eventual last runt (smaller) zone */ @@ -1096,26 +1097,29 @@ static int dmz_init_zone(struct dmz_metadata *zmd, struct dm_zone *zone, atomic_set(&zone->refcount, 0); zone->chunk = DMZ_MAP_UNMAPPED; - if (blkz->type == BLK_ZONE_TYPE_CONVENTIONAL) { + switch (blkz->type) { + case BLK_ZONE_TYPE_CONVENTIONAL: set_bit(DMZ_RND, &zone->flags); zmd->nr_rnd_zones++; - } else if (blkz->type == BLK_ZONE_TYPE_SEQWRITE_REQ || - blkz->type == BLK_ZONE_TYPE_SEQWRITE_PREF) { + break; + case BLK_ZONE_TYPE_SEQWRITE_REQ: + case BLK_ZONE_TYPE_SEQWRITE_PREF: set_bit(DMZ_SEQ, &zone->flags); - } else + break; + default: return -ENXIO; - - if (blkz->cond == BLK_ZONE_COND_OFFLINE) - set_bit(DMZ_OFFLINE, &zone->flags); - else if (blkz->cond == BLK_ZONE_COND_READONLY) - set_bit(DMZ_READ_ONLY, &zone->flags); + } if (dmz_is_rnd(zone)) zone->wp_block = 0; else zone->wp_block = dmz_sect2blk(blkz->wp - blkz->start); - if (!dmz_is_offline(zone) && !dmz_is_readonly(zone)) { + if (blkz->cond == BLK_ZONE_COND_OFFLINE) + set_bit(DMZ_OFFLINE, &zone->flags); + else if (blkz->cond == BLK_ZONE_COND_READONLY) + set_bit(DMZ_READ_ONLY, &zone->flags); + else { zmd->nr_useable_zones++; if (dmz_is_rnd(zone)) { zmd->nr_rnd_zones++; @@ -1138,12 +1142,6 @@ static void dmz_drop_zones(struct dmz_metadata *zmd) zmd->zones = NULL; } -/* - * The size of a zone report in number of zones. - * This results in 4096*64B=256KB report zones commands. - */ -#define DMZ_REPORT_NR_ZONES 4096 - /* * Allocate and initialize zone descriptors using the zone * information from disk. @@ -1151,11 +1149,7 @@ static void dmz_drop_zones(struct dmz_metadata *zmd) static int dmz_init_zones(struct dmz_metadata *zmd) { struct dmz_dev *dev = zmd->dev; - struct dm_zone *zone; - struct blk_zone *blkz; - unsigned int nr_blkz; - sector_t sector = 0; - int i, ret = 0; + int ret; /* Init */ zmd->zone_bitmap_size = dev->zone_nr_blocks >> 3; @@ -1169,54 +1163,38 @@ static int dmz_init_zones(struct dmz_metadata *zmd) dmz_dev_info(dev, "Using %zu B for zone information", sizeof(struct dm_zone) * dev->nr_zones); - /* Get zone information */ - nr_blkz = DMZ_REPORT_NR_ZONES; - blkz = kcalloc(nr_blkz, sizeof(struct blk_zone), GFP_KERNEL); - if (!blkz) { - ret = -ENOMEM; - goto out; - } - /* - * Get zone information and initialize zone descriptors. - * At the same time, determine where the super block - * should be: first block of the first randomly writable - * zone. + * Get zone information and initialize zone descriptors. At the same + * time, determine where the super block should be: first block of the + * first randomly writable zone. */ - zone = zmd->zones; - while (sector < dev->capacity) { - /* Get zone information */ - nr_blkz = DMZ_REPORT_NR_ZONES; - ret = blkdev_report_zones(dev->bdev, sector, blkz, &nr_blkz); - if (ret) { - dmz_dev_err(dev, "Report zones failed %d", ret); - goto out; - } + ret = blkdev_report_zones(dev->bdev, 0, BLK_ALL_ZONES, dmz_init_zone, + zmd); + if (ret < 0) { + dmz_drop_zones(zmd); + return ret; + } - if (!nr_blkz) - break; + return 0; +} - /* Process report */ - for (i = 0; i < nr_blkz; i++) { - ret = dmz_init_zone(zmd, zone, &blkz[i]); - if (ret) - goto out; - sector += dev->zone_nr_sectors; - zone++; - } - } +static int dmz_update_zone_cb(struct blk_zone *blkz, unsigned int idx, + void *data) +{ + struct dm_zone *zone = data; - /* The entire zone configuration of the disk should now be known */ - if (sector < dev->capacity) { - dmz_dev_err(dev, "Failed to get correct zone information"); - ret = -ENXIO; - } -out: - kfree(blkz); - if (ret) - dmz_drop_zones(zmd); + clear_bit(DMZ_OFFLINE, &zone->flags); + clear_bit(DMZ_READ_ONLY, &zone->flags); + if (blkz->cond == BLK_ZONE_COND_OFFLINE) + set_bit(DMZ_OFFLINE, &zone->flags); + else if (blkz->cond == BLK_ZONE_COND_READONLY) + set_bit(DMZ_READ_ONLY, &zone->flags); - return ret; + if (dmz_is_seq(zone)) + zone->wp_block = dmz_sect2blk(blkz->wp - blkz->start); + else + zone->wp_block = 0; + return 0; } /* @@ -1224,9 +1202,7 @@ out: */ static int dmz_update_zone(struct dmz_metadata *zmd, struct dm_zone *zone) { - unsigned int nr_blkz = 1; unsigned int noio_flag; - struct blk_zone blkz; int ret; /* @@ -1236,29 +1212,18 @@ static int dmz_update_zone(struct dmz_metadata *zmd, struct dm_zone *zone) * GFP_NOIO was specified. */ noio_flag = memalloc_noio_save(); - ret = blkdev_report_zones(zmd->dev->bdev, dmz_start_sect(zmd, zone), - &blkz, &nr_blkz); + ret = blkdev_report_zones(zmd->dev->bdev, dmz_start_sect(zmd, zone), 1, + dmz_update_zone_cb, zone); memalloc_noio_restore(noio_flag); - if (!nr_blkz) + + if (ret == 0) ret = -EIO; - if (ret) { + if (ret < 0) { dmz_dev_err(zmd->dev, "Get zone %u report failed", dmz_id(zmd, zone)); return ret; } - clear_bit(DMZ_OFFLINE, &zone->flags); - clear_bit(DMZ_READ_ONLY, &zone->flags); - if (blkz.cond == BLK_ZONE_COND_OFFLINE) - set_bit(DMZ_OFFLINE, &zone->flags); - else if (blkz.cond == BLK_ZONE_COND_READONLY) - set_bit(DMZ_READ_ONLY, &zone->flags); - - if (dmz_is_seq(zone)) - zone->wp_block = dmz_sect2blk(blkz.wp - blkz.start); - else - zone->wp_block = 0; - return 0; } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 76f4cfdd6b41..e8f9661a10a1 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -440,14 +440,48 @@ static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo) return dm_get_geometry(md, geo); } +#ifdef CONFIG_BLK_DEV_ZONED +int dm_report_zones_cb(struct blk_zone *zone, unsigned int idx, void *data) +{ + struct dm_report_zones_args *args = data; + sector_t sector_diff = args->tgt->begin - args->start; + + /* + * Ignore zones beyond the target range. + */ + if (zone->start >= args->start + args->tgt->len) + return 0; + + /* + * Remap the start sector and write pointer position of the zone + * to match its position in the target range. + */ + zone->start += sector_diff; + if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) { + if (zone->cond == BLK_ZONE_COND_FULL) + zone->wp = zone->start + zone->len; + else if (zone->cond == BLK_ZONE_COND_EMPTY) + zone->wp = zone->start; + else + zone->wp += sector_diff; + } + + args->next_sector = zone->start + zone->len; + return args->orig_cb(zone, args->zone_idx++, args->orig_data); +} +EXPORT_SYMBOL_GPL(dm_report_zones_cb); + static int dm_blk_report_zones(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones) + unsigned int nr_zones, report_zones_cb cb, void *data) { -#ifdef CONFIG_BLK_DEV_ZONED struct mapped_device *md = disk->private_data; - struct dm_target *tgt; struct dm_table *map; int srcu_idx, ret; + struct dm_report_zones_args args = { + .next_sector = sector, + .orig_data = data, + .orig_cb = cb, + }; if (dm_suspended_md(md)) return -EAGAIN; @@ -456,32 +490,30 @@ static int dm_blk_report_zones(struct gendisk *disk, sector_t sector, if (!map) return -EIO; - tgt = dm_table_find_target(map, sector); - if (!tgt) { - ret = -EIO; - goto out; - } + do { + struct dm_target *tgt; - /* - * If we are executing this, we already know that the block device - * is a zoned device and so each target should have support for that - * type of drive. A missing report_zones method means that the target - * driver has a problem. - */ - if (WARN_ON(!tgt->type->report_zones)) { - ret = -EIO; - goto out; - } + tgt = dm_table_find_target(map, args.next_sector); + if (WARN_ON_ONCE(!tgt->type->report_zones)) { + ret = -EIO; + goto out; + } - ret = tgt->type->report_zones(tgt, sector, zones, nr_zones); + args.tgt = tgt; + ret = tgt->type->report_zones(tgt, &args, nr_zones); + if (ret < 0) + goto out; + } while (args.zone_idx < nr_zones && + args.next_sector < get_capacity(disk)); + ret = args.zone_idx; out: dm_put_live_table(md, srcu_idx); return ret; -#else - return -ENOTSUPP; -#endif } +#else +#define dm_blk_report_zones NULL +#endif /* CONFIG_BLK_DEV_ZONED */ static int dm_prepare_ioctl(struct mapped_device *md, int *srcu_idx, struct block_device **bdev) @@ -1207,51 +1239,6 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors) } EXPORT_SYMBOL_GPL(dm_accept_partial_bio); -/* - * The zone descriptors obtained with a zone report indicate - * zone positions within the underlying device of the target. The zone - * descriptors must be remapped to match their position within the dm device. - */ -void dm_remap_zone_report(struct dm_target *ti, sector_t start, - struct blk_zone *zones, unsigned int *nr_zones) -{ -#ifdef CONFIG_BLK_DEV_ZONED - struct blk_zone *zone; - unsigned int nrz = *nr_zones; - int i; - - /* - * Remap the start sector and write pointer position of the zones in - * the array. Since we may have obtained from the target underlying - * device more zones that the target size, also adjust the number - * of zones. - */ - for (i = 0; i < nrz; i++) { - zone = zones + i; - if (zone->start >= start + ti->len) { - memset(zone, 0, sizeof(struct blk_zone) * (nrz - i)); - break; - } - - zone->start = zone->start + ti->begin - start; - if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) - continue; - - if (zone->cond == BLK_ZONE_COND_FULL) - zone->wp = zone->start + zone->len; - else if (zone->cond == BLK_ZONE_COND_EMPTY) - zone->wp = zone->start; - else - zone->wp = zone->wp + ti->begin - start; - } - - *nr_zones = i; -#else /* !CONFIG_BLK_DEV_ZONED */ - *nr_zones = 0; -#endif -} -EXPORT_SYMBOL_GPL(dm_remap_zone_report); - static blk_qc_t __map_bio(struct dm_target_io *tio) { int r; diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h index bf2102a749bc..42fd3f00e4a5 100644 --- a/drivers/scsi/sd.h +++ b/drivers/scsi/sd.h @@ -213,8 +213,8 @@ blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd, unsigned char op, bool all); extern void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes, struct scsi_sense_hdr *sshdr); -extern int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones); +int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, + unsigned int nr_zones, report_zones_cb cb, void *data); #else /* CONFIG_BLK_DEV_ZONED */ diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index 663608d1003b..23281825ec38 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -19,34 +19,27 @@ #include "sd.h" -/** - * sd_zbc_parse_report - Convert a zone descriptor to a struct blk_zone, - * @sdkp: The disk the report originated from - * @buf: Address of the report zone descriptor - * @zone: the destination zone structure - * - * All LBA sized values are converted to 512B sectors unit. - */ -static void sd_zbc_parse_report(struct scsi_disk *sdkp, u8 *buf, - struct blk_zone *zone) +static int sd_zbc_parse_report(struct scsi_disk *sdkp, u8 *buf, + unsigned int idx, report_zones_cb cb, void *data) { struct scsi_device *sdp = sdkp->device; + struct blk_zone zone = { 0 }; - memset(zone, 0, sizeof(struct blk_zone)); - - zone->type = buf[0] & 0x0f; - zone->cond = (buf[1] >> 4) & 0xf; + zone.type = buf[0] & 0x0f; + zone.cond = (buf[1] >> 4) & 0xf; if (buf[1] & 0x01) - zone->reset = 1; + zone.reset = 1; if (buf[1] & 0x02) - zone->non_seq = 1; - - zone->len = logical_to_sectors(sdp, get_unaligned_be64(&buf[8])); - zone->start = logical_to_sectors(sdp, get_unaligned_be64(&buf[16])); - zone->wp = logical_to_sectors(sdp, get_unaligned_be64(&buf[24])); - if (zone->type != ZBC_ZONE_TYPE_CONV && - zone->cond == ZBC_ZONE_COND_FULL) - zone->wp = zone->start + zone->len; + zone.non_seq = 1; + + zone.len = logical_to_sectors(sdp, get_unaligned_be64(&buf[8])); + zone.start = logical_to_sectors(sdp, get_unaligned_be64(&buf[16])); + zone.wp = logical_to_sectors(sdp, get_unaligned_be64(&buf[24])); + if (zone.type != ZBC_ZONE_TYPE_CONV && + zone.cond == ZBC_ZONE_COND_FULL) + zone.wp = zone.start + zone.len; + + return cb(&zone, idx, data); } /** @@ -154,60 +147,61 @@ static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp, } /** - * sd_zbc_report_zones - Disk report zones operation. - * @disk: The target disk - * @sector: Start 512B sector of the report - * @zones: Array of zone descriptors - * @nr_zones: Number of descriptors in the array - * - * Execute a report zones command on the target disk. + * sd_zbc_zone_sectors - Get the device zone size in number of 512B sectors. + * @sdkp: The target disk */ +static inline sector_t sd_zbc_zone_sectors(struct scsi_disk *sdkp) +{ + return logical_to_sectors(sdkp->device, sdkp->zone_blocks); +} + int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones) + unsigned int nr_zones, report_zones_cb cb, void *data) { struct scsi_disk *sdkp = scsi_disk(disk); - unsigned int i, nrz = *nr_zones; + unsigned int nr, i; unsigned char *buf; - size_t buflen = 0, offset = 0; - int ret = 0; + size_t offset, buflen = 0; + int zone_idx = 0; + int ret; if (!sd_is_zoned(sdkp)) /* Not a zoned device */ return -EOPNOTSUPP; - buf = sd_zbc_alloc_report_buffer(sdkp, nrz, &buflen); + buf = sd_zbc_alloc_report_buffer(sdkp, nr_zones, &buflen); if (!buf) return -ENOMEM; - ret = sd_zbc_do_report_zones(sdkp, buf, buflen, - sectors_to_logical(sdkp->device, sector), true); - if (ret) - goto out; + while (zone_idx < nr_zones && sector < get_capacity(disk)) { + ret = sd_zbc_do_report_zones(sdkp, buf, buflen, + sectors_to_logical(sdkp->device, sector), true); + if (ret) + goto out; + + offset = 0; + nr = min(nr_zones, get_unaligned_be32(&buf[0]) / 64); + if (!nr) + break; + + for (i = 0; i < nr && zone_idx < nr_zones; i++) { + offset += 64; + ret = sd_zbc_parse_report(sdkp, buf + offset, zone_idx, + cb, data); + if (ret) + goto out; + zone_idx++; + } - nrz = min(nrz, get_unaligned_be32(&buf[0]) / 64); - for (i = 0; i < nrz; i++) { - offset += 64; - sd_zbc_parse_report(sdkp, buf + offset, zones); - zones++; + sector += sd_zbc_zone_sectors(sdkp) * i; } - *nr_zones = nrz; - + ret = zone_idx; out: kvfree(buf); - return ret; } -/** - * sd_zbc_zone_sectors - Get the device zone size in number of 512B sectors. - * @sdkp: The target disk - */ -static inline sector_t sd_zbc_zone_sectors(struct scsi_disk *sdkp) -{ - return logical_to_sectors(sdkp->device, sdkp->zone_blocks); -} - /** * sd_zbc_setup_zone_mgmt_cmnd - Prepare a zone ZBC_OUT command. The operations * can be RESET WRITE POINTER, OPEN, CLOSE or FINISH. diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 1443cee15863..95761740cf1f 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2857,15 +2857,21 @@ static int init_percpu_info(struct f2fs_sb_info *sbi) } #ifdef CONFIG_BLK_DEV_ZONED +static int f2fs_report_zone_cb(struct blk_zone *zone, unsigned int idx, + void *data) +{ + struct f2fs_dev_info *dev = data; + + if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) + set_bit(idx, dev->blkz_seq); + return 0; +} + static int init_blkz_info(struct f2fs_sb_info *sbi, int devi) { struct block_device *bdev = FDEV(devi).bdev; sector_t nr_sectors = bdev->bd_part->nr_sects; - sector_t sector = 0; - struct blk_zone *zones; - unsigned int i, nr_zones; - unsigned int n = 0; - int err = -EIO; + int ret; if (!f2fs_sb_has_blkzoned(sbi)) return 0; @@ -2890,38 +2896,13 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi) if (!FDEV(devi).blkz_seq) return -ENOMEM; -#define F2FS_REPORT_NR_ZONES 4096 - - zones = f2fs_kzalloc(sbi, - array_size(F2FS_REPORT_NR_ZONES, - sizeof(struct blk_zone)), - GFP_KERNEL); - if (!zones) - return -ENOMEM; - /* Get block zones type */ - while (zones && sector < nr_sectors) { - - nr_zones = F2FS_REPORT_NR_ZONES; - err = blkdev_report_zones(bdev, sector, zones, &nr_zones); - if (err) - break; - if (!nr_zones) { - err = -EIO; - break; - } - - for (i = 0; i < nr_zones; i++) { - if (zones[i].type != BLK_ZONE_TYPE_CONVENTIONAL) - set_bit(n, FDEV(devi).blkz_seq); - sector += zones[i].len; - n++; - } - } - - kvfree(zones); + ret = blkdev_report_zones(bdev, 0, BLK_ALL_ZONES, f2fs_report_zone_cb, + &FDEV(devi)); + if (ret < 0) + return ret; - return err; + return 0; } #endif diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6a4f7abbdcf7..397bb9bc230b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -349,17 +349,16 @@ struct queue_limits { enum blk_zoned_model zoned; }; +typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, + void *data); + #ifdef CONFIG_BLK_DEV_ZONED -/* - * Maximum number of zones to report with a single report zones command. - */ -#define BLK_ZONED_REPORT_MAX_ZONES 8192U +#define BLK_ALL_ZONES ((unsigned int)-1) +int blkdev_report_zones(struct block_device *bdev, sector_t sector, + unsigned int nr_zones, report_zones_cb cb, void *data); extern unsigned int blkdev_nr_zones(struct block_device *bdev); -extern int blkdev_report_zones(struct block_device *bdev, - sector_t sector, struct blk_zone *zones, - unsigned int *nr_zones); extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op, sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask); @@ -1709,7 +1708,7 @@ struct block_device_operations { /* this callback is with swap_lock and sometimes page table lock held */ void (*swap_slot_free_notify) (struct block_device *, unsigned long); int (*report_zones)(struct gendisk *, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones); + unsigned int nr_zones, report_zones_cb cb, void *data); struct module *owner; const struct pr_ops *pr_ops; }; diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 399ad8632356..a164cc81b710 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -17,6 +17,7 @@ struct dm_dev; struct dm_target; struct dm_table; +struct dm_report_zones_args; struct mapped_device; struct bio_vec; @@ -93,9 +94,9 @@ typedef int (*dm_message_fn) (struct dm_target *ti, unsigned argc, char **argv, typedef int (*dm_prepare_ioctl_fn) (struct dm_target *ti, struct block_device **bdev); -typedef int (*dm_report_zones_fn) (struct dm_target *ti, sector_t sector, - struct blk_zone *zones, - unsigned int *nr_zones); +typedef int (*dm_report_zones_fn) (struct dm_target *ti, + struct dm_report_zones_args *args, + unsigned int nr_zones); /* * These iteration functions are typically used to check (and combine) @@ -422,10 +423,23 @@ struct gendisk *dm_disk(struct mapped_device *md); int dm_suspended(struct dm_target *ti); int dm_noflush_suspending(struct dm_target *ti); void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors); -void dm_remap_zone_report(struct dm_target *ti, sector_t start, - struct blk_zone *zones, unsigned int *nr_zones); union map_info *dm_get_rq_mapinfo(struct request *rq); +#ifdef CONFIG_BLK_DEV_ZONED +struct dm_report_zones_args { + struct dm_target *tgt; + sector_t next_sector; + + void *orig_data; + report_zones_cb orig_cb; + unsigned int zone_idx; + + /* must be filled by ->report_zones before calling dm_report_zones_cb */ + sector_t start; +}; +int dm_report_zones_cb(struct blk_zone *zone, unsigned int idx, void *data); +#endif /* CONFIG_BLK_DEV_ZONED */ + /* * Device mapper functions to parse and create devices specified by the * parameter "dm-mod.create=" -- cgit v1.2.3-71-gd317 From c29f74e0df7a02b8303bcdce93a7c0132d62577a Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 12 Nov 2019 00:29:56 +0100 Subject: netfilter: nf_flow_table: hardware offload support This patch adds the dataplane hardware offload to the flowtable infrastructure. Three new flags represent the hardware state of this flow: * FLOW_OFFLOAD_HW: This flow entry resides in the hardware. * FLOW_OFFLOAD_HW_DYING: This flow entry has been scheduled to be remove from hardware. This might be triggered by either packet path (via TCP RST/FIN packet) or via aging. * FLOW_OFFLOAD_HW_DEAD: This flow entry has been already removed from the hardware, the software garbage collector can remove it from the software flowtable. This patch supports for: * IPv4 only. * Aging via FLOW_CLS_STATS, no packet and byte counter synchronization at this stage. This patch also adds the action callback that specifies how to convert the flow entry into the flow_rule object that is passed to the driver. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + include/net/netfilter/nf_flow_table.h | 33 +- net/ipv4/netfilter/nf_flow_table_ipv4.c | 1 + net/ipv6/netfilter/nf_flow_table_ipv6.c | 1 + net/netfilter/Makefile | 3 +- net/netfilter/nf_flow_table_core.c | 33 +- net/netfilter/nf_flow_table_inet.c | 1 + net/netfilter/nf_flow_table_offload.c | 758 ++++++++++++++++++++++++++++++++ 8 files changed, 822 insertions(+), 9 deletions(-) create mode 100644 net/netfilter/nf_flow_table_offload.c (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f857f01234f7..9e6fb8524d91 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -848,6 +848,7 @@ enum tc_setup_type { TC_SETUP_ROOT_QDISC, TC_SETUP_QDISC_GRED, TC_SETUP_QDISC_TAPRIO, + TC_SETUP_FT, }; /* These structures hold the attributes of bpf state that are being passed diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index ece09d36c7a6..eea66de328d3 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -12,6 +12,9 @@ #include struct nf_flowtable; +struct nf_flow_rule; +struct flow_offload; +enum flow_offload_tuple_dir; struct nf_flowtable_type { struct list_head list; @@ -20,6 +23,10 @@ struct nf_flowtable_type { int (*setup)(struct nf_flowtable *ft, struct net_device *dev, enum flow_block_command cmd); + int (*action)(struct net *net, + const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct nf_flow_rule *flow_rule); void (*free)(struct nf_flowtable *ft); nf_hookfn *hook; struct module *owner; @@ -80,6 +87,9 @@ struct flow_offload_tuple_rhash { #define FLOW_OFFLOAD_DNAT 0x2 #define FLOW_OFFLOAD_DYING 0x4 #define FLOW_OFFLOAD_TEARDOWN 0x8 +#define FLOW_OFFLOAD_HW 0x10 +#define FLOW_OFFLOAD_HW_DYING 0x20 +#define FLOW_OFFLOAD_HW_DEAD 0x40 enum flow_offload_type { NF_FLOW_OFFLOAD_UNSPEC = 0, @@ -142,11 +152,22 @@ unsigned int nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, #define MODULE_ALIAS_NF_FLOWTABLE(family) \ MODULE_ALIAS("nf-flowtable-" __stringify(family)) -static inline int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, - struct net_device *dev, - enum flow_block_command cmd) -{ - return 0; -} +void nf_flow_offload_add(struct nf_flowtable *flowtable, + struct flow_offload *flow); +void nf_flow_offload_del(struct nf_flowtable *flowtable, + struct flow_offload *flow); +void nf_flow_offload_stats(struct nf_flowtable *flowtable, + struct flow_offload *flow); + +void nf_flow_table_offload_flush(struct nf_flowtable *flowtable); +int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, + struct net_device *dev, + enum flow_block_command cmd); +int nf_flow_rule_route(struct net *net, const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct nf_flow_rule *flow_rule); + +int nf_flow_table_offload_init(void); +void nf_flow_table_offload_exit(void); #endif /* _NF_FLOW_TABLE_H */ diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c index f3befddb5fdd..168b72e18be0 100644 --- a/net/ipv4/netfilter/nf_flow_table_ipv4.c +++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c @@ -10,6 +10,7 @@ static struct nf_flowtable_type flowtable_ipv4 = { .family = NFPROTO_IPV4, .init = nf_flow_table_init, .setup = nf_flow_table_offload_setup, + .action = nf_flow_rule_route, .free = nf_flow_table_free, .hook = nf_flow_offload_ip_hook, .owner = THIS_MODULE, diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c index 1c47f05eabd6..f069bc0dc056 100644 --- a/net/ipv6/netfilter/nf_flow_table_ipv6.c +++ b/net/ipv6/netfilter/nf_flow_table_ipv6.c @@ -11,6 +11,7 @@ static struct nf_flowtable_type flowtable_ipv6 = { .family = NFPROTO_IPV6, .init = nf_flow_table_init, .setup = nf_flow_table_offload_setup, + .action = nf_flow_rule_route, .free = nf_flow_table_free, .hook = nf_flow_offload_ipv6_hook, .owner = THIS_MODULE, diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 4fc075b612fe..5e9b2eb24349 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -120,7 +120,8 @@ obj-$(CONFIG_NFT_FWD_NETDEV) += nft_fwd_netdev.o # flow table infrastructure obj-$(CONFIG_NF_FLOW_TABLE) += nf_flow_table.o -nf_flow_table-objs := nf_flow_table_core.o nf_flow_table_ip.o +nf_flow_table-objs := nf_flow_table_core.o nf_flow_table_ip.o \ + nf_flow_table_offload.o obj-$(CONFIG_NF_FLOW_TABLE_INET) += nf_flow_table_inet.o diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 139a5e074743..8468d2d02284 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -250,6 +250,9 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) return err; } + if (flow_table->flags & NF_FLOWTABLE_HW_OFFLOAD) + nf_flow_offload_add(flow_table, flow); + return 0; } EXPORT_SYMBOL_GPL(flow_offload_add); @@ -350,9 +353,20 @@ static void nf_flow_offload_gc_step(struct flow_offload *flow, void *data) { struct nf_flowtable *flow_table = data; + if (flow->flags & FLOW_OFFLOAD_HW) + nf_flow_offload_stats(flow_table, flow); + if (nf_flow_has_expired(flow) || nf_ct_is_dying(flow->ct) || - (flow->flags & (FLOW_OFFLOAD_DYING | FLOW_OFFLOAD_TEARDOWN))) - flow_offload_del(flow_table, flow); + (flow->flags & (FLOW_OFFLOAD_DYING | FLOW_OFFLOAD_TEARDOWN))) { + if (flow->flags & FLOW_OFFLOAD_HW) { + if (!(flow->flags & FLOW_OFFLOAD_HW_DYING)) + nf_flow_offload_del(flow_table, flow); + else if (flow->flags & FLOW_OFFLOAD_HW_DEAD) + flow_offload_del(flow_table, flow); + } else { + flow_offload_del(flow_table, flow); + } + } } static void nf_flow_offload_work_gc(struct work_struct *work) @@ -485,6 +499,7 @@ int nf_flow_table_init(struct nf_flowtable *flowtable) int err; INIT_DEFERRABLE_WORK(&flowtable->gc_work, nf_flow_offload_work_gc); + flow_block_init(&flowtable->flow_block); err = rhashtable_init(&flowtable->rhashtable, &nf_flow_offload_rhash_params); @@ -520,6 +535,7 @@ static void nf_flow_table_do_cleanup(struct flow_offload *flow, void *data) static void nf_flow_table_iterate_cleanup(struct nf_flowtable *flowtable, struct net_device *dev) { + nf_flow_table_offload_flush(flowtable); nf_flow_table_iterate(flowtable, nf_flow_table_do_cleanup, dev); flush_delayed_work(&flowtable->gc_work); } @@ -547,5 +563,18 @@ void nf_flow_table_free(struct nf_flowtable *flow_table) } EXPORT_SYMBOL_GPL(nf_flow_table_free); +static int __init nf_flow_table_module_init(void) +{ + return nf_flow_table_offload_init(); +} + +static void __exit nf_flow_table_module_exit(void) +{ + nf_flow_table_offload_exit(); +} + +module_init(nf_flow_table_module_init); +module_exit(nf_flow_table_module_exit); + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso "); diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c index 1e70fd504da3..bfb910b874ce 100644 --- a/net/netfilter/nf_flow_table_inet.c +++ b/net/netfilter/nf_flow_table_inet.c @@ -25,6 +25,7 @@ static struct nf_flowtable_type flowtable_inet = { .family = NFPROTO_INET, .init = nf_flow_table_init, .setup = nf_flow_table_offload_setup, + .action = nf_flow_rule_route, .free = nf_flow_table_free, .hook = nf_flow_offload_inet_hook, .owner = THIS_MODULE, diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c new file mode 100644 index 000000000000..9be61f47303a --- /dev/null +++ b/net/netfilter/nf_flow_table_offload.c @@ -0,0 +1,758 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static struct work_struct nf_flow_offload_work; +static DEFINE_SPINLOCK(flow_offload_pending_list_lock); +static LIST_HEAD(flow_offload_pending_list); + +struct flow_offload_work { + struct list_head list; + enum flow_cls_command cmd; + int priority; + struct nf_flowtable *flowtable; + struct flow_offload *flow; +}; + +struct nf_flow_key { + struct flow_dissector_key_control control; + struct flow_dissector_key_basic basic; + union { + struct flow_dissector_key_ipv4_addrs ipv4; + }; + struct flow_dissector_key_tcp tcp; + struct flow_dissector_key_ports tp; +} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ + +struct nf_flow_match { + struct flow_dissector dissector; + struct nf_flow_key key; + struct nf_flow_key mask; +}; + +struct nf_flow_rule { + struct nf_flow_match match; + struct flow_rule *rule; +}; + +#define NF_FLOW_DISSECTOR(__match, __type, __field) \ + (__match)->dissector.offset[__type] = \ + offsetof(struct nf_flow_key, __field) + +static int nf_flow_rule_match(struct nf_flow_match *match, + const struct flow_offload_tuple *tuple) +{ + struct nf_flow_key *mask = &match->mask; + struct nf_flow_key *key = &match->key; + + NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_CONTROL, control); + NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_BASIC, basic); + NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4); + NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_TCP, tcp); + NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_PORTS, tp); + + switch (tuple->l3proto) { + case AF_INET: + key->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + key->basic.n_proto = htons(ETH_P_IP); + key->ipv4.src = tuple->src_v4.s_addr; + mask->ipv4.src = 0xffffffff; + key->ipv4.dst = tuple->dst_v4.s_addr; + mask->ipv4.dst = 0xffffffff; + break; + default: + return -EOPNOTSUPP; + } + mask->basic.n_proto = 0xffff; + + switch (tuple->l4proto) { + case IPPROTO_TCP: + key->tcp.flags = 0; + mask->tcp.flags = TCP_FLAG_RST | TCP_FLAG_FIN; + match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_TCP); + break; + case IPPROTO_UDP: + break; + default: + return -EOPNOTSUPP; + } + + key->basic.ip_proto = tuple->l4proto; + mask->basic.ip_proto = 0xff; + + key->tp.src = tuple->src_port; + mask->tp.src = 0xffff; + key->tp.dst = tuple->dst_port; + mask->tp.dst = 0xffff; + + match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL) | + BIT(FLOW_DISSECTOR_KEY_BASIC) | + BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_PORTS); + return 0; +} + +static void flow_offload_mangle(struct flow_action_entry *entry, + enum flow_action_mangle_base htype, + u32 offset, u8 *value, u8 *mask) +{ + entry->id = FLOW_ACTION_MANGLE; + entry->mangle.htype = htype; + entry->mangle.offset = offset; + memcpy(&entry->mangle.mask, mask, sizeof(u32)); + memcpy(&entry->mangle.val, value, sizeof(u32)); +} + +static int flow_offload_eth_src(struct net *net, + const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct flow_action_entry *entry0, + struct flow_action_entry *entry1) +{ + const struct flow_offload_tuple *tuple = &flow->tuplehash[!dir].tuple; + struct net_device *dev; + u32 mask, val; + u16 val16; + + dev = dev_get_by_index(net, tuple->iifidx); + if (!dev) + return -ENOENT; + + mask = ~0xffff0000; + memcpy(&val16, dev->dev_addr, 2); + val = val16 << 16; + flow_offload_mangle(entry0, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 4, + (u8 *)&val, (u8 *)&mask); + + mask = ~0xffffffff; + memcpy(&val, dev->dev_addr + 2, 4); + flow_offload_mangle(entry1, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 8, + (u8 *)&val, (u8 *)&mask); + dev_put(dev); + + return 0; +} + +static int flow_offload_eth_dst(struct net *net, + const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct flow_action_entry *entry0, + struct flow_action_entry *entry1) +{ + const struct flow_offload_tuple *tuple = &flow->tuplehash[dir].tuple; + struct neighbour *n; + u32 mask, val; + u16 val16; + + n = dst_neigh_lookup(tuple->dst_cache, &tuple->dst_v4); + if (!n) + return -ENOENT; + + mask = ~0xffffffff; + memcpy(&val, n->ha, 4); + flow_offload_mangle(entry0, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 0, + (u8 *)&val, (u8 *)&mask); + + mask = ~0x0000ffff; + memcpy(&val16, n->ha + 4, 2); + val = val16; + flow_offload_mangle(entry1, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 4, + (u8 *)&val, (u8 *)&mask); + neigh_release(n); + + return 0; +} + +static void flow_offload_ipv4_snat(struct net *net, + const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct flow_action_entry *entry) +{ + u32 mask = ~htonl(0xffffffff); + __be32 addr; + u32 offset; + + switch (dir) { + case FLOW_OFFLOAD_DIR_ORIGINAL: + addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4.s_addr; + offset = offsetof(struct iphdr, saddr); + break; + case FLOW_OFFLOAD_DIR_REPLY: + addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4.s_addr; + offset = offsetof(struct iphdr, daddr); + break; + default: + return; + } + + flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP4, offset, + (u8 *)&addr, (u8 *)&mask); +} + +static void flow_offload_ipv4_dnat(struct net *net, + const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct flow_action_entry *entry) +{ + u32 mask = ~htonl(0xffffffff); + __be32 addr; + u32 offset; + + switch (dir) { + case FLOW_OFFLOAD_DIR_ORIGINAL: + addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4.s_addr; + offset = offsetof(struct iphdr, daddr); + break; + case FLOW_OFFLOAD_DIR_REPLY: + addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4.s_addr; + offset = offsetof(struct iphdr, saddr); + break; + default: + return; + } + + flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP4, offset, + (u8 *)&addr, (u8 *)&mask); +} + +static int flow_offload_l4proto(const struct flow_offload *flow) +{ + u8 protonum = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l4proto; + u8 type = 0; + + switch (protonum) { + case IPPROTO_TCP: + type = FLOW_ACT_MANGLE_HDR_TYPE_TCP; + break; + case IPPROTO_UDP: + type = FLOW_ACT_MANGLE_HDR_TYPE_UDP; + break; + default: + break; + } + + return type; +} + +static void flow_offload_port_snat(struct net *net, + const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct flow_action_entry *entry) +{ + u32 mask = ~htonl(0xffff0000); + __be16 port; + u32 offset; + + switch (dir) { + case FLOW_OFFLOAD_DIR_ORIGINAL: + port = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port; + offset = 0; /* offsetof(struct tcphdr, source); */ + break; + case FLOW_OFFLOAD_DIR_REPLY: + port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port; + offset = 0; /* offsetof(struct tcphdr, dest); */ + break; + default: + break; + } + + flow_offload_mangle(entry, flow_offload_l4proto(flow), offset, + (u8 *)&port, (u8 *)&mask); +} + +static void flow_offload_port_dnat(struct net *net, + const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct flow_action_entry *entry) +{ + u32 mask = ~htonl(0xffff); + __be16 port; + u32 offset; + + switch (dir) { + case FLOW_OFFLOAD_DIR_ORIGINAL: + port = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port; + offset = 0; /* offsetof(struct tcphdr, source); */ + break; + case FLOW_OFFLOAD_DIR_REPLY: + port = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port; + offset = 0; /* offsetof(struct tcphdr, dest); */ + break; + default: + break; + } + + flow_offload_mangle(entry, flow_offload_l4proto(flow), offset, + (u8 *)&port, (u8 *)&mask); +} + +static void flow_offload_ipv4_checksum(struct net *net, + const struct flow_offload *flow, + struct flow_action_entry *entry) +{ + u8 protonum = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l4proto; + + entry->id = FLOW_ACTION_CSUM; + entry->csum_flags = TCA_CSUM_UPDATE_FLAG_IPV4HDR; + + switch (protonum) { + case IPPROTO_TCP: + entry->csum_flags |= TCA_CSUM_UPDATE_FLAG_TCP; + break; + case IPPROTO_UDP: + entry->csum_flags |= TCA_CSUM_UPDATE_FLAG_UDP; + break; + } +} + +static void flow_offload_redirect(const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct flow_action_entry *entry) +{ + struct rtable *rt; + + rt = (struct rtable *)flow->tuplehash[dir].tuple.dst_cache; + entry->id = FLOW_ACTION_REDIRECT; + entry->dev = rt->dst.dev; + dev_hold(rt->dst.dev); +} + +int nf_flow_rule_route(struct net *net, const struct flow_offload *flow, + enum flow_offload_tuple_dir dir, + struct nf_flow_rule *flow_rule) +{ + int i; + + if (flow_offload_eth_src(net, flow, dir, + &flow_rule->rule->action.entries[0], + &flow_rule->rule->action.entries[1]) < 0) + return -1; + + if (flow_offload_eth_dst(net, flow, dir, + &flow_rule->rule->action.entries[2], + &flow_rule->rule->action.entries[3]) < 0) + return -1; + + i = 4; + if (flow->flags & FLOW_OFFLOAD_SNAT) { + flow_offload_ipv4_snat(net, flow, dir, + &flow_rule->rule->action.entries[i++]); + flow_offload_port_snat(net, flow, dir, + &flow_rule->rule->action.entries[i++]); + } + if (flow->flags & FLOW_OFFLOAD_DNAT) { + flow_offload_ipv4_dnat(net, flow, dir, + &flow_rule->rule->action.entries[i++]); + flow_offload_port_dnat(net, flow, dir, + &flow_rule->rule->action.entries[i++]); + } + if (flow->flags & FLOW_OFFLOAD_SNAT || + flow->flags & FLOW_OFFLOAD_DNAT) + flow_offload_ipv4_checksum(net, flow, + &flow_rule->rule->action.entries[i++]); + + flow_offload_redirect(flow, dir, &flow_rule->rule->action.entries[i++]); + + return i; +} +EXPORT_SYMBOL_GPL(nf_flow_rule_route); + +static struct nf_flow_rule * +nf_flow_offload_rule_alloc(struct net *net, + const struct flow_offload_work *offload, + enum flow_offload_tuple_dir dir) +{ + const struct nf_flowtable *flowtable = offload->flowtable; + const struct flow_offload *flow = offload->flow; + const struct flow_offload_tuple *tuple; + struct nf_flow_rule *flow_rule; + int err = -ENOMEM, num_actions; + + flow_rule = kzalloc(sizeof(*flow_rule), GFP_KERNEL); + if (!flow_rule) + goto err_flow; + + flow_rule->rule = flow_rule_alloc(10); + if (!flow_rule->rule) + goto err_flow_rule; + + flow_rule->rule->match.dissector = &flow_rule->match.dissector; + flow_rule->rule->match.mask = &flow_rule->match.mask; + flow_rule->rule->match.key = &flow_rule->match.key; + + tuple = &flow->tuplehash[dir].tuple; + err = nf_flow_rule_match(&flow_rule->match, tuple); + if (err < 0) + goto err_flow_match; + + num_actions = flowtable->type->action(net, flow, dir, flow_rule); + if (num_actions < 0) + goto err_flow_match; + + flow_rule->rule->action.num_entries = num_actions; + + return flow_rule; + +err_flow_match: + kfree(flow_rule->rule); +err_flow_rule: + kfree(flow_rule); +err_flow: + return NULL; +} + +static void __nf_flow_offload_destroy(struct nf_flow_rule *flow_rule) +{ + struct flow_action_entry *entry; + int i; + + for (i = 0; i < flow_rule->rule->action.num_entries; i++) { + entry = &flow_rule->rule->action.entries[i]; + if (entry->id != FLOW_ACTION_REDIRECT) + continue; + + dev_put(entry->dev); + } + kfree(flow_rule->rule); + kfree(flow_rule); +} + +static void nf_flow_offload_destroy(struct nf_flow_rule *flow_rule[]) +{ + int i; + + for (i = 0; i < FLOW_OFFLOAD_DIR_MAX; i++) + __nf_flow_offload_destroy(flow_rule[i]); +} + +static int nf_flow_offload_alloc(const struct flow_offload_work *offload, + struct nf_flow_rule *flow_rule[]) +{ + struct net *net = read_pnet(&offload->flowtable->net); + + flow_rule[0] = nf_flow_offload_rule_alloc(net, offload, + FLOW_OFFLOAD_DIR_ORIGINAL); + if (!flow_rule[0]) + return -ENOMEM; + + flow_rule[1] = nf_flow_offload_rule_alloc(net, offload, + FLOW_OFFLOAD_DIR_REPLY); + if (!flow_rule[1]) { + __nf_flow_offload_destroy(flow_rule[0]); + return -ENOMEM; + } + + return 0; +} + +static void nf_flow_offload_init(struct flow_cls_offload *cls_flow, + __be16 proto, int priority, + enum flow_cls_command cmd, + const struct flow_offload_tuple *tuple, + struct netlink_ext_ack *extack) +{ + cls_flow->common.protocol = proto; + cls_flow->common.prio = priority; + cls_flow->common.extack = extack; + cls_flow->command = cmd; + cls_flow->cookie = (unsigned long)tuple; +} + +static int flow_offload_tuple_add(struct flow_offload_work *offload, + struct nf_flow_rule *flow_rule, + enum flow_offload_tuple_dir dir) +{ + struct nf_flowtable *flowtable = offload->flowtable; + struct flow_cls_offload cls_flow = {}; + struct flow_block_cb *block_cb; + struct netlink_ext_ack extack; + __be16 proto = ETH_P_ALL; + int err, i = 0; + + nf_flow_offload_init(&cls_flow, proto, offload->priority, + FLOW_CLS_REPLACE, + &offload->flow->tuplehash[dir].tuple, &extack); + cls_flow.rule = flow_rule->rule; + + list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list) { + err = block_cb->cb(TC_SETUP_FT, &cls_flow, + block_cb->cb_priv); + if (err < 0) + continue; + + i++; + } + + return i; +} + +static void flow_offload_tuple_del(struct flow_offload_work *offload, + enum flow_offload_tuple_dir dir) +{ + struct nf_flowtable *flowtable = offload->flowtable; + struct flow_cls_offload cls_flow = {}; + struct flow_block_cb *block_cb; + struct netlink_ext_ack extack; + __be16 proto = ETH_P_ALL; + + nf_flow_offload_init(&cls_flow, proto, offload->priority, + FLOW_CLS_DESTROY, + &offload->flow->tuplehash[dir].tuple, &extack); + + list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list) + block_cb->cb(TC_SETUP_FT, &cls_flow, block_cb->cb_priv); + + offload->flow->flags |= FLOW_OFFLOAD_HW_DEAD; +} + +static int flow_offload_rule_add(struct flow_offload_work *offload, + struct nf_flow_rule *flow_rule[]) +{ + int ok_count = 0; + + ok_count += flow_offload_tuple_add(offload, flow_rule[0], + FLOW_OFFLOAD_DIR_ORIGINAL); + ok_count += flow_offload_tuple_add(offload, flow_rule[1], + FLOW_OFFLOAD_DIR_REPLY); + if (ok_count == 0) + return -ENOENT; + + return 0; +} + +static int flow_offload_work_add(struct flow_offload_work *offload) +{ + struct nf_flow_rule *flow_rule[FLOW_OFFLOAD_DIR_MAX]; + int err; + + err = nf_flow_offload_alloc(offload, flow_rule); + if (err < 0) + return -ENOMEM; + + err = flow_offload_rule_add(offload, flow_rule); + + nf_flow_offload_destroy(flow_rule); + + return err; +} + +static void flow_offload_work_del(struct flow_offload_work *offload) +{ + flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_ORIGINAL); + flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_REPLY); +} + +static void flow_offload_tuple_stats(struct flow_offload_work *offload, + enum flow_offload_tuple_dir dir, + struct flow_stats *stats) +{ + struct nf_flowtable *flowtable = offload->flowtable; + struct flow_cls_offload cls_flow = {}; + struct flow_block_cb *block_cb; + struct netlink_ext_ack extack; + __be16 proto = ETH_P_ALL; + + nf_flow_offload_init(&cls_flow, proto, offload->priority, + FLOW_CLS_STATS, + &offload->flow->tuplehash[dir].tuple, &extack); + + list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list) + block_cb->cb(TC_SETUP_FT, &cls_flow, block_cb->cb_priv); + memcpy(stats, &cls_flow.stats, sizeof(*stats)); +} + +static void flow_offload_work_stats(struct flow_offload_work *offload) +{ + struct flow_stats stats[FLOW_OFFLOAD_DIR_MAX] = {}; + u64 lastused; + + flow_offload_tuple_stats(offload, FLOW_OFFLOAD_DIR_ORIGINAL, &stats[0]); + flow_offload_tuple_stats(offload, FLOW_OFFLOAD_DIR_REPLY, &stats[1]); + + lastused = max_t(u64, stats[0].lastused, stats[1].lastused); + offload->flow->timeout = max_t(u64, offload->flow->timeout, + lastused + NF_FLOW_TIMEOUT); +} + +static void flow_offload_work_handler(struct work_struct *work) +{ + struct flow_offload_work *offload, *next; + LIST_HEAD(offload_pending_list); + int ret; + + spin_lock_bh(&flow_offload_pending_list_lock); + list_replace_init(&flow_offload_pending_list, &offload_pending_list); + spin_unlock_bh(&flow_offload_pending_list_lock); + + list_for_each_entry_safe(offload, next, &offload_pending_list, list) { + switch (offload->cmd) { + case FLOW_CLS_REPLACE: + ret = flow_offload_work_add(offload); + if (ret < 0) + offload->flow->flags &= ~FLOW_OFFLOAD_HW; + break; + case FLOW_CLS_DESTROY: + flow_offload_work_del(offload); + break; + case FLOW_CLS_STATS: + flow_offload_work_stats(offload); + break; + default: + WARN_ON_ONCE(1); + } + list_del(&offload->list); + kfree(offload); + } +} + +static void flow_offload_queue_work(struct flow_offload_work *offload) +{ + spin_lock_bh(&flow_offload_pending_list_lock); + list_add_tail(&offload->list, &flow_offload_pending_list); + spin_unlock_bh(&flow_offload_pending_list_lock); + + schedule_work(&nf_flow_offload_work); +} + +void nf_flow_offload_add(struct nf_flowtable *flowtable, + struct flow_offload *flow) +{ + struct flow_offload_work *offload; + + offload = kmalloc(sizeof(struct flow_offload_work), GFP_ATOMIC); + if (!offload) + return; + + offload->cmd = FLOW_CLS_REPLACE; + offload->flow = flow; + offload->priority = flowtable->priority; + offload->flowtable = flowtable; + flow->flags |= FLOW_OFFLOAD_HW; + + flow_offload_queue_work(offload); +} + +void nf_flow_offload_del(struct nf_flowtable *flowtable, + struct flow_offload *flow) +{ + struct flow_offload_work *offload; + + offload = kzalloc(sizeof(struct flow_offload_work), GFP_ATOMIC); + if (!offload) + return; + + offload->cmd = FLOW_CLS_DESTROY; + offload->flow = flow; + offload->flow->flags |= FLOW_OFFLOAD_HW_DYING; + offload->flowtable = flowtable; + + flow_offload_queue_work(offload); +} + +void nf_flow_offload_stats(struct nf_flowtable *flowtable, + struct flow_offload *flow) +{ + struct flow_offload_work *offload; + s64 delta; + + delta = flow->timeout - jiffies; + if ((delta >= (9 * NF_FLOW_TIMEOUT) / 10) || + flow->flags & FLOW_OFFLOAD_HW_DYING) + return; + + offload = kzalloc(sizeof(struct flow_offload_work), GFP_ATOMIC); + if (!offload) + return; + + offload->cmd = FLOW_CLS_STATS; + offload->flow = flow; + offload->flowtable = flowtable; + + flow_offload_queue_work(offload); +} + +void nf_flow_table_offload_flush(struct nf_flowtable *flowtable) +{ + if (flowtable->flags & NF_FLOWTABLE_HW_OFFLOAD) + flush_work(&nf_flow_offload_work); +} + +static int nf_flow_table_block_setup(struct nf_flowtable *flowtable, + struct flow_block_offload *bo, + enum flow_block_command cmd) +{ + struct flow_block_cb *block_cb, *next; + int err = 0; + + switch (cmd) { + case FLOW_BLOCK_BIND: + list_splice(&bo->cb_list, &flowtable->flow_block.cb_list); + break; + case FLOW_BLOCK_UNBIND: + list_for_each_entry_safe(block_cb, next, &bo->cb_list, list) { + list_del(&block_cb->list); + flow_block_cb_free(block_cb); + } + break; + default: + WARN_ON_ONCE(1); + err = -EOPNOTSUPP; + } + + return err; +} + +int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, + struct net_device *dev, + enum flow_block_command cmd) +{ + struct netlink_ext_ack extack = {}; + struct flow_block_offload bo = {}; + int err; + + if (!(flowtable->flags & NF_FLOWTABLE_HW_OFFLOAD)) + return 0; + + bo.net = dev_net(dev); + bo.block = &flowtable->flow_block; + bo.command = cmd; + bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; + bo.extack = &extack; + INIT_LIST_HEAD(&bo.cb_list); + + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); + if (err < 0) + return err; + + return nf_flow_table_block_setup(flowtable, &bo, cmd); +} +EXPORT_SYMBOL_GPL(nf_flow_table_offload_setup); + +int nf_flow_table_offload_init(void) +{ + INIT_WORK(&nf_flow_offload_work, flow_offload_work_handler); + + return 0; +} + +void nf_flow_table_offload_exit(void) +{ + struct flow_offload_work *offload, *next; + LIST_HEAD(offload_pending_list); + + cancel_work_sync(&nf_flow_offload_work); + + list_for_each_entry_safe(offload, next, &offload_pending_list, list) { + list_del(&offload->list); + kfree(offload); + } +} -- cgit v1.2.3-71-gd317 From a4faf00d994c40e64f656805ac375c65e324eefb Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 25 Oct 2019 17:08:33 +0300 Subject: perf/aux: Allow using AUX data in perf samples AUX data can be used to annotate perf events such as performance counters or tracepoints/breakpoints by including it in sample records when PERF_SAMPLE_AUX flag is set. Such samples would be instrumental in debugging and profiling by providing, for example, a history of instruction flow leading up to the event's overflow. The implementation makes use of grouping an AUX event with all the events that wish to take samples of the AUX data, such that the former is the group leader. The samplees should also specify the desired size of the AUX sample via attr.aux_sample_size. AUX capable PMUs need to explicitly add support for sampling, because it relies on a new callback to take a snapshot of the buffer without touching the event states. Signed-off-by: Alexander Shishkin Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: David Ahern Cc: Jiri Olsa Cc: Linus Torvalds Cc: Mark Rutland Cc: Namhyung Kim Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: adrian.hunter@intel.com Cc: mathieu.poirier@linaro.org Link: https://lkml.kernel.org/r/20191025140835.53665-2-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 19 +++++ include/uapi/linux/perf_event.h | 10 ++- kernel/events/core.c | 173 +++++++++++++++++++++++++++++++++++++++- kernel/events/internal.h | 1 + kernel/events/ring_buffer.c | 36 +++++++++ 5 files changed, 234 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 011dcbdbccc2..34c7c6910026 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -249,6 +249,8 @@ struct perf_event; #define PERF_PMU_CAP_NO_EXCLUDE 0x80 #define PERF_PMU_CAP_AUX_OUTPUT 0x100 +struct perf_output_handle; + /** * struct pmu - generic performance monitoring unit */ @@ -432,6 +434,19 @@ struct pmu { */ void (*free_aux) (void *aux); /* optional */ + /* + * Take a snapshot of the AUX buffer without touching the event + * state, so that preempting ->start()/->stop() callbacks does + * not interfere with their logic. Called in PMI context. + * + * Returns the size of AUX data copied to the output handle. + * + * Optional. + */ + long (*snapshot_aux) (struct perf_event *event, + struct perf_output_handle *handle, + unsigned long size); + /* * Validate address range filters: make sure the HW supports the * requested configuration and number of filters; return 0 if the @@ -973,6 +988,7 @@ struct perf_sample_data { u32 reserved; } cpu_entry; struct perf_callchain_entry *callchain; + u64 aux_size; /* * regs_user may point to task_pt_regs or to regs_user_copy, depending @@ -1362,6 +1378,9 @@ extern unsigned int perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len); extern unsigned int perf_output_skip(struct perf_output_handle *handle, unsigned int len); +extern long perf_output_copy_aux(struct perf_output_handle *aux_handle, + struct perf_output_handle *handle, + unsigned long from, unsigned long to); extern int perf_swevent_get_recursion_context(void); extern void perf_swevent_put_recursion_context(int rctx); extern u64 perf_swevent_set_period(struct perf_event *event); diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index bb7b271397a6..377d794d3105 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -141,8 +141,9 @@ enum perf_event_sample_format { PERF_SAMPLE_TRANSACTION = 1U << 17, PERF_SAMPLE_REGS_INTR = 1U << 18, PERF_SAMPLE_PHYS_ADDR = 1U << 19, + PERF_SAMPLE_AUX = 1U << 20, - PERF_SAMPLE_MAX = 1U << 20, /* non-ABI */ + PERF_SAMPLE_MAX = 1U << 21, /* non-ABI */ __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, /* non-ABI; internal use */ }; @@ -300,6 +301,7 @@ enum perf_event_read_format { /* add: sample_stack_user */ #define PERF_ATTR_SIZE_VER4 104 /* add: sample_regs_intr */ #define PERF_ATTR_SIZE_VER5 112 /* add: aux_watermark */ +#define PERF_ATTR_SIZE_VER6 120 /* add: aux_sample_size */ /* * Hardware event_id to monitor via a performance monitoring event: @@ -424,7 +426,9 @@ struct perf_event_attr { */ __u32 aux_watermark; __u16 sample_max_stack; - __u16 __reserved_2; /* align to __u64 */ + __u16 __reserved_2; + __u32 aux_sample_size; + __u32 __reserved_3; }; /* @@ -864,6 +868,8 @@ enum perf_event_type { * { u64 abi; # enum perf_sample_regs_abi * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR * { u64 phys_addr;} && PERF_SAMPLE_PHYS_ADDR + * { u64 size; + * char data[size]; } && PERF_SAMPLE_AUX * }; */ PERF_RECORD_SAMPLE = 9, diff --git a/kernel/events/core.c b/kernel/events/core.c index 8d65e03b98f2..16d80ad8d6d7 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1941,6 +1941,11 @@ static void perf_put_aux_event(struct perf_event *event) } } +static bool perf_need_aux_event(struct perf_event *event) +{ + return !!event->attr.aux_output || !!event->attr.aux_sample_size; +} + static int perf_get_aux_event(struct perf_event *event, struct perf_event *group_leader) { @@ -1953,7 +1958,17 @@ static int perf_get_aux_event(struct perf_event *event, if (!group_leader) return 0; - if (!perf_aux_output_match(event, group_leader)) + /* + * aux_output and aux_sample_size are mutually exclusive. + */ + if (event->attr.aux_output && event->attr.aux_sample_size) + return 0; + + if (event->attr.aux_output && + !perf_aux_output_match(event, group_leader)) + return 0; + + if (event->attr.aux_sample_size && !group_leader->pmu->snapshot_aux) return 0; if (!atomic_long_inc_not_zero(&group_leader->refcount)) @@ -6222,6 +6237,122 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size, } } +static unsigned long perf_prepare_sample_aux(struct perf_event *event, + struct perf_sample_data *data, + size_t size) +{ + struct perf_event *sampler = event->aux_event; + struct ring_buffer *rb; + + data->aux_size = 0; + + if (!sampler) + goto out; + + if (WARN_ON_ONCE(READ_ONCE(sampler->state) != PERF_EVENT_STATE_ACTIVE)) + goto out; + + if (WARN_ON_ONCE(READ_ONCE(sampler->oncpu) != smp_processor_id())) + goto out; + + rb = ring_buffer_get(sampler->parent ? sampler->parent : sampler); + if (!rb) + goto out; + + /* + * If this is an NMI hit inside sampling code, don't take + * the sample. See also perf_aux_sample_output(). + */ + if (READ_ONCE(rb->aux_in_sampling)) { + data->aux_size = 0; + } else { + size = min_t(size_t, size, perf_aux_size(rb)); + data->aux_size = ALIGN(size, sizeof(u64)); + } + ring_buffer_put(rb); + +out: + return data->aux_size; +} + +long perf_pmu_snapshot_aux(struct ring_buffer *rb, + struct perf_event *event, + struct perf_output_handle *handle, + unsigned long size) +{ + unsigned long flags; + long ret; + + /* + * Normal ->start()/->stop() callbacks run in IRQ mode in scheduler + * paths. If we start calling them in NMI context, they may race with + * the IRQ ones, that is, for example, re-starting an event that's just + * been stopped, which is why we're using a separate callback that + * doesn't change the event state. + * + * IRQs need to be disabled to prevent IPIs from racing with us. + */ + local_irq_save(flags); + /* + * Guard against NMI hits inside the critical section; + * see also perf_prepare_sample_aux(). + */ + WRITE_ONCE(rb->aux_in_sampling, 1); + barrier(); + + ret = event->pmu->snapshot_aux(event, handle, size); + + barrier(); + WRITE_ONCE(rb->aux_in_sampling, 0); + local_irq_restore(flags); + + return ret; +} + +static void perf_aux_sample_output(struct perf_event *event, + struct perf_output_handle *handle, + struct perf_sample_data *data) +{ + struct perf_event *sampler = event->aux_event; + unsigned long pad; + struct ring_buffer *rb; + long size; + + if (WARN_ON_ONCE(!sampler || !data->aux_size)) + return; + + rb = ring_buffer_get(sampler->parent ? sampler->parent : sampler); + if (!rb) + return; + + size = perf_pmu_snapshot_aux(rb, sampler, handle, data->aux_size); + + /* + * An error here means that perf_output_copy() failed (returned a + * non-zero surplus that it didn't copy), which in its current + * enlightened implementation is not possible. If that changes, we'd + * like to know. + */ + if (WARN_ON_ONCE(size < 0)) + goto out_put; + + /* + * The pad comes from ALIGN()ing data->aux_size up to u64 in + * perf_prepare_sample_aux(), so should not be more than that. + */ + pad = data->aux_size - size; + if (WARN_ON_ONCE(pad >= sizeof(u64))) + pad = 8; + + if (pad) { + u64 zero = 0; + perf_output_copy(handle, &zero, pad); + } + +out_put: + ring_buffer_put(rb); +} + static void __perf_event_header__init_id(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event) @@ -6541,6 +6672,13 @@ void perf_output_sample(struct perf_output_handle *handle, if (sample_type & PERF_SAMPLE_PHYS_ADDR) perf_output_put(handle, data->phys_addr); + if (sample_type & PERF_SAMPLE_AUX) { + perf_output_put(handle, data->aux_size); + + if (data->aux_size) + perf_aux_sample_output(event, handle, data); + } + if (!event->attr.watermark) { int wakeup_events = event->attr.wakeup_events; @@ -6729,6 +6867,35 @@ void perf_prepare_sample(struct perf_event_header *header, if (sample_type & PERF_SAMPLE_PHYS_ADDR) data->phys_addr = perf_virt_to_phys(data->addr); + + if (sample_type & PERF_SAMPLE_AUX) { + u64 size; + + header->size += sizeof(u64); /* size */ + + /* + * Given the 16bit nature of header::size, an AUX sample can + * easily overflow it, what with all the preceding sample bits. + * Make sure this doesn't happen by using up to U16_MAX bytes + * per sample in total (rounded down to 8 byte boundary). + */ + size = min_t(size_t, U16_MAX - header->size, + event->attr.aux_sample_size); + size = rounddown(size, 8); + size = perf_prepare_sample_aux(event, data, size); + + WARN_ON_ONCE(size + header->size > U16_MAX); + header->size += size; + } + /* + * If you're adding more sample types here, you likely need to do + * something about the overflowing header::size, like repurpose the + * lowest 3 bits of size, which should be always zero at the moment. + * This raises a more important question, do we really need 512k sized + * samples and why, so good argumentation is in order for whatever you + * do here next. + */ + WARN_ON_ONCE(header->size & 7); } static __always_inline int @@ -10727,7 +10894,7 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr, attr->size = size; - if (attr->__reserved_1 || attr->__reserved_2) + if (attr->__reserved_1 || attr->__reserved_2 || attr->__reserved_3) return -EINVAL; if (attr->sample_type & ~(PERF_SAMPLE_MAX-1)) @@ -11277,7 +11444,7 @@ SYSCALL_DEFINE5(perf_event_open, } } - if (event->attr.aux_output && !perf_get_aux_event(event, group_leader)) + if (perf_need_aux_event(event) && !perf_get_aux_event(event, group_leader)) goto err_locked; /* diff --git a/kernel/events/internal.h b/kernel/events/internal.h index 3aef4191798c..747d67f130cb 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -50,6 +50,7 @@ struct ring_buffer { unsigned long aux_mmap_locked; void (*free_aux)(void *); refcount_t aux_refcount; + int aux_in_sampling; void **aux_pages; void *aux_priv; diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 246c83ac5643..7ffd5c763f93 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -562,6 +562,42 @@ void *perf_get_aux(struct perf_output_handle *handle) } EXPORT_SYMBOL_GPL(perf_get_aux); +/* + * Copy out AUX data from an AUX handle. + */ +long perf_output_copy_aux(struct perf_output_handle *aux_handle, + struct perf_output_handle *handle, + unsigned long from, unsigned long to) +{ + unsigned long tocopy, remainder, len = 0; + struct ring_buffer *rb = aux_handle->rb; + void *addr; + + from &= (rb->aux_nr_pages << PAGE_SHIFT) - 1; + to &= (rb->aux_nr_pages << PAGE_SHIFT) - 1; + + do { + tocopy = PAGE_SIZE - offset_in_page(from); + if (to > from) + tocopy = min(tocopy, to - from); + if (!tocopy) + break; + + addr = rb->aux_pages[from >> PAGE_SHIFT]; + addr += offset_in_page(from); + + remainder = perf_output_copy(handle, addr, tocopy); + if (remainder) + return -EFAULT; + + len += tocopy; + from += tocopy; + from &= (rb->aux_nr_pages << PAGE_SHIFT) - 1; + } while (to != from); + + return len; +} + #define PERF_AUX_GFP (GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY) static struct page *rb_alloc_aux_page(int node, int order) -- cgit v1.2.3-71-gd317 From cf25e24db61cc9df42c47485a2ec2bff4e9a3692 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 7 Nov 2019 11:07:58 +0100 Subject: time: Rename tsk->real_start_time to ->start_boottime Since it stores CLOCK_BOOTTIME, not, as the name suggests, CLOCK_REALTIME, let's rename ->real_start_time to ->start_bootime. Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- fs/exec.c | 2 +- fs/proc/array.c | 2 +- include/linux/sched.h | 2 +- kernel/fork.c | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/exec.c b/fs/exec.c index 555e93c7dec8..f4d0f3acf861 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1132,7 +1132,7 @@ static int de_thread(struct task_struct *tsk) * also take its birthdate (always earlier than our own). */ tsk->start_time = leader->start_time; - tsk->real_start_time = leader->real_start_time; + tsk->start_boottime = leader->start_boottime; BUG_ON(!same_thread_group(leader, tsk)); BUG_ON(has_group_leader_pid(tsk)); diff --git a/fs/proc/array.c b/fs/proc/array.c index 46dcb6f0eccf..5efaf3708ec6 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -533,7 +533,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, nice = task_nice(task); /* convert nsec -> ticks */ - start_time = nsec_to_clock_t(task->real_start_time); + start_time = nsec_to_clock_t(task->start_boottime); seq_put_decimal_ull(m, "", pid_nr_ns(pid, ns)); seq_puts(m, " ("); diff --git a/include/linux/sched.h b/include/linux/sched.h index 67a1d86981a9..254128952eab 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -857,7 +857,7 @@ struct task_struct { u64 start_time; /* Boot based time in nsecs: */ - u64 real_start_time; + u64 start_boottime; /* MM fault and swap info: this can arguably be seen as either mm-specific or thread-specific: */ unsigned long min_flt; diff --git a/kernel/fork.c b/kernel/fork.c index bcdf53125210..1392ee8f4848 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2130,7 +2130,7 @@ static __latent_entropy struct task_struct *copy_process( */ p->start_time = ktime_get_ns(); - p->real_start_time = ktime_get_boottime_ns(); + p->start_boottime = ktime_get_boottime_ns(); /* * Make it visible to the rest of the system, but dont wake it up yet. -- cgit v1.2.3-71-gd317 From 2079fe6ea8cbd2fb2fbadba911f1eca6c362eb9b Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Tue, 15 Oct 2019 14:12:38 +0100 Subject: ARM: OMAP2+: SmartReflex: add omap_sr_pdata definition The omap_sr_pdata is not declared but is exported, so add a define for it to fix the following warning: arch/arm/mach-omap2/pdata-quirks.c:609:36: warning: symbol 'omap_sr_pdata' was not declared. Should it be static? Signed-off-by: Ben Dooks Signed-off-by: Rafael J. Wysocki --- include/linux/power/smartreflex.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power/smartreflex.h b/include/linux/power/smartreflex.h index d0b37e937037..971c9264179e 100644 --- a/include/linux/power/smartreflex.h +++ b/include/linux/power/smartreflex.h @@ -293,6 +293,9 @@ struct omap_sr_data { struct voltagedomain *voltdm; }; + +extern struct omap_sr_data omap_sr_pdata[OMAP_SR_NR]; + #ifdef CONFIG_POWER_AVS_OMAP /* Smartreflex module enable/disable interface */ -- cgit v1.2.3-71-gd317 From ca765a8cfe0c78bfa47b9d67121f4e342d4b4512 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Wed, 16 Oct 2019 15:16:03 +0200 Subject: PM / Domains: Introduce dev_pm_domain_start() For a subsystem/driver that either doesn't support runtime PM or makes use of pm_runtime_set_active() during ->probe(), may try to access its device when probing, even if it may not be fully powered on from the PM domain's point of view. This may be the case when the used PM domain is a genpd provider, that implements genpd's ->start|stop() device callbacks. There are cases where the subsystem/driver managed to avoid the above problem, simply by calling pm_runtime_enable() and pm_runtime_get_sync() during ->probe(). However, this approach comes with a drawback, especially if the subsystem/driver implements a ->runtime_resume() callback. More precisely, the subsystem/driver then needs to use a device flag, which is checked in its ->runtime_resume() callback, as to avoid powering on its resources the first time the callback is invoked. This is needed because the subsystem/driver has already powered on the resources for the device, during ->probe() and before it called pm_runtime_get_sync(). In a way to avoid this boilerplate code and the inefficient check for "if (first_time_suspend)" in the ->runtime_resume() callback for these subsystems/drivers, let's introduce and export a dev_pm_domain_start() function, that may be called during ->probe() instead. Moreover, let the dev_pm_domain_start() invoke an optional ->start() callback, added to the struct dev_pm_domain, as to allow a PM domain specific implementation. Signed-off-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- drivers/base/power/common.c | 20 ++++++++++++++++++++ include/linux/pm.h | 2 ++ include/linux/pm_domain.h | 5 +++++ 3 files changed, 27 insertions(+) (limited to 'include/linux') diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c index 8db98a1f83dc..bbddb267c2e6 100644 --- a/drivers/base/power/common.c +++ b/drivers/base/power/common.c @@ -187,6 +187,26 @@ void dev_pm_domain_detach(struct device *dev, bool power_off) } EXPORT_SYMBOL_GPL(dev_pm_domain_detach); +/** + * dev_pm_domain_start - Start the device through its PM domain. + * @dev: Device to start. + * + * This function should typically be called during probe by a subsystem/driver, + * when it needs to start its device from the PM domain's perspective. Note + * that, it's assumed that the PM domain is already powered on when this + * function is called. + * + * Returns 0 on success and negative error values on failures. + */ +int dev_pm_domain_start(struct device *dev) +{ + if (dev->pm_domain && dev->pm_domain->start) + return dev->pm_domain->start(dev); + + return 0; +} +EXPORT_SYMBOL_GPL(dev_pm_domain_start); + /** * dev_pm_domain_set - Set PM domain of a device. * @dev: Device whose PM domain is to be set. diff --git a/include/linux/pm.h b/include/linux/pm.h index 4c441be03079..e057d1fa2469 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -637,6 +637,7 @@ extern void dev_pm_put_subsys_data(struct device *dev); * struct dev_pm_domain - power management domain representation. * * @ops: Power management operations associated with this domain. + * @start: Called when a user needs to start the device via the domain. * @detach: Called when removing a device from the domain. * @activate: Called before executing probe routines for bus types and drivers. * @sync: Called after successful driver probe. @@ -648,6 +649,7 @@ extern void dev_pm_put_subsys_data(struct device *dev); */ struct dev_pm_domain { struct dev_pm_ops ops; + int (*start)(struct device *dev); void (*detach)(struct device *dev, bool power_off); int (*activate)(struct device *dev); void (*sync)(struct device *dev); diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index baf02ff91a31..5a31c711b896 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -366,6 +366,7 @@ struct device *dev_pm_domain_attach_by_id(struct device *dev, struct device *dev_pm_domain_attach_by_name(struct device *dev, const char *name); void dev_pm_domain_detach(struct device *dev, bool power_off); +int dev_pm_domain_start(struct device *dev); void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd); #else static inline int dev_pm_domain_attach(struct device *dev, bool power_on) @@ -383,6 +384,10 @@ static inline struct device *dev_pm_domain_attach_by_name(struct device *dev, return NULL; } static inline void dev_pm_domain_detach(struct device *dev, bool power_off) {} +static inline int dev_pm_domain_start(struct device *dev) +{ + return 0; +} static inline void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd) {} #endif -- cgit v1.2.3-71-gd317 From bee3bbe616a2c8de641a64d874f9206835bd4401 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Tue, 12 Nov 2019 18:35:59 -0800 Subject: driver core: Clarify documentation for fwnode_operations.add_links() The wording was a bit ambiguous. So update it to make it clear. Signed-off-by: Saravana Kannan Reviewed-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20191113023559.62295-2-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fwnode.h | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 766ff9bb5876..23df37f85398 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -94,15 +94,16 @@ struct fwnode_reference_args { * available suppliers. * * Return 0 if device links have been successfully created to all - * the suppliers this device needs to create device links to or if - * the supplier information is not known. + * the known suppliers of this device or if the supplier + * information is not known. * - * Return -ENODEV if and only if the suppliers needed for probing - * the device are not yet available to create device links to. + * Return -ENODEV if the suppliers needed for probing this device + * have not been registered yet (because device links can only be + * created to devices registered with the driver core). * - * Return -EAGAIN if there are suppliers that need to be linked to - * that are not yet available but none of those suppliers are - * necessary for probing this device. + * Return -EAGAIN if some of the suppliers of this device have not + * been registered yet, but none of those suppliers are necessary + * for probing the device. */ struct fwnode_operations { struct fwnode_handle *(*get)(struct fwnode_handle *fwnode); -- cgit v1.2.3-71-gd317 From c059d579961d62c1a675cb89ef799902e6bce815 Mon Sep 17 00:00:00 2001 From: Sudip Mukherjee Date: Wed, 16 Oct 2019 15:45:37 +0100 Subject: parport: daisy: avoid hardcoded name The daisy device name is hardcoded, define it in the header file and use it in the code. Signed-off-by: Sudip Mukherjee Link: https://lore.kernel.org/r/20191016144540.18810-1-sudipm.mukherjee@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/parport/probe.c | 2 +- include/linux/parport.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/parport/probe.c b/drivers/parport/probe.c index e035174ba205..e5e6a463a941 100644 --- a/drivers/parport/probe.c +++ b/drivers/parport/probe.c @@ -257,7 +257,7 @@ static ssize_t parport_read_device_id (struct parport *port, char *buffer, ssize_t parport_device_id (int devnum, char *buffer, size_t count) { ssize_t retval = -ENXIO; - struct pardevice *dev = parport_open (devnum, "Device ID probe"); + struct pardevice *dev = parport_open(devnum, daisy_dev_name); if (!dev) return -ENXIO; diff --git a/include/linux/parport.h b/include/linux/parport.h index 397607a0c0eb..13932ce8b37b 100644 --- a/include/linux/parport.h +++ b/include/linux/parport.h @@ -460,6 +460,7 @@ extern size_t parport_ieee1284_epp_read_addr (struct parport *, void *, size_t, int); /* IEEE1284.3 functions */ +#define daisy_dev_name "Device ID probe" extern int parport_daisy_init (struct parport *port); extern void parport_daisy_fini (struct parport *port); extern struct pardevice *parport_open (int devnum, const char *name); -- cgit v1.2.3-71-gd317 From b056ca1c2f01b2d261c2dd6d167c17ac27977034 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 4 Nov 2019 18:09:39 +0200 Subject: gpiolib: Introduce ->add_pin_ranges() callback When IRQ chip is being added by GPIO library, the ACPI based platform expects GPIO <-> pin mapping ranges to be initialized in order to correctly initialize ACPI event mechanism on affected platforms. Unfortunately this step is missed. Introduce ->add_pin_ranges() callback to fill the above mentioned gap. Signed-off-by: Andy Shevchenko Reviewed-by: Linus Walleij Reviewed-by: Mika Westerberg Reviewed-by: Hans de Goede Tested-by: Hans de Goede --- drivers/gpio/gpiolib.c | 12 ++++++++++++ include/linux/gpio/driver.h | 5 +++++ 2 files changed, 17 insertions(+) (limited to 'include/linux') diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 731d732cdc2b..1dc144f83483 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -390,6 +390,14 @@ static void gpiochip_free_valid_mask(struct gpio_chip *gpiochip) gpiochip->valid_mask = NULL; } +static int gpiochip_add_pin_ranges(struct gpio_chip *gc) +{ + if (gc->add_pin_ranges) + return gc->add_pin_ranges(gc); + + return 0; +} + bool gpiochip_line_is_valid(const struct gpio_chip *gpiochip, unsigned int offset) { @@ -1397,6 +1405,10 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data, } } + ret = gpiochip_add_pin_ranges(chip); + if (ret) + goto err_remove_of_chip; + acpi_gpiochip_add(chip); machine_gpiochip_add(chip); diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index cc9ade4552d9..e2480ef94c55 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -289,6 +289,9 @@ struct gpio_irq_chip { * state (such as pullup/pulldown configuration). * @init_valid_mask: optional routine to initialize @valid_mask, to be used if * not all GPIOs are valid. + * @add_pin_ranges: optional routine to initialize pin ranges, to be used when + * requires special mapping of the pins that provides GPIO functionality. + * It is called after adding GPIO chip and before adding IRQ chip. * @base: identifies the first GPIO number handled by this chip; * or, if negative during registration, requests dynamic ID allocation. * DEPRECATION: providing anything non-negative and nailing the base @@ -379,6 +382,8 @@ struct gpio_chip { unsigned long *valid_mask, unsigned int ngpios); + int (*add_pin_ranges)(struct gpio_chip *chip); + int base; u16 ngpio; const char *const *names; -- cgit v1.2.3-71-gd317 From 763e34e74bb7d5c316015e2e39fcc8520bfd071c Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 8 Nov 2019 13:07:06 -0500 Subject: ftrace: Add register_ftrace_direct() Add the start of the functionality to allow other trampolines to use the ftrace mcount/fentry/nop location. This adds two new functions: register_ftrace_direct() and unregister_ftrace_direct() Both take two parameters: the first is the instruction address of where the mcount/fentry/nop exists, and the second is the trampoline to have that location called. This will handle cases where ftrace is already used on that same location, and will make it still work, where the registered direct called trampoline will get called after all the registered ftrace callers are handled. Currently, it will not allow for IP_MODIFY functions to be called at the same locations, which include some kprobes and live kernel patching. At this point, no architecture supports this. This is only the start of implementing the framework. Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 36 ++++++- kernel/trace/Kconfig | 8 ++ kernel/trace/ftrace.c | 269 ++++++++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 306 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 8385cafe4f9f..efe3e521aff4 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -144,6 +144,8 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops); * TRACE_ARRAY - The ops->private points to a trace_array descriptor. * PERMANENT - Set when the ops is permanent and should not be affected by * ftrace_enabled. + * DIRECT - Used by the direct ftrace_ops helper for direct functions + * (internal ftrace only, should not be used by others) */ enum { FTRACE_OPS_FL_ENABLED = 1 << 0, @@ -163,6 +165,7 @@ enum { FTRACE_OPS_FL_RCU = 1 << 14, FTRACE_OPS_FL_TRACE_ARRAY = 1 << 15, FTRACE_OPS_FL_PERMANENT = 1 << 16, + FTRACE_OPS_FL_DIRECT = 1 << 17, }; #ifdef CONFIG_DYNAMIC_FTRACE @@ -242,6 +245,32 @@ static inline void ftrace_free_init_mem(void) { } static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { } #endif /* CONFIG_FUNCTION_TRACER */ +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +int register_ftrace_direct(unsigned long ip, unsigned long addr); +int unregister_ftrace_direct(unsigned long ip, unsigned long addr); +#else +static inline int register_ftrace_direct(unsigned long ip, unsigned long addr) +{ + return -ENODEV; +} +static inline int unregister_ftrace_direct(unsigned long ip, unsigned long addr) +{ + return -ENODEV; +} +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ + +#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +/* + * This must be implemented by the architecture. + * It is the way the ftrace direct_ops helper, when called + * via ftrace (because there's other callbacks besides the + * direct call), can inform the architecture's trampoline that this + * routine has a direct caller, and what the caller is. + */ +static inline void arch_ftrace_set_direct_caller(struct pt_regs *regs, + unsigned long addr) { } +#endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ + #ifdef CONFIG_STACK_TRACER extern int stack_tracer_enabled; @@ -333,6 +362,7 @@ bool is_ftrace_trampoline(unsigned long addr); * REGS_EN - the function is set up to save regs. * IPMODIFY - the record allows for the IP address to be changed. * DISABLED - the record is not ready to be touched yet + * DIRECT - there is a direct function to call * * When a new ftrace_ops is registered and wants a function to save * pt_regs, the rec->flag REGS is set. When the function has been @@ -348,10 +378,12 @@ enum { FTRACE_FL_TRAMP_EN = (1UL << 27), FTRACE_FL_IPMODIFY = (1UL << 26), FTRACE_FL_DISABLED = (1UL << 25), + FTRACE_FL_DIRECT = (1UL << 24), + FTRACE_FL_DIRECT_EN = (1UL << 23), }; -#define FTRACE_REF_MAX_SHIFT 25 -#define FTRACE_FL_BITS 7 +#define FTRACE_REF_MAX_SHIFT 23 +#define FTRACE_FL_BITS 9 #define FTRACE_FL_MASKED_BITS ((1UL << FTRACE_FL_BITS) - 1) #define FTRACE_FL_MASK (FTRACE_FL_MASKED_BITS << FTRACE_REF_MAX_SHIFT) #define FTRACE_REF_MAX ((1UL << FTRACE_REF_MAX_SHIFT) - 1) diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index e08527f50d2a..624a05e99b0b 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -33,6 +33,9 @@ config HAVE_DYNAMIC_FTRACE config HAVE_DYNAMIC_FTRACE_WITH_REGS bool +config HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + bool + config HAVE_FTRACE_MCOUNT_RECORD bool help @@ -557,6 +560,11 @@ config DYNAMIC_FTRACE_WITH_REGS depends on DYNAMIC_FTRACE depends on HAVE_DYNAMIC_FTRACE_WITH_REGS +config DYNAMIC_FTRACE_WITH_DIRECT_CALLS + def_bool y + depends on DYNAMIC_FTRACE + depends on HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + config FUNCTION_PROFILER bool "Kernel function profiler" depends on FUNCTION_TRACER diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index b0e7f03919de..329a3f3789a1 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1023,6 +1023,7 @@ static bool update_all_ops; struct ftrace_func_entry { struct hlist_node hlist; unsigned long ip; + unsigned long direct; /* for direct lookup only */ }; struct ftrace_func_probe { @@ -1730,6 +1731,9 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, if (FTRACE_WARN_ON(ftrace_rec_count(rec) == FTRACE_REF_MAX)) return false; + if (ops->flags & FTRACE_OPS_FL_DIRECT) + rec->flags |= FTRACE_FL_DIRECT; + /* * If there's only a single callback registered to a * function, and the ops has a trampoline registered @@ -1757,6 +1761,15 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, return false; rec->flags--; + /* + * Only the internal direct_ops should have the + * DIRECT flag set. Thus, if it is removing a + * function, then that function should no longer + * be direct. + */ + if (ops->flags & FTRACE_OPS_FL_DIRECT) + rec->flags &= ~FTRACE_FL_DIRECT; + /* * If the rec had REGS enabled and the ops that is * being removed had REGS set, then see if there is @@ -2092,15 +2105,34 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update) * If enabling and the REGS flag does not match the REGS_EN, or * the TRAMP flag doesn't match the TRAMP_EN, then do not ignore * this record. Set flags to fail the compare against ENABLED. + * Same for direct calls. */ if (flag) { - if (!(rec->flags & FTRACE_FL_REGS) != + if (!(rec->flags & FTRACE_FL_REGS) != !(rec->flags & FTRACE_FL_REGS_EN)) flag |= FTRACE_FL_REGS; - if (!(rec->flags & FTRACE_FL_TRAMP) != + if (!(rec->flags & FTRACE_FL_TRAMP) != !(rec->flags & FTRACE_FL_TRAMP_EN)) flag |= FTRACE_FL_TRAMP; + + /* + * Direct calls are special, as count matters. + * We must test the record for direct, if the + * DIRECT and DIRECT_EN do not match, but only + * if the count is 1. That's because, if the + * count is something other than one, we do not + * want the direct enabled (it will be done via the + * direct helper). But if DIRECT_EN is set, and + * the count is not one, we need to clear it. + */ + if (ftrace_rec_count(rec) == 1) { + if (!(rec->flags & FTRACE_FL_DIRECT) != + !(rec->flags & FTRACE_FL_DIRECT_EN)) + flag |= FTRACE_FL_DIRECT; + } else if (rec->flags & FTRACE_FL_DIRECT_EN) { + flag |= FTRACE_FL_DIRECT; + } } /* If the state of this record hasn't changed, then do nothing */ @@ -2125,6 +2157,25 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update) else rec->flags &= ~FTRACE_FL_TRAMP_EN; } + if (flag & FTRACE_FL_DIRECT) { + /* + * If there's only one user (direct_ops helper) + * then we can call the direct function + * directly (no ftrace trampoline). + */ + if (ftrace_rec_count(rec) == 1) { + if (rec->flags & FTRACE_FL_DIRECT) + rec->flags |= FTRACE_FL_DIRECT_EN; + else + rec->flags &= ~FTRACE_FL_DIRECT_EN; + } else { + /* + * Can only call directly if there's + * only one callback to the function. + */ + rec->flags &= ~FTRACE_FL_DIRECT_EN; + } + } } /* @@ -2154,7 +2205,7 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update) * and REGS states. The _EN flags must be disabled though. */ rec->flags &= ~(FTRACE_FL_ENABLED | FTRACE_FL_TRAMP_EN | - FTRACE_FL_REGS_EN); + FTRACE_FL_REGS_EN | FTRACE_FL_DIRECT_EN); } ftrace_bug_type = FTRACE_BUG_NOP; @@ -2309,6 +2360,51 @@ ftrace_find_tramp_ops_new(struct dyn_ftrace *rec) return NULL; } +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +/* Protected by rcu_tasks for reading, and direct_mutex for writing */ +static struct ftrace_hash *direct_functions = EMPTY_HASH; +static DEFINE_MUTEX(direct_mutex); + +/* + * Search the direct_functions hash to see if the given instruction pointer + * has a direct caller attached to it. + */ +static unsigned long find_rec_direct(unsigned long ip) +{ + struct ftrace_func_entry *entry; + + entry = __ftrace_lookup_ip(direct_functions, ip); + if (!entry) + return 0; + + return entry->direct; +} + +static void call_direct_funcs(unsigned long ip, unsigned long pip, + struct ftrace_ops *ops, struct pt_regs *regs) +{ + unsigned long addr; + + addr = find_rec_direct(ip); + if (!addr) + return; + + arch_ftrace_set_direct_caller(regs, addr); +} + +struct ftrace_ops direct_ops = { + .func = call_direct_funcs, + .flags = FTRACE_OPS_FL_IPMODIFY | FTRACE_OPS_FL_RECURSION_SAFE + | FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS + | FTRACE_OPS_FL_PERMANENT, +}; +#else +static inline unsigned long find_rec_direct(unsigned long ip) +{ + return 0; +} +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ + /** * ftrace_get_addr_new - Get the call address to set to * @rec: The ftrace record descriptor @@ -2322,6 +2418,15 @@ ftrace_find_tramp_ops_new(struct dyn_ftrace *rec) unsigned long ftrace_get_addr_new(struct dyn_ftrace *rec) { struct ftrace_ops *ops; + unsigned long addr; + + if ((rec->flags & FTRACE_FL_DIRECT) && + (ftrace_rec_count(rec) == 1)) { + addr = find_rec_direct(rec->ip); + if (addr) + return addr; + WARN_ON_ONCE(1); + } /* Trampolines take precedence over regs */ if (rec->flags & FTRACE_FL_TRAMP) { @@ -2354,6 +2459,15 @@ unsigned long ftrace_get_addr_new(struct dyn_ftrace *rec) unsigned long ftrace_get_addr_curr(struct dyn_ftrace *rec) { struct ftrace_ops *ops; + unsigned long addr; + + /* Direct calls take precedence over trampolines */ + if (rec->flags & FTRACE_FL_DIRECT_EN) { + addr = find_rec_direct(rec->ip); + if (addr) + return addr; + WARN_ON_ONCE(1); + } /* Trampolines take precedence over regs */ if (rec->flags & FTRACE_FL_TRAMP_EN) { @@ -3465,10 +3579,11 @@ static int t_show(struct seq_file *m, void *v) if (iter->flags & FTRACE_ITER_ENABLED) { struct ftrace_ops *ops; - seq_printf(m, " (%ld)%s%s", + seq_printf(m, " (%ld)%s%s%s", ftrace_rec_count(rec), rec->flags & FTRACE_FL_REGS ? " R" : " ", - rec->flags & FTRACE_FL_IPMODIFY ? " I" : " "); + rec->flags & FTRACE_FL_IPMODIFY ? " I" : " ", + rec->flags & FTRACE_FL_DIRECT ? " D" : " "); if (rec->flags & FTRACE_FL_TRAMP_EN) { ops = ftrace_find_tramp_ops_any(rec); if (ops) { @@ -3484,6 +3599,13 @@ static int t_show(struct seq_file *m, void *v) } else { add_trampoline_func(m, NULL, rec); } + if (rec->flags & FTRACE_FL_DIRECT) { + unsigned long direct; + + direct = find_rec_direct(rec->ip); + if (direct) + seq_printf(m, "\n\tdirect-->%pS", (void *)direct); + } } seq_putc(m, '\n'); @@ -4815,6 +4937,143 @@ ftrace_set_addr(struct ftrace_ops *ops, unsigned long ip, int remove, return ftrace_set_hash(ops, NULL, 0, ip, remove, reset, enable); } +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +/** + * register_ftrace_direct - Call a custom trampoline directly + * @ip: The address of the nop at the beginning of a function + * @addr: The address of the trampoline to call at @ip + * + * This is used to connect a direct call from the nop location (@ip) + * at the start of ftrace traced functions. The location that it calls + * (@addr) must be able to handle a direct call, and save the parameters + * of the function being traced, and restore them (or inject new ones + * if needed), before returning. + * + * Returns: + * 0 on success + * -EBUSY - Another direct function is already attached (there can be only one) + * -ENODEV - @ip does not point to a ftrace nop location (or not supported) + * -ENOMEM - There was an allocation failure. + */ +int register_ftrace_direct(unsigned long ip, unsigned long addr) +{ + struct ftrace_func_entry *entry; + struct ftrace_hash *free_hash = NULL; + struct dyn_ftrace *rec; + int ret = -EBUSY; + + mutex_lock(&direct_mutex); + + /* See if there's a direct function at @ip already */ + if (find_rec_direct(ip)) + goto out_unlock; + + ret = -ENODEV; + rec = lookup_rec(ip, ip); + if (!rec) + goto out_unlock; + + /* + * Check if the rec says it has a direct call but we didn't + * find one earlier? + */ + if (WARN_ON(rec->flags & FTRACE_FL_DIRECT)) + goto out_unlock; + + /* Make sure the ip points to the exact record */ + ip = rec->ip; + + ret = -ENOMEM; + if (ftrace_hash_empty(direct_functions) || + direct_functions->count > 2 * (1 << direct_functions->size_bits)) { + struct ftrace_hash *new_hash; + int size = ftrace_hash_empty(direct_functions) ? 0 : + direct_functions->count + 1; + + if (size < 32) + size = 32; + + new_hash = dup_hash(direct_functions, size); + if (!new_hash) + goto out_unlock; + + free_hash = direct_functions; + direct_functions = new_hash; + } + + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + goto out_unlock; + + entry->ip = ip; + entry->direct = addr; + __add_hash_entry(direct_functions, entry); + + ret = ftrace_set_filter_ip(&direct_ops, ip, 0, 0); + if (ret) + remove_hash_entry(direct_functions, entry); + + if (!ret && !(direct_ops.flags & FTRACE_OPS_FL_ENABLED)) { + ret = register_ftrace_function(&direct_ops); + if (ret) + ftrace_set_filter_ip(&direct_ops, ip, 1, 0); + } + + if (ret) + kfree(entry); + out_unlock: + mutex_unlock(&direct_mutex); + + if (free_hash) { + synchronize_rcu_tasks(); + free_ftrace_hash(free_hash); + } + + return ret; +} +EXPORT_SYMBOL_GPL(register_ftrace_direct); + +int unregister_ftrace_direct(unsigned long ip, unsigned long addr) +{ + struct ftrace_func_entry *entry; + struct dyn_ftrace *rec; + int ret = -ENODEV; + + mutex_lock(&direct_mutex); + + entry = __ftrace_lookup_ip(direct_functions, ip); + if (!entry) { + /* OK if it is off by a little */ + rec = lookup_rec(ip, ip); + if (!rec || rec->ip == ip) + goto out_unlock; + + entry = __ftrace_lookup_ip(direct_functions, rec->ip); + if (!entry) { + WARN_ON(rec->flags & FTRACE_FL_DIRECT); + goto out_unlock; + } + + WARN_ON(!(rec->flags & FTRACE_FL_DIRECT)); + } + + if (direct_functions->count == 1) + unregister_ftrace_function(&direct_ops); + + ret = ftrace_set_filter_ip(&direct_ops, ip, 1, 0); + + WARN_ON(ret); + + remove_hash_entry(direct_functions, entry); + + out_unlock: + mutex_unlock(&direct_mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(unregister_ftrace_direct); +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ + /** * ftrace_set_filter_ip - set a function to filter on in ftrace by address * @ops - the ops to set the filter with -- cgit v1.2.3-71-gd317 From 013bf0da0474816f57739daa006c8564ad7396a3 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 8 Nov 2019 13:11:27 -0500 Subject: ftrace: Add ftrace_find_direct_func() As function_graph tracer modifies the return address to insert a trampoline to trace the return of a function, it must be aware of a direct caller, as when it gets called, the function's return address may not be at on the stack where it expects. It may have to see if that return address points to the a direct caller and adjust if it is. Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 6 ++++ kernel/trace/ftrace.c | 79 +++++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 84 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index efe3e521aff4..8b37b8105398 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -51,6 +51,7 @@ static inline void early_trace_init(void) { } struct module; struct ftrace_hash; +struct ftrace_direct_func; #if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_MODULES) && \ defined(CONFIG_DYNAMIC_FTRACE) @@ -248,6 +249,7 @@ static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS int register_ftrace_direct(unsigned long ip, unsigned long addr); int unregister_ftrace_direct(unsigned long ip, unsigned long addr); +struct ftrace_direct_func *ftrace_find_direct_func(unsigned long addr); #else static inline int register_ftrace_direct(unsigned long ip, unsigned long addr) { @@ -257,6 +259,10 @@ static inline int unregister_ftrace_direct(unsigned long ip, unsigned long addr) { return -ENODEV; } +static inline struct ftrace_direct_func *ftrace_find_direct_func(unsigned long addr) +{ + return NULL; +} #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ #ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 329a3f3789a1..c4446eabacbe 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4938,6 +4938,46 @@ ftrace_set_addr(struct ftrace_ops *ops, unsigned long ip, int remove, } #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + +struct ftrace_direct_func { + struct list_head next; + unsigned long addr; + int count; +}; + +static LIST_HEAD(ftrace_direct_funcs); + +/** + * ftrace_find_direct_func - test an address if it is a registered direct caller + * @addr: The address of a registered direct caller + * + * This searches to see if a ftrace direct caller has been registered + * at a specific address, and if so, it returns a descriptor for it. + * + * This can be used by architecture code to see if an address is + * a direct caller (trampoline) attached to a fentry/mcount location. + * This is useful for the function_graph tracer, as it may need to + * do adjustments if it traced a location that also has a direct + * trampoline attached to it. + */ +struct ftrace_direct_func *ftrace_find_direct_func(unsigned long addr) +{ + struct ftrace_direct_func *entry; + bool found = false; + + /* May be called by fgraph trampoline (protected by rcu tasks) */ + list_for_each_entry_rcu(entry, &ftrace_direct_funcs, next) { + if (entry->addr == addr) { + found = true; + break; + } + } + if (found) + return entry; + + return NULL; +} + /** * register_ftrace_direct - Call a custom trampoline directly * @ip: The address of the nop at the beginning of a function @@ -4957,6 +4997,7 @@ ftrace_set_addr(struct ftrace_ops *ops, unsigned long ip, int remove, */ int register_ftrace_direct(unsigned long ip, unsigned long addr) { + struct ftrace_direct_func *direct; struct ftrace_func_entry *entry; struct ftrace_hash *free_hash = NULL; struct dyn_ftrace *rec; @@ -5005,6 +5046,18 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr) if (!entry) goto out_unlock; + direct = ftrace_find_direct_func(addr); + if (!direct) { + direct = kmalloc(sizeof(*direct), GFP_KERNEL); + if (!direct) { + kfree(entry); + goto out_unlock; + } + direct->addr = addr; + direct->count = 0; + list_add_rcu(&direct->next, &ftrace_direct_funcs); + } + entry->ip = ip; entry->direct = addr; __add_hash_entry(direct_functions, entry); @@ -5019,8 +5072,20 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr) ftrace_set_filter_ip(&direct_ops, ip, 1, 0); } - if (ret) + if (ret) { kfree(entry); + if (!direct->count) { + list_del_rcu(&direct->next); + synchronize_rcu_tasks(); + kfree(direct); + if (free_hash) + free_ftrace_hash(free_hash); + free_hash = NULL; + } + } else { + if (!direct->count) + direct->count++; + } out_unlock: mutex_unlock(&direct_mutex); @@ -5036,6 +5101,7 @@ EXPORT_SYMBOL_GPL(register_ftrace_direct); int unregister_ftrace_direct(unsigned long ip, unsigned long addr) { struct ftrace_func_entry *entry; + struct ftrace_direct_func *direct; struct dyn_ftrace *rec; int ret = -ENODEV; @@ -5066,6 +5132,17 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr) remove_hash_entry(direct_functions, entry); + direct = ftrace_find_direct_func(addr); + if (!WARN_ON(!direct)) { + /* This is the good path (see the ! before WARN) */ + direct->count--; + WARN_ON(direct->count < 0); + if (!direct->count) { + list_del_rcu(&direct->next); + synchronize_rcu_tasks(); + kfree(direct); + } + } out_unlock: mutex_unlock(&direct_mutex); -- cgit v1.2.3-71-gd317 From 562955fe6a558b9ef98ad87c470314946338cb2f Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 8 Nov 2019 13:11:39 -0500 Subject: ftrace/x86: Add register_ftrace_direct() for custom trampolines Enable x86 to allow for register_ftrace_direct(), where a custom trampoline may be called directly from an ftrace mcount/fentry location. Signed-off-by: Steven Rostedt (VMware) --- arch/x86/Kconfig | 1 + arch/x86/include/asm/ftrace.h | 13 +++++++++++++ arch/x86/kernel/ftrace.c | 12 ++++++++++++ arch/x86/kernel/ftrace_64.S | 34 +++++++++++++++++++++++++++------- include/linux/ftrace.h | 6 ++++++ 5 files changed, 59 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index d6e1faa28c58..329d9c729ba3 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -158,6 +158,7 @@ config X86 select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS + select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS select HAVE_EBPF_JIT select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_EISA diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index c38a66661576..c2a7458f912c 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -28,6 +28,19 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr) return addr; } +/* + * When a ftrace registered caller is tracing a function that is + * also set by a register_ftrace_direct() call, it needs to be + * differentiated in the ftrace_caller trampoline. To do this, we + * place the direct caller in the ORIG_AX part of pt_regs. This + * tells the ftrace_caller that there's a direct caller. + */ +static inline void arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr) +{ + /* Emulate a call */ + regs->orig_ax = addr; +} + #ifdef CONFIG_DYNAMIC_FTRACE struct dyn_arch_ftrace { diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 024c3053dbba..fef283f6341d 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -1042,6 +1042,18 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, if (unlikely(atomic_read(¤t->tracing_graph_pause))) return; + /* + * If the return location is actually pointing directly to + * the start of a direct trampoline (if we trace the trampoline + * it will still be offset by MCOUNT_INSN_SIZE), then the + * return address is actually off by one word, and we + * need to adjust for that. + */ + if (ftrace_find_direct_func(self_addr + MCOUNT_INSN_SIZE)) { + self_addr = *parent; + parent++; + } + /* * Protect against fault, even if it shouldn't * happen. This tool is too much intrusive to diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 809d54397dba..6ac7ff304886 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -88,6 +88,7 @@ EXPORT_SYMBOL(__fentry__) movq %rdi, RDI(%rsp) movq %r8, R8(%rsp) movq %r9, R9(%rsp) + movq $0, ORIG_RAX(%rsp) /* * Save the original RBP. Even though the mcount ABI does not * require this, it helps out callers. @@ -114,7 +115,11 @@ EXPORT_SYMBOL(__fentry__) subq $MCOUNT_INSN_SIZE, %rdi .endm -.macro restore_mcount_regs +.macro restore_mcount_regs save=0 + + /* ftrace_regs_caller or frame pointers require this */ + movq RBP(%rsp), %rbp + movq R9(%rsp), %r9 movq R8(%rsp), %r8 movq RDI(%rsp), %rdi @@ -123,10 +128,7 @@ EXPORT_SYMBOL(__fentry__) movq RCX(%rsp), %rcx movq RAX(%rsp), %rax - /* ftrace_regs_caller can modify %rbp */ - movq RBP(%rsp), %rbp - - addq $MCOUNT_REG_SIZE, %rsp + addq $MCOUNT_REG_SIZE-\save, %rsp .endm @@ -228,10 +230,28 @@ GLOBAL(ftrace_regs_call) movq R10(%rsp), %r10 movq RBX(%rsp), %rbx - restore_mcount_regs + movq ORIG_RAX(%rsp), %rax + movq %rax, MCOUNT_REG_SIZE-8(%rsp) + + /* If ORIG_RAX is anything but zero, make this a call to that */ + movq ORIG_RAX(%rsp), %rax + cmpq $0, %rax + je 1f + + /* Swap the flags with orig_rax */ + movq MCOUNT_REG_SIZE(%rsp), %rdi + movq %rdi, MCOUNT_REG_SIZE-8(%rsp) + movq %rax, MCOUNT_REG_SIZE(%rsp) + + restore_mcount_regs 8 + + jmp 2f + +1: restore_mcount_regs + /* Restore flags */ - popfq +2: popfq /* * As this jmp to ftrace_epilogue can be a short jump diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 8b37b8105398..2bc7bd6b8387 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -272,6 +272,12 @@ static inline struct ftrace_direct_func *ftrace_find_direct_func(unsigned long a * via ftrace (because there's other callbacks besides the * direct call), can inform the architecture's trampoline that this * routine has a direct caller, and what the caller is. + * + * For example, in x86, it returns the direct caller + * callback function via the regs->orig_ax parameter. + * Then in the ftrace trampoline, if this is set, it makes + * the return from the trampoline jump to the direct caller + * instead of going back to the function it just traced. */ static inline void arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr) { } -- cgit v1.2.3-71-gd317 From a3ad1a7e39689005cb04a4f2adb82f9d55b4724f Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 8 Nov 2019 13:12:57 -0500 Subject: ftrace/x86: Add a counter to test function_graph with direct As testing for direct calls from the function graph tracer adds a little overhead (which is a lot when tracing every function), add a counter that can be used to test if function_graph tracer needs to test for a direct caller or not. It would have been nicer if we could use a static branch, but the static branch logic fails when used within the function graph tracer trampoline. Signed-off-by: Steven Rostedt (VMware) --- arch/x86/kernel/ftrace.c | 8 +++++--- include/linux/ftrace.h | 2 ++ kernel/trace/ftrace.c | 4 ++++ 3 files changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index fef283f6341d..060a361d9d11 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -1049,9 +1049,11 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, * return address is actually off by one word, and we * need to adjust for that. */ - if (ftrace_find_direct_func(self_addr + MCOUNT_INSN_SIZE)) { - self_addr = *parent; - parent++; + if (ftrace_direct_func_count) { + if (ftrace_find_direct_func(self_addr + MCOUNT_INSN_SIZE)) { + self_addr = *parent; + parent++; + } } /* diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 2bc7bd6b8387..55647e185141 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -247,10 +247,12 @@ static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { #endif /* CONFIG_FUNCTION_TRACER */ #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +extern int ftrace_direct_func_count; int register_ftrace_direct(unsigned long ip, unsigned long addr); int unregister_ftrace_direct(unsigned long ip, unsigned long addr); struct ftrace_direct_func *ftrace_find_direct_func(unsigned long addr); #else +# define ftrace_direct_func_count 0 static inline int register_ftrace_direct(unsigned long ip, unsigned long addr) { return -ENODEV; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index c4446eabacbe..f9456346ec66 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2364,6 +2364,7 @@ ftrace_find_tramp_ops_new(struct dyn_ftrace *rec) /* Protected by rcu_tasks for reading, and direct_mutex for writing */ static struct ftrace_hash *direct_functions = EMPTY_HASH; static DEFINE_MUTEX(direct_mutex); +int ftrace_direct_func_count; /* * Search the direct_functions hash to see if the given instruction pointer @@ -5056,6 +5057,7 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr) direct->addr = addr; direct->count = 0; list_add_rcu(&direct->next, &ftrace_direct_funcs); + ftrace_direct_func_count++; } entry->ip = ip; @@ -5081,6 +5083,7 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr) if (free_hash) free_ftrace_hash(free_hash); free_hash = NULL; + ftrace_direct_func_count--; } } else { if (!direct->count) @@ -5141,6 +5144,7 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr) list_del_rcu(&direct->next); synchronize_rcu_tasks(); kfree(direct); + ftrace_direct_func_count--; } } out_unlock: -- cgit v1.2.3-71-gd317 From 2d6425af61166e026e7476db64f70f1266127b1d Mon Sep 17 00:00:00 2001 From: Divya Indi Date: Wed, 14 Aug 2019 10:55:23 -0700 Subject: tracing: Declare newly exported APIs in include/linux/trace.h Declare the newly introduced and exported APIs in the header file - include/linux/trace.h. Moving previous declarations from kernel/trace/trace.h to include/linux/trace.h. Link: http://lkml.kernel.org/r/1565805327-579-2-git-send-email-divya.indi@oracle.com Signed-off-by: Divya Indi Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace.h | 7 +++++++ kernel/trace/trace.h | 4 +--- 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace.h b/include/linux/trace.h index b95ffb2188ab..24fcf07812ae 100644 --- a/include/linux/trace.h +++ b/include/linux/trace.h @@ -24,6 +24,13 @@ struct trace_export { int register_ftrace_export(struct trace_export *export); int unregister_ftrace_export(struct trace_export *export); +struct trace_array; + +void trace_printk_init_buffers(void); +int trace_array_printk(struct trace_array *tr, unsigned long ip, + const char *fmt, ...); +struct trace_array *trace_array_create(const char *name); +int trace_array_destroy(struct trace_array *tr); #endif /* CONFIG_TRACING */ #endif /* _LINUX_TRACE_H */ diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 718eb998c13e..90cba68c8b50 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -873,8 +874,6 @@ trace_vprintk(unsigned long ip, const char *fmt, va_list args); extern int trace_array_vprintk(struct trace_array *tr, unsigned long ip, const char *fmt, va_list args); -int trace_array_printk(struct trace_array *tr, - unsigned long ip, const char *fmt, ...); int trace_array_printk_buf(struct ring_buffer *buffer, unsigned long ip, const char *fmt, ...); void trace_printk_seq(struct trace_seq *s); @@ -1890,7 +1889,6 @@ extern const char *__start___tracepoint_str[]; extern const char *__stop___tracepoint_str[]; void trace_printk_control(bool enabled); -void trace_printk_init_buffers(void); void trace_printk_start_comm(void); int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set); int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled); -- cgit v1.2.3-71-gd317 From cb711b91a3c685192f2cabd3735ca3de04694ed8 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 14 Nov 2019 01:27:21 +0800 Subject: blk-mq: Delete blk_mq_has_free_tags() and blk_mq_can_queue() These functions are not referenced, so delete them. Signed-off-by: John Garry Signed-off-by: Jens Axboe --- block/blk-mq-tag.c | 8 -------- block/blk-mq-tag.h | 1 - block/blk-mq.c | 6 ------ include/linux/blk-mq.h | 1 - 4 files changed, 16 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 008388e82b5c..fbacde454718 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -15,14 +15,6 @@ #include "blk-mq.h" #include "blk-mq-tag.h" -bool blk_mq_has_free_tags(struct blk_mq_tags *tags) -{ - if (!tags) - return true; - - return sbitmap_any_bit_clear(&tags->bitmap_tags.sb); -} - /* * If a previously inactive queue goes active, bump the active user count. * We need to do this before try to allocate driver tag, then even if fail diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index 61deab0b5a5a..15bc74acb57e 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -28,7 +28,6 @@ extern void blk_mq_free_tags(struct blk_mq_tags *tags); extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data); extern void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, unsigned int tag); -extern bool blk_mq_has_free_tags(struct blk_mq_tags *tags); extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags **tags, unsigned int depth, bool can_grow); diff --git a/block/blk-mq.c b/block/blk-mq.c index 5c9adcaa27ac..323c9cb28066 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -260,12 +260,6 @@ void blk_mq_wake_waiters(struct request_queue *q) blk_mq_tag_wakeup_all(hctx->tags, true); } -bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx) -{ - return blk_mq_has_free_tags(hctx->tags); -} -EXPORT_SYMBOL(blk_mq_can_queue); - /* * Only need start/end time stamping if we have iostat or * blk stats enabled, or using an IO scheduler. diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index dc03e059fdff..11cfd6470b1a 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -424,7 +424,6 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set); void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule); void blk_mq_free_request(struct request *rq); -bool blk_mq_can_queue(struct blk_mq_hw_ctx *); bool blk_mq_queue_inflight(struct request_queue *q); -- cgit v1.2.3-71-gd317 From 708edafa883186f55b24fa0c380242b5282f9105 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 14 Nov 2019 01:27:22 +0800 Subject: sbitmap: Delete sbitmap_any_bit_clear() Since the only caller of this function has been deleted, delete this one also. Signed-off-by: John Garry Signed-off-by: Jens Axboe --- include/linux/sbitmap.h | 9 --------- lib/sbitmap.c | 17 ----------------- 2 files changed, 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index a986ac12a848..e40d019c3d9d 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -216,15 +216,6 @@ int sbitmap_get_shallow(struct sbitmap *sb, unsigned int alloc_hint, */ bool sbitmap_any_bit_set(const struct sbitmap *sb); -/** - * sbitmap_any_bit_clear() - Check for an unset bit in a &struct - * sbitmap. - * @sb: Bitmap to check. - * - * Return: true if any bit in the bitmap is clear, false otherwise. - */ -bool sbitmap_any_bit_clear(const struct sbitmap *sb); - #define SB_NR_TO_INDEX(sb, bitnr) ((bitnr) >> (sb)->shift) #define SB_NR_TO_BIT(sb, bitnr) ((bitnr) & ((1U << (sb)->shift) - 1U)) diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 969e5400a615..33feec8989f1 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -236,23 +236,6 @@ bool sbitmap_any_bit_set(const struct sbitmap *sb) } EXPORT_SYMBOL_GPL(sbitmap_any_bit_set); -bool sbitmap_any_bit_clear(const struct sbitmap *sb) -{ - unsigned int i; - - for (i = 0; i < sb->map_nr; i++) { - const struct sbitmap_word *word = &sb->map[i]; - unsigned long mask = word->word & ~word->cleared; - unsigned long ret; - - ret = find_first_zero_bit(&mask, word->depth); - if (ret < word->depth) - return true; - } - return false; -} -EXPORT_SYMBOL_GPL(sbitmap_any_bit_clear); - static unsigned int __sbitmap_weight(const struct sbitmap *sb, bool set) { unsigned int i, weight = 0; -- cgit v1.2.3-71-gd317 From 3ad2522c64cff1f5aebb987b00683268f0cc7c29 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 29 Oct 2019 13:41:38 -0700 Subject: statx: define STATX_ATTR_VERITY Add a statx attribute bit STATX_ATTR_VERITY which will be set if the file has fs-verity enabled. This is the statx() equivalent of FS_VERITY_FL which is returned by FS_IOC_GETFLAGS. This is useful because it allows applications to check whether a file is a verity file without opening it. Opening a verity file can be expensive because the fsverity_info is set up on open, which involves parsing metadata and optionally verifying a cryptographic signature. This is analogous to how various other bits are exposed through both FS_IOC_GETFLAGS and statx(), e.g. the encrypt bit. Reviewed-by: Andreas Dilger Acked-by: Darrick J. Wong Signed-off-by: Eric Biggers --- include/linux/stat.h | 3 ++- include/uapi/linux/stat.h | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stat.h b/include/linux/stat.h index 765573dc17d6..528c4baad091 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -33,7 +33,8 @@ struct kstat { STATX_ATTR_IMMUTABLE | \ STATX_ATTR_APPEND | \ STATX_ATTR_NODUMP | \ - STATX_ATTR_ENCRYPTED \ + STATX_ATTR_ENCRYPTED | \ + STATX_ATTR_VERITY \ )/* Attrs corresponding to FS_*_FL flags */ u64 ino; dev_t dev; diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index 7b35e98d3c58..ad80a5c885d5 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -167,8 +167,8 @@ struct statx { #define STATX_ATTR_APPEND 0x00000020 /* [I] File is append-only */ #define STATX_ATTR_NODUMP 0x00000040 /* [I] File is not to be dumped */ #define STATX_ATTR_ENCRYPTED 0x00000800 /* [I] File requires key to decrypt in fs */ - #define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */ +#define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */ #endif /* _UAPI_LINUX_STAT_H */ -- cgit v1.2.3-71-gd317 From 975b992fdd4b38028d7c1dcf38286d6e7991c1b2 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 12 Nov 2019 00:34:29 +0100 Subject: net/mlx5: Add new chain for netfilter flow table offload Netfilter tables (nftables) implements a software datapath that comes after tc ingress datapath. The datapath supports offloading such rules via the flow table offload API. This API is currently only used by NFT and it doesn't provide the global priority in regards to tc offload, so we assume offloading such rules must come after tc. It does provide a flow table priority parameter, so we need to provide some supported priority range. For that, split fastpath prio to two, flow table offload and tc offload, with one dedicated priority chain for flow table offload. Next patch will re-use the multi chain API to access this chain by allowing access to this chain by the fdb_sub_namespace. Signed-off-by: Paul Blakey Reviewed-by: Mark Bloch Acked-by: Pablo Neira Ayuso Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 9 +++++++-- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 9 ++++++--- include/linux/mlx5/fs.h | 3 ++- 3 files changed, 15 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 8c9d8dc85861..2b563700c664 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -44,7 +44,12 @@ #include "lib/mpfs.h" #define FDB_TC_MAX_CHAIN 3 -#define FDB_TC_SLOW_PATH_CHAIN (FDB_TC_MAX_CHAIN + 1) +#define FDB_FT_CHAIN (FDB_TC_MAX_CHAIN + 1) +#define FDB_TC_SLOW_PATH_CHAIN (FDB_FT_CHAIN + 1) + +/* The index of the last real chain (FT) + 1 as chain zero is valid as well */ +#define FDB_NUM_CHAINS (FDB_FT_CHAIN + 1) + #define FDB_TC_MAX_PRIO 16 #define FDB_TC_LEVELS_PER_PRIO 2 @@ -173,7 +178,7 @@ struct mlx5_eswitch_fdb { struct { struct mlx5_flow_table *fdb; u32 num_rules; - } fdb_prio[FDB_TC_MAX_CHAIN + 1][FDB_TC_MAX_PRIO + 1][FDB_TC_LEVELS_PER_PRIO]; + } fdb_prio[FDB_NUM_CHAINS][FDB_TC_MAX_PRIO + 1][FDB_TC_LEVELS_PER_PRIO]; /* Protects fdb_prio table */ struct mutex fdb_prio_lock; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 4aa6990a38b3..84e90b21e148 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2624,16 +2624,19 @@ static int create_fdb_chains(struct mlx5_flow_steering *steering, static int create_fdb_fast_path(struct mlx5_flow_steering *steering) { - const int total_chains = FDB_TC_MAX_CHAIN + 1; int err; - steering->fdb_sub_ns = kcalloc(total_chains, + steering->fdb_sub_ns = kcalloc(FDB_NUM_CHAINS, sizeof(*steering->fdb_sub_ns), GFP_KERNEL); if (!steering->fdb_sub_ns) return -ENOMEM; - err = create_fdb_chains(steering, FDB_FAST_PATH, FDB_TC_MAX_CHAIN + 1); + err = create_fdb_chains(steering, FDB_TC_OFFLOAD, FDB_TC_MAX_CHAIN + 1); + if (err) + return err; + + err = create_fdb_chains(steering, FDB_FT_OFFLOAD, 1); if (err) return err; diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 724d276ea133..4e5b84e66822 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -80,7 +80,8 @@ enum mlx5_flow_namespace_type { enum { FDB_BYPASS_PATH, - FDB_FAST_PATH, + FDB_TC_OFFLOAD, + FDB_FT_OFFLOAD, FDB_SLOW_PATH, }; -- cgit v1.2.3-71-gd317 From bf49d9dd6fef688733e2ddbd55f7bcb57df194e4 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 18 Oct 2019 13:50:53 +0900 Subject: export,module: add SPDX GPL-2.0 license identifier to headers with no license Commit b24413180f56 ("License cleanup: add SPDX GPL-2.0 license identifier to files with no license") took care of a lot of files without any license information. These headers were not processed by the tool perhaps because they contain "GPL" in the code. I do not see any license boilerplate in them, so they fall back to GPL version 2 only, which is the project default. Signed-off-by: Masahiro Yamada Link: https://lore.kernel.org/r/20191018045053.8424-1-yamada.masahiro@socionext.com Signed-off-by: Greg Kroah-Hartman --- include/asm-generic/export.h | 1 + include/linux/export.h | 1 + include/linux/license.h | 1 + include/linux/module.h | 7 +++++-- 4 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/asm-generic/export.h b/include/asm-generic/export.h index fa577978fbbd..d0166115a825 100644 --- a/include/asm-generic/export.h +++ b/include/asm-generic/export.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ #ifndef __ASM_GENERIC_EXPORT_H #define __ASM_GENERIC_EXPORT_H diff --git a/include/linux/export.h b/include/linux/export.h index 941d075f03d6..aee5c86ae350 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ #ifndef _LINUX_EXPORT_H #define _LINUX_EXPORT_H diff --git a/include/linux/license.h b/include/linux/license.h index decdbf43cb5c..7cce390f120b 100644 --- a/include/linux/license.h +++ b/include/linux/license.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ #ifndef __LICENSE_H #define __LICENSE_H diff --git a/include/linux/module.h b/include/linux/module.h index 6d20895e7739..bd165ba68617 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -1,11 +1,14 @@ -#ifndef _LINUX_MODULE_H -#define _LINUX_MODULE_H +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Dynamic loading of modules into the kernel. * * Rewritten by Richard Henderson Dec 1996 * Rewritten again by Rusty Russell, 2002 */ + +#ifndef _LINUX_MODULE_H +#define _LINUX_MODULE_H + #include #include #include -- cgit v1.2.3-71-gd317 From 46549769d0512e44c5a08ae2dd05cebe55b3db16 Mon Sep 17 00:00:00 2001 From: Dhanuka Warusadura Date: Mon, 28 Oct 2019 16:37:44 +0530 Subject: w1: Fix documentation warning. This patch fixes - warning: Function parameter or member 'of_match_table' not described in 'w1_family' Signed-off-by: Dhanuka Warusadura Link: https://lore.kernel.org/r/20191028110744.6523-1-csx@disroot.org Signed-off-by: Greg Kroah-Hartman --- include/linux/w1.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/w1.h b/include/linux/w1.h index 7da0c7588e04..cebf3464bc03 100644 --- a/include/linux/w1.h +++ b/include/linux/w1.h @@ -262,6 +262,7 @@ struct w1_family_ops { * @family_entry: family linked list * @fid: 8 bit family identifier * @fops: operations for this family + * @of_match_table: open firmware match table * @refcnt: reference counter */ struct w1_family { -- cgit v1.2.3-71-gd317 From edb44e8461cfb9da8fd7a60d1ded2912a01100be Mon Sep 17 00:00:00 2001 From: "Ben Dooks (Codethink)" Date: Tue, 22 Oct 2019 09:43:23 +0100 Subject: cpu-topology: declare parse_acpi_topology in The parse_acpi_topology() is not declared anywhere which causes the following sparse warning: drivers/base/arch_topology.c:522:19: warning: symbol 'parse_acpi_topology' was not declared. Should it be static? Signed-off-by: Ben Dooks (Codethink) Acked-by: Sudeep Holla Link: https://lore.kernel.org/r/20191022084323.13594-1-ben.dooks@codethink.co.uk Signed-off-by: Greg Kroah-Hartman --- include/linux/arch_topology.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index 42f2b5126094..3015ecbb90b1 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -57,6 +57,7 @@ const struct cpumask *cpu_coregroup_mask(int cpu); void update_siblings_masks(unsigned int cpu); void remove_cpu_topology(unsigned int cpuid); void reset_cpu_topology(void); +int parse_acpi_topology(void); #endif #endif /* _LINUX_ARCH_TOPOLOGY_H_ */ -- cgit v1.2.3-71-gd317 From c0e5f4e73a7148e18b763067d181661987cb4c09 Mon Sep 17 00:00:00 2001 From: Rui Feng Date: Mon, 21 Oct 2019 16:05:05 +0800 Subject: misc: rtsx: Add support for RTS5261 Add support for new chip rts5261. In order to support rts5261, the definitions of some internal registers and workflow have to be modified and are different from its predecessors. So we need this patch to ensure RTS5261 can work. Signed-off-by: Rui Feng Link: https://lore.kernel.org/r/1571645105-5028-1-git-send-email-rui_feng@realsil.com.cn Signed-off-by: Greg Kroah-Hartman --- drivers/misc/cardreader/Makefile | 2 +- drivers/misc/cardreader/rts5261.c | 792 +++++++++++++++++++++++++++++++++++++ drivers/misc/cardreader/rts5261.h | 233 +++++++++++ drivers/misc/cardreader/rtsx_pcr.c | 43 +- drivers/misc/cardreader/rtsx_pcr.h | 1 + include/linux/rtsx_pci.h | 1 + 6 files changed, 1064 insertions(+), 8 deletions(-) create mode 100644 drivers/misc/cardreader/rts5261.c create mode 100644 drivers/misc/cardreader/rts5261.h (limited to 'include/linux') diff --git a/drivers/misc/cardreader/Makefile b/drivers/misc/cardreader/Makefile index d9bff5a2217e..1f56267ed2f4 100644 --- a/drivers/misc/cardreader/Makefile +++ b/drivers/misc/cardreader/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_MISC_ALCOR_PCI) += alcor_pci.o obj-$(CONFIG_MISC_RTSX_PCI) += rtsx_pci.o -rtsx_pci-objs := rtsx_pcr.o rts5209.o rts5229.o rtl8411.o rts5227.o rts5249.o rts5260.o +rtsx_pci-objs := rtsx_pcr.o rts5209.o rts5229.o rtl8411.o rts5227.o rts5249.o rts5260.o rts5261.o obj-$(CONFIG_MISC_RTSX_USB) += rtsx_usb.o diff --git a/drivers/misc/cardreader/rts5261.c b/drivers/misc/cardreader/rts5261.c new file mode 100644 index 000000000000..32dcec2e9dfd --- /dev/null +++ b/drivers/misc/cardreader/rts5261.c @@ -0,0 +1,792 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Driver for Realtek PCI-Express card reader + * + * Copyright(c) 2018-2019 Realtek Semiconductor Corp. All rights reserved. + * + * Author: + * Rui FENG + * Wei WANG + */ + +#include +#include +#include + +#include "rts5261.h" +#include "rtsx_pcr.h" + +static u8 rts5261_get_ic_version(struct rtsx_pcr *pcr) +{ + u8 val; + + rtsx_pci_read_register(pcr, DUMMY_REG_RESET_0, &val); + return val & IC_VERSION_MASK; +} + +static void rts5261_fill_driving(struct rtsx_pcr *pcr, u8 voltage) +{ + u8 driving_3v3[4][3] = { + {0x13, 0x13, 0x13}, + {0x96, 0x96, 0x96}, + {0x7F, 0x7F, 0x7F}, + {0x96, 0x96, 0x96}, + }; + u8 driving_1v8[4][3] = { + {0x99, 0x99, 0x99}, + {0x3A, 0x3A, 0x3A}, + {0xE6, 0xE6, 0xE6}, + {0xB3, 0xB3, 0xB3}, + }; + u8 (*driving)[3], drive_sel; + + if (voltage == OUTPUT_3V3) { + driving = driving_3v3; + drive_sel = pcr->sd30_drive_sel_3v3; + } else { + driving = driving_1v8; + drive_sel = pcr->sd30_drive_sel_1v8; + } + + rtsx_pci_write_register(pcr, SD30_CLK_DRIVE_SEL, + 0xFF, driving[drive_sel][0]); + + rtsx_pci_write_register(pcr, SD30_CMD_DRIVE_SEL, + 0xFF, driving[drive_sel][1]); + + rtsx_pci_write_register(pcr, SD30_DAT_DRIVE_SEL, + 0xFF, driving[drive_sel][2]); +} + +static void rtsx5261_fetch_vendor_settings(struct rtsx_pcr *pcr) +{ + u32 reg; + /* 0x814~0x817 */ + rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG2, ®); + pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG2, reg); + + if (!rts5261_vendor_setting_valid(reg)) { + pcr_dbg(pcr, "skip fetch vendor setting\n"); + return; + } + + pcr->card_drive_sel &= 0x3F; + pcr->card_drive_sel |= rts5261_reg_to_card_drive_sel(reg); + + if (rts5261_reg_check_reverse_socket(reg)) + pcr->flags |= PCR_REVERSE_SOCKET; + + /* 0x724~0x727 */ + rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG1, ®); + pcr_dbg(pcr, "Cfg 0x%x: 0x%x\n", PCR_SETTING_REG1, reg); + + pcr->aspm_en = rts5261_reg_to_aspm(reg); + pcr->sd30_drive_sel_1v8 = rts5261_reg_to_sd30_drive_sel_1v8(reg); + pcr->sd30_drive_sel_3v3 = rts5261_reg_to_sd30_drive_sel_3v3(reg); +} + +static void rts5261_force_power_down(struct rtsx_pcr *pcr, u8 pm_state) +{ + /* Set relink_time to 0 */ + rtsx_pci_write_register(pcr, AUTOLOAD_CFG_BASE + 1, MASK_8_BIT_DEF, 0); + rtsx_pci_write_register(pcr, AUTOLOAD_CFG_BASE + 2, MASK_8_BIT_DEF, 0); + rtsx_pci_write_register(pcr, AUTOLOAD_CFG_BASE + 3, + RELINK_TIME_MASK, 0); + + if (pm_state == HOST_ENTER_S3) + rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, + D3_DELINK_MODE_EN, D3_DELINK_MODE_EN); + + rtsx_pci_write_register(pcr, RTS5261_REG_FPDCTL, + SSC_POWER_DOWN, SSC_POWER_DOWN); +} + +static int rts5261_enable_auto_blink(struct rtsx_pcr *pcr) +{ + return rtsx_pci_write_register(pcr, OLT_LED_CTL, + LED_SHINE_MASK, LED_SHINE_EN); +} + +static int rts5261_disable_auto_blink(struct rtsx_pcr *pcr) +{ + return rtsx_pci_write_register(pcr, OLT_LED_CTL, + LED_SHINE_MASK, LED_SHINE_DISABLE); +} + +static int rts5261_turn_on_led(struct rtsx_pcr *pcr) +{ + return rtsx_pci_write_register(pcr, GPIO_CTL, + 0x02, 0x02); +} + +static int rts5261_turn_off_led(struct rtsx_pcr *pcr) +{ + return rtsx_pci_write_register(pcr, GPIO_CTL, + 0x02, 0x00); +} + +/* SD Pull Control Enable: + * SD_DAT[3:0] ==> pull up + * SD_CD ==> pull up + * SD_WP ==> pull up + * SD_CMD ==> pull up + * SD_CLK ==> pull down + */ +static const u32 rts5261_sd_pull_ctl_enable_tbl[] = { + RTSX_REG_PAIR(CARD_PULL_CTL2, 0xAA), + RTSX_REG_PAIR(CARD_PULL_CTL3, 0xE9), + 0, +}; + +/* SD Pull Control Disable: + * SD_DAT[3:0] ==> pull down + * SD_CD ==> pull up + * SD_WP ==> pull down + * SD_CMD ==> pull down + * SD_CLK ==> pull down + */ +static const u32 rts5261_sd_pull_ctl_disable_tbl[] = { + RTSX_REG_PAIR(CARD_PULL_CTL2, 0x55), + RTSX_REG_PAIR(CARD_PULL_CTL3, 0xD5), + 0, +}; + +static int rts5261_sd_set_sample_push_timing_sd30(struct rtsx_pcr *pcr) +{ + rtsx_pci_write_register(pcr, SD_CFG1, SD_MODE_SELECT_MASK + | SD_ASYNC_FIFO_NOT_RST, SD_30_MODE | SD_ASYNC_FIFO_NOT_RST); + rtsx_pci_write_register(pcr, CLK_CTL, CLK_LOW_FREQ, CLK_LOW_FREQ); + rtsx_pci_write_register(pcr, CARD_CLK_SOURCE, 0xFF, + CRC_VAR_CLK0 | SD30_FIX_CLK | SAMPLE_VAR_CLK1); + rtsx_pci_write_register(pcr, CLK_CTL, CLK_LOW_FREQ, 0); + + return 0; +} + +static int rts5261_card_power_on(struct rtsx_pcr *pcr, int card) +{ + struct rtsx_cr_option *option = &pcr->option; + + if (option->ocp_en) + rtsx_pci_enable_ocp(pcr); + + + rtsx_pci_write_register(pcr, RTS5261_LDO1_CFG1, + RTS5261_LDO1_TUNE_MASK, RTS5261_LDO1_33); + rtsx_pci_write_register(pcr, RTS5261_LDO1233318_POW_CTL, + RTS5261_LDO1_POWERON, RTS5261_LDO1_POWERON); + + rtsx_pci_write_register(pcr, RTS5261_LDO1233318_POW_CTL, + RTS5261_LDO3318_POWERON, RTS5261_LDO3318_POWERON); + + msleep(20); + + rtsx_pci_write_register(pcr, CARD_OE, SD_OUTPUT_EN, SD_OUTPUT_EN); + + /* Initialize SD_CFG1 register */ + rtsx_pci_write_register(pcr, SD_CFG1, 0xFF, + SD_CLK_DIVIDE_128 | SD_20_MODE | SD_BUS_WIDTH_1BIT); + + rtsx_pci_write_register(pcr, SD_SAMPLE_POINT_CTL, + 0xFF, SD20_RX_POS_EDGE); + rtsx_pci_write_register(pcr, SD_PUSH_POINT_CTL, 0xFF, 0); + rtsx_pci_write_register(pcr, CARD_STOP, SD_STOP | SD_CLR_ERR, + SD_STOP | SD_CLR_ERR); + + /* Reset SD_CFG3 register */ + rtsx_pci_write_register(pcr, SD_CFG3, SD30_CLK_END_EN, 0); + rtsx_pci_write_register(pcr, REG_SD_STOP_SDCLK_CFG, + SD30_CLK_STOP_CFG_EN | SD30_CLK_STOP_CFG1 | + SD30_CLK_STOP_CFG0, 0); + + if (pcr->extra_caps & EXTRA_CAPS_SD_SDR50 || + pcr->extra_caps & EXTRA_CAPS_SD_SDR104) + rts5261_sd_set_sample_push_timing_sd30(pcr); + + return 0; +} + +static int rts5261_switch_output_voltage(struct rtsx_pcr *pcr, u8 voltage) +{ + int err; + u16 val = 0; + + rtsx_pci_write_register(pcr, RTS5261_CARD_PWR_CTL, + RTS5261_PUPDC, RTS5261_PUPDC); + + switch (voltage) { + case OUTPUT_3V3: + rtsx_pci_read_phy_register(pcr, PHY_TUNE, &val); + val |= PHY_TUNE_SDBUS_33; + err = rtsx_pci_write_phy_register(pcr, PHY_TUNE, val); + if (err < 0) + return err; + + rtsx_pci_write_register(pcr, RTS5261_DV3318_CFG, + RTS5261_DV3318_TUNE_MASK, RTS5261_DV3318_33); + rtsx_pci_write_register(pcr, SD_PAD_CTL, + SD_IO_USING_1V8, 0); + break; + case OUTPUT_1V8: + rtsx_pci_read_phy_register(pcr, PHY_TUNE, &val); + val &= ~PHY_TUNE_SDBUS_33; + err = rtsx_pci_write_phy_register(pcr, PHY_TUNE, val); + if (err < 0) + return err; + + rtsx_pci_write_register(pcr, RTS5261_DV3318_CFG, + RTS5261_DV3318_TUNE_MASK, RTS5261_DV3318_18); + rtsx_pci_write_register(pcr, SD_PAD_CTL, + SD_IO_USING_1V8, SD_IO_USING_1V8); + break; + default: + return -EINVAL; + } + + /* set pad drive */ + rts5261_fill_driving(pcr, voltage); + + return 0; +} + +static void rts5261_stop_cmd(struct rtsx_pcr *pcr) +{ + rtsx_pci_writel(pcr, RTSX_HCBCTLR, STOP_CMD); + rtsx_pci_writel(pcr, RTSX_HDBCTLR, STOP_DMA); + rtsx_pci_write_register(pcr, RTS5260_DMA_RST_CTL_0, + RTS5260_DMA_RST | RTS5260_ADMA3_RST, + RTS5260_DMA_RST | RTS5260_ADMA3_RST); + rtsx_pci_write_register(pcr, RBCTL, RB_FLUSH, RB_FLUSH); +} + +static void rts5261_card_before_power_off(struct rtsx_pcr *pcr) +{ + rts5261_stop_cmd(pcr); + rts5261_switch_output_voltage(pcr, OUTPUT_3V3); + +} + +static void rts5261_enable_ocp(struct rtsx_pcr *pcr) +{ + u8 val = 0; + + val = SD_OCP_INT_EN | SD_DETECT_EN; + rtsx_pci_write_register(pcr, REG_OCPCTL, 0xFF, val); + +} + +static void rts5261_disable_ocp(struct rtsx_pcr *pcr) +{ + u8 mask = 0; + + mask = SD_OCP_INT_EN | SD_DETECT_EN; + rtsx_pci_write_register(pcr, REG_OCPCTL, mask, 0); + rtsx_pci_write_register(pcr, RTS5261_LDO1_CFG0, + RTS5261_LDO1_OCP_EN | RTS5261_LDO1_OCP_LMT_EN, 0); + +} + +static int rts5261_card_power_off(struct rtsx_pcr *pcr, int card) +{ + int err = 0; + + rts5261_card_before_power_off(pcr); + err = rtsx_pci_write_register(pcr, RTS5261_LDO1233318_POW_CTL, + RTS5261_LDO_POWERON_MASK, 0); + + if (pcr->option.ocp_en) + rtsx_pci_disable_ocp(pcr); + + return err; +} + +static void rts5261_init_ocp(struct rtsx_pcr *pcr) +{ + struct rtsx_cr_option *option = &pcr->option; + + if (option->ocp_en) { + u8 mask, val; + + rtsx_pci_write_register(pcr, RTS5261_LDO1_CFG0, + RTS5261_LDO1_OCP_EN | RTS5261_LDO1_OCP_LMT_EN, + RTS5261_LDO1_OCP_EN | RTS5261_LDO1_OCP_LMT_EN); + + rtsx_pci_write_register(pcr, RTS5261_LDO1_CFG0, + RTS5261_LDO1_OCP_THD_MASK, option->sd_800mA_ocp_thd); + + rtsx_pci_write_register(pcr, RTS5261_LDO1_CFG0, + RTS5261_LDO1_OCP_LMT_THD_MASK, + RTS5261_LDO1_LMT_THD_2000); + + mask = SD_OCP_GLITCH_MASK; + val = pcr->hw_param.ocp_glitch; + rtsx_pci_write_register(pcr, REG_OCPGLITCH, mask, val); + + rts5261_enable_ocp(pcr); + } else { + rtsx_pci_write_register(pcr, RTS5261_LDO1_CFG0, + RTS5261_LDO1_OCP_EN | RTS5261_LDO1_OCP_LMT_EN, 0); + } +} + +static void rts5261_clear_ocpstat(struct rtsx_pcr *pcr) +{ + u8 mask = 0; + u8 val = 0; + + mask = SD_OCP_INT_CLR | SD_OC_CLR; + val = SD_OCP_INT_CLR | SD_OC_CLR; + + rtsx_pci_write_register(pcr, REG_OCPCTL, mask, val); + + udelay(10); + rtsx_pci_write_register(pcr, REG_OCPCTL, mask, 0); + +} + +static void rts5261_process_ocp(struct rtsx_pcr *pcr) +{ + if (!pcr->option.ocp_en) + return; + + rtsx_pci_get_ocpstat(pcr, &pcr->ocp_stat); + + if (pcr->ocp_stat & (SD_OC_NOW | SD_OC_EVER)) { + rts5261_card_power_off(pcr, RTSX_SD_CARD); + rtsx_pci_write_register(pcr, CARD_OE, SD_OUTPUT_EN, 0); + rts5261_clear_ocpstat(pcr); + pcr->ocp_stat = 0; + } + +} + +static int rts5261_init_from_hw(struct rtsx_pcr *pcr) +{ + int retval; + u32 lval, i; + u8 valid, efuse_valid, tmp; + + rtsx_pci_write_register(pcr, RTS5261_REG_PME_FORCE_CTL, + REG_EFUSE_POR | REG_EFUSE_POWER_MASK, + REG_EFUSE_POR | REG_EFUSE_POWERON); + udelay(1); + rtsx_pci_write_register(pcr, RTS5261_EFUSE_ADDR, + RTS5261_EFUSE_ADDR_MASK, 0x00); + rtsx_pci_write_register(pcr, RTS5261_EFUSE_CTL, + RTS5261_EFUSE_ENABLE | RTS5261_EFUSE_MODE_MASK, + RTS5261_EFUSE_ENABLE); + + /* Wait transfer end */ + for (i = 0; i < MAX_RW_REG_CNT; i++) { + rtsx_pci_read_register(pcr, RTS5261_EFUSE_CTL, &tmp); + if ((tmp & 0x80) == 0) + break; + } + rtsx_pci_read_register(pcr, RTS5261_EFUSE_READ_DATA, &tmp); + efuse_valid = ((tmp & 0x0C) >> 2); + pcr_dbg(pcr, "Load efuse valid: 0x%x\n", efuse_valid); + + if (efuse_valid == 0) { + retval = rtsx_pci_read_config_dword(pcr, + PCR_SETTING_REG2, &lval); + if (retval != 0) + pcr_dbg(pcr, "read 0x814 DW fail\n"); + pcr_dbg(pcr, "DW from 0x814: 0x%x\n", lval); + /* 0x816 */ + valid = (u8)((lval >> 16) & 0x03); + pcr_dbg(pcr, "0x816: %d\n", valid); + } + rtsx_pci_write_register(pcr, RTS5261_REG_PME_FORCE_CTL, + REG_EFUSE_POR, 0); + pcr_dbg(pcr, "Disable efuse por!\n"); + + rtsx_pci_read_config_dword(pcr, PCR_SETTING_REG2, &lval); + lval = lval & 0x00FFFFFF; + retval = rtsx_pci_write_config_dword(pcr, PCR_SETTING_REG2, lval); + if (retval != 0) + pcr_dbg(pcr, "write config fail\n"); + + return retval; +} + +static void rts5261_init_from_cfg(struct rtsx_pcr *pcr) +{ + u32 lval; + struct rtsx_cr_option *option = &pcr->option; + + rtsx_pci_read_config_dword(pcr, PCR_ASPM_SETTING_REG1, &lval); + + if (lval & ASPM_L1_1_EN_MASK) + rtsx_set_dev_flag(pcr, ASPM_L1_1_EN); + else + rtsx_clear_dev_flag(pcr, ASPM_L1_1_EN); + + if (lval & ASPM_L1_2_EN_MASK) + rtsx_set_dev_flag(pcr, ASPM_L1_2_EN); + else + rtsx_clear_dev_flag(pcr, ASPM_L1_2_EN); + + if (lval & PM_L1_1_EN_MASK) + rtsx_set_dev_flag(pcr, PM_L1_1_EN); + else + rtsx_clear_dev_flag(pcr, PM_L1_1_EN); + + if (lval & PM_L1_2_EN_MASK) + rtsx_set_dev_flag(pcr, PM_L1_2_EN); + else + rtsx_clear_dev_flag(pcr, PM_L1_2_EN); + + rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, 0xFF, 0); + if (option->ltr_en) { + u16 val; + + pcie_capability_read_word(pcr->pci, PCI_EXP_DEVCTL2, &val); + if (val & PCI_EXP_DEVCTL2_LTR_EN) { + option->ltr_enabled = true; + option->ltr_active = true; + rtsx_set_ltr_latency(pcr, option->ltr_active_latency); + } else { + option->ltr_enabled = false; + } + } + + if (rtsx_check_dev_flag(pcr, ASPM_L1_1_EN | ASPM_L1_2_EN + | PM_L1_1_EN | PM_L1_2_EN)) + option->force_clkreq_0 = false; + else + option->force_clkreq_0 = true; +} + +static int rts5261_extra_init_hw(struct rtsx_pcr *pcr) +{ + struct rtsx_cr_option *option = &pcr->option; + + rtsx_pci_write_register(pcr, RTS5261_AUTOLOAD_CFG1, + CD_RESUME_EN_MASK, CD_RESUME_EN_MASK); + + rts5261_init_from_cfg(pcr); + rts5261_init_from_hw(pcr); + + /* power off efuse */ + rtsx_pci_write_register(pcr, RTS5261_REG_PME_FORCE_CTL, + REG_EFUSE_POWER_MASK, REG_EFUSE_POWEROFF); + rtsx_pci_write_register(pcr, L1SUB_CONFIG1, + AUX_CLK_ACTIVE_SEL_MASK, MAC_CKSW_DONE); + rtsx_pci_write_register(pcr, L1SUB_CONFIG3, 0xFF, 0); + + rtsx_pci_write_register(pcr, RTS5261_AUTOLOAD_CFG4, + RTS5261_AUX_CLK_16M_EN, 0); + + /* Release PRSNT# */ + rtsx_pci_write_register(pcr, RTS5261_AUTOLOAD_CFG4, + RTS5261_FORCE_PRSNT_LOW, 0); + rtsx_pci_write_register(pcr, FUNC_FORCE_CTL, + FUNC_FORCE_UPME_XMT_DBG, FUNC_FORCE_UPME_XMT_DBG); + + rtsx_pci_write_register(pcr, PCLK_CTL, + PCLK_MODE_SEL, PCLK_MODE_SEL); + + rtsx_pci_write_register(pcr, PM_EVENT_DEBUG, PME_DEBUG_0, PME_DEBUG_0); + rtsx_pci_write_register(pcr, PM_CLK_FORCE_CTL, CLK_PM_EN, CLK_PM_EN); + + /* LED shine disabled, set initial shine cycle period */ + rtsx_pci_write_register(pcr, OLT_LED_CTL, 0x0F, 0x02); + + /* Configure driving */ + rts5261_fill_driving(pcr, OUTPUT_3V3); + + /* + * If u_force_clkreq_0 is enabled, CLKREQ# PIN will be forced + * to drive low, and we forcibly request clock. + */ + if (option->force_clkreq_0) + rtsx_pci_write_register(pcr, PETXCFG, + FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_LOW); + else + rtsx_pci_write_register(pcr, PETXCFG, + FORCE_CLKREQ_DELINK_MASK, FORCE_CLKREQ_HIGH); + + rtsx_pci_write_register(pcr, pcr->reg_pm_ctrl3, 0x10, 0x00); + rtsx_pci_write_register(pcr, RTS5261_REG_PME_FORCE_CTL, + FORCE_PM_CONTROL | FORCE_PM_VALUE, FORCE_PM_CONTROL); + + /* Clear Enter RTD3_cold Information*/ + rtsx_pci_write_register(pcr, RTS5261_FW_CTL, + RTS5261_INFORM_RTD3_COLD, 0); + + return 0; +} + +static void rts5261_enable_aspm(struct rtsx_pcr *pcr, bool enable) +{ + struct rtsx_cr_option *option = &pcr->option; + u8 val = 0; + + if (pcr->aspm_enabled == enable) + return; + + if (option->dev_aspm_mode == DEV_ASPM_DYNAMIC) { + val = pcr->aspm_en; + rtsx_pci_update_cfg_byte(pcr, pcr->pcie_cap + PCI_EXP_LNKCTL, + ASPM_MASK_NEG, val); + } else if (option->dev_aspm_mode == DEV_ASPM_BACKDOOR) { + u8 mask = FORCE_ASPM_VAL_MASK | FORCE_ASPM_CTL0; + + val = FORCE_ASPM_CTL0; + val |= (pcr->aspm_en & 0x02); + rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, mask, val); + val = pcr->aspm_en; + rtsx_pci_update_cfg_byte(pcr, pcr->pcie_cap + PCI_EXP_LNKCTL, + ASPM_MASK_NEG, val); + } + pcr->aspm_enabled = enable; + +} + +static void rts5261_disable_aspm(struct rtsx_pcr *pcr, bool enable) +{ + struct rtsx_cr_option *option = &pcr->option; + u8 val = 0; + + if (pcr->aspm_enabled == enable) + return; + + if (option->dev_aspm_mode == DEV_ASPM_DYNAMIC) { + val = 0; + rtsx_pci_update_cfg_byte(pcr, pcr->pcie_cap + PCI_EXP_LNKCTL, + ASPM_MASK_NEG, val); + } else if (option->dev_aspm_mode == DEV_ASPM_BACKDOOR) { + u8 mask = FORCE_ASPM_VAL_MASK | FORCE_ASPM_CTL0; + + val = 0; + rtsx_pci_update_cfg_byte(pcr, pcr->pcie_cap + PCI_EXP_LNKCTL, + ASPM_MASK_NEG, val); + val = FORCE_ASPM_CTL0; + rtsx_pci_write_register(pcr, ASPM_FORCE_CTL, mask, val); + } + rtsx_pci_write_register(pcr, SD_CFG1, SD_ASYNC_FIFO_NOT_RST, 0); + udelay(10); + pcr->aspm_enabled = enable; +} + +static void rts5261_set_aspm(struct rtsx_pcr *pcr, bool enable) +{ + if (enable) + rts5261_enable_aspm(pcr, true); + else + rts5261_disable_aspm(pcr, false); +} + +static void rts5261_set_l1off_cfg_sub_d0(struct rtsx_pcr *pcr, int active) +{ + struct rtsx_cr_option *option = &pcr->option; + int aspm_L1_1, aspm_L1_2; + u8 val = 0; + + aspm_L1_1 = rtsx_check_dev_flag(pcr, ASPM_L1_1_EN); + aspm_L1_2 = rtsx_check_dev_flag(pcr, ASPM_L1_2_EN); + + if (active) { + /* run, latency: 60us */ + if (aspm_L1_1) + val = option->ltr_l1off_snooze_sspwrgate; + } else { + /* l1off, latency: 300us */ + if (aspm_L1_2) + val = option->ltr_l1off_sspwrgate; + } + + rtsx_set_l1off_sub(pcr, val); +} + +static const struct pcr_ops rts5261_pcr_ops = { + .fetch_vendor_settings = rtsx5261_fetch_vendor_settings, + .turn_on_led = rts5261_turn_on_led, + .turn_off_led = rts5261_turn_off_led, + .extra_init_hw = rts5261_extra_init_hw, + .enable_auto_blink = rts5261_enable_auto_blink, + .disable_auto_blink = rts5261_disable_auto_blink, + .card_power_on = rts5261_card_power_on, + .card_power_off = rts5261_card_power_off, + .switch_output_voltage = rts5261_switch_output_voltage, + .force_power_down = rts5261_force_power_down, + .stop_cmd = rts5261_stop_cmd, + .set_aspm = rts5261_set_aspm, + .set_l1off_cfg_sub_d0 = rts5261_set_l1off_cfg_sub_d0, + .enable_ocp = rts5261_enable_ocp, + .disable_ocp = rts5261_disable_ocp, + .init_ocp = rts5261_init_ocp, + .process_ocp = rts5261_process_ocp, + .clear_ocpstat = rts5261_clear_ocpstat, +}; + +static inline u8 double_ssc_depth(u8 depth) +{ + return ((depth > 1) ? (depth - 1) : depth); +} + +int rts5261_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock, + u8 ssc_depth, bool initial_mode, bool double_clk, bool vpclk) +{ + int err, clk; + u8 n, clk_divider, mcu_cnt, div; + static const u8 depth[] = { + [RTSX_SSC_DEPTH_4M] = RTS5261_SSC_DEPTH_4M, + [RTSX_SSC_DEPTH_2M] = RTS5261_SSC_DEPTH_2M, + [RTSX_SSC_DEPTH_1M] = RTS5261_SSC_DEPTH_1M, + [RTSX_SSC_DEPTH_500K] = RTS5261_SSC_DEPTH_512K, + }; + + if (initial_mode) { + /* We use 250k(around) here, in initial stage */ + clk_divider = SD_CLK_DIVIDE_128; + card_clock = 30000000; + } else { + clk_divider = SD_CLK_DIVIDE_0; + } + err = rtsx_pci_write_register(pcr, SD_CFG1, + SD_CLK_DIVIDE_MASK, clk_divider); + if (err < 0) + return err; + + card_clock /= 1000000; + pcr_dbg(pcr, "Switch card clock to %dMHz\n", card_clock); + + clk = card_clock; + if (!initial_mode && double_clk) + clk = card_clock * 2; + pcr_dbg(pcr, "Internal SSC clock: %dMHz (cur_clock = %d)\n", + clk, pcr->cur_clock); + + if (clk == pcr->cur_clock) + return 0; + + if (pcr->ops->conv_clk_and_div_n) + n = (u8)pcr->ops->conv_clk_and_div_n(clk, CLK_TO_DIV_N); + else + n = (u8)(clk - 4); + if ((clk <= 4) || (n > 396)) + return -EINVAL; + + mcu_cnt = (u8)(125/clk + 3); + if (mcu_cnt > 15) + mcu_cnt = 15; + + div = CLK_DIV_1; + while ((n < MIN_DIV_N_PCR - 4) && (div < CLK_DIV_8)) { + if (pcr->ops->conv_clk_and_div_n) { + int dbl_clk = pcr->ops->conv_clk_and_div_n(n, + DIV_N_TO_CLK) * 2; + n = (u8)pcr->ops->conv_clk_and_div_n(dbl_clk, + CLK_TO_DIV_N); + } else { + n = (n + 4) * 2 - 4; + } + div++; + } + + n = (n / 2); + pcr_dbg(pcr, "n = %d, div = %d\n", n, div); + + ssc_depth = depth[ssc_depth]; + if (double_clk) + ssc_depth = double_ssc_depth(ssc_depth); + + if (ssc_depth) { + if (div == CLK_DIV_2) { + if (ssc_depth > 1) + ssc_depth -= 1; + else + ssc_depth = RTS5261_SSC_DEPTH_8M; + } else if (div == CLK_DIV_4) { + if (ssc_depth > 2) + ssc_depth -= 2; + else + ssc_depth = RTS5261_SSC_DEPTH_8M; + } else if (div == CLK_DIV_8) { + if (ssc_depth > 3) + ssc_depth -= 3; + else + ssc_depth = RTS5261_SSC_DEPTH_8M; + } + } else { + ssc_depth = 0; + } + pcr_dbg(pcr, "ssc_depth = %d\n", ssc_depth); + + rtsx_pci_init_cmd(pcr); + rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CLK_CTL, + CLK_LOW_FREQ, CLK_LOW_FREQ); + rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CLK_DIV, + 0xFF, (div << 4) | mcu_cnt); + rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1, SSC_RSTB, 0); + rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2, + SSC_DEPTH_MASK, ssc_depth); + rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_DIV_N_0, 0xFF, n); + rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1, SSC_RSTB, SSC_RSTB); + if (vpclk) { + rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK0_CTL, + PHASE_NOT_RESET, 0); + rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK1_CTL, + PHASE_NOT_RESET, 0); + rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK0_CTL, + PHASE_NOT_RESET, PHASE_NOT_RESET); + rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_VPCLK1_CTL, + PHASE_NOT_RESET, PHASE_NOT_RESET); + } + + err = rtsx_pci_send_cmd(pcr, 2000); + if (err < 0) + return err; + + /* Wait SSC clock stable */ + udelay(SSC_CLOCK_STABLE_WAIT); + err = rtsx_pci_write_register(pcr, CLK_CTL, CLK_LOW_FREQ, 0); + if (err < 0) + return err; + + pcr->cur_clock = clk; + return 0; + +} + +void rts5261_init_params(struct rtsx_pcr *pcr) +{ + struct rtsx_cr_option *option = &pcr->option; + struct rtsx_hw_param *hw_param = &pcr->hw_param; + + pcr->extra_caps = EXTRA_CAPS_SD_SDR50 | EXTRA_CAPS_SD_SDR104; + pcr->num_slots = 1; + pcr->ops = &rts5261_pcr_ops; + + pcr->flags = 0; + pcr->card_drive_sel = RTSX_CARD_DRIVE_DEFAULT; + pcr->sd30_drive_sel_1v8 = CFG_DRIVER_TYPE_B; + pcr->sd30_drive_sel_3v3 = CFG_DRIVER_TYPE_B; + pcr->aspm_en = ASPM_L1_EN; + pcr->tx_initial_phase = SET_CLOCK_PHASE(20, 27, 16); + pcr->rx_initial_phase = SET_CLOCK_PHASE(24, 6, 5); + + pcr->ic_version = rts5261_get_ic_version(pcr); + pcr->sd_pull_ctl_enable_tbl = rts5261_sd_pull_ctl_enable_tbl; + pcr->sd_pull_ctl_disable_tbl = rts5261_sd_pull_ctl_disable_tbl; + + pcr->reg_pm_ctrl3 = RTS5261_AUTOLOAD_CFG3; + + option->dev_flags = (LTR_L1SS_PWR_GATE_CHECK_CARD_EN + | LTR_L1SS_PWR_GATE_EN); + option->ltr_en = true; + + /* init latency of active, idle, L1OFF to 60us, 300us, 3ms */ + option->ltr_active_latency = LTR_ACTIVE_LATENCY_DEF; + option->ltr_idle_latency = LTR_IDLE_LATENCY_DEF; + option->ltr_l1off_latency = LTR_L1OFF_LATENCY_DEF; + option->l1_snooze_delay = L1_SNOOZE_DELAY_DEF; + option->ltr_l1off_sspwrgate = 0x7F; + option->ltr_l1off_snooze_sspwrgate = 0x78; + option->dev_aspm_mode = DEV_ASPM_DYNAMIC; + + option->ocp_en = 1; + hw_param->interrupt_en |= SD_OC_INT_EN; + hw_param->ocp_glitch = SD_OCP_GLITCH_800U; + option->sd_800mA_ocp_thd = RTS5261_LDO1_OCP_THD_1040; +} diff --git a/drivers/misc/cardreader/rts5261.h b/drivers/misc/cardreader/rts5261.h new file mode 100644 index 000000000000..ebfdd236a553 --- /dev/null +++ b/drivers/misc/cardreader/rts5261.h @@ -0,0 +1,233 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Driver for Realtek PCI-Express card reader + * + * Copyright(c) 2018-2019 Realtek Semiconductor Corp. All rights reserved. + * + * Author: + * Rui FENG + * Wei WANG + */ +#ifndef RTS5261_H +#define RTS5261_H + +/*New add*/ +#define rts5261_vendor_setting_valid(reg) ((reg) & 0x010000) +#define rts5261_reg_to_aspm(reg) (((reg) >> 28) ^ 0x03) +#define rts5261_reg_check_reverse_socket(reg) ((reg) & 0x04) +#define rts5261_reg_to_card_drive_sel(reg) ((((reg) >> 6) & 0x01) << 6) +#define rts5261_reg_to_sd30_drive_sel_1v8(reg) (((reg) >> 22) ^ 0x03) +#define rts5261_reg_to_sd30_drive_sel_3v3(reg) (((reg) >> 16) ^ 0x03) + + +#define RTS5261_AUTOLOAD_CFG0 0xFF7B +#define RTS5261_AUTOLOAD_CFG1 0xFF7C +#define RTS5261_AUTOLOAD_CFG2 0xFF7D +#define RTS5261_AUTOLOAD_CFG3 0xFF7E +#define RTS5261_AUTOLOAD_CFG4 0xFF7F +#define RTS5261_FORCE_PRSNT_LOW (1 << 6) +#define RTS5261_AUX_CLK_16M_EN (1 << 5) + +#define RTS5261_REG_VREF 0xFE97 +#define RTS5261_PWD_SUSPND_EN (1 << 4) + +#define RTS5261_PAD_H3L1 0xFF79 +#define PAD_GPIO_H3L1 (1 << 3) + +/* SSC_CTL2 0xFC12 */ +#define RTS5261_SSC_DEPTH_MASK 0x07 +#define RTS5261_SSC_DEPTH_DISALBE 0x00 +#define RTS5261_SSC_DEPTH_8M 0x01 +#define RTS5261_SSC_DEPTH_4M 0x02 +#define RTS5261_SSC_DEPTH_2M 0x03 +#define RTS5261_SSC_DEPTH_1M 0x04 +#define RTS5261_SSC_DEPTH_512K 0x05 +#define RTS5261_SSC_DEPTH_256K 0x06 +#define RTS5261_SSC_DEPTH_128K 0x07 + +/* efuse control register*/ +#define RTS5261_EFUSE_CTL 0xFC30 +#define RTS5261_EFUSE_ENABLE 0x80 +/* EFUSE_MODE: 0=READ 1=PROGRAM */ +#define RTS5261_EFUSE_MODE_MASK 0x40 +#define RTS5261_EFUSE_PROGRAM 0x40 + +#define RTS5261_EFUSE_ADDR 0xFC31 +#define RTS5261_EFUSE_ADDR_MASK 0x3F + +#define RTS5261_EFUSE_WRITE_DATA 0xFC32 +#define RTS5261_EFUSE_READ_DATA 0xFC34 + +/* DMACTL 0xFE2C */ +#define RTS5261_DMA_PACK_SIZE_MASK 0xF0 + +/* FW config info register */ +#define RTS5261_FW_CFG_INFO0 0xFF50 +#define RTS5261_FW_EXPRESS_TEST_MASK (0x01<<0) +#define RTS5261_FW_EA_MODE_MASK (0x01<<5) + +/* FW config register */ +#define RTS5261_FW_CFG0 0xFF54 +#define RTS5261_FW_ENTER_EXPRESS (0x01<<0) + +#define RTS5261_FW_CFG1 0xFF55 +#define RTS5261_SYS_CLK_SEL_MCU_CLK (0x01<<7) +#define RTS5261_CRC_CLK_SEL_MCU_CLK (0x01<<6) +#define RTS5261_FAKE_MCU_CLOCK_GATING (0x01<<5) +/*MCU_bus_mode_sel: 0=real 8051 1=fake mcu*/ +#define RTS5261_MCU_BUS_SEL_MASK (0x01<<4) +/*MCU_clock_sel:VerA 00=aux16M 01=aux400K 1x=REFCLK100M*/ +/*MCU_clock_sel:VerB 00=aux400K 01=aux16M 10=REFCLK100M*/ +#define RTS5261_MCU_CLOCK_SEL_MASK (0x03<<2) +#define RTS5261_MCU_CLOCK_SEL_16M (0x01<<2) +#define RTS5261_MCU_CLOCK_GATING (0x01<<1) +#define RTS5261_DRIVER_ENABLE_FW (0x01<<0) + +/* FW status register */ +#define RTS5261_FW_STATUS 0xFF56 +#define RTS5261_EXPRESS_LINK_FAIL_MASK (0x01<<7) + +/* FW control register */ +#define RTS5261_FW_CTL 0xFF5F +#define RTS5261_INFORM_RTD3_COLD (0x01<<5) + +#define RTS5261_REG_FPDCTL 0xFF60 + +#define RTS5261_REG_LDO12_CFG 0xFF6E +#define RTS5261_LDO12_VO_TUNE_MASK (0x07<<1) +#define RTS5261_LDO12_115 (0x03<<1) +#define RTS5261_LDO12_120 (0x04<<1) +#define RTS5261_LDO12_125 (0x05<<1) +#define RTS5261_LDO12_130 (0x06<<1) +#define RTS5261_LDO12_135 (0x07<<1) + +/* LDO control register */ +#define RTS5261_CARD_PWR_CTL 0xFD50 +#define RTS5261_SD_CLK_ISO (0x01<<7) +#define RTS5261_PAD_SD_DAT_FW_CTRL (0x01<<6) +#define RTS5261_PUPDC (0x01<<5) +#define RTS5261_SD_CMD_ISO (0x01<<4) +#define RTS5261_SD_DAT_ISO_MASK (0x0F<<0) + +#define RTS5261_LDO1233318_POW_CTL 0xFF70 +#define RTS5261_LDO3318_POWERON (0x01<<3) +#define RTS5261_LDO3_POWERON (0x01<<2) +#define RTS5261_LDO2_POWERON (0x01<<1) +#define RTS5261_LDO1_POWERON (0x01<<0) +#define RTS5261_LDO_POWERON_MASK (0x0F<<0) + +#define RTS5261_DV3318_CFG 0xFF71 +#define RTS5261_DV3318_TUNE_MASK (0x07<<4) +#define RTS5261_DV3318_18 (0x02<<4) +#define RTS5261_DV3318_19 (0x04<<4) +#define RTS5261_DV3318_33 (0x07<<4) + +#define RTS5261_LDO1_CFG0 0xFF72 +#define RTS5261_LDO1_OCP_THD_MASK (0x07<<5) +#define RTS5261_LDO1_OCP_EN (0x01<<4) +#define RTS5261_LDO1_OCP_LMT_THD_MASK (0x03<<2) +#define RTS5261_LDO1_OCP_LMT_EN (0x01<<1) + +/* CRD6603-433 190319 request changed */ +#define RTS5261_LDO1_OCP_THD_740 (0x00<<5) +#define RTS5261_LDO1_OCP_THD_800 (0x01<<5) +#define RTS5261_LDO1_OCP_THD_860 (0x02<<5) +#define RTS5261_LDO1_OCP_THD_920 (0x03<<5) +#define RTS5261_LDO1_OCP_THD_980 (0x04<<5) +#define RTS5261_LDO1_OCP_THD_1040 (0x05<<5) +#define RTS5261_LDO1_OCP_THD_1100 (0x06<<5) +#define RTS5261_LDO1_OCP_THD_1160 (0x07<<5) + +#define RTS5261_LDO1_LMT_THD_450 (0x00<<2) +#define RTS5261_LDO1_LMT_THD_1000 (0x01<<2) +#define RTS5261_LDO1_LMT_THD_1500 (0x02<<2) +#define RTS5261_LDO1_LMT_THD_2000 (0x03<<2) + +#define RTS5261_LDO1_CFG1 0xFF73 +#define RTS5261_LDO1_TUNE_MASK (0x07<<1) +#define RTS5261_LDO1_18 (0x05<<1) +#define RTS5261_LDO1_33 (0x07<<1) +#define RTS5261_LDO1_PWD_MASK (0x01<<0) + +#define RTS5261_LDO2_CFG0 0xFF74 +#define RTS5261_LDO2_OCP_THD_MASK (0x07<<5) +#define RTS5261_LDO2_OCP_EN (0x01<<4) +#define RTS5261_LDO2_OCP_LMT_THD_MASK (0x03<<2) +#define RTS5261_LDO2_OCP_LMT_EN (0x01<<1) + +#define RTS5261_LDO2_OCP_THD_620 (0x00<<5) +#define RTS5261_LDO2_OCP_THD_650 (0x01<<5) +#define RTS5261_LDO2_OCP_THD_680 (0x02<<5) +#define RTS5261_LDO2_OCP_THD_720 (0x03<<5) +#define RTS5261_LDO2_OCP_THD_750 (0x04<<5) +#define RTS5261_LDO2_OCP_THD_780 (0x05<<5) +#define RTS5261_LDO2_OCP_THD_810 (0x06<<5) +#define RTS5261_LDO2_OCP_THD_840 (0x07<<5) + +#define RTS5261_LDO2_CFG1 0xFF75 +#define RTS5261_LDO2_TUNE_MASK (0x07<<1) +#define RTS5261_LDO2_18 (0x05<<1) +#define RTS5261_LDO2_33 (0x07<<1) +#define RTS5261_LDO2_PWD_MASK (0x01<<0) + +#define RTS5261_LDO3_CFG0 0xFF76 +#define RTS5261_LDO3_OCP_THD_MASK (0x07<<5) +#define RTS5261_LDO3_OCP_EN (0x01<<4) +#define RTS5261_LDO3_OCP_LMT_THD_MASK (0x03<<2) +#define RTS5261_LDO3_OCP_LMT_EN (0x01<<1) + +#define RTS5261_LDO3_OCP_THD_620 (0x00<<5) +#define RTS5261_LDO3_OCP_THD_650 (0x01<<5) +#define RTS5261_LDO3_OCP_THD_680 (0x02<<5) +#define RTS5261_LDO3_OCP_THD_720 (0x03<<5) +#define RTS5261_LDO3_OCP_THD_750 (0x04<<5) +#define RTS5261_LDO3_OCP_THD_780 (0x05<<5) +#define RTS5261_LDO3_OCP_THD_810 (0x06<<5) +#define RTS5261_LDO3_OCP_THD_840 (0x07<<5) + +#define RTS5261_LDO3_CFG1 0xFF77 +#define RTS5261_LDO3_TUNE_MASK (0x07<<1) +#define RTS5261_LDO3_18 (0x05<<1) +#define RTS5261_LDO3_33 (0x07<<1) +#define RTS5261_LDO3_PWD_MASK (0x01<<0) + +#define RTS5261_REG_PME_FORCE_CTL 0xFF78 +#define FORCE_PM_CONTROL 0x20 +#define FORCE_PM_VALUE 0x10 +#define REG_EFUSE_BYPASS 0x08 +#define REG_EFUSE_POR 0x04 +#define REG_EFUSE_POWER_MASK 0x03 +#define REG_EFUSE_POWERON 0x03 +#define REG_EFUSE_POWEROFF 0x00 + + +/* Single LUN, support SD/SD EXPRESS */ +#define DEFAULT_SINGLE 0 +#define SD_LUN 1 +#define SD_EXPRESS_LUN 2 + +/* For Change_FPGA_SSCClock Function */ +#define MULTIPLY_BY_1 0x00 +#define MULTIPLY_BY_2 0x01 +#define MULTIPLY_BY_3 0x02 +#define MULTIPLY_BY_4 0x03 +#define MULTIPLY_BY_5 0x04 +#define MULTIPLY_BY_6 0x05 +#define MULTIPLY_BY_7 0x06 +#define MULTIPLY_BY_8 0x07 +#define MULTIPLY_BY_9 0x08 +#define MULTIPLY_BY_10 0x09 + +#define DIVIDE_BY_2 0x01 +#define DIVIDE_BY_3 0x02 +#define DIVIDE_BY_4 0x03 +#define DIVIDE_BY_5 0x04 +#define DIVIDE_BY_6 0x05 +#define DIVIDE_BY_7 0x06 +#define DIVIDE_BY_8 0x07 +#define DIVIDE_BY_9 0x08 +#define DIVIDE_BY_10 0x09 + +int rts5261_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock, + u8 ssc_depth, bool initial_mode, bool double_clk, bool vpclk); + +#endif /* RTS5261_H */ diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c index b4a66b64f742..fd7b2167103d 100644 --- a/drivers/misc/cardreader/rtsx_pcr.c +++ b/drivers/misc/cardreader/rtsx_pcr.c @@ -22,6 +22,7 @@ #include #include "rtsx_pcr.h" +#include "rts5261.h" static bool msi_en = true; module_param(msi_en, bool, S_IRUGO | S_IWUSR); @@ -34,9 +35,6 @@ static struct mfd_cell rtsx_pcr_cells[] = { [RTSX_SD_CARD] = { .name = DRV_NAME_RTSX_PCI_SDMMC, }, - [RTSX_MS_CARD] = { - .name = DRV_NAME_RTSX_PCI_MS, - }, }; static const struct pci_device_id rtsx_pci_ids[] = { @@ -51,6 +49,7 @@ static const struct pci_device_id rtsx_pci_ids[] = { { PCI_DEVICE(0x10EC, 0x524A), PCI_CLASS_OTHERS << 16, 0xFF0000 }, { PCI_DEVICE(0x10EC, 0x525A), PCI_CLASS_OTHERS << 16, 0xFF0000 }, { PCI_DEVICE(0x10EC, 0x5260), PCI_CLASS_OTHERS << 16, 0xFF0000 }, + { PCI_DEVICE(0x10EC, 0x5261), PCI_CLASS_OTHERS << 16, 0xFF0000 }, { 0, } }; @@ -438,8 +437,16 @@ static void rtsx_pci_add_sg_tbl(struct rtsx_pcr *pcr, if (end) option |= RTSX_SG_END; - val = ((u64)addr << 32) | ((u64)len << 12) | option; + if (PCI_PID(pcr) == PID_5261) { + if (len > 0xFFFF) + val = ((u64)addr << 32) | (((u64)len & 0xFFFF) << 16) + | (((u64)len >> 16) << 6) | option; + else + val = ((u64)addr << 32) | ((u64)len << 16) | option; + } else { + val = ((u64)addr << 32) | ((u64)len << 12) | option; + } put_unaligned_le64(val, ptr); pcr->sgi++; } @@ -684,7 +691,6 @@ int rtsx_pci_card_pull_ctl_disable(struct rtsx_pcr *pcr, int card) else return -EINVAL; - return rtsx_pci_set_pull_ctl(pcr, tbl); } EXPORT_SYMBOL_GPL(rtsx_pci_card_pull_ctl_disable); @@ -735,6 +741,10 @@ int rtsx_pci_switch_clock(struct rtsx_pcr *pcr, unsigned int card_clock, [RTSX_SSC_DEPTH_250K] = SSC_DEPTH_250K, }; + if (PCI_PID(pcr) == PID_5261) + return rts5261_pci_switch_clock(pcr, card_clock, + ssc_depth, initial_mode, double_clk, vpclk); + if (initial_mode) { /* We use 250k(around) here, in initial stage */ clk_divider = SD_CLK_DIVIDE_128; @@ -1253,7 +1263,15 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr) rtsx_pci_enable_bus_int(pcr); /* Power on SSC */ - err = rtsx_pci_write_register(pcr, FPDCTL, SSC_POWER_DOWN, 0); + if (PCI_PID(pcr) == PID_5261) { + /* Gating real mcu clock */ + err = rtsx_pci_write_register(pcr, RTS5261_FW_CFG1, + RTS5261_MCU_CLOCK_GATING, 0); + err = rtsx_pci_write_register(pcr, RTS5261_REG_FPDCTL, + SSC_POWER_DOWN, 0); + } else { + err = rtsx_pci_write_register(pcr, FPDCTL, SSC_POWER_DOWN, 0); + } if (err < 0) return err; @@ -1283,7 +1301,12 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr) /* Enable SSC Clock */ rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL1, 0xFF, SSC_8X_EN | SSC_SEL_4M); - rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2, 0xFF, 0x12); + if (PCI_PID(pcr) == PID_5261) + rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2, 0xFF, + RTS5261_SSC_DEPTH_2M); + else + rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SSC_CTL2, 0xFF, 0x12); + /* Disable cd_pwr_save */ rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CHANGE_LINK_STATE, 0x16, 0x10); /* Clear Link Ready Interrupt */ @@ -1314,6 +1337,7 @@ static int rtsx_pci_init_hw(struct rtsx_pcr *pcr) case PID_524A: case PID_525A: case PID_5260: + case PID_5261: rtsx_pci_write_register(pcr, PM_CLK_FORCE_CTL, 1, 1); break; default: @@ -1393,9 +1417,14 @@ static int rtsx_pci_init_chip(struct rtsx_pcr *pcr) case 0x5286: rtl8402_init_params(pcr); break; + case 0x5260: rts5260_init_params(pcr); break; + + case 0x5261: + rts5261_init_params(pcr); + break; } pcr_dbg(pcr, "PID: 0x%04x, IC version: 0x%02x\n", diff --git a/drivers/misc/cardreader/rtsx_pcr.h b/drivers/misc/cardreader/rtsx_pcr.h index 98f729263dc1..ed391df52f4f 100644 --- a/drivers/misc/cardreader/rtsx_pcr.h +++ b/drivers/misc/cardreader/rtsx_pcr.h @@ -53,6 +53,7 @@ void rts524a_init_params(struct rtsx_pcr *pcr); void rts525a_init_params(struct rtsx_pcr *pcr); void rtl8411b_init_params(struct rtsx_pcr *pcr); void rts5260_init_params(struct rtsx_pcr *pcr); +void rts5261_init_params(struct rtsx_pcr *pcr); static inline u8 map_sd_drive(int idx) { diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h index f87da30a58b1..65b8142a7fed 100644 --- a/include/linux/rtsx_pci.h +++ b/include/linux/rtsx_pci.h @@ -1262,6 +1262,7 @@ struct rtsx_pcr { #define PID_5250 0x5250 #define PID_525A 0x525A #define PID_5260 0x5260 +#define PID_5261 0x5261 #define CHK_PCI_PID(pcr, pid) ((pcr)->pci->device == (pid)) #define PCI_VID(pcr) ((pcr)->pci->vendor) -- cgit v1.2.3-71-gd317 From e9cb0497b1c801a66f9abc907b2c55241099e6ac Mon Sep 17 00:00:00 2001 From: Richard Gong Date: Mon, 4 Nov 2019 10:24:36 -0600 Subject: firmware: Fix incompatible function behavior for RSU driver The older versions of remote system update (RSU) firmware don't support retry and notify features then the kernel module dies when it queries the RSU retry counter or performs notify operation. Update the Intel service layer and RSU drivers to be compatible with all versions of RSU firmware. Reported-by: Radu Barcau Reported-by: kbuild test robot Signed-off-by: Richard Gong Link: https://lore.kernel.org/r/1572884676-1385-1-git-send-email-richard.gong@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/firmware/stratix10-rsu.c | 42 ++++++++++------------ drivers/firmware/stratix10-svc.c | 18 +++++++++- .../linux/firmware/intel/stratix10-svc-client.h | 8 +++++ 3 files changed, 43 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/stratix10-rsu.c b/drivers/firmware/stratix10-rsu.c index bb008c019920..f8533338b018 100644 --- a/drivers/firmware/stratix10-rsu.c +++ b/drivers/firmware/stratix10-rsu.c @@ -20,7 +20,6 @@ #define RSU_VERSION_MASK GENMASK_ULL(63, 32) #define RSU_ERROR_LOCATION_MASK GENMASK_ULL(31, 0) #define RSU_ERROR_DETAIL_MASK GENMASK_ULL(63, 32) -#define RSU_FW_VERSION_MASK GENMASK_ULL(15, 0) #define RSU_TIMEOUT (msecs_to_jiffies(SVC_RSU_REQUEST_TIMEOUT_MS)) @@ -109,9 +108,12 @@ static void rsu_command_callback(struct stratix10_svc_client *client, { struct stratix10_rsu_priv *priv = client->priv; - if (data->status != BIT(SVC_STATUS_RSU_OK)) - dev_err(client->dev, "RSU returned status is %i\n", - data->status); + if (data->status == BIT(SVC_STATUS_RSU_NO_SUPPORT)) + dev_warn(client->dev, "Secure FW doesn't support notify\n"); + else if (data->status == BIT(SVC_STATUS_RSU_ERROR)) + dev_err(client->dev, "Failure, returned status is %lu\n", + BIT(data->status)); + complete(&priv->completion); } @@ -133,9 +135,11 @@ static void rsu_retry_callback(struct stratix10_svc_client *client, if (data->status == BIT(SVC_STATUS_RSU_OK)) priv->retry_counter = *counter; + else if (data->status == BIT(SVC_STATUS_RSU_NO_SUPPORT)) + dev_warn(client->dev, "Secure FW doesn't support retry\n"); else - dev_err(client->dev, "Failed to get retry counter %i\n", - data->status); + dev_err(client->dev, "Failed to get retry counter %lu\n", + BIT(data->status)); complete(&priv->completion); } @@ -333,15 +337,10 @@ static ssize_t notify_store(struct device *dev, return ret; } - /* only 19.3 or late version FW supports retry counter feature */ - if (FIELD_GET(RSU_FW_VERSION_MASK, priv->status.version)) { - ret = rsu_send_msg(priv, COMMAND_RSU_RETRY, - 0, rsu_retry_callback); - if (ret) { - dev_err(dev, - "Error, getting RSU retry %i\n", ret); - return ret; - } + ret = rsu_send_msg(priv, COMMAND_RSU_RETRY, 0, rsu_retry_callback); + if (ret) { + dev_err(dev, "Error, getting RSU retry %i\n", ret); + return ret; } return count; @@ -413,15 +412,10 @@ static int stratix10_rsu_probe(struct platform_device *pdev) stratix10_svc_free_channel(priv->chan); } - /* only 19.3 or late version FW supports retry counter feature */ - if (FIELD_GET(RSU_FW_VERSION_MASK, priv->status.version)) { - ret = rsu_send_msg(priv, COMMAND_RSU_RETRY, 0, - rsu_retry_callback); - if (ret) { - dev_err(dev, - "Error, getting RSU retry %i\n", ret); - stratix10_svc_free_channel(priv->chan); - } + ret = rsu_send_msg(priv, COMMAND_RSU_RETRY, 0, rsu_retry_callback); + if (ret) { + dev_err(dev, "Error, getting RSU retry %i\n", ret); + stratix10_svc_free_channel(priv->chan); } return ret; diff --git a/drivers/firmware/stratix10-svc.c b/drivers/firmware/stratix10-svc.c index b485321189e1..c6c31402848d 100644 --- a/drivers/firmware/stratix10-svc.c +++ b/drivers/firmware/stratix10-svc.c @@ -493,8 +493,24 @@ static int svc_normal_to_secure_thread(void *data) pdata->chan->scl->receive_cb(pdata->chan->scl, cbdata); break; default: - pr_warn("it shouldn't happen\n"); + pr_warn("Secure firmware doesn't support...\n"); + + /* + * be compatible with older version firmware which + * doesn't support RSU notify or retry + */ + if ((pdata->command == COMMAND_RSU_RETRY) || + (pdata->command == COMMAND_RSU_NOTIFY)) { + cbdata->status = + BIT(SVC_STATUS_RSU_NO_SUPPORT); + cbdata->kaddr1 = NULL; + cbdata->kaddr2 = NULL; + cbdata->kaddr3 = NULL; + pdata->chan->scl->receive_cb( + pdata->chan->scl, cbdata); + } break; + } }; diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h index b6c4302a39e0..59bc6e2af693 100644 --- a/include/linux/firmware/intel/stratix10-svc-client.h +++ b/include/linux/firmware/intel/stratix10-svc-client.h @@ -41,6 +41,12 @@ * * SVC_STATUS_RSU_OK: * Secure firmware accepts the request of remote status update (RSU). + * + * SVC_STATUS_RSU_ERROR: + * Error encountered during remote system update. + * + * SVC_STATUS_RSU_NO_SUPPORT: + * Secure firmware doesn't support RSU retry or notify feature. */ #define SVC_STATUS_RECONFIG_REQUEST_OK 0 #define SVC_STATUS_RECONFIG_BUFFER_SUBMITTED 1 @@ -50,6 +56,8 @@ #define SVC_STATUS_RECONFIG_ERROR 5 #define SVC_STATUS_RSU_OK 6 #define SVC_STATUS_RSU_ERROR 7 +#define SVC_STATUS_RSU_NO_SUPPORT 8 + /** * Flag bit for COMMAND_RECONFIG * -- cgit v1.2.3-71-gd317 From a7e335deed174a37fc6f84f69caaeff8a08f8ff8 Mon Sep 17 00:00:00 2001 From: Eric Long Date: Wed, 23 Oct 2019 14:31:32 +0800 Subject: dmaengine: sprd: Add wrap address support for link-list mode The Spreadtrum Audio compress offload mode will use 2-stage DMA transfer to save power. That means we can request 2 dma channels, one for source channel, and another one for destination channel. Once the source channel's transaction is done, it will trigger the destination channel's transaction automatically by hardware signal. In this case, the source channel will transfer data from IRAM buffer to the DSP fifo to decoding/encoding, once IRAM buffer is empty by transferring done, the destination channel will start to transfer data from DDR buffer to IRAM buffer. Since the destination channel will use link-list mode to fill the IRAM data, and IRAM buffer is allocated by 32K, and DDR buffer is larger to 2M, that means we need lots of link-list nodes to do a cyclic transfer, instead wasting lots of link-list memory, we can use wrap address support to reduce link-list node number, which means when the transfer address reaches the wrap address, the transfer address will jump to the wrap_to address specified by wrap_to register, and only 2 link-list nodes can do a cyclic transfer to transfer data from DDR to IRAM. Thus this patch adds wrap address to support this case. [Baolin Wang changes the commit message] Signed-off-by: Eric Long Signed-off-by: Baolin Wang Link: https://lore.kernel.org/r/85a5484bc1f3dd53ce6f92700ad8b35f30a0b096.1571812029.git.baolin.wang@linaro.org Signed-off-by: Vinod Koul --- drivers/dma/sprd-dma.c | 13 +++++++++++++ include/linux/dma/sprd-dma.h | 4 ++++ 2 files changed, 17 insertions(+) (limited to 'include/linux') diff --git a/drivers/dma/sprd-dma.c b/drivers/dma/sprd-dma.c index 32402c2615de..9a31a315dbef 100644 --- a/drivers/dma/sprd-dma.c +++ b/drivers/dma/sprd-dma.c @@ -99,6 +99,7 @@ /* DMA_CHN_WARP_* register definition */ #define SPRD_DMA_HIGH_ADDR_MASK GENMASK(31, 28) #define SPRD_DMA_LOW_ADDR_MASK GENMASK(31, 0) +#define SPRD_DMA_WRAP_ADDR_MASK GENMASK(27, 0) #define SPRD_DMA_HIGH_ADDR_OFFSET 4 /* SPRD_DMA_CHN_INTC register definition */ @@ -118,6 +119,8 @@ #define SPRD_DMA_SWT_MODE_OFFSET 26 #define SPRD_DMA_REQ_MODE_OFFSET 24 #define SPRD_DMA_REQ_MODE_MASK GENMASK(1, 0) +#define SPRD_DMA_WRAP_SEL_DEST BIT(23) +#define SPRD_DMA_WRAP_EN BIT(22) #define SPRD_DMA_FIX_SEL_OFFSET 21 #define SPRD_DMA_FIX_EN_OFFSET 20 #define SPRD_DMA_LLIST_END BIT(19) @@ -804,6 +807,8 @@ static int sprd_dma_fill_desc(struct dma_chan *chan, temp |= req_mode << SPRD_DMA_REQ_MODE_OFFSET; temp |= fix_mode << SPRD_DMA_FIX_SEL_OFFSET; temp |= fix_en << SPRD_DMA_FIX_EN_OFFSET; + temp |= schan->linklist.wrap_addr ? + SPRD_DMA_WRAP_EN | SPRD_DMA_WRAP_SEL_DEST : 0; temp |= slave_cfg->src_maxburst & SPRD_DMA_FRG_LEN_MASK; hw->frg_len = temp; @@ -831,6 +836,12 @@ static int sprd_dma_fill_desc(struct dma_chan *chan, hw->llist_ptr = lower_32_bits(llist_ptr); hw->src_blk_step = (upper_32_bits(llist_ptr) << SPRD_DMA_LLIST_HIGH_SHIFT) & SPRD_DMA_LLIST_HIGH_MASK; + + if (schan->linklist.wrap_addr) { + hw->wrap_ptr |= schan->linklist.wrap_addr & + SPRD_DMA_WRAP_ADDR_MASK; + hw->wrap_to |= dst & SPRD_DMA_WRAP_ADDR_MASK; + } } else { hw->llist_ptr = 0; hw->src_blk_step = 0; @@ -939,9 +950,11 @@ sprd_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, schan->linklist.phy_addr = ll_cfg->phy_addr; schan->linklist.virt_addr = ll_cfg->virt_addr; + schan->linklist.wrap_addr = ll_cfg->wrap_addr; } else { schan->linklist.phy_addr = 0; schan->linklist.virt_addr = 0; + schan->linklist.wrap_addr = 0; } /* diff --git a/include/linux/dma/sprd-dma.h b/include/linux/dma/sprd-dma.h index ab82df64682a..d09c6f6f6da5 100644 --- a/include/linux/dma/sprd-dma.h +++ b/include/linux/dma/sprd-dma.h @@ -118,6 +118,9 @@ enum sprd_dma_int_type { * struct sprd_dma_linklist - DMA link-list address structure * @virt_addr: link-list virtual address to configure link-list node * @phy_addr: link-list physical address to link DMA transfer + * @wrap_addr: the wrap address for link-list mode, which means once the + * transfer address reaches the wrap address, the next transfer address + * will jump to the address specified by wrap_to register. * * The Spreadtrum DMA controller supports the link-list mode, that means slaves * can supply several groups configurations (each configuration represents one @@ -181,6 +184,7 @@ enum sprd_dma_int_type { struct sprd_dma_linklist { unsigned long virt_addr; phys_addr_t phy_addr; + phys_addr_t wrap_addr; }; #endif -- cgit v1.2.3-71-gd317 From 6917d0689993f46d97d40dd66c601d0fd5b1dbdd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 14 Nov 2019 15:34:33 +0100 Subject: block: merge invalidate_partitions into rescan_partitions A lot of the logic in invalidate_partitions and rescan_partitions is shared. Merge the two functions to simplify things. There is a small behavior change in that we now send the kevent change notice also if we were not invalidating but no partitions were found, which seems like the right thing to do. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Signed-off-by: Jens Axboe --- block/ioctl.c | 2 +- block/partition-generic.c | 38 ++++++++++++++------------------------ fs/block_dev.c | 5 +---- include/linux/genhd.h | 4 ++-- 4 files changed, 18 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/block/ioctl.c b/block/ioctl.c index 8756efb1419e..f6576a6d5778 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -171,7 +171,7 @@ int __blkdev_reread_part(struct block_device *bdev) lockdep_assert_held(&bdev->bd_mutex); - return rescan_partitions(disk, bdev); + return rescan_partitions(disk, bdev, false); } EXPORT_SYMBOL(__blkdev_reread_part); diff --git a/block/partition-generic.c b/block/partition-generic.c index 7eabb67f99b5..6b9f4f5d993a 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -576,7 +576,8 @@ out_free_state: return ret; } -int rescan_partitions(struct gendisk *disk, struct block_device *bdev) +int rescan_partitions(struct gendisk *disk, struct block_device *bdev, + bool invalidate) { int ret; @@ -585,13 +586,22 @@ rescan: if (ret) return ret; - if (disk->fops->revalidate_disk) + if (invalidate) + set_capacity(disk, 0); + else if (disk->fops->revalidate_disk) disk->fops->revalidate_disk(disk); - check_disk_size_change(disk, bdev, true); + + check_disk_size_change(disk, bdev, !invalidate); bdev->bd_invalidated = 0; - if (!get_capacity(disk)) + if (!get_capacity(disk)) { + /* + * Tell userspace that the media / partition table may have + * changed. + */ + kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); return 0; + } ret = blk_add_partitions(disk, bdev); if (ret == -EAGAIN) @@ -599,26 +609,6 @@ rescan: return ret; } -int invalidate_partitions(struct gendisk *disk, struct block_device *bdev) -{ - int res; - - if (!bdev->bd_invalidated) - return 0; - - res = drop_partitions(disk, bdev); - if (res) - return res; - - set_capacity(disk, 0); - check_disk_size_change(disk, bdev, false); - bdev->bd_invalidated = 0; - /* tell userspace that the media / partition table may have changed */ - kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); - - return 0; -} - unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p) { struct address_space *mapping = bdev->bd_inode->i_mapping; diff --git a/fs/block_dev.c b/fs/block_dev.c index d612468ee66b..0af62b76d031 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1511,10 +1511,7 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part); static void bdev_disk_changed(struct block_device *bdev, bool invalidate) { if (disk_part_scan_enabled(bdev->bd_disk)) { - if (invalidate) - invalidate_partitions(bdev->bd_disk, bdev); - else - rescan_partitions(bdev->bd_disk, bdev); + rescan_partitions(bdev->bd_disk, bdev, invalidate); } else { check_disk_size_change(bdev->bd_disk, bdev, !invalidate); bdev->bd_invalidated = 0; diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 8b5330dd5ac0..fd7774e64f0b 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -622,8 +622,8 @@ extern dev_t blk_lookup_devt(const char *name, int partno); extern char *disk_name (struct gendisk *hd, int partno, char *buf); extern int disk_expand_part_tbl(struct gendisk *disk, int target); -extern int rescan_partitions(struct gendisk *disk, struct block_device *bdev); -extern int invalidate_partitions(struct gendisk *disk, struct block_device *bdev); +int rescan_partitions(struct gendisk *disk, struct block_device *bdev, + bool invalidate); extern struct hd_struct * __must_check add_partition(struct gendisk *disk, int partno, sector_t start, sector_t len, int flags, -- cgit v1.2.3-71-gd317 From a1548b674403c0de70cc29a1575689917ba60157 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 14 Nov 2019 15:34:34 +0100 Subject: block: move rescan_partitions to fs/block_dev.c Large parts of rescan_partitions aren't about partitions, and moving it to block_dev.c will allow for some further cleanups by merging it into its only caller. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Signed-off-by: Jens Axboe --- block/partition-generic.c | 37 ++----------------------------------- fs/block_dev.c | 38 ++++++++++++++++++++++++++++++++++++-- include/linux/fs.h | 2 -- include/linux/genhd.h | 4 ++-- 4 files changed, 40 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/block/partition-generic.c b/block/partition-generic.c index 6b9f4f5d993a..2cbc23f6032c 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -439,7 +439,7 @@ static bool disk_unlock_native_capacity(struct gendisk *disk) } } -static int drop_partitions(struct gendisk *disk, struct block_device *bdev) +int blk_drop_partitions(struct gendisk *disk, struct block_device *bdev) { struct disk_part_iter piter; struct hd_struct *part; @@ -509,7 +509,7 @@ static bool blk_add_partition(struct gendisk *disk, struct block_device *bdev, return true; } -static int blk_add_partitions(struct gendisk *disk, struct block_device *bdev) +int blk_add_partitions(struct gendisk *disk, struct block_device *bdev) { struct parsed_partitions *state; int ret = -EAGAIN, p, highest; @@ -576,39 +576,6 @@ out_free_state: return ret; } -int rescan_partitions(struct gendisk *disk, struct block_device *bdev, - bool invalidate) -{ - int ret; - -rescan: - ret = drop_partitions(disk, bdev); - if (ret) - return ret; - - if (invalidate) - set_capacity(disk, 0); - else if (disk->fops->revalidate_disk) - disk->fops->revalidate_disk(disk); - - check_disk_size_change(disk, bdev, !invalidate); - bdev->bd_invalidated = 0; - - if (!get_capacity(disk)) { - /* - * Tell userspace that the media / partition table may have - * changed. - */ - kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); - return 0; - } - - ret = blk_add_partitions(disk, bdev); - if (ret == -EAGAIN) - goto rescan; - return ret; -} - unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p) { struct address_space *mapping = bdev->bd_inode->i_mapping; diff --git a/fs/block_dev.c b/fs/block_dev.c index 0af62b76d031..ec10dacd18d0 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1416,8 +1416,8 @@ static void flush_disk(struct block_device *bdev, bool kill_dirty) * and adjusts it if it differs. When shrinking the bdev size, its all caches * are freed. */ -void check_disk_size_change(struct gendisk *disk, struct block_device *bdev, - bool verbose) +static void check_disk_size_change(struct gendisk *disk, + struct block_device *bdev, bool verbose) { loff_t disk_size, bdev_size; @@ -1508,6 +1508,40 @@ EXPORT_SYMBOL(bd_set_size); static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part); +static int rescan_partitions(struct gendisk *disk, struct block_device *bdev, + bool invalidate) +{ + int ret; + +rescan: + ret = blk_drop_partitions(disk, bdev); + if (ret) + return ret; + + if (invalidate) + set_capacity(disk, 0); + else if (disk->fops->revalidate_disk) + disk->fops->revalidate_disk(disk); + + check_disk_size_change(disk, bdev, !invalidate); + bdev->bd_invalidated = 0; + + if (!get_capacity(disk)) { + /* + * Tell userspace that the media / partition table may have + * changed. + */ + kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); + return 0; + } + + ret = blk_add_partitions(disk, bdev); + if (ret == -EAGAIN) + goto rescan; + return ret; +} + + static void bdev_disk_changed(struct block_device *bdev, bool invalidate) { if (disk_part_scan_enabled(bdev->bd_disk)) { diff --git a/include/linux/fs.h b/include/linux/fs.h index e0d909d35763..d233dd661df7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2703,8 +2703,6 @@ extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); #ifdef CONFIG_BLOCK -extern void check_disk_size_change(struct gendisk *disk, - struct block_device *bdev, bool verbose); extern int revalidate_disk(struct gendisk *); extern int check_disk_change(struct block_device *); extern int __invalidate_device(struct block_device *, bool); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index fd7774e64f0b..f5cffbf63abf 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -621,9 +621,9 @@ extern void blk_invalidate_devt(dev_t devt); extern dev_t blk_lookup_devt(const char *name, int partno); extern char *disk_name (struct gendisk *hd, int partno, char *buf); +int blk_add_partitions(struct gendisk *disk, struct block_device *bdev); +int blk_drop_partitions(struct gendisk *disk, struct block_device *bdev); extern int disk_expand_part_tbl(struct gendisk *disk, int target); -int rescan_partitions(struct gendisk *disk, struct block_device *bdev, - bool invalidate); extern struct hd_struct * __must_check add_partition(struct gendisk *disk, int partno, sector_t start, sector_t len, int flags, -- cgit v1.2.3-71-gd317 From 142fe8f4bb169e8632024d51c64653a8bf140561 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 14 Nov 2019 15:34:35 +0100 Subject: block: fix bdev_disk_changed for non-partitioned devices We still have to set the capacity to 0 if invalidating or call revalidate_disk if not even if the disk has no partitions. Fix that by merging rescan_partitions into bdev_disk_changed and just stubbing out blk_add_partitions and blk_drop_partitions for non-partitioned devices. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Signed-off-by: Jens Axboe --- block/ioctl.c | 6 ++---- block/partition-generic.c | 5 +++++ fs/block_dev.c | 25 +++++++------------------ include/linux/genhd.h | 1 + 4 files changed, 15 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/block/ioctl.c b/block/ioctl.c index f6576a6d5778..5ccd9f016594 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -162,16 +162,14 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user */ int __blkdev_reread_part(struct block_device *bdev) { - struct gendisk *disk = bdev->bd_disk; - - if (!disk_part_scan_enabled(disk) || bdev != bdev->bd_contains) + if (!disk_part_scan_enabled(bdev->bd_disk) || bdev != bdev->bd_contains) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EACCES; lockdep_assert_held(&bdev->bd_mutex); - return rescan_partitions(disk, bdev, false); + return bdev_disk_changed(bdev, false); } EXPORT_SYMBOL(__blkdev_reread_part); diff --git a/block/partition-generic.c b/block/partition-generic.c index 2cbc23f6032c..61487421a319 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -445,6 +445,8 @@ int blk_drop_partitions(struct gendisk *disk, struct block_device *bdev) struct hd_struct *part; int res; + if (!disk_part_scan_enabled(disk)) + return 0; if (bdev->bd_part_count || bdev->bd_super) return -EBUSY; res = invalidate_partition(disk, 0); @@ -514,6 +516,9 @@ int blk_add_partitions(struct gendisk *disk, struct block_device *bdev) struct parsed_partitions *state; int ret = -EAGAIN, p, highest; + if (!disk_part_scan_enabled(disk)) + return 0; + state = check_partition(disk, bdev); if (!state) return 0; diff --git a/fs/block_dev.c b/fs/block_dev.c index ec10dacd18d0..ae16466a67f7 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1508,9 +1508,9 @@ EXPORT_SYMBOL(bd_set_size); static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part); -static int rescan_partitions(struct gendisk *disk, struct block_device *bdev, - bool invalidate) +int bdev_disk_changed(struct block_device *bdev, bool invalidate) { + struct gendisk *disk = bdev->bd_disk; int ret; rescan: @@ -1526,32 +1526,21 @@ rescan: check_disk_size_change(disk, bdev, !invalidate); bdev->bd_invalidated = 0; - if (!get_capacity(disk)) { + if (get_capacity(disk)) { + ret = blk_add_partitions(disk, bdev); + if (ret == -EAGAIN) + goto rescan; + } else { /* * Tell userspace that the media / partition table may have * changed. */ kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); - return 0; } - ret = blk_add_partitions(disk, bdev); - if (ret == -EAGAIN) - goto rescan; return ret; } - -static void bdev_disk_changed(struct block_device *bdev, bool invalidate) -{ - if (disk_part_scan_enabled(bdev->bd_disk)) { - rescan_partitions(bdev->bd_disk, bdev, invalidate); - } else { - check_disk_size_change(bdev->bd_disk, bdev, !invalidate); - bdev->bd_invalidated = 0; - } -} - /* * bd_mutex locking: * diff --git a/include/linux/genhd.h b/include/linux/genhd.h index f5cffbf63abf..8bb63027e4d6 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -621,6 +621,7 @@ extern void blk_invalidate_devt(dev_t devt); extern dev_t blk_lookup_devt(const char *name, int partno); extern char *disk_name (struct gendisk *hd, int partno, char *buf); +int bdev_disk_changed(struct block_device *bdev, bool invalidate); int blk_add_partitions(struct gendisk *disk, struct block_device *bdev); int blk_drop_partitions(struct gendisk *disk, struct block_device *bdev); extern int disk_expand_part_tbl(struct gendisk *disk, int target); -- cgit v1.2.3-71-gd317 From f0b870df80bc70dad432fd0c142bb709a49964f5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 14 Nov 2019 15:34:36 +0100 Subject: block: remove (__)blkdev_reread_part as an exported API In general drivers should never mess with partition tables directly. Unfortunately s390 and loop do for somewhat historic reasons, but they can use bdev_disk_changed directly instead when we export it as they satisfy the sanity checks we have in __blkdev_reread_part. Signed-off-by: Christoph Hellwig Reviewed-by: Stefan Haberland [dasd] Reviewed-by: Jan Kara Signed-off-by: Jens Axboe --- block/ioctl.c | 35 +++++------------------------------ drivers/block/loop.c | 13 ++++++++----- drivers/s390/block/dasd_genhd.c | 4 +++- fs/block_dev.c | 7 +++++++ include/linux/fs.h | 2 -- 5 files changed, 23 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/block/ioctl.c b/block/ioctl.c index 5ccd9f016594..7ac8a66c9787 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -155,46 +155,21 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user } } -/* - * This is an exported API for the block driver, and will not - * acquire bd_mutex. This API should be used in case that - * caller has held bd_mutex already. - */ -int __blkdev_reread_part(struct block_device *bdev) +static int blkdev_reread_part(struct block_device *bdev) { + int ret; + if (!disk_part_scan_enabled(bdev->bd_disk) || bdev != bdev->bd_contains) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EACCES; - lockdep_assert_held(&bdev->bd_mutex); - - return bdev_disk_changed(bdev, false); -} -EXPORT_SYMBOL(__blkdev_reread_part); - -/* - * This is an exported API for the block driver, and will - * try to acquire bd_mutex. If bd_mutex has been held already - * in current context, please call __blkdev_reread_part(). - * - * Make sure the held locks in current context aren't required - * in open()/close() handler and I/O path for avoiding ABBA deadlock: - * - bd_mutex is held before calling block driver's open/close - * handler - * - reading partition table may submit I/O to the block device - */ -int blkdev_reread_part(struct block_device *bdev) -{ - int res; - mutex_lock(&bdev->bd_mutex); - res = __blkdev_reread_part(bdev); + ret = bdev_disk_changed(bdev, false); mutex_unlock(&bdev->bd_mutex); - return res; + return ret; } -EXPORT_SYMBOL(blkdev_reread_part); static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, unsigned long arg, unsigned long flags) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index ef6e251857c8..739b372a5112 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -640,7 +640,9 @@ static void loop_reread_partitions(struct loop_device *lo, { int rc; - rc = blkdev_reread_part(bdev); + mutex_lock(&bdev->bd_mutex); + rc = bdev_disk_changed(bdev, false); + mutex_unlock(&bdev->bd_mutex); if (rc) pr_warn("%s: partition scan of loop%d (%s) failed (rc=%d)\n", __func__, lo->lo_number, lo->lo_file_name, rc); @@ -1164,10 +1166,11 @@ out_unlock: * must be at least one and it can only become zero when the * current holder is released. */ - if (release) - err = __blkdev_reread_part(bdev); - else - err = blkdev_reread_part(bdev); + if (!release) + mutex_lock(&bdev->bd_mutex); + err = bdev_disk_changed(bdev, false); + if (!release) + mutex_unlock(&bdev->bd_mutex); if (err) pr_warn("%s: partition scan of loop%d failed (rc=%d)\n", __func__, lo_number, err); diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c index 5542d9eadfe0..7d079154f849 100644 --- a/drivers/s390/block/dasd_genhd.c +++ b/drivers/s390/block/dasd_genhd.c @@ -116,7 +116,9 @@ int dasd_scan_partitions(struct dasd_block *block) return -ENODEV; } - rc = blkdev_reread_part(bdev); + mutex_lock(&bdev->bd_mutex); + rc = bdev_disk_changed(bdev, false); + mutex_unlock(&bdev->bd_mutex); if (rc) DBF_DEV_EVENT(DBF_ERR, block->base, "scan partitions error, rc %d", rc); diff --git a/fs/block_dev.c b/fs/block_dev.c index ae16466a67f7..9558a2f064b1 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1513,6 +1513,8 @@ int bdev_disk_changed(struct block_device *bdev, bool invalidate) struct gendisk *disk = bdev->bd_disk; int ret; + lockdep_assert_held(&bdev->bd_mutex); + rescan: ret = blk_drop_partitions(disk, bdev); if (ret) @@ -1540,6 +1542,11 @@ rescan: return ret; } +/* + * Only exported for for loop and dasd for historic reasons. Don't use in new + * code! + */ +EXPORT_SYMBOL_GPL(bdev_disk_changed); /* * bd_mutex locking: diff --git a/include/linux/fs.h b/include/linux/fs.h index d233dd661df7..ae6c5c37f3ae 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2632,8 +2632,6 @@ extern void bd_finish_claiming(struct block_device *bdev, extern void bd_abort_claiming(struct block_device *bdev, struct block_device *whole, void *holder); extern void blkdev_put(struct block_device *bdev, fmode_t mode); -extern int __blkdev_reread_part(struct block_device *bdev); -extern int blkdev_reread_part(struct block_device *bdev); #ifdef CONFIG_SYSFS extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); -- cgit v1.2.3-71-gd317 From 2ac55d5e5ec9ad0a07e194f0eaca865fe5aa3c40 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Thu, 17 Oct 2019 15:25:36 +0200 Subject: mmc: core: Re-work HW reset for SDIO cards It have turned out that it's not a good idea to unconditionally do a power cycle and then to re-initialize the SDIO card, as currently done through mmc_hw_reset() -> mmc_sdio_hw_reset(). This because there may be multiple SDIO func drivers probed, who also shares the same SDIO card. To address these scenarios, one may be tempted to use a notification mechanism, as to allow the core to inform each of the probed func drivers, about an ongoing HW reset. However, supporting such an operation from the func driver point of view, may not be entirely trivial. Therefore, let's use a more simplistic approach to solve the problem, by instead forcing the card to be removed and re-detected, via scheduling a rescan-work. In this way, we can rely on existing infrastructure, as the func driver's ->remove() and ->probe() callbacks, becomes invoked to deal with the cleanup and the re-initialization. This solution may be considered as rather heavy, especially if a func driver doesn't share its card with other func drivers. To address this, let's keep the current immediate HW reset option as well, but run it only when there is one func driver probed for the card. Finally, to allow the caller of mmc_hw_reset(), to understand if the reset is being asynchronously managed from a scheduled work, it returns 1 (propagated from mmc_sdio_hw_reset()). If the HW reset is executed successfully and synchronously it returns 0, which maintains the existing behaviour. Reviewed-by: Douglas Anderson Tested-by: Douglas Anderson Cc: stable@vger.kernel.org # v5.4+ Signed-off-by: Ulf Hansson --- drivers/mmc/core/core.c | 5 ++--- drivers/mmc/core/core.h | 2 ++ drivers/mmc/core/sdio.c | 28 +++++++++++++++++++++++++++- drivers/mmc/core/sdio_bus.c | 9 ++++++++- include/linux/mmc/card.h | 1 + 5 files changed, 40 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 6f8342702c73..abf8f5eb0a1c 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -1469,8 +1469,7 @@ void mmc_detach_bus(struct mmc_host *host) mmc_bus_put(host); } -static void _mmc_detect_change(struct mmc_host *host, unsigned long delay, - bool cd_irq) +void _mmc_detect_change(struct mmc_host *host, unsigned long delay, bool cd_irq) { /* * If the device is configured as wakeup, we prevent a new sleep for @@ -2129,7 +2128,7 @@ int mmc_hw_reset(struct mmc_host *host) ret = host->bus_ops->hw_reset(host); mmc_bus_put(host); - if (ret) + if (ret < 0) pr_warn("%s: tried to HW reset card, got error %d\n", mmc_hostname(host), ret); diff --git a/drivers/mmc/core/core.h b/drivers/mmc/core/core.h index 328c78dbee66..575ac0257af2 100644 --- a/drivers/mmc/core/core.h +++ b/drivers/mmc/core/core.h @@ -70,6 +70,8 @@ void mmc_rescan(struct work_struct *work); void mmc_start_host(struct mmc_host *host); void mmc_stop_host(struct mmc_host *host); +void _mmc_detect_change(struct mmc_host *host, unsigned long delay, + bool cd_irq); int _mmc_detect_card_removed(struct mmc_host *host); int mmc_detect_card_removed(struct mmc_host *host); diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c index 26cabd53ddc5..ebb387aa5158 100644 --- a/drivers/mmc/core/sdio.c +++ b/drivers/mmc/core/sdio.c @@ -1048,9 +1048,35 @@ static int mmc_sdio_runtime_resume(struct mmc_host *host) return ret; } +/* + * SDIO HW reset + * + * Returns 0 if the HW reset was executed synchronously, returns 1 if the HW + * reset was asynchronously scheduled, else a negative error code. + */ static int mmc_sdio_hw_reset(struct mmc_host *host) { - mmc_power_cycle(host, host->card->ocr); + struct mmc_card *card = host->card; + + /* + * In case the card is shared among multiple func drivers, reset the + * card through a rescan work. In this way it will be removed and + * re-detected, thus all func drivers becomes informed about it. + */ + if (atomic_read(&card->sdio_funcs_probed) > 1) { + if (mmc_card_removed(card)) + return 1; + host->rescan_entered = 0; + mmc_card_set_removed(card); + _mmc_detect_change(host, 0, false); + return 1; + } + + /* + * A single func driver has been probed, then let's skip the heavy + * hotplug dance above and execute the reset immediately. + */ + mmc_power_cycle(host, card->ocr); return mmc_sdio_reinit_card(host); } diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c index 2963e6542958..3cc928282af7 100644 --- a/drivers/mmc/core/sdio_bus.c +++ b/drivers/mmc/core/sdio_bus.c @@ -138,6 +138,8 @@ static int sdio_bus_probe(struct device *dev) if (ret) return ret; + atomic_inc(&func->card->sdio_funcs_probed); + /* Unbound SDIO functions are always suspended. * During probe, the function is set active and the usage count * is incremented. If the driver supports runtime PM, @@ -153,7 +155,10 @@ static int sdio_bus_probe(struct device *dev) /* Set the default block size so the driver is sure it's something * sensible. */ sdio_claim_host(func); - ret = sdio_set_block_size(func, 0); + if (mmc_card_removed(func->card)) + ret = -ENOMEDIUM; + else + ret = sdio_set_block_size(func, 0); sdio_release_host(func); if (ret) goto disable_runtimepm; @@ -165,6 +170,7 @@ static int sdio_bus_probe(struct device *dev) return 0; disable_runtimepm: + atomic_dec(&func->card->sdio_funcs_probed); if (func->card->host->caps & MMC_CAP_POWER_OFF_CARD) pm_runtime_put_noidle(dev); dev_pm_domain_detach(dev, false); @@ -181,6 +187,7 @@ static int sdio_bus_remove(struct device *dev) pm_runtime_get_sync(dev); drv->remove(func); + atomic_dec(&func->card->sdio_funcs_probed); if (func->irq_handler) { pr_warn("WARNING: driver %s did not remove its interrupt handler!\n", diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 9b6336ad3266..e459b38ef33c 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -291,6 +291,7 @@ struct mmc_card { struct sd_switch_caps sw_caps; /* switch (CMD6) caps */ unsigned int sdio_funcs; /* number of SDIO functions */ + atomic_t sdio_funcs_probed; /* number of probed SDIO funcs */ struct sdio_cccr cccr; /* common card info */ struct sdio_cis cis; /* common tuple info */ struct sdio_func *sdio_func[SDIO_MAX_FUNCS]; /* SDIO functions (devices) */ -- cgit v1.2.3-71-gd317 From 7283fff8b524b2f27438429aca458b232f5c5c8a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 13 Nov 2019 08:32:13 +0100 Subject: dma-mapping: remove the DMA_ATTR_WRITE_BARRIER flag This flag is not implemented by any backend and only set by the ib_umem module in a single instance. Link: https://lore.kernel.org/r/20191113073214.9514-2-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe --- Documentation/DMA-attributes.txt | 18 ------------------ drivers/infiniband/core/umem.c | 9 ++------- include/linux/dma-mapping.h | 5 +---- 3 files changed, 3 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/Documentation/DMA-attributes.txt b/Documentation/DMA-attributes.txt index 8f8d97f65d73..29dcbe8826e8 100644 --- a/Documentation/DMA-attributes.txt +++ b/Documentation/DMA-attributes.txt @@ -5,24 +5,6 @@ DMA attributes This document describes the semantics of the DMA attributes that are defined in linux/dma-mapping.h. -DMA_ATTR_WRITE_BARRIER ----------------------- - -DMA_ATTR_WRITE_BARRIER is a (write) barrier attribute for DMA. DMA -to a memory region with the DMA_ATTR_WRITE_BARRIER attribute forces -all pending DMA writes to complete, and thus provides a mechanism to -strictly order DMA from a device across all intervening busses and -bridges. This barrier is not specific to a particular type of -interconnect, it applies to the system as a whole, and so its -implementation must account for the idiosyncrasies of the system all -the way from the DMA device to memory. - -As an example of a situation where DMA_ATTR_WRITE_BARRIER would be -useful, suppose that a device does a DMA write to indicate that data is -ready and available in memory. The DMA of the "completion indication" -could race with data DMA. Mapping the memory used for completion -indications with DMA_ATTR_WRITE_BARRIER would prevent the race. - DMA_ATTR_WEAK_ORDERING ---------------------- diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 24244a2f68cc..66148739b00f 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -199,7 +199,6 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr, struct mm_struct *mm; unsigned long npages; int ret; - unsigned long dma_attrs = 0; struct scatterlist *sg; unsigned int gup_flags = FOLL_WRITE; @@ -211,9 +210,6 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr, if (!context) return ERR_PTR(-EIO); - if (dmasync) - dma_attrs |= DMA_ATTR_WRITE_BARRIER; - /* * If the combination of the addr and size requested for this memory * region causes an integer overflow, return error. @@ -294,11 +290,10 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr, sg_mark_end(sg); - umem->nmap = ib_dma_map_sg_attrs(context->device, + umem->nmap = ib_dma_map_sg(context->device, umem->sg_head.sgl, umem->sg_nents, - DMA_BIDIRECTIONAL, - dma_attrs); + DMA_BIDIRECTIONAL); if (!umem->nmap) { ret = -ENOMEM; diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 4a1c4fca475a..8023071d6903 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -15,11 +15,8 @@ /** * List of possible attributes associated with a DMA mapping. The semantics * of each attribute should be defined in Documentation/DMA-attributes.txt. - * - * DMA_ATTR_WRITE_BARRIER: DMA to a memory region with this attribute - * forces all pending DMA writes to complete. */ -#define DMA_ATTR_WRITE_BARRIER (1UL << 0) + /* * DMA_ATTR_WEAK_ORDERING: Specifies that reads and writes to the mapping * may be weakly ordered, that is that reads and writes may pass each other. -- cgit v1.2.3-71-gd317 From 020003f763e24e4ed0bb3d8909f3940891536d5d Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Thu, 14 Nov 2019 08:25:28 -0800 Subject: bus: ti-sysc: Add module enable quirk for audio AESS We must set the autogating bit on enable for AESS (Audio Engine SubSystem) when probed with ti-sysc interconnect target module driver. Otherwise it won't idle properly. Cc: Peter Ujfalusi Tested-by: Peter Ujfalusi Signed-off-by: Tony Lindgren --- drivers/bus/ti-sysc.c | 14 +++++++++++++- include/linux/platform_data/ti-sysc.h | 1 + 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 97b85493aa43..99d7356e245b 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -1242,6 +1242,8 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = { SYSC_QUIRK_SWSUP_SIDLE), /* Quirks that need to be set based on detected module */ + SYSC_QUIRK("aess", 0, 0, 0x10, -1, 0x40000000, 0xffffffff, + SYSC_MODULE_QUIRK_AESS), SYSC_QUIRK("hdq1w", 0, 0, 0x14, 0x18, 0x00000006, 0xffffffff, SYSC_MODULE_QUIRK_HDQ1W), SYSC_QUIRK("hdq1w", 0, 0, 0x14, 0x18, 0x0000000a, 0xffffffff, @@ -1270,7 +1272,6 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = { #ifdef DEBUG SYSC_QUIRK("adc", 0, 0, 0x10, -1, 0x47300001, 0xffffffff, 0), SYSC_QUIRK("atl", 0, 0, -1, -1, 0x0a070100, 0xffffffff, 0), - SYSC_QUIRK("aess", 0, 0, 0x10, -1, 0x40000000, 0xffffffff, 0), SYSC_QUIRK("cm", 0, 0, -1, -1, 0x40000301, 0xffffffff, 0), SYSC_QUIRK("control", 0, 0, 0x10, -1, 0x40000900, 0xffffffff, 0), SYSC_QUIRK("cpgmac", 0, 0x1200, 0x1208, 0x1204, 0x4edb1902, @@ -1402,6 +1403,14 @@ static void sysc_clk_enable_quirk_hdq1w(struct sysc *ddata) sysc_write(ddata, offset, val); } +/* AESS (Audio Engine SubSystem) needs autogating set after enable */ +static void sysc_module_enable_quirk_aess(struct sysc *ddata) +{ + int offset = 0x7c; /* AESS_AUTO_GATING_ENABLE */ + + sysc_write(ddata, offset, 1); +} + /* I2C needs extra enable bit toggling for reset */ static void sysc_clk_quirk_i2c(struct sysc *ddata, bool enable) { @@ -1484,6 +1493,9 @@ static void sysc_init_module_quirks(struct sysc *ddata) return; } + if (ddata->cfg.quirks & SYSC_MODULE_QUIRK_AESS) + ddata->module_enable_quirk = sysc_module_enable_quirk_aess; + if (ddata->cfg.quirks & SYSC_MODULE_QUIRK_SGX) ddata->module_enable_quirk = sysc_module_enable_quirk_sgx; diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h index b5b7a3423ca8..0b9380475144 100644 --- a/include/linux/platform_data/ti-sysc.h +++ b/include/linux/platform_data/ti-sysc.h @@ -49,6 +49,7 @@ struct sysc_regbits { s8 emufree_shift; }; +#define SYSC_MODULE_QUIRK_AESS BIT(19) #define SYSC_MODULE_QUIRK_SGX BIT(18) #define SYSC_MODULE_QUIRK_HDQ1W BIT(17) #define SYSC_MODULE_QUIRK_I2C BIT(16) -- cgit v1.2.3-71-gd317 From 52ae533b8a18e7ca868e7ac5953ad7258210f320 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 7 Oct 2019 16:56:54 +0300 Subject: lib/sort: Move swap, cmp and cmp_r function types for wider use The function types for swap, cmp and cmp_r functions are already being in use by modules. Move them to types.h that everybody in kernel will be able to use generic types instead of custom ones. This adds more sense to the comment in bsearch() later on. Link: http://lkml.kernel.org/r/20191007135656.37734-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Signed-off-by: Steven Rostedt (VMware) --- include/linux/sort.h | 8 ++++---- include/linux/types.h | 5 +++++ lib/sort.c | 15 +++++---------- 3 files changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sort.h b/include/linux/sort.h index 61b96d0ebc44..b5898725fe9d 100644 --- a/include/linux/sort.h +++ b/include/linux/sort.h @@ -5,12 +5,12 @@ #include void sort_r(void *base, size_t num, size_t size, - int (*cmp)(const void *, const void *, const void *), - void (*swap)(void *, void *, int), + cmp_r_func_t cmp_func, + swap_func_t swap_func, const void *priv); void sort(void *base, size_t num, size_t size, - int (*cmp)(const void *, const void *), - void (*swap)(void *, void *, int)); + cmp_func_t cmp_func, + swap_func_t swap_func); #endif diff --git a/include/linux/types.h b/include/linux/types.h index 05030f608be3..85c0e7b18153 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -225,5 +225,10 @@ struct callback_head { typedef void (*rcu_callback_t)(struct rcu_head *head); typedef void (*call_rcu_func_t)(struct rcu_head *head, rcu_callback_t func); +typedef void (*swap_func_t)(void *a, void *b, int size); + +typedef int (*cmp_r_func_t)(const void *a, const void *b, const void *priv); +typedef int (*cmp_func_t)(const void *a, const void *b); + #endif /* __ASSEMBLY__ */ #endif /* _LINUX_TYPES_H */ diff --git a/lib/sort.c b/lib/sort.c index d54cf97e9548..3ad454411997 100644 --- a/lib/sort.c +++ b/lib/sort.c @@ -117,8 +117,6 @@ static void swap_bytes(void *a, void *b, size_t n) } while (n); } -typedef void (*swap_func_t)(void *a, void *b, int size); - /* * The values are arbitrary as long as they can't be confused with * a pointer, but small integers make for the smallest compare @@ -144,12 +142,9 @@ static void do_swap(void *a, void *b, size_t size, swap_func_t swap_func) swap_func(a, b, (int)size); } -typedef int (*cmp_func_t)(const void *, const void *); -typedef int (*cmp_r_func_t)(const void *, const void *, const void *); #define _CMP_WRAPPER ((cmp_r_func_t)0L) -static int do_cmp(const void *a, const void *b, - cmp_r_func_t cmp, const void *priv) +static int do_cmp(const void *a, const void *b, cmp_r_func_t cmp, const void *priv) { if (cmp == _CMP_WRAPPER) return ((cmp_func_t)(priv))(a, b); @@ -202,8 +197,8 @@ static size_t parent(size_t i, unsigned int lsbit, size_t size) * it less suitable for kernel use. */ void sort_r(void *base, size_t num, size_t size, - int (*cmp_func)(const void *, const void *, const void *), - void (*swap_func)(void *, void *, int size), + cmp_r_func_t cmp_func, + swap_func_t swap_func, const void *priv) { /* pre-scale counters for performance */ @@ -269,8 +264,8 @@ void sort_r(void *base, size_t num, size_t size, EXPORT_SYMBOL(sort_r); void sort(void *base, size_t num, size_t size, - int (*cmp_func)(const void *, const void *), - void (*swap_func)(void *, void *, int size)) + cmp_func_t cmp_func, + swap_func_t swap_func) { return sort_r(base, num, size, _CMP_WRAPPER, swap_func, cmp_func); } -- cgit v1.2.3-71-gd317 From e8877ec5dbba6f39d25ca3a81716c23b1760f2ee Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 7 Oct 2019 16:56:55 +0300 Subject: lib/bsearch: Use generic type for comparator function Comparator function type, cmp_func_t, is defined in the types.h, use it in bsearch() and, thus, add more sense to the corresponding comment in the code. Link: http://lkml.kernel.org/r/20191007135656.37734-2-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Signed-off-by: Steven Rostedt (VMware) --- include/linux/bsearch.h | 2 +- lib/bsearch.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bsearch.h b/include/linux/bsearch.h index 62b1eb348858..8ed53d7524ea 100644 --- a/include/linux/bsearch.h +++ b/include/linux/bsearch.h @@ -5,6 +5,6 @@ #include void *bsearch(const void *key, const void *base, size_t num, size_t size, - int (*cmp)(const void *key, const void *elt)); + cmp_func_t cmp); #endif /* _LINUX_BSEARCH_H */ diff --git a/lib/bsearch.c b/lib/bsearch.c index 8baa83968162..8b3aae5ae77a 100644 --- a/lib/bsearch.c +++ b/lib/bsearch.c @@ -29,7 +29,7 @@ * the same comparison function for both sort() and bsearch(). */ void *bsearch(const void *key, const void *base, size_t num, size_t size, - int (*cmp)(const void *key, const void *elt)) + cmp_func_t cmp) { const char *pivot; int result; -- cgit v1.2.3-71-gd317 From 353cade3149c27b53260932ee3ff1ebde405976d Mon Sep 17 00:00:00 2001 From: Piotr Maziarz Date: Thu, 7 Nov 2019 13:45:37 +0100 Subject: seq_buf: Add printing formatted hex dumps Provided function is an analogue of print_hex_dump(). Implementing this function in seq_buf allows using for multiple purposes (e.g. for tracing) and therefore prevents from code duplication in every layer that uses seq_buf. print_hex_dump() is an essential part of logging data to dmesg. Adding similar capability for other purposes is beneficial to all users. Example usage: seq_buf_hex_dump(seq, "", DUMP_PREFIX_OFFSET, 16, 4, buf, ARRAY_SIZE(buf), true); Example output: 00000000: 00000000 ffffff10 ffffff32 ffff3210 ........2....2.. 00000010: ffff3210 83d00437 c0700000 00000000 .2..7.....p..... 00000020: 02010004 0000000f 0000000f 00004002 .............@.. 00000030: 00000fff 00000000 ........ Link: http://lkml.kernel.org/r/1573130738-29390-1-git-send-email-piotrx.maziarz@linux.intel.com Signed-off-by: Piotr Maziarz Signed-off-by: Cezary Rojewski Signed-off-by: Steven Rostedt (VMware) --- include/linux/seq_buf.h | 3 +++ lib/seq_buf.c | 62 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 65 insertions(+) (limited to 'include/linux') diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h index aa5deb041c25..fb0205d87d3c 100644 --- a/include/linux/seq_buf.h +++ b/include/linux/seq_buf.h @@ -125,6 +125,9 @@ extern int seq_buf_putmem(struct seq_buf *s, const void *mem, unsigned int len); extern int seq_buf_putmem_hex(struct seq_buf *s, const void *mem, unsigned int len); extern int seq_buf_path(struct seq_buf *s, const struct path *path, const char *esc); +extern int seq_buf_hex_dump(struct seq_buf *s, const char *prefix_str, + int prefix_type, int rowsize, int groupsize, + const void *buf, size_t len, bool ascii); #ifdef CONFIG_BINARY_PRINTF extern int diff --git a/lib/seq_buf.c b/lib/seq_buf.c index bd807f545a9d..4e865d42ab03 100644 --- a/lib/seq_buf.c +++ b/lib/seq_buf.c @@ -328,3 +328,65 @@ int seq_buf_to_user(struct seq_buf *s, char __user *ubuf, int cnt) s->readpos += cnt; return cnt; } + +/** + * seq_buf_hex_dump - print formatted hex dump into the sequence buffer + * @s: seq_buf descriptor + * @prefix_str: string to prefix each line with; + * caller supplies trailing spaces for alignment if desired + * @prefix_type: controls whether prefix of an offset, address, or none + * is printed (%DUMP_PREFIX_OFFSET, %DUMP_PREFIX_ADDRESS, %DUMP_PREFIX_NONE) + * @rowsize: number of bytes to print per line; must be 16 or 32 + * @groupsize: number of bytes to print at a time (1, 2, 4, 8; default = 1) + * @buf: data blob to dump + * @len: number of bytes in the @buf + * @ascii: include ASCII after the hex output + * + * Function is an analogue of print_hex_dump() and thus has similar interface. + * + * linebuf size is maximal length for one line. + * 32 * 3 - maximum bytes per line, each printed into 2 chars + 1 for + * separating space + * 2 - spaces separating hex dump and ascii representation + * 32 - ascii representation + * 1 - terminating '\0' + * + * Returns zero on success, -1 on overflow + */ +int seq_buf_hex_dump(struct seq_buf *s, const char *prefix_str, int prefix_type, + int rowsize, int groupsize, + const void *buf, size_t len, bool ascii) +{ + const u8 *ptr = buf; + int i, linelen, remaining = len; + unsigned char linebuf[32 * 3 + 2 + 32 + 1]; + int ret; + + if (rowsize != 16 && rowsize != 32) + rowsize = 16; + + for (i = 0; i < len; i += rowsize) { + linelen = min(remaining, rowsize); + remaining -= rowsize; + + hex_dump_to_buffer(ptr + i, linelen, rowsize, groupsize, + linebuf, sizeof(linebuf), ascii); + + switch (prefix_type) { + case DUMP_PREFIX_ADDRESS: + ret = seq_buf_printf(s, "%s%p: %s\n", + prefix_str, ptr + i, linebuf); + break; + case DUMP_PREFIX_OFFSET: + ret = seq_buf_printf(s, "%s%.8x: %s\n", + prefix_str, i, linebuf); + break; + default: + ret = seq_buf_printf(s, "%s%s\n", prefix_str, linebuf); + break; + } + if (ret) + return ret; + } + return 0; +} -- cgit v1.2.3-71-gd317 From ef56e047b2bd4dabb801fd073dfcab5f40de5f78 Mon Sep 17 00:00:00 2001 From: Piotr Maziarz Date: Thu, 7 Nov 2019 13:45:38 +0100 Subject: tracing: Use seq_buf_hex_dump() to dump buffers Without this, buffers can be printed with __print_array macro that has no formatting options and can be hard to read. The other way is to mimic formatting capability with multiple calls of trace event with one call per row which gives performance impact and different timestamp in each row. Link: http://lkml.kernel.org/r/1573130738-29390-2-git-send-email-piotrx.maziarz@linux.intel.com Signed-off-by: Piotr Maziarz Signed-off-by: Cezary Rojewski Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 5 +++++ include/linux/trace_seq.h | 4 ++++ include/trace/trace_events.h | 6 ++++++ kernel/trace/trace_output.c | 15 +++++++++++++++ kernel/trace/trace_seq.c | 30 ++++++++++++++++++++++++++++++ 5 files changed, 60 insertions(+) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 30a8cdcfd4a4..60a41b7069dd 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -45,6 +45,11 @@ const char *trace_print_array_seq(struct trace_seq *p, const void *buf, int count, size_t el_size); +const char * +trace_print_hex_dump_seq(struct trace_seq *p, const char *prefix_str, + int prefix_type, int rowsize, int groupsize, + const void *buf, size_t len, bool ascii); + struct trace_iterator; struct trace_event; diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h index 6609b39a7232..6c30508fca19 100644 --- a/include/linux/trace_seq.h +++ b/include/linux/trace_seq.h @@ -92,6 +92,10 @@ extern int trace_seq_path(struct trace_seq *s, const struct path *path); extern void trace_seq_bitmask(struct trace_seq *s, const unsigned long *maskp, int nmaskbits); +extern int trace_seq_hex_dump(struct trace_seq *s, const char *prefix_str, + int prefix_type, int rowsize, int groupsize, + const void *buf, size_t len, bool ascii); + #else /* CONFIG_TRACING */ static inline void trace_seq_printf(struct trace_seq *s, const char *fmt, ...) { diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h index 4ecdfe2e3580..7089760d4c7a 100644 --- a/include/trace/trace_events.h +++ b/include/trace/trace_events.h @@ -340,6 +340,12 @@ TRACE_MAKE_SYSTEM_STR(); trace_print_array_seq(p, array, count, el_size); \ }) +#undef __print_hex_dump +#define __print_hex_dump(prefix_str, prefix_type, \ + rowsize, groupsize, buf, len, ascii) \ + trace_print_hex_dump_seq(p, prefix_str, prefix_type, \ + rowsize, groupsize, buf, len, ascii) + #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ static notrace enum print_line_t \ diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index d54ce252b05a..d9b4b7c22db4 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -274,6 +274,21 @@ trace_print_array_seq(struct trace_seq *p, const void *buf, int count, } EXPORT_SYMBOL(trace_print_array_seq); +const char * +trace_print_hex_dump_seq(struct trace_seq *p, const char *prefix_str, + int prefix_type, int rowsize, int groupsize, + const void *buf, size_t len, bool ascii) +{ + const char *ret = trace_seq_buffer_ptr(p); + + trace_seq_putc(p, '\n'); + trace_seq_hex_dump(p, prefix_str, prefix_type, + rowsize, groupsize, buf, len, ascii); + trace_seq_putc(p, 0); + return ret; +} +EXPORT_SYMBOL(trace_print_hex_dump_seq); + int trace_raw_output_prep(struct trace_iterator *iter, struct trace_event *trace_event) { diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c index 6b1c562ffdaf..344e4c1aa09c 100644 --- a/kernel/trace/trace_seq.c +++ b/kernel/trace/trace_seq.c @@ -376,3 +376,33 @@ int trace_seq_to_user(struct trace_seq *s, char __user *ubuf, int cnt) return seq_buf_to_user(&s->seq, ubuf, cnt); } EXPORT_SYMBOL_GPL(trace_seq_to_user); + +int trace_seq_hex_dump(struct trace_seq *s, const char *prefix_str, + int prefix_type, int rowsize, int groupsize, + const void *buf, size_t len, bool ascii) +{ + unsigned int save_len = s->seq.len; + + if (s->full) + return 0; + + __trace_seq_init(s); + + if (TRACE_SEQ_BUF_LEFT(s) < 1) { + s->full = 1; + return 0; + } + + seq_buf_hex_dump(&(s->seq), prefix_str, + prefix_type, rowsize, groupsize, + buf, len, ascii); + + if (unlikely(seq_buf_has_overflowed(&s->seq))) { + s->seq.len = save_len; + s->full = 1; + return 0; + } + + return 1; +} +EXPORT_SYMBOL(trace_seq_hex_dump); -- cgit v1.2.3-71-gd317 From db205c766862edae48d64e69e2f2502e2a3e9135 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Thu, 14 Nov 2019 10:57:37 +0100 Subject: vsock: remove vm_sockets_get_local_cid() vm_sockets_get_local_cid() is only used in virtio_transport_common.c. We can replace it calling the virtio_transport_get_ops() and using the get_local_cid() callback registered by the transport. Reviewed-by: Stefan Hajnoczi Reviewed-by: Jorgen Hansen Signed-off-by: Stefano Garzarella Signed-off-by: David S. Miller --- include/linux/vm_sockets.h | 2 -- net/vmw_vsock/af_vsock.c | 10 ---------- net/vmw_vsock/virtio_transport_common.c | 2 +- 3 files changed, 1 insertion(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vm_sockets.h b/include/linux/vm_sockets.h index 33f1a2ecd905..7dd899ccb920 100644 --- a/include/linux/vm_sockets.h +++ b/include/linux/vm_sockets.h @@ -10,6 +10,4 @@ #include -int vm_sockets_get_local_cid(void); - #endif /* _VM_SOCKETS_H */ diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 1f4fde4711b6..eb13693e9d04 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -129,16 +129,6 @@ static struct proto vsock_proto = { static const struct vsock_transport *transport; static DEFINE_MUTEX(vsock_register_mutex); -/**** EXPORTS ****/ - -/* Get the ID of the local context. This is transport dependent. */ - -int vm_sockets_get_local_cid(void) -{ - return transport->get_local_cid(); -} -EXPORT_SYMBOL_GPL(vm_sockets_get_local_cid); - /**** UTILS ****/ /* Each bound VSocket is stored in the bind hash table and each connected diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 828edd88488c..3edc373d2acc 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -168,7 +168,7 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, struct virtio_vsock_pkt *pkt; u32 pkt_len = info->pkt_len; - src_cid = vm_sockets_get_local_cid(); + src_cid = virtio_transport_get_ops()->transport.get_local_cid(); src_port = vsk->local_addr.svm_port; if (!info->remote_cid) { dst_cid = vsk->remote_addr.svm_cid; -- cgit v1.2.3-71-gd317 From 3603a2e991a82e5094c3107a792859b08342aed3 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Thu, 14 Nov 2019 10:57:38 +0100 Subject: vsock: remove include/linux/vm_sockets.h file This header file now only includes the "uapi/linux/vm_sockets.h". We can include directly it when needed. Reviewed-by: Stefan Hajnoczi Reviewed-by: Jorgen Hansen Signed-off-by: Stefano Garzarella Signed-off-by: David S. Miller --- include/linux/vm_sockets.h | 13 ------------- include/net/af_vsock.h | 2 +- include/net/vsock_addr.h | 2 +- net/vmw_vsock/vmci_transport_notify.h | 1 - 4 files changed, 2 insertions(+), 16 deletions(-) delete mode 100644 include/linux/vm_sockets.h (limited to 'include/linux') diff --git a/include/linux/vm_sockets.h b/include/linux/vm_sockets.h deleted file mode 100644 index 7dd899ccb920..000000000000 --- a/include/linux/vm_sockets.h +++ /dev/null @@ -1,13 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * VMware vSockets Driver - * - * Copyright (C) 2007-2013 VMware, Inc. All rights reserved. - */ - -#ifndef _VM_SOCKETS_H -#define _VM_SOCKETS_H - -#include - -#endif /* _VM_SOCKETS_H */ diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 80ea0f93d3f7..c660402b10f2 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -10,7 +10,7 @@ #include #include -#include +#include #include "vsock_addr.h" diff --git a/include/net/vsock_addr.h b/include/net/vsock_addr.h index 57d2db5c4bdf..cf8cc140d68d 100644 --- a/include/net/vsock_addr.h +++ b/include/net/vsock_addr.h @@ -8,7 +8,7 @@ #ifndef _VSOCK_ADDR_H_ #define _VSOCK_ADDR_H_ -#include +#include void vsock_addr_init(struct sockaddr_vm *addr, u32 cid, u32 port); int vsock_addr_validate(const struct sockaddr_vm *addr); diff --git a/net/vmw_vsock/vmci_transport_notify.h b/net/vmw_vsock/vmci_transport_notify.h index 7843f08d4290..a1aa5a998c0e 100644 --- a/net/vmw_vsock/vmci_transport_notify.h +++ b/net/vmw_vsock/vmci_transport_notify.h @@ -11,7 +11,6 @@ #include #include #include -#include #include "vmci_transport.h" -- cgit v1.2.3-71-gd317 From 4c7246dc45e2706770d5233f7ce1597a07e069ba Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Thu, 14 Nov 2019 10:57:40 +0100 Subject: vsock/virtio: add transport parameter to the virtio_transport_reset_no_sock() We are going to add 'struct vsock_sock *' parameter to virtio_transport_get_ops(). In some cases, like in the virtio_transport_reset_no_sock(), we don't have any socket assigned to the packet received, so we can't use the virtio_transport_get_ops(). In order to allow virtio_transport_reset_no_sock() to use the '.send_pkt' callback from the 'vhost_transport' or 'virtio_transport', we add the 'struct virtio_transport *' to it and to its caller: virtio_transport_recv_pkt(). We moved the 'vhost_transport' and 'virtio_transport' definition, to pass their address to the virtio_transport_recv_pkt(). Reviewed-by: Stefan Hajnoczi Signed-off-by: Stefano Garzarella Signed-off-by: David S. Miller --- drivers/vhost/vsock.c | 94 +++++++++---------- include/linux/virtio_vsock.h | 3 +- net/vmw_vsock/virtio_transport.c | 160 ++++++++++++++++---------------- net/vmw_vsock/virtio_transport_common.c | 12 +-- 4 files changed, 135 insertions(+), 134 deletions(-) (limited to 'include/linux') diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 9f57736fe15e..92ab3852c954 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -384,6 +384,52 @@ static bool vhost_vsock_more_replies(struct vhost_vsock *vsock) return val < vq->num; } +static struct virtio_transport vhost_transport = { + .transport = { + .get_local_cid = vhost_transport_get_local_cid, + + .init = virtio_transport_do_socket_init, + .destruct = virtio_transport_destruct, + .release = virtio_transport_release, + .connect = virtio_transport_connect, + .shutdown = virtio_transport_shutdown, + .cancel_pkt = vhost_transport_cancel_pkt, + + .dgram_enqueue = virtio_transport_dgram_enqueue, + .dgram_dequeue = virtio_transport_dgram_dequeue, + .dgram_bind = virtio_transport_dgram_bind, + .dgram_allow = virtio_transport_dgram_allow, + + .stream_enqueue = virtio_transport_stream_enqueue, + .stream_dequeue = virtio_transport_stream_dequeue, + .stream_has_data = virtio_transport_stream_has_data, + .stream_has_space = virtio_transport_stream_has_space, + .stream_rcvhiwat = virtio_transport_stream_rcvhiwat, + .stream_is_active = virtio_transport_stream_is_active, + .stream_allow = virtio_transport_stream_allow, + + .notify_poll_in = virtio_transport_notify_poll_in, + .notify_poll_out = virtio_transport_notify_poll_out, + .notify_recv_init = virtio_transport_notify_recv_init, + .notify_recv_pre_block = virtio_transport_notify_recv_pre_block, + .notify_recv_pre_dequeue = virtio_transport_notify_recv_pre_dequeue, + .notify_recv_post_dequeue = virtio_transport_notify_recv_post_dequeue, + .notify_send_init = virtio_transport_notify_send_init, + .notify_send_pre_block = virtio_transport_notify_send_pre_block, + .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue, + .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue, + + .set_buffer_size = virtio_transport_set_buffer_size, + .set_min_buffer_size = virtio_transport_set_min_buffer_size, + .set_max_buffer_size = virtio_transport_set_max_buffer_size, + .get_buffer_size = virtio_transport_get_buffer_size, + .get_min_buffer_size = virtio_transport_get_min_buffer_size, + .get_max_buffer_size = virtio_transport_get_max_buffer_size, + }, + + .send_pkt = vhost_transport_send_pkt, +}; + static void vhost_vsock_handle_tx_kick(struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue, @@ -438,7 +484,7 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work) /* Only accept correctly addressed packets */ if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid) - virtio_transport_recv_pkt(pkt); + virtio_transport_recv_pkt(&vhost_transport, pkt); else virtio_transport_free_pkt(pkt); @@ -786,52 +832,6 @@ static struct miscdevice vhost_vsock_misc = { .fops = &vhost_vsock_fops, }; -static struct virtio_transport vhost_transport = { - .transport = { - .get_local_cid = vhost_transport_get_local_cid, - - .init = virtio_transport_do_socket_init, - .destruct = virtio_transport_destruct, - .release = virtio_transport_release, - .connect = virtio_transport_connect, - .shutdown = virtio_transport_shutdown, - .cancel_pkt = vhost_transport_cancel_pkt, - - .dgram_enqueue = virtio_transport_dgram_enqueue, - .dgram_dequeue = virtio_transport_dgram_dequeue, - .dgram_bind = virtio_transport_dgram_bind, - .dgram_allow = virtio_transport_dgram_allow, - - .stream_enqueue = virtio_transport_stream_enqueue, - .stream_dequeue = virtio_transport_stream_dequeue, - .stream_has_data = virtio_transport_stream_has_data, - .stream_has_space = virtio_transport_stream_has_space, - .stream_rcvhiwat = virtio_transport_stream_rcvhiwat, - .stream_is_active = virtio_transport_stream_is_active, - .stream_allow = virtio_transport_stream_allow, - - .notify_poll_in = virtio_transport_notify_poll_in, - .notify_poll_out = virtio_transport_notify_poll_out, - .notify_recv_init = virtio_transport_notify_recv_init, - .notify_recv_pre_block = virtio_transport_notify_recv_pre_block, - .notify_recv_pre_dequeue = virtio_transport_notify_recv_pre_dequeue, - .notify_recv_post_dequeue = virtio_transport_notify_recv_post_dequeue, - .notify_send_init = virtio_transport_notify_send_init, - .notify_send_pre_block = virtio_transport_notify_send_pre_block, - .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue, - .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue, - - .set_buffer_size = virtio_transport_set_buffer_size, - .set_min_buffer_size = virtio_transport_set_min_buffer_size, - .set_max_buffer_size = virtio_transport_set_max_buffer_size, - .get_buffer_size = virtio_transport_get_buffer_size, - .get_min_buffer_size = virtio_transport_get_min_buffer_size, - .get_max_buffer_size = virtio_transport_get_max_buffer_size, - }, - - .send_pkt = vhost_transport_send_pkt, -}; - static int __init vhost_vsock_init(void) { int ret; diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 07875ccc7bb5..b139f76060a6 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -150,7 +150,8 @@ virtio_transport_dgram_enqueue(struct vsock_sock *vsk, void virtio_transport_destruct(struct vsock_sock *vsk); -void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt); +void virtio_transport_recv_pkt(struct virtio_transport *t, + struct virtio_vsock_pkt *pkt); void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt); void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt); u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 wanted); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 082a30936690..3756f0857946 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -86,33 +86,6 @@ out_rcu: return ret; } -static void virtio_transport_loopback_work(struct work_struct *work) -{ - struct virtio_vsock *vsock = - container_of(work, struct virtio_vsock, loopback_work); - LIST_HEAD(pkts); - - spin_lock_bh(&vsock->loopback_list_lock); - list_splice_init(&vsock->loopback_list, &pkts); - spin_unlock_bh(&vsock->loopback_list_lock); - - mutex_lock(&vsock->rx_lock); - - if (!vsock->rx_run) - goto out; - - while (!list_empty(&pkts)) { - struct virtio_vsock_pkt *pkt; - - pkt = list_first_entry(&pkts, struct virtio_vsock_pkt, list); - list_del_init(&pkt->list); - - virtio_transport_recv_pkt(pkt); - } -out: - mutex_unlock(&vsock->rx_lock); -} - static int virtio_transport_send_pkt_loopback(struct virtio_vsock *vsock, struct virtio_vsock_pkt *pkt) { @@ -370,59 +343,6 @@ static bool virtio_transport_more_replies(struct virtio_vsock *vsock) return val < virtqueue_get_vring_size(vq); } -static void virtio_transport_rx_work(struct work_struct *work) -{ - struct virtio_vsock *vsock = - container_of(work, struct virtio_vsock, rx_work); - struct virtqueue *vq; - - vq = vsock->vqs[VSOCK_VQ_RX]; - - mutex_lock(&vsock->rx_lock); - - if (!vsock->rx_run) - goto out; - - do { - virtqueue_disable_cb(vq); - for (;;) { - struct virtio_vsock_pkt *pkt; - unsigned int len; - - if (!virtio_transport_more_replies(vsock)) { - /* Stop rx until the device processes already - * pending replies. Leave rx virtqueue - * callbacks disabled. - */ - goto out; - } - - pkt = virtqueue_get_buf(vq, &len); - if (!pkt) { - break; - } - - vsock->rx_buf_nr--; - - /* Drop short/long packets */ - if (unlikely(len < sizeof(pkt->hdr) || - len > sizeof(pkt->hdr) + pkt->len)) { - virtio_transport_free_pkt(pkt); - continue; - } - - pkt->len = len - sizeof(pkt->hdr); - virtio_transport_deliver_tap_pkt(pkt); - virtio_transport_recv_pkt(pkt); - } - } while (!virtqueue_enable_cb(vq)); - -out: - if (vsock->rx_buf_nr < vsock->rx_buf_max_nr / 2) - virtio_vsock_rx_fill(vsock); - mutex_unlock(&vsock->rx_lock); -} - /* event_lock must be held */ static int virtio_vsock_event_fill_one(struct virtio_vsock *vsock, struct virtio_vsock_event *event) @@ -586,6 +506,86 @@ static struct virtio_transport virtio_transport = { .send_pkt = virtio_transport_send_pkt, }; +static void virtio_transport_loopback_work(struct work_struct *work) +{ + struct virtio_vsock *vsock = + container_of(work, struct virtio_vsock, loopback_work); + LIST_HEAD(pkts); + + spin_lock_bh(&vsock->loopback_list_lock); + list_splice_init(&vsock->loopback_list, &pkts); + spin_unlock_bh(&vsock->loopback_list_lock); + + mutex_lock(&vsock->rx_lock); + + if (!vsock->rx_run) + goto out; + + while (!list_empty(&pkts)) { + struct virtio_vsock_pkt *pkt; + + pkt = list_first_entry(&pkts, struct virtio_vsock_pkt, list); + list_del_init(&pkt->list); + + virtio_transport_recv_pkt(&virtio_transport, pkt); + } +out: + mutex_unlock(&vsock->rx_lock); +} + +static void virtio_transport_rx_work(struct work_struct *work) +{ + struct virtio_vsock *vsock = + container_of(work, struct virtio_vsock, rx_work); + struct virtqueue *vq; + + vq = vsock->vqs[VSOCK_VQ_RX]; + + mutex_lock(&vsock->rx_lock); + + if (!vsock->rx_run) + goto out; + + do { + virtqueue_disable_cb(vq); + for (;;) { + struct virtio_vsock_pkt *pkt; + unsigned int len; + + if (!virtio_transport_more_replies(vsock)) { + /* Stop rx until the device processes already + * pending replies. Leave rx virtqueue + * callbacks disabled. + */ + goto out; + } + + pkt = virtqueue_get_buf(vq, &len); + if (!pkt) { + break; + } + + vsock->rx_buf_nr--; + + /* Drop short/long packets */ + if (unlikely(len < sizeof(pkt->hdr) || + len > sizeof(pkt->hdr) + pkt->len)) { + virtio_transport_free_pkt(pkt); + continue; + } + + pkt->len = len - sizeof(pkt->hdr); + virtio_transport_deliver_tap_pkt(pkt); + virtio_transport_recv_pkt(&virtio_transport, pkt); + } + } while (!virtqueue_enable_cb(vq)); + +out: + if (vsock->rx_buf_nr < vsock->rx_buf_max_nr / 2) + virtio_vsock_rx_fill(vsock); + mutex_unlock(&vsock->rx_lock); +} + static int virtio_vsock_probe(struct virtio_device *vdev) { vq_callback_t *callbacks[] = { diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 3edc373d2acc..e7b5e99842c9 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -745,9 +745,9 @@ static int virtio_transport_reset(struct vsock_sock *vsk, /* Normally packets are associated with a socket. There may be no socket if an * attempt was made to connect to a socket that does not exist. */ -static int virtio_transport_reset_no_sock(struct virtio_vsock_pkt *pkt) +static int virtio_transport_reset_no_sock(const struct virtio_transport *t, + struct virtio_vsock_pkt *pkt) { - const struct virtio_transport *t; struct virtio_vsock_pkt *reply; struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_RST, @@ -767,7 +767,6 @@ static int virtio_transport_reset_no_sock(struct virtio_vsock_pkt *pkt) if (!reply) return -ENOMEM; - t = virtio_transport_get_ops(); if (!t) { virtio_transport_free_pkt(reply); return -ENOTCONN; @@ -1109,7 +1108,8 @@ static bool virtio_transport_space_update(struct sock *sk, /* We are under the virtio-vsock's vsock->rx_lock or vhost-vsock's vq->mutex * lock. */ -void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt) +void virtio_transport_recv_pkt(struct virtio_transport *t, + struct virtio_vsock_pkt *pkt) { struct sockaddr_vm src, dst; struct vsock_sock *vsk; @@ -1131,7 +1131,7 @@ void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt) le32_to_cpu(pkt->hdr.fwd_cnt)); if (le16_to_cpu(pkt->hdr.type) != VIRTIO_VSOCK_TYPE_STREAM) { - (void)virtio_transport_reset_no_sock(pkt); + (void)virtio_transport_reset_no_sock(t, pkt); goto free_pkt; } @@ -1142,7 +1142,7 @@ void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt) if (!sk) { sk = vsock_find_bound_socket(&dst); if (!sk) { - (void)virtio_transport_reset_no_sock(pkt); + (void)virtio_transport_reset_no_sock(t, pkt); goto free_pkt; } } -- cgit v1.2.3-71-gd317 From b9f2b0ffde0c9b666b2b1672eb468b8f805a9b97 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Thu, 14 Nov 2019 10:57:42 +0100 Subject: vsock: handle buffer_size sockopts in the core virtio_transport and vmci_transport handle the buffer_size sockopts in a very similar way. In order to support multiple transports, this patch moves this handling in the core to allow the user to change the options also if the socket is not yet assigned to any transport. This patch also adds the '.notify_buffer_size' callback in the 'struct virtio_transport' in order to inform the transport, when the buffer_size is changed by the user. It is also useful to limit the 'buffer_size' requested (e.g. virtio transports). Acked-by: Dexuan Cui Reviewed-by: Stefan Hajnoczi Reviewed-by: Jorgen Hansen Signed-off-by: Stefano Garzarella Signed-off-by: David S. Miller --- drivers/vhost/vsock.c | 7 +-- include/linux/virtio_vsock.h | 15 +----- include/net/af_vsock.h | 15 +++--- net/vmw_vsock/af_vsock.c | 43 ++++++++++++++--- net/vmw_vsock/hyperv_transport.c | 36 -------------- net/vmw_vsock/virtio_transport.c | 8 +-- net/vmw_vsock/virtio_transport_common.c | 79 +++++------------------------- net/vmw_vsock/vmci_transport.c | 86 ++++----------------------------- net/vmw_vsock/vmci_transport.h | 3 -- 9 files changed, 65 insertions(+), 227 deletions(-) (limited to 'include/linux') diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 92ab3852c954..6d7e4f022748 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -418,13 +418,8 @@ static struct virtio_transport vhost_transport = { .notify_send_pre_block = virtio_transport_notify_send_pre_block, .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue, .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue, + .notify_buffer_size = virtio_transport_notify_buffer_size, - .set_buffer_size = virtio_transport_set_buffer_size, - .set_min_buffer_size = virtio_transport_set_min_buffer_size, - .set_max_buffer_size = virtio_transport_set_max_buffer_size, - .get_buffer_size = virtio_transport_get_buffer_size, - .get_min_buffer_size = virtio_transport_get_min_buffer_size, - .get_max_buffer_size = virtio_transport_get_max_buffer_size, }, .send_pkt = vhost_transport_send_pkt, diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index b139f76060a6..71c81e0dc8f2 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -7,9 +7,6 @@ #include #include -#define VIRTIO_VSOCK_DEFAULT_MIN_BUF_SIZE 128 -#define VIRTIO_VSOCK_DEFAULT_BUF_SIZE (1024 * 256) -#define VIRTIO_VSOCK_DEFAULT_MAX_BUF_SIZE (1024 * 256) #define VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE (1024 * 4) #define VIRTIO_VSOCK_MAX_BUF_SIZE 0xFFFFFFFFUL #define VIRTIO_VSOCK_MAX_PKT_BUF_SIZE (1024 * 64) @@ -25,11 +22,6 @@ enum { struct virtio_vsock_sock { struct vsock_sock *vsk; - /* Protected by lock_sock(sk_vsock(trans->vsk)) */ - u32 buf_size; - u32 buf_size_min; - u32 buf_size_max; - spinlock_t tx_lock; spinlock_t rx_lock; @@ -92,12 +84,6 @@ s64 virtio_transport_stream_has_space(struct vsock_sock *vsk); int virtio_transport_do_socket_init(struct vsock_sock *vsk, struct vsock_sock *psk); -u64 virtio_transport_get_buffer_size(struct vsock_sock *vsk); -u64 virtio_transport_get_min_buffer_size(struct vsock_sock *vsk); -u64 virtio_transport_get_max_buffer_size(struct vsock_sock *vsk); -void virtio_transport_set_buffer_size(struct vsock_sock *vsk, u64 val); -void virtio_transport_set_min_buffer_size(struct vsock_sock *vsk, u64 val); -void virtio_transport_set_max_buffer_size(struct vsock_sock *vs, u64 val); int virtio_transport_notify_poll_in(struct vsock_sock *vsk, size_t target, @@ -124,6 +110,7 @@ int virtio_transport_notify_send_pre_enqueue(struct vsock_sock *vsk, struct vsock_transport_send_notify_data *data); int virtio_transport_notify_send_post_enqueue(struct vsock_sock *vsk, ssize_t written, struct vsock_transport_send_notify_data *data); +void virtio_transport_notify_buffer_size(struct vsock_sock *vsk, u64 *val); u64 virtio_transport_stream_rcvhiwat(struct vsock_sock *vsk); bool virtio_transport_stream_is_active(struct vsock_sock *vsk); diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 2ca67d048de4..4b5d16840fd4 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -65,6 +65,11 @@ struct vsock_sock { bool sent_request; bool ignore_connecting_rst; + /* Protected by lock_sock(sk) */ + u64 buffer_size; + u64 buffer_min_size; + u64 buffer_max_size; + /* Private to transport. */ void *trans; }; @@ -140,18 +145,12 @@ struct vsock_transport { struct vsock_transport_send_notify_data *); int (*notify_send_post_enqueue)(struct vsock_sock *, ssize_t, struct vsock_transport_send_notify_data *); + /* sk_lock held by the caller */ + void (*notify_buffer_size)(struct vsock_sock *, u64 *); /* Shutdown. */ int (*shutdown)(struct vsock_sock *, int); - /* Buffer sizes. */ - void (*set_buffer_size)(struct vsock_sock *, u64); - void (*set_min_buffer_size)(struct vsock_sock *, u64); - void (*set_max_buffer_size)(struct vsock_sock *, u64); - u64 (*get_buffer_size)(struct vsock_sock *); - u64 (*get_min_buffer_size)(struct vsock_sock *); - u64 (*get_max_buffer_size)(struct vsock_sock *); - /* Addressing. */ u32 (*get_local_cid)(void); }; diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index f057acb0ee29..11b88094e3b2 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -126,6 +126,10 @@ static struct proto vsock_proto = { */ #define VSOCK_DEFAULT_CONNECT_TIMEOUT (2 * HZ) +#define VSOCK_DEFAULT_BUFFER_SIZE (1024 * 256) +#define VSOCK_DEFAULT_BUFFER_MAX_SIZE (1024 * 256) +#define VSOCK_DEFAULT_BUFFER_MIN_SIZE 128 + static const struct vsock_transport *transport_single; static DEFINE_MUTEX(vsock_register_mutex); @@ -613,10 +617,16 @@ struct sock *__vsock_create(struct net *net, vsk->trusted = psk->trusted; vsk->owner = get_cred(psk->owner); vsk->connect_timeout = psk->connect_timeout; + vsk->buffer_size = psk->buffer_size; + vsk->buffer_min_size = psk->buffer_min_size; + vsk->buffer_max_size = psk->buffer_max_size; } else { vsk->trusted = capable(CAP_NET_ADMIN); vsk->owner = get_current_cred(); vsk->connect_timeout = VSOCK_DEFAULT_CONNECT_TIMEOUT; + vsk->buffer_size = VSOCK_DEFAULT_BUFFER_SIZE; + vsk->buffer_min_size = VSOCK_DEFAULT_BUFFER_MIN_SIZE; + vsk->buffer_max_size = VSOCK_DEFAULT_BUFFER_MAX_SIZE; } if (vsk->transport->init(vsk, psk) < 0) { @@ -1366,6 +1376,23 @@ out: return err; } +static void vsock_update_buffer_size(struct vsock_sock *vsk, + const struct vsock_transport *transport, + u64 val) +{ + if (val > vsk->buffer_max_size) + val = vsk->buffer_max_size; + + if (val < vsk->buffer_min_size) + val = vsk->buffer_min_size; + + if (val != vsk->buffer_size && + transport && transport->notify_buffer_size) + transport->notify_buffer_size(vsk, &val); + + vsk->buffer_size = val; +} + static int vsock_stream_setsockopt(struct socket *sock, int level, int optname, @@ -1403,17 +1430,19 @@ static int vsock_stream_setsockopt(struct socket *sock, switch (optname) { case SO_VM_SOCKETS_BUFFER_SIZE: COPY_IN(val); - transport->set_buffer_size(vsk, val); + vsock_update_buffer_size(vsk, transport, val); break; case SO_VM_SOCKETS_BUFFER_MAX_SIZE: COPY_IN(val); - transport->set_max_buffer_size(vsk, val); + vsk->buffer_max_size = val; + vsock_update_buffer_size(vsk, transport, vsk->buffer_size); break; case SO_VM_SOCKETS_BUFFER_MIN_SIZE: COPY_IN(val); - transport->set_min_buffer_size(vsk, val); + vsk->buffer_min_size = val; + vsock_update_buffer_size(vsk, transport, vsk->buffer_size); break; case SO_VM_SOCKETS_CONNECT_TIMEOUT: { @@ -1454,7 +1483,6 @@ static int vsock_stream_getsockopt(struct socket *sock, int len; struct sock *sk; struct vsock_sock *vsk; - const struct vsock_transport *transport; u64 val; if (level != AF_VSOCK) @@ -1478,21 +1506,20 @@ static int vsock_stream_getsockopt(struct socket *sock, err = 0; sk = sock->sk; vsk = vsock_sk(sk); - transport = vsk->transport; switch (optname) { case SO_VM_SOCKETS_BUFFER_SIZE: - val = transport->get_buffer_size(vsk); + val = vsk->buffer_size; COPY_OUT(val); break; case SO_VM_SOCKETS_BUFFER_MAX_SIZE: - val = transport->get_max_buffer_size(vsk); + val = vsk->buffer_max_size; COPY_OUT(val); break; case SO_VM_SOCKETS_BUFFER_MIN_SIZE: - val = transport->get_min_buffer_size(vsk); + val = vsk->buffer_min_size; COPY_OUT(val); break; diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index 7fa09c5e4625..ab947561543e 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -845,36 +845,6 @@ int hvs_notify_send_post_enqueue(struct vsock_sock *vsk, ssize_t written, return 0; } -static void hvs_set_buffer_size(struct vsock_sock *vsk, u64 val) -{ - /* Ignored. */ -} - -static void hvs_set_min_buffer_size(struct vsock_sock *vsk, u64 val) -{ - /* Ignored. */ -} - -static void hvs_set_max_buffer_size(struct vsock_sock *vsk, u64 val) -{ - /* Ignored. */ -} - -static u64 hvs_get_buffer_size(struct vsock_sock *vsk) -{ - return -ENOPROTOOPT; -} - -static u64 hvs_get_min_buffer_size(struct vsock_sock *vsk) -{ - return -ENOPROTOOPT; -} - -static u64 hvs_get_max_buffer_size(struct vsock_sock *vsk) -{ - return -ENOPROTOOPT; -} - static struct vsock_transport hvs_transport = { .get_local_cid = hvs_get_local_cid, @@ -908,12 +878,6 @@ static struct vsock_transport hvs_transport = { .notify_send_pre_enqueue = hvs_notify_send_pre_enqueue, .notify_send_post_enqueue = hvs_notify_send_post_enqueue, - .set_buffer_size = hvs_set_buffer_size, - .set_min_buffer_size = hvs_set_min_buffer_size, - .set_max_buffer_size = hvs_set_max_buffer_size, - .get_buffer_size = hvs_get_buffer_size, - .get_min_buffer_size = hvs_get_min_buffer_size, - .get_max_buffer_size = hvs_get_max_buffer_size, }; static int hvs_probe(struct hv_device *hdev, diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 3756f0857946..fb1fc7760e8c 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -494,13 +494,7 @@ static struct virtio_transport virtio_transport = { .notify_send_pre_block = virtio_transport_notify_send_pre_block, .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue, .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue, - - .set_buffer_size = virtio_transport_set_buffer_size, - .set_min_buffer_size = virtio_transport_set_min_buffer_size, - .set_max_buffer_size = virtio_transport_set_max_buffer_size, - .get_buffer_size = virtio_transport_get_buffer_size, - .get_min_buffer_size = virtio_transport_get_min_buffer_size, - .get_max_buffer_size = virtio_transport_get_max_buffer_size, + .notify_buffer_size = virtio_transport_notify_buffer_size, }, .send_pkt = virtio_transport_send_pkt, diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index b113619d9576..d4a0bf19aa98 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -456,17 +456,13 @@ int virtio_transport_do_socket_init(struct vsock_sock *vsk, if (psk) { struct virtio_vsock_sock *ptrans = psk->trans; - vvs->buf_size = ptrans->buf_size; - vvs->buf_size_min = ptrans->buf_size_min; - vvs->buf_size_max = ptrans->buf_size_max; vvs->peer_buf_alloc = ptrans->peer_buf_alloc; - } else { - vvs->buf_size = VIRTIO_VSOCK_DEFAULT_BUF_SIZE; - vvs->buf_size_min = VIRTIO_VSOCK_DEFAULT_MIN_BUF_SIZE; - vvs->buf_size_max = VIRTIO_VSOCK_DEFAULT_MAX_BUF_SIZE; } - vvs->buf_alloc = vvs->buf_size; + if (vsk->buffer_size > VIRTIO_VSOCK_MAX_BUF_SIZE) + vsk->buffer_size = VIRTIO_VSOCK_MAX_BUF_SIZE; + + vvs->buf_alloc = vsk->buffer_size; spin_lock_init(&vvs->rx_lock); spin_lock_init(&vvs->tx_lock); @@ -476,71 +472,20 @@ int virtio_transport_do_socket_init(struct vsock_sock *vsk, } EXPORT_SYMBOL_GPL(virtio_transport_do_socket_init); -u64 virtio_transport_get_buffer_size(struct vsock_sock *vsk) -{ - struct virtio_vsock_sock *vvs = vsk->trans; - - return vvs->buf_size; -} -EXPORT_SYMBOL_GPL(virtio_transport_get_buffer_size); - -u64 virtio_transport_get_min_buffer_size(struct vsock_sock *vsk) +/* sk_lock held by the caller */ +void virtio_transport_notify_buffer_size(struct vsock_sock *vsk, u64 *val) { struct virtio_vsock_sock *vvs = vsk->trans; - return vvs->buf_size_min; -} -EXPORT_SYMBOL_GPL(virtio_transport_get_min_buffer_size); - -u64 virtio_transport_get_max_buffer_size(struct vsock_sock *vsk) -{ - struct virtio_vsock_sock *vvs = vsk->trans; - - return vvs->buf_size_max; -} -EXPORT_SYMBOL_GPL(virtio_transport_get_max_buffer_size); - -void virtio_transport_set_buffer_size(struct vsock_sock *vsk, u64 val) -{ - struct virtio_vsock_sock *vvs = vsk->trans; + if (*val > VIRTIO_VSOCK_MAX_BUF_SIZE) + *val = VIRTIO_VSOCK_MAX_BUF_SIZE; - if (val > VIRTIO_VSOCK_MAX_BUF_SIZE) - val = VIRTIO_VSOCK_MAX_BUF_SIZE; - if (val < vvs->buf_size_min) - vvs->buf_size_min = val; - if (val > vvs->buf_size_max) - vvs->buf_size_max = val; - vvs->buf_size = val; - vvs->buf_alloc = val; + vvs->buf_alloc = *val; virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_STREAM, NULL); } -EXPORT_SYMBOL_GPL(virtio_transport_set_buffer_size); - -void virtio_transport_set_min_buffer_size(struct vsock_sock *vsk, u64 val) -{ - struct virtio_vsock_sock *vvs = vsk->trans; - - if (val > VIRTIO_VSOCK_MAX_BUF_SIZE) - val = VIRTIO_VSOCK_MAX_BUF_SIZE; - if (val > vvs->buf_size) - vvs->buf_size = val; - vvs->buf_size_min = val; -} -EXPORT_SYMBOL_GPL(virtio_transport_set_min_buffer_size); - -void virtio_transport_set_max_buffer_size(struct vsock_sock *vsk, u64 val) -{ - struct virtio_vsock_sock *vvs = vsk->trans; - - if (val > VIRTIO_VSOCK_MAX_BUF_SIZE) - val = VIRTIO_VSOCK_MAX_BUF_SIZE; - if (val < vvs->buf_size) - vvs->buf_size = val; - vvs->buf_size_max = val; -} -EXPORT_SYMBOL_GPL(virtio_transport_set_max_buffer_size); +EXPORT_SYMBOL_GPL(virtio_transport_notify_buffer_size); int virtio_transport_notify_poll_in(struct vsock_sock *vsk, @@ -632,9 +577,7 @@ EXPORT_SYMBOL_GPL(virtio_transport_notify_send_post_enqueue); u64 virtio_transport_stream_rcvhiwat(struct vsock_sock *vsk) { - struct virtio_vsock_sock *vvs = vsk->trans; - - return vvs->buf_size; + return vsk->buffer_size; } EXPORT_SYMBOL_GPL(virtio_transport_stream_rcvhiwat); diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index cf3b78f0038f..608bb6bd79aa 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -74,10 +74,6 @@ static u32 vmci_transport_qp_resumed_sub_id = VMCI_INVALID_ID; static int PROTOCOL_OVERRIDE = -1; -#define VMCI_TRANSPORT_DEFAULT_QP_SIZE_MIN 128 -#define VMCI_TRANSPORT_DEFAULT_QP_SIZE 262144 -#define VMCI_TRANSPORT_DEFAULT_QP_SIZE_MAX 262144 - /* Helper function to convert from a VMCI error code to a VSock error code. */ static s32 vmci_transport_error_to_vsock_error(s32 vmci_error) @@ -1025,11 +1021,11 @@ static int vmci_transport_recv_listen(struct sock *sk, /* If the proposed size fits within our min/max, accept it. Otherwise * propose our own size. */ - if (pkt->u.size >= vmci_trans(vpending)->queue_pair_min_size && - pkt->u.size <= vmci_trans(vpending)->queue_pair_max_size) { + if (pkt->u.size >= vpending->buffer_min_size && + pkt->u.size <= vpending->buffer_max_size) { qp_size = pkt->u.size; } else { - qp_size = vmci_trans(vpending)->queue_pair_size; + qp_size = vpending->buffer_size; } /* Figure out if we are using old or new requests based on the @@ -1098,7 +1094,7 @@ static int vmci_transport_recv_listen(struct sock *sk, pending->sk_state = TCP_SYN_SENT; vmci_trans(vpending)->produce_size = vmci_trans(vpending)->consume_size = qp_size; - vmci_trans(vpending)->queue_pair_size = qp_size; + vpending->buffer_size = qp_size; vmci_trans(vpending)->notify_ops->process_request(pending); @@ -1392,8 +1388,8 @@ static int vmci_transport_recv_connecting_client_negotiate( vsk->ignore_connecting_rst = false; /* Verify that we're OK with the proposed queue pair size */ - if (pkt->u.size < vmci_trans(vsk)->queue_pair_min_size || - pkt->u.size > vmci_trans(vsk)->queue_pair_max_size) { + if (pkt->u.size < vsk->buffer_min_size || + pkt->u.size > vsk->buffer_max_size) { err = -EINVAL; goto destroy; } @@ -1498,8 +1494,7 @@ vmci_transport_recv_connecting_client_invalid(struct sock *sk, vsk->sent_request = false; vsk->ignore_connecting_rst = true; - err = vmci_transport_send_conn_request( - sk, vmci_trans(vsk)->queue_pair_size); + err = vmci_transport_send_conn_request(sk, vsk->buffer_size); if (err < 0) err = vmci_transport_error_to_vsock_error(err); else @@ -1583,21 +1578,6 @@ static int vmci_transport_socket_init(struct vsock_sock *vsk, INIT_LIST_HEAD(&vmci_trans(vsk)->elem); vmci_trans(vsk)->sk = &vsk->sk; spin_lock_init(&vmci_trans(vsk)->lock); - if (psk) { - vmci_trans(vsk)->queue_pair_size = - vmci_trans(psk)->queue_pair_size; - vmci_trans(vsk)->queue_pair_min_size = - vmci_trans(psk)->queue_pair_min_size; - vmci_trans(vsk)->queue_pair_max_size = - vmci_trans(psk)->queue_pair_max_size; - } else { - vmci_trans(vsk)->queue_pair_size = - VMCI_TRANSPORT_DEFAULT_QP_SIZE; - vmci_trans(vsk)->queue_pair_min_size = - VMCI_TRANSPORT_DEFAULT_QP_SIZE_MIN; - vmci_trans(vsk)->queue_pair_max_size = - VMCI_TRANSPORT_DEFAULT_QP_SIZE_MAX; - } return 0; } @@ -1813,8 +1793,7 @@ static int vmci_transport_connect(struct vsock_sock *vsk) if (vmci_transport_old_proto_override(&old_pkt_proto) && old_pkt_proto) { - err = vmci_transport_send_conn_request( - sk, vmci_trans(vsk)->queue_pair_size); + err = vmci_transport_send_conn_request(sk, vsk->buffer_size); if (err < 0) { sk->sk_state = TCP_CLOSE; return err; @@ -1822,8 +1801,7 @@ static int vmci_transport_connect(struct vsock_sock *vsk) } else { int supported_proto_versions = vmci_transport_new_proto_supported_versions(); - err = vmci_transport_send_conn_request2( - sk, vmci_trans(vsk)->queue_pair_size, + err = vmci_transport_send_conn_request2(sk, vsk->buffer_size, supported_proto_versions); if (err < 0) { sk->sk_state = TCP_CLOSE; @@ -1876,46 +1854,6 @@ static bool vmci_transport_stream_is_active(struct vsock_sock *vsk) return !vmci_handle_is_invalid(vmci_trans(vsk)->qp_handle); } -static u64 vmci_transport_get_buffer_size(struct vsock_sock *vsk) -{ - return vmci_trans(vsk)->queue_pair_size; -} - -static u64 vmci_transport_get_min_buffer_size(struct vsock_sock *vsk) -{ - return vmci_trans(vsk)->queue_pair_min_size; -} - -static u64 vmci_transport_get_max_buffer_size(struct vsock_sock *vsk) -{ - return vmci_trans(vsk)->queue_pair_max_size; -} - -static void vmci_transport_set_buffer_size(struct vsock_sock *vsk, u64 val) -{ - if (val < vmci_trans(vsk)->queue_pair_min_size) - vmci_trans(vsk)->queue_pair_min_size = val; - if (val > vmci_trans(vsk)->queue_pair_max_size) - vmci_trans(vsk)->queue_pair_max_size = val; - vmci_trans(vsk)->queue_pair_size = val; -} - -static void vmci_transport_set_min_buffer_size(struct vsock_sock *vsk, - u64 val) -{ - if (val > vmci_trans(vsk)->queue_pair_size) - vmci_trans(vsk)->queue_pair_size = val; - vmci_trans(vsk)->queue_pair_min_size = val; -} - -static void vmci_transport_set_max_buffer_size(struct vsock_sock *vsk, - u64 val) -{ - if (val < vmci_trans(vsk)->queue_pair_size) - vmci_trans(vsk)->queue_pair_size = val; - vmci_trans(vsk)->queue_pair_max_size = val; -} - static int vmci_transport_notify_poll_in( struct vsock_sock *vsk, size_t target, @@ -2098,12 +2036,6 @@ static const struct vsock_transport vmci_transport = { .notify_send_pre_enqueue = vmci_transport_notify_send_pre_enqueue, .notify_send_post_enqueue = vmci_transport_notify_send_post_enqueue, .shutdown = vmci_transport_shutdown, - .set_buffer_size = vmci_transport_set_buffer_size, - .set_min_buffer_size = vmci_transport_set_min_buffer_size, - .set_max_buffer_size = vmci_transport_set_max_buffer_size, - .get_buffer_size = vmci_transport_get_buffer_size, - .get_min_buffer_size = vmci_transport_get_min_buffer_size, - .get_max_buffer_size = vmci_transport_get_max_buffer_size, .get_local_cid = vmci_transport_get_local_cid, }; diff --git a/net/vmw_vsock/vmci_transport.h b/net/vmw_vsock/vmci_transport.h index 1ca1e8640b31..b7b072194282 100644 --- a/net/vmw_vsock/vmci_transport.h +++ b/net/vmw_vsock/vmci_transport.h @@ -108,9 +108,6 @@ struct vmci_transport { struct vmci_qp *qpair; u64 produce_size; u64 consume_size; - u64 queue_pair_size; - u64 queue_pair_min_size; - u64 queue_pair_max_size; u32 detach_sub_id; union vmci_transport_notify notify; const struct vmci_transport_notify_ops *notify_ops; -- cgit v1.2.3-71-gd317 From b1bba80a4376aef34de2b57bfb8834bd095703ed Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Thu, 14 Nov 2019 10:57:47 +0100 Subject: vsock/vmci: register vmci_transport only when VMCI guest/host are active To allow other transports to be loaded with vmci_transport, we register the vmci_transport as G2H or H2G only when a VMCI guest or host is active. To do that, this patch adds a callback registered in the vmci driver that will be called when the host or guest becomes active. This callback will register the vmci_transport in the VSOCK core. Cc: Jorgen Hansen Signed-off-by: Stefano Garzarella Signed-off-by: David S. Miller --- drivers/misc/vmw_vmci/vmci_driver.c | 67 +++++++++++++++++++++++++++++++++++++ drivers/misc/vmw_vmci/vmci_driver.h | 2 ++ drivers/misc/vmw_vmci/vmci_guest.c | 2 ++ drivers/misc/vmw_vmci/vmci_host.c | 7 ++++ include/linux/vmw_vmci_api.h | 2 ++ net/vmw_vsock/vmci_transport.c | 33 ++++++++++++------ 6 files changed, 102 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/misc/vmw_vmci/vmci_driver.c b/drivers/misc/vmw_vmci/vmci_driver.c index 819e35995d32..95fed4664a2d 100644 --- a/drivers/misc/vmw_vmci/vmci_driver.c +++ b/drivers/misc/vmw_vmci/vmci_driver.c @@ -28,6 +28,10 @@ MODULE_PARM_DESC(disable_guest, static bool vmci_guest_personality_initialized; static bool vmci_host_personality_initialized; +static DEFINE_MUTEX(vmci_vsock_mutex); /* protects vmci_vsock_transport_cb */ +static vmci_vsock_cb vmci_vsock_transport_cb; +bool vmci_vsock_cb_host_called; + /* * vmci_get_context_id() - Gets the current context ID. * @@ -45,6 +49,69 @@ u32 vmci_get_context_id(void) } EXPORT_SYMBOL_GPL(vmci_get_context_id); +/* + * vmci_register_vsock_callback() - Register the VSOCK vmci_transport callback. + * + * The callback will be called when the first host or guest becomes active, + * or if they are already active when this function is called. + * To unregister the callback, call this function with NULL parameter. + * + * Returns 0 on success. -EBUSY if a callback is already registered. + */ +int vmci_register_vsock_callback(vmci_vsock_cb callback) +{ + int err = 0; + + mutex_lock(&vmci_vsock_mutex); + + if (vmci_vsock_transport_cb && callback) { + err = -EBUSY; + goto out; + } + + vmci_vsock_transport_cb = callback; + + if (!vmci_vsock_transport_cb) { + vmci_vsock_cb_host_called = false; + goto out; + } + + if (vmci_guest_code_active()) + vmci_vsock_transport_cb(false); + + if (vmci_host_users() > 0) { + vmci_vsock_cb_host_called = true; + vmci_vsock_transport_cb(true); + } + +out: + mutex_unlock(&vmci_vsock_mutex); + return err; +} +EXPORT_SYMBOL_GPL(vmci_register_vsock_callback); + +void vmci_call_vsock_callback(bool is_host) +{ + mutex_lock(&vmci_vsock_mutex); + + if (!vmci_vsock_transport_cb) + goto out; + + /* In the host, this function could be called multiple times, + * but we want to register it only once. + */ + if (is_host) { + if (vmci_vsock_cb_host_called) + goto out; + + vmci_vsock_cb_host_called = true; + } + + vmci_vsock_transport_cb(is_host); +out: + mutex_unlock(&vmci_vsock_mutex); +} + static int __init vmci_drv_init(void) { int vmci_err; diff --git a/drivers/misc/vmw_vmci/vmci_driver.h b/drivers/misc/vmw_vmci/vmci_driver.h index aab81b67670c..990682480bf6 100644 --- a/drivers/misc/vmw_vmci/vmci_driver.h +++ b/drivers/misc/vmw_vmci/vmci_driver.h @@ -36,10 +36,12 @@ extern struct pci_dev *vmci_pdev; u32 vmci_get_context_id(void); int vmci_send_datagram(struct vmci_datagram *dg); +void vmci_call_vsock_callback(bool is_host); int vmci_host_init(void); void vmci_host_exit(void); bool vmci_host_code_active(void); +int vmci_host_users(void); int vmci_guest_init(void); void vmci_guest_exit(void); diff --git a/drivers/misc/vmw_vmci/vmci_guest.c b/drivers/misc/vmw_vmci/vmci_guest.c index 7a84a48c75da..cc8eeb361fcd 100644 --- a/drivers/misc/vmw_vmci/vmci_guest.c +++ b/drivers/misc/vmw_vmci/vmci_guest.c @@ -637,6 +637,8 @@ static int vmci_guest_probe_device(struct pci_dev *pdev, vmci_dev->iobase + VMCI_CONTROL_ADDR); pci_set_drvdata(pdev, vmci_dev); + + vmci_call_vsock_callback(false); return 0; err_free_irq: diff --git a/drivers/misc/vmw_vmci/vmci_host.c b/drivers/misc/vmw_vmci/vmci_host.c index 833e2bd248a5..ff3c396146ff 100644 --- a/drivers/misc/vmw_vmci/vmci_host.c +++ b/drivers/misc/vmw_vmci/vmci_host.c @@ -108,6 +108,11 @@ bool vmci_host_code_active(void) atomic_read(&vmci_host_active_users) > 0); } +int vmci_host_users(void) +{ + return atomic_read(&vmci_host_active_users); +} + /* * Called on open of /dev/vmci. */ @@ -338,6 +343,8 @@ static int vmci_host_do_init_context(struct vmci_host_dev *vmci_host_dev, vmci_host_dev->ct_type = VMCIOBJ_CONTEXT; atomic_inc(&vmci_host_active_users); + vmci_call_vsock_callback(true); + retval = 0; out: diff --git a/include/linux/vmw_vmci_api.h b/include/linux/vmw_vmci_api.h index acd9fafe4fc6..f28907345c80 100644 --- a/include/linux/vmw_vmci_api.h +++ b/include/linux/vmw_vmci_api.h @@ -19,6 +19,7 @@ struct msghdr; typedef void (vmci_device_shutdown_fn) (void *device_registration, void *user_data); +typedef void (*vmci_vsock_cb) (bool is_host); int vmci_datagram_create_handle(u32 resource_id, u32 flags, vmci_datagram_recv_cb recv_cb, @@ -37,6 +38,7 @@ int vmci_doorbell_destroy(struct vmci_handle handle); int vmci_doorbell_notify(struct vmci_handle handle, u32 priv_flags); u32 vmci_get_context_id(void); bool vmci_is_context_owner(u32 context_id, kuid_t uid); +int vmci_register_vsock_callback(vmci_vsock_cb callback); int vmci_event_subscribe(u32 event, vmci_event_cb callback, void *callback_data, diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 86030ecb53dd..d9c9c834ad6f 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -2054,19 +2054,21 @@ static bool vmci_check_transport(struct vsock_sock *vsk) return vsk->transport == &vmci_transport; } -static int __init vmci_transport_init(void) +void vmci_vsock_transport_cb(bool is_host) { - int features = VSOCK_TRANSPORT_F_DGRAM | VSOCK_TRANSPORT_F_H2G; - int cid; - int err; + int features; - cid = vmci_get_context_id(); + if (is_host) + features = VSOCK_TRANSPORT_F_H2G; + else + features = VSOCK_TRANSPORT_F_G2H; - if (cid == VMCI_INVALID_ID) - return -EINVAL; + vsock_core_register(&vmci_transport, features); +} - if (cid != VMCI_HOST_CONTEXT_ID) - features |= VSOCK_TRANSPORT_F_G2H; +static int __init vmci_transport_init(void) +{ + int err; /* Create the datagram handle that we will use to send and receive all * VSocket control messages for this context. @@ -2080,7 +2082,6 @@ static int __init vmci_transport_init(void) pr_err("Unable to create datagram handle. (%d)\n", err); return vmci_transport_error_to_vsock_error(err); } - err = vmci_event_subscribe(VMCI_EVENT_QP_RESUMED, vmci_transport_qp_resumed_cb, NULL, &vmci_transport_qp_resumed_sub_id); @@ -2091,12 +2092,21 @@ static int __init vmci_transport_init(void) goto err_destroy_stream_handle; } - err = vsock_core_register(&vmci_transport, features); + /* Register only with dgram feature, other features (H2G, G2H) will be + * registered when the first host or guest becomes active. + */ + err = vsock_core_register(&vmci_transport, VSOCK_TRANSPORT_F_DGRAM); if (err < 0) goto err_unsubscribe; + err = vmci_register_vsock_callback(vmci_vsock_transport_cb); + if (err < 0) + goto err_unregister; + return 0; +err_unregister: + vsock_core_unregister(&vmci_transport); err_unsubscribe: vmci_event_unsubscribe(vmci_transport_qp_resumed_sub_id); err_destroy_stream_handle: @@ -2122,6 +2132,7 @@ static void __exit vmci_transport_exit(void) vmci_transport_qp_resumed_sub_id = VMCI_INVALID_ID; } + vmci_register_vsock_callback(NULL); vsock_core_unregister(&vmci_transport); } module_exit(vmci_transport_exit); -- cgit v1.2.3-71-gd317 From 2f4741497c9d5151c6bde0edb6faf34fc3859b80 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 14 Nov 2019 19:06:47 -0800 Subject: libnvdimm: Trivial comment fix Signed-off-by: Ira Weiny Link: https://lore.kernel.org/r/20190918211933.13213-1-ira.weiny@intel.com Signed-off-by: Dan Williams --- include/linux/nd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nd.h b/include/linux/nd.h index f778f962d1b6..55c735997805 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -147,7 +147,7 @@ static inline int nvdimm_read_bytes(struct nd_namespace_common *ndns, /** * nvdimm_write_bytes() - synchronously write bytes to an nvdimm namespace - * @ndns: device to read + * @ndns: device to write * @offset: namespace-relative starting offset * @buf: buffer to drain * @size: transfer length -- cgit v1.2.3-71-gd317 From 0567d6809182df53da03636fad36c507c5cf07a5 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 14 Nov 2019 14:39:35 -0500 Subject: ftrace: Add modify_ftrace_direct() Add a new function modify_ftrace_direct() that will allow a user to update an existing direct caller to a new trampoline, without missing hits due to unregistering one and then adding another. Link: https://lore.kernel.org/r/20191109022907.6zzo6orhxpt5n2sv@ast-mbp.dhcp.thefacebook.com Suggested-by: Alexei Starovoitov Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 6 ++++ kernel/trace/ftrace.c | 78 ++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 84 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 55647e185141..73eb2e93593f 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -250,6 +250,7 @@ static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { extern int ftrace_direct_func_count; int register_ftrace_direct(unsigned long ip, unsigned long addr); int unregister_ftrace_direct(unsigned long ip, unsigned long addr); +int modify_ftrace_direct(unsigned long ip, unsigned long old_addr, unsigned long new_addr); struct ftrace_direct_func *ftrace_find_direct_func(unsigned long addr); #else # define ftrace_direct_func_count 0 @@ -261,6 +262,11 @@ static inline int unregister_ftrace_direct(unsigned long ip, unsigned long addr) { return -ENODEV; } +static inline int modify_ftrace_direct(unsigned long ip, + unsigned long old_addr, unsigned long new_addr) +{ + return -ENODEV; +} static inline struct ftrace_direct_func *ftrace_find_direct_func(unsigned long addr) { return NULL; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 82ef8d60a42b..834f3556ea1e 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5160,6 +5160,84 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr) return ret; } EXPORT_SYMBOL_GPL(unregister_ftrace_direct); + +static struct ftrace_ops stub_ops = { + .func = ftrace_stub, +}; + +/** + * modify_ftrace_direct - Modify an existing direct call to call something else + * @ip: The instruction pointer to modify + * @old_addr: The address that the current @ip calls directly + * @new_addr: The address that the @ip should call + * + * This modifies a ftrace direct caller at an instruction pointer without + * having to disable it first. The direct call will switch over to the + * @new_addr without missing anything. + * + * Returns: zero on success. Non zero on error, which includes: + * -ENODEV : the @ip given has no direct caller attached + * -EINVAL : the @old_addr does not match the current direct caller + */ +int modify_ftrace_direct(unsigned long ip, + unsigned long old_addr, unsigned long new_addr) +{ + struct ftrace_func_entry *entry; + struct dyn_ftrace *rec; + int ret = -ENODEV; + + mutex_lock(&direct_mutex); + entry = __ftrace_lookup_ip(direct_functions, ip); + if (!entry) { + /* OK if it is off by a little */ + rec = lookup_rec(ip, ip); + if (!rec || rec->ip == ip) + goto out_unlock; + + entry = __ftrace_lookup_ip(direct_functions, rec->ip); + if (!entry) + goto out_unlock; + + ip = rec->ip; + WARN_ON(!(rec->flags & FTRACE_FL_DIRECT)); + } + + ret = -EINVAL; + if (entry->direct != old_addr) + goto out_unlock; + + /* + * By setting a stub function at the same address, we force + * the code to call the iterator and the direct_ops helper. + * This means that @ip does not call the direct call, and + * we can simply modify it. + */ + ret = ftrace_set_filter_ip(&stub_ops, ip, 0, 0); + if (ret) + goto out_unlock; + + ret = register_ftrace_function(&stub_ops); + if (ret) { + ftrace_set_filter_ip(&stub_ops, ip, 1, 0); + goto out_unlock; + } + + entry->direct = new_addr; + + /* + * By removing the stub, we put back the direct call, calling + * the @new_addr. + */ + unregister_ftrace_function(&stub_ops); + ftrace_set_filter_ip(&stub_ops, ip, 1, 0); + + ret = 0; + + out_unlock: + mutex_unlock(&direct_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(modify_ftrace_direct); #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ /** -- cgit v1.2.3-71-gd317 From 4d219f4cf0322ab40c1b21a836a6d4b61e01216f Mon Sep 17 00:00:00 2001 From: "H. Nikolaus Schaller" Date: Thu, 7 Nov 2019 11:30:41 +0100 Subject: mmc: host: omap-hsmmc: remove init_card pdata callback from pdata Now as we have removed the last user (pandora_wl1251_init_card) of this callback, we can remove it from the hsmmc code. Suggested-by: Ulf Hansson Signed-off-by: H. Nikolaus Schaller Signed-off-by: Ulf Hansson --- drivers/mmc/host/omap_hsmmc.c | 5 +---- include/linux/platform_data/hsmmc-omap.h | 3 --- 2 files changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index d0df054b0b47..767e964ca5a2 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -1510,10 +1510,7 @@ static void omap_hsmmc_init_card(struct mmc_host *mmc, struct mmc_card *card) { struct omap_hsmmc_host *host = mmc_priv(mmc); - if (mmc_pdata(host)->init_card) - mmc_pdata(host)->init_card(card); - else if (card->type == MMC_TYPE_SDIO || - card->type == MMC_TYPE_SD_COMBO) { + if (card->type == MMC_TYPE_SDIO || card->type == MMC_TYPE_SD_COMBO) { struct device_node *np = mmc_dev(mmc)->of_node; /* diff --git a/include/linux/platform_data/hsmmc-omap.h b/include/linux/platform_data/hsmmc-omap.h index e79d238ff18f..7124a5f4bf06 100644 --- a/include/linux/platform_data/hsmmc-omap.h +++ b/include/linux/platform_data/hsmmc-omap.h @@ -67,9 +67,6 @@ struct omap_hsmmc_platform_data { /* string specifying a particular variant of hardware */ char *version; - /* if we have special card, init it using this callback */ - void (*init_card)(struct mmc_card *card); - const char *name; u32 ocr_mask; }; -- cgit v1.2.3-71-gd317 From e5db673e7fe2f971ec82039a28dc0811c2100e87 Mon Sep 17 00:00:00 2001 From: "H. Nikolaus Schaller" Date: Thu, 7 Nov 2019 11:30:42 +0100 Subject: mmc: sdio: fix wl1251 vendor id v4.11-rc1 did introduce a patch series that rearranged the sdio quirks into a header file. Unfortunately this did forget to handle SDIO_VENDOR_ID_TI differently between wl1251 and wl1271 with the result that although the wl1251 was found on the sdio bus, the firmware did not load any more and there was no interface registration. This patch defines separate constants to be used by sdio quirks and drivers. Fixes: 884f38607897 ("mmc: core: move some sdio IDs out of quirks file") Signed-off-by: H. Nikolaus Schaller Cc: # v4.11+ Signed-off-by: Ulf Hansson --- include/linux/mmc/sdio_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index d1a5d5df02f5..08b25c02b5a1 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -71,6 +71,8 @@ #define SDIO_VENDOR_ID_TI 0x0097 #define SDIO_DEVICE_ID_TI_WL1271 0x4076 +#define SDIO_VENDOR_ID_TI_WL1251 0x104c +#define SDIO_DEVICE_ID_TI_WL1251 0x9066 #define SDIO_VENDOR_ID_STE 0x0020 #define SDIO_DEVICE_ID_STE_CW1200 0x2280 -- cgit v1.2.3-71-gd317 From 4df4cb9e99f83b70d54bc0e25081ac23cceafcbc Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Wed, 13 Nov 2019 01:11:49 +0000 Subject: x86/hyperv: Initialize clockevents earlier in CPU onlining Hyper-V has historically initialized stimer-based clockevents late in the process of onlining a CPU because clockevents depend on stimer interrupts. In the original Hyper-V design, stimer interrupts generate a VMbus message, so the VMbus machinery must be running first, and VMbus can't be initialized until relatively late. On x86/64, LAPIC timer based clockevents are used during early initialization before VMbus and stimer-based clockevents are ready, and again during CPU offlining after the stimer clockevents have been shut down. Unfortunately, this design creates problems when offlining CPUs for hibernation or other purposes. stimer-based clockevents are shut down relatively early in the offlining process, so clockevents_unbind_device() must be used to fallback to the LAPIC-based clockevents for the remainder of the offlining process. Furthermore, the late initialization and early shutdown of stimer-based clockevents doesn't work well on ARM64 since there is no other timer like the LAPIC to fallback to. So CPU onlining and offlining doesn't work properly. Fix this by recognizing that stimer Direct Mode is the normal path for newer versions of Hyper-V on x86/64, and the only path on other architectures. With stimer Direct Mode, stimer interrupts don't require any VMbus machinery. stimer clockevents can be initialized and shut down consistent with how it is done for other clockevent devices. While the old VMbus-based stimer interrupts must still be supported for backward compatibility on x86, that mode of operation can be treated as legacy. So add a new Hyper-V stimer entry in the CPU hotplug state list, and use that new state when in Direct Mode. Update the Hyper-V clocksource driver to allocate and initialize stimer clockevents earlier during boot. Update Hyper-V initialization and the VMbus driver to use this new design. As a result, the LAPIC timer is no longer used during boot or CPU onlining/offlining and clockevents_unbind_device() is not called. But retain the old design as a legacy implementation for older versions of Hyper-V that don't support Direct Mode. Signed-off-by: Michael Kelley Signed-off-by: Thomas Gleixner Tested-by: Dexuan Cui Reviewed-by: Dexuan Cui Link: https://lkml.kernel.org/r/1573607467-9456-1-git-send-email-mikelley@microsoft.com --- arch/x86/hyperv/hv_init.c | 6 ++ drivers/clocksource/hyperv_timer.c | 154 +++++++++++++++++++++++++++++-------- drivers/hv/hv.c | 4 +- drivers/hv/vmbus_drv.c | 30 ++++---- include/clocksource/hyperv_timer.h | 7 +- include/linux/cpuhotplug.h | 1 + 6 files changed, 151 insertions(+), 51 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 2db3972c0e0f..50ff030d9224 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -311,6 +311,12 @@ void __init hyperv_init(void) hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg); wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + /* + * Ignore any errors in setting up stimer clockevents + * as we can run with the LAPIC timer as a fallback. + */ + (void)hv_stimer_alloc(); + hv_apic_init(); x86_init.pci.arch_init = hv_pci_init; diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c index 2317d4e3daaf..287d8d58c21a 100644 --- a/drivers/clocksource/hyperv_timer.c +++ b/drivers/clocksource/hyperv_timer.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -30,6 +31,15 @@ static u64 hv_sched_clock_offset __ro_after_init; * mechanism is used when running on older versions of Hyper-V * that don't support Direct Mode. While Hyper-V provides * four stimer's per CPU, Linux uses only stimer0. + * + * Because Direct Mode does not require processing a VMbus + * message, stimer interrupts can be enabled earlier in the + * process of booting a CPU, and consistent with when timer + * interrupts are enabled for other clocksource drivers. + * However, for legacy versions of Hyper-V when Direct Mode + * is not enabled, setting up stimer interrupts must be + * delayed until VMbus is initialized and can process the + * interrupt message. */ static bool direct_mode_enabled; @@ -102,17 +112,12 @@ static int hv_ce_set_oneshot(struct clock_event_device *evt) /* * hv_stimer_init - Per-cpu initialization of the clockevent */ -void hv_stimer_init(unsigned int cpu) +static int hv_stimer_init(unsigned int cpu) { struct clock_event_device *ce; - /* - * Synthetic timers are always available except on old versions of - * Hyper-V on x86. In that case, just return as Linux will use a - * clocksource based on emulated PIT or LAPIC timer hardware. - */ - if (!(ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE)) - return; + if (!hv_clock_event) + return 0; ce = per_cpu_ptr(hv_clock_event, cpu); ce->name = "Hyper-V clockevent"; @@ -127,28 +132,55 @@ void hv_stimer_init(unsigned int cpu) HV_CLOCK_HZ, HV_MIN_DELTA_TICKS, HV_MAX_MAX_DELTA_TICKS); + return 0; } -EXPORT_SYMBOL_GPL(hv_stimer_init); /* * hv_stimer_cleanup - Per-cpu cleanup of the clockevent */ -void hv_stimer_cleanup(unsigned int cpu) +int hv_stimer_cleanup(unsigned int cpu) { struct clock_event_device *ce; - /* Turn off clockevent device */ - if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE) { - ce = per_cpu_ptr(hv_clock_event, cpu); + if (!hv_clock_event) + return 0; + + /* + * In the legacy case where Direct Mode is not enabled + * (which can only be on x86/64), stimer cleanup happens + * relatively early in the CPU offlining process. We + * must unbind the stimer-based clockevent device so + * that the LAPIC timer can take over until clockevents + * are no longer needed in the offlining process. Note + * that clockevents_unbind_device() eventually calls + * hv_ce_shutdown(). + * + * The unbind should not be done when Direct Mode is + * enabled because we may be on an architecture where + * there are no other clockevent devices to fallback to. + */ + ce = per_cpu_ptr(hv_clock_event, cpu); + if (direct_mode_enabled) hv_ce_shutdown(ce); - } + else + clockevents_unbind_device(ce, cpu); + + return 0; } EXPORT_SYMBOL_GPL(hv_stimer_cleanup); /* hv_stimer_alloc - Global initialization of the clockevent and stimer0 */ -int hv_stimer_alloc(int sint) +int hv_stimer_alloc(void) { - int ret; + int ret = 0; + + /* + * Synthetic timers are always available except on old versions of + * Hyper-V on x86. In that case, return as error as Linux will use a + * clockevent based on emulated LAPIC timer hardware. + */ + if (!(ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE)) + return -EINVAL; hv_clock_event = alloc_percpu(struct clock_event_device); if (!hv_clock_event) @@ -159,22 +191,78 @@ int hv_stimer_alloc(int sint) if (direct_mode_enabled) { ret = hv_setup_stimer0_irq(&stimer0_irq, &stimer0_vector, hv_stimer0_isr); - if (ret) { - free_percpu(hv_clock_event); - hv_clock_event = NULL; - return ret; - } + if (ret) + goto free_percpu; + + /* + * Since we are in Direct Mode, stimer initialization + * can be done now with a CPUHP value in the same range + * as other clockevent devices. + */ + ret = cpuhp_setup_state(CPUHP_AP_HYPERV_TIMER_STARTING, + "clockevents/hyperv/stimer:starting", + hv_stimer_init, hv_stimer_cleanup); + if (ret < 0) + goto free_stimer0_irq; } + return ret; - stimer0_message_sint = sint; - return 0; +free_stimer0_irq: + hv_remove_stimer0_irq(stimer0_irq); + stimer0_irq = 0; +free_percpu: + free_percpu(hv_clock_event); + hv_clock_event = NULL; + return ret; } EXPORT_SYMBOL_GPL(hv_stimer_alloc); +/* + * hv_stimer_legacy_init -- Called from the VMbus driver to handle + * the case when Direct Mode is not enabled, and the stimer + * must be initialized late in the CPU onlining process. + * + */ +void hv_stimer_legacy_init(unsigned int cpu, int sint) +{ + if (direct_mode_enabled) + return; + + /* + * This function gets called by each vCPU, so setting the + * global stimer_message_sint value each time is conceptually + * not ideal, but the value passed in is always the same and + * it avoids introducing yet another interface into this + * clocksource driver just to set the sint in the legacy case. + */ + stimer0_message_sint = sint; + (void)hv_stimer_init(cpu); +} +EXPORT_SYMBOL_GPL(hv_stimer_legacy_init); + +/* + * hv_stimer_legacy_cleanup -- Called from the VMbus driver to + * handle the case when Direct Mode is not enabled, and the + * stimer must be cleaned up early in the CPU offlining + * process. + */ +void hv_stimer_legacy_cleanup(unsigned int cpu) +{ + if (direct_mode_enabled) + return; + (void)hv_stimer_cleanup(cpu); +} +EXPORT_SYMBOL_GPL(hv_stimer_legacy_cleanup); + + /* hv_stimer_free - Free global resources allocated by hv_stimer_alloc() */ void hv_stimer_free(void) { - if (direct_mode_enabled && (stimer0_irq != 0)) { + if (!hv_clock_event) + return; + + if (direct_mode_enabled) { + cpuhp_remove_state(CPUHP_AP_HYPERV_TIMER_STARTING); hv_remove_stimer0_irq(stimer0_irq); stimer0_irq = 0; } @@ -190,14 +278,20 @@ EXPORT_SYMBOL_GPL(hv_stimer_free); void hv_stimer_global_cleanup(void) { int cpu; - struct clock_event_device *ce; - if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE) { - for_each_present_cpu(cpu) { - ce = per_cpu_ptr(hv_clock_event, cpu); - clockevents_unbind_device(ce, cpu); - } + /* + * hv_stime_legacy_cleanup() will stop the stimer if Direct + * Mode is not enabled, and fallback to the LAPIC timer. + */ + for_each_present_cpu(cpu) { + hv_stimer_legacy_cleanup(cpu); } + + /* + * If Direct Mode is enabled, the cpuhp teardown callback + * (hv_stimer_cleanup) will be run on all CPUs to stop the + * stimers. + */ hv_stimer_free(); } EXPORT_SYMBOL_GPL(hv_stimer_global_cleanup); diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index fcc52797c169..6098e0cbdb4b 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -202,7 +202,7 @@ int hv_synic_init(unsigned int cpu) { hv_synic_enable_regs(cpu); - hv_stimer_init(cpu); + hv_stimer_legacy_init(cpu, VMBUS_MESSAGE_SINT); return 0; } @@ -277,7 +277,7 @@ int hv_synic_cleanup(unsigned int cpu) if (channel_found && vmbus_connection.conn_state == CONNECTED) return -EBUSY; - hv_stimer_cleanup(cpu); + hv_stimer_legacy_cleanup(cpu); hv_synic_disable_regs(cpu); diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 53a60c81e220..8c06b3361c27 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -1340,10 +1340,6 @@ static int vmbus_bus_init(void) if (ret) goto err_alloc; - ret = hv_stimer_alloc(VMBUS_MESSAGE_SINT); - if (ret < 0) - goto err_alloc; - /* * Initialize the per-cpu interrupt state and stimer state. * Then connect to the host. @@ -1400,9 +1396,8 @@ static int vmbus_bus_init(void) err_connect: cpuhp_remove_state(hyperv_cpuhp_online); err_cpuhp: - hv_stimer_free(); -err_alloc: hv_synic_free(); +err_alloc: hv_remove_vmbus_irq(); bus_unregister(&hv_bus); @@ -2315,20 +2310,23 @@ static void hv_crash_handler(struct pt_regs *regs) static int hv_synic_suspend(void) { /* - * When we reach here, all the non-boot CPUs have been offlined, and - * the stimers on them have been unbound in hv_synic_cleanup() -> + * When we reach here, all the non-boot CPUs have been offlined. + * If we're in a legacy configuration where stimer Direct Mode is + * not enabled, the stimers on the non-boot CPUs have been unbound + * in hv_synic_cleanup() -> hv_stimer_legacy_cleanup() -> * hv_stimer_cleanup() -> clockevents_unbind_device(). * - * hv_synic_suspend() only runs on CPU0 with interrupts disabled. Here - * we do not unbind the stimer on CPU0 because: 1) it's unnecessary - * because the interrupts remain disabled between syscore_suspend() - * and syscore_resume(): see create_image() and resume_target_kernel(); + * hv_synic_suspend() only runs on CPU0 with interrupts disabled. + * Here we do not call hv_stimer_legacy_cleanup() on CPU0 because: + * 1) it's unnecessary as interrupts remain disabled between + * syscore_suspend() and syscore_resume(): see create_image() and + * resume_target_kernel() * 2) the stimer on CPU0 is automatically disabled later by * syscore_suspend() -> timekeeping_suspend() -> tick_suspend() -> ... - * -> clockevents_shutdown() -> ... -> hv_ce_shutdown(); 3) a warning - * would be triggered if we call clockevents_unbind_device(), which - * may sleep, in an interrupts-disabled context. So, we intentionally - * don't call hv_stimer_cleanup(0) here. + * -> clockevents_shutdown() -> ... -> hv_ce_shutdown() + * 3) a warning would be triggered if we call + * clockevents_unbind_device(), which may sleep, in an + * interrupts-disabled context. */ hv_synic_disable_regs(0); diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h index 422f5e5237be..553e539469f0 100644 --- a/include/clocksource/hyperv_timer.h +++ b/include/clocksource/hyperv_timer.h @@ -21,10 +21,11 @@ #define HV_MIN_DELTA_TICKS 1 /* Routines called by the VMbus driver */ -extern int hv_stimer_alloc(int sint); +extern int hv_stimer_alloc(void); extern void hv_stimer_free(void); -extern void hv_stimer_init(unsigned int cpu); -extern void hv_stimer_cleanup(unsigned int cpu); +extern int hv_stimer_cleanup(unsigned int cpu); +extern void hv_stimer_legacy_init(unsigned int cpu, int sint); +extern void hv_stimer_legacy_cleanup(unsigned int cpu); extern void hv_stimer_global_cleanup(void); extern void hv_stimer0_isr(void); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 068793a619ca..4dcaea13b1f0 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -129,6 +129,7 @@ enum cpuhp_state { CPUHP_AP_ARC_TIMER_STARTING, CPUHP_AP_RISCV_TIMER_STARTING, CPUHP_AP_CSKY_TIMER_STARTING, + CPUHP_AP_HYPERV_TIMER_STARTING, CPUHP_AP_KVM_STARTING, CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING, CPUHP_AP_KVM_ARM_VGIC_STARTING, -- cgit v1.2.3-71-gd317 From 3ca270fc9edb258d5bfa271bcf851614e9e6e7d4 Mon Sep 17 00:00:00 2001 From: Like Xu Date: Sun, 27 Oct 2019 18:52:38 +0800 Subject: perf/core: Provide a kernel-internal interface to recalibrate event period Currently, perf_event_period() is used by user tools via ioctl. Based on naming convention, exporting perf_event_period() for kernel users (such as KVM) who may recalibrate the event period for their assigned counter according to their requirements. The perf_event_period() is an external accessor, just like the perf_event_{en,dis}able() and should thus use perf_event_ctx_lock(). Suggested-by: Kan Liang Signed-off-by: Like Xu Acked-by: Peter Zijlstra Signed-off-by: Paolo Bonzini --- include/linux/perf_event.h | 5 +++++ kernel/events/core.c | 28 +++++++++++++++++++++------- 2 files changed, 26 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 61448c19a132..d601df36e671 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1336,6 +1336,7 @@ extern void perf_event_disable_local(struct perf_event *event); extern void perf_event_disable_inatomic(struct perf_event *event); extern void perf_event_task_tick(void); extern int perf_event_account_interrupt(struct perf_event *event); +extern int perf_event_period(struct perf_event *event, u64 value); #else /* !CONFIG_PERF_EVENTS: */ static inline void * perf_aux_output_begin(struct perf_output_handle *handle, @@ -1415,6 +1416,10 @@ static inline void perf_event_disable(struct perf_event *event) { } static inline int __perf_event_disable(void *info) { return -1; } static inline void perf_event_task_tick(void) { } static inline int perf_event_release_kernel(struct perf_event *event) { return 0; } +static inline int perf_event_period(struct perf_event *event, u64 value) +{ + return -EINVAL; +} #endif #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) diff --git a/kernel/events/core.c b/kernel/events/core.c index 9ec0b0bfddbd..e1b83d2731da 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5106,16 +5106,11 @@ static int perf_event_check_period(struct perf_event *event, u64 value) return event->pmu->check_period(event, value); } -static int perf_event_period(struct perf_event *event, u64 __user *arg) +static int _perf_event_period(struct perf_event *event, u64 value) { - u64 value; - if (!is_sampling_event(event)) return -EINVAL; - if (copy_from_user(&value, arg, sizeof(value))) - return -EFAULT; - if (!value) return -EINVAL; @@ -5133,6 +5128,19 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg) return 0; } +int perf_event_period(struct perf_event *event, u64 value) +{ + struct perf_event_context *ctx; + int ret; + + ctx = perf_event_ctx_lock(event); + ret = _perf_event_period(event, value); + perf_event_ctx_unlock(event, ctx); + + return ret; +} +EXPORT_SYMBOL_GPL(perf_event_period); + static const struct file_operations perf_fops; static inline int perf_fget_light(int fd, struct fd *p) @@ -5176,8 +5184,14 @@ static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned lon return _perf_event_refresh(event, arg); case PERF_EVENT_IOC_PERIOD: - return perf_event_period(event, (u64 __user *)arg); + { + u64 value; + + if (copy_from_user(&value, (u64 __user *)arg, sizeof(value))) + return -EFAULT; + return _perf_event_period(event, value); + } case PERF_EVENT_IOC_ID: { u64 id = primary_event_id(event); -- cgit v1.2.3-71-gd317 From 52ba4b0b99770e892f43da1238f437155acb8b58 Mon Sep 17 00:00:00 2001 From: Like Xu Date: Sun, 27 Oct 2019 18:52:39 +0800 Subject: perf/core: Provide a kernel-internal interface to pause perf_event Exporting perf_event_pause() as an external accessor for kernel users (such as KVM) who may do both disable perf_event and read count with just one time to hold perf_event_ctx_lock. Also the value could be reset optionally. Suggested-by: Peter Zijlstra Signed-off-by: Like Xu Acked-by: Peter Zijlstra Signed-off-by: Paolo Bonzini --- include/linux/perf_event.h | 5 +++++ kernel/events/core.c | 18 ++++++++++++++++++ 2 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index d601df36e671..e9768bfc76f6 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1337,6 +1337,7 @@ extern void perf_event_disable_inatomic(struct perf_event *event); extern void perf_event_task_tick(void); extern int perf_event_account_interrupt(struct perf_event *event); extern int perf_event_period(struct perf_event *event, u64 value); +extern u64 perf_event_pause(struct perf_event *event, bool reset); #else /* !CONFIG_PERF_EVENTS: */ static inline void * perf_aux_output_begin(struct perf_output_handle *handle, @@ -1420,6 +1421,10 @@ static inline int perf_event_period(struct perf_event *event, u64 value) { return -EINVAL; } +static inline u64 perf_event_pause(struct perf_event *event, bool reset) +{ + return 0; +} #endif #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) diff --git a/kernel/events/core.c b/kernel/events/core.c index e1b83d2731da..fc9f5ebf4849 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5029,6 +5029,24 @@ static void _perf_event_reset(struct perf_event *event) perf_event_update_userpage(event); } +/* Assume it's not an event with inherit set. */ +u64 perf_event_pause(struct perf_event *event, bool reset) +{ + struct perf_event_context *ctx; + u64 count; + + ctx = perf_event_ctx_lock(event); + WARN_ON_ONCE(event->attr.inherit); + _perf_event_disable(event); + count = local64_read(&event->count); + if (reset) + local64_set(&event->count, 0); + perf_event_ctx_unlock(event, ctx); + + return count; +} +EXPORT_SYMBOL_GPL(perf_event_pause); + /* * Holding the top-level event's child_mutex means that any * descendant process that has inherited this event will block -- cgit v1.2.3-71-gd317 From 8750e72a79dda2f665ce17b62049f4d62130d991 Mon Sep 17 00:00:00 2001 From: Radim Krčmář Date: Thu, 7 Nov 2019 07:53:42 -0500 Subject: KVM: remember position in kvm->vcpus array MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fetching an index for any vcpu in kvm->vcpus array by traversing the entire array everytime is costly. This patch remembers the position of each vcpu in kvm->vcpus array by storing it in vcpus_idx under kvm_vcpu structure. Signed-off-by: Radim Krčmář Signed-off-by: Nitesh Narayan Lal Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 11 +++-------- virt/kvm/kvm_main.c | 5 +++-- 2 files changed, 6 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index a817e446c9aa..70b2296fb2ae 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -266,7 +266,8 @@ struct kvm_vcpu { struct preempt_notifier preempt_notifier; #endif int cpu; - int vcpu_id; + int vcpu_id; /* id given by userspace at creation */ + int vcpu_idx; /* index in kvm->vcpus array */ int srcu_idx; int mode; u64 requests; @@ -570,13 +571,7 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu) { - struct kvm_vcpu *tmp; - int idx; - - kvm_for_each_vcpu(idx, tmp, vcpu->kvm) - if (tmp == vcpu) - return idx; - BUG(); + return vcpu->vcpu_idx; } #define kvm_for_each_memslot(memslot, slots) \ diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index b8534c6b8cf6..a158a93323f7 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2685,7 +2685,8 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) goto unlock_vcpu_destroy; } - BUG_ON(kvm->vcpus[atomic_read(&kvm->online_vcpus)]); + vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus); + BUG_ON(kvm->vcpus[vcpu->vcpu_idx]); /* Now it's all set up, let userspace reach it */ kvm_get_kvm(kvm); @@ -2695,7 +2696,7 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) goto unlock_vcpu_destroy; } - kvm->vcpus[atomic_read(&kvm->online_vcpus)] = vcpu; + kvm->vcpus[vcpu->vcpu_idx] = vcpu; /* * Pairs with smp_rmb() in kvm_get_vcpu. Write kvm->vcpus -- cgit v1.2.3-71-gd317 From 7ee30bc132c683d06a6d9e360e39e483e3990708 Mon Sep 17 00:00:00 2001 From: Nitesh Narayan Lal Date: Thu, 7 Nov 2019 07:53:43 -0500 Subject: KVM: x86: deliver KVM IOAPIC scan request to target vCPUs In IOAPIC fixed delivery mode instead of flushing the scan requests to all vCPUs, we should only send the requests to vCPUs specified within the destination field. This patch introduces kvm_get_dest_vcpus_mask() API which retrieves an array of target vCPUs by using kvm_apic_map_get_dest_lapic() and then based on the vcpus_idx, it sets the bit in a bitmap. However, if the above fails kvm_get_dest_vcpus_mask() finds the target vCPUs by traversing all available vCPUs. Followed by setting the bits in the bitmap. If we had different vCPUs in the previous request for the same redirection table entry then bits corresponding to these vCPUs are also set. This to done to keep ioapic_handled_vectors synchronized. This bitmap is then eventually passed on to kvm_make_vcpus_request_mask() to generate a masked request only for the target vCPUs. This would enable us to reduce the latency overhead on isolated vCPUs caused by the IPI to process due to KVM_REQ_IOAPIC_SCAN. Suggested-by: Marcelo Tosatti Signed-off-by: Nitesh Narayan Lal Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 2 ++ arch/x86/kvm/ioapic.c | 33 +++++++++++++++++++++++++++++-- arch/x86/kvm/lapic.c | 44 +++++++++++++++++++++++++++++++++++++++++ arch/x86/kvm/lapic.h | 3 +++ arch/x86/kvm/x86.c | 14 +++++++++++++ include/linux/kvm_host.h | 2 ++ 6 files changed, 96 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 20bb2fc0883a..898ab9eb4dc8 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1588,6 +1588,8 @@ bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip); void kvm_make_mclock_inprogress_request(struct kvm *kvm); void kvm_make_scan_ioapic_request(struct kvm *kvm); +void kvm_make_scan_ioapic_request_mask(struct kvm *kvm, + unsigned long *vcpu_bitmap); void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work); diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index d859ae8890d0..ce30ef23c86b 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -271,8 +271,9 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) { unsigned index; bool mask_before, mask_after; - int old_remote_irr, old_delivery_status; union kvm_ioapic_redirect_entry *e; + unsigned long vcpu_bitmap; + int old_remote_irr, old_delivery_status, old_dest_id, old_dest_mode; switch (ioapic->ioregsel) { case IOAPIC_REG_VERSION: @@ -296,6 +297,8 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) /* Preserve read-only fields */ old_remote_irr = e->fields.remote_irr; old_delivery_status = e->fields.delivery_status; + old_dest_id = e->fields.dest_id; + old_dest_mode = e->fields.dest_mode; if (ioapic->ioregsel & 1) { e->bits &= 0xffffffff; e->bits |= (u64) val << 32; @@ -321,7 +324,33 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG && ioapic->irr & (1 << index)) ioapic_service(ioapic, index, false); - kvm_make_scan_ioapic_request(ioapic->kvm); + if (e->fields.delivery_mode == APIC_DM_FIXED) { + struct kvm_lapic_irq irq; + + irq.shorthand = 0; + irq.vector = e->fields.vector; + irq.delivery_mode = e->fields.delivery_mode << 8; + irq.dest_id = e->fields.dest_id; + irq.dest_mode = e->fields.dest_mode; + kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq, + &vcpu_bitmap); + if (old_dest_mode != e->fields.dest_mode || + old_dest_id != e->fields.dest_id) { + /* + * Update vcpu_bitmap with vcpus specified in + * the previous request as well. This is done to + * keep ioapic_handled_vectors synchronized. + */ + irq.dest_id = old_dest_id; + irq.dest_mode = old_dest_mode; + kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq, + &vcpu_bitmap); + } + kvm_make_scan_ioapic_request_mask(ioapic->kvm, + &vcpu_bitmap); + } else { + kvm_make_scan_ioapic_request(ioapic->kvm); + } break; } } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 60fb21fe7f42..452cedd6382b 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1122,6 +1122,50 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, return result; } +/* + * This routine identifies the destination vcpus mask meant to receive the + * IOAPIC interrupts. It either uses kvm_apic_map_get_dest_lapic() to find + * out the destination vcpus array and set the bitmap or it traverses to + * each available vcpu to identify the same. + */ +void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq, + unsigned long *vcpu_bitmap) +{ + struct kvm_lapic **dest_vcpu = NULL; + struct kvm_lapic *src = NULL; + struct kvm_apic_map *map; + struct kvm_vcpu *vcpu; + unsigned long bitmap; + int i, vcpu_idx; + bool ret; + + rcu_read_lock(); + map = rcu_dereference(kvm->arch.apic_map); + + ret = kvm_apic_map_get_dest_lapic(kvm, &src, irq, map, &dest_vcpu, + &bitmap); + if (ret) { + for_each_set_bit(i, &bitmap, 16) { + if (!dest_vcpu[i]) + continue; + vcpu_idx = dest_vcpu[i]->vcpu->vcpu_idx; + __set_bit(vcpu_idx, vcpu_bitmap); + } + } else { + kvm_for_each_vcpu(i, vcpu, kvm) { + if (!kvm_apic_present(vcpu)) + continue; + if (!kvm_apic_match_dest(vcpu, NULL, + irq->delivery_mode, + irq->dest_id, + irq->dest_mode)) + continue; + __set_bit(i, vcpu_bitmap); + } + } + rcu_read_unlock(); +} + int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2) { return vcpu1->arch.apic_arb_prio - vcpu2->arch.apic_arb_prio; diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 2aad7e226fc0..c1d77436126a 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -226,6 +226,9 @@ bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector); void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu); +void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq, + unsigned long *vcpu_bitmap); + bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_vcpu **dest_vcpu); int kvm_vector_to_index(u32 vector, u32 dest_vcpus, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 8db7275d313f..991dd01ba08b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7874,6 +7874,20 @@ static void process_smi(struct kvm_vcpu *vcpu) kvm_make_request(KVM_REQ_EVENT, vcpu); } +void kvm_make_scan_ioapic_request_mask(struct kvm *kvm, + unsigned long *vcpu_bitmap) +{ + cpumask_var_t cpus; + bool called; + + zalloc_cpumask_var(&cpus, GFP_ATOMIC); + + called = kvm_make_vcpus_request_mask(kvm, KVM_REQ_SCAN_IOAPIC, + vcpu_bitmap, cpus); + + free_cpumask_var(cpus); +} + void kvm_make_scan_ioapic_request(struct kvm *kvm) { kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 70b2296fb2ae..bfe6c6729988 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -786,6 +786,8 @@ void kvm_reload_remote_mmus(struct kvm *kvm); bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, unsigned long *vcpu_bitmap, cpumask_var_t tmp); bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req); +bool kvm_make_cpus_request_mask(struct kvm *kvm, unsigned int req, + unsigned long *vcpu_bitmap); long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); -- cgit v1.2.3-71-gd317 From 2a785996cc5e2fc1d1d29d196f530905f68d2dc2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 5 Nov 2019 11:10:01 +0100 Subject: y2038: uapi: change __kernel_time_t to __kernel_old_time_t This is mainly a patch for clarification, and to let us remove the time_t definition from the kernel to prevent new users from creeping in that might not be y2038-safe. All remaining uses of 'time_t' or '__kernel_time_t' are part of the user API that cannot be changed by that either have a replacement or that do not suffer from the y2038 overflow. Acked-by: Deepa Dinamani Acked-by: Christian Brauner Signed-off-by: Arnd Bergmann --- include/linux/syscalls.h | 4 ++-- include/linux/time32.h | 2 +- include/linux/types.h | 2 +- include/uapi/linux/cyclades.h | 6 +++--- include/uapi/linux/msg.h | 6 +++--- include/uapi/linux/ppp_defs.h | 4 ++-- include/uapi/linux/sem.h | 4 ++-- include/uapi/linux/shm.h | 6 +++--- include/uapi/linux/time.h | 6 +++--- include/uapi/linux/time_types.h | 4 ++-- include/uapi/linux/utime.h | 4 ++-- kernel/time/time.c | 6 +++--- 12 files changed, 27 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index f7c561c4dcdd..2f27bc9d5ef0 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1076,7 +1076,7 @@ asmlinkage long sys_fadvise64(int fd, loff_t offset, size_t len, int advice); asmlinkage long sys_alarm(unsigned int seconds); asmlinkage long sys_getpgrp(void); asmlinkage long sys_pause(void); -asmlinkage long sys_time(time_t __user *tloc); +asmlinkage long sys_time(__kernel_old_time_t __user *tloc); asmlinkage long sys_time32(old_time32_t __user *tloc); #ifdef __ARCH_WANT_SYS_UTIME asmlinkage long sys_utime(char __user *filename, @@ -1116,7 +1116,7 @@ asmlinkage long sys_sysfs(int option, asmlinkage long sys_fork(void); /* obsolete: kernel/time/time.c */ -asmlinkage long sys_stime(time_t __user *tptr); +asmlinkage long sys_stime(__kernel_old_time_t __user *tptr); asmlinkage long sys_stime32(old_time32_t __user *tptr); /* obsolete: kernel/signal.c */ diff --git a/include/linux/time32.h b/include/linux/time32.h index 0a1f302a1753..cad4c3186002 100644 --- a/include/linux/time32.h +++ b/include/linux/time32.h @@ -12,7 +12,7 @@ #include #include -#define TIME_T_MAX (time_t)((1UL << ((sizeof(time_t) << 3) - 1)) - 1) +#define TIME_T_MAX (__kernel_old_time_t)((1UL << ((sizeof(__kernel_old_time_t) << 3) - 1)) - 1) typedef s32 old_time32_t; diff --git a/include/linux/types.h b/include/linux/types.h index 05030f608be3..e32c1180b742 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -67,7 +67,7 @@ typedef __kernel_ptrdiff_t ptrdiff_t; #ifndef _TIME_T #define _TIME_T -typedef __kernel_time_t time_t; +typedef __kernel_old_time_t time_t; #endif #ifndef _CLOCK_T diff --git a/include/uapi/linux/cyclades.h b/include/uapi/linux/cyclades.h index 8279bc3d60ca..fc0add2194a9 100644 --- a/include/uapi/linux/cyclades.h +++ b/include/uapi/linux/cyclades.h @@ -83,9 +83,9 @@ struct cyclades_monitor { * open) */ struct cyclades_idle_stats { - __kernel_time_t in_use; /* Time device has been in use (secs) */ - __kernel_time_t recv_idle; /* Time since last char received (secs) */ - __kernel_time_t xmit_idle; /* Time since last char transmitted (secs) */ + __kernel_old_time_t in_use; /* Time device has been in use (secs) */ + __kernel_old_time_t recv_idle; /* Time since last char received (secs) */ + __kernel_old_time_t xmit_idle; /* Time since last char transmitted (secs) */ unsigned long recv_bytes; /* Bytes received */ unsigned long xmit_bytes; /* Bytes transmitted */ unsigned long overruns; /* Input overruns */ diff --git a/include/uapi/linux/msg.h b/include/uapi/linux/msg.h index e4a0d9a9a9e8..01ee8d54c1c8 100644 --- a/include/uapi/linux/msg.h +++ b/include/uapi/linux/msg.h @@ -19,9 +19,9 @@ struct msqid_ds { struct ipc_perm msg_perm; struct msg *msg_first; /* first message on queue,unused */ struct msg *msg_last; /* last message in queue,unused */ - __kernel_time_t msg_stime; /* last msgsnd time */ - __kernel_time_t msg_rtime; /* last msgrcv time */ - __kernel_time_t msg_ctime; /* last change time */ + __kernel_old_time_t msg_stime; /* last msgsnd time */ + __kernel_old_time_t msg_rtime; /* last msgrcv time */ + __kernel_old_time_t msg_ctime; /* last change time */ unsigned long msg_lcbytes; /* Reuse junk fields for 32 bit */ unsigned long msg_lqbytes; /* ditto */ unsigned short msg_cbytes; /* current number of bytes on queue */ diff --git a/include/uapi/linux/ppp_defs.h b/include/uapi/linux/ppp_defs.h index fff51b91b409..9277a33d08a2 100644 --- a/include/uapi/linux/ppp_defs.h +++ b/include/uapi/linux/ppp_defs.h @@ -144,8 +144,8 @@ struct ppp_comp_stats { * the last NP packet was sent or received. */ struct ppp_idle { - __kernel_time_t xmit_idle; /* time since last NP packet sent */ - __kernel_time_t recv_idle; /* time since last NP packet received */ + __kernel_old_time_t xmit_idle; /* time since last NP packet sent */ + __kernel_old_time_t recv_idle; /* time since last NP packet received */ }; #endif /* _UAPI_PPP_DEFS_H_ */ diff --git a/include/uapi/linux/sem.h b/include/uapi/linux/sem.h index 39a1876f039e..75aa3b273cd9 100644 --- a/include/uapi/linux/sem.h +++ b/include/uapi/linux/sem.h @@ -24,8 +24,8 @@ /* Obsolete, used only for backwards compatibility and libc5 compiles */ struct semid_ds { struct ipc_perm sem_perm; /* permissions .. see ipc.h */ - __kernel_time_t sem_otime; /* last semop time */ - __kernel_time_t sem_ctime; /* create/last semctl() time */ + __kernel_old_time_t sem_otime; /* last semop time */ + __kernel_old_time_t sem_ctime; /* create/last semctl() time */ struct sem *sem_base; /* ptr to first semaphore in array */ struct sem_queue *sem_pending; /* pending operations to be processed */ struct sem_queue **sem_pending_last; /* last pending operation */ diff --git a/include/uapi/linux/shm.h b/include/uapi/linux/shm.h index 6507ad0afc81..8d1f17a4e08e 100644 --- a/include/uapi/linux/shm.h +++ b/include/uapi/linux/shm.h @@ -28,9 +28,9 @@ struct shmid_ds { struct ipc_perm shm_perm; /* operation perms */ int shm_segsz; /* size of segment (bytes) */ - __kernel_time_t shm_atime; /* last attach time */ - __kernel_time_t shm_dtime; /* last detach time */ - __kernel_time_t shm_ctime; /* last change time */ + __kernel_old_time_t shm_atime; /* last attach time */ + __kernel_old_time_t shm_dtime; /* last detach time */ + __kernel_old_time_t shm_ctime; /* last change time */ __kernel_ipc_pid_t shm_cpid; /* pid of creator */ __kernel_ipc_pid_t shm_lpid; /* pid of last operator */ unsigned short shm_nattch; /* no. of current attaches */ diff --git a/include/uapi/linux/time.h b/include/uapi/linux/time.h index 958932effc5e..a655aa28dc6e 100644 --- a/include/uapi/linux/time.h +++ b/include/uapi/linux/time.h @@ -8,13 +8,13 @@ #ifndef _STRUCT_TIMESPEC #define _STRUCT_TIMESPEC struct timespec { - __kernel_time_t tv_sec; /* seconds */ - long tv_nsec; /* nanoseconds */ + __kernel_old_time_t tv_sec; /* seconds */ + long tv_nsec; /* nanoseconds */ }; #endif struct timeval { - __kernel_time_t tv_sec; /* seconds */ + __kernel_old_time_t tv_sec; /* seconds */ __kernel_suseconds_t tv_usec; /* microseconds */ }; diff --git a/include/uapi/linux/time_types.h b/include/uapi/linux/time_types.h index 60b37f29842d..074e391d73a1 100644 --- a/include/uapi/linux/time_types.h +++ b/include/uapi/linux/time_types.h @@ -29,8 +29,8 @@ struct __kernel_old_timeval { #endif struct __kernel_old_timespec { - __kernel_time_t tv_sec; /* seconds */ - long tv_nsec; /* nanoseconds */ + __kernel_old_time_t tv_sec; /* seconds */ + long tv_nsec; /* nanoseconds */ }; struct __kernel_sock_timeval { diff --git a/include/uapi/linux/utime.h b/include/uapi/linux/utime.h index fd9aa26b6860..bc8f13e81d6e 100644 --- a/include/uapi/linux/utime.h +++ b/include/uapi/linux/utime.h @@ -5,8 +5,8 @@ #include struct utimbuf { - __kernel_time_t actime; - __kernel_time_t modtime; + __kernel_old_time_t actime; + __kernel_old_time_t modtime; }; #endif diff --git a/kernel/time/time.c b/kernel/time/time.c index 96b8c02657ed..833abae3364f 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -59,9 +59,9 @@ EXPORT_SYMBOL(sys_tz); * why not move it into the appropriate arch directory (for those * architectures that need it). */ -SYSCALL_DEFINE1(time, time_t __user *, tloc) +SYSCALL_DEFINE1(time, __kernel_old_time_t __user *, tloc) { - time_t i = (time_t)ktime_get_real_seconds(); + __kernel_old_time_t i = (__kernel_old_time_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) @@ -78,7 +78,7 @@ SYSCALL_DEFINE1(time, time_t __user *, tloc) * architectures that need it). */ -SYSCALL_DEFINE1(stime, time_t __user *, tptr) +SYSCALL_DEFINE1(stime, __kernel_old_time_t __user *, tptr) { struct timespec64 tv; int err; -- cgit v1.2.3-71-gd317 From 75d319c06e6a76f67549c0ae1007dc3167804f4e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 25 Oct 2019 22:56:17 +0200 Subject: y2038: syscalls: change remaining timeval to __kernel_old_timeval All of the remaining syscalls that pass a timeval (gettimeofday, utime, futimesat) can trivially be changed to pass a __kernel_old_timeval instead, which has a compatible layout, but avoids ambiguity with the timeval type in user space. Acked-by: Christian Brauner Acked-by: Rafael J. Wysocki Signed-off-by: Arnd Bergmann --- arch/powerpc/include/asm/asm-prototypes.h | 3 ++- arch/powerpc/kernel/syscalls.c | 4 ++-- fs/select.c | 10 +++++----- fs/utimes.c | 8 ++++---- include/linux/syscalls.h | 10 +++++----- kernel/power/power.h | 2 +- kernel/time/time.c | 2 +- 7 files changed, 20 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index 8561498e653c..2c25dc079cb9 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -92,7 +92,8 @@ long sys_swapcontext(struct ucontext __user *old_ctx, long sys_debug_setcontext(struct ucontext __user *ctx, int ndbg, struct sig_dbg_op __user *dbg); int -ppc_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp); +ppc_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, + struct __kernel_old_timeval __user *tvp); unsigned long __init early_init(unsigned long dt_ptr); void __init machine_init(u64 dt_ptr); #endif diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index 3bfb3888e897..078608ec2e92 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -79,7 +79,7 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, size_t, len, * sys_select() with the appropriate args. -- Cort */ int -ppc_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp) +ppc_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct __kernel_old_timeval __user *tvp) { if ( (unsigned long)n >= 4096 ) { @@ -89,7 +89,7 @@ ppc_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, s || __get_user(inp, ((fd_set __user * __user *)(buffer+1))) || __get_user(outp, ((fd_set __user * __user *)(buffer+2))) || __get_user(exp, ((fd_set __user * __user *)(buffer+3))) - || __get_user(tvp, ((struct timeval __user * __user *)(buffer+4)))) + || __get_user(tvp, ((struct __kernel_old_timeval __user * __user *)(buffer+4)))) return -EFAULT; } return sys_select(n, inp, outp, exp, tvp); diff --git a/fs/select.c b/fs/select.c index 53a0c149f528..11d0285d46b7 100644 --- a/fs/select.c +++ b/fs/select.c @@ -321,7 +321,7 @@ static int poll_select_finish(struct timespec64 *end_time, switch (pt_type) { case PT_TIMEVAL: { - struct timeval rtv; + struct __kernel_old_timeval rtv; if (sizeof(rtv) > sizeof(rtv.tv_sec) + sizeof(rtv.tv_usec)) memset(&rtv, 0, sizeof(rtv)); @@ -698,10 +698,10 @@ out_nofds: } static int kern_select(int n, fd_set __user *inp, fd_set __user *outp, - fd_set __user *exp, struct timeval __user *tvp) + fd_set __user *exp, struct __kernel_old_timeval __user *tvp) { struct timespec64 end_time, *to = NULL; - struct timeval tv; + struct __kernel_old_timeval tv; int ret; if (tvp) { @@ -720,7 +720,7 @@ static int kern_select(int n, fd_set __user *inp, fd_set __user *outp, } SYSCALL_DEFINE5(select, int, n, fd_set __user *, inp, fd_set __user *, outp, - fd_set __user *, exp, struct timeval __user *, tvp) + fd_set __user *, exp, struct __kernel_old_timeval __user *, tvp) { return kern_select(n, inp, outp, exp, tvp); } @@ -810,7 +810,7 @@ SYSCALL_DEFINE6(pselect6_time32, int, n, fd_set __user *, inp, fd_set __user *, struct sel_arg_struct { unsigned long n; fd_set __user *inp, *outp, *exp; - struct timeval __user *tvp; + struct __kernel_old_timeval __user *tvp; }; SYSCALL_DEFINE1(old_select, struct sel_arg_struct __user *, arg) diff --git a/fs/utimes.c b/fs/utimes.c index 1ba3f7883870..c952b6b3d8a0 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -161,9 +161,9 @@ SYSCALL_DEFINE4(utimensat, int, dfd, const char __user *, filename, * utimensat() instead. */ static long do_futimesat(int dfd, const char __user *filename, - struct timeval __user *utimes) + struct __kernel_old_timeval __user *utimes) { - struct timeval times[2]; + struct __kernel_old_timeval times[2]; struct timespec64 tstimes[2]; if (utimes) { @@ -190,13 +190,13 @@ static long do_futimesat(int dfd, const char __user *filename, SYSCALL_DEFINE3(futimesat, int, dfd, const char __user *, filename, - struct timeval __user *, utimes) + struct __kernel_old_timeval __user *, utimes) { return do_futimesat(dfd, filename, utimes); } SYSCALL_DEFINE2(utimes, char __user *, filename, - struct timeval __user *, utimes) + struct __kernel_old_timeval __user *, utimes) { return do_futimesat(AT_FDCWD, filename, utimes); } diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 2f27bc9d5ef0..e665920fa359 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -51,7 +51,7 @@ struct statx; struct __sysctl_args; struct sysinfo; struct timespec; -struct timeval; +struct __kernel_old_timeval; struct __kernel_timex; struct timezone; struct tms; @@ -732,7 +732,7 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3, asmlinkage long sys_getcpu(unsigned __user *cpu, unsigned __user *node, struct getcpu_cache __user *cache); /* kernel/time.c */ -asmlinkage long sys_gettimeofday(struct timeval __user *tv, +asmlinkage long sys_gettimeofday(struct __kernel_old_timeval __user *tv, struct timezone __user *tz); asmlinkage long sys_settimeofday(struct timeval __user *tv, struct timezone __user *tz); @@ -1082,9 +1082,9 @@ asmlinkage long sys_time32(old_time32_t __user *tloc); asmlinkage long sys_utime(char __user *filename, struct utimbuf __user *times); asmlinkage long sys_utimes(char __user *filename, - struct timeval __user *utimes); + struct __kernel_old_timeval __user *utimes); asmlinkage long sys_futimesat(int dfd, const char __user *filename, - struct timeval __user *utimes); + struct __kernel_old_timeval __user *utimes); #endif asmlinkage long sys_futimesat_time32(unsigned int dfd, const char __user *filename, @@ -1098,7 +1098,7 @@ asmlinkage long sys_getdents(unsigned int fd, struct linux_dirent __user *dirent, unsigned int count); asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp, - fd_set __user *exp, struct timeval __user *tvp); + fd_set __user *exp, struct __kernel_old_timeval __user *tvp); asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds, int timeout); asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events, diff --git a/kernel/power/power.h b/kernel/power/power.h index 44bee462ff57..7cdc64dc2373 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -179,7 +179,7 @@ extern void swsusp_close(fmode_t); extern int swsusp_unmark(void); #endif -struct timeval; +struct __kernel_old_timeval; /* kernel/power/swsusp.c */ extern void swsusp_show_speed(ktime_t, ktime_t, unsigned int, char *); diff --git a/kernel/time/time.c b/kernel/time/time.c index 833abae3364f..a0e7b9909f2d 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -137,7 +137,7 @@ SYSCALL_DEFINE1(stime32, old_time32_t __user *, tptr) #endif /* __ARCH_WANT_SYS_TIME32 */ #endif -SYSCALL_DEFINE2(gettimeofday, struct timeval __user *, tv, +SYSCALL_DEFINE2(gettimeofday, struct __kernel_old_timeval __user *, tv, struct timezone __user *, tz) { if (likely(tv != NULL)) { -- cgit v1.2.3-71-gd317 From df1b4ba9d4a8454285c53c2ec7224228105bc5c8 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 25 Oct 2019 22:04:46 +0200 Subject: y2038: socket: use __kernel_old_timespec instead of timespec The 'timespec' type definition and helpers like ktime_to_timespec() or timespec64_to_timespec() should no longer be used in the kernel so we can remove them and avoid introducing y2038 issues in new code. Change the socket code that needs to pass a timespec to user space for backward compatibility to use __kernel_old_timespec instead. This type has the same layout but with a clearer defined name. Slightly reformat tcp_recv_timestamp() for consistency after the removal of timespec64_to_timespec(). Acked-by: Deepa Dinamani Signed-off-by: Arnd Bergmann --- include/linux/skbuff.h | 7 +++++-- net/compat.c | 2 +- net/ipv4/tcp.c | 28 ++++++++++++++++------------ net/socket.c | 2 +- 4 files changed, 23 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 64a395c7f689..6d64ffe92867 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3656,9 +3656,12 @@ static inline void skb_get_new_timestamp(const struct sk_buff *skb, } static inline void skb_get_timestampns(const struct sk_buff *skb, - struct timespec *stamp) + struct __kernel_old_timespec *stamp) { - *stamp = ktime_to_timespec(skb->tstamp); + struct timespec64 ts = ktime_to_timespec64(skb->tstamp); + + stamp->tv_sec = ts.tv_sec; + stamp->tv_nsec = ts.tv_nsec; } static inline void skb_get_new_timestampns(const struct sk_buff *skb, diff --git a/net/compat.c b/net/compat.c index 0f7ded26059e..47d99c784947 100644 --- a/net/compat.c +++ b/net/compat.c @@ -232,7 +232,7 @@ int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *dat (type == SO_TIMESTAMPNS_OLD || type == SO_TIMESTAMPING_OLD)) { int count = type == SO_TIMESTAMPNS_OLD ? 1 : 3; int i; - struct timespec *ts = (struct timespec *)data; + struct __kernel_old_timespec *ts = data; for (i = 0; i < count; i++) { cts[i].tv_sec = ts[i].tv_sec; cts[i].tv_nsec = ts[i].tv_nsec; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index d8876f0e9672..013f635db19c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1864,29 +1864,33 @@ static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, if (sock_flag(sk, SOCK_RCVTSTAMP)) { if (sock_flag(sk, SOCK_RCVTSTAMPNS)) { if (new_tstamp) { - struct __kernel_timespec kts = {tss->ts[0].tv_sec, tss->ts[0].tv_nsec}; - + struct __kernel_timespec kts = { + .tv_sec = tss->ts[0].tv_sec, + .tv_nsec = tss->ts[0].tv_nsec, + }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_NEW, sizeof(kts), &kts); } else { - struct timespec ts_old = timespec64_to_timespec(tss->ts[0]); - + struct __kernel_old_timespec ts_old = { + .tv_sec = tss->ts[0].tv_sec, + .tv_nsec = tss->ts[0].tv_nsec, + }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD, sizeof(ts_old), &ts_old); } } else { if (new_tstamp) { - struct __kernel_sock_timeval stv; - - stv.tv_sec = tss->ts[0].tv_sec; - stv.tv_usec = tss->ts[0].tv_nsec / 1000; + struct __kernel_sock_timeval stv = { + .tv_sec = tss->ts[0].tv_sec, + .tv_usec = tss->ts[0].tv_nsec / 1000, + }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW, sizeof(stv), &stv); } else { - struct __kernel_old_timeval tv; - - tv.tv_sec = tss->ts[0].tv_sec; - tv.tv_usec = tss->ts[0].tv_nsec / 1000; + struct __kernel_old_timeval tv = { + .tv_sec = tss->ts[0].tv_sec, + .tv_usec = tss->ts[0].tv_nsec / 1000, + }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, sizeof(tv), &tv); } diff --git a/net/socket.c b/net/socket.c index 98f6544b0096..9ab00a080760 100644 --- a/net/socket.c +++ b/net/socket.c @@ -793,7 +793,7 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_NEW, sizeof(ts), &ts); } else { - struct timespec ts; + struct __kernel_old_timespec ts; skb_get_timestampns(skb, &ts); put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD, -- cgit v1.2.3-71-gd317 From 693737b6cc2edc258040b28462a90b63503394d9 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 23 Nov 2017 14:22:06 +0100 Subject: y2038: make ns_to_compat_timeval use __kernel_old_timeval This gets us one step closer to removing 'struct timeval' from the kernel. We still keep __kernel_old_timeval for interfaces that we cannot fix otherwise, and ns_to_compat_timeval() is provably safe for interfaces that are legitimate users of __kernel_old_timeval on native kernels, so this is an obvious change. Signed-off-by: Arnd Bergmann --- include/linux/compat.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 16dafd9f4b86..3735a22bfbc0 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -937,10 +937,10 @@ static inline bool in_compat_syscall(void) { return is_compat_task(); } */ static inline struct old_timeval32 ns_to_old_timeval32(s64 nsec) { - struct timeval tv; + struct __kernel_old_timeval tv; struct old_timeval32 ctv; - tv = ns_to_timeval(nsec); + tv = ns_to_kernel_old_timeval(nsec); ctv.tv_sec = tv.tv_sec; ctv.tv_usec = tv.tv_usec; -- cgit v1.2.3-71-gd317 From 5e0fb1b57bea8d11fe77da2bc80f4c9a67e28318 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 15 Aug 2018 20:04:11 +0200 Subject: y2038: time: avoid timespec usage in settimeofday() The compat_get_timeval() and timeval_valid() interfaces are deprecated and getting removed along with the definition of struct timeval itself. Change the two implementations of the settimeofday() system call to open-code these helpers and completely avoid references to timeval. The timeval_valid() call is not needed any more here, only a check to avoid overflowing tv_nsec during the multiplication, as there is another range check in do_sys_settimeofday64(). Tested-by: syzbot+dccce9b26ba09ca49966@syzkaller.appspotmail.com Signed-off-by: Arnd Bergmann --- include/linux/syscalls.h | 2 +- kernel/time/time.c | 20 +++++++++----------- 2 files changed, 10 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index e665920fa359..d0391cc2dae9 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -734,7 +734,7 @@ asmlinkage long sys_getcpu(unsigned __user *cpu, unsigned __user *node, struct g /* kernel/time.c */ asmlinkage long sys_gettimeofday(struct __kernel_old_timeval __user *tv, struct timezone __user *tz); -asmlinkage long sys_settimeofday(struct timeval __user *tv, +asmlinkage long sys_settimeofday(struct __kernel_old_timeval __user *tv, struct timezone __user *tz); asmlinkage long sys_adjtimex(struct __kernel_timex __user *txc_p); asmlinkage long sys_adjtimex_time32(struct old_timex32 __user *txc_p); diff --git a/kernel/time/time.c b/kernel/time/time.c index a0e7b9909f2d..58e312e7380f 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -196,22 +196,21 @@ int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz return 0; } -SYSCALL_DEFINE2(settimeofday, struct timeval __user *, tv, +SYSCALL_DEFINE2(settimeofday, struct __kernel_old_timeval __user *, tv, struct timezone __user *, tz) { struct timespec64 new_ts; - struct timeval user_tv; struct timezone new_tz; if (tv) { - if (copy_from_user(&user_tv, tv, sizeof(*tv))) + if (get_user(new_ts.tv_sec, &tv->tv_sec) || + get_user(new_ts.tv_nsec, &tv->tv_usec)) return -EFAULT; - if (!timeval_valid(&user_tv)) + if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0) return -EINVAL; - new_ts.tv_sec = user_tv.tv_sec; - new_ts.tv_nsec = user_tv.tv_usec * NSEC_PER_USEC; + new_ts.tv_nsec *= NSEC_PER_USEC; } if (tz) { if (copy_from_user(&new_tz, tz, sizeof(*tz))) @@ -245,18 +244,17 @@ COMPAT_SYSCALL_DEFINE2(settimeofday, struct old_timeval32 __user *, tv, struct timezone __user *, tz) { struct timespec64 new_ts; - struct timeval user_tv; struct timezone new_tz; if (tv) { - if (compat_get_timeval(&user_tv, tv)) + if (get_user(new_ts.tv_sec, &tv->tv_sec) || + get_user(new_ts.tv_nsec, &tv->tv_usec)) return -EFAULT; - if (!timeval_valid(&user_tv)) + if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0) return -EINVAL; - new_ts.tv_sec = user_tv.tv_sec; - new_ts.tv_nsec = user_tv.tv_usec * NSEC_PER_USEC; + new_ts.tv_nsec *= NSEC_PER_USEC; } if (tz) { if (copy_from_user(&new_tz, tz, sizeof(*tz))) -- cgit v1.2.3-71-gd317 From c1745f84be2657f5702388133551b759b9237f59 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 25 Oct 2019 10:46:22 +0200 Subject: y2038: itimer: compat handling to itimer.c The structure is only used in one place, moving it there simplifies the interface and helps with later changes to this code. Rename it to match the other time32 structures in the process. Reviewed-by: Thomas Gleixner Signed-off-by: Arnd Bergmann --- include/linux/compat.h | 15 ++++----------- kernel/compat.c | 24 ------------------------ kernel/time/itimer.c | 42 +++++++++++++++++++++++++++++++++++------- 3 files changed, 39 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 3735a22bfbc0..906a0ea933cd 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -116,14 +116,7 @@ typedef __compat_gid32_t compat_gid_t; struct compat_sel_arg_struct; struct rusage; -struct compat_itimerval { - struct old_timeval32 it_interval; - struct old_timeval32 it_value; -}; - -struct itimerval; -int get_compat_itimerval(struct itimerval *, const struct compat_itimerval __user *); -int put_compat_itimerval(struct compat_itimerval __user *, const struct itimerval *); +struct old_itimerval32; struct compat_tms { compat_clock_t tms_utime; @@ -668,10 +661,10 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr, /* kernel/itimer.c */ asmlinkage long compat_sys_getitimer(int which, - struct compat_itimerval __user *it); + struct old_itimerval32 __user *it); asmlinkage long compat_sys_setitimer(int which, - struct compat_itimerval __user *in, - struct compat_itimerval __user *out); + struct old_itimerval32 __user *in, + struct old_itimerval32 __user *out); /* kernel/kexec.c */ asmlinkage long compat_sys_kexec_load(compat_ulong_t entry, diff --git a/kernel/compat.c b/kernel/compat.c index a2bc1d6ceb57..95005f849c68 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -90,30 +90,6 @@ int compat_put_timespec(const struct timespec *ts, void __user *uts) } EXPORT_SYMBOL_GPL(compat_put_timespec); -int get_compat_itimerval(struct itimerval *o, const struct compat_itimerval __user *i) -{ - struct compat_itimerval v32; - - if (copy_from_user(&v32, i, sizeof(struct compat_itimerval))) - return -EFAULT; - o->it_interval.tv_sec = v32.it_interval.tv_sec; - o->it_interval.tv_usec = v32.it_interval.tv_usec; - o->it_value.tv_sec = v32.it_value.tv_sec; - o->it_value.tv_usec = v32.it_value.tv_usec; - return 0; -} - -int put_compat_itimerval(struct compat_itimerval __user *o, const struct itimerval *i) -{ - struct compat_itimerval v32; - - v32.it_interval.tv_sec = i->it_interval.tv_sec; - v32.it_interval.tv_usec = i->it_interval.tv_usec; - v32.it_value.tv_sec = i->it_value.tv_sec; - v32.it_value.tv_usec = i->it_value.tv_usec; - return copy_to_user(o, &v32, sizeof(struct compat_itimerval)) ? -EFAULT : 0; -} - #ifdef __ARCH_WANT_SYS_SIGPROCMASK /* diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c index 77f1e5635cc1..c52ebb40b60b 100644 --- a/kernel/time/itimer.c +++ b/kernel/time/itimer.c @@ -112,19 +112,34 @@ SYSCALL_DEFINE2(getitimer, int, which, struct itimerval __user *, value) } #ifdef CONFIG_COMPAT +struct old_itimerval32 { + struct old_timeval32 it_interval; + struct old_timeval32 it_value; +}; + +static int put_old_itimerval32(struct old_itimerval32 __user *o, const struct itimerval *i) +{ + struct old_itimerval32 v32; + + v32.it_interval.tv_sec = i->it_interval.tv_sec; + v32.it_interval.tv_usec = i->it_interval.tv_usec; + v32.it_value.tv_sec = i->it_value.tv_sec; + v32.it_value.tv_usec = i->it_value.tv_usec; + return copy_to_user(o, &v32, sizeof(struct old_itimerval32)) ? -EFAULT : 0; +} + COMPAT_SYSCALL_DEFINE2(getitimer, int, which, - struct compat_itimerval __user *, it) + struct old_itimerval32 __user *, it) { struct itimerval kit; int error = do_getitimer(which, &kit); - if (!error && put_compat_itimerval(it, &kit)) + if (!error && put_old_itimerval32(it, &kit)) error = -EFAULT; return error; } #endif - /* * The timer is automagically restarted, when interval != 0 */ @@ -310,15 +325,28 @@ SYSCALL_DEFINE3(setitimer, int, which, struct itimerval __user *, value, } #ifdef CONFIG_COMPAT +static int get_old_itimerval32(struct itimerval *o, const struct old_itimerval32 __user *i) +{ + struct old_itimerval32 v32; + + if (copy_from_user(&v32, i, sizeof(struct old_itimerval32))) + return -EFAULT; + o->it_interval.tv_sec = v32.it_interval.tv_sec; + o->it_interval.tv_usec = v32.it_interval.tv_usec; + o->it_value.tv_sec = v32.it_value.tv_sec; + o->it_value.tv_usec = v32.it_value.tv_usec; + return 0; +} + COMPAT_SYSCALL_DEFINE3(setitimer, int, which, - struct compat_itimerval __user *, in, - struct compat_itimerval __user *, out) + struct old_itimerval32 __user *, in, + struct old_itimerval32 __user *, out) { struct itimerval kin, kout; int error; if (in) { - if (get_compat_itimerval(&kin, in)) + if (get_old_itimerval32(&kin, in)) return -EFAULT; } else { memset(&kin, 0, sizeof(kin)); @@ -327,7 +355,7 @@ COMPAT_SYSCALL_DEFINE3(setitimer, int, which, error = do_setitimer(which, &kin, out ? &kout : NULL); if (error || !out) return error; - if (put_compat_itimerval(out, &kout)) + if (put_old_itimerval32(out, &kout)) return -EFAULT; return 0; } -- cgit v1.2.3-71-gd317 From ddbc7d0657e9fd38b69f16bd0310703367b52d29 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 25 Oct 2019 21:37:43 +0200 Subject: y2038: move itimer reset into itimer.c Preparing for a change to the itimer internals, stop using the do_setitimer() symbol and instead use a new higher-level interface. The do_getitimer()/do_setitimer functions can now be made static, allowing the compiler to potentially produce better object code. Reviewed-by: Thomas Gleixner Signed-off-by: Arnd Bergmann --- include/linux/time.h | 9 +++++---- kernel/time/itimer.c | 15 +++++++++++++-- security/selinux/hooks.c | 10 +++------- 3 files changed, 21 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index 27d83fd2ae61..0760a4f5a15c 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -35,10 +35,11 @@ extern time64_t mktime64(const unsigned int year, const unsigned int mon, extern u32 (*arch_gettimeoffset)(void); #endif -struct itimerval; -extern int do_setitimer(int which, struct itimerval *value, - struct itimerval *ovalue); -extern int do_getitimer(int which, struct itimerval *value); +#ifdef CONFIG_POSIX_TIMERS +extern void clear_itimer(void); +#else +static inline void clear_itimer(void) {} +#endif extern long do_utimes(int dfd, const char __user *filename, struct timespec64 *times, int flags); diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c index 4664c6addf69..ce9cd19ce72e 100644 --- a/kernel/time/itimer.c +++ b/kernel/time/itimer.c @@ -73,7 +73,7 @@ static void get_cpu_itimer(struct task_struct *tsk, unsigned int clock_id, value->it_interval = ns_to_timeval(interval); } -int do_getitimer(int which, struct itimerval *value) +static int do_getitimer(int which, struct itimerval *value) { struct task_struct *tsk = current; @@ -197,7 +197,7 @@ static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id, #define timeval_valid(t) \ (((t)->tv_sec >= 0) && (((unsigned long) (t)->tv_usec) < USEC_PER_SEC)) -int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue) +static int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue) { struct task_struct *tsk = current; struct hrtimer *timer; @@ -249,6 +249,17 @@ again: return 0; } +#ifdef CONFIG_SECURITY_SELINUX +void clear_itimer(void) +{ + struct itimerval v = {}; + int i; + + for (i = 0; i < 3; i++) + do_setitimer(i, &v, NULL); +} +#endif + #ifdef __ARCH_WANT_SYS_ALARM /** diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 9625b99e677f..456b5b596e1d 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -2549,9 +2549,8 @@ static void selinux_bprm_committing_creds(struct linux_binprm *bprm) static void selinux_bprm_committed_creds(struct linux_binprm *bprm) { const struct task_security_struct *tsec = selinux_cred(current_cred()); - struct itimerval itimer; u32 osid, sid; - int rc, i; + int rc; osid = tsec->osid; sid = tsec->sid; @@ -2569,11 +2568,8 @@ static void selinux_bprm_committed_creds(struct linux_binprm *bprm) rc = avc_has_perm(&selinux_state, osid, sid, SECCLASS_PROCESS, PROCESS__SIGINH, NULL); if (rc) { - if (IS_ENABLED(CONFIG_POSIX_TIMERS)) { - memset(&itimer, 0, sizeof itimer); - for (i = 0; i < 3; i++) - do_setitimer(i, &itimer, NULL); - } + clear_itimer(); + spin_lock_irq(¤t->sighand->siglock); if (!fatal_signal_pending(current)) { flush_sigqueue(¤t->pending); -- cgit v1.2.3-71-gd317 From 3c845acd0237caef617f330a0e3b37ad8ae9fea5 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 15 Nov 2019 11:22:10 +0100 Subject: jbd2: make jbd2_handle_buffer_credits() handle reserved handles The helper jbd2_handle_buffer_credits() doesn't correctly handle reserved handles which can lead to crashes. Fix it getting of journal pointer to work for reserved handles as well. Fixes: a9a8344ee171 ("ext4, jbd2: Provide accessor function for handle credits") Reported-by: Eric Biggers Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20191115102210.29445-1-jack@suse.cz Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 587c146d3987..842b62606025 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1627,10 +1627,14 @@ static inline tid_t jbd2_get_latest_transaction(journal_t *journal) return tid; } - static inline int jbd2_handle_buffer_credits(handle_t *handle) { - journal_t *journal = handle->h_transaction->t_journal; + journal_t *journal; + + if (!handle->h_reserved) + journal = handle->h_transaction->t_journal; + else + journal = handle->h_journal; return handle->h_total_credits - DIV_ROUND_UP(handle->h_revoke_credits_requested, -- cgit v1.2.3-71-gd317 From 6718b6f855a0b4962d54bd625be2718cb820cec6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 16 Oct 2019 16:47:32 +0100 Subject: pipe: Allow pipes to have kernel-reserved slots Split pipe->ring_size into two numbers: (1) pipe->ring_size - indicates the hard size of the pipe ring. (2) pipe->max_usage - indicates the maximum number of pipe ring slots that userspace orchestrated events can fill. This allows for a pipe that is both writable by the general kernel notification facility and by userspace, allowing plenty of ring space for notifications to be added whilst preventing userspace from being able to pin too much unswappable kernel space. Signed-off-by: David Howells --- fs/fuse/dev.c | 8 ++++---- fs/pipe.c | 10 ++++++---- fs/splice.c | 26 +++++++++++++------------- include/linux/pipe_fs_i.h | 6 +++++- lib/iov_iter.c | 4 ++-- 5 files changed, 30 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index c56011f95a87..423b6c657bf0 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -703,7 +703,7 @@ static int fuse_copy_fill(struct fuse_copy_state *cs) cs->pipebufs++; cs->nr_segs--; } else { - if (cs->nr_segs >= cs->pipe->ring_size) + if (cs->nr_segs >= cs->pipe->max_usage) return -EIO; page = alloc_page(GFP_HIGHUSER); @@ -879,7 +879,7 @@ static int fuse_ref_page(struct fuse_copy_state *cs, struct page *page, struct pipe_buffer *buf; int err; - if (cs->nr_segs >= cs->pipe->ring_size) + if (cs->nr_segs >= cs->pipe->max_usage) return -EIO; err = unlock_request(cs->req); @@ -1341,7 +1341,7 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos, if (!fud) return -EPERM; - bufs = kvmalloc_array(pipe->ring_size, sizeof(struct pipe_buffer), + bufs = kvmalloc_array(pipe->max_usage, sizeof(struct pipe_buffer), GFP_KERNEL); if (!bufs) return -ENOMEM; @@ -1353,7 +1353,7 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos, if (ret < 0) goto out; - if (pipe_occupancy(pipe->head, pipe->tail) + cs.nr_segs > pipe->ring_size) { + if (pipe_occupancy(pipe->head, pipe->tail) + cs.nr_segs > pipe->max_usage) { ret = -EIO; goto out; } diff --git a/fs/pipe.c b/fs/pipe.c index e9b361cb093e..69afeab8a73a 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -404,7 +404,7 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) tail = pipe->tail; head = pipe->head; - max_usage = pipe->ring_size; + max_usage = pipe->max_usage; mask = pipe->ring_size - 1; /* We try to merge small writes */ @@ -571,7 +571,7 @@ pipe_poll(struct file *filp, poll_table *wait) } if (filp->f_mode & FMODE_WRITE) { - if (!pipe_full(head, tail, pipe->ring_size)) + if (!pipe_full(head, tail, pipe->max_usage)) mask |= EPOLLOUT | EPOLLWRNORM; /* * Most Unices do not set EPOLLERR for FIFOs but on Linux they @@ -696,6 +696,7 @@ struct pipe_inode_info *alloc_pipe_info(void) if (pipe->bufs) { init_waitqueue_head(&pipe->wait); pipe->r_counter = pipe->w_counter = 1; + pipe->max_usage = pipe_bufs; pipe->ring_size = pipe_bufs; pipe->user = user; mutex_init(&pipe->mutex); @@ -1150,9 +1151,10 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) kfree(pipe->bufs); pipe->bufs = bufs; pipe->ring_size = nr_slots; + pipe->max_usage = nr_slots; pipe->tail = tail; pipe->head = head; - return pipe->ring_size * PAGE_SIZE; + return pipe->max_usage * PAGE_SIZE; out_revert_acct: (void) account_pipe_buffers(pipe->user, nr_slots, pipe->ring_size); @@ -1185,7 +1187,7 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg) ret = pipe_set_size(pipe, arg); break; case F_GETPIPE_SZ: - ret = pipe->ring_size * PAGE_SIZE; + ret = pipe->max_usage * PAGE_SIZE; break; default: ret = -EINVAL; diff --git a/fs/splice.c b/fs/splice.c index 22b0a47a35c0..c521090a0469 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -199,7 +199,7 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe, goto out; } - while (!pipe_full(head, tail, pipe->ring_size)) { + while (!pipe_full(head, tail, pipe->max_usage)) { struct pipe_buffer *buf = &pipe->bufs[head & mask]; buf->page = spd->pages[page_nr]; @@ -239,7 +239,7 @@ ssize_t add_to_pipe(struct pipe_inode_info *pipe, struct pipe_buffer *buf) if (unlikely(!pipe->readers)) { send_sig(SIGPIPE, current, 0); ret = -EPIPE; - } else if (pipe_full(head, tail, pipe->ring_size)) { + } else if (pipe_full(head, tail, pipe->max_usage)) { ret = -EAGAIN; } else { pipe->bufs[head & mask] = *buf; @@ -257,7 +257,7 @@ EXPORT_SYMBOL(add_to_pipe); */ int splice_grow_spd(const struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) { - unsigned int max_usage = READ_ONCE(pipe->ring_size); + unsigned int max_usage = READ_ONCE(pipe->max_usage); spd->nr_pages_max = max_usage; if (max_usage <= PIPE_DEF_BUFFERS) @@ -381,7 +381,7 @@ static ssize_t default_file_splice_read(struct file *in, loff_t *ppos, ssize_t res; int i; - if (pipe_full(pipe->head, pipe->tail, pipe->ring_size)) + if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) return -EAGAIN; /* @@ -698,7 +698,7 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, .pos = *ppos, .u.file = out, }; - int nbufs = pipe->ring_size; + int nbufs = pipe->max_usage; struct bio_vec *array = kcalloc(nbufs, sizeof(struct bio_vec), GFP_KERNEL); ssize_t ret; @@ -721,9 +721,9 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, if (ret <= 0) break; - if (unlikely(nbufs < pipe->ring_size)) { + if (unlikely(nbufs < pipe->max_usage)) { kfree(array); - nbufs = pipe->ring_size; + nbufs = pipe->max_usage; array = kcalloc(nbufs, sizeof(struct bio_vec), GFP_KERNEL); if (!array) { @@ -963,7 +963,7 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd, loff_t pos = sd->pos, prev_pos = pos; /* Don't try to read more the pipe has space for. */ - p_space = pipe->ring_size - + p_space = pipe->max_usage - pipe_occupancy(pipe->head, pipe->tail); read_len = min_t(size_t, len, p_space << PAGE_SHIFT); ret = do_splice_to(in, &pos, pipe, read_len, flags); @@ -1090,7 +1090,7 @@ static int wait_for_space(struct pipe_inode_info *pipe, unsigned flags) send_sig(SIGPIPE, current, 0); return -EPIPE; } - if (!pipe_full(pipe->head, pipe->tail, pipe->ring_size)) + if (!pipe_full(pipe->head, pipe->tail, pipe->max_usage)) return 0; if (flags & SPLICE_F_NONBLOCK) return -EAGAIN; @@ -1498,13 +1498,13 @@ static int opipe_prep(struct pipe_inode_info *pipe, unsigned int flags) * Check pipe occupancy without the inode lock first. This function * is speculative anyways, so missing one is ok. */ - if (pipe_full(pipe->head, pipe->tail, pipe->ring_size)) + if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) return 0; ret = 0; pipe_lock(pipe); - while (pipe_full(pipe->head, pipe->tail, pipe->ring_size)) { + while (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) { if (!pipe->readers) { send_sig(SIGPIPE, current, 0); ret = -EPIPE; @@ -1584,7 +1584,7 @@ retry: * pipe is empty or the output pipe is full. */ if (pipe_empty(i_head, i_tail) || - pipe_full(o_head, o_tail, opipe->ring_size)) { + pipe_full(o_head, o_tail, opipe->max_usage)) { /* Already processed some buffers, break */ if (ret) break; @@ -1706,7 +1706,7 @@ static int link_pipe(struct pipe_inode_info *ipipe, * output room, break. */ if (pipe_empty(i_head, i_tail) || - pipe_full(o_head, o_tail, opipe->ring_size)) + pipe_full(o_head, o_tail, opipe->max_usage)) break; ibuf = &ipipe->bufs[i_tail & i_mask]; diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 96158ca80456..44f2245debda 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -32,6 +32,7 @@ struct pipe_buffer { * @wait: reader/writer wait point in case of empty/full pipe * @head: The point of buffer production * @tail: The point of buffer consumption + * @max_usage: The maximum number of slots that may be used in the ring * @ring_size: total number of buffers (should be a power of 2) * @tmp_page: cached released page * @readers: number of current readers of this pipe @@ -50,6 +51,7 @@ struct pipe_inode_info { wait_queue_head_t wait; unsigned int head; unsigned int tail; + unsigned int max_usage; unsigned int ring_size; unsigned int readers; unsigned int writers; @@ -150,9 +152,11 @@ static inline unsigned int pipe_space_for_user(unsigned int head, unsigned int t unsigned int p_occupancy, p_space; p_occupancy = pipe_occupancy(head, tail); - if (p_occupancy >= pipe->ring_size) + if (p_occupancy >= pipe->max_usage) return 0; p_space = pipe->ring_size - p_occupancy; + if (p_space > pipe->max_usage) + p_space = pipe->max_usage; return p_space; } diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 957f8828378a..be2fc5793ddd 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -395,7 +395,7 @@ static size_t copy_page_to_iter_pipe(struct page *page, size_t offset, size_t by i_head++; buf = &pipe->bufs[i_head & p_mask]; } - if (pipe_full(i_head, p_tail, pipe->ring_size)) + if (pipe_full(i_head, p_tail, pipe->max_usage)) return 0; buf->ops = &page_cache_pipe_buf_ops; @@ -528,7 +528,7 @@ static size_t push_pipe(struct iov_iter *i, size_t size, pipe->bufs[iter_head & p_mask].len = PAGE_SIZE; iter_head++; } - while (!pipe_full(iter_head, p_tail, pipe->ring_size)) { + while (!pipe_full(iter_head, p_tail, pipe->max_usage)) { struct pipe_buffer *buf = &pipe->bufs[iter_head & p_mask]; struct page *page = alloc_page(GFP_USER); if (!page) -- cgit v1.2.3-71-gd317 From d41efb522e902364ab09c782d511c1bedc388ddd Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 4 Nov 2019 22:30:52 -0500 Subject: fs/namei.c: pull positivity check into follow_managed() There are 4 callers; two proceed to check if result is positive and fail with ENOENT if it isn't; one (in handle_lookup_down()) is guaranteed to yield positive and one (in lookup_fast()) is _preceded_ by positivity check. However, follow_managed() on a negative dentry is a (fairly cheap) no-op on anything other than autofs. And negative autofs dentries are never hashed, so lookup_fast() is not going to run into one of those. Moreover, successful follow_managed() on a _positive_ dentry never yields a negative one (and we significantly rely upon that in callers of lookup_fast()). In other words, we can easily transpose the positivity check and the call of follow_managed() in lookup_fast(). And that allows to fold the positivity check *into* follow_managed(), simplifying life for the code downstream of its calls. Signed-off-by: Al Viro --- fs/namei.c | 34 +++++++++++----------------------- include/linux/dcache.h | 5 +++++ 2 files changed, 16 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/fs/namei.c b/fs/namei.c index 671c3c1a3425..ef55155d152f 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1206,25 +1206,25 @@ static int follow_automount(struct path *path, struct nameidata *nd, * - Flagged as automount point * * This may only be called in refwalk mode. + * On success path->dentry is known positive. * * Serialization is taken care of in namespace.c */ static int follow_managed(struct path *path, struct nameidata *nd) { struct vfsmount *mnt = path->mnt; /* held by caller, must be left alone */ - unsigned managed; + unsigned flags; bool need_mntput = false; int ret = 0; /* Given that we're not holding a lock here, we retain the value in a * local variable for each dentry as we look at it so that we don't see * the components of that value change under us */ - while (managed = READ_ONCE(path->dentry->d_flags), - managed &= DCACHE_MANAGED_DENTRY, - unlikely(managed != 0)) { + while (flags = READ_ONCE(path->dentry->d_flags), + unlikely(flags & DCACHE_MANAGED_DENTRY)) { /* Allow the filesystem to manage the transit without i_mutex * being held. */ - if (managed & DCACHE_MANAGE_TRANSIT) { + if (flags & DCACHE_MANAGE_TRANSIT) { BUG_ON(!path->dentry->d_op); BUG_ON(!path->dentry->d_op->d_manage); ret = path->dentry->d_op->d_manage(path, false); @@ -1233,7 +1233,7 @@ static int follow_managed(struct path *path, struct nameidata *nd) } /* Transit to a mounted filesystem. */ - if (managed & DCACHE_MOUNTED) { + if (flags & DCACHE_MOUNTED) { struct vfsmount *mounted = lookup_mnt(path); if (mounted) { dput(path->dentry); @@ -1252,7 +1252,7 @@ static int follow_managed(struct path *path, struct nameidata *nd) } /* Handle an automount point */ - if (managed & DCACHE_NEED_AUTOMOUNT) { + if (flags & DCACHE_NEED_AUTOMOUNT) { ret = follow_automount(path, nd, &need_mntput); if (ret < 0) break; @@ -1265,10 +1265,12 @@ static int follow_managed(struct path *path, struct nameidata *nd) if (need_mntput && path->mnt == mnt) mntput(path->mnt); - if (ret == -EISDIR || !ret) - ret = 1; if (need_mntput) nd->flags |= LOOKUP_JUMPED; + if (ret == -EISDIR || !ret) + ret = 1; + if (ret > 0 && unlikely(d_flags_negative(flags))) + ret = -ENOENT; if (unlikely(ret < 0)) path_put_conditional(path, nd); return ret; @@ -1617,10 +1619,6 @@ static int lookup_fast(struct nameidata *nd, dput(dentry); return status; } - if (unlikely(d_is_negative(dentry))) { - dput(dentry); - return -ENOENT; - } path->mnt = mnt; path->dentry = dentry; @@ -1807,11 +1805,6 @@ static int walk_component(struct nameidata *nd, int flags) if (unlikely(err < 0)) return err; - if (unlikely(d_is_negative(path.dentry))) { - path_to_nameidata(&path, nd); - return -ENOENT; - } - seq = 0; /* we are already out of RCU mode */ inode = d_backing_inode(path.dentry); } @@ -3352,11 +3345,6 @@ static int do_last(struct nameidata *nd, if (unlikely(error < 0)) return error; - if (unlikely(d_is_negative(path.dentry))) { - path_to_nameidata(&path, nd); - return -ENOENT; - } - /* * create/update audit record if it already exists. */ diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 10090f11ab95..c1488cc84fd9 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -440,6 +440,11 @@ static inline bool d_is_negative(const struct dentry *dentry) return d_is_miss(dentry); } +static inline bool d_flags_negative(unsigned flags) +{ + return (flags & DCACHE_ENTRY_TYPE) == DCACHE_MISS_TYPE; +} + static inline bool d_is_positive(const struct dentry *dentry) { return !d_is_negative(dentry); -- cgit v1.2.3-71-gd317 From 6c2d4798a8d16cf4f3a28c3cd4af4f1dcbbb4d04 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 31 Oct 2019 01:21:58 -0400 Subject: new helper: lookup_positive_unlocked() Most of the callers of lookup_one_len_unlocked() treat negatives are ERR_PTR(-ENOENT). Provide a helper that would do just that. Note that a pinned positive dentry remains positive - it's ->d_inode is stable, etc.; a pinned _negative_ dentry can become positive at any point as long as you are not holding its parent at least shared. So using lookup_one_len_unlocked() needs to be careful; lookup_positive_unlocked() is safer and that's what the callers end up open-coding anyway. Signed-off-by: Al Viro --- fs/cifs/cifsfs.c | 7 +------ fs/debugfs/inode.c | 6 +----- fs/kernfs/mount.c | 2 +- fs/namei.c | 20 ++++++++++++++++++++ fs/nfsd/nfs3xdr.c | 4 +--- fs/nfsd/nfs4xdr.c | 11 +---------- fs/overlayfs/namei.c | 24 ++++++++---------------- fs/quota/dquot.c | 7 +------ include/linux/namei.h | 1 + 9 files changed, 35 insertions(+), 47 deletions(-) (limited to 'include/linux') diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index c049c7b3aa87..8c8600e53339 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -719,11 +719,6 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb) struct inode *dir = d_inode(dentry); struct dentry *child; - if (!dir) { - dput(dentry); - dentry = ERR_PTR(-ENOENT); - break; - } if (!S_ISDIR(dir->i_mode)) { dput(dentry); dentry = ERR_PTR(-ENOTDIR); @@ -740,7 +735,7 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb) while (*s && *s != sep) s++; - child = lookup_one_len_unlocked(p, dentry, s - p); + child = lookup_positive_unlocked(p, dentry, s - p); dput(dentry); dentry = child; } while (!IS_ERR(dentry)); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 7b975dbb2bb4..f4d8df5e4714 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -299,13 +299,9 @@ struct dentry *debugfs_lookup(const char *name, struct dentry *parent) if (!parent) parent = debugfs_mount->mnt_root; - dentry = lookup_one_len_unlocked(name, parent, strlen(name)); + dentry = lookup_positive_unlocked(name, parent, strlen(name)); if (IS_ERR(dentry)) return NULL; - if (!d_really_is_positive(dentry)) { - dput(dentry); - return NULL; - } return dentry; } EXPORT_SYMBOL_GPL(debugfs_lookup); diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index 6c12fac2c287..d62cec6d838d 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -200,7 +200,7 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, dput(dentry); return ERR_PTR(-EINVAL); } - dtmp = lookup_one_len_unlocked(kntmp->name, dentry, + dtmp = lookup_positive_unlocked(kntmp->name, dentry, strlen(kntmp->name)); dput(dentry); if (IS_ERR(dtmp)) diff --git a/fs/namei.c b/fs/namei.c index ef55155d152f..6f72fb7ef5ad 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2557,6 +2557,26 @@ struct dentry *lookup_one_len_unlocked(const char *name, } EXPORT_SYMBOL(lookup_one_len_unlocked); +/* + * Like lookup_one_len_unlocked(), except that it yields ERR_PTR(-ENOENT) + * on negatives. Returns known positive or ERR_PTR(); that's what + * most of the users want. Note that pinned negative with unlocked parent + * _can_ become positive at any time, so callers of lookup_one_len_unlocked() + * need to be very careful; pinned positives have ->d_inode stable, so + * this one avoids such problems. + */ +struct dentry *lookup_positive_unlocked(const char *name, + struct dentry *base, int len) +{ + struct dentry *ret = lookup_one_len_unlocked(name, base, len); + if (!IS_ERR(ret) && d_is_negative(ret)) { + dput(ret); + ret = ERR_PTR(-ENOENT); + } + return ret; +} +EXPORT_SYMBOL(lookup_positive_unlocked); + #ifdef CONFIG_UNIX98_PTYS int path_pts(struct path *path) { diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 86e5658651f1..195ab7a0fc89 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -863,13 +863,11 @@ compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp, } else dchild = dget(dparent); } else - dchild = lookup_one_len_unlocked(name, dparent, namlen); + dchild = lookup_positive_unlocked(name, dparent, namlen); if (IS_ERR(dchild)) return rv; if (d_mountpoint(dchild)) goto out; - if (d_really_is_negative(dchild)) - goto out; if (dchild->d_inode->i_ino != ino) goto out; rv = fh_compose(fhp, exp, dchild, &cd->fh); diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 533d0fc3c96b..b09237431ae2 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2991,18 +2991,9 @@ nfsd4_encode_dirent_fattr(struct xdr_stream *xdr, struct nfsd4_readdir *cd, __be32 nfserr; int ignore_crossmnt = 0; - dentry = lookup_one_len_unlocked(name, cd->rd_fhp->fh_dentry, namlen); + dentry = lookup_positive_unlocked(name, cd->rd_fhp->fh_dentry, namlen); if (IS_ERR(dentry)) return nfserrno(PTR_ERR(dentry)); - if (d_really_is_negative(dentry)) { - /* - * we're not holding the i_mutex here, so there's - * a window where this directory entry could have gone - * away. - */ - dput(dentry); - return nfserr_noent; - } exp_get(exp); /* diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index e9717c2f7d45..c269d6033525 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -200,7 +200,7 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d, int err; bool last_element = !post[0]; - this = lookup_one_len_unlocked(name, base, namelen); + this = lookup_positive_unlocked(name, base, namelen); if (IS_ERR(this)) { err = PTR_ERR(this); this = NULL; @@ -208,8 +208,6 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d, goto out; goto out_err; } - if (!this->d_inode) - goto put_and_out; if (ovl_dentry_weird(this)) { /* Don't support traversing automounts and other weirdness */ @@ -651,7 +649,7 @@ struct dentry *ovl_get_index_fh(struct ovl_fs *ofs, struct ovl_fh *fh) if (err) return ERR_PTR(err); - index = lookup_one_len_unlocked(name.name, ofs->indexdir, name.len); + index = lookup_positive_unlocked(name.name, ofs->indexdir, name.len); kfree(name.name); if (IS_ERR(index)) { if (PTR_ERR(index) == -ENOENT) @@ -659,9 +657,7 @@ struct dentry *ovl_get_index_fh(struct ovl_fs *ofs, struct ovl_fh *fh) return index; } - if (d_is_negative(index)) - err = 0; - else if (ovl_is_whiteout(index)) + if (ovl_is_whiteout(index)) err = -ESTALE; else if (ovl_dentry_weird(index)) err = -EIO; @@ -685,7 +681,7 @@ struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper, if (err) return ERR_PTR(err); - index = lookup_one_len_unlocked(name.name, ofs->indexdir, name.len); + index = lookup_positive_unlocked(name.name, ofs->indexdir, name.len); if (IS_ERR(index)) { err = PTR_ERR(index); if (err == -ENOENT) { @@ -700,9 +696,7 @@ struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper, } inode = d_inode(index); - if (d_is_negative(index)) { - goto out_dput; - } else if (ovl_is_whiteout(index) && !verify) { + if (ovl_is_whiteout(index) && !verify) { /* * When index lookup is called with !verify for decoding an * overlay file handle, a whiteout index implies that decode @@ -1131,7 +1125,7 @@ bool ovl_lower_positive(struct dentry *dentry) struct dentry *this; struct dentry *lowerdir = poe->lowerstack[i].dentry; - this = lookup_one_len_unlocked(name->name, lowerdir, + this = lookup_positive_unlocked(name->name, lowerdir, name->len); if (IS_ERR(this)) { switch (PTR_ERR(this)) { @@ -1148,10 +1142,8 @@ bool ovl_lower_positive(struct dentry *dentry) break; } } else { - if (this->d_inode) { - positive = !ovl_is_whiteout(this); - done = true; - } + positive = !ovl_is_whiteout(this); + done = true; dput(this); } } diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 6e826b454082..a37e1b117721 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2507,15 +2507,10 @@ int dquot_quota_on_mount(struct super_block *sb, char *qf_name, struct dentry *dentry; int error; - dentry = lookup_one_len_unlocked(qf_name, sb->s_root, strlen(qf_name)); + dentry = lookup_positive_unlocked(qf_name, sb->s_root, strlen(qf_name)); if (IS_ERR(dentry)) return PTR_ERR(dentry); - if (d_really_is_negative(dentry)) { - error = -ENOENT; - goto out; - } - error = security_quota_on(dentry); if (!error) error = vfs_load_quota_inode(d_inode(dentry), type, format_id, diff --git a/include/linux/namei.h b/include/linux/namei.h index 397a08ade6a2..7fe7b87a3ded 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -60,6 +60,7 @@ extern int kern_path_mountpoint(int, const char *, struct path *, unsigned int); extern struct dentry *try_lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int); +extern struct dentry *lookup_positive_unlocked(const char *, struct dentry *, int); extern int follow_down_one(struct path *); extern int follow_down(struct path *); -- cgit v1.2.3-71-gd317 From 9af433840b3f61ac30d569a85234ab8f210f813a Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Sat, 9 Nov 2019 22:16:33 +0100 Subject: i2c: remove helpers for ref-counting clients MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are no in-tree users of these helpers anymore, and there shouldn't. Most use cases went away once the driver model started to refcount for us. There have been users like the media subsystem, but they all switched to better refcounting methods meanwhile. Media did this in 2008. Last user (IPMI) left 2018. Remove this cruft. Signed-off-by: Wolfram Sang Reviewed-by: Niklas Söderlund Reviewed-by: Jean Delvare Tested-by: Luca Ceresoli Reviewed-by: Luca Ceresoli Reviewed-by: Geert Uytterhoeven --- drivers/i2c/i2c-core-base.c | 32 -------------------------------- include/linux/i2c.h | 3 --- 2 files changed, 35 deletions(-) (limited to 'include/linux') diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 6a5183cffdfc..b594cb81cdce 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -1743,38 +1743,6 @@ EXPORT_SYMBOL(i2c_del_driver); /* ------------------------------------------------------------------------- */ -/** - * i2c_use_client - increments the reference count of the i2c client structure - * @client: the client being referenced - * - * Each live reference to a client should be refcounted. The driver model does - * that automatically as part of driver binding, so that most drivers don't - * need to do this explicitly: they hold a reference until they're unbound - * from the device. - * - * A pointer to the client with the incremented reference counter is returned. - */ -struct i2c_client *i2c_use_client(struct i2c_client *client) -{ - if (client && get_device(&client->dev)) - return client; - return NULL; -} -EXPORT_SYMBOL(i2c_use_client); - -/** - * i2c_release_client - release a use of the i2c client structure - * @client: the client being no longer referenced - * - * Must be called when a user of a client is finished with it. - */ -void i2c_release_client(struct i2c_client *client) -{ - if (client) - put_device(&client->dev); -} -EXPORT_SYMBOL(i2c_release_client); - struct i2c_cmd_arg { unsigned cmd; void *arg; diff --git a/include/linux/i2c.h b/include/linux/i2c.h index aaf57d9b41db..88b825601f3d 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -850,9 +850,6 @@ extern void i2c_del_driver(struct i2c_driver *driver); #define i2c_add_driver(driver) \ i2c_register_driver(THIS_MODULE, driver) -extern struct i2c_client *i2c_use_client(struct i2c_client *client); -extern void i2c_release_client(struct i2c_client *client); - /* call the i2c_client->command() of all attached clients with * the given arguments */ extern void i2c_clients_command(struct i2c_adapter *adap, -- cgit v1.2.3-71-gd317 From b7b3fc8dd95bc02bd30680da258e09dda55270db Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Fri, 15 Nov 2019 13:37:22 +0100 Subject: bpf: Support doubleword alignment in bpf_jit_binary_alloc Currently passing alignment greater than 4 to bpf_jit_binary_alloc does not work: in such cases it silently aligns only to 4 bytes. On s390, in order to load a constant from memory in a large (>512k) BPF program, one must use lgrl instruction, whose memory operand must be aligned on an 8-byte boundary. This patch makes it possible to request 8-byte alignment from bpf_jit_binary_alloc, and also makes it issue a warning when an unsupported alignment is requested. Signed-off-by: Ilya Leoshkevich Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20191115123722.58462-1-iii@linux.ibm.com --- include/linux/filter.h | 6 ++++-- kernel/bpf/core.c | 4 ++++ 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 7a6f8f6f1da4..ad80e9c6111c 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -515,10 +515,12 @@ struct sock_fprog_kern { struct sock_filter *filter; }; +/* Some arches need doubleword alignment for their instructions and/or data */ +#define BPF_IMAGE_ALIGNMENT 8 + struct bpf_binary_header { u32 pages; - /* Some arches need word alignment for their instructions */ - u8 image[] __aligned(4); + u8 image[] __aligned(BPF_IMAGE_ALIGNMENT); }; struct bpf_prog { diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index c1fde0303280..99693f3c4e99 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -31,6 +31,7 @@ #include #include #include +#include #include /* Registers */ @@ -815,6 +816,9 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, struct bpf_binary_header *hdr; u32 size, hole, start, pages; + WARN_ON_ONCE(!is_power_of_2(alignment) || + alignment > BPF_IMAGE_ALIGNMENT); + /* Most of BPF filters are really small, but if some of them * fill a page, allow at least 128 extra bytes to insert a * random section of illegal instructions. -- cgit v1.2.3-71-gd317 From 5964b2000f283ff5df366f718e0f083ebbaae977 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 14 Nov 2019 10:57:03 -0800 Subject: bpf: Add bpf_arch_text_poke() helper Add bpf_arch_text_poke() helper that is used by BPF trampoline logic to patch nops/calls in kernel text into calls into BPF trampoline and to patch calls/nops inside BPF programs too. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Song Liu Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20191114185720.1641606-4-ast@kernel.org --- arch/x86/net/bpf_jit_comp.c | 51 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/bpf.h | 8 +++++++ kernel/bpf/core.c | 6 ++++++ 3 files changed, 65 insertions(+) (limited to 'include/linux') diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index fb99d976ad6e..254b2889e881 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -9,9 +9,11 @@ #include #include #include +#include #include #include #include +#include static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) { @@ -486,6 +488,55 @@ static int emit_call(u8 **pprog, void *func, void *ip) return 0; } +int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, + void *old_addr, void *new_addr) +{ + u8 old_insn[X86_CALL_SIZE] = {}; + u8 new_insn[X86_CALL_SIZE] = {}; + u8 *prog; + int ret; + + if (!is_kernel_text((long)ip)) + /* BPF trampoline in modules is not supported */ + return -EINVAL; + + if (old_addr) { + prog = old_insn; + ret = emit_call(&prog, old_addr, (void *)ip); + if (ret) + return ret; + } + if (new_addr) { + prog = new_insn; + ret = emit_call(&prog, new_addr, (void *)ip); + if (ret) + return ret; + } + ret = -EBUSY; + mutex_lock(&text_mutex); + switch (t) { + case BPF_MOD_NOP_TO_CALL: + if (memcmp(ip, ideal_nops[NOP_ATOMIC5], X86_CALL_SIZE)) + goto out; + text_poke_bp(ip, new_insn, X86_CALL_SIZE, NULL); + break; + case BPF_MOD_CALL_TO_CALL: + if (memcmp(ip, old_insn, X86_CALL_SIZE)) + goto out; + text_poke_bp(ip, new_insn, X86_CALL_SIZE, NULL); + break; + case BPF_MOD_CALL_TO_NOP: + if (memcmp(ip, old_insn, X86_CALL_SIZE)) + goto out; + text_poke_bp(ip, ideal_nops[NOP_ATOMIC5], X86_CALL_SIZE, NULL); + break; + } + ret = 0; +out: + mutex_unlock(&text_mutex); + return ret; +} + static bool ex_handler_bpf(const struct exception_table_entry *x, struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7c7f518811a6..8b90db25348a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1157,4 +1157,12 @@ static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, } #endif /* CONFIG_INET */ +enum bpf_text_poke_type { + BPF_MOD_NOP_TO_CALL, + BPF_MOD_CALL_TO_CALL, + BPF_MOD_CALL_TO_NOP, +}; +int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, + void *addr1, void *addr2); + #endif /* _LINUX_BPF_H */ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 99693f3c4e99..434a0d920153 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2144,6 +2144,12 @@ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to, return -EFAULT; } +int __weak bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, + void *addr1, void *addr2) +{ + return -ENOTSUPP; +} + DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key); EXPORT_SYMBOL(bpf_stats_enabled_key); -- cgit v1.2.3-71-gd317 From fec56f5890d93fc2ed74166c397dc186b1c25951 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 14 Nov 2019 10:57:04 -0800 Subject: bpf: Introduce BPF trampoline Introduce BPF trampoline concept to allow kernel code to call into BPF programs with practically zero overhead. The trampoline generation logic is architecture dependent. It's converting native calling convention into BPF calling convention. BPF ISA is 64-bit (even on 32-bit architectures). The registers R1 to R5 are used to pass arguments into BPF functions. The main BPF program accepts only single argument "ctx" in R1. Whereas CPU native calling convention is different. x86-64 is passing first 6 arguments in registers and the rest on the stack. x86-32 is passing first 3 arguments in registers. sparc64 is passing first 6 in registers. And so on. The trampolines between BPF and kernel already exist. BPF_CALL_x macros in include/linux/filter.h statically compile trampolines from BPF into kernel helpers. They convert up to five u64 arguments into kernel C pointers and integers. On 64-bit architectures this BPF_to_kernel trampolines are nops. On 32-bit architecture they're meaningful. The opposite job kernel_to_BPF trampolines is done by CAST_TO_U64 macros and __bpf_trace_##call() shim functions in include/trace/bpf_probe.h. They convert kernel function arguments into array of u64s that BPF program consumes via R1=ctx pointer. This patch set is doing the same job as __bpf_trace_##call() static trampolines, but dynamically for any kernel function. There are ~22k global kernel functions that are attachable via nop at function entry. The function arguments and types are described in BTF. The job of btf_distill_func_proto() function is to extract useful information from BTF into "function model" that architecture dependent trampoline generators will use to generate assembly code to cast kernel function arguments into array of u64s. For example the kernel function eth_type_trans has two pointers. They will be casted to u64 and stored into stack of generated trampoline. The pointer to that stack space will be passed into BPF program in R1. On x86-64 such generated trampoline will consume 16 bytes of stack and two stores of %rdi and %rsi into stack. The verifier will make sure that only two u64 are accessed read-only by BPF program. The verifier will also recognize the precise type of the pointers being accessed and will not allow typecasting of the pointer to a different type within BPF program. The tracing use case in the datacenter demonstrated that certain key kernel functions have (like tcp_retransmit_skb) have 2 or more kprobes that are always active. Other functions have both kprobe and kretprobe. So it is essential to keep both kernel code and BPF programs executing at maximum speed. Hence generated BPF trampoline is re-generated every time new program is attached or detached to maintain maximum performance. To avoid the high cost of retpoline the attached BPF programs are called directly. __bpf_prog_enter/exit() are used to support per-program execution stats. In the future this logic will be optimized further by adding support for bpf_stats_enabled_key inside generated assembly code. Introduction of preemptible and sleepable BPF programs will completely remove the need to call to __bpf_prog_enter/exit(). Detach of a BPF program from the trampoline should not fail. To avoid memory allocation in detach path the half of the page is used as a reserve and flipped after each attach/detach. 2k bytes is enough to call 40+ BPF programs directly which is enough for BPF tracing use cases. This limit can be increased in the future. BPF_TRACE_FENTRY programs have access to raw kernel function arguments while BPF_TRACE_FEXIT programs have access to kernel return value as well. Often kprobe BPF program remembers function arguments in a map while kretprobe fetches arguments from a map and analyzes them together with return value. BPF_TRACE_FEXIT accelerates this typical use case. Recursion prevention for kprobe BPF programs is done via per-cpu bpf_prog_active counter. In practice that turned out to be a mistake. It caused programs to randomly skip execution. The tracing tools missed results they were looking for. Hence BPF trampoline doesn't provide builtin recursion prevention. It's a job of BPF program itself and will be addressed in the follow up patches. BPF trampoline is intended to be used beyond tracing and fentry/fexit use cases in the future. For example to remove retpoline cost from XDP programs. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20191114185720.1641606-5-ast@kernel.org --- arch/x86/net/bpf_jit_comp.c | 211 +++++++++++++++++++++++++++++++++++- include/linux/bpf.h | 105 ++++++++++++++++++ include/uapi/linux/bpf.h | 2 + kernel/bpf/Makefile | 1 + kernel/bpf/btf.c | 77 +++++++++++++- kernel/bpf/core.c | 1 + kernel/bpf/syscall.c | 53 +++++++++- kernel/bpf/trampoline.c | 253 ++++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/verifier.c | 42 ++++++++ 9 files changed, 735 insertions(+), 10 deletions(-) create mode 100644 kernel/bpf/trampoline.c (limited to 'include/linux') diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 254b2889e881..be2b43a894f6 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -98,6 +98,7 @@ static int bpf_size_to_x86_bytes(int bpf_size) /* Pick a register outside of BPF range for JIT internal work */ #define AUX_REG (MAX_BPF_JIT_REG + 1) +#define X86_REG_R9 (MAX_BPF_JIT_REG + 2) /* * The following table maps BPF registers to x86-64 registers. @@ -106,8 +107,8 @@ static int bpf_size_to_x86_bytes(int bpf_size) * register in load/store instructions, it always needs an * extra byte of encoding and is callee saved. * - * Also x86-64 register R9 is unused. x86-64 register R10 is - * used for blinding (if enabled). + * x86-64 register R9 is not used by BPF programs, but can be used by BPF + * trampoline. x86-64 register R10 is used for blinding (if enabled). */ static const int reg2hex[] = { [BPF_REG_0] = 0, /* RAX */ @@ -123,6 +124,7 @@ static const int reg2hex[] = { [BPF_REG_FP] = 5, /* RBP readonly */ [BPF_REG_AX] = 2, /* R10 temp register */ [AUX_REG] = 3, /* R11 temp register */ + [X86_REG_R9] = 1, /* R9 register, 6th function argument */ }; static const int reg2pt_regs[] = { @@ -150,6 +152,7 @@ static bool is_ereg(u32 reg) BIT(BPF_REG_7) | BIT(BPF_REG_8) | BIT(BPF_REG_9) | + BIT(X86_REG_R9) | BIT(BPF_REG_AX)); } @@ -1233,6 +1236,210 @@ emit_jmp: return proglen; } +static void save_regs(struct btf_func_model *m, u8 **prog, int nr_args, + int stack_size) +{ + int i; + /* Store function arguments to stack. + * For a function that accepts two pointers the sequence will be: + * mov QWORD PTR [rbp-0x10],rdi + * mov QWORD PTR [rbp-0x8],rsi + */ + for (i = 0; i < min(nr_args, 6); i++) + emit_stx(prog, bytes_to_bpf_size(m->arg_size[i]), + BPF_REG_FP, + i == 5 ? X86_REG_R9 : BPF_REG_1 + i, + -(stack_size - i * 8)); +} + +static void restore_regs(struct btf_func_model *m, u8 **prog, int nr_args, + int stack_size) +{ + int i; + + /* Restore function arguments from stack. + * For a function that accepts two pointers the sequence will be: + * EMIT4(0x48, 0x8B, 0x7D, 0xF0); mov rdi,QWORD PTR [rbp-0x10] + * EMIT4(0x48, 0x8B, 0x75, 0xF8); mov rsi,QWORD PTR [rbp-0x8] + */ + for (i = 0; i < min(nr_args, 6); i++) + emit_ldx(prog, bytes_to_bpf_size(m->arg_size[i]), + i == 5 ? X86_REG_R9 : BPF_REG_1 + i, + BPF_REG_FP, + -(stack_size - i * 8)); +} + +static int invoke_bpf(struct btf_func_model *m, u8 **pprog, + struct bpf_prog **progs, int prog_cnt, int stack_size) +{ + u8 *prog = *pprog; + int cnt = 0, i; + + for (i = 0; i < prog_cnt; i++) { + if (emit_call(&prog, __bpf_prog_enter, prog)) + return -EINVAL; + /* remember prog start time returned by __bpf_prog_enter */ + emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0); + + /* arg1: lea rdi, [rbp - stack_size] */ + EMIT4(0x48, 0x8D, 0x7D, -stack_size); + /* arg2: progs[i]->insnsi for interpreter */ + if (!progs[i]->jited) + emit_mov_imm64(&prog, BPF_REG_2, + (long) progs[i]->insnsi >> 32, + (u32) (long) progs[i]->insnsi); + /* call JITed bpf program or interpreter */ + if (emit_call(&prog, progs[i]->bpf_func, prog)) + return -EINVAL; + + /* arg1: mov rdi, progs[i] */ + emit_mov_imm64(&prog, BPF_REG_1, (long) progs[i] >> 32, + (u32) (long) progs[i]); + /* arg2: mov rsi, rbx <- start time in nsec */ + emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6); + if (emit_call(&prog, __bpf_prog_exit, prog)) + return -EINVAL; + } + *pprog = prog; + return 0; +} + +/* Example: + * __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); + * its 'struct btf_func_model' will be nr_args=2 + * The assembly code when eth_type_trans is executing after trampoline: + * + * push rbp + * mov rbp, rsp + * sub rsp, 16 // space for skb and dev + * push rbx // temp regs to pass start time + * mov qword ptr [rbp - 16], rdi // save skb pointer to stack + * mov qword ptr [rbp - 8], rsi // save dev pointer to stack + * call __bpf_prog_enter // rcu_read_lock and preempt_disable + * mov rbx, rax // remember start time in bpf stats are enabled + * lea rdi, [rbp - 16] // R1==ctx of bpf prog + * call addr_of_jited_FENTRY_prog + * movabsq rdi, 64bit_addr_of_struct_bpf_prog // unused if bpf stats are off + * mov rsi, rbx // prog start time + * call __bpf_prog_exit // rcu_read_unlock, preempt_enable and stats math + * mov rdi, qword ptr [rbp - 16] // restore skb pointer from stack + * mov rsi, qword ptr [rbp - 8] // restore dev pointer from stack + * pop rbx + * leave + * ret + * + * eth_type_trans has 5 byte nop at the beginning. These 5 bytes will be + * replaced with 'call generated_bpf_trampoline'. When it returns + * eth_type_trans will continue executing with original skb and dev pointers. + * + * The assembly code when eth_type_trans is called from trampoline: + * + * push rbp + * mov rbp, rsp + * sub rsp, 24 // space for skb, dev, return value + * push rbx // temp regs to pass start time + * mov qword ptr [rbp - 24], rdi // save skb pointer to stack + * mov qword ptr [rbp - 16], rsi // save dev pointer to stack + * call __bpf_prog_enter // rcu_read_lock and preempt_disable + * mov rbx, rax // remember start time if bpf stats are enabled + * lea rdi, [rbp - 24] // R1==ctx of bpf prog + * call addr_of_jited_FENTRY_prog // bpf prog can access skb and dev + * movabsq rdi, 64bit_addr_of_struct_bpf_prog // unused if bpf stats are off + * mov rsi, rbx // prog start time + * call __bpf_prog_exit // rcu_read_unlock, preempt_enable and stats math + * mov rdi, qword ptr [rbp - 24] // restore skb pointer from stack + * mov rsi, qword ptr [rbp - 16] // restore dev pointer from stack + * call eth_type_trans+5 // execute body of eth_type_trans + * mov qword ptr [rbp - 8], rax // save return value + * call __bpf_prog_enter // rcu_read_lock and preempt_disable + * mov rbx, rax // remember start time in bpf stats are enabled + * lea rdi, [rbp - 24] // R1==ctx of bpf prog + * call addr_of_jited_FEXIT_prog // bpf prog can access skb, dev, return value + * movabsq rdi, 64bit_addr_of_struct_bpf_prog // unused if bpf stats are off + * mov rsi, rbx // prog start time + * call __bpf_prog_exit // rcu_read_unlock, preempt_enable and stats math + * mov rax, qword ptr [rbp - 8] // restore eth_type_trans's return value + * pop rbx + * leave + * add rsp, 8 // skip eth_type_trans's frame + * ret // return to its caller + */ +int arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags, + struct bpf_prog **fentry_progs, int fentry_cnt, + struct bpf_prog **fexit_progs, int fexit_cnt, + void *orig_call) +{ + int cnt = 0, nr_args = m->nr_args; + int stack_size = nr_args * 8; + u8 *prog; + + /* x86-64 supports up to 6 arguments. 7+ can be added in the future */ + if (nr_args > 6) + return -ENOTSUPP; + + if ((flags & BPF_TRAMP_F_RESTORE_REGS) && + (flags & BPF_TRAMP_F_SKIP_FRAME)) + return -EINVAL; + + if (flags & BPF_TRAMP_F_CALL_ORIG) + stack_size += 8; /* room for return value of orig_call */ + + if (flags & BPF_TRAMP_F_SKIP_FRAME) + /* skip patched call instruction and point orig_call to actual + * body of the kernel function. + */ + orig_call += X86_CALL_SIZE; + + prog = image; + + EMIT1(0x55); /* push rbp */ + EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */ + EMIT4(0x48, 0x83, 0xEC, stack_size); /* sub rsp, stack_size */ + EMIT1(0x53); /* push rbx */ + + save_regs(m, &prog, nr_args, stack_size); + + if (fentry_cnt) + if (invoke_bpf(m, &prog, fentry_progs, fentry_cnt, stack_size)) + return -EINVAL; + + if (flags & BPF_TRAMP_F_CALL_ORIG) { + if (fentry_cnt) + restore_regs(m, &prog, nr_args, stack_size); + + /* call original function */ + if (emit_call(&prog, orig_call, prog)) + return -EINVAL; + /* remember return value in a stack for bpf prog to access */ + emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); + } + + if (fexit_cnt) + if (invoke_bpf(m, &prog, fexit_progs, fexit_cnt, stack_size)) + return -EINVAL; + + if (flags & BPF_TRAMP_F_RESTORE_REGS) + restore_regs(m, &prog, nr_args, stack_size); + + if (flags & BPF_TRAMP_F_CALL_ORIG) + /* restore original return value back into RAX */ + emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8); + + EMIT1(0x5B); /* pop rbx */ + EMIT1(0xC9); /* leave */ + if (flags & BPF_TRAMP_F_SKIP_FRAME) + /* skip our return address and return to parent */ + EMIT4(0x48, 0x83, 0xC4, 8); /* add rsp, 8 */ + EMIT1(0xC3); /* ret */ + /* One half of the page has active running trampoline. + * Another half is an area for next trampoline. + * Make sure the trampoline generation logic doesn't overflow. + */ + if (WARN_ON_ONCE(prog - (u8 *)image > PAGE_SIZE / 2 - BPF_INSN_SAFETY)) + return -EFAULT; + return 0; +} + struct x64_jit_data { struct bpf_binary_header *header; int *addrs; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8b90db25348a..0d4c5c224d79 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -14,6 +14,8 @@ #include #include #include +#include +#include struct bpf_verifier_env; struct bpf_verifier_log; @@ -384,6 +386,100 @@ struct bpf_prog_stats { struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); +struct btf_func_model { + u8 ret_size; + u8 nr_args; + u8 arg_size[MAX_BPF_FUNC_ARGS]; +}; + +/* Restore arguments before returning from trampoline to let original function + * continue executing. This flag is used for fentry progs when there are no + * fexit progs. + */ +#define BPF_TRAMP_F_RESTORE_REGS BIT(0) +/* Call original function after fentry progs, but before fexit progs. + * Makes sense for fentry/fexit, normal calls and indirect calls. + */ +#define BPF_TRAMP_F_CALL_ORIG BIT(1) +/* Skip current frame and return to parent. Makes sense for fentry/fexit + * programs only. Should not be used with normal calls and indirect calls. + */ +#define BPF_TRAMP_F_SKIP_FRAME BIT(2) + +/* Different use cases for BPF trampoline: + * 1. replace nop at the function entry (kprobe equivalent) + * flags = BPF_TRAMP_F_RESTORE_REGS + * fentry = a set of programs to run before returning from trampoline + * + * 2. replace nop at the function entry (kprobe + kretprobe equivalent) + * flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME + * orig_call = fentry_ip + MCOUNT_INSN_SIZE + * fentry = a set of program to run before calling original function + * fexit = a set of program to run after original function + * + * 3. replace direct call instruction anywhere in the function body + * or assign a function pointer for indirect call (like tcp_congestion_ops->cong_avoid) + * With flags = 0 + * fentry = a set of programs to run before returning from trampoline + * With flags = BPF_TRAMP_F_CALL_ORIG + * orig_call = original callback addr or direct function addr + * fentry = a set of program to run before calling original function + * fexit = a set of program to run after original function + */ +int arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags, + struct bpf_prog **fentry_progs, int fentry_cnt, + struct bpf_prog **fexit_progs, int fexit_cnt, + void *orig_call); +/* these two functions are called from generated trampoline */ +u64 notrace __bpf_prog_enter(void); +void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); + +enum bpf_tramp_prog_type { + BPF_TRAMP_FENTRY, + BPF_TRAMP_FEXIT, + BPF_TRAMP_MAX +}; + +struct bpf_trampoline { + /* hlist for trampoline_table */ + struct hlist_node hlist; + /* serializes access to fields of this trampoline */ + struct mutex mutex; + refcount_t refcnt; + u64 key; + struct { + struct btf_func_model model; + void *addr; + } func; + /* list of BPF programs using this trampoline */ + struct hlist_head progs_hlist[BPF_TRAMP_MAX]; + /* Number of attached programs. A counter per kind. */ + int progs_cnt[BPF_TRAMP_MAX]; + /* Executable image of trampoline */ + void *image; + u64 selector; +}; +#ifdef CONFIG_BPF_JIT +struct bpf_trampoline *bpf_trampoline_lookup(u64 key); +int bpf_trampoline_link_prog(struct bpf_prog *prog); +int bpf_trampoline_unlink_prog(struct bpf_prog *prog); +void bpf_trampoline_put(struct bpf_trampoline *tr); +#else +static inline struct bpf_trampoline *bpf_trampoline_lookup(u64 key) +{ + return NULL; +} +static inline int bpf_trampoline_link_prog(struct bpf_prog *prog) +{ + return -ENOTSUPP; +} +static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog) +{ + return -ENOTSUPP; +} +static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {} +#endif + struct bpf_prog_aux { atomic_t refcnt; u32 used_map_cnt; @@ -398,6 +494,9 @@ struct bpf_prog_aux { bool verifier_zext; /* Zero extensions has been inserted by verifier. */ bool offload_requested; bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ + enum bpf_tramp_prog_type trampoline_prog_type; + struct bpf_trampoline *trampoline; + struct hlist_node tramp_hlist; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; /* function name for valid attach_btf_id */ @@ -784,6 +883,12 @@ int btf_struct_access(struct bpf_verifier_log *log, u32 *next_btf_id); u32 btf_resolve_helper_id(struct bpf_verifier_log *log, void *, int); +int btf_distill_func_proto(struct bpf_verifier_log *log, + struct btf *btf, + const struct btf_type *func_proto, + const char *func_name, + struct btf_func_model *m); + #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index df6809a76404..69c200e6e696 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -201,6 +201,8 @@ enum bpf_attach_type { BPF_CGROUP_GETSOCKOPT, BPF_CGROUP_SETSOCKOPT, BPF_TRACE_RAW_TP, + BPF_TRACE_FENTRY, + BPF_TRACE_FEXIT, __MAX_BPF_ATTACH_TYPE }; diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index e1d9adb212f9..3f671bf617e8 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -6,6 +6,7 @@ obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o obj-$(CONFIG_BPF_SYSCALL) += disasm.o +obj-$(CONFIG_BPF_JIT) += trampoline.o obj-$(CONFIG_BPF_SYSCALL) += btf.o ifeq ($(CONFIG_NET),y) obj-$(CONFIG_BPF_SYSCALL) += devmap.o diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 4639c4ba9a9b..9e1164e5b429 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3517,13 +3517,18 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, args++; nr_args--; } - if (arg >= nr_args) { + + if (prog->expected_attach_type == BPF_TRACE_FEXIT && + arg == nr_args) { + /* function return type */ + t = btf_type_by_id(btf_vmlinux, t->type); + } else if (arg >= nr_args) { bpf_log(log, "func '%s' doesn't have %d-th argument\n", - tname, arg); + tname, arg + 1); return false; + } else { + t = btf_type_by_id(btf_vmlinux, args[arg].type); } - - t = btf_type_by_id(btf_vmlinux, args[arg].type); /* skip modifiers */ while (btf_type_is_modifier(t)) t = btf_type_by_id(btf_vmlinux, t->type); @@ -3784,6 +3789,70 @@ u32 btf_resolve_helper_id(struct bpf_verifier_log *log, void *fn, int arg) return btf_id; } +static int __get_type_size(struct btf *btf, u32 btf_id, + const struct btf_type **bad_type) +{ + const struct btf_type *t; + + if (!btf_id) + /* void */ + return 0; + t = btf_type_by_id(btf, btf_id); + while (t && btf_type_is_modifier(t)) + t = btf_type_by_id(btf, t->type); + if (!t) + return -EINVAL; + if (btf_type_is_ptr(t)) + /* kernel size of pointer. Not BPF's size of pointer*/ + return sizeof(void *); + if (btf_type_is_int(t) || btf_type_is_enum(t)) + return t->size; + *bad_type = t; + return -EINVAL; +} + +int btf_distill_func_proto(struct bpf_verifier_log *log, + struct btf *btf, + const struct btf_type *func, + const char *tname, + struct btf_func_model *m) +{ + const struct btf_param *args; + const struct btf_type *t; + u32 i, nargs; + int ret; + + args = (const struct btf_param *)(func + 1); + nargs = btf_type_vlen(func); + if (nargs >= MAX_BPF_FUNC_ARGS) { + bpf_log(log, + "The function %s has %d arguments. Too many.\n", + tname, nargs); + return -EINVAL; + } + ret = __get_type_size(btf, func->type, &t); + if (ret < 0) { + bpf_log(log, + "The function %s return type %s is unsupported.\n", + tname, btf_kind_str[BTF_INFO_KIND(t->info)]); + return -EINVAL; + } + m->ret_size = ret; + + for (i = 0; i < nargs; i++) { + ret = __get_type_size(btf, args[i].type, &t); + if (ret < 0) { + bpf_log(log, + "The function %s arg%d type %s is unsupported.\n", + tname, i, btf_kind_str[BTF_INFO_KIND(t->info)]); + return -EINVAL; + } + m->arg_size[i] = ret; + } + m->nr_args = nargs; + return 0; +} + void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, struct seq_file *m) { diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 434a0d920153..da5a8b8e278f 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2015,6 +2015,7 @@ static void bpf_prog_free_deferred(struct work_struct *work) if (aux->prog->has_callchain_buf) put_callchain_buffers(); #endif + bpf_trampoline_put(aux->trampoline); for (i = 0; i < aux->func_cnt; i++) bpf_jit_free(aux->func[i]); if (aux->func_cnt) { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 6d9ce95e5a8d..e2e37bea86bc 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1799,6 +1799,49 @@ static int bpf_obj_get(const union bpf_attr *attr) attr->file_flags); } +static int bpf_tracing_prog_release(struct inode *inode, struct file *filp) +{ + struct bpf_prog *prog = filp->private_data; + + WARN_ON_ONCE(bpf_trampoline_unlink_prog(prog)); + bpf_prog_put(prog); + return 0; +} + +static const struct file_operations bpf_tracing_prog_fops = { + .release = bpf_tracing_prog_release, + .read = bpf_dummy_read, + .write = bpf_dummy_write, +}; + +static int bpf_tracing_prog_attach(struct bpf_prog *prog) +{ + int tr_fd, err; + + if (prog->expected_attach_type != BPF_TRACE_FENTRY && + prog->expected_attach_type != BPF_TRACE_FEXIT) { + err = -EINVAL; + goto out_put_prog; + } + + err = bpf_trampoline_link_prog(prog); + if (err) + goto out_put_prog; + + tr_fd = anon_inode_getfd("bpf-tracing-prog", &bpf_tracing_prog_fops, + prog, O_CLOEXEC); + if (tr_fd < 0) { + WARN_ON_ONCE(bpf_trampoline_unlink_prog(prog)); + err = tr_fd; + goto out_put_prog; + } + return tr_fd; + +out_put_prog: + bpf_prog_put(prog); + return err; +} + struct bpf_raw_tracepoint { struct bpf_raw_event_map *btp; struct bpf_prog *prog; @@ -1850,14 +1893,16 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) if (prog->type == BPF_PROG_TYPE_TRACING) { if (attr->raw_tracepoint.name) { - /* raw_tp name should not be specified in raw_tp - * programs that were verified via in-kernel BTF info + /* The attach point for this category of programs + * should be specified via btf_id during program load. */ err = -EINVAL; goto out_put_prog; } - /* raw_tp name is taken from type name instead */ - tp_name = prog->aux->attach_func_name; + if (prog->expected_attach_type == BPF_TRACE_RAW_TP) + tp_name = prog->aux->attach_func_name; + else + return bpf_tracing_prog_attach(prog); } else { if (strncpy_from_user(buf, u64_to_user_ptr(attr->raw_tracepoint.name), diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c new file mode 100644 index 000000000000..10ae59d65f13 --- /dev/null +++ b/kernel/bpf/trampoline.c @@ -0,0 +1,253 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2019 Facebook */ +#include +#include +#include + +/* btf_vmlinux has ~22k attachable functions. 1k htab is enough. */ +#define TRAMPOLINE_HASH_BITS 10 +#define TRAMPOLINE_TABLE_SIZE (1 << TRAMPOLINE_HASH_BITS) + +static struct hlist_head trampoline_table[TRAMPOLINE_TABLE_SIZE]; + +/* serializes access to trampoline_table */ +static DEFINE_MUTEX(trampoline_mutex); + +struct bpf_trampoline *bpf_trampoline_lookup(u64 key) +{ + struct bpf_trampoline *tr; + struct hlist_head *head; + void *image; + int i; + + mutex_lock(&trampoline_mutex); + head = &trampoline_table[hash_64(key, TRAMPOLINE_HASH_BITS)]; + hlist_for_each_entry(tr, head, hlist) { + if (tr->key == key) { + refcount_inc(&tr->refcnt); + goto out; + } + } + tr = kzalloc(sizeof(*tr), GFP_KERNEL); + if (!tr) + goto out; + + /* is_root was checked earlier. No need for bpf_jit_charge_modmem() */ + image = bpf_jit_alloc_exec(PAGE_SIZE); + if (!image) { + kfree(tr); + tr = NULL; + goto out; + } + + tr->key = key; + INIT_HLIST_NODE(&tr->hlist); + hlist_add_head(&tr->hlist, head); + refcount_set(&tr->refcnt, 1); + mutex_init(&tr->mutex); + for (i = 0; i < BPF_TRAMP_MAX; i++) + INIT_HLIST_HEAD(&tr->progs_hlist[i]); + + set_vm_flush_reset_perms(image); + /* Keep image as writeable. The alternative is to keep flipping ro/rw + * everytime new program is attached or detached. + */ + set_memory_x((long)image, 1); + tr->image = image; +out: + mutex_unlock(&trampoline_mutex); + return tr; +} + +/* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 + * bytes on x86. Pick a number to fit into PAGE_SIZE / 2 + */ +#define BPF_MAX_TRAMP_PROGS 40 + +static int bpf_trampoline_update(struct bpf_trampoline *tr) +{ + void *old_image = tr->image + ((tr->selector + 1) & 1) * PAGE_SIZE/2; + void *new_image = tr->image + (tr->selector & 1) * PAGE_SIZE/2; + struct bpf_prog *progs_to_run[BPF_MAX_TRAMP_PROGS]; + int fentry_cnt = tr->progs_cnt[BPF_TRAMP_FENTRY]; + int fexit_cnt = tr->progs_cnt[BPF_TRAMP_FEXIT]; + struct bpf_prog **progs, **fentry, **fexit; + u32 flags = BPF_TRAMP_F_RESTORE_REGS; + struct bpf_prog_aux *aux; + int err; + + if (fentry_cnt + fexit_cnt == 0) { + err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL_TO_NOP, + old_image, NULL); + tr->selector = 0; + goto out; + } + + /* populate fentry progs */ + fentry = progs = progs_to_run; + hlist_for_each_entry(aux, &tr->progs_hlist[BPF_TRAMP_FENTRY], tramp_hlist) + *progs++ = aux->prog; + + /* populate fexit progs */ + fexit = progs; + hlist_for_each_entry(aux, &tr->progs_hlist[BPF_TRAMP_FEXIT], tramp_hlist) + *progs++ = aux->prog; + + if (fexit_cnt) + flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME; + + err = arch_prepare_bpf_trampoline(new_image, &tr->func.model, flags, + fentry, fentry_cnt, + fexit, fexit_cnt, + tr->func.addr); + if (err) + goto out; + + if (tr->selector) + /* progs already running at this address */ + err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL_TO_CALL, + old_image, new_image); + else + /* first time registering */ + err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_NOP_TO_CALL, + NULL, new_image); + if (err) + goto out; + tr->selector++; +out: + return err; +} + +static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(enum bpf_attach_type t) +{ + switch (t) { + case BPF_TRACE_FENTRY: + return BPF_TRAMP_FENTRY; + default: + return BPF_TRAMP_FEXIT; + } +} + +int bpf_trampoline_link_prog(struct bpf_prog *prog) +{ + enum bpf_tramp_prog_type kind; + struct bpf_trampoline *tr; + int err = 0; + + tr = prog->aux->trampoline; + kind = bpf_attach_type_to_tramp(prog->expected_attach_type); + mutex_lock(&tr->mutex); + if (tr->progs_cnt[BPF_TRAMP_FENTRY] + tr->progs_cnt[BPF_TRAMP_FEXIT] + >= BPF_MAX_TRAMP_PROGS) { + err = -E2BIG; + goto out; + } + if (!hlist_unhashed(&prog->aux->tramp_hlist)) { + /* prog already linked */ + err = -EBUSY; + goto out; + } + hlist_add_head(&prog->aux->tramp_hlist, &tr->progs_hlist[kind]); + tr->progs_cnt[kind]++; + err = bpf_trampoline_update(prog->aux->trampoline); + if (err) { + hlist_del(&prog->aux->tramp_hlist); + tr->progs_cnt[kind]--; + } +out: + mutex_unlock(&tr->mutex); + return err; +} + +/* bpf_trampoline_unlink_prog() should never fail. */ +int bpf_trampoline_unlink_prog(struct bpf_prog *prog) +{ + enum bpf_tramp_prog_type kind; + struct bpf_trampoline *tr; + int err; + + tr = prog->aux->trampoline; + kind = bpf_attach_type_to_tramp(prog->expected_attach_type); + mutex_lock(&tr->mutex); + hlist_del(&prog->aux->tramp_hlist); + tr->progs_cnt[kind]--; + err = bpf_trampoline_update(prog->aux->trampoline); + mutex_unlock(&tr->mutex); + return err; +} + +void bpf_trampoline_put(struct bpf_trampoline *tr) +{ + if (!tr) + return; + mutex_lock(&trampoline_mutex); + if (!refcount_dec_and_test(&tr->refcnt)) + goto out; + WARN_ON_ONCE(mutex_is_locked(&tr->mutex)); + if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FENTRY]))) + goto out; + if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FEXIT]))) + goto out; + bpf_jit_free_exec(tr->image); + hlist_del(&tr->hlist); + kfree(tr); +out: + mutex_unlock(&trampoline_mutex); +} + +/* The logic is similar to BPF_PROG_RUN, but with explicit rcu and preempt that + * are needed for trampoline. The macro is split into + * call _bpf_prog_enter + * call prog->bpf_func + * call __bpf_prog_exit + */ +u64 notrace __bpf_prog_enter(void) +{ + u64 start = 0; + + rcu_read_lock(); + preempt_disable(); + if (static_branch_unlikely(&bpf_stats_enabled_key)) + start = sched_clock(); + return start; +} + +void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start) +{ + struct bpf_prog_stats *stats; + + if (static_branch_unlikely(&bpf_stats_enabled_key) && + /* static_key could be enabled in __bpf_prog_enter + * and disabled in __bpf_prog_exit. + * And vice versa. + * Hence check that 'start' is not zero. + */ + start) { + stats = this_cpu_ptr(prog->aux->stats); + u64_stats_update_begin(&stats->syncp); + stats->cnt++; + stats->nsecs += sched_clock() - start; + u64_stats_update_end(&stats->syncp); + } + preempt_enable(); + rcu_read_unlock(); +} + +int __weak +arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags, + struct bpf_prog **fentry_progs, int fentry_cnt, + struct bpf_prog **fexit_progs, int fexit_cnt, + void *orig_call) +{ + return -ENOTSUPP; +} + +static int __init init_trampolines(void) +{ + int i; + + for (i = 0; i < TRAMPOLINE_TABLE_SIZE; i++) + INIT_HLIST_HEAD(&trampoline_table[i]); + return 0; +} +late_initcall(init_trampolines); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 2f2374967b36..8f89cfa93e88 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -9382,8 +9382,11 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) struct bpf_prog *prog = env->prog; u32 btf_id = prog->aux->attach_btf_id; const char prefix[] = "btf_trace_"; + struct bpf_trampoline *tr; const struct btf_type *t; const char *tname; + int ret = 0; + long addr; if (prog->type != BPF_PROG_TYPE_TRACING) return 0; @@ -9432,6 +9435,45 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) prog->aux->attach_func_proto = t; prog->aux->attach_btf_trace = true; return 0; + case BPF_TRACE_FENTRY: + case BPF_TRACE_FEXIT: + if (!btf_type_is_func(t)) { + verbose(env, "attach_btf_id %u is not a function\n", + btf_id); + return -EINVAL; + } + t = btf_type_by_id(btf_vmlinux, t->type); + if (!btf_type_is_func_proto(t)) + return -EINVAL; + tr = bpf_trampoline_lookup(btf_id); + if (!tr) + return -ENOMEM; + prog->aux->attach_func_name = tname; + prog->aux->attach_func_proto = t; + mutex_lock(&tr->mutex); + if (tr->func.addr) { + prog->aux->trampoline = tr; + goto out; + } + ret = btf_distill_func_proto(&env->log, btf_vmlinux, t, + tname, &tr->func.model); + if (ret < 0) + goto out; + addr = kallsyms_lookup_name(tname); + if (!addr) { + verbose(env, + "The address of function %s cannot be found\n", + tname); + ret = -ENOENT; + goto out; + } + tr->func.addr = (void *)addr; + prog->aux->trampoline = tr; +out: + mutex_unlock(&tr->mutex); + if (ret) + bpf_trampoline_put(tr); + return ret; default: return -EINVAL; } -- cgit v1.2.3-71-gd317 From 9cc31b3a092d9bf2a18f09ad77e727ddb42a5b1e Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 14 Nov 2019 10:57:14 -0800 Subject: bpf: Fix race in btf_resolve_helper_id() btf_resolve_helper_id() caching logic is a bit racy, since under root the verifier can verify several programs in parallel. Fix it with READ/WRITE_ONCE. Fix the type as well, since error is also recorded. Fixes: a7658e1a4164 ("bpf: Check types of arguments passed into helpers") Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Song Liu Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20191114185720.1641606-15-ast@kernel.org --- include/linux/bpf.h | 5 +++-- kernel/bpf/btf.c | 26 +++++++++++++++++++++++++- kernel/bpf/verifier.c | 8 +++----- net/core/filter.c | 2 +- 4 files changed, 32 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0d4c5c224d79..cb5a356381f5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -248,7 +248,7 @@ struct bpf_func_proto { }; enum bpf_arg_type arg_type[5]; }; - u32 *btf_id; /* BTF ids of arguments */ + int *btf_id; /* BTF ids of arguments */ }; /* bpf_context is intentionally undefined structure. Pointer to bpf_context is @@ -881,7 +881,8 @@ int btf_struct_access(struct bpf_verifier_log *log, const struct btf_type *t, int off, int size, enum bpf_access_type atype, u32 *next_btf_id); -u32 btf_resolve_helper_id(struct bpf_verifier_log *log, void *, int); +int btf_resolve_helper_id(struct bpf_verifier_log *log, + const struct bpf_func_proto *fn, int); int btf_distill_func_proto(struct bpf_verifier_log *log, struct btf *btf, diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 9e1164e5b429..033d071eb59c 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3721,7 +3721,8 @@ again: return -EINVAL; } -u32 btf_resolve_helper_id(struct bpf_verifier_log *log, void *fn, int arg) +static int __btf_resolve_helper_id(struct bpf_verifier_log *log, void *fn, + int arg) { char fnname[KSYM_SYMBOL_LEN + 4] = "btf_"; const struct btf_param *args; @@ -3789,6 +3790,29 @@ u32 btf_resolve_helper_id(struct bpf_verifier_log *log, void *fn, int arg) return btf_id; } +int btf_resolve_helper_id(struct bpf_verifier_log *log, + const struct bpf_func_proto *fn, int arg) +{ + int *btf_id = &fn->btf_id[arg]; + int ret; + + if (fn->arg_type[arg] != ARG_PTR_TO_BTF_ID) + return -EINVAL; + + ret = READ_ONCE(*btf_id); + if (ret) + return ret; + /* ok to race the search. The result is the same */ + ret = __btf_resolve_helper_id(log, fn->func, arg); + if (!ret) { + /* Function argument cannot be type 'void' */ + bpf_log(log, "BTF resolution bug\n"); + return -EFAULT; + } + WRITE_ONCE(*btf_id, ret); + return ret; +} + static int __get_type_size(struct btf *btf, u32 btf_id, const struct btf_type **bad_type) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 8f89cfa93e88..e78ec7990767 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4147,11 +4147,9 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn meta.func_id = func_id; /* check args */ for (i = 0; i < 5; i++) { - if (fn->arg_type[i] == ARG_PTR_TO_BTF_ID) { - if (!fn->btf_id[i]) - fn->btf_id[i] = btf_resolve_helper_id(&env->log, fn->func, i); - meta.btf_id = fn->btf_id[i]; - } + err = btf_resolve_helper_id(&env->log, fn, i); + if (err > 0) + meta.btf_id = err; err = check_func_arg(env, BPF_REG_1 + i, fn->arg_type[i], &meta); if (err) return err; diff --git a/net/core/filter.c b/net/core/filter.c index fc303abec8fa..f72face90659 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3816,7 +3816,7 @@ static const struct bpf_func_proto bpf_skb_event_output_proto = { .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; -static u32 bpf_skb_output_btf_ids[5]; +static int bpf_skb_output_btf_ids[5]; const struct bpf_func_proto bpf_skb_output_proto = { .func = bpf_skb_event_output, .gpl_only = true, -- cgit v1.2.3-71-gd317 From 91cc1a99740e2ed1d903b5906afb470cc5a07379 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 14 Nov 2019 10:57:15 -0800 Subject: bpf: Annotate context types Annotate BPF program context types with program-side type and kernel-side type. This type information is used by the verifier. btf_get_prog_ctx_type() is used in the later patches to verify that BTF type of ctx in BPF program matches to kernel expected ctx type. For example, the XDP program type is: BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp, struct xdp_md, struct xdp_buff) That means that XDP program should be written as: int xdp_prog(struct xdp_md *ctx) { ... } Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20191114185720.1641606-16-ast@kernel.org --- include/linux/bpf.h | 11 ++++- include/linux/bpf_types.h | 78 ++++++++++++++++++++----------- kernel/bpf/btf.c | 114 ++++++++++++++++++++++++++++++++++++++++++++-- kernel/bpf/syscall.c | 4 +- kernel/bpf/verifier.c | 2 +- net/core/filter.c | 10 ---- 6 files changed, 176 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cb5a356381f5..9c48f11fe56e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -747,7 +747,7 @@ DECLARE_PER_CPU(int, bpf_prog_active); extern const struct file_operations bpf_map_fops; extern const struct file_operations bpf_prog_fops; -#define BPF_PROG_TYPE(_id, _name) \ +#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ extern const struct bpf_prog_ops _name ## _prog_ops; \ extern const struct bpf_verifier_ops _name ## _verifier_ops; #define BPF_MAP_TYPE(_id, _ops) \ @@ -1213,6 +1213,15 @@ static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, #endif #ifdef CONFIG_INET +struct sk_reuseport_kern { + struct sk_buff *skb; + struct sock *sk; + struct sock *selected_sk; + void *data_end; + u32 hash; + u32 reuseport_id; + bool bind_inany; +}; bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index de14872b01ba..93740b3614d7 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -2,42 +2,68 @@ /* internal file - do not include directly */ #ifdef CONFIG_NET -BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter) -BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act) -BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act) -BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp) +BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp, + struct xdp_md, struct xdp_buff) #ifdef CONFIG_CGROUP_BPF -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb) -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock) -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, cg_sock_addr) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock, + struct bpf_sock, struct sock) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, cg_sock_addr, + struct bpf_sock_addr, struct bpf_sock_addr_kern) #endif -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_in) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_out) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_SEG6LOCAL, lwt_seg6local) -BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb) -BPF_PROG_TYPE(BPF_PROG_TYPE_SK_MSG, sk_msg) -BPF_PROG_TYPE(BPF_PROG_TYPE_FLOW_DISSECTOR, flow_dissector) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_in, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_out, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_SEG6LOCAL, lwt_seg6local, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops, + struct bpf_sock_ops, struct bpf_sock_ops_kern) +BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_SK_MSG, sk_msg, + struct sk_msg_md, struct sk_msg) +BPF_PROG_TYPE(BPF_PROG_TYPE_FLOW_DISSECTOR, flow_dissector, + struct __sk_buff, struct bpf_flow_dissector) #endif #ifdef CONFIG_BPF_EVENTS -BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe) -BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint) -BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event) -BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint) -BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable) -BPF_PROG_TYPE(BPF_PROG_TYPE_TRACING, tracing) +BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe, + bpf_user_pt_regs_t, struct pt_regs) +BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint, + __u64, u64) +BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event, + struct bpf_perf_event_data, struct bpf_perf_event_data_kern) +BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint, + struct bpf_raw_tracepoint_args, u64) +BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable, + struct bpf_raw_tracepoint_args, u64) +BPF_PROG_TYPE(BPF_PROG_TYPE_TRACING, tracing, + void *, void *) #endif #ifdef CONFIG_CGROUP_BPF -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev) -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SYSCTL, cg_sysctl) -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCKOPT, cg_sockopt) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev, + struct bpf_cgroup_dev_ctx, struct bpf_cgroup_dev_ctx) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SYSCTL, cg_sysctl, + struct bpf_sysctl, struct bpf_sysctl_kern) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCKOPT, cg_sockopt, + struct bpf_sockopt, struct bpf_sockopt_kern) #endif #ifdef CONFIG_BPF_LIRC_MODE2 -BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2) +BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2, + __u32, u32) #endif #ifdef CONFIG_INET -BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport) +BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport, + struct sk_reuseport_md, struct sk_reuseport_kern) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 033d071eb59c..4b7c8bd423d6 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -2,6 +2,8 @@ /* Copyright (c) 2018 Facebook */ #include +#include +#include #include #include #include @@ -16,6 +18,9 @@ #include #include #include +#include +#include +#include /* BTF (BPF Type Format) is the meta data format which describes * the data types of BPF program/map. Hence, it basically focus @@ -3439,13 +3444,98 @@ errout: extern char __weak _binary__btf_vmlinux_bin_start[]; extern char __weak _binary__btf_vmlinux_bin_end[]; +extern struct btf *btf_vmlinux; + +#define BPF_MAP_TYPE(_id, _ops) +static union { + struct bpf_ctx_convert { +#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ + prog_ctx_type _id##_prog; \ + kern_ctx_type _id##_kern; +#include +#undef BPF_PROG_TYPE + } *__t; + /* 't' is written once under lock. Read many times. */ + const struct btf_type *t; +} bpf_ctx_convert; +enum { +#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ + __ctx_convert##_id, +#include +#undef BPF_PROG_TYPE +}; +static u8 bpf_ctx_convert_map[] = { +#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ + [_id] = __ctx_convert##_id, +#include +#undef BPF_PROG_TYPE +}; +#undef BPF_MAP_TYPE + +static const struct btf_member * +btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf, + const struct btf_type *t, enum bpf_prog_type prog_type) +{ + const struct btf_type *conv_struct; + const struct btf_type *ctx_struct; + const struct btf_member *ctx_type; + const char *tname, *ctx_tname; + + conv_struct = bpf_ctx_convert.t; + if (!conv_struct) { + bpf_log(log, "btf_vmlinux is malformed\n"); + return NULL; + } + t = btf_type_by_id(btf, t->type); + while (btf_type_is_modifier(t)) + t = btf_type_by_id(btf, t->type); + if (!btf_type_is_struct(t)) { + /* Only pointer to struct is supported for now. + * That means that BPF_PROG_TYPE_TRACEPOINT with BTF + * is not supported yet. + * BPF_PROG_TYPE_RAW_TRACEPOINT is fine. + */ + bpf_log(log, "BPF program ctx type is not a struct\n"); + return NULL; + } + tname = btf_name_by_offset(btf, t->name_off); + if (!tname) { + bpf_log(log, "BPF program ctx struct doesn't have a name\n"); + return NULL; + } + /* prog_type is valid bpf program type. No need for bounds check. */ + ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2; + /* ctx_struct is a pointer to prog_ctx_type in vmlinux. + * Like 'struct __sk_buff' + */ + ctx_struct = btf_type_by_id(btf_vmlinux, ctx_type->type); + if (!ctx_struct) + /* should not happen */ + return NULL; + ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_struct->name_off); + if (!ctx_tname) { + /* should not happen */ + bpf_log(log, "Please fix kernel include/linux/bpf_types.h\n"); + return NULL; + } + /* only compare that prog's ctx type name is the same as + * kernel expects. No need to compare field by field. + * It's ok for bpf prog to do: + * struct __sk_buff {}; + * int socket_filter_bpf_prog(struct __sk_buff *skb) + * { // no fields of skb are ever used } + */ + if (strcmp(ctx_tname, tname)) + return NULL; + return ctx_type; +} struct btf *btf_parse_vmlinux(void) { struct btf_verifier_env *env = NULL; struct bpf_verifier_log *log; struct btf *btf = NULL; - int err; + int err, i; env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN); if (!env) @@ -3479,6 +3569,26 @@ struct btf *btf_parse_vmlinux(void) if (err) goto errout; + /* find struct bpf_ctx_convert for type checking later */ + for (i = 1; i <= btf->nr_types; i++) { + const struct btf_type *t; + const char *tname; + + t = btf_type_by_id(btf, i); + if (!__btf_type_is_struct(t)) + continue; + tname = __btf_name_by_offset(btf, t->name_off); + if (!strcmp(tname, "bpf_ctx_convert")) { + /* btf_parse_vmlinux() runs under bpf_verifier_lock */ + bpf_ctx_convert.t = t; + break; + } + } + if (i > btf->nr_types) { + err = -ENOENT; + goto errout; + } + btf_verifier_env_free(env); refcount_set(&btf->refcnt, 1); return btf; @@ -3492,8 +3602,6 @@ errout: return ERR_PTR(err); } -extern struct btf *btf_vmlinux; - bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index e2e37bea86bc..05a0ee75eca0 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -43,7 +43,7 @@ static DEFINE_SPINLOCK(map_idr_lock); int sysctl_unprivileged_bpf_disabled __read_mostly; static const struct bpf_map_ops * const bpf_map_types[] = { -#define BPF_PROG_TYPE(_id, _ops) +#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) #define BPF_MAP_TYPE(_id, _ops) \ [_id] = &_ops, #include @@ -1189,7 +1189,7 @@ err_put: } static const struct bpf_prog_ops * const bpf_prog_types[] = { -#define BPF_PROG_TYPE(_id, _name) \ +#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ [_id] = & _name ## _prog_ops, #define BPF_MAP_TYPE(_id, _ops) #include diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e78ec7990767..7395d6bebefd 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -23,7 +23,7 @@ #include "disasm.h" static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { -#define BPF_PROG_TYPE(_id, _name) \ +#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ [_id] = & _name ## _verifier_ops, #define BPF_MAP_TYPE(_id, _ops) #include diff --git a/net/core/filter.c b/net/core/filter.c index f72face90659..49ded4a7588a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -8684,16 +8684,6 @@ out: } #ifdef CONFIG_INET -struct sk_reuseport_kern { - struct sk_buff *skb; - struct sock *sk; - struct sock *selected_sk; - void *data_end; - u32 hash; - u32 reuseport_id; - bool bind_inany; -}; - static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern, struct sock_reuseport *reuse, struct sock *sk, struct sk_buff *skb, -- cgit v1.2.3-71-gd317 From 8c1b6e69dcc1e11bd24111e3734dd740aaf3fda1 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 14 Nov 2019 10:57:16 -0800 Subject: bpf: Compare BTF types of functions arguments with actual types Make the verifier check that BTF types of function arguments match actual types passed into top-level BPF program and into BPF-to-BPF calls. If types match such BPF programs and sub-programs will have full support of BPF trampoline. If types mismatch the trampoline has to be conservative. It has to save/restore five program arguments and assume 64-bit scalars. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Song Liu Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20191114185720.1641606-17-ast@kernel.org --- include/linux/bpf.h | 8 +++++ include/linux/bpf_verifier.h | 1 + kernel/bpf/btf.c | 82 ++++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 1 + kernel/bpf/verifier.c | 18 ++++++++-- 5 files changed, 107 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9c48f11fe56e..c70bf04726b4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -480,6 +480,10 @@ static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog) static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {} #endif +struct bpf_func_info_aux { + bool unreliable; +}; + struct bpf_prog_aux { atomic_t refcnt; u32 used_map_cnt; @@ -494,6 +498,7 @@ struct bpf_prog_aux { bool verifier_zext; /* Zero extensions has been inserted by verifier. */ bool offload_requested; bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ + bool func_proto_unreliable; enum bpf_tramp_prog_type trampoline_prog_type; struct bpf_trampoline *trampoline; struct hlist_node tramp_hlist; @@ -518,6 +523,7 @@ struct bpf_prog_aux { struct bpf_prog_offload *offload; struct btf *btf; struct bpf_func_info *func_info; + struct bpf_func_info_aux *func_info_aux; /* bpf_line_info loaded from userspace. linfo->insn_off * has the xlated insn offset. * Both the main and sub prog share the same linfo. @@ -890,6 +896,8 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, const char *func_name, struct btf_func_model *m); +int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog); + #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 6e7284ea1468..cdd08bf0ec06 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -343,6 +343,7 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) #define BPF_MAX_SUBPROGS 256 struct bpf_subprog_info { + /* 'start' has to be the first field otherwise find_subprog() won't work */ u32 start; /* insn idx of function entry point */ u32 linfo_idx; /* The idx to the main_prog->aux->linfo */ u16 stack_depth; /* max. stack depth used by this function */ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 4b7c8bd423d6..4620267b186e 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3985,6 +3985,88 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, return 0; } +int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog) +{ + struct bpf_verifier_state *st = env->cur_state; + struct bpf_func_state *func = st->frame[st->curframe]; + struct bpf_reg_state *reg = func->regs; + struct bpf_verifier_log *log = &env->log; + struct bpf_prog *prog = env->prog; + struct btf *btf = prog->aux->btf; + const struct btf_param *args; + const struct btf_type *t; + u32 i, nargs, btf_id; + const char *tname; + + if (!prog->aux->func_info) + return 0; + + btf_id = prog->aux->func_info[subprog].type_id; + if (!btf_id) + return 0; + + if (prog->aux->func_info_aux[subprog].unreliable) + return 0; + + t = btf_type_by_id(btf, btf_id); + if (!t || !btf_type_is_func(t)) { + bpf_log(log, "BTF of subprog %d doesn't point to KIND_FUNC\n", + subprog); + return -EINVAL; + } + tname = btf_name_by_offset(btf, t->name_off); + + t = btf_type_by_id(btf, t->type); + if (!t || !btf_type_is_func_proto(t)) { + bpf_log(log, "Invalid type of func %s\n", tname); + return -EINVAL; + } + args = (const struct btf_param *)(t + 1); + nargs = btf_type_vlen(t); + if (nargs > 5) { + bpf_log(log, "Function %s has %d > 5 args\n", tname, nargs); + goto out; + } + /* check that BTF function arguments match actual types that the + * verifier sees. + */ + for (i = 0; i < nargs; i++) { + t = btf_type_by_id(btf, args[i].type); + while (btf_type_is_modifier(t)) + t = btf_type_by_id(btf, t->type); + if (btf_type_is_int(t) || btf_type_is_enum(t)) { + if (reg[i + 1].type == SCALAR_VALUE) + continue; + bpf_log(log, "R%d is not a scalar\n", i + 1); + goto out; + } + if (btf_type_is_ptr(t)) { + if (reg[i + 1].type == SCALAR_VALUE) { + bpf_log(log, "R%d is not a pointer\n", i + 1); + goto out; + } + /* If program is passing PTR_TO_CTX into subprogram + * check that BTF type matches. + */ + if (reg[i + 1].type == PTR_TO_CTX && + !btf_get_prog_ctx_type(log, btf, t, prog->type)) + goto out; + /* All other pointers are ok */ + continue; + } + bpf_log(log, "Unrecognized argument type %s\n", + btf_kind_str[BTF_INFO_KIND(t->info)]); + goto out; + } + return 0; +out: + /* LLVM optimizations can remove arguments from static functions. */ + bpf_log(log, + "Type info disagrees with actual arguments due to compiler optimizations\n"); + prog->aux->func_info_aux[subprog].unreliable = true; + return 0; +} + void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, struct seq_file *m) { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 05a0ee75eca0..43ba647de720 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1328,6 +1328,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu); kvfree(aux->func_info); + kfree(aux->func_info_aux); free_used_maps(aux); bpf_prog_uncharge_memlock(aux->prog); security_bpf_prog_free(aux); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 7395d6bebefd..11910149ca2f 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3970,6 +3970,9 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, /* only increment it after check_reg_arg() finished */ state->curframe++; + if (btf_check_func_arg_match(env, subprog)) + return -EINVAL; + /* and go analyze first insn of the callee */ *insn_idx = target_insn; @@ -6564,6 +6567,7 @@ static int check_btf_func(struct bpf_verifier_env *env, u32 i, nfuncs, urec_size, min_size; u32 krec_size = sizeof(struct bpf_func_info); struct bpf_func_info *krecord; + struct bpf_func_info_aux *info_aux = NULL; const struct btf_type *type; struct bpf_prog *prog; const struct btf *btf; @@ -6597,6 +6601,9 @@ static int check_btf_func(struct bpf_verifier_env *env, krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL | __GFP_NOWARN); if (!krecord) return -ENOMEM; + info_aux = kcalloc(nfuncs, sizeof(*info_aux), GFP_KERNEL | __GFP_NOWARN); + if (!info_aux) + goto err_free; for (i = 0; i < nfuncs; i++) { ret = bpf_check_uarg_tail_zero(urecord, krec_size, urec_size); @@ -6648,29 +6655,31 @@ static int check_btf_func(struct bpf_verifier_env *env, ret = -EINVAL; goto err_free; } - prev_offset = krecord[i].insn_off; urecord += urec_size; } prog->aux->func_info = krecord; prog->aux->func_info_cnt = nfuncs; + prog->aux->func_info_aux = info_aux; return 0; err_free: kvfree(krecord); + kfree(info_aux); return ret; } static void adjust_btf_func(struct bpf_verifier_env *env) { + struct bpf_prog_aux *aux = env->prog->aux; int i; - if (!env->prog->aux->func_info) + if (!aux->func_info) return; for (i = 0; i < env->subprog_cnt; i++) - env->prog->aux->func_info[i].insn_off = env->subprog_info[i].start; + aux->func_info[i].insn_off = env->subprog_info[i].start; } #define MIN_BPF_LINEINFO_SIZE (offsetof(struct bpf_line_info, line_col) + \ @@ -7651,6 +7660,9 @@ static int do_check(struct bpf_verifier_env *env) 0 /* frameno */, 0 /* subprogno, zero == main subprog */); + if (btf_check_func_arg_match(env, 0)) + return -EINVAL; + for (;;) { struct bpf_insn *insn; u8 class; -- cgit v1.2.3-71-gd317 From 5b92a28aae4dd0f88778d540ecfdcdaec5a41723 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 14 Nov 2019 10:57:17 -0800 Subject: bpf: Support attaching tracing BPF program to other BPF programs Allow FENTRY/FEXIT BPF programs to attach to other BPF programs of any type including their subprograms. This feature allows snooping on input and output packets in XDP, TC programs including their return values. In order to do that the verifier needs to track types not only of vmlinux, but types of other BPF programs as well. The verifier also needs to translate uapi/linux/bpf.h types used by networking programs into kernel internal BTF types used by FENTRY/FEXIT BPF programs. In some cases LLVM optimizations can remove arguments from BPF subprograms without adjusting BTF info that LLVM backend knows. When BTF info disagrees with actual types that the verifiers sees the BPF trampoline has to fallback to conservative and treat all arguments as u64. The FENTRY/FEXIT program can still attach to such subprograms, but it won't be able to recognize pointer types like 'struct sk_buff *' and it won't be able to pass them to bpf_skb_output() for dumping packets to user space. The FENTRY/FEXIT program would need to use bpf_probe_read_kernel() instead. The BPF_PROG_LOAD command is extended with attach_prog_fd field. When it's set to zero the attach_btf_id is one vmlinux BTF type ids. When attach_prog_fd points to previously loaded BPF program the attach_btf_id is BTF type id of main function or one of its subprograms. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20191114185720.1641606-18-ast@kernel.org --- arch/x86/net/bpf_jit_comp.c | 3 +- include/linux/bpf.h | 1 + include/linux/btf.h | 1 + include/uapi/linux/bpf.h | 1 + kernel/bpf/btf.c | 70 +++++++++++++++++++++++++++++++++----- kernel/bpf/core.c | 2 ++ kernel/bpf/syscall.c | 19 ++++++++--- kernel/bpf/verifier.c | 83 +++++++++++++++++++++++++++++++++++++-------- 8 files changed, 152 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index c06096df9118..2e586f579945 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -504,7 +504,8 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, u8 *prog; int ret; - if (!is_kernel_text((long)ip)) + if (!is_kernel_text((long)ip) && + !is_bpf_text_address((long)ip)) /* BPF trampoline in modules is not supported */ return -EINVAL; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c70bf04726b4..5b81cde47314 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -495,6 +495,7 @@ struct bpf_prog_aux { u32 func_cnt; /* used by non-func prog as the number of func progs */ u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */ u32 attach_btf_id; /* in-kernel BTF type id to attach to */ + struct bpf_prog *linked_prog; bool verifier_zext; /* Zero extensions has been inserted by verifier. */ bool offload_requested; bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ diff --git a/include/linux/btf.h b/include/linux/btf.h index 9dee00859c5f..79d4abc2556a 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -88,6 +88,7 @@ static inline bool btf_type_is_func_proto(const struct btf_type *t) const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); const char *btf_name_by_offset(const struct btf *btf, u32 offset); struct btf *btf_parse_vmlinux(void); +struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog); #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 69c200e6e696..4842a134b202 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -425,6 +425,7 @@ union bpf_attr { __aligned_u64 line_info; /* line info */ __u32 line_info_cnt; /* number of bpf_line_info records */ __u32 attach_btf_id; /* in-kernel BTF type id to attach to */ + __u32 attach_prog_fd; /* 0 to attach to vmlinux */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 4620267b186e..40efde5eedcb 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3530,6 +3530,20 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf, return ctx_type; } +static int btf_translate_to_vmlinux(struct bpf_verifier_log *log, + struct btf *btf, + const struct btf_type *t, + enum bpf_prog_type prog_type) +{ + const struct btf_member *prog_ctx_type, *kern_ctx_type; + + prog_ctx_type = btf_get_prog_ctx_type(log, btf, t, prog_type); + if (!prog_ctx_type) + return -ENOENT; + kern_ctx_type = prog_ctx_type + 1; + return kern_ctx_type->type; +} + struct btf *btf_parse_vmlinux(void) { struct btf_verifier_env *env = NULL; @@ -3602,15 +3616,29 @@ errout: return ERR_PTR(err); } +struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog) +{ + struct bpf_prog *tgt_prog = prog->aux->linked_prog; + + if (tgt_prog) { + return tgt_prog->aux->btf; + } else { + return btf_vmlinux; + } +} + bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const struct btf_type *t = prog->aux->attach_func_proto; + struct bpf_prog *tgt_prog = prog->aux->linked_prog; + struct btf *btf = bpf_prog_get_target_btf(prog); const char *tname = prog->aux->attach_func_name; struct bpf_verifier_log *log = info->log; const struct btf_param *args; u32 nr_args, arg; + int ret; if (off % 8) { bpf_log(log, "func '%s' offset %d is not multiple of 8\n", @@ -3619,7 +3647,8 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, } arg = off / 8; args = (const struct btf_param *)(t + 1); - nr_args = btf_type_vlen(t); + /* if (t == NULL) Fall back to default BPF prog with 5 u64 arguments */ + nr_args = t ? btf_type_vlen(t) : 5; if (prog->aux->attach_btf_trace) { /* skip first 'void *__data' argument in btf_trace_##name typedef */ args++; @@ -3628,18 +3657,24 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, if (prog->expected_attach_type == BPF_TRACE_FEXIT && arg == nr_args) { + if (!t) + /* Default prog with 5 args. 6th arg is retval. */ + return true; /* function return type */ - t = btf_type_by_id(btf_vmlinux, t->type); + t = btf_type_by_id(btf, t->type); } else if (arg >= nr_args) { bpf_log(log, "func '%s' doesn't have %d-th argument\n", tname, arg + 1); return false; } else { - t = btf_type_by_id(btf_vmlinux, args[arg].type); + if (!t) + /* Default prog with 5 args */ + return true; + t = btf_type_by_id(btf, args[arg].type); } /* skip modifiers */ while (btf_type_is_modifier(t)) - t = btf_type_by_id(btf_vmlinux, t->type); + t = btf_type_by_id(btf, t->type); if (btf_type_is_int(t)) /* accessing a scalar */ return true; @@ -3647,7 +3682,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, bpf_log(log, "func '%s' arg%d '%s' has type %s. Only pointer access is allowed\n", tname, arg, - __btf_name_by_offset(btf_vmlinux, t->name_off), + __btf_name_by_offset(btf, t->name_off), btf_kind_str[BTF_INFO_KIND(t->info)]); return false; } @@ -3662,10 +3697,19 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, info->reg_type = PTR_TO_BTF_ID; info->btf_id = t->type; - t = btf_type_by_id(btf_vmlinux, t->type); + if (tgt_prog) { + ret = btf_translate_to_vmlinux(log, btf, t, tgt_prog->type); + if (ret > 0) { + info->btf_id = ret; + return true; + } else { + return false; + } + } + t = btf_type_by_id(btf, t->type); /* skip modifiers */ while (btf_type_is_modifier(t)) - t = btf_type_by_id(btf_vmlinux, t->type); + t = btf_type_by_id(btf, t->type); if (!btf_type_is_struct(t)) { bpf_log(log, "func '%s' arg%d type %s is not a struct\n", @@ -3674,7 +3718,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, } bpf_log(log, "func '%s' arg%d has btf_id %d type %s '%s'\n", tname, arg, info->btf_id, btf_kind_str[BTF_INFO_KIND(t->info)], - __btf_name_by_offset(btf_vmlinux, t->name_off)); + __btf_name_by_offset(btf, t->name_off)); return true; } @@ -3954,6 +3998,16 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, u32 i, nargs; int ret; + if (!func) { + /* BTF function prototype doesn't match the verifier types. + * Fall back to 5 u64 args. + */ + for (i = 0; i < 5; i++) + m->arg_size[i] = 8; + m->ret_size = 8; + m->nr_args = 5; + return 0; + } args = (const struct btf_param *)(func + 1); nargs = btf_type_vlen(func); if (nargs >= MAX_BPF_FUNC_ARGS) { diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index da5a8b8e278f..b5945c3aaa8e 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2031,6 +2031,8 @@ void bpf_prog_free(struct bpf_prog *fp) { struct bpf_prog_aux *aux = fp->aux; + if (aux->linked_prog) + bpf_prog_put(aux->linked_prog); INIT_WORK(&aux->work, bpf_prog_free_deferred); schedule_work(&aux->work); } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 43ba647de720..c88c815c2154 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1577,7 +1577,7 @@ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr) static int bpf_prog_load_check_attach(enum bpf_prog_type prog_type, enum bpf_attach_type expected_attach_type, - u32 btf_id) + u32 btf_id, u32 prog_fd) { switch (prog_type) { case BPF_PROG_TYPE_TRACING: @@ -1585,7 +1585,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, return -EINVAL; break; default: - if (btf_id) + if (btf_id || prog_fd) return -EINVAL; break; } @@ -1636,7 +1636,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD attach_btf_id +#define BPF_PROG_LOAD_LAST_FIELD attach_prog_fd static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) { @@ -1679,7 +1679,8 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) bpf_prog_load_fixup_attach_type(attr); if (bpf_prog_load_check_attach(type, attr->expected_attach_type, - attr->attach_btf_id)) + attr->attach_btf_id, + attr->attach_prog_fd)) return -EINVAL; /* plain bpf_prog allocation */ @@ -1689,6 +1690,16 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) prog->expected_attach_type = attr->expected_attach_type; prog->aux->attach_btf_id = attr->attach_btf_id; + if (attr->attach_prog_fd) { + struct bpf_prog *tgt_prog; + + tgt_prog = bpf_prog_get(attr->attach_prog_fd); + if (IS_ERR(tgt_prog)) { + err = PTR_ERR(tgt_prog); + goto free_prog_nouncharge; + } + prog->aux->linked_prog = tgt_prog; + } prog->aux->offload_requested = !!attr->prog_ifindex; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 11910149ca2f..e9dc95a18d44 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -9390,13 +9390,17 @@ static void print_verification_stats(struct bpf_verifier_env *env) static int check_attach_btf_id(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog; + struct bpf_prog *tgt_prog = prog->aux->linked_prog; u32 btf_id = prog->aux->attach_btf_id; const char prefix[] = "btf_trace_"; + int ret = 0, subprog = -1, i; struct bpf_trampoline *tr; const struct btf_type *t; + bool conservative = true; const char *tname; - int ret = 0; + struct btf *btf; long addr; + u64 key; if (prog->type != BPF_PROG_TYPE_TRACING) return 0; @@ -9405,19 +9409,47 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) verbose(env, "Tracing programs must provide btf_id\n"); return -EINVAL; } - t = btf_type_by_id(btf_vmlinux, btf_id); + btf = bpf_prog_get_target_btf(prog); + if (!btf) { + verbose(env, + "FENTRY/FEXIT program can only be attached to another program annotated with BTF\n"); + return -EINVAL; + } + t = btf_type_by_id(btf, btf_id); if (!t) { verbose(env, "attach_btf_id %u is invalid\n", btf_id); return -EINVAL; } - tname = btf_name_by_offset(btf_vmlinux, t->name_off); + tname = btf_name_by_offset(btf, t->name_off); if (!tname) { verbose(env, "attach_btf_id %u doesn't have a name\n", btf_id); return -EINVAL; } + if (tgt_prog) { + struct bpf_prog_aux *aux = tgt_prog->aux; + + for (i = 0; i < aux->func_info_cnt; i++) + if (aux->func_info[i].type_id == btf_id) { + subprog = i; + break; + } + if (subprog == -1) { + verbose(env, "Subprog %s doesn't exist\n", tname); + return -EINVAL; + } + conservative = aux->func_info_aux[subprog].unreliable; + key = ((u64)aux->id) << 32 | btf_id; + } else { + key = btf_id; + } switch (prog->expected_attach_type) { case BPF_TRACE_RAW_TP: + if (tgt_prog) { + verbose(env, + "Only FENTRY/FEXIT progs are attachable to another BPF prog\n"); + return -EINVAL; + } if (!btf_type_is_typedef(t)) { verbose(env, "attach_btf_id %u is not a typedef\n", btf_id); @@ -9429,11 +9461,11 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) return -EINVAL; } tname += sizeof(prefix) - 1; - t = btf_type_by_id(btf_vmlinux, t->type); + t = btf_type_by_id(btf, t->type); if (!btf_type_is_ptr(t)) /* should never happen in valid vmlinux build */ return -EINVAL; - t = btf_type_by_id(btf_vmlinux, t->type); + t = btf_type_by_id(btf, t->type); if (!btf_type_is_func_proto(t)) /* should never happen in valid vmlinux build */ return -EINVAL; @@ -9452,30 +9484,51 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) btf_id); return -EINVAL; } - t = btf_type_by_id(btf_vmlinux, t->type); + t = btf_type_by_id(btf, t->type); if (!btf_type_is_func_proto(t)) return -EINVAL; - tr = bpf_trampoline_lookup(btf_id); + tr = bpf_trampoline_lookup(key); if (!tr) return -ENOMEM; prog->aux->attach_func_name = tname; + /* t is either vmlinux type or another program's type */ prog->aux->attach_func_proto = t; mutex_lock(&tr->mutex); if (tr->func.addr) { prog->aux->trampoline = tr; goto out; } - ret = btf_distill_func_proto(&env->log, btf_vmlinux, t, + if (tgt_prog && conservative) { + prog->aux->attach_func_proto = NULL; + t = NULL; + } + ret = btf_distill_func_proto(&env->log, btf, t, tname, &tr->func.model); if (ret < 0) goto out; - addr = kallsyms_lookup_name(tname); - if (!addr) { - verbose(env, - "The address of function %s cannot be found\n", - tname); - ret = -ENOENT; - goto out; + if (tgt_prog) { + if (!tgt_prog->jited) { + /* for now */ + verbose(env, "Can trace only JITed BPF progs\n"); + ret = -EINVAL; + goto out; + } + if (tgt_prog->type == BPF_PROG_TYPE_TRACING) { + /* prevent cycles */ + verbose(env, "Cannot recursively attach\n"); + ret = -EINVAL; + goto out; + } + addr = (long) tgt_prog->aux->func[subprog]->bpf_func; + } else { + addr = kallsyms_lookup_name(tname); + if (!addr) { + verbose(env, + "The address of function %s cannot be found\n", + tname); + ret = -ENOENT; + goto out; + } } tr->func.addr = (void *)addr; prog->aux->trampoline = tr; -- cgit v1.2.3-71-gd317 From 49cb2fc42ce4b7a656ee605e30c302efaa39c1a7 Mon Sep 17 00:00:00 2001 From: Adrian Reber Date: Fri, 15 Nov 2019 13:36:20 +0100 Subject: fork: extend clone3() to support setting a PID The main motivation to add set_tid to clone3() is CRIU. To restore a process with the same PID/TID CRIU currently uses /proc/sys/kernel/ns_last_pid. It writes the desired (PID - 1) to ns_last_pid and then (quickly) does a clone(). This works most of the time, but it is racy. It is also slow as it requires multiple syscalls. Extending clone3() to support *set_tid makes it possible restore a process using CRIU without accessing /proc/sys/kernel/ns_last_pid and race free (as long as the desired PID/TID is available). This clone3() extension places the same restrictions (CAP_SYS_ADMIN) on clone3() with *set_tid as they are currently in place for ns_last_pid. The original version of this change was using a single value for set_tid. At the 2019 LPC, after presenting set_tid, it was, however, decided to change set_tid to an array to enable setting the PID of a process in multiple PID namespaces at the same time. If a process is created in a PID namespace it is possible to influence the PID inside and outside of the PID namespace. Details also in the corresponding selftest. To create a process with the following PIDs: PID NS level Requested PID 0 (host) 31496 1 42 2 1 For that example the two newly introduced parameters to struct clone_args (set_tid and set_tid_size) would need to be: set_tid[0] = 1; set_tid[1] = 42; set_tid[2] = 31496; set_tid_size = 3; If only the PIDs of the two innermost nested PID namespaces should be defined it would look like this: set_tid[0] = 1; set_tid[1] = 42; set_tid_size = 2; The PID of the newly created process would then be the next available free PID in the PID namespace level 0 (host) and 42 in the PID namespace at level 1 and the PID of the process in the innermost PID namespace would be 1. The set_tid array is used to specify the PID of a process starting from the innermost nested PID namespaces up to set_tid_size PID namespaces. set_tid_size cannot be larger then the current PID namespace level. Signed-off-by: Adrian Reber Reviewed-by: Christian Brauner Reviewed-by: Oleg Nesterov Reviewed-by: Dmitry Safonov <0x7f454c46@gmail.com> Acked-by: Andrei Vagin Link: https://lore.kernel.org/r/20191115123621.142252-1-areber@redhat.com Signed-off-by: Christian Brauner --- include/linux/pid.h | 3 +- include/linux/pid_namespace.h | 2 ++ include/linux/sched/task.h | 3 ++ include/uapi/linux/sched.h | 53 ++++++++++++++++++++----------- kernel/fork.c | 24 ++++++++++++++- kernel/pid.c | 72 ++++++++++++++++++++++++++++++++++--------- kernel/pid_namespace.c | 2 -- 7 files changed, 122 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index 034e3cd60dc0..998ae7d24450 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -124,7 +124,8 @@ extern struct pid *find_vpid(int nr); extern struct pid *find_get_pid(int nr); extern struct pid *find_ge_pid(int nr, struct pid_namespace *); -extern struct pid *alloc_pid(struct pid_namespace *ns); +extern struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, + size_t set_tid_size); extern void free_pid(struct pid *pid); extern void disable_pid_allocation(struct pid_namespace *ns); diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 49538b172483..2ed6af88794b 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -12,6 +12,8 @@ #include #include +/* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */ +#define MAX_PID_NS_LEVEL 32 struct fs_pin; diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 4b1c3b664f51..f1879884238e 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -26,6 +26,9 @@ struct kernel_clone_args { unsigned long stack; unsigned long stack_size; unsigned long tls; + pid_t *set_tid; + /* Number of elements in *set_tid */ + size_t set_tid_size; }; /* diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h index 1d500ed03c63..a0b1c224c72b 100644 --- a/include/uapi/linux/sched.h +++ b/include/uapi/linux/sched.h @@ -39,24 +39,38 @@ #ifndef __ASSEMBLY__ /** * struct clone_args - arguments for the clone3 syscall - * @flags: Flags for the new process as listed above. - * All flags are valid except for CSIGNAL and - * CLONE_DETACHED. - * @pidfd: If CLONE_PIDFD is set, a pidfd will be - * returned in this argument. - * @child_tid: If CLONE_CHILD_SETTID is set, the TID of the - * child process will be returned in the child's - * memory. - * @parent_tid: If CLONE_PARENT_SETTID is set, the TID of - * the child process will be returned in the - * parent's memory. - * @exit_signal: The exit_signal the parent process will be - * sent when the child exits. - * @stack: Specify the location of the stack for the - * child process. - * @stack_size: The size of the stack for the child process. - * @tls: If CLONE_SETTLS is set, the tls descriptor - * is set to tls. + * @flags: Flags for the new process as listed above. + * All flags are valid except for CSIGNAL and + * CLONE_DETACHED. + * @pidfd: If CLONE_PIDFD is set, a pidfd will be + * returned in this argument. + * @child_tid: If CLONE_CHILD_SETTID is set, the TID of the + * child process will be returned in the child's + * memory. + * @parent_tid: If CLONE_PARENT_SETTID is set, the TID of + * the child process will be returned in the + * parent's memory. + * @exit_signal: The exit_signal the parent process will be + * sent when the child exits. + * @stack: Specify the location of the stack for the + * child process. + * @stack_size: The size of the stack for the child process. + * @tls: If CLONE_SETTLS is set, the tls descriptor + * is set to tls. + * @set_tid: Pointer to an array of type *pid_t. The size + * of the array is defined using @set_tid_size. + * This array is used to select PIDs/TIDs for + * newly created processes. The first element in + * this defines the PID in the most nested PID + * namespace. Each additional element in the array + * defines the PID in the parent PID namespace of + * the original PID namespace. If the array has + * less entries than the number of currently + * nested PID namespaces only the PIDs in the + * corresponding namespaces are set. + * @set_tid_size: This defines the size of the array referenced + * in @set_tid. This cannot be larger than the + * kernel's limit of nested PID namespaces. * * The structure is versioned by size and thus extensible. * New struct members must go at the end of the struct and @@ -71,10 +85,13 @@ struct clone_args { __aligned_u64 stack; __aligned_u64 stack_size; __aligned_u64 tls; + __aligned_u64 set_tid; + __aligned_u64 set_tid_size; }; #endif #define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */ +#define CLONE_ARGS_SIZE_VER1 80 /* sizeof second published struct */ /* * Scheduling policies diff --git a/kernel/fork.c b/kernel/fork.c index 954e875e72b1..417570263f1f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2087,7 +2087,8 @@ static __latent_entropy struct task_struct *copy_process( stackleak_task_init(p); if (pid != &init_struct_pid) { - pid = alloc_pid(p->nsproxy->pid_ns_for_children); + pid = alloc_pid(p->nsproxy->pid_ns_for_children, args->set_tid, + args->set_tid_size); if (IS_ERR(pid)) { retval = PTR_ERR(pid); goto bad_fork_cleanup_thread; @@ -2590,6 +2591,7 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs, { int err; struct clone_args args; + pid_t *kset_tid = kargs->set_tid; if (unlikely(usize > PAGE_SIZE)) return -E2BIG; @@ -2600,6 +2602,15 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs, if (err) return err; + if (unlikely(args.set_tid_size > MAX_PID_NS_LEVEL)) + return -EINVAL; + + if (unlikely(!args.set_tid && args.set_tid_size > 0)) + return -EINVAL; + + if (unlikely(args.set_tid && args.set_tid_size == 0)) + return -EINVAL; + /* * Verify that higher 32bits of exit_signal are unset and that * it is a valid signal @@ -2617,8 +2628,16 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs, .stack = args.stack, .stack_size = args.stack_size, .tls = args.tls, + .set_tid_size = args.set_tid_size, }; + if (args.set_tid && + copy_from_user(kset_tid, u64_to_user_ptr(args.set_tid), + (kargs->set_tid_size * sizeof(pid_t)))) + return -EFAULT; + + kargs->set_tid = kset_tid; + return 0; } @@ -2662,6 +2681,9 @@ SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size) int err; struct kernel_clone_args kargs; + pid_t set_tid[MAX_PID_NS_LEVEL]; + + kargs.set_tid = set_tid; err = copy_clone_args_from_user(&kargs, uargs, size); if (err) diff --git a/kernel/pid.c b/kernel/pid.c index 7b5f6c963d72..2278e249141d 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -157,7 +157,8 @@ void free_pid(struct pid *pid) call_rcu(&pid->rcu, delayed_put_pid); } -struct pid *alloc_pid(struct pid_namespace *ns) +struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, + size_t set_tid_size) { struct pid *pid; enum pid_type type; @@ -166,6 +167,17 @@ struct pid *alloc_pid(struct pid_namespace *ns) struct upid *upid; int retval = -ENOMEM; + /* + * set_tid_size contains the size of the set_tid array. Starting at + * the most nested currently active PID namespace it tells alloc_pid() + * which PID to set for a process in that most nested PID namespace + * up to set_tid_size PID namespaces. It does not have to set the PID + * for a process in all nested PID namespaces but set_tid_size must + * never be greater than the current ns->level + 1. + */ + if (set_tid_size > ns->level + 1) + return ERR_PTR(-EINVAL); + pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL); if (!pid) return ERR_PTR(retval); @@ -174,24 +186,54 @@ struct pid *alloc_pid(struct pid_namespace *ns) pid->level = ns->level; for (i = ns->level; i >= 0; i--) { - int pid_min = 1; + int tid = 0; + + if (set_tid_size) { + tid = set_tid[ns->level - i]; + + retval = -EINVAL; + if (tid < 1 || tid >= pid_max) + goto out_free; + /* + * Also fail if a PID != 1 is requested and + * no PID 1 exists. + */ + if (tid != 1 && !tmp->child_reaper) + goto out_free; + retval = -EPERM; + if (!ns_capable(tmp->user_ns, CAP_SYS_ADMIN)) + goto out_free; + set_tid_size--; + } idr_preload(GFP_KERNEL); spin_lock_irq(&pidmap_lock); - /* - * init really needs pid 1, but after reaching the maximum - * wrap back to RESERVED_PIDS - */ - if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS) - pid_min = RESERVED_PIDS; - - /* - * Store a null pointer so find_pid_ns does not find - * a partially initialized PID (see below). - */ - nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min, - pid_max, GFP_ATOMIC); + if (tid) { + nr = idr_alloc(&tmp->idr, NULL, tid, + tid + 1, GFP_ATOMIC); + /* + * If ENOSPC is returned it means that the PID is + * alreay in use. Return EEXIST in that case. + */ + if (nr == -ENOSPC) + nr = -EEXIST; + } else { + int pid_min = 1; + /* + * init really needs pid 1, but after reaching the + * maximum wrap back to RESERVED_PIDS + */ + if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS) + pid_min = RESERVED_PIDS; + + /* + * Store a null pointer so find_pid_ns does not find + * a partially initialized PID (see below). + */ + nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min, + pid_max, GFP_ATOMIC); + } spin_unlock_irq(&pidmap_lock); idr_preload_end(); diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index a6a79f85c81a..d40017e79ebe 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -26,8 +26,6 @@ static DEFINE_MUTEX(pid_caches_mutex); static struct kmem_cache *pid_ns_cachep; -/* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */ -#define MAX_PID_NS_LEVEL 32 /* Write once array, filled from the beginning. */ static struct kmem_cache *pid_cache[MAX_PID_NS_LEVEL]; -- cgit v1.2.3-71-gd317 From d46bca2b5d06cbb5f3e66945080f275bcfab7181 Mon Sep 17 00:00:00 2001 From: Lina Iyer Date: Fri, 15 Nov 2019 15:11:44 -0700 Subject: irqdomain: Add bus token DOMAIN_BUS_WAKEUP A single controller can handle normal interrupts and wake-up interrupts independently, with a different numbering space. It is thus crucial to allow the driver for such a controller discriminate between the two. A simple way to do so is to tag the wake-up irqdomain with a "bus token" that indicates the wake-up domain. This slightly abuses the notion of bus, but also radically simplifies the design of such a driver. Between two evils, we choose the least damaging. Suggested-by: Stephen Boyd Signed-off-by: Lina Iyer Signed-off-by: Marc Zyngier Reviewed-by: Stephen Boyd Link: https://lore.kernel.org/r/1573855915-9841-2-git-send-email-ilina@codeaurora.org --- include/linux/irqdomain.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 583e7abd07f9..3c340dbc5a1f 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -83,6 +83,7 @@ enum irq_domain_bus_token { DOMAIN_BUS_IPI, DOMAIN_BUS_FSL_MC_MSI, DOMAIN_BUS_TI_SCI_INTA_MSI, + DOMAIN_BUS_WAKEUP, }; /** -- cgit v1.2.3-71-gd317 From 4a169a95d885fe5c050bac1a21d43c86ba955bcf Mon Sep 17 00:00:00 2001 From: Maulik Shah Date: Fri, 15 Nov 2019 15:11:49 -0700 Subject: genirq: Introduce irq_chip_get/set_parent_state calls On certain QTI chipsets some GPIOs are direct-connect interrupts to the GIC to be used as regular interrupt lines. When the GPIOs are not used for interrupt generation the interrupt line is disabled. But disabling the interrupt at GIC does not prevent the interrupt to be reported as pending at GIC_ISPEND. Later, when drivers call enable_irq() on the interrupt, an unwanted interrupt occurs. Introduce get and set methods for irqchip's parent to clear it's pending irq state. This then can be invoked by the GPIO interrupt controller on the parents in it hierarchy to clear the interrupt before enabling the interrupt. Signed-off-by: Maulik Shah Signed-off-by: Lina Iyer Signed-off-by: Marc Zyngier Reviewed-by: Stephen Boyd Link: https://lore.kernel.org/r/1573855915-9841-7-git-send-email-ilina@codeaurora.org [updated commit text and minor code fixes] --- include/linux/irq.h | 6 ++++++ kernel/irq/chip.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 50 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index fb301cf29148..7853eb9301f2 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -610,6 +610,12 @@ extern int irq_chip_pm_put(struct irq_data *data); #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY extern void handle_fasteoi_ack_irq(struct irq_desc *desc); extern void handle_fasteoi_mask_irq(struct irq_desc *desc); +extern int irq_chip_set_parent_state(struct irq_data *data, + enum irqchip_irq_state which, + bool val); +extern int irq_chip_get_parent_state(struct irq_data *data, + enum irqchip_irq_state which, + bool *state); extern void irq_chip_enable_parent(struct irq_data *data); extern void irq_chip_disable_parent(struct irq_data *data); extern void irq_chip_ack_parent(struct irq_data *data); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index b76703b2c0af..b3fa2d87d2f3 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -1297,6 +1297,50 @@ EXPORT_SYMBOL_GPL(handle_fasteoi_mask_irq); #endif /* CONFIG_IRQ_FASTEOI_HIERARCHY_HANDLERS */ +/** + * irq_chip_set_parent_state - set the state of a parent interrupt. + * + * @data: Pointer to interrupt specific data + * @which: State to be restored (one of IRQCHIP_STATE_*) + * @val: Value corresponding to @which + * + * Conditional success, if the underlying irqchip does not implement it. + */ +int irq_chip_set_parent_state(struct irq_data *data, + enum irqchip_irq_state which, + bool val) +{ + data = data->parent_data; + + if (!data || !data->chip->irq_set_irqchip_state) + return 0; + + return data->chip->irq_set_irqchip_state(data, which, val); +} +EXPORT_SYMBOL_GPL(irq_chip_set_parent_state); + +/** + * irq_chip_get_parent_state - get the state of a parent interrupt. + * + * @data: Pointer to interrupt specific data + * @which: one of IRQCHIP_STATE_* the caller wants to know + * @state: a pointer to a boolean where the state is to be stored + * + * Conditional success, if the underlying irqchip does not implement it. + */ +int irq_chip_get_parent_state(struct irq_data *data, + enum irqchip_irq_state which, + bool *state) +{ + data = data->parent_data; + + if (!data || !data->chip->irq_get_irqchip_state) + return 0; + + return data->chip->irq_get_irqchip_state(data, which, state); +} +EXPORT_SYMBOL_GPL(irq_chip_get_parent_state); + /** * irq_chip_enable_parent - Enable the parent interrupt (defaults to unmask if * NULL) -- cgit v1.2.3-71-gd317 From 81ef8bf88065b07d597c723ca5b0f1f10a808de4 Mon Sep 17 00:00:00 2001 From: Lina Iyer Date: Fri, 15 Nov 2019 15:11:47 -0700 Subject: irqchip/qcom-pdc: Add irqdomain for wakeup capable GPIOs Introduce a new domain for wakeup capable GPIOs. The domain can be requested using the bus token DOMAIN_BUS_WAKEUP. In the following patches, we will specify PDC as the wakeup-parent for the TLMM GPIO irqchip. Requesting a wakeup GPIO will setup the GPIO and the corresponding PDC interrupt as its parent. Co-developed-by: Stephen Boyd Signed-off-by: Stephen Boyd Signed-off-by: Lina Iyer Signed-off-by: Marc Zyngier Reviewed-by: Stephen Boyd Link: https://lore.kernel.org/r/1573855915-9841-5-git-send-email-ilina@codeaurora.org --- drivers/irqchip/qcom-pdc.c | 104 +++++++++++++++++++++++++++++++++++++++---- include/linux/soc/qcom/irq.h | 21 +++++++++ 2 files changed, 116 insertions(+), 9 deletions(-) create mode 100644 include/linux/soc/qcom/irq.h (limited to 'include/linux') diff --git a/drivers/irqchip/qcom-pdc.c b/drivers/irqchip/qcom-pdc.c index 527c29e212bd..4f2c76229fb7 100644 --- a/drivers/irqchip/qcom-pdc.c +++ b/drivers/irqchip/qcom-pdc.c @@ -13,12 +13,13 @@ #include #include #include +#include #include -#include #include #include #define PDC_MAX_IRQS 168 +#define PDC_MAX_GPIO_IRQS 256 #define CLEAR_INTR(reg, intr) (reg & ~(1 << intr)) #define ENABLE_INTR(reg, intr) (reg | (1 << intr)) @@ -26,6 +27,8 @@ #define IRQ_ENABLE_BANK 0x10 #define IRQ_i_CFG 0x110 +#define PDC_NO_PARENT_IRQ ~0UL + struct pdc_pin_region { u32 pin_base; u32 parent_base; @@ -65,23 +68,35 @@ static void pdc_enable_intr(struct irq_data *d, bool on) static void qcom_pdc_gic_disable(struct irq_data *d) { + if (d->hwirq == GPIO_NO_WAKE_IRQ) + return; + pdc_enable_intr(d, false); irq_chip_disable_parent(d); } static void qcom_pdc_gic_enable(struct irq_data *d) { + if (d->hwirq == GPIO_NO_WAKE_IRQ) + return; + pdc_enable_intr(d, true); irq_chip_enable_parent(d); } static void qcom_pdc_gic_mask(struct irq_data *d) { + if (d->hwirq == GPIO_NO_WAKE_IRQ) + return; + irq_chip_mask_parent(d); } static void qcom_pdc_gic_unmask(struct irq_data *d) { + if (d->hwirq == GPIO_NO_WAKE_IRQ) + return; + irq_chip_unmask_parent(d); } @@ -124,6 +139,9 @@ static int qcom_pdc_gic_set_type(struct irq_data *d, unsigned int type) int pin_out = d->hwirq; enum pdc_irq_config_bits pdc_type; + if (pin_out == GPIO_NO_WAKE_IRQ) + return 0; + switch (type) { case IRQ_TYPE_EDGE_RISING: pdc_type = PDC_EDGE_RISING; @@ -181,8 +199,7 @@ static irq_hw_number_t get_parent_hwirq(int pin) return (region->parent_base + pin - region->pin_base); } - WARN_ON(1); - return ~0UL; + return PDC_NO_PARENT_IRQ; } static int qcom_pdc_translate(struct irq_domain *d, struct irq_fwspec *fwspec, @@ -211,17 +228,17 @@ static int qcom_pdc_alloc(struct irq_domain *domain, unsigned int virq, ret = qcom_pdc_translate(domain, fwspec, &hwirq, &type); if (ret) - return -EINVAL; - - parent_hwirq = get_parent_hwirq(hwirq); - if (parent_hwirq == ~0UL) - return -EINVAL; + return ret; ret = irq_domain_set_hwirq_and_chip(domain, virq, hwirq, &qcom_pdc_gic_chip, NULL); if (ret) return ret; + parent_hwirq = get_parent_hwirq(hwirq); + if (parent_hwirq == PDC_NO_PARENT_IRQ) + return 0; + if (type & IRQ_TYPE_EDGE_BOTH) type = IRQ_TYPE_EDGE_RISING; @@ -244,6 +261,60 @@ static const struct irq_domain_ops qcom_pdc_ops = { .free = irq_domain_free_irqs_common, }; +static int qcom_pdc_gpio_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *data) +{ + struct irq_fwspec *fwspec = data; + struct irq_fwspec parent_fwspec; + irq_hw_number_t hwirq, parent_hwirq; + unsigned int type; + int ret; + + ret = qcom_pdc_translate(domain, fwspec, &hwirq, &type); + if (ret) + return ret; + + ret = irq_domain_set_hwirq_and_chip(domain, virq, hwirq, + &qcom_pdc_gic_chip, NULL); + if (ret) + return ret; + + if (hwirq == GPIO_NO_WAKE_IRQ) + return 0; + + parent_hwirq = get_parent_hwirq(hwirq); + if (parent_hwirq == PDC_NO_PARENT_IRQ) + return 0; + + if (type & IRQ_TYPE_EDGE_BOTH) + type = IRQ_TYPE_EDGE_RISING; + + if (type & IRQ_TYPE_LEVEL_MASK) + type = IRQ_TYPE_LEVEL_HIGH; + + parent_fwspec.fwnode = domain->parent->fwnode; + parent_fwspec.param_count = 3; + parent_fwspec.param[0] = 0; + parent_fwspec.param[1] = parent_hwirq; + parent_fwspec.param[2] = type; + + return irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, + &parent_fwspec); +} + +static int qcom_pdc_gpio_domain_select(struct irq_domain *d, + struct irq_fwspec *fwspec, + enum irq_domain_bus_token bus_token) +{ + return bus_token == DOMAIN_BUS_WAKEUP; +} + +static const struct irq_domain_ops qcom_pdc_gpio_ops = { + .select = qcom_pdc_gpio_domain_select, + .alloc = qcom_pdc_gpio_alloc, + .free = irq_domain_free_irqs_common, +}; + static int pdc_setup_pin_mapping(struct device_node *np) { int ret, n; @@ -282,7 +353,7 @@ static int pdc_setup_pin_mapping(struct device_node *np) static int qcom_pdc_init(struct device_node *node, struct device_node *parent) { - struct irq_domain *parent_domain, *pdc_domain; + struct irq_domain *parent_domain, *pdc_domain, *pdc_gpio_domain; int ret; pdc_base = of_iomap(node, 0); @@ -313,8 +384,23 @@ static int qcom_pdc_init(struct device_node *node, struct device_node *parent) goto fail; } + pdc_gpio_domain = irq_domain_create_hierarchy(parent_domain, + IRQ_DOMAIN_FLAG_QCOM_PDC_WAKEUP, + PDC_MAX_GPIO_IRQS, + of_fwnode_handle(node), + &qcom_pdc_gpio_ops, NULL); + if (!pdc_gpio_domain) { + pr_err("%pOF: PDC domain add failed for GPIO domain\n", node); + ret = -ENOMEM; + goto remove; + } + + irq_domain_update_bus_token(pdc_gpio_domain, DOMAIN_BUS_WAKEUP); + return 0; +remove: + irq_domain_remove(pdc_domain); fail: kfree(pdc_region); iounmap(pdc_base); diff --git a/include/linux/soc/qcom/irq.h b/include/linux/soc/qcom/irq.h new file mode 100644 index 000000000000..637c0bfa89e7 --- /dev/null +++ b/include/linux/soc/qcom/irq.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __QCOM_IRQ_H +#define __QCOM_IRQ_H + +#include + +#define GPIO_NO_WAKE_IRQ ~0U + +/** + * QCOM specific IRQ domain flags that distinguishes the handling of wakeup + * capable interrupts by different interrupt controllers. + * + * IRQ_DOMAIN_FLAG_QCOM_PDC_WAKEUP: Line must be masked at TLMM and the + * interrupt configuration is done at PDC + * IRQ_DOMAIN_FLAG_QCOM_MPM_WAKEUP: Interrupt configuration is handled at TLMM + */ +#define IRQ_DOMAIN_FLAG_QCOM_PDC_WAKEUP (IRQ_DOMAIN_FLAG_NONCORE << 0) +#define IRQ_DOMAIN_FLAG_QCOM_MPM_WAKEUP (IRQ_DOMAIN_FLAG_NONCORE << 1) + +#endif -- cgit v1.2.3-71-gd317 From e35a6ae0eb3a7cc451e8d8db55e9b938a95de416 Mon Sep 17 00:00:00 2001 From: Lina Iyer Date: Fri, 15 Nov 2019 15:11:51 -0700 Subject: pinctrl/msm: Setup GPIO chip in hierarchy Some GPIOs are marked as wakeup capable and are routed to another interrupt controller that is an always-domain and can detect interrupts even when most of the SoC is powered off. The wakeup interrupt controller wakes up the GIC and replays the interrupt at the GIC. Setup the TLMM irqchip in hierarchy with the wakeup interrupt controller and ensure the wakeup GPIOs are handled correctly. Co-developed-by: Maulik Shah Signed-off-by: Lina Iyer Signed-off-by: Marc Zyngier Reviewed-by: Stephen Boyd Link: https://lore.kernel.org/r/1573855915-9841-9-git-send-email-ilina@codeaurora.org ---- Changes in v2: - Address review comments - Fix Co-developed-by tag Changes in v1: - Address minor review comments - Remove redundant call to set irq handler - Move irq_domain_qcom_handle_wakeup() to this patch Changes in RFC v2: - Rebase on top of GPIO hierarchy support in linux-next - Set the chained irq handler for summary line --- drivers/pinctrl/qcom/pinctrl-msm.c | 112 ++++++++++++++++++++++++++++++++++++- drivers/pinctrl/qcom/pinctrl-msm.h | 14 +++++ include/linux/soc/qcom/irq.h | 13 +++++ 3 files changed, 137 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index 763da0be10d6..978838464093 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -23,6 +23,8 @@ #include #include +#include + #include "../core.h" #include "../pinconf.h" #include "pinctrl-msm.h" @@ -44,6 +46,7 @@ * @enabled_irqs: Bitmap of currently enabled irqs. * @dual_edge_irqs: Bitmap of irqs that need sw emulated dual edge * detection. + * @skip_wake_irqs: Skip IRQs that are handled by wakeup interrupt controller * @soc; Reference to soc_data of platform specific data. * @regs: Base addresses for the TLMM tiles. */ @@ -61,6 +64,7 @@ struct msm_pinctrl { DECLARE_BITMAP(dual_edge_irqs, MAX_NR_GPIO); DECLARE_BITMAP(enabled_irqs, MAX_NR_GPIO); + DECLARE_BITMAP(skip_wake_irqs, MAX_NR_GPIO); const struct msm_pinctrl_soc_data *soc; void __iomem *regs[MAX_NR_TILES]; @@ -707,6 +711,12 @@ static void msm_gpio_irq_mask(struct irq_data *d) unsigned long flags; u32 val; + if (d->parent_data) + irq_chip_mask_parent(d); + + if (test_bit(d->hwirq, pctrl->skip_wake_irqs)) + return; + g = &pctrl->soc->groups[d->hwirq]; raw_spin_lock_irqsave(&pctrl->lock, flags); @@ -751,6 +761,12 @@ static void msm_gpio_irq_clear_unmask(struct irq_data *d, bool status_clear) unsigned long flags; u32 val; + if (d->parent_data) + irq_chip_unmask_parent(d); + + if (test_bit(d->hwirq, pctrl->skip_wake_irqs)) + return; + g = &pctrl->soc->groups[d->hwirq]; raw_spin_lock_irqsave(&pctrl->lock, flags); @@ -778,10 +794,35 @@ static void msm_gpio_irq_clear_unmask(struct irq_data *d, bool status_clear) static void msm_gpio_irq_enable(struct irq_data *d) { + /* + * Clear the interrupt that may be pending before we enable + * the line. + * This is especially a problem with the GPIOs routed to the + * PDC. These GPIOs are direct-connect interrupts to the GIC. + * Disabling the interrupt line at the PDC does not prevent + * the interrupt from being latched at the GIC. The state at + * GIC needs to be cleared before enabling. + */ + if (d->parent_data) { + irq_chip_set_parent_state(d, IRQCHIP_STATE_PENDING, 0); + irq_chip_enable_parent(d); + } msm_gpio_irq_clear_unmask(d, true); } +static void msm_gpio_irq_disable(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct msm_pinctrl *pctrl = gpiochip_get_data(gc); + + if (d->parent_data) + irq_chip_disable_parent(d); + + if (!test_bit(d->hwirq, pctrl->skip_wake_irqs)) + msm_gpio_irq_mask(d); +} + static void msm_gpio_irq_unmask(struct irq_data *d) { msm_gpio_irq_clear_unmask(d, false); @@ -795,6 +836,9 @@ static void msm_gpio_irq_ack(struct irq_data *d) unsigned long flags; u32 val; + if (test_bit(d->hwirq, pctrl->skip_wake_irqs)) + return; + g = &pctrl->soc->groups[d->hwirq]; raw_spin_lock_irqsave(&pctrl->lock, flags); @@ -820,6 +864,12 @@ static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int type) unsigned long flags; u32 val; + if (d->parent_data) + irq_chip_set_type_parent(d, type); + + if (test_bit(d->hwirq, pctrl->skip_wake_irqs)) + return 0; + g = &pctrl->soc->groups[d->hwirq]; raw_spin_lock_irqsave(&pctrl->lock, flags); @@ -912,6 +962,15 @@ static int msm_gpio_irq_set_wake(struct irq_data *d, unsigned int on) struct msm_pinctrl *pctrl = gpiochip_get_data(gc); unsigned long flags; + /* + * While they may not wake up when the TLMM is powered off, + * some GPIOs would like to wakeup the system from suspend + * when TLMM is powered on. To allow that, enable the GPIO + * summary line to be wakeup capable at GIC. + */ + if (d->parent_data) + irq_chip_set_wake_parent(d, on); + raw_spin_lock_irqsave(&pctrl->lock, flags); irq_set_irq_wake(pctrl->irq, on); @@ -990,6 +1049,30 @@ static void msm_gpio_irq_handler(struct irq_desc *desc) chained_irq_exit(chip, desc); } +static int msm_gpio_wakeirq(struct gpio_chip *gc, + unsigned int child, + unsigned int child_type, + unsigned int *parent, + unsigned int *parent_type) +{ + struct msm_pinctrl *pctrl = gpiochip_get_data(gc); + const struct msm_gpio_wakeirq_map *map; + int i; + + *parent = GPIO_NO_WAKE_IRQ; + *parent_type = IRQ_TYPE_EDGE_RISING; + + for (i = 0; i < pctrl->soc->nwakeirq_map; i++) { + map = &pctrl->soc->wakeirq_map[i]; + if (map->gpio == child) { + *parent = map->wakeirq; + break; + } + } + + return 0; +} + static bool msm_gpio_needs_valid_mask(struct msm_pinctrl *pctrl) { if (pctrl->soc->reserved_gpios) @@ -1002,8 +1085,10 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl) { struct gpio_chip *chip; struct gpio_irq_chip *girq; - int ret; - unsigned ngpio = pctrl->soc->ngpios; + int i, ret; + unsigned gpio, ngpio = pctrl->soc->ngpios; + struct device_node *np; + bool skip; if (WARN_ON(ngpio > MAX_NR_GPIO)) return -EINVAL; @@ -1020,17 +1105,40 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl) pctrl->irq_chip.name = "msmgpio"; pctrl->irq_chip.irq_enable = msm_gpio_irq_enable; + pctrl->irq_chip.irq_disable = msm_gpio_irq_disable; pctrl->irq_chip.irq_mask = msm_gpio_irq_mask; pctrl->irq_chip.irq_unmask = msm_gpio_irq_unmask; pctrl->irq_chip.irq_ack = msm_gpio_irq_ack; + pctrl->irq_chip.irq_eoi = irq_chip_eoi_parent; pctrl->irq_chip.irq_set_type = msm_gpio_irq_set_type; pctrl->irq_chip.irq_set_wake = msm_gpio_irq_set_wake; pctrl->irq_chip.irq_request_resources = msm_gpio_irq_reqres; pctrl->irq_chip.irq_release_resources = msm_gpio_irq_relres; + np = of_parse_phandle(pctrl->dev->of_node, "wakeup-parent", 0); + if (np) { + chip->irq.parent_domain = irq_find_matching_host(np, + DOMAIN_BUS_WAKEUP); + of_node_put(np); + if (!chip->irq.parent_domain) + return -EPROBE_DEFER; + chip->irq.child_to_parent_hwirq = msm_gpio_wakeirq; + + /* + * Let's skip handling the GPIOs, if the parent irqchip + * is handling the direct connect IRQ of the GPIO. + */ + skip = irq_domain_qcom_handle_wakeup(chip->irq.parent_domain); + for (i = 0; skip && i < pctrl->soc->nwakeirq_map; i++) { + gpio = pctrl->soc->wakeirq_map[i].gpio; + set_bit(gpio, pctrl->skip_wake_irqs); + } + } + girq = &chip->irq; girq->chip = &pctrl->irq_chip; girq->parent_handler = msm_gpio_irq_handler; + girq->fwnode = pctrl->dev->fwnode; girq->num_parents = 1; girq->parents = devm_kcalloc(pctrl->dev, 1, sizeof(*girq->parents), GFP_KERNEL); diff --git a/drivers/pinctrl/qcom/pinctrl-msm.h b/drivers/pinctrl/qcom/pinctrl-msm.h index 48569cda8471..9452da18a78b 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.h +++ b/drivers/pinctrl/qcom/pinctrl-msm.h @@ -91,6 +91,16 @@ struct msm_pingroup { unsigned intr_detection_width:5; }; +/** + * struct msm_gpio_wakeirq_map - Map of GPIOs and their wakeup pins + * @gpio: The GPIOs that are wakeup capable + * @wakeirq: The interrupt at the always-on interrupt controller + */ +struct msm_gpio_wakeirq_map { + unsigned int gpio; + unsigned int wakeirq; +}; + /** * struct msm_pinctrl_soc_data - Qualcomm pin controller driver configuration * @pins: An array describing all pins the pin controller affects. @@ -101,6 +111,8 @@ struct msm_pingroup { * @ngroups: The numbmer of entries in @groups. * @ngpio: The number of pingroups the driver should expose as GPIOs. * @pull_no_keeper: The SoC does not support keeper bias. + * @wakeirq_map: The map of wakeup capable GPIOs and the pin at PDC/MPM + * @nwakeirq_map: The number of entries in @wakeirq_map */ struct msm_pinctrl_soc_data { const struct pinctrl_pin_desc *pins; @@ -114,6 +126,8 @@ struct msm_pinctrl_soc_data { const char *const *tiles; unsigned int ntiles; const int *reserved_gpios; + const struct msm_gpio_wakeirq_map *wakeirq_map; + unsigned int nwakeirq_map; }; extern const struct dev_pm_ops msm_pinctrl_dev_pm_ops; diff --git a/include/linux/soc/qcom/irq.h b/include/linux/soc/qcom/irq.h index 637c0bfa89e7..9e1ece58e55b 100644 --- a/include/linux/soc/qcom/irq.h +++ b/include/linux/soc/qcom/irq.h @@ -18,4 +18,17 @@ #define IRQ_DOMAIN_FLAG_QCOM_PDC_WAKEUP (IRQ_DOMAIN_FLAG_NONCORE << 0) #define IRQ_DOMAIN_FLAG_QCOM_MPM_WAKEUP (IRQ_DOMAIN_FLAG_NONCORE << 1) +/** + * irq_domain_qcom_handle_wakeup: Return if the domain handles interrupt + * configuration + * @d: irq domain + * + * This QCOM specific irq domain call returns if the interrupt controller + * requires the interrupt be masked at the child interrupt controller. + */ +static inline bool irq_domain_qcom_handle_wakeup(const struct irq_domain *d) +{ + return (d->flags & IRQ_DOMAIN_FLAG_QCOM_PDC_WAKEUP); +} + #endif -- cgit v1.2.3-71-gd317 From a079973f462a3d506c6a7f00c770a55b167ed094 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 14 Nov 2019 12:18:40 +0100 Subject: usb: typec: tcpm: Remove tcpc_config configuration mechanism All configuration can and should be done through fwnodes instead of through the tcpc_config struct and there are no existing users left of struct tcpc_config, so lets remove it. Signed-off-by: Hans de Goede Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20191114111840.40876-1-hdegoede@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/tcpm.c | 90 ++----------------------------------------- include/linux/usb/tcpm.h | 41 -------------------- 2 files changed, 3 insertions(+), 128 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index bc9edb4c013b..56fc356bc55c 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -380,9 +380,6 @@ static enum tcpm_state tcpm_default_state(struct tcpm_port *port) return SNK_UNATTACHED; else if (port->try_role == TYPEC_SOURCE) return SRC_UNATTACHED; - else if (port->tcpc->config && - port->tcpc->config->default_role == TYPEC_SINK) - return SNK_UNATTACHED; /* Fall through to return SRC_UNATTACHED */ } else if (port->port_type == TYPEC_PORT_SNK) { return SNK_UNATTACHED; @@ -4122,7 +4119,7 @@ static int tcpm_try_role(struct typec_port *p, int role) mutex_lock(&port->lock); if (tcpc->try_role) ret = tcpc->try_role(tcpc, role); - if (!ret && (!tcpc->config || !tcpc->config->try_role_hw)) + if (!ret) port->try_role = role; port->try_src_count = 0; port->try_snk_count = 0; @@ -4366,34 +4363,6 @@ void tcpm_tcpc_reset(struct tcpm_port *port) } EXPORT_SYMBOL_GPL(tcpm_tcpc_reset); -static int tcpm_copy_pdos(u32 *dest_pdo, const u32 *src_pdo, - unsigned int nr_pdo) -{ - unsigned int i; - - if (nr_pdo > PDO_MAX_OBJECTS) - nr_pdo = PDO_MAX_OBJECTS; - - for (i = 0; i < nr_pdo; i++) - dest_pdo[i] = src_pdo[i]; - - return nr_pdo; -} - -static int tcpm_copy_vdos(u32 *dest_vdo, const u32 *src_vdo, - unsigned int nr_vdo) -{ - unsigned int i; - - if (nr_vdo > VDO_MAX_OBJECTS) - nr_vdo = VDO_MAX_OBJECTS; - - for (i = 0; i < nr_vdo; i++) - dest_vdo[i] = src_vdo[i]; - - return nr_vdo; -} - static int tcpm_fw_get_caps(struct tcpm_port *port, struct fwnode_handle *fwnode) { @@ -4696,35 +4665,10 @@ static int devm_tcpm_psy_register(struct tcpm_port *port) return PTR_ERR_OR_ZERO(port->psy); } -static int tcpm_copy_caps(struct tcpm_port *port, - const struct tcpc_config *tcfg) -{ - if (tcpm_validate_caps(port, tcfg->src_pdo, tcfg->nr_src_pdo) || - tcpm_validate_caps(port, tcfg->snk_pdo, tcfg->nr_snk_pdo)) - return -EINVAL; - - port->nr_src_pdo = tcpm_copy_pdos(port->src_pdo, tcfg->src_pdo, - tcfg->nr_src_pdo); - port->nr_snk_pdo = tcpm_copy_pdos(port->snk_pdo, tcfg->snk_pdo, - tcfg->nr_snk_pdo); - - port->nr_snk_vdo = tcpm_copy_vdos(port->snk_vdo, tcfg->snk_vdo, - tcfg->nr_snk_vdo); - - port->operating_snk_mw = tcfg->operating_snk_mw; - - port->typec_caps.prefer_role = tcfg->default_role; - port->typec_caps.type = tcfg->type; - port->typec_caps.data = tcfg->data; - port->self_powered = tcfg->self_powered; - - return 0; -} - struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc) { struct tcpm_port *port; - int i, err; + int err; if (!dev || !tcpc || !tcpc->get_vbus || !tcpc->set_cc || !tcpc->get_cc || @@ -4757,15 +4701,10 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc) tcpm_debugfs_init(port); err = tcpm_fw_get_caps(port, tcpc->fwnode); - if ((err < 0) && tcpc->config) - err = tcpm_copy_caps(port, tcpc->config); if (err < 0) goto out_destroy_wq; - if (!tcpc->config || !tcpc->config->try_role_hw) - port->try_role = port->typec_caps.prefer_role; - else - port->try_role = TYPEC_NO_PREFERRED_ROLE; + port->try_role = port->typec_caps.prefer_role; port->typec_caps.fwnode = tcpc->fwnode; port->typec_caps.revision = 0x0120; /* Type-C spec release 1.2 */ @@ -4792,29 +4731,6 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc) goto out_role_sw_put; } - if (tcpc->config && tcpc->config->alt_modes) { - const struct typec_altmode_desc *paltmode = tcpc->config->alt_modes; - - i = 0; - while (paltmode->svid && i < ARRAY_SIZE(port->port_altmode)) { - struct typec_altmode *alt; - - alt = typec_port_register_altmode(port->typec_port, - paltmode); - if (IS_ERR(alt)) { - tcpm_log(port, - "%s: failed to register port alternate mode 0x%x", - dev_name(dev), paltmode->svid); - break; - } - typec_altmode_set_drvdata(alt, port); - alt->ops = &tcpm_altmode_ops; - port->port_altmode[i] = alt; - i++; - paltmode++; - } - } - mutex_lock(&port->lock); tcpm_init(port); mutex_unlock(&port->lock); diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h index f516955a0cf4..e7979c01c351 100644 --- a/include/linux/usb/tcpm.h +++ b/include/linux/usb/tcpm.h @@ -46,45 +46,6 @@ enum tcpm_transmit_type { TCPC_TX_BIST_MODE_2 = 7 }; -/** - * struct tcpc_config - Port configuration - * @src_pdo: PDO parameters sent to port partner as response to - * PD_CTRL_GET_SOURCE_CAP message - * @nr_src_pdo: Number of entries in @src_pdo - * @snk_pdo: PDO parameters sent to partner as response to - * PD_CTRL_GET_SINK_CAP message - * @nr_snk_pdo: Number of entries in @snk_pdo - * @operating_snk_mw: - * Required operating sink power in mW - * @type: Port type (TYPEC_PORT_DFP, TYPEC_PORT_UFP, or - * TYPEC_PORT_DRP) - * @default_role: - * Default port role (TYPEC_SINK or TYPEC_SOURCE). - * Set to TYPEC_NO_PREFERRED_ROLE if no default role. - * @try_role_hw:True if try.{Src,Snk} is implemented in hardware - * @alt_modes: List of supported alternate modes - */ -struct tcpc_config { - const u32 *src_pdo; - unsigned int nr_src_pdo; - - const u32 *snk_pdo; - unsigned int nr_snk_pdo; - - const u32 *snk_vdo; - unsigned int nr_snk_vdo; - - unsigned int operating_snk_mw; - - enum typec_port_type type; - enum typec_port_data data; - enum typec_role default_role; - bool try_role_hw; /* try.{src,snk} implemented in hardware */ - bool self_powered; /* port belongs to a self powered device */ - - const struct typec_altmode_desc *alt_modes; -}; - /* Mux state attributes */ #define TCPC_MUX_USB_ENABLED BIT(0) /* USB enabled */ #define TCPC_MUX_DP_ENABLED BIT(1) /* DP enabled */ @@ -92,7 +53,6 @@ struct tcpc_config { /** * struct tcpc_dev - Port configuration and callback functions - * @config: Pointer to port configuration * @fwnode: Pointer to port fwnode * @get_vbus: Called to read current VBUS state * @get_current_limit: @@ -121,7 +81,6 @@ struct tcpc_config { * @mux: Pointer to multiplexer data */ struct tcpc_dev { - const struct tcpc_config *config; struct fwnode_handle *fwnode; int (*init)(struct tcpc_dev *dev); -- cgit v1.2.3-71-gd317 From d63007eb954e425f45766482813738f41db9af45 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Sat, 9 Nov 2019 18:09:53 +0100 Subject: crypto: ablkcipher - remove deprecated and unused ablkcipher support Now that all users of the deprecated ablkcipher interface have been moved to the skcipher interface, ablkcipher is no longer used and can be removed. Reviewed-by: Eric Biggers Signed-off-by: Ard Biesheuvel Signed-off-by: Herbert Xu --- Documentation/crypto/api-skcipher.rst | 20 +- Documentation/crypto/architecture.rst | 2 - Documentation/crypto/crypto_engine.rst | 4 - crypto/Makefile | 4 +- crypto/ablkcipher.c | 407 ------------------------------ crypto/algapi.c | 26 -- crypto/crypto_engine.c | 29 --- crypto/skcipher.c | 106 -------- include/crypto/aead.h | 2 +- include/crypto/algapi.h | 75 ------ include/crypto/engine.h | 4 - include/crypto/hash.h | 2 +- include/crypto/internal/des.h | 12 - include/crypto/internal/skcipher.h | 20 -- include/crypto/skcipher.h | 6 - include/linux/crypto.h | 435 --------------------------------- 16 files changed, 4 insertions(+), 1150 deletions(-) delete mode 100644 crypto/ablkcipher.c (limited to 'include/linux') diff --git a/Documentation/crypto/api-skcipher.rst b/Documentation/crypto/api-skcipher.rst index 56274109ee56..1aaf8985894b 100644 --- a/Documentation/crypto/api-skcipher.rst +++ b/Documentation/crypto/api-skcipher.rst @@ -5,7 +5,7 @@ Block Cipher Algorithm Definitions :doc: Block Cipher Algorithm Definitions .. kernel-doc:: include/linux/crypto.h - :functions: crypto_alg ablkcipher_alg cipher_alg compress_alg + :functions: crypto_alg cipher_alg compress_alg Symmetric Key Cipher API ------------------------ @@ -33,21 +33,3 @@ Single Block Cipher API .. kernel-doc:: include/linux/crypto.h :functions: crypto_alloc_cipher crypto_free_cipher crypto_has_cipher crypto_cipher_blocksize crypto_cipher_setkey crypto_cipher_encrypt_one crypto_cipher_decrypt_one - -Asynchronous Block Cipher API - Deprecated ------------------------------------------- - -.. kernel-doc:: include/linux/crypto.h - :doc: Asynchronous Block Cipher API - -.. kernel-doc:: include/linux/crypto.h - :functions: crypto_free_ablkcipher crypto_ablkcipher_ivsize crypto_ablkcipher_blocksize crypto_ablkcipher_setkey crypto_ablkcipher_reqtfm crypto_ablkcipher_encrypt crypto_ablkcipher_decrypt - -Asynchronous Cipher Request Handle - Deprecated ------------------------------------------------ - -.. kernel-doc:: include/linux/crypto.h - :doc: Asynchronous Cipher Request Handle - -.. kernel-doc:: include/linux/crypto.h - :functions: crypto_ablkcipher_reqsize ablkcipher_request_set_tfm ablkcipher_request_alloc ablkcipher_request_free ablkcipher_request_set_callback ablkcipher_request_set_crypt diff --git a/Documentation/crypto/architecture.rst b/Documentation/crypto/architecture.rst index da90bb006ab0..646c3380a7ed 100644 --- a/Documentation/crypto/architecture.rst +++ b/Documentation/crypto/architecture.rst @@ -201,8 +201,6 @@ the aforementioned cipher types: - CRYPTO_ALG_TYPE_AEAD Authenticated Encryption with Associated Data (MAC) -- CRYPTO_ALG_TYPE_ABLKCIPHER Asynchronous multi-block cipher - - CRYPTO_ALG_TYPE_KPP Key-agreement Protocol Primitive (KPP) such as an ECDH or DH implementation diff --git a/Documentation/crypto/crypto_engine.rst b/Documentation/crypto/crypto_engine.rst index 3baa23c2cd08..25cf9836c336 100644 --- a/Documentation/crypto/crypto_engine.rst +++ b/Documentation/crypto/crypto_engine.rst @@ -63,8 +63,6 @@ request by using: When your driver receives a crypto_request, you must to transfer it to the crypto engine via one of: -* crypto_transfer_ablkcipher_request_to_engine() - * crypto_transfer_aead_request_to_engine() * crypto_transfer_akcipher_request_to_engine() @@ -75,8 +73,6 @@ the crypto engine via one of: At the end of the request process, a call to one of the following functions is needed: -* crypto_finalize_ablkcipher_request() - * crypto_finalize_aead_request() * crypto_finalize_akcipher_request() diff --git a/crypto/Makefile b/crypto/Makefile index d627ec4e0522..4ca12b6044f7 100644 --- a/crypto/Makefile +++ b/crypto/Makefile @@ -16,9 +16,7 @@ obj-$(CONFIG_CRYPTO_ALGAPI2) += crypto_algapi.o obj-$(CONFIG_CRYPTO_AEAD2) += aead.o obj-$(CONFIG_CRYPTO_AEAD2) += geniv.o -crypto_skcipher-y := ablkcipher.o -crypto_skcipher-y += skcipher.o -obj-$(CONFIG_CRYPTO_SKCIPHER2) += crypto_skcipher.o +obj-$(CONFIG_CRYPTO_SKCIPHER2) += skcipher.o obj-$(CONFIG_CRYPTO_SEQIV) += seqiv.o obj-$(CONFIG_CRYPTO_ECHAINIV) += echainiv.o diff --git a/crypto/ablkcipher.c b/crypto/ablkcipher.c deleted file mode 100644 index 072b5646a0a3..000000000000 --- a/crypto/ablkcipher.c +++ /dev/null @@ -1,407 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Asynchronous block chaining cipher operations. - * - * This is the asynchronous version of blkcipher.c indicating completion - * via a callback. - * - * Copyright (c) 2006 Herbert Xu - */ - -#include -#include -#include -#include -#include -#include -#include -#include - -#include - -#include "internal.h" - -struct ablkcipher_buffer { - struct list_head entry; - struct scatter_walk dst; - unsigned int len; - void *data; -}; - -enum { - ABLKCIPHER_WALK_SLOW = 1 << 0, -}; - -static inline void ablkcipher_buffer_write(struct ablkcipher_buffer *p) -{ - scatterwalk_copychunks(p->data, &p->dst, p->len, 1); -} - -void __ablkcipher_walk_complete(struct ablkcipher_walk *walk) -{ - struct ablkcipher_buffer *p, *tmp; - - list_for_each_entry_safe(p, tmp, &walk->buffers, entry) { - ablkcipher_buffer_write(p); - list_del(&p->entry); - kfree(p); - } -} -EXPORT_SYMBOL_GPL(__ablkcipher_walk_complete); - -static inline void ablkcipher_queue_write(struct ablkcipher_walk *walk, - struct ablkcipher_buffer *p) -{ - p->dst = walk->out; - list_add_tail(&p->entry, &walk->buffers); -} - -/* Get a spot of the specified length that does not straddle a page. - * The caller needs to ensure that there is enough space for this operation. - */ -static inline u8 *ablkcipher_get_spot(u8 *start, unsigned int len) -{ - u8 *end_page = (u8 *)(((unsigned long)(start + len - 1)) & PAGE_MASK); - - return max(start, end_page); -} - -static inline void ablkcipher_done_slow(struct ablkcipher_walk *walk, - unsigned int n) -{ - for (;;) { - unsigned int len_this_page = scatterwalk_pagelen(&walk->out); - - if (len_this_page > n) - len_this_page = n; - scatterwalk_advance(&walk->out, n); - if (n == len_this_page) - break; - n -= len_this_page; - scatterwalk_start(&walk->out, sg_next(walk->out.sg)); - } -} - -static inline void ablkcipher_done_fast(struct ablkcipher_walk *walk, - unsigned int n) -{ - scatterwalk_advance(&walk->in, n); - scatterwalk_advance(&walk->out, n); -} - -static int ablkcipher_walk_next(struct ablkcipher_request *req, - struct ablkcipher_walk *walk); - -int ablkcipher_walk_done(struct ablkcipher_request *req, - struct ablkcipher_walk *walk, int err) -{ - struct crypto_tfm *tfm = req->base.tfm; - unsigned int n; /* bytes processed */ - bool more; - - if (unlikely(err < 0)) - goto finish; - - n = walk->nbytes - err; - walk->total -= n; - more = (walk->total != 0); - - if (likely(!(walk->flags & ABLKCIPHER_WALK_SLOW))) { - ablkcipher_done_fast(walk, n); - } else { - if (WARN_ON(err)) { - /* unexpected case; didn't process all bytes */ - err = -EINVAL; - goto finish; - } - ablkcipher_done_slow(walk, n); - } - - scatterwalk_done(&walk->in, 0, more); - scatterwalk_done(&walk->out, 1, more); - - if (more) { - crypto_yield(req->base.flags); - return ablkcipher_walk_next(req, walk); - } - err = 0; -finish: - walk->nbytes = 0; - if (walk->iv != req->info) - memcpy(req->info, walk->iv, tfm->crt_ablkcipher.ivsize); - kfree(walk->iv_buffer); - return err; -} -EXPORT_SYMBOL_GPL(ablkcipher_walk_done); - -static inline int ablkcipher_next_slow(struct ablkcipher_request *req, - struct ablkcipher_walk *walk, - unsigned int bsize, - unsigned int alignmask, - void **src_p, void **dst_p) -{ - unsigned aligned_bsize = ALIGN(bsize, alignmask + 1); - struct ablkcipher_buffer *p; - void *src, *dst, *base; - unsigned int n; - - n = ALIGN(sizeof(struct ablkcipher_buffer), alignmask + 1); - n += (aligned_bsize * 3 - (alignmask + 1) + - (alignmask & ~(crypto_tfm_ctx_alignment() - 1))); - - p = kmalloc(n, GFP_ATOMIC); - if (!p) - return ablkcipher_walk_done(req, walk, -ENOMEM); - - base = p + 1; - - dst = (u8 *)ALIGN((unsigned long)base, alignmask + 1); - src = dst = ablkcipher_get_spot(dst, bsize); - - p->len = bsize; - p->data = dst; - - scatterwalk_copychunks(src, &walk->in, bsize, 0); - - ablkcipher_queue_write(walk, p); - - walk->nbytes = bsize; - walk->flags |= ABLKCIPHER_WALK_SLOW; - - *src_p = src; - *dst_p = dst; - - return 0; -} - -static inline int ablkcipher_copy_iv(struct ablkcipher_walk *walk, - struct crypto_tfm *tfm, - unsigned int alignmask) -{ - unsigned bs = walk->blocksize; - unsigned int ivsize = tfm->crt_ablkcipher.ivsize; - unsigned aligned_bs = ALIGN(bs, alignmask + 1); - unsigned int size = aligned_bs * 2 + ivsize + max(aligned_bs, ivsize) - - (alignmask + 1); - u8 *iv; - - size += alignmask & ~(crypto_tfm_ctx_alignment() - 1); - walk->iv_buffer = kmalloc(size, GFP_ATOMIC); - if (!walk->iv_buffer) - return -ENOMEM; - - iv = (u8 *)ALIGN((unsigned long)walk->iv_buffer, alignmask + 1); - iv = ablkcipher_get_spot(iv, bs) + aligned_bs; - iv = ablkcipher_get_spot(iv, bs) + aligned_bs; - iv = ablkcipher_get_spot(iv, ivsize); - - walk->iv = memcpy(iv, walk->iv, ivsize); - return 0; -} - -static inline int ablkcipher_next_fast(struct ablkcipher_request *req, - struct ablkcipher_walk *walk) -{ - walk->src.page = scatterwalk_page(&walk->in); - walk->src.offset = offset_in_page(walk->in.offset); - walk->dst.page = scatterwalk_page(&walk->out); - walk->dst.offset = offset_in_page(walk->out.offset); - - return 0; -} - -static int ablkcipher_walk_next(struct ablkcipher_request *req, - struct ablkcipher_walk *walk) -{ - struct crypto_tfm *tfm = req->base.tfm; - unsigned int alignmask, bsize, n; - void *src, *dst; - int err; - - alignmask = crypto_tfm_alg_alignmask(tfm); - n = walk->total; - if (unlikely(n < crypto_tfm_alg_blocksize(tfm))) { - req->base.flags |= CRYPTO_TFM_RES_BAD_BLOCK_LEN; - return ablkcipher_walk_done(req, walk, -EINVAL); - } - - walk->flags &= ~ABLKCIPHER_WALK_SLOW; - src = dst = NULL; - - bsize = min(walk->blocksize, n); - n = scatterwalk_clamp(&walk->in, n); - n = scatterwalk_clamp(&walk->out, n); - - if (n < bsize || - !scatterwalk_aligned(&walk->in, alignmask) || - !scatterwalk_aligned(&walk->out, alignmask)) { - err = ablkcipher_next_slow(req, walk, bsize, alignmask, - &src, &dst); - goto set_phys_lowmem; - } - - walk->nbytes = n; - - return ablkcipher_next_fast(req, walk); - -set_phys_lowmem: - if (err >= 0) { - walk->src.page = virt_to_page(src); - walk->dst.page = virt_to_page(dst); - walk->src.offset = ((unsigned long)src & (PAGE_SIZE - 1)); - walk->dst.offset = ((unsigned long)dst & (PAGE_SIZE - 1)); - } - - return err; -} - -static int ablkcipher_walk_first(struct ablkcipher_request *req, - struct ablkcipher_walk *walk) -{ - struct crypto_tfm *tfm = req->base.tfm; - unsigned int alignmask; - - alignmask = crypto_tfm_alg_alignmask(tfm); - if (WARN_ON_ONCE(in_irq())) - return -EDEADLK; - - walk->iv = req->info; - walk->nbytes = walk->total; - if (unlikely(!walk->total)) - return 0; - - walk->iv_buffer = NULL; - if (unlikely(((unsigned long)walk->iv & alignmask))) { - int err = ablkcipher_copy_iv(walk, tfm, alignmask); - - if (err) - return err; - } - - scatterwalk_start(&walk->in, walk->in.sg); - scatterwalk_start(&walk->out, walk->out.sg); - - return ablkcipher_walk_next(req, walk); -} - -int ablkcipher_walk_phys(struct ablkcipher_request *req, - struct ablkcipher_walk *walk) -{ - walk->blocksize = crypto_tfm_alg_blocksize(req->base.tfm); - return ablkcipher_walk_first(req, walk); -} -EXPORT_SYMBOL_GPL(ablkcipher_walk_phys); - -static int setkey_unaligned(struct crypto_ablkcipher *tfm, const u8 *key, - unsigned int keylen) -{ - struct ablkcipher_alg *cipher = crypto_ablkcipher_alg(tfm); - unsigned long alignmask = crypto_ablkcipher_alignmask(tfm); - int ret; - u8 *buffer, *alignbuffer; - unsigned long absize; - - absize = keylen + alignmask; - buffer = kmalloc(absize, GFP_ATOMIC); - if (!buffer) - return -ENOMEM; - - alignbuffer = (u8 *)ALIGN((unsigned long)buffer, alignmask + 1); - memcpy(alignbuffer, key, keylen); - ret = cipher->setkey(tfm, alignbuffer, keylen); - memset(alignbuffer, 0, keylen); - kfree(buffer); - return ret; -} - -static int setkey(struct crypto_ablkcipher *tfm, const u8 *key, - unsigned int keylen) -{ - struct ablkcipher_alg *cipher = crypto_ablkcipher_alg(tfm); - unsigned long alignmask = crypto_ablkcipher_alignmask(tfm); - - if (keylen < cipher->min_keysize || keylen > cipher->max_keysize) { - crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); - return -EINVAL; - } - - if ((unsigned long)key & alignmask) - return setkey_unaligned(tfm, key, keylen); - - return cipher->setkey(tfm, key, keylen); -} - -static unsigned int crypto_ablkcipher_ctxsize(struct crypto_alg *alg, u32 type, - u32 mask) -{ - return alg->cra_ctxsize; -} - -static int crypto_init_ablkcipher_ops(struct crypto_tfm *tfm, u32 type, - u32 mask) -{ - struct ablkcipher_alg *alg = &tfm->__crt_alg->cra_ablkcipher; - struct ablkcipher_tfm *crt = &tfm->crt_ablkcipher; - - if (alg->ivsize > PAGE_SIZE / 8) - return -EINVAL; - - crt->setkey = setkey; - crt->encrypt = alg->encrypt; - crt->decrypt = alg->decrypt; - crt->base = __crypto_ablkcipher_cast(tfm); - crt->ivsize = alg->ivsize; - - return 0; -} - -#ifdef CONFIG_NET -static int crypto_ablkcipher_report(struct sk_buff *skb, struct crypto_alg *alg) -{ - struct crypto_report_blkcipher rblkcipher; - - memset(&rblkcipher, 0, sizeof(rblkcipher)); - - strscpy(rblkcipher.type, "ablkcipher", sizeof(rblkcipher.type)); - strscpy(rblkcipher.geniv, "", sizeof(rblkcipher.geniv)); - - rblkcipher.blocksize = alg->cra_blocksize; - rblkcipher.min_keysize = alg->cra_ablkcipher.min_keysize; - rblkcipher.max_keysize = alg->cra_ablkcipher.max_keysize; - rblkcipher.ivsize = alg->cra_ablkcipher.ivsize; - - return nla_put(skb, CRYPTOCFGA_REPORT_BLKCIPHER, - sizeof(rblkcipher), &rblkcipher); -} -#else -static int crypto_ablkcipher_report(struct sk_buff *skb, struct crypto_alg *alg) -{ - return -ENOSYS; -} -#endif - -static void crypto_ablkcipher_show(struct seq_file *m, struct crypto_alg *alg) - __maybe_unused; -static void crypto_ablkcipher_show(struct seq_file *m, struct crypto_alg *alg) -{ - struct ablkcipher_alg *ablkcipher = &alg->cra_ablkcipher; - - seq_printf(m, "type : ablkcipher\n"); - seq_printf(m, "async : %s\n", alg->cra_flags & CRYPTO_ALG_ASYNC ? - "yes" : "no"); - seq_printf(m, "blocksize : %u\n", alg->cra_blocksize); - seq_printf(m, "min keysize : %u\n", ablkcipher->min_keysize); - seq_printf(m, "max keysize : %u\n", ablkcipher->max_keysize); - seq_printf(m, "ivsize : %u\n", ablkcipher->ivsize); - seq_printf(m, "geniv : \n"); -} - -const struct crypto_type crypto_ablkcipher_type = { - .ctxsize = crypto_ablkcipher_ctxsize, - .init = crypto_init_ablkcipher_ops, -#ifdef CONFIG_PROC_FS - .show = crypto_ablkcipher_show, -#endif - .report = crypto_ablkcipher_report, -}; -EXPORT_SYMBOL_GPL(crypto_ablkcipher_type); diff --git a/crypto/algapi.c b/crypto/algapi.c index de30ddc952d8..b052f38edba6 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -1052,32 +1052,6 @@ void crypto_stats_get(struct crypto_alg *alg) } EXPORT_SYMBOL_GPL(crypto_stats_get); -void crypto_stats_ablkcipher_encrypt(unsigned int nbytes, int ret, - struct crypto_alg *alg) -{ - if (ret && ret != -EINPROGRESS && ret != -EBUSY) { - atomic64_inc(&alg->stats.cipher.err_cnt); - } else { - atomic64_inc(&alg->stats.cipher.encrypt_cnt); - atomic64_add(nbytes, &alg->stats.cipher.encrypt_tlen); - } - crypto_alg_put(alg); -} -EXPORT_SYMBOL_GPL(crypto_stats_ablkcipher_encrypt); - -void crypto_stats_ablkcipher_decrypt(unsigned int nbytes, int ret, - struct crypto_alg *alg) -{ - if (ret && ret != -EINPROGRESS && ret != -EBUSY) { - atomic64_inc(&alg->stats.cipher.err_cnt); - } else { - atomic64_inc(&alg->stats.cipher.decrypt_cnt); - atomic64_add(nbytes, &alg->stats.cipher.decrypt_tlen); - } - crypto_alg_put(alg); -} -EXPORT_SYMBOL_GPL(crypto_stats_ablkcipher_decrypt); - void crypto_stats_aead_encrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret) { diff --git a/crypto/crypto_engine.c b/crypto/crypto_engine.c index 055d17977280..eb029ff1e05a 100644 --- a/crypto/crypto_engine.c +++ b/crypto/crypto_engine.c @@ -213,20 +213,6 @@ static int crypto_transfer_request_to_engine(struct crypto_engine *engine, return crypto_transfer_request(engine, req, true); } -/** - * crypto_transfer_ablkcipher_request_to_engine - transfer one ablkcipher_request - * to list into the engine queue - * @engine: the hardware engine - * @req: the request need to be listed into the engine queue - * TODO: Remove this function when skcipher conversion is finished - */ -int crypto_transfer_ablkcipher_request_to_engine(struct crypto_engine *engine, - struct ablkcipher_request *req) -{ - return crypto_transfer_request_to_engine(engine, &req->base); -} -EXPORT_SYMBOL_GPL(crypto_transfer_ablkcipher_request_to_engine); - /** * crypto_transfer_aead_request_to_engine - transfer one aead_request * to list into the engine queue @@ -279,21 +265,6 @@ int crypto_transfer_skcipher_request_to_engine(struct crypto_engine *engine, } EXPORT_SYMBOL_GPL(crypto_transfer_skcipher_request_to_engine); -/** - * crypto_finalize_ablkcipher_request - finalize one ablkcipher_request if - * the request is done - * @engine: the hardware engine - * @req: the request need to be finalized - * @err: error number - * TODO: Remove this function when skcipher conversion is finished - */ -void crypto_finalize_ablkcipher_request(struct crypto_engine *engine, - struct ablkcipher_request *req, int err) -{ - return crypto_finalize_request(engine, &req->base, err); -} -EXPORT_SYMBOL_GPL(crypto_finalize_ablkcipher_request); - /** * crypto_finalize_aead_request - finalize one aead_request if * the request is done diff --git a/crypto/skcipher.c b/crypto/skcipher.c index 1ce8fbb85f95..13da43c84b64 100644 --- a/crypto/skcipher.c +++ b/crypto/skcipher.c @@ -580,9 +580,6 @@ EXPORT_SYMBOL_GPL(skcipher_walk_aead_decrypt); static unsigned int crypto_skcipher_extsize(struct crypto_alg *alg) { - if (alg->cra_type == &crypto_ablkcipher_type) - return sizeof(struct crypto_ablkcipher *); - return crypto_alg_extsize(alg); } @@ -592,106 +589,6 @@ static void skcipher_set_needkey(struct crypto_skcipher *tfm) crypto_skcipher_set_flags(tfm, CRYPTO_TFM_NEED_KEY); } -static int skcipher_setkey_ablkcipher(struct crypto_skcipher *tfm, - const u8 *key, unsigned int keylen) -{ - struct crypto_ablkcipher **ctx = crypto_skcipher_ctx(tfm); - struct crypto_ablkcipher *ablkcipher = *ctx; - int err; - - crypto_ablkcipher_clear_flags(ablkcipher, ~0); - crypto_ablkcipher_set_flags(ablkcipher, - crypto_skcipher_get_flags(tfm) & - CRYPTO_TFM_REQ_MASK); - err = crypto_ablkcipher_setkey(ablkcipher, key, keylen); - crypto_skcipher_set_flags(tfm, - crypto_ablkcipher_get_flags(ablkcipher) & - CRYPTO_TFM_RES_MASK); - if (unlikely(err)) { - skcipher_set_needkey(tfm); - return err; - } - - crypto_skcipher_clear_flags(tfm, CRYPTO_TFM_NEED_KEY); - return 0; -} - -static int skcipher_crypt_ablkcipher(struct skcipher_request *req, - int (*crypt)(struct ablkcipher_request *)) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct crypto_ablkcipher **ctx = crypto_skcipher_ctx(tfm); - struct ablkcipher_request *subreq = skcipher_request_ctx(req); - - ablkcipher_request_set_tfm(subreq, *ctx); - ablkcipher_request_set_callback(subreq, skcipher_request_flags(req), - req->base.complete, req->base.data); - ablkcipher_request_set_crypt(subreq, req->src, req->dst, req->cryptlen, - req->iv); - - return crypt(subreq); -} - -static int skcipher_encrypt_ablkcipher(struct skcipher_request *req) -{ - struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req); - struct crypto_tfm *tfm = crypto_skcipher_tfm(skcipher); - struct ablkcipher_alg *alg = &tfm->__crt_alg->cra_ablkcipher; - - return skcipher_crypt_ablkcipher(req, alg->encrypt); -} - -static int skcipher_decrypt_ablkcipher(struct skcipher_request *req) -{ - struct crypto_skcipher *skcipher = crypto_skcipher_reqtfm(req); - struct crypto_tfm *tfm = crypto_skcipher_tfm(skcipher); - struct ablkcipher_alg *alg = &tfm->__crt_alg->cra_ablkcipher; - - return skcipher_crypt_ablkcipher(req, alg->decrypt); -} - -static void crypto_exit_skcipher_ops_ablkcipher(struct crypto_tfm *tfm) -{ - struct crypto_ablkcipher **ctx = crypto_tfm_ctx(tfm); - - crypto_free_ablkcipher(*ctx); -} - -static int crypto_init_skcipher_ops_ablkcipher(struct crypto_tfm *tfm) -{ - struct crypto_alg *calg = tfm->__crt_alg; - struct crypto_skcipher *skcipher = __crypto_skcipher_cast(tfm); - struct crypto_ablkcipher **ctx = crypto_tfm_ctx(tfm); - struct crypto_ablkcipher *ablkcipher; - struct crypto_tfm *abtfm; - - if (!crypto_mod_get(calg)) - return -EAGAIN; - - abtfm = __crypto_alloc_tfm(calg, 0, 0); - if (IS_ERR(abtfm)) { - crypto_mod_put(calg); - return PTR_ERR(abtfm); - } - - ablkcipher = __crypto_ablkcipher_cast(abtfm); - *ctx = ablkcipher; - tfm->exit = crypto_exit_skcipher_ops_ablkcipher; - - skcipher->setkey = skcipher_setkey_ablkcipher; - skcipher->encrypt = skcipher_encrypt_ablkcipher; - skcipher->decrypt = skcipher_decrypt_ablkcipher; - - skcipher->ivsize = crypto_ablkcipher_ivsize(ablkcipher); - skcipher->reqsize = crypto_ablkcipher_reqsize(ablkcipher) + - sizeof(struct ablkcipher_request); - skcipher->keysize = calg->cra_ablkcipher.max_keysize; - - skcipher_set_needkey(skcipher); - - return 0; -} - static int skcipher_setkey_unaligned(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) { @@ -786,9 +683,6 @@ static int crypto_skcipher_init_tfm(struct crypto_tfm *tfm) struct crypto_skcipher *skcipher = __crypto_skcipher_cast(tfm); struct skcipher_alg *alg = crypto_skcipher_alg(skcipher); - if (tfm->__crt_alg->cra_type == &crypto_ablkcipher_type) - return crypto_init_skcipher_ops_ablkcipher(tfm); - skcipher->setkey = skcipher_setkey; skcipher->encrypt = alg->encrypt; skcipher->decrypt = alg->decrypt; diff --git a/include/crypto/aead.h b/include/crypto/aead.h index 3c245b1859e7..a3bdadf6221e 100644 --- a/include/crypto/aead.h +++ b/include/crypto/aead.h @@ -321,7 +321,7 @@ int crypto_aead_encrypt(struct aead_request *req); /** * crypto_aead_decrypt() - decrypt ciphertext - * @req: reference to the ablkcipher_request handle that holds all information + * @req: reference to the aead_request handle that holds all information * needed to perform the cipher operation * * Decrypt ciphertext data using the aead_request handle. That data structure diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h index cadc5257c612..5cd846defdd6 100644 --- a/include/crypto/algapi.h +++ b/include/crypto/algapi.h @@ -85,25 +85,6 @@ struct scatter_walk { unsigned int offset; }; -struct ablkcipher_walk { - struct { - struct page *page; - unsigned int offset; - } src, dst; - - struct scatter_walk in; - unsigned int nbytes; - struct scatter_walk out; - unsigned int total; - struct list_head buffers; - u8 *iv_buffer; - u8 *iv; - int flags; - unsigned int blocksize; -}; - -extern const struct crypto_type crypto_ablkcipher_type; - void crypto_mod_put(struct crypto_alg *alg); int crypto_register_template(struct crypto_template *tmpl); @@ -202,12 +183,6 @@ static inline void crypto_xor_cpy(u8 *dst, const u8 *src1, const u8 *src2, } } -int ablkcipher_walk_done(struct ablkcipher_request *req, - struct ablkcipher_walk *walk, int err); -int ablkcipher_walk_phys(struct ablkcipher_request *req, - struct ablkcipher_walk *walk); -void __ablkcipher_walk_complete(struct ablkcipher_walk *walk); - static inline void *crypto_tfm_ctx_aligned(struct crypto_tfm *tfm) { return PTR_ALIGN(crypto_tfm_ctx(tfm), @@ -225,22 +200,6 @@ static inline void *crypto_instance_ctx(struct crypto_instance *inst) return inst->__ctx; } -static inline struct ablkcipher_alg *crypto_ablkcipher_alg( - struct crypto_ablkcipher *tfm) -{ - return &crypto_ablkcipher_tfm(tfm)->__crt_alg->cra_ablkcipher; -} - -static inline void *crypto_ablkcipher_ctx(struct crypto_ablkcipher *tfm) -{ - return crypto_tfm_ctx(&tfm->base); -} - -static inline void *crypto_ablkcipher_ctx_aligned(struct crypto_ablkcipher *tfm) -{ - return crypto_tfm_ctx_aligned(&tfm->base); -} - static inline struct crypto_cipher *crypto_spawn_cipher( struct crypto_spawn *spawn) { @@ -255,23 +214,6 @@ static inline struct cipher_alg *crypto_cipher_alg(struct crypto_cipher *tfm) return &crypto_cipher_tfm(tfm)->__crt_alg->cra_cipher; } -static inline void ablkcipher_walk_init(struct ablkcipher_walk *walk, - struct scatterlist *dst, - struct scatterlist *src, - unsigned int nbytes) -{ - walk->in.sg = src; - walk->out.sg = dst; - walk->total = nbytes; - INIT_LIST_HEAD(&walk->buffers); -} - -static inline void ablkcipher_walk_complete(struct ablkcipher_walk *walk) -{ - if (unlikely(!list_empty(&walk->buffers))) - __ablkcipher_walk_complete(walk); -} - static inline struct crypto_async_request *crypto_get_backlog( struct crypto_queue *queue) { @@ -279,23 +221,6 @@ static inline struct crypto_async_request *crypto_get_backlog( container_of(queue->backlog, struct crypto_async_request, list); } -static inline int ablkcipher_enqueue_request(struct crypto_queue *queue, - struct ablkcipher_request *request) -{ - return crypto_enqueue_request(queue, &request->base); -} - -static inline struct ablkcipher_request *ablkcipher_dequeue_request( - struct crypto_queue *queue) -{ - return ablkcipher_request_cast(crypto_dequeue_request(queue)); -} - -static inline void *ablkcipher_request_ctx(struct ablkcipher_request *req) -{ - return req->__ctx; -} - static inline struct crypto_alg *crypto_get_attr_alg(struct rtattr **tb, u32 type, u32 mask) { diff --git a/include/crypto/engine.h b/include/crypto/engine.h index 84c708bba00b..e29cd67f93c7 100644 --- a/include/crypto/engine.h +++ b/include/crypto/engine.h @@ -83,8 +83,6 @@ struct crypto_engine_ctx { struct crypto_engine_op op; }; -int crypto_transfer_ablkcipher_request_to_engine(struct crypto_engine *engine, - struct ablkcipher_request *req); int crypto_transfer_aead_request_to_engine(struct crypto_engine *engine, struct aead_request *req); int crypto_transfer_akcipher_request_to_engine(struct crypto_engine *engine, @@ -93,8 +91,6 @@ int crypto_transfer_hash_request_to_engine(struct crypto_engine *engine, struct ahash_request *req); int crypto_transfer_skcipher_request_to_engine(struct crypto_engine *engine, struct skcipher_request *req); -void crypto_finalize_ablkcipher_request(struct crypto_engine *engine, - struct ablkcipher_request *req, int err); void crypto_finalize_aead_request(struct crypto_engine *engine, struct aead_request *req, int err); void crypto_finalize_akcipher_request(struct crypto_engine *engine, diff --git a/include/crypto/hash.h b/include/crypto/hash.h index d52b95b75ae4..fe7f73bad1e2 100644 --- a/include/crypto/hash.h +++ b/include/crypto/hash.h @@ -227,7 +227,7 @@ struct crypto_shash { * CRYPTO_ALG_TYPE_AHASH (listed as type "ahash" in /proc/crypto) * * The asynchronous cipher operation discussion provided for the - * CRYPTO_ALG_TYPE_ABLKCIPHER API applies here as well. + * CRYPTO_ALG_TYPE_SKCIPHER API applies here as well. */ static inline struct crypto_ahash *__crypto_ahash_cast(struct crypto_tfm *tfm) diff --git a/include/crypto/internal/des.h b/include/crypto/internal/des.h index 81ea1a425e9c..f62a2bb1866b 100644 --- a/include/crypto/internal/des.h +++ b/include/crypto/internal/des.h @@ -117,18 +117,6 @@ static inline int verify_skcipher_des3_key(struct crypto_skcipher *tfm, return crypto_des3_ede_verify_key(crypto_skcipher_tfm(tfm), key); } -static inline int verify_ablkcipher_des_key(struct crypto_ablkcipher *tfm, - const u8 *key) -{ - return crypto_des_verify_key(crypto_ablkcipher_tfm(tfm), key); -} - -static inline int verify_ablkcipher_des3_key(struct crypto_ablkcipher *tfm, - const u8 *key) -{ - return crypto_des3_ede_verify_key(crypto_ablkcipher_tfm(tfm), key); -} - static inline int verify_aead_des_key(struct crypto_aead *tfm, const u8 *key, int keylen) { diff --git a/include/crypto/internal/skcipher.h b/include/crypto/internal/skcipher.h index 454e898d5f5f..921c409fe1b1 100644 --- a/include/crypto/internal/skcipher.h +++ b/include/crypto/internal/skcipher.h @@ -153,17 +153,6 @@ static inline void skcipher_walk_abort(struct skcipher_walk *walk) skcipher_walk_done(walk, -ECANCELED); } -static inline void ablkcipher_request_complete(struct ablkcipher_request *req, - int err) -{ - req->base.complete(&req->base, err); -} - -static inline u32 ablkcipher_request_flags(struct ablkcipher_request *req) -{ - return req->base.flags; -} - static inline void *crypto_skcipher_ctx(struct crypto_skcipher *tfm) { return crypto_tfm_ctx(&tfm->base); @@ -182,27 +171,18 @@ static inline u32 skcipher_request_flags(struct skcipher_request *req) static inline unsigned int crypto_skcipher_alg_min_keysize( struct skcipher_alg *alg) { - if (alg->base.cra_ablkcipher.encrypt) - return alg->base.cra_ablkcipher.min_keysize; - return alg->min_keysize; } static inline unsigned int crypto_skcipher_alg_max_keysize( struct skcipher_alg *alg) { - if (alg->base.cra_ablkcipher.encrypt) - return alg->base.cra_ablkcipher.max_keysize; - return alg->max_keysize; } static inline unsigned int crypto_skcipher_alg_walksize( struct skcipher_alg *alg) { - if (alg->base.cra_ablkcipher.encrypt) - return alg->base.cra_blocksize; - return alg->walksize; } diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h index 8c5a31e810da..b4655d91661f 100644 --- a/include/crypto/skcipher.h +++ b/include/crypto/skcipher.h @@ -241,9 +241,6 @@ static inline struct skcipher_alg *crypto_skcipher_alg( static inline unsigned int crypto_skcipher_alg_ivsize(struct skcipher_alg *alg) { - if (alg->base.cra_ablkcipher.encrypt) - return alg->base.cra_ablkcipher.ivsize; - return alg->ivsize; } @@ -286,9 +283,6 @@ static inline unsigned int crypto_skcipher_blocksize( static inline unsigned int crypto_skcipher_alg_chunksize( struct skcipher_alg *alg) { - if (alg->base.cra_ablkcipher.encrypt) - return alg->base.cra_blocksize; - return alg->chunksize; } diff --git a/include/linux/crypto.h b/include/linux/crypto.h index e9f2c6b5d800..23365a9d062e 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -41,7 +41,6 @@ #define CRYPTO_ALG_TYPE_CIPHER 0x00000001 #define CRYPTO_ALG_TYPE_COMPRESS 0x00000002 #define CRYPTO_ALG_TYPE_AEAD 0x00000003 -#define CRYPTO_ALG_TYPE_ABLKCIPHER 0x00000005 #define CRYPTO_ALG_TYPE_SKCIPHER 0x00000005 #define CRYPTO_ALG_TYPE_KPP 0x00000008 #define CRYPTO_ALG_TYPE_ACOMPRESS 0x0000000a @@ -137,7 +136,6 @@ #define CRYPTO_MINALIGN_ATTR __attribute__ ((__aligned__(CRYPTO_MINALIGN))) struct scatterlist; -struct crypto_ablkcipher; struct crypto_async_request; struct crypto_tfm; struct crypto_type; @@ -160,19 +158,6 @@ struct crypto_async_request { u32 flags; }; -struct ablkcipher_request { - struct crypto_async_request base; - - unsigned int nbytes; - - void *info; - - struct scatterlist *src; - struct scatterlist *dst; - - void *__ctx[] CRYPTO_MINALIGN_ATTR; -}; - /** * DOC: Block Cipher Algorithm Definitions * @@ -180,57 +165,6 @@ struct ablkcipher_request { * managed via crypto_register_alg() and crypto_unregister_alg(). */ -/** - * struct ablkcipher_alg - asynchronous block cipher definition - * @min_keysize: Minimum key size supported by the transformation. This is the - * smallest key length supported by this transformation algorithm. - * This must be set to one of the pre-defined values as this is - * not hardware specific. Possible values for this field can be - * found via git grep "_MIN_KEY_SIZE" include/crypto/ - * @max_keysize: Maximum key size supported by the transformation. This is the - * largest key length supported by this transformation algorithm. - * This must be set to one of the pre-defined values as this is - * not hardware specific. Possible values for this field can be - * found via git grep "_MAX_KEY_SIZE" include/crypto/ - * @setkey: Set key for the transformation. This function is used to either - * program a supplied key into the hardware or store the key in the - * transformation context for programming it later. Note that this - * function does modify the transformation context. This function can - * be called multiple times during the existence of the transformation - * object, so one must make sure the key is properly reprogrammed into - * the hardware. This function is also responsible for checking the key - * length for validity. In case a software fallback was put in place in - * the @cra_init call, this function might need to use the fallback if - * the algorithm doesn't support all of the key sizes. - * @encrypt: Encrypt a scatterlist of blocks. This function is used to encrypt - * the supplied scatterlist containing the blocks of data. The crypto - * API consumer is responsible for aligning the entries of the - * scatterlist properly and making sure the chunks are correctly - * sized. In case a software fallback was put in place in the - * @cra_init call, this function might need to use the fallback if - * the algorithm doesn't support all of the key sizes. In case the - * key was stored in transformation context, the key might need to be - * re-programmed into the hardware in this function. This function - * shall not modify the transformation context, as this function may - * be called in parallel with the same transformation object. - * @decrypt: Decrypt a single block. This is a reverse counterpart to @encrypt - * and the conditions are exactly the same. - * @ivsize: IV size applicable for transformation. The consumer must provide an - * IV of exactly that size to perform the encrypt or decrypt operation. - * - * All fields except @ivsize are mandatory and must be filled. - */ -struct ablkcipher_alg { - int (*setkey)(struct crypto_ablkcipher *tfm, const u8 *key, - unsigned int keylen); - int (*encrypt)(struct ablkcipher_request *req); - int (*decrypt)(struct ablkcipher_request *req); - - unsigned int min_keysize; - unsigned int max_keysize; - unsigned int ivsize; -}; - /** * struct cipher_alg - single-block symmetric ciphers definition * @cia_min_keysize: Minimum key size supported by the transformation. This is @@ -415,7 +349,6 @@ struct crypto_istat_rng { }; #endif /* CONFIG_CRYPTO_STATS */ -#define cra_ablkcipher cra_u.ablkcipher #define cra_cipher cra_u.cipher #define cra_compress cra_u.compress @@ -483,8 +416,6 @@ struct crypto_istat_rng { * @cra_exit: Deinitialize the cryptographic transformation object. This is a * counterpart to @cra_init, used to remove various changes set in * @cra_init. - * @cra_u.ablkcipher: Union member which contains an asynchronous block cipher - * definition. See @struct @ablkcipher_alg. * @cra_u.cipher: Union member which contains a single-block symmetric cipher * definition. See @struct @cipher_alg. * @cra_u.compress: Union member which contains a (de)compression algorithm. @@ -526,7 +457,6 @@ struct crypto_alg { const struct crypto_type *cra_type; union { - struct ablkcipher_alg ablkcipher; struct cipher_alg cipher; struct compress_alg compress; } cra_u; @@ -554,8 +484,6 @@ struct crypto_alg { #ifdef CONFIG_CRYPTO_STATS void crypto_stats_init(struct crypto_alg *alg); void crypto_stats_get(struct crypto_alg *alg); -void crypto_stats_ablkcipher_encrypt(unsigned int nbytes, int ret, struct crypto_alg *alg); -void crypto_stats_ablkcipher_decrypt(unsigned int nbytes, int ret, struct crypto_alg *alg); void crypto_stats_aead_encrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret); void crypto_stats_aead_decrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret); void crypto_stats_ahash_update(unsigned int nbytes, int ret, struct crypto_alg *alg); @@ -578,10 +506,6 @@ static inline void crypto_stats_init(struct crypto_alg *alg) {} static inline void crypto_stats_get(struct crypto_alg *alg) {} -static inline void crypto_stats_ablkcipher_encrypt(unsigned int nbytes, int ret, struct crypto_alg *alg) -{} -static inline void crypto_stats_ablkcipher_decrypt(unsigned int nbytes, int ret, struct crypto_alg *alg) -{} static inline void crypto_stats_aead_encrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret) {} static inline void crypto_stats_aead_decrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret) @@ -675,18 +599,6 @@ int crypto_has_alg(const char *name, u32 type, u32 mask); * crypto_free_*(), as well as the various helpers below. */ -struct ablkcipher_tfm { - int (*setkey)(struct crypto_ablkcipher *tfm, const u8 *key, - unsigned int keylen); - int (*encrypt)(struct ablkcipher_request *req); - int (*decrypt)(struct ablkcipher_request *req); - - struct crypto_ablkcipher *base; - - unsigned int ivsize; - unsigned int reqsize; -}; - struct cipher_tfm { int (*cit_setkey)(struct crypto_tfm *tfm, const u8 *key, unsigned int keylen); @@ -703,7 +615,6 @@ struct compress_tfm { u8 *dst, unsigned int *dlen); }; -#define crt_ablkcipher crt_u.ablkcipher #define crt_cipher crt_u.cipher #define crt_compress crt_u.compress @@ -712,7 +623,6 @@ struct crypto_tfm { u32 crt_flags; union { - struct ablkcipher_tfm ablkcipher; struct cipher_tfm cipher; struct compress_tfm compress; } crt_u; @@ -724,10 +634,6 @@ struct crypto_tfm { void *__crt_ctx[] CRYPTO_MINALIGN_ATTR; }; -struct crypto_ablkcipher { - struct crypto_tfm base; -}; - struct crypto_cipher { struct crypto_tfm base; }; @@ -835,347 +741,6 @@ static inline unsigned int crypto_tfm_ctx_alignment(void) return __alignof__(tfm->__crt_ctx); } -/* - * API wrappers. - */ -static inline struct crypto_ablkcipher *__crypto_ablkcipher_cast( - struct crypto_tfm *tfm) -{ - return (struct crypto_ablkcipher *)tfm; -} - -/** - * DOC: Asynchronous Block Cipher API - * - * Asynchronous block cipher API is used with the ciphers of type - * CRYPTO_ALG_TYPE_ABLKCIPHER (listed as type "ablkcipher" in /proc/crypto). - * - * Asynchronous cipher operations imply that the function invocation for a - * cipher request returns immediately before the completion of the operation. - * The cipher request is scheduled as a separate kernel thread and therefore - * load-balanced on the different CPUs via the process scheduler. To allow - * the kernel crypto API to inform the caller about the completion of a cipher - * request, the caller must provide a callback function. That function is - * invoked with the cipher handle when the request completes. - * - * To support the asynchronous operation, additional information than just the - * cipher handle must be supplied to the kernel crypto API. That additional - * information is given by filling in the ablkcipher_request data structure. - * - * For the asynchronous block cipher API, the state is maintained with the tfm - * cipher handle. A single tfm can be used across multiple calls and in - * parallel. For asynchronous block cipher calls, context data supplied and - * only used by the caller can be referenced the request data structure in - * addition to the IV used for the cipher request. The maintenance of such - * state information would be important for a crypto driver implementer to - * have, because when calling the callback function upon completion of the - * cipher operation, that callback function may need some information about - * which operation just finished if it invoked multiple in parallel. This - * state information is unused by the kernel crypto API. - */ - -static inline struct crypto_tfm *crypto_ablkcipher_tfm( - struct crypto_ablkcipher *tfm) -{ - return &tfm->base; -} - -/** - * crypto_free_ablkcipher() - zeroize and free cipher handle - * @tfm: cipher handle to be freed - */ -static inline void crypto_free_ablkcipher(struct crypto_ablkcipher *tfm) -{ - crypto_free_tfm(crypto_ablkcipher_tfm(tfm)); -} - -static inline struct ablkcipher_tfm *crypto_ablkcipher_crt( - struct crypto_ablkcipher *tfm) -{ - return &crypto_ablkcipher_tfm(tfm)->crt_ablkcipher; -} - -/** - * crypto_ablkcipher_ivsize() - obtain IV size - * @tfm: cipher handle - * - * The size of the IV for the ablkcipher referenced by the cipher handle is - * returned. This IV size may be zero if the cipher does not need an IV. - * - * Return: IV size in bytes - */ -static inline unsigned int crypto_ablkcipher_ivsize( - struct crypto_ablkcipher *tfm) -{ - return crypto_ablkcipher_crt(tfm)->ivsize; -} - -/** - * crypto_ablkcipher_blocksize() - obtain block size of cipher - * @tfm: cipher handle - * - * The block size for the ablkcipher referenced with the cipher handle is - * returned. The caller may use that information to allocate appropriate - * memory for the data returned by the encryption or decryption operation - * - * Return: block size of cipher - */ -static inline unsigned int crypto_ablkcipher_blocksize( - struct crypto_ablkcipher *tfm) -{ - return crypto_tfm_alg_blocksize(crypto_ablkcipher_tfm(tfm)); -} - -static inline unsigned int crypto_ablkcipher_alignmask( - struct crypto_ablkcipher *tfm) -{ - return crypto_tfm_alg_alignmask(crypto_ablkcipher_tfm(tfm)); -} - -static inline u32 crypto_ablkcipher_get_flags(struct crypto_ablkcipher *tfm) -{ - return crypto_tfm_get_flags(crypto_ablkcipher_tfm(tfm)); -} - -static inline void crypto_ablkcipher_set_flags(struct crypto_ablkcipher *tfm, - u32 flags) -{ - crypto_tfm_set_flags(crypto_ablkcipher_tfm(tfm), flags); -} - -static inline void crypto_ablkcipher_clear_flags(struct crypto_ablkcipher *tfm, - u32 flags) -{ - crypto_tfm_clear_flags(crypto_ablkcipher_tfm(tfm), flags); -} - -/** - * crypto_ablkcipher_setkey() - set key for cipher - * @tfm: cipher handle - * @key: buffer holding the key - * @keylen: length of the key in bytes - * - * The caller provided key is set for the ablkcipher referenced by the cipher - * handle. - * - * Note, the key length determines the cipher type. Many block ciphers implement - * different cipher modes depending on the key size, such as AES-128 vs AES-192 - * vs. AES-256. When providing a 16 byte key for an AES cipher handle, AES-128 - * is performed. - * - * Return: 0 if the setting of the key was successful; < 0 if an error occurred - */ -static inline int crypto_ablkcipher_setkey(struct crypto_ablkcipher *tfm, - const u8 *key, unsigned int keylen) -{ - struct ablkcipher_tfm *crt = crypto_ablkcipher_crt(tfm); - - return crt->setkey(crt->base, key, keylen); -} - -/** - * crypto_ablkcipher_reqtfm() - obtain cipher handle from request - * @req: ablkcipher_request out of which the cipher handle is to be obtained - * - * Return the crypto_ablkcipher handle when furnishing an ablkcipher_request - * data structure. - * - * Return: crypto_ablkcipher handle - */ -static inline struct crypto_ablkcipher *crypto_ablkcipher_reqtfm( - struct ablkcipher_request *req) -{ - return __crypto_ablkcipher_cast(req->base.tfm); -} - -/** - * crypto_ablkcipher_encrypt() - encrypt plaintext - * @req: reference to the ablkcipher_request handle that holds all information - * needed to perform the cipher operation - * - * Encrypt plaintext data using the ablkcipher_request handle. That data - * structure and how it is filled with data is discussed with the - * ablkcipher_request_* functions. - * - * Return: 0 if the cipher operation was successful; < 0 if an error occurred - */ -static inline int crypto_ablkcipher_encrypt(struct ablkcipher_request *req) -{ - struct ablkcipher_tfm *crt = - crypto_ablkcipher_crt(crypto_ablkcipher_reqtfm(req)); - struct crypto_alg *alg = crt->base->base.__crt_alg; - unsigned int nbytes = req->nbytes; - int ret; - - crypto_stats_get(alg); - ret = crt->encrypt(req); - crypto_stats_ablkcipher_encrypt(nbytes, ret, alg); - return ret; -} - -/** - * crypto_ablkcipher_decrypt() - decrypt ciphertext - * @req: reference to the ablkcipher_request handle that holds all information - * needed to perform the cipher operation - * - * Decrypt ciphertext data using the ablkcipher_request handle. That data - * structure and how it is filled with data is discussed with the - * ablkcipher_request_* functions. - * - * Return: 0 if the cipher operation was successful; < 0 if an error occurred - */ -static inline int crypto_ablkcipher_decrypt(struct ablkcipher_request *req) -{ - struct ablkcipher_tfm *crt = - crypto_ablkcipher_crt(crypto_ablkcipher_reqtfm(req)); - struct crypto_alg *alg = crt->base->base.__crt_alg; - unsigned int nbytes = req->nbytes; - int ret; - - crypto_stats_get(alg); - ret = crt->decrypt(req); - crypto_stats_ablkcipher_decrypt(nbytes, ret, alg); - return ret; -} - -/** - * DOC: Asynchronous Cipher Request Handle - * - * The ablkcipher_request data structure contains all pointers to data - * required for the asynchronous cipher operation. This includes the cipher - * handle (which can be used by multiple ablkcipher_request instances), pointer - * to plaintext and ciphertext, asynchronous callback function, etc. It acts - * as a handle to the ablkcipher_request_* API calls in a similar way as - * ablkcipher handle to the crypto_ablkcipher_* API calls. - */ - -/** - * crypto_ablkcipher_reqsize() - obtain size of the request data structure - * @tfm: cipher handle - * - * Return: number of bytes - */ -static inline unsigned int crypto_ablkcipher_reqsize( - struct crypto_ablkcipher *tfm) -{ - return crypto_ablkcipher_crt(tfm)->reqsize; -} - -/** - * ablkcipher_request_set_tfm() - update cipher handle reference in request - * @req: request handle to be modified - * @tfm: cipher handle that shall be added to the request handle - * - * Allow the caller to replace the existing ablkcipher handle in the request - * data structure with a different one. - */ -static inline void ablkcipher_request_set_tfm( - struct ablkcipher_request *req, struct crypto_ablkcipher *tfm) -{ - req->base.tfm = crypto_ablkcipher_tfm(crypto_ablkcipher_crt(tfm)->base); -} - -static inline struct ablkcipher_request *ablkcipher_request_cast( - struct crypto_async_request *req) -{ - return container_of(req, struct ablkcipher_request, base); -} - -/** - * ablkcipher_request_alloc() - allocate request data structure - * @tfm: cipher handle to be registered with the request - * @gfp: memory allocation flag that is handed to kmalloc by the API call. - * - * Allocate the request data structure that must be used with the ablkcipher - * encrypt and decrypt API calls. During the allocation, the provided ablkcipher - * handle is registered in the request data structure. - * - * Return: allocated request handle in case of success, or NULL if out of memory - */ -static inline struct ablkcipher_request *ablkcipher_request_alloc( - struct crypto_ablkcipher *tfm, gfp_t gfp) -{ - struct ablkcipher_request *req; - - req = kmalloc(sizeof(struct ablkcipher_request) + - crypto_ablkcipher_reqsize(tfm), gfp); - - if (likely(req)) - ablkcipher_request_set_tfm(req, tfm); - - return req; -} - -/** - * ablkcipher_request_free() - zeroize and free request data structure - * @req: request data structure cipher handle to be freed - */ -static inline void ablkcipher_request_free(struct ablkcipher_request *req) -{ - kzfree(req); -} - -/** - * ablkcipher_request_set_callback() - set asynchronous callback function - * @req: request handle - * @flags: specify zero or an ORing of the flags - * CRYPTO_TFM_REQ_MAY_BACKLOG the request queue may back log and - * increase the wait queue beyond the initial maximum size; - * CRYPTO_TFM_REQ_MAY_SLEEP the request processing may sleep - * @compl: callback function pointer to be registered with the request handle - * @data: The data pointer refers to memory that is not used by the kernel - * crypto API, but provided to the callback function for it to use. Here, - * the caller can provide a reference to memory the callback function can - * operate on. As the callback function is invoked asynchronously to the - * related functionality, it may need to access data structures of the - * related functionality which can be referenced using this pointer. The - * callback function can access the memory via the "data" field in the - * crypto_async_request data structure provided to the callback function. - * - * This function allows setting the callback function that is triggered once the - * cipher operation completes. - * - * The callback function is registered with the ablkcipher_request handle and - * must comply with the following template:: - * - * void callback_function(struct crypto_async_request *req, int error) - */ -static inline void ablkcipher_request_set_callback( - struct ablkcipher_request *req, - u32 flags, crypto_completion_t compl, void *data) -{ - req->base.complete = compl; - req->base.data = data; - req->base.flags = flags; -} - -/** - * ablkcipher_request_set_crypt() - set data buffers - * @req: request handle - * @src: source scatter / gather list - * @dst: destination scatter / gather list - * @nbytes: number of bytes to process from @src - * @iv: IV for the cipher operation which must comply with the IV size defined - * by crypto_ablkcipher_ivsize - * - * This function allows setting of the source data and destination data - * scatter / gather lists. - * - * For encryption, the source is treated as the plaintext and the - * destination is the ciphertext. For a decryption operation, the use is - * reversed - the source is the ciphertext and the destination is the plaintext. - */ -static inline void ablkcipher_request_set_crypt( - struct ablkcipher_request *req, - struct scatterlist *src, struct scatterlist *dst, - unsigned int nbytes, void *iv) -{ - req->src = src; - req->dst = dst; - req->nbytes = nbytes; - req->info = iv; -} - /** * DOC: Single Block Cipher API * -- cgit v1.2.3-71-gd317 From 9e8d42a0f7eb9056f8bdb241b91738b5a2923f4c Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 8 Nov 2019 18:35:53 +0100 Subject: percpu-refcount: Use normal instead of RCU-sched" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is a revert of commit a4244454df129 ("percpu-refcount: use RCU-sched insted of normal RCU") which claims the only reason for using RCU-sched is "rcu_read_[un]lock() … are slightly more expensive than preempt_disable/enable()" and "As the RCU critical sections are extremely short, using sched-RCU shouldn't have any latency implications." The problem with using RCU-sched here is that it disables preemption and the release callback (called from percpu_ref_put_many()) must not acquire any sleeping locks like spinlock_t. This breaks PREEMPT_RT because some of the users acquire spinlock_t locks in their callbacks. Using rcu_read_lock() on PREEMPTION=n kernels is not any different compared to rcu_read_lock_sched(). On PREEMPTION=y kernels there are already performance issues due to additional preemption points. Looking at the code, the rcu_read_lock() is just an increment and unlock is almost just a decrement unless there is something special to do. Both are functions while disabling preemption is inlined. Doing a small benchmark, the minimal amount of time required was mostly the same. The average time required was higher due to the higher MAX value (which could be preemption). With DEBUG_PREEMPT=y it is rcu_read_lock_sched() that takes a little longer due to the additional debug code. Convert back to normal RCU. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Dennis Zhou --- include/linux/percpu-refcount.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index 7aef0abc194a..390031e816dc 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -186,14 +186,14 @@ static inline void percpu_ref_get_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; - rcu_read_lock_sched(); + rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) this_cpu_add(*percpu_count, nr); else atomic_long_add(nr, &ref->count); - rcu_read_unlock_sched(); + rcu_read_unlock(); } /** @@ -223,7 +223,7 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref) unsigned long __percpu *percpu_count; bool ret; - rcu_read_lock_sched(); + rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) { this_cpu_inc(*percpu_count); @@ -232,7 +232,7 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref) ret = atomic_long_inc_not_zero(&ref->count); } - rcu_read_unlock_sched(); + rcu_read_unlock(); return ret; } @@ -257,7 +257,7 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref) unsigned long __percpu *percpu_count; bool ret = false; - rcu_read_lock_sched(); + rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) { this_cpu_inc(*percpu_count); @@ -266,7 +266,7 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref) ret = atomic_long_inc_not_zero(&ref->count); } - rcu_read_unlock_sched(); + rcu_read_unlock(); return ret; } @@ -285,14 +285,14 @@ static inline void percpu_ref_put_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; - rcu_read_lock_sched(); + rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) this_cpu_sub(*percpu_count, nr); else if (unlikely(atomic_long_sub_and_test(nr, &ref->count))) ref->release(ref); - rcu_read_unlock_sched(); + rcu_read_unlock(); } /** -- cgit v1.2.3-71-gd317 From adbb68293fc5950a46e3e22f9dc9c619661194ae Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 12 Nov 2019 17:00:24 -0800 Subject: libnvdimm: Move nd_device_attribute_group to device_type A 'struct device_type' instance can carry default attributes for the device. Use this facility to remove the export of nd_device_attribute_group and put the responsibility on the core rather than leaf implementations to define this attribute. For regions this creates a new nd_region_attribute_groups[] added to the per-region device-type instances. Cc: Ira Weiny Cc: Michael Ellerman Cc: "Oliver O'Halloran" Cc: Vishal Verma Cc: Aneesh Kumar K.V Reviewed-by: Aneesh Kumar K.V Link: https://lore.kernel.org/r/157309901138.1582359.12909354140826530394.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- arch/powerpc/platforms/pseries/papr_scm.c | 2 -- drivers/acpi/nfit/core.c | 2 -- drivers/nvdimm/bus.c | 3 +-- drivers/nvdimm/dimm_devs.c | 8 +++++++- drivers/nvdimm/e820.c | 1 - drivers/nvdimm/nd.h | 1 + drivers/nvdimm/of_pmem.c | 1 - drivers/nvdimm/region_devs.c | 18 +++++++++++++----- include/linux/libnvdimm.h | 1 - 9 files changed, 22 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 61883291defc..04726f8fd189 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -286,7 +286,6 @@ int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, static const struct attribute_group *region_attr_groups[] = { &nd_region_attribute_group, - &nd_device_attribute_group, &nd_mapping_attribute_group, &nd_numa_attribute_group, NULL, @@ -299,7 +298,6 @@ static const struct attribute_group *bus_attr_groups[] = { static const struct attribute_group *papr_scm_dimm_groups[] = { &nvdimm_attribute_group, - &nd_device_attribute_group, NULL, }; diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 14e68f202f81..dec7c2b08672 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -1699,7 +1699,6 @@ static const struct attribute_group acpi_nfit_dimm_attribute_group = { static const struct attribute_group *acpi_nfit_dimm_attribute_groups[] = { &nvdimm_attribute_group, - &nd_device_attribute_group, &acpi_nfit_dimm_attribute_group, NULL, }; @@ -2199,7 +2198,6 @@ static const struct attribute_group acpi_nfit_region_attribute_group = { static const struct attribute_group *acpi_nfit_region_attribute_groups[] = { &nd_region_attribute_group, &nd_mapping_attribute_group, - &nd_device_attribute_group, &nd_numa_attribute_group, &acpi_nfit_region_attribute_group, NULL, diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index d47412dcdf38..eb422527dd57 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -669,10 +669,9 @@ static struct attribute *nd_device_attributes[] = { /* * nd_device_attribute_group - generic attributes for all devices on an nd bus */ -struct attribute_group nd_device_attribute_group = { +const struct attribute_group nd_device_attribute_group = { .attrs = nd_device_attributes, }; -EXPORT_SYMBOL_GPL(nd_device_attribute_group); static ssize_t numa_node_show(struct device *dev, struct device_attribute *attr, char *buf) diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c index 196aa44c4936..278867c68682 100644 --- a/drivers/nvdimm/dimm_devs.c +++ b/drivers/nvdimm/dimm_devs.c @@ -202,9 +202,15 @@ static void nvdimm_release(struct device *dev) kfree(nvdimm); } -static struct device_type nvdimm_device_type = { +static const struct attribute_group *nvdimm_attribute_groups[] = { + &nd_device_attribute_group, + NULL, +}; + +static const struct device_type nvdimm_device_type = { .name = "nvdimm", .release = nvdimm_release, + .groups = nvdimm_attribute_groups, }; bool is_nvdimm(struct device *dev) diff --git a/drivers/nvdimm/e820.c b/drivers/nvdimm/e820.c index 87f72f725e4f..adde2864c6a4 100644 --- a/drivers/nvdimm/e820.c +++ b/drivers/nvdimm/e820.c @@ -15,7 +15,6 @@ static const struct attribute_group *e820_pmem_attribute_groups[] = { static const struct attribute_group *e820_pmem_region_attribute_groups[] = { &nd_region_attribute_group, - &nd_device_attribute_group, NULL, }; diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index d83dd34cd169..21e018bfa188 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -239,6 +239,7 @@ int __init nd_label_init(void); void nvdimm_exit(void); void nd_region_exit(void); struct nvdimm; +extern const struct attribute_group nd_device_attribute_group; struct nvdimm_drvdata *to_ndd(struct nd_mapping *nd_mapping); int nvdimm_check_config_data(struct device *dev); int nvdimm_init_nsarea(struct nvdimm_drvdata *ndd); diff --git a/drivers/nvdimm/of_pmem.c b/drivers/nvdimm/of_pmem.c index 97187d6c0bdb..41348fa6b74c 100644 --- a/drivers/nvdimm/of_pmem.c +++ b/drivers/nvdimm/of_pmem.c @@ -11,7 +11,6 @@ static const struct attribute_group *region_attr_groups[] = { &nd_region_attribute_group, - &nd_device_attribute_group, NULL, }; diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index e89f2eb3678c..710b5111eaa8 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -763,19 +763,27 @@ struct attribute_group nd_region_attribute_group = { }; EXPORT_SYMBOL_GPL(nd_region_attribute_group); -static struct device_type nd_blk_device_type = { +static const struct attribute_group *nd_region_attribute_groups[] = { + &nd_device_attribute_group, + NULL, +}; + +static const struct device_type nd_blk_device_type = { .name = "nd_blk", .release = nd_region_release, + .groups = nd_region_attribute_groups, }; -static struct device_type nd_pmem_device_type = { +static const struct device_type nd_pmem_device_type = { .name = "nd_pmem", .release = nd_region_release, + .groups = nd_region_attribute_groups, }; -static struct device_type nd_volatile_device_type = { +static const struct device_type nd_volatile_device_type = { .name = "nd_volatile", .release = nd_region_release, + .groups = nd_region_attribute_groups, }; bool is_nd_pmem(struct device *dev) @@ -931,8 +939,8 @@ void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane) EXPORT_SYMBOL(nd_region_release_lane); static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus, - struct nd_region_desc *ndr_desc, struct device_type *dev_type, - const char *caller) + struct nd_region_desc *ndr_desc, + const struct device_type *dev_type, const char *caller) { struct nd_region *nd_region; struct device *dev; diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index b6eddf912568..d7dbf42498af 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -67,7 +67,6 @@ enum { extern struct attribute_group nvdimm_bus_attribute_group; extern struct attribute_group nvdimm_attribute_group; -extern struct attribute_group nd_device_attribute_group; extern struct attribute_group nd_numa_attribute_group; extern struct attribute_group nd_region_attribute_group; extern struct attribute_group nd_mapping_attribute_group; -- cgit v1.2.3-71-gd317 From f3d7c2292d104519195fdb11192daec13229c219 Mon Sep 17 00:00:00 2001 From: Bradley Bolen Date: Sat, 16 Nov 2019 20:00:45 -0500 Subject: mmc: core: Fix size overflow for mmc partitions With large eMMC cards, it is possible to create general purpose partitions that are bigger than 4GB. The size member of the mmc_part struct is only an unsigned int which overflows for gp partitions larger than 4GB. Change this to a u64 to handle the overflow. Signed-off-by: Bradley Bolen Signed-off-by: Ulf Hansson --- drivers/mmc/core/mmc.c | 9 ++++----- include/linux/mmc/card.h | 2 +- 2 files changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index c8804895595f..f6912ded652d 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -297,7 +297,7 @@ static void mmc_manage_enhanced_area(struct mmc_card *card, u8 *ext_csd) } } -static void mmc_part_add(struct mmc_card *card, unsigned int size, +static void mmc_part_add(struct mmc_card *card, u64 size, unsigned int part_cfg, char *name, int idx, bool ro, int area_type) { @@ -313,7 +313,7 @@ static void mmc_manage_gp_partitions(struct mmc_card *card, u8 *ext_csd) { int idx; u8 hc_erase_grp_sz, hc_wp_grp_sz; - unsigned int part_size; + u64 part_size; /* * General purpose partition feature support -- @@ -343,8 +343,7 @@ static void mmc_manage_gp_partitions(struct mmc_card *card, u8 *ext_csd) (ext_csd[EXT_CSD_GP_SIZE_MULT + idx * 3 + 1] << 8) + ext_csd[EXT_CSD_GP_SIZE_MULT + idx * 3]; - part_size *= (size_t)(hc_erase_grp_sz * - hc_wp_grp_sz); + part_size *= (hc_erase_grp_sz * hc_wp_grp_sz); mmc_part_add(card, part_size << 19, EXT_CSD_PART_CONFIG_ACC_GP0 + idx, "gp%d", idx, false, @@ -362,7 +361,7 @@ static void mmc_manage_gp_partitions(struct mmc_card *card, u8 *ext_csd) static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd) { int err = 0, idx; - unsigned int part_size; + u64 part_size; struct device_node *np; bool broken_hpi = false; diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index e459b38ef33c..cf3780a6ccc4 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -226,7 +226,7 @@ struct mmc_queue_req; * MMC Physical partitions */ struct mmc_part { - unsigned int size; /* partition size (in bytes) */ + u64 size; /* partition size (in bytes) */ unsigned int part_cfg; /* partition type */ char name[MAX_MMC_PART_NAME_LEN]; bool force_ro; /* to make boot parts RO by default */ -- cgit v1.2.3-71-gd317 From 1e0bd5a091e5d9e0f1d5b0e6329b87bb1792f784 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Sun, 17 Nov 2019 09:28:02 -0800 Subject: bpf: Switch bpf_map ref counter to atomic64_t so bpf_map_inc() never fails 92117d8443bc ("bpf: fix refcnt overflow") turned refcounting of bpf_map into potentially failing operation, when refcount reaches BPF_MAX_REFCNT limit (32k). Due to using 32-bit counter, it's possible in practice to overflow refcounter and make it wrap around to 0, causing erroneous map free, while there are still references to it, causing use-after-free problems. But having a failing refcounting operations are problematic in some cases. One example is mmap() interface. After establishing initial memory-mapping, user is allowed to arbitrarily map/remap/unmap parts of mapped memory, arbitrarily splitting it into multiple non-contiguous regions. All this happening without any control from the users of mmap subsystem. Rather mmap subsystem sends notifications to original creator of memory mapping through open/close callbacks, which are optionally specified during initial memory mapping creation. These callbacks are used to maintain accurate refcount for bpf_map (see next patch in this series). The problem is that open() callback is not supposed to fail, because memory-mapped resource is set up and properly referenced. This is posing a problem for using memory-mapping with BPF maps. One solution to this is to maintain separate refcount for just memory-mappings and do single bpf_map_inc/bpf_map_put when it goes from/to zero, respectively. There are similar use cases in current work on tcp-bpf, necessitating extra counter as well. This seems like a rather unfortunate and ugly solution that doesn't scale well to various new use cases. Another approach to solve this is to use non-failing refcount_t type, which uses 32-bit counter internally, but, once reaching overflow state at UINT_MAX, stays there. This utlimately causes memory leak, but prevents use after free. But given refcounting is not the most performance-critical operation with BPF maps (it's not used from running BPF program code), we can also just switch to 64-bit counter that can't overflow in practice, potentially disadvantaging 32-bit platforms a tiny bit. This simplifies semantics and allows above described scenarios to not worry about failing refcount increment operation. In terms of struct bpf_map size, we are still good and use the same amount of space: BEFORE (3 cache lines, 8 bytes of padding at the end): struct bpf_map { const struct bpf_map_ops * ops __attribute__((__aligned__(64))); /* 0 8 */ struct bpf_map * inner_map_meta; /* 8 8 */ void * security; /* 16 8 */ enum bpf_map_type map_type; /* 24 4 */ u32 key_size; /* 28 4 */ u32 value_size; /* 32 4 */ u32 max_entries; /* 36 4 */ u32 map_flags; /* 40 4 */ int spin_lock_off; /* 44 4 */ u32 id; /* 48 4 */ int numa_node; /* 52 4 */ u32 btf_key_type_id; /* 56 4 */ u32 btf_value_type_id; /* 60 4 */ /* --- cacheline 1 boundary (64 bytes) --- */ struct btf * btf; /* 64 8 */ struct bpf_map_memory memory; /* 72 16 */ bool unpriv_array; /* 88 1 */ bool frozen; /* 89 1 */ /* XXX 38 bytes hole, try to pack */ /* --- cacheline 2 boundary (128 bytes) --- */ atomic_t refcnt __attribute__((__aligned__(64))); /* 128 4 */ atomic_t usercnt; /* 132 4 */ struct work_struct work; /* 136 32 */ char name[16]; /* 168 16 */ /* size: 192, cachelines: 3, members: 21 */ /* sum members: 146, holes: 1, sum holes: 38 */ /* padding: 8 */ /* forced alignments: 2, forced holes: 1, sum forced holes: 38 */ } __attribute__((__aligned__(64))); AFTER (same 3 cache lines, no extra padding now): struct bpf_map { const struct bpf_map_ops * ops __attribute__((__aligned__(64))); /* 0 8 */ struct bpf_map * inner_map_meta; /* 8 8 */ void * security; /* 16 8 */ enum bpf_map_type map_type; /* 24 4 */ u32 key_size; /* 28 4 */ u32 value_size; /* 32 4 */ u32 max_entries; /* 36 4 */ u32 map_flags; /* 40 4 */ int spin_lock_off; /* 44 4 */ u32 id; /* 48 4 */ int numa_node; /* 52 4 */ u32 btf_key_type_id; /* 56 4 */ u32 btf_value_type_id; /* 60 4 */ /* --- cacheline 1 boundary (64 bytes) --- */ struct btf * btf; /* 64 8 */ struct bpf_map_memory memory; /* 72 16 */ bool unpriv_array; /* 88 1 */ bool frozen; /* 89 1 */ /* XXX 38 bytes hole, try to pack */ /* --- cacheline 2 boundary (128 bytes) --- */ atomic64_t refcnt __attribute__((__aligned__(64))); /* 128 8 */ atomic64_t usercnt; /* 136 8 */ struct work_struct work; /* 144 32 */ char name[16]; /* 176 16 */ /* size: 192, cachelines: 3, members: 21 */ /* sum members: 154, holes: 1, sum holes: 38 */ /* forced alignments: 2, forced holes: 1, sum forced holes: 38 */ } __attribute__((__aligned__(64))); This patch, while modifying all users of bpf_map_inc, also cleans up its interface to match bpf_map_put with separate operations for bpf_map_inc and bpf_map_inc_with_uref (to match bpf_map_put and bpf_map_put_with_uref, respectively). Also, given there are no users of bpf_map_inc_not_zero specifying uref=true, remove uref flag and default to uref=false internally. Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20191117172806.2195367-2-andriin@fb.com --- drivers/net/ethernet/netronome/nfp/bpf/offload.c | 4 +- include/linux/bpf.h | 10 ++--- kernel/bpf/inode.c | 2 +- kernel/bpf/map_in_map.c | 2 +- kernel/bpf/syscall.c | 51 ++++++++++-------------- kernel/bpf/verifier.c | 6 +-- kernel/bpf/xskmap.c | 6 +-- net/core/bpf_sk_storage.c | 2 +- 8 files changed, 34 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c index 88fab6a82acf..06927ba5a3ae 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c @@ -46,9 +46,7 @@ nfp_map_ptr_record(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog, /* Grab a single ref to the map for our record. The prog destroy ndo * happens after free_used_maps(). */ - map = bpf_map_inc(map, false); - if (IS_ERR(map)) - return PTR_ERR(map); + bpf_map_inc(map); record = kmalloc(sizeof(*record), GFP_KERNEL); if (!record) { diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5b81cde47314..34a34445c009 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -103,8 +103,8 @@ struct bpf_map { /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. */ - atomic_t refcnt ____cacheline_aligned; - atomic_t usercnt; + atomic64_t refcnt ____cacheline_aligned; + atomic64_t usercnt; struct work_struct work; char name[BPF_OBJ_NAME_LEN]; }; @@ -783,9 +783,9 @@ void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock); struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); -struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref); -struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map, - bool uref); +void bpf_map_inc(struct bpf_map *map); +void bpf_map_inc_with_uref(struct bpf_map *map); +struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); int bpf_map_charge_memlock(struct bpf_map *map, u32 pages); diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index a70f7209cda3..2f17f24258dc 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -34,7 +34,7 @@ static void *bpf_any_get(void *raw, enum bpf_type type) raw = bpf_prog_inc(raw); break; case BPF_TYPE_MAP: - raw = bpf_map_inc(raw, true); + bpf_map_inc_with_uref(raw); break; default: WARN_ON_ONCE(1); diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index fab4fb134547..4cbe987be35b 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -98,7 +98,7 @@ void *bpf_map_fd_get_ptr(struct bpf_map *map, return inner_map; if (bpf_map_meta_equal(map->inner_map_meta, inner_map)) - inner_map = bpf_map_inc(inner_map, false); + bpf_map_inc(inner_map); else inner_map = ERR_PTR(-EINVAL); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index c88c815c2154..20030751b7a2 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -311,7 +311,7 @@ static void bpf_map_free_deferred(struct work_struct *work) static void bpf_map_put_uref(struct bpf_map *map) { - if (atomic_dec_and_test(&map->usercnt)) { + if (atomic64_dec_and_test(&map->usercnt)) { if (map->ops->map_release_uref) map->ops->map_release_uref(map); } @@ -322,7 +322,7 @@ static void bpf_map_put_uref(struct bpf_map *map) */ static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock) { - if (atomic_dec_and_test(&map->refcnt)) { + if (atomic64_dec_and_test(&map->refcnt)) { /* bpf_map_free_id() must be called first */ bpf_map_free_id(map, do_idr_lock); btf_put(map->btf); @@ -575,8 +575,8 @@ static int map_create(union bpf_attr *attr) if (err) goto free_map; - atomic_set(&map->refcnt, 1); - atomic_set(&map->usercnt, 1); + atomic64_set(&map->refcnt, 1); + atomic64_set(&map->usercnt, 1); if (attr->btf_key_type_id || attr->btf_value_type_id) { struct btf *btf; @@ -653,21 +653,19 @@ struct bpf_map *__bpf_map_get(struct fd f) return f.file->private_data; } -/* prog's and map's refcnt limit */ -#define BPF_MAX_REFCNT 32768 - -struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref) +void bpf_map_inc(struct bpf_map *map) { - if (atomic_inc_return(&map->refcnt) > BPF_MAX_REFCNT) { - atomic_dec(&map->refcnt); - return ERR_PTR(-EBUSY); - } - if (uref) - atomic_inc(&map->usercnt); - return map; + atomic64_inc(&map->refcnt); } EXPORT_SYMBOL_GPL(bpf_map_inc); +void bpf_map_inc_with_uref(struct bpf_map *map) +{ + atomic64_inc(&map->refcnt); + atomic64_inc(&map->usercnt); +} +EXPORT_SYMBOL_GPL(bpf_map_inc_with_uref); + struct bpf_map *bpf_map_get_with_uref(u32 ufd) { struct fd f = fdget(ufd); @@ -677,38 +675,30 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd) if (IS_ERR(map)) return map; - map = bpf_map_inc(map, true); + bpf_map_inc_with_uref(map); fdput(f); return map; } /* map_idr_lock should have been held */ -static struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, - bool uref) +static struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref) { int refold; - refold = atomic_fetch_add_unless(&map->refcnt, 1, 0); - - if (refold >= BPF_MAX_REFCNT) { - __bpf_map_put(map, false); - return ERR_PTR(-EBUSY); - } - + refold = atomic64_fetch_add_unless(&map->refcnt, 1, 0); if (!refold) return ERR_PTR(-ENOENT); - if (uref) - atomic_inc(&map->usercnt); + atomic64_inc(&map->usercnt); return map; } -struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map, bool uref) +struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map) { spin_lock_bh(&map_idr_lock); - map = __bpf_map_inc_not_zero(map, uref); + map = __bpf_map_inc_not_zero(map, false); spin_unlock_bh(&map_idr_lock); return map; @@ -1455,6 +1445,9 @@ static struct bpf_prog *____bpf_prog_get(struct fd f) return f.file->private_data; } +/* prog's refcnt limit */ +#define BPF_MAX_REFCNT 32768 + struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i) { if (atomic_add_return(i, &prog->aux->refcnt) > BPF_MAX_REFCNT) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e9dc95a18d44..9f59f7a19dd0 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8179,11 +8179,7 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) * will be used by the valid program until it's unloaded * and all maps are released in free_used_maps() */ - map = bpf_map_inc(map, false); - if (IS_ERR(map)) { - fdput(f); - return PTR_ERR(map); - } + bpf_map_inc(map); aux->map_index = env->used_map_cnt; env->used_maps[env->used_map_cnt++] = map; diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c index da16c30868f3..90c4fce1c981 100644 --- a/kernel/bpf/xskmap.c +++ b/kernel/bpf/xskmap.c @@ -11,10 +11,8 @@ int xsk_map_inc(struct xsk_map *map) { - struct bpf_map *m = &map->map; - - m = bpf_map_inc(m, false); - return PTR_ERR_OR_ZERO(m); + bpf_map_inc(&map->map); + return 0; } void xsk_map_put(struct xsk_map *map) diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index da5639a5bd3b..458be6b3eda9 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -798,7 +798,7 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) * Try to grab map refcnt to make sure that it's still * alive and prevent concurrent removal. */ - map = bpf_map_inc_not_zero(&smap->map, false); + map = bpf_map_inc_not_zero(&smap->map); if (IS_ERR(map)) continue; -- cgit v1.2.3-71-gd317 From 85192dbf4de08795afe2b88e52a36fc6abfc3dba Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Sun, 17 Nov 2019 09:28:03 -0800 Subject: bpf: Convert bpf_prog refcnt to atomic64_t Similarly to bpf_map's refcnt/usercnt, convert bpf_prog's refcnt to atomic64 and remove artificial 32k limit. This allows to make bpf_prog's refcounting non-failing, simplifying logic of users of bpf_prog_add/bpf_prog_inc. Validated compilation by running allyesconfig kernel build. Suggested-by: Daniel Borkmann Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20191117172806.2195367-3-andriin@fb.com --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 9 ++----- drivers/net/ethernet/cavium/thunder/nicvf_main.c | 9 ++----- drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 7 ++---- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 24 +++++------------- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 18 ++++---------- drivers/net/ethernet/qlogic/qede/qede_main.c | 8 ++---- drivers/net/virtio_net.c | 7 ++---- include/linux/bpf.h | 13 ++++------ kernel/bpf/inode.c | 5 ++-- kernel/bpf/syscall.c | 30 +++++++---------------- kernel/events/core.c | 7 ++---- 11 files changed, 40 insertions(+), 97 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index c07172429c70..9da4fbee3cf7 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -3171,13 +3171,8 @@ static int bnxt_init_one_rx_ring(struct bnxt *bp, int ring_nr) bnxt_init_rxbd_pages(ring, type); if (BNXT_RX_PAGE_MODE(bp) && bp->xdp_prog) { - rxr->xdp_prog = bpf_prog_add(bp->xdp_prog, 1); - if (IS_ERR(rxr->xdp_prog)) { - int rc = PTR_ERR(rxr->xdp_prog); - - rxr->xdp_prog = NULL; - return rc; - } + bpf_prog_add(bp->xdp_prog, 1); + rxr->xdp_prog = bp->xdp_prog; } prod = rxr->rx_prod; for (i = 0; i < bp->rx_ring_size; i++) { diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 40a44dcb3d9b..f28409279ea4 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -1876,13 +1876,8 @@ static int nicvf_xdp_setup(struct nicvf *nic, struct bpf_prog *prog) if (nic->xdp_prog) { /* Attach BPF program */ - nic->xdp_prog = bpf_prog_add(nic->xdp_prog, nic->rx_queues - 1); - if (!IS_ERR(nic->xdp_prog)) { - bpf_attached = true; - } else { - ret = PTR_ERR(nic->xdp_prog); - nic->xdp_prog = NULL; - } + bpf_prog_add(nic->xdp_prog, nic->rx_queues - 1); + bpf_attached = true; } /* Calculate Tx queues needed for XDP and network stack */ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index c26c0a7cbb6b..acc56606d3a5 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -1807,11 +1807,8 @@ static int setup_xdp(struct net_device *dev, struct bpf_prog *prog) if (prog && !xdp_mtu_valid(priv, dev->mtu)) return -EINVAL; - if (prog) { - prog = bpf_prog_add(prog, priv->num_channels); - if (IS_ERR(prog)) - return PTR_ERR(prog); - } + if (prog) + bpf_prog_add(prog, priv->num_channels); up = netif_running(dev); need_update = (!!priv->xdp_prog != !!prog); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 40ec5acf79c0..d4697beeacc2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2286,11 +2286,7 @@ int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv, lockdep_is_held(&priv->mdev->state_lock)); if (xdp_prog && carry_xdp_prog) { - xdp_prog = bpf_prog_add(xdp_prog, tmp->rx_ring_num); - if (IS_ERR(xdp_prog)) { - mlx4_en_free_resources(tmp); - return PTR_ERR(xdp_prog); - } + bpf_prog_add(xdp_prog, tmp->rx_ring_num); for (i = 0; i < tmp->rx_ring_num; i++) rcu_assign_pointer(tmp->rx_ring[i]->xdp_prog, xdp_prog); @@ -2782,11 +2778,9 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog) * program for a new one. */ if (priv->tx_ring_num[TX_XDP] == xdp_ring_num) { - if (prog) { - prog = bpf_prog_add(prog, priv->rx_ring_num - 1); - if (IS_ERR(prog)) - return PTR_ERR(prog); - } + if (prog) + bpf_prog_add(prog, priv->rx_ring_num - 1); + mutex_lock(&mdev->state_lock); for (i = 0; i < priv->rx_ring_num; i++) { old_prog = rcu_dereference_protected( @@ -2807,13 +2801,8 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog) if (!tmp) return -ENOMEM; - if (prog) { - prog = bpf_prog_add(prog, priv->rx_ring_num - 1); - if (IS_ERR(prog)) { - err = PTR_ERR(prog); - goto out; - } - } + if (prog) + bpf_prog_add(prog, priv->rx_ring_num - 1); mutex_lock(&mdev->state_lock); memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile)); @@ -2862,7 +2851,6 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog) unlock_out: mutex_unlock(&mdev->state_lock); -out: kfree(tmp); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 772bfdbdeb9c..1d4a66fb466a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -408,12 +408,9 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, rq->stats = &c->priv->channel_stats[c->ix].rq; INIT_WORK(&rq->recover_work, mlx5e_rq_err_cqe_work); - rq->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL; - if (IS_ERR(rq->xdp_prog)) { - err = PTR_ERR(rq->xdp_prog); - rq->xdp_prog = NULL; - goto err_rq_wq_destroy; - } + if (params->xdp_prog) + bpf_prog_inc(params->xdp_prog); + rq->xdp_prog = params->xdp_prog; rq_xdp_ix = rq->ix; if (xsk) @@ -4406,16 +4403,11 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) /* no need for full reset when exchanging programs */ reset = (!priv->channels.params.xdp_prog || !prog); - if (was_opened && !reset) { + if (was_opened && !reset) /* num_channels is invariant here, so we can take the * batched reference right upfront. */ - prog = bpf_prog_add(prog, priv->channels.num); - if (IS_ERR(prog)) { - err = PTR_ERR(prog); - goto unlock; - } - } + bpf_prog_add(prog, priv->channels.num); if (was_opened && reset) { struct mlx5e_channels new_channels = {}; diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 8d1c208f778f..1e26964fe4e9 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -2107,12 +2107,8 @@ static int qede_start_queues(struct qede_dev *edev, bool clear_stats) if (rc) goto out; - fp->rxq->xdp_prog = bpf_prog_add(edev->xdp_prog, 1); - if (IS_ERR(fp->rxq->xdp_prog)) { - rc = PTR_ERR(fp->rxq->xdp_prog); - fp->rxq->xdp_prog = NULL; - goto out; - } + bpf_prog_add(edev->xdp_prog, 1); + fp->rxq->xdp_prog = edev->xdp_prog; } if (fp->type & QEDE_FASTPATH_TX) { diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 5a635f028bdc..4d7d5434cc5d 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2445,11 +2445,8 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, if (!prog && !old_prog) return 0; - if (prog) { - prog = bpf_prog_add(prog, vi->max_queue_pairs - 1); - if (IS_ERR(prog)) - return PTR_ERR(prog); - } + if (prog) + bpf_prog_add(prog, vi->max_queue_pairs - 1); /* Make sure NAPI is not using any XDP TX queues for RX. */ if (netif_running(dev)) { diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 34a34445c009..fb606dc61a3a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -485,7 +485,7 @@ struct bpf_func_info_aux { }; struct bpf_prog_aux { - atomic_t refcnt; + atomic64_t refcnt; u32 used_map_cnt; u32 max_ctx_offset; u32 max_pkt_offset; @@ -770,9 +770,9 @@ extern const struct bpf_verifier_ops xdp_analyzer_ops; struct bpf_prog *bpf_prog_get(u32 ufd); struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, bool attach_drv); -struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, int i); +void bpf_prog_add(struct bpf_prog *prog, int i); void bpf_prog_sub(struct bpf_prog *prog, int i); -struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog); +void bpf_prog_inc(struct bpf_prog *prog); struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); int __bpf_prog_charge(struct user_struct *user, u32 pages); @@ -912,10 +912,8 @@ static inline struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, return ERR_PTR(-EOPNOTSUPP); } -static inline struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, - int i) +static inline void bpf_prog_add(struct bpf_prog *prog, int i) { - return ERR_PTR(-EOPNOTSUPP); } static inline void bpf_prog_sub(struct bpf_prog *prog, int i) @@ -926,9 +924,8 @@ static inline void bpf_prog_put(struct bpf_prog *prog) { } -static inline struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog) +static inline void bpf_prog_inc(struct bpf_prog *prog) { - return ERR_PTR(-EOPNOTSUPP); } static inline struct bpf_prog *__must_check diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 2f17f24258dc..ecf42bec38c0 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -31,7 +31,7 @@ static void *bpf_any_get(void *raw, enum bpf_type type) { switch (type) { case BPF_TYPE_PROG: - raw = bpf_prog_inc(raw); + bpf_prog_inc(raw); break; case BPF_TYPE_MAP: bpf_map_inc_with_uref(raw); @@ -534,7 +534,8 @@ static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type if (!bpf_prog_get_ok(prog, &type, false)) return ERR_PTR(-EINVAL); - return bpf_prog_inc(prog); + bpf_prog_inc(prog); + return prog; } struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 20030751b7a2..52fe4bacb330 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1339,7 +1339,7 @@ static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred) static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) { - if (atomic_dec_and_test(&prog->aux->refcnt)) { + if (atomic64_dec_and_test(&prog->aux->refcnt)) { perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0); /* bpf_prog_free_id() must be called first */ bpf_prog_free_id(prog, do_idr_lock); @@ -1445,16 +1445,9 @@ static struct bpf_prog *____bpf_prog_get(struct fd f) return f.file->private_data; } -/* prog's refcnt limit */ -#define BPF_MAX_REFCNT 32768 - -struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i) +void bpf_prog_add(struct bpf_prog *prog, int i) { - if (atomic_add_return(i, &prog->aux->refcnt) > BPF_MAX_REFCNT) { - atomic_sub(i, &prog->aux->refcnt); - return ERR_PTR(-EBUSY); - } - return prog; + atomic64_add(i, &prog->aux->refcnt); } EXPORT_SYMBOL_GPL(bpf_prog_add); @@ -1465,13 +1458,13 @@ void bpf_prog_sub(struct bpf_prog *prog, int i) * path holds a reference to the program, thus atomic_sub() can * be safely used in such cases! */ - WARN_ON(atomic_sub_return(i, &prog->aux->refcnt) == 0); + WARN_ON(atomic64_sub_return(i, &prog->aux->refcnt) == 0); } EXPORT_SYMBOL_GPL(bpf_prog_sub); -struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog) +void bpf_prog_inc(struct bpf_prog *prog) { - return bpf_prog_add(prog, 1); + atomic64_inc(&prog->aux->refcnt); } EXPORT_SYMBOL_GPL(bpf_prog_inc); @@ -1480,12 +1473,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) { int refold; - refold = atomic_fetch_add_unless(&prog->aux->refcnt, 1, 0); - - if (refold >= BPF_MAX_REFCNT) { - __bpf_prog_put(prog, false); - return ERR_PTR(-EBUSY); - } + refold = atomic64_fetch_add_unless(&prog->aux->refcnt, 1, 0); if (!refold) return ERR_PTR(-ENOENT); @@ -1523,7 +1511,7 @@ static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type, goto out; } - prog = bpf_prog_inc(prog); + bpf_prog_inc(prog); out: fdput(f); return prog; @@ -1714,7 +1702,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) prog->orig_prog = NULL; prog->jited = 0; - atomic_set(&prog->aux->refcnt, 1); + atomic64_set(&prog->aux->refcnt, 1); prog->gpl_compatible = is_gpl ? 1 : 0; if (bpf_prog_is_dev_bound(prog->aux)) { diff --git a/kernel/events/core.c b/kernel/events/core.c index aec8dba2bea4..73c616876597 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10477,12 +10477,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, context = parent_event->overflow_handler_context; #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_EVENT_TRACING) if (overflow_handler == bpf_overflow_handler) { - struct bpf_prog *prog = bpf_prog_inc(parent_event->prog); + struct bpf_prog *prog = parent_event->prog; - if (IS_ERR(prog)) { - err = PTR_ERR(prog); - goto err_ns; - } + bpf_prog_inc(prog); event->prog = prog; event->orig_overflow_handler = parent_event->orig_overflow_handler; -- cgit v1.2.3-71-gd317 From fc9702273e2edb90400a34b3be76f7b08fa3344b Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Sun, 17 Nov 2019 09:28:04 -0800 Subject: bpf: Add mmap() support for BPF_MAP_TYPE_ARRAY Add ability to memory-map contents of BPF array map. This is extremely useful for working with BPF global data from userspace programs. It allows to avoid typical bpf_map_{lookup,update}_elem operations, improving both performance and usability. There had to be special considerations for map freezing, to avoid having writable memory view into a frozen map. To solve this issue, map freezing and mmap-ing is happening under mutex now: - if map is already frozen, no writable mapping is allowed; - if map has writable memory mappings active (accounted in map->writecnt), map freezing will keep failing with -EBUSY; - once number of writable memory mappings drops to zero, map freezing can be performed again. Only non-per-CPU plain arrays are supported right now. Maps with spinlocks can't be memory mapped either. For BPF_F_MMAPABLE array, memory allocation has to be done through vmalloc() to be mmap()'able. We also need to make sure that array data memory is page-sized and page-aligned, so we over-allocate memory in such a way that struct bpf_array is at the end of a single page of memory with array->value being aligned with the start of the second page. On deallocation we need to accomodate this memory arrangement to free vmalloc()'ed memory correctly. One important consideration regarding how memory-mapping subsystem functions. Memory-mapping subsystem provides few optional callbacks, among them open() and close(). close() is called for each memory region that is unmapped, so that users can decrease their reference counters and free up resources, if necessary. open() is *almost* symmetrical: it's called for each memory region that is being mapped, **except** the very first one. So bpf_map_mmap does initial refcnt bump, while open() will do any extra ones after that. Thus number of close() calls is equal to number of open() calls plus one more. Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Song Liu Acked-by: John Fastabend Acked-by: Johannes Weiner Link: https://lore.kernel.org/bpf/20191117172806.2195367-4-andriin@fb.com --- include/linux/bpf.h | 11 +++-- include/linux/vmalloc.h | 1 + include/uapi/linux/bpf.h | 3 ++ kernel/bpf/arraymap.c | 58 ++++++++++++++++++++++--- kernel/bpf/syscall.c | 99 ++++++++++++++++++++++++++++++++++++++++-- mm/vmalloc.c | 20 +++++++++ tools/include/uapi/linux/bpf.h | 3 ++ 7 files changed, 183 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index fb606dc61a3a..e913dd5946ae 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -68,6 +69,7 @@ struct bpf_map_ops { u64 *imm, u32 off); int (*map_direct_value_meta)(const struct bpf_map *map, u64 imm, u32 *off); + int (*map_mmap)(struct bpf_map *map, struct vm_area_struct *vma); }; struct bpf_map_memory { @@ -96,9 +98,10 @@ struct bpf_map { u32 btf_value_type_id; struct btf *btf; struct bpf_map_memory memory; + char name[BPF_OBJ_NAME_LEN]; bool unpriv_array; - bool frozen; /* write-once */ - /* 48 bytes hole */ + bool frozen; /* write-once; write-protected by freeze_mutex */ + /* 22 bytes hole */ /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. @@ -106,7 +109,8 @@ struct bpf_map { atomic64_t refcnt ____cacheline_aligned; atomic64_t usercnt; struct work_struct work; - char name[BPF_OBJ_NAME_LEN]; + struct mutex freeze_mutex; + u64 writecnt; /* writable mmap cnt; protected by freeze_mutex */ }; static inline bool map_value_has_spin_lock(const struct bpf_map *map) @@ -795,6 +799,7 @@ void bpf_map_charge_finish(struct bpf_map_memory *mem); void bpf_map_charge_move(struct bpf_map_memory *dst, struct bpf_map_memory *src); void *bpf_map_area_alloc(size_t size, int numa_node); +void *bpf_map_area_mmapable_alloc(size_t size, int numa_node); void bpf_map_area_free(void *base); void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 4e7809408073..b4c58a191eb1 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -93,6 +93,7 @@ extern void *vzalloc(unsigned long size); extern void *vmalloc_user(unsigned long size); extern void *vmalloc_node(unsigned long size, int node); extern void *vzalloc_node(unsigned long size, int node); +extern void *vmalloc_user_node_flags(unsigned long size, int node, gfp_t flags); extern void *vmalloc_exec(unsigned long size); extern void *vmalloc_32(unsigned long size); extern void *vmalloc_32_user(unsigned long size); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4842a134b202..dbbcf0b02970 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -348,6 +348,9 @@ enum bpf_attach_type { /* Clone map from listener for newly accepted socket */ #define BPF_F_CLONE (1U << 9) +/* Enable memory-mapping BPF map */ +#define BPF_F_MMAPABLE (1U << 10) + /* flags for BPF_PROG_QUERY */ #define BPF_F_QUERY_EFFECTIVE (1U << 0) diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 1c65ce0098a9..a42097c36b0c 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -14,7 +14,7 @@ #include "map_in_map.h" #define ARRAY_CREATE_FLAG_MASK \ - (BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK) + (BPF_F_NUMA_NODE | BPF_F_MMAPABLE | BPF_F_ACCESS_MASK) static void bpf_array_free_percpu(struct bpf_array *array) { @@ -59,6 +59,10 @@ int array_map_alloc_check(union bpf_attr *attr) (percpu && numa_node != NUMA_NO_NODE)) return -EINVAL; + if (attr->map_type != BPF_MAP_TYPE_ARRAY && + attr->map_flags & BPF_F_MMAPABLE) + return -EINVAL; + if (attr->value_size > KMALLOC_MAX_SIZE) /* if value_size is bigger, the user space won't be able to * access the elements. @@ -102,10 +106,19 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) } array_size = sizeof(*array); - if (percpu) + if (percpu) { array_size += (u64) max_entries * sizeof(void *); - else - array_size += (u64) max_entries * elem_size; + } else { + /* rely on vmalloc() to return page-aligned memory and + * ensure array->value is exactly page-aligned + */ + if (attr->map_flags & BPF_F_MMAPABLE) { + array_size = PAGE_ALIGN(array_size); + array_size += PAGE_ALIGN((u64) max_entries * elem_size); + } else { + array_size += (u64) max_entries * elem_size; + } + } /* make sure there is no u32 overflow later in round_up() */ cost = array_size; @@ -117,7 +130,20 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) return ERR_PTR(ret); /* allocate all map elements and zero-initialize them */ - array = bpf_map_area_alloc(array_size, numa_node); + if (attr->map_flags & BPF_F_MMAPABLE) { + void *data; + + /* kmalloc'ed memory can't be mmap'ed, use explicit vmalloc */ + data = bpf_map_area_mmapable_alloc(array_size, numa_node); + if (!data) { + bpf_map_charge_finish(&mem); + return ERR_PTR(-ENOMEM); + } + array = data + PAGE_ALIGN(sizeof(struct bpf_array)) + - offsetof(struct bpf_array, value); + } else { + array = bpf_map_area_alloc(array_size, numa_node); + } if (!array) { bpf_map_charge_finish(&mem); return ERR_PTR(-ENOMEM); @@ -350,6 +376,11 @@ static int array_map_delete_elem(struct bpf_map *map, void *key) return -EINVAL; } +static void *array_map_vmalloc_addr(struct bpf_array *array) +{ + return (void *)round_down((unsigned long)array, PAGE_SIZE); +} + /* Called when map->refcnt goes to zero, either from workqueue or from syscall */ static void array_map_free(struct bpf_map *map) { @@ -365,7 +396,10 @@ static void array_map_free(struct bpf_map *map) if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) bpf_array_free_percpu(array); - bpf_map_area_free(array); + if (array->map.map_flags & BPF_F_MMAPABLE) + bpf_map_area_free(array_map_vmalloc_addr(array)); + else + bpf_map_area_free(array); } static void array_map_seq_show_elem(struct bpf_map *map, void *key, @@ -444,6 +478,17 @@ static int array_map_check_btf(const struct bpf_map *map, return 0; } +int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + pgoff_t pgoff = PAGE_ALIGN(sizeof(*array)) >> PAGE_SHIFT; + + if (!(map->map_flags & BPF_F_MMAPABLE)) + return -EINVAL; + + return remap_vmalloc_range(vma, array_map_vmalloc_addr(array), pgoff); +} + const struct bpf_map_ops array_map_ops = { .map_alloc_check = array_map_alloc_check, .map_alloc = array_map_alloc, @@ -455,6 +500,7 @@ const struct bpf_map_ops array_map_ops = { .map_gen_lookup = array_map_gen_lookup, .map_direct_value_addr = array_map_direct_value_addr, .map_direct_value_meta = array_map_direct_value_meta, + .map_mmap = array_map_mmap, .map_seq_show_elem = array_map_seq_show_elem, .map_check_btf = array_map_check_btf, }; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 52fe4bacb330..bac3becf9f90 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -127,7 +127,7 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) return map; } -void *bpf_map_area_alloc(size_t size, int numa_node) +static void *__bpf_map_area_alloc(size_t size, int numa_node, bool mmapable) { /* We really just want to fail instead of triggering OOM killer * under memory pressure, therefore we set __GFP_NORETRY to kmalloc, @@ -142,18 +142,33 @@ void *bpf_map_area_alloc(size_t size, int numa_node) const gfp_t flags = __GFP_NOWARN | __GFP_ZERO; void *area; - if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { + /* kmalloc()'ed memory can't be mmap()'ed */ + if (!mmapable && size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { area = kmalloc_node(size, GFP_USER | __GFP_NORETRY | flags, numa_node); if (area != NULL) return area; } - + if (mmapable) { + BUG_ON(!PAGE_ALIGNED(size)); + return vmalloc_user_node_flags(size, numa_node, GFP_KERNEL | + __GFP_RETRY_MAYFAIL | flags); + } return __vmalloc_node_flags_caller(size, numa_node, GFP_KERNEL | __GFP_RETRY_MAYFAIL | flags, __builtin_return_address(0)); } +void *bpf_map_area_alloc(size_t size, int numa_node) +{ + return __bpf_map_area_alloc(size, numa_node, false); +} + +void *bpf_map_area_mmapable_alloc(size_t size, int numa_node) +{ + return __bpf_map_area_alloc(size, numa_node, true); +} + void bpf_map_area_free(void *area) { kvfree(area); @@ -425,6 +440,74 @@ static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf, return -EINVAL; } +/* called for any extra memory-mapped regions (except initial) */ +static void bpf_map_mmap_open(struct vm_area_struct *vma) +{ + struct bpf_map *map = vma->vm_file->private_data; + + bpf_map_inc_with_uref(map); + + if (vma->vm_flags & VM_WRITE) { + mutex_lock(&map->freeze_mutex); + map->writecnt++; + mutex_unlock(&map->freeze_mutex); + } +} + +/* called for all unmapped memory region (including initial) */ +static void bpf_map_mmap_close(struct vm_area_struct *vma) +{ + struct bpf_map *map = vma->vm_file->private_data; + + if (vma->vm_flags & VM_WRITE) { + mutex_lock(&map->freeze_mutex); + map->writecnt--; + mutex_unlock(&map->freeze_mutex); + } + + bpf_map_put_with_uref(map); +} + +static const struct vm_operations_struct bpf_map_default_vmops = { + .open = bpf_map_mmap_open, + .close = bpf_map_mmap_close, +}; + +static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) +{ + struct bpf_map *map = filp->private_data; + int err; + + if (!map->ops->map_mmap || map_value_has_spin_lock(map)) + return -ENOTSUPP; + + if (!(vma->vm_flags & VM_SHARED)) + return -EINVAL; + + mutex_lock(&map->freeze_mutex); + + if ((vma->vm_flags & VM_WRITE) && map->frozen) { + err = -EPERM; + goto out; + } + + /* set default open/close callbacks */ + vma->vm_ops = &bpf_map_default_vmops; + vma->vm_private_data = map; + + err = map->ops->map_mmap(map, vma); + if (err) + goto out; + + bpf_map_inc_with_uref(map); + + if (vma->vm_flags & VM_WRITE) + map->writecnt++; +out: + mutex_unlock(&map->freeze_mutex); + return err; +} + const struct file_operations bpf_map_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_map_show_fdinfo, @@ -432,6 +515,7 @@ const struct file_operations bpf_map_fops = { .release = bpf_map_release, .read = bpf_dummy_read, .write = bpf_dummy_write, + .mmap = bpf_map_mmap, }; int bpf_map_new_fd(struct bpf_map *map, int flags) @@ -577,6 +661,7 @@ static int map_create(union bpf_attr *attr) atomic64_set(&map->refcnt, 1); atomic64_set(&map->usercnt, 1); + mutex_init(&map->freeze_mutex); if (attr->btf_key_type_id || attr->btf_value_type_id) { struct btf *btf; @@ -1163,6 +1248,13 @@ static int map_freeze(const union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); + + mutex_lock(&map->freeze_mutex); + + if (map->writecnt) { + err = -EBUSY; + goto err_put; + } if (READ_ONCE(map->frozen)) { err = -EBUSY; goto err_put; @@ -1174,6 +1266,7 @@ static int map_freeze(const union bpf_attr *attr) WRITE_ONCE(map->frozen, true); err_put: + mutex_unlock(&map->freeze_mutex); fdput(f); return err; } diff --git a/mm/vmalloc.c b/mm/vmalloc.c index a3c70e275f4e..4a7d7459c4f9 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2671,6 +2671,26 @@ void *vzalloc_node(unsigned long size, int node) } EXPORT_SYMBOL(vzalloc_node); +/** + * vmalloc_user_node_flags - allocate memory for userspace on a specific node + * @size: allocation size + * @node: numa node + * @flags: flags for the page level allocator + * + * The resulting memory area is zeroed so it can be mapped to userspace + * without leaking data. + * + * Return: pointer to the allocated memory or %NULL on error + */ +void *vmalloc_user_node_flags(unsigned long size, int node, gfp_t flags) +{ + return __vmalloc_node_range(size, SHMLBA, VMALLOC_START, VMALLOC_END, + flags | __GFP_ZERO, PAGE_KERNEL, + VM_USERMAP, node, + __builtin_return_address(0)); +} +EXPORT_SYMBOL(vmalloc_user_node_flags); + /** * vmalloc_exec - allocate virtually contiguous, executable memory * @size: allocation size diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 4842a134b202..dbbcf0b02970 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -348,6 +348,9 @@ enum bpf_attach_type { /* Clone map from listener for newly accepted socket */ #define BPF_F_CLONE (1U << 9) +/* Enable memory-mapping BPF map */ +#define BPF_F_MMAPABLE (1U << 10) + /* flags for BPF_PROG_QUERY */ #define BPF_F_QUERY_EFFECTIVE (1U << 0) -- cgit v1.2.3-71-gd317 From 496074f94b19574c77240d3b3f84cfb1097de51d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 14 Nov 2019 14:31:28 -0800 Subject: blk-cgroup: cgroup_rstat_updated() shouldn't be called on cgroup1 Currently, cgroup rstat is supported only on cgroup2 hierarchy and rstat functions shouldn't be called on cgroup1 cgroups. While converting blk-cgroup core statistics to rstat, f73316482977 ("blk-cgroup: reimplement basic IO stats using cgroup rstat") accidentally ended up calling cgroup_rstat_updated() on cgroup1 cgroups causing crashes. Longer term, we probably should add cgroup1 support to rstat but for now let's mask the call directly. Fixes: f73316482977 ("blk-cgroup: reimplement basic IO stats using cgroup rstat") Tested-by: Faiz Abbas Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 48a66738143d..19394c77ed99 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -626,7 +626,8 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, bis->cur.ios[rwd]++; u64_stats_update_end(&bis->sync); - cgroup_rstat_updated(blkg->blkcg->css.cgroup, cpu); + if (cgroup_subsys_on_dfl(io_cgrp_subsys)) + cgroup_rstat_updated(blkg->blkcg->css.cgroup, cpu); put_cpu(); } -- cgit v1.2.3-71-gd317 From ea806eb3eab35528b578a061b2c4b28f0f92c465 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Sun, 17 Nov 2019 17:04:15 -0500 Subject: ftrace: Add a helper function to modify_ftrace_direct() to allow arch optimization If a direct ftrace callback is at a location that does not have any other ftrace helpers attached to it, it is possible to simply just change the text to call the new caller (if the architecture supports it). But this requires special architecture code. Currently, modify_ftrace_direct() uses a trick to add a stub ftrace callback to the location forcing it to call the ftrace iterator. Then it can change the direct helper to call the new function in C, and then remove the stub. Removing the stub will have the location now call the new location that the direct helper is using. The new helper function does the registering the stub trick, but is a weak function, allowing an architecture to override it to do something a bit more direct. Link: https://lore.kernel.org/r/20191115215125.mbqv7taqnx376yed@ast-mbp.dhcp.thefacebook.com Suggested-by: Alexei Starovoitov Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 21 ++++++++- kernel/trace/ftrace.c | 120 ++++++++++++++++++++++++++++++++++++------------- 2 files changed, 107 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 73eb2e93593f..dfaa37e1943d 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -246,12 +246,24 @@ static inline void ftrace_free_init_mem(void) { } static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { } #endif /* CONFIG_FUNCTION_TRACER */ +struct ftrace_func_entry { + struct hlist_node hlist; + unsigned long ip; + unsigned long direct; /* for direct lookup only */ +}; + +struct dyn_ftrace; + #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS extern int ftrace_direct_func_count; int register_ftrace_direct(unsigned long ip, unsigned long addr); int unregister_ftrace_direct(unsigned long ip, unsigned long addr); int modify_ftrace_direct(unsigned long ip, unsigned long old_addr, unsigned long new_addr); struct ftrace_direct_func *ftrace_find_direct_func(unsigned long addr); +int ftrace_modify_direct_caller(struct ftrace_func_entry *entry, + struct dyn_ftrace *rec, + unsigned long old_addr, + unsigned long new_addr); #else # define ftrace_direct_func_count 0 static inline int register_ftrace_direct(unsigned long ip, unsigned long addr) @@ -271,6 +283,13 @@ static inline struct ftrace_direct_func *ftrace_find_direct_func(unsigned long a { return NULL; } +static inline int ftrace_modify_direct_caller(struct ftrace_func_entry *entry, + struct dyn_ftrace *rec, + unsigned long old_addr, + unsigned long new_addr) +{ + return -ENODEV; +} #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ #ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS @@ -343,8 +362,6 @@ static inline void stack_tracer_enable(void) { } int ftrace_arch_code_modify_prepare(void); int ftrace_arch_code_modify_post_process(void); -struct dyn_ftrace; - enum ftrace_bug_type { FTRACE_BUG_UNKNOWN, FTRACE_BUG_INIT, diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index ef79c8393f53..caae523f4ef3 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1020,12 +1020,6 @@ static bool update_all_ops; # error Dynamic ftrace depends on MCOUNT_RECORD #endif -struct ftrace_func_entry { - struct hlist_node hlist; - unsigned long ip; - unsigned long direct; /* for direct lookup only */ -}; - struct ftrace_func_probe { struct ftrace_probe_ops *probe_ops; struct ftrace_ops ops; @@ -5112,7 +5106,8 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr) } EXPORT_SYMBOL_GPL(register_ftrace_direct); -static struct ftrace_func_entry *find_direct_entry(unsigned long *ip) +static struct ftrace_func_entry *find_direct_entry(unsigned long *ip, + struct dyn_ftrace **recp) { struct ftrace_func_entry *entry; struct dyn_ftrace *rec; @@ -5132,6 +5127,9 @@ static struct ftrace_func_entry *find_direct_entry(unsigned long *ip) /* Passed in ip just needs to be on the call site */ *ip = rec->ip; + if (recp) + *recp = rec; + return entry; } @@ -5143,7 +5141,7 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr) mutex_lock(&direct_mutex); - entry = find_direct_entry(&ip); + entry = find_direct_entry(&ip, NULL); if (!entry) goto out_unlock; @@ -5179,6 +5177,75 @@ static struct ftrace_ops stub_ops = { .func = ftrace_stub, }; +/** + * ftrace_modify_direct_caller - modify ftrace nop directly + * @entry: The ftrace hash entry of the direct helper for @rec + * @rec: The record representing the function site to patch + * @old_addr: The location that the site at @rec->ip currently calls + * @new_addr: The location that the site at @rec->ip should call + * + * An architecture may overwrite this function to optimize the + * changing of the direct callback on an ftrace nop location. + * This is called with the ftrace_lock mutex held, and no other + * ftrace callbacks are on the associated record (@rec). Thus, + * it is safe to modify the ftrace record, where it should be + * currently calling @old_addr directly, to call @new_addr. + * + * Safety checks should be made to make sure that the code at + * @rec->ip is currently calling @old_addr. And this must + * also update entry->direct to @new_addr. + */ +int __weak ftrace_modify_direct_caller(struct ftrace_func_entry *entry, + struct dyn_ftrace *rec, + unsigned long old_addr, + unsigned long new_addr) +{ + unsigned long ip = rec->ip; + int ret; + + /* + * The ftrace_lock was used to determine if the record + * had more than one registered user to it. If it did, + * we needed to prevent that from changing to do the quick + * switch. But if it did not (only a direct caller was attached) + * then this function is called. But this function can deal + * with attached callers to the rec that we care about, and + * since this function uses standard ftrace calls that take + * the ftrace_lock mutex, we need to release it. + */ + mutex_unlock(&ftrace_lock); + + /* + * By setting a stub function at the same address, we force + * the code to call the iterator and the direct_ops helper. + * This means that @ip does not call the direct call, and + * we can simply modify it. + */ + ret = ftrace_set_filter_ip(&stub_ops, ip, 0, 0); + if (ret) + goto out_lock; + + ret = register_ftrace_function(&stub_ops); + if (ret) { + ftrace_set_filter_ip(&stub_ops, ip, 1, 0); + goto out_lock; + } + + entry->direct = new_addr; + + /* + * By removing the stub, we put back the direct call, calling + * the @new_addr. + */ + unregister_ftrace_function(&stub_ops); + ftrace_set_filter_ip(&stub_ops, ip, 1, 0); + + out_lock: + mutex_lock(&ftrace_lock); + + return ret; +} + /** * modify_ftrace_direct - Modify an existing direct call to call something else * @ip: The instruction pointer to modify @@ -5197,11 +5264,13 @@ int modify_ftrace_direct(unsigned long ip, unsigned long old_addr, unsigned long new_addr) { struct ftrace_func_entry *entry; + struct dyn_ftrace *rec; int ret = -ENODEV; mutex_lock(&direct_mutex); - entry = find_direct_entry(&ip); + mutex_lock(&ftrace_lock); + entry = find_direct_entry(&ip, &rec); if (!entry) goto out_unlock; @@ -5210,33 +5279,20 @@ int modify_ftrace_direct(unsigned long ip, goto out_unlock; /* - * By setting a stub function at the same address, we force - * the code to call the iterator and the direct_ops helper. - * This means that @ip does not call the direct call, and - * we can simply modify it. + * If there's no other ftrace callback on the rec->ip location, + * then it can be changed directly by the architecture. + * If there is another caller, then we just need to change the + * direct caller helper to point to @new_addr. */ - ret = ftrace_set_filter_ip(&stub_ops, ip, 0, 0); - if (ret) - goto out_unlock; - - ret = register_ftrace_function(&stub_ops); - if (ret) { - ftrace_set_filter_ip(&stub_ops, ip, 1, 0); - goto out_unlock; + if (ftrace_rec_count(rec) == 1) { + ret = ftrace_modify_direct_caller(entry, rec, old_addr, new_addr); + } else { + entry->direct = new_addr; + ret = 0; } - entry->direct = new_addr; - - /* - * By removing the stub, we put back the direct call, calling - * the @new_addr. - */ - unregister_ftrace_function(&stub_ops); - ftrace_set_filter_ip(&stub_ops, ip, 1, 0); - - ret = 0; - out_unlock: + mutex_unlock(&ftrace_lock); mutex_unlock(&direct_mutex); return ret; } -- cgit v1.2.3-71-gd317 From ae7c2d342a10dbef1e054482f46498b6282a1df0 Mon Sep 17 00:00:00 2001 From: Luhua Xu Date: Mon, 18 Nov 2019 12:57:16 +0800 Subject: spi: mediatek: add SPI_CS_HIGH support Change to use SPI_CS_HIGH to support spi CS polarity setting for chips support enhance_timing. Signed-off-by: Luhua Xu Link: https://lore.kernel.org/r/1574053037-26721-2-git-send-email-luhua.xu@mediatek.com Signed-off-by: Mark Brown --- drivers/spi/spi-mt65xx.c | 12 ++++++++++-- include/linux/platform_data/spi-mt65xx.h | 1 - 2 files changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c index 25fe149a8d9a..6783e12c40c2 100644 --- a/drivers/spi/spi-mt65xx.c +++ b/drivers/spi/spi-mt65xx.c @@ -139,7 +139,6 @@ static const struct mtk_spi_compatible mt8183_compat = { * supplies it. */ static const struct mtk_chip_config mtk_default_chip_info = { - .cs_pol = 0, .sample_sel = 0, }; @@ -230,10 +229,12 @@ static int mtk_spi_prepare_message(struct spi_master *master, #endif if (mdata->dev_comp->enhance_timing) { - if (chip_config->cs_pol) + /* set CS polarity */ + if (spi->mode & SPI_CS_HIGH) reg_val |= SPI_CMD_CS_POL; else reg_val &= ~SPI_CMD_CS_POL; + if (chip_config->sample_sel) reg_val |= SPI_CMD_SAMPLE_SEL; else @@ -264,6 +265,9 @@ static void mtk_spi_set_cs(struct spi_device *spi, bool enable) u32 reg_val; struct mtk_spi *mdata = spi_master_get_devdata(spi->master); + if (spi->mode & SPI_CS_HIGH) + enable = !enable; + reg_val = readl(mdata->base + SPI_CMD_REG); if (!enable) { reg_val |= SPI_CMD_PAUSE_EN; @@ -646,6 +650,10 @@ static int mtk_spi_probe(struct platform_device *pdev) mdata = spi_master_get_devdata(master); mdata->dev_comp = of_id->data; + + if (mdata->dev_comp->enhance_timing) + master->mode_bits |= SPI_CS_HIGH; + if (mdata->dev_comp->must_tx) master->flags = SPI_MASTER_MUST_TX; diff --git a/include/linux/platform_data/spi-mt65xx.h b/include/linux/platform_data/spi-mt65xx.h index f0e6d6483e62..65fd5ffd257c 100644 --- a/include/linux/platform_data/spi-mt65xx.h +++ b/include/linux/platform_data/spi-mt65xx.h @@ -11,7 +11,6 @@ /* Board specific platform_data */ struct mtk_chip_config { - u32 cs_pol; u32 sample_sel; }; #endif -- cgit v1.2.3-71-gd317 From 5ca470a0c3886b80ec13c3a19e9aae4c2f469202 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Fri, 4 Oct 2019 10:39:55 -0600 Subject: docs: Add request_irq() documentation While checking the results of the :c:func: removal, I noticed that there was no documentation for request_irq(), and request_threaded_irq() was not mentioned at all. Add a kerneldoc comment for request_irq() and add request_threaded_irq() to the list of functions. Reviewed-by: Thomas Gleixner Signed-off-by: Jonathan Corbet --- Documentation/core-api/genericirq.rst | 2 ++ include/linux/interrupt.h | 13 +++++++++++++ 2 files changed, 15 insertions(+) (limited to 'include/linux') diff --git a/Documentation/core-api/genericirq.rst b/Documentation/core-api/genericirq.rst index 2e6c99e3ce3b..8f06d885c310 100644 --- a/Documentation/core-api/genericirq.rst +++ b/Documentation/core-api/genericirq.rst @@ -127,6 +127,8 @@ The high-level Driver API consists of following functions: - request_irq() +- request_threaded_irq() + - free_irq() - disable_irq() diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 89fc59dab57d..ba873ec7e09d 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -140,6 +140,19 @@ request_threaded_irq(unsigned int irq, irq_handler_t handler, irq_handler_t thread_fn, unsigned long flags, const char *name, void *dev); +/** + * request_irq - Add a handler for an interrupt line + * @irq: The interrupt line to allocate + * @handler: Function to be called when the IRQ occurs. + * Primary handler for threaded interrupts + * If NULL, the default primary handler is installed + * @flags: Handling flags + * @name: Name of the device generating this interrupt + * @dev: A cookie passed to the handler function + * + * This call allocates an interrupt and establishes a handler; see + * the documentation for request_threaded_irq() for details. + */ static inline int __must_check request_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *name, void *dev) -- cgit v1.2.3-71-gd317 From 298e54fa810e027f1b0800d789eb862592721f08 Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 15 Nov 2019 19:56:51 +0000 Subject: net: phy: add core phylib sfp support Add core phylib help for supporting SFP sockets on PHYs. This provides a mechanism to inform the SFP layer about PHY up/down events, and also unregister the SFP bus when the PHY is going away. Signed-off-by: Russell King Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/phy.c | 7 +++++ drivers/net/phy/phy_device.c | 66 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/phy.h | 11 ++++++++ 3 files changed, 84 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 105d389b58e7..36d4ffe1cd3f 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include @@ -841,6 +842,9 @@ void phy_stop(struct phy_device *phydev) mutex_lock(&phydev->lock); + if (phydev->sfp_bus) + sfp_upstream_stop(phydev->sfp_bus); + phydev->state = PHY_HALTED; mutex_unlock(&phydev->lock); @@ -875,6 +879,9 @@ void phy_start(struct phy_device *phydev) goto out; } + if (phydev->sfp_bus) + sfp_upstream_start(phydev->sfp_bus); + /* if phy was suspended, bring the physical link up again */ __phy_resume(phydev); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index fa71998fea51..40f1942f1606 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -1174,6 +1175,65 @@ phy_standalone_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RO(phy_standalone); +/** + * phy_sfp_attach - attach the SFP bus to the PHY upstream network device + * @upstream: pointer to the phy device + * @bus: sfp bus representing cage being attached + * + * This is used to fill in the sfp_upstream_ops .attach member. + */ +void phy_sfp_attach(void *upstream, struct sfp_bus *bus) +{ + struct phy_device *phydev = upstream; + + if (phydev->attached_dev) + phydev->attached_dev->sfp_bus = bus; + phydev->sfp_bus_attached = true; +} +EXPORT_SYMBOL(phy_sfp_attach); + +/** + * phy_sfp_detach - detach the SFP bus from the PHY upstream network device + * @upstream: pointer to the phy device + * @bus: sfp bus representing cage being attached + * + * This is used to fill in the sfp_upstream_ops .detach member. + */ +void phy_sfp_detach(void *upstream, struct sfp_bus *bus) +{ + struct phy_device *phydev = upstream; + + if (phydev->attached_dev) + phydev->attached_dev->sfp_bus = NULL; + phydev->sfp_bus_attached = false; +} +EXPORT_SYMBOL(phy_sfp_detach); + +/** + * phy_sfp_probe - probe for a SFP cage attached to this PHY device + * @phydev: Pointer to phy_device + * @ops: SFP's upstream operations + */ +int phy_sfp_probe(struct phy_device *phydev, + const struct sfp_upstream_ops *ops) +{ + struct sfp_bus *bus; + int ret; + + if (phydev->mdio.dev.fwnode) { + bus = sfp_bus_find_fwnode(phydev->mdio.dev.fwnode); + if (IS_ERR(bus)) + return PTR_ERR(bus); + + phydev->sfp_bus = bus; + + ret = sfp_bus_add_upstream(bus, phydev, ops); + sfp_bus_put(bus); + } + return 0; +} +EXPORT_SYMBOL(phy_sfp_probe); + /** * phy_attach_direct - attach a network device to a given PHY device pointer * @dev: network device to attach @@ -1249,6 +1309,9 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, if (dev) { phydev->attached_dev = dev; dev->phydev = phydev; + + if (phydev->sfp_bus_attached) + dev->sfp_bus = phydev->sfp_bus; } /* Some Ethernet drivers try to connect to a PHY device before @@ -2418,6 +2481,9 @@ static int phy_remove(struct device *dev) phydev->state = PHY_DOWN; mutex_unlock(&phydev->lock); + sfp_bus_del_upstream(phydev->sfp_bus); + phydev->sfp_bus = NULL; + if (phydev->drv && phydev->drv->remove) { phydev->drv->remove(phydev); diff --git a/include/linux/phy.h b/include/linux/phy.h index 78436d58ce7c..124516fe2763 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -203,6 +203,8 @@ static inline const char *phy_modes(phy_interface_t interface) struct device; struct phylink; +struct sfp_bus; +struct sfp_upstream_ops; struct sk_buff; /* @@ -342,6 +344,8 @@ struct phy_c45_device_ids { * dev_flags: Device-specific flags used by the PHY driver. * irq: IRQ number of the PHY's interrupt (-1 if none) * phy_timer: The timer for handling the state machine + * sfp_bus_attached: flag indicating whether the SFP bus has been attached + * sfp_bus: SFP bus attached to this PHY's fiber port * attached_dev: The attached enet driver's device instance ptr * adjust_link: Callback for the enet controller to respond to * changes in the link state. @@ -432,6 +436,9 @@ struct phy_device { struct mutex lock; + /* This may be modified under the rtnl lock */ + bool sfp_bus_attached; + struct sfp_bus *sfp_bus; struct phylink *phylink; struct net_device *attached_dev; @@ -1020,6 +1027,10 @@ int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); int __phy_resume(struct phy_device *phydev); int phy_loopback(struct phy_device *phydev, bool enable); +void phy_sfp_attach(void *upstream, struct sfp_bus *bus); +void phy_sfp_detach(void *upstream, struct sfp_bus *bus); +int phy_sfp_probe(struct phy_device *phydev, + const struct sfp_upstream_ops *ops); struct phy_device *phy_attach(struct net_device *dev, const char *bus_id, phy_interface_t interface); struct phy_device *phy_find_first(struct mii_bus *bus); -- cgit v1.2.3-71-gd317 From cbda56d5fefcebc01448982a55836c88a825b34c Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 18 Nov 2019 12:11:24 +0100 Subject: cpuidle: Introduce cpuidle_driver_state_disabled() for driver quirks Commit 99e98d3fb100 ("cpuidle: Consolidate disabled state checks") overlooked the fact that the imx6q and tegra20 cpuidle drivers use the "disabled" field in struct cpuidle_state for quirks which trigger after the initialization of cpuidle, so reading the initial value of that field is not sufficient for those drivers. In order to allow them to implement the quirks without using the "disabled" field in struct cpuidle_state, introduce a new helper function and modify them to use it. Fixes: 99e98d3fb100 ("cpuidle: Consolidate disabled state checks") Reported-by: Len Brown Signed-off-by: Rafael J. Wysocki --- arch/arm/mach-imx/cpuidle-imx6q.c | 4 ++-- arch/arm/mach-tegra/cpuidle-tegra20.c | 2 +- drivers/cpuidle/driver.c | 28 ++++++++++++++++++++++++++++ include/linux/cpuidle.h | 4 ++++ 4 files changed, 35 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mach-imx/cpuidle-imx6q.c b/arch/arm/mach-imx/cpuidle-imx6q.c index 39a7d9393641..24dd5bbe60e4 100644 --- a/arch/arm/mach-imx/cpuidle-imx6q.c +++ b/arch/arm/mach-imx/cpuidle-imx6q.c @@ -62,13 +62,13 @@ static struct cpuidle_driver imx6q_cpuidle_driver = { */ void imx6q_cpuidle_fec_irqs_used(void) { - imx6q_cpuidle_driver.states[1].disabled = true; + cpuidle_driver_state_disabled(&imx6q_cpuidle_driver, 1, true); } EXPORT_SYMBOL_GPL(imx6q_cpuidle_fec_irqs_used); void imx6q_cpuidle_fec_irqs_unused(void) { - imx6q_cpuidle_driver.states[1].disabled = false; + cpuidle_driver_state_disabled(&imx6q_cpuidle_driver, 1, false); } EXPORT_SYMBOL_GPL(imx6q_cpuidle_fec_irqs_unused); diff --git a/arch/arm/mach-tegra/cpuidle-tegra20.c b/arch/arm/mach-tegra/cpuidle-tegra20.c index 2447427cb4a8..69f3fa270fbe 100644 --- a/arch/arm/mach-tegra/cpuidle-tegra20.c +++ b/arch/arm/mach-tegra/cpuidle-tegra20.c @@ -203,7 +203,7 @@ void tegra20_cpuidle_pcie_irqs_in_use(void) { pr_info_once( "Disabling cpuidle LP2 state, since PCIe IRQs are in use\n"); - tegra_idle_driver.states[1].disabled = true; + cpuidle_driver_state_disabled(&tegra_idle_driver, 1, true); } int __init tegra20_cpuidle_init(void) diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c index fcaf8b2bab96..c76423aaef4d 100644 --- a/drivers/cpuidle/driver.c +++ b/drivers/cpuidle/driver.c @@ -389,3 +389,31 @@ void cpuidle_driver_unref(void) spin_unlock(&cpuidle_driver_lock); } + +/** + * cpuidle_driver_state_disabled - Disable or enable an idle state + * @drv: cpuidle driver owning the state + * @idx: State index + * @disable: Whether or not to disable the state + */ +void cpuidle_driver_state_disabled(struct cpuidle_driver *drv, int idx, + bool disable) +{ + unsigned int cpu; + + mutex_lock(&cpuidle_lock); + + for_each_cpu(cpu, drv->cpumask) { + struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu); + + if (!dev) + continue; + + if (disable) + dev->states_usage[idx].disable |= CPUIDLE_STATE_DISABLED_BY_DRIVER; + else + dev->states_usage[idx].disable &= ~CPUIDLE_STATE_DISABLED_BY_DRIVER; + } + + mutex_unlock(&cpuidle_lock); +} diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 22602747f468..afb6a573b46d 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -149,6 +149,8 @@ extern int cpuidle_register_driver(struct cpuidle_driver *drv); extern struct cpuidle_driver *cpuidle_get_driver(void); extern struct cpuidle_driver *cpuidle_driver_ref(void); extern void cpuidle_driver_unref(void); +extern void cpuidle_driver_state_disabled(struct cpuidle_driver *drv, int idx, + bool disable); extern void cpuidle_unregister_driver(struct cpuidle_driver *drv); extern int cpuidle_register_device(struct cpuidle_device *dev); extern void cpuidle_unregister_device(struct cpuidle_device *dev); @@ -186,6 +188,8 @@ static inline int cpuidle_register_driver(struct cpuidle_driver *drv) static inline struct cpuidle_driver *cpuidle_get_driver(void) {return NULL; } static inline struct cpuidle_driver *cpuidle_driver_ref(void) {return NULL; } static inline void cpuidle_driver_unref(void) {} +static inline void cpuidle_driver_state_disabled(struct cpuidle_driver *drv, + int idx, bool disable) { } static inline void cpuidle_unregister_driver(struct cpuidle_driver *drv) { } static inline int cpuidle_register_device(struct cpuidle_device *dev) {return -ENODEV; } -- cgit v1.2.3-71-gd317 From 3c4d77b68928df6c2bf07f4c3ba8e5d5e490bf4e Mon Sep 17 00:00:00 2001 From: Nick Crews Date: Thu, 24 Oct 2019 16:28:05 -0600 Subject: platform/chrome: wilco_ec: Add charging config driver Add a device to control the charging algorithm used on Wilco devices, which will be picked up by the drivers/power/supply/wilco-charger.c driver. See Documentation/ABI/testing/sysfs-class-power-wilco for the userspace interface and other info. Signed-off-by: Nick Crews Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/wilco_ec/core.c | 15 ++++++++++++++- include/linux/platform_data/wilco-ec.h | 2 ++ 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/platform/chrome/wilco_ec/core.c b/drivers/platform/chrome/wilco_ec/core.c index 3724bf4b77c6..9a438ebae3ed 100644 --- a/drivers/platform/chrome/wilco_ec/core.c +++ b/drivers/platform/chrome/wilco_ec/core.c @@ -93,6 +93,16 @@ static int wilco_ec_probe(struct platform_device *pdev) goto unregister_rtc; } + /* Register child device to be found by charger config driver. */ + ec->charger_pdev = platform_device_register_data(dev, "wilco-charger", + PLATFORM_DEVID_AUTO, + NULL, 0); + if (IS_ERR(ec->charger_pdev)) { + dev_err(dev, "Failed to create charger platform device\n"); + ret = PTR_ERR(ec->charger_pdev); + goto remove_sysfs; + } + /* Register child device that will be found by the telemetry driver. */ ec->telem_pdev = platform_device_register_data(dev, "wilco_telem", PLATFORM_DEVID_AUTO, @@ -100,11 +110,13 @@ static int wilco_ec_probe(struct platform_device *pdev) if (IS_ERR(ec->telem_pdev)) { dev_err(dev, "Failed to create telemetry platform device\n"); ret = PTR_ERR(ec->telem_pdev); - goto remove_sysfs; + goto unregister_charge_config; } return 0; +unregister_charge_config: + platform_device_unregister(ec->charger_pdev); remove_sysfs: wilco_ec_remove_sysfs(ec); unregister_rtc: @@ -120,6 +132,7 @@ static int wilco_ec_remove(struct platform_device *pdev) { struct wilco_ec_device *ec = platform_get_drvdata(pdev); + platform_device_unregister(ec->charger_pdev); wilco_ec_remove_sysfs(ec); platform_device_unregister(ec->telem_pdev); platform_device_unregister(ec->rtc_pdev); diff --git a/include/linux/platform_data/wilco-ec.h b/include/linux/platform_data/wilco-ec.h index ad03b586a095..0d104e780632 100644 --- a/include/linux/platform_data/wilco-ec.h +++ b/include/linux/platform_data/wilco-ec.h @@ -29,6 +29,7 @@ * @data_size: Size of the data buffer used for EC communication. * @debugfs_pdev: The child platform_device used by the debugfs sub-driver. * @rtc_pdev: The child platform_device used by the RTC sub-driver. + * @charger_pdev: Child platform_device used by the charger config sub-driver. * @telem_pdev: The child platform_device used by the telemetry sub-driver. */ struct wilco_ec_device { @@ -41,6 +42,7 @@ struct wilco_ec_device { size_t data_size; struct platform_device *debugfs_pdev; struct platform_device *rtc_pdev; + struct platform_device *charger_pdev; struct platform_device *telem_pdev; }; -- cgit v1.2.3-71-gd317 From 119a3cb6d687259f2be333351c1c5d634204e68b Mon Sep 17 00:00:00 2001 From: Daniel Campello Date: Wed, 6 Nov 2019 09:33:19 -0700 Subject: platform/chrome: wilco_ec: Add keyboard backlight LED support The EC is in charge of controlling the keyboard backlight on the Wilco platform. We expose a standard LED class device named platform::kbd_backlight. Since the EC will never change the backlight level of its own accord, we don't need to implement a brightness_get() method. Signed-off-by: Nick Crews Signed-off-by: Daniel Campello Reviewed-by: Daniel Campello Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/wilco_ec/Kconfig | 2 +- drivers/platform/chrome/wilco_ec/Makefile | 3 +- drivers/platform/chrome/wilco_ec/core.c | 13 +- drivers/platform/chrome/wilco_ec/keyboard_leds.c | 191 +++++++++++++++++++++++ include/linux/platform_data/wilco-ec.h | 13 ++ 5 files changed, 216 insertions(+), 6 deletions(-) create mode 100644 drivers/platform/chrome/wilco_ec/keyboard_leds.c (limited to 'include/linux') diff --git a/drivers/platform/chrome/wilco_ec/Kconfig b/drivers/platform/chrome/wilco_ec/Kconfig index 89007b0bc743..365f30e116ee 100644 --- a/drivers/platform/chrome/wilco_ec/Kconfig +++ b/drivers/platform/chrome/wilco_ec/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only config WILCO_EC tristate "ChromeOS Wilco Embedded Controller" - depends on ACPI && X86 && CROS_EC_LPC + depends on ACPI && X86 && CROS_EC_LPC && LEDS_CLASS help If you say Y here, you get support for talking to the ChromeOS Wilco EC over an eSPI bus. This uses a simple byte-level protocol diff --git a/drivers/platform/chrome/wilco_ec/Makefile b/drivers/platform/chrome/wilco_ec/Makefile index bc817164596e..ecb3145cab18 100644 --- a/drivers/platform/chrome/wilco_ec/Makefile +++ b/drivers/platform/chrome/wilco_ec/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 -wilco_ec-objs := core.o mailbox.o properties.o sysfs.o +wilco_ec-objs := core.o keyboard_leds.o mailbox.o \ + properties.o sysfs.o obj-$(CONFIG_WILCO_EC) += wilco_ec.o wilco_ec_debugfs-objs := debugfs.o obj-$(CONFIG_WILCO_EC_DEBUGFS) += wilco_ec_debugfs.o diff --git a/drivers/platform/chrome/wilco_ec/core.c b/drivers/platform/chrome/wilco_ec/core.c index 9a438ebae3ed..5210c357feef 100644 --- a/drivers/platform/chrome/wilco_ec/core.c +++ b/drivers/platform/chrome/wilco_ec/core.c @@ -5,10 +5,6 @@ * Copyright 2018 Google LLC * * This is the entry point for the drivers that control the Wilco EC. - * This driver is responsible for several tasks: - * - Initialize the register interface that is used by wilco_ec_mailbox() - * - Create a platform device which is picked up by the debugfs driver - * - Create a platform device which is picked up by the RTC driver */ #include @@ -87,6 +83,15 @@ static int wilco_ec_probe(struct platform_device *pdev) goto unregister_debugfs; } + /* Set up the keyboard backlight LEDs. */ + ret = wilco_keyboard_leds_init(ec); + if (ret < 0) { + dev_err(dev, + "Failed to initialize keyboard LEDs: %d\n", + ret); + goto unregister_rtc; + } + ret = wilco_ec_add_sysfs(ec); if (ret < 0) { dev_err(dev, "Failed to create sysfs entries: %d", ret); diff --git a/drivers/platform/chrome/wilco_ec/keyboard_leds.c b/drivers/platform/chrome/wilco_ec/keyboard_leds.c new file mode 100644 index 000000000000..bb0edf51dfda --- /dev/null +++ b/drivers/platform/chrome/wilco_ec/keyboard_leds.c @@ -0,0 +1,191 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Keyboard backlight LED driver for the Wilco Embedded Controller + * + * Copyright 2019 Google LLC + * + * Since the EC will never change the backlight level of its own accord, + * we don't need to implement a brightness_get() method. + */ + +#include +#include +#include +#include +#include + +#define WILCO_EC_COMMAND_KBBL 0x75 +#define WILCO_KBBL_MODE_FLAG_PWM BIT(1) /* Set brightness by percent. */ +#define WILCO_KBBL_DEFAULT_BRIGHTNESS 0 + +struct wilco_keyboard_leds { + struct wilco_ec_device *ec; + struct led_classdev keyboard; +}; + +enum wilco_kbbl_subcommand { + WILCO_KBBL_SUBCMD_GET_FEATURES = 0x00, + WILCO_KBBL_SUBCMD_GET_STATE = 0x01, + WILCO_KBBL_SUBCMD_SET_STATE = 0x02, +}; + +/** + * struct wilco_keyboard_leds_msg - Message to/from EC for keyboard LED control. + * @command: Always WILCO_EC_COMMAND_KBBL. + * @status: Set by EC to 0 on success, 0xFF on failure. + * @subcmd: One of enum wilco_kbbl_subcommand. + * @reserved3: Should be 0. + * @mode: Bit flags for used mode, we want to use WILCO_KBBL_MODE_FLAG_PWM. + * @reserved5to8: Should be 0. + * @percent: Brightness in 0-100. Only meaningful in PWM mode. + * @reserved10to15: Should be 0. + */ +struct wilco_keyboard_leds_msg { + u8 command; + u8 status; + u8 subcmd; + u8 reserved3; + u8 mode; + u8 reserved5to8[4]; + u8 percent; + u8 reserved10to15[6]; +} __packed; + +/* Send a request, get a response, and check that the response is good. */ +static int send_kbbl_msg(struct wilco_ec_device *ec, + struct wilco_keyboard_leds_msg *request, + struct wilco_keyboard_leds_msg *response) +{ + struct wilco_ec_message msg; + int ret; + + memset(&msg, 0, sizeof(msg)); + msg.type = WILCO_EC_MSG_LEGACY; + msg.request_data = request; + msg.request_size = sizeof(*request); + msg.response_data = response; + msg.response_size = sizeof(*response); + + ret = wilco_ec_mailbox(ec, &msg); + if (ret < 0) { + dev_err(ec->dev, + "Failed sending keyboard LEDs command: %d", ret); + return ret; + } + + if (response->status) { + dev_err(ec->dev, + "EC reported failure sending keyboard LEDs command: %d", + response->status); + return -EIO; + } + + return 0; +} + +static int set_kbbl(struct wilco_ec_device *ec, enum led_brightness brightness) +{ + struct wilco_keyboard_leds_msg request; + struct wilco_keyboard_leds_msg response; + + memset(&request, 0, sizeof(request)); + request.command = WILCO_EC_COMMAND_KBBL; + request.subcmd = WILCO_KBBL_SUBCMD_SET_STATE; + request.mode = WILCO_KBBL_MODE_FLAG_PWM; + request.percent = brightness; + + return send_kbbl_msg(ec, &request, &response); +} + +static int kbbl_exist(struct wilco_ec_device *ec, bool *exists) +{ + struct wilco_keyboard_leds_msg request; + struct wilco_keyboard_leds_msg response; + int ret; + + memset(&request, 0, sizeof(request)); + request.command = WILCO_EC_COMMAND_KBBL; + request.subcmd = WILCO_KBBL_SUBCMD_GET_FEATURES; + + ret = send_kbbl_msg(ec, &request, &response); + if (ret < 0) + return ret; + + *exists = response.status != 0xFF; + + return 0; +} + +/** + * kbbl_init() - Initialize the state of the keyboard backlight. + * @ec: EC device to talk to. + * + * Gets the current brightness, ensuring that the BIOS already initialized the + * backlight to PWM mode. If not in PWM mode, then the current brightness is + * meaningless, so set the brightness to WILCO_KBBL_DEFAULT_BRIGHTNESS. + * + * Return: Final brightness of the keyboard, or negative error code on failure. + */ +static int kbbl_init(struct wilco_ec_device *ec) +{ + struct wilco_keyboard_leds_msg request; + struct wilco_keyboard_leds_msg response; + int ret; + + memset(&request, 0, sizeof(request)); + request.command = WILCO_EC_COMMAND_KBBL; + request.subcmd = WILCO_KBBL_SUBCMD_GET_STATE; + + ret = send_kbbl_msg(ec, &request, &response); + if (ret < 0) + return ret; + + if (response.mode & WILCO_KBBL_MODE_FLAG_PWM) + return response.percent; + + ret = set_kbbl(ec, WILCO_KBBL_DEFAULT_BRIGHTNESS); + if (ret < 0) + return ret; + + return WILCO_KBBL_DEFAULT_BRIGHTNESS; +} + +static int wilco_keyboard_leds_set(struct led_classdev *cdev, + enum led_brightness brightness) +{ + struct wilco_keyboard_leds *wkl = + container_of(cdev, struct wilco_keyboard_leds, keyboard); + return set_kbbl(wkl->ec, brightness); +} + +int wilco_keyboard_leds_init(struct wilco_ec_device *ec) +{ + struct wilco_keyboard_leds *wkl; + bool leds_exist; + int ret; + + ret = kbbl_exist(ec, &leds_exist); + if (ret < 0) { + dev_err(ec->dev, + "Failed checking keyboard LEDs support: %d", ret); + return ret; + } + if (!leds_exist) + return 0; + + wkl = devm_kzalloc(ec->dev, sizeof(*wkl), GFP_KERNEL); + if (!wkl) + return -ENOMEM; + + wkl->ec = ec; + wkl->keyboard.name = "platform::kbd_backlight"; + wkl->keyboard.max_brightness = 100; + wkl->keyboard.flags = LED_CORE_SUSPENDRESUME; + wkl->keyboard.brightness_set_blocking = wilco_keyboard_leds_set; + ret = kbbl_init(ec); + if (ret < 0) + return ret; + wkl->keyboard.brightness = ret; + + return devm_led_classdev_register(ec->dev, &wkl->keyboard); +} diff --git a/include/linux/platform_data/wilco-ec.h b/include/linux/platform_data/wilco-ec.h index 0d104e780632..afede15a95bf 100644 --- a/include/linux/platform_data/wilco-ec.h +++ b/include/linux/platform_data/wilco-ec.h @@ -122,6 +122,19 @@ struct wilco_ec_message { */ int wilco_ec_mailbox(struct wilco_ec_device *ec, struct wilco_ec_message *msg); +/** + * wilco_keyboard_leds_init() - Set up the keyboard backlight LEDs. + * @ec: EC device to query. + * + * After this call, the keyboard backlight will be exposed through a an LED + * device at /sys/class/leds. + * + * This may sleep because it uses wilco_ec_mailbox(). + * + * Return: 0 on success, negative error code on failure. + */ +int wilco_keyboard_leds_init(struct wilco_ec_device *ec); + /* * A Property is typically a data item that is stored to NVRAM * by the EC. Each of these data items has an index associated -- cgit v1.2.3-71-gd317 From e2f6a0e34870ff1bdb1411e250dd2f03908cfa9f Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 19 Nov 2019 09:51:54 -0800 Subject: libnvdimm: Move nd_numa_attribute_group to device_type A 'struct device_type' instance can carry default attributes for the device. Use this facility to remove the export of nd_numa_attribute_group and put the responsibility on the core rather than leaf implementations to define this attribute. Cc: Ira Weiny Cc: Michael Ellerman Cc: "Oliver O'Halloran" Cc: Vishal Verma Cc: Aneesh Kumar K.V Reviewed-by: Aneesh Kumar K.V Link: https://lore.kernel.org/r/157401269537.43284.14411189404186877352.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- arch/powerpc/platforms/pseries/papr_scm.c | 1 - drivers/acpi/nfit/core.c | 1 - drivers/nvdimm/bus.c | 3 +-- drivers/nvdimm/nd.h | 1 + drivers/nvdimm/region_devs.c | 1 + include/linux/libnvdimm.h | 1 - 6 files changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 04726f8fd189..6ffda03a6349 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -287,7 +287,6 @@ int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, static const struct attribute_group *region_attr_groups[] = { &nd_region_attribute_group, &nd_mapping_attribute_group, - &nd_numa_attribute_group, NULL, }; diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index dec7c2b08672..b3213faf37b5 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -2198,7 +2198,6 @@ static const struct attribute_group acpi_nfit_region_attribute_group = { static const struct attribute_group *acpi_nfit_region_attribute_groups[] = { &nd_region_attribute_group, &nd_mapping_attribute_group, - &nd_numa_attribute_group, &acpi_nfit_region_attribute_group, NULL, }; diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index eb422527dd57..28e1b265aa63 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -697,11 +697,10 @@ static umode_t nd_numa_attr_visible(struct kobject *kobj, struct attribute *a, /* * nd_numa_attribute_group - NUMA attributes for all devices on an nd bus */ -struct attribute_group nd_numa_attribute_group = { +const struct attribute_group nd_numa_attribute_group = { .attrs = nd_numa_attributes, .is_visible = nd_numa_attr_visible, }; -EXPORT_SYMBOL_GPL(nd_numa_attribute_group); int nvdimm_bus_create_ndctl(struct nvdimm_bus *nvdimm_bus) { diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index 21e018bfa188..ec3d5f619957 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -240,6 +240,7 @@ void nvdimm_exit(void); void nd_region_exit(void); struct nvdimm; extern const struct attribute_group nd_device_attribute_group; +extern const struct attribute_group nd_numa_attribute_group; struct nvdimm_drvdata *to_ndd(struct nd_mapping *nd_mapping); int nvdimm_check_config_data(struct device *dev); int nvdimm_init_nsarea(struct nvdimm_drvdata *ndd); diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index 710b5111eaa8..e4281f806adc 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -765,6 +765,7 @@ EXPORT_SYMBOL_GPL(nd_region_attribute_group); static const struct attribute_group *nd_region_attribute_groups[] = { &nd_device_attribute_group, + &nd_numa_attribute_group, NULL, }; diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index d7dbf42498af..e9a4e25fc708 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -67,7 +67,6 @@ enum { extern struct attribute_group nvdimm_bus_attribute_group; extern struct attribute_group nvdimm_attribute_group; -extern struct attribute_group nd_numa_attribute_group; extern struct attribute_group nd_region_attribute_group; extern struct attribute_group nd_mapping_attribute_group; -- cgit v1.2.3-71-gd317 From 7c4fc8cde1641e3213eb1dafc6854331e9e0828c Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 12 Nov 2019 17:07:16 -0800 Subject: libnvdimm: Move nd_region_attribute_group to device_type A 'struct device_type' instance can carry default attributes for the device. Use this facility to remove the export of nd_region_attribute_group and put the responsibility on the core rather than leaf implementations to define this attribute. Cc: Ira Weiny Cc: Michael Ellerman Cc: "Oliver O'Halloran" Cc: Vishal Verma Cc: Aneesh Kumar K.V Signed-off-by: Dan Williams Reviewed-by: Aneesh Kumar K.V Link: https://lore.kernel.org/r/157309902169.1582359.16828508538444551337.stgit@dwillia2-desk3.amr.corp.intel.com --- arch/powerpc/platforms/pseries/papr_scm.c | 1 - drivers/acpi/nfit/core.c | 1 - drivers/nvdimm/e820.c | 6 ------ drivers/nvdimm/of_pmem.c | 6 ------ drivers/nvdimm/region_devs.c | 4 ++-- include/linux/libnvdimm.h | 1 - 6 files changed, 2 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 6ffda03a6349..6428834d7cd5 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -285,7 +285,6 @@ int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, } static const struct attribute_group *region_attr_groups[] = { - &nd_region_attribute_group, &nd_mapping_attribute_group, NULL, }; diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index b3213faf37b5..99e20b8b6ea0 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -2196,7 +2196,6 @@ static const struct attribute_group acpi_nfit_region_attribute_group = { }; static const struct attribute_group *acpi_nfit_region_attribute_groups[] = { - &nd_region_attribute_group, &nd_mapping_attribute_group, &acpi_nfit_region_attribute_group, NULL, diff --git a/drivers/nvdimm/e820.c b/drivers/nvdimm/e820.c index adde2864c6a4..9a971a59dec7 100644 --- a/drivers/nvdimm/e820.c +++ b/drivers/nvdimm/e820.c @@ -13,11 +13,6 @@ static const struct attribute_group *e820_pmem_attribute_groups[] = { NULL, }; -static const struct attribute_group *e820_pmem_region_attribute_groups[] = { - &nd_region_attribute_group, - NULL, -}; - static int e820_pmem_remove(struct platform_device *pdev) { struct nvdimm_bus *nvdimm_bus = platform_get_drvdata(pdev); @@ -45,7 +40,6 @@ static int e820_register_one(struct resource *res, void *data) memset(&ndr_desc, 0, sizeof(ndr_desc)); ndr_desc.res = res; - ndr_desc.attr_groups = e820_pmem_region_attribute_groups; ndr_desc.numa_node = e820_range_to_nid(res->start); ndr_desc.target_node = ndr_desc.numa_node; set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags); diff --git a/drivers/nvdimm/of_pmem.c b/drivers/nvdimm/of_pmem.c index 41348fa6b74c..c0b5ac36df9d 100644 --- a/drivers/nvdimm/of_pmem.c +++ b/drivers/nvdimm/of_pmem.c @@ -9,11 +9,6 @@ #include #include -static const struct attribute_group *region_attr_groups[] = { - &nd_region_attribute_group, - NULL, -}; - static const struct attribute_group *bus_attr_groups[] = { &nvdimm_bus_attribute_group, NULL, @@ -65,7 +60,6 @@ static int of_pmem_region_probe(struct platform_device *pdev) * structures so passing a stack pointer is fine. */ memset(&ndr_desc, 0, sizeof(ndr_desc)); - ndr_desc.attr_groups = region_attr_groups; ndr_desc.numa_node = dev_to_node(&pdev->dev); ndr_desc.target_node = ndr_desc.numa_node; ndr_desc.res = &pdev->resource[i]; diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index e4281f806adc..f97166583294 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -757,14 +757,14 @@ struct attribute_group nd_mapping_attribute_group = { }; EXPORT_SYMBOL_GPL(nd_mapping_attribute_group); -struct attribute_group nd_region_attribute_group = { +static const struct attribute_group nd_region_attribute_group = { .attrs = nd_region_attributes, .is_visible = region_visible, }; -EXPORT_SYMBOL_GPL(nd_region_attribute_group); static const struct attribute_group *nd_region_attribute_groups[] = { &nd_device_attribute_group, + &nd_region_attribute_group, &nd_numa_attribute_group, NULL, }; diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index e9a4e25fc708..312248d334c7 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -67,7 +67,6 @@ enum { extern struct attribute_group nvdimm_bus_attribute_group; extern struct attribute_group nvdimm_attribute_group; -extern struct attribute_group nd_region_attribute_group; extern struct attribute_group nd_mapping_attribute_group; struct nvdimm; -- cgit v1.2.3-71-gd317 From 4ce79fa97e6a54ee028063381346dc2fea91a76b Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 12 Nov 2019 17:07:39 -0800 Subject: libnvdimm: Move nd_mapping_attribute_group to device_type A 'struct device_type' instance can carry default attributes for the device. Use this facility to remove the export of nd_mapping_attribute_group and put the responsibility on the core rather than leaf implementations to define this attribute. Cc: Ira Weiny Cc: Michael Ellerman Cc: "Oliver O'Halloran" Cc: Vishal Verma Cc: Aneesh Kumar K.V Signed-off-by: Dan Williams Reviewed-by: Aneesh Kumar K.V Link: https://lore.kernel.org/r/157309902686.1582359.6749533709859492704.stgit@dwillia2-desk3.amr.corp.intel.com --- arch/powerpc/platforms/pseries/papr_scm.c | 6 ------ drivers/acpi/nfit/core.c | 1 - drivers/nvdimm/region_devs.c | 4 ++-- include/linux/libnvdimm.h | 1 - 4 files changed, 2 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 6428834d7cd5..0405fb769336 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -284,11 +284,6 @@ int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, return 0; } -static const struct attribute_group *region_attr_groups[] = { - &nd_mapping_attribute_group, - NULL, -}; - static const struct attribute_group *bus_attr_groups[] = { &nvdimm_bus_attribute_group, NULL, @@ -362,7 +357,6 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) mapping.size = p->blocks * p->block_size; // XXX: potential overflow? memset(&ndr_desc, 0, sizeof(ndr_desc)); - ndr_desc.attr_groups = region_attr_groups; target_nid = dev_to_node(&p->pdev->dev); online_nid = papr_scm_node(target_nid); ndr_desc.numa_node = online_nid; diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 99e20b8b6ea0..69c406ecc3a6 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -2196,7 +2196,6 @@ static const struct attribute_group acpi_nfit_region_attribute_group = { }; static const struct attribute_group *acpi_nfit_region_attribute_groups[] = { - &nd_mapping_attribute_group, &acpi_nfit_region_attribute_group, NULL, }; diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index f97166583294..0afc1973e938 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -751,11 +751,10 @@ static struct attribute *mapping_attributes[] = { NULL, }; -struct attribute_group nd_mapping_attribute_group = { +static const struct attribute_group nd_mapping_attribute_group = { .is_visible = mapping_visible, .attrs = mapping_attributes, }; -EXPORT_SYMBOL_GPL(nd_mapping_attribute_group); static const struct attribute_group nd_region_attribute_group = { .attrs = nd_region_attributes, @@ -766,6 +765,7 @@ static const struct attribute_group *nd_region_attribute_groups[] = { &nd_device_attribute_group, &nd_region_attribute_group, &nd_numa_attribute_group, + &nd_mapping_attribute_group, NULL, }; diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 312248d334c7..eb597d1cb891 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -67,7 +67,6 @@ enum { extern struct attribute_group nvdimm_bus_attribute_group; extern struct attribute_group nvdimm_attribute_group; -extern struct attribute_group nd_mapping_attribute_group; struct nvdimm; struct nvdimm_bus_descriptor; -- cgit v1.2.3-71-gd317 From 360eba7ebdf716194ed2ede1ebc3ce0f9790a91c Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 12 Nov 2019 17:08:04 -0800 Subject: libnvdimm: Move nvdimm_attribute_group to device_type A 'struct device_type' instance can carry default attributes for the device. Use this facility to remove the export of nvdimm_attribute_group and put the responsibility on the core rather than leaf implementations to define this attribute. Cc: Ira Weiny Cc: Michael Ellerman Cc: "Oliver O'Halloran" Cc: Vishal Verma Cc: Aneesh Kumar K.V Signed-off-by: Dan Williams Reviewed-by: Aneesh Kumar K.V Link: https://lore.kernel.org/r/157309903201.1582359.10966209746585062329.stgit@dwillia2-desk3.amr.corp.intel.com --- arch/powerpc/platforms/pseries/papr_scm.c | 9 ++------ drivers/acpi/nfit/core.c | 1 - drivers/nvdimm/dimm_devs.c | 36 +++++++++++++++---------------- include/linux/libnvdimm.h | 1 - 4 files changed, 20 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 0405fb769336..8354737ac340 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -289,11 +289,6 @@ static const struct attribute_group *bus_attr_groups[] = { NULL, }; -static const struct attribute_group *papr_scm_dimm_groups[] = { - &nvdimm_attribute_group, - NULL, -}; - static inline int papr_scm_node(int node) { int min_dist = INT_MAX, dist; @@ -339,8 +334,8 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) dimm_flags = 0; set_bit(NDD_ALIASING, &dimm_flags); - p->nvdimm = nvdimm_create(p->bus, p, papr_scm_dimm_groups, - dimm_flags, PAPR_SCM_DIMM_CMD_MASK, 0, NULL); + p->nvdimm = nvdimm_create(p->bus, p, NULL, dimm_flags, + PAPR_SCM_DIMM_CMD_MASK, 0, NULL); if (!p->nvdimm) { dev_err(dev, "Error creating DIMM object for %pOF\n", p->dn); goto err; diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 69c406ecc3a6..84fc1f865802 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -1698,7 +1698,6 @@ static const struct attribute_group acpi_nfit_dimm_attribute_group = { }; static const struct attribute_group *acpi_nfit_dimm_attribute_groups[] = { - &nvdimm_attribute_group, &acpi_nfit_dimm_attribute_group, NULL, }; diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c index 278867c68682..94ea6dba6b4f 100644 --- a/drivers/nvdimm/dimm_devs.c +++ b/drivers/nvdimm/dimm_devs.c @@ -202,22 +202,6 @@ static void nvdimm_release(struct device *dev) kfree(nvdimm); } -static const struct attribute_group *nvdimm_attribute_groups[] = { - &nd_device_attribute_group, - NULL, -}; - -static const struct device_type nvdimm_device_type = { - .name = "nvdimm", - .release = nvdimm_release, - .groups = nvdimm_attribute_groups, -}; - -bool is_nvdimm(struct device *dev) -{ - return dev->type == &nvdimm_device_type; -} - struct nvdimm *to_nvdimm(struct device *dev) { struct nvdimm *nvdimm = container_of(dev, struct nvdimm, dev); @@ -456,11 +440,27 @@ static umode_t nvdimm_visible(struct kobject *kobj, struct attribute *a, int n) return 0; } -struct attribute_group nvdimm_attribute_group = { +static const struct attribute_group nvdimm_attribute_group = { .attrs = nvdimm_attributes, .is_visible = nvdimm_visible, }; -EXPORT_SYMBOL_GPL(nvdimm_attribute_group); + +static const struct attribute_group *nvdimm_attribute_groups[] = { + &nd_device_attribute_group, + &nvdimm_attribute_group, + NULL, +}; + +static const struct device_type nvdimm_device_type = { + .name = "nvdimm", + .release = nvdimm_release, + .groups = nvdimm_attribute_groups, +}; + +bool is_nvdimm(struct device *dev) +{ + return dev->type == &nvdimm_device_type; +} struct nvdimm *__nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data, const struct attribute_group **groups, diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index eb597d1cb891..3644af97bcb4 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -66,7 +66,6 @@ enum { }; extern struct attribute_group nvdimm_bus_attribute_group; -extern struct attribute_group nvdimm_attribute_group; struct nvdimm; struct nvdimm_bus_descriptor; -- cgit v1.2.3-71-gd317 From e755799aefa9385469bec49b2c2ccf1aaa33829a Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 12 Nov 2019 17:08:56 -0800 Subject: libnvdimm: Move nvdimm_bus_attribute_group to device_type A 'struct device_type' instance can carry default attributes for the device. Use this facility to remove the export of nvdimm_bus_attribute_group and put the responsibility on the core rather than leaf implementations to define this attribute. Cc: Ira Weiny Cc: Michael Ellerman Cc: "Oliver O'Halloran" Cc: Vishal Verma Cc: Aneesh Kumar K.V Signed-off-by: Dan Williams Reviewed-by: Aneesh Kumar K.V Link: https://lore.kernel.org/r/157309903815.1582359.6418211876315050283.stgit@dwillia2-desk3.amr.corp.intel.com --- arch/powerpc/platforms/pseries/papr_scm.c | 6 ------ drivers/acpi/nfit/core.c | 1 - drivers/nvdimm/bus.c | 9 +++++++-- drivers/nvdimm/core.c | 8 ++++++-- drivers/nvdimm/e820.c | 6 ------ drivers/nvdimm/nd.h | 1 + drivers/nvdimm/of_pmem.c | 6 ------ include/linux/libnvdimm.h | 2 -- 8 files changed, 14 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 8354737ac340..33aa59e666e5 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -284,11 +284,6 @@ int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, return 0; } -static const struct attribute_group *bus_attr_groups[] = { - &nvdimm_bus_attribute_group, - NULL, -}; - static inline int papr_scm_node(int node) { int min_dist = INT_MAX, dist; @@ -319,7 +314,6 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) p->bus_desc.ndctl = papr_scm_ndctl; p->bus_desc.module = THIS_MODULE; p->bus_desc.of_node = p->pdev->dev.of_node; - p->bus_desc.attr_groups = bus_attr_groups; p->bus_desc.provider_name = kstrdup(p->pdev->name, GFP_KERNEL); if (!p->bus_desc.provider_name) diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 84fc1f865802..a3320f93616d 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -1404,7 +1404,6 @@ static const struct attribute_group acpi_nfit_attribute_group = { }; static const struct attribute_group *acpi_nfit_attribute_groups[] = { - &nvdimm_bus_attribute_group, &acpi_nfit_attribute_group, NULL, }; diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 28e1b265aa63..1d330d46d036 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -300,9 +300,14 @@ static void nvdimm_bus_release(struct device *dev) kfree(nvdimm_bus); } +static const struct device_type nvdimm_bus_dev_type = { + .release = nvdimm_bus_release, + .groups = nvdimm_bus_attribute_groups, +}; + bool is_nvdimm_bus(struct device *dev) { - return dev->release == nvdimm_bus_release; + return dev->type == &nvdimm_bus_dev_type; } struct nvdimm_bus *walk_to_nvdimm_bus(struct device *nd_dev) @@ -355,7 +360,7 @@ struct nvdimm_bus *nvdimm_bus_register(struct device *parent, badrange_init(&nvdimm_bus->badrange); nvdimm_bus->nd_desc = nd_desc; nvdimm_bus->dev.parent = parent; - nvdimm_bus->dev.release = nvdimm_bus_release; + nvdimm_bus->dev.type = &nvdimm_bus_dev_type; nvdimm_bus->dev.groups = nd_desc->attr_groups; nvdimm_bus->dev.bus = &nvdimm_bus_type; nvdimm_bus->dev.of_node = nd_desc->of_node; diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c index 9204f1e9fd14..81231ca23db0 100644 --- a/drivers/nvdimm/core.c +++ b/drivers/nvdimm/core.c @@ -385,10 +385,14 @@ static struct attribute *nvdimm_bus_attributes[] = { NULL, }; -struct attribute_group nvdimm_bus_attribute_group = { +static const struct attribute_group nvdimm_bus_attribute_group = { .attrs = nvdimm_bus_attributes, }; -EXPORT_SYMBOL_GPL(nvdimm_bus_attribute_group); + +const struct attribute_group *nvdimm_bus_attribute_groups[] = { + &nvdimm_bus_attribute_group, + NULL, +}; int nvdimm_bus_add_badrange(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length) { diff --git a/drivers/nvdimm/e820.c b/drivers/nvdimm/e820.c index 9a971a59dec7..e02f60ad6c99 100644 --- a/drivers/nvdimm/e820.c +++ b/drivers/nvdimm/e820.c @@ -8,11 +8,6 @@ #include #include -static const struct attribute_group *e820_pmem_attribute_groups[] = { - &nvdimm_bus_attribute_group, - NULL, -}; - static int e820_pmem_remove(struct platform_device *pdev) { struct nvdimm_bus *nvdimm_bus = platform_get_drvdata(pdev); @@ -55,7 +50,6 @@ static int e820_pmem_probe(struct platform_device *pdev) struct nvdimm_bus *nvdimm_bus; int rc = -ENXIO; - nd_desc.attr_groups = e820_pmem_attribute_groups; nd_desc.provider_name = "e820"; nd_desc.module = THIS_MODULE; nvdimm_bus = nvdimm_bus_register(dev, &nd_desc); diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index ec3d5f619957..c9f6a5b5253a 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -241,6 +241,7 @@ void nd_region_exit(void); struct nvdimm; extern const struct attribute_group nd_device_attribute_group; extern const struct attribute_group nd_numa_attribute_group; +extern const struct attribute_group *nvdimm_bus_attribute_groups[]; struct nvdimm_drvdata *to_ndd(struct nd_mapping *nd_mapping); int nvdimm_check_config_data(struct device *dev); int nvdimm_init_nsarea(struct nvdimm_drvdata *ndd); diff --git a/drivers/nvdimm/of_pmem.c b/drivers/nvdimm/of_pmem.c index c0b5ac36df9d..8224d1431ea9 100644 --- a/drivers/nvdimm/of_pmem.c +++ b/drivers/nvdimm/of_pmem.c @@ -9,11 +9,6 @@ #include #include -static const struct attribute_group *bus_attr_groups[] = { - &nvdimm_bus_attribute_group, - NULL, -}; - struct of_pmem_private { struct nvdimm_bus_descriptor bus_desc; struct nvdimm_bus *bus; @@ -35,7 +30,6 @@ static int of_pmem_region_probe(struct platform_device *pdev) if (!priv) return -ENOMEM; - priv->bus_desc.attr_groups = bus_attr_groups; priv->bus_desc.provider_name = kstrdup(pdev->name, GFP_KERNEL); priv->bus_desc.module = THIS_MODULE; priv->bus_desc.of_node = np; diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 3644af97bcb4..9df091bd30ba 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -65,8 +65,6 @@ enum { DPA_RESOURCE_ADJUSTED = 1 << 0, }; -extern struct attribute_group nvdimm_bus_attribute_group; - struct nvdimm; struct nvdimm_bus_descriptor; typedef int (*ndctl_fn)(struct nvdimm_bus_descriptor *nd_desc, -- cgit v1.2.3-71-gd317 From ba31c1a48538992316cc71ce94fa9cd3e7b427c0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 6 Nov 2019 22:55:36 +0100 Subject: futex: Move futex exit handling into futex code The futex exit handling is #ifdeffed into mm_release() which is not pretty to begin with. But upcoming changes to address futex exit races need to add more functionality to this exit code. Split it out into a function, move it into futex code and make the various futex exit functions static. Preparatory only and no functional change. Folded build fix from Borislav. Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Acked-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20191106224556.049705556@linutronix.de --- include/linux/compat.h | 2 -- include/linux/futex.h | 29 ++++++++++++++++------------- kernel/fork.c | 25 +++---------------------- kernel/futex.c | 33 +++++++++++++++++++++++++++++---- 4 files changed, 48 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 16dafd9f4b86..c4c389c7e1b4 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -410,8 +410,6 @@ struct compat_kexec_segment; struct compat_mq_attr; struct compat_msgbuf; -extern void compat_exit_robust_list(struct task_struct *curr); - #define BITS_PER_COMPAT_LONG (8*sizeof(compat_long_t)) #define BITS_TO_COMPAT_LONGS(bits) DIV_ROUND_UP(bits, BITS_PER_COMPAT_LONG) diff --git a/include/linux/futex.h b/include/linux/futex.h index ccaef0097785..d6ed11c51a8e 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -2,7 +2,9 @@ #ifndef _LINUX_FUTEX_H #define _LINUX_FUTEX_H +#include #include + #include struct inode; @@ -48,15 +50,24 @@ union futex_key { #define FUTEX_KEY_INIT (union futex_key) { .both = { .ptr = NULL } } #ifdef CONFIG_FUTEX -extern void exit_robust_list(struct task_struct *curr); -long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, - u32 __user *uaddr2, u32 val2, u32 val3); -#else -static inline void exit_robust_list(struct task_struct *curr) +static inline void futex_init_task(struct task_struct *tsk) { + tsk->robust_list = NULL; +#ifdef CONFIG_COMPAT + tsk->compat_robust_list = NULL; +#endif + INIT_LIST_HEAD(&tsk->pi_state_list); + tsk->pi_state_cache = NULL; } +void futex_mm_release(struct task_struct *tsk); + +long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, + u32 __user *uaddr2, u32 val2, u32 val3); +#else +static inline void futex_init_task(struct task_struct *tsk) { } +static inline void futex_mm_release(struct task_struct *tsk) { } static inline long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3) @@ -65,12 +76,4 @@ static inline long do_futex(u32 __user *uaddr, int op, u32 val, } #endif -#ifdef CONFIG_FUTEX_PI -extern void exit_pi_state_list(struct task_struct *curr); -#else -static inline void exit_pi_state_list(struct task_struct *curr) -{ -} -#endif - #endif diff --git a/kernel/fork.c b/kernel/fork.c index bcdf53125210..bd7c218691d4 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1286,20 +1286,7 @@ static int wait_for_vfork_done(struct task_struct *child, void mm_release(struct task_struct *tsk, struct mm_struct *mm) { /* Get rid of any futexes when releasing the mm */ -#ifdef CONFIG_FUTEX - if (unlikely(tsk->robust_list)) { - exit_robust_list(tsk); - tsk->robust_list = NULL; - } -#ifdef CONFIG_COMPAT - if (unlikely(tsk->compat_robust_list)) { - compat_exit_robust_list(tsk); - tsk->compat_robust_list = NULL; - } -#endif - if (unlikely(!list_empty(&tsk->pi_state_list))) - exit_pi_state_list(tsk); -#endif + futex_mm_release(tsk); uprobe_free_utask(tsk); @@ -2062,14 +2049,8 @@ static __latent_entropy struct task_struct *copy_process( #ifdef CONFIG_BLOCK p->plug = NULL; #endif -#ifdef CONFIG_FUTEX - p->robust_list = NULL; -#ifdef CONFIG_COMPAT - p->compat_robust_list = NULL; -#endif - INIT_LIST_HEAD(&p->pi_state_list); - p->pi_state_cache = NULL; -#endif + futex_init_task(p); + /* * sigaltstack should be cleared when sharing the same VM */ diff --git a/kernel/futex.c b/kernel/futex.c index 49eaf5be851a..f8f00d47c821 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -325,6 +325,12 @@ static inline bool should_fail_futex(bool fshared) } #endif /* CONFIG_FAIL_FUTEX */ +#ifdef CONFIG_COMPAT +static void compat_exit_robust_list(struct task_struct *curr); +#else +static inline void compat_exit_robust_list(struct task_struct *curr) { } +#endif + static inline void futex_get_mm(union futex_key *key) { mmgrab(key->private.mm); @@ -890,7 +896,7 @@ static void put_pi_state(struct futex_pi_state *pi_state) * Kernel cleans up PI-state, but userspace is likely hosed. * (Robust-futex cleanup is separate and might save the day for userspace.) */ -void exit_pi_state_list(struct task_struct *curr) +static void exit_pi_state_list(struct task_struct *curr) { struct list_head *next, *head = &curr->pi_state_list; struct futex_pi_state *pi_state; @@ -960,7 +966,8 @@ void exit_pi_state_list(struct task_struct *curr) } raw_spin_unlock_irq(&curr->pi_lock); } - +#else +static inline void exit_pi_state_list(struct task_struct *curr) { } #endif /* @@ -3588,7 +3595,7 @@ static inline int fetch_robust_entry(struct robust_list __user **entry, * * We silently return on any sign of list-walking problem. */ -void exit_robust_list(struct task_struct *curr) +static void exit_robust_list(struct task_struct *curr) { struct robust_list_head __user *head = curr->robust_list; struct robust_list __user *entry, *next_entry, *pending; @@ -3653,6 +3660,24 @@ void exit_robust_list(struct task_struct *curr) } } +void futex_mm_release(struct task_struct *tsk) +{ + if (unlikely(tsk->robust_list)) { + exit_robust_list(tsk); + tsk->robust_list = NULL; + } + +#ifdef CONFIG_COMPAT + if (unlikely(tsk->compat_robust_list)) { + compat_exit_robust_list(tsk); + tsk->compat_robust_list = NULL; + } +#endif + + if (unlikely(!list_empty(&tsk->pi_state_list))) + exit_pi_state_list(tsk); +} + long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3) { @@ -3780,7 +3805,7 @@ static void __user *futex_uaddr(struct robust_list __user *entry, * * We silently return on any sign of list-walking problem. */ -void compat_exit_robust_list(struct task_struct *curr) +static void compat_exit_robust_list(struct task_struct *curr) { struct compat_robust_list_head __user *head = curr->compat_robust_list; struct robust_list __user *entry, *next_entry, *pending; -- cgit v1.2.3-71-gd317 From 3d4775df0a89240f671861c6ab6e8d59af8e9e41 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 6 Nov 2019 22:55:37 +0100 Subject: futex: Replace PF_EXITPIDONE with a state The futex exit handling relies on PF_ flags. That's suboptimal as it requires a smp_mb() and an ugly lock/unlock of the exiting tasks pi_lock in the middle of do_exit() to enforce the observability of PF_EXITING in the futex code. Add a futex_state member to task_struct and convert the PF_EXITPIDONE logic over to the new state. The PF_EXITING dependency will be cleaned up in a later step. This prepares for handling various futex exit issues later. Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Acked-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20191106224556.149449274@linutronix.de --- include/linux/futex.h | 33 +++++++++++++++++++++++++++++++++ include/linux/sched.h | 2 +- kernel/exit.c | 18 ++---------------- kernel/futex.c | 25 +++++++++++++------------ 4 files changed, 49 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/futex.h b/include/linux/futex.h index d6ed11c51a8e..025ad96bcf9d 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -50,6 +50,10 @@ union futex_key { #define FUTEX_KEY_INIT (union futex_key) { .both = { .ptr = NULL } } #ifdef CONFIG_FUTEX +enum { + FUTEX_STATE_OK, + FUTEX_STATE_DEAD, +}; static inline void futex_init_task(struct task_struct *tsk) { @@ -59,6 +63,34 @@ static inline void futex_init_task(struct task_struct *tsk) #endif INIT_LIST_HEAD(&tsk->pi_state_list); tsk->pi_state_cache = NULL; + tsk->futex_state = FUTEX_STATE_OK; +} + +/** + * futex_exit_done - Sets the tasks futex state to FUTEX_STATE_DEAD + * @tsk: task to set the state on + * + * Set the futex exit state of the task lockless. The futex waiter code + * observes that state when a task is exiting and loops until the task has + * actually finished the futex cleanup. The worst case for this is that the + * waiter runs through the wait loop until the state becomes visible. + * + * This has two callers: + * + * - futex_mm_release() after the futex exit cleanup has been done + * + * - do_exit() from the recursive fault handling path. + * + * In case of a recursive fault this is best effort. Either the futex exit + * code has run already or not. If the OWNER_DIED bit has been set on the + * futex then the waiter can take it over. If not, the problem is pushed + * back to user space. If the futex exit code did not run yet, then an + * already queued waiter might block forever, but there is nothing which + * can be done about that. + */ +static inline void futex_exit_done(struct task_struct *tsk) +{ + tsk->futex_state = FUTEX_STATE_DEAD; } void futex_mm_release(struct task_struct *tsk); @@ -68,6 +100,7 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, #else static inline void futex_init_task(struct task_struct *tsk) { } static inline void futex_mm_release(struct task_struct *tsk) { } +static inline void futex_exit_done(struct task_struct *tsk) { } static inline long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3) diff --git a/include/linux/sched.h b/include/linux/sched.h index 2c2e56bd8913..85dab2f721c9 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1053,6 +1053,7 @@ struct task_struct { #endif struct list_head pi_state_list; struct futex_pi_state *pi_state_cache; + unsigned int futex_state; #endif #ifdef CONFIG_PERF_EVENTS struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts]; @@ -1441,7 +1442,6 @@ extern struct pid *cad_pid; */ #define PF_IDLE 0x00000002 /* I am an IDLE thread */ #define PF_EXITING 0x00000004 /* Getting shut down */ -#define PF_EXITPIDONE 0x00000008 /* PI exit done on shut down */ #define PF_VCPU 0x00000010 /* I'm a virtual CPU */ #define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */ #define PF_FORKNOEXEC 0x00000040 /* Forked but didn't exec */ diff --git a/kernel/exit.c b/kernel/exit.c index a46a50d67002..d11bdcaac2e1 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -746,16 +746,7 @@ void __noreturn do_exit(long code) */ if (unlikely(tsk->flags & PF_EXITING)) { pr_alert("Fixing recursive fault but reboot is needed!\n"); - /* - * We can do this unlocked here. The futex code uses - * this flag just to verify whether the pi state - * cleanup has been done or not. In the worst case it - * loops once more. We pretend that the cleanup was - * done as there is no way to return. Either the - * OWNER_DIED bit is set by now or we push the blocked - * task into the wait for ever nirwana as well. - */ - tsk->flags |= PF_EXITPIDONE; + futex_exit_done(tsk); set_current_state(TASK_UNINTERRUPTIBLE); schedule(); } @@ -846,12 +837,7 @@ void __noreturn do_exit(long code) * Make sure we are holding no locks: */ debug_check_no_locks_held(); - /* - * We can do this unlocked here. The futex code uses this flag - * just to verify whether the pi state cleanup has been done - * or not. In the worst case it loops once more. - */ - tsk->flags |= PF_EXITPIDONE; + futex_exit_done(tsk); if (tsk->io_context) exit_io_context(tsk); diff --git a/kernel/futex.c b/kernel/futex.c index f8f00d47c821..41c75277d7d1 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1182,9 +1182,10 @@ static int handle_exit_race(u32 __user *uaddr, u32 uval, u32 uval2; /* - * If PF_EXITPIDONE is not yet set, then try again. + * If the futex exit state is not yet FUTEX_STATE_DEAD, wait + * for it to finish. */ - if (tsk && !(tsk->flags & PF_EXITPIDONE)) + if (tsk && tsk->futex_state != FUTEX_STATE_DEAD) return -EAGAIN; /* @@ -1203,8 +1204,9 @@ static int handle_exit_race(u32 __user *uaddr, u32 uval, * *uaddr = 0xC0000000; tsk = get_task(PID); * } if (!tsk->flags & PF_EXITING) { * ... attach(); - * tsk->flags |= PF_EXITPIDONE; } else { - * if (!(tsk->flags & PF_EXITPIDONE)) + * tsk->futex_state = } else { + * FUTEX_STATE_DEAD; if (tsk->futex_state != + * FUTEX_STATE_DEAD) * return -EAGAIN; * return -ESRCH; <--- FAIL * } @@ -1260,17 +1262,16 @@ static int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key, } /* - * We need to look at the task state flags to figure out, - * whether the task is exiting. To protect against the do_exit - * change of the task flags, we do this protected by - * p->pi_lock: + * We need to look at the task state to figure out, whether the + * task is exiting. To protect against the change of the task state + * in futex_exit_release(), we do this protected by p->pi_lock: */ raw_spin_lock_irq(&p->pi_lock); - if (unlikely(p->flags & PF_EXITING)) { + if (unlikely(p->futex_state != FUTEX_STATE_OK)) { /* - * The task is on the way out. When PF_EXITPIDONE is - * set, we know that the task has finished the - * cleanup: + * The task is on the way out. When the futex state is + * FUTEX_STATE_DEAD, we know that the task has finished + * the cleanup: */ int ret = handle_exit_race(uaddr, uval, p); -- cgit v1.2.3-71-gd317 From 4610ba7ad877fafc0a25a30c6c82015304120426 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 6 Nov 2019 22:55:38 +0100 Subject: exit/exec: Seperate mm_release() mm_release() contains the futex exit handling. mm_release() is called from do_exit()->exit_mm() and from exec()->exec_mm(). In the exit_mm() case PF_EXITING and the futex state is updated. In the exec_mm() case these states are not touched. As the futex exit code needs further protections against exit races, this needs to be split into two functions. Preparatory only, no functional change. Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Acked-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20191106224556.240518241@linutronix.de --- fs/exec.c | 2 +- include/linux/sched/mm.h | 6 ++++-- kernel/exit.c | 2 +- kernel/fork.c | 12 +++++++++++- 4 files changed, 17 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/exec.c b/fs/exec.c index 555e93c7dec8..c27231234764 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1015,7 +1015,7 @@ static int exec_mmap(struct mm_struct *mm) /* Notify parent that we're no longer interested in the old VM */ tsk = current; old_mm = current->mm; - mm_release(tsk, old_mm); + exec_mm_release(tsk, old_mm); if (old_mm) { sync_mm_rss(old_mm); diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index e6770012db18..c49257a3b510 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -117,8 +117,10 @@ extern struct mm_struct *get_task_mm(struct task_struct *task); * succeeds. */ extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode); -/* Remove the current tasks stale references to the old mm_struct */ -extern void mm_release(struct task_struct *, struct mm_struct *); +/* Remove the current tasks stale references to the old mm_struct on exit() */ +extern void exit_mm_release(struct task_struct *, struct mm_struct *); +/* Remove the current tasks stale references to the old mm_struct on exec() */ +extern void exec_mm_release(struct task_struct *, struct mm_struct *); #ifdef CONFIG_MEMCG extern void mm_update_next_owner(struct mm_struct *mm); diff --git a/kernel/exit.c b/kernel/exit.c index d11bdcaac2e1..cd893b530902 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -437,7 +437,7 @@ static void exit_mm(void) struct mm_struct *mm = current->mm; struct core_state *core_state; - mm_release(current, mm); + exit_mm_release(current, mm); if (!mm) return; sync_mm_rss(mm); diff --git a/kernel/fork.c b/kernel/fork.c index bd7c218691d4..096f9d840bb8 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1283,7 +1283,7 @@ static int wait_for_vfork_done(struct task_struct *child, * restoring the old one. . . * Eric Biederman 10 January 1998 */ -void mm_release(struct task_struct *tsk, struct mm_struct *mm) +static void mm_release(struct task_struct *tsk, struct mm_struct *mm) { /* Get rid of any futexes when releasing the mm */ futex_mm_release(tsk); @@ -1320,6 +1320,16 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm) complete_vfork_done(tsk); } +void exit_mm_release(struct task_struct *tsk, struct mm_struct *mm) +{ + mm_release(tsk, mm); +} + +void exec_mm_release(struct task_struct *tsk, struct mm_struct *mm) +{ + mm_release(tsk, mm); +} + /** * dup_mm() - duplicates an existing mm structure * @tsk: the task_struct with which the new mm will be associated. -- cgit v1.2.3-71-gd317 From 150d71584b12809144b8145b817e83b81158ae5f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 6 Nov 2019 22:55:39 +0100 Subject: futex: Split futex_mm_release() for exit/exec To allow separate handling of the futex exit state in the futex exit code for exit and exec, split futex_mm_release() into two functions and invoke them from the corresponding exit/exec_mm_release() callsites. Preparatory only, no functional change. Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Acked-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20191106224556.332094221@linutronix.de --- include/linux/futex.h | 6 ++++-- kernel/fork.c | 5 ++--- kernel/futex.c | 7 ++++++- 3 files changed, 12 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/futex.h b/include/linux/futex.h index 025ad96bcf9d..6414cfaf88e0 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -93,14 +93,16 @@ static inline void futex_exit_done(struct task_struct *tsk) tsk->futex_state = FUTEX_STATE_DEAD; } -void futex_mm_release(struct task_struct *tsk); +void futex_exit_release(struct task_struct *tsk); +void futex_exec_release(struct task_struct *tsk); long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3); #else static inline void futex_init_task(struct task_struct *tsk) { } -static inline void futex_mm_release(struct task_struct *tsk) { } static inline void futex_exit_done(struct task_struct *tsk) { } +static inline void futex_exit_release(struct task_struct *tsk) { } +static inline void futex_exec_release(struct task_struct *tsk) { } static inline long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3) diff --git a/kernel/fork.c b/kernel/fork.c index 096f9d840bb8..f1eb4d1f1a3b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1285,9 +1285,6 @@ static int wait_for_vfork_done(struct task_struct *child, */ static void mm_release(struct task_struct *tsk, struct mm_struct *mm) { - /* Get rid of any futexes when releasing the mm */ - futex_mm_release(tsk); - uprobe_free_utask(tsk); /* Get rid of any cached register state */ @@ -1322,11 +1319,13 @@ static void mm_release(struct task_struct *tsk, struct mm_struct *mm) void exit_mm_release(struct task_struct *tsk, struct mm_struct *mm) { + futex_exit_release(tsk); mm_release(tsk, mm); } void exec_mm_release(struct task_struct *tsk, struct mm_struct *mm) { + futex_exec_release(tsk); mm_release(tsk, mm); } diff --git a/kernel/futex.c b/kernel/futex.c index 41c75277d7d1..909e4d3c3099 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -3661,7 +3661,7 @@ static void exit_robust_list(struct task_struct *curr) } } -void futex_mm_release(struct task_struct *tsk) +void futex_exec_release(struct task_struct *tsk) { if (unlikely(tsk->robust_list)) { exit_robust_list(tsk); @@ -3679,6 +3679,11 @@ void futex_mm_release(struct task_struct *tsk) exit_pi_state_list(tsk); } +void futex_exit_release(struct task_struct *tsk) +{ + futex_exec_release(tsk); +} + long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3) { -- cgit v1.2.3-71-gd317 From 18f694385c4fd77a09851fd301236746ca83f3cb Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 6 Nov 2019 22:55:41 +0100 Subject: futex: Mark the begin of futex exit explicitly Instead of relying on PF_EXITING use an explicit state for the futex exit and set it in the futex exit function. This moves the smp barrier and the lock/unlock serialization into the futex code. As with the DEAD state this is restricted to the exit path as exec continues to use the same task struct. This allows to simplify that logic in a next step. Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Acked-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20191106224556.539409004@linutronix.de --- include/linux/futex.h | 31 +++---------------------------- kernel/exit.c | 13 +------------ kernel/futex.c | 37 ++++++++++++++++++++++++++++++++++++- 3 files changed, 40 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/futex.h b/include/linux/futex.h index 6414cfaf88e0..9f2792427d64 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -52,6 +52,7 @@ union futex_key { #ifdef CONFIG_FUTEX enum { FUTEX_STATE_OK, + FUTEX_STATE_EXITING, FUTEX_STATE_DEAD, }; @@ -66,33 +67,7 @@ static inline void futex_init_task(struct task_struct *tsk) tsk->futex_state = FUTEX_STATE_OK; } -/** - * futex_exit_done - Sets the tasks futex state to FUTEX_STATE_DEAD - * @tsk: task to set the state on - * - * Set the futex exit state of the task lockless. The futex waiter code - * observes that state when a task is exiting and loops until the task has - * actually finished the futex cleanup. The worst case for this is that the - * waiter runs through the wait loop until the state becomes visible. - * - * This has two callers: - * - * - futex_mm_release() after the futex exit cleanup has been done - * - * - do_exit() from the recursive fault handling path. - * - * In case of a recursive fault this is best effort. Either the futex exit - * code has run already or not. If the OWNER_DIED bit has been set on the - * futex then the waiter can take it over. If not, the problem is pushed - * back to user space. If the futex exit code did not run yet, then an - * already queued waiter might block forever, but there is nothing which - * can be done about that. - */ -static inline void futex_exit_done(struct task_struct *tsk) -{ - tsk->futex_state = FUTEX_STATE_DEAD; -} - +void futex_exit_recursive(struct task_struct *tsk); void futex_exit_release(struct task_struct *tsk); void futex_exec_release(struct task_struct *tsk); @@ -100,7 +75,7 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3); #else static inline void futex_init_task(struct task_struct *tsk) { } -static inline void futex_exit_done(struct task_struct *tsk) { } +static inline void futex_exit_recursive(struct task_struct *tsk) { } static inline void futex_exit_release(struct task_struct *tsk) { } static inline void futex_exec_release(struct task_struct *tsk) { } static inline long do_futex(u32 __user *uaddr, int op, u32 val, diff --git a/kernel/exit.c b/kernel/exit.c index f3b8fa1b8945..d351fd09e739 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -746,23 +746,12 @@ void __noreturn do_exit(long code) */ if (unlikely(tsk->flags & PF_EXITING)) { pr_alert("Fixing recursive fault but reboot is needed!\n"); - futex_exit_done(tsk); + futex_exit_recursive(tsk); set_current_state(TASK_UNINTERRUPTIBLE); schedule(); } exit_signals(tsk); /* sets PF_EXITING */ - /* - * Ensure that all new tsk->pi_lock acquisitions must observe - * PF_EXITING. Serializes against futex.c:attach_to_pi_owner(). - */ - smp_mb(); - /* - * Ensure that we must observe the pi_state in exit_mm() -> - * mm_release() -> exit_pi_state_list(). - */ - raw_spin_lock_irq(&tsk->pi_lock); - raw_spin_unlock_irq(&tsk->pi_lock); if (unlikely(in_atomic())) { pr_info("note: %s[%d] exited with preempt_count %d\n", diff --git a/kernel/futex.c b/kernel/futex.c index 426dd71e170d..3488fb024a20 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -3679,10 +3679,45 @@ void futex_exec_release(struct task_struct *tsk) exit_pi_state_list(tsk); } +/** + * futex_exit_recursive - Set the tasks futex state to FUTEX_STATE_DEAD + * @tsk: task to set the state on + * + * Set the futex exit state of the task lockless. The futex waiter code + * observes that state when a task is exiting and loops until the task has + * actually finished the futex cleanup. The worst case for this is that the + * waiter runs through the wait loop until the state becomes visible. + * + * This is called from the recursive fault handling path in do_exit(). + * + * This is best effort. Either the futex exit code has run already or + * not. If the OWNER_DIED bit has been set on the futex then the waiter can + * take it over. If not, the problem is pushed back to user space. If the + * futex exit code did not run yet, then an already queued waiter might + * block forever, but there is nothing which can be done about that. + */ +void futex_exit_recursive(struct task_struct *tsk) +{ + tsk->futex_state = FUTEX_STATE_DEAD; +} + void futex_exit_release(struct task_struct *tsk) { + tsk->futex_state = FUTEX_STATE_EXITING; + /* + * Ensure that all new tsk->pi_lock acquisitions must observe + * FUTEX_STATE_EXITING. Serializes against attach_to_pi_owner(). + */ + smp_mb(); + /* + * Ensure that we must observe the pi_state in exit_pi_state_list(). + */ + raw_spin_lock_irq(&tsk->pi_lock); + raw_spin_unlock_irq(&tsk->pi_lock); + futex_exec_release(tsk); - futex_exit_done(tsk); + + tsk->futex_state = FUTEX_STATE_DEAD; } long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, -- cgit v1.2.3-71-gd317 From 3f186d974826847a07bc7964d79ec4eded475ad9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 6 Nov 2019 22:55:44 +0100 Subject: futex: Add mutex around futex exit The mutex will be used in subsequent changes to replace the busy looping of a waiter when the futex owner is currently executing the exit cleanup to prevent a potential live lock. Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Acked-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20191106224556.845798895@linutronix.de --- include/linux/futex.h | 1 + include/linux/sched.h | 1 + kernel/futex.c | 16 ++++++++++++++++ 3 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/futex.h b/include/linux/futex.h index 9f2792427d64..5cc3fed27d4c 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -65,6 +65,7 @@ static inline void futex_init_task(struct task_struct *tsk) INIT_LIST_HEAD(&tsk->pi_state_list); tsk->pi_state_cache = NULL; tsk->futex_state = FUTEX_STATE_OK; + mutex_init(&tsk->futex_exit_mutex); } void futex_exit_recursive(struct task_struct *tsk); diff --git a/include/linux/sched.h b/include/linux/sched.h index 85dab2f721c9..1ebe540f8a08 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1053,6 +1053,7 @@ struct task_struct { #endif struct list_head pi_state_list; struct futex_pi_state *pi_state_cache; + struct mutex futex_exit_mutex; unsigned int futex_state; #endif #ifdef CONFIG_PERF_EVENTS diff --git a/kernel/futex.c b/kernel/futex.c index 0c9850af2724..46a81e611065 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -3698,11 +3698,22 @@ static void futex_cleanup(struct task_struct *tsk) */ void futex_exit_recursive(struct task_struct *tsk) { + /* If the state is FUTEX_STATE_EXITING then futex_exit_mutex is held */ + if (tsk->futex_state == FUTEX_STATE_EXITING) + mutex_unlock(&tsk->futex_exit_mutex); tsk->futex_state = FUTEX_STATE_DEAD; } static void futex_cleanup_begin(struct task_struct *tsk) { + /* + * Prevent various race issues against a concurrent incoming waiter + * including live locks by forcing the waiter to block on + * tsk->futex_exit_mutex when it observes FUTEX_STATE_EXITING in + * attach_to_pi_owner(). + */ + mutex_lock(&tsk->futex_exit_mutex); + /* * Switch the state to FUTEX_STATE_EXITING under tsk->pi_lock. * @@ -3726,6 +3737,11 @@ static void futex_cleanup_end(struct task_struct *tsk, int state) * take another loop until it becomes visible. */ tsk->futex_state = state; + /* + * Drop the exit protection. This unblocks waiters which observed + * FUTEX_STATE_EXITING to reevaluate the state. + */ + mutex_unlock(&tsk->futex_exit_mutex); } void futex_exec_release(struct task_struct *tsk) -- cgit v1.2.3-71-gd317 From c55b51a06b01d67a99457bb82a8c31081c7faa23 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Sat, 16 Nov 2019 14:16:12 +0100 Subject: cpuidle: Allow idle injection to apply exit latency limit In some cases it may be useful to specify an exit latency limit for the idle state to be used during CPU idle time injection. Instead of duplicating the information in struct cpuidle_device or propagating the latency limit in the call stack, replace the use_deepest_state field with forced_latency_limit_ns to represent that limit, so that the deepest idle state with exit latency within that limit is forced (i.e. no governors) when it is set. A zero exit latency limit for forced idle means to use governors in the usual way (analogous to use_deepest_state equal to "false" before this change). Additionally, add play_idle_precise() taking two arguments, the duration of forced idle and the idle state exit latency limit, both in nanoseconds, and redefine play_idle() as a wrapper around that new function. This change is preparatory, no functional impact is expected. Suggested-by: Rafael J. Wysocki Signed-off-by: Daniel Lezcano [ rjw: Subject, changelog, cpuidle_use_deepest_state() kerneldoc, whitespace ] Signed-off-by: Rafael J. Wysocki --- drivers/cpuidle/cpuidle.c | 13 +++++++------ include/linux/cpu.h | 7 ++++++- include/linux/cpuidle.h | 6 +++--- kernel/sched/idle.c | 14 +++++++------- 4 files changed, 23 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index bf9b030cd7e1..12077db1158e 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -99,20 +99,21 @@ static int find_deepest_state(struct cpuidle_driver *drv, } /** - * cpuidle_use_deepest_state - Set/clear governor override flag. - * @enable: New value of the flag. + * cpuidle_use_deepest_state - Set/unset governor override mode. + * @latency_limit_ns: Idle state exit latency limit (or no override if 0). * - * Set/unset the current CPU to use the deepest idle state (override governors - * going forward if set). + * If @latency_limit_ns is nonzero, set the current CPU to use the deepest idle + * state with exit latency within @latency_limit_ns (override governors going + * forward), or do not override governors if it is zero. */ -void cpuidle_use_deepest_state(bool enable) +void cpuidle_use_deepest_state(u64 latency_limit_ns) { struct cpuidle_device *dev; preempt_disable(); dev = cpuidle_get_device(); if (dev) - dev->use_deepest_state = enable; + dev->forced_idle_latency_limit_ns = latency_limit_ns; preempt_enable(); } diff --git a/include/linux/cpu.h b/include/linux/cpu.h index d0633ebdaa9c..cc03a7848b63 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -179,7 +179,12 @@ void arch_cpu_idle_dead(void); int cpu_report_state(int cpu); int cpu_check_up_prepare(int cpu); void cpu_set_state_online(int cpu); -void play_idle(unsigned long duration_us); +void play_idle_precise(u64 duration_ns, u64 latency_ns); + +static inline void play_idle(unsigned long duration_us) +{ + play_idle_precise(duration_us * NSEC_PER_USEC, U64_MAX); +} #ifdef CONFIG_HOTPLUG_CPU bool cpu_wait_death(unsigned int cpu, int seconds); diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index afb6a573b46d..72b26ff1de4b 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -85,7 +85,6 @@ struct cpuidle_driver_kobj; struct cpuidle_device { unsigned int registered:1; unsigned int enabled:1; - unsigned int use_deepest_state:1; unsigned int poll_time_limit:1; unsigned int cpu; ktime_t next_hrtimer; @@ -93,6 +92,7 @@ struct cpuidle_device { int last_state_idx; u64 last_residency_ns; u64 poll_limit_ns; + u64 forced_idle_latency_limit_ns; struct cpuidle_state_usage states_usage[CPUIDLE_STATE_MAX]; struct cpuidle_state_kobj *kobjs[CPUIDLE_STATE_MAX]; struct cpuidle_driver_kobj *kobj_driver; @@ -216,7 +216,7 @@ extern int cpuidle_find_deepest_state(struct cpuidle_driver *drv, struct cpuidle_device *dev); extern int cpuidle_enter_s2idle(struct cpuidle_driver *drv, struct cpuidle_device *dev); -extern void cpuidle_use_deepest_state(bool enable); +extern void cpuidle_use_deepest_state(u64 latency_limit_ns); #else static inline int cpuidle_find_deepest_state(struct cpuidle_driver *drv, struct cpuidle_device *dev) @@ -224,7 +224,7 @@ static inline int cpuidle_find_deepest_state(struct cpuidle_driver *drv, static inline int cpuidle_enter_s2idle(struct cpuidle_driver *drv, struct cpuidle_device *dev) {return -ENODEV; } -static inline void cpuidle_use_deepest_state(bool enable) +static inline void cpuidle_use_deepest_state(u64 latency_limit_ns) { } #endif diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 1aa260702b38..cd05ffa0abfe 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -165,7 +165,7 @@ static void cpuidle_idle_call(void) * until a proper wakeup interrupt happens. */ - if (idle_should_enter_s2idle() || dev->use_deepest_state) { + if (idle_should_enter_s2idle() || dev->forced_idle_latency_limit_ns) { if (idle_should_enter_s2idle()) { rcu_idle_enter(); @@ -311,7 +311,7 @@ static enum hrtimer_restart idle_inject_timer_fn(struct hrtimer *timer) return HRTIMER_NORESTART; } -void play_idle(unsigned long duration_us) +void play_idle_precise(u64 duration_ns, u64 latency_ns) { struct idle_timer it; @@ -323,29 +323,29 @@ void play_idle(unsigned long duration_us) WARN_ON_ONCE(current->nr_cpus_allowed != 1); WARN_ON_ONCE(!(current->flags & PF_KTHREAD)); WARN_ON_ONCE(!(current->flags & PF_NO_SETAFFINITY)); - WARN_ON_ONCE(!duration_us); + WARN_ON_ONCE(!duration_ns); rcu_sleep_check(); preempt_disable(); current->flags |= PF_IDLE; - cpuidle_use_deepest_state(true); + cpuidle_use_deepest_state(latency_ns); it.done = 0; hrtimer_init_on_stack(&it.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); it.timer.function = idle_inject_timer_fn; - hrtimer_start(&it.timer, ns_to_ktime(duration_us * NSEC_PER_USEC), + hrtimer_start(&it.timer, ns_to_ktime(duration_ns), HRTIMER_MODE_REL_PINNED); while (!READ_ONCE(it.done)) do_idle(); - cpuidle_use_deepest_state(false); + cpuidle_use_deepest_state(0); current->flags &= ~PF_IDLE; preempt_fold_need_resched(); preempt_enable(); } -EXPORT_SYMBOL_GPL(play_idle); +EXPORT_SYMBOL_GPL(play_idle_precise); void cpu_startup_entry(enum cpuhp_state state) { -- cgit v1.2.3-71-gd317 From 5aa9ba6312e36c18626e73506b92d1513d815435 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Sat, 16 Nov 2019 14:16:13 +0100 Subject: cpuidle: Pass exit latency limit to cpuidle_use_deepest_state() Modify cpuidle_use_deepest_state() to take an additional exit latency limit argument to be passed to find_deepest_idle_state() and make cpuidle_idle_call() pass dev->forced_idle_latency_limit_ns to it for forced idle. Suggested-by: Rafael J. Wysocki Signed-off-by: Daniel Lezcano [ rjw: Rebase and rearrange code, subject & changelog ] Signed-off-by: Rafael J. Wysocki --- drivers/cpuidle/cpuidle.c | 5 +++-- include/linux/cpuidle.h | 6 ++++-- kernel/sched/idle.c | 8 +++++++- 3 files changed, 14 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 12077db1158e..569dbac443bd 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -123,9 +123,10 @@ void cpuidle_use_deepest_state(u64 latency_limit_ns) * @dev: cpuidle device for the given CPU. */ int cpuidle_find_deepest_state(struct cpuidle_driver *drv, - struct cpuidle_device *dev) + struct cpuidle_device *dev, + u64 latency_limit_ns) { - return find_deepest_state(drv, dev, U64_MAX, 0, false); + return find_deepest_state(drv, dev, latency_limit_ns, 0, false); } #ifdef CONFIG_SUSPEND diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 72b26ff1de4b..2dbe46b7c213 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -213,13 +213,15 @@ static inline struct cpuidle_device *cpuidle_get_device(void) {return NULL; } #ifdef CONFIG_CPU_IDLE extern int cpuidle_find_deepest_state(struct cpuidle_driver *drv, - struct cpuidle_device *dev); + struct cpuidle_device *dev, + u64 latency_limit_ns); extern int cpuidle_enter_s2idle(struct cpuidle_driver *drv, struct cpuidle_device *dev); extern void cpuidle_use_deepest_state(u64 latency_limit_ns); #else static inline int cpuidle_find_deepest_state(struct cpuidle_driver *drv, - struct cpuidle_device *dev) + struct cpuidle_device *dev, + u64 latency_limit_ns) {return -ENODEV; } static inline int cpuidle_enter_s2idle(struct cpuidle_driver *drv, struct cpuidle_device *dev) diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index cd05ffa0abfe..fc9604ddd802 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -166,6 +166,8 @@ static void cpuidle_idle_call(void) */ if (idle_should_enter_s2idle() || dev->forced_idle_latency_limit_ns) { + u64 max_latency_ns; + if (idle_should_enter_s2idle()) { rcu_idle_enter(); @@ -176,12 +178,16 @@ static void cpuidle_idle_call(void) } rcu_idle_exit(); + + max_latency_ns = U64_MAX; + } else { + max_latency_ns = dev->forced_idle_latency_limit_ns; } tick_nohz_idle_stop_tick(); rcu_idle_enter(); - next_state = cpuidle_find_deepest_state(drv, dev); + next_state = cpuidle_find_deepest_state(drv, dev, max_latency_ns); call_cpuidle(drv, dev, next_state); } else { bool stop_tick = true; -- cgit v1.2.3-71-gd317 From 1ed7d5c8f82d2aebabb6fe24f436a68bdd8c1065 Mon Sep 17 00:00:00 2001 From: Manish Narani Date: Wed, 20 Nov 2019 12:17:27 +0530 Subject: firmware: xilinx: Add SDIO Tap Delay nodes Add tap delay nodes for setting SDIO Tap Delays on ZynqMP platform. Signed-off-by: Manish Narani Signed-off-by: Ulf Hansson --- include/linux/firmware/xlnx-zynqmp.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 778abbbc7d94..df366f1a4cb4 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -91,7 +91,8 @@ enum pm_ret_status { }; enum pm_ioctl_id { - IOCTL_SET_PLL_FRAC_MODE = 8, + IOCTL_SET_SD_TAPDELAY = 7, + IOCTL_SET_PLL_FRAC_MODE, IOCTL_GET_PLL_FRAC_MODE, IOCTL_SET_PLL_FRAC_DATA, IOCTL_GET_PLL_FRAC_DATA, @@ -250,6 +251,16 @@ enum zynqmp_pm_request_ack { ZYNQMP_PM_REQUEST_ACK_NON_BLOCKING, }; +enum pm_node_id { + NODE_SD_0 = 39, + NODE_SD_1, +}; + +enum tap_delay_type { + PM_TAPDELAY_INPUT = 0, + PM_TAPDELAY_OUTPUT, +}; + /** * struct zynqmp_pm_query_data - PM query data * @qid: query ID -- cgit v1.2.3-71-gd317 From ec11e5c213cc20cac5e8310728b06793448b9f6d Mon Sep 17 00:00:00 2001 From: Jon Derrick Date: Tue, 12 Nov 2019 05:47:53 -0700 Subject: PCI: vmd: Add device id for VMD device 8086:9A0B This patch adds support for this VMD device which supports the bus restriction mode. Signed-off-by: Jon Derrick Signed-off-by: Lorenzo Pieralisi --- drivers/pci/controller/vmd.c | 2 ++ include/linux/pci_ids.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c index 15302a17ee3f..6bff95115d28 100644 --- a/drivers/pci/controller/vmd.c +++ b/drivers/pci/controller/vmd.c @@ -868,6 +868,8 @@ static const struct pci_device_id vmd_ids[] = { {PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_28C0), .driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW | VMD_FEAT_HAS_BUS_RESTRICTIONS,}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_9A0B), + .driver_data = VMD_FEAT_HAS_BUS_RESTRICTIONS,}, {0,} }; MODULE_DEVICE_TABLE(pci, vmd_ids); diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 21a572469a4e..2302d133af6f 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -3006,6 +3006,7 @@ #define PCI_DEVICE_ID_INTEL_84460GX 0x84ea #define PCI_DEVICE_ID_INTEL_IXP4XX 0x8500 #define PCI_DEVICE_ID_INTEL_IXP2800 0x9004 +#define PCI_DEVICE_ID_INTEL_VMD_9A0B 0x9a0b #define PCI_DEVICE_ID_INTEL_S21152BB 0xb152 #define PCI_VENDOR_ID_SCALEMP 0x8686 -- cgit v1.2.3-71-gd317 From 331f63457165a30c708280de2c77f1742c6351dc Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 30 Oct 2019 17:30:57 -0500 Subject: PCI: of: Add inbound resource parsing to helpers Extend devm_of_pci_get_host_bridge_resources() and pci_parse_request_of_pci_ranges() helpers to also parse the inbound addresses from DT 'dma-ranges' and populate a resource list with the translated addresses. This will help ensure 'dma-ranges' is always parsed in a consistent way. Tested-by: Srinath Mannam Tested-by: Thomas Petazzoni # for AArdvark Signed-off-by: Rob Herring Signed-off-by: Lorenzo Pieralisi Reviewed-by: Srinath Mannam Reviewed-by: Andrew Murray Acked-by: Gustavo Pimentel Cc: Jingoo Han Cc: Gustavo Pimentel Cc: Lorenzo Pieralisi Cc: Bjorn Helgaas Cc: Thomas Petazzoni Cc: Will Deacon Cc: Linus Walleij Cc: Toan Le Cc: Ley Foon Tan Cc: Tom Joseph Cc: Ray Jui Cc: Scott Branden Cc: bcm-kernel-feedback-list@broadcom.com Cc: Ryder Lee Cc: Karthikeyan Mitran Cc: Hou Zhiqiang Cc: Simon Horman Cc: Shawn Lin Cc: Heiko Stuebner Cc: Michal Simek Cc: rfi@lists.rocketboards.org Cc: linux-mediatek@lists.infradead.org Cc: linux-renesas-soc@vger.kernel.org Cc: linux-rockchip@lists.infradead.org --- drivers/pci/controller/dwc/pcie-designware-host.c | 3 +- drivers/pci/controller/pci-aardvark.c | 2 +- drivers/pci/controller/pci-ftpci100.c | 3 +- drivers/pci/controller/pci-host-common.c | 2 +- drivers/pci/controller/pci-v3-semi.c | 3 +- drivers/pci/controller/pci-versatile.c | 3 +- drivers/pci/controller/pci-xgene.c | 3 +- drivers/pci/controller/pcie-altera.c | 2 +- drivers/pci/controller/pcie-cadence-host.c | 2 +- drivers/pci/controller/pcie-iproc-platform.c | 3 +- drivers/pci/controller/pcie-mediatek.c | 2 +- drivers/pci/controller/pcie-mobiveil.c | 3 +- drivers/pci/controller/pcie-rcar.c | 3 +- drivers/pci/controller/pcie-rockchip-host.c | 3 +- drivers/pci/controller/pcie-xilinx-nwl.c | 3 +- drivers/pci/controller/pcie-xilinx.c | 3 +- drivers/pci/of.c | 61 ++++++++++++++++++++--- drivers/pci/pci.h | 8 ++- include/linux/pci.h | 9 ++-- 19 files changed, 93 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index aeec8b65eb97..f7b1d80c4a0a 100644 --- a/drivers/pci/controller/dwc/pcie-designware-host.c +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -342,7 +342,8 @@ int dw_pcie_host_init(struct pcie_port *pp) if (!bridge) return -ENOMEM; - ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows, NULL); + ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows, + &bridge->dma_ranges, NULL); if (ret) return ret; diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index 9cbeba507f0c..b34eaa2cd762 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -939,7 +939,7 @@ static int advk_pcie_probe(struct platform_device *pdev) } ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows, - &bus); + &bridge->dma_ranges, &bus); if (ret) { dev_err(dev, "Failed to parse resources\n"); return ret; diff --git a/drivers/pci/controller/pci-ftpci100.c b/drivers/pci/controller/pci-ftpci100.c index 75603348b88a..66288b94e92d 100644 --- a/drivers/pci/controller/pci-ftpci100.c +++ b/drivers/pci/controller/pci-ftpci100.c @@ -477,7 +477,8 @@ static int faraday_pci_probe(struct platform_device *pdev) if (IS_ERR(p->base)) return PTR_ERR(p->base); - ret = pci_parse_request_of_pci_ranges(dev, &host->windows, NULL); + ret = pci_parse_request_of_pci_ranges(dev, &host->windows, + &host->dma_ranges, NULL); if (ret) return ret; diff --git a/drivers/pci/controller/pci-host-common.c b/drivers/pci/controller/pci-host-common.c index c8cb9c5188a4..250a3fc80ec6 100644 --- a/drivers/pci/controller/pci-host-common.c +++ b/drivers/pci/controller/pci-host-common.c @@ -27,7 +27,7 @@ static struct pci_config_window *gen_pci_init(struct device *dev, struct pci_config_window *cfg; /* Parse our PCI ranges and request their resources */ - err = pci_parse_request_of_pci_ranges(dev, resources, &bus_range); + err = pci_parse_request_of_pci_ranges(dev, resources, NULL, &bus_range); if (err) return ERR_PTR(err); diff --git a/drivers/pci/controller/pci-v3-semi.c b/drivers/pci/controller/pci-v3-semi.c index 96677520f6c1..2209c7671115 100644 --- a/drivers/pci/controller/pci-v3-semi.c +++ b/drivers/pci/controller/pci-v3-semi.c @@ -776,7 +776,8 @@ static int v3_pci_probe(struct platform_device *pdev) if (IS_ERR(v3->config_base)) return PTR_ERR(v3->config_base); - ret = pci_parse_request_of_pci_ranges(dev, &host->windows, NULL); + ret = pci_parse_request_of_pci_ranges(dev, &host->windows, + &host->dma_ranges, NULL); if (ret) return ret; diff --git a/drivers/pci/controller/pci-versatile.c b/drivers/pci/controller/pci-versatile.c index eae1b859990b..b911359b6d81 100644 --- a/drivers/pci/controller/pci-versatile.c +++ b/drivers/pci/controller/pci-versatile.c @@ -92,7 +92,8 @@ static int versatile_pci_probe(struct platform_device *pdev) if (IS_ERR(versatile_cfg_base[1])) return PTR_ERR(versatile_cfg_base[1]); - ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows, NULL); + ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows, + NULL, NULL); if (ret) return ret; diff --git a/drivers/pci/controller/pci-xgene.c b/drivers/pci/controller/pci-xgene.c index 7d0f0395a479..9408269d943d 100644 --- a/drivers/pci/controller/pci-xgene.c +++ b/drivers/pci/controller/pci-xgene.c @@ -627,7 +627,8 @@ static int xgene_pcie_probe(struct platform_device *pdev) if (ret) return ret; - ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows, NULL); + ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows, + &bridge->dma_ranges, NULL); if (ret) return ret; diff --git a/drivers/pci/controller/pcie-altera.c b/drivers/pci/controller/pcie-altera.c index ba025efeae28..b447c3e4abad 100644 --- a/drivers/pci/controller/pcie-altera.c +++ b/drivers/pci/controller/pcie-altera.c @@ -800,7 +800,7 @@ static int altera_pcie_probe(struct platform_device *pdev) } ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows, - NULL); + &bridge->dma_ranges, NULL); if (ret) { dev_err(dev, "Failed add resources\n"); return ret; diff --git a/drivers/pci/controller/pcie-cadence-host.c b/drivers/pci/controller/pcie-cadence-host.c index 97e251090b4f..a8f7a6284c3e 100644 --- a/drivers/pci/controller/pcie-cadence-host.c +++ b/drivers/pci/controller/pcie-cadence-host.c @@ -211,7 +211,7 @@ static int cdns_pcie_host_init(struct device *dev, int err; /* Parse our PCI ranges and request their resources */ - err = pci_parse_request_of_pci_ranges(dev, resources, &bus_range); + err = pci_parse_request_of_pci_ranges(dev, resources, NULL, &bus_range); if (err) return err; diff --git a/drivers/pci/controller/pcie-iproc-platform.c b/drivers/pci/controller/pcie-iproc-platform.c index 375d815f7301..ff0a81a632a1 100644 --- a/drivers/pci/controller/pcie-iproc-platform.c +++ b/drivers/pci/controller/pcie-iproc-platform.c @@ -95,7 +95,8 @@ static int iproc_pcie_pltfm_probe(struct platform_device *pdev) if (IS_ERR(pcie->phy)) return PTR_ERR(pcie->phy); - ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows, NULL); + ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows, + &bridge->dma_ranges, NULL); if (ret) { dev_err(dev, "unable to get PCI host bridge resources\n"); return ret; diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c index d9206a3cd56b..cb982891b22b 100644 --- a/drivers/pci/controller/pcie-mediatek.c +++ b/drivers/pci/controller/pcie-mediatek.c @@ -1034,7 +1034,7 @@ static int mtk_pcie_setup(struct mtk_pcie *pcie) int err; err = pci_parse_request_of_pci_ranges(dev, windows, - &bus); + &host->dma_ranges, &bus); if (err) return err; diff --git a/drivers/pci/controller/pcie-mobiveil.c b/drivers/pci/controller/pcie-mobiveil.c index 4eab8624ce4d..257ba49c177c 100644 --- a/drivers/pci/controller/pcie-mobiveil.c +++ b/drivers/pci/controller/pcie-mobiveil.c @@ -875,7 +875,8 @@ static int mobiveil_pcie_probe(struct platform_device *pdev) } /* parse the host bridge base addresses from the device tree file */ - ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows, NULL); + ret = pci_parse_request_of_pci_ranges(dev, &bridge->windows, + &bridge->dma_ranges, NULL); if (ret) { dev_err(dev, "Getting bridge resources failed\n"); return ret; diff --git a/drivers/pci/controller/pcie-rcar.c b/drivers/pci/controller/pcie-rcar.c index f6a669a9af41..b8d6e86a5539 100644 --- a/drivers/pci/controller/pcie-rcar.c +++ b/drivers/pci/controller/pcie-rcar.c @@ -1138,7 +1138,8 @@ static int rcar_pcie_probe(struct platform_device *pdev) pcie->dev = dev; platform_set_drvdata(pdev, pcie); - err = pci_parse_request_of_pci_ranges(dev, &pcie->resources, NULL); + err = pci_parse_request_of_pci_ranges(dev, &pcie->resources, + &bridge->dma_ranges, NULL); if (err) goto err_free_bridge; diff --git a/drivers/pci/controller/pcie-rockchip-host.c b/drivers/pci/controller/pcie-rockchip-host.c index f375e55ea02e..ee83f8494ee9 100644 --- a/drivers/pci/controller/pcie-rockchip-host.c +++ b/drivers/pci/controller/pcie-rockchip-host.c @@ -1004,7 +1004,8 @@ static int rockchip_pcie_probe(struct platform_device *pdev) if (err < 0) goto err_deinit_port; - err = pci_parse_request_of_pci_ranges(dev, &bridge->windows, &bus_res); + err = pci_parse_request_of_pci_ranges(dev, &bridge->windows, + &bridge->dma_ranges, &bus_res); if (err) goto err_remove_irq_domain; diff --git a/drivers/pci/controller/pcie-xilinx-nwl.c b/drivers/pci/controller/pcie-xilinx-nwl.c index e135a4b60489..9bd1427f2fd6 100644 --- a/drivers/pci/controller/pcie-xilinx-nwl.c +++ b/drivers/pci/controller/pcie-xilinx-nwl.c @@ -843,7 +843,8 @@ static int nwl_pcie_probe(struct platform_device *pdev) return err; } - err = pci_parse_request_of_pci_ranges(dev, &bridge->windows, NULL); + err = pci_parse_request_of_pci_ranges(dev, &bridge->windows, + &bridge->dma_ranges, NULL); if (err) { dev_err(dev, "Getting bridge resources failed\n"); return err; diff --git a/drivers/pci/controller/pcie-xilinx.c b/drivers/pci/controller/pcie-xilinx.c index 257702288787..98e55297815b 100644 --- a/drivers/pci/controller/pcie-xilinx.c +++ b/drivers/pci/controller/pcie-xilinx.c @@ -645,7 +645,8 @@ static int xilinx_pcie_probe(struct platform_device *pdev) return err; } - err = pci_parse_request_of_pci_ranges(dev, &bridge->windows, NULL); + err = pci_parse_request_of_pci_ranges(dev, &bridge->windows, + &bridge->dma_ranges, NULL); if (err) { dev_err(dev, "Getting bridge resources failed\n"); return err; diff --git a/drivers/pci/of.c b/drivers/pci/of.c index f3da49a31db4..1dfde6f9e82d 100644 --- a/drivers/pci/of.c +++ b/drivers/pci/of.c @@ -257,14 +257,16 @@ EXPORT_SYMBOL_GPL(of_pci_check_probe_only); */ int devm_of_pci_get_host_bridge_resources(struct device *dev, unsigned char busno, unsigned char bus_max, - struct list_head *resources, resource_size_t *io_base) + struct list_head *resources, + struct list_head *ib_resources, + resource_size_t *io_base) { struct device_node *dev_node = dev->of_node; struct resource *res, tmp_res; struct resource *bus_range; struct of_pci_range range; struct of_pci_range_parser parser; - char range_type[4]; + const char *range_type; int err; if (io_base) @@ -298,12 +300,12 @@ int devm_of_pci_get_host_bridge_resources(struct device *dev, for_each_of_pci_range(&parser, &range) { /* Read next ranges element */ if ((range.flags & IORESOURCE_TYPE_BITS) == IORESOURCE_IO) - snprintf(range_type, 4, " IO"); + range_type = "IO"; else if ((range.flags & IORESOURCE_TYPE_BITS) == IORESOURCE_MEM) - snprintf(range_type, 4, "MEM"); + range_type = "MEM"; else - snprintf(range_type, 4, "err"); - dev_info(dev, " %s %#010llx..%#010llx -> %#010llx\n", + range_type = "err"; + dev_info(dev, " %6s %#012llx..%#012llx -> %#012llx\n", range_type, range.cpu_addr, range.cpu_addr + range.size - 1, range.pci_addr); @@ -340,6 +342,48 @@ int devm_of_pci_get_host_bridge_resources(struct device *dev, pci_add_resource_offset(resources, res, res->start - range.pci_addr); } + /* Check for dma-ranges property */ + if (!ib_resources) + return 0; + err = of_pci_dma_range_parser_init(&parser, dev_node); + if (err) + return 0; + + dev_dbg(dev, "Parsing dma-ranges property...\n"); + for_each_of_pci_range(&parser, &range) { + struct resource_entry *entry; + /* + * If we failed translation or got a zero-sized region + * then skip this range + */ + if (((range.flags & IORESOURCE_TYPE_BITS) != IORESOURCE_MEM) || + range.cpu_addr == OF_BAD_ADDR || range.size == 0) + continue; + + dev_info(dev, " %6s %#012llx..%#012llx -> %#012llx\n", + "IB MEM", range.cpu_addr, + range.cpu_addr + range.size - 1, range.pci_addr); + + + err = of_pci_range_to_resource(&range, dev_node, &tmp_res); + if (err) + continue; + + res = devm_kmemdup(dev, &tmp_res, sizeof(tmp_res), GFP_KERNEL); + if (!res) { + err = -ENOMEM; + goto failed; + } + + /* Keep the resource list sorted */ + resource_list_for_each_entry(entry, ib_resources) + if (entry->res->start > res->start) + break; + + pci_add_resource_offset(&entry->node, res, + res->start - range.pci_addr); + } + return 0; failed: @@ -482,6 +526,7 @@ EXPORT_SYMBOL_GPL(of_irq_parse_and_map_pci); int pci_parse_request_of_pci_ranges(struct device *dev, struct list_head *resources, + struct list_head *ib_resources, struct resource **bus_range) { int err, res_valid = 0; @@ -489,8 +534,10 @@ int pci_parse_request_of_pci_ranges(struct device *dev, struct resource_entry *win, *tmp; INIT_LIST_HEAD(resources); + if (ib_resources) + INIT_LIST_HEAD(ib_resources); err = devm_of_pci_get_host_bridge_resources(dev, 0, 0xff, resources, - &iobase); + ib_resources, &iobase); if (err) return err; diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 3f6947ee3324..6692c4fe4290 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -633,11 +633,15 @@ static inline void pci_release_bus_of_node(struct pci_bus *bus) { } #if defined(CONFIG_OF_ADDRESS) int devm_of_pci_get_host_bridge_resources(struct device *dev, unsigned char busno, unsigned char bus_max, - struct list_head *resources, resource_size_t *io_base); + struct list_head *resources, + struct list_head *ib_resources, + resource_size_t *io_base); #else static inline int devm_of_pci_get_host_bridge_resources(struct device *dev, unsigned char busno, unsigned char bus_max, - struct list_head *resources, resource_size_t *io_base) + struct list_head *resources, + struct list_head *ib_resources, + resource_size_t *io_base) { return -EINVAL; } diff --git a/include/linux/pci.h b/include/linux/pci.h index f9088c89a534..5cb94916eaa1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2278,6 +2278,7 @@ struct irq_domain; struct irq_domain *pci_host_bridge_of_msi_domain(struct pci_bus *bus); int pci_parse_request_of_pci_ranges(struct device *dev, struct list_head *resources, + struct list_head *ib_resources, struct resource **bus_range); /* Arch may override this (weak) */ @@ -2286,9 +2287,11 @@ struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus); #else /* CONFIG_OF */ static inline struct irq_domain * pci_host_bridge_of_msi_domain(struct pci_bus *bus) { return NULL; } -static inline int pci_parse_request_of_pci_ranges(struct device *dev, - struct list_head *resources, - struct resource **bus_range) +static inline int +pci_parse_request_of_pci_ranges(struct device *dev, + struct list_head *resources, + struct list_head *ib_resources, + struct resource **bus_range) { return -EINVAL; } -- cgit v1.2.3-71-gd317 From 56e35f9c5b87ec1ae93e483284e189c84388de16 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 7 Nov 2019 18:03:11 +0100 Subject: dma-mapping: drop the dev argument to arch_sync_dma_for_* These are pure cache maintainance routines, so drop the unused struct device argument. Signed-off-by: Christoph Hellwig Suggested-by: Daniel Vetter --- arch/arc/mm/dma.c | 8 ++++---- arch/arm/mm/dma-mapping.c | 8 ++++---- arch/arm/xen/mm.c | 12 ++++++------ arch/arm64/mm/dma-mapping.c | 8 ++++---- arch/c6x/mm/dma-coherent.c | 14 +++++++------- arch/csky/mm/dma-mapping.c | 8 ++++---- arch/hexagon/kernel/dma.c | 4 ++-- arch/ia64/mm/init.c | 4 ++-- arch/m68k/kernel/dma.c | 4 ++-- arch/microblaze/kernel/dma.c | 14 +++++++------- arch/mips/bmips/dma.c | 2 +- arch/mips/jazz/jazzdma.c | 17 ++++++++--------- arch/mips/mm/dma-noncoherent.c | 12 ++++++------ arch/nds32/kernel/dma.c | 8 ++++---- arch/nios2/mm/dma-mapping.c | 8 ++++---- arch/openrisc/kernel/dma.c | 2 +- arch/parisc/kernel/pci-dma.c | 8 ++++---- arch/powerpc/mm/dma-noncoherent.c | 8 ++++---- arch/sh/kernel/dma-coherent.c | 6 +++--- arch/sparc/kernel/ioport.c | 4 ++-- arch/xtensa/kernel/pci-dma.c | 8 ++++---- drivers/iommu/dma-iommu.c | 10 +++++----- drivers/xen/swiotlb-xen.c | 8 ++++---- include/linux/dma-noncoherent.h | 20 ++++++++++---------- include/xen/swiotlb-xen.h | 8 ++++---- kernel/dma/direct.c | 14 +++++++------- 26 files changed, 113 insertions(+), 114 deletions(-) (limited to 'include/linux') diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c index 73a7e88a1e92..e947572a521e 100644 --- a/arch/arc/mm/dma.c +++ b/arch/arc/mm/dma.c @@ -48,8 +48,8 @@ void arch_dma_prep_coherent(struct page *page, size_t size) * upper layer functions (in include/linux/dma-mapping.h) */ -void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { switch (dir) { case DMA_TO_DEVICE: @@ -69,8 +69,8 @@ void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, } } -void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { switch (dir) { case DMA_TO_DEVICE: diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index f3cbeba7f9cb..da1a32b5e192 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -2332,15 +2332,15 @@ void arch_teardown_dma_ops(struct device *dev) } #ifdef CONFIG_SWIOTLB -void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { __dma_page_cpu_to_dev(phys_to_page(paddr), paddr & (PAGE_SIZE - 1), size, dir); } -void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { __dma_page_dev_to_cpu(phys_to_page(paddr), paddr & (PAGE_SIZE - 1), size, dir); diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c index 38fa917c8585..a6a2514e5fe8 100644 --- a/arch/arm/xen/mm.c +++ b/arch/arm/xen/mm.c @@ -70,20 +70,20 @@ static void dma_cache_maint(dma_addr_t handle, size_t size, u32 op) * pfn_valid returns true the pages is local and we can use the native * dma-direct functions, otherwise we call the Xen specific version. */ -void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle, - phys_addr_t paddr, size_t size, enum dma_data_direction dir) +void xen_dma_sync_for_cpu(dma_addr_t handle, phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { if (pfn_valid(PFN_DOWN(handle))) - arch_sync_dma_for_cpu(dev, paddr, size, dir); + arch_sync_dma_for_cpu(paddr, size, dir); else if (dir != DMA_TO_DEVICE) dma_cache_maint(handle, size, GNTTAB_CACHE_INVAL); } -void xen_dma_sync_for_device(struct device *dev, dma_addr_t handle, - phys_addr_t paddr, size_t size, enum dma_data_direction dir) +void xen_dma_sync_for_device(dma_addr_t handle, phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { if (pfn_valid(PFN_DOWN(handle))) - arch_sync_dma_for_device(dev, paddr, size, dir); + arch_sync_dma_for_device(paddr, size, dir); else if (dir == DMA_FROM_DEVICE) dma_cache_maint(handle, size, GNTTAB_CACHE_INVAL); else diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 9239416e93d4..6c45350e33aa 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -13,14 +13,14 @@ #include -void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { __dma_map_area(phys_to_virt(paddr), size, dir); } -void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { __dma_unmap_area(phys_to_virt(paddr), size, dir); } diff --git a/arch/c6x/mm/dma-coherent.c b/arch/c6x/mm/dma-coherent.c index b319808e8f6b..a5909091cb14 100644 --- a/arch/c6x/mm/dma-coherent.c +++ b/arch/c6x/mm/dma-coherent.c @@ -140,7 +140,7 @@ void __init coherent_mem_init(phys_addr_t start, u32 size) sizeof(long)); } -static void c6x_dma_sync(struct device *dev, phys_addr_t paddr, size_t size, +static void c6x_dma_sync(phys_addr_t paddr, size_t size, enum dma_data_direction dir) { BUG_ON(!valid_dma_direction(dir)); @@ -160,14 +160,14 @@ static void c6x_dma_sync(struct device *dev, phys_addr_t paddr, size_t size, } } -void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { - return c6x_dma_sync(dev, paddr, size, dir); + return c6x_dma_sync(paddr, size, dir); } -void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { - return c6x_dma_sync(dev, paddr, size, dir); + return c6x_dma_sync(paddr, size, dir); } diff --git a/arch/csky/mm/dma-mapping.c b/arch/csky/mm/dma-mapping.c index 06e85b565454..8f6571ae27c8 100644 --- a/arch/csky/mm/dma-mapping.c +++ b/arch/csky/mm/dma-mapping.c @@ -58,8 +58,8 @@ void arch_dma_prep_coherent(struct page *page, size_t size) cache_op(page_to_phys(page), size, dma_wbinv_set_zero_range); } -void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { switch (dir) { case DMA_TO_DEVICE: @@ -74,8 +74,8 @@ void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, } } -void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { switch (dir) { case DMA_TO_DEVICE: diff --git a/arch/hexagon/kernel/dma.c b/arch/hexagon/kernel/dma.c index f561b127c4b4..25f388d9cfcc 100644 --- a/arch/hexagon/kernel/dma.c +++ b/arch/hexagon/kernel/dma.c @@ -55,8 +55,8 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr, gen_pool_free(coherent_pool, (unsigned long) vaddr, size); } -void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { void *addr = phys_to_virt(paddr); diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index bf9df2625bc8..58fd67068bac 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -73,8 +73,8 @@ __ia64_sync_icache_dcache (pte_t pte) * DMA can be marked as "clean" so that lazy_mmu_prot_update() doesn't have to * flush them when they get mapped into an executable vm-area. */ -void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { unsigned long pfn = PHYS_PFN(paddr); diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c index 3fab684cc0db..871a0e11da34 100644 --- a/arch/m68k/kernel/dma.c +++ b/arch/m68k/kernel/dma.c @@ -61,8 +61,8 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr, #endif /* CONFIG_MMU && !CONFIG_COLDFIRE */ -void arch_sync_dma_for_device(struct device *dev, phys_addr_t handle, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_device(phys_addr_t handle, size_t size, + enum dma_data_direction dir) { switch (dir) { case DMA_BIDIRECTIONAL: diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c index a89c2d4ed5ff..d7bebd04247b 100644 --- a/arch/microblaze/kernel/dma.c +++ b/arch/microblaze/kernel/dma.c @@ -15,7 +15,7 @@ #include #include -static void __dma_sync(struct device *dev, phys_addr_t paddr, size_t size, +static void __dma_sync(phys_addr_t paddr, size_t size, enum dma_data_direction direction) { switch (direction) { @@ -31,14 +31,14 @@ static void __dma_sync(struct device *dev, phys_addr_t paddr, size_t size, } } -void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { - __dma_sync(dev, paddr, size, dir); + __dma_sync(paddr, size, dir); } -void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { - __dma_sync(dev, paddr, size, dir); + __dma_sync(paddr, size, dir); } diff --git a/arch/mips/bmips/dma.c b/arch/mips/bmips/dma.c index 3d13c77c125f..df56bf4179e3 100644 --- a/arch/mips/bmips/dma.c +++ b/arch/mips/bmips/dma.c @@ -64,7 +64,7 @@ phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr) return dma_addr; } -void arch_sync_dma_for_cpu_all(struct device *dev) +void arch_sync_dma_for_cpu_all(void) { void __iomem *cbr = BMIPS_GET_CBR(); u32 cfg; diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c index a01e14955187..c64a297e82b3 100644 --- a/arch/mips/jazz/jazzdma.c +++ b/arch/mips/jazz/jazzdma.c @@ -592,7 +592,7 @@ static dma_addr_t jazz_dma_map_page(struct device *dev, struct page *page, phys_addr_t phys = page_to_phys(page) + offset; if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - arch_sync_dma_for_device(dev, phys, size, dir); + arch_sync_dma_for_device(phys, size, dir); return vdma_alloc(phys, size); } @@ -600,7 +600,7 @@ static void jazz_dma_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - arch_sync_dma_for_cpu(dev, vdma_log2phys(dma_addr), size, dir); + arch_sync_dma_for_cpu(vdma_log2phys(dma_addr), size, dir); vdma_free(dma_addr); } @@ -612,7 +612,7 @@ static int jazz_dma_map_sg(struct device *dev, struct scatterlist *sglist, for_each_sg(sglist, sg, nents, i) { if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, + arch_sync_dma_for_device(sg_phys(sg), sg->length, dir); sg->dma_address = vdma_alloc(sg_phys(sg), sg->length); if (sg->dma_address == DMA_MAPPING_ERROR) @@ -631,8 +631,7 @@ static void jazz_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, for_each_sg(sglist, sg, nents, i) { if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, - dir); + arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir); vdma_free(sg->dma_address); } } @@ -640,13 +639,13 @@ static void jazz_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, static void jazz_dma_sync_single_for_device(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { - arch_sync_dma_for_device(dev, vdma_log2phys(addr), size, dir); + arch_sync_dma_for_device(vdma_log2phys(addr), size, dir); } static void jazz_dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) { - arch_sync_dma_for_cpu(dev, vdma_log2phys(addr), size, dir); + arch_sync_dma_for_cpu(vdma_log2phys(addr), size, dir); } static void jazz_dma_sync_sg_for_device(struct device *dev, @@ -656,7 +655,7 @@ static void jazz_dma_sync_sg_for_device(struct device *dev, int i; for_each_sg(sgl, sg, nents, i) - arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir); + arch_sync_dma_for_device(sg_phys(sg), sg->length, dir); } static void jazz_dma_sync_sg_for_cpu(struct device *dev, @@ -666,7 +665,7 @@ static void jazz_dma_sync_sg_for_cpu(struct device *dev, int i; for_each_sg(sgl, sg, nents, i) - arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir); + arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir); } const struct dma_map_ops jazz_dma_ops = { diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c index fcf6d3eaac66..dc42ffc83825 100644 --- a/arch/mips/mm/dma-noncoherent.c +++ b/arch/mips/mm/dma-noncoherent.c @@ -27,7 +27,7 @@ * R10000 and R12000 are used in such systems, the SGI IP28 Indigo² rsp. * SGI IP32 aka O2. */ -static inline bool cpu_needs_post_dma_flush(struct device *dev) +static inline bool cpu_needs_post_dma_flush(void) { switch (boot_cpu_type()) { case CPU_R10000: @@ -112,17 +112,17 @@ static inline void dma_sync_phys(phys_addr_t paddr, size_t size, } while (left); } -void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { dma_sync_phys(paddr, size, dir); } #ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU -void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { - if (cpu_needs_post_dma_flush(dev)) + if (cpu_needs_post_dma_flush()) dma_sync_phys(paddr, size, dir); } #endif diff --git a/arch/nds32/kernel/dma.c b/arch/nds32/kernel/dma.c index 4206d4b6c8ce..69d762182d49 100644 --- a/arch/nds32/kernel/dma.c +++ b/arch/nds32/kernel/dma.c @@ -46,8 +46,8 @@ static inline void cache_op(phys_addr_t paddr, size_t size, } while (left); } -void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { switch (dir) { case DMA_FROM_DEVICE: @@ -61,8 +61,8 @@ void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, } } -void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { switch (dir) { case DMA_TO_DEVICE: diff --git a/arch/nios2/mm/dma-mapping.c b/arch/nios2/mm/dma-mapping.c index 9cb238664584..0ed711e37902 100644 --- a/arch/nios2/mm/dma-mapping.c +++ b/arch/nios2/mm/dma-mapping.c @@ -18,8 +18,8 @@ #include #include -void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { void *vaddr = phys_to_virt(paddr); @@ -42,8 +42,8 @@ void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, } } -void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { void *vaddr = phys_to_virt(paddr); diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c index 4d5b8bd1d795..adec711ad39d 100644 --- a/arch/openrisc/kernel/dma.c +++ b/arch/openrisc/kernel/dma.c @@ -125,7 +125,7 @@ arch_dma_free(struct device *dev, size_t size, void *vaddr, free_pages_exact(vaddr, size); } -void arch_sync_dma_for_device(struct device *dev, phys_addr_t addr, size_t size, +void arch_sync_dma_for_device(phys_addr_t addr, size_t size, enum dma_data_direction dir) { unsigned long cl; diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c index ca35d9a76e50..a60d47fd4d55 100644 --- a/arch/parisc/kernel/pci-dma.c +++ b/arch/parisc/kernel/pci-dma.c @@ -439,14 +439,14 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr, free_pages((unsigned long)__va(dma_handle), order); } -void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size); } -void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size); } diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c index 2a82984356f8..5ab4f868e919 100644 --- a/arch/powerpc/mm/dma-noncoherent.c +++ b/arch/powerpc/mm/dma-noncoherent.c @@ -104,14 +104,14 @@ static void __dma_sync_page(phys_addr_t paddr, size_t size, int dir) #endif } -void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { __dma_sync_page(paddr, size, dir); } -void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { __dma_sync_page(paddr, size, dir); } diff --git a/arch/sh/kernel/dma-coherent.c b/arch/sh/kernel/dma-coherent.c index b17514619b7e..eeb25a4fa55f 100644 --- a/arch/sh/kernel/dma-coherent.c +++ b/arch/sh/kernel/dma-coherent.c @@ -25,7 +25,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, * Pages from the page allocator may have data present in * cache. So flush the cache before using uncached memory. */ - arch_sync_dma_for_device(dev, virt_to_phys(ret), size, + arch_sync_dma_for_device(virt_to_phys(ret), size, DMA_BIDIRECTIONAL); ret_nocache = (void __force *)ioremap_nocache(virt_to_phys(ret), size); @@ -59,8 +59,8 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr, iounmap(vaddr); } -void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { void *addr = sh_cacheop_vaddr(phys_to_virt(paddr)); diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c index f89603855f1e..e59461d03b9a 100644 --- a/arch/sparc/kernel/ioport.c +++ b/arch/sparc/kernel/ioport.c @@ -366,8 +366,8 @@ void arch_dma_free(struct device *dev, size_t size, void *cpu_addr, /* IIep is write-through, not flushing on cpu to device transfer. */ -void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { if (dir != PCI_DMA_TODEVICE) dma_make_coherent(paddr, PAGE_ALIGN(size)); diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c index 1c82e21de4f6..72b6222daa0b 100644 --- a/arch/xtensa/kernel/pci-dma.c +++ b/arch/xtensa/kernel/pci-dma.c @@ -44,8 +44,8 @@ static void do_cache_op(phys_addr_t paddr, size_t size, } } -void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { switch (dir) { case DMA_BIDIRECTIONAL: @@ -62,8 +62,8 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, } } -void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir) +void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { switch (dir) { case DMA_BIDIRECTIONAL: diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index f321279baf9e..0fa8c1d818b7 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -659,7 +659,7 @@ static void iommu_dma_sync_single_for_cpu(struct device *dev, return; phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle); - arch_sync_dma_for_cpu(dev, phys, size, dir); + arch_sync_dma_for_cpu(phys, size, dir); } static void iommu_dma_sync_single_for_device(struct device *dev, @@ -671,7 +671,7 @@ static void iommu_dma_sync_single_for_device(struct device *dev, return; phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle); - arch_sync_dma_for_device(dev, phys, size, dir); + arch_sync_dma_for_device(phys, size, dir); } static void iommu_dma_sync_sg_for_cpu(struct device *dev, @@ -685,7 +685,7 @@ static void iommu_dma_sync_sg_for_cpu(struct device *dev, return; for_each_sg(sgl, sg, nelems, i) - arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir); + arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir); } static void iommu_dma_sync_sg_for_device(struct device *dev, @@ -699,7 +699,7 @@ static void iommu_dma_sync_sg_for_device(struct device *dev, return; for_each_sg(sgl, sg, nelems, i) - arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir); + arch_sync_dma_for_device(sg_phys(sg), sg->length, dir); } static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, @@ -714,7 +714,7 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, dma_handle =__iommu_dma_map(dev, phys, size, prot); if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC) && dma_handle != DMA_MAPPING_ERROR) - arch_sync_dma_for_device(dev, phys, size, dir); + arch_sync_dma_for_device(phys, size, dir); return dma_handle; } diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index bd3a10dfac15..3f8b2cdb4acb 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -405,7 +405,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, done: if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - xen_dma_sync_for_device(dev, dev_addr, phys, size, dir); + xen_dma_sync_for_device(dev_addr, phys, size, dir); return dev_addr; } @@ -425,7 +425,7 @@ static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, BUG_ON(dir == DMA_NONE); if (!dev_is_dma_coherent(hwdev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - xen_dma_sync_for_cpu(hwdev, dev_addr, paddr, size, dir); + xen_dma_sync_for_cpu(dev_addr, paddr, size, dir); /* NOTE: We use dev_addr here, not paddr! */ if (is_xen_swiotlb_buffer(dev_addr)) @@ -439,7 +439,7 @@ xen_swiotlb_sync_single_for_cpu(struct device *dev, dma_addr_t dma_addr, phys_addr_t paddr = xen_bus_to_phys(dma_addr); if (!dev_is_dma_coherent(dev)) - xen_dma_sync_for_cpu(dev, dma_addr, paddr, size, dir); + xen_dma_sync_for_cpu(dma_addr, paddr, size, dir); if (is_xen_swiotlb_buffer(dma_addr)) swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU); @@ -455,7 +455,7 @@ xen_swiotlb_sync_single_for_device(struct device *dev, dma_addr_t dma_addr, swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE); if (!dev_is_dma_coherent(dev)) - xen_dma_sync_for_device(dev, dma_addr, paddr, size, dir); + xen_dma_sync_for_device(dma_addr, paddr, size, dir); } /* diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h index e30fca1f1b12..ca9b5770caee 100644 --- a/include/linux/dma-noncoherent.h +++ b/include/linux/dma-noncoherent.h @@ -73,29 +73,29 @@ static inline void arch_dma_cache_sync(struct device *dev, void *vaddr, #endif /* CONFIG_DMA_NONCOHERENT_CACHE_SYNC */ #ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE -void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir); +void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, + enum dma_data_direction dir); #else -static inline void arch_sync_dma_for_device(struct device *dev, - phys_addr_t paddr, size_t size, enum dma_data_direction dir) +static inline void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { } #endif /* ARCH_HAS_SYNC_DMA_FOR_DEVICE */ #ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU -void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, - size_t size, enum dma_data_direction dir); +void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, + enum dma_data_direction dir); #else -static inline void arch_sync_dma_for_cpu(struct device *dev, - phys_addr_t paddr, size_t size, enum dma_data_direction dir) +static inline void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) { } #endif /* ARCH_HAS_SYNC_DMA_FOR_CPU */ #ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL -void arch_sync_dma_for_cpu_all(struct device *dev); +void arch_sync_dma_for_cpu_all(void); #else -static inline void arch_sync_dma_for_cpu_all(struct device *dev) +static inline void arch_sync_dma_for_cpu_all(void) { } #endif /* CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL */ diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h index d71380f6ed0b..ffc0d3902b71 100644 --- a/include/xen/swiotlb-xen.h +++ b/include/xen/swiotlb-xen.h @@ -4,10 +4,10 @@ #include -void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle, - phys_addr_t paddr, size_t size, enum dma_data_direction dir); -void xen_dma_sync_for_device(struct device *dev, dma_addr_t handle, - phys_addr_t paddr, size_t size, enum dma_data_direction dir); +void xen_dma_sync_for_cpu(dma_addr_t handle, phys_addr_t paddr, size_t size, + enum dma_data_direction dir); +void xen_dma_sync_for_device(dma_addr_t handle, phys_addr_t paddr, size_t size, + enum dma_data_direction dir); extern int xen_swiotlb_init(int verbose, bool early); extern const struct dma_map_ops xen_swiotlb_dma_ops; diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 22a2e0833862..077876ae5c74 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -268,7 +268,7 @@ void dma_direct_sync_single_for_device(struct device *dev, swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE); if (!dev_is_dma_coherent(dev)) - arch_sync_dma_for_device(dev, paddr, size, dir); + arch_sync_dma_for_device(paddr, size, dir); } EXPORT_SYMBOL(dma_direct_sync_single_for_device); @@ -286,7 +286,7 @@ void dma_direct_sync_sg_for_device(struct device *dev, dir, SYNC_FOR_DEVICE); if (!dev_is_dma_coherent(dev)) - arch_sync_dma_for_device(dev, paddr, sg->length, + arch_sync_dma_for_device(paddr, sg->length, dir); } } @@ -302,8 +302,8 @@ void dma_direct_sync_single_for_cpu(struct device *dev, phys_addr_t paddr = dma_to_phys(dev, addr); if (!dev_is_dma_coherent(dev)) { - arch_sync_dma_for_cpu(dev, paddr, size, dir); - arch_sync_dma_for_cpu_all(dev); + arch_sync_dma_for_cpu(paddr, size, dir); + arch_sync_dma_for_cpu_all(); } if (unlikely(is_swiotlb_buffer(paddr))) @@ -321,7 +321,7 @@ void dma_direct_sync_sg_for_cpu(struct device *dev, phys_addr_t paddr = dma_to_phys(dev, sg_dma_address(sg)); if (!dev_is_dma_coherent(dev)) - arch_sync_dma_for_cpu(dev, paddr, sg->length, dir); + arch_sync_dma_for_cpu(paddr, sg->length, dir); if (unlikely(is_swiotlb_buffer(paddr))) swiotlb_tbl_sync_single(dev, paddr, sg->length, dir, @@ -329,7 +329,7 @@ void dma_direct_sync_sg_for_cpu(struct device *dev, } if (!dev_is_dma_coherent(dev)) - arch_sync_dma_for_cpu_all(dev); + arch_sync_dma_for_cpu_all(); } EXPORT_SYMBOL(dma_direct_sync_sg_for_cpu); @@ -380,7 +380,7 @@ dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, } if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - arch_sync_dma_for_device(dev, phys, size, dir); + arch_sync_dma_for_device(phys, size, dir); return dma_addr; } EXPORT_SYMBOL(dma_direct_map_page); -- cgit v1.2.3-71-gd317 From 130c1ccbf55330b55e82612a6e54eebb82c9d746 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Nov 2019 17:06:04 +0100 Subject: dma-direct: unify the dma_capable definitions Currently each architectures that wants to override dma_to_phys and phys_to_dma also has to provide dma_capable. But there isn't really any good reason for that. powerpc and mips just have copies of the generic one minus the latests fix, and the arm one was the inspiration for said fix, but misses the bus_dma_mask handling. Make all architectures use the generic version instead. Signed-off-by: Christoph Hellwig Acked-by: Michael Ellerman (powerpc) Reviewed-by: Nicolas Saenz Julienne --- arch/arm/include/asm/dma-direct.h | 19 ------------------- arch/mips/include/asm/dma-direct.h | 8 -------- arch/powerpc/include/asm/dma-direct.h | 9 --------- include/linux/dma-direct.h | 2 +- 4 files changed, 1 insertion(+), 37 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/include/asm/dma-direct.h b/arch/arm/include/asm/dma-direct.h index b67e5fc1fe43..7c3001a6a775 100644 --- a/arch/arm/include/asm/dma-direct.h +++ b/arch/arm/include/asm/dma-direct.h @@ -14,23 +14,4 @@ static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dev_addr) return __pfn_to_phys(dma_to_pfn(dev, dev_addr)) + offset; } -static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) -{ - u64 limit, mask; - - if (!dev->dma_mask) - return 0; - - mask = *dev->dma_mask; - - limit = (mask + 1) & ~mask; - if (limit && size > limit) - return 0; - - if ((addr | (addr + size - 1)) & ~mask) - return 0; - - return 1; -} - #endif /* ASM_ARM_DMA_DIRECT_H */ diff --git a/arch/mips/include/asm/dma-direct.h b/arch/mips/include/asm/dma-direct.h index b5c240806e1b..14e352651ce9 100644 --- a/arch/mips/include/asm/dma-direct.h +++ b/arch/mips/include/asm/dma-direct.h @@ -2,14 +2,6 @@ #ifndef _MIPS_DMA_DIRECT_H #define _MIPS_DMA_DIRECT_H 1 -static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) -{ - if (!dev->dma_mask) - return false; - - return addr + size - 1 <= *dev->dma_mask; -} - dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr); phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr); diff --git a/arch/powerpc/include/asm/dma-direct.h b/arch/powerpc/include/asm/dma-direct.h index a2912b47102c..e29e8a236b8d 100644 --- a/arch/powerpc/include/asm/dma-direct.h +++ b/arch/powerpc/include/asm/dma-direct.h @@ -2,15 +2,6 @@ #ifndef ASM_POWERPC_DMA_DIRECT_H #define ASM_POWERPC_DMA_DIRECT_H 1 -static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) -{ - if (!dev->dma_mask) - return false; - - return addr + size - 1 <= - min_not_zero(*dev->dma_mask, dev->bus_dma_mask); -} - static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr) { if (!dev) diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 6db863c3eb93..991f8aa2676e 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -24,6 +24,7 @@ static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dev_addr) return paddr + ((phys_addr_t)dev->dma_pfn_offset << PAGE_SHIFT); } +#endif /* !CONFIG_ARCH_HAS_PHYS_TO_DMA */ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) { @@ -38,7 +39,6 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) return end <= min_not_zero(*dev->dma_mask, dev->bus_dma_mask); } -#endif /* !CONFIG_ARCH_HAS_PHYS_TO_DMA */ #ifdef CONFIG_ARCH_HAS_FORCE_DMA_UNENCRYPTED bool force_dma_unencrypted(struct device *dev); -- cgit v1.2.3-71-gd317 From c7345159f7db6fb69ec1c3b3f8f28cd05c731be2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Nov 2019 17:07:43 +0100 Subject: dma-direct: avoid a forward declaration for phys_to_dma Move dma_capable down a bit so that we don't need a forward declaration for phys_to_dma. Signed-off-by: Christoph Hellwig Reviewed-by: Nicolas Saenz Julienne --- include/linux/dma-direct.h | 30 ++++++++++++++---------------- 1 file changed, 14 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 991f8aa2676e..f8959f75e496 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -6,8 +6,6 @@ #include /* for min_low_pfn */ #include -static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr); - #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA #include #else @@ -26,20 +24,6 @@ static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dev_addr) } #endif /* !CONFIG_ARCH_HAS_PHYS_TO_DMA */ -static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) -{ - dma_addr_t end = addr + size - 1; - - if (!dev->dma_mask) - return false; - - if (!IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) && - min(addr, end) < phys_to_dma(dev, PFN_PHYS(min_low_pfn))) - return false; - - return end <= min_not_zero(*dev->dma_mask, dev->bus_dma_mask); -} - #ifdef CONFIG_ARCH_HAS_FORCE_DMA_UNENCRYPTED bool force_dma_unencrypted(struct device *dev); #else @@ -65,6 +49,20 @@ static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr) return __sme_clr(__dma_to_phys(dev, daddr)); } +static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) +{ + dma_addr_t end = addr + size - 1; + + if (!dev->dma_mask) + return false; + + if (!IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) && + min(addr, end) < phys_to_dma(dev, PFN_PHYS(min_low_pfn))) + return false; + + return end <= min_not_zero(*dev->dma_mask, dev->bus_dma_mask); +} + u64 dma_direct_get_required_mask(struct device *dev); void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); -- cgit v1.2.3-71-gd317 From 68a33b1794665ba8a1d1ef1d3bfcc7c587d380a6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 Nov 2019 17:38:58 +0100 Subject: dma-direct: exclude dma_direct_map_resource from the min_low_pfn check The valid memory address check in dma_capable only makes sense when mapping normal memory, not when using dma_map_resource to map a device resource. Add a new boolean argument to dma_capable to exclude that check for the dma_map_resource case. Fixes: b12d66278dd6 ("dma-direct: check for overflows on 32 bit DMA addresses") Reported-by: Marek Szyprowski Signed-off-by: Christoph Hellwig Acked-by: Marek Szyprowski Tested-by: Marek Szyprowski --- arch/x86/kernel/amd_gart_64.c | 4 ++-- drivers/xen/swiotlb-xen.c | 4 ++-- include/linux/dma-direct.h | 5 +++-- kernel/dma/direct.c | 4 ++-- kernel/dma/swiotlb.c | 2 +- 5 files changed, 10 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index a6ac3712db8b..5cfab41e8509 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -185,13 +185,13 @@ static void iommu_full(struct device *dev, size_t size, int dir) static inline int need_iommu(struct device *dev, unsigned long addr, size_t size) { - return force_iommu || !dma_capable(dev, addr, size); + return force_iommu || !dma_capable(dev, addr, size, true); } static inline int nonforced_iommu(struct device *dev, unsigned long addr, size_t size) { - return !dma_capable(dev, addr, size); + return !dma_capable(dev, addr, size, true); } /* Map a single continuous physical area into the IOMMU. diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 3f8b2cdb4acb..b6d27762c6f8 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -375,7 +375,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, * we can safely return the device addr and not worry about bounce * buffering it. */ - if (dma_capable(dev, dev_addr, size) && + if (dma_capable(dev, dev_addr, size, true) && !range_straddles_page_boundary(phys, size) && !xen_arch_need_swiotlb(dev, phys, dev_addr) && swiotlb_force != SWIOTLB_FORCE) @@ -397,7 +397,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, /* * Ensure that the address returned is DMA'ble */ - if (unlikely(!dma_capable(dev, dev_addr, size))) { + if (unlikely(!dma_capable(dev, dev_addr, size, true))) { swiotlb_tbl_unmap_single(dev, map, size, size, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC); return DMA_MAPPING_ERROR; diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index f8959f75e496..99b77dd5f79b 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -49,14 +49,15 @@ static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr) return __sme_clr(__dma_to_phys(dev, daddr)); } -static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) +static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size, + bool is_ram) { dma_addr_t end = addr + size - 1; if (!dev->dma_mask) return false; - if (!IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) && + if (is_ram && !IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) && min(addr, end) < phys_to_dma(dev, PFN_PHYS(min_low_pfn))) return false; diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index a479bd2d1e8b..40f1f0aac4b1 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -363,7 +363,7 @@ static inline bool dma_direct_possible(struct device *dev, dma_addr_t dma_addr, size_t size) { return swiotlb_force != SWIOTLB_FORCE && - dma_capable(dev, dma_addr, size); + dma_capable(dev, dma_addr, size, true); } dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, @@ -412,7 +412,7 @@ dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr, { dma_addr_t dma_addr = paddr; - if (unlikely(!dma_capable(dev, dma_addr, size))) { + if (unlikely(!dma_capable(dev, dma_addr, size, false))) { report_addr(dev, dma_addr, size); return DMA_MAPPING_ERROR; } diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 673a2cdb2656..9280d6f8271e 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -678,7 +678,7 @@ bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr, /* Ensure that the address returned is DMA'ble */ *dma_addr = __phys_to_dma(dev, *phys); - if (unlikely(!dma_capable(dev, *dma_addr, size))) { + if (unlikely(!dma_capable(dev, *dma_addr, size, true))) { swiotlb_tbl_unmap_single(dev, *phys, size, size, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC); return false; -- cgit v1.2.3-71-gd317 From 91e6015b082b08a74e5d9d326f651e5890a93519 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 20 Nov 2019 22:38:16 +0100 Subject: bpf: Emit audit messages upon successful prog load and unload Allow for audit messages to be emitted upon BPF program load and unload for having a timeline of events. The load itself is in syscall context, so additional info about the process initiating the BPF prog creation can be logged and later directly correlated to the unload event. The only info really needed from BPF side is the globally unique prog ID where then audit user space tooling can query / dump all info needed about the specific BPF program right upon load event and enrich the record, thus these changes needed here can be kept small and non-intrusive to the core. Raw example output: # auditctl -D # auditctl -a always,exit -F arch=x86_64 -S bpf # ausearch --start recent -m 1334 [...] ---- time->Wed Nov 20 12:45:51 2019 type=PROCTITLE msg=audit(1574271951.590:8974): proctitle="./test_verifier" type=SYSCALL msg=audit(1574271951.590:8974): arch=c000003e syscall=321 success=yes exit=14 a0=5 a1=7ffe2d923e80 a2=78 a3=0 items=0 ppid=742 pid=949 auid=0 uid=0 gid=0 euid=0 suid=0 fsuid=0 egid=0 sgid=0 fsgid=0 tty=pts0 ses=2 comm="test_verifier" exe="/root/bpf-next/tools/testing/selftests/bpf/test_verifier" subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 key=(null) type=UNKNOWN[1334] msg=audit(1574271951.590:8974): auid=0 uid=0 gid=0 ses=2 subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 pid=949 comm="test_verifier" exe="/root/bpf-next/tools/testing/selftests/bpf/test_verifier" prog-id=3260 event=LOAD ---- time->Wed Nov 20 12:45:51 2019 type=UNKNOWN[1334] msg=audit(1574271951.590:8975): prog-id=3260 event=UNLOAD ---- [...] Signed-off-by: Daniel Borkmann Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20191120213816.8186-1-jolsa@kernel.org --- include/linux/audit.h | 3 +++ include/uapi/linux/audit.h | 1 + kernel/auditsc.c | 2 +- kernel/bpf/syscall.c | 31 +++++++++++++++++++++++++++++++ 4 files changed, 36 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index aee3dc9eb378..edd006f4597d 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -159,6 +159,7 @@ extern void audit_log_key(struct audit_buffer *ab, extern void audit_log_link_denied(const char *operation); extern void audit_log_lost(const char *message); +extern void audit_log_task(struct audit_buffer *ab); extern int audit_log_task_context(struct audit_buffer *ab); extern void audit_log_task_info(struct audit_buffer *ab); @@ -219,6 +220,8 @@ static inline void audit_log_key(struct audit_buffer *ab, char *key) { } static inline void audit_log_link_denied(const char *string) { } +static inline void audit_log_task(struct audit_buffer *ab) +{ } static inline int audit_log_task_context(struct audit_buffer *ab) { return 0; diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index c89c6495983d..32a5db900f47 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -116,6 +116,7 @@ #define AUDIT_FANOTIFY 1331 /* Fanotify access decision */ #define AUDIT_TIME_INJOFFSET 1332 /* Timekeeping offset injected */ #define AUDIT_TIME_ADJNTPVAL 1333 /* NTP value adjustment */ +#define AUDIT_BPF 1334 /* BPF subsystem */ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 4effe01ebbe2..9bf1045fedfa 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -2545,7 +2545,7 @@ void __audit_ntp_log(const struct audit_ntp_data *ad) audit_log_ntp_val(ad, "adjust", AUDIT_NTP_ADJUST); } -static void audit_log_task(struct audit_buffer *ab) +void audit_log_task(struct audit_buffer *ab) { kuid_t auid, uid; kgid_t gid; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index bac3becf9f90..17f4254495f2 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \ @@ -1318,6 +1319,34 @@ static void free_used_maps(struct bpf_prog_aux *aux) kfree(aux->used_maps); } +enum bpf_event { + BPF_EVENT_LOAD, + BPF_EVENT_UNLOAD, +}; + +static const char * const bpf_event_audit_str[] = { + [BPF_EVENT_LOAD] = "LOAD", + [BPF_EVENT_UNLOAD] = "UNLOAD", +}; + +static void bpf_audit_prog(const struct bpf_prog *prog, enum bpf_event event) +{ + bool has_task_context = event == BPF_EVENT_LOAD; + struct audit_buffer *ab; + + if (audit_enabled == AUDIT_OFF) + return; + ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_BPF); + if (unlikely(!ab)) + return; + if (has_task_context) + audit_log_task(ab); + audit_log_format(ab, "%sprog-id=%u event=%s", + has_task_context ? " " : "", + prog->aux->id, bpf_event_audit_str[event]); + audit_log_end(ab); +} + int __bpf_prog_charge(struct user_struct *user, u32 pages) { unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; @@ -1434,6 +1463,7 @@ static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) { if (atomic64_dec_and_test(&prog->aux->refcnt)) { perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0); + bpf_audit_prog(prog, BPF_EVENT_UNLOAD); /* bpf_prog_free_id() must be called first */ bpf_prog_free_id(prog, do_idr_lock); __bpf_prog_put_noref(prog, true); @@ -1843,6 +1873,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) */ bpf_prog_kallsyms_add(prog); perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_LOAD, 0); + bpf_audit_prog(prog, BPF_EVENT_LOAD); err = bpf_prog_new_fd(prog); if (err < 0) -- cgit v1.2.3-71-gd317 From 196e8ca74886c433dcfc64a809707074b936aaf5 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 20 Nov 2019 23:04:44 +0100 Subject: bpf: Switch bpf_map_{area_alloc,area_mmapable_alloc}() to u64 size Given we recently extended the original bpf_map_area_alloc() helper in commit fc9702273e2e ("bpf: Add mmap() support for BPF_MAP_TYPE_ARRAY"), we need to apply the same logic as in ff1c08e1f74b ("bpf: Change size to u64 for bpf_map_{area_alloc, charge_init}()"). To avoid conflicts, extend it for bpf-next. Reported-by: Stephen Rothwell Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 6 +++--- kernel/bpf/syscall.c | 11 +++++++---- 2 files changed, 10 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e913dd5946ae..e89e86122233 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -794,12 +794,12 @@ void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); int bpf_map_charge_memlock(struct bpf_map *map, u32 pages); void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages); -int bpf_map_charge_init(struct bpf_map_memory *mem, size_t size); +int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size); void bpf_map_charge_finish(struct bpf_map_memory *mem); void bpf_map_charge_move(struct bpf_map_memory *dst, struct bpf_map_memory *src); -void *bpf_map_area_alloc(size_t size, int numa_node); -void *bpf_map_area_mmapable_alloc(size_t size, int numa_node); +void *bpf_map_area_alloc(u64 size, int numa_node); +void *bpf_map_area_mmapable_alloc(u64 size, int numa_node); void bpf_map_area_free(void *base); void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 17f4254495f2..b51ecb9644d0 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -128,7 +128,7 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) return map; } -static void *__bpf_map_area_alloc(size_t size, int numa_node, bool mmapable) +static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable) { /* We really just want to fail instead of triggering OOM killer * under memory pressure, therefore we set __GFP_NORETRY to kmalloc, @@ -143,6 +143,9 @@ static void *__bpf_map_area_alloc(size_t size, int numa_node, bool mmapable) const gfp_t flags = __GFP_NOWARN | __GFP_ZERO; void *area; + if (size >= SIZE_MAX) + return NULL; + /* kmalloc()'ed memory can't be mmap()'ed */ if (!mmapable && size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { area = kmalloc_node(size, GFP_USER | __GFP_NORETRY | flags, @@ -160,12 +163,12 @@ static void *__bpf_map_area_alloc(size_t size, int numa_node, bool mmapable) flags, __builtin_return_address(0)); } -void *bpf_map_area_alloc(size_t size, int numa_node) +void *bpf_map_area_alloc(u64 size, int numa_node) { return __bpf_map_area_alloc(size, numa_node, false); } -void *bpf_map_area_mmapable_alloc(size_t size, int numa_node) +void *bpf_map_area_mmapable_alloc(u64 size, int numa_node) { return __bpf_map_area_alloc(size, numa_node, true); } @@ -214,7 +217,7 @@ static void bpf_uncharge_memlock(struct user_struct *user, u32 pages) atomic_long_sub(pages, &user->locked_vm); } -int bpf_map_charge_init(struct bpf_map_memory *mem, size_t size) +int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size) { u32 pages = round_up(size, PAGE_SIZE) >> PAGE_SHIFT; struct user_struct *user; -- cgit v1.2.3-71-gd317 From 12bcae44bf48595c71898330076576075590e15b Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Mon, 7 Oct 2019 07:52:28 -0500 Subject: PCI/PM: Use pci_WARN() to include device information Add and use pci_WARN() wrappers so warnings include device information. Link: https://lore.kernel.org/r/20191017212851.54237-3-helgaas@kernel.org Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki --- drivers/pci/pci-driver.c | 34 +++++++++++++++++----------------- include/linux/pci.h | 8 ++++++++ 2 files changed, 25 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 407b1df5ea7c..5337cbbd69de 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -585,9 +585,9 @@ static int pci_legacy_suspend(struct device *dev, pm_message_t state) if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0 && pci_dev->current_state != PCI_UNKNOWN) { - WARN_ONCE(pci_dev->current_state != prev, - "PCI PM: Device state not saved by %pS\n", - drv->suspend); + pci_WARN_ONCE(pci_dev, pci_dev->current_state != prev, + "PCI PM: Device state not saved by %pS\n", + drv->suspend); } } @@ -612,9 +612,9 @@ static int pci_legacy_suspend_late(struct device *dev, pm_message_t state) if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0 && pci_dev->current_state != PCI_UNKNOWN) { - WARN_ONCE(pci_dev->current_state != prev, - "PCI PM: Device state not saved by %pS\n", - drv->suspend_late); + pci_WARN_ONCE(pci_dev, pci_dev->current_state != prev, + "PCI PM: Device state not saved by %pS\n", + drv->suspend_late); goto Fixup; } } @@ -670,8 +670,8 @@ static bool pci_has_legacy_pm_support(struct pci_dev *pci_dev) * supported as well. Drivers are supposed to support either the * former, or the latter, but not both at the same time. */ - WARN(ret && drv->driver.pm, "driver %s device %04x:%04x\n", - drv->name, pci_dev->vendor, pci_dev->device); + pci_WARN(pci_dev, ret && drv->driver.pm, "device %04x:%04x\n", + pci_dev->vendor, pci_dev->device); return ret; } @@ -794,9 +794,9 @@ static int pci_pm_suspend(struct device *dev) if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0 && pci_dev->current_state != PCI_UNKNOWN) { - WARN_ONCE(pci_dev->current_state != prev, - "PCI PM: State of device not saved by %pS\n", - pm->suspend); + pci_WARN_ONCE(pci_dev, pci_dev->current_state != prev, + "PCI PM: State of device not saved by %pS\n", + pm->suspend); } } @@ -842,9 +842,9 @@ static int pci_pm_suspend_noirq(struct device *dev) if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0 && pci_dev->current_state != PCI_UNKNOWN) { - WARN_ONCE(pci_dev->current_state != prev, - "PCI PM: State of device not saved by %pS\n", - pm->suspend_noirq); + pci_WARN_ONCE(pci_dev, pci_dev->current_state != prev, + "PCI PM: State of device not saved by %pS\n", + pm->suspend_noirq); goto Fixup; } } @@ -1311,9 +1311,9 @@ static int pci_pm_runtime_suspend(struct device *dev) if (pm && pm->runtime_suspend && !pci_dev->state_saved && pci_dev->current_state != PCI_D0 && pci_dev->current_state != PCI_UNKNOWN) { - WARN_ONCE(pci_dev->current_state != prev, - "PCI PM: State of device not saved by %pS\n", - pm->runtime_suspend); + pci_WARN_ONCE(pci_dev, pci_dev->current_state != prev, + "PCI PM: State of device not saved by %pS\n", + pm->runtime_suspend); return 0; } diff --git a/include/linux/pci.h b/include/linux/pci.h index f9088c89a534..4846306d521c 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2400,4 +2400,12 @@ void pci_uevent_ers(struct pci_dev *pdev, enum pci_ers_result err_type); #define pci_info_ratelimited(pdev, fmt, arg...) \ dev_info_ratelimited(&(pdev)->dev, fmt, ##arg) +#define pci_WARN(pdev, condition, fmt, arg...) \ + WARN(condition, "%s %s: " fmt, \ + dev_driver_string(&(pdev)->dev), pci_name(pdev), ##arg) + +#define pci_WARN_ONCE(pdev, condition, fmt, arg...) \ + WARN_ONCE(condition, "%s %s: " fmt, \ + dev_driver_string(&(pdev)->dev), pci_name(pdev), ##arg) + #endif /* LINUX_PCI_H */ -- cgit v1.2.3-71-gd317 From 89cdbc3546354c359558a1809133902028c57da4 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 31 Oct 2019 17:53:04 -0500 Subject: PCI/PM: Remove unused pci_driver.resume_early() hook The struct pci_driver.resume_early() hook is one of the legacy PCI power management callbacks, and there are no remaining users of it. Remove it. Link: https://lore.kernel.org/r/20191101204558.210235-6-helgaas@kernel.org Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki --- Documentation/power/pci.rst | 2 +- drivers/pci/pci-driver.c | 23 ++++++----------------- include/linux/pci.h | 2 -- 3 files changed, 7 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/Documentation/power/pci.rst b/Documentation/power/pci.rst index a90e82c70a3b..ff7029b94068 100644 --- a/Documentation/power/pci.rst +++ b/Documentation/power/pci.rst @@ -692,7 +692,7 @@ controlling the runtime power management of their devices. At the time of this writing there are two ways to define power management callbacks for a PCI device driver, the recommended one, based on using a dev_pm_ops structure described in Documentation/driver-api/pm/devices.rst, and -the "legacy" one, in which the .suspend(), .suspend_late(), .resume_early(), and +the "legacy" one, in which the .suspend(), .suspend_late(), and .resume() callbacks from struct pci_driver are used. The legacy approach, however, doesn't allow one to define runtime power management callbacks and is not really suitable for any new drivers. Therefore it is not covered by this diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 5337cbbd69de..fc372c2d529a 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -630,15 +630,6 @@ Fixup: return 0; } -static int pci_legacy_resume_early(struct device *dev) -{ - struct pci_dev *pci_dev = to_pci_dev(dev); - struct pci_driver *drv = pci_dev->driver; - - return drv && drv->resume_early ? - drv->resume_early(pci_dev) : 0; -} - static int pci_legacy_resume(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); @@ -662,8 +653,7 @@ static void pci_pm_default_suspend(struct pci_dev *pci_dev) static bool pci_has_legacy_pm_support(struct pci_dev *pci_dev) { struct pci_driver *drv = pci_dev->driver; - bool ret = drv && (drv->suspend || drv->suspend_late || drv->resume - || drv->resume_early); + bool ret = drv && (drv->suspend || drv->suspend_late || drv->resume); /* * Legacy PM support is used by default, so warn if the new framework is @@ -944,7 +934,7 @@ static int pci_pm_resume_noirq(struct device *dev) pcie_pme_root_status_cleanup(pci_dev); if (pci_has_legacy_pm_support(pci_dev)) - return pci_legacy_resume_early(dev); + return 0; if (pm && pm->resume_noirq) return pm->resume_noirq(dev); @@ -1074,9 +1064,8 @@ static int pci_pm_thaw_noirq(struct device *dev) } /* - * Both the legacy ->resume_early() and the new pm->thaw_noirq() - * callbacks assume the device has been returned to D0 and its - * config state has been restored. + * The pm->thaw_noirq() callback assumes the device has been + * returned to D0 and its config state has been restored. * * In addition, pci_restore_state() restores MSI-X state in MMIO * space, which requires the device to be in D0, so return it to D0 @@ -1087,7 +1076,7 @@ static int pci_pm_thaw_noirq(struct device *dev) pci_restore_state(pci_dev); if (pci_has_legacy_pm_support(pci_dev)) - return pci_legacy_resume_early(dev); + return 0; if (pm && pm->thaw_noirq) return pm->thaw_noirq(dev); @@ -1219,7 +1208,7 @@ static int pci_pm_restore_noirq(struct device *dev) pci_fixup_device(pci_fixup_resume_early, pci_dev); if (pci_has_legacy_pm_support(pci_dev)) - return pci_legacy_resume_early(dev); + return 0; if (pm && pm->restore_noirq) return pm->restore_noirq(dev); diff --git a/include/linux/pci.h b/include/linux/pci.h index 4846306d521c..dd4596fc1208 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -806,7 +806,6 @@ struct module; * context, so it can sleep. * @suspend: Put device into low power state. * @suspend_late: Put device into low power state. - * @resume_early: Wake device from low power state. * @resume: Wake device from low power state. * (Please see Documentation/power/pci.rst for descriptions * of PCI Power Management and the related functions.) @@ -830,7 +829,6 @@ struct pci_driver { void (*remove)(struct pci_dev *dev); /* Device removed (NULL if not a hot-plug capable driver) */ int (*suspend)(struct pci_dev *dev, pm_message_t state); /* Device suspended */ int (*suspend_late)(struct pci_dev *dev, pm_message_t state); - int (*resume_early)(struct pci_dev *dev); int (*resume)(struct pci_dev *dev); /* Device woken up */ void (*shutdown)(struct pci_dev *dev); int (*sriov_configure)(struct pci_dev *dev, int num_vfs); /* On PF */ -- cgit v1.2.3-71-gd317 From 1a1daf097e21e544dd3e7c0ff620d78a9795fbf2 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 31 Oct 2019 17:37:54 -0500 Subject: PCI/PM: Remove unused pci_driver.suspend_late() hook The struct pci_driver.suspend_late() hook is one of the legacy PCI power management callbacks, and there are no remaining users of it. Remove it. Link: https://lore.kernel.org/r/20191101204558.210235-7-helgaas@kernel.org Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki --- Documentation/power/pci.rst | 10 +++++----- drivers/pci/pci-driver.c | 22 +--------------------- include/linux/pci.h | 2 -- 3 files changed, 6 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/Documentation/power/pci.rst b/Documentation/power/pci.rst index ff7029b94068..0924d29636ad 100644 --- a/Documentation/power/pci.rst +++ b/Documentation/power/pci.rst @@ -692,11 +692,11 @@ controlling the runtime power management of their devices. At the time of this writing there are two ways to define power management callbacks for a PCI device driver, the recommended one, based on using a dev_pm_ops structure described in Documentation/driver-api/pm/devices.rst, and -the "legacy" one, in which the .suspend(), .suspend_late(), and -.resume() callbacks from struct pci_driver are used. The legacy approach, -however, doesn't allow one to define runtime power management callbacks and is -not really suitable for any new drivers. Therefore it is not covered by this -document (refer to the source code to learn more about it). +the "legacy" one, in which the .suspend() and .resume() callbacks from struct +pci_driver are used. The legacy approach, however, doesn't allow one to define +runtime power management callbacks and is not really suitable for any new +drivers. Therefore it is not covered by this document (refer to the source code +to learn more about it). It is recommended that all PCI device drivers define a struct dev_pm_ops object containing pointers to power management (PM) callbacks that will be executed by diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index fc372c2d529a..e89fd90eaa93 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -599,32 +599,12 @@ static int pci_legacy_suspend(struct device *dev, pm_message_t state) static int pci_legacy_suspend_late(struct device *dev, pm_message_t state) { struct pci_dev *pci_dev = to_pci_dev(dev); - struct pci_driver *drv = pci_dev->driver; - - if (drv && drv->suspend_late) { - pci_power_t prev = pci_dev->current_state; - int error; - - error = drv->suspend_late(pci_dev, state); - suspend_report_result(drv->suspend_late, error); - if (error) - return error; - - if (!pci_dev->state_saved && pci_dev->current_state != PCI_D0 - && pci_dev->current_state != PCI_UNKNOWN) { - pci_WARN_ONCE(pci_dev, pci_dev->current_state != prev, - "PCI PM: Device state not saved by %pS\n", - drv->suspend_late); - goto Fixup; - } - } if (!pci_dev->state_saved) pci_save_state(pci_dev); pci_pm_set_unknown_state(pci_dev); -Fixup: pci_fixup_device(pci_fixup_suspend_late, pci_dev); return 0; @@ -653,7 +633,7 @@ static void pci_pm_default_suspend(struct pci_dev *pci_dev) static bool pci_has_legacy_pm_support(struct pci_dev *pci_dev) { struct pci_driver *drv = pci_dev->driver; - bool ret = drv && (drv->suspend || drv->suspend_late || drv->resume); + bool ret = drv && (drv->suspend || drv->resume); /* * Legacy PM support is used by default, so warn if the new framework is diff --git a/include/linux/pci.h b/include/linux/pci.h index dd4596fc1208..9b0e35e09874 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -805,7 +805,6 @@ struct module; * The remove function always gets called from process * context, so it can sleep. * @suspend: Put device into low power state. - * @suspend_late: Put device into low power state. * @resume: Wake device from low power state. * (Please see Documentation/power/pci.rst for descriptions * of PCI Power Management and the related functions.) @@ -828,7 +827,6 @@ struct pci_driver { int (*probe)(struct pci_dev *dev, const struct pci_device_id *id); /* New device inserted */ void (*remove)(struct pci_dev *dev); /* Device removed (NULL if not a hot-plug capable driver) */ int (*suspend)(struct pci_dev *dev, pm_message_t state); /* Device suspended */ - int (*suspend_late)(struct pci_dev *dev, pm_message_t state); int (*resume)(struct pci_dev *dev); /* Device woken up */ void (*shutdown)(struct pci_dev *dev); int (*sriov_configure)(struct pci_dev *dev, int num_vfs); /* On PF */ -- cgit v1.2.3-71-gd317 From d6aa37cd04fdafaf31ae89691e537535df43ca78 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 5 Nov 2019 11:30:36 +0100 Subject: PCI/PM: Avoid exporting __pci_complete_power_transition() Notice that radeon_set_suspend(), which is the only caller of __pci_complete_power_transition() outside of pci.c, really only cares about the pci_platform_power_transition() invoked by it, so export the latter instead of it, update the radeon driver to call pci_platform_power_transition() directly and make __pci_complete_power_transition() static. Code rearrangement, no intentional functional impact. Link: https://lore.kernel.org/r/1731661.ykamz2Tiuf@kreacher Signed-off-by: Rafael J. Wysocki Signed-off-by: Bjorn Helgaas Reviewed-by: Mika Westerberg --- drivers/pci/pci.c | 6 +++--- drivers/video/fbdev/aty/radeon_pm.c | 2 +- include/linux/pci.h | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 56bc79e33286..2f53234f9e91 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -963,7 +963,7 @@ void pci_refresh_power_state(struct pci_dev *dev) * @dev: PCI device to handle. * @state: State to put the device into. */ -static int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state) +int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state) { int error; @@ -979,6 +979,7 @@ static int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state) return error; } +EXPORT_SYMBOL_GPL(pci_platform_power_transition); /** * pci_wakeup - Wake up a PCI device @@ -1061,7 +1062,7 @@ void pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state) * * This function should not be called directly by device drivers. */ -int __pci_complete_power_transition(struct pci_dev *dev, pci_power_t state) +static int __pci_complete_power_transition(struct pci_dev *dev, pci_power_t state) { int ret; @@ -1073,7 +1074,6 @@ int __pci_complete_power_transition(struct pci_dev *dev, pci_power_t state) pci_bus_set_current_state(dev->subordinate, PCI_D3cold); return ret; } -EXPORT_SYMBOL_GPL(__pci_complete_power_transition); /** * pci_set_power_state - Set the power state of a PCI device diff --git a/drivers/video/fbdev/aty/radeon_pm.c b/drivers/video/fbdev/aty/radeon_pm.c index 2dc5703eac51..7c4483c7f313 100644 --- a/drivers/video/fbdev/aty/radeon_pm.c +++ b/drivers/video/fbdev/aty/radeon_pm.c @@ -2593,7 +2593,7 @@ static void radeon_set_suspend(struct radeonfb_info *rinfo, int suspend) * calling pci_set_power_state() */ radeonfb_whack_power_state(rinfo, PCI_D2); - __pci_complete_power_transition(rinfo->pdev, PCI_D2); + pci_platform_power_transition(rinfo->pdev, PCI_D2); } else { printk(KERN_DEBUG "radeonfb (%s): switching to D0 state...\n", pci_name(rinfo->pdev)); diff --git a/include/linux/pci.h b/include/linux/pci.h index 9b0e35e09874..86976cccdfe3 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1228,7 +1228,7 @@ struct pci_cap_saved_state *pci_find_saved_ext_cap(struct pci_dev *dev, int pci_add_cap_save_buffer(struct pci_dev *dev, char cap, unsigned int size); int pci_add_ext_cap_save_buffer(struct pci_dev *dev, u16 cap, unsigned int size); -int __pci_complete_power_transition(struct pci_dev *dev, pci_power_t state); +int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state); int pci_set_power_state(struct pci_dev *dev, pci_power_t state); pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state); bool pci_pme_capable(struct pci_dev *dev, pci_power_t state); -- cgit v1.2.3-71-gd317 From eb01fedc3d539f9443082aa2384c5d1ca26ed5c1 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 20 Nov 2019 18:32:25 -0500 Subject: ftrace: Return ENOTSUPP when DYNAMIC_FTRACE_WITH_DIRECT_CALLS is not configured When CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS is not set it's best to have the stub functions return ENOTSUPP instead of ENODEV, otherwise ENODEV is a valid error when ip is incorrect which is indistinguishable from ftrace not compiled in. Link: http://lkml.kernel.org/r/CAADnVQ+OzTikM9EhrfsC7NFsVYhATW1SVHxK64w3xn9qpk81pg@mail.gmail.com Signed-off-by: Alexei Starovoitov Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index dfaa37e1943d..af79b0f8cdc1 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -268,16 +268,16 @@ int ftrace_modify_direct_caller(struct ftrace_func_entry *entry, # define ftrace_direct_func_count 0 static inline int register_ftrace_direct(unsigned long ip, unsigned long addr) { - return -ENODEV; + return -ENOTSUPP; } static inline int unregister_ftrace_direct(unsigned long ip, unsigned long addr) { - return -ENODEV; + return -ENOTSUPP; } static inline int modify_ftrace_direct(unsigned long ip, unsigned long old_addr, unsigned long new_addr) { - return -ENODEV; + return -ENOTSUPP; } static inline struct ftrace_direct_func *ftrace_find_direct_func(unsigned long addr) { -- cgit v1.2.3-71-gd317 From f3c9a666b28572b1a0ae691a47d9a7de4d9cefb3 Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 20 Nov 2019 12:29:59 +0000 Subject: net: sfp: soft status and control support Add support for the soft status and control register, which allows TX_FAULT and RX_LOS to be monitored and TX_DISABLE to be set. We make use of this when the board does not support GPIOs for these signals. Signed-off-by: Russell King Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/sfp.c | 110 +++++++++++++++++++++++++++++++++++++++++--------- include/linux/sfp.h | 4 ++ 2 files changed, 94 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index b0f88c2c0153..bdbbb76f8fd3 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -201,7 +201,10 @@ struct sfp { struct gpio_desc *gpio[GPIO_MAX]; int gpio_irq[GPIO_MAX]; + bool need_poll; + struct mutex st_mutex; /* Protects state */ + unsigned int state_soft_mask; unsigned int state; struct delayed_work poll; struct delayed_work timeout; @@ -395,24 +398,90 @@ static int sfp_i2c_configure(struct sfp *sfp, struct i2c_adapter *i2c) } /* Interface */ -static unsigned int sfp_get_state(struct sfp *sfp) +static int sfp_read(struct sfp *sfp, bool a2, u8 addr, void *buf, size_t len) { - return sfp->get_state(sfp); + return sfp->read(sfp, a2, addr, buf, len); } -static void sfp_set_state(struct sfp *sfp, unsigned int state) +static int sfp_write(struct sfp *sfp, bool a2, u8 addr, void *buf, size_t len) { - sfp->set_state(sfp, state); + return sfp->write(sfp, a2, addr, buf, len); } -static int sfp_read(struct sfp *sfp, bool a2, u8 addr, void *buf, size_t len) +static unsigned int sfp_soft_get_state(struct sfp *sfp) { - return sfp->read(sfp, a2, addr, buf, len); + unsigned int state = 0; + u8 status; + + if (sfp_read(sfp, true, SFP_STATUS, &status, sizeof(status)) == + sizeof(status)) { + if (status & SFP_STATUS_RX_LOS) + state |= SFP_F_LOS; + if (status & SFP_STATUS_TX_FAULT) + state |= SFP_F_TX_FAULT; + } + + return state & sfp->state_soft_mask; } -static int sfp_write(struct sfp *sfp, bool a2, u8 addr, void *buf, size_t len) +static void sfp_soft_set_state(struct sfp *sfp, unsigned int state) { - return sfp->write(sfp, a2, addr, buf, len); + u8 status; + + if (sfp_read(sfp, true, SFP_STATUS, &status, sizeof(status)) == + sizeof(status)) { + if (state & SFP_F_TX_DISABLE) + status |= SFP_STATUS_TX_DISABLE_FORCE; + else + status &= ~SFP_STATUS_TX_DISABLE_FORCE; + + sfp_write(sfp, true, SFP_STATUS, &status, sizeof(status)); + } +} + +static void sfp_soft_start_poll(struct sfp *sfp) +{ + const struct sfp_eeprom_id *id = &sfp->id; + + sfp->state_soft_mask = 0; + if (id->ext.enhopts & SFP_ENHOPTS_SOFT_TX_DISABLE && + !sfp->gpio[GPIO_TX_DISABLE]) + sfp->state_soft_mask |= SFP_F_TX_DISABLE; + if (id->ext.enhopts & SFP_ENHOPTS_SOFT_TX_FAULT && + !sfp->gpio[GPIO_TX_FAULT]) + sfp->state_soft_mask |= SFP_F_TX_FAULT; + if (id->ext.enhopts & SFP_ENHOPTS_SOFT_RX_LOS && + !sfp->gpio[GPIO_LOS]) + sfp->state_soft_mask |= SFP_F_LOS; + + if (sfp->state_soft_mask & (SFP_F_LOS | SFP_F_TX_FAULT) && + !sfp->need_poll) + mod_delayed_work(system_wq, &sfp->poll, poll_jiffies); +} + +static void sfp_soft_stop_poll(struct sfp *sfp) +{ + sfp->state_soft_mask = 0; +} + +static unsigned int sfp_get_state(struct sfp *sfp) +{ + unsigned int state = sfp->get_state(sfp); + + if (state & SFP_F_PRESENT && + sfp->state_soft_mask & (SFP_F_LOS | SFP_F_TX_FAULT)) + state |= sfp_soft_get_state(sfp); + + return state; +} + +static void sfp_set_state(struct sfp *sfp, unsigned int state) +{ + sfp->set_state(sfp, state); + + if (state & SFP_F_PRESENT && + sfp->state_soft_mask & SFP_F_TX_DISABLE) + sfp_soft_set_state(sfp, state); } static unsigned int sfp_check(void *buf, size_t len) @@ -1407,11 +1476,6 @@ static void sfp_sm_fault(struct sfp *sfp, unsigned int next_state, bool warn) } } -static void sfp_sm_mod_init(struct sfp *sfp) -{ - sfp_module_tx_enable(sfp); -} - static void sfp_sm_probe_for_phy(struct sfp *sfp) { /* Setting the serdes link mode is guesswork: there's no @@ -1574,7 +1638,7 @@ static int sfp_sm_mod_probe(struct sfp *sfp, bool report) (int)sizeof(id.ext.datecode), id.ext.datecode); /* Check whether we support this module */ - if (!sfp->type->module_supported(&sfp->id)) { + if (!sfp->type->module_supported(&id)) { dev_err(sfp->dev, "module is not supported - phys id 0x%02x 0x%02x\n", sfp->id.base.phys_id, sfp->id.base.phys_ext_id); @@ -1764,6 +1828,7 @@ static void sfp_sm_main(struct sfp *sfp, unsigned int event) if (sfp->mod_phy) sfp_sm_phy_detach(sfp); sfp_module_tx_disable(sfp); + sfp_soft_stop_poll(sfp); sfp_sm_next(sfp, SFP_S_DOWN, 0); return; } @@ -1775,7 +1840,10 @@ static void sfp_sm_main(struct sfp *sfp, unsigned int event) sfp->sm_dev_state != SFP_DEV_UP) break; - sfp_sm_mod_init(sfp); + if (!(sfp->id.ext.diagmon & SFP_DIAGMON_ADDRMODE)) + sfp_soft_start_poll(sfp); + + sfp_module_tx_enable(sfp); /* Initialise the fault clearance retries */ sfp->sm_retries = 5; @@ -2031,7 +2099,10 @@ static void sfp_poll(struct work_struct *work) struct sfp *sfp = container_of(work, struct sfp, poll.work); sfp_check_state(sfp); - mod_delayed_work(system_wq, &sfp->poll, poll_jiffies); + + if (sfp->state_soft_mask & (SFP_F_LOS | SFP_F_TX_FAULT) || + sfp->need_poll) + mod_delayed_work(system_wq, &sfp->poll, poll_jiffies); } static struct sfp *sfp_alloc(struct device *dev) @@ -2076,7 +2147,6 @@ static int sfp_probe(struct platform_device *pdev) const struct sff_data *sff; struct i2c_adapter *i2c; struct sfp *sfp; - bool poll = false; int err, i; sfp = sfp_alloc(&pdev->dev); @@ -2183,7 +2253,7 @@ static int sfp_probe(struct platform_device *pdev) sfp->gpio_irq[i] = gpiod_to_irq(sfp->gpio[i]); if (!sfp->gpio_irq[i]) { - poll = true; + sfp->need_poll = true; continue; } @@ -2195,11 +2265,11 @@ static int sfp_probe(struct platform_device *pdev) dev_name(sfp->dev), sfp); if (err) { sfp->gpio_irq[i] = 0; - poll = true; + sfp->need_poll = true; } } - if (poll) + if (sfp->need_poll) mod_delayed_work(system_wq, &sfp->poll, poll_jiffies); /* We could have an issue in cases no Tx disable pin is available or diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 3b35efd85bb1..487fd9412d10 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -428,6 +428,10 @@ enum { SFP_TEC_CUR = 0x6c, SFP_STATUS = 0x6e, + SFP_STATUS_TX_DISABLE = BIT(7), + SFP_STATUS_TX_DISABLE_FORCE = BIT(6), + SFP_STATUS_TX_FAULT = BIT(2), + SFP_STATUS_RX_LOS = BIT(1), SFP_ALARM0 = 0x70, SFP_ALARM0_TEMP_HIGH = BIT(7), SFP_ALARM0_TEMP_LOW = BIT(6), -- cgit v1.2.3-71-gd317 From 74722bb223d0f236303b60c9509ff924a9713780 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 21 Nov 2019 03:44:26 +0100 Subject: sched/vtime: Bring up complete kcpustat accessor Many callsites want to fetch the values of system, user, user_nice, guest or guest_nice kcpustat fields altogether or at least a pair of these. In that case calling kcpustat_field() for each requested field brings unecessary overhead when we could fetch all of them in a row. So provide kcpustat_cpu_fetch() that fetches the whole kcpustat array in a vtime safe way under the same RCU and seqcount block. Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: Wanpeng Li Cc: Yauheni Kaliuta Link: https://lkml.kernel.org/r/20191121024430.19938-3-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/kernel_stat.h | 7 +++ kernel/sched/cputime.c | 136 +++++++++++++++++++++++++++++++++++++------- 2 files changed, 123 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 79781196eb25..89f0745c096d 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -81,12 +81,19 @@ static inline unsigned int kstat_cpu_irqs_sum(unsigned int cpu) #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN extern u64 kcpustat_field(struct kernel_cpustat *kcpustat, enum cpu_usage_stat usage, int cpu); +extern void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu); #else static inline u64 kcpustat_field(struct kernel_cpustat *kcpustat, enum cpu_usage_stat usage, int cpu) { return kcpustat->cpustat[usage]; } + +static inline void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu) +{ + *dst = kcpustat_cpu(cpu); +} + #endif extern void account_user_time(struct task_struct *, u64); diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 27b5406222fc..d43318a489f2 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -912,6 +912,30 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) } while (read_seqcount_retry(&vtime->seqcount, seq)); } +static int vtime_state_check(struct vtime *vtime, int cpu) +{ + /* + * We raced against a context switch, fetch the + * kcpustat task again. + */ + if (vtime->cpu != cpu && vtime->cpu != -1) + return -EAGAIN; + + /* + * Two possible things here: + * 1) We are seeing the scheduling out task (prev) or any past one. + * 2) We are seeing the scheduling in task (next) but it hasn't + * passed though vtime_task_switch() yet so the pending + * cputime of the prev task may not be flushed yet. + * + * Case 1) is ok but 2) is not. So wait for a safe VTIME state. + */ + if (vtime->state == VTIME_INACTIVE) + return -EAGAIN; + + return 0; +} + static u64 kcpustat_user_vtime(struct vtime *vtime) { if (vtime->state == VTIME_USER) @@ -933,26 +957,9 @@ static int kcpustat_field_vtime(u64 *cpustat, do { seq = read_seqcount_begin(&vtime->seqcount); - /* - * We raced against context switch, fetch the - * kcpustat task again. - */ - if (vtime->cpu != cpu && vtime->cpu != -1) - return -EAGAIN; - - /* - * Two possible things here: - * 1) We are seeing the scheduling out task (prev) or any past one. - * 2) We are seeing the scheduling in task (next) but it hasn't - * passed though vtime_task_switch() yet so the pending - * cputime of the prev task may not be flushed yet. - * - * Case 1) is ok but 2) is not. So wait for a safe VTIME state. - */ - if (vtime->state == VTIME_INACTIVE) - return -EAGAIN; - - err = 0; + err = vtime_state_check(vtime, cpu); + if (err < 0) + return err; *val = cpustat[usage]; @@ -1025,4 +1032,93 @@ u64 kcpustat_field(struct kernel_cpustat *kcpustat, } } EXPORT_SYMBOL_GPL(kcpustat_field); + +static int kcpustat_cpu_fetch_vtime(struct kernel_cpustat *dst, + const struct kernel_cpustat *src, + struct task_struct *tsk, int cpu) +{ + struct vtime *vtime = &tsk->vtime; + unsigned int seq; + int err; + + do { + u64 *cpustat; + u64 delta; + + seq = read_seqcount_begin(&vtime->seqcount); + + err = vtime_state_check(vtime, cpu); + if (err < 0) + return err; + + *dst = *src; + cpustat = dst->cpustat; + + /* Task is sleeping, dead or idle, nothing to add */ + if (vtime->state < VTIME_SYS) + continue; + + delta = vtime_delta(vtime); + + /* + * Task runs either in user (including guest) or kernel space, + * add pending nohz time to the right place. + */ + if (vtime->state == VTIME_SYS) { + cpustat[CPUTIME_SYSTEM] += vtime->stime + delta; + } else if (vtime->state == VTIME_USER) { + if (task_nice(tsk) > 0) + cpustat[CPUTIME_NICE] += vtime->utime + delta; + else + cpustat[CPUTIME_USER] += vtime->utime + delta; + } else { + WARN_ON_ONCE(vtime->state != VTIME_GUEST); + if (task_nice(tsk) > 0) { + cpustat[CPUTIME_GUEST_NICE] += vtime->gtime + delta; + cpustat[CPUTIME_NICE] += vtime->gtime + delta; + } else { + cpustat[CPUTIME_GUEST] += vtime->gtime + delta; + cpustat[CPUTIME_USER] += vtime->gtime + delta; + } + } + } while (read_seqcount_retry(&vtime->seqcount, seq)); + + return err; +} + +void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu) +{ + const struct kernel_cpustat *src = &kcpustat_cpu(cpu); + struct rq *rq; + int err; + + if (!vtime_accounting_enabled_cpu(cpu)) { + *dst = *src; + return; + } + + rq = cpu_rq(cpu); + + for (;;) { + struct task_struct *curr; + + rcu_read_lock(); + curr = rcu_dereference(rq->curr); + if (WARN_ON_ONCE(!curr)) { + rcu_read_unlock(); + *dst = *src; + return; + } + + err = kcpustat_cpu_fetch_vtime(dst, src, curr, cpu); + rcu_read_unlock(); + + if (!err) + return; + + cpu_relax(); + } +} +EXPORT_SYMBOL_GPL(kcpustat_cpu_fetch); + #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ -- cgit v1.2.3-71-gd317 From c9b465683a554212c3dd92915ed2088849c513bf Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Tue, 19 Nov 2019 13:45:45 +0100 Subject: platform/chrome: cros_ec: Put docs with the code To avoid doc rot, put function documentations with code, not header. Use kernel-doc style comments for exported functions. Signed-off-by: Gwendal Grignou Acked-by: Jonathan Cameron Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/cros_ec.c | 33 +++++++++ drivers/platform/chrome/cros_ec_proto.c | 70 +++++++++++++++++++ include/linux/platform_data/cros_ec_proto.h | 103 ---------------------------- 3 files changed, 103 insertions(+), 103 deletions(-) (limited to 'include/linux') diff --git a/drivers/platform/chrome/cros_ec.c b/drivers/platform/chrome/cros_ec.c index fd77e6fa74c2..9b2d07422e17 100644 --- a/drivers/platform/chrome/cros_ec.c +++ b/drivers/platform/chrome/cros_ec.c @@ -104,6 +104,15 @@ static int cros_ec_sleep_event(struct cros_ec_device *ec_dev, u8 sleep_event) return ret; } +/** + * cros_ec_register() - Register a new ChromeOS EC, using the provided info. + * @ec_dev: Device to register. + * + * Before calling this, allocate a pointer to a new device and then fill + * in all the fields up to the --private-- marker. + * + * Return: 0 on success or negative error code. + */ int cros_ec_register(struct cros_ec_device *ec_dev) { struct device *dev = ec_dev->dev; @@ -198,6 +207,14 @@ int cros_ec_register(struct cros_ec_device *ec_dev) } EXPORT_SYMBOL(cros_ec_register); +/** + * cros_ec_unregister() - Remove a ChromeOS EC. + * @ec_dev: Device to unregister. + * + * Call this to deregister a ChromeOS EC, then clean up any private data. + * + * Return: 0 on success or negative error code. + */ int cros_ec_unregister(struct cros_ec_device *ec_dev) { if (ec_dev->pd) @@ -209,6 +226,14 @@ int cros_ec_unregister(struct cros_ec_device *ec_dev) EXPORT_SYMBOL(cros_ec_unregister); #ifdef CONFIG_PM_SLEEP +/** + * cros_ec_suspend() - Handle a suspend operation for the ChromeOS EC device. + * @ec_dev: Device to suspend. + * + * This can be called by drivers to handle a suspend event. + * + * Return: 0 on success or negative error code. + */ int cros_ec_suspend(struct cros_ec_device *ec_dev) { struct device *dev = ec_dev->dev; @@ -243,6 +268,14 @@ static void cros_ec_report_events_during_suspend(struct cros_ec_device *ec_dev) 1, ec_dev); } +/** + * cros_ec_resume() - Handle a resume operation for the ChromeOS EC device. + * @ec_dev: Device to resume. + * + * This can be called by drivers to handle a resume event. + * + * Return: 0 on success or negative error code. + */ int cros_ec_resume(struct cros_ec_device *ec_dev) { int ret; diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index f659f96bda12..7db58771ec77 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -117,6 +117,17 @@ static int send_command(struct cros_ec_device *ec_dev, return ret; } +/** + * cros_ec_prepare_tx() - Prepare an outgoing message in the output buffer. + * @ec_dev: Device to register. + * @msg: Message to write. + * + * This is intended to be used by all ChromeOS EC drivers, but at present + * only SPI uses it. Once LPC uses the same protocol it can start using it. + * I2C could use it now, with a refactor of the existing code. + * + * Return: 0 on success or negative error code. + */ int cros_ec_prepare_tx(struct cros_ec_device *ec_dev, struct cros_ec_command *msg) { @@ -141,6 +152,16 @@ int cros_ec_prepare_tx(struct cros_ec_device *ec_dev, } EXPORT_SYMBOL(cros_ec_prepare_tx); +/** + * cros_ec_check_result() - Check ec_msg->result. + * @ec_dev: EC device. + * @msg: Message to check. + * + * This is used by ChromeOS EC drivers to check the ec_msg->result for + * errors and to warn about them. + * + * Return: 0 on success or negative error code. + */ int cros_ec_check_result(struct cros_ec_device *ec_dev, struct cros_ec_command *msg) { @@ -326,6 +347,13 @@ static int cros_ec_get_host_command_version_mask(struct cros_ec_device *ec_dev, return ret; } +/** + * cros_ec_query_all() - Query the protocol version supported by the + * ChromeOS EC. + * @ec_dev: Device to register. + * + * Return: 0 on success or negative error code. + */ int cros_ec_query_all(struct cros_ec_device *ec_dev) { struct device *dev = ec_dev->dev; @@ -453,6 +481,16 @@ exit: } EXPORT_SYMBOL(cros_ec_query_all); +/** + * cros_ec_cmd_xfer() - Send a command to the ChromeOS EC. + * @ec_dev: EC device. + * @msg: Message to write. + * + * Call this to send a command to the ChromeOS EC. This should be used + * instead of calling the EC's cmd_xfer() callback directly. + * + * Return: 0 on success or negative error code. + */ int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, struct cros_ec_command *msg) { @@ -500,6 +538,18 @@ int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, } EXPORT_SYMBOL(cros_ec_cmd_xfer); +/** + * cros_ec_cmd_xfer_status() - Send a command to the ChromeOS EC. + * @ec_dev: EC device. + * @msg: Message to write. + * + * This function is identical to cros_ec_cmd_xfer, except it returns success + * status only if both the command was transmitted successfully and the EC + * replied with success status. It's not necessary to check msg->result when + * using this function. + * + * Return: The number of bytes transferred on success or negative error code. + */ int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev, struct cros_ec_command *msg) { @@ -584,6 +634,16 @@ static int get_keyboard_state_event(struct cros_ec_device *ec_dev) return ec_dev->event_size; } +/** + * cros_ec_get_next_event() - Fetch next event from the ChromeOS EC. + * @ec_dev: Device to fetch event from. + * @wake_event: Pointer to a bool set to true upon return if the event might be + * treated as a wake event. Ignored if null. + * + * Return: negative error code on errors; 0 for no data; or else number of + * bytes received (i.e., an event was retrieved successfully). Event types are + * written out to @ec_dev->event_data.event_type on success. + */ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event) { u8 event_type; @@ -628,6 +688,16 @@ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event) } EXPORT_SYMBOL(cros_ec_get_next_event); +/** + * cros_ec_get_host_event() - Return a mask of event set by the ChromeOS EC. + * @ec_dev: Device to fetch event from. + * + * When MKBP is supported, when the EC raises an interrupt, we collect the + * events raised and call the functions in the ec notifier. This function + * is a helper to know which events are raised. + * + * Return: 0 on error or non-zero bitmask of one or more EC_HOST_EVENT_*. + */ u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev) { u32 host_event; diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index eab7036cda09..0d4e4aaed37a 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -187,133 +187,30 @@ struct cros_ec_platform { u16 cmd_offset; }; -/** - * cros_ec_suspend() - Handle a suspend operation for the ChromeOS EC device. - * @ec_dev: Device to suspend. - * - * This can be called by drivers to handle a suspend event. - * - * Return: 0 on success or negative error code. - */ int cros_ec_suspend(struct cros_ec_device *ec_dev); -/** - * cros_ec_resume() - Handle a resume operation for the ChromeOS EC device. - * @ec_dev: Device to resume. - * - * This can be called by drivers to handle a resume event. - * - * Return: 0 on success or negative error code. - */ int cros_ec_resume(struct cros_ec_device *ec_dev); -/** - * cros_ec_prepare_tx() - Prepare an outgoing message in the output buffer. - * @ec_dev: Device to register. - * @msg: Message to write. - * - * This is intended to be used by all ChromeOS EC drivers, but at present - * only SPI uses it. Once LPC uses the same protocol it can start using it. - * I2C could use it now, with a refactor of the existing code. - * - * Return: 0 on success or negative error code. - */ int cros_ec_prepare_tx(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); -/** - * cros_ec_check_result() - Check ec_msg->result. - * @ec_dev: EC device. - * @msg: Message to check. - * - * This is used by ChromeOS EC drivers to check the ec_msg->result for - * errors and to warn about them. - * - * Return: 0 on success or negative error code. - */ int cros_ec_check_result(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); -/** - * cros_ec_cmd_xfer() - Send a command to the ChromeOS EC. - * @ec_dev: EC device. - * @msg: Message to write. - * - * Call this to send a command to the ChromeOS EC. This should be used - * instead of calling the EC's cmd_xfer() callback directly. - * - * Return: 0 on success or negative error code. - */ int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); -/** - * cros_ec_cmd_xfer_status() - Send a command to the ChromeOS EC. - * @ec_dev: EC device. - * @msg: Message to write. - * - * This function is identical to cros_ec_cmd_xfer, except it returns success - * status only if both the command was transmitted successfully and the EC - * replied with success status. It's not necessary to check msg->result when - * using this function. - * - * Return: The number of bytes transferred on success or negative error code. - */ int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); -/** - * cros_ec_register() - Register a new ChromeOS EC, using the provided info. - * @ec_dev: Device to register. - * - * Before calling this, allocate a pointer to a new device and then fill - * in all the fields up to the --private-- marker. - * - * Return: 0 on success or negative error code. - */ int cros_ec_register(struct cros_ec_device *ec_dev); -/** - * cros_ec_unregister() - Remove a ChromeOS EC. - * @ec_dev: Device to unregister. - * - * Call this to deregister a ChromeOS EC, then clean up any private data. - * - * Return: 0 on success or negative error code. - */ int cros_ec_unregister(struct cros_ec_device *ec_dev); -/** - * cros_ec_query_all() - Query the protocol version supported by the - * ChromeOS EC. - * @ec_dev: Device to register. - * - * Return: 0 on success or negative error code. - */ int cros_ec_query_all(struct cros_ec_device *ec_dev); -/** - * cros_ec_get_next_event() - Fetch next event from the ChromeOS EC. - * @ec_dev: Device to fetch event from. - * @wake_event: Pointer to a bool set to true upon return if the event might be - * treated as a wake event. Ignored if null. - * - * Return: negative error code on errors; 0 for no data; or else number of - * bytes received (i.e., an event was retrieved successfully). Event types are - * written out to @ec_dev->event_data.event_type on success. - */ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event); -/** - * cros_ec_get_host_event() - Return a mask of event set by the ChromeOS EC. - * @ec_dev: Device to fetch event from. - * - * When MKBP is supported, when the EC raises an interrupt, we collect the - * events raised and call the functions in the ec notifier. This function - * is a helper to know which events are raised. - * - * Return: 0 on error or non-zero bitmask of one or more EC_HOST_EVENT_*. - */ u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev); #endif /* __LINUX_CROS_EC_PROTO_H */ -- cgit v1.2.3-71-gd317 From a16b2e28190255a0729c27902fa88fb8fff39bb0 Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Tue, 19 Nov 2019 13:45:45 +0100 Subject: mfd / platform: cros_ec: Add sensor_count and make check_features public Add a new function to return the number of MEMS sensors available in a ChromeOS Embedded Controller. It uses MOTIONSENSE_CMD_DUMP if available or a specific memory map ACPI registers to find out. Also, make check_features public as it can be useful for other drivers to know what the Embedded Controller supports. Signed-off-by: Gwendal Grignou Acked-by: Lee Jones Signed-off-by: Enric Balletbo i Serra --- drivers/mfd/cros_ec_dev.c | 32 -------- drivers/platform/chrome/cros_ec_proto.c | 117 ++++++++++++++++++++++++++++ include/linux/platform_data/cros_ec_proto.h | 5 ++ 3 files changed, 122 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/cros_ec_dev.c b/drivers/mfd/cros_ec_dev.c index 6e6dfd6c1871..a35104e35cb4 100644 --- a/drivers/mfd/cros_ec_dev.c +++ b/drivers/mfd/cros_ec_dev.c @@ -112,38 +112,6 @@ static const struct mfd_cell cros_ec_vbc_cells[] = { { .name = "cros-ec-vbc", } }; -static int cros_ec_check_features(struct cros_ec_dev *ec, int feature) -{ - struct cros_ec_command *msg; - int ret; - - if (ec->features[0] == -1U && ec->features[1] == -1U) { - /* features bitmap not read yet */ - msg = kzalloc(sizeof(*msg) + sizeof(ec->features), GFP_KERNEL); - if (!msg) - return -ENOMEM; - - msg->command = EC_CMD_GET_FEATURES + ec->cmd_offset; - msg->insize = sizeof(ec->features); - - ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); - if (ret < 0) { - dev_warn(ec->dev, "cannot get EC features: %d/%d\n", - ret, msg->result); - memset(ec->features, 0, sizeof(ec->features)); - } else { - memcpy(ec->features, msg->data, sizeof(ec->features)); - } - - dev_dbg(ec->dev, "EC features %08x %08x\n", - ec->features[0], ec->features[1]); - - kfree(msg); - } - - return ec->features[feature / 32] & EC_FEATURE_MASK_0(feature); -} - static void cros_ec_class_release(struct device *dev) { kfree(to_cros_ec_dev(dev)); diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index 7db58771ec77..12bdd1f3aee9 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -717,3 +717,120 @@ u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev) return host_event; } EXPORT_SYMBOL(cros_ec_get_host_event); + +/** + * cros_ec_check_features() - Test for the presence of EC features + * + * @ec: EC device, does not have to be connected directly to the AP, + * can be daisy chained through another device. + * @feature: One of ec_feature_code bit. + * + * Call this function to test whether the ChromeOS EC supports a feature. + * + * Return: 1 if supported, 0 if not + */ +int cros_ec_check_features(struct cros_ec_dev *ec, int feature) +{ + struct cros_ec_command *msg; + int ret; + + if (ec->features[0] == -1U && ec->features[1] == -1U) { + /* features bitmap not read yet */ + msg = kzalloc(sizeof(*msg) + sizeof(ec->features), GFP_KERNEL); + if (!msg) + return -ENOMEM; + + msg->command = EC_CMD_GET_FEATURES + ec->cmd_offset; + msg->insize = sizeof(ec->features); + + ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); + if (ret < 0) { + dev_warn(ec->dev, "cannot get EC features: %d/%d\n", + ret, msg->result); + memset(ec->features, 0, sizeof(ec->features)); + } else { + memcpy(ec->features, msg->data, sizeof(ec->features)); + } + + dev_dbg(ec->dev, "EC features %08x %08x\n", + ec->features[0], ec->features[1]); + + kfree(msg); + } + + return ec->features[feature / 32] & EC_FEATURE_MASK_0(feature); +} +EXPORT_SYMBOL_GPL(cros_ec_check_features); + +/** + * cros_ec_get_sensor_count() - Return the number of MEMS sensors supported. + * + * @ec: EC device, does not have to be connected directly to the AP, + * can be daisy chained through another device. + * Return: < 0 in case of error. + */ +int cros_ec_get_sensor_count(struct cros_ec_dev *ec) +{ + /* + * Issue a command to get the number of sensor reported. + * If not supported, check for legacy mode. + */ + int ret, sensor_count; + struct ec_params_motion_sense *params; + struct ec_response_motion_sense *resp; + struct cros_ec_command *msg; + struct cros_ec_device *ec_dev = ec->ec_dev; + u8 status; + + msg = kzalloc(sizeof(*msg) + max(sizeof(*params), sizeof(*resp)), + GFP_KERNEL); + if (!msg) + return -ENOMEM; + + msg->version = 1; + msg->command = EC_CMD_MOTION_SENSE_CMD + ec->cmd_offset; + msg->outsize = sizeof(*params); + msg->insize = sizeof(*resp); + + params = (struct ec_params_motion_sense *)msg->data; + params->cmd = MOTIONSENSE_CMD_DUMP; + + ret = cros_ec_cmd_xfer(ec->ec_dev, msg); + if (ret < 0) { + sensor_count = ret; + } else if (msg->result != EC_RES_SUCCESS) { + sensor_count = -EPROTO; + } else { + resp = (struct ec_response_motion_sense *)msg->data; + sensor_count = resp->dump.sensor_count; + } + kfree(msg); + + /* + * Check legacy mode: Let's find out if sensors are accessible + * via LPC interface. + */ + if (sensor_count == -EPROTO && + ec->cmd_offset == 0 && + ec_dev->cmd_readmem) { + ret = ec_dev->cmd_readmem(ec_dev, EC_MEMMAP_ACC_STATUS, + 1, &status); + if (ret >= 0 && + (status & EC_MEMMAP_ACC_STATUS_PRESENCE_BIT)) { + /* + * We have 2 sensors, one in the lid, one in the base. + */ + sensor_count = 2; + } else { + /* + * EC uses LPC interface and no sensors are presented. + */ + sensor_count = 0; + } + } else if (sensor_count == -EPROTO) { + /* EC responded, but does not understand DUMP command. */ + sensor_count = 0; + } + return sensor_count; +} +EXPORT_SYMBOL_GPL(cros_ec_get_sensor_count); diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index 0d4e4aaed37a..f3de0662135d 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -12,6 +12,7 @@ #include #include +#include #include #define CROS_EC_DEV_NAME "cros_ec" @@ -213,4 +214,8 @@ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event); u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev); +int cros_ec_check_features(struct cros_ec_dev *ec, int feature); + +int cros_ec_get_sensor_count(struct cros_ec_dev *ec); + #endif /* __LINUX_CROS_EC_PROTO_H */ -- cgit v1.2.3-71-gd317 From 53067471188c4066fc393ab892d0a74482eac000 Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Tue, 19 Nov 2019 13:45:45 +0100 Subject: iio / platform: cros_ec: Add cros-ec-sensorhub driver Similar to HID sensor stack, the new driver sits between cros-ec-dev and the IIO device drivers: The EC based IIO device topology would be: iio:device1 -> ...0/0000:00:1f.0/PNP0C09:00/GOOG0004:00/cros-ec-dev.6.auto/ cros-ec-sensorhub.7.auto/ cros-ec-accel.15.auto/ iio:device1 It will be expanded to control EC sensor FIFO. Signed-off-by: Gwendal Grignou Reviewed-by: Jonathan Cameron [Fix "unknown type name 'uint32_t'" type errors] Reported-by: kbuild test robot Signed-off-by: Enric Balletbo i Serra --- drivers/iio/common/cros_ec_sensors/Kconfig | 2 +- drivers/platform/chrome/Kconfig | 12 ++ drivers/platform/chrome/Makefile | 1 + drivers/platform/chrome/cros_ec_sensorhub.c | 199 ++++++++++++++++++++++++ include/linux/platform_data/cros_ec_sensorhub.h | 22 +++ 5 files changed, 235 insertions(+), 1 deletion(-) create mode 100644 drivers/platform/chrome/cros_ec_sensorhub.c create mode 100644 include/linux/platform_data/cros_ec_sensorhub.h (limited to 'include/linux') diff --git a/drivers/iio/common/cros_ec_sensors/Kconfig b/drivers/iio/common/cros_ec_sensors/Kconfig index cdbb29cfb907..fefad9572790 100644 --- a/drivers/iio/common/cros_ec_sensors/Kconfig +++ b/drivers/iio/common/cros_ec_sensors/Kconfig @@ -4,7 +4,7 @@ # config IIO_CROS_EC_SENSORS_CORE tristate "ChromeOS EC Sensors Core" - depends on SYSFS && CROS_EC + depends on SYSFS && CROS_EC_SENSORHUB select IIO_BUFFER select IIO_TRIGGERED_BUFFER help diff --git a/drivers/platform/chrome/Kconfig b/drivers/platform/chrome/Kconfig index ee5f08ea57b6..884ac9a287f2 100644 --- a/drivers/platform/chrome/Kconfig +++ b/drivers/platform/chrome/Kconfig @@ -190,6 +190,18 @@ config CROS_EC_DEBUGFS To compile this driver as a module, choose M here: the module will be called cros_ec_debugfs. +config CROS_EC_SENSORHUB + tristate "ChromeOS EC MEMS Sensor Hub" + depends on CROS_EC + help + Allow loading IIO sensors. This driver is loaded by MFD and will in + turn query the EC and register the sensors. + It also spreads the sensor data coming from the EC to the IIO sensor + object. + + To compile this driver as a module, choose M here: the + module will be called cros_ec_sensorhub. + config CROS_EC_SYSFS tristate "ChromeOS EC control and information through sysfs" depends on MFD_CROS_EC_DEV && SYSFS diff --git a/drivers/platform/chrome/Makefile b/drivers/platform/chrome/Makefile index 477ec3d1d1c9..aacd5920d8a1 100644 --- a/drivers/platform/chrome/Makefile +++ b/drivers/platform/chrome/Makefile @@ -19,6 +19,7 @@ obj-$(CONFIG_CROS_EC_CHARDEV) += cros_ec_chardev.o obj-$(CONFIG_CROS_EC_LIGHTBAR) += cros_ec_lightbar.o obj-$(CONFIG_CROS_EC_VBC) += cros_ec_vbc.o obj-$(CONFIG_CROS_EC_DEBUGFS) += cros_ec_debugfs.o +obj-$(CONFIG_CROS_EC_SENSORHUB) += cros_ec_sensorhub.o obj-$(CONFIG_CROS_EC_SYSFS) += cros_ec_sysfs.o obj-$(CONFIG_CROS_USBPD_LOGGER) += cros_usbpd_logger.o diff --git a/drivers/platform/chrome/cros_ec_sensorhub.c b/drivers/platform/chrome/cros_ec_sensorhub.c new file mode 100644 index 000000000000..04d8879689e9 --- /dev/null +++ b/drivers/platform/chrome/cros_ec_sensorhub.c @@ -0,0 +1,199 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Sensor HUB driver that discovers sensors behind a ChromeOS Embedded + * Controller. + * + * Copyright 2019 Google LLC + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define DRV_NAME "cros-ec-sensorhub" + +static void cros_ec_sensorhub_free_sensor(void *arg) +{ + struct platform_device *pdev = arg; + + platform_device_unregister(pdev); +} + +static int cros_ec_sensorhub_allocate_sensor(struct device *parent, + char *sensor_name, + int sensor_num) +{ + struct cros_ec_sensor_platform sensor_platforms = { + .sensor_num = sensor_num, + }; + struct platform_device *pdev; + + pdev = platform_device_register_data(parent, sensor_name, + PLATFORM_DEVID_AUTO, + &sensor_platforms, + sizeof(sensor_platforms)); + if (IS_ERR(pdev)) + return PTR_ERR(pdev); + + return devm_add_action_or_reset(parent, + cros_ec_sensorhub_free_sensor, + pdev); +} + +static int cros_ec_sensorhub_register(struct device *dev, + struct cros_ec_sensorhub *sensorhub) +{ + int sensor_type[MOTIONSENSE_TYPE_MAX] = { 0 }; + struct cros_ec_dev *ec = sensorhub->ec; + struct ec_params_motion_sense *params; + struct ec_response_motion_sense *resp; + struct cros_ec_command *msg; + int ret, i, sensor_num; + char *name; + + sensor_num = cros_ec_get_sensor_count(ec); + if (sensor_num < 0) { + dev_err(dev, + "Unable to retrieve sensor information (err:%d)\n", + sensor_num); + return sensor_num; + } + + if (sensor_num == 0) { + dev_err(dev, "Zero sensors reported.\n"); + return -EINVAL; + } + + /* Prepare a message to send INFO command to each sensor. */ + msg = kzalloc(sizeof(*msg) + max(sizeof(*params), sizeof(*resp)), + GFP_KERNEL); + if (!msg) + return -ENOMEM; + + msg->version = 1; + msg->command = EC_CMD_MOTION_SENSE_CMD + ec->cmd_offset; + msg->outsize = sizeof(*params); + msg->insize = sizeof(*resp); + params = (struct ec_params_motion_sense *)msg->data; + resp = (struct ec_response_motion_sense *)msg->data; + + for (i = 0; i < sensor_num; i++) { + params->cmd = MOTIONSENSE_CMD_INFO; + params->info.sensor_num = i; + + ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); + if (ret < 0) { + dev_warn(dev, "no info for EC sensor %d : %d/%d\n", + i, ret, msg->result); + continue; + } + + switch (resp->info.type) { + case MOTIONSENSE_TYPE_ACCEL: + name = "cros-ec-accel"; + break; + case MOTIONSENSE_TYPE_BARO: + name = "cros-ec-baro"; + break; + case MOTIONSENSE_TYPE_GYRO: + name = "cros-ec-gyro"; + break; + case MOTIONSENSE_TYPE_MAG: + name = "cros-ec-mag"; + break; + case MOTIONSENSE_TYPE_PROX: + name = "cros-ec-prox"; + break; + case MOTIONSENSE_TYPE_LIGHT: + name = "cros-ec-light"; + break; + case MOTIONSENSE_TYPE_ACTIVITY: + name = "cros-ec-activity"; + break; + default: + dev_warn(dev, "unknown type %d\n", resp->info.type); + continue; + } + + ret = cros_ec_sensorhub_allocate_sensor(dev, name, i); + if (ret) + goto error; + + sensor_type[resp->info.type]++; + } + + if (sensor_type[MOTIONSENSE_TYPE_ACCEL] >= 2) + ec->has_kb_wake_angle = true; + + if (cros_ec_check_features(ec, + EC_FEATURE_REFINED_TABLET_MODE_HYSTERESIS)) { + ret = cros_ec_sensorhub_allocate_sensor(dev, + "cros-ec-lid-angle", + 0); + if (ret) + goto error; + } + + kfree(msg); + return 0; + +error: + kfree(msg); + return ret; +} + +static int cros_ec_sensorhub_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct cros_ec_sensorhub *data; + int ret; + int i; + + data = devm_kzalloc(dev, sizeof(struct cros_ec_sensorhub), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->ec = dev_get_drvdata(dev->parent); + dev_set_drvdata(dev, data); + + /* Check whether this EC is a sensor hub. */ + if (cros_ec_check_features(data->ec, EC_FEATURE_MOTION_SENSE)) { + ret = cros_ec_sensorhub_register(dev, data); + if (ret) + return ret; + } else { + /* + * If the device has sensors but does not claim to + * be a sensor hub, we are in legacy mode. + */ + for (i = 0; i < 2; i++) { + ret = cros_ec_sensorhub_allocate_sensor(dev, + "cros-ec-accel-legacy", i); + if (ret) + return ret; + } + } + + return 0; +} + +static struct platform_driver cros_ec_sensorhub_driver = { + .driver = { + .name = DRV_NAME, + }, + .probe = cros_ec_sensorhub_probe, +}; + +module_platform_driver(cros_ec_sensorhub_driver); + +MODULE_ALIAS("platform:" DRV_NAME); +MODULE_AUTHOR("Gwendal Grignou "); +MODULE_DESCRIPTION("ChromeOS EC MEMS Sensor Hub Driver"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/platform_data/cros_ec_sensorhub.h b/include/linux/platform_data/cros_ec_sensorhub.h new file mode 100644 index 000000000000..5f6f9bb65079 --- /dev/null +++ b/include/linux/platform_data/cros_ec_sensorhub.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Chrome OS EC MEMS Sensor Hub driver. + * + * Copyright 2019 Google LLC + */ + +#ifndef __LINUX_PLATFORM_DATA_CROS_EC_SENSORHUB_H +#define __LINUX_PLATFORM_DATA_CROS_EC_SENSORHUB_H + +#include + +/** + * struct cros_ec_sensorhub - Sensor Hub device data. + * + * @ec: Embedded Controller where the hub is located. + */ +struct cros_ec_sensorhub { + struct cros_ec_dev *ec; +}; + +#endif /* __LINUX_PLATFORM_DATA_CROS_EC_SENSORHUB_H */ -- cgit v1.2.3-71-gd317 From d60ac88a62df71cb12b2d60d2dae5658fb4eab43 Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Tue, 19 Nov 2019 13:45:45 +0100 Subject: mfd / platform / iio: cros_ec: Register sensor through sensorhub Remove the duplicated code in MFD, since MFD just registers cros-ec-sensorhub if at least one sensor is present. Change IIO cros-ec driver to get the pointer to the cros-ec-dev through cros-ec-sensorhub. Signed-off-by: Gwendal Grignou Acked-by: Jonathan Cameron Acked-by: Lee Jones Signed-off-by: Enric Balletbo i Serra --- drivers/iio/accel/cros_ec_accel_legacy.c | 6 - .../iio/common/cros_ec_sensors/cros_ec_sensors.c | 6 - .../common/cros_ec_sensors/cros_ec_sensors_core.c | 4 +- drivers/iio/light/cros_ec_light_prox.c | 6 - drivers/mfd/cros_ec_dev.c | 203 ++------------------- include/linux/platform_data/cros_ec_proto.h | 8 - include/linux/platform_data/cros_ec_sensorhub.h | 8 + 7 files changed, 23 insertions(+), 218 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/accel/cros_ec_accel_legacy.c b/drivers/iio/accel/cros_ec_accel_legacy.c index fcc3f999e482..65f85faf6f31 100644 --- a/drivers/iio/accel/cros_ec_accel_legacy.c +++ b/drivers/iio/accel/cros_ec_accel_legacy.c @@ -163,16 +163,10 @@ static const struct iio_chan_spec cros_ec_accel_legacy_channels[] = { static int cros_ec_accel_legacy_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct cros_ec_dev *ec = dev_get_drvdata(dev->parent); struct iio_dev *indio_dev; struct cros_ec_sensors_core_state *state; int ret; - if (!ec || !ec->ec_dev) { - dev_warn(&pdev->dev, "No EC device found.\n"); - return -EINVAL; - } - indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*state)); if (!indio_dev) return -ENOMEM; diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c index a6987726eeb8..7dce04473467 100644 --- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c +++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c @@ -222,17 +222,11 @@ static const struct iio_info ec_sensors_info = { static int cros_ec_sensors_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct cros_ec_dev *ec_dev = dev_get_drvdata(dev->parent); struct iio_dev *indio_dev; struct cros_ec_sensors_state *state; struct iio_chan_spec *channel; int ret, i; - if (!ec_dev || !ec_dev->ec_dev) { - dev_warn(&pdev->dev, "No CROS EC device found.\n"); - return -EINVAL; - } - indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*state)); if (!indio_dev) return -ENOMEM; diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c index d2609e6feda4..81a7f692de2f 100644 --- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c +++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c @@ -18,6 +18,7 @@ #include #include #include +#include #include static char *cros_ec_loc[] = { @@ -88,7 +89,8 @@ int cros_ec_sensors_core_init(struct platform_device *pdev, { struct device *dev = &pdev->dev; struct cros_ec_sensors_core_state *state = iio_priv(indio_dev); - struct cros_ec_dev *ec = dev_get_drvdata(pdev->dev.parent); + struct cros_ec_sensorhub *sensor_hub = dev_get_drvdata(dev->parent); + struct cros_ec_dev *ec = sensor_hub->ec; struct cros_ec_sensor_platform *sensor_platform = dev_get_platdata(dev); u32 ver_mask; int ret, i; diff --git a/drivers/iio/light/cros_ec_light_prox.c b/drivers/iio/light/cros_ec_light_prox.c index c5263b563fc1..d85a391e50c5 100644 --- a/drivers/iio/light/cros_ec_light_prox.c +++ b/drivers/iio/light/cros_ec_light_prox.c @@ -169,17 +169,11 @@ static const struct iio_info cros_ec_light_prox_info = { static int cros_ec_light_prox_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct cros_ec_dev *ec_dev = dev_get_drvdata(dev->parent); struct iio_dev *indio_dev; struct cros_ec_light_prox_state *state; struct iio_chan_spec *channel; int ret; - if (!ec_dev || !ec_dev->ec_dev) { - dev_warn(dev, "No CROS EC device found.\n"); - return -EINVAL; - } - indio_dev = devm_iio_device_alloc(dev, sizeof(*state)); if (!indio_dev) return -ENOMEM; diff --git a/drivers/mfd/cros_ec_dev.c b/drivers/mfd/cros_ec_dev.c index a35104e35cb4..c4b977a5dd96 100644 --- a/drivers/mfd/cros_ec_dev.c +++ b/drivers/mfd/cros_ec_dev.c @@ -78,6 +78,10 @@ static const struct mfd_cell cros_ec_rtc_cells[] = { { .name = "cros-ec-rtc", }, }; +static const struct mfd_cell cros_ec_sensorhub_cells[] = { + { .name = "cros-ec-sensorhub", }, +}; + static const struct mfd_cell cros_usbpd_charger_cells[] = { { .name = "cros-usbpd-charger", }, { .name = "cros-usbpd-logger", }, @@ -117,192 +121,6 @@ static void cros_ec_class_release(struct device *dev) kfree(to_cros_ec_dev(dev)); } -static void cros_ec_sensors_register(struct cros_ec_dev *ec) -{ - /* - * Issue a command to get the number of sensor reported. - * Build an array of sensors driver and register them all. - */ - int ret, i, id, sensor_num; - struct mfd_cell *sensor_cells; - struct cros_ec_sensor_platform *sensor_platforms; - int sensor_type[MOTIONSENSE_TYPE_MAX]; - struct ec_params_motion_sense *params; - struct ec_response_motion_sense *resp; - struct cros_ec_command *msg; - - msg = kzalloc(sizeof(struct cros_ec_command) + - max(sizeof(*params), sizeof(*resp)), GFP_KERNEL); - if (msg == NULL) - return; - - msg->version = 2; - msg->command = EC_CMD_MOTION_SENSE_CMD + ec->cmd_offset; - msg->outsize = sizeof(*params); - msg->insize = sizeof(*resp); - - params = (struct ec_params_motion_sense *)msg->data; - params->cmd = MOTIONSENSE_CMD_DUMP; - - ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); - if (ret < 0) { - dev_warn(ec->dev, "cannot get EC sensor information: %d/%d\n", - ret, msg->result); - goto error; - } - - resp = (struct ec_response_motion_sense *)msg->data; - sensor_num = resp->dump.sensor_count; - /* - * Allocate 2 extra sensors if lid angle sensor and/or FIFO are needed. - */ - sensor_cells = kcalloc(sensor_num + 2, sizeof(struct mfd_cell), - GFP_KERNEL); - if (sensor_cells == NULL) - goto error; - - sensor_platforms = kcalloc(sensor_num, - sizeof(struct cros_ec_sensor_platform), - GFP_KERNEL); - if (sensor_platforms == NULL) - goto error_platforms; - - memset(sensor_type, 0, sizeof(sensor_type)); - id = 0; - for (i = 0; i < sensor_num; i++) { - params->cmd = MOTIONSENSE_CMD_INFO; - params->info.sensor_num = i; - ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); - if (ret < 0) { - dev_warn(ec->dev, "no info for EC sensor %d : %d/%d\n", - i, ret, msg->result); - continue; - } - switch (resp->info.type) { - case MOTIONSENSE_TYPE_ACCEL: - sensor_cells[id].name = "cros-ec-accel"; - break; - case MOTIONSENSE_TYPE_BARO: - sensor_cells[id].name = "cros-ec-baro"; - break; - case MOTIONSENSE_TYPE_GYRO: - sensor_cells[id].name = "cros-ec-gyro"; - break; - case MOTIONSENSE_TYPE_MAG: - sensor_cells[id].name = "cros-ec-mag"; - break; - case MOTIONSENSE_TYPE_PROX: - sensor_cells[id].name = "cros-ec-prox"; - break; - case MOTIONSENSE_TYPE_LIGHT: - sensor_cells[id].name = "cros-ec-light"; - break; - case MOTIONSENSE_TYPE_ACTIVITY: - sensor_cells[id].name = "cros-ec-activity"; - break; - default: - dev_warn(ec->dev, "unknown type %d\n", resp->info.type); - continue; - } - sensor_platforms[id].sensor_num = i; - sensor_cells[id].id = sensor_type[resp->info.type]; - sensor_cells[id].platform_data = &sensor_platforms[id]; - sensor_cells[id].pdata_size = - sizeof(struct cros_ec_sensor_platform); - - sensor_type[resp->info.type]++; - id++; - } - - if (sensor_type[MOTIONSENSE_TYPE_ACCEL] >= 2) - ec->has_kb_wake_angle = true; - - if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE_FIFO)) { - sensor_cells[id].name = "cros-ec-ring"; - id++; - } - if (cros_ec_check_features(ec, - EC_FEATURE_REFINED_TABLET_MODE_HYSTERESIS)) { - sensor_cells[id].name = "cros-ec-lid-angle"; - id++; - } - - ret = mfd_add_devices(ec->dev, 0, sensor_cells, id, - NULL, 0, NULL); - if (ret) - dev_err(ec->dev, "failed to add EC sensors\n"); - - kfree(sensor_platforms); -error_platforms: - kfree(sensor_cells); -error: - kfree(msg); -} - -static struct cros_ec_sensor_platform sensor_platforms[] = { - { .sensor_num = 0 }, - { .sensor_num = 1 } -}; - -static const struct mfd_cell cros_ec_accel_legacy_cells[] = { - { - .name = "cros-ec-accel-legacy", - .platform_data = &sensor_platforms[0], - .pdata_size = sizeof(struct cros_ec_sensor_platform), - }, - { - .name = "cros-ec-accel-legacy", - .platform_data = &sensor_platforms[1], - .pdata_size = sizeof(struct cros_ec_sensor_platform), - } -}; - -static void cros_ec_accel_legacy_register(struct cros_ec_dev *ec) -{ - struct cros_ec_device *ec_dev = ec->ec_dev; - u8 status; - int ret; - - /* - * ECs that need legacy support are the main EC, directly connected to - * the AP. - */ - if (ec->cmd_offset != 0) - return; - - /* - * Check if EC supports direct memory reads and if EC has - * accelerometers. - */ - if (ec_dev->cmd_readmem) { - ret = ec_dev->cmd_readmem(ec_dev, EC_MEMMAP_ACC_STATUS, 1, - &status); - if (ret < 0) { - dev_warn(ec->dev, "EC direct read error.\n"); - return; - } - - /* Check if EC has accelerometers. */ - if (!(status & EC_MEMMAP_ACC_STATUS_PRESENCE_BIT)) { - dev_info(ec->dev, "EC does not have accelerometers.\n"); - return; - } - } - - /* - * The device may still support accelerometers: - * it would be an older ARM based device that do not suppor the - * EC_CMD_GET_FEATURES command. - * - * Register 2 accelerometers, we will fail in the IIO driver if there - * are no sensors. - */ - ret = mfd_add_hotplug_devices(ec->dev, cros_ec_accel_legacy_cells, - ARRAY_SIZE(cros_ec_accel_legacy_cells)); - if (ret) - dev_err(ec_dev->dev, "failed to add EC sensors\n"); -} - static int ec_device_probe(struct platform_device *pdev) { int retval = -ENOMEM; @@ -358,11 +176,14 @@ static int ec_device_probe(struct platform_device *pdev) goto failed; /* check whether this EC is a sensor hub. */ - if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE)) - cros_ec_sensors_register(ec); - else - /* Workaroud for older EC firmware */ - cros_ec_accel_legacy_register(ec); + if (cros_ec_get_sensor_count(ec) > 0) { + retval = mfd_add_hotplug_devices(ec->dev, + cros_ec_sensorhub_cells, + ARRAY_SIZE(cros_ec_sensorhub_cells)); + if (retval) + dev_err(ec->dev, "failed to add %s subdevice: %d\n", + cros_ec_sensorhub_cells->name, retval); + } /* * The following subdevices can be detected by sending the diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index f3de0662135d..691f9e953a96 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -168,14 +168,6 @@ struct cros_ec_device { struct platform_device *pd; }; -/** - * struct cros_ec_sensor_platform - ChromeOS EC sensor platform information. - * @sensor_num: Id of the sensor, as reported by the EC. - */ -struct cros_ec_sensor_platform { - u8 sensor_num; -}; - /** * struct cros_ec_platform - ChromeOS EC platform information. * @ec_name: Name of EC device (e.g. 'cros-ec', 'cros-pd', ...) diff --git a/include/linux/platform_data/cros_ec_sensorhub.h b/include/linux/platform_data/cros_ec_sensorhub.h index 5f6f9bb65079..bef7ffc7fce1 100644 --- a/include/linux/platform_data/cros_ec_sensorhub.h +++ b/include/linux/platform_data/cros_ec_sensorhub.h @@ -10,6 +10,14 @@ #include +/** + * struct cros_ec_sensor_platform - ChromeOS EC sensor platform information. + * @sensor_num: Id of the sensor, as reported by the EC. + */ +struct cros_ec_sensor_platform { + u8 sensor_num; +}; + /** * struct cros_ec_sensorhub - Sensor Hub device data. * -- cgit v1.2.3-71-gd317 From 05a3c420eaa6857cb20afe7e3a3c39ed94a3b2c1 Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Tue, 19 Nov 2019 13:45:46 +0100 Subject: platform/chrome: cros-ec: Record event timestamp in the hard irq To improve sensor timestamp precision, given EC and AP are in different time domains, the AP needs to try to record the exact moment an event was signalled to the AP by the EC as soon as possible after it happens. First thing in the hard irq is the best place for this. Signed-off-by: Gwendal Grignou Acked-by: Jonathan Cameron Acked-by: Lee Jones Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/cros_ec.c | 17 ++++++++++++++--- drivers/platform/chrome/cros_ec_ishtp.c | 17 +++++++++++++++-- drivers/platform/chrome/cros_ec_lpc.c | 2 ++ include/linux/platform_data/cros_ec_proto.h | 16 ++++++++++++++++ 4 files changed, 47 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/platform/chrome/cros_ec.c b/drivers/platform/chrome/cros_ec.c index 9b2d07422e17..925f84dbf621 100644 --- a/drivers/platform/chrome/cros_ec.c +++ b/drivers/platform/chrome/cros_ec.c @@ -31,6 +31,15 @@ static struct cros_ec_platform pd_p = { .cmd_offset = EC_CMD_PASSTHRU_OFFSET(CROS_EC_DEV_PD_INDEX), }; +static irqreturn_t ec_irq_handler(int irq, void *data) +{ + struct cros_ec_device *ec_dev = data; + + ec_dev->last_event_time = cros_ec_get_time_ns(); + + return IRQ_WAKE_THREAD; +} + static irqreturn_t ec_irq_thread(int irq, void *data) { struct cros_ec_device *ec_dev = data; @@ -141,9 +150,11 @@ int cros_ec_register(struct cros_ec_device *ec_dev) } if (ec_dev->irq) { - err = devm_request_threaded_irq(dev, ec_dev->irq, NULL, - ec_irq_thread, IRQF_TRIGGER_LOW | IRQF_ONESHOT, - "chromeos-ec", ec_dev); + err = devm_request_threaded_irq(dev, ec_dev->irq, + ec_irq_handler, + ec_irq_thread, + IRQF_TRIGGER_LOW | IRQF_ONESHOT, + "chromeos-ec", ec_dev); if (err) { dev_err(dev, "Failed to request IRQ %d: %d", ec_dev->irq, err); diff --git a/drivers/platform/chrome/cros_ec_ishtp.c b/drivers/platform/chrome/cros_ec_ishtp.c index 25ca2c894b4d..5c848f22b44b 100644 --- a/drivers/platform/chrome/cros_ec_ishtp.c +++ b/drivers/platform/chrome/cros_ec_ishtp.c @@ -200,13 +200,14 @@ static int ish_send(struct ishtp_cl_data *client_data, * process_recv() - Received and parse incoming packet * @cros_ish_cl: Client instance to get stats * @rb_in_proc: Host interface message buffer + * @timestamp: Timestamp of when parent callback started * * Parse the incoming packet. If it is a response packet then it will * update per instance flags and wake up the caller waiting to for the * response. If it is an event packet then it will schedule event work. */ static void process_recv(struct ishtp_cl *cros_ish_cl, - struct ishtp_cl_rb *rb_in_proc) + struct ishtp_cl_rb *rb_in_proc, ktime_t timestamp) { size_t data_len = rb_in_proc->buf_idx; struct ishtp_cl_data *client_data = @@ -295,6 +296,11 @@ error_wake_up: break; case CROS_MKBP_EVENT: + /* + * Set timestamp from beginning of function since we actually + * got an incoming MKBP event + */ + client_data->ec_dev->last_event_time = timestamp; /* The event system doesn't send any data in buffer */ schedule_work(&client_data->work_ec_evt); @@ -322,10 +328,17 @@ static void ish_event_cb(struct ishtp_cl_device *cl_device) { struct ishtp_cl_rb *rb_in_proc; struct ishtp_cl *cros_ish_cl = ishtp_get_drvdata(cl_device); + ktime_t timestamp; + + /* + * Take timestamp as close to hardware interrupt as possible for sensor + * timestamps. + */ + timestamp = cros_ec_get_time_ns(); while ((rb_in_proc = ishtp_cl_rx_get_rb(cros_ish_cl)) != NULL) { /* Decide what to do with received data */ - process_recv(cros_ish_cl, rb_in_proc); + process_recv(cros_ish_cl, rb_in_proc, timestamp); } } diff --git a/drivers/platform/chrome/cros_ec_lpc.c b/drivers/platform/chrome/cros_ec_lpc.c index 7d10d909435f..3c77496e164d 100644 --- a/drivers/platform/chrome/cros_ec_lpc.c +++ b/drivers/platform/chrome/cros_ec_lpc.c @@ -313,6 +313,8 @@ static void cros_ec_lpc_acpi_notify(acpi_handle device, u32 value, void *data) { struct cros_ec_device *ec_dev = data; + ec_dev->last_event_time = cros_ec_get_time_ns(); + if (ec_dev->mkbp_event_supported && cros_ec_get_next_event(ec_dev, NULL) > 0) blocking_notifier_call_chain(&ec_dev->event_notifier, 0, diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index 691f9e953a96..02dc34f366d7 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -122,6 +122,8 @@ struct cros_ec_command { * @event_data: Raw payload transferred with the MKBP event. * @event_size: Size in bytes of the event data. * @host_event_wake_mask: Mask of host events that cause wake from suspend. + * @last_event_time: exact time from the hard irq when we got notified of + * a new event. * @ec: The platform_device used by the mfd driver to interface with the * main EC. * @pd: The platform_device used by the mfd driver to interface with the @@ -162,6 +164,7 @@ struct cros_ec_device { int event_size; u32 host_event_wake_mask; u32 last_resume_result; + ktime_t last_event_time; /* The platform devices used by the mfd driver */ struct platform_device *ec; @@ -210,4 +213,17 @@ int cros_ec_check_features(struct cros_ec_dev *ec, int feature); int cros_ec_get_sensor_count(struct cros_ec_dev *ec); +/** + * cros_ec_get_time_ns() - Return time in ns. + * + * This is the function used to record the time for last_event_time in struct + * cros_ec_device during the hard irq. + * + * Return: ktime_t format since boot. + */ +static inline ktime_t cros_ec_get_time_ns(void) +{ + return ktime_get_boottime_ns(); +} + #endif /* __LINUX_CROS_EC_PROTO_H */ -- cgit v1.2.3-71-gd317 From 3300fdd630d4d3d96e3ba9af63a740d3a4e8fc61 Mon Sep 17 00:00:00 2001 From: Enrico Granata Date: Tue, 19 Nov 2019 13:45:46 +0100 Subject: platform/chrome: cros_ec: handle MKBP more events flag The ChromeOS EC has support for signaling to the host that a single IRQ can serve multiple MKBP (Matrix KeyBoard Protocol) events. Doing this serves an optimization purpose, as it minimizes the number of round-trips into the interrupt handling machinery, and it proves beneficial to sensor timestamping as it keeps the desired synchronization of event times between the two processors. This patch adds kernel support for this EC feature, allowing the ec_irq to loop until all events have been served. Signed-off-by: Enrico Granata Signed-off-by: Gwendal Grignou Reviewed-by: Jonathan Cameron Acked-by: Lee Jones Signed-off-by: Enric Balletbo i Serra --- drivers/platform/chrome/cros_ec.c | 34 ++++++++++-- drivers/platform/chrome/cros_ec_ishtp.c | 8 +-- drivers/platform/chrome/cros_ec_lpc.c | 15 ++++-- drivers/platform/chrome/cros_ec_proto.c | 80 ++++++++++++++++++----------- drivers/platform/chrome/cros_ec_rpmsg.c | 19 ++----- include/linux/platform_data/cros_ec_proto.h | 12 +++-- 6 files changed, 107 insertions(+), 61 deletions(-) (limited to 'include/linux') diff --git a/drivers/platform/chrome/cros_ec.c b/drivers/platform/chrome/cros_ec.c index d3dfa27171e6..6d6ce86a1408 100644 --- a/drivers/platform/chrome/cros_ec.c +++ b/drivers/platform/chrome/cros_ec.c @@ -40,13 +40,23 @@ static irqreturn_t ec_irq_handler(int irq, void *data) return IRQ_WAKE_THREAD; } -static irqreturn_t ec_irq_thread(int irq, void *data) +/** + * cros_ec_handle_event() - process and forward pending events on EC + * @ec_dev: Device with events to process. + * + * Call this function in a loop when the kernel is notified that the EC has + * pending events. + * + * Return: true if more events are still pending and this function should be + * called again. + */ +bool cros_ec_handle_event(struct cros_ec_device *ec_dev) { - struct cros_ec_device *ec_dev = data; - bool wake_event = true; + bool wake_event; + bool ec_has_more_events; int ret; - ret = cros_ec_get_next_event(ec_dev, &wake_event); + ret = cros_ec_get_next_event(ec_dev, &wake_event, &ec_has_more_events); /* * Signal only if wake host events or any interrupt if @@ -59,6 +69,20 @@ static irqreturn_t ec_irq_thread(int irq, void *data) if (ret > 0) blocking_notifier_call_chain(&ec_dev->event_notifier, 0, ec_dev); + + return ec_has_more_events; +} +EXPORT_SYMBOL(cros_ec_handle_event); + +static irqreturn_t ec_irq_thread(int irq, void *data) +{ + struct cros_ec_device *ec_dev = data; + bool ec_has_more_events; + + do { + ec_has_more_events = cros_ec_handle_event(ec_dev); + } while (ec_has_more_events); + return IRQ_HANDLED; } @@ -274,7 +298,7 @@ EXPORT_SYMBOL(cros_ec_suspend); static void cros_ec_report_events_during_suspend(struct cros_ec_device *ec_dev) { while (ec_dev->mkbp_event_supported && - cros_ec_get_next_event(ec_dev, NULL) > 0) + cros_ec_get_next_event(ec_dev, NULL, NULL) > 0) blocking_notifier_call_chain(&ec_dev->event_notifier, 1, ec_dev); } diff --git a/drivers/platform/chrome/cros_ec_ishtp.c b/drivers/platform/chrome/cros_ec_ishtp.c index 5c848f22b44b..e5996821d08b 100644 --- a/drivers/platform/chrome/cros_ec_ishtp.c +++ b/drivers/platform/chrome/cros_ec_ishtp.c @@ -136,11 +136,11 @@ static void ish_evt_handler(struct work_struct *work) struct ishtp_cl_data *client_data = container_of(work, struct ishtp_cl_data, work_ec_evt); struct cros_ec_device *ec_dev = client_data->ec_dev; + bool ec_has_more_events; - if (cros_ec_get_next_event(ec_dev, NULL) > 0) { - blocking_notifier_call_chain(&ec_dev->event_notifier, - 0, ec_dev); - } + do { + ec_has_more_events = cros_ec_handle_event(ec_dev); + } while (ec_has_more_events); } /** diff --git a/drivers/platform/chrome/cros_ec_lpc.c b/drivers/platform/chrome/cros_ec_lpc.c index 3c77496e164d..dccf479c6625 100644 --- a/drivers/platform/chrome/cros_ec_lpc.c +++ b/drivers/platform/chrome/cros_ec_lpc.c @@ -312,13 +312,20 @@ static int cros_ec_lpc_readmem(struct cros_ec_device *ec, unsigned int offset, static void cros_ec_lpc_acpi_notify(acpi_handle device, u32 value, void *data) { struct cros_ec_device *ec_dev = data; + bool ec_has_more_events; + int ret; ec_dev->last_event_time = cros_ec_get_time_ns(); - if (ec_dev->mkbp_event_supported && - cros_ec_get_next_event(ec_dev, NULL) > 0) - blocking_notifier_call_chain(&ec_dev->event_notifier, 0, - ec_dev); + if (ec_dev->mkbp_event_supported) + do { + ret = cros_ec_get_next_event(ec_dev, NULL, + &ec_has_more_events); + if (ret > 0) + blocking_notifier_call_chain( + &ec_dev->event_notifier, 0, + ec_dev); + } while (ec_has_more_events); if (value == ACPI_NOTIFY_DEVICE_WAKE) pm_system_wakeup(); diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index 12bdd1f3aee9..da1b1c450433 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -456,7 +456,10 @@ int cros_ec_query_all(struct cros_ec_device *ec_dev) if (ret < 0 || ver_mask == 0) ec_dev->mkbp_event_supported = 0; else - ec_dev->mkbp_event_supported = 1; + ec_dev->mkbp_event_supported = fls(ver_mask); + + dev_dbg(ec_dev->dev, "MKBP support version %u\n", + ec_dev->mkbp_event_supported - 1); /* Probe if host sleep v1 is supported for S0ix failure detection. */ ret = cros_ec_get_host_command_version_mask(ec_dev, @@ -569,6 +572,7 @@ EXPORT_SYMBOL(cros_ec_cmd_xfer_status); static int get_next_event_xfer(struct cros_ec_device *ec_dev, struct cros_ec_command *msg, + struct ec_response_get_next_event_v1 *event, int version, uint32_t size) { int ret; @@ -581,7 +585,7 @@ static int get_next_event_xfer(struct cros_ec_device *ec_dev, ret = cros_ec_cmd_xfer(ec_dev, msg); if (ret > 0) { ec_dev->event_size = ret - 1; - memcpy(&ec_dev->event_data, msg->data, ret); + ec_dev->event_data = *event; } return ret; @@ -589,30 +593,26 @@ static int get_next_event_xfer(struct cros_ec_device *ec_dev, static int get_next_event(struct cros_ec_device *ec_dev) { - u8 buffer[sizeof(struct cros_ec_command) + sizeof(ec_dev->event_data)]; - struct cros_ec_command *msg = (struct cros_ec_command *)&buffer; - static int cmd_version = 1; - int ret; + struct { + struct cros_ec_command msg; + struct ec_response_get_next_event_v1 event; + } __packed buf; + struct cros_ec_command *msg = &buf.msg; + struct ec_response_get_next_event_v1 *event = &buf.event; + const int cmd_version = ec_dev->mkbp_event_supported - 1; + memset(msg, 0, sizeof(*msg)); if (ec_dev->suspended) { dev_dbg(ec_dev->dev, "Device suspended.\n"); return -EHOSTDOWN; } - if (cmd_version == 1) { - ret = get_next_event_xfer(ec_dev, msg, cmd_version, - sizeof(struct ec_response_get_next_event_v1)); - if (ret < 0 || msg->result != EC_RES_INVALID_VERSION) - return ret; - - /* Fallback to version 0 for future send attempts */ - cmd_version = 0; - } - - ret = get_next_event_xfer(ec_dev, msg, cmd_version, + if (cmd_version == 0) + return get_next_event_xfer(ec_dev, msg, event, 0, sizeof(struct ec_response_get_next_event)); - return ret; + return get_next_event_xfer(ec_dev, msg, event, cmd_version, + sizeof(struct ec_response_get_next_event_v1)); } static int get_keyboard_state_event(struct cros_ec_device *ec_dev) @@ -639,32 +639,55 @@ static int get_keyboard_state_event(struct cros_ec_device *ec_dev) * @ec_dev: Device to fetch event from. * @wake_event: Pointer to a bool set to true upon return if the event might be * treated as a wake event. Ignored if null. + * @has_more_events: Pointer to bool set to true if more than one event is + * pending. + * Some EC will set this flag to indicate cros_ec_get_next_event() + * can be called multiple times in a row. + * It is an optimization to prevent issuing a EC command for + * nothing or wait for another interrupt from the EC to process + * the next message. + * Ignored if null. * * Return: negative error code on errors; 0 for no data; or else number of * bytes received (i.e., an event was retrieved successfully). Event types are * written out to @ec_dev->event_data.event_type on success. */ -int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event) +int cros_ec_get_next_event(struct cros_ec_device *ec_dev, + bool *wake_event, + bool *has_more_events) { u8 event_type; u32 host_event; int ret; - if (!ec_dev->mkbp_event_supported) { - ret = get_keyboard_state_event(ec_dev); - if (ret <= 0) - return ret; + /* + * Default value for wake_event. + * Wake up on keyboard event, wake up for spurious interrupt or link + * error to the EC. + */ + if (wake_event) + *wake_event = true; - if (wake_event) - *wake_event = true; + /* + * Default value for has_more_events. + * EC will raise another interrupt if AP does not process all events + * anyway. + */ + if (has_more_events) + *has_more_events = false; - return ret; - } + if (!ec_dev->mkbp_event_supported) + return get_keyboard_state_event(ec_dev); ret = get_next_event(ec_dev); if (ret <= 0) return ret; + if (has_more_events) + *has_more_events = ec_dev->event_data.event_type & + EC_MKBP_HAS_MORE_EVENTS; + ec_dev->event_data.event_type &= EC_MKBP_EVENT_TYPE_MASK; + if (wake_event) { event_type = ec_dev->event_data.event_type; host_event = cros_ec_get_host_event(ec_dev); @@ -679,9 +702,6 @@ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event) else if (host_event && !(host_event & ec_dev->host_event_wake_mask)) *wake_event = false; - /* Consider all other events as wake events. */ - else - *wake_event = true; } return ret; diff --git a/drivers/platform/chrome/cros_ec_rpmsg.c b/drivers/platform/chrome/cros_ec_rpmsg.c index 0c3738c3244d..bd068afe43b5 100644 --- a/drivers/platform/chrome/cros_ec_rpmsg.c +++ b/drivers/platform/chrome/cros_ec_rpmsg.c @@ -143,22 +143,11 @@ cros_ec_rpmsg_host_event_function(struct work_struct *host_event_work) struct cros_ec_rpmsg, host_event_work); struct cros_ec_device *ec_dev = dev_get_drvdata(&ec_rpmsg->rpdev->dev); - bool wake_event = true; - int ret; - - ret = cros_ec_get_next_event(ec_dev, &wake_event); - - /* - * Signal only if wake host events or any interrupt if - * cros_ec_get_next_event() returned an error (default value for - * wake_event is true) - */ - if (wake_event && device_may_wakeup(ec_dev->dev)) - pm_wakeup_event(ec_dev->dev, 0); + bool ec_has_more_events; - if (ret > 0) - blocking_notifier_call_chain(&ec_dev->event_notifier, - 0, ec_dev); + do { + ec_has_more_events = cros_ec_handle_event(ec_dev); + } while (ec_has_more_events); } static int cros_ec_rpmsg_callback(struct rpmsg_device *rpdev, void *data, diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index 02dc34f366d7..30098a551523 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -116,7 +116,9 @@ struct cros_ec_command { * code. * @pkt_xfer: Send packet to EC and get response. * @lock: One transaction at a time. - * @mkbp_event_supported: True if this EC supports the MKBP event protocol. + * @mkbp_event_supported: 0 if MKBP not supported. Otherwise its value is + * the maximum supported version of the MKBP host event + * command + 1. * @host_sleep_v1: True if this EC supports the sleep v1 command. * @event_notifier: Interrupt event notifier for transport devices. * @event_data: Raw payload transferred with the MKBP event. @@ -156,7 +158,7 @@ struct cros_ec_device { int (*pkt_xfer)(struct cros_ec_device *ec, struct cros_ec_command *msg); struct mutex lock; - bool mkbp_event_supported; + u8 mkbp_event_supported; bool host_sleep_v1; struct blocking_notifier_head event_notifier; @@ -205,7 +207,9 @@ int cros_ec_unregister(struct cros_ec_device *ec_dev); int cros_ec_query_all(struct cros_ec_device *ec_dev); -int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event); +int cros_ec_get_next_event(struct cros_ec_device *ec_dev, + bool *wake_event, + bool *has_more_events); u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev); @@ -213,6 +217,8 @@ int cros_ec_check_features(struct cros_ec_dev *ec, int feature); int cros_ec_get_sensor_count(struct cros_ec_dev *ec); +bool cros_ec_handle_event(struct cros_ec_device *ec_dev); + /** * cros_ec_get_time_ns() - Return time in ns. * -- cgit v1.2.3-71-gd317 From 4250b047039d324e0ff65267c8beb5bad5052a86 Mon Sep 17 00:00:00 2001 From: Kusanagi Kouichi Date: Thu, 21 Nov 2019 19:20:21 +0900 Subject: debugfs: Fix !DEBUG_FS debugfs_create_automount If DEBUG_FS=n, compile fails with the following error: kernel/trace/trace.c: In function 'tracing_init_dentry': kernel/trace/trace.c:8658:9: error: passing argument 3 of 'debugfs_create_automount' from incompatible pointer type [-Werror=incompatible-pointer-types] 8658 | trace_automount, NULL); | ^~~~~~~~~~~~~~~ | | | struct vfsmount * (*)(struct dentry *, void *) In file included from kernel/trace/trace.c:24: ./include/linux/debugfs.h:206:25: note: expected 'struct vfsmount * (*)(void *)' but argument is of type 'struct vfsmount * (*)(struct dentry *, void *)' 206 | struct vfsmount *(*f)(void *), | ~~~~~~~~~~~~~~~~~~~^~~~~~~~~~ Signed-off-by: Kusanagi Kouichi Link: https://lore.kernel.org/r/20191121102021787.MLMY.25002.ppp.dion.ne.jp@dmta0003.auone-net.jp Signed-off-by: Greg Kroah-Hartman --- include/linux/debugfs.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 0e8f2e0cb91f..bf9b6cafa4c2 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -54,6 +54,8 @@ static const struct file_operations __fops = { \ .llseek = no_llseek, \ } +typedef struct vfsmount *(*debugfs_automount_t)(struct dentry *, void *); + #if defined(CONFIG_DEBUG_FS) struct dentry *debugfs_lookup(const char *name, struct dentry *parent); @@ -75,7 +77,6 @@ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent); struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, const char *dest); -typedef struct vfsmount *(*debugfs_automount_t)(struct dentry *, void *); struct dentry *debugfs_create_automount(const char *name, struct dentry *parent, debugfs_automount_t f, @@ -203,7 +204,7 @@ static inline struct dentry *debugfs_create_symlink(const char *name, static inline struct dentry *debugfs_create_automount(const char *name, struct dentry *parent, - struct vfsmount *(*f)(void *), + debugfs_automount_t f, void *data) { return ERR_PTR(-ENODEV); -- cgit v1.2.3-71-gd317 From bbd8810d399812f2016713565e4d8ff8f1508aa6 Mon Sep 17 00:00:00 2001 From: Krzysztof Wilczynski Date: Tue, 3 Sep 2019 13:30:59 +0200 Subject: PCI: Remove unused includes and superfluous struct declaration Remove and from being included directly as part of the include/linux/of_pci.h, and remove superfluous declaration of struct of_phandle_args. Move users of include to include and directly rather than rely on both being included transitively through . Link: https://lore.kernel.org/r/20190903113059.2901-1-kw@linux.com Signed-off-by: Krzysztof Wilczynski Signed-off-by: Bjorn Helgaas Reviewed-by: Rob Herring --- drivers/iommu/of_iommu.c | 2 ++ drivers/irqchip/irq-gic-v2m.c | 1 + drivers/irqchip/irq-gic-v3-its-pci-msi.c | 1 + drivers/pci/controller/dwc/pcie-designware-host.c | 1 + drivers/pci/controller/pci-aardvark.c | 1 + drivers/pci/controller/pci-thunder-pem.c | 1 + drivers/pci/pci.c | 1 + drivers/pci/probe.c | 1 + include/linux/of_pci.h | 5 ++--- 9 files changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c index 614a93aa5305..026ad2b29dcd 100644 --- a/drivers/iommu/of_iommu.c +++ b/drivers/iommu/of_iommu.c @@ -8,6 +8,8 @@ #include #include #include +#include +#include #include #include #include diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c index e88e75c22b6a..fbec07d634ad 100644 --- a/drivers/irqchip/irq-gic-v2m.c +++ b/drivers/irqchip/irq-gic-v2m.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/irqchip/irq-gic-v3-its-pci-msi.c b/drivers/irqchip/irq-gic-v3-its-pci-msi.c index 229d586c3d7a..87711e0f8014 100644 --- a/drivers/irqchip/irq-gic-v3-its-pci-msi.c +++ b/drivers/irqchip/irq-gic-v3-its-pci-msi.c @@ -5,6 +5,7 @@ */ #include +#include #include #include #include diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index 0f36a926059a..43ce6de70374 100644 --- a/drivers/pci/controller/dwc/pcie-designware-host.c +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -10,6 +10,7 @@ #include #include +#include #include #include #include diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index fc0fe4d4de49..3a05f6ca95b0 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include diff --git a/drivers/pci/controller/pci-thunder-pem.c b/drivers/pci/controller/pci-thunder-pem.c index f127ce8bd4ef..9491e266b1ea 100644 --- a/drivers/pci/controller/pci-thunder-pem.c +++ b/drivers/pci/controller/pci-thunder-pem.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index e7982af9a5d8..2d36995e4ea5 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 3d5271a7a849..7c5d68b807ef 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h index 21a89c4880fa..29658c0ee71f 100644 --- a/include/linux/of_pci.h +++ b/include/linux/of_pci.h @@ -2,11 +2,10 @@ #ifndef __OF_PCI_H #define __OF_PCI_H -#include -#include +#include +#include struct pci_dev; -struct of_phandle_args; struct device_node; #if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_PCI) -- cgit v1.2.3-71-gd317 From b6866318657717c8914673a6394894d12bc9ff5e Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Thu, 21 Nov 2019 13:40:26 +0300 Subject: block: add iostat counters for flush requests Requests that triggers flushing volatile writeback cache to disk (barriers) have significant effect to overall performance. Block layer has sophisticated engine for combining several flush requests into one. But there is no statistics for actual flushes executed by disk. Requests which trigger flushes usually are barriers - zero-size writes. This patch adds two iostat counters into /sys/class/block/$dev/stat and /proc/diskstats - count of completed flush requests and their total time. Signed-off-by: Konstantin Khlebnikov Signed-off-by: Jens Axboe --- Documentation/ABI/testing/procfs-diskstats | 5 +++++ Documentation/ABI/testing/sysfs-block | 6 ++++++ Documentation/admin-guide/iostats.rst | 9 +++++++++ Documentation/block/stat.rst | 14 ++++++++++++-- block/blk-flush.c | 15 ++++++++++++++- block/genhd.c | 8 ++++++-- block/partition-generic.c | 7 +++++-- include/linux/blk_types.h | 1 + 8 files changed, 58 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/Documentation/ABI/testing/procfs-diskstats b/Documentation/ABI/testing/procfs-diskstats index 2c44b4f1b060..70dcaf2481f4 100644 --- a/Documentation/ABI/testing/procfs-diskstats +++ b/Documentation/ABI/testing/procfs-diskstats @@ -29,4 +29,9 @@ Description: 17 - sectors discarded 18 - time spent discarding + Kernel 5.5+ appends two more fields for flush requests: + + 19 - flush requests completed successfully + 20 - time spent flushing + For more details refer to Documentation/admin-guide/iostats.rst diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block index f8c7c7126bb1..ed8c14f161ee 100644 --- a/Documentation/ABI/testing/sysfs-block +++ b/Documentation/ABI/testing/sysfs-block @@ -15,6 +15,12 @@ Description: 9 - I/Os currently in progress 10 - time spent doing I/Os (ms) 11 - weighted time spent doing I/Os (ms) + 12 - discards completed + 13 - discards merged + 14 - sectors discarded + 15 - time spent discarding (ms) + 16 - flush requests completed + 17 - time spent flushing (ms) For more details refer Documentation/admin-guide/iostats.rst diff --git a/Documentation/admin-guide/iostats.rst b/Documentation/admin-guide/iostats.rst index 5d63b18bd6d1..4f0462af3ca7 100644 --- a/Documentation/admin-guide/iostats.rst +++ b/Documentation/admin-guide/iostats.rst @@ -121,6 +121,15 @@ Field 15 -- # of milliseconds spent discarding This is the total number of milliseconds spent by all discards (as measured from __make_request() to end_that_request_last()). +Field 16 -- # of flush requests completed + This is the total number of flush requests completed successfully. + + Block layer combines flush requests and executes at most one at a time. + This counts flush requests executed by disk. Not tracked for partitions. + +Field 17 -- # of milliseconds spent flushing + This is the total number of milliseconds spent by all flush requests. + To avoid introducing performance bottlenecks, no locks are held while modifying these counters. This implies that minor inaccuracies may be introduced when changes collide, so (for instance) adding up all the diff --git a/Documentation/block/stat.rst b/Documentation/block/stat.rst index 9c07bc22b0bc..77311335c08b 100644 --- a/Documentation/block/stat.rst +++ b/Documentation/block/stat.rst @@ -41,6 +41,8 @@ discard I/Os requests number of discard I/Os processed discard merges requests number of discard I/Os merged with in-queue I/O discard sectors sectors number of sectors discarded discard ticks milliseconds total wait time for discard requests +flush I/Os requests number of flush I/Os processed +flush ticks milliseconds total wait time for flush requests =============== ============= ================================================= read I/Os, write I/Os, discard I/0s @@ -48,6 +50,14 @@ read I/Os, write I/Os, discard I/0s These values increment when an I/O request completes. +flush I/Os +========== + +These values increment when an flush I/O request completes. + +Block layer combines flush requests and executes at most one at a time. +This counts flush requests executed by disk. Not tracked for partitions. + read merges, write merges, discard merges ========================================= @@ -62,8 +72,8 @@ discarded from this block device. The "sectors" in question are the standard UNIX 512-byte sectors, not any device- or filesystem-specific block size. The counters are incremented when the I/O completes. -read ticks, write ticks, discard ticks -====================================== +read ticks, write ticks, discard ticks, flush ticks +=================================================== These values count the number of milliseconds that I/O requests have waited on this block device. If there are multiple I/O requests waiting, diff --git a/block/blk-flush.c b/block/blk-flush.c index 1eec9cbe5a0a..1777346baf06 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -136,6 +136,17 @@ static void blk_flush_queue_rq(struct request *rq, bool add_front) blk_mq_add_to_requeue_list(rq, add_front, true); } +static void blk_account_io_flush(struct request *rq) +{ + struct hd_struct *part = &rq->rq_disk->part0; + + part_stat_lock(); + part_stat_inc(part, ios[STAT_FLUSH]); + part_stat_add(part, nsecs[STAT_FLUSH], + ktime_get_ns() - rq->start_time_ns); + part_stat_unlock(); +} + /** * blk_flush_complete_seq - complete flush sequence * @rq: PREFLUSH/FUA request being sequenced @@ -185,7 +196,7 @@ static void blk_flush_complete_seq(struct request *rq, case REQ_FSEQ_DONE: /* - * @rq was previously adjusted by blk_flush_issue() for + * @rq was previously adjusted by blk_insert_flush() for * flush sequencing and may already have gone through the * flush data request completion path. Restore @rq for * normal completion and end it. @@ -212,6 +223,8 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error) struct blk_flush_queue *fq = blk_get_flush_queue(q, flush_rq->mq_ctx); struct blk_mq_hw_ctx *hctx; + blk_account_io_flush(flush_rq); + /* release the tag's ownership to the req cloned from */ spin_lock_irqsave(&fq->mq_flush_lock, flags); diff --git a/block/genhd.c b/block/genhd.c index 26b31fcae217..ff6268970ddc 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1385,7 +1385,9 @@ static int diskstats_show(struct seq_file *seqf, void *v) "%lu %lu %lu %u " "%lu %lu %lu %u " "%u %u %u " - "%lu %lu %lu %u\n", + "%lu %lu %lu %u " + "%lu %u" + "\n", MAJOR(part_devt(hd)), MINOR(part_devt(hd)), disk_name(gp, hd->partno, buf), part_stat_read(hd, ios[STAT_READ]), @@ -1402,7 +1404,9 @@ static int diskstats_show(struct seq_file *seqf, void *v) part_stat_read(hd, ios[STAT_DISCARD]), part_stat_read(hd, merges[STAT_DISCARD]), part_stat_read(hd, sectors[STAT_DISCARD]), - (unsigned int)part_stat_read_msecs(hd, STAT_DISCARD) + (unsigned int)part_stat_read_msecs(hd, STAT_DISCARD), + part_stat_read(hd, ios[STAT_FLUSH]), + (unsigned int)part_stat_read_msecs(hd, STAT_FLUSH) ); } disk_part_iter_exit(&piter); diff --git a/block/partition-generic.c b/block/partition-generic.c index aee643ce13d1..3db8b73a96b1 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -127,7 +127,8 @@ ssize_t part_stat_show(struct device *dev, "%8lu %8lu %8llu %8u " "%8lu %8lu %8llu %8u " "%8u %8u %8u " - "%8lu %8lu %8llu %8u" + "%8lu %8lu %8llu %8u " + "%8lu %8u" "\n", part_stat_read(p, ios[STAT_READ]), part_stat_read(p, merges[STAT_READ]), @@ -143,7 +144,9 @@ ssize_t part_stat_show(struct device *dev, part_stat_read(p, ios[STAT_DISCARD]), part_stat_read(p, merges[STAT_DISCARD]), (unsigned long long)part_stat_read(p, sectors[STAT_DISCARD]), - (unsigned int)part_stat_read_msecs(p, STAT_DISCARD)); + (unsigned int)part_stat_read_msecs(p, STAT_DISCARD), + part_stat_read(p, ios[STAT_FLUSH]), + (unsigned int)part_stat_read_msecs(p, STAT_FLUSH)); } ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr, diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 23a2fd534817..70254ae11769 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -377,6 +377,7 @@ enum stat_group { STAT_READ, STAT_WRITE, STAT_DISCARD, + STAT_FLUSH, NR_STAT_GROUPS }; -- cgit v1.2.3-71-gd317 From a7ba70f1787f977f970cd116076c6fce4b9e01cc Mon Sep 17 00:00:00 2001 From: Nicolas Saenz Julienne Date: Thu, 21 Nov 2019 10:26:44 +0100 Subject: dma-mapping: treat dev->bus_dma_mask as a DMA limit Using a mask to represent bus DMA constraints has a set of limitations. The biggest one being it can only hold a power of two (minus one). The DMA mapping code is already aware of this and treats dev->bus_dma_mask as a limit. This quirk is already used by some architectures although still rare. With the introduction of the Raspberry Pi 4 we've found a new contender for the use of bus DMA limits, as its PCIe bus can only address the lower 3GB of memory (of a total of 4GB). This is impossible to represent with a mask. To make things worse the device-tree code rounds non power of two bus DMA limits to the next power of two, which is unacceptable in this case. In the light of this, rename dev->bus_dma_mask to dev->bus_dma_limit all over the tree and treat it as such. Note that dev->bus_dma_limit should contain the higher accessible DMA address. Signed-off-by: Nicolas Saenz Julienne Reviewed-by: Robin Murphy Signed-off-by: Christoph Hellwig --- arch/mips/pci/fixup-sb1250.c | 16 ++++++++-------- arch/powerpc/sysdev/fsl_pci.c | 6 +++--- arch/x86/kernel/pci-dma.c | 2 +- arch/x86/mm/mem_encrypt.c | 2 +- arch/x86/pci/sta2x11-fixup.c | 2 +- drivers/acpi/arm64/iort.c | 20 +++++++------------- drivers/ata/ahci.c | 2 +- drivers/iommu/dma-iommu.c | 3 +-- drivers/of/device.c | 9 +++++---- include/linux/device.h | 6 +++--- include/linux/dma-direct.h | 2 +- include/linux/dma-mapping.h | 2 +- kernel/dma/direct.c | 27 +++++++++++++-------------- 13 files changed, 46 insertions(+), 53 deletions(-) (limited to 'include/linux') diff --git a/arch/mips/pci/fixup-sb1250.c b/arch/mips/pci/fixup-sb1250.c index 8a41b359cf90..40efc990cdce 100644 --- a/arch/mips/pci/fixup-sb1250.c +++ b/arch/mips/pci/fixup-sb1250.c @@ -21,22 +21,22 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SIBYTE, PCI_DEVICE_ID_BCM1250_PCI, /* * The BCM1250, etc. PCI host bridge does not support DAC on its 32-bit - * bus, so we set the bus's DMA mask accordingly. However the HT link + * bus, so we set the bus's DMA limit accordingly. However the HT link * down the artificial PCI-HT bridge supports 40-bit addressing and the * SP1011 HT-PCI bridge downstream supports both DAC and a 64-bit bus * width, so we record the PCI-HT bridge's secondary and subordinate bus - * numbers and do not set the mask for devices present in the inclusive + * numbers and do not set the limit for devices present in the inclusive * range of those. */ -struct sb1250_bus_dma_mask_exclude { +struct sb1250_bus_dma_limit_exclude { bool set; unsigned char start; unsigned char end; }; -static int sb1250_bus_dma_mask(struct pci_dev *dev, void *data) +static int sb1250_bus_dma_limit(struct pci_dev *dev, void *data) { - struct sb1250_bus_dma_mask_exclude *exclude = data; + struct sb1250_bus_dma_limit_exclude *exclude = data; bool exclude_this; bool ht_bridge; @@ -55,7 +55,7 @@ static int sb1250_bus_dma_mask(struct pci_dev *dev, void *data) exclude->start, exclude->end); } else { dev_dbg(&dev->dev, "disabling DAC for device"); - dev->dev.bus_dma_mask = DMA_BIT_MASK(32); + dev->dev.bus_dma_limit = DMA_BIT_MASK(32); } return 0; @@ -63,9 +63,9 @@ static int sb1250_bus_dma_mask(struct pci_dev *dev, void *data) static void quirk_sb1250_pci_dac(struct pci_dev *dev) { - struct sb1250_bus_dma_mask_exclude exclude = { .set = false }; + struct sb1250_bus_dma_limit_exclude exclude = { .set = false }; - pci_walk_bus(dev->bus, sb1250_bus_dma_mask, &exclude); + pci_walk_bus(dev->bus, sb1250_bus_dma_limit, &exclude); } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SIBYTE, PCI_DEVICE_ID_BCM1250_PCI, quirk_sb1250_pci_dac); diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index ff0e2b156cb5..617a443d673d 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -115,8 +115,8 @@ static void pci_dma_dev_setup_swiotlb(struct pci_dev *pdev) { struct pci_controller *hose = pci_bus_to_host(pdev->bus); - pdev->dev.bus_dma_mask = - hose->dma_window_base_cur + hose->dma_window_size; + pdev->dev.bus_dma_limit = + hose->dma_window_base_cur + hose->dma_window_size - 1; } static void setup_swiotlb_ops(struct pci_controller *hose) @@ -135,7 +135,7 @@ static void fsl_pci_dma_set_mask(struct device *dev, u64 dma_mask) * mapping that allows addressing any RAM address from across PCI. */ if (dev_is_pci(dev) && dma_mask >= pci64_dma_offset * 2 - 1) { - dev->bus_dma_mask = 0; + dev->bus_dma_limit = 0; dev->archdata.dma_offset = pci64_dma_offset; } } diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index fa4352dce491..3a75d665d43c 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -146,7 +146,7 @@ rootfs_initcall(pci_iommu_init); static int via_no_dac_cb(struct pci_dev *pdev, void *data) { - pdev->dev.bus_dma_mask = DMA_BIT_MASK(32); + pdev->dev.bus_dma_limit = DMA_BIT_MASK(32); return 0; } diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 9268c12458c8..a03614bd3e1a 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -367,7 +367,7 @@ bool force_dma_unencrypted(struct device *dev) if (sme_active()) { u64 dma_enc_mask = DMA_BIT_MASK(__ffs64(sme_me_mask)); u64 dma_dev_mask = min_not_zero(dev->coherent_dma_mask, - dev->bus_dma_mask); + dev->bus_dma_limit); if (dma_dev_mask <= dma_enc_mask) return true; diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c index 4a631264b809..c313d784efab 100644 --- a/arch/x86/pci/sta2x11-fixup.c +++ b/arch/x86/pci/sta2x11-fixup.c @@ -143,7 +143,7 @@ static void sta2x11_map_ep(struct pci_dev *pdev) dev->dma_pfn_offset = PFN_DOWN(-amba_base); - dev->bus_dma_mask = max_amba_addr; + dev->bus_dma_limit = max_amba_addr; pci_set_consistent_dma_mask(pdev, max_amba_addr); pci_set_dma_mask(pdev, max_amba_addr); diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index 5a7551d060f2..33f71983e001 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -1057,8 +1057,8 @@ static int rc_dma_get_range(struct device *dev, u64 *size) */ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size) { - u64 mask, dmaaddr = 0, size = 0, offset = 0; - int ret, msb; + u64 end, mask, dmaaddr = 0, size = 0, offset = 0; + int ret; /* * If @dev is expected to be DMA-capable then the bus code that created @@ -1085,19 +1085,13 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size) } if (!ret) { - msb = fls64(dmaaddr + size - 1); /* - * Round-up to the power-of-two mask or set - * the mask to the whole 64-bit address space - * in case the DMA region covers the full - * memory window. + * Limit coherent and dma mask based on size retrieved from + * firmware. */ - mask = msb == 64 ? U64_MAX : (1ULL << msb) - 1; - /* - * Limit coherent and dma mask based on size - * retrieved from firmware. - */ - dev->bus_dma_mask = mask; + end = dmaaddr + size - 1; + mask = DMA_BIT_MASK(ilog2(end) + 1); + dev->bus_dma_limit = end; dev->coherent_dma_mask = mask; *dev->dma_mask = mask; } diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 05c2b32dcc4d..7c6d06ffb586 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -897,7 +897,7 @@ static int ahci_configure_dma_masks(struct pci_dev *pdev, int using_dac) * value, don't extend it here. This happens on STA2X11, for example. * * XXX: manipulating the DMA mask from platform code is completely - * bogus, platform code should use dev->bus_dma_mask instead.. + * bogus, platform code should use dev->bus_dma_limit instead.. */ if (pdev->dma_mask && pdev->dma_mask < DMA_BIT_MASK(32)) return 0; diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 0fa8c1d818b7..646332fbf3d7 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -405,8 +405,7 @@ static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain, if (iova_len < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1))) iova_len = roundup_pow_of_two(iova_len); - if (dev->bus_dma_mask) - dma_limit &= dev->bus_dma_mask; + dma_limit = min_not_zero(dma_limit, dev->bus_dma_limit); if (domain->geometry.force_aperture) dma_limit = min(dma_limit, domain->geometry.aperture_end); diff --git a/drivers/of/device.c b/drivers/of/device.c index da8158392010..e9127db7b067 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -93,7 +93,7 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma) bool coherent; unsigned long offset; const struct iommu_ops *iommu; - u64 mask; + u64 mask, end; ret = of_dma_get_range(np, &dma_addr, &paddr, &size); if (ret < 0) { @@ -148,12 +148,13 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma) * Limit coherent and dma mask based on size and default mask * set by the driver. */ - mask = DMA_BIT_MASK(ilog2(dma_addr + size - 1) + 1); + end = dma_addr + size - 1; + mask = DMA_BIT_MASK(ilog2(end) + 1); dev->coherent_dma_mask &= mask; *dev->dma_mask &= mask; - /* ...but only set bus mask if we found valid dma-ranges earlier */ + /* ...but only set bus limit if we found valid dma-ranges earlier */ if (!ret) - dev->bus_dma_mask = mask; + dev->bus_dma_limit = end; coherent = of_dma_is_coherent(np); dev_dbg(dev, "device is%sdma coherent\n", diff --git a/include/linux/device.h b/include/linux/device.h index 297239a08bb7..e396de656f20 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1186,8 +1186,8 @@ struct dev_links_info { * @coherent_dma_mask: Like dma_mask, but for alloc_coherent mapping as not all * hardware supports 64-bit addresses for consistent allocations * such descriptors. - * @bus_dma_mask: Mask of an upstream bridge or bus which imposes a smaller DMA - * limit than the device itself supports. + * @bus_dma_limit: Limit of an upstream bridge or bus which imposes a smaller + * DMA limit than the device itself supports. * @dma_pfn_offset: offset of DMA memory range relatively of RAM * @dma_parms: A low level driver may set these to teach IOMMU code about * segment limitations. @@ -1270,7 +1270,7 @@ struct device { not all hardware supports 64 bit addresses for consistent allocations such descriptors. */ - u64 bus_dma_mask; /* upstream dma_mask constraint */ + u64 bus_dma_limit; /* upstream dma constraint */ unsigned long dma_pfn_offset; struct device_dma_parameters *dma_parms; diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 452f5280cde3..24b8684aa21d 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -63,7 +63,7 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size, min(addr, end) < phys_to_dma(dev, PFN_PHYS(min_low_pfn))) return false; - return end <= min_not_zero(*dev->dma_mask, dev->bus_dma_mask); + return end <= min_not_zero(*dev->dma_mask, dev->bus_dma_limit); } u64 dma_direct_get_required_mask(struct device *dev); diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 4d450672b7d6..c4d8741264bd 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -697,7 +697,7 @@ static inline int dma_coerce_mask_and_coherent(struct device *dev, u64 mask) */ static inline bool dma_addressing_limited(struct device *dev) { - return min_not_zero(dma_get_mask(dev), dev->bus_dma_mask) < + return min_not_zero(dma_get_mask(dev), dev->bus_dma_limit) < dma_get_required_mask(dev); } diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 267b23a13b69..6af7ae83c4ad 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -27,10 +27,10 @@ static void report_addr(struct device *dev, dma_addr_t dma_addr, size_t size) { if (!dev->dma_mask) { dev_err_once(dev, "DMA map on device without dma_mask\n"); - } else if (*dev->dma_mask >= DMA_BIT_MASK(32) || dev->bus_dma_mask) { + } else if (*dev->dma_mask >= DMA_BIT_MASK(32) || dev->bus_dma_limit) { dev_err_once(dev, - "overflow %pad+%zu of DMA mask %llx bus mask %llx\n", - &dma_addr, size, *dev->dma_mask, dev->bus_dma_mask); + "overflow %pad+%zu of DMA mask %llx bus limit %llx\n", + &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit); } WARN_ON_ONCE(1); } @@ -57,15 +57,14 @@ u64 dma_direct_get_required_mask(struct device *dev) } static gfp_t __dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, - u64 *phys_mask) + u64 *phys_limit) { - if (dev->bus_dma_mask && dev->bus_dma_mask < dma_mask) - dma_mask = dev->bus_dma_mask; + u64 dma_limit = min_not_zero(dma_mask, dev->bus_dma_limit); if (force_dma_unencrypted(dev)) - *phys_mask = __dma_to_phys(dev, dma_mask); + *phys_limit = __dma_to_phys(dev, dma_limit); else - *phys_mask = dma_to_phys(dev, dma_mask); + *phys_limit = dma_to_phys(dev, dma_limit); /* * Optimistically try the zone that the physical address mask falls @@ -75,9 +74,9 @@ static gfp_t __dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, * Note that GFP_DMA32 and GFP_DMA are no ops without the corresponding * zones. */ - if (*phys_mask <= DMA_BIT_MASK(zone_dma_bits)) + if (*phys_limit <= DMA_BIT_MASK(zone_dma_bits)) return GFP_DMA; - if (*phys_mask <= DMA_BIT_MASK(32)) + if (*phys_limit <= DMA_BIT_MASK(32)) return GFP_DMA32; return 0; } @@ -85,7 +84,7 @@ static gfp_t __dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size) { return phys_to_dma_direct(dev, phys) + size - 1 <= - min_not_zero(dev->coherent_dma_mask, dev->bus_dma_mask); + min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit); } struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, @@ -94,7 +93,7 @@ struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, size_t alloc_size = PAGE_ALIGN(size); int node = dev_to_node(dev); struct page *page = NULL; - u64 phys_mask; + u64 phys_limit; if (attrs & DMA_ATTR_NO_WARN) gfp |= __GFP_NOWARN; @@ -102,7 +101,7 @@ struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, /* we always manually zero the memory once we are done: */ gfp &= ~__GFP_ZERO; gfp |= __dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask, - &phys_mask); + &phys_limit); page = dma_alloc_contiguous(dev, alloc_size, gfp); if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) { dma_free_contiguous(dev, page, alloc_size); @@ -116,7 +115,7 @@ again: page = NULL; if (IS_ENABLED(CONFIG_ZONE_DMA32) && - phys_mask < DMA_BIT_MASK(64) && + phys_limit < DMA_BIT_MASK(64) && !(gfp & (GFP_DMA32 | GFP_DMA))) { gfp |= GFP_DMA32; goto again; -- cgit v1.2.3-71-gd317 From 52deba0f02a98c150677a9c381cc1991a928bcff Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Fri, 15 Nov 2019 00:40:00 +0900 Subject: nvme: hwmon: provide temperature min and max values for each sensor MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit According to the NVMe specification, the over temperature threshold and under temperature threshold features shall be implemented for Composite Temperature if a non-zero WCTEMP field value is reported in the Identify Controller data structure. The features are also implemented for all implemented temperature sensors (i.e., all Temperature Sensor fields that report a non-zero value). This provides the over temperature threshold and under temperature threshold for each sensor as temperature min and max values of hwmon sysfs attributes. The WCTEMP is already provided as a temperature max value for Composite Temperature, but this change isn't incompatible. Because the default value of the over temperature threshold for Composite Temperature is the WCTEMP. Now the alarm attribute for Composite Temperature indicates one of the temperature is outside of a temperature threshold. Because there is only a single bit in Critical Warning field that indicates a temperature is outside of a threshold. Example output from the "sensors" command: nvme-pci-0100 Adapter: PCI adapter Composite: +33.9°C (low = -273.1°C, high = +69.8°C) (crit = +79.8°C) Sensor 1: +34.9°C (low = -273.1°C, high = +65261.8°C) Sensor 2: +31.9°C (low = -273.1°C, high = +65261.8°C) Sensor 5: +47.9°C (low = -273.1°C, high = +65261.8°C) This also adds helper macros for kelvin from/to milli Celsius conversion, and replaces the repeated code in hwmon.c. Cc: Keith Busch Cc: Jens Axboe Cc: Christoph Hellwig Cc: Sagi Grimberg Cc: Jean Delvare Reviewed-by: Guenter Roeck Tested-by: Guenter Roeck Signed-off-by: Akinobu Mita Signed-off-by: Keith Busch --- drivers/nvme/host/hwmon.c | 106 +++++++++++++++++++++++++++++++++++++++------- include/linux/nvme.h | 6 +++ 2 files changed, 96 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c index 5480cbb84f9f..97a84b4b45db 100644 --- a/drivers/nvme/host/hwmon.c +++ b/drivers/nvme/host/hwmon.c @@ -9,12 +9,57 @@ #include "nvme.h" +/* These macros should be moved to linux/temperature.h */ +#define MILLICELSIUS_TO_KELVIN(t) DIV_ROUND_CLOSEST((t) + 273150, 1000) +#define KELVIN_TO_MILLICELSIUS(t) ((t) * 1000L - 273150) + struct nvme_hwmon_data { struct nvme_ctrl *ctrl; struct nvme_smart_log log; struct mutex read_lock; }; +static int nvme_get_temp_thresh(struct nvme_ctrl *ctrl, int sensor, bool under, + long *temp) +{ + unsigned int threshold = sensor << NVME_TEMP_THRESH_SELECT_SHIFT; + u32 status; + int ret; + + if (under) + threshold |= NVME_TEMP_THRESH_TYPE_UNDER; + + ret = nvme_get_features(ctrl, NVME_FEAT_TEMP_THRESH, threshold, NULL, 0, + &status); + if (ret > 0) + return -EIO; + if (ret < 0) + return ret; + *temp = KELVIN_TO_MILLICELSIUS(status & NVME_TEMP_THRESH_MASK); + + return 0; +} + +static int nvme_set_temp_thresh(struct nvme_ctrl *ctrl, int sensor, bool under, + long temp) +{ + unsigned int threshold = sensor << NVME_TEMP_THRESH_SELECT_SHIFT; + int ret; + + temp = MILLICELSIUS_TO_KELVIN(temp); + threshold |= clamp_val(temp, 0, NVME_TEMP_THRESH_MASK); + + if (under) + threshold |= NVME_TEMP_THRESH_TYPE_UNDER; + + ret = nvme_set_features(ctrl, NVME_FEAT_TEMP_THRESH, threshold, NULL, 0, + NULL); + if (ret > 0) + return -EIO; + + return ret; +} + static int nvme_hwmon_get_smart_log(struct nvme_hwmon_data *data) { int ret; @@ -39,10 +84,11 @@ static int nvme_hwmon_read(struct device *dev, enum hwmon_sensor_types type, */ switch (attr) { case hwmon_temp_max: - *val = (data->ctrl->wctemp - 273) * 1000; - return 0; + return nvme_get_temp_thresh(data->ctrl, channel, false, val); + case hwmon_temp_min: + return nvme_get_temp_thresh(data->ctrl, channel, true, val); case hwmon_temp_crit: - *val = (data->ctrl->cctemp - 273) * 1000; + *val = KELVIN_TO_MILLICELSIUS(data->ctrl->cctemp); return 0; default: break; @@ -59,7 +105,7 @@ static int nvme_hwmon_read(struct device *dev, enum hwmon_sensor_types type, temp = get_unaligned_le16(log->temperature); else temp = le16_to_cpu(log->temp_sensor[channel - 1]); - *val = (temp - 273) * 1000; + *val = KELVIN_TO_MILLICELSIUS(temp); break; case hwmon_temp_alarm: *val = !!(log->critical_warning & NVME_SMART_CRIT_TEMPERATURE); @@ -73,6 +119,23 @@ unlock: return err; } +static int nvme_hwmon_write(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel, long val) +{ + struct nvme_hwmon_data *data = dev_get_drvdata(dev); + + switch (attr) { + case hwmon_temp_max: + return nvme_set_temp_thresh(data->ctrl, channel, false, val); + case hwmon_temp_min: + return nvme_set_temp_thresh(data->ctrl, channel, true, val); + default: + break; + } + + return -EOPNOTSUPP; +} + static const char * const nvme_hwmon_sensor_names[] = { "Composite", "Sensor 1", @@ -105,8 +168,10 @@ static umode_t nvme_hwmon_is_visible(const void *_data, return 0444; break; case hwmon_temp_max: - if (!channel && data->ctrl->wctemp) - return 0444; + case hwmon_temp_min: + if ((!channel && data->ctrl->wctemp) || + (channel && data->log.temp_sensor[channel - 1])) + return 0644; break; case hwmon_temp_alarm: if (!channel) @@ -126,16 +191,24 @@ static umode_t nvme_hwmon_is_visible(const void *_data, static const struct hwmon_channel_info *nvme_hwmon_info[] = { HWMON_CHANNEL_INFO(chip, HWMON_C_REGISTER_TZ), HWMON_CHANNEL_INFO(temp, - HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_CRIT | - HWMON_T_LABEL | HWMON_T_ALARM, - HWMON_T_INPUT | HWMON_T_LABEL, - HWMON_T_INPUT | HWMON_T_LABEL, - HWMON_T_INPUT | HWMON_T_LABEL, - HWMON_T_INPUT | HWMON_T_LABEL, - HWMON_T_INPUT | HWMON_T_LABEL, - HWMON_T_INPUT | HWMON_T_LABEL, - HWMON_T_INPUT | HWMON_T_LABEL, - HWMON_T_INPUT | HWMON_T_LABEL), + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_CRIT | HWMON_T_LABEL | HWMON_T_ALARM, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_LABEL, + HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | + HWMON_T_LABEL), NULL }; @@ -143,6 +216,7 @@ static const struct hwmon_ops nvme_hwmon_ops = { .is_visible = nvme_hwmon_is_visible, .read = nvme_hwmon_read, .read_string = nvme_hwmon_read_string, + .write = nvme_hwmon_write, }; static const struct hwmon_chip_info nvme_hwmon_chip_info = { diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 3eca4f7d8510..3d5189f46cb1 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -804,6 +804,12 @@ struct nvme_write_zeroes_cmd { /* Features */ +enum { + NVME_TEMP_THRESH_MASK = 0xffff, + NVME_TEMP_THRESH_SELECT_SHIFT = 16, + NVME_TEMP_THRESH_TYPE_UNDER = 0x100000, +}; + struct nvme_feat_auto_pst { __le64 entries[32]; }; -- cgit v1.2.3-71-gd317 From 7599a896f2e46e9c072e02a8299a67d4d2f96675 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 21 Nov 2019 16:58:53 +0100 Subject: audit: Move audit_log_task declaration under CONFIG_AUDITSYSCALL The 0-DAY found that audit_log_task is not declared under CONFIG_AUDITSYSCALL which causes compilation error when it is not defined: kernel/bpf/syscall.o: In function `bpf_audit_prog.isra.30': >> syscall.c:(.text+0x860): undefined reference to `audit_log_task' Adding the audit_log_task declaration and stub within CONFIG_AUDITSYSCALL ifdef. Fixes: 91e6015b082b ("bpf: Emit audit messages upon successful prog load and unload") Reported-by: kbuild test robot Signed-off-by: Jiri Olsa Signed-off-by: David S. Miller --- include/linux/audit.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index edd006f4597d..18925d924c73 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -159,7 +159,6 @@ extern void audit_log_key(struct audit_buffer *ab, extern void audit_log_link_denied(const char *operation); extern void audit_log_lost(const char *message); -extern void audit_log_task(struct audit_buffer *ab); extern int audit_log_task_context(struct audit_buffer *ab); extern void audit_log_task_info(struct audit_buffer *ab); @@ -220,8 +219,6 @@ static inline void audit_log_key(struct audit_buffer *ab, char *key) { } static inline void audit_log_link_denied(const char *string) { } -static inline void audit_log_task(struct audit_buffer *ab) -{ } static inline int audit_log_task_context(struct audit_buffer *ab) { return 0; @@ -361,6 +358,8 @@ static inline void audit_ptrace(struct task_struct *t) __audit_ptrace(t); } +extern void audit_log_task(struct audit_buffer *ab); + /* Private API (for audit.c only) */ extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp); extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode); @@ -648,6 +647,9 @@ static inline void audit_ntp_log(const struct audit_ntp_data *ad) static inline void audit_ptrace(struct task_struct *t) { } + +static inline void audit_log_task(struct audit_buffer *ab) +{ } #define audit_n_rules 0 #define audit_signals 0 #endif /* CONFIG_AUDITSYSCALL */ -- cgit v1.2.3-71-gd317 From bedc61a922f9dbbe3bfb26ec2745f8cd63b57637 Mon Sep 17 00:00:00 2001 From: Andrea Parri Date: Tue, 15 Oct 2019 13:46:44 +0200 Subject: Drivers: hv: vmbus: Introduce table of VMBus protocol versions The technique used to get the next VMBus version seems increasisly clumsy as the number of VMBus versions increases. Performance is not a concern since this is only done once during system boot; it's just that we'll end up with more lines of code than is really needed. As an alternative, introduce a table with the version numbers listed in order (from the most recent to the oldest). vmbus_connect() loops through the versions listed in the table until it gets an accepted connection or gets to the end of the table (invalid version). Suggested-by: Michael Kelley Signed-off-by: Andrea Parri Reviewed-by: Wei Liu Reviewed-by: Michael Kelley Signed-off-by: Sasha Levin --- drivers/hv/connection.c | 50 ++++++++++++++++++------------------------------- drivers/hv/vmbus_drv.c | 3 +-- include/linux/hyperv.h | 4 ---- 3 files changed, 19 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index 6e4c015783ff..8dc48f53c1ac 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -40,29 +40,17 @@ EXPORT_SYMBOL_GPL(vmbus_connection); __u32 vmbus_proto_version; EXPORT_SYMBOL_GPL(vmbus_proto_version); -static __u32 vmbus_get_next_version(__u32 current_version) -{ - switch (current_version) { - case (VERSION_WIN7): - return VERSION_WS2008; - - case (VERSION_WIN8): - return VERSION_WIN7; - - case (VERSION_WIN8_1): - return VERSION_WIN8; - - case (VERSION_WIN10): - return VERSION_WIN8_1; - - case (VERSION_WIN10_V5): - return VERSION_WIN10; - - case (VERSION_WS2008): - default: - return VERSION_INVAL; - } -} +/* + * Table of VMBus versions listed from newest to oldest. + */ +static __u32 vmbus_versions[] = { + VERSION_WIN10_V5, + VERSION_WIN10, + VERSION_WIN8_1, + VERSION_WIN8, + VERSION_WIN7, + VERSION_WS2008 +}; int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version) { @@ -169,8 +157,8 @@ int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version) */ int vmbus_connect(void) { - int ret = 0; struct vmbus_channel_msginfo *msginfo = NULL; + int i, ret = 0; __u32 version; /* Initialize the vmbus connection */ @@ -244,21 +232,19 @@ int vmbus_connect(void) * version. */ - version = VERSION_CURRENT; + for (i = 0; ; i++) { + if (i == ARRAY_SIZE(vmbus_versions)) + goto cleanup; + + version = vmbus_versions[i]; - do { ret = vmbus_negotiate_version(msginfo, version); if (ret == -ETIMEDOUT) goto cleanup; if (vmbus_connection.conn_state == CONNECTED) break; - - version = vmbus_get_next_version(version); - } while (version != VERSION_INVAL); - - if (version == VERSION_INVAL) - goto cleanup; + } vmbus_proto_version = version; pr_info("Vmbus version:%d.%d\n", diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 53a60c81e220..0ac874faf720 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -2220,8 +2220,7 @@ static int vmbus_bus_resume(struct device *dev) * We only use the 'vmbus_proto_version', which was in use before * hibernation, to re-negotiate with the host. */ - if (vmbus_proto_version == VERSION_INVAL || - vmbus_proto_version == 0) { + if (!vmbus_proto_version) { pr_err("Invalid proto version = 0x%x\n", vmbus_proto_version); return -EINVAL; } diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index b4a017093b69..c08b62dbd151 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -192,10 +192,6 @@ static inline u32 hv_get_avail_to_write_percent( #define VERSION_WIN10 ((4 << 16) | (0)) #define VERSION_WIN10_V5 ((5 << 16) | (0)) -#define VERSION_INVAL -1 - -#define VERSION_CURRENT VERSION_WIN10_V5 - /* Make maximum size of pipe payload of 16K */ #define MAX_PIPE_DATA_PAYLOAD (sizeof(u8) * 16384) -- cgit v1.2.3-71-gd317 From 2d4f49b3e1e3a24ce16dfeeb2235688c8aba57ef Mon Sep 17 00:00:00 2001 From: Andrea Parri Date: Tue, 15 Oct 2019 13:46:45 +0200 Subject: Drivers: hv: vmbus: Enable VMBus protocol versions 4.1, 5.1 and 5.2 Hyper-V has added VMBus protocol versions 5.1 and 5.2 in recent release versions. Allow Linux guests to negotiate these new protocol versions on versions of Hyper-V that support them. While on this, also allow guests to negotiate the VMBus protocol version 4.1 (which was missing). Signed-off-by: Andrea Parri Reviewed-by: Wei Liu Reviewed-by: Michael Kelley Signed-off-by: Sasha Levin --- drivers/hv/connection.c | 13 ++++++++----- include/linux/hyperv.h | 8 +++++++- 2 files changed, 15 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index 8dc48f53c1ac..cadfb34b38d8 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -44,7 +44,10 @@ EXPORT_SYMBOL_GPL(vmbus_proto_version); * Table of VMBus versions listed from newest to oldest. */ static __u32 vmbus_versions[] = { + VERSION_WIN10_V5_2, + VERSION_WIN10_V5_1, VERSION_WIN10_V5, + VERSION_WIN10_V4_1, VERSION_WIN10, VERSION_WIN8_1, VERSION_WIN8, @@ -68,12 +71,12 @@ int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version) msg->vmbus_version_requested = version; /* - * VMBus protocol 5.0 (VERSION_WIN10_V5) requires that we must use - * VMBUS_MESSAGE_CONNECTION_ID_4 for the Initiate Contact Message, + * VMBus protocol 5.0 (VERSION_WIN10_V5) and higher require that we must + * use VMBUS_MESSAGE_CONNECTION_ID_4 for the Initiate Contact Message, * and for subsequent messages, we must use the Message Connection ID * field in the host-returned Version Response Message. And, with - * VERSION_WIN10_V5, we don't use msg->interrupt_page, but we tell - * the host explicitly that we still use VMBUS_MESSAGE_SINT(2) for + * VERSION_WIN10_V5 and higher, we don't use msg->interrupt_page, but we + * tell the host explicitly that we still use VMBUS_MESSAGE_SINT(2) for * compatibility. * * On old hosts, we should always use VMBUS_MESSAGE_CONNECTION_ID (1). @@ -399,7 +402,7 @@ int vmbus_post_msg(void *buffer, size_t buflen, bool can_sleep) case HV_STATUS_INVALID_CONNECTION_ID: /* * See vmbus_negotiate_version(): VMBus protocol 5.0 - * requires that we must use + * and higher require that we must use * VMBUS_MESSAGE_CONNECTION_ID_4 for the Initiate * Contact message, but on old hosts that only * support VMBus protocol 4.0 or lower, here we get diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index c08b62dbd151..f17f2cd22e39 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -182,15 +182,21 @@ static inline u32 hv_get_avail_to_write_percent( * 2 . 4 (Windows 8) * 3 . 0 (Windows 8 R2) * 4 . 0 (Windows 10) + * 4 . 1 (Windows 10 RS3) * 5 . 0 (Newer Windows 10) + * 5 . 1 (Windows 10 RS4) + * 5 . 2 (Windows Server 2019, RS5) */ #define VERSION_WS2008 ((0 << 16) | (13)) #define VERSION_WIN7 ((1 << 16) | (1)) #define VERSION_WIN8 ((2 << 16) | (4)) #define VERSION_WIN8_1 ((3 << 16) | (0)) -#define VERSION_WIN10 ((4 << 16) | (0)) +#define VERSION_WIN10 ((4 << 16) | (0)) +#define VERSION_WIN10_V4_1 ((4 << 16) | (1)) #define VERSION_WIN10_V5 ((5 << 16) | (0)) +#define VERSION_WIN10_V5_1 ((5 << 16) | (1)) +#define VERSION_WIN10_V5_2 ((5 << 16) | (2)) /* Make maximum size of pipe payload of 16K */ #define MAX_PIPE_DATA_PAYLOAD (sizeof(u8) * 16384) -- cgit v1.2.3-71-gd317 From af9ca6f9bb16e446a44393a797d0ae74d356a5c7 Mon Sep 17 00:00:00 2001 From: Branden Bonaby Date: Thu, 3 Oct 2019 17:01:49 -0400 Subject: drivers: hv: vmbus: Introduce latency testing Introduce user specified latency in the packet reception path By exposing the test parameters as part of the debugfs channel attributes. We will control the testing state via these attributes. Signed-off-by: Branden Bonaby Reviewed-by: Michael Kelley Signed-off-by: Sasha Levin --- Documentation/ABI/testing/debugfs-hyperv | 23 ++++ MAINTAINERS | 1 + drivers/hv/Makefile | 1 + drivers/hv/connection.c | 1 + drivers/hv/hv_debugfs.c | 178 +++++++++++++++++++++++++++++++ drivers/hv/hyperv_vmbus.h | 31 ++++++ drivers/hv/ring_buffer.c | 2 + drivers/hv/vmbus_drv.c | 6 ++ include/linux/hyperv.h | 19 ++++ lib/Kconfig.debug | 7 ++ 10 files changed, 269 insertions(+) create mode 100644 Documentation/ABI/testing/debugfs-hyperv create mode 100644 drivers/hv/hv_debugfs.c (limited to 'include/linux') diff --git a/Documentation/ABI/testing/debugfs-hyperv b/Documentation/ABI/testing/debugfs-hyperv new file mode 100644 index 000000000000..9185e1b06bba --- /dev/null +++ b/Documentation/ABI/testing/debugfs-hyperv @@ -0,0 +1,23 @@ +What: /sys/kernel/debug/hyperv//fuzz_test_state +Date: October 2019 +KernelVersion: 5.5 +Contact: Branden Bonaby +Description: Fuzz testing status of a vmbus device, whether its in an ON + state or a OFF state +Users: Debugging tools + +What: /sys/kernel/debug/hyperv//delay/fuzz_test_buffer_interrupt_delay +Date: October 2019 +KernelVersion: 5.5 +Contact: Branden Bonaby +Description: Fuzz testing buffer interrupt delay value between 0 - 1000 + microseconds (inclusive). +Users: Debugging tools + +What: /sys/kernel/debug/hyperv//delay/fuzz_test_message_delay +Date: October 2019 +KernelVersion: 5.5 +Contact: Branden Bonaby +Description: Fuzz testing message delay value between 0 - 1000 microseconds + (inclusive). +Users: Debugging tools diff --git a/MAINTAINERS b/MAINTAINERS index cba1095547fd..e7febfbf44ab 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7578,6 +7578,7 @@ F: include/uapi/linux/hyperv.h F: include/asm-generic/mshyperv.h F: tools/hv/ F: Documentation/ABI/stable/sysfs-bus-vmbus +F: Documentation/ABI/testing/debugfs-hyperv HYPERBUS SUPPORT M: Vignesh Raghavendra diff --git a/drivers/hv/Makefile b/drivers/hv/Makefile index a1eec7177c2d..94daf8240c95 100644 --- a/drivers/hv/Makefile +++ b/drivers/hv/Makefile @@ -9,4 +9,5 @@ CFLAGS_hv_balloon.o = -I$(src) hv_vmbus-y := vmbus_drv.o \ hv.o connection.o channel.o \ channel_mgmt.o ring_buffer.o hv_trace.o +hv_vmbus-$(CONFIG_HYPERV_TESTING) += hv_debugfs.o hv_utils-y := hv_util.o hv_kvp.o hv_snapshot.o hv_fcopy.o hv_utils_transport.o diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index 0475be4356dd..e947c39d4cc7 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -363,6 +363,7 @@ void vmbus_on_event(unsigned long data) trace_vmbus_on_event(channel); + hv_debug_delay_test(channel, INTERRUPT_DELAY); do { void (*callback_fn)(void *); diff --git a/drivers/hv/hv_debugfs.c b/drivers/hv/hv_debugfs.c new file mode 100644 index 000000000000..8a2878573582 --- /dev/null +++ b/drivers/hv/hv_debugfs.c @@ -0,0 +1,178 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Authors: + * Branden Bonaby + */ + +#include +#include +#include +#include + +#include "hyperv_vmbus.h" + +struct dentry *hv_debug_root; + +static int hv_debugfs_delay_get(void *data, u64 *val) +{ + *val = *(u32 *)data; + return 0; +} + +static int hv_debugfs_delay_set(void *data, u64 val) +{ + if (val > 1000) + return -EINVAL; + *(u32 *)data = val; + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(hv_debugfs_delay_fops, hv_debugfs_delay_get, + hv_debugfs_delay_set, "%llu\n"); + +static int hv_debugfs_state_get(void *data, u64 *val) +{ + *val = *(bool *)data; + return 0; +} + +static int hv_debugfs_state_set(void *data, u64 val) +{ + if (val == 1) + *(bool *)data = true; + else if (val == 0) + *(bool *)data = false; + else + return -EINVAL; + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(hv_debugfs_state_fops, hv_debugfs_state_get, + hv_debugfs_state_set, "%llu\n"); + +/* Setup delay files to store test values */ +static int hv_debug_delay_files(struct hv_device *dev, struct dentry *root) +{ + struct vmbus_channel *channel = dev->channel; + char *buffer = "fuzz_test_buffer_interrupt_delay"; + char *message = "fuzz_test_message_delay"; + int *buffer_val = &channel->fuzz_testing_interrupt_delay; + int *message_val = &channel->fuzz_testing_message_delay; + struct dentry *buffer_file, *message_file; + + buffer_file = debugfs_create_file(buffer, 0644, root, + buffer_val, + &hv_debugfs_delay_fops); + if (IS_ERR(buffer_file)) { + pr_debug("debugfs_hyperv: file %s not created\n", buffer); + return PTR_ERR(buffer_file); + } + + message_file = debugfs_create_file(message, 0644, root, + message_val, + &hv_debugfs_delay_fops); + if (IS_ERR(message_file)) { + pr_debug("debugfs_hyperv: file %s not created\n", message); + return PTR_ERR(message_file); + } + + return 0; +} + +/* Setup test state value for vmbus device */ +static int hv_debug_set_test_state(struct hv_device *dev, struct dentry *root) +{ + struct vmbus_channel *channel = dev->channel; + bool *state = &channel->fuzz_testing_state; + char *status = "fuzz_test_state"; + struct dentry *test_state; + + test_state = debugfs_create_file(status, 0644, root, + state, + &hv_debugfs_state_fops); + if (IS_ERR(test_state)) { + pr_debug("debugfs_hyperv: file %s not created\n", status); + return PTR_ERR(test_state); + } + + return 0; +} + +/* Bind hv device to a dentry for debugfs */ +static void hv_debug_set_dir_dentry(struct hv_device *dev, struct dentry *root) +{ + if (hv_debug_root) + dev->debug_dir = root; +} + +/* Create all test dentry's and names for fuzz testing */ +int hv_debug_add_dev_dir(struct hv_device *dev) +{ + const char *device = dev_name(&dev->device); + char *delay_name = "delay"; + struct dentry *delay, *dev_root; + int ret; + + if (!IS_ERR(hv_debug_root)) { + dev_root = debugfs_create_dir(device, hv_debug_root); + if (IS_ERR(dev_root)) { + pr_debug("debugfs_hyperv: hyperv/%s/ not created\n", + device); + return PTR_ERR(dev_root); + } + hv_debug_set_test_state(dev, dev_root); + hv_debug_set_dir_dentry(dev, dev_root); + delay = debugfs_create_dir(delay_name, dev_root); + + if (IS_ERR(delay)) { + pr_debug("debugfs_hyperv: hyperv/%s/%s/ not created\n", + device, delay_name); + return PTR_ERR(delay); + } + ret = hv_debug_delay_files(dev, delay); + + return ret; + } + pr_debug("debugfs_hyperv: hyperv/ not in root debugfs path\n"); + return PTR_ERR(hv_debug_root); +} + +/* Remove dentry associated with released hv device */ +void hv_debug_rm_dev_dir(struct hv_device *dev) +{ + if (!IS_ERR(hv_debug_root)) + debugfs_remove_recursive(dev->debug_dir); +} + +/* Remove all dentrys associated with vmbus testing */ +void hv_debug_rm_all_dir(void) +{ + debugfs_remove_recursive(hv_debug_root); +} + +/* Delay buffer/message reads on a vmbus channel */ +void hv_debug_delay_test(struct vmbus_channel *channel, enum delay delay_type) +{ + struct vmbus_channel *test_channel = channel->primary_channel ? + channel->primary_channel : + channel; + bool state = test_channel->fuzz_testing_state; + + if (state) { + if (delay_type == 0) + udelay(test_channel->fuzz_testing_interrupt_delay); + else + udelay(test_channel->fuzz_testing_message_delay); + } +} + +/* Initialize top dentry for vmbus testing */ +int hv_debug_init(void) +{ + hv_debug_root = debugfs_create_dir("hyperv", NULL); + if (IS_ERR(hv_debug_root)) { + pr_debug("debugfs_hyperv: hyperv/ not created\n"); + return PTR_ERR(hv_debug_root); + } + return 0; +} diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index af9379a3bf89..20edcfd3b96c 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -385,4 +385,35 @@ enum hvutil_device_state { HVUTIL_DEVICE_DYING, /* driver unload is in progress */ }; +enum delay { + INTERRUPT_DELAY = 0, + MESSAGE_DELAY = 1, +}; + +#ifdef CONFIG_HYPERV_TESTING + +int hv_debug_add_dev_dir(struct hv_device *dev); +void hv_debug_rm_dev_dir(struct hv_device *dev); +void hv_debug_rm_all_dir(void); +int hv_debug_init(void); +void hv_debug_delay_test(struct vmbus_channel *channel, enum delay delay_type); + +#else /* CONFIG_HYPERV_TESTING */ + +static inline void hv_debug_rm_dev_dir(struct hv_device *dev) {}; +static inline void hv_debug_rm_all_dir(void) {}; +static inline void hv_debug_delay_test(struct vmbus_channel *channel, + enum delay delay_type) {}; +static inline int hv_debug_init(void) +{ + return -1; +} + +static inline int hv_debug_add_dev_dir(struct hv_device *dev) +{ + return -1; +} + +#endif /* CONFIG_HYPERV_TESTING */ + #endif /* _HYPERV_VMBUS_H */ diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 9a03b163cbbd..356e22159e83 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -396,6 +396,7 @@ struct vmpacket_descriptor *hv_pkt_iter_first(struct vmbus_channel *channel) struct hv_ring_buffer_info *rbi = &channel->inbound; struct vmpacket_descriptor *desc; + hv_debug_delay_test(channel, MESSAGE_DELAY); if (hv_pkt_iter_avail(rbi) < sizeof(struct vmpacket_descriptor)) return NULL; @@ -421,6 +422,7 @@ __hv_pkt_iter_next(struct vmbus_channel *channel, u32 packetlen = desc->len8 << 3; u32 dsize = rbi->ring_datasize; + hv_debug_delay_test(channel, MESSAGE_DELAY); /* bump offset to next potential packet */ rbi->priv_read_index += packetlen + VMBUS_PKT_TRAILER; if (rbi->priv_read_index >= dsize) diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 0ac874faf720..125991820278 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -960,6 +960,8 @@ static void vmbus_device_release(struct device *device) struct hv_device *hv_dev = device_to_hv_device(device); struct vmbus_channel *channel = hv_dev->channel; + hv_debug_rm_dev_dir(hv_dev); + mutex_lock(&vmbus_connection.channel_mutex); hv_process_channel_removal(channel); mutex_unlock(&vmbus_connection.channel_mutex); @@ -1814,6 +1816,7 @@ int vmbus_device_register(struct hv_device *child_device_obj) pr_err("Unable to register primary channeln"); goto err_kset_unregister; } + hv_debug_add_dev_dir(child_device_obj); return 0; @@ -2374,6 +2377,7 @@ static int __init hv_acpi_init(void) ret = -ETIMEDOUT; goto cleanup; } + hv_debug_init(); ret = vmbus_bus_init(); if (ret) @@ -2410,6 +2414,8 @@ static void __exit vmbus_exit(void) tasklet_kill(&hv_cpu->msg_dpc); } + hv_debug_rm_all_dir(); + vmbus_free_channels(); if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) { diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index f17f2cd22e39..26f3aeeae1ca 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -934,6 +934,21 @@ struct vmbus_channel { * full outbound ring buffer. */ u64 out_full_first; + + /* enabling/disabling fuzz testing on the channel (default is false)*/ + bool fuzz_testing_state; + + /* + * Interrupt delay will delay the guest from emptying the ring buffer + * for a specific amount of time. The delay is in microseconds and will + * be between 1 to a maximum of 1000, its default is 0 (no delay). + * The Message delay will delay guest reading on a per message basis + * in microseconds between 1 to 1000 with the default being 0 + * (no delay). + */ + u32 fuzz_testing_interrupt_delay; + u32 fuzz_testing_message_delay; + }; static inline bool is_hvsock_channel(const struct vmbus_channel *c) @@ -1182,6 +1197,10 @@ struct hv_device { struct vmbus_channel *channel; struct kset *channels_kset; + + /* place holder to keep track of the dir for hv device in debugfs */ + struct dentry *debug_dir; + }; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 93d97f9b0157..55eebbc0b0fb 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2127,4 +2127,11 @@ config IO_STRICT_DEVMEM source "arch/$(SRCARCH)/Kconfig.debug" +config HYPERV_TESTING + bool "Microsoft Hyper-V driver testing" + default n + depends on HYPERV && DEBUG_FS + help + Select this option to enable Hyper-V vmbus testing. + endmenu # Kernel hacking -- cgit v1.2.3-71-gd317 From 30aad41721e087babcf27c5192474724d555936c Mon Sep 17 00:00:00 2001 From: Danit Goldberg Date: Wed, 6 Nov 2019 15:30:07 +0200 Subject: net/core: Add support for getting VF GUIDs Introduce a new ndo: ndo_get_vf_guid, to get from the net device the port and node GUID. New applications can choose to use this interface to show GUIDs with iproute2 with commands such as: - ip link show ib4 ib4: mtu 4092 qdisc noop state DOWN mode DEFAULT group default qlen 256 link/infiniband 00:00:0a:2d:fe:80:00:00:00:00:00:00:ec:0d:9a:03:00:44:36:8d brd 00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff vf 0 link/infiniband 00:00:0a:2d:fe:80:00:00:00:00:00:00:ec:0d:9a:03:00:44:36:8d brd 00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff, spoof checking off, NODE_GUID 22:44:33:00:33:11:00:33, PORT_GUID 10:21:33:12:00:11:22:10, link-state disable, trust off, query_rss off Signed-off-by: Danit Goldberg Acked-by: David Ahern Signed-off-by: Leon Romanovsky --- include/linux/netdevice.h | 4 ++++ net/core/rtnetlink.c | 14 ++++++++++++++ 2 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9eda1c31d1f7..379338239e49 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1316,6 +1316,10 @@ struct net_device_ops { struct nlattr *port[]); int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); + int (*ndo_get_vf_guid)(struct net_device *dev, + int vf, + struct ifla_vf_guid *node_guid, + struct ifla_vf_guid *port_guid); int (*ndo_set_vf_guid)(struct net_device *dev, int vf, u64 guid, int guid_type); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 1ee6460f8275..93791dad3e31 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1204,6 +1204,8 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, struct ifla_vf_mac vf_mac; struct ifla_vf_broadcast vf_broadcast; struct ifla_vf_info ivi; + struct ifla_vf_guid node_guid; + struct ifla_vf_guid port_guid; memset(&ivi, 0, sizeof(ivi)); @@ -1270,6 +1272,18 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, nla_put(skb, IFLA_VF_TRUST, sizeof(vf_trust), &vf_trust)) goto nla_put_vf_failure; + + memset(&node_guid, 0, sizeof(node_guid)); + memset(&port_guid, 0, sizeof(port_guid)); + if (dev->netdev_ops->ndo_get_vf_guid && + !dev->netdev_ops->ndo_get_vf_guid(dev, vfs_num, &node_guid, + &port_guid)) { + if (nla_put(skb, IFLA_VF_IB_NODE_GUID, sizeof(node_guid), + &node_guid) || + nla_put(skb, IFLA_VF_IB_PORT_GUID, sizeof(port_guid), + &port_guid)) + goto nla_put_vf_failure; + } vfvlanlist = nla_nest_start_noflag(skb, IFLA_VF_VLAN_LIST); if (!vfvlanlist) goto nla_put_vf_failure; -- cgit v1.2.3-71-gd317 From 677bf08cfdf9ee411c2084157f15d85edb09a81a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 21 Nov 2019 06:56:23 +0100 Subject: udp: drop skb extensions before marking skb stateless Once udp stack has set the UDP_SKB_IS_STATELESS flag, later skb free assumes all skb head state has been dropped already. This will leak the extension memory in case the skb has extensions other than the ipsec secpath, e.g. bridge nf data. To fix this, set the UDP_SKB_IS_STATELESS flag only if we don't have extensions or if the extension space can be free'd. Fixes: 895b5c9f206eb7d25dc1360a ("netfilter: drop bridge nf reset from nf_reset") Cc: Paolo Abeni Reported-by: Byron Stanoszek Signed-off-by: Florian Westphal Acked-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ++++++ net/ipv4/udp.c | 27 ++++++++++++++++++++++----- 2 files changed, 28 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 64a395c7f689..8688f7adfda7 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4169,12 +4169,18 @@ static inline void skb_ext_reset(struct sk_buff *skb) skb->active_extensions = 0; } } + +static inline bool skb_has_extensions(struct sk_buff *skb) +{ + return unlikely(skb->active_extensions); +} #else static inline void skb_ext_put(struct sk_buff *skb) {} static inline void skb_ext_reset(struct sk_buff *skb) {} static inline void skb_ext_del(struct sk_buff *skb, int unused) {} static inline void __skb_ext_copy(struct sk_buff *d, const struct sk_buff *s) {} static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *s) {} +static inline bool skb_has_extensions(struct sk_buff *skb) { return false; } #endif /* CONFIG_SKB_EXTENSIONS */ static inline void nf_reset_ct(struct sk_buff *skb) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1d58ce829dca..447defbfccdd 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1297,6 +1297,27 @@ out: #define UDP_SKB_IS_STATELESS 0x80000000 +/* all head states (dst, sk, nf conntrack) except skb extensions are + * cleared by udp_rcv(). + * + * We need to preserve secpath, if present, to eventually process + * IP_CMSG_PASSSEC at recvmsg() time. + * + * Other extensions can be cleared. + */ +static bool udp_try_make_stateless(struct sk_buff *skb) +{ + if (!skb_has_extensions(skb)) + return true; + + if (!secpath_exists(skb)) { + skb_ext_reset(skb); + return true; + } + + return false; +} + static void udp_set_dev_scratch(struct sk_buff *skb) { struct udp_dev_scratch *scratch = udp_skb_scratch(skb); @@ -1308,11 +1329,7 @@ static void udp_set_dev_scratch(struct sk_buff *skb) scratch->csum_unnecessary = !!skb_csum_unnecessary(skb); scratch->is_linear = !skb_is_nonlinear(skb); #endif - /* all head states execept sp (dst, sk, nf) are always cleared by - * udp_rcv() and we need to preserve secpath, if present, to eventually - * process IP_CMSG_PASSSEC at recvmsg() time - */ - if (likely(!skb_sec_path(skb))) + if (udp_try_make_stateless(skb)) scratch->_tsize_state |= UDP_SKB_IS_STATELESS; } -- cgit v1.2.3-71-gd317 From a18fab48dbacbb7ff104a13e987778b7995bec07 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Mon, 28 Oct 2019 16:58:53 +0200 Subject: net/mlx5: DR, Add HW bits and definitions for Geneve flex parser Add definition for flex parser tunneling header for Geneve. Signed-off-by: Yevgeny Kliteynik Reviewed-by: Alex Vesker Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h | 13 +++++++++++++ include/linux/mlx5/mlx5_ifc.h | 1 + 2 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h index 6d78b027fe56..1722f4668269 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h @@ -559,6 +559,19 @@ struct mlx5_ifc_ste_flex_parser_tnl_vxlan_gpe_bits { u8 reserved_at_40[0x40]; }; +struct mlx5_ifc_ste_flex_parser_tnl_geneve_bits { + u8 reserved_at_0[0x2]; + u8 geneve_opt_len[0x6]; + u8 geneve_oam[0x1]; + u8 reserved_at_9[0x7]; + u8 geneve_protocol_type[0x10]; + + u8 geneve_vni[0x18]; + u8 reserved_at_38[0x8]; + + u8 reserved_at_40[0x40]; +}; + struct mlx5_ifc_ste_general_purpose_bits { u8 general_purpose_lookup_field[0x20]; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 4f912d4e67bc..5d54fccf87fc 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1110,6 +1110,7 @@ enum { }; enum { + MLX5_FLEX_PARSER_GENEVE_ENABLED = 1 << 3, MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED = 1 << 7, MLX5_FLEX_PARSER_ICMP_V4_ENABLED = 1 << 8, MLX5_FLEX_PARSER_ICMP_V6_ENABLED = 1 << 9, -- cgit v1.2.3-71-gd317 From b41db132821fdad9d80a177344a47468791fbe62 Mon Sep 17 00:00:00 2001 From: "Enrico Weigelt, metux IT consult" Date: Thu, 21 Nov 2019 14:38:15 +0100 Subject: ftrace: Use BIT() macro It's cleaner to use the BIT() macro instead of raw shift operation. Link: http://lkml.kernel.org/r/20191121133815.15040-1-info@metux.net Signed-off-by: Enrico Weigelt, metux IT consult [ Added BIT() for bits 16 and 17 ] Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index af79b0f8cdc1..232806d5689d 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -149,24 +149,24 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops); * (internal ftrace only, should not be used by others) */ enum { - FTRACE_OPS_FL_ENABLED = 1 << 0, - FTRACE_OPS_FL_DYNAMIC = 1 << 1, - FTRACE_OPS_FL_SAVE_REGS = 1 << 2, - FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED = 1 << 3, - FTRACE_OPS_FL_RECURSION_SAFE = 1 << 4, - FTRACE_OPS_FL_STUB = 1 << 5, - FTRACE_OPS_FL_INITIALIZED = 1 << 6, - FTRACE_OPS_FL_DELETED = 1 << 7, - FTRACE_OPS_FL_ADDING = 1 << 8, - FTRACE_OPS_FL_REMOVING = 1 << 9, - FTRACE_OPS_FL_MODIFYING = 1 << 10, - FTRACE_OPS_FL_ALLOC_TRAMP = 1 << 11, - FTRACE_OPS_FL_IPMODIFY = 1 << 12, - FTRACE_OPS_FL_PID = 1 << 13, - FTRACE_OPS_FL_RCU = 1 << 14, - FTRACE_OPS_FL_TRACE_ARRAY = 1 << 15, - FTRACE_OPS_FL_PERMANENT = 1 << 16, - FTRACE_OPS_FL_DIRECT = 1 << 17, + FTRACE_OPS_FL_ENABLED = BIT(0), + FTRACE_OPS_FL_DYNAMIC = BIT(1), + FTRACE_OPS_FL_SAVE_REGS = BIT(2), + FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED = BIT(3), + FTRACE_OPS_FL_RECURSION_SAFE = BIT(4), + FTRACE_OPS_FL_STUB = BIT(5), + FTRACE_OPS_FL_INITIALIZED = BIT(6), + FTRACE_OPS_FL_DELETED = BIT(7), + FTRACE_OPS_FL_ADDING = BIT(8), + FTRACE_OPS_FL_REMOVING = BIT(9), + FTRACE_OPS_FL_MODIFYING = BIT(10), + FTRACE_OPS_FL_ALLOC_TRAMP = BIT(11), + FTRACE_OPS_FL_IPMODIFY = BIT(12), + FTRACE_OPS_FL_PID = BIT(13), + FTRACE_OPS_FL_RCU = BIT(14), + FTRACE_OPS_FL_TRACE_ARRAY = BIT(15), + FTRACE_OPS_FL_PERMANENT = BIT(16), + FTRACE_OPS_FL_DIRECT = BIT(17), }; #ifdef CONFIG_DYNAMIC_FTRACE -- cgit v1.2.3-71-gd317 From 28879787147358e8ffcae397f11748de3dd26577 Mon Sep 17 00:00:00 2001 From: Divya Indi Date: Wed, 20 Nov 2019 11:08:38 -0800 Subject: tracing: Adding new functions for kernel access to Ftrace instances Adding 2 new functions - 1) struct trace_array *trace_array_get_by_name(const char *name); Return pointer to a trace array with given name. If it does not exist, create and return pointer to the new trace array. 2) int trace_array_set_clr_event(struct trace_array *tr, const char *system ,const char *event, bool enable); Enable/Disable events to this trace array. Additionally, - To handle reference counters, export trace_array_put() - Due to introduction of the above 2 new functions, we no longer need to export - ftrace_set_clr_event & trace_array_create APIs. Link: http://lkml.kernel.org/r/1574276919-11119-2-git-send-email-divya.indi@oracle.com Signed-off-by: Divya Indi Reviewed-by: Aruna Ramakrishna Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace.h | 3 +- include/linux/trace_events.h | 3 +- kernel/trace/trace.c | 96 +++++++++++++++++++++++++++++++++++--------- kernel/trace/trace.h | 1 - kernel/trace/trace_events.c | 27 ++++++++++++- 5 files changed, 106 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace.h b/include/linux/trace.h index 24fcf07812ae..7fd86d3c691f 100644 --- a/include/linux/trace.h +++ b/include/linux/trace.h @@ -29,7 +29,8 @@ struct trace_array; void trace_printk_init_buffers(void); int trace_array_printk(struct trace_array *tr, unsigned long ip, const char *fmt, ...); -struct trace_array *trace_array_create(const char *name); +void trace_array_put(struct trace_array *tr); +struct trace_array *trace_array_get_by_name(const char *name); int trace_array_destroy(struct trace_array *tr); #endif /* CONFIG_TRACING */ diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 60a41b7069dd..4c6e15605766 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -555,7 +555,8 @@ extern int trace_event_get_offsets(struct trace_event_call *call); int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set); int trace_set_clr_event(const char *system, const char *event, int set); - +int trace_array_set_clr_event(struct trace_array *tr, const char *system, + const char *event, bool enable); /* * The double __builtin_constant_p is because gcc will give us an error * if we try to allocate the static variable to fmt if it is not a diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 42659ce6ac0c..02a23a6e5e00 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -301,12 +301,24 @@ static void __trace_array_put(struct trace_array *this_tr) this_tr->ref--; } +/** + * trace_array_put - Decrement the reference counter for this trace array. + * + * NOTE: Use this when we no longer need the trace array returned by + * trace_array_get_by_name(). This ensures the trace array can be later + * destroyed. + * + */ void trace_array_put(struct trace_array *this_tr) { + if (!this_tr) + return; + mutex_lock(&trace_types_lock); __trace_array_put(this_tr); mutex_unlock(&trace_types_lock); } +EXPORT_SYMBOL_GPL(trace_array_put); int tracing_check_open_get_tr(struct trace_array *tr) { @@ -8437,24 +8449,15 @@ static void update_tracer_options(struct trace_array *tr) mutex_unlock(&trace_types_lock); } -struct trace_array *trace_array_create(const char *name) +static struct trace_array *trace_array_create(const char *name) { struct trace_array *tr; int ret; - mutex_lock(&event_mutex); - mutex_lock(&trace_types_lock); - - ret = -EEXIST; - list_for_each_entry(tr, &ftrace_trace_arrays, list) { - if (tr->name && strcmp(tr->name, name) == 0) - goto out_unlock; - } - ret = -ENOMEM; tr = kzalloc(sizeof(*tr), GFP_KERNEL); if (!tr) - goto out_unlock; + return ERR_PTR(ret); tr->name = kstrdup(name, GFP_KERNEL); if (!tr->name) @@ -8499,8 +8502,8 @@ struct trace_array *trace_array_create(const char *name) list_add(&tr->list, &ftrace_trace_arrays); - mutex_unlock(&trace_types_lock); - mutex_unlock(&event_mutex); + tr->ref++; + return tr; @@ -8510,24 +8513,77 @@ struct trace_array *trace_array_create(const char *name) kfree(tr->name); kfree(tr); - out_unlock: - mutex_unlock(&trace_types_lock); - mutex_unlock(&event_mutex); - return ERR_PTR(ret); } -EXPORT_SYMBOL_GPL(trace_array_create); static int instance_mkdir(const char *name) { - return PTR_ERR_OR_ZERO(trace_array_create(name)); + struct trace_array *tr; + int ret; + + mutex_lock(&event_mutex); + mutex_lock(&trace_types_lock); + + ret = -EEXIST; + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (tr->name && strcmp(tr->name, name) == 0) + goto out_unlock; + } + + tr = trace_array_create(name); + + ret = PTR_ERR_OR_ZERO(tr); + +out_unlock: + mutex_unlock(&trace_types_lock); + mutex_unlock(&event_mutex); + return ret; +} + +/** + * trace_array_get_by_name - Create/Lookup a trace array, given its name. + * @name: The name of the trace array to be looked up/created. + * + * Returns pointer to trace array with given name. + * NULL, if it cannot be created. + * + * NOTE: This function increments the reference counter associated with the + * trace array returned. This makes sure it cannot be freed while in use. + * Use trace_array_put() once the trace array is no longer needed. + * + */ +struct trace_array *trace_array_get_by_name(const char *name) +{ + struct trace_array *tr; + + mutex_lock(&event_mutex); + mutex_lock(&trace_types_lock); + + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (tr->name && strcmp(tr->name, name) == 0) + goto out_unlock; + } + + tr = trace_array_create(name); + + if (IS_ERR(tr)) + tr = NULL; +out_unlock: + if (tr) + tr->ref++; + + mutex_unlock(&trace_types_lock); + mutex_unlock(&event_mutex); + return tr; } +EXPORT_SYMBOL_GPL(trace_array_get_by_name); static int __remove_instance(struct trace_array *tr) { int i; - if (tr->ref || (tr->current_trace && tr->current_trace->ref)) + /* Reference counter for a newly created trace array = 1. */ + if (tr->ref > 1 || (tr->current_trace && tr->current_trace->ref)) return -EBUSY; list_del(&tr->list); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 2df8aed6a8f0..ca7fccafbcbb 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -345,7 +345,6 @@ extern struct list_head ftrace_trace_arrays; extern struct mutex trace_types_lock; extern int trace_array_get(struct trace_array *tr); -extern void trace_array_put(struct trace_array *tr); extern int tracing_check_open_get_tr(struct trace_array *tr); extern int tracing_set_time_stamp_abs(struct trace_array *tr, bool abs); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 2a3ac2365445..6b3a69e9aa6a 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -827,7 +827,6 @@ int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set) return ret; } -EXPORT_SYMBOL_GPL(ftrace_set_clr_event); /** * trace_set_clr_event - enable or disable an event @@ -852,6 +851,32 @@ int trace_set_clr_event(const char *system, const char *event, int set) } EXPORT_SYMBOL_GPL(trace_set_clr_event); +/** + * trace_array_set_clr_event - enable or disable an event for a trace array. + * @tr: concerned trace array. + * @system: system name to match (NULL for any system) + * @event: event name to match (NULL for all events, within system) + * @enable: true to enable, false to disable + * + * This is a way for other parts of the kernel to enable or disable + * event recording. + * + * Returns 0 on success, -EINVAL if the parameters do not match any + * registered events. + */ +int trace_array_set_clr_event(struct trace_array *tr, const char *system, + const char *event, bool enable) +{ + int set; + + if (!tr) + return -ENOENT; + + set = (enable == true) ? 1 : 0; + return __ftrace_set_clr_event(tr, NULL, system, event, set); +} +EXPORT_SYMBOL_GPL(trace_array_set_clr_event); + /* 128 should be much more than enough */ #define EVENT_BUF_SIZE 127 -- cgit v1.2.3-71-gd317 From 84bb46cd62283cc371769ec1f77ff7924099f584 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sat, 23 Nov 2019 09:54:58 -0800 Subject: Revert "bpf: Emit audit messages upon successful prog load and unload" This commit reverts commit 91e6015b082b ("bpf: Emit audit messages upon successful prog load and unload") and its follow up commit 7599a896f2e4 ("audit: Move audit_log_task declaration under CONFIG_AUDITSYSCALL") as requested by Paul Moore. The change needs close review on linux-audit, tests etc. Signed-off-by: Jakub Kicinski --- include/linux/audit.h | 5 ----- include/uapi/linux/audit.h | 1 - kernel/auditsc.c | 2 +- kernel/bpf/syscall.c | 31 ------------------------------- 4 files changed, 1 insertion(+), 38 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 18925d924c73..aee3dc9eb378 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -358,8 +358,6 @@ static inline void audit_ptrace(struct task_struct *t) __audit_ptrace(t); } -extern void audit_log_task(struct audit_buffer *ab); - /* Private API (for audit.c only) */ extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp); extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode); @@ -647,9 +645,6 @@ static inline void audit_ntp_log(const struct audit_ntp_data *ad) static inline void audit_ptrace(struct task_struct *t) { } - -static inline void audit_log_task(struct audit_buffer *ab) -{ } #define audit_n_rules 0 #define audit_signals 0 #endif /* CONFIG_AUDITSYSCALL */ diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index 32a5db900f47..c89c6495983d 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -116,7 +116,6 @@ #define AUDIT_FANOTIFY 1331 /* Fanotify access decision */ #define AUDIT_TIME_INJOFFSET 1332 /* Timekeeping offset injected */ #define AUDIT_TIME_ADJNTPVAL 1333 /* NTP value adjustment */ -#define AUDIT_BPF 1334 /* BPF subsystem */ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 9bf1045fedfa..4effe01ebbe2 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -2545,7 +2545,7 @@ void __audit_ntp_log(const struct audit_ntp_data *ad) audit_log_ntp_val(ad, "adjust", AUDIT_NTP_ADJUST); } -void audit_log_task(struct audit_buffer *ab) +static void audit_log_task(struct audit_buffer *ab) { kuid_t auid, uid; kgid_t gid; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b51ecb9644d0..4ae52eb05f41 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -23,7 +23,6 @@ #include #include #include -#include #include #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \ @@ -1322,34 +1321,6 @@ static void free_used_maps(struct bpf_prog_aux *aux) kfree(aux->used_maps); } -enum bpf_event { - BPF_EVENT_LOAD, - BPF_EVENT_UNLOAD, -}; - -static const char * const bpf_event_audit_str[] = { - [BPF_EVENT_LOAD] = "LOAD", - [BPF_EVENT_UNLOAD] = "UNLOAD", -}; - -static void bpf_audit_prog(const struct bpf_prog *prog, enum bpf_event event) -{ - bool has_task_context = event == BPF_EVENT_LOAD; - struct audit_buffer *ab; - - if (audit_enabled == AUDIT_OFF) - return; - ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_BPF); - if (unlikely(!ab)) - return; - if (has_task_context) - audit_log_task(ab); - audit_log_format(ab, "%sprog-id=%u event=%s", - has_task_context ? " " : "", - prog->aux->id, bpf_event_audit_str[event]); - audit_log_end(ab); -} - int __bpf_prog_charge(struct user_struct *user, u32 pages) { unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; @@ -1466,7 +1437,6 @@ static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) { if (atomic64_dec_and_test(&prog->aux->refcnt)) { perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0); - bpf_audit_prog(prog, BPF_EVENT_UNLOAD); /* bpf_prog_free_id() must be called first */ bpf_prog_free_id(prog, do_idr_lock); __bpf_prog_put_noref(prog, true); @@ -1876,7 +1846,6 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) */ bpf_prog_kallsyms_add(prog); perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_LOAD, 0); - bpf_audit_prog(prog, BPF_EVENT_LOAD); err = bpf_prog_new_fd(prog); if (err < 0) -- cgit v1.2.3-71-gd317 From e3cf8b3668a808c1d252269ffc34a5723cfb9a7b Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 22 Nov 2019 12:37:08 +0000 Subject: net: phy: remove phy_ethtool_sset() There are no users of phy_ethtool_sset() in the kernel anymore, and as of commit 3c1bcc8614db ("net: ethernet: Convert phydev advertize and supported from u32 to link mode"), the implementation is slightly buggy - it doesn't correctly check the masked advertising mask as it used to. Remove it, and update the phy documentation to refer to its replacement function. Signed-off-by: Russell King Reviewed-by: Andrew Lunn Signed-off-by: Jakub Kicinski --- Documentation/networking/phy.rst | 3 +- drivers/net/phy/phy.c | 60 ---------------------------------------- include/linux/phy.h | 1 - 3 files changed, 2 insertions(+), 62 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/phy.rst b/Documentation/networking/phy.rst index a689966bc4be..cda1c0a0492a 100644 --- a/Documentation/networking/phy.rst +++ b/Documentation/networking/phy.rst @@ -352,7 +352,8 @@ Fills the phydev structure with up-to-date information about the current settings in the PHY. :: - int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd); + int phy_ethtool_ksettings_set(struct phy_device *phydev, + const struct ethtool_link_ksettings *cmd); Ethtool convenience functions. :: diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 36d4ffe1cd3f..80be4d691e5b 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -253,66 +253,6 @@ static void phy_sanitize_settings(struct phy_device *phydev) } } -/** - * phy_ethtool_sset - generic ethtool sset function, handles all the details - * @phydev: target phy_device struct - * @cmd: ethtool_cmd - * - * A few notes about parameter checking: - * - * - We don't set port or transceiver, so we don't care what they - * were set to. - * - phy_start_aneg() will make sure forced settings are sane, and - * choose the next best ones from the ones selected, so we don't - * care if ethtool tries to give us bad values. - */ -int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd) -{ - __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); - u32 speed = ethtool_cmd_speed(cmd); - - if (cmd->phy_address != phydev->mdio.addr) - return -EINVAL; - - /* We make sure that we don't pass unsupported values in to the PHY */ - ethtool_convert_legacy_u32_to_link_mode(advertising, cmd->advertising); - linkmode_and(advertising, advertising, phydev->supported); - - /* Verify the settings we care about. */ - if (cmd->autoneg != AUTONEG_ENABLE && cmd->autoneg != AUTONEG_DISABLE) - return -EINVAL; - - if (cmd->autoneg == AUTONEG_ENABLE && cmd->advertising == 0) - return -EINVAL; - - if (cmd->autoneg == AUTONEG_DISABLE && - ((speed != SPEED_1000 && - speed != SPEED_100 && - speed != SPEED_10) || - (cmd->duplex != DUPLEX_HALF && - cmd->duplex != DUPLEX_FULL))) - return -EINVAL; - - phydev->autoneg = cmd->autoneg; - - phydev->speed = speed; - - linkmode_copy(phydev->advertising, advertising); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, - phydev->advertising, AUTONEG_ENABLE == cmd->autoneg); - - phydev->duplex = cmd->duplex; - - phydev->mdix_ctrl = cmd->eth_tp_mdix_ctrl; - - /* Restart the PHY */ - phy_start_aneg(phydev); - - return 0; -} -EXPORT_SYMBOL(phy_ethtool_sset); - int phy_ethtool_ksettings_set(struct phy_device *phydev, const struct ethtool_link_ksettings *cmd) { diff --git a/include/linux/phy.h b/include/linux/phy.h index 124516fe2763..f5cdfb206097 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1160,7 +1160,6 @@ void phy_queue_state_machine(struct phy_device *phydev, unsigned long jiffies); void phy_mac_interrupt(struct phy_device *phydev); void phy_start_machine(struct phy_device *phydev); void phy_stop_machine(struct phy_device *phydev); -int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd); void phy_ethtool_ksettings_get(struct phy_device *phydev, struct ethtool_link_ksettings *cmd); int phy_ethtool_ksettings_set(struct phy_device *phydev, -- cgit v1.2.3-71-gd317 From 99cb252f5e68d72afa3245a4e73d216d295cd335 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 12 Nov 2019 16:22:19 -0400 Subject: mm/mmu_notifier: add an interval tree notifier MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Of the 13 users of mmu_notifiers, 8 of them use only invalidate_range_start/end() and immediately intersect the mmu_notifier_range with some kind of internal list of VAs. 4 use an interval tree (i915_gem, radeon_mn, umem_odp, hfi1). 4 use a linked list of some kind (scif_dma, vhost, gntdev, hmm) And the remaining 5 either don't use invalidate_range_start() or do some special thing with it. It turns out that building a correct scheme with an interval tree is pretty complicated, particularly if the use case is synchronizing against another thread doing get_user_pages(). Many of these implementations have various subtle and difficult to fix races. This approach puts the interval tree as common code at the top of the mmu notifier call tree and implements a shareable locking scheme. It includes: - An interval tree tracking VA ranges, with per-range callbacks - A read/write locking scheme for the interval tree that avoids sleeping in the notifier path (for OOM killer) - A sequence counter based collision-retry locking scheme to tell device page fault that a VA range is being concurrently invalidated. This is based on various ideas: - hmm accumulates invalidated VA ranges and releases them when all invalidates are done, via active_invalidate_ranges count. This approach avoids having to intersect the interval tree twice (as umem_odp does) at the potential cost of a longer device page fault. - kvm/umem_odp use a sequence counter to drive the collision retry, via invalidate_seq - a deferred work todo list on unlock scheme like RTNL, via deferred_list. This makes adding/removing interval tree members more deterministic - seqlock, except this version makes the seqlock idea multi-holder on the write side by protecting it with active_invalidate_ranges and a spinlock To minimize MM overhead when only the interval tree is being used, the entire SRCU and hlist overheads are dropped using some simple branches. Similarly the interval tree overhead is dropped when in hlist mode. The overhead from the mandatory spinlock is broadly the same as most of existing users which already had a lock (or two) of some sort on the invalidation path. Link: https://lore.kernel.org/r/20191112202231.3856-3-jgg@ziepe.ca Acked-by: Christian König Tested-by: Philip Yang Tested-by: Ralph Campbell Reviewed-by: John Hubbard Reviewed-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe --- include/linux/mmu_notifier.h | 101 ++++++++ mm/Kconfig | 1 + mm/mmu_notifier.c | 544 ++++++++++++++++++++++++++++++++++++++++--- 3 files changed, 620 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 12bd603d318c..9e6caa8ecd19 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -6,10 +6,12 @@ #include #include #include +#include struct mmu_notifier_mm; struct mmu_notifier; struct mmu_notifier_range; +struct mmu_interval_notifier; /** * enum mmu_notifier_event - reason for the mmu notifier callback @@ -32,6 +34,9 @@ struct mmu_notifier_range; * access flags). User should soft dirty the page in the end callback to make * sure that anyone relying on soft dirtyness catch pages that might be written * through non CPU mappings. + * + * @MMU_NOTIFY_RELEASE: used during mmu_interval_notifier invalidate to signal + * that the mm refcount is zero and the range is no longer accessible. */ enum mmu_notifier_event { MMU_NOTIFY_UNMAP = 0, @@ -39,6 +44,7 @@ enum mmu_notifier_event { MMU_NOTIFY_PROTECTION_VMA, MMU_NOTIFY_PROTECTION_PAGE, MMU_NOTIFY_SOFT_DIRTY, + MMU_NOTIFY_RELEASE, }; #define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0) @@ -222,6 +228,26 @@ struct mmu_notifier { unsigned int users; }; +/** + * struct mmu_interval_notifier_ops + * @invalidate: Upon return the caller must stop using any SPTEs within this + * range. This function can sleep. Return false only if sleeping + * was required but mmu_notifier_range_blockable(range) is false. + */ +struct mmu_interval_notifier_ops { + bool (*invalidate)(struct mmu_interval_notifier *mni, + const struct mmu_notifier_range *range, + unsigned long cur_seq); +}; + +struct mmu_interval_notifier { + struct interval_tree_node interval_tree; + const struct mmu_interval_notifier_ops *ops; + struct mm_struct *mm; + struct hlist_node deferred_item; + unsigned long invalidate_seq; +}; + #ifdef CONFIG_MMU_NOTIFIER #ifdef CONFIG_LOCKDEP @@ -263,6 +289,81 @@ extern int __mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm); extern void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm); + +unsigned long mmu_interval_read_begin(struct mmu_interval_notifier *mni); +int mmu_interval_notifier_insert(struct mmu_interval_notifier *mni, + struct mm_struct *mm, unsigned long start, + unsigned long length, + const struct mmu_interval_notifier_ops *ops); +int mmu_interval_notifier_insert_locked( + struct mmu_interval_notifier *mni, struct mm_struct *mm, + unsigned long start, unsigned long length, + const struct mmu_interval_notifier_ops *ops); +void mmu_interval_notifier_remove(struct mmu_interval_notifier *mni); + +/** + * mmu_interval_set_seq - Save the invalidation sequence + * @mni - The mni passed to invalidate + * @cur_seq - The cur_seq passed to the invalidate() callback + * + * This must be called unconditionally from the invalidate callback of a + * struct mmu_interval_notifier_ops under the same lock that is used to call + * mmu_interval_read_retry(). It updates the sequence number for later use by + * mmu_interval_read_retry(). The provided cur_seq will always be odd. + * + * If the caller does not call mmu_interval_read_begin() or + * mmu_interval_read_retry() then this call is not required. + */ +static inline void mmu_interval_set_seq(struct mmu_interval_notifier *mni, + unsigned long cur_seq) +{ + WRITE_ONCE(mni->invalidate_seq, cur_seq); +} + +/** + * mmu_interval_read_retry - End a read side critical section against a VA range + * mni: The range + * seq: The return of the paired mmu_interval_read_begin() + * + * This MUST be called under a user provided lock that is also held + * unconditionally by op->invalidate() when it calls mmu_interval_set_seq(). + * + * Each call should be paired with a single mmu_interval_read_begin() and + * should be used to conclude the read side. + * + * Returns true if an invalidation collided with this critical section, and + * the caller should retry. + */ +static inline bool mmu_interval_read_retry(struct mmu_interval_notifier *mni, + unsigned long seq) +{ + return mni->invalidate_seq != seq; +} + +/** + * mmu_interval_check_retry - Test if a collision has occurred + * mni: The range + * seq: The return of the matching mmu_interval_read_begin() + * + * This can be used in the critical section between mmu_interval_read_begin() + * and mmu_interval_read_retry(). A return of true indicates an invalidation + * has collided with this critical region and a future + * mmu_interval_read_retry() will return true. + * + * False is not reliable and only suggests a collision may not have + * occured. It can be called many times and does not have to hold the user + * provided lock. + * + * This call can be used as part of loops and other expensive operations to + * expedite a retry. + */ +static inline bool mmu_interval_check_retry(struct mmu_interval_notifier *mni, + unsigned long seq) +{ + /* Pairs with the WRITE_ONCE in mmu_interval_set_seq() */ + return READ_ONCE(mni->invalidate_seq) != seq; +} + extern void __mmu_notifier_mm_destroy(struct mm_struct *mm); extern void __mmu_notifier_release(struct mm_struct *mm); extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm, diff --git a/mm/Kconfig b/mm/Kconfig index a5dae9a7eb51..d0b5046d9aef 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -284,6 +284,7 @@ config VIRT_TO_BUS config MMU_NOTIFIER bool select SRCU + select INTERVAL_TREE config KSM bool "Enable KSM for page merging" diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 367670cfd02b..30abbfdc25be 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -36,10 +37,245 @@ struct lockdep_map __mmu_notifier_invalidate_range_start_map = { struct mmu_notifier_mm { /* all mmu notifiers registered in this mm are queued in this list */ struct hlist_head list; + bool has_itree; /* to serialize the list modifications and hlist_unhashed */ spinlock_t lock; + unsigned long invalidate_seq; + unsigned long active_invalidate_ranges; + struct rb_root_cached itree; + wait_queue_head_t wq; + struct hlist_head deferred_list; }; +/* + * This is a collision-retry read-side/write-side 'lock', a lot like a + * seqcount, however this allows multiple write-sides to hold it at + * once. Conceptually the write side is protecting the values of the PTEs in + * this mm, such that PTES cannot be read into SPTEs (shadow PTEs) while any + * writer exists. + * + * Note that the core mm creates nested invalidate_range_start()/end() regions + * within the same thread, and runs invalidate_range_start()/end() in parallel + * on multiple CPUs. This is designed to not reduce concurrency or block + * progress on the mm side. + * + * As a secondary function, holding the full write side also serves to prevent + * writers for the itree, this is an optimization to avoid extra locking + * during invalidate_range_start/end notifiers. + * + * The write side has two states, fully excluded: + * - mm->active_invalidate_ranges != 0 + * - mnn->invalidate_seq & 1 == True (odd) + * - some range on the mm_struct is being invalidated + * - the itree is not allowed to change + * + * And partially excluded: + * - mm->active_invalidate_ranges != 0 + * - mnn->invalidate_seq & 1 == False (even) + * - some range on the mm_struct is being invalidated + * - the itree is allowed to change + * + * Operations on mmu_notifier_mm->invalidate_seq (under spinlock): + * seq |= 1 # Begin writing + * seq++ # Release the writing state + * seq & 1 # True if a writer exists + * + * The later state avoids some expensive work on inv_end in the common case of + * no mni monitoring the VA. + */ +static bool mn_itree_is_invalidating(struct mmu_notifier_mm *mmn_mm) +{ + lockdep_assert_held(&mmn_mm->lock); + return mmn_mm->invalidate_seq & 1; +} + +static struct mmu_interval_notifier * +mn_itree_inv_start_range(struct mmu_notifier_mm *mmn_mm, + const struct mmu_notifier_range *range, + unsigned long *seq) +{ + struct interval_tree_node *node; + struct mmu_interval_notifier *res = NULL; + + spin_lock(&mmn_mm->lock); + mmn_mm->active_invalidate_ranges++; + node = interval_tree_iter_first(&mmn_mm->itree, range->start, + range->end - 1); + if (node) { + mmn_mm->invalidate_seq |= 1; + res = container_of(node, struct mmu_interval_notifier, + interval_tree); + } + + *seq = mmn_mm->invalidate_seq; + spin_unlock(&mmn_mm->lock); + return res; +} + +static struct mmu_interval_notifier * +mn_itree_inv_next(struct mmu_interval_notifier *mni, + const struct mmu_notifier_range *range) +{ + struct interval_tree_node *node; + + node = interval_tree_iter_next(&mni->interval_tree, range->start, + range->end - 1); + if (!node) + return NULL; + return container_of(node, struct mmu_interval_notifier, interval_tree); +} + +static void mn_itree_inv_end(struct mmu_notifier_mm *mmn_mm) +{ + struct mmu_interval_notifier *mni; + struct hlist_node *next; + + spin_lock(&mmn_mm->lock); + if (--mmn_mm->active_invalidate_ranges || + !mn_itree_is_invalidating(mmn_mm)) { + spin_unlock(&mmn_mm->lock); + return; + } + + /* Make invalidate_seq even */ + mmn_mm->invalidate_seq++; + + /* + * The inv_end incorporates a deferred mechanism like rtnl_unlock(). + * Adds and removes are queued until the final inv_end happens then + * they are progressed. This arrangement for tree updates is used to + * avoid using a blocking lock during invalidate_range_start. + */ + hlist_for_each_entry_safe(mni, next, &mmn_mm->deferred_list, + deferred_item) { + if (RB_EMPTY_NODE(&mni->interval_tree.rb)) + interval_tree_insert(&mni->interval_tree, + &mmn_mm->itree); + else + interval_tree_remove(&mni->interval_tree, + &mmn_mm->itree); + hlist_del(&mni->deferred_item); + } + spin_unlock(&mmn_mm->lock); + + wake_up_all(&mmn_mm->wq); +} + +/** + * mmu_interval_read_begin - Begin a read side critical section against a VA + * range + * mni: The range to use + * + * mmu_iterval_read_begin()/mmu_iterval_read_retry() implement a + * collision-retry scheme similar to seqcount for the VA range under mni. If + * the mm invokes invalidation during the critical section then + * mmu_interval_read_retry() will return true. + * + * This is useful to obtain shadow PTEs where teardown or setup of the SPTEs + * require a blocking context. The critical region formed by this can sleep, + * and the required 'user_lock' can also be a sleeping lock. + * + * The caller is required to provide a 'user_lock' to serialize both teardown + * and setup. + * + * The return value should be passed to mmu_interval_read_retry(). + */ +unsigned long mmu_interval_read_begin(struct mmu_interval_notifier *mni) +{ + struct mmu_notifier_mm *mmn_mm = mni->mm->mmu_notifier_mm; + unsigned long seq; + bool is_invalidating; + + /* + * If the mni has a different seq value under the user_lock than we + * started with then it has collided. + * + * If the mni currently has the same seq value as the mmn_mm seq, then + * it is currently between invalidate_start/end and is colliding. + * + * The locking looks broadly like this: + * mn_tree_invalidate_start(): mmu_interval_read_begin(): + * spin_lock + * seq = READ_ONCE(mni->invalidate_seq); + * seq == mmn_mm->invalidate_seq + * spin_unlock + * spin_lock + * seq = ++mmn_mm->invalidate_seq + * spin_unlock + * op->invalidate_range(): + * user_lock + * mmu_interval_set_seq() + * mni->invalidate_seq = seq + * user_unlock + * + * [Required: mmu_interval_read_retry() == true] + * + * mn_itree_inv_end(): + * spin_lock + * seq = ++mmn_mm->invalidate_seq + * spin_unlock + * + * user_lock + * mmu_interval_read_retry(): + * mni->invalidate_seq != seq + * user_unlock + * + * Barriers are not needed here as any races here are closed by an + * eventual mmu_interval_read_retry(), which provides a barrier via the + * user_lock. + */ + spin_lock(&mmn_mm->lock); + /* Pairs with the WRITE_ONCE in mmu_interval_set_seq() */ + seq = READ_ONCE(mni->invalidate_seq); + is_invalidating = seq == mmn_mm->invalidate_seq; + spin_unlock(&mmn_mm->lock); + + /* + * mni->invalidate_seq must always be set to an odd value via + * mmu_interval_set_seq() using the provided cur_seq from + * mn_itree_inv_start_range(). This ensures that if seq does wrap we + * will always clear the below sleep in some reasonable time as + * mmn_mm->invalidate_seq is even in the idle state. + */ + lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); + lock_map_release(&__mmu_notifier_invalidate_range_start_map); + if (is_invalidating) + wait_event(mmn_mm->wq, + READ_ONCE(mmn_mm->invalidate_seq) != seq); + + /* + * Notice that mmu_interval_read_retry() can already be true at this + * point, avoiding loops here allows the caller to provide a global + * time bound. + */ + + return seq; +} +EXPORT_SYMBOL_GPL(mmu_interval_read_begin); + +static void mn_itree_release(struct mmu_notifier_mm *mmn_mm, + struct mm_struct *mm) +{ + struct mmu_notifier_range range = { + .flags = MMU_NOTIFIER_RANGE_BLOCKABLE, + .event = MMU_NOTIFY_RELEASE, + .mm = mm, + .start = 0, + .end = ULONG_MAX, + }; + struct mmu_interval_notifier *mni; + unsigned long cur_seq; + bool ret; + + for (mni = mn_itree_inv_start_range(mmn_mm, &range, &cur_seq); mni; + mni = mn_itree_inv_next(mni, &range)) { + ret = mni->ops->invalidate(mni, &range, cur_seq); + WARN_ON(!ret); + } + + mn_itree_inv_end(mmn_mm); +} + /* * This function can't run concurrently against mmu_notifier_register * because mm->mm_users > 0 during mmu_notifier_register and exit_mmap @@ -52,7 +288,8 @@ struct mmu_notifier_mm { * can't go away from under us as exit_mmap holds an mm_count pin * itself. */ -void __mmu_notifier_release(struct mm_struct *mm) +static void mn_hlist_release(struct mmu_notifier_mm *mmn_mm, + struct mm_struct *mm) { struct mmu_notifier *mn; int id; @@ -62,7 +299,7 @@ void __mmu_notifier_release(struct mm_struct *mm) * ->release returns. */ id = srcu_read_lock(&srcu); - hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) + hlist_for_each_entry_rcu(mn, &mmn_mm->list, hlist) /* * If ->release runs before mmu_notifier_unregister it must be * handled, as it's the only way for the driver to flush all @@ -72,10 +309,9 @@ void __mmu_notifier_release(struct mm_struct *mm) if (mn->ops->release) mn->ops->release(mn, mm); - spin_lock(&mm->mmu_notifier_mm->lock); - while (unlikely(!hlist_empty(&mm->mmu_notifier_mm->list))) { - mn = hlist_entry(mm->mmu_notifier_mm->list.first, - struct mmu_notifier, + spin_lock(&mmn_mm->lock); + while (unlikely(!hlist_empty(&mmn_mm->list))) { + mn = hlist_entry(mmn_mm->list.first, struct mmu_notifier, hlist); /* * We arrived before mmu_notifier_unregister so @@ -85,7 +321,7 @@ void __mmu_notifier_release(struct mm_struct *mm) */ hlist_del_init_rcu(&mn->hlist); } - spin_unlock(&mm->mmu_notifier_mm->lock); + spin_unlock(&mmn_mm->lock); srcu_read_unlock(&srcu, id); /* @@ -100,6 +336,17 @@ void __mmu_notifier_release(struct mm_struct *mm) synchronize_srcu(&srcu); } +void __mmu_notifier_release(struct mm_struct *mm) +{ + struct mmu_notifier_mm *mmn_mm = mm->mmu_notifier_mm; + + if (mmn_mm->has_itree) + mn_itree_release(mmn_mm, mm); + + if (!hlist_empty(&mmn_mm->list)) + mn_hlist_release(mmn_mm, mm); +} + /* * If no young bitflag is supported by the hardware, ->clear_flush_young can * unmap the address and return 1 or 0 depending if the mapping previously @@ -172,14 +419,43 @@ void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, srcu_read_unlock(&srcu, id); } -int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) +static int mn_itree_invalidate(struct mmu_notifier_mm *mmn_mm, + const struct mmu_notifier_range *range) +{ + struct mmu_interval_notifier *mni; + unsigned long cur_seq; + + for (mni = mn_itree_inv_start_range(mmn_mm, range, &cur_seq); mni; + mni = mn_itree_inv_next(mni, range)) { + bool ret; + + ret = mni->ops->invalidate(mni, range, cur_seq); + if (!ret) { + if (WARN_ON(mmu_notifier_range_blockable(range))) + continue; + goto out_would_block; + } + } + return 0; + +out_would_block: + /* + * On -EAGAIN the non-blocking caller is not allowed to call + * invalidate_range_end() + */ + mn_itree_inv_end(mmn_mm); + return -EAGAIN; +} + +static int mn_hlist_invalidate_range_start(struct mmu_notifier_mm *mmn_mm, + struct mmu_notifier_range *range) { struct mmu_notifier *mn; int ret = 0; int id; id = srcu_read_lock(&srcu); - hlist_for_each_entry_rcu(mn, &range->mm->mmu_notifier_mm->list, hlist) { + hlist_for_each_entry_rcu(mn, &mmn_mm->list, hlist) { if (mn->ops->invalidate_range_start) { int _ret; @@ -203,15 +479,30 @@ int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) return ret; } -void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range, - bool only_end) +int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) +{ + struct mmu_notifier_mm *mmn_mm = range->mm->mmu_notifier_mm; + int ret; + + if (mmn_mm->has_itree) { + ret = mn_itree_invalidate(mmn_mm, range); + if (ret) + return ret; + } + if (!hlist_empty(&mmn_mm->list)) + return mn_hlist_invalidate_range_start(mmn_mm, range); + return 0; +} + +static void mn_hlist_invalidate_end(struct mmu_notifier_mm *mmn_mm, + struct mmu_notifier_range *range, + bool only_end) { struct mmu_notifier *mn; int id; - lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); id = srcu_read_lock(&srcu); - hlist_for_each_entry_rcu(mn, &range->mm->mmu_notifier_mm->list, hlist) { + hlist_for_each_entry_rcu(mn, &mmn_mm->list, hlist) { /* * Call invalidate_range here too to avoid the need for the * subsystem of having to register an invalidate_range_end @@ -238,6 +529,19 @@ void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range, } } srcu_read_unlock(&srcu, id); +} + +void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range, + bool only_end) +{ + struct mmu_notifier_mm *mmn_mm = range->mm->mmu_notifier_mm; + + lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); + if (mmn_mm->has_itree) + mn_itree_inv_end(mmn_mm); + + if (!hlist_empty(&mmn_mm->list)) + mn_hlist_invalidate_end(mmn_mm, range, only_end); lock_map_release(&__mmu_notifier_invalidate_range_start_map); } @@ -256,8 +560,9 @@ void __mmu_notifier_invalidate_range(struct mm_struct *mm, } /* - * Same as mmu_notifier_register but here the caller must hold the - * mmap_sem in write mode. + * Same as mmu_notifier_register but here the caller must hold the mmap_sem in + * write mode. A NULL mn signals the notifier is being registered for itree + * mode. */ int __mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm) { @@ -274,9 +579,6 @@ int __mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm) fs_reclaim_release(GFP_KERNEL); } - mn->mm = mm; - mn->users = 1; - if (!mm->mmu_notifier_mm) { /* * kmalloc cannot be called under mm_take_all_locks(), but we @@ -284,21 +586,22 @@ int __mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm) * the write side of the mmap_sem. */ mmu_notifier_mm = - kmalloc(sizeof(struct mmu_notifier_mm), GFP_KERNEL); + kzalloc(sizeof(struct mmu_notifier_mm), GFP_KERNEL); if (!mmu_notifier_mm) return -ENOMEM; INIT_HLIST_HEAD(&mmu_notifier_mm->list); spin_lock_init(&mmu_notifier_mm->lock); + mmu_notifier_mm->invalidate_seq = 2; + mmu_notifier_mm->itree = RB_ROOT_CACHED; + init_waitqueue_head(&mmu_notifier_mm->wq); + INIT_HLIST_HEAD(&mmu_notifier_mm->deferred_list); } ret = mm_take_all_locks(mm); if (unlikely(ret)) goto out_clean; - /* Pairs with the mmdrop in mmu_notifier_unregister_* */ - mmgrab(mm); - /* * Serialize the update against mmu_notifier_unregister. A * side note: mmu_notifier_release can't run concurrently with @@ -306,13 +609,28 @@ int __mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm) * current->mm or explicitly with get_task_mm() or similar). * We can't race against any other mmu notifier method either * thanks to mm_take_all_locks(). + * + * release semantics on the initialization of the mmu_notifier_mm's + * contents are provided for unlocked readers. acquire can only be + * used while holding the mmgrab or mmget, and is safe because once + * created the mmu_notififer_mm is not freed until the mm is + * destroyed. As above, users holding the mmap_sem or one of the + * mm_take_all_locks() do not need to use acquire semantics. */ if (mmu_notifier_mm) - mm->mmu_notifier_mm = mmu_notifier_mm; + smp_store_release(&mm->mmu_notifier_mm, mmu_notifier_mm); - spin_lock(&mm->mmu_notifier_mm->lock); - hlist_add_head_rcu(&mn->hlist, &mm->mmu_notifier_mm->list); - spin_unlock(&mm->mmu_notifier_mm->lock); + if (mn) { + /* Pairs with the mmdrop in mmu_notifier_unregister_* */ + mmgrab(mm); + mn->mm = mm; + mn->users = 1; + + spin_lock(&mm->mmu_notifier_mm->lock); + hlist_add_head_rcu(&mn->hlist, &mm->mmu_notifier_mm->list); + spin_unlock(&mm->mmu_notifier_mm->lock); + } else + mm->mmu_notifier_mm->has_itree = true; mm_drop_all_locks(mm); BUG_ON(atomic_read(&mm->mm_users) <= 0); @@ -529,6 +847,180 @@ out_unlock: } EXPORT_SYMBOL_GPL(mmu_notifier_put); +static int __mmu_interval_notifier_insert( + struct mmu_interval_notifier *mni, struct mm_struct *mm, + struct mmu_notifier_mm *mmn_mm, unsigned long start, + unsigned long length, const struct mmu_interval_notifier_ops *ops) +{ + mni->mm = mm; + mni->ops = ops; + RB_CLEAR_NODE(&mni->interval_tree.rb); + mni->interval_tree.start = start; + /* + * Note that the representation of the intervals in the interval tree + * considers the ending point as contained in the interval. + */ + if (length == 0 || + check_add_overflow(start, length - 1, &mni->interval_tree.last)) + return -EOVERFLOW; + + /* Must call with a mmget() held */ + if (WARN_ON(atomic_read(&mm->mm_count) <= 0)) + return -EINVAL; + + /* pairs with mmdrop in mmu_interval_notifier_remove() */ + mmgrab(mm); + + /* + * If some invalidate_range_start/end region is going on in parallel + * we don't know what VA ranges are affected, so we must assume this + * new range is included. + * + * If the itree is invalidating then we are not allowed to change + * it. Retrying until invalidation is done is tricky due to the + * possibility for live lock, instead defer the add to + * mn_itree_inv_end() so this algorithm is deterministic. + * + * In all cases the value for the mni->invalidate_seq should be + * odd, see mmu_interval_read_begin() + */ + spin_lock(&mmn_mm->lock); + if (mmn_mm->active_invalidate_ranges) { + if (mn_itree_is_invalidating(mmn_mm)) + hlist_add_head(&mni->deferred_item, + &mmn_mm->deferred_list); + else { + mmn_mm->invalidate_seq |= 1; + interval_tree_insert(&mni->interval_tree, + &mmn_mm->itree); + } + mni->invalidate_seq = mmn_mm->invalidate_seq; + } else { + WARN_ON(mn_itree_is_invalidating(mmn_mm)); + /* + * The starting seq for a mni not under invalidation should be + * odd, not equal to the current invalidate_seq and + * invalidate_seq should not 'wrap' to the new seq any time + * soon. + */ + mni->invalidate_seq = mmn_mm->invalidate_seq - 1; + interval_tree_insert(&mni->interval_tree, &mmn_mm->itree); + } + spin_unlock(&mmn_mm->lock); + return 0; +} + +/** + * mmu_interval_notifier_insert - Insert an interval notifier + * @mni: Interval notifier to register + * @start: Starting virtual address to monitor + * @length: Length of the range to monitor + * @mm : mm_struct to attach to + * + * This function subscribes the interval notifier for notifications from the + * mm. Upon return the ops related to mmu_interval_notifier will be called + * whenever an event that intersects with the given range occurs. + * + * Upon return the range_notifier may not be present in the interval tree yet. + * The caller must use the normal interval notifier read flow via + * mmu_interval_read_begin() to establish SPTEs for this range. + */ +int mmu_interval_notifier_insert(struct mmu_interval_notifier *mni, + struct mm_struct *mm, unsigned long start, + unsigned long length, + const struct mmu_interval_notifier_ops *ops) +{ + struct mmu_notifier_mm *mmn_mm; + int ret; + + might_lock(&mm->mmap_sem); + + mmn_mm = smp_load_acquire(&mm->mmu_notifier_mm); + if (!mmn_mm || !mmn_mm->has_itree) { + ret = mmu_notifier_register(NULL, mm); + if (ret) + return ret; + mmn_mm = mm->mmu_notifier_mm; + } + return __mmu_interval_notifier_insert(mni, mm, mmn_mm, start, length, + ops); +} +EXPORT_SYMBOL_GPL(mmu_interval_notifier_insert); + +int mmu_interval_notifier_insert_locked( + struct mmu_interval_notifier *mni, struct mm_struct *mm, + unsigned long start, unsigned long length, + const struct mmu_interval_notifier_ops *ops) +{ + struct mmu_notifier_mm *mmn_mm; + int ret; + + lockdep_assert_held_write(&mm->mmap_sem); + + mmn_mm = mm->mmu_notifier_mm; + if (!mmn_mm || !mmn_mm->has_itree) { + ret = __mmu_notifier_register(NULL, mm); + if (ret) + return ret; + mmn_mm = mm->mmu_notifier_mm; + } + return __mmu_interval_notifier_insert(mni, mm, mmn_mm, start, length, + ops); +} +EXPORT_SYMBOL_GPL(mmu_interval_notifier_insert_locked); + +/** + * mmu_interval_notifier_remove - Remove a interval notifier + * @mni: Interval notifier to unregister + * + * This function must be paired with mmu_interval_notifier_insert(). It cannot + * be called from any ops callback. + * + * Once this returns ops callbacks are no longer running on other CPUs and + * will not be called in future. + */ +void mmu_interval_notifier_remove(struct mmu_interval_notifier *mni) +{ + struct mm_struct *mm = mni->mm; + struct mmu_notifier_mm *mmn_mm = mm->mmu_notifier_mm; + unsigned long seq = 0; + + might_sleep(); + + spin_lock(&mmn_mm->lock); + if (mn_itree_is_invalidating(mmn_mm)) { + /* + * remove is being called after insert put this on the + * deferred list, but before the deferred list was processed. + */ + if (RB_EMPTY_NODE(&mni->interval_tree.rb)) { + hlist_del(&mni->deferred_item); + } else { + hlist_add_head(&mni->deferred_item, + &mmn_mm->deferred_list); + seq = mmn_mm->invalidate_seq; + } + } else { + WARN_ON(RB_EMPTY_NODE(&mni->interval_tree.rb)); + interval_tree_remove(&mni->interval_tree, &mmn_mm->itree); + } + spin_unlock(&mmn_mm->lock); + + /* + * The possible sleep on progress in the invalidation requires the + * caller not hold any locks held by invalidation callbacks. + */ + lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); + lock_map_release(&__mmu_notifier_invalidate_range_start_map); + if (seq) + wait_event(mmn_mm->wq, + READ_ONCE(mmn_mm->invalidate_seq) != seq); + + /* pairs with mmgrab in mmu_interval_notifier_insert() */ + mmdrop(mm); +} +EXPORT_SYMBOL_GPL(mmu_interval_notifier_remove); + /** * mmu_notifier_synchronize - Ensure all mmu_notifiers are freed * -- cgit v1.2.3-71-gd317 From 04ec32fbc2b29a640d67872d2f88daac4c73e45b Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 12 Nov 2019 16:22:20 -0400 Subject: mm/hmm: allow hmm_range to be used with a mmu_interval_notifier or hmm_mirror MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit hmm_mirror's handling of ranges does not use a sequence count which results in this bug: CPU0 CPU1 hmm_range_wait_until_valid(range) valid == true hmm_range_fault(range) hmm_invalidate_range_start() range->valid = false hmm_invalidate_range_end() range->valid = true hmm_range_valid(range) valid == true Where the hmm_range_valid() should not have succeeded. Adding the required sequence count would make it nearly identical to the new mmu_interval_notifier. Instead replace the hmm_mirror stuff with mmu_interval_notifier. Co-existence of the two APIs is the first step. Link: https://lore.kernel.org/r/20191112202231.3856-4-jgg@ziepe.ca Reviewed-by: Jérôme Glisse Tested-by: Philip Yang Tested-by: Ralph Campbell Reviewed-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 5 +++++ mm/hmm.c | 25 +++++++++++++++++++------ 2 files changed, 24 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 3fec513b9c00..fbb35c78637e 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -145,6 +145,9 @@ enum hmm_pfn_value_e { /* * struct hmm_range - track invalidation lock on virtual address range * + * @notifier: an optional mmu_interval_notifier + * @notifier_seq: when notifier is used this is the result of + * mmu_interval_read_begin() * @hmm: the core HMM structure this range is active against * @vma: the vm area struct for the range * @list: all range lock are on a list @@ -159,6 +162,8 @@ enum hmm_pfn_value_e { * @valid: pfns array did not change since it has been fill by an HMM function */ struct hmm_range { + struct mmu_interval_notifier *notifier; + unsigned long notifier_seq; struct hmm *hmm; struct list_head list; unsigned long start; diff --git a/mm/hmm.c b/mm/hmm.c index 6b0136665407..8d060c5dabe3 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -858,6 +858,14 @@ void hmm_range_unregister(struct hmm_range *range) } EXPORT_SYMBOL(hmm_range_unregister); +static bool needs_retry(struct hmm_range *range) +{ + if (range->notifier) + return mmu_interval_check_retry(range->notifier, + range->notifier_seq); + return !range->valid; +} + static const struct mm_walk_ops hmm_walk_ops = { .pud_entry = hmm_vma_walk_pud, .pmd_entry = hmm_vma_walk_pmd, @@ -898,18 +906,23 @@ long hmm_range_fault(struct hmm_range *range, unsigned int flags) const unsigned long device_vma = VM_IO | VM_PFNMAP | VM_MIXEDMAP; unsigned long start = range->start, end; struct hmm_vma_walk hmm_vma_walk; - struct hmm *hmm = range->hmm; + struct mm_struct *mm; struct vm_area_struct *vma; int ret; - lockdep_assert_held(&hmm->mmu_notifier.mm->mmap_sem); + if (range->notifier) + mm = range->notifier->mm; + else + mm = range->hmm->mmu_notifier.mm; + + lockdep_assert_held(&mm->mmap_sem); do { /* If range is no longer valid force retry. */ - if (!range->valid) + if (needs_retry(range)) return -EBUSY; - vma = find_vma(hmm->mmu_notifier.mm, start); + vma = find_vma(mm, start); if (vma == NULL || (vma->vm_flags & device_vma)) return -EFAULT; @@ -939,7 +952,7 @@ long hmm_range_fault(struct hmm_range *range, unsigned int flags) start = hmm_vma_walk.last; /* Keep trying while the range is valid. */ - } while (ret == -EBUSY && range->valid); + } while (ret == -EBUSY && !needs_retry(range)); if (ret) { unsigned long i; @@ -997,7 +1010,7 @@ long hmm_range_dma_map(struct hmm_range *range, struct device *device, continue; /* Check if range is being invalidated */ - if (!range->valid) { + if (needs_retry(range)) { ret = -EBUSY; goto unmap; } -- cgit v1.2.3-71-gd317 From 107e899874e95dcddc779142942bf285eba38bc5 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 12 Nov 2019 16:22:21 -0400 Subject: mm/hmm: define the pre-processor related parts of hmm.h even if disabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Only the function calls are stubbed out with static inlines that always fail. This is the standard way to write a header for an optional component and makes it easier for drivers that only optionally need HMM_MIRROR. Link: https://lore.kernel.org/r/20191112202231.3856-5-jgg@ziepe.ca Reviewed-by: Jérôme Glisse Tested-by: Ralph Campbell Reviewed-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 59 ++++++++++++++++++++++++++++++++++++++++++----------- kernel/fork.c | 1 - 2 files changed, 47 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index fbb35c78637e..cb69bf10dc78 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -62,8 +62,6 @@ #include #include -#ifdef CONFIG_HMM_MIRROR - #include #include #include @@ -374,6 +372,15 @@ struct hmm_mirror { struct list_head list; }; +/* + * Retry fault if non-blocking, drop mmap_sem and return -EAGAIN in that case. + */ +#define HMM_FAULT_ALLOW_RETRY (1 << 0) + +/* Don't fault in missing PTEs, just snapshot the current state. */ +#define HMM_FAULT_SNAPSHOT (1 << 1) + +#ifdef CONFIG_HMM_MIRROR int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm); void hmm_mirror_unregister(struct hmm_mirror *mirror); @@ -383,14 +390,6 @@ void hmm_mirror_unregister(struct hmm_mirror *mirror); int hmm_range_register(struct hmm_range *range, struct hmm_mirror *mirror); void hmm_range_unregister(struct hmm_range *range); -/* - * Retry fault if non-blocking, drop mmap_sem and return -EAGAIN in that case. - */ -#define HMM_FAULT_ALLOW_RETRY (1 << 0) - -/* Don't fault in missing PTEs, just snapshot the current state. */ -#define HMM_FAULT_SNAPSHOT (1 << 1) - long hmm_range_fault(struct hmm_range *range, unsigned int flags); long hmm_range_dma_map(struct hmm_range *range, @@ -401,6 +400,44 @@ long hmm_range_dma_unmap(struct hmm_range *range, struct device *device, dma_addr_t *daddrs, bool dirty); +#else +int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm) +{ + return -EOPNOTSUPP; +} + +void hmm_mirror_unregister(struct hmm_mirror *mirror) +{ +} + +int hmm_range_register(struct hmm_range *range, struct hmm_mirror *mirror) +{ + return -EOPNOTSUPP; +} + +void hmm_range_unregister(struct hmm_range *range) +{ +} + +static inline long hmm_range_fault(struct hmm_range *range, unsigned int flags) +{ + return -EOPNOTSUPP; +} + +static inline long hmm_range_dma_map(struct hmm_range *range, + struct device *device, dma_addr_t *daddrs, + unsigned int flags) +{ + return -EOPNOTSUPP; +} + +static inline long hmm_range_dma_unmap(struct hmm_range *range, + struct device *device, + dma_addr_t *daddrs, bool dirty) +{ + return -EOPNOTSUPP; +} +#endif /* * HMM_RANGE_DEFAULT_TIMEOUT - default timeout (ms) when waiting for a range @@ -411,6 +448,4 @@ long hmm_range_dma_unmap(struct hmm_range *range, */ #define HMM_RANGE_DEFAULT_TIMEOUT 1000 -#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ - #endif /* LINUX_HMM_H */ diff --git a/kernel/fork.c b/kernel/fork.c index bcdf53125210..ca39cfc404e3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -40,7 +40,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3-71-gd317 From a22dd506400d0f4784ad596f073b9eb5ed7c6a2a Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 12 Nov 2019 16:22:30 -0400 Subject: mm/hmm: remove hmm_mirror and related MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The only two users of this are now converted to use mmu_interval_notifier, delete all the code and update hmm.rst. Link: https://lore.kernel.org/r/20191112202231.3856-14-jgg@ziepe.ca Reviewed-by: Jérôme Glisse Tested-by: Ralph Campbell Reviewed-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe --- Documentation/vm/hmm.rst | 105 ++++------------- include/linux/hmm.h | 183 +----------------------------- mm/Kconfig | 1 - mm/hmm.c | 285 ++--------------------------------------------- 4 files changed, 34 insertions(+), 540 deletions(-) (limited to 'include/linux') diff --git a/Documentation/vm/hmm.rst b/Documentation/vm/hmm.rst index 0a5960beccf7..893a8ba0e9fe 100644 --- a/Documentation/vm/hmm.rst +++ b/Documentation/vm/hmm.rst @@ -147,49 +147,16 @@ Address space mirroring implementation and API Address space mirroring's main objective is to allow duplication of a range of CPU page table into a device page table; HMM helps keep both synchronized. A device driver that wants to mirror a process address space must start with the -registration of an hmm_mirror struct:: - - int hmm_mirror_register(struct hmm_mirror *mirror, - struct mm_struct *mm); - -The mirror struct has a set of callbacks that are used -to propagate CPU page tables:: - - struct hmm_mirror_ops { - /* release() - release hmm_mirror - * - * @mirror: pointer to struct hmm_mirror - * - * This is called when the mm_struct is being released. The callback - * must ensure that all access to any pages obtained from this mirror - * is halted before the callback returns. All future access should - * fault. - */ - void (*release)(struct hmm_mirror *mirror); - - /* sync_cpu_device_pagetables() - synchronize page tables - * - * @mirror: pointer to struct hmm_mirror - * @update: update information (see struct mmu_notifier_range) - * Return: -EAGAIN if update.blockable false and callback need to - * block, 0 otherwise. - * - * This callback ultimately originates from mmu_notifiers when the CPU - * page table is updated. The device driver must update its page table - * in response to this callback. The update argument tells what action - * to perform. - * - * The device driver must not return from this callback until the device - * page tables are completely updated (TLBs flushed, etc); this is a - * synchronous call. - */ - int (*sync_cpu_device_pagetables)(struct hmm_mirror *mirror, - const struct hmm_update *update); - }; - -The device driver must perform the update action to the range (mark range -read only, or fully unmap, etc.). The device must complete the update before -the driver callback returns. +registration of a mmu_interval_notifier:: + + mni->ops = &driver_ops; + int mmu_interval_notifier_insert(struct mmu_interval_notifier *mni, + unsigned long start, unsigned long length, + struct mm_struct *mm); + +During the driver_ops->invalidate() callback the device driver must perform +the update action to the range (mark range read only, or fully unmap, +etc.). The device must complete the update before the driver callback returns. When the device driver wants to populate a range of virtual addresses, it can use:: @@ -216,70 +183,46 @@ The usage pattern is:: struct hmm_range range; ... + range.notifier = &mni; range.start = ...; range.end = ...; range.pfns = ...; range.flags = ...; range.values = ...; range.pfn_shift = ...; - hmm_range_register(&range, mirror); - /* - * Just wait for range to be valid, safe to ignore return value as we - * will use the return value of hmm_range_fault() below under the - * mmap_sem to ascertain the validity of the range. - */ - hmm_range_wait_until_valid(&range, TIMEOUT_IN_MSEC); + if (!mmget_not_zero(mni->notifier.mm)) + return -EFAULT; again: + range.notifier_seq = mmu_interval_read_begin(&mni); down_read(&mm->mmap_sem); ret = hmm_range_fault(&range, HMM_RANGE_SNAPSHOT); if (ret) { up_read(&mm->mmap_sem); - if (ret == -EBUSY) { - /* - * No need to check hmm_range_wait_until_valid() return value - * on retry we will get proper error with hmm_range_fault() - */ - hmm_range_wait_until_valid(&range, TIMEOUT_IN_MSEC); - goto again; - } - hmm_range_unregister(&range); + if (ret == -EBUSY) + goto again; return ret; } + up_read(&mm->mmap_sem); + take_lock(driver->update); - if (!hmm_range_valid(&range)) { + if (mmu_interval_read_retry(&ni, range.notifier_seq) { release_lock(driver->update); - up_read(&mm->mmap_sem); goto again; } - // Use pfns array content to update device page table + /* Use pfns array content to update device page table, + * under the update lock */ - hmm_range_unregister(&range); release_lock(driver->update); - up_read(&mm->mmap_sem); return 0; } The driver->update lock is the same lock that the driver takes inside its -sync_cpu_device_pagetables() callback. That lock must be held before calling -hmm_range_valid() to avoid any race with a concurrent CPU page table update. - -HMM implements all this on top of the mmu_notifier API because we wanted a -simpler API and also to be able to perform optimizations latter on like doing -concurrent device updates in multi-devices scenario. - -HMM also serves as an impedance mismatch between how CPU page table updates -are done (by CPU write to the page table and TLB flushes) and how devices -update their own page table. Device updates are a multi-step process. First, -appropriate commands are written to a buffer, then this buffer is scheduled for -execution on the device. It is only once the device has executed commands in -the buffer that the update is done. Creating and scheduling the update command -buffer can happen concurrently for multiple devices. Waiting for each device to -report commands as executed is serialized (there is no point in doing this -concurrently). - +invalidate() callback. That lock must be held before calling +mmu_interval_read_retry() to avoid any race with a concurrent CPU page table +update. Leverage default_flags and pfn_flags_mask ========================================= diff --git a/include/linux/hmm.h b/include/linux/hmm.h index cb69bf10dc78..1225b3c87aba 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -68,29 +68,6 @@ #include #include - -/* - * struct hmm - HMM per mm struct - * - * @mm: mm struct this HMM struct is bound to - * @lock: lock protecting ranges list - * @ranges: list of range being snapshotted - * @mirrors: list of mirrors for this mm - * @mmu_notifier: mmu notifier to track updates to CPU page table - * @mirrors_sem: read/write semaphore protecting the mirrors list - * @wq: wait queue for user waiting on a range invalidation - * @notifiers: count of active mmu notifiers - */ -struct hmm { - struct mmu_notifier mmu_notifier; - spinlock_t ranges_lock; - struct list_head ranges; - struct list_head mirrors; - struct rw_semaphore mirrors_sem; - wait_queue_head_t wq; - long notifiers; -}; - /* * hmm_pfn_flag_e - HMM flag enums * @@ -143,9 +120,8 @@ enum hmm_pfn_value_e { /* * struct hmm_range - track invalidation lock on virtual address range * - * @notifier: an optional mmu_interval_notifier - * @notifier_seq: when notifier is used this is the result of - * mmu_interval_read_begin() + * @notifier: a mmu_interval_notifier that includes the start/end + * @notifier_seq: result of mmu_interval_read_begin() * @hmm: the core HMM structure this range is active against * @vma: the vm area struct for the range * @list: all range lock are on a list @@ -162,8 +138,6 @@ enum hmm_pfn_value_e { struct hmm_range { struct mmu_interval_notifier *notifier; unsigned long notifier_seq; - struct hmm *hmm; - struct list_head list; unsigned long start; unsigned long end; uint64_t *pfns; @@ -172,32 +146,8 @@ struct hmm_range { uint64_t default_flags; uint64_t pfn_flags_mask; uint8_t pfn_shift; - bool valid; }; -/* - * hmm_range_wait_until_valid() - wait for range to be valid - * @range: range affected by invalidation to wait on - * @timeout: time out for wait in ms (ie abort wait after that period of time) - * Return: true if the range is valid, false otherwise. - */ -static inline bool hmm_range_wait_until_valid(struct hmm_range *range, - unsigned long timeout) -{ - return wait_event_timeout(range->hmm->wq, range->valid, - msecs_to_jiffies(timeout)) != 0; -} - -/* - * hmm_range_valid() - test if a range is valid or not - * @range: range - * Return: true if the range is valid, false otherwise. - */ -static inline bool hmm_range_valid(struct hmm_range *range) -{ - return range->valid; -} - /* * hmm_device_entry_to_page() - return struct page pointed to by a device entry * @range: range use to decode device entry value @@ -267,111 +217,6 @@ static inline uint64_t hmm_device_entry_from_pfn(const struct hmm_range *range, range->flags[HMM_PFN_VALID]; } -/* - * Mirroring: how to synchronize device page table with CPU page table. - * - * A device driver that is participating in HMM mirroring must always - * synchronize with CPU page table updates. For this, device drivers can either - * directly use mmu_notifier APIs or they can use the hmm_mirror API. Device - * drivers can decide to register one mirror per device per process, or just - * one mirror per process for a group of devices. The pattern is: - * - * int device_bind_address_space(..., struct mm_struct *mm, ...) - * { - * struct device_address_space *das; - * - * // Device driver specific initialization, and allocation of das - * // which contains an hmm_mirror struct as one of its fields. - * ... - * - * ret = hmm_mirror_register(&das->mirror, mm, &device_mirror_ops); - * if (ret) { - * // Cleanup on error - * return ret; - * } - * - * // Other device driver specific initialization - * ... - * } - * - * Once an hmm_mirror is registered for an address space, the device driver - * will get callbacks through sync_cpu_device_pagetables() operation (see - * hmm_mirror_ops struct). - * - * Device driver must not free the struct containing the hmm_mirror struct - * before calling hmm_mirror_unregister(). The expected usage is to do that when - * the device driver is unbinding from an address space. - * - * - * void device_unbind_address_space(struct device_address_space *das) - * { - * // Device driver specific cleanup - * ... - * - * hmm_mirror_unregister(&das->mirror); - * - * // Other device driver specific cleanup, and now das can be freed - * ... - * } - */ - -struct hmm_mirror; - -/* - * struct hmm_mirror_ops - HMM mirror device operations callback - * - * @update: callback to update range on a device - */ -struct hmm_mirror_ops { - /* release() - release hmm_mirror - * - * @mirror: pointer to struct hmm_mirror - * - * This is called when the mm_struct is being released. The callback - * must ensure that all access to any pages obtained from this mirror - * is halted before the callback returns. All future access should - * fault. - */ - void (*release)(struct hmm_mirror *mirror); - - /* sync_cpu_device_pagetables() - synchronize page tables - * - * @mirror: pointer to struct hmm_mirror - * @update: update information (see struct mmu_notifier_range) - * Return: -EAGAIN if mmu_notifier_range_blockable(update) is false - * and callback needs to block, 0 otherwise. - * - * This callback ultimately originates from mmu_notifiers when the CPU - * page table is updated. The device driver must update its page table - * in response to this callback. The update argument tells what action - * to perform. - * - * The device driver must not return from this callback until the device - * page tables are completely updated (TLBs flushed, etc); this is a - * synchronous call. - */ - int (*sync_cpu_device_pagetables)( - struct hmm_mirror *mirror, - const struct mmu_notifier_range *update); -}; - -/* - * struct hmm_mirror - mirror struct for a device driver - * - * @hmm: pointer to struct hmm (which is unique per mm_struct) - * @ops: device driver callback for HMM mirror operations - * @list: for list of mirrors of a given mm - * - * Each address space (mm_struct) being mirrored by a device must register one - * instance of an hmm_mirror struct with HMM. HMM will track the list of all - * mirrors for each mm_struct. - */ -struct hmm_mirror { - struct hmm *hmm; - const struct hmm_mirror_ops *ops; - struct list_head list; -}; - /* * Retry fault if non-blocking, drop mmap_sem and return -EAGAIN in that case. */ @@ -381,15 +226,9 @@ struct hmm_mirror { #define HMM_FAULT_SNAPSHOT (1 << 1) #ifdef CONFIG_HMM_MIRROR -int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm); -void hmm_mirror_unregister(struct hmm_mirror *mirror); - /* * Please see Documentation/vm/hmm.rst for how to use the range API. */ -int hmm_range_register(struct hmm_range *range, struct hmm_mirror *mirror); -void hmm_range_unregister(struct hmm_range *range); - long hmm_range_fault(struct hmm_range *range, unsigned int flags); long hmm_range_dma_map(struct hmm_range *range, @@ -401,24 +240,6 @@ long hmm_range_dma_unmap(struct hmm_range *range, dma_addr_t *daddrs, bool dirty); #else -int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm) -{ - return -EOPNOTSUPP; -} - -void hmm_mirror_unregister(struct hmm_mirror *mirror) -{ -} - -int hmm_range_register(struct hmm_range *range, struct hmm_mirror *mirror) -{ - return -EOPNOTSUPP; -} - -void hmm_range_unregister(struct hmm_range *range) -{ -} - static inline long hmm_range_fault(struct hmm_range *range, unsigned int flags) { return -EOPNOTSUPP; diff --git a/mm/Kconfig b/mm/Kconfig index d0b5046d9aef..e38ff1d5968d 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -675,7 +675,6 @@ config DEV_PAGEMAP_OPS config HMM_MIRROR bool depends on MMU - depends on MMU_NOTIFIER config DEVICE_PRIVATE bool "Unaddressable device memory (GPU memory, ...)" diff --git a/mm/hmm.c b/mm/hmm.c index 8d060c5dabe3..aed2f39d1a98 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -26,193 +26,6 @@ #include #include -static struct mmu_notifier *hmm_alloc_notifier(struct mm_struct *mm) -{ - struct hmm *hmm; - - hmm = kzalloc(sizeof(*hmm), GFP_KERNEL); - if (!hmm) - return ERR_PTR(-ENOMEM); - - init_waitqueue_head(&hmm->wq); - INIT_LIST_HEAD(&hmm->mirrors); - init_rwsem(&hmm->mirrors_sem); - INIT_LIST_HEAD(&hmm->ranges); - spin_lock_init(&hmm->ranges_lock); - hmm->notifiers = 0; - return &hmm->mmu_notifier; -} - -static void hmm_free_notifier(struct mmu_notifier *mn) -{ - struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier); - - WARN_ON(!list_empty(&hmm->ranges)); - WARN_ON(!list_empty(&hmm->mirrors)); - kfree(hmm); -} - -static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm) -{ - struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier); - struct hmm_mirror *mirror; - - /* - * Since hmm_range_register() holds the mmget() lock hmm_release() is - * prevented as long as a range exists. - */ - WARN_ON(!list_empty_careful(&hmm->ranges)); - - down_read(&hmm->mirrors_sem); - list_for_each_entry(mirror, &hmm->mirrors, list) { - /* - * Note: The driver is not allowed to trigger - * hmm_mirror_unregister() from this thread. - */ - if (mirror->ops->release) - mirror->ops->release(mirror); - } - up_read(&hmm->mirrors_sem); -} - -static void notifiers_decrement(struct hmm *hmm) -{ - unsigned long flags; - - spin_lock_irqsave(&hmm->ranges_lock, flags); - hmm->notifiers--; - if (!hmm->notifiers) { - struct hmm_range *range; - - list_for_each_entry(range, &hmm->ranges, list) { - if (range->valid) - continue; - range->valid = true; - } - wake_up_all(&hmm->wq); - } - spin_unlock_irqrestore(&hmm->ranges_lock, flags); -} - -static int hmm_invalidate_range_start(struct mmu_notifier *mn, - const struct mmu_notifier_range *nrange) -{ - struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier); - struct hmm_mirror *mirror; - struct hmm_range *range; - unsigned long flags; - int ret = 0; - - spin_lock_irqsave(&hmm->ranges_lock, flags); - hmm->notifiers++; - list_for_each_entry(range, &hmm->ranges, list) { - if (nrange->end < range->start || nrange->start >= range->end) - continue; - - range->valid = false; - } - spin_unlock_irqrestore(&hmm->ranges_lock, flags); - - if (mmu_notifier_range_blockable(nrange)) - down_read(&hmm->mirrors_sem); - else if (!down_read_trylock(&hmm->mirrors_sem)) { - ret = -EAGAIN; - goto out; - } - - list_for_each_entry(mirror, &hmm->mirrors, list) { - int rc; - - rc = mirror->ops->sync_cpu_device_pagetables(mirror, nrange); - if (rc) { - if (WARN_ON(mmu_notifier_range_blockable(nrange) || - rc != -EAGAIN)) - continue; - ret = -EAGAIN; - break; - } - } - up_read(&hmm->mirrors_sem); - -out: - if (ret) - notifiers_decrement(hmm); - return ret; -} - -static void hmm_invalidate_range_end(struct mmu_notifier *mn, - const struct mmu_notifier_range *nrange) -{ - struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier); - - notifiers_decrement(hmm); -} - -static const struct mmu_notifier_ops hmm_mmu_notifier_ops = { - .release = hmm_release, - .invalidate_range_start = hmm_invalidate_range_start, - .invalidate_range_end = hmm_invalidate_range_end, - .alloc_notifier = hmm_alloc_notifier, - .free_notifier = hmm_free_notifier, -}; - -/* - * hmm_mirror_register() - register a mirror against an mm - * - * @mirror: new mirror struct to register - * @mm: mm to register against - * Return: 0 on success, -ENOMEM if no memory, -EINVAL if invalid arguments - * - * To start mirroring a process address space, the device driver must register - * an HMM mirror struct. - * - * The caller cannot unregister the hmm_mirror while any ranges are - * registered. - * - * Callers using this function must put a call to mmu_notifier_synchronize() - * in their module exit functions. - */ -int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm) -{ - struct mmu_notifier *mn; - - lockdep_assert_held_write(&mm->mmap_sem); - - /* Sanity check */ - if (!mm || !mirror || !mirror->ops) - return -EINVAL; - - mn = mmu_notifier_get_locked(&hmm_mmu_notifier_ops, mm); - if (IS_ERR(mn)) - return PTR_ERR(mn); - mirror->hmm = container_of(mn, struct hmm, mmu_notifier); - - down_write(&mirror->hmm->mirrors_sem); - list_add(&mirror->list, &mirror->hmm->mirrors); - up_write(&mirror->hmm->mirrors_sem); - - return 0; -} -EXPORT_SYMBOL(hmm_mirror_register); - -/* - * hmm_mirror_unregister() - unregister a mirror - * - * @mirror: mirror struct to unregister - * - * Stop mirroring a process address space, and cleanup. - */ -void hmm_mirror_unregister(struct hmm_mirror *mirror) -{ - struct hmm *hmm = mirror->hmm; - - down_write(&hmm->mirrors_sem); - list_del(&mirror->list); - up_write(&hmm->mirrors_sem); - mmu_notifier_put(&hmm->mmu_notifier); -} -EXPORT_SYMBOL(hmm_mirror_unregister); - struct hmm_vma_walk { struct hmm_range *range; struct dev_pagemap *pgmap; @@ -785,87 +598,6 @@ static void hmm_pfns_clear(struct hmm_range *range, *pfns = range->values[HMM_PFN_NONE]; } -/* - * hmm_range_register() - start tracking change to CPU page table over a range - * @range: range - * @mm: the mm struct for the range of virtual address - * - * Return: 0 on success, -EFAULT if the address space is no longer valid - * - * Track updates to the CPU page table see include/linux/hmm.h - */ -int hmm_range_register(struct hmm_range *range, struct hmm_mirror *mirror) -{ - struct hmm *hmm = mirror->hmm; - unsigned long flags; - - range->valid = false; - range->hmm = NULL; - - if ((range->start & (PAGE_SIZE - 1)) || (range->end & (PAGE_SIZE - 1))) - return -EINVAL; - if (range->start >= range->end) - return -EINVAL; - - /* Prevent hmm_release() from running while the range is valid */ - if (!mmget_not_zero(hmm->mmu_notifier.mm)) - return -EFAULT; - - /* Initialize range to track CPU page table updates. */ - spin_lock_irqsave(&hmm->ranges_lock, flags); - - range->hmm = hmm; - list_add(&range->list, &hmm->ranges); - - /* - * If there are any concurrent notifiers we have to wait for them for - * the range to be valid (see hmm_range_wait_until_valid()). - */ - if (!hmm->notifiers) - range->valid = true; - spin_unlock_irqrestore(&hmm->ranges_lock, flags); - - return 0; -} -EXPORT_SYMBOL(hmm_range_register); - -/* - * hmm_range_unregister() - stop tracking change to CPU page table over a range - * @range: range - * - * Range struct is used to track updates to the CPU page table after a call to - * hmm_range_register(). See include/linux/hmm.h for how to use it. - */ -void hmm_range_unregister(struct hmm_range *range) -{ - struct hmm *hmm = range->hmm; - unsigned long flags; - - spin_lock_irqsave(&hmm->ranges_lock, flags); - list_del_init(&range->list); - spin_unlock_irqrestore(&hmm->ranges_lock, flags); - - /* Drop reference taken by hmm_range_register() */ - mmput(hmm->mmu_notifier.mm); - - /* - * The range is now invalid and the ref on the hmm is dropped, so - * poison the pointer. Leave other fields in place, for the caller's - * use. - */ - range->valid = false; - memset(&range->hmm, POISON_INUSE, sizeof(range->hmm)); -} -EXPORT_SYMBOL(hmm_range_unregister); - -static bool needs_retry(struct hmm_range *range) -{ - if (range->notifier) - return mmu_interval_check_retry(range->notifier, - range->notifier_seq); - return !range->valid; -} - static const struct mm_walk_ops hmm_walk_ops = { .pud_entry = hmm_vma_walk_pud, .pmd_entry = hmm_vma_walk_pmd, @@ -906,20 +638,16 @@ long hmm_range_fault(struct hmm_range *range, unsigned int flags) const unsigned long device_vma = VM_IO | VM_PFNMAP | VM_MIXEDMAP; unsigned long start = range->start, end; struct hmm_vma_walk hmm_vma_walk; - struct mm_struct *mm; + struct mm_struct *mm = range->notifier->mm; struct vm_area_struct *vma; int ret; - if (range->notifier) - mm = range->notifier->mm; - else - mm = range->hmm->mmu_notifier.mm; - lockdep_assert_held(&mm->mmap_sem); do { /* If range is no longer valid force retry. */ - if (needs_retry(range)) + if (mmu_interval_check_retry(range->notifier, + range->notifier_seq)) return -EBUSY; vma = find_vma(mm, start); @@ -952,7 +680,9 @@ long hmm_range_fault(struct hmm_range *range, unsigned int flags) start = hmm_vma_walk.last; /* Keep trying while the range is valid. */ - } while (ret == -EBUSY && !needs_retry(range)); + } while (ret == -EBUSY && + !mmu_interval_check_retry(range->notifier, + range->notifier_seq)); if (ret) { unsigned long i; @@ -1010,7 +740,8 @@ long hmm_range_dma_map(struct hmm_range *range, struct device *device, continue; /* Check if range is being invalidated */ - if (needs_retry(range)) { + if (mmu_interval_check_retry(range->notifier, + range->notifier_seq)) { ret = -EBUSY; goto unmap; } -- cgit v1.2.3-71-gd317 From 93f4e735b6d98ee4b7a1252d81e815a983e359f2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 13 Nov 2019 14:45:28 +0100 Subject: mm/hmm: remove hmm_range_dma_map and hmm_range_dma_unmap These two functions have never been used since they were added. Link: https://lore.kernel.org/r/20191113134528.21187-1-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: John Hubbard Reviewed-by: Jason Gunthorpe Signed-off-by: Jason Gunthorpe --- include/linux/hmm.h | 23 -------- mm/hmm.c | 147 ---------------------------------------------------- 2 files changed, 170 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 1225b3c87aba..ddf9f7144c43 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -230,34 +230,11 @@ static inline uint64_t hmm_device_entry_from_pfn(const struct hmm_range *range, * Please see Documentation/vm/hmm.rst for how to use the range API. */ long hmm_range_fault(struct hmm_range *range, unsigned int flags); - -long hmm_range_dma_map(struct hmm_range *range, - struct device *device, - dma_addr_t *daddrs, - unsigned int flags); -long hmm_range_dma_unmap(struct hmm_range *range, - struct device *device, - dma_addr_t *daddrs, - bool dirty); #else static inline long hmm_range_fault(struct hmm_range *range, unsigned int flags) { return -EOPNOTSUPP; } - -static inline long hmm_range_dma_map(struct hmm_range *range, - struct device *device, dma_addr_t *daddrs, - unsigned int flags) -{ - return -EOPNOTSUPP; -} - -static inline long hmm_range_dma_unmap(struct hmm_range *range, - struct device *device, - dma_addr_t *daddrs, bool dirty) -{ - return -EOPNOTSUPP; -} #endif /* diff --git a/mm/hmm.c b/mm/hmm.c index d903b1555de4..d379cb6496ae 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -691,150 +691,3 @@ long hmm_range_fault(struct hmm_range *range, unsigned int flags) return (hmm_vma_walk.last - range->start) >> PAGE_SHIFT; } EXPORT_SYMBOL(hmm_range_fault); - -/** - * hmm_range_dma_map - hmm_range_fault() and dma map page all in one. - * @range: range being faulted - * @device: device to map page to - * @daddrs: array of dma addresses for the mapped pages - * @flags: HMM_FAULT_* - * - * Return: the number of pages mapped on success (including zero), or any - * status return from hmm_range_fault() otherwise. - */ -long hmm_range_dma_map(struct hmm_range *range, struct device *device, - dma_addr_t *daddrs, unsigned int flags) -{ - unsigned long i, npages, mapped; - long ret; - - ret = hmm_range_fault(range, flags); - if (ret <= 0) - return ret ? ret : -EBUSY; - - npages = (range->end - range->start) >> PAGE_SHIFT; - for (i = 0, mapped = 0; i < npages; ++i) { - enum dma_data_direction dir = DMA_TO_DEVICE; - struct page *page; - - /* - * FIXME need to update DMA API to provide invalid DMA address - * value instead of a function to test dma address value. This - * would remove lot of dumb code duplicated accross many arch. - * - * For now setting it to 0 here is good enough as the pfns[] - * value is what is use to check what is valid and what isn't. - */ - daddrs[i] = 0; - - page = hmm_device_entry_to_page(range, range->pfns[i]); - if (page == NULL) - continue; - - /* Check if range is being invalidated */ - if (mmu_interval_check_retry(range->notifier, - range->notifier_seq)) { - ret = -EBUSY; - goto unmap; - } - - /* If it is read and write than map bi-directional. */ - if (range->pfns[i] & range->flags[HMM_PFN_WRITE]) - dir = DMA_BIDIRECTIONAL; - - daddrs[i] = dma_map_page(device, page, 0, PAGE_SIZE, dir); - if (dma_mapping_error(device, daddrs[i])) { - ret = -EFAULT; - goto unmap; - } - - mapped++; - } - - return mapped; - -unmap: - for (npages = i, i = 0; (i < npages) && mapped; ++i) { - enum dma_data_direction dir = DMA_TO_DEVICE; - struct page *page; - - page = hmm_device_entry_to_page(range, range->pfns[i]); - if (page == NULL) - continue; - - if (dma_mapping_error(device, daddrs[i])) - continue; - - /* If it is read and write than map bi-directional. */ - if (range->pfns[i] & range->flags[HMM_PFN_WRITE]) - dir = DMA_BIDIRECTIONAL; - - dma_unmap_page(device, daddrs[i], PAGE_SIZE, dir); - mapped--; - } - - return ret; -} -EXPORT_SYMBOL(hmm_range_dma_map); - -/** - * hmm_range_dma_unmap() - unmap range of that was map with hmm_range_dma_map() - * @range: range being unmapped - * @device: device against which dma map was done - * @daddrs: dma address of mapped pages - * @dirty: dirty page if it had the write flag set - * Return: number of page unmapped on success, -EINVAL otherwise - * - * Note that caller MUST abide by mmu notifier or use HMM mirror and abide - * to the sync_cpu_device_pagetables() callback so that it is safe here to - * call set_page_dirty(). Caller must also take appropriate locks to avoid - * concurrent mmu notifier or sync_cpu_device_pagetables() to make progress. - */ -long hmm_range_dma_unmap(struct hmm_range *range, - struct device *device, - dma_addr_t *daddrs, - bool dirty) -{ - unsigned long i, npages; - long cpages = 0; - - /* Sanity check. */ - if (range->end <= range->start) - return -EINVAL; - if (!daddrs) - return -EINVAL; - if (!range->pfns) - return -EINVAL; - - npages = (range->end - range->start) >> PAGE_SHIFT; - for (i = 0; i < npages; ++i) { - enum dma_data_direction dir = DMA_TO_DEVICE; - struct page *page; - - page = hmm_device_entry_to_page(range, range->pfns[i]); - if (page == NULL) - continue; - - /* If it is read and write than map bi-directional. */ - if (range->pfns[i] & range->flags[HMM_PFN_WRITE]) { - dir = DMA_BIDIRECTIONAL; - - /* - * See comments in function description on why it is - * safe here to call set_page_dirty() - */ - if (dirty) - set_page_dirty(page); - } - - /* Unmap and clear pfns/dma address */ - dma_unmap_page(device, daddrs[i], PAGE_SIZE, dir); - range->pfns[i] = range->values[HMM_PFN_NONE]; - /* FIXME see comments in hmm_vma_dma_map() */ - daddrs[i] = 0; - cpages++; - } - - return cpages; -} -EXPORT_SYMBOL(hmm_range_dma_unmap); -- cgit v1.2.3-71-gd317 From d46b7e4fb06037a61415f5b6964fcf632ee1dc34 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 21 Nov 2019 00:36:22 +0000 Subject: net: phylink: rename mac_link_state() op to mac_pcs_get_state() Rename the mac_link_state() method to mac_pcs_get_state() to make it clear that it should be returning the MACs PCS current state, which is used for inband negotiation rather than just reading back what the MAC has been configured for. Update the documentation to explicitly mention that this is for inband. We drop the return value as well; most of phylink doesn't check the return value and it is not clear what it should do on error - instead arrange for state->link to be false. Signed-off-by: Russell King Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/cadence/macb_main.c | 8 ++++---- drivers/net/ethernet/marvell/mvneta.c | 8 +++----- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 21 +++++++++---------- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 8 +++----- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 8 ++++---- drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 8 +++----- drivers/net/phy/phylink.c | 15 ++++++-------- include/linux/phylink.h | 25 ++++++++++++----------- net/dsa/dsa_priv.h | 4 ++-- net/dsa/port.c | 19 +++++++++-------- 10 files changed, 59 insertions(+), 65 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 8fc2e21f0bb1..d5ae2e1e0b0e 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -505,10 +505,10 @@ static void macb_validate(struct phylink_config *config, __ETHTOOL_LINK_MODE_MASK_NBITS); } -static int macb_mac_link_state(struct phylink_config *config, - struct phylink_link_state *state) +static void macb_mac_pcs_get_state(struct phylink_config *config, + struct phylink_link_state *state) { - return -EOPNOTSUPP; + state->link = 0; } static void macb_mac_an_restart(struct phylink_config *config) @@ -604,7 +604,7 @@ static void macb_mac_link_up(struct phylink_config *config, unsigned int mode, static const struct phylink_mac_ops macb_phylink_ops = { .validate = macb_validate, - .mac_link_state = macb_mac_link_state, + .mac_pcs_get_state = macb_mac_pcs_get_state, .mac_an_restart = macb_mac_an_restart, .mac_config = macb_mac_config, .mac_link_down = macb_mac_link_down, diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index a06d109c9e80..71a872d46bc4 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -3694,8 +3694,8 @@ static void mvneta_validate(struct phylink_config *config, phylink_helper_basex_speed(state); } -static int mvneta_mac_link_state(struct phylink_config *config, - struct phylink_link_state *state) +static void mvneta_mac_pcs_get_state(struct phylink_config *config, + struct phylink_link_state *state) { struct net_device *ndev = to_net_dev(config->dev); struct mvneta_port *pp = netdev_priv(ndev); @@ -3721,8 +3721,6 @@ static int mvneta_mac_link_state(struct phylink_config *config, state->pause |= MLO_PAUSE_RX; if (gmac_stat & MVNETA_GMAC_TX_FLOW_CTRL_ENABLE) state->pause |= MLO_PAUSE_TX; - - return 1; } static void mvneta_mac_an_restart(struct phylink_config *config) @@ -3915,7 +3913,7 @@ static void mvneta_mac_link_up(struct phylink_config *config, unsigned int mode, static const struct phylink_mac_ops mvneta_phylink_ops = { .validate = mvneta_validate, - .mac_link_state = mvneta_mac_link_state, + .mac_pcs_get_state = mvneta_mac_pcs_get_state, .mac_an_restart = mvneta_mac_an_restart, .mac_config = mvneta_mac_config, .mac_link_down = mvneta_mac_link_down, diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 17e24c1e1c2b..62dc2f362a16 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -4823,8 +4823,8 @@ empty_set: bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS); } -static void mvpp22_xlg_link_state(struct mvpp2_port *port, - struct phylink_link_state *state) +static void mvpp22_xlg_pcs_get_state(struct mvpp2_port *port, + struct phylink_link_state *state) { u32 val; @@ -4843,8 +4843,8 @@ static void mvpp22_xlg_link_state(struct mvpp2_port *port, state->pause |= MLO_PAUSE_RX; } -static void mvpp2_gmac_link_state(struct mvpp2_port *port, - struct phylink_link_state *state) +static void mvpp2_gmac_pcs_get_state(struct mvpp2_port *port, + struct phylink_link_state *state) { u32 val; @@ -4877,8 +4877,8 @@ static void mvpp2_gmac_link_state(struct mvpp2_port *port, state->pause |= MLO_PAUSE_TX; } -static int mvpp2_phylink_mac_link_state(struct phylink_config *config, - struct phylink_link_state *state) +static void mvpp2_phylink_mac_pcs_get_state(struct phylink_config *config, + struct phylink_link_state *state) { struct mvpp2_port *port = container_of(config, struct mvpp2_port, phylink_config); @@ -4888,13 +4888,12 @@ static int mvpp2_phylink_mac_link_state(struct phylink_config *config, mode &= MVPP22_XLG_CTRL3_MACMODESELECT_MASK; if (mode == MVPP22_XLG_CTRL3_MACMODESELECT_10G) { - mvpp22_xlg_link_state(port, state); - return 1; + mvpp22_xlg_pcs_get_state(port, state); + return; } } - mvpp2_gmac_link_state(port, state); - return 1; + mvpp2_gmac_pcs_get_state(port, state); } static void mvpp2_mac_an_restart(struct phylink_config *config) @@ -5186,7 +5185,7 @@ static void mvpp2_mac_link_down(struct phylink_config *config, static const struct phylink_mac_ops mvpp2_phylink_ops = { .validate = mvpp2_phylink_validate, - .mac_link_state = mvpp2_phylink_mac_link_state, + .mac_pcs_get_state = mvpp2_phylink_mac_pcs_get_state, .mac_an_restart = mvpp2_mac_an_restart, .mac_config = mvpp2_mac_config, .mac_link_up = mvpp2_mac_link_up, diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 1923ba76a1ec..527ad2aadcca 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -361,8 +361,8 @@ init_err: mac->id, phy_modes(state->interface), err); } -static int mtk_mac_link_state(struct phylink_config *config, - struct phylink_link_state *state) +static void mtk_mac_pcs_get_state(struct phylink_config *config, + struct phylink_link_state *state) { struct mtk_mac *mac = container_of(config, struct mtk_mac, phylink_config); @@ -391,8 +391,6 @@ static int mtk_mac_link_state(struct phylink_config *config, state->pause |= MLO_PAUSE_RX; if (pmsr & MAC_MSR_TX_FC) state->pause |= MLO_PAUSE_TX; - - return 1; } static void mtk_mac_an_restart(struct phylink_config *config) @@ -514,7 +512,7 @@ static void mtk_validate(struct phylink_config *config, static const struct phylink_mac_ops mtk_phylink_ops = { .validate = mtk_validate, - .mac_link_state = mtk_mac_link_state, + .mac_pcs_get_state = mtk_mac_pcs_get_state, .mac_an_restart = mtk_mac_an_restart, .mac_config = mtk_mac_config, .mac_link_down = mtk_mac_link_down, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 8cc4cd0cc515..644cb5d1fd4f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -868,10 +868,10 @@ static void stmmac_validate(struct phylink_config *config, __ETHTOOL_LINK_MODE_MASK_NBITS); } -static int stmmac_mac_link_state(struct phylink_config *config, - struct phylink_link_state *state) +static void stmmac_mac_pcs_get_state(struct phylink_config *config, + struct phylink_link_state *state) { - return -EOPNOTSUPP; + state->link = 0; } static void stmmac_mac_config(struct phylink_config *config, unsigned int mode, @@ -965,7 +965,7 @@ static void stmmac_mac_link_up(struct phylink_config *config, static const struct phylink_mac_ops stmmac_phylink_mac_ops = { .validate = stmmac_validate, - .mac_link_state = stmmac_mac_link_state, + .mac_pcs_get_state = stmmac_mac_pcs_get_state, .mac_config = stmmac_mac_config, .mac_an_restart = stmmac_mac_an_restart, .mac_link_down = stmmac_mac_link_down, diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 8f32db6d2c45..20746b801959 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1405,8 +1405,8 @@ static void axienet_validate(struct phylink_config *config, __ETHTOOL_LINK_MODE_MASK_NBITS); } -static int axienet_mac_link_state(struct phylink_config *config, - struct phylink_link_state *state) +static void axienet_mac_pcs_get_state(struct phylink_config *config, + struct phylink_link_state *state) { struct net_device *ndev = to_net_dev(config->dev); struct axienet_local *lp = netdev_priv(ndev); @@ -1431,8 +1431,6 @@ static int axienet_mac_link_state(struct phylink_config *config, state->an_complete = 0; state->duplex = 1; - - return 1; } static void axienet_mac_an_restart(struct phylink_config *config) @@ -1497,7 +1495,7 @@ static void axienet_mac_link_up(struct phylink_config *config, static const struct phylink_mac_ops axienet_phylink_ops = { .validate = axienet_validate, - .mac_link_state = axienet_mac_link_state, + .mac_pcs_get_state = axienet_mac_pcs_get_state, .mac_an_restart = axienet_mac_an_restart, .mac_config = axienet_mac_config, .mac_link_down = axienet_mac_link_down, diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 8e2a12885789..9a616d6bc4eb 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -357,9 +357,9 @@ static void phylink_mac_an_restart(struct phylink *pl) pl->ops->mac_an_restart(pl->config); } -static int phylink_get_mac_state(struct phylink *pl, struct phylink_link_state *state) +static void phylink_mac_pcs_get_state(struct phylink *pl, + struct phylink_link_state *state) { - linkmode_copy(state->advertising, pl->link_config.advertising); linkmode_zero(state->lp_advertising); state->interface = pl->link_config.interface; @@ -370,7 +370,7 @@ static int phylink_get_mac_state(struct phylink *pl, struct phylink_link_state * state->an_complete = 0; state->link = 1; - return pl->ops->mac_link_state(pl->config, state); + pl->ops->mac_pcs_get_state(pl->config, state); } /* The fixed state is... fixed except for the link state, @@ -493,7 +493,7 @@ static void phylink_resolve(struct work_struct *w) break; case MLO_AN_INBAND: - phylink_get_mac_state(pl, &link_state); + phylink_mac_pcs_get_state(pl, &link_state); /* If we have a phy, the "up" state is the union of * both the PHY and the MAC */ @@ -1142,7 +1142,7 @@ int phylink_ethtool_ksettings_get(struct phylink *pl, if (pl->phydev) break; - phylink_get_mac_state(pl, &link_state); + phylink_mac_pcs_get_state(pl, &link_state); /* The MAC is reporting the link results from its own PCS * layer via in-band status. Report these as the current @@ -1561,10 +1561,7 @@ static int phylink_mii_read(struct phylink *pl, unsigned int phy_id, case MLO_AN_INBAND: if (phy_id == 0) { - val = phylink_get_mac_state(pl, &state); - if (val < 0) - return val; - + phylink_mac_pcs_get_state(pl, &state); val = phylink_mii_emul_read(reg, &state); } break; diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 300ecdb6790a..fed5488e3c75 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -72,7 +72,7 @@ struct phylink_config { /** * struct phylink_mac_ops - MAC operations structure. * @validate: Validate and update the link configuration. - * @mac_link_state: Read the current link state from the hardware. + * @mac_pcs_get_state: Read the current link state from the hardware. * @mac_config: configure the MAC for the selected mode and state. * @mac_an_restart: restart 802.3z BaseX autonegotiation. * @mac_link_down: take the link down. @@ -84,8 +84,8 @@ struct phylink_mac_ops { void (*validate)(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state); - int (*mac_link_state)(struct phylink_config *config, - struct phylink_link_state *state); + void (*mac_pcs_get_state)(struct phylink_config *config, + struct phylink_link_state *state); void (*mac_config)(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state); void (*mac_an_restart)(struct phylink_config *config); @@ -127,18 +127,19 @@ void validate(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state); /** - * mac_link_state() - Read the current link state from the hardware + * mac_pcs_get_state() - Read the current inband link state from the hardware * @config: a pointer to a &struct phylink_config. * @state: a pointer to a &struct phylink_link_state. * - * Read the current link state from the MAC, reporting the current - * speed in @state->speed, duplex mode in @state->duplex, pause mode - * in @state->pause using the %MLO_PAUSE_RX and %MLO_PAUSE_TX bits, - * negotiation completion state in @state->an_complete, and link - * up state in @state->link. + * Read the current inband link state from the MAC PCS, reporting the + * current speed in @state->speed, duplex mode in @state->duplex, pause + * mode in @state->pause using the %MLO_PAUSE_RX and %MLO_PAUSE_TX bits, + * negotiation completion state in @state->an_complete, and link up state + * in @state->link. If possible, @state->lp_advertising should also be + * populated. */ -int mac_link_state(struct phylink_config *config, - struct phylink_link_state *state); +void mac_pcs_get_state(struct phylink_config *config, + struct phylink_link_state *state); /** * mac_config() - configure the MAC for the selected mode and state @@ -166,7 +167,7 @@ int mac_link_state(struct phylink_config *config, * 1000base-X or Cisco SGMII mode depending on the @state->interface * mode). In both cases, link state management (whether the link * is up or not) is performed by the MAC, and reported via the - * mac_link_state() callback. Changes in link state must be made + * mac_pcs_get_state() callback. Changes in link state must be made * by calling phylink_mac_change(). * * If in 802.3z mode, the link speed is fixed, dependent on the diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 53e7577896b6..2dd86d9bcda9 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -153,8 +153,8 @@ void dsa_port_link_unregister_of(struct dsa_port *dp); void dsa_port_phylink_validate(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state); -int dsa_port_phylink_mac_link_state(struct phylink_config *config, - struct phylink_link_state *state); +void dsa_port_phylink_mac_pcs_get_state(struct phylink_config *config, + struct phylink_link_state *state); void dsa_port_phylink_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state); diff --git a/net/dsa/port.c b/net/dsa/port.c index 6e93c36bf0c0..46ac9ba21987 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -429,19 +429,22 @@ void dsa_port_phylink_validate(struct phylink_config *config, } EXPORT_SYMBOL_GPL(dsa_port_phylink_validate); -int dsa_port_phylink_mac_link_state(struct phylink_config *config, - struct phylink_link_state *state) +void dsa_port_phylink_mac_pcs_get_state(struct phylink_config *config, + struct phylink_link_state *state) { struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); struct dsa_switch *ds = dp->ds; - /* Only called for SGMII and 802.3z */ - if (!ds->ops->phylink_mac_link_state) - return -EOPNOTSUPP; + /* Only called for inband modes */ + if (!ds->ops->phylink_mac_link_state) { + state->link = 0; + return; + } - return ds->ops->phylink_mac_link_state(ds, dp->index, state); + if (ds->ops->phylink_mac_link_state(ds, dp->index, state) < 0) + state->link = 0; } -EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_link_state); +EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_pcs_get_state); void dsa_port_phylink_mac_config(struct phylink_config *config, unsigned int mode, @@ -510,7 +513,7 @@ EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_link_up); const struct phylink_mac_ops dsa_port_phylink_mac_ops = { .validate = dsa_port_phylink_validate, - .mac_link_state = dsa_port_phylink_mac_link_state, + .mac_pcs_get_state = dsa_port_phylink_mac_pcs_get_state, .mac_config = dsa_port_phylink_mac_config, .mac_an_restart = dsa_port_phylink_mac_an_restart, .mac_link_down = dsa_port_phylink_mac_link_down, -- cgit v1.2.3-71-gd317 From 4b3da77b72ad6b3c48c6fe4a395ace7db39a12c5 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 22 Nov 2019 21:07:54 +0100 Subject: bpf, x86: Generalize and extend bpf_arch_text_poke for direct jumps Add BPF_MOD_{NOP_TO_JUMP,JUMP_TO_JUMP,JUMP_TO_NOP} patching for x86 JIT in order to be able to patch direct jumps or nop them out. We need this facility in order to patch tail call jumps and in later work also BPF static keys. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/aa4784196a8e5e985af4b30a4fe5336bce6e9643.1574452833.git.daniel@iogearbox.net --- arch/x86/net/bpf_jit_comp.c | 64 ++++++++++++++++++++++++++++++++------------- include/linux/bpf.h | 6 +++++ 2 files changed, 52 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 2e586f579945..f438bd3b7689 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -203,8 +203,9 @@ struct jit_context { /* Maximum number of bytes emitted while JITing one eBPF insn */ #define BPF_MAX_INSN_SIZE 128 #define BPF_INSN_SAFETY 64 -/* number of bytes emit_call() needs to generate call instruction */ -#define X86_CALL_SIZE 5 + +/* Number of bytes emit_patch() needs to generate instructions */ +#define X86_PATCH_SIZE 5 #define PROLOGUE_SIZE 25 @@ -215,7 +216,7 @@ struct jit_context { static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf) { u8 *prog = *pprog; - int cnt = X86_CALL_SIZE; + int cnt = X86_PATCH_SIZE; /* BPF trampoline can be made to work without these nops, * but let's waste 5 bytes for now and optimize later @@ -480,64 +481,91 @@ static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) *pprog = prog; } -static int emit_call(u8 **pprog, void *func, void *ip) +static int emit_patch(u8 **pprog, void *func, void *ip, u8 opcode) { u8 *prog = *pprog; int cnt = 0; s64 offset; - offset = func - (ip + X86_CALL_SIZE); + offset = func - (ip + X86_PATCH_SIZE); if (!is_simm32(offset)) { pr_err("Target call %p is out of range\n", func); return -EINVAL; } - EMIT1_off32(0xE8, offset); + EMIT1_off32(opcode, offset); *pprog = prog; return 0; } +static int emit_call(u8 **pprog, void *func, void *ip) +{ + return emit_patch(pprog, func, ip, 0xE8); +} + +static int emit_jump(u8 **pprog, void *func, void *ip) +{ + return emit_patch(pprog, func, ip, 0xE9); +} + int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *old_addr, void *new_addr) { - u8 old_insn[X86_CALL_SIZE] = {}; - u8 new_insn[X86_CALL_SIZE] = {}; + int (*emit_patch_fn)(u8 **pprog, void *func, void *ip); + u8 old_insn[X86_PATCH_SIZE] = {}; + u8 new_insn[X86_PATCH_SIZE] = {}; u8 *prog; int ret; if (!is_kernel_text((long)ip) && !is_bpf_text_address((long)ip)) - /* BPF trampoline in modules is not supported */ + /* BPF poking in modules is not supported */ return -EINVAL; + switch (t) { + case BPF_MOD_NOP_TO_CALL ... BPF_MOD_CALL_TO_NOP: + emit_patch_fn = emit_call; + break; + case BPF_MOD_NOP_TO_JUMP ... BPF_MOD_JUMP_TO_NOP: + emit_patch_fn = emit_jump; + break; + default: + return -ENOTSUPP; + } + if (old_addr) { prog = old_insn; - ret = emit_call(&prog, old_addr, (void *)ip); + ret = emit_patch_fn(&prog, old_addr, (void *)ip); if (ret) return ret; } if (new_addr) { prog = new_insn; - ret = emit_call(&prog, new_addr, (void *)ip); + ret = emit_patch_fn(&prog, new_addr, (void *)ip); if (ret) return ret; } + ret = -EBUSY; mutex_lock(&text_mutex); switch (t) { case BPF_MOD_NOP_TO_CALL: - if (memcmp(ip, ideal_nops[NOP_ATOMIC5], X86_CALL_SIZE)) + case BPF_MOD_NOP_TO_JUMP: + if (memcmp(ip, ideal_nops[NOP_ATOMIC5], X86_PATCH_SIZE)) goto out; - text_poke_bp(ip, new_insn, X86_CALL_SIZE, NULL); + text_poke_bp(ip, new_insn, X86_PATCH_SIZE, NULL); break; case BPF_MOD_CALL_TO_CALL: - if (memcmp(ip, old_insn, X86_CALL_SIZE)) + case BPF_MOD_JUMP_TO_JUMP: + if (memcmp(ip, old_insn, X86_PATCH_SIZE)) goto out; - text_poke_bp(ip, new_insn, X86_CALL_SIZE, NULL); + text_poke_bp(ip, new_insn, X86_PATCH_SIZE, NULL); break; case BPF_MOD_CALL_TO_NOP: - if (memcmp(ip, old_insn, X86_CALL_SIZE)) + case BPF_MOD_JUMP_TO_NOP: + if (memcmp(ip, old_insn, X86_PATCH_SIZE)) goto out; - text_poke_bp(ip, ideal_nops[NOP_ATOMIC5], X86_CALL_SIZE, NULL); + text_poke_bp(ip, ideal_nops[NOP_ATOMIC5], X86_PATCH_SIZE, + NULL); break; } ret = 0; @@ -1394,7 +1422,7 @@ int arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags /* skip patched call instruction and point orig_call to actual * body of the kernel function. */ - orig_call += X86_CALL_SIZE; + orig_call += X86_PATCH_SIZE; prog = image; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e89e86122233..7978b617caa8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1284,10 +1284,16 @@ static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, #endif /* CONFIG_INET */ enum bpf_text_poke_type { + /* All call-related pokes. */ BPF_MOD_NOP_TO_CALL, BPF_MOD_CALL_TO_CALL, BPF_MOD_CALL_TO_NOP, + /* All jump-related pokes. */ + BPF_MOD_NOP_TO_JUMP, + BPF_MOD_JUMP_TO_JUMP, + BPF_MOD_JUMP_TO_NOP, }; + int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2); -- cgit v1.2.3-71-gd317 From 6332be04c039a72fca32ed0a4265bac58d606bb6 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 22 Nov 2019 21:07:55 +0100 Subject: bpf: Move bpf_free_used_maps into sleepable section We later on are going to need a sleepable context as opposed to plain RCU callback in order to untrack programs we need to poke at runtime and tracking as well as image update is performed under mutex. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/09823b1d5262876e9b83a8e75df04cf0467357a4.1574452833.git.daniel@iogearbox.net --- include/linux/bpf.h | 4 ++++ kernel/bpf/core.c | 23 +++++++++++++++++++++++ kernel/bpf/syscall.c | 20 -------------------- 3 files changed, 27 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7978b617caa8..561b920f0bf7 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1031,6 +1031,10 @@ static inline int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, { return -ENOTSUPP; } + +static inline void bpf_map_put(struct bpf_map *map) +{ +} #endif /* CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index b5945c3aaa8e..0e825c164f1a 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2003,12 +2003,35 @@ int bpf_prog_array_copy_info(struct bpf_prog_array *array, : 0; } +static void bpf_free_cgroup_storage(struct bpf_prog_aux *aux) +{ + enum bpf_cgroup_storage_type stype; + + for_each_cgroup_storage_type(stype) { + if (!aux->cgroup_storage[stype]) + continue; + bpf_cgroup_storage_release(aux->prog, + aux->cgroup_storage[stype]); + } +} + +static void bpf_free_used_maps(struct bpf_prog_aux *aux) +{ + int i; + + bpf_free_cgroup_storage(aux); + for (i = 0; i < aux->used_map_cnt; i++) + bpf_map_put(aux->used_maps[i]); + kfree(aux->used_maps); +} + static void bpf_prog_free_deferred(struct work_struct *work) { struct bpf_prog_aux *aux; int i; aux = container_of(work, struct bpf_prog_aux, work); + bpf_free_used_maps(aux); if (bpf_prog_is_dev_bound(aux)) bpf_prog_offload_destroy(aux->prog); #ifdef CONFIG_PERF_EVENTS diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 4ae52eb05f41..373778da8489 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1302,25 +1302,6 @@ static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) return 0; } -/* drop refcnt on maps used by eBPF program and free auxilary data */ -static void free_used_maps(struct bpf_prog_aux *aux) -{ - enum bpf_cgroup_storage_type stype; - int i; - - for_each_cgroup_storage_type(stype) { - if (!aux->cgroup_storage[stype]) - continue; - bpf_cgroup_storage_release(aux->prog, - aux->cgroup_storage[stype]); - } - - for (i = 0; i < aux->used_map_cnt; i++) - bpf_map_put(aux->used_maps[i]); - - kfree(aux->used_maps); -} - int __bpf_prog_charge(struct user_struct *user, u32 pages) { unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; @@ -1415,7 +1396,6 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) kvfree(aux->func_info); kfree(aux->func_info_aux); - free_used_maps(aux); bpf_prog_uncharge_memlock(aux->prog); security_bpf_prog_free(aux); bpf_prog_free(aux->prog); -- cgit v1.2.3-71-gd317 From 2beee5f57441413b64a9c2bd657e17beabb98d1c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 22 Nov 2019 21:07:56 +0100 Subject: bpf: Move owner type, jited info into array auxiliary data We're going to extend this with further information which is only relevant for prog array at this point. Given this info is not used in critical path, move it into its own structure such that the main array map structure can be kept on diet. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/b9ddccdb0f6f7026489ee955f16c96381e1e7238.1574452833.git.daniel@iogearbox.net --- include/linux/bpf.h | 18 +++++++++++------- kernel/bpf/arraymap.c | 32 ++++++++++++++++++++++++++++++-- kernel/bpf/core.c | 11 +++++------ kernel/bpf/map_in_map.c | 5 ++--- kernel/bpf/syscall.c | 16 ++++++---------- 5 files changed, 54 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 561b920f0bf7..c3b29061284e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -560,17 +560,21 @@ struct bpf_prog_aux { }; }; +struct bpf_array_aux { + /* 'Ownership' of prog array is claimed by the first program that + * is going to use this map or by the first program which FD is + * stored in the map to make sure that all callers and callees have + * the same prog type and JITed flag. + */ + enum bpf_prog_type type; + bool jited; +}; + struct bpf_array { struct bpf_map map; u32 elem_size; u32 index_mask; - /* 'ownership' of prog_array is claimed by the first program that - * is going to use this map or by the first program which FD is stored - * in the map to make sure that all callers and callees have the same - * prog_type and JITed flag - */ - enum bpf_prog_type owner_prog_type; - bool owner_jited; + struct bpf_array_aux *aux; union { char value[0] __aligned(8); void *ptrs[0] __aligned(8); diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 633c8c701ff6..57da950ee55b 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -671,10 +671,38 @@ static void prog_array_map_seq_show_elem(struct bpf_map *map, void *key, rcu_read_unlock(); } +static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr) +{ + struct bpf_array_aux *aux; + struct bpf_map *map; + + aux = kzalloc(sizeof(*aux), GFP_KERNEL); + if (!aux) + return ERR_PTR(-ENOMEM); + + map = array_map_alloc(attr); + if (IS_ERR(map)) { + kfree(aux); + return map; + } + + container_of(map, struct bpf_array, map)->aux = aux; + return map; +} + +static void prog_array_map_free(struct bpf_map *map) +{ + struct bpf_array_aux *aux; + + aux = container_of(map, struct bpf_array, map)->aux; + kfree(aux); + fd_array_map_free(map); +} + const struct bpf_map_ops prog_array_map_ops = { .map_alloc_check = fd_array_map_alloc_check, - .map_alloc = array_map_alloc, - .map_free = fd_array_map_free, + .map_alloc = prog_array_map_alloc, + .map_free = prog_array_map_free, .map_get_next_key = array_map_get_next_key, .map_lookup_elem = fd_array_map_lookup_elem, .map_delete_elem = fd_array_map_delete_elem, diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 0e825c164f1a..07af9c1d9cf1 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1691,18 +1691,17 @@ bool bpf_prog_array_compatible(struct bpf_array *array, if (fp->kprobe_override) return false; - if (!array->owner_prog_type) { + if (!array->aux->type) { /* There's no owner yet where we could check for * compatibility. */ - array->owner_prog_type = fp->type; - array->owner_jited = fp->jited; - + array->aux->type = fp->type; + array->aux->jited = fp->jited; return true; } - return array->owner_prog_type == fp->type && - array->owner_jited == fp->jited; + return array->aux->type == fp->type && + array->aux->jited == fp->jited; } static int bpf_check_tail_call(const struct bpf_prog *fp) diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index 4cbe987be35b..5e9366b33f0f 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -17,9 +17,8 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) if (IS_ERR(inner_map)) return inner_map; - /* prog_array->owner_prog_type and owner_jited - * is a runtime binding. Doing static check alone - * in the verifier is not enough. + /* prog_array->aux->{type,jited} is a runtime binding. + * Doing static check alone in the verifier is not enough. */ if (inner_map->map_type == BPF_MAP_TYPE_PROG_ARRAY || inner_map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE || diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 373778da8489..b904d56ec686 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -389,13 +389,12 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_map *map = filp->private_data; const struct bpf_array *array; - u32 owner_prog_type = 0; - u32 owner_jited = 0; + u32 type = 0, jited = 0; if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) { array = container_of(map, struct bpf_array, map); - owner_prog_type = array->owner_prog_type; - owner_jited = array->owner_jited; + type = array->aux->type; + jited = array->aux->jited; } seq_printf(m, @@ -415,12 +414,9 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) map->memory.pages * 1ULL << PAGE_SHIFT, map->id, READ_ONCE(map->frozen)); - - if (owner_prog_type) { - seq_printf(m, "owner_prog_type:\t%u\n", - owner_prog_type); - seq_printf(m, "owner_jited:\t%u\n", - owner_jited); + if (type) { + seq_printf(m, "owner_prog_type:\t%u\n", type); + seq_printf(m, "owner_jited:\t%u\n", jited); } } #endif -- cgit v1.2.3-71-gd317 From a66886fe6c24ebeeb6dc10fbd9b75158029eacf7 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 22 Nov 2019 21:07:57 +0100 Subject: bpf: Add initial poke descriptor table for jit images Add initial poke table data structures and management to the BPF prog that can later be used by JITs. Also add an instance of poke specific data for tail call maps; plan for later work is to extend this also for BPF static keys. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/1db285ec2ea4207ee0455b3f8e191a4fc58b9ade.1574452833.git.daniel@iogearbox.net --- include/linux/bpf.h | 20 ++++++++++++++++++++ include/linux/filter.h | 10 ++++++++++ kernel/bpf/core.c | 34 ++++++++++++++++++++++++++++++++++ 3 files changed, 64 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c3b29061284e..312983bf7faa 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -488,6 +488,24 @@ struct bpf_func_info_aux { bool unreliable; }; +enum bpf_jit_poke_reason { + BPF_POKE_REASON_TAIL_CALL, +}; + +/* Descriptor of pokes pointing /into/ the JITed image. */ +struct bpf_jit_poke_descriptor { + void *ip; + union { + struct { + struct bpf_map *map; + u32 key; + } tail_call; + }; + bool ip_stable; + u8 adj_off; + u16 reason; +}; + struct bpf_prog_aux { atomic64_t refcnt; u32 used_map_cnt; @@ -513,6 +531,8 @@ struct bpf_prog_aux { const char *attach_func_name; struct bpf_prog **func; void *jit_data; /* JIT specific data. arch dependent */ + struct bpf_jit_poke_descriptor *poke_tab; + u32 size_poke_tab; struct latch_tree_node ksym_tnode; struct list_head ksym_lnode; const struct bpf_prog_ops *ops; diff --git a/include/linux/filter.h b/include/linux/filter.h index ad80e9c6111c..796b60d8cc6c 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -952,6 +952,9 @@ void *bpf_jit_alloc_exec(unsigned long size); void bpf_jit_free_exec(void *addr); void bpf_jit_free(struct bpf_prog *fp); +int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, + struct bpf_jit_poke_descriptor *poke); + int bpf_jit_get_func_addr(const struct bpf_prog *prog, const struct bpf_insn *insn, bool extra_pass, u64 *func_addr, bool *func_addr_fixed); @@ -1055,6 +1058,13 @@ static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp) return false; } +static inline int +bpf_jit_add_poke_descriptor(struct bpf_prog *prog, + struct bpf_jit_poke_descriptor *poke) +{ + return -ENOTSUPP; +} + static inline void bpf_jit_free(struct bpf_prog *fp) { bpf_prog_unlock_free(fp); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 07af9c1d9cf1..608b7085e0c9 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -256,6 +256,7 @@ void __bpf_prog_free(struct bpf_prog *fp) { if (fp->aux) { free_percpu(fp->aux->stats); + kfree(fp->aux->poke_tab); kfree(fp->aux); } vfree(fp); @@ -756,6 +757,39 @@ int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, return ret; } +int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, + struct bpf_jit_poke_descriptor *poke) +{ + struct bpf_jit_poke_descriptor *tab = prog->aux->poke_tab; + static const u32 poke_tab_max = 1024; + u32 slot = prog->aux->size_poke_tab; + u32 size = slot + 1; + + if (size > poke_tab_max) + return -ENOSPC; + if (poke->ip || poke->ip_stable || poke->adj_off) + return -EINVAL; + + switch (poke->reason) { + case BPF_POKE_REASON_TAIL_CALL: + if (!poke->tail_call.map) + return -EINVAL; + break; + default: + return -EINVAL; + } + + tab = krealloc(tab, size * sizeof(*poke), GFP_KERNEL); + if (!tab) + return -ENOMEM; + + memcpy(&tab[slot], poke, sizeof(*poke)); + prog->aux->size_poke_tab = size; + prog->aux->poke_tab = tab; + + return slot; +} + static atomic_long_t bpf_jit_current; /* Can be overridden by an arch's JIT compiler if it has a custom, -- cgit v1.2.3-71-gd317 From da765a2f599304a81a25e77908d1790414ecdbb6 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 22 Nov 2019 21:07:58 +0100 Subject: bpf: Add poke dependency tracking for prog array maps This work adds program tracking to prog array maps. This is needed such that upon prog array updates/deletions we can fix up all programs which make use of this tail call map. We add ops->map_poke_{un,}track() helpers to maps to maintain the list of programs and ops->map_poke_run() for triggering the actual update. bpf_array_aux is extended to contain the list head and poke_mutex in order to serialize program patching during updates/deletions. bpf_free_used_maps() will untrack the program shortly before dropping the reference to the map. For clearing out the prog array once all urefs are dropped we need to use schedule_work() to have a sleepable context. The prog_array_map_poke_run() is triggered during updates/deletions and walks the maintained prog list. It checks in their poke_tabs whether the map and key is matching and runs the actual bpf_arch_text_poke() for patching in the nop or new jmp location. Depending on the type of update, we use one of BPF_MOD_{NOP_TO_JUMP,JUMP_TO_NOP,JUMP_TO_JUMP}. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/1fb364bb3c565b3e415d5ea348f036ff379e779d.1574452833.git.daniel@iogearbox.net --- include/linux/bpf.h | 12 ++++ kernel/bpf/arraymap.c | 183 ++++++++++++++++++++++++++++++++++++++++++++++++-- kernel/bpf/core.c | 9 ++- kernel/bpf/syscall.c | 20 ++++-- 4 files changed, 212 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 312983bf7faa..c2f07fd410c1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -22,6 +22,7 @@ struct bpf_verifier_env; struct bpf_verifier_log; struct perf_event; struct bpf_prog; +struct bpf_prog_aux; struct bpf_map; struct sock; struct seq_file; @@ -64,6 +65,12 @@ struct bpf_map_ops { const struct btf_type *key_type, const struct btf_type *value_type); + /* Prog poke tracking helpers. */ + int (*map_poke_track)(struct bpf_map *map, struct bpf_prog_aux *aux); + void (*map_poke_untrack)(struct bpf_map *map, struct bpf_prog_aux *aux); + void (*map_poke_run)(struct bpf_map *map, u32 key, struct bpf_prog *old, + struct bpf_prog *new); + /* Direct value access helpers. */ int (*map_direct_value_addr)(const struct bpf_map *map, u64 *imm, u32 off); @@ -588,6 +595,11 @@ struct bpf_array_aux { */ enum bpf_prog_type type; bool jited; + /* Programs with direct jumps into programs part of this array. */ + struct list_head poke_progs; + struct bpf_map *map; + struct mutex poke_mutex; + struct work_struct work; }; struct bpf_array { diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 57da950ee55b..58bdf5fd24cc 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -586,10 +586,17 @@ int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file, if (IS_ERR(new_ptr)) return PTR_ERR(new_ptr); - old_ptr = xchg(array->ptrs + index, new_ptr); + if (map->ops->map_poke_run) { + mutex_lock(&array->aux->poke_mutex); + old_ptr = xchg(array->ptrs + index, new_ptr); + map->ops->map_poke_run(map, index, old_ptr, new_ptr); + mutex_unlock(&array->aux->poke_mutex); + } else { + old_ptr = xchg(array->ptrs + index, new_ptr); + } + if (old_ptr) map->ops->map_fd_put_ptr(old_ptr); - return 0; } @@ -602,7 +609,15 @@ static int fd_array_map_delete_elem(struct bpf_map *map, void *key) if (index >= array->map.max_entries) return -E2BIG; - old_ptr = xchg(array->ptrs + index, NULL); + if (map->ops->map_poke_run) { + mutex_lock(&array->aux->poke_mutex); + old_ptr = xchg(array->ptrs + index, NULL); + map->ops->map_poke_run(map, index, old_ptr, NULL); + mutex_unlock(&array->aux->poke_mutex); + } else { + old_ptr = xchg(array->ptrs + index, NULL); + } + if (old_ptr) { map->ops->map_fd_put_ptr(old_ptr); return 0; @@ -671,6 +686,152 @@ static void prog_array_map_seq_show_elem(struct bpf_map *map, void *key, rcu_read_unlock(); } +struct prog_poke_elem { + struct list_head list; + struct bpf_prog_aux *aux; +}; + +static int prog_array_map_poke_track(struct bpf_map *map, + struct bpf_prog_aux *prog_aux) +{ + struct prog_poke_elem *elem; + struct bpf_array_aux *aux; + int ret = 0; + + aux = container_of(map, struct bpf_array, map)->aux; + mutex_lock(&aux->poke_mutex); + list_for_each_entry(elem, &aux->poke_progs, list) { + if (elem->aux == prog_aux) + goto out; + } + + elem = kmalloc(sizeof(*elem), GFP_KERNEL); + if (!elem) { + ret = -ENOMEM; + goto out; + } + + INIT_LIST_HEAD(&elem->list); + /* We must track the program's aux info at this point in time + * since the program pointer itself may not be stable yet, see + * also comment in prog_array_map_poke_run(). + */ + elem->aux = prog_aux; + + list_add_tail(&elem->list, &aux->poke_progs); +out: + mutex_unlock(&aux->poke_mutex); + return ret; +} + +static void prog_array_map_poke_untrack(struct bpf_map *map, + struct bpf_prog_aux *prog_aux) +{ + struct prog_poke_elem *elem, *tmp; + struct bpf_array_aux *aux; + + aux = container_of(map, struct bpf_array, map)->aux; + mutex_lock(&aux->poke_mutex); + list_for_each_entry_safe(elem, tmp, &aux->poke_progs, list) { + if (elem->aux == prog_aux) { + list_del_init(&elem->list); + kfree(elem); + break; + } + } + mutex_unlock(&aux->poke_mutex); +} + +static void prog_array_map_poke_run(struct bpf_map *map, u32 key, + struct bpf_prog *old, + struct bpf_prog *new) +{ + enum bpf_text_poke_type type; + struct prog_poke_elem *elem; + struct bpf_array_aux *aux; + + if (!old && new) + type = BPF_MOD_NOP_TO_JUMP; + else if (old && !new) + type = BPF_MOD_JUMP_TO_NOP; + else if (old && new) + type = BPF_MOD_JUMP_TO_JUMP; + else + return; + + aux = container_of(map, struct bpf_array, map)->aux; + WARN_ON_ONCE(!mutex_is_locked(&aux->poke_mutex)); + + list_for_each_entry(elem, &aux->poke_progs, list) { + struct bpf_jit_poke_descriptor *poke; + int i, ret; + + for (i = 0; i < elem->aux->size_poke_tab; i++) { + poke = &elem->aux->poke_tab[i]; + + /* Few things to be aware of: + * + * 1) We can only ever access aux in this context, but + * not aux->prog since it might not be stable yet and + * there could be danger of use after free otherwise. + * 2) Initially when we start tracking aux, the program + * is not JITed yet and also does not have a kallsyms + * entry. We skip these as poke->ip_stable is not + * active yet. The JIT will do the final fixup before + * setting it stable. The various poke->ip_stable are + * successively activated, so tail call updates can + * arrive from here while JIT is still finishing its + * final fixup for non-activated poke entries. + * 3) On program teardown, the program's kallsym entry gets + * removed out of RCU callback, but we can only untrack + * from sleepable context, therefore bpf_arch_text_poke() + * might not see that this is in BPF text section and + * bails out with -EINVAL. As these are unreachable since + * RCU grace period already passed, we simply skip them. + * 4) Also programs reaching refcount of zero while patching + * is in progress is okay since we're protected under + * poke_mutex and untrack the programs before the JIT + * buffer is freed. When we're still in the middle of + * patching and suddenly kallsyms entry of the program + * gets evicted, we just skip the rest which is fine due + * to point 3). + * 5) Any other error happening below from bpf_arch_text_poke() + * is a unexpected bug. + */ + if (!READ_ONCE(poke->ip_stable)) + continue; + if (poke->reason != BPF_POKE_REASON_TAIL_CALL) + continue; + if (poke->tail_call.map != map || + poke->tail_call.key != key) + continue; + + ret = bpf_arch_text_poke(poke->ip, type, + old ? (u8 *)old->bpf_func + + poke->adj_off : NULL, + new ? (u8 *)new->bpf_func + + poke->adj_off : NULL); + BUG_ON(ret < 0 && ret != -EINVAL); + } + } +} + +static void prog_array_map_clear_deferred(struct work_struct *work) +{ + struct bpf_map *map = container_of(work, struct bpf_array_aux, + work)->map; + bpf_fd_array_map_clear(map); + bpf_map_put(map); +} + +static void prog_array_map_clear(struct bpf_map *map) +{ + struct bpf_array_aux *aux = container_of(map, struct bpf_array, + map)->aux; + bpf_map_inc(map); + schedule_work(&aux->work); +} + static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr) { struct bpf_array_aux *aux; @@ -680,6 +841,10 @@ static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr) if (!aux) return ERR_PTR(-ENOMEM); + INIT_WORK(&aux->work, prog_array_map_clear_deferred); + INIT_LIST_HEAD(&aux->poke_progs); + mutex_init(&aux->poke_mutex); + map = array_map_alloc(attr); if (IS_ERR(map)) { kfree(aux); @@ -687,14 +852,21 @@ static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr) } container_of(map, struct bpf_array, map)->aux = aux; + aux->map = map; + return map; } static void prog_array_map_free(struct bpf_map *map) { + struct prog_poke_elem *elem, *tmp; struct bpf_array_aux *aux; aux = container_of(map, struct bpf_array, map)->aux; + list_for_each_entry_safe(elem, tmp, &aux->poke_progs, list) { + list_del_init(&elem->list); + kfree(elem); + } kfree(aux); fd_array_map_free(map); } @@ -703,13 +875,16 @@ const struct bpf_map_ops prog_array_map_ops = { .map_alloc_check = fd_array_map_alloc_check, .map_alloc = prog_array_map_alloc, .map_free = prog_array_map_free, + .map_poke_track = prog_array_map_poke_track, + .map_poke_untrack = prog_array_map_poke_untrack, + .map_poke_run = prog_array_map_poke_run, .map_get_next_key = array_map_get_next_key, .map_lookup_elem = fd_array_map_lookup_elem, .map_delete_elem = fd_array_map_delete_elem, .map_fd_get_ptr = prog_fd_array_get_ptr, .map_fd_put_ptr = prog_fd_array_put_ptr, .map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem, - .map_release_uref = bpf_fd_array_map_clear, + .map_release_uref = prog_array_map_clear, .map_seq_show_elem = prog_array_map_seq_show_elem, }; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 608b7085e0c9..49e32acad7d8 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2050,11 +2050,16 @@ static void bpf_free_cgroup_storage(struct bpf_prog_aux *aux) static void bpf_free_used_maps(struct bpf_prog_aux *aux) { + struct bpf_map *map; int i; bpf_free_cgroup_storage(aux); - for (i = 0; i < aux->used_map_cnt; i++) - bpf_map_put(aux->used_maps[i]); + for (i = 0; i < aux->used_map_cnt; i++) { + map = aux->used_maps[i]; + if (map->ops->map_poke_untrack) + map->ops->map_poke_untrack(map, aux); + bpf_map_put(map); + } kfree(aux->used_maps); } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b904d56ec686..e3461ec59570 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -25,12 +25,13 @@ #include #include -#define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \ - (map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ - (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \ - (map)->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) +#define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ + (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \ + (map)->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) +#define IS_FD_PROG_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY) #define IS_FD_HASH(map) ((map)->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) -#define IS_FD_MAP(map) (IS_FD_ARRAY(map) || IS_FD_HASH(map)) +#define IS_FD_MAP(map) (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map) || \ + IS_FD_HASH(map)) #define BPF_OBJ_FLAG_MASK (BPF_F_RDONLY | BPF_F_WRONLY) @@ -877,7 +878,7 @@ static int map_lookup_elem(union bpf_attr *attr) err = bpf_percpu_cgroup_storage_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) { err = bpf_stackmap_copy(map, key, value); - } else if (IS_FD_ARRAY(map)) { + } else if (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map)) { err = bpf_fd_array_map_lookup_elem(map, key, value); } else if (IS_FD_HASH(map)) { err = bpf_fd_htab_map_lookup_elem(map, key, value); @@ -1004,6 +1005,10 @@ static int map_update_elem(union bpf_attr *attr) map->map_type == BPF_MAP_TYPE_SOCKMAP) { err = map->ops->map_update_elem(map, key, value, attr->flags); goto out; + } else if (IS_FD_PROG_ARRAY(map)) { + err = bpf_fd_array_map_update_elem(map, f.file, key, value, + attr->flags); + goto out; } /* must increment bpf_prog_active to avoid kprobe+bpf triggering from @@ -1086,6 +1091,9 @@ static int map_delete_elem(union bpf_attr *attr) if (bpf_map_is_dev_bound(map)) { err = bpf_map_offload_delete_elem(map, key); goto out; + } else if (IS_FD_PROG_ARRAY(map)) { + err = map->ops->map_delete_elem(map, key); + goto out; } preempt_disable(); -- cgit v1.2.3-71-gd317 From d2e4c1e6c2947269346054ac8937ccfe9e0bcc6b Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 22 Nov 2019 21:07:59 +0100 Subject: bpf: Constant map key tracking for prog array pokes Add tracking of constant keys into tail call maps. The signature of bpf_tail_call_proto is that arg1 is ctx, arg2 map pointer and arg3 is a index key. The direct call approach for tail calls can be enabled if the verifier asserted that for all branches leading to the tail call helper invocation, the map pointer and index key were both constant and the same. Tracking of map pointers we already do from prior work via c93552c443eb ("bpf: properly enforce index mask to prevent out-of-bounds speculation") and 09772d92cd5a ("bpf: avoid retpoline for lookup/update/ delete calls on maps"). Given the tail call map index key is not on stack but directly in the register, we can add similar tracking approach and later in fixup_bpf_calls() add a poke descriptor to the progs poke_tab with the relevant information for the JITing phase. We internally reuse insn->imm for the rewritten BPF_JMP | BPF_TAIL_CALL instruction in order to point into the prog's poke_tab, and keep insn->imm as 0 as indicator that current indirect tail call emission must be used. Note that publishing to the tracker must happen at the end of fixup_bpf_calls() since adding elements to the poke_tab reallocates its memory, so we need to wait until its in final state. Future work can generalize and add similar approach to optimize plain array map lookups. Difference there is that we need to look into the key value that sits on stack. For clarity in bpf_insn_aux_data, map_state has been renamed into map_ptr_state, so we get map_{ptr,key}_state as trackers. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/e8db37f6b2ae60402fa40216c96738ee9b316c32.1574452833.git.daniel@iogearbox.net --- include/linux/bpf_verifier.h | 3 +- kernel/bpf/verifier.c | 120 +++++++++++++++++++++++++++++++++++++++---- 2 files changed, 113 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index cdd08bf0ec06..26e40de9ef55 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -293,7 +293,7 @@ struct bpf_verifier_state_list { struct bpf_insn_aux_data { union { enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ - unsigned long map_state; /* pointer/poison value for maps */ + unsigned long map_ptr_state; /* pointer/poison value for maps */ s32 call_imm; /* saved imm field of call insn */ u32 alu_limit; /* limit for add/sub register with pointer */ struct { @@ -301,6 +301,7 @@ struct bpf_insn_aux_data { u32 map_off; /* offset from value base address */ }; }; + u64 map_key_state; /* constant (32 bit) key tracking for maps */ int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ int sanitize_stack_off; /* stack slot to be cleared */ bool seen; /* this insn was processed by the verifier */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index fc85714428c7..a0482e1c4a77 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -171,6 +171,9 @@ struct bpf_verifier_stack_elem { #define BPF_COMPLEXITY_LIMIT_JMP_SEQ 8192 #define BPF_COMPLEXITY_LIMIT_STATES 64 +#define BPF_MAP_KEY_POISON (1ULL << 63) +#define BPF_MAP_KEY_SEEN (1ULL << 62) + #define BPF_MAP_PTR_UNPRIV 1UL #define BPF_MAP_PTR_POISON ((void *)((0xeB9FUL << 1) + \ POISON_POINTER_DELTA)) @@ -178,12 +181,12 @@ struct bpf_verifier_stack_elem { static bool bpf_map_ptr_poisoned(const struct bpf_insn_aux_data *aux) { - return BPF_MAP_PTR(aux->map_state) == BPF_MAP_PTR_POISON; + return BPF_MAP_PTR(aux->map_ptr_state) == BPF_MAP_PTR_POISON; } static bool bpf_map_ptr_unpriv(const struct bpf_insn_aux_data *aux) { - return aux->map_state & BPF_MAP_PTR_UNPRIV; + return aux->map_ptr_state & BPF_MAP_PTR_UNPRIV; } static void bpf_map_ptr_store(struct bpf_insn_aux_data *aux, @@ -191,8 +194,31 @@ static void bpf_map_ptr_store(struct bpf_insn_aux_data *aux, { BUILD_BUG_ON((unsigned long)BPF_MAP_PTR_POISON & BPF_MAP_PTR_UNPRIV); unpriv |= bpf_map_ptr_unpriv(aux); - aux->map_state = (unsigned long)map | - (unpriv ? BPF_MAP_PTR_UNPRIV : 0UL); + aux->map_ptr_state = (unsigned long)map | + (unpriv ? BPF_MAP_PTR_UNPRIV : 0UL); +} + +static bool bpf_map_key_poisoned(const struct bpf_insn_aux_data *aux) +{ + return aux->map_key_state & BPF_MAP_KEY_POISON; +} + +static bool bpf_map_key_unseen(const struct bpf_insn_aux_data *aux) +{ + return !(aux->map_key_state & BPF_MAP_KEY_SEEN); +} + +static u64 bpf_map_key_immediate(const struct bpf_insn_aux_data *aux) +{ + return aux->map_key_state & ~(BPF_MAP_KEY_SEEN | BPF_MAP_KEY_POISON); +} + +static void bpf_map_key_store(struct bpf_insn_aux_data *aux, u64 state) +{ + bool poisoned = bpf_map_key_poisoned(aux); + + aux->map_key_state = state | BPF_MAP_KEY_SEEN | + (poisoned ? BPF_MAP_KEY_POISON : 0ULL); } struct bpf_call_arg_meta { @@ -4090,15 +4116,49 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, return -EACCES; } - if (!BPF_MAP_PTR(aux->map_state)) + if (!BPF_MAP_PTR(aux->map_ptr_state)) bpf_map_ptr_store(aux, meta->map_ptr, meta->map_ptr->unpriv_array); - else if (BPF_MAP_PTR(aux->map_state) != meta->map_ptr) + else if (BPF_MAP_PTR(aux->map_ptr_state) != meta->map_ptr) bpf_map_ptr_store(aux, BPF_MAP_PTR_POISON, meta->map_ptr->unpriv_array); return 0; } +static int +record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, + int func_id, int insn_idx) +{ + struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx]; + struct bpf_reg_state *regs = cur_regs(env), *reg; + struct bpf_map *map = meta->map_ptr; + struct tnum range; + u64 val; + + if (func_id != BPF_FUNC_tail_call) + return 0; + if (!map || map->map_type != BPF_MAP_TYPE_PROG_ARRAY) { + verbose(env, "kernel subsystem misconfigured verifier\n"); + return -EINVAL; + } + + range = tnum_range(0, map->max_entries - 1); + reg = ®s[BPF_REG_3]; + + if (!register_is_const(reg) || !tnum_in(range, reg->var_off)) { + bpf_map_key_store(aux, BPF_MAP_KEY_POISON); + return 0; + } + + val = reg->var_off.value; + if (bpf_map_key_unseen(aux)) + bpf_map_key_store(aux, val); + else if (!bpf_map_key_poisoned(aux) && + bpf_map_key_immediate(aux) != val) + bpf_map_key_store(aux, BPF_MAP_KEY_POISON); + return 0; +} + static int check_reference_leak(struct bpf_verifier_env *env) { struct bpf_func_state *state = cur_func(env); @@ -4173,6 +4233,10 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn if (err) return err; + err = record_func_key(env, &meta, func_id, insn_idx); + if (err) + return err; + /* Mark slots with STACK_MISC in case of raw mode, stack offset * is inferred from register state. */ @@ -9065,6 +9129,7 @@ static int fixup_call_args(struct bpf_verifier_env *env) static int fixup_bpf_calls(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog; + bool expect_blinding = bpf_jit_blinding_enabled(prog); struct bpf_insn *insn = prog->insnsi; const struct bpf_func_proto *fn; const int insn_cnt = prog->len; @@ -9073,7 +9138,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) struct bpf_insn insn_buf[16]; struct bpf_prog *new_prog; struct bpf_map *map_ptr; - int i, cnt, delta = 0; + int i, ret, cnt, delta = 0; for (i = 0; i < insn_cnt; i++, insn++) { if (insn->code == (BPF_ALU64 | BPF_MOD | BPF_X) || @@ -9217,6 +9282,26 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) insn->code = BPF_JMP | BPF_TAIL_CALL; aux = &env->insn_aux_data[i + delta]; + if (prog->jit_requested && !expect_blinding && + !bpf_map_key_poisoned(aux) && + !bpf_map_ptr_poisoned(aux) && + !bpf_map_ptr_unpriv(aux)) { + struct bpf_jit_poke_descriptor desc = { + .reason = BPF_POKE_REASON_TAIL_CALL, + .tail_call.map = BPF_MAP_PTR(aux->map_ptr_state), + .tail_call.key = bpf_map_key_immediate(aux), + }; + + ret = bpf_jit_add_poke_descriptor(prog, &desc); + if (ret < 0) { + verbose(env, "adding tail call poke descriptor failed\n"); + return ret; + } + + insn->imm = ret + 1; + continue; + } + if (!bpf_map_ptr_unpriv(aux)) continue; @@ -9231,7 +9316,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) return -EINVAL; } - map_ptr = BPF_MAP_PTR(aux->map_state); + map_ptr = BPF_MAP_PTR(aux->map_ptr_state); insn_buf[0] = BPF_JMP_IMM(BPF_JGE, BPF_REG_3, map_ptr->max_entries, 2); insn_buf[1] = BPF_ALU32_IMM(BPF_AND, BPF_REG_3, @@ -9265,7 +9350,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) if (bpf_map_ptr_poisoned(aux)) goto patch_call_imm; - map_ptr = BPF_MAP_PTR(aux->map_state); + map_ptr = BPF_MAP_PTR(aux->map_ptr_state); ops = map_ptr->ops; if (insn->imm == BPF_FUNC_map_lookup_elem && ops->map_gen_lookup) { @@ -9345,6 +9430,23 @@ patch_call_imm: insn->imm = fn->func - __bpf_call_base; } + /* Since poke tab is now finalized, publish aux to tracker. */ + for (i = 0; i < prog->aux->size_poke_tab; i++) { + map_ptr = prog->aux->poke_tab[i].tail_call.map; + if (!map_ptr->ops->map_poke_track || + !map_ptr->ops->map_poke_untrack || + !map_ptr->ops->map_poke_run) { + verbose(env, "bpf verifier is misconfigured\n"); + return -EINVAL; + } + + ret = map_ptr->ops->map_poke_track(map_ptr, prog->aux); + if (ret < 0) { + verbose(env, "tracking tail call prog failed\n"); + return ret; + } + } + return 0; } -- cgit v1.2.3-71-gd317 From b8cd76ca4ae34731d47cd6a876d912a08efcc240 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 23 Nov 2019 21:37:31 +0100 Subject: bpf: Add bpf_jit_blinding_enabled for !CONFIG_BPF_JIT MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a definition of bpf_jit_blinding_enabled() when CONFIG_BPF_JIT is not set in order to fix a recent build regression: [...] CC kernel/bpf/verifier.o CC kernel/bpf/inode.o kernel/bpf/verifier.c: In function ‘fixup_bpf_calls’: kernel/bpf/verifier.c:9132:25: error: implicit declaration of function ‘bpf_jit_blinding_enabled’; did you mean ‘bpf_jit_kallsyms_enabled’? [-Werror=implicit-function-declaration] 9132 | bool expect_blinding = bpf_jit_blinding_enabled(prog); | ^~~~~~~~~~~~~~~~~~~~~~~~ | bpf_jit_kallsyms_enabled CC kernel/bpf/helpers.o CC kernel/bpf/hashtab.o [...] Fixes: d2e4c1e6c294 ("bpf: Constant map key tracking for prog array pokes") Reported-by: Jakub Sitnicki Reported-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/40baf8f3507cac4851a310578edfb98ce73b5605.1574541375.git.daniel@iogearbox.net --- include/linux/filter.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 796b60d8cc6c..1b1e8b8f88da 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1053,6 +1053,11 @@ static inline bool ebpf_jit_enabled(void) return false; } +static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog) +{ + return false; +} + static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp) { return false; -- cgit v1.2.3-71-gd317 From b553a6ec570044fc1ae300c6fb24f9ce204c5894 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 24 Nov 2019 01:39:42 +0100 Subject: bpf: Simplify __bpf_arch_text_poke poke type handling Given that we have BPF_MOD_NOP_TO_{CALL,JUMP}, BPF_MOD_{CALL,JUMP}_TO_NOP and BPF_MOD_{CALL,JUMP}_TO_{CALL,JUMP} poke types and that we also pass in old_addr as well as new_addr, it's a bit redundant and unnecessarily complicates __bpf_arch_text_poke() itself since we can derive the same from the *_addr that were passed in. Hence simplify and use BPF_MOD_{CALL,JUMP} as types which also allows to clean up call-sites. In addition to that, __bpf_arch_text_poke() currently verifies that text matches expected old_insn before we invoke text_poke_bp(). Also add a check on new_insn and skip rewrite if it already matches. Reason why this is rather useful is that it avoids making any special casing in prog_array_map_poke_run() when old and new prog were NULL and has the benefit that also for this case we perform a check on text whether it really matches our expectations. Suggested-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/fcb00a2b0b288d6c73de4ef58116a821c8fe8f2f.1574555798.git.daniel@iogearbox.net --- arch/x86/net/bpf_jit_comp.c | 85 +++++++++++++-------------------------------- include/linux/bpf.h | 10 ++---- kernel/bpf/arraymap.c | 12 +------ kernel/bpf/trampoline.c | 8 ++--- 4 files changed, 32 insertions(+), 83 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 15615c94804f..b8be18427277 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -269,76 +269,42 @@ static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *old_addr, void *new_addr, const bool text_live) { - int (*emit_patch_fn)(u8 **pprog, void *func, void *ip); const u8 *nop_insn = ideal_nops[NOP_ATOMIC5]; - u8 old_insn[X86_PATCH_SIZE] = {}; - u8 new_insn[X86_PATCH_SIZE] = {}; + u8 old_insn[X86_PATCH_SIZE]; + u8 new_insn[X86_PATCH_SIZE]; u8 *prog; int ret; - switch (t) { - case BPF_MOD_NOP_TO_CALL ... BPF_MOD_CALL_TO_NOP: - emit_patch_fn = emit_call; - break; - case BPF_MOD_NOP_TO_JUMP ... BPF_MOD_JUMP_TO_NOP: - emit_patch_fn = emit_jump; - break; - default: - return -ENOTSUPP; + memcpy(old_insn, nop_insn, X86_PATCH_SIZE); + if (old_addr) { + prog = old_insn; + ret = t == BPF_MOD_CALL ? + emit_call(&prog, old_addr, ip) : + emit_jump(&prog, old_addr, ip); + if (ret) + return ret; } - switch (t) { - case BPF_MOD_NOP_TO_CALL: - case BPF_MOD_NOP_TO_JUMP: - if (!old_addr && new_addr) { - memcpy(old_insn, nop_insn, X86_PATCH_SIZE); - - prog = new_insn; - ret = emit_patch_fn(&prog, new_addr, ip); - if (ret) - return ret; - break; - } - return -ENXIO; - case BPF_MOD_CALL_TO_CALL: - case BPF_MOD_JUMP_TO_JUMP: - if (old_addr && new_addr) { - prog = old_insn; - ret = emit_patch_fn(&prog, old_addr, ip); - if (ret) - return ret; - - prog = new_insn; - ret = emit_patch_fn(&prog, new_addr, ip); - if (ret) - return ret; - break; - } - return -ENXIO; - case BPF_MOD_CALL_TO_NOP: - case BPF_MOD_JUMP_TO_NOP: - if (old_addr && !new_addr) { - memcpy(new_insn, nop_insn, X86_PATCH_SIZE); - - prog = old_insn; - ret = emit_patch_fn(&prog, old_addr, ip); - if (ret) - return ret; - break; - } - return -ENXIO; - default: - return -ENOTSUPP; + memcpy(new_insn, nop_insn, X86_PATCH_SIZE); + if (new_addr) { + prog = new_insn; + ret = t == BPF_MOD_CALL ? + emit_call(&prog, new_addr, ip) : + emit_jump(&prog, new_addr, ip); + if (ret) + return ret; } ret = -EBUSY; mutex_lock(&text_mutex); if (memcmp(ip, old_insn, X86_PATCH_SIZE)) goto out; - if (text_live) - text_poke_bp(ip, new_insn, X86_PATCH_SIZE, NULL); - else - memcpy(ip, new_insn, X86_PATCH_SIZE); + if (memcmp(ip, new_insn, X86_PATCH_SIZE)) { + if (text_live) + text_poke_bp(ip, new_insn, X86_PATCH_SIZE, NULL); + else + memcpy(ip, new_insn, X86_PATCH_SIZE); + } ret = 0; out: mutex_unlock(&text_mutex); @@ -465,7 +431,6 @@ static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke, static void bpf_tail_call_direct_fixup(struct bpf_prog *prog) { - static const enum bpf_text_poke_type type = BPF_MOD_NOP_TO_JUMP; struct bpf_jit_poke_descriptor *poke; struct bpf_array *array; struct bpf_prog *target; @@ -490,7 +455,7 @@ static void bpf_tail_call_direct_fixup(struct bpf_prog *prog) * read-only. Both modifications on the given image * are under text_mutex to avoid interference. */ - ret = __bpf_arch_text_poke(poke->ip, type, NULL, + ret = __bpf_arch_text_poke(poke->ip, BPF_MOD_JUMP, NULL, (u8 *)target->bpf_func + poke->adj_off, false); BUG_ON(ret < 0); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c2f07fd410c1..35903f148be5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1324,14 +1324,8 @@ static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, #endif /* CONFIG_INET */ enum bpf_text_poke_type { - /* All call-related pokes. */ - BPF_MOD_NOP_TO_CALL, - BPF_MOD_CALL_TO_CALL, - BPF_MOD_CALL_TO_NOP, - /* All jump-related pokes. */ - BPF_MOD_NOP_TO_JUMP, - BPF_MOD_JUMP_TO_JUMP, - BPF_MOD_JUMP_TO_NOP, + BPF_MOD_CALL, + BPF_MOD_JUMP, }; int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 58bdf5fd24cc..f0d19bbb9211 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -746,19 +746,9 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key, struct bpf_prog *old, struct bpf_prog *new) { - enum bpf_text_poke_type type; struct prog_poke_elem *elem; struct bpf_array_aux *aux; - if (!old && new) - type = BPF_MOD_NOP_TO_JUMP; - else if (old && !new) - type = BPF_MOD_JUMP_TO_NOP; - else if (old && new) - type = BPF_MOD_JUMP_TO_JUMP; - else - return; - aux = container_of(map, struct bpf_array, map)->aux; WARN_ON_ONCE(!mutex_is_locked(&aux->poke_mutex)); @@ -806,7 +796,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key, poke->tail_call.key != key) continue; - ret = bpf_arch_text_poke(poke->ip, type, + ret = bpf_arch_text_poke(poke->ip, BPF_MOD_JUMP, old ? (u8 *)old->bpf_func + poke->adj_off : NULL, new ? (u8 *)new->bpf_func + diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 10ae59d65f13..7e89f1f49d77 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -77,7 +77,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) int err; if (fentry_cnt + fexit_cnt == 0) { - err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL_TO_NOP, + err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL, old_image, NULL); tr->selector = 0; goto out; @@ -105,12 +105,12 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) if (tr->selector) /* progs already running at this address */ - err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL_TO_CALL, + err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL, old_image, new_image); else /* first time registering */ - err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_NOP_TO_CALL, - NULL, new_image); + err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL, NULL, + new_image); if (err) goto out; tr->selector++; -- cgit v1.2.3-71-gd317 From 23e6b169c9917fbd77534f8c5f378cb073f548bd Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 21 Nov 2019 11:58:53 +0000 Subject: locking/refcount: Define constants for saturation and max refcount values The REFCOUNT_FULL implementation uses a different saturation point than the x86 implementation, which means that the shared refcount code in lib/refcount.c (e.g. refcount_dec_not_one()) needs to be aware of the difference. Rather than duplicate the definitions from the lkdtm driver, instead move them into and update all references accordingly. Signed-off-by: Will Deacon Reviewed-by: Ard Biesheuvel Reviewed-by: Kees Cook Tested-by: Hanjun Guo Cc: Ard Biesheuvel Cc: Elena Reshetova Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20191121115902.2551-2-will@kernel.org Signed-off-by: Ingo Molnar --- drivers/misc/lkdtm/refcount.c | 8 -------- include/linux/refcount.h | 10 +++++++++- lib/refcount.c | 37 ++++++++++++++++++++----------------- 3 files changed, 29 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/drivers/misc/lkdtm/refcount.c b/drivers/misc/lkdtm/refcount.c index 0a146b32da13..abf3b7c1f686 100644 --- a/drivers/misc/lkdtm/refcount.c +++ b/drivers/misc/lkdtm/refcount.c @@ -6,14 +6,6 @@ #include "lkdtm.h" #include -#ifdef CONFIG_REFCOUNT_FULL -#define REFCOUNT_MAX (UINT_MAX - 1) -#define REFCOUNT_SATURATED UINT_MAX -#else -#define REFCOUNT_MAX INT_MAX -#define REFCOUNT_SATURATED (INT_MIN / 2) -#endif - static void overflow_check(refcount_t *ref) { switch (refcount_read(ref)) { diff --git a/include/linux/refcount.h b/include/linux/refcount.h index e28cce21bad6..79f62e8d2256 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -4,6 +4,7 @@ #include #include +#include #include struct mutex; @@ -12,7 +13,7 @@ struct mutex; * struct refcount_t - variant of atomic_t specialized for reference counts * @refs: atomic_t counter field * - * The counter saturates at UINT_MAX and will not move once + * The counter saturates at REFCOUNT_SATURATED and will not move once * there. This avoids wrapping the counter and causing 'spurious' * use-after-free bugs. */ @@ -56,6 +57,9 @@ extern void refcount_dec_checked(refcount_t *r); #ifdef CONFIG_REFCOUNT_FULL +#define REFCOUNT_MAX (UINT_MAX - 1) +#define REFCOUNT_SATURATED UINT_MAX + #define refcount_add_not_zero refcount_add_not_zero_checked #define refcount_add refcount_add_checked @@ -68,6 +72,10 @@ extern void refcount_dec_checked(refcount_t *r); #define refcount_dec refcount_dec_checked #else + +#define REFCOUNT_MAX INT_MAX +#define REFCOUNT_SATURATED (INT_MIN / 2) + # ifdef CONFIG_ARCH_HAS_REFCOUNT # include # else diff --git a/lib/refcount.c b/lib/refcount.c index 6e904af0fb3e..48b78a423d7d 100644 --- a/lib/refcount.c +++ b/lib/refcount.c @@ -5,8 +5,8 @@ * The interface matches the atomic_t interface (to aid in porting) but only * provides the few functions one should use for reference counting. * - * It differs in that the counter saturates at UINT_MAX and will not move once - * there. This avoids wrapping the counter and causing 'spurious' + * It differs in that the counter saturates at REFCOUNT_SATURATED and will not + * move once there. This avoids wrapping the counter and causing 'spurious' * use-after-free issues. * * Memory ordering rules are slightly relaxed wrt regular atomic_t functions @@ -48,7 +48,7 @@ * @i: the value to add to the refcount * @r: the refcount * - * Will saturate at UINT_MAX and WARN. + * Will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency @@ -69,16 +69,17 @@ bool refcount_add_not_zero_checked(unsigned int i, refcount_t *r) if (!val) return false; - if (unlikely(val == UINT_MAX)) + if (unlikely(val == REFCOUNT_SATURATED)) return true; new = val + i; if (new < val) - new = UINT_MAX; + new = REFCOUNT_SATURATED; } while (!atomic_try_cmpxchg_relaxed(&r->refs, &val, new)); - WARN_ONCE(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n"); + WARN_ONCE(new == REFCOUNT_SATURATED, + "refcount_t: saturated; leaking memory.\n"); return true; } @@ -89,7 +90,7 @@ EXPORT_SYMBOL(refcount_add_not_zero_checked); * @i: the value to add to the refcount * @r: the refcount * - * Similar to atomic_add(), but will saturate at UINT_MAX and WARN. + * Similar to atomic_add(), but will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency @@ -110,7 +111,8 @@ EXPORT_SYMBOL(refcount_add_checked); * refcount_inc_not_zero_checked - increment a refcount unless it is 0 * @r: the refcount to increment * - * Similar to atomic_inc_not_zero(), but will saturate at UINT_MAX and WARN. + * Similar to atomic_inc_not_zero(), but will saturate at REFCOUNT_SATURATED + * and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency @@ -133,7 +135,8 @@ bool refcount_inc_not_zero_checked(refcount_t *r) } while (!atomic_try_cmpxchg_relaxed(&r->refs, &val, new)); - WARN_ONCE(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n"); + WARN_ONCE(new == REFCOUNT_SATURATED, + "refcount_t: saturated; leaking memory.\n"); return true; } @@ -143,7 +146,7 @@ EXPORT_SYMBOL(refcount_inc_not_zero_checked); * refcount_inc_checked - increment a refcount * @r: the refcount to increment * - * Similar to atomic_inc(), but will saturate at UINT_MAX and WARN. + * Similar to atomic_inc(), but will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller already has a * reference on the object. @@ -164,7 +167,7 @@ EXPORT_SYMBOL(refcount_inc_checked); * * Similar to atomic_dec_and_test(), but it will WARN, return false and * ultimately leak on underflow and will fail to decrement when saturated - * at UINT_MAX. + * at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides an acquire ordering on success such that free() @@ -182,7 +185,7 @@ bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r) unsigned int new, val = atomic_read(&r->refs); do { - if (unlikely(val == UINT_MAX)) + if (unlikely(val == REFCOUNT_SATURATED)) return false; new = val - i; @@ -207,7 +210,7 @@ EXPORT_SYMBOL(refcount_sub_and_test_checked); * @r: the refcount * * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to - * decrement when saturated at UINT_MAX. + * decrement when saturated at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides an acquire ordering on success such that free() @@ -226,7 +229,7 @@ EXPORT_SYMBOL(refcount_dec_and_test_checked); * @r: the refcount * * Similar to atomic_dec(), it will WARN on underflow and fail to decrement - * when saturated at UINT_MAX. + * when saturated at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before. @@ -277,7 +280,7 @@ bool refcount_dec_not_one(refcount_t *r) unsigned int new, val = atomic_read(&r->refs); do { - if (unlikely(val == UINT_MAX)) + if (unlikely(val == REFCOUNT_SATURATED)) return true; if (val == 1) @@ -302,7 +305,7 @@ EXPORT_SYMBOL(refcount_dec_not_one); * @lock: the mutex to be locked * * Similar to atomic_dec_and_mutex_lock(), it will WARN on underflow and fail - * to decrement when saturated at UINT_MAX. + * to decrement when saturated at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides a control dependency such that free() must come after. @@ -333,7 +336,7 @@ EXPORT_SYMBOL(refcount_dec_and_mutex_lock); * @lock: the spinlock to be locked * * Similar to atomic_dec_and_lock(), it will WARN on underflow and fail to - * decrement when saturated at UINT_MAX. + * decrement when saturated at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides a control dependency such that free() must come after. -- cgit v1.2.3-71-gd317 From 97a1420adf0cdf0cf6f41bab0b2acf658c96b94b Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 21 Nov 2019 11:58:54 +0000 Subject: locking/refcount: Ensure integer operands are treated as signed In preparation for changing the saturation point of REFCOUNT_FULL to INT_MIN/2, change the type of integer operands passed into the API from 'unsigned int' to 'int' so that we can avoid casting during comparisons when we don't want to fall foul of C integral conversion rules for signed and unsigned types. Since the kernel is compiled with '-fno-strict-overflow', we don't need to worry about the UB introduced by signed overflow here. Furthermore, we're already making heavy use of the atomic_t API, which operates exclusively on signed types. Signed-off-by: Will Deacon Reviewed-by: Ard Biesheuvel Reviewed-by: Kees Cook Tested-by: Hanjun Guo Cc: Ard Biesheuvel Cc: Elena Reshetova Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20191121115902.2551-3-will@kernel.org Signed-off-by: Ingo Molnar --- include/linux/refcount.h | 14 +++++++------- lib/refcount.c | 6 +++--- 2 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/refcount.h b/include/linux/refcount.h index 79f62e8d2256..89066a1471dd 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -28,7 +28,7 @@ typedef struct refcount_struct { * @r: the refcount * @n: value to which the refcount will be set */ -static inline void refcount_set(refcount_t *r, unsigned int n) +static inline void refcount_set(refcount_t *r, int n) { atomic_set(&r->refs, n); } @@ -44,13 +44,13 @@ static inline unsigned int refcount_read(const refcount_t *r) return atomic_read(&r->refs); } -extern __must_check bool refcount_add_not_zero_checked(unsigned int i, refcount_t *r); -extern void refcount_add_checked(unsigned int i, refcount_t *r); +extern __must_check bool refcount_add_not_zero_checked(int i, refcount_t *r); +extern void refcount_add_checked(int i, refcount_t *r); extern __must_check bool refcount_inc_not_zero_checked(refcount_t *r); extern void refcount_inc_checked(refcount_t *r); -extern __must_check bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r); +extern __must_check bool refcount_sub_and_test_checked(int i, refcount_t *r); extern __must_check bool refcount_dec_and_test_checked(refcount_t *r); extern void refcount_dec_checked(refcount_t *r); @@ -79,12 +79,12 @@ extern void refcount_dec_checked(refcount_t *r); # ifdef CONFIG_ARCH_HAS_REFCOUNT # include # else -static inline __must_check bool refcount_add_not_zero(unsigned int i, refcount_t *r) +static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) { return atomic_add_unless(&r->refs, i, 0); } -static inline void refcount_add(unsigned int i, refcount_t *r) +static inline void refcount_add(int i, refcount_t *r) { atomic_add(i, &r->refs); } @@ -99,7 +99,7 @@ static inline void refcount_inc(refcount_t *r) atomic_inc(&r->refs); } -static inline __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r) +static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r) { return atomic_sub_and_test(i, &r->refs); } diff --git a/lib/refcount.c b/lib/refcount.c index 48b78a423d7d..719b0bc42ab1 100644 --- a/lib/refcount.c +++ b/lib/refcount.c @@ -61,7 +61,7 @@ * * Return: false if the passed refcount is 0, true otherwise */ -bool refcount_add_not_zero_checked(unsigned int i, refcount_t *r) +bool refcount_add_not_zero_checked(int i, refcount_t *r) { unsigned int new, val = atomic_read(&r->refs); @@ -101,7 +101,7 @@ EXPORT_SYMBOL(refcount_add_not_zero_checked); * cases, refcount_inc(), or one of its variants, should instead be used to * increment a reference count. */ -void refcount_add_checked(unsigned int i, refcount_t *r) +void refcount_add_checked(int i, refcount_t *r) { WARN_ONCE(!refcount_add_not_zero_checked(i, r), "refcount_t: addition on 0; use-after-free.\n"); } @@ -180,7 +180,7 @@ EXPORT_SYMBOL(refcount_inc_checked); * * Return: true if the resulting refcount is 0, false otherwise */ -bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r) +bool refcount_sub_and_test_checked(int i, refcount_t *r) { unsigned int new, val = atomic_read(&r->refs); -- cgit v1.2.3-71-gd317 From 7221762c48c6bbbcc6cc51d8b803c06930215e34 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 21 Nov 2019 11:58:55 +0000 Subject: locking/refcount: Remove unused refcount_*_checked() variants The full-fat refcount implementation is exposed via a set of functions suffixed with "_checked()", the idea being that code can choose to use the more expensive, yet more secure implementation on a case-by-case basis. In reality, this hasn't happened, so with a grand total of zero users, let's remove the checked variants for now by simply dropping the suffix and predicating the out-of-line functions on CONFIG_REFCOUNT_FULL=y. Signed-off-by: Will Deacon Reviewed-by: Ard Biesheuvel Reviewed-by: Kees Cook Tested-by: Hanjun Guo Cc: Ard Biesheuvel Cc: Elena Reshetova Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20191121115902.2551-4-will@kernel.org Signed-off-by: Ingo Molnar --- include/linux/refcount.h | 25 +++++++--------------- lib/refcount.c | 54 ++++++++++++++++++++++++++---------------------- 2 files changed, 36 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/include/linux/refcount.h b/include/linux/refcount.h index 89066a1471dd..edd505d1a23b 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -44,32 +44,21 @@ static inline unsigned int refcount_read(const refcount_t *r) return atomic_read(&r->refs); } -extern __must_check bool refcount_add_not_zero_checked(int i, refcount_t *r); -extern void refcount_add_checked(int i, refcount_t *r); - -extern __must_check bool refcount_inc_not_zero_checked(refcount_t *r); -extern void refcount_inc_checked(refcount_t *r); - -extern __must_check bool refcount_sub_and_test_checked(int i, refcount_t *r); - -extern __must_check bool refcount_dec_and_test_checked(refcount_t *r); -extern void refcount_dec_checked(refcount_t *r); - #ifdef CONFIG_REFCOUNT_FULL #define REFCOUNT_MAX (UINT_MAX - 1) #define REFCOUNT_SATURATED UINT_MAX -#define refcount_add_not_zero refcount_add_not_zero_checked -#define refcount_add refcount_add_checked +extern __must_check bool refcount_add_not_zero(int i, refcount_t *r); +extern void refcount_add(int i, refcount_t *r); -#define refcount_inc_not_zero refcount_inc_not_zero_checked -#define refcount_inc refcount_inc_checked +extern __must_check bool refcount_inc_not_zero(refcount_t *r); +extern void refcount_inc(refcount_t *r); -#define refcount_sub_and_test refcount_sub_and_test_checked +extern __must_check bool refcount_sub_and_test(int i, refcount_t *r); -#define refcount_dec_and_test refcount_dec_and_test_checked -#define refcount_dec refcount_dec_checked +extern __must_check bool refcount_dec_and_test(refcount_t *r); +extern void refcount_dec(refcount_t *r); #else diff --git a/lib/refcount.c b/lib/refcount.c index 719b0bc42ab1..a2f670998cee 100644 --- a/lib/refcount.c +++ b/lib/refcount.c @@ -43,8 +43,10 @@ #include #include +#ifdef CONFIG_REFCOUNT_FULL + /** - * refcount_add_not_zero_checked - add a value to a refcount unless it is 0 + * refcount_add_not_zero - add a value to a refcount unless it is 0 * @i: the value to add to the refcount * @r: the refcount * @@ -61,7 +63,7 @@ * * Return: false if the passed refcount is 0, true otherwise */ -bool refcount_add_not_zero_checked(int i, refcount_t *r) +bool refcount_add_not_zero(int i, refcount_t *r) { unsigned int new, val = atomic_read(&r->refs); @@ -83,10 +85,10 @@ bool refcount_add_not_zero_checked(int i, refcount_t *r) return true; } -EXPORT_SYMBOL(refcount_add_not_zero_checked); +EXPORT_SYMBOL(refcount_add_not_zero); /** - * refcount_add_checked - add a value to a refcount + * refcount_add - add a value to a refcount * @i: the value to add to the refcount * @r: the refcount * @@ -101,14 +103,14 @@ EXPORT_SYMBOL(refcount_add_not_zero_checked); * cases, refcount_inc(), or one of its variants, should instead be used to * increment a reference count. */ -void refcount_add_checked(int i, refcount_t *r) +void refcount_add(int i, refcount_t *r) { - WARN_ONCE(!refcount_add_not_zero_checked(i, r), "refcount_t: addition on 0; use-after-free.\n"); + WARN_ONCE(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n"); } -EXPORT_SYMBOL(refcount_add_checked); +EXPORT_SYMBOL(refcount_add); /** - * refcount_inc_not_zero_checked - increment a refcount unless it is 0 + * refcount_inc_not_zero - increment a refcount unless it is 0 * @r: the refcount to increment * * Similar to atomic_inc_not_zero(), but will saturate at REFCOUNT_SATURATED @@ -120,7 +122,7 @@ EXPORT_SYMBOL(refcount_add_checked); * * Return: true if the increment was successful, false otherwise */ -bool refcount_inc_not_zero_checked(refcount_t *r) +bool refcount_inc_not_zero(refcount_t *r) { unsigned int new, val = atomic_read(&r->refs); @@ -140,10 +142,10 @@ bool refcount_inc_not_zero_checked(refcount_t *r) return true; } -EXPORT_SYMBOL(refcount_inc_not_zero_checked); +EXPORT_SYMBOL(refcount_inc_not_zero); /** - * refcount_inc_checked - increment a refcount + * refcount_inc - increment a refcount * @r: the refcount to increment * * Similar to atomic_inc(), but will saturate at REFCOUNT_SATURATED and WARN. @@ -154,14 +156,14 @@ EXPORT_SYMBOL(refcount_inc_not_zero_checked); * Will WARN if the refcount is 0, as this represents a possible use-after-free * condition. */ -void refcount_inc_checked(refcount_t *r) +void refcount_inc(refcount_t *r) { - WARN_ONCE(!refcount_inc_not_zero_checked(r), "refcount_t: increment on 0; use-after-free.\n"); + WARN_ONCE(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n"); } -EXPORT_SYMBOL(refcount_inc_checked); +EXPORT_SYMBOL(refcount_inc); /** - * refcount_sub_and_test_checked - subtract from a refcount and test if it is 0 + * refcount_sub_and_test - subtract from a refcount and test if it is 0 * @i: amount to subtract from the refcount * @r: the refcount * @@ -180,7 +182,7 @@ EXPORT_SYMBOL(refcount_inc_checked); * * Return: true if the resulting refcount is 0, false otherwise */ -bool refcount_sub_and_test_checked(int i, refcount_t *r) +bool refcount_sub_and_test(int i, refcount_t *r) { unsigned int new, val = atomic_read(&r->refs); @@ -203,10 +205,10 @@ bool refcount_sub_and_test_checked(int i, refcount_t *r) return false; } -EXPORT_SYMBOL(refcount_sub_and_test_checked); +EXPORT_SYMBOL(refcount_sub_and_test); /** - * refcount_dec_and_test_checked - decrement a refcount and test if it is 0 + * refcount_dec_and_test - decrement a refcount and test if it is 0 * @r: the refcount * * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to @@ -218,14 +220,14 @@ EXPORT_SYMBOL(refcount_sub_and_test_checked); * * Return: true if the resulting refcount is 0, false otherwise */ -bool refcount_dec_and_test_checked(refcount_t *r) +bool refcount_dec_and_test(refcount_t *r) { - return refcount_sub_and_test_checked(1, r); + return refcount_sub_and_test(1, r); } -EXPORT_SYMBOL(refcount_dec_and_test_checked); +EXPORT_SYMBOL(refcount_dec_and_test); /** - * refcount_dec_checked - decrement a refcount + * refcount_dec - decrement a refcount * @r: the refcount * * Similar to atomic_dec(), it will WARN on underflow and fail to decrement @@ -234,11 +236,13 @@ EXPORT_SYMBOL(refcount_dec_and_test_checked); * Provides release memory ordering, such that prior loads and stores are done * before. */ -void refcount_dec_checked(refcount_t *r) +void refcount_dec(refcount_t *r) { - WARN_ONCE(refcount_dec_and_test_checked(r), "refcount_t: decrement hit 0; leaking memory.\n"); + WARN_ONCE(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n"); } -EXPORT_SYMBOL(refcount_dec_checked); +EXPORT_SYMBOL(refcount_dec); + +#endif /* CONFIG_REFCOUNT_FULL */ /** * refcount_dec_if_one - decrement a refcount if it is 1 -- cgit v1.2.3-71-gd317 From 77e9971c79c29542ab7dd4140f9343bf2ff36158 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 21 Nov 2019 11:58:56 +0000 Subject: locking/refcount: Move the bulk of the REFCOUNT_FULL implementation into the header In an effort to improve performance of the REFCOUNT_FULL implementation, move the bulk of its functions into linux/refcount.h. This allows them to be inlined in the same way as if they had been provided via CONFIG_ARCH_HAS_REFCOUNT. Signed-off-by: Will Deacon Reviewed-by: Ard Biesheuvel Reviewed-by: Kees Cook Tested-by: Hanjun Guo Cc: Ard Biesheuvel Cc: Elena Reshetova Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20191121115902.2551-5-will@kernel.org Signed-off-by: Ingo Molnar --- include/linux/refcount.h | 237 ++++++++++++++++++++++++++++++++++++++++++++-- lib/refcount.c | 238 +---------------------------------------------- 2 files changed, 229 insertions(+), 246 deletions(-) (limited to 'include/linux') diff --git a/include/linux/refcount.h b/include/linux/refcount.h index edd505d1a23b..e719b5b1220e 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -45,22 +45,241 @@ static inline unsigned int refcount_read(const refcount_t *r) } #ifdef CONFIG_REFCOUNT_FULL +#include #define REFCOUNT_MAX (UINT_MAX - 1) #define REFCOUNT_SATURATED UINT_MAX -extern __must_check bool refcount_add_not_zero(int i, refcount_t *r); -extern void refcount_add(int i, refcount_t *r); +/* + * Variant of atomic_t specialized for reference counts. + * + * The interface matches the atomic_t interface (to aid in porting) but only + * provides the few functions one should use for reference counting. + * + * It differs in that the counter saturates at REFCOUNT_SATURATED and will not + * move once there. This avoids wrapping the counter and causing 'spurious' + * use-after-free issues. + * + * Memory ordering rules are slightly relaxed wrt regular atomic_t functions + * and provide only what is strictly required for refcounts. + * + * The increments are fully relaxed; these will not provide ordering. The + * rationale is that whatever is used to obtain the object we're increasing the + * reference count on will provide the ordering. For locked data structures, + * its the lock acquire, for RCU/lockless data structures its the dependent + * load. + * + * Do note that inc_not_zero() provides a control dependency which will order + * future stores against the inc, this ensures we'll never modify the object + * if we did not in fact acquire a reference. + * + * The decrements will provide release order, such that all the prior loads and + * stores will be issued before, it also provides a control dependency, which + * will order us against the subsequent free(). + * + * The control dependency is against the load of the cmpxchg (ll/sc) that + * succeeded. This means the stores aren't fully ordered, but this is fine + * because the 1->0 transition indicates no concurrency. + * + * Note that the allocator is responsible for ordering things between free() + * and alloc(). + * + * The decrements dec_and_test() and sub_and_test() also provide acquire + * ordering on success. + * + */ + +/** + * refcount_add_not_zero - add a value to a refcount unless it is 0 + * @i: the value to add to the refcount + * @r: the refcount + * + * Will saturate at REFCOUNT_SATURATED and WARN. + * + * Provides no memory ordering, it is assumed the caller has guaranteed the + * object memory to be stable (RCU, etc.). It does provide a control dependency + * and thereby orders future stores. See the comment on top. + * + * Use of this function is not recommended for the normal reference counting + * use case in which references are taken and released one at a time. In these + * cases, refcount_inc(), or one of its variants, should instead be used to + * increment a reference count. + * + * Return: false if the passed refcount is 0, true otherwise + */ +static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) +{ + unsigned int new, val = atomic_read(&r->refs); + + do { + if (!val) + return false; + + if (unlikely(val == REFCOUNT_SATURATED)) + return true; + + new = val + i; + if (new < val) + new = REFCOUNT_SATURATED; + + } while (!atomic_try_cmpxchg_relaxed(&r->refs, &val, new)); + + WARN_ONCE(new == REFCOUNT_SATURATED, + "refcount_t: saturated; leaking memory.\n"); + + return true; +} + +/** + * refcount_add - add a value to a refcount + * @i: the value to add to the refcount + * @r: the refcount + * + * Similar to atomic_add(), but will saturate at REFCOUNT_SATURATED and WARN. + * + * Provides no memory ordering, it is assumed the caller has guaranteed the + * object memory to be stable (RCU, etc.). It does provide a control dependency + * and thereby orders future stores. See the comment on top. + * + * Use of this function is not recommended for the normal reference counting + * use case in which references are taken and released one at a time. In these + * cases, refcount_inc(), or one of its variants, should instead be used to + * increment a reference count. + */ +static inline void refcount_add(int i, refcount_t *r) +{ + WARN_ONCE(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n"); +} + +/** + * refcount_inc_not_zero - increment a refcount unless it is 0 + * @r: the refcount to increment + * + * Similar to atomic_inc_not_zero(), but will saturate at REFCOUNT_SATURATED + * and WARN. + * + * Provides no memory ordering, it is assumed the caller has guaranteed the + * object memory to be stable (RCU, etc.). It does provide a control dependency + * and thereby orders future stores. See the comment on top. + * + * Return: true if the increment was successful, false otherwise + */ +static inline __must_check bool refcount_inc_not_zero(refcount_t *r) +{ + unsigned int new, val = atomic_read(&r->refs); + + do { + new = val + 1; -extern __must_check bool refcount_inc_not_zero(refcount_t *r); -extern void refcount_inc(refcount_t *r); + if (!val) + return false; -extern __must_check bool refcount_sub_and_test(int i, refcount_t *r); + if (unlikely(!new)) + return true; -extern __must_check bool refcount_dec_and_test(refcount_t *r); -extern void refcount_dec(refcount_t *r); + } while (!atomic_try_cmpxchg_relaxed(&r->refs, &val, new)); + + WARN_ONCE(new == REFCOUNT_SATURATED, + "refcount_t: saturated; leaking memory.\n"); + + return true; +} + +/** + * refcount_inc - increment a refcount + * @r: the refcount to increment + * + * Similar to atomic_inc(), but will saturate at REFCOUNT_SATURATED and WARN. + * + * Provides no memory ordering, it is assumed the caller already has a + * reference on the object. + * + * Will WARN if the refcount is 0, as this represents a possible use-after-free + * condition. + */ +static inline void refcount_inc(refcount_t *r) +{ + WARN_ONCE(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n"); +} + +/** + * refcount_sub_and_test - subtract from a refcount and test if it is 0 + * @i: amount to subtract from the refcount + * @r: the refcount + * + * Similar to atomic_dec_and_test(), but it will WARN, return false and + * ultimately leak on underflow and will fail to decrement when saturated + * at REFCOUNT_SATURATED. + * + * Provides release memory ordering, such that prior loads and stores are done + * before, and provides an acquire ordering on success such that free() + * must come after. + * + * Use of this function is not recommended for the normal reference counting + * use case in which references are taken and released one at a time. In these + * cases, refcount_dec(), or one of its variants, should instead be used to + * decrement a reference count. + * + * Return: true if the resulting refcount is 0, false otherwise + */ +static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r) +{ + unsigned int new, val = atomic_read(&r->refs); + + do { + if (unlikely(val == REFCOUNT_SATURATED)) + return false; + + new = val - i; + if (new > val) { + WARN_ONCE(new > val, "refcount_t: underflow; use-after-free.\n"); + return false; + } + + } while (!atomic_try_cmpxchg_release(&r->refs, &val, new)); + + if (!new) { + smp_acquire__after_ctrl_dep(); + return true; + } + return false; + +} + +/** + * refcount_dec_and_test - decrement a refcount and test if it is 0 + * @r: the refcount + * + * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to + * decrement when saturated at REFCOUNT_SATURATED. + * + * Provides release memory ordering, such that prior loads and stores are done + * before, and provides an acquire ordering on success such that free() + * must come after. + * + * Return: true if the resulting refcount is 0, false otherwise + */ +static inline __must_check bool refcount_dec_and_test(refcount_t *r) +{ + return refcount_sub_and_test(1, r); +} + +/** + * refcount_dec - decrement a refcount + * @r: the refcount + * + * Similar to atomic_dec(), it will WARN on underflow and fail to decrement + * when saturated at REFCOUNT_SATURATED. + * + * Provides release memory ordering, such that prior loads and stores are done + * before. + */ +static inline void refcount_dec(refcount_t *r) +{ + WARN_ONCE(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n"); +} -#else +#else /* CONFIG_REFCOUNT_FULL */ #define REFCOUNT_MAX INT_MAX #define REFCOUNT_SATURATED (INT_MIN / 2) @@ -103,7 +322,7 @@ static inline void refcount_dec(refcount_t *r) atomic_dec(&r->refs); } # endif /* !CONFIG_ARCH_HAS_REFCOUNT */ -#endif /* CONFIG_REFCOUNT_FULL */ +#endif /* !CONFIG_REFCOUNT_FULL */ extern __must_check bool refcount_dec_if_one(refcount_t *r); extern __must_check bool refcount_dec_not_one(refcount_t *r); diff --git a/lib/refcount.c b/lib/refcount.c index a2f670998cee..3a534fbebdcc 100644 --- a/lib/refcount.c +++ b/lib/refcount.c @@ -1,41 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Variant of atomic_t specialized for reference counts. - * - * The interface matches the atomic_t interface (to aid in porting) but only - * provides the few functions one should use for reference counting. - * - * It differs in that the counter saturates at REFCOUNT_SATURATED and will not - * move once there. This avoids wrapping the counter and causing 'spurious' - * use-after-free issues. - * - * Memory ordering rules are slightly relaxed wrt regular atomic_t functions - * and provide only what is strictly required for refcounts. - * - * The increments are fully relaxed; these will not provide ordering. The - * rationale is that whatever is used to obtain the object we're increasing the - * reference count on will provide the ordering. For locked data structures, - * its the lock acquire, for RCU/lockless data structures its the dependent - * load. - * - * Do note that inc_not_zero() provides a control dependency which will order - * future stores against the inc, this ensures we'll never modify the object - * if we did not in fact acquire a reference. - * - * The decrements will provide release order, such that all the prior loads and - * stores will be issued before, it also provides a control dependency, which - * will order us against the subsequent free(). - * - * The control dependency is against the load of the cmpxchg (ll/sc) that - * succeeded. This means the stores aren't fully ordered, but this is fine - * because the 1->0 transition indicates no concurrency. - * - * Note that the allocator is responsible for ordering things between free() - * and alloc(). - * - * The decrements dec_and_test() and sub_and_test() also provide acquire - * ordering on success. - * + * Out-of-line refcount functions common to all refcount implementations. */ #include @@ -43,207 +8,6 @@ #include #include -#ifdef CONFIG_REFCOUNT_FULL - -/** - * refcount_add_not_zero - add a value to a refcount unless it is 0 - * @i: the value to add to the refcount - * @r: the refcount - * - * Will saturate at REFCOUNT_SATURATED and WARN. - * - * Provides no memory ordering, it is assumed the caller has guaranteed the - * object memory to be stable (RCU, etc.). It does provide a control dependency - * and thereby orders future stores. See the comment on top. - * - * Use of this function is not recommended for the normal reference counting - * use case in which references are taken and released one at a time. In these - * cases, refcount_inc(), or one of its variants, should instead be used to - * increment a reference count. - * - * Return: false if the passed refcount is 0, true otherwise - */ -bool refcount_add_not_zero(int i, refcount_t *r) -{ - unsigned int new, val = atomic_read(&r->refs); - - do { - if (!val) - return false; - - if (unlikely(val == REFCOUNT_SATURATED)) - return true; - - new = val + i; - if (new < val) - new = REFCOUNT_SATURATED; - - } while (!atomic_try_cmpxchg_relaxed(&r->refs, &val, new)); - - WARN_ONCE(new == REFCOUNT_SATURATED, - "refcount_t: saturated; leaking memory.\n"); - - return true; -} -EXPORT_SYMBOL(refcount_add_not_zero); - -/** - * refcount_add - add a value to a refcount - * @i: the value to add to the refcount - * @r: the refcount - * - * Similar to atomic_add(), but will saturate at REFCOUNT_SATURATED and WARN. - * - * Provides no memory ordering, it is assumed the caller has guaranteed the - * object memory to be stable (RCU, etc.). It does provide a control dependency - * and thereby orders future stores. See the comment on top. - * - * Use of this function is not recommended for the normal reference counting - * use case in which references are taken and released one at a time. In these - * cases, refcount_inc(), or one of its variants, should instead be used to - * increment a reference count. - */ -void refcount_add(int i, refcount_t *r) -{ - WARN_ONCE(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n"); -} -EXPORT_SYMBOL(refcount_add); - -/** - * refcount_inc_not_zero - increment a refcount unless it is 0 - * @r: the refcount to increment - * - * Similar to atomic_inc_not_zero(), but will saturate at REFCOUNT_SATURATED - * and WARN. - * - * Provides no memory ordering, it is assumed the caller has guaranteed the - * object memory to be stable (RCU, etc.). It does provide a control dependency - * and thereby orders future stores. See the comment on top. - * - * Return: true if the increment was successful, false otherwise - */ -bool refcount_inc_not_zero(refcount_t *r) -{ - unsigned int new, val = atomic_read(&r->refs); - - do { - new = val + 1; - - if (!val) - return false; - - if (unlikely(!new)) - return true; - - } while (!atomic_try_cmpxchg_relaxed(&r->refs, &val, new)); - - WARN_ONCE(new == REFCOUNT_SATURATED, - "refcount_t: saturated; leaking memory.\n"); - - return true; -} -EXPORT_SYMBOL(refcount_inc_not_zero); - -/** - * refcount_inc - increment a refcount - * @r: the refcount to increment - * - * Similar to atomic_inc(), but will saturate at REFCOUNT_SATURATED and WARN. - * - * Provides no memory ordering, it is assumed the caller already has a - * reference on the object. - * - * Will WARN if the refcount is 0, as this represents a possible use-after-free - * condition. - */ -void refcount_inc(refcount_t *r) -{ - WARN_ONCE(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n"); -} -EXPORT_SYMBOL(refcount_inc); - -/** - * refcount_sub_and_test - subtract from a refcount and test if it is 0 - * @i: amount to subtract from the refcount - * @r: the refcount - * - * Similar to atomic_dec_and_test(), but it will WARN, return false and - * ultimately leak on underflow and will fail to decrement when saturated - * at REFCOUNT_SATURATED. - * - * Provides release memory ordering, such that prior loads and stores are done - * before, and provides an acquire ordering on success such that free() - * must come after. - * - * Use of this function is not recommended for the normal reference counting - * use case in which references are taken and released one at a time. In these - * cases, refcount_dec(), or one of its variants, should instead be used to - * decrement a reference count. - * - * Return: true if the resulting refcount is 0, false otherwise - */ -bool refcount_sub_and_test(int i, refcount_t *r) -{ - unsigned int new, val = atomic_read(&r->refs); - - do { - if (unlikely(val == REFCOUNT_SATURATED)) - return false; - - new = val - i; - if (new > val) { - WARN_ONCE(new > val, "refcount_t: underflow; use-after-free.\n"); - return false; - } - - } while (!atomic_try_cmpxchg_release(&r->refs, &val, new)); - - if (!new) { - smp_acquire__after_ctrl_dep(); - return true; - } - return false; - -} -EXPORT_SYMBOL(refcount_sub_and_test); - -/** - * refcount_dec_and_test - decrement a refcount and test if it is 0 - * @r: the refcount - * - * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to - * decrement when saturated at REFCOUNT_SATURATED. - * - * Provides release memory ordering, such that prior loads and stores are done - * before, and provides an acquire ordering on success such that free() - * must come after. - * - * Return: true if the resulting refcount is 0, false otherwise - */ -bool refcount_dec_and_test(refcount_t *r) -{ - return refcount_sub_and_test(1, r); -} -EXPORT_SYMBOL(refcount_dec_and_test); - -/** - * refcount_dec - decrement a refcount - * @r: the refcount - * - * Similar to atomic_dec(), it will WARN on underflow and fail to decrement - * when saturated at REFCOUNT_SATURATED. - * - * Provides release memory ordering, such that prior loads and stores are done - * before. - */ -void refcount_dec(refcount_t *r) -{ - WARN_ONCE(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n"); -} -EXPORT_SYMBOL(refcount_dec); - -#endif /* CONFIG_REFCOUNT_FULL */ - /** * refcount_dec_if_one - decrement a refcount if it is 1 * @r: the refcount -- cgit v1.2.3-71-gd317 From dcb786493f3e48da3272b710028d42ec608cfda1 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 21 Nov 2019 11:58:57 +0000 Subject: locking/refcount: Improve performance of generic REFCOUNT_FULL code Rewrite the generic REFCOUNT_FULL implementation so that the saturation point is moved to INT_MIN / 2. This allows us to defer the sanity checks until after the atomic operation, which removes many uses of cmpxchg() in favour of atomic_fetch_{add,sub}(). Some crude perf results obtained from lkdtm show substantially less overhead, despite the checking: $ perf stat -r 3 -B -- echo {ATOMIC,REFCOUNT}_TIMING >/sys/kernel/debug/provoke-crash/DIRECT # arm64 ATOMIC_TIMING: 46.50451 +- 0.00134 seconds time elapsed ( +- 0.00% ) REFCOUNT_TIMING (REFCOUNT_FULL, mainline): 77.57522 +- 0.00982 seconds time elapsed ( +- 0.01% ) REFCOUNT_TIMING (REFCOUNT_FULL, this series): 48.7181 +- 0.0256 seconds time elapsed ( +- 0.05% ) # x86 ATOMIC_TIMING: 31.6225 +- 0.0776 seconds time elapsed ( +- 0.25% ) REFCOUNT_TIMING (!REFCOUNT_FULL, mainline/x86 asm): 31.6689 +- 0.0901 seconds time elapsed ( +- 0.28% ) REFCOUNT_TIMING (REFCOUNT_FULL, mainline): 53.203 +- 0.138 seconds time elapsed ( +- 0.26% ) REFCOUNT_TIMING (REFCOUNT_FULL, this series): 31.7408 +- 0.0486 seconds time elapsed ( +- 0.15% ) Signed-off-by: Will Deacon Reviewed-by: Ard Biesheuvel Reviewed-by: Kees Cook Tested-by: Hanjun Guo Tested-by: Jan Glauber Cc: Ard Biesheuvel Cc: Elena Reshetova Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20191121115902.2551-6-will@kernel.org Signed-off-by: Ingo Molnar --- include/linux/refcount.h | 131 +++++++++++++++++++++++++++-------------------- 1 file changed, 75 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/include/linux/refcount.h b/include/linux/refcount.h index e719b5b1220e..e3b218d669ce 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -47,8 +47,8 @@ static inline unsigned int refcount_read(const refcount_t *r) #ifdef CONFIG_REFCOUNT_FULL #include -#define REFCOUNT_MAX (UINT_MAX - 1) -#define REFCOUNT_SATURATED UINT_MAX +#define REFCOUNT_MAX INT_MAX +#define REFCOUNT_SATURATED (INT_MIN / 2) /* * Variant of atomic_t specialized for reference counts. @@ -56,9 +56,47 @@ static inline unsigned int refcount_read(const refcount_t *r) * The interface matches the atomic_t interface (to aid in porting) but only * provides the few functions one should use for reference counting. * - * It differs in that the counter saturates at REFCOUNT_SATURATED and will not - * move once there. This avoids wrapping the counter and causing 'spurious' - * use-after-free issues. + * Saturation semantics + * ==================== + * + * refcount_t differs from atomic_t in that the counter saturates at + * REFCOUNT_SATURATED and will not move once there. This avoids wrapping the + * counter and causing 'spurious' use-after-free issues. In order to avoid the + * cost associated with introducing cmpxchg() loops into all of the saturating + * operations, we temporarily allow the counter to take on an unchecked value + * and then explicitly set it to REFCOUNT_SATURATED on detecting that underflow + * or overflow has occurred. Although this is racy when multiple threads + * access the refcount concurrently, by placing REFCOUNT_SATURATED roughly + * equidistant from 0 and INT_MAX we minimise the scope for error: + * + * INT_MAX REFCOUNT_SATURATED UINT_MAX + * 0 (0x7fff_ffff) (0xc000_0000) (0xffff_ffff) + * +--------------------------------+----------------+----------------+ + * <---------- bad value! ----------> + * + * (in a signed view of the world, the "bad value" range corresponds to + * a negative counter value). + * + * As an example, consider a refcount_inc() operation that causes the counter + * to overflow: + * + * int old = atomic_fetch_add_relaxed(r); + * // old is INT_MAX, refcount now INT_MIN (0x8000_0000) + * if (old < 0) + * atomic_set(r, REFCOUNT_SATURATED); + * + * If another thread also performs a refcount_inc() operation between the two + * atomic operations, then the count will continue to edge closer to 0. If it + * reaches a value of 1 before /any/ of the threads reset it to the saturated + * value, then a concurrent refcount_dec_and_test() may erroneously free the + * underlying object. Given the precise timing details involved with the + * round-robin scheduling of each thread manipulating the refcount and the need + * to hit the race multiple times in succession, there doesn't appear to be a + * practical avenue of attack even if using refcount_add() operations with + * larger increments. + * + * Memory ordering + * =============== * * Memory ordering rules are slightly relaxed wrt regular atomic_t functions * and provide only what is strictly required for refcounts. @@ -109,25 +147,19 @@ static inline unsigned int refcount_read(const refcount_t *r) */ static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) { - unsigned int new, val = atomic_read(&r->refs); + int old = refcount_read(r); do { - if (!val) - return false; - - if (unlikely(val == REFCOUNT_SATURATED)) - return true; - - new = val + i; - if (new < val) - new = REFCOUNT_SATURATED; + if (!old) + break; + } while (!atomic_try_cmpxchg_relaxed(&r->refs, &old, old + i)); - } while (!atomic_try_cmpxchg_relaxed(&r->refs, &val, new)); - - WARN_ONCE(new == REFCOUNT_SATURATED, - "refcount_t: saturated; leaking memory.\n"); + if (unlikely(old < 0 || old + i < 0)) { + refcount_set(r, REFCOUNT_SATURATED); + WARN_ONCE(1, "refcount_t: saturated; leaking memory.\n"); + } - return true; + return old; } /** @@ -148,7 +180,13 @@ static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) */ static inline void refcount_add(int i, refcount_t *r) { - WARN_ONCE(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n"); + int old = atomic_fetch_add_relaxed(i, &r->refs); + + WARN_ONCE(!old, "refcount_t: addition on 0; use-after-free.\n"); + if (unlikely(old <= 0 || old + i <= 0)) { + refcount_set(r, REFCOUNT_SATURATED); + WARN_ONCE(old, "refcount_t: saturated; leaking memory.\n"); + } } /** @@ -166,23 +204,7 @@ static inline void refcount_add(int i, refcount_t *r) */ static inline __must_check bool refcount_inc_not_zero(refcount_t *r) { - unsigned int new, val = atomic_read(&r->refs); - - do { - new = val + 1; - - if (!val) - return false; - - if (unlikely(!new)) - return true; - - } while (!atomic_try_cmpxchg_relaxed(&r->refs, &val, new)); - - WARN_ONCE(new == REFCOUNT_SATURATED, - "refcount_t: saturated; leaking memory.\n"); - - return true; + return refcount_add_not_zero(1, r); } /** @@ -199,7 +221,7 @@ static inline __must_check bool refcount_inc_not_zero(refcount_t *r) */ static inline void refcount_inc(refcount_t *r) { - WARN_ONCE(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n"); + refcount_add(1, r); } /** @@ -224,26 +246,19 @@ static inline void refcount_inc(refcount_t *r) */ static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r) { - unsigned int new, val = atomic_read(&r->refs); - - do { - if (unlikely(val == REFCOUNT_SATURATED)) - return false; + int old = atomic_fetch_sub_release(i, &r->refs); - new = val - i; - if (new > val) { - WARN_ONCE(new > val, "refcount_t: underflow; use-after-free.\n"); - return false; - } - - } while (!atomic_try_cmpxchg_release(&r->refs, &val, new)); - - if (!new) { + if (old == i) { smp_acquire__after_ctrl_dep(); return true; } - return false; + if (unlikely(old < 0 || old - i < 0)) { + refcount_set(r, REFCOUNT_SATURATED); + WARN_ONCE(1, "refcount_t: underflow; use-after-free.\n"); + } + + return false; } /** @@ -276,9 +291,13 @@ static inline __must_check bool refcount_dec_and_test(refcount_t *r) */ static inline void refcount_dec(refcount_t *r) { - WARN_ONCE(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n"); -} + int old = atomic_fetch_sub_release(1, &r->refs); + if (unlikely(old <= 1)) { + refcount_set(r, REFCOUNT_SATURATED); + WARN_ONCE(1, "refcount_t: decrement hit 0; leaking memory.\n"); + } +} #else /* CONFIG_REFCOUNT_FULL */ #define REFCOUNT_MAX INT_MAX -- cgit v1.2.3-71-gd317 From 1eb085d94256aaa69b00cf5a86e3c5f5bb2bc460 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 21 Nov 2019 11:58:58 +0000 Subject: locking/refcount: Move saturation warnings out of line Having the refcount saturation and warnings inline bloats the text, despite the fact that these paths should never be executed in normal operation. Move the refcount saturation and warnings out of line to reduce the image size when refcount_t checking is enabled. Relative to an x86_64 defconfig, the sizes reported by bloat-o-meter are: # defconfig+REFCOUNT_FULL, inline saturation (i.e. before this patch) Total: Before=14762076, After=14915442, chg +1.04% # defconfig+REFCOUNT_FULL, out-of-line saturation (i.e. after this patch) Total: Before=14762076, After=14835497, chg +0.50% A side-effect of this change is that we now only get one warning per refcount saturation type, rather than one per problematic call-site. Signed-off-by: Will Deacon Reviewed-by: Ard Biesheuvel Reviewed-by: Kees Cook Tested-by: Hanjun Guo Cc: Ard Biesheuvel Cc: Elena Reshetova Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20191121115902.2551-7-will@kernel.org Signed-off-by: Ingo Molnar --- include/linux/refcount.h | 39 ++++++++++++++++++++------------------- lib/refcount.c | 28 ++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/refcount.h b/include/linux/refcount.h index e3b218d669ce..1cd0a876a789 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -23,6 +23,16 @@ typedef struct refcount_struct { #define REFCOUNT_INIT(n) { .refs = ATOMIC_INIT(n), } +enum refcount_saturation_type { + REFCOUNT_ADD_NOT_ZERO_OVF, + REFCOUNT_ADD_OVF, + REFCOUNT_ADD_UAF, + REFCOUNT_SUB_UAF, + REFCOUNT_DEC_LEAK, +}; + +void refcount_warn_saturate(refcount_t *r, enum refcount_saturation_type t); + /** * refcount_set - set a refcount's value * @r: the refcount @@ -154,10 +164,8 @@ static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) break; } while (!atomic_try_cmpxchg_relaxed(&r->refs, &old, old + i)); - if (unlikely(old < 0 || old + i < 0)) { - refcount_set(r, REFCOUNT_SATURATED); - WARN_ONCE(1, "refcount_t: saturated; leaking memory.\n"); - } + if (unlikely(old < 0 || old + i < 0)) + refcount_warn_saturate(r, REFCOUNT_ADD_NOT_ZERO_OVF); return old; } @@ -182,11 +190,10 @@ static inline void refcount_add(int i, refcount_t *r) { int old = atomic_fetch_add_relaxed(i, &r->refs); - WARN_ONCE(!old, "refcount_t: addition on 0; use-after-free.\n"); - if (unlikely(old <= 0 || old + i <= 0)) { - refcount_set(r, REFCOUNT_SATURATED); - WARN_ONCE(old, "refcount_t: saturated; leaking memory.\n"); - } + if (unlikely(!old)) + refcount_warn_saturate(r, REFCOUNT_ADD_UAF); + else if (unlikely(old < 0 || old + i < 0)) + refcount_warn_saturate(r, REFCOUNT_ADD_OVF); } /** @@ -253,10 +260,8 @@ static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r) return true; } - if (unlikely(old < 0 || old - i < 0)) { - refcount_set(r, REFCOUNT_SATURATED); - WARN_ONCE(1, "refcount_t: underflow; use-after-free.\n"); - } + if (unlikely(old < 0 || old - i < 0)) + refcount_warn_saturate(r, REFCOUNT_SUB_UAF); return false; } @@ -291,12 +296,8 @@ static inline __must_check bool refcount_dec_and_test(refcount_t *r) */ static inline void refcount_dec(refcount_t *r) { - int old = atomic_fetch_sub_release(1, &r->refs); - - if (unlikely(old <= 1)) { - refcount_set(r, REFCOUNT_SATURATED); - WARN_ONCE(1, "refcount_t: decrement hit 0; leaking memory.\n"); - } + if (unlikely(atomic_fetch_sub_release(1, &r->refs) <= 1)) + refcount_warn_saturate(r, REFCOUNT_DEC_LEAK); } #else /* CONFIG_REFCOUNT_FULL */ diff --git a/lib/refcount.c b/lib/refcount.c index 3a534fbebdcc..8b7e249c0e10 100644 --- a/lib/refcount.c +++ b/lib/refcount.c @@ -8,6 +8,34 @@ #include #include +#define REFCOUNT_WARN(str) WARN_ONCE(1, "refcount_t: " str ".\n") + +void refcount_warn_saturate(refcount_t *r, enum refcount_saturation_type t) +{ + refcount_set(r, REFCOUNT_SATURATED); + + switch (t) { + case REFCOUNT_ADD_NOT_ZERO_OVF: + REFCOUNT_WARN("saturated; leaking memory"); + break; + case REFCOUNT_ADD_OVF: + REFCOUNT_WARN("saturated; leaking memory"); + break; + case REFCOUNT_ADD_UAF: + REFCOUNT_WARN("addition on 0; use-after-free"); + break; + case REFCOUNT_SUB_UAF: + REFCOUNT_WARN("underflow; use-after-free"); + break; + case REFCOUNT_DEC_LEAK: + REFCOUNT_WARN("decrement hit 0; leaking memory"); + break; + default: + REFCOUNT_WARN("unknown saturation event!?"); + } +} +EXPORT_SYMBOL(refcount_warn_saturate); + /** * refcount_dec_if_one - decrement a refcount if it is 1 * @r: the refcount -- cgit v1.2.3-71-gd317 From 65b008552469f1c37f5e06e0016924502e40b4f5 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 21 Nov 2019 11:58:59 +0000 Subject: locking/refcount: Consolidate REFCOUNT_{MAX,SATURATED} definitions The definitions of REFCOUNT_MAX and REFCOUNT_SATURATED are the same, regardless of CONFIG_REFCOUNT_FULL, so consolidate them into a single pair of definitions. Signed-off-by: Will Deacon Reviewed-by: Ard Biesheuvel Reviewed-by: Kees Cook Tested-by: Hanjun Guo Cc: Ard Biesheuvel Cc: Elena Reshetova Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20191121115902.2551-8-will@kernel.org Signed-off-by: Ingo Molnar --- include/linux/refcount.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/refcount.h b/include/linux/refcount.h index 1cd0a876a789..757d4630115c 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -22,6 +22,8 @@ typedef struct refcount_struct { } refcount_t; #define REFCOUNT_INIT(n) { .refs = ATOMIC_INIT(n), } +#define REFCOUNT_MAX INT_MAX +#define REFCOUNT_SATURATED (INT_MIN / 2) enum refcount_saturation_type { REFCOUNT_ADD_NOT_ZERO_OVF, @@ -57,9 +59,6 @@ static inline unsigned int refcount_read(const refcount_t *r) #ifdef CONFIG_REFCOUNT_FULL #include -#define REFCOUNT_MAX INT_MAX -#define REFCOUNT_SATURATED (INT_MIN / 2) - /* * Variant of atomic_t specialized for reference counts. * @@ -300,10 +299,6 @@ static inline void refcount_dec(refcount_t *r) refcount_warn_saturate(r, REFCOUNT_DEC_LEAK); } #else /* CONFIG_REFCOUNT_FULL */ - -#define REFCOUNT_MAX INT_MAX -#define REFCOUNT_SATURATED (INT_MIN / 2) - # ifdef CONFIG_ARCH_HAS_REFCOUNT # include # else -- cgit v1.2.3-71-gd317 From fb041bb7c0a918b95c6889fc965cdc4a75b4c0ca Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 21 Nov 2019 11:59:00 +0000 Subject: locking/refcount: Consolidate implementations of refcount_t The generic implementation of refcount_t should be good enough for everybody, so remove ARCH_HAS_REFCOUNT and REFCOUNT_FULL entirely, leaving the generic implementation enabled unconditionally. Signed-off-by: Will Deacon Reviewed-by: Ard Biesheuvel Acked-by: Kees Cook Tested-by: Hanjun Guo Cc: Ard Biesheuvel Cc: Elena Reshetova Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20191121115902.2551-9-will@kernel.org Signed-off-by: Ingo Molnar --- arch/Kconfig | 21 ----- arch/arm/Kconfig | 1 - arch/arm64/Kconfig | 1 - arch/s390/configs/debug_defconfig | 1 - arch/x86/Kconfig | 1 - arch/x86/include/asm/asm.h | 6 -- arch/x86/include/asm/refcount.h | 126 ----------------------------- arch/x86/mm/extable.c | 49 ------------ drivers/gpu/drm/i915/Kconfig.debug | 1 - include/linux/refcount.h | 158 ++++++++++++++----------------------- lib/refcount.c | 2 +- 11 files changed, 59 insertions(+), 308 deletions(-) delete mode 100644 arch/x86/include/asm/refcount.h (limited to 'include/linux') diff --git a/arch/Kconfig b/arch/Kconfig index 5f8a5d84dbbe..8bcc1c746142 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -892,27 +892,6 @@ config STRICT_MODULE_RWX config ARCH_HAS_PHYS_TO_DMA bool -config ARCH_HAS_REFCOUNT - bool - help - An architecture selects this when it has implemented refcount_t - using open coded assembly primitives that provide an optimized - refcount_t implementation, possibly at the expense of some full - refcount state checks of CONFIG_REFCOUNT_FULL=y. - - The refcount overflow check behavior, however, must be retained. - Catching overflows is the primary security concern for protecting - against bugs in reference counts. - -config REFCOUNT_FULL - bool "Perform full reference count validation at the expense of speed" - help - Enabling this switches the refcounting infrastructure from a fast - unchecked atomic_t implementation to a fully state checked - implementation, which can be (slightly) slower but provides protections - against various use-after-free conditions that can be used in - security flaw exploits. - config HAVE_ARCH_COMPILER_H bool help diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 8a50efb559f3..0d3c5d7cceb7 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -117,7 +117,6 @@ config ARM select OLD_SIGSUSPEND3 select PCI_SYSCALL if PCI select PERF_USE_VMALLOC - select REFCOUNT_FULL select RTC_LIB select SYS_SUPPORTS_APM_EMULATION # Above selects are sorted alphabetically; please add new ones diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 41a9b4257b72..bc990d3abfe9 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -181,7 +181,6 @@ config ARM64 select PCI_SYSCALL if PCI select POWER_RESET select POWER_SUPPLY - select REFCOUNT_FULL select SPARSE_IRQ select SWIOTLB select SYSCTL_EXCEPTION_TRACE diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 38d64030aacf..2e60c80395ab 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -62,7 +62,6 @@ CONFIG_OPROFILE=m CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y CONFIG_STATIC_KEYS_SELFTEST=y -CONFIG_REFCOUNT_FULL=y CONFIG_LOCK_EVENT_COUNTS=y CONFIG_MODULES=y CONFIG_MODULE_FORCE_LOAD=y diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index d6e1faa28c58..fa6274f1e370 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -73,7 +73,6 @@ config X86 select ARCH_HAS_PMEM_API if X86_64 select ARCH_HAS_PTE_DEVMAP if X86_64 select ARCH_HAS_PTE_SPECIAL - select ARCH_HAS_REFCOUNT select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64 select ARCH_HAS_UACCESS_MCSAFE if X86_64 && X86_MCE select ARCH_HAS_SET_MEMORY diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 3ff577c0b102..5a0c14ebef70 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -139,9 +139,6 @@ # define _ASM_EXTABLE_EX(from, to) \ _ASM_EXTABLE_HANDLE(from, to, ex_handler_ext) -# define _ASM_EXTABLE_REFCOUNT(from, to) \ - _ASM_EXTABLE_HANDLE(from, to, ex_handler_refcount) - # define _ASM_NOKPROBE(entry) \ .pushsection "_kprobe_blacklist","aw" ; \ _ASM_ALIGN ; \ @@ -170,9 +167,6 @@ # define _ASM_EXTABLE_EX(from, to) \ _ASM_EXTABLE_HANDLE(from, to, ex_handler_ext) -# define _ASM_EXTABLE_REFCOUNT(from, to) \ - _ASM_EXTABLE_HANDLE(from, to, ex_handler_refcount) - /* For C file, we already have NOKPROBE_SYMBOL macro */ #endif diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h deleted file mode 100644 index 232f856e0db0..000000000000 --- a/arch/x86/include/asm/refcount.h +++ /dev/null @@ -1,126 +0,0 @@ -#ifndef __ASM_X86_REFCOUNT_H -#define __ASM_X86_REFCOUNT_H -/* - * x86-specific implementation of refcount_t. Based on PAX_REFCOUNT from - * PaX/grsecurity. - */ -#include -#include - -/* - * This is the first portion of the refcount error handling, which lives in - * .text.unlikely, and is jumped to from the CPU flag check (in the - * following macros). This saves the refcount value location into CX for - * the exception handler to use (in mm/extable.c), and then triggers the - * central refcount exception. The fixup address for the exception points - * back to the regular execution flow in .text. - */ -#define _REFCOUNT_EXCEPTION \ - ".pushsection .text..refcount\n" \ - "111:\tlea %[var], %%" _ASM_CX "\n" \ - "112:\t" ASM_UD2 "\n" \ - ASM_UNREACHABLE \ - ".popsection\n" \ - "113:\n" \ - _ASM_EXTABLE_REFCOUNT(112b, 113b) - -/* Trigger refcount exception if refcount result is negative. */ -#define REFCOUNT_CHECK_LT_ZERO \ - "js 111f\n\t" \ - _REFCOUNT_EXCEPTION - -/* Trigger refcount exception if refcount result is zero or negative. */ -#define REFCOUNT_CHECK_LE_ZERO \ - "jz 111f\n\t" \ - REFCOUNT_CHECK_LT_ZERO - -/* Trigger refcount exception unconditionally. */ -#define REFCOUNT_ERROR \ - "jmp 111f\n\t" \ - _REFCOUNT_EXCEPTION - -static __always_inline void refcount_add(unsigned int i, refcount_t *r) -{ - asm volatile(LOCK_PREFIX "addl %1,%0\n\t" - REFCOUNT_CHECK_LT_ZERO - : [var] "+m" (r->refs.counter) - : "ir" (i) - : "cc", "cx"); -} - -static __always_inline void refcount_inc(refcount_t *r) -{ - asm volatile(LOCK_PREFIX "incl %0\n\t" - REFCOUNT_CHECK_LT_ZERO - : [var] "+m" (r->refs.counter) - : : "cc", "cx"); -} - -static __always_inline void refcount_dec(refcount_t *r) -{ - asm volatile(LOCK_PREFIX "decl %0\n\t" - REFCOUNT_CHECK_LE_ZERO - : [var] "+m" (r->refs.counter) - : : "cc", "cx"); -} - -static __always_inline __must_check -bool refcount_sub_and_test(unsigned int i, refcount_t *r) -{ - bool ret = GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl", - REFCOUNT_CHECK_LT_ZERO, - r->refs.counter, e, "er", i, "cx"); - - if (ret) { - smp_acquire__after_ctrl_dep(); - return true; - } - - return false; -} - -static __always_inline __must_check bool refcount_dec_and_test(refcount_t *r) -{ - bool ret = GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl", - REFCOUNT_CHECK_LT_ZERO, - r->refs.counter, e, "cx"); - - if (ret) { - smp_acquire__after_ctrl_dep(); - return true; - } - - return false; -} - -static __always_inline __must_check -bool refcount_add_not_zero(unsigned int i, refcount_t *r) -{ - int c, result; - - c = atomic_read(&(r->refs)); - do { - if (unlikely(c == 0)) - return false; - - result = c + i; - - /* Did we try to increment from/to an undesirable state? */ - if (unlikely(c < 0 || c == INT_MAX || result < c)) { - asm volatile(REFCOUNT_ERROR - : : [var] "m" (r->refs.counter) - : "cc", "cx"); - break; - } - - } while (!atomic_try_cmpxchg(&(r->refs), &c, result)); - - return c != 0; -} - -static __always_inline __must_check bool refcount_inc_not_zero(refcount_t *r) -{ - return refcount_add_not_zero(1, r); -} - -#endif diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 4d75bc656f97..30bb0bd3b1b8 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -44,55 +44,6 @@ __visible bool ex_handler_fault(const struct exception_table_entry *fixup, } EXPORT_SYMBOL_GPL(ex_handler_fault); -/* - * Handler for UD0 exception following a failed test against the - * result of a refcount inc/dec/add/sub. - */ -__visible bool ex_handler_refcount(const struct exception_table_entry *fixup, - struct pt_regs *regs, int trapnr, - unsigned long error_code, - unsigned long fault_addr) -{ - /* First unconditionally saturate the refcount. */ - *(int *)regs->cx = INT_MIN / 2; - - /* - * Strictly speaking, this reports the fixup destination, not - * the fault location, and not the actually overflowing - * instruction, which is the instruction before the "js", but - * since that instruction could be a variety of lengths, just - * report the location after the overflow, which should be close - * enough for finding the overflow, as it's at least back in - * the function, having returned from .text.unlikely. - */ - regs->ip = ex_fixup_addr(fixup); - - /* - * This function has been called because either a negative refcount - * value was seen by any of the refcount functions, or a zero - * refcount value was seen by refcount_dec(). - * - * If we crossed from INT_MAX to INT_MIN, OF (Overflow Flag: result - * wrapped around) will be set. Additionally, seeing the refcount - * reach 0 will set ZF (Zero Flag: result was zero). In each of - * these cases we want a report, since it's a boundary condition. - * The SF case is not reported since it indicates post-boundary - * manipulations below zero or above INT_MAX. And if none of the - * flags are set, something has gone very wrong, so report it. - */ - if (regs->flags & (X86_EFLAGS_OF | X86_EFLAGS_ZF)) { - bool zero = regs->flags & X86_EFLAGS_ZF; - - refcount_error_report(regs, zero ? "hit zero" : "overflow"); - } else if ((regs->flags & X86_EFLAGS_SF) == 0) { - /* Report if none of OF, ZF, nor SF are set. */ - refcount_error_report(regs, "unexpected saturation"); - } - - return true; -} -EXPORT_SYMBOL(ex_handler_refcount); - /* * Handler for when we fail to restore a task's FPU state. We should never get * here because the FPU state of a task using the FPU (task->thread.fpu.state) diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug index 00786a142ff0..1400fce39c58 100644 --- a/drivers/gpu/drm/i915/Kconfig.debug +++ b/drivers/gpu/drm/i915/Kconfig.debug @@ -22,7 +22,6 @@ config DRM_I915_DEBUG depends on DRM_I915 select DEBUG_FS select PREEMPT_COUNT - select REFCOUNT_FULL select I2C_CHARDEV select STACKDEPOT select DRM_DP_AUX_CHARDEV diff --git a/include/linux/refcount.h b/include/linux/refcount.h index 757d4630115c..0ac50cf62d06 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -1,64 +1,4 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_REFCOUNT_H -#define _LINUX_REFCOUNT_H - -#include -#include -#include -#include - -struct mutex; - -/** - * struct refcount_t - variant of atomic_t specialized for reference counts - * @refs: atomic_t counter field - * - * The counter saturates at REFCOUNT_SATURATED and will not move once - * there. This avoids wrapping the counter and causing 'spurious' - * use-after-free bugs. - */ -typedef struct refcount_struct { - atomic_t refs; -} refcount_t; - -#define REFCOUNT_INIT(n) { .refs = ATOMIC_INIT(n), } -#define REFCOUNT_MAX INT_MAX -#define REFCOUNT_SATURATED (INT_MIN / 2) - -enum refcount_saturation_type { - REFCOUNT_ADD_NOT_ZERO_OVF, - REFCOUNT_ADD_OVF, - REFCOUNT_ADD_UAF, - REFCOUNT_SUB_UAF, - REFCOUNT_DEC_LEAK, -}; - -void refcount_warn_saturate(refcount_t *r, enum refcount_saturation_type t); - -/** - * refcount_set - set a refcount's value - * @r: the refcount - * @n: value to which the refcount will be set - */ -static inline void refcount_set(refcount_t *r, int n) -{ - atomic_set(&r->refs, n); -} - -/** - * refcount_read - get a refcount's value - * @r: the refcount - * - * Return: the refcount's value - */ -static inline unsigned int refcount_read(const refcount_t *r) -{ - return atomic_read(&r->refs); -} - -#ifdef CONFIG_REFCOUNT_FULL -#include - /* * Variant of atomic_t specialized for reference counts. * @@ -136,6 +76,64 @@ static inline unsigned int refcount_read(const refcount_t *r) * */ +#ifndef _LINUX_REFCOUNT_H +#define _LINUX_REFCOUNT_H + +#include +#include +#include +#include +#include + +struct mutex; + +/** + * struct refcount_t - variant of atomic_t specialized for reference counts + * @refs: atomic_t counter field + * + * The counter saturates at REFCOUNT_SATURATED and will not move once + * there. This avoids wrapping the counter and causing 'spurious' + * use-after-free bugs. + */ +typedef struct refcount_struct { + atomic_t refs; +} refcount_t; + +#define REFCOUNT_INIT(n) { .refs = ATOMIC_INIT(n), } +#define REFCOUNT_MAX INT_MAX +#define REFCOUNT_SATURATED (INT_MIN / 2) + +enum refcount_saturation_type { + REFCOUNT_ADD_NOT_ZERO_OVF, + REFCOUNT_ADD_OVF, + REFCOUNT_ADD_UAF, + REFCOUNT_SUB_UAF, + REFCOUNT_DEC_LEAK, +}; + +void refcount_warn_saturate(refcount_t *r, enum refcount_saturation_type t); + +/** + * refcount_set - set a refcount's value + * @r: the refcount + * @n: value to which the refcount will be set + */ +static inline void refcount_set(refcount_t *r, int n) +{ + atomic_set(&r->refs, n); +} + +/** + * refcount_read - get a refcount's value + * @r: the refcount + * + * Return: the refcount's value + */ +static inline unsigned int refcount_read(const refcount_t *r) +{ + return atomic_read(&r->refs); +} + /** * refcount_add_not_zero - add a value to a refcount unless it is 0 * @i: the value to add to the refcount @@ -298,46 +296,6 @@ static inline void refcount_dec(refcount_t *r) if (unlikely(atomic_fetch_sub_release(1, &r->refs) <= 1)) refcount_warn_saturate(r, REFCOUNT_DEC_LEAK); } -#else /* CONFIG_REFCOUNT_FULL */ -# ifdef CONFIG_ARCH_HAS_REFCOUNT -# include -# else -static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) -{ - return atomic_add_unless(&r->refs, i, 0); -} - -static inline void refcount_add(int i, refcount_t *r) -{ - atomic_add(i, &r->refs); -} - -static inline __must_check bool refcount_inc_not_zero(refcount_t *r) -{ - return atomic_add_unless(&r->refs, 1, 0); -} - -static inline void refcount_inc(refcount_t *r) -{ - atomic_inc(&r->refs); -} - -static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r) -{ - return atomic_sub_and_test(i, &r->refs); -} - -static inline __must_check bool refcount_dec_and_test(refcount_t *r) -{ - return atomic_dec_and_test(&r->refs); -} - -static inline void refcount_dec(refcount_t *r) -{ - atomic_dec(&r->refs); -} -# endif /* !CONFIG_ARCH_HAS_REFCOUNT */ -#endif /* !CONFIG_REFCOUNT_FULL */ extern __must_check bool refcount_dec_if_one(refcount_t *r); extern __must_check bool refcount_dec_not_one(refcount_t *r); diff --git a/lib/refcount.c b/lib/refcount.c index 8b7e249c0e10..ebac8b7d15a7 100644 --- a/lib/refcount.c +++ b/lib/refcount.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Out-of-line refcount functions common to all refcount implementations. + * Out-of-line refcount functions. */ #include -- cgit v1.2.3-71-gd317 From 2f30b36943adca070f2e1551f701bd524ed1ae5a Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 21 Nov 2019 11:59:01 +0000 Subject: locking/refcount: Remove unused 'refcount_error_report()' function 'refcount_error_report()' has no callers. Remove it. Signed-off-by: Will Deacon Reviewed-by: Ard Biesheuvel Acked-by: Kees Cook Tested-by: Hanjun Guo Cc: Ard Biesheuvel Cc: Elena Reshetova Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20191121115902.2551-10-will@kernel.org Signed-off-by: Ingo Molnar --- include/linux/kernel.h | 7 ------- kernel/panic.c | 11 ----------- 2 files changed, 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index d83d403dac2e..09f759228e3f 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -328,13 +328,6 @@ extern int oops_may_print(void); void do_exit(long error_code) __noreturn; void complete_and_exit(struct completion *, long) __noreturn; -#ifdef CONFIG_ARCH_HAS_REFCOUNT -void refcount_error_report(struct pt_regs *regs, const char *err); -#else -static inline void refcount_error_report(struct pt_regs *regs, const char *err) -{ } -#endif - /* Internal, do not use. */ int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res); int __must_check _kstrtol(const char *s, unsigned int base, long *res); diff --git a/kernel/panic.c b/kernel/panic.c index f470a038b05b..b69ee9e76cb2 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -671,17 +671,6 @@ EXPORT_SYMBOL(__stack_chk_fail); #endif -#ifdef CONFIG_ARCH_HAS_REFCOUNT -void refcount_error_report(struct pt_regs *regs, const char *err) -{ - WARN_RATELIMIT(1, "refcount_t %s at %pB in %s[%d], uid/euid: %u/%u\n", - err, (void *)instruction_pointer(regs), - current->comm, task_pid_nr(current), - from_kuid_munged(&init_user_ns, current_uid()), - from_kuid_munged(&init_user_ns, current_euid())); -} -#endif - core_param(panic, panic_timeout, int, 0644); core_param(panic_print, panic_print, ulong, 0644); core_param(pause_on_oops, pause_on_oops, int, 0644); -- cgit v1.2.3-71-gd317 From 0be0ee71816b2b6725e2b4f32ad6726c9d729777 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 11 Nov 2019 15:51:03 -0800 Subject: vfs: properly and reliably lock f_pos in fdget_pos() fdget_pos() is used by file operations that will read and update f_pos: things like "read()", "write()" and "lseek()" (but not, for example, "pread()/pwrite" that get their file positions elsewhere). However, it had two separate escape clauses for this, because not everybody wants or needs serialization of the file position. The first and most obvious case is the "file descriptor doesn't have a position at all", ie a stream-like file. Except we didn't actually use FMODE_STREAM, but instead used FMODE_ATOMIC_POS. The reason for that was that FMODE_STREAM didn't exist back in the days, but also that we didn't want to mark all the special cases, so we only marked the ones that _required_ position atomicity according to POSIX - regular files and directories. The case one was intentionally lazy, but now that we _do_ have FMODE_STREAM we could and should just use it. With the change to use FMODE_STREAM, there are no remaining uses for FMODE_ATOMIC_POS, and all the code to set it is deleted. Any cases where we don't want the serialization because the driver (or subsystem) doesn't use the file position should just be updated to do "stream_open()". We've done that for all the obvious and common situations, we may need a few more. Quoting Kirill Smelkov in the original FMODE_STREAM thread (see link below for full email): "And I appreciate if people could help at least somehow with "getting rid of mixed case entirely" (i.e. always lock f_pos_lock on !FMODE_STREAM), because this transition starts to diverge from my particular use-case too far. To me it makes sense to do that transition as follows: - convert nonseekable_open -> stream_open via stream_open.cocci; - audit other nonseekable_open calls and convert left users that truly don't depend on position to stream_open; - extend stream_open.cocci to analyze alloc_file_pseudo as well (this will cover pipes and sockets), or maybe convert pipes and sockets to FMODE_STREAM manually; - extend stream_open.cocci to analyze file_operations that use no_llseek or noop_llseek, but do not use nonseekable_open or alloc_file_pseudo. This might find files that have stream semantic but are opened differently; - extend stream_open.cocci to analyze file_operations whose .read/.write do not use ppos at all (independently of how file was opened); - ... - after that remove FMODE_ATOMIC_POS and always take f_pos_lock if !FMODE_STREAM; - gather bug reports for deadlocked read/write and convert missed cases to FMODE_STREAM, probably extending stream_open.cocci along the road to catch similar cases i.e. always take f_pos_lock unless a file is explicitly marked as being stream, and try to find and cover all files that are streams" We have not done the "extend stream_open.cocci to analyze alloc_file_pseudo" as well, but the previous commit did manually handle the case of pipes and sockets. The other case where we can avoid locking f_pos is the "this file descriptor only has a single user and it is us, and thus there is no need to lock it". The second test was correct, although a bit subtle and worth just re-iterating here. There are two kinds of other sources of references to the same file descriptor: file descriptors that have been explicitly shared across fork() or with dup(), and file tables having elevated reference counts due to threading (or explicit file sharing with clone()). The first case would have incremented the file count explicitly, and in the second case the previous __fdget() would have incremented it for us and set the FDPUT_FPUT flag. But in both cases the file count would be greater than one, so the "file_count(file) > 1" test catches both situations. Also note that if file_count is 1, that also means that no other thread can have access to the file table, so there also cannot be races with concurrent calls to dup()/fork()/clone() that would increment the file count any other way. Link: https://lore.kernel.org/linux-fsdevel/20190413184404.GA13490@deco.navytux.spb.ru Cc: Kirill Smelkov Cc: Eic Dumazet Cc: Al Viro Cc: Alan Stern Cc: Marco Elver Cc: Andrea Parri Cc: Paul McKenney Signed-off-by: Linus Torvalds --- fs/file.c | 2 +- fs/open.c | 6 +----- include/linux/fs.h | 2 -- 3 files changed, 2 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/fs/file.c b/fs/file.c index 3da91a112bab..b241ea7f1aa4 100644 --- a/fs/file.c +++ b/fs/file.c @@ -795,7 +795,7 @@ unsigned long __fdget_pos(unsigned int fd) unsigned long v = __fdget(fd); struct file *file = (struct file *)(v & ~3); - if (file && (file->f_mode & FMODE_ATOMIC_POS)) { + if (file && !(file->f_mode & FMODE_STREAM)) { if (file_count(file) > 1) { v |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); diff --git a/fs/open.c b/fs/open.c index b62f5c0923a8..5c68282ea79e 100644 --- a/fs/open.c +++ b/fs/open.c @@ -771,10 +771,6 @@ static int do_dentry_open(struct file *f, f->f_mode |= FMODE_WRITER; } - /* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */ - if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)) - f->f_mode |= FMODE_ATOMIC_POS; - f->f_op = fops_get(inode->i_fop); if (WARN_ON(!f->f_op)) { error = -ENODEV; @@ -1256,7 +1252,7 @@ EXPORT_SYMBOL(nonseekable_open); */ int stream_open(struct inode *inode, struct file *filp) { - filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS); + filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE); filp->f_mode |= FMODE_STREAM; return 0; } diff --git a/include/linux/fs.h b/include/linux/fs.h index e0d909d35763..a7c3f6dd5701 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -148,8 +148,6 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File is opened with O_PATH; almost nothing can be done with it */ #define FMODE_PATH ((__force fmode_t)0x4000) -/* File needs atomic accesses to f_pos */ -#define FMODE_ATOMIC_POS ((__force fmode_t)0x8000) /* Write access to underlying fs */ #define FMODE_WRITER ((__force fmode_t)0x10000) /* Has read method(s) */ -- cgit v1.2.3-71-gd317 From bec170e55982c2d3b8e1beccadf16e288fe6fb5a Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sat, 23 Nov 2019 17:28:37 +0100 Subject: net: phy: add helpers phy_(un)lock_mdio_bus Add helpers to make locking/unlocking the MDIO bus easier. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- drivers/net/phy/phy-core.c | 28 ++++++++++++++-------------- include/linux/phy.h | 10 ++++++++++ 2 files changed, 24 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 5458ed1b87a8..769a076514b0 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -419,9 +419,9 @@ int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum) { int ret; - mutex_lock(&phydev->mdio.bus->mdio_lock); + phy_lock_mdio_bus(phydev); ret = __phy_read_mmd(phydev, devad, regnum); - mutex_unlock(&phydev->mdio.bus->mdio_lock); + phy_unlock_mdio_bus(phydev); return ret; } @@ -480,9 +480,9 @@ int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) { int ret; - mutex_lock(&phydev->mdio.bus->mdio_lock); + phy_lock_mdio_bus(phydev); ret = __phy_write_mmd(phydev, devad, regnum, val); - mutex_unlock(&phydev->mdio.bus->mdio_lock); + phy_unlock_mdio_bus(phydev); return ret; } @@ -536,9 +536,9 @@ int phy_modify_changed(struct phy_device *phydev, u32 regnum, u16 mask, u16 set) { int ret; - mutex_lock(&phydev->mdio.bus->mdio_lock); + phy_lock_mdio_bus(phydev); ret = __phy_modify_changed(phydev, regnum, mask, set); - mutex_unlock(&phydev->mdio.bus->mdio_lock); + phy_unlock_mdio_bus(phydev); return ret; } @@ -580,9 +580,9 @@ int phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set) { int ret; - mutex_lock(&phydev->mdio.bus->mdio_lock); + phy_lock_mdio_bus(phydev); ret = __phy_modify(phydev, regnum, mask, set); - mutex_unlock(&phydev->mdio.bus->mdio_lock); + phy_unlock_mdio_bus(phydev); return ret; } @@ -639,9 +639,9 @@ int phy_modify_mmd_changed(struct phy_device *phydev, int devad, u32 regnum, { int ret; - mutex_lock(&phydev->mdio.bus->mdio_lock); + phy_lock_mdio_bus(phydev); ret = __phy_modify_mmd_changed(phydev, devad, regnum, mask, set); - mutex_unlock(&phydev->mdio.bus->mdio_lock); + phy_unlock_mdio_bus(phydev); return ret; } @@ -687,9 +687,9 @@ int phy_modify_mmd(struct phy_device *phydev, int devad, u32 regnum, { int ret; - mutex_lock(&phydev->mdio.bus->mdio_lock); + phy_lock_mdio_bus(phydev); ret = __phy_modify_mmd(phydev, devad, regnum, mask, set); - mutex_unlock(&phydev->mdio.bus->mdio_lock); + phy_unlock_mdio_bus(phydev); return ret; } @@ -721,7 +721,7 @@ static int __phy_write_page(struct phy_device *phydev, int page) */ int phy_save_page(struct phy_device *phydev) { - mutex_lock(&phydev->mdio.bus->mdio_lock); + phy_lock_mdio_bus(phydev); return __phy_read_page(phydev); } EXPORT_SYMBOL_GPL(phy_save_page); @@ -788,7 +788,7 @@ int phy_restore_page(struct phy_device *phydev, int oldpage, int ret) ret = oldpage; } - mutex_unlock(&phydev->mdio.bus->mdio_lock); + phy_unlock_mdio_bus(phydev); return ret; } diff --git a/include/linux/phy.h b/include/linux/phy.h index f5cdfb206097..5032d453ac66 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1076,6 +1076,16 @@ static inline const char *phydev_name(const struct phy_device *phydev) return dev_name(&phydev->mdio.dev); } +static inline void phy_lock_mdio_bus(struct phy_device *phydev) +{ + mutex_lock(&phydev->mdio.bus->mdio_lock); +} + +static inline void phy_unlock_mdio_bus(struct phy_device *phydev) +{ + mutex_unlock(&phydev->mdio.bus->mdio_lock); +} + void phy_attached_print(struct phy_device *phydev, const char *fmt, ...) __printf(2, 3); void phy_attached_info(struct phy_device *phydev); -- cgit v1.2.3-71-gd317 From ba30e27405afa0b13b79532a345977b3e58ad501 Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Mon, 25 Nov 2019 14:28:04 -0800 Subject: Revert "percpu: add __percpu to SHIFT_PERCPU_PTR" This reverts commit 825dbc6ff7a3a063ea91be7d94af940080b0c991. I mistakenly applied this and only now have thought about it a little more and had time to evaluate a kbuild error for dmaengine. Once we're calling RELOC_HIDE, we're moving back into the __kernel address space and letting users interact with the actual memory address rather than in __percpu which is before adding the offsets. Signed-off-by: Dennis Zhou --- include/linux/percpu-defs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index a49b6c702598..a6fabd865211 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -229,7 +229,7 @@ do { \ * pointer value. The weird cast keeps both GCC and sparse happy. */ #define SHIFT_PERCPU_PTR(__p, __offset) \ - RELOC_HIDE((typeof(*(__p)) __kernel __percpu __force *)(__p), (__offset)) + RELOC_HIDE((typeof(*(__p)) __kernel __force *)(__p), (__offset)) #define per_cpu_ptr(ptr, cpu) \ ({ \ -- cgit v1.2.3-71-gd317 From bd3ded3146daa2cbb57ed353749ef99cf75371b0 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 23 Nov 2019 14:17:16 -0700 Subject: net: add __sys_connect_file() helper This is identical to __sys_connect(), except it takes a struct file instead of an fd, and it also allows passing in extra file->f_flags flags. The latter is done to support masking in O_NONBLOCK without manipulating the original file flags. No functional changes in this patch. Cc: netdev@vger.kernel.org Acked-by: David S. Miller Signed-off-by: Jens Axboe --- include/linux/socket.h | 3 +++ net/socket.c | 30 ++++++++++++++++++++++-------- 2 files changed, 25 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 09c32a21555b..4bde63021c09 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -399,6 +399,9 @@ extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_socket(int family, int type, int protocol); extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen); +extern int __sys_connect_file(struct file *file, + struct sockaddr __user *uservaddr, int addrlen, + int file_flags); extern int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen); extern int __sys_listen(int fd, int backlog); diff --git a/net/socket.c b/net/socket.c index 17bc1eee198a..274df4ddfc2c 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1825,32 +1825,46 @@ SYSCALL_DEFINE3(accept, int, fd, struct sockaddr __user *, upeer_sockaddr, * include the -EINPROGRESS status for such sockets. */ -int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen) +int __sys_connect_file(struct file *file, struct sockaddr __user *uservaddr, + int addrlen, int file_flags) { struct socket *sock; struct sockaddr_storage address; - int err, fput_needed; + int err; - sock = sockfd_lookup_light(fd, &err, &fput_needed); + sock = sock_from_file(file, &err); if (!sock) goto out; err = move_addr_to_kernel(uservaddr, addrlen, &address); if (err < 0) - goto out_put; + goto out; err = security_socket_connect(sock, (struct sockaddr *)&address, addrlen); if (err) - goto out_put; + goto out; err = sock->ops->connect(sock, (struct sockaddr *)&address, addrlen, - sock->file->f_flags); -out_put: - fput_light(sock->file, fput_needed); + sock->file->f_flags | file_flags); out: return err; } +int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen) +{ + int ret = -EBADF; + struct fd f; + + f = fdget(fd); + if (f.file) { + ret = __sys_connect_file(f.file, uservaddr, addrlen, 0); + if (f.flags) + fput(f.file); + } + + return ret; +} + SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr, int, addrlen) { -- cgit v1.2.3-71-gd317 From 863fbae929c7a5b64e96b8a3ffb34a29eefb9f8f Mon Sep 17 00:00:00 2001 From: James Smart Date: Thu, 14 Nov 2019 15:15:26 -0800 Subject: nvme_fc: add module to ops template to allow module references In nvme-fc: it's possible to have connected active controllers and as no references are taken on the LLDD, the LLDD can be unloaded. The controller would enter a reconnect state and as long as the LLDD resumed within the reconnect timeout, the controller would resume. But if a namespace on the controller is the root device, allowing the driver to unload can be problematic. To reload the driver, it may require new io to the boot device, and as it's no longer connected we get into a catch-22 that eventually fails, and the system locks up. Fix this issue by taking a module reference for every connected controller (which is what the core layer did to the transport module). Reference is cleared when the controller is removed. Acked-by: Himanshu Madhani Reviewed-by: Christoph Hellwig Signed-off-by: James Smart Signed-off-by: Keith Busch --- drivers/nvme/host/fc.c | 14 ++++++++++++-- drivers/nvme/target/fcloop.c | 1 + drivers/scsi/lpfc/lpfc_nvme.c | 2 ++ drivers/scsi/qla2xxx/qla_nvme.c | 1 + include/linux/nvme-fc-driver.h | 4 ++++ 5 files changed, 20 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 13cb00e56cac..d61439f8f5a9 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -342,7 +342,8 @@ nvme_fc_register_localport(struct nvme_fc_port_info *pinfo, !template->ls_req || !template->fcp_io || !template->ls_abort || !template->fcp_abort || !template->max_hw_queues || !template->max_sgl_segments || - !template->max_dif_sgl_segments || !template->dma_boundary) { + !template->max_dif_sgl_segments || !template->dma_boundary || + !template->module) { ret = -EINVAL; goto out_reghost_failed; } @@ -2015,6 +2016,7 @@ nvme_fc_ctrl_free(struct kref *ref) { struct nvme_fc_ctrl *ctrl = container_of(ref, struct nvme_fc_ctrl, ref); + struct nvme_fc_lport *lport = ctrl->lport; unsigned long flags; if (ctrl->ctrl.tagset) { @@ -2041,6 +2043,7 @@ nvme_fc_ctrl_free(struct kref *ref) if (ctrl->ctrl.opts) nvmf_free_options(ctrl->ctrl.opts); kfree(ctrl); + module_put(lport->ops->module); } static void @@ -3059,10 +3062,15 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, goto out_fail; } + if (!try_module_get(lport->ops->module)) { + ret = -EUNATCH; + goto out_free_ctrl; + } + idx = ida_simple_get(&nvme_fc_ctrl_cnt, 0, 0, GFP_KERNEL); if (idx < 0) { ret = -ENOSPC; - goto out_free_ctrl; + goto out_mod_put; } ctrl->ctrl.opts = opts; @@ -3215,6 +3223,8 @@ out_free_queues: out_free_ida: put_device(ctrl->dev); ida_simple_remove(&nvme_fc_ctrl_cnt, ctrl->cnum); +out_mod_put: + module_put(lport->ops->module); out_free_ctrl: kfree(ctrl); out_fail: diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index b50b53db3746..1c50af6219f3 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -850,6 +850,7 @@ fcloop_targetport_delete(struct nvmet_fc_target_port *targetport) #define FCLOOP_DMABOUND_4G 0xFFFFFFFF static struct nvme_fc_port_template fctemplate = { + .module = THIS_MODULE, .localport_delete = fcloop_localport_delete, .remoteport_delete = fcloop_remoteport_delete, .create_queue = fcloop_create_queue, diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index a227e36cbdc2..8e0f03ef346b 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -1976,6 +1976,8 @@ out_unlock: /* Declare and initialization an instance of the FC NVME template. */ static struct nvme_fc_port_template lpfc_nvme_template = { + .module = THIS_MODULE, + /* initiator-based functions */ .localport_delete = lpfc_nvme_localport_delete, .remoteport_delete = lpfc_nvme_remoteport_delete, diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index 6cc19e060afc..6e4d71302534 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -610,6 +610,7 @@ static void qla_nvme_remoteport_delete(struct nvme_fc_remote_port *rport) } static struct nvme_fc_port_template qla_nvme_fc_transport = { + .module = THIS_MODULE, .localport_delete = qla_nvme_localport_delete, .remoteport_delete = qla_nvme_remoteport_delete, .create_queue = qla_nvme_alloc_queue, diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 10f81629b9ce..6d0d70f3219c 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -270,6 +270,8 @@ struct nvme_fc_remote_port { * * Host/Initiator Transport Entrypoints/Parameters: * + * @module: The LLDD module using the interface + * * @localport_delete: The LLDD initiates deletion of a localport via * nvme_fc_deregister_localport(). However, the teardown is * asynchronous. This routine is called upon the completion of the @@ -383,6 +385,8 @@ struct nvme_fc_remote_port { * Value is Mandatory. Allowed to be zero. */ struct nvme_fc_port_template { + struct module *module; + /* initiator-based functions */ void (*localport_delete)(struct nvme_fc_local_port *); void (*remoteport_delete)(struct nvme_fc_remote_port *); -- cgit v1.2.3-71-gd317 From d41b0e64d206f8948212b4d0f30c330db95c9636 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 14 Oct 2019 12:04:52 +0200 Subject: PCI/MSI: Remove unused pci_irq_get_node() The function pci_irq_get_node() is not used by anyone in the tree, so just delete it. Link: https://lore.kernel.org/r/20191014100452.GA6699@kroah.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Bjorn Helgaas Reviewed-by: Andrew Murray --- drivers/pci/msi.c | 16 ---------------- include/linux/pci.h | 6 ------ 2 files changed, 22 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 0884bedcfc7a..f95fe23830f0 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -1315,22 +1315,6 @@ const struct cpumask *pci_irq_get_affinity(struct pci_dev *dev, int nr) } EXPORT_SYMBOL(pci_irq_get_affinity); -/** - * pci_irq_get_node - return the NUMA node of a particular MSI vector - * @pdev: PCI device to operate on - * @vec: device-relative interrupt vector index (0-based). - */ -int pci_irq_get_node(struct pci_dev *pdev, int vec) -{ - const struct cpumask *mask; - - mask = pci_irq_get_affinity(pdev, vec); - if (mask) - return local_memory_node(cpu_to_node(cpumask_first(mask))); - return dev_to_node(&pdev->dev); -} -EXPORT_SYMBOL(pci_irq_get_node); - struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc) { return to_pci_dev(desc->dev); diff --git a/include/linux/pci.h b/include/linux/pci.h index f9088c89a534..755d8c0176b9 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1454,7 +1454,6 @@ int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs, void pci_free_irq_vectors(struct pci_dev *dev); int pci_irq_vector(struct pci_dev *dev, unsigned int nr); const struct cpumask *pci_irq_get_affinity(struct pci_dev *pdev, int vec); -int pci_irq_get_node(struct pci_dev *pdev, int vec); #else static inline int pci_msi_vec_count(struct pci_dev *dev) { return -ENOSYS; } @@ -1497,11 +1496,6 @@ static inline const struct cpumask *pci_irq_get_affinity(struct pci_dev *pdev, { return cpu_possible_mask; } - -static inline int pci_irq_get_node(struct pci_dev *pdev, int vec) -{ - return first_online_node; -} #endif /** -- cgit v1.2.3-71-gd317 From 2be7d348fe924f0c5583c6a805bd42cecda93104 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 26 Nov 2019 11:34:06 -0800 Subject: Revert "vfs: properly and reliably lock f_pos in fdget_pos()" This reverts commit 0be0ee71816b2b6725e2b4f32ad6726c9d729777. I was hoping it would be benign to switch over entirely to FMODE_STREAM, and we'd have just a couple of small fixups we'd need, but it looks like we're not quite there yet. While it worked fine on both my desktop and laptop, they are fairly similar in other respects, and run mostly the same loads. Kenneth Crudup reports that it seems to break both his vmware installation and the KDE upower service. In both cases apparently leading to timeouts due to waitinmg for the f_pos lock. There are a number of character devices in particular that definitely want stream-like behavior, but that currently don't get marked as streams, and as a result get the exclusion between concurrent read()/write() on the same file descriptor. Which doesn't work well for them. The most obvious example if this is /dev/console and /dev/tty, which use console_fops and tty_fops respectively (and ptmx_fops for the pty master side). It may be that it's just this that causes problems, but we clearly weren't ready yet. Because there's a number of other likely common cases that don't have llseek implementations and would seem to act as stream devices: /dev/fuse (fuse_dev_operations) /dev/mcelog (mce_chrdev_ops) /dev/mei0 (mei_fops) /dev/net/tun (tun_fops) /dev/nvme0 (nvme_dev_fops) /dev/tpm0 (tpm_fops) /proc/self/ns/mnt (ns_file_operations) /dev/snd/pcm* (snd_pcm_f_ops[]) and while some of these could be trivially automatically detected by the vfs layer when the character device is opened by just noticing that they have no read or write operations either, it often isn't that obvious. Some character devices most definitely do use the file position, even if they don't allow seeking: the firmware update code, for example, uses simple_read_from_buffer() that does use f_pos, but doesn't allow seeking back and forth. We'll revisit this when there's a better way to detect the problem and fix it (possibly with a coccinelle script to do more of the FMODE_STREAM annotations). Reported-by: Kenneth R. Crudup Cc: Kirill Smelkov Signed-off-by: Linus Torvalds --- fs/file.c | 2 +- fs/open.c | 6 +++++- include/linux/fs.h | 2 ++ 3 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/file.c b/fs/file.c index b241ea7f1aa4..3da91a112bab 100644 --- a/fs/file.c +++ b/fs/file.c @@ -795,7 +795,7 @@ unsigned long __fdget_pos(unsigned int fd) unsigned long v = __fdget(fd); struct file *file = (struct file *)(v & ~3); - if (file && !(file->f_mode & FMODE_STREAM)) { + if (file && (file->f_mode & FMODE_ATOMIC_POS)) { if (file_count(file) > 1) { v |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); diff --git a/fs/open.c b/fs/open.c index 5c68282ea79e..b62f5c0923a8 100644 --- a/fs/open.c +++ b/fs/open.c @@ -771,6 +771,10 @@ static int do_dentry_open(struct file *f, f->f_mode |= FMODE_WRITER; } + /* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */ + if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)) + f->f_mode |= FMODE_ATOMIC_POS; + f->f_op = fops_get(inode->i_fop); if (WARN_ON(!f->f_op)) { error = -ENODEV; @@ -1252,7 +1256,7 @@ EXPORT_SYMBOL(nonseekable_open); */ int stream_open(struct inode *inode, struct file *filp) { - filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE); + filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS); filp->f_mode |= FMODE_STREAM; return 0; } diff --git a/include/linux/fs.h b/include/linux/fs.h index dde6dc4492a0..ae6c5c37f3ae 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -148,6 +148,8 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File is opened with O_PATH; almost nothing can be done with it */ #define FMODE_PATH ((__force fmode_t)0x4000) +/* File needs atomic accesses to f_pos */ +#define FMODE_ATOMIC_POS ((__force fmode_t)0x8000) /* Write access to underlying fs */ #define FMODE_WRITER ((__force fmode_t)0x10000) /* Has read method(s) */ -- cgit v1.2.3-71-gd317 From a8de1304b7df30e3a14f2a8b9709bb4ff31a0385 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 13 Nov 2019 16:12:02 +0900 Subject: libfdt: define INT32_MAX and UINT32_MAX in libfdt_env.h The DTC v1.5.1 added references to (U)INT32_MAX. This is no problem for user-space programs since defines (U)INT32_MAX along with (u)int32_t. For the kernel space, libfdt_env.h needs to be adjusted before we pull in the changes. In the kernel, we usually use s/u32 instead of (u)int32_t for the fixed-width types. Accordingly, we already have S/U32_MAX for their max values. So, we should not add (U)INT32_MAX to any more. Instead, add them to the in-kernel libfdt_env.h to compile the latest libfdt. Signed-off-by: Masahiro Yamada Signed-off-by: Rob Herring --- arch/arm/boot/compressed/libfdt_env.h | 4 +++- arch/powerpc/boot/libfdt_env.h | 2 ++ include/linux/libfdt_env.h | 3 +++ 3 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/arm/boot/compressed/libfdt_env.h b/arch/arm/boot/compressed/libfdt_env.h index b36c0289a308..6a0f1f524466 100644 --- a/arch/arm/boot/compressed/libfdt_env.h +++ b/arch/arm/boot/compressed/libfdt_env.h @@ -2,11 +2,13 @@ #ifndef _ARM_LIBFDT_ENV_H #define _ARM_LIBFDT_ENV_H +#include #include #include #include -#define INT_MAX ((int)(~0U>>1)) +#define INT32_MAX S32_MAX +#define UINT32_MAX U32_MAX typedef __be16 fdt16_t; typedef __be32 fdt32_t; diff --git a/arch/powerpc/boot/libfdt_env.h b/arch/powerpc/boot/libfdt_env.h index 2abc8e83b95e..9757d4f6331e 100644 --- a/arch/powerpc/boot/libfdt_env.h +++ b/arch/powerpc/boot/libfdt_env.h @@ -6,6 +6,8 @@ #include #define INT_MAX ((int)(~0U>>1)) +#define UINT32_MAX ((u32)~0U) +#define INT32_MAX ((s32)(UINT32_MAX >> 1)) #include "of.h" diff --git a/include/linux/libfdt_env.h b/include/linux/libfdt_env.h index 2231eb855e8f..cea8574a29b1 100644 --- a/include/linux/libfdt_env.h +++ b/include/linux/libfdt_env.h @@ -7,6 +7,9 @@ #include +#define INT32_MAX S32_MAX +#define UINT32_MAX U32_MAX + typedef __be16 fdt16_t; typedef __be32 fdt32_t; typedef __be64 fdt64_t; -- cgit v1.2.3-71-gd317 From 82995cc6c5ae4bf4d72edef381a085e52d5b5905 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 25 Mar 2019 16:38:32 +0000 Subject: libceph, rbd, ceph: convert to use the new mount API Convert the ceph filesystem to the new internal mount API as the old one will be obsoleted and removed. This allows greater flexibility in communication of mount parameters between userspace, the VFS and the filesystem. See Documentation/filesystems/mount_api.txt for more information. [ Numerous string handling, leak and regression fixes; rbd conversion was particularly broken and had to be redone almost from scratch. ] Signed-off-by: David Howells Signed-off-by: Jeff Layton Signed-off-by: Ilya Dryomov --- drivers/block/rbd.c | 262 ++++++++++-------- fs/ceph/cache.c | 9 +- fs/ceph/cache.h | 5 +- fs/ceph/super.c | 646 ++++++++++++++++++++++--------------------- fs/ceph/super.h | 1 - include/linux/ceph/libceph.h | 10 +- net/ceph/ceph_common.c | 419 +++++++++++++--------------- net/ceph/messenger.c | 2 - 8 files changed, 681 insertions(+), 673 deletions(-) (limited to 'include/linux') diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 3a40b5f60810..2b184563cd32 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -34,7 +34,7 @@ #include #include #include -#include +#include #include #include @@ -838,34 +838,34 @@ enum { Opt_queue_depth, Opt_alloc_size, Opt_lock_timeout, - Opt_last_int, /* int args above */ Opt_pool_ns, - Opt_last_string, /* string args above */ Opt_read_only, Opt_read_write, Opt_lock_on_read, Opt_exclusive, Opt_notrim, - Opt_err }; -static match_table_t rbd_opts_tokens = { - {Opt_queue_depth, "queue_depth=%d"}, - {Opt_alloc_size, "alloc_size=%d"}, - {Opt_lock_timeout, "lock_timeout=%d"}, - /* int args above */ - {Opt_pool_ns, "_pool_ns=%s"}, - /* string args above */ - {Opt_read_only, "read_only"}, - {Opt_read_only, "ro"}, /* Alternate spelling */ - {Opt_read_write, "read_write"}, - {Opt_read_write, "rw"}, /* Alternate spelling */ - {Opt_lock_on_read, "lock_on_read"}, - {Opt_exclusive, "exclusive"}, - {Opt_notrim, "notrim"}, - {Opt_err, NULL} +static const struct fs_parameter_spec rbd_param_specs[] = { + fsparam_u32 ("alloc_size", Opt_alloc_size), + fsparam_flag ("exclusive", Opt_exclusive), + fsparam_flag ("lock_on_read", Opt_lock_on_read), + fsparam_u32 ("lock_timeout", Opt_lock_timeout), + fsparam_flag ("notrim", Opt_notrim), + fsparam_string ("_pool_ns", Opt_pool_ns), + fsparam_u32 ("queue_depth", Opt_queue_depth), + fsparam_flag ("read_only", Opt_read_only), + fsparam_flag ("read_write", Opt_read_write), + fsparam_flag ("ro", Opt_read_only), + fsparam_flag ("rw", Opt_read_write), + {} +}; + +static const struct fs_parameter_description rbd_parameters = { + .name = "rbd", + .specs = rbd_param_specs, }; struct rbd_options { @@ -886,87 +886,12 @@ struct rbd_options { #define RBD_EXCLUSIVE_DEFAULT false #define RBD_TRIM_DEFAULT true -struct parse_rbd_opts_ctx { +struct rbd_parse_opts_ctx { struct rbd_spec *spec; + struct ceph_options *copts; struct rbd_options *opts; }; -static int parse_rbd_opts_token(char *c, void *private) -{ - struct parse_rbd_opts_ctx *pctx = private; - substring_t argstr[MAX_OPT_ARGS]; - int token, intval, ret; - - token = match_token(c, rbd_opts_tokens, argstr); - if (token < Opt_last_int) { - ret = match_int(&argstr[0], &intval); - if (ret < 0) { - pr_err("bad option arg (not int) at '%s'\n", c); - return ret; - } - dout("got int token %d val %d\n", token, intval); - } else if (token > Opt_last_int && token < Opt_last_string) { - dout("got string token %d val %s\n", token, argstr[0].from); - } else { - dout("got token %d\n", token); - } - - switch (token) { - case Opt_queue_depth: - if (intval < 1) { - pr_err("queue_depth out of range\n"); - return -EINVAL; - } - pctx->opts->queue_depth = intval; - break; - case Opt_alloc_size: - if (intval < SECTOR_SIZE) { - pr_err("alloc_size out of range\n"); - return -EINVAL; - } - if (!is_power_of_2(intval)) { - pr_err("alloc_size must be a power of 2\n"); - return -EINVAL; - } - pctx->opts->alloc_size = intval; - break; - case Opt_lock_timeout: - /* 0 is "wait forever" (i.e. infinite timeout) */ - if (intval < 0 || intval > INT_MAX / 1000) { - pr_err("lock_timeout out of range\n"); - return -EINVAL; - } - pctx->opts->lock_timeout = msecs_to_jiffies(intval * 1000); - break; - case Opt_pool_ns: - kfree(pctx->spec->pool_ns); - pctx->spec->pool_ns = match_strdup(argstr); - if (!pctx->spec->pool_ns) - return -ENOMEM; - break; - case Opt_read_only: - pctx->opts->read_only = true; - break; - case Opt_read_write: - pctx->opts->read_only = false; - break; - case Opt_lock_on_read: - pctx->opts->lock_on_read = true; - break; - case Opt_exclusive: - pctx->opts->exclusive = true; - break; - case Opt_notrim: - pctx->opts->trim = false; - break; - default: - /* libceph prints "bad option" msg */ - return -EINVAL; - } - - return 0; -} - static char* obj_op_name(enum obj_operation_type op_type) { switch (op_type) { @@ -6423,6 +6348,122 @@ static inline char *dup_token(const char **buf, size_t *lenp) return dup; } +static int rbd_parse_param(struct fs_parameter *param, + struct rbd_parse_opts_ctx *pctx) +{ + struct rbd_options *opt = pctx->opts; + struct fs_parse_result result; + int token, ret; + + ret = ceph_parse_param(param, pctx->copts, NULL); + if (ret != -ENOPARAM) + return ret; + + token = fs_parse(NULL, &rbd_parameters, param, &result); + dout("%s fs_parse '%s' token %d\n", __func__, param->key, token); + if (token < 0) { + if (token == -ENOPARAM) { + return invalf(NULL, "rbd: Unknown parameter '%s'", + param->key); + } + return token; + } + + switch (token) { + case Opt_queue_depth: + if (result.uint_32 < 1) + goto out_of_range; + opt->queue_depth = result.uint_32; + break; + case Opt_alloc_size: + if (result.uint_32 < SECTOR_SIZE) + goto out_of_range; + if (!is_power_of_2(result.uint_32)) { + return invalf(NULL, "rbd: alloc_size must be a power of 2"); + } + opt->alloc_size = result.uint_32; + break; + case Opt_lock_timeout: + /* 0 is "wait forever" (i.e. infinite timeout) */ + if (result.uint_32 > INT_MAX / 1000) + goto out_of_range; + opt->lock_timeout = msecs_to_jiffies(result.uint_32 * 1000); + break; + case Opt_pool_ns: + kfree(pctx->spec->pool_ns); + pctx->spec->pool_ns = param->string; + param->string = NULL; + break; + case Opt_read_only: + opt->read_only = true; + break; + case Opt_read_write: + opt->read_only = false; + break; + case Opt_lock_on_read: + opt->lock_on_read = true; + break; + case Opt_exclusive: + opt->exclusive = true; + break; + case Opt_notrim: + opt->trim = false; + break; + default: + BUG(); + } + + return 0; + +out_of_range: + return invalf(NULL, "rbd: %s out of range", param->key); +} + +/* + * This duplicates most of generic_parse_monolithic(), untying it from + * fs_context and skipping standard superblock and security options. + */ +static int rbd_parse_options(char *options, struct rbd_parse_opts_ctx *pctx) +{ + char *key; + int ret = 0; + + dout("%s '%s'\n", __func__, options); + while ((key = strsep(&options, ",")) != NULL) { + if (*key) { + struct fs_parameter param = { + .key = key, + .type = fs_value_is_string, + }; + char *value = strchr(key, '='); + size_t v_len = 0; + + if (value) { + if (value == key) + continue; + *value++ = 0; + v_len = strlen(value); + } + + + if (v_len > 0) { + param.string = kmemdup_nul(value, v_len, + GFP_KERNEL); + if (!param.string) + return -ENOMEM; + } + param.size = v_len; + + ret = rbd_parse_param(¶m, pctx); + kfree(param.string); + if (ret) + break; + } + } + + return ret; +} + /* * Parse the options provided for an "rbd add" (i.e., rbd image * mapping) request. These arrive via a write to /sys/bus/rbd/add, @@ -6474,8 +6515,7 @@ static int rbd_add_parse_args(const char *buf, const char *mon_addrs; char *snap_name; size_t mon_addrs_size; - struct parse_rbd_opts_ctx pctx = { 0 }; - struct ceph_options *copts; + struct rbd_parse_opts_ctx pctx = { 0 }; int ret; /* The first four tokens are required */ @@ -6486,7 +6526,7 @@ static int rbd_add_parse_args(const char *buf, return -EINVAL; } mon_addrs = buf; - mon_addrs_size = len + 1; + mon_addrs_size = len; buf += len; ret = -EINVAL; @@ -6536,6 +6576,10 @@ static int rbd_add_parse_args(const char *buf, *(snap_name + len) = '\0'; pctx.spec->snap_name = snap_name; + pctx.copts = ceph_alloc_options(); + if (!pctx.copts) + goto out_mem; + /* Initialize all rbd options to the defaults */ pctx.opts = kzalloc(sizeof(*pctx.opts), GFP_KERNEL); @@ -6550,27 +6594,27 @@ static int rbd_add_parse_args(const char *buf, pctx.opts->exclusive = RBD_EXCLUSIVE_DEFAULT; pctx.opts->trim = RBD_TRIM_DEFAULT; - copts = ceph_parse_options(options, mon_addrs, - mon_addrs + mon_addrs_size - 1, - parse_rbd_opts_token, &pctx); - if (IS_ERR(copts)) { - ret = PTR_ERR(copts); + ret = ceph_parse_mon_ips(mon_addrs, mon_addrs_size, pctx.copts, NULL); + if (ret) goto out_err; - } - kfree(options); - *ceph_opts = copts; + ret = rbd_parse_options(options, &pctx); + if (ret) + goto out_err; + + *ceph_opts = pctx.copts; *opts = pctx.opts; *rbd_spec = pctx.spec; - + kfree(options); return 0; + out_mem: ret = -ENOMEM; out_err: kfree(pctx.opts); + ceph_destroy_options(pctx.copts); rbd_spec_put(pctx.spec); kfree(options); - return ret; } diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c index b2ec29eeb4c4..73f24f307a4a 100644 --- a/fs/ceph/cache.c +++ b/fs/ceph/cache.c @@ -8,6 +8,7 @@ #include +#include #include "super.h" #include "cache.h" @@ -49,7 +50,7 @@ void ceph_fscache_unregister(void) fscache_unregister_netfs(&ceph_cache_netfs); } -int ceph_fscache_register_fs(struct ceph_fs_client* fsc) +int ceph_fscache_register_fs(struct ceph_fs_client* fsc, struct fs_context *fc) { const struct ceph_fsid *fsid = &fsc->client->fsid; const char *fscache_uniq = fsc->mount_options->fscache_uniq; @@ -66,8 +67,8 @@ int ceph_fscache_register_fs(struct ceph_fs_client* fsc) if (uniq_len && memcmp(ent->uniquifier, fscache_uniq, uniq_len)) continue; - pr_err("fscache cookie already registered for fsid %pU\n", fsid); - pr_err(" use fsc=%%s mount option to specify a uniquifier\n"); + errorf(fc, "ceph: fscache cookie already registered for fsid %pU, use fsc= option", + fsid); err = -EBUSY; goto out_unlock; } @@ -95,7 +96,7 @@ int ceph_fscache_register_fs(struct ceph_fs_client* fsc) list_add_tail(&ent->list, &ceph_fscache_list); } else { kfree(ent); - pr_err("unable to register fscache cookie for fsid %pU\n", + errorf(fc, "ceph: unable to register fscache cookie for fsid %pU", fsid); /* all other fs ignore this error */ } diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h index e486fac3434d..89dbdd1eb14a 100644 --- a/fs/ceph/cache.h +++ b/fs/ceph/cache.h @@ -16,7 +16,7 @@ extern struct fscache_netfs ceph_cache_netfs; int ceph_fscache_register(void); void ceph_fscache_unregister(void); -int ceph_fscache_register_fs(struct ceph_fs_client* fsc); +int ceph_fscache_register_fs(struct ceph_fs_client* fsc, struct fs_context *fc); void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc); void ceph_fscache_register_inode_cookie(struct inode *inode); @@ -88,7 +88,8 @@ static inline void ceph_fscache_unregister(void) { } -static inline int ceph_fscache_register_fs(struct ceph_fs_client* fsc) +static inline int ceph_fscache_register_fs(struct ceph_fs_client* fsc, + struct fs_context *fc) { return 0; } diff --git a/fs/ceph/super.c b/fs/ceph/super.c index b47f43fc2d68..9c9a7c68eea3 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -9,7 +9,8 @@ #include #include #include -#include +#include +#include #include #include #include @@ -138,280 +139,308 @@ enum { Opt_readdir_max_entries, Opt_readdir_max_bytes, Opt_congestion_kb, - Opt_last_int, /* int args above */ Opt_snapdirname, Opt_mds_namespace, - Opt_fscache_uniq, Opt_recover_session, - Opt_last_string, + Opt_source, /* string args above */ Opt_dirstat, - Opt_nodirstat, Opt_rbytes, - Opt_norbytes, Opt_asyncreaddir, - Opt_noasyncreaddir, Opt_dcache, - Opt_nodcache, Opt_ino32, - Opt_noino32, Opt_fscache, - Opt_nofscache, Opt_poolperm, - Opt_nopoolperm, Opt_require_active_mds, - Opt_norequire_active_mds, -#ifdef CONFIG_CEPH_FS_POSIX_ACL Opt_acl, -#endif - Opt_noacl, Opt_quotadf, - Opt_noquotadf, Opt_copyfrom, - Opt_nocopyfrom, }; -static match_table_t fsopt_tokens = { - {Opt_wsize, "wsize=%d"}, - {Opt_rsize, "rsize=%d"}, - {Opt_rasize, "rasize=%d"}, - {Opt_caps_wanted_delay_min, "caps_wanted_delay_min=%d"}, - {Opt_caps_wanted_delay_max, "caps_wanted_delay_max=%d"}, - {Opt_caps_max, "caps_max=%d"}, - {Opt_readdir_max_entries, "readdir_max_entries=%d"}, - {Opt_readdir_max_bytes, "readdir_max_bytes=%d"}, - {Opt_congestion_kb, "write_congestion_kb=%d"}, - /* int args above */ - {Opt_snapdirname, "snapdirname=%s"}, - {Opt_mds_namespace, "mds_namespace=%s"}, - {Opt_recover_session, "recover_session=%s"}, - {Opt_fscache_uniq, "fsc=%s"}, - /* string args above */ - {Opt_dirstat, "dirstat"}, - {Opt_nodirstat, "nodirstat"}, - {Opt_rbytes, "rbytes"}, - {Opt_norbytes, "norbytes"}, - {Opt_asyncreaddir, "asyncreaddir"}, - {Opt_noasyncreaddir, "noasyncreaddir"}, - {Opt_dcache, "dcache"}, - {Opt_nodcache, "nodcache"}, - {Opt_ino32, "ino32"}, - {Opt_noino32, "noino32"}, - {Opt_fscache, "fsc"}, - {Opt_nofscache, "nofsc"}, - {Opt_poolperm, "poolperm"}, - {Opt_nopoolperm, "nopoolperm"}, - {Opt_require_active_mds, "require_active_mds"}, - {Opt_norequire_active_mds, "norequire_active_mds"}, -#ifdef CONFIG_CEPH_FS_POSIX_ACL - {Opt_acl, "acl"}, -#endif - {Opt_noacl, "noacl"}, - {Opt_quotadf, "quotadf"}, - {Opt_noquotadf, "noquotadf"}, - {Opt_copyfrom, "copyfrom"}, - {Opt_nocopyfrom, "nocopyfrom"}, - {-1, NULL} +enum ceph_recover_session_mode { + ceph_recover_session_no, + ceph_recover_session_clean +}; + +static const struct fs_parameter_enum ceph_mount_param_enums[] = { + { Opt_recover_session, "no", ceph_recover_session_no }, + { Opt_recover_session, "clean", ceph_recover_session_clean }, + {} +}; + +static const struct fs_parameter_spec ceph_mount_param_specs[] = { + fsparam_flag_no ("acl", Opt_acl), + fsparam_flag_no ("asyncreaddir", Opt_asyncreaddir), + fsparam_u32 ("caps_max", Opt_caps_max), + fsparam_u32 ("caps_wanted_delay_max", Opt_caps_wanted_delay_max), + fsparam_u32 ("caps_wanted_delay_min", Opt_caps_wanted_delay_min), + fsparam_s32 ("write_congestion_kb", Opt_congestion_kb), + fsparam_flag_no ("copyfrom", Opt_copyfrom), + fsparam_flag_no ("dcache", Opt_dcache), + fsparam_flag_no ("dirstat", Opt_dirstat), + __fsparam (fs_param_is_string, "fsc", Opt_fscache, + fs_param_neg_with_no | fs_param_v_optional), + fsparam_flag_no ("ino32", Opt_ino32), + fsparam_string ("mds_namespace", Opt_mds_namespace), + fsparam_flag_no ("poolperm", Opt_poolperm), + fsparam_flag_no ("quotadf", Opt_quotadf), + fsparam_u32 ("rasize", Opt_rasize), + fsparam_flag_no ("rbytes", Opt_rbytes), + fsparam_s32 ("readdir_max_bytes", Opt_readdir_max_bytes), + fsparam_s32 ("readdir_max_entries", Opt_readdir_max_entries), + fsparam_enum ("recover_session", Opt_recover_session), + fsparam_flag_no ("require_active_mds", Opt_require_active_mds), + fsparam_u32 ("rsize", Opt_rsize), + fsparam_string ("snapdirname", Opt_snapdirname), + fsparam_string ("source", Opt_source), + fsparam_u32 ("wsize", Opt_wsize), + {} +}; + +static const struct fs_parameter_description ceph_mount_parameters = { + .name = "ceph", + .specs = ceph_mount_param_specs, + .enums = ceph_mount_param_enums, }; -static int parse_fsopt_token(char *c, void *private) +struct ceph_parse_opts_ctx { + struct ceph_options *copts; + struct ceph_mount_options *opts; +}; + +/* + * Parse the source parameter. Distinguish the server list from the path. + * Internally we do not include the leading '/' in the path. + * + * The source will look like: + * [,...]:[] + * where + * is [:] + * is optional, but if present must begin with '/' + */ +static int ceph_parse_source(struct fs_parameter *param, struct fs_context *fc) { - struct ceph_mount_options *fsopt = private; - substring_t argstr[MAX_OPT_ARGS]; - int token, intval, ret; + struct ceph_parse_opts_ctx *pctx = fc->fs_private; + struct ceph_mount_options *fsopt = pctx->opts; + char *dev_name = param->string, *dev_name_end; + int ret; - token = match_token((char *)c, fsopt_tokens, argstr); - if (token < 0) - return -EINVAL; + dout("%s '%s'\n", __func__, dev_name); + if (!dev_name || !*dev_name) + return invalf(fc, "ceph: Empty source"); - if (token < Opt_last_int) { - ret = match_int(&argstr[0], &intval); - if (ret < 0) { - pr_err("bad option arg (not int) at '%s'\n", c); - return ret; + dev_name_end = strchr(dev_name, '/'); + if (dev_name_end) { + if (strlen(dev_name_end) > 1) { + kfree(fsopt->server_path); + fsopt->server_path = kstrdup(dev_name_end, GFP_KERNEL); + if (!fsopt->server_path) + return -ENOMEM; } - dout("got int token %d val %d\n", token, intval); - } else if (token > Opt_last_int && token < Opt_last_string) { - dout("got string token %d val %s\n", token, - argstr[0].from); } else { - dout("got token %d\n", token); + dev_name_end = dev_name + strlen(dev_name); } + dev_name_end--; /* back up to ':' separator */ + if (dev_name_end < dev_name || *dev_name_end != ':') + return invalf(fc, "ceph: No path or : separator in source"); + + dout("device name '%.*s'\n", (int)(dev_name_end - dev_name), dev_name); + if (fsopt->server_path) + dout("server path '%s'\n", fsopt->server_path); + + ret = ceph_parse_mon_ips(param->string, dev_name_end - dev_name, + pctx->copts, fc); + if (ret) + return ret; + + fc->source = param->string; + param->string = NULL; + return 0; +} + +static int ceph_parse_mount_param(struct fs_context *fc, + struct fs_parameter *param) +{ + struct ceph_parse_opts_ctx *pctx = fc->fs_private; + struct ceph_mount_options *fsopt = pctx->opts; + struct fs_parse_result result; + unsigned int mode; + int token, ret; + + ret = ceph_parse_param(param, pctx->copts, fc); + if (ret != -ENOPARAM) + return ret; + + token = fs_parse(fc, &ceph_mount_parameters, param, &result); + dout("%s fs_parse '%s' token %d\n", __func__, param->key, token); + if (token < 0) + return token; + switch (token) { case Opt_snapdirname: kfree(fsopt->snapdir_name); - fsopt->snapdir_name = kstrndup(argstr[0].from, - argstr[0].to-argstr[0].from, - GFP_KERNEL); - if (!fsopt->snapdir_name) - return -ENOMEM; + fsopt->snapdir_name = param->string; + param->string = NULL; break; case Opt_mds_namespace: kfree(fsopt->mds_namespace); - fsopt->mds_namespace = kstrndup(argstr[0].from, - argstr[0].to-argstr[0].from, - GFP_KERNEL); - if (!fsopt->mds_namespace) - return -ENOMEM; + fsopt->mds_namespace = param->string; + param->string = NULL; break; case Opt_recover_session: - if (!strncmp(argstr[0].from, "no", - argstr[0].to - argstr[0].from)) { + mode = result.uint_32; + if (mode == ceph_recover_session_no) fsopt->flags &= ~CEPH_MOUNT_OPT_CLEANRECOVER; - } else if (!strncmp(argstr[0].from, "clean", - argstr[0].to - argstr[0].from)) { + else if (mode == ceph_recover_session_clean) fsopt->flags |= CEPH_MOUNT_OPT_CLEANRECOVER; - } else { - return -EINVAL; - } - break; - case Opt_fscache_uniq: -#ifdef CONFIG_CEPH_FSCACHE - kfree(fsopt->fscache_uniq); - fsopt->fscache_uniq = kstrndup(argstr[0].from, - argstr[0].to-argstr[0].from, - GFP_KERNEL); - if (!fsopt->fscache_uniq) - return -ENOMEM; - fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE; + else + BUG(); break; -#else - pr_err("fscache support is disabled\n"); - return -EINVAL; -#endif + case Opt_source: + if (fc->source) + return invalf(fc, "ceph: Multiple sources specified"); + return ceph_parse_source(param, fc); case Opt_wsize: - if (intval < (int)PAGE_SIZE || intval > CEPH_MAX_WRITE_SIZE) - return -EINVAL; - fsopt->wsize = ALIGN(intval, PAGE_SIZE); + if (result.uint_32 < PAGE_SIZE || + result.uint_32 > CEPH_MAX_WRITE_SIZE) + goto out_of_range; + fsopt->wsize = ALIGN(result.uint_32, PAGE_SIZE); break; case Opt_rsize: - if (intval < (int)PAGE_SIZE || intval > CEPH_MAX_READ_SIZE) - return -EINVAL; - fsopt->rsize = ALIGN(intval, PAGE_SIZE); + if (result.uint_32 < PAGE_SIZE || + result.uint_32 > CEPH_MAX_READ_SIZE) + goto out_of_range; + fsopt->rsize = ALIGN(result.uint_32, PAGE_SIZE); break; case Opt_rasize: - if (intval < 0) - return -EINVAL; - fsopt->rasize = ALIGN(intval, PAGE_SIZE); + fsopt->rasize = ALIGN(result.uint_32, PAGE_SIZE); break; case Opt_caps_wanted_delay_min: - if (intval < 1) - return -EINVAL; - fsopt->caps_wanted_delay_min = intval; + if (result.uint_32 < 1) + goto out_of_range; + fsopt->caps_wanted_delay_min = result.uint_32; break; case Opt_caps_wanted_delay_max: - if (intval < 1) - return -EINVAL; - fsopt->caps_wanted_delay_max = intval; + if (result.uint_32 < 1) + goto out_of_range; + fsopt->caps_wanted_delay_max = result.uint_32; break; case Opt_caps_max: - if (intval < 0) - return -EINVAL; - fsopt->caps_max = intval; + fsopt->caps_max = result.uint_32; break; case Opt_readdir_max_entries: - if (intval < 1) - return -EINVAL; - fsopt->max_readdir = intval; + if (result.uint_32 < 1) + goto out_of_range; + fsopt->max_readdir = result.uint_32; break; case Opt_readdir_max_bytes: - if (intval < (int)PAGE_SIZE && intval != 0) - return -EINVAL; - fsopt->max_readdir_bytes = intval; + if (result.uint_32 < PAGE_SIZE && result.uint_32 != 0) + goto out_of_range; + fsopt->max_readdir_bytes = result.uint_32; break; case Opt_congestion_kb: - if (intval < 1024) /* at least 1M */ - return -EINVAL; - fsopt->congestion_kb = intval; + if (result.uint_32 < 1024) /* at least 1M */ + goto out_of_range; + fsopt->congestion_kb = result.uint_32; break; case Opt_dirstat: - fsopt->flags |= CEPH_MOUNT_OPT_DIRSTAT; - break; - case Opt_nodirstat: - fsopt->flags &= ~CEPH_MOUNT_OPT_DIRSTAT; + if (!result.negated) + fsopt->flags |= CEPH_MOUNT_OPT_DIRSTAT; + else + fsopt->flags &= ~CEPH_MOUNT_OPT_DIRSTAT; break; case Opt_rbytes: - fsopt->flags |= CEPH_MOUNT_OPT_RBYTES; - break; - case Opt_norbytes: - fsopt->flags &= ~CEPH_MOUNT_OPT_RBYTES; + if (!result.negated) + fsopt->flags |= CEPH_MOUNT_OPT_RBYTES; + else + fsopt->flags &= ~CEPH_MOUNT_OPT_RBYTES; break; case Opt_asyncreaddir: - fsopt->flags &= ~CEPH_MOUNT_OPT_NOASYNCREADDIR; - break; - case Opt_noasyncreaddir: - fsopt->flags |= CEPH_MOUNT_OPT_NOASYNCREADDIR; + if (!result.negated) + fsopt->flags &= ~CEPH_MOUNT_OPT_NOASYNCREADDIR; + else + fsopt->flags |= CEPH_MOUNT_OPT_NOASYNCREADDIR; break; case Opt_dcache: - fsopt->flags |= CEPH_MOUNT_OPT_DCACHE; - break; - case Opt_nodcache: - fsopt->flags &= ~CEPH_MOUNT_OPT_DCACHE; + if (!result.negated) + fsopt->flags |= CEPH_MOUNT_OPT_DCACHE; + else + fsopt->flags &= ~CEPH_MOUNT_OPT_DCACHE; break; case Opt_ino32: - fsopt->flags |= CEPH_MOUNT_OPT_INO32; - break; - case Opt_noino32: - fsopt->flags &= ~CEPH_MOUNT_OPT_INO32; + if (!result.negated) + fsopt->flags |= CEPH_MOUNT_OPT_INO32; + else + fsopt->flags &= ~CEPH_MOUNT_OPT_INO32; break; + case Opt_fscache: #ifdef CONFIG_CEPH_FSCACHE - fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE; kfree(fsopt->fscache_uniq); fsopt->fscache_uniq = NULL; + if (result.negated) { + fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE; + } else { + fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE; + fsopt->fscache_uniq = param->string; + param->string = NULL; + } break; #else - pr_err("fscache support is disabled\n"); - return -EINVAL; + return invalf(fc, "ceph: fscache support is disabled"); #endif - case Opt_nofscache: - fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE; - kfree(fsopt->fscache_uniq); - fsopt->fscache_uniq = NULL; - break; case Opt_poolperm: - fsopt->flags &= ~CEPH_MOUNT_OPT_NOPOOLPERM; - break; - case Opt_nopoolperm: - fsopt->flags |= CEPH_MOUNT_OPT_NOPOOLPERM; + if (!result.negated) + fsopt->flags &= ~CEPH_MOUNT_OPT_NOPOOLPERM; + else + fsopt->flags |= CEPH_MOUNT_OPT_NOPOOLPERM; break; case Opt_require_active_mds: - fsopt->flags &= ~CEPH_MOUNT_OPT_MOUNTWAIT; - break; - case Opt_norequire_active_mds: - fsopt->flags |= CEPH_MOUNT_OPT_MOUNTWAIT; + if (!result.negated) + fsopt->flags &= ~CEPH_MOUNT_OPT_MOUNTWAIT; + else + fsopt->flags |= CEPH_MOUNT_OPT_MOUNTWAIT; break; case Opt_quotadf: - fsopt->flags &= ~CEPH_MOUNT_OPT_NOQUOTADF; - break; - case Opt_noquotadf: - fsopt->flags |= CEPH_MOUNT_OPT_NOQUOTADF; + if (!result.negated) + fsopt->flags &= ~CEPH_MOUNT_OPT_NOQUOTADF; + else + fsopt->flags |= CEPH_MOUNT_OPT_NOQUOTADF; break; case Opt_copyfrom: - fsopt->flags &= ~CEPH_MOUNT_OPT_NOCOPYFROM; - break; - case Opt_nocopyfrom: - fsopt->flags |= CEPH_MOUNT_OPT_NOCOPYFROM; + if (!result.negated) + fsopt->flags &= ~CEPH_MOUNT_OPT_NOCOPYFROM; + else + fsopt->flags |= CEPH_MOUNT_OPT_NOCOPYFROM; break; -#ifdef CONFIG_CEPH_FS_POSIX_ACL case Opt_acl: - fsopt->sb_flags |= SB_POSIXACL; - break; + if (!result.negated) { +#ifdef CONFIG_CEPH_FS_POSIX_ACL + fc->sb_flags |= SB_POSIXACL; +#else + return invalf(fc, "ceph: POSIX ACL support is disabled"); #endif - case Opt_noacl: - fsopt->sb_flags &= ~SB_POSIXACL; + } else { + fc->sb_flags &= ~SB_POSIXACL; + } break; default: - BUG_ON(token); + BUG(); } return 0; + +out_of_range: + return invalf(fc, "ceph: %s out of range", param->key); } static void destroy_mount_options(struct ceph_mount_options *args) { dout("destroy_mount_options %p\n", args); + if (!args) + return; + kfree(args->snapdir_name); kfree(args->mds_namespace); kfree(args->server_path); @@ -459,91 +488,6 @@ static int compare_mount_options(struct ceph_mount_options *new_fsopt, return ceph_compare_options(new_opt, fsc->client); } -static int parse_mount_options(struct ceph_mount_options **pfsopt, - struct ceph_options **popt, - int flags, char *options, - const char *dev_name) -{ - struct ceph_mount_options *fsopt; - const char *dev_name_end; - int err; - - if (!dev_name || !*dev_name) - return -EINVAL; - - fsopt = kzalloc(sizeof(*fsopt), GFP_KERNEL); - if (!fsopt) - return -ENOMEM; - - dout("parse_mount_options %p, dev_name '%s'\n", fsopt, dev_name); - - fsopt->sb_flags = flags; - fsopt->flags = CEPH_MOUNT_OPT_DEFAULT; - - fsopt->wsize = CEPH_MAX_WRITE_SIZE; - fsopt->rsize = CEPH_MAX_READ_SIZE; - fsopt->rasize = CEPH_RASIZE_DEFAULT; - fsopt->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL); - if (!fsopt->snapdir_name) { - err = -ENOMEM; - goto out; - } - - fsopt->caps_wanted_delay_min = CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT; - fsopt->caps_wanted_delay_max = CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT; - fsopt->max_readdir = CEPH_MAX_READDIR_DEFAULT; - fsopt->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT; - fsopt->congestion_kb = default_congestion_kb(); - - /* - * Distinguish the server list from the path in "dev_name". - * Internally we do not include the leading '/' in the path. - * - * "dev_name" will look like: - * [,...]:[] - * where - * is [:] - * is optional, but if present must begin with '/' - */ - dev_name_end = strchr(dev_name, '/'); - if (dev_name_end) { - if (strlen(dev_name_end) > 1) { - fsopt->server_path = kstrdup(dev_name_end, GFP_KERNEL); - if (!fsopt->server_path) { - err = -ENOMEM; - goto out; - } - } - } else { - dev_name_end = dev_name + strlen(dev_name); - } - err = -EINVAL; - dev_name_end--; /* back up to ':' separator */ - if (dev_name_end < dev_name || *dev_name_end != ':') { - pr_err("device name is missing path (no : separator in %s)\n", - dev_name); - goto out; - } - dout("device name '%.*s'\n", (int)(dev_name_end - dev_name), dev_name); - if (fsopt->server_path) - dout("server path '%s'\n", fsopt->server_path); - - *popt = ceph_parse_options(options, dev_name, dev_name_end, - parse_fsopt_token, (void *)fsopt); - if (IS_ERR(*popt)) { - err = PTR_ERR(*popt); - goto out; - } - - /* success */ - *pfsopt = fsopt; - return 0; - -out: - destroy_mount_options(fsopt); - return err; -} - /** * ceph_show_options - Show mount options in /proc/mounts * @m: seq_file to write to @@ -587,7 +531,7 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root) seq_puts(m, ",noquotadf"); #ifdef CONFIG_CEPH_FS_POSIX_ACL - if (fsopt->sb_flags & SB_POSIXACL) + if (root->d_sb->s_flags & SB_POSIXACL) seq_puts(m, ",acl"); else seq_puts(m, ",noacl"); @@ -860,12 +804,6 @@ static void ceph_umount_begin(struct super_block *sb) fsc->filp_gen++; // invalidate open files } -static int ceph_remount(struct super_block *sb, int *flags, char *data) -{ - sync_filesystem(sb); - return 0; -} - static const struct super_operations ceph_super_ops = { .alloc_inode = ceph_alloc_inode, .free_inode = ceph_free_inode, @@ -874,7 +812,6 @@ static const struct super_operations ceph_super_ops = { .evict_inode = ceph_evict_inode, .sync_fs = ceph_sync_fs, .put_super = ceph_put_super, - .remount_fs = ceph_remount, .show_options = ceph_show_options, .statfs = ceph_statfs, .umount_begin = ceph_umount_begin, @@ -935,7 +872,8 @@ out: /* * mount: join the ceph cluster, and open root directory. */ -static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc) +static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc, + struct fs_context *fc) { int err; unsigned long started = jiffies; /* note the start time */ @@ -952,7 +890,7 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc) /* setup fscache */ if (fsc->mount_options->flags & CEPH_MOUNT_OPT_FSCACHE) { - err = ceph_fscache_register_fs(fsc); + err = ceph_fscache_register_fs(fsc, fc); if (err < 0) goto out; } @@ -987,18 +925,16 @@ out: return ERR_PTR(err); } -static int ceph_set_super(struct super_block *s, void *data) +static int ceph_set_super(struct super_block *s, struct fs_context *fc) { - struct ceph_fs_client *fsc = data; + struct ceph_fs_client *fsc = s->s_fs_info; int ret; - dout("set_super %p data %p\n", s, data); + dout("set_super %p\n", s); - s->s_flags = fsc->mount_options->sb_flags; s->s_maxbytes = MAX_LFS_FILESIZE; s->s_xattr = ceph_xattr_handlers; - s->s_fs_info = fsc; fsc->sb = s; fsc->max_file_size = 1ULL << 40; /* temp value until we get mdsmap */ @@ -1010,24 +946,18 @@ static int ceph_set_super(struct super_block *s, void *data) s->s_time_min = 0; s->s_time_max = U32_MAX; - ret = set_anon_super(s, NULL); /* what is that second arg for? */ + ret = set_anon_super_fc(s, fc); if (ret != 0) - goto fail; - - return ret; - -fail: - s->s_fs_info = NULL; - fsc->sb = NULL; + fsc->sb = NULL; return ret; } /* * share superblock if same fs AND options */ -static int ceph_compare_super(struct super_block *sb, void *data) +static int ceph_compare_super(struct super_block *sb, struct fs_context *fc) { - struct ceph_fs_client *new = data; + struct ceph_fs_client *new = fc->s_fs_info; struct ceph_mount_options *fsopt = new->mount_options; struct ceph_options *opt = new->client->options; struct ceph_fs_client *other = ceph_sb_to_client(sb); @@ -1043,7 +973,7 @@ static int ceph_compare_super(struct super_block *sb, void *data) dout("fsid doesn't match\n"); return 0; } - if (fsopt->sb_flags != other->mount_options->sb_flags) { + if (fc->sb_flags != (sb->s_flags & ~SB_BORN)) { dout("flags differ\n"); return 0; } @@ -1073,46 +1003,46 @@ static int ceph_setup_bdi(struct super_block *sb, struct ceph_fs_client *fsc) return 0; } -static struct dentry *ceph_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data) +static int ceph_get_tree(struct fs_context *fc) { + struct ceph_parse_opts_ctx *pctx = fc->fs_private; struct super_block *sb; struct ceph_fs_client *fsc; struct dentry *res; + int (*compare_super)(struct super_block *, struct fs_context *) = + ceph_compare_super; int err; - int (*compare_super)(struct super_block *, void *) = ceph_compare_super; - struct ceph_mount_options *fsopt = NULL; - struct ceph_options *opt = NULL; - dout("ceph_mount\n"); + dout("ceph_get_tree\n"); + + if (!fc->source) + return invalf(fc, "ceph: No source"); #ifdef CONFIG_CEPH_FS_POSIX_ACL - flags |= SB_POSIXACL; + fc->sb_flags |= SB_POSIXACL; #endif - err = parse_mount_options(&fsopt, &opt, flags, data, dev_name); - if (err < 0) { - res = ERR_PTR(err); - goto out_final; - } /* create client (which we may/may not use) */ - fsc = create_fs_client(fsopt, opt); + fsc = create_fs_client(pctx->opts, pctx->copts); + pctx->opts = NULL; + pctx->copts = NULL; if (IS_ERR(fsc)) { - res = ERR_CAST(fsc); + err = PTR_ERR(fsc); goto out_final; } err = ceph_mdsc_init(fsc); - if (err < 0) { - res = ERR_PTR(err); + if (err < 0) goto out; - } if (ceph_test_opt(fsc->client, NOSHARE)) compare_super = NULL; - sb = sget(fs_type, compare_super, ceph_set_super, flags, fsc); + + fc->s_fs_info = fsc; + sb = sget_fc(fc, compare_super, ceph_set_super); + fc->s_fs_info = NULL; if (IS_ERR(sb)) { - res = ERR_CAST(sb); + err = PTR_ERR(sb); goto out; } @@ -1123,18 +1053,19 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type, } else { dout("get_sb using new client %p\n", fsc); err = ceph_setup_bdi(sb, fsc); - if (err < 0) { - res = ERR_PTR(err); + if (err < 0) goto out_splat; - } } - res = ceph_real_mount(fsc); - if (IS_ERR(res)) + res = ceph_real_mount(fsc, fc); + if (IS_ERR(res)) { + err = PTR_ERR(res); goto out_splat; + } dout("root %p inode %p ino %llx.%llx\n", res, d_inode(res), ceph_vinop(d_inode(res))); - return res; + fc->root = fsc->sb->s_root; + return 0; out_splat: ceph_mdsc_close_sessions(fsc->mdsc); @@ -1144,8 +1075,79 @@ out_splat: out: destroy_fs_client(fsc); out_final: - dout("ceph_mount fail %ld\n", PTR_ERR(res)); - return res; + dout("ceph_get_tree fail %d\n", err); + return err; +} + +static void ceph_free_fc(struct fs_context *fc) +{ + struct ceph_parse_opts_ctx *pctx = fc->fs_private; + + if (pctx) { + destroy_mount_options(pctx->opts); + ceph_destroy_options(pctx->copts); + kfree(pctx); + } +} + +static int ceph_reconfigure_fc(struct fs_context *fc) +{ + sync_filesystem(fc->root->d_sb); + return 0; +} + +static const struct fs_context_operations ceph_context_ops = { + .free = ceph_free_fc, + .parse_param = ceph_parse_mount_param, + .get_tree = ceph_get_tree, + .reconfigure = ceph_reconfigure_fc, +}; + +/* + * Set up the filesystem mount context. + */ +static int ceph_init_fs_context(struct fs_context *fc) +{ + struct ceph_parse_opts_ctx *pctx; + struct ceph_mount_options *fsopt; + + pctx = kzalloc(sizeof(*pctx), GFP_KERNEL); + if (!pctx) + return -ENOMEM; + + pctx->copts = ceph_alloc_options(); + if (!pctx->copts) + goto nomem; + + pctx->opts = kzalloc(sizeof(*pctx->opts), GFP_KERNEL); + if (!pctx->opts) + goto nomem; + + fsopt = pctx->opts; + fsopt->flags = CEPH_MOUNT_OPT_DEFAULT; + + fsopt->wsize = CEPH_MAX_WRITE_SIZE; + fsopt->rsize = CEPH_MAX_READ_SIZE; + fsopt->rasize = CEPH_RASIZE_DEFAULT; + fsopt->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL); + if (!fsopt->snapdir_name) + goto nomem; + + fsopt->caps_wanted_delay_min = CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT; + fsopt->caps_wanted_delay_max = CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT; + fsopt->max_readdir = CEPH_MAX_READDIR_DEFAULT; + fsopt->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT; + fsopt->congestion_kb = default_congestion_kb(); + + fc->fs_private = pctx; + fc->ops = &ceph_context_ops; + return 0; + +nomem: + destroy_mount_options(pctx->opts); + ceph_destroy_options(pctx->copts); + kfree(pctx); + return -ENOMEM; } static void ceph_kill_sb(struct super_block *s) @@ -1172,7 +1174,7 @@ static void ceph_kill_sb(struct super_block *s) static struct file_system_type ceph_fs_type = { .owner = THIS_MODULE, .name = "ceph", - .mount = ceph_mount, + .init_fs_context = ceph_init_fs_context, .kill_sb = ceph_kill_sb, .fs_flags = FS_RENAME_DOES_D_MOVE, }; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index e31c0177fcc6..f0f9cb7447ac 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -74,7 +74,6 @@ struct ceph_mount_options { int flags; - int sb_flags; int wsize; /* max write size */ int rsize; /* max read size */ diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index b9dbda1c26aa..8fe9b80e80a5 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -280,10 +280,12 @@ extern const char *ceph_msg_type_name(int type); extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid); extern void *ceph_kvmalloc(size_t size, gfp_t flags); -extern struct ceph_options *ceph_parse_options(char *options, - const char *dev_name, const char *dev_name_end, - int (*parse_extra_token)(char *c, void *private), - void *private); +struct fs_parameter; +struct ceph_options *ceph_alloc_options(void); +int ceph_parse_mon_ips(const char *buf, size_t len, struct ceph_options *opt, + struct fs_context *fc); +int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt, + struct fs_context *fc); int ceph_print_client_options(struct seq_file *m, struct ceph_client *client, bool show_all); extern void ceph_destroy_options(struct ceph_options *opt); diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 2d568246803f..a9d6c97b5b0d 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -11,7 +11,7 @@ #include #include #include -#include +#include #include #include #include @@ -254,58 +254,77 @@ enum { Opt_mount_timeout, Opt_osd_idle_ttl, Opt_osd_request_timeout, - Opt_last_int, /* int args above */ Opt_fsid, Opt_name, Opt_secret, Opt_key, Opt_ip, - Opt_last_string, /* string args above */ Opt_share, - Opt_noshare, Opt_crc, - Opt_nocrc, Opt_cephx_require_signatures, - Opt_nocephx_require_signatures, Opt_cephx_sign_messages, - Opt_nocephx_sign_messages, Opt_tcp_nodelay, - Opt_notcp_nodelay, Opt_abort_on_full, }; -static match_table_t opt_tokens = { - {Opt_osdtimeout, "osdtimeout=%d"}, - {Opt_osdkeepalivetimeout, "osdkeepalive=%d"}, - {Opt_mount_timeout, "mount_timeout=%d"}, - {Opt_osd_idle_ttl, "osd_idle_ttl=%d"}, - {Opt_osd_request_timeout, "osd_request_timeout=%d"}, - /* int args above */ - {Opt_fsid, "fsid=%s"}, - {Opt_name, "name=%s"}, - {Opt_secret, "secret=%s"}, - {Opt_key, "key=%s"}, - {Opt_ip, "ip=%s"}, - /* string args above */ - {Opt_share, "share"}, - {Opt_noshare, "noshare"}, - {Opt_crc, "crc"}, - {Opt_nocrc, "nocrc"}, - {Opt_cephx_require_signatures, "cephx_require_signatures"}, - {Opt_nocephx_require_signatures, "nocephx_require_signatures"}, - {Opt_cephx_sign_messages, "cephx_sign_messages"}, - {Opt_nocephx_sign_messages, "nocephx_sign_messages"}, - {Opt_tcp_nodelay, "tcp_nodelay"}, - {Opt_notcp_nodelay, "notcp_nodelay"}, - {Opt_abort_on_full, "abort_on_full"}, - {-1, NULL} +static const struct fs_parameter_spec ceph_param_specs[] = { + fsparam_flag ("abort_on_full", Opt_abort_on_full), + fsparam_flag_no ("cephx_require_signatures", Opt_cephx_require_signatures), + fsparam_flag_no ("cephx_sign_messages", Opt_cephx_sign_messages), + fsparam_flag_no ("crc", Opt_crc), + fsparam_string ("fsid", Opt_fsid), + fsparam_string ("ip", Opt_ip), + fsparam_string ("key", Opt_key), + fsparam_u32 ("mount_timeout", Opt_mount_timeout), + fsparam_string ("name", Opt_name), + fsparam_u32 ("osd_idle_ttl", Opt_osd_idle_ttl), + fsparam_u32 ("osd_request_timeout", Opt_osd_request_timeout), + fsparam_u32 ("osdkeepalive", Opt_osdkeepalivetimeout), + __fsparam (fs_param_is_s32, "osdtimeout", Opt_osdtimeout, + fs_param_deprecated), + fsparam_string ("secret", Opt_secret), + fsparam_flag_no ("share", Opt_share), + fsparam_flag_no ("tcp_nodelay", Opt_tcp_nodelay), + {} +}; + +static const struct fs_parameter_description ceph_parameters = { + .name = "libceph", + .specs = ceph_param_specs, }; +struct ceph_options *ceph_alloc_options(void) +{ + struct ceph_options *opt; + + opt = kzalloc(sizeof(*opt), GFP_KERNEL); + if (!opt) + return NULL; + + opt->mon_addr = kcalloc(CEPH_MAX_MON, sizeof(*opt->mon_addr), + GFP_KERNEL); + if (!opt->mon_addr) { + kfree(opt); + return NULL; + } + + opt->flags = CEPH_OPT_DEFAULT; + opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT; + opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; + opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT; + opt->osd_request_timeout = CEPH_OSD_REQUEST_TIMEOUT_DEFAULT; + return opt; +} +EXPORT_SYMBOL(ceph_alloc_options); + void ceph_destroy_options(struct ceph_options *opt) { dout("destroy_options %p\n", opt); + if (!opt) + return; + kfree(opt->name); if (opt->key) { ceph_crypto_key_destroy(opt->key); @@ -317,7 +336,9 @@ void ceph_destroy_options(struct ceph_options *opt) EXPORT_SYMBOL(ceph_destroy_options); /* get secret from key store */ -static int get_secret(struct ceph_crypto_key *dst, const char *name) { +static int get_secret(struct ceph_crypto_key *dst, const char *name, + struct fs_context *fc) +{ struct key *ukey; int key_err; int err = 0; @@ -330,20 +351,20 @@ static int get_secret(struct ceph_crypto_key *dst, const char *name) { key_err = PTR_ERR(ukey); switch (key_err) { case -ENOKEY: - pr_warn("ceph: Mount failed due to key not found: %s\n", - name); + errorf(fc, "libceph: Failed due to key not found: %s", + name); break; case -EKEYEXPIRED: - pr_warn("ceph: Mount failed due to expired key: %s\n", - name); + errorf(fc, "libceph: Failed due to expired key: %s", + name); break; case -EKEYREVOKED: - pr_warn("ceph: Mount failed due to revoked key: %s\n", - name); + errorf(fc, "libceph: Failed due to revoked key: %s", + name); break; default: - pr_warn("ceph: Mount failed due to unknown key error %d: %s\n", - key_err, name); + errorf(fc, "libceph: Failed due to key error %d: %s", + key_err, name); } err = -EPERM; goto out; @@ -361,217 +382,157 @@ out: return err; } -struct ceph_options * -ceph_parse_options(char *options, const char *dev_name, - const char *dev_name_end, - int (*parse_extra_token)(char *c, void *private), - void *private) +int ceph_parse_mon_ips(const char *buf, size_t len, struct ceph_options *opt, + struct fs_context *fc) { - struct ceph_options *opt; - const char *c; - int err = -ENOMEM; - substring_t argstr[MAX_OPT_ARGS]; - - opt = kzalloc(sizeof(*opt), GFP_KERNEL); - if (!opt) - return ERR_PTR(-ENOMEM); - opt->mon_addr = kcalloc(CEPH_MAX_MON, sizeof(*opt->mon_addr), - GFP_KERNEL); - if (!opt->mon_addr) - goto out; - - dout("parse_options %p options '%s' dev_name '%s'\n", opt, options, - dev_name); - - /* start with defaults */ - opt->flags = CEPH_OPT_DEFAULT; - opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT; - opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; - opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT; - opt->osd_request_timeout = CEPH_OSD_REQUEST_TIMEOUT_DEFAULT; + int ret; - /* get mon ip(s) */ /* ip1[:port1][,ip2[:port2]...] */ - err = ceph_parse_ips(dev_name, dev_name_end, opt->mon_addr, - CEPH_MAX_MON, &opt->num_mon); - if (err < 0) - goto out; + ret = ceph_parse_ips(buf, buf + len, opt->mon_addr, CEPH_MAX_MON, + &opt->num_mon); + if (ret) { + errorf(fc, "libceph: Failed to parse monitor IPs: %d", ret); + return ret; + } - /* parse mount options */ - while ((c = strsep(&options, ",")) != NULL) { - int token, intval; - if (!*c) - continue; - err = -EINVAL; - token = match_token((char *)c, opt_tokens, argstr); - if (token < 0 && parse_extra_token) { - /* extra? */ - err = parse_extra_token((char *)c, private); - if (err < 0) { - pr_err("bad option at '%s'\n", c); - goto out; - } - continue; - } - if (token < Opt_last_int) { - err = match_int(&argstr[0], &intval); - if (err < 0) { - pr_err("bad option arg (not int) at '%s'\n", c); - goto out; - } - dout("got int token %d val %d\n", token, intval); - } else if (token > Opt_last_int && token < Opt_last_string) { - dout("got string token %d val %s\n", token, - argstr[0].from); - } else { - dout("got token %d\n", token); + return 0; +} +EXPORT_SYMBOL(ceph_parse_mon_ips); + +int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt, + struct fs_context *fc) +{ + struct fs_parse_result result; + int token, err; + + token = fs_parse(fc, &ceph_parameters, param, &result); + dout("%s fs_parse '%s' token %d\n", __func__, param->key, token); + if (token < 0) + return token; + + switch (token) { + case Opt_ip: + err = ceph_parse_ips(param->string, + param->string + param->size, + &opt->my_addr, + 1, NULL); + if (err) { + errorf(fc, "libceph: Failed to parse ip: %d", err); + return err; } - switch (token) { - case Opt_ip: - err = ceph_parse_ips(argstr[0].from, - argstr[0].to, - &opt->my_addr, - 1, NULL); - if (err < 0) - goto out; - opt->flags |= CEPH_OPT_MYIP; - break; + opt->flags |= CEPH_OPT_MYIP; + break; - case Opt_fsid: - err = parse_fsid(argstr[0].from, &opt->fsid); - if (err == 0) - opt->flags |= CEPH_OPT_FSID; - break; - case Opt_name: - kfree(opt->name); - opt->name = kstrndup(argstr[0].from, - argstr[0].to-argstr[0].from, - GFP_KERNEL); - if (!opt->name) { - err = -ENOMEM; - goto out; - } - break; - case Opt_secret: - ceph_crypto_key_destroy(opt->key); - kfree(opt->key); - - opt->key = kzalloc(sizeof(*opt->key), GFP_KERNEL); - if (!opt->key) { - err = -ENOMEM; - goto out; - } - err = ceph_crypto_key_unarmor(opt->key, argstr[0].from); - if (err < 0) - goto out; - break; - case Opt_key: - ceph_crypto_key_destroy(opt->key); - kfree(opt->key); - - opt->key = kzalloc(sizeof(*opt->key), GFP_KERNEL); - if (!opt->key) { - err = -ENOMEM; - goto out; - } - err = get_secret(opt->key, argstr[0].from); - if (err < 0) - goto out; - break; + case Opt_fsid: + err = parse_fsid(param->string, &opt->fsid); + if (err) { + errorf(fc, "libceph: Failed to parse fsid: %d", err); + return err; + } + opt->flags |= CEPH_OPT_FSID; + break; + case Opt_name: + kfree(opt->name); + opt->name = param->string; + param->string = NULL; + break; + case Opt_secret: + ceph_crypto_key_destroy(opt->key); + kfree(opt->key); - /* misc */ - case Opt_osdtimeout: - pr_warn("ignoring deprecated osdtimeout option\n"); - break; - case Opt_osdkeepalivetimeout: - /* 0 isn't well defined right now, reject it */ - if (intval < 1 || intval > INT_MAX / 1000) { - pr_err("osdkeepalive out of range\n"); - err = -EINVAL; - goto out; - } - opt->osd_keepalive_timeout = - msecs_to_jiffies(intval * 1000); - break; - case Opt_osd_idle_ttl: - /* 0 isn't well defined right now, reject it */ - if (intval < 1 || intval > INT_MAX / 1000) { - pr_err("osd_idle_ttl out of range\n"); - err = -EINVAL; - goto out; - } - opt->osd_idle_ttl = msecs_to_jiffies(intval * 1000); - break; - case Opt_mount_timeout: - /* 0 is "wait forever" (i.e. infinite timeout) */ - if (intval < 0 || intval > INT_MAX / 1000) { - pr_err("mount_timeout out of range\n"); - err = -EINVAL; - goto out; - } - opt->mount_timeout = msecs_to_jiffies(intval * 1000); - break; - case Opt_osd_request_timeout: - /* 0 is "wait forever" (i.e. infinite timeout) */ - if (intval < 0 || intval > INT_MAX / 1000) { - pr_err("osd_request_timeout out of range\n"); - err = -EINVAL; - goto out; - } - opt->osd_request_timeout = msecs_to_jiffies(intval * 1000); - break; + opt->key = kzalloc(sizeof(*opt->key), GFP_KERNEL); + if (!opt->key) + return -ENOMEM; + err = ceph_crypto_key_unarmor(opt->key, param->string); + if (err) { + errorf(fc, "libceph: Failed to parse secret: %d", err); + return err; + } + break; + case Opt_key: + ceph_crypto_key_destroy(opt->key); + kfree(opt->key); - case Opt_share: + opt->key = kzalloc(sizeof(*opt->key), GFP_KERNEL); + if (!opt->key) + return -ENOMEM; + return get_secret(opt->key, param->string, fc); + + case Opt_osdtimeout: + warnf(fc, "libceph: Ignoring osdtimeout"); + break; + case Opt_osdkeepalivetimeout: + /* 0 isn't well defined right now, reject it */ + if (result.uint_32 < 1 || result.uint_32 > INT_MAX / 1000) + goto out_of_range; + opt->osd_keepalive_timeout = + msecs_to_jiffies(result.uint_32 * 1000); + break; + case Opt_osd_idle_ttl: + /* 0 isn't well defined right now, reject it */ + if (result.uint_32 < 1 || result.uint_32 > INT_MAX / 1000) + goto out_of_range; + opt->osd_idle_ttl = msecs_to_jiffies(result.uint_32 * 1000); + break; + case Opt_mount_timeout: + /* 0 is "wait forever" (i.e. infinite timeout) */ + if (result.uint_32 > INT_MAX / 1000) + goto out_of_range; + opt->mount_timeout = msecs_to_jiffies(result.uint_32 * 1000); + break; + case Opt_osd_request_timeout: + /* 0 is "wait forever" (i.e. infinite timeout) */ + if (result.uint_32 > INT_MAX / 1000) + goto out_of_range; + opt->osd_request_timeout = + msecs_to_jiffies(result.uint_32 * 1000); + break; + + case Opt_share: + if (!result.negated) opt->flags &= ~CEPH_OPT_NOSHARE; - break; - case Opt_noshare: + else opt->flags |= CEPH_OPT_NOSHARE; - break; - - case Opt_crc: + break; + case Opt_crc: + if (!result.negated) opt->flags &= ~CEPH_OPT_NOCRC; - break; - case Opt_nocrc: + else opt->flags |= CEPH_OPT_NOCRC; - break; - - case Opt_cephx_require_signatures: + break; + case Opt_cephx_require_signatures: + if (!result.negated) opt->flags &= ~CEPH_OPT_NOMSGAUTH; - break; - case Opt_nocephx_require_signatures: + else opt->flags |= CEPH_OPT_NOMSGAUTH; - break; - case Opt_cephx_sign_messages: + break; + case Opt_cephx_sign_messages: + if (!result.negated) opt->flags &= ~CEPH_OPT_NOMSGSIGN; - break; - case Opt_nocephx_sign_messages: + else opt->flags |= CEPH_OPT_NOMSGSIGN; - break; - - case Opt_tcp_nodelay: + break; + case Opt_tcp_nodelay: + if (!result.negated) opt->flags |= CEPH_OPT_TCP_NODELAY; - break; - case Opt_notcp_nodelay: + else opt->flags &= ~CEPH_OPT_TCP_NODELAY; - break; + break; - case Opt_abort_on_full: - opt->flags |= CEPH_OPT_ABORT_ON_FULL; - break; + case Opt_abort_on_full: + opt->flags |= CEPH_OPT_ABORT_ON_FULL; + break; - default: - BUG_ON(token); - } + default: + BUG(); } - /* success */ - return opt; + return 0; -out: - ceph_destroy_options(opt); - return ERR_PTR(err); +out_of_range: + return invalf(fc, "libceph: %s out of range", param->key); } -EXPORT_SYMBOL(ceph_parse_options); +EXPORT_SYMBOL(ceph_parse_param); int ceph_print_client_options(struct seq_file *m, struct ceph_client *client, bool show_all) diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index e4cb3db2ee77..5b4bd8261002 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -2004,10 +2004,8 @@ int ceph_parse_ips(const char *c, const char *end, return 0; bad: - pr_err("parse_ips bad ip '%.*s'\n", (int)(end - c), c); return ret; } -EXPORT_SYMBOL(ceph_parse_ips); static int process_banner(struct ceph_connection *con) { -- cgit v1.2.3-71-gd317 From c1d084759c95ecd0ef08274654a1f6c4f343cdcd Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Wed, 6 Nov 2019 10:50:19 +0100 Subject: i2c: replace i2c_new_probed_device with an ERR_PTR variant In the general move to have i2c_new_*_device functions which return ERR_PTR instead of NULL, this patch converts i2c_new_probed_device(). There are only few users, so this patch converts the I2C core and all users in one go. The function gets renamed to i2c_new_scanned_device() so out-of-tree users will get a build failure to understand they need to adapt their error checking code. Signed-off-by: Wolfram Sang Reviewed-by: Luca Ceresoli Reviewed-by: Max Staudt Signed-off-by: Wolfram Sang --- Documentation/i2c/instantiating-devices.rst | 10 +++++----- Documentation/i2c/writing-clients.rst | 8 ++++---- drivers/i2c/i2c-core-base.c | 25 +++++++++++++++++++------ include/linux/i2c.h | 12 +++++++++--- 4 files changed, 37 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/Documentation/i2c/instantiating-devices.rst b/Documentation/i2c/instantiating-devices.rst index 1238f1fa3382..875ebe9e78e3 100644 --- a/Documentation/i2c/instantiating-devices.rst +++ b/Documentation/i2c/instantiating-devices.rst @@ -123,7 +123,7 @@ present or not (for example for an optional feature which is not present on cheap variants of a board but you have no way to tell them apart), or it may have different addresses from one board to the next (manufacturer changing its design without notice). In this case, you can call -i2c_new_probed_device() instead of i2c_new_device(). +i2c_new_scanned_device() instead of i2c_new_device(). Example (from the nxp OHCI driver):: @@ -139,8 +139,8 @@ Example (from the nxp OHCI driver):: i2c_adap = i2c_get_adapter(2); memset(&i2c_info, 0, sizeof(struct i2c_board_info)); strscpy(i2c_info.type, "isp1301_nxp", sizeof(i2c_info.type)); - isp1301_i2c_client = i2c_new_probed_device(i2c_adap, &i2c_info, - normal_i2c, NULL); + isp1301_i2c_client = i2c_new_scanned_device(i2c_adap, &i2c_info, + normal_i2c, NULL); i2c_put_adapter(i2c_adap); (...) } @@ -153,14 +153,14 @@ simply gives up. The driver which instantiated the I2C device is responsible for destroying it on cleanup. This is done by calling i2c_unregister_device() on the pointer that was earlier returned by i2c_new_device() or -i2c_new_probed_device(). +i2c_new_scanned_device(). Method 3: Probe an I2C bus for certain devices ---------------------------------------------- Sometimes you do not have enough information about an I2C device, not even -to call i2c_new_probed_device(). The typical case is hardware monitoring +to call i2c_new_scanned_device(). The typical case is hardware monitoring chips on PC mainboards. There are several dozen models, which can live at 25 different addresses. Given the huge number of mainboards out there, it is next to impossible to build an exhaustive list of the hardware diff --git a/Documentation/i2c/writing-clients.rst b/Documentation/i2c/writing-clients.rst index dddf0a14ab7c..ced309b5e0cc 100644 --- a/Documentation/i2c/writing-clients.rst +++ b/Documentation/i2c/writing-clients.rst @@ -185,14 +185,14 @@ Sometimes you know that a device is connected to a given I2C bus, but you don't know the exact address it uses. This happens on TV adapters for example, where the same driver supports dozens of slightly different models, and I2C device addresses change from one model to the next. In -that case, you can use the i2c_new_probed_device() variant, which is +that case, you can use the i2c_new_scanned_device() variant, which is similar to i2c_new_device(), except that it takes an additional list of possible I2C addresses to probe. A device is created for the first responsive address in the list. If you expect more than one device to be -present in the address range, simply call i2c_new_probed_device() that +present in the address range, simply call i2c_new_scanned_device() that many times. -The call to i2c_new_device() or i2c_new_probed_device() typically happens +The call to i2c_new_device() or i2c_new_scanned_device() typically happens in the I2C bus driver. You may want to save the returned i2c_client reference for later use. @@ -237,7 +237,7 @@ Device Deletion --------------- Each I2C device which has been created using i2c_new_device() or -i2c_new_probed_device() can be unregistered by calling +i2c_new_scanned_device() can be unregistered by calling i2c_unregister_device(). If you don't call it explicitly, it will be called automatically before the underlying I2C bus itself is removed, as a device can't survive its parent in the device driver model. diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index b594cb81cdce..9333c865d4a9 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -2245,10 +2245,10 @@ int i2c_probe_func_quick_read(struct i2c_adapter *adap, unsigned short addr) EXPORT_SYMBOL_GPL(i2c_probe_func_quick_read); struct i2c_client * -i2c_new_probed_device(struct i2c_adapter *adap, - struct i2c_board_info *info, - unsigned short const *addr_list, - int (*probe)(struct i2c_adapter *adap, unsigned short addr)) +i2c_new_scanned_device(struct i2c_adapter *adap, + struct i2c_board_info *info, + unsigned short const *addr_list, + int (*probe)(struct i2c_adapter *adap, unsigned short addr)) { int i; @@ -2278,11 +2278,24 @@ i2c_new_probed_device(struct i2c_adapter *adap, if (addr_list[i] == I2C_CLIENT_END) { dev_dbg(&adap->dev, "Probing failed, no device found\n"); - return NULL; + return ERR_PTR(-ENODEV); } info->addr = addr_list[i]; - return i2c_new_device(adap, info); + return i2c_new_client_device(adap, info); +} +EXPORT_SYMBOL_GPL(i2c_new_scanned_device); + +struct i2c_client * +i2c_new_probed_device(struct i2c_adapter *adap, + struct i2c_board_info *info, + unsigned short const *addr_list, + int (*probe)(struct i2c_adapter *adap, unsigned short addr)) +{ + struct i2c_client *client; + + client = i2c_new_scanned_device(adap, info, addr_list, probe); + return IS_ERR(client) ? NULL : client; } EXPORT_SYMBOL_GPL(i2c_new_probed_device); diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 88b825601f3d..d2f786706657 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -452,10 +452,16 @@ i2c_new_client_device(struct i2c_adapter *adap, struct i2c_board_info const *inf * a default probing method is used. */ extern struct i2c_client * +i2c_new_scanned_device(struct i2c_adapter *adap, + struct i2c_board_info *info, + unsigned short const *addr_list, + int (*probe)(struct i2c_adapter *adap, unsigned short addr)); + +extern struct i2c_client * i2c_new_probed_device(struct i2c_adapter *adap, - struct i2c_board_info *info, - unsigned short const *addr_list, - int (*probe)(struct i2c_adapter *adap, unsigned short addr)); + struct i2c_board_info *info, + unsigned short const *addr_list, + int (*probe)(struct i2c_adapter *adap, unsigned short addr)); /* Common custom probe functions */ extern int i2c_probe_func_quick_read(struct i2c_adapter *adap, unsigned short addr); -- cgit v1.2.3-71-gd317 From 031097d9e079e40dce401031d1012e83d80eaf01 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 27 Nov 2019 12:16:41 -0800 Subject: net: skmsg: fix TLS 1.3 crash with full sk_msg TLS 1.3 started using the entry at the end of the SG array for chaining-in the single byte content type entry. This mostly works: [ E E E E E E . . ] ^ ^ start end E < content type / [ E E E E E E C . ] ^ ^ start end (Where E denotes a populated SG entry; C denotes a chaining entry.) If the array is full, however, the end will point to the start: [ E E E E E E E E ] ^ start end And we end up overwriting the start: E < content type / [ C E E E E E E E ] ^ start end The sg array is supposed to be a circular buffer with start and end markers pointing anywhere. In case where start > end (i.e. the circular buffer has "wrapped") there is an extra entry reserved at the end to chain the two halves together. [ E E E E E E . . l ] (Where l is the reserved entry for "looping" back to front. As suggested by John, let's reserve another entry for chaining SG entries after the main circular buffer. Note that this entry has to be pointed to by the end entry so its position is not fixed. Examples of full messages: [ E E E E E E E E . l ] ^ ^ start end <---------------. [ E E . E E E E E E l ] ^ ^ end start Now the end will always point to an unused entry, so TLS 1.3 can always use it. Fixes: 130b392c6cd6 ("net: tls: Add tls 1.3 support") Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/skmsg.h | 28 ++++++++++++++-------------- net/core/filter.c | 8 ++++---- net/core/skmsg.c | 2 +- net/ipv4/tcp_bpf.c | 2 +- 4 files changed, 20 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 6cb077b646a5..ef7031f8a304 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -14,6 +14,7 @@ #include #define MAX_MSG_FRAGS MAX_SKB_FRAGS +#define NR_MSG_FRAG_IDS (MAX_MSG_FRAGS + 1) enum __sk_action { __SK_DROP = 0, @@ -29,13 +30,15 @@ struct sk_msg_sg { u32 size; u32 copybreak; unsigned long copy; - /* The extra element is used for chaining the front and sections when - * the list becomes partitioned (e.g. end < start). The crypto APIs - * require the chaining. + /* The extra two elements: + * 1) used for chaining the front and sections when the list becomes + * partitioned (e.g. end < start). The crypto APIs require the + * chaining; + * 2) to chain tailer SG entries after the message. */ - struct scatterlist data[MAX_MSG_FRAGS + 1]; + struct scatterlist data[MAX_MSG_FRAGS + 2]; }; -static_assert(BITS_PER_LONG >= MAX_MSG_FRAGS); +static_assert(BITS_PER_LONG >= NR_MSG_FRAG_IDS); /* UAPI in filter.c depends on struct sk_msg_sg being first element. */ struct sk_msg { @@ -142,13 +145,13 @@ static inline void sk_msg_apply_bytes(struct sk_psock *psock, u32 bytes) static inline u32 sk_msg_iter_dist(u32 start, u32 end) { - return end >= start ? end - start : end + (MAX_MSG_FRAGS - start); + return end >= start ? end - start : end + (NR_MSG_FRAG_IDS - start); } #define sk_msg_iter_var_prev(var) \ do { \ if (var == 0) \ - var = MAX_MSG_FRAGS - 1; \ + var = NR_MSG_FRAG_IDS - 1; \ else \ var--; \ } while (0) @@ -156,7 +159,7 @@ static inline u32 sk_msg_iter_dist(u32 start, u32 end) #define sk_msg_iter_var_next(var) \ do { \ var++; \ - if (var == MAX_MSG_FRAGS) \ + if (var == NR_MSG_FRAG_IDS) \ var = 0; \ } while (0) @@ -173,9 +176,9 @@ static inline void sk_msg_clear_meta(struct sk_msg *msg) static inline void sk_msg_init(struct sk_msg *msg) { - BUILD_BUG_ON(ARRAY_SIZE(msg->sg.data) - 1 != MAX_MSG_FRAGS); + BUILD_BUG_ON(ARRAY_SIZE(msg->sg.data) - 1 != NR_MSG_FRAG_IDS); memset(msg, 0, sizeof(*msg)); - sg_init_marker(msg->sg.data, MAX_MSG_FRAGS); + sg_init_marker(msg->sg.data, NR_MSG_FRAG_IDS); } static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src, @@ -196,14 +199,11 @@ static inline void sk_msg_xfer_full(struct sk_msg *dst, struct sk_msg *src) static inline bool sk_msg_full(const struct sk_msg *msg) { - return (msg->sg.end == msg->sg.start) && msg->sg.size; + return sk_msg_iter_dist(msg->sg.start, msg->sg.end) == MAX_MSG_FRAGS; } static inline u32 sk_msg_elem_used(const struct sk_msg *msg) { - if (sk_msg_full(msg)) - return MAX_MSG_FRAGS; - return sk_msg_iter_dist(msg->sg.start, msg->sg.end); } diff --git a/net/core/filter.c b/net/core/filter.c index b0ed048585ba..f1e703eed3d2 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2299,7 +2299,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, WARN_ON_ONCE(last_sge == first_sge); shift = last_sge > first_sge ? last_sge - first_sge - 1 : - MAX_SKB_FRAGS - first_sge + last_sge - 1; + NR_MSG_FRAG_IDS - first_sge + last_sge - 1; if (!shift) goto out; @@ -2308,8 +2308,8 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, do { u32 move_from; - if (i + shift >= MAX_MSG_FRAGS) - move_from = i + shift - MAX_MSG_FRAGS; + if (i + shift >= NR_MSG_FRAG_IDS) + move_from = i + shift - NR_MSG_FRAG_IDS; else move_from = i + shift; if (move_from == msg->sg.end) @@ -2323,7 +2323,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, } while (1); msg->sg.end = msg->sg.end - shift > msg->sg.end ? - msg->sg.end - shift + MAX_MSG_FRAGS : + msg->sg.end - shift + NR_MSG_FRAG_IDS : msg->sg.end - shift; out: msg->data = sg_virt(&msg->sg.data[first_sge]) + start - offset; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index a469d2124f3f..ded2d5227678 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -421,7 +421,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) copied = skb->len; msg->sg.start = 0; msg->sg.size = copied; - msg->sg.end = num_sge == MAX_MSG_FRAGS ? 0 : num_sge; + msg->sg.end = num_sge; msg->skb = skb; sk_psock_queue_msg(psock, msg); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 8a56e09cfb0e..e38705165ac9 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -301,7 +301,7 @@ EXPORT_SYMBOL_GPL(tcp_bpf_sendmsg_redir); static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg, int *copied, int flags) { - bool cork = false, enospc = msg->sg.start == msg->sg.end; + bool cork = false, enospc = sk_msg_full(msg); struct sock *sk_redir; u32 tosend, delta = 0; int ret; -- cgit v1.2.3-71-gd317 From ba1e78a1dc0ca3e92f0be82279e6ba24177af7d6 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 21 Nov 2019 19:41:51 +0100 Subject: cpuidle: Drop disabled field from struct cpuidle_state After recent cpuidle updates the "disabled" field in struct cpuidle_state is only used by two drivers (intel_idle and shmobile cpuidle) for marking unusable idle states, but that may as well be achieved with the help of a state flag, so define an "unusable" idle state flag, CPUIDLE_FLAG_UNUSABLE, make the drivers in question use it instead of the "disabled" field and make the core set CPUIDLE_STATE_DISABLED_BY_DRIVER for the idle states with that flag set. After the above changes, the "disabled" field in struct cpuidle_state is not used any more, so drop it. No intentional functional impact. Signed-off-by: Rafael J. Wysocki --- arch/sh/kernel/cpu/shmobile/cpuidle.c | 8 ++++---- drivers/cpuidle/cpuidle.c | 2 +- drivers/cpuidle/poll_state.c | 1 - drivers/idle/intel_idle.c | 6 +++--- include/linux/cpuidle.h | 2 +- 5 files changed, 9 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/arch/sh/kernel/cpu/shmobile/cpuidle.c b/arch/sh/kernel/cpu/shmobile/cpuidle.c index dbd2cdec2ddb..b0f9c8f8fd14 100644 --- a/arch/sh/kernel/cpu/shmobile/cpuidle.c +++ b/arch/sh/kernel/cpu/shmobile/cpuidle.c @@ -67,7 +67,7 @@ static struct cpuidle_driver cpuidle_driver = { .enter = cpuidle_sleep_enter, .name = "C2", .desc = "SuperH Sleep Mode [SF]", - .disabled = true, + .flags = CPUIDLE_FLAG_UNUSABLE, }, { .exit_latency = 2300, @@ -76,7 +76,7 @@ static struct cpuidle_driver cpuidle_driver = { .enter = cpuidle_sleep_enter, .name = "C3", .desc = "SuperH Mobile Standby Mode [SF]", - .disabled = true, + .flags = CPUIDLE_FLAG_UNUSABLE, }, }, .safe_state_index = 0, @@ -86,10 +86,10 @@ static struct cpuidle_driver cpuidle_driver = { int __init sh_mobile_setup_cpuidle(void) { if (sh_mobile_sleep_supported & SUSP_SH_SF) - cpuidle_driver.states[1].disabled = false; + cpuidle_driver.states[1].flags = CPUIDLE_FLAG_NONE; if (sh_mobile_sleep_supported & SUSP_SH_STANDBY) - cpuidle_driver.states[2].disabled = false; + cpuidle_driver.states[2].flags = CPUIDLE_FLAG_NONE; return cpuidle_register(&cpuidle_driver, NULL); } diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 569dbac443bd..0005be5ea2b4 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -572,7 +572,7 @@ static int __cpuidle_register_device(struct cpuidle_device *dev) return -EINVAL; for (i = 0; i < drv->state_count; i++) - if (drv->states[i].disabled) + if (drv->states[i].flags & CPUIDLE_FLAG_UNUSABLE) dev->states_usage[i].disable |= CPUIDLE_STATE_DISABLED_BY_DRIVER; per_cpu(cpuidle_devices, dev->cpu) = dev; diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c index 9f1ace9c53da..f7e83613ae94 100644 --- a/drivers/cpuidle/poll_state.c +++ b/drivers/cpuidle/poll_state.c @@ -53,7 +53,6 @@ void cpuidle_poll_state_init(struct cpuidle_driver *drv) state->target_residency_ns = 0; state->power_usage = -1; state->enter = poll_idle; - state->disabled = false; state->flags = CPUIDLE_FLAG_POLLING; } EXPORT_SYMBOL_GPL(cpuidle_poll_state_init); diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 347b08b56042..75fd2a7b0842 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -1291,8 +1291,8 @@ static void sklh_idle_state_table_update(void) return; } - skl_cstates[5].disabled = 1; /* C8-SKL */ - skl_cstates[6].disabled = 1; /* C9-SKL */ + skl_cstates[5].flags |= CPUIDLE_FLAG_UNUSABLE; /* C8-SKL */ + skl_cstates[6].flags |= CPUIDLE_FLAG_UNUSABLE; /* C9-SKL */ } /* * intel_idle_state_table_update() @@ -1355,7 +1355,7 @@ static void __init intel_idle_cpuidle_driver_init(void) continue; /* if state marked as disabled, skip it */ - if (cpuidle_state_table[cstate].disabled != 0) { + if (cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_UNUSABLE) { pr_debug("state %s is disabled\n", cpuidle_state_table[cstate].name); continue; diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 2dbe46b7c213..1dabe36bd011 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -54,7 +54,6 @@ struct cpuidle_state { unsigned int exit_latency; /* in US */ int power_usage; /* in mW */ unsigned int target_residency; /* in US */ - bool disabled; /* disabled on all CPUs */ int (*enter) (struct cpuidle_device *dev, struct cpuidle_driver *drv, @@ -77,6 +76,7 @@ struct cpuidle_state { #define CPUIDLE_FLAG_POLLING BIT(0) /* polling state */ #define CPUIDLE_FLAG_COUPLED BIT(1) /* state applies to multiple cpus */ #define CPUIDLE_FLAG_TIMER_STOP BIT(2) /* timer is stopped on this state */ +#define CPUIDLE_FLAG_UNUSABLE BIT(3) /* avoid using this state */ struct cpuidle_device_kobj; struct cpuidle_state_kobj; -- cgit v1.2.3-71-gd317 From c6a3aea93571a5393602256d8f74772bd64c8225 Mon Sep 17 00:00:00 2001 From: Leonard Crestez Date: Tue, 26 Nov 2019 17:17:11 +0200 Subject: PM / QoS: Redefine FREQ_QOS_MAX_DEFAULT_VALUE to S32_MAX QOS requests for DEFAULT_VALUE are supposed to be ignored but this is not the case for FREQ_QOS_MAX. Adding one request for MAX_DEFAULT_VALUE and one for a real value will cause freq_qos_read_value to unexpectedly return MAX_DEFAULT_VALUE (-1). This happens because freq_qos max value is aggregated with PM_QOS_MIN but FREQ_QOS_MAX_DEFAULT_VALUE is (-1) so it's smaller than other values. Fix this by redefining FREQ_QOS_MAX_DEFAULT_VALUE to S32_MAX. Looking at current users for freq_qos it seems that none of them create requests for FREQ_QOS_MAX_DEFAULT_VALUE. Fixes: 77751a466ebd ("PM: QoS: Introduce frequency QoS") Signed-off-by: Leonard Crestez Reported-by: Matthias Kaehlcke Reviewed-by: Matthias Kaehlcke Cc: 5.4+ # 5.4+ Signed-off-by: Rafael J. Wysocki --- include/linux/pm_qos.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index ebf5ef17cc2a..24a6263c9931 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -256,7 +256,7 @@ static inline s32 dev_pm_qos_raw_resume_latency(struct device *dev) #endif #define FREQ_QOS_MIN_DEFAULT_VALUE 0 -#define FREQ_QOS_MAX_DEFAULT_VALUE (-1) +#define FREQ_QOS_MAX_DEFAULT_VALUE S32_MAX enum freq_qos_req_type { FREQ_QOS_MIN = 1, -- cgit v1.2.3-71-gd317 From 342035f66c866f4ad750477b21b210e98d1f6818 Mon Sep 17 00:00:00 2001 From: Leonard Crestez Date: Tue, 26 Nov 2019 17:17:12 +0200 Subject: PM / QoS: Reorder pm_qos/freq_qos/dev_pm_qos structs This allows dev_pm_qos to embed freq_qos structs, which is done in the next patch. Separate commit to make it easier to review. Signed-off-by: Leonard Crestez Reviewed-by: Matthias Kaehlcke Signed-off-by: Rafael J. Wysocki --- include/linux/pm_qos.h | 74 ++++++++++++++++++++++++++------------------------ 1 file changed, 38 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index 24a6263c9931..678fec6da5b9 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -49,21 +49,6 @@ struct pm_qos_flags_request { s32 flags; /* Do not change to 64 bit */ }; -enum dev_pm_qos_req_type { - DEV_PM_QOS_RESUME_LATENCY = 1, - DEV_PM_QOS_LATENCY_TOLERANCE, - DEV_PM_QOS_FLAGS, -}; - -struct dev_pm_qos_request { - enum dev_pm_qos_req_type type; - union { - struct plist_node pnode; - struct pm_qos_flags_request flr; - } data; - struct device *dev; -}; - enum pm_qos_type { PM_QOS_UNITIALIZED, PM_QOS_MAX, /* return the largest value */ @@ -90,6 +75,44 @@ struct pm_qos_flags { s32 effective_flags; /* Do not change to 64 bit */ }; + +#define FREQ_QOS_MIN_DEFAULT_VALUE 0 +#define FREQ_QOS_MAX_DEFAULT_VALUE S32_MAX + +enum freq_qos_req_type { + FREQ_QOS_MIN = 1, + FREQ_QOS_MAX, +}; + +struct freq_constraints { + struct pm_qos_constraints min_freq; + struct blocking_notifier_head min_freq_notifiers; + struct pm_qos_constraints max_freq; + struct blocking_notifier_head max_freq_notifiers; +}; + +struct freq_qos_request { + enum freq_qos_req_type type; + struct plist_node pnode; + struct freq_constraints *qos; +}; + + +enum dev_pm_qos_req_type { + DEV_PM_QOS_RESUME_LATENCY = 1, + DEV_PM_QOS_LATENCY_TOLERANCE, + DEV_PM_QOS_FLAGS, +}; + +struct dev_pm_qos_request { + enum dev_pm_qos_req_type type; + union { + struct plist_node pnode; + struct pm_qos_flags_request flr; + } data; + struct device *dev; +}; + struct dev_pm_qos { struct pm_qos_constraints resume_latency; struct pm_qos_constraints latency_tolerance; @@ -255,27 +278,6 @@ static inline s32 dev_pm_qos_raw_resume_latency(struct device *dev) } #endif -#define FREQ_QOS_MIN_DEFAULT_VALUE 0 -#define FREQ_QOS_MAX_DEFAULT_VALUE S32_MAX - -enum freq_qos_req_type { - FREQ_QOS_MIN = 1, - FREQ_QOS_MAX, -}; - -struct freq_constraints { - struct pm_qos_constraints min_freq; - struct blocking_notifier_head min_freq_notifiers; - struct pm_qos_constraints max_freq; - struct blocking_notifier_head max_freq_notifiers; -}; - -struct freq_qos_request { - enum freq_qos_req_type type; - struct plist_node pnode; - struct freq_constraints *qos; -}; - static inline int freq_qos_request_active(struct freq_qos_request *req) { return !IS_ERR_OR_NULL(req->qos); -- cgit v1.2.3-71-gd317 From 36a8015f89e40f7c9c91cc7e6d028fa288dad27b Mon Sep 17 00:00:00 2001 From: Leonard Crestez Date: Tue, 26 Nov 2019 17:17:13 +0200 Subject: PM / QoS: Restore DEV_PM_QOS_MIN/MAX_FREQUENCY Support for adding per-device frequency limits was removed in commit 2aac8bdf7a0f ("PM: QoS: Drop frequency QoS types from device PM QoS") after cpufreq switched to use a new "freq_constraints" construct. Restore support for per-device freq limits but base this upon freq_constraints. This is primarily meant to be used by the devfreq subsystem. This removes the "static" marking on freq_qos_apply but does not export it for modules. Signed-off-by: Leonard Crestez Reviewed-by: Matthias Kaehlcke Tested-by: Matthias Kaehlcke Signed-off-by: Rafael J. Wysocki --- drivers/base/power/qos.c | 73 ++++++++++++++++++++++++++++++++++++++++++++---- include/linux/pm_qos.h | 12 ++++++++ kernel/power/qos.c | 4 ++- 3 files changed, 82 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c index 350dcafd751f..8e93167f1783 100644 --- a/drivers/base/power/qos.c +++ b/drivers/base/power/qos.c @@ -115,10 +115,20 @@ s32 dev_pm_qos_read_value(struct device *dev, enum dev_pm_qos_req_type type) spin_lock_irqsave(&dev->power.lock, flags); - if (type == DEV_PM_QOS_RESUME_LATENCY) { + switch (type) { + case DEV_PM_QOS_RESUME_LATENCY: ret = IS_ERR_OR_NULL(qos) ? PM_QOS_RESUME_LATENCY_NO_CONSTRAINT : pm_qos_read_value(&qos->resume_latency); - } else { + break; + case DEV_PM_QOS_MIN_FREQUENCY: + ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE + : freq_qos_read_value(&qos->freq, FREQ_QOS_MIN); + break; + case DEV_PM_QOS_MAX_FREQUENCY: + ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE + : freq_qos_read_value(&qos->freq, FREQ_QOS_MAX); + break; + default: WARN_ON(1); ret = 0; } @@ -159,6 +169,10 @@ static int apply_constraint(struct dev_pm_qos_request *req, req->dev->power.set_latency_tolerance(req->dev, value); } break; + case DEV_PM_QOS_MIN_FREQUENCY: + case DEV_PM_QOS_MAX_FREQUENCY: + ret = freq_qos_apply(&req->data.freq, action, value); + break; case DEV_PM_QOS_FLAGS: ret = pm_qos_update_flags(&qos->flags, &req->data.flr, action, value); @@ -209,6 +223,8 @@ static int dev_pm_qos_constraints_allocate(struct device *dev) c->no_constraint_value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT; c->type = PM_QOS_MIN; + freq_constraints_init(&qos->freq); + INIT_LIST_HEAD(&qos->flags.list); spin_lock_irq(&dev->power.lock); @@ -269,6 +285,20 @@ void dev_pm_qos_constraints_destroy(struct device *dev) memset(req, 0, sizeof(*req)); } + c = &qos->freq.min_freq; + plist_for_each_entry_safe(req, tmp, &c->list, data.freq.pnode) { + apply_constraint(req, PM_QOS_REMOVE_REQ, + PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE); + memset(req, 0, sizeof(*req)); + } + + c = &qos->freq.max_freq; + plist_for_each_entry_safe(req, tmp, &c->list, data.freq.pnode) { + apply_constraint(req, PM_QOS_REMOVE_REQ, + PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE); + memset(req, 0, sizeof(*req)); + } + f = &qos->flags; list_for_each_entry_safe(req, tmp, &f->list, data.flr.node) { apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); @@ -314,11 +344,22 @@ static int __dev_pm_qos_add_request(struct device *dev, ret = dev_pm_qos_constraints_allocate(dev); trace_dev_pm_qos_add_request(dev_name(dev), type, value); - if (!ret) { - req->dev = dev; - req->type = type; + if (ret) + return ret; + + req->dev = dev; + req->type = type; + if (req->type == DEV_PM_QOS_MIN_FREQUENCY) + ret = freq_qos_add_request(&dev->power.qos->freq, + &req->data.freq, + FREQ_QOS_MIN, value); + else if (req->type == DEV_PM_QOS_MAX_FREQUENCY) + ret = freq_qos_add_request(&dev->power.qos->freq, + &req->data.freq, + FREQ_QOS_MAX, value); + else ret = apply_constraint(req, PM_QOS_ADD_REQ, value); - } + return ret; } @@ -382,6 +423,10 @@ static int __dev_pm_qos_update_request(struct dev_pm_qos_request *req, case DEV_PM_QOS_LATENCY_TOLERANCE: curr_value = req->data.pnode.prio; break; + case DEV_PM_QOS_MIN_FREQUENCY: + case DEV_PM_QOS_MAX_FREQUENCY: + curr_value = req->data.freq.pnode.prio; + break; case DEV_PM_QOS_FLAGS: curr_value = req->data.flr.flags; break; @@ -507,6 +552,14 @@ int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier, ret = blocking_notifier_chain_register(dev->power.qos->resume_latency.notifiers, notifier); break; + case DEV_PM_QOS_MIN_FREQUENCY: + ret = freq_qos_add_notifier(&dev->power.qos->freq, + FREQ_QOS_MIN, notifier); + break; + case DEV_PM_QOS_MAX_FREQUENCY: + ret = freq_qos_add_notifier(&dev->power.qos->freq, + FREQ_QOS_MAX, notifier); + break; default: WARN_ON(1); ret = -EINVAL; @@ -546,6 +599,14 @@ int dev_pm_qos_remove_notifier(struct device *dev, ret = blocking_notifier_chain_unregister(dev->power.qos->resume_latency.notifiers, notifier); break; + case DEV_PM_QOS_MIN_FREQUENCY: + ret = freq_qos_remove_notifier(&dev->power.qos->freq, + FREQ_QOS_MIN, notifier); + break; + case DEV_PM_QOS_MAX_FREQUENCY: + ret = freq_qos_remove_notifier(&dev->power.qos->freq, + FREQ_QOS_MAX, notifier); + break; default: WARN_ON(1); ret = -EINVAL; diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index 678fec6da5b9..19eafca5680e 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -34,6 +34,8 @@ enum pm_qos_flags_status { #define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT PM_QOS_LATENCY_ANY #define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS PM_QOS_LATENCY_ANY_NS #define PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE 0 +#define PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE 0 +#define PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE FREQ_QOS_MAX_DEFAULT_VALUE #define PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT (-1) #define PM_QOS_FLAG_NO_POWER_OFF (1 << 0) @@ -101,6 +103,8 @@ struct freq_qos_request { enum dev_pm_qos_req_type { DEV_PM_QOS_RESUME_LATENCY = 1, DEV_PM_QOS_LATENCY_TOLERANCE, + DEV_PM_QOS_MIN_FREQUENCY, + DEV_PM_QOS_MAX_FREQUENCY, DEV_PM_QOS_FLAGS, }; @@ -109,6 +113,7 @@ struct dev_pm_qos_request { union { struct plist_node pnode; struct pm_qos_flags_request flr; + struct freq_qos_request freq; } data; struct device *dev; }; @@ -116,6 +121,7 @@ struct dev_pm_qos_request { struct dev_pm_qos { struct pm_qos_constraints resume_latency; struct pm_qos_constraints latency_tolerance; + struct freq_constraints freq; struct pm_qos_flags flags; struct dev_pm_qos_request *resume_latency_req; struct dev_pm_qos_request *latency_tolerance_req; @@ -214,6 +220,10 @@ static inline s32 dev_pm_qos_read_value(struct device *dev, switch (type) { case DEV_PM_QOS_RESUME_LATENCY: return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; + case DEV_PM_QOS_MIN_FREQUENCY: + return PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE; + case DEV_PM_QOS_MAX_FREQUENCY: + return PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE; default: WARN_ON(1); return 0; @@ -293,6 +303,8 @@ int freq_qos_add_request(struct freq_constraints *qos, enum freq_qos_req_type type, s32 value); int freq_qos_update_request(struct freq_qos_request *req, s32 new_value); int freq_qos_remove_request(struct freq_qos_request *req); +int freq_qos_apply(struct freq_qos_request *req, + enum pm_qos_req_action action, s32 value); int freq_qos_add_notifier(struct freq_constraints *qos, enum freq_qos_req_type type, diff --git a/kernel/power/qos.c b/kernel/power/qos.c index a45cba7df0ae..83edf8698118 100644 --- a/kernel/power/qos.c +++ b/kernel/power/qos.c @@ -714,8 +714,10 @@ s32 freq_qos_read_value(struct freq_constraints *qos, * @req: Constraint request to apply. * @action: Action to perform (add/update/remove). * @value: Value to assign to the QoS request. + * + * This is only meant to be called from inside pm_qos, not drivers. */ -static int freq_qos_apply(struct freq_qos_request *req, +int freq_qos_apply(struct freq_qos_request *req, enum pm_qos_req_action action, s32 value) { int ret; -- cgit v1.2.3-71-gd317 From dc0a7f7558dd52e972408ebb535b0153c06d08c2 Mon Sep 17 00:00:00 2001 From: Pengfei Li Date: Sat, 30 Nov 2019 17:49:25 -0800 Subject: mm, slab: remove unused kmalloc_size() The size of kmalloc can be obtained from kmalloc_info[], so remove kmalloc_size() that will not be used anymore. Link: http://lkml.kernel.org/r/1569241648-26908-3-git-send-email-lpf.vector@gmail.com Signed-off-by: Pengfei Li Acked-by: Vlastimil Babka Acked-by: Roman Gushchin Acked-by: David Rientjes Cc: Christoph Lameter Cc: Joonsoo Kim Cc: Pekka Enberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 20 -------------------- mm/slab.c | 5 +++-- mm/slab_common.c | 5 ++--- 3 files changed, 5 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 4d2a2fa55ed5..877a95c6a2d2 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -561,26 +561,6 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags) return __kmalloc(size, flags); } -/* - * Determine size used for the nth kmalloc cache. - * return size or 0 if a kmalloc cache for that - * size does not exist - */ -static __always_inline unsigned int kmalloc_size(unsigned int n) -{ -#ifndef CONFIG_SLOB - if (n > 2) - return 1U << n; - - if (n == 1 && KMALLOC_MIN_SIZE <= 32) - return 96; - - if (n == 2 && KMALLOC_MIN_SIZE <= 64) - return 192; -#endif - return 0; -} - static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { #ifndef CONFIG_SLOB diff --git a/mm/slab.c b/mm/slab.c index 66b3310b42b8..f1e1840af533 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1248,8 +1248,9 @@ void __init kmem_cache_init(void) */ kmalloc_caches[KMALLOC_NORMAL][INDEX_NODE] = create_kmalloc_cache( kmalloc_info[INDEX_NODE].name[KMALLOC_NORMAL], - kmalloc_size(INDEX_NODE), ARCH_KMALLOC_FLAGS, - 0, kmalloc_size(INDEX_NODE)); + kmalloc_info[INDEX_NODE].size, + ARCH_KMALLOC_FLAGS, 0, + kmalloc_info[INDEX_NODE].size); slab_state = PARTIAL_NODE; setup_kmalloc_cache_index_table(); diff --git a/mm/slab_common.c b/mm/slab_common.c index 68a8c294ca89..b67cbe464338 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -1286,11 +1286,10 @@ void __init create_kmalloc_caches(slab_flags_t flags) struct kmem_cache *s = kmalloc_caches[KMALLOC_NORMAL][i]; if (s) { - unsigned int size = kmalloc_size(i); - kmalloc_caches[KMALLOC_DMA][i] = create_kmalloc_cache( kmalloc_info[i].name[KMALLOC_DMA], - size, SLAB_CACHE_DMA | flags, 0, 0); + kmalloc_info[i].size, + SLAB_CACHE_DMA | flags, 0, 0); } } #endif -- cgit v1.2.3-71-gd317 From a92853b6746fe5ffef20a7c30addf6320561e669 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Sat, 30 Nov 2019 17:49:44 -0800 Subject: fs/direct-io.c: keep dio_warn_stale_pagecache() when CONFIG_BLOCK=n This helper prints warning if direct I/O write failed to invalidate cache, and set EIO at inode to warn usersapce about possible data corruption. See also commit 5a9d929d6e13 ("iomap: report collisions between directio and buffered writes to userspace"). Direct I/O is supported by non-disk filesystems, for example NFS. Thus generic code needs this even in kernel without CONFIG_BLOCK. Link: http://lkml.kernel.org/r/157270038074.4812.7980855544557488880.stgit@buzz Signed-off-by: Konstantin Khlebnikov Reviewed-by: Andrew Morton Reviewed-by: Jan Kara Cc: Jens Axboe Cc: Alexander Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/direct-io.c | 21 --------------------- include/linux/fs.h | 6 +++++- mm/filemap.c | 21 +++++++++++++++++++++ 3 files changed, 26 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/fs/direct-io.c b/fs/direct-io.c index 9329ced91f1d..0ec4f270139f 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -220,27 +220,6 @@ static inline struct page *dio_get_page(struct dio *dio, return dio->pages[sdio->head]; } -/* - * Warn about a page cache invalidation failure during a direct io write. - */ -void dio_warn_stale_pagecache(struct file *filp) -{ - static DEFINE_RATELIMIT_STATE(_rs, 86400 * HZ, DEFAULT_RATELIMIT_BURST); - char pathname[128]; - struct inode *inode = file_inode(filp); - char *path; - - errseq_set(&inode->i_mapping->wb_err, -EIO); - if (__ratelimit(&_rs)) { - path = file_path(filp, pathname, sizeof(pathname)); - if (IS_ERR(path)) - path = "(unknown)"; - pr_crit("Page cache invalidation failure on direct I/O. Possible data corruption due to collision with buffered I/O!\n"); - pr_crit("File: %s PID: %d Comm: %.20s\n", path, current->pid, - current->comm); - } -} - /* * dio_complete() - called when all DIO BIO I/O has been completed * diff --git a/include/linux/fs.h b/include/linux/fs.h index ae6c5c37f3ae..eeed80fab36a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3149,7 +3149,6 @@ enum { }; void dio_end_io(struct bio *bio); -void dio_warn_stale_pagecache(struct file *filp); ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, @@ -3194,6 +3193,11 @@ static inline void inode_dio_end(struct inode *inode) wake_up_bit(&inode->i_state, __I_DIO_WAKEUP); } +/* + * Warn about a page cache invalidation failure diring a direct I/O write. + */ +void dio_warn_stale_pagecache(struct file *filp); + extern void inode_set_flags(struct inode *inode, unsigned int flags, unsigned int mask); diff --git a/mm/filemap.c b/mm/filemap.c index 288e38199068..189b8f318da2 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3161,6 +3161,27 @@ int pagecache_write_end(struct file *file, struct address_space *mapping, } EXPORT_SYMBOL(pagecache_write_end); +/* + * Warn about a page cache invalidation failure during a direct I/O write. + */ +void dio_warn_stale_pagecache(struct file *filp) +{ + static DEFINE_RATELIMIT_STATE(_rs, 86400 * HZ, DEFAULT_RATELIMIT_BURST); + char pathname[128]; + struct inode *inode = file_inode(filp); + char *path; + + errseq_set(&inode->i_mapping->wb_err, -EIO); + if (__ratelimit(&_rs)) { + path = file_path(filp, pathname, sizeof(pathname)); + if (IS_ERR(path)) + path = "(unknown)"; + pr_crit("Page cache invalidation failure on direct I/O. Possible data corruption due to collision with buffered I/O!\n"); + pr_crit("File: %s PID: %d Comm: %.20s\n", path, current->pid, + current->comm); + } +} + ssize_t generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) { -- cgit v1.2.3-71-gd317 From 9da83f3fc74b806ee419a29977ef0239454bd8ec Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Sat, 30 Nov 2019 17:50:03 -0800 Subject: mm, memcg: clean up reclaim iter array The mem_cgroup_reclaim_cookie is only used in memcg softlimit reclaim now, and the priority of the reclaim is always 0. We don't need to define the iter in struct mem_cgroup_per_node as an array any more. That could make the code more clear and save some space. Link: http://lkml.kernel.org/r/1569897728-1686-1-git-send-email-laoar.shao@gmail.com Signed-off-by: Yafang Shao Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 +-- mm/memcontrol.c | 11 +++-------- 2 files changed, 4 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index ae703ea3ef48..2b34925fc19d 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -58,7 +58,6 @@ enum mem_cgroup_protection { struct mem_cgroup_reclaim_cookie { pg_data_t *pgdat; - int priority; unsigned int generation; }; @@ -126,7 +125,7 @@ struct mem_cgroup_per_node { unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; - struct mem_cgroup_reclaim_iter iter[DEF_PRIORITY + 1]; + struct mem_cgroup_reclaim_iter iter; struct memcg_shrinker_map __rcu *shrinker_map; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 01f3f8b665e9..2788fd5870bc 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1052,7 +1052,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup_per_node *mz; mz = mem_cgroup_nodeinfo(root, reclaim->pgdat->node_id); - iter = &mz->iter[reclaim->priority]; + iter = &mz->iter; if (prev && reclaim->generation != iter->generation) goto out_unlock; @@ -1152,15 +1152,11 @@ static void __invalidate_reclaim_iterators(struct mem_cgroup *from, struct mem_cgroup_reclaim_iter *iter; struct mem_cgroup_per_node *mz; int nid; - int i; for_each_node(nid) { mz = mem_cgroup_nodeinfo(from, nid); - for (i = 0; i <= DEF_PRIORITY; i++) { - iter = &mz->iter[i]; - cmpxchg(&iter->position, - dead_memcg, NULL); - } + iter = &mz->iter; + cmpxchg(&iter->position, dead_memcg, NULL); } } @@ -1705,7 +1701,6 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg, unsigned long nr_scanned; struct mem_cgroup_reclaim_cookie reclaim = { .pgdat = pgdat, - .priority = 0, }; excess = soft_limit_excess(root_memcg); -- cgit v1.2.3-71-gd317 From 242c37b459ce9ea1be53b75bdb76a7d9268a0791 Mon Sep 17 00:00:00 2001 From: Hao Lee Date: Sat, 30 Nov 2019 17:50:12 -0800 Subject: include/linux/memcontrol.h: fix comments based on per-node memcg These comments should be updated as memcg limit enforcement has been moved from zones to nodes. Link: http://lkml.kernel.org/r/20191022150618.GA15519@haolee.github.io Signed-off-by: Hao Lee Acked-by: Roman Gushchin Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 2b34925fc19d..e82928deea88 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -111,7 +111,7 @@ struct memcg_shrinker_map { }; /* - * per-zone information in memory controller. + * per-node information in memory controller. */ struct mem_cgroup_per_node { struct lruvec lruvec; @@ -398,8 +398,7 @@ mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid) * @memcg: memcg of the wanted lruvec * * Returns the lru list vector holding pages for a given @node or a given - * @memcg and @zone. This can be the node lruvec, if the memory controller - * is disabled. + * @memcg. This can be the node lruvec, if the memory controller is disabled. */ static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat, struct mem_cgroup *memcg) -- cgit v1.2.3-71-gd317 From fa40d1ee9f156624658ca409a04a78882ca5b3c5 Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Sat, 30 Nov 2019 17:50:16 -0800 Subject: mm: vmscan: memcontrol: remove mem_cgroup_select_victim_node() Since commit 1ba6fc9af35b ("mm: vmscan: do not share cgroup iteration between reclaimers"), the memcg reclaim does not bail out earlier based on sc->nr_reclaimed and will traverse all the nodes. All the reclaimable pages of the memcg on all the nodes will be scanned relative to the reclaim priority. So, there is no need to maintain state regarding which node to start the memcg reclaim from. This patch effectively reverts the commit 889976dbcb12 ("memcg: reclaim memory from nodes in round-robin order") and commit 453a9bf347f1 ("memcg: fix numa scan information update to be triggered by memory event"). [shakeelb@google.com: v2] Link: http://lkml.kernel.org/r/20191030204232.139424-1-shakeelb@google.com Link: http://lkml.kernel.org/r/20191029234753.224143-1-shakeelb@google.com Signed-off-by: Shakeel Butt Acked-by: Roman Gushchin Acked-by: Michal Hocko Acked-by: Johannes Weiner Cc: Greg Thelen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 8 ---- mm/memcontrol.c | 112 --------------------------------------------- mm/vmscan.c | 14 ++---- 3 files changed, 5 insertions(+), 129 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e82928deea88..239e752a7817 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -80,7 +80,6 @@ struct mem_cgroup_id { enum mem_cgroup_events_target { MEM_CGROUP_TARGET_THRESH, MEM_CGROUP_TARGET_SOFTLIMIT, - MEM_CGROUP_TARGET_NUMAINFO, MEM_CGROUP_NTARGETS, }; @@ -312,13 +311,6 @@ struct mem_cgroup { struct list_head kmem_caches; #endif - int last_scanned_node; -#if MAX_NUMNODES > 1 - nodemask_t scan_nodes; - atomic_t numainfo_events; - atomic_t numainfo_updating; -#endif - #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; struct wb_domain cgwb_domain; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 94a5b6d831f9..529e12a59131 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -108,7 +108,6 @@ static const char *const mem_cgroup_lru_names[] = { #define THRESHOLDS_EVENTS_TARGET 128 #define SOFTLIMIT_EVENTS_TARGET 1024 -#define NUMAINFO_EVENTS_TARGET 1024 /* * Cgroups above their limits are maintained in a RB-Tree, independent of @@ -877,9 +876,6 @@ static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg, case MEM_CGROUP_TARGET_SOFTLIMIT: next = val + SOFTLIMIT_EVENTS_TARGET; break; - case MEM_CGROUP_TARGET_NUMAINFO: - next = val + NUMAINFO_EVENTS_TARGET; - break; default: break; } @@ -899,21 +895,12 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) if (unlikely(mem_cgroup_event_ratelimit(memcg, MEM_CGROUP_TARGET_THRESH))) { bool do_softlimit; - bool do_numainfo __maybe_unused; do_softlimit = mem_cgroup_event_ratelimit(memcg, MEM_CGROUP_TARGET_SOFTLIMIT); -#if MAX_NUMNODES > 1 - do_numainfo = mem_cgroup_event_ratelimit(memcg, - MEM_CGROUP_TARGET_NUMAINFO); -#endif mem_cgroup_threshold(memcg); if (unlikely(do_softlimit)) mem_cgroup_update_tree(memcg, page); -#if MAX_NUMNODES > 1 - if (unlikely(do_numainfo)) - atomic_inc(&memcg->numainfo_events); -#endif } } @@ -1591,104 +1578,6 @@ static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, return ret; } -#if MAX_NUMNODES > 1 - -/** - * test_mem_cgroup_node_reclaimable - * @memcg: the target memcg - * @nid: the node ID to be checked. - * @noswap : specify true here if the user wants flle only information. - * - * This function returns whether the specified memcg contains any - * reclaimable pages on a node. Returns true if there are any reclaimable - * pages in the node. - */ -static bool test_mem_cgroup_node_reclaimable(struct mem_cgroup *memcg, - int nid, bool noswap) -{ - struct lruvec *lruvec = mem_cgroup_lruvec(NODE_DATA(nid), memcg); - - if (lruvec_page_state(lruvec, NR_INACTIVE_FILE) || - lruvec_page_state(lruvec, NR_ACTIVE_FILE)) - return true; - if (noswap || !total_swap_pages) - return false; - if (lruvec_page_state(lruvec, NR_INACTIVE_ANON) || - lruvec_page_state(lruvec, NR_ACTIVE_ANON)) - return true; - return false; - -} - -/* - * Always updating the nodemask is not very good - even if we have an empty - * list or the wrong list here, we can start from some node and traverse all - * nodes based on the zonelist. So update the list loosely once per 10 secs. - * - */ -static void mem_cgroup_may_update_nodemask(struct mem_cgroup *memcg) -{ - int nid; - /* - * numainfo_events > 0 means there was at least NUMAINFO_EVENTS_TARGET - * pagein/pageout changes since the last update. - */ - if (!atomic_read(&memcg->numainfo_events)) - return; - if (atomic_inc_return(&memcg->numainfo_updating) > 1) - return; - - /* make a nodemask where this memcg uses memory from */ - memcg->scan_nodes = node_states[N_MEMORY]; - - for_each_node_mask(nid, node_states[N_MEMORY]) { - - if (!test_mem_cgroup_node_reclaimable(memcg, nid, false)) - node_clear(nid, memcg->scan_nodes); - } - - atomic_set(&memcg->numainfo_events, 0); - atomic_set(&memcg->numainfo_updating, 0); -} - -/* - * Selecting a node where we start reclaim from. Because what we need is just - * reducing usage counter, start from anywhere is O,K. Considering - * memory reclaim from current node, there are pros. and cons. - * - * Freeing memory from current node means freeing memory from a node which - * we'll use or we've used. So, it may make LRU bad. And if several threads - * hit limits, it will see a contention on a node. But freeing from remote - * node means more costs for memory reclaim because of memory latency. - * - * Now, we use round-robin. Better algorithm is welcomed. - */ -int mem_cgroup_select_victim_node(struct mem_cgroup *memcg) -{ - int node; - - mem_cgroup_may_update_nodemask(memcg); - node = memcg->last_scanned_node; - - node = next_node_in(node, memcg->scan_nodes); - /* - * mem_cgroup_may_update_nodemask might have seen no reclaimmable pages - * last time it really checked all the LRUs due to rate limiting. - * Fallback to the current node in that case for simplicity. - */ - if (unlikely(node == MAX_NUMNODES)) - node = numa_node_id(); - - memcg->last_scanned_node = node; - return node; -} -#else -int mem_cgroup_select_victim_node(struct mem_cgroup *memcg) -{ - return 0; -} -#endif - static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg, pg_data_t *pgdat, gfp_t gfp_mask, @@ -5073,7 +4962,6 @@ static struct mem_cgroup *mem_cgroup_alloc(void) goto fail; INIT_WORK(&memcg->high_work, high_work_func); - memcg->last_scanned_node = MAX_NUMNODES; INIT_LIST_HEAD(&memcg->oom_notify); mutex_init(&memcg->thresholds_lock); spin_lock_init(&memcg->move_lock); diff --git a/mm/vmscan.c b/mm/vmscan.c index ee4eecc7e1c2..2beff0e0dc7b 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3348,10 +3348,8 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, gfp_t gfp_mask, bool may_swap) { - struct zonelist *zonelist; unsigned long nr_reclaimed; unsigned long pflags; - int nid; unsigned int noreclaim_flag; struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), @@ -3364,16 +3362,14 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, .may_unmap = 1, .may_swap = may_swap, }; - - set_task_reclaim_state(current, &sc.reclaim_state); /* - * Unlike direct reclaim via alloc_pages(), memcg's reclaim doesn't - * take care of from where we get pages. So the node where we start the - * scan does not need to be the current node. + * Traverse the ZONELIST_FALLBACK zonelist of the current node to put + * equal pressure on all the nodes. This is based on the assumption that + * the reclaim does not bail out early. */ - nid = mem_cgroup_select_victim_node(memcg); + struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); - zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK]; + set_task_reclaim_state(current, &sc.reclaim_state); trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask); -- cgit v1.2.3-71-gd317 From b3d1411b6726ea6930222f8f12587d89762477c6 Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Sat, 30 Nov 2019 17:50:30 -0800 Subject: mm: emit tracepoint when RSS changes Useful to track how RSS is changing per TGID to detect spikes in RSS and memory hogs. Several Android teams have been using this patch in various kernel trees for half a year now. Many reported to me it is really useful so I'm posting it upstream. Initial patch developed by Tim Murray. Changes I made from original patch: o Prevent any additional space consumed by mm_struct. Regarding the fact that the RSS may change too often thus flooding the traces - note that, there is some "hysterisis" with this already. That is - We update the counter only if we receive 64 page faults due to SPLIT_RSS_ACCOUNTING. However, during zapping or copying of pte range, the RSS is updated immediately which can become noisy/flooding. In a previous discussion, we agreed that BPF or ftrace can be used to rate limit the signal if this becomes an issue. Also note that I added wrappers to trace_rss_stat to prevent compiler errors where linux/mm.h is included from tracing code, causing errors such as: CC kernel/trace/power-traces.o In file included from ./include/trace/define_trace.h:102, from ./include/trace/events/kmem.h:342, from ./include/linux/mm.h:31, from ./include/linux/ring_buffer.h:5, from ./include/linux/trace_events.h:6, from ./include/trace/events/power.h:12, from kernel/trace/power-traces.c:15: ./include/trace/trace_events.h:113:22: error: field `ent' has incomplete type struct trace_entry ent; \ Link: http://lore.kernel.org/r/20190903200905.198642-1-joel@joelfernandes.org Link: http://lkml.kernel.org/r/20191001172817.234886-1-joel@joelfernandes.org Co-developed-by: Tim Murray Signed-off-by: Tim Murray Signed-off-by: Joel Fernandes (Google) Acked-by: Michal Hocko Cc: Carmen Jackson Cc: Mayank Gupta Cc: Daniel Colascione Cc: Steven Rostedt (VMware) Cc: Minchan Kim Cc: "Aneesh Kumar K.V" Cc: Dan Williams Cc: Jerome Glisse Cc: Matthew Wilcox Cc: Ralph Campbell Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 14 +++++++++++--- include/trace/events/kmem.h | 21 +++++++++++++++++++++ mm/memory.c | 6 ++++++ 3 files changed, 38 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index f6fb714fa851..935383081397 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1643,19 +1643,27 @@ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member) return (unsigned long)val; } +void mm_trace_rss_stat(int member, long count); + static inline void add_mm_counter(struct mm_struct *mm, int member, long value) { - atomic_long_add(value, &mm->rss_stat.count[member]); + long count = atomic_long_add_return(value, &mm->rss_stat.count[member]); + + mm_trace_rss_stat(member, count); } static inline void inc_mm_counter(struct mm_struct *mm, int member) { - atomic_long_inc(&mm->rss_stat.count[member]); + long count = atomic_long_inc_return(&mm->rss_stat.count[member]); + + mm_trace_rss_stat(member, count); } static inline void dec_mm_counter(struct mm_struct *mm, int member) { - atomic_long_dec(&mm->rss_stat.count[member]); + long count = atomic_long_dec_return(&mm->rss_stat.count[member]); + + mm_trace_rss_stat(member, count); } /* Optimized variant when page is already known not to be PageAnon */ diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index 69e8bb8963db..5a0666bfcf85 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -316,6 +316,27 @@ TRACE_EVENT(mm_page_alloc_extfrag, __entry->change_ownership) ); +TRACE_EVENT(rss_stat, + + TP_PROTO(int member, + long count), + + TP_ARGS(member, count), + + TP_STRUCT__entry( + __field(int, member) + __field(long, size) + ), + + TP_fast_assign( + __entry->member = member; + __entry->size = (count << PAGE_SHIFT); + ), + + TP_printk("member=%d size=%ldB", + __entry->member, + __entry->size) + ); #endif /* _TRACE_KMEM_H */ /* This part must be outside protection */ diff --git a/mm/memory.c b/mm/memory.c index 9ea917e28ef4..57c910aaba45 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -72,6 +72,8 @@ #include #include +#include + #include #include #include @@ -152,6 +154,10 @@ static int __init init_zero_pfn(void) } core_initcall(init_zero_pfn); +void mm_trace_rss_stat(int member, long count) +{ + trace_rss_stat(member, count); +} #if defined(SPLIT_RSS_COUNTING) -- cgit v1.2.3-71-gd317 From e4dcad204d3a281be6f8573e0a82648a4ad84e69 Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Sat, 30 Nov 2019 17:50:33 -0800 Subject: rss_stat: add support to detect RSS updates of external mm When a process updates the RSS of a different process, the rss_stat tracepoint appears in the context of the process doing the update. This can confuse userspace that the RSS of process doing the update is updated, while in reality a different process's RSS was updated. This issue happens in reclaim paths such as with direct reclaim or background reclaim. This patch adds more information to the tracepoint about whether the mm being updated belongs to the current process's context (curr field). We also include a hash of the mm pointer so that the process who the mm belongs to can be uniquely identified (mm_id field). Also vsprintf.c is refactored a bit to allow reuse of hashing code. [akpm@linux-foundation.org: remove unused local `str'] [joelaf@google.com: inline call to ptr_to_hashval] Link: http://lore.kernel.org/r/20191113153816.14b95acd@gandalf.local.home Link: http://lkml.kernel.org/r/20191114164622.GC233237@google.com Link: http://lkml.kernel.org/r/20191106024452.81923-1-joel@joelfernandes.org Signed-off-by: Joel Fernandes (Google) Reported-by: Ioannis Ilkos Acked-by: Petr Mladek [lib/vsprintf.c] Cc: Tim Murray Cc: Michal Hocko Cc: Carmen Jackson Cc: Mayank Gupta Cc: Daniel Colascione Cc: Steven Rostedt (VMware) Cc: Minchan Kim Cc: "Aneesh Kumar K.V" Cc: Dan Williams Cc: Jerome Glisse Cc: Matthew Wilcox Cc: Ralph Campbell Cc: Vlastimil Babka Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 8 ++++---- include/linux/string.h | 2 ++ include/trace/events/kmem.h | 32 +++++++++++++++++++++++++++++--- lib/vsprintf.c | 40 +++++++++++++++++++++++++++++----------- mm/memory.c | 4 ++-- 5 files changed, 66 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 935383081397..b5b2523c80af 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1643,27 +1643,27 @@ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member) return (unsigned long)val; } -void mm_trace_rss_stat(int member, long count); +void mm_trace_rss_stat(struct mm_struct *mm, int member, long count); static inline void add_mm_counter(struct mm_struct *mm, int member, long value) { long count = atomic_long_add_return(value, &mm->rss_stat.count[member]); - mm_trace_rss_stat(member, count); + mm_trace_rss_stat(mm, member, count); } static inline void inc_mm_counter(struct mm_struct *mm, int member) { long count = atomic_long_inc_return(&mm->rss_stat.count[member]); - mm_trace_rss_stat(member, count); + mm_trace_rss_stat(mm, member, count); } static inline void dec_mm_counter(struct mm_struct *mm, int member) { long count = atomic_long_dec_return(&mm->rss_stat.count[member]); - mm_trace_rss_stat(member, count); + mm_trace_rss_stat(mm, member, count); } /* Optimized variant when page is already known not to be PageAnon */ diff --git a/include/linux/string.h b/include/linux/string.h index b6ccdc2c7f02..02894e417565 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -216,6 +216,8 @@ int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) __printf(3, 4); extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, const void *from, size_t available); +int ptr_to_hashval(const void *ptr, unsigned long *hashval_out); + /** * strstarts - does @str start with @prefix? * @str: string to examine diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index 5a0666bfcf85..ad7e642bd497 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -316,24 +316,50 @@ TRACE_EVENT(mm_page_alloc_extfrag, __entry->change_ownership) ); +/* + * Required for uniquely and securely identifying mm in rss_stat tracepoint. + */ +#ifndef __PTR_TO_HASHVAL +static unsigned int __maybe_unused mm_ptr_to_hash(const void *ptr) +{ + int ret; + unsigned long hashval; + + ret = ptr_to_hashval(ptr, &hashval); + if (ret) + return 0; + + /* The hashed value is only 32-bit */ + return (unsigned int)hashval; +} +#define __PTR_TO_HASHVAL +#endif + TRACE_EVENT(rss_stat, - TP_PROTO(int member, + TP_PROTO(struct mm_struct *mm, + int member, long count), - TP_ARGS(member, count), + TP_ARGS(mm, member, count), TP_STRUCT__entry( + __field(unsigned int, mm_id) + __field(unsigned int, curr) __field(int, member) __field(long, size) ), TP_fast_assign( + __entry->mm_id = mm_ptr_to_hash(mm); + __entry->curr = !!(current->mm == mm); __entry->member = member; __entry->size = (count << PAGE_SHIFT); ), - TP_printk("member=%d size=%ldB", + TP_printk("mm_id=%u curr=%d member=%d size=%ldB", + __entry->mm_id, + __entry->curr, __entry->member, __entry->size) ); diff --git a/lib/vsprintf.c b/lib/vsprintf.c index dee8fc467fcf..7c488a1ce318 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -761,11 +761,38 @@ static int __init initialize_ptr_random(void) early_initcall(initialize_ptr_random); /* Maps a pointer to a 32 bit unique identifier. */ +static inline int __ptr_to_hashval(const void *ptr, unsigned long *hashval_out) +{ + unsigned long hashval; + + if (static_branch_unlikely(¬_filled_random_ptr_key)) + return -EAGAIN; + +#ifdef CONFIG_64BIT + hashval = (unsigned long)siphash_1u64((u64)ptr, &ptr_key); + /* + * Mask off the first 32 bits, this makes explicit that we have + * modified the address (and 32 bits is plenty for a unique ID). + */ + hashval = hashval & 0xffffffff; +#else + hashval = (unsigned long)siphash_1u32((u32)ptr, &ptr_key); +#endif + *hashval_out = hashval; + return 0; +} + +int ptr_to_hashval(const void *ptr, unsigned long *hashval_out) +{ + return __ptr_to_hashval(ptr, hashval_out); +} + static char *ptr_to_id(char *buf, char *end, const void *ptr, struct printf_spec spec) { const char *str = sizeof(ptr) == 8 ? "(____ptrval____)" : "(ptrval)"; unsigned long hashval; + int ret; /* When debugging early boot use non-cryptographically secure hash. */ if (unlikely(debug_boot_weak_hash)) { @@ -773,22 +800,13 @@ static char *ptr_to_id(char *buf, char *end, const void *ptr, return pointer_string(buf, end, (const void *)hashval, spec); } - if (static_branch_unlikely(¬_filled_random_ptr_key)) { + ret = __ptr_to_hashval(ptr, &hashval); + if (ret) { spec.field_width = 2 * sizeof(ptr); /* string length must be less than default_width */ return error_string(buf, end, str, spec); } -#ifdef CONFIG_64BIT - hashval = (unsigned long)siphash_1u64((u64)ptr, &ptr_key); - /* - * Mask off the first 32 bits, this makes explicit that we have - * modified the address (and 32 bits is plenty for a unique ID). - */ - hashval = hashval & 0xffffffff; -#else - hashval = (unsigned long)siphash_1u32((u32)ptr, &ptr_key); -#endif return pointer_string(buf, end, (const void *)hashval, spec); } diff --git a/mm/memory.c b/mm/memory.c index 57c910aaba45..62b5cce653f6 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -154,9 +154,9 @@ static int __init init_zero_pfn(void) } core_initcall(init_zero_pfn); -void mm_trace_rss_stat(int member, long count) +void mm_trace_rss_stat(struct mm_struct *mm, int member, long count) { - trace_rss_stat(member, count); + trace_rss_stat(mm, member, count); } #if defined(SPLIT_RSS_COUNTING) -- cgit v1.2.3-71-gd317 From bf1a12a8095615c9486f5463ca473d2d69ff6952 Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Sat, 30 Nov 2019 17:51:29 -0800 Subject: mm: move the backup x_devmap() functions to asm-generic/pgtable.h The asm-generic/pgtable.h include file appears to be the correct place for the backup x_devmap() inline functions. Moving them here is also necessary if we want to include x_devmap() in the [pmd|pud]_unstable functions. So move the x_devmap() functions to asm-generic/pgtable.h Link: http://lkml.kernel.org/r/20191115115808.21181-1-thomas_os@shipmail.org Signed-off-by: Thomas Hellstrom Cc: Arnd Bergmann Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/pgtable.h | 15 +++++++++++++++ include/linux/mm.h | 15 --------------- 2 files changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 9cdcbc7c0b7b..3127f9028f54 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -914,6 +914,21 @@ static inline int pud_write(pud_t pud) } #endif /* pud_write */ +#if !defined(CONFIG_ARCH_HAS_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE) +static inline int pmd_devmap(pmd_t pmd) +{ + return 0; +} +static inline int pud_devmap(pud_t pud) +{ + return 0; +} +static inline int pgd_devmap(pgd_t pgd) +{ + return 0; +} +#endif + #if !defined(CONFIG_TRANSPARENT_HUGEPAGE) || \ (defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ !defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)) diff --git a/include/linux/mm.h b/include/linux/mm.h index b5b2523c80af..06b51d8728ec 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -564,21 +564,6 @@ int vma_is_stack_for_current(struct vm_area_struct *vma); struct mmu_gather; struct inode; -#if !defined(CONFIG_ARCH_HAS_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE) -static inline int pmd_devmap(pmd_t pmd) -{ - return 0; -} -static inline int pud_devmap(pud_t pud) -{ - return 0; -} -static inline int pgd_devmap(pgd_t pgd) -{ - return 0; -} -#endif - /* * FIXME: take this include out, include page-flags.h in * files which need it (119 of them) -- cgit v1.2.3-71-gd317 From e1608f3fa857b600045b6df7f7dadc70eeaa4496 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 29 Nov 2019 23:29:11 +0100 Subject: bpf: Avoid setting bpf insns pages read-only when prog is jited For the case where the interpreter is compiled out or when the prog is jited it is completely unnecessary to set the BPF insn pages as read-only. In fact, on frequent churn of BPF programs, it could lead to performance degradation of the system over time since it would break the direct map down to 4k pages when calling set_memory_ro() for the insn buffer on x86-64 / arm64 and there is no reverse operation. Thus, avoid breaking up large pages for data maps, and only limit this to the module range used by the JIT where it is necessary to set the image read-only and executable. Suggested-by: Peter Zijlstra Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20191129222911.3710-1-daniel@iogearbox.net --- include/linux/filter.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 1b1e8b8f88da..a141cb07e76a 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -776,8 +776,12 @@ bpf_ctx_narrow_access_offset(u32 off, u32 size, u32 size_default) static inline void bpf_prog_lock_ro(struct bpf_prog *fp) { - set_vm_flush_reset_perms(fp); - set_memory_ro((unsigned long)fp, fp->pages); +#ifndef CONFIG_BPF_JIT_ALWAYS_ON + if (!fp->jited) { + set_vm_flush_reset_perms(fp); + set_memory_ro((unsigned long)fp, fp->pages); + } +#endif } static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) -- cgit v1.2.3-71-gd317 From feec24a6139d4640c6ef344e0271a8cd4d509e60 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Sat, 30 Nov 2019 17:53:38 -0800 Subject: mm, soft-offline: convert parameter to pfn Currently soft_offline_page() receives struct page, and its sibling memory_failure() receives pfn. This discrepancy looks weird and makes precheck on pfn validity tricky. So let's align them. Link: http://lkml.kernel.org/r/20191016234706.GA5493@www9186uo.sakura.ne.jp Signed-off-by: Naoya Horiguchi Acked-by: Andrew Morton Cc: David Hildenbrand Cc: Michal Hocko Cc: Oscar Salvador Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/memory.c | 7 +------ include/linux/mm.h | 2 +- mm/madvise.c | 2 +- mm/memory-failure.c | 19 +++++++++---------- 4 files changed, 12 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 84c4e1f72cbd..d65ecdeb83e8 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -538,12 +538,7 @@ static ssize_t soft_offline_page_store(struct device *dev, if (kstrtoull(buf, 0, &pfn) < 0) return -EINVAL; pfn >>= PAGE_SHIFT; - if (!pfn_valid(pfn)) - return -ENXIO; - /* Only online pages can be soft-offlined (esp., not ZONE_DEVICE). */ - if (!pfn_to_online_page(pfn)) - return -EIO; - ret = soft_offline_page(pfn_to_page(pfn), 0); + ret = soft_offline_page(pfn, 0); return ret == 0 ? count : ret; } diff --git a/include/linux/mm.h b/include/linux/mm.h index 06b51d8728ec..19a0e687878a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2773,7 +2773,7 @@ extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p, int access); extern atomic_long_t num_poisoned_pages __read_mostly; -extern int soft_offline_page(struct page *page, int flags); +extern int soft_offline_page(unsigned long pfn, int flags); /* diff --git a/mm/madvise.c b/mm/madvise.c index 94c343b4c968..63e130800570 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -895,7 +895,7 @@ static int madvise_inject_error(int behavior, pr_info("Soft offlining pfn %#lx at process virtual address %#lx\n", pfn, start); - ret = soft_offline_page(page, MF_COUNT_INCREASED); + ret = soft_offline_page(pfn, MF_COUNT_INCREASED); if (ret) return ret; continue; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 05c8c6df25e6..af2712004a4d 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1476,7 +1476,7 @@ static void memory_failure_work_func(struct work_struct *work) if (!gotten) break; if (entry.flags & MF_SOFT_OFFLINE) - soft_offline_page(pfn_to_page(entry.pfn), entry.flags); + soft_offline_page(entry.pfn, entry.flags); else memory_failure(entry.pfn, entry.flags); } @@ -1857,7 +1857,7 @@ static int soft_offline_free_page(struct page *page) /** * soft_offline_page - Soft offline a page. - * @page: page to offline + * @pfn: pfn to soft-offline * @flags: flags. Same as memory_failure(). * * Returns 0 on success, otherwise negated errno. @@ -1877,18 +1877,17 @@ static int soft_offline_free_page(struct page *page) * This is not a 100% solution for all memory, but tries to be * ``good enough'' for the majority of memory. */ -int soft_offline_page(struct page *page, int flags) +int soft_offline_page(unsigned long pfn, int flags) { int ret; - unsigned long pfn = page_to_pfn(page); + struct page *page; - if (is_zone_device_page(page)) { - pr_debug_ratelimited("soft_offline: %#lx page is device page\n", - pfn); - if (flags & MF_COUNT_INCREASED) - put_page(page); + if (!pfn_valid(pfn)) + return -ENXIO; + /* Only online pages can be soft-offlined (esp., not ZONE_DEVICE). */ + page = pfn_to_online_page(pfn); + if (!page) return -EIO; - } if (PageHWPoison(page)) { pr_info("soft offline: %#lx page already poisoned\n", pfn); -- cgit v1.2.3-71-gd317 From 18db149120c106cf2b1a2595f82f3229f9d223b8 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Sat, 30 Nov 2019 17:53:51 -0800 Subject: mm/memory_hotplug: export generic_online_page() Patch series "mm/memory_hotplug: Export generic_online_page()". Let's replace the __online_page...() functions by generic_online_page(). Hyper-V only wants to delay the actual onlining of un-backed pages, so we can simpy re-use the generic function. This patch (of 3): Let's expose generic_online_page() so online_page_callback users can simply fall back to the generic implementation when actually deciding to online the pages. Link: http://lkml.kernel.org/r/20190909114830.662-2-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Michal Hocko Cc: Oscar Salvador Cc: Pavel Tatashin Cc: Dan Williams Cc: Wei Yang Cc: Qian Cai Cc: Haiyang Zhang Cc: "K. Y. Srinivasan" Cc: Sasha Levin Cc: Stephen Hemminger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 1 + mm/memory_hotplug.c | 5 ++--- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index f46ea71b4ffd..3b3b1c7641fe 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -102,6 +102,7 @@ extern unsigned long __offline_isolated_pages(unsigned long start_pfn, typedef void (*online_page_callback_t)(struct page *page, unsigned int order); +extern void generic_online_page(struct page *page, unsigned int order); extern int set_online_page_callback(online_page_callback_t callback); extern int restore_online_page_callback(online_page_callback_t callback); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 8b485900d941..690426fdb40a 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -49,8 +49,6 @@ * and restore_online_page_callback() for generic callback restore. */ -static void generic_online_page(struct page *page, unsigned int order); - static online_page_callback_t online_page_callback = generic_online_page; static DEFINE_MUTEX(online_page_callback_lock); @@ -617,7 +615,7 @@ void __online_page_free(struct page *page) } EXPORT_SYMBOL_GPL(__online_page_free); -static void generic_online_page(struct page *page, unsigned int order) +void generic_online_page(struct page *page, unsigned int order) { kernel_map_pages(page, 1 << order, 1); __free_pages_core(page, order); @@ -627,6 +625,7 @@ static void generic_online_page(struct page *page, unsigned int order) totalhigh_pages_add(1UL << order); #endif } +EXPORT_SYMBOL_GPL(generic_online_page); static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages, void *arg) -- cgit v1.2.3-71-gd317 From 0ec47097434847c0c3a3bb7287feb46386a62720 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Sat, 30 Nov 2019 17:54:00 -0800 Subject: mm/memory_hotplug: remove __online_page_free() and __online_page_increment_counters() Let's drop the now unused functions. Link: http://lkml.kernel.org/r/20190909114830.662-4-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Michal Hocko Cc: Oscar Salvador Cc: Pavel Tatashin Cc: Wei Yang Cc: Dan Williams Cc: Qian Cai Cc: Haiyang Zhang Cc: "K. Y. Srinivasan" Cc: Sasha Levin Cc: Stephen Hemminger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 2 -- mm/memory_hotplug.c | 12 ------------ 2 files changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 3b3b1c7641fe..fb638cadf8c0 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -107,8 +107,6 @@ extern int set_online_page_callback(online_page_callback_t callback); extern int restore_online_page_callback(online_page_callback_t callback); extern void __online_page_set_limits(struct page *page); -extern void __online_page_increment_counters(struct page *page); -extern void __online_page_free(struct page *page); extern int try_online_node(int nid); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 690426fdb40a..5e9d18849a0c 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -603,18 +603,6 @@ void __online_page_set_limits(struct page *page) } EXPORT_SYMBOL_GPL(__online_page_set_limits); -void __online_page_increment_counters(struct page *page) -{ - adjust_managed_page_count(page, 1); -} -EXPORT_SYMBOL_GPL(__online_page_increment_counters); - -void __online_page_free(struct page *page) -{ - __free_reserved_page(page); -} -EXPORT_SYMBOL_GPL(__online_page_free); - void generic_online_page(struct page *page, unsigned int order) { kernel_map_pages(page, 1 << order, 1); -- cgit v1.2.3-71-gd317 From 756d25be457fc5497da0ceee0f3d0c9eb4d8535d Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Sat, 30 Nov 2019 17:54:07 -0800 Subject: mm/page_isolation.c: convert SKIP_HWPOISON to MEMORY_OFFLINE We have two types of users of page isolation: 1. Memory offlining: Offline memory so it can be unplugged. Memory won't be touched. 2. Memory allocation: Allocate memory (e.g., alloc_contig_range()) to become the owner of the memory and make use of it. For example, in case we want to offline memory, we can ignore (skip over) PageHWPoison() pages, as the memory won't get used. We can allow to offline memory. In contrast, we don't want to allow to allocate such memory. Let's generalize the approach so we can special case other types of pages we want to skip over in case we offline memory. While at it, also pass the same flags to test_pages_isolated(). Link: http://lkml.kernel.org/r/20191021172353.3056-3-david@redhat.com Signed-off-by: David Hildenbrand Suggested-by: Michal Hocko Acked-by: Michal Hocko Cc: Oscar Salvador Cc: Anshuman Khandual Cc: David Hildenbrand Cc: Pingfan Liu Cc: Qian Cai Cc: Pavel Tatashin Cc: Dan Williams Cc: Vlastimil Babka Cc: Mel Gorman Cc: Mike Rapoport Cc: Alexander Duyck Cc: Mike Rapoport Cc: Pavel Tatashin Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-isolation.h | 4 ++-- mm/memory_hotplug.c | 8 +++++--- mm/page_alloc.c | 4 ++-- mm/page_isolation.c | 12 ++++++------ 4 files changed, 15 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 1099c2fee20f..6861df759fad 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -30,7 +30,7 @@ static inline bool is_migrate_isolate(int migratetype) } #endif -#define SKIP_HWPOISON 0x1 +#define MEMORY_OFFLINE 0x1 #define REPORT_FAILURE 0x2 bool has_unmovable_pages(struct zone *zone, struct page *page, int count, @@ -58,7 +58,7 @@ undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, * Test all pages in [start_pfn, end_pfn) are isolated or not. */ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, - bool skip_hwpoisoned_pages); + int isol_flags); struct page *alloc_migrate_target(struct page *page, unsigned long private); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 929d4209e78b..84ab3298cce9 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1187,7 +1187,8 @@ static bool is_pageblock_removable_nolock(unsigned long pfn) if (!zone_spans_pfn(zone, pfn)) return false; - return !has_unmovable_pages(zone, page, 0, MIGRATE_MOVABLE, SKIP_HWPOISON); + return !has_unmovable_pages(zone, page, 0, MIGRATE_MOVABLE, + MEMORY_OFFLINE); } /* Checks if this range of memory is likely to be hot-removable. */ @@ -1402,7 +1403,8 @@ static int check_pages_isolated_cb(unsigned long start_pfn, unsigned long nr_pages, void *data) { - return test_pages_isolated(start_pfn, start_pfn + nr_pages, true); + return test_pages_isolated(start_pfn, start_pfn + nr_pages, + MEMORY_OFFLINE); } static int __init cmdline_parse_movable_node(char *p) @@ -1513,7 +1515,7 @@ static int __ref __offline_pages(unsigned long start_pfn, /* set above range as isolated */ ret = start_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE, - SKIP_HWPOISON | REPORT_FAILURE); + MEMORY_OFFLINE | REPORT_FAILURE); if (ret < 0) { reason = "failure to isolate range"; goto failed_removal; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 293c8c145415..c289b02aaa3b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8261,7 +8261,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, * The HWPoisoned page may be not in buddy system, and * page_count() is not 0. */ - if ((flags & SKIP_HWPOISON) && PageHWPoison(page)) + if ((flags & MEMORY_OFFLINE) && PageHWPoison(page)) continue; if (__PageMovable(page)) @@ -8477,7 +8477,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, } /* Make sure the range is really isolated. */ - if (test_pages_isolated(outer_start, end, false)) { + if (test_pages_isolated(outer_start, end, 0)) { pr_info_ratelimited("%s: [%lx, %lx) PFNs busy\n", __func__, outer_start, end); ret = -EBUSY; diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 89c19c0feadb..04ee1663cdbe 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -168,7 +168,8 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages) * @migratetype: Migrate type to set in error recovery. * @flags: The following flags are allowed (they can be combined in * a bit mask) - * SKIP_HWPOISON - ignore hwpoison pages + * MEMORY_OFFLINE - isolate to offline (!allocate) memory + * e.g., skip over PageHWPoison() pages * REPORT_FAILURE - report details about the failure to * isolate the range * @@ -257,7 +258,7 @@ void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, */ static unsigned long __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn, - bool skip_hwpoisoned_pages) + int flags) { struct page *page; @@ -274,7 +275,7 @@ __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn, * simple way to verify that as VM_BUG_ON(), though. */ pfn += 1 << page_order(page); - else if (skip_hwpoisoned_pages && PageHWPoison(page)) + else if ((flags & MEMORY_OFFLINE) && PageHWPoison(page)) /* A HWPoisoned page cannot be also PageBuddy */ pfn++; else @@ -286,7 +287,7 @@ __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn, /* Caller should ensure that requested range is in a single zone */ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, - bool skip_hwpoisoned_pages) + int isol_flags) { unsigned long pfn, flags; struct page *page; @@ -308,8 +309,7 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, /* Check all pages are free or marked as ISOLATED */ zone = page_zone(page); spin_lock_irqsave(&zone->lock, flags); - pfn = __test_page_isolated_in_pageblock(start_pfn, end_pfn, - skip_hwpoisoned_pages); + pfn = __test_page_isolated_in_pageblock(start_pfn, end_pfn, isol_flags); spin_unlock_irqrestore(&zone->lock, flags); trace_test_pages_isolated(start_pfn, end_pfn, pfn); -- cgit v1.2.3-71-gd317 From aba9817da150e9dcf4c599c0508c38d1971d66e1 Mon Sep 17 00:00:00 2001 From: "Ben Dooks (Codethink)" Date: Sat, 30 Nov 2019 17:54:10 -0800 Subject: include/linux/memory_hotplug.h: move definitions of {set,clear}_zone_contiguous The {set,clear}_zone_contiguous are built whatever the configuratoon so move the definitions outside the current ifdef to avoid the following compiler warnings: mm/page_alloc.c:1550:6: warning: no previous prototype for 'set_zone_contiguous' [-Wmissing-prototypes] mm/page_alloc.c:1571:6: warning: no previous prototype for 'clear_zone_contiguous' [-Wmissing-prototypes] Link: http://lkml.kernel.org/r/20191106123911.7435-1-ben.dooks@codethink.co.uk Signed-off-by: Ben Dooks (Codethink) Acked-by: Michal Hocko Reviewed-by: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index fb638cadf8c0..101d97e7e2ac 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -228,9 +228,6 @@ void put_online_mems(void); void mem_hotplug_begin(void); void mem_hotplug_done(void); -extern void set_zone_contiguous(struct zone *zone); -extern void clear_zone_contiguous(struct zone *zone); - #else /* ! CONFIG_MEMORY_HOTPLUG */ #define pfn_to_online_page(pfn) \ ({ \ @@ -338,6 +335,9 @@ static inline int remove_memory(int nid, u64 start, u64 size) static inline void __remove_memory(int nid, u64 start, u64 size) {} #endif /* CONFIG_MEMORY_HOTREMOVE */ +extern void set_zone_contiguous(struct zone *zone); +extern void clear_zone_contiguous(struct zone *zone); + extern void __ref free_area_init_core_hotplug(int nid); extern int __add_memory(int nid, u64 start, u64 size); extern int add_memory(int nid, u64 start, u64 size); -- cgit v1.2.3-71-gd317 From 3c5c3cfb9ef4da957e3357a2bd36f76ee34c0862 Mon Sep 17 00:00:00 2001 From: Daniel Axtens Date: Sat, 30 Nov 2019 17:54:50 -0800 Subject: kasan: support backing vmalloc space with real shadow memory Patch series "kasan: support backing vmalloc space with real shadow memory", v11. Currently, vmalloc space is backed by the early shadow page. This means that kasan is incompatible with VMAP_STACK. This series provides a mechanism to back vmalloc space with real, dynamically allocated memory. I have only wired up x86, because that's the only currently supported arch I can work with easily, but it's very easy to wire up other architectures, and it appears that there is some work-in-progress code to do this on arm64 and s390. This has been discussed before in the context of VMAP_STACK: - https://bugzilla.kernel.org/show_bug.cgi?id=202009 - https://lkml.org/lkml/2018/7/22/198 - https://lkml.org/lkml/2019/7/19/822 In terms of implementation details: Most mappings in vmalloc space are small, requiring less than a full page of shadow space. Allocating a full shadow page per mapping would therefore be wasteful. Furthermore, to ensure that different mappings use different shadow pages, mappings would have to be aligned to KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE. Instead, share backing space across multiple mappings. Allocate a backing page when a mapping in vmalloc space uses a particular page of the shadow region. This page can be shared by other vmalloc mappings later on. We hook in to the vmap infrastructure to lazily clean up unused shadow memory. Testing with test_vmalloc.sh on an x86 VM with 2 vCPUs shows that: - Turning on KASAN, inline instrumentation, without vmalloc, introuduces a 4.1x-4.2x slowdown in vmalloc operations. - Turning this on introduces the following slowdowns over KASAN: * ~1.76x slower single-threaded (test_vmalloc.sh performance) * ~2.18x slower when both cpus are performing operations simultaneously (test_vmalloc.sh sequential_test_order=1) This is unfortunate but given that this is a debug feature only, not the end of the world. The benchmarks are also a stress-test for the vmalloc subsystem: they're not indicative of an overall 2x slowdown! This patch (of 4): Hook into vmalloc and vmap, and dynamically allocate real shadow memory to back the mappings. Most mappings in vmalloc space are small, requiring less than a full page of shadow space. Allocating a full shadow page per mapping would therefore be wasteful. Furthermore, to ensure that different mappings use different shadow pages, mappings would have to be aligned to KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE. Instead, share backing space across multiple mappings. Allocate a backing page when a mapping in vmalloc space uses a particular page of the shadow region. This page can be shared by other vmalloc mappings later on. We hook in to the vmap infrastructure to lazily clean up unused shadow memory. To avoid the difficulties around swapping mappings around, this code expects that the part of the shadow region that covers the vmalloc space will not be covered by the early shadow page, but will be left unmapped. This will require changes in arch-specific code. This allows KASAN with VMAP_STACK, and may be helpful for architectures that do not have a separate module space (e.g. powerpc64, which I am currently working on). It also allows relaxing the module alignment back to PAGE_SIZE. Testing with test_vmalloc.sh on an x86 VM with 2 vCPUs shows that: - Turning on KASAN, inline instrumentation, without vmalloc, introuduces a 4.1x-4.2x slowdown in vmalloc operations. - Turning this on introduces the following slowdowns over KASAN: * ~1.76x slower single-threaded (test_vmalloc.sh performance) * ~2.18x slower when both cpus are performing operations simultaneously (test_vmalloc.sh sequential_test_order=3D1) This is unfortunate but given that this is a debug feature only, not the end of the world. The full benchmark results are: Performance No KASAN KASAN original x baseline KASAN vmalloc x baseline x KASAN fix_size_alloc_test 662004 11404956 17.23 19144610 28.92 1.68 full_fit_alloc_test 710950 12029752 16.92 13184651 18.55 1.10 long_busy_list_alloc_test 9431875 43990172 4.66 82970178 8.80 1.89 random_size_alloc_test 5033626 23061762 4.58 47158834 9.37 2.04 fix_align_alloc_test 1252514 15276910 12.20 31266116 24.96 2.05 random_size_align_alloc_te 1648501 14578321 8.84 25560052 15.51 1.75 align_shift_alloc_test 147 830 5.65 5692 38.72 6.86 pcpu_alloc_test 80732 125520 1.55 140864 1.74 1.12 Total Cycles 119240774314 763211341128 6.40 1390338696894 11.66 1.82 Sequential, 2 cpus No KASAN KASAN original x baseline KASAN vmalloc x baseline x KASAN fix_size_alloc_test 1423150 14276550 10.03 27733022 19.49 1.94 full_fit_alloc_test 1754219 14722640 8.39 15030786 8.57 1.02 long_busy_list_alloc_test 11451858 52154973 4.55 107016027 9.34 2.05 random_size_alloc_test 5989020 26735276 4.46 68885923 11.50 2.58 fix_align_alloc_test 2050976 20166900 9.83 50491675 24.62 2.50 random_size_align_alloc_te 2858229 17971700 6.29 38730225 13.55 2.16 align_shift_alloc_test 405 6428 15.87 26253 64.82 4.08 pcpu_alloc_test 127183 151464 1.19 216263 1.70 1.43 Total Cycles 54181269392 308723699764 5.70 650772566394 12.01 2.11 fix_size_alloc_test 1420404 14289308 10.06 27790035 19.56 1.94 full_fit_alloc_test 1736145 14806234 8.53 15274301 8.80 1.03 long_busy_list_alloc_test 11404638 52270785 4.58 107550254 9.43 2.06 random_size_alloc_test 6017006 26650625 4.43 68696127 11.42 2.58 fix_align_alloc_test 2045504 20280985 9.91 50414862 24.65 2.49 random_size_align_alloc_te 2845338 17931018 6.30 38510276 13.53 2.15 align_shift_alloc_test 472 3760 7.97 9656 20.46 2.57 pcpu_alloc_test 118643 132732 1.12 146504 1.23 1.10 Total Cycles 54040011688 309102805492 5.72 651325675652 12.05 2.11 [dja@axtens.net: fixups] Link: http://lkml.kernel.org/r/20191120052719.7201-1-dja@axtens.net Link: https://bugzilla.kernel.org/show_bug.cgi?id=3D202009 Link: http://lkml.kernel.org/r/20191031093909.9228-2-dja@axtens.net Signed-off-by: Mark Rutland [shadow rework] Signed-off-by: Daniel Axtens Co-developed-by: Mark Rutland Acked-by: Vasily Gorbik Reviewed-by: Andrey Ryabinin Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Christophe Leroy Cc: Qian Cai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/dev-tools/kasan.rst | 63 +++++++++++ include/linux/kasan.h | 31 +++++ include/linux/moduleloader.h | 2 +- include/linux/vmalloc.h | 12 ++ lib/Kconfig.kasan | 16 +++ mm/kasan/common.c | 233 ++++++++++++++++++++++++++++++++++++++ mm/kasan/generic_report.c | 3 + mm/kasan/kasan.h | 1 + mm/vmalloc.c | 56 +++++++-- 9 files changed, 408 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst index 525296121d89..e4d66e7c50de 100644 --- a/Documentation/dev-tools/kasan.rst +++ b/Documentation/dev-tools/kasan.rst @@ -218,3 +218,66 @@ brk handler is used to print bug reports. A potential expansion of this mode is a hardware tag-based mode, which would use hardware memory tagging support instead of compiler instrumentation and manual shadow memory manipulation. + +What memory accesses are sanitised by KASAN? +-------------------------------------------- + +The kernel maps memory in a number of different parts of the address +space. This poses something of a problem for KASAN, which requires +that all addresses accessed by instrumented code have a valid shadow +region. + +The range of kernel virtual addresses is large: there is not enough +real memory to support a real shadow region for every address that +could be accessed by the kernel. + +By default +~~~~~~~~~~ + +By default, architectures only map real memory over the shadow region +for the linear mapping (and potentially other small areas). For all +other areas - such as vmalloc and vmemmap space - a single read-only +page is mapped over the shadow area. This read-only shadow page +declares all memory accesses as permitted. + +This presents a problem for modules: they do not live in the linear +mapping, but in a dedicated module space. By hooking in to the module +allocator, KASAN can temporarily map real shadow memory to cover +them. This allows detection of invalid accesses to module globals, for +example. + +This also creates an incompatibility with ``VMAP_STACK``: if the stack +lives in vmalloc space, it will be shadowed by the read-only page, and +the kernel will fault when trying to set up the shadow data for stack +variables. + +CONFIG_KASAN_VMALLOC +~~~~~~~~~~~~~~~~~~~~ + +With ``CONFIG_KASAN_VMALLOC``, KASAN can cover vmalloc space at the +cost of greater memory usage. Currently this is only supported on x86. + +This works by hooking into vmalloc and vmap, and dynamically +allocating real shadow memory to back the mappings. + +Most mappings in vmalloc space are small, requiring less than a full +page of shadow space. Allocating a full shadow page per mapping would +therefore be wasteful. Furthermore, to ensure that different mappings +use different shadow pages, mappings would have to be aligned to +``KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE``. + +Instead, we share backing space across multiple mappings. We allocate +a backing page when a mapping in vmalloc space uses a particular page +of the shadow region. This page can be shared by other vmalloc +mappings later on. + +We hook in to the vmap infrastructure to lazily clean up unused shadow +memory. + +To avoid the difficulties around swapping mappings around, we expect +that the part of the shadow region that covers the vmalloc space will +not be covered by the early shadow page, but will be left +unmapped. This will require changes in arch-specific code. + +This allows ``VMAP_STACK`` support on x86, and can simplify support of +architectures that do not have a fixed module region. diff --git a/include/linux/kasan.h b/include/linux/kasan.h index cc8a03cc9674..4f404c565db1 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -70,8 +70,18 @@ struct kasan_cache { int free_meta_offset; }; +/* + * These functions provide a special case to support backing module + * allocations with real shadow memory. With KASAN vmalloc, the special + * case is unnecessary, as the work is handled in the generic case. + */ +#ifndef CONFIG_KASAN_VMALLOC int kasan_module_alloc(void *addr, size_t size); void kasan_free_shadow(const struct vm_struct *vm); +#else +static inline int kasan_module_alloc(void *addr, size_t size) { return 0; } +static inline void kasan_free_shadow(const struct vm_struct *vm) {} +#endif int kasan_add_zero_shadow(void *start, unsigned long size); void kasan_remove_zero_shadow(void *start, unsigned long size); @@ -194,4 +204,25 @@ static inline void *kasan_reset_tag(const void *addr) #endif /* CONFIG_KASAN_SW_TAGS */ +#ifdef CONFIG_KASAN_VMALLOC +int kasan_populate_vmalloc(unsigned long requested_size, + struct vm_struct *area); +void kasan_poison_vmalloc(void *start, unsigned long size); +void kasan_release_vmalloc(unsigned long start, unsigned long end, + unsigned long free_region_start, + unsigned long free_region_end); +#else +static inline int kasan_populate_vmalloc(unsigned long requested_size, + struct vm_struct *area) +{ + return 0; +} + +static inline void kasan_poison_vmalloc(void *start, unsigned long size) {} +static inline void kasan_release_vmalloc(unsigned long start, + unsigned long end, + unsigned long free_region_start, + unsigned long free_region_end) {} +#endif + #endif /* LINUX_KASAN_H */ diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index 5229c18025e9..ca92aea8a6bd 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -91,7 +91,7 @@ void module_arch_cleanup(struct module *mod); /* Any cleanup before freeing mod->module_init */ void module_arch_freeing_init(struct module *mod); -#ifdef CONFIG_KASAN +#if defined(CONFIG_KASAN) && !defined(CONFIG_KASAN_VMALLOC) #include #define MODULE_ALIGN (PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT) #else diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index b4c58a191eb1..a4b241102771 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -22,6 +22,18 @@ struct notifier_block; /* in notifier.h */ #define VM_UNINITIALIZED 0x00000020 /* vm_struct is not fully initialized */ #define VM_NO_GUARD 0x00000040 /* don't add guard page */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ + +/* + * VM_KASAN is used slighly differently depending on CONFIG_KASAN_VMALLOC. + * + * If IS_ENABLED(CONFIG_KASAN_VMALLOC), VM_KASAN is set on a vm_struct after + * shadow memory has been mapped. It's used to handle allocation errors so that + * we don't try to poision shadow on free if it was never allocated. + * + * Otherwise, VM_KASAN is set for kasan_module_alloc() allocations and used to + * determine which allocations need the module shadow freed. + */ + /* * Memory with VM_FLUSH_RESET_PERMS cannot be freed in an interrupt or with * vfree_atomic(). diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index 6c9682ce0254..81f5464ea9e1 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -6,6 +6,9 @@ config HAVE_ARCH_KASAN config HAVE_ARCH_KASAN_SW_TAGS bool +config HAVE_ARCH_KASAN_VMALLOC + bool + config CC_HAS_KASAN_GENERIC def_bool $(cc-option, -fsanitize=kernel-address) @@ -142,6 +145,19 @@ config KASAN_SW_TAGS_IDENTIFY (use-after-free or out-of-bounds) at the cost of increased memory consumption. +config KASAN_VMALLOC + bool "Back mappings in vmalloc space with real shadow memory" + depends on KASAN && HAVE_ARCH_KASAN_VMALLOC + help + By default, the shadow region for vmalloc space is the read-only + zero page. This means that KASAN cannot detect errors involving + vmalloc space. + + Enabling this option will hook in to vmap/vmalloc and back those + mappings with real shadow memory allocated on demand. This allows + for KASAN to detect more sorts of errors (and to support vmapped + stacks), but at the cost of higher memory usage. + config TEST_KASAN tristate "Module for testing KASAN for bug detection" depends on m && KASAN diff --git a/mm/kasan/common.c b/mm/kasan/common.c index 6814d6d6a023..df3371d5c572 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -36,6 +36,8 @@ #include #include +#include + #include "kasan.h" #include "../slab.h" @@ -590,6 +592,7 @@ void kasan_kfree_large(void *ptr, unsigned long ip) /* The object will be poisoned by page_alloc. */ } +#ifndef CONFIG_KASAN_VMALLOC int kasan_module_alloc(void *addr, size_t size) { void *ret; @@ -625,6 +628,7 @@ void kasan_free_shadow(const struct vm_struct *vm) if (vm->flags & VM_KASAN) vfree(kasan_mem_to_shadow(vm->addr)); } +#endif extern void __kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip); @@ -744,3 +748,232 @@ static int __init kasan_memhotplug_init(void) core_initcall(kasan_memhotplug_init); #endif + +#ifdef CONFIG_KASAN_VMALLOC +static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr, + void *unused) +{ + unsigned long page; + pte_t pte; + + if (likely(!pte_none(*ptep))) + return 0; + + page = __get_free_page(GFP_KERNEL); + if (!page) + return -ENOMEM; + + memset((void *)page, KASAN_VMALLOC_INVALID, PAGE_SIZE); + pte = pfn_pte(PFN_DOWN(__pa(page)), PAGE_KERNEL); + + spin_lock(&init_mm.page_table_lock); + if (likely(pte_none(*ptep))) { + set_pte_at(&init_mm, addr, ptep, pte); + page = 0; + } + spin_unlock(&init_mm.page_table_lock); + if (page) + free_page(page); + return 0; +} + +int kasan_populate_vmalloc(unsigned long requested_size, struct vm_struct *area) +{ + unsigned long shadow_start, shadow_end; + int ret; + + shadow_start = (unsigned long)kasan_mem_to_shadow(area->addr); + shadow_start = ALIGN_DOWN(shadow_start, PAGE_SIZE); + shadow_end = (unsigned long)kasan_mem_to_shadow(area->addr + + area->size); + shadow_end = ALIGN(shadow_end, PAGE_SIZE); + + ret = apply_to_page_range(&init_mm, shadow_start, + shadow_end - shadow_start, + kasan_populate_vmalloc_pte, NULL); + if (ret) + return ret; + + flush_cache_vmap(shadow_start, shadow_end); + + kasan_unpoison_shadow(area->addr, requested_size); + + area->flags |= VM_KASAN; + + /* + * We need to be careful about inter-cpu effects here. Consider: + * + * CPU#0 CPU#1 + * WRITE_ONCE(p, vmalloc(100)); while (x = READ_ONCE(p)) ; + * p[99] = 1; + * + * With compiler instrumentation, that ends up looking like this: + * + * CPU#0 CPU#1 + * // vmalloc() allocates memory + * // let a = area->addr + * // we reach kasan_populate_vmalloc + * // and call kasan_unpoison_shadow: + * STORE shadow(a), unpoison_val + * ... + * STORE shadow(a+99), unpoison_val x = LOAD p + * // rest of vmalloc process + * STORE p, a LOAD shadow(x+99) + * + * If there is no barrier between the end of unpoisioning the shadow + * and the store of the result to p, the stores could be committed + * in a different order by CPU#0, and CPU#1 could erroneously observe + * poison in the shadow. + * + * We need some sort of barrier between the stores. + * + * In the vmalloc() case, this is provided by a smp_wmb() in + * clear_vm_uninitialized_flag(). In the per-cpu allocator and in + * get_vm_area() and friends, the caller gets shadow allocated but + * doesn't have any pages mapped into the virtual address space that + * has been reserved. Mapping those pages in will involve taking and + * releasing a page-table lock, which will provide the barrier. + */ + + return 0; +} + +/* + * Poison the shadow for a vmalloc region. Called as part of the + * freeing process at the time the region is freed. + */ +void kasan_poison_vmalloc(void *start, unsigned long size) +{ + size = round_up(size, KASAN_SHADOW_SCALE_SIZE); + kasan_poison_shadow(start, size, KASAN_VMALLOC_INVALID); +} + +static int kasan_depopulate_vmalloc_pte(pte_t *ptep, unsigned long addr, + void *unused) +{ + unsigned long page; + + page = (unsigned long)__va(pte_pfn(*ptep) << PAGE_SHIFT); + + spin_lock(&init_mm.page_table_lock); + + if (likely(!pte_none(*ptep))) { + pte_clear(&init_mm, addr, ptep); + free_page(page); + } + spin_unlock(&init_mm.page_table_lock); + + return 0; +} + +/* + * Release the backing for the vmalloc region [start, end), which + * lies within the free region [free_region_start, free_region_end). + * + * This can be run lazily, long after the region was freed. It runs + * under vmap_area_lock, so it's not safe to interact with the vmalloc/vmap + * infrastructure. + * + * How does this work? + * ------------------- + * + * We have a region that is page aligned, labelled as A. + * That might not map onto the shadow in a way that is page-aligned: + * + * start end + * v v + * |????????|????????|AAAAAAAA|AA....AA|AAAAAAAA|????????| < vmalloc + * -------- -------- -------- -------- -------- + * | | | | | + * | | | /-------/ | + * \-------\|/------/ |/---------------/ + * ||| || + * |??AAAAAA|AAAAAAAA|AA??????| < shadow + * (1) (2) (3) + * + * First we align the start upwards and the end downwards, so that the + * shadow of the region aligns with shadow page boundaries. In the + * example, this gives us the shadow page (2). This is the shadow entirely + * covered by this allocation. + * + * Then we have the tricky bits. We want to know if we can free the + * partially covered shadow pages - (1) and (3) in the example. For this, + * we are given the start and end of the free region that contains this + * allocation. Extending our previous example, we could have: + * + * free_region_start free_region_end + * | start end | + * v v v v + * |FFFFFFFF|FFFFFFFF|AAAAAAAA|AA....AA|AAAAAAAA|FFFFFFFF| < vmalloc + * -------- -------- -------- -------- -------- + * | | | | | + * | | | /-------/ | + * \-------\|/------/ |/---------------/ + * ||| || + * |FFAAAAAA|AAAAAAAA|AAF?????| < shadow + * (1) (2) (3) + * + * Once again, we align the start of the free region up, and the end of + * the free region down so that the shadow is page aligned. So we can free + * page (1) - we know no allocation currently uses anything in that page, + * because all of it is in the vmalloc free region. But we cannot free + * page (3), because we can't be sure that the rest of it is unused. + * + * We only consider pages that contain part of the original region for + * freeing: we don't try to free other pages from the free region or we'd + * end up trying to free huge chunks of virtual address space. + * + * Concurrency + * ----------- + * + * How do we know that we're not freeing a page that is simultaneously + * being used for a fresh allocation in kasan_populate_vmalloc(_pte)? + * + * We _can_ have kasan_release_vmalloc and kasan_populate_vmalloc running + * at the same time. While we run under free_vmap_area_lock, the population + * code does not. + * + * free_vmap_area_lock instead operates to ensure that the larger range + * [free_region_start, free_region_end) is safe: because __alloc_vmap_area and + * the per-cpu region-finding algorithm both run under free_vmap_area_lock, + * no space identified as free will become used while we are running. This + * means that so long as we are careful with alignment and only free shadow + * pages entirely covered by the free region, we will not run in to any + * trouble - any simultaneous allocations will be for disjoint regions. + */ +void kasan_release_vmalloc(unsigned long start, unsigned long end, + unsigned long free_region_start, + unsigned long free_region_end) +{ + void *shadow_start, *shadow_end; + unsigned long region_start, region_end; + + region_start = ALIGN(start, PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE); + region_end = ALIGN_DOWN(end, PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE); + + free_region_start = ALIGN(free_region_start, + PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE); + + if (start != region_start && + free_region_start < region_start) + region_start -= PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE; + + free_region_end = ALIGN_DOWN(free_region_end, + PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE); + + if (end != region_end && + free_region_end > region_end) + region_end += PAGE_SIZE * KASAN_SHADOW_SCALE_SIZE; + + shadow_start = kasan_mem_to_shadow((void *)region_start); + shadow_end = kasan_mem_to_shadow((void *)region_end); + + if (shadow_end > shadow_start) { + apply_to_page_range(&init_mm, (unsigned long)shadow_start, + (unsigned long)(shadow_end - shadow_start), + kasan_depopulate_vmalloc_pte, NULL); + flush_tlb_kernel_range((unsigned long)shadow_start, + (unsigned long)shadow_end); + } +} +#endif diff --git a/mm/kasan/generic_report.c b/mm/kasan/generic_report.c index 36c645939bc9..2d97efd4954f 100644 --- a/mm/kasan/generic_report.c +++ b/mm/kasan/generic_report.c @@ -86,6 +86,9 @@ static const char *get_shadow_bug_type(struct kasan_access_info *info) case KASAN_ALLOCA_RIGHT: bug_type = "alloca-out-of-bounds"; break; + case KASAN_VMALLOC_INVALID: + bug_type = "vmalloc-out-of-bounds"; + break; } return bug_type; diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 35cff6bbb716..3a083274628e 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -25,6 +25,7 @@ #endif #define KASAN_GLOBAL_REDZONE 0xFA /* redzone for global variable */ +#define KASAN_VMALLOC_INVALID 0xF9 /* unallocated space in vmapped page */ /* * Stack redzone shadow values diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 33e245ebe70c..4d3b3d60d893 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -683,7 +683,7 @@ insert_vmap_area_augment(struct vmap_area *va, * free area is inserted. If VA has been merged, it is * freed. */ -static __always_inline void +static __always_inline struct vmap_area * merge_or_add_vmap_area(struct vmap_area *va, struct rb_root *root, struct list_head *head) { @@ -750,7 +750,10 @@ merge_or_add_vmap_area(struct vmap_area *va, /* Free vmap_area object. */ kmem_cache_free(vmap_area_cachep, va); - return; + + /* Point to the new merged area. */ + va = sibling; + merged = true; } } @@ -759,6 +762,8 @@ insert: link_va(va, root, parent, link, head); augment_tree_propagate_from(va); } + + return va; } static __always_inline bool @@ -1196,8 +1201,7 @@ static void free_vmap_area(struct vmap_area *va) * Insert/Merge it back to the free tree/list. */ spin_lock(&free_vmap_area_lock); - merge_or_add_vmap_area(va, - &free_vmap_area_root, &free_vmap_area_list); + merge_or_add_vmap_area(va, &free_vmap_area_root, &free_vmap_area_list); spin_unlock(&free_vmap_area_lock); } @@ -1294,14 +1298,20 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end) spin_lock(&free_vmap_area_lock); llist_for_each_entry_safe(va, n_va, valist, purge_list) { unsigned long nr = (va->va_end - va->va_start) >> PAGE_SHIFT; + unsigned long orig_start = va->va_start; + unsigned long orig_end = va->va_end; /* * Finally insert or merge lazily-freed area. It is * detached and there is no need to "unlink" it from * anything. */ - merge_or_add_vmap_area(va, - &free_vmap_area_root, &free_vmap_area_list); + va = merge_or_add_vmap_area(va, &free_vmap_area_root, + &free_vmap_area_list); + + if (is_vmalloc_or_module_addr((void *)orig_start)) + kasan_release_vmalloc(orig_start, orig_end, + va->va_start, va->va_end); atomic_long_sub(nr, &vmap_lazy_nr); @@ -2090,6 +2100,22 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, setup_vmalloc_vm(area, va, flags, caller); + /* + * For KASAN, if we are in vmalloc space, we need to cover the shadow + * area with real memory. If we come here through VM_ALLOC, this is + * done by a higher level function that has access to the true size, + * which might not be a full page. + * + * We assume module space comes via VM_ALLOC path. + */ + if (is_vmalloc_addr(area->addr) && !(area->flags & VM_ALLOC)) { + if (kasan_populate_vmalloc(area->size, area)) { + unmap_vmap_area(va); + kfree(area); + return NULL; + } + } + return area; } @@ -2267,6 +2293,9 @@ static void __vunmap(const void *addr, int deallocate_pages) debug_check_no_locks_freed(area->addr, get_vm_area_size(area)); debug_check_no_obj_freed(area->addr, get_vm_area_size(area)); + if (area->flags & VM_KASAN) + kasan_poison_vmalloc(area->addr, area->size); + vm_remove_mappings(area, deallocate_pages); if (deallocate_pages) { @@ -2519,6 +2548,11 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, if (!addr) return NULL; + if (is_vmalloc_or_module_addr(area->addr)) { + if (kasan_populate_vmalloc(real_size, area)) + return NULL; + } + /* * In this function, newly allocated vm_struct has VM_UNINITIALIZED * flag. It means that vm_struct is not fully initialized. @@ -3400,6 +3434,12 @@ retry: } spin_unlock(&vmap_area_lock); + /* populate the shadow space outside of the lock */ + for (area = 0; area < nr_vms; area++) { + /* assume success here */ + kasan_populate_vmalloc(sizes[area], vms[area]); + } + kfree(vas); return vms; @@ -3411,8 +3451,8 @@ recovery: * and when pcpu_get_vm_areas() is success. */ while (area--) { - merge_or_add_vmap_area(vas[area], - &free_vmap_area_root, &free_vmap_area_list); + merge_or_add_vmap_area(vas[area], &free_vmap_area_root, + &free_vmap_area_list); vas[area] = NULL; } -- cgit v1.2.3-71-gd317 From 5e27a2df03b8933aa7c1579816ecb6a071bb0e0d Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Sat, 30 Nov 2019 17:55:06 -0800 Subject: mm/page_alloc: add alloc_contig_pages() HugeTLB helper alloc_gigantic_page() implements fairly generic allocation method where it scans over various zones looking for a large contiguous pfn range before trying to allocate it with alloc_contig_range(). Other than deriving the requested order from 'struct hstate', there is nothing HugeTLB specific in there. This can be made available for general use to allocate contiguous memory which could not have been allocated through the buddy allocator. alloc_gigantic_page() has been split carving out actual allocation method which is then made available via new alloc_contig_pages() helper wrapped under CONFIG_CONTIG_ALLOC. All references to 'gigantic' have been replaced with more generic term 'contig'. Allocated pages here should be freed with free_contig_range() or by calling __free_page() on each allocated page. Link: http://lkml.kernel.org/r/1571300646-32240-1-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Acked-by: David Hildenbrand Acked-by: Michal Hocko Cc: Mike Kravetz Cc: Vlastimil Babka Cc: Michal Hocko Cc: David Rientjes Cc: Andrea Arcangeli Cc: Oscar Salvador Cc: Mel Gorman Cc: Mike Rapoport Cc: Dan Williams Cc: Pavel Tatashin Cc: Matthew Wilcox Cc: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 2 ++ mm/hugetlb.c | 77 ++------------------------------------- mm/page_alloc.c | 101 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 105 insertions(+), 75 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 61f2f6ff9467..e5b817cb86e7 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -612,6 +612,8 @@ static inline bool pm_suspended_storage(void) /* The below functions must be run on a range from a single zone. */ extern int alloc_contig_range(unsigned long start, unsigned long end, unsigned migratetype, gfp_t gfp_mask); +extern struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, + int nid, nodemask_t *nodemask); #endif void free_contig_range(unsigned long pfn, unsigned int nr_pages); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b45a95363a84..26b722faf740 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1069,85 +1069,12 @@ static void free_gigantic_page(struct page *page, unsigned int order) } #ifdef CONFIG_CONTIG_ALLOC -static int __alloc_gigantic_page(unsigned long start_pfn, - unsigned long nr_pages, gfp_t gfp_mask) -{ - unsigned long end_pfn = start_pfn + nr_pages; - return alloc_contig_range(start_pfn, end_pfn, MIGRATE_MOVABLE, - gfp_mask); -} - -static bool pfn_range_valid_gigantic(struct zone *z, - unsigned long start_pfn, unsigned long nr_pages) -{ - unsigned long i, end_pfn = start_pfn + nr_pages; - struct page *page; - - for (i = start_pfn; i < end_pfn; i++) { - page = pfn_to_online_page(i); - if (!page) - return false; - - if (page_zone(page) != z) - return false; - - if (PageReserved(page)) - return false; - - if (page_count(page) > 0) - return false; - - if (PageHuge(page)) - return false; - } - - return true; -} - -static bool zone_spans_last_pfn(const struct zone *zone, - unsigned long start_pfn, unsigned long nr_pages) -{ - unsigned long last_pfn = start_pfn + nr_pages - 1; - return zone_spans_pfn(zone, last_pfn); -} - static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { - unsigned int order = huge_page_order(h); - unsigned long nr_pages = 1 << order; - unsigned long ret, pfn, flags; - struct zonelist *zonelist; - struct zone *zone; - struct zoneref *z; - - zonelist = node_zonelist(nid, gfp_mask); - for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nodemask) { - spin_lock_irqsave(&zone->lock, flags); + unsigned long nr_pages = 1UL << huge_page_order(h); - pfn = ALIGN(zone->zone_start_pfn, nr_pages); - while (zone_spans_last_pfn(zone, pfn, nr_pages)) { - if (pfn_range_valid_gigantic(zone, pfn, nr_pages)) { - /* - * We release the zone lock here because - * alloc_contig_range() will also lock the zone - * at some point. If there's an allocation - * spinning on this lock, it may win the race - * and cause alloc_contig_range() to fail... - */ - spin_unlock_irqrestore(&zone->lock, flags); - ret = __alloc_gigantic_page(pfn, nr_pages, gfp_mask); - if (!ret) - return pfn_to_page(pfn); - spin_lock_irqsave(&zone->lock, flags); - } - pfn += nr_pages; - } - - spin_unlock_irqrestore(&zone->lock, flags); - } - - return NULL; + return alloc_contig_pages(nr_pages, gfp_mask, nid, nodemask); } static void prep_new_huge_page(struct hstate *h, struct page *page, int nid); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c289b02aaa3b..2e47398ba498 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8502,6 +8502,107 @@ done: pfn_max_align_up(end), migratetype); return ret; } + +static int __alloc_contig_pages(unsigned long start_pfn, + unsigned long nr_pages, gfp_t gfp_mask) +{ + unsigned long end_pfn = start_pfn + nr_pages; + + return alloc_contig_range(start_pfn, end_pfn, MIGRATE_MOVABLE, + gfp_mask); +} + +static bool pfn_range_valid_contig(struct zone *z, unsigned long start_pfn, + unsigned long nr_pages) +{ + unsigned long i, end_pfn = start_pfn + nr_pages; + struct page *page; + + for (i = start_pfn; i < end_pfn; i++) { + page = pfn_to_online_page(i); + if (!page) + return false; + + if (page_zone(page) != z) + return false; + + if (PageReserved(page)) + return false; + + if (page_count(page) > 0) + return false; + + if (PageHuge(page)) + return false; + } + return true; +} + +static bool zone_spans_last_pfn(const struct zone *zone, + unsigned long start_pfn, unsigned long nr_pages) +{ + unsigned long last_pfn = start_pfn + nr_pages - 1; + + return zone_spans_pfn(zone, last_pfn); +} + +/** + * alloc_contig_pages() -- tries to find and allocate contiguous range of pages + * @nr_pages: Number of contiguous pages to allocate + * @gfp_mask: GFP mask to limit search and used during compaction + * @nid: Target node + * @nodemask: Mask for other possible nodes + * + * This routine is a wrapper around alloc_contig_range(). It scans over zones + * on an applicable zonelist to find a contiguous pfn range which can then be + * tried for allocation with alloc_contig_range(). This routine is intended + * for allocation requests which can not be fulfilled with the buddy allocator. + * + * The allocated memory is always aligned to a page boundary. If nr_pages is a + * power of two then the alignment is guaranteed to be to the given nr_pages + * (e.g. 1GB request would be aligned to 1GB). + * + * Allocated pages can be freed with free_contig_range() or by manually calling + * __free_page() on each allocated page. + * + * Return: pointer to contiguous pages on success, or NULL if not successful. + */ +struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, + int nid, nodemask_t *nodemask) +{ + unsigned long ret, pfn, flags; + struct zonelist *zonelist; + struct zone *zone; + struct zoneref *z; + + zonelist = node_zonelist(nid, gfp_mask); + for_each_zone_zonelist_nodemask(zone, z, zonelist, + gfp_zone(gfp_mask), nodemask) { + spin_lock_irqsave(&zone->lock, flags); + + pfn = ALIGN(zone->zone_start_pfn, nr_pages); + while (zone_spans_last_pfn(zone, pfn, nr_pages)) { + if (pfn_range_valid_contig(zone, pfn, nr_pages)) { + /* + * We release the zone lock here because + * alloc_contig_range() will also lock the zone + * at some point. If there's an allocation + * spinning on this lock, it may win the race + * and cause alloc_contig_range() to fail... + */ + spin_unlock_irqrestore(&zone->lock, flags); + ret = __alloc_contig_pages(pfn, nr_pages, + gfp_mask); + if (!ret) + return pfn_to_page(pfn); + spin_lock_irqsave(&zone->lock, flags); + } + pfn += nr_pages; + } + spin_unlock_irqrestore(&zone->lock, flags); + } + return NULL; +} #endif /* CONFIG_CONTIG_ALLOC */ void free_contig_range(unsigned long pfn, unsigned int nr_pages) -- cgit v1.2.3-71-gd317 From 68265390f9aa625e2ce94ed1bcff8906db702d79 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Sat, 30 Nov 2019 17:55:15 -0800 Subject: mm, pcpu: make zone pcp updates and reset internal to the mm Memory hotplug needs to be able to reset and reinit the pcpu allocator batch and high limits but this action is internal to the VM. Move the declaration to internal.h Link: http://lkml.kernel.org/r/20191021094808.28824-4-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Borislav Petkov Cc: Matt Fleming Cc: Qian Cai Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 --- mm/internal.h | 3 +++ 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 19a0e687878a..8b0ef04b6d15 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2207,9 +2207,6 @@ void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...); extern void setup_per_cpu_pageset(void); -extern void zone_pcp_update(struct zone *zone); -extern void zone_pcp_reset(struct zone *zone); - /* page_alloc.c */ extern int min_free_kbytes; extern int watermark_boost_factor; diff --git a/mm/internal.h b/mm/internal.h index a246c516ade2..3cf20ab3ca01 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -165,6 +165,9 @@ extern void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); extern int user_min_free_kbytes; +extern void zone_pcp_update(struct zone *zone); +extern void zone_pcp_reset(struct zone *zone); + #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* -- cgit v1.2.3-71-gd317 From 653e003d7f37716f84c17edcad3c228497888bfc Mon Sep 17 00:00:00 2001 From: Hao Lee Date: Sat, 30 Nov 2019 17:55:18 -0800 Subject: include/linux/mmzone.h: fix comment for ISOLATE_UNMAPPED macro Both file-backed pages and anonymous pages can be unmapped. ISOLATE_UNMAPPED is not just for file-backed pages. Link: http://lkml.kernel.org/r/20191024151621.GA20400@haolee.github.io Signed-off-by: Hao Lee Reviewed-by: Andrew Morton Cc: Vlastimil Babka Cc: Dan Williams Cc: Michal Hocko Cc: Wei Yang Cc: Mel Gorman Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b0a36d1580b6..c7fb21f19edd 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -308,7 +308,7 @@ struct lruvec { #endif }; -/* Isolate unmapped file */ +/* Isolate unmapped pages */ #define ISOLATE_UNMAPPED ((__force isolate_mode_t)0x2) /* Isolate for asynchronous migration */ #define ISOLATE_ASYNC_MIGRATE ((__force isolate_mode_t)0x4) -- cgit v1.2.3-71-gd317 From 867e5e1de14b2b2bde324cdfeec3f3f83eb21424 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Sat, 30 Nov 2019 17:55:34 -0800 Subject: mm: clean up and clarify lruvec lookup procedure There is a per-memcg lruvec and a NUMA node lruvec. Which one is being used is somewhat confusing right now, and it's easy to make mistakes - especially when it comes to global reclaim. How it works: when memory cgroups are enabled, we always use the root_mem_cgroup's per-node lruvecs. When memory cgroups are not compiled in or disabled at runtime, we use pgdat->lruvec. Document that in a comment. Due to the way the reclaim code is generalized, all lookups use the mem_cgroup_lruvec() helper function, and nobody should have to find the right lruvec manually right now. But to avoid future mistakes, rename the pgdat->lruvec member to pgdat->__lruvec and delete the convenience wrapper that suggests it's a commonly accessed member. While in this area, swap the mem_cgroup_lruvec() argument order. The name suggests a memcg operation, yet it takes a pgdat first and a memcg second. I have to double take every time I call this. Fix that. Link: http://lkml.kernel.org/r/20191022144803.302233-3-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Reviewed-by: Shakeel Butt Cc: Roman Gushchin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 24 ++++++++++++------------ include/linux/mmzone.h | 15 ++++++++------- mm/memcontrol.c | 10 +++++----- mm/page_alloc.c | 2 +- mm/slab.h | 4 ++-- mm/vmscan.c | 6 +++--- mm/workingset.c | 8 ++++---- 7 files changed, 35 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 239e752a7817..feeb2c76f568 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -385,21 +385,21 @@ mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid) } /** - * mem_cgroup_lruvec - get the lru list vector for a node or a memcg zone - * @node: node of the wanted lruvec + * mem_cgroup_lruvec - get the lru list vector for a memcg & node * @memcg: memcg of the wanted lruvec * - * Returns the lru list vector holding pages for a given @node or a given - * @memcg. This can be the node lruvec, if the memory controller is disabled. + * Returns the lru list vector holding pages for a given @memcg & + * @node combination. This can be the node lruvec, if the memory + * controller is disabled. */ -static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat, - struct mem_cgroup *memcg) +static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, + struct pglist_data *pgdat) { struct mem_cgroup_per_node *mz; struct lruvec *lruvec; if (mem_cgroup_disabled()) { - lruvec = node_lruvec(pgdat); + lruvec = &pgdat->__lruvec; goto out; } @@ -718,7 +718,7 @@ static inline void __mod_lruvec_page_state(struct page *page, return; } - lruvec = mem_cgroup_lruvec(pgdat, page->mem_cgroup); + lruvec = mem_cgroup_lruvec(page->mem_cgroup, pgdat); __mod_lruvec_state(lruvec, idx, val); } @@ -889,16 +889,16 @@ static inline void mem_cgroup_migrate(struct page *old, struct page *new) { } -static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat, - struct mem_cgroup *memcg) +static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, + struct pglist_data *pgdat) { - return node_lruvec(pgdat); + return &pgdat->__lruvec; } static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgdat) { - return &pgdat->lruvec; + return &pgdat->__lruvec; } static inline bool mm_match_cgroup(struct mm_struct *mm, diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c7fb21f19edd..cc8232a100bd 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -777,7 +777,13 @@ typedef struct pglist_data { #endif /* Fields commonly accessed by the page reclaim scanner */ - struct lruvec lruvec; + + /* + * NOTE: THIS IS UNUSED IF MEMCG IS ENABLED. + * + * Use mem_cgroup_lruvec() to look up lruvecs. + */ + struct lruvec __lruvec; unsigned long flags; @@ -800,11 +806,6 @@ typedef struct pglist_data { #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid)) -static inline struct lruvec *node_lruvec(struct pglist_data *pgdat) -{ - return &pgdat->lruvec; -} - static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) { return pgdat->node_start_pfn + pgdat->node_spanned_pages; @@ -842,7 +843,7 @@ static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec) #ifdef CONFIG_MEMCG return lruvec->pgdat; #else - return container_of(lruvec, struct pglist_data, lruvec); + return container_of(lruvec, struct pglist_data, __lruvec); #endif } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 529e12a59131..bc01423277c5 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -777,7 +777,7 @@ void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val) if (!memcg || memcg == root_mem_cgroup) { __mod_node_page_state(pgdat, idx, val); } else { - lruvec = mem_cgroup_lruvec(pgdat, memcg); + lruvec = mem_cgroup_lruvec(memcg, pgdat); __mod_lruvec_state(lruvec, idx, val); } rcu_read_unlock(); @@ -1221,7 +1221,7 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgd struct lruvec *lruvec; if (mem_cgroup_disabled()) { - lruvec = &pgdat->lruvec; + lruvec = &pgdat->__lruvec; goto out; } @@ -3634,7 +3634,7 @@ static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css, static unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, int nid, unsigned int lru_mask) { - struct lruvec *lruvec = mem_cgroup_lruvec(NODE_DATA(nid), memcg); + struct lruvec *lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid)); unsigned long nr = 0; enum lru_list lru; @@ -5338,8 +5338,8 @@ static int mem_cgroup_move_account(struct page *page, anon = PageAnon(page); pgdat = page_pgdat(page); - from_vec = mem_cgroup_lruvec(pgdat, from); - to_vec = mem_cgroup_lruvec(pgdat, to); + from_vec = mem_cgroup_lruvec(from, pgdat); + to_vec = mem_cgroup_lruvec(to, pgdat); spin_lock_irqsave(&from->move_lock, flags); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e3a69ba5ec53..4785a8a2040e 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6713,7 +6713,7 @@ static void __meminit pgdat_init_internals(struct pglist_data *pgdat) pgdat_page_ext_init(pgdat); spin_lock_init(&pgdat->lru_lock); - lruvec_init(node_lruvec(pgdat)); + lruvec_init(&pgdat->__lruvec); } static void __meminit zone_init_internals(struct zone *zone, enum zone_type idx, int nid, diff --git a/mm/slab.h b/mm/slab.h index 8b77f973a6ab..7e94700aa78c 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -369,7 +369,7 @@ static __always_inline int memcg_charge_slab(struct page *page, if (ret) goto out; - lruvec = mem_cgroup_lruvec(page_pgdat(page), memcg); + lruvec = mem_cgroup_lruvec(memcg, page_pgdat(page)); mod_lruvec_state(lruvec, cache_vmstat_idx(s), 1 << order); /* transer try_charge() page references to kmem_cache */ @@ -393,7 +393,7 @@ static __always_inline void memcg_uncharge_slab(struct page *page, int order, rcu_read_lock(); memcg = READ_ONCE(s->memcg_params.memcg); if (likely(!mem_cgroup_is_root(memcg))) { - lruvec = mem_cgroup_lruvec(page_pgdat(page), memcg); + lruvec = mem_cgroup_lruvec(memcg, page_pgdat(page)); mod_lruvec_state(lruvec, cache_vmstat_idx(s), -(1 << order)); memcg_kmem_uncharge_memcg(page, order, memcg); } else { diff --git a/mm/vmscan.c b/mm/vmscan.c index 266620f7c814..94d73725813d 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2545,7 +2545,7 @@ out: static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memcg, struct scan_control *sc) { - struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg); + struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); unsigned long nr[NR_LRU_LISTS]; unsigned long targets[NR_LRU_LISTS]; unsigned long nr_to_scan; @@ -3023,7 +3023,7 @@ static void snapshot_refaults(struct mem_cgroup *root_memcg, pg_data_t *pgdat) unsigned long refaults; struct lruvec *lruvec; - lruvec = mem_cgroup_lruvec(pgdat, memcg); + lruvec = mem_cgroup_lruvec(memcg, pgdat); refaults = lruvec_page_state_local(lruvec, WORKINGSET_ACTIVATE); lruvec->refaults = refaults; } while ((memcg = mem_cgroup_iter(root_memcg, memcg, NULL))); @@ -3379,7 +3379,7 @@ static void age_active_anon(struct pglist_data *pgdat, memcg = mem_cgroup_iter(NULL, NULL, NULL); do { - struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg); + struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); if (inactive_list_is_low(lruvec, false, sc, true)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, diff --git a/mm/workingset.c b/mm/workingset.c index c963831d354f..e8212123c1c3 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -233,7 +233,7 @@ void *workingset_eviction(struct page *page) VM_BUG_ON_PAGE(page_count(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); - lruvec = mem_cgroup_lruvec(pgdat, memcg); + lruvec = mem_cgroup_lruvec(memcg, pgdat); eviction = atomic_long_inc_return(&lruvec->inactive_age); return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page)); } @@ -280,7 +280,7 @@ void workingset_refault(struct page *page, void *shadow) memcg = mem_cgroup_from_id(memcgid); if (!mem_cgroup_disabled() && !memcg) goto out; - lruvec = mem_cgroup_lruvec(pgdat, memcg); + lruvec = mem_cgroup_lruvec(memcg, pgdat); refault = atomic_long_read(&lruvec->inactive_age); active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES); @@ -345,7 +345,7 @@ void workingset_activation(struct page *page) memcg = page_memcg_rcu(page); if (!mem_cgroup_disabled() && !memcg) goto out; - lruvec = mem_cgroup_lruvec(page_pgdat(page), memcg); + lruvec = mem_cgroup_lruvec(memcg, page_pgdat(page)); atomic_long_inc(&lruvec->inactive_age); out: rcu_read_unlock(); @@ -426,7 +426,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, struct lruvec *lruvec; int i; - lruvec = mem_cgroup_lruvec(NODE_DATA(sc->nid), sc->memcg); + lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid)); for (pages = 0, i = 0; i < NR_LRU_LISTS; i++) pages += lruvec_page_state_local(lruvec, NR_LRU_BASE + i); -- cgit v1.2.3-71-gd317 From 1b05117df78e035afb5f66ef50bf8750d976ef08 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Sat, 30 Nov 2019 17:55:52 -0800 Subject: mm: vmscan: harmonize writeback congestion tracking for nodes & memcgs The current writeback congestion tracking has separate flags for kswapd reclaim (node level) and cgroup limit reclaim (memcg-node level). This is unnecessarily complicated: the lruvec is an existing abstraction layer for that node-memcg intersection. Introduce lruvec->flags and LRUVEC_CONGESTED. Then track that at the reclaim root level, which is either the NUMA node for global reclaim, or the cgroup-node intersection for cgroup reclaim. Link: http://lkml.kernel.org/r/20191022144803.302233-9-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Reviewed-by: Roman Gushchin Reviewed-by: Shakeel Butt Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 6 ++-- include/linux/mmzone.h | 11 ++++-- mm/vmscan.c | 84 ++++++++++++++-------------------------------- 3 files changed, 37 insertions(+), 64 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index feeb2c76f568..5b86287fa069 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -132,9 +132,6 @@ struct mem_cgroup_per_node { unsigned long usage_in_excess;/* Set to the value by which */ /* the soft limit is exceeded*/ bool on_tree; - bool congested; /* memcg has many dirty pages */ - /* backed by a congested BDI */ - struct mem_cgroup *memcg; /* Back pointer, we cannot */ /* use container_of */ }; @@ -403,6 +400,9 @@ static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, goto out; } + if (!memcg) + memcg = root_mem_cgroup; + mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id); lruvec = &mz->lruvec; out: diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index cc8232a100bd..ddee00e91a22 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -296,6 +296,12 @@ struct zone_reclaim_stat { unsigned long recent_scanned[2]; }; +enum lruvec_flags { + LRUVEC_CONGESTED, /* lruvec has many dirty pages + * backed by a congested BDI + */ +}; + struct lruvec { struct list_head lists[NR_LRU_LISTS]; struct zone_reclaim_stat reclaim_stat; @@ -303,6 +309,8 @@ struct lruvec { atomic_long_t inactive_age; /* Refaults at the time of last reclaim cycle */ unsigned long refaults; + /* Various lruvec state flags (enum lruvec_flags) */ + unsigned long flags; #ifdef CONFIG_MEMCG struct pglist_data *pgdat; #endif @@ -572,9 +580,6 @@ struct zone { } ____cacheline_internodealigned_in_smp; enum pgdat_flags { - PGDAT_CONGESTED, /* pgdat has many dirty pages backed by - * a congested BDI - */ PGDAT_DIRTY, /* reclaim scanning has recently found * many dirty file pages at the tail * of the LRU. diff --git a/mm/vmscan.c b/mm/vmscan.c index d35864850b43..39589e561c8f 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -267,29 +267,6 @@ static bool writeback_throttling_sane(struct scan_control *sc) #endif return false; } - -static void set_memcg_congestion(pg_data_t *pgdat, - struct mem_cgroup *memcg, - bool congested) -{ - struct mem_cgroup_per_node *mn; - - if (!memcg) - return; - - mn = mem_cgroup_nodeinfo(memcg, pgdat->node_id); - WRITE_ONCE(mn->congested, congested); -} - -static bool memcg_congested(pg_data_t *pgdat, - struct mem_cgroup *memcg) -{ - struct mem_cgroup_per_node *mn; - - mn = mem_cgroup_nodeinfo(memcg, pgdat->node_id); - return READ_ONCE(mn->congested); - -} #else static int prealloc_memcg_shrinker(struct shrinker *shrinker) { @@ -309,18 +286,6 @@ static bool writeback_throttling_sane(struct scan_control *sc) { return true; } - -static inline void set_memcg_congestion(struct pglist_data *pgdat, - struct mem_cgroup *memcg, bool congested) -{ -} - -static inline bool memcg_congested(struct pglist_data *pgdat, - struct mem_cgroup *memcg) -{ - return false; - -} #endif /* @@ -2716,12 +2681,6 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat, return inactive_lru_pages > pages_for_compaction; } -static bool pgdat_memcg_congested(pg_data_t *pgdat, struct mem_cgroup *memcg) -{ - return test_bit(PGDAT_CONGESTED, &pgdat->flags) || - (memcg && memcg_congested(pgdat, memcg)); -} - static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) { struct mem_cgroup *target_memcg = sc->target_mem_cgroup; @@ -2783,10 +2742,12 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc) { struct reclaim_state *reclaim_state = current->reclaim_state; - struct mem_cgroup *target_memcg = sc->target_mem_cgroup; unsigned long nr_reclaimed, nr_scanned; + struct lruvec *target_lruvec; bool reclaimable = false; + target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); + again: memset(&sc->nr, 0, sizeof(sc->nr)); @@ -2801,7 +2762,7 @@ again: } /* Record the subtree's reclaim efficiency */ - vmpressure(sc->gfp_mask, target_memcg, true, + vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true, sc->nr_scanned - nr_scanned, sc->nr_reclaimed - nr_reclaimed); @@ -2829,14 +2790,6 @@ again: if (sc->nr.writeback && sc->nr.writeback == sc->nr.taken) set_bit(PGDAT_WRITEBACK, &pgdat->flags); - /* - * Tag a node as congested if all the dirty pages - * scanned were backed by a congested BDI and - * wait_iff_congested will stall. - */ - if (sc->nr.dirty && sc->nr.dirty == sc->nr.congested) - set_bit(PGDAT_CONGESTED, &pgdat->flags); - /* Allow kswapd to start writing pages during reclaim.*/ if (sc->nr.unqueued_dirty == sc->nr.file_taken) set_bit(PGDAT_DIRTY, &pgdat->flags); @@ -2852,12 +2805,17 @@ again: } /* + * Tag a node/memcg as congested if all the dirty pages + * scanned were backed by a congested BDI and + * wait_iff_congested will stall. + * * Legacy memcg will stall in page writeback so avoid forcibly * stalling in wait_iff_congested(). */ - if (cgroup_reclaim(sc) && writeback_throttling_sane(sc) && + if ((current_is_kswapd() || + (cgroup_reclaim(sc) && writeback_throttling_sane(sc))) && sc->nr.dirty && sc->nr.dirty == sc->nr.congested) - set_memcg_congestion(pgdat, target_memcg, true); + set_bit(LRUVEC_CONGESTED, &target_lruvec->flags); /* * Stall direct reclaim for IO completions if underlying BDIs @@ -2865,9 +2823,9 @@ again: * starts encountering unqueued dirty pages or cycling through * the LRU too quickly. */ - if (!sc->hibernation_mode && !current_is_kswapd() && - current_may_throttle() && - pgdat_memcg_congested(pgdat, target_memcg)) + if (!current_is_kswapd() && current_may_throttle() && + !sc->hibernation_mode && + test_bit(LRUVEC_CONGESTED, &target_lruvec->flags)) wait_iff_congested(BLK_RW_ASYNC, HZ/10); if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed, @@ -3081,8 +3039,16 @@ retry: if (zone->zone_pgdat == last_pgdat) continue; last_pgdat = zone->zone_pgdat; + snapshot_refaults(sc->target_mem_cgroup, zone->zone_pgdat); - set_memcg_congestion(last_pgdat, sc->target_mem_cgroup, false); + + if (cgroup_reclaim(sc)) { + struct lruvec *lruvec; + + lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, + zone->zone_pgdat); + clear_bit(LRUVEC_CONGESTED, &lruvec->flags); + } } delayacct_freepages_end(); @@ -3450,7 +3416,9 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx) /* Clear pgdat state for congested, dirty or under writeback. */ static void clear_pgdat_congested(pg_data_t *pgdat) { - clear_bit(PGDAT_CONGESTED, &pgdat->flags); + struct lruvec *lruvec = mem_cgroup_lruvec(NULL, pgdat); + + clear_bit(LRUVEC_CONGESTED, &lruvec->flags); clear_bit(PGDAT_DIRTY, &pgdat->flags); clear_bit(PGDAT_WRITEBACK, &pgdat->flags); } -- cgit v1.2.3-71-gd317 From b910718a948a9120d90faf632b33ed23c70e266a Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Sat, 30 Nov 2019 17:55:59 -0800 Subject: mm: vmscan: detect file thrashing at the reclaim root We use refault information to determine whether the cache workingset is stable or transitioning, and dynamically adjust the inactive:active file LRU ratio so as to maximize protection from one-off cache during stable periods, and minimize IO during transitions. With cgroups and their nested LRU lists, we currently don't do this correctly. While recursive cgroup reclaim establishes a relative LRU order among the pages of all involved cgroups, refaults only affect the local LRU order in the cgroup in which they are occuring. As a result, cache transitions can take longer in a cgrouped system as the active pages of sibling cgroups aren't challenged when they should be. [ Right now, this is somewhat theoretical, because the siblings, under continued regular reclaim pressure, should eventually run out of inactive pages - and since inactive:active *size* balancing is also done on a cgroup-local level, we will challenge the active pages eventually in most cases. But the next patch will move that relative size enforcement to the reclaim root as well, and then this patch here will be necessary to propagate refault pressure to siblings. ] This patch moves refault detection to the root of reclaim. Instead of remembering the cgroup owner of an evicted page, remember the cgroup that caused the reclaim to happen. When refaults later occur, they'll correctly influence the cross-cgroup LRU order that reclaim follows. I.e. if global reclaim kicked out pages in some subgroup A/B/C, the refault of those pages will challenge the global LRU order, and not just the local order down inside C. [hannes@cmpxchg.org: use page_memcg() instead of another lookup] Link: http://lkml.kernel.org/r/20191115160722.GA309754@cmpxchg.org Link: http://lkml.kernel.org/r/20191107205334.158354-3-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Reviewed-by: Suren Baghdasaryan Cc: Andrey Ryabinin Cc: Michal Hocko Cc: Rik van Riel Cc: Shakeel Butt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 ++++ include/linux/swap.h | 2 +- mm/vmscan.c | 32 +++++++++++----------- mm/workingset.c | 67 +++++++++++++++++++++++++++++++++++----------- 4 files changed, 73 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 5b86287fa069..a7a0a1a5c8d5 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -901,6 +901,11 @@ static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page, return &pgdat->__lruvec; } +static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) +{ + return NULL; +} + static inline bool mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *memcg) { diff --git a/include/linux/swap.h b/include/linux/swap.h index 063c0c1e112b..1e99f7ac1d7e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -307,7 +307,7 @@ struct vma_swap_readahead { }; /* linux/mm/workingset.c */ -void *workingset_eviction(struct page *page); +void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg); void workingset_refault(struct page *page, void *shadow); void workingset_activation(struct page *page); diff --git a/mm/vmscan.c b/mm/vmscan.c index 725b5d4784f7..39657012e2d8 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -853,7 +853,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping) * gets returned with a refcount of 0. */ static int __remove_mapping(struct address_space *mapping, struct page *page, - bool reclaimed) + bool reclaimed, struct mem_cgroup *target_memcg) { unsigned long flags; int refcount; @@ -925,7 +925,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, */ if (reclaimed && page_is_file_cache(page) && !mapping_exiting(mapping) && !dax_mapping(mapping)) - shadow = workingset_eviction(page); + shadow = workingset_eviction(page, target_memcg); __delete_from_page_cache(page, shadow); xa_unlock_irqrestore(&mapping->i_pages, flags); @@ -948,7 +948,7 @@ cannot_free: */ int remove_mapping(struct address_space *mapping, struct page *page) { - if (__remove_mapping(mapping, page, false)) { + if (__remove_mapping(mapping, page, false, NULL)) { /* * Unfreezing the refcount with 1 rather than 2 effectively * drops the pagecache ref for us without requiring another @@ -1426,7 +1426,8 @@ static unsigned long shrink_page_list(struct list_head *page_list, count_vm_event(PGLAZYFREED); count_memcg_page_event(page, PGLAZYFREED); - } else if (!mapping || !__remove_mapping(mapping, page, true)) + } else if (!mapping || !__remove_mapping(mapping, page, true, + sc->target_mem_cgroup)) goto keep_locked; unlock_page(page); @@ -2189,6 +2190,7 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file, enum lru_list inactive_lru = file * LRU_FILE; unsigned long inactive, active; unsigned long inactive_ratio; + struct lruvec *target_lruvec; unsigned long refaults; unsigned long gb; @@ -2200,8 +2202,9 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file, * is being established. Disable active list protection to get * rid of the stale workingset quickly. */ - refaults = lruvec_page_state_local(lruvec, WORKINGSET_ACTIVATE); - if (file && lruvec->refaults != refaults) { + target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); + refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE); + if (file && target_lruvec->refaults != refaults) { inactive_ratio = 0; } else { gb = (inactive + active) >> (30 - PAGE_SHIFT); @@ -2973,19 +2976,14 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) sc->gfp_mask = orig_mask; } -static void snapshot_refaults(struct mem_cgroup *root_memcg, pg_data_t *pgdat) +static void snapshot_refaults(struct mem_cgroup *target_memcg, pg_data_t *pgdat) { - struct mem_cgroup *memcg; - - memcg = mem_cgroup_iter(root_memcg, NULL, NULL); - do { - unsigned long refaults; - struct lruvec *lruvec; + struct lruvec *target_lruvec; + unsigned long refaults; - lruvec = mem_cgroup_lruvec(memcg, pgdat); - refaults = lruvec_page_state_local(lruvec, WORKINGSET_ACTIVATE); - lruvec->refaults = refaults; - } while ((memcg = mem_cgroup_iter(root_memcg, memcg, NULL))); + target_lruvec = mem_cgroup_lruvec(target_memcg, pgdat); + refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE); + target_lruvec->refaults = refaults; } /* diff --git a/mm/workingset.c b/mm/workingset.c index e8212123c1c3..474186b76ced 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -213,28 +213,53 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, *workingsetp = workingset; } +static void advance_inactive_age(struct mem_cgroup *memcg, pg_data_t *pgdat) +{ + /* + * Reclaiming a cgroup means reclaiming all its children in a + * round-robin fashion. That means that each cgroup has an LRU + * order that is composed of the LRU orders of its child + * cgroups; and every page has an LRU position not just in the + * cgroup that owns it, but in all of that group's ancestors. + * + * So when the physical inactive list of a leaf cgroup ages, + * the virtual inactive lists of all its parents, including + * the root cgroup's, age as well. + */ + do { + struct lruvec *lruvec; + + lruvec = mem_cgroup_lruvec(memcg, pgdat); + atomic_long_inc(&lruvec->inactive_age); + } while (memcg && (memcg = parent_mem_cgroup(memcg))); +} + /** * workingset_eviction - note the eviction of a page from memory + * @target_memcg: the cgroup that is causing the reclaim * @page: the page being evicted * * Returns a shadow entry to be stored in @page->mapping->i_pages in place * of the evicted @page so that a later refault can be detected. */ -void *workingset_eviction(struct page *page) +void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg) { struct pglist_data *pgdat = page_pgdat(page); - struct mem_cgroup *memcg = page_memcg(page); - int memcgid = mem_cgroup_id(memcg); unsigned long eviction; struct lruvec *lruvec; + int memcgid; /* Page is fully exclusive and pins page->mem_cgroup */ VM_BUG_ON_PAGE(PageLRU(page), page); VM_BUG_ON_PAGE(page_count(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); - lruvec = mem_cgroup_lruvec(memcg, pgdat); - eviction = atomic_long_inc_return(&lruvec->inactive_age); + advance_inactive_age(page_memcg(page), pgdat); + + lruvec = mem_cgroup_lruvec(target_memcg, pgdat); + /* XXX: target_memcg can be NULL, go through lruvec */ + memcgid = mem_cgroup_id(lruvec_memcg(lruvec)); + eviction = atomic_long_read(&lruvec->inactive_age); return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page)); } @@ -244,10 +269,13 @@ void *workingset_eviction(struct page *page) * @shadow: shadow entry of the evicted page * * Calculates and evaluates the refault distance of the previously - * evicted page in the context of the node it was allocated in. + * evicted page in the context of the node and the memcg whose memory + * pressure caused the eviction. */ void workingset_refault(struct page *page, void *shadow) { + struct mem_cgroup *eviction_memcg; + struct lruvec *eviction_lruvec; unsigned long refault_distance; struct pglist_data *pgdat; unsigned long active_file; @@ -277,12 +305,12 @@ void workingset_refault(struct page *page, void *shadow) * would be better if the root_mem_cgroup existed in all * configurations instead. */ - memcg = mem_cgroup_from_id(memcgid); - if (!mem_cgroup_disabled() && !memcg) + eviction_memcg = mem_cgroup_from_id(memcgid); + if (!mem_cgroup_disabled() && !eviction_memcg) goto out; - lruvec = mem_cgroup_lruvec(memcg, pgdat); - refault = atomic_long_read(&lruvec->inactive_age); - active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES); + eviction_lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat); + refault = atomic_long_read(&eviction_lruvec->inactive_age); + active_file = lruvec_page_state(eviction_lruvec, NR_ACTIVE_FILE); /* * Calculate the refault distance @@ -302,6 +330,17 @@ void workingset_refault(struct page *page, void *shadow) */ refault_distance = (refault - eviction) & EVICTION_MASK; + /* + * The activation decision for this page is made at the level + * where the eviction occurred, as that is where the LRU order + * during page reclaim is being determined. + * + * However, the cgroup that will own the page is the one that + * is actually experiencing the refault event. + */ + memcg = page_memcg(page); + lruvec = mem_cgroup_lruvec(memcg, pgdat); + inc_lruvec_state(lruvec, WORKINGSET_REFAULT); /* @@ -313,7 +352,7 @@ void workingset_refault(struct page *page, void *shadow) goto out; SetPageActive(page); - atomic_long_inc(&lruvec->inactive_age); + advance_inactive_age(memcg, pgdat); inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE); /* Page was active prior to eviction */ @@ -332,7 +371,6 @@ out: void workingset_activation(struct page *page) { struct mem_cgroup *memcg; - struct lruvec *lruvec; rcu_read_lock(); /* @@ -345,8 +383,7 @@ void workingset_activation(struct page *page) memcg = page_memcg_rcu(page); if (!mem_cgroup_disabled() && !memcg) goto out; - lruvec = mem_cgroup_lruvec(memcg, page_pgdat(page)); - atomic_long_inc(&lruvec->inactive_age); + advance_inactive_age(memcg, page_pgdat(page)); out: rcu_read_unlock(); } -- cgit v1.2.3-71-gd317 From b91ac374346ba206cfd568bb0ab830af6b205cfd Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Sat, 30 Nov 2019 17:56:02 -0800 Subject: mm: vmscan: enforce inactive:active ratio at the reclaim root We split the LRU lists into inactive and an active parts to maximize workingset protection while allowing just enough inactive cache space to faciltate readahead and writeback for one-off file accesses (e.g. a linear scan through a file, or logging); or just enough inactive anon to maintain recent reference information when reclaim needs to swap. With cgroups and their nested LRU lists, we currently don't do this correctly. While recursive cgroup reclaim establishes a relative LRU order among the pages of all involved cgroups, inactive:active size decisions are done on a per-cgroup level. As a result, we'll reclaim a cgroup's workingset when it doesn't have cold pages, even when one of its siblings has plenty of it that should be reclaimed first. For example: workload A has 50M worth of hot cache but doesn't do any one-off file accesses; meanwhile, parallel workload B scans files and rarely accesses the same page twice. If these workloads were to run in an uncgrouped system, A would be protected from the high rate of cache faults from B. But if they were put in parallel cgroups for memory accounting purposes, B's fast cache fault rate would push out the hot cache pages of A. This is unexpected and undesirable - the "scan resistance" of the page cache is broken. This patch moves inactive:active size balancing decisions to the root of reclaim - the same level where the LRU order is established. It does this by looking at the recursive size of the inactive and the active file sets of the cgroup subtree at the beginning of the reclaim cycle, and then making a decision - scan or skip active pages - that applies throughout the entire run and to every cgroup involved. With that in place, in the test above, the VM will recognize that there are plenty of inactive pages in the combined cache set of workloads A and B and prefer the one-off cache in B over the hot pages in A. The scan resistance of the cache is restored. [cai@lca.pw: fix some -Wenum-conversion warnings] Link: http://lkml.kernel.org/r/1573848697-29262-1-git-send-email-cai@lca.pw Link: http://lkml.kernel.org/r/20191107205334.158354-4-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Reviewed-by: Suren Baghdasaryan Reviewed-by: Shakeel Butt Cc: Andrey Ryabinin Cc: Rik van Riel Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 4 +- mm/vmscan.c | 185 +++++++++++++++++++++++++++++++------------------ 2 files changed, 118 insertions(+), 71 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ddee00e91a22..d9e62b0b584e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -273,12 +273,12 @@ enum lru_list { #define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_ACTIVE_FILE; lru++) -static inline int is_file_lru(enum lru_list lru) +static inline bool is_file_lru(enum lru_list lru) { return (lru == LRU_INACTIVE_FILE || lru == LRU_ACTIVE_FILE); } -static inline int is_active_lru(enum lru_list lru) +static inline bool is_active_lru(enum lru_list lru) { return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE); } diff --git a/mm/vmscan.c b/mm/vmscan.c index 39657012e2d8..23273293532b 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -79,6 +79,13 @@ struct scan_control { */ struct mem_cgroup *target_mem_cgroup; + /* Can active pages be deactivated as part of reclaim? */ +#define DEACTIVATE_ANON 1 +#define DEACTIVATE_FILE 2 + unsigned int may_deactivate:2; + unsigned int force_deactivate:1; + unsigned int skipped_deactivate:1; + /* Writepage batching in laptop mode; RECLAIM_WRITE */ unsigned int may_writepage:1; @@ -101,6 +108,9 @@ struct scan_control { /* One of the zones is ready for compaction */ unsigned int compaction_ready:1; + /* There is easily reclaimable cold cache in the current node */ + unsigned int cache_trim_mode:1; + /* The file pages on the current node are dangerously low */ unsigned int file_is_tiny:1; @@ -2154,6 +2164,20 @@ unsigned long reclaim_pages(struct list_head *page_list) return nr_reclaimed; } +static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, + struct lruvec *lruvec, struct scan_control *sc) +{ + if (is_active_lru(lru)) { + if (sc->may_deactivate & (1 << is_file_lru(lru))) + shrink_active_list(nr_to_scan, lruvec, sc, lru); + else + sc->skipped_deactivate = 1; + return 0; + } + + return shrink_inactive_list(nr_to_scan, lruvec, sc, lru); +} + /* * The inactive anon list should be small enough that the VM never has * to do too much work. @@ -2182,59 +2206,25 @@ unsigned long reclaim_pages(struct list_head *page_list) * 1TB 101 10GB * 10TB 320 32GB */ -static bool inactive_list_is_low(struct lruvec *lruvec, bool file, - struct scan_control *sc, bool trace) +static bool inactive_is_low(struct lruvec *lruvec, enum lru_list inactive_lru) { - enum lru_list active_lru = file * LRU_FILE + LRU_ACTIVE; - struct pglist_data *pgdat = lruvec_pgdat(lruvec); - enum lru_list inactive_lru = file * LRU_FILE; + enum lru_list active_lru = inactive_lru + LRU_ACTIVE; unsigned long inactive, active; unsigned long inactive_ratio; - struct lruvec *target_lruvec; - unsigned long refaults; unsigned long gb; - inactive = lruvec_lru_size(lruvec, inactive_lru, sc->reclaim_idx); - active = lruvec_lru_size(lruvec, active_lru, sc->reclaim_idx); + inactive = lruvec_page_state(lruvec, NR_LRU_BASE + inactive_lru); + active = lruvec_page_state(lruvec, NR_LRU_BASE + active_lru); - /* - * When refaults are being observed, it means a new workingset - * is being established. Disable active list protection to get - * rid of the stale workingset quickly. - */ - target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); - refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE); - if (file && target_lruvec->refaults != refaults) { - inactive_ratio = 0; - } else { - gb = (inactive + active) >> (30 - PAGE_SHIFT); - if (gb) - inactive_ratio = int_sqrt(10 * gb); - else - inactive_ratio = 1; - } - - if (trace) - trace_mm_vmscan_inactive_list_is_low(pgdat->node_id, sc->reclaim_idx, - lruvec_lru_size(lruvec, inactive_lru, MAX_NR_ZONES), inactive, - lruvec_lru_size(lruvec, active_lru, MAX_NR_ZONES), active, - inactive_ratio, file); + gb = (inactive + active) >> (30 - PAGE_SHIFT); + if (gb) + inactive_ratio = int_sqrt(10 * gb); + else + inactive_ratio = 1; return inactive * inactive_ratio < active; } -static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, - struct lruvec *lruvec, struct scan_control *sc) -{ - if (is_active_lru(lru)) { - if (inactive_list_is_low(lruvec, is_file_lru(lru), sc, true)) - shrink_active_list(nr_to_scan, lruvec, sc, lru); - return 0; - } - - return shrink_inactive_list(nr_to_scan, lruvec, sc, lru); -} - enum scan_balance { SCAN_EQUAL, SCAN_FRACT, @@ -2296,28 +2286,17 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, /* * If the system is almost out of file pages, force-scan anon. - * But only if there are enough inactive anonymous pages on - * the LRU. Otherwise, the small LRU gets thrashed. */ - if (sc->file_is_tiny && - !inactive_list_is_low(lruvec, false, sc, false) && - lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, - sc->reclaim_idx) >> sc->priority) { + if (sc->file_is_tiny) { scan_balance = SCAN_ANON; goto out; } /* - * If there is enough inactive page cache, i.e. if the size of the - * inactive list is greater than that of the active list *and* the - * inactive list actually has some pages to scan on this priority, we - * do not reclaim anything from the anonymous working set right now. - * Without the second condition we could end up never scanning an - * lruvec even if it has plenty of old anonymous pages unless the - * system is under heavy pressure. + * If there is enough inactive page cache, we do not reclaim + * anything from the anonymous working right now. */ - if (!inactive_list_is_low(lruvec, true, sc, false) && - lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, sc->reclaim_idx) >> sc->priority) { + if (sc->cache_trim_mode) { scan_balance = SCAN_FILE; goto out; } @@ -2582,7 +2561,7 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) * Even if we did not try to evict anon pages at all, we want to * rebalance the anon lru active/inactive ratio. */ - if (total_swap_pages && inactive_list_is_low(lruvec, false, sc, true)) + if (total_swap_pages && inactive_is_low(lruvec, LRU_INACTIVE_ANON)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); } @@ -2722,6 +2701,7 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc) unsigned long nr_reclaimed, nr_scanned; struct lruvec *target_lruvec; bool reclaimable = false; + unsigned long file; target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); @@ -2731,6 +2711,44 @@ again: nr_reclaimed = sc->nr_reclaimed; nr_scanned = sc->nr_scanned; + /* + * Target desirable inactive:active list ratios for the anon + * and file LRU lists. + */ + if (!sc->force_deactivate) { + unsigned long refaults; + + if (inactive_is_low(target_lruvec, LRU_INACTIVE_ANON)) + sc->may_deactivate |= DEACTIVATE_ANON; + else + sc->may_deactivate &= ~DEACTIVATE_ANON; + + /* + * When refaults are being observed, it means a new + * workingset is being established. Deactivate to get + * rid of any stale active pages quickly. + */ + refaults = lruvec_page_state(target_lruvec, + WORKINGSET_ACTIVATE); + if (refaults != target_lruvec->refaults || + inactive_is_low(target_lruvec, LRU_INACTIVE_FILE)) + sc->may_deactivate |= DEACTIVATE_FILE; + else + sc->may_deactivate &= ~DEACTIVATE_FILE; + } else + sc->may_deactivate = DEACTIVATE_ANON | DEACTIVATE_FILE; + + /* + * If we have plenty of inactive file pages that aren't + * thrashing, try to reclaim those first before touching + * anonymous pages. + */ + file = lruvec_page_state(target_lruvec, NR_INACTIVE_FILE); + if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE)) + sc->cache_trim_mode = 1; + else + sc->cache_trim_mode = 0; + /* * Prevent the reclaimer from falling into the cache trap: as * cache pages start out inactive, every cache fault will tip @@ -2741,10 +2759,9 @@ again: * anon pages. Try to detect this based on file LRU size. */ if (!cgroup_reclaim(sc)) { - unsigned long file; - unsigned long free; - int z; unsigned long total_high_wmark = 0; + unsigned long free, anon; + int z; free = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES); file = node_page_state(pgdat, NR_ACTIVE_FILE) + @@ -2758,7 +2775,17 @@ again: total_high_wmark += high_wmark_pages(zone); } - sc->file_is_tiny = file + free <= total_high_wmark; + /* + * Consider anon: if that's low too, this isn't a + * runaway file reclaim problem, but rather just + * extreme pressure. Reclaim as per usual then. + */ + anon = node_page_state(pgdat, NR_INACTIVE_ANON); + + sc->file_is_tiny = + file + free <= total_high_wmark && + !(sc->may_deactivate & DEACTIVATE_ANON) && + anon >> sc->priority; } shrink_node_memcgs(pgdat, sc); @@ -3062,9 +3089,27 @@ retry: if (sc->compaction_ready) return 1; + /* + * We make inactive:active ratio decisions based on the node's + * composition of memory, but a restrictive reclaim_idx or a + * memory.low cgroup setting can exempt large amounts of + * memory from reclaim. Neither of which are very common, so + * instead of doing costly eligibility calculations of the + * entire cgroup subtree up front, we assume the estimates are + * good, and retry with forcible deactivation if that fails. + */ + if (sc->skipped_deactivate) { + sc->priority = initial_priority; + sc->force_deactivate = 1; + sc->skipped_deactivate = 0; + goto retry; + } + /* Untapped cgroup reserves? Don't OOM, retry. */ if (sc->memcg_low_skipped) { sc->priority = initial_priority; + sc->force_deactivate = 0; + sc->skipped_deactivate = 0; sc->memcg_low_reclaim = 1; sc->memcg_low_skipped = 0; goto retry; @@ -3339,18 +3384,20 @@ static void age_active_anon(struct pglist_data *pgdat, struct scan_control *sc) { struct mem_cgroup *memcg; + struct lruvec *lruvec; if (!total_swap_pages) return; + lruvec = mem_cgroup_lruvec(NULL, pgdat); + if (!inactive_is_low(lruvec, LRU_INACTIVE_ANON)) + return; + memcg = mem_cgroup_iter(NULL, NULL, NULL); do { - struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); - - if (inactive_list_is_low(lruvec, false, sc, true)) - shrink_active_list(SWAP_CLUSTER_MAX, lruvec, - sc, LRU_ACTIVE_ANON); - + lruvec = mem_cgroup_lruvec(memcg, pgdat); + shrink_active_list(SWAP_CLUSTER_MAX, lruvec, + sc, LRU_ACTIVE_ANON); memcg = mem_cgroup_iter(NULL, memcg, NULL); } while (memcg); } -- cgit v1.2.3-71-gd317 From 0ac398b171aacd0f0c132d989ec4efb5de94f34a Mon Sep 17 00:00:00 2001 From: Yunfeng Ye Date: Sat, 30 Nov 2019 17:56:27 -0800 Subject: mm: support memblock alloc on the exact node for sparse_buffer_init() sparse_buffer_init() use memblock_alloc_try_nid_raw() to allocate memory for page management structure, if memory allocation fails from specified node, it will fall back to allocate from other nodes. Normally, the page management structure will not exceed 2% of the total memory, but a large continuous block of allocation is needed. In most cases, memory allocation from the specified node will succeed, but a node memory become highly fragmented will fail. we expect to allocate memory base section rather than by allocating a large block of memory from other NUMA nodes Add memblock_alloc_exact_nid_raw() for this situation, which allocate boot memory block on the exact node. If a large contiguous block memory allocate fail in sparse_buffer_init(), it will fall back to allocate small block memory base section. Link: http://lkml.kernel.org/r/66755ea7-ab10-8882-36fd-3e02b03775d5@huawei.com Signed-off-by: Yunfeng Ye Reviewed-by: Mike Rapoport Cc: Wei Yang Cc: Oscar Salvador Cc: Dan Williams Cc: David Hildenbrand Cc: Qian Cai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 3 +++ mm/memblock.c | 65 ++++++++++++++++++++++++++++++++++++++++-------- mm/sparse.c | 2 +- 3 files changed, 58 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index f491690d54c6..b38bbefabfab 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -358,6 +358,9 @@ static inline phys_addr_t memblock_phys_alloc(phys_addr_t size, MEMBLOCK_ALLOC_ACCESSIBLE); } +void *memblock_alloc_exact_nid_raw(phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid); void *memblock_alloc_try_nid_raw(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid); diff --git a/mm/memblock.c b/mm/memblock.c index 203ed317551b..4bc2c7d8bf42 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1319,12 +1319,13 @@ __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, * @start: the lower bound of the memory region to allocate (phys address) * @end: the upper bound of the memory region to allocate (phys address) * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * @exact_nid: control the allocation fall back to other nodes * * The allocation is performed from memory region limited by * memblock.current_limit if @end == %MEMBLOCK_ALLOC_ACCESSIBLE. * - * If the specified node can not hold the requested memory the - * allocation falls back to any node in the system + * If the specified node can not hold the requested memory and @exact_nid + * is false, the allocation falls back to any node in the system. * * For systems with memory mirroring, the allocation is attempted first * from the regions with mirroring enabled and then retried from any @@ -1338,7 +1339,8 @@ __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, */ static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, phys_addr_t align, phys_addr_t start, - phys_addr_t end, int nid) + phys_addr_t end, int nid, + bool exact_nid) { enum memblock_flags flags = choose_memblock_flags(); phys_addr_t found; @@ -1358,7 +1360,7 @@ again: if (found && !memblock_reserve(found, size)) goto done; - if (nid != NUMA_NO_NODE) { + if (nid != NUMA_NO_NODE && !exact_nid) { found = memblock_find_in_range_node(size, align, start, end, NUMA_NO_NODE, flags); @@ -1406,7 +1408,8 @@ phys_addr_t __init memblock_phys_alloc_range(phys_addr_t size, phys_addr_t start, phys_addr_t end) { - return memblock_alloc_range_nid(size, align, start, end, NUMA_NO_NODE); + return memblock_alloc_range_nid(size, align, start, end, NUMA_NO_NODE, + false); } /** @@ -1425,7 +1428,7 @@ phys_addr_t __init memblock_phys_alloc_range(phys_addr_t size, phys_addr_t __init memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid) { return memblock_alloc_range_nid(size, align, 0, - MEMBLOCK_ALLOC_ACCESSIBLE, nid); + MEMBLOCK_ALLOC_ACCESSIBLE, nid, false); } /** @@ -1435,6 +1438,7 @@ phys_addr_t __init memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t ali * @min_addr: the lower bound of the memory region to allocate (phys address) * @max_addr: the upper bound of the memory region to allocate (phys address) * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * @exact_nid: control the allocation fall back to other nodes * * Allocates memory block using memblock_alloc_range_nid() and * converts the returned physical address to virtual. @@ -1450,7 +1454,7 @@ phys_addr_t __init memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t ali static void * __init memblock_alloc_internal( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, - int nid) + int nid, bool exact_nid) { phys_addr_t alloc; @@ -1465,11 +1469,13 @@ static void * __init memblock_alloc_internal( if (max_addr > memblock.current_limit) max_addr = memblock.current_limit; - alloc = memblock_alloc_range_nid(size, align, min_addr, max_addr, nid); + alloc = memblock_alloc_range_nid(size, align, min_addr, max_addr, nid, + exact_nid); /* retry allocation without lower limit */ if (!alloc && min_addr) - alloc = memblock_alloc_range_nid(size, align, 0, max_addr, nid); + alloc = memblock_alloc_range_nid(size, align, 0, max_addr, nid, + exact_nid); if (!alloc) return NULL; @@ -1477,6 +1483,43 @@ static void * __init memblock_alloc_internal( return phys_to_virt(alloc); } +/** + * memblock_alloc_exact_nid_raw - allocate boot memory block on the exact node + * without zeroing memory + * @size: size of memory block to be allocated in bytes + * @align: alignment of the region and block's size + * @min_addr: the lower bound of the memory region from where the allocation + * is preferred (phys address) + * @max_addr: the upper bound of the memory region from where the allocation + * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to + * allocate only from memory limited by memblock.current_limit value + * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * + * Public function, provides additional debug information (including caller + * info), if enabled. Does not zero allocated memory. + * + * Return: + * Virtual address of allocated memory block on success, NULL on failure. + */ +void * __init memblock_alloc_exact_nid_raw( + phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid) +{ + void *ptr; + + memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n", + __func__, (u64)size, (u64)align, nid, &min_addr, + &max_addr, (void *)_RET_IP_); + + ptr = memblock_alloc_internal(size, align, + min_addr, max_addr, nid, true); + if (ptr && size > 0) + page_init_poison(ptr, size); + + return ptr; +} + /** * memblock_alloc_try_nid_raw - allocate boot memory block without zeroing * memory and without panicking @@ -1508,7 +1551,7 @@ void * __init memblock_alloc_try_nid_raw( &max_addr, (void *)_RET_IP_); ptr = memblock_alloc_internal(size, align, - min_addr, max_addr, nid); + min_addr, max_addr, nid, false); if (ptr && size > 0) page_init_poison(ptr, size); @@ -1543,7 +1586,7 @@ void * __init memblock_alloc_try_nid( __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); ptr = memblock_alloc_internal(size, align, - min_addr, max_addr, nid); + min_addr, max_addr, nid, false); if (ptr) memset(ptr, 0, size); diff --git a/mm/sparse.c b/mm/sparse.c index 8526d3bf1e4e..b20ab7cdac86 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -486,7 +486,7 @@ static void __init sparse_buffer_init(unsigned long size, int nid) * and we want it to be properly aligned to the section size - this is * especially the case for VMEMMAP which maps memmap to PMDs */ - sparsemap_buf = memblock_alloc_try_nid_raw(size, section_map_size(), + sparsemap_buf = memblock_alloc_exact_nid_raw(size, section_map_size(), addr, MEMBLOCK_ALLOC_ACCESSIBLE, nid); sparsemap_buf_end = sparsemap_buf + size; } -- cgit v1.2.3-71-gd317 From 552546366a30d88bd1d6f5efe848b2ab50fd57e5 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Sat, 30 Nov 2019 17:56:30 -0800 Subject: hugetlbfs: hugetlb_fault_mutex_hash() cleanup A new clang diagnostic (-Wsizeof-array-div) warns about the calculation to determine the number of u32's in an array of unsigned longs. Suppress warning by adding parentheses. While looking at the above issue, noticed that the 'address' parameter to hugetlb_fault_mutex_hash is no longer used. So, remove it from the definition and all callers. No functional change. Link: http://lkml.kernel.org/r/20190919011847.18400-1-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Reported-by: Nathan Chancellor Reviewed-by: Nathan Chancellor Reviewed-by: Davidlohr Bueso Reviewed-by: Andrew Morton Cc: Nick Desaulniers Cc: Ilie Halip Cc: David Bolvansky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 4 ++-- include/linux/hugetlb.h | 2 +- mm/hugetlb.c | 10 +++++----- mm/userfaultfd.c | 2 +- 4 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index a478df035651..6e5eadee6b0d 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -440,7 +440,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, u32 hash; index = page->index; - hash = hugetlb_fault_mutex_hash(h, mapping, index, 0); + hash = hugetlb_fault_mutex_hash(h, mapping, index); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* @@ -644,7 +644,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, addr = index * hpage_size; /* mutex taken here, fault path and hole punch */ - hash = hugetlb_fault_mutex_hash(h, mapping, index, addr); + hash = hugetlb_fault_mutex_hash(h, mapping, index); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* See if already present in mapping to avoid alloc/free */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 53fc34f930d0..d3814bd686ba 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -106,7 +106,7 @@ void free_huge_page(struct page *page); void hugetlb_fix_reserve_counts(struct inode *inode); extern struct mutex *hugetlb_fault_mutex_table; u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, - pgoff_t idx, unsigned long address); + pgoff_t idx); pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 26b722faf740..39579f98d6f3 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3842,7 +3842,7 @@ retry: * handling userfault. Reacquire after handling * fault to make calling code simpler. */ - hash = hugetlb_fault_mutex_hash(h, mapping, idx, haddr); + hash = hugetlb_fault_mutex_hash(h, mapping, idx); mutex_unlock(&hugetlb_fault_mutex_table[hash]); ret = handle_userfault(&vmf, VM_UFFD_MISSING); mutex_lock(&hugetlb_fault_mutex_table[hash]); @@ -3970,7 +3970,7 @@ backout_unlocked: #ifdef CONFIG_SMP u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, - pgoff_t idx, unsigned long address) + pgoff_t idx) { unsigned long key[2]; u32 hash; @@ -3978,7 +3978,7 @@ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, key[0] = (unsigned long) mapping; key[1] = idx; - hash = jhash2((u32 *)&key, sizeof(key)/sizeof(u32), 0); + hash = jhash2((u32 *)&key, sizeof(key)/(sizeof(u32)), 0); return hash & (num_fault_mutexes - 1); } @@ -3988,7 +3988,7 @@ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, * return 0 and avoid the hashing overhead. */ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, - pgoff_t idx, unsigned long address) + pgoff_t idx) { return 0; } @@ -4032,7 +4032,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, * get spurious allocation failures if two CPUs race to instantiate * the same page in the page cache. */ - hash = hugetlb_fault_mutex_hash(h, mapping, idx, haddr); + hash = hugetlb_fault_mutex_hash(h, mapping, idx); mutex_lock(&hugetlb_fault_mutex_table[hash]); entry = huge_ptep_get(ptep); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index c7ae74ce5ff3..640ff2bd9a69 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -269,7 +269,7 @@ retry: */ idx = linear_page_index(dst_vma, dst_addr); mapping = dst_vma->vm_file->f_mapping; - hash = hugetlb_fault_mutex_hash(h, mapping, idx, dst_addr); + hash = hugetlb_fault_mutex_hash(h, mapping, idx); mutex_lock(&hugetlb_fault_mutex_table[hash]); err = -ENOMEM; -- cgit v1.2.3-71-gd317 From 1f9dccb25b8fb48778149a002bb25d4ac2899633 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Sat, 30 Nov 2019 17:56:40 -0800 Subject: hugetlbfs: convert macros to static inline, fix sparse warning huge_pte_offset() produced a sparse warning due to an improper return type when the kernel was built with !CONFIG_HUGETLB_PAGE. Fix the bad type and also convert all the macros in this block to static inline wrappers. Two existing wrappers in this block had lines in excess of 80 columns so clean those up as well. No functional change. Link: http://lkml.kernel.org/r/20191112194558.139389-3-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Reported-by: Ben Dooks Suggested-by: Jason Gunthorpe Cc: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 137 ++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 115 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index d3814bd686ba..159d2012cdb1 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -164,38 +164,130 @@ static inline void adjust_range_if_pmd_sharing_possible( { } -#define follow_hugetlb_page(m,v,p,vs,a,b,i,w,n) ({ BUG(); 0; }) -#define follow_huge_addr(mm, addr, write) ERR_PTR(-EINVAL) -#define copy_hugetlb_page_range(src, dst, vma) ({ BUG(); 0; }) +static inline long follow_hugetlb_page(struct mm_struct *mm, + struct vm_area_struct *vma, struct page **pages, + struct vm_area_struct **vmas, unsigned long *position, + unsigned long *nr_pages, long i, unsigned int flags, + int *nonblocking) +{ + BUG(); + return 0; +} + +static inline struct page *follow_huge_addr(struct mm_struct *mm, + unsigned long address, int write) +{ + return ERR_PTR(-EINVAL); +} + +static inline int copy_hugetlb_page_range(struct mm_struct *dst, + struct mm_struct *src, struct vm_area_struct *vma) +{ + BUG(); + return 0; +} + static inline void hugetlb_report_meminfo(struct seq_file *m) { } -#define hugetlb_report_node_meminfo(n, buf) 0 + +static inline int hugetlb_report_node_meminfo(int nid, char *buf) +{ + return 0; +} + static inline void hugetlb_show_meminfo(void) { } -#define follow_huge_pd(vma, addr, hpd, flags, pdshift) NULL -#define follow_huge_pmd(mm, addr, pmd, flags) NULL -#define follow_huge_pud(mm, addr, pud, flags) NULL -#define follow_huge_pgd(mm, addr, pgd, flags) NULL -#define prepare_hugepage_range(file, addr, len) (-EINVAL) -#define pmd_huge(x) 0 -#define pud_huge(x) 0 -#define is_hugepage_only_range(mm, addr, len) 0 -#define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; }) -#define hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \ - src_addr, pagep) ({ BUG(); 0; }) -#define huge_pte_offset(mm, address, sz) 0 + +static inline struct page *follow_huge_pd(struct vm_area_struct *vma, + unsigned long address, hugepd_t hpd, int flags, + int pdshift) +{ + return NULL; +} + +static inline struct page *follow_huge_pmd(struct mm_struct *mm, + unsigned long address, pmd_t *pmd, int flags) +{ + return NULL; +} + +static inline struct page *follow_huge_pud(struct mm_struct *mm, + unsigned long address, pud_t *pud, int flags) +{ + return NULL; +} + +static inline struct page *follow_huge_pgd(struct mm_struct *mm, + unsigned long address, pgd_t *pgd, int flags) +{ + return NULL; +} + +static inline int prepare_hugepage_range(struct file *file, + unsigned long addr, unsigned long len) +{ + return -EINVAL; +} + +static inline int pmd_huge(pmd_t pmd) +{ + return 0; +} + +static inline int pud_huge(pud_t pud) +{ + return 0; +} + +static inline int is_hugepage_only_range(struct mm_struct *mm, + unsigned long addr, unsigned long len) +{ + return 0; +} + +static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, + unsigned long addr, unsigned long end, + unsigned long floor, unsigned long ceiling) +{ + BUG(); +} + +static inline int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, + pte_t *dst_pte, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + struct page **pagep) +{ + BUG(); + return 0; +} + +static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, + unsigned long sz) +{ + return NULL; +} static inline bool isolate_huge_page(struct page *page, struct list_head *list) { return false; } -#define putback_active_hugepage(p) do {} while (0) -#define move_hugetlb_state(old, new, reason) do {} while (0) -static inline unsigned long hugetlb_change_protection(struct vm_area_struct *vma, - unsigned long address, unsigned long end, pgprot_t newprot) +static inline void putback_active_hugepage(struct page *page) +{ +} + +static inline void move_hugetlb_state(struct page *oldpage, + struct page *newpage, int reason) +{ +} + +static inline unsigned long hugetlb_change_protection( + struct vm_area_struct *vma, unsigned long address, + unsigned long end, pgprot_t newprot) { return 0; } @@ -213,9 +305,10 @@ static inline void __unmap_hugepage_range(struct mmu_gather *tlb, { BUG(); } + static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, - struct vm_area_struct *vma, unsigned long address, - unsigned int flags) + struct vm_area_struct *vma, unsigned long address, + unsigned int flags) { BUG(); return 0; -- cgit v1.2.3-71-gd317 From 188b04a7d93860fd100b2671600b8ad81fb0a842 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Sat, 30 Nov 2019 17:57:02 -0800 Subject: hugetlb: remove unused hstate in hugetlb_fault_mutex_hash() The first parameter hstate in function hugetlb_fault_mutex_hash() is not used anymore. This patch removes it. [akpm@linux-foundation.org: various build fixes] [cai@lca.pw: fix a GCC compilation warning] Link: http://lkml.kernel.org/r/1570544108-32331-1-git-send-email-cai@lca.pw Link: http://lkml.kernel.org/r/20191005003302.785-1-richardw.yang@linux.intel.com Signed-off-by: Wei Yang Signed-off-by: Qian Cai Suggested-by: Andrew Morton Reviewed-by: Andrew Morton Cc: Mike Kravetz Cc: Hugh Dickins Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 4 ++-- include/linux/hugetlb.h | 3 +-- mm/hugetlb.c | 10 ++++------ mm/userfaultfd.c | 5 +---- 4 files changed, 8 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index c978061c3893..d5c2a3158610 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -440,7 +440,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, u32 hash; index = page->index; - hash = hugetlb_fault_mutex_hash(h, mapping, index); + hash = hugetlb_fault_mutex_hash(mapping, index); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* @@ -644,7 +644,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, addr = index * hpage_size; /* mutex taken here, fault path and hole punch */ - hash = hugetlb_fault_mutex_hash(h, mapping, index); + hash = hugetlb_fault_mutex_hash(mapping, index); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* See if already present in mapping to avoid alloc/free */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 159d2012cdb1..31d4920994b9 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -105,8 +105,7 @@ void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason); void free_huge_page(struct page *page); void hugetlb_fix_reserve_counts(struct inode *inode); extern struct mutex *hugetlb_fault_mutex_table; -u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, - pgoff_t idx); +u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx); pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index a8e43aa9c670..8624b7758abb 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3796,7 +3796,7 @@ retry: * handling userfault. Reacquire after handling * fault to make calling code simpler. */ - hash = hugetlb_fault_mutex_hash(h, mapping, idx); + hash = hugetlb_fault_mutex_hash(mapping, idx); mutex_unlock(&hugetlb_fault_mutex_table[hash]); ret = handle_userfault(&vmf, VM_UFFD_MISSING); mutex_lock(&hugetlb_fault_mutex_table[hash]); @@ -3923,8 +3923,7 @@ backout_unlocked: } #ifdef CONFIG_SMP -u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, - pgoff_t idx) +u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) { unsigned long key[2]; u32 hash; @@ -3941,8 +3940,7 @@ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, * For uniprocesor systems we always use a single mutex, so just * return 0 and avoid the hashing overhead. */ -u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, - pgoff_t idx) +u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) { return 0; } @@ -3986,7 +3984,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, * get spurious allocation failures if two CPUs race to instantiate * the same page in the page cache. */ - hash = hugetlb_fault_mutex_hash(h, mapping, idx); + hash = hugetlb_fault_mutex_hash(mapping, idx); mutex_lock(&hugetlb_fault_mutex_table[hash]); entry = huge_ptep_get(ptep); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 640ff2bd9a69..6d152741bb26 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -184,7 +184,6 @@ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, unsigned long src_addr, dst_addr; long copied; struct page *page; - struct hstate *h; unsigned long vma_hpagesize; pgoff_t idx; u32 hash; @@ -256,8 +255,6 @@ retry: goto out_unlock; } - h = hstate_vma(dst_vma); - while (src_addr < src_start + len) { pte_t dst_pteval; @@ -269,7 +266,7 @@ retry: */ idx = linear_page_index(dst_vma, dst_addr); mapping = dst_vma->vm_file->f_mapping; - hash = hugetlb_fault_mutex_hash(h, mapping, idx); + hash = hugetlb_fault_mutex_hash(mapping, idx); mutex_lock(&hugetlb_fault_mutex_table[hash]); err = -ENOMEM; -- cgit v1.2.3-71-gd317 From 84218b552e0a591ac706a926d5e1e8eaf0d5a03a Mon Sep 17 00:00:00 2001 From: Hao Lee Date: Sat, 30 Nov 2019 17:58:14 -0800 Subject: mm: fix struct member name in function comments The member in struct zonelist is _zonerefs instead of zones. Link: http://lkml.kernel.org/r/20190927144049.GA29622@haolee.github.io Signed-off-by: Hao Lee Reviewed-by: Andrew Morton Reviewed-by: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index d9e62b0b584e..89d8ff06c9ce 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1085,7 +1085,7 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, /** * for_each_zone_zonelist_nodemask - helper macro to iterate over valid zones in a zonelist at or below a given zone index and within a nodemask * @zone - The current zone in the iterator - * @z - The current pointer within zonelist->zones being iterated + * @z - The current pointer within zonelist->_zonerefs being iterated * @zlist - The zonelist being iterated * @highidx - The zone index of the highest zone to return * @nodemask - Nodemask allowed by the allocator -- cgit v1.2.3-71-gd317 From 12cc1c7345b6bf34c45ccaa75393e2d6eb707d7b Mon Sep 17 00:00:00 2001 From: Souptick Joarder Date: Sat, 30 Nov 2019 17:58:20 -0800 Subject: mm/memory_hotplug.c: remove __online_page_set_limits() __online_page_set_limits() is a dummy function - remove it and all callers. Link: http://lkml.kernel.org/r/8e1bc9d3b492f6bde16e95ebc1dee11d6aefabd7.1567889743.git.jrdr.linux@gmail.com Link: http://lkml.kernel.org/r/854db2cf8145d9635249c95584d9a91fd774a229.1567889743.git.jrdr.linux@gmail.com Link: http://lkml.kernel.org/r/9afe6c5a18158f3884a6b302ac2c772f3da49ccc.1567889743.git.jrdr.linux@gmail.com Signed-off-by: Souptick Joarder Reviewed-by: David Hildenbrand Acked-by: Michal Hocko Cc: Juergen Gross Cc: "Kirill A. Shutemov" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/hv/hv_balloon.c | 1 - drivers/xen/balloon.c | 1 - include/linux/memory_hotplug.h | 2 -- mm/memory_hotplug.c | 5 ----- 4 files changed, 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index 65ab170d4a9a..da6ced15c6c5 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -680,7 +680,6 @@ static void hv_page_online_one(struct hv_hotadd_state *has, struct page *pg) __ClearPageOffline(pg); /* This frame is currently backed; online the page. */ - __online_page_set_limits(pg); generic_online_page(pg, 0); lockdep_assert_held(&dm_device.ha_lock); diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 5bae515c8e25..4f2e78a5e4db 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -374,7 +374,6 @@ static void xen_online_page(struct page *page, unsigned int order) mutex_lock(&balloon_mutex); for (i = 0; i < size; i++) { p = pfn_to_page(start_pfn + i); - __online_page_set_limits(p); balloon_append(p); } mutex_unlock(&balloon_mutex); diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 101d97e7e2ac..3a08ecdfca11 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -106,8 +106,6 @@ extern void generic_online_page(struct page *page, unsigned int order); extern int set_online_page_callback(online_page_callback_t callback); extern int restore_online_page_callback(online_page_callback_t callback); -extern void __online_page_set_limits(struct page *page); - extern int try_online_node(int nid); extern int arch_add_memory(int nid, u64 start, u64 size, diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index fee3bacdd700..55ac23ef11c1 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -598,11 +598,6 @@ int restore_online_page_callback(online_page_callback_t callback) } EXPORT_SYMBOL_GPL(restore_online_page_callback); -void __online_page_set_limits(struct page *page) -{ -} -EXPORT_SYMBOL_GPL(__online_page_set_limits); - void generic_online_page(struct page *page, unsigned int order) { kernel_map_pages(page, 1 << order, 1); -- cgit v1.2.3-71-gd317 From 040b5cfbcefa263ccf2c118c4938308606bb7ed8 Mon Sep 17 00:00:00 2001 From: Martin Varghese Date: Mon, 2 Dec 2019 10:49:51 +0530 Subject: Fixed updating of ethertype in function skb_mpls_pop The skb_mpls_pop was not updating ethertype of an ethernet packet if the packet was originally received from a non ARPHRD_ETHER device. In the below OVS data path flow, since the device corresponding to port 7 is an l3 device (ARPHRD_NONE) the skb_mpls_pop function does not update the ethertype of the packet even though the previous push_eth action had added an ethernet header to the packet. recirc_id(0),in_port(7),eth_type(0x8847), mpls(label=12/0xfffff,tc=0/0,ttl=0/0x0,bos=1/1), actions:push_eth(src=00:00:00:00:00:00,dst=00:00:00:00:00:00), pop_mpls(eth_type=0x800),4 Fixes: ed246cee09b9 ("net: core: move pop MPLS functionality from OvS to core helper") Signed-off-by: Martin Varghese Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 ++- net/core/skbuff.c | 6 ++++-- net/openvswitch/actions.c | 3 ++- net/sched/act_mpls.c | 4 +++- 4 files changed, 11 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7af5bec7d3b0..5aea72fe8498 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3530,7 +3530,8 @@ int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, int mac_len); -int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len); +int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, + bool ethernet); int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse); int skb_mpls_dec_ttl(struct sk_buff *skb); struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 867e61df00db..312e80e86898 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5529,12 +5529,14 @@ EXPORT_SYMBOL_GPL(skb_mpls_push); * @skb: buffer * @next_proto: ethertype of header after popped MPLS header * @mac_len: length of the MAC header + * @ethernet: flag to indicate if ethernet header is present in packet * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ -int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len) +int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, + bool ethernet) { int err; @@ -5553,7 +5555,7 @@ int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len) skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); - if (skb->dev && skb->dev->type == ARPHRD_ETHER) { + if (ethernet) { struct ethhdr *hdr; /* use mpls_hdr() to get ethertype to account for VLANs. */ diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 12936c151cc0..91e210061bb3 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -179,7 +179,8 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key, { int err; - err = skb_mpls_pop(skb, ethertype, skb->mac_len); + err = skb_mpls_pop(skb, ethertype, skb->mac_len, + ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET); if (err) return err; diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index 325eddcc6621..a7d856203af1 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (C) 2019 Netronome Systems, Inc. */ +#include #include #include #include @@ -76,7 +77,8 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, switch (p->tcfm_action) { case TCA_MPLS_ACT_POP: - if (skb_mpls_pop(skb, p->tcfm_proto, mac_len)) + if (skb_mpls_pop(skb, p->tcfm_proto, mac_len, + skb->dev && skb->dev->type == ARPHRD_ETHER)) goto drop; break; case TCA_MPLS_ACT_PUSH: -- cgit v1.2.3-71-gd317 From 9e0afe3910ff7e5493c5d8ebe3b499994b5e0272 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Tue, 3 Dec 2019 11:20:37 +0100 Subject: firmware: dmi: Remember the memory type Store the memory type while walking the memory slots, and provide a way to retrieve it later. Signed-off-by: Jean Delvare --- drivers/firmware/dmi_scan.c | 25 ++++++++++++++++++++++++- include/linux/dmi.h | 2 ++ 2 files changed, 26 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index 1e21fc3e9851..6f28e515fdc0 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -35,6 +35,7 @@ static struct dmi_memdev_info { const char *bank; u64 size; /* bytes */ u16 handle; + u8 type; /* DDR2, DDR3, DDR4 etc */ } *dmi_memdev; static int dmi_memdev_nr; @@ -391,7 +392,7 @@ static void __init save_mem_devices(const struct dmi_header *dm, void *v) u64 bytes; u16 size; - if (dm->type != DMI_ENTRY_MEM_DEVICE || dm->length < 0x12) + if (dm->type != DMI_ENTRY_MEM_DEVICE || dm->length < 0x13) return; if (nr >= dmi_memdev_nr) { pr_warn(FW_BUG "Too many DIMM entries in SMBIOS table\n"); @@ -400,6 +401,7 @@ static void __init save_mem_devices(const struct dmi_header *dm, void *v) dmi_memdev[nr].handle = get_unaligned(&dm->handle); dmi_memdev[nr].device = dmi_string(dm, d[0x10]); dmi_memdev[nr].bank = dmi_string(dm, d[0x11]); + dmi_memdev[nr].type = d[0x12]; size = get_unaligned((u16 *)&d[0xC]); if (size == 0) @@ -1128,3 +1130,24 @@ u64 dmi_memdev_size(u16 handle) return ~0ull; } EXPORT_SYMBOL_GPL(dmi_memdev_size); + +/** + * dmi_memdev_type - get the memory type + * @handle: DMI structure handle + * + * Return the DMI memory type of the module in the slot associated with the + * given DMI handle, or 0x0 if no such DMI handle exists. + */ +u8 dmi_memdev_type(u16 handle) +{ + int n; + + if (dmi_memdev) { + for (n = 0; n < dmi_memdev_nr; n++) { + if (handle == dmi_memdev[n].handle) + return dmi_memdev[n].type; + } + } + return 0x0; /* Not a valid value */ +} +EXPORT_SYMBOL_GPL(dmi_memdev_type); diff --git a/include/linux/dmi.h b/include/linux/dmi.h index 8de8c4f15163..13a48b167e2d 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -113,6 +113,7 @@ extern int dmi_walk(void (*decode)(const struct dmi_header *, void *), extern bool dmi_match(enum dmi_field f, const char *str); extern void dmi_memdev_name(u16 handle, const char **bank, const char **device); extern u64 dmi_memdev_size(u16 handle); +extern u8 dmi_memdev_type(u16 handle); #else @@ -142,6 +143,7 @@ static inline bool dmi_match(enum dmi_field f, const char *str) static inline void dmi_memdev_name(u16 handle, const char **bank, const char **device) { } static inline u64 dmi_memdev_size(u16 handle) { return ~0ul; } +static inline u8 dmi_memdev_type(u16 handle) { return 0x0; } static inline const struct dmi_system_id * dmi_first_match(const struct dmi_system_id *list) { return NULL; } -- cgit v1.2.3-71-gd317 From 7c2378800cf7ac87e2663afa7f39d102871f0c28 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Tue, 3 Dec 2019 11:20:37 +0100 Subject: firmware: dmi: Add dmi_memdev_handle Add a utility function dmi_memdev_handle() which returns the DMI handle associated with a given memory slot. This will allow kernel drivers to iterate over the memory slots. Signed-off-by: Jean Delvare --- drivers/firmware/dmi_scan.c | 16 ++++++++++++++++ include/linux/dmi.h | 2 ++ 2 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index 6f28e515fdc0..2045566d622f 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -1151,3 +1151,19 @@ u8 dmi_memdev_type(u16 handle) return 0x0; /* Not a valid value */ } EXPORT_SYMBOL_GPL(dmi_memdev_type); + +/** + * dmi_memdev_handle - get the DMI handle of a memory slot + * @slot: slot number + * + * Return the DMI handle associated with a given memory slot, or %0xFFFF + * if there is no such slot. + */ +u16 dmi_memdev_handle(int slot) +{ + if (dmi_memdev && slot >= 0 && slot < dmi_memdev_nr) + return dmi_memdev[slot].handle; + + return 0xffff; /* Not a valid value */ +} +EXPORT_SYMBOL_GPL(dmi_memdev_handle); diff --git a/include/linux/dmi.h b/include/linux/dmi.h index 13a48b167e2d..927f8a8b7a1d 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -114,6 +114,7 @@ extern bool dmi_match(enum dmi_field f, const char *str); extern void dmi_memdev_name(u16 handle, const char **bank, const char **device); extern u64 dmi_memdev_size(u16 handle); extern u8 dmi_memdev_type(u16 handle); +extern u16 dmi_memdev_handle(int slot); #else @@ -144,6 +145,7 @@ static inline void dmi_memdev_name(u16 handle, const char **bank, const char **device) { } static inline u64 dmi_memdev_size(u16 handle) { return ~0ul; } static inline u8 dmi_memdev_type(u16 handle) { return 0x0; } +static inline u16 dmi_memdev_handle(int slot) { return 0xffff; } static inline const struct dmi_system_id * dmi_first_match(const struct dmi_system_id *list) { return NULL; } -- cgit v1.2.3-71-gd317 From 03b1230ca12a12e045d83b0357792075bf94a1e0 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 2 Dec 2019 18:50:25 -0700 Subject: io_uring: ensure async punted sendmsg/recvmsg requests copy data Just like commit f67676d160c6 for read/write requests, this one ensures that the msghdr data is fully copied if we need to punt a recvmsg or sendmsg system call to async context. Signed-off-by: Jens Axboe --- fs/io_uring.c | 145 +++++++++++++++++++++++++++++++++++++++++++------ include/linux/socket.h | 15 +++-- net/socket.c | 60 ++++++-------------- 3 files changed, 156 insertions(+), 64 deletions(-) (limited to 'include/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index 1689aea55527..2700382ebcc7 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -308,6 +308,13 @@ struct io_timeout { struct io_timeout_data *data; }; +struct io_async_msghdr { + struct iovec fast_iov[UIO_FASTIOV]; + struct iovec *iov; + struct sockaddr __user *uaddr; + struct msghdr msg; +}; + struct io_async_rw { struct iovec fast_iov[UIO_FASTIOV]; struct iovec *iov; @@ -319,6 +326,7 @@ struct io_async_ctx { struct io_uring_sqe sqe; union { struct io_async_rw rw; + struct io_async_msghdr msg; }; }; @@ -1991,12 +1999,25 @@ static int io_sync_file_range(struct io_kiocb *req, return 0; } +static int io_sendmsg_prep(struct io_kiocb *req, struct io_async_ctx *io) +{ #if defined(CONFIG_NET) -static int io_send_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, - struct io_kiocb **nxt, bool force_nonblock, - long (*fn)(struct socket *, struct user_msghdr __user *, - unsigned int)) + const struct io_uring_sqe *sqe = req->sqe; + struct user_msghdr __user *msg; + unsigned flags; + + flags = READ_ONCE(sqe->msg_flags); + msg = (struct user_msghdr __user *)(unsigned long) READ_ONCE(sqe->addr); + return sendmsg_copy_msghdr(&io->msg.msg, msg, flags, &io->msg.iov); +#else + return 0; +#endif +} + +static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, + struct io_kiocb **nxt, bool force_nonblock) { +#if defined(CONFIG_NET) struct socket *sock; int ret; @@ -2005,7 +2026,9 @@ static int io_send_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, sock = sock_from_file(req->file, &ret); if (sock) { - struct user_msghdr __user *msg; + struct io_async_ctx io, *copy; + struct sockaddr_storage addr; + struct msghdr *kmsg; unsigned flags; flags = READ_ONCE(sqe->msg_flags); @@ -2014,32 +2037,59 @@ static int io_send_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, else if (force_nonblock) flags |= MSG_DONTWAIT; - msg = (struct user_msghdr __user *) (unsigned long) - READ_ONCE(sqe->addr); + if (req->io) { + kmsg = &req->io->msg.msg; + kmsg->msg_name = &addr; + } else { + kmsg = &io.msg.msg; + kmsg->msg_name = &addr; + io.msg.iov = io.msg.fast_iov; + ret = io_sendmsg_prep(req, &io); + if (ret) + goto out; + } - ret = fn(sock, msg, flags); - if (force_nonblock && ret == -EAGAIN) + ret = __sys_sendmsg_sock(sock, kmsg, flags); + if (force_nonblock && ret == -EAGAIN) { + copy = kmalloc(sizeof(*copy), GFP_KERNEL); + if (!copy) { + ret = -ENOMEM; + goto out; + } + memcpy(©->msg, &io.msg, sizeof(copy->msg)); + req->io = copy; + memcpy(&req->io->sqe, req->sqe, sizeof(*req->sqe)); + req->sqe = &req->io->sqe; return ret; + } if (ret == -ERESTARTSYS) ret = -EINTR; } +out: io_cqring_add_event(req, ret); if (ret < 0 && (req->flags & REQ_F_LINK)) req->flags |= REQ_F_FAIL_LINK; io_put_req_find_next(req, nxt); return 0; -} +#else + return -EOPNOTSUPP; #endif +} -static int io_sendmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, - struct io_kiocb **nxt, bool force_nonblock) +static int io_recvmsg_prep(struct io_kiocb *req, struct io_async_ctx *io) { #if defined(CONFIG_NET) - return io_send_recvmsg(req, sqe, nxt, force_nonblock, - __sys_sendmsg_sock); + const struct io_uring_sqe *sqe = req->sqe; + struct user_msghdr __user *msg; + unsigned flags; + + flags = READ_ONCE(sqe->msg_flags); + msg = (struct user_msghdr __user *)(unsigned long) READ_ONCE(sqe->addr); + return recvmsg_copy_msghdr(&io->msg.msg, msg, flags, &io->msg.uaddr, + &io->msg.iov); #else - return -EOPNOTSUPP; + return 0; #endif } @@ -2047,8 +2097,63 @@ static int io_recvmsg(struct io_kiocb *req, const struct io_uring_sqe *sqe, struct io_kiocb **nxt, bool force_nonblock) { #if defined(CONFIG_NET) - return io_send_recvmsg(req, sqe, nxt, force_nonblock, - __sys_recvmsg_sock); + struct socket *sock; + int ret; + + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + + sock = sock_from_file(req->file, &ret); + if (sock) { + struct user_msghdr __user *msg; + struct io_async_ctx io, *copy; + struct sockaddr_storage addr; + struct msghdr *kmsg; + unsigned flags; + + flags = READ_ONCE(sqe->msg_flags); + if (flags & MSG_DONTWAIT) + req->flags |= REQ_F_NOWAIT; + else if (force_nonblock) + flags |= MSG_DONTWAIT; + + msg = (struct user_msghdr __user *) (unsigned long) + READ_ONCE(sqe->addr); + if (req->io) { + kmsg = &req->io->msg.msg; + kmsg->msg_name = &addr; + } else { + kmsg = &io.msg.msg; + kmsg->msg_name = &addr; + io.msg.iov = io.msg.fast_iov; + ret = io_recvmsg_prep(req, &io); + if (ret) + goto out; + } + + ret = __sys_recvmsg_sock(sock, kmsg, msg, io.msg.uaddr, flags); + if (force_nonblock && ret == -EAGAIN) { + copy = kmalloc(sizeof(*copy), GFP_KERNEL); + if (!copy) { + ret = -ENOMEM; + goto out; + } + memcpy(copy, &io, sizeof(*copy)); + req->io = copy; + memcpy(&req->io->sqe, req->sqe, sizeof(*req->sqe)); + req->sqe = &req->io->sqe; + return ret; + } + if (ret == -ERESTARTSYS) + ret = -EINTR; + } + +out: + io_cqring_add_event(req, ret); + if (ret < 0 && (req->flags & REQ_F_LINK)) + req->flags |= REQ_F_FAIL_LINK; + io_put_req_find_next(req, nxt); + return 0; #else return -EOPNOTSUPP; #endif @@ -2721,6 +2826,12 @@ static int io_req_defer_prep(struct io_kiocb *req, struct io_async_ctx *io) case IORING_OP_WRITE_FIXED: ret = io_write_prep(req, &iovec, &iter, true); break; + case IORING_OP_SENDMSG: + ret = io_sendmsg_prep(req, io); + break; + case IORING_OP_RECVMSG: + ret = io_recvmsg_prep(req, io); + break; default: req->io = io; return 0; diff --git a/include/linux/socket.h b/include/linux/socket.h index 4bde63021c09..903507fb901f 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -378,12 +378,19 @@ extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, bool forbid_cmsg_compat); -extern long __sys_sendmsg_sock(struct socket *sock, - struct user_msghdr __user *msg, +extern long __sys_sendmsg_sock(struct socket *sock, struct msghdr *msg, unsigned int flags); -extern long __sys_recvmsg_sock(struct socket *sock, - struct user_msghdr __user *msg, +extern long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg, + struct user_msghdr __user *umsg, + struct sockaddr __user *uaddr, unsigned int flags); +extern int sendmsg_copy_msghdr(struct msghdr *msg, + struct user_msghdr __user *umsg, unsigned flags, + struct iovec **iov); +extern int recvmsg_copy_msghdr(struct msghdr *msg, + struct user_msghdr __user *umsg, unsigned flags, + struct sockaddr __user **uaddr, + struct iovec **iov); /* helpers which do the actual work for syscalls */ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, diff --git a/net/socket.c b/net/socket.c index ea28cbb9e2e7..0fb0820edeec 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2346,9 +2346,9 @@ out: return err; } -static int sendmsg_copy_msghdr(struct msghdr *msg, - struct user_msghdr __user *umsg, unsigned flags, - struct iovec **iov) +int sendmsg_copy_msghdr(struct msghdr *msg, + struct user_msghdr __user *umsg, unsigned flags, + struct iovec **iov) { int err; @@ -2390,27 +2390,14 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, /* * BSD sendmsg interface */ -long __sys_sendmsg_sock(struct socket *sock, struct user_msghdr __user *umsg, +long __sys_sendmsg_sock(struct socket *sock, struct msghdr *msg, unsigned int flags) { - struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; - struct sockaddr_storage address; - struct msghdr msg = { .msg_name = &address }; - ssize_t err; - - err = sendmsg_copy_msghdr(&msg, umsg, flags, &iov); - if (err) - return err; /* disallow ancillary data requests from this path */ - if (msg.msg_control || msg.msg_controllen) { - err = -EINVAL; - goto out; - } + if (msg->msg_control || msg->msg_controllen) + return -EINVAL; - err = ____sys_sendmsg(sock, &msg, flags, NULL, 0); -out: - kfree(iov); - return err; + return ____sys_sendmsg(sock, msg, flags, NULL, 0); } long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, @@ -2516,10 +2503,10 @@ SYSCALL_DEFINE4(sendmmsg, int, fd, struct mmsghdr __user *, mmsg, return __sys_sendmmsg(fd, mmsg, vlen, flags, true); } -static int recvmsg_copy_msghdr(struct msghdr *msg, - struct user_msghdr __user *umsg, unsigned flags, - struct sockaddr __user **uaddr, - struct iovec **iov) +int recvmsg_copy_msghdr(struct msghdr *msg, + struct user_msghdr __user *umsg, unsigned flags, + struct sockaddr __user **uaddr, + struct iovec **iov) { ssize_t err; @@ -2609,28 +2596,15 @@ static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg, * BSD recvmsg interface */ -long __sys_recvmsg_sock(struct socket *sock, struct user_msghdr __user *umsg, - unsigned int flags) +long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg, + struct user_msghdr __user *umsg, + struct sockaddr __user *uaddr, unsigned int flags) { - struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; - struct sockaddr_storage address; - struct msghdr msg = { .msg_name = &address }; - struct sockaddr __user *uaddr; - ssize_t err; - - err = recvmsg_copy_msghdr(&msg, umsg, flags, &uaddr, &iov); - if (err) - return err; /* disallow ancillary data requests from this path */ - if (msg.msg_control || msg.msg_controllen) { - err = -EINVAL; - goto out; - } + if (msg->msg_control || msg->msg_controllen) + return -EINVAL; - err = ____sys_recvmsg(sock, &msg, umsg, uaddr, flags, 0); -out: - kfree(iov); - return err; + return ____sys_recvmsg(sock, msg, umsg, uaddr, flags, 0); } long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, -- cgit v1.2.3-71-gd317 From f499a021ea8c9f70321fce3d674d8eca5bbeee2c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 2 Dec 2019 16:28:46 -0700 Subject: io_uring: ensure async punted connect requests copy data Just like commit f67676d160c6 for read/write requests, this one ensures that the sockaddr data has been copied for IORING_OP_CONNECT if we need to punt the request to async context. Signed-off-by: Jens Axboe --- fs/io_uring.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++---- include/linux/socket.h | 5 ++--- net/socket.c | 16 ++++++++-------- 3 files changed, 57 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index 2700382ebcc7..5fcd89c507ec 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -308,6 +308,10 @@ struct io_timeout { struct io_timeout_data *data; }; +struct io_async_connect { + struct sockaddr_storage address; +}; + struct io_async_msghdr { struct iovec fast_iov[UIO_FASTIOV]; struct iovec *iov; @@ -327,6 +331,7 @@ struct io_async_ctx { union { struct io_async_rw rw; struct io_async_msghdr msg; + struct io_async_connect connect; }; }; @@ -2195,11 +2200,26 @@ static int io_accept(struct io_kiocb *req, const struct io_uring_sqe *sqe, #endif } +static int io_connect_prep(struct io_kiocb *req, struct io_async_ctx *io) +{ +#if defined(CONFIG_NET) + const struct io_uring_sqe *sqe = req->sqe; + struct sockaddr __user *addr; + int addr_len; + + addr = (struct sockaddr __user *) (unsigned long) READ_ONCE(sqe->addr); + addr_len = READ_ONCE(sqe->addr2); + return move_addr_to_kernel(addr, addr_len, &io->connect.address); +#else + return 0; +#endif +} + static int io_connect(struct io_kiocb *req, const struct io_uring_sqe *sqe, struct io_kiocb **nxt, bool force_nonblock) { #if defined(CONFIG_NET) - struct sockaddr __user *addr; + struct io_async_ctx __io, *io; unsigned file_flags; int addr_len, ret; @@ -2208,15 +2228,35 @@ static int io_connect(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (sqe->ioprio || sqe->len || sqe->buf_index || sqe->rw_flags) return -EINVAL; - addr = (struct sockaddr __user *) (unsigned long) READ_ONCE(sqe->addr); addr_len = READ_ONCE(sqe->addr2); file_flags = force_nonblock ? O_NONBLOCK : 0; - ret = __sys_connect_file(req->file, addr, addr_len, file_flags); - if (ret == -EAGAIN && force_nonblock) + if (req->io) { + io = req->io; + } else { + ret = io_connect_prep(req, &__io); + if (ret) + goto out; + io = &__io; + } + + ret = __sys_connect_file(req->file, &io->connect.address, addr_len, + file_flags); + if (ret == -EAGAIN && force_nonblock) { + io = kmalloc(sizeof(*io), GFP_KERNEL); + if (!io) { + ret = -ENOMEM; + goto out; + } + memcpy(&io->connect, &__io.connect, sizeof(io->connect)); + req->io = io; + memcpy(&io->sqe, req->sqe, sizeof(*req->sqe)); + req->sqe = &io->sqe; return -EAGAIN; + } if (ret == -ERESTARTSYS) ret = -EINTR; +out: if (ret < 0 && (req->flags & REQ_F_LINK)) req->flags |= REQ_F_FAIL_LINK; io_cqring_add_event(req, ret); @@ -2832,6 +2872,9 @@ static int io_req_defer_prep(struct io_kiocb *req, struct io_async_ctx *io) case IORING_OP_RECVMSG: ret = io_recvmsg_prep(req, io); break; + case IORING_OP_CONNECT: + ret = io_connect_prep(req, io); + break; default: req->io = io; return 0; diff --git a/include/linux/socket.h b/include/linux/socket.h index 903507fb901f..2d2313403101 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -406,9 +406,8 @@ extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_socket(int family, int type, int protocol); extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen); -extern int __sys_connect_file(struct file *file, - struct sockaddr __user *uservaddr, int addrlen, - int file_flags); +extern int __sys_connect_file(struct file *file, struct sockaddr_storage *addr, + int addrlen, int file_flags); extern int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen); extern int __sys_listen(int fd, int backlog); diff --git a/net/socket.c b/net/socket.c index 0fb0820edeec..b343db1489bd 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1826,26 +1826,22 @@ SYSCALL_DEFINE3(accept, int, fd, struct sockaddr __user *, upeer_sockaddr, * include the -EINPROGRESS status for such sockets. */ -int __sys_connect_file(struct file *file, struct sockaddr __user *uservaddr, +int __sys_connect_file(struct file *file, struct sockaddr_storage *address, int addrlen, int file_flags) { struct socket *sock; - struct sockaddr_storage address; int err; sock = sock_from_file(file, &err); if (!sock) goto out; - err = move_addr_to_kernel(uservaddr, addrlen, &address); - if (err < 0) - goto out; err = - security_socket_connect(sock, (struct sockaddr *)&address, addrlen); + security_socket_connect(sock, (struct sockaddr *)address, addrlen); if (err) goto out; - err = sock->ops->connect(sock, (struct sockaddr *)&address, addrlen, + err = sock->ops->connect(sock, (struct sockaddr *)address, addrlen, sock->file->f_flags | file_flags); out: return err; @@ -1858,7 +1854,11 @@ int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen) f = fdget(fd); if (f.file) { - ret = __sys_connect_file(f.file, uservaddr, addrlen, 0); + struct sockaddr_storage address; + + ret = move_addr_to_kernel(uservaddr, addrlen, &address); + if (!ret) + ret = __sys_connect_file(f.file, &address, addrlen, 0); if (f.flags) fput(f.file); } -- cgit v1.2.3-71-gd317 From 795ee49c1a28d1b3eeb2b463f18d557700fc6153 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sat, 30 Nov 2019 23:23:52 +0300 Subject: block: optimise bvec_iter_advance() bvec_iter_advance() is quite popular, but compilers fail to do proper alias analysis and optimise it good enough. The assembly is checked for gcc 9.2, x86-64. - remove @iter->bi_size from min(...), as it's always less than @bytes. Modify at the beginning and forget about it. - the compiler isn't able to collapse memory dependencies and remove writes in the loop. Help it by explicitely using local vars. Signed-off-by: Arvind Sankar Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- include/linux/bvec.h | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bvec.h b/include/linux/bvec.h index a032f01e928c..679a42253170 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -87,26 +87,24 @@ struct bvec_iter_all { static inline bool bvec_iter_advance(const struct bio_vec *bv, struct bvec_iter *iter, unsigned bytes) { + unsigned int idx = iter->bi_idx; + if (WARN_ONCE(bytes > iter->bi_size, "Attempted to advance past end of bvec iter\n")) { iter->bi_size = 0; return false; } - while (bytes) { - const struct bio_vec *cur = bv + iter->bi_idx; - unsigned len = min3(bytes, iter->bi_size, - cur->bv_len - iter->bi_bvec_done); - - bytes -= len; - iter->bi_size -= len; - iter->bi_bvec_done += len; + iter->bi_size -= bytes; + bytes += iter->bi_bvec_done; - if (iter->bi_bvec_done == cur->bv_len) { - iter->bi_bvec_done = 0; - iter->bi_idx++; - } + while (bytes && bytes >= bv[idx].bv_len) { + bytes -= bv[idx].bv_len; + idx++; } + + iter->bi_idx = idx; + iter->bi_bvec_done = bytes; return true; } -- cgit v1.2.3-71-gd317 From 9b38bb4b1e6de47b379afaad2c707df639bb4dc7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 3 Dec 2019 10:39:04 +0100 Subject: block: simplify blkdev_nr_zones Simplify the arguments to blkdev_nr_zones by passing a gendisk instead of the block_device and capacity. This also removes the need for __blkdev_nr_zones as all callers are outside the fast path and can deal with the additional branch. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-zoned.c | 26 ++++++++------------------ block/ioctl.c | 2 +- drivers/md/dm-zoned-target.c | 2 +- include/linux/blkdev.h | 5 ++--- 4 files changed, 12 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 618786f8275c..65a9bdc9fe27 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -70,30 +70,20 @@ void __blk_req_zone_write_unlock(struct request *rq) } EXPORT_SYMBOL_GPL(__blk_req_zone_write_unlock); -static inline unsigned int __blkdev_nr_zones(struct request_queue *q, - sector_t nr_sectors) -{ - sector_t zone_sectors = blk_queue_zone_sectors(q); - - return (nr_sectors + zone_sectors - 1) >> ilog2(zone_sectors); -} - /** * blkdev_nr_zones - Get number of zones - * @bdev: Target block device + * @disk: Target gendisk * - * Description: - * Return the total number of zones of a zoned block device. - * For a regular block device, the number of zones is always 0. + * Return the total number of zones of a zoned block device. For a block + * device without zone capabilities, the number of zones is always 0. */ -unsigned int blkdev_nr_zones(struct block_device *bdev) +unsigned int blkdev_nr_zones(struct gendisk *disk) { - struct request_queue *q = bdev_get_queue(bdev); + sector_t zone_sectors = blk_queue_zone_sectors(disk->queue); - if (!blk_queue_is_zoned(q)) + if (!blk_queue_is_zoned(disk->queue)) return 0; - - return __blkdev_nr_zones(q, get_capacity(bdev->bd_disk)); + return (get_capacity(disk) + zone_sectors - 1) >> ilog2(zone_sectors); } EXPORT_SYMBOL_GPL(blkdev_nr_zones); @@ -447,7 +437,7 @@ static int blk_update_zone_info(struct gendisk *disk, unsigned int nr_zones, int blk_revalidate_disk_zones(struct gendisk *disk) { struct request_queue *q = disk->queue; - unsigned int nr_zones = __blkdev_nr_zones(q, get_capacity(disk)); + unsigned int nr_zones = blkdev_nr_zones(disk); struct blk_revalidate_zone_args args = { .disk = disk }; int ret = 0; diff --git a/block/ioctl.c b/block/ioctl.c index 7ac8a66c9787..5de98b97af2a 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -512,7 +512,7 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, case BLKGETZONESZ: return put_uint(arg, bdev_zone_sectors(bdev)); case BLKGETNRZONES: - return put_uint(arg, blkdev_nr_zones(bdev)); + return put_uint(arg, blkdev_nr_zones(bdev->bd_disk)); case HDIO_GETGEO: return blkdev_getgeo(bdev, argp); case BLKRAGET: diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index 4574e0dedbd6..70a1063161c0 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -727,7 +727,7 @@ static int dmz_get_zoned_device(struct dm_target *ti, char *path) dev->zone_nr_blocks = dmz_sect2blk(dev->zone_nr_sectors); dev->zone_nr_blocks_shift = ilog2(dev->zone_nr_blocks); - dev->nr_zones = blkdev_nr_zones(dev->bdev); + dev->nr_zones = blkdev_nr_zones(dev->bdev->bd_disk); dmz->dev = dev; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6012e2592628..c5852de402b6 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -357,8 +357,7 @@ typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, #define BLK_ALL_ZONES ((unsigned int)-1) int blkdev_report_zones(struct block_device *bdev, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); - -extern unsigned int blkdev_nr_zones(struct block_device *bdev); +unsigned int blkdev_nr_zones(struct gendisk *disk); extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op, sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask); @@ -371,7 +370,7 @@ extern int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, #else /* CONFIG_BLK_DEV_ZONED */ -static inline unsigned int blkdev_nr_zones(struct block_device *bdev) +static inline unsigned int blkdev_nr_zones(struct gendisk *disk) { return 0; } -- cgit v1.2.3-71-gd317 From f216fdd77b5654f8c4f6fac6020d6aabc58878ef Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 3 Dec 2019 10:39:05 +0100 Subject: block: replace seq_zones_bitmap with conv_zones_bitmap MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Invert the meaning of seq_zones_bitmap by keeping a bitmap of conventional zones. This allows not having a bitmap for devices that do not have conventional zones. Reviewed-by: Javier González Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-zoned.c | 18 +++++++++--------- include/linux/blkdev.h | 14 ++++++++------ 2 files changed, 17 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 65a9bdc9fe27..9c3931051f4f 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -332,15 +332,15 @@ static inline unsigned long *blk_alloc_zone_bitmap(int node, void blk_queue_free_zone_bitmaps(struct request_queue *q) { - kfree(q->seq_zones_bitmap); - q->seq_zones_bitmap = NULL; + kfree(q->conv_zones_bitmap); + q->conv_zones_bitmap = NULL; kfree(q->seq_zones_wlock); q->seq_zones_wlock = NULL; } struct blk_revalidate_zone_args { struct gendisk *disk; - unsigned long *seq_zones_bitmap; + unsigned long *conv_zones_bitmap; unsigned long *seq_zones_wlock; sector_t sector; }; @@ -394,8 +394,8 @@ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx, return -ENODEV; } - if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) - set_bit(idx, args->seq_zones_bitmap); + if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) + set_bit(idx, args->conv_zones_bitmap); args->sector += zone->len; return 0; @@ -415,8 +415,8 @@ static int blk_update_zone_info(struct gendisk *disk, unsigned int nr_zones, args->seq_zones_wlock = blk_alloc_zone_bitmap(q->node, nr_zones); if (!args->seq_zones_wlock) return -ENOMEM; - args->seq_zones_bitmap = blk_alloc_zone_bitmap(q->node, nr_zones); - if (!args->seq_zones_bitmap) + args->conv_zones_bitmap = blk_alloc_zone_bitmap(q->node, nr_zones); + if (!args->conv_zones_bitmap) return -ENOMEM; ret = disk->fops->report_zones(disk, 0, nr_zones, @@ -465,7 +465,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk) if (ret >= 0) { q->nr_zones = nr_zones; swap(q->seq_zones_wlock, args.seq_zones_wlock); - swap(q->seq_zones_bitmap, args.seq_zones_bitmap); + swap(q->conv_zones_bitmap, args.conv_zones_bitmap); ret = 0; } else { pr_warn("%s: failed to revalidate zones\n", disk->disk_name); @@ -474,7 +474,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk) blk_mq_unfreeze_queue(q); kfree(args.seq_zones_wlock); - kfree(args.seq_zones_bitmap); + kfree(args.conv_zones_bitmap); return ret; } EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c5852de402b6..503c4d4c5884 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -503,9 +503,9 @@ struct request_queue { /* * Zoned block device information for request dispatch control. * nr_zones is the total number of zones of the device. This is always - * 0 for regular block devices. seq_zones_bitmap is a bitmap of nr_zones - * bits which indicates if a zone is conventional (bit clear) or - * sequential (bit set). seq_zones_wlock is a bitmap of nr_zones + * 0 for regular block devices. conv_zones_bitmap is a bitmap of nr_zones + * bits which indicates if a zone is conventional (bit set) or + * sequential (bit clear). seq_zones_wlock is a bitmap of nr_zones * bits which indicates if a zone is write locked, that is, if a write * request targeting the zone was dispatched. All three fields are * initialized by the low level device driver (e.g. scsi/sd.c). @@ -518,7 +518,7 @@ struct request_queue { * blk_mq_unfreeze_queue(). */ unsigned int nr_zones; - unsigned long *seq_zones_bitmap; + unsigned long *conv_zones_bitmap; unsigned long *seq_zones_wlock; #endif /* CONFIG_BLK_DEV_ZONED */ @@ -723,9 +723,11 @@ static inline unsigned int blk_queue_zone_no(struct request_queue *q, static inline bool blk_queue_zone_is_seq(struct request_queue *q, sector_t sector) { - if (!blk_queue_is_zoned(q) || !q->seq_zones_bitmap) + if (!blk_queue_is_zoned(q)) return false; - return test_bit(blk_queue_zone_no(q, sector), q->seq_zones_bitmap); + if (!q->conv_zones_bitmap) + return true; + return !test_bit(blk_queue_zone_no(q, sector), q->conv_zones_bitmap); } #else /* CONFIG_BLK_DEV_ZONED */ static inline unsigned int blk_queue_nr_zones(struct request_queue *q) -- cgit v1.2.3-71-gd317 From ae58954d8734c44298f55ed71e683ea944994fab Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 3 Dec 2019 10:39:07 +0100 Subject: block: don't handle bio based drivers in blk_revalidate_disk_zones MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit bio based drivers only need to update q->nr_zones. Do that manually instead of overloading blk_revalidate_disk_zones to keep that function simpler for the next round of changes that will rely even more on the request based functionality. Reviewed-by: Javier González Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-zoned.c | 16 +++++----------- drivers/block/null_blk_main.c | 12 +++++++++--- drivers/md/dm-table.c | 12 +++++++----- include/linux/blkdev.h | 5 ----- 4 files changed, 21 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 0131f9e14bd1..51d427659ce7 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -419,8 +419,9 @@ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx, * * Helper function for low-level device drivers to (re) allocate and initialize * a disk request queue zone bitmaps. This functions should normally be called - * within the disk ->revalidate method. For BIO based queues, no zone bitmap - * is allocated. + * within the disk ->revalidate method for blk-mq based drivers. For BIO based + * drivers only q->nr_zones needs to be updated so that the sysfs exposed value + * is correct. */ int blk_revalidate_disk_zones(struct gendisk *disk) { @@ -433,15 +434,8 @@ int blk_revalidate_disk_zones(struct gendisk *disk) if (WARN_ON_ONCE(!blk_queue_is_zoned(q))) return -EIO; - - /* - * BIO based queues do not use a scheduler so only q->nr_zones - * needs to be updated so that the sysfs exposed value is correct. - */ - if (!queue_is_mq(q)) { - q->nr_zones = args.nr_zones; - return 0; - } + if (WARN_ON_ONCE(!queue_is_mq(q))) + return -EIO; /* * Ensure that all memory allocations in this context are done as diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c index dd6026289fbf..068cd0ae6e2c 100644 --- a/drivers/block/null_blk_main.c +++ b/drivers/block/null_blk_main.c @@ -1576,11 +1576,17 @@ static int null_gendisk_register(struct nullb *nullb) disk->queue = nullb->q; strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN); +#ifdef CONFIG_BLK_DEV_ZONED if (nullb->dev->zoned) { - ret = blk_revalidate_disk_zones(disk); - if (ret) - return ret; + if (queue_is_mq(nullb->q)) { + ret = blk_revalidate_disk_zones(disk); + if (ret) + return ret; + } else { + nullb->q->nr_zones = blkdev_nr_zones(disk); + } } +#endif add_disk(disk); return 0; diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 2ae0c1913766..0a2cc197f62b 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1954,12 +1954,14 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, /* * For a zoned target, the number of zones should be updated for the * correct value to be exposed in sysfs queue/nr_zones. For a BIO based - * target, this is all that is needed. For a request based target, the - * queue zone bitmaps must also be updated. - * Use blk_revalidate_disk_zones() to handle this. + * target, this is all that is needed. */ - if (blk_queue_is_zoned(q)) - blk_revalidate_disk_zones(t->md->disk); +#ifdef CONFIG_BLK_DEV_ZONED + if (blk_queue_is_zoned(q)) { + WARN_ON_ONCE(queue_is_mq(q)); + q->nr_zones = blkdev_nr_zones(t->md->disk); + } +#endif /* Allow reads to exceed readahead limits */ q->backing_dev_info->io_pages = limits->max_sectors >> (PAGE_SHIFT - 9); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 503c4d4c5884..47eb22a3b7f9 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -375,11 +375,6 @@ static inline unsigned int blkdev_nr_zones(struct gendisk *disk) return 0; } -static inline int blk_revalidate_disk_zones(struct gendisk *disk) -{ - return 0; -} - static inline int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) -- cgit v1.2.3-71-gd317 From 0f109f0e9a608c381846b3f2270a6a7b72158cb4 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Thu, 21 Nov 2019 08:14:42 +0000 Subject: agp: move AGPGART_MINOR to include/linux/miscdevice.h This patch move the define for AGPGART_MINOR to include/linux/miscdevice.h. It is better that all minor number definitions are in the same place. Signed-off-by: Corentin Labbe Acked-by: Arnd Bergmann Signed-off-by: Dave Airlie Link: https://patchwork.freedesktop.org/patch/msgid/1574324085-4338-3-git-send-email-clabbe@baylibre.com --- include/linux/agpgart.h | 2 -- include/linux/miscdevice.h | 1 + 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/agpgart.h b/include/linux/agpgart.h index c6b61ca97053..21b34a96cfd8 100644 --- a/include/linux/agpgart.h +++ b/include/linux/agpgart.h @@ -30,8 +30,6 @@ #include #include -#define AGPGART_MINOR 175 - struct agp_info { struct agp_version version; /* version of the driver */ u32 bridge_id; /* bridge vendor/device */ diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index 3247a3dc7934..6f2ca42152a0 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -33,6 +33,7 @@ #define SGI_MMTIMER 153 #define STORE_QUEUE_MINOR 155 /* unused */ #define I2O_MINOR 166 +#define AGPGART_MINOR 175 #define HWRNG_MINOR 183 #define MICROCODE_MINOR 184 #define IRNET_MINOR 187 -- cgit v1.2.3-71-gd317 From d04ac224b1688f005a84f764cfe29844f8e9da08 Mon Sep 17 00:00:00 2001 From: Martin Varghese Date: Thu, 5 Dec 2019 05:57:22 +0530 Subject: net: Fixed updating of ethertype in skb_mpls_push() The skb_mpls_push was not updating ethertype of an ethernet packet if the packet was originally received from a non ARPHRD_ETHER device. In the below OVS data path flow, since the device corresponding to port 7 is an l3 device (ARPHRD_NONE) the skb_mpls_push function does not update the ethertype of the packet even though the previous push_eth action had added an ethernet header to the packet. recirc_id(0),in_port(7),eth_type(0x0800),ipv4(tos=0/0xfc,ttl=64,frag=no), actions:push_eth(src=00:00:00:00:00:00,dst=00:00:00:00:00:00), push_mpls(label=13,tc=0,ttl=64,bos=1,eth_type=0x8847),4 Fixes: 8822e270d697 ("net: core: move push MPLS functionality from OvS to core helper") Signed-off-by: Martin Varghese Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- net/core/skbuff.c | 4 ++-- net/openvswitch/actions.c | 3 ++- net/sched/act_mpls.c | 3 ++- 4 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5aea72fe8498..e9133bcf0544 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3529,7 +3529,7 @@ int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, - int mac_len); + int mac_len, bool ethernet); int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, bool ethernet); int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 312e80e86898..973a71f4bc89 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5484,7 +5484,7 @@ static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr, * Returns 0 on success, -errno otherwise. */ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, - int mac_len) + int mac_len, bool ethernet) { struct mpls_shim_hdr *lse; int err; @@ -5515,7 +5515,7 @@ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, lse->label_stack_entry = mpls_lse; skb_postpush_rcsum(skb, lse, MPLS_HLEN); - if (skb->dev && skb->dev->type == ARPHRD_ETHER) + if (ethernet) skb_mod_eth_type(skb, eth_hdr(skb), mpls_proto); skb->protocol = mpls_proto; diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 91e210061bb3..4c8395462303 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -166,7 +166,8 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key, int err; err = skb_mpls_push(skb, mpls->mpls_lse, mpls->mpls_ethertype, - skb->mac_len); + skb->mac_len, + ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET); if (err) return err; diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index a7d856203af1..be3f215cd027 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -83,7 +83,8 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, break; case TCA_MPLS_ACT_PUSH: new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb->protocol)); - if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len)) + if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len, + skb->dev && skb->dev->type == ARPHRD_ETHER)) goto drop; break; case TCA_MPLS_ACT_MODIFY: -- cgit v1.2.3-71-gd317 From 9d7ea9a297e6445d567056f15b469dde13ca4134 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Wed, 4 Dec 2019 16:49:50 -0800 Subject: mm/vmstat: add helpers to get vmstat item names for each enum type Statistics in vmstat is combined from counters with different structure, but names for them are merged into one array. This patch adds trivial helpers to get name for each item: const char *zone_stat_name(enum zone_stat_item item); const char *numa_stat_name(enum numa_stat_item item); const char *node_stat_name(enum node_stat_item item); const char *writeback_stat_name(enum writeback_stat_item item); const char *vm_event_name(enum vm_event_item item); Names for enum writeback_stat_item are folded in the middle of vmstat_text so this patch moves declaration into header to calculate offset of following items. Also this patch reuses piece of node stat names for lru list names: const char *lru_list_name(enum lru_list lru); This returns common lru list names: "inactive_anon", "active_anon", "inactive_file", "active_file", "unevictable". [khlebnikov@yandex-team.ru: do not use size of vmstat_text as count of /proc/vmstat items] Link: http://lkml.kernel.org/r/157152151769.4139.15423465513138349343.stgit@buzz Link: https://lore.kernel.org/linux-mm/cd1c42ae-281f-c8a8-70ac-1d01d417b2e1@infradead.org/T/#u Link: http://lkml.kernel.org/r/157113012325.453.562783073839432766.stgit@buzz Signed-off-by: Konstantin Khlebnikov Reviewed-by: Andrew Morton Cc: Randy Dunlap Cc: Michal Hocko Cc: Vladimir Davydov Cc: Johannes Weiner Cc: YueHaibing Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/node.c | 9 +++------ include/linux/vmstat.h | 50 +++++++++++++++++++++++++++++++++++++++++++++++++ mm/vmstat.c | 51 ++++++++++++++++++++------------------------------ 3 files changed, 73 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/node.c b/drivers/base/node.c index 296546ffed6c..98a31bafc8a2 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -496,20 +496,17 @@ static ssize_t node_read_vmstat(struct device *dev, int n = 0; for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - n += sprintf(buf+n, "%s %lu\n", vmstat_text[i], + n += sprintf(buf+n, "%s %lu\n", zone_stat_name(i), sum_zone_node_page_state(nid, i)); #ifdef CONFIG_NUMA for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) - n += sprintf(buf+n, "%s %lu\n", - vmstat_text[i + NR_VM_ZONE_STAT_ITEMS], + n += sprintf(buf+n, "%s %lu\n", numa_stat_name(i), sum_zone_numa_state(nid, i)); #endif for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) - n += sprintf(buf+n, "%s %lu\n", - vmstat_text[i + NR_VM_ZONE_STAT_ITEMS + - NR_VM_NUMA_STAT_ITEMS], + n += sprintf(buf+n, "%s %lu\n", node_stat_name(i), node_page_state(pgdat, i)); return n; diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index bdeda4b079fe..b995d8b680c2 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -31,6 +31,12 @@ struct reclaim_stat { unsigned nr_unmap_fail; }; +enum writeback_stat_item { + NR_DIRTY_THRESHOLD, + NR_DIRTY_BG_THRESHOLD, + NR_VM_WRITEBACK_STAT_ITEMS, +}; + #ifdef CONFIG_VM_EVENT_COUNTERS /* * Light weight per cpu counter implementation. @@ -381,4 +387,48 @@ static inline void __mod_zone_freepage_state(struct zone *zone, int nr_pages, extern const char * const vmstat_text[]; +static inline const char *zone_stat_name(enum zone_stat_item item) +{ + return vmstat_text[item]; +} + +#ifdef CONFIG_NUMA +static inline const char *numa_stat_name(enum numa_stat_item item) +{ + return vmstat_text[NR_VM_ZONE_STAT_ITEMS + + item]; +} +#endif /* CONFIG_NUMA */ + +static inline const char *node_stat_name(enum node_stat_item item) +{ + return vmstat_text[NR_VM_ZONE_STAT_ITEMS + + NR_VM_NUMA_STAT_ITEMS + + item]; +} + +static inline const char *lru_list_name(enum lru_list lru) +{ + return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_" +} + +static inline const char *writeback_stat_name(enum writeback_stat_item item) +{ + return vmstat_text[NR_VM_ZONE_STAT_ITEMS + + NR_VM_NUMA_STAT_ITEMS + + NR_VM_NODE_STAT_ITEMS + + item]; +} + +#ifdef CONFIG_VM_EVENT_COUNTERS +static inline const char *vm_event_name(enum vm_event_item item) +{ + return vmstat_text[NR_VM_ZONE_STAT_ITEMS + + NR_VM_NUMA_STAT_ITEMS + + NR_VM_NODE_STAT_ITEMS + + NR_VM_WRITEBACK_STAT_ITEMS + + item]; +} +#endif /* CONFIG_VM_EVENT_COUNTERS */ + #endif /* _LINUX_VMSTAT_H */ diff --git a/mm/vmstat.c b/mm/vmstat.c index a8222041bd44..fa627329428b 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1134,7 +1134,7 @@ const char * const vmstat_text[] = { "numa_other", #endif - /* Node-based counters */ + /* enum node_stat_item counters */ "nr_inactive_anon", "nr_active_anon", "nr_inactive_file", @@ -1564,10 +1564,8 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, if (is_zone_first_populated(pgdat, zone)) { seq_printf(m, "\n per-node stats"); for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) { - seq_printf(m, "\n %-12s %lu", - vmstat_text[i + NR_VM_ZONE_STAT_ITEMS + - NR_VM_NUMA_STAT_ITEMS], - node_page_state(pgdat, i)); + seq_printf(m, "\n %-12s %lu", node_stat_name(i), + node_page_state(pgdat, i)); } } seq_printf(m, @@ -1600,14 +1598,13 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, } for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - seq_printf(m, "\n %-12s %lu", vmstat_text[i], - zone_page_state(zone, i)); + seq_printf(m, "\n %-12s %lu", zone_stat_name(i), + zone_page_state(zone, i)); #ifdef CONFIG_NUMA for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) - seq_printf(m, "\n %-12s %lu", - vmstat_text[i + NR_VM_ZONE_STAT_ITEMS], - zone_numa_state_snapshot(zone, i)); + seq_printf(m, "\n %-12s %lu", numa_stat_name(i), + zone_numa_state_snapshot(zone, i)); #endif seq_printf(m, "\n pagesets"); @@ -1658,31 +1655,23 @@ static const struct seq_operations zoneinfo_op = { .show = zoneinfo_show, }; -enum writeback_stat_item { - NR_DIRTY_THRESHOLD, - NR_DIRTY_BG_THRESHOLD, - NR_VM_WRITEBACK_STAT_ITEMS, -}; +#define NR_VMSTAT_ITEMS (NR_VM_ZONE_STAT_ITEMS + \ + NR_VM_NUMA_STAT_ITEMS + \ + NR_VM_NODE_STAT_ITEMS + \ + NR_VM_WRITEBACK_STAT_ITEMS + \ + (IS_ENABLED(CONFIG_VM_EVENT_COUNTERS) ? \ + NR_VM_EVENT_ITEMS : 0)) static void *vmstat_start(struct seq_file *m, loff_t *pos) { unsigned long *v; - int i, stat_items_size; + int i; - if (*pos >= ARRAY_SIZE(vmstat_text)) + if (*pos >= NR_VMSTAT_ITEMS) return NULL; - stat_items_size = NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long) + - NR_VM_NUMA_STAT_ITEMS * sizeof(unsigned long) + - NR_VM_NODE_STAT_ITEMS * sizeof(unsigned long) + - NR_VM_WRITEBACK_STAT_ITEMS * sizeof(unsigned long); - -#ifdef CONFIG_VM_EVENT_COUNTERS - stat_items_size += sizeof(struct vm_event_state); -#endif - BUILD_BUG_ON(stat_items_size != - ARRAY_SIZE(vmstat_text) * sizeof(unsigned long)); - v = kmalloc(stat_items_size, GFP_KERNEL); + BUILD_BUG_ON(ARRAY_SIZE(vmstat_text) < NR_VMSTAT_ITEMS); + v = kmalloc_array(NR_VMSTAT_ITEMS, sizeof(unsigned long), GFP_KERNEL); m->private = v; if (!v) return ERR_PTR(-ENOMEM); @@ -1715,7 +1704,7 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos) static void *vmstat_next(struct seq_file *m, void *arg, loff_t *pos) { (*pos)++; - if (*pos >= ARRAY_SIZE(vmstat_text)) + if (*pos >= NR_VMSTAT_ITEMS) return NULL; return (unsigned long *)m->private + *pos; } @@ -1781,7 +1770,7 @@ int vmstat_refresh(struct ctl_table *table, int write, val = atomic_long_read(&vm_zone_stat[i]); if (val < 0) { pr_warn("%s: %s %ld\n", - __func__, vmstat_text[i], val); + __func__, zone_stat_name(i), val); err = -EINVAL; } } @@ -1790,7 +1779,7 @@ int vmstat_refresh(struct ctl_table *table, int write, val = atomic_long_read(&vm_numa_stat[i]); if (val < 0) { pr_warn("%s: %s %ld\n", - __func__, vmstat_text[i + NR_VM_ZONE_STAT_ITEMS], val); + __func__, numa_stat_name(i), val); err = -EINVAL; } } -- cgit v1.2.3-71-gd317 From ebc5d83d04438116c24dcc556b0ab6c8ef64b77e Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Wed, 4 Dec 2019 16:49:53 -0800 Subject: mm/memcontrol: use vmstat names for printing statistics Use common names from vmstat array when possible. This gives not much difference in code size for now, but should help in keeping interfaces consistent. add/remove: 0/2 grow/shrink: 2/0 up/down: 70/-72 (-2) Function old new delta memory_stat_format 984 1050 +66 memcg_stat_show 957 961 +4 memcg1_event_names 32 - -32 mem_cgroup_lru_names 40 - -40 Total: Before=14485337, After=14485335, chg -0.00% Link: http://lkml.kernel.org/r/157113012508.453.80391533767219371.stgit@buzz Signed-off-by: Konstantin Khlebnikov Acked-by: Andrew Morton Cc: Michal Hocko Cc: Vladimir Davydov Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 4 ++-- mm/memcontrol.c | 52 +++++++++++++++++++++----------------------------- mm/vmstat.c | 9 +++++---- 3 files changed, 29 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index b995d8b680c2..292485f3d24d 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -420,7 +420,7 @@ static inline const char *writeback_stat_name(enum writeback_stat_item item) item]; } -#ifdef CONFIG_VM_EVENT_COUNTERS +#if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) static inline const char *vm_event_name(enum vm_event_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + @@ -429,6 +429,6 @@ static inline const char *vm_event_name(enum vm_event_item item) NR_VM_WRITEBACK_STAT_ITEMS + item]; } -#endif /* CONFIG_VM_EVENT_COUNTERS */ +#endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ #endif /* _LINUX_VMSTAT_H */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index bc01423277c5..c5b5f74cfd4d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -98,14 +98,6 @@ static bool do_memsw_account(void) return !cgroup_subsys_on_dfl(memory_cgrp_subsys) && do_swap_account; } -static const char *const mem_cgroup_lru_names[] = { - "inactive_anon", - "active_anon", - "inactive_file", - "active_file", - "unevictable", -}; - #define THRESHOLDS_EVENTS_TARGET 128 #define SOFTLIMIT_EVENTS_TARGET 1024 @@ -1421,7 +1413,7 @@ static char *memory_stat_format(struct mem_cgroup *memcg) PAGE_SIZE); for (i = 0; i < NR_LRU_LISTS; i++) - seq_buf_printf(&s, "%s %llu\n", mem_cgroup_lru_names[i], + seq_buf_printf(&s, "%s %llu\n", lru_list_name(i), (u64)memcg_page_state(memcg, NR_LRU_BASE + i) * PAGE_SIZE); @@ -1434,8 +1426,10 @@ static char *memory_stat_format(struct mem_cgroup *memcg) /* Accumulated memory events */ - seq_buf_printf(&s, "pgfault %lu\n", memcg_events(memcg, PGFAULT)); - seq_buf_printf(&s, "pgmajfault %lu\n", memcg_events(memcg, PGMAJFAULT)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGFAULT), + memcg_events(memcg, PGFAULT)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGMAJFAULT), + memcg_events(memcg, PGMAJFAULT)); seq_buf_printf(&s, "workingset_refault %lu\n", memcg_page_state(memcg, WORKINGSET_REFAULT)); @@ -1444,22 +1438,27 @@ static char *memory_stat_format(struct mem_cgroup *memcg) seq_buf_printf(&s, "workingset_nodereclaim %lu\n", memcg_page_state(memcg, WORKINGSET_NODERECLAIM)); - seq_buf_printf(&s, "pgrefill %lu\n", memcg_events(memcg, PGREFILL)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGREFILL), + memcg_events(memcg, PGREFILL)); seq_buf_printf(&s, "pgscan %lu\n", memcg_events(memcg, PGSCAN_KSWAPD) + memcg_events(memcg, PGSCAN_DIRECT)); seq_buf_printf(&s, "pgsteal %lu\n", memcg_events(memcg, PGSTEAL_KSWAPD) + memcg_events(memcg, PGSTEAL_DIRECT)); - seq_buf_printf(&s, "pgactivate %lu\n", memcg_events(memcg, PGACTIVATE)); - seq_buf_printf(&s, "pgdeactivate %lu\n", memcg_events(memcg, PGDEACTIVATE)); - seq_buf_printf(&s, "pglazyfree %lu\n", memcg_events(memcg, PGLAZYFREE)); - seq_buf_printf(&s, "pglazyfreed %lu\n", memcg_events(memcg, PGLAZYFREED)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGACTIVATE), + memcg_events(memcg, PGACTIVATE)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGDEACTIVATE), + memcg_events(memcg, PGDEACTIVATE)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGLAZYFREE), + memcg_events(memcg, PGLAZYFREE)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGLAZYFREED), + memcg_events(memcg, PGLAZYFREED)); #ifdef CONFIG_TRANSPARENT_HUGEPAGE - seq_buf_printf(&s, "thp_fault_alloc %lu\n", + seq_buf_printf(&s, "%s %lu\n", vm_event_name(THP_FAULT_ALLOC), memcg_events(memcg, THP_FAULT_ALLOC)); - seq_buf_printf(&s, "thp_collapse_alloc %lu\n", + seq_buf_printf(&s, "%s %lu\n", vm_event_name(THP_COLLAPSE_ALLOC), memcg_events(memcg, THP_COLLAPSE_ALLOC)); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -3742,13 +3741,6 @@ static const unsigned int memcg1_events[] = { PGMAJFAULT, }; -static const char *const memcg1_event_names[] = { - "pgpgin", - "pgpgout", - "pgfault", - "pgmajfault", -}; - static int memcg_stat_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_seq(m); @@ -3757,7 +3749,6 @@ static int memcg_stat_show(struct seq_file *m, void *v) unsigned int i; BUILD_BUG_ON(ARRAY_SIZE(memcg1_stat_names) != ARRAY_SIZE(memcg1_stats)); - BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS); for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) { if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account()) @@ -3768,11 +3759,11 @@ static int memcg_stat_show(struct seq_file *m, void *v) } for (i = 0; i < ARRAY_SIZE(memcg1_events); i++) - seq_printf(m, "%s %lu\n", memcg1_event_names[i], + seq_printf(m, "%s %lu\n", vm_event_name(memcg1_events[i]), memcg_events_local(memcg, memcg1_events[i])); for (i = 0; i < NR_LRU_LISTS; i++) - seq_printf(m, "%s %lu\n", mem_cgroup_lru_names[i], + seq_printf(m, "%s %lu\n", lru_list_name(i), memcg_page_state_local(memcg, NR_LRU_BASE + i) * PAGE_SIZE); @@ -3797,11 +3788,12 @@ static int memcg_stat_show(struct seq_file *m, void *v) } for (i = 0; i < ARRAY_SIZE(memcg1_events); i++) - seq_printf(m, "total_%s %llu\n", memcg1_event_names[i], + seq_printf(m, "total_%s %llu\n", + vm_event_name(memcg1_events[i]), (u64)memcg_events(memcg, memcg1_events[i])); for (i = 0; i < NR_LRU_LISTS; i++) - seq_printf(m, "total_%s %llu\n", mem_cgroup_lru_names[i], + seq_printf(m, "total_%s %llu\n", lru_list_name(i), (u64)memcg_page_state(memcg, NR_LRU_BASE + i) * PAGE_SIZE); diff --git a/mm/vmstat.c b/mm/vmstat.c index fa627329428b..78d53378db99 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1084,7 +1084,8 @@ int fragmentation_index(struct zone *zone, unsigned int order) } #endif -#if defined(CONFIG_PROC_FS) || defined(CONFIG_SYSFS) || defined(CONFIG_NUMA) +#if defined(CONFIG_PROC_FS) || defined(CONFIG_SYSFS) || \ + defined(CONFIG_NUMA) || defined(CONFIG_MEMCG) #ifdef CONFIG_ZONE_DMA #define TEXT_FOR_DMA(xx) xx "_dma", #else @@ -1172,7 +1173,7 @@ const char * const vmstat_text[] = { "nr_dirty_threshold", "nr_dirty_background_threshold", -#ifdef CONFIG_VM_EVENT_COUNTERS +#if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) /* enum vm_event_item counters */ "pgpgin", "pgpgout", @@ -1291,9 +1292,9 @@ const char * const vmstat_text[] = { "swap_ra", "swap_ra_hit", #endif -#endif /* CONFIG_VM_EVENTS_COUNTERS */ +#endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ }; -#endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA */ +#endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA || CONFIG_MEMCG */ #if (defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION)) || \ defined(CONFIG_PROC_FS) -- cgit v1.2.3-71-gd317 From 9573e8f70a82bcbac95b1ea222ac9d5e50266f9f Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Wed, 4 Dec 2019 16:50:08 -0800 Subject: include/linux/proc_fs.h: fix confusing macro arg name state_size and ops are in the wrong position. Link: http://lkml.kernel.org/r/20190910021747.11216-1-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: Andrew Morton Acked-by: Aleksa Sarai Reviewed-by: Christian Brauner Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/proc_fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index a705aa2d03f9..0640be56dcbd 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -58,8 +58,8 @@ extern int remove_proc_subtree(const char *, struct proc_dir_entry *); struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct seq_operations *ops, unsigned int state_size, void *data); -#define proc_create_net(name, mode, parent, state_size, ops) \ - proc_create_net_data(name, mode, parent, state_size, ops, NULL) +#define proc_create_net(name, mode, parent, ops, state_size) \ + proc_create_net_data(name, mode, parent, ops, state_size, NULL) struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode, struct proc_dir_entry *parent, int (*show)(struct seq_file *, void *), void *data); -- cgit v1.2.3-71-gd317 From d5ffb71b633cd5c4b8cce633c9d6448dced4eb74 Mon Sep 17 00:00:00 2001 From: Alessio Balsini Date: Wed, 4 Dec 2019 16:50:14 -0800 Subject: include/linux/sysctl.h: inline braces for ctl_table and ctl_table_header Fix coding style of "struct ctl_table" and "struct ctl_table_header" to have inline braces. Besides the wide use of this proposed cose style, this change helps to find at a glance the struct definition when navigating the code. Link: http://lkml.kernel.org/r/20190903154906.188651-1-balsini@android.com Signed-off-by: Alessio Balsini Acked-by: Luis Chamberlain Cc: Kees Cook Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sysctl.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 6df477329b76..02fa84493f23 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -120,8 +120,7 @@ static inline void *proc_sys_poll_event(struct ctl_table_poll *poll) struct ctl_table_poll name = __CTL_TABLE_POLL_INITIALIZER(name) /* A sysctl table is an array of struct ctl_table: */ -struct ctl_table -{ +struct ctl_table { const char *procname; /* Text ID for /proc/sys, or zero */ void *data; int maxlen; @@ -140,8 +139,7 @@ struct ctl_node { /* struct ctl_table_header is used to maintain dynamic lists of struct ctl_table trees. */ -struct ctl_table_header -{ +struct ctl_table_header { union { struct { struct ctl_table *ctl_table; -- cgit v1.2.3-71-gd317 From 8788994376d84d627450fd0d67deb6a66ddf07d7 Mon Sep 17 00:00:00 2001 From: Rikard Falkeborn Date: Wed, 4 Dec 2019 16:50:20 -0800 Subject: linux/build_bug.h: change type to int Having BUILD_BUG_ON_ZERO produce a value of type size_t leads to awkward casts in cases where the result needs to be signed, or of smaller type than size_t. To avoid this, cast the value to int instead and rely on implicit type conversions when a larger or unsigned type is needed. Link: http://lkml.kernel.org/r/20190811184938.1796-3-rikard.falkeborn@gmail.com Signed-off-by: Rikard Falkeborn Suggested-by: Masahiro Yamada Reviewed-by: Kees Cook Reviewed-by: Masahiro Yamada Cc: Joe Perches Cc: Johannes Berg Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/build_bug.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h index 0fe5426f2bdc..e3a0be2c90ad 100644 --- a/include/linux/build_bug.h +++ b/include/linux/build_bug.h @@ -9,11 +9,11 @@ #else /* __CHECKER__ */ /* * Force a compilation error if condition is true, but also produce a - * result (of value 0 and type size_t), so the expression can be used + * result (of value 0 and type int), so the expression can be used * e.g. in a structure initializer (or where-ever else comma expressions * aren't permitted). */ -#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:(-!!(e)); })) +#define BUILD_BUG_ON_ZERO(e) ((int)(sizeof(struct { int:(-!!(e)); }))) #endif /* __CHECKER__ */ /* Force a compilation error if a constant expression is not a power of 2 */ -- cgit v1.2.3-71-gd317 From 885e68e8b7b1328aa1e28b27e13fbfb5f020d269 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 4 Dec 2019 16:50:32 -0800 Subject: kernel.h: update comment about simple_strto() functions There were discussions in the past about use cases for simple_strto() functions and, in some rare cases, they have a benefit over kstrto() ones. Update a comment to reduce confusion about special use cases. Link: http://lkml.kernel.org/r/20190801192904.41087-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Suggested-by: Miguel Ojeda Cc: Geert Uytterhoeven Cc: Mans Rullgard Cc: Petr Mladek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 09f759228e3f..3adcb39fa6f5 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -348,8 +348,7 @@ int __must_check kstrtoll(const char *s, unsigned int base, long long *res); * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. - * Used as a replacement for the obsolete simple_strtoull. Return code must - * be checked. + * Used as a replacement for the simple_strtoull. Return code must be checked. */ static inline int __must_check kstrtoul(const char *s, unsigned int base, unsigned long *res) { @@ -377,8 +376,7 @@ static inline int __must_check kstrtoul(const char *s, unsigned int base, unsign * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. - * Used as a replacement for the obsolete simple_strtoull. Return code must - * be checked. + * Used as a replacement for the simple_strtoull. Return code must be checked. */ static inline int __must_check kstrtol(const char *s, unsigned int base, long *res) { @@ -454,7 +452,18 @@ static inline int __must_check kstrtos32_from_user(const char __user *s, size_t return kstrtoint_from_user(s, count, base, res); } -/* Obsolete, do not use. Use kstrto instead */ +/* + * Use kstrto instead. + * + * NOTE: simple_strto does not check for the range overflow and, + * depending on the input, may give interesting results. + * + * Use these functions if and only if you cannot use kstrto, because + * the conversion ends on the first non-digit character, which may be far + * beyond the supported range. It might be useful to parse the strings like + * 10x50 or 12:21 without altering original string or temporary buffer in use. + * Keep in mind above caveat. + */ extern unsigned long simple_strtoul(const char *,char **,unsigned int); extern long simple_strtol(const char *,char **,unsigned int); -- cgit v1.2.3-71-gd317 From 260a2679e5cbfb3d8a4cf6cd1cb6f57e89c7e543 Mon Sep 17 00:00:00 2001 From: Xiaoming Ni Date: Wed, 4 Dec 2019 16:50:47 -0800 Subject: kernel/notifier.c: remove blocking_notifier_chain_cond_register() blocking_notifier_chain_cond_register() does not consider system_booting state, which is the only difference between this function and blocking_notifier_cain_register(). This can be a bug and is a piece of duplicate code. Delete blocking_notifier_chain_cond_register() Link: http://lkml.kernel.org/r/1568861888-34045-4-git-send-email-nixiaoming@huawei.com Signed-off-by: Xiaoming Ni Reviewed-by: Andrew Morton Cc: Alan Stern Cc: Alexey Dobriyan Cc: Andy Lutomirski Cc: Anna Schumaker Cc: Arjan van de Ven Cc: Chuck Lever Cc: David S. Miller Cc: Ingo Molnar Cc: J. Bruce Fields Cc: Jeff Layton Cc: Nadia Derbey Cc: "Paul E. McKenney" Cc: Sam Protsenko Cc: Thomas Gleixner Cc: Trond Myklebust Cc: Vasily Averin Cc: Viresh Kumar Cc: YueHaibing Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/notifier.h | 4 ---- kernel/notifier.c | 23 ----------------------- net/sunrpc/rpc_pipe.c | 2 +- 3 files changed, 1 insertion(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 0096a05395e3..018947611483 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -150,10 +150,6 @@ extern int raw_notifier_chain_register(struct raw_notifier_head *nh, extern int srcu_notifier_chain_register(struct srcu_notifier_head *nh, struct notifier_block *nb); -extern int blocking_notifier_chain_cond_register( - struct blocking_notifier_head *nh, - struct notifier_block *nb); - extern int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh, struct notifier_block *nb); extern int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh, diff --git a/kernel/notifier.c b/kernel/notifier.c index e3d221f092fe..63d7501ac638 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -220,29 +220,6 @@ int blocking_notifier_chain_register(struct blocking_notifier_head *nh, } EXPORT_SYMBOL_GPL(blocking_notifier_chain_register); -/** - * blocking_notifier_chain_cond_register - Cond add notifier to a blocking notifier chain - * @nh: Pointer to head of the blocking notifier chain - * @n: New entry in notifier chain - * - * Adds a notifier to a blocking notifier chain, only if not already - * present in the chain. - * Must be called in process context. - * - * Currently always returns zero. - */ -int blocking_notifier_chain_cond_register(struct blocking_notifier_head *nh, - struct notifier_block *n) -{ - int ret; - - down_write(&nh->rwsem); - ret = notifier_chain_register(&nh->head, n); - up_write(&nh->rwsem); - return ret; -} -EXPORT_SYMBOL_GPL(blocking_notifier_chain_cond_register); - /** * blocking_notifier_chain_unregister - Remove notifier from a blocking notifier chain * @nh: Pointer to head of the blocking notifier chain diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index b71a39ded930..39e14d5edaf1 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -51,7 +51,7 @@ static BLOCKING_NOTIFIER_HEAD(rpc_pipefs_notifier_list); int rpc_pipefs_notifier_register(struct notifier_block *nb) { - return blocking_notifier_chain_cond_register(&rpc_pipefs_notifier_list, nb); + return blocking_notifier_chain_register(&rpc_pipefs_notifier_list, nb); } EXPORT_SYMBOL_GPL(rpc_pipefs_notifier_register); -- cgit v1.2.3-71-gd317 From 169c474fb22d8a5e909e172f177b957546d0519d Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Wed, 4 Dec 2019 16:50:57 -0800 Subject: bitops: introduce the for_each_set_clump8 macro Pach series "Introduce the for_each_set_clump8 macro", v18. While adding GPIO get_multiple/set_multiple callback support for various drivers, I noticed a pattern of looping manifesting that would be useful standardized as a macro. This patchset introduces the for_each_set_clump8 macro and utilizes it in several GPIO drivers. The for_each_set_clump macro8 facilitates a for-loop syntax that iterates over a memory region entire groups of set bits at a time. For example, suppose you would like to iterate over a 32-bit integer 8 bits at a time, skipping over 8-bit groups with no set bit, where XXXXXXXX represents the current 8-bit group: Example: 10111110 00000000 11111111 00110011 First loop: 10111110 00000000 11111111 XXXXXXXX Second loop: 10111110 00000000 XXXXXXXX 00110011 Third loop: XXXXXXXX 00000000 11111111 00110011 Each iteration of the loop returns the next 8-bit group that has at least one set bit. The for_each_set_clump8 macro has four parameters: * start: set to the bit offset of the current clump * clump: set to the current clump value * bits: bitmap to search within * size: bitmap size in number of bits In this version of the patchset, the for_each_set_clump macro has been reimplemented and simplified based on the suggestions provided by Rasmus Villemoes and Andy Shevchenko in the version 4 submission. In particular, the function of the for_each_set_clump macro has been restricted to handle only 8-bit clumps; the drivers that use the for_each_set_clump macro only handle 8-bit ports so a generic for_each_set_clump implementation is not necessary. Thus, a solution for large clumps (i.e. those larger than the width of a bitmap word) can be postponed until a driver appears that actually requires such a generic for_each_set_clump implementation. For what it's worth, a semi-generic for_each_set_clump (i.e. for clumps smaller than the width of a bitmap word) can be implemented by simply replacing the hardcoded '8' and '0xFF' instances with respective variables. I have not yet had a need for such an implementation, and since it falls short of a true generic for_each_set_clump function, I have decided to forgo such an implementation for now. In addition, the bitmap_get_value8 and bitmap_set_value8 functions are introduced to get and set 8-bit values respectively. Their use is based on the behavior suggested in the patchset version 4 review. This patch (of 14): This macro iterates for each 8-bit group of bits (clump) with set bits, within a bitmap memory region. For each iteration, "start" is set to the bit offset of the found clump, while the respective clump value is stored to the location pointed by "clump". Additionally, the bitmap_get_value8 and bitmap_set_value8 functions are introduced to respectively get and set an 8-bit value in a bitmap memory region. [gustavo@embeddedor.com: fix potential sign-extension overflow] Link: http://lkml.kernel.org/r/20191015184657.GA26541@embeddedor [akpm@linux-foundation.org: s/ULL/UL/, per Joe] [vilhelm.gray@gmail.com: add for_each_set_clump8 documentation] Link: http://lkml.kernel.org/r/20191016161825.301082-1-vilhelm.gray@gmail.com Link: http://lkml.kernel.org/r/893c3b4f03266c9496137cc98ac2b1bd27f92c73.1570641097.git.vilhelm.gray@gmail.com Signed-off-by: William Breathitt Gray Signed-off-by: Gustavo A. R. Silva Suggested-by: Andy Shevchenko Suggested-by: Rasmus Villemoes Suggested-by: Lukas Wunner Tested-by: Andy Shevchenko Cc: Arnd Bergmann Cc: Linus Walleij Cc: Bartosz Golaszewski Cc: Masahiro Yamada Cc: Geert Uytterhoeven Cc: Phil Reid Cc: Geert Uytterhoeven Cc: Mathias Duckeck Cc: Morten Hein Tiljeset Cc: Sean Nyekjaer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/bitops/find.h | 17 +++++++++++++++++ include/linux/bitmap.h | 35 +++++++++++++++++++++++++++++++++++ include/linux/bitops.h | 12 ++++++++++++ lib/find_bit.c | 14 ++++++++++++++ 4 files changed, 78 insertions(+) (limited to 'include/linux') diff --git a/include/asm-generic/bitops/find.h b/include/asm-generic/bitops/find.h index 8a1ee10014de..9fdf21302fdf 100644 --- a/include/asm-generic/bitops/find.h +++ b/include/asm-generic/bitops/find.h @@ -80,4 +80,21 @@ extern unsigned long find_first_zero_bit(const unsigned long *addr, #endif /* CONFIG_GENERIC_FIND_FIRST_BIT */ +/** + * find_next_clump8 - find next 8-bit clump with set bits in a memory region + * @clump: location to store copy of found clump + * @addr: address to base the search on + * @size: bitmap size in number of bits + * @offset: bit offset at which to start searching + * + * Returns the bit offset for the next set clump; the found clump value is + * copied to the location pointed by @clump. If no bits are set, returns @size. + */ +extern unsigned long find_next_clump8(unsigned long *clump, + const unsigned long *addr, + unsigned long size, unsigned long offset); + +#define find_first_clump8(clump, bits, size) \ + find_next_clump8((clump), (bits), (size), 0) + #endif /*_ASM_GENERIC_BITOPS_FIND_H_ */ diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 29fc933df3bf..9f046609e809 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -66,6 +66,8 @@ * bitmap_allocate_region(bitmap, pos, order) Allocate specified bit region * bitmap_from_arr32(dst, buf, nbits) Copy nbits from u32[] buf to dst * bitmap_to_arr32(buf, src, nbits) Copy nbits from buf to u32[] dst + * bitmap_get_value8(map, start) Get 8bit value from map at start + * bitmap_set_value8(map, value, start) Set 8bit value to map at start * * Note, bitmap_zero() and bitmap_fill() operate over the region of * unsigned longs, that is, bits behind bitmap till the unsigned long @@ -489,6 +491,39 @@ static inline void bitmap_from_u64(unsigned long *dst, u64 mask) dst[1] = mask >> 32; } +/** + * bitmap_get_value8 - get an 8-bit value within a memory region + * @map: address to the bitmap memory region + * @start: bit offset of the 8-bit value; must be a multiple of 8 + * + * Returns the 8-bit value located at the @start bit offset within the @src + * memory region. + */ +static inline unsigned long bitmap_get_value8(const unsigned long *map, + unsigned long start) +{ + const size_t index = BIT_WORD(start); + const unsigned long offset = start % BITS_PER_LONG; + + return (map[index] >> offset) & 0xFF; +} + +/** + * bitmap_set_value8 - set an 8-bit value within a memory region + * @map: address to the bitmap memory region + * @value: the 8-bit value; values wider than 8 bits may clobber bitmap + * @start: bit offset of the 8-bit value; must be a multiple of 8 + */ +static inline void bitmap_set_value8(unsigned long *map, unsigned long value, + unsigned long start) +{ + const size_t index = BIT_WORD(start); + const unsigned long offset = start % BITS_PER_LONG; + + map[index] &= ~(0xFFUL << offset); + map[index] |= value << offset; +} + #endif /* __ASSEMBLY__ */ #endif /* __LINUX_BITMAP_H */ diff --git a/include/linux/bitops.h b/include/linux/bitops.h index c94a9ff9f082..e479067c202c 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -47,6 +47,18 @@ extern unsigned long __sw_hweight64(__u64 w); (bit) < (size); \ (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) +/** + * for_each_set_clump8 - iterate over bitmap for each 8-bit clump with set bits + * @start: bit offset to start search and to store the current iteration offset + * @clump: location to store copy of current 8-bit clump + * @bits: bitmap address to base the search on + * @size: bitmap size in number of bits + */ +#define for_each_set_clump8(start, clump, bits, size) \ + for ((start) = find_first_clump8(&(clump), (bits), (size)); \ + (start) < (size); \ + (start) = find_next_clump8(&(clump), (bits), (size), (start) + 8)) + static inline int get_bitmask_order(unsigned int count) { int order; diff --git a/lib/find_bit.c b/lib/find_bit.c index 5c51eb45178a..e35a76b291e6 100644 --- a/lib/find_bit.c +++ b/lib/find_bit.c @@ -214,3 +214,17 @@ EXPORT_SYMBOL(find_next_bit_le); #endif #endif /* __BIG_ENDIAN */ + +unsigned long find_next_clump8(unsigned long *clump, const unsigned long *addr, + unsigned long size, unsigned long offset) +{ + offset = find_next_bit(addr, size, offset); + if (offset == size) + return size; + + offset = round_down(offset, 8); + *clump = bitmap_get_value8(addr, offset); + + return offset; +} +EXPORT_SYMBOL(find_next_clump8); -- cgit v1.2.3-71-gd317 From 11d43e62f693c66c8c76c2ea2349e0f3c5764964 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Wed, 4 Dec 2019 16:51:47 -0800 Subject: lib/rbtree: set successor's parent unconditionally Both in Case 2 and 3, we exchange n and s. This mean no matter whether child2 is NULL or not, successor's parent should be assigned to node's. This patch takes this step out to make it explicit and reduce the ambiguity. Besides, this step reduces some symbol size like rb_erase(). KERN_CONFIG upstream patched OPT_FOR_PERF 877 870 OPT_FOR_SIZE 635 621 Link: http://lkml.kernel.org/r/20191028021442.5450-1-richardw.yang@linux.intel.com Signed-off-by: Wei Yang Acked-by: Peter Zijlstra (Intel) Reviewed-by: Michel Lespinasse Reviewed-by: Davidlohr Bueso Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rbtree_augmented.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index fdd421b8d9ae..99c42e1a74b8 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -283,14 +283,13 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root, __rb_change_child(node, successor, tmp, root); if (child2) { - successor->__rb_parent_color = pc; rb_set_parent_color(child2, parent, RB_BLACK); rebalance = NULL; } else { unsigned long pc2 = successor->__rb_parent_color; - successor->__rb_parent_color = pc; rebalance = __rb_is_black(pc2) ? parent : NULL; } + successor->__rb_parent_color = pc; tmp = successor; } -- cgit v1.2.3-71-gd317 From 8b7569a224a18953b9aee29c375e439b8a6eeb05 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Wed, 4 Dec 2019 16:51:50 -0800 Subject: lib/rbtree: get successor's color directly After move parent assignment out, we can check the color directly. Link: http://lkml.kernel.org/r/20191028021442.5450-2-richardw.yang@linux.intel.com Signed-off-by: Wei Yang Acked-by: Peter Zijlstra (Intel) Reviewed-by: Michel Lespinasse Reviewed-by: Davidlohr Bueso Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rbtree_augmented.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index 99c42e1a74b8..724b0d036b57 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -286,8 +286,7 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root, rb_set_parent_color(child2, parent, RB_BLACK); rebalance = NULL; } else { - unsigned long pc2 = successor->__rb_parent_color; - rebalance = __rb_is_black(pc2) ? parent : NULL; + rebalance = rb_is_black(successor) ? parent : NULL; } successor->__rb_parent_color = pc; tmp = successor; -- cgit v1.2.3-71-gd317 From 964975ac6677c97ae61ec9d6969dd5d03f18d1c3 Mon Sep 17 00:00:00 2001 From: Huang Shijie Date: Wed, 4 Dec 2019 16:52:03 -0800 Subject: lib/genalloc.c: rename addr_in_gen_pool to gen_pool_has_addr Follow the kernel conventions, rename addr_in_gen_pool to gen_pool_has_addr. [sjhuang@iluvatar.ai: fix Documentation/ too] Link: http://lkml.kernel.org/r/20181229015914.5573-1-sjhuang@iluvatar.ai Link: http://lkml.kernel.org/r/20181228083950.20398-1-sjhuang@iluvatar.ai Signed-off-by: Huang Shijie Reviewed-by: Andrew Morton Cc: Russell King Cc: Arnd Bergmann Cc: Greg Kroah-Hartman Cc: Christoph Hellwig Cc: Marek Szyprowski Cc: Robin Murphy Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/core-api/genalloc.rst | 2 +- arch/arm/mm/dma-mapping.c | 2 +- drivers/misc/sram-exec.c | 2 +- include/linux/genalloc.h | 2 +- kernel/dma/remap.c | 2 +- lib/genalloc.c | 6 +++--- 6 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/Documentation/core-api/genalloc.rst b/Documentation/core-api/genalloc.rst index 098a46f55798..a5af2cbf58a5 100644 --- a/Documentation/core-api/genalloc.rst +++ b/Documentation/core-api/genalloc.rst @@ -129,7 +129,7 @@ writing of special-purpose memory allocators in the future. :functions: gen_pool_for_each_chunk .. kernel-doc:: lib/genalloc.c - :functions: addr_in_gen_pool + :functions: gen_pool_has_addr .. kernel-doc:: lib/genalloc.c :functions: gen_pool_avail diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 1df6eb42f22e..e822af0d9219 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -529,7 +529,7 @@ static void *__alloc_from_pool(size_t size, struct page **ret_page) static bool __in_atomic_pool(void *start, size_t size) { - return addr_in_gen_pool(atomic_pool, (unsigned long)start, size); + return gen_pool_has_addr(atomic_pool, (unsigned long)start, size); } static int __free_from_pool(void *start, size_t size) diff --git a/drivers/misc/sram-exec.c b/drivers/misc/sram-exec.c index 426ad912b441..d054e2842a5f 100644 --- a/drivers/misc/sram-exec.c +++ b/drivers/misc/sram-exec.c @@ -96,7 +96,7 @@ void *sram_exec_copy(struct gen_pool *pool, void *dst, void *src, if (!part) return NULL; - if (!addr_in_gen_pool(pool, (unsigned long)dst, size)) + if (!gen_pool_has_addr(pool, (unsigned long)dst, size)) return NULL; base = (unsigned long)part->base; diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index 4bd583bd6934..5b14a0f38124 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -206,7 +206,7 @@ extern struct gen_pool *devm_gen_pool_create(struct device *dev, int min_alloc_order, int nid, const char *name); extern struct gen_pool *gen_pool_get(struct device *dev, const char *name); -bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start, +extern bool gen_pool_has_addr(struct gen_pool *pool, unsigned long start, size_t size); #ifdef CONFIG_OF diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c index d47bd40fc0f5..d14cbc83986a 100644 --- a/kernel/dma/remap.c +++ b/kernel/dma/remap.c @@ -178,7 +178,7 @@ bool dma_in_atomic_pool(void *start, size_t size) if (unlikely(!atomic_pool)) return false; - return addr_in_gen_pool(atomic_pool, (unsigned long)start, size); + return gen_pool_has_addr(atomic_pool, (unsigned long)start, size); } void *dma_alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags) diff --git a/lib/genalloc.c b/lib/genalloc.c index af9a57422186..7f1244b5294a 100644 --- a/lib/genalloc.c +++ b/lib/genalloc.c @@ -540,7 +540,7 @@ void gen_pool_for_each_chunk(struct gen_pool *pool, EXPORT_SYMBOL(gen_pool_for_each_chunk); /** - * addr_in_gen_pool - checks if an address falls within the range of a pool + * gen_pool_has_addr - checks if an address falls within the range of a pool * @pool: the generic memory pool * @start: start address * @size: size of the region @@ -548,7 +548,7 @@ EXPORT_SYMBOL(gen_pool_for_each_chunk); * Check if the range of addresses falls within the specified pool. Returns * true if the entire range is contained in the pool and false otherwise. */ -bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start, +bool gen_pool_has_addr(struct gen_pool *pool, unsigned long start, size_t size) { bool found = false; @@ -567,7 +567,7 @@ bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start, rcu_read_unlock(); return found; } -EXPORT_SYMBOL(addr_in_gen_pool); +EXPORT_SYMBOL(gen_pool_has_addr); /** * gen_pool_avail - get available free space of the pool -- cgit v1.2.3-71-gd317 From 6d13de1489b6bf539695f96d945de3860e6d5e17 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 4 Dec 2019 16:52:40 -0800 Subject: uaccess: disallow > INT_MAX copy sizes As we've done with VFS, string operations, etc, reject usercopy sizes larger than INT_MAX, which would be nice to have for catching bugs related to size calculation overflows[1]. This adds 10 bytes to x86_64 defconfig text and 1980 bytes to the data section: text data bss dec hex filename 19691167 5134320 1646664 26472151 193eed7 vmlinux.before 19691177 5136300 1646664 26474141 193f69d vmlinux.after [1] https://marc.info/?l=linux-s390&m=156631939010493&w=2 Link: http://lkml.kernel.org/r/201908251612.F9902D7A@keescook Signed-off-by: Kees Cook Suggested-by: Dan Carpenter Cc: Alexander Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/thread_info.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 659a4400517b..e93e249a4e9b 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -147,6 +147,8 @@ check_copy_size(const void *addr, size_t bytes, bool is_source) __bad_copy_to(); return false; } + if (WARN_ON_ONCE(bytes > INT_MAX)) + return false; check_object_size(addr, bytes, is_source); return true; } -- cgit v1.2.3-71-gd317 From eec028c9386ed1a692aa01a85b55952202b41619 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Wed, 4 Dec 2019 16:52:43 -0800 Subject: kcov: remote coverage support Patch series " kcov: collect coverage from usb and vhost", v3. This patchset extends kcov to allow collecting coverage from backgound kernel threads. This extension requires custom annotations for each of the places where coverage collection is desired. This patchset implements this for hub events in the USB subsystem and for vhost workers. See the first patch description for details about the kcov extension. The other two patches apply this kcov extension to USB and vhost. Examples of other subsystems that might potentially benefit from this when custom annotations are added (the list is based on process_one_work() callers for bugs recently reported by syzbot): 1. fs: writeback wb_workfn() worker, 2. net: addrconf_dad_work()/addrconf_verify_work() workers, 3. net: neigh_periodic_work() worker, 4. net/p9: p9_write_work()/p9_read_work() workers, 5. block: blk_mq_run_work_fn() worker. These patches have been used to enable coverage-guided USB fuzzing with syzkaller for the last few years, see the details here: https://github.com/google/syzkaller/blob/master/docs/linux/external_fuzzing_usb.md This patchset has been pushed to the public Linux kernel Gerrit instance: https://linux-review.googlesource.com/c/linux/kernel/git/torvalds/linux/+/1524 This patch (of 3): Add background thread coverage collection ability to kcov. With KCOV_ENABLE coverage is collected only for syscalls that are issued from the current process. With KCOV_REMOTE_ENABLE it's possible to collect coverage for arbitrary parts of the kernel code, provided that those parts are annotated with kcov_remote_start()/kcov_remote_stop(). This allows to collect coverage from two types of kernel background threads: the global ones, that are spawned during kernel boot in a limited number of instances (e.g. one USB hub_event() worker thread is spawned per USB HCD); and the local ones, that are spawned when a user interacts with some kernel interface (e.g. vhost workers). To enable collecting coverage from a global background thread, a unique global handle must be assigned and passed to the corresponding kcov_remote_start() call. Then a userspace process can pass a list of such handles to the KCOV_REMOTE_ENABLE ioctl in the handles array field of the kcov_remote_arg struct. This will attach the used kcov device to the code sections, that are referenced by those handles. Since there might be many local background threads spawned from different userspace processes, we can't use a single global handle per annotation. Instead, the userspace process passes a non-zero handle through the common_handle field of the kcov_remote_arg struct. This common handle gets saved to the kcov_handle field in the current task_struct and needs to be passed to the newly spawned threads via custom annotations. Those threads should in turn be annotated with kcov_remote_start()/kcov_remote_stop(). Internally kcov stores handles as u64 integers. The top byte of a handle is used to denote the id of a subsystem that this handle belongs to, and the lower 4 bytes are used to denote the id of a thread instance within that subsystem. A reserved value 0 is used as a subsystem id for common handles as they don't belong to a particular subsystem. The bytes 4-7 are currently reserved and must be zero. In the future the number of bytes used for the subsystem or handle ids might be increased. When a particular userspace process collects coverage by via a common handle, kcov will collect coverage for each code section that is annotated to use the common handle obtained as kcov_handle from the current task_struct. However non common handles allow to collect coverage selectively from different subsystems. Link: http://lkml.kernel.org/r/e90e315426a384207edbec1d6aa89e43008e4caf.1572366574.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Cc: Dmitry Vyukov Cc: Greg Kroah-Hartman Cc: Alan Stern Cc: "Michael S. Tsirkin" Cc: Jason Wang Cc: Arnd Bergmann Cc: Steven Rostedt Cc: David Windsor Cc: Elena Reshetova Cc: Anders Roxell Cc: Alexander Potapenko Cc: Marco Elver Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/dev-tools/kcov.rst | 129 +++++++++ include/linux/kcov.h | 23 ++ include/linux/sched.h | 8 + include/uapi/linux/kcov.h | 28 ++ kernel/kcov.c | 547 ++++++++++++++++++++++++++++++++++++--- 5 files changed, 700 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/Documentation/dev-tools/kcov.rst b/Documentation/dev-tools/kcov.rst index 42b612677799..36890b026e77 100644 --- a/Documentation/dev-tools/kcov.rst +++ b/Documentation/dev-tools/kcov.rst @@ -34,6 +34,7 @@ Profiling data will only become accessible once debugfs has been mounted:: Coverage collection ------------------- + The following program demonstrates coverage collection from within a test program using kcov: @@ -128,6 +129,7 @@ only need to enable coverage (disable happens automatically on thread end). Comparison operands collection ------------------------------ + Comparison operands collection is similar to coverage collection: .. code-block:: c @@ -202,3 +204,130 @@ Comparison operands collection is similar to coverage collection: Note that the kcov modes (coverage collection or comparison operands) are mutually exclusive. + +Remote coverage collection +-------------------------- + +With KCOV_ENABLE coverage is collected only for syscalls that are issued +from the current process. With KCOV_REMOTE_ENABLE it's possible to collect +coverage for arbitrary parts of the kernel code, provided that those parts +are annotated with kcov_remote_start()/kcov_remote_stop(). + +This allows to collect coverage from two types of kernel background +threads: the global ones, that are spawned during kernel boot in a limited +number of instances (e.g. one USB hub_event() worker thread is spawned per +USB HCD); and the local ones, that are spawned when a user interacts with +some kernel interface (e.g. vhost workers). + +To enable collecting coverage from a global background thread, a unique +global handle must be assigned and passed to the corresponding +kcov_remote_start() call. Then a userspace process can pass a list of such +handles to the KCOV_REMOTE_ENABLE ioctl in the handles array field of the +kcov_remote_arg struct. This will attach the used kcov device to the code +sections, that are referenced by those handles. + +Since there might be many local background threads spawned from different +userspace processes, we can't use a single global handle per annotation. +Instead, the userspace process passes a non-zero handle through the +common_handle field of the kcov_remote_arg struct. This common handle gets +saved to the kcov_handle field in the current task_struct and needs to be +passed to the newly spawned threads via custom annotations. Those threads +should in turn be annotated with kcov_remote_start()/kcov_remote_stop(). + +Internally kcov stores handles as u64 integers. The top byte of a handle +is used to denote the id of a subsystem that this handle belongs to, and +the lower 4 bytes are used to denote the id of a thread instance within +that subsystem. A reserved value 0 is used as a subsystem id for common +handles as they don't belong to a particular subsystem. The bytes 4-7 are +currently reserved and must be zero. In the future the number of bytes +used for the subsystem or handle ids might be increased. + +When a particular userspace proccess collects coverage by via a common +handle, kcov will collect coverage for each code section that is annotated +to use the common handle obtained as kcov_handle from the current +task_struct. However non common handles allow to collect coverage +selectively from different subsystems. + +.. code-block:: c + + struct kcov_remote_arg { + unsigned trace_mode; + unsigned area_size; + unsigned num_handles; + uint64_t common_handle; + uint64_t handles[0]; + }; + + #define KCOV_INIT_TRACE _IOR('c', 1, unsigned long) + #define KCOV_DISABLE _IO('c', 101) + #define KCOV_REMOTE_ENABLE _IOW('c', 102, struct kcov_remote_arg) + + #define COVER_SIZE (64 << 10) + + #define KCOV_TRACE_PC 0 + + #define KCOV_SUBSYSTEM_COMMON (0x00ull << 56) + #define KCOV_SUBSYSTEM_USB (0x01ull << 56) + + #define KCOV_SUBSYSTEM_MASK (0xffull << 56) + #define KCOV_INSTANCE_MASK (0xffffffffull) + + static inline __u64 kcov_remote_handle(__u64 subsys, __u64 inst) + { + if (subsys & ~KCOV_SUBSYSTEM_MASK || inst & ~KCOV_INSTANCE_MASK) + return 0; + return subsys | inst; + } + + #define KCOV_COMMON_ID 0x42 + #define KCOV_USB_BUS_NUM 1 + + int main(int argc, char **argv) + { + int fd; + unsigned long *cover, n, i; + struct kcov_remote_arg *arg; + + fd = open("/sys/kernel/debug/kcov", O_RDWR); + if (fd == -1) + perror("open"), exit(1); + if (ioctl(fd, KCOV_INIT_TRACE, COVER_SIZE)) + perror("ioctl"), exit(1); + cover = (unsigned long*)mmap(NULL, COVER_SIZE * sizeof(unsigned long), + PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + if ((void*)cover == MAP_FAILED) + perror("mmap"), exit(1); + + /* Enable coverage collection via common handle and from USB bus #1. */ + arg = calloc(1, sizeof(*arg) + sizeof(uint64_t)); + if (!arg) + perror("calloc"), exit(1); + arg->trace_mode = KCOV_TRACE_PC; + arg->area_size = COVER_SIZE; + arg->num_handles = 1; + arg->common_handle = kcov_remote_handle(KCOV_SUBSYSTEM_COMMON, + KCOV_COMMON_ID); + arg->handles[0] = kcov_remote_handle(KCOV_SUBSYSTEM_USB, + KCOV_USB_BUS_NUM); + if (ioctl(fd, KCOV_REMOTE_ENABLE, arg)) + perror("ioctl"), free(arg), exit(1); + free(arg); + + /* + * Here the user needs to trigger execution of a kernel code section + * that is either annotated with the common handle, or to trigger some + * activity on USB bus #1. + */ + sleep(2); + + n = __atomic_load_n(&cover[0], __ATOMIC_RELAXED); + for (i = 0; i < n; i++) + printf("0x%lx\n", cover[i + 1]); + if (ioctl(fd, KCOV_DISABLE, 0)) + perror("ioctl"), exit(1); + if (munmap(cover, COVER_SIZE * sizeof(unsigned long))) + perror("munmap"), exit(1); + if (close(fd)) + perror("close"), exit(1); + return 0; + } diff --git a/include/linux/kcov.h b/include/linux/kcov.h index b76a1807028d..a10e84707d82 100644 --- a/include/linux/kcov.h +++ b/include/linux/kcov.h @@ -37,12 +37,35 @@ do { \ (t)->kcov_mode &= ~KCOV_IN_CTXSW; \ } while (0) +/* See Documentation/dev-tools/kcov.rst for usage details. */ +void kcov_remote_start(u64 handle); +void kcov_remote_stop(void); +u64 kcov_common_handle(void); + +static inline void kcov_remote_start_common(u64 id) +{ + kcov_remote_start(kcov_remote_handle(KCOV_SUBSYSTEM_COMMON, id)); +} + +static inline void kcov_remote_start_usb(u64 id) +{ + kcov_remote_start(kcov_remote_handle(KCOV_SUBSYSTEM_USB, id)); +} + #else static inline void kcov_task_init(struct task_struct *t) {} static inline void kcov_task_exit(struct task_struct *t) {} static inline void kcov_prepare_switch(struct task_struct *t) {} static inline void kcov_finish_switch(struct task_struct *t) {} +static inline void kcov_remote_start(u64 handle) {} +static inline void kcov_remote_stop(void) {} +static inline u64 kcov_common_handle(void) +{ + return 0; +} +static inline void kcov_remote_start_common(u64 id) {} +static inline void kcov_remote_start_usb(u64 id) {} #endif /* CONFIG_KCOV */ #endif /* _LINUX_KCOV_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 0cd97d9dd021..467d26046416 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1210,6 +1210,8 @@ struct task_struct { #endif /* CONFIG_TRACING */ #ifdef CONFIG_KCOV + /* See kernel/kcov.c for more details. */ + /* Coverage collection mode enabled for this task (0 if disabled): */ unsigned int kcov_mode; @@ -1221,6 +1223,12 @@ struct task_struct { /* KCOV descriptor wired with this task or NULL: */ struct kcov *kcov; + + /* KCOV common handle for remote coverage collection: */ + u64 kcov_handle; + + /* KCOV sequence number: */ + int kcov_sequence; #endif #ifdef CONFIG_MEMCG diff --git a/include/uapi/linux/kcov.h b/include/uapi/linux/kcov.h index 9529867717a8..409d3ad1e6e2 100644 --- a/include/uapi/linux/kcov.h +++ b/include/uapi/linux/kcov.h @@ -4,9 +4,24 @@ #include +/* + * Argument for KCOV_REMOTE_ENABLE ioctl, see Documentation/dev-tools/kcov.rst + * and the comment before kcov_remote_start() for usage details. + */ +struct kcov_remote_arg { + unsigned int trace_mode; /* KCOV_TRACE_PC or KCOV_TRACE_CMP */ + unsigned int area_size; /* Length of coverage buffer in words */ + unsigned int num_handles; /* Size of handles array */ + __u64 common_handle; + __u64 handles[0]; +}; + +#define KCOV_REMOTE_MAX_HANDLES 0x100 + #define KCOV_INIT_TRACE _IOR('c', 1, unsigned long) #define KCOV_ENABLE _IO('c', 100) #define KCOV_DISABLE _IO('c', 101) +#define KCOV_REMOTE_ENABLE _IOW('c', 102, struct kcov_remote_arg) enum { /* @@ -32,4 +47,17 @@ enum { #define KCOV_CMP_SIZE(n) ((n) << 1) #define KCOV_CMP_MASK KCOV_CMP_SIZE(3) +#define KCOV_SUBSYSTEM_COMMON (0x00ull << 56) +#define KCOV_SUBSYSTEM_USB (0x01ull << 56) + +#define KCOV_SUBSYSTEM_MASK (0xffull << 56) +#define KCOV_INSTANCE_MASK (0xffffffffull) + +static inline __u64 kcov_remote_handle(__u64 subsys, __u64 inst) +{ + if (subsys & ~KCOV_SUBSYSTEM_MASK || inst & ~KCOV_INSTANCE_MASK) + return 0; + return subsys | inst; +} + #endif /* _LINUX_KCOV_IOCTLS_H */ diff --git a/kernel/kcov.c b/kernel/kcov.c index 2ee38727844a..f50354202dbe 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -21,8 +22,11 @@ #include #include #include +#include #include +#define kcov_debug(fmt, ...) pr_debug("%s: " fmt, __func__, ##__VA_ARGS__) + /* Number of 64-bit words written per one comparison: */ #define KCOV_WORDS_PER_CMP 4 @@ -44,19 +48,100 @@ struct kcov { * Reference counter. We keep one for: * - opened file descriptor * - task with enabled coverage (we can't unwire it from another task) + * - each code section for remote coverage collection */ refcount_t refcount; /* The lock protects mode, size, area and t. */ spinlock_t lock; enum kcov_mode mode; - /* Size of arena (in long's for KCOV_MODE_TRACE). */ - unsigned size; + /* Size of arena (in long's). */ + unsigned int size; /* Coverage buffer shared with user space. */ void *area; /* Task for which we collect coverage, or NULL. */ struct task_struct *t; + /* Collecting coverage from remote (background) threads. */ + bool remote; + /* Size of remote area (in long's). */ + unsigned int remote_size; + /* + * Sequence is incremented each time kcov is reenabled, used by + * kcov_remote_stop(), see the comment there. + */ + int sequence; }; +struct kcov_remote_area { + struct list_head list; + unsigned int size; +}; + +struct kcov_remote { + u64 handle; + struct kcov *kcov; + struct hlist_node hnode; +}; + +static DEFINE_SPINLOCK(kcov_remote_lock); +static DEFINE_HASHTABLE(kcov_remote_map, 4); +static struct list_head kcov_remote_areas = LIST_HEAD_INIT(kcov_remote_areas); + +/* Must be called with kcov_remote_lock locked. */ +static struct kcov_remote *kcov_remote_find(u64 handle) +{ + struct kcov_remote *remote; + + hash_for_each_possible(kcov_remote_map, remote, hnode, handle) { + if (remote->handle == handle) + return remote; + } + return NULL; +} + +static struct kcov_remote *kcov_remote_add(struct kcov *kcov, u64 handle) +{ + struct kcov_remote *remote; + + if (kcov_remote_find(handle)) + return ERR_PTR(-EEXIST); + remote = kmalloc(sizeof(*remote), GFP_ATOMIC); + if (!remote) + return ERR_PTR(-ENOMEM); + remote->handle = handle; + remote->kcov = kcov; + hash_add(kcov_remote_map, &remote->hnode, handle); + return remote; +} + +/* Must be called with kcov_remote_lock locked. */ +static struct kcov_remote_area *kcov_remote_area_get(unsigned int size) +{ + struct kcov_remote_area *area; + struct list_head *pos; + + kcov_debug("size = %u\n", size); + list_for_each(pos, &kcov_remote_areas) { + area = list_entry(pos, struct kcov_remote_area, list); + if (area->size == size) { + list_del(&area->list); + kcov_debug("rv = %px\n", area); + return area; + } + } + kcov_debug("rv = NULL\n"); + return NULL; +} + +/* Must be called with kcov_remote_lock locked. */ +static void kcov_remote_area_put(struct kcov_remote_area *area, + unsigned int size) +{ + kcov_debug("area = %px, size = %u\n", area, size); + INIT_LIST_HEAD(&area->list); + area->size = size; + list_add(&area->list, &kcov_remote_areas); +} + static notrace bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t) { unsigned int mode; @@ -73,7 +158,7 @@ static notrace bool check_kcov_mode(enum kcov_mode needed_mode, struct task_stru * in_interrupt() returns false (e.g. preempt_schedule_irq()). * READ_ONCE()/barrier() effectively provides load-acquire wrt * interrupts, there are paired barrier()/WRITE_ONCE() in - * kcov_ioctl_locked(). + * kcov_start(). */ barrier(); return mode == needed_mode; @@ -227,6 +312,78 @@ void notrace __sanitizer_cov_trace_switch(u64 val, u64 *cases) EXPORT_SYMBOL(__sanitizer_cov_trace_switch); #endif /* ifdef CONFIG_KCOV_ENABLE_COMPARISONS */ +static void kcov_start(struct task_struct *t, unsigned int size, + void *area, enum kcov_mode mode, int sequence) +{ + kcov_debug("t = %px, size = %u, area = %px\n", t, size, area); + /* Cache in task struct for performance. */ + t->kcov_size = size; + t->kcov_area = area; + /* See comment in check_kcov_mode(). */ + barrier(); + WRITE_ONCE(t->kcov_mode, mode); + t->kcov_sequence = sequence; +} + +static void kcov_stop(struct task_struct *t) +{ + WRITE_ONCE(t->kcov_mode, KCOV_MODE_DISABLED); + barrier(); + t->kcov_size = 0; + t->kcov_area = NULL; +} + +static void kcov_task_reset(struct task_struct *t) +{ + kcov_stop(t); + t->kcov = NULL; + t->kcov_sequence = 0; + t->kcov_handle = 0; +} + +void kcov_task_init(struct task_struct *t) +{ + kcov_task_reset(t); + t->kcov_handle = current->kcov_handle; +} + +static void kcov_reset(struct kcov *kcov) +{ + kcov->t = NULL; + kcov->mode = KCOV_MODE_INIT; + kcov->remote = false; + kcov->remote_size = 0; + kcov->sequence++; +} + +static void kcov_remote_reset(struct kcov *kcov) +{ + int bkt; + struct kcov_remote *remote; + struct hlist_node *tmp; + + spin_lock(&kcov_remote_lock); + hash_for_each_safe(kcov_remote_map, bkt, tmp, remote, hnode) { + if (remote->kcov != kcov) + continue; + kcov_debug("removing handle %llx\n", remote->handle); + hash_del(&remote->hnode); + kfree(remote); + } + /* Do reset before unlock to prevent races with kcov_remote_start(). */ + kcov_reset(kcov); + spin_unlock(&kcov_remote_lock); +} + +static void kcov_disable(struct task_struct *t, struct kcov *kcov) +{ + kcov_task_reset(t); + if (kcov->remote) + kcov_remote_reset(kcov); + else + kcov_reset(kcov); +} + static void kcov_get(struct kcov *kcov) { refcount_inc(&kcov->refcount); @@ -235,20 +392,12 @@ static void kcov_get(struct kcov *kcov) static void kcov_put(struct kcov *kcov) { if (refcount_dec_and_test(&kcov->refcount)) { + kcov_remote_reset(kcov); vfree(kcov->area); kfree(kcov); } } -void kcov_task_init(struct task_struct *t) -{ - WRITE_ONCE(t->kcov_mode, KCOV_MODE_DISABLED); - barrier(); - t->kcov_size = 0; - t->kcov_area = NULL; - t->kcov = NULL; -} - void kcov_task_exit(struct task_struct *t) { struct kcov *kcov; @@ -256,15 +405,36 @@ void kcov_task_exit(struct task_struct *t) kcov = t->kcov; if (kcov == NULL) return; + spin_lock(&kcov->lock); + kcov_debug("t = %px, kcov->t = %px\n", t, kcov->t); + /* + * For KCOV_ENABLE devices we want to make sure that t->kcov->t == t, + * which comes down to: + * WARN_ON(!kcov->remote && kcov->t != t); + * + * For KCOV_REMOTE_ENABLE devices, the exiting task is either: + * 2. A remote task between kcov_remote_start() and kcov_remote_stop(). + * In this case we should print a warning right away, since a task + * shouldn't be exiting when it's in a kcov coverage collection + * section. Here t points to the task that is collecting remote + * coverage, and t->kcov->t points to the thread that created the + * kcov device. Which means that to detect this case we need to + * check that t != t->kcov->t, and this gives us the following: + * WARN_ON(kcov->remote && kcov->t != t); + * + * 2. The task that created kcov exiting without calling KCOV_DISABLE, + * and then again we can make sure that t->kcov->t == t: + * WARN_ON(kcov->remote && kcov->t != t); + * + * By combining all three checks into one we get: + */ if (WARN_ON(kcov->t != t)) { spin_unlock(&kcov->lock); return; } /* Just to not leave dangling references behind. */ - kcov_task_init(t); - kcov->t = NULL; - kcov->mode = KCOV_MODE_INIT; + kcov_disable(t, kcov); spin_unlock(&kcov->lock); kcov_put(kcov); } @@ -313,6 +483,7 @@ static int kcov_open(struct inode *inode, struct file *filep) if (!kcov) return -ENOMEM; kcov->mode = KCOV_MODE_DISABLED; + kcov->sequence = 1; refcount_set(&kcov->refcount, 1); spin_lock_init(&kcov->lock); filep->private_data = kcov; @@ -325,6 +496,20 @@ static int kcov_close(struct inode *inode, struct file *filep) return 0; } +static int kcov_get_mode(unsigned long arg) +{ + if (arg == KCOV_TRACE_PC) + return KCOV_MODE_TRACE_PC; + else if (arg == KCOV_TRACE_CMP) +#ifdef CONFIG_KCOV_ENABLE_COMPARISONS + return KCOV_MODE_TRACE_CMP; +#else + return -ENOTSUPP; +#endif + else + return -EINVAL; +} + /* * Fault in a lazily-faulted vmalloc area before it can be used by * __santizer_cov_trace_pc(), to avoid recursion issues if any code on the @@ -340,14 +525,35 @@ static void kcov_fault_in_area(struct kcov *kcov) READ_ONCE(area[offset]); } +static inline bool kcov_check_handle(u64 handle, bool common_valid, + bool uncommon_valid, bool zero_valid) +{ + if (handle & ~(KCOV_SUBSYSTEM_MASK | KCOV_INSTANCE_MASK)) + return false; + switch (handle & KCOV_SUBSYSTEM_MASK) { + case KCOV_SUBSYSTEM_COMMON: + return (handle & KCOV_INSTANCE_MASK) ? + common_valid : zero_valid; + case KCOV_SUBSYSTEM_USB: + return uncommon_valid; + default: + return false; + } + return false; +} + static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, unsigned long arg) { struct task_struct *t; unsigned long size, unused; + int mode, i; + struct kcov_remote_arg *remote_arg; + struct kcov_remote *remote; switch (cmd) { case KCOV_INIT_TRACE: + kcov_debug("KCOV_INIT_TRACE\n"); /* * Enable kcov in trace mode and setup buffer size. * Must happen before anything else. @@ -366,6 +572,7 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, kcov->mode = KCOV_MODE_INIT; return 0; case KCOV_ENABLE: + kcov_debug("KCOV_ENABLE\n"); /* * Enable coverage for the current task. * At this point user must have been enabled trace mode, @@ -378,29 +585,20 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, t = current; if (kcov->t != NULL || t->kcov != NULL) return -EBUSY; - if (arg == KCOV_TRACE_PC) - kcov->mode = KCOV_MODE_TRACE_PC; - else if (arg == KCOV_TRACE_CMP) -#ifdef CONFIG_KCOV_ENABLE_COMPARISONS - kcov->mode = KCOV_MODE_TRACE_CMP; -#else - return -ENOTSUPP; -#endif - else - return -EINVAL; + mode = kcov_get_mode(arg); + if (mode < 0) + return mode; kcov_fault_in_area(kcov); - /* Cache in task struct for performance. */ - t->kcov_size = kcov->size; - t->kcov_area = kcov->area; - /* See comment in check_kcov_mode(). */ - barrier(); - WRITE_ONCE(t->kcov_mode, kcov->mode); + kcov->mode = mode; + kcov_start(t, kcov->size, kcov->area, kcov->mode, + kcov->sequence); t->kcov = kcov; kcov->t = t; - /* This is put either in kcov_task_exit() or in KCOV_DISABLE. */ + /* Put either in kcov_task_exit() or in KCOV_DISABLE. */ kcov_get(kcov); return 0; case KCOV_DISABLE: + kcov_debug("KCOV_DISABLE\n"); /* Disable coverage for the current task. */ unused = arg; if (unused != 0 || current->kcov != kcov) @@ -408,11 +606,65 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, t = current; if (WARN_ON(kcov->t != t)) return -EINVAL; - kcov_task_init(t); - kcov->t = NULL; - kcov->mode = KCOV_MODE_INIT; + kcov_disable(t, kcov); kcov_put(kcov); return 0; + case KCOV_REMOTE_ENABLE: + kcov_debug("KCOV_REMOTE_ENABLE\n"); + if (kcov->mode != KCOV_MODE_INIT || !kcov->area) + return -EINVAL; + t = current; + if (kcov->t != NULL || t->kcov != NULL) + return -EBUSY; + remote_arg = (struct kcov_remote_arg *)arg; + mode = kcov_get_mode(remote_arg->trace_mode); + if (mode < 0) + return mode; + if (remote_arg->area_size > LONG_MAX / sizeof(unsigned long)) + return -EINVAL; + kcov->mode = mode; + t->kcov = kcov; + kcov->t = t; + kcov->remote = true; + kcov->remote_size = remote_arg->area_size; + spin_lock(&kcov_remote_lock); + for (i = 0; i < remote_arg->num_handles; i++) { + kcov_debug("handle %llx\n", remote_arg->handles[i]); + if (!kcov_check_handle(remote_arg->handles[i], + false, true, false)) { + spin_unlock(&kcov_remote_lock); + kcov_disable(t, kcov); + return -EINVAL; + } + remote = kcov_remote_add(kcov, remote_arg->handles[i]); + if (IS_ERR(remote)) { + spin_unlock(&kcov_remote_lock); + kcov_disable(t, kcov); + return PTR_ERR(remote); + } + } + if (remote_arg->common_handle) { + kcov_debug("common handle %llx\n", + remote_arg->common_handle); + if (!kcov_check_handle(remote_arg->common_handle, + true, false, false)) { + spin_unlock(&kcov_remote_lock); + kcov_disable(t, kcov); + return -EINVAL; + } + remote = kcov_remote_add(kcov, + remote_arg->common_handle); + if (IS_ERR(remote)) { + spin_unlock(&kcov_remote_lock); + kcov_disable(t, kcov); + return PTR_ERR(remote); + } + t->kcov_handle = remote_arg->common_handle; + } + spin_unlock(&kcov_remote_lock); + /* Put either in kcov_task_exit() or in KCOV_DISABLE. */ + kcov_get(kcov); + return 0; default: return -ENOTTY; } @@ -422,11 +674,35 @@ static long kcov_ioctl(struct file *filep, unsigned int cmd, unsigned long arg) { struct kcov *kcov; int res; + struct kcov_remote_arg *remote_arg = NULL; + unsigned int remote_num_handles; + unsigned long remote_arg_size; + + if (cmd == KCOV_REMOTE_ENABLE) { + if (get_user(remote_num_handles, (unsigned __user *)(arg + + offsetof(struct kcov_remote_arg, num_handles)))) + return -EFAULT; + if (remote_num_handles > KCOV_REMOTE_MAX_HANDLES) + return -EINVAL; + remote_arg_size = struct_size(remote_arg, handles, + remote_num_handles); + remote_arg = memdup_user((void __user *)arg, remote_arg_size); + if (IS_ERR(remote_arg)) + return PTR_ERR(remote_arg); + if (remote_arg->num_handles != remote_num_handles) { + kfree(remote_arg); + return -EINVAL; + } + arg = (unsigned long)remote_arg; + } kcov = filep->private_data; spin_lock(&kcov->lock); res = kcov_ioctl_locked(kcov, cmd, arg); spin_unlock(&kcov->lock); + + kfree(remote_arg); + return res; } @@ -438,6 +714,207 @@ static const struct file_operations kcov_fops = { .release = kcov_close, }; +/* + * kcov_remote_start() and kcov_remote_stop() can be used to annotate a section + * of code in a kernel background thread to allow kcov to be used to collect + * coverage from that part of code. + * + * The handle argument of kcov_remote_start() identifies a code section that is + * used for coverage collection. A userspace process passes this handle to + * KCOV_REMOTE_ENABLE ioctl to make the used kcov device start collecting + * coverage for the code section identified by this handle. + * + * The usage of these annotations in the kernel code is different depending on + * the type of the kernel thread whose code is being annotated. + * + * For global kernel threads that are spawned in a limited number of instances + * (e.g. one USB hub_event() worker thread is spawned per USB HCD), each + * instance must be assigned a unique 4-byte instance id. The instance id is + * then combined with a 1-byte subsystem id to get a handle via + * kcov_remote_handle(subsystem_id, instance_id). + * + * For local kernel threads that are spawned from system calls handler when a + * user interacts with some kernel interface (e.g. vhost workers), a handle is + * passed from a userspace process as the common_handle field of the + * kcov_remote_arg struct (note, that the user must generate a handle by using + * kcov_remote_handle() with KCOV_SUBSYSTEM_COMMON as the subsystem id and an + * arbitrary 4-byte non-zero number as the instance id). This common handle + * then gets saved into the task_struct of the process that issued the + * KCOV_REMOTE_ENABLE ioctl. When this proccess issues system calls that spawn + * kernel threads, the common handle must be retrived via kcov_common_handle() + * and passed to the spawned threads via custom annotations. Those kernel + * threads must in turn be annotated with kcov_remote_start(common_handle) and + * kcov_remote_stop(). All of the threads that are spawned by the same process + * obtain the same handle, hence the name "common". + * + * See Documentation/dev-tools/kcov.rst for more details. + * + * Internally, this function looks up the kcov device associated with the + * provided handle, allocates an area for coverage collection, and saves the + * pointers to kcov and area into the current task_struct to allow coverage to + * be collected via __sanitizer_cov_trace_pc() + * In turns kcov_remote_stop() clears those pointers from task_struct to stop + * collecting coverage and copies all collected coverage into the kcov area. + */ +void kcov_remote_start(u64 handle) +{ + struct kcov_remote *remote; + void *area; + struct task_struct *t; + unsigned int size; + enum kcov_mode mode; + int sequence; + + if (WARN_ON(!kcov_check_handle(handle, true, true, true))) + return; + if (WARN_ON(!in_task())) + return; + t = current; + /* + * Check that kcov_remote_start is not called twice + * nor called by user tasks (with enabled kcov). + */ + if (WARN_ON(t->kcov)) + return; + + kcov_debug("handle = %llx\n", handle); + + spin_lock(&kcov_remote_lock); + remote = kcov_remote_find(handle); + if (!remote) { + kcov_debug("no remote found"); + spin_unlock(&kcov_remote_lock); + return; + } + /* Put in kcov_remote_stop(). */ + kcov_get(remote->kcov); + t->kcov = remote->kcov; + /* + * Read kcov fields before unlock to prevent races with + * KCOV_DISABLE / kcov_remote_reset(). + */ + size = remote->kcov->remote_size; + mode = remote->kcov->mode; + sequence = remote->kcov->sequence; + area = kcov_remote_area_get(size); + spin_unlock(&kcov_remote_lock); + + if (!area) { + area = vmalloc(size * sizeof(unsigned long)); + if (!area) { + t->kcov = NULL; + kcov_put(remote->kcov); + return; + } + } + /* Reset coverage size. */ + *(u64 *)area = 0; + + kcov_debug("area = %px, size = %u", area, size); + + kcov_start(t, size, area, mode, sequence); + +} +EXPORT_SYMBOL(kcov_remote_start); + +static void kcov_move_area(enum kcov_mode mode, void *dst_area, + unsigned int dst_area_size, void *src_area) +{ + u64 word_size = sizeof(unsigned long); + u64 count_size, entry_size_log; + u64 dst_len, src_len; + void *dst_entries, *src_entries; + u64 dst_occupied, dst_free, bytes_to_move, entries_moved; + + kcov_debug("%px %u <= %px %lu\n", + dst_area, dst_area_size, src_area, *(unsigned long *)src_area); + + switch (mode) { + case KCOV_MODE_TRACE_PC: + dst_len = READ_ONCE(*(unsigned long *)dst_area); + src_len = *(unsigned long *)src_area; + count_size = sizeof(unsigned long); + entry_size_log = __ilog2_u64(sizeof(unsigned long)); + break; + case KCOV_MODE_TRACE_CMP: + dst_len = READ_ONCE(*(u64 *)dst_area); + src_len = *(u64 *)src_area; + count_size = sizeof(u64); + BUILD_BUG_ON(!is_power_of_2(KCOV_WORDS_PER_CMP)); + entry_size_log = __ilog2_u64(sizeof(u64) * KCOV_WORDS_PER_CMP); + break; + default: + WARN_ON(1); + return; + } + + /* As arm can't divide u64 integers use log of entry size. */ + if (dst_len > ((dst_area_size * word_size - count_size) >> + entry_size_log)) + return; + dst_occupied = count_size + (dst_len << entry_size_log); + dst_free = dst_area_size * word_size - dst_occupied; + bytes_to_move = min(dst_free, src_len << entry_size_log); + dst_entries = dst_area + dst_occupied; + src_entries = src_area + count_size; + memcpy(dst_entries, src_entries, bytes_to_move); + entries_moved = bytes_to_move >> entry_size_log; + + switch (mode) { + case KCOV_MODE_TRACE_PC: + WRITE_ONCE(*(unsigned long *)dst_area, dst_len + entries_moved); + break; + case KCOV_MODE_TRACE_CMP: + WRITE_ONCE(*(u64 *)dst_area, dst_len + entries_moved); + break; + default: + break; + } +} + +/* See the comment before kcov_remote_start() for usage details. */ +void kcov_remote_stop(void) +{ + struct task_struct *t = current; + struct kcov *kcov = t->kcov; + void *area = t->kcov_area; + unsigned int size = t->kcov_size; + int sequence = t->kcov_sequence; + + if (!kcov) { + kcov_debug("no kcov found\n"); + return; + } + + kcov_stop(t); + t->kcov = NULL; + + spin_lock(&kcov->lock); + /* + * KCOV_DISABLE could have been called between kcov_remote_start() + * and kcov_remote_stop(), hence the check. + */ + kcov_debug("move if: %d == %d && %d\n", + sequence, kcov->sequence, (int)kcov->remote); + if (sequence == kcov->sequence && kcov->remote) + kcov_move_area(kcov->mode, kcov->area, kcov->size, area); + spin_unlock(&kcov->lock); + + spin_lock(&kcov_remote_lock); + kcov_remote_area_put(area, size); + spin_unlock(&kcov_remote_lock); + + kcov_put(kcov); +} +EXPORT_SYMBOL(kcov_remote_stop); + +/* See the comment before kcov_remote_start() for usage details. */ +u64 kcov_common_handle(void) +{ + return current->kcov_handle; +} +EXPORT_SYMBOL(kcov_common_handle); + static int __init kcov_init(void) { /* -- cgit v1.2.3-71-gd317 From 30544ed5de431fe25d3793e4dd5a058d877c4d77 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 4 Dec 2019 16:53:26 -0800 Subject: lib/bitmap: introduce bitmap_replace() helper In some drivers we want to have a single operation over bitmap which is an equivalent to: *dst = (*old & ~(*mask)) | (*new & *mask) Introduce bitmap_replace() helper for this. Link: http://lkml.kernel.org/r/20191022172922.61232-8-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Acked-by: Linus Walleij Cc: Rasmus Villemoes Cc: Bartosz Golaszewski Cc: Geert Uytterhoeven Cc: Marek Vasut Cc: Thomas Petazzoni Cc: William Breathitt Gray Cc: Yury Norov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 16 ++++++++++++++++ lib/bitmap.c | 12 ++++++++++++ lib/test_bitmap.c | 38 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 66 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 9f046609e809..ff335b22f23c 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -53,6 +53,7 @@ * bitmap_find_next_zero_area_off(buf, len, pos, n, mask) as above * bitmap_shift_right(dst, src, n, nbits) *dst = *src >> n * bitmap_shift_left(dst, src, n, nbits) *dst = *src << n + * bitmap_replace(dst, old, new, mask, nbits) *dst = (*old & ~(*mask)) | (*new & *mask) * bitmap_remap(dst, src, old, new, nbits) *dst = map(old, new)(src) * bitmap_bitremap(oldbit, old, new, nbits) newbit = map(old, new)(oldbit) * bitmap_onto(dst, orig, relmap, nbits) *dst = orig relative to relmap @@ -140,6 +141,9 @@ extern void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); +extern void __bitmap_replace(unsigned long *dst, + const unsigned long *old, const unsigned long *new, + const unsigned long *mask, unsigned int nbits); extern int __bitmap_intersects(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern int __bitmap_subset(const unsigned long *bitmap1, @@ -434,6 +438,18 @@ static inline void bitmap_shift_left(unsigned long *dst, const unsigned long *sr __bitmap_shift_left(dst, src, shift, nbits); } +static inline void bitmap_replace(unsigned long *dst, + const unsigned long *old, + const unsigned long *new, + const unsigned long *mask, + unsigned int nbits) +{ + if (small_const_nbits(nbits)) + *dst = (*old & ~(*mask)) | (*new & *mask); + else + __bitmap_replace(dst, old, new, mask, nbits); +} + static inline int bitmap_parse(const char *buf, unsigned int buflen, unsigned long *maskp, int nmaskbits) { diff --git a/lib/bitmap.c b/lib/bitmap.c index f9e834841e94..4250519d7d1c 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -222,6 +222,18 @@ int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, } EXPORT_SYMBOL(__bitmap_andnot); +void __bitmap_replace(unsigned long *dst, + const unsigned long *old, const unsigned long *new, + const unsigned long *mask, unsigned int nbits) +{ + unsigned int k; + unsigned int nr = BITS_TO_LONGS(nbits); + + for (k = 0; k < nr; k++) + dst[k] = (old[k] & ~mask[k]) | (new[k] & mask[k]); +} +EXPORT_SYMBOL(__bitmap_replace); + int __bitmap_intersects(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index 4544847cf81e..e14a15ac250b 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -42,6 +42,19 @@ static const unsigned long exp2[] __initconst = { BITMAP_FROM_U64(0xffffffff77777777ULL), }; +/* Fibonacci sequence */ +static const unsigned long exp2_to_exp3_mask[] __initconst = { + BITMAP_FROM_U64(0x008000020020212eULL), +}; +/* exp3_0_1 = (exp2[0] & ~exp2_to_exp3_mask) | (exp2[1] & exp2_to_exp3_mask) */ +static const unsigned long exp3_0_1[] __initconst = { + BITMAP_FROM_U64(0x33b3333311313137ULL), +}; +/* exp3_1_0 = (exp2[1] & ~exp2_to_exp3_mask) | (exp2[0] & exp2_to_exp3_mask) */ +static const unsigned long exp3_1_0[] __initconst = { + BITMAP_FROM_U64(0xff7fffff77575751ULL), +}; + static bool __init __check_eq_uint(const char *srcfile, unsigned int line, const unsigned int exp_uint, unsigned int x) @@ -257,6 +270,30 @@ static void __init test_copy(void) expect_eq_pbl("0-108,128-1023", bmap2, 1024); } +#define EXP2_IN_BITS (sizeof(exp2) * 8) + +static void __init test_replace(void) +{ + unsigned int nbits = 64; + DECLARE_BITMAP(bmap, 1024); + + bitmap_zero(bmap, 1024); + bitmap_replace(bmap, &exp2[0], &exp2[1], exp2_to_exp3_mask, nbits); + expect_eq_bitmap(bmap, exp3_0_1, nbits); + + bitmap_zero(bmap, 1024); + bitmap_replace(bmap, &exp2[1], &exp2[0], exp2_to_exp3_mask, nbits); + expect_eq_bitmap(bmap, exp3_1_0, nbits); + + bitmap_fill(bmap, 1024); + bitmap_replace(bmap, &exp2[0], &exp2[1], exp2_to_exp3_mask, nbits); + expect_eq_bitmap(bmap, exp3_0_1, nbits); + + bitmap_fill(bmap, 1024); + bitmap_replace(bmap, &exp2[1], &exp2[0], exp2_to_exp3_mask, nbits); + expect_eq_bitmap(bmap, exp3_1_0, nbits); +} + #define PARSE_TIME 0x1 struct test_bitmap_parselist{ @@ -476,6 +513,7 @@ static void __init selftest(void) test_zero_clear(); test_fill_set(); test_copy(); + test_replace(); test_bitmap_arr32(); test_bitmap_parselist(); test_bitmap_parselist_user(); -- cgit v1.2.3-71-gd317 From f949286c668aed5aa24acdb5838be9cfd9513bd3 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 4 Dec 2019 16:54:32 -0800 Subject: mm: remove __ARCH_HAS_4LEVEL_HACK and include/asm-generic/4level-fixup.h There are no architectures that use include/asm-generic/4level-fixup.h therefore it can be removed along with __ARCH_HAS_4LEVEL_HACK define. Link: http://lkml.kernel.org/r/1572938135-31886-14-git-send-email-rppt@kernel.org Signed-off-by: Mike Rapoport Cc: Anatoly Pugachev Cc: Anton Ivanov Cc: Arnd Bergmann Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Ungerer Cc: Helge Deller Cc: "James E.J. Bottomley" Cc: Jeff Dike Cc: "Kirill A. Shutemov" Cc: Mark Salter Cc: Matt Turner Cc: Michal Simek Cc: Peter Rosin Cc: Richard Weinberger Cc: Rolf Eike Beer Cc: Russell King Cc: Russell King Cc: Sam Creasey Cc: Vincent Chen Cc: Vineet Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/4level-fixup.h | 39 -------------------------------------- include/linux/mm.h | 10 +++++----- mm/memory.c | 8 -------- 3 files changed, 5 insertions(+), 52 deletions(-) delete mode 100644 include/asm-generic/4level-fixup.h (limited to 'include/linux') diff --git a/include/asm-generic/4level-fixup.h b/include/asm-generic/4level-fixup.h deleted file mode 100644 index c86cf7cb4bba..000000000000 --- a/include/asm-generic/4level-fixup.h +++ /dev/null @@ -1,39 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _4LEVEL_FIXUP_H -#define _4LEVEL_FIXUP_H - -#define __ARCH_HAS_4LEVEL_HACK -#define __PAGETABLE_PUD_FOLDED 1 - -#define PUD_SHIFT PGDIR_SHIFT -#define PUD_SIZE PGDIR_SIZE -#define PUD_MASK PGDIR_MASK -#define PTRS_PER_PUD 1 - -#define pud_t pgd_t - -#define pmd_alloc(mm, pud, address) \ - ((unlikely(pgd_none(*(pud))) && __pmd_alloc(mm, pud, address))? \ - NULL: pmd_offset(pud, address)) - -#define pud_offset(pgd, start) (pgd) -#define pud_none(pud) 0 -#define pud_bad(pud) 0 -#define pud_present(pud) 1 -#define pud_ERROR(pud) do { } while (0) -#define pud_clear(pud) pgd_clear(pud) -#define pud_val(pud) pgd_val(pud) -#define pud_populate(mm, pud, pmd) pgd_populate(mm, pud, pmd) -#define pud_page(pud) pgd_page(pud) -#define pud_page_vaddr(pud) pgd_page_vaddr(pud) - -#undef pud_free_tlb -#define pud_free_tlb(tlb, x, addr) do { } while (0) -#define pud_free(mm, x) do { } while (0) - -#undef pud_addr_end -#define pud_addr_end(addr, end) (end) - -#include - -#endif diff --git a/include/linux/mm.h b/include/linux/mm.h index 8b0ef04b6d15..c97ea3b694e6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1838,12 +1838,12 @@ static inline void mm_dec_nr_ptes(struct mm_struct *mm) {} int __pte_alloc(struct mm_struct *mm, pmd_t *pmd); int __pte_alloc_kernel(pmd_t *pmd); +#if defined(CONFIG_MMU) + /* - * The following ifdef needed to get the 4level-fixup.h header to work. - * Remove it when 4level-fixup.h has been removed. + * The following ifdef needed to get the 5level-fixup.h header to work. + * Remove it when 5level-fixup.h has been removed. */ -#if defined(CONFIG_MMU) && !defined(__ARCH_HAS_4LEVEL_HACK) - #ifndef __ARCH_HAS_5LEVEL_HACK static inline p4d_t *p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) @@ -1865,7 +1865,7 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))? NULL: pmd_offset(pud, address); } -#endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */ +#endif /* CONFIG_MMU */ #if USE_SPLIT_PTE_PTLOCKS #if ALLOC_SPLIT_PTLOCKS diff --git a/mm/memory.c b/mm/memory.c index e455160e0f75..606da187d1de 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4197,19 +4197,11 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) smp_wmb(); /* See comment in __pte_alloc */ ptl = pud_lock(mm, pud); -#ifndef __ARCH_HAS_4LEVEL_HACK if (!pud_present(*pud)) { mm_inc_nr_pmds(mm); pud_populate(mm, pud, new); } else /* Another has populated it */ pmd_free(mm, new); -#else - if (!pgd_present(*pud)) { - mm_inc_nr_pmds(mm); - pgd_populate(mm, pud, new); - } else /* Another has populated it */ - pmd_free(mm, new); -#endif /* __ARCH_HAS_4LEVEL_HACK */ spin_unlock(ptl); return 0; } -- cgit v1.2.3-71-gd317 From 61ff72f4016804b99d28988a57e65c217f01769d Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Thu, 28 Nov 2019 08:47:51 +0800 Subject: printk: Drop pr_warning definition With all pr_warning are removed, saftely drop pr_warning definition. Link: http://lkml.kernel.org/r/20191128004752.35268-4-wangkefeng.wang@huawei.com To: joe@perches.com To: linux-kernel@vger.kernel.org Cc: gregkh@linuxfoundation.org Cc: tj@kernel.org Cc: arnd@arndb.de Cc: sergey.senozhatsky@gmail.com Cc: rostedt@goodmis.org Signed-off-by: Kefeng Wang Signed-off-by: Petr Mladek --- include/linux/printk.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index c09d67edda3a..1e6108b8d15f 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -302,9 +302,8 @@ extern int kptr_restrict; printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) #define pr_err(fmt, ...) \ printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) -#define pr_warning(fmt, ...) \ +#define pr_warn(fmt, ...) \ printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) -#define pr_warn pr_warning #define pr_notice(fmt, ...) \ printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) #define pr_info(fmt, ...) \ -- cgit v1.2.3-71-gd317 From 04d26e7b159a396372646a480f4caa166d1b6720 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 6 Dec 2019 12:38:36 +0100 Subject: tcp: fix rejected syncookies due to stale timestamps If no synflood happens for a long enough period of time, then the synflood timestamp isn't refreshed and jiffies can advance so much that time_after32() can't accurately compare them any more. Therefore, we can end up in a situation where time_after32(now, last_overflow + HZ) returns false, just because these two values are too far apart. In that case, the synflood timestamp isn't updated as it should be, which can trick tcp_synq_no_recent_overflow() into rejecting valid syncookies. For example, let's consider the following scenario on a system with HZ=1000: * The synflood timestamp is 0, either because that's the timestamp of the last synflood or, more commonly, because we're working with a freshly created socket. * We receive a new SYN, which triggers synflood protection. Let's say that this happens when jiffies == 2147484649 (that is, 'synflood timestamp' + HZ + 2^31 + 1). * Then tcp_synq_overflow() doesn't update the synflood timestamp, because time_after32(2147484649, 1000) returns false. With: - 2147484649: the value of jiffies, aka. 'now'. - 1000: the value of 'last_overflow' + HZ. * A bit later, we receive the ACK completing the 3WHS. But cookie_v[46]_check() rejects it because tcp_synq_no_recent_overflow() says that we're not under synflood. That's because time_after32(2147484649, 120000) returns false. With: - 2147484649: the value of jiffies, aka. 'now'. - 120000: the value of 'last_overflow' + TCP_SYNCOOKIE_VALID. Of course, in reality jiffies would have increased a bit, but this condition will last for the next 119 seconds, which is far enough to accommodate for jiffie's growth. Fix this by updating the overflow timestamp whenever jiffies isn't within the [last_overflow, last_overflow + HZ] range. That shouldn't have any performance impact since the update still happens at most once per second. Now we're guaranteed to have fresh timestamps while under synflood, so tcp_synq_no_recent_overflow() can safely use it with time_after32() in such situations. Stale timestamps can still make tcp_synq_no_recent_overflow() return the wrong verdict when not under synflood. This will be handled in the next patch. For 64 bits architectures, the problem was introduced with the conversion of ->tw_ts_recent_stamp to 32 bits integer by commit cca9bab1b72c ("tcp: use monotonic timestamps for PAWS"). The problem has always been there on 32 bits architectures. Fixes: cca9bab1b72c ("tcp: use monotonic timestamps for PAWS") Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Guillaume Nault Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/time.h | 13 +++++++++++++ include/net/tcp.h | 5 +++-- 2 files changed, 16 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index 0760a4f5a15c..8e10b9dbd8c2 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -97,4 +97,17 @@ static inline bool itimerspec64_valid(const struct itimerspec64 *its) */ #define time_after32(a, b) ((s32)((u32)(b) - (u32)(a)) < 0) #define time_before32(b, a) time_after32(a, b) + +/** + * time_between32 - check if a 32-bit timestamp is within a given time range + * @t: the time which may be within [l,h] + * @l: the lower bound of the range + * @h: the higher bound of the range + * + * time_before32(t, l, h) returns true if @l <= @t <= @h. All operands are + * treated as 32-bit integers. + * + * Equivalent to !(time_before32(@t, @l) || time_after32(@t, @h)). + */ +#define time_between32(t, l, h) ((u32)(h) - (u32)(l) >= (u32)(t) - (u32)(l)) #endif diff --git a/include/net/tcp.h b/include/net/tcp.h index 36f195fb576a..7d734ba391fc 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -494,14 +494,15 @@ static inline void tcp_synq_overflow(const struct sock *sk) reuse = rcu_dereference(sk->sk_reuseport_cb); if (likely(reuse)) { last_overflow = READ_ONCE(reuse->synq_overflow_ts); - if (time_after32(now, last_overflow + HZ)) + if (!time_between32(now, last_overflow, + last_overflow + HZ)) WRITE_ONCE(reuse->synq_overflow_ts, now); return; } } last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; - if (time_after32(now, last_overflow + HZ)) + if (!time_between32(now, last_overflow, last_overflow + HZ)) tcp_sk(sk)->rx_opt.ts_recent_stamp = now; } -- cgit v1.2.3-71-gd317 From 501a90c945103e8627406763dac418f20f3837b2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 5 Dec 2019 20:43:46 -0800 Subject: inet: protect against too small mtu values. syzbot was once again able to crash a host by setting a very small mtu on loopback device. Let's make inetdev_valid_mtu() available in include/net/ip.h, and use it in ip_setup_cork(), so that we protect both ip_append_page() and __ip_append_data() Also add a READ_ONCE() when the device mtu is read. Pairs this lockless read with one WRITE_ONCE() in __dev_set_mtu(), even if other code paths might write over this field. Add a big comment in include/linux/netdevice.h about dev->mtu needing READ_ONCE()/WRITE_ONCE() annotations. Hopefully we will add the missing ones in followup patches. [1] refcount_t: saturated; leaking memory. WARNING: CPU: 0 PID: 9464 at lib/refcount.c:22 refcount_warn_saturate+0x138/0x1f0 lib/refcount.c:22 Kernel panic - not syncing: panic_on_warn set ... CPU: 0 PID: 9464 Comm: syz-executor850 Not tainted 5.4.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x197/0x210 lib/dump_stack.c:118 panic+0x2e3/0x75c kernel/panic.c:221 __warn.cold+0x2f/0x3e kernel/panic.c:582 report_bug+0x289/0x300 lib/bug.c:195 fixup_bug arch/x86/kernel/traps.c:174 [inline] fixup_bug arch/x86/kernel/traps.c:169 [inline] do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:267 do_invalid_op+0x37/0x50 arch/x86/kernel/traps.c:286 invalid_op+0x23/0x30 arch/x86/entry/entry_64.S:1027 RIP: 0010:refcount_warn_saturate+0x138/0x1f0 lib/refcount.c:22 Code: 06 31 ff 89 de e8 c8 f5 e6 fd 84 db 0f 85 6f ff ff ff e8 7b f4 e6 fd 48 c7 c7 e0 71 4f 88 c6 05 56 a6 a4 06 01 e8 c7 a8 b7 fd <0f> 0b e9 50 ff ff ff e8 5c f4 e6 fd 0f b6 1d 3d a6 a4 06 31 ff 89 RSP: 0018:ffff88809689f550 EFLAGS: 00010286 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffff815e4336 RDI: ffffed1012d13e9c RBP: ffff88809689f560 R08: ffff88809c50a3c0 R09: fffffbfff15d31b1 R10: fffffbfff15d31b0 R11: ffffffff8ae98d87 R12: 0000000000000001 R13: 0000000000040100 R14: ffff888099041104 R15: ffff888218d96e40 refcount_add include/linux/refcount.h:193 [inline] skb_set_owner_w+0x2b6/0x410 net/core/sock.c:1999 sock_wmalloc+0xf1/0x120 net/core/sock.c:2096 ip_append_page+0x7ef/0x1190 net/ipv4/ip_output.c:1383 udp_sendpage+0x1c7/0x480 net/ipv4/udp.c:1276 inet_sendpage+0xdb/0x150 net/ipv4/af_inet.c:821 kernel_sendpage+0x92/0xf0 net/socket.c:3794 sock_sendpage+0x8b/0xc0 net/socket.c:936 pipe_to_sendpage+0x2da/0x3c0 fs/splice.c:458 splice_from_pipe_feed fs/splice.c:512 [inline] __splice_from_pipe+0x3ee/0x7c0 fs/splice.c:636 splice_from_pipe+0x108/0x170 fs/splice.c:671 generic_splice_sendpage+0x3c/0x50 fs/splice.c:842 do_splice_from fs/splice.c:861 [inline] direct_splice_actor+0x123/0x190 fs/splice.c:1035 splice_direct_to_actor+0x3b4/0xa30 fs/splice.c:990 do_splice_direct+0x1da/0x2a0 fs/splice.c:1078 do_sendfile+0x597/0xd00 fs/read_write.c:1464 __do_sys_sendfile64 fs/read_write.c:1525 [inline] __se_sys_sendfile64 fs/read_write.c:1511 [inline] __x64_sys_sendfile64+0x1dd/0x220 fs/read_write.c:1511 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x441409 Code: e8 ac e8 ff ff 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb 08 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007fffb64c4f78 EFLAGS: 00000246 ORIG_RAX: 0000000000000028 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000441409 RDX: 0000000000000000 RSI: 0000000000000006 RDI: 0000000000000005 RBP: 0000000000073b8a R08: 0000000000000010 R09: 0000000000000010 R10: 0000000000010001 R11: 0000000000000246 R12: 0000000000402180 R13: 0000000000402210 R14: 0000000000000000 R15: 0000000000000000 Kernel Offset: disabled Rebooting in 86400 seconds.. Fixes: 1470ddf7f8ce ("inet: Remove explicit write references to sk/inet in ip_append_data") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++++ include/net/ip.h | 5 +++++ net/core/dev.c | 3 ++- net/ipv4/devinet.c | 5 ----- net/ipv4/ip_output.c | 13 ++++++++----- 5 files changed, 20 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cf0923579af4..9ef20389622d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1881,6 +1881,11 @@ struct net_device { unsigned char if_port; unsigned char dma; + /* Note : dev->mtu is often read without holding a lock. + * Writers usually hold RTNL. + * It is recommended to use READ_ONCE() to annotate the reads, + * and to use WRITE_ONCE() to annotate the writes. + */ unsigned int mtu; unsigned int min_mtu; unsigned int max_mtu; diff --git a/include/net/ip.h b/include/net/ip.h index 02d68e346f67..5b317c9f4470 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -760,4 +760,9 @@ int ip_misc_proc_init(void); int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, u8 family, struct netlink_ext_ack *extack); +static inline bool inetdev_valid_mtu(unsigned int mtu) +{ + return likely(mtu >= IPV4_MIN_MTU); +} + #endif /* _IP_H */ diff --git a/net/core/dev.c b/net/core/dev.c index e7c027fb4808..2c277b8aba38 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8188,7 +8188,8 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu) if (ops->ndo_change_mtu) return ops->ndo_change_mtu(dev, new_mtu); - dev->mtu = new_mtu; + /* Pairs with all the lockless reads of dev->mtu in the stack */ + WRITE_ONCE(dev->mtu, new_mtu); return 0; } EXPORT_SYMBOL(__dev_set_mtu); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index a4b5bd4d2c89..e4632bd2026d 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1496,11 +1496,6 @@ skip: } } -static bool inetdev_valid_mtu(unsigned int mtu) -{ - return mtu >= IPV4_MIN_MTU; -} - static void inetdev_send_gratuitous_arp(struct net_device *dev, struct in_device *in_dev) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 9d83cb320dcb..14db1e0b8a6e 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1258,15 +1258,18 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->addr = ipc->addr; } - /* - * We steal reference to this route, caller should not release it - */ - *rtp = NULL; cork->fragsize = ip_sk_use_pmtu(sk) ? - dst_mtu(&rt->dst) : rt->dst.dev->mtu; + dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); + + if (!inetdev_valid_mtu(cork->fragsize)) + return -ENETUNREACH; cork->gso_size = ipc->gso_size; + cork->dst = &rt->dst; + /* We stole this route, caller should not release it. */ + *rtp = NULL; + cork->length = 0; cork->ttl = ipc->ttl; cork->tos = ipc->tos; -- cgit v1.2.3-71-gd317 From a28c8b9db8a1014aa572cd19a3bdb9ddebd3e555 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 7 Dec 2019 13:21:01 -0800 Subject: pipe: remove 'waiting_writers' merging logic This code is ancient, and goes back to when we only had a single page for the pipe buffers. The exact history is hidden in the mists of time (ie "before git", and in fact predates the BK repository too). At that long-ago point in time, it actually helped to try to merge big back-and-forth pipe reads and writes, and not limit pipe reads to the single pipe buffer in length just because that was all we had at a time. However, since then we've expanded the pipe buffers to multiple pages, and this logic really doesn't seem to make sense. And a lot of it is somewhat questionable (ie "hmm, the user asked for a non-blocking read, but we see that there's a writer pending, so let's wait anyway to get the extra data that the writer will have"). But more importantly, it makes the "go to sleep" logic much less obvious, and considering the wakeup issues we've had, I want to make for less of those kinds of things. Cc: David Howells Signed-off-by: Linus Torvalds --- fs/pipe.c | 19 +++++-------------- fs/splice.c | 21 ++++----------------- include/linux/pipe_fs_i.h | 2 -- 3 files changed, 9 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/fs/pipe.c b/fs/pipe.c index bcc2192d33e2..58f236c65bea 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -348,18 +348,11 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) if (!pipe->writers) break; - if (!pipe->waiting_writers) { - /* syscall merging: Usually we must not sleep - * if O_NONBLOCK is set, or if we got some data. - * But if a writer sleeps in kernel space, then - * we can wait for that data without violating POSIX. - */ - if (ret) - break; - if (filp->f_flags & O_NONBLOCK) { - ret = -EAGAIN; - break; - } + if (ret) + break; + if (filp->f_flags & O_NONBLOCK) { + ret = -EAGAIN; + break; } if (signal_pending(current)) { if (!ret) @@ -540,9 +533,7 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) wake_up_interruptible_sync_poll(&pipe->wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); } - pipe->waiting_writers++; pipe_wait(pipe); - pipe->waiting_writers--; was_empty = pipe_empty(head, pipe->tail); } diff --git a/fs/splice.c b/fs/splice.c index fa1f3773c8cd..3009652a41c8 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -559,7 +559,7 @@ static int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_des if (!pipe->writers) return 0; - if (!pipe->waiting_writers && sd->num_spliced) + if (sd->num_spliced) return 0; if (sd->flags & SPLICE_F_NONBLOCK) @@ -1098,9 +1098,7 @@ static int wait_for_space(struct pipe_inode_info *pipe, unsigned flags) return -EAGAIN; if (signal_pending(current)) return -ERESTARTSYS; - pipe->waiting_writers++; pipe_wait(pipe); - pipe->waiting_writers--; } } @@ -1482,11 +1480,9 @@ static int ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags) } if (!pipe->writers) break; - if (!pipe->waiting_writers) { - if (flags & SPLICE_F_NONBLOCK) { - ret = -EAGAIN; - break; - } + if (flags & SPLICE_F_NONBLOCK) { + ret = -EAGAIN; + break; } pipe_wait(pipe); } @@ -1527,9 +1523,7 @@ static int opipe_prep(struct pipe_inode_info *pipe, unsigned int flags) ret = -ERESTARTSYS; break; } - pipe->waiting_writers++; pipe_wait(pipe); - pipe->waiting_writers--; } pipe_unlock(pipe); @@ -1751,13 +1745,6 @@ static int link_pipe(struct pipe_inode_info *ipipe, i_tail++; } while (len); - /* - * return EAGAIN if we have the potential of some data in the - * future, otherwise just return 0 - */ - if (!ret && ipipe->waiting_writers && (flags & SPLICE_F_NONBLOCK)) - ret = -EAGAIN; - pipe_unlock(ipipe); pipe_unlock(opipe); diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 44f2245debda..dbcfa6892384 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -38,7 +38,6 @@ struct pipe_buffer { * @readers: number of current readers of this pipe * @writers: number of current writers of this pipe * @files: number of struct file referring this pipe (protected by ->i_lock) - * @waiting_writers: number of writers blocked waiting for room * @r_counter: reader counter * @w_counter: writer counter * @fasync_readers: reader side fasync @@ -56,7 +55,6 @@ struct pipe_inode_info { unsigned int readers; unsigned int writers; unsigned int files; - unsigned int waiting_writers; unsigned int r_counter; unsigned int w_counter; struct page *tmp_page; -- cgit v1.2.3-71-gd317 From 9fa76ca7b8bdcdf51fc8c7b7b7a7bfc4eccceb58 Mon Sep 17 00:00:00 2001 From: Arvind Sankar Date: Fri, 6 Dec 2019 16:55:41 +0000 Subject: efi: Fix efi_loaded_image_t::unload type The ::unload field is a function pointer, so it should be u32 for 32-bit, u64 for 64-bit. Add a prototype for it in the native efi_loaded_image_t type. Also change type of parent_handle and device_handle from void * to efi_handle_t for documentation purposes. The unload method is not used, so no functional change. Signed-off-by: Arvind Sankar Signed-off-by: Ard Biesheuvel Cc: Andy Shevchenko Cc: Bhupesh Sharma Cc: Linus Torvalds Cc: Masayoshi Mizuma Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: https://lkml.kernel.org/r/20191206165542.31469-6-ardb@kernel.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 99dfea595c8c..aa54586db7a5 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -824,7 +824,7 @@ typedef struct { __aligned_u64 image_size; unsigned int image_code_type; unsigned int image_data_type; - unsigned long unload; + u32 unload; } efi_loaded_image_32_t; typedef struct { @@ -840,14 +840,14 @@ typedef struct { __aligned_u64 image_size; unsigned int image_code_type; unsigned int image_data_type; - unsigned long unload; + u64 unload; } efi_loaded_image_64_t; typedef struct { u32 revision; - void *parent_handle; + efi_handle_t parent_handle; efi_system_table_t *system_table; - void *device_handle; + efi_handle_t device_handle; void *file_path; void *reserved; u32 load_options_size; @@ -856,7 +856,7 @@ typedef struct { __aligned_u64 image_size; unsigned int image_code_type; unsigned int image_data_type; - unsigned long unload; + efi_status_t (*unload)(efi_handle_t image_handle); } efi_loaded_image_t; -- cgit v1.2.3-71-gd317 From 05d7ae15cfb18f9ce55eef85bb6bcd62d31acc57 Mon Sep 17 00:00:00 2001 From: Leonard Crestez Date: Thu, 5 Dec 2019 12:05:06 +0200 Subject: PM / devfreq: Add PM QoS support Register notifiers with the PM QoS framework in order to respond to requests for DEV_PM_QOS_MIN_FREQUENCY and DEV_PM_QOS_MAX_FREQUENCY. No notifiers are added by this patch but PM QoS constraints can be imposed externally (for example from other devices). Signed-off-by: Leonard Crestez Acked-by: Chanwoo Choi Reviewed-by: Matthias Kaehlcke Tested-by: Matthias Kaehlcke Signed-off-by: Chanwoo Choi --- drivers/devfreq/devfreq.c | 77 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/devfreq.h | 5 +++ 2 files changed, 82 insertions(+) (limited to 'include/linux') diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 59f9fa8b54d1..f6e272085448 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -24,11 +24,14 @@ #include #include #include +#include #include "governor.h" #define CREATE_TRACE_POINTS #include +#define HZ_PER_KHZ 1000 + static struct class *devfreq_class; /* @@ -111,6 +114,7 @@ static void get_freq_range(struct devfreq *devfreq, unsigned long *max_freq) { unsigned long *freq_table = devfreq->profile->freq_table; + s32 qos_min_freq, qos_max_freq; lockdep_assert_held(&devfreq->lock); @@ -127,6 +131,16 @@ static void get_freq_range(struct devfreq *devfreq, *max_freq = freq_table[0]; } + /* Apply constraints from PM QoS */ + qos_min_freq = dev_pm_qos_read_value(devfreq->dev.parent, + DEV_PM_QOS_MIN_FREQUENCY); + qos_max_freq = dev_pm_qos_read_value(devfreq->dev.parent, + DEV_PM_QOS_MAX_FREQUENCY); + *min_freq = max(*min_freq, (unsigned long)HZ_PER_KHZ * qos_min_freq); + if (qos_max_freq != PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE) + *max_freq = min(*max_freq, + (unsigned long)HZ_PER_KHZ * qos_max_freq); + /* Apply constraints from sysfs */ *min_freq = max(*min_freq, devfreq->min_freq); *max_freq = min(*max_freq, devfreq->max_freq); @@ -626,6 +640,45 @@ out: return NOTIFY_OK; } +/** + * qos_notifier_call() - Common handler for QoS constraints. + * @devfreq: the devfreq instance. + */ +static int qos_notifier_call(struct devfreq *devfreq) +{ + int err; + + mutex_lock(&devfreq->lock); + err = update_devfreq(devfreq); + mutex_unlock(&devfreq->lock); + if (err) + dev_err(devfreq->dev.parent, + "failed to update frequency from PM QoS (%d)\n", + err); + + return NOTIFY_OK; +} + +/** + * qos_min_notifier_call() - Callback for QoS min_freq changes. + * @nb: Should be devfreq->nb_min + */ +static int qos_min_notifier_call(struct notifier_block *nb, + unsigned long val, void *ptr) +{ + return qos_notifier_call(container_of(nb, struct devfreq, nb_min)); +} + +/** + * qos_max_notifier_call() - Callback for QoS max_freq changes. + * @nb: Should be devfreq->nb_max + */ +static int qos_max_notifier_call(struct notifier_block *nb, + unsigned long val, void *ptr) +{ + return qos_notifier_call(container_of(nb, struct devfreq, nb_max)); +} + /** * devfreq_dev_release() - Callback for struct device to release the device. * @dev: the devfreq device @@ -635,11 +688,23 @@ out: static void devfreq_dev_release(struct device *dev) { struct devfreq *devfreq = to_devfreq(dev); + int err; mutex_lock(&devfreq_list_lock); list_del(&devfreq->node); mutex_unlock(&devfreq_list_lock); + err = dev_pm_qos_remove_notifier(devfreq->dev.parent, &devfreq->nb_max, + DEV_PM_QOS_MAX_FREQUENCY); + if (err && err != -ENOENT) + dev_warn(dev->parent, + "Failed to remove max_freq notifier: %d\n", err); + err = dev_pm_qos_remove_notifier(devfreq->dev.parent, &devfreq->nb_min, + DEV_PM_QOS_MIN_FREQUENCY); + if (err && err != -ENOENT) + dev_warn(dev->parent, + "Failed to remove min_freq notifier: %d\n", err); + if (devfreq->profile->exit) devfreq->profile->exit(devfreq->dev.parent); @@ -762,6 +827,18 @@ struct devfreq *devfreq_add_device(struct device *dev, mutex_unlock(&devfreq->lock); + devfreq->nb_min.notifier_call = qos_min_notifier_call; + err = dev_pm_qos_add_notifier(devfreq->dev.parent, &devfreq->nb_min, + DEV_PM_QOS_MIN_FREQUENCY); + if (err) + goto err_devfreq; + + devfreq->nb_max.notifier_call = qos_max_notifier_call; + err = dev_pm_qos_add_notifier(devfreq->dev.parent, &devfreq->nb_max, + DEV_PM_QOS_MAX_FREQUENCY); + if (err) + goto err_devfreq; + mutex_lock(&devfreq_list_lock); governor = try_then_request_governor(devfreq->governor_name); diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 2bae9ed3c783..8b92ccbd1962 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -136,6 +136,8 @@ struct devfreq_dev_profile { * @time_in_state: Statistics of devfreq states * @last_stat_updated: The last time stat updated * @transition_notifier_list: list head of DEVFREQ_TRANSITION_NOTIFIER notifier + * @nb_min: Notifier block for DEV_PM_QOS_MIN_FREQUENCY + * @nb_max: Notifier block for DEV_PM_QOS_MAX_FREQUENCY * * This structure stores the devfreq information for a give device. * @@ -178,6 +180,9 @@ struct devfreq { unsigned long last_stat_updated; struct srcu_notifier_head transition_notifier_list; + + struct notifier_block nb_min; + struct notifier_block nb_max; }; struct devfreq_freqs { -- cgit v1.2.3-71-gd317 From 27dbc542f651ed09de910f274b32634904103774 Mon Sep 17 00:00:00 2001 From: Leonard Crestez Date: Thu, 5 Dec 2019 12:05:07 +0200 Subject: PM / devfreq: Use PM QoS for sysfs min/max_freq Switch the handling of min_freq and max_freq from sysfs to use the dev_pm_qos_request interface. Since PM QoS handles frequencies as kHz this change reduces the precision of min_freq and max_freq. This shouldn't introduce problems because frequencies which are not an integer number of kHz are likely not an integer number of Hz either. Try to ensure compatibility by rounding min values down and rounding max values up. Signed-off-by: Leonard Crestez Acked-by: Chanwoo Choi Reviewed-by: Matthias Kaehlcke Tested-by: Matthias Kaehlcke [cw00.choi: Return -EAGAIN instead of -EINVAL if dev_pm_qos is inactive] Signed-off-by: Chanwoo Choi --- drivers/devfreq/devfreq.c | 76 ++++++++++++++++++++++++++++++++++++----------- include/linux/devfreq.h | 9 +++--- 2 files changed, 64 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index f6e272085448..57f6944d65a6 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -141,10 +141,6 @@ static void get_freq_range(struct devfreq *devfreq, *max_freq = min(*max_freq, (unsigned long)HZ_PER_KHZ * qos_max_freq); - /* Apply constraints from sysfs */ - *min_freq = max(*min_freq, devfreq->min_freq); - *max_freq = min(*max_freq, devfreq->max_freq); - /* Apply constraints from OPP interface */ *min_freq = max(*min_freq, devfreq->scaling_min_freq); *max_freq = min(*max_freq, devfreq->scaling_max_freq); @@ -705,6 +701,19 @@ static void devfreq_dev_release(struct device *dev) dev_warn(dev->parent, "Failed to remove min_freq notifier: %d\n", err); + if (dev_pm_qos_request_active(&devfreq->user_max_freq_req)) { + err = dev_pm_qos_remove_request(&devfreq->user_max_freq_req); + if (err) + dev_warn(dev->parent, + "Failed to remove max_freq request: %d\n", err); + } + if (dev_pm_qos_request_active(&devfreq->user_min_freq_req)) { + err = dev_pm_qos_remove_request(&devfreq->user_min_freq_req); + if (err) + dev_warn(dev->parent, + "Failed to remove min_freq request: %d\n", err); + } + if (devfreq->profile->exit) devfreq->profile->exit(devfreq->dev.parent); @@ -778,7 +787,6 @@ struct devfreq *devfreq_add_device(struct device *dev, err = -EINVAL; goto err_dev; } - devfreq->min_freq = devfreq->scaling_min_freq; devfreq->scaling_max_freq = find_available_max_freq(devfreq); if (!devfreq->scaling_max_freq) { @@ -786,7 +794,6 @@ struct devfreq *devfreq_add_device(struct device *dev, err = -EINVAL; goto err_dev; } - devfreq->max_freq = devfreq->scaling_max_freq; devfreq->suspend_freq = dev_pm_opp_get_suspend_opp_freq(dev); atomic_set(&devfreq->suspend_count, 0); @@ -827,6 +834,16 @@ struct devfreq *devfreq_add_device(struct device *dev, mutex_unlock(&devfreq->lock); + err = dev_pm_qos_add_request(dev, &devfreq->user_min_freq_req, + DEV_PM_QOS_MIN_FREQUENCY, 0); + if (err < 0) + goto err_devfreq; + err = dev_pm_qos_add_request(dev, &devfreq->user_max_freq_req, + DEV_PM_QOS_MAX_FREQUENCY, + PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE); + if (err < 0) + goto err_devfreq; + devfreq->nb_min.notifier_call = qos_min_notifier_call; err = dev_pm_qos_add_notifier(devfreq->dev.parent, &devfreq->nb_min, DEV_PM_QOS_MIN_FREQUENCY); @@ -1412,14 +1429,22 @@ static ssize_t min_freq_store(struct device *dev, struct device_attribute *attr, unsigned long value; int ret; + /* + * Protect against theoretical sysfs writes between + * device_add and dev_pm_qos_add_request + */ + if (!dev_pm_qos_request_active(&df->user_min_freq_req)) + return -EAGAIN; + ret = sscanf(buf, "%lu", &value); if (ret != 1) return -EINVAL; - mutex_lock(&df->lock); - df->min_freq = value; - update_devfreq(df); - mutex_unlock(&df->lock); + /* Round down to kHz for PM QoS */ + ret = dev_pm_qos_update_request(&df->user_min_freq_req, + value / HZ_PER_KHZ); + if (ret < 0) + return ret; return count; } @@ -1444,18 +1469,35 @@ static ssize_t max_freq_store(struct device *dev, struct device_attribute *attr, unsigned long value; int ret; + /* + * Protect against theoretical sysfs writes between + * device_add and dev_pm_qos_add_request + */ + if (!dev_pm_qos_request_active(&df->user_max_freq_req)) + return -EINVAL; + ret = sscanf(buf, "%lu", &value); if (ret != 1) return -EINVAL; - mutex_lock(&df->lock); - - if (!value) - value = ULONG_MAX; + /* + * PM QoS frequencies are in kHz so we need to convert. Convert by + * rounding upwards so that the acceptable interval never shrinks. + * + * For example if the user writes "666666666" to sysfs this value will + * be converted to 666667 kHz and back to 666667000 Hz before an OPP + * lookup, this ensures that an OPP of 666666666Hz is still accepted. + * + * A value of zero means "no limit". + */ + if (value) + value = DIV_ROUND_UP(value, HZ_PER_KHZ); + else + value = PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE; - df->max_freq = value; - update_devfreq(df); - mutex_unlock(&df->lock); + ret = dev_pm_qos_update_request(&df->user_max_freq_req, value); + if (ret < 0) + return ret; return count; } diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 8b92ccbd1962..fb376b5b7281 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -13,6 +13,7 @@ #include #include #include +#include #define DEVFREQ_NAME_LEN 16 @@ -123,8 +124,8 @@ struct devfreq_dev_profile { * @previous_freq: previously configured frequency value. * @data: Private data of the governor. The devfreq framework does not * touch this. - * @min_freq: Limit minimum frequency requested by user (0: none) - * @max_freq: Limit maximum frequency requested by user (0: none) + * @user_min_freq_req: PM QoS minimum frequency request from user (via sysfs) + * @user_max_freq_req: PM QoS maximum frequency request from user (via sysfs) * @scaling_min_freq: Limit minimum frequency requested by OPP interface * @scaling_max_freq: Limit maximum frequency requested by OPP interface * @stop_polling: devfreq polling status of a device. @@ -163,8 +164,8 @@ struct devfreq { void *data; /* private data for governors */ - unsigned long min_freq; - unsigned long max_freq; + struct dev_pm_qos_request user_min_freq_req; + struct dev_pm_qos_request user_max_freq_req; unsigned long scaling_min_freq; unsigned long scaling_max_freq; bool stop_polling; -- cgit v1.2.3-71-gd317 From c593642c8be046915ca3a4a300243a68077cd207 Mon Sep 17 00:00:00 2001 From: Pankaj Bharadiya Date: Mon, 9 Dec 2019 10:31:43 -0800 Subject: treewide: Use sizeof_field() macro Replace all the occurrences of FIELD_SIZEOF() with sizeof_field() except at places where these are defined. Later patches will remove the unused definition of FIELD_SIZEOF(). This patch is generated using following script: EXCLUDE_FILES="include/linux/stddef.h|include/linux/kernel.h" git grep -l -e "\bFIELD_SIZEOF\b" | while read file; do if [[ "$file" =~ $EXCLUDE_FILES ]]; then continue fi sed -i -e 's/\bFIELD_SIZEOF\b/sizeof_field/g' $file; done Signed-off-by: Pankaj Bharadiya Link: https://lore.kernel.org/r/20190924105839.110713-3-pankaj.laxminarayan.bharadiya@intel.com Co-developed-by: Kees Cook Signed-off-by: Kees Cook Acked-by: David Miller # for net --- Documentation/process/coding-style.rst | 2 +- .../translations/it_IT/process/coding-style.rst | 2 +- .../translations/zh_CN/process/coding-style.rst | 2 +- arch/arc/kernel/unwind.c | 6 +- arch/powerpc/net/bpf_jit32.h | 4 +- arch/powerpc/net/bpf_jit_comp.c | 16 +-- arch/sparc/net/bpf_jit_comp_32.c | 8 +- arch/x86/kernel/fpu/xstate.c | 2 +- block/blk-core.c | 4 +- crypto/adiantum.c | 4 +- crypto/essiv.c | 2 +- drivers/firmware/efi/efi.c | 2 +- drivers/infiniband/hw/efa/efa_verbs.c | 2 +- drivers/infiniband/hw/hfi1/sdma.c | 2 +- drivers/infiniband/hw/hfi1/verbs.h | 4 +- drivers/infiniband/ulp/opa_vnic/opa_vnic_ethtool.c | 2 +- drivers/md/raid5-ppl.c | 2 +- drivers/media/platform/omap3isp/isppreview.c | 24 ++-- drivers/media/v4l2-core/v4l2-ioctl.c | 2 +- drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c | 4 +- .../net/ethernet/cavium/liquidio/octeon_console.c | 16 +-- drivers/net/ethernet/emulex/benet/be_ethtool.c | 2 +- .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 2 +- .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c | 2 +- drivers/net/ethernet/huawei/hinic/hinic_ethtool.c | 8 +- drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c | 2 +- drivers/net/ethernet/intel/iavf/iavf_ethtool.c | 2 +- drivers/net/ethernet/intel/ice/ice_ethtool.c | 10 +- drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h | 2 +- drivers/net/ethernet/intel/igb/igb_ethtool.c | 4 +- drivers/net/ethernet/intel/igc/igc_ethtool.c | 4 +- drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c | 4 +- drivers/net/ethernet/intel/ixgbevf/ethtool.c | 4 +- drivers/net/ethernet/marvell/mv643xx_eth.c | 4 +- drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 2 +- .../net/ethernet/mellanox/mlx5/core/fpga/ipsec.c | 6 +- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 4 +- drivers/net/ethernet/netronome/nfp/bpf/jit.c | 10 +- drivers/net/ethernet/netronome/nfp/bpf/main.c | 2 +- drivers/net/ethernet/netronome/nfp/bpf/offload.c | 2 +- drivers/net/ethernet/netronome/nfp/flower/main.h | 2 +- .../ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c | 2 +- drivers/net/ethernet/qlogic/qede/qede.h | 2 +- .../net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c | 2 +- drivers/net/ethernet/realtek/r8169_firmware.c | 2 +- drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c | 2 +- .../net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 4 +- drivers/net/ethernet/ti/cpsw_ethtool.c | 6 +- drivers/net/ethernet/ti/netcp_ethss.c | 32 ++--- drivers/net/fjes/fjes_ethtool.c | 2 +- drivers/net/geneve.c | 2 +- drivers/net/hyperv/netvsc_drv.c | 2 +- drivers/net/usb/sierra_net.c | 2 +- drivers/net/usb/usbnet.c | 2 +- drivers/net/vxlan.c | 4 +- drivers/net/wireless/marvell/libertas/debugfs.c | 2 +- drivers/net/wireless/marvell/mwifiex/util.h | 4 +- drivers/s390/net/qeth_core_main.c | 2 +- drivers/s390/net/qeth_core_mpc.h | 10 +- drivers/scsi/aacraid/aachba.c | 4 +- drivers/scsi/be2iscsi/be_cmds.h | 2 +- drivers/scsi/cxgbi/libcxgbi.c | 2 +- drivers/scsi/smartpqi/smartpqi_init.c | 6 +- drivers/staging/qlge/qlge_ethtool.c | 2 +- drivers/staging/wfx/data_tx.c | 2 +- drivers/target/iscsi/cxgbit/cxgbit_main.c | 2 +- drivers/usb/atm/usbatm.c | 2 +- drivers/usb/gadget/function/f_fs.c | 2 +- fs/crypto/keyring.c | 2 +- fs/verity/enable.c | 2 +- include/linux/filter.h | 12 +- include/linux/kvm_host.h | 2 +- include/linux/phy_led_triggers.h | 2 +- include/net/garp.h | 2 +- include/net/ip_tunnels.h | 6 +- include/net/mrp.h | 2 +- include/net/netfilter/nf_conntrack_helper.h | 2 +- include/net/netfilter/nf_tables_core.h | 2 +- include/net/sock.h | 2 +- ipc/util.c | 2 +- kernel/bpf/cgroup.c | 2 +- kernel/bpf/local_storage.c | 4 +- net/802/mrp.c | 6 +- net/batman-adv/main.c | 2 +- net/bpf/test_run.c | 8 +- net/bridge/br.c | 2 +- net/core/dev.c | 2 +- net/core/filter.c | 140 ++++++++++----------- net/core/flow_dissector.c | 10 +- net/core/xdp.c | 4 +- net/dccp/proto.c | 2 +- net/ipv4/ip_gre.c | 4 +- net/ipv4/ip_vti.c | 4 +- net/ipv4/tcp.c | 2 +- net/ipv6/ip6_gre.c | 4 +- net/iucv/af_iucv.c | 2 +- net/netfilter/nf_tables_api.c | 4 +- net/netfilter/nfnetlink_cthelper.c | 2 +- net/netfilter/nft_ct.c | 12 +- net/netfilter/nft_masq.c | 2 +- net/netfilter/nft_nat.c | 6 +- net/netfilter/nft_redir.c | 2 +- net/netfilter/nft_tproxy.c | 4 +- net/netfilter/xt_RATEEST.c | 2 +- net/netlink/af_netlink.c | 2 +- net/openvswitch/datapath.c | 2 +- net/openvswitch/flow.h | 4 +- net/rxrpc/af_rxrpc.c | 2 +- net/sched/act_ct.c | 4 +- net/sched/cls_flower.c | 2 +- net/unix/af_unix.c | 2 +- security/integrity/ima/ima_policy.c | 4 +- sound/soc/codecs/hdmi-codec.c | 2 +- 115 files changed, 298 insertions(+), 298 deletions(-) (limited to 'include/linux') diff --git a/Documentation/process/coding-style.rst b/Documentation/process/coding-style.rst index ada573b7d703..edb296c52f61 100644 --- a/Documentation/process/coding-style.rst +++ b/Documentation/process/coding-style.rst @@ -988,7 +988,7 @@ Similarly, if you need to calculate the size of some structure member, use .. code-block:: c - #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) + #define sizeof_field(t, f) (sizeof(((t*)0)->f)) There are also min() and max() macros that do strict type checking if you need them. Feel free to peruse that header file to see what else is already diff --git a/Documentation/translations/it_IT/process/coding-style.rst b/Documentation/translations/it_IT/process/coding-style.rst index 8995d2d19f20..8725f2b9e960 100644 --- a/Documentation/translations/it_IT/process/coding-style.rst +++ b/Documentation/translations/it_IT/process/coding-style.rst @@ -1005,7 +1005,7 @@ struttura, usate .. code-block:: c - #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) + #define sizeof_field(t, f) (sizeof(((t*)0)->f)) Ci sono anche le macro min() e max() che, se vi serve, effettuano un controllo rigido sui tipi. Sentitevi liberi di leggere attentamente questo file diff --git a/Documentation/translations/zh_CN/process/coding-style.rst b/Documentation/translations/zh_CN/process/coding-style.rst index 4f6237392e65..eae10bc7f86f 100644 --- a/Documentation/translations/zh_CN/process/coding-style.rst +++ b/Documentation/translations/zh_CN/process/coding-style.rst @@ -826,7 +826,7 @@ inline gcc 也可以自动使其内联。而且其他用户可能会要求移除 .. code-block:: c - #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) + #define sizeof_field(t, f) (sizeof(((t*)0)->f)) 还有可以做严格的类型检查的 min() 和 max() 宏，如果你需要可以使用它们。你可以 自己看看那个头文件里还定义了什么你可以拿来用的东西，如果有定义的话，你就不应 diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index dc05a63516f5..27ea64b1fa33 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -42,10 +42,10 @@ do { \ #define EXTRA_INFO(f) { \ BUILD_BUG_ON_ZERO(offsetof(struct unwind_frame_info, f) \ - % FIELD_SIZEOF(struct unwind_frame_info, f)) \ + % sizeof_field(struct unwind_frame_info, f)) \ + offsetof(struct unwind_frame_info, f) \ - / FIELD_SIZEOF(struct unwind_frame_info, f), \ - FIELD_SIZEOF(struct unwind_frame_info, f) \ + / sizeof_field(struct unwind_frame_info, f), \ + sizeof_field(struct unwind_frame_info, f) \ } #define PTREGS_INFO(f) EXTRA_INFO(regs.f) diff --git a/arch/powerpc/net/bpf_jit32.h b/arch/powerpc/net/bpf_jit32.h index 6e5a2a4faeab..4ec2a9f14f84 100644 --- a/arch/powerpc/net/bpf_jit32.h +++ b/arch/powerpc/net/bpf_jit32.h @@ -97,12 +97,12 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh); #ifdef CONFIG_SMP #ifdef CONFIG_PPC64 #define PPC_BPF_LOAD_CPU(r) \ - do { BUILD_BUG_ON(FIELD_SIZEOF(struct paca_struct, paca_index) != 2); \ + do { BUILD_BUG_ON(sizeof_field(struct paca_struct, paca_index) != 2); \ PPC_LHZ_OFFS(r, 13, offsetof(struct paca_struct, paca_index)); \ } while (0) #else #define PPC_BPF_LOAD_CPU(r) \ - do { BUILD_BUG_ON(FIELD_SIZEOF(struct task_struct, cpu) != 4); \ + do { BUILD_BUG_ON(sizeof_field(struct task_struct, cpu) != 4); \ PPC_LHZ_OFFS(r, 2, offsetof(struct task_struct, cpu)); \ } while(0) #endif diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index d57b46e0dd60..0acc9d5fb19e 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -321,7 +321,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, ctx->seen |= SEEN_XREG | SEEN_MEM | (1<<(K & 0xf)); break; case BPF_LD | BPF_W | BPF_LEN: /* A = skb->len; */ - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4); + BUILD_BUG_ON(sizeof_field(struct sk_buff, len) != 4); PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, len)); break; case BPF_LDX | BPF_W | BPF_ABS: /* A = *((u32 *)(seccomp_data + K)); */ @@ -333,16 +333,16 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, /*** Ancillary info loads ***/ case BPF_ANC | SKF_AD_PROTOCOL: /* A = ntohs(skb->protocol); */ - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, + BUILD_BUG_ON(sizeof_field(struct sk_buff, protocol) != 2); PPC_NTOHS_OFFS(r_A, r_skb, offsetof(struct sk_buff, protocol)); break; case BPF_ANC | SKF_AD_IFINDEX: case BPF_ANC | SKF_AD_HATYPE: - BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, + BUILD_BUG_ON(sizeof_field(struct net_device, ifindex) != 4); - BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, + BUILD_BUG_ON(sizeof_field(struct net_device, type) != 2); PPC_LL_OFFS(r_scratch1, r_skb, offsetof(struct sk_buff, dev)); @@ -365,17 +365,17 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, break; case BPF_ANC | SKF_AD_MARK: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); + BUILD_BUG_ON(sizeof_field(struct sk_buff, mark) != 4); PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, mark)); break; case BPF_ANC | SKF_AD_RXHASH: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); + BUILD_BUG_ON(sizeof_field(struct sk_buff, hash) != 4); PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, hash)); break; case BPF_ANC | SKF_AD_VLAN_TAG: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); + BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_tci) != 2); PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, vlan_tci)); @@ -388,7 +388,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, PPC_ANDI(r_A, r_A, 1); break; case BPF_ANC | SKF_AD_QUEUE: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, + BUILD_BUG_ON(sizeof_field(struct sk_buff, queue_mapping) != 2); PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, queue_mapping)); diff --git a/arch/sparc/net/bpf_jit_comp_32.c b/arch/sparc/net/bpf_jit_comp_32.c index 84cc8f7f83e9..c8eabb973b86 100644 --- a/arch/sparc/net/bpf_jit_comp_32.c +++ b/arch/sparc/net/bpf_jit_comp_32.c @@ -180,19 +180,19 @@ do { \ #define emit_loadptr(BASE, STRUCT, FIELD, DEST) \ do { unsigned int _off = offsetof(STRUCT, FIELD); \ - BUILD_BUG_ON(FIELD_SIZEOF(STRUCT, FIELD) != sizeof(void *)); \ + BUILD_BUG_ON(sizeof_field(STRUCT, FIELD) != sizeof(void *)); \ *prog++ = LDPTRI | RS1(BASE) | S13(_off) | RD(DEST); \ } while (0) #define emit_load32(BASE, STRUCT, FIELD, DEST) \ do { unsigned int _off = offsetof(STRUCT, FIELD); \ - BUILD_BUG_ON(FIELD_SIZEOF(STRUCT, FIELD) != sizeof(u32)); \ + BUILD_BUG_ON(sizeof_field(STRUCT, FIELD) != sizeof(u32)); \ *prog++ = LD32I | RS1(BASE) | S13(_off) | RD(DEST); \ } while (0) #define emit_load16(BASE, STRUCT, FIELD, DEST) \ do { unsigned int _off = offsetof(STRUCT, FIELD); \ - BUILD_BUG_ON(FIELD_SIZEOF(STRUCT, FIELD) != sizeof(u16)); \ + BUILD_BUG_ON(sizeof_field(STRUCT, FIELD) != sizeof(u16)); \ *prog++ = LD16I | RS1(BASE) | S13(_off) | RD(DEST); \ } while (0) @@ -202,7 +202,7 @@ do { unsigned int _off = offsetof(STRUCT, FIELD); \ } while (0) #define emit_load8(BASE, STRUCT, FIELD, DEST) \ -do { BUILD_BUG_ON(FIELD_SIZEOF(STRUCT, FIELD) != sizeof(u8)); \ +do { BUILD_BUG_ON(sizeof_field(STRUCT, FIELD) != sizeof(u8)); \ __emit_load8(BASE, STRUCT, FIELD, DEST); \ } while (0) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 319be936c348..fa31470bbf24 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -259,7 +259,7 @@ static void __init setup_xstate_features(void) xmm_space); xstate_offsets[XFEATURE_SSE] = xstate_sizes[XFEATURE_FP]; - xstate_sizes[XFEATURE_SSE] = FIELD_SIZEOF(struct fxregs_state, + xstate_sizes[XFEATURE_SSE] = sizeof_field(struct fxregs_state, xmm_space); for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { diff --git a/block/blk-core.c b/block/blk-core.c index a1e228752083..e4b27f7e9f51 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1792,9 +1792,9 @@ int __init blk_dev_init(void) { BUILD_BUG_ON(REQ_OP_LAST >= (1 << REQ_OP_BITS)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * - FIELD_SIZEOF(struct request, cmd_flags)); + sizeof_field(struct request, cmd_flags)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * - FIELD_SIZEOF(struct bio, bi_opf)); + sizeof_field(struct bio, bi_opf)); /* used for unplugging and affects IO latency/throughput - HIGHPRI */ kblockd_workqueue = alloc_workqueue("kblockd", diff --git a/crypto/adiantum.c b/crypto/adiantum.c index aded26092268..9dc53cf9b1f1 100644 --- a/crypto/adiantum.c +++ b/crypto/adiantum.c @@ -436,10 +436,10 @@ static int adiantum_init_tfm(struct crypto_skcipher *tfm) BUILD_BUG_ON(offsetofend(struct adiantum_request_ctx, u) != sizeof(struct adiantum_request_ctx)); - subreq_size = max(FIELD_SIZEOF(struct adiantum_request_ctx, + subreq_size = max(sizeof_field(struct adiantum_request_ctx, u.hash_desc) + crypto_shash_descsize(hash), - FIELD_SIZEOF(struct adiantum_request_ctx, + sizeof_field(struct adiantum_request_ctx, u.streamcipher_req) + crypto_skcipher_reqsize(streamcipher)); diff --git a/crypto/essiv.c b/crypto/essiv.c index 808f2b362106..495a2d1e1460 100644 --- a/crypto/essiv.c +++ b/crypto/essiv.c @@ -347,7 +347,7 @@ static int essiv_aead_init_tfm(struct crypto_aead *tfm) if (IS_ERR(aead)) return PTR_ERR(aead); - subreq_size = FIELD_SIZEOF(struct essiv_aead_request_ctx, aead_req) + + subreq_size = sizeof_field(struct essiv_aead_request_ctx, aead_req) + crypto_aead_reqsize(aead); tctx->ivoffset = offsetof(struct essiv_aead_request_ctx, aead_req) + diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index d101f072c8f8..407816da9fcb 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -681,7 +681,7 @@ device_initcall(efi_load_efivars); { name }, \ { prop }, \ offsetof(struct efi_fdt_params, field), \ - FIELD_SIZEOF(struct efi_fdt_params, field) \ + sizeof_field(struct efi_fdt_params, field) \ } struct params { diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index c9d294caa27a..50c22575aed6 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -145,7 +145,7 @@ static inline bool is_rdma_read_cap(struct efa_dev *dev) } #define field_avail(x, fld, sz) (offsetof(typeof(x), fld) + \ - FIELD_SIZEOF(typeof(x), fld) <= (sz)) + sizeof_field(typeof(x), fld) <= (sz)) #define is_reserved_cleared(reserved) \ !memchr_inv(reserved, 0, sizeof(reserved)) diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index 5774dfc22e18..a51525647ac8 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -848,7 +848,7 @@ static const struct rhashtable_params sdma_rht_params = { .nelem_hint = NR_CPUS_HINT, .head_offset = offsetof(struct sdma_rht_node, node), .key_offset = offsetof(struct sdma_rht_node, cpu_id), - .key_len = FIELD_SIZEOF(struct sdma_rht_node, cpu_id), + .key_len = sizeof_field(struct sdma_rht_node, cpu_id), .max_size = NR_CPUS, .min_size = 8, .automatic_shrinking = true, diff --git a/drivers/infiniband/hw/hfi1/verbs.h b/drivers/infiniband/hw/hfi1/verbs.h index b0e9bf7cd150..d36e3e14896d 100644 --- a/drivers/infiniband/hw/hfi1/verbs.h +++ b/drivers/infiniband/hw/hfi1/verbs.h @@ -107,9 +107,9 @@ enum { HFI1_HAS_GRH = (1 << 0), }; -#define LRH_16B_BYTES (FIELD_SIZEOF(struct hfi1_16b_header, lrh)) +#define LRH_16B_BYTES (sizeof_field(struct hfi1_16b_header, lrh)) #define LRH_16B_DWORDS (LRH_16B_BYTES / sizeof(u32)) -#define LRH_9B_BYTES (FIELD_SIZEOF(struct ib_header, lrh)) +#define LRH_9B_BYTES (sizeof_field(struct ib_header, lrh)) #define LRH_9B_DWORDS (LRH_9B_BYTES / sizeof(u32)) /* 24Bits for qpn, upper 8Bits reserved */ diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_ethtool.c b/drivers/infiniband/ulp/opa_vnic/opa_vnic_ethtool.c index 62390e9e0023..8ad7da989a0e 100644 --- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_ethtool.c +++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_ethtool.c @@ -63,7 +63,7 @@ struct vnic_stats { }; }; -#define VNIC_STAT(m) { FIELD_SIZEOF(struct opa_vnic_stats, m), \ +#define VNIC_STAT(m) { sizeof_field(struct opa_vnic_stats, m), \ offsetof(struct opa_vnic_stats, m) } static struct vnic_stats vnic_gstrings_stats[] = { diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index cab5b1352892..d50238d0a85d 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -1360,7 +1360,7 @@ int ppl_init_log(struct r5conf *conf) return -EINVAL; } - max_disks = FIELD_SIZEOF(struct ppl_log, disk_flush_bitmap) * + max_disks = sizeof_field(struct ppl_log, disk_flush_bitmap) * BITS_PER_BYTE; if (conf->raid_disks > max_disks) { pr_warn("md/raid:%s PPL doesn't support over %d disks in the array\n", diff --git a/drivers/media/platform/omap3isp/isppreview.c b/drivers/media/platform/omap3isp/isppreview.c index 97d660606d98..4dbdf3180d10 100644 --- a/drivers/media/platform/omap3isp/isppreview.c +++ b/drivers/media/platform/omap3isp/isppreview.c @@ -753,7 +753,7 @@ static const struct preview_update update_attrs[] = { preview_config_luma_enhancement, preview_enable_luma_enhancement, offsetof(struct prev_params, luma), - FIELD_SIZEOF(struct prev_params, luma), + sizeof_field(struct prev_params, luma), offsetof(struct omap3isp_prev_update_config, luma), }, /* OMAP3ISP_PREV_INVALAW */ { NULL, @@ -762,55 +762,55 @@ static const struct preview_update update_attrs[] = { preview_config_hmed, preview_enable_hmed, offsetof(struct prev_params, hmed), - FIELD_SIZEOF(struct prev_params, hmed), + sizeof_field(struct prev_params, hmed), offsetof(struct omap3isp_prev_update_config, hmed), }, /* OMAP3ISP_PREV_CFA */ { preview_config_cfa, NULL, offsetof(struct prev_params, cfa), - FIELD_SIZEOF(struct prev_params, cfa), + sizeof_field(struct prev_params, cfa), offsetof(struct omap3isp_prev_update_config, cfa), }, /* OMAP3ISP_PREV_CHROMA_SUPP */ { preview_config_chroma_suppression, preview_enable_chroma_suppression, offsetof(struct prev_params, csup), - FIELD_SIZEOF(struct prev_params, csup), + sizeof_field(struct prev_params, csup), offsetof(struct omap3isp_prev_update_config, csup), }, /* OMAP3ISP_PREV_WB */ { preview_config_whitebalance, NULL, offsetof(struct prev_params, wbal), - FIELD_SIZEOF(struct prev_params, wbal), + sizeof_field(struct prev_params, wbal), offsetof(struct omap3isp_prev_update_config, wbal), }, /* OMAP3ISP_PREV_BLKADJ */ { preview_config_blkadj, NULL, offsetof(struct prev_params, blkadj), - FIELD_SIZEOF(struct prev_params, blkadj), + sizeof_field(struct prev_params, blkadj), offsetof(struct omap3isp_prev_update_config, blkadj), }, /* OMAP3ISP_PREV_RGB2RGB */ { preview_config_rgb_blending, NULL, offsetof(struct prev_params, rgb2rgb), - FIELD_SIZEOF(struct prev_params, rgb2rgb), + sizeof_field(struct prev_params, rgb2rgb), offsetof(struct omap3isp_prev_update_config, rgb2rgb), }, /* OMAP3ISP_PREV_COLOR_CONV */ { preview_config_csc, NULL, offsetof(struct prev_params, csc), - FIELD_SIZEOF(struct prev_params, csc), + sizeof_field(struct prev_params, csc), offsetof(struct omap3isp_prev_update_config, csc), }, /* OMAP3ISP_PREV_YC_LIMIT */ { preview_config_yc_range, NULL, offsetof(struct prev_params, yclimit), - FIELD_SIZEOF(struct prev_params, yclimit), + sizeof_field(struct prev_params, yclimit), offsetof(struct omap3isp_prev_update_config, yclimit), }, /* OMAP3ISP_PREV_DEFECT_COR */ { preview_config_dcor, preview_enable_dcor, offsetof(struct prev_params, dcor), - FIELD_SIZEOF(struct prev_params, dcor), + sizeof_field(struct prev_params, dcor), offsetof(struct omap3isp_prev_update_config, dcor), }, /* Previously OMAP3ISP_PREV_GAMMABYPASS, not used anymore */ { NULL, @@ -828,13 +828,13 @@ static const struct preview_update update_attrs[] = { preview_config_noisefilter, preview_enable_noisefilter, offsetof(struct prev_params, nf), - FIELD_SIZEOF(struct prev_params, nf), + sizeof_field(struct prev_params, nf), offsetof(struct omap3isp_prev_update_config, nf), }, /* OMAP3ISP_PREV_GAMMA */ { preview_config_gammacorrn, preview_enable_gammacorrn, offsetof(struct prev_params, gamma), - FIELD_SIZEOF(struct prev_params, gamma), + sizeof_field(struct prev_params, gamma), offsetof(struct omap3isp_prev_update_config, gamma), }, /* OMAP3ISP_PREV_CONTRAST */ { preview_config_contrast, diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 4e700583659b..003b7422aeef 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -2652,7 +2652,7 @@ struct v4l2_ioctl_info { /* Zero struct from after the field to the end */ #define INFO_FL_CLEAR(v4l2_struct, field) \ ((offsetof(struct v4l2_struct, field) + \ - FIELD_SIZEOF(struct v4l2_struct, field)) << 16) + sizeof_field(struct v4l2_struct, field)) << 16) #define INFO_FL_CLEAR_MASK (_IOC_SIZEMASK << 16) #define DEFINE_V4L_STUB_FUNC(_vidioc) \ diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c index a880f10e3e70..8083173f1a8f 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c @@ -129,13 +129,13 @@ struct xgbe_stats { #define XGMAC_MMC_STAT(_string, _var) \ { _string, \ - FIELD_SIZEOF(struct xgbe_mmc_stats, _var), \ + sizeof_field(struct xgbe_mmc_stats, _var), \ offsetof(struct xgbe_prv_data, mmc_stats._var), \ } #define XGMAC_EXT_STAT(_string, _var) \ { _string, \ - FIELD_SIZEOF(struct xgbe_ext_stats, _var), \ + sizeof_field(struct xgbe_ext_stats, _var), \ offsetof(struct xgbe_prv_data, ext_stats._var), \ } diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_console.c b/drivers/net/ethernet/cavium/liquidio/octeon_console.c index 0cc2338d8d2a..dfc77507b159 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_console.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_console.c @@ -205,11 +205,11 @@ static int __cvmx_bootmem_check_version(struct octeon_device *oct, major_version = (u32)__cvmx_bootmem_desc_get( oct, oct->bootmem_desc_addr, offsetof(struct cvmx_bootmem_desc, major_version), - FIELD_SIZEOF(struct cvmx_bootmem_desc, major_version)); + sizeof_field(struct cvmx_bootmem_desc, major_version)); minor_version = (u32)__cvmx_bootmem_desc_get( oct, oct->bootmem_desc_addr, offsetof(struct cvmx_bootmem_desc, minor_version), - FIELD_SIZEOF(struct cvmx_bootmem_desc, minor_version)); + sizeof_field(struct cvmx_bootmem_desc, minor_version)); dev_dbg(&oct->pci_dev->dev, "%s: major_version=%d\n", __func__, major_version); @@ -237,13 +237,13 @@ static const struct cvmx_bootmem_named_block_desc oct, named_addr, offsetof(struct cvmx_bootmem_named_block_desc, base_addr), - FIELD_SIZEOF( + sizeof_field( struct cvmx_bootmem_named_block_desc, base_addr)); desc->size = __cvmx_bootmem_desc_get(oct, named_addr, offsetof(struct cvmx_bootmem_named_block_desc, size), - FIELD_SIZEOF( + sizeof_field( struct cvmx_bootmem_named_block_desc, size)); @@ -268,20 +268,20 @@ static u64 cvmx_bootmem_phy_named_block_find(struct octeon_device *oct, oct, oct->bootmem_desc_addr, offsetof(struct cvmx_bootmem_desc, named_block_array_addr), - FIELD_SIZEOF(struct cvmx_bootmem_desc, + sizeof_field(struct cvmx_bootmem_desc, named_block_array_addr)); u32 num_blocks = (u32)__cvmx_bootmem_desc_get( oct, oct->bootmem_desc_addr, offsetof(struct cvmx_bootmem_desc, nb_num_blocks), - FIELD_SIZEOF(struct cvmx_bootmem_desc, + sizeof_field(struct cvmx_bootmem_desc, nb_num_blocks)); u32 name_length = (u32)__cvmx_bootmem_desc_get( oct, oct->bootmem_desc_addr, offsetof(struct cvmx_bootmem_desc, named_block_name_len), - FIELD_SIZEOF(struct cvmx_bootmem_desc, + sizeof_field(struct cvmx_bootmem_desc, named_block_name_len)); u64 named_addr = named_block_array_addr; @@ -292,7 +292,7 @@ static u64 cvmx_bootmem_phy_named_block_find(struct octeon_device *oct, offsetof( struct cvmx_bootmem_named_block_desc, size), - FIELD_SIZEOF( + sizeof_field( struct cvmx_bootmem_named_block_desc, size)); diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c index 5bb5abf99588..022a54a1805b 100644 --- a/drivers/net/ethernet/emulex/benet/be_ethtool.c +++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c @@ -23,7 +23,7 @@ struct be_ethtool_stat { }; enum {DRVSTAT_TX, DRVSTAT_RX, DRVSTAT}; -#define FIELDINFO(_struct, field) FIELD_SIZEOF(_struct, field), \ +#define FIELDINFO(_struct, field) sizeof_field(_struct, field), \ offsetof(_struct, field) #define DRVSTAT_TX_INFO(field) #field, DRVSTAT_TX,\ FIELDINFO(struct be_tx_stats, field) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index d862e9ba27e1..13dbd249f35f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -10240,7 +10240,7 @@ static int hclge_get_dfx_reg_len(struct hclge_dev *hdev, int *len) return ret; } - data_len_per_desc = FIELD_SIZEOF(struct hclge_desc, data); + data_len_per_desc = sizeof_field(struct hclge_desc, data); *len = 0; for (i = 0; i < dfx_reg_type_num; i++) { bd_num = bd_num_list[i]; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index fbc39a2480d0..180224eab1ca 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -614,7 +614,7 @@ static void hclge_tm_vport_tc_info_update(struct hclge_vport *vport) } memcpy(kinfo->prio_tc, hdev->tm_info.prio_tc, - FIELD_SIZEOF(struct hnae3_knic_private_info, prio_tc)); + sizeof_field(struct hnae3_knic_private_info, prio_tc)); } static void hclge_tm_vport_info_update(struct hclge_dev *hdev) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c index 60ec48fe4144..966aea949c0b 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c @@ -450,7 +450,7 @@ static u32 hinic_get_rxfh_indir_size(struct net_device *netdev) #define HINIC_FUNC_STAT(_stat_item) { \ .name = #_stat_item, \ - .size = FIELD_SIZEOF(struct hinic_vport_stats, _stat_item), \ + .size = sizeof_field(struct hinic_vport_stats, _stat_item), \ .offset = offsetof(struct hinic_vport_stats, _stat_item) \ } @@ -477,7 +477,7 @@ static struct hinic_stats hinic_function_stats[] = { #define HINIC_PORT_STAT(_stat_item) { \ .name = #_stat_item, \ - .size = FIELD_SIZEOF(struct hinic_phy_port_stats, _stat_item), \ + .size = sizeof_field(struct hinic_phy_port_stats, _stat_item), \ .offset = offsetof(struct hinic_phy_port_stats, _stat_item) \ } @@ -571,7 +571,7 @@ static struct hinic_stats hinic_port_stats[] = { #define HINIC_TXQ_STAT(_stat_item) { \ .name = "txq%d_"#_stat_item, \ - .size = FIELD_SIZEOF(struct hinic_txq_stats, _stat_item), \ + .size = sizeof_field(struct hinic_txq_stats, _stat_item), \ .offset = offsetof(struct hinic_txq_stats, _stat_item) \ } @@ -586,7 +586,7 @@ static struct hinic_stats hinic_tx_queue_stats[] = { #define HINIC_RXQ_STAT(_stat_item) { \ .name = "rxq%d_"#_stat_item, \ - .size = FIELD_SIZEOF(struct hinic_rxq_stats, _stat_item), \ + .size = sizeof_field(struct hinic_rxq_stats, _stat_item), \ .offset = offsetof(struct hinic_rxq_stats, _stat_item) \ } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c index c681d2d28107..68edf55ac906 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c @@ -18,7 +18,7 @@ struct fm10k_stats { #define FM10K_STAT_FIELDS(_type, _name, _stat) { \ .stat_string = _name, \ - .sizeof_stat = FIELD_SIZEOF(_type, _stat), \ + .sizeof_stat = sizeof_field(_type, _stat), \ .stat_offset = offsetof(_type, _stat) \ } diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index d24d8731bef0..317f3f1458db 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -43,7 +43,7 @@ struct i40e_stats { */ #define I40E_STAT(_type, _name, _stat) { \ .stat_string = _name, \ - .sizeof_stat = FIELD_SIZEOF(_type, _stat), \ + .sizeof_stat = sizeof_field(_type, _stat), \ .stat_offset = offsetof(_type, _stat) \ } diff --git a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c index be24d42280d8..a3da422ab05b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c +++ b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c @@ -659,7 +659,7 @@ i40e_status i40e_shutdown_lan_hmc(struct i40e_hw *hw) #define I40E_HMC_STORE(_struct, _ele) \ offsetof(struct _struct, _ele), \ - FIELD_SIZEOF(struct _struct, _ele) + sizeof_field(struct _struct, _ele) struct i40e_context_ele { u16 offset; diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index dad3eec8ccd8..84c3d8d97ef6 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -42,7 +42,7 @@ struct iavf_stats { */ #define IAVF_STAT(_type, _name, _stat) { \ .stat_string = _name, \ - .sizeof_stat = FIELD_SIZEOF(_type, _stat), \ + .sizeof_stat = sizeof_field(_type, _stat), \ .stat_offset = offsetof(_type, _stat) \ } diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index aec3c6c379df..9ebd93e79aeb 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -15,7 +15,7 @@ struct ice_stats { #define ICE_STAT(_type, _name, _stat) { \ .stat_string = _name, \ - .sizeof_stat = FIELD_SIZEOF(_type, _stat), \ + .sizeof_stat = sizeof_field(_type, _stat), \ .stat_offset = offsetof(_type, _stat) \ } @@ -36,10 +36,10 @@ static int ice_q_stats_len(struct net_device *netdev) #define ICE_VSI_STATS_LEN ARRAY_SIZE(ice_gstrings_vsi_stats) #define ICE_PFC_STATS_LEN ( \ - (FIELD_SIZEOF(struct ice_pf, stats.priority_xoff_rx) + \ - FIELD_SIZEOF(struct ice_pf, stats.priority_xon_rx) + \ - FIELD_SIZEOF(struct ice_pf, stats.priority_xoff_tx) + \ - FIELD_SIZEOF(struct ice_pf, stats.priority_xon_tx)) \ + (sizeof_field(struct ice_pf, stats.priority_xoff_rx) + \ + sizeof_field(struct ice_pf, stats.priority_xon_rx) + \ + sizeof_field(struct ice_pf, stats.priority_xoff_tx) + \ + sizeof_field(struct ice_pf, stats.priority_xon_tx)) \ / sizeof(u64)) #define ICE_ALL_STATS_LEN(n) (ICE_PF_STATS_LEN + ICE_PFC_STATS_LEN + \ ICE_VSI_STATS_LEN + ice_q_stats_len(n)) diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h index ad34f22d44ef..0997d352709b 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -302,7 +302,7 @@ struct ice_ctx_ele { #define ICE_CTX_STORE(_struct, _ele, _width, _lsb) { \ .offset = offsetof(struct _struct, _ele), \ - .size_of = FIELD_SIZEOF(struct _struct, _ele), \ + .size_of = sizeof_field(struct _struct, _ele), \ .width = _width, \ .lsb = _lsb, \ } diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 3182b059bf55..4690d6c87f39 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -26,7 +26,7 @@ struct igb_stats { #define IGB_STAT(_name, _stat) { \ .stat_string = _name, \ - .sizeof_stat = FIELD_SIZEOF(struct igb_adapter, _stat), \ + .sizeof_stat = sizeof_field(struct igb_adapter, _stat), \ .stat_offset = offsetof(struct igb_adapter, _stat) \ } static const struct igb_stats igb_gstrings_stats[] = { @@ -76,7 +76,7 @@ static const struct igb_stats igb_gstrings_stats[] = { #define IGB_NETDEV_STAT(_net_stat) { \ .stat_string = __stringify(_net_stat), \ - .sizeof_stat = FIELD_SIZEOF(struct rtnl_link_stats64, _net_stat), \ + .sizeof_stat = sizeof_field(struct rtnl_link_stats64, _net_stat), \ .stat_offset = offsetof(struct rtnl_link_stats64, _net_stat) \ } static const struct igb_stats igb_gstrings_net_stats[] = { diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index ac98f1d96892..455c1cdceb6e 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -16,7 +16,7 @@ struct igc_stats { #define IGC_STAT(_name, _stat) { \ .stat_string = _name, \ - .sizeof_stat = FIELD_SIZEOF(struct igc_adapter, _stat), \ + .sizeof_stat = sizeof_field(struct igc_adapter, _stat), \ .stat_offset = offsetof(struct igc_adapter, _stat) \ } @@ -67,7 +67,7 @@ static const struct igc_stats igc_gstrings_stats[] = { #define IGC_NETDEV_STAT(_net_stat) { \ .stat_string = __stringify(_net_stat), \ - .sizeof_stat = FIELD_SIZEOF(struct rtnl_link_stats64, _net_stat), \ + .sizeof_stat = sizeof_field(struct rtnl_link_stats64, _net_stat), \ .stat_offset = offsetof(struct rtnl_link_stats64, _net_stat) \ } diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c index c8c93ac436d4..c65eb1afc8fb 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c @@ -19,10 +19,10 @@ struct ixgb_stats { }; #define IXGB_STAT(m) IXGB_STATS, \ - FIELD_SIZEOF(struct ixgb_adapter, m), \ + sizeof_field(struct ixgb_adapter, m), \ offsetof(struct ixgb_adapter, m) #define IXGB_NETDEV_STAT(m) NETDEV_STATS, \ - FIELD_SIZEOF(struct net_device, m), \ + sizeof_field(struct net_device, m), \ offsetof(struct net_device, m) static struct ixgb_stats ixgb_gstrings_stats[] = { diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c index 54459b69c948..f7f309c96fa8 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c +++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c @@ -31,14 +31,14 @@ struct ixgbe_stats { #define IXGBEVF_STAT(_name, _stat) { \ .stat_string = _name, \ .type = IXGBEVF_STATS, \ - .sizeof_stat = FIELD_SIZEOF(struct ixgbevf_adapter, _stat), \ + .sizeof_stat = sizeof_field(struct ixgbevf_adapter, _stat), \ .stat_offset = offsetof(struct ixgbevf_adapter, _stat) \ } #define IXGBEVF_NETDEV_STAT(_net_stat) { \ .stat_string = #_net_stat, \ .type = NETDEV_STATS, \ - .sizeof_stat = FIELD_SIZEOF(struct net_device_stats, _net_stat), \ + .sizeof_stat = sizeof_field(struct net_device_stats, _net_stat), \ .stat_offset = offsetof(struct net_device_stats, _net_stat) \ } diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index d5b644131cff..65a093216dac 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -1432,11 +1432,11 @@ struct mv643xx_eth_stats { }; #define SSTAT(m) \ - { #m, FIELD_SIZEOF(struct net_device_stats, m), \ + { #m, sizeof_field(struct net_device_stats, m), \ offsetof(struct net_device, stats.m), -1 } #define MIBSTAT(m) \ - { #m, FIELD_SIZEOF(struct mib_counters, m), \ + { #m, sizeof_field(struct mib_counters, m), \ -1, offsetof(struct mv643xx_eth_private, mib_counters.m) } static const struct mv643xx_eth_stats mv643xx_eth_stats[] = { diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index a1202e53710c..8bf1f08fdee2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -611,7 +611,7 @@ static u32 ptys_get_active_port(struct mlx4_ptys_reg *ptys_reg) } #define MLX4_LINK_MODES_SZ \ - (FIELD_SIZEOF(struct mlx4_ptys_reg, eth_proto_cap) * 8) + (sizeof_field(struct mlx4_ptys_reg, eth_proto_cap) * 8) enum ethtool_report { SUPPORTED = 0, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c index c76da309506b..e4ec0e03c289 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c @@ -87,10 +87,10 @@ static const struct rhashtable_params rhash_sa = { * value is not constant during the lifetime * of the key object. */ - .key_len = FIELD_SIZEOF(struct mlx5_fpga_ipsec_sa_ctx, hw_sa) - - FIELD_SIZEOF(struct mlx5_ifc_fpga_ipsec_sa_v1, cmd), + .key_len = sizeof_field(struct mlx5_fpga_ipsec_sa_ctx, hw_sa) - + sizeof_field(struct mlx5_ifc_fpga_ipsec_sa_v1, cmd), .key_offset = offsetof(struct mlx5_fpga_ipsec_sa_ctx, hw_sa) + - FIELD_SIZEOF(struct mlx5_ifc_fpga_ipsec_sa_v1, cmd), + sizeof_field(struct mlx5_ifc_fpga_ipsec_sa_v1, cmd), .head_offset = offsetof(struct mlx5_fpga_ipsec_sa_ctx, hash), .automatic_shrinking = true, .min_size = 1, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index d60577484567..9a48c4310887 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -209,7 +209,7 @@ enum fs_i_lock_class { }; static const struct rhashtable_params rhash_fte = { - .key_len = FIELD_SIZEOF(struct fs_fte, val), + .key_len = sizeof_field(struct fs_fte, val), .key_offset = offsetof(struct fs_fte, val), .head_offset = offsetof(struct fs_fte, hash), .automatic_shrinking = true, @@ -217,7 +217,7 @@ static const struct rhashtable_params rhash_fte = { }; static const struct rhashtable_params rhash_fg = { - .key_len = FIELD_SIZEOF(struct mlx5_flow_group, mask), + .key_len = sizeof_field(struct mlx5_flow_group, mask), .key_offset = offsetof(struct mlx5_flow_group, mask), .head_offset = offsetof(struct mlx5_flow_group, hash), .automatic_shrinking = true, diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index c80bb83c8ac9..0a721f6e8676 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -2652,17 +2652,17 @@ static int mem_ldx_skb(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, switch (meta->insn.off) { case offsetof(struct __sk_buff, len): - if (size != FIELD_SIZEOF(struct __sk_buff, len)) + if (size != sizeof_field(struct __sk_buff, len)) return -EOPNOTSUPP; wrp_mov(nfp_prog, dst, plen_reg(nfp_prog)); break; case offsetof(struct __sk_buff, data): - if (size != FIELD_SIZEOF(struct __sk_buff, data)) + if (size != sizeof_field(struct __sk_buff, data)) return -EOPNOTSUPP; wrp_mov(nfp_prog, dst, pptr_reg(nfp_prog)); break; case offsetof(struct __sk_buff, data_end): - if (size != FIELD_SIZEOF(struct __sk_buff, data_end)) + if (size != sizeof_field(struct __sk_buff, data_end)) return -EOPNOTSUPP; emit_alu(nfp_prog, dst, plen_reg(nfp_prog), ALU_OP_ADD, pptr_reg(nfp_prog)); @@ -2683,12 +2683,12 @@ static int mem_ldx_xdp(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, switch (meta->insn.off) { case offsetof(struct xdp_md, data): - if (size != FIELD_SIZEOF(struct xdp_md, data)) + if (size != sizeof_field(struct xdp_md, data)) return -EOPNOTSUPP; wrp_mov(nfp_prog, dst, pptr_reg(nfp_prog)); break; case offsetof(struct xdp_md, data_end): - if (size != FIELD_SIZEOF(struct xdp_md, data_end)) + if (size != sizeof_field(struct xdp_md, data_end)) return -EOPNOTSUPP; emit_alu(nfp_prog, dst, plen_reg(nfp_prog), ALU_OP_ADD, pptr_reg(nfp_prog)); diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index 8f732771d3fa..11c83a99b014 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -15,7 +15,7 @@ const struct rhashtable_params nfp_bpf_maps_neutral_params = { .nelem_hint = 4, - .key_len = FIELD_SIZEOF(struct bpf_map, id), + .key_len = sizeof_field(struct bpf_map, id), .key_offset = offsetof(struct nfp_bpf_neutral_map, map_id), .head_offset = offsetof(struct nfp_bpf_neutral_map, l), .automatic_shrinking = true, diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c index 95a0d3910e31..ac02369174a9 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c @@ -374,7 +374,7 @@ nfp_bpf_map_alloc(struct nfp_app_bpf *bpf, struct bpf_offloaded_map *offmap) } use_map_size = DIV_ROUND_UP(offmap->map.value_size, 4) * - FIELD_SIZEOF(struct nfp_bpf_map, use_map[0]); + sizeof_field(struct nfp_bpf_map, use_map[0]); nfp_map = kzalloc(sizeof(*nfp_map) + use_map_size, GFP_USER); if (!nfp_map) diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index 31d94592a7c0..e0c985fcaec1 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -24,7 +24,7 @@ struct nfp_app; #define NFP_FL_STAT_ID_MU_NUM GENMASK(31, 22) #define NFP_FL_STAT_ID_STAT GENMASK(21, 0) -#define NFP_FL_STATS_ELEM_RS FIELD_SIZEOF(struct nfp_fl_stats_id, \ +#define NFP_FL_STATS_ELEM_RS sizeof_field(struct nfp_fl_stats_id, \ init_unalloc) #define NFP_FLOWER_MASK_ENTRY_RS 256 #define NFP_FLOWER_MASK_ELEMENT_RS 1 diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c index 1a3008e33182..b36aa5bf3c5f 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c @@ -20,7 +20,7 @@ struct pch_gbe_stats { #define PCH_GBE_STAT(m) \ { \ .string = #m, \ - .size = FIELD_SIZEOF(struct pch_gbe_hw_stats, m), \ + .size = sizeof_field(struct pch_gbe_hw_stats, m), \ .offset = offsetof(struct pch_gbe_hw_stats, m), \ } diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index c303a92d5b06..e8a1b27db84d 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -464,7 +464,7 @@ struct qede_fastpath { struct qede_tx_queue *txq; struct qede_tx_queue *xdp_tx; -#define VEC_NAME_SIZE (FIELD_SIZEOF(struct net_device, name) + 8) +#define VEC_NAME_SIZE (sizeof_field(struct net_device, name) + 8) char name[VEC_NAME_SIZE]; }; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c index a4cd6f2cfb86..75d83c3cbf27 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c @@ -20,7 +20,7 @@ struct qlcnic_stats { int stat_offset; }; -#define QLC_SIZEOF(m) FIELD_SIZEOF(struct qlcnic_adapter, m) +#define QLC_SIZEOF(m) sizeof_field(struct qlcnic_adapter, m) #define QLC_OFF(m) offsetof(struct qlcnic_adapter, m) static const u32 qlcnic_fw_dump_level[] = { 0x3, 0x7, 0xf, 0x1f, 0x3f, 0x7f, 0xff diff --git a/drivers/net/ethernet/realtek/r8169_firmware.c b/drivers/net/ethernet/realtek/r8169_firmware.c index 355cc810e322..cbc6b846ded5 100644 --- a/drivers/net/ethernet/realtek/r8169_firmware.c +++ b/drivers/net/ethernet/realtek/r8169_firmware.c @@ -37,7 +37,7 @@ struct fw_info { u8 chksum; } __packed; -#define FW_OPCODE_SIZE FIELD_SIZEOF(struct rtl_fw_phy_action, code[0]) +#define FW_OPCODE_SIZE sizeof_field(struct rtl_fw_phy_action, code[0]) static bool rtl_fw_format_ok(struct rtl_fw *rtl_fw) { diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c index 0775b9464b4e..466483c4ac67 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c @@ -30,7 +30,7 @@ struct sxgbe_stats { #define SXGBE_STAT(m) \ { \ #m, \ - FIELD_SIZEOF(struct sxgbe_extra_stats, m), \ + sizeof_field(struct sxgbe_extra_stats, m), \ offsetof(struct sxgbe_priv_data, xstats.m) \ } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 1a768837ca72..b29603ec744c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -34,7 +34,7 @@ struct stmmac_stats { }; #define STMMAC_STAT(m) \ - { #m, FIELD_SIZEOF(struct stmmac_extra_stats, m), \ + { #m, sizeof_field(struct stmmac_extra_stats, m), \ offsetof(struct stmmac_priv, xstats.m)} static const struct stmmac_stats stmmac_gstrings_stats[] = { @@ -163,7 +163,7 @@ static const struct stmmac_stats stmmac_gstrings_stats[] = { /* HW MAC Management counters (if supported) */ #define STMMAC_MMC_STAT(m) \ - { #m, FIELD_SIZEOF(struct stmmac_counters, m), \ + { #m, sizeof_field(struct stmmac_counters, m), \ offsetof(struct stmmac_priv, mmc.m)} static const struct stmmac_stats stmmac_mmc[] = { diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c index 31248a6cc642..fa54efe3be63 100644 --- a/drivers/net/ethernet/ti/cpsw_ethtool.c +++ b/drivers/net/ethernet/ti/cpsw_ethtool.c @@ -73,13 +73,13 @@ enum { }; #define CPSW_STAT(m) CPSW_STATS, \ - FIELD_SIZEOF(struct cpsw_hw_stats, m), \ + sizeof_field(struct cpsw_hw_stats, m), \ offsetof(struct cpsw_hw_stats, m) #define CPDMA_RX_STAT(m) CPDMA_RX_STATS, \ - FIELD_SIZEOF(struct cpdma_chan_stats, m), \ + sizeof_field(struct cpdma_chan_stats, m), \ offsetof(struct cpdma_chan_stats, m) #define CPDMA_TX_STAT(m) CPDMA_TX_STATS, \ - FIELD_SIZEOF(struct cpdma_chan_stats, m), \ + sizeof_field(struct cpdma_chan_stats, m), \ offsetof(struct cpdma_chan_stats, m) static const struct cpsw_stats cpsw_gstrings_stats[] = { diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index 86a3f42a3dcc..d6a192c1f337 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -783,28 +783,28 @@ struct netcp_ethtool_stat { #define GBE_STATSA_INFO(field) \ { \ "GBE_A:"#field, GBE_STATSA_MODULE, \ - FIELD_SIZEOF(struct gbe_hw_stats, field), \ + sizeof_field(struct gbe_hw_stats, field), \ offsetof(struct gbe_hw_stats, field) \ } #define GBE_STATSB_INFO(field) \ { \ "GBE_B:"#field, GBE_STATSB_MODULE, \ - FIELD_SIZEOF(struct gbe_hw_stats, field), \ + sizeof_field(struct gbe_hw_stats, field), \ offsetof(struct gbe_hw_stats, field) \ } #define GBE_STATSC_INFO(field) \ { \ "GBE_C:"#field, GBE_STATSC_MODULE, \ - FIELD_SIZEOF(struct gbe_hw_stats, field), \ + sizeof_field(struct gbe_hw_stats, field), \ offsetof(struct gbe_hw_stats, field) \ } #define GBE_STATSD_INFO(field) \ { \ "GBE_D:"#field, GBE_STATSD_MODULE, \ - FIELD_SIZEOF(struct gbe_hw_stats, field), \ + sizeof_field(struct gbe_hw_stats, field), \ offsetof(struct gbe_hw_stats, field) \ } @@ -957,7 +957,7 @@ static const struct netcp_ethtool_stat gbe13_et_stats[] = { #define GBENU_STATS_HOST(field) \ { \ "GBE_HOST:"#field, GBENU_STATS0_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } @@ -967,56 +967,56 @@ static const struct netcp_ethtool_stat gbe13_et_stats[] = { #define GBENU_STATS_P1(field) \ { \ "GBE_P1:"#field, GBENU_STATS1_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } #define GBENU_STATS_P2(field) \ { \ "GBE_P2:"#field, GBENU_STATS2_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } #define GBENU_STATS_P3(field) \ { \ "GBE_P3:"#field, GBENU_STATS3_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } #define GBENU_STATS_P4(field) \ { \ "GBE_P4:"#field, GBENU_STATS4_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } #define GBENU_STATS_P5(field) \ { \ "GBE_P5:"#field, GBENU_STATS5_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } #define GBENU_STATS_P6(field) \ { \ "GBE_P6:"#field, GBENU_STATS6_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } #define GBENU_STATS_P7(field) \ { \ "GBE_P7:"#field, GBENU_STATS7_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } #define GBENU_STATS_P8(field) \ { \ "GBE_P8:"#field, GBENU_STATS8_MODULE, \ - FIELD_SIZEOF(struct gbenu_hw_stats, field), \ + sizeof_field(struct gbenu_hw_stats, field), \ offsetof(struct gbenu_hw_stats, field) \ } @@ -1607,21 +1607,21 @@ static const struct netcp_ethtool_stat gbenu_et_stats[] = { #define XGBE_STATS0_INFO(field) \ { \ "GBE_0:"#field, XGBE_STATS0_MODULE, \ - FIELD_SIZEOF(struct xgbe_hw_stats, field), \ + sizeof_field(struct xgbe_hw_stats, field), \ offsetof(struct xgbe_hw_stats, field) \ } #define XGBE_STATS1_INFO(field) \ { \ "GBE_1:"#field, XGBE_STATS1_MODULE, \ - FIELD_SIZEOF(struct xgbe_hw_stats, field), \ + sizeof_field(struct xgbe_hw_stats, field), \ offsetof(struct xgbe_hw_stats, field) \ } #define XGBE_STATS2_INFO(field) \ { \ "GBE_2:"#field, XGBE_STATS2_MODULE, \ - FIELD_SIZEOF(struct xgbe_hw_stats, field), \ + sizeof_field(struct xgbe_hw_stats, field), \ offsetof(struct xgbe_hw_stats, field) \ } diff --git a/drivers/net/fjes/fjes_ethtool.c b/drivers/net/fjes/fjes_ethtool.c index 09f3604cfbf8..746736c83873 100644 --- a/drivers/net/fjes/fjes_ethtool.c +++ b/drivers/net/fjes/fjes_ethtool.c @@ -21,7 +21,7 @@ struct fjes_stats { #define FJES_STAT(name, stat) { \ .stat_string = name, \ - .sizeof_stat = FIELD_SIZEOF(struct fjes_adapter, stat), \ + .sizeof_stat = sizeof_field(struct fjes_adapter, stat), \ .stat_offset = offsetof(struct fjes_adapter, stat) \ } diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 5c6b7fc04ea6..75757e9954ba 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1156,7 +1156,7 @@ static void geneve_setup(struct net_device *dev) static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = { [IFLA_GENEVE_ID] = { .type = NLA_U32 }, - [IFLA_GENEVE_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, + [IFLA_GENEVE_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_GENEVE_REMOTE6] = { .len = sizeof(struct in6_addr) }, [IFLA_GENEVE_TTL] = { .type = NLA_U8 }, [IFLA_GENEVE_TOS] = { .type = NLA_U8 }, diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index eff8fef4f775..02e66473f2ed 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -571,7 +571,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net) /* Use the skb control buffer for building up the packet */ BUILD_BUG_ON(sizeof(struct hv_netvsc_packet) > - FIELD_SIZEOF(struct sk_buff, cb)); + sizeof_field(struct sk_buff, cb)); packet = (struct hv_netvsc_packet *)skb->cb; packet->q_idx = skb_get_queue_mapping(skb); diff --git a/drivers/net/usb/sierra_net.c b/drivers/net/usb/sierra_net.c index 34c1eaba536c..389d19dd7909 100644 --- a/drivers/net/usb/sierra_net.c +++ b/drivers/net/usb/sierra_net.c @@ -865,7 +865,7 @@ static struct sk_buff *sierra_net_tx_fixup(struct usbnet *dev, u16 len; bool need_tail; - BUILD_BUG_ON(FIELD_SIZEOF(struct usbnet, data) + BUILD_BUG_ON(sizeof_field(struct usbnet, data) < sizeof(struct cdc_state)); dev_dbg(&dev->udev->dev, "%s", __func__); diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 30e511c2c8d0..9ce6d30576dd 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -2184,7 +2184,7 @@ static int __init usbnet_init(void) { /* Compiler should optimize this out. */ BUILD_BUG_ON( - FIELD_SIZEOF(struct sk_buff, cb) < sizeof(struct skb_data)); + sizeof_field(struct sk_buff, cb) < sizeof(struct skb_data)); eth_random_addr(node_id); return 0; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 4c34375c2e22..3ec6b506033d 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -3069,10 +3069,10 @@ static void vxlan_raw_setup(struct net_device *dev) static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [IFLA_VXLAN_ID] = { .type = NLA_U32 }, - [IFLA_VXLAN_GROUP] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, + [IFLA_VXLAN_GROUP] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_VXLAN_GROUP6] = { .len = sizeof(struct in6_addr) }, [IFLA_VXLAN_LINK] = { .type = NLA_U32 }, - [IFLA_VXLAN_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) }, + [IFLA_VXLAN_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, [IFLA_VXLAN_LOCAL6] = { .len = sizeof(struct in6_addr) }, [IFLA_VXLAN_TOS] = { .type = NLA_U8 }, [IFLA_VXLAN_TTL] = { .type = NLA_U8 }, diff --git a/drivers/net/wireless/marvell/libertas/debugfs.c b/drivers/net/wireless/marvell/libertas/debugfs.c index fe14814af300..c604613ab506 100644 --- a/drivers/net/wireless/marvell/libertas/debugfs.c +++ b/drivers/net/wireless/marvell/libertas/debugfs.c @@ -774,7 +774,7 @@ void lbs_debugfs_remove_one(struct lbs_private *priv) #ifdef PROC_DEBUG -#define item_size(n) (FIELD_SIZEOF(struct lbs_private, n)) +#define item_size(n) (sizeof_field(struct lbs_private, n)) #define item_addr(n) (offsetof(struct lbs_private, n)) diff --git a/drivers/net/wireless/marvell/mwifiex/util.h b/drivers/net/wireless/marvell/mwifiex/util.h index c386992abcdb..7cafcecd7b85 100644 --- a/drivers/net/wireless/marvell/mwifiex/util.h +++ b/drivers/net/wireless/marvell/mwifiex/util.h @@ -36,11 +36,11 @@ struct mwifiex_cb { }; /* size/addr for mwifiex_debug_info */ -#define item_size(n) (FIELD_SIZEOF(struct mwifiex_debug_info, n)) +#define item_size(n) (sizeof_field(struct mwifiex_debug_info, n)) #define item_addr(n) (offsetof(struct mwifiex_debug_info, n)) /* size/addr for struct mwifiex_adapter */ -#define adapter_item_size(n) (FIELD_SIZEOF(struct mwifiex_adapter, n)) +#define adapter_item_size(n) (sizeof_field(struct mwifiex_adapter, n)) #define adapter_item_addr(n) (offsetof(struct mwifiex_adapter, n)) struct mwifiex_debug_data { diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index b9a2349e4b90..33a62a6692c0 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -4779,7 +4779,7 @@ static int qeth_qdio_establish(struct qeth_card *card) QETH_CARD_TEXT(card, 2, "qdioest"); - qib_param_field = kzalloc(FIELD_SIZEOF(struct qib, parm), GFP_KERNEL); + qib_param_field = kzalloc(sizeof_field(struct qib, parm), GFP_KERNEL); if (!qib_param_field) { rc = -ENOMEM; goto out_free_nothing; diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h index 88f4dc140751..c1ecce95094d 100644 --- a/drivers/s390/net/qeth_core_mpc.h +++ b/drivers/s390/net/qeth_core_mpc.h @@ -421,7 +421,7 @@ struct qeth_ipacmd_setassparms { } data; } __attribute__ ((packed)); -#define SETASS_DATA_SIZEOF(field) FIELD_SIZEOF(struct qeth_ipacmd_setassparms,\ +#define SETASS_DATA_SIZEOF(field) sizeof_field(struct qeth_ipacmd_setassparms,\ data.field) /* SETRTG IPA Command: ****************************************************/ @@ -535,7 +535,7 @@ struct qeth_ipacmd_setadpparms { } data; } __attribute__ ((packed)); -#define SETADP_DATA_SIZEOF(field) FIELD_SIZEOF(struct qeth_ipacmd_setadpparms,\ +#define SETADP_DATA_SIZEOF(field) sizeof_field(struct qeth_ipacmd_setadpparms,\ data.field) /* CREATE_ADDR IPA Command: ***********************************************/ @@ -648,7 +648,7 @@ struct qeth_ipacmd_vnicc { } data; }; -#define VNICC_DATA_SIZEOF(field) FIELD_SIZEOF(struct qeth_ipacmd_vnicc,\ +#define VNICC_DATA_SIZEOF(field) sizeof_field(struct qeth_ipacmd_vnicc,\ data.field) /* SETBRIDGEPORT IPA Command: *********************************************/ @@ -729,7 +729,7 @@ struct qeth_ipacmd_setbridgeport { } data; } __packed; -#define SBP_DATA_SIZEOF(field) FIELD_SIZEOF(struct qeth_ipacmd_setbridgeport,\ +#define SBP_DATA_SIZEOF(field) sizeof_field(struct qeth_ipacmd_setbridgeport,\ data.field) /* ADDRESS_CHANGE_NOTIFICATION adapter-initiated "command" *******************/ @@ -790,7 +790,7 @@ struct qeth_ipa_cmd { } data; } __attribute__ ((packed)); -#define IPA_DATA_SIZEOF(field) FIELD_SIZEOF(struct qeth_ipa_cmd, data.field) +#define IPA_DATA_SIZEOF(field) sizeof_field(struct qeth_ipa_cmd, data.field) /* * special command for ARP processing. diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c index e36608ce937a..33dbc051bff9 100644 --- a/drivers/scsi/aacraid/aachba.c +++ b/drivers/scsi/aacraid/aachba.c @@ -535,7 +535,7 @@ static void get_container_name_callback(void *context, struct fib * fibptr) if ((le32_to_cpu(get_name_reply->status) == CT_OK) && (get_name_reply->data[0] != '\0')) { char *sp = get_name_reply->data; - int data_size = FIELD_SIZEOF(struct aac_get_name_resp, data); + int data_size = sizeof_field(struct aac_get_name_resp, data); sp[data_size - 1] = '\0'; while (*sp == ' ') @@ -574,7 +574,7 @@ static int aac_get_container_name(struct scsi_cmnd * scsicmd) dev = (struct aac_dev *)scsicmd->device->host->hostdata; - data_size = FIELD_SIZEOF(struct aac_get_name_resp, data); + data_size = sizeof_field(struct aac_get_name_resp, data); cmd_fibcontext = aac_fib_alloc_tag(dev, scsicmd); diff --git a/drivers/scsi/be2iscsi/be_cmds.h b/drivers/scsi/be2iscsi/be_cmds.h index 063dccc18f70..5f9f0b18ddf3 100644 --- a/drivers/scsi/be2iscsi/be_cmds.h +++ b/drivers/scsi/be2iscsi/be_cmds.h @@ -1300,7 +1300,7 @@ struct be_cmd_get_port_name { /* Returns the number of items in the field array. */ #define BE_NUMBER_OF_FIELD(_type_, _field_) \ - (FIELD_SIZEOF(_type_, _field_)/sizeof((((_type_ *)0)->_field_[0])))\ + (sizeof_field(_type_, _field_)/sizeof((((_type_ *)0)->_field_[0])))\ /** * Different types of iSCSI completions to host driver for both initiator diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c index 0d044c165960..c4e4b0136f86 100644 --- a/drivers/scsi/cxgbi/libcxgbi.c +++ b/drivers/scsi/cxgbi/libcxgbi.c @@ -2746,7 +2746,7 @@ static int __init libcxgbi_init_module(void) { pr_info("%s", version); - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, cb) < + BUILD_BUG_ON(sizeof_field(struct sk_buff, cb) < sizeof(struct cxgbi_skb_cb)); return 0; } diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c index 7b7ef3acb504..412ac56ecd60 100644 --- a/drivers/scsi/smartpqi/smartpqi_init.c +++ b/drivers/scsi/smartpqi/smartpqi_init.c @@ -8689,11 +8689,11 @@ static void __attribute__((unused)) verify_structures(void) BUILD_BUG_ON(offsetof(struct pqi_general_admin_request, data.delete_operational_queue.queue_id) != 12); BUILD_BUG_ON(sizeof(struct pqi_general_admin_request) != 64); - BUILD_BUG_ON(FIELD_SIZEOF(struct pqi_general_admin_request, + BUILD_BUG_ON(sizeof_field(struct pqi_general_admin_request, data.create_operational_iq) != 64 - 11); - BUILD_BUG_ON(FIELD_SIZEOF(struct pqi_general_admin_request, + BUILD_BUG_ON(sizeof_field(struct pqi_general_admin_request, data.create_operational_oq) != 64 - 11); - BUILD_BUG_ON(FIELD_SIZEOF(struct pqi_general_admin_request, + BUILD_BUG_ON(sizeof_field(struct pqi_general_admin_request, data.delete_operational_queue) != 64 - 11); BUILD_BUG_ON(offsetof(struct pqi_general_admin_response, diff --git a/drivers/staging/qlge/qlge_ethtool.c b/drivers/staging/qlge/qlge_ethtool.c index a6886cc5654c..56d116d79e56 100644 --- a/drivers/staging/qlge/qlge_ethtool.c +++ b/drivers/staging/qlge/qlge_ethtool.c @@ -41,7 +41,7 @@ struct ql_stats { int stat_offset; }; -#define QL_SIZEOF(m) FIELD_SIZEOF(struct ql_adapter, m) +#define QL_SIZEOF(m) sizeof_field(struct ql_adapter, m) #define QL_OFF(m) offsetof(struct ql_adapter, m) static const struct ql_stats ql_gstrings_stats[] = { diff --git a/drivers/staging/wfx/data_tx.c b/drivers/staging/wfx/data_tx.c index b722e9773232..df2640a79f02 100644 --- a/drivers/staging/wfx/data_tx.c +++ b/drivers/staging/wfx/data_tx.c @@ -679,7 +679,7 @@ void wfx_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control, struct ieee80211_sta *sta = control ? control->sta : NULL; struct ieee80211_tx_info *tx_info = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; - size_t driver_data_room = FIELD_SIZEOF(struct ieee80211_tx_info, + size_t driver_data_room = sizeof_field(struct ieee80211_tx_info, rate_driver_data); compiletime_assert(sizeof(struct wfx_tx_priv) <= driver_data_room, diff --git a/drivers/target/iscsi/cxgbit/cxgbit_main.c b/drivers/target/iscsi/cxgbit/cxgbit_main.c index e877b917c15f..30ea37e1a3f5 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_main.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_main.c @@ -708,7 +708,7 @@ static int __init cxgbit_init(void) pr_info("%s dcb enabled.\n", DRV_NAME); register_dcbevent_notifier(&cxgbit_dcbevent_nb); #endif - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, cb) < + BUILD_BUG_ON(sizeof_field(struct sk_buff, cb) < sizeof(union cxgbit_skb_cb)); return 0; } diff --git a/drivers/usb/atm/usbatm.c b/drivers/usb/atm/usbatm.c index dbea28495e1d..4e12a32ca392 100644 --- a/drivers/usb/atm/usbatm.c +++ b/drivers/usb/atm/usbatm.c @@ -1275,7 +1275,7 @@ EXPORT_SYMBOL_GPL(usbatm_usb_disconnect); static int __init usbatm_usb_init(void) { - if (sizeof(struct usbatm_control) > FIELD_SIZEOF(struct sk_buff, cb)) { + if (sizeof(struct usbatm_control) > sizeof_field(struct sk_buff, cb)) { printk(KERN_ERR "%s unusable with this kernel!\n", usbatm_driver_name); return -EIO; } diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index ce1d0235969c..0bbccac94d6c 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -3509,7 +3509,7 @@ static void ffs_free_inst(struct usb_function_instance *f) static int ffs_set_inst_name(struct usb_function_instance *fi, const char *name) { - if (strlen(name) >= FIELD_SIZEOF(struct ffs_dev, name)) + if (strlen(name) >= sizeof_field(struct ffs_dev, name)) return -ENAMETOOLONG; return ffs_name_dev(to_f_fs_opts(fi)->dev, name); } diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c index 040df1f5e1c8..40cca351273f 100644 --- a/fs/crypto/keyring.c +++ b/fs/crypto/keyring.c @@ -151,7 +151,7 @@ static struct key *search_fscrypt_keyring(struct key *keyring, } #define FSCRYPT_FS_KEYRING_DESCRIPTION_SIZE \ - (CONST_STRLEN("fscrypt-") + FIELD_SIZEOF(struct super_block, s_id)) + (CONST_STRLEN("fscrypt-") + sizeof_field(struct super_block, s_id)) #define FSCRYPT_MK_DESCRIPTION_SIZE (2 * FSCRYPT_KEY_IDENTIFIER_SIZE + 1) diff --git a/fs/verity/enable.c b/fs/verity/enable.c index eabc6ac19906..b79e3fd19d11 100644 --- a/fs/verity/enable.c +++ b/fs/verity/enable.c @@ -315,7 +315,7 @@ int fsverity_ioctl_enable(struct file *filp, const void __user *uarg) if (arg.block_size != PAGE_SIZE) return -EINVAL; - if (arg.salt_size > FIELD_SIZEOF(struct fsverity_descriptor, salt)) + if (arg.salt_size > sizeof_field(struct fsverity_descriptor, salt)) return -EMSGSIZE; if (arg.sig_size > FS_VERITY_MAX_SIGNATURE_SIZE) diff --git a/include/linux/filter.h b/include/linux/filter.h index a141cb07e76a..345f3748e0fb 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -420,7 +420,7 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) #define BPF_FIELD_SIZEOF(type, field) \ ({ \ - const int __size = bytes_to_bpf_size(FIELD_SIZEOF(type, field)); \ + const int __size = bytes_to_bpf_size(sizeof_field(type, field)); \ BUILD_BUG_ON(__size < 0); \ __size; \ }) @@ -497,7 +497,7 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) #define bpf_target_off(TYPE, MEMBER, SIZE, PTR_SIZE) \ ({ \ - BUILD_BUG_ON(FIELD_SIZEOF(TYPE, MEMBER) != (SIZE)); \ + BUILD_BUG_ON(sizeof_field(TYPE, MEMBER) != (SIZE)); \ *(PTR_SIZE) = (SIZE); \ offsetof(TYPE, MEMBER); \ }) @@ -608,7 +608,7 @@ static inline void bpf_compute_data_pointers(struct sk_buff *skb) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; - BUILD_BUG_ON(sizeof(*cb) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(*cb) > sizeof_field(struct sk_buff, cb)); cb->data_meta = skb->data - skb_metadata_len(skb); cb->data_end = skb->data + skb_headlen(skb); } @@ -646,9 +646,9 @@ static inline u8 *bpf_skb_cb(struct sk_buff *skb) * attached to sockets, we need to clear the bpf_skb_cb() area * to not leak previous contents to user space. */ - BUILD_BUG_ON(FIELD_SIZEOF(struct __sk_buff, cb) != BPF_SKB_CB_LEN); - BUILD_BUG_ON(FIELD_SIZEOF(struct __sk_buff, cb) != - FIELD_SIZEOF(struct qdisc_skb_cb, data)); + BUILD_BUG_ON(sizeof_field(struct __sk_buff, cb) != BPF_SKB_CB_LEN); + BUILD_BUG_ON(sizeof_field(struct __sk_buff, cb) != + sizeof_field(struct qdisc_skb_cb, data)); return qdisc_skb_cb(skb)->data; } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7ed1e2f8641e..538c25e778c0 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -149,7 +149,7 @@ static inline bool is_error_page(struct page *page) #define KVM_REQUEST_ARCH_BASE 8 #define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \ - BUILD_BUG_ON((unsigned)(nr) >= (FIELD_SIZEOF(struct kvm_vcpu, requests) * 8) - KVM_REQUEST_ARCH_BASE); \ + BUILD_BUG_ON((unsigned)(nr) >= (sizeof_field(struct kvm_vcpu, requests) * 8) - KVM_REQUEST_ARCH_BASE); \ (unsigned)(((nr) + KVM_REQUEST_ARCH_BASE) | (flags)); \ }) #define KVM_ARCH_REQ(nr) KVM_ARCH_REQ_FLAGS(nr, 0) diff --git a/include/linux/phy_led_triggers.h b/include/linux/phy_led_triggers.h index 3d507a8a6989..5c4d7a755101 100644 --- a/include/linux/phy_led_triggers.h +++ b/include/linux/phy_led_triggers.h @@ -14,7 +14,7 @@ struct phy_device; #define PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE 11 #define PHY_LINK_LED_TRIGGER_NAME_SIZE (MII_BUS_ID_SIZE + \ - FIELD_SIZEOF(struct mdio_device, addr)+\ + sizeof_field(struct mdio_device, addr)+\ PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE) struct phy_led_trigger { diff --git a/include/net/garp.h b/include/net/garp.h index c41833bd4590..4d9a0c6a2e5f 100644 --- a/include/net/garp.h +++ b/include/net/garp.h @@ -37,7 +37,7 @@ struct garp_skb_cb { static inline struct garp_skb_cb *garp_cb(struct sk_buff *skb) { BUILD_BUG_ON(sizeof(struct garp_skb_cb) > - FIELD_SIZEOF(struct sk_buff, cb)); + sizeof_field(struct sk_buff, cb)); return (struct garp_skb_cb *)skb->cb; } diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index af645604f328..236503a50759 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -33,8 +33,8 @@ /* Used to memset ipv4 address padding. */ #define IP_TUNNEL_KEY_IPV4_PAD offsetofend(struct ip_tunnel_key, u.ipv4.dst) #define IP_TUNNEL_KEY_IPV4_PAD_LEN \ - (FIELD_SIZEOF(struct ip_tunnel_key, u) - \ - FIELD_SIZEOF(struct ip_tunnel_key, u.ipv4)) + (sizeof_field(struct ip_tunnel_key, u) - \ + sizeof_field(struct ip_tunnel_key, u.ipv4)) struct ip_tunnel_key { __be64 tun_id; @@ -63,7 +63,7 @@ struct ip_tunnel_key { /* Maximum tunnel options length. */ #define IP_TUNNEL_OPTS_MAX \ - GENMASK((FIELD_SIZEOF(struct ip_tunnel_info, \ + GENMASK((sizeof_field(struct ip_tunnel_info, \ options_len) * BITS_PER_BYTE) - 1, 0) struct ip_tunnel_info { diff --git a/include/net/mrp.h b/include/net/mrp.h index ef58b4a07190..1c308c034e1a 100644 --- a/include/net/mrp.h +++ b/include/net/mrp.h @@ -39,7 +39,7 @@ struct mrp_skb_cb { static inline struct mrp_skb_cb *mrp_cb(struct sk_buff *skb) { BUILD_BUG_ON(sizeof(struct mrp_skb_cb) > - FIELD_SIZEOF(struct sk_buff, cb)); + sizeof_field(struct sk_buff, cb)); return (struct mrp_skb_cb *)skb->cb; } diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index 44b5a00a9c64..37f0fbefb060 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -81,7 +81,7 @@ struct nf_conn_help { }; #define NF_CT_HELPER_BUILD_BUG_ON(structsize) \ - BUILD_BUG_ON((structsize) > FIELD_SIZEOF(struct nf_conn_help, data)) + BUILD_BUG_ON((structsize) > sizeof_field(struct nf_conn_help, data)) struct nf_conntrack_helper *__nf_conntrack_helper_find(const char *name, u16 l3num, u8 protonum); diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index 7281895fa6d9..2656155b4069 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -41,7 +41,7 @@ struct nft_immediate_expr { */ static inline u32 nft_cmp_fast_mask(unsigned int len) { - return cpu_to_le32(~0U >> (FIELD_SIZEOF(struct nft_cmp_fast_expr, + return cpu_to_le32(~0U >> (sizeof_field(struct nft_cmp_fast_expr, data) * BITS_PER_BYTE - len)); } diff --git a/include/net/sock.h b/include/net/sock.h index 87d54ef57f00..80f996406bba 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2305,7 +2305,7 @@ struct sock_skb_cb { * using skb->cb[] would keep using it directly and utilize its * alignement guarantee. */ -#define SOCK_SKB_CB_OFFSET ((FIELD_SIZEOF(struct sk_buff, cb) - \ +#define SOCK_SKB_CB_OFFSET ((sizeof_field(struct sk_buff, cb) - \ sizeof(struct sock_skb_cb))) #define SOCK_SKB_CB(__skb) ((struct sock_skb_cb *)((__skb)->cb + \ diff --git a/ipc/util.c b/ipc/util.c index d126d156efc6..915eacb9c059 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -100,7 +100,7 @@ device_initcall(ipc_init); static const struct rhashtable_params ipc_kht_params = { .head_offset = offsetof(struct kern_ipc_perm, khtnode), .key_offset = offsetof(struct kern_ipc_perm, key), - .key_len = FIELD_SIZEOF(struct kern_ipc_perm, key), + .key_len = sizeof_field(struct kern_ipc_perm, key), .automatic_shrinking = true, }; diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 9f90d3c92bda..4fb20ab179fe 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1341,7 +1341,7 @@ static u32 sysctl_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sysctl_kern, write, - FIELD_SIZEOF(struct bpf_sysctl_kern, + sizeof_field(struct bpf_sysctl_kern, write), target_size)); break; diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 2ba750725cb2..6bd22f6d9f41 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -357,7 +357,7 @@ static int cgroup_storage_check_btf(const struct bpf_map *map, * The first field must be a 64 bit integer at 0 offset. */ m = (struct btf_member *)(key_type + 1); - size = FIELD_SIZEOF(struct bpf_cgroup_storage_key, cgroup_inode_id); + size = sizeof_field(struct bpf_cgroup_storage_key, cgroup_inode_id); if (!btf_member_is_reg_int(btf, key_type, m, 0, size)) return -EINVAL; @@ -366,7 +366,7 @@ static int cgroup_storage_check_btf(const struct bpf_map *map, */ m++; offset = offsetof(struct bpf_cgroup_storage_key, attach_type); - size = FIELD_SIZEOF(struct bpf_cgroup_storage_key, attach_type); + size = sizeof_field(struct bpf_cgroup_storage_key, attach_type); if (!btf_member_is_reg_int(btf, key_type, m, offset, size)) return -EINVAL; diff --git a/net/802/mrp.c b/net/802/mrp.c index 2cfdfbfbb2ed..bea6e43d45a0 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -523,7 +523,7 @@ int mrp_request_join(const struct net_device *dev, struct mrp_attr *attr; if (sizeof(struct mrp_skb_cb) + len > - FIELD_SIZEOF(struct sk_buff, cb)) + sizeof_field(struct sk_buff, cb)) return -ENOMEM; spin_lock_bh(&app->lock); @@ -548,7 +548,7 @@ void mrp_request_leave(const struct net_device *dev, struct mrp_attr *attr; if (sizeof(struct mrp_skb_cb) + len > - FIELD_SIZEOF(struct sk_buff, cb)) + sizeof_field(struct sk_buff, cb)) return; spin_lock_bh(&app->lock); @@ -692,7 +692,7 @@ static int mrp_pdu_parse_vecattr(struct mrp_applicant *app, * advance to the next event in its Vector. */ if (sizeof(struct mrp_skb_cb) + mrp_cb(skb)->mh->attrlen > - FIELD_SIZEOF(struct sk_buff, cb)) + sizeof_field(struct sk_buff, cb)) return -1; if (skb_copy_bits(skb, *offset, mrp_cb(skb)->attrvalue, mrp_cb(skb)->mh->attrlen) < 0) diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 4a89177def64..4811ec65bc43 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -548,7 +548,7 @@ static void batadv_recv_handler_init(void) BUILD_BUG_ON(sizeof(struct batadv_tvlv_tt_change) != 12); BUILD_BUG_ON(sizeof(struct batadv_tvlv_roam_adv) != 8); - i = FIELD_SIZEOF(struct sk_buff, cb); + i = sizeof_field(struct sk_buff, cb); BUILD_BUG_ON(sizeof(struct batadv_skb_cb) > i); /* broadcast packet */ diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 915c2d6f7fb9..f79205d4444f 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -253,21 +253,21 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb) /* priority is allowed */ if (!range_is_zero(__skb, offsetof(struct __sk_buff, priority) + - FIELD_SIZEOF(struct __sk_buff, priority), + sizeof_field(struct __sk_buff, priority), offsetof(struct __sk_buff, cb))) return -EINVAL; /* cb is allowed */ if (!range_is_zero(__skb, offsetof(struct __sk_buff, cb) + - FIELD_SIZEOF(struct __sk_buff, cb), + sizeof_field(struct __sk_buff, cb), offsetof(struct __sk_buff, tstamp))) return -EINVAL; /* tstamp is allowed */ if (!range_is_zero(__skb, offsetof(struct __sk_buff, tstamp) + - FIELD_SIZEOF(struct __sk_buff, tstamp), + sizeof_field(struct __sk_buff, tstamp), sizeof(struct __sk_buff))) return -EINVAL; @@ -438,7 +438,7 @@ static int verify_user_bpf_flow_keys(struct bpf_flow_keys *ctx) /* flags is allowed */ if (!range_is_zero(ctx, offsetof(struct bpf_flow_keys, flags) + - FIELD_SIZEOF(struct bpf_flow_keys, flags), + sizeof_field(struct bpf_flow_keys, flags), sizeof(struct bpf_flow_keys))) return -EINVAL; diff --git a/net/bridge/br.c b/net/bridge/br.c index 8a8f9e5f264f..b6fe30e3768f 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -312,7 +312,7 @@ static int __init br_init(void) { int err; - BUILD_BUG_ON(sizeof(struct br_input_skb_cb) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct br_input_skb_cb) > sizeof_field(struct sk_buff, cb)); err = stp_proto_register(&br_stp_proto); if (err < 0) { diff --git a/net/core/dev.c b/net/core/dev.c index 2c277b8aba38..0ad39c87b7fd 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10165,7 +10165,7 @@ static struct hlist_head * __net_init netdev_create_hash(void) static int __net_init netdev_init(struct net *net) { BUILD_BUG_ON(GRO_HASH_BUCKETS > - 8 * FIELD_SIZEOF(struct napi_struct, gro_bitmask)); + 8 * sizeof_field(struct napi_struct, gro_bitmask)); if (net != &init_net) INIT_LIST_HEAD(&net->dev_base_head); diff --git a/net/core/filter.c b/net/core/filter.c index f1e703eed3d2..c19dd0973e0c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -274,7 +274,7 @@ static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg, switch (skb_field) { case SKF_AD_MARK: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); + BUILD_BUG_ON(sizeof_field(struct sk_buff, mark) != 4); *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, offsetof(struct sk_buff, mark)); @@ -289,14 +289,14 @@ static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg, break; case SKF_AD_QUEUE: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2); + BUILD_BUG_ON(sizeof_field(struct sk_buff, queue_mapping) != 2); *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, offsetof(struct sk_buff, queue_mapping)); break; case SKF_AD_VLAN_TAG: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); + BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_tci) != 2); /* dst_reg = *(u16 *) (src_reg + offsetof(vlan_tci)) */ *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, @@ -322,7 +322,7 @@ static bool convert_bpf_extensions(struct sock_filter *fp, switch (fp->k) { case SKF_AD_OFF + SKF_AD_PROTOCOL: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2); + BUILD_BUG_ON(sizeof_field(struct sk_buff, protocol) != 2); /* A = *(u16 *) (CTX + offsetof(protocol)) */ *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, @@ -338,8 +338,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp, case SKF_AD_OFF + SKF_AD_IFINDEX: case SKF_AD_OFF + SKF_AD_HATYPE: - BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); - BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2); + BUILD_BUG_ON(sizeof_field(struct net_device, ifindex) != 4); + BUILD_BUG_ON(sizeof_field(struct net_device, type) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), BPF_REG_TMP, BPF_REG_CTX, @@ -361,7 +361,7 @@ static bool convert_bpf_extensions(struct sock_filter *fp, break; case SKF_AD_OFF + SKF_AD_RXHASH: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); + BUILD_BUG_ON(sizeof_field(struct sk_buff, hash) != 4); *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, offsetof(struct sk_buff, hash)); @@ -385,7 +385,7 @@ static bool convert_bpf_extensions(struct sock_filter *fp, break; case SKF_AD_OFF + SKF_AD_VLAN_TPID: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_proto) != 2); + BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_proto) != 2); /* A = *(u16 *) (CTX + offsetof(vlan_proto)) */ *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, @@ -5589,8 +5589,8 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, #define BPF_TCP_SOCK_GET_COMMON(FIELD) \ do { \ - BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, FIELD) > \ - FIELD_SIZEOF(struct bpf_tcp_sock, FIELD)); \ + BUILD_BUG_ON(sizeof_field(struct tcp_sock, FIELD) > \ + sizeof_field(struct bpf_tcp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct tcp_sock, FIELD),\ si->dst_reg, si->src_reg, \ offsetof(struct tcp_sock, FIELD)); \ @@ -5598,9 +5598,9 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, #define BPF_INET_SOCK_GET_COMMON(FIELD) \ do { \ - BUILD_BUG_ON(FIELD_SIZEOF(struct inet_connection_sock, \ + BUILD_BUG_ON(sizeof_field(struct inet_connection_sock, \ FIELD) > \ - FIELD_SIZEOF(struct bpf_tcp_sock, FIELD)); \ + sizeof_field(struct bpf_tcp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct inet_connection_sock, \ FIELD), \ @@ -5615,7 +5615,7 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, switch (si->off) { case offsetof(struct bpf_tcp_sock, rtt_min): - BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, rtt_min) != + BUILD_BUG_ON(sizeof_field(struct tcp_sock, rtt_min) != sizeof(struct minmax)); BUILD_BUG_ON(sizeof(struct minmax) < sizeof(struct minmax_sample)); @@ -5780,8 +5780,8 @@ u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, #define BPF_XDP_SOCK_GET(FIELD) \ do { \ - BUILD_BUG_ON(FIELD_SIZEOF(struct xdp_sock, FIELD) > \ - FIELD_SIZEOF(struct bpf_xdp_sock, FIELD)); \ + BUILD_BUG_ON(sizeof_field(struct xdp_sock, FIELD) > \ + sizeof_field(struct bpf_xdp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_sock, FIELD),\ si->dst_reg, si->src_reg, \ offsetof(struct xdp_sock, FIELD)); \ @@ -7344,7 +7344,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, case offsetof(struct __sk_buff, cb[0]) ... offsetofend(struct __sk_buff, cb[4]) - 1: - BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, data) < 20); + BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, data) < 20); BUILD_BUG_ON((offsetof(struct sk_buff, cb) + offsetof(struct qdisc_skb_cb, data)) % sizeof(__u64)); @@ -7363,7 +7363,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct __sk_buff, tc_classid): - BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, tc_classid) != 2); + BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, tc_classid) != 2); off = si->off; off -= offsetof(struct __sk_buff, tc_classid); @@ -7434,7 +7434,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, #endif break; case offsetof(struct __sk_buff, family): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_family) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, @@ -7445,7 +7445,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, 2, target_size)); break; case offsetof(struct __sk_buff, remote_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_daddr) != 4); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, @@ -7456,7 +7456,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, 4, target_size)); break; case offsetof(struct __sk_buff, local_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), @@ -7470,7 +7470,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, case offsetof(struct __sk_buff, remote_ip6[0]) ... offsetof(struct __sk_buff, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; @@ -7490,7 +7490,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, case offsetof(struct __sk_buff, local_ip6[0]) ... offsetof(struct __sk_buff, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; @@ -7509,7 +7509,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct __sk_buff, remote_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_dport) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, @@ -7524,7 +7524,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct __sk_buff, local_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_num) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, @@ -7535,7 +7535,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct __sk_buff, tstamp): - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, tstamp) != 8); + BUILD_BUG_ON(sizeof_field(struct sk_buff, tstamp) != 8); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_DW, @@ -7573,7 +7573,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, target_size)); break; case offsetof(struct __sk_buff, wire_len): - BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, pkt_len) != 4); + BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, pkt_len) != 4); off = si->off; off -= offsetof(struct __sk_buff, wire_len); @@ -7603,7 +7603,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, switch (si->off) { case offsetof(struct bpf_sock, bound_dev_if): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_bound_dev_if) != 4); + BUILD_BUG_ON(sizeof_field(struct sock, sk_bound_dev_if) != 4); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, @@ -7614,7 +7614,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock, mark): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_mark) != 4); + BUILD_BUG_ON(sizeof_field(struct sock, sk_mark) != 4); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, @@ -7625,7 +7625,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock, priority): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_priority) != 4); + BUILD_BUG_ON(sizeof_field(struct sock, sk_priority) != 4); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, @@ -7641,7 +7641,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_family, - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_family), target_size)); break; @@ -7668,7 +7668,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_rcv_saddr, - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_rcv_saddr), target_size)); break; @@ -7677,7 +7677,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_daddr, - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_daddr), target_size)); break; @@ -7691,7 +7691,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, bpf_target_off( struct sock_common, skc_v6_rcv_saddr.s6_addr32[0], - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]), target_size) + off); #else @@ -7708,7 +7708,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_v6_daddr.s6_addr32[0], - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]), target_size) + off); #else @@ -7722,7 +7722,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, BPF_FIELD_SIZEOF(struct sock_common, skc_num), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_num, - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_num), target_size)); break; @@ -7732,7 +7732,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, BPF_FIELD_SIZEOF(struct sock_common, skc_dport), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_dport, - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_dport), target_size)); break; @@ -7742,7 +7742,7 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, BPF_FIELD_SIZEOF(struct sock_common, skc_state), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_state, - FIELD_SIZEOF(struct sock_common, + sizeof_field(struct sock_common, skc_state), target_size)); break; @@ -7837,7 +7837,7 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type, si->src_reg, offsetof(S, F)); \ *insn++ = BPF_LDX_MEM( \ SIZE, si->dst_reg, si->dst_reg, \ - bpf_target_off(NS, NF, FIELD_SIZEOF(NS, NF), \ + bpf_target_off(NS, NF, sizeof_field(NS, NF), \ target_size) \ + OFF); \ } while (0) @@ -7868,7 +7868,7 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(S, F), tmp_reg, \ si->dst_reg, offsetof(S, F)); \ *insn++ = BPF_STX_MEM(SIZE, tmp_reg, si->src_reg, \ - bpf_target_off(NS, NF, FIELD_SIZEOF(NS, NF), \ + bpf_target_off(NS, NF, sizeof_field(NS, NF), \ target_size) \ + OFF); \ *insn++ = BPF_LDX_MEM(BPF_DW, tmp_reg, si->dst_reg, \ @@ -7930,8 +7930,8 @@ static u32 sock_addr_convert_ctx_access(enum bpf_access_type type, */ BUILD_BUG_ON(offsetof(struct sockaddr_in, sin_port) != offsetof(struct sockaddr_in6, sin6_port)); - BUILD_BUG_ON(FIELD_SIZEOF(struct sockaddr_in, sin_port) != - FIELD_SIZEOF(struct sockaddr_in6, sin6_port)); + BUILD_BUG_ON(sizeof_field(struct sockaddr_in, sin_port) != + sizeof_field(struct sockaddr_in6, sin6_port)); SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD(struct bpf_sock_addr_kern, struct sockaddr_in6, uaddr, sin6_port, tmp_reg); @@ -7997,8 +7997,8 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, /* Helper macro for adding read access to tcp_sock or sock fields. */ #define SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ do { \ - BUILD_BUG_ON(FIELD_SIZEOF(OBJ, OBJ_FIELD) > \ - FIELD_SIZEOF(struct bpf_sock_ops, BPF_FIELD)); \ + BUILD_BUG_ON(sizeof_field(OBJ, OBJ_FIELD) > \ + sizeof_field(struct bpf_sock_ops, BPF_FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ is_fullsock), \ @@ -8031,8 +8031,8 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, #define SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ do { \ int reg = BPF_REG_9; \ - BUILD_BUG_ON(FIELD_SIZEOF(OBJ, OBJ_FIELD) > \ - FIELD_SIZEOF(struct bpf_sock_ops, BPF_FIELD)); \ + BUILD_BUG_ON(sizeof_field(OBJ, OBJ_FIELD) > \ + sizeof_field(struct bpf_sock_ops, BPF_FIELD)); \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == reg || si->src_reg == reg) \ @@ -8073,12 +8073,12 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, switch (si->off) { case offsetof(struct bpf_sock_ops, op) ... offsetof(struct bpf_sock_ops, replylong[3]): - BUILD_BUG_ON(FIELD_SIZEOF(struct bpf_sock_ops, op) != - FIELD_SIZEOF(struct bpf_sock_ops_kern, op)); - BUILD_BUG_ON(FIELD_SIZEOF(struct bpf_sock_ops, reply) != - FIELD_SIZEOF(struct bpf_sock_ops_kern, reply)); - BUILD_BUG_ON(FIELD_SIZEOF(struct bpf_sock_ops, replylong) != - FIELD_SIZEOF(struct bpf_sock_ops_kern, replylong)); + BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, op) != + sizeof_field(struct bpf_sock_ops_kern, op)); + BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, reply) != + sizeof_field(struct bpf_sock_ops_kern, reply)); + BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, replylong) != + sizeof_field(struct bpf_sock_ops_kern, replylong)); off = si->off; off -= offsetof(struct bpf_sock_ops, op); off += offsetof(struct bpf_sock_ops_kern, op); @@ -8091,7 +8091,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, family): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_family) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@ -8102,7 +8102,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, remote_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_daddr) != 4); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@ -8113,7 +8113,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, local_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( @@ -8128,7 +8128,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, case offsetof(struct bpf_sock_ops, remote_ip6[0]) ... offsetof(struct bpf_sock_ops, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; @@ -8149,7 +8149,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, case offsetof(struct bpf_sock_ops, local_ip6[0]) ... offsetof(struct bpf_sock_ops, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; @@ -8168,7 +8168,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, remote_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_dport) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@ -8182,7 +8182,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, local_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_num) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@ -8202,7 +8202,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, state): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_state) != 1); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_state) != 1); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@ -8213,7 +8213,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, rtt_min): - BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, rtt_min) != + BUILD_BUG_ON(sizeof_field(struct tcp_sock, rtt_min) != sizeof(struct minmax)); BUILD_BUG_ON(sizeof(struct minmax) < sizeof(struct minmax_sample)); @@ -8224,7 +8224,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct tcp_sock, rtt_min) + - FIELD_SIZEOF(struct minmax_sample, t)); + sizeof_field(struct minmax_sample, t)); break; case offsetof(struct bpf_sock_ops, bpf_sock_ops_cb_flags): @@ -8366,7 +8366,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, offsetof(struct sk_msg, data_end)); break; case offsetof(struct sk_msg_md, family): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_family) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), @@ -8377,7 +8377,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct sk_msg_md, remote_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_daddr) != 4); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), @@ -8388,7 +8388,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct sk_msg_md, local_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( @@ -8403,7 +8403,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, case offsetof(struct sk_msg_md, remote_ip6[0]) ... offsetof(struct sk_msg_md, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; @@ -8424,7 +8424,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, case offsetof(struct sk_msg_md, local_ip6[0]) ... offsetof(struct sk_msg_md, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; @@ -8443,7 +8443,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct sk_msg_md, remote_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_dport) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), @@ -8457,7 +8457,7 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct sk_msg_md, local_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_num) != 2); + BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), @@ -8847,7 +8847,7 @@ sk_reuseport_is_valid_access(int off, int size, /* Fields that allow narrowing */ case bpf_ctx_range(struct sk_reuseport_md, eth_protocol): - if (size < FIELD_SIZEOF(struct sk_buff, protocol)) + if (size < sizeof_field(struct sk_buff, protocol)) return false; /* fall through */ case bpf_ctx_range(struct sk_reuseport_md, ip_protocol): @@ -8865,7 +8865,7 @@ sk_reuseport_is_valid_access(int off, int size, *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_reuseport_kern, F), \ si->dst_reg, si->src_reg, \ bpf_target_off(struct sk_reuseport_kern, F, \ - FIELD_SIZEOF(struct sk_reuseport_kern, F), \ + sizeof_field(struct sk_reuseport_kern, F), \ target_size)); \ }) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index d524a693e00f..2dbbb030fbed 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -599,8 +599,8 @@ __skb_flow_dissect_gre(const struct sk_buff *skb, offset += sizeof(struct gre_base_hdr); if (hdr->flags & GRE_CSUM) - offset += FIELD_SIZEOF(struct gre_full_hdr, csum) + - FIELD_SIZEOF(struct gre_full_hdr, reserved1); + offset += sizeof_field(struct gre_full_hdr, csum) + + sizeof_field(struct gre_full_hdr, reserved1); if (hdr->flags & GRE_KEY) { const __be32 *keyid; @@ -622,11 +622,11 @@ __skb_flow_dissect_gre(const struct sk_buff *skb, else key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK; } - offset += FIELD_SIZEOF(struct gre_full_hdr, key); + offset += sizeof_field(struct gre_full_hdr, key); } if (hdr->flags & GRE_SEQ) - offset += FIELD_SIZEOF(struct pptp_gre_header, seq); + offset += sizeof_field(struct pptp_gre_header, seq); if (gre_ver == 0) { if (*p_proto == htons(ETH_P_TEB)) { @@ -653,7 +653,7 @@ __skb_flow_dissect_gre(const struct sk_buff *skb, u8 *ppp_hdr; if (hdr->flags & GRE_ACK) - offset += FIELD_SIZEOF(struct pptp_gre_header, ack); + offset += sizeof_field(struct pptp_gre_header, ack); ppp_hdr = __skb_header_pointer(skb, *p_nhoff + offset, sizeof(_ppp_hdr), diff --git a/net/core/xdp.c b/net/core/xdp.c index 7c8390ad4dc6..8310714c47fd 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -36,7 +36,7 @@ static u32 xdp_mem_id_hashfn(const void *data, u32 len, u32 seed) const u32 *k = data; const u32 key = *k; - BUILD_BUG_ON(FIELD_SIZEOF(struct xdp_mem_allocator, mem.id) + BUILD_BUG_ON(sizeof_field(struct xdp_mem_allocator, mem.id) != sizeof(u32)); /* Use cyclic increasing ID as direct hash key */ @@ -56,7 +56,7 @@ static const struct rhashtable_params mem_id_rht_params = { .nelem_hint = 64, .head_offset = offsetof(struct xdp_mem_allocator, node), .key_offset = offsetof(struct xdp_mem_allocator, mem.id), - .key_len = FIELD_SIZEOF(struct xdp_mem_allocator, mem.id), + .key_len = sizeof_field(struct xdp_mem_allocator, mem.id), .max_size = MEM_ID_MAX, .min_size = 8, .automatic_shrinking = true, diff --git a/net/dccp/proto.c b/net/dccp/proto.c index a52e8ba1ced0..4af8a98fe784 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -1132,7 +1132,7 @@ static int __init dccp_init(void) int rc; BUILD_BUG_ON(sizeof(struct dccp_skb_cb) > - FIELD_SIZEOF(struct sk_buff, cb)); + sizeof_field(struct sk_buff, cb)); rc = percpu_counter_init(&dccp_orphan_count, 0, GFP_KERNEL); if (rc) goto out_fail; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 572b6307a2df..8274f98c511c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1464,8 +1464,8 @@ static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = { [IFLA_GRE_OFLAGS] = { .type = NLA_U16 }, [IFLA_GRE_IKEY] = { .type = NLA_U32 }, [IFLA_GRE_OKEY] = { .type = NLA_U32 }, - [IFLA_GRE_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) }, - [IFLA_GRE_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, + [IFLA_GRE_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, + [IFLA_GRE_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_GRE_TTL] = { .type = NLA_U8 }, [IFLA_GRE_TOS] = { .type = NLA_U8 }, [IFLA_GRE_PMTUDISC] = { .type = NLA_U8 }, diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index cfb025606793..9b153c7fcbb4 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -580,8 +580,8 @@ static const struct nla_policy vti_policy[IFLA_VTI_MAX + 1] = { [IFLA_VTI_LINK] = { .type = NLA_U32 }, [IFLA_VTI_IKEY] = { .type = NLA_U32 }, [IFLA_VTI_OKEY] = { .type = NLA_U32 }, - [IFLA_VTI_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) }, - [IFLA_VTI_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, + [IFLA_VTI_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, + [IFLA_VTI_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_VTI_FWMARK] = { .type = NLA_U32 }, }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 8a39ee794891..3e50ac24fe41 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3949,7 +3949,7 @@ void __init tcp_init(void) BUILD_BUG_ON(TCP_MIN_SND_MSS <= MAX_TCP_OPTION_SPACE); BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > - FIELD_SIZEOF(struct sk_buff, cb)); + sizeof_field(struct sk_buff, cb)); percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL); percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 923034c52ce4..9d0965252ddf 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -2170,8 +2170,8 @@ static const struct nla_policy ip6gre_policy[IFLA_GRE_MAX + 1] = { [IFLA_GRE_OFLAGS] = { .type = NLA_U16 }, [IFLA_GRE_IKEY] = { .type = NLA_U32 }, [IFLA_GRE_OKEY] = { .type = NLA_U32 }, - [IFLA_GRE_LOCAL] = { .len = FIELD_SIZEOF(struct ipv6hdr, saddr) }, - [IFLA_GRE_REMOTE] = { .len = FIELD_SIZEOF(struct ipv6hdr, daddr) }, + [IFLA_GRE_LOCAL] = { .len = sizeof_field(struct ipv6hdr, saddr) }, + [IFLA_GRE_REMOTE] = { .len = sizeof_field(struct ipv6hdr, daddr) }, [IFLA_GRE_TTL] = { .type = NLA_U8 }, [IFLA_GRE_ENCAP_LIMIT] = { .type = NLA_U8 }, [IFLA_GRE_FLOWINFO] = { .type = NLA_U32 }, diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index ebb62a4ebe30..c4bdcbc84b07 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -50,7 +50,7 @@ static struct iucv_interface *pr_iucv; static const u8 iprm_shutdown[8] = {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01}; -#define TRGCLS_SIZE FIELD_SIZEOF(struct iucv_message, class) +#define TRGCLS_SIZE sizeof_field(struct iucv_message, class) #define __iucv_sock_wait(sk, condition, timeo, ret) \ do { \ diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 062b73a83af0..c26a5663795e 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -7595,7 +7595,7 @@ int nft_validate_register_load(enum nft_registers reg, unsigned int len) return -EINVAL; if (len == 0) return -EINVAL; - if (reg * NFT_REG32_SIZE + len > FIELD_SIZEOF(struct nft_regs, data)) + if (reg * NFT_REG32_SIZE + len > sizeof_field(struct nft_regs, data)) return -ERANGE; return 0; @@ -7643,7 +7643,7 @@ int nft_validate_register_store(const struct nft_ctx *ctx, if (len == 0) return -EINVAL; if (reg * NFT_REG32_SIZE + len > - FIELD_SIZEOF(struct nft_regs, data)) + sizeof_field(struct nft_regs, data)) return -ERANGE; if (data != NULL && type != NFT_DATA_VALUE) diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index 7525063c25f5..de3a9596b7f1 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -236,7 +236,7 @@ nfnl_cthelper_create(const struct nlattr * const tb[], nla_strlcpy(helper->name, tb[NFCTH_NAME], NF_CT_HELPER_NAME_LEN); size = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN])); - if (size > FIELD_SIZEOF(struct nf_conn_help, data)) { + if (size > sizeof_field(struct nf_conn_help, data)) { ret = -ENOMEM; goto err2; } diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 46ca8bcca1bd..faea72c2df32 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -440,12 +440,12 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, switch (ctx->family) { case NFPROTO_IPV4: - len = FIELD_SIZEOF(struct nf_conntrack_tuple, + len = sizeof_field(struct nf_conntrack_tuple, src.u3.ip); break; case NFPROTO_IPV6: case NFPROTO_INET: - len = FIELD_SIZEOF(struct nf_conntrack_tuple, + len = sizeof_field(struct nf_conntrack_tuple, src.u3.ip6); break; default: @@ -457,20 +457,20 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, if (tb[NFTA_CT_DIRECTION] == NULL) return -EINVAL; - len = FIELD_SIZEOF(struct nf_conntrack_tuple, src.u3.ip); + len = sizeof_field(struct nf_conntrack_tuple, src.u3.ip); break; case NFT_CT_SRC_IP6: case NFT_CT_DST_IP6: if (tb[NFTA_CT_DIRECTION] == NULL) return -EINVAL; - len = FIELD_SIZEOF(struct nf_conntrack_tuple, src.u3.ip6); + len = sizeof_field(struct nf_conntrack_tuple, src.u3.ip6); break; case NFT_CT_PROTO_SRC: case NFT_CT_PROTO_DST: if (tb[NFTA_CT_DIRECTION] == NULL) return -EINVAL; - len = FIELD_SIZEOF(struct nf_conntrack_tuple, src.u.all); + len = sizeof_field(struct nf_conntrack_tuple, src.u.all); break; case NFT_CT_BYTES: case NFT_CT_PKTS: @@ -551,7 +551,7 @@ static int nft_ct_set_init(const struct nft_ctx *ctx, case NFT_CT_MARK: if (tb[NFTA_CT_DIRECTION]) return -EINVAL; - len = FIELD_SIZEOF(struct nf_conn, mark); + len = sizeof_field(struct nf_conn, mark); break; #endif #ifdef CONFIG_NF_CONNTRACK_LABELS diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c index 39dc94f2491e..bc9fd98c5d6d 100644 --- a/net/netfilter/nft_masq.c +++ b/net/netfilter/nft_masq.c @@ -43,7 +43,7 @@ static int nft_masq_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { - u32 plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all); + u32 plen = sizeof_field(struct nf_nat_range, min_addr.all); struct nft_masq *priv = nft_expr_priv(expr); int err; diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index c3c93e95b46e..8b44a4de5329 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -141,10 +141,10 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, switch (family) { case NFPROTO_IPV4: - alen = FIELD_SIZEOF(struct nf_nat_range, min_addr.ip); + alen = sizeof_field(struct nf_nat_range, min_addr.ip); break; case NFPROTO_IPV6: - alen = FIELD_SIZEOF(struct nf_nat_range, min_addr.ip6); + alen = sizeof_field(struct nf_nat_range, min_addr.ip6); break; default: return -EAFNOSUPPORT; @@ -171,7 +171,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, } } - plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all); + plen = sizeof_field(struct nf_nat_range, min_addr.all); if (tb[NFTA_NAT_REG_PROTO_MIN]) { priv->sreg_proto_min = nft_parse_register(tb[NFTA_NAT_REG_PROTO_MIN]); diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index 43eeb1f609f1..5b779171565c 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -48,7 +48,7 @@ static int nft_redir_init(const struct nft_ctx *ctx, unsigned int plen; int err; - plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all); + plen = sizeof_field(struct nf_nat_range, min_addr.all); if (tb[NFTA_REDIR_REG_PROTO_MIN]) { priv->sreg_proto_min = nft_parse_register(tb[NFTA_REDIR_REG_PROTO_MIN]); diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index f92a82c73880..4c33dfc9dab5 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -218,14 +218,14 @@ static int nft_tproxy_init(const struct nft_ctx *ctx, switch (priv->family) { case NFPROTO_IPV4: - alen = FIELD_SIZEOF(union nf_inet_addr, in); + alen = sizeof_field(union nf_inet_addr, in); err = nf_defrag_ipv4_enable(ctx->net); if (err) return err; break; #if IS_ENABLED(CONFIG_NF_TABLES_IPV6) case NFPROTO_IPV6: - alen = FIELD_SIZEOF(union nf_inet_addr, in6); + alen = sizeof_field(union nf_inet_addr, in6); err = nf_defrag_ipv6_enable(ctx->net); if (err) return err; diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c index 2236455b10a3..37253d399c6b 100644 --- a/net/netfilter/xt_RATEEST.c +++ b/net/netfilter/xt_RATEEST.c @@ -30,7 +30,7 @@ static unsigned int jhash_rnd __read_mostly; static unsigned int xt_rateest_hash(const char *name) { - return jhash(name, FIELD_SIZEOF(struct xt_rateest, name), jhash_rnd) & + return jhash(name, sizeof_field(struct xt_rateest, name), jhash_rnd) & (RATEEST_HSIZE - 1); } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 90b2ab9dd449..4e31721e7293 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2755,7 +2755,7 @@ static int __init netlink_proto_init(void) if (err != 0) goto out; - BUILD_BUG_ON(sizeof(struct netlink_skb_parms) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct netlink_skb_parms) > sizeof_field(struct sk_buff, cb)); nl_table = kcalloc(MAX_LINKS, sizeof(*nl_table), GFP_KERNEL); if (!nl_table) diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 1047e8043084..e3a37d22539c 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -2497,7 +2497,7 @@ static int __init dp_init(void) { int err; - BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > sizeof_field(struct sk_buff, cb)); pr_info("Open vSwitch switching datapath\n"); diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index fd8ed766bdd1..758a8c77f736 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -37,7 +37,7 @@ enum sw_flow_mac_proto { * matching for small options. */ #define TUN_METADATA_OFFSET(opt_len) \ - (FIELD_SIZEOF(struct sw_flow_key, tun_opts) - opt_len) + (sizeof_field(struct sw_flow_key, tun_opts) - opt_len) #define TUN_METADATA_OPTS(flow_key, opt_len) \ ((void *)((flow_key)->tun_opts + TUN_METADATA_OFFSET(opt_len))) @@ -52,7 +52,7 @@ struct vlan_head { #define OVS_SW_FLOW_KEY_METADATA_SIZE \ (offsetof(struct sw_flow_key, recirc_id) + \ - FIELD_SIZEOF(struct sw_flow_key, recirc_id)) + sizeof_field(struct sw_flow_key, recirc_id)) struct ovs_key_nsh { struct ovs_nsh_key_base base; diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index d72ddb67bb74..9d3c4d2d893a 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -972,7 +972,7 @@ static int __init af_rxrpc_init(void) int ret = -1; unsigned int tmp; - BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > sizeof_field(struct sk_buff, cb)); get_random_bytes(&tmp, sizeof(tmp)); tmp &= 0x3fffffff; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index bf2d69335d4b..f685c0d73708 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -312,7 +312,7 @@ static void tcf_ct_act_set_labels(struct nf_conn *ct, u32 *labels_m) { #if IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) - size_t labels_sz = FIELD_SIZEOF(struct tcf_ct_params, labels); + size_t labels_sz = sizeof_field(struct tcf_ct_params, labels); if (!memchr_inv(labels_m, 0, labels_sz)) return; @@ -936,7 +936,7 @@ static struct tc_action_ops act_ct_ops = { static __net_init int ct_init_net(struct net *net) { - unsigned int n_bits = FIELD_SIZEOF(struct tcf_ct_params, labels) * 8; + unsigned int n_bits = sizeof_field(struct tcf_ct_params, labels) * 8; struct tc_ct_action_net *tn = net_generic(net, ct_net_id); if (nf_connlabels_get(net, n_bits - 1)) { diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 6c68971d99df..0d125de54285 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1481,7 +1481,7 @@ static int fl_init_mask_hashtable(struct fl_flow_mask *mask) } #define FL_KEY_MEMBER_OFFSET(member) offsetof(struct fl_flow_key, member) -#define FL_KEY_MEMBER_SIZE(member) FIELD_SIZEOF(struct fl_flow_key, member) +#define FL_KEY_MEMBER_SIZE(member) sizeof_field(struct fl_flow_key, member) #define FL_KEY_IS_MASKED(mask, member) \ memchr_inv(((char *)mask) + FL_KEY_MEMBER_OFFSET(member), \ diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 7cfdce10de36..774babbee045 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2865,7 +2865,7 @@ static int __init af_unix_init(void) { int rc = -1; - BUILD_BUG_ON(sizeof(struct unix_skb_parms) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct unix_skb_parms) > sizeof_field(struct sk_buff, cb)); rc = proto_register(&unix_proto, 1); if (rc != 0) { diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index f19a895ad7cd..ef8dfd47c7e3 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -45,7 +45,7 @@ #define DONT_HASH 0x0200 #define INVALID_PCR(a) (((a) < 0) || \ - (a) >= (FIELD_SIZEOF(struct integrity_iint_cache, measured_pcrs) * 8)) + (a) >= (sizeof_field(struct integrity_iint_cache, measured_pcrs) * 8)) int ima_policy_flag; static int temp_ima_appraise; @@ -274,7 +274,7 @@ static struct ima_rule_entry *ima_lsm_copy_rule(struct ima_rule_entry *entry) * lsm rules can change */ memcpy(nentry, entry, sizeof(*nentry)); - memset(nentry->lsm, 0, FIELD_SIZEOF(struct ima_rule_entry, lsm)); + memset(nentry->lsm, 0, sizeof_field(struct ima_rule_entry, lsm)); for (i = 0; i < MAX_LSM_RULES; i++) { if (!entry->lsm[i].rule) diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c index f8b5b960e597..4eaa2b5b20a5 100644 --- a/sound/soc/codecs/hdmi-codec.c +++ b/sound/soc/codecs/hdmi-codec.c @@ -292,7 +292,7 @@ static int hdmi_eld_ctl_info(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo) { uinfo->type = SNDRV_CTL_ELEM_TYPE_BYTES; - uinfo->count = FIELD_SIZEOF(struct hdmi_codec_priv, eld); + uinfo->count = sizeof_field(struct hdmi_codec_priv, eld); return 0; } -- cgit v1.2.3-71-gd317 From 93c60483b5feefced92b869d5f97769495bc6313 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 9 Dec 2019 13:55:15 -0800 Subject: bus: ti-sysc: Fix missing force mstandby quirk handling Commit 03856e928b0e ("bus: ti-sysc: Handle mstandby quirk and use it for musb") added quirk handling for mstandby quirk but did not consider that we also need a quirk variant for SYSC_QUIRK_FORCE_MSTANDBY. We need to use forced idle mode for both SYSC_QUIRK_SWSUP_MSTANDBY and SYSC_QUIRK_FORCE_MSTANDBY, but SYSC_QUIRK_SWSUP_MSTANDBY also need to additionally also configure no-idle mode when enabled. Fixes: 03856e928b0e ("bus: ti-sysc: Handle mstandby quirk and use it for musb") Signed-off-by: Tony Lindgren --- drivers/bus/ti-sysc.c | 3 ++- include/linux/platform_data/ti-sysc.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 56887c6877a7..563707779e18 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -981,7 +981,8 @@ static int sysc_disable_module(struct device *dev) return ret; } - if (ddata->cfg.quirks & SYSC_QUIRK_SWSUP_MSTANDBY) + if (ddata->cfg.quirks & (SYSC_QUIRK_SWSUP_MSTANDBY) || + ddata->cfg.quirks & (SYSC_QUIRK_FORCE_MSTANDBY)) best_mode = SYSC_IDLE_FORCE; reg &= ~(SYSC_IDLE_MASK << regbits->midle_shift); diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h index 0b9380475144..8cfe570fdece 100644 --- a/include/linux/platform_data/ti-sysc.h +++ b/include/linux/platform_data/ti-sysc.h @@ -49,6 +49,7 @@ struct sysc_regbits { s8 emufree_shift; }; +#define SYSC_QUIRK_FORCE_MSTANDBY BIT(20) #define SYSC_MODULE_QUIRK_AESS BIT(19) #define SYSC_MODULE_QUIRK_SGX BIT(18) #define SYSC_MODULE_QUIRK_HDQ1W BIT(17) -- cgit v1.2.3-71-gd317 From ff205766dbbee024a4a716638868d98ffb17748a Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Sun, 8 Dec 2019 16:01:12 -0800 Subject: ftrace: Fix function_graph tracer interaction with BPF trampoline Depending on type of BPF programs served by BPF trampoline it can call original function. In such case the trampoline will skip one stack frame while returning. That will confuse function_graph tracer and will cause crashes with bad RIP. Teach graph tracer to skip functions that have BPF trampoline attached. Signed-off-by: Alexei Starovoitov Signed-off-by: Steven Rostedt (VMware) --- arch/x86/kernel/ftrace.c | 14 -------------- include/linux/ftrace.h | 5 +++++ kernel/trace/fgraph.c | 9 +++++++++ kernel/trace/ftrace.c | 19 +++++++------------ 4 files changed, 21 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 060a361d9d11..024c3053dbba 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -1042,20 +1042,6 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, if (unlikely(atomic_read(¤t->tracing_graph_pause))) return; - /* - * If the return location is actually pointing directly to - * the start of a direct trampoline (if we trace the trampoline - * it will still be offset by MCOUNT_INSN_SIZE), then the - * return address is actually off by one word, and we - * need to adjust for that. - */ - if (ftrace_direct_func_count) { - if (ftrace_find_direct_func(self_addr + MCOUNT_INSN_SIZE)) { - self_addr = *parent; - parent++; - } - } - /* * Protect against fault, even if it shouldn't * happen. This tool is too much intrusive to diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 232806d5689d..987c2dc55bde 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -264,6 +264,7 @@ int ftrace_modify_direct_caller(struct ftrace_func_entry *entry, struct dyn_ftrace *rec, unsigned long old_addr, unsigned long new_addr); +unsigned long ftrace_find_rec_direct(unsigned long ip); #else # define ftrace_direct_func_count 0 static inline int register_ftrace_direct(unsigned long ip, unsigned long addr) @@ -290,6 +291,10 @@ static inline int ftrace_modify_direct_caller(struct ftrace_func_entry *entry, { return -ENODEV; } +static inline unsigned long ftrace_find_rec_direct(unsigned long ip) +{ + return 0; +} #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ #ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 67e0c462b059..a2659735db73 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -101,6 +101,15 @@ int function_graph_enter(unsigned long ret, unsigned long func, { struct ftrace_graph_ent trace; + /* + * Skip graph tracing if the return location is served by direct trampoline, + * since call sequence and return addresses is unpredicatable anymore. + * Ex: BPF trampoline may call original function and may skip frame + * depending on type of BPF programs attached. + */ + if (ftrace_direct_func_count && + ftrace_find_rec_direct(ret - MCOUNT_INSN_SIZE)) + return -EBUSY; trace.func = func; trace.depth = ++current->curr_ret_depth; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index caae523f4ef3..57477dc683db 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2364,7 +2364,7 @@ int ftrace_direct_func_count; * Search the direct_functions hash to see if the given instruction pointer * has a direct caller attached to it. */ -static unsigned long find_rec_direct(unsigned long ip) +unsigned long ftrace_find_rec_direct(unsigned long ip) { struct ftrace_func_entry *entry; @@ -2380,7 +2380,7 @@ static void call_direct_funcs(unsigned long ip, unsigned long pip, { unsigned long addr; - addr = find_rec_direct(ip); + addr = ftrace_find_rec_direct(ip); if (!addr) return; @@ -2393,11 +2393,6 @@ struct ftrace_ops direct_ops = { | FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS | FTRACE_OPS_FL_PERMANENT, }; -#else -static inline unsigned long find_rec_direct(unsigned long ip) -{ - return 0; -} #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ /** @@ -2417,7 +2412,7 @@ unsigned long ftrace_get_addr_new(struct dyn_ftrace *rec) if ((rec->flags & FTRACE_FL_DIRECT) && (ftrace_rec_count(rec) == 1)) { - addr = find_rec_direct(rec->ip); + addr = ftrace_find_rec_direct(rec->ip); if (addr) return addr; WARN_ON_ONCE(1); @@ -2458,7 +2453,7 @@ unsigned long ftrace_get_addr_curr(struct dyn_ftrace *rec) /* Direct calls take precedence over trampolines */ if (rec->flags & FTRACE_FL_DIRECT_EN) { - addr = find_rec_direct(rec->ip); + addr = ftrace_find_rec_direct(rec->ip); if (addr) return addr; WARN_ON_ONCE(1); @@ -3604,7 +3599,7 @@ static int t_show(struct seq_file *m, void *v) if (rec->flags & FTRACE_FL_DIRECT) { unsigned long direct; - direct = find_rec_direct(rec->ip); + direct = ftrace_find_rec_direct(rec->ip); if (direct) seq_printf(m, "\n\tdirect-->%pS", (void *)direct); } @@ -5008,7 +5003,7 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr) mutex_lock(&direct_mutex); /* See if there's a direct function at @ip already */ - if (find_rec_direct(ip)) + if (ftrace_find_rec_direct(ip)) goto out_unlock; ret = -ENODEV; @@ -5027,7 +5022,7 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr) if (ip != rec->ip) { ip = rec->ip; /* Need to check this ip for a direct. */ - if (find_rec_direct(ip)) + if (ftrace_find_rec_direct(ip)) goto out_unlock; } -- cgit v1.2.3-71-gd317 From 2c2f00ab1641895183488ff2bce53c415344fb87 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Fri, 6 Dec 2019 01:23:22 +0100 Subject: i2c: remove i2c_new_dummy() API MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit All in-kernel users have been converted to {devm_}i2c_new_dummy_device(). Remove the old API. Signed-off-by: Wolfram Sang Reviewed-by: Niklas Söderlund Tested-by: Luca Ceresoli Reviewed-by: Luca Ceresoli Signed-off-by: Wolfram Sang --- drivers/i2c/i2c-core-base.c | 23 ----------------------- include/linux/i2c.h | 6 ------ 2 files changed, 29 deletions(-) (limited to 'include/linux') diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 9333c865d4a9..9f8dcd3f8385 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -896,29 +896,6 @@ struct i2c_client *i2c_new_dummy_device(struct i2c_adapter *adapter, u16 address } EXPORT_SYMBOL_GPL(i2c_new_dummy_device); -/** - * i2c_new_dummy - return a new i2c device bound to a dummy driver - * @adapter: the adapter managing the device - * @address: seven bit address to be used - * Context: can sleep - * - * This deprecated function has the same functionality as @i2c_new_dummy_device, - * it just returns NULL instead of an ERR_PTR in case of an error for - * compatibility with current I2C API. It will be removed once all users are - * converted. - * - * This returns the new i2c client, which should be saved for later use with - * i2c_unregister_device(); or NULL to indicate an error. - */ -struct i2c_client *i2c_new_dummy(struct i2c_adapter *adapter, u16 address) -{ - struct i2c_client *ret; - - ret = i2c_new_dummy_device(adapter, address); - return IS_ERR(ret) ? NULL : ret; -} -EXPORT_SYMBOL_GPL(i2c_new_dummy); - struct i2c_dummy_devres { struct i2c_client *client; }; diff --git a/include/linux/i2c.h b/include/linux/i2c.h index d2f786706657..d1baf8d57536 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -466,12 +466,6 @@ i2c_new_probed_device(struct i2c_adapter *adap, /* Common custom probe functions */ extern int i2c_probe_func_quick_read(struct i2c_adapter *adap, unsigned short addr); -/* For devices that use several addresses, use i2c_new_dummy() to make - * client handles for the extra addresses. - */ -extern struct i2c_client * -i2c_new_dummy(struct i2c_adapter *adap, u16 address); - extern struct i2c_client * i2c_new_dummy_device(struct i2c_adapter *adapter, u16 address); -- cgit v1.2.3-71-gd317 From 3ac61258599b5abe45d97b926d44a79262385bae Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 8 Dec 2019 20:35:38 -0800 Subject: i2c: fix header file kernel-doc warning Fix kernel-doc warning in . ../include/linux/i2c.h:337: warning: Function parameter or member 'init_irq' not described in 'i2c_client' Signed-off-by: Randy Dunlap Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index d1baf8d57536..91954324f985 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -300,6 +300,7 @@ struct i2c_driver { * generic enough to hide second-sourcing and compatible revisions. * @adapter: manages the bus segment hosting this I2C device * @dev: Driver model device node for the slave. + * @init_irq: IRQ that was set at initialization * @irq: indicates the IRQ generated by this device (if any) * @detected: member of an i2c_driver.clients list or i2c-core's * userspace_devices list -- cgit v1.2.3-71-gd317 From 8c9312a925ad859daefd0f443ef3b6dc7157d881 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Wed, 6 Nov 2019 22:21:01 +0100 Subject: i2c: add helper to check if a client has a driver attached As a preparation for an API conversion, factor out something frequently used in the media subsystem. As an improvement, it bails out on both, NULL and ERRPTR to handle the old and new API. Signed-off-by: Wolfram Sang Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 91954324f985..582ef05ec07e 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -851,6 +851,11 @@ extern void i2c_del_driver(struct i2c_driver *driver); #define i2c_add_driver(driver) \ i2c_register_driver(THIS_MODULE, driver) +static inline bool i2c_client_has_driver(struct i2c_client *client) +{ + return !IS_ERR_OR_NULL(client) && client->dev.driver; +} + /* call the i2c_client->command() of all attached clients with * the given arguments */ extern void i2c_clients_command(struct i2c_adapter *adap, -- cgit v1.2.3-71-gd317 From b91e014f078e2e4f24778680e28dbbdecc7f0eb9 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Sun, 8 Dec 2019 16:01:13 -0800 Subject: bpf: Make BPF trampoline use register_ftrace_direct() API Make BPF trampoline attach its generated assembly code to kernel functions via register_ftrace_direct() API. It helps ftrace-based tracers co-exist with BPF trampoline on the same kernel function. It also switches attaching logic from arch specific text_poke to generic ftrace that is available on many architectures. text_poke is still necessary for bpf-to-bpf attach and for bpf_tail_call optimization. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20191209000114.1876138-3-ast@kernel.org --- include/linux/bpf.h | 1 + kernel/bpf/trampoline.c | 64 ++++++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 59 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 35903f148be5..ac7de5291509 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -461,6 +461,7 @@ struct bpf_trampoline { struct { struct btf_func_model model; void *addr; + bool ftrace_managed; } func; /* list of BPF programs using this trampoline */ struct hlist_head progs_hlist[BPF_TRAMP_MAX]; diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 7e89f1f49d77..23b0d5cfd47e 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -3,6 +3,7 @@ #include #include #include +#include /* btf_vmlinux has ~22k attachable functions. 1k htab is enough. */ #define TRAMPOLINE_HASH_BITS 10 @@ -59,6 +60,60 @@ out: return tr; } +static int is_ftrace_location(void *ip) +{ + long addr; + + addr = ftrace_location((long)ip); + if (!addr) + return 0; + if (WARN_ON_ONCE(addr != (long)ip)) + return -EFAULT; + return 1; +} + +static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr) +{ + void *ip = tr->func.addr; + int ret; + + if (tr->func.ftrace_managed) + ret = unregister_ftrace_direct((long)ip, (long)old_addr); + else + ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, NULL); + return ret; +} + +static int modify_fentry(struct bpf_trampoline *tr, void *old_addr, void *new_addr) +{ + void *ip = tr->func.addr; + int ret; + + if (tr->func.ftrace_managed) + ret = modify_ftrace_direct((long)ip, (long)old_addr, (long)new_addr); + else + ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, new_addr); + return ret; +} + +/* first time registering */ +static int register_fentry(struct bpf_trampoline *tr, void *new_addr) +{ + void *ip = tr->func.addr; + int ret; + + ret = is_ftrace_location(ip); + if (ret < 0) + return ret; + tr->func.ftrace_managed = ret; + + if (tr->func.ftrace_managed) + ret = register_ftrace_direct((long)ip, (long)new_addr); + else + ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, NULL, new_addr); + return ret; +} + /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. Pick a number to fit into PAGE_SIZE / 2 */ @@ -77,8 +132,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) int err; if (fentry_cnt + fexit_cnt == 0) { - err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL, - old_image, NULL); + err = unregister_fentry(tr, old_image); tr->selector = 0; goto out; } @@ -105,12 +159,10 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) if (tr->selector) /* progs already running at this address */ - err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL, - old_image, new_image); + err = modify_fentry(tr, old_image, new_image); else /* first time registering */ - err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_CALL, NULL, - new_image); + err = register_fentry(tr, new_image); if (err) goto out; tr->selector++; -- cgit v1.2.3-71-gd317 From 5e787dbf659fe77d56215be74044f85e01b3920f Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 23 Oct 2018 22:10:35 +0200 Subject: devtmpfs: use do_mount() instead of ksys_mount() In devtmpfs, do_mount() can be called directly instead of complex wrapping by ksys_mount(): - the first and third arguments are const strings in the kernel, and do not need to be copied over from userspace; - the fifth argument is NULL, and therefore no page needs to be copied over from userspace; - the second and fourth argument are passed through anyway. Signed-off-by: Dominik Brodowski --- drivers/base/devtmpfs.c | 6 +++--- include/linux/device.h | 4 ++-- init/do_mounts.c | 2 +- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c index 30d0523014e0..6cdbf1531238 100644 --- a/drivers/base/devtmpfs.c +++ b/drivers/base/devtmpfs.c @@ -359,7 +359,7 @@ static int handle_remove(const char *nodename, struct device *dev) * If configured, or requested by the commandline, devtmpfs will be * auto-mounted after the kernel mounted the root filesystem. */ -int devtmpfs_mount(const char *mntdir) +int devtmpfs_mount(void) { int err; @@ -369,7 +369,7 @@ int devtmpfs_mount(const char *mntdir) if (!thread) return 0; - err = ksys_mount("devtmpfs", mntdir, "devtmpfs", MS_SILENT, NULL); + err = do_mount("devtmpfs", "dev", "devtmpfs", MS_SILENT, NULL); if (err) printk(KERN_INFO "devtmpfs: error mounting %i\n", err); else @@ -394,7 +394,7 @@ static int devtmpfsd(void *p) *err = ksys_unshare(CLONE_NEWNS); if (*err) goto out; - *err = ksys_mount("devtmpfs", "/", "devtmpfs", MS_SILENT, NULL); + *err = do_mount("devtmpfs", "/", "devtmpfs", MS_SILENT, NULL); if (*err) goto out; ksys_chdir("/.."); /* will traverse into overmounted root */ diff --git a/include/linux/device.h b/include/linux/device.h index e226030c1df3..96ff76731e93 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1666,11 +1666,11 @@ extern bool kill_device(struct device *dev); #ifdef CONFIG_DEVTMPFS extern int devtmpfs_create_node(struct device *dev); extern int devtmpfs_delete_node(struct device *dev); -extern int devtmpfs_mount(const char *mntdir); +extern int devtmpfs_mount(void); #else static inline int devtmpfs_create_node(struct device *dev) { return 0; } static inline int devtmpfs_delete_node(struct device *dev) { return 0; } -static inline int devtmpfs_mount(const char *mountpoint) { return 0; } +static inline int devtmpfs_mount(void) { return 0; } #endif /* drivers/base/power/shutdown.c */ diff --git a/init/do_mounts.c b/init/do_mounts.c index af9cda887a23..43f6d098c880 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -670,7 +670,7 @@ void __init prepare_namespace(void) mount_root(); out: - devtmpfs_mount("dev"); + devtmpfs_mount(); ksys_mount(".", "/", NULL, MS_MOVE, NULL); ksys_chroot("."); } -- cgit v1.2.3-71-gd317 From cccaa5e33525fc07f4a2ce0518e50b9ddf435e47 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 23 Oct 2018 22:41:09 +0200 Subject: init: use do_mount() instead of ksys_mount() In prepare_namespace(), do_mount() can be used instead of ksys_mount() as the first and third argument are const strings in the kernel, the second and fourth argument are passed through anyway, and the fifth argument is NULL. In do_mount_root(), ksys_mount() is called with the first and third argument being already kernelspace strings, which do not need to be copied over from userspace to kernelspace (again). The second and fourth arguments are passed through to do_mount() anyway. The fifth argument, while already residing in kernelspace, needs to be put into a page of its own. Then, do_mount() can be used instead of ksys_mount(). Once this is done, there are no in-kernel users to ksys_mount() left, which can therefore be removed. Signed-off-by: Dominik Brodowski --- fs/namespace.c | 10 ++-------- include/linux/syscalls.h | 2 -- init/do_mounts.c | 28 ++++++++++++++++++++++------ 3 files changed, 24 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/fs/namespace.c b/fs/namespace.c index 2fd0c8bcb8c1..be601d3a8008 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -3325,8 +3325,8 @@ struct dentry *mount_subtree(struct vfsmount *m, const char *name) } EXPORT_SYMBOL(mount_subtree); -int ksys_mount(const char __user *dev_name, const char __user *dir_name, - const char __user *type, unsigned long flags, void __user *data) +SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, + char __user *, type, unsigned long, flags, void __user *, data) { int ret; char *kernel_type; @@ -3359,12 +3359,6 @@ out_type: return ret; } -SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, - char __user *, type, unsigned long, flags, void __user *, data) -{ - return ksys_mount(dev_name, dir_name, type, flags, data); -} - /* * Create a kernel mount representation for a new, prepared superblock * (specified by fs_fd) and attach to an open_tree-like file descriptor. diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index d0391cc2dae9..5262b7a76d39 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1231,8 +1231,6 @@ asmlinkage long sys_ni_syscall(void); * the ksys_xyzyyz() functions prototyped below. */ -int ksys_mount(const char __user *dev_name, const char __user *dir_name, - const char __user *type, unsigned long flags, void __user *data); int ksys_umount(char __user *name, int flags); int ksys_dup(unsigned int fildes); int ksys_chroot(const char __user *filename); diff --git a/init/do_mounts.c b/init/do_mounts.c index 43f6d098c880..f55cbd9cb818 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -387,12 +387,25 @@ static void __init get_fs_names(char *page) *s = '\0'; } -static int __init do_mount_root(char *name, char *fs, int flags, void *data) +static int __init do_mount_root(const char *name, const char *fs, + const int flags, const void *data) { struct super_block *s; - int err = ksys_mount(name, "/root", fs, flags, data); - if (err) - return err; + char *data_page; + struct page *p; + int ret; + + /* do_mount() requires a full page as fifth argument */ + p = alloc_page(GFP_KERNEL); + if (!p) + return -ENOMEM; + + data_page = page_address(p); + strncpy(data_page, data, PAGE_SIZE - 1); + + ret = do_mount(name, "/root", fs, flags, data_page); + if (ret) + goto out; ksys_chdir("/root"); s = current->fs->pwd.dentry->d_sb; @@ -402,7 +415,10 @@ static int __init do_mount_root(char *name, char *fs, int flags, void *data) s->s_type->name, sb_rdonly(s) ? " readonly" : "", MAJOR(ROOT_DEV), MINOR(ROOT_DEV)); - return 0; + +out: + put_page(p); + return ret; } void __init mount_block_root(char *name, int flags) @@ -671,7 +687,7 @@ void __init prepare_namespace(void) mount_root(); out: devtmpfs_mount(); - ksys_mount(".", "/", NULL, MS_MOVE, NULL); + do_mount(".", "/", NULL, MS_MOVE, NULL); ksys_chroot("."); } -- cgit v1.2.3-71-gd317 From 5addeae1bedc4c126b179f61e43e039bb373581f Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Thu, 12 Dec 2019 16:52:00 +0100 Subject: blk-cgroup: remove blkcg_drain_queue Since blk_drain_queue had already been removed, so this function is not needed anymore. Signed-off-by: Guoqing Jiang Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 20 -------------------- include/linux/blk-cgroup.h | 2 -- 2 files changed, 22 deletions(-) (limited to 'include/linux') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 708dea92dac8..a229b94d5390 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1061,26 +1061,6 @@ err_unlock: return PTR_ERR(blkg); } -/** - * blkcg_drain_queue - drain blkcg part of request_queue - * @q: request_queue to drain - * - * Called from blk_drain_queue(). Responsible for draining blkcg part. - */ -void blkcg_drain_queue(struct request_queue *q) -{ - lockdep_assert_held(&q->queue_lock); - - /* - * @q could be exiting and already have destroyed all blkgs as - * indicated by NULL root_blkg. If so, don't confuse policies. - */ - if (!q->root_blkg) - return; - - blk_throtl_drain(q); -} - /** * blkcg_exit_queue - exit and release blkcg part of request_queue * @q: request_queue being released diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 19394c77ed99..e4a6949fd171 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -188,7 +188,6 @@ struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg, struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, struct request_queue *q); int blkcg_init_queue(struct request_queue *q); -void blkcg_drain_queue(struct request_queue *q); void blkcg_exit_queue(struct request_queue *q); /* Blkio controller policy registration */ @@ -720,7 +719,6 @@ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { ret static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q) { return NULL; } static inline int blkcg_init_queue(struct request_queue *q) { return 0; } -static inline void blkcg_drain_queue(struct request_queue *q) { } static inline void blkcg_exit_queue(struct request_queue *q) { } static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; } static inline void blkcg_policy_unregister(struct blkcg_policy *pol) { } -- cgit v1.2.3-71-gd317 From 85572c2c4a45a541e880e087b5b17a48198b2416 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 11 Dec 2019 11:28:41 +0100 Subject: cpufreq: Avoid leaving stale IRQ work items during CPU offline The scheduler code calling cpufreq_update_util() may run during CPU offline on the target CPU after the IRQ work lists have been flushed for it, so the target CPU should be prevented from running code that may queue up an IRQ work item on it at that point. Unfortunately, that may not be the case if dvfs_possible_from_any_cpu is set for at least one cpufreq policy in the system, because that allows the CPU going offline to run the utilization update callback of the cpufreq governor on behalf of another (online) CPU in some cases. If that happens, the cpufreq governor callback may queue up an IRQ work on the CPU running it, which is going offline, and the IRQ work may not be flushed after that point. Moreover, that IRQ work cannot be flushed until the "offlining" CPU goes back online, so if any other CPU calls irq_work_sync() to wait for the completion of that IRQ work, it will have to wait until the "offlining" CPU is back online and that may not happen forever. In particular, a system-wide deadlock may occur during CPU online as a result of that. The failing scenario is as follows. CPU0 is the boot CPU, so it creates a cpufreq policy and becomes the "leader" of it (policy->cpu). It cannot go offline, because it is the boot CPU. Next, other CPUs join the cpufreq policy as they go online and they leave it when they go offline. The last CPU to go offline, say CPU3, may queue up an IRQ work while running the governor callback on behalf of CPU0 after leaving the cpufreq policy because of the dvfs_possible_from_any_cpu effect described above. Then, CPU0 is the only online CPU in the system and the stale IRQ work is still queued on CPU3. When, say, CPU1 goes back online, it will run irq_work_sync() to wait for that IRQ work to complete and so it will wait for CPU3 to go back online (which may never happen even in principle), but (worse yet) CPU0 is waiting for CPU1 at that point too and a system-wide deadlock occurs. To address this problem notice that CPUs which cannot run cpufreq utilization update code for themselves (for example, because they have left the cpufreq policies that they belonged to), should also be prevented from running that code on behalf of the other CPUs that belong to a cpufreq policy with dvfs_possible_from_any_cpu set and so in that case the cpufreq_update_util_data pointer of the CPU running the code must not be NULL as well as for the CPU which is the target of the cpufreq utilization update in progress. Accordingly, change cpufreq_this_cpu_can_update() into a regular function in kernel/sched/cpufreq.c (instead of a static inline in a header file) and make it check the cpufreq_update_util_data pointer of the local CPU if dvfs_possible_from_any_cpu is set for the target cpufreq policy. Also update the schedutil governor to do the cpufreq_this_cpu_can_update() check in the non-fast-switch case too to avoid the stale IRQ work issues. Fixes: 99d14d0e16fa ("cpufreq: Process remote callbacks from any CPU if the platform permits") Link: https://lore.kernel.org/linux-pm/20191121093557.bycvdo4xyinbc5cb@vireshk-i7/ Reported-by: Anson Huang Tested-by: Anson Huang Cc: 4.14+ # 4.14+ Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar Tested-by: Peng Fan (i.MX8QXP-MEK) Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 11 ----------- include/linux/sched/cpufreq.h | 3 +++ kernel/sched/cpufreq.c | 18 ++++++++++++++++++ kernel/sched/cpufreq_schedutil.c | 8 +++----- 4 files changed, 24 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 92d5fdc8154e..31b1b0e03df8 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -595,17 +595,6 @@ struct governor_attr { size_t count); }; -static inline bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy) -{ - /* - * Allow remote callbacks if: - * - dvfs_possible_from_any_cpu flag is set - * - the local and remote CPUs share cpufreq policy - */ - return policy->dvfs_possible_from_any_cpu || - cpumask_test_cpu(smp_processor_id(), policy->cpus); -} - /********************************************************************* * FREQUENCY TABLE HELPERS * *********************************************************************/ diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h index afa940cd50dc..cc6bcc1e96bc 100644 --- a/include/linux/sched/cpufreq.h +++ b/include/linux/sched/cpufreq.h @@ -12,6 +12,8 @@ #define SCHED_CPUFREQ_MIGRATION (1U << 1) #ifdef CONFIG_CPU_FREQ +struct cpufreq_policy; + struct update_util_data { void (*func)(struct update_util_data *data, u64 time, unsigned int flags); }; @@ -20,6 +22,7 @@ void cpufreq_add_update_util_hook(int cpu, struct update_util_data *data, void (*func)(struct update_util_data *data, u64 time, unsigned int flags)); void cpufreq_remove_update_util_hook(int cpu); +bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy); static inline unsigned long map_util_freq(unsigned long util, unsigned long freq, unsigned long cap) diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c index b5dcd1d83c7f..7c2fe50fd76d 100644 --- a/kernel/sched/cpufreq.c +++ b/kernel/sched/cpufreq.c @@ -5,6 +5,8 @@ * Copyright (C) 2016, Intel Corporation * Author: Rafael J. Wysocki */ +#include + #include "sched.h" DEFINE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data); @@ -57,3 +59,19 @@ void cpufreq_remove_update_util_hook(int cpu) rcu_assign_pointer(per_cpu(cpufreq_update_util_data, cpu), NULL); } EXPORT_SYMBOL_GPL(cpufreq_remove_update_util_hook); + +/** + * cpufreq_this_cpu_can_update - Check if cpufreq policy can be updated. + * @policy: cpufreq policy to check. + * + * Return 'true' if: + * - the local and remote CPUs share @policy, + * - dvfs_possible_from_any_cpu is set in @policy and the local CPU is not going + * offline (in which case it is not expected to run cpufreq updates any more). + */ +bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy) +{ + return cpumask_test_cpu(smp_processor_id(), policy->cpus) || + (policy->dvfs_possible_from_any_cpu && + rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data))); +} diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 322ca8860f54..9b8916fd00a2 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -82,12 +82,10 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time) * by the hardware, as calculating the frequency is pointless if * we cannot in fact act on it. * - * For the slow switching platforms, the kthread is always scheduled on - * the right set of CPUs and any CPU can find the next frequency and - * schedule the kthread. + * This is needed on the slow switching platforms too to prevent CPUs + * going offline from leaving stale IRQ work items behind. */ - if (sg_policy->policy->fast_switch_enabled && - !cpufreq_this_cpu_can_update(sg_policy->policy)) + if (!cpufreq_this_cpu_can_update(sg_policy->policy)) return false; if (unlikely(sg_policy->limits_changed)) { -- cgit v1.2.3-71-gd317 From b49a733d684e0096340b93e9dfd471f0e3ddc06d Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 23 Oct 2018 16:00:10 +0200 Subject: init: unify opening /dev/console as stdin/stdout/stderr Merge the two instances where /dev/console is opened as stdin/stdout/stderr. Signed-off-by: Dominik Brodowski --- include/linux/initrd.h | 2 ++ init/do_mounts_initrd.c | 5 +---- init/main.c | 17 ++++++++++++----- 3 files changed, 15 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/initrd.h b/include/linux/initrd.h index d77fe34fb00a..aa5914355728 100644 --- a/include/linux/initrd.h +++ b/include/linux/initrd.h @@ -28,3 +28,5 @@ extern unsigned int real_root_dev; extern char __initramfs_start[]; extern unsigned long __initramfs_size; + +void console_on_rootfs(void); diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index 3bf7b74153ab..dab8b1151b56 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -48,10 +48,7 @@ early_param("initrd", early_initrd); static int init_linuxrc(struct subprocess_info *info, struct cred *new) { ksys_unshare(CLONE_FS | CLONE_FILES); - /* stdin/stdout/stderr for /linuxrc */ - ksys_open("/dev/console", O_RDWR, 0); - ksys_dup(0); - ksys_dup(0); + console_on_rootfs(); /* move initrd over / and chdir/chroot in initrd root */ ksys_chdir("/root"); do_mount(".", "/", NULL, MS_MOVE, NULL); diff --git a/init/main.c b/init/main.c index 91f6ebb30ef0..2cd736059416 100644 --- a/init/main.c +++ b/init/main.c @@ -1155,6 +1155,17 @@ static int __ref kernel_init(void *unused) "See Linux Documentation/admin-guide/init.rst for guidance."); } +void console_on_rootfs(void) +{ + /* Open the /dev/console as stdin, this should never fail */ + if (ksys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0) + pr_err("Warning: unable to open an initial console.\n"); + + /* create stdout/stderr */ + (void) ksys_dup(0); + (void) ksys_dup(0); +} + static noinline void __init kernel_init_freeable(void) { /* @@ -1190,12 +1201,8 @@ static noinline void __init kernel_init_freeable(void) do_basic_setup(); - /* Open the /dev/console on the rootfs, this should never fail */ - if (ksys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0) - pr_err("Warning: unable to open an initial console.\n"); + console_on_rootfs(); - (void) ksys_dup(0); - (void) ksys_dup(0); /* * check if there is an early userspace init. If yes, let it do all * the work -- cgit v1.2.3-71-gd317 From 8243186f0cc7c57cf9d6a110cd7315c44e3e0be8 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 23 Oct 2018 16:24:09 +0200 Subject: fs: remove ksys_dup() ksys_dup() is used only at one place in the kernel, namely to duplicate fd 0 of /dev/console to stdout and stderr. The same functionality can be achieved by using functions already available within the kernel namespace. Signed-off-by: Dominik Brodowski --- fs/file.c | 7 +------ include/linux/syscalls.h | 1 - init/main.c | 26 ++++++++++++++++++++------ 3 files changed, 21 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/fs/file.c b/fs/file.c index 3da91a112bab..2f4fcf985079 100644 --- a/fs/file.c +++ b/fs/file.c @@ -960,7 +960,7 @@ SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) return ksys_dup3(oldfd, newfd, 0); } -int ksys_dup(unsigned int fildes) +SYSCALL_DEFINE1(dup, unsigned int, fildes) { int ret = -EBADF; struct file *file = fget_raw(fildes); @@ -975,11 +975,6 @@ int ksys_dup(unsigned int fildes) return ret; } -SYSCALL_DEFINE1(dup, unsigned int, fildes) -{ - return ksys_dup(fildes); -} - int f_dupfd(unsigned int from, struct file *file, unsigned flags) { int err; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 5262b7a76d39..2960dedcfde8 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1232,7 +1232,6 @@ asmlinkage long sys_ni_syscall(void); */ int ksys_umount(char __user *name, int flags); -int ksys_dup(unsigned int fildes); int ksys_chroot(const char __user *filename); ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count); int ksys_chdir(const char __user *filename); diff --git a/init/main.c b/init/main.c index 2cd736059416..ec3a1463ac69 100644 --- a/init/main.c +++ b/init/main.c @@ -93,6 +93,7 @@ #include #include #include +#include #include #include @@ -1157,13 +1158,26 @@ static int __ref kernel_init(void *unused) void console_on_rootfs(void) { - /* Open the /dev/console as stdin, this should never fail */ - if (ksys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0) - pr_err("Warning: unable to open an initial console.\n"); + struct file *file; + unsigned int i; + + /* Open /dev/console in kernelspace, this should never fail */ + file = filp_open("/dev/console", O_RDWR, 0); + if (!file) + goto err_out; + + /* create stdin/stdout/stderr, this should never fail */ + for (i = 0; i < 3; i++) { + if (f_dupfd(i, file, 0) != i) + goto err_out; + } + + return; - /* create stdout/stderr */ - (void) ksys_dup(0); - (void) ksys_dup(0); +err_out: + /* no panic -- this might not be fatal */ + pr_err("Warning: unable to open an initial console.\n"); + return; } static noinline void __init kernel_init_freeable(void) -- cgit v1.2.3-71-gd317 From 8dbd76e79a16b45b2ccb01d2f2e08dbf64e71e40 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 Dec 2019 18:20:41 -0800 Subject: tcp/dccp: fix possible race __inet_lookup_established() Michal Kubecek and Firo Yang did a very nice analysis of crashes happening in __inet_lookup_established(). Since a TCP socket can go from TCP_ESTABLISH to TCP_LISTEN (via a close()/socket()/listen() cycle) without a RCU grace period, I should not have changed listeners linkage in their hash table. They must use the nulls protocol (Documentation/RCU/rculist_nulls.txt), so that a lookup can detect a socket in a hash list was moved in another one. Since we added code in commit d296ba60d8e2 ("soreuseport: Resolve merge conflict for v4/v6 ordering fix"), we have to add hlist_nulls_add_tail_rcu() helper. Fixes: 3b24d854cb35 ("tcp/dccp: do not touch listener sk_refcnt under synflood") Signed-off-by: Eric Dumazet Reported-by: Michal Kubecek Reported-by: Firo Yang Reviewed-by: Michal Kubecek Link: https://lore.kernel.org/netdev/20191120083919.GH27852@unicorn.suse.cz/ Signed-off-by: Jakub Kicinski --- include/linux/rculist_nulls.h | 37 +++++++++++++++++++++++++++++++++++++ include/net/inet_hashtables.h | 12 +++++++++--- include/net/sock.h | 5 +++++ net/ipv4/inet_diag.c | 3 ++- net/ipv4/inet_hashtables.c | 16 ++++++++-------- net/ipv4/tcp_ipv4.c | 7 ++++--- 6 files changed, 65 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index bc8206a8f30e..61974c4c566b 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -100,6 +100,43 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n, first->pprev = &n->next; } +/** + * hlist_nulls_add_tail_rcu + * @n: the element to add to the hash list. + * @h: the list to add to. + * + * Description: + * Adds the specified element to the specified hlist_nulls, + * while permitting racing traversals. + * + * The caller must take whatever precautions are necessary + * (such as holding appropriate locks) to avoid racing + * with another list-mutation primitive, such as hlist_nulls_add_head_rcu() + * or hlist_nulls_del_rcu(), running on this same list. + * However, it is perfectly legal to run concurrently with + * the _rcu list-traversal primitives, such as + * hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency + * problems on Alpha CPUs. Regardless of the type of CPU, the + * list-traversal primitive must be guarded by rcu_read_lock(). + */ +static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n, + struct hlist_nulls_head *h) +{ + struct hlist_nulls_node *i, *last = NULL; + + /* Note: write side code, so rcu accessors are not needed. */ + for (i = h->first; !is_a_nulls(i); i = i->next) + last = i; + + if (last) { + n->next = last->next; + n->pprev = &last->next; + rcu_assign_pointer(hlist_next_rcu(last), n); + } else { + hlist_nulls_add_head_rcu(n, h); + } +} + /** * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type * @tpos: the type * to use as a loop cursor. diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index af2b4c065a04..d0019d3395cf 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -103,13 +103,19 @@ struct inet_bind_hashbucket { struct hlist_head chain; }; -/* - * Sockets can be hashed in established or listening table +/* Sockets can be hashed in established or listening table. + * We must use different 'nulls' end-of-chain value for all hash buckets : + * A socket might transition from ESTABLISH to LISTEN state without + * RCU grace period. A lookup in ehash table needs to handle this case. */ +#define LISTENING_NULLS_BASE (1U << 29) struct inet_listen_hashbucket { spinlock_t lock; unsigned int count; - struct hlist_head head; + union { + struct hlist_head head; + struct hlist_nulls_head nulls_head; + }; }; /* This is for listening sockets, thus all sockets which possess wildcards. */ diff --git a/include/net/sock.h b/include/net/sock.h index 87d54ef57f00..04c274a20620 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -722,6 +722,11 @@ static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_h hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list); } +static inline void __sk_nulls_add_node_tail_rcu(struct sock *sk, struct hlist_nulls_head *list) +{ + hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list); +} + static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) { sock_hold(sk); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index af154977904c..f11e997e517b 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -911,11 +911,12 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, for (i = s_i; i < INET_LHTABLE_SIZE; i++) { struct inet_listen_hashbucket *ilb; + struct hlist_nulls_node *node; num = 0; ilb = &hashinfo->listening_hash[i]; spin_lock(&ilb->lock); - sk_for_each(sk, &ilb->head) { + sk_nulls_for_each(sk, node, &ilb->nulls_head) { struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 83fb00153018..2bbaaf0c7176 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -516,10 +516,11 @@ static int inet_reuseport_add_sock(struct sock *sk, struct inet_listen_hashbucket *ilb) { struct inet_bind_bucket *tb = inet_csk(sk)->icsk_bind_hash; + const struct hlist_nulls_node *node; struct sock *sk2; kuid_t uid = sock_i_uid(sk); - sk_for_each_rcu(sk2, &ilb->head) { + sk_nulls_for_each_rcu(sk2, node, &ilb->nulls_head) { if (sk2 != sk && sk2->sk_family == sk->sk_family && ipv6_only_sock(sk2) == ipv6_only_sock(sk) && @@ -555,9 +556,9 @@ int __inet_hash(struct sock *sk, struct sock *osk) } if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport && sk->sk_family == AF_INET6) - hlist_add_tail_rcu(&sk->sk_node, &ilb->head); + __sk_nulls_add_node_tail_rcu(sk, &ilb->nulls_head); else - hlist_add_head_rcu(&sk->sk_node, &ilb->head); + __sk_nulls_add_node_rcu(sk, &ilb->nulls_head); inet_hash2(hashinfo, sk); ilb->count++; sock_set_flag(sk, SOCK_RCU_FREE); @@ -606,11 +607,9 @@ void inet_unhash(struct sock *sk) reuseport_detach_sock(sk); if (ilb) { inet_unhash2(hashinfo, sk); - __sk_del_node_init(sk); - ilb->count--; - } else { - __sk_nulls_del_node_init_rcu(sk); + ilb->count--; } + __sk_nulls_del_node_init_rcu(sk); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); unlock: spin_unlock_bh(lock); @@ -750,7 +749,8 @@ void inet_hashinfo_init(struct inet_hashinfo *h) for (i = 0; i < INET_LHTABLE_SIZE; i++) { spin_lock_init(&h->listening_hash[i].lock); - INIT_HLIST_HEAD(&h->listening_hash[i].head); + INIT_HLIST_NULLS_HEAD(&h->listening_hash[i].nulls_head, + i + LISTENING_NULLS_BASE); h->listening_hash[i].count = 0; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 92282f98dc82..1c7326e04f9b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2147,13 +2147,14 @@ static void *listening_get_next(struct seq_file *seq, void *cur) struct tcp_iter_state *st = seq->private; struct net *net = seq_file_net(seq); struct inet_listen_hashbucket *ilb; + struct hlist_nulls_node *node; struct sock *sk = cur; if (!sk) { get_head: ilb = &tcp_hashinfo.listening_hash[st->bucket]; spin_lock(&ilb->lock); - sk = sk_head(&ilb->head); + sk = sk_nulls_head(&ilb->nulls_head); st->offset = 0; goto get_sk; } @@ -2161,9 +2162,9 @@ get_head: ++st->num; ++st->offset; - sk = sk_next(sk); + sk = sk_nulls_next(sk); get_sk: - sk_for_each_from(sk) { + sk_nulls_for_each_from(sk, node) { if (!net_eq(sock_net(sk), net)) continue; if (sk->sk_family == afinfo->family) -- cgit v1.2.3-71-gd317 From d82d47d5d8a6d40bb622cef31b6c6fa09cbd01ea Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 8 Dec 2019 20:31:32 -0800 Subject: jbd2: fix kernel-doc notation warning Fix kernel-doc warning by inserting a beginning '*' character for the kernel-doc line. ../include/linux/jbd2.h:461: warning: bad line: journal. These are dirty buffers and revoke descriptor blocks. Link: https://lore.kernel.org/r/53e3ce27-ceae-560d-0fd4-f95728a33e12@infradead.org Cc: stable@kernel.org Signed-off-by: Randy Dunlap Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 842b62606025..89bf48a81798 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -457,7 +457,7 @@ struct jbd2_revoke_table_s; * @h_journal: Which journal handle belongs to - used iff h_reserved set. * @h_rsv_handle: Handle reserved for finishing the logical operation. * @h_total_credits: Number of remaining buffers we are allowed to add to - journal. These are dirty buffers and revoke descriptor blocks. + * journal. These are dirty buffers and revoke descriptor blocks. * @h_revoke_credits: Number of remaining revoke records available for handle * @h_ref: Reference count on this handle. * @h_err: Field for caller's use to track errors through large fs operations. -- cgit v1.2.3-71-gd317 From a2ea07465c8d7984cc6b8b1f0b3324f9b138094a Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 16 Dec 2019 17:49:00 +0100 Subject: bpf: Fix missing prog untrack in release_maps Commit da765a2f5993 ("bpf: Add poke dependency tracking for prog array maps") wrongly assumed that in case of prog load errors, we're cleaning up all program tracking via bpf_free_used_maps(). However, it can happen that we're still at the point where we didn't copy map pointers into the prog's aux section such that env->prog->aux->used_maps is still zero, running into a UAF. In such case, the verifier has similar release_maps() helper that drops references to used maps from its env. Consolidate the release code into __bpf_free_used_maps() and call it from all sides to fix it. Fixes: da765a2f5993 ("bpf: Add poke dependency tracking for prog array maps") Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/1c2909484ca524ae9f55109b06f22b6213e76376.1576514756.git.daniel@iogearbox.net --- include/linux/bpf.h | 2 ++ kernel/bpf/core.c | 14 ++++++++++---- kernel/bpf/verifier.c | 14 ++------------ 3 files changed, 14 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ac7de5291509..085a59afba85 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -818,6 +818,8 @@ struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); int __bpf_prog_charge(struct user_struct *user, u32 pages); void __bpf_prog_uncharge(struct user_struct *user, u32 pages); +void __bpf_free_used_maps(struct bpf_prog_aux *aux, + struct bpf_map **used_maps, u32 len); void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock); void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 49e32acad7d8..6231858df723 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2048,18 +2048,24 @@ static void bpf_free_cgroup_storage(struct bpf_prog_aux *aux) } } -static void bpf_free_used_maps(struct bpf_prog_aux *aux) +void __bpf_free_used_maps(struct bpf_prog_aux *aux, + struct bpf_map **used_maps, u32 len) { struct bpf_map *map; - int i; + u32 i; bpf_free_cgroup_storage(aux); - for (i = 0; i < aux->used_map_cnt; i++) { - map = aux->used_maps[i]; + for (i = 0; i < len; i++) { + map = used_maps[i]; if (map->ops->map_poke_untrack) map->ops->map_poke_untrack(map, aux); bpf_map_put(map); } +} + +static void bpf_free_used_maps(struct bpf_prog_aux *aux) +{ + __bpf_free_used_maps(aux, aux->used_maps, aux->used_map_cnt); kfree(aux->used_maps); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 034ef81f935b..a1acdce77070 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8298,18 +8298,8 @@ next_insn: /* drop refcnt of maps used by the rejected program */ static void release_maps(struct bpf_verifier_env *env) { - enum bpf_cgroup_storage_type stype; - int i; - - for_each_cgroup_storage_type(stype) { - if (!env->prog->aux->cgroup_storage[stype]) - continue; - bpf_cgroup_storage_release(env->prog, - env->prog->aux->cgroup_storage[stype]); - } - - for (i = 0; i < env->used_map_cnt; i++) - bpf_map_put(env->used_maps[i]); + __bpf_free_used_maps(env->prog->aux, env->used_maps, + env->used_map_cnt); } /* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */ -- cgit v1.2.3-71-gd317 From 45477b3fe3d10376b649b1b85fce72b2f9f1da84 Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Thu, 12 Dec 2019 12:58:35 -0500 Subject: security: keys: trusted: fix lost handle flush The original code, before it was moved into security/keys/trusted-keys had a flush after the blob unseal. Without that flush, the volatile handles increase in the TPM until it becomes unusable and the system either has to be rebooted or the TPM volatile area manually flushed. Fix by adding back the lost flush, which we now have to export because of the relocation of the trusted key code may cause the consumer to be modular. Signed-off-by: James Bottomley Fixes: 2e19e10131a0 ("KEYS: trusted: Move TPM2 trusted keys code") Reviewed-by: Jerry Snitselaar Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- drivers/char/tpm/tpm.h | 1 - drivers/char/tpm/tpm2-cmd.c | 1 + include/linux/tpm.h | 1 + security/keys/trusted-keys/trusted_tpm2.c | 1 + 4 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h index b9e1547be6b5..5620747da0cf 100644 --- a/drivers/char/tpm/tpm.h +++ b/drivers/char/tpm/tpm.h @@ -218,7 +218,6 @@ int tpm2_pcr_read(struct tpm_chip *chip, u32 pcr_idx, int tpm2_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, struct tpm_digest *digests); int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max); -void tpm2_flush_context(struct tpm_chip *chip, u32 handle); ssize_t tpm2_get_tpm_pt(struct tpm_chip *chip, u32 property_id, u32 *value, const char *desc); diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index fdb457704aa7..13696deceae8 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -362,6 +362,7 @@ void tpm2_flush_context(struct tpm_chip *chip, u32 handle) tpm_transmit_cmd(chip, &buf, 0, "flushing context"); tpm_buf_destroy(&buf); } +EXPORT_SYMBOL_GPL(tpm2_flush_context); struct tpm2_get_cap_out { u8 more_data; diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 0d6e949ba315..03e9b184411b 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -403,6 +403,7 @@ extern int tpm_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, extern int tpm_send(struct tpm_chip *chip, void *cmd, size_t buflen); extern int tpm_get_random(struct tpm_chip *chip, u8 *data, size_t max); extern struct tpm_chip *tpm_default_chip(void); +void tpm2_flush_context(struct tpm_chip *chip, u32 handle); #else static inline int tpm_is_tpm2(struct tpm_chip *chip) { diff --git a/security/keys/trusted-keys/trusted_tpm2.c b/security/keys/trusted-keys/trusted_tpm2.c index a9810ac2776f..08ec7f48f01d 100644 --- a/security/keys/trusted-keys/trusted_tpm2.c +++ b/security/keys/trusted-keys/trusted_tpm2.c @@ -309,6 +309,7 @@ int tpm2_unseal_trusted(struct tpm_chip *chip, return rc; rc = tpm2_unseal_cmd(chip, payload, options, blob_handle); + tpm2_flush_context(chip, blob_handle); return rc; } -- cgit v1.2.3-71-gd317 From e47304232b373362228bf233f17bd12b11c9aafc Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 17 Dec 2019 13:28:16 +0100 Subject: bpf: Fix cgroup local storage prog tracking Recently noticed that we're tracking programs related to local storage maps through their prog pointer. This is a wrong assumption since the prog pointer can still change throughout the verification process, for example, whenever bpf_patch_insn_single() is called. Therefore, the prog pointer that was assigned via bpf_cgroup_storage_assign() is not guaranteed to be the same as we pass in bpf_cgroup_storage_release() and the map would therefore remain in busy state forever. Fix this by using the prog's aux pointer which is stable throughout verification and beyond. Fixes: de9cbbaadba5 ("bpf: introduce cgroup storage maps") Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Cc: Roman Gushchin Cc: Martin KaFai Lau Link: https://lore.kernel.org/bpf/1471c69eca3022218666f909bc927a92388fd09e.1576580332.git.daniel@iogearbox.net --- include/linux/bpf-cgroup.h | 8 ++++---- kernel/bpf/core.c | 3 +-- kernel/bpf/local_storage.c | 24 ++++++++++++------------ kernel/bpf/verifier.c | 2 +- 4 files changed, 18 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 169fd25f6bc2..9be71c195d74 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -157,8 +157,8 @@ void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, struct cgroup *cgroup, enum bpf_attach_type type); void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage); -int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *map); -void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *map); +int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map); +void bpf_cgroup_storage_release(struct bpf_prog_aux *aux, struct bpf_map *map); int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, @@ -360,9 +360,9 @@ static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, static inline void bpf_cgroup_storage_set( struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) {} -static inline int bpf_cgroup_storage_assign(struct bpf_prog *prog, +static inline int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map) { return 0; } -static inline void bpf_cgroup_storage_release(struct bpf_prog *prog, +static inline void bpf_cgroup_storage_release(struct bpf_prog_aux *aux, struct bpf_map *map) {} static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { return NULL; } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 6231858df723..af6b738cf435 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2043,8 +2043,7 @@ static void bpf_free_cgroup_storage(struct bpf_prog_aux *aux) for_each_cgroup_storage_type(stype) { if (!aux->cgroup_storage[stype]) continue; - bpf_cgroup_storage_release(aux->prog, - aux->cgroup_storage[stype]); + bpf_cgroup_storage_release(aux, aux->cgroup_storage[stype]); } } diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 2ba750725cb2..6bf605dd4b94 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -20,7 +20,7 @@ struct bpf_cgroup_storage_map { struct bpf_map map; spinlock_t lock; - struct bpf_prog *prog; + struct bpf_prog_aux *aux; struct rb_root root; struct list_head list; }; @@ -420,7 +420,7 @@ const struct bpf_map_ops cgroup_storage_map_ops = { .map_seq_show_elem = cgroup_storage_seq_show_elem, }; -int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map) +int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *_map) { enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map); struct bpf_cgroup_storage_map *map = map_to_storage(_map); @@ -428,14 +428,14 @@ int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map) spin_lock_bh(&map->lock); - if (map->prog && map->prog != prog) + if (map->aux && map->aux != aux) goto unlock; - if (prog->aux->cgroup_storage[stype] && - prog->aux->cgroup_storage[stype] != _map) + if (aux->cgroup_storage[stype] && + aux->cgroup_storage[stype] != _map) goto unlock; - map->prog = prog; - prog->aux->cgroup_storage[stype] = _map; + map->aux = aux; + aux->cgroup_storage[stype] = _map; ret = 0; unlock: spin_unlock_bh(&map->lock); @@ -443,16 +443,16 @@ unlock: return ret; } -void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *_map) +void bpf_cgroup_storage_release(struct bpf_prog_aux *aux, struct bpf_map *_map) { enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map); struct bpf_cgroup_storage_map *map = map_to_storage(_map); spin_lock_bh(&map->lock); - if (map->prog == prog) { - WARN_ON(prog->aux->cgroup_storage[stype] != _map); - map->prog = NULL; - prog->aux->cgroup_storage[stype] = NULL; + if (map->aux == aux) { + WARN_ON(aux->cgroup_storage[stype] != _map); + map->aux = NULL; + aux->cgroup_storage[stype] = NULL; } spin_unlock_bh(&map->lock); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a1acdce77070..6ef71429d997 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8268,7 +8268,7 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) env->used_maps[env->used_map_cnt++] = map; if (bpf_map_is_cgroup_storage(map) && - bpf_cgroup_storage_assign(env->prog, map)) { + bpf_cgroup_storage_assign(env->prog->aux, map)) { verbose(env, "only one cgroup storage of each type is allowed\n"); fdput(f); return -EBUSY; -- cgit v1.2.3-71-gd317 From d98c9e83b5e7ca78175df1b13ac4a6d460d3962d Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Tue, 17 Dec 2019 20:51:38 -0800 Subject: kasan: fix crashes on access to memory mapped by vm_map_ram() With CONFIG_KASAN_VMALLOC=y any use of memory obtained via vm_map_ram() will crash because there is no shadow backing that memory. Instead of sprinkling additional kasan_populate_vmalloc() calls all over the vmalloc code, move it into alloc_vmap_area(). This will fix vm_map_ram() and simplify the code a bit. [aryabinin@virtuozzo.com: v2] Link: http://lkml.kernel.org/r/20191205095942.1761-1-aryabinin@virtuozzo.comLink: http://lkml.kernel.org/r/20191204204534.32202-1-aryabinin@virtuozzo.com Fixes: 3c5c3cfb9ef4 ("kasan: support backing vmalloc space with real shadow memory") Signed-off-by: Andrey Ryabinin Reported-by: Dmitry Vyukov Reviewed-by: Uladzislau Rezki (Sony) Cc: Daniel Axtens Cc: Alexander Potapenko Cc: Daniel Axtens Cc: Qian Cai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 15 +++++---- mm/kasan/common.c | 27 ++++++++++------ mm/vmalloc.c | 85 ++++++++++++++++++++++++--------------------------- 3 files changed, 67 insertions(+), 60 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 4f404c565db1..e18fe54969e9 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -205,20 +205,23 @@ static inline void *kasan_reset_tag(const void *addr) #endif /* CONFIG_KASAN_SW_TAGS */ #ifdef CONFIG_KASAN_VMALLOC -int kasan_populate_vmalloc(unsigned long requested_size, - struct vm_struct *area); -void kasan_poison_vmalloc(void *start, unsigned long size); +int kasan_populate_vmalloc(unsigned long addr, unsigned long size); +void kasan_poison_vmalloc(const void *start, unsigned long size); +void kasan_unpoison_vmalloc(const void *start, unsigned long size); void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, unsigned long free_region_end); #else -static inline int kasan_populate_vmalloc(unsigned long requested_size, - struct vm_struct *area) +static inline int kasan_populate_vmalloc(unsigned long start, + unsigned long size) { return 0; } -static inline void kasan_poison_vmalloc(void *start, unsigned long size) {} +static inline void kasan_poison_vmalloc(const void *start, unsigned long size) +{ } +static inline void kasan_unpoison_vmalloc(const void *start, unsigned long size) +{ } static inline void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, diff --git a/mm/kasan/common.c b/mm/kasan/common.c index 2fa710bb6358..e04e73603dfc 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -778,15 +778,17 @@ static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr, return 0; } -int kasan_populate_vmalloc(unsigned long requested_size, struct vm_struct *area) +int kasan_populate_vmalloc(unsigned long addr, unsigned long size) { unsigned long shadow_start, shadow_end; int ret; - shadow_start = (unsigned long)kasan_mem_to_shadow(area->addr); + if (!is_vmalloc_or_module_addr((void *)addr)) + return 0; + + shadow_start = (unsigned long)kasan_mem_to_shadow((void *)addr); shadow_start = ALIGN_DOWN(shadow_start, PAGE_SIZE); - shadow_end = (unsigned long)kasan_mem_to_shadow(area->addr + - area->size); + shadow_end = (unsigned long)kasan_mem_to_shadow((void *)addr + size); shadow_end = ALIGN(shadow_end, PAGE_SIZE); ret = apply_to_page_range(&init_mm, shadow_start, @@ -797,10 +799,6 @@ int kasan_populate_vmalloc(unsigned long requested_size, struct vm_struct *area) flush_cache_vmap(shadow_start, shadow_end); - kasan_unpoison_shadow(area->addr, requested_size); - - area->flags |= VM_KASAN; - /* * We need to be careful about inter-cpu effects here. Consider: * @@ -843,12 +841,23 @@ int kasan_populate_vmalloc(unsigned long requested_size, struct vm_struct *area) * Poison the shadow for a vmalloc region. Called as part of the * freeing process at the time the region is freed. */ -void kasan_poison_vmalloc(void *start, unsigned long size) +void kasan_poison_vmalloc(const void *start, unsigned long size) { + if (!is_vmalloc_or_module_addr(start)) + return; + size = round_up(size, KASAN_SHADOW_SCALE_SIZE); kasan_poison_shadow(start, size, KASAN_VMALLOC_INVALID); } +void kasan_unpoison_vmalloc(const void *start, unsigned long size) +{ + if (!is_vmalloc_or_module_addr(start)) + return; + + kasan_unpoison_shadow(start, size); +} + static int kasan_depopulate_vmalloc_pte(pte_t *ptep, unsigned long addr, void *unused) { diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 4d3b3d60d893..6e865cea846c 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1061,6 +1061,26 @@ __alloc_vmap_area(unsigned long size, unsigned long align, return nva_start_addr; } +/* + * Free a region of KVA allocated by alloc_vmap_area + */ +static void free_vmap_area(struct vmap_area *va) +{ + /* + * Remove from the busy tree/list. + */ + spin_lock(&vmap_area_lock); + unlink_va(va, &vmap_area_root); + spin_unlock(&vmap_area_lock); + + /* + * Insert/Merge it back to the free tree/list. + */ + spin_lock(&free_vmap_area_lock); + merge_or_add_vmap_area(va, &free_vmap_area_root, &free_vmap_area_list); + spin_unlock(&free_vmap_area_lock); +} + /* * Allocate a region of KVA of the specified size and alignment, within the * vstart and vend. @@ -1073,6 +1093,7 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, struct vmap_area *va, *pva; unsigned long addr; int purged = 0; + int ret; BUG_ON(!size); BUG_ON(offset_in_page(size)); @@ -1139,6 +1160,7 @@ retry: va->va_end = addr + size; va->vm = NULL; + spin_lock(&vmap_area_lock); insert_vmap_area(va, &vmap_area_root, &vmap_area_list); spin_unlock(&vmap_area_lock); @@ -1147,6 +1169,12 @@ retry: BUG_ON(va->va_start < vstart); BUG_ON(va->va_end > vend); + ret = kasan_populate_vmalloc(addr, size); + if (ret) { + free_vmap_area(va); + return ERR_PTR(ret); + } + return va; overflow: @@ -1185,26 +1213,6 @@ int unregister_vmap_purge_notifier(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(unregister_vmap_purge_notifier); -/* - * Free a region of KVA allocated by alloc_vmap_area - */ -static void free_vmap_area(struct vmap_area *va) -{ - /* - * Remove from the busy tree/list. - */ - spin_lock(&vmap_area_lock); - unlink_va(va, &vmap_area_root); - spin_unlock(&vmap_area_lock); - - /* - * Insert/Merge it back to the free tree/list. - */ - spin_lock(&free_vmap_area_lock); - merge_or_add_vmap_area(va, &free_vmap_area_root, &free_vmap_area_list); - spin_unlock(&free_vmap_area_lock); -} - /* * Clear the pagetable entries of a given vmap_area */ @@ -1771,6 +1779,8 @@ void vm_unmap_ram(const void *mem, unsigned int count) BUG_ON(addr > VMALLOC_END); BUG_ON(!PAGE_ALIGNED(addr)); + kasan_poison_vmalloc(mem, size); + if (likely(count <= VMAP_MAX_ALLOC)) { debug_check_no_locks_freed(mem, size); vb_free(mem, size); @@ -1821,6 +1831,9 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t pro addr = va->va_start; mem = (void *)addr; } + + kasan_unpoison_vmalloc(mem, size); + if (vmap_page_range(addr, addr + size, prot, pages) < 0) { vm_unmap_ram(mem, count); return NULL; @@ -2075,6 +2088,7 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, { struct vmap_area *va; struct vm_struct *area; + unsigned long requested_size = size; BUG_ON(in_interrupt()); size = PAGE_ALIGN(size); @@ -2098,23 +2112,9 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, return NULL; } - setup_vmalloc_vm(area, va, flags, caller); + kasan_unpoison_vmalloc((void *)va->va_start, requested_size); - /* - * For KASAN, if we are in vmalloc space, we need to cover the shadow - * area with real memory. If we come here through VM_ALLOC, this is - * done by a higher level function that has access to the true size, - * which might not be a full page. - * - * We assume module space comes via VM_ALLOC path. - */ - if (is_vmalloc_addr(area->addr) && !(area->flags & VM_ALLOC)) { - if (kasan_populate_vmalloc(area->size, area)) { - unmap_vmap_area(va); - kfree(area); - return NULL; - } - } + setup_vmalloc_vm(area, va, flags, caller); return area; } @@ -2293,8 +2293,7 @@ static void __vunmap(const void *addr, int deallocate_pages) debug_check_no_locks_freed(area->addr, get_vm_area_size(area)); debug_check_no_obj_freed(area->addr, get_vm_area_size(area)); - if (area->flags & VM_KASAN) - kasan_poison_vmalloc(area->addr, area->size); + kasan_poison_vmalloc(area->addr, area->size); vm_remove_mappings(area, deallocate_pages); @@ -2539,7 +2538,7 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, if (!size || (size >> PAGE_SHIFT) > totalram_pages()) goto fail; - area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNINITIALIZED | + area = __get_vm_area_node(real_size, align, VM_ALLOC | VM_UNINITIALIZED | vm_flags, start, end, node, gfp_mask, caller); if (!area) goto fail; @@ -2548,11 +2547,6 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, if (!addr) return NULL; - if (is_vmalloc_or_module_addr(area->addr)) { - if (kasan_populate_vmalloc(real_size, area)) - return NULL; - } - /* * In this function, newly allocated vm_struct has VM_UNINITIALIZED * flag. It means that vm_struct is not fully initialized. @@ -3437,7 +3431,8 @@ retry: /* populate the shadow space outside of the lock */ for (area = 0; area < nr_vms; area++) { /* assume success here */ - kasan_populate_vmalloc(sizes[area], vms[area]); + kasan_populate_vmalloc(vas[area]->va_start, sizes[area]); + kasan_unpoison_vmalloc((void *)vms[area]->addr, sizes[area]); } kfree(vas); -- cgit v1.2.3-71-gd317 From be1db4753ee6a0db80a900df9dbbf6ad2acc4bd1 Mon Sep 17 00:00:00 2001 From: Daniel Axtens Date: Tue, 17 Dec 2019 20:51:41 -0800 Subject: mm/memory.c: add apply_to_existing_page_range() helper apply_to_page_range() takes an address range, and if any parts of it are not covered by the existing page table hierarchy, it allocates memory to fill them in. In some use cases, this is not what we want - we want to be able to operate exclusively on PTEs that are already in the tables. Add apply_to_existing_page_range() for this. Adjust the walker functions for apply_to_page_range to take 'create', which switches them between the old and new modes. This will be used in KASAN vmalloc. [akpm@linux-foundation.org: reduce code duplication] [akpm@linux-foundation.org: s/apply_to_existing_pages/apply_to_existing_page_range/] [akpm@linux-foundation.org: initialize __apply_to_page_range::err] Link: http://lkml.kernel.org/r/20191205140407.1874-1-dja@axtens.net Signed-off-by: Daniel Axtens Cc: Dmitry Vyukov Cc: Uladzislau Rezki (Sony) Cc: Alexander Potapenko Cc: Daniel Axtens Cc: Qian Cai Cc: Andrey Ryabinin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 ++ mm/memory.c | 136 ++++++++++++++++++++++++++++++++++++----------------- 2 files changed, 97 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index c97ea3b694e6..80a9162b406c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2621,6 +2621,9 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data); extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); +extern int apply_to_existing_page_range(struct mm_struct *mm, + unsigned long address, unsigned long size, + pte_fn_t fn, void *data); #ifdef CONFIG_PAGE_POISONING extern bool page_poisoning_enabled(void); diff --git a/mm/memory.c b/mm/memory.c index 606da187d1de..45442d9a4f52 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2021,26 +2021,34 @@ EXPORT_SYMBOL(vm_iomap_memory); static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, - pte_fn_t fn, void *data) + pte_fn_t fn, void *data, bool create) { pte_t *pte; - int err; + int err = 0; spinlock_t *uninitialized_var(ptl); - pte = (mm == &init_mm) ? - pte_alloc_kernel(pmd, addr) : - pte_alloc_map_lock(mm, pmd, addr, &ptl); - if (!pte) - return -ENOMEM; + if (create) { + pte = (mm == &init_mm) ? + pte_alloc_kernel(pmd, addr) : + pte_alloc_map_lock(mm, pmd, addr, &ptl); + if (!pte) + return -ENOMEM; + } else { + pte = (mm == &init_mm) ? + pte_offset_kernel(pmd, addr) : + pte_offset_map_lock(mm, pmd, addr, &ptl); + } BUG_ON(pmd_huge(*pmd)); arch_enter_lazy_mmu_mode(); do { - err = fn(pte++, addr, data); - if (err) - break; + if (create || !pte_none(*pte)) { + err = fn(pte++, addr, data); + if (err) + break; + } } while (addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); @@ -2052,77 +2060,95 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud, unsigned long addr, unsigned long end, - pte_fn_t fn, void *data) + pte_fn_t fn, void *data, bool create) { pmd_t *pmd; unsigned long next; - int err; + int err = 0; BUG_ON(pud_huge(*pud)); - pmd = pmd_alloc(mm, pud, addr); - if (!pmd) - return -ENOMEM; + if (create) { + pmd = pmd_alloc(mm, pud, addr); + if (!pmd) + return -ENOMEM; + } else { + pmd = pmd_offset(pud, addr); + } do { next = pmd_addr_end(addr, end); - err = apply_to_pte_range(mm, pmd, addr, next, fn, data); - if (err) - break; + if (create || !pmd_none_or_clear_bad(pmd)) { + err = apply_to_pte_range(mm, pmd, addr, next, fn, data, + create); + if (err) + break; + } } while (pmd++, addr = next, addr != end); return err; } static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, - pte_fn_t fn, void *data) + pte_fn_t fn, void *data, bool create) { pud_t *pud; unsigned long next; - int err; + int err = 0; - pud = pud_alloc(mm, p4d, addr); - if (!pud) - return -ENOMEM; + if (create) { + pud = pud_alloc(mm, p4d, addr); + if (!pud) + return -ENOMEM; + } else { + pud = pud_offset(p4d, addr); + } do { next = pud_addr_end(addr, end); - err = apply_to_pmd_range(mm, pud, addr, next, fn, data); - if (err) - break; + if (create || !pud_none_or_clear_bad(pud)) { + err = apply_to_pmd_range(mm, pud, addr, next, fn, data, + create); + if (err) + break; + } } while (pud++, addr = next, addr != end); return err; } static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd, unsigned long addr, unsigned long end, - pte_fn_t fn, void *data) + pte_fn_t fn, void *data, bool create) { p4d_t *p4d; unsigned long next; - int err; + int err = 0; - p4d = p4d_alloc(mm, pgd, addr); - if (!p4d) - return -ENOMEM; + if (create) { + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return -ENOMEM; + } else { + p4d = p4d_offset(pgd, addr); + } do { next = p4d_addr_end(addr, end); - err = apply_to_pud_range(mm, p4d, addr, next, fn, data); - if (err) - break; + if (create || !p4d_none_or_clear_bad(p4d)) { + err = apply_to_pud_range(mm, p4d, addr, next, fn, data, + create); + if (err) + break; + } } while (p4d++, addr = next, addr != end); return err; } -/* - * Scan a region of virtual memory, filling in page tables as necessary - * and calling a provided function on each leaf page table. - */ -int apply_to_page_range(struct mm_struct *mm, unsigned long addr, - unsigned long size, pte_fn_t fn, void *data) +static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr, + unsigned long size, pte_fn_t fn, + void *data, bool create) { pgd_t *pgd; unsigned long next; unsigned long end = addr + size; - int err; + int err = 0; if (WARN_ON(addr >= end)) return -EINVAL; @@ -2130,15 +2156,41 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, pgd = pgd_offset(mm, addr); do { next = pgd_addr_end(addr, end); - err = apply_to_p4d_range(mm, pgd, addr, next, fn, data); + if (!create && pgd_none_or_clear_bad(pgd)) + continue; + err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create); if (err) break; } while (pgd++, addr = next, addr != end); return err; } + +/* + * Scan a region of virtual memory, filling in page tables as necessary + * and calling a provided function on each leaf page table. + */ +int apply_to_page_range(struct mm_struct *mm, unsigned long addr, + unsigned long size, pte_fn_t fn, void *data) +{ + return __apply_to_page_range(mm, addr, size, fn, data, true); +} EXPORT_SYMBOL_GPL(apply_to_page_range); +/* + * Scan a region of virtual memory, calling a provided function on + * each leaf page table where it exists. + * + * Unlike apply_to_page_range, this does _not_ fill in page tables + * where they are absent. + */ +int apply_to_existing_page_range(struct mm_struct *mm, unsigned long addr, + unsigned long size, pte_fn_t fn, void *data) +{ + return __apply_to_page_range(mm, addr, size, fn, data, false); +} +EXPORT_SYMBOL_GPL(apply_to_existing_page_range); + /* * handle_pte_fault chooses page fault handler according to an entry which was * read non-atomically. Before making any commitment, on those architectures -- cgit v1.2.3-71-gd317 From 1f26c0d3d24125992ab0026b0dab16c08df947c7 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 16 Dec 2019 18:52:45 -0800 Subject: net: fix kernel-doc warning in Fix missing '*' kernel-doc notation that causes this warning: ../include/linux/netdevice.h:1779: warning: bad line: spinlock Fixes: ab92d68fc22f ("net: core: add generic lockdep keys") Signed-off-by: Randy Dunlap Cc: Taehee Yoo Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9ef20389622d..ae5e260911e2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1775,7 +1775,7 @@ enum netdev_priv_flags { * for hardware timestamping * @sfp_bus: attached &struct sfp_bus structure. * @qdisc_tx_busylock_key: lockdep class annotating Qdisc->busylock - spinlock + * spinlock * @qdisc_running_key: lockdep class annotating Qdisc->running seqcount * @qdisc_xmit_lock_key: lockdep class annotating * netdev_queue->_xmit_lock spinlock -- cgit v1.2.3-71-gd317 From 0aa4d016c043d16a282e7e93edf6213a7b954c90 Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Tue, 17 Dec 2019 18:07:41 +0100 Subject: of: mdio: export of_mdiobus_child_is_phy This patch exports of_mdiobus_child_is_phy, allowing to check if a child node is a network PHY. Signed-off-by: Antoine Tenart Signed-off-by: David S. Miller --- drivers/of/of_mdio.c | 3 ++- include/linux/of_mdio.h | 6 ++++++ 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index c6b87ce2b0cc..fc757ef6eadc 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -162,7 +162,7 @@ static const struct of_device_id whitelist_phys[] = { * A device which is not a phy is expected to have a compatible string * indicating what sort of device it is. */ -static bool of_mdiobus_child_is_phy(struct device_node *child) +bool of_mdiobus_child_is_phy(struct device_node *child) { u32 phy_id; @@ -187,6 +187,7 @@ static bool of_mdiobus_child_is_phy(struct device_node *child) return false; } +EXPORT_SYMBOL(of_mdiobus_child_is_phy); /** * of_mdiobus_register - Register mii_bus and create PHYs from the device tree diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 99cefe6f5edb..79bc82e30c02 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -12,6 +12,7 @@ #include #if IS_ENABLED(CONFIG_OF_MDIO) +extern bool of_mdiobus_child_is_phy(struct device_node *child); extern int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np); extern struct phy_device *of_phy_find_device(struct device_node *phy_np); extern struct phy_device *of_phy_connect(struct net_device *dev, @@ -54,6 +55,11 @@ static inline int of_mdio_parse_addr(struct device *dev, } #else /* CONFIG_OF_MDIO */ +static bool of_mdiobus_child_is_phy(struct device_node *child) +{ + return false; +} + static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) { /* -- cgit v1.2.3-71-gd317 From d2ed49cf6c13e379c5819aa5ac20e1f9674ebc89 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 19 Dec 2019 23:24:47 +0000 Subject: mod_devicetable: fix PHY module format When a PHY is probed, if the top bit is set, we end up requesting a module with the string "mdio:-10101110000000100101000101010001" - the top bit is printed to a signed -1 value. This leads to the module not being loaded. Fix the module format string and the macro generating the values for it to ensure that we only print unsigned types and the top bit is always 0/1. We correctly end up with "mdio:10101110000000100101000101010001". Fixes: 8626d3b43280 ("phylib: Support phy module autoloading") Reviewed-by: Andrew Lunn Signed-off-by: Russell King Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/mod_devicetable.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 5714fd35a83c..e3596db077dc 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -587,9 +587,9 @@ struct platform_device_id { #define MDIO_NAME_SIZE 32 #define MDIO_MODULE_PREFIX "mdio:" -#define MDIO_ID_FMT "%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d" +#define MDIO_ID_FMT "%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u%u" #define MDIO_ID_ARGS(_id) \ - (_id)>>31, ((_id)>>30) & 1, ((_id)>>29) & 1, ((_id)>>28) & 1, \ + ((_id)>>31) & 1, ((_id)>>30) & 1, ((_id)>>29) & 1, ((_id)>>28) & 1, \ ((_id)>>27) & 1, ((_id)>>26) & 1, ((_id)>>25) & 1, ((_id)>>24) & 1, \ ((_id)>>23) & 1, ((_id)>>22) & 1, ((_id)>>21) & 1, ((_id)>>20) & 1, \ ((_id)>>19) & 1, ((_id)>>18) & 1, ((_id)>>17) & 1, ((_id)>>16) & 1, \ -- cgit v1.2.3-71-gd317 From 7d49a32a66d2215c5b3bf9bc67c9036ea9904111 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 19 Dec 2019 23:24:52 +0000 Subject: net: phy: ensure that phy IDs are correctly typed PHY IDs are 32-bit unsigned quantities. Ensure that they are always treated as such, and not passed around as "int"s. Fixes: 13d0ab6750b2 ("net: phy: check return code when requesting PHY driver module") Signed-off-by: Russell King Reviewed-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 8 ++++---- include/linux/phy.h | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 0887ed2bb050..b13c52873ef5 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -553,7 +553,7 @@ static const struct device_type mdio_bus_phy_type = { .pm = MDIO_BUS_PHY_PM_OPS, }; -static int phy_request_driver_module(struct phy_device *dev, int phy_id) +static int phy_request_driver_module(struct phy_device *dev, u32 phy_id) { int ret; @@ -565,15 +565,15 @@ static int phy_request_driver_module(struct phy_device *dev, int phy_id) * then modprobe isn't available. */ if (IS_ENABLED(CONFIG_MODULES) && ret < 0 && ret != -ENOENT) { - phydev_err(dev, "error %d loading PHY driver module for ID 0x%08x\n", - ret, phy_id); + phydev_err(dev, "error %d loading PHY driver module for ID 0x%08lx\n", + ret, (unsigned long)phy_id); return ret; } return 0; } -struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id, +struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, bool is_c45, struct phy_c45_device_ids *c45_ids) { diff --git a/include/linux/phy.h b/include/linux/phy.h index 5032d453ac66..dd4a91f1feaa 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1000,7 +1000,7 @@ int phy_modify_paged_changed(struct phy_device *phydev, int page, u32 regnum, int phy_modify_paged(struct phy_device *phydev, int page, u32 regnum, u16 mask, u16 set); -struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id, +struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, bool is_c45, struct phy_c45_device_ids *c45_ids); #if IS_ENABLED(CONFIG_PHYLIB) -- cgit v1.2.3-71-gd317 From 8385d756e114f2df8568e508902d5f9850817ffb Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Fri, 13 Dec 2019 09:04:08 +0100 Subject: libata: Fix retrieving of active qcs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ata_qc_complete_multiple() is called with a mask of the still active tags. mv_sata doesn't have this information directly and instead calculates the still active tags from the started tags (ap->qc_active) and the finished tags as (ap->qc_active ^ done_mask) Since 28361c40368 the hw_tag and tag are no longer the same and the equation is no longer valid. In ata_exec_internal_sg() ap->qc_active is initialized as 1ULL << ATA_TAG_INTERNAL, but in hardware tag 0 is started and this will be in done_mask on completion. ap->qc_active ^ done_mask becomes 0x100000000 ^ 0x1 = 0x100000001 and thus tag 0 used as the internal tag will never be reported as completed. This is fixed by introducing ata_qc_get_active() which returns the active hardware tags and calling it where appropriate. This is tested on mv_sata, but sata_fsl and sata_nv suffer from the same problem. There is another case in sata_nv that most likely needs fixing as well, but this looks a little different, so I wasn't confident enough to change that. Fixes: 28361c403683 ("libata: add extra internal command") Cc: stable@vger.kernel.org Tested-by: Pali Rohár Signed-off-by: Sascha Hauer Add missing export of ata_qc_get_active(), as per Pali. Signed-off-by: Jens Axboe --- drivers/ata/libata-core.c | 24 ++++++++++++++++++++++++ drivers/ata/sata_fsl.c | 2 +- drivers/ata/sata_mv.c | 2 +- drivers/ata/sata_nv.c | 2 +- include/linux/libata.h | 1 + 5 files changed, 28 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index e9017c570bc5..6f4ab5c5b52d 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -5328,6 +5328,30 @@ void ata_qc_complete(struct ata_queued_cmd *qc) } } +/** + * ata_qc_get_active - get bitmask of active qcs + * @ap: port in question + * + * LOCKING: + * spin_lock_irqsave(host lock) + * + * RETURNS: + * Bitmask of active qcs + */ +u64 ata_qc_get_active(struct ata_port *ap) +{ + u64 qc_active = ap->qc_active; + + /* ATA_TAG_INTERNAL is sent to hw as tag 0 */ + if (qc_active & (1ULL << ATA_TAG_INTERNAL)) { + qc_active |= (1 << 0); + qc_active &= ~(1ULL << ATA_TAG_INTERNAL); + } + + return qc_active; +} +EXPORT_SYMBOL_GPL(ata_qc_get_active); + /** * ata_qc_complete_multiple - Complete multiple qcs successfully * @ap: port in question diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index 9239615d8a04..d55ee244d693 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -1280,7 +1280,7 @@ static void sata_fsl_host_intr(struct ata_port *ap) i, ioread32(hcr_base + CC), ioread32(hcr_base + CA)); } - ata_qc_complete_multiple(ap, ap->qc_active ^ done_mask); + ata_qc_complete_multiple(ap, ata_qc_get_active(ap) ^ done_mask); return; } else if ((ap->qc_active & (1ULL << ATA_TAG_INTERNAL))) { diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index 277f11909fc1..d7228f8e9297 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -2829,7 +2829,7 @@ static void mv_process_crpb_entries(struct ata_port *ap, struct mv_port_priv *pp } if (work_done) { - ata_qc_complete_multiple(ap, ap->qc_active ^ done_mask); + ata_qc_complete_multiple(ap, ata_qc_get_active(ap) ^ done_mask); /* Update the software queue position index in hardware */ writelfl((pp->crpb_dma & EDMA_RSP_Q_BASE_LO_MASK) | diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c index f3e62f5528bd..eb9dc14e5147 100644 --- a/drivers/ata/sata_nv.c +++ b/drivers/ata/sata_nv.c @@ -984,7 +984,7 @@ static irqreturn_t nv_adma_interrupt(int irq, void *dev_instance) check_commands = 0; check_commands &= ~(1 << pos); } - ata_qc_complete_multiple(ap, ap->qc_active ^ done_mask); + ata_qc_complete_multiple(ap, ata_qc_get_active(ap) ^ done_mask); } } diff --git a/include/linux/libata.h b/include/linux/libata.h index d3bbfddf616a..2dbde119721d 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1175,6 +1175,7 @@ extern unsigned int ata_do_dev_read_id(struct ata_device *dev, struct ata_taskfile *tf, u16 *id); extern void ata_qc_complete(struct ata_queued_cmd *qc); extern int ata_qc_complete_multiple(struct ata_port *ap, u64 qc_active); +extern u64 ata_qc_get_active(struct ata_port *ap); extern void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd); extern int ata_std_bios_param(struct scsi_device *sdev, struct block_device *bdev, -- cgit v1.2.3-71-gd317 From 84b032dbfdf1c139cd2b864e43959510646975f8 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 10 Dec 2019 10:53:44 -0800 Subject: ata: libahci_platform: Export again ahci_platform_able_phys() This reverts commit 6bb86fefa086faba7b60bb452300b76a47cde1a5 ("libahci_platform: Staticize ahci_platform_able_phys()") we are going to need ahci_platform_{enable,disable}_phys() in a subsequent commit for ahci_brcm.c in order to properly control the PHY initialization order. Also make sure the function prototypes are declared in include/linux/ahci_platform.h as a result. Cc: stable@vger.kernel.org Reviewed-by: Hans de Goede Signed-off-by: Florian Fainelli Signed-off-by: Jens Axboe --- drivers/ata/libahci_platform.c | 6 ++++-- include/linux/ahci_platform.h | 2 ++ 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c index 8befce036af8..129556fcf6be 100644 --- a/drivers/ata/libahci_platform.c +++ b/drivers/ata/libahci_platform.c @@ -43,7 +43,7 @@ EXPORT_SYMBOL_GPL(ahci_platform_ops); * RETURNS: * 0 on success otherwise a negative error code */ -static int ahci_platform_enable_phys(struct ahci_host_priv *hpriv) +int ahci_platform_enable_phys(struct ahci_host_priv *hpriv) { int rc, i; @@ -74,6 +74,7 @@ disable_phys: } return rc; } +EXPORT_SYMBOL_GPL(ahci_platform_enable_phys); /** * ahci_platform_disable_phys - Disable PHYs @@ -81,7 +82,7 @@ disable_phys: * * This function disables all PHYs found in hpriv->phys. */ -static void ahci_platform_disable_phys(struct ahci_host_priv *hpriv) +void ahci_platform_disable_phys(struct ahci_host_priv *hpriv) { int i; @@ -90,6 +91,7 @@ static void ahci_platform_disable_phys(struct ahci_host_priv *hpriv) phy_exit(hpriv->phys[i]); } } +EXPORT_SYMBOL_GPL(ahci_platform_disable_phys); /** * ahci_platform_enable_clks - Enable platform clocks diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h index 6782f0d45ebe..49e5383d4222 100644 --- a/include/linux/ahci_platform.h +++ b/include/linux/ahci_platform.h @@ -19,6 +19,8 @@ struct ahci_host_priv; struct platform_device; struct scsi_host_template; +int ahci_platform_enable_phys(struct ahci_host_priv *hpriv); +void ahci_platform_disable_phys(struct ahci_host_priv *hpriv); int ahci_platform_enable_clks(struct ahci_host_priv *hpriv); void ahci_platform_disable_clks(struct ahci_host_priv *hpriv); int ahci_platform_enable_regulators(struct ahci_host_priv *hpriv); -- cgit v1.2.3-71-gd317