From 814abfabef3ceed390c10d06a0cc69a86454b6cf Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 17 Jul 2017 09:27:07 -0700 Subject: xdp: add bpf_redirect helper function This adds support for a bpf_redirect helper function to the XDP infrastructure. For now this only supports redirecting to the egress path of a port. In order to support drivers handling a xdp_buff natively this patches uses a new ndo operation ndo_xdp_xmit() that takes pushes a xdp_buff to the specified device. If the program specifies either (a) an unknown device or (b) a device that does not support the operation a BPF warning is thrown and the XDP_ABORTED error code is returned. Signed-off-by: John Fastabend Acked-by: Daniel Borkmann Acked-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e99e3e6f8b37..4dbb7a3f4677 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -717,6 +717,7 @@ enum xdp_action { XDP_DROP, XDP_PASS, XDP_TX, + XDP_REDIRECT, }; /* user accessible metadata for XDP packet hook -- cgit v1.2.3-71-gd317 From 546ac1ffb70d25b56c1126940e5ec639c4dd7413 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 17 Jul 2017 09:28:56 -0700 Subject: bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend Acked-by: Daniel Borkmann Acked-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/bpf_types.h | 3 + include/uapi/linux/bpf.h | 1 + kernel/bpf/Makefile | 3 + kernel/bpf/devmap.c | 264 ++++++++++++++++++++++++++++++++ kernel/bpf/verifier.c | 8 + tools/testing/selftests/bpf/test_maps.c | 15 ++ 6 files changed, 294 insertions(+) create mode 100644 kernel/bpf/devmap.c (limited to 'include/uapi/linux') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 3d137c33d664..b1e1035ca24b 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -35,3 +35,6 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) +#ifdef CONFIG_NET +BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) +#endif diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4dbb7a3f4677..ecbb0e7e15bc 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -104,6 +104,7 @@ enum bpf_map_type { BPF_MAP_TYPE_LPM_TRIE, BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_HASH_OF_MAPS, + BPF_MAP_TYPE_DEVMAP, }; enum bpf_prog_type { diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index e1e5e658f2db..48e92705be59 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -2,6 +2,9 @@ obj-y := core.o obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o +ifeq ($(CONFIG_NET),y) +obj-$(CONFIG_BPF_SYSCALL) += devmap.o +endif ifeq ($(CONFIG_PERF_EVENTS),y) obj-$(CONFIG_BPF_SYSCALL) += stackmap.o endif diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c new file mode 100644 index 000000000000..1a878356bd37 --- /dev/null +++ b/kernel/bpf/devmap.c @@ -0,0 +1,264 @@ +/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +/* Devmaps primary use is as a backend map for XDP BPF helper call + * bpf_redirect_map(). Because XDP is mostly concerned with performance we + * spent some effort to ensure the datapath with redirect maps does not use + * any locking. This is a quick note on the details. + * + * We have three possible paths to get into the devmap control plane bpf + * syscalls, bpf programs, and driver side xmit/flush operations. A bpf syscall + * will invoke an update, delete, or lookup operation. To ensure updates and + * deletes appear atomic from the datapath side xchg() is used to modify the + * netdev_map array. Then because the datapath does a lookup into the netdev_map + * array (read-only) from an RCU critical section we use call_rcu() to wait for + * an rcu grace period before free'ing the old data structures. This ensures the + * datapath always has a valid copy. However, the datapath does a "flush" + * operation that pushes any pending packets in the driver outside the RCU + * critical section. Each bpf_dtab_netdev tracks these pending operations using + * an atomic per-cpu bitmap. The bpf_dtab_netdev object will not be destroyed + * until all bits are cleared indicating outstanding flush operations have + * completed. + * + * BPF syscalls may race with BPF program calls on any of the update, delete + * or lookup operations. As noted above the xchg() operation also keep the + * netdev_map consistent in this case. From the devmap side BPF programs + * calling into these operations are the same as multiple user space threads + * making system calls. + */ +#include +#include +#include +#include +#include "percpu_freelist.h" +#include "bpf_lru_list.h" +#include "map_in_map.h" + +struct bpf_dtab_netdev { + struct net_device *dev; + int key; + struct rcu_head rcu; + struct bpf_dtab *dtab; +}; + +struct bpf_dtab { + struct bpf_map map; + struct bpf_dtab_netdev **netdev_map; +}; + +static struct bpf_map *dev_map_alloc(union bpf_attr *attr) +{ + struct bpf_dtab *dtab; + u64 cost; + int err; + + /* check sanity of attributes */ + if (attr->max_entries == 0 || attr->key_size != 4 || + attr->value_size != 4 || attr->map_flags) + return ERR_PTR(-EINVAL); + + /* if value_size is bigger, the user space won't be able to + * access the elements. + */ + if (attr->value_size > KMALLOC_MAX_SIZE) + return ERR_PTR(-E2BIG); + + dtab = kzalloc(sizeof(*dtab), GFP_USER); + if (!dtab) + return ERR_PTR(-ENOMEM); + + /* mandatory map attributes */ + dtab->map.map_type = attr->map_type; + dtab->map.key_size = attr->key_size; + dtab->map.value_size = attr->value_size; + dtab->map.max_entries = attr->max_entries; + dtab->map.map_flags = attr->map_flags; + + err = -ENOMEM; + + /* make sure page count doesn't overflow */ + cost = (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *); + if (cost >= U32_MAX - PAGE_SIZE) + goto free_dtab; + + dtab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + /* if map size is larger than memlock limit, reject it early */ + err = bpf_map_precharge_memlock(dtab->map.pages); + if (err) + goto free_dtab; + + dtab->netdev_map = bpf_map_area_alloc(dtab->map.max_entries * + sizeof(struct bpf_dtab_netdev *)); + if (!dtab->netdev_map) + goto free_dtab; + + return &dtab->map; + +free_dtab: + kfree(dtab); + return ERR_PTR(err); +} + +static void dev_map_free(struct bpf_map *map) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + int i; + + /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, + * so the programs (can be more than one that used this map) were + * disconnected from events. Wait for outstanding critical sections in + * these programs to complete. The rcu critical section only guarantees + * no further reads against netdev_map. It does __not__ ensure pending + * flush operations (if any) are complete. + */ + synchronize_rcu(); + + for (i = 0; i < dtab->map.max_entries; i++) { + struct bpf_dtab_netdev *dev; + + dev = dtab->netdev_map[i]; + if (!dev) + continue; + + dev_put(dev->dev); + kfree(dev); + } + + /* At this point bpf program is detached and all pending operations + * _must_ be complete + */ + bpf_map_area_free(dtab->netdev_map); + kfree(dtab); +} + +static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + u32 index = key ? *(u32 *)key : U32_MAX; + u32 *next = (u32 *)next_key; + + if (index >= dtab->map.max_entries) { + *next = 0; + return 0; + } + + if (index == dtab->map.max_entries - 1) + return -ENOENT; + + *next = index + 1; + return 0; +} + +/* rcu_read_lock (from syscall and BPF contexts) ensures that if a delete and/or + * update happens in parallel here a dev_put wont happen until after reading the + * ifindex. + */ +static void *dev_map_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct bpf_dtab_netdev *dev; + u32 i = *(u32 *)key; + + if (i >= map->max_entries) + return NULL; + + dev = READ_ONCE(dtab->netdev_map[i]); + return dev ? &dev->dev->ifindex : NULL; +} + +static void __dev_map_entry_free(struct rcu_head *rcu) +{ + struct bpf_dtab_netdev *old_dev; + + old_dev = container_of(rcu, struct bpf_dtab_netdev, rcu); + dev_put(old_dev->dev); + kfree(old_dev); +} + +static int dev_map_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct bpf_dtab_netdev *old_dev; + int k = *(u32 *)key; + + if (k >= map->max_entries) + return -EINVAL; + + /* Use synchronize_rcu() here to ensure any rcu critical sections + * have completed, but this does not guarantee a flush has happened + * yet. Because driver side rcu_read_lock/unlock only protects the + * running XDP program. However, for pending flush operations the + * dev and ctx are stored in another per cpu map. And additionally, + * the driver tear down ensures all soft irqs are complete before + * removing the net device in the case of dev_put equals zero. + */ + old_dev = xchg(&dtab->netdev_map[k], NULL); + if (old_dev) + call_rcu(&old_dev->rcu, __dev_map_entry_free); + return 0; +} + +static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct net *net = current->nsproxy->net_ns; + struct bpf_dtab_netdev *dev, *old_dev; + u32 i = *(u32 *)key; + u32 ifindex = *(u32 *)value; + + if (unlikely(map_flags > BPF_EXIST)) + return -EINVAL; + + if (unlikely(i >= dtab->map.max_entries)) + return -E2BIG; + + if (unlikely(map_flags == BPF_NOEXIST)) + return -EEXIST; + + if (!ifindex) { + dev = NULL; + } else { + dev = kmalloc(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN); + if (!dev) + return -ENOMEM; + + dev->dev = dev_get_by_index(net, ifindex); + if (!dev->dev) { + kfree(dev); + return -EINVAL; + } + + dev->key = i; + dev->dtab = dtab; + } + + /* Use call_rcu() here to ensure rcu critical sections have completed + * Remembering the driver side flush operation will happen before the + * net device is removed. + */ + old_dev = xchg(&dtab->netdev_map[i], dev); + if (old_dev) + call_rcu(&old_dev->rcu, __dev_map_entry_free); + + return 0; +} + +const struct bpf_map_ops dev_map_ops = { + .map_alloc = dev_map_alloc, + .map_free = dev_map_free, + .map_get_next_key = dev_map_get_next_key, + .map_lookup_elem = dev_map_lookup_elem, + .map_update_elem = dev_map_update_elem, + .map_delete_elem = dev_map_delete_elem, +}; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6a86723c5b64..4016774d5cca 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1276,6 +1276,14 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) func_id != BPF_FUNC_current_task_under_cgroup) goto error; break; + /* devmap returns a pointer to a live net_device ifindex that we cannot + * allow to be modified from bpf side. So do not allow lookup elements + * for now. + */ + case BPF_MAP_TYPE_DEVMAP: + if (func_id == BPF_FUNC_map_lookup_elem) + goto error; + break; case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH_OF_MAPS: if (func_id != BPF_FUNC_map_lookup_elem) diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 79601c81e169..36d6ac3f0c1c 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -438,6 +438,21 @@ static void test_arraymap_percpu_many_keys(void) close(fd); } +static void test_devmap(int task, void *data) +{ + int next_key, fd; + __u32 key, value; + + fd = bpf_create_map(BPF_MAP_TYPE_DEVMAP, sizeof(key), sizeof(value), + 2, 0); + if (fd < 0) { + printf("Failed to create arraymap '%s'!\n", strerror(errno)); + exit(1); + } + + close(fd); +} + #define MAP_SIZE (32 * 1024) static void test_map_large(void) -- cgit v1.2.3-71-gd317 From 97f91a7cf04ff605845c20948b8a80e54cbd3376 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 17 Jul 2017 09:29:18 -0700 Subject: bpf: add bpf_redirect_map helper routine BPF programs can use the devmap with a bpf_redirect_map() helper routine to forward packets to netdevice in map. Signed-off-by: John Fastabend Signed-off-by: Jesper Dangaard Brouer Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf.h | 3 +++ include/uapi/linux/bpf.h | 8 +++++++- kernel/bpf/devmap.c | 12 +++++++++++ kernel/bpf/verifier.c | 4 ++++ net/core/filter.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 78 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b69e7a5869ff..d0d3281ac678 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -379,4 +379,7 @@ extern const struct bpf_func_proto bpf_get_stackid_proto; void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); +/* Map specifics */ +struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key); + #endif /* _LINUX_BPF_H */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index ecbb0e7e15bc..1106a8c4cd36 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -348,6 +348,11 @@ union bpf_attr { * @flags: bit 0 - if set, redirect to ingress instead of egress * other bits - reserved * Return: TC_ACT_REDIRECT + * int bpf_redirect_map(key, map, flags) + * redirect to endpoint in map + * @key: index in map to lookup + * @map: fd of map to do lookup in + * @flags: -- * * u32 bpf_get_route_realm(skb) * retrieve a dst's tclassid @@ -592,7 +597,8 @@ union bpf_attr { FN(get_socket_uid), \ FN(set_hash), \ FN(setsockopt), \ - FN(skb_adjust_room), + FN(skb_adjust_room), \ + FN(redirect_map), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 1a878356bd37..36dc13deb2e1 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -159,6 +159,18 @@ static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key) return 0; } +struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct bpf_dtab_netdev *dev; + + if (key >= map->max_entries) + return NULL; + + dev = READ_ONCE(dtab->netdev_map[key]); + return dev ? dev->dev : NULL; +} + /* rcu_read_lock (from syscall and BPF contexts) ensures that if a delete and/or * update happens in parallel here a dev_put wont happen until after reading the * ifindex. diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 4016774d5cca..df05d65f0c87 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1312,6 +1312,10 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY) goto error; break; + case BPF_FUNC_redirect_map: + if (map->map_type != BPF_MAP_TYPE_DEVMAP) + goto error; + break; default: break; } diff --git a/net/core/filter.c b/net/core/filter.c index e30d38b27f21..e93a558324b5 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1779,6 +1779,7 @@ static const struct bpf_func_proto bpf_clone_redirect_proto = { struct redirect_info { u32 ifindex; u32 flags; + struct bpf_map *map; }; static DEFINE_PER_CPU(struct redirect_info, redirect_info); @@ -1792,6 +1793,7 @@ BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags) ri->ifindex = ifindex; ri->flags = flags; + ri->map = NULL; return TC_ACT_REDIRECT; } @@ -1819,6 +1821,29 @@ static const struct bpf_func_proto bpf_redirect_proto = { .arg2_type = ARG_ANYTHING, }; +BPF_CALL_3(bpf_redirect_map, struct bpf_map *, map, u32, ifindex, u64, flags) +{ + struct redirect_info *ri = this_cpu_ptr(&redirect_info); + + if (unlikely(flags)) + return XDP_ABORTED; + + ri->ifindex = ifindex; + ri->flags = flags; + ri->map = map; + + return XDP_REDIRECT; +} + +static const struct bpf_func_proto bpf_redirect_map_proto = { + .func = bpf_redirect_map, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; + BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb) { return task_get_classid(skb); @@ -2423,14 +2448,39 @@ static int __bpf_tx_xdp(struct net_device *dev, struct xdp_buff *xdp) return -EOPNOTSUPP; } +int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp, + struct bpf_prog *xdp_prog) +{ + struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct bpf_map *map = ri->map; + struct net_device *fwd; + int err = -EINVAL; + + ri->ifindex = 0; + ri->map = NULL; + + fwd = __dev_map_lookup_elem(map, ri->ifindex); + if (!fwd) + goto out; + + trace_xdp_redirect(dev, fwd, xdp_prog, XDP_REDIRECT); + err = __bpf_tx_xdp(fwd, xdp); +out: + return err; +} + int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { struct redirect_info *ri = this_cpu_ptr(&redirect_info); struct net_device *fwd; + if (ri->map) + return xdp_do_redirect_map(dev, xdp, xdp_prog); + fwd = dev_get_by_index_rcu(dev_net(dev), ri->ifindex); ri->ifindex = 0; + ri->map = NULL; if (unlikely(!fwd)) { bpf_warn_invalid_xdp_redirect(ri->ifindex); return -EINVAL; @@ -3089,6 +3139,8 @@ xdp_func_proto(enum bpf_func_id func_id) return &bpf_xdp_adjust_head_proto; case BPF_FUNC_redirect: return &bpf_xdp_redirect_proto; + case BPF_FUNC_redirect_map: + return &bpf_redirect_map_proto; default: return bpf_base_func_proto(func_id); } -- cgit v1.2.3-71-gd317 From fc60a8b675bd9499c71716d21c238eed5092ddfc Mon Sep 17 00:00:00 2001 From: Andreas Färber Date: Sun, 9 Jul 2017 22:29:42 +0200 Subject: tty: serial: owl: Implement console driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Implement serial console driver to complement earlycon. Based on LeMaker linux-actions tree. Signed-off-by: Andreas Färber Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/Kconfig | 4 +- drivers/tty/serial/owl-uart.c | 635 ++++++++++++++++++++++++++++++++++++++- include/uapi/linux/serial_core.h | 1 + 3 files changed, 636 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 1f096e2bb398..b788fee54249 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -1689,7 +1689,7 @@ config SERIAL_MVEBU_CONSOLE Otherwise, say 'N'. config SERIAL_OWL - bool "Actions Semi Owl serial port support" + tristate "Actions Semi Owl serial port support" depends on ARCH_ACTIONS || COMPILE_TEST select SERIAL_CORE help @@ -1705,7 +1705,7 @@ config SERIAL_OWL_CONSOLE default y help Say 'Y' here if you wish to use Actions Semiconductor S500/S900 UART - as the system console. Only earlycon is implemented currently. + as the system console. endmenu diff --git a/drivers/tty/serial/owl-uart.c b/drivers/tty/serial/owl-uart.c index 1b8008797a1b..683b05478ade 100644 --- a/drivers/tty/serial/owl-uart.c +++ b/drivers/tty/serial/owl-uart.c @@ -20,6 +20,7 @@ * along with this program. If not, see . */ +#include #include #include #include @@ -28,22 +29,66 @@ #include #include #include +#include +#include + +#define OWL_UART_PORT_NUM 7 +#define OWL_UART_DEV_NAME "ttyOWL" #define OWL_UART_CTL 0x000 +#define OWL_UART_RXDAT 0x004 #define OWL_UART_TXDAT 0x008 #define OWL_UART_STAT 0x00c +#define OWL_UART_CTL_DWLS_MASK GENMASK(1, 0) +#define OWL_UART_CTL_DWLS_5BITS (0x0 << 0) +#define OWL_UART_CTL_DWLS_6BITS (0x1 << 0) +#define OWL_UART_CTL_DWLS_7BITS (0x2 << 0) +#define OWL_UART_CTL_DWLS_8BITS (0x3 << 0) +#define OWL_UART_CTL_STPS_2BITS BIT(2) +#define OWL_UART_CTL_PRS_MASK GENMASK(6, 4) +#define OWL_UART_CTL_PRS_NONE (0x0 << 4) +#define OWL_UART_CTL_PRS_ODD (0x4 << 4) +#define OWL_UART_CTL_PRS_MARK (0x5 << 4) +#define OWL_UART_CTL_PRS_EVEN (0x6 << 4) +#define OWL_UART_CTL_PRS_SPACE (0x7 << 4) +#define OWL_UART_CTL_AFE BIT(12) #define OWL_UART_CTL_TRFS_TX BIT(14) #define OWL_UART_CTL_EN BIT(15) +#define OWL_UART_CTL_RXDE BIT(16) +#define OWL_UART_CTL_TXDE BIT(17) #define OWL_UART_CTL_RXIE BIT(18) #define OWL_UART_CTL_TXIE BIT(19) +#define OWL_UART_CTL_LBEN BIT(20) #define OWL_UART_STAT_RIP BIT(0) #define OWL_UART_STAT_TIP BIT(1) +#define OWL_UART_STAT_RXER BIT(2) +#define OWL_UART_STAT_TFER BIT(3) +#define OWL_UART_STAT_RXST BIT(4) +#define OWL_UART_STAT_RFEM BIT(5) #define OWL_UART_STAT_TFFU BIT(6) -#define OWL_UART_STAT_TRFL_MASK (0x1f << 11) +#define OWL_UART_STAT_CTSS BIT(7) +#define OWL_UART_STAT_RTSS BIT(8) +#define OWL_UART_STAT_TFES BIT(10) +#define OWL_UART_STAT_TRFL_MASK GENMASK(16, 11) #define OWL_UART_STAT_UTBB BIT(17) +static struct uart_driver owl_uart_driver; + +struct owl_uart_info { + unsigned int tx_fifosize; +}; + +struct owl_uart_port { + struct uart_port port; + struct clk *clk; +}; + +#define to_owl_uart_port(prt) container_of(prt, struct owl_uart_port, prt) + +static struct owl_uart_port *owl_uart_ports[OWL_UART_PORT_NUM]; + static inline void owl_uart_write(struct uart_port *port, u32 val, unsigned int off) { writel(val, port->membase + off); @@ -54,6 +99,397 @@ static inline u32 owl_uart_read(struct uart_port *port, unsigned int off) return readl(port->membase + off); } +static void owl_uart_set_mctrl(struct uart_port *port, unsigned int mctrl) +{ + u32 ctl; + + ctl = owl_uart_read(port, OWL_UART_CTL); + + if (mctrl & TIOCM_LOOP) + ctl |= OWL_UART_CTL_LBEN; + else + ctl &= ~OWL_UART_CTL_LBEN; + + owl_uart_write(port, ctl, OWL_UART_CTL); +} + +static unsigned int owl_uart_get_mctrl(struct uart_port *port) +{ + unsigned int mctrl = TIOCM_CAR | TIOCM_DSR; + u32 stat, ctl; + + ctl = owl_uart_read(port, OWL_UART_CTL); + stat = owl_uart_read(port, OWL_UART_STAT); + if (stat & OWL_UART_STAT_RTSS) + mctrl |= TIOCM_RTS; + if ((stat & OWL_UART_STAT_CTSS) || !(ctl & OWL_UART_CTL_AFE)) + mctrl |= TIOCM_CTS; + return mctrl; +} + +static unsigned int owl_uart_tx_empty(struct uart_port *port) +{ + unsigned long flags; + u32 val; + unsigned int ret; + + spin_lock_irqsave(&port->lock, flags); + + val = owl_uart_read(port, OWL_UART_STAT); + ret = (val & OWL_UART_STAT_TFES) ? TIOCSER_TEMT : 0; + + spin_unlock_irqrestore(&port->lock, flags); + + return ret; +} + +static void owl_uart_stop_rx(struct uart_port *port) +{ + u32 val; + + val = owl_uart_read(port, OWL_UART_CTL); + val &= ~(OWL_UART_CTL_RXIE | OWL_UART_CTL_RXDE); + owl_uart_write(port, val, OWL_UART_CTL); + + val = owl_uart_read(port, OWL_UART_STAT); + val |= OWL_UART_STAT_RIP; + owl_uart_write(port, val, OWL_UART_STAT); +} + +static void owl_uart_stop_tx(struct uart_port *port) +{ + u32 val; + + val = owl_uart_read(port, OWL_UART_CTL); + val &= ~(OWL_UART_CTL_TXIE | OWL_UART_CTL_TXDE); + owl_uart_write(port, val, OWL_UART_CTL); + + val = owl_uart_read(port, OWL_UART_STAT); + val |= OWL_UART_STAT_TIP; + owl_uart_write(port, val, OWL_UART_STAT); +} + +static void owl_uart_start_tx(struct uart_port *port) +{ + u32 val; + + if (uart_tx_stopped(port)) { + owl_uart_stop_tx(port); + return; + } + + val = owl_uart_read(port, OWL_UART_STAT); + val |= OWL_UART_STAT_TIP; + owl_uart_write(port, val, OWL_UART_STAT); + + val = owl_uart_read(port, OWL_UART_CTL); + val |= OWL_UART_CTL_TXIE; + owl_uart_write(port, val, OWL_UART_CTL); +} + +static void owl_uart_send_chars(struct uart_port *port) +{ + struct circ_buf *xmit = &port->state->xmit; + unsigned int ch; + + if (uart_tx_stopped(port)) + return; + + if (port->x_char) { + while (!(owl_uart_read(port, OWL_UART_STAT) & OWL_UART_STAT_TFFU)) + cpu_relax(); + owl_uart_write(port, port->x_char, OWL_UART_TXDAT); + port->icount.tx++; + port->x_char = 0; + } + + while (!(owl_uart_read(port, OWL_UART_STAT) & OWL_UART_STAT_TFFU)) { + if (uart_circ_empty(xmit)) + break; + + ch = xmit->buf[xmit->tail]; + owl_uart_write(port, ch, OWL_UART_TXDAT); + xmit->tail = (xmit->tail + 1) & (SERIAL_XMIT_SIZE - 1); + port->icount.tx++; + } + + if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS) + uart_write_wakeup(port); + + if (uart_circ_empty(xmit)) + owl_uart_stop_tx(port); +} + +static void owl_uart_receive_chars(struct uart_port *port) +{ + u32 stat, val; + + val = owl_uart_read(port, OWL_UART_CTL); + val &= ~OWL_UART_CTL_TRFS_TX; + owl_uart_write(port, val, OWL_UART_CTL); + + stat = owl_uart_read(port, OWL_UART_STAT); + while (!(stat & OWL_UART_STAT_RFEM)) { + char flag = TTY_NORMAL; + + if (stat & OWL_UART_STAT_RXER) + port->icount.overrun++; + + if (stat & OWL_UART_STAT_RXST) { + /* We are not able to distinguish the error type. */ + port->icount.brk++; + port->icount.frame++; + + stat &= port->read_status_mask; + if (stat & OWL_UART_STAT_RXST) + flag = TTY_PARITY; + } else + port->icount.rx++; + + val = owl_uart_read(port, OWL_UART_RXDAT); + val &= 0xff; + + if ((stat & port->ignore_status_mask) == 0) + tty_insert_flip_char(&port->state->port, val, flag); + + stat = owl_uart_read(port, OWL_UART_STAT); + } + + spin_unlock(&port->lock); + tty_flip_buffer_push(&port->state->port); + spin_lock(&port->lock); +} + +static irqreturn_t owl_uart_irq(int irq, void *dev_id) +{ + struct uart_port *port = dev_id; + unsigned long flags; + u32 stat; + + spin_lock_irqsave(&port->lock, flags); + + stat = owl_uart_read(port, OWL_UART_STAT); + + if (stat & OWL_UART_STAT_RIP) + owl_uart_receive_chars(port); + + if (stat & OWL_UART_STAT_TIP) + owl_uart_send_chars(port); + + stat = owl_uart_read(port, OWL_UART_STAT); + stat |= OWL_UART_STAT_RIP | OWL_UART_STAT_TIP; + owl_uart_write(port, stat, OWL_UART_STAT); + + spin_unlock_irqrestore(&port->lock, flags); + + return IRQ_HANDLED; +} + +static void owl_uart_shutdown(struct uart_port *port) +{ + u32 val; + unsigned long flags; + + spin_lock_irqsave(&port->lock, flags); + + val = owl_uart_read(port, OWL_UART_CTL); + val &= ~(OWL_UART_CTL_TXIE | OWL_UART_CTL_RXIE + | OWL_UART_CTL_TXDE | OWL_UART_CTL_RXDE | OWL_UART_CTL_EN); + owl_uart_write(port, val, OWL_UART_CTL); + + spin_unlock_irqrestore(&port->lock, flags); + + free_irq(port->irq, port); +} + +static int owl_uart_startup(struct uart_port *port) +{ + u32 val; + unsigned long flags; + int ret; + + ret = request_irq(port->irq, owl_uart_irq, IRQF_TRIGGER_HIGH, + "owl-uart", port); + if (ret) + return ret; + + spin_lock_irqsave(&port->lock, flags); + + val = owl_uart_read(port, OWL_UART_STAT); + val |= OWL_UART_STAT_RIP | OWL_UART_STAT_TIP + | OWL_UART_STAT_RXER | OWL_UART_STAT_TFER | OWL_UART_STAT_RXST; + owl_uart_write(port, val, OWL_UART_STAT); + + val = owl_uart_read(port, OWL_UART_CTL); + val |= OWL_UART_CTL_RXIE | OWL_UART_CTL_TXIE; + val |= OWL_UART_CTL_EN; + owl_uart_write(port, val, OWL_UART_CTL); + + spin_unlock_irqrestore(&port->lock, flags); + + return 0; +} + +static void owl_uart_change_baudrate(struct owl_uart_port *owl_port, + unsigned long baud) +{ + clk_set_rate(owl_port->clk, baud * 8); +} + +static void owl_uart_set_termios(struct uart_port *port, + struct ktermios *termios, + struct ktermios *old) +{ + struct owl_uart_port *owl_port = to_owl_uart_port(port); + unsigned int baud; + u32 ctl; + unsigned long flags; + + spin_lock_irqsave(&port->lock, flags); + + ctl = owl_uart_read(port, OWL_UART_CTL); + + ctl &= ~OWL_UART_CTL_DWLS_MASK; + switch (termios->c_cflag & CSIZE) { + case CS5: + ctl |= OWL_UART_CTL_DWLS_5BITS; + break; + case CS6: + ctl |= OWL_UART_CTL_DWLS_6BITS; + break; + case CS7: + ctl |= OWL_UART_CTL_DWLS_7BITS; + break; + case CS8: + default: + ctl |= OWL_UART_CTL_DWLS_8BITS; + break; + } + + if (termios->c_cflag & CSTOPB) + ctl |= OWL_UART_CTL_STPS_2BITS; + else + ctl &= ~OWL_UART_CTL_STPS_2BITS; + + ctl &= ~OWL_UART_CTL_PRS_MASK; + if (termios->c_cflag & PARENB) { + if (termios->c_cflag & CMSPAR) { + if (termios->c_cflag & PARODD) + ctl |= OWL_UART_CTL_PRS_MARK; + else + ctl |= OWL_UART_CTL_PRS_SPACE; + } else if (termios->c_cflag & PARODD) + ctl |= OWL_UART_CTL_PRS_ODD; + else + ctl |= OWL_UART_CTL_PRS_EVEN; + } else + ctl |= OWL_UART_CTL_PRS_NONE; + + if (termios->c_cflag & CRTSCTS) + ctl |= OWL_UART_CTL_AFE; + else + ctl &= ~OWL_UART_CTL_AFE; + + owl_uart_write(port, ctl, OWL_UART_CTL); + + baud = uart_get_baud_rate(port, termios, old, 9600, 3200000); + owl_uart_change_baudrate(owl_port, baud); + + /* Don't rewrite B0 */ + if (tty_termios_baud_rate(termios)) + tty_termios_encode_baud_rate(termios, baud, baud); + + port->read_status_mask |= OWL_UART_STAT_RXER; + if (termios->c_iflag & INPCK) + port->read_status_mask |= OWL_UART_STAT_RXST; + + uart_update_timeout(port, termios->c_cflag, baud); + + spin_unlock_irqrestore(&port->lock, flags); +} + +static void owl_uart_release_port(struct uart_port *port) +{ + struct platform_device *pdev = to_platform_device(port->dev); + struct resource *res; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) + return; + + if (port->flags & UPF_IOREMAP) { + devm_release_mem_region(port->dev, port->mapbase, + resource_size(res)); + devm_iounmap(port->dev, port->membase); + port->membase = NULL; + } +} + +static int owl_uart_request_port(struct uart_port *port) +{ + struct platform_device *pdev = to_platform_device(port->dev); + struct resource *res; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) + return -ENXIO; + + if (!devm_request_mem_region(port->dev, port->mapbase, + resource_size(res), dev_name(port->dev))) + return -EBUSY; + + if (port->flags & UPF_IOREMAP) { + port->membase = devm_ioremap_nocache(port->dev, port->mapbase, + resource_size(res)); + if (!port->membase) + return -EBUSY; + } + + return 0; +} + +static const char *owl_uart_type(struct uart_port *port) +{ + return (port->type == PORT_OWL) ? "owl-uart" : NULL; +} + +static int owl_uart_verify_port(struct uart_port *port, + struct serial_struct *ser) +{ + if (port->type != PORT_OWL) + return -EINVAL; + + if (port->irq != ser->irq) + return -EINVAL; + + return 0; +} + +static void owl_uart_config_port(struct uart_port *port, int flags) +{ + if (flags & UART_CONFIG_TYPE) { + port->type = PORT_OWL; + owl_uart_request_port(port); + } +} + +static struct uart_ops owl_uart_ops = { + .set_mctrl = owl_uart_set_mctrl, + .get_mctrl = owl_uart_get_mctrl, + .tx_empty = owl_uart_tx_empty, + .start_tx = owl_uart_start_tx, + .stop_rx = owl_uart_stop_rx, + .stop_tx = owl_uart_stop_tx, + .startup = owl_uart_startup, + .shutdown = owl_uart_shutdown, + .set_termios = owl_uart_set_termios, + .type = owl_uart_type, + .config_port = owl_uart_config_port, + .request_port = owl_uart_request_port, + .release_port = owl_uart_release_port, + .verify_port = owl_uart_verify_port, +}; + #ifdef CONFIG_SERIAL_OWL_CONSOLE static void owl_console_putchar(struct uart_port *port, int ch) @@ -110,6 +546,57 @@ static void owl_uart_port_write(struct uart_port *port, const char *s, local_irq_restore(flags); } +static void owl_uart_console_write(struct console *co, const char *s, + u_int count) +{ + struct owl_uart_port *owl_port; + + owl_port = owl_uart_ports[co->index]; + if (!owl_port) + return; + + owl_uart_port_write(&owl_port->port, s, count); +} + +static int owl_uart_console_setup(struct console *co, char *options) +{ + struct owl_uart_port *owl_port; + int baud = 115200; + int bits = 8; + int parity = 'n'; + int flow = 'n'; + + if (co->index < 0 || co->index >= OWL_UART_PORT_NUM) + return -EINVAL; + + owl_port = owl_uart_ports[co->index]; + if (!owl_port || !owl_port->port.membase) + return -ENODEV; + + if (options) + uart_parse_options(options, &baud, &parity, &bits, &flow); + + return uart_set_options(&owl_port->port, co, baud, parity, bits, flow); +} + +static struct console owl_uart_console = { + .name = OWL_UART_DEV_NAME, + .write = owl_uart_console_write, + .device = uart_console_device, + .setup = owl_uart_console_setup, + .flags = CON_PRINTBUFFER, + .index = -1, + .data = &owl_uart_driver, +}; + +static int __init owl_uart_console_init(void) +{ + register_console(&owl_uart_console); + + return 0; +} +console_initcall(owl_uart_console_init); + static void owl_uart_early_console_write(struct console *co, const char *s, u_int count) @@ -132,4 +619,148 @@ owl_uart_early_console_setup(struct earlycon_device *device, const char *opt) OF_EARLYCON_DECLARE(owl, "actions,owl-uart", owl_uart_early_console_setup); -#endif /* CONFIG_SERIAL_OWL_CONSOLE */ +#define OWL_UART_CONSOLE (&owl_uart_console) +#else +#define OWL_UART_CONSOLE NULL +#endif + +static struct uart_driver owl_uart_driver = { + .owner = THIS_MODULE, + .driver_name = "owl-uart", + .dev_name = OWL_UART_DEV_NAME, + .nr = OWL_UART_PORT_NUM, + .cons = OWL_UART_CONSOLE, +}; + +static const struct owl_uart_info owl_s500_info = { + .tx_fifosize = 16, +}; + +static const struct owl_uart_info owl_s900_info = { + .tx_fifosize = 32, +}; + +static const struct of_device_id owl_uart_dt_matches[] = { + { .compatible = "actions,s500-uart", .data = &owl_s500_info }, + { .compatible = "actions,s900-uart", .data = &owl_s900_info }, + { } +}; +MODULE_DEVICE_TABLE(of, owl_uart_dt_matches); + +static int owl_uart_probe(struct platform_device *pdev) +{ + const struct of_device_id *match; + const struct owl_uart_info *info = NULL; + struct resource *res_mem; + struct owl_uart_port *owl_port; + int ret, irq; + + if (pdev->dev.of_node) { + pdev->id = of_alias_get_id(pdev->dev.of_node, "serial"); + match = of_match_node(owl_uart_dt_matches, pdev->dev.of_node); + if (match) + info = match->data; + } + + if (pdev->id < 0 || pdev->id >= OWL_UART_PORT_NUM) { + dev_err(&pdev->dev, "id %d out of range\n", pdev->id); + return -EINVAL; + } + + res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res_mem) { + dev_err(&pdev->dev, "could not get mem\n"); + return -ENODEV; + } + + irq = platform_get_irq(pdev, 0); + if (irq < 0) { + dev_err(&pdev->dev, "could not get irq\n"); + return irq; + } + + if (owl_uart_ports[pdev->id]) { + dev_err(&pdev->dev, "port %d already allocated\n", pdev->id); + return -EBUSY; + } + + owl_port = devm_kzalloc(&pdev->dev, sizeof(*owl_port), GFP_KERNEL); + if (!owl_port) + return -ENOMEM; + + owl_port->clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(owl_port->clk)) { + dev_err(&pdev->dev, "could not get clk\n"); + return PTR_ERR(owl_port->clk); + } + + owl_port->port.dev = &pdev->dev; + owl_port->port.line = pdev->id; + owl_port->port.type = PORT_OWL; + owl_port->port.iotype = UPIO_MEM; + owl_port->port.mapbase = res_mem->start; + owl_port->port.irq = irq; + owl_port->port.uartclk = clk_get_rate(owl_port->clk); + if (owl_port->port.uartclk == 0) { + dev_err(&pdev->dev, "clock rate is zero\n"); + return -EINVAL; + } + owl_port->port.flags = UPF_BOOT_AUTOCONF | UPF_IOREMAP | UPF_LOW_LATENCY; + owl_port->port.x_char = 0; + owl_port->port.fifosize = (info) ? info->tx_fifosize : 16; + owl_port->port.ops = &owl_uart_ops; + + owl_uart_ports[pdev->id] = owl_port; + platform_set_drvdata(pdev, owl_port); + + ret = uart_add_one_port(&owl_uart_driver, &owl_port->port); + if (ret) + owl_uart_ports[pdev->id] = NULL; + + return ret; +} + +static int owl_uart_remove(struct platform_device *pdev) +{ + struct owl_uart_port *owl_port = platform_get_drvdata(pdev); + + uart_remove_one_port(&owl_uart_driver, &owl_port->port); + owl_uart_ports[pdev->id] = NULL; + + return 0; +} + +static struct platform_driver owl_uart_platform_driver = { + .probe = owl_uart_probe, + .remove = owl_uart_remove, + .driver = { + .name = "owl-uart", + .of_match_table = owl_uart_dt_matches, + }, +}; + +static int __init owl_uart_init(void) +{ + int ret; + + ret = uart_register_driver(&owl_uart_driver); + if (ret) + return ret; + + ret = platform_driver_register(&owl_uart_platform_driver); + if (ret) + uart_unregister_driver(&owl_uart_driver); + + return ret; +} + +static void __init owl_uart_exit(void) +{ + platform_driver_unregister(&owl_uart_platform_driver); + uart_unregister_driver(&owl_uart_driver); +} + +module_init(owl_uart_init); +module_exit(owl_uart_exit); + +MODULE_LICENSE("GPL"); diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index c34a2a3eeff5..38bea3217ead 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -70,6 +70,7 @@ #define PORT_CLPS711X 33 #define PORT_SA1100 34 #define PORT_UART00 35 +#define PORT_OWL 36 #define PORT_21285 37 /* Sparc type numbers. */ -- cgit v1.2.3-71-gd317 From 6303d97873d340e89acdef12effb66f88d79836f Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 11 Jul 2017 03:30:38 -0300 Subject: media: linux/cec.h: add pin monitoring API support Add support for low-level CEC pin monitoring. This adds a new monitor mode, a new capability and two new events. Signed-off-by: Hans Verkuil Reviewed-by: Maxime Ripard Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/cec.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/cec.h b/include/uapi/linux/cec.h index 44579a24f95d..bba73f33c8aa 100644 --- a/include/uapi/linux/cec.h +++ b/include/uapi/linux/cec.h @@ -318,6 +318,7 @@ static inline int cec_is_unconfigured(__u16 log_addr_mask) #define CEC_MODE_FOLLOWER (0x1 << 4) #define CEC_MODE_EXCL_FOLLOWER (0x2 << 4) #define CEC_MODE_EXCL_FOLLOWER_PASSTHRU (0x3 << 4) +#define CEC_MODE_MONITOR_PIN (0xd << 4) #define CEC_MODE_MONITOR (0xe << 4) #define CEC_MODE_MONITOR_ALL (0xf << 4) #define CEC_MODE_FOLLOWER_MSK 0xf0 @@ -338,6 +339,8 @@ static inline int cec_is_unconfigured(__u16 log_addr_mask) #define CEC_CAP_MONITOR_ALL (1 << 5) /* Hardware can use CEC only if the HDMI HPD pin is high. */ #define CEC_CAP_NEEDS_HPD (1 << 6) +/* Hardware can monitor CEC pin transitions */ +#define CEC_CAP_MONITOR_PIN (1 << 7) /** * struct cec_caps - CEC capabilities structure. @@ -405,6 +408,8 @@ struct cec_log_addrs { * didn't empty the message queue in time */ #define CEC_EVENT_LOST_MSGS 2 +#define CEC_EVENT_PIN_LOW 3 +#define CEC_EVENT_PIN_HIGH 4 #define CEC_EVENT_FL_INITIAL_STATE (1 << 0) -- cgit v1.2.3-71-gd317 From 6b2bbb08747a56dcf4ee33606a06025eca571260 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 11 Jul 2017 03:30:39 -0300 Subject: media: cec: rework the cec event handling Event handling was always fairly simplistic since there were only two events. With the addition of pin events this needed to be redesigned. The state_change and lost_msgs events are now core events with the guarantee that the last state is always available. The new pin events are a queue of events (up to 64 for each event) and the oldest event will be dropped if the application cannot keep up. Lost events are marked with a new event flag. Signed-off-by: Hans Verkuil Reviewed-by: Maxime Ripard Signed-off-by: Mauro Carvalho Chehab --- drivers/media/cec/cec-adap.c | 128 +++++++++++++++++++++++++------------------ drivers/media/cec/cec-api.c | 48 +++++++++++----- include/media/cec.h | 14 ++++- include/uapi/linux/cec.h | 3 +- 4 files changed, 124 insertions(+), 69 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/media/cec/cec-adap.c b/drivers/media/cec/cec-adap.c index 82c1633f5b92..5080d7aa6105 100644 --- a/drivers/media/cec/cec-adap.c +++ b/drivers/media/cec/cec-adap.c @@ -78,42 +78,62 @@ static unsigned int cec_log_addr2dev(const struct cec_adapter *adap, u8 log_addr * Queue a new event for this filehandle. If ts == 0, then set it * to the current time. * - * The two events that are currently defined do not need to keep track - * of intermediate events, so no actual queue of events is needed, - * instead just store the latest state and the total number of lost - * messages. - * - * Should new events be added in the future that require intermediate - * results to be queued as well, then a proper queue data structure is - * required. But until then, just keep it simple. + * We keep a queue of at most max_event events where max_event differs + * per event. If the queue becomes full, then drop the oldest event and + * keep track of how many events we've dropped. */ void cec_queue_event_fh(struct cec_fh *fh, const struct cec_event *new_ev, u64 ts) { - struct cec_event *ev = &fh->events[new_ev->event - 1]; + static const u8 max_events[CEC_NUM_EVENTS] = { + 1, 1, 64, 64, + }; + struct cec_event_entry *entry; + unsigned int ev_idx = new_ev->event - 1; + + if (WARN_ON(ev_idx >= ARRAY_SIZE(fh->events))) + return; if (ts == 0) ts = ktime_get_ns(); mutex_lock(&fh->lock); - if (new_ev->event == CEC_EVENT_LOST_MSGS && - fh->pending_events & (1 << new_ev->event)) { - /* - * If there is already a lost_msgs event, then just - * update the lost_msgs count. This effectively - * merges the old and new events into one. - */ - ev->lost_msgs.lost_msgs += new_ev->lost_msgs.lost_msgs; - goto unlock; - } + if (ev_idx < CEC_NUM_CORE_EVENTS) + entry = &fh->core_events[ev_idx]; + else + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (entry) { + if (new_ev->event == CEC_EVENT_LOST_MSGS && + fh->queued_events[ev_idx]) { + entry->ev.lost_msgs.lost_msgs += + new_ev->lost_msgs.lost_msgs; + goto unlock; + } + entry->ev = *new_ev; + entry->ev.ts = ts; + + if (fh->queued_events[ev_idx] < max_events[ev_idx]) { + /* Add new msg at the end of the queue */ + list_add_tail(&entry->list, &fh->events[ev_idx]); + fh->queued_events[ev_idx]++; + fh->total_queued_events++; + goto unlock; + } - /* - * Intermediate states are not interesting, so just - * overwrite any older event. - */ - *ev = *new_ev; - ev->ts = ts; - fh->pending_events |= 1 << new_ev->event; + if (ev_idx >= CEC_NUM_CORE_EVENTS) { + list_add_tail(&entry->list, &fh->events[ev_idx]); + /* drop the oldest event */ + entry = list_first_entry(&fh->events[ev_idx], + struct cec_event_entry, list); + list_del(&entry->list); + kfree(entry); + } + } + /* Mark that events were lost */ + entry = list_first_entry_or_null(&fh->events[ev_idx], + struct cec_event_entry, list); + if (entry) + entry->ev.flags |= CEC_EVENT_FL_DROPPED_EVENTS; unlock: mutex_unlock(&fh->lock); @@ -134,46 +154,50 @@ static void cec_queue_event(struct cec_adapter *adap, } /* - * Queue a new message for this filehandle. If there is no more room - * in the queue, then send the LOST_MSGS event instead. + * Queue a new message for this filehandle. + * + * We keep a queue of at most CEC_MAX_MSG_RX_QUEUE_SZ messages. If the + * queue becomes full, then drop the oldest message and keep track + * of how many messages we've dropped. */ static void cec_queue_msg_fh(struct cec_fh *fh, const struct cec_msg *msg) { - static const struct cec_event ev_lost_msg = { - .ts = 0, + static const struct cec_event ev_lost_msgs = { .event = CEC_EVENT_LOST_MSGS, - .flags = 0, - { - .lost_msgs.lost_msgs = 1, - }, + .lost_msgs.lost_msgs = 1, }; struct cec_msg_entry *entry; mutex_lock(&fh->lock); entry = kmalloc(sizeof(*entry), GFP_KERNEL); - if (!entry) - goto lost_msgs; - - entry->msg = *msg; - /* Add new msg at the end of the queue */ - list_add_tail(&entry->list, &fh->msgs); + if (entry) { + entry->msg = *msg; + /* Add new msg at the end of the queue */ + list_add_tail(&entry->list, &fh->msgs); + + if (fh->queued_msgs < CEC_MAX_MSG_RX_QUEUE_SZ) { + /* All is fine if there is enough room */ + fh->queued_msgs++; + mutex_unlock(&fh->lock); + wake_up_interruptible(&fh->wait); + return; + } - /* - * if the queue now has more than CEC_MAX_MSG_RX_QUEUE_SZ - * messages, drop the oldest one and send a lost message event. - */ - if (fh->queued_msgs == CEC_MAX_MSG_RX_QUEUE_SZ) { + /* + * if the message queue is full, then drop the oldest one and + * send a lost message event. + */ + entry = list_first_entry(&fh->msgs, struct cec_msg_entry, list); list_del(&entry->list); - goto lost_msgs; + kfree(entry); } - fh->queued_msgs++; mutex_unlock(&fh->lock); - wake_up_interruptible(&fh->wait); - return; -lost_msgs: - mutex_unlock(&fh->lock); - cec_queue_event_fh(fh, &ev_lost_msg, 0); + /* + * We lost a message, either because kmalloc failed or the queue + * was full. + */ + cec_queue_event_fh(fh, &ev_lost_msgs, ktime_get_ns()); } /* diff --git a/drivers/media/cec/cec-api.c b/drivers/media/cec/cec-api.c index f7eb4c54a354..48bef1c718ad 100644 --- a/drivers/media/cec/cec-api.c +++ b/drivers/media/cec/cec-api.c @@ -57,7 +57,7 @@ static unsigned int cec_poll(struct file *filp, res |= POLLOUT | POLLWRNORM; if (fh->queued_msgs) res |= POLLIN | POLLRDNORM; - if (fh->pending_events) + if (fh->total_queued_events) res |= POLLPRI; poll_wait(filp, &fh->wait, poll); mutex_unlock(&adap->lock); @@ -289,15 +289,17 @@ static long cec_receive(struct cec_adapter *adap, struct cec_fh *fh, static long cec_dqevent(struct cec_adapter *adap, struct cec_fh *fh, bool block, struct cec_event __user *parg) { - struct cec_event *ev = NULL; + struct cec_event_entry *ev = NULL; u64 ts = ~0ULL; unsigned int i; + unsigned int ev_idx; long err = 0; mutex_lock(&fh->lock); - while (!fh->pending_events && block) { + while (!fh->total_queued_events && block) { mutex_unlock(&fh->lock); - err = wait_event_interruptible(fh->wait, fh->pending_events); + err = wait_event_interruptible(fh->wait, + fh->total_queued_events); if (err) return err; mutex_lock(&fh->lock); @@ -305,23 +307,29 @@ static long cec_dqevent(struct cec_adapter *adap, struct cec_fh *fh, /* Find the oldest event */ for (i = 0; i < CEC_NUM_EVENTS; i++) { - if (fh->pending_events & (1 << (i + 1)) && - fh->events[i].ts <= ts) { - ev = &fh->events[i]; - ts = ev->ts; + struct cec_event_entry *entry = + list_first_entry_or_null(&fh->events[i], + struct cec_event_entry, list); + + if (entry && entry->ev.ts <= ts) { + ev = entry; + ev_idx = i; + ts = ev->ev.ts; } } + if (!ev) { err = -EAGAIN; goto unlock; } + list_del(&ev->list); - if (copy_to_user(parg, ev, sizeof(*ev))) { + if (copy_to_user(parg, &ev->ev, sizeof(ev->ev))) err = -EFAULT; - goto unlock; - } - - fh->pending_events &= ~(1 << ev->event); + if (ev_idx >= CEC_NUM_CORE_EVENTS) + kfree(ev); + fh->queued_events[ev_idx]--; + fh->total_queued_events--; unlock: mutex_unlock(&fh->lock); @@ -495,6 +503,7 @@ static int cec_open(struct inode *inode, struct file *filp) .event = CEC_EVENT_STATE_CHANGE, .flags = CEC_EVENT_FL_INITIAL_STATE, }; + unsigned int i; int err; if (!fh) @@ -502,6 +511,8 @@ static int cec_open(struct inode *inode, struct file *filp) INIT_LIST_HEAD(&fh->msgs); INIT_LIST_HEAD(&fh->xfer_list); + for (i = 0; i < CEC_NUM_EVENTS; i++) + INIT_LIST_HEAD(&fh->events[i]); mutex_init(&fh->lock); init_waitqueue_head(&fh->wait); @@ -544,6 +555,7 @@ static int cec_release(struct inode *inode, struct file *filp) struct cec_devnode *devnode = cec_devnode_data(filp); struct cec_adapter *adap = to_cec_adapter(devnode); struct cec_fh *fh = filp->private_data; + unsigned int i; mutex_lock(&adap->lock); if (adap->cec_initiator == fh) @@ -585,6 +597,16 @@ static int cec_release(struct inode *inode, struct file *filp) list_del(&entry->list); kfree(entry); } + for (i = CEC_NUM_CORE_EVENTS; i < CEC_NUM_EVENTS; i++) { + while (!list_empty(&fh->events[i])) { + struct cec_event_entry *entry = + list_first_entry(&fh->events[i], + struct cec_event_entry, list); + + list_del(&entry->list); + kfree(entry); + } + } kfree(fh); cec_put_device(devnode); diff --git a/include/media/cec.h b/include/media/cec.h index 37768203572d..6cc862af74e5 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -81,7 +81,13 @@ struct cec_msg_entry { struct cec_msg msg; }; -#define CEC_NUM_EVENTS CEC_EVENT_LOST_MSGS +struct cec_event_entry { + struct list_head list; + struct cec_event ev; +}; + +#define CEC_NUM_CORE_EVENTS 2 +#define CEC_NUM_EVENTS CEC_EVENT_PIN_HIGH struct cec_fh { struct list_head list; @@ -92,9 +98,11 @@ struct cec_fh { /* Events */ wait_queue_head_t wait; - unsigned int pending_events; - struct cec_event events[CEC_NUM_EVENTS]; struct mutex lock; + struct list_head events[CEC_NUM_EVENTS]; /* queued events */ + u8 queued_events[CEC_NUM_EVENTS]; + unsigned int total_queued_events; + struct cec_event_entry core_events[CEC_NUM_CORE_EVENTS]; struct list_head msgs; /* queued messages */ unsigned int queued_msgs; }; diff --git a/include/uapi/linux/cec.h b/include/uapi/linux/cec.h index bba73f33c8aa..d87a67b0bb06 100644 --- a/include/uapi/linux/cec.h +++ b/include/uapi/linux/cec.h @@ -412,6 +412,7 @@ struct cec_log_addrs { #define CEC_EVENT_PIN_HIGH 4 #define CEC_EVENT_FL_INITIAL_STATE (1 << 0) +#define CEC_EVENT_FL_DROPPED_EVENTS (1 << 1) /** * struct cec_event_state_change - used when the CEC adapter changes state. @@ -424,7 +425,7 @@ struct cec_event_state_change { }; /** - * struct cec_event_lost_msgs - tells you how many messages were lost due. + * struct cec_event_lost_msgs - tells you how many messages were lost. * @lost_msgs: how many messages were lost. */ struct cec_event_lost_msgs { -- cgit v1.2.3-71-gd317 From eb0baf8a0d9259d168523b8e7c436b55ade7c546 Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Tue, 18 Jul 2017 20:13:09 +0800 Subject: perf/core: Define the common branch type classification MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It is often useful to know the branch types while analyzing branch data. For example, a call is very different from a conditional branch. Currently we have to look it up in binary while the binary may later not be available and even the binary is available but user has to take some time. It is very useful for user to check it directly in perf report. Perf already has support for disassembling the branch instruction to get the x86 branch type. To keep consistent on kernel and userspace and make the classification more common, the patch adds the common branch type classification in perf_event.h. The patch only defines a minimum but most common set of branch types. PERF_BR_UNKNOWN : unknown PERF_BR_COND ：conditional PERF_BR_UNCOND : unconditional PERF_BR_IND : indirect PERF_BR_CALL : function call PERF_BR_IND_CALL : indirect function call PERF_BR_RET : function return PERF_BR_SYSCALL : syscall PERF_BR_SYSRET : syscall return PERF_BR_COND_CALL : conditional function call PERF_BR_COND_RET : conditional function return The patch also adds a new field type (4 bits) in perf_branch_entry to record the branch type. Since the disassembling of branch instruction needs some overhead, a new PERF_SAMPLE_BRANCH_TYPE_SAVE is introduced to indicate if it needs to disassemble the branch instruction and record the branch type. Change log: v10: Not changed. v9: Not changed. v8: Change PERF_BR_NONE to PERF_BR_UNKNOWN. No other change. v7: Just keep the most common branch types. Others are removed. v6: Not changed. v5: Not changed. The v5 patch series just change the userspace. v4: Comparing to previous version, the major changes are: 1. Remove the PERF_BR_JCC_FWD/PERF_BR_JCC_BWD, they will be computed later in userspace. 2. Remove the "cross" field in perf_branch_entry. The cross page computing will be done later in userspace. Signed-off-by: Yao Jin Acked-by: Jiri Olsa Acked-by: Michael Ellerman Acked-by: Peter Zijlstra Cc: Alexander Shishkin Cc: Andi Kleen Cc: Kan Liang Link: http://lkml.kernel.org/r/1500379995-6449-2-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- include/uapi/linux/perf_event.h | 27 ++++++++++++++++++++++++++- tools/include/uapi/linux/perf_event.h | 27 ++++++++++++++++++++++++++- 2 files changed, 52 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index b1c0b187acfe..642db5fa3286 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -174,6 +174,8 @@ enum perf_branch_sample_type_shift { PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT = 14, /* no flags */ PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT = 15, /* no cycles */ + PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT = 16, /* save branch type */ + PERF_SAMPLE_BRANCH_MAX_SHIFT /* non-ABI */ }; @@ -198,9 +200,30 @@ enum perf_branch_sample_type { PERF_SAMPLE_BRANCH_NO_FLAGS = 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT, PERF_SAMPLE_BRANCH_NO_CYCLES = 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT, + PERF_SAMPLE_BRANCH_TYPE_SAVE = + 1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT, + PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT, }; +/* + * Common flow change classification + */ +enum { + PERF_BR_UNKNOWN = 0, /* unknown */ + PERF_BR_COND = 1, /* conditional */ + PERF_BR_UNCOND = 2, /* unconditional */ + PERF_BR_IND = 3, /* indirect */ + PERF_BR_CALL = 4, /* function call */ + PERF_BR_IND_CALL = 5, /* indirect function call */ + PERF_BR_RET = 6, /* function return */ + PERF_BR_SYSCALL = 7, /* syscall */ + PERF_BR_SYSRET = 8, /* syscall return */ + PERF_BR_COND_CALL = 9, /* conditional function call */ + PERF_BR_COND_RET = 10, /* conditional function return */ + PERF_BR_MAX, +}; + #define PERF_SAMPLE_BRANCH_PLM_ALL \ (PERF_SAMPLE_BRANCH_USER|\ PERF_SAMPLE_BRANCH_KERNEL|\ @@ -1015,6 +1038,7 @@ union perf_mem_data_src { * in_tx: running in a hardware transaction * abort: aborting a hardware transaction * cycles: cycles from last branch (or 0 if not supported) + * type: branch type */ struct perf_branch_entry { __u64 from; @@ -1024,7 +1048,8 @@ struct perf_branch_entry { in_tx:1, /* in transaction */ abort:1, /* transaction abort */ cycles:16, /* cycle count to last branch */ - reserved:44; + type:4, /* branch type */ + reserved:40; }; #endif /* _UAPI_LINUX_PERF_EVENT_H */ diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index b1c0b187acfe..642db5fa3286 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -174,6 +174,8 @@ enum perf_branch_sample_type_shift { PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT = 14, /* no flags */ PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT = 15, /* no cycles */ + PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT = 16, /* save branch type */ + PERF_SAMPLE_BRANCH_MAX_SHIFT /* non-ABI */ }; @@ -198,9 +200,30 @@ enum perf_branch_sample_type { PERF_SAMPLE_BRANCH_NO_FLAGS = 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT, PERF_SAMPLE_BRANCH_NO_CYCLES = 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT, + PERF_SAMPLE_BRANCH_TYPE_SAVE = + 1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT, + PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT, }; +/* + * Common flow change classification + */ +enum { + PERF_BR_UNKNOWN = 0, /* unknown */ + PERF_BR_COND = 1, /* conditional */ + PERF_BR_UNCOND = 2, /* unconditional */ + PERF_BR_IND = 3, /* indirect */ + PERF_BR_CALL = 4, /* function call */ + PERF_BR_IND_CALL = 5, /* indirect function call */ + PERF_BR_RET = 6, /* function return */ + PERF_BR_SYSCALL = 7, /* syscall */ + PERF_BR_SYSRET = 8, /* syscall return */ + PERF_BR_COND_CALL = 9, /* conditional function call */ + PERF_BR_COND_RET = 10, /* conditional function return */ + PERF_BR_MAX, +}; + #define PERF_SAMPLE_BRANCH_PLM_ALL \ (PERF_SAMPLE_BRANCH_USER|\ PERF_SAMPLE_BRANCH_KERNEL|\ @@ -1015,6 +1038,7 @@ union perf_mem_data_src { * in_tx: running in a hardware transaction * abort: aborting a hardware transaction * cycles: cycles from last branch (or 0 if not supported) + * type: branch type */ struct perf_branch_entry { __u64 from; @@ -1024,7 +1048,8 @@ struct perf_branch_entry { in_tx:1, /* in transaction */ abort:1, /* transaction abort */ cycles:16, /* cycle count to last branch */ - reserved:44; + type:4, /* branch type */ + reserved:40; }; #endif /* _UAPI_LINUX_PERF_EVENT_H */ -- cgit v1.2.3-71-gd317 From 727f8914477e4642c7d1ff381667cdc4178b40c6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 21 Jul 2017 10:39:26 +0100 Subject: rxrpc: Expose UAPI definitions to userspace Move UAPI definitions from the internal header and place them in a UAPI header file so that userspace can make use of them. Signed-off-by: David Howells --- include/linux/rxrpc.h | 79 --------------------------------------------- include/uapi/linux/rxrpc.h | 80 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 80 insertions(+), 79 deletions(-) delete mode 100644 include/linux/rxrpc.h create mode 100644 include/uapi/linux/rxrpc.h (limited to 'include/uapi/linux') diff --git a/include/linux/rxrpc.h b/include/linux/rxrpc.h deleted file mode 100644 index 7343f71783dc..000000000000 --- a/include/linux/rxrpc.h +++ /dev/null @@ -1,79 +0,0 @@ -/* AF_RXRPC parameters - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#ifndef _LINUX_RXRPC_H -#define _LINUX_RXRPC_H - -#include -#include - -/* - * RxRPC socket address - */ -struct sockaddr_rxrpc { - sa_family_t srx_family; /* address family */ - u16 srx_service; /* service desired */ - u16 transport_type; /* type of transport socket (SOCK_DGRAM) */ - u16 transport_len; /* length of transport address */ - union { - sa_family_t family; /* transport address family */ - struct sockaddr_in sin; /* IPv4 transport address */ - struct sockaddr_in6 sin6; /* IPv6 transport address */ - } transport; -}; - -/* - * RxRPC socket options - */ -#define RXRPC_SECURITY_KEY 1 /* [clnt] set client security key */ -#define RXRPC_SECURITY_KEYRING 2 /* [srvr] set ring of server security keys */ -#define RXRPC_EXCLUSIVE_CONNECTION 3 /* Deprecated; use RXRPC_EXCLUSIVE_CALL instead */ -#define RXRPC_MIN_SECURITY_LEVEL 4 /* minimum security level */ -#define RXRPC_UPGRADEABLE_SERVICE 5 /* Upgrade service[0] -> service[1] */ -#define RXRPC_SUPPORTED_CMSG 6 /* Get highest supported control message type */ - -/* - * RxRPC control messages - * - If neither abort or accept are specified, the message is a data message. - * - terminal messages mean that a user call ID tag can be recycled - * - s/r/- indicate whether these are applicable to sendmsg() and/or recvmsg() - */ -enum rxrpc_cmsg_type { - RXRPC_USER_CALL_ID = 1, /* sr: user call ID specifier */ - RXRPC_ABORT = 2, /* sr: abort request / notification [terminal] */ - RXRPC_ACK = 3, /* -r: [Service] RPC op final ACK received [terminal] */ - RXRPC_NET_ERROR = 5, /* -r: network error received [terminal] */ - RXRPC_BUSY = 6, /* -r: server busy received [terminal] */ - RXRPC_LOCAL_ERROR = 7, /* -r: local error generated [terminal] */ - RXRPC_NEW_CALL = 8, /* -r: [Service] new incoming call notification */ - RXRPC_ACCEPT = 9, /* s-: [Service] accept request */ - RXRPC_EXCLUSIVE_CALL = 10, /* s-: Call should be on exclusive connection */ - RXRPC_UPGRADE_SERVICE = 11, /* s-: Request service upgrade for client call */ - RXRPC_TX_LENGTH = 12, /* s-: Total length of Tx data */ - RXRPC__SUPPORTED -}; - -/* - * RxRPC security levels - */ -#define RXRPC_SECURITY_PLAIN 0 /* plain secure-checksummed packets only */ -#define RXRPC_SECURITY_AUTH 1 /* authenticated packets */ -#define RXRPC_SECURITY_ENCRYPT 2 /* encrypted packets */ - -/* - * RxRPC security indices - */ -#define RXRPC_SECURITY_NONE 0 /* no security protocol */ -#define RXRPC_SECURITY_RXKAD 2 /* kaserver or kerberos 4 */ -#define RXRPC_SECURITY_RXGK 4 /* gssapi-based */ -#define RXRPC_SECURITY_RXK5 5 /* kerberos 5 */ - -#endif /* _LINUX_RXRPC_H */ diff --git a/include/uapi/linux/rxrpc.h b/include/uapi/linux/rxrpc.h new file mode 100644 index 000000000000..08e2fb9c70ae --- /dev/null +++ b/include/uapi/linux/rxrpc.h @@ -0,0 +1,80 @@ +/* Types and definitions for AF_RXRPC. + * + * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#ifndef _UAPI_LINUX_RXRPC_H +#define _UAPI_LINUX_RXRPC_H + +#include +#include +#include + +/* + * RxRPC socket address + */ +struct sockaddr_rxrpc { + sa_family_t srx_family; /* address family */ + u16 srx_service; /* service desired */ + u16 transport_type; /* type of transport socket (SOCK_DGRAM) */ + u16 transport_len; /* length of transport address */ + union { + sa_family_t family; /* transport address family */ + struct sockaddr_in sin; /* IPv4 transport address */ + struct sockaddr_in6 sin6; /* IPv6 transport address */ + } transport; +}; + +/* + * RxRPC socket options + */ +#define RXRPC_SECURITY_KEY 1 /* [clnt] set client security key */ +#define RXRPC_SECURITY_KEYRING 2 /* [srvr] set ring of server security keys */ +#define RXRPC_EXCLUSIVE_CONNECTION 3 /* Deprecated; use RXRPC_EXCLUSIVE_CALL instead */ +#define RXRPC_MIN_SECURITY_LEVEL 4 /* minimum security level */ +#define RXRPC_UPGRADEABLE_SERVICE 5 /* Upgrade service[0] -> service[1] */ +#define RXRPC_SUPPORTED_CMSG 6 /* Get highest supported control message type */ + +/* + * RxRPC control messages + * - If neither abort or accept are specified, the message is a data message. + * - terminal messages mean that a user call ID tag can be recycled + * - s/r/- indicate whether these are applicable to sendmsg() and/or recvmsg() + */ +enum rxrpc_cmsg_type { + RXRPC_USER_CALL_ID = 1, /* sr: user call ID specifier */ + RXRPC_ABORT = 2, /* sr: abort request / notification [terminal] */ + RXRPC_ACK = 3, /* -r: [Service] RPC op final ACK received [terminal] */ + RXRPC_NET_ERROR = 5, /* -r: network error received [terminal] */ + RXRPC_BUSY = 6, /* -r: server busy received [terminal] */ + RXRPC_LOCAL_ERROR = 7, /* -r: local error generated [terminal] */ + RXRPC_NEW_CALL = 8, /* -r: [Service] new incoming call notification */ + RXRPC_ACCEPT = 9, /* s-: [Service] accept request */ + RXRPC_EXCLUSIVE_CALL = 10, /* s-: Call should be on exclusive connection */ + RXRPC_UPGRADE_SERVICE = 11, /* s-: Request service upgrade for client call */ + RXRPC_TX_LENGTH = 12, /* s-: Total length of Tx data */ + RXRPC__SUPPORTED +}; + +/* + * RxRPC security levels + */ +#define RXRPC_SECURITY_PLAIN 0 /* plain secure-checksummed packets only */ +#define RXRPC_SECURITY_AUTH 1 /* authenticated packets */ +#define RXRPC_SECURITY_ENCRYPT 2 /* encrypted packets */ + +/* + * RxRPC security indices + */ +#define RXRPC_SECURITY_NONE 0 /* no security protocol */ +#define RXRPC_SECURITY_RXKAD 2 /* kaserver or kerberos 4 */ +#define RXRPC_SECURITY_RXGK 4 /* gssapi-based */ +#define RXRPC_SECURITY_RXK5 5 /* kerberos 5 */ + +#endif /* _UAPI_LINUX_RXRPC_H */ -- cgit v1.2.3-71-gd317 From ddc6c70f07bb1f6dd39a2c6c430f7b4fa95199c8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 21 Jul 2017 10:07:10 +0100 Subject: rxrpc: Move the packet.h include file into net/rxrpc/ Move the protocol description header file into net/rxrpc/ and rename it to protocol.h. It's no longer necessary to expose it as packets are no longer exposed to kernel services (such as AFS) that use the facility. The abort codes are transferred to the UAPI header instead as we pass these back to userspace and also to kernel services. Signed-off-by: David Howells --- fs/afs/misc.c | 1 - fs/afs/rxrpc.c | 1 - include/rxrpc/packet.h | 235 --------------------------------------------- include/uapi/linux/rxrpc.h | 44 +++++++++ net/rxrpc/ar-internal.h | 2 +- net/rxrpc/protocol.h | 190 ++++++++++++++++++++++++++++++++++++ 6 files changed, 235 insertions(+), 238 deletions(-) delete mode 100644 include/rxrpc/packet.h create mode 100644 net/rxrpc/protocol.h (limited to 'include/uapi/linux') diff --git a/fs/afs/misc.c b/fs/afs/misc.c index 100b207efc9e..c05f1f1c0d41 100644 --- a/fs/afs/misc.c +++ b/fs/afs/misc.c @@ -12,7 +12,6 @@ #include #include #include -#include #include "internal.h" #include "afs_fs.h" diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 02781e78ffb6..10743043d431 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -14,7 +14,6 @@ #include #include -#include #include "internal.h" #include "afs_cm.h" diff --git a/include/rxrpc/packet.h b/include/rxrpc/packet.h deleted file mode 100644 index a2dcfb850b9f..000000000000 --- a/include/rxrpc/packet.h +++ /dev/null @@ -1,235 +0,0 @@ -/* packet.h: Rx packet layout and definitions - * - * Copyright (C) 2002, 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#ifndef _LINUX_RXRPC_PACKET_H -#define _LINUX_RXRPC_PACKET_H - -typedef u32 rxrpc_seq_t; /* Rx message sequence number */ -typedef u32 rxrpc_serial_t; /* Rx message serial number */ -typedef __be32 rxrpc_seq_net_t; /* on-the-wire Rx message sequence number */ -typedef __be32 rxrpc_serial_net_t; /* on-the-wire Rx message serial number */ - -/*****************************************************************************/ -/* - * on-the-wire Rx packet header - * - all multibyte fields should be in network byte order - */ -struct rxrpc_wire_header { - __be32 epoch; /* client boot timestamp */ -#define RXRPC_RANDOM_EPOCH 0x80000000 /* Random if set, date-based if not */ - - __be32 cid; /* connection and channel ID */ -#define RXRPC_MAXCALLS 4 /* max active calls per conn */ -#define RXRPC_CHANNELMASK (RXRPC_MAXCALLS-1) /* mask for channel ID */ -#define RXRPC_CIDMASK (~RXRPC_CHANNELMASK) /* mask for connection ID */ -#define RXRPC_CIDSHIFT ilog2(RXRPC_MAXCALLS) /* shift for connection ID */ -#define RXRPC_CID_INC (1 << RXRPC_CIDSHIFT) /* connection ID increment */ - - __be32 callNumber; /* call ID (0 for connection-level packets) */ - __be32 seq; /* sequence number of pkt in call stream */ - __be32 serial; /* serial number of pkt sent to network */ - - uint8_t type; /* packet type */ -#define RXRPC_PACKET_TYPE_DATA 1 /* data */ -#define RXRPC_PACKET_TYPE_ACK 2 /* ACK */ -#define RXRPC_PACKET_TYPE_BUSY 3 /* call reject */ -#define RXRPC_PACKET_TYPE_ABORT 4 /* call/connection abort */ -#define RXRPC_PACKET_TYPE_ACKALL 5 /* ACK all outstanding packets on call */ -#define RXRPC_PACKET_TYPE_CHALLENGE 6 /* connection security challenge (SRVR->CLNT) */ -#define RXRPC_PACKET_TYPE_RESPONSE 7 /* connection secutity response (CLNT->SRVR) */ -#define RXRPC_PACKET_TYPE_DEBUG 8 /* debug info request */ -#define RXRPC_PACKET_TYPE_VERSION 13 /* version string request */ -#define RXRPC_N_PACKET_TYPES 14 /* number of packet types (incl type 0) */ - - uint8_t flags; /* packet flags */ -#define RXRPC_CLIENT_INITIATED 0x01 /* signifies a packet generated by a client */ -#define RXRPC_REQUEST_ACK 0x02 /* request an unconditional ACK of this packet */ -#define RXRPC_LAST_PACKET 0x04 /* the last packet from this side for this call */ -#define RXRPC_MORE_PACKETS 0x08 /* more packets to come */ -#define RXRPC_JUMBO_PACKET 0x20 /* [DATA] this is a jumbo packet */ -#define RXRPC_SLOW_START_OK 0x20 /* [ACK] slow start supported */ - - uint8_t userStatus; /* app-layer defined status */ -#define RXRPC_USERSTATUS_SERVICE_UPGRADE 0x01 /* AuriStor service upgrade request */ - - uint8_t securityIndex; /* security protocol ID */ - union { - __be16 _rsvd; /* reserved */ - __be16 cksum; /* kerberos security checksum */ - }; - __be16 serviceId; /* service ID */ - -} __packed; - -#define RXRPC_SUPPORTED_PACKET_TYPES ( \ - (1 << RXRPC_PACKET_TYPE_DATA) | \ - (1 << RXRPC_PACKET_TYPE_ACK) | \ - (1 << RXRPC_PACKET_TYPE_BUSY) | \ - (1 << RXRPC_PACKET_TYPE_ABORT) | \ - (1 << RXRPC_PACKET_TYPE_ACKALL) | \ - (1 << RXRPC_PACKET_TYPE_CHALLENGE) | \ - (1 << RXRPC_PACKET_TYPE_RESPONSE) | \ - /*(1 << RXRPC_PACKET_TYPE_DEBUG) | */ \ - (1 << RXRPC_PACKET_TYPE_VERSION)) - -/*****************************************************************************/ -/* - * jumbo packet secondary header - * - can be mapped to read header by: - * - new_serial = serial + 1 - * - new_seq = seq + 1 - * - new_flags = j_flags - * - new__rsvd = j__rsvd - * - duplicating all other fields - */ -struct rxrpc_jumbo_header { - uint8_t flags; /* packet flags (as per rxrpc_header) */ - uint8_t pad; - union { - __be16 _rsvd; /* reserved */ - __be16 cksum; /* kerberos security checksum */ - }; -}; - -#define RXRPC_JUMBO_DATALEN 1412 /* non-terminal jumbo packet data length */ -#define RXRPC_JUMBO_SUBPKTLEN (RXRPC_JUMBO_DATALEN + sizeof(struct rxrpc_jumbo_header)) - -/*****************************************************************************/ -/* - * on-the-wire Rx ACK packet data payload - * - all multibyte fields should be in network byte order - */ -struct rxrpc_ackpacket { - __be16 bufferSpace; /* number of packet buffers available */ - __be16 maxSkew; /* diff between serno being ACK'd and highest serial no - * received */ - __be32 firstPacket; /* sequence no of first ACK'd packet in attached list */ - __be32 previousPacket; /* sequence no of previous packet received */ - __be32 serial; /* serial no of packet that prompted this ACK */ - - uint8_t reason; /* reason for ACK */ -#define RXRPC_ACK_REQUESTED 1 /* ACK was requested on packet */ -#define RXRPC_ACK_DUPLICATE 2 /* duplicate packet received */ -#define RXRPC_ACK_OUT_OF_SEQUENCE 3 /* out of sequence packet received */ -#define RXRPC_ACK_EXCEEDS_WINDOW 4 /* packet received beyond end of ACK window */ -#define RXRPC_ACK_NOSPACE 5 /* packet discarded due to lack of buffer space */ -#define RXRPC_ACK_PING 6 /* keep alive ACK */ -#define RXRPC_ACK_PING_RESPONSE 7 /* response to RXRPC_ACK_PING */ -#define RXRPC_ACK_DELAY 8 /* nothing happened since received packet */ -#define RXRPC_ACK_IDLE 9 /* ACK due to fully received ACK window */ -#define RXRPC_ACK__INVALID 10 /* Representation of invalid ACK reason */ - - uint8_t nAcks; /* number of ACKs */ -#define RXRPC_MAXACKS 255 - - uint8_t acks[0]; /* list of ACK/NAKs */ -#define RXRPC_ACK_TYPE_NACK 0 -#define RXRPC_ACK_TYPE_ACK 1 - -} __packed; - -/* Some ACKs refer to specific packets and some are general and can be updated. */ -#define RXRPC_ACK_UPDATEABLE ((1 << RXRPC_ACK_REQUESTED) | \ - (1 << RXRPC_ACK_PING_RESPONSE) | \ - (1 << RXRPC_ACK_DELAY) | \ - (1 << RXRPC_ACK_IDLE)) - - -/* - * ACK packets can have a further piece of information tagged on the end - */ -struct rxrpc_ackinfo { - __be32 rxMTU; /* maximum Rx MTU size (bytes) [AFS 3.3] */ - __be32 maxMTU; /* maximum interface MTU size (bytes) [AFS 3.3] */ - __be32 rwind; /* Rx window size (packets) [AFS 3.4] */ - __be32 jumbo_max; /* max packets to stick into a jumbo packet [AFS 3.5] */ -}; - -/*****************************************************************************/ -/* - * Kerberos security type-2 challenge packet - */ -struct rxkad_challenge { - __be32 version; /* version of this challenge type */ - __be32 nonce; /* encrypted random number */ - __be32 min_level; /* minimum security level */ - __be32 __padding; /* padding to 8-byte boundary */ -} __packed; - -/*****************************************************************************/ -/* - * Kerberos security type-2 response packet - */ -struct rxkad_response { - __be32 version; /* version of this response type */ - __be32 __pad; - - /* encrypted bit of the response */ - struct { - __be32 epoch; /* current epoch */ - __be32 cid; /* parent connection ID */ - __be32 checksum; /* checksum */ - __be32 securityIndex; /* security type */ - __be32 call_id[4]; /* encrypted call IDs */ - __be32 inc_nonce; /* challenge nonce + 1 */ - __be32 level; /* desired level */ - } encrypted; - - __be32 kvno; /* Kerberos key version number */ - __be32 ticket_len; /* Kerberos ticket length */ -} __packed; - -/*****************************************************************************/ -/* - * RxRPC-level abort codes - */ -#define RX_CALL_DEAD -1 /* call/conn has been inactive and is shut down */ -#define RX_INVALID_OPERATION -2 /* invalid operation requested / attempted */ -#define RX_CALL_TIMEOUT -3 /* call timeout exceeded */ -#define RX_EOF -4 /* unexpected end of data on read op */ -#define RX_PROTOCOL_ERROR -5 /* low-level protocol error */ -#define RX_USER_ABORT -6 /* generic user abort */ -#define RX_ADDRINUSE -7 /* UDP port in use */ -#define RX_DEBUGI_BADTYPE -8 /* bad debugging packet type */ - -/* - * (un)marshalling abort codes (rxgen) - */ -#define RXGEN_CC_MARSHAL -450 -#define RXGEN_CC_UNMARSHAL -451 -#define RXGEN_SS_MARSHAL -452 -#define RXGEN_SS_UNMARSHAL -453 -#define RXGEN_DECODE -454 -#define RXGEN_OPCODE -455 -#define RXGEN_SS_XDRFREE -456 -#define RXGEN_CC_XDRFREE -457 - -/* - * Rx kerberos security abort codes - * - unfortunately we have no generalised security abort codes to say things - * like "unsupported security", so we have to use these instead and hope the - * other side understands - */ -#define RXKADINCONSISTENCY 19270400 /* security module structure inconsistent */ -#define RXKADPACKETSHORT 19270401 /* packet too short for security challenge */ -#define RXKADLEVELFAIL 19270402 /* security level negotiation failed */ -#define RXKADTICKETLEN 19270403 /* ticket length too short or too long */ -#define RXKADOUTOFSEQUENCE 19270404 /* packet had bad sequence number */ -#define RXKADNOAUTH 19270405 /* caller not authorised */ -#define RXKADBADKEY 19270406 /* illegal key: bad parity or weak */ -#define RXKADBADTICKET 19270407 /* security object was passed a bad ticket */ -#define RXKADUNKNOWNKEY 19270408 /* ticket contained unknown key version number */ -#define RXKADEXPIRED 19270409 /* authentication expired */ -#define RXKADSEALEDINCON 19270410 /* sealed data inconsistent */ -#define RXKADDATALEN 19270411 /* user data too long */ -#define RXKADILLEGALLEVEL 19270412 /* caller not authorised to use encrypted conns */ - -#endif /* _LINUX_RXRPC_PACKET_H */ diff --git a/include/uapi/linux/rxrpc.h b/include/uapi/linux/rxrpc.h index 08e2fb9c70ae..9656aad8f8f7 100644 --- a/include/uapi/linux/rxrpc.h +++ b/include/uapi/linux/rxrpc.h @@ -77,4 +77,48 @@ enum rxrpc_cmsg_type { #define RXRPC_SECURITY_RXGK 4 /* gssapi-based */ #define RXRPC_SECURITY_RXK5 5 /* kerberos 5 */ +/* + * RxRPC-level abort codes + */ +#define RX_CALL_DEAD -1 /* call/conn has been inactive and is shut down */ +#define RX_INVALID_OPERATION -2 /* invalid operation requested / attempted */ +#define RX_CALL_TIMEOUT -3 /* call timeout exceeded */ +#define RX_EOF -4 /* unexpected end of data on read op */ +#define RX_PROTOCOL_ERROR -5 /* low-level protocol error */ +#define RX_USER_ABORT -6 /* generic user abort */ +#define RX_ADDRINUSE -7 /* UDP port in use */ +#define RX_DEBUGI_BADTYPE -8 /* bad debugging packet type */ + +/* + * (un)marshalling abort codes (rxgen) + */ +#define RXGEN_CC_MARSHAL -450 +#define RXGEN_CC_UNMARSHAL -451 +#define RXGEN_SS_MARSHAL -452 +#define RXGEN_SS_UNMARSHAL -453 +#define RXGEN_DECODE -454 +#define RXGEN_OPCODE -455 +#define RXGEN_SS_XDRFREE -456 +#define RXGEN_CC_XDRFREE -457 + +/* + * Rx kerberos security abort codes + * - unfortunately we have no generalised security abort codes to say things + * like "unsupported security", so we have to use these instead and hope the + * other side understands + */ +#define RXKADINCONSISTENCY 19270400 /* security module structure inconsistent */ +#define RXKADPACKETSHORT 19270401 /* packet too short for security challenge */ +#define RXKADLEVELFAIL 19270402 /* security level negotiation failed */ +#define RXKADTICKETLEN 19270403 /* ticket length too short or too long */ +#define RXKADOUTOFSEQUENCE 19270404 /* packet had bad sequence number */ +#define RXKADNOAUTH 19270405 /* caller not authorised */ +#define RXKADBADKEY 19270406 /* illegal key: bad parity or weak */ +#define RXKADBADTICKET 19270407 /* security object was passed a bad ticket */ +#define RXKADUNKNOWNKEY 19270408 /* ticket contained unknown key version number */ +#define RXKADEXPIRED 19270409 /* authentication expired */ +#define RXKADSEALEDINCON 19270410 /* sealed data inconsistent */ +#define RXKADDATALEN 19270411 /* user data too long */ +#define RXKADILLEGALLEVEL 19270412 /* caller not authorised to use encrypted conns */ + #endif /* _UAPI_LINUX_RXRPC_H */ diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 69b97339ff9d..8c0db9b3e4ab 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -15,7 +15,7 @@ #include #include #include -#include +#include "protocol.h" #if 0 #define CHECK_SLAB_OKAY(X) \ diff --git a/net/rxrpc/protocol.h b/net/rxrpc/protocol.h new file mode 100644 index 000000000000..4bddcf3face3 --- /dev/null +++ b/net/rxrpc/protocol.h @@ -0,0 +1,190 @@ +/* packet.h: Rx packet layout and definitions + * + * Copyright (C) 2002, 2007 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _LINUX_RXRPC_PACKET_H +#define _LINUX_RXRPC_PACKET_H + +typedef u32 rxrpc_seq_t; /* Rx message sequence number */ +typedef u32 rxrpc_serial_t; /* Rx message serial number */ +typedef __be32 rxrpc_seq_net_t; /* on-the-wire Rx message sequence number */ +typedef __be32 rxrpc_serial_net_t; /* on-the-wire Rx message serial number */ + +/*****************************************************************************/ +/* + * on-the-wire Rx packet header + * - all multibyte fields should be in network byte order + */ +struct rxrpc_wire_header { + __be32 epoch; /* client boot timestamp */ +#define RXRPC_RANDOM_EPOCH 0x80000000 /* Random if set, date-based if not */ + + __be32 cid; /* connection and channel ID */ +#define RXRPC_MAXCALLS 4 /* max active calls per conn */ +#define RXRPC_CHANNELMASK (RXRPC_MAXCALLS-1) /* mask for channel ID */ +#define RXRPC_CIDMASK (~RXRPC_CHANNELMASK) /* mask for connection ID */ +#define RXRPC_CIDSHIFT ilog2(RXRPC_MAXCALLS) /* shift for connection ID */ +#define RXRPC_CID_INC (1 << RXRPC_CIDSHIFT) /* connection ID increment */ + + __be32 callNumber; /* call ID (0 for connection-level packets) */ + __be32 seq; /* sequence number of pkt in call stream */ + __be32 serial; /* serial number of pkt sent to network */ + + uint8_t type; /* packet type */ +#define RXRPC_PACKET_TYPE_DATA 1 /* data */ +#define RXRPC_PACKET_TYPE_ACK 2 /* ACK */ +#define RXRPC_PACKET_TYPE_BUSY 3 /* call reject */ +#define RXRPC_PACKET_TYPE_ABORT 4 /* call/connection abort */ +#define RXRPC_PACKET_TYPE_ACKALL 5 /* ACK all outstanding packets on call */ +#define RXRPC_PACKET_TYPE_CHALLENGE 6 /* connection security challenge (SRVR->CLNT) */ +#define RXRPC_PACKET_TYPE_RESPONSE 7 /* connection secutity response (CLNT->SRVR) */ +#define RXRPC_PACKET_TYPE_DEBUG 8 /* debug info request */ +#define RXRPC_PACKET_TYPE_VERSION 13 /* version string request */ +#define RXRPC_N_PACKET_TYPES 14 /* number of packet types (incl type 0) */ + + uint8_t flags; /* packet flags */ +#define RXRPC_CLIENT_INITIATED 0x01 /* signifies a packet generated by a client */ +#define RXRPC_REQUEST_ACK 0x02 /* request an unconditional ACK of this packet */ +#define RXRPC_LAST_PACKET 0x04 /* the last packet from this side for this call */ +#define RXRPC_MORE_PACKETS 0x08 /* more packets to come */ +#define RXRPC_JUMBO_PACKET 0x20 /* [DATA] this is a jumbo packet */ +#define RXRPC_SLOW_START_OK 0x20 /* [ACK] slow start supported */ + + uint8_t userStatus; /* app-layer defined status */ +#define RXRPC_USERSTATUS_SERVICE_UPGRADE 0x01 /* AuriStor service upgrade request */ + + uint8_t securityIndex; /* security protocol ID */ + union { + __be16 _rsvd; /* reserved */ + __be16 cksum; /* kerberos security checksum */ + }; + __be16 serviceId; /* service ID */ + +} __packed; + +#define RXRPC_SUPPORTED_PACKET_TYPES ( \ + (1 << RXRPC_PACKET_TYPE_DATA) | \ + (1 << RXRPC_PACKET_TYPE_ACK) | \ + (1 << RXRPC_PACKET_TYPE_BUSY) | \ + (1 << RXRPC_PACKET_TYPE_ABORT) | \ + (1 << RXRPC_PACKET_TYPE_ACKALL) | \ + (1 << RXRPC_PACKET_TYPE_CHALLENGE) | \ + (1 << RXRPC_PACKET_TYPE_RESPONSE) | \ + /*(1 << RXRPC_PACKET_TYPE_DEBUG) | */ \ + (1 << RXRPC_PACKET_TYPE_VERSION)) + +/*****************************************************************************/ +/* + * jumbo packet secondary header + * - can be mapped to read header by: + * - new_serial = serial + 1 + * - new_seq = seq + 1 + * - new_flags = j_flags + * - new__rsvd = j__rsvd + * - duplicating all other fields + */ +struct rxrpc_jumbo_header { + uint8_t flags; /* packet flags (as per rxrpc_header) */ + uint8_t pad; + union { + __be16 _rsvd; /* reserved */ + __be16 cksum; /* kerberos security checksum */ + }; +}; + +#define RXRPC_JUMBO_DATALEN 1412 /* non-terminal jumbo packet data length */ +#define RXRPC_JUMBO_SUBPKTLEN (RXRPC_JUMBO_DATALEN + sizeof(struct rxrpc_jumbo_header)) + +/*****************************************************************************/ +/* + * on-the-wire Rx ACK packet data payload + * - all multibyte fields should be in network byte order + */ +struct rxrpc_ackpacket { + __be16 bufferSpace; /* number of packet buffers available */ + __be16 maxSkew; /* diff between serno being ACK'd and highest serial no + * received */ + __be32 firstPacket; /* sequence no of first ACK'd packet in attached list */ + __be32 previousPacket; /* sequence no of previous packet received */ + __be32 serial; /* serial no of packet that prompted this ACK */ + + uint8_t reason; /* reason for ACK */ +#define RXRPC_ACK_REQUESTED 1 /* ACK was requested on packet */ +#define RXRPC_ACK_DUPLICATE 2 /* duplicate packet received */ +#define RXRPC_ACK_OUT_OF_SEQUENCE 3 /* out of sequence packet received */ +#define RXRPC_ACK_EXCEEDS_WINDOW 4 /* packet received beyond end of ACK window */ +#define RXRPC_ACK_NOSPACE 5 /* packet discarded due to lack of buffer space */ +#define RXRPC_ACK_PING 6 /* keep alive ACK */ +#define RXRPC_ACK_PING_RESPONSE 7 /* response to RXRPC_ACK_PING */ +#define RXRPC_ACK_DELAY 8 /* nothing happened since received packet */ +#define RXRPC_ACK_IDLE 9 /* ACK due to fully received ACK window */ +#define RXRPC_ACK__INVALID 10 /* Representation of invalid ACK reason */ + + uint8_t nAcks; /* number of ACKs */ +#define RXRPC_MAXACKS 255 + + uint8_t acks[0]; /* list of ACK/NAKs */ +#define RXRPC_ACK_TYPE_NACK 0 +#define RXRPC_ACK_TYPE_ACK 1 + +} __packed; + +/* Some ACKs refer to specific packets and some are general and can be updated. */ +#define RXRPC_ACK_UPDATEABLE ((1 << RXRPC_ACK_REQUESTED) | \ + (1 << RXRPC_ACK_PING_RESPONSE) | \ + (1 << RXRPC_ACK_DELAY) | \ + (1 << RXRPC_ACK_IDLE)) + + +/* + * ACK packets can have a further piece of information tagged on the end + */ +struct rxrpc_ackinfo { + __be32 rxMTU; /* maximum Rx MTU size (bytes) [AFS 3.3] */ + __be32 maxMTU; /* maximum interface MTU size (bytes) [AFS 3.3] */ + __be32 rwind; /* Rx window size (packets) [AFS 3.4] */ + __be32 jumbo_max; /* max packets to stick into a jumbo packet [AFS 3.5] */ +}; + +/*****************************************************************************/ +/* + * Kerberos security type-2 challenge packet + */ +struct rxkad_challenge { + __be32 version; /* version of this challenge type */ + __be32 nonce; /* encrypted random number */ + __be32 min_level; /* minimum security level */ + __be32 __padding; /* padding to 8-byte boundary */ +} __packed; + +/*****************************************************************************/ +/* + * Kerberos security type-2 response packet + */ +struct rxkad_response { + __be32 version; /* version of this response type */ + __be32 __pad; + + /* encrypted bit of the response */ + struct { + __be32 epoch; /* current epoch */ + __be32 cid; /* parent connection ID */ + __be32 checksum; /* checksum */ + __be32 securityIndex; /* security type */ + __be32 call_id[4]; /* encrypted call IDs */ + __be32 inc_nonce; /* challenge nonce + 1 */ + __be32 level; /* desired level */ + } encrypted; + + __be32 kvno; /* Kerberos key version number */ + __be32 ticket_len; /* Kerberos ticket length */ +} __packed; + +#endif /* _LINUX_RXRPC_PACKET_H */ -- cgit v1.2.3-71-gd317 From 784b4e612d42a2b7578d7fab2ed78940e10536bc Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Wed, 19 Jul 2017 16:32:23 +0200 Subject: netfilter: nf_tables: Attach process info to NFT_MSG_NEWGEN notifications This is helpful for 'nft monitor' to track which process caused a given change to the ruleset. Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 2 ++ net/netfilter/nf_tables_api.c | 5 ++++- 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 683f6f88fcac..6f0a950e21c3 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1221,6 +1221,8 @@ enum nft_objref_attributes { enum nft_gen_attributes { NFTA_GEN_UNSPEC, NFTA_GEN_ID, + NFTA_GEN_PROC_PID, + NFTA_GEN_PROC_NAME, __NFTA_GEN_MAX }; #define NFTA_GEN_MAX (__NFTA_GEN_MAX - 1) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 7fbf0070aba1..b77ad0813564 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4657,6 +4657,7 @@ static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net, { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; + char buf[TASK_COMM_LEN]; int event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_NEWGEN); nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), 0); @@ -4668,7 +4669,9 @@ static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net, nfmsg->version = NFNETLINK_V0; nfmsg->res_id = htons(net->nft.base_seq & 0xffff); - if (nla_put_be32(skb, NFTA_GEN_ID, htonl(net->nft.base_seq))) + if (nla_put_be32(skb, NFTA_GEN_ID, htonl(net->nft.base_seq)) || + nla_put_be32(skb, NFTA_GEN_PROC_PID, htonl(task_pid_nr(current))) || + nla_put_string(skb, NFTA_GEN_PROC_NAME, get_task_comm(buf, current))) goto nla_put_failure; nlmsg_end(skb, nlh); -- cgit v1.2.3-71-gd317 From ca1136c99b66b1566781ff12ecddc635d570f932 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 12 Jul 2017 11:49:53 -0700 Subject: blktrace: export cgroup info in trace Currently blktrace isn't cgroup aware. blktrace prints out task name of current context, but the task of current context isn't always in the cgroup where the BIO comes from. We can't use task name to find out IO cgroup. For example, Writeback BIOs always comes from flusher thread but the BIOs are for different blk cgroups. Request could be requeued and dispatched from completely different tasks. MD/DM are another examples. This patch tries to fix the gap. We print out cgroup fhandle info in blktrace. Userspace can use open_by_handle_at() syscall to find the cgroup by fhandle. Or userspace can use name_to_handle_at() syscall to find fhandle for a cgroup and use a BPF program to filter out blktrace for a specific cgroup. We add a new 'blk_cgroup' trace option for blk tracer. It's default off. Application which doesn't know the new option isn't affected. When it's on, we output fhandle info right after blk_io_trace with an extra bit set in event action. So from application point of view, blktrace with the option will output new actions. I didn't change blk trace event yet, since I'm not sure if changing the trace event output is an ABI issue. If not, I'll do it later. Acked-by: Steven Rostedt (VMware) Signed-off-by: Shaohua Li Signed-off-by: Jens Axboe --- include/uapi/linux/blktrace_api.h | 3 + kernel/trace/blktrace.c | 231 ++++++++++++++++++++++++++------------ 2 files changed, 161 insertions(+), 73 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/blktrace_api.h b/include/uapi/linux/blktrace_api.h index c590ca6bfbd9..9cdaedeadb84 100644 --- a/include/uapi/linux/blktrace_api.h +++ b/include/uapi/linux/blktrace_api.h @@ -52,6 +52,7 @@ enum blktrace_act { __BLK_TA_REMAP, /* bio was remapped */ __BLK_TA_ABORT, /* request aborted */ __BLK_TA_DRV_DATA, /* driver-specific binary data */ + __BLK_TA_CGROUP = 1 << 8, /* from a cgroup*/ }; /* @@ -61,6 +62,7 @@ enum blktrace_notify { __BLK_TN_PROCESS = 0, /* establish pid/name mapping */ __BLK_TN_TIMESTAMP, /* include system clock */ __BLK_TN_MESSAGE, /* Character string message */ + __BLK_TN_CGROUP = __BLK_TA_CGROUP, /* from a cgroup */ }; @@ -107,6 +109,7 @@ struct blk_io_trace { __u32 cpu; /* on what cpu did it happen */ __u16 error; /* completion error */ __u16 pdu_len; /* length of data after this trace */ + /* cgroup id will be stored here if exists */ }; /* diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index bc364f86100a..f393d7a43695 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -27,6 +27,7 @@ #include #include #include +#include #include "../../block/blk.h" @@ -46,10 +47,14 @@ static __cacheline_aligned_in_smp DEFINE_SPINLOCK(running_trace_lock); /* Select an alternative, minimalistic output than the original one */ #define TRACE_BLK_OPT_CLASSIC 0x1 +#define TRACE_BLK_OPT_CGROUP 0x2 static struct tracer_opt blk_tracer_opts[] = { /* Default disable the minimalistic output */ { TRACER_OPT(blk_classic, TRACE_BLK_OPT_CLASSIC) }, +#ifdef CONFIG_BLK_CGROUP + { TRACER_OPT(blk_cgroup, TRACE_BLK_OPT_CGROUP) }, +#endif { } }; @@ -68,7 +73,8 @@ 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) + const void *data, size_t len, + union kernfs_node_id *cgid) { struct blk_io_trace *t; struct ring_buffer_event *event = NULL; @@ -76,12 +82,13 @@ 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; if (blk_tracer) { buffer = blk_tr->trace_buffer.buffer; pc = preempt_count(); event = trace_buffer_lock_reserve(buffer, TRACE_BLK, - sizeof(*t) + len, + sizeof(*t) + len + cgid_len, 0, pc); if (!event) return; @@ -92,17 +99,19 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action, if (!bt->rchan) return; - t = relay_reserve(bt->rchan, sizeof(*t) + len); + t = relay_reserve(bt->rchan, sizeof(*t) + len + cgid_len); if (t) { t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION; t->time = ktime_to_ns(ktime_get()); record_it: t->device = bt->dev; - t->action = action; + t->action = action | (cgid ? __BLK_TN_CGROUP : 0); t->pid = pid; t->cpu = cpu; - t->pdu_len = len; - memcpy((void *) t + sizeof(*t), data, len); + t->pdu_len = len + cgid_len; + if (cgid) + memcpy((void *)t + sizeof(*t), cgid, cgid_len); + memcpy((void *) t + sizeof(*t) + cgid_len, data, len); if (blk_tracer) trace_buffer_unlock_commit(blk_tr, buffer, event, 0, pc); @@ -122,7 +131,7 @@ 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)); + sizeof(tsk->comm), NULL); } spin_unlock_irqrestore(&running_trace_lock, flags); } @@ -139,7 +148,7 @@ 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)); + trace_note(bt, 0, BLK_TN_TIMESTAMP, words, sizeof(words), NULL); local_irq_restore(flags); } @@ -167,7 +176,7 @@ void __trace_note_message(struct blk_trace *bt, const char *fmt, ...) n = vscnprintf(buf, BLK_TN_MAX_MSG, fmt, args); va_end(args); - trace_note(bt, 0, BLK_TN_MESSAGE, buf, n); + trace_note(bt, 0, BLK_TN_MESSAGE, buf, n, NULL); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(__trace_note_message); @@ -204,7 +213,7 @@ 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) + void *pdu_data, union kernfs_node_id *cgid) { struct task_struct *tsk = current; struct ring_buffer_event *event = NULL; @@ -215,6 +224,7 @@ 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; if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer)) return; @@ -229,6 +239,8 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, what |= BLK_TC_ACT(BLK_TC_DISCARD); if (op == REQ_OP_FLUSH) what |= BLK_TC_ACT(BLK_TC_FLUSH); + if (cgid) + what |= __BLK_TA_CGROUP; pid = tsk->pid; if (act_log_check(bt, what, sector, pid)) @@ -241,7 +253,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, buffer = blk_tr->trace_buffer.buffer; pc = preempt_count(); event = trace_buffer_lock_reserve(buffer, TRACE_BLK, - sizeof(*t) + pdu_len, + sizeof(*t) + pdu_len + cgid_len, 0, pc); if (!event) return; @@ -258,7 +270,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, * from coming in and stepping on our toes. */ local_irq_save(flags); - t = relay_reserve(bt->rchan, sizeof(*t) + pdu_len); + t = relay_reserve(bt->rchan, sizeof(*t) + pdu_len + cgid_len); if (t) { sequence = per_cpu_ptr(bt->sequence, cpu); @@ -280,10 +292,12 @@ record_it: t->action = what; t->device = bt->dev; t->error = error; - t->pdu_len = pdu_len; + t->pdu_len = pdu_len + cgid_len; + if (cgid_len) + memcpy((void *)t + sizeof(*t), cgid, cgid_len); if (pdu_len) - memcpy((void *) t + sizeof(*t), pdu_data, pdu_len); + memcpy((void *)t + sizeof(*t) + cgid_len, pdu_data, pdu_len); if (blk_tracer) { trace_buffer_unlock_commit(blk_tr, buffer, event, 0, pc); @@ -684,6 +698,36 @@ 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) +{ + struct blk_trace *bt = q->blk_trace; + + if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) + return NULL; + + if (!bio->bi_css) + return NULL; + return cgroup_get_kernfs_id(bio->bi_css->cgroup); +} +#else +static union kernfs_node_id * +blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) +{ + return NULL; +} +#endif + +static union kernfs_node_id * +blk_trace_request_get_cgid(struct request_queue *q, struct request *rq) +{ + if (!rq->bio) + return NULL; + /* Use the first bio */ + return blk_trace_bio_get_cgid(q, rq->bio); +} + /* * blktrace probes */ @@ -694,13 +738,15 @@ void blk_trace_shutdown(struct request_queue *q) * @error: return status to log * @nr_bytes: number of completed bytes * @what: the action + * @cgid: the cgroup info * * Description: * Records an action against a request. Will log the bio offset + size. * **/ static void blk_add_trace_rq(struct request *rq, int error, - unsigned int nr_bytes, u32 what) + unsigned int nr_bytes, u32 what, + union kernfs_node_id *cgid) { struct blk_trace *bt = rq->q->blk_trace; @@ -713,32 +759,36 @@ static void blk_add_trace_rq(struct request *rq, int error, what |= BLK_TC_ACT(BLK_TC_FS); __blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq), - rq->cmd_flags, what, error, 0, NULL); + rq->cmd_flags, what, error, 0, NULL, cgid); } static void blk_add_trace_rq_insert(void *ignore, struct request_queue *q, struct request *rq) { - blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_INSERT); + blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_INSERT, + blk_trace_request_get_cgid(q, rq)); } static void blk_add_trace_rq_issue(void *ignore, struct request_queue *q, struct request *rq) { - blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_ISSUE); + blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_ISSUE, + blk_trace_request_get_cgid(q, rq)); } static void blk_add_trace_rq_requeue(void *ignore, struct request_queue *q, struct request *rq) { - blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_REQUEUE); + blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_REQUEUE, + blk_trace_request_get_cgid(q, rq)); } static void blk_add_trace_rq_complete(void *ignore, struct request *rq, int error, unsigned int nr_bytes) { - blk_add_trace_rq(rq, error, nr_bytes, BLK_TA_COMPLETE); + blk_add_trace_rq(rq, error, nr_bytes, BLK_TA_COMPLETE, + blk_trace_request_get_cgid(rq->q, rq)); } /** @@ -753,7 +803,7 @@ static void blk_add_trace_rq_complete(void *ignore, struct request *rq, * **/ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio, - u32 what, int error) + u32 what, int error, union kernfs_node_id *cgid) { struct blk_trace *bt = q->blk_trace; @@ -761,20 +811,22 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio, return; __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, - bio_op(bio), bio->bi_opf, what, error, 0, NULL); + bio_op(bio), bio->bi_opf, what, error, 0, NULL, cgid); } static void blk_add_trace_bio_bounce(void *ignore, struct request_queue *q, struct bio *bio) { - blk_add_trace_bio(q, bio, BLK_TA_BOUNCE, 0); + blk_add_trace_bio(q, bio, BLK_TA_BOUNCE, 0, + blk_trace_bio_get_cgid(q, bio)); } static void blk_add_trace_bio_complete(void *ignore, struct request_queue *q, struct bio *bio, int error) { - blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, error); + blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, error, + blk_trace_bio_get_cgid(q, bio)); } static void blk_add_trace_bio_backmerge(void *ignore, @@ -782,7 +834,8 @@ static void blk_add_trace_bio_backmerge(void *ignore, struct request *rq, struct bio *bio) { - blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE, 0); + blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE, 0, + blk_trace_bio_get_cgid(q, bio)); } static void blk_add_trace_bio_frontmerge(void *ignore, @@ -790,13 +843,15 @@ static void blk_add_trace_bio_frontmerge(void *ignore, struct request *rq, struct bio *bio) { - blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE, 0); + blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE, 0, + blk_trace_bio_get_cgid(q, bio)); } static void blk_add_trace_bio_queue(void *ignore, struct request_queue *q, struct bio *bio) { - blk_add_trace_bio(q, bio, BLK_TA_QUEUE, 0); + blk_add_trace_bio(q, bio, BLK_TA_QUEUE, 0, + blk_trace_bio_get_cgid(q, bio)); } static void blk_add_trace_getrq(void *ignore, @@ -804,13 +859,14 @@ static void blk_add_trace_getrq(void *ignore, struct bio *bio, int rw) { if (bio) - blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0); + blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0, + blk_trace_bio_get_cgid(q, bio)); else { struct blk_trace *bt = q->blk_trace; if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_GETRQ, 0, 0, - NULL); + NULL, NULL); } } @@ -820,13 +876,14 @@ static void blk_add_trace_sleeprq(void *ignore, struct bio *bio, int rw) { if (bio) - blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0); + blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0, + blk_trace_bio_get_cgid(q, bio)); else { struct blk_trace *bt = q->blk_trace; if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_SLEEPRQ, - 0, 0, NULL); + 0, 0, NULL, NULL); } } @@ -835,7 +892,7 @@ 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); + __blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, NULL); } static void blk_add_trace_unplug(void *ignore, struct request_queue *q, @@ -852,7 +909,7 @@ 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); + __blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, NULL); } } @@ -868,7 +925,7 @@ static void blk_add_trace_split(void *ignore, __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, BLK_TA_SPLIT, bio->bi_status, sizeof(rpdu), - &rpdu); + &rpdu, blk_trace_bio_get_cgid(q, bio)); } } @@ -901,7 +958,7 @@ static void blk_add_trace_bio_remap(void *ignore, __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_status, - sizeof(r), &r); + sizeof(r), &r, blk_trace_bio_get_cgid(q, bio)); } /** @@ -934,7 +991,7 @@ static void blk_add_trace_rq_remap(void *ignore, __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), rq_data_dir(rq), 0, BLK_TA_REMAP, 0, - sizeof(r), &r); + sizeof(r), &r, blk_trace_request_get_cgid(q, rq)); } /** @@ -958,7 +1015,8 @@ void blk_add_driver_data(struct request_queue *q, return; __blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0, - BLK_TA_DRV_DATA, 0, len, data); + BLK_TA_DRV_DATA, 0, len, data, + blk_trace_request_get_cgid(q, rq)); } EXPORT_SYMBOL_GPL(blk_add_driver_data); @@ -1031,7 +1089,7 @@ static void fill_rwbs(char *rwbs, const struct blk_io_trace *t) int i = 0; int tc = t->action >> BLK_TC_SHIFT; - if (t->action == BLK_TN_MESSAGE) { + if ((t->action & ~__BLK_TN_CGROUP) == BLK_TN_MESSAGE) { rwbs[i++] = 'N'; goto out; } @@ -1066,9 +1124,21 @@ const struct blk_io_trace *te_blk_io_trace(const struct trace_entry *ent) return (const struct blk_io_trace *)ent; } -static inline const void *pdu_start(const struct trace_entry *ent) +static inline const void *pdu_start(const struct trace_entry *ent, bool has_cg) { - return te_blk_io_trace(ent) + 1; + return (void *)(te_blk_io_trace(ent) + 1) + + (has_cg ? sizeof(union kernfs_node_id) : 0); +} + +static inline const void *cgid_start(const struct trace_entry *ent) +{ + return (void *)(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); } static inline u32 t_action(const struct trace_entry *ent) @@ -1096,16 +1166,16 @@ static inline __u16 t_error(const struct trace_entry *ent) return te_blk_io_trace(ent)->error; } -static __u64 get_pdu_int(const struct trace_entry *ent) +static __u64 get_pdu_int(const struct trace_entry *ent, bool has_cg) { - const __u64 *val = pdu_start(ent); + const __u64 *val = pdu_start(ent, has_cg); return be64_to_cpu(*val); } static void get_pdu_remap(const struct trace_entry *ent, - struct blk_io_trace_remap *r) + struct blk_io_trace_remap *r, bool has_cg) { - const struct blk_io_trace_remap *__r = pdu_start(ent); + const struct blk_io_trace_remap *__r = pdu_start(ent, has_cg); __u64 sector_from = __r->sector_from; r->device_from = be32_to_cpu(__r->device_from); @@ -1113,9 +1183,11 @@ static void get_pdu_remap(const struct trace_entry *ent, r->sector_from = be64_to_cpu(sector_from); } -typedef void (blk_log_action_t) (struct trace_iterator *iter, const char *act); +typedef void (blk_log_action_t) (struct trace_iterator *iter, const char *act, + bool has_cg); -static void blk_log_action_classic(struct trace_iterator *iter, const char *act) +static void blk_log_action_classic(struct trace_iterator *iter, const char *act, + bool has_cg) { char rwbs[RWBS_LEN]; unsigned long long ts = iter->ts; @@ -1131,24 +1203,33 @@ static void blk_log_action_classic(struct trace_iterator *iter, const char *act) secs, nsec_rem, iter->ent->pid, act, rwbs); } -static void blk_log_action(struct trace_iterator *iter, const char *act) +static void blk_log_action(struct trace_iterator *iter, const char *act, + bool has_cg) { char rwbs[RWBS_LEN]; const struct blk_io_trace *t = te_blk_io_trace(iter->ent); fill_rwbs(rwbs, t); - trace_seq_printf(&iter->seq, "%3d,%-3d %2s %3s ", - MAJOR(t->device), MINOR(t->device), act, rwbs); + if (has_cg) { + const union kernfs_node_id *id = cgid_start(iter->ent); + + trace_seq_printf(&iter->seq, "%3d,%-3d %x,%-x %2s %3s ", + MAJOR(t->device), MINOR(t->device), + id->ino, id->generation, act, rwbs); + } else + trace_seq_printf(&iter->seq, "%3d,%-3d %2s %3s ", + MAJOR(t->device), MINOR(t->device), act, rwbs); } -static void blk_log_dump_pdu(struct trace_seq *s, const struct trace_entry *ent) +static void blk_log_dump_pdu(struct trace_seq *s, + const struct trace_entry *ent, bool has_cg) { const unsigned char *pdu_buf; int pdu_len; int i, end; - pdu_buf = pdu_start(ent); - pdu_len = te_blk_io_trace(ent)->pdu_len; + pdu_buf = pdu_start(ent, has_cg); + pdu_len = pdu_real_len(ent, has_cg); if (!pdu_len) return; @@ -1179,7 +1260,7 @@ static void blk_log_dump_pdu(struct trace_seq *s, const struct trace_entry *ent) trace_seq_puts(s, ") "); } -static void blk_log_generic(struct trace_seq *s, const struct trace_entry *ent) +static void blk_log_generic(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { char cmd[TASK_COMM_LEN]; @@ -1187,7 +1268,7 @@ static void blk_log_generic(struct trace_seq *s, const struct trace_entry *ent) if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) { trace_seq_printf(s, "%u ", t_bytes(ent)); - blk_log_dump_pdu(s, ent); + blk_log_dump_pdu(s, ent, has_cg); trace_seq_printf(s, "[%s]\n", cmd); } else { if (t_sec(ent)) @@ -1199,10 +1280,10 @@ static void blk_log_generic(struct trace_seq *s, const struct trace_entry *ent) } static void blk_log_with_error(struct trace_seq *s, - const struct trace_entry *ent) + const struct trace_entry *ent, bool has_cg) { if (t_action(ent) & BLK_TC_ACT(BLK_TC_PC)) { - blk_log_dump_pdu(s, ent); + blk_log_dump_pdu(s, ent, has_cg); trace_seq_printf(s, "[%d]\n", t_error(ent)); } else { if (t_sec(ent)) @@ -1215,18 +1296,18 @@ static void blk_log_with_error(struct trace_seq *s, } } -static void blk_log_remap(struct trace_seq *s, const struct trace_entry *ent) +static void blk_log_remap(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { struct blk_io_trace_remap r = { .device_from = 0, }; - get_pdu_remap(ent, &r); + get_pdu_remap(ent, &r, has_cg); trace_seq_printf(s, "%llu + %u <- (%d,%d) %llu\n", t_sector(ent), t_sec(ent), MAJOR(r.device_from), MINOR(r.device_from), (unsigned long long)r.sector_from); } -static void blk_log_plug(struct trace_seq *s, const struct trace_entry *ent) +static void blk_log_plug(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { char cmd[TASK_COMM_LEN]; @@ -1235,30 +1316,31 @@ static void blk_log_plug(struct trace_seq *s, const struct trace_entry *ent) trace_seq_printf(s, "[%s]\n", cmd); } -static void blk_log_unplug(struct trace_seq *s, const struct trace_entry *ent) +static void blk_log_unplug(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { char cmd[TASK_COMM_LEN]; trace_find_cmdline(ent->pid, cmd); - trace_seq_printf(s, "[%s] %llu\n", cmd, get_pdu_int(ent)); + trace_seq_printf(s, "[%s] %llu\n", cmd, get_pdu_int(ent, has_cg)); } -static void blk_log_split(struct trace_seq *s, const struct trace_entry *ent) +static void blk_log_split(struct trace_seq *s, const struct trace_entry *ent, bool has_cg) { char cmd[TASK_COMM_LEN]; trace_find_cmdline(ent->pid, cmd); trace_seq_printf(s, "%llu / %llu [%s]\n", t_sector(ent), - get_pdu_int(ent), cmd); + get_pdu_int(ent, has_cg), cmd); } -static void blk_log_msg(struct trace_seq *s, const struct trace_entry *ent) +static void blk_log_msg(struct trace_seq *s, const struct trace_entry *ent, + bool has_cg) { - const struct blk_io_trace *t = te_blk_io_trace(ent); - trace_seq_putmem(s, t + 1, t->pdu_len); + trace_seq_putmem(s, pdu_start(ent, has_cg), + pdu_real_len(ent, has_cg)); trace_seq_putc(s, '\n'); } @@ -1298,7 +1380,8 @@ static void blk_tracer_reset(struct trace_array *tr) static const struct { const char *act[2]; - void (*print)(struct trace_seq *s, const struct trace_entry *ent); + void (*print)(struct trace_seq *s, const struct trace_entry *ent, + bool has_cg); } what2act[] = { [__BLK_TA_QUEUE] = {{ "Q", "queue" }, blk_log_generic }, [__BLK_TA_BACKMERGE] = {{ "M", "backmerge" }, blk_log_generic }, @@ -1326,23 +1409,25 @@ static enum print_line_t print_one_line(struct trace_iterator *iter, u16 what; bool long_act; blk_log_action_t *log_action; + bool has_cg; t = te_blk_io_trace(iter->ent); - what = t->action & ((1 << BLK_TC_SHIFT) - 1); + what = (t->action & ((1 << BLK_TC_SHIFT) - 1)) & ~__BLK_TA_CGROUP; long_act = !!(tr->trace_flags & TRACE_ITER_VERBOSE); log_action = classic ? &blk_log_action_classic : &blk_log_action; + has_cg = t->action & __BLK_TA_CGROUP; - if (t->action == BLK_TN_MESSAGE) { - log_action(iter, long_act ? "message" : "m"); - blk_log_msg(s, iter->ent); + if ((t->action & ~__BLK_TN_CGROUP) == BLK_TN_MESSAGE) { + log_action(iter, long_act ? "message" : "m", has_cg); + blk_log_msg(s, iter->ent, has_cg); return trace_handle_return(s); } if (unlikely(what == 0 || what >= ARRAY_SIZE(what2act))) trace_seq_printf(s, "Unknown action %x\n", what); else { - log_action(iter, what2act[what].act[long_act]); - what2act[what].print(s, iter->ent); + log_action(iter, what2act[what].act[long_act], has_cg); + what2act[what].print(s, iter->ent, has_cg); } return trace_handle_return(s); -- cgit v1.2.3-71-gd317 From 1a5f3da20bd966220931239fbd31e6ac6ff42251 Mon Sep 17 00:00:00 2001 From: Vidya Sagar Ravipati Date: Thu, 27 Jul 2017 16:47:26 -0700 Subject: net: ethtool: add support for forward error correction modes Forward Error Correction (FEC) modes i.e Base-R and Reed-Solomon modes are introduced in 25G/40G/100G standards for providing good BER at high speeds. Various networking devices which support 25G/40G/100G provides ability to manage supported FEC modes and the lack of FEC encoding control and reporting today is a source for interoperability issues for many vendors. FEC capability as well as specific FEC mode i.e. Base-R or RS modes can be requested or advertised through bits D44:47 of base link codeword. This patch set intends to provide option under ethtool to manage and report FEC encoding settings for networking devices as per IEEE 802.3 bj, bm and by specs. set-fec/show-fec option(s) are designed to provide control and report the FEC encoding on the link. SET FEC option: root@tor: ethtool --set-fec swp1 encoding [off | RS | BaseR | auto] Encoding: Types of encoding Off : Turning off any encoding RS : enforcing RS-FEC encoding on supported speeds BaseR : enforcing Base R encoding on supported speeds Auto : IEEE defaults for the speed/medium combination Here are a few examples of what we would expect if encoding=auto: - if autoneg is on, we are expecting FEC to be negotiated as on or off as long as protocol supports it - if the hardware is capable of detecting the FEC encoding on it's receiver it will reconfigure its encoder to match - in absence of the above, the configuration would be set to IEEE defaults. >From our understanding , this is essentially what most hardware/driver combinations are doing today in the absence of a way for users to control the behavior. SHOW FEC option: root@tor: ethtool --show-fec swp1 FEC parameters for swp1: Active FEC encodings: RS Configured FEC encodings: RS | BaseR ETHTOOL DEVNAME output modification: ethtool devname output: root@tor:~# ethtool swp1 Settings for swp1: root@hpe-7712-03:~# ethtool swp18 Settings for swp18: Supported ports: [ FIBRE ] Supported link modes: 40000baseCR4/Full 40000baseSR4/Full 40000baseLR4/Full 100000baseSR4/Full 100000baseCR4/Full 100000baseLR4_ER4/Full Supported pause frame use: No Supports auto-negotiation: Yes Supported FEC modes: [RS | BaseR | None | Not reported] Advertised link modes: Not reported Advertised pause frame use: No Advertised auto-negotiation: No Advertised FEC modes: [RS | BaseR | None | Not reported] <<<< One or more FEC modes Speed: 100000Mb/s Duplex: Full Port: FIBRE PHYAD: 106 Transceiver: internal Auto-negotiation: off Link detected: yes This patch includes following changes a) New ETHTOOL_SFECPARAM/SFECPARAM API, handled by the new get_fecparam/set_fecparam callbacks, provides support for configuration of forward error correction modes. b) Link mode bits for FEC modes i.e. None (No FEC mode), RS, BaseR/FC are defined so that users can configure these fec modes for supported and advertising fields as part of link autonegotiation. Signed-off-by: Vidya Sagar Ravipati Signed-off-by: Dustin Byford Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/linux/ethtool.h | 4 ++++ include/uapi/linux/ethtool.h | 48 +++++++++++++++++++++++++++++++++++++++++++- net/core/ethtool.c | 34 +++++++++++++++++++++++++++++++ 3 files changed, 85 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 83cc9863444b..afdbb701fdb4 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -374,5 +374,9 @@ struct ethtool_ops { struct ethtool_link_ksettings *); int (*set_link_ksettings)(struct net_device *, const struct ethtool_link_ksettings *); + int (*get_fecparam)(struct net_device *, + struct ethtool_fecparam *); + int (*set_fecparam)(struct net_device *, + struct ethtool_fecparam *); }; #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 7d4a594d5d58..9c041dae8e2c 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1238,6 +1238,47 @@ struct ethtool_per_queue_op { char data[]; }; +/** + * struct ethtool_fecparam - Ethernet forward error correction(fec) parameters + * @cmd: Command number = %ETHTOOL_GFECPARAM or %ETHTOOL_SFECPARAM + * @active_fec: FEC mode which is active on porte + * @fec: Bitmask of supported/configured FEC modes + * @rsvd: Reserved for future extensions. i.e FEC bypass feature. + * + * Drivers should reject a non-zero setting of @autoneg when + * autoneogotiation is disabled (or not supported) for the link. + * + */ +struct ethtool_fecparam { + __u32 cmd; + /* bitmask of FEC modes */ + __u32 active_fec; + __u32 fec; + __u32 reserved; +}; + +/** + * enum ethtool_fec_config_bits - flags definition of ethtool_fec_configuration + * @ETHTOOL_FEC_NONE: FEC mode configuration is not supported + * @ETHTOOL_FEC_AUTO: Default/Best FEC mode provided by driver + * @ETHTOOL_FEC_OFF: No FEC Mode + * @ETHTOOL_FEC_RS: Reed-Solomon Forward Error Detection mode + * @ETHTOOL_FEC_BASER: Base-R/Reed-Solomon Forward Error Detection mode + */ +enum ethtool_fec_config_bits { + ETHTOOL_FEC_NONE_BIT, + ETHTOOL_FEC_AUTO_BIT, + ETHTOOL_FEC_OFF_BIT, + ETHTOOL_FEC_RS_BIT, + ETHTOOL_FEC_BASER_BIT, +}; + +#define ETHTOOL_FEC_NONE (1 << ETHTOOL_FEC_NONE_BIT) +#define ETHTOOL_FEC_AUTO (1 << ETHTOOL_FEC_AUTO_BIT) +#define ETHTOOL_FEC_OFF (1 << ETHTOOL_FEC_OFF_BIT) +#define ETHTOOL_FEC_RS (1 << ETHTOOL_FEC_RS_BIT) +#define ETHTOOL_FEC_BASER (1 << ETHTOOL_FEC_BASER_BIT) + /* CMDs currently supported */ #define ETHTOOL_GSET 0x00000001 /* DEPRECATED, Get settings. * Please use ETHTOOL_GLINKSETTINGS @@ -1330,6 +1371,8 @@ struct ethtool_per_queue_op { #define ETHTOOL_SLINKSETTINGS 0x0000004d /* Set ethtool_link_settings */ #define ETHTOOL_PHY_GTUNABLE 0x0000004e /* Get PHY tunable configuration */ #define ETHTOOL_PHY_STUNABLE 0x0000004f /* Set PHY tunable configuration */ +#define ETHTOOL_GFECPARAM 0x00000050 /* Get FEC settings */ +#define ETHTOOL_SFECPARAM 0x00000051 /* Set FEC settings */ /* compatibility with older code */ #define SPARC_ETH_GSET ETHTOOL_GSET @@ -1387,6 +1430,9 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_2500baseT_Full_BIT = 47, ETHTOOL_LINK_MODE_5000baseT_Full_BIT = 48, + ETHTOOL_LINK_MODE_FEC_NONE_BIT = 49, + ETHTOOL_LINK_MODE_FEC_RS_BIT = 50, + ETHTOOL_LINK_MODE_FEC_BASER_BIT = 51, /* Last allowed bit for __ETHTOOL_LINK_MODE_LEGACY_MASK is bit * 31. Please do NOT define any SUPPORTED_* or ADVERTISED_* @@ -1395,7 +1441,7 @@ enum ethtool_link_mode_bit_indices { */ __ETHTOOL_LINK_MODE_LAST - = ETHTOOL_LINK_MODE_5000baseT_Full_BIT, + = ETHTOOL_LINK_MODE_FEC_BASER_BIT, }; #define __ETHTOOL_LINK_MODE_LEGACY_MASK(base_name) \ diff --git a/net/core/ethtool.c b/net/core/ethtool.c index b987bc475fc8..6a582ae4c5d9 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -2512,6 +2512,33 @@ static int set_phy_tunable(struct net_device *dev, void __user *useraddr) return ret; } +static int ethtool_get_fecparam(struct net_device *dev, void __user *useraddr) +{ + struct ethtool_fecparam fecparam = { ETHTOOL_GFECPARAM }; + + if (!dev->ethtool_ops->get_fecparam) + return -EOPNOTSUPP; + + dev->ethtool_ops->get_fecparam(dev, &fecparam); + + if (copy_to_user(useraddr, &fecparam, sizeof(fecparam))) + return -EFAULT; + return 0; +} + +static int ethtool_set_fecparam(struct net_device *dev, void __user *useraddr) +{ + struct ethtool_fecparam fecparam; + + if (!dev->ethtool_ops->set_fecparam) + return -EOPNOTSUPP; + + if (copy_from_user(&fecparam, useraddr, sizeof(fecparam))) + return -EFAULT; + + return dev->ethtool_ops->set_fecparam(dev, &fecparam); +} + /* The main entry point in this file. Called from net/core/dev_ioctl.c */ int dev_ethtool(struct net *net, struct ifreq *ifr) @@ -2570,6 +2597,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GTUNABLE: case ETHTOOL_PHY_GTUNABLE: case ETHTOOL_GLINKSETTINGS: + case ETHTOOL_GFECPARAM: break; default: if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) @@ -2779,6 +2807,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_PHY_STUNABLE: rc = set_phy_tunable(dev, useraddr); break; + case ETHTOOL_GFECPARAM: + rc = ethtool_get_fecparam(dev, useraddr); + break; + case ETHTOOL_SFECPARAM: + rc = ethtool_set_fecparam(dev, useraddr); + break; default: rc = -EOPNOTSUPP; } -- cgit v1.2.3-71-gd317 From 64c83d837329531252a1a0f0dfdd4fd607e1d8e9 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sun, 30 Jul 2017 13:24:49 -0400 Subject: net netlink: Add new type NLA_BITFIELD32 Generic bitflags attribute content sent to the kernel by user. With this netlink attr type the user can either set or unset a flag in the kernel. The value is a bitmap that defines the bit values being set The selector is a bitmask that defines which value bit is to be considered. A check is made to ensure the rules that a kernel subsystem always conforms to bitflags the kernel already knows about. i.e if the user tries to set a bit flag that is not understood then the _it will be rejected_. In the most basic form, the user specifies the attribute policy as: [ATTR_GOO] = { .type = NLA_BITFIELD32, .validation_data = &myvalidflags }, where myvalidflags is the bit mask of the flags the kernel understands. If the user _does not_ provide myvalidflags then the attribute will also be rejected. Examples: value = 0x0, and selector = 0x1 implies we are selecting bit 1 and we want to set its value to 0. value = 0x2, and selector = 0x2 implies we are selecting bit 2 and we want to set its value to 1. Suggested-by: Jiri Pirko Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/netlink.h | 16 ++++++++++++++++ include/uapi/linux/netlink.h | 17 +++++++++++++++++ lib/nlattr.c | 30 ++++++++++++++++++++++++++++++ 3 files changed, 63 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/netlink.h b/include/net/netlink.h index ef8e6c3a80a6..82dd298b40c7 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -178,6 +178,7 @@ enum { NLA_S16, NLA_S32, NLA_S64, + NLA_BITFIELD32, __NLA_TYPE_MAX, }; @@ -206,6 +207,7 @@ enum { * NLA_MSECS Leaving the length field zero will verify the * given type fits, using it verifies minimum length * just like "All other" + * NLA_BITFIELD32 A 32-bit bitmap/bitselector attribute * All other Minimum length of attribute payload * * Example: @@ -213,11 +215,13 @@ enum { * [ATTR_FOO] = { .type = NLA_U16 }, * [ATTR_BAR] = { .type = NLA_STRING, .len = BARSIZ }, * [ATTR_BAZ] = { .len = sizeof(struct mystruct) }, + * [ATTR_GOO] = { .type = NLA_BITFIELD32, .validation_data = &myvalidflags }, * }; */ struct nla_policy { u16 type; u16 len; + void *validation_data; }; /** @@ -1202,6 +1206,18 @@ static inline struct in6_addr nla_get_in6_addr(const struct nlattr *nla) return tmp; } +/** + * nla_get_bitfield32 - return payload of 32 bitfield attribute + * @nla: nla_bitfield32 attribute + */ +static inline struct nla_bitfield32 nla_get_bitfield32(const struct nlattr *nla) +{ + struct nla_bitfield32 tmp; + + nla_memcpy(&tmp, nla, sizeof(tmp)); + return tmp; +} + /** * nla_memdup - duplicate attribute memory (kmemdup) * @src: netlink attribute to duplicate from diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index f86127a46cfc..f4fc9c9e123d 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -226,5 +226,22 @@ struct nlattr { #define NLA_ALIGN(len) (((len) + NLA_ALIGNTO - 1) & ~(NLA_ALIGNTO - 1)) #define NLA_HDRLEN ((int) NLA_ALIGN(sizeof(struct nlattr))) +/* Generic 32 bitflags attribute content sent to the kernel. + * + * The value is a bitmap that defines the values being set + * The selector is a bitmask that defines which value is legit + * + * Examples: + * value = 0x0, and selector = 0x1 + * implies we are selecting bit 1 and we want to set its value to 0. + * + * value = 0x2, and selector = 0x2 + * implies we are selecting bit 2 and we want to set its value to 1. + * + */ +struct nla_bitfield32 { + __u32 value; + __u32 selector; +}; #endif /* _UAPI__LINUX_NETLINK_H */ diff --git a/lib/nlattr.c b/lib/nlattr.c index fb52435be42d..ee79b7a3c6b0 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -27,6 +27,30 @@ static const u8 nla_attr_minlen[NLA_TYPE_MAX+1] = { [NLA_S64] = sizeof(s64), }; +static int validate_nla_bitfield32(const struct nlattr *nla, + u32 *valid_flags_allowed) +{ + const struct nla_bitfield32 *bf = nla_data(nla); + u32 *valid_flags_mask = valid_flags_allowed; + + if (!valid_flags_allowed) + return -EINVAL; + + /*disallow invalid bit selector */ + if (bf->selector & ~*valid_flags_mask) + return -EINVAL; + + /*disallow invalid bit values */ + if (bf->value & ~*valid_flags_mask) + return -EINVAL; + + /*disallow valid bit values that are not selected*/ + if (bf->value & ~bf->selector) + return -EINVAL; + + return 0; +} + static int validate_nla(const struct nlattr *nla, int maxtype, const struct nla_policy *policy) { @@ -46,6 +70,12 @@ static int validate_nla(const struct nlattr *nla, int maxtype, return -ERANGE; break; + case NLA_BITFIELD32: + if (attrlen != sizeof(struct nla_bitfield32)) + return -ERANGE; + + return validate_nla_bitfield32(nla, pt->validation_data); + case NLA_NUL_STRING: if (pt->len) minlen = min_t(int, attrlen, pt->len + 1); -- cgit v1.2.3-71-gd317 From 90825b23a887f06f6c05bdde77b200c5fe9b6217 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sun, 30 Jul 2017 13:24:51 -0400 Subject: net sched actions: dump more than TCA_ACT_MAX_PRIO actions per batch When you dump hundreds of thousands of actions, getting only 32 per dump batch even when the socket buffer and memory allocations allow is inefficient. With this change, the user will get as many as possibly fitting within the given constraints available to the kernel. The top level action TLV space is extended. An attribute TCA_ROOT_FLAGS is used to carry flags; flag TCA_FLAG_LARGE_DUMP_ON is set by the user indicating the user is capable of processing these large dumps. Older user space which doesnt set this flag doesnt get the large (than 32) batches. The kernel uses the TCA_ROOT_COUNT attribute to tell the user how many actions are put in a single batch. As such user space app knows how long to iterate (independent of the type of action being dumped) instead of hardcoded maximum of 32 thus maintaining backward compat. Some results dumping 1.5M actions below: first an unpatched tc which doesnt understand these features... prompt$ time -p tc actions ls action gact | grep index | wc -l 1500000 real 1388.43 user 2.07 sys 1386.79 Now lets see a patched tc which sets the correct flags when requesting a dump: prompt$ time -p updatedtc actions ls action gact | grep index | wc -l 1500000 real 178.13 user 2.02 sys 176.96 That is about 8x performance improvement for tc app which sets its receive buffer to about 32K. Signed-off-by: Jamal Hadi Salim Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/rtnetlink.h | 22 +++++++++++++++++-- net/sched/act_api.c | 50 +++++++++++++++++++++++++++++++++--------- 2 files changed, 60 insertions(+), 12 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index d148505010a7..bfa80a6164d9 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -683,10 +683,28 @@ struct tcamsg { unsigned char tca__pad1; unsigned short tca__pad2; }; + +enum { + TCA_ROOT_UNSPEC, + TCA_ROOT_TAB, +#define TCA_ACT_TAB TCA_ROOT_TAB +#define TCAA_MAX TCA_ROOT_TAB + TCA_ROOT_FLAGS, + TCA_ROOT_COUNT, + __TCA_ROOT_MAX, +#define TCA_ROOT_MAX (__TCA_ROOT_MAX - 1) +}; + #define TA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct tcamsg)))) #define TA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct tcamsg)) -#define TCA_ACT_TAB 1 /* attr type must be >=1 */ -#define TCAA_MAX 1 +/* tcamsg flags stored in attribute TCA_ROOT_FLAGS + * + * TCA_FLAG_LARGE_DUMP_ON user->kernel to request for larger than TCA_ACT_MAX_PRIO + * actions in a dump. All dump responses will contain the number of actions + * being dumped stored in for user app's consumption in TCA_ROOT_COUNT + * + */ +#define TCA_FLAG_LARGE_DUMP_ON (1 << 0) /* New extended info filters for IFLA_EXT_MASK */ #define RTEXT_FILTER_VF (1 << 0) diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 848370e2fcca..d53653a73c4f 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -110,6 +110,7 @@ static int tcf_dump_walker(struct tcf_hashinfo *hinfo, struct sk_buff *skb, struct netlink_callback *cb) { int err = 0, index = -1, i = 0, s_i = 0, n_i = 0; + u32 act_flags = cb->args[2]; struct nlattr *nest; spin_lock_bh(&hinfo->lock); @@ -138,14 +139,18 @@ static int tcf_dump_walker(struct tcf_hashinfo *hinfo, struct sk_buff *skb, } nla_nest_end(skb, nest); n_i++; - if (n_i >= TCA_ACT_MAX_PRIO) + if (!(act_flags & TCA_FLAG_LARGE_DUMP_ON) && + n_i >= TCA_ACT_MAX_PRIO) goto done; } } done: spin_unlock_bh(&hinfo->lock); - if (n_i) + if (n_i) { cb->args[0] += n_i; + if (act_flags & TCA_FLAG_LARGE_DUMP_ON) + cb->args[1] = n_i; + } return n_i; nla_put_failure: @@ -1068,11 +1073,17 @@ static int tcf_action_add(struct net *net, struct nlattr *nla, return tcf_add_notify(net, n, &actions, portid); } +static u32 tcaa_root_flags_allowed = TCA_FLAG_LARGE_DUMP_ON; +static const struct nla_policy tcaa_policy[TCA_ROOT_MAX + 1] = { + [TCA_ROOT_FLAGS] = { .type = NLA_BITFIELD32, + .validation_data = &tcaa_root_flags_allowed }, +}; + static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); - struct nlattr *tca[TCAA_MAX + 1]; + struct nlattr *tca[TCA_ROOT_MAX + 1]; u32 portid = skb ? NETLINK_CB(skb).portid : 0; int ret = 0, ovr = 0; @@ -1080,7 +1091,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; - ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCAA_MAX, NULL, + ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ROOT_MAX, NULL, extack); if (ret < 0) return ret; @@ -1121,16 +1132,12 @@ replay: return ret; } -static struct nlattr *find_dump_kind(const struct nlmsghdr *n) +static struct nlattr *find_dump_kind(struct nlattr **nla) { struct nlattr *tb1, *tb2[TCA_ACT_MAX + 1]; struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; - struct nlattr *nla[TCAA_MAX + 1]; struct nlattr *kind; - if (nlmsg_parse(n, sizeof(struct tcamsg), nla, TCAA_MAX, - NULL, NULL) < 0) - return NULL; tb1 = nla[TCA_ACT_TAB]; if (tb1 == NULL) return NULL; @@ -1157,8 +1164,18 @@ static int tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) struct tc_action_ops *a_o; int ret = 0; struct tcamsg *t = (struct tcamsg *) nlmsg_data(cb->nlh); - struct nlattr *kind = find_dump_kind(cb->nlh); + struct nlattr *tb[TCA_ROOT_MAX + 1]; + struct nlattr *count_attr = NULL; + struct nlattr *kind = NULL; + struct nla_bitfield32 bf; + u32 act_count = 0; + + ret = nlmsg_parse(cb->nlh, sizeof(struct tcamsg), tb, TCA_ROOT_MAX, + tcaa_policy, NULL); + if (ret < 0) + return ret; + kind = find_dump_kind(tb); if (kind == NULL) { pr_info("tc_dump_action: action bad kind\n"); return 0; @@ -1168,14 +1185,24 @@ static int tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) if (a_o == NULL) return 0; + cb->args[2] = 0; + if (tb[TCA_ROOT_FLAGS]) { + bf = nla_get_bitfield32(tb[TCA_ROOT_FLAGS]); + cb->args[2] = bf.value; + } + nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cb->nlh->nlmsg_type, sizeof(*t), 0); if (!nlh) goto out_module_put; + t = nlmsg_data(nlh); t->tca_family = AF_UNSPEC; t->tca__pad1 = 0; t->tca__pad2 = 0; + count_attr = nla_reserve(skb, TCA_ROOT_COUNT, sizeof(u32)); + if (!count_attr) + goto out_module_put; nest = nla_nest_start(skb, TCA_ACT_TAB); if (nest == NULL) @@ -1188,6 +1215,9 @@ static int tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) if (ret > 0) { nla_nest_end(skb, nest); ret = skb->len; + act_count = cb->args[1]; + memcpy(nla_data(count_attr), &act_count, sizeof(u32)); + cb->args[1] = 0; } else nlmsg_trim(skb, b); -- cgit v1.2.3-71-gd317 From e62e484df04964ac947c679ef4f00c54ae5395aa Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sun, 30 Jul 2017 13:24:52 -0400 Subject: net sched actions: add time filter for action dumping This patch adds support for filtering based on time since last used. When we are dumping a large number of actions it is useful to have the option of filtering based on when the action was last used to reduce the amount of data crossing to user space. With this patch the user space app sets the TCA_ROOT_TIME_DELTA attribute with the value in milliseconds with "time of interest since now". The kernel converts this to jiffies and does the filtering comparison matching entries that have seen activity since then and returns them to user space. Old kernels and old tc continue to work in legacy mode since they dont specify this attribute. Some example (we have 400 actions bound to 400 filters); at installation time. Using updated when tc setting the time of interest to 120 seconds earlier (we see 400 actions): prompt$ hackedtc actions ls action gact since 120000| grep index | wc -l 400 go get some coffee and wait for > 120 seconds and try again: prompt$ hackedtc actions ls action gact since 120000 | grep index | wc -l 0 Lets see a filter bound to one of these actions: .... filter pref 10 u32 filter pref 10 u32 fh 800: ht divisor 1 filter pref 10 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 2 success 1) match 7f000002/ffffffff at 12 (success 1 ) action order 1: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1145 sec used 802 sec Action statistics: Sent 84 bytes 1 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 .... that coffee took long, no? It was good. Now lets ping -c 1 127.0.0.2, then run the actions again: prompt$ hackedtc actions ls action gact since 120 | grep index | wc -l 1 More details please: prompt$ hackedtc -s actions ls action gact since 120000 action order 0: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1270 sec used 30 sec Action statistics: Sent 168 bytes 2 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 And the filter? filter pref 10 u32 filter pref 10 u32 fh 800: ht divisor 1 filter pref 10 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:10 (rule hit 4 success 2) match 7f000002/ffffffff at 12 (success 2 ) action order 1: gact action pass random type none pass val 0 index 23 ref 2 bind 1 installed 1324 sec used 84 sec Action statistics: Sent 168 bytes 2 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 Signed-off-by: Jamal Hadi Salim Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/rtnetlink.h | 1 + net/sched/act_api.c | 21 ++++++++++++++++++++- 2 files changed, 21 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index bfa80a6164d9..dab7dad9e01a 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -691,6 +691,7 @@ enum { #define TCAA_MAX TCA_ROOT_TAB TCA_ROOT_FLAGS, TCA_ROOT_COUNT, + TCA_ROOT_TIME_DELTA, /* in msecs */ __TCA_ROOT_MAX, #define TCA_ROOT_MAX (__TCA_ROOT_MAX - 1) }; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index d53653a73c4f..f19b118df414 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -111,6 +111,7 @@ static int tcf_dump_walker(struct tcf_hashinfo *hinfo, struct sk_buff *skb, { int err = 0, index = -1, i = 0, s_i = 0, n_i = 0; u32 act_flags = cb->args[2]; + unsigned long jiffy_since = cb->args[3]; struct nlattr *nest; spin_lock_bh(&hinfo->lock); @@ -128,6 +129,11 @@ static int tcf_dump_walker(struct tcf_hashinfo *hinfo, struct sk_buff *skb, if (index < s_i) continue; + if (jiffy_since && + time_after(jiffy_since, + (unsigned long)p->tcfa_tm.lastuse)) + continue; + nest = nla_nest_start(skb, n_i); if (nest == NULL) goto nla_put_failure; @@ -145,9 +151,11 @@ static int tcf_dump_walker(struct tcf_hashinfo *hinfo, struct sk_buff *skb, } } done: + if (index >= 0) + cb->args[0] = index + 1; + spin_unlock_bh(&hinfo->lock); if (n_i) { - cb->args[0] += n_i; if (act_flags & TCA_FLAG_LARGE_DUMP_ON) cb->args[1] = n_i; } @@ -1077,6 +1085,7 @@ static u32 tcaa_root_flags_allowed = TCA_FLAG_LARGE_DUMP_ON; static const struct nla_policy tcaa_policy[TCA_ROOT_MAX + 1] = { [TCA_ROOT_FLAGS] = { .type = NLA_BITFIELD32, .validation_data = &tcaa_root_flags_allowed }, + [TCA_ROOT_TIME_DELTA] = { .type = NLA_U32 }, }; static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, @@ -1166,8 +1175,10 @@ static int tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) struct tcamsg *t = (struct tcamsg *) nlmsg_data(cb->nlh); struct nlattr *tb[TCA_ROOT_MAX + 1]; struct nlattr *count_attr = NULL; + unsigned long jiffy_since = 0; struct nlattr *kind = NULL; struct nla_bitfield32 bf; + u32 msecs_since = 0; u32 act_count = 0; ret = nlmsg_parse(cb->nlh, sizeof(struct tcamsg), tb, TCA_ROOT_MAX, @@ -1191,15 +1202,23 @@ static int tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) cb->args[2] = bf.value; } + if (tb[TCA_ROOT_TIME_DELTA]) { + msecs_since = nla_get_u32(tb[TCA_ROOT_TIME_DELTA]); + } + nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cb->nlh->nlmsg_type, sizeof(*t), 0); if (!nlh) goto out_module_put; + if (msecs_since) + jiffy_since = jiffies - msecs_to_jiffies(msecs_since); + t = nlmsg_data(nlh); t->tca_family = AF_UNSPEC; t->tca__pad1 = 0; t->tca__pad2 = 0; + cb->args[3] = jiffy_since; count_attr = nla_reserve(skb, TCA_ROOT_COUNT, sizeof(u32)); if (!count_attr) goto out_module_put; -- cgit v1.2.3-71-gd317 From e46abbcc05aa8a16b0e7f5c94e86d11af9aa2770 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Thu, 27 Jul 2017 16:56:41 +0200 Subject: netfilter: nf_tables: Allow table names of up to 255 chars Allocate all table names dynamically to allow for arbitrary lengths but introduce NFT_NAME_MAXLEN as an upper sanity boundary. It's value was chosen to allow using a domain name as per RFC 1035. Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 2 +- include/uapi/linux/netfilter/nf_tables.h | 3 +- net/netfilter/nf_tables_api.c | 49 +++++++++++++++++++++++--------- net/netfilter/nf_tables_trace.c | 2 +- 4 files changed, 40 insertions(+), 16 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index bd5be0d691d5..05ecf78ec078 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -957,7 +957,7 @@ struct nft_table { u32 use; u16 flags:14, genmask:2; - char name[NFT_TABLE_MAXNAMELEN]; + char *name; }; enum nft_af_flags { diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 6f0a950e21c3..0b94e572ef16 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1,7 +1,8 @@ #ifndef _LINUX_NF_TABLES_H #define _LINUX_NF_TABLES_H -#define NFT_TABLE_MAXNAMELEN 32 +#define NFT_NAME_MAXLEN 256 +#define NFT_TABLE_MAXNAMELEN NFT_NAME_MAXLEN #define NFT_CHAIN_MAXNAMELEN 32 #define NFT_SET_MAXNAMELEN 32 #define NFT_OBJ_MAXNAMELEN 32 diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index b77ad0813564..c2e392d5e512 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -726,7 +726,10 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, if (table == NULL) goto err2; - nla_strlcpy(table->name, name, NFT_TABLE_MAXNAMELEN); + table->name = nla_strdup(name, GFP_KERNEL); + if (table->name == NULL) + goto err3; + INIT_LIST_HEAD(&table->chains); INIT_LIST_HEAD(&table->sets); INIT_LIST_HEAD(&table->objects); @@ -735,10 +738,12 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, nft_ctx_init(&ctx, net, skb, nlh, afi, table, NULL, nla); err = nft_trans_table_add(&ctx, NFT_MSG_NEWTABLE); if (err < 0) - goto err3; + goto err4; list_add_tail_rcu(&table->list, &afi->tables); return 0; +err4: + kfree(table->name); err3: kfree(table); err2: @@ -865,6 +870,7 @@ static void nf_tables_table_destroy(struct nft_ctx *ctx) { BUG_ON(ctx->table->use > 0); + kfree(ctx->table->name); kfree(ctx->table); module_put(ctx->afi->owner); } @@ -1972,7 +1978,7 @@ err: } struct nft_rule_dump_ctx { - char table[NFT_TABLE_MAXNAMELEN]; + char *table; char chain[NFT_CHAIN_MAXNAMELEN]; }; @@ -1997,7 +2003,7 @@ static int nf_tables_dump_rules(struct sk_buff *skb, continue; list_for_each_entry_rcu(table, &afi->tables, list) { - if (ctx && ctx->table[0] && + if (ctx && ctx->table && strcmp(ctx->table, table->name) != 0) continue; @@ -2037,7 +2043,12 @@ done: static int nf_tables_dump_rules_done(struct netlink_callback *cb) { - kfree(cb->data); + struct nft_rule_dump_ctx *ctx = cb->data; + + if (ctx) { + kfree(ctx->table); + kfree(ctx); + } return 0; } @@ -2069,9 +2080,14 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, if (!ctx) return -ENOMEM; - if (nla[NFTA_RULE_TABLE]) - nla_strlcpy(ctx->table, nla[NFTA_RULE_TABLE], - sizeof(ctx->table)); + if (nla[NFTA_RULE_TABLE]) { + ctx->table = nla_strdup(nla[NFTA_RULE_TABLE], + GFP_KERNEL); + if (!ctx->table) { + kfree(ctx); + return -ENOMEM; + } + } if (nla[NFTA_RULE_CHAIN]) nla_strlcpy(ctx->chain, nla[NFTA_RULE_CHAIN], sizeof(ctx->chain)); @@ -4410,7 +4426,7 @@ nla_put_failure: } struct nft_obj_filter { - char table[NFT_OBJ_MAXNAMELEN]; + char *table; u32 type; }; @@ -4475,7 +4491,10 @@ done: static int nf_tables_dump_obj_done(struct netlink_callback *cb) { - kfree(cb->data); + struct nft_obj_filter *filter = cb->data; + + kfree(filter->table); + kfree(filter); return 0; } @@ -4489,9 +4508,13 @@ nft_obj_filter_alloc(const struct nlattr * const nla[]) if (!filter) return ERR_PTR(-ENOMEM); - if (nla[NFTA_OBJ_TABLE]) - nla_strlcpy(filter->table, nla[NFTA_OBJ_TABLE], - NFT_TABLE_MAXNAMELEN); + if (nla[NFTA_OBJ_TABLE]) { + filter->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_KERNEL); + if (!filter->table) { + kfree(filter); + return ERR_PTR(-ENOMEM); + } + } if (nla[NFTA_OBJ_TYPE]) filter->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c index 0c3a0049e4aa..62787d985e9d 100644 --- a/net/netfilter/nf_tables_trace.c +++ b/net/netfilter/nf_tables_trace.c @@ -175,7 +175,7 @@ void nft_trace_notify(struct nft_traceinfo *info) return; size = nlmsg_total_size(sizeof(struct nfgenmsg)) + - nla_total_size(NFT_TABLE_MAXNAMELEN) + + nla_total_size(strlen(info->chain->table->name)) + nla_total_size(NFT_CHAIN_MAXNAMELEN) + nla_total_size_64bit(sizeof(__be64)) + /* rule handle */ nla_total_size(sizeof(__be32)) + /* trace type */ -- cgit v1.2.3-71-gd317 From b7263e071aba736cea9e71cdf2e76dfa7aebd039 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Thu, 27 Jul 2017 16:56:42 +0200 Subject: netfilter: nf_tables: Allow chain name of up to 255 chars Same conversion as for table names, use NFT_NAME_MAXLEN as upper boundary as well. Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 4 ++-- include/uapi/linux/netfilter/nf_tables.h | 2 +- net/netfilter/nf_tables_api.c | 34 ++++++++++++++++++++++++-------- net/netfilter/nf_tables_trace.c | 27 +++++++++++++++++++++++-- 4 files changed, 54 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 05ecf78ec078..be1610162ee0 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -859,7 +859,7 @@ struct nft_chain { u16 level; u8 flags:6, genmask:2; - char name[NFT_CHAIN_MAXNAMELEN]; + char *name; }; enum nft_chain_type { @@ -1272,7 +1272,7 @@ struct nft_trans_set { struct nft_trans_chain { bool update; - char name[NFT_CHAIN_MAXNAMELEN]; + char *name; struct nft_stats __percpu *stats; u8 policy; }; diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 0b94e572ef16..d9c03a8608ee 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -3,7 +3,7 @@ #define NFT_NAME_MAXLEN 256 #define NFT_TABLE_MAXNAMELEN NFT_NAME_MAXLEN -#define NFT_CHAIN_MAXNAMELEN 32 +#define NFT_CHAIN_MAXNAMELEN NFT_NAME_MAXLEN #define NFT_SET_MAXNAMELEN 32 #define NFT_OBJ_MAXNAMELEN 32 #define NFT_USERDATA_MAXLEN 256 diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c2e392d5e512..747499039709 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1250,8 +1250,10 @@ static void nf_tables_chain_destroy(struct nft_chain *chain) static_branch_dec(&nft_counters_enabled); if (basechain->ops[0].dev != NULL) dev_put(basechain->ops[0].dev); + kfree(chain->name); kfree(basechain); } else { + kfree(chain->name); kfree(chain); } } @@ -1476,8 +1478,13 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, nft_trans_chain_policy(trans) = -1; if (nla[NFTA_CHAIN_HANDLE] && name) { - nla_strlcpy(nft_trans_chain_name(trans), name, - NFT_CHAIN_MAXNAMELEN); + nft_trans_chain_name(trans) = + nla_strdup(name, GFP_KERNEL); + if (!nft_trans_chain_name(trans)) { + kfree(trans); + free_percpu(stats); + return -ENOMEM; + } } list_add_tail(&trans->list, &net->nft.commit_list); return 0; @@ -1544,7 +1551,11 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, INIT_LIST_HEAD(&chain->rules); chain->handle = nf_tables_alloc_handle(table); chain->table = table; - nla_strlcpy(chain->name, name, NFT_CHAIN_MAXNAMELEN); + chain->name = nla_strdup(name, GFP_KERNEL); + if (!chain->name) { + err = -ENOMEM; + goto err1; + } err = nf_tables_register_hooks(net, table, chain, afi->nops); if (err < 0) @@ -1979,7 +1990,7 @@ err: struct nft_rule_dump_ctx { char *table; - char chain[NFT_CHAIN_MAXNAMELEN]; + char *chain; }; static int nf_tables_dump_rules(struct sk_buff *skb, @@ -2047,6 +2058,7 @@ static int nf_tables_dump_rules_done(struct netlink_callback *cb) if (ctx) { kfree(ctx->table); + kfree(ctx->chain); kfree(ctx); } return 0; @@ -2088,9 +2100,15 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, return -ENOMEM; } } - if (nla[NFTA_RULE_CHAIN]) - nla_strlcpy(ctx->chain, nla[NFTA_RULE_CHAIN], - sizeof(ctx->chain)); + if (nla[NFTA_RULE_CHAIN]) { + ctx->chain = nla_strdup(nla[NFTA_RULE_CHAIN], + GFP_KERNEL); + if (!ctx->chain) { + kfree(ctx->table); + kfree(ctx); + return -ENOMEM; + } + } c.data = ctx; } @@ -4863,7 +4881,7 @@ static void nft_chain_commit_update(struct nft_trans *trans) { struct nft_base_chain *basechain; - if (nft_trans_chain_name(trans)[0]) + if (nft_trans_chain_name(trans)) strcpy(trans->ctx.chain->name, nft_trans_chain_name(trans)); if (!nft_is_base_chain(trans->ctx.chain)) diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c index 62787d985e9d..e1dc527a493b 100644 --- a/net/netfilter/nf_tables_trace.c +++ b/net/netfilter/nf_tables_trace.c @@ -162,6 +162,27 @@ static int nf_trace_fill_rule_info(struct sk_buff *nlskb, NFTA_TRACE_PAD); } +static bool nft_trace_have_verdict_chain(struct nft_traceinfo *info) +{ + switch (info->type) { + case NFT_TRACETYPE_RETURN: + case NFT_TRACETYPE_RULE: + break; + default: + return false; + } + + switch (info->verdict->code) { + case NFT_JUMP: + case NFT_GOTO: + break; + default: + return false; + } + + return true; +} + void nft_trace_notify(struct nft_traceinfo *info) { const struct nft_pktinfo *pkt = info->pkt; @@ -176,12 +197,11 @@ void nft_trace_notify(struct nft_traceinfo *info) size = nlmsg_total_size(sizeof(struct nfgenmsg)) + nla_total_size(strlen(info->chain->table->name)) + - nla_total_size(NFT_CHAIN_MAXNAMELEN) + + nla_total_size(strlen(info->chain->name)) + nla_total_size_64bit(sizeof(__be64)) + /* rule handle */ nla_total_size(sizeof(__be32)) + /* trace type */ nla_total_size(0) + /* VERDICT, nested */ nla_total_size(sizeof(u32)) + /* verdict code */ - nla_total_size(NFT_CHAIN_MAXNAMELEN) + /* jump target */ nla_total_size(sizeof(u32)) + /* id */ nla_total_size(NFT_TRACETYPE_LL_HSIZE) + nla_total_size(NFT_TRACETYPE_NETWORK_HSIZE) + @@ -194,6 +214,9 @@ void nft_trace_notify(struct nft_traceinfo *info) nla_total_size(sizeof(u32)) + /* nfproto */ nla_total_size(sizeof(u32)); /* policy */ + if (nft_trace_have_verdict_chain(info)) + size += nla_total_size(strlen(info->verdict->chain->name)); /* jump target */ + skb = nlmsg_new(size, GFP_ATOMIC); if (!skb) return; -- cgit v1.2.3-71-gd317 From 387454901bd62022ac1b04e15bd8d4fcc60bbed4 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Thu, 27 Jul 2017 16:56:43 +0200 Subject: netfilter: nf_tables: Allow set names of up to 255 chars Same conversion as for table names, use NFT_NAME_MAXLEN as upper boundary as well. Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 2 +- include/uapi/linux/netfilter/nf_tables.h | 2 +- net/netfilter/nf_tables_api.c | 18 ++++++++++++++---- 3 files changed, 16 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index be1610162ee0..66ba62fa7d90 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -396,7 +396,7 @@ void nft_unregister_set(struct nft_set_type *type); struct nft_set { struct list_head list; struct list_head bindings; - char name[NFT_SET_MAXNAMELEN]; + char *name; u32 ktype; u32 dtype; u32 objtype; diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index d9c03a8608ee..b5e73e80b7b6 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -4,7 +4,7 @@ #define NFT_NAME_MAXLEN 256 #define NFT_TABLE_MAXNAMELEN NFT_NAME_MAXLEN #define NFT_CHAIN_MAXNAMELEN NFT_NAME_MAXLEN -#define NFT_SET_MAXNAMELEN 32 +#define NFT_SET_MAXNAMELEN NFT_NAME_MAXLEN #define NFT_OBJ_MAXNAMELEN 32 #define NFT_USERDATA_MAXLEN 256 diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 747499039709..e6a07f27b1a3 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2650,7 +2650,7 @@ static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set, unsigned long *inuse; unsigned int n = 0, min = 0; - p = strnchr(name, NFT_SET_MAXNAMELEN, '%'); + p = strchr(name, '%'); if (p != NULL) { if (p[1] != 'd' || strchr(p + 2, '%')) return -EINVAL; @@ -2681,7 +2681,10 @@ cont: free_page((unsigned long)inuse); } - snprintf(set->name, sizeof(set->name), name, min + n); + set->name = kasprintf(GFP_KERNEL, name, min + n); + if (!set->name) + return -ENOMEM; + list_for_each_entry(i, &ctx->table->sets, list) { if (!nft_is_active_next(ctx->net, i)) continue; @@ -2958,7 +2961,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, struct nft_table *table; struct nft_set *set; struct nft_ctx ctx; - char name[NFT_SET_MAXNAMELEN]; + char *name; unsigned int size; bool create; u64 timeout; @@ -3104,8 +3107,14 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, goto err1; } - nla_strlcpy(name, nla[NFTA_SET_NAME], sizeof(set->name)); + name = nla_strdup(nla[NFTA_SET_NAME], GFP_KERNEL); + if (!name) { + err = -ENOMEM; + goto err2; + } + err = nf_tables_set_alloc_name(&ctx, set, name); + kfree(name); if (err < 0) goto err2; @@ -3155,6 +3164,7 @@ static void nft_set_destroy(struct nft_set *set) { set->ops->destroy(set); module_put(set->ops->type->owner); + kfree(set->name); kvfree(set); } -- cgit v1.2.3-71-gd317 From 615095752100748e221028fc96163c2b78185ae4 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Thu, 27 Jul 2017 16:56:44 +0200 Subject: netfilter: nf_tables: Allow object names of up to 255 chars Same conversion as for table names, use NFT_NAME_MAXLEN as upper boundary as well. Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 2 +- include/uapi/linux/netfilter/nf_tables.h | 2 +- net/netfilter/nf_tables_api.c | 11 +++++++++-- 3 files changed, 11 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 66ba62fa7d90..f9795fe394f3 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1016,7 +1016,7 @@ int nft_verdict_dump(struct sk_buff *skb, int type, */ struct nft_object { struct list_head list; - char name[NFT_OBJ_MAXNAMELEN]; + char *name; struct nft_table *table; u32 genmask:2, use:30; diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index b5e73e80b7b6..be25cf69295b 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -5,7 +5,7 @@ #define NFT_TABLE_MAXNAMELEN NFT_NAME_MAXLEN #define NFT_CHAIN_MAXNAMELEN NFT_NAME_MAXLEN #define NFT_SET_MAXNAMELEN NFT_NAME_MAXLEN -#define NFT_OBJ_MAXNAMELEN 32 +#define NFT_OBJ_MAXNAMELEN NFT_NAME_MAXLEN #define NFT_USERDATA_MAXLEN 256 /** diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index e6a07f27b1a3..149785ff1c7b 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4402,15 +4402,21 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, goto err1; } obj->table = table; - nla_strlcpy(obj->name, nla[NFTA_OBJ_NAME], NFT_OBJ_MAXNAMELEN); + obj->name = nla_strdup(nla[NFTA_OBJ_NAME], GFP_KERNEL); + if (!obj->name) { + err = -ENOMEM; + goto err2; + } err = nft_trans_obj_add(&ctx, NFT_MSG_NEWOBJ, obj); if (err < 0) - goto err2; + goto err3; list_add_tail_rcu(&obj->list, &table->objects); table->use++; return 0; +err3: + kfree(obj->name); err2: if (obj->type->destroy) obj->type->destroy(obj); @@ -4626,6 +4632,7 @@ static void nft_obj_destroy(struct nft_object *obj) obj->type->destroy(obj); module_put(obj->type->owner); + kfree(obj->name); kfree(obj); } -- cgit v1.2.3-71-gd317 From 3282e65558b3651e230ee985c174c35cb2fedaf1 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sun, 30 Jul 2017 03:57:23 +0200 Subject: tcp: remove unused mib counters was used by tcp prequeue and header prediction. TCPFORWARDRETRANS use was removed in january. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/uapi/linux/snmp.h | 9 --------- net/ipv4/proc.c | 9 --------- 2 files changed, 18 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index d85693295798..b3f346fb9fe3 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -184,14 +184,7 @@ enum LINUX_MIB_DELAYEDACKLOST, /* DelayedACKLost */ LINUX_MIB_LISTENOVERFLOWS, /* ListenOverflows */ LINUX_MIB_LISTENDROPS, /* ListenDrops */ - LINUX_MIB_TCPPREQUEUED, /* TCPPrequeued */ - LINUX_MIB_TCPDIRECTCOPYFROMBACKLOG, /* TCPDirectCopyFromBacklog */ - LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE, /* TCPDirectCopyFromPrequeue */ - LINUX_MIB_TCPPREQUEUEDROPPED, /* TCPPrequeueDropped */ - LINUX_MIB_TCPHPHITS, /* TCPHPHits */ - LINUX_MIB_TCPHPHITSTOUSER, /* TCPHPHitsToUser */ LINUX_MIB_TCPPUREACKS, /* TCPPureAcks */ - LINUX_MIB_TCPHPACKS, /* TCPHPAcks */ LINUX_MIB_TCPRENORECOVERY, /* TCPRenoRecovery */ LINUX_MIB_TCPSACKRECOVERY, /* TCPSackRecovery */ LINUX_MIB_TCPSACKRENEGING, /* TCPSACKReneging */ @@ -208,14 +201,12 @@ enum LINUX_MIB_TCPSACKFAILURES, /* TCPSackFailures */ LINUX_MIB_TCPLOSSFAILURES, /* TCPLossFailures */ LINUX_MIB_TCPFASTRETRANS, /* TCPFastRetrans */ - LINUX_MIB_TCPFORWARDRETRANS, /* TCPForwardRetrans */ LINUX_MIB_TCPSLOWSTARTRETRANS, /* TCPSlowStartRetrans */ LINUX_MIB_TCPTIMEOUTS, /* TCPTimeouts */ LINUX_MIB_TCPLOSSPROBES, /* TCPLossProbes */ LINUX_MIB_TCPLOSSPROBERECOVERY, /* TCPLossProbeRecovery */ LINUX_MIB_TCPRENORECOVERYFAIL, /* TCPRenoRecoveryFail */ LINUX_MIB_TCPSACKRECOVERYFAIL, /* TCPSackRecoveryFail */ - LINUX_MIB_TCPSCHEDULERFAILED, /* TCPSchedulerFailed */ LINUX_MIB_TCPRCVCOLLAPSED, /* TCPRcvCollapsed */ LINUX_MIB_TCPDSACKOLDSENT, /* TCPDSACKOldSent */ LINUX_MIB_TCPDSACKOFOSENT, /* TCPDSACKOfoSent */ diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 43eb6567b3a0..b6d3fe03feb3 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -206,14 +206,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("DelayedACKLost", LINUX_MIB_DELAYEDACKLOST), SNMP_MIB_ITEM("ListenOverflows", LINUX_MIB_LISTENOVERFLOWS), SNMP_MIB_ITEM("ListenDrops", LINUX_MIB_LISTENDROPS), - SNMP_MIB_ITEM("TCPPrequeued", LINUX_MIB_TCPPREQUEUED), - SNMP_MIB_ITEM("TCPDirectCopyFromBacklog", LINUX_MIB_TCPDIRECTCOPYFROMBACKLOG), - SNMP_MIB_ITEM("TCPDirectCopyFromPrequeue", LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE), - SNMP_MIB_ITEM("TCPPrequeueDropped", LINUX_MIB_TCPPREQUEUEDROPPED), - SNMP_MIB_ITEM("TCPHPHits", LINUX_MIB_TCPHPHITS), - SNMP_MIB_ITEM("TCPHPHitsToUser", LINUX_MIB_TCPHPHITSTOUSER), SNMP_MIB_ITEM("TCPPureAcks", LINUX_MIB_TCPPUREACKS), - SNMP_MIB_ITEM("TCPHPAcks", LINUX_MIB_TCPHPACKS), SNMP_MIB_ITEM("TCPRenoRecovery", LINUX_MIB_TCPRENORECOVERY), SNMP_MIB_ITEM("TCPSackRecovery", LINUX_MIB_TCPSACKRECOVERY), SNMP_MIB_ITEM("TCPSACKReneging", LINUX_MIB_TCPSACKRENEGING), @@ -230,14 +223,12 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPSackFailures", LINUX_MIB_TCPSACKFAILURES), SNMP_MIB_ITEM("TCPLossFailures", LINUX_MIB_TCPLOSSFAILURES), SNMP_MIB_ITEM("TCPFastRetrans", LINUX_MIB_TCPFASTRETRANS), - SNMP_MIB_ITEM("TCPForwardRetrans", LINUX_MIB_TCPFORWARDRETRANS), SNMP_MIB_ITEM("TCPSlowStartRetrans", LINUX_MIB_TCPSLOWSTARTRETRANS), SNMP_MIB_ITEM("TCPTimeouts", LINUX_MIB_TCPTIMEOUTS), SNMP_MIB_ITEM("TCPLossProbes", LINUX_MIB_TCPLOSSPROBES), SNMP_MIB_ITEM("TCPLossProbeRecovery", LINUX_MIB_TCPLOSSPROBERECOVERY), SNMP_MIB_ITEM("TCPRenoRecoveryFail", LINUX_MIB_TCPRENORECOVERYFAIL), SNMP_MIB_ITEM("TCPSackRecoveryFail", LINUX_MIB_TCPSACKRECOVERYFAIL), - SNMP_MIB_ITEM("TCPSchedulerFailed", LINUX_MIB_TCPSCHEDULERFAILED), SNMP_MIB_ITEM("TCPRcvCollapsed", LINUX_MIB_TCPRCVCOLLAPSED), SNMP_MIB_ITEM("TCPDSACKOldSent", LINUX_MIB_TCPDSACKOLDSENT), SNMP_MIB_ITEM("TCPDSACKOfoSent", LINUX_MIB_TCPDSACKOFOSENT), -- cgit v1.2.3-71-gd317 From bb7c19f96012720b895111300b9d9f3f858c3a69 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 28 Jul 2017 10:28:21 -0700 Subject: tcp: add related fields into SCM_TIMESTAMPING_OPT_STATS Add the following stats into SCM_TIMESTAMPING_OPT_STATS control msg: TCP_NLA_PACING_RATE TCP_NLA_DELIVERY_RATE TCP_NLA_SND_CWND TCP_NLA_REORDERING TCP_NLA_MIN_RTT TCP_NLA_RECUR_RETRANS TCP_NLA_DELIVERY_RATE_APP_LMT Signed-off-by: Wei Wang Acked-by: Yuchung Cheng Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/uapi/linux/tcp.h | 8 ++++++++ net/ipv4/tcp.c | 20 +++++++++++++++++++- 2 files changed, 27 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index a5507c977497..030e594bab45 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -231,6 +231,14 @@ enum { TCP_NLA_SNDBUF_LIMITED, /* Time (usec) limited by send buffer */ TCP_NLA_DATA_SEGS_OUT, /* Data pkts sent including retransmission */ TCP_NLA_TOTAL_RETRANS, /* Data pkts retransmitted */ + TCP_NLA_PACING_RATE, /* Pacing rate in bytes per second */ + TCP_NLA_DELIVERY_RATE, /* Delivery rate in bytes per second */ + TCP_NLA_SND_CWND, /* Sending congestion window */ + TCP_NLA_REORDERING, /* Reordering metric */ + TCP_NLA_MIN_RTT, /* minimum RTT */ + TCP_NLA_RECUR_RETRANS, /* Recurring retransmits for the current pkt */ + TCP_NLA_DELIVERY_RATE_APP_LMT, /* delivery rate application limited ? */ + }; /* for TCP_MD5SIG socket option */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index acee7acdcba6..5326b50a3450 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2840,8 +2840,12 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) const struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *stats; struct tcp_info info; + u64 rate64; + u32 rate; - stats = alloc_skb(5 * nla_total_size_64bit(sizeof(u64)), GFP_ATOMIC); + stats = alloc_skb(7 * nla_total_size_64bit(sizeof(u64)) + + 3 * nla_total_size(sizeof(u32)) + + 2 * nla_total_size(sizeof(u8)), GFP_ATOMIC); if (!stats) return NULL; @@ -2856,6 +2860,20 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) tp->data_segs_out, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_TOTAL_RETRANS, tp->total_retrans, TCP_NLA_PAD); + + rate = READ_ONCE(sk->sk_pacing_rate); + rate64 = rate != ~0U ? rate : ~0ULL; + nla_put_u64_64bit(stats, TCP_NLA_PACING_RATE, rate64, TCP_NLA_PAD); + + rate64 = tcp_compute_delivery_rate(tp); + nla_put_u64_64bit(stats, TCP_NLA_DELIVERY_RATE, rate64, TCP_NLA_PAD); + + nla_put_u32(stats, TCP_NLA_SND_CWND, tp->snd_cwnd); + nla_put_u32(stats, TCP_NLA_REORDERING, tp->reordering); + nla_put_u32(stats, TCP_NLA_MIN_RTT, tcp_min_rtt(tp)); + + nla_put_u8(stats, TCP_NLA_RECUR_RETRANS, inet_csk(sk)->icsk_retransmits); + nla_put_u8(stats, TCP_NLA_DELIVERY_RATE_APP_LMT, !!tp->rate_app_limited); return stats; } -- cgit v1.2.3-71-gd317 From 61e4d01e16acddadb9723143637a20417fa67ac9 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 3 Aug 2017 13:28:20 +0200 Subject: ipv6: fib: Add offload indication to routes Allow user space applications to see which routes are offloaded and which aren't by setting the RTNH_F_OFFLOAD flag when dumping them. To be consistent with IPv4, offload indication is provided on a per-nexthop basis. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/ipv6_route.h | 1 + net/ipv6/route.c | 8 ++++++++ 2 files changed, 9 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ipv6_route.h b/include/uapi/linux/ipv6_route.h index d496c02e14bc..33e2a5732bd1 100644 --- a/include/uapi/linux/ipv6_route.h +++ b/include/uapi/linux/ipv6_route.h @@ -35,6 +35,7 @@ #define RTF_PREF(pref) ((pref) << 27) #define RTF_PREF_MASK 0x18000000 +#define RTF_OFFLOAD 0x20000000 /* offloaded route */ #define RTF_PCPU 0x40000000 /* read-only: can not be set by user */ #define RTF_LOCAL 0x80000000 diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 4d30c96a819d..aba07fce67fb 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1820,6 +1820,11 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, goto out; } + if (cfg->fc_flags & RTF_OFFLOAD) { + NL_SET_ERR_MSG(extack, "Userspace can not set RTF_OFFLOAD"); + goto out; + } + if (cfg->fc_dst_len > 128) { NL_SET_ERR_MSG(extack, "Invalid prefix length"); goto out; @@ -3327,6 +3332,9 @@ static int rt6_nexthop_info(struct sk_buff *skb, struct rt6_info *rt, goto nla_put_failure; } + if (rt->rt6i_flags & RTF_OFFLOAD) + *flags |= RTNH_F_OFFLOAD; + /* not needed for multipath encoding b/c it has a rtnexthop struct */ if (!skip_oif && rt->dst.dev && nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex)) -- cgit v1.2.3-71-gd317 From 52267790ef52d7513879238ca9fac22c1733e0e3 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Thu, 3 Aug 2017 16:29:39 -0400 Subject: sock: add MSG_ZEROCOPY The kernel supports zerocopy sendmsg in virtio and tap. Expand the infrastructure to support other socket types. Introduce a completion notification channel over the socket error queue. Notifications are returned with ee_origin SO_EE_ORIGIN_ZEROCOPY. ee_errno is 0 to avoid blocking the send/recv path on receiving notifications. Add reference counting, to support the skb split, merge, resize and clone operations possible with SOCK_STREAM and other socket types. The patch does not yet modify any datapaths. Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/skbuff.h | 60 +++++++++++++++++++ include/linux/socket.h | 1 + include/net/sock.h | 2 + include/uapi/linux/errqueue.h | 3 + net/core/datagram.c | 55 ++++++++++------- net/core/skbuff.c | 133 ++++++++++++++++++++++++++++++++++++++++++ net/core/sock.c | 2 + 7 files changed, 235 insertions(+), 21 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2f64e2bbb592..59cff7aa494e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -429,6 +429,7 @@ enum { SKBTX_SCHED_TSTAMP = 1 << 6, }; +#define SKBTX_ZEROCOPY_FRAG (SKBTX_DEV_ZEROCOPY | SKBTX_SHARED_FRAG) #define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \ SKBTX_SCHED_TSTAMP) #define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | SKBTX_ANY_SW_TSTAMP) @@ -445,8 +446,28 @@ struct ubuf_info { void (*callback)(struct ubuf_info *, bool zerocopy_success); void *ctx; unsigned long desc; + u16 zerocopy:1; + atomic_t refcnt; }; +#define skb_uarg(SKB) ((struct ubuf_info *)(skb_shinfo(SKB)->destructor_arg)) + +struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size); + +static inline void sock_zerocopy_get(struct ubuf_info *uarg) +{ + atomic_inc(&uarg->refcnt); +} + +void sock_zerocopy_put(struct ubuf_info *uarg); +void sock_zerocopy_put_abort(struct ubuf_info *uarg); + +void sock_zerocopy_callback(struct ubuf_info *uarg, bool success); + +int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, + struct msghdr *msg, int len, + struct ubuf_info *uarg); + /* This data is invariant across clones and lives at * the end of the header data, ie. at skb->end. */ @@ -1214,6 +1235,45 @@ static inline struct skb_shared_hwtstamps *skb_hwtstamps(struct sk_buff *skb) return &skb_shinfo(skb)->hwtstamps; } +static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) +{ + bool is_zcopy = skb && skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY; + + return is_zcopy ? skb_uarg(skb) : NULL; +} + +static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg) +{ + if (skb && uarg && !skb_zcopy(skb)) { + sock_zerocopy_get(uarg); + skb_shinfo(skb)->destructor_arg = uarg; + skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG; + } +} + +/* Release a reference on a zerocopy structure */ +static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy) +{ + struct ubuf_info *uarg = skb_zcopy(skb); + + if (uarg) { + uarg->zerocopy = uarg->zerocopy && zerocopy; + sock_zerocopy_put(uarg); + skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG; + } +} + +/* Abort a zerocopy operation and revert zckey on error in send syscall */ +static inline void skb_zcopy_abort(struct sk_buff *skb) +{ + struct ubuf_info *uarg = skb_zcopy(skb); + + if (uarg) { + sock_zerocopy_put_abort(uarg); + skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG; + } +} + /** * skb_queue_empty - check if a queue is empty * @list: queue head diff --git a/include/linux/socket.h b/include/linux/socket.h index 8b13db5163cc..8ad963cdc88c 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -287,6 +287,7 @@ struct ucred { #define MSG_BATCH 0x40000 /* sendmmsg(): more messages coming */ #define MSG_EOF MSG_FIN +#define MSG_ZEROCOPY 0x4000000 /* Use user data in kernel path */ #define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */ #define MSG_CMSG_CLOEXEC 0x40000000 /* Set close_on_exec for file descriptor received through diff --git a/include/net/sock.h b/include/net/sock.h index 0f778d3c4300..fe1a0bc25cd3 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -294,6 +294,7 @@ struct sock_common { * @sk_stamp: time stamp of last packet received * @sk_tsflags: SO_TIMESTAMPING socket options * @sk_tskey: counter to disambiguate concurrent tstamp requests + * @sk_zckey: counter to order MSG_ZEROCOPY notifications * @sk_socket: Identd and reporting IO signals * @sk_user_data: RPC layer private data * @sk_frag: cached page frag @@ -462,6 +463,7 @@ struct sock { u16 sk_tsflags; u8 sk_shutdown; u32 sk_tskey; + atomic_t sk_zckey; struct socket *sk_socket; void *sk_user_data; #ifdef CONFIG_SECURITY diff --git a/include/uapi/linux/errqueue.h b/include/uapi/linux/errqueue.h index 07bdce1f444a..78fdf52d6b2f 100644 --- a/include/uapi/linux/errqueue.h +++ b/include/uapi/linux/errqueue.h @@ -18,10 +18,13 @@ struct sock_extended_err { #define SO_EE_ORIGIN_ICMP 2 #define SO_EE_ORIGIN_ICMP6 3 #define SO_EE_ORIGIN_TXSTATUS 4 +#define SO_EE_ORIGIN_ZEROCOPY 5 #define SO_EE_ORIGIN_TIMESTAMPING SO_EE_ORIGIN_TXSTATUS #define SO_EE_OFFENDER(ee) ((struct sockaddr*)((ee)+1)) +#define SO_EE_CODE_ZEROCOPY_COPIED 1 + /** * struct scm_timestamping - timestamps exposed through cmsg * diff --git a/net/core/datagram.c b/net/core/datagram.c index ee5647bd91b3..2f3277945d35 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -573,27 +573,12 @@ fault: } EXPORT_SYMBOL(skb_copy_datagram_from_iter); -/** - * zerocopy_sg_from_iter - Build a zerocopy datagram from an iov_iter - * @skb: buffer to copy - * @from: the source to copy from - * - * The function will first copy up to headlen, and then pin the userspace - * pages and build frags through them. - * - * Returns 0, -EFAULT or -EMSGSIZE. - */ -int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from) +int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, + struct iov_iter *from, size_t length) { - int len = iov_iter_count(from); - int copy = min_t(int, skb_headlen(skb), len); - int frag = 0; + int frag = skb_shinfo(skb)->nr_frags; - /* copy up to skb headlen */ - if (skb_copy_datagram_from_iter(skb, 0, from, copy)) - return -EFAULT; - - while (iov_iter_count(from)) { + while (length && iov_iter_count(from)) { struct page *pages[MAX_SKB_FRAGS]; size_t start; ssize_t copied; @@ -603,18 +588,24 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from) if (frag == MAX_SKB_FRAGS) return -EMSGSIZE; - copied = iov_iter_get_pages(from, pages, ~0U, + copied = iov_iter_get_pages(from, pages, length, MAX_SKB_FRAGS - frag, &start); if (copied < 0) return -EFAULT; iov_iter_advance(from, copied); + length -= copied; truesize = PAGE_ALIGN(copied + start); skb->data_len += copied; skb->len += copied; skb->truesize += truesize; - refcount_add(truesize, &skb->sk->sk_wmem_alloc); + if (sk && sk->sk_type == SOCK_STREAM) { + sk->sk_wmem_queued += truesize; + sk_mem_charge(sk, truesize); + } else { + refcount_add(truesize, &skb->sk->sk_wmem_alloc); + } while (copied) { int size = min_t(int, copied, PAGE_SIZE - start); skb_fill_page_desc(skb, frag++, pages[n], start, size); @@ -625,6 +616,28 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from) } return 0; } +EXPORT_SYMBOL(__zerocopy_sg_from_iter); + +/** + * zerocopy_sg_from_iter - Build a zerocopy datagram from an iov_iter + * @skb: buffer to copy + * @from: the source to copy from + * + * The function will first copy up to headlen, and then pin the userspace + * pages and build frags through them. + * + * Returns 0, -EFAULT or -EMSGSIZE. + */ +int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from) +{ + int copy = min_t(int, skb_headlen(skb), iov_iter_count(from)); + + /* copy up to skb headlen */ + if (skb_copy_datagram_from_iter(skb, 0, from, copy)) + return -EFAULT; + + return __zerocopy_sg_from_iter(NULL, skb, from, ~0U); +} EXPORT_SYMBOL(zerocopy_sg_from_iter); static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index a95877a8ac8b..0603e44950da 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -915,6 +915,139 @@ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src) } EXPORT_SYMBOL_GPL(skb_morph); +struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size) +{ + struct ubuf_info *uarg; + struct sk_buff *skb; + + WARN_ON_ONCE(!in_task()); + + skb = sock_omalloc(sk, 0, GFP_KERNEL); + if (!skb) + return NULL; + + BUILD_BUG_ON(sizeof(*uarg) > sizeof(skb->cb)); + uarg = (void *)skb->cb; + + uarg->callback = sock_zerocopy_callback; + uarg->desc = atomic_inc_return(&sk->sk_zckey) - 1; + uarg->zerocopy = 1; + atomic_set(&uarg->refcnt, 0); + sock_hold(sk); + + return uarg; +} +EXPORT_SYMBOL_GPL(sock_zerocopy_alloc); + +static inline struct sk_buff *skb_from_uarg(struct ubuf_info *uarg) +{ + return container_of((void *)uarg, struct sk_buff, cb); +} + +void sock_zerocopy_callback(struct ubuf_info *uarg, bool success) +{ + struct sk_buff *skb = skb_from_uarg(uarg); + struct sock_exterr_skb *serr; + struct sock *sk = skb->sk; + u16 id = uarg->desc; + + if (sock_flag(sk, SOCK_DEAD)) + goto release; + + serr = SKB_EXT_ERR(skb); + memset(serr, 0, sizeof(*serr)); + serr->ee.ee_errno = 0; + serr->ee.ee_origin = SO_EE_ORIGIN_ZEROCOPY; + serr->ee.ee_data = id; + if (!success) + serr->ee.ee_code |= SO_EE_CODE_ZEROCOPY_COPIED; + + skb_queue_tail(&sk->sk_error_queue, skb); + skb = NULL; + + sk->sk_error_report(sk); + +release: + consume_skb(skb); + sock_put(sk); +} +EXPORT_SYMBOL_GPL(sock_zerocopy_callback); + +void sock_zerocopy_put(struct ubuf_info *uarg) +{ + if (uarg && atomic_dec_and_test(&uarg->refcnt)) { + if (uarg->callback) + uarg->callback(uarg, uarg->zerocopy); + else + consume_skb(skb_from_uarg(uarg)); + } +} +EXPORT_SYMBOL_GPL(sock_zerocopy_put); + +void sock_zerocopy_put_abort(struct ubuf_info *uarg) +{ + if (uarg) { + struct sock *sk = skb_from_uarg(uarg)->sk; + + atomic_dec(&sk->sk_zckey); + + /* sock_zerocopy_put expects a ref. Most sockets take one per + * skb, which is zero on abort. tcp_sendmsg holds one extra, to + * avoid an skb send inside the main loop triggering uarg free. + */ + if (sk->sk_type != SOCK_STREAM) + atomic_inc(&uarg->refcnt); + + sock_zerocopy_put(uarg); + } +} +EXPORT_SYMBOL_GPL(sock_zerocopy_put_abort); + +extern int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, + struct iov_iter *from, size_t length); + +int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, + struct msghdr *msg, int len, + struct ubuf_info *uarg) +{ + struct iov_iter orig_iter = msg->msg_iter; + int err, orig_len = skb->len; + + err = __zerocopy_sg_from_iter(sk, skb, &msg->msg_iter, len); + if (err == -EFAULT || (err == -EMSGSIZE && skb->len == orig_len)) { + /* Streams do not free skb on error. Reset to prev state. */ + msg->msg_iter = orig_iter; + ___pskb_trim(skb, orig_len); + return err; + } + + skb_zcopy_set(skb, uarg); + return skb->len - orig_len; +} +EXPORT_SYMBOL_GPL(skb_zerocopy_iter_stream); + +/* unused only until next patch in the series; will remove attribute */ +static int __attribute__((unused)) + skb_zerocopy_clone(struct sk_buff *nskb, struct sk_buff *orig, + gfp_t gfp_mask) +{ + if (skb_zcopy(orig)) { + if (skb_zcopy(nskb)) { + /* !gfp_mask callers are verified to !skb_zcopy(nskb) */ + if (!gfp_mask) { + WARN_ON_ONCE(1); + return -ENOMEM; + } + if (skb_uarg(nskb) == skb_uarg(orig)) + return 0; + if (skb_copy_ubufs(nskb, GFP_ATOMIC)) + return -EIO; + } + skb_zcopy_set(nskb, skb_uarg(orig)); + } + return 0; +} + /** * skb_copy_ubufs - copy userspace skb frags buffers to kernel * @skb: the skb to modify diff --git a/net/core/sock.c b/net/core/sock.c index 1261880bdcc8..e8b696858cad 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1670,6 +1670,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) atomic_set(&newsk->sk_drops, 0); newsk->sk_send_head = NULL; newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; + atomic_set(&newsk->sk_zckey, 0); sock_reset_flag(newsk, SOCK_DONE); @@ -2722,6 +2723,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; sk->sk_stamp = SK_DEFAULT_STAMP; + atomic_set(&sk->sk_zckey, 0); #ifdef CONFIG_NET_RX_BUSY_POLL sk->sk_napi_id = 0; -- cgit v1.2.3-71-gd317 From 059cf566e123ca7eb7434285c6455d7afafb4e02 Mon Sep 17 00:00:00 2001 From: Jens Wiklander Date: Thu, 16 Feb 2017 09:07:02 +0100 Subject: tee: indicate privileged dev in gen_caps Mirrors the TEE_DESC_PRIVILEGED bit of struct tee_desc:flags into struct tee_ioctl_version_data:gen_caps as TEE_GEN_CAP_PRIVILEGED in tee_ioctl_version() Reviewed-by: Jerome Forissier Signed-off-by: Jens Wiklander --- drivers/tee/tee_core.c | 5 +++++ include/uapi/linux/tee.h | 1 + 2 files changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c index 5c60bf4423e6..58a5009eacc3 100644 --- a/drivers/tee/tee_core.c +++ b/drivers/tee/tee_core.c @@ -90,8 +90,13 @@ static int tee_ioctl_version(struct tee_context *ctx, struct tee_ioctl_version_data vers; ctx->teedev->desc->ops->get_version(ctx->teedev, &vers); + + if (ctx->teedev->desc->flags & TEE_DESC_PRIVILEGED) + vers.gen_caps |= TEE_GEN_CAP_PRIVILEGED; + if (copy_to_user(uvers, &vers, sizeof(vers))) return -EFAULT; + return 0; } diff --git a/include/uapi/linux/tee.h b/include/uapi/linux/tee.h index 370d8845ab21..688782e90140 100644 --- a/include/uapi/linux/tee.h +++ b/include/uapi/linux/tee.h @@ -49,6 +49,7 @@ #define TEE_MAX_ARG_SIZE 1024 #define TEE_GEN_CAP_GP (1 << 0)/* GlobalPlatform compliant TEE */ +#define TEE_GEN_CAP_PRIVILEGED (1 << 1)/* Privileged device (for supplicant) */ /* * TEE Implementation ID -- cgit v1.2.3-71-gd317 From 56ce097c1caede1f9c191a7c9699b950e7c36ad9 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 4 Aug 2017 08:24:05 -0700 Subject: net: comment fixes against BPF devmap helper calls Update BPF comments to accurately reflect XDP usage. Fixes: 97f91a7cf04ff ("bpf: add bpf_redirect_map helper routine") Reported-by: Alexei Starovoitov Signed-off-by: John Fastabend Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1106a8c4cd36..1d06be1569b1 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -345,14 +345,20 @@ union bpf_attr { * int bpf_redirect(ifindex, flags) * redirect to another netdev * @ifindex: ifindex of the net device - * @flags: bit 0 - if set, redirect to ingress instead of egress - * other bits - reserved - * Return: TC_ACT_REDIRECT - * int bpf_redirect_map(key, map, flags) + * @flags: + * cls_bpf: + * bit 0 - if set, redirect to ingress instead of egress + * other bits - reserved + * xdp_bpf: + * all bits - reserved + * Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error + * xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error + * int bpf_redirect_map(map, key, flags) * redirect to endpoint in map + * @map: pointer to dev map * @key: index in map to lookup - * @map: fd of map to do lookup in * @flags: -- + * Return: XDP_REDIRECT on success or XDP_ABORT on error * * u32 bpf_get_route_realm(skb) * retrieve a dst's tclassid -- cgit v1.2.3-71-gd317 From 472b46c352c9ff0b6fa57dbf85d77c51901a3368 Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Sun, 6 Aug 2017 18:44:27 +0200 Subject: uapi linux/kfd_ioctl.h: only use __u32 and __u64 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Include instead of which on Linux includes and on non-Linux platforms defines __u32 etc types. Fixes user space compilation errors like: linux/kfd_ioctl.h:33:2: error: unknown type name ‘uint32_t’ uint32_t major_version; /* from KFD */ ^~~~~~~~ Signed-off-by: Mikko Rapeli Acked-by: Arnd Bergmann Signed-off-by: Oded Gabbay --- include/uapi/linux/kfd_ioctl.h | 172 ++++++++++++++++++++--------------------- 1 file changed, 86 insertions(+), 86 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 7b4567bacfc2..26283fefdf5f 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -23,15 +23,15 @@ #ifndef KFD_IOCTL_H_INCLUDED #define KFD_IOCTL_H_INCLUDED -#include +#include #include #define KFD_IOCTL_MAJOR_VERSION 1 #define KFD_IOCTL_MINOR_VERSION 1 struct kfd_ioctl_get_version_args { - uint32_t major_version; /* from KFD */ - uint32_t minor_version; /* from KFD */ + __u32 major_version; /* from KFD */ + __u32 minor_version; /* from KFD */ }; /* For kfd_ioctl_create_queue_args.queue_type. */ @@ -43,36 +43,36 @@ struct kfd_ioctl_get_version_args { #define KFD_MAX_QUEUE_PRIORITY 15 struct kfd_ioctl_create_queue_args { - uint64_t ring_base_address; /* to KFD */ - uint64_t write_pointer_address; /* from KFD */ - uint64_t read_pointer_address; /* from KFD */ - uint64_t doorbell_offset; /* from KFD */ - - uint32_t ring_size; /* to KFD */ - uint32_t gpu_id; /* to KFD */ - uint32_t queue_type; /* to KFD */ - uint32_t queue_percentage; /* to KFD */ - uint32_t queue_priority; /* to KFD */ - uint32_t queue_id; /* from KFD */ - - uint64_t eop_buffer_address; /* to KFD */ - uint64_t eop_buffer_size; /* to KFD */ - uint64_t ctx_save_restore_address; /* to KFD */ - uint64_t ctx_save_restore_size; /* to KFD */ + __u64 ring_base_address; /* to KFD */ + __u64 write_pointer_address; /* from KFD */ + __u64 read_pointer_address; /* from KFD */ + __u64 doorbell_offset; /* from KFD */ + + __u32 ring_size; /* to KFD */ + __u32 gpu_id; /* to KFD */ + __u32 queue_type; /* to KFD */ + __u32 queue_percentage; /* to KFD */ + __u32 queue_priority; /* to KFD */ + __u32 queue_id; /* from KFD */ + + __u64 eop_buffer_address; /* to KFD */ + __u64 eop_buffer_size; /* to KFD */ + __u64 ctx_save_restore_address; /* to KFD */ + __u64 ctx_save_restore_size; /* to KFD */ }; struct kfd_ioctl_destroy_queue_args { - uint32_t queue_id; /* to KFD */ - uint32_t pad; + __u32 queue_id; /* to KFD */ + __u32 pad; }; struct kfd_ioctl_update_queue_args { - uint64_t ring_base_address; /* to KFD */ + __u64 ring_base_address; /* to KFD */ - uint32_t queue_id; /* to KFD */ - uint32_t ring_size; /* to KFD */ - uint32_t queue_percentage; /* to KFD */ - uint32_t queue_priority; /* to KFD */ + __u32 queue_id; /* to KFD */ + __u32 ring_size; /* to KFD */ + __u32 queue_percentage; /* to KFD */ + __u32 queue_priority; /* to KFD */ }; /* For kfd_ioctl_set_memory_policy_args.default_policy and alternate_policy */ @@ -80,13 +80,13 @@ struct kfd_ioctl_update_queue_args { #define KFD_IOC_CACHE_POLICY_NONCOHERENT 1 struct kfd_ioctl_set_memory_policy_args { - uint64_t alternate_aperture_base; /* to KFD */ - uint64_t alternate_aperture_size; /* to KFD */ + __u64 alternate_aperture_base; /* to KFD */ + __u64 alternate_aperture_size; /* to KFD */ - uint32_t gpu_id; /* to KFD */ - uint32_t default_policy; /* to KFD */ - uint32_t alternate_policy; /* to KFD */ - uint32_t pad; + __u32 gpu_id; /* to KFD */ + __u32 default_policy; /* to KFD */ + __u32 alternate_policy; /* to KFD */ + __u32 pad; }; /* @@ -97,26 +97,26 @@ struct kfd_ioctl_set_memory_policy_args { */ struct kfd_ioctl_get_clock_counters_args { - uint64_t gpu_clock_counter; /* from KFD */ - uint64_t cpu_clock_counter; /* from KFD */ - uint64_t system_clock_counter; /* from KFD */ - uint64_t system_clock_freq; /* from KFD */ + __u64 gpu_clock_counter; /* from KFD */ + __u64 cpu_clock_counter; /* from KFD */ + __u64 system_clock_counter; /* from KFD */ + __u64 system_clock_freq; /* from KFD */ - uint32_t gpu_id; /* to KFD */ - uint32_t pad; + __u32 gpu_id; /* to KFD */ + __u32 pad; }; #define NUM_OF_SUPPORTED_GPUS 7 struct kfd_process_device_apertures { - uint64_t lds_base; /* from KFD */ - uint64_t lds_limit; /* from KFD */ - uint64_t scratch_base; /* from KFD */ - uint64_t scratch_limit; /* from KFD */ - uint64_t gpuvm_base; /* from KFD */ - uint64_t gpuvm_limit; /* from KFD */ - uint32_t gpu_id; /* from KFD */ - uint32_t pad; + __u64 lds_base; /* from KFD */ + __u64 lds_limit; /* from KFD */ + __u64 scratch_base; /* from KFD */ + __u64 scratch_limit; /* from KFD */ + __u64 gpuvm_base; /* from KFD */ + __u64 gpuvm_limit; /* from KFD */ + __u32 gpu_id; /* from KFD */ + __u32 pad; }; struct kfd_ioctl_get_process_apertures_args { @@ -124,8 +124,8 @@ struct kfd_ioctl_get_process_apertures_args { process_apertures[NUM_OF_SUPPORTED_GPUS];/* from KFD */ /* from KFD, should be in the range [1 - NUM_OF_SUPPORTED_GPUS] */ - uint32_t num_of_nodes; - uint32_t pad; + __u32 num_of_nodes; + __u32 pad; }; #define MAX_ALLOWED_NUM_POINTS 100 @@ -133,25 +133,25 @@ struct kfd_ioctl_get_process_apertures_args { #define MAX_ALLOWED_WAC_BUFF_SIZE 128 struct kfd_ioctl_dbg_register_args { - uint32_t gpu_id; /* to KFD */ - uint32_t pad; + __u32 gpu_id; /* to KFD */ + __u32 pad; }; struct kfd_ioctl_dbg_unregister_args { - uint32_t gpu_id; /* to KFD */ - uint32_t pad; + __u32 gpu_id; /* to KFD */ + __u32 pad; }; struct kfd_ioctl_dbg_address_watch_args { - uint64_t content_ptr; /* a pointer to the actual content */ - uint32_t gpu_id; /* to KFD */ - uint32_t buf_size_in_bytes; /*including gpu_id and buf_size */ + __u64 content_ptr; /* a pointer to the actual content */ + __u32 gpu_id; /* to KFD */ + __u32 buf_size_in_bytes; /*including gpu_id and buf_size */ }; struct kfd_ioctl_dbg_wave_control_args { - uint64_t content_ptr; /* a pointer to the actual content */ - uint32_t gpu_id; /* to KFD */ - uint32_t buf_size_in_bytes; /*including gpu_id and buf_size */ + __u64 content_ptr; /* a pointer to the actual content */ + __u32 gpu_id; /* to KFD */ + __u32 buf_size_in_bytes; /*including gpu_id and buf_size */ }; /* Matching HSA_EVENTTYPE */ @@ -172,44 +172,44 @@ struct kfd_ioctl_dbg_wave_control_args { #define KFD_SIGNAL_EVENT_LIMIT 256 struct kfd_ioctl_create_event_args { - uint64_t event_page_offset; /* from KFD */ - uint32_t event_trigger_data; /* from KFD - signal events only */ - uint32_t event_type; /* to KFD */ - uint32_t auto_reset; /* to KFD */ - uint32_t node_id; /* to KFD - only valid for certain + __u64 event_page_offset; /* from KFD */ + __u32 event_trigger_data; /* from KFD - signal events only */ + __u32 event_type; /* to KFD */ + __u32 auto_reset; /* to KFD */ + __u32 node_id; /* to KFD - only valid for certain event types */ - uint32_t event_id; /* from KFD */ - uint32_t event_slot_index; /* from KFD */ + __u32 event_id; /* from KFD */ + __u32 event_slot_index; /* from KFD */ }; struct kfd_ioctl_destroy_event_args { - uint32_t event_id; /* to KFD */ - uint32_t pad; + __u32 event_id; /* to KFD */ + __u32 pad; }; struct kfd_ioctl_set_event_args { - uint32_t event_id; /* to KFD */ - uint32_t pad; + __u32 event_id; /* to KFD */ + __u32 pad; }; struct kfd_ioctl_reset_event_args { - uint32_t event_id; /* to KFD */ - uint32_t pad; + __u32 event_id; /* to KFD */ + __u32 pad; }; struct kfd_memory_exception_failure { - uint32_t NotPresent; /* Page not present or supervisor privilege */ - uint32_t ReadOnly; /* Write access to a read-only page */ - uint32_t NoExecute; /* Execute access to a page marked NX */ - uint32_t pad; + __u32 NotPresent; /* Page not present or supervisor privilege */ + __u32 ReadOnly; /* Write access to a read-only page */ + __u32 NoExecute; /* Execute access to a page marked NX */ + __u32 pad; }; /* memory exception data*/ struct kfd_hsa_memory_exception_data { struct kfd_memory_exception_failure failure; - uint64_t va; - uint32_t gpu_id; - uint32_t pad; + __u64 va; + __u32 gpu_id; + __u32 pad; }; /* Event data*/ @@ -217,19 +217,19 @@ struct kfd_event_data { union { struct kfd_hsa_memory_exception_data memory_exception_data; }; /* From KFD */ - uint64_t kfd_event_data_ext; /* pointer to an extension structure + __u64 kfd_event_data_ext; /* pointer to an extension structure for future exception types */ - uint32_t event_id; /* to KFD */ - uint32_t pad; + __u32 event_id; /* to KFD */ + __u32 pad; }; struct kfd_ioctl_wait_events_args { - uint64_t events_ptr; /* pointed to struct + __u64 events_ptr; /* pointed to struct kfd_event_data array, to KFD */ - uint32_t num_events; /* to KFD */ - uint32_t wait_for_all; /* to KFD */ - uint32_t timeout; /* to KFD */ - uint32_t wait_result; /* from KFD */ + __u32 num_events; /* to KFD */ + __u32 wait_for_all; /* to KFD */ + __u32 timeout; /* to KFD */ + __u32 wait_result; /* from KFD */ }; struct kfd_ioctl_set_scratch_backing_va_args { -- cgit v1.2.3-71-gd317 From f02a60924c221985fb8b634734d6610706fa779a Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Sun, 6 Aug 2017 18:44:07 +0200 Subject: uapi linux/dlm_netlink.h: include linux/dlmconstants.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes userspace compilation error: error: ‘DLM_RESNAME_MAXLEN’ undeclared here (not in a function) char resource_name[DLM_RESNAME_MAXLEN]; Signed-off-by: Mikko Rapeli Signed-off-by: David Teigland --- include/uapi/linux/dlm_netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/dlm_netlink.h b/include/uapi/linux/dlm_netlink.h index 647c8ef27227..ef1e2e08769a 100644 --- a/include/uapi/linux/dlm_netlink.h +++ b/include/uapi/linux/dlm_netlink.h @@ -10,6 +10,7 @@ #define _DLM_NETLINK_H #include +#include enum { DLM_STATUS_WAITING = 1, -- cgit v1.2.3-71-gd317 From d1df6fd8a1d22d37cffa0075ab8ad423ce656777 Mon Sep 17 00:00:00 2001 From: David Lebrun Date: Sat, 5 Aug 2017 12:38:26 +0200 Subject: ipv6: sr: define core operations for seg6local lightweight tunnel This patch implements a new type of lightweight tunnel named seg6local. A seg6local lwt is defined by a type of action and a set of parameters. The action represents the operation to perform on the packets matching the lwt's route, and is not necessarily an encapsulation. The set of parameters are arguments for the processing function. Each action is defined in a struct seg6_action_desc within seg6_action_table[]. This structure contains the action, mandatory attributes, the processing function, and a static headroom size required by the action. The mandatory attributes are encoded as a bitmask field. The static headroom is set to a non-zero value when the processing function always add a constant number of bytes to the skb (e.g. the header size for encapsulations). To facilitate rtnetlink-related operations such as parsing, fill_encap, and cmp_encap, each type of action parameter is associated to three function pointers, in seg6_action_params[]. All actions defined in seg6_local.h are detailed in [1]. [1] https://tools.ietf.org/html/draft-filsfils-spring-srv6-network-programming-01 Signed-off-by: David Lebrun Signed-off-by: David S. Miller --- include/linux/seg6_local.h | 6 + include/net/seg6.h | 2 + include/uapi/linux/lwtunnel.h | 1 + include/uapi/linux/seg6_local.h | 68 +++++++++ net/core/lwtunnel.c | 2 + net/ipv6/Kconfig | 3 +- net/ipv6/Makefile | 2 +- net/ipv6/seg6.c | 5 + net/ipv6/seg6_local.c | 320 ++++++++++++++++++++++++++++++++++++++++ 9 files changed, 407 insertions(+), 2 deletions(-) create mode 100644 include/linux/seg6_local.h create mode 100644 include/uapi/linux/seg6_local.h create mode 100644 net/ipv6/seg6_local.c (limited to 'include/uapi/linux') diff --git a/include/linux/seg6_local.h b/include/linux/seg6_local.h new file mode 100644 index 000000000000..ee63e76fe0c7 --- /dev/null +++ b/include/linux/seg6_local.h @@ -0,0 +1,6 @@ +#ifndef _LINUX_SEG6_LOCAL_H +#define _LINUX_SEG6_LOCAL_H + +#include + +#endif diff --git a/include/net/seg6.h b/include/net/seg6.h index a32abb040e1d..5379f550f521 100644 --- a/include/net/seg6.h +++ b/include/net/seg6.h @@ -56,6 +56,8 @@ extern int seg6_init(void); extern void seg6_exit(void); extern int seg6_iptunnel_init(void); extern void seg6_iptunnel_exit(void); +extern int seg6_local_init(void); +extern void seg6_local_exit(void); extern bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len); extern int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh); diff --git a/include/uapi/linux/lwtunnel.h b/include/uapi/linux/lwtunnel.h index 92724cba1eba..7fdd19ca7511 100644 --- a/include/uapi/linux/lwtunnel.h +++ b/include/uapi/linux/lwtunnel.h @@ -11,6 +11,7 @@ enum lwtunnel_encap_types { LWTUNNEL_ENCAP_IP6, LWTUNNEL_ENCAP_SEG6, LWTUNNEL_ENCAP_BPF, + LWTUNNEL_ENCAP_SEG6_LOCAL, __LWTUNNEL_ENCAP_MAX, }; diff --git a/include/uapi/linux/seg6_local.h b/include/uapi/linux/seg6_local.h new file mode 100644 index 000000000000..ef2d8c3e76c1 --- /dev/null +++ b/include/uapi/linux/seg6_local.h @@ -0,0 +1,68 @@ +/* + * SR-IPv6 implementation + * + * Author: + * David Lebrun + * + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _UAPI_LINUX_SEG6_LOCAL_H +#define _UAPI_LINUX_SEG6_LOCAL_H + +#include + +enum { + SEG6_LOCAL_UNSPEC, + SEG6_LOCAL_ACTION, + SEG6_LOCAL_SRH, + SEG6_LOCAL_TABLE, + SEG6_LOCAL_NH4, + SEG6_LOCAL_NH6, + SEG6_LOCAL_IIF, + SEG6_LOCAL_OIF, + __SEG6_LOCAL_MAX, +}; +#define SEG6_LOCAL_MAX (__SEG6_LOCAL_MAX - 1) + +enum { + SEG6_LOCAL_ACTION_UNSPEC = 0, + /* node segment */ + SEG6_LOCAL_ACTION_END = 1, + /* adjacency segment (IPv6 cross-connect) */ + SEG6_LOCAL_ACTION_END_X = 2, + /* lookup of next seg NH in table */ + SEG6_LOCAL_ACTION_END_T = 3, + /* decap and L2 cross-connect */ + SEG6_LOCAL_ACTION_END_DX2 = 4, + /* decap and IPv6 cross-connect */ + SEG6_LOCAL_ACTION_END_DX6 = 5, + /* decap and IPv4 cross-connect */ + SEG6_LOCAL_ACTION_END_DX4 = 6, + /* decap and lookup of DA in v6 table */ + SEG6_LOCAL_ACTION_END_DT6 = 7, + /* decap and lookup of DA in v4 table */ + SEG6_LOCAL_ACTION_END_DT4 = 8, + /* binding segment with insertion */ + SEG6_LOCAL_ACTION_END_B6 = 9, + /* binding segment with encapsulation */ + SEG6_LOCAL_ACTION_END_B6_ENCAP = 10, + /* binding segment with MPLS encap */ + SEG6_LOCAL_ACTION_END_BM = 11, + /* lookup last seg in table */ + SEG6_LOCAL_ACTION_END_S = 12, + /* forward to SR-unaware VNF with static proxy */ + SEG6_LOCAL_ACTION_END_AS = 13, + /* forward to SR-unaware VNF with masquerading */ + SEG6_LOCAL_ACTION_END_AM = 14, + + __SEG6_LOCAL_ACTION_MAX, +}; + +#define SEG6_LOCAL_ACTION_MAX (__SEG6_LOCAL_ACTION_MAX - 1) + +#endif diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index 435f35f9a61c..0b171756453c 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -44,6 +44,8 @@ static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type) return "SEG6"; case LWTUNNEL_ENCAP_BPF: return "BPF"; + case LWTUNNEL_ENCAP_SEG6_LOCAL: + return "SEG6LOCAL"; case LWTUNNEL_ENCAP_IP6: case LWTUNNEL_ENCAP_IP: case LWTUNNEL_ENCAP_NONE: diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 50181a96923e..0d722396dce6 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -311,7 +311,8 @@ config IPV6_SEG6_LWTUNNEL ---help--- Support for encapsulation of packets within an outer IPv6 header and a Segment Routing Header using the lightweight - tunnels mechanism. + tunnels mechanism. Also enable support for advanced local + processing of SRv6 packets based on their active segment. If unsure, say N. diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index f8b24c2e0d77..10e342363793 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -23,7 +23,7 @@ ipv6-$(CONFIG_IPV6_MULTIPLE_TABLES) += fib6_rules.o ipv6-$(CONFIG_PROC_FS) += proc.o ipv6-$(CONFIG_SYN_COOKIES) += syncookies.o ipv6-$(CONFIG_NETLABEL) += calipso.o -ipv6-$(CONFIG_IPV6_SEG6_LWTUNNEL) += seg6_iptunnel.o +ipv6-$(CONFIG_IPV6_SEG6_LWTUNNEL) += seg6_iptunnel.o seg6_local.o ipv6-$(CONFIG_IPV6_SEG6_HMAC) += seg6_hmac.o ipv6-objs += $(ipv6-y) diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 81c2339b3285..c81407770956 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -456,6 +456,10 @@ int __init seg6_init(void) err = seg6_iptunnel_init(); if (err) goto out_unregister_pernet; + + err = seg6_local_init(); + if (err) + goto out_unregister_pernet; #endif #ifdef CONFIG_IPV6_SEG6_HMAC @@ -471,6 +475,7 @@ out: #ifdef CONFIG_IPV6_SEG6_HMAC out_unregister_iptun: #ifdef CONFIG_IPV6_SEG6_LWTUNNEL + seg6_local_exit(); seg6_iptunnel_exit(); #endif #endif diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c new file mode 100644 index 000000000000..53615d7e0723 --- /dev/null +++ b/net/ipv6/seg6_local.c @@ -0,0 +1,320 @@ +/* + * SR-IPv6 implementation + * + * Author: + * David Lebrun + * + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#ifdef CONFIG_IPV6_SEG6_HMAC +#include +#endif + +struct seg6_local_lwt; + +struct seg6_action_desc { + int action; + unsigned long attrs; + int (*input)(struct sk_buff *skb, struct seg6_local_lwt *slwt); + int static_headroom; +}; + +struct seg6_local_lwt { + int action; + struct ipv6_sr_hdr *srh; + int table; + struct in_addr nh4; + struct in6_addr nh6; + int iif; + int oif; + + int headroom; + struct seg6_action_desc *desc; +}; + +static struct seg6_local_lwt *seg6_local_lwtunnel(struct lwtunnel_state *lwt) +{ + return (struct seg6_local_lwt *)lwt->data; +} + +static struct seg6_action_desc seg6_action_table[] = { + { + .action = SEG6_LOCAL_ACTION_END, + .attrs = 0, + }, +}; + +static struct seg6_action_desc *__get_action_desc(int action) +{ + struct seg6_action_desc *desc; + int i, count; + + count = sizeof(seg6_action_table) / sizeof(struct seg6_action_desc); + for (i = 0; i < count; i++) { + desc = &seg6_action_table[i]; + if (desc->action == action) + return desc; + } + + return NULL; +} + +static int seg6_local_input(struct sk_buff *skb) +{ + struct dst_entry *orig_dst = skb_dst(skb); + struct seg6_action_desc *desc; + struct seg6_local_lwt *slwt; + + slwt = seg6_local_lwtunnel(orig_dst->lwtstate); + desc = slwt->desc; + + return desc->input(skb, slwt); +} + +static const struct nla_policy seg6_local_policy[SEG6_LOCAL_MAX + 1] = { + [SEG6_LOCAL_ACTION] = { .type = NLA_U32 }, + [SEG6_LOCAL_SRH] = { .type = NLA_BINARY }, + [SEG6_LOCAL_TABLE] = { .type = NLA_U32 }, + [SEG6_LOCAL_NH4] = { .type = NLA_BINARY, + .len = sizeof(struct in_addr) }, + [SEG6_LOCAL_NH6] = { .type = NLA_BINARY, + .len = sizeof(struct in6_addr) }, + [SEG6_LOCAL_IIF] = { .type = NLA_U32 }, + [SEG6_LOCAL_OIF] = { .type = NLA_U32 }, +}; + +struct seg6_action_param { + int (*parse)(struct nlattr **attrs, struct seg6_local_lwt *slwt); + int (*put)(struct sk_buff *skb, struct seg6_local_lwt *slwt); + int (*cmp)(struct seg6_local_lwt *a, struct seg6_local_lwt *b); +}; + +static struct seg6_action_param seg6_action_params[SEG6_LOCAL_MAX + 1] = { + [SEG6_LOCAL_SRH] = { .parse = NULL, + .put = NULL, + .cmp = NULL }, + + [SEG6_LOCAL_TABLE] = { .parse = NULL, + .put = NULL, + .cmp = NULL }, + + [SEG6_LOCAL_NH4] = { .parse = NULL, + .put = NULL, + .cmp = NULL }, + + [SEG6_LOCAL_NH6] = { .parse = NULL, + .put = NULL, + .cmp = NULL }, + + [SEG6_LOCAL_IIF] = { .parse = NULL, + .put = NULL, + .cmp = NULL }, + + [SEG6_LOCAL_OIF] = { .parse = NULL, + .put = NULL, + .cmp = NULL }, +}; + +static int parse_nla_action(struct nlattr **attrs, struct seg6_local_lwt *slwt) +{ + struct seg6_action_param *param; + struct seg6_action_desc *desc; + int i, err; + + desc = __get_action_desc(slwt->action); + if (!desc) + return -EINVAL; + + if (!desc->input) + return -EOPNOTSUPP; + + slwt->desc = desc; + slwt->headroom += desc->static_headroom; + + for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) { + if (desc->attrs & (1 << i)) { + if (!attrs[i]) + return -EINVAL; + + param = &seg6_action_params[i]; + + err = param->parse(attrs, slwt); + if (err < 0) + return err; + } + } + + return 0; +} + +static int seg6_local_build_state(struct nlattr *nla, unsigned int family, + const void *cfg, struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[SEG6_LOCAL_MAX + 1]; + struct lwtunnel_state *newts; + struct seg6_local_lwt *slwt; + int err; + + err = nla_parse_nested(tb, SEG6_LOCAL_MAX, nla, seg6_local_policy, + extack); + + if (err < 0) + return err; + + if (!tb[SEG6_LOCAL_ACTION]) + return -EINVAL; + + newts = lwtunnel_state_alloc(sizeof(*slwt)); + if (!newts) + return -ENOMEM; + + slwt = seg6_local_lwtunnel(newts); + slwt->action = nla_get_u32(tb[SEG6_LOCAL_ACTION]); + + err = parse_nla_action(tb, slwt); + if (err < 0) + goto out_free; + + newts->type = LWTUNNEL_ENCAP_SEG6_LOCAL; + newts->flags = LWTUNNEL_STATE_INPUT_REDIRECT; + newts->headroom = slwt->headroom; + + *ts = newts; + + return 0; + +out_free: + kfree(slwt->srh); + kfree(newts); + return err; +} + +static void seg6_local_destroy_state(struct lwtunnel_state *lwt) +{ + struct seg6_local_lwt *slwt = seg6_local_lwtunnel(lwt); + + kfree(slwt->srh); +} + +static int seg6_local_fill_encap(struct sk_buff *skb, + struct lwtunnel_state *lwt) +{ + struct seg6_local_lwt *slwt = seg6_local_lwtunnel(lwt); + struct seg6_action_param *param; + int i, err; + + if (nla_put_u32(skb, SEG6_LOCAL_ACTION, slwt->action)) + return -EMSGSIZE; + + for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) { + if (slwt->desc->attrs & (1 << i)) { + param = &seg6_action_params[i]; + err = param->put(skb, slwt); + if (err < 0) + return err; + } + } + + return 0; +} + +static int seg6_local_get_encap_size(struct lwtunnel_state *lwt) +{ + struct seg6_local_lwt *slwt = seg6_local_lwtunnel(lwt); + unsigned long attrs; + int nlsize; + + nlsize = nla_total_size(4); /* action */ + + attrs = slwt->desc->attrs; + + if (attrs & (1 << SEG6_LOCAL_SRH)) + nlsize += nla_total_size((slwt->srh->hdrlen + 1) << 3); + + if (attrs & (1 << SEG6_LOCAL_TABLE)) + nlsize += nla_total_size(4); + + if (attrs & (1 << SEG6_LOCAL_NH4)) + nlsize += nla_total_size(4); + + if (attrs & (1 << SEG6_LOCAL_NH6)) + nlsize += nla_total_size(16); + + if (attrs & (1 << SEG6_LOCAL_IIF)) + nlsize += nla_total_size(4); + + if (attrs & (1 << SEG6_LOCAL_OIF)) + nlsize += nla_total_size(4); + + return nlsize; +} + +static int seg6_local_cmp_encap(struct lwtunnel_state *a, + struct lwtunnel_state *b) +{ + struct seg6_local_lwt *slwt_a, *slwt_b; + struct seg6_action_param *param; + int i; + + slwt_a = seg6_local_lwtunnel(a); + slwt_b = seg6_local_lwtunnel(b); + + if (slwt_a->action != slwt_b->action) + return 1; + + if (slwt_a->desc->attrs != slwt_b->desc->attrs) + return 1; + + for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) { + if (slwt_a->desc->attrs & (1 << i)) { + param = &seg6_action_params[i]; + if (param->cmp(slwt_a, slwt_b)) + return 1; + } + } + + return 0; +} + +static const struct lwtunnel_encap_ops seg6_local_ops = { + .build_state = seg6_local_build_state, + .destroy_state = seg6_local_destroy_state, + .input = seg6_local_input, + .fill_encap = seg6_local_fill_encap, + .get_encap_size = seg6_local_get_encap_size, + .cmp_encap = seg6_local_cmp_encap, + .owner = THIS_MODULE, +}; + +int __init seg6_local_init(void) +{ + return lwtunnel_encap_add_ops(&seg6_local_ops, + LWTUNNEL_ENCAP_SEG6_LOCAL); +} + +void seg6_local_exit(void) +{ + lwtunnel_encap_del_ops(&seg6_local_ops, LWTUNNEL_ENCAP_SEG6_LOCAL); +} -- cgit v1.2.3-71-gd317 From 6c2c188f35c61c8eee71ec6d07524ce122c06539 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 28 Jul 2017 03:25:06 -0400 Subject: media: drop use of MEDIA_API_VERSION Set media_version to LINUX_VERSION_CODE, just as we did for driver_version. Nobody ever rememebers to update the version number, but LINUX_VERSION_CODE will always be updated. Move the MEDIA_API_VERSION define to the ifndef __KERNEL__ section of the media.h header. That way kernelspace can't accidentally start to use it again. Signed-off-by: Hans Verkuil Reviewed-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- drivers/media/media-device.c | 4 ++-- include/uapi/linux/media.h | 5 +++-- 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c index 979e4307d248..e79f72b8b858 100644 --- a/drivers/media/media-device.c +++ b/drivers/media/media-device.c @@ -69,9 +69,9 @@ static int media_device_get_info(struct media_device *dev, strlcpy(info->serial, dev->serial, sizeof(info->serial)); strlcpy(info->bus_info, dev->bus_info, sizeof(info->bus_info)); - info->media_version = MEDIA_API_VERSION; + info->media_version = LINUX_VERSION_CODE; + info->driver_version = info->media_version; info->hw_revision = dev->hw_revision; - info->driver_version = LINUX_VERSION_CODE; return 0; } diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index fac96c64fe51..4865f1e71339 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -30,8 +30,6 @@ #include #include -#define MEDIA_API_VERSION KERNEL_VERSION(0, 1, 0) - struct media_device_info { char driver[16]; char model[32]; @@ -187,6 +185,9 @@ struct media_device_info { #define MEDIA_ENT_T_V4L2_SUBDEV_LENS MEDIA_ENT_F_LENS #define MEDIA_ENT_T_V4L2_SUBDEV_DECODER MEDIA_ENT_F_ATV_DECODER #define MEDIA_ENT_T_V4L2_SUBDEV_TUNER MEDIA_ENT_F_TUNER + +/* Obsolete symbol for media_version, no longer used in the kernel */ +#define MEDIA_API_VERSION KERNEL_VERSION(0, 1, 0) #endif /* Entity flags */ -- cgit v1.2.3-71-gd317 From 79bcd34ccfe009ad21d16100ae2aef9b378a512d Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 1 Aug 2017 07:53:30 -0400 Subject: media: cec-funcs.h: cec_ops_report_features: set *dev_features to NULL gcc can get confused by this code and it thinks dev_features can be returned uninitialized. So initialize to NULL at the beginning to shut up the warning. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/cec-funcs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/cec-funcs.h b/include/uapi/linux/cec-funcs.h index c451eec42a83..270b251a3d9b 100644 --- a/include/uapi/linux/cec-funcs.h +++ b/include/uapi/linux/cec-funcs.h @@ -895,6 +895,7 @@ static inline void cec_ops_report_features(const struct cec_msg *msg, *cec_version = msg->msg[2]; *all_device_types = msg->msg[3]; *rc_profile = p; + *dev_features = NULL; while (p < &msg->msg[14] && (*p & CEC_OP_FEAT_EXT)) p++; if (!(*p & CEC_OP_FEAT_EXT)) { -- cgit v1.2.3-71-gd317 From 92b31a9af73b3a3fc801899335d6c47966351830 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 10 Aug 2017 01:39:55 +0200 Subject: bpf: add BPF_J{LT,LE,SLT,SLE} instructions Currently, eBPF only understands BPF_JGT (>), BPF_JGE (>=), BPF_JSGT (s>), BPF_JSGE (s>=) instructions, this means that particularly *JLT/*JLE counterparts involving immediates need to be rewritten from e.g. X < [IMM] by swapping arguments into [IMM] > X, meaning the immediate first is required to be loaded into a register Y := [IMM], such that then we can compare with Y > X. Note that the destination operand is always required to be a register. This has the downside of having unnecessarily increased register pressure, meaning complex program would need to spill other registers temporarily to stack in order to obtain an unused register for the [IMM]. Loading to registers will thus also affect state pruning since we need to account for that register use and potentially those registers that had to be spilled/filled again. As a consequence slightly more stack space might have been used due to spilling, and BPF programs are a bit longer due to extra code involving the register load and potentially required spill/fills. Thus, add BPF_JLT (<), BPF_JLE (<=), BPF_JSLT (s<), BPF_JSLE (s<=) counterparts to the eBPF instruction set. Modifying LLVM to remove the NegateCC() workaround in a PoC patch at [1] and allowing it to also emit the new instructions resulted in cilium's BPF programs that are injected into the fast-path to have a reduced program length in the range of 2-3% (e.g. accumulated main and tail call sections from one of the object file reduced from 4864 to 4729 insns), reduced complexity in the range of 10-30% (e.g. accumulated sections reduced in one of the cases from 116432 to 88428 insns), and reduced stack usage in the range of 1-5% (e.g. accumulated sections from one of the object files reduced from 824 to 784b). The modification for LLVM will be incorporated in a backwards compatible way. Plan is for LLVM to have i) a target specific option to offer a possibility to explicitly enable the extension by the user (as we have with -m target specific extensions today for various CPU insns), and ii) have the kernel checked for presence of the extensions and enable them transparently when the user is selecting more aggressive options such as -march=native in a bpf target context. (Other frontends generating BPF byte code, e.g. ply can probe the kernel directly for its code generation.) [1] https://github.com/borkmann/llvm/tree/bpf-insns Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- Documentation/networking/filter.txt | 4 + include/uapi/linux/bpf.h | 5 + kernel/bpf/core.c | 60 ++++++ lib/test_bpf.c | 364 ++++++++++++++++++++++++++++++++++++ net/core/filter.c | 21 ++- tools/include/uapi/linux/bpf.h | 5 + 6 files changed, 455 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt index d0fdba7d66e2..6a0df8df6c43 100644 --- a/Documentation/networking/filter.txt +++ b/Documentation/networking/filter.txt @@ -906,6 +906,10 @@ If BPF_CLASS(code) == BPF_JMP, BPF_OP(code) is one of: BPF_JSGE 0x70 /* eBPF only: signed '>=' */ BPF_CALL 0x80 /* eBPF only: function call */ BPF_EXIT 0x90 /* eBPF only: function return */ + BPF_JLT 0xa0 /* eBPF only: unsigned '<' */ + BPF_JLE 0xb0 /* eBPF only: unsigned '<=' */ + BPF_JSLT 0xc0 /* eBPF only: signed '<' */ + BPF_JSLE 0xd0 /* eBPF only: signed '<=' */ So BPF_ADD | BPF_X | BPF_ALU means 32-bit addition in both classic BPF and eBPF. There are only two registers in classic BPF, so it means A += X. diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1d06be1569b1..91da8371a2d0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -30,9 +30,14 @@ #define BPF_FROM_LE BPF_TO_LE #define BPF_FROM_BE BPF_TO_BE +/* jmp encodings */ #define BPF_JNE 0x50 /* jump != */ +#define BPF_JLT 0xa0 /* LT is unsigned, '<' */ +#define BPF_JLE 0xb0 /* LE is unsigned, '<=' */ #define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */ #define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */ +#define BPF_JSLT 0xc0 /* SLT is signed, '<' */ +#define BPF_JSLE 0xd0 /* SLE is signed, '<=' */ #define BPF_CALL 0x80 /* function call */ #define BPF_EXIT 0x90 /* function return */ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index ad5f55922a13..c69e7f5bfde7 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -595,9 +595,13 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from, case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JNE | BPF_K: case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JLT | BPF_K: case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JLE | BPF_K: case BPF_JMP | BPF_JSGT | BPF_K: + case BPF_JMP | BPF_JSLT | BPF_K: case BPF_JMP | BPF_JSGE | BPF_K: + case BPF_JMP | BPF_JSLE | BPF_K: case BPF_JMP | BPF_JSET | BPF_K: /* Accommodate for extra offset in case of a backjump. */ off = from->off; @@ -833,12 +837,20 @@ static unsigned int ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, [BPF_JMP | BPF_JNE | BPF_K] = &&JMP_JNE_K, [BPF_JMP | BPF_JGT | BPF_X] = &&JMP_JGT_X, [BPF_JMP | BPF_JGT | BPF_K] = &&JMP_JGT_K, + [BPF_JMP | BPF_JLT | BPF_X] = &&JMP_JLT_X, + [BPF_JMP | BPF_JLT | BPF_K] = &&JMP_JLT_K, [BPF_JMP | BPF_JGE | BPF_X] = &&JMP_JGE_X, [BPF_JMP | BPF_JGE | BPF_K] = &&JMP_JGE_K, + [BPF_JMP | BPF_JLE | BPF_X] = &&JMP_JLE_X, + [BPF_JMP | BPF_JLE | BPF_K] = &&JMP_JLE_K, [BPF_JMP | BPF_JSGT | BPF_X] = &&JMP_JSGT_X, [BPF_JMP | BPF_JSGT | BPF_K] = &&JMP_JSGT_K, + [BPF_JMP | BPF_JSLT | BPF_X] = &&JMP_JSLT_X, + [BPF_JMP | BPF_JSLT | BPF_K] = &&JMP_JSLT_K, [BPF_JMP | BPF_JSGE | BPF_X] = &&JMP_JSGE_X, [BPF_JMP | BPF_JSGE | BPF_K] = &&JMP_JSGE_K, + [BPF_JMP | BPF_JSLE | BPF_X] = &&JMP_JSLE_X, + [BPF_JMP | BPF_JSLE | BPF_K] = &&JMP_JSLE_K, [BPF_JMP | BPF_JSET | BPF_X] = &&JMP_JSET_X, [BPF_JMP | BPF_JSET | BPF_K] = &&JMP_JSET_K, /* Program return */ @@ -1073,6 +1085,18 @@ out: CONT_JMP; } CONT; + JMP_JLT_X: + if (DST < SRC) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JLT_K: + if (DST < IMM) { + insn += insn->off; + CONT_JMP; + } + CONT; JMP_JGE_X: if (DST >= SRC) { insn += insn->off; @@ -1085,6 +1109,18 @@ out: CONT_JMP; } CONT; + JMP_JLE_X: + if (DST <= SRC) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JLE_K: + if (DST <= IMM) { + insn += insn->off; + CONT_JMP; + } + CONT; JMP_JSGT_X: if (((s64) DST) > ((s64) SRC)) { insn += insn->off; @@ -1097,6 +1133,18 @@ out: CONT_JMP; } CONT; + JMP_JSLT_X: + if (((s64) DST) < ((s64) SRC)) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JSLT_K: + if (((s64) DST) < ((s64) IMM)) { + insn += insn->off; + CONT_JMP; + } + CONT; JMP_JSGE_X: if (((s64) DST) >= ((s64) SRC)) { insn += insn->off; @@ -1109,6 +1157,18 @@ out: CONT_JMP; } CONT; + JMP_JSLE_X: + if (((s64) DST) <= ((s64) SRC)) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JSLE_K: + if (((s64) DST) <= ((s64) IMM)) { + insn += insn->off; + CONT_JMP; + } + CONT; JMP_JSET_X: if (DST & SRC) { insn += insn->off; diff --git a/lib/test_bpf.c b/lib/test_bpf.c index d9d5a410955c..aa8812ae6776 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -951,6 +951,32 @@ static struct bpf_test tests[] = { { 4, 4, 4, 3, 3 }, { { 2, 0 }, { 3, 1 }, { 4, MAX_K } }, }, + { + "JGE (jt 0), test 1", + .u.insns = { + BPF_STMT(BPF_LDX | BPF_LEN, 0), + BPF_STMT(BPF_LD | BPF_B | BPF_ABS, 2), + BPF_JUMP(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 1), + BPF_STMT(BPF_RET | BPF_K, 1), + BPF_STMT(BPF_RET | BPF_K, MAX_K) + }, + CLASSIC, + { 4, 4, 4, 3, 3 }, + { { 2, 0 }, { 3, 1 }, { 4, 1 } }, + }, + { + "JGE (jt 0), test 2", + .u.insns = { + BPF_STMT(BPF_LDX | BPF_LEN, 0), + BPF_STMT(BPF_LD | BPF_B | BPF_ABS, 2), + BPF_JUMP(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 1), + BPF_STMT(BPF_RET | BPF_K, 1), + BPF_STMT(BPF_RET | BPF_K, MAX_K) + }, + CLASSIC, + { 4, 4, 5, 3, 3 }, + { { 4, 1 }, { 5, 1 }, { 6, MAX_K } }, + }, { "JGE", .u.insns = { @@ -4492,6 +4518,35 @@ static struct bpf_test tests[] = { { }, { { 0, 1 } }, }, + /* BPF_JMP | BPF_JSLT | BPF_K */ + { + "JMP_JSLT_K: Signed jump: if (-2 < -1) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 0xfffffffffffffffeLL), + BPF_JMP_IMM(BPF_JSLT, R1, -1, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "JMP_JSLT_K: Signed jump: if (-1 < -1) return 0", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_LD_IMM64(R1, 0xffffffffffffffffLL), + BPF_JMP_IMM(BPF_JSLT, R1, -1, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, /* BPF_JMP | BPF_JSGT | BPF_K */ { "JMP_JSGT_K: Signed jump: if (-1 > -2) return 1", @@ -4521,6 +4576,73 @@ static struct bpf_test tests[] = { { }, { { 0, 1 } }, }, + /* BPF_JMP | BPF_JSLE | BPF_K */ + { + "JMP_JSLE_K: Signed jump: if (-2 <= -1) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 0xfffffffffffffffeLL), + BPF_JMP_IMM(BPF_JSLE, R1, -1, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "JMP_JSLE_K: Signed jump: if (-1 <= -1) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 0xffffffffffffffffLL), + BPF_JMP_IMM(BPF_JSLE, R1, -1, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "JMP_JSLE_K: Signed jump: value walk 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 3), + BPF_JMP_IMM(BPF_JSLE, R1, 0, 6), + BPF_ALU64_IMM(BPF_SUB, R1, 1), + BPF_JMP_IMM(BPF_JSLE, R1, 0, 4), + BPF_ALU64_IMM(BPF_SUB, R1, 1), + BPF_JMP_IMM(BPF_JSLE, R1, 0, 2), + BPF_ALU64_IMM(BPF_SUB, R1, 1), + BPF_JMP_IMM(BPF_JSLE, R1, 0, 1), + BPF_EXIT_INSN(), /* bad exit */ + BPF_ALU32_IMM(BPF_MOV, R0, 1), /* good exit */ + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "JMP_JSLE_K: Signed jump: value walk 2", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 3), + BPF_JMP_IMM(BPF_JSLE, R1, 0, 4), + BPF_ALU64_IMM(BPF_SUB, R1, 2), + BPF_JMP_IMM(BPF_JSLE, R1, 0, 2), + BPF_ALU64_IMM(BPF_SUB, R1, 2), + BPF_JMP_IMM(BPF_JSLE, R1, 0, 1), + BPF_EXIT_INSN(), /* bad exit */ + BPF_ALU32_IMM(BPF_MOV, R0, 1), /* good exit */ + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, /* BPF_JMP | BPF_JSGE | BPF_K */ { "JMP_JSGE_K: Signed jump: if (-1 >= -2) return 1", @@ -4617,6 +4739,35 @@ static struct bpf_test tests[] = { { }, { { 0, 1 } }, }, + /* BPF_JMP | BPF_JLT | BPF_K */ + { + "JMP_JLT_K: if (2 < 3) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 2), + BPF_JMP_IMM(BPF_JLT, R1, 3, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "JMP_JGT_K: Unsigned jump: if (1 < -1) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 1), + BPF_JMP_IMM(BPF_JLT, R1, -1, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, /* BPF_JMP | BPF_JGE | BPF_K */ { "JMP_JGE_K: if (3 >= 2) return 1", @@ -4632,6 +4783,21 @@ static struct bpf_test tests[] = { { }, { { 0, 1 } }, }, + /* BPF_JMP | BPF_JLE | BPF_K */ + { + "JMP_JLE_K: if (2 <= 3) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 2), + BPF_JMP_IMM(BPF_JLE, R1, 3, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, /* BPF_JMP | BPF_JGT | BPF_K jump backwards */ { "JMP_JGT_K: if (3 > 2) return 1 (jump backwards)", @@ -4662,6 +4828,36 @@ static struct bpf_test tests[] = { { }, { { 0, 1 } }, }, + /* BPF_JMP | BPF_JLT | BPF_K jump backwards */ + { + "JMP_JGT_K: if (2 < 3) return 1 (jump backwards)", + .u.insns_int = { + BPF_JMP_IMM(BPF_JA, 0, 0, 2), /* goto start */ + BPF_ALU32_IMM(BPF_MOV, R0, 1), /* out: */ + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 0), /* start: */ + BPF_LD_IMM64(R1, 2), /* note: this takes 2 insns */ + BPF_JMP_IMM(BPF_JLT, R1, 3, -6), /* goto out */ + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "JMP_JLE_K: if (3 <= 3) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 3), + BPF_JMP_IMM(BPF_JLE, R1, 3, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, /* BPF_JMP | BPF_JNE | BPF_K */ { "JMP_JNE_K: if (3 != 2) return 1", @@ -4752,6 +4948,37 @@ static struct bpf_test tests[] = { { }, { { 0, 1 } }, }, + /* BPF_JMP | BPF_JSLT | BPF_X */ + { + "JMP_JSLT_X: Signed jump: if (-2 < -1) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, -1), + BPF_LD_IMM64(R2, -2), + BPF_JMP_REG(BPF_JSLT, R2, R1, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "JMP_JSLT_X: Signed jump: if (-1 < -1) return 0", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_LD_IMM64(R1, -1), + BPF_LD_IMM64(R2, -1), + BPF_JMP_REG(BPF_JSLT, R1, R2, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, /* BPF_JMP | BPF_JSGE | BPF_X */ { "JMP_JSGE_X: Signed jump: if (-1 >= -2) return 1", @@ -4783,6 +5010,37 @@ static struct bpf_test tests[] = { { }, { { 0, 1 } }, }, + /* BPF_JMP | BPF_JSLE | BPF_X */ + { + "JMP_JSLE_X: Signed jump: if (-2 <= -1) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, -1), + BPF_LD_IMM64(R2, -2), + BPF_JMP_REG(BPF_JSLE, R2, R1, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "JMP_JSLE_X: Signed jump: if (-1 <= -1) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, -1), + BPF_LD_IMM64(R2, -1), + BPF_JMP_REG(BPF_JSLE, R1, R2, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, /* BPF_JMP | BPF_JGT | BPF_X */ { "JMP_JGT_X: if (3 > 2) return 1", @@ -4814,6 +5072,37 @@ static struct bpf_test tests[] = { { }, { { 0, 1 } }, }, + /* BPF_JMP | BPF_JLT | BPF_X */ + { + "JMP_JLT_X: if (2 < 3) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 3), + BPF_LD_IMM64(R2, 2), + BPF_JMP_REG(BPF_JLT, R2, R1, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "JMP_JLT_X: Unsigned jump: if (1 < -1) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, -1), + BPF_LD_IMM64(R2, 1), + BPF_JMP_REG(BPF_JLT, R2, R1, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, /* BPF_JMP | BPF_JGE | BPF_X */ { "JMP_JGE_X: if (3 >= 2) return 1", @@ -4845,6 +5134,37 @@ static struct bpf_test tests[] = { { }, { { 0, 1 } }, }, + /* BPF_JMP | BPF_JLE | BPF_X */ + { + "JMP_JLE_X: if (2 <= 3) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 3), + BPF_LD_IMM64(R2, 2), + BPF_JMP_REG(BPF_JLE, R2, R1, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, + { + "JMP_JLE_X: if (3 <= 3) return 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 3), + BPF_LD_IMM64(R2, 3), + BPF_JMP_REG(BPF_JLE, R1, R2, 1), + BPF_EXIT_INSN(), + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, { /* Mainly testing JIT + imm64 here. */ "JMP_JGE_X: ldimm64 test 1", @@ -4890,6 +5210,50 @@ static struct bpf_test tests[] = { { }, { { 0, 1 } }, }, + { + "JMP_JLE_X: ldimm64 test 1", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 3), + BPF_LD_IMM64(R2, 2), + BPF_JMP_REG(BPF_JLE, R2, R1, 2), + BPF_LD_IMM64(R0, 0xffffffffffffffffULL), + BPF_LD_IMM64(R0, 0xeeeeeeeeeeeeeeeeULL), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xeeeeeeeeU } }, + }, + { + "JMP_JLE_X: ldimm64 test 2", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 0), + BPF_LD_IMM64(R1, 3), + BPF_LD_IMM64(R2, 2), + BPF_JMP_REG(BPF_JLE, R2, R1, 0), + BPF_LD_IMM64(R0, 0xffffffffffffffffULL), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 0xffffffffU } }, + }, + { + "JMP_JLE_X: ldimm64 test 3", + .u.insns_int = { + BPF_ALU32_IMM(BPF_MOV, R0, 1), + BPF_LD_IMM64(R1, 3), + BPF_LD_IMM64(R2, 2), + BPF_JMP_REG(BPF_JLE, R2, R1, 4), + BPF_LD_IMM64(R0, 0xffffffffffffffffULL), + BPF_LD_IMM64(R0, 0xeeeeeeeeeeeeeeeeULL), + BPF_EXIT_INSN(), + }, + INTERNAL, + { }, + { { 0, 1 } }, + }, /* BPF_JMP | BPF_JNE | BPF_X */ { "JMP_JNE_X: if (3 != 2) return 1", diff --git a/net/core/filter.c b/net/core/filter.c index 78d00933dbe7..5afe3ac191ec 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -514,14 +514,27 @@ do_pass: break; } - /* Convert JEQ into JNE when 'jump_true' is next insn. */ - if (fp->jt == 0 && BPF_OP(fp->code) == BPF_JEQ) { - insn->code = BPF_JMP | BPF_JNE | bpf_src; + /* Convert some jumps when 'jump_true' is next insn. */ + if (fp->jt == 0) { + switch (BPF_OP(fp->code)) { + case BPF_JEQ: + insn->code = BPF_JMP | BPF_JNE | bpf_src; + break; + case BPF_JGT: + insn->code = BPF_JMP | BPF_JLE | bpf_src; + break; + case BPF_JGE: + insn->code = BPF_JMP | BPF_JLT | bpf_src; + break; + default: + goto jmp_rest; + } + target = i + fp->jf + 1; BPF_EMIT_JMP; break; } - +jmp_rest: /* Other jumps are mapped into two insns: Jxx and JA. */ target = i + fp->jt + 1; insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 8d9bfcca3fe4..bf3b2e230455 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -30,9 +30,14 @@ #define BPF_FROM_LE BPF_TO_LE #define BPF_FROM_BE BPF_TO_BE +/* jmp encodings */ #define BPF_JNE 0x50 /* jump != */ +#define BPF_JLT 0xa0 /* LT is unsigned, '<' */ +#define BPF_JLE 0xb0 /* LE is unsigned, '<=' */ #define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */ #define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */ +#define BPF_JSLT 0xc0 /* SLT is signed, '<' */ +#define BPF_JSLE 0xd0 /* SLE is signed, '<=' */ #define BPF_CALL 0x80 /* function call */ #define BPF_EXIT 0x90 /* function return */ -- cgit v1.2.3-71-gd317 From 077fbac405bfc6d41419ad6c1725804ad4e9887c Mon Sep 17 00:00:00 2001 From: Lorenzo Colitti Date: Fri, 11 Aug 2017 02:11:33 +0900 Subject: net: xfrm: support setting an output mark. On systems that use mark-based routing it may be necessary for routing lookups to use marks in order for packets to be routed correctly. An example of such a system is Android, which uses socket marks to route packets via different networks. Currently, routing lookups in tunnel mode always use a mark of zero, making routing incorrect on such systems. This patch adds a new output_mark element to the xfrm state and a corresponding XFRMA_OUTPUT_MARK netlink attribute. The output mark differs from the existing xfrm mark in two ways: 1. The xfrm mark is used to match xfrm policies and states, while the xfrm output mark is used to set the mark (and influence the routing) of the packets emitted by those states. 2. The existing mark is constrained to be a subset of the bits of the originating socket or transformed packet, but the output mark is arbitrary and depends only on the state. The use of a separate mark provides additional flexibility. For example: - A packet subject to two transforms (e.g., transport mode inside tunnel mode) can have two different output marks applied to it, one for the transport mode SA and one for the tunnel mode SA. - On a system where socket marks determine routing, the packets emitted by an IPsec tunnel can be routed based on a mark that is determined by the tunnel, not by the marks of the unencrypted packets. - Support for setting the output marks can be introduced without breaking any existing setups that employ both mark-based routing and xfrm tunnel mode. Simply changing the code to use the xfrm mark for routing output packets could xfrm mark could change behaviour in a way that breaks these setups. If the output mark is unspecified or set to zero, the mark is not set or changed. Tested: make allyesconfig; make -j64 Tested: https://android-review.googlesource.com/452776 Signed-off-by: Lorenzo Colitti Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 9 ++++++--- include/uapi/linux/xfrm.h | 1 + net/ipv4/xfrm4_policy.c | 14 +++++++++----- net/ipv6/xfrm6_policy.c | 9 ++++++--- net/xfrm/xfrm_device.c | 3 ++- net/xfrm/xfrm_output.c | 3 +++ net/xfrm/xfrm_policy.c | 17 +++++++++-------- net/xfrm/xfrm_user.c | 11 +++++++++++ 8 files changed, 47 insertions(+), 20 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 18d7de34a5c3..9c7b70cce6d6 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -165,6 +165,7 @@ struct xfrm_state { int header_len; int trailer_len; u32 extra_flags; + u32 output_mark; } props; struct xfrm_lifetime_cfg lft; @@ -298,10 +299,12 @@ struct xfrm_policy_afinfo { struct dst_entry *(*dst_lookup)(struct net *net, int tos, int oif, const xfrm_address_t *saddr, - const xfrm_address_t *daddr); + const xfrm_address_t *daddr, + u32 mark); int (*get_saddr)(struct net *net, int oif, xfrm_address_t *saddr, - xfrm_address_t *daddr); + xfrm_address_t *daddr, + u32 mark); void (*decode_session)(struct sk_buff *skb, struct flowi *fl, int reverse); @@ -1640,7 +1643,7 @@ static inline int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb) struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif, const xfrm_address_t *saddr, const xfrm_address_t *daddr, - int family); + int family, u32 mark); struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp); diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index 2b384ff09fa0..5fe7370a2bef 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -304,6 +304,7 @@ enum xfrm_attr_type_t { XFRMA_ADDRESS_FILTER, /* struct xfrm_address_filter */ XFRMA_PAD, XFRMA_OFFLOAD_DEV, /* struct xfrm_state_offload */ + XFRMA_OUTPUT_MARK, /* __u32 */ __XFRMA_MAX #define XFRMA_MAX (__XFRMA_MAX - 1) diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 4aefb149fe0a..d7bf0b041885 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -20,7 +20,8 @@ static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4, int tos, int oif, const xfrm_address_t *saddr, - const xfrm_address_t *daddr) + const xfrm_address_t *daddr, + u32 mark) { struct rtable *rt; @@ -28,6 +29,7 @@ static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4, fl4->daddr = daddr->a4; fl4->flowi4_tos = tos; fl4->flowi4_oif = l3mdev_master_ifindex_by_index(net, oif); + fl4->flowi4_mark = mark; if (saddr) fl4->saddr = saddr->a4; @@ -42,20 +44,22 @@ static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4, static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos, int oif, const xfrm_address_t *saddr, - const xfrm_address_t *daddr) + const xfrm_address_t *daddr, + u32 mark) { struct flowi4 fl4; - return __xfrm4_dst_lookup(net, &fl4, tos, oif, saddr, daddr); + return __xfrm4_dst_lookup(net, &fl4, tos, oif, saddr, daddr, mark); } static int xfrm4_get_saddr(struct net *net, int oif, - xfrm_address_t *saddr, xfrm_address_t *daddr) + xfrm_address_t *saddr, xfrm_address_t *daddr, + u32 mark) { struct dst_entry *dst; struct flowi4 fl4; - dst = __xfrm4_dst_lookup(net, &fl4, 0, oif, NULL, daddr); + dst = __xfrm4_dst_lookup(net, &fl4, 0, oif, NULL, daddr, mark); if (IS_ERR(dst)) return -EHOSTUNREACH; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index f44b25a48478..11d1314ab6c5 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -27,7 +27,8 @@ static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif, const xfrm_address_t *saddr, - const xfrm_address_t *daddr) + const xfrm_address_t *daddr, + u32 mark) { struct flowi6 fl6; struct dst_entry *dst; @@ -36,6 +37,7 @@ static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif, memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_oif = l3mdev_master_ifindex_by_index(net, oif); fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF; + fl6.flowi6_mark = mark; memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr)); if (saddr) memcpy(&fl6.saddr, saddr, sizeof(fl6.saddr)); @@ -52,12 +54,13 @@ static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif, } static int xfrm6_get_saddr(struct net *net, int oif, - xfrm_address_t *saddr, xfrm_address_t *daddr) + xfrm_address_t *saddr, xfrm_address_t *daddr, + u32 mark) { struct dst_entry *dst; struct net_device *dev; - dst = xfrm6_dst_lookup(net, 0, oif, NULL, daddr); + dst = xfrm6_dst_lookup(net, 0, oif, NULL, daddr, mark); if (IS_ERR(dst)) return -EHOSTUNREACH; diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 1904127f5fb8..acf00104ef31 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -79,7 +79,8 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, daddr = &x->props.saddr; } - dst = __xfrm_dst_lookup(net, 0, 0, saddr, daddr, x->props.family); + dst = __xfrm_dst_lookup(net, 0, 0, saddr, daddr, + x->props.family, x->props.output_mark); if (IS_ERR(dst)) return 0; diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 8c0b6722aaa8..31a2e6d34dba 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -66,6 +66,9 @@ static int xfrm_output_one(struct sk_buff *skb, int err) goto error_nolock; } + if (x->props.output_mark) + skb->mark = x->props.output_mark; + err = x->outer_mode->output(x, skb); if (err) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 06c3bf7ab86b..1de52f36caf5 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -122,7 +122,7 @@ static const struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short fa struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif, const xfrm_address_t *saddr, const xfrm_address_t *daddr, - int family) + int family, u32 mark) { const struct xfrm_policy_afinfo *afinfo; struct dst_entry *dst; @@ -131,7 +131,7 @@ struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif, if (unlikely(afinfo == NULL)) return ERR_PTR(-EAFNOSUPPORT); - dst = afinfo->dst_lookup(net, tos, oif, saddr, daddr); + dst = afinfo->dst_lookup(net, tos, oif, saddr, daddr, mark); rcu_read_unlock(); @@ -143,7 +143,7 @@ static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x, int tos, int oif, xfrm_address_t *prev_saddr, xfrm_address_t *prev_daddr, - int family) + int family, u32 mark) { struct net *net = xs_net(x); xfrm_address_t *saddr = &x->props.saddr; @@ -159,7 +159,7 @@ static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x, daddr = x->coaddr; } - dst = __xfrm_dst_lookup(net, tos, oif, saddr, daddr, family); + dst = __xfrm_dst_lookup(net, tos, oif, saddr, daddr, family, mark); if (!IS_ERR(dst)) { if (prev_saddr != saddr) @@ -1340,14 +1340,14 @@ int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) static int xfrm_get_saddr(struct net *net, int oif, xfrm_address_t *local, - xfrm_address_t *remote, unsigned short family) + xfrm_address_t *remote, unsigned short family, u32 mark) { int err; const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); if (unlikely(afinfo == NULL)) return -EINVAL; - err = afinfo->get_saddr(net, oif, local, remote); + err = afinfo->get_saddr(net, oif, local, remote, mark); rcu_read_unlock(); return err; } @@ -1378,7 +1378,7 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl, if (xfrm_addr_any(local, tmpl->encap_family)) { error = xfrm_get_saddr(net, fl->flowi_oif, &tmp, remote, - tmpl->encap_family); + tmpl->encap_family, 0); if (error) goto fail; local = &tmp; @@ -1598,7 +1598,8 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) { family = xfrm[i]->props.family; dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif, - &saddr, &daddr, family); + &saddr, &daddr, family, + xfrm[i]->props.output_mark); err = PTR_ERR(dst); if (IS_ERR(dst)) goto put_states; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index ffe8d5ef09eb..cc3268d814b4 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -584,6 +584,9 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, xfrm_mark_get(attrs, &x->mark); + if (attrs[XFRMA_OUTPUT_MARK]) + x->props.output_mark = nla_get_u32(attrs[XFRMA_OUTPUT_MARK]); + err = __xfrm_init_state(x, false, attrs[XFRMA_OFFLOAD_DEV]); if (err) goto error; @@ -899,6 +902,11 @@ static int copy_to_user_state_extra(struct xfrm_state *x, goto out; if (x->security) ret = copy_sec_ctx(x->security, skb); + if (x->props.output_mark) { + ret = nla_put_u32(skb, XFRMA_OUTPUT_MARK, x->props.output_mark); + if (ret) + goto out; + } out: return ret; } @@ -2454,6 +2462,7 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_PROTO] = { .type = NLA_U8 }, [XFRMA_ADDRESS_FILTER] = { .len = sizeof(struct xfrm_address_filter) }, [XFRMA_OFFLOAD_DEV] = { .len = sizeof(struct xfrm_user_offload) }, + [XFRMA_OUTPUT_MARK] = { .len = NLA_U32 }, }; static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = { @@ -2673,6 +2682,8 @@ static inline size_t xfrm_sa_len(struct xfrm_state *x) l += nla_total_size(sizeof(x->props.extra_flags)); if (x->xso.dev) l += nla_total_size(sizeof(x->xso)); + if (x->props.output_mark) + l += nla_total_size(sizeof(x->props.output_mark)); /* Must count x->lastused as it may become non-zero behind our back. */ l += nla_total_size_64bit(sizeof(u64)); -- cgit v1.2.3-71-gd317 From 34fc75bfc616f1c1fbab56508c3f48f4b97c97ea Mon Sep 17 00:00:00 2001 From: Florian Weimer Date: Fri, 11 Aug 2017 16:24:15 +0200 Subject: uapi/linux/quota.h: Do not include linux/errno.h linux/errno.h is very sensitive to coordination with libc headers. Nothing in linux/quota.h needs it, so this change allows using this header in more contexts. Signed-off-by: Florian Weimer Signed-off-by: Jan Kara --- include/uapi/linux/quota.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/quota.h b/include/uapi/linux/quota.h index 4d2489ef6f10..f17c9636a859 100644 --- a/include/uapi/linux/quota.h +++ b/include/uapi/linux/quota.h @@ -33,7 +33,6 @@ #ifndef _UAPI_LINUX_QUOTA_ #define _UAPI_LINUX_QUOTA_ -#include #include #define __DQUOT_VERSION__ "dquot_6.6.0" -- cgit v1.2.3-71-gd317 From d612b1fd8010d0d67b5287fe146b8b55bcbb8655 Mon Sep 17 00:00:00 2001 From: Tyler Hicks Date: Fri, 11 Aug 2017 04:33:53 +0000 Subject: seccomp: Operation for checking if an action is available Userspace code that needs to check if the kernel supports a given action may not be able to use the /proc/sys/kernel/seccomp/actions_avail sysctl. The process may be running in a sandbox and, therefore, sufficient filesystem access may not be available. This patch adds an operation to the seccomp(2) syscall that allows userspace code to ask the kernel if a given action is available. If the action is supported by the kernel, 0 is returned. If the action is not supported by the kernel, -1 is returned with errno set to -EOPNOTSUPP. If this check is attempted on a kernel that doesn't support this new operation, -1 is returned with errno set to -EINVAL meaning that userspace code will have the ability to differentiate between the two error cases. Signed-off-by: Tyler Hicks Suggested-by: Andy Lutomirski Signed-off-by: Kees Cook --- include/uapi/linux/seccomp.h | 5 ++-- kernel/seccomp.c | 26 +++++++++++++++++++ tools/testing/selftests/seccomp/seccomp_bpf.c | 36 +++++++++++++++++++++++++++ 3 files changed, 65 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h index 0f238a43ff1e..aaad61cc46bc 100644 --- a/include/uapi/linux/seccomp.h +++ b/include/uapi/linux/seccomp.h @@ -11,8 +11,9 @@ #define SECCOMP_MODE_FILTER 2 /* uses user-supplied filter. */ /* Valid operations for seccomp syscall. */ -#define SECCOMP_SET_MODE_STRICT 0 -#define SECCOMP_SET_MODE_FILTER 1 +#define SECCOMP_SET_MODE_STRICT 0 +#define SECCOMP_SET_MODE_FILTER 1 +#define SECCOMP_GET_ACTION_AVAIL 2 /* Valid flags for SECCOMP_SET_MODE_FILTER */ #define SECCOMP_FILTER_FLAG_TSYNC 1 diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 5f19f41e4e50..7a6089f66fed 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -808,6 +808,27 @@ static inline long seccomp_set_mode_filter(unsigned int flags, } #endif +static long seccomp_get_action_avail(const char __user *uaction) +{ + u32 action; + + if (copy_from_user(&action, uaction, sizeof(action))) + return -EFAULT; + + switch (action) { + case SECCOMP_RET_KILL: + case SECCOMP_RET_TRAP: + case SECCOMP_RET_ERRNO: + case SECCOMP_RET_TRACE: + case SECCOMP_RET_ALLOW: + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + /* Common entry point for both prctl and syscall. */ static long do_seccomp(unsigned int op, unsigned int flags, const char __user *uargs) @@ -819,6 +840,11 @@ static long do_seccomp(unsigned int op, unsigned int flags, return seccomp_set_mode_strict(); case SECCOMP_SET_MODE_FILTER: return seccomp_set_mode_filter(flags, uargs); + case SECCOMP_GET_ACTION_AVAIL: + if (flags != 0) + return -EINVAL; + + return seccomp_get_action_avail(uargs); default: return -EINVAL; } diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 2fb49d99588d..1f2888f6678b 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -1731,6 +1731,10 @@ TEST_F_SIGNAL(TRACE_syscall, kill_after_ptrace, SIGSYS) #define SECCOMP_SET_MODE_FILTER 1 #endif +#ifndef SECCOMP_GET_ACTION_AVAIL +#define SECCOMP_GET_ACTION_AVAIL 2 +#endif + #ifndef SECCOMP_FILTER_FLAG_TSYNC #define SECCOMP_FILTER_FLAG_TSYNC 1 #endif @@ -2469,6 +2473,38 @@ TEST(syscall_restart) _metadata->passed = 0; } +TEST(get_action_avail) +{ + __u32 actions[] = { SECCOMP_RET_KILL, SECCOMP_RET_TRAP, + SECCOMP_RET_ERRNO, SECCOMP_RET_TRACE, + SECCOMP_RET_ALLOW }; + __u32 unknown_action = 0x10000000U; + int i; + long ret; + + ret = seccomp(SECCOMP_GET_ACTION_AVAIL, 0, &actions[0]); + ASSERT_NE(ENOSYS, errno) { + TH_LOG("Kernel does not support seccomp syscall!"); + } + ASSERT_NE(EINVAL, errno) { + TH_LOG("Kernel does not support SECCOMP_GET_ACTION_AVAIL operation!"); + } + EXPECT_EQ(ret, 0); + + for (i = 0; i < ARRAY_SIZE(actions); i++) { + ret = seccomp(SECCOMP_GET_ACTION_AVAIL, 0, &actions[i]); + EXPECT_EQ(ret, 0) { + TH_LOG("Expected action (0x%X) not available!", + actions[i]); + } + } + + /* Check that an unknown action is handled properly (EOPNOTSUPP) */ + ret = seccomp(SECCOMP_GET_ACTION_AVAIL, 0, &unknown_action); + EXPECT_EQ(ret, -1); + EXPECT_EQ(errno, EOPNOTSUPP); +} + /* * TODO: * - add microbenchmarks -- cgit v1.2.3-71-gd317 From e66a39977985b1e69e17c4042cb290768eca9b02 Mon Sep 17 00:00:00 2001 From: Tyler Hicks Date: Fri, 11 Aug 2017 04:33:56 +0000 Subject: seccomp: Filter flag to log all actions except SECCOMP_RET_ALLOW Add a new filter flag, SECCOMP_FILTER_FLAG_LOG, that enables logging for all actions except for SECCOMP_RET_ALLOW for the given filter. SECCOMP_RET_KILL actions are always logged, when "kill" is in the actions_logged sysctl, and SECCOMP_RET_ALLOW actions are never logged, regardless of this flag. This flag can be used to create noisy filters that result in all non-allowed actions to be logged. A process may have one noisy filter, which is loaded with this flag, as well as a quiet filter that's not loaded with this flag. This allows for the actions in a set of filters to be selectively conveyed to the admin. Since a system could have a large number of allocated seccomp_filter structs, struct packing was taken in consideration. On 64 bit x86, the new log member takes up one byte of an existing four byte hole in the struct. On 32 bit x86, the new log member creates a new four byte hole (unavoidable) and consumes one of those bytes. Unfortunately, the tests added for SECCOMP_FILTER_FLAG_LOG are not capable of inspecting the audit log to verify that the actions taken in the filter were logged. With this patch, the logic for deciding if an action will be logged is: if action == RET_ALLOW: do not log else if action == RET_KILL && RET_KILL in actions_logged: log else if filter-requests-logging && action in actions_logged: log else if audit_enabled && process-is-being-audited: log else: do not log Signed-off-by: Tyler Hicks Signed-off-by: Kees Cook --- include/linux/seccomp.h | 3 +- include/uapi/linux/seccomp.h | 1 + kernel/seccomp.c | 26 +++++++--- tools/testing/selftests/seccomp/seccomp_bpf.c | 69 ++++++++++++++++++++++++++- 4 files changed, 91 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index ecc296c137cd..c8bef436b61d 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -3,7 +3,8 @@ #include -#define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC) +#define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC | \ + SECCOMP_FILTER_FLAG_LOG) #ifdef CONFIG_SECCOMP diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h index aaad61cc46bc..19a611d0712e 100644 --- a/include/uapi/linux/seccomp.h +++ b/include/uapi/linux/seccomp.h @@ -17,6 +17,7 @@ /* Valid flags for SECCOMP_SET_MODE_FILTER */ #define SECCOMP_FILTER_FLAG_TSYNC 1 +#define SECCOMP_FILTER_FLAG_LOG 2 /* * All BPF programs must return a 32-bit value. diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 54357e361aea..ed9fde418fc4 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -44,6 +44,7 @@ * get/put helpers should be used when accessing an instance * outside of a lifetime-guarded section. In general, this * is only needed for handling filters shared across tasks. + * @log: true if all actions except for SECCOMP_RET_ALLOW should be logged * @prev: points to a previously installed, or inherited, filter * @prog: the BPF program to evaluate * @@ -59,6 +60,7 @@ */ struct seccomp_filter { refcount_t usage; + bool log; struct seccomp_filter *prev; struct bpf_prog *prog; }; @@ -452,6 +454,10 @@ static long seccomp_attach_filter(unsigned int flags, return ret; } + /* Set log flag, if present. */ + if (flags & SECCOMP_FILTER_FLAG_LOG) + filter->log = true; + /* * If there is an existing filter, make it the prev and don't drop its * task reference. @@ -532,15 +538,22 @@ static void seccomp_send_sigsys(int syscall, int reason) static u32 seccomp_actions_logged = SECCOMP_LOG_KILL | SECCOMP_LOG_TRAP | SECCOMP_LOG_ERRNO | SECCOMP_LOG_TRACE; -static inline void seccomp_log(unsigned long syscall, long signr, u32 action) +static inline void seccomp_log(unsigned long syscall, long signr, u32 action, + bool requested) { bool log = false; switch (action) { case SECCOMP_RET_ALLOW: + break; case SECCOMP_RET_TRAP: + log = requested && seccomp_actions_logged & SECCOMP_LOG_TRAP; + break; case SECCOMP_RET_ERRNO: + log = requested && seccomp_actions_logged & SECCOMP_LOG_ERRNO; + break; case SECCOMP_RET_TRACE: + log = requested && seccomp_actions_logged & SECCOMP_LOG_TRACE; break; case SECCOMP_RET_KILL: default: @@ -548,8 +561,9 @@ static inline void seccomp_log(unsigned long syscall, long signr, u32 action) } /* - * Force an audit message to be emitted when the action is RET_KILL and - * the action is allowed to be logged by the admin. + * Force an audit message to be emitted when the action is RET_KILL or + * the FILTER_FLAG_LOG bit was set and the action is allowed to be + * logged by the admin. */ if (log) return __audit_seccomp(syscall, signr, action); @@ -586,7 +600,7 @@ static void __secure_computing_strict(int this_syscall) #ifdef SECCOMP_DEBUG dump_stack(); #endif - seccomp_log(this_syscall, SIGKILL, SECCOMP_RET_KILL); + seccomp_log(this_syscall, SIGKILL, SECCOMP_RET_KILL, true); do_exit(SIGKILL); } @@ -695,7 +709,7 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, case SECCOMP_RET_KILL: default: - seccomp_log(this_syscall, SIGSYS, action); + seccomp_log(this_syscall, SIGSYS, action, true); /* Dump core only if this is the last remaining thread. */ if (get_nr_threads(current) == 1) { siginfo_t info; @@ -712,7 +726,7 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, unreachable(); skip: - seccomp_log(this_syscall, 0, action); + seccomp_log(this_syscall, 0, action, match ? match->log : false); return -1; } #else diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index abf708e09892..1c8c22ce7740 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -1739,6 +1739,10 @@ TEST_F_SIGNAL(TRACE_syscall, kill_after_ptrace, SIGSYS) #define SECCOMP_FILTER_FLAG_TSYNC 1 #endif +#ifndef SECCOMP_FILTER_FLAG_LOG +#define SECCOMP_FILTER_FLAG_LOG 2 +#endif + #ifndef seccomp int seccomp(unsigned int op, unsigned int flags, void *args) { @@ -1844,7 +1848,8 @@ TEST(seccomp_syscall_mode_lock) */ TEST(detect_seccomp_filter_flags) { - unsigned int flags[] = { SECCOMP_FILTER_FLAG_TSYNC }; + unsigned int flags[] = { SECCOMP_FILTER_FLAG_TSYNC, + SECCOMP_FILTER_FLAG_LOG }; unsigned int flag, all_flags; int i; long ret; @@ -2533,6 +2538,67 @@ TEST(syscall_restart) _metadata->passed = 0; } +TEST_SIGNAL(filter_flag_log, SIGSYS) +{ + struct sock_filter allow_filter[] = { + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_filter kill_filter[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 0, 1), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog allow_prog = { + .len = (unsigned short)ARRAY_SIZE(allow_filter), + .filter = allow_filter, + }; + struct sock_fprog kill_prog = { + .len = (unsigned short)ARRAY_SIZE(kill_filter), + .filter = kill_filter, + }; + long ret; + pid_t parent = getppid(); + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); + + /* Verify that the FILTER_FLAG_LOG flag isn't accepted in strict mode */ + ret = seccomp(SECCOMP_SET_MODE_STRICT, SECCOMP_FILTER_FLAG_LOG, + &allow_prog); + ASSERT_NE(ENOSYS, errno) { + TH_LOG("Kernel does not support seccomp syscall!"); + } + EXPECT_NE(0, ret) { + TH_LOG("Kernel accepted FILTER_FLAG_LOG flag in strict mode!"); + } + EXPECT_EQ(EINVAL, errno) { + TH_LOG("Kernel returned unexpected errno for FILTER_FLAG_LOG flag in strict mode!"); + } + + /* Verify that a simple, permissive filter can be added with no flags */ + ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &allow_prog); + EXPECT_EQ(0, ret); + + /* See if the same filter can be added with the FILTER_FLAG_LOG flag */ + ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_LOG, + &allow_prog); + ASSERT_NE(EINVAL, errno) { + TH_LOG("Kernel does not support the FILTER_FLAG_LOG flag!"); + } + EXPECT_EQ(0, ret); + + /* Ensure that the kill filter works with the FILTER_FLAG_LOG flag */ + ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_LOG, + &kill_prog); + EXPECT_EQ(0, ret); + + EXPECT_EQ(parent, syscall(__NR_getppid)); + /* getpid() should never return. */ + EXPECT_EQ(0, syscall(__NR_getpid)); +} + TEST(get_action_avail) { __u32 actions[] = { SECCOMP_RET_KILL, SECCOMP_RET_TRAP, @@ -2573,6 +2639,7 @@ TEST(get_action_avail) * - endianness checking when appropriate * - 64-bit arg prodding * - arch value testing (x86 modes especially) + * - verify that FILTER_FLAG_LOG filters generate log messages * - ... */ -- cgit v1.2.3-71-gd317 From 59f5cf44a38284eb9e76270c786fb6cc62ef8ac4 Mon Sep 17 00:00:00 2001 From: Tyler Hicks Date: Fri, 11 Aug 2017 04:33:57 +0000 Subject: seccomp: Action to log before allowing Add a new action, SECCOMP_RET_LOG, that logs a syscall before allowing the syscall. At the implementation level, this action is identical to the existing SECCOMP_RET_ALLOW action. However, it can be very useful when initially developing a seccomp filter for an application. The developer can set the default action to be SECCOMP_RET_LOG, maybe mark any obviously needed syscalls with SECCOMP_RET_ALLOW, and then put the application through its paces. A list of syscalls that triggered the default action (SECCOMP_RET_LOG) can be easily gleaned from the logs and that list can be used to build the syscall whitelist. Finally, the developer can change the default action to the desired value. This provides a more friendly experience than seeing the application get killed, then updating the filter and rebuilding the app, seeing the application get killed due to a different syscall, then updating the filter and rebuilding the app, etc. The functionality is similar to what's supported by the various LSMs. SELinux has permissive mode, AppArmor has complain mode, SMACK has bring-up mode, etc. SECCOMP_RET_LOG is given a lower value than SECCOMP_RET_ALLOW as allow while logging is slightly more restrictive than quietly allowing. Unfortunately, the tests added for SECCOMP_RET_LOG are not capable of inspecting the audit log to verify that the syscall was logged. With this patch, the logic for deciding if an action will be logged is: if action == RET_ALLOW: do not log else if action == RET_KILL && RET_KILL in actions_logged: log else if action == RET_LOG && RET_LOG in actions_logged: log else if filter-requests-logging && action in actions_logged: log else if audit_enabled && process-is-being-audited: log else: do not log Signed-off-by: Tyler Hicks Signed-off-by: Kees Cook --- Documentation/userspace-api/seccomp_filter.rst | 9 +++ include/uapi/linux/seccomp.h | 1 + kernel/seccomp.c | 23 ++++-- tools/testing/selftests/seccomp/seccomp_bpf.c | 98 +++++++++++++++++++++++++- 4 files changed, 125 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/seccomp_filter.rst b/Documentation/userspace-api/seccomp_filter.rst index 2d1d8ab04ac5..f4977357daf2 100644 --- a/Documentation/userspace-api/seccomp_filter.rst +++ b/Documentation/userspace-api/seccomp_filter.rst @@ -141,6 +141,15 @@ In precedence order, they are: allow use of ptrace, even of other sandboxed processes, without extreme care; ptracers can use this mechanism to escape.) +``SECCOMP_RET_LOG``: + Results in the system call being executed after it is logged. This + should be used by application developers to learn which syscalls their + application needs without having to iterate through multiple test and + development cycles to build the list. + + This action will only be logged if "log" is present in the + actions_logged sysctl string. + ``SECCOMP_RET_ALLOW``: Results in the system call being executed. diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h index 19a611d0712e..f94433263e4b 100644 --- a/include/uapi/linux/seccomp.h +++ b/include/uapi/linux/seccomp.h @@ -31,6 +31,7 @@ #define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */ #define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */ #define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */ +#define SECCOMP_RET_LOG 0x7ffc0000U /* allow after logging */ #define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */ /* Masks for the return value sections. */ diff --git a/kernel/seccomp.c b/kernel/seccomp.c index ed9fde418fc4..59cde2ed3b92 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -533,10 +533,12 @@ static void seccomp_send_sigsys(int syscall, int reason) #define SECCOMP_LOG_TRAP (1 << 2) #define SECCOMP_LOG_ERRNO (1 << 3) #define SECCOMP_LOG_TRACE (1 << 4) -#define SECCOMP_LOG_ALLOW (1 << 5) +#define SECCOMP_LOG_LOG (1 << 5) +#define SECCOMP_LOG_ALLOW (1 << 6) static u32 seccomp_actions_logged = SECCOMP_LOG_KILL | SECCOMP_LOG_TRAP | - SECCOMP_LOG_ERRNO | SECCOMP_LOG_TRACE; + SECCOMP_LOG_ERRNO | SECCOMP_LOG_TRACE | + SECCOMP_LOG_LOG; static inline void seccomp_log(unsigned long syscall, long signr, u32 action, bool requested) @@ -555,15 +557,18 @@ static inline void seccomp_log(unsigned long syscall, long signr, u32 action, case SECCOMP_RET_TRACE: log = requested && seccomp_actions_logged & SECCOMP_LOG_TRACE; break; + case SECCOMP_RET_LOG: + log = seccomp_actions_logged & SECCOMP_LOG_LOG; + break; case SECCOMP_RET_KILL: default: log = seccomp_actions_logged & SECCOMP_LOG_KILL; } /* - * Force an audit message to be emitted when the action is RET_KILL or - * the FILTER_FLAG_LOG bit was set and the action is allowed to be - * logged by the admin. + * Force an audit message to be emitted when the action is RET_KILL, + * RET_LOG, or the FILTER_FLAG_LOG bit was set and the action is + * allowed to be logged by the admin. */ if (log) return __audit_seccomp(syscall, signr, action); @@ -699,6 +704,10 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, return 0; + case SECCOMP_RET_LOG: + seccomp_log(this_syscall, 0, action, true); + return 0; + case SECCOMP_RET_ALLOW: /* * Note that the "match" filter will always be NULL for @@ -873,6 +882,7 @@ static long seccomp_get_action_avail(const char __user *uaction) case SECCOMP_RET_TRAP: case SECCOMP_RET_ERRNO: case SECCOMP_RET_TRACE: + case SECCOMP_RET_LOG: case SECCOMP_RET_ALLOW: break; default: @@ -1023,12 +1033,14 @@ out: #define SECCOMP_RET_TRAP_NAME "trap" #define SECCOMP_RET_ERRNO_NAME "errno" #define SECCOMP_RET_TRACE_NAME "trace" +#define SECCOMP_RET_LOG_NAME "log" #define SECCOMP_RET_ALLOW_NAME "allow" static const char seccomp_actions_avail[] = SECCOMP_RET_KILL_NAME " " SECCOMP_RET_TRAP_NAME " " SECCOMP_RET_ERRNO_NAME " " SECCOMP_RET_TRACE_NAME " " + SECCOMP_RET_LOG_NAME " " SECCOMP_RET_ALLOW_NAME; struct seccomp_log_name { @@ -1041,6 +1053,7 @@ static const struct seccomp_log_name seccomp_log_names[] = { { SECCOMP_LOG_TRAP, SECCOMP_RET_TRAP_NAME }, { SECCOMP_LOG_ERRNO, SECCOMP_RET_ERRNO_NAME }, { SECCOMP_LOG_TRACE, SECCOMP_RET_TRACE_NAME }, + { SECCOMP_LOG_LOG, SECCOMP_RET_LOG_NAME }, { SECCOMP_LOG_ALLOW, SECCOMP_RET_ALLOW_NAME }, { } }; diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 1c8c22ce7740..7372958eccb5 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -74,7 +74,12 @@ #define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */ #define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */ #define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */ +#endif +#ifndef SECCOMP_RET_LOG +#define SECCOMP_RET_LOG 0x7ffc0000U /* allow after logging */ +#endif +#ifndef SECCOMP_RET_ACTION /* Masks for the return value sections. */ #define SECCOMP_RET_ACTION 0x7fff0000U #define SECCOMP_RET_DATA 0x0000ffffU @@ -342,6 +347,28 @@ TEST(empty_prog) EXPECT_EQ(EINVAL, errno); } +TEST(log_all) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_LOG), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + long ret; + pid_t parent = getppid(); + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); + + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog); + ASSERT_EQ(0, ret); + + /* getppid() should succeed and be logged (no check for logging) */ + EXPECT_EQ(parent, syscall(__NR_getppid)); +} + TEST_SIGNAL(unknown_ret_is_kill_inside, SIGSYS) { struct sock_filter filter[] = { @@ -756,6 +783,7 @@ TEST_F(TRAP, handler) FIXTURE_DATA(precedence) { struct sock_fprog allow; + struct sock_fprog log; struct sock_fprog trace; struct sock_fprog error; struct sock_fprog trap; @@ -767,6 +795,13 @@ FIXTURE_SETUP(precedence) struct sock_filter allow_insns[] = { BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), }; + struct sock_filter log_insns[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 1, 0), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_LOG), + }; struct sock_filter trace_insns[] = { BPF_STMT(BPF_LD|BPF_W|BPF_ABS, offsetof(struct seccomp_data, nr)), @@ -803,6 +838,7 @@ FIXTURE_SETUP(precedence) memcpy(self->_x.filter, &_x##_insns, sizeof(_x##_insns)); \ self->_x.len = (unsigned short)ARRAY_SIZE(_x##_insns) FILTER_ALLOC(allow); + FILTER_ALLOC(log); FILTER_ALLOC(trace); FILTER_ALLOC(error); FILTER_ALLOC(trap); @@ -813,6 +849,7 @@ FIXTURE_TEARDOWN(precedence) { #define FILTER_FREE(_x) if (self->_x.filter) free(self->_x.filter) FILTER_FREE(allow); + FILTER_FREE(log); FILTER_FREE(trace); FILTER_FREE(error); FILTER_FREE(trap); @@ -830,6 +867,8 @@ TEST_F(precedence, allow_ok) ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace); ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error); @@ -854,6 +893,8 @@ TEST_F_SIGNAL(precedence, kill_is_highest, SIGSYS) ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace); ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error); @@ -885,6 +926,8 @@ TEST_F_SIGNAL(precedence, kill_is_highest_in_any_order, SIGSYS) ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace); ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trap); @@ -906,6 +949,8 @@ TEST_F_SIGNAL(precedence, trap_is_second, SIGSYS) ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace); ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error); @@ -931,6 +976,8 @@ TEST_F_SIGNAL(precedence, trap_is_second_in_any_order, SIGSYS) ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trap); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace); ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error); @@ -952,6 +999,8 @@ TEST_F(precedence, errno_is_third) ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace); ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error); @@ -970,6 +1019,8 @@ TEST_F(precedence, errno_is_third_in_any_order) ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error); ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace); @@ -992,6 +1043,8 @@ TEST_F(precedence, trace_is_fourth) ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace); ASSERT_EQ(0, ret); /* Should work just fine. */ @@ -1013,12 +1066,54 @@ TEST_F(precedence, trace_is_fourth_in_any_order) ASSERT_EQ(0, ret); ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow); ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); /* Should work just fine. */ EXPECT_EQ(parent, syscall(__NR_getppid)); /* No ptracer */ EXPECT_EQ(-1, syscall(__NR_getpid)); } +TEST_F(precedence, log_is_fifth) +{ + pid_t mypid, parent; + long ret; + + mypid = getpid(); + parent = getppid(); + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); + + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow); + ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); + /* Should work just fine. */ + EXPECT_EQ(parent, syscall(__NR_getppid)); + /* Should also work just fine */ + EXPECT_EQ(mypid, syscall(__NR_getpid)); +} + +TEST_F(precedence, log_is_fifth_in_any_order) +{ + pid_t mypid, parent; + long ret; + + mypid = getpid(); + parent = getppid(); + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); + + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log); + ASSERT_EQ(0, ret); + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow); + ASSERT_EQ(0, ret); + /* Should work just fine. */ + EXPECT_EQ(parent, syscall(__NR_getppid)); + /* Should also work just fine */ + EXPECT_EQ(mypid, syscall(__NR_getpid)); +} + #ifndef PTRACE_O_TRACESECCOMP #define PTRACE_O_TRACESECCOMP 0x00000080 #endif @@ -2603,7 +2698,7 @@ TEST(get_action_avail) { __u32 actions[] = { SECCOMP_RET_KILL, SECCOMP_RET_TRAP, SECCOMP_RET_ERRNO, SECCOMP_RET_TRACE, - SECCOMP_RET_ALLOW }; + SECCOMP_RET_LOG, SECCOMP_RET_ALLOW }; __u32 unknown_action = 0x10000000U; int i; long ret; @@ -2640,6 +2735,7 @@ TEST(get_action_avail) * - 64-bit arg prodding * - arch value testing (x86 modes especially) * - verify that FILTER_FLAG_LOG filters generate log messages + * - verify that RET_LOG generates log messages * - ... */ -- cgit v1.2.3-71-gd317 From fd76875ca289a3d4722f266fd2d5532a27083903 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 11 Aug 2017 12:53:18 -0700 Subject: seccomp: Rename SECCOMP_RET_KILL to SECCOMP_RET_KILL_THREAD In preparation for adding SECCOMP_RET_KILL_PROCESS, rename SECCOMP_RET_KILL to the more accurate SECCOMP_RET_KILL_THREAD. The existing selftest values are intentionally left as SECCOMP_RET_KILL just to be sure we're exercising the alias. Signed-off-by: Kees Cook --- Documentation/networking/filter.txt | 2 +- Documentation/userspace-api/seccomp_filter.rst | 4 +-- include/uapi/linux/seccomp.h | 3 +- kernel/seccomp.c | 39 ++++++++++++++------------ samples/seccomp/bpf-direct.c | 4 +-- samples/seccomp/bpf-helper.h | 2 +- tools/testing/selftests/seccomp/seccomp_bpf.c | 17 ++++++----- 7 files changed, 39 insertions(+), 32 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt index b69b205501de..73aa0f12156d 100644 --- a/Documentation/networking/filter.txt +++ b/Documentation/networking/filter.txt @@ -337,7 +337,7 @@ Examples for low-level BPF: jeq #14, good /* __NR_rt_sigprocmask */ jeq #13, good /* __NR_rt_sigaction */ jeq #35, good /* __NR_nanosleep */ - bad: ret #0 /* SECCOMP_RET_KILL */ + bad: ret #0 /* SECCOMP_RET_KILL_THREAD */ good: ret #0x7fff0000 /* SECCOMP_RET_ALLOW */ The above example code can be placed into a file (here called "foo"), and diff --git a/Documentation/userspace-api/seccomp_filter.rst b/Documentation/userspace-api/seccomp_filter.rst index f4977357daf2..d76396f2d8ed 100644 --- a/Documentation/userspace-api/seccomp_filter.rst +++ b/Documentation/userspace-api/seccomp_filter.rst @@ -87,11 +87,11 @@ Return values A seccomp filter may return any of the following values. If multiple filters exist, the return value for the evaluation of a given system call will always use the highest precedent value. (For example, -``SECCOMP_RET_KILL`` will always take precedence.) +``SECCOMP_RET_KILL_THREAD`` will always take precedence.) In precedence order, they are: -``SECCOMP_RET_KILL``: +``SECCOMP_RET_KILL_THREAD``: Results in the task exiting immediately without executing the system call. The exit status of the task (``status & 0x7f``) will be ``SIGSYS``, not ``SIGKILL``. diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h index f94433263e4b..5a03f699eb17 100644 --- a/include/uapi/linux/seccomp.h +++ b/include/uapi/linux/seccomp.h @@ -27,7 +27,8 @@ * The ordering ensures that a min_t() over composed return values always * selects the least permissive choice. */ -#define SECCOMP_RET_KILL 0x00000000U /* kill the task immediately */ +#define SECCOMP_RET_KILL_THREAD 0x00000000U /* kill the thread */ +#define SECCOMP_RET_KILL SECCOMP_RET_KILL_THREAD #define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */ #define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */ #define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */ diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 59cde2ed3b92..95ac54cff00f 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -192,7 +192,7 @@ static u32 seccomp_run_filters(const struct seccomp_data *sd, /* Ensure unexpected behavior doesn't result in failing open. */ if (unlikely(WARN_ON(f == NULL))) - return SECCOMP_RET_KILL; + return SECCOMP_RET_KILL_THREAD; if (!sd) { populate_seccomp_data(&sd_local); @@ -529,15 +529,17 @@ static void seccomp_send_sigsys(int syscall, int reason) #endif /* CONFIG_SECCOMP_FILTER */ /* For use with seccomp_actions_logged */ -#define SECCOMP_LOG_KILL (1 << 0) +#define SECCOMP_LOG_KILL_THREAD (1 << 0) #define SECCOMP_LOG_TRAP (1 << 2) #define SECCOMP_LOG_ERRNO (1 << 3) #define SECCOMP_LOG_TRACE (1 << 4) #define SECCOMP_LOG_LOG (1 << 5) #define SECCOMP_LOG_ALLOW (1 << 6) -static u32 seccomp_actions_logged = SECCOMP_LOG_KILL | SECCOMP_LOG_TRAP | - SECCOMP_LOG_ERRNO | SECCOMP_LOG_TRACE | +static u32 seccomp_actions_logged = SECCOMP_LOG_KILL_THREAD | + SECCOMP_LOG_TRAP | + SECCOMP_LOG_ERRNO | + SECCOMP_LOG_TRACE | SECCOMP_LOG_LOG; static inline void seccomp_log(unsigned long syscall, long signr, u32 action, @@ -560,13 +562,13 @@ static inline void seccomp_log(unsigned long syscall, long signr, u32 action, case SECCOMP_RET_LOG: log = seccomp_actions_logged & SECCOMP_LOG_LOG; break; - case SECCOMP_RET_KILL: + case SECCOMP_RET_KILL_THREAD: default: - log = seccomp_actions_logged & SECCOMP_LOG_KILL; + log = seccomp_actions_logged & SECCOMP_LOG_KILL_THREAD; } /* - * Force an audit message to be emitted when the action is RET_KILL, + * Force an audit message to be emitted when the action is RET_KILL_*, * RET_LOG, or the FILTER_FLAG_LOG bit was set and the action is * allowed to be logged by the admin. */ @@ -605,7 +607,7 @@ static void __secure_computing_strict(int this_syscall) #ifdef SECCOMP_DEBUG dump_stack(); #endif - seccomp_log(this_syscall, SIGKILL, SECCOMP_RET_KILL, true); + seccomp_log(this_syscall, SIGKILL, SECCOMP_RET_KILL_THREAD, true); do_exit(SIGKILL); } @@ -716,7 +718,7 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, */ return 0; - case SECCOMP_RET_KILL: + case SECCOMP_RET_KILL_THREAD: default: seccomp_log(this_syscall, SIGSYS, action, true); /* Dump core only if this is the last remaining thread. */ @@ -878,7 +880,7 @@ static long seccomp_get_action_avail(const char __user *uaction) return -EFAULT; switch (action) { - case SECCOMP_RET_KILL: + case SECCOMP_RET_KILL_THREAD: case SECCOMP_RET_TRAP: case SECCOMP_RET_ERRNO: case SECCOMP_RET_TRACE: @@ -1029,19 +1031,20 @@ out: #ifdef CONFIG_SYSCTL /* Human readable action names for friendly sysctl interaction */ -#define SECCOMP_RET_KILL_NAME "kill" +#define SECCOMP_RET_KILL_THREAD_NAME "kill_thread" #define SECCOMP_RET_TRAP_NAME "trap" #define SECCOMP_RET_ERRNO_NAME "errno" #define SECCOMP_RET_TRACE_NAME "trace" #define SECCOMP_RET_LOG_NAME "log" #define SECCOMP_RET_ALLOW_NAME "allow" -static const char seccomp_actions_avail[] = SECCOMP_RET_KILL_NAME " " - SECCOMP_RET_TRAP_NAME " " - SECCOMP_RET_ERRNO_NAME " " - SECCOMP_RET_TRACE_NAME " " - SECCOMP_RET_LOG_NAME " " - SECCOMP_RET_ALLOW_NAME; +static const char seccomp_actions_avail[] = + SECCOMP_RET_KILL_THREAD_NAME " " + SECCOMP_RET_TRAP_NAME " " + SECCOMP_RET_ERRNO_NAME " " + SECCOMP_RET_TRACE_NAME " " + SECCOMP_RET_LOG_NAME " " + SECCOMP_RET_ALLOW_NAME; struct seccomp_log_name { u32 log; @@ -1049,7 +1052,7 @@ struct seccomp_log_name { }; static const struct seccomp_log_name seccomp_log_names[] = { - { SECCOMP_LOG_KILL, SECCOMP_RET_KILL_NAME }, + { SECCOMP_LOG_KILL_THREAD, SECCOMP_RET_KILL_THREAD_NAME }, { SECCOMP_LOG_TRAP, SECCOMP_RET_TRAP_NAME }, { SECCOMP_LOG_ERRNO, SECCOMP_RET_ERRNO_NAME }, { SECCOMP_LOG_TRACE, SECCOMP_RET_TRACE_NAME }, diff --git a/samples/seccomp/bpf-direct.c b/samples/seccomp/bpf-direct.c index 151ec3f52189..235ce3c49ee9 100644 --- a/samples/seccomp/bpf-direct.c +++ b/samples/seccomp/bpf-direct.c @@ -129,7 +129,7 @@ static int install_filter(void) /* Check that read is only using stdin. */ BPF_STMT(BPF_LD+BPF_W+BPF_ABS, syscall_arg(0)), BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, STDIN_FILENO, 4, 0), - BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_KILL), + BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_KILL_THREAD), /* Check that write is only using stdout */ BPF_STMT(BPF_LD+BPF_W+BPF_ABS, syscall_arg(0)), @@ -139,7 +139,7 @@ static int install_filter(void) BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW), BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_TRAP), - BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_KILL), + BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_KILL_THREAD), }; struct sock_fprog prog = { .len = (unsigned short)(sizeof(filter)/sizeof(filter[0])), diff --git a/samples/seccomp/bpf-helper.h b/samples/seccomp/bpf-helper.h index 1d8de9edd858..83dbe79cbe2c 100644 --- a/samples/seccomp/bpf-helper.h +++ b/samples/seccomp/bpf-helper.h @@ -44,7 +44,7 @@ void seccomp_bpf_print(struct sock_filter *filter, size_t count); #define ALLOW \ BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW) #define DENY \ - BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_KILL) + BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_KILL_THREAD) #define JUMP(labels, label) \ BPF_JUMP(BPF_JMP+BPF_JA, FIND_LABEL((labels), (label)), \ JUMP_JT, JUMP_JF) diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 7372958eccb5..a3ba39a32449 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -68,15 +68,18 @@ #define SECCOMP_MODE_FILTER 2 #endif +#ifndef SECCOMP_RET_KILL_THREAD +#define SECCOMP_RET_KILL_THREAD 0x00000000U /* kill the thread */ +#endif #ifndef SECCOMP_RET_KILL -#define SECCOMP_RET_KILL 0x00000000U /* kill the task immediately */ -#define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */ -#define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */ -#define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */ -#define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */ +#define SECCOMP_RET_KILL SECCOMP_RET_KILL_THREAD +#define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */ +#define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */ +#define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */ +#define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */ #endif #ifndef SECCOMP_RET_LOG -#define SECCOMP_RET_LOG 0x7ffc0000U /* allow after logging */ +#define SECCOMP_RET_LOG 0x7ffc0000U /* allow after logging */ #endif #ifndef SECCOMP_RET_ACTION @@ -2696,7 +2699,7 @@ TEST_SIGNAL(filter_flag_log, SIGSYS) TEST(get_action_avail) { - __u32 actions[] = { SECCOMP_RET_KILL, SECCOMP_RET_TRAP, + __u32 actions[] = { SECCOMP_RET_KILL_THREAD, SECCOMP_RET_TRAP, SECCOMP_RET_ERRNO, SECCOMP_RET_TRACE, SECCOMP_RET_LOG, SECCOMP_RET_ALLOW }; __u32 unknown_action = 0x10000000U; -- cgit v1.2.3-71-gd317 From 4d3b0b05aae9ee9ce0970dc4cc0fb3fad5e85945 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 11 Aug 2017 13:01:39 -0700 Subject: seccomp: Introduce SECCOMP_RET_KILL_PROCESS This introduces the BPF return value for SECCOMP_RET_KILL_PROCESS to kill an entire process. This cannot yet be reached by seccomp, but it changes the default-kill behavior (for unknown return values) from kill-thread to kill-process. Signed-off-by: Kees Cook --- include/uapi/linux/seccomp.h | 18 ++++++++++-------- kernel/seccomp.c | 22 ++++++++++++++++------ 2 files changed, 26 insertions(+), 14 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h index 5a03f699eb17..7e77c92df78a 100644 --- a/include/uapi/linux/seccomp.h +++ b/include/uapi/linux/seccomp.h @@ -22,18 +22,20 @@ /* * All BPF programs must return a 32-bit value. * The bottom 16-bits are for optional return data. - * The upper 16-bits are ordered from least permissive values to most. + * The upper 16-bits are ordered from least permissive values to most, + * as a signed value (so 0x8000000 is negative). * * The ordering ensures that a min_t() over composed return values always * selects the least permissive choice. */ -#define SECCOMP_RET_KILL_THREAD 0x00000000U /* kill the thread */ -#define SECCOMP_RET_KILL SECCOMP_RET_KILL_THREAD -#define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */ -#define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */ -#define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */ -#define SECCOMP_RET_LOG 0x7ffc0000U /* allow after logging */ -#define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */ +#define SECCOMP_RET_KILL_PROCESS 0x80000000U /* kill the process */ +#define SECCOMP_RET_KILL_THREAD 0x00000000U /* kill the thread */ +#define SECCOMP_RET_KILL SECCOMP_RET_KILL_THREAD +#define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */ +#define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */ +#define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */ +#define SECCOMP_RET_LOG 0x7ffc0000U /* allow after logging */ +#define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */ /* Masks for the return value sections. */ #define SECCOMP_RET_ACTION 0x7fff0000U diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 95ac54cff00f..5c7299b9d953 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -192,7 +192,7 @@ static u32 seccomp_run_filters(const struct seccomp_data *sd, /* Ensure unexpected behavior doesn't result in failing open. */ if (unlikely(WARN_ON(f == NULL))) - return SECCOMP_RET_KILL_THREAD; + return SECCOMP_RET_KILL_PROCESS; if (!sd) { populate_seccomp_data(&sd_local); @@ -529,14 +529,16 @@ static void seccomp_send_sigsys(int syscall, int reason) #endif /* CONFIG_SECCOMP_FILTER */ /* For use with seccomp_actions_logged */ -#define SECCOMP_LOG_KILL_THREAD (1 << 0) +#define SECCOMP_LOG_KILL_PROCESS (1 << 0) +#define SECCOMP_LOG_KILL_THREAD (1 << 1) #define SECCOMP_LOG_TRAP (1 << 2) #define SECCOMP_LOG_ERRNO (1 << 3) #define SECCOMP_LOG_TRACE (1 << 4) #define SECCOMP_LOG_LOG (1 << 5) #define SECCOMP_LOG_ALLOW (1 << 6) -static u32 seccomp_actions_logged = SECCOMP_LOG_KILL_THREAD | +static u32 seccomp_actions_logged = SECCOMP_LOG_KILL_PROCESS | + SECCOMP_LOG_KILL_THREAD | SECCOMP_LOG_TRAP | SECCOMP_LOG_ERRNO | SECCOMP_LOG_TRACE | @@ -563,8 +565,11 @@ static inline void seccomp_log(unsigned long syscall, long signr, u32 action, log = seccomp_actions_logged & SECCOMP_LOG_LOG; break; case SECCOMP_RET_KILL_THREAD: - default: log = seccomp_actions_logged & SECCOMP_LOG_KILL_THREAD; + break; + case SECCOMP_RET_KILL_PROCESS: + default: + log = seccomp_actions_logged & SECCOMP_LOG_KILL_PROCESS; } /* @@ -719,10 +724,12 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, return 0; case SECCOMP_RET_KILL_THREAD: + case SECCOMP_RET_KILL_PROCESS: default: seccomp_log(this_syscall, SIGSYS, action, true); /* Dump core only if this is the last remaining thread. */ - if (get_nr_threads(current) == 1) { + if (action == SECCOMP_RET_KILL_PROCESS || + get_nr_threads(current) == 1) { siginfo_t info; /* Show the original registers in the dump. */ @@ -731,7 +738,10 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, seccomp_init_siginfo(&info, this_syscall, data); do_coredump(&info); } - do_exit(SIGSYS); + if (action == SECCOMP_RET_KILL_PROCESS) + do_group_exit(SIGSYS); + else + do_exit(SIGSYS); } unreachable(); -- cgit v1.2.3-71-gd317 From 0466bdb99e8744bc9befa8d62a317f0fd7fd7421 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 11 Aug 2017 13:12:11 -0700 Subject: seccomp: Implement SECCOMP_RET_KILL_PROCESS action MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Right now, SECCOMP_RET_KILL_THREAD (neé SECCOMP_RET_KILL) kills the current thread. There have been a few requests for this to kill the entire process (the thread group). This cannot be just changed (discovered when adding coredump support since coredumping kills the entire process) because there are userspace programs depending on the thread-kill behavior. Instead, implement SECCOMP_RET_KILL_PROCESS, which is 0x80000000, and can be processed as "-1" by the kernel, below the existing RET_KILL that is ABI-set to "0". For userspace, SECCOMP_RET_ACTION_FULL is added to expand the mask to the signed bit. Old userspace using the SECCOMP_RET_ACTION mask will see SECCOMP_RET_KILL_PROCESS as 0 still, but this would only be visible when examining the siginfo in a core dump from a RET_KILL_*, where it will think it was thread-killed instead of process-killed. Attempts to introduce this behavior via other ways (filter flags, seccomp struct flags, masked RET_DATA bits) all come with weird side-effects and baggage. This change preserves the central behavioral expectations of the seccomp filter engine without putting too great a burden on changes needed in userspace to use the new action. The new action is discoverable by userspace through either the new actions_avail sysctl or through the SECCOMP_GET_ACTION_AVAIL seccomp operation. If used without checking for availability, old kernels will treat RET_KILL_PROCESS as RET_KILL_THREAD (since the old mask will produce RET_KILL_THREAD). Cc: Paul Moore Cc: Fabricio Voznika Signed-off-by: Kees Cook --- Documentation/userspace-api/seccomp_filter.rst | 7 ++++++- include/uapi/linux/seccomp.h | 1 + kernel/seccomp.c | 9 +++++++-- 3 files changed, 14 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/seccomp_filter.rst b/Documentation/userspace-api/seccomp_filter.rst index d76396f2d8ed..099c412951d6 100644 --- a/Documentation/userspace-api/seccomp_filter.rst +++ b/Documentation/userspace-api/seccomp_filter.rst @@ -87,10 +87,15 @@ Return values A seccomp filter may return any of the following values. If multiple filters exist, the return value for the evaluation of a given system call will always use the highest precedent value. (For example, -``SECCOMP_RET_KILL_THREAD`` will always take precedence.) +``SECCOMP_RET_KILL_PROCESS`` will always take precedence.) In precedence order, they are: +``SECCOMP_RET_KILL_PROCESS``: + Results in the entire process exiting immediately without executing + the system call. The exit status of the task (``status & 0x7f``) + will be ``SIGSYS``, not ``SIGKILL``. + ``SECCOMP_RET_KILL_THREAD``: Results in the task exiting immediately without executing the system call. The exit status of the task (``status & 0x7f``) will diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h index 7e77c92df78a..f6bc1dea3247 100644 --- a/include/uapi/linux/seccomp.h +++ b/include/uapi/linux/seccomp.h @@ -38,6 +38,7 @@ #define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */ /* Masks for the return value sections. */ +#define SECCOMP_RET_ACTION_FULL 0xffff0000U #define SECCOMP_RET_ACTION 0x7fff0000U #define SECCOMP_RET_DATA 0x0000ffffU diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 5c7299b9d953..c24579dfa7a1 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -181,6 +181,7 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen) * * Returns valid seccomp BPF response codes. */ +#define ACTION_ONLY(ret) ((s32)((ret) & (SECCOMP_RET_ACTION_FULL))) static u32 seccomp_run_filters(const struct seccomp_data *sd, struct seccomp_filter **match) { @@ -206,7 +207,7 @@ static u32 seccomp_run_filters(const struct seccomp_data *sd, for (; f; f = f->prev) { u32 cur_ret = BPF_PROG_RUN(f->prog, sd); - if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION)) { + if (ACTION_ONLY(cur_ret) < ACTION_ONLY(ret)) { ret = cur_ret; *match = f; } @@ -650,7 +651,7 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, filter_ret = seccomp_run_filters(sd, &match); data = filter_ret & SECCOMP_RET_DATA; - action = filter_ret & SECCOMP_RET_ACTION; + action = filter_ret & SECCOMP_RET_ACTION_FULL; switch (action) { case SECCOMP_RET_ERRNO: @@ -890,6 +891,7 @@ static long seccomp_get_action_avail(const char __user *uaction) return -EFAULT; switch (action) { + case SECCOMP_RET_KILL_PROCESS: case SECCOMP_RET_KILL_THREAD: case SECCOMP_RET_TRAP: case SECCOMP_RET_ERRNO: @@ -1041,6 +1043,7 @@ out: #ifdef CONFIG_SYSCTL /* Human readable action names for friendly sysctl interaction */ +#define SECCOMP_RET_KILL_PROCESS_NAME "kill_process" #define SECCOMP_RET_KILL_THREAD_NAME "kill_thread" #define SECCOMP_RET_TRAP_NAME "trap" #define SECCOMP_RET_ERRNO_NAME "errno" @@ -1049,6 +1052,7 @@ out: #define SECCOMP_RET_ALLOW_NAME "allow" static const char seccomp_actions_avail[] = + SECCOMP_RET_KILL_PROCESS_NAME " " SECCOMP_RET_KILL_THREAD_NAME " " SECCOMP_RET_TRAP_NAME " " SECCOMP_RET_ERRNO_NAME " " @@ -1062,6 +1066,7 @@ struct seccomp_log_name { }; static const struct seccomp_log_name seccomp_log_names[] = { + { SECCOMP_LOG_KILL_PROCESS, SECCOMP_RET_KILL_PROCESS_NAME }, { SECCOMP_LOG_KILL_THREAD, SECCOMP_RET_KILL_THREAD_NAME }, { SECCOMP_LOG_TRAP, SECCOMP_RET_TRAP_NAME }, { SECCOMP_LOG_ERRNO, SECCOMP_RET_ERRNO_NAME }, -- cgit v1.2.3-71-gd317 From 44dd8a989c787e9077745417140aa132bfe45bf5 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Tue, 15 Aug 2017 19:07:53 +0800 Subject: include: uapi: usb: Introduce USB charger type and state definition Introducing USB charger type and state definition can help to support USB charging which will be added in USB phy core. Signed-off-by: Baolin Wang Signed-off-by: Felipe Balbi --- include/uapi/linux/usb/charger.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) create mode 100644 include/uapi/linux/usb/charger.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/usb/charger.h b/include/uapi/linux/usb/charger.h new file mode 100644 index 000000000000..5f72af35b3ed --- /dev/null +++ b/include/uapi/linux/usb/charger.h @@ -0,0 +1,31 @@ +/* + * This file defines the USB charger type and state that are needed for + * USB device APIs. + */ + +#ifndef _UAPI__LINUX_USB_CHARGER_H +#define _UAPI__LINUX_USB_CHARGER_H + +/* + * USB charger type: + * SDP (Standard Downstream Port) + * DCP (Dedicated Charging Port) + * CDP (Charging Downstream Port) + * ACA (Accessory Charger Adapters) + */ +enum usb_charger_type { + UNKNOWN_TYPE, + SDP_TYPE, + DCP_TYPE, + CDP_TYPE, + ACA_TYPE, +}; + +/* USB charger state */ +enum usb_charger_state { + USB_CHARGER_DEFAULT, + USB_CHARGER_PRESENT, + USB_CHARGER_ABSENT, +}; + +#endif /* _UAPI__LINUX_USB_CHARGER_H */ -- cgit v1.2.3-71-gd317 From 5c1aab1dd5445ed8bdcdbb575abc1b0d7ee5b2e7 Mon Sep 17 00:00:00 2001 From: Nick Terrell Date: Wed, 9 Aug 2017 19:39:02 -0700 Subject: btrfs: Add zstd support Add zstd compression and decompression support to BtrFS. zstd at its fastest level compresses almost as well as zlib, while offering much faster compression and decompression, approaching lzo speeds. I benchmarked btrfs with zstd compression against no compression, lzo compression, and zlib compression. I benchmarked two scenarios. Copying a set of files to btrfs, and then reading the files. Copying a tarball to btrfs, extracting it to btrfs, and then reading the extracted files. After every operation, I call `sync` and include the sync time. Between every pair of operations I unmount and remount the filesystem to avoid caching. The benchmark files can be found in the upstream zstd source repository under `contrib/linux-kernel/{btrfs-benchmark.sh,btrfs-extract-benchmark.sh}` [1] [2]. I ran the benchmarks on a Ubuntu 14.04 VM with 2 cores and 4 GiB of RAM. The VM is running on a MacBook Pro with a 3.1 GHz Intel Core i7 processor, 16 GB of RAM, and a SSD. The first compression benchmark is copying 10 copies of the unzipped Silesia corpus [3] into a BtrFS filesystem mounted with `-o compress-force=Method`. The decompression benchmark times how long it takes to `tar` all 10 copies into `/dev/null`. The compression ratio is measured by comparing the output of `df` and `du`. See the benchmark file [1] for details. I benchmarked multiple zstd compression levels, although the patch uses zstd level 1. | Method | Ratio | Compression MB/s | Decompression speed | |---------|-------|------------------|---------------------| | None | 0.99 | 504 | 686 | | lzo | 1.66 | 398 | 442 | | zlib | 2.58 | 65 | 241 | | zstd 1 | 2.57 | 260 | 383 | | zstd 3 | 2.71 | 174 | 408 | | zstd 6 | 2.87 | 70 | 398 | | zstd 9 | 2.92 | 43 | 406 | | zstd 12 | 2.93 | 21 | 408 | | zstd 15 | 3.01 | 11 | 354 | The next benchmark first copies `linux-4.11.6.tar` [4] to btrfs. Then it measures the compression ratio, extracts the tar, and deletes the tar. Then it measures the compression ratio again, and `tar`s the extracted files into `/dev/null`. See the benchmark file [2] for details. | Method | Tar Ratio | Extract Ratio | Copy (s) | Extract (s)| Read (s) | |--------|-----------|---------------|----------|------------|----------| | None | 0.97 | 0.78 | 0.981 | 5.501 | 8.807 | | lzo | 2.06 | 1.38 | 1.631 | 8.458 | 8.585 | | zlib | 3.40 | 1.86 | 7.750 | 21.544 | 11.744 | | zstd 1 | 3.57 | 1.85 | 2.579 | 11.479 | 9.389 | [1] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/btrfs-benchmark.sh [2] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/btrfs-extract-benchmark.sh [3] http://sun.aei.polsl.pl/~sdeor/index.php?page=silesia [4] https://cdn.kernel.org/pub/linux/kernel/v4.x/linux-4.11.6.tar.xz zstd source repository: https://github.com/facebook/zstd Signed-off-by: Nick Terrell Signed-off-by: Chris Mason --- fs/btrfs/Kconfig | 2 + fs/btrfs/Makefile | 2 +- fs/btrfs/compression.c | 1 + fs/btrfs/compression.h | 6 +- fs/btrfs/ctree.h | 1 + fs/btrfs/disk-io.c | 2 + fs/btrfs/ioctl.c | 6 +- fs/btrfs/props.c | 6 + fs/btrfs/super.c | 12 +- fs/btrfs/sysfs.c | 2 + fs/btrfs/zstd.c | 432 +++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/btrfs.h | 8 +- 12 files changed, 468 insertions(+), 12 deletions(-) create mode 100644 fs/btrfs/zstd.c (limited to 'include/uapi/linux') diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig index 80e9c18ea64f..a26c63b4ad68 100644 --- a/fs/btrfs/Kconfig +++ b/fs/btrfs/Kconfig @@ -6,6 +6,8 @@ config BTRFS_FS select ZLIB_DEFLATE select LZO_COMPRESS select LZO_DECOMPRESS + select ZSTD_COMPRESS + select ZSTD_DECOMPRESS select RAID6_PQ select XOR_BLOCKS select SRCU diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile index 128ce17a80b0..962a95aefb81 100644 --- a/fs/btrfs/Makefile +++ b/fs/btrfs/Makefile @@ -6,7 +6,7 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \ transaction.o inode.o file.o tree-defrag.o \ extent_map.o sysfs.o struct-funcs.o xattr.o ordered-data.o \ extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \ - export.o tree-log.o free-space-cache.o zlib.o lzo.o \ + export.o tree-log.o free-space-cache.o zlib.o lzo.o zstd.o \ compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \ reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \ uuid-tree.o props.o hash.o free-space-tree.o diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index d2ef9ac2a630..4ff42d18a64d 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -704,6 +704,7 @@ static struct { static const struct btrfs_compress_op * const btrfs_compress_op[] = { &btrfs_zlib_compress, &btrfs_lzo_compress, + &btrfs_zstd_compress, }; void __init btrfs_init_compress(void) diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h index 87f6d3332163..2269e00854d8 100644 --- a/fs/btrfs/compression.h +++ b/fs/btrfs/compression.h @@ -99,8 +99,9 @@ enum btrfs_compression_type { BTRFS_COMPRESS_NONE = 0, BTRFS_COMPRESS_ZLIB = 1, BTRFS_COMPRESS_LZO = 2, - BTRFS_COMPRESS_TYPES = 2, - BTRFS_COMPRESS_LAST = 3, + BTRFS_COMPRESS_ZSTD = 3, + BTRFS_COMPRESS_TYPES = 3, + BTRFS_COMPRESS_LAST = 4, }; struct btrfs_compress_op { @@ -128,5 +129,6 @@ struct btrfs_compress_op { extern const struct btrfs_compress_op btrfs_zlib_compress; extern const struct btrfs_compress_op btrfs_lzo_compress; +extern const struct btrfs_compress_op btrfs_zstd_compress; #endif diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 3f3eb7b17cac..845d77c097d6 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -270,6 +270,7 @@ struct btrfs_super_block { BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS | \ BTRFS_FEATURE_INCOMPAT_BIG_METADATA | \ BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO | \ + BTRFS_FEATURE_INCOMPAT_COMPRESS_ZSTD | \ BTRFS_FEATURE_INCOMPAT_RAID56 | \ BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF | \ BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA | \ diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 080e2ebb8aa0..04632f4de933 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2828,6 +2828,8 @@ int open_ctree(struct super_block *sb, features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF; if (fs_info->compress_type == BTRFS_COMPRESS_LZO) features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO; + else if (fs_info->compress_type == BTRFS_COMPRESS_ZSTD) + features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_ZSTD; if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA) btrfs_info(fs_info, "has skinny extents"); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index fa1b78cf25f6..b9963d94d727 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -327,8 +327,10 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) if (fs_info->compress_type == BTRFS_COMPRESS_LZO) comp = "lzo"; - else + else if (fs_info->compress_type == BTRFS_COMPRESS_ZLIB) comp = "zlib"; + else + comp = "zstd"; ret = btrfs_set_prop(inode, "btrfs.compression", comp, strlen(comp), 0); if (ret) @@ -1466,6 +1468,8 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, if (range->compress_type == BTRFS_COMPRESS_LZO) { btrfs_set_fs_incompat(fs_info, COMPRESS_LZO); + } else if (range->compress_type == BTRFS_COMPRESS_ZSTD) { + btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD); } ret = defrag_count; diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c index 4b23ae5d0e5c..20631e9273a0 100644 --- a/fs/btrfs/props.c +++ b/fs/btrfs/props.c @@ -390,6 +390,8 @@ static int prop_compression_validate(const char *value, size_t len) return 0; else if (!strncmp("zlib", value, len)) return 0; + else if (!strncmp("zstd", value, len)) + return 0; return -EINVAL; } @@ -412,6 +414,8 @@ static int prop_compression_apply(struct inode *inode, type = BTRFS_COMPRESS_LZO; else if (!strncmp("zlib", value, len)) type = BTRFS_COMPRESS_ZLIB; + else if (!strncmp("zstd", value, len)) + type = BTRFS_COMPRESS_ZSTD; else return -EINVAL; @@ -429,6 +433,8 @@ static const char *prop_compression_extract(struct inode *inode) return "zlib"; case BTRFS_COMPRESS_LZO: return "lzo"; + case BTRFS_COMPRESS_ZSTD: + return "zstd"; } return NULL; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 12540b6104b5..c370deadb790 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -513,6 +513,14 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, btrfs_clear_opt(info->mount_opt, NODATASUM); btrfs_set_fs_incompat(info, COMPRESS_LZO); no_compress = 0; + } else if (strcmp(args[0].from, "zstd") == 0) { + compress_type = "zstd"; + info->compress_type = BTRFS_COMPRESS_ZSTD; + btrfs_set_opt(info->mount_opt, COMPRESS); + btrfs_clear_opt(info->mount_opt, NODATACOW); + btrfs_clear_opt(info->mount_opt, NODATASUM); + btrfs_set_fs_incompat(info, COMPRESS_ZSTD); + no_compress = 0; } else if (strncmp(args[0].from, "no", 2) == 0) { compress_type = "no"; btrfs_clear_opt(info->mount_opt, COMPRESS); @@ -1227,8 +1235,10 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) if (btrfs_test_opt(info, COMPRESS)) { if (info->compress_type == BTRFS_COMPRESS_ZLIB) compress_type = "zlib"; - else + else if (info->compress_type == BTRFS_COMPRESS_LZO) compress_type = "lzo"; + else + compress_type = "zstd"; if (btrfs_test_opt(info, FORCE_COMPRESS)) seq_printf(seq, ",compress-force=%s", compress_type); else diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index c2d5f3580b4c..2b6d37c09a81 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -200,6 +200,7 @@ BTRFS_FEAT_ATTR_INCOMPAT(mixed_backref, MIXED_BACKREF); BTRFS_FEAT_ATTR_INCOMPAT(default_subvol, DEFAULT_SUBVOL); BTRFS_FEAT_ATTR_INCOMPAT(mixed_groups, MIXED_GROUPS); BTRFS_FEAT_ATTR_INCOMPAT(compress_lzo, COMPRESS_LZO); +BTRFS_FEAT_ATTR_INCOMPAT(compress_zstd, COMPRESS_ZSTD); BTRFS_FEAT_ATTR_INCOMPAT(big_metadata, BIG_METADATA); BTRFS_FEAT_ATTR_INCOMPAT(extended_iref, EXTENDED_IREF); BTRFS_FEAT_ATTR_INCOMPAT(raid56, RAID56); @@ -212,6 +213,7 @@ static struct attribute *btrfs_supported_feature_attrs[] = { BTRFS_FEAT_ATTR_PTR(default_subvol), BTRFS_FEAT_ATTR_PTR(mixed_groups), BTRFS_FEAT_ATTR_PTR(compress_lzo), + BTRFS_FEAT_ATTR_PTR(compress_zstd), BTRFS_FEAT_ATTR_PTR(big_metadata), BTRFS_FEAT_ATTR_PTR(extended_iref), BTRFS_FEAT_ATTR_PTR(raid56), diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c new file mode 100644 index 000000000000..607ce47b483a --- /dev/null +++ b/fs/btrfs/zstd.c @@ -0,0 +1,432 @@ +/* + * Copyright (c) 2016-present, Facebook, Inc. + * All rights reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public + * License v2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "compression.h" + +#define ZSTD_BTRFS_MAX_WINDOWLOG 17 +#define ZSTD_BTRFS_MAX_INPUT (1 << ZSTD_BTRFS_MAX_WINDOWLOG) +#define ZSTD_BTRFS_DEFAULT_LEVEL 3 + +static ZSTD_parameters zstd_get_btrfs_parameters(size_t src_len) +{ + ZSTD_parameters params = ZSTD_getParams(ZSTD_BTRFS_DEFAULT_LEVEL, + src_len, 0); + + if (params.cParams.windowLog > ZSTD_BTRFS_MAX_WINDOWLOG) + params.cParams.windowLog = ZSTD_BTRFS_MAX_WINDOWLOG; + WARN_ON(src_len > ZSTD_BTRFS_MAX_INPUT); + return params; +} + +struct workspace { + void *mem; + size_t size; + char *buf; + struct list_head list; +}; + +static void zstd_free_workspace(struct list_head *ws) +{ + struct workspace *workspace = list_entry(ws, struct workspace, list); + + kvfree(workspace->mem); + kfree(workspace->buf); + kfree(workspace); +} + +static struct list_head *zstd_alloc_workspace(void) +{ + ZSTD_parameters params = + zstd_get_btrfs_parameters(ZSTD_BTRFS_MAX_INPUT); + struct workspace *workspace; + + workspace = kzalloc(sizeof(*workspace), GFP_KERNEL); + if (!workspace) + return ERR_PTR(-ENOMEM); + + workspace->size = max_t(size_t, + ZSTD_CStreamWorkspaceBound(params.cParams), + ZSTD_DStreamWorkspaceBound(ZSTD_BTRFS_MAX_INPUT)); + workspace->mem = kvmalloc(workspace->size, GFP_KERNEL); + workspace->buf = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!workspace->mem || !workspace->buf) + goto fail; + + INIT_LIST_HEAD(&workspace->list); + + return &workspace->list; +fail: + zstd_free_workspace(&workspace->list); + return ERR_PTR(-ENOMEM); +} + +static int zstd_compress_pages(struct list_head *ws, + struct address_space *mapping, + u64 start, + struct page **pages, + unsigned long *out_pages, + unsigned long *total_in, + unsigned long *total_out) +{ + struct workspace *workspace = list_entry(ws, struct workspace, list); + ZSTD_CStream *stream; + int ret = 0; + int nr_pages = 0; + struct page *in_page = NULL; /* The current page to read */ + struct page *out_page = NULL; /* The current page to write to */ + ZSTD_inBuffer in_buf = { NULL, 0, 0 }; + ZSTD_outBuffer out_buf = { NULL, 0, 0 }; + unsigned long tot_in = 0; + unsigned long tot_out = 0; + unsigned long len = *total_out; + const unsigned long nr_dest_pages = *out_pages; + unsigned long max_out = nr_dest_pages * PAGE_SIZE; + ZSTD_parameters params = zstd_get_btrfs_parameters(len); + + *out_pages = 0; + *total_out = 0; + *total_in = 0; + + /* Initialize the stream */ + stream = ZSTD_initCStream(params, len, workspace->mem, + workspace->size); + if (!stream) { + pr_warn("BTRFS: ZSTD_initCStream failed\n"); + ret = -EIO; + goto out; + } + + /* map in the first page of input data */ + in_page = find_get_page(mapping, start >> PAGE_SHIFT); + in_buf.src = kmap(in_page); + in_buf.pos = 0; + in_buf.size = min_t(size_t, len, PAGE_SIZE); + + + /* Allocate and map in the output buffer */ + out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM); + if (out_page == NULL) { + ret = -ENOMEM; + goto out; + } + pages[nr_pages++] = out_page; + out_buf.dst = kmap(out_page); + out_buf.pos = 0; + out_buf.size = min_t(size_t, max_out, PAGE_SIZE); + + while (1) { + size_t ret2; + + ret2 = ZSTD_compressStream(stream, &out_buf, &in_buf); + if (ZSTD_isError(ret2)) { + pr_debug("BTRFS: ZSTD_compressStream returned %d\n", + ZSTD_getErrorCode(ret2)); + ret = -EIO; + goto out; + } + + /* Check to see if we are making it bigger */ + if (tot_in + in_buf.pos > 8192 && + tot_in + in_buf.pos < + tot_out + out_buf.pos) { + ret = -E2BIG; + goto out; + } + + /* We've reached the end of our output range */ + if (out_buf.pos >= max_out) { + tot_out += out_buf.pos; + ret = -E2BIG; + goto out; + } + + /* Check if we need more output space */ + if (out_buf.pos == out_buf.size) { + tot_out += PAGE_SIZE; + max_out -= PAGE_SIZE; + kunmap(out_page); + if (nr_pages == nr_dest_pages) { + out_page = NULL; + ret = -E2BIG; + goto out; + } + out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM); + if (out_page == NULL) { + ret = -ENOMEM; + goto out; + } + pages[nr_pages++] = out_page; + out_buf.dst = kmap(out_page); + out_buf.pos = 0; + out_buf.size = min_t(size_t, max_out, PAGE_SIZE); + } + + /* We've reached the end of the input */ + if (in_buf.pos >= len) { + tot_in += in_buf.pos; + break; + } + + /* Check if we need more input */ + if (in_buf.pos == in_buf.size) { + tot_in += PAGE_SIZE; + kunmap(in_page); + put_page(in_page); + + start += PAGE_SIZE; + len -= PAGE_SIZE; + in_page = find_get_page(mapping, start >> PAGE_SHIFT); + in_buf.src = kmap(in_page); + in_buf.pos = 0; + in_buf.size = min_t(size_t, len, PAGE_SIZE); + } + } + while (1) { + size_t ret2; + + ret2 = ZSTD_endStream(stream, &out_buf); + if (ZSTD_isError(ret2)) { + pr_debug("BTRFS: ZSTD_endStream returned %d\n", + ZSTD_getErrorCode(ret2)); + ret = -EIO; + goto out; + } + if (ret2 == 0) { + tot_out += out_buf.pos; + break; + } + if (out_buf.pos >= max_out) { + tot_out += out_buf.pos; + ret = -E2BIG; + goto out; + } + + tot_out += PAGE_SIZE; + max_out -= PAGE_SIZE; + kunmap(out_page); + if (nr_pages == nr_dest_pages) { + out_page = NULL; + ret = -E2BIG; + goto out; + } + out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM); + if (out_page == NULL) { + ret = -ENOMEM; + goto out; + } + pages[nr_pages++] = out_page; + out_buf.dst = kmap(out_page); + out_buf.pos = 0; + out_buf.size = min_t(size_t, max_out, PAGE_SIZE); + } + + if (tot_out >= tot_in) { + ret = -E2BIG; + goto out; + } + + ret = 0; + *total_in = tot_in; + *total_out = tot_out; +out: + *out_pages = nr_pages; + /* Cleanup */ + if (in_page) { + kunmap(in_page); + put_page(in_page); + } + if (out_page) + kunmap(out_page); + return ret; +} + +static int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb) +{ + struct workspace *workspace = list_entry(ws, struct workspace, list); + struct page **pages_in = cb->compressed_pages; + u64 disk_start = cb->start; + struct bio *orig_bio = cb->orig_bio; + size_t srclen = cb->compressed_len; + ZSTD_DStream *stream; + int ret = 0; + unsigned long page_in_index = 0; + unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_SIZE); + unsigned long buf_start; + unsigned long total_out = 0; + ZSTD_inBuffer in_buf = { NULL, 0, 0 }; + ZSTD_outBuffer out_buf = { NULL, 0, 0 }; + + stream = ZSTD_initDStream( + ZSTD_BTRFS_MAX_INPUT, workspace->mem, workspace->size); + if (!stream) { + pr_debug("BTRFS: ZSTD_initDStream failed\n"); + ret = -EIO; + goto done; + } + + in_buf.src = kmap(pages_in[page_in_index]); + in_buf.pos = 0; + in_buf.size = min_t(size_t, srclen, PAGE_SIZE); + + out_buf.dst = workspace->buf; + out_buf.pos = 0; + out_buf.size = PAGE_SIZE; + + while (1) { + size_t ret2; + + ret2 = ZSTD_decompressStream(stream, &out_buf, &in_buf); + if (ZSTD_isError(ret2)) { + pr_debug("BTRFS: ZSTD_decompressStream returned %d\n", + ZSTD_getErrorCode(ret2)); + ret = -EIO; + goto done; + } + buf_start = total_out; + total_out += out_buf.pos; + out_buf.pos = 0; + + ret = btrfs_decompress_buf2page(out_buf.dst, buf_start, + total_out, disk_start, orig_bio); + if (ret == 0) + break; + + if (in_buf.pos >= srclen) + break; + + /* Check if we've hit the end of a frame */ + if (ret2 == 0) + break; + + if (in_buf.pos == in_buf.size) { + kunmap(pages_in[page_in_index++]); + if (page_in_index >= total_pages_in) { + in_buf.src = NULL; + ret = -EIO; + goto done; + } + srclen -= PAGE_SIZE; + in_buf.src = kmap(pages_in[page_in_index]); + in_buf.pos = 0; + in_buf.size = min_t(size_t, srclen, PAGE_SIZE); + } + } + ret = 0; + zero_fill_bio(orig_bio); +done: + if (in_buf.src) + kunmap(pages_in[page_in_index]); + return ret; +} + +static int zstd_decompress(struct list_head *ws, unsigned char *data_in, + struct page *dest_page, + unsigned long start_byte, + size_t srclen, size_t destlen) +{ + struct workspace *workspace = list_entry(ws, struct workspace, list); + ZSTD_DStream *stream; + int ret = 0; + size_t ret2; + ZSTD_inBuffer in_buf = { NULL, 0, 0 }; + ZSTD_outBuffer out_buf = { NULL, 0, 0 }; + unsigned long total_out = 0; + unsigned long pg_offset = 0; + char *kaddr; + + stream = ZSTD_initDStream( + ZSTD_BTRFS_MAX_INPUT, workspace->mem, workspace->size); + if (!stream) { + pr_warn("BTRFS: ZSTD_initDStream failed\n"); + ret = -EIO; + goto finish; + } + + destlen = min_t(size_t, destlen, PAGE_SIZE); + + in_buf.src = data_in; + in_buf.pos = 0; + in_buf.size = srclen; + + out_buf.dst = workspace->buf; + out_buf.pos = 0; + out_buf.size = PAGE_SIZE; + + ret2 = 1; + while (pg_offset < destlen && in_buf.pos < in_buf.size) { + unsigned long buf_start; + unsigned long buf_offset; + unsigned long bytes; + + /* Check if the frame is over and we still need more input */ + if (ret2 == 0) { + pr_debug("BTRFS: ZSTD_decompressStream ended early\n"); + ret = -EIO; + goto finish; + } + ret2 = ZSTD_decompressStream(stream, &out_buf, &in_buf); + if (ZSTD_isError(ret2)) { + pr_debug("BTRFS: ZSTD_decompressStream returned %d\n", + ZSTD_getErrorCode(ret2)); + ret = -EIO; + goto finish; + } + + buf_start = total_out; + total_out += out_buf.pos; + out_buf.pos = 0; + + if (total_out <= start_byte) + continue; + + if (total_out > start_byte && buf_start < start_byte) + buf_offset = start_byte - buf_start; + else + buf_offset = 0; + + bytes = min_t(unsigned long, destlen - pg_offset, + out_buf.size - buf_offset); + + kaddr = kmap_atomic(dest_page); + memcpy(kaddr + pg_offset, out_buf.dst + buf_offset, bytes); + kunmap_atomic(kaddr); + + pg_offset += bytes; + } + ret = 0; +finish: + if (pg_offset < destlen) { + kaddr = kmap_atomic(dest_page); + memset(kaddr + pg_offset, 0, destlen - pg_offset); + kunmap_atomic(kaddr); + } + return ret; +} + +const struct btrfs_compress_op btrfs_zstd_compress = { + .alloc_workspace = zstd_alloc_workspace, + .free_workspace = zstd_free_workspace, + .compress_pages = zstd_compress_pages, + .decompress_bio = zstd_decompress_bio, + .decompress = zstd_decompress, +}; diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 9aa74f317747..378230c163d5 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -255,13 +255,7 @@ struct btrfs_ioctl_fs_info_args { #define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL (1ULL << 1) #define BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS (1ULL << 2) #define BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO (1ULL << 3) -/* - * some patches floated around with a second compression method - * lets save that incompat here for when they do get in - * Note we don't actually support it, we're just reserving the - * number - */ -#define BTRFS_FEATURE_INCOMPAT_COMPRESS_LZOv2 (1ULL << 4) +#define BTRFS_FEATURE_INCOMPAT_COMPRESS_ZSTD (1ULL << 4) /* * older kernels tried to do bigger metadata blocks, but the -- cgit v1.2.3-71-gd317 From fe4007999599c02598c17b643e8de43e487d48e8 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 15 Aug 2017 09:09:49 +0200 Subject: ipv6: fib: Provide offload indication using nexthop flags IPv6 routes currently lack nexthop flags as in IPv4. This has several implications. In the forwarding path, it requires us to check the carrier state of the nexthop device and potentially ignore a linkdown route, instead of checking for RTNH_F_LINKDOWN. It also requires capable drivers to use the user facing IPv6-specific route flags to provide offload indication, instead of using the nexthop flags as in IPv4. Add nexthop flags to IPv6 routes in the 40 bytes hole and use it to provide offload indication instead of the RTF_OFFLOAD flag, which is removed while it's still not part of any official kernel release. In the near future we would like to use the field for the RTNH_F_{LINKDOWN,DEAD} flags, but this change is more involved and might not be ready in time for the current cycle. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Acked-by: David Ahern Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 8 ++++---- include/net/ip6_fib.h | 2 ++ include/uapi/linux/ipv6_route.h | 1 - net/ipv6/route.c | 7 +------ 4 files changed, 7 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 16676fffbf70..4895d5b8942b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -2397,7 +2397,7 @@ mlxsw_sp_fib6_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry) if (fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_LOCAL) { list_first_entry(&fib6_entry->rt6_list, struct mlxsw_sp_rt6, - list)->rt->rt6i_flags |= RTF_OFFLOAD; + list)->rt->rt6i_nh_flags |= RTNH_F_OFFLOAD; return; } @@ -2407,9 +2407,9 @@ mlxsw_sp_fib6_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry) nh = mlxsw_sp_rt6_nexthop(nh_grp, mlxsw_sp_rt6); if (nh && nh->offloaded) - mlxsw_sp_rt6->rt->rt6i_flags |= RTF_OFFLOAD; + mlxsw_sp_rt6->rt->rt6i_nh_flags |= RTNH_F_OFFLOAD; else - mlxsw_sp_rt6->rt->rt6i_flags &= ~RTF_OFFLOAD; + mlxsw_sp_rt6->rt->rt6i_nh_flags &= ~RTNH_F_OFFLOAD; } } @@ -2424,7 +2424,7 @@ mlxsw_sp_fib6_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry) list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) { struct rt6_info *rt = mlxsw_sp_rt6->rt; - rt->rt6i_flags &= ~RTF_OFFLOAD; + rt->rt6i_nh_flags &= ~RTNH_F_OFFLOAD; } } diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 1d790ea40ea7..71c1646298ae 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -120,6 +120,8 @@ struct rt6_info { atomic_t rt6i_ref; + unsigned int rt6i_nh_flags; + /* These are in a separate cache line. */ struct rt6key rt6i_dst ____cacheline_aligned_in_smp; u32 rt6i_flags; diff --git a/include/uapi/linux/ipv6_route.h b/include/uapi/linux/ipv6_route.h index 33e2a5732bd1..d496c02e14bc 100644 --- a/include/uapi/linux/ipv6_route.h +++ b/include/uapi/linux/ipv6_route.h @@ -35,7 +35,6 @@ #define RTF_PREF(pref) ((pref) << 27) #define RTF_PREF_MASK 0x18000000 -#define RTF_OFFLOAD 0x20000000 /* offloaded route */ #define RTF_PCPU 0x40000000 /* read-only: can not be set by user */ #define RTF_LOCAL 0x80000000 diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 035762fed07d..6793135d49db 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1820,11 +1820,6 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, goto out; } - if (cfg->fc_flags & RTF_OFFLOAD) { - NL_SET_ERR_MSG(extack, "Userspace can not set RTF_OFFLOAD"); - goto out; - } - if (cfg->fc_dst_len > 128) { NL_SET_ERR_MSG(extack, "Invalid prefix length"); goto out; @@ -3335,7 +3330,7 @@ static int rt6_nexthop_info(struct sk_buff *skb, struct rt6_info *rt, goto nla_put_failure; } - if (rt->rt6i_flags & RTF_OFFLOAD) + if (rt->rt6i_nh_flags & RTNH_F_OFFLOAD) *flags |= RTNH_F_OFFLOAD; /* not needed for multipath encoding b/c it has a rtnexthop struct */ -- cgit v1.2.3-71-gd317 From 6a1c9510694fe1e901a3b5b53386eac069adcea6 Mon Sep 17 00:00:00 2001 From: Moses Reuben Date: Tue, 15 Aug 2017 23:00:20 -0400 Subject: drm/amdkfd: Adding new IOCTL for scratch memory v2 v2: * Renamed ALLOC_MEMORY_OF_SCRATCH to SET_SCRATCH_BACKING_VA * Removed size parameter from the ioctl, it was unused * Removed hole in ioctl number space * No more call to write_config_static_mem * Return correct error code from ioctl Signed-off-by: Moses Reuben Signed-off-by: Ben Goz Signed-off-by: Felix Kuehling Signed-off-by: Oded Gabbay --- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 37 ++++++++++++++++++++++ .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 3 ++ .../drm/amd/amdkfd/kfd_device_queue_manager_cik.c | 2 ++ .../drm/amd/amdkfd/kfd_device_queue_manager_vi.c | 2 ++ drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 1 + include/uapi/linux/kfd_ioctl.h | 11 ++++++- 6 files changed, 55 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 65b506f19b46..7436d34b77ab 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -848,6 +848,40 @@ static int kfd_ioctl_wait_events(struct file *filp, struct kfd_process *p, return err; } +static int kfd_ioctl_set_scratch_backing_va(struct file *filep, + struct kfd_process *p, void *data) +{ + struct kfd_ioctl_set_scratch_backing_va_args *args = data; + struct kfd_process_device *pdd; + struct kfd_dev *dev; + long err; + + dev = kfd_device_by_id(args->gpu_id); + if (!dev) + return -EINVAL; + + mutex_lock(&p->mutex); + + pdd = kfd_bind_process_to_device(dev, p); + if (IS_ERR(pdd)) { + err = PTR_ERR(pdd); + goto bind_process_to_device_fail; + } + + pdd->qpd.sh_hidden_private_base = args->va_addr; + + mutex_unlock(&p->mutex); + + if (sched_policy == KFD_SCHED_POLICY_NO_HWS && pdd->qpd.vmid != 0) + dev->kfd2kgd->set_scratch_backing_va( + dev->kgd, args->va_addr, pdd->qpd.vmid); + + return 0; + +bind_process_to_device_fail: + mutex_unlock(&p->mutex); + return err; +} #define AMDKFD_IOCTL_DEF(ioctl, _func, _flags) \ [_IOC_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, \ @@ -902,6 +936,9 @@ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = { AMDKFD_IOCTL_DEF(AMDKFD_IOC_DBG_WAVE_CONTROL, kfd_ioctl_dbg_wave_control, 0), + + AMDKFD_IOCTL_DEF(AMDKFD_IOC_SET_SCRATCH_BACKING_VA, + kfd_ioctl_set_scratch_backing_va, 0), }; #define AMDKFD_CORE_IOCTL_COUNT ARRAY_SIZE(amdkfd_ioctls) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 618ac65b6136..53a66e821624 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -270,6 +270,9 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm, pr_debug("Loading mqd to hqd on pipe %d, queue %d\n", q->pipe, q->queue); + dqm->dev->kfd2kgd->set_scratch_backing_va( + dqm->dev->kgd, qpd->sh_hidden_private_base, qpd->vmid); + retval = mqd->load_mqd(mqd, q->mqd, q->pipe, q->queue, &q->properties, q->process->mm); if (retval) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c index fadc56a8be71..72c3cbabc0a7 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c @@ -24,6 +24,7 @@ #include "kfd_device_queue_manager.h" #include "cik_regs.h" #include "oss/oss_2_4_sh_mask.h" +#include "gca/gfx_7_2_sh_mask.h" static bool set_cache_memory_policy_cik(struct device_queue_manager *dqm, struct qcm_process_device *qpd, @@ -123,6 +124,7 @@ static int register_process_cik(struct device_queue_manager *dqm, } else { temp = get_sh_mem_bases_nybble_64(pdd); qpd->sh_mem_bases = compute_sh_mem_bases_64bit(temp); + qpd->sh_mem_config |= 1 << SH_MEM_CONFIG__PRIVATE_ATC__SHIFT; } pr_debug("is32bit process: %d sh_mem_bases nybble: 0x%X and register 0x%X\n", diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_vi.c index 15e81ae9d2f4..40e9ddd096cd 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_vi.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_vi.c @@ -135,6 +135,8 @@ static int register_process_vi(struct device_queue_manager *dqm, qpd->sh_mem_bases = compute_sh_mem_bases_64bit(temp); qpd->sh_mem_config |= SH_MEM_ADDRESS_MODE_HSA64 << SH_MEM_CONFIG__ADDRESS_MODE__SHIFT; + qpd->sh_mem_config |= 1 << + SH_MEM_CONFIG__PRIVATE_ATC__SHIFT; } pr_debug("is32bit process: %d sh_mem_bases nybble: 0x%X and register 0x%X\n", diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 30ce92c6e6a1..b397ec726400 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -432,6 +432,7 @@ struct qcm_process_device { uint32_t gds_size; uint32_t num_gws; uint32_t num_oac; + uint32_t sh_hidden_private_base; }; /* Data that is per-process-per device. */ diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index d6833426fdef..1b9c5609d523 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -232,6 +232,12 @@ struct kfd_ioctl_wait_events_args { uint32_t wait_result; /* from KFD */ }; +struct kfd_ioctl_set_scratch_backing_va_args { + uint64_t va_addr; /* to KFD */ + uint32_t gpu_id; /* to KFD */ + uint32_t pad; +}; + #define AMDKFD_IOCTL_BASE 'K' #define AMDKFD_IO(nr) _IO(AMDKFD_IOCTL_BASE, nr) #define AMDKFD_IOR(nr, type) _IOR(AMDKFD_IOCTL_BASE, nr, type) @@ -286,7 +292,10 @@ struct kfd_ioctl_wait_events_args { #define AMDKFD_IOC_DBG_WAVE_CONTROL \ AMDKFD_IOW(0x10, struct kfd_ioctl_dbg_wave_control_args) +#define AMDKFD_IOC_SET_SCRATCH_BACKING_VA \ + AMDKFD_IOWR(0x11, struct kfd_ioctl_set_scratch_backing_va_args) + #define AMDKFD_COMMAND_START 0x01 -#define AMDKFD_COMMAND_END 0x11 +#define AMDKFD_COMMAND_END 0x12 #endif -- cgit v1.2.3-71-gd317 From 5d71dbc3a588690c3d66d76db8cd29973425ce6d Mon Sep 17 00:00:00 2001 From: Yong Zhao Date: Tue, 15 Aug 2017 23:00:22 -0400 Subject: drm/amdkfd: Implement image tiling mode support v2 v2: Removed hole in ioctl number space Signed-off-by: Yong Zhao Signed-off-by: Felix Kuehling Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 43 ++++++++++++++++++++++++++++++++ include/uapi/linux/kfd_ioctl.h | 28 ++++++++++++++++++++- 2 files changed, 70 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 7436d34b77ab..e4a8c2e52cb2 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -883,6 +883,46 @@ bind_process_to_device_fail: return err; } +static int kfd_ioctl_get_tile_config(struct file *filep, + struct kfd_process *p, void *data) +{ + struct kfd_ioctl_get_tile_config_args *args = data; + struct kfd_dev *dev; + struct tile_config config; + int err = 0; + + dev = kfd_device_by_id(args->gpu_id); + + dev->kfd2kgd->get_tile_config(dev->kgd, &config); + + args->gb_addr_config = config.gb_addr_config; + args->num_banks = config.num_banks; + args->num_ranks = config.num_ranks; + + if (args->num_tile_configs > config.num_tile_configs) + args->num_tile_configs = config.num_tile_configs; + err = copy_to_user((void __user *)args->tile_config_ptr, + config.tile_config_ptr, + args->num_tile_configs * sizeof(uint32_t)); + if (err) { + args->num_tile_configs = 0; + return -EFAULT; + } + + if (args->num_macro_tile_configs > config.num_macro_tile_configs) + args->num_macro_tile_configs = + config.num_macro_tile_configs; + err = copy_to_user((void __user *)args->macro_tile_config_ptr, + config.macro_tile_config_ptr, + args->num_macro_tile_configs * sizeof(uint32_t)); + if (err) { + args->num_macro_tile_configs = 0; + return -EFAULT; + } + + return 0; +} + #define AMDKFD_IOCTL_DEF(ioctl, _func, _flags) \ [_IOC_NR(ioctl)] = {.cmd = ioctl, .func = _func, .flags = _flags, \ .cmd_drv = 0, .name = #ioctl} @@ -939,6 +979,9 @@ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = { AMDKFD_IOCTL_DEF(AMDKFD_IOC_SET_SCRATCH_BACKING_VA, kfd_ioctl_set_scratch_backing_va, 0), + + AMDKFD_IOCTL_DEF(AMDKFD_IOC_GET_TILE_CONFIG, + kfd_ioctl_get_tile_config, 0) }; #define AMDKFD_CORE_IOCTL_COUNT ARRAY_SIZE(amdkfd_ioctls) diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 1b9c5609d523..7b4567bacfc2 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -238,6 +238,29 @@ struct kfd_ioctl_set_scratch_backing_va_args { uint32_t pad; }; +struct kfd_ioctl_get_tile_config_args { + /* to KFD: pointer to tile array */ + uint64_t tile_config_ptr; + /* to KFD: pointer to macro tile array */ + uint64_t macro_tile_config_ptr; + /* to KFD: array size allocated by user mode + * from KFD: array size filled by kernel + */ + uint32_t num_tile_configs; + /* to KFD: array size allocated by user mode + * from KFD: array size filled by kernel + */ + uint32_t num_macro_tile_configs; + + uint32_t gpu_id; /* to KFD */ + uint32_t gb_addr_config; /* from KFD */ + uint32_t num_banks; /* from KFD */ + uint32_t num_ranks; /* from KFD */ + /* struct size can be extended later if needed + * without breaking ABI compatibility + */ +}; + #define AMDKFD_IOCTL_BASE 'K' #define AMDKFD_IO(nr) _IO(AMDKFD_IOCTL_BASE, nr) #define AMDKFD_IOR(nr, type) _IOR(AMDKFD_IOCTL_BASE, nr, type) @@ -295,7 +318,10 @@ struct kfd_ioctl_set_scratch_backing_va_args { #define AMDKFD_IOC_SET_SCRATCH_BACKING_VA \ AMDKFD_IOWR(0x11, struct kfd_ioctl_set_scratch_backing_va_args) +#define AMDKFD_IOC_GET_TILE_CONFIG \ + AMDKFD_IOWR(0x12, struct kfd_ioctl_get_tile_config_args) + #define AMDKFD_COMMAND_START 0x01 -#define AMDKFD_COMMAND_END 0x12 +#define AMDKFD_COMMAND_END 0x13 #endif -- cgit v1.2.3-71-gd317 From b005fd189cec9407b700599e1e80e0552446ee79 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 15 Aug 2017 22:31:58 -0700 Subject: bpf: introduce new program type for skbs on sockets A class of programs, run from strparser and soon from a new map type called sock map, are used with skb as the context but on established sockets. By creating a specific program type for these we can use bpf helpers that expect full sockets and get the verifier to ensure these helpers are not used out of context. The new type is BPF_PROG_TYPE_SK_SKB. This patch introduces the infrastructure and type. Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/bpf_types.h | 1 + include/uapi/linux/bpf.h | 1 + net/core/filter.c | 36 ++++++++++++++++++++++++++++++++++++ 3 files changed, 38 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index b1e1035ca24b..4b72db30dacf 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -11,6 +11,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout_prog_ops) BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout_prog_ops) BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit_prog_ops) BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops_prog_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb_prog_ops) #endif #ifdef CONFIG_BPF_EVENTS BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe_prog_ops) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 91da8371a2d0..2e796e384aeb 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -127,6 +127,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_LWT_OUT, BPF_PROG_TYPE_LWT_XMIT, BPF_PROG_TYPE_SOCK_OPS, + BPF_PROG_TYPE_SK_SKB, }; enum bpf_attach_type { diff --git a/net/core/filter.c b/net/core/filter.c index e0688a855c47..46321033ae0e 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3234,6 +3234,20 @@ static const struct bpf_func_proto * } } +static const struct bpf_func_proto *sk_skb_func_proto(enum bpf_func_id func_id) +{ + switch (func_id) { + case BPF_FUNC_skb_load_bytes: + return &bpf_skb_load_bytes_proto; + case BPF_FUNC_get_socket_cookie: + return &bpf_get_socket_cookie_proto; + case BPF_FUNC_get_socket_uid: + return &bpf_get_socket_uid_proto; + default: + return bpf_base_func_proto(func_id); + } +} + static const struct bpf_func_proto * lwt_xmit_func_proto(enum bpf_func_id func_id) { @@ -3525,6 +3539,22 @@ static bool sock_ops_is_valid_access(int off, int size, return __is_valid_sock_ops_access(off, size); } +static bool sk_skb_is_valid_access(int off, int size, + enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + switch (off) { + case bpf_ctx_range(struct __sk_buff, data): + info->reg_type = PTR_TO_PACKET; + break; + case bpf_ctx_range(struct __sk_buff, data_end): + info->reg_type = PTR_TO_PACKET_END; + break; + } + + return bpf_skb_is_valid_access(off, size, type, info); +} + static u32 bpf_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, @@ -3994,6 +4024,12 @@ const struct bpf_verifier_ops sock_ops_prog_ops = { .convert_ctx_access = sock_ops_convert_ctx_access, }; +const struct bpf_verifier_ops sk_skb_prog_ops = { + .get_func_proto = sk_skb_func_proto, + .is_valid_access = sk_skb_is_valid_access, + .convert_ctx_access = bpf_convert_ctx_access, +}; + int sk_detach_filter(struct sock *sk) { int ret = -ENOENT; -- cgit v1.2.3-71-gd317 From 174a79ff9515f400b9a6115643dafd62a635b7e6 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 15 Aug 2017 22:32:47 -0700 Subject: bpf: sockmap with sk redirect support Recently we added a new map type called dev map used to forward XDP packets between ports (6093ec2dc313). This patches introduces a similar notion for sockets. A sockmap allows users to add participating sockets to a map. When sockets are added to the map enough context is stored with the map entry to use the entry with a new helper bpf_sk_redirect_map(map, key, flags) This helper (analogous to bpf_redirect_map in XDP) is given the map and an entry in the map. When called from a sockmap program, discussed below, the skb will be sent on the socket using skb_send_sock(). With the above we need a bpf program to call the helper from that will then implement the send logic. The initial site implemented in this series is the recv_sock hook. For this to work we implemented a map attach command to add attributes to a map. In sockmap we add two programs a parse program and a verdict program. The parse program uses strparser to build messages and pass them to the verdict program. The parse programs use the normal strparser semantics. The verdict program is of type SK_SKB. The verdict program returns a verdict SK_DROP, or SK_REDIRECT for now. Additional actions may be added later. When SK_REDIRECT is returned, expected when bpf program uses bpf_sk_redirect_map(), the sockmap logic will consult per cpu variables set by the helper routine and pull the sock entry out of the sock map. This pattern follows the existing redirect logic in cls and xdp programs. This gives the flow, recv_sock -> str_parser (parse_prog) -> verdict_prog -> skb_send_sock \ -> kfree_skb As an example use case a message based load balancer may use specific logic in the verdict program to select the sock to send on. Sample programs are provided in future patches that hopefully illustrate the user interfaces. Also selftests are in follow-on patches. Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/bpf.h | 7 +- include/linux/bpf_types.h | 1 + include/linux/filter.h | 2 + include/uapi/linux/bpf.h | 33 +- kernel/bpf/Makefile | 2 +- kernel/bpf/sockmap.c | 792 ++++++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 51 ++- kernel/bpf/verifier.c | 14 + net/core/filter.c | 43 +++ 9 files changed, 940 insertions(+), 5 deletions(-) create mode 100644 kernel/bpf/sockmap.c (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d6e1de8ce0fc..a4145e9c74b5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -16,6 +16,7 @@ #include struct perf_event; +struct bpf_prog; struct bpf_map; /* map is generic key/value storage optionally accesible by eBPF programs */ @@ -37,6 +38,8 @@ struct bpf_map_ops { void (*map_fd_put_ptr)(void *ptr); u32 (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); u32 (*map_fd_sys_lookup_elem)(void *ptr); + int (*map_attach)(struct bpf_map *map, + struct bpf_prog *p1, struct bpf_prog *p2); }; struct bpf_map { @@ -138,8 +141,6 @@ enum bpf_reg_type { PTR_TO_PACKET_END, /* skb->data + headlen */ }; -struct bpf_prog; - /* The information passed from prog-specific *_is_valid_access * back to the verifier. */ @@ -312,6 +313,7 @@ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); /* Map specifics */ struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key); +struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key); void __dev_map_insert_ctx(struct bpf_map *map, u32 index); void __dev_map_flush(struct bpf_map *map); @@ -391,6 +393,7 @@ extern const struct bpf_func_proto bpf_get_current_comm_proto; extern const struct bpf_func_proto bpf_skb_vlan_push_proto; extern const struct bpf_func_proto bpf_skb_vlan_pop_proto; extern const struct bpf_func_proto bpf_get_stackid_proto; +extern const struct bpf_func_proto bpf_sock_map_update_proto; /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 4b72db30dacf..fa805074d168 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -38,4 +38,5 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) #ifdef CONFIG_NET BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) #endif diff --git a/include/linux/filter.h b/include/linux/filter.h index d19ed3c15e1e..7015116331af 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -727,6 +727,8 @@ void xdp_do_flush_map(void); void bpf_warn_invalid_xdp_action(u32 act); void bpf_warn_invalid_xdp_redirect(u32 ifindex); +struct sock *do_sk_redirect_map(void); + #ifdef CONFIG_BPF_JIT extern int bpf_jit_enable; extern int bpf_jit_harden; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2e796e384aeb..7f774769e3f5 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -110,6 +110,7 @@ enum bpf_map_type { BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_DEVMAP, + BPF_MAP_TYPE_SOCKMAP, }; enum bpf_prog_type { @@ -135,11 +136,15 @@ enum bpf_attach_type { BPF_CGROUP_INET_EGRESS, BPF_CGROUP_INET_SOCK_CREATE, BPF_CGROUP_SOCK_OPS, + BPF_CGROUP_SMAP_INGRESS, __MAX_BPF_ATTACH_TYPE }; #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE +/* If BPF_SOCKMAP_STRPARSER is used sockmap will use strparser on receive */ +#define BPF_SOCKMAP_STRPARSER (1U << 0) + /* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command * to the given target_fd cgroup the descendent cgroup will be able to * override effective bpf program that was inherited from this cgroup @@ -211,6 +216,7 @@ union bpf_attr { __u32 attach_bpf_fd; /* eBPF program to attach */ __u32 attach_type; __u32 attach_flags; + __u32 attach_bpf_fd2; }; struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */ @@ -557,6 +563,23 @@ union bpf_attr { * @mode: operation mode (enum bpf_adj_room_mode) * @flags: reserved for future use * Return: 0 on success or negative error code + * + * int bpf_sk_redirect_map(map, key, flags) + * Redirect skb to a sock in map using key as a lookup key for the + * sock in map. + * @map: pointer to sockmap + * @key: key to lookup sock in map + * @flags: reserved for future use + * Return: SK_REDIRECT + * + * int bpf_sock_map_update(skops, map, key, flags, map_flags) + * @skops: pointer to bpf_sock_ops + * @map: pointer to sockmap to update + * @key: key to insert/update sock in map + * @flags: same flags as map update elem + * @map_flags: sock map specific flags + * bit 1: Enable strparser + * other bits: reserved */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -610,7 +633,9 @@ union bpf_attr { FN(set_hash), \ FN(setsockopt), \ FN(skb_adjust_room), \ - FN(redirect_map), + FN(redirect_map), \ + FN(sk_redirect_map), \ + FN(sock_map_update), \ /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -747,6 +772,12 @@ struct xdp_md { __u32 data_end; }; +enum sk_action { + SK_ABORTED = 0, + SK_DROP, + SK_REDIRECT, +}; + #define BPF_TAG_SIZE 8 struct bpf_prog_info { diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 2f0bcda40e90..aa24287db888 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -3,7 +3,7 @@ obj-y := core.o obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o ifeq ($(CONFIG_NET),y) -obj-$(CONFIG_BPF_SYSCALL) += devmap.o +obj-$(CONFIG_BPF_SYSCALL) += devmap.o sockmap.o endif ifeq ($(CONFIG_PERF_EVENTS),y) obj-$(CONFIG_BPF_SYSCALL) += stackmap.o diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c new file mode 100644 index 000000000000..792f0addfafa --- /dev/null +++ b/kernel/bpf/sockmap.c @@ -0,0 +1,792 @@ +/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +/* A BPF sock_map is used to store sock objects. This is primarly used + * for doing socket redirect with BPF helper routines. + * + * A sock map may have two BPF programs attached to it, a program used + * to parse packets and a program to provide a verdict and redirect + * decision on the packet. If no BPF parse program is provided it is + * assumed that every skb is a "message" (skb->len). Otherwise the + * parse program is attached to strparser and used to build messages + * that may span multiple skbs. The verdict program will either select + * a socket to send/receive the skb on or provide the drop code indicating + * the skb should be dropped. More actions may be added later as needed. + * The default program will drop packets. + * + * For reference this program is similar to devmap used in XDP context + * reviewing these together may be useful. For an example please review + * ./samples/bpf/sockmap/. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct bpf_stab { + struct bpf_map map; + struct sock **sock_map; + struct bpf_prog *bpf_parse; + struct bpf_prog *bpf_verdict; + refcount_t refcnt; +}; + +enum smap_psock_state { + SMAP_TX_RUNNING, +}; + +struct smap_psock { + struct rcu_head rcu; + + /* datapath variables */ + struct sk_buff_head rxqueue; + bool strp_enabled; + + /* datapath error path cache across tx work invocations */ + int save_rem; + int save_off; + struct sk_buff *save_skb; + + struct strparser strp; + struct bpf_prog *bpf_parse; + struct bpf_prog *bpf_verdict; + struct bpf_stab *stab; + + /* Back reference used when sock callback trigger sockmap operations */ + int key; + struct sock *sock; + unsigned long state; + + struct work_struct tx_work; + struct work_struct gc_work; + + void (*save_data_ready)(struct sock *sk); + void (*save_write_space)(struct sock *sk); + void (*save_state_change)(struct sock *sk); +}; + +static inline struct smap_psock *smap_psock_sk(const struct sock *sk) +{ + return (struct smap_psock *)rcu_dereference_sk_user_data(sk); +} + +static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) +{ + struct bpf_prog *prog = READ_ONCE(psock->bpf_verdict); + int rc; + + if (unlikely(!prog)) + return SK_DROP; + + skb_orphan(skb); + skb->sk = psock->sock; + bpf_compute_data_end(skb); + rc = (*prog->bpf_func)(skb, prog->insnsi); + skb->sk = NULL; + + return rc; +} + +static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb) +{ + struct sock *sock; + int rc; + + /* Because we use per cpu values to feed input from sock redirect + * in BPF program to do_sk_redirect_map() call we need to ensure we + * are not preempted. RCU read lock is not sufficient in this case + * with CONFIG_PREEMPT_RCU enabled so we must be explicit here. + */ + preempt_disable(); + rc = smap_verdict_func(psock, skb); + switch (rc) { + case SK_REDIRECT: + sock = do_sk_redirect_map(); + preempt_enable(); + if (likely(sock)) { + struct smap_psock *peer = smap_psock_sk(sock); + + if (likely(peer && + test_bit(SMAP_TX_RUNNING, &peer->state) && + sk_stream_memory_free(peer->sock))) { + peer->sock->sk_wmem_queued += skb->truesize; + sk_mem_charge(peer->sock, skb->truesize); + skb_queue_tail(&peer->rxqueue, skb); + schedule_work(&peer->tx_work); + break; + } + } + /* Fall through and free skb otherwise */ + case SK_DROP: + default: + preempt_enable(); + kfree_skb(skb); + } +} + +static void smap_report_sk_error(struct smap_psock *psock, int err) +{ + struct sock *sk = psock->sock; + + sk->sk_err = err; + sk->sk_error_report(sk); +} + +static void smap_release_sock(struct sock *sock); + +/* Called with lock_sock(sk) held */ +static void smap_state_change(struct sock *sk) +{ + struct smap_psock *psock; + struct sock *osk; + + rcu_read_lock(); + + /* Allowing transitions into an established syn_recv states allows + * for early binding sockets to a smap object before the connection + * is established. + */ + switch (sk->sk_state) { + case TCP_SYN_RECV: + case TCP_ESTABLISHED: + break; + case TCP_CLOSE_WAIT: + case TCP_CLOSING: + case TCP_LAST_ACK: + case TCP_FIN_WAIT1: + case TCP_FIN_WAIT2: + case TCP_LISTEN: + break; + case TCP_CLOSE: + /* Only release if the map entry is in fact the sock in + * question. There is a case where the operator deletes + * the sock from the map, but the TCP sock is closed before + * the psock is detached. Use cmpxchg to verify correct + * sock is removed. + */ + psock = smap_psock_sk(sk); + if (unlikely(!psock)) + break; + osk = cmpxchg(&psock->stab->sock_map[psock->key], sk, NULL); + if (osk == sk) + smap_release_sock(sk); + break; + default: + smap_report_sk_error(psock, EPIPE); + break; + } + rcu_read_unlock(); +} + +static void smap_read_sock_strparser(struct strparser *strp, + struct sk_buff *skb) +{ + struct smap_psock *psock; + + rcu_read_lock(); + psock = container_of(strp, struct smap_psock, strp); + smap_do_verdict(psock, skb); + rcu_read_unlock(); +} + +/* Called with lock held on socket */ +static void smap_data_ready(struct sock *sk) +{ + struct smap_psock *psock; + + write_lock_bh(&sk->sk_callback_lock); + psock = smap_psock_sk(sk); + if (likely(psock)) + strp_data_ready(&psock->strp); + write_unlock_bh(&sk->sk_callback_lock); +} + +static void smap_tx_work(struct work_struct *w) +{ + struct smap_psock *psock; + struct sk_buff *skb; + int rem, off, n; + + psock = container_of(w, struct smap_psock, tx_work); + + /* lock sock to avoid losing sk_socket at some point during loop */ + lock_sock(psock->sock); + if (psock->save_skb) { + skb = psock->save_skb; + rem = psock->save_rem; + off = psock->save_off; + psock->save_skb = NULL; + goto start; + } + + while ((skb = skb_dequeue(&psock->rxqueue))) { + rem = skb->len; + off = 0; +start: + do { + if (likely(psock->sock->sk_socket)) + n = skb_send_sock_locked(psock->sock, + skb, off, rem); + else + n = -EINVAL; + if (n <= 0) { + if (n == -EAGAIN) { + /* Retry when space is available */ + psock->save_skb = skb; + psock->save_rem = rem; + psock->save_off = off; + goto out; + } + /* Hard errors break pipe and stop xmit */ + smap_report_sk_error(psock, n ? -n : EPIPE); + clear_bit(SMAP_TX_RUNNING, &psock->state); + sk_mem_uncharge(psock->sock, skb->truesize); + psock->sock->sk_wmem_queued -= skb->truesize; + kfree_skb(skb); + goto out; + } + rem -= n; + off += n; + } while (rem); + sk_mem_uncharge(psock->sock, skb->truesize); + psock->sock->sk_wmem_queued -= skb->truesize; + kfree_skb(skb); + } +out: + release_sock(psock->sock); +} + +static void smap_write_space(struct sock *sk) +{ + struct smap_psock *psock; + + rcu_read_lock(); + psock = smap_psock_sk(sk); + if (likely(psock && test_bit(SMAP_TX_RUNNING, &psock->state))) + schedule_work(&psock->tx_work); + rcu_read_unlock(); +} + +static void smap_stop_sock(struct smap_psock *psock, struct sock *sk) +{ + write_lock_bh(&sk->sk_callback_lock); + if (!psock->strp_enabled) + goto out; + sk->sk_data_ready = psock->save_data_ready; + sk->sk_write_space = psock->save_write_space; + sk->sk_state_change = psock->save_state_change; + psock->save_data_ready = NULL; + psock->save_write_space = NULL; + psock->save_state_change = NULL; + strp_stop(&psock->strp); + psock->strp_enabled = false; +out: + write_unlock_bh(&sk->sk_callback_lock); +} + +static void smap_destroy_psock(struct rcu_head *rcu) +{ + struct smap_psock *psock = container_of(rcu, + struct smap_psock, rcu); + + /* Now that a grace period has passed there is no longer + * any reference to this sock in the sockmap so we can + * destroy the psock, strparser, and bpf programs. But, + * because we use workqueue sync operations we can not + * do it in rcu context + */ + schedule_work(&psock->gc_work); +} + +static void smap_release_sock(struct sock *sock) +{ + struct smap_psock *psock = smap_psock_sk(sock); + + smap_stop_sock(psock, sock); + clear_bit(SMAP_TX_RUNNING, &psock->state); + rcu_assign_sk_user_data(sock, NULL); + call_rcu_sched(&psock->rcu, smap_destroy_psock); +} + +static int smap_parse_func_strparser(struct strparser *strp, + struct sk_buff *skb) +{ + struct smap_psock *psock; + struct bpf_prog *prog; + int rc; + + rcu_read_lock(); + psock = container_of(strp, struct smap_psock, strp); + prog = READ_ONCE(psock->bpf_parse); + + if (unlikely(!prog)) { + rcu_read_unlock(); + return skb->len; + } + + /* Attach socket for bpf program to use if needed we can do this + * because strparser clones the skb before handing it to a upper + * layer, meaning skb_orphan has been called. We NULL sk on the + * way out to ensure we don't trigger a BUG_ON in skb/sk operations + * later and because we are not charging the memory of this skb to + * any socket yet. + */ + skb->sk = psock->sock; + bpf_compute_data_end(skb); + rc = (*prog->bpf_func)(skb, prog->insnsi); + skb->sk = NULL; + rcu_read_unlock(); + return rc; +} + + +static int smap_read_sock_done(struct strparser *strp, int err) +{ + return err; +} + +static int smap_init_sock(struct smap_psock *psock, + struct sock *sk) +{ + struct strp_callbacks cb; + + memset(&cb, 0, sizeof(cb)); + cb.rcv_msg = smap_read_sock_strparser; + cb.parse_msg = smap_parse_func_strparser; + cb.read_sock_done = smap_read_sock_done; + return strp_init(&psock->strp, sk, &cb); +} + +static void smap_init_progs(struct smap_psock *psock, + struct bpf_stab *stab, + struct bpf_prog *verdict, + struct bpf_prog *parse) +{ + struct bpf_prog *orig_parse, *orig_verdict; + + orig_parse = xchg(&psock->bpf_parse, parse); + orig_verdict = xchg(&psock->bpf_verdict, verdict); + + if (orig_verdict) + bpf_prog_put(orig_verdict); + if (orig_parse) + bpf_prog_put(orig_parse); +} + +static void smap_start_sock(struct smap_psock *psock, struct sock *sk) +{ + if (sk->sk_data_ready == smap_data_ready) + return; + psock->save_data_ready = sk->sk_data_ready; + psock->save_write_space = sk->sk_write_space; + psock->save_state_change = sk->sk_state_change; + sk->sk_data_ready = smap_data_ready; + sk->sk_write_space = smap_write_space; + sk->sk_state_change = smap_state_change; + psock->strp_enabled = true; +} + +static void sock_map_remove_complete(struct bpf_stab *stab) +{ + bpf_map_area_free(stab->sock_map); + kfree(stab); +} + +static void smap_gc_work(struct work_struct *w) +{ + struct smap_psock *psock; + + psock = container_of(w, struct smap_psock, gc_work); + + /* no callback lock needed because we already detached sockmap ops */ + if (psock->strp_enabled) + strp_done(&psock->strp); + + cancel_work_sync(&psock->tx_work); + __skb_queue_purge(&psock->rxqueue); + + /* At this point all strparser and xmit work must be complete */ + if (psock->bpf_parse) + bpf_prog_put(psock->bpf_parse); + if (psock->bpf_verdict) + bpf_prog_put(psock->bpf_verdict); + + if (refcount_dec_and_test(&psock->stab->refcnt)) + sock_map_remove_complete(psock->stab); + + sock_put(psock->sock); + kfree(psock); +} + +static struct smap_psock *smap_init_psock(struct sock *sock, + struct bpf_stab *stab) +{ + struct smap_psock *psock; + + psock = kzalloc(sizeof(struct smap_psock), GFP_ATOMIC | __GFP_NOWARN); + if (!psock) + return ERR_PTR(-ENOMEM); + + psock->sock = sock; + skb_queue_head_init(&psock->rxqueue); + INIT_WORK(&psock->tx_work, smap_tx_work); + INIT_WORK(&psock->gc_work, smap_gc_work); + + rcu_assign_sk_user_data(sock, psock); + sock_hold(sock); + return psock; +} + +static struct bpf_map *sock_map_alloc(union bpf_attr *attr) +{ + struct bpf_stab *stab; + int err = -EINVAL; + u64 cost; + + /* check sanity of attributes */ + if (attr->max_entries == 0 || attr->key_size != 4 || + attr->value_size != 4 || attr->map_flags) + return ERR_PTR(-EINVAL); + + if (attr->value_size > KMALLOC_MAX_SIZE) + return ERR_PTR(-E2BIG); + + stab = kzalloc(sizeof(*stab), GFP_USER); + if (!stab) + return ERR_PTR(-ENOMEM); + + /* mandatory map attributes */ + stab->map.map_type = attr->map_type; + stab->map.key_size = attr->key_size; + stab->map.value_size = attr->value_size; + stab->map.max_entries = attr->max_entries; + stab->map.map_flags = attr->map_flags; + + /* make sure page count doesn't overflow */ + cost = (u64) stab->map.max_entries * sizeof(struct sock *); + if (cost >= U32_MAX - PAGE_SIZE) + goto free_stab; + + stab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + /* if map size is larger than memlock limit, reject it early */ + err = bpf_map_precharge_memlock(stab->map.pages); + if (err) + goto free_stab; + + stab->sock_map = bpf_map_area_alloc(stab->map.max_entries * + sizeof(struct sock *)); + if (!stab->sock_map) + goto free_stab; + + refcount_set(&stab->refcnt, 1); + return &stab->map; +free_stab: + kfree(stab); + return ERR_PTR(err); +} + +static void sock_map_free(struct bpf_map *map) +{ + struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + int i; + + synchronize_rcu(); + + /* At this point no update, lookup or delete operations can happen. + * However, be aware we can still get a socket state event updates, + * and data ready callabacks that reference the psock from sk_user_data + * Also psock worker threads are still in-flight. So smap_release_sock + * will only free the psock after cancel_sync on the worker threads + * and a grace period expire to ensure psock is really safe to remove. + */ + rcu_read_lock(); + for (i = 0; i < stab->map.max_entries; i++) { + struct sock *sock; + + sock = xchg(&stab->sock_map[i], NULL); + if (!sock) + continue; + + smap_release_sock(sock); + } + rcu_read_unlock(); + + if (stab->bpf_verdict) + bpf_prog_put(stab->bpf_verdict); + if (stab->bpf_parse) + bpf_prog_put(stab->bpf_parse); + + if (refcount_dec_and_test(&stab->refcnt)) + sock_map_remove_complete(stab); +} + +static int sock_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + u32 i = key ? *(u32 *)key : U32_MAX; + u32 *next = (u32 *)next_key; + + if (i >= stab->map.max_entries) { + *next = 0; + return 0; + } + + if (i == stab->map.max_entries - 1) + return -ENOENT; + + *next = i + 1; + return 0; +} + +struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key) +{ + struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + + if (key >= map->max_entries) + return NULL; + + return READ_ONCE(stab->sock_map[key]); +} + +static int sock_map_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + int k = *(u32 *)key; + struct sock *sock; + + if (k >= map->max_entries) + return -EINVAL; + + sock = xchg(&stab->sock_map[k], NULL); + if (!sock) + return -EINVAL; + + smap_release_sock(sock); + return 0; +} + +/* Locking notes: Concurrent updates, deletes, and lookups are allowed and are + * done inside rcu critical sections. This ensures on updates that the psock + * will not be released via smap_release_sock() until concurrent updates/deletes + * complete. All operations operate on sock_map using cmpxchg and xchg + * operations to ensure we do not get stale references. Any reads into the + * map must be done with READ_ONCE() because of this. + * + * A psock is destroyed via call_rcu and after any worker threads are cancelled + * and syncd so we are certain all references from the update/lookup/delete + * operations as well as references in the data path are no longer in use. + * + * A psock object holds a refcnt on the sockmap it is attached to and this is + * not decremented until after a RCU grace period and garbage collection occurs. + * This ensures the map is not free'd until psocks linked to it are removed. The + * map link is used when the independent sock events trigger map deletion. + * + * Psocks may only participate in one sockmap at a time. Users that try to + * join a single sock to multiple maps will get an error. + * + * Last, but not least, it is possible the socket is closed while running + * an update on an existing psock. This will release the psock, but again + * not until the update has completed due to rcu grace period rules. + */ +static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, + struct bpf_map *map, + void *key, u64 flags, u64 map_flags) +{ + struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + struct bpf_prog *verdict, *parse; + struct smap_psock *psock = NULL; + struct sock *old_sock, *sock; + u32 i = *(u32 *)key; + bool update = false; + int err = 0; + + if (unlikely(flags > BPF_EXIST)) + return -EINVAL; + + if (unlikely(i >= stab->map.max_entries)) + return -E2BIG; + + if (unlikely(map_flags > BPF_SOCKMAP_STRPARSER)) + return -EINVAL; + + verdict = parse = NULL; + sock = READ_ONCE(stab->sock_map[i]); + + if (flags == BPF_EXIST || flags == BPF_ANY) { + if (!sock && flags == BPF_EXIST) { + return -ENOENT; + } else if (sock && sock != skops->sk) { + return -EINVAL; + } else if (sock) { + psock = smap_psock_sk(sock); + if (unlikely(!psock)) + return -EBUSY; + update = true; + } + } else if (sock && BPF_NOEXIST) { + return -EEXIST; + } + + /* reserve BPF programs early so can abort easily on failures */ + if (map_flags & BPF_SOCKMAP_STRPARSER) { + verdict = READ_ONCE(stab->bpf_verdict); + parse = READ_ONCE(stab->bpf_parse); + + if (!verdict || !parse) + return -ENOENT; + + /* bpf prog refcnt may be zero if a concurrent attach operation + * removes the program after the above READ_ONCE() but before + * we increment the refcnt. If this is the case abort with an + * error. + */ + verdict = bpf_prog_inc_not_zero(stab->bpf_verdict); + if (IS_ERR(verdict)) + return PTR_ERR(verdict); + + parse = bpf_prog_inc_not_zero(stab->bpf_parse); + if (IS_ERR(parse)) { + bpf_prog_put(verdict); + return PTR_ERR(parse); + } + } + + if (!psock) { + sock = skops->sk; + if (rcu_dereference_sk_user_data(sock)) + return -EEXIST; + psock = smap_init_psock(sock, stab); + if (IS_ERR(psock)) { + if (verdict) + bpf_prog_put(verdict); + if (parse) + bpf_prog_put(parse); + return PTR_ERR(psock); + } + psock->key = i; + psock->stab = stab; + refcount_inc(&stab->refcnt); + set_bit(SMAP_TX_RUNNING, &psock->state); + } + + if (map_flags & BPF_SOCKMAP_STRPARSER) { + write_lock_bh(&sock->sk_callback_lock); + if (psock->strp_enabled) + goto start_done; + err = smap_init_sock(psock, sock); + if (err) + goto out; + smap_init_progs(psock, stab, verdict, parse); + smap_start_sock(psock, sock); +start_done: + write_unlock_bh(&sock->sk_callback_lock); + } else if (update) { + smap_stop_sock(psock, sock); + } + + if (!update) { + old_sock = xchg(&stab->sock_map[i], skops->sk); + if (old_sock) + smap_release_sock(old_sock); + } + + return 0; +out: + write_unlock_bh(&sock->sk_callback_lock); + if (!update) + smap_release_sock(sock); + return err; +} + +static int sock_map_attach_prog(struct bpf_map *map, + struct bpf_prog *parse, + struct bpf_prog *verdict) +{ + struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + struct bpf_prog *_parse, *_verdict; + + _parse = xchg(&stab->bpf_parse, parse); + _verdict = xchg(&stab->bpf_verdict, verdict); + + if (_parse) + bpf_prog_put(_parse); + if (_verdict) + bpf_prog_put(_verdict); + + return 0; +} + +static void *sock_map_lookup(struct bpf_map *map, void *key) +{ + return NULL; +} + +static int sock_map_update_elem(struct bpf_map *map, + void *key, void *value, u64 flags) +{ + struct bpf_sock_ops_kern skops; + u32 fd = *(u32 *)value; + struct socket *socket; + int err; + + socket = sockfd_lookup(fd, &err); + if (!socket) + return err; + + skops.sk = socket->sk; + if (!skops.sk) { + fput(socket->file); + return -EINVAL; + } + + err = sock_map_ctx_update_elem(&skops, map, key, + flags, BPF_SOCKMAP_STRPARSER); + fput(socket->file); + return err; +} + +const struct bpf_map_ops sock_map_ops = { + .map_alloc = sock_map_alloc, + .map_free = sock_map_free, + .map_lookup_elem = sock_map_lookup, + .map_get_next_key = sock_map_get_next_key, + .map_update_elem = sock_map_update_elem, + .map_delete_elem = sock_map_delete_elem, + .map_attach = sock_map_attach_prog, +}; + +BPF_CALL_5(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock, + struct bpf_map *, map, void *, key, u64, flags, u64, map_flags) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + return sock_map_ctx_update_elem(bpf_sock, map, key, flags, map_flags); +} + +const struct bpf_func_proto bpf_sock_map_update_proto = { + .func = bpf_sock_map_update, + .gpl_only = false, + .pkt_access = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_PTR_TO_MAP_KEY, + .arg4_type = ARG_ANYTHING, + .arg5_type = ARG_ANYTHING, +}; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 17e29f596de1..d2f2bdf71ffa 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1087,7 +1087,50 @@ static int bpf_obj_get(const union bpf_attr *attr) #ifdef CONFIG_CGROUP_BPF -#define BPF_PROG_ATTACH_LAST_FIELD attach_flags +#define BPF_PROG_ATTACH_LAST_FIELD attach_bpf_fd2 + +static int sockmap_get_from_fd(const union bpf_attr *attr, int ptype) +{ + struct bpf_prog *prog1, *prog2; + int ufd = attr->target_fd; + struct bpf_map *map; + struct fd f; + int err; + + f = fdget(ufd); + map = __bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + if (!map->ops->map_attach) { + fdput(f); + return -EOPNOTSUPP; + } + + prog1 = bpf_prog_get_type(attr->attach_bpf_fd, ptype); + if (IS_ERR(prog1)) { + fdput(f); + return PTR_ERR(prog1); + } + + prog2 = bpf_prog_get_type(attr->attach_bpf_fd2, ptype); + if (IS_ERR(prog2)) { + fdput(f); + bpf_prog_put(prog1); + return PTR_ERR(prog2); + } + + err = map->ops->map_attach(map, prog1, prog2); + if (err) { + fdput(f); + bpf_prog_put(prog1); + bpf_prog_put(prog2); + return PTR_ERR(map); + } + + fdput(f); + return err; +} static int bpf_prog_attach(const union bpf_attr *attr) { @@ -1116,10 +1159,16 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_CGROUP_SOCK_OPS: ptype = BPF_PROG_TYPE_SOCK_OPS; break; + case BPF_CGROUP_SMAP_INGRESS: + ptype = BPF_PROG_TYPE_SK_SKB; + break; default: return -EINVAL; } + if (attr->attach_type == BPF_CGROUP_SMAP_INGRESS) + return sockmap_get_from_fd(attr, ptype); + prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); if (IS_ERR(prog)) return PTR_ERR(prog); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 7dd96d064be1..a71bc0996572 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1522,6 +1522,12 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) case BPF_MAP_TYPE_HASH_OF_MAPS: if (func_id != BPF_FUNC_map_lookup_elem) goto error; + case BPF_MAP_TYPE_SOCKMAP: + if (func_id != BPF_FUNC_sk_redirect_map && + func_id != BPF_FUNC_sock_map_update && + func_id != BPF_FUNC_map_delete_elem) + goto error; + break; default: break; } @@ -1550,6 +1556,14 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) if (map->map_type != BPF_MAP_TYPE_DEVMAP) goto error; break; + case BPF_FUNC_sk_redirect_map: + if (map->map_type != BPF_MAP_TYPE_SOCKMAP) + goto error; + break; + case BPF_FUNC_sock_map_update: + if (map->map_type != BPF_MAP_TYPE_SOCKMAP) + goto error; + break; default: break; } diff --git a/net/core/filter.c b/net/core/filter.c index 46321033ae0e..8e136578488c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1858,6 +1858,45 @@ static const struct bpf_func_proto bpf_redirect_map_proto = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_3(bpf_sk_redirect_map, struct bpf_map *, map, u32, key, u64, flags) +{ + struct redirect_info *ri = this_cpu_ptr(&redirect_info); + + if (unlikely(flags)) + return SK_ABORTED; + + ri->ifindex = key; + ri->flags = flags; + ri->map = map; + + return SK_REDIRECT; +} + +struct sock *do_sk_redirect_map(void) +{ + struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct sock *sk = NULL; + + if (ri->map) { + sk = __sock_map_lookup_elem(ri->map, ri->ifindex); + + ri->ifindex = 0; + ri->map = NULL; + /* we do not clear flags for future lookup */ + } + + return sk; +} + +static const struct bpf_func_proto bpf_sk_redirect_map_proto = { + .func = bpf_sk_redirect_map, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; + BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb) { return task_get_classid(skb); @@ -3229,6 +3268,8 @@ static const struct bpf_func_proto * switch (func_id) { case BPF_FUNC_setsockopt: return &bpf_setsockopt_proto; + case BPF_FUNC_sock_map_update: + return &bpf_sock_map_update_proto; default: return bpf_base_func_proto(func_id); } @@ -3243,6 +3284,8 @@ static const struct bpf_func_proto *sk_skb_func_proto(enum bpf_func_id func_id) return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_socket_uid: return &bpf_get_socket_uid_proto; + case BPF_FUNC_sk_redirect_map: + return &bpf_sk_redirect_map_proto; default: return bpf_base_func_proto(func_id); } -- cgit v1.2.3-71-gd317 From 8a31db5615667956c513d205cfb06885c3ec6d0b Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 15 Aug 2017 22:33:09 -0700 Subject: bpf: add access to sock fields and pkt data from sk_skb programs Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 9 +++ kernel/bpf/verifier.c | 1 + net/core/filter.c | 169 +++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 179 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7f774769e3f5..5ecbe812a2cc 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -712,6 +712,15 @@ struct __sk_buff { __u32 data; __u32 data_end; __u32 napi_id; + + /* accessed by BPF_PROG_TYPE_sk_skb types */ + __u32 family; + __u32 remote_ip4; /* Stored in network byte order */ + __u32 local_ip4; /* Stored in network byte order */ + __u32 remote_ip6[4]; /* Stored in network byte order */ + __u32 local_ip6[4]; /* Stored in network byte order */ + __u32 remote_port; /* Stored in network byte order */ + __u32 local_port; /* stored in host byte order */ }; struct bpf_tunnel_key { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a71bc0996572..958ba84a9995 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -886,6 +886,7 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, case BPF_PROG_TYPE_SCHED_ACT: case BPF_PROG_TYPE_XDP: case BPF_PROG_TYPE_LWT_XMIT: + case BPF_PROG_TYPE_SK_SKB: if (meta) return meta->pkt_access; diff --git a/net/core/filter.c b/net/core/filter.c index 8e136578488c..e9f8dcef6c57 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3278,8 +3278,16 @@ static const struct bpf_func_proto * static const struct bpf_func_proto *sk_skb_func_proto(enum bpf_func_id func_id) { switch (func_id) { + case BPF_FUNC_skb_store_bytes: + return &bpf_skb_store_bytes_proto; case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; + case BPF_FUNC_skb_pull_data: + return &bpf_skb_pull_data_proto; + case BPF_FUNC_skb_change_tail: + return &bpf_skb_change_tail_proto; + case BPF_FUNC_skb_change_head: + return &bpf_skb_change_head_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_socket_uid: @@ -3343,6 +3351,10 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type if (off + size > offsetofend(struct __sk_buff, cb[4])) return false; break; + case bpf_ctx_range_till(struct __sk_buff, remote_ip6[0], remote_ip6[3]): + case bpf_ctx_range_till(struct __sk_buff, local_ip6[0], local_ip6[3]): + case bpf_ctx_range_till(struct __sk_buff, remote_ip4, remote_ip4): + case bpf_ctx_range_till(struct __sk_buff, local_ip4, local_ip4): case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_end): if (size != size_default) @@ -3371,6 +3383,7 @@ static bool sk_filter_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_end): + case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; } @@ -3392,6 +3405,7 @@ static bool lwt_is_valid_access(int off, int size, { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): + case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; } @@ -3505,6 +3519,8 @@ static bool tc_cls_act_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; + case bpf_ctx_range_till(struct __sk_buff, family, local_port): + return false; } return bpf_skb_is_valid_access(off, size, type, info); @@ -3582,11 +3598,63 @@ static bool sock_ops_is_valid_access(int off, int size, return __is_valid_sock_ops_access(off, size); } +static int sk_skb_prologue(struct bpf_insn *insn_buf, bool direct_write, + const struct bpf_prog *prog) +{ + struct bpf_insn *insn = insn_buf; + + if (!direct_write) + return 0; + + /* if (!skb->cloned) + * goto start; + * + * (Fast-path, otherwise approximation that we might be + * a clone, do the rest in helper.) + */ + *insn++ = BPF_LDX_MEM(BPF_B, BPF_REG_6, BPF_REG_1, CLONED_OFFSET()); + *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_6, CLONED_MASK); + *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 7); + + /* ret = bpf_skb_pull_data(skb, 0); */ + *insn++ = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1); + *insn++ = BPF_ALU64_REG(BPF_XOR, BPF_REG_2, BPF_REG_2); + *insn++ = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_pull_data); + /* if (!ret) + * goto restore; + * return SK_DROP; + */ + *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2); + *insn++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, SK_DROP); + *insn++ = BPF_EXIT_INSN(); + + /* restore: */ + *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6); + /* start: */ + *insn++ = prog->insnsi[0]; + + return insn - insn_buf; +} + static bool sk_skb_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { + if (type == BPF_WRITE) { + switch (off) { + case bpf_ctx_range(struct __sk_buff, mark): + case bpf_ctx_range(struct __sk_buff, tc_index): + case bpf_ctx_range(struct __sk_buff, priority): + break; + default: + return false; + } + } + switch (off) { + case bpf_ctx_range(struct __sk_buff, tc_classid): + return false; case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; @@ -3783,6 +3851,106 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); #endif break; + case offsetof(struct __sk_buff, family): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_family) != 2); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, sk)); + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, + bpf_target_off(struct sock_common, + skc_family, + 2, target_size)); + break; + case offsetof(struct __sk_buff, remote_ip4): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_daddr) != 4); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, sk)); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, + bpf_target_off(struct sock_common, + skc_daddr, + 4, target_size)); + break; + case offsetof(struct __sk_buff, local_ip4): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + skc_rcv_saddr) != 4); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, sk)); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, + bpf_target_off(struct sock_common, + skc_rcv_saddr, + 4, target_size)); + break; + 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, + skc_v6_daddr.s6_addr32[0]) != 4); + + off = si->off; + off -= offsetof(struct __sk_buff, remote_ip6[0]); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, sk)); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, + skc_v6_daddr.s6_addr32[0]) + + off); +#else + *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); +#endif + break; + 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, + skc_v6_rcv_saddr.s6_addr32[0]) != 4); + + off = si->off; + off -= offsetof(struct __sk_buff, local_ip6[0]); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, sk)); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, + skc_v6_rcv_saddr.s6_addr32[0]) + + off); +#else + *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); +#endif + break; + + case offsetof(struct __sk_buff, remote_port): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_dport) != 2); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, sk)); + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, + bpf_target_off(struct sock_common, + skc_dport, + 2, target_size)); +#ifndef __BIG_ENDIAN_BITFIELD + *insn++ = BPF_ALU32_IMM(BPF_LSH, si->dst_reg, 16); +#endif + break; + + case offsetof(struct __sk_buff, local_port): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_num) != 2); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, sk)); + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, + bpf_target_off(struct sock_common, + skc_num, 2, target_size)); + break; } return insn - insn_buf; @@ -4071,6 +4239,7 @@ const struct bpf_verifier_ops sk_skb_prog_ops = { .get_func_proto = sk_skb_func_proto, .is_valid_access = sk_skb_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, + .gen_prologue = sk_skb_prologue, }; int sk_detach_filter(struct sock *sk) -- cgit v1.2.3-71-gd317 From 22e4ebb975822833b083533035233d128b30e98f Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Fri, 28 Jul 2017 16:40:40 -0400 Subject: membarrier: Provide expedited private command Implement MEMBARRIER_CMD_PRIVATE_EXPEDITED with IPIs using cpumask built from all runqueues for which current thread's mm is the same as the thread calling sys_membarrier. It executes faster than the non-expedited variant (no blocking). It also works on NOHZ_FULL configurations. Scheduler-wise, it requires a memory barrier before and after context switching between processes (which have different mm). The memory barrier before context switch is already present. For the barrier after context switch: * Our TSO archs can do RELEASE without being a full barrier. Look at x86 spin_unlock() being a regular STORE for example. But for those archs, all atomics imply smp_mb and all of them have atomic ops in switch_mm() for mm_cpumask(), and on x86 the CR3 load acts as a full barrier. * From all weakly ordered machines, only ARM64 and PPC can do RELEASE, the rest does indeed do smp_mb(), so there the spin_unlock() is a full barrier and we're good. * ARM64 has a very heavy barrier in switch_to(), which suffices. * PPC just removed its barrier from switch_to(), but appears to be talking about adding something to switch_mm(). So add a smp_mb__after_unlock_lock() for now, until this is settled on the PPC side. Changes since v3: - Properly document the memory barriers provided by each architecture. Changes since v2: - Address comments from Peter Zijlstra, - Add smp_mb__after_unlock_lock() after finish_lock_switch() in finish_task_switch() to add the memory barrier we need after storing to rq->curr. This is much simpler than the previous approach relying on atomic_dec_and_test() in mmdrop(), which actually added a memory barrier in the common case of switching between userspace processes. - Return -EINVAL when MEMBARRIER_CMD_SHARED is used on a nohz_full kernel, rather than having the whole membarrier system call returning -ENOSYS. Indeed, CMD_PRIVATE_EXPEDITED is compatible with nohz_full. Adapt the CMD_QUERY mask accordingly. Changes since v1: - move membarrier code under kernel/sched/ because it uses the scheduler runqueue, - only add the barrier when we switch from a kernel thread. The case where we switch from a user-space thread is already handled by the atomic_dec_and_test() in mmdrop(). - add a comment to mmdrop() documenting the requirement on the implicit memory barrier. CC: Peter Zijlstra CC: Paul E. McKenney CC: Boqun Feng CC: Andrew Hunter CC: Maged Michael CC: gromer@google.com CC: Avi Kivity CC: Benjamin Herrenschmidt CC: Paul Mackerras CC: Michael Ellerman Signed-off-by: Mathieu Desnoyers Signed-off-by: Paul E. McKenney Tested-by: Dave Watson --- MAINTAINERS | 2 +- arch/arm64/kernel/process.c | 2 + include/uapi/linux/membarrier.h | 23 +++++- kernel/Makefile | 1 - kernel/membarrier.c | 70 ------------------ kernel/sched/Makefile | 1 + kernel/sched/core.c | 25 +++++++ kernel/sched/membarrier.c | 152 ++++++++++++++++++++++++++++++++++++++++ 8 files changed, 202 insertions(+), 74 deletions(-) delete mode 100644 kernel/membarrier.c create mode 100644 kernel/sched/membarrier.c (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index f66488dfdbc9..3b035584272f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8621,7 +8621,7 @@ M: Mathieu Desnoyers M: "Paul E. McKenney" L: linux-kernel@vger.kernel.org S: Supported -F: kernel/membarrier.c +F: kernel/sched/membarrier.c F: include/uapi/linux/membarrier.h MEMORY MANAGEMENT diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 659ae8094ed5..c8f7d98d8cb9 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -360,6 +360,8 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev, /* * Complete any pending TLB or cache maintenance on this CPU in case * the thread migrates to a different CPU. + * This full barrier is also required by the membarrier system + * call. */ dsb(ish); diff --git a/include/uapi/linux/membarrier.h b/include/uapi/linux/membarrier.h index e0b108bd2624..6d47b3249d8a 100644 --- a/include/uapi/linux/membarrier.h +++ b/include/uapi/linux/membarrier.h @@ -40,14 +40,33 @@ * (non-running threads are de facto in such a * state). This covers threads from all processes * running on the system. This command returns 0. + * @MEMBARRIER_CMD_PRIVATE_EXPEDITED: + * Execute a memory barrier on each running + * thread belonging to the same process as the current + * thread. Upon return from system call, the + * caller thread is ensured that all its running + * threads siblings have passed through a state + * where all memory accesses to user-space + * addresses match program order between entry + * to and return from the system call + * (non-running threads are de facto in such a + * state). This only covers threads from the + * same processes as the caller thread. This + * command returns 0. The "expedited" commands + * complete faster than the non-expedited ones, + * they never block, but have the downside of + * causing extra overhead. * * Command to be passed to the membarrier system call. The commands need to * be a single bit each, except for MEMBARRIER_CMD_QUERY which is assigned to * the value 0. */ enum membarrier_cmd { - MEMBARRIER_CMD_QUERY = 0, - MEMBARRIER_CMD_SHARED = (1 << 0), + MEMBARRIER_CMD_QUERY = 0, + MEMBARRIER_CMD_SHARED = (1 << 0), + /* reserved for MEMBARRIER_CMD_SHARED_EXPEDITED (1 << 1) */ + /* reserved for MEMBARRIER_CMD_PRIVATE (1 << 2) */ + MEMBARRIER_CMD_PRIVATE_EXPEDITED = (1 << 3), }; #endif /* _UAPI_LINUX_MEMBARRIER_H */ diff --git a/kernel/Makefile b/kernel/Makefile index 4cb8e8b23c6e..9c323a6daa46 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -108,7 +108,6 @@ obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_CONTEXT_TRACKING) += context_tracking.o obj-$(CONFIG_TORTURE_TEST) += torture.o -obj-$(CONFIG_MEMBARRIER) += membarrier.o obj-$(CONFIG_HAS_IOMEM) += memremap.o diff --git a/kernel/membarrier.c b/kernel/membarrier.c deleted file mode 100644 index 9f9284f37f8d..000000000000 --- a/kernel/membarrier.c +++ /dev/null @@ -1,70 +0,0 @@ -/* - * Copyright (C) 2010, 2015 Mathieu Desnoyers - * - * membarrier system call - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ - -#include -#include -#include - -/* - * Bitmask made from a "or" of all commands within enum membarrier_cmd, - * except MEMBARRIER_CMD_QUERY. - */ -#define MEMBARRIER_CMD_BITMASK (MEMBARRIER_CMD_SHARED) - -/** - * sys_membarrier - issue memory barriers on a set of threads - * @cmd: Takes command values defined in enum membarrier_cmd. - * @flags: Currently needs to be 0. For future extensions. - * - * If this system call is not implemented, -ENOSYS is returned. If the - * command specified does not exist, or if the command argument is invalid, - * this system call returns -EINVAL. For a given command, with flags argument - * set to 0, this system call is guaranteed to always return the same value - * until reboot. - * - * All memory accesses performed in program order from each targeted thread - * is guaranteed to be ordered with respect to sys_membarrier(). If we use - * the semantic "barrier()" to represent a compiler barrier forcing memory - * accesses to be performed in program order across the barrier, and - * smp_mb() to represent explicit memory barriers forcing full memory - * ordering across the barrier, we have the following ordering table for - * each pair of barrier(), sys_membarrier() and smp_mb(): - * - * The pair ordering is detailed as (O: ordered, X: not ordered): - * - * barrier() smp_mb() sys_membarrier() - * barrier() X X O - * smp_mb() X O O - * sys_membarrier() O O O - */ -SYSCALL_DEFINE2(membarrier, int, cmd, int, flags) -{ - /* MEMBARRIER_CMD_SHARED is not compatible with nohz_full. */ - if (tick_nohz_full_enabled()) - return -ENOSYS; - if (unlikely(flags)) - return -EINVAL; - switch (cmd) { - case MEMBARRIER_CMD_QUERY: - return MEMBARRIER_CMD_BITMASK; - case MEMBARRIER_CMD_SHARED: - if (num_online_cpus() > 1) - synchronize_sched(); - return 0; - default: - return -EINVAL; - } -} diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 53f0164ed362..78f54932ea1d 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -25,3 +25,4 @@ obj-$(CONFIG_SCHED_DEBUG) += debug.o obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o obj-$(CONFIG_CPU_FREQ) += cpufreq.o obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o +obj-$(CONFIG_MEMBARRIER) += membarrier.o diff --git a/kernel/sched/core.c b/kernel/sched/core.c index bfee6ea7db49..f77269c6c2f8 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2640,6 +2640,16 @@ static struct rq *finish_task_switch(struct task_struct *prev) prev_state = prev->state; vtime_task_switch(prev); perf_event_task_sched_in(prev, current); + /* + * The membarrier system call requires a full memory barrier + * after storing to rq->curr, before going back to user-space. + * + * TODO: This smp_mb__after_unlock_lock can go away if PPC end + * up adding a full barrier to switch_mm(), or we should figure + * out if a smp_mb__after_unlock_lock is really the proper API + * to use. + */ + smp_mb__after_unlock_lock(); finish_lock_switch(rq, prev); finish_arch_post_lock_switch(); @@ -3329,6 +3339,21 @@ static void __sched notrace __schedule(bool preempt) if (likely(prev != next)) { rq->nr_switches++; rq->curr = next; + /* + * The membarrier system call requires each architecture + * to have a full memory barrier after updating + * rq->curr, before returning to user-space. For TSO + * (e.g. x86), the architecture must provide its own + * barrier in switch_mm(). For weakly ordered machines + * for which spin_unlock() acts as a full memory + * barrier, finish_lock_switch() in common code takes + * care of this barrier. For weakly ordered machines for + * which spin_unlock() acts as a RELEASE barrier (only + * arm64 and PowerPC), arm64 has a full barrier in + * switch_to(), and PowerPC has + * smp_mb__after_unlock_lock() before + * finish_lock_switch(). + */ ++*switch_count; trace_sched_switch(preempt, prev, next); diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c new file mode 100644 index 000000000000..a92fddc22747 --- /dev/null +++ b/kernel/sched/membarrier.c @@ -0,0 +1,152 @@ +/* + * Copyright (C) 2010-2017 Mathieu Desnoyers + * + * membarrier system call + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include +#include +#include +#include + +#include "sched.h" /* for cpu_rq(). */ + +/* + * Bitmask made from a "or" of all commands within enum membarrier_cmd, + * except MEMBARRIER_CMD_QUERY. + */ +#define MEMBARRIER_CMD_BITMASK \ + (MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED) + +static void ipi_mb(void *info) +{ + smp_mb(); /* IPIs should be serializing but paranoid. */ +} + +static void membarrier_private_expedited(void) +{ + int cpu; + bool fallback = false; + cpumask_var_t tmpmask; + + if (num_online_cpus() == 1) + return; + + /* + * Matches memory barriers around rq->curr modification in + * scheduler. + */ + smp_mb(); /* system call entry is not a mb. */ + + /* + * Expedited membarrier commands guarantee that they won't + * block, hence the GFP_NOWAIT allocation flag and fallback + * implementation. + */ + if (!zalloc_cpumask_var(&tmpmask, GFP_NOWAIT)) { + /* Fallback for OOM. */ + fallback = true; + } + + cpus_read_lock(); + for_each_online_cpu(cpu) { + struct task_struct *p; + + /* + * Skipping the current CPU is OK even through we can be + * migrated at any point. The current CPU, at the point + * where we read raw_smp_processor_id(), is ensured to + * be in program order with respect to the caller + * thread. Therefore, we can skip this CPU from the + * iteration. + */ + if (cpu == raw_smp_processor_id()) + continue; + rcu_read_lock(); + p = task_rcu_dereference(&cpu_rq(cpu)->curr); + if (p && p->mm == current->mm) { + if (!fallback) + __cpumask_set_cpu(cpu, tmpmask); + else + smp_call_function_single(cpu, ipi_mb, NULL, 1); + } + rcu_read_unlock(); + } + if (!fallback) { + smp_call_function_many(tmpmask, ipi_mb, NULL, 1); + free_cpumask_var(tmpmask); + } + cpus_read_unlock(); + + /* + * Memory barrier on the caller thread _after_ we finished + * waiting for the last IPI. Matches memory barriers around + * rq->curr modification in scheduler. + */ + smp_mb(); /* exit from system call is not a mb */ +} + +/** + * sys_membarrier - issue memory barriers on a set of threads + * @cmd: Takes command values defined in enum membarrier_cmd. + * @flags: Currently needs to be 0. For future extensions. + * + * If this system call is not implemented, -ENOSYS is returned. If the + * command specified does not exist, not available on the running + * kernel, or if the command argument is invalid, this system call + * returns -EINVAL. For a given command, with flags argument set to 0, + * this system call is guaranteed to always return the same value until + * reboot. + * + * All memory accesses performed in program order from each targeted thread + * is guaranteed to be ordered with respect to sys_membarrier(). If we use + * the semantic "barrier()" to represent a compiler barrier forcing memory + * accesses to be performed in program order across the barrier, and + * smp_mb() to represent explicit memory barriers forcing full memory + * ordering across the barrier, we have the following ordering table for + * each pair of barrier(), sys_membarrier() and smp_mb(): + * + * The pair ordering is detailed as (O: ordered, X: not ordered): + * + * barrier() smp_mb() sys_membarrier() + * barrier() X X O + * smp_mb() X O O + * sys_membarrier() O O O + */ +SYSCALL_DEFINE2(membarrier, int, cmd, int, flags) +{ + if (unlikely(flags)) + return -EINVAL; + switch (cmd) { + case MEMBARRIER_CMD_QUERY: + { + int cmd_mask = MEMBARRIER_CMD_BITMASK; + + if (tick_nohz_full_enabled()) + cmd_mask &= ~MEMBARRIER_CMD_SHARED; + return cmd_mask; + } + case MEMBARRIER_CMD_SHARED: + /* MEMBARRIER_CMD_SHARED is not compatible with nohz_full. */ + if (tick_nohz_full_enabled()) + return -EINVAL; + if (num_online_cpus() > 1) + synchronize_sched(); + return 0; + case MEMBARRIER_CMD_PRIVATE_EXPEDITED: + membarrier_private_expedited(); + return 0; + default: + return -EINVAL; + } +} -- cgit v1.2.3-71-gd317 From 0888e372c37fa31882c8ed89fb2f8188b08b6718 Mon Sep 17 00:00:00 2001 From: "Levin, Alexander (Sasha Levin)" Date: Thu, 17 Aug 2017 00:35:11 +0000 Subject: net: inet: diag: expose sockets cgroup classid This is useful for directly looking up a task based on class id rather than having to scan through all open file descriptors. Signed-off-by: Sasha Levin Signed-off-by: David S. Miller --- include/uapi/linux/inet_diag.h | 1 + net/ipv4/inet_diag.c | 11 +++++++++++ 2 files changed, 12 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h index bbe201047df6..678496897a68 100644 --- a/include/uapi/linux/inet_diag.h +++ b/include/uapi/linux/inet_diag.h @@ -142,6 +142,7 @@ enum { INET_DIAG_PAD, INET_DIAG_MARK, INET_DIAG_BBRINFO, + INET_DIAG_CLASS_ID, __INET_DIAG_MAX, }; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 3828b3a805cd..67325d5832d7 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -274,6 +274,17 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, goto errout; } + if (ext & (1 << (INET_DIAG_CLASS_ID - 1))) { + u32 classid = 0; + +#ifdef CONFIG_SOCK_CGROUP_DATA + classid = sock_cgroup_classid(&sk->sk_cgrp_data); +#endif + + if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid)) + goto errout; + } + out: nlmsg_end(skb, nlh); return 0; -- cgit v1.2.3-71-gd317 From 99d1712bc41c7c9a5a473c104a4ad15427757b22 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 8 Aug 2017 15:15:29 +0200 Subject: netfilter: exthdr: tcp option set support This allows setting 2 and 4 byte quantities in the tcp option space. Main purpose is to allow native replacement for xt_TCPMSS to work around pmtu blackholes. Writes to kind and len are now allowed at the moment, it does not seem useful to do this as it causes corruption of the tcp option space. We can always lift this restriction later if a use-case appears. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 4 +- net/netfilter/nft_exthdr.c | 164 ++++++++++++++++++++++++++++++- 2 files changed, 165 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index be25cf69295b..40fd199f7531 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -732,7 +732,8 @@ enum nft_exthdr_op { * @NFTA_EXTHDR_OFFSET: extension header offset (NLA_U32) * @NFTA_EXTHDR_LEN: extension header length (NLA_U32) * @NFTA_EXTHDR_FLAGS: extension header flags (NLA_U32) - * @NFTA_EXTHDR_OP: option match type (NLA_U8) + * @NFTA_EXTHDR_OP: option match type (NLA_U32) + * @NFTA_EXTHDR_SREG: option match type (NLA_U32) */ enum nft_exthdr_attributes { NFTA_EXTHDR_UNSPEC, @@ -742,6 +743,7 @@ enum nft_exthdr_attributes { NFTA_EXTHDR_LEN, NFTA_EXTHDR_FLAGS, NFTA_EXTHDR_OP, + NFTA_EXTHDR_SREG, __NFTA_EXTHDR_MAX }; #define NFTA_EXTHDR_MAX (__NFTA_EXTHDR_MAX - 1) diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index e3a6eebe7e0c..f5a0bf5e3bdd 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -8,6 +8,7 @@ * Development of this code funded by Astaro AG (http://www.astaro.com/) */ +#include #include #include #include @@ -23,6 +24,7 @@ struct nft_exthdr { u8 len; u8 op; enum nft_registers dreg:8; + enum nft_registers sreg:8; u8 flags; }; @@ -124,6 +126,88 @@ err: regs->verdict.code = NFT_BREAK; } +static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + u8 buff[sizeof(struct tcphdr) + MAX_TCP_OPTION_SPACE]; + struct nft_exthdr *priv = nft_expr_priv(expr); + unsigned int i, optl, tcphdr_len, offset; + struct tcphdr *tcph; + u8 *opt; + u32 src; + + tcph = nft_tcp_header_pointer(pkt, sizeof(buff), buff, &tcphdr_len); + if (!tcph) + return; + + opt = (u8 *)tcph; + for (i = sizeof(*tcph); i < tcphdr_len - 1; i += optl) { + union { + u8 octet; + __be16 v16; + __be32 v32; + } old, new; + + optl = optlen(opt, i); + + if (priv->type != opt[i]) + continue; + + if (i + optl > tcphdr_len || priv->len + priv->offset > optl) + return; + + if (!skb_make_writable(pkt->skb, pkt->xt.thoff + i + priv->len)) + return; + + tcph = nft_tcp_header_pointer(pkt, sizeof(buff), buff, + &tcphdr_len); + if (!tcph) + return; + + src = regs->data[priv->sreg]; + offset = i + priv->offset; + + switch (priv->len) { + case 2: + old.v16 = get_unaligned((u16 *)(opt + offset)); + new.v16 = src; + + switch (priv->type) { + case TCPOPT_MSS: + /* increase can cause connection to stall */ + if (ntohs(old.v16) <= ntohs(new.v16)) + return; + break; + } + + if (old.v16 == new.v16) + return; + + put_unaligned(new.v16, (u16*)(opt + offset)); + inet_proto_csum_replace2(&tcph->check, pkt->skb, + old.v16, new.v16, false); + break; + case 4: + new.v32 = src; + old.v32 = get_unaligned((u32 *)(opt + offset)); + + if (old.v32 == new.v32) + return; + + put_unaligned(new.v32, (u32*)(opt + offset)); + inet_proto_csum_replace4(&tcph->check, pkt->skb, + old.v32, new.v32, false); + break; + default: + WARN_ON_ONCE(1); + break; + } + + return; + } +} + static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = { [NFTA_EXTHDR_DREG] = { .type = NLA_U32 }, [NFTA_EXTHDR_TYPE] = { .type = NLA_U8 }, @@ -180,6 +264,55 @@ static int nft_exthdr_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, priv->len); } +static int nft_exthdr_tcp_set_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_exthdr *priv = nft_expr_priv(expr); + u32 offset, len, flags = 0, op = NFT_EXTHDR_OP_IPV6; + int err; + + if (!tb[NFTA_EXTHDR_SREG] || + !tb[NFTA_EXTHDR_TYPE] || + !tb[NFTA_EXTHDR_OFFSET] || + !tb[NFTA_EXTHDR_LEN]) + return -EINVAL; + + if (tb[NFTA_EXTHDR_DREG] || tb[NFTA_EXTHDR_FLAGS]) + return -EINVAL; + + err = nft_parse_u32_check(tb[NFTA_EXTHDR_OFFSET], U8_MAX, &offset); + if (err < 0) + return err; + + err = nft_parse_u32_check(tb[NFTA_EXTHDR_LEN], U8_MAX, &len); + if (err < 0) + return err; + + if (offset < 2) + return -EOPNOTSUPP; + + switch (len) { + case 2: break; + case 4: break; + default: + return -EOPNOTSUPP; + } + + err = nft_parse_u32_check(tb[NFTA_EXTHDR_OP], U8_MAX, &op); + if (err < 0) + return err; + + priv->type = nla_get_u8(tb[NFTA_EXTHDR_TYPE]); + priv->offset = offset; + priv->len = len; + priv->sreg = nft_parse_register(tb[NFTA_EXTHDR_SREG]); + priv->flags = flags; + priv->op = op; + + return nft_validate_register_load(priv->sreg, priv->len); +} + static int nft_exthdr_dump_common(struct sk_buff *skb, const struct nft_exthdr *priv) { if (nla_put_u8(skb, NFTA_EXTHDR_TYPE, priv->type)) @@ -208,6 +341,16 @@ static int nft_exthdr_dump(struct sk_buff *skb, const struct nft_expr *expr) return nft_exthdr_dump_common(skb, priv); } +static int nft_exthdr_dump_set(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_exthdr *priv = nft_expr_priv(expr); + + if (nft_dump_register(skb, NFTA_EXTHDR_SREG, priv->sreg)) + return -1; + + return nft_exthdr_dump_common(skb, priv); +} + static struct nft_expr_type nft_exthdr_type; static const struct nft_expr_ops nft_exthdr_ipv6_ops = { .type = &nft_exthdr_type, @@ -225,6 +368,14 @@ static const struct nft_expr_ops nft_exthdr_tcp_ops = { .dump = nft_exthdr_dump, }; +static const struct nft_expr_ops nft_exthdr_tcp_set_ops = { + .type = &nft_exthdr_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_exthdr)), + .eval = nft_exthdr_tcp_set_eval, + .init = nft_exthdr_tcp_set_init, + .dump = nft_exthdr_dump_set, +}; + static const struct nft_expr_ops * nft_exthdr_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) @@ -234,12 +385,21 @@ nft_exthdr_select_ops(const struct nft_ctx *ctx, if (!tb[NFTA_EXTHDR_OP]) return &nft_exthdr_ipv6_ops; + if (tb[NFTA_EXTHDR_SREG] && tb[NFTA_EXTHDR_DREG]) + return ERR_PTR(-EOPNOTSUPP); + op = ntohl(nla_get_u32(tb[NFTA_EXTHDR_OP])); switch (op) { case NFT_EXTHDR_OP_TCPOPT: - return &nft_exthdr_tcp_ops; + if (tb[NFTA_EXTHDR_SREG]) + return &nft_exthdr_tcp_set_ops; + if (tb[NFTA_EXTHDR_DREG]) + return &nft_exthdr_tcp_ops; + break; case NFT_EXTHDR_OP_IPV6: - return &nft_exthdr_ipv6_ops; + if (tb[NFTA_EXTHDR_DREG]) + return &nft_exthdr_ipv6_ops; + break; } return ERR_PTR(-EOPNOTSUPP); -- cgit v1.2.3-71-gd317 From 6b5dc98e8fac041a3decfc3186e08c1c570ea691 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 8 Aug 2017 15:48:04 +0200 Subject: netfilter: rt: add support to fetch path mss to be used in combination with tcp option set support to mimic iptables TCPMSS --clamp-mss-to-pmtu. v2: Eric Dumazet points out dst must be initialized. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 2 + net/netfilter/nft_rt.c | 66 ++++++++++++++++++++++++++++++++ 2 files changed, 68 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 40fd199f7531..b49da72efa68 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -811,11 +811,13 @@ enum nft_meta_keys { * @NFT_RT_CLASSID: realm value of packet's route (skb->dst->tclassid) * @NFT_RT_NEXTHOP4: routing nexthop for IPv4 * @NFT_RT_NEXTHOP6: routing nexthop for IPv6 + * @NFT_RT_TCPMSS: fetch current path tcp mss */ enum nft_rt_keys { NFT_RT_CLASSID, NFT_RT_NEXTHOP4, NFT_RT_NEXTHOP6, + NFT_RT_TCPMSS, }; /** diff --git a/net/netfilter/nft_rt.c b/net/netfilter/nft_rt.c index c7383d8f88d0..e142e65d3176 100644 --- a/net/netfilter/nft_rt.c +++ b/net/netfilter/nft_rt.c @@ -23,6 +23,42 @@ struct nft_rt { enum nft_registers dreg:8; }; +static u16 get_tcpmss(const struct nft_pktinfo *pkt, const struct dst_entry *skbdst) +{ + u32 minlen = sizeof(struct ipv6hdr), mtu = dst_mtu(skbdst); + const struct sk_buff *skb = pkt->skb; + const struct nf_afinfo *ai; + struct flowi fl; + + memset(&fl, 0, sizeof(fl)); + + switch (nft_pf(pkt)) { + case NFPROTO_IPV4: + fl.u.ip4.daddr = ip_hdr(skb)->saddr; + minlen = sizeof(struct iphdr); + break; + case NFPROTO_IPV6: + fl.u.ip6.daddr = ipv6_hdr(skb)->saddr; + break; + } + + ai = nf_get_afinfo(nft_pf(pkt)); + if (ai) { + struct dst_entry *dst = NULL; + + ai->route(nft_net(pkt), &dst, &fl, false); + if (dst) { + mtu = min(mtu, dst_mtu(dst)); + dst_release(dst); + } + } + + if (mtu <= minlen || mtu > 0xffff) + return TCP_MSS_DEFAULT; + + return mtu - minlen; +} + static void nft_rt_get_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -57,6 +93,9 @@ static void nft_rt_get_eval(const struct nft_expr *expr, &ipv6_hdr(skb)->daddr), sizeof(struct in6_addr)); break; + case NFT_RT_TCPMSS: + nft_reg_store16(dest, get_tcpmss(pkt, dst)); + break; default: WARN_ON(1); goto err; @@ -94,6 +133,9 @@ static int nft_rt_get_init(const struct nft_ctx *ctx, case NFT_RT_NEXTHOP6: len = sizeof(struct in6_addr); break; + case NFT_RT_TCPMSS: + len = sizeof(u16); + break; default: return -EOPNOTSUPP; } @@ -118,6 +160,29 @@ nla_put_failure: return -1; } +static int nft_rt_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, + const struct nft_data **data) +{ + const struct nft_rt *priv = nft_expr_priv(expr); + unsigned int hooks; + + switch (priv->key) { + case NFT_RT_NEXTHOP4: + case NFT_RT_NEXTHOP6: + case NFT_RT_CLASSID: + return 0; + case NFT_RT_TCPMSS: + hooks = (1 << NF_INET_FORWARD) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_POST_ROUTING); + break; + default: + return -EINVAL; + } + + return nft_chain_validate_hooks(ctx->chain, hooks); +} + static struct nft_expr_type nft_rt_type; static const struct nft_expr_ops nft_rt_get_ops = { .type = &nft_rt_type, @@ -125,6 +190,7 @@ static const struct nft_expr_ops nft_rt_get_ops = { .eval = nft_rt_get_eval, .init = nft_rt_get_init, .dump = nft_rt_get_dump, + .validate = nft_rt_validate, }; static struct nft_expr_type nft_rt_type __read_mostly = { -- cgit v1.2.3-71-gd317 From 96eabe7a40aa17e613cf3db2c742ee8b1fc764d0 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 18 Aug 2017 11:28:00 -0700 Subject: bpf: Allow selecting numa node during map creation The current map creation API does not allow to provide the numa-node preference. The memory usually comes from where the map-creation-process is running. The performance is not ideal if the bpf_prog is known to always run in a numa node different from the map-creation-process. One of the use case is sharding on CPU to different LRU maps (i.e. an array of LRU maps). Here is the test result of map_perf_test on the INNER_LRU_HASH_PREALLOC test if we force the lru map used by CPU0 to be allocated from a remote numa node: [ The machine has 20 cores. CPU0-9 at node 0. CPU10-19 at node 1 ] ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1628380 events per sec 4:inner_lru_hash_map_perf pre-alloc 1626396 events per sec 3:inner_lru_hash_map_perf pre-alloc 1626144 events per sec 6:inner_lru_hash_map_perf pre-alloc 1621657 events per sec 2:inner_lru_hash_map_perf pre-alloc 1621534 events per sec 1:inner_lru_hash_map_perf pre-alloc 1620292 events per sec 7:inner_lru_hash_map_perf pre-alloc 1613305 events per sec 0:inner_lru_hash_map_perf pre-alloc 1239150 events per sec #<<< After specifying numa node: ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1629627 events per sec 3:inner_lru_hash_map_perf pre-alloc 1628057 events per sec 1:inner_lru_hash_map_perf pre-alloc 1623054 events per sec 6:inner_lru_hash_map_perf pre-alloc 1616033 events per sec 2:inner_lru_hash_map_perf pre-alloc 1614630 events per sec 4:inner_lru_hash_map_perf pre-alloc 1612651 events per sec 7:inner_lru_hash_map_perf pre-alloc 1609337 events per sec 0:inner_lru_hash_map_perf pre-alloc 1619340 events per sec #<<< This patch adds one field, numa_node, to the bpf_attr. Since numa node 0 is a valid node, a new flag BPF_F_NUMA_NODE is also added. The numa_node field is honored if and only if the BPF_F_NUMA_NODE flag is set. Numa node selection is not supported for percpu map. This patch does not change all the kmalloc. F.e. 'htab = kzalloc()' is not changed since the object is small enough to stay in the cache. Signed-off-by: Martin KaFai Lau Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 10 +++++++++- include/uapi/linux/bpf.h | 10 +++++++++- kernel/bpf/arraymap.c | 7 +++++-- kernel/bpf/devmap.c | 9 ++++++--- kernel/bpf/hashtab.c | 19 +++++++++++++++---- kernel/bpf/lpm_trie.c | 9 +++++++-- kernel/bpf/sockmap.c | 10 +++++++--- kernel/bpf/stackmap.c | 8 +++++--- kernel/bpf/syscall.c | 14 ++++++++++---- 9 files changed, 73 insertions(+), 23 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1cc6c5ff61ec..55b88e329804 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -51,6 +51,7 @@ struct bpf_map { u32 map_flags; u32 pages; u32 id; + int numa_node; struct user_struct *user; const struct bpf_map_ops *ops; struct work_struct work; @@ -264,7 +265,7 @@ struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); int bpf_map_precharge_memlock(u32 pages); -void *bpf_map_area_alloc(size_t size); +void *bpf_map_area_alloc(size_t size, int numa_node); void bpf_map_area_free(void *base); extern int sysctl_unprivileged_bpf_disabled; @@ -316,6 +317,13 @@ struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key); void __dev_map_insert_ctx(struct bpf_map *map, u32 index); void __dev_map_flush(struct bpf_map *map); +/* Return map's numa specified by userspace */ +static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) +{ + return (attr->map_flags & BPF_F_NUMA_NODE) ? + attr->numa_node : NUMA_NO_NODE; +} + #else 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 5ecbe812a2cc..843818dff96d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -165,6 +165,7 @@ enum bpf_attach_type { #define BPF_NOEXIST 1 /* create new element if it didn't exist */ #define BPF_EXIST 2 /* update existing element */ +/* flags for BPF_MAP_CREATE command */ #define BPF_F_NO_PREALLOC (1U << 0) /* Instead of having one common LRU list in the * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list @@ -173,6 +174,8 @@ enum bpf_attach_type { * across different LRU lists. */ #define BPF_F_NO_COMMON_LRU (1U << 1) +/* Specify numa node during map creation */ +#define BPF_F_NUMA_NODE (1U << 2) union bpf_attr { struct { /* anonymous struct used by BPF_MAP_CREATE command */ @@ -180,8 +183,13 @@ union bpf_attr { __u32 key_size; /* size of key in bytes */ __u32 value_size; /* size of value in bytes */ __u32 max_entries; /* max number of entries in a map */ - __u32 map_flags; /* prealloc or not */ + __u32 map_flags; /* BPF_MAP_CREATE related + * flags defined above. + */ __u32 inner_map_fd; /* fd pointing to the inner map */ + __u32 numa_node; /* numa node (effective only if + * BPF_F_NUMA_NODE is set). + */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index d771a3872500..96e9c5c1dfc9 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -49,13 +49,15 @@ static int bpf_array_alloc_percpu(struct bpf_array *array) static struct bpf_map *array_map_alloc(union bpf_attr *attr) { bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; + int numa_node = bpf_map_attr_numa_node(attr); struct bpf_array *array; u64 array_size; u32 elem_size; /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size == 0 || attr->map_flags) + attr->value_size == 0 || attr->map_flags & ~BPF_F_NUMA_NODE || + (percpu && numa_node != NUMA_NO_NODE)) return ERR_PTR(-EINVAL); if (attr->value_size > KMALLOC_MAX_SIZE) @@ -77,7 +79,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) return ERR_PTR(-ENOMEM); /* allocate all map elements and zero-initialize them */ - array = bpf_map_area_alloc(array_size); + array = bpf_map_area_alloc(array_size, numa_node); if (!array) return ERR_PTR(-ENOMEM); @@ -87,6 +89,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) array->map.value_size = attr->value_size; array->map.max_entries = attr->max_entries; array->map.map_flags = attr->map_flags; + array->map.numa_node = numa_node; array->elem_size = elem_size; if (!percpu) diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 18a72a8add43..67f4f00ce33a 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -80,7 +80,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size != 4 || attr->map_flags) + attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) return ERR_PTR(-EINVAL); dtab = kzalloc(sizeof(*dtab), GFP_USER); @@ -93,6 +93,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) dtab->map.value_size = attr->value_size; dtab->map.max_entries = attr->max_entries; dtab->map.map_flags = attr->map_flags; + dtab->map.numa_node = bpf_map_attr_numa_node(attr); err = -ENOMEM; @@ -119,7 +120,8 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) goto free_dtab; dtab->netdev_map = bpf_map_area_alloc(dtab->map.max_entries * - sizeof(struct bpf_dtab_netdev *)); + sizeof(struct bpf_dtab_netdev *), + dtab->map.numa_node); if (!dtab->netdev_map) goto free_dtab; @@ -344,7 +346,8 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, if (!ifindex) { dev = NULL; } else { - dev = kmalloc(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN); + dev = kmalloc_node(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN, + map->numa_node); if (!dev) return -ENOMEM; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 4fb463172aa8..47ae748c3a49 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -18,6 +18,9 @@ #include "bpf_lru_list.h" #include "map_in_map.h" +#define HTAB_CREATE_FLAG_MASK \ + (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE) + struct bucket { struct hlist_nulls_head head; raw_spinlock_t lock; @@ -138,7 +141,8 @@ static int prealloc_init(struct bpf_htab *htab) if (!htab_is_percpu(htab) && !htab_is_lru(htab)) num_entries += num_possible_cpus(); - htab->elems = bpf_map_area_alloc(htab->elem_size * num_entries); + htab->elems = bpf_map_area_alloc(htab->elem_size * num_entries, + htab->map.numa_node); if (!htab->elems) return -ENOMEM; @@ -233,6 +237,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) */ bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU); bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC); + int numa_node = bpf_map_attr_numa_node(attr); struct bpf_htab *htab; int err, i; u64 cost; @@ -248,7 +253,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) */ return ERR_PTR(-EPERM); - if (attr->map_flags & ~(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU)) + if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK) /* reserved bits should not be used */ return ERR_PTR(-EINVAL); @@ -258,6 +263,9 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) if (lru && !prealloc) return ERR_PTR(-ENOTSUPP); + if (numa_node != NUMA_NO_NODE && (percpu || percpu_lru)) + return ERR_PTR(-EINVAL); + htab = kzalloc(sizeof(*htab), GFP_USER); if (!htab) return ERR_PTR(-ENOMEM); @@ -268,6 +276,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) htab->map.value_size = attr->value_size; htab->map.max_entries = attr->max_entries; htab->map.map_flags = attr->map_flags; + htab->map.numa_node = numa_node; /* check sanity of attributes. * value_size == 0 may be allowed in the future to use map as a set @@ -346,7 +355,8 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) err = -ENOMEM; htab->buckets = bpf_map_area_alloc(htab->n_buckets * - sizeof(struct bucket)); + sizeof(struct bucket), + htab->map.numa_node); if (!htab->buckets) goto free_htab; @@ -689,7 +699,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, atomic_dec(&htab->count); return ERR_PTR(-E2BIG); } - l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN); + l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN, + htab->map.numa_node); if (!l_new) return ERR_PTR(-ENOMEM); } diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index b09185f0f17d..1b767844a76f 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -244,7 +244,8 @@ static struct lpm_trie_node *lpm_trie_node_alloc(const struct lpm_trie *trie, if (value) size += trie->map.value_size; - node = kmalloc(size, GFP_ATOMIC | __GFP_NOWARN); + node = kmalloc_node(size, GFP_ATOMIC | __GFP_NOWARN, + trie->map.numa_node); if (!node) return NULL; @@ -405,6 +406,8 @@ static int trie_delete_elem(struct bpf_map *map, void *key) #define LPM_KEY_SIZE_MAX LPM_KEY_SIZE(LPM_DATA_SIZE_MAX) #define LPM_KEY_SIZE_MIN LPM_KEY_SIZE(LPM_DATA_SIZE_MIN) +#define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE) + static struct bpf_map *trie_alloc(union bpf_attr *attr) { struct lpm_trie *trie; @@ -416,7 +419,8 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || - attr->map_flags != BPF_F_NO_PREALLOC || + !(attr->map_flags & BPF_F_NO_PREALLOC) || + attr->map_flags & ~LPM_CREATE_FLAG_MASK || attr->key_size < LPM_KEY_SIZE_MIN || attr->key_size > LPM_KEY_SIZE_MAX || attr->value_size < LPM_VAL_SIZE_MIN || @@ -433,6 +437,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) trie->map.value_size = attr->value_size; trie->map.max_entries = attr->max_entries; trie->map.map_flags = attr->map_flags; + trie->map.numa_node = bpf_map_attr_numa_node(attr); trie->data_size = attr->key_size - offsetof(struct bpf_lpm_trie_key, data); trie->max_prefixlen = trie->data_size * 8; diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 39de541fbcdc..78b2bb9370ac 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -443,7 +443,9 @@ static struct smap_psock *smap_init_psock(struct sock *sock, { struct smap_psock *psock; - psock = kzalloc(sizeof(struct smap_psock), GFP_ATOMIC | __GFP_NOWARN); + psock = kzalloc_node(sizeof(struct smap_psock), + GFP_ATOMIC | __GFP_NOWARN, + stab->map.numa_node); if (!psock) return ERR_PTR(-ENOMEM); @@ -465,7 +467,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size != 4 || attr->map_flags) + attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) return ERR_PTR(-EINVAL); if (attr->value_size > KMALLOC_MAX_SIZE) @@ -481,6 +483,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) stab->map.value_size = attr->value_size; stab->map.max_entries = attr->max_entries; stab->map.map_flags = attr->map_flags; + stab->map.numa_node = bpf_map_attr_numa_node(attr); /* make sure page count doesn't overflow */ cost = (u64) stab->map.max_entries * sizeof(struct sock *); @@ -495,7 +498,8 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) goto free_stab; stab->sock_map = bpf_map_area_alloc(stab->map.max_entries * - sizeof(struct sock *)); + sizeof(struct sock *), + stab->map.numa_node); if (!stab->sock_map) goto free_stab; diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 31147d730abf..135be433e9a0 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -31,7 +31,8 @@ static int prealloc_elems_and_freelist(struct bpf_stack_map *smap) u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size; int err; - smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries); + smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries, + smap->map.numa_node); if (!smap->elems) return -ENOMEM; @@ -59,7 +60,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) if (!capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); - if (attr->map_flags) + if (attr->map_flags & ~BPF_F_NUMA_NODE) return ERR_PTR(-EINVAL); /* check sanity of attributes */ @@ -75,7 +76,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) if (cost >= U32_MAX - PAGE_SIZE) return ERR_PTR(-E2BIG); - smap = bpf_map_area_alloc(cost); + smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr)); if (!smap) return ERR_PTR(-ENOMEM); @@ -91,6 +92,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) smap->map.map_flags = attr->map_flags; smap->n_buckets = n_buckets; smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + smap->map.numa_node = bpf_map_attr_numa_node(attr); err = bpf_map_precharge_memlock(smap->map.pages); if (err) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b8cb1b3c9bfb..9378f3ba2cbf 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -105,7 +105,7 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) return map; } -void *bpf_map_area_alloc(size_t size) +void *bpf_map_area_alloc(size_t size, int numa_node) { /* We definitely need __GFP_NORETRY, so OOM killer doesn't * trigger under memory pressure as we really just want to @@ -115,12 +115,13 @@ void *bpf_map_area_alloc(size_t size) void *area; if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { - area = kmalloc(size, GFP_USER | flags); + area = kmalloc_node(size, GFP_USER | flags, numa_node); if (area != NULL) return area; } - return __vmalloc(size, GFP_KERNEL | flags, PAGE_KERNEL); + return __vmalloc_node_flags_caller(size, numa_node, GFP_KERNEL | flags, + __builtin_return_address(0)); } void bpf_map_area_free(void *area) @@ -309,10 +310,11 @@ int bpf_map_new_fd(struct bpf_map *map) offsetof(union bpf_attr, CMD##_LAST_FIELD) - \ sizeof(attr->CMD##_LAST_FIELD)) != NULL -#define BPF_MAP_CREATE_LAST_FIELD inner_map_fd +#define BPF_MAP_CREATE_LAST_FIELD numa_node /* called via syscall */ static int map_create(union bpf_attr *attr) { + int numa_node = bpf_map_attr_numa_node(attr); struct bpf_map *map; int err; @@ -320,6 +322,10 @@ static int map_create(union bpf_attr *attr) if (err) return -EINVAL; + if (numa_node != NUMA_NO_NODE && + (numa_node >= nr_node_ids || !node_online(numa_node))) + return -EINVAL; + /* find map type and init map: hashtable vs rbtree vs bloom vs ... */ map = find_and_alloc_map(attr); if (IS_ERR(map)) -- cgit v1.2.3-71-gd317 From 9a6b2a87405a5022660022722d4a830b768e8033 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 15 Aug 2017 15:26:25 -0400 Subject: media: cec: rename pin events/function The CEC_EVENT_PIN_LOW/HIGH defines and the cec_queue_pin_event() function did not specify that these were about CEC pin events. Since in the future there will also be HPD pin events it is wise to rename the event defines and function to CEC_EVENT_PIN_CEC_LOW/HIGH and cec_queue_pin_cec_event() now before these become part of the ABI. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst | 2 +- Documentation/media/uapi/cec/cec-ioc-dqevent.rst | 8 ++++---- Documentation/media/uapi/cec/cec-ioc-g-mode.rst | 2 +- drivers/media/cec/cec-adap.c | 7 ++++--- drivers/media/cec/cec-api.c | 4 ++-- drivers/media/cec/cec-pin.c | 5 +++-- include/media/cec.h | 9 +++++---- include/uapi/linux/cec.h | 4 ++-- 8 files changed, 22 insertions(+), 19 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst b/Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst index 0a7aa21f24f4..6c1f6efb822e 100644 --- a/Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst +++ b/Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst @@ -127,7 +127,7 @@ returns the information to the application. The ioctl never fails. - 0x00000080 - The CEC hardware can monitor CEC pin changes from low to high voltage and vice versa. When in pin monitoring mode the application will - receive ``CEC_EVENT_PIN_LOW`` and ``CEC_EVENT_PIN_HIGH`` events. + receive ``CEC_EVENT_PIN_CEC_LOW`` and ``CEC_EVENT_PIN_CEC_HIGH`` events. diff --git a/Documentation/media/uapi/cec/cec-ioc-dqevent.rst b/Documentation/media/uapi/cec/cec-ioc-dqevent.rst index 766d8b0ce431..db615e3405c0 100644 --- a/Documentation/media/uapi/cec/cec-ioc-dqevent.rst +++ b/Documentation/media/uapi/cec/cec-ioc-dqevent.rst @@ -146,16 +146,16 @@ it is guaranteed that the state did change in between the two events. - 2 - Generated if one or more CEC messages were lost because the application didn't dequeue CEC messages fast enough. - * .. _`CEC-EVENT-PIN-LOW`: + * .. _`CEC-EVENT-PIN-CEC-LOW`: - - ``CEC_EVENT_PIN_LOW`` + - ``CEC_EVENT_PIN_CEC_LOW`` - 3 - Generated if the CEC pin goes from a high voltage to a low voltage. Only applies to adapters that have the ``CEC_CAP_MONITOR_PIN`` capability set. - * .. _`CEC-EVENT-PIN-HIGH`: + * .. _`CEC-EVENT-PIN-CEC-HIGH`: - - ``CEC_EVENT_PIN_HIGH`` + - ``CEC_EVENT_PIN_CEC_HIGH`` - 4 - Generated if the CEC pin goes from a low voltage to a high voltage. Only applies to adapters that have the ``CEC_CAP_MONITOR_PIN`` diff --git a/Documentation/media/uapi/cec/cec-ioc-g-mode.rst b/Documentation/media/uapi/cec/cec-ioc-g-mode.rst index 494154e9d449..4d8e0647e832 100644 --- a/Documentation/media/uapi/cec/cec-ioc-g-mode.rst +++ b/Documentation/media/uapi/cec/cec-ioc-g-mode.rst @@ -159,7 +159,7 @@ Available follower modes are: This mode requires that the :ref:`CEC_CAP_MONITOR_PIN ` capability is set, otherwise the ``EINVAL`` error code is returned. While in pin monitoring mode this file descriptor can receive the - ``CEC_EVENT_PIN_LOW`` and ``CEC_EVENT_PIN_HIGH`` events to see the + ``CEC_EVENT_PIN_CEC_LOW`` and ``CEC_EVENT_PIN_CEC_HIGH`` events to see the low-level CEC pin transitions. This is very useful for debugging. This mode is only allowed if the process has the ``CAP_NET_ADMIN`` capability. If that is not set, then the ``EPERM`` error code is returned. diff --git a/drivers/media/cec/cec-adap.c b/drivers/media/cec/cec-adap.c index 8ac39ddf892c..d9adeb505c09 100644 --- a/drivers/media/cec/cec-adap.c +++ b/drivers/media/cec/cec-adap.c @@ -154,10 +154,11 @@ static void cec_queue_event(struct cec_adapter *adap, } /* Notify userspace that the CEC pin changed state at the given time. */ -void cec_queue_pin_event(struct cec_adapter *adap, bool is_high, ktime_t ts) +void cec_queue_pin_cec_event(struct cec_adapter *adap, bool is_high, ktime_t ts) { struct cec_event ev = { - .event = is_high ? CEC_EVENT_PIN_HIGH : CEC_EVENT_PIN_LOW, + .event = is_high ? CEC_EVENT_PIN_CEC_HIGH : + CEC_EVENT_PIN_CEC_LOW, }; struct cec_fh *fh; @@ -167,7 +168,7 @@ void cec_queue_pin_event(struct cec_adapter *adap, bool is_high, ktime_t ts) cec_queue_event_fh(fh, &ev, ktime_to_ns(ts)); mutex_unlock(&adap->devnode.lock); } -EXPORT_SYMBOL_GPL(cec_queue_pin_event); +EXPORT_SYMBOL_GPL(cec_queue_pin_cec_event); /* * Queue a new message for this filehandle. diff --git a/drivers/media/cec/cec-api.c b/drivers/media/cec/cec-api.c index 00d43d74020f..87649b0c6381 100644 --- a/drivers/media/cec/cec-api.c +++ b/drivers/media/cec/cec-api.c @@ -449,8 +449,8 @@ static long cec_s_mode(struct cec_adapter *adap, struct cec_fh *fh, .flags = CEC_EVENT_FL_INITIAL_STATE, }; - ev.event = adap->pin->cur_value ? CEC_EVENT_PIN_HIGH : - CEC_EVENT_PIN_LOW; + ev.event = adap->pin->cur_value ? CEC_EVENT_PIN_CEC_HIGH : + CEC_EVENT_PIN_CEC_LOW; cec_queue_event_fh(fh, &ev, 0); #endif adap->monitor_pin_cnt++; diff --git a/drivers/media/cec/cec-pin.c b/drivers/media/cec/cec-pin.c index 03f800e5ec1f..31a26d3b8bd8 100644 --- a/drivers/media/cec/cec-pin.c +++ b/drivers/media/cec/cec-pin.c @@ -609,8 +609,9 @@ static int cec_pin_thread_func(void *_adap) while (atomic_read(&pin->work_pin_events)) { unsigned int idx = pin->work_pin_events_rd; - cec_queue_pin_event(adap, pin->work_pin_is_high[idx], - pin->work_pin_ts[idx]); + cec_queue_pin_cec_event(adap, + pin->work_pin_is_high[idx], + pin->work_pin_ts[idx]); pin->work_pin_events_rd = (idx + 1) % CEC_NUM_PIN_EVENTS; atomic_dec(&pin->work_pin_events); } diff --git a/include/media/cec.h b/include/media/cec.h index 1bec7bde4792..224359c9941a 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -91,7 +91,7 @@ struct cec_event_entry { }; #define CEC_NUM_CORE_EVENTS 2 -#define CEC_NUM_EVENTS CEC_EVENT_PIN_HIGH +#define CEC_NUM_EVENTS CEC_EVENT_PIN_CEC_HIGH struct cec_fh { struct list_head list; @@ -280,14 +280,15 @@ static inline void cec_received_msg(struct cec_adapter *adap, } /** - * cec_queue_pin_event() - queue a pin event with a given timestamp. + * cec_queue_pin_cec_event() - queue a CEC pin event with a given timestamp. * * @adap: pointer to the cec adapter - * @is_high: when true the pin is high, otherwise it is low + * @is_high: when true the CEC pin is high, otherwise it is low * @ts: the timestamp for this event * */ -void cec_queue_pin_event(struct cec_adapter *adap, bool is_high, ktime_t ts); +void cec_queue_pin_cec_event(struct cec_adapter *adap, + bool is_high, ktime_t ts); /** * cec_get_edid_phys_addr() - find and return the physical address diff --git a/include/uapi/linux/cec.h b/include/uapi/linux/cec.h index d87a67b0bb06..4351c3481aea 100644 --- a/include/uapi/linux/cec.h +++ b/include/uapi/linux/cec.h @@ -408,8 +408,8 @@ struct cec_log_addrs { * didn't empty the message queue in time */ #define CEC_EVENT_LOST_MSGS 2 -#define CEC_EVENT_PIN_LOW 3 -#define CEC_EVENT_PIN_HIGH 4 +#define CEC_EVENT_PIN_CEC_LOW 3 +#define CEC_EVENT_PIN_CEC_HIGH 4 #define CEC_EVENT_FL_INITIAL_STATE (1 << 0) #define CEC_EVENT_FL_DROPPED_EVENTS (1 << 1) -- cgit v1.2.3-71-gd317 From 84e54fe0a5eaed696dee4019c396f8396f5a908b Mon Sep 17 00:00:00 2001 From: William Tu Date: Tue, 22 Aug 2017 09:40:28 -0700 Subject: gre: introduce native tunnel support for ERSPAN The patch adds ERSPAN type II tunnel support. The implementation is based on the draft at [1]. One of the purposes is for Linux box to be able to receive ERSPAN monitoring traffic sent from the Cisco switch, by creating a ERSPAN tunnel device. In addition, the patch also adds ERSPAN TX, so Linux virtual switch can redirect monitored traffic to the ERSPAN tunnel device. The traffic will be encapsulated into ERSPAN and sent out. The implementation reuses tunnel key as ERSPAN session ID, and field 'erspan' as ERSPAN Index fields: ./ip link add dev ers11 type erspan seq key 100 erspan 123 \ local 172.16.1.200 remote 172.16.1.100 To use the above device as ERSPAN receiver, configure Nexus 5000 switch as below: monitor session 100 type erspan-source erspan-id 123 vrf default destination ip 172.16.1.200 source interface Ethernet1/11 both source interface Ethernet1/12 both no shut monitor erspan origin ip-address 172.16.1.100 global [1] https://tools.ietf.org/html/draft-foschiano-erspan-01 [2] iproute2 patch: http://marc.info/?l=linux-netdev&m=150306086924951&w=2 [3] test script: http://marc.info/?l=linux-netdev&m=150231021807304&w=2 Signed-off-by: William Tu Signed-off-by: Meenakshi Vohra Cc: Alexey Kuznetsov Cc: Hideaki YOSHIFUJI Signed-off-by: David S. Miller --- include/net/erspan.h | 61 ++++++++++ include/net/ip_tunnels.h | 3 + include/uapi/linux/if_ether.h | 1 + include/uapi/linux/if_tunnel.h | 1 + net/ipv4/ip_gre.c | 269 +++++++++++++++++++++++++++++++++++++++++ 5 files changed, 335 insertions(+) create mode 100644 include/net/erspan.h (limited to 'include/uapi/linux') diff --git a/include/net/erspan.h b/include/net/erspan.h new file mode 100644 index 000000000000..ca94fc86865e --- /dev/null +++ b/include/net/erspan.h @@ -0,0 +1,61 @@ +#ifndef __LINUX_ERSPAN_H +#define __LINUX_ERSPAN_H + +/* + * GRE header for ERSPAN encapsulation (8 octets [34:41]) -- 8 bytes + * 0 1 2 3 + * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * |0|0|0|1|0|00000|000000000|00000| Protocol Type for ERSPAN | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Sequence Number (increments per packet per session) | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * Note that in the above GRE header [RFC1701] out of the C, R, K, S, + * s, Recur, Flags, Version fields only S (bit 03) is set to 1. The + * other fields are set to zero, so only a sequence number follows. + * + * ERSPAN Type II header (8 octets [42:49]) + * 0 1 2 3 + * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Ver | VLAN | COS | En|T| Session ID | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Reserved | Index | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * GRE proto ERSPAN type II = 0x88BE, type III = 0x22EB + */ + +#define ERSPAN_VERSION 0x1 + +#define VER_MASK 0xf000 +#define VLAN_MASK 0x0fff +#define COS_MASK 0xe000 +#define EN_MASK 0x1800 +#define T_MASK 0x0400 +#define ID_MASK 0x03ff +#define INDEX_MASK 0xfffff + +enum erspan_encap_type { + ERSPAN_ENCAP_NOVLAN = 0x0, /* originally without VLAN tag */ + ERSPAN_ENCAP_ISL = 0x1, /* originally ISL encapsulated */ + ERSPAN_ENCAP_8021Q = 0x2, /* originally 802.1Q encapsulated */ + ERSPAN_ENCAP_INFRAME = 0x3, /* VLAN tag perserved in frame */ +}; + +struct erspan_metadata { + __be32 index; /* type II */ +}; + +struct erspanhdr { + __be16 ver_vlan; +#define VER_OFFSET 12 + __be16 session_id; +#define COS_OFFSET 13 +#define EN_OFFSET 11 +#define T_OFFSET 10 + struct erspan_metadata md; +}; + +#endif diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 520809912f03..625c29329372 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -115,6 +115,9 @@ struct ip_tunnel { u32 o_seqno; /* The last output seqno */ int tun_hlen; /* Precalculated header length */ + /* This field used only by ERSPAN */ + u32 index; /* ERSPAN type II index */ + struct dst_cache dst_cache; struct ip_tunnel_parm parms; diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 5bc9bfd816b7..efeb1190c2ca 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -66,6 +66,7 @@ #define ETH_P_ATALK 0x809B /* Appletalk DDP */ #define ETH_P_AARP 0x80F3 /* Appletalk AARP */ #define ETH_P_8021Q 0x8100 /* 802.1Q VLAN Extended Header */ +#define ETH_P_ERSPAN 0x88BE /* ERSPAN type II */ #define ETH_P_IPX 0x8137 /* IPX over DIX */ #define ETH_P_IPV6 0x86DD /* IPv6 over bluebook */ #define ETH_P_PAUSE 0x8808 /* IEEE Pause frames. See 802.3 31B */ diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 6792d1967d31..2e520883c054 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -134,6 +134,7 @@ enum { IFLA_GRE_COLLECT_METADATA, IFLA_GRE_IGNORE_DF, IFLA_GRE_FWMARK, + IFLA_GRE_ERSPAN_INDEX, __IFLA_GRE_MAX, }; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 7a7829e839c2..6e8a62289e03 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -48,6 +48,7 @@ #include #include #include +#include /* Problems & solutions @@ -115,6 +116,7 @@ static int ipgre_tunnel_init(struct net_device *dev); static unsigned int ipgre_net_id __read_mostly; static unsigned int gre_tap_net_id __read_mostly; +static unsigned int erspan_net_id __read_mostly; static void ipgre_err(struct sk_buff *skb, u32 info, const struct tnl_ptk_info *tpi) @@ -246,6 +248,56 @@ static void gre_err(struct sk_buff *skb, u32 info) ipgre_err(skb, info, &tpi); } +static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, + int gre_hdr_len) +{ + struct net *net = dev_net(skb->dev); + struct metadata_dst *tun_dst = NULL; + struct ip_tunnel_net *itn; + struct ip_tunnel *tunnel; + struct erspanhdr *ershdr; + const struct iphdr *iph; + __be32 session_id; + __be32 index; + int len; + + itn = net_generic(net, erspan_net_id); + iph = ip_hdr(skb); + len = gre_hdr_len + sizeof(*ershdr); + + if (unlikely(!pskb_may_pull(skb, len))) + return -ENOMEM; + + iph = ip_hdr(skb); + ershdr = (struct erspanhdr *)(skb->data + gre_hdr_len); + + /* The original GRE header does not have key field, + * Use ERSPAN 10-bit session ID as key. + */ + session_id = cpu_to_be32(ntohs(ershdr->session_id)); + tpi->key = session_id; + index = ershdr->md.index; + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, + tpi->flags | TUNNEL_KEY, + iph->saddr, iph->daddr, tpi->key); + + if (tunnel) { + if (__iptunnel_pull_header(skb, + gre_hdr_len + sizeof(*ershdr), + htons(ETH_P_TEB), + false, false) < 0) + goto drop; + + tunnel->index = ntohl(index); + skb_reset_mac_header(skb); + ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); + return PACKET_RCVD; + } +drop: + kfree_skb(skb); + return PACKET_RCVD; +} + static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct ip_tunnel_net *itn, int hdr_len, bool raw_proto) { @@ -328,6 +380,11 @@ static int gre_rcv(struct sk_buff *skb) if (hdr_len < 0) goto drop; + if (unlikely(tpi.proto == htons(ETH_P_ERSPAN))) { + if (erspan_rcv(skb, &tpi, hdr_len) == PACKET_RCVD) + return 0; + } + if (ipgre_rcv(skb, &tpi, hdr_len) == PACKET_RCVD) return 0; @@ -503,6 +560,81 @@ free_skb: return NETDEV_TX_OK; } +static inline u8 tos_to_cos(u8 tos) +{ + u8 dscp, cos; + + dscp = tos >> 2; + cos = dscp >> 3; + return cos; +} + +static void erspan_build_header(struct sk_buff *skb, + __be32 id, u32 index, bool truncate) +{ + struct iphdr *iphdr = ip_hdr(skb); + struct ethhdr *eth = eth_hdr(skb); + enum erspan_encap_type enc_type; + struct erspanhdr *ershdr; + struct qtag_prefix { + __be16 eth_type; + __be16 tci; + } *qp; + u16 vlan_tci = 0; + + enc_type = ERSPAN_ENCAP_NOVLAN; + + /* If mirrored packet has vlan tag, extract tci and + * perserve vlan header in the mirrored frame. + */ + if (eth->h_proto == htons(ETH_P_8021Q)) { + qp = (struct qtag_prefix *)(skb->data + 2 * ETH_ALEN); + vlan_tci = ntohs(qp->tci); + enc_type = ERSPAN_ENCAP_INFRAME; + } + + skb_push(skb, sizeof(*ershdr)); + ershdr = (struct erspanhdr *)skb->data; + memset(ershdr, 0, sizeof(*ershdr)); + + ershdr->ver_vlan = htons((vlan_tci & VLAN_MASK) | + (ERSPAN_VERSION << VER_OFFSET)); + ershdr->session_id = htons((u16)(ntohl(id) & ID_MASK) | + ((tos_to_cos(iphdr->tos) << COS_OFFSET) & COS_MASK) | + (enc_type << EN_OFFSET & EN_MASK) | + ((truncate << T_OFFSET) & T_MASK)); + ershdr->md.index = htonl(index & INDEX_MASK); +} + +static netdev_tx_t erspan_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + bool truncate = false; + + if (gre_handle_offloads(skb, false)) + goto free_skb; + + if (skb_cow_head(skb, dev->needed_headroom)) + goto free_skb; + + if (skb->len > dev->mtu) { + pskb_trim(skb, dev->mtu); + truncate = true; + } + + /* Push ERSPAN header */ + erspan_build_header(skb, tunnel->parms.o_key, tunnel->index, truncate); + tunnel->parms.o_flags &= ~TUNNEL_KEY; + __gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_ERSPAN)); + return NETDEV_TX_OK; + +free_skb: + kfree_skb(skb); + dev->stats.tx_dropped++; + return NETDEV_TX_OK; +} + static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -828,6 +960,39 @@ out: return ipgre_tunnel_validate(tb, data, extack); } +static int erspan_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + __be16 flags = 0; + int ret; + + if (!data) + return 0; + + ret = ipgre_tap_validate(tb, data, extack); + if (ret) + return ret; + + /* ERSPAN should only have GRE sequence and key flag */ + flags |= nla_get_be16(data[IFLA_GRE_OFLAGS]); + flags |= nla_get_be16(data[IFLA_GRE_IFLAGS]); + if (flags != (GRE_SEQ | GRE_KEY)) + return -EINVAL; + + /* ERSPAN Session ID only has 10-bit. Since we reuse + * 32-bit key field as ID, check it's range. + */ + if (data[IFLA_GRE_IKEY] && + (ntohl(nla_get_be32(data[IFLA_GRE_IKEY])) & ~ID_MASK)) + return -EINVAL; + + if (data[IFLA_GRE_OKEY] && + (ntohl(nla_get_be32(data[IFLA_GRE_OKEY])) & ~ID_MASK)) + return -EINVAL; + + return 0; +} + static int ipgre_netlink_parms(struct net_device *dev, struct nlattr *data[], struct nlattr *tb[], @@ -892,6 +1057,13 @@ static int ipgre_netlink_parms(struct net_device *dev, if (data[IFLA_GRE_FWMARK]) *fwmark = nla_get_u32(data[IFLA_GRE_FWMARK]); + if (data[IFLA_GRE_ERSPAN_INDEX]) { + t->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]); + + if (t->index & ~INDEX_MASK) + return -EINVAL; + } + return 0; } @@ -949,6 +1121,36 @@ static const struct net_device_ops gre_tap_netdev_ops = { .ndo_fill_metadata_dst = gre_fill_metadata_dst, }; +static int erspan_tunnel_init(struct net_device *dev) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + int t_hlen; + + tunnel->tun_hlen = 8; + tunnel->parms.iph.protocol = IPPROTO_GRE; + t_hlen = tunnel->hlen + sizeof(struct iphdr) + sizeof(struct erspanhdr); + + dev->needed_headroom = LL_MAX_HEADER + t_hlen + 4; + dev->mtu = ETH_DATA_LEN - t_hlen - 4; + dev->features |= GRE_FEATURES; + dev->hw_features |= GRE_FEATURES; + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + + return ip_tunnel_init(dev); +} + +static const struct net_device_ops erspan_netdev_ops = { + .ndo_init = erspan_tunnel_init, + .ndo_uninit = ip_tunnel_uninit, + .ndo_start_xmit = erspan_xmit, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, + .ndo_change_mtu = ip_tunnel_change_mtu, + .ndo_get_stats64 = ip_tunnel_get_stats64, + .ndo_get_iflink = ip_tunnel_get_iflink, + .ndo_fill_metadata_dst = gre_fill_metadata_dst, +}; + static void ipgre_tap_setup(struct net_device *dev) { ether_setup(dev); @@ -1041,6 +1243,8 @@ static size_t ipgre_get_size(const struct net_device *dev) nla_total_size(1) + /* IFLA_GRE_FWMARK */ nla_total_size(4) + + /* IFLA_GRE_ERSPAN_INDEX */ + nla_total_size(4) + 0; } @@ -1083,12 +1287,25 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) goto nla_put_failure; } + if (t->index) + if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index)) + goto nla_put_failure; + return 0; nla_put_failure: return -EMSGSIZE; } +static void erspan_setup(struct net_device *dev) +{ + ether_setup(dev); + dev->netdev_ops = &erspan_netdev_ops; + dev->priv_flags &= ~IFF_TX_SKB_SHARING; + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + ip_tunnel_setup(dev, erspan_net_id); +} + static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = { [IFLA_GRE_LINK] = { .type = NLA_U32 }, [IFLA_GRE_IFLAGS] = { .type = NLA_U16 }, @@ -1107,6 +1324,7 @@ static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = { [IFLA_GRE_COLLECT_METADATA] = { .type = NLA_FLAG }, [IFLA_GRE_IGNORE_DF] = { .type = NLA_U8 }, [IFLA_GRE_FWMARK] = { .type = NLA_U32 }, + [IFLA_GRE_ERSPAN_INDEX] = { .type = NLA_U32 }, }; static struct rtnl_link_ops ipgre_link_ops __read_mostly = { @@ -1139,6 +1357,21 @@ static struct rtnl_link_ops ipgre_tap_ops __read_mostly = { .get_link_net = ip_tunnel_get_link_net, }; +static struct rtnl_link_ops erspan_link_ops __read_mostly = { + .kind = "erspan", + .maxtype = IFLA_GRE_MAX, + .policy = ipgre_policy, + .priv_size = sizeof(struct ip_tunnel), + .setup = erspan_setup, + .validate = erspan_validate, + .newlink = ipgre_newlink, + .changelink = ipgre_changelink, + .dellink = ip_tunnel_dellink, + .get_size = ipgre_get_size, + .fill_info = ipgre_fill_info, + .get_link_net = ip_tunnel_get_link_net, +}; + struct net_device *gretap_fb_dev_create(struct net *net, const char *name, u8 name_assign_type) { @@ -1202,6 +1435,26 @@ static struct pernet_operations ipgre_tap_net_ops = { .size = sizeof(struct ip_tunnel_net), }; +static int __net_init erspan_init_net(struct net *net) +{ + return ip_tunnel_init_net(net, erspan_net_id, + &erspan_link_ops, "erspan0"); +} + +static void __net_exit erspan_exit_net(struct net *net) +{ + struct ip_tunnel_net *itn = net_generic(net, erspan_net_id); + + ip_tunnel_delete_net(itn, &erspan_link_ops); +} + +static struct pernet_operations erspan_net_ops = { + .init = erspan_init_net, + .exit = erspan_exit_net, + .id = &erspan_net_id, + .size = sizeof(struct ip_tunnel_net), +}; + static int __init ipgre_init(void) { int err; @@ -1216,6 +1469,10 @@ static int __init ipgre_init(void) if (err < 0) goto pnet_tap_faied; + err = register_pernet_device(&erspan_net_ops); + if (err < 0) + goto pnet_erspan_failed; + err = gre_add_protocol(&ipgre_protocol, GREPROTO_CISCO); if (err < 0) { pr_info("%s: can't add protocol\n", __func__); @@ -1230,13 +1487,21 @@ static int __init ipgre_init(void) if (err < 0) goto tap_ops_failed; + err = rtnl_link_register(&erspan_link_ops); + if (err < 0) + goto erspan_link_failed; + return 0; +erspan_link_failed: + rtnl_link_unregister(&ipgre_tap_ops); tap_ops_failed: rtnl_link_unregister(&ipgre_link_ops); rtnl_link_failed: gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); add_proto_failed: + unregister_pernet_device(&erspan_net_ops); +pnet_erspan_failed: unregister_pernet_device(&ipgre_tap_net_ops); pnet_tap_faied: unregister_pernet_device(&ipgre_net_ops); @@ -1247,9 +1512,11 @@ static void __exit ipgre_fini(void) { rtnl_link_unregister(&ipgre_tap_ops); rtnl_link_unregister(&ipgre_link_ops); + rtnl_link_unregister(&erspan_link_ops); gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); unregister_pernet_device(&ipgre_tap_net_ops); unregister_pernet_device(&ipgre_net_ops); + unregister_pernet_device(&erspan_net_ops); } module_init(ipgre_init); @@ -1257,5 +1524,7 @@ module_exit(ipgre_fini); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("gre"); MODULE_ALIAS_RTNL_LINK("gretap"); +MODULE_ALIAS_RTNL_LINK("erspan"); MODULE_ALIAS_NETDEV("gre0"); MODULE_ALIAS_NETDEV("gretap0"); +MODULE_ALIAS_NETDEV("erspan0"); -- cgit v1.2.3-71-gd317 From 5cdcf4c6a638591ec0e98c57404a19e7f9997567 Mon Sep 17 00:00:00 2001 From: Martijn Coenen Date: Fri, 28 Jul 2017 13:56:06 +0200 Subject: ANDROID: binder: add padding to binder_fd_array_object. binder_fd_array_object starts with a 4-byte header, followed by a few fields that are 8 bytes when ANDROID_BINDER_IPC_32BIT=N. This can cause alignment issues in a 64-bit kernel with a 32-bit userspace, as on x86_32 an 8-byte primitive may be aligned to a 4-byte address. Pad with a __u32 to fix this. Signed-off-by: Martijn Coenen Cc: stable # 4.11+ Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/android/binder.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h index 51f891fb1b18..7668b5791c91 100644 --- a/include/uapi/linux/android/binder.h +++ b/include/uapi/linux/android/binder.h @@ -132,6 +132,7 @@ enum { /* struct binder_fd_array_object - object describing an array of fds in a buffer * @hdr: common header structure + * @pad: padding to ensure correct alignment * @num_fds: number of file descriptors in the buffer * @parent: index in offset array to buffer holding the fd array * @parent_offset: start offset of fd array in the buffer @@ -152,6 +153,7 @@ enum { */ struct binder_fd_array_object { struct binder_object_header hdr; + __u32 pad; binder_size_t num_fds; binder_size_t parent; binder_size_t parent_offset; -- cgit v1.2.3-71-gd317 From 1e6ec9ea89d30739b9447c1860fcb07fc29f3aef Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Wed, 23 Aug 2017 14:54:59 -0700 Subject: Revert "loop: support 4k physical blocksize" There's some stuff still up in the air, let's not get stuck with a subpar ABI. I'll follow up with something better for 4.14. Signed-off-by: Omar Sandoval Signed-off-by: Jens Axboe --- drivers/block/loop.c | 42 ++++++------------------------------------ drivers/block/loop.h | 1 - include/uapi/linux/loop.h | 3 --- 3 files changed, 6 insertions(+), 40 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/block/loop.c b/drivers/block/loop.c index ef8334949b42..f321b96405f5 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -221,8 +221,7 @@ static void __loop_update_dio(struct loop_device *lo, bool dio) } static int -figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit, - loff_t logical_blocksize) +figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit) { loff_t size = get_size(offset, sizelimit, lo->lo_backing_file); sector_t x = (sector_t)size; @@ -234,12 +233,6 @@ figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit, lo->lo_offset = offset; if (lo->lo_sizelimit != sizelimit) lo->lo_sizelimit = sizelimit; - if (lo->lo_flags & LO_FLAGS_BLOCKSIZE) { - lo->lo_logical_blocksize = logical_blocksize; - blk_queue_physical_block_size(lo->lo_queue, lo->lo_blocksize); - blk_queue_logical_block_size(lo->lo_queue, - lo->lo_logical_blocksize); - } set_capacity(lo->lo_disk, x); bd_set_size(bdev, (loff_t)get_capacity(bdev->bd_disk) << 9); /* let user-space know about the new size */ @@ -820,7 +813,6 @@ static void loop_config_discard(struct loop_device *lo) struct file *file = lo->lo_backing_file; struct inode *inode = file->f_mapping->host; struct request_queue *q = lo->lo_queue; - int lo_bits = 9; /* * We use punch hole to reclaim the free space used by the @@ -840,11 +832,9 @@ static void loop_config_discard(struct loop_device *lo) q->limits.discard_granularity = inode->i_sb->s_blocksize; q->limits.discard_alignment = 0; - if (lo->lo_flags & LO_FLAGS_BLOCKSIZE) - lo_bits = blksize_bits(lo->lo_logical_blocksize); - blk_queue_max_discard_sectors(q, UINT_MAX >> lo_bits); - blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> lo_bits); + blk_queue_max_discard_sectors(q, UINT_MAX >> 9); + blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9); queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q); } @@ -938,7 +928,6 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, lo->use_dio = false; lo->lo_blocksize = lo_blocksize; - lo->lo_logical_blocksize = 512; lo->lo_device = bdev; lo->lo_flags = lo_flags; lo->lo_backing_file = file; @@ -1104,7 +1093,6 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) int err; struct loop_func_table *xfer; kuid_t uid = current_uid(); - int lo_flags = lo->lo_flags; if (lo->lo_encrypt_key_size && !uid_eq(lo->lo_key_owner, uid) && @@ -1137,26 +1125,9 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) if (err) goto exit; - if (info->lo_flags & LO_FLAGS_BLOCKSIZE) { - if (!(lo->lo_flags & LO_FLAGS_BLOCKSIZE)) - lo->lo_logical_blocksize = 512; - lo->lo_flags |= LO_FLAGS_BLOCKSIZE; - if (LO_INFO_BLOCKSIZE(info) != 512 && - LO_INFO_BLOCKSIZE(info) != 1024 && - LO_INFO_BLOCKSIZE(info) != 2048 && - LO_INFO_BLOCKSIZE(info) != 4096) - return -EINVAL; - if (LO_INFO_BLOCKSIZE(info) > lo->lo_blocksize) - return -EINVAL; - } - if (lo->lo_offset != info->lo_offset || - lo->lo_sizelimit != info->lo_sizelimit || - lo->lo_flags != lo_flags || - ((lo->lo_flags & LO_FLAGS_BLOCKSIZE) && - lo->lo_logical_blocksize != LO_INFO_BLOCKSIZE(info))) { - if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit, - LO_INFO_BLOCKSIZE(info))) { + lo->lo_sizelimit != info->lo_sizelimit) { + if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit)) { err = -EFBIG; goto exit; } @@ -1348,8 +1319,7 @@ static int loop_set_capacity(struct loop_device *lo) if (unlikely(lo->lo_state != Lo_bound)) return -ENXIO; - return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit, - lo->lo_logical_blocksize); + return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit); } static int loop_set_dio(struct loop_device *lo, unsigned long arg) diff --git a/drivers/block/loop.h b/drivers/block/loop.h index 2c096b9a17b8..fecd3f97ef8c 100644 --- a/drivers/block/loop.h +++ b/drivers/block/loop.h @@ -49,7 +49,6 @@ struct loop_device { struct file * lo_backing_file; struct block_device *lo_device; unsigned lo_blocksize; - unsigned lo_logical_blocksize; void *key_data; gfp_t old_gfp_mask; diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h index a3960f98679c..c8125ec1f4f2 100644 --- a/include/uapi/linux/loop.h +++ b/include/uapi/linux/loop.h @@ -22,7 +22,6 @@ enum { LO_FLAGS_AUTOCLEAR = 4, LO_FLAGS_PARTSCAN = 8, LO_FLAGS_DIRECT_IO = 16, - LO_FLAGS_BLOCKSIZE = 32, }; #include /* for __kernel_old_dev_t */ @@ -60,8 +59,6 @@ struct loop_info64 { __u64 lo_init[2]; }; -#define LO_INFO_BLOCKSIZE(l) (l)->lo_init[0] - /* * Loop filter types */ -- cgit v1.2.3-71-gd317 From ecda85e70277ef24e44a1f6bc00243cebd19f985 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Wed, 16 Aug 2017 19:31:57 +0200 Subject: x86/lguest: Remove lguest support Lguest seems to be rather unused these days. It has seen only patches ensuring it still builds the last two years and its official state is "Odd Fixes". Remove it in order to be able to clean up the paravirt code. Signed-off-by: Juergen Gross Acked-by: Rusty Russell Acked-by: Thomas Gleixner Cc: Linus Torvalds Cc: Peter Zijlstra Cc: boris.ostrovsky@oracle.com Cc: lguest@lists.ozlabs.org Cc: rusty@rustcorp.com.au Cc: xen-devel@lists.xenproject.org Link: http://lkml.kernel.org/r/20170816173157.8633-3-jgross@suse.com Signed-off-by: Ingo Molnar --- MAINTAINERS | 11 - arch/x86/Kbuild | 3 - arch/x86/Kconfig | 2 - arch/x86/include/asm/lguest.h | 91 - arch/x86/include/asm/lguest_hcall.h | 74 - arch/x86/include/asm/processor.h | 2 +- arch/x86/include/uapi/asm/bootparam.h | 2 +- arch/x86/kernel/asm-offsets_32.c | 20 - arch/x86/kernel/head_32.S | 2 - arch/x86/kernel/platform-quirks.c | 1 - arch/x86/kvm/Kconfig | 1 - arch/x86/lguest/Kconfig | 14 - arch/x86/lguest/Makefile | 2 - arch/x86/lguest/boot.c | 1558 --------------- arch/x86/lguest/head_32.S | 192 -- drivers/Makefile | 1 - drivers/block/Kconfig | 2 +- drivers/char/Kconfig | 2 +- drivers/char/virtio_console.c | 2 +- drivers/lguest/Kconfig | 13 - drivers/lguest/Makefile | 26 - drivers/lguest/README | 47 - drivers/lguest/core.c | 398 ---- drivers/lguest/hypercalls.c | 304 --- drivers/lguest/interrupts_and_traps.c | 706 ------- drivers/lguest/lg.h | 258 --- drivers/lguest/lguest_user.c | 446 ----- drivers/lguest/page_tables.c | 1239 ------------ drivers/lguest/segments.c | 228 --- drivers/lguest/x86/core.c | 724 ------- drivers/lguest/x86/switcher_32.S | 388 ---- drivers/net/Kconfig | 2 +- drivers/tty/hvc/Kconfig | 2 +- drivers/virtio/Kconfig | 4 +- include/linux/lguest.h | 73 - include/linux/lguest_launcher.h | 44 - include/uapi/linux/virtio_ring.h | 4 +- tools/Makefile | 11 +- tools/lguest/.gitignore | 2 - tools/lguest/Makefile | 14 - tools/lguest/extract | 58 - tools/lguest/lguest.c | 3420 --------------------------------- tools/lguest/lguest.txt | 125 -- 43 files changed, 16 insertions(+), 10502 deletions(-) delete mode 100644 arch/x86/include/asm/lguest.h delete mode 100644 arch/x86/include/asm/lguest_hcall.h delete mode 100644 arch/x86/lguest/Kconfig delete mode 100644 arch/x86/lguest/Makefile delete mode 100644 arch/x86/lguest/boot.c delete mode 100644 arch/x86/lguest/head_32.S delete mode 100644 drivers/lguest/Kconfig delete mode 100644 drivers/lguest/Makefile delete mode 100644 drivers/lguest/README delete mode 100644 drivers/lguest/core.c delete mode 100644 drivers/lguest/hypercalls.c delete mode 100644 drivers/lguest/interrupts_and_traps.c delete mode 100644 drivers/lguest/lg.h delete mode 100644 drivers/lguest/lguest_user.c delete mode 100644 drivers/lguest/page_tables.c delete mode 100644 drivers/lguest/segments.c delete mode 100644 drivers/lguest/x86/core.c delete mode 100644 drivers/lguest/x86/switcher_32.S delete mode 100644 include/linux/lguest.h delete mode 100644 include/linux/lguest_launcher.h delete mode 100644 tools/lguest/.gitignore delete mode 100644 tools/lguest/Makefile delete mode 100644 tools/lguest/extract delete mode 100644 tools/lguest/lguest.c delete mode 100644 tools/lguest/lguest.txt (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 84d6a8277cbd..6c8b66d2adcb 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7640,17 +7640,6 @@ T: git git://linuxtv.org/mkrufky/tuners.git S: Maintained F: drivers/media/dvb-frontends/lgdt3305.* -LGUEST -M: Rusty Russell -L: lguest@lists.ozlabs.org -W: http://lguest.ozlabs.org/ -S: Odd Fixes -F: arch/x86/include/asm/lguest*.h -F: arch/x86/lguest/ -F: drivers/lguest/ -F: include/linux/lguest*.h -F: tools/lguest/ - LIBATA PATA ARASAN COMPACT FLASH CONTROLLER M: Viresh Kumar L: linux-ide@vger.kernel.org diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild index 586b786b3edf..f65a804b86f0 100644 --- a/arch/x86/Kbuild +++ b/arch/x86/Kbuild @@ -10,9 +10,6 @@ obj-$(CONFIG_XEN) += xen/ # Hyper-V paravirtualization support obj-$(CONFIG_HYPERVISOR_GUEST) += hyperv/ -# lguest paravirtualization support -obj-$(CONFIG_LGUEST_GUEST) += lguest/ - obj-y += realmode/ obj-y += kernel/ obj-y += mm/ diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 9b302121584d..651021713385 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -777,8 +777,6 @@ config KVM_DEBUG_FS Statistics are displayed in debugfs filesystem. Enabling this option may incur significant overhead. -source "arch/x86/lguest/Kconfig" - config PARAVIRT_TIME_ACCOUNTING bool "Paravirtual steal time accounting" depends on PARAVIRT diff --git a/arch/x86/include/asm/lguest.h b/arch/x86/include/asm/lguest.h deleted file mode 100644 index 73d0c9b92087..000000000000 --- a/arch/x86/include/asm/lguest.h +++ /dev/null @@ -1,91 +0,0 @@ -#ifndef _ASM_X86_LGUEST_H -#define _ASM_X86_LGUEST_H - -#define GDT_ENTRY_LGUEST_CS 10 -#define GDT_ENTRY_LGUEST_DS 11 -#define LGUEST_CS (GDT_ENTRY_LGUEST_CS * 8) -#define LGUEST_DS (GDT_ENTRY_LGUEST_DS * 8) - -#ifndef __ASSEMBLY__ -#include - -#define GUEST_PL 1 - -/* Page for Switcher text itself, then two pages per cpu */ -#define SWITCHER_TEXT_PAGES (1) -#define SWITCHER_STACK_PAGES (2 * nr_cpu_ids) -#define TOTAL_SWITCHER_PAGES (SWITCHER_TEXT_PAGES + SWITCHER_STACK_PAGES) - -/* Where we map the Switcher, in both Host and Guest. */ -extern unsigned long switcher_addr; - -/* Found in switcher.S */ -extern unsigned long default_idt_entries[]; - -/* Declarations for definitions in arch/x86/lguest/head_32.S */ -extern char lguest_noirq_iret[]; -extern const char lgstart_cli[], lgend_cli[]; -extern const char lgstart_pushf[], lgend_pushf[]; - -extern void lguest_iret(void); -extern void lguest_init(void); - -struct lguest_regs { - /* Manually saved part. */ - unsigned long eax, ebx, ecx, edx; - unsigned long esi, edi, ebp; - unsigned long gs; - unsigned long fs, ds, es; - unsigned long trapnum, errcode; - /* Trap pushed part */ - unsigned long eip; - unsigned long cs; - unsigned long eflags; - unsigned long esp; - unsigned long ss; -}; - -/* This is a guest-specific page (mapped ro) into the guest. */ -struct lguest_ro_state { - /* Host information we need to restore when we switch back. */ - u32 host_cr3; - struct desc_ptr host_idt_desc; - struct desc_ptr host_gdt_desc; - u32 host_sp; - - /* Fields which are used when guest is running. */ - struct desc_ptr guest_idt_desc; - struct desc_ptr guest_gdt_desc; - struct x86_hw_tss guest_tss; - struct desc_struct guest_idt[IDT_ENTRIES]; - struct desc_struct guest_gdt[GDT_ENTRIES]; -}; - -struct lg_cpu_arch { - /* The GDT entries copied into lguest_ro_state when running. */ - struct desc_struct gdt[GDT_ENTRIES]; - - /* The IDT entries: some copied into lguest_ro_state when running. */ - struct desc_struct idt[IDT_ENTRIES]; - - /* The address of the last guest-visible pagefault (ie. cr2). */ - unsigned long last_pagefault; -}; - -static inline void lguest_set_ts(void) -{ - u32 cr0; - - cr0 = read_cr0(); - if (!(cr0 & 8)) - write_cr0(cr0 | 8); -} - -/* Full 4G segment descriptors, suitable for CS and DS. */ -#define FULL_EXEC_SEGMENT \ - ((struct desc_struct)GDT_ENTRY_INIT(0xc09b, 0, 0xfffff)) -#define FULL_SEGMENT ((struct desc_struct)GDT_ENTRY_INIT(0xc093, 0, 0xfffff)) - -#endif /* __ASSEMBLY__ */ - -#endif /* _ASM_X86_LGUEST_H */ diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h deleted file mode 100644 index 6c119cfae218..000000000000 --- a/arch/x86/include/asm/lguest_hcall.h +++ /dev/null @@ -1,74 +0,0 @@ -/* Architecture specific portion of the lguest hypercalls */ -#ifndef _ASM_X86_LGUEST_HCALL_H -#define _ASM_X86_LGUEST_HCALL_H - -#define LHCALL_FLUSH_ASYNC 0 -#define LHCALL_LGUEST_INIT 1 -#define LHCALL_SHUTDOWN 2 -#define LHCALL_NEW_PGTABLE 4 -#define LHCALL_FLUSH_TLB 5 -#define LHCALL_LOAD_IDT_ENTRY 6 -#define LHCALL_SET_STACK 7 -#define LHCALL_SET_CLOCKEVENT 9 -#define LHCALL_HALT 10 -#define LHCALL_SET_PMD 13 -#define LHCALL_SET_PTE 14 -#define LHCALL_SET_PGD 15 -#define LHCALL_LOAD_TLS 16 -#define LHCALL_LOAD_GDT_ENTRY 18 -#define LHCALL_SEND_INTERRUPTS 19 - -#define LGUEST_TRAP_ENTRY 0x1F - -/* Argument number 3 to LHCALL_LGUEST_SHUTDOWN */ -#define LGUEST_SHUTDOWN_POWEROFF 1 -#define LGUEST_SHUTDOWN_RESTART 2 - -#ifndef __ASSEMBLY__ -#include - -/*G:030 - * But first, how does our Guest contact the Host to ask for privileged - * operations? There are two ways: the direct way is to make a "hypercall", - * to make requests of the Host Itself. - * - * Our hypercall mechanism uses the highest unused trap code (traps 32 and - * above are used by real hardware interrupts). Seventeen hypercalls are - * available: the hypercall number is put in the %eax register, and the - * arguments (when required) are placed in %ebx, %ecx, %edx and %esi. - * If a return value makes sense, it's returned in %eax. - * - * Grossly invalid calls result in Sudden Death at the hands of the vengeful - * Host, rather than returning failure. This reflects Winston Churchill's - * definition of a gentleman: "someone who is only rude intentionally". - */ -static inline unsigned long -hcall(unsigned long call, - unsigned long arg1, unsigned long arg2, unsigned long arg3, - unsigned long arg4) -{ - /* "int" is the Intel instruction to trigger a trap. */ - asm volatile("int $" __stringify(LGUEST_TRAP_ENTRY) - /* The call in %eax (aka "a") might be overwritten */ - : "=a"(call) - /* The arguments are in %eax, %ebx, %ecx, %edx & %esi */ - : "a"(call), "b"(arg1), "c"(arg2), "d"(arg3), "S"(arg4) - /* "memory" means this might write somewhere in memory. - * This isn't true for all calls, but it's safe to tell - * gcc that it might happen so it doesn't get clever. */ - : "memory"); - return call; -} -/*:*/ - -/* Can't use our min() macro here: needs to be a constant */ -#define LGUEST_IRQS (NR_IRQS < 32 ? NR_IRQS: 32) - -#define LHCALL_RING_SIZE 64 -struct hcall_args { - /* These map directly onto eax/ebx/ecx/edx/esi in struct lguest_regs */ - unsigned long arg0, arg1, arg2, arg3, arg4; -}; - -#endif /* !__ASSEMBLY__ */ -#endif /* _ASM_X86_LGUEST_HCALL_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 0b03d655db7c..abc99b9c7ffd 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -662,7 +662,7 @@ static inline void sync_core(void) * In case NMI unmasking or performance ever becomes a problem, * the next best option appears to be MOV-to-CR2 and an * unconditional jump. That sequence also works on all CPUs, - * but it will fault at CPL3 (i.e. Xen PV and lguest). + * but it will fault at CPL3 (i.e. Xen PV). * * CPUID is the conventional way, but it's nasty: it doesn't * exist on some 486-like CPUs, and it usually exits to a diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index ddef37b16af2..66b8f93333d1 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -201,7 +201,7 @@ struct boot_params { * * @X86_SUBARCH_PC: Should be used if the hardware is enumerable using standard * PC mechanisms (PCI, ACPI) and doesn't need a special boot flow. - * @X86_SUBARCH_LGUEST: Used for x86 hypervisor demo, lguest + * @X86_SUBARCH_LGUEST: Used for x86 hypervisor demo, lguest, deprecated * @X86_SUBARCH_XEN: Used for Xen guest types which follow the PV boot path, * which start at asm startup_xen() entry point and later jump to the C * xen_start_kernel() entry point. Both domU and dom0 type of guests are diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index 880aa093268d..710edab9e644 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -4,9 +4,6 @@ #include -#include -#include "../../../drivers/lguest/lg.h" - #define __SYSCALL_I386(nr, sym, qual) [nr] = 1, static char syscalls[] = { #include @@ -62,23 +59,6 @@ void foo(void) OFFSET(stack_canary_offset, stack_canary, canary); #endif -#if defined(CONFIG_LGUEST) || defined(CONFIG_LGUEST_GUEST) || defined(CONFIG_LGUEST_MODULE) - BLANK(); - OFFSET(LGUEST_DATA_irq_enabled, lguest_data, irq_enabled); - OFFSET(LGUEST_DATA_irq_pending, lguest_data, irq_pending); - - BLANK(); - OFFSET(LGUEST_PAGES_host_gdt_desc, lguest_pages, state.host_gdt_desc); - OFFSET(LGUEST_PAGES_host_idt_desc, lguest_pages, state.host_idt_desc); - OFFSET(LGUEST_PAGES_host_cr3, lguest_pages, state.host_cr3); - OFFSET(LGUEST_PAGES_host_sp, lguest_pages, state.host_sp); - OFFSET(LGUEST_PAGES_guest_gdt_desc, lguest_pages,state.guest_gdt_desc); - OFFSET(LGUEST_PAGES_guest_idt_desc, lguest_pages,state.guest_idt_desc); - OFFSET(LGUEST_PAGES_guest_gdt, lguest_pages, state.guest_gdt); - OFFSET(LGUEST_PAGES_regs_trapnum, lguest_pages, regs.trapnum); - OFFSET(LGUEST_PAGES_regs_errcode, lguest_pages, regs.errcode); - OFFSET(LGUEST_PAGES_regs, lguest_pages, regs); -#endif BLANK(); DEFINE(__NR_syscall_max, sizeof(syscalls) - 1); DEFINE(NR_syscalls, sizeof(syscalls)); diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 0332664eb158..29da9599fec0 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -155,7 +155,6 @@ ENTRY(startup_32) jmp *%eax .Lbad_subarch: -WEAK(lguest_entry) WEAK(xen_entry) /* Unknown implementation; there's really nothing we can do at this point. */ @@ -165,7 +164,6 @@ WEAK(xen_entry) subarch_entries: .long .Ldefault_entry /* normal x86/PC */ - .long lguest_entry /* lguest hypervisor */ .long xen_entry /* Xen hypervisor */ .long .Ldefault_entry /* Moorestown MID */ num_subarch_entries = (. - subarch_entries) / 4 diff --git a/arch/x86/kernel/platform-quirks.c b/arch/x86/kernel/platform-quirks.c index 91271122f0df..502a77d0adb0 100644 --- a/arch/x86/kernel/platform-quirks.c +++ b/arch/x86/kernel/platform-quirks.c @@ -16,7 +16,6 @@ void __init x86_early_init_platform_quirks(void) x86_platform.legacy.reserve_bios_regions = 1; break; case X86_SUBARCH_XEN: - case X86_SUBARCH_LGUEST: x86_platform.legacy.devices.pnpbios = 0; x86_platform.legacy.rtc = 0; break; diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 2688c7dc5323..3ea624452f93 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -89,6 +89,5 @@ config KVM_MMU_AUDIT # OK, it's a little counter-intuitive to do this, but it puts it neatly under # the virtualization menu. source drivers/vhost/Kconfig -source drivers/lguest/Kconfig endif # VIRTUALIZATION diff --git a/arch/x86/lguest/Kconfig b/arch/x86/lguest/Kconfig deleted file mode 100644 index 08f41caada45..000000000000 --- a/arch/x86/lguest/Kconfig +++ /dev/null @@ -1,14 +0,0 @@ -config LGUEST_GUEST - bool "Lguest guest support" - depends on X86_32 && PARAVIRT && PCI - select TTY - select VIRTUALIZATION - select VIRTIO - select VIRTIO_CONSOLE - help - Lguest is a tiny in-kernel hypervisor. Selecting this will - allow your kernel to boot under lguest. This option will increase - your kernel size by about 10k. If in doubt, say N. - - If you say Y here, make sure you say Y (or M) to the virtio block - and net drivers which lguest needs. diff --git a/arch/x86/lguest/Makefile b/arch/x86/lguest/Makefile deleted file mode 100644 index 8f38d577a2fa..000000000000 --- a/arch/x86/lguest/Makefile +++ /dev/null @@ -1,2 +0,0 @@ -obj-y := head_32.o boot.o -CFLAGS_boot.o := $(call cc-option, -fno-stack-protector) diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c deleted file mode 100644 index 99472698c931..000000000000 --- a/arch/x86/lguest/boot.c +++ /dev/null @@ -1,1558 +0,0 @@ -/*P:010 - * A hypervisor allows multiple Operating Systems to run on a single machine. - * To quote David Wheeler: "Any problem in computer science can be solved with - * another layer of indirection." - * - * We keep things simple in two ways. First, we start with a normal Linux - * kernel and insert a module (lg.ko) which allows us to run other Linux - * kernels the same way we'd run processes. We call the first kernel the Host, - * and the others the Guests. The program which sets up and configures Guests - * (such as the example in tools/lguest/lguest.c) is called the Launcher. - * - * Secondly, we only run specially modified Guests, not normal kernels: setting - * CONFIG_LGUEST_GUEST to "y" compiles this file into the kernel so it knows - * how to be a Guest at boot time. This means that you can use the same kernel - * you boot normally (ie. as a Host) as a Guest. - * - * These Guests know that they cannot do privileged operations, such as disable - * interrupts, and that they have to ask the Host to do such things explicitly. - * This file consists of all the replacements for such low-level native - * hardware operations: these special Guest versions call the Host. - * - * So how does the kernel know it's a Guest? We'll see that later, but let's - * just say that we end up here where we replace the native functions various - * "paravirt" structures with our Guest versions, then boot like normal. -:*/ - -/* - * Copyright (C) 2006, Rusty Russell IBM Corporation. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or - * NON INFRINGEMENT. See the GNU General Public License for more - * details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include /* for struct machine_ops */ -#include -#include -#include - -/*G:010 - * Welcome to the Guest! - * - * The Guest in our tale is a simple creature: identical to the Host but - * behaving in simplified but equivalent ways. In particular, the Guest is the - * same kernel as the Host (or at least, built from the same source code). -:*/ - -struct lguest_data lguest_data = { - .hcall_status = { [0 ... LHCALL_RING_SIZE-1] = 0xFF }, - .noirq_iret = (u32)lguest_noirq_iret, - .kernel_address = PAGE_OFFSET, - .blocked_interrupts = { 1 }, /* Block timer interrupts */ - .syscall_vec = IA32_SYSCALL_VECTOR, -}; - -/*G:037 - * async_hcall() is pretty simple: I'm quite proud of it really. We have a - * ring buffer of stored hypercalls which the Host will run though next time we - * do a normal hypercall. Each entry in the ring has 5 slots for the hypercall - * arguments, and a "hcall_status" word which is 0 if the call is ready to go, - * and 255 once the Host has finished with it. - * - * If we come around to a slot which hasn't been finished, then the table is - * full and we just make the hypercall directly. This has the nice side - * effect of causing the Host to run all the stored calls in the ring buffer - * which empties it for next time! - */ -static void async_hcall(unsigned long call, unsigned long arg1, - unsigned long arg2, unsigned long arg3, - unsigned long arg4) -{ - /* Note: This code assumes we're uniprocessor. */ - static unsigned int next_call; - unsigned long flags; - - /* - * Disable interrupts if not already disabled: we don't want an - * interrupt handler making a hypercall while we're already doing - * one! - */ - local_irq_save(flags); - if (lguest_data.hcall_status[next_call] != 0xFF) { - /* Table full, so do normal hcall which will flush table. */ - hcall(call, arg1, arg2, arg3, arg4); - } else { - lguest_data.hcalls[next_call].arg0 = call; - lguest_data.hcalls[next_call].arg1 = arg1; - lguest_data.hcalls[next_call].arg2 = arg2; - lguest_data.hcalls[next_call].arg3 = arg3; - lguest_data.hcalls[next_call].arg4 = arg4; - /* Arguments must all be written before we mark it to go */ - wmb(); - lguest_data.hcall_status[next_call] = 0; - if (++next_call == LHCALL_RING_SIZE) - next_call = 0; - } - local_irq_restore(flags); -} - -/*G:035 - * Notice the lazy_hcall() above, rather than hcall(). This is our first real - * optimization trick! - * - * When lazy_mode is set, it means we're allowed to defer all hypercalls and do - * them as a batch when lazy_mode is eventually turned off. Because hypercalls - * are reasonably expensive, batching them up makes sense. For example, a - * large munmap might update dozens of page table entries: that code calls - * paravirt_enter_lazy_mmu(), does the dozen updates, then calls - * lguest_leave_lazy_mode(). - * - * So, when we're in lazy mode, we call async_hcall() to store the call for - * future processing: - */ -static void lazy_hcall1(unsigned long call, unsigned long arg1) -{ - if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) - hcall(call, arg1, 0, 0, 0); - else - async_hcall(call, arg1, 0, 0, 0); -} - -/* You can imagine what lazy_hcall2, 3 and 4 look like. :*/ -static void lazy_hcall2(unsigned long call, - unsigned long arg1, - unsigned long arg2) -{ - if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) - hcall(call, arg1, arg2, 0, 0); - else - async_hcall(call, arg1, arg2, 0, 0); -} - -static void lazy_hcall3(unsigned long call, - unsigned long arg1, - unsigned long arg2, - unsigned long arg3) -{ - if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) - hcall(call, arg1, arg2, arg3, 0); - else - async_hcall(call, arg1, arg2, arg3, 0); -} - -#ifdef CONFIG_X86_PAE -static void lazy_hcall4(unsigned long call, - unsigned long arg1, - unsigned long arg2, - unsigned long arg3, - unsigned long arg4) -{ - if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) - hcall(call, arg1, arg2, arg3, arg4); - else - async_hcall(call, arg1, arg2, arg3, arg4); -} -#endif - -/*G:036 - * When lazy mode is turned off, we issue the do-nothing hypercall to - * flush any stored calls, and call the generic helper to reset the - * per-cpu lazy mode variable. - */ -static void lguest_leave_lazy_mmu_mode(void) -{ - hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0, 0); - paravirt_leave_lazy_mmu(); -} - -/* - * We also catch the end of context switch; we enter lazy mode for much of - * that too, so again we need to flush here. - * - * (Technically, this is lazy CPU mode, and normally we're in lazy MMU - * mode, but unlike Xen, lguest doesn't care about the difference). - */ -static void lguest_end_context_switch(struct task_struct *next) -{ - hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0, 0); - paravirt_end_context_switch(next); -} - -/*G:032 - * After that diversion we return to our first native-instruction - * replacements: four functions for interrupt control. - * - * The simplest way of implementing these would be to have "turn interrupts - * off" and "turn interrupts on" hypercalls. Unfortunately, this is too slow: - * these are by far the most commonly called functions of those we override. - * - * So instead we keep an "irq_enabled" field inside our "struct lguest_data", - * which the Guest can update with a single instruction. The Host knows to - * check there before it tries to deliver an interrupt. - */ - -/* - * save_flags() is expected to return the processor state (ie. "flags"). The - * flags word contains all kind of stuff, but in practice Linux only cares - * about the interrupt flag. Our "save_flags()" just returns that. - */ -asmlinkage __visible unsigned long lguest_save_fl(void) -{ - return lguest_data.irq_enabled; -} - -/* Interrupts go off... */ -asmlinkage __visible void lguest_irq_disable(void) -{ - lguest_data.irq_enabled = 0; -} - -/* - * Let's pause a moment. Remember how I said these are called so often? - * Jeremy Fitzhardinge optimized them so hard early in 2009 that he had to - * break some rules. In particular, these functions are assumed to save their - * own registers if they need to: normal C functions assume they can trash the - * eax register. To use normal C functions, we use - * PV_CALLEE_SAVE_REGS_THUNK(), which pushes %eax onto the stack, calls the - * C function, then restores it. - */ -PV_CALLEE_SAVE_REGS_THUNK(lguest_save_fl); -PV_CALLEE_SAVE_REGS_THUNK(lguest_irq_disable); -/*:*/ - -/* These are in head_32.S */ -extern void lg_irq_enable(void); -extern void lg_restore_fl(unsigned long flags); - -/*M:003 - * We could be more efficient in our checking of outstanding interrupts, rather - * than using a branch. One way would be to put the "irq_enabled" field in a - * page by itself, and have the Host write-protect it when an interrupt comes - * in when irqs are disabled. There will then be a page fault as soon as - * interrupts are re-enabled. - * - * A better method is to implement soft interrupt disable generally for x86: - * instead of disabling interrupts, we set a flag. If an interrupt does come - * in, we then disable them for real. This is uncommon, so we could simply use - * a hypercall for interrupt control and not worry about efficiency. -:*/ - -/*G:034 - * The Interrupt Descriptor Table (IDT). - * - * The IDT tells the processor what to do when an interrupt comes in. Each - * entry in the table is a 64-bit descriptor: this holds the privilege level, - * address of the handler, and... well, who cares? The Guest just asks the - * Host to make the change anyway, because the Host controls the real IDT. - */ -static void lguest_write_idt_entry(gate_desc *dt, - int entrynum, const gate_desc *g) -{ - /* - * The gate_desc structure is 8 bytes long: we hand it to the Host in - * two 32-bit chunks. The whole 32-bit kernel used to hand descriptors - * around like this; typesafety wasn't a big concern in Linux's early - * years. - */ - u32 *desc = (u32 *)g; - /* Keep the local copy up to date. */ - native_write_idt_entry(dt, entrynum, g); - /* Tell Host about this new entry. */ - hcall(LHCALL_LOAD_IDT_ENTRY, entrynum, desc[0], desc[1], 0); -} - -/* - * Changing to a different IDT is very rare: we keep the IDT up-to-date every - * time it is written, so we can simply loop through all entries and tell the - * Host about them. - */ -static void lguest_load_idt(const struct desc_ptr *desc) -{ - unsigned int i; - struct desc_struct *idt = (void *)desc->address; - - for (i = 0; i < (desc->size+1)/8; i++) - hcall(LHCALL_LOAD_IDT_ENTRY, i, idt[i].a, idt[i].b, 0); -} - -/* - * The Global Descriptor Table. - * - * The Intel architecture defines another table, called the Global Descriptor - * Table (GDT). You tell the CPU where it is (and its size) using the "lgdt" - * instruction, and then several other instructions refer to entries in the - * table. There are three entries which the Switcher needs, so the Host simply - * controls the entire thing and the Guest asks it to make changes using the - * LOAD_GDT hypercall. - * - * This is the exactly like the IDT code. - */ -static void lguest_load_gdt(const struct desc_ptr *desc) -{ - unsigned int i; - struct desc_struct *gdt = (void *)desc->address; - - for (i = 0; i < (desc->size+1)/8; i++) - hcall(LHCALL_LOAD_GDT_ENTRY, i, gdt[i].a, gdt[i].b, 0); -} - -/* - * For a single GDT entry which changes, we simply change our copy and - * then tell the host about it. - */ -static void lguest_write_gdt_entry(struct desc_struct *dt, int entrynum, - const void *desc, int type) -{ - native_write_gdt_entry(dt, entrynum, desc, type); - /* Tell Host about this new entry. */ - hcall(LHCALL_LOAD_GDT_ENTRY, entrynum, - dt[entrynum].a, dt[entrynum].b, 0); -} - -/* - * There are three "thread local storage" GDT entries which change - * on every context switch (these three entries are how glibc implements - * __thread variables). As an optimization, we have a hypercall - * specifically for this case. - * - * Wouldn't it be nicer to have a general LOAD_GDT_ENTRIES hypercall - * which took a range of entries? - */ -static void lguest_load_tls(struct thread_struct *t, unsigned int cpu) -{ - /* - * There's one problem which normal hardware doesn't have: the Host - * can't handle us removing entries we're currently using. So we clear - * the GS register here: if it's needed it'll be reloaded anyway. - */ - lazy_load_gs(0); - lazy_hcall2(LHCALL_LOAD_TLS, __pa(&t->tls_array), cpu); -} - -/*G:038 - * That's enough excitement for now, back to ploughing through each of the - * different pv_ops structures (we're about 1/3 of the way through). - * - * This is the Local Descriptor Table, another weird Intel thingy. Linux only - * uses this for some strange applications like Wine. We don't do anything - * here, so they'll get an informative and friendly Segmentation Fault. - */ -static void lguest_set_ldt(const void *addr, unsigned entries) -{ -} - -/* - * This loads a GDT entry into the "Task Register": that entry points to a - * structure called the Task State Segment. Some comments scattered though the - * kernel code indicate that this used for task switching in ages past, along - * with blood sacrifice and astrology. - * - * Now there's nothing interesting in here that we don't get told elsewhere. - * But the native version uses the "ltr" instruction, which makes the Host - * complain to the Guest about a Segmentation Fault and it'll oops. So we - * override the native version with a do-nothing version. - */ -static void lguest_load_tr_desc(void) -{ -} - -/* - * The "cpuid" instruction is a way of querying both the CPU identity - * (manufacturer, model, etc) and its features. It was introduced before the - * Pentium in 1993 and keeps getting extended by both Intel, AMD and others. - * As you might imagine, after a decade and a half this treatment, it is now a - * giant ball of hair. Its entry in the current Intel manual runs to 28 pages. - * - * This instruction even it has its own Wikipedia entry. The Wikipedia entry - * has been translated into 6 languages. I am not making this up! - * - * We could get funky here and identify ourselves as "GenuineLguest", but - * instead we just use the real "cpuid" instruction. Then I pretty much turned - * off feature bits until the Guest booted. (Don't say that: you'll damage - * lguest sales!) Shut up, inner voice! (Hey, just pointing out that this is - * hardly future proof.) No one's listening! They don't like you anyway, - * parenthetic weirdo! - * - * Replacing the cpuid so we can turn features off is great for the kernel, but - * anyone (including userspace) can just use the raw "cpuid" instruction and - * the Host won't even notice since it isn't privileged. So we try not to get - * too worked up about it. - */ -static void lguest_cpuid(unsigned int *ax, unsigned int *bx, - unsigned int *cx, unsigned int *dx) -{ - int function = *ax; - - native_cpuid(ax, bx, cx, dx); - switch (function) { - /* - * CPUID 0 gives the highest legal CPUID number (and the ID string). - * We futureproof our code a little by sticking to known CPUID values. - */ - case 0: - if (*ax > 5) - *ax = 5; - break; - - /* - * CPUID 1 is a basic feature request. - * - * CX: we only allow kernel to see SSE3, CMPXCHG16B and SSSE3 - * DX: SSE, SSE2, FXSR, MMX, CMOV, CMPXCHG8B, TSC, FPU and PAE. - */ - case 1: - *cx &= 0x00002201; - *dx &= 0x07808151; - /* - * The Host can do a nice optimization if it knows that the - * kernel mappings (addresses above 0xC0000000 or whatever - * PAGE_OFFSET is set to) haven't changed. But Linux calls - * flush_tlb_user() for both user and kernel mappings unless - * the Page Global Enable (PGE) feature bit is set. - */ - *dx |= 0x00002000; - /* - * We also lie, and say we're family id 5. 6 or greater - * leads to a rdmsr in early_init_intel which we can't handle. - * Family ID is returned as bits 8-12 in ax. - */ - *ax &= 0xFFFFF0FF; - *ax |= 0x00000500; - break; - - /* - * This is used to detect if we're running under KVM. We might be, - * but that's a Host matter, not us. So say we're not. - */ - case KVM_CPUID_SIGNATURE: - *bx = *cx = *dx = 0; - break; - - /* - * 0x80000000 returns the highest Extended Function, so we futureproof - * like we do above by limiting it to known fields. - */ - case 0x80000000: - if (*ax > 0x80000008) - *ax = 0x80000008; - break; - - /* - * PAE systems can mark pages as non-executable. Linux calls this the - * NX bit. Intel calls it XD (eXecute Disable), AMD EVP (Enhanced - * Virus Protection). We just switch it off here, since we don't - * support it. - */ - case 0x80000001: - *dx &= ~(1 << 20); - break; - } -} - -/* - * Intel has four control registers, imaginatively named cr0, cr2, cr3 and cr4. - * I assume there's a cr1, but it hasn't bothered us yet, so we'll not bother - * it. The Host needs to know when the Guest wants to change them, so we have - * a whole series of functions like read_cr0() and write_cr0(). - * - * We start with cr0. cr0 allows you to turn on and off all kinds of basic - * features, but the only cr0 bit that Linux ever used at runtime was the - * horrifically-named Task Switched (TS) bit at bit 3 (ie. 8) - * - * What does the TS bit do? Well, it causes the CPU to trap (interrupt 7) if - * the floating point unit is used. Which allows us to restore FPU state - * lazily after a task switch if we wanted to, but wouldn't a name like - * "FPUTRAP bit" be a little less cryptic? - * - * Fortunately, Linux keeps it simple and doesn't use TS, so we can ignore - * cr0. - */ -static void lguest_write_cr0(unsigned long val) -{ -} - -static unsigned long lguest_read_cr0(void) -{ - return 0; -} - -/* - * cr2 is the virtual address of the last page fault, which the Guest only ever - * reads. The Host kindly writes this into our "struct lguest_data", so we - * just read it out of there. - */ -static unsigned long lguest_read_cr2(void) -{ - return lguest_data.cr2; -} - -/* See lguest_set_pte() below. */ -static bool cr3_changed = false; -static unsigned long current_cr3; - -/* - * cr3 is the current toplevel pagetable page: the principle is the same as - * cr0. Keep a local copy, and tell the Host when it changes. - */ -static void lguest_write_cr3(unsigned long cr3) -{ - lazy_hcall1(LHCALL_NEW_PGTABLE, cr3); - current_cr3 = cr3; - - /* These two page tables are simple, linear, and used during boot */ - if (cr3 != __pa_symbol(swapper_pg_dir) && - cr3 != __pa_symbol(initial_page_table)) - cr3_changed = true; -} - -static unsigned long lguest_read_cr3(void) -{ - return current_cr3; -} - -/* cr4 is used to enable and disable PGE, but we don't care. */ -static unsigned long lguest_read_cr4(void) -{ - return 0; -} - -static void lguest_write_cr4(unsigned long val) -{ -} - -/* - * Page Table Handling. - * - * Now would be a good time to take a rest and grab a coffee or similarly - * relaxing stimulant. The easy parts are behind us, and the trek gradually - * winds uphill from here. - * - * Quick refresher: memory is divided into "pages" of 4096 bytes each. The CPU - * maps virtual addresses to physical addresses using "page tables". We could - * use one huge index of 1 million entries: each address is 4 bytes, so that's - * 1024 pages just to hold the page tables. But since most virtual addresses - * are unused, we use a two level index which saves space. The cr3 register - * contains the physical address of the top level "page directory" page, which - * contains physical addresses of up to 1024 second-level pages. Each of these - * second level pages contains up to 1024 physical addresses of actual pages, - * or Page Table Entries (PTEs). - * - * Here's a diagram, where arrows indicate physical addresses: - * - * cr3 ---> +---------+ - * | --------->+---------+ - * | | | PADDR1 | - * Mid-level | | PADDR2 | - * (PMD) page | | | - * | | Lower-level | - * | | (PTE) page | - * | | | | - * .... .... - * - * So to convert a virtual address to a physical address, we look up the top - * level, which points us to the second level, which gives us the physical - * address of that page. If the top level entry was not present, or the second - * level entry was not present, then the virtual address is invalid (we - * say "the page was not mapped"). - * - * Put another way, a 32-bit virtual address is divided up like so: - * - * 1 1 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 - * |<---- 10 bits ---->|<---- 10 bits ---->|<------ 12 bits ------>| - * Index into top Index into second Offset within page - * page directory page pagetable page - * - * Now, unfortunately, this isn't the whole story: Intel added Physical Address - * Extension (PAE) to allow 32 bit systems to use 64GB of memory (ie. 36 bits). - * These are held in 64-bit page table entries, so we can now only fit 512 - * entries in a page, and the neat three-level tree breaks down. - * - * The result is a four level page table: - * - * cr3 --> [ 4 Upper ] - * [ Level ] - * [ Entries ] - * [(PUD Page)]---> +---------+ - * | --------->+---------+ - * | | | PADDR1 | - * Mid-level | | PADDR2 | - * (PMD) page | | | - * | | Lower-level | - * | | (PTE) page | - * | | | | - * .... .... - * - * - * And the virtual address is decoded as: - * - * 1 1 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 - * |<-2->|<--- 9 bits ---->|<---- 9 bits --->|<------ 12 bits ------>| - * Index into Index into mid Index into lower Offset within page - * top entries directory page pagetable page - * - * It's too hard to switch between these two formats at runtime, so Linux only - * supports one or the other depending on whether CONFIG_X86_PAE is set. Many - * distributions turn it on, and not just for people with silly amounts of - * memory: the larger PTE entries allow room for the NX bit, which lets the - * kernel disable execution of pages and increase security. - * - * This was a problem for lguest, which couldn't run on these distributions; - * then Matias Zabaljauregui figured it all out and implemented it, and only a - * handful of puppies were crushed in the process! - * - * Back to our point: the kernel spends a lot of time changing both the - * top-level page directory and lower-level pagetable pages. The Guest doesn't - * know physical addresses, so while it maintains these page tables exactly - * like normal, it also needs to keep the Host informed whenever it makes a - * change: the Host will create the real page tables based on the Guests'. - */ - -/* - * The Guest calls this after it has set a second-level entry (pte), ie. to map - * a page into a process' address space. We tell the Host the toplevel and - * address this corresponds to. The Guest uses one pagetable per process, so - * we need to tell the Host which one we're changing (mm->pgd). - */ -static void lguest_pte_update(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) -{ -#ifdef CONFIG_X86_PAE - /* PAE needs to hand a 64 bit page table entry, so it uses two args. */ - lazy_hcall4(LHCALL_SET_PTE, __pa(mm->pgd), addr, - ptep->pte_low, ptep->pte_high); -#else - lazy_hcall3(LHCALL_SET_PTE, __pa(mm->pgd), addr, ptep->pte_low); -#endif -} - -/* This is the "set and update" combo-meal-deal version. */ -static void lguest_set_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pteval) -{ - native_set_pte(ptep, pteval); - lguest_pte_update(mm, addr, ptep); -} - -/* - * The Guest calls lguest_set_pud to set a top-level entry and lguest_set_pmd - * to set a middle-level entry when PAE is activated. - * - * Again, we set the entry then tell the Host which page we changed, - * and the index of the entry we changed. - */ -#ifdef CONFIG_X86_PAE -static void lguest_set_pud(pud_t *pudp, pud_t pudval) -{ - native_set_pud(pudp, pudval); - - /* 32 bytes aligned pdpt address and the index. */ - lazy_hcall2(LHCALL_SET_PGD, __pa(pudp) & 0xFFFFFFE0, - (__pa(pudp) & 0x1F) / sizeof(pud_t)); -} - -static void lguest_set_pmd(pmd_t *pmdp, pmd_t pmdval) -{ - native_set_pmd(pmdp, pmdval); - lazy_hcall2(LHCALL_SET_PMD, __pa(pmdp) & PAGE_MASK, - (__pa(pmdp) & (PAGE_SIZE - 1)) / sizeof(pmd_t)); -} -#else - -/* The Guest calls lguest_set_pmd to set a top-level entry when !PAE. */ -static void lguest_set_pmd(pmd_t *pmdp, pmd_t pmdval) -{ - native_set_pmd(pmdp, pmdval); - lazy_hcall2(LHCALL_SET_PGD, __pa(pmdp) & PAGE_MASK, - (__pa(pmdp) & (PAGE_SIZE - 1)) / sizeof(pmd_t)); -} -#endif - -/* - * There are a couple of legacy places where the kernel sets a PTE, but we - * don't know the top level any more. This is useless for us, since we don't - * know which pagetable is changing or what address, so we just tell the Host - * to forget all of them. Fortunately, this is very rare. - * - * ... except in early boot when the kernel sets up the initial pagetables, - * which makes booting astonishingly slow: 48 seconds! So we don't even tell - * the Host anything changed until we've done the first real page table switch, - * which brings boot back to 4.3 seconds. - */ -static void lguest_set_pte(pte_t *ptep, pte_t pteval) -{ - native_set_pte(ptep, pteval); - if (cr3_changed) - lazy_hcall1(LHCALL_FLUSH_TLB, 1); -} - -#ifdef CONFIG_X86_PAE -/* - * With 64-bit PTE values, we need to be careful setting them: if we set 32 - * bits at a time, the hardware could see a weird half-set entry. These - * versions ensure we update all 64 bits at once. - */ -static void lguest_set_pte_atomic(pte_t *ptep, pte_t pte) -{ - native_set_pte_atomic(ptep, pte); - if (cr3_changed) - lazy_hcall1(LHCALL_FLUSH_TLB, 1); -} - -static void lguest_pte_clear(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) -{ - native_pte_clear(mm, addr, ptep); - lguest_pte_update(mm, addr, ptep); -} - -static void lguest_pmd_clear(pmd_t *pmdp) -{ - lguest_set_pmd(pmdp, __pmd(0)); -} -#endif - -/* - * Unfortunately for Lguest, the pv_mmu_ops for page tables were based on - * native page table operations. On native hardware you can set a new page - * table entry whenever you want, but if you want to remove one you have to do - * a TLB flush (a TLB is a little cache of page table entries kept by the CPU). - * - * So the lguest_set_pte_at() and lguest_set_pmd() functions above are only - * called when a valid entry is written, not when it's removed (ie. marked not - * present). Instead, this is where we come when the Guest wants to remove a - * page table entry: we tell the Host to set that entry to 0 (ie. the present - * bit is zero). - */ -static void lguest_flush_tlb_single(unsigned long addr) -{ - /* Simply set it to zero: if it was not, it will fault back in. */ - lazy_hcall3(LHCALL_SET_PTE, current_cr3, addr, 0); -} - -/* - * This is what happens after the Guest has removed a large number of entries. - * This tells the Host that any of the page table entries for userspace might - * have changed, ie. virtual addresses below PAGE_OFFSET. - */ -static void lguest_flush_tlb_user(void) -{ - lazy_hcall1(LHCALL_FLUSH_TLB, 0); -} - -/* - * This is called when the kernel page tables have changed. That's not very - * common (unless the Guest is using highmem, which makes the Guest extremely - * slow), so it's worth separating this from the user flushing above. - */ -static void lguest_flush_tlb_kernel(void) -{ - lazy_hcall1(LHCALL_FLUSH_TLB, 1); -} - -/* - * The Unadvanced Programmable Interrupt Controller. - * - * This is an attempt to implement the simplest possible interrupt controller. - * I spent some time looking though routines like set_irq_chip_and_handler, - * set_irq_chip_and_handler_name, set_irq_chip_data and set_phasers_to_stun and - * I *think* this is as simple as it gets. - * - * We can tell the Host what interrupts we want blocked ready for using the - * lguest_data.interrupts bitmap, so disabling (aka "masking") them is as - * simple as setting a bit. We don't actually "ack" interrupts as such, we - * just mask and unmask them. I wonder if we should be cleverer? - */ -static void disable_lguest_irq(struct irq_data *data) -{ - set_bit(data->irq, lguest_data.blocked_interrupts); -} - -static void enable_lguest_irq(struct irq_data *data) -{ - clear_bit(data->irq, lguest_data.blocked_interrupts); -} - -/* This structure describes the lguest IRQ controller. */ -static struct irq_chip lguest_irq_controller = { - .name = "lguest", - .irq_mask = disable_lguest_irq, - .irq_mask_ack = disable_lguest_irq, - .irq_unmask = enable_lguest_irq, -}; - -/* - * Interrupt descriptors are allocated as-needed, but low-numbered ones are - * reserved by the generic x86 code. So we ignore irq_alloc_desc_at if it - * tells us the irq is already used: other errors (ie. ENOMEM) we take - * seriously. - */ -static int lguest_setup_irq(unsigned int irq) -{ - struct irq_desc *desc; - int err; - - /* Returns -ve error or vector number. */ - err = irq_alloc_desc_at(irq, 0); - if (err < 0 && err != -EEXIST) - return err; - - /* - * Tell the Linux infrastructure that the interrupt is - * controlled by our level-based lguest interrupt controller. - */ - irq_set_chip_and_handler_name(irq, &lguest_irq_controller, - handle_level_irq, "level"); - - /* Some systems map "vectors" to interrupts weirdly. Not us! */ - desc = irq_to_desc(irq); - __this_cpu_write(vector_irq[FIRST_EXTERNAL_VECTOR + irq], desc); - return 0; -} - -static int lguest_enable_irq(struct pci_dev *dev) -{ - int err; - u8 line = 0; - - /* We literally use the PCI interrupt line as the irq number. */ - pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &line); - err = lguest_setup_irq(line); - if (!err) - dev->irq = line; - return err; -} - -/* We don't do hotplug PCI, so this shouldn't be called. */ -static void lguest_disable_irq(struct pci_dev *dev) -{ - WARN_ON(1); -} - -/* - * This sets up the Interrupt Descriptor Table (IDT) entry for each hardware - * interrupt (except 128, which is used for system calls). - */ -static void __init lguest_init_IRQ(void) -{ - unsigned int i; - - for (i = FIRST_EXTERNAL_VECTOR; i < FIRST_SYSTEM_VECTOR; i++) { - if (i != IA32_SYSCALL_VECTOR) - set_intr_gate(i, irq_entries_start + - 8 * (i - FIRST_EXTERNAL_VECTOR)); - } - - /* - * This call is required to set up for 4k stacks, where we have - * separate stacks for hard and soft interrupts. - */ - irq_ctx_init(smp_processor_id()); -} - -/* - * Time. - * - * It would be far better for everyone if the Guest had its own clock, but - * until then the Host gives us the time on every interrupt. - */ -static void lguest_get_wallclock(struct timespec *now) -{ - *now = lguest_data.time; -} - -/* - * The TSC is an Intel thing called the Time Stamp Counter. The Host tells us - * what speed it runs at, or 0 if it's unusable as a reliable clock source. - * This matches what we want here: if we return 0 from this function, the x86 - * TSC clock will give up and not register itself. - */ -static unsigned long lguest_tsc_khz(void) -{ - return lguest_data.tsc_khz; -} - -/* - * If we can't use the TSC, the kernel falls back to our lower-priority - * "lguest_clock", where we read the time value given to us by the Host. - */ -static u64 lguest_clock_read(struct clocksource *cs) -{ - unsigned long sec, nsec; - - /* - * Since the time is in two parts (seconds and nanoseconds), we risk - * reading it just as it's changing from 99 & 0.999999999 to 100 and 0, - * and getting 99 and 0. As Linux tends to come apart under the stress - * of time travel, we must be careful: - */ - do { - /* First we read the seconds part. */ - sec = lguest_data.time.tv_sec; - /* - * This read memory barrier tells the compiler and the CPU that - * this can't be reordered: we have to complete the above - * before going on. - */ - rmb(); - /* Now we read the nanoseconds part. */ - nsec = lguest_data.time.tv_nsec; - /* Make sure we've done that. */ - rmb(); - /* Now if the seconds part has changed, try again. */ - } while (unlikely(lguest_data.time.tv_sec != sec)); - - /* Our lguest clock is in real nanoseconds. */ - return sec*1000000000ULL + nsec; -} - -/* This is the fallback clocksource: lower priority than the TSC clocksource. */ -static struct clocksource lguest_clock = { - .name = "lguest", - .rating = 200, - .read = lguest_clock_read, - .mask = CLOCKSOURCE_MASK(64), - .flags = CLOCK_SOURCE_IS_CONTINUOUS, -}; - -/* - * We also need a "struct clock_event_device": Linux asks us to set it to go - * off some time in the future. Actually, James Morris figured all this out, I - * just applied the patch. - */ -static int lguest_clockevent_set_next_event(unsigned long delta, - struct clock_event_device *evt) -{ - /* FIXME: I don't think this can ever happen, but James tells me he had - * to put this code in. Maybe we should remove it now. Anyone? */ - if (delta < LG_CLOCK_MIN_DELTA) { - if (printk_ratelimit()) - printk(KERN_DEBUG "%s: small delta %lu ns\n", - __func__, delta); - return -ETIME; - } - - /* Please wake us this far in the future. */ - hcall(LHCALL_SET_CLOCKEVENT, delta, 0, 0, 0); - return 0; -} - -static int lguest_clockevent_shutdown(struct clock_event_device *evt) -{ - /* A 0 argument shuts the clock down. */ - hcall(LHCALL_SET_CLOCKEVENT, 0, 0, 0, 0); - return 0; -} - -/* This describes our primitive timer chip. */ -static struct clock_event_device lguest_clockevent = { - .name = "lguest", - .features = CLOCK_EVT_FEAT_ONESHOT, - .set_next_event = lguest_clockevent_set_next_event, - .set_state_shutdown = lguest_clockevent_shutdown, - .rating = INT_MAX, - .mult = 1, - .shift = 0, - .min_delta_ns = LG_CLOCK_MIN_DELTA, - .min_delta_ticks = LG_CLOCK_MIN_DELTA, - .max_delta_ns = LG_CLOCK_MAX_DELTA, - .max_delta_ticks = LG_CLOCK_MAX_DELTA, -}; - -/* - * This is the Guest timer interrupt handler (hardware interrupt 0). We just - * call the clockevent infrastructure and it does whatever needs doing. - */ -static void lguest_time_irq(struct irq_desc *desc) -{ - unsigned long flags; - - /* Don't interrupt us while this is running. */ - local_irq_save(flags); - lguest_clockevent.event_handler(&lguest_clockevent); - local_irq_restore(flags); -} - -/* - * At some point in the boot process, we get asked to set up our timing - * infrastructure. The kernel doesn't expect timer interrupts before this, but - * we cleverly initialized the "blocked_interrupts" field of "struct - * lguest_data" so that timer interrupts were blocked until now. - */ -static void lguest_time_init(void) -{ - /* Set up the timer interrupt (0) to go to our simple timer routine */ - if (lguest_setup_irq(0) != 0) - panic("Could not set up timer irq"); - irq_set_handler(0, lguest_time_irq); - - clocksource_register_hz(&lguest_clock, NSEC_PER_SEC); - - /* We can't set cpumask in the initializer: damn C limitations! Set it - * here and register our timer device. */ - lguest_clockevent.cpumask = cpumask_of(0); - clockevents_register_device(&lguest_clockevent); - - /* Finally, we unblock the timer interrupt. */ - clear_bit(0, lguest_data.blocked_interrupts); -} - -/* - * Miscellaneous bits and pieces. - * - * Here is an oddball collection of functions which the Guest needs for things - * to work. They're pretty simple. - */ - -/* - * The Guest needs to tell the Host what stack it expects traps to use. For - * native hardware, this is part of the Task State Segment mentioned above in - * lguest_load_tr_desc(), but to help hypervisors there's this special call. - * - * We tell the Host the segment we want to use (__KERNEL_DS is the kernel data - * segment), the privilege level (we're privilege level 1, the Host is 0 and - * will not tolerate us trying to use that), the stack pointer, and the number - * of pages in the stack. - */ -static void lguest_load_sp0(struct tss_struct *tss, - struct thread_struct *thread) -{ - lazy_hcall3(LHCALL_SET_STACK, __KERNEL_DS | 0x1, thread->sp0, - THREAD_SIZE / PAGE_SIZE); - tss->x86_tss.sp0 = thread->sp0; -} - -/* Let's just say, I wouldn't do debugging under a Guest. */ -static unsigned long lguest_get_debugreg(int regno) -{ - /* FIXME: Implement */ - return 0; -} - -static void lguest_set_debugreg(int regno, unsigned long value) -{ - /* FIXME: Implement */ -} - -/* - * There are times when the kernel wants to make sure that no memory writes are - * caught in the cache (that they've all reached real hardware devices). This - * doesn't matter for the Guest which has virtual hardware. - * - * On the Pentium 4 and above, cpuid() indicates that the Cache Line Flush - * (clflush) instruction is available and the kernel uses that. Otherwise, it - * uses the older "Write Back and Invalidate Cache" (wbinvd) instruction. - * Unlike clflush, wbinvd can only be run at privilege level 0. So we can - * ignore clflush, but replace wbinvd. - */ -static void lguest_wbinvd(void) -{ -} - -/* - * If the Guest expects to have an Advanced Programmable Interrupt Controller, - * we play dumb by ignoring writes and returning 0 for reads. So it's no - * longer Programmable nor Controlling anything, and I don't think 8 lines of - * code qualifies for Advanced. It will also never interrupt anything. It - * does, however, allow us to get through the Linux boot code. - */ -#ifdef CONFIG_X86_LOCAL_APIC -static void lguest_apic_write(u32 reg, u32 v) -{ -} - -static u32 lguest_apic_read(u32 reg) -{ - return 0; -} - -static u64 lguest_apic_icr_read(void) -{ - return 0; -} - -static void lguest_apic_icr_write(u32 low, u32 id) -{ - /* Warn to see if there's any stray references */ - WARN_ON(1); -} - -static void lguest_apic_wait_icr_idle(void) -{ - return; -} - -static u32 lguest_apic_safe_wait_icr_idle(void) -{ - return 0; -} - -static void set_lguest_basic_apic_ops(void) -{ - apic->read = lguest_apic_read; - apic->write = lguest_apic_write; - apic->icr_read = lguest_apic_icr_read; - apic->icr_write = lguest_apic_icr_write; - apic->wait_icr_idle = lguest_apic_wait_icr_idle; - apic->safe_wait_icr_idle = lguest_apic_safe_wait_icr_idle; -}; -#endif - -/* STOP! Until an interrupt comes in. */ -static void lguest_safe_halt(void) -{ - hcall(LHCALL_HALT, 0, 0, 0, 0); -} - -/* - * The SHUTDOWN hypercall takes a string to describe what's happening, and - * an argument which says whether this to restart (reboot) the Guest or not. - * - * Note that the Host always prefers that the Guest speak in physical addresses - * rather than virtual addresses, so we use __pa() here. - */ -static void lguest_power_off(void) -{ - hcall(LHCALL_SHUTDOWN, __pa("Power down"), - LGUEST_SHUTDOWN_POWEROFF, 0, 0); -} - -/* - * Panicing. - * - * Don't. But if you did, this is what happens. - */ -static int lguest_panic(struct notifier_block *nb, unsigned long l, void *p) -{ - hcall(LHCALL_SHUTDOWN, __pa(p), LGUEST_SHUTDOWN_POWEROFF, 0, 0); - /* The hcall won't return, but to keep gcc happy, we're "done". */ - return NOTIFY_DONE; -} - -static struct notifier_block paniced = { - .notifier_call = lguest_panic -}; - -/* Setting up memory is fairly easy. */ -static __init char *lguest_memory_setup(void) -{ - /* - * The Linux bootloader header contains an "e820" memory map: the - * Launcher populated the first entry with our memory limit. - */ - e820__range_add(boot_params.e820_table[0].addr, - boot_params.e820_table[0].size, - boot_params.e820_table[0].type); - - /* This string is for the boot messages. */ - return "LGUEST"; -} - -/* Offset within PCI config space of BAR access capability. */ -static int console_cfg_offset = 0; -static int console_access_cap; - -/* Set up so that we access off in bar0 (on bus 0, device 1, function 0) */ -static void set_cfg_window(u32 cfg_offset, u32 off) -{ - write_pci_config_byte(0, 1, 0, - cfg_offset + offsetof(struct virtio_pci_cap, bar), - 0); - write_pci_config(0, 1, 0, - cfg_offset + offsetof(struct virtio_pci_cap, length), - 4); - write_pci_config(0, 1, 0, - cfg_offset + offsetof(struct virtio_pci_cap, offset), - off); -} - -static void write_bar_via_cfg(u32 cfg_offset, u32 off, u32 val) -{ - /* - * We could set this up once, then leave it; nothing else in the * - * kernel should touch these registers. But if it went wrong, that - * would be a horrible bug to find. - */ - set_cfg_window(cfg_offset, off); - write_pci_config(0, 1, 0, - cfg_offset + sizeof(struct virtio_pci_cap), val); -} - -static void probe_pci_console(void) -{ - u8 cap, common_cap = 0, device_cap = 0; - u32 device_len; - - /* Avoid recursive printk into here. */ - console_cfg_offset = -1; - - if (!early_pci_allowed()) { - printk(KERN_ERR "lguest: early PCI access not allowed!\n"); - return; - } - - /* We expect a console PCI device at BUS0, slot 1. */ - if (read_pci_config(0, 1, 0, 0) != 0x10431AF4) { - printk(KERN_ERR "lguest: PCI device is %#x!\n", - read_pci_config(0, 1, 0, 0)); - return; - } - - /* Find the capabilities we need (must be in bar0) */ - cap = read_pci_config_byte(0, 1, 0, PCI_CAPABILITY_LIST); - while (cap) { - u8 vndr = read_pci_config_byte(0, 1, 0, cap); - if (vndr == PCI_CAP_ID_VNDR) { - u8 type, bar; - - type = read_pci_config_byte(0, 1, 0, - cap + offsetof(struct virtio_pci_cap, cfg_type)); - bar = read_pci_config_byte(0, 1, 0, - cap + offsetof(struct virtio_pci_cap, bar)); - - switch (type) { - case VIRTIO_PCI_CAP_DEVICE_CFG: - if (bar == 0) - device_cap = cap; - break; - case VIRTIO_PCI_CAP_PCI_CFG: - console_access_cap = cap; - break; - } - } - cap = read_pci_config_byte(0, 1, 0, cap + PCI_CAP_LIST_NEXT); - } - if (!device_cap || !console_access_cap) { - printk(KERN_ERR "lguest: No caps (%u/%u/%u) in console!\n", - common_cap, device_cap, console_access_cap); - return; - } - - /* - * Note that we can't check features, until we've set the DRIVER - * status bit. We don't want to do that until we have a real driver, - * so we just check that the device-specific config has room for - * emerg_wr. If it doesn't support VIRTIO_CONSOLE_F_EMERG_WRITE - * it should ignore the access. - */ - device_len = read_pci_config(0, 1, 0, - device_cap + offsetof(struct virtio_pci_cap, length)); - if (device_len < (offsetof(struct virtio_console_config, emerg_wr) - + sizeof(u32))) { - printk(KERN_ERR "lguest: console missing emerg_wr field\n"); - return; - } - - console_cfg_offset = read_pci_config(0, 1, 0, - device_cap + offsetof(struct virtio_pci_cap, offset)); - printk(KERN_INFO "lguest: Console via virtio-pci emerg_wr\n"); -} - -/* - * We will eventually use the virtio console device to produce console output, - * but before that is set up we use the virtio PCI console's backdoor mmio - * access and the "emergency" write facility (which is legal even before the - * device is configured). - */ -static __init int early_put_chars(u32 vtermno, const char *buf, int count) -{ - /* If we couldn't find PCI console, forget it. */ - if (console_cfg_offset < 0) - return count; - - if (unlikely(!console_cfg_offset)) { - probe_pci_console(); - if (console_cfg_offset < 0) - return count; - } - - write_bar_via_cfg(console_access_cap, - console_cfg_offset - + offsetof(struct virtio_console_config, emerg_wr), - buf[0]); - return 1; -} - -/* - * Rebooting also tells the Host we're finished, but the RESTART flag tells the - * Launcher to reboot us. - */ -static void lguest_restart(char *reason) -{ - hcall(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART, 0, 0); -} - -/*G:050 - * Patching (Powerfully Placating Performance Pedants) - * - * We have already seen that pv_ops structures let us replace simple native - * instructions with calls to the appropriate back end all throughout the - * kernel. This allows the same kernel to run as a Guest and as a native - * kernel, but it's slow because of all the indirect branches. - * - * Remember that David Wheeler quote about "Any problem in computer science can - * be solved with another layer of indirection"? The rest of that quote is - * "... But that usually will create another problem." This is the first of - * those problems. - * - * Our current solution is to allow the paravirt back end to optionally patch - * over the indirect calls to replace them with something more efficient. We - * patch two of the simplest of the most commonly called functions: disable - * interrupts and save interrupts. We usually have 6 or 10 bytes to patch - * into: the Guest versions of these operations are small enough that we can - * fit comfortably. - * - * First we need assembly templates of each of the patchable Guest operations, - * and these are in head_32.S. - */ - -/*G:060 We construct a table from the assembler templates: */ -static const struct lguest_insns -{ - const char *start, *end; -} lguest_insns[] = { - [PARAVIRT_PATCH(pv_irq_ops.irq_disable)] = { lgstart_cli, lgend_cli }, - [PARAVIRT_PATCH(pv_irq_ops.save_fl)] = { lgstart_pushf, lgend_pushf }, -}; - -/* - * Now our patch routine is fairly simple (based on the native one in - * paravirt.c). If we have a replacement, we copy it in and return how much of - * the available space we used. - */ -static unsigned lguest_patch(u8 type, u16 clobber, void *ibuf, - unsigned long addr, unsigned len) -{ - unsigned int insn_len; - - /* Don't do anything special if we don't have a replacement */ - if (type >= ARRAY_SIZE(lguest_insns) || !lguest_insns[type].start) - return paravirt_patch_default(type, clobber, ibuf, addr, len); - - insn_len = lguest_insns[type].end - lguest_insns[type].start; - - /* Similarly if it can't fit (doesn't happen, but let's be thorough). */ - if (len < insn_len) - return paravirt_patch_default(type, clobber, ibuf, addr, len); - - /* Copy in our instructions. */ - memcpy(ibuf, lguest_insns[type].start, insn_len); - return insn_len; -} - -/*G:029 - * Once we get to lguest_init(), we know we're a Guest. The various - * pv_ops structures in the kernel provide points for (almost) every routine we - * have to override to avoid privileged instructions. - */ -__init void lguest_init(void) -{ - /* We're under lguest. */ - pv_info.name = "lguest"; - /* We're running at privilege level 1, not 0 as normal. */ - pv_info.kernel_rpl = 1; - /* Everyone except Xen runs with this set. */ - pv_info.shared_kernel_pmd = 1; - - /* - * We set up all the lguest overrides for sensitive operations. These - * are detailed with the operations themselves. - */ - - /* Interrupt-related operations */ - pv_irq_ops.save_fl = PV_CALLEE_SAVE(lguest_save_fl); - pv_irq_ops.restore_fl = __PV_IS_CALLEE_SAVE(lg_restore_fl); - pv_irq_ops.irq_disable = PV_CALLEE_SAVE(lguest_irq_disable); - pv_irq_ops.irq_enable = __PV_IS_CALLEE_SAVE(lg_irq_enable); - pv_irq_ops.safe_halt = lguest_safe_halt; - - /* Setup operations */ - pv_init_ops.patch = lguest_patch; - - /* Intercepts of various CPU instructions */ - pv_cpu_ops.load_gdt = lguest_load_gdt; - pv_cpu_ops.cpuid = lguest_cpuid; - pv_cpu_ops.load_idt = lguest_load_idt; - pv_cpu_ops.iret = lguest_iret; - pv_cpu_ops.load_sp0 = lguest_load_sp0; - pv_cpu_ops.load_tr_desc = lguest_load_tr_desc; - pv_cpu_ops.set_ldt = lguest_set_ldt; - pv_cpu_ops.load_tls = lguest_load_tls; - pv_cpu_ops.get_debugreg = lguest_get_debugreg; - pv_cpu_ops.set_debugreg = lguest_set_debugreg; - pv_cpu_ops.read_cr0 = lguest_read_cr0; - pv_cpu_ops.write_cr0 = lguest_write_cr0; - pv_cpu_ops.read_cr4 = lguest_read_cr4; - pv_cpu_ops.write_cr4 = lguest_write_cr4; - pv_cpu_ops.write_gdt_entry = lguest_write_gdt_entry; - pv_cpu_ops.write_idt_entry = lguest_write_idt_entry; - pv_cpu_ops.wbinvd = lguest_wbinvd; - pv_cpu_ops.start_context_switch = paravirt_start_context_switch; - pv_cpu_ops.end_context_switch = lguest_end_context_switch; - - /* Pagetable management */ - pv_mmu_ops.write_cr3 = lguest_write_cr3; - pv_mmu_ops.flush_tlb_user = lguest_flush_tlb_user; - pv_mmu_ops.flush_tlb_single = lguest_flush_tlb_single; - pv_mmu_ops.flush_tlb_kernel = lguest_flush_tlb_kernel; - pv_mmu_ops.set_pte = lguest_set_pte; - pv_mmu_ops.set_pte_at = lguest_set_pte_at; - pv_mmu_ops.set_pmd = lguest_set_pmd; -#ifdef CONFIG_X86_PAE - pv_mmu_ops.set_pte_atomic = lguest_set_pte_atomic; - pv_mmu_ops.pte_clear = lguest_pte_clear; - pv_mmu_ops.pmd_clear = lguest_pmd_clear; - pv_mmu_ops.set_pud = lguest_set_pud; -#endif - pv_mmu_ops.read_cr2 = lguest_read_cr2; - pv_mmu_ops.read_cr3 = lguest_read_cr3; - pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu; - pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode; - pv_mmu_ops.lazy_mode.flush = paravirt_flush_lazy_mmu; - pv_mmu_ops.pte_update = lguest_pte_update; - -#ifdef CONFIG_X86_LOCAL_APIC - /* APIC read/write intercepts */ - set_lguest_basic_apic_ops(); -#endif - - x86_init.resources.memory_setup = lguest_memory_setup; - x86_init.irqs.intr_init = lguest_init_IRQ; - x86_init.timers.timer_init = lguest_time_init; - x86_platform.calibrate_tsc = lguest_tsc_khz; - x86_platform.get_wallclock = lguest_get_wallclock; - - /* - * Now is a good time to look at the implementations of these functions - * before returning to the rest of lguest_init(). - */ - - /*G:070 - * Now we've seen all the paravirt_ops, we return to - * lguest_init() where the rest of the fairly chaotic boot setup - * occurs. - */ - - /* - * The stack protector is a weird thing where gcc places a canary - * value on the stack and then checks it on return. This file is - * compiled with -fno-stack-protector it, so we got this far without - * problems. The value of the canary is kept at offset 20 from the - * %gs register, so we need to set that up before calling C functions - * in other files. - */ - setup_stack_canary_segment(0); - - /* - * We could just call load_stack_canary_segment(), but we might as well - * call switch_to_new_gdt() which loads the whole table and sets up the - * per-cpu segment descriptor register %fs as well. - */ - switch_to_new_gdt(0); - - /* - * The Host<->Guest Switcher lives at the top of our address space, and - * the Host told us how big it is when we made LGUEST_INIT hypercall: - * it put the answer in lguest_data.reserve_mem - */ - reserve_top_address(lguest_data.reserve_mem); - - /* Hook in our special panic hypercall code. */ - atomic_notifier_chain_register(&panic_notifier_list, &paniced); - - /* - * This is messy CPU setup stuff which the native boot code does before - * start_kernel, so we have to do, too: - */ - cpu_detect(&new_cpu_data); - /* head.S usually sets up the first capability word, so do it here. */ - new_cpu_data.x86_capability[CPUID_1_EDX] = cpuid_edx(1); - - /* Math is always hard! */ - set_cpu_cap(&new_cpu_data, X86_FEATURE_FPU); - - /* We don't have features. We have puppies! Puppies! */ -#ifdef CONFIG_X86_MCE - mca_cfg.disabled = true; -#endif -#ifdef CONFIG_ACPI - acpi_disabled = 1; -#endif - - /* - * We set the preferred console to "hvc". This is the "hypervisor - * virtual console" driver written by the PowerPC people, which we also - * adapted for lguest's use. - */ - add_preferred_console("hvc", 0, NULL); - - /* Register our very early console. */ - virtio_cons_early_init(early_put_chars); - - /* Don't let ACPI try to control our PCI interrupts. */ - disable_acpi(); - - /* We control them ourselves, by overriding these two hooks. */ - pcibios_enable_irq = lguest_enable_irq; - pcibios_disable_irq = lguest_disable_irq; - - /* - * Last of all, we set the power management poweroff hook to point to - * the Guest routine to power off, and the reboot hook to our restart - * routine. - */ - pm_power_off = lguest_power_off; - machine_ops.restart = lguest_restart; - - /* - * Now we're set up, call i386_start_kernel() in head32.c and we proceed - * to boot as normal. It never returns. - */ - i386_start_kernel(); -} -/* - * This marks the end of stage II of our journey, The Guest. - * - * It is now time for us to explore the layer of virtual drivers and complete - * our understanding of the Guest in "make Drivers". - */ diff --git a/arch/x86/lguest/head_32.S b/arch/x86/lguest/head_32.S deleted file mode 100644 index d5ae63f5ec5d..000000000000 --- a/arch/x86/lguest/head_32.S +++ /dev/null @@ -1,192 +0,0 @@ -#include -#include -#include -#include -#include -#include - -/*G:020 - - * Our story starts with the bzImage: booting starts at startup_32 in - * arch/x86/boot/compressed/head_32.S. This merely uncompresses the real - * kernel in place and then jumps into it: startup_32 in - * arch/x86/kernel/head_32.S. Both routines expects a boot header in the %esi - * register, which is created by the bootloader (the Launcher in our case). - * - * The startup_32 function does very little: it clears the uninitialized global - * C variables which we expect to be zero (ie. BSS) and then copies the boot - * header and kernel command line somewhere safe, and populates some initial - * page tables. Finally it checks the 'hardware_subarch' field. This was - * introduced in 2.6.24 for lguest and Xen: if it's set to '1' (lguest's - * assigned number), then it calls us here. - * - * WARNING: be very careful here! We're running at addresses equal to physical - * addresses (around 0), not above PAGE_OFFSET as most code expects - * (eg. 0xC0000000). Jumps are relative, so they're OK, but we can't touch any - * data without remembering to subtract __PAGE_OFFSET! - * - * The .section line puts this code in .init.text so it will be discarded after - * boot. - */ -.section .init.text, "ax", @progbits -ENTRY(lguest_entry) - /* - * We make the "initialization" hypercall now to tell the Host where - * our lguest_data struct is. - */ - movl $LHCALL_LGUEST_INIT, %eax - movl $lguest_data - __PAGE_OFFSET, %ebx - int $LGUEST_TRAP_ENTRY - - /* Now turn our pagetables on; setup by arch/x86/kernel/head_32.S. */ - movl $LHCALL_NEW_PGTABLE, %eax - movl $(initial_page_table - __PAGE_OFFSET), %ebx - int $LGUEST_TRAP_ENTRY - - /* Set up the initial stack so we can run C code. */ - movl $(init_thread_union+THREAD_SIZE),%esp - - /* Jumps are relative: we're running __PAGE_OFFSET too low. */ - jmp lguest_init+__PAGE_OFFSET - -/*G:055 - * We create a macro which puts the assembler code between lgstart_ and lgend_ - * markers. These templates are put in the .text section: they can't be - * discarded after boot as we may need to patch modules, too. - */ -.text -#define LGUEST_PATCH(name, insns...) \ - lgstart_##name: insns; lgend_##name:; \ - .globl lgstart_##name; .globl lgend_##name - -LGUEST_PATCH(cli, movl $0, lguest_data+LGUEST_DATA_irq_enabled) -LGUEST_PATCH(pushf, movl lguest_data+LGUEST_DATA_irq_enabled, %eax) - -/*G:033 - * But using those wrappers is inefficient (we'll see why that doesn't matter - * for save_fl and irq_disable later). If we write our routines carefully in - * assembler, we can avoid clobbering any registers and avoid jumping through - * the wrapper functions. - * - * I skipped over our first piece of assembler, but this one is worth studying - * in a bit more detail so I'll describe in easy stages. First, the routine to - * enable interrupts: - */ -ENTRY(lg_irq_enable) - /* - * The reverse of irq_disable, this sets lguest_data.irq_enabled to - * X86_EFLAGS_IF (ie. "Interrupts enabled"). - */ - movl $X86_EFLAGS_IF, lguest_data+LGUEST_DATA_irq_enabled - /* - * But now we need to check if the Host wants to know: there might have - * been interrupts waiting to be delivered, in which case it will have - * set lguest_data.irq_pending to X86_EFLAGS_IF. If it's not zero, we - * jump to send_interrupts, otherwise we're done. - */ - cmpl $0, lguest_data+LGUEST_DATA_irq_pending - jnz send_interrupts - /* - * One cool thing about x86 is that you can do many things without using - * a register. In this case, the normal path hasn't needed to save or - * restore any registers at all! - */ - ret -send_interrupts: - /* - * OK, now we need a register: eax is used for the hypercall number, - * which is LHCALL_SEND_INTERRUPTS. - * - * We used not to bother with this pending detection at all, which was - * much simpler. Sooner or later the Host would realize it had to - * send us an interrupt. But that turns out to make performance 7 - * times worse on a simple tcp benchmark. So now we do this the hard - * way. - */ - pushl %eax - movl $LHCALL_SEND_INTERRUPTS, %eax - /* This is the actual hypercall trap. */ - int $LGUEST_TRAP_ENTRY - /* Put eax back the way we found it. */ - popl %eax - ret - -/* - * Finally, the "popf" or "restore flags" routine. The %eax register holds the - * flags (in practice, either X86_EFLAGS_IF or 0): if it's X86_EFLAGS_IF we're - * enabling interrupts again, if it's 0 we're leaving them off. - */ -ENTRY(lg_restore_fl) - /* This is just "lguest_data.irq_enabled = flags;" */ - movl %eax, lguest_data+LGUEST_DATA_irq_enabled - /* - * Now, if the %eax value has enabled interrupts and - * lguest_data.irq_pending is set, we want to tell the Host so it can - * deliver any outstanding interrupts. Fortunately, both values will - * be X86_EFLAGS_IF (ie. 512) in that case, and the "testl" - * instruction will AND them together for us. If both are set, we - * jump to send_interrupts. - */ - testl lguest_data+LGUEST_DATA_irq_pending, %eax - jnz send_interrupts - /* Again, the normal path has used no extra registers. Clever, huh? */ - ret -/*:*/ - -/* These demark the EIP where host should never deliver interrupts. */ -.global lguest_noirq_iret - -/*M:004 - * When the Host reflects a trap or injects an interrupt into the Guest, it - * sets the eflags interrupt bit on the stack based on lguest_data.irq_enabled, - * so the Guest iret logic does the right thing when restoring it. However, - * when the Host sets the Guest up for direct traps, such as system calls, the - * processor is the one to push eflags onto the stack, and the interrupt bit - * will be 1 (in reality, interrupts are always enabled in the Guest). - * - * This turns out to be harmless: the only trap which should happen under Linux - * with interrupts disabled is Page Fault (due to our lazy mapping of vmalloc - * regions), which has to be reflected through the Host anyway. If another - * trap *does* go off when interrupts are disabled, the Guest will panic, and - * we'll never get to this iret! -:*/ - -/*G:045 - * There is one final paravirt_op that the Guest implements, and glancing at it - * you can see why I left it to last. It's *cool*! It's in *assembler*! - * - * The "iret" instruction is used to return from an interrupt or trap. The - * stack looks like this: - * old address - * old code segment & privilege level - * old processor flags ("eflags") - * - * The "iret" instruction pops those values off the stack and restores them all - * at once. The only problem is that eflags includes the Interrupt Flag which - * the Guest can't change: the CPU will simply ignore it when we do an "iret". - * So we have to copy eflags from the stack to lguest_data.irq_enabled before - * we do the "iret". - * - * There are two problems with this: firstly, we can't clobber any registers - * and secondly, the whole thing needs to be atomic. The first problem - * is solved by using "push memory"/"pop memory" instruction pair for copying. - * - * The second is harder: copying eflags to lguest_data.irq_enabled will turn - * interrupts on before we're finished, so we could be interrupted before we - * return to userspace or wherever. Our solution to this is to tell the - * Host that it is *never* to interrupt us there, even if interrupts seem to be - * enabled. (It's not necessary to protect pop instruction, since - * data gets updated only after it completes, so we only need to protect - * one instruction, iret). - */ -ENTRY(lguest_iret) - pushl 2*4(%esp) - /* - * Note the %ss: segment prefix here. Normal data accesses use the - * "ds" segment, but that will have already been restored for whatever - * we're returning to (such as userspace): we can't trust it. The %ss: - * prefix makes sure we use the stack segment, which is still valid. - */ - popl %ss:lguest_data+LGUEST_DATA_irq_enabled -lguest_noirq_iret: - iret diff --git a/drivers/Makefile b/drivers/Makefile index dfdcda00bfe3..d90fdc413648 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -125,7 +125,6 @@ obj-$(CONFIG_ACCESSIBILITY) += accessibility/ obj-$(CONFIG_ISDN) += isdn/ obj-$(CONFIG_EDAC) += edac/ obj-$(CONFIG_EISA) += eisa/ -obj-y += lguest/ obj-$(CONFIG_CPU_FREQ) += cpufreq/ obj-$(CONFIG_CPU_IDLE) += cpuidle/ obj-y += mmc/ diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 8ddc98279c8f..80aaf3420e12 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -470,7 +470,7 @@ config VIRTIO_BLK depends on VIRTIO ---help--- This is the virtual block driver for virtio. It can be used with - lguest or QEMU based VMMs (like KVM or Xen). Say Y or M. + QEMU based VMMs (like KVM or Xen). Say Y or M. config VIRTIO_BLK_SCSI bool "SCSI passthrough request for the Virtio block driver" diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig index ccd239ab879f..623714344600 100644 --- a/drivers/char/Kconfig +++ b/drivers/char/Kconfig @@ -161,7 +161,7 @@ config VIRTIO_CONSOLE depends on VIRTIO && TTY select HVC_DRIVER help - Virtio console for use with lguest and other hypervisors. + Virtio console for use with hypervisors. Also serves as a general-purpose serial device for data transfer between the guest and host. Character devices at diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index ad843eb02ae7..4d229dde6522 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -1130,7 +1130,7 @@ static const struct file_operations port_fops = { * We turn the characters into a scatter-gather list, add it to the * output queue and then kick the Host. Then we sit here waiting for * it to finish: inefficient in theory, but in practice - * implementations will do it immediately (lguest's Launcher does). + * implementations will do it immediately. */ static int put_chars(u32 vtermno, const char *buf, int count) { diff --git a/drivers/lguest/Kconfig b/drivers/lguest/Kconfig deleted file mode 100644 index 169172d2ba05..000000000000 --- a/drivers/lguest/Kconfig +++ /dev/null @@ -1,13 +0,0 @@ -config LGUEST - tristate "Linux hypervisor example code" - depends on X86_32 && EVENTFD && TTY && PCI_DIRECT - select HVC_DRIVER - ---help--- - This is a very simple module which allows you to run - multiple instances of the same Linux kernel, using the - "lguest" command found in the tools/lguest directory. - - Note that "lguest" is pronounced to rhyme with "fell quest", - not "rustyvisor". See tools/lguest/lguest.txt. - - If unsure, say N. If curious, say M. If masochistic, say Y. diff --git a/drivers/lguest/Makefile b/drivers/lguest/Makefile deleted file mode 100644 index 16f52ee73994..000000000000 --- a/drivers/lguest/Makefile +++ /dev/null @@ -1,26 +0,0 @@ -# Host requires the other files, which can be a module. -obj-$(CONFIG_LGUEST) += lg.o -lg-y = core.o hypercalls.o page_tables.o interrupts_and_traps.o \ - segments.o lguest_user.o - -lg-$(CONFIG_X86_32) += x86/switcher_32.o x86/core.o - -Preparation Preparation!: PREFIX=P -Guest: PREFIX=G -Drivers: PREFIX=D -Launcher: PREFIX=L -Host: PREFIX=H -Switcher: PREFIX=S -Mastery: PREFIX=M -Beer: - @for f in Preparation Guest Drivers Launcher Host Switcher Mastery; do echo "{==- $$f -==}"; make -s $$f; done; echo "{==-==}" -Preparation Preparation! Guest Drivers Launcher Host Switcher Mastery: - @sh ../../tools/lguest/extract $(PREFIX) `find ../../* -name '*.[chS]' -wholename '*lguest*'` -Puppy: - @clear - @printf " __ \n (___()'\`;\n /, /\`\n \\\\\\\"--\\\\\\ \n" - @sleep 2; clear; printf "\n\n Sit!\n\n"; sleep 1; clear - @printf " __ \n ()'\`; \n /\\|\` \n / | \n(/_)_|_ \n" - @sleep 2; clear; printf "\n\n Stand!\n\n"; sleep 1; clear - @printf " __ \n ()'\`; \n /\\|\` \n /._.= \n /| / \n(_\_)_ \n" - @sleep 2; clear; printf "\n\n Good puppy!\n\n"; sleep 1; clear diff --git a/drivers/lguest/README b/drivers/lguest/README deleted file mode 100644 index b7db39a64c66..000000000000 --- a/drivers/lguest/README +++ /dev/null @@ -1,47 +0,0 @@ -Welcome, friend reader, to lguest. - -Lguest is an adventure, with you, the reader, as Hero. I can't think of many -5000-line projects which offer both such capability and glimpses of future -potential; it is an exciting time to be delving into the source! - -But be warned; this is an arduous journey of several hours or more! And as we -know, all true Heroes are driven by a Noble Goal. Thus I offer a Beer (or -equivalent) to anyone I meet who has completed this documentation. - -So get comfortable and keep your wits about you (both quick and humorous). -Along your way to the Noble Goal, you will also gain masterly insight into -lguest, and hypervisors and x86 virtualization in general. - -Our Quest is in seven parts: (best read with C highlighting turned on) - -I) Preparation - - In which our potential hero is flown quickly over the landscape for a - taste of its scope. Suitable for the armchair coders and other such - persons of faint constitution. - -II) Guest - - Where we encounter the first tantalising wisps of code, and come to - understand the details of the life of a Guest kernel. - -III) Drivers - - Whereby the Guest finds its voice and become useful, and our - understanding of the Guest is completed. - -IV) Launcher - - Where we trace back to the creation of the Guest, and thus begin our - understanding of the Host. - -V) Host - - Where we master the Host code, through a long and tortuous journey. - Indeed, it is here that our hero is tested in the Bit of Despair. - -VI) Switcher - - Where our understanding of the intertwined nature of Guests and Hosts - is completed. - -VII) Mastery - - Where our fully fledged hero grapples with the Great Question: - "What next?" - -make Preparation! -Rusty Russell. diff --git a/drivers/lguest/core.c b/drivers/lguest/core.c deleted file mode 100644 index 395ed1961dbf..000000000000 --- a/drivers/lguest/core.c +++ /dev/null @@ -1,398 +0,0 @@ -/*P:400 - * This contains run_guest() which actually calls into the Host<->Guest - * Switcher and analyzes the return, such as determining if the Guest wants the - * Host to do something. This file also contains useful helper routines. -:*/ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include "lg.h" - -unsigned long switcher_addr; -struct page **lg_switcher_pages; -static struct vm_struct *switcher_text_vma; -static struct vm_struct *switcher_stacks_vma; - -/* This One Big lock protects all inter-guest data structures. */ -DEFINE_MUTEX(lguest_lock); - -/*H:010 - * We need to set up the Switcher at a high virtual address. Remember the - * Switcher is a few hundred bytes of assembler code which actually changes the - * CPU to run the Guest, and then changes back to the Host when a trap or - * interrupt happens. - * - * The Switcher code must be at the same virtual address in the Guest as the - * Host since it will be running as the switchover occurs. - * - * Trying to map memory at a particular address is an unusual thing to do, so - * it's not a simple one-liner. - */ -static __init int map_switcher(void) -{ - int i, err; - - /* - * Map the Switcher in to high memory. - * - * It turns out that if we choose the address 0xFFC00000 (4MB under the - * top virtual address), it makes setting up the page tables really - * easy. - */ - - /* We assume Switcher text fits into a single page. */ - if (end_switcher_text - start_switcher_text > PAGE_SIZE) { - printk(KERN_ERR "lguest: switcher text too large (%zu)\n", - end_switcher_text - start_switcher_text); - return -EINVAL; - } - - /* - * We allocate an array of struct page pointers. map_vm_area() wants - * this, rather than just an array of pages. - */ - lg_switcher_pages = kmalloc(sizeof(lg_switcher_pages[0]) - * TOTAL_SWITCHER_PAGES, - GFP_KERNEL); - if (!lg_switcher_pages) { - err = -ENOMEM; - goto out; - } - - /* - * Now we actually allocate the pages. The Guest will see these pages, - * so we make sure they're zeroed. - */ - for (i = 0; i < TOTAL_SWITCHER_PAGES; i++) { - lg_switcher_pages[i] = alloc_page(GFP_KERNEL|__GFP_ZERO); - if (!lg_switcher_pages[i]) { - err = -ENOMEM; - goto free_some_pages; - } - } - - /* - * Copy in the compiled-in Switcher code (from x86/switcher_32.S). - * It goes in the first page, which we map in momentarily. - */ - memcpy(kmap(lg_switcher_pages[0]), start_switcher_text, - end_switcher_text - start_switcher_text); - kunmap(lg_switcher_pages[0]); - - /* - * We place the Switcher underneath the fixmap area, which is the - * highest virtual address we can get. This is important, since we - * tell the Guest it can't access this memory, so we want its ceiling - * as high as possible. - */ - switcher_addr = FIXADDR_START - TOTAL_SWITCHER_PAGES*PAGE_SIZE; - - /* - * Now we reserve the "virtual memory area"s we want. We might - * not get them in theory, but in practice it's worked so far. - * - * We want the switcher text to be read-only and executable, and - * the stacks to be read-write and non-executable. - */ - switcher_text_vma = __get_vm_area(PAGE_SIZE, VM_ALLOC|VM_NO_GUARD, - switcher_addr, - switcher_addr + PAGE_SIZE); - - if (!switcher_text_vma) { - err = -ENOMEM; - printk("lguest: could not map switcher pages high\n"); - goto free_pages; - } - - switcher_stacks_vma = __get_vm_area(SWITCHER_STACK_PAGES * PAGE_SIZE, - VM_ALLOC|VM_NO_GUARD, - switcher_addr + PAGE_SIZE, - switcher_addr + TOTAL_SWITCHER_PAGES * PAGE_SIZE); - if (!switcher_stacks_vma) { - err = -ENOMEM; - printk("lguest: could not map switcher pages high\n"); - goto free_text_vma; - } - - /* - * This code actually sets up the pages we've allocated to appear at - * switcher_addr. map_vm_area() takes the vma we allocated above, the - * kind of pages we're mapping (kernel text pages and kernel writable - * pages respectively), and a pointer to our array of struct pages. - */ - err = map_vm_area(switcher_text_vma, PAGE_KERNEL_RX, lg_switcher_pages); - if (err) { - printk("lguest: text map_vm_area failed: %i\n", err); - goto free_vmas; - } - - err = map_vm_area(switcher_stacks_vma, PAGE_KERNEL, - lg_switcher_pages + SWITCHER_TEXT_PAGES); - if (err) { - printk("lguest: stacks map_vm_area failed: %i\n", err); - goto free_vmas; - } - - /* - * Now the Switcher is mapped at the right address, we can't fail! - */ - printk(KERN_INFO "lguest: mapped switcher at %p\n", - switcher_text_vma->addr); - /* And we succeeded... */ - return 0; - -free_vmas: - /* Undoes map_vm_area and __get_vm_area */ - vunmap(switcher_stacks_vma->addr); -free_text_vma: - vunmap(switcher_text_vma->addr); -free_pages: - i = TOTAL_SWITCHER_PAGES; -free_some_pages: - for (--i; i >= 0; i--) - __free_pages(lg_switcher_pages[i], 0); - kfree(lg_switcher_pages); -out: - return err; -} -/*:*/ - -/* Cleaning up the mapping when the module is unloaded is almost... too easy. */ -static void unmap_switcher(void) -{ - unsigned int i; - - /* vunmap() undoes *both* map_vm_area() and __get_vm_area(). */ - vunmap(switcher_text_vma->addr); - vunmap(switcher_stacks_vma->addr); - /* Now we just need to free the pages we copied the switcher into */ - for (i = 0; i < TOTAL_SWITCHER_PAGES; i++) - __free_pages(lg_switcher_pages[i], 0); - kfree(lg_switcher_pages); -} - -/*H:032 - * Dealing With Guest Memory. - * - * Before we go too much further into the Host, we need to grok the routines - * we use to deal with Guest memory. - * - * When the Guest gives us (what it thinks is) a physical address, we can use - * the normal copy_from_user() & copy_to_user() on the corresponding place in - * the memory region allocated by the Launcher. - * - * But we can't trust the Guest: it might be trying to access the Launcher - * code. We have to check that the range is below the pfn_limit the Launcher - * gave us. We have to make sure that addr + len doesn't give us a false - * positive by overflowing, too. - */ -bool lguest_address_ok(const struct lguest *lg, - unsigned long addr, unsigned long len) -{ - return addr+len <= lg->pfn_limit * PAGE_SIZE && (addr+len >= addr); -} - -/* - * This routine copies memory from the Guest. Here we can see how useful the - * kill_lguest() routine we met in the Launcher can be: we return a random - * value (all zeroes) instead of needing to return an error. - */ -void __lgread(struct lg_cpu *cpu, void *b, unsigned long addr, unsigned bytes) -{ - if (!lguest_address_ok(cpu->lg, addr, bytes) - || copy_from_user(b, cpu->lg->mem_base + addr, bytes) != 0) { - /* copy_from_user should do this, but as we rely on it... */ - memset(b, 0, bytes); - kill_guest(cpu, "bad read address %#lx len %u", addr, bytes); - } -} - -/* This is the write (copy into Guest) version. */ -void __lgwrite(struct lg_cpu *cpu, unsigned long addr, const void *b, - unsigned bytes) -{ - if (!lguest_address_ok(cpu->lg, addr, bytes) - || copy_to_user(cpu->lg->mem_base + addr, b, bytes) != 0) - kill_guest(cpu, "bad write address %#lx len %u", addr, bytes); -} -/*:*/ - -/*H:030 - * Let's jump straight to the the main loop which runs the Guest. - * Remember, this is called by the Launcher reading /dev/lguest, and we keep - * going around and around until something interesting happens. - */ -int run_guest(struct lg_cpu *cpu, unsigned long __user *user) -{ - /* If the launcher asked for a register with LHREQ_GETREG */ - if (cpu->reg_read) { - if (put_user(*cpu->reg_read, user)) - return -EFAULT; - cpu->reg_read = NULL; - return sizeof(*cpu->reg_read); - } - - /* We stop running once the Guest is dead. */ - while (!cpu->lg->dead) { - unsigned int irq; - bool more; - - /* First we run any hypercalls the Guest wants done. */ - if (cpu->hcall) - do_hypercalls(cpu); - - /* Do we have to tell the Launcher about a trap? */ - if (cpu->pending.trap) { - if (copy_to_user(user, &cpu->pending, - sizeof(cpu->pending))) - return -EFAULT; - return sizeof(cpu->pending); - } - - /* - * All long-lived kernel loops need to check with this horrible - * thing called the freezer. If the Host is trying to suspend, - * it stops us. - */ - try_to_freeze(); - - /* Check for signals */ - if (signal_pending(current)) - return -ERESTARTSYS; - - /* - * Check if there are any interrupts which can be delivered now: - * if so, this sets up the hander to be executed when we next - * run the Guest. - */ - irq = interrupt_pending(cpu, &more); - if (irq < LGUEST_IRQS) - try_deliver_interrupt(cpu, irq, more); - - /* - * Just make absolutely sure the Guest is still alive. One of - * those hypercalls could have been fatal, for example. - */ - if (cpu->lg->dead) - break; - - /* - * If the Guest asked to be stopped, we sleep. The Guest's - * clock timer will wake us. - */ - if (cpu->halted) { - set_current_state(TASK_INTERRUPTIBLE); - /* - * Just before we sleep, make sure no interrupt snuck in - * which we should be doing. - */ - if (interrupt_pending(cpu, &more) < LGUEST_IRQS) - set_current_state(TASK_RUNNING); - else - schedule(); - continue; - } - - /* - * OK, now we're ready to jump into the Guest. First we put up - * the "Do Not Disturb" sign: - */ - local_irq_disable(); - - /* Actually run the Guest until something happens. */ - lguest_arch_run_guest(cpu); - - /* Now we're ready to be interrupted or moved to other CPUs */ - local_irq_enable(); - - /* Now we deal with whatever happened to the Guest. */ - lguest_arch_handle_trap(cpu); - } - - /* Special case: Guest is 'dead' but wants a reboot. */ - if (cpu->lg->dead == ERR_PTR(-ERESTART)) - return -ERESTART; - - /* The Guest is dead => "No such file or directory" */ - return -ENOENT; -} - -/*H:000 - * Welcome to the Host! - * - * By this point your brain has been tickled by the Guest code and numbed by - * the Launcher code; prepare for it to be stretched by the Host code. This is - * the heart. Let's begin at the initialization routine for the Host's lg - * module. - */ -static int __init init(void) -{ - int err; - - /* Lguest can't run under Xen, VMI or itself. It does Tricky Stuff. */ - if (get_kernel_rpl() != 0) { - printk("lguest is afraid of being a guest\n"); - return -EPERM; - } - - /* First we put the Switcher up in very high virtual memory. */ - err = map_switcher(); - if (err) - goto out; - - /* We might need to reserve an interrupt vector. */ - err = init_interrupts(); - if (err) - goto unmap; - - /* /dev/lguest needs to be registered. */ - err = lguest_device_init(); - if (err) - goto free_interrupts; - - /* Finally we do some architecture-specific setup. */ - lguest_arch_host_init(); - - /* All good! */ - return 0; - -free_interrupts: - free_interrupts(); -unmap: - unmap_switcher(); -out: - return err; -} - -/* Cleaning up is just the same code, backwards. With a little French. */ -static void __exit fini(void) -{ - lguest_device_remove(); - free_interrupts(); - unmap_switcher(); - - lguest_arch_host_fini(); -} -/*:*/ - -/* - * The Host side of lguest can be a module. This is a nice way for people to - * play with it. - */ -module_init(init); -module_exit(fini); -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Rusty Russell "); diff --git a/drivers/lguest/hypercalls.c b/drivers/lguest/hypercalls.c deleted file mode 100644 index 601f81c04873..000000000000 --- a/drivers/lguest/hypercalls.c +++ /dev/null @@ -1,304 +0,0 @@ -/*P:500 - * Just as userspace programs request kernel operations through a system - * call, the Guest requests Host operations through a "hypercall". You might - * notice this nomenclature doesn't really follow any logic, but the name has - * been around for long enough that we're stuck with it. As you'd expect, this - * code is basically a one big switch statement. -:*/ - -/* Copyright (C) 2006 Rusty Russell IBM Corporation - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - (at your option) any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA -*/ -#include -#include -#include -#include -#include -#include -#include "lg.h" - -/*H:120 - * This is the core hypercall routine: where the Guest gets what it wants. - * Or gets killed. Or, in the case of LHCALL_SHUTDOWN, both. - */ -static void do_hcall(struct lg_cpu *cpu, struct hcall_args *args) -{ - switch (args->arg0) { - case LHCALL_FLUSH_ASYNC: - /* - * This call does nothing, except by breaking out of the Guest - * it makes us process all the asynchronous hypercalls. - */ - break; - case LHCALL_SEND_INTERRUPTS: - /* - * This call does nothing too, but by breaking out of the Guest - * it makes us process any pending interrupts. - */ - break; - case LHCALL_LGUEST_INIT: - /* - * You can't get here unless you're already initialized. Don't - * do that. - */ - kill_guest(cpu, "already have lguest_data"); - break; - case LHCALL_SHUTDOWN: { - char msg[128]; - /* - * Shutdown is such a trivial hypercall that we do it in five - * lines right here. - * - * If the lgread fails, it will call kill_guest() itself; the - * kill_guest() with the message will be ignored. - */ - __lgread(cpu, msg, args->arg1, sizeof(msg)); - msg[sizeof(msg)-1] = '\0'; - kill_guest(cpu, "CRASH: %s", msg); - if (args->arg2 == LGUEST_SHUTDOWN_RESTART) - cpu->lg->dead = ERR_PTR(-ERESTART); - break; - } - case LHCALL_FLUSH_TLB: - /* FLUSH_TLB comes in two flavors, depending on the argument: */ - if (args->arg1) - guest_pagetable_clear_all(cpu); - else - guest_pagetable_flush_user(cpu); - break; - - /* - * All these calls simply pass the arguments through to the right - * routines. - */ - case LHCALL_NEW_PGTABLE: - guest_new_pagetable(cpu, args->arg1); - break; - case LHCALL_SET_STACK: - guest_set_stack(cpu, args->arg1, args->arg2, args->arg3); - break; - case LHCALL_SET_PTE: -#ifdef CONFIG_X86_PAE - guest_set_pte(cpu, args->arg1, args->arg2, - __pte(args->arg3 | (u64)args->arg4 << 32)); -#else - guest_set_pte(cpu, args->arg1, args->arg2, __pte(args->arg3)); -#endif - break; - case LHCALL_SET_PGD: - guest_set_pgd(cpu->lg, args->arg1, args->arg2); - break; -#ifdef CONFIG_X86_PAE - case LHCALL_SET_PMD: - guest_set_pmd(cpu->lg, args->arg1, args->arg2); - break; -#endif - case LHCALL_SET_CLOCKEVENT: - guest_set_clockevent(cpu, args->arg1); - break; - case LHCALL_HALT: - /* Similarly, this sets the halted flag for run_guest(). */ - cpu->halted = 1; - break; - default: - /* It should be an architecture-specific hypercall. */ - if (lguest_arch_do_hcall(cpu, args)) - kill_guest(cpu, "Bad hypercall %li\n", args->arg0); - } -} - -/*H:124 - * Asynchronous hypercalls are easy: we just look in the array in the - * Guest's "struct lguest_data" to see if any new ones are marked "ready". - * - * We are careful to do these in order: obviously we respect the order the - * Guest put them in the ring, but we also promise the Guest that they will - * happen before any normal hypercall (which is why we check this before - * checking for a normal hcall). - */ -static void do_async_hcalls(struct lg_cpu *cpu) -{ - unsigned int i; - u8 st[LHCALL_RING_SIZE]; - - /* For simplicity, we copy the entire call status array in at once. */ - if (copy_from_user(&st, &cpu->lg->lguest_data->hcall_status, sizeof(st))) - return; - - /* We process "struct lguest_data"s hcalls[] ring once. */ - for (i = 0; i < ARRAY_SIZE(st); i++) { - struct hcall_args args; - /* - * We remember where we were up to from last time. This makes - * sure that the hypercalls are done in the order the Guest - * places them in the ring. - */ - unsigned int n = cpu->next_hcall; - - /* 0xFF means there's no call here (yet). */ - if (st[n] == 0xFF) - break; - - /* - * OK, we have hypercall. Increment the "next_hcall" cursor, - * and wrap back to 0 if we reach the end. - */ - if (++cpu->next_hcall == LHCALL_RING_SIZE) - cpu->next_hcall = 0; - - /* - * Copy the hypercall arguments into a local copy of the - * hcall_args struct. - */ - if (copy_from_user(&args, &cpu->lg->lguest_data->hcalls[n], - sizeof(struct hcall_args))) { - kill_guest(cpu, "Fetching async hypercalls"); - break; - } - - /* Do the hypercall, same as a normal one. */ - do_hcall(cpu, &args); - - /* Mark the hypercall done. */ - if (put_user(0xFF, &cpu->lg->lguest_data->hcall_status[n])) { - kill_guest(cpu, "Writing result for async hypercall"); - break; - } - - /* - * Stop doing hypercalls if they want to notify the Launcher: - * it needs to service this first. - */ - if (cpu->pending.trap) - break; - } -} - -/* - * Last of all, we look at what happens first of all. The very first time the - * Guest makes a hypercall, we end up here to set things up: - */ -static void initialize(struct lg_cpu *cpu) -{ - /* - * You can't do anything until you're initialized. The Guest knows the - * rules, so we're unforgiving here. - */ - if (cpu->hcall->arg0 != LHCALL_LGUEST_INIT) { - kill_guest(cpu, "hypercall %li before INIT", cpu->hcall->arg0); - return; - } - - if (lguest_arch_init_hypercalls(cpu)) - kill_guest(cpu, "bad guest page %p", cpu->lg->lguest_data); - - /* - * The Guest tells us where we're not to deliver interrupts by putting - * the instruction address into "struct lguest_data". - */ - if (get_user(cpu->lg->noirq_iret, &cpu->lg->lguest_data->noirq_iret)) - kill_guest(cpu, "bad guest page %p", cpu->lg->lguest_data); - - /* - * We write the current time into the Guest's data page once so it can - * set its clock. - */ - write_timestamp(cpu); - - /* page_tables.c will also do some setup. */ - page_table_guest_data_init(cpu); - - /* - * This is the one case where the above accesses might have been the - * first write to a Guest page. This may have caused a copy-on-write - * fault, but the old page might be (read-only) in the Guest - * pagetable. - */ - guest_pagetable_clear_all(cpu); -} -/*:*/ - -/*M:013 - * If a Guest reads from a page (so creates a mapping) that it has never - * written to, and then the Launcher writes to it (ie. the output of a virtual - * device), the Guest will still see the old page. In practice, this never - * happens: why would the Guest read a page which it has never written to? But - * a similar scenario might one day bite us, so it's worth mentioning. - * - * Note that if we used a shared anonymous mapping in the Launcher instead of - * mapping /dev/zero private, we wouldn't worry about cop-on-write. And we - * need that to switch the Launcher to processes (away from threads) anyway. -:*/ - -/*H:100 - * Hypercalls - * - * Remember from the Guest, hypercalls come in two flavors: normal and - * asynchronous. This file handles both of types. - */ -void do_hypercalls(struct lg_cpu *cpu) -{ - /* Not initialized yet? This hypercall must do it. */ - if (unlikely(!cpu->lg->lguest_data)) { - /* Set up the "struct lguest_data" */ - initialize(cpu); - /* Hcall is done. */ - cpu->hcall = NULL; - return; - } - - /* - * The Guest has initialized. - * - * Look in the hypercall ring for the async hypercalls: - */ - do_async_hcalls(cpu); - - /* - * If we stopped reading the hypercall ring because the Guest did a - * NOTIFY to the Launcher, we want to return now. Otherwise we do - * the hypercall. - */ - if (!cpu->pending.trap) { - do_hcall(cpu, cpu->hcall); - /* - * Tricky point: we reset the hcall pointer to mark the - * hypercall as "done". We use the hcall pointer rather than - * the trap number to indicate a hypercall is pending. - * Normally it doesn't matter: the Guest will run again and - * update the trap number before we come back here. - * - * However, if we are signalled or the Guest sends I/O to the - * Launcher, the run_guest() loop will exit without running the - * Guest. When it comes back it would try to re-run the - * hypercall. Finding that bug sucked. - */ - cpu->hcall = NULL; - } -} - -/* - * This routine supplies the Guest with time: it's used for wallclock time at - * initial boot and as a rough time source if the TSC isn't available. - */ -void write_timestamp(struct lg_cpu *cpu) -{ - struct timespec now; - ktime_get_real_ts(&now); - if (copy_to_user(&cpu->lg->lguest_data->time, - &now, sizeof(struct timespec))) - kill_guest(cpu, "Writing timestamp"); -} diff --git a/drivers/lguest/interrupts_and_traps.c b/drivers/lguest/interrupts_and_traps.c deleted file mode 100644 index 67392b6ab845..000000000000 --- a/drivers/lguest/interrupts_and_traps.c +++ /dev/null @@ -1,706 +0,0 @@ -/*P:800 - * Interrupts (traps) are complicated enough to earn their own file. - * There are three classes of interrupts: - * - * 1) Real hardware interrupts which occur while we're running the Guest, - * 2) Interrupts for virtual devices attached to the Guest, and - * 3) Traps and faults from the Guest. - * - * Real hardware interrupts must be delivered to the Host, not the Guest. - * Virtual interrupts must be delivered to the Guest, but we make them look - * just like real hardware would deliver them. Traps from the Guest can be set - * up to go directly back into the Guest, but sometimes the Host wants to see - * them first, so we also have a way of "reflecting" them into the Guest as if - * they had been delivered to it directly. -:*/ -#include -#include -#include -#include -#include "lg.h" - -/* Allow Guests to use a non-128 (ie. non-Linux) syscall trap. */ -static unsigned int syscall_vector = IA32_SYSCALL_VECTOR; -module_param(syscall_vector, uint, 0444); - -/* The address of the interrupt handler is split into two bits: */ -static unsigned long idt_address(u32 lo, u32 hi) -{ - return (lo & 0x0000FFFF) | (hi & 0xFFFF0000); -} - -/* - * The "type" of the interrupt handler is a 4 bit field: we only support a - * couple of types. - */ -static int idt_type(u32 lo, u32 hi) -{ - return (hi >> 8) & 0xF; -} - -/* An IDT entry can't be used unless the "present" bit is set. */ -static bool idt_present(u32 lo, u32 hi) -{ - return (hi & 0x8000); -} - -/* - * We need a helper to "push" a value onto the Guest's stack, since that's a - * big part of what delivering an interrupt does. - */ -static void push_guest_stack(struct lg_cpu *cpu, unsigned long *gstack, u32 val) -{ - /* Stack grows upwards: move stack then write value. */ - *gstack -= 4; - lgwrite(cpu, *gstack, u32, val); -} - -/*H:210 - * The push_guest_interrupt_stack() routine saves Guest state on the stack for - * an interrupt or trap. The mechanics of delivering traps and interrupts to - * the Guest are the same, except some traps have an "error code" which gets - * pushed onto the stack as well: the caller tells us if this is one. - * - * We set up the stack just like the CPU does for a real interrupt, so it's - * identical for the Guest (and the standard "iret" instruction will undo - * it). - */ -static void push_guest_interrupt_stack(struct lg_cpu *cpu, bool has_err) -{ - unsigned long gstack, origstack; - u32 eflags, ss, irq_enable; - unsigned long virtstack; - - /* - * There are two cases for interrupts: one where the Guest is already - * in the kernel, and a more complex one where the Guest is in - * userspace. We check the privilege level to find out. - */ - if ((cpu->regs->ss&0x3) != GUEST_PL) { - /* - * The Guest told us their kernel stack with the SET_STACK - * hypercall: both the virtual address and the segment. - */ - virtstack = cpu->esp1; - ss = cpu->ss1; - - origstack = gstack = guest_pa(cpu, virtstack); - /* - * We push the old stack segment and pointer onto the new - * stack: when the Guest does an "iret" back from the interrupt - * handler the CPU will notice they're dropping privilege - * levels and expect these here. - */ - push_guest_stack(cpu, &gstack, cpu->regs->ss); - push_guest_stack(cpu, &gstack, cpu->regs->esp); - } else { - /* We're staying on the same Guest (kernel) stack. */ - virtstack = cpu->regs->esp; - ss = cpu->regs->ss; - - origstack = gstack = guest_pa(cpu, virtstack); - } - - /* - * Remember that we never let the Guest actually disable interrupts, so - * the "Interrupt Flag" bit is always set. We copy that bit from the - * Guest's "irq_enabled" field into the eflags word: we saw the Guest - * copy it back in "lguest_iret". - */ - eflags = cpu->regs->eflags; - if (get_user(irq_enable, &cpu->lg->lguest_data->irq_enabled) == 0 - && !(irq_enable & X86_EFLAGS_IF)) - eflags &= ~X86_EFLAGS_IF; - - /* - * An interrupt is expected to push three things on the stack: the old - * "eflags" word, the old code segment, and the old instruction - * pointer. - */ - push_guest_stack(cpu, &gstack, eflags); - push_guest_stack(cpu, &gstack, cpu->regs->cs); - push_guest_stack(cpu, &gstack, cpu->regs->eip); - - /* For the six traps which supply an error code, we push that, too. */ - if (has_err) - push_guest_stack(cpu, &gstack, cpu->regs->errcode); - - /* Adjust the stack pointer and stack segment. */ - cpu->regs->ss = ss; - cpu->regs->esp = virtstack + (gstack - origstack); -} - -/* - * This actually makes the Guest start executing the given interrupt/trap - * handler. - * - * "lo" and "hi" are the two parts of the Interrupt Descriptor Table for this - * interrupt or trap. It's split into two parts for traditional reasons: gcc - * on i386 used to be frightened by 64 bit numbers. - */ -static void guest_run_interrupt(struct lg_cpu *cpu, u32 lo, u32 hi) -{ - /* If we're already in the kernel, we don't change stacks. */ - if ((cpu->regs->ss&0x3) != GUEST_PL) - cpu->regs->ss = cpu->esp1; - - /* - * Set the code segment and the address to execute. - */ - cpu->regs->cs = (__KERNEL_CS|GUEST_PL); - cpu->regs->eip = idt_address(lo, hi); - - /* - * Trapping always clears these flags: - * TF: Trap flag - * VM: Virtual 8086 mode - * RF: Resume - * NT: Nested task. - */ - cpu->regs->eflags &= - ~(X86_EFLAGS_TF|X86_EFLAGS_VM|X86_EFLAGS_RF|X86_EFLAGS_NT); - - /* - * There are two kinds of interrupt handlers: 0xE is an "interrupt - * gate" which expects interrupts to be disabled on entry. - */ - if (idt_type(lo, hi) == 0xE) - if (put_user(0, &cpu->lg->lguest_data->irq_enabled)) - kill_guest(cpu, "Disabling interrupts"); -} - -/* This restores the eflags word which was pushed on the stack by a trap */ -static void restore_eflags(struct lg_cpu *cpu) -{ - /* This is the physical address of the stack. */ - unsigned long stack_pa = guest_pa(cpu, cpu->regs->esp); - - /* - * Stack looks like this: - * Address Contents - * esp EIP - * esp + 4 CS - * esp + 8 EFLAGS - */ - cpu->regs->eflags = lgread(cpu, stack_pa + 8, u32); - cpu->regs->eflags &= - ~(X86_EFLAGS_TF|X86_EFLAGS_VM|X86_EFLAGS_RF|X86_EFLAGS_NT); -} - -/*H:205 - * Virtual Interrupts. - * - * interrupt_pending() returns the first pending interrupt which isn't blocked - * by the Guest. It is called before every entry to the Guest, and just before - * we go to sleep when the Guest has halted itself. - */ -unsigned int interrupt_pending(struct lg_cpu *cpu, bool *more) -{ - unsigned int irq; - DECLARE_BITMAP(blk, LGUEST_IRQS); - - /* If the Guest hasn't even initialized yet, we can do nothing. */ - if (!cpu->lg->lguest_data) - return LGUEST_IRQS; - - /* - * Take our "irqs_pending" array and remove any interrupts the Guest - * wants blocked: the result ends up in "blk". - */ - if (copy_from_user(&blk, cpu->lg->lguest_data->blocked_interrupts, - sizeof(blk))) - return LGUEST_IRQS; - bitmap_andnot(blk, cpu->irqs_pending, blk, LGUEST_IRQS); - - /* Find the first interrupt. */ - irq = find_first_bit(blk, LGUEST_IRQS); - *more = find_next_bit(blk, LGUEST_IRQS, irq+1); - - return irq; -} - -/* - * This actually diverts the Guest to running an interrupt handler, once an - * interrupt has been identified by interrupt_pending(). - */ -void try_deliver_interrupt(struct lg_cpu *cpu, unsigned int irq, bool more) -{ - struct desc_struct *idt; - - BUG_ON(irq >= LGUEST_IRQS); - - /* If they're halted, interrupts restart them. */ - if (cpu->halted) { - /* Re-enable interrupts. */ - if (put_user(X86_EFLAGS_IF, &cpu->lg->lguest_data->irq_enabled)) - kill_guest(cpu, "Re-enabling interrupts"); - cpu->halted = 0; - } else { - /* Otherwise we check if they have interrupts disabled. */ - u32 irq_enabled; - if (get_user(irq_enabled, &cpu->lg->lguest_data->irq_enabled)) - irq_enabled = 0; - if (!irq_enabled) { - /* Make sure they know an IRQ is pending. */ - put_user(X86_EFLAGS_IF, - &cpu->lg->lguest_data->irq_pending); - return; - } - } - - /* - * Look at the IDT entry the Guest gave us for this interrupt. The - * first 32 (FIRST_EXTERNAL_VECTOR) entries are for traps, so we skip - * over them. - */ - idt = &cpu->arch.idt[FIRST_EXTERNAL_VECTOR+irq]; - /* If they don't have a handler (yet?), we just ignore it */ - if (idt_present(idt->a, idt->b)) { - /* OK, mark it no longer pending and deliver it. */ - clear_bit(irq, cpu->irqs_pending); - - /* - * They may be about to iret, where they asked us never to - * deliver interrupts. In this case, we can emulate that iret - * then immediately deliver the interrupt. This is basically - * a noop: the iret would pop the interrupt frame and restore - * eflags, and then we'd set it up again. So just restore the - * eflags word and jump straight to the handler in this case. - * - * Denys Vlasenko points out that this isn't quite right: if - * the iret was returning to userspace, then that interrupt - * would reset the stack pointer (which the Guest told us - * about via LHCALL_SET_STACK). But unless the Guest is being - * *really* weird, that will be the same as the current stack - * anyway. - */ - if (cpu->regs->eip == cpu->lg->noirq_iret) { - restore_eflags(cpu); - } else { - /* - * set_guest_interrupt() takes a flag to say whether - * this interrupt pushes an error code onto the stack - * as well: virtual interrupts never do. - */ - push_guest_interrupt_stack(cpu, false); - } - /* Actually make Guest cpu jump to handler. */ - guest_run_interrupt(cpu, idt->a, idt->b); - } - - /* - * Every time we deliver an interrupt, we update the timestamp in the - * Guest's lguest_data struct. It would be better for the Guest if we - * did this more often, but it can actually be quite slow: doing it - * here is a compromise which means at least it gets updated every - * timer interrupt. - */ - write_timestamp(cpu); - - /* - * If there are no other interrupts we want to deliver, clear - * the pending flag. - */ - if (!more) - put_user(0, &cpu->lg->lguest_data->irq_pending); -} - -/* And this is the routine when we want to set an interrupt for the Guest. */ -void set_interrupt(struct lg_cpu *cpu, unsigned int irq) -{ - /* - * Next time the Guest runs, the core code will see if it can deliver - * this interrupt. - */ - set_bit(irq, cpu->irqs_pending); - - /* - * Make sure it sees it; it might be asleep (eg. halted), or running - * the Guest right now, in which case kick_process() will knock it out. - */ - if (!wake_up_process(cpu->tsk)) - kick_process(cpu->tsk); -} -/*:*/ - -/* - * Linux uses trap 128 for system calls. Plan9 uses 64, and Ron Minnich sent - * me a patch, so we support that too. It'd be a big step for lguest if half - * the Plan 9 user base were to start using it. - * - * Actually now I think of it, it's possible that Ron *is* half the Plan 9 - * userbase. Oh well. - */ -bool could_be_syscall(unsigned int num) -{ - /* Normal Linux IA32_SYSCALL_VECTOR or reserved vector? */ - return num == IA32_SYSCALL_VECTOR || num == syscall_vector; -} - -/* The syscall vector it wants must be unused by Host. */ -bool check_syscall_vector(struct lguest *lg) -{ - u32 vector; - - if (get_user(vector, &lg->lguest_data->syscall_vec)) - return false; - - return could_be_syscall(vector); -} - -int init_interrupts(void) -{ - /* If they want some strange system call vector, reserve it now */ - if (syscall_vector != IA32_SYSCALL_VECTOR) { - if (test_bit(syscall_vector, used_vectors) || - vector_used_by_percpu_irq(syscall_vector)) { - printk(KERN_ERR "lg: couldn't reserve syscall %u\n", - syscall_vector); - return -EBUSY; - } - set_bit(syscall_vector, used_vectors); - } - - return 0; -} - -void free_interrupts(void) -{ - if (syscall_vector != IA32_SYSCALL_VECTOR) - clear_bit(syscall_vector, used_vectors); -} - -/*H:220 - * Now we've got the routines to deliver interrupts, delivering traps like - * page fault is easy. The only trick is that Intel decided that some traps - * should have error codes: - */ -static bool has_err(unsigned int trap) -{ - return (trap == 8 || (trap >= 10 && trap <= 14) || trap == 17); -} - -/* deliver_trap() returns true if it could deliver the trap. */ -bool deliver_trap(struct lg_cpu *cpu, unsigned int num) -{ - /* - * Trap numbers are always 8 bit, but we set an impossible trap number - * for traps inside the Switcher, so check that here. - */ - if (num >= ARRAY_SIZE(cpu->arch.idt)) - return false; - - /* - * Early on the Guest hasn't set the IDT entries (or maybe it put a - * bogus one in): if we fail here, the Guest will be killed. - */ - if (!idt_present(cpu->arch.idt[num].a, cpu->arch.idt[num].b)) - return false; - push_guest_interrupt_stack(cpu, has_err(num)); - guest_run_interrupt(cpu, cpu->arch.idt[num].a, - cpu->arch.idt[num].b); - return true; -} - -/*H:250 - * Here's the hard part: returning to the Host every time a trap happens - * and then calling deliver_trap() and re-entering the Guest is slow. - * Particularly because Guest userspace system calls are traps (usually trap - * 128). - * - * So we'd like to set up the IDT to tell the CPU to deliver traps directly - * into the Guest. This is possible, but the complexities cause the size of - * this file to double! However, 150 lines of code is worth writing for taking - * system calls down from 1750ns to 270ns. Plus, if lguest didn't do it, all - * the other hypervisors would beat it up at lunchtime. - * - * This routine indicates if a particular trap number could be delivered - * directly. - * - * Unfortunately, Linux 4.6 started using an interrupt gate instead of a - * trap gate for syscalls, so this trick is ineffective. See Mastery for - * how we could do this anyway... - */ -static bool direct_trap(unsigned int num) -{ - /* - * Hardware interrupts don't go to the Guest at all (except system - * call). - */ - if (num >= FIRST_EXTERNAL_VECTOR && !could_be_syscall(num)) - return false; - - /* - * The Host needs to see page faults (for shadow paging and to save the - * fault address), general protection faults (in/out emulation) and - * device not available (TS handling) and of course, the hypercall trap. - */ - return num != 14 && num != 13 && num != 7 && num != LGUEST_TRAP_ENTRY; -} -/*:*/ - -/*M:005 - * The Guest has the ability to turn its interrupt gates into trap gates, - * if it is careful. The Host will let trap gates can go directly to the - * Guest, but the Guest needs the interrupts atomically disabled for an - * interrupt gate. The Host could provide a mechanism to register more - * "no-interrupt" regions, and the Guest could point the trap gate at - * instructions within that region, where it can safely disable interrupts. - */ - -/*M:006 - * The Guests do not use the sysenter (fast system call) instruction, - * because it's hardcoded to enter privilege level 0 and so can't go direct. - * It's about twice as fast as the older "int 0x80" system call, so it might - * still be worthwhile to handle it in the Switcher and lcall down to the - * Guest. The sysenter semantics are hairy tho: search for that keyword in - * entry.S -:*/ - -/*H:260 - * When we make traps go directly into the Guest, we need to make sure - * the kernel stack is valid (ie. mapped in the page tables). Otherwise, the - * CPU trying to deliver the trap will fault while trying to push the interrupt - * words on the stack: this is called a double fault, and it forces us to kill - * the Guest. - * - * Which is deeply unfair, because (literally!) it wasn't the Guests' fault. - */ -void pin_stack_pages(struct lg_cpu *cpu) -{ - unsigned int i; - - /* - * Depending on the CONFIG_4KSTACKS option, the Guest can have one or - * two pages of stack space. - */ - for (i = 0; i < cpu->lg->stack_pages; i++) - /* - * The stack grows *upwards*, so the address we're given is the - * start of the page after the kernel stack. Subtract one to - * get back onto the first stack page, and keep subtracting to - * get to the rest of the stack pages. - */ - pin_page(cpu, cpu->esp1 - 1 - i * PAGE_SIZE); -} - -/* - * Direct traps also mean that we need to know whenever the Guest wants to use - * a different kernel stack, so we can change the guest TSS to use that - * stack. The TSS entries expect a virtual address, so unlike most addresses - * the Guest gives us, the "esp" (stack pointer) value here is virtual, not - * physical. - * - * In Linux each process has its own kernel stack, so this happens a lot: we - * change stacks on each context switch. - */ -void guest_set_stack(struct lg_cpu *cpu, u32 seg, u32 esp, unsigned int pages) -{ - /* - * You're not allowed a stack segment with privilege level 0: bad Guest! - */ - if ((seg & 0x3) != GUEST_PL) - kill_guest(cpu, "bad stack segment %i", seg); - /* We only expect one or two stack pages. */ - if (pages > 2) - kill_guest(cpu, "bad stack pages %u", pages); - /* Save where the stack is, and how many pages */ - cpu->ss1 = seg; - cpu->esp1 = esp; - cpu->lg->stack_pages = pages; - /* Make sure the new stack pages are mapped */ - pin_stack_pages(cpu); -} - -/* - * All this reference to mapping stacks leads us neatly into the other complex - * part of the Host: page table handling. - */ - -/*H:235 - * This is the routine which actually checks the Guest's IDT entry and - * transfers it into the entry in "struct lguest": - */ -static void set_trap(struct lg_cpu *cpu, struct desc_struct *trap, - unsigned int num, u32 lo, u32 hi) -{ - u8 type = idt_type(lo, hi); - - /* We zero-out a not-present entry */ - if (!idt_present(lo, hi)) { - trap->a = trap->b = 0; - return; - } - - /* We only support interrupt and trap gates. */ - if (type != 0xE && type != 0xF) - kill_guest(cpu, "bad IDT type %i", type); - - /* - * We only copy the handler address, present bit, privilege level and - * type. The privilege level controls where the trap can be triggered - * manually with an "int" instruction. This is usually GUEST_PL, - * except for system calls which userspace can use. - */ - trap->a = ((__KERNEL_CS|GUEST_PL)<<16) | (lo&0x0000FFFF); - trap->b = (hi&0xFFFFEF00); -} - -/*H:230 - * While we're here, dealing with delivering traps and interrupts to the - * Guest, we might as well complete the picture: how the Guest tells us where - * it wants them to go. This would be simple, except making traps fast - * requires some tricks. - * - * We saw the Guest setting Interrupt Descriptor Table (IDT) entries with the - * LHCALL_LOAD_IDT_ENTRY hypercall before: that comes here. - */ -void load_guest_idt_entry(struct lg_cpu *cpu, unsigned int num, u32 lo, u32 hi) -{ - /* - * Guest never handles: NMI, doublefault, spurious interrupt or - * hypercall. We ignore when it tries to set them. - */ - if (num == 2 || num == 8 || num == 15 || num == LGUEST_TRAP_ENTRY) - return; - - /* - * Mark the IDT as changed: next time the Guest runs we'll know we have - * to copy this again. - */ - cpu->changed |= CHANGED_IDT; - - /* Check that the Guest doesn't try to step outside the bounds. */ - if (num >= ARRAY_SIZE(cpu->arch.idt)) - kill_guest(cpu, "Setting idt entry %u", num); - else - set_trap(cpu, &cpu->arch.idt[num], num, lo, hi); -} - -/* - * The default entry for each interrupt points into the Switcher routines which - * simply return to the Host. The run_guest() loop will then call - * deliver_trap() to bounce it back into the Guest. - */ -static void default_idt_entry(struct desc_struct *idt, - int trap, - const unsigned long handler, - const struct desc_struct *base) -{ - /* A present interrupt gate. */ - u32 flags = 0x8e00; - - /* - * Set the privilege level on the entry for the hypercall: this allows - * the Guest to use the "int" instruction to trigger it. - */ - if (trap == LGUEST_TRAP_ENTRY) - flags |= (GUEST_PL << 13); - else if (base) - /* - * Copy privilege level from what Guest asked for. This allows - * debug (int 3) traps from Guest userspace, for example. - */ - flags |= (base->b & 0x6000); - - /* Now pack it into the IDT entry in its weird format. */ - idt->a = (LGUEST_CS<<16) | (handler&0x0000FFFF); - idt->b = (handler&0xFFFF0000) | flags; -} - -/* When the Guest first starts, we put default entries into the IDT. */ -void setup_default_idt_entries(struct lguest_ro_state *state, - const unsigned long *def) -{ - unsigned int i; - - for (i = 0; i < ARRAY_SIZE(state->guest_idt); i++) - default_idt_entry(&state->guest_idt[i], i, def[i], NULL); -} - -/*H:240 - * We don't use the IDT entries in the "struct lguest" directly, instead - * we copy them into the IDT which we've set up for Guests on this CPU, just - * before we run the Guest. This routine does that copy. - */ -void copy_traps(const struct lg_cpu *cpu, struct desc_struct *idt, - const unsigned long *def) -{ - unsigned int i; - - /* - * We can simply copy the direct traps, otherwise we use the default - * ones in the Switcher: they will return to the Host. - */ - for (i = 0; i < ARRAY_SIZE(cpu->arch.idt); i++) { - const struct desc_struct *gidt = &cpu->arch.idt[i]; - - /* If no Guest can ever override this trap, leave it alone. */ - if (!direct_trap(i)) - continue; - - /* - * Only trap gates (type 15) can go direct to the Guest. - * Interrupt gates (type 14) disable interrupts as they are - * entered, which we never let the Guest do. Not present - * entries (type 0x0) also can't go direct, of course. - * - * If it can't go direct, we still need to copy the priv. level: - * they might want to give userspace access to a software - * interrupt. - */ - if (idt_type(gidt->a, gidt->b) == 0xF) - idt[i] = *gidt; - else - default_idt_entry(&idt[i], i, def[i], gidt); - } -} - -/*H:200 - * The Guest Clock. - * - * There are two sources of virtual interrupts. We saw one in lguest_user.c: - * the Launcher sending interrupts for virtual devices. The other is the Guest - * timer interrupt. - * - * The Guest uses the LHCALL_SET_CLOCKEVENT hypercall to tell us how long to - * the next timer interrupt (in nanoseconds). We use the high-resolution timer - * infrastructure to set a callback at that time. - * - * 0 means "turn off the clock". - */ -void guest_set_clockevent(struct lg_cpu *cpu, unsigned long delta) -{ - ktime_t expires; - - if (unlikely(delta == 0)) { - /* Clock event device is shutting down. */ - hrtimer_cancel(&cpu->hrt); - return; - } - - /* - * We use wallclock time here, so the Guest might not be running for - * all the time between now and the timer interrupt it asked for. This - * is almost always the right thing to do. - */ - expires = ktime_add_ns(ktime_get_real(), delta); - hrtimer_start(&cpu->hrt, expires, HRTIMER_MODE_ABS); -} - -/* This is the function called when the Guest's timer expires. */ -static enum hrtimer_restart clockdev_fn(struct hrtimer *timer) -{ - struct lg_cpu *cpu = container_of(timer, struct lg_cpu, hrt); - - /* Remember the first interrupt is the timer interrupt. */ - set_interrupt(cpu, 0); - return HRTIMER_NORESTART; -} - -/* This sets up the timer for this Guest. */ -void init_clockdev(struct lg_cpu *cpu) -{ - hrtimer_init(&cpu->hrt, CLOCK_REALTIME, HRTIMER_MODE_ABS); - cpu->hrt.function = clockdev_fn; -} diff --git a/drivers/lguest/lg.h b/drivers/lguest/lg.h deleted file mode 100644 index 2356a2318034..000000000000 --- a/drivers/lguest/lg.h +++ /dev/null @@ -1,258 +0,0 @@ -#ifndef _LGUEST_H -#define _LGUEST_H - -#ifndef __ASSEMBLY__ -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include - -struct pgdir { - unsigned long gpgdir; - bool switcher_mapped; - int last_host_cpu; - pgd_t *pgdir; -}; - -/* We have two pages shared with guests, per cpu. */ -struct lguest_pages { - /* This is the stack page mapped rw in guest */ - char spare[PAGE_SIZE - sizeof(struct lguest_regs)]; - struct lguest_regs regs; - - /* This is the host state & guest descriptor page, ro in guest */ - struct lguest_ro_state state; -} __attribute__((aligned(PAGE_SIZE))); - -#define CHANGED_IDT 1 -#define CHANGED_GDT 2 -#define CHANGED_GDT_TLS 4 /* Actually a subset of CHANGED_GDT */ -#define CHANGED_ALL 3 - -struct lg_cpu { - unsigned int id; - struct lguest *lg; - struct task_struct *tsk; - struct mm_struct *mm; /* == tsk->mm, but that becomes NULL on exit */ - - u32 cr2; - u32 esp1; - u16 ss1; - - /* Bitmap of what has changed: see CHANGED_* above. */ - int changed; - - /* Pending operation. */ - struct lguest_pending pending; - - unsigned long *reg_read; /* register from LHREQ_GETREG */ - - /* At end of a page shared mapped over lguest_pages in guest. */ - unsigned long regs_page; - struct lguest_regs *regs; - - struct lguest_pages *last_pages; - - /* Initialization mode: linear map everything. */ - bool linear_pages; - int cpu_pgd; /* Which pgd this cpu is currently using */ - - /* If a hypercall was asked for, this points to the arguments. */ - struct hcall_args *hcall; - u32 next_hcall; - - /* Virtual clock device */ - struct hrtimer hrt; - - /* Did the Guest tell us to halt? */ - int halted; - - /* Pending virtual interrupts */ - DECLARE_BITMAP(irqs_pending, LGUEST_IRQS); - - struct lg_cpu_arch arch; -}; - -/* The private info the thread maintains about the guest. */ -struct lguest { - struct lguest_data __user *lguest_data; - struct lg_cpu cpus[NR_CPUS]; - unsigned int nr_cpus; - - /* Valid guest memory pages must be < this. */ - u32 pfn_limit; - - /* Device memory is >= pfn_limit and < device_limit. */ - u32 device_limit; - - /* - * This provides the offset to the base of guest-physical memory in the - * Launcher. - */ - void __user *mem_base; - unsigned long kernel_address; - - struct pgdir pgdirs[4]; - - unsigned long noirq_iret; - - unsigned int stack_pages; - u32 tsc_khz; - - /* Dead? */ - const char *dead; -}; - -extern struct mutex lguest_lock; - -/* core.c: */ -bool lguest_address_ok(const struct lguest *lg, - unsigned long addr, unsigned long len); -void __lgread(struct lg_cpu *, void *, unsigned long, unsigned); -void __lgwrite(struct lg_cpu *, unsigned long, const void *, unsigned); -extern struct page **lg_switcher_pages; - -/*H:035 - * Using memory-copy operations like that is usually inconvient, so we - * have the following helper macros which read and write a specific type (often - * an unsigned long). - * - * This reads into a variable of the given type then returns that. - */ -#define lgread(cpu, addr, type) \ - ({ type _v; __lgread((cpu), &_v, (addr), sizeof(_v)); _v; }) - -/* This checks that the variable is of the given type, then writes it out. */ -#define lgwrite(cpu, addr, type, val) \ - do { \ - typecheck(type, val); \ - __lgwrite((cpu), (addr), &(val), sizeof(val)); \ - } while(0) -/* (end of memory access helper routines) :*/ - -int run_guest(struct lg_cpu *cpu, unsigned long __user *user); - -/* - * Helper macros to obtain the first 12 or the last 20 bits, this is only the - * first step in the migration to the kernel types. pte_pfn is already defined - * in the kernel. - */ -#define pgd_flags(x) (pgd_val(x) & ~PAGE_MASK) -#define pgd_pfn(x) (pgd_val(x) >> PAGE_SHIFT) -#define pmd_flags(x) (pmd_val(x) & ~PAGE_MASK) -#define pmd_pfn(x) (pmd_val(x) >> PAGE_SHIFT) - -/* interrupts_and_traps.c: */ -unsigned int interrupt_pending(struct lg_cpu *cpu, bool *more); -void try_deliver_interrupt(struct lg_cpu *cpu, unsigned int irq, bool more); -void set_interrupt(struct lg_cpu *cpu, unsigned int irq); -bool deliver_trap(struct lg_cpu *cpu, unsigned int num); -void load_guest_idt_entry(struct lg_cpu *cpu, unsigned int i, - u32 low, u32 hi); -void guest_set_stack(struct lg_cpu *cpu, u32 seg, u32 esp, unsigned int pages); -void pin_stack_pages(struct lg_cpu *cpu); -void setup_default_idt_entries(struct lguest_ro_state *state, - const unsigned long *def); -void copy_traps(const struct lg_cpu *cpu, struct desc_struct *idt, - const unsigned long *def); -void guest_set_clockevent(struct lg_cpu *cpu, unsigned long delta); -bool send_notify_to_eventfd(struct lg_cpu *cpu); -void init_clockdev(struct lg_cpu *cpu); -bool check_syscall_vector(struct lguest *lg); -bool could_be_syscall(unsigned int num); -int init_interrupts(void); -void free_interrupts(void); - -/* segments.c: */ -void setup_default_gdt_entries(struct lguest_ro_state *state); -void setup_guest_gdt(struct lg_cpu *cpu); -void load_guest_gdt_entry(struct lg_cpu *cpu, unsigned int i, - u32 low, u32 hi); -void guest_load_tls(struct lg_cpu *cpu, unsigned long tls_array); -void copy_gdt(const struct lg_cpu *cpu, struct desc_struct *gdt); -void copy_gdt_tls(const struct lg_cpu *cpu, struct desc_struct *gdt); - -/* page_tables.c: */ -int init_guest_pagetable(struct lguest *lg); -void free_guest_pagetable(struct lguest *lg); -void guest_new_pagetable(struct lg_cpu *cpu, unsigned long pgtable); -void guest_set_pgd(struct lguest *lg, unsigned long gpgdir, u32 i); -#ifdef CONFIG_X86_PAE -void guest_set_pmd(struct lguest *lg, unsigned long gpgdir, u32 i); -#endif -void guest_pagetable_clear_all(struct lg_cpu *cpu); -void guest_pagetable_flush_user(struct lg_cpu *cpu); -void guest_set_pte(struct lg_cpu *cpu, unsigned long gpgdir, - unsigned long vaddr, pte_t val); -void map_switcher_in_guest(struct lg_cpu *cpu, struct lguest_pages *pages); -bool demand_page(struct lg_cpu *cpu, unsigned long cr2, int errcode, - unsigned long *iomem); -void pin_page(struct lg_cpu *cpu, unsigned long vaddr); -bool __guest_pa(struct lg_cpu *cpu, unsigned long vaddr, unsigned long *paddr); -unsigned long guest_pa(struct lg_cpu *cpu, unsigned long vaddr); -void page_table_guest_data_init(struct lg_cpu *cpu); - -/* /core.c: */ -void lguest_arch_host_init(void); -void lguest_arch_host_fini(void); -void lguest_arch_run_guest(struct lg_cpu *cpu); -void lguest_arch_handle_trap(struct lg_cpu *cpu); -int lguest_arch_init_hypercalls(struct lg_cpu *cpu); -int lguest_arch_do_hcall(struct lg_cpu *cpu, struct hcall_args *args); -void lguest_arch_setup_regs(struct lg_cpu *cpu, unsigned long start); -unsigned long *lguest_arch_regptr(struct lg_cpu *cpu, size_t reg_off, bool any); - -/* /switcher.S: */ -extern char start_switcher_text[], end_switcher_text[], switch_to_guest[]; - -/* lguest_user.c: */ -int lguest_device_init(void); -void lguest_device_remove(void); - -/* hypercalls.c: */ -void do_hypercalls(struct lg_cpu *cpu); -void write_timestamp(struct lg_cpu *cpu); - -/*L:035 - * Let's step aside for the moment, to study one important routine that's used - * widely in the Host code. - * - * There are many cases where the Guest can do something invalid, like pass crap - * to a hypercall. Since only the Guest kernel can make hypercalls, it's quite - * acceptable to simply terminate the Guest and give the Launcher a nicely - * formatted reason. It's also simpler for the Guest itself, which doesn't - * need to check most hypercalls for "success"; if you're still running, it - * succeeded. - * - * Once this is called, the Guest will never run again, so most Host code can - * call this then continue as if nothing had happened. This means many - * functions don't have to explicitly return an error code, which keeps the - * code simple. - * - * It also means that this can be called more than once: only the first one is - * remembered. The only trick is that we still need to kill the Guest even if - * we can't allocate memory to store the reason. Linux has a neat way of - * packing error codes into invalid pointers, so we use that here. - * - * Like any macro which uses an "if", it is safely wrapped in a run-once "do { - * } while(0)". - */ -#define kill_guest(cpu, fmt...) \ -do { \ - if (!(cpu)->lg->dead) { \ - (cpu)->lg->dead = kasprintf(GFP_ATOMIC, fmt); \ - if (!(cpu)->lg->dead) \ - (cpu)->lg->dead = ERR_PTR(-ENOMEM); \ - } \ -} while(0) -/* (End of aside) :*/ - -#endif /* __ASSEMBLY__ */ -#endif /* _LGUEST_H */ diff --git a/drivers/lguest/lguest_user.c b/drivers/lguest/lguest_user.c deleted file mode 100644 index 1a6787bc9386..000000000000 --- a/drivers/lguest/lguest_user.c +++ /dev/null @@ -1,446 +0,0 @@ -/*P:200 This contains all the /dev/lguest code, whereby the userspace - * launcher controls and communicates with the Guest. For example, - * the first write will tell us the Guest's memory layout and entry - * point. A read will run the Guest until something happens, such as - * a signal or the Guest accessing a device. -:*/ -#include -#include -#include -#include -#include -#include -#include -#include -#include "lg.h" - -/*L:052 - The Launcher can get the registers, and also set some of them. -*/ -static int getreg_setup(struct lg_cpu *cpu, const unsigned long __user *input) -{ - unsigned long which; - - /* We re-use the ptrace structure to specify which register to read. */ - if (get_user(which, input) != 0) - return -EFAULT; - - /* - * We set up the cpu register pointer, and their next read will - * actually get the value (instead of running the guest). - * - * The last argument 'true' says we can access any register. - */ - cpu->reg_read = lguest_arch_regptr(cpu, which, true); - if (!cpu->reg_read) - return -ENOENT; - - /* And because this is a write() call, we return the length used. */ - return sizeof(unsigned long) * 2; -} - -static int setreg(struct lg_cpu *cpu, const unsigned long __user *input) -{ - unsigned long which, value, *reg; - - /* We re-use the ptrace structure to specify which register to read. */ - if (get_user(which, input) != 0) - return -EFAULT; - input++; - if (get_user(value, input) != 0) - return -EFAULT; - - /* The last argument 'false' means we can't access all registers. */ - reg = lguest_arch_regptr(cpu, which, false); - if (!reg) - return -ENOENT; - - *reg = value; - - /* And because this is a write() call, we return the length used. */ - return sizeof(unsigned long) * 3; -} - -/*L:050 - * Sending an interrupt is done by writing LHREQ_IRQ and an interrupt - * number to /dev/lguest. - */ -static int user_send_irq(struct lg_cpu *cpu, const unsigned long __user *input) -{ - unsigned long irq; - - if (get_user(irq, input) != 0) - return -EFAULT; - if (irq >= LGUEST_IRQS) - return -EINVAL; - - /* - * Next time the Guest runs, the core code will see if it can deliver - * this interrupt. - */ - set_interrupt(cpu, irq); - return 0; -} - -/*L:053 - * Deliver a trap: this is used by the Launcher if it can't emulate - * an instruction. - */ -static int trap(struct lg_cpu *cpu, const unsigned long __user *input) -{ - unsigned long trapnum; - - if (get_user(trapnum, input) != 0) - return -EFAULT; - - if (!deliver_trap(cpu, trapnum)) - return -EINVAL; - - return 0; -} - -/*L:040 - * Once our Guest is initialized, the Launcher makes it run by reading - * from /dev/lguest. - */ -static ssize_t read(struct file *file, char __user *user, size_t size,loff_t*o) -{ - struct lguest *lg = file->private_data; - struct lg_cpu *cpu; - unsigned int cpu_id = *o; - - /* You must write LHREQ_INITIALIZE first! */ - if (!lg) - return -EINVAL; - - /* Watch out for arbitrary vcpu indexes! */ - if (cpu_id >= lg->nr_cpus) - return -EINVAL; - - cpu = &lg->cpus[cpu_id]; - - /* If you're not the task which owns the Guest, go away. */ - if (current != cpu->tsk) - return -EPERM; - - /* If the Guest is already dead, we indicate why */ - if (lg->dead) { - size_t len; - - /* lg->dead either contains an error code, or a string. */ - if (IS_ERR(lg->dead)) - return PTR_ERR(lg->dead); - - /* We can only return as much as the buffer they read with. */ - len = min(size, strlen(lg->dead)+1); - if (copy_to_user(user, lg->dead, len) != 0) - return -EFAULT; - return len; - } - - /* - * If we returned from read() last time because the Guest sent I/O, - * clear the flag. - */ - if (cpu->pending.trap) - cpu->pending.trap = 0; - - /* Run the Guest until something interesting happens. */ - return run_guest(cpu, (unsigned long __user *)user); -} - -/*L:025 - * This actually initializes a CPU. For the moment, a Guest is only - * uniprocessor, so "id" is always 0. - */ -static int lg_cpu_start(struct lg_cpu *cpu, unsigned id, unsigned long start_ip) -{ - /* We have a limited number of CPUs in the lguest struct. */ - if (id >= ARRAY_SIZE(cpu->lg->cpus)) - return -EINVAL; - - /* Set up this CPU's id, and pointer back to the lguest struct. */ - cpu->id = id; - cpu->lg = container_of(cpu, struct lguest, cpus[id]); - cpu->lg->nr_cpus++; - - /* Each CPU has a timer it can set. */ - init_clockdev(cpu); - - /* - * We need a complete page for the Guest registers: they are accessible - * to the Guest and we can only grant it access to whole pages. - */ - cpu->regs_page = get_zeroed_page(GFP_KERNEL); - if (!cpu->regs_page) - return -ENOMEM; - - /* We actually put the registers at the end of the page. */ - cpu->regs = (void *)cpu->regs_page + PAGE_SIZE - sizeof(*cpu->regs); - - /* - * Now we initialize the Guest's registers, handing it the start - * address. - */ - lguest_arch_setup_regs(cpu, start_ip); - - /* - * We keep a pointer to the Launcher task (ie. current task) for when - * other Guests want to wake this one (eg. console input). - */ - cpu->tsk = current; - - /* - * We need to keep a pointer to the Launcher's memory map, because if - * the Launcher dies we need to clean it up. If we don't keep a - * reference, it is destroyed before close() is called. - */ - cpu->mm = get_task_mm(cpu->tsk); - - /* - * We remember which CPU's pages this Guest used last, for optimization - * when the same Guest runs on the same CPU twice. - */ - cpu->last_pages = NULL; - - /* No error == success. */ - return 0; -} - -/*L:020 - * The initialization write supplies 3 pointer sized (32 or 64 bit) values (in - * addition to the LHREQ_INITIALIZE value). These are: - * - * base: The start of the Guest-physical memory inside the Launcher memory. - * - * pfnlimit: The highest (Guest-physical) page number the Guest should be - * allowed to access. The Guest memory lives inside the Launcher, so it sets - * this to ensure the Guest can only reach its own memory. - * - * start: The first instruction to execute ("eip" in x86-speak). - */ -static int initialize(struct file *file, const unsigned long __user *input) -{ - /* "struct lguest" contains all we (the Host) know about a Guest. */ - struct lguest *lg; - int err; - unsigned long args[4]; - - /* - * We grab the Big Lguest lock, which protects against multiple - * simultaneous initializations. - */ - mutex_lock(&lguest_lock); - /* You can't initialize twice! Close the device and start again... */ - if (file->private_data) { - err = -EBUSY; - goto unlock; - } - - if (copy_from_user(args, input, sizeof(args)) != 0) { - err = -EFAULT; - goto unlock; - } - - lg = kzalloc(sizeof(*lg), GFP_KERNEL); - if (!lg) { - err = -ENOMEM; - goto unlock; - } - - /* Populate the easy fields of our "struct lguest" */ - lg->mem_base = (void __user *)args[0]; - lg->pfn_limit = args[1]; - lg->device_limit = args[3]; - - /* This is the first cpu (cpu 0) and it will start booting at args[2] */ - err = lg_cpu_start(&lg->cpus[0], 0, args[2]); - if (err) - goto free_lg; - - /* - * Initialize the Guest's shadow page tables. This allocates - * memory, so can fail. - */ - err = init_guest_pagetable(lg); - if (err) - goto free_regs; - - /* We keep our "struct lguest" in the file's private_data. */ - file->private_data = lg; - - mutex_unlock(&lguest_lock); - - /* And because this is a write() call, we return the length used. */ - return sizeof(args); - -free_regs: - /* FIXME: This should be in free_vcpu */ - free_page(lg->cpus[0].regs_page); -free_lg: - kfree(lg); -unlock: - mutex_unlock(&lguest_lock); - return err; -} - -/*L:010 - * The first operation the Launcher does must be a write. All writes - * start with an unsigned long number: for the first write this must be - * LHREQ_INITIALIZE to set up the Guest. After that the Launcher can use - * writes of other values to send interrupts or set up receipt of notifications. - * - * Note that we overload the "offset" in the /dev/lguest file to indicate what - * CPU number we're dealing with. Currently this is always 0 since we only - * support uniprocessor Guests, but you can see the beginnings of SMP support - * here. - */ -static ssize_t write(struct file *file, const char __user *in, - size_t size, loff_t *off) -{ - /* - * Once the Guest is initialized, we hold the "struct lguest" in the - * file private data. - */ - struct lguest *lg = file->private_data; - const unsigned long __user *input = (const unsigned long __user *)in; - unsigned long req; - struct lg_cpu *uninitialized_var(cpu); - unsigned int cpu_id = *off; - - /* The first value tells us what this request is. */ - if (get_user(req, input) != 0) - return -EFAULT; - input++; - - /* If you haven't initialized, you must do that first. */ - if (req != LHREQ_INITIALIZE) { - if (!lg || (cpu_id >= lg->nr_cpus)) - return -EINVAL; - cpu = &lg->cpus[cpu_id]; - - /* Once the Guest is dead, you can only read() why it died. */ - if (lg->dead) - return -ENOENT; - } - - switch (req) { - case LHREQ_INITIALIZE: - return initialize(file, input); - case LHREQ_IRQ: - return user_send_irq(cpu, input); - case LHREQ_GETREG: - return getreg_setup(cpu, input); - case LHREQ_SETREG: - return setreg(cpu, input); - case LHREQ_TRAP: - return trap(cpu, input); - default: - return -EINVAL; - } -} - -static int open(struct inode *inode, struct file *file) -{ - file->private_data = NULL; - - return 0; -} - -/*L:060 - * The final piece of interface code is the close() routine. It reverses - * everything done in initialize(). This is usually called because the - * Launcher exited. - * - * Note that the close routine returns 0 or a negative error number: it can't - * really fail, but it can whine. I blame Sun for this wart, and K&R C for - * letting them do it. -:*/ -static int close(struct inode *inode, struct file *file) -{ - struct lguest *lg = file->private_data; - unsigned int i; - - /* If we never successfully initialized, there's nothing to clean up */ - if (!lg) - return 0; - - /* - * We need the big lock, to protect from inter-guest I/O and other - * Launchers initializing guests. - */ - mutex_lock(&lguest_lock); - - /* Free up the shadow page tables for the Guest. */ - free_guest_pagetable(lg); - - for (i = 0; i < lg->nr_cpus; i++) { - /* Cancels the hrtimer set via LHCALL_SET_CLOCKEVENT. */ - hrtimer_cancel(&lg->cpus[i].hrt); - /* We can free up the register page we allocated. */ - free_page(lg->cpus[i].regs_page); - /* - * Now all the memory cleanups are done, it's safe to release - * the Launcher's memory management structure. - */ - mmput(lg->cpus[i].mm); - } - - /* - * If lg->dead doesn't contain an error code it will be NULL or a - * kmalloc()ed string, either of which is ok to hand to kfree(). - */ - if (!IS_ERR(lg->dead)) - kfree(lg->dead); - /* Free the memory allocated to the lguest_struct */ - kfree(lg); - /* Release lock and exit. */ - mutex_unlock(&lguest_lock); - - return 0; -} - -/*L:000 - * Welcome to our journey through the Launcher! - * - * The Launcher is the Host userspace program which sets up, runs and services - * the Guest. In fact, many comments in the Drivers which refer to "the Host" - * doing things are inaccurate: the Launcher does all the device handling for - * the Guest, but the Guest can't know that. - * - * Just to confuse you: to the Host kernel, the Launcher *is* the Guest and we - * shall see more of that later. - * - * We begin our understanding with the Host kernel interface which the Launcher - * uses: reading and writing a character device called /dev/lguest. All the - * work happens in the read(), write() and close() routines: - */ -static const struct file_operations lguest_fops = { - .owner = THIS_MODULE, - .open = open, - .release = close, - .write = write, - .read = read, - .llseek = default_llseek, -}; -/*:*/ - -/* - * This is a textbook example of a "misc" character device. Populate a "struct - * miscdevice" and register it with misc_register(). - */ -static struct miscdevice lguest_dev = { - .minor = MISC_DYNAMIC_MINOR, - .name = "lguest", - .fops = &lguest_fops, -}; - -int __init lguest_device_init(void) -{ - return misc_register(&lguest_dev); -} - -void __exit lguest_device_remove(void) -{ - misc_deregister(&lguest_dev); -} diff --git a/drivers/lguest/page_tables.c b/drivers/lguest/page_tables.c deleted file mode 100644 index 0bc127e9f16a..000000000000 --- a/drivers/lguest/page_tables.c +++ /dev/null @@ -1,1239 +0,0 @@ -/*P:700 - * The pagetable code, on the other hand, still shows the scars of - * previous encounters. It's functional, and as neat as it can be in the - * circumstances, but be wary, for these things are subtle and break easily. - * The Guest provides a virtual to physical mapping, but we can neither trust - * it nor use it: we verify and convert it here then point the CPU to the - * converted Guest pages when running the Guest. -:*/ - -/* Copyright (C) Rusty Russell IBM Corporation 2013. - * GPL v2 and any later version */ -#include -#include -#include -#include -#include -#include -#include -#include -#include "lg.h" - -/*M:008 - * We hold reference to pages, which prevents them from being swapped. - * It'd be nice to have a callback in the "struct mm_struct" when Linux wants - * to swap out. If we had this, and a shrinker callback to trim PTE pages, we - * could probably consider launching Guests as non-root. -:*/ - -/*H:300 - * The Page Table Code - * - * We use two-level page tables for the Guest, or three-level with PAE. If - * you're not entirely comfortable with virtual addresses, physical addresses - * and page tables then I recommend you review arch/x86/lguest/boot.c's "Page - * Table Handling" (with diagrams!). - * - * The Guest keeps page tables, but we maintain the actual ones here: these are - * called "shadow" page tables. Which is a very Guest-centric name: these are - * the real page tables the CPU uses, although we keep them up to date to - * reflect the Guest's. (See what I mean about weird naming? Since when do - * shadows reflect anything?) - * - * Anyway, this is the most complicated part of the Host code. There are seven - * parts to this: - * (i) Looking up a page table entry when the Guest faults, - * (ii) Making sure the Guest stack is mapped, - * (iii) Setting up a page table entry when the Guest tells us one has changed, - * (iv) Switching page tables, - * (v) Flushing (throwing away) page tables, - * (vi) Mapping the Switcher when the Guest is about to run, - * (vii) Setting up the page tables initially. -:*/ - -/* - * The Switcher uses the complete top PTE page. That's 1024 PTE entries (4MB) - * or 512 PTE entries with PAE (2MB). - */ -#define SWITCHER_PGD_INDEX (PTRS_PER_PGD - 1) - -/* - * For PAE we need the PMD index as well. We use the last 2MB, so we - * will need the last pmd entry of the last pmd page. - */ -#ifdef CONFIG_X86_PAE -#define CHECK_GPGD_MASK _PAGE_PRESENT -#else -#define CHECK_GPGD_MASK _PAGE_TABLE -#endif - -/*H:320 - * The page table code is curly enough to need helper functions to keep it - * clear and clean. The kernel itself provides many of them; one advantage - * of insisting that the Guest and Host use the same CONFIG_X86_PAE setting. - * - * There are two functions which return pointers to the shadow (aka "real") - * page tables. - * - * spgd_addr() takes the virtual address and returns a pointer to the top-level - * page directory entry (PGD) for that address. Since we keep track of several - * page tables, the "i" argument tells us which one we're interested in (it's - * usually the current one). - */ -static pgd_t *spgd_addr(struct lg_cpu *cpu, u32 i, unsigned long vaddr) -{ - unsigned int index = pgd_index(vaddr); - - /* Return a pointer index'th pgd entry for the i'th page table. */ - return &cpu->lg->pgdirs[i].pgdir[index]; -} - -#ifdef CONFIG_X86_PAE -/* - * This routine then takes the PGD entry given above, which contains the - * address of the PMD page. It then returns a pointer to the PMD entry for the - * given address. - */ -static pmd_t *spmd_addr(struct lg_cpu *cpu, pgd_t spgd, unsigned long vaddr) -{ - unsigned int index = pmd_index(vaddr); - pmd_t *page; - - /* You should never call this if the PGD entry wasn't valid */ - BUG_ON(!(pgd_flags(spgd) & _PAGE_PRESENT)); - page = __va(pgd_pfn(spgd) << PAGE_SHIFT); - - return &page[index]; -} -#endif - -/* - * This routine then takes the page directory entry returned above, which - * contains the address of the page table entry (PTE) page. It then returns a - * pointer to the PTE entry for the given address. - */ -static pte_t *spte_addr(struct lg_cpu *cpu, pgd_t spgd, unsigned long vaddr) -{ -#ifdef CONFIG_X86_PAE - pmd_t *pmd = spmd_addr(cpu, spgd, vaddr); - pte_t *page = __va(pmd_pfn(*pmd) << PAGE_SHIFT); - - /* You should never call this if the PMD entry wasn't valid */ - BUG_ON(!(pmd_flags(*pmd) & _PAGE_PRESENT)); -#else - pte_t *page = __va(pgd_pfn(spgd) << PAGE_SHIFT); - /* You should never call this if the PGD entry wasn't valid */ - BUG_ON(!(pgd_flags(spgd) & _PAGE_PRESENT)); -#endif - - return &page[pte_index(vaddr)]; -} - -/* - * These functions are just like the above, except they access the Guest - * page tables. Hence they return a Guest address. - */ -static unsigned long gpgd_addr(struct lg_cpu *cpu, unsigned long vaddr) -{ - unsigned int index = vaddr >> (PGDIR_SHIFT); - return cpu->lg->pgdirs[cpu->cpu_pgd].gpgdir + index * sizeof(pgd_t); -} - -#ifdef CONFIG_X86_PAE -/* Follow the PGD to the PMD. */ -static unsigned long gpmd_addr(pgd_t gpgd, unsigned long vaddr) -{ - unsigned long gpage = pgd_pfn(gpgd) << PAGE_SHIFT; - BUG_ON(!(pgd_flags(gpgd) & _PAGE_PRESENT)); - return gpage + pmd_index(vaddr) * sizeof(pmd_t); -} - -/* Follow the PMD to the PTE. */ -static unsigned long gpte_addr(struct lg_cpu *cpu, - pmd_t gpmd, unsigned long vaddr) -{ - unsigned long gpage = pmd_pfn(gpmd) << PAGE_SHIFT; - - BUG_ON(!(pmd_flags(gpmd) & _PAGE_PRESENT)); - return gpage + pte_index(vaddr) * sizeof(pte_t); -} -#else -/* Follow the PGD to the PTE (no mid-level for !PAE). */ -static unsigned long gpte_addr(struct lg_cpu *cpu, - pgd_t gpgd, unsigned long vaddr) -{ - unsigned long gpage = pgd_pfn(gpgd) << PAGE_SHIFT; - - BUG_ON(!(pgd_flags(gpgd) & _PAGE_PRESENT)); - return gpage + pte_index(vaddr) * sizeof(pte_t); -} -#endif -/*:*/ - -/*M:007 - * get_pfn is slow: we could probably try to grab batches of pages here as - * an optimization (ie. pre-faulting). -:*/ - -/*H:350 - * This routine takes a page number given by the Guest and converts it to - * an actual, physical page number. It can fail for several reasons: the - * virtual address might not be mapped by the Launcher, the write flag is set - * and the page is read-only, or the write flag was set and the page was - * shared so had to be copied, but we ran out of memory. - * - * This holds a reference to the page, so release_pte() is careful to put that - * back. - */ -static unsigned long get_pfn(unsigned long virtpfn, int write) -{ - struct page *page; - - /* gup me one page at this address please! */ - if (get_user_pages_fast(virtpfn << PAGE_SHIFT, 1, write, &page) == 1) - return page_to_pfn(page); - - /* This value indicates failure. */ - return -1UL; -} - -/*H:340 - * Converting a Guest page table entry to a shadow (ie. real) page table - * entry can be a little tricky. The flags are (almost) the same, but the - * Guest PTE contains a virtual page number: the CPU needs the real page - * number. - */ -static pte_t gpte_to_spte(struct lg_cpu *cpu, pte_t gpte, int write) -{ - unsigned long pfn, base, flags; - - /* - * The Guest sets the global flag, because it thinks that it is using - * PGE. We only told it to use PGE so it would tell us whether it was - * flushing a kernel mapping or a userspace mapping. We don't actually - * use the global bit, so throw it away. - */ - flags = (pte_flags(gpte) & ~_PAGE_GLOBAL); - - /* The Guest's pages are offset inside the Launcher. */ - base = (unsigned long)cpu->lg->mem_base / PAGE_SIZE; - - /* - * We need a temporary "unsigned long" variable to hold the answer from - * get_pfn(), because it returns 0xFFFFFFFF on failure, which wouldn't - * fit in spte.pfn. get_pfn() finds the real physical number of the - * page, given the virtual number. - */ - pfn = get_pfn(base + pte_pfn(gpte), write); - if (pfn == -1UL) { - kill_guest(cpu, "failed to get page %lu", pte_pfn(gpte)); - /* - * When we destroy the Guest, we'll go through the shadow page - * tables and release_pte() them. Make sure we don't think - * this one is valid! - */ - flags = 0; - } - /* Now we assemble our shadow PTE from the page number and flags. */ - return pfn_pte(pfn, __pgprot(flags)); -} - -/*H:460 And to complete the chain, release_pte() looks like this: */ -static void release_pte(pte_t pte) -{ - /* - * Remember that get_user_pages_fast() took a reference to the page, in - * get_pfn()? We have to put it back now. - */ - if (pte_flags(pte) & _PAGE_PRESENT) - put_page(pte_page(pte)); -} -/*:*/ - -static bool gpte_in_iomem(struct lg_cpu *cpu, pte_t gpte) -{ - /* We don't handle large pages. */ - if (pte_flags(gpte) & _PAGE_PSE) - return false; - - return (pte_pfn(gpte) >= cpu->lg->pfn_limit - && pte_pfn(gpte) < cpu->lg->device_limit); -} - -static bool check_gpte(struct lg_cpu *cpu, pte_t gpte) -{ - if ((pte_flags(gpte) & _PAGE_PSE) || - pte_pfn(gpte) >= cpu->lg->pfn_limit) { - kill_guest(cpu, "bad page table entry"); - return false; - } - return true; -} - -static bool check_gpgd(struct lg_cpu *cpu, pgd_t gpgd) -{ - if ((pgd_flags(gpgd) & ~CHECK_GPGD_MASK) || - (pgd_pfn(gpgd) >= cpu->lg->pfn_limit)) { - kill_guest(cpu, "bad page directory entry"); - return false; - } - return true; -} - -#ifdef CONFIG_X86_PAE -static bool check_gpmd(struct lg_cpu *cpu, pmd_t gpmd) -{ - if ((pmd_flags(gpmd) & ~_PAGE_TABLE) || - (pmd_pfn(gpmd) >= cpu->lg->pfn_limit)) { - kill_guest(cpu, "bad page middle directory entry"); - return false; - } - return true; -} -#endif - -/*H:331 - * This is the core routine to walk the shadow page tables and find the page - * table entry for a specific address. - * - * If allocate is set, then we allocate any missing levels, setting the flags - * on the new page directory and mid-level directories using the arguments - * (which are copied from the Guest's page table entries). - */ -static pte_t *find_spte(struct lg_cpu *cpu, unsigned long vaddr, bool allocate, - int pgd_flags, int pmd_flags) -{ - pgd_t *spgd; - /* Mid level for PAE. */ -#ifdef CONFIG_X86_PAE - pmd_t *spmd; -#endif - - /* Get top level entry. */ - spgd = spgd_addr(cpu, cpu->cpu_pgd, vaddr); - if (!(pgd_flags(*spgd) & _PAGE_PRESENT)) { - /* No shadow entry: allocate a new shadow PTE page. */ - unsigned long ptepage; - - /* If they didn't want us to allocate anything, stop. */ - if (!allocate) - return NULL; - - ptepage = get_zeroed_page(GFP_KERNEL); - /* - * This is not really the Guest's fault, but killing it is - * simple for this corner case. - */ - if (!ptepage) { - kill_guest(cpu, "out of memory allocating pte page"); - return NULL; - } - /* - * And we copy the flags to the shadow PGD entry. The page - * number in the shadow PGD is the page we just allocated. - */ - set_pgd(spgd, __pgd(__pa(ptepage) | pgd_flags)); - } - - /* - * Intel's Physical Address Extension actually uses three levels of - * page tables, so we need to look in the mid-level. - */ -#ifdef CONFIG_X86_PAE - /* Now look at the mid-level shadow entry. */ - spmd = spmd_addr(cpu, *spgd, vaddr); - - if (!(pmd_flags(*spmd) & _PAGE_PRESENT)) { - /* No shadow entry: allocate a new shadow PTE page. */ - unsigned long ptepage; - - /* If they didn't want us to allocate anything, stop. */ - if (!allocate) - return NULL; - - ptepage = get_zeroed_page(GFP_KERNEL); - - /* - * This is not really the Guest's fault, but killing it is - * simple for this corner case. - */ - if (!ptepage) { - kill_guest(cpu, "out of memory allocating pmd page"); - return NULL; - } - - /* - * And we copy the flags to the shadow PMD entry. The page - * number in the shadow PMD is the page we just allocated. - */ - set_pmd(spmd, __pmd(__pa(ptepage) | pmd_flags)); - } -#endif - - /* Get the pointer to the shadow PTE entry we're going to set. */ - return spte_addr(cpu, *spgd, vaddr); -} - -/*H:330 - * (i) Looking up a page table entry when the Guest faults. - * - * We saw this call in run_guest(): when we see a page fault in the Guest, we - * come here. That's because we only set up the shadow page tables lazily as - * they're needed, so we get page faults all the time and quietly fix them up - * and return to the Guest without it knowing. - * - * If we fixed up the fault (ie. we mapped the address), this routine returns - * true. Otherwise, it was a real fault and we need to tell the Guest. - * - * There's a corner case: they're trying to access memory between - * pfn_limit and device_limit, which is I/O memory. In this case, we - * return false and set @iomem to the physical address, so the the - * Launcher can handle the instruction manually. - */ -bool demand_page(struct lg_cpu *cpu, unsigned long vaddr, int errcode, - unsigned long *iomem) -{ - unsigned long gpte_ptr; - pte_t gpte; - pte_t *spte; - pmd_t gpmd; - pgd_t gpgd; - - *iomem = 0; - - /* We never demand page the Switcher, so trying is a mistake. */ - if (vaddr >= switcher_addr) - return false; - - /* First step: get the top-level Guest page table entry. */ - if (unlikely(cpu->linear_pages)) { - /* Faking up a linear mapping. */ - gpgd = __pgd(CHECK_GPGD_MASK); - } else { - gpgd = lgread(cpu, gpgd_addr(cpu, vaddr), pgd_t); - /* Toplevel not present? We can't map it in. */ - if (!(pgd_flags(gpgd) & _PAGE_PRESENT)) - return false; - - /* - * This kills the Guest if it has weird flags or tries to - * refer to a "physical" address outside the bounds. - */ - if (!check_gpgd(cpu, gpgd)) - return false; - } - - /* This "mid-level" entry is only used for non-linear, PAE mode. */ - gpmd = __pmd(_PAGE_TABLE); - -#ifdef CONFIG_X86_PAE - if (likely(!cpu->linear_pages)) { - gpmd = lgread(cpu, gpmd_addr(gpgd, vaddr), pmd_t); - /* Middle level not present? We can't map it in. */ - if (!(pmd_flags(gpmd) & _PAGE_PRESENT)) - return false; - - /* - * This kills the Guest if it has weird flags or tries to - * refer to a "physical" address outside the bounds. - */ - if (!check_gpmd(cpu, gpmd)) - return false; - } - - /* - * OK, now we look at the lower level in the Guest page table: keep its - * address, because we might update it later. - */ - gpte_ptr = gpte_addr(cpu, gpmd, vaddr); -#else - /* - * OK, now we look at the lower level in the Guest page table: keep its - * address, because we might update it later. - */ - gpte_ptr = gpte_addr(cpu, gpgd, vaddr); -#endif - - if (unlikely(cpu->linear_pages)) { - /* Linear? Make up a PTE which points to same page. */ - gpte = __pte((vaddr & PAGE_MASK) | _PAGE_RW | _PAGE_PRESENT); - } else { - /* Read the actual PTE value. */ - gpte = lgread(cpu, gpte_ptr, pte_t); - } - - /* If this page isn't in the Guest page tables, we can't page it in. */ - if (!(pte_flags(gpte) & _PAGE_PRESENT)) - return false; - - /* - * Check they're not trying to write to a page the Guest wants - * read-only (bit 2 of errcode == write). - */ - if ((errcode & 2) && !(pte_flags(gpte) & _PAGE_RW)) - return false; - - /* User access to a kernel-only page? (bit 3 == user access) */ - if ((errcode & 4) && !(pte_flags(gpte) & _PAGE_USER)) - return false; - - /* If they're accessing io memory, we expect a fault. */ - if (gpte_in_iomem(cpu, gpte)) { - *iomem = (pte_pfn(gpte) << PAGE_SHIFT) | (vaddr & ~PAGE_MASK); - return false; - } - - /* - * Check that the Guest PTE flags are OK, and the page number is below - * the pfn_limit (ie. not mapping the Launcher binary). - */ - if (!check_gpte(cpu, gpte)) - return false; - - /* Add the _PAGE_ACCESSED and (for a write) _PAGE_DIRTY flag */ - gpte = pte_mkyoung(gpte); - if (errcode & 2) - gpte = pte_mkdirty(gpte); - - /* Get the pointer to the shadow PTE entry we're going to set. */ - spte = find_spte(cpu, vaddr, true, pgd_flags(gpgd), pmd_flags(gpmd)); - if (!spte) - return false; - - /* - * If there was a valid shadow PTE entry here before, we release it. - * This can happen with a write to a previously read-only entry. - */ - release_pte(*spte); - - /* - * If this is a write, we insist that the Guest page is writable (the - * final arg to gpte_to_spte()). - */ - if (pte_dirty(gpte)) - *spte = gpte_to_spte(cpu, gpte, 1); - else - /* - * If this is a read, don't set the "writable" bit in the page - * table entry, even if the Guest says it's writable. That way - * we will come back here when a write does actually occur, so - * we can update the Guest's _PAGE_DIRTY flag. - */ - set_pte(spte, gpte_to_spte(cpu, pte_wrprotect(gpte), 0)); - - /* - * Finally, we write the Guest PTE entry back: we've set the - * _PAGE_ACCESSED and maybe the _PAGE_DIRTY flags. - */ - if (likely(!cpu->linear_pages)) - lgwrite(cpu, gpte_ptr, pte_t, gpte); - - /* - * The fault is fixed, the page table is populated, the mapping - * manipulated, the result returned and the code complete. A small - * delay and a trace of alliteration are the only indications the Guest - * has that a page fault occurred at all. - */ - return true; -} - -/*H:360 - * (ii) Making sure the Guest stack is mapped. - * - * Remember that direct traps into the Guest need a mapped Guest kernel stack. - * pin_stack_pages() calls us here: we could simply call demand_page(), but as - * we've seen that logic is quite long, and usually the stack pages are already - * mapped, so it's overkill. - * - * This is a quick version which answers the question: is this virtual address - * mapped by the shadow page tables, and is it writable? - */ -static bool page_writable(struct lg_cpu *cpu, unsigned long vaddr) -{ - pte_t *spte; - unsigned long flags; - - /* You can't put your stack in the Switcher! */ - if (vaddr >= switcher_addr) - return false; - - /* If there's no shadow PTE, it's not writable. */ - spte = find_spte(cpu, vaddr, false, 0, 0); - if (!spte) - return false; - - /* - * Check the flags on the pte entry itself: it must be present and - * writable. - */ - flags = pte_flags(*spte); - return (flags & (_PAGE_PRESENT|_PAGE_RW)) == (_PAGE_PRESENT|_PAGE_RW); -} - -/* - * So, when pin_stack_pages() asks us to pin a page, we check if it's already - * in the page tables, and if not, we call demand_page() with error code 2 - * (meaning "write"). - */ -void pin_page(struct lg_cpu *cpu, unsigned long vaddr) -{ - unsigned long iomem; - - if (!page_writable(cpu, vaddr) && !demand_page(cpu, vaddr, 2, &iomem)) - kill_guest(cpu, "bad stack page %#lx", vaddr); -} -/*:*/ - -#ifdef CONFIG_X86_PAE -static void release_pmd(pmd_t *spmd) -{ - /* If the entry's not present, there's nothing to release. */ - if (pmd_flags(*spmd) & _PAGE_PRESENT) { - unsigned int i; - pte_t *ptepage = __va(pmd_pfn(*spmd) << PAGE_SHIFT); - /* For each entry in the page, we might need to release it. */ - for (i = 0; i < PTRS_PER_PTE; i++) - release_pte(ptepage[i]); - /* Now we can free the page of PTEs */ - free_page((long)ptepage); - /* And zero out the PMD entry so we never release it twice. */ - set_pmd(spmd, __pmd(0)); - } -} - -static void release_pgd(pgd_t *spgd) -{ - /* If the entry's not present, there's nothing to release. */ - if (pgd_flags(*spgd) & _PAGE_PRESENT) { - unsigned int i; - pmd_t *pmdpage = __va(pgd_pfn(*spgd) << PAGE_SHIFT); - - for (i = 0; i < PTRS_PER_PMD; i++) - release_pmd(&pmdpage[i]); - - /* Now we can free the page of PMDs */ - free_page((long)pmdpage); - /* And zero out the PGD entry so we never release it twice. */ - set_pgd(spgd, __pgd(0)); - } -} - -#else /* !CONFIG_X86_PAE */ -/*H:450 - * If we chase down the release_pgd() code, the non-PAE version looks like - * this. The PAE version is almost identical, but instead of calling - * release_pte it calls release_pmd(), which looks much like this. - */ -static void release_pgd(pgd_t *spgd) -{ - /* If the entry's not present, there's nothing to release. */ - if (pgd_flags(*spgd) & _PAGE_PRESENT) { - unsigned int i; - /* - * Converting the pfn to find the actual PTE page is easy: turn - * the page number into a physical address, then convert to a - * virtual address (easy for kernel pages like this one). - */ - pte_t *ptepage = __va(pgd_pfn(*spgd) << PAGE_SHIFT); - /* For each entry in the page, we might need to release it. */ - for (i = 0; i < PTRS_PER_PTE; i++) - release_pte(ptepage[i]); - /* Now we can free the page of PTEs */ - free_page((long)ptepage); - /* And zero out the PGD entry so we never release it twice. */ - *spgd = __pgd(0); - } -} -#endif - -/*H:445 - * We saw flush_user_mappings() twice: once from the flush_user_mappings() - * hypercall and once in new_pgdir() when we re-used a top-level pgdir page. - * It simply releases every PTE page from 0 up to the Guest's kernel address. - */ -static void flush_user_mappings(struct lguest *lg, int idx) -{ - unsigned int i; - /* Release every pgd entry up to the kernel's address. */ - for (i = 0; i < pgd_index(lg->kernel_address); i++) - release_pgd(lg->pgdirs[idx].pgdir + i); -} - -/*H:440 - * (v) Flushing (throwing away) page tables, - * - * The Guest has a hypercall to throw away the page tables: it's used when a - * large number of mappings have been changed. - */ -void guest_pagetable_flush_user(struct lg_cpu *cpu) -{ - /* Drop the userspace part of the current page table. */ - flush_user_mappings(cpu->lg, cpu->cpu_pgd); -} -/*:*/ - -/* We walk down the guest page tables to get a guest-physical address */ -bool __guest_pa(struct lg_cpu *cpu, unsigned long vaddr, unsigned long *paddr) -{ - pgd_t gpgd; - pte_t gpte; -#ifdef CONFIG_X86_PAE - pmd_t gpmd; -#endif - - /* Still not set up? Just map 1:1. */ - if (unlikely(cpu->linear_pages)) { - *paddr = vaddr; - return true; - } - - /* First step: get the top-level Guest page table entry. */ - gpgd = lgread(cpu, gpgd_addr(cpu, vaddr), pgd_t); - /* Toplevel not present? We can't map it in. */ - if (!(pgd_flags(gpgd) & _PAGE_PRESENT)) - goto fail; - -#ifdef CONFIG_X86_PAE - gpmd = lgread(cpu, gpmd_addr(gpgd, vaddr), pmd_t); - if (!(pmd_flags(gpmd) & _PAGE_PRESENT)) - goto fail; - gpte = lgread(cpu, gpte_addr(cpu, gpmd, vaddr), pte_t); -#else - gpte = lgread(cpu, gpte_addr(cpu, gpgd, vaddr), pte_t); -#endif - if (!(pte_flags(gpte) & _PAGE_PRESENT)) - goto fail; - - *paddr = pte_pfn(gpte) * PAGE_SIZE | (vaddr & ~PAGE_MASK); - return true; - -fail: - *paddr = -1UL; - return false; -} - -/* - * This is the version we normally use: kills the Guest if it uses a - * bad address - */ -unsigned long guest_pa(struct lg_cpu *cpu, unsigned long vaddr) -{ - unsigned long paddr; - - if (!__guest_pa(cpu, vaddr, &paddr)) - kill_guest(cpu, "Bad address %#lx", vaddr); - return paddr; -} - -/* - * We keep several page tables. This is a simple routine to find the page - * table (if any) corresponding to this top-level address the Guest has given - * us. - */ -static unsigned int find_pgdir(struct lguest *lg, unsigned long pgtable) -{ - unsigned int i; - for (i = 0; i < ARRAY_SIZE(lg->pgdirs); i++) - if (lg->pgdirs[i].pgdir && lg->pgdirs[i].gpgdir == pgtable) - break; - return i; -} - -/*H:435 - * And this is us, creating the new page directory. If we really do - * allocate a new one (and so the kernel parts are not there), we set - * blank_pgdir. - */ -static unsigned int new_pgdir(struct lg_cpu *cpu, - unsigned long gpgdir, - int *blank_pgdir) -{ - unsigned int next; - - /* - * We pick one entry at random to throw out. Choosing the Least - * Recently Used might be better, but this is easy. - */ - next = prandom_u32() % ARRAY_SIZE(cpu->lg->pgdirs); - /* If it's never been allocated at all before, try now. */ - if (!cpu->lg->pgdirs[next].pgdir) { - cpu->lg->pgdirs[next].pgdir = - (pgd_t *)get_zeroed_page(GFP_KERNEL); - /* If the allocation fails, just keep using the one we have */ - if (!cpu->lg->pgdirs[next].pgdir) - next = cpu->cpu_pgd; - else { - /* - * This is a blank page, so there are no kernel - * mappings: caller must map the stack! - */ - *blank_pgdir = 1; - } - } - /* Record which Guest toplevel this shadows. */ - cpu->lg->pgdirs[next].gpgdir = gpgdir; - /* Release all the non-kernel mappings. */ - flush_user_mappings(cpu->lg, next); - - /* This hasn't run on any CPU at all. */ - cpu->lg->pgdirs[next].last_host_cpu = -1; - - return next; -} - -/*H:501 - * We do need the Switcher code mapped at all times, so we allocate that - * part of the Guest page table here. We map the Switcher code immediately, - * but defer mapping of the guest register page and IDT/LDT etc page until - * just before we run the guest in map_switcher_in_guest(). - * - * We *could* do this setup in map_switcher_in_guest(), but at that point - * we've interrupts disabled, and allocating pages like that is fraught: we - * can't sleep if we need to free up some memory. - */ -static bool allocate_switcher_mapping(struct lg_cpu *cpu) -{ - int i; - - for (i = 0; i < TOTAL_SWITCHER_PAGES; i++) { - pte_t *pte = find_spte(cpu, switcher_addr + i * PAGE_SIZE, true, - CHECK_GPGD_MASK, _PAGE_TABLE); - if (!pte) - return false; - - /* - * Map the switcher page if not already there. It might - * already be there because we call allocate_switcher_mapping() - * in guest_set_pgd() just in case it did discard our Switcher - * mapping, but it probably didn't. - */ - if (i == 0 && !(pte_flags(*pte) & _PAGE_PRESENT)) { - /* Get a reference to the Switcher page. */ - get_page(lg_switcher_pages[0]); - /* Create a read-only, exectuable, kernel-style PTE */ - set_pte(pte, - mk_pte(lg_switcher_pages[0], PAGE_KERNEL_RX)); - } - } - cpu->lg->pgdirs[cpu->cpu_pgd].switcher_mapped = true; - return true; -} - -/*H:470 - * Finally, a routine which throws away everything: all PGD entries in all - * the shadow page tables, including the Guest's kernel mappings. This is used - * when we destroy the Guest. - */ -static void release_all_pagetables(struct lguest *lg) -{ - unsigned int i, j; - - /* Every shadow pagetable this Guest has */ - for (i = 0; i < ARRAY_SIZE(lg->pgdirs); i++) { - if (!lg->pgdirs[i].pgdir) - continue; - - /* Every PGD entry. */ - for (j = 0; j < PTRS_PER_PGD; j++) - release_pgd(lg->pgdirs[i].pgdir + j); - lg->pgdirs[i].switcher_mapped = false; - lg->pgdirs[i].last_host_cpu = -1; - } -} - -/* - * We also throw away everything when a Guest tells us it's changed a kernel - * mapping. Since kernel mappings are in every page table, it's easiest to - * throw them all away. This traps the Guest in amber for a while as - * everything faults back in, but it's rare. - */ -void guest_pagetable_clear_all(struct lg_cpu *cpu) -{ - release_all_pagetables(cpu->lg); - /* We need the Guest kernel stack mapped again. */ - pin_stack_pages(cpu); - /* And we need Switcher allocated. */ - if (!allocate_switcher_mapping(cpu)) - kill_guest(cpu, "Cannot populate switcher mapping"); -} - -/*H:430 - * (iv) Switching page tables - * - * Now we've seen all the page table setting and manipulation, let's see - * what happens when the Guest changes page tables (ie. changes the top-level - * pgdir). This occurs on almost every context switch. - */ -void guest_new_pagetable(struct lg_cpu *cpu, unsigned long pgtable) -{ - int newpgdir, repin = 0; - - /* - * The very first time they call this, we're actually running without - * any page tables; we've been making it up. Throw them away now. - */ - if (unlikely(cpu->linear_pages)) { - release_all_pagetables(cpu->lg); - cpu->linear_pages = false; - /* Force allocation of a new pgdir. */ - newpgdir = ARRAY_SIZE(cpu->lg->pgdirs); - } else { - /* Look to see if we have this one already. */ - newpgdir = find_pgdir(cpu->lg, pgtable); - } - - /* - * If not, we allocate or mug an existing one: if it's a fresh one, - * repin gets set to 1. - */ - if (newpgdir == ARRAY_SIZE(cpu->lg->pgdirs)) - newpgdir = new_pgdir(cpu, pgtable, &repin); - /* Change the current pgd index to the new one. */ - cpu->cpu_pgd = newpgdir; - /* - * If it was completely blank, we map in the Guest kernel stack and - * the Switcher. - */ - if (repin) - pin_stack_pages(cpu); - - if (!cpu->lg->pgdirs[cpu->cpu_pgd].switcher_mapped) { - if (!allocate_switcher_mapping(cpu)) - kill_guest(cpu, "Cannot populate switcher mapping"); - } -} -/*:*/ - -/*M:009 - * Since we throw away all mappings when a kernel mapping changes, our - * performance sucks for guests using highmem. In fact, a guest with - * PAGE_OFFSET 0xc0000000 (the default) and more than about 700MB of RAM is - * usually slower than a Guest with less memory. - * - * This, of course, cannot be fixed. It would take some kind of... well, I - * don't know, but the term "puissant code-fu" comes to mind. -:*/ - -/*H:420 - * This is the routine which actually sets the page table entry for then - * "idx"'th shadow page table. - * - * Normally, we can just throw out the old entry and replace it with 0: if they - * use it demand_page() will put the new entry in. We need to do this anyway: - * The Guest expects _PAGE_ACCESSED to be set on its PTE the first time a page - * is read from, and _PAGE_DIRTY when it's written to. - * - * But Avi Kivity pointed out that most Operating Systems (Linux included) set - * these bits on PTEs immediately anyway. This is done to save the CPU from - * having to update them, but it helps us the same way: if they set - * _PAGE_ACCESSED then we can put a read-only PTE entry in immediately, and if - * they set _PAGE_DIRTY then we can put a writable PTE entry in immediately. - */ -static void __guest_set_pte(struct lg_cpu *cpu, int idx, - unsigned long vaddr, pte_t gpte) -{ - /* Look up the matching shadow page directory entry. */ - pgd_t *spgd = spgd_addr(cpu, idx, vaddr); -#ifdef CONFIG_X86_PAE - pmd_t *spmd; -#endif - - /* If the top level isn't present, there's no entry to update. */ - if (pgd_flags(*spgd) & _PAGE_PRESENT) { -#ifdef CONFIG_X86_PAE - spmd = spmd_addr(cpu, *spgd, vaddr); - if (pmd_flags(*spmd) & _PAGE_PRESENT) { -#endif - /* Otherwise, start by releasing the existing entry. */ - pte_t *spte = spte_addr(cpu, *spgd, vaddr); - release_pte(*spte); - - /* - * If they're setting this entry as dirty or accessed, - * we might as well put that entry they've given us in - * now. This shaves 10% off a copy-on-write - * micro-benchmark. - */ - if ((pte_flags(gpte) & (_PAGE_DIRTY | _PAGE_ACCESSED)) - && !gpte_in_iomem(cpu, gpte)) { - if (!check_gpte(cpu, gpte)) - return; - set_pte(spte, - gpte_to_spte(cpu, gpte, - pte_flags(gpte) & _PAGE_DIRTY)); - } else { - /* - * Otherwise kill it and we can demand_page() - * it in later. - */ - set_pte(spte, __pte(0)); - } -#ifdef CONFIG_X86_PAE - } -#endif - } -} - -/*H:410 - * Updating a PTE entry is a little trickier. - * - * We keep track of several different page tables (the Guest uses one for each - * process, so it makes sense to cache at least a few). Each of these have - * identical kernel parts: ie. every mapping above PAGE_OFFSET is the same for - * all processes. So when the page table above that address changes, we update - * all the page tables, not just the current one. This is rare. - * - * The benefit is that when we have to track a new page table, we can keep all - * the kernel mappings. This speeds up context switch immensely. - */ -void guest_set_pte(struct lg_cpu *cpu, - unsigned long gpgdir, unsigned long vaddr, pte_t gpte) -{ - /* We don't let you remap the Switcher; we need it to get back! */ - if (vaddr >= switcher_addr) { - kill_guest(cpu, "attempt to set pte into Switcher pages"); - return; - } - - /* - * Kernel mappings must be changed on all top levels. Slow, but doesn't - * happen often. - */ - if (vaddr >= cpu->lg->kernel_address) { - unsigned int i; - for (i = 0; i < ARRAY_SIZE(cpu->lg->pgdirs); i++) - if (cpu->lg->pgdirs[i].pgdir) - __guest_set_pte(cpu, i, vaddr, gpte); - } else { - /* Is this page table one we have a shadow for? */ - int pgdir = find_pgdir(cpu->lg, gpgdir); - if (pgdir != ARRAY_SIZE(cpu->lg->pgdirs)) - /* If so, do the update. */ - __guest_set_pte(cpu, pgdir, vaddr, gpte); - } -} - -/*H:400 - * (iii) Setting up a page table entry when the Guest tells us one has changed. - * - * Just like we did in interrupts_and_traps.c, it makes sense for us to deal - * with the other side of page tables while we're here: what happens when the - * Guest asks for a page table to be updated? - * - * We already saw that demand_page() will fill in the shadow page tables when - * needed, so we can simply remove shadow page table entries whenever the Guest - * tells us they've changed. When the Guest tries to use the new entry it will - * fault and demand_page() will fix it up. - * - * So with that in mind here's our code to update a (top-level) PGD entry: - */ -void guest_set_pgd(struct lguest *lg, unsigned long gpgdir, u32 idx) -{ - int pgdir; - - if (idx > PTRS_PER_PGD) { - kill_guest(&lg->cpus[0], "Attempt to set pgd %u/%u", - idx, PTRS_PER_PGD); - return; - } - - /* If they're talking about a page table we have a shadow for... */ - pgdir = find_pgdir(lg, gpgdir); - if (pgdir < ARRAY_SIZE(lg->pgdirs)) { - /* ... throw it away. */ - release_pgd(lg->pgdirs[pgdir].pgdir + idx); - /* That might have been the Switcher mapping, remap it. */ - if (!allocate_switcher_mapping(&lg->cpus[0])) { - kill_guest(&lg->cpus[0], - "Cannot populate switcher mapping"); - } - lg->pgdirs[pgdir].last_host_cpu = -1; - } -} - -#ifdef CONFIG_X86_PAE -/* For setting a mid-level, we just throw everything away. It's easy. */ -void guest_set_pmd(struct lguest *lg, unsigned long pmdp, u32 idx) -{ - guest_pagetable_clear_all(&lg->cpus[0]); -} -#endif - -/*H:500 - * (vii) Setting up the page tables initially. - * - * When a Guest is first created, set initialize a shadow page table which - * we will populate on future faults. The Guest doesn't have any actual - * pagetables yet, so we set linear_pages to tell demand_page() to fake it - * for the moment. - * - * We do need the Switcher to be mapped at all times, so we allocate that - * part of the Guest page table here. - */ -int init_guest_pagetable(struct lguest *lg) -{ - struct lg_cpu *cpu = &lg->cpus[0]; - int allocated = 0; - - /* lg (and lg->cpus[]) starts zeroed: this allocates a new pgdir */ - cpu->cpu_pgd = new_pgdir(cpu, 0, &allocated); - if (!allocated) - return -ENOMEM; - - /* We start with a linear mapping until the initialize. */ - cpu->linear_pages = true; - - /* Allocate the page tables for the Switcher. */ - if (!allocate_switcher_mapping(cpu)) { - release_all_pagetables(lg); - return -ENOMEM; - } - - return 0; -} - -/*H:508 When the Guest calls LHCALL_LGUEST_INIT we do more setup. */ -void page_table_guest_data_init(struct lg_cpu *cpu) -{ - /* - * We tell the Guest that it can't use the virtual addresses - * used by the Switcher. This trick is equivalent to 4GB - - * switcher_addr. - */ - u32 top = ~switcher_addr + 1; - - /* We get the kernel address: above this is all kernel memory. */ - if (get_user(cpu->lg->kernel_address, - &cpu->lg->lguest_data->kernel_address) - /* - * We tell the Guest that it can't use the top virtual - * addresses (used by the Switcher). - */ - || put_user(top, &cpu->lg->lguest_data->reserve_mem)) { - kill_guest(cpu, "bad guest page %p", cpu->lg->lguest_data); - return; - } - - /* - * In flush_user_mappings() we loop from 0 to - * "pgd_index(lg->kernel_address)". This assumes it won't hit the - * Switcher mappings, so check that now. - */ - if (cpu->lg->kernel_address >= switcher_addr) - kill_guest(cpu, "bad kernel address %#lx", - cpu->lg->kernel_address); -} - -/* When a Guest dies, our cleanup is fairly simple. */ -void free_guest_pagetable(struct lguest *lg) -{ - unsigned int i; - - /* Throw away all page table pages. */ - release_all_pagetables(lg); - /* Now free the top levels: free_page() can handle 0 just fine. */ - for (i = 0; i < ARRAY_SIZE(lg->pgdirs); i++) - free_page((long)lg->pgdirs[i].pgdir); -} - -/*H:481 - * This clears the Switcher mappings for cpu #i. - */ -static void remove_switcher_percpu_map(struct lg_cpu *cpu, unsigned int i) -{ - unsigned long base = switcher_addr + PAGE_SIZE + i * PAGE_SIZE*2; - pte_t *pte; - - /* Clear the mappings for both pages. */ - pte = find_spte(cpu, base, false, 0, 0); - release_pte(*pte); - set_pte(pte, __pte(0)); - - pte = find_spte(cpu, base + PAGE_SIZE, false, 0, 0); - release_pte(*pte); - set_pte(pte, __pte(0)); -} - -/*H:480 - * (vi) Mapping the Switcher when the Guest is about to run. - * - * The Switcher and the two pages for this CPU need to be visible in the Guest - * (and not the pages for other CPUs). - * - * The pages for the pagetables have all been allocated before: we just need - * to make sure the actual PTEs are up-to-date for the CPU we're about to run - * on. - */ -void map_switcher_in_guest(struct lg_cpu *cpu, struct lguest_pages *pages) -{ - unsigned long base; - struct page *percpu_switcher_page, *regs_page; - pte_t *pte; - struct pgdir *pgdir = &cpu->lg->pgdirs[cpu->cpu_pgd]; - - /* Switcher page should always be mapped by now! */ - BUG_ON(!pgdir->switcher_mapped); - - /* - * Remember that we have two pages for each Host CPU, so we can run a - * Guest on each CPU without them interfering. We need to make sure - * those pages are mapped correctly in the Guest, but since we usually - * run on the same CPU, we cache that, and only update the mappings - * when we move. - */ - if (pgdir->last_host_cpu == raw_smp_processor_id()) - return; - - /* -1 means unknown so we remove everything. */ - if (pgdir->last_host_cpu == -1) { - unsigned int i; - for_each_possible_cpu(i) - remove_switcher_percpu_map(cpu, i); - } else { - /* We know exactly what CPU mapping to remove. */ - remove_switcher_percpu_map(cpu, pgdir->last_host_cpu); - } - - /* - * When we're running the Guest, we want the Guest's "regs" page to - * appear where the first Switcher page for this CPU is. This is an - * optimization: when the Switcher saves the Guest registers, it saves - * them into the first page of this CPU's "struct lguest_pages": if we - * make sure the Guest's register page is already mapped there, we - * don't have to copy them out again. - */ - /* Find the shadow PTE for this regs page. */ - base = switcher_addr + PAGE_SIZE - + raw_smp_processor_id() * sizeof(struct lguest_pages); - pte = find_spte(cpu, base, false, 0, 0); - regs_page = pfn_to_page(__pa(cpu->regs_page) >> PAGE_SHIFT); - get_page(regs_page); - set_pte(pte, mk_pte(regs_page, __pgprot(__PAGE_KERNEL & ~_PAGE_GLOBAL))); - - /* - * We map the second page of the struct lguest_pages read-only in - * the Guest: the IDT, GDT and other things it's not supposed to - * change. - */ - pte = find_spte(cpu, base + PAGE_SIZE, false, 0, 0); - percpu_switcher_page - = lg_switcher_pages[1 + raw_smp_processor_id()*2 + 1]; - get_page(percpu_switcher_page); - set_pte(pte, mk_pte(percpu_switcher_page, - __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL))); - - pgdir->last_host_cpu = raw_smp_processor_id(); -} - -/*H:490 - * We've made it through the page table code. Perhaps our tired brains are - * still processing the details, or perhaps we're simply glad it's over. - * - * If nothing else, note that all this complexity in juggling shadow page tables - * in sync with the Guest's page tables is for one reason: for most Guests this - * page table dance determines how bad performance will be. This is why Xen - * uses exotic direct Guest pagetable manipulation, and why both Intel and AMD - * have implemented shadow page table support directly into hardware. - * - * There is just one file remaining in the Host. - */ diff --git a/drivers/lguest/segments.c b/drivers/lguest/segments.c deleted file mode 100644 index c4fb424dfddb..000000000000 --- a/drivers/lguest/segments.c +++ /dev/null @@ -1,228 +0,0 @@ -/*P:600 - * The x86 architecture has segments, which involve a table of descriptors - * which can be used to do funky things with virtual address interpretation. - * We originally used to use segments so the Guest couldn't alter the - * Guest<->Host Switcher, and then we had to trim Guest segments, and restore - * for userspace per-thread segments, but trim again for on userspace->kernel - * transitions... This nightmarish creation was contained within this file, - * where we knew not to tread without heavy armament and a change of underwear. - * - * In these modern times, the segment handling code consists of simple sanity - * checks, and the worst you'll experience reading this code is butterfly-rash - * from frolicking through its parklike serenity. -:*/ -#include "lg.h" - -/*H:600 - * Segments & The Global Descriptor Table - * - * (That title sounds like a bad Nerdcore group. Not to suggest that there are - * any good Nerdcore groups, but in high school a friend of mine had a band - * called Joe Fish and the Chips, so there are definitely worse band names). - * - * To refresh: the GDT is a table of 8-byte values describing segments. Once - * set up, these segments can be loaded into one of the 6 "segment registers". - * - * GDT entries are passed around as "struct desc_struct"s, which like IDT - * entries are split into two 32-bit members, "a" and "b". One day, someone - * will clean that up, and be declared a Hero. (No pressure, I'm just saying). - * - * Anyway, the GDT entry contains a base (the start address of the segment), a - * limit (the size of the segment - 1), and some flags. Sounds simple, and it - * would be, except those zany Intel engineers decided that it was too boring - * to put the base at one end, the limit at the other, and the flags in - * between. They decided to shotgun the bits at random throughout the 8 bytes, - * like so: - * - * 0 16 40 48 52 56 63 - * [ limit part 1 ][ base part 1 ][ flags ][li][fl][base ] - * mit ags part 2 - * part 2 - * - * As a result, this file contains a certain amount of magic numeracy. Let's - * begin. - */ - -/* - * There are several entries we don't let the Guest set. The TSS entry is the - * "Task State Segment" which controls all kinds of delicate things. The - * LGUEST_CS and LGUEST_DS entries are reserved for the Switcher, and the - * the Guest can't be trusted to deal with double faults. - */ -static bool ignored_gdt(unsigned int num) -{ - return (num == GDT_ENTRY_TSS - || num == GDT_ENTRY_LGUEST_CS - || num == GDT_ENTRY_LGUEST_DS - || num == GDT_ENTRY_DOUBLEFAULT_TSS); -} - -/*H:630 - * Once the Guest gave us new GDT entries, we fix them up a little. We - * don't care if they're invalid: the worst that can happen is a General - * Protection Fault in the Switcher when it restores a Guest segment register - * which tries to use that entry. Then we kill the Guest for causing such a - * mess: the message will be "unhandled trap 256". - */ -static void fixup_gdt_table(struct lg_cpu *cpu, unsigned start, unsigned end) -{ - unsigned int i; - - for (i = start; i < end; i++) { - /* - * We never copy these ones to real GDT, so we don't care what - * they say - */ - if (ignored_gdt(i)) - continue; - - /* - * Segment descriptors contain a privilege level: the Guest is - * sometimes careless and leaves this as 0, even though it's - * running at privilege level 1. If so, we fix it here. - */ - if (cpu->arch.gdt[i].dpl == 0) - cpu->arch.gdt[i].dpl |= GUEST_PL; - - /* - * Each descriptor has an "accessed" bit. If we don't set it - * now, the CPU will try to set it when the Guest first loads - * that entry into a segment register. But the GDT isn't - * writable by the Guest, so bad things can happen. - */ - cpu->arch.gdt[i].type |= 0x1; - } -} - -/*H:610 - * Like the IDT, we never simply use the GDT the Guest gives us. We keep - * a GDT for each CPU, and copy across the Guest's entries each time we want to - * run the Guest on that CPU. - * - * This routine is called at boot or modprobe time for each CPU to set up the - * constant GDT entries: the ones which are the same no matter what Guest we're - * running. - */ -void setup_default_gdt_entries(struct lguest_ro_state *state) -{ - struct desc_struct *gdt = state->guest_gdt; - unsigned long tss = (unsigned long)&state->guest_tss; - - /* The Switcher segments are full 0-4G segments, privilege level 0 */ - gdt[GDT_ENTRY_LGUEST_CS] = FULL_EXEC_SEGMENT; - gdt[GDT_ENTRY_LGUEST_DS] = FULL_SEGMENT; - - /* - * The TSS segment refers to the TSS entry for this particular CPU. - */ - gdt[GDT_ENTRY_TSS].a = 0; - gdt[GDT_ENTRY_TSS].b = 0; - - gdt[GDT_ENTRY_TSS].limit0 = 0x67; - gdt[GDT_ENTRY_TSS].base0 = tss & 0xFFFF; - gdt[GDT_ENTRY_TSS].base1 = (tss >> 16) & 0xFF; - gdt[GDT_ENTRY_TSS].base2 = tss >> 24; - gdt[GDT_ENTRY_TSS].type = 0x9; /* 32-bit TSS (available) */ - gdt[GDT_ENTRY_TSS].p = 0x1; /* Entry is present */ - gdt[GDT_ENTRY_TSS].dpl = 0x0; /* Privilege level 0 */ - gdt[GDT_ENTRY_TSS].s = 0x0; /* system segment */ - -} - -/* - * This routine sets up the initial Guest GDT for booting. All entries start - * as 0 (unusable). - */ -void setup_guest_gdt(struct lg_cpu *cpu) -{ - /* - * Start with full 0-4G segments...except the Guest is allowed to use - * them, so set the privilege level appropriately in the flags. - */ - cpu->arch.gdt[GDT_ENTRY_KERNEL_CS] = FULL_EXEC_SEGMENT; - cpu->arch.gdt[GDT_ENTRY_KERNEL_DS] = FULL_SEGMENT; - cpu->arch.gdt[GDT_ENTRY_KERNEL_CS].dpl |= GUEST_PL; - cpu->arch.gdt[GDT_ENTRY_KERNEL_DS].dpl |= GUEST_PL; -} - -/*H:650 - * An optimization of copy_gdt(), for just the three "thead-local storage" - * entries. - */ -void copy_gdt_tls(const struct lg_cpu *cpu, struct desc_struct *gdt) -{ - unsigned int i; - - for (i = GDT_ENTRY_TLS_MIN; i <= GDT_ENTRY_TLS_MAX; i++) - gdt[i] = cpu->arch.gdt[i]; -} - -/*H:640 - * When the Guest is run on a different CPU, or the GDT entries have changed, - * copy_gdt() is called to copy the Guest's GDT entries across to this CPU's - * GDT. - */ -void copy_gdt(const struct lg_cpu *cpu, struct desc_struct *gdt) -{ - unsigned int i; - - /* - * The default entries from setup_default_gdt_entries() are not - * replaced. See ignored_gdt() above. - */ - for (i = 0; i < GDT_ENTRIES; i++) - if (!ignored_gdt(i)) - gdt[i] = cpu->arch.gdt[i]; -} - -/*H:620 - * This is where the Guest asks us to load a new GDT entry - * (LHCALL_LOAD_GDT_ENTRY). We tweak the entry and copy it in. - */ -void load_guest_gdt_entry(struct lg_cpu *cpu, u32 num, u32 lo, u32 hi) -{ - /* - * We assume the Guest has the same number of GDT entries as the - * Host, otherwise we'd have to dynamically allocate the Guest GDT. - */ - if (num >= ARRAY_SIZE(cpu->arch.gdt)) { - kill_guest(cpu, "too many gdt entries %i", num); - return; - } - - /* Set it up, then fix it. */ - cpu->arch.gdt[num].a = lo; - cpu->arch.gdt[num].b = hi; - fixup_gdt_table(cpu, num, num+1); - /* - * Mark that the GDT changed so the core knows it has to copy it again, - * even if the Guest is run on the same CPU. - */ - cpu->changed |= CHANGED_GDT; -} - -/* - * This is the fast-track version for just changing the three TLS entries. - * Remember that this happens on every context switch, so it's worth - * optimizing. But wouldn't it be neater to have a single hypercall to cover - * both cases? - */ -void guest_load_tls(struct lg_cpu *cpu, unsigned long gtls) -{ - struct desc_struct *tls = &cpu->arch.gdt[GDT_ENTRY_TLS_MIN]; - - __lgread(cpu, tls, gtls, sizeof(*tls)*GDT_ENTRY_TLS_ENTRIES); - fixup_gdt_table(cpu, GDT_ENTRY_TLS_MIN, GDT_ENTRY_TLS_MAX+1); - /* Note that just the TLS entries have changed. */ - cpu->changed |= CHANGED_GDT_TLS; -} - -/*H:660 - * With this, we have finished the Host. - * - * Five of the seven parts of our task are complete. You have made it through - * the Bit of Despair (I think that's somewhere in the page table code, - * myself). - * - * Next, we examine "make Switcher". It's short, but intense. - */ diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c deleted file mode 100644 index b4f79b923aea..000000000000 --- a/drivers/lguest/x86/core.c +++ /dev/null @@ -1,724 +0,0 @@ -/* - * Copyright (C) 2006, Rusty Russell IBM Corporation. - * Copyright (C) 2007, Jes Sorensen SGI. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or - * NON INFRINGEMENT. See the GNU General Public License for more - * details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - */ -/*P:450 - * This file contains the x86-specific lguest code. It used to be all - * mixed in with drivers/lguest/core.c but several foolhardy code slashers - * wrestled most of the dependencies out to here in preparation for porting - * lguest to other architectures (see what I mean by foolhardy?). - * - * This also contains a couple of non-obvious setup and teardown pieces which - * were implemented after days of debugging pain. -:*/ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include "../lg.h" - -static int cpu_had_pge; - -static struct { - unsigned long offset; - unsigned short segment; -} lguest_entry; - -/* Offset from where switcher.S was compiled to where we've copied it */ -static unsigned long switcher_offset(void) -{ - return switcher_addr - (unsigned long)start_switcher_text; -} - -/* This cpu's struct lguest_pages (after the Switcher text page) */ -static struct lguest_pages *lguest_pages(unsigned int cpu) -{ - return &(((struct lguest_pages *)(switcher_addr + PAGE_SIZE))[cpu]); -} - -static DEFINE_PER_CPU(struct lg_cpu *, lg_last_cpu); - -/*S:010 - * We approach the Switcher. - * - * Remember that each CPU has two pages which are visible to the Guest when it - * runs on that CPU. This has to contain the state for that Guest: we copy the - * state in just before we run the Guest. - * - * Each Guest has "changed" flags which indicate what has changed in the Guest - * since it last ran. We saw this set in interrupts_and_traps.c and - * segments.c. - */ -static void copy_in_guest_info(struct lg_cpu *cpu, struct lguest_pages *pages) -{ - /* - * Copying all this data can be quite expensive. We usually run the - * same Guest we ran last time (and that Guest hasn't run anywhere else - * meanwhile). If that's not the case, we pretend everything in the - * Guest has changed. - */ - if (__this_cpu_read(lg_last_cpu) != cpu || cpu->last_pages != pages) { - __this_cpu_write(lg_last_cpu, cpu); - cpu->last_pages = pages; - cpu->changed = CHANGED_ALL; - } - - /* - * These copies are pretty cheap, so we do them unconditionally: */ - /* Save the current Host top-level page directory. - */ - pages->state.host_cr3 = __pa(current->mm->pgd); - /* - * Set up the Guest's page tables to see this CPU's pages (and no - * other CPU's pages). - */ - map_switcher_in_guest(cpu, pages); - /* - * Set up the two "TSS" members which tell the CPU what stack to use - * for traps which do directly into the Guest (ie. traps at privilege - * level 1). - */ - pages->state.guest_tss.sp1 = cpu->esp1; - pages->state.guest_tss.ss1 = cpu->ss1; - - /* Copy direct-to-Guest trap entries. */ - if (cpu->changed & CHANGED_IDT) - copy_traps(cpu, pages->state.guest_idt, default_idt_entries); - - /* Copy all GDT entries which the Guest can change. */ - if (cpu->changed & CHANGED_GDT) - copy_gdt(cpu, pages->state.guest_gdt); - /* If only the TLS entries have changed, copy them. */ - else if (cpu->changed & CHANGED_GDT_TLS) - copy_gdt_tls(cpu, pages->state.guest_gdt); - - /* Mark the Guest as unchanged for next time. */ - cpu->changed = 0; -} - -/* Finally: the code to actually call into the Switcher to run the Guest. */ -static void run_guest_once(struct lg_cpu *cpu, struct lguest_pages *pages) -{ - /* This is a dummy value we need for GCC's sake. */ - unsigned int clobber; - - /* - * Copy the guest-specific information into this CPU's "struct - * lguest_pages". - */ - copy_in_guest_info(cpu, pages); - - /* - * Set the trap number to 256 (impossible value). If we fault while - * switching to the Guest (bad segment registers or bug), this will - * cause us to abort the Guest. - */ - cpu->regs->trapnum = 256; - - /* - * Now: we push the "eflags" register on the stack, then do an "lcall". - * This is how we change from using the kernel code segment to using - * the dedicated lguest code segment, as well as jumping into the - * Switcher. - * - * The lcall also pushes the old code segment (KERNEL_CS) onto the - * stack, then the address of this call. This stack layout happens to - * exactly match the stack layout created by an interrupt... - */ - asm volatile("pushf; lcall *%4" - /* - * This is how we tell GCC that %eax ("a") and %ebx ("b") - * are changed by this routine. The "=" means output. - */ - : "=a"(clobber), "=b"(clobber) - /* - * %eax contains the pages pointer. ("0" refers to the - * 0-th argument above, ie "a"). %ebx contains the - * physical address of the Guest's top-level page - * directory. - */ - : "0"(pages), - "1"(__pa(cpu->lg->pgdirs[cpu->cpu_pgd].pgdir)), - "m"(lguest_entry) - /* - * We tell gcc that all these registers could change, - * which means we don't have to save and restore them in - * the Switcher. - */ - : "memory", "%edx", "%ecx", "%edi", "%esi"); -} -/*:*/ - -unsigned long *lguest_arch_regptr(struct lg_cpu *cpu, size_t reg_off, bool any) -{ - switch (reg_off) { - case offsetof(struct pt_regs, bx): - return &cpu->regs->ebx; - case offsetof(struct pt_regs, cx): - return &cpu->regs->ecx; - case offsetof(struct pt_regs, dx): - return &cpu->regs->edx; - case offsetof(struct pt_regs, si): - return &cpu->regs->esi; - case offsetof(struct pt_regs, di): - return &cpu->regs->edi; - case offsetof(struct pt_regs, bp): - return &cpu->regs->ebp; - case offsetof(struct pt_regs, ax): - return &cpu->regs->eax; - case offsetof(struct pt_regs, ip): - return &cpu->regs->eip; - case offsetof(struct pt_regs, sp): - return &cpu->regs->esp; - } - - /* Launcher can read these, but we don't allow any setting. */ - if (any) { - switch (reg_off) { - case offsetof(struct pt_regs, ds): - return &cpu->regs->ds; - case offsetof(struct pt_regs, es): - return &cpu->regs->es; - case offsetof(struct pt_regs, fs): - return &cpu->regs->fs; - case offsetof(struct pt_regs, gs): - return &cpu->regs->gs; - case offsetof(struct pt_regs, cs): - return &cpu->regs->cs; - case offsetof(struct pt_regs, flags): - return &cpu->regs->eflags; - case offsetof(struct pt_regs, ss): - return &cpu->regs->ss; - } - } - - return NULL; -} - -/*M:002 - * There are hooks in the scheduler which we can register to tell when we - * get kicked off the CPU (preempt_notifier_register()). This would allow us - * to lazily disable SYSENTER which would regain some performance, and should - * also simplify copy_in_guest_info(). Note that we'd still need to restore - * things when we exit to Launcher userspace, but that's fairly easy. - * - * We could also try using these hooks for PGE, but that might be too expensive. - * - * The hooks were designed for KVM, but we can also put them to good use. -:*/ - -/*H:040 - * This is the i386-specific code to setup and run the Guest. Interrupts - * are disabled: we own the CPU. - */ -void lguest_arch_run_guest(struct lg_cpu *cpu) -{ - /* - * SYSENTER is an optimized way of doing system calls. We can't allow - * it because it always jumps to privilege level 0. A normal Guest - * won't try it because we don't advertise it in CPUID, but a malicious - * Guest (or malicious Guest userspace program) could, so we tell the - * CPU to disable it before running the Guest. - */ - if (boot_cpu_has(X86_FEATURE_SEP)) - wrmsr(MSR_IA32_SYSENTER_CS, 0, 0); - - /* - * Now we actually run the Guest. It will return when something - * interesting happens, and we can examine its registers to see what it - * was doing. - */ - run_guest_once(cpu, lguest_pages(raw_smp_processor_id())); - - /* - * Note that the "regs" structure contains two extra entries which are - * not really registers: a trap number which says what interrupt or - * trap made the switcher code come back, and an error code which some - * traps set. - */ - - /* Restore SYSENTER if it's supposed to be on. */ - if (boot_cpu_has(X86_FEATURE_SEP)) - wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0); - - /* - * If the Guest page faulted, then the cr2 register will tell us the - * bad virtual address. We have to grab this now, because once we - * re-enable interrupts an interrupt could fault and thus overwrite - * cr2, or we could even move off to a different CPU. - */ - if (cpu->regs->trapnum == 14) - cpu->arch.last_pagefault = read_cr2(); - /* - * Similarly, if we took a trap because the Guest used the FPU, - * we have to restore the FPU it expects to see. - * fpu__restore() may sleep and we may even move off to - * a different CPU. So all the critical stuff should be done - * before this. - */ - else if (cpu->regs->trapnum == 7 && !fpregs_active()) - fpu__restore(¤t->thread.fpu); -} - -/*H:130 - * Now we've examined the hypercall code; our Guest can make requests. - * Our Guest is usually so well behaved; it never tries to do things it isn't - * allowed to, and uses hypercalls instead. Unfortunately, Linux's paravirtual - * infrastructure isn't quite complete, because it doesn't contain replacements - * for the Intel I/O instructions. As a result, the Guest sometimes fumbles - * across one during the boot process as it probes for various things which are - * usually attached to a PC. - * - * When the Guest uses one of these instructions, we get a trap (General - * Protection Fault) and come here. We queue this to be sent out to the - * Launcher to handle. - */ - -/* - * The eip contains the *virtual* address of the Guest's instruction: - * we copy the instruction here so the Launcher doesn't have to walk - * the page tables to decode it. We handle the case (eg. in a kernel - * module) where the instruction is over two pages, and the pages are - * virtually but not physically contiguous. - * - * The longest possible x86 instruction is 15 bytes, but we don't handle - * anything that strange. - */ -static void copy_from_guest(struct lg_cpu *cpu, - void *dst, unsigned long vaddr, size_t len) -{ - size_t to_page_end = PAGE_SIZE - (vaddr % PAGE_SIZE); - unsigned long paddr; - - BUG_ON(len > PAGE_SIZE); - - /* If it goes over a page, copy in two parts. */ - if (len > to_page_end) { - /* But make sure the next page is mapped! */ - if (__guest_pa(cpu, vaddr + to_page_end, &paddr)) - copy_from_guest(cpu, dst + to_page_end, - vaddr + to_page_end, - len - to_page_end); - else - /* Otherwise fill with zeroes. */ - memset(dst + to_page_end, 0, len - to_page_end); - len = to_page_end; - } - - /* This will kill the guest if it isn't mapped, but that - * shouldn't happen. */ - __lgread(cpu, dst, guest_pa(cpu, vaddr), len); -} - - -static void setup_emulate_insn(struct lg_cpu *cpu) -{ - cpu->pending.trap = 13; - copy_from_guest(cpu, cpu->pending.insn, cpu->regs->eip, - sizeof(cpu->pending.insn)); -} - -static void setup_iomem_insn(struct lg_cpu *cpu, unsigned long iomem_addr) -{ - cpu->pending.trap = 14; - cpu->pending.addr = iomem_addr; - copy_from_guest(cpu, cpu->pending.insn, cpu->regs->eip, - sizeof(cpu->pending.insn)); -} - -/*H:050 Once we've re-enabled interrupts, we look at why the Guest exited. */ -void lguest_arch_handle_trap(struct lg_cpu *cpu) -{ - unsigned long iomem_addr; - - switch (cpu->regs->trapnum) { - case 13: /* We've intercepted a General Protection Fault. */ - /* Hand to Launcher to emulate those pesky IN and OUT insns */ - if (cpu->regs->errcode == 0) { - setup_emulate_insn(cpu); - return; - } - break; - case 14: /* We've intercepted a Page Fault. */ - /* - * The Guest accessed a virtual address that wasn't mapped. - * This happens a lot: we don't actually set up most of the page - * tables for the Guest at all when we start: as it runs it asks - * for more and more, and we set them up as required. In this - * case, we don't even tell the Guest that the fault happened. - * - * The errcode tells whether this was a read or a write, and - * whether kernel or userspace code. - */ - if (demand_page(cpu, cpu->arch.last_pagefault, - cpu->regs->errcode, &iomem_addr)) - return; - - /* Was this an access to memory mapped IO? */ - if (iomem_addr) { - /* Tell Launcher, let it handle it. */ - setup_iomem_insn(cpu, iomem_addr); - return; - } - - /* - * OK, it's really not there (or not OK): the Guest needs to - * know. We write out the cr2 value so it knows where the - * fault occurred. - * - * Note that if the Guest were really messed up, this could - * happen before it's done the LHCALL_LGUEST_INIT hypercall, so - * lg->lguest_data could be NULL - */ - if (cpu->lg->lguest_data && - put_user(cpu->arch.last_pagefault, - &cpu->lg->lguest_data->cr2)) - kill_guest(cpu, "Writing cr2"); - break; - case 7: /* We've intercepted a Device Not Available fault. */ - /* No special handling is needed here. */ - break; - case 32 ... 255: - /* This might be a syscall. */ - if (could_be_syscall(cpu->regs->trapnum)) - break; - - /* - * Other values mean a real interrupt occurred, in which case - * the Host handler has already been run. We just do a - * friendly check if another process should now be run, then - * return to run the Guest again. - */ - cond_resched(); - return; - case LGUEST_TRAP_ENTRY: - /* - * Our 'struct hcall_args' maps directly over our regs: we set - * up the pointer now to indicate a hypercall is pending. - */ - cpu->hcall = (struct hcall_args *)cpu->regs; - return; - } - - /* We didn't handle the trap, so it needs to go to the Guest. */ - if (!deliver_trap(cpu, cpu->regs->trapnum)) - /* - * If the Guest doesn't have a handler (either it hasn't - * registered any yet, or it's one of the faults we don't let - * it handle), it dies with this cryptic error message. - */ - kill_guest(cpu, "unhandled trap %li at %#lx (%#lx)", - cpu->regs->trapnum, cpu->regs->eip, - cpu->regs->trapnum == 14 ? cpu->arch.last_pagefault - : cpu->regs->errcode); -} - -/* - * Now we can look at each of the routines this calls, in increasing order of - * complexity: do_hypercalls(), emulate_insn(), maybe_do_interrupt(), - * deliver_trap() and demand_page(). After all those, we'll be ready to - * examine the Switcher, and our philosophical understanding of the Host/Guest - * duality will be complete. -:*/ -static void adjust_pge(void *on) -{ - if (on) - cr4_set_bits(X86_CR4_PGE); - else - cr4_clear_bits(X86_CR4_PGE); -} - -/*H:020 - * Now the Switcher is mapped and every thing else is ready, we need to do - * some more i386-specific initialization. - */ -void __init lguest_arch_host_init(void) -{ - int i; - - /* - * Most of the x86/switcher_32.S doesn't care that it's been moved; on - * Intel, jumps are relative, and it doesn't access any references to - * external code or data. - * - * The only exception is the interrupt handlers in switcher.S: their - * addresses are placed in a table (default_idt_entries), so we need to - * update the table with the new addresses. switcher_offset() is a - * convenience function which returns the distance between the - * compiled-in switcher code and the high-mapped copy we just made. - */ - for (i = 0; i < IDT_ENTRIES; i++) - default_idt_entries[i] += switcher_offset(); - - /* - * Set up the Switcher's per-cpu areas. - * - * Each CPU gets two pages of its own within the high-mapped region - * (aka. "struct lguest_pages"). Much of this can be initialized now, - * but some depends on what Guest we are running (which is set up in - * copy_in_guest_info()). - */ - for_each_possible_cpu(i) { - /* lguest_pages() returns this CPU's two pages. */ - struct lguest_pages *pages = lguest_pages(i); - /* This is a convenience pointer to make the code neater. */ - struct lguest_ro_state *state = &pages->state; - - /* - * The Global Descriptor Table: the Host has a different one - * for each CPU. We keep a descriptor for the GDT which says - * where it is and how big it is (the size is actually the last - * byte, not the size, hence the "-1"). - */ - state->host_gdt_desc.size = GDT_SIZE-1; - state->host_gdt_desc.address = (long)get_cpu_gdt_rw(i); - - /* - * All CPUs on the Host use the same Interrupt Descriptor - * Table, so we just use store_idt(), which gets this CPU's IDT - * descriptor. - */ - store_idt(&state->host_idt_desc); - - /* - * The descriptors for the Guest's GDT and IDT can be filled - * out now, too. We copy the GDT & IDT into ->guest_gdt and - * ->guest_idt before actually running the Guest. - */ - state->guest_idt_desc.size = sizeof(state->guest_idt)-1; - state->guest_idt_desc.address = (long)&state->guest_idt; - state->guest_gdt_desc.size = sizeof(state->guest_gdt)-1; - state->guest_gdt_desc.address = (long)&state->guest_gdt; - - /* - * We know where we want the stack to be when the Guest enters - * the Switcher: in pages->regs. The stack grows upwards, so - * we start it at the end of that structure. - */ - state->guest_tss.sp0 = (long)(&pages->regs + 1); - /* - * And this is the GDT entry to use for the stack: we keep a - * couple of special LGUEST entries. - */ - state->guest_tss.ss0 = LGUEST_DS; - - /* - * x86 can have a finegrained bitmap which indicates what I/O - * ports the process can use. We set it to the end of our - * structure, meaning "none". - */ - state->guest_tss.io_bitmap_base = sizeof(state->guest_tss); - - /* - * Some GDT entries are the same across all Guests, so we can - * set them up now. - */ - setup_default_gdt_entries(state); - /* Most IDT entries are the same for all Guests, too.*/ - setup_default_idt_entries(state, default_idt_entries); - - /* - * The Host needs to be able to use the LGUEST segments on this - * CPU, too, so put them in the Host GDT. - */ - get_cpu_gdt_rw(i)[GDT_ENTRY_LGUEST_CS] = FULL_EXEC_SEGMENT; - get_cpu_gdt_rw(i)[GDT_ENTRY_LGUEST_DS] = FULL_SEGMENT; - } - - /* - * In the Switcher, we want the %cs segment register to use the - * LGUEST_CS GDT entry: we've put that in the Host and Guest GDTs, so - * it will be undisturbed when we switch. To change %cs and jump we - * need this structure to feed to Intel's "lcall" instruction. - */ - lguest_entry.offset = (long)switch_to_guest + switcher_offset(); - lguest_entry.segment = LGUEST_CS; - - /* - * Finally, we need to turn off "Page Global Enable". PGE is an - * optimization where page table entries are specially marked to show - * they never change. The Host kernel marks all the kernel pages this - * way because it's always present, even when userspace is running. - * - * Lguest breaks this: unbeknownst to the rest of the Host kernel, we - * switch to the Guest kernel. If you don't disable this on all CPUs, - * you'll get really weird bugs that you'll chase for two days. - * - * I used to turn PGE off every time we switched to the Guest and back - * on when we return, but that slowed the Switcher down noticibly. - */ - - /* - * We don't need the complexity of CPUs coming and going while we're - * doing this. - */ - get_online_cpus(); - if (boot_cpu_has(X86_FEATURE_PGE)) { /* We have a broader idea of "global". */ - /* Remember that this was originally set (for cleanup). */ - cpu_had_pge = 1; - /* - * adjust_pge is a helper function which sets or unsets the PGE - * bit on its CPU, depending on the argument (0 == unset). - */ - on_each_cpu(adjust_pge, (void *)0, 1); - /* Turn off the feature in the global feature set. */ - clear_cpu_cap(&boot_cpu_data, X86_FEATURE_PGE); - } - put_online_cpus(); -} -/*:*/ - -void __exit lguest_arch_host_fini(void) -{ - /* If we had PGE before we started, turn it back on now. */ - get_online_cpus(); - if (cpu_had_pge) { - set_cpu_cap(&boot_cpu_data, X86_FEATURE_PGE); - /* adjust_pge's argument "1" means set PGE. */ - on_each_cpu(adjust_pge, (void *)1, 1); - } - put_online_cpus(); -} - - -/*H:122 The i386-specific hypercalls simply farm out to the right functions. */ -int lguest_arch_do_hcall(struct lg_cpu *cpu, struct hcall_args *args) -{ - switch (args->arg0) { - case LHCALL_LOAD_GDT_ENTRY: - load_guest_gdt_entry(cpu, args->arg1, args->arg2, args->arg3); - break; - case LHCALL_LOAD_IDT_ENTRY: - load_guest_idt_entry(cpu, args->arg1, args->arg2, args->arg3); - break; - case LHCALL_LOAD_TLS: - guest_load_tls(cpu, args->arg1); - break; - default: - /* Bad Guest. Bad! */ - return -EIO; - } - return 0; -} - -/*H:126 i386-specific hypercall initialization: */ -int lguest_arch_init_hypercalls(struct lg_cpu *cpu) -{ - u32 tsc_speed; - - /* - * The pointer to the Guest's "struct lguest_data" is the only argument. - * We check that address now. - */ - if (!lguest_address_ok(cpu->lg, cpu->hcall->arg1, - sizeof(*cpu->lg->lguest_data))) - return -EFAULT; - - /* - * Having checked it, we simply set lg->lguest_data to point straight - * into the Launcher's memory at the right place and then use - * copy_to_user/from_user from now on, instead of lgread/write. I put - * this in to show that I'm not immune to writing stupid - * optimizations. - */ - cpu->lg->lguest_data = cpu->lg->mem_base + cpu->hcall->arg1; - - /* - * We insist that the Time Stamp Counter exist and doesn't change with - * cpu frequency. Some devious chip manufacturers decided that TSC - * changes could be handled in software. I decided that time going - * backwards might be good for benchmarks, but it's bad for users. - * - * We also insist that the TSC be stable: the kernel detects unreliable - * TSCs for its own purposes, and we use that here. - */ - if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) && !check_tsc_unstable()) - tsc_speed = tsc_khz; - else - tsc_speed = 0; - if (put_user(tsc_speed, &cpu->lg->lguest_data->tsc_khz)) - return -EFAULT; - - /* The interrupt code might not like the system call vector. */ - if (!check_syscall_vector(cpu->lg)) - kill_guest(cpu, "bad syscall vector"); - - return 0; -} -/*:*/ - -/*L:030 - * Most of the Guest's registers are left alone: we used get_zeroed_page() to - * allocate the structure, so they will be 0. - */ -void lguest_arch_setup_regs(struct lg_cpu *cpu, unsigned long start) -{ - struct lguest_regs *regs = cpu->regs; - - /* - * There are four "segment" registers which the Guest needs to boot: - * The "code segment" register (cs) refers to the kernel code segment - * __KERNEL_CS, and the "data", "extra" and "stack" segment registers - * refer to the kernel data segment __KERNEL_DS. - * - * The privilege level is packed into the lower bits. The Guest runs - * at privilege level 1 (GUEST_PL). - */ - regs->ds = regs->es = regs->ss = __KERNEL_DS|GUEST_PL; - regs->cs = __KERNEL_CS|GUEST_PL; - - /* - * The "eflags" register contains miscellaneous flags. Bit 1 (0x002) - * is supposed to always be "1". Bit 9 (0x200) controls whether - * interrupts are enabled. We always leave interrupts enabled while - * running the Guest. - */ - regs->eflags = X86_EFLAGS_IF | X86_EFLAGS_FIXED; - - /* - * The "Extended Instruction Pointer" register says where the Guest is - * running. - */ - regs->eip = start; - - /* - * %esi points to our boot information, at physical address 0, so don't - * touch it. - */ - - /* There are a couple of GDT entries the Guest expects at boot. */ - setup_guest_gdt(cpu); -} diff --git a/drivers/lguest/x86/switcher_32.S b/drivers/lguest/x86/switcher_32.S deleted file mode 100644 index 40634b0db9f7..000000000000 --- a/drivers/lguest/x86/switcher_32.S +++ /dev/null @@ -1,388 +0,0 @@ -/*P:900 - * This is the Switcher: code which sits at 0xFFC00000 (or 0xFFE00000) astride - * both the Host and Guest to do the low-level Guest<->Host switch. It is as - * simple as it can be made, but it's naturally very specific to x86. - * - * You have now completed Preparation. If this has whet your appetite; if you - * are feeling invigorated and refreshed then the next, more challenging stage - * can be found in "make Guest". - :*/ - -/*M:012 - * Lguest is meant to be simple: my rule of thumb is that 1% more LOC must - * gain at least 1% more performance. Since neither LOC nor performance can be - * measured beforehand, it generally means implementing a feature then deciding - * if it's worth it. And once it's implemented, who can say no? - * - * This is why I haven't implemented this idea myself. I want to, but I - * haven't. You could, though. - * - * The main place where lguest performance sucks is Guest page faulting. When - * a Guest userspace process hits an unmapped page we switch back to the Host, - * walk the page tables, find it's not mapped, switch back to the Guest page - * fault handler, which calls a hypercall to set the page table entry, then - * finally returns to userspace. That's two round-trips. - * - * If we had a small walker in the Switcher, we could quickly check the Guest - * page table and if the page isn't mapped, immediately reflect the fault back - * into the Guest. This means the Switcher would have to know the top of the - * Guest page table and the page fault handler address. - * - * For simplicity, the Guest should only handle the case where the privilege - * level of the fault is 3 and probably only not present or write faults. It - * should also detect recursive faults, and hand the original fault to the - * Host (which is actually really easy). - * - * Two questions remain. Would the performance gain outweigh the complexity? - * And who would write the verse documenting it? -:*/ - -/*M:011 - * Lguest64 handles NMI. This gave me NMI envy (until I looked at their - * code). It's worth doing though, since it would let us use oprofile in the - * Host when a Guest is running. -:*/ - -/*S:100 - * Welcome to the Switcher itself! - * - * This file contains the low-level code which changes the CPU to run the Guest - * code, and returns to the Host when something happens. Understand this, and - * you understand the heart of our journey. - * - * Because this is in assembler rather than C, our tale switches from prose to - * verse. First I tried limericks: - * - * There once was an eax reg, - * To which our pointer was fed, - * It needed an add, - * Which asm-offsets.h had - * But this limerick is hurting my head. - * - * Next I tried haikus, but fitting the required reference to the seasons in - * every stanza was quickly becoming tiresome: - * - * The %eax reg - * Holds "struct lguest_pages" now: - * Cherry blossoms fall. - * - * Then I started with Heroic Verse, but the rhyming requirement leeched away - * the content density and led to some uniquely awful oblique rhymes: - * - * These constants are coming from struct offsets - * For use within the asm switcher text. - * - * Finally, I settled for something between heroic hexameter, and normal prose - * with inappropriate linebreaks. Anyway, it aint no Shakespeare. - */ - -// Not all kernel headers work from assembler -// But these ones are needed: the ENTRY() define -// And constants extracted from struct offsets -// To avoid magic numbers and breakage: -// Should they change the compiler can't save us -// Down here in the depths of assembler code. -#include -#include -#include -#include -#include - -// We mark the start of the code to copy -// It's placed in .text tho it's never run here -// You'll see the trick macro at the end -// Which interleaves data and text to effect. -.text -ENTRY(start_switcher_text) - -// When we reach switch_to_guest we have just left -// The safe and comforting shores of C code -// %eax has the "struct lguest_pages" to use -// Where we save state and still see it from the Guest -// And %ebx holds the Guest shadow pagetable: -// Once set we have truly left Host behind. -ENTRY(switch_to_guest) - // We told gcc all its regs could fade, - // Clobbered by our journey into the Guest - // We could have saved them, if we tried - // But time is our master and cycles count. - - // Segment registers must be saved for the Host - // We push them on the Host stack for later - pushl %es - pushl %ds - pushl %gs - pushl %fs - // But the compiler is fickle, and heeds - // No warning of %ebp clobbers - // When frame pointers are used. That register - // Must be saved and restored or chaos strikes. - pushl %ebp - // The Host's stack is done, now save it away - // In our "struct lguest_pages" at offset - // Distilled into asm-offsets.h - movl %esp, LGUEST_PAGES_host_sp(%eax) - - // All saved and there's now five steps before us: - // Stack, GDT, IDT, TSS - // Then last of all the page tables are flipped. - - // Yet beware that our stack pointer must be - // Always valid lest an NMI hits - // %edx does the duty here as we juggle - // %eax is lguest_pages: our stack lies within. - movl %eax, %edx - addl $LGUEST_PAGES_regs, %edx - movl %edx, %esp - - // The Guest's GDT we so carefully - // Placed in the "struct lguest_pages" before - lgdt LGUEST_PAGES_guest_gdt_desc(%eax) - - // The Guest's IDT we did partially - // Copy to "struct lguest_pages" as well. - lidt LGUEST_PAGES_guest_idt_desc(%eax) - - // The TSS entry which controls traps - // Must be loaded up with "ltr" now: - // The GDT entry that TSS uses - // Changes type when we load it: damn Intel! - // For after we switch over our page tables - // That entry will be read-only: we'd crash. - movl $(GDT_ENTRY_TSS*8), %edx - ltr %dx - - // Look back now, before we take this last step! - // The Host's TSS entry was also marked used; - // Let's clear it again for our return. - // The GDT descriptor of the Host - // Points to the table after two "size" bytes - movl (LGUEST_PAGES_host_gdt_desc+2)(%eax), %edx - // Clear "used" from type field (byte 5, bit 2) - andb $0xFD, (GDT_ENTRY_TSS*8 + 5)(%edx) - - // Once our page table's switched, the Guest is live! - // The Host fades as we run this final step. - // Our "struct lguest_pages" is now read-only. - movl %ebx, %cr3 - - // The page table change did one tricky thing: - // The Guest's register page has been mapped - // Writable under our %esp (stack) -- - // We can simply pop off all Guest regs. - popl %eax - popl %ebx - popl %ecx - popl %edx - popl %esi - popl %edi - popl %ebp - popl %gs - popl %fs - popl %ds - popl %es - - // Near the base of the stack lurk two strange fields - // Which we fill as we exit the Guest - // These are the trap number and its error - // We can simply step past them on our way. - addl $8, %esp - - // The last five stack slots hold return address - // And everything needed to switch privilege - // From Switcher's level 0 to Guest's 1, - // And the stack where the Guest had last left it. - // Interrupts are turned back on: we are Guest. - iret - -// We tread two paths to switch back to the Host -// Yet both must save Guest state and restore Host -// So we put the routine in a macro. -#define SWITCH_TO_HOST \ - /* We save the Guest state: all registers first \ - * Laid out just as "struct lguest_regs" defines */ \ - pushl %es; \ - pushl %ds; \ - pushl %fs; \ - pushl %gs; \ - pushl %ebp; \ - pushl %edi; \ - pushl %esi; \ - pushl %edx; \ - pushl %ecx; \ - pushl %ebx; \ - pushl %eax; \ - /* Our stack and our code are using segments \ - * Set in the TSS and IDT \ - * Yet if we were to touch data we'd use \ - * Whatever data segment the Guest had. \ - * Load the lguest ds segment for now. */ \ - movl $(LGUEST_DS), %eax; \ - movl %eax, %ds; \ - /* So where are we? Which CPU, which struct? \ - * The stack is our clue: our TSS starts \ - * It at the end of "struct lguest_pages". \ - * Or we may have stumbled while restoring \ - * Our Guest segment regs while in switch_to_guest, \ - * The fault pushed atop that part-unwound stack. \ - * If we round the stack down to the page start \ - * We're at the start of "struct lguest_pages". */ \ - movl %esp, %eax; \ - andl $(~(1 << PAGE_SHIFT - 1)), %eax; \ - /* Save our trap number: the switch will obscure it \ - * (In the Host the Guest regs are not mapped here) \ - * %ebx holds it safe for deliver_to_host */ \ - movl LGUEST_PAGES_regs_trapnum(%eax), %ebx; \ - /* The Host GDT, IDT and stack! \ - * All these lie safely hidden from the Guest: \ - * We must return to the Host page tables \ - * (Hence that was saved in struct lguest_pages) */ \ - movl LGUEST_PAGES_host_cr3(%eax), %edx; \ - movl %edx, %cr3; \ - /* As before, when we looked back at the Host \ - * As we left and marked TSS unused \ - * So must we now for the Guest left behind. */ \ - andb $0xFD, (LGUEST_PAGES_guest_gdt+GDT_ENTRY_TSS*8+5)(%eax); \ - /* Switch to Host's GDT, IDT. */ \ - lgdt LGUEST_PAGES_host_gdt_desc(%eax); \ - lidt LGUEST_PAGES_host_idt_desc(%eax); \ - /* Restore the Host's stack where its saved regs lie */ \ - movl LGUEST_PAGES_host_sp(%eax), %esp; \ - /* Last the TSS: our Host is returned */ \ - movl $(GDT_ENTRY_TSS*8), %edx; \ - ltr %dx; \ - /* Restore now the regs saved right at the first. */ \ - popl %ebp; \ - popl %fs; \ - popl %gs; \ - popl %ds; \ - popl %es - -// The first path is trod when the Guest has trapped: -// (Which trap it was has been pushed on the stack). -// We need only switch back, and the Host will decode -// Why we came home, and what needs to be done. -return_to_host: - SWITCH_TO_HOST - iret - -// We are lead to the second path like so: -// An interrupt, with some cause external -// Has ajerked us rudely from the Guest's code -// Again we must return home to the Host -deliver_to_host: - SWITCH_TO_HOST - // But now we must go home via that place - // Where that interrupt was supposed to go - // Had we not been ensconced, running the Guest. - // Here we see the trickness of run_guest_once(): - // The Host stack is formed like an interrupt - // With EIP, CS and EFLAGS layered. - // Interrupt handlers end with "iret" - // And that will take us home at long long last. - - // But first we must find the handler to call! - // The IDT descriptor for the Host - // Has two bytes for size, and four for address: - // %edx will hold it for us for now. - movl (LGUEST_PAGES_host_idt_desc+2)(%eax), %edx - // We now know the table address we need, - // And saved the trap's number inside %ebx. - // Yet the pointer to the handler is smeared - // Across the bits of the table entry. - // What oracle can tell us how to extract - // From such a convoluted encoding? - // I consulted gcc, and it gave - // These instructions, which I gladly credit: - leal (%edx,%ebx,8), %eax - movzwl (%eax),%edx - movl 4(%eax), %eax - xorw %ax, %ax - orl %eax, %edx - // Now the address of the handler's in %edx - // We call it now: its "iret" drops us home. - jmp *%edx - -// Every interrupt can come to us here -// But we must truly tell each apart. -// They number two hundred and fifty six -// And each must land in a different spot, -// Push its number on stack, and join the stream. - -// And worse, a mere six of the traps stand apart -// And push on their stack an addition: -// An error number, thirty two bits long -// So we punish the other two fifty -// And make them push a zero so they match. - -// Yet two fifty six entries is long -// And all will look most the same as the last -// So we create a macro which can make -// As many entries as we need to fill. - -// Note the change to .data then .text: -// We plant the address of each entry -// Into a (data) table for the Host -// To know where each Guest interrupt should go. -.macro IRQ_STUB N TARGET - .data; .long 1f; .text; 1: - // Trap eight, ten through fourteen and seventeen - // Supply an error number. Else zero. - .if (\N <> 8) && (\N < 10 || \N > 14) && (\N <> 17) - pushl $0 - .endif - pushl $\N - jmp \TARGET - ALIGN -.endm - -// This macro creates numerous entries -// Using GAS macros which out-power C's. -.macro IRQ_STUBS FIRST LAST TARGET - irq=\FIRST - .rept \LAST-\FIRST+1 - IRQ_STUB irq \TARGET - irq=irq+1 - .endr -.endm - -// Here's the marker for our pointer table -// Laid in the data section just before -// Each macro places the address of code -// Forming an array: each one points to text -// Which handles interrupt in its turn. -.data -.global default_idt_entries -default_idt_entries: -.text - // The first two traps go straight back to the Host - IRQ_STUBS 0 1 return_to_host - // We'll say nothing, yet, about NMI - IRQ_STUB 2 handle_nmi - // Other traps also return to the Host - IRQ_STUBS 3 31 return_to_host - // All interrupts go via their handlers - IRQ_STUBS 32 127 deliver_to_host - // 'Cept system calls coming from userspace - // Are to go to the Guest, never the Host. - IRQ_STUB 128 return_to_host - IRQ_STUBS 129 255 deliver_to_host - -// The NMI, what a fabulous beast -// Which swoops in and stops us no matter that -// We're suspended between heaven and hell, -// (Or more likely between the Host and Guest) -// When in it comes! We are dazed and confused -// So we do the simplest thing which one can. -// Though we've pushed the trap number and zero -// We discard them, return, and hope we live. -handle_nmi: - addl $8, %esp - iret - -// We are done; all that's left is Mastery -// And "make Mastery" is a journey long -// Designed to make your fingers itch to code. - -// Here ends the text, the file and poem. -ENTRY(end_switcher_text) diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 83a1616903f8..aba0d652095b 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -333,7 +333,7 @@ config VIRTIO_NET depends on VIRTIO ---help--- This is the virtual network driver for virtio. It can be used with - lguest or QEMU based VMMs (like KVM or Xen). Say Y or M. + QEMU based VMMs (like KVM or Xen). Say Y or M. config NLMON tristate "Virtual netlink monitoring device" diff --git a/drivers/tty/hvc/Kconfig b/drivers/tty/hvc/Kconfig index b8d5ea0ae26b..fec457edad14 100644 --- a/drivers/tty/hvc/Kconfig +++ b/drivers/tty/hvc/Kconfig @@ -4,7 +4,7 @@ config HVC_DRIVER bool help Generic "hypervisor virtual console" infrastructure for various - hypervisors (pSeries, iSeries, Xen, lguest). + hypervisors (pSeries, iSeries, Xen). It will automatically be selected if one of the back-end console drivers is selected. diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index 623f72334fa5..cff773f15b7e 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -2,8 +2,8 @@ config VIRTIO tristate ---help--- This option is selected by any driver which implements the virtio - bus, such as CONFIG_VIRTIO_PCI, CONFIG_VIRTIO_MMIO, CONFIG_LGUEST, - CONFIG_RPMSG or CONFIG_S390_GUEST. + bus, such as CONFIG_VIRTIO_PCI, CONFIG_VIRTIO_MMIO, CONFIG_RPMSG + or CONFIG_S390_GUEST. menu "Virtio drivers" diff --git a/include/linux/lguest.h b/include/linux/lguest.h deleted file mode 100644 index 6db19f35f7c5..000000000000 --- a/include/linux/lguest.h +++ /dev/null @@ -1,73 +0,0 @@ -/* - * Things the lguest guest needs to know. Note: like all lguest interfaces, - * this is subject to wild and random change between versions. - */ -#ifndef _LINUX_LGUEST_H -#define _LINUX_LGUEST_H - -#ifndef __ASSEMBLY__ -#include -#include -#include - -#define LG_CLOCK_MIN_DELTA 100UL -#define LG_CLOCK_MAX_DELTA ULONG_MAX - -/*G:031 - * The second method of communicating with the Host is to via "struct - * lguest_data". Once the Guest's initialization hypercall tells the Host where - * this is, the Guest and Host both publish information in it. -:*/ -struct lguest_data { - /* - * 512 == enabled (same as eflags in normal hardware). The Guest - * changes interrupts so often that a hypercall is too slow. - */ - unsigned int irq_enabled; - /* Fine-grained interrupt disabling by the Guest */ - DECLARE_BITMAP(blocked_interrupts, LGUEST_IRQS); - - /* - * The Host writes the virtual address of the last page fault here, - * which saves the Guest a hypercall. CR2 is the native register where - * this address would normally be found. - */ - unsigned long cr2; - - /* Wallclock time set by the Host. */ - struct timespec time; - - /* - * Interrupt pending set by the Host. The Guest should do a hypercall - * if it re-enables interrupts and sees this set (to X86_EFLAGS_IF). - */ - int irq_pending; - - /* - * Async hypercall ring. Instead of directly making hypercalls, we can - * place them in here for processing the next time the Host wants. - * This batching can be quite efficient. - */ - - /* 0xFF == done (set by Host), 0 == pending (set by Guest). */ - u8 hcall_status[LHCALL_RING_SIZE]; - /* The actual registers for the hypercalls. */ - struct hcall_args hcalls[LHCALL_RING_SIZE]; - -/* Fields initialized by the Host at boot: */ - /* Memory not to try to access */ - unsigned long reserve_mem; - /* KHz for the TSC clock. */ - u32 tsc_khz; - -/* Fields initialized by the Guest at boot: */ - /* Instruction to suppress interrupts even if enabled */ - unsigned long noirq_iret; - /* Address above which page tables are all identical. */ - unsigned long kernel_address; - /* The vector to try to use for system calls (0x40 or 0x80). */ - unsigned int syscall_vec; -}; -extern struct lguest_data lguest_data; -#endif /* __ASSEMBLY__ */ -#endif /* _LINUX_LGUEST_H */ diff --git a/include/linux/lguest_launcher.h b/include/linux/lguest_launcher.h deleted file mode 100644 index acd5b12565cc..000000000000 --- a/include/linux/lguest_launcher.h +++ /dev/null @@ -1,44 +0,0 @@ -#ifndef _LINUX_LGUEST_LAUNCHER -#define _LINUX_LGUEST_LAUNCHER -/* Everything the "lguest" userspace program needs to know. */ -#include - -/*D:010 - * Drivers - * - * The Guest needs devices to do anything useful. Since we don't let it touch - * real devices (think of the damage it could do!) we provide virtual devices. - * We emulate a PCI bus with virtio devices on it; we used to have our own - * lguest bus which was far simpler, but this tests the virtio 1.0 standard. - * - * Virtio devices are also used by kvm, so we can simply reuse their optimized - * device drivers. And one day when everyone uses virtio, my plan will be - * complete. Bwahahahah! - */ - -/* Write command first word is a request. */ -enum lguest_req -{ - LHREQ_INITIALIZE, /* + base, pfnlimit, start */ - LHREQ_GETDMA, /* No longer used */ - LHREQ_IRQ, /* + irq */ - LHREQ_BREAK, /* No longer used */ - LHREQ_EVENTFD, /* No longer used. */ - LHREQ_GETREG, /* + offset within struct pt_regs (then read value). */ - LHREQ_SETREG, /* + offset within struct pt_regs, value. */ - LHREQ_TRAP, /* + trap number to deliver to guest. */ -}; - -/* - * This is what read() of the lguest fd populates. trap == - * LGUEST_TRAP_ENTRY for an LHCALL_NOTIFY (addr is the - * argument), 14 for a page fault in the MMIO region (addr is - * the trap address, insn is the instruction), or 13 for a GPF - * (insn is the instruction). - */ -struct lguest_pending { - __u8 trap; - __u8 insn[7]; - __u32 addr; -}; -#endif /* _LINUX_LGUEST_LAUNCHER */ diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h index c07295969b7e..6d5d5faa989b 100644 --- a/include/uapi/linux/virtio_ring.h +++ b/include/uapi/linux/virtio_ring.h @@ -1,7 +1,7 @@ #ifndef _UAPI_LINUX_VIRTIO_RING_H #define _UAPI_LINUX_VIRTIO_RING_H -/* An interface for efficient virtio implementation, currently for use by KVM - * and lguest, but hopefully others soon. Do NOT change this since it will +/* An interface for efficient virtio implementation, currently for use by KVM, + * but hopefully others soon. Do NOT change this since it will * break existing servers and clients. * * This header is BSD licensed so anyone can use the definitions to implement diff --git a/tools/Makefile b/tools/Makefile index 221e1ce78b06..a19b176b914b 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -18,7 +18,6 @@ help: @echo ' iio - IIO tools' @echo ' kvm_stat - top-like utility for displaying kvm statistics' @echo ' leds - LEDs tools' - @echo ' lguest - a minimal 32-bit x86 hypervisor' @echo ' liblockdep - user-space wrapper for kernel locking-validator' @echo ' net - misc networking tools' @echo ' perf - Linux performance measurement and analysis tool' @@ -90,7 +89,7 @@ freefall: FORCE kvm_stat: FORCE $(call descend,kvm/$@) -all: acpi cgroup cpupower gpio hv firewire lguest liblockdep \ +all: acpi cgroup cpupower gpio hv firewire liblockdep \ perf selftests turbostat usb \ virtio vm net x86_energy_perf_policy \ tmon freefall objtool kvm_stat @@ -101,7 +100,7 @@ acpi_install: cpupower_install: $(call descend,power/$(@:_install=),install) -cgroup_install firewire_install gpio_install hv_install lguest_install perf_install usb_install virtio_install vm_install net_install objtool_install: +cgroup_install firewire_install gpio_install hv_install perf_install usb_install virtio_install vm_install net_install objtool_install: $(call descend,$(@:_install=),install) liblockdep_install: @@ -123,7 +122,7 @@ kvm_stat_install: $(call descend,kvm/$(@:_install=),install) install: acpi_install cgroup_install cpupower_install gpio_install \ - hv_install firewire_install lguest_install liblockdep_install \ + hv_install firewire_install liblockdep_install \ perf_install selftests_install turbostat_install usb_install \ virtio_install vm_install net_install x86_energy_perf_policy_install \ tmon_install freefall_install objtool_install kvm_stat_install @@ -134,7 +133,7 @@ acpi_clean: cpupower_clean: $(call descend,power/cpupower,clean) -cgroup_clean hv_clean firewire_clean lguest_clean spi_clean usb_clean virtio_clean vm_clean net_clean iio_clean gpio_clean objtool_clean leds_clean: +cgroup_clean hv_clean firewire_clean spi_clean usb_clean virtio_clean vm_clean net_clean iio_clean gpio_clean objtool_clean leds_clean: $(call descend,$(@:_clean=),clean) liblockdep_clean: @@ -168,7 +167,7 @@ freefall_clean: build_clean: $(call descend,build,clean) -clean: acpi_clean cgroup_clean cpupower_clean hv_clean firewire_clean lguest_clean \ +clean: acpi_clean cgroup_clean cpupower_clean hv_clean firewire_clean \ perf_clean selftests_clean turbostat_clean spi_clean usb_clean virtio_clean \ vm_clean net_clean iio_clean x86_energy_perf_policy_clean tmon_clean \ freefall_clean build_clean libbpf_clean libsubcmd_clean liblockdep_clean \ diff --git a/tools/lguest/.gitignore b/tools/lguest/.gitignore deleted file mode 100644 index 8d9a8383a52e..000000000000 --- a/tools/lguest/.gitignore +++ /dev/null @@ -1,2 +0,0 @@ -lguest -include diff --git a/tools/lguest/Makefile b/tools/lguest/Makefile deleted file mode 100644 index d04599a79802..000000000000 --- a/tools/lguest/Makefile +++ /dev/null @@ -1,14 +0,0 @@ -# This creates the demonstration utility "lguest" which runs a Linux guest. -CFLAGS:=-m32 -Wall -Wmissing-declarations -Wmissing-prototypes -O3 -U_FORTIFY_SOURCE -Iinclude - -all: lguest - -include/linux/virtio_types.h: ../../include/uapi/linux/virtio_types.h - mkdir -p include/linux 2>&1 || true - ln -sf ../../../../include/uapi/linux/virtio_types.h $@ - -lguest: include/linux/virtio_types.h - -clean: - rm -f lguest - rm -rf include diff --git a/tools/lguest/extract b/tools/lguest/extract deleted file mode 100644 index 7730bb6e4b94..000000000000 --- a/tools/lguest/extract +++ /dev/null @@ -1,58 +0,0 @@ -#! /bin/sh - -set -e - -PREFIX=$1 -shift - -trap 'rm -r $TMPDIR' 0 -TMPDIR=`mktemp -d` - -exec 3>/dev/null -for f; do - while IFS=" -" read -r LINE; do - case "$LINE" in - *$PREFIX:[0-9]*:\**) - NUM=`echo "$LINE" | sed "s/.*$PREFIX:\([0-9]*\).*/\1/"` - if [ -f $TMPDIR/$NUM ]; then - echo "$TMPDIR/$NUM already exits prior to $f" - exit 1 - fi - exec 3>>$TMPDIR/$NUM - echo $f | sed 's,\.\./,,g' > $TMPDIR/.$NUM - /bin/echo "$LINE" | sed -e "s/$PREFIX:[0-9]*//" -e "s/:\*/*/" >&3 - ;; - *$PREFIX:[0-9]*) - NUM=`echo "$LINE" | sed "s/.*$PREFIX:\([0-9]*\).*/\1/"` - if [ -f $TMPDIR/$NUM ]; then - echo "$TMPDIR/$NUM already exits prior to $f" - exit 1 - fi - exec 3>>$TMPDIR/$NUM - echo $f | sed 's,\.\./,,g' > $TMPDIR/.$NUM - /bin/echo "$LINE" | sed "s/$PREFIX:[0-9]*//" >&3 - ;; - *:\**) - /bin/echo "$LINE" | sed -e "s/:\*/*/" -e "s,/\*\*/,," >&3 - echo >&3 - exec 3>/dev/null - ;; - *) - /bin/echo "$LINE" >&3 - ;; - esac - done < $f - echo >&3 - exec 3>/dev/null -done - -LASTFILE="" -for f in $TMPDIR/*; do - if [ "$LASTFILE" != $(cat $TMPDIR/.$(basename $f) ) ]; then - LASTFILE=$(cat $TMPDIR/.$(basename $f) ) - echo "[ $LASTFILE ]" - fi - cat $f -done - diff --git a/tools/lguest/lguest.c b/tools/lguest/lguest.c deleted file mode 100644 index 897cd6f3f687..000000000000 --- a/tools/lguest/lguest.c +++ /dev/null @@ -1,3420 +0,0 @@ -/*P:100 - * This is the Launcher code, a simple program which lays out the "physical" - * memory for the new Guest by mapping the kernel image and the virtual - * devices, then opens /dev/lguest to tell the kernel about the Guest and - * control it. -:*/ -#define _LARGEFILE64_SOURCE -#define _GNU_SOURCE -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#ifndef VIRTIO_F_ANY_LAYOUT -#define VIRTIO_F_ANY_LAYOUT 27 -#endif - -/*L:110 - * We can ignore the 43 include files we need for this program, but I do want - * to draw attention to the use of kernel-style types. - * - * As Linus said, "C is a Spartan language, and so should your naming be." I - * like these abbreviations, so we define them here. Note that u64 is always - * unsigned long long, which works on all Linux systems: this means that we can - * use %llu in printf for any u64. - */ -typedef unsigned long long u64; -typedef uint32_t u32; -typedef uint16_t u16; -typedef uint8_t u8; -/*:*/ - -#define VIRTIO_CONFIG_NO_LEGACY -#define VIRTIO_PCI_NO_LEGACY -#define VIRTIO_BLK_NO_LEGACY -#define VIRTIO_NET_NO_LEGACY - -/* Use in-kernel ones, which defines VIRTIO_F_VERSION_1 */ -#include "../../include/uapi/linux/virtio_config.h" -#include "../../include/uapi/linux/virtio_net.h" -#include "../../include/uapi/linux/virtio_blk.h" -#include "../../include/uapi/linux/virtio_console.h" -#include "../../include/uapi/linux/virtio_rng.h" -#include -#include "../../include/uapi/linux/virtio_pci.h" -#include -#include "../../include/linux/lguest_launcher.h" - -#define BRIDGE_PFX "bridge:" -#ifndef SIOCBRADDIF -#define SIOCBRADDIF 0x89a2 /* add interface to bridge */ -#endif -/* We can have up to 256 pages for devices. */ -#define DEVICE_PAGES 256 -/* This will occupy 3 pages: it must be a power of 2. */ -#define VIRTQUEUE_NUM 256 - -/*L:120 - * verbose is both a global flag and a macro. The C preprocessor allows - * this, and although I wouldn't recommend it, it works quite nicely here. - */ -static bool verbose; -#define verbose(args...) \ - do { if (verbose) printf(args); } while(0) -/*:*/ - -/* The pointer to the start of guest memory. */ -static void *guest_base; -/* The maximum guest physical address allowed, and maximum possible. */ -static unsigned long guest_limit, guest_max, guest_mmio; -/* The /dev/lguest file descriptor. */ -static int lguest_fd; - -/* a per-cpu variable indicating whose vcpu is currently running */ -static unsigned int __thread cpu_id; - -/* 5 bit device number in the PCI_CONFIG_ADDR => 32 only */ -#define MAX_PCI_DEVICES 32 - -/* This is our list of devices. */ -struct device_list { - /* Counter to assign interrupt numbers. */ - unsigned int next_irq; - - /* Counter to print out convenient device numbers. */ - unsigned int device_num; - - /* PCI devices. */ - struct device *pci[MAX_PCI_DEVICES]; -}; - -/* The list of Guest devices, based on command line arguments. */ -static struct device_list devices; - -/* - * Just like struct virtio_pci_cfg_cap in uapi/linux/virtio_pci.h, - * but uses a u32 explicitly for the data. - */ -struct virtio_pci_cfg_cap_u32 { - struct virtio_pci_cap cap; - u32 pci_cfg_data; /* Data for BAR access. */ -}; - -struct virtio_pci_mmio { - struct virtio_pci_common_cfg cfg; - u16 notify; - u8 isr; - u8 padding; - /* Device-specific configuration follows this. */ -}; - -/* This is the layout (little-endian) of the PCI config space. */ -struct pci_config { - u16 vendor_id, device_id; - u16 command, status; - u8 revid, prog_if, subclass, class; - u8 cacheline_size, lat_timer, header_type, bist; - u32 bar[6]; - u32 cardbus_cis_ptr; - u16 subsystem_vendor_id, subsystem_device_id; - u32 expansion_rom_addr; - u8 capabilities, reserved1[3]; - u32 reserved2; - u8 irq_line, irq_pin, min_grant, max_latency; - - /* Now, this is the linked capability list. */ - struct virtio_pci_cap common; - struct virtio_pci_notify_cap notify; - struct virtio_pci_cap isr; - struct virtio_pci_cap device; - struct virtio_pci_cfg_cap_u32 cfg_access; -}; - -/* The device structure describes a single device. */ -struct device { - /* The name of this device, for --verbose. */ - const char *name; - - /* Any queues attached to this device */ - struct virtqueue *vq; - - /* Is it operational */ - bool running; - - /* Has it written FEATURES_OK but not re-checked it? */ - bool wrote_features_ok; - - /* PCI configuration */ - union { - struct pci_config config; - u32 config_words[sizeof(struct pci_config) / sizeof(u32)]; - }; - - /* Features we offer, and those accepted. */ - u64 features, features_accepted; - - /* Device-specific config hangs off the end of this. */ - struct virtio_pci_mmio *mmio; - - /* PCI MMIO resources (all in BAR0) */ - size_t mmio_size; - u32 mmio_addr; - - /* Device-specific data. */ - void *priv; -}; - -/* The virtqueue structure describes a queue attached to a device. */ -struct virtqueue { - struct virtqueue *next; - - /* Which device owns me. */ - struct device *dev; - - /* Name for printing errors. */ - const char *name; - - /* The actual ring of buffers. */ - struct vring vring; - - /* The information about this virtqueue (we only use queue_size on) */ - struct virtio_pci_common_cfg pci_config; - - /* Last available index we saw. */ - u16 last_avail_idx; - - /* How many are used since we sent last irq? */ - unsigned int pending_used; - - /* Eventfd where Guest notifications arrive. */ - int eventfd; - - /* Function for the thread which is servicing this virtqueue. */ - void (*service)(struct virtqueue *vq); - pid_t thread; -}; - -/* Remember the arguments to the program so we can "reboot" */ -static char **main_args; - -/* The original tty settings to restore on exit. */ -static struct termios orig_term; - -/* - * We have to be careful with barriers: our devices are all run in separate - * threads and so we need to make sure that changes visible to the Guest happen - * in precise order. - */ -#define wmb() __asm__ __volatile__("" : : : "memory") -#define rmb() __asm__ __volatile__("lock; addl $0,0(%%esp)" : : : "memory") -#define mb() __asm__ __volatile__("lock; addl $0,0(%%esp)" : : : "memory") - -/* Wrapper for the last available index. Makes it easier to change. */ -#define lg_last_avail(vq) ((vq)->last_avail_idx) - -/* - * The virtio configuration space is defined to be little-endian. x86 is - * little-endian too, but it's nice to be explicit so we have these helpers. - */ -#define cpu_to_le16(v16) (v16) -#define cpu_to_le32(v32) (v32) -#define cpu_to_le64(v64) (v64) -#define le16_to_cpu(v16) (v16) -#define le32_to_cpu(v32) (v32) -#define le64_to_cpu(v64) (v64) - -/* - * A real device would ignore weird/non-compliant driver behaviour. We - * stop and flag it, to help debugging Linux problems. - */ -#define bad_driver(d, fmt, ...) \ - errx(1, "%s: bad driver: " fmt, (d)->name, ## __VA_ARGS__) -#define bad_driver_vq(vq, fmt, ...) \ - errx(1, "%s vq %s: bad driver: " fmt, (vq)->dev->name, \ - vq->name, ## __VA_ARGS__) - -/* Is this iovec empty? */ -static bool iov_empty(const struct iovec iov[], unsigned int num_iov) -{ - unsigned int i; - - for (i = 0; i < num_iov; i++) - if (iov[i].iov_len) - return false; - return true; -} - -/* Take len bytes from the front of this iovec. */ -static void iov_consume(struct device *d, - struct iovec iov[], unsigned num_iov, - void *dest, unsigned len) -{ - unsigned int i; - - for (i = 0; i < num_iov; i++) { - unsigned int used; - - used = iov[i].iov_len < len ? iov[i].iov_len : len; - if (dest) { - memcpy(dest, iov[i].iov_base, used); - dest += used; - } - iov[i].iov_base += used; - iov[i].iov_len -= used; - len -= used; - } - if (len != 0) - bad_driver(d, "iovec too short!"); -} - -/*L:100 - * The Launcher code itself takes us out into userspace, that scary place where - * pointers run wild and free! Unfortunately, like most userspace programs, - * it's quite boring (which is why everyone likes to hack on the kernel!). - * Perhaps if you make up an Lguest Drinking Game at this point, it will get - * you through this section. Or, maybe not. - * - * The Launcher sets up a big chunk of memory to be the Guest's "physical" - * memory and stores it in "guest_base". In other words, Guest physical == - * Launcher virtual with an offset. - * - * This can be tough to get your head around, but usually it just means that we - * use these trivial conversion functions when the Guest gives us its - * "physical" addresses: - */ -static void *from_guest_phys(unsigned long addr) -{ - return guest_base + addr; -} - -static unsigned long to_guest_phys(const void *addr) -{ - return (addr - guest_base); -} - -/*L:130 - * Loading the Kernel. - * - * We start with couple of simple helper routines. open_or_die() avoids - * error-checking code cluttering the callers: - */ -static int open_or_die(const char *name, int flags) -{ - int fd = open(name, flags); - if (fd < 0) - err(1, "Failed to open %s", name); - return fd; -} - -/* map_zeroed_pages() takes a number of pages. */ -static void *map_zeroed_pages(unsigned int num) -{ - int fd = open_or_die("/dev/zero", O_RDONLY); - void *addr; - - /* - * We use a private mapping (ie. if we write to the page, it will be - * copied). We allocate an extra two pages PROT_NONE to act as guard - * pages against read/write attempts that exceed allocated space. - */ - addr = mmap(NULL, getpagesize() * (num+2), - PROT_NONE, MAP_PRIVATE, fd, 0); - - if (addr == MAP_FAILED) - err(1, "Mmapping %u pages of /dev/zero", num); - - if (mprotect(addr + getpagesize(), getpagesize() * num, - PROT_READ|PROT_WRITE) == -1) - err(1, "mprotect rw %u pages failed", num); - - /* - * One neat mmap feature is that you can close the fd, and it - * stays mapped. - */ - close(fd); - - /* Return address after PROT_NONE page */ - return addr + getpagesize(); -} - -/* Get some bytes which won't be mapped into the guest. */ -static unsigned long get_mmio_region(size_t size) -{ - unsigned long addr = guest_mmio; - size_t i; - - if (!size) - return addr; - - /* Size has to be a power of 2 (and multiple of 16) */ - for (i = 1; i < size; i <<= 1); - - guest_mmio += i; - - return addr; -} - -/* - * This routine is used to load the kernel or initrd. It tries mmap, but if - * that fails (Plan 9's kernel file isn't nicely aligned on page boundaries), - * it falls back to reading the memory in. - */ -static void map_at(int fd, void *addr, unsigned long offset, unsigned long len) -{ - ssize_t r; - - /* - * We map writable even though for some segments are marked read-only. - * The kernel really wants to be writable: it patches its own - * instructions. - * - * MAP_PRIVATE means that the page won't be copied until a write is - * done to it. This allows us to share untouched memory between - * Guests. - */ - if (mmap(addr, len, PROT_READ|PROT_WRITE, - MAP_FIXED|MAP_PRIVATE, fd, offset) != MAP_FAILED) - return; - - /* pread does a seek and a read in one shot: saves a few lines. */ - r = pread(fd, addr, len, offset); - if (r != len) - err(1, "Reading offset %lu len %lu gave %zi", offset, len, r); -} - -/* - * This routine takes an open vmlinux image, which is in ELF, and maps it into - * the Guest memory. ELF = Embedded Linking Format, which is the format used - * by all modern binaries on Linux including the kernel. - * - * The ELF headers give *two* addresses: a physical address, and a virtual - * address. We use the physical address; the Guest will map itself to the - * virtual address. - * - * We return the starting address. - */ -static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr) -{ - Elf32_Phdr phdr[ehdr->e_phnum]; - unsigned int i; - - /* - * Sanity checks on the main ELF header: an x86 executable with a - * reasonable number of correctly-sized program headers. - */ - if (ehdr->e_type != ET_EXEC - || ehdr->e_machine != EM_386 - || ehdr->e_phentsize != sizeof(Elf32_Phdr) - || ehdr->e_phnum < 1 || ehdr->e_phnum > 65536U/sizeof(Elf32_Phdr)) - errx(1, "Malformed elf header"); - - /* - * An ELF executable contains an ELF header and a number of "program" - * headers which indicate which parts ("segments") of the program to - * load where. - */ - - /* We read in all the program headers at once: */ - if (lseek(elf_fd, ehdr->e_phoff, SEEK_SET) < 0) - err(1, "Seeking to program headers"); - if (read(elf_fd, phdr, sizeof(phdr)) != sizeof(phdr)) - err(1, "Reading program headers"); - - /* - * Try all the headers: there are usually only three. A read-only one, - * a read-write one, and a "note" section which we don't load. - */ - for (i = 0; i < ehdr->e_phnum; i++) { - /* If this isn't a loadable segment, we ignore it */ - if (phdr[i].p_type != PT_LOAD) - continue; - - verbose("Section %i: size %i addr %p\n", - i, phdr[i].p_memsz, (void *)phdr[i].p_paddr); - - /* We map this section of the file at its physical address. */ - map_at(elf_fd, from_guest_phys(phdr[i].p_paddr), - phdr[i].p_offset, phdr[i].p_filesz); - } - - /* The entry point is given in the ELF header. */ - return ehdr->e_entry; -} - -/*L:150 - * A bzImage, unlike an ELF file, is not meant to be loaded. You're supposed - * to jump into it and it will unpack itself. We used to have to perform some - * hairy magic because the unpacking code scared me. - * - * Fortunately, Jeremy Fitzhardinge convinced me it wasn't that hard and wrote - * a small patch to jump over the tricky bits in the Guest, so now we just read - * the funky header so we know where in the file to load, and away we go! - */ -static unsigned long load_bzimage(int fd) -{ - struct boot_params boot; - int r; - /* Modern bzImages get loaded at 1M. */ - void *p = from_guest_phys(0x100000); - - /* - * Go back to the start of the file and read the header. It should be - * a Linux boot header (see Documentation/x86/boot.txt) - */ - lseek(fd, 0, SEEK_SET); - read(fd, &boot, sizeof(boot)); - - /* Inside the setup_hdr, we expect the magic "HdrS" */ - if (memcmp(&boot.hdr.header, "HdrS", 4) != 0) - errx(1, "This doesn't look like a bzImage to me"); - - /* Skip over the extra sectors of the header. */ - lseek(fd, (boot.hdr.setup_sects+1) * 512, SEEK_SET); - - /* Now read everything into memory. in nice big chunks. */ - while ((r = read(fd, p, 65536)) > 0) - p += r; - - /* Finally, code32_start tells us where to enter the kernel. */ - return boot.hdr.code32_start; -} - -/*L:140 - * Loading the kernel is easy when it's a "vmlinux", but most kernels - * come wrapped up in the self-decompressing "bzImage" format. With a little - * work, we can load those, too. - */ -static unsigned long load_kernel(int fd) -{ - Elf32_Ehdr hdr; - - /* Read in the first few bytes. */ - if (read(fd, &hdr, sizeof(hdr)) != sizeof(hdr)) - err(1, "Reading kernel"); - - /* If it's an ELF file, it starts with "\177ELF" */ - if (memcmp(hdr.e_ident, ELFMAG, SELFMAG) == 0) - return map_elf(fd, &hdr); - - /* Otherwise we assume it's a bzImage, and try to load it. */ - return load_bzimage(fd); -} - -/* - * This is a trivial little helper to align pages. Andi Kleen hated it because - * it calls getpagesize() twice: "it's dumb code." - * - * Kernel guys get really het up about optimization, even when it's not - * necessary. I leave this code as a reaction against that. - */ -static inline unsigned long page_align(unsigned long addr) -{ - /* Add upwards and truncate downwards. */ - return ((addr + getpagesize()-1) & ~(getpagesize()-1)); -} - -/*L:180 - * An "initial ram disk" is a disk image loaded into memory along with the - * kernel which the kernel can use to boot from without needing any drivers. - * Most distributions now use this as standard: the initrd contains the code to - * load the appropriate driver modules for the current machine. - * - * Importantly, James Morris works for RedHat, and Fedora uses initrds for its - * kernels. He sent me this (and tells me when I break it). - */ -static unsigned long load_initrd(const char *name, unsigned long mem) -{ - int ifd; - struct stat st; - unsigned long len; - - ifd = open_or_die(name, O_RDONLY); - /* fstat() is needed to get the file size. */ - if (fstat(ifd, &st) < 0) - err(1, "fstat() on initrd '%s'", name); - - /* - * We map the initrd at the top of memory, but mmap wants it to be - * page-aligned, so we round the size up for that. - */ - len = page_align(st.st_size); - map_at(ifd, from_guest_phys(mem - len), 0, st.st_size); - /* - * Once a file is mapped, you can close the file descriptor. It's a - * little odd, but quite useful. - */ - close(ifd); - verbose("mapped initrd %s size=%lu @ %p\n", name, len, (void*)mem-len); - - /* We return the initrd size. */ - return len; -} -/*:*/ - -/* - * Simple routine to roll all the commandline arguments together with spaces - * between them. - */ -static void concat(char *dst, char *args[]) -{ - unsigned int i, len = 0; - - for (i = 0; args[i]; i++) { - if (i) { - strcat(dst+len, " "); - len++; - } - strcpy(dst+len, args[i]); - len += strlen(args[i]); - } - /* In case it's empty. */ - dst[len] = '\0'; -} - -/*L:185 - * This is where we actually tell the kernel to initialize the Guest. We - * saw the arguments it expects when we looked at initialize() in lguest_user.c: - * the base of Guest "physical" memory, the top physical page to allow and the - * entry point for the Guest. - */ -static void tell_kernel(unsigned long start) -{ - unsigned long args[] = { LHREQ_INITIALIZE, - (unsigned long)guest_base, - guest_limit / getpagesize(), start, - (guest_mmio+getpagesize()-1) / getpagesize() }; - verbose("Guest: %p - %p (%#lx, MMIO %#lx)\n", - guest_base, guest_base + guest_limit, - guest_limit, guest_mmio); - lguest_fd = open_or_die("/dev/lguest", O_RDWR); - if (write(lguest_fd, args, sizeof(args)) < 0) - err(1, "Writing to /dev/lguest"); -} -/*:*/ - -/*L:200 - * Device Handling. - * - * When the Guest gives us a buffer, it sends an array of addresses and sizes. - * We need to make sure it's not trying to reach into the Launcher itself, so - * we have a convenient routine which checks it and exits with an error message - * if something funny is going on: - */ -static void *_check_pointer(struct device *d, - unsigned long addr, unsigned int size, - unsigned int line) -{ - /* - * Check if the requested address and size exceeds the allocated memory, - * or addr + size wraps around. - */ - if ((addr + size) > guest_limit || (addr + size) < addr) - bad_driver(d, "%s:%i: Invalid address %#lx", - __FILE__, line, addr); - /* - * We return a pointer for the caller's convenience, now we know it's - * safe to use. - */ - return from_guest_phys(addr); -} -/* A macro which transparently hands the line number to the real function. */ -#define check_pointer(d,addr,size) _check_pointer(d, addr, size, __LINE__) - -/* - * Each buffer in the virtqueues is actually a chain of descriptors. This - * function returns the next descriptor in the chain, or vq->vring.num if we're - * at the end. - */ -static unsigned next_desc(struct device *d, struct vring_desc *desc, - unsigned int i, unsigned int max) -{ - unsigned int next; - - /* If this descriptor says it doesn't chain, we're done. */ - if (!(desc[i].flags & VRING_DESC_F_NEXT)) - return max; - - /* Check they're not leading us off end of descriptors. */ - next = desc[i].next; - /* Make sure compiler knows to grab that: we don't want it changing! */ - wmb(); - - if (next >= max) - bad_driver(d, "Desc next is %u", next); - - return next; -} - -/* - * This actually sends the interrupt for this virtqueue, if we've used a - * buffer. - */ -static void trigger_irq(struct virtqueue *vq) -{ - unsigned long buf[] = { LHREQ_IRQ, vq->dev->config.irq_line }; - - /* Don't inform them if nothing used. */ - if (!vq->pending_used) - return; - vq->pending_used = 0; - - /* - * 2.4.7.1: - * - * If the VIRTIO_F_EVENT_IDX feature bit is not negotiated: - * The driver MUST set flags to 0 or 1. - */ - if (vq->vring.avail->flags > 1) - bad_driver_vq(vq, "avail->flags = %u\n", vq->vring.avail->flags); - - /* - * 2.4.7.2: - * - * If the VIRTIO_F_EVENT_IDX feature bit is not negotiated: - * - * - The device MUST ignore the used_event value. - * - After the device writes a descriptor index into the used ring: - * - If flags is 1, the device SHOULD NOT send an interrupt. - * - If flags is 0, the device MUST send an interrupt. - */ - if (vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT) { - return; - } - - /* - * 4.1.4.5.1: - * - * If MSI-X capability is disabled, the device MUST set the Queue - * Interrupt bit in ISR status before sending a virtqueue notification - * to the driver. - */ - vq->dev->mmio->isr = 0x1; - - /* Send the Guest an interrupt tell them we used something up. */ - if (write(lguest_fd, buf, sizeof(buf)) != 0) - err(1, "Triggering irq %i", vq->dev->config.irq_line); -} - -/* - * This looks in the virtqueue for the first available buffer, and converts - * it to an iovec for convenient access. Since descriptors consist of some - * number of output then some number of input descriptors, it's actually two - * iovecs, but we pack them into one and note how many of each there were. - * - * This function waits if necessary, and returns the descriptor number found. - */ -static unsigned wait_for_vq_desc(struct virtqueue *vq, - struct iovec iov[], - unsigned int *out_num, unsigned int *in_num) -{ - unsigned int i, head, max; - struct vring_desc *desc; - u16 last_avail = lg_last_avail(vq); - - /* - * 2.4.7.1: - * - * The driver MUST handle spurious interrupts from the device. - * - * That's why this is a while loop. - */ - - /* There's nothing available? */ - while (last_avail == vq->vring.avail->idx) { - u64 event; - - /* - * Since we're about to sleep, now is a good time to tell the - * Guest about what we've used up to now. - */ - trigger_irq(vq); - - /* OK, now we need to know about added descriptors. */ - vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY; - - /* - * They could have slipped one in as we were doing that: make - * sure it's written, then check again. - */ - mb(); - if (last_avail != vq->vring.avail->idx) { - vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY; - break; - } - - /* Nothing new? Wait for eventfd to tell us they refilled. */ - if (read(vq->eventfd, &event, sizeof(event)) != sizeof(event)) - errx(1, "Event read failed?"); - - /* We don't need to be notified again. */ - vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY; - } - - /* Check it isn't doing very strange things with descriptor numbers. */ - if ((u16)(vq->vring.avail->idx - last_avail) > vq->vring.num) - bad_driver_vq(vq, "Guest moved used index from %u to %u", - last_avail, vq->vring.avail->idx); - - /* - * Make sure we read the descriptor number *after* we read the ring - * update; don't let the cpu or compiler change the order. - */ - rmb(); - - /* - * Grab the next descriptor number they're advertising, and increment - * the index we've seen. - */ - head = vq->vring.avail->ring[last_avail % vq->vring.num]; - lg_last_avail(vq)++; - - /* If their number is silly, that's a fatal mistake. */ - if (head >= vq->vring.num) - bad_driver_vq(vq, "Guest says index %u is available", head); - - /* When we start there are none of either input nor output. */ - *out_num = *in_num = 0; - - max = vq->vring.num; - desc = vq->vring.desc; - i = head; - - /* - * We have to read the descriptor after we read the descriptor number, - * but there's a data dependency there so the CPU shouldn't reorder - * that: no rmb() required. - */ - - do { - /* - * If this is an indirect entry, then this buffer contains a - * descriptor table which we handle as if it's any normal - * descriptor chain. - */ - if (desc[i].flags & VRING_DESC_F_INDIRECT) { - /* 2.4.5.3.1: - * - * The driver MUST NOT set the VIRTQ_DESC_F_INDIRECT - * flag unless the VIRTIO_F_INDIRECT_DESC feature was - * negotiated. - */ - if (!(vq->dev->features_accepted & - (1<vring.desc) - bad_driver_vq(vq, "Indirect within indirect"); - - /* - * Proposed update VIRTIO-134 spells this out: - * - * A driver MUST NOT set both VIRTQ_DESC_F_INDIRECT - * and VIRTQ_DESC_F_NEXT in flags. - */ - if (desc[i].flags & VRING_DESC_F_NEXT) - bad_driver_vq(vq, "indirect and next together"); - - if (desc[i].len % sizeof(struct vring_desc)) - bad_driver_vq(vq, - "Invalid size for indirect table"); - /* - * 2.4.5.3.2: - * - * The device MUST ignore the write-only flag - * (flags&VIRTQ_DESC_F_WRITE) in the descriptor that - * refers to an indirect table. - * - * We ignore it here: :) - */ - - max = desc[i].len / sizeof(struct vring_desc); - desc = check_pointer(vq->dev, desc[i].addr, desc[i].len); - i = 0; - - /* 2.4.5.3.1: - * - * A driver MUST NOT create a descriptor chain longer - * than the Queue Size of the device. - */ - if (max > vq->pci_config.queue_size) - bad_driver_vq(vq, - "indirect has too many entries"); - } - - /* Grab the first descriptor, and check it's OK. */ - iov[*out_num + *in_num].iov_len = desc[i].len; - iov[*out_num + *in_num].iov_base - = check_pointer(vq->dev, desc[i].addr, desc[i].len); - /* If this is an input descriptor, increment that count. */ - if (desc[i].flags & VRING_DESC_F_WRITE) - (*in_num)++; - else { - /* - * If it's an output descriptor, they're all supposed - * to come before any input descriptors. - */ - if (*in_num) - bad_driver_vq(vq, - "Descriptor has out after in"); - (*out_num)++; - } - - /* If we've got too many, that implies a descriptor loop. */ - if (*out_num + *in_num > max) - bad_driver_vq(vq, "Looped descriptor"); - } while ((i = next_desc(vq->dev, desc, i, max)) != max); - - return head; -} - -/* - * After we've used one of their buffers, we tell the Guest about it. Sometime - * later we'll want to send them an interrupt using trigger_irq(); note that - * wait_for_vq_desc() does that for us if it has to wait. - */ -static void add_used(struct virtqueue *vq, unsigned int head, int len) -{ - struct vring_used_elem *used; - - /* - * The virtqueue contains a ring of used buffers. Get a pointer to the - * next entry in that used ring. - */ - used = &vq->vring.used->ring[vq->vring.used->idx % vq->vring.num]; - used->id = head; - used->len = len; - /* Make sure buffer is written before we update index. */ - wmb(); - vq->vring.used->idx++; - vq->pending_used++; -} - -/* And here's the combo meal deal. Supersize me! */ -static void add_used_and_trigger(struct virtqueue *vq, unsigned head, int len) -{ - add_used(vq, head, len); - trigger_irq(vq); -} - -/* - * The Console - * - * We associate some data with the console for our exit hack. - */ -struct console_abort { - /* How many times have they hit ^C? */ - int count; - /* When did they start? */ - struct timeval start; -}; - -/* This is the routine which handles console input (ie. stdin). */ -static void console_input(struct virtqueue *vq) -{ - int len; - unsigned int head, in_num, out_num; - struct console_abort *abort = vq->dev->priv; - struct iovec iov[vq->vring.num]; - - /* Make sure there's a descriptor available. */ - head = wait_for_vq_desc(vq, iov, &out_num, &in_num); - if (out_num) - bad_driver_vq(vq, "Output buffers in console in queue?"); - - /* Read into it. This is where we usually wait. */ - len = readv(STDIN_FILENO, iov, in_num); - if (len <= 0) { - /* Ran out of input? */ - warnx("Failed to get console input, ignoring console."); - /* - * For simplicity, dying threads kill the whole Launcher. So - * just nap here. - */ - for (;;) - pause(); - } - - /* Tell the Guest we used a buffer. */ - add_used_and_trigger(vq, head, len); - - /* - * Three ^C within one second? Exit. - * - * This is such a hack, but works surprisingly well. Each ^C has to - * be in a buffer by itself, so they can't be too fast. But we check - * that we get three within about a second, so they can't be too - * slow. - */ - if (len != 1 || ((char *)iov[0].iov_base)[0] != 3) { - abort->count = 0; - return; - } - - abort->count++; - if (abort->count == 1) - gettimeofday(&abort->start, NULL); - else if (abort->count == 3) { - struct timeval now; - gettimeofday(&now, NULL); - /* Kill all Launcher processes with SIGINT, like normal ^C */ - if (now.tv_sec <= abort->start.tv_sec+1) - kill(0, SIGINT); - abort->count = 0; - } -} - -/* This is the routine which handles console output (ie. stdout). */ -static void console_output(struct virtqueue *vq) -{ - unsigned int head, out, in; - struct iovec iov[vq->vring.num]; - - /* We usually wait in here, for the Guest to give us something. */ - head = wait_for_vq_desc(vq, iov, &out, &in); - if (in) - bad_driver_vq(vq, "Input buffers in console output queue?"); - - /* writev can return a partial write, so we loop here. */ - while (!iov_empty(iov, out)) { - int len = writev(STDOUT_FILENO, iov, out); - if (len <= 0) { - warn("Write to stdout gave %i (%d)", len, errno); - break; - } - iov_consume(vq->dev, iov, out, NULL, len); - } - - /* - * We're finished with that buffer: if we're going to sleep, - * wait_for_vq_desc() will prod the Guest with an interrupt. - */ - add_used(vq, head, 0); -} - -/* - * The Network - * - * Handling output for network is also simple: we get all the output buffers - * and write them to /dev/net/tun. - */ -struct net_info { - int tunfd; -}; - -static void net_output(struct virtqueue *vq) -{ - struct net_info *net_info = vq->dev->priv; - unsigned int head, out, in; - struct iovec iov[vq->vring.num]; - - /* We usually wait in here for the Guest to give us a packet. */ - head = wait_for_vq_desc(vq, iov, &out, &in); - if (in) - bad_driver_vq(vq, "Input buffers in net output queue?"); - /* - * Send the whole thing through to /dev/net/tun. It expects the exact - * same format: what a coincidence! - */ - if (writev(net_info->tunfd, iov, out) < 0) - warnx("Write to tun failed (%d)?", errno); - - /* - * Done with that one; wait_for_vq_desc() will send the interrupt if - * all packets are processed. - */ - add_used(vq, head, 0); -} - -/* - * Handling network input is a bit trickier, because I've tried to optimize it. - * - * First we have a helper routine which tells is if from this file descriptor - * (ie. the /dev/net/tun device) will block: - */ -static bool will_block(int fd) -{ - fd_set fdset; - struct timeval zero = { 0, 0 }; - FD_ZERO(&fdset); - FD_SET(fd, &fdset); - return select(fd+1, &fdset, NULL, NULL, &zero) != 1; -} - -/* - * This handles packets coming in from the tun device to our Guest. Like all - * service routines, it gets called again as soon as it returns, so you don't - * see a while(1) loop here. - */ -static void net_input(struct virtqueue *vq) -{ - int len; - unsigned int head, out, in; - struct iovec iov[vq->vring.num]; - struct net_info *net_info = vq->dev->priv; - - /* - * Get a descriptor to write an incoming packet into. This will also - * send an interrupt if they're out of descriptors. - */ - head = wait_for_vq_desc(vq, iov, &out, &in); - if (out) - bad_driver_vq(vq, "Output buffers in net input queue?"); - - /* - * If it looks like we'll block reading from the tun device, send them - * an interrupt. - */ - if (vq->pending_used && will_block(net_info->tunfd)) - trigger_irq(vq); - - /* - * Read in the packet. This is where we normally wait (when there's no - * incoming network traffic). - */ - len = readv(net_info->tunfd, iov, in); - if (len <= 0) - warn("Failed to read from tun (%d).", errno); - - /* - * Mark that packet buffer as used, but don't interrupt here. We want - * to wait until we've done as much work as we can. - */ - add_used(vq, head, len); -} -/*:*/ - -/* This is the helper to create threads: run the service routine in a loop. */ -static int do_thread(void *_vq) -{ - struct virtqueue *vq = _vq; - - for (;;) - vq->service(vq); - return 0; -} - -/* - * When a child dies, we kill our entire process group with SIGTERM. This - * also has the side effect that the shell restores the console for us! - */ -static void kill_launcher(int signal) -{ - kill(0, SIGTERM); -} - -static void reset_vq_pci_config(struct virtqueue *vq) -{ - vq->pci_config.queue_size = VIRTQUEUE_NUM; - vq->pci_config.queue_enable = 0; -} - -static void reset_device(struct device *dev) -{ - struct virtqueue *vq; - - verbose("Resetting device %s\n", dev->name); - - /* Clear any features they've acked. */ - dev->features_accepted = 0; - - /* We're going to be explicitly killing threads, so ignore them. */ - signal(SIGCHLD, SIG_IGN); - - /* - * 4.1.4.3.1: - * - * The device MUST present a 0 in queue_enable on reset. - * - * This means we set it here, and reset the saved ones in every vq. - */ - dev->mmio->cfg.queue_enable = 0; - - /* Get rid of the virtqueue threads */ - for (vq = dev->vq; vq; vq = vq->next) { - vq->last_avail_idx = 0; - reset_vq_pci_config(vq); - if (vq->thread != (pid_t)-1) { - kill(vq->thread, SIGTERM); - waitpid(vq->thread, NULL, 0); - vq->thread = (pid_t)-1; - } - } - dev->running = false; - dev->wrote_features_ok = false; - - /* Now we care if threads die. */ - signal(SIGCHLD, (void *)kill_launcher); -} - -static void cleanup_devices(void) -{ - unsigned int i; - - for (i = 1; i < MAX_PCI_DEVICES; i++) { - struct device *d = devices.pci[i]; - if (!d) - continue; - reset_device(d); - } - - /* If we saved off the original terminal settings, restore them now. */ - if (orig_term.c_lflag & (ISIG|ICANON|ECHO)) - tcsetattr(STDIN_FILENO, TCSANOW, &orig_term); -} - -/*L:217 - * We do PCI. This is mainly done to let us test the kernel virtio PCI - * code. - */ - -/* Linux expects a PCI host bridge: ours is a dummy, and first on the bus. */ -static struct device pci_host_bridge; - -static void init_pci_host_bridge(void) -{ - pci_host_bridge.name = "PCI Host Bridge"; - pci_host_bridge.config.class = 0x06; /* bridge */ - pci_host_bridge.config.subclass = 0; /* host bridge */ - devices.pci[0] = &pci_host_bridge; -} - -/* The IO ports used to read the PCI config space. */ -#define PCI_CONFIG_ADDR 0xCF8 -#define PCI_CONFIG_DATA 0xCFC - -/* - * Not really portable, but does help readability: this is what the Guest - * writes to the PCI_CONFIG_ADDR IO port. - */ -union pci_config_addr { - struct { - unsigned mbz: 2; - unsigned offset: 6; - unsigned funcnum: 3; - unsigned devnum: 5; - unsigned busnum: 8; - unsigned reserved: 7; - unsigned enabled : 1; - } bits; - u32 val; -}; - -/* - * We cache what they wrote to the address port, so we know what they're - * talking about when they access the data port. - */ -static union pci_config_addr pci_config_addr; - -static struct device *find_pci_device(unsigned int index) -{ - return devices.pci[index]; -} - -/* PCI can do 1, 2 and 4 byte reads; we handle that here. */ -static void ioread(u16 off, u32 v, u32 mask, u32 *val) -{ - assert(off < 4); - assert(mask == 0xFF || mask == 0xFFFF || mask == 0xFFFFFFFF); - *val = (v >> (off * 8)) & mask; -} - -/* PCI can do 1, 2 and 4 byte writes; we handle that here. */ -static void iowrite(u16 off, u32 v, u32 mask, u32 *dst) -{ - assert(off < 4); - assert(mask == 0xFF || mask == 0xFFFF || mask == 0xFFFFFFFF); - *dst &= ~(mask << (off * 8)); - *dst |= (v & mask) << (off * 8); -} - -/* - * Where PCI_CONFIG_DATA accesses depends on the previous write to - * PCI_CONFIG_ADDR. - */ -static struct device *dev_and_reg(u32 *reg) -{ - if (!pci_config_addr.bits.enabled) - return NULL; - - if (pci_config_addr.bits.funcnum != 0) - return NULL; - - if (pci_config_addr.bits.busnum != 0) - return NULL; - - if (pci_config_addr.bits.offset * 4 >= sizeof(struct pci_config)) - return NULL; - - *reg = pci_config_addr.bits.offset; - return find_pci_device(pci_config_addr.bits.devnum); -} - -/* - * We can get invalid combinations of values while they're writing, so we - * only fault if they try to write with some invalid bar/offset/length. - */ -static bool valid_bar_access(struct device *d, - struct virtio_pci_cfg_cap_u32 *cfg_access) -{ - /* We only have 1 bar (BAR0) */ - if (cfg_access->cap.bar != 0) - return false; - - /* Check it's within BAR0. */ - if (cfg_access->cap.offset >= d->mmio_size - || cfg_access->cap.offset + cfg_access->cap.length > d->mmio_size) - return false; - - /* Check length is 1, 2 or 4. */ - if (cfg_access->cap.length != 1 - && cfg_access->cap.length != 2 - && cfg_access->cap.length != 4) - return false; - - /* - * 4.1.4.7.2: - * - * The driver MUST NOT write a cap.offset which is not a multiple of - * cap.length (ie. all accesses MUST be aligned). - */ - if (cfg_access->cap.offset % cfg_access->cap.length != 0) - return false; - - /* Return pointer into word in BAR0. */ - return true; -} - -/* Is this accessing the PCI config address port?. */ -static bool is_pci_addr_port(u16 port) -{ - return port >= PCI_CONFIG_ADDR && port < PCI_CONFIG_ADDR + 4; -} - -static bool pci_addr_iowrite(u16 port, u32 mask, u32 val) -{ - iowrite(port - PCI_CONFIG_ADDR, val, mask, - &pci_config_addr.val); - verbose("PCI%s: %#x/%x: bus %u dev %u func %u reg %u\n", - pci_config_addr.bits.enabled ? "" : " DISABLED", - val, mask, - pci_config_addr.bits.busnum, - pci_config_addr.bits.devnum, - pci_config_addr.bits.funcnum, - pci_config_addr.bits.offset); - return true; -} - -static void pci_addr_ioread(u16 port, u32 mask, u32 *val) -{ - ioread(port - PCI_CONFIG_ADDR, pci_config_addr.val, mask, val); -} - -/* Is this accessing the PCI config data port?. */ -static bool is_pci_data_port(u16 port) -{ - return port >= PCI_CONFIG_DATA && port < PCI_CONFIG_DATA + 4; -} - -static void emulate_mmio_write(struct device *d, u32 off, u32 val, u32 mask); - -static bool pci_data_iowrite(u16 port, u32 mask, u32 val) -{ - u32 reg, portoff; - struct device *d = dev_and_reg(®); - - /* Complain if they don't belong to a device. */ - if (!d) - return false; - - /* They can do 1 byte writes, etc. */ - portoff = port - PCI_CONFIG_DATA; - - /* - * PCI uses a weird way to determine the BAR size: the OS - * writes all 1's, and sees which ones stick. - */ - if (&d->config_words[reg] == &d->config.bar[0]) { - int i; - - iowrite(portoff, val, mask, &d->config.bar[0]); - for (i = 0; (1 << i) < d->mmio_size; i++) - d->config.bar[0] &= ~(1 << i); - return true; - } else if ((&d->config_words[reg] > &d->config.bar[0] - && &d->config_words[reg] <= &d->config.bar[6]) - || &d->config_words[reg] == &d->config.expansion_rom_addr) { - /* Allow writing to any other BAR, or expansion ROM */ - iowrite(portoff, val, mask, &d->config_words[reg]); - return true; - /* We let them override latency timer and cacheline size */ - } else if (&d->config_words[reg] == (void *)&d->config.cacheline_size) { - /* Only let them change the first two fields. */ - if (mask == 0xFFFFFFFF) - mask = 0xFFFF; - iowrite(portoff, val, mask, &d->config_words[reg]); - return true; - } else if (&d->config_words[reg] == (void *)&d->config.command - && mask == 0xFFFF) { - /* Ignore command writes. */ - return true; - } else if (&d->config_words[reg] - == (void *)&d->config.cfg_access.cap.bar - || &d->config_words[reg] - == &d->config.cfg_access.cap.length - || &d->config_words[reg] - == &d->config.cfg_access.cap.offset) { - - /* - * The VIRTIO_PCI_CAP_PCI_CFG capability - * provides a backdoor to access the MMIO - * regions without mapping them. Weird, but - * useful. - */ - iowrite(portoff, val, mask, &d->config_words[reg]); - return true; - } else if (&d->config_words[reg] == &d->config.cfg_access.pci_cfg_data) { - u32 write_mask; - - /* - * 4.1.4.7.1: - * - * Upon detecting driver write access to pci_cfg_data, the - * device MUST execute a write access at offset cap.offset at - * BAR selected by cap.bar using the first cap.length bytes - * from pci_cfg_data. - */ - - /* Must be bar 0 */ - if (!valid_bar_access(d, &d->config.cfg_access)) - return false; - - iowrite(portoff, val, mask, &d->config.cfg_access.pci_cfg_data); - - /* - * Now emulate a write. The mask we use is set by - * len, *not* this write! - */ - write_mask = (1ULL<<(8*d->config.cfg_access.cap.length)) - 1; - verbose("Window writing %#x/%#x to bar %u, offset %u len %u\n", - d->config.cfg_access.pci_cfg_data, write_mask, - d->config.cfg_access.cap.bar, - d->config.cfg_access.cap.offset, - d->config.cfg_access.cap.length); - - emulate_mmio_write(d, d->config.cfg_access.cap.offset, - d->config.cfg_access.pci_cfg_data, - write_mask); - return true; - } - - /* - * 4.1.4.1: - * - * The driver MUST NOT write into any field of the capability - * structure, with the exception of those with cap_type - * VIRTIO_PCI_CAP_PCI_CFG... - */ - return false; -} - -static u32 emulate_mmio_read(struct device *d, u32 off, u32 mask); - -static void pci_data_ioread(u16 port, u32 mask, u32 *val) -{ - u32 reg; - struct device *d = dev_and_reg(®); - - if (!d) - return; - - /* Read through the PCI MMIO access window is special */ - if (&d->config_words[reg] == &d->config.cfg_access.pci_cfg_data) { - u32 read_mask; - - /* - * 4.1.4.7.1: - * - * Upon detecting driver read access to pci_cfg_data, the - * device MUST execute a read access of length cap.length at - * offset cap.offset at BAR selected by cap.bar and store the - * first cap.length bytes in pci_cfg_data. - */ - /* Must be bar 0 */ - if (!valid_bar_access(d, &d->config.cfg_access)) - bad_driver(d, - "Invalid cfg_access to bar%u, offset %u len %u", - d->config.cfg_access.cap.bar, - d->config.cfg_access.cap.offset, - d->config.cfg_access.cap.length); - - /* - * Read into the window. The mask we use is set by - * len, *not* this read! - */ - read_mask = (1ULL<<(8*d->config.cfg_access.cap.length))-1; - d->config.cfg_access.pci_cfg_data - = emulate_mmio_read(d, - d->config.cfg_access.cap.offset, - read_mask); - verbose("Window read %#x/%#x from bar %u, offset %u len %u\n", - d->config.cfg_access.pci_cfg_data, read_mask, - d->config.cfg_access.cap.bar, - d->config.cfg_access.cap.offset, - d->config.cfg_access.cap.length); - } - ioread(port - PCI_CONFIG_DATA, d->config_words[reg], mask, val); -} - -/*L:216 - * This is where we emulate a handful of Guest instructions. It's ugly - * and we used to do it in the kernel but it grew over time. - */ - -/* - * We use the ptrace syscall's pt_regs struct to talk about registers - * to lguest: these macros convert the names to the offsets. - */ -#define getreg(name) getreg_off(offsetof(struct user_regs_struct, name)) -#define setreg(name, val) \ - setreg_off(offsetof(struct user_regs_struct, name), (val)) - -static u32 getreg_off(size_t offset) -{ - u32 r; - unsigned long args[] = { LHREQ_GETREG, offset }; - - if (pwrite(lguest_fd, args, sizeof(args), cpu_id) < 0) - err(1, "Getting register %u", offset); - if (pread(lguest_fd, &r, sizeof(r), cpu_id) != sizeof(r)) - err(1, "Reading register %u", offset); - - return r; -} - -static void setreg_off(size_t offset, u32 val) -{ - unsigned long args[] = { LHREQ_SETREG, offset, val }; - - if (pwrite(lguest_fd, args, sizeof(args), cpu_id) < 0) - err(1, "Setting register %u", offset); -} - -/* Get register by instruction encoding */ -static u32 getreg_num(unsigned regnum, u32 mask) -{ - /* 8 bit ops use regnums 4-7 for high parts of word */ - if (mask == 0xFF && (regnum & 0x4)) - return getreg_num(regnum & 0x3, 0xFFFF) >> 8; - - switch (regnum) { - case 0: return getreg(eax) & mask; - case 1: return getreg(ecx) & mask; - case 2: return getreg(edx) & mask; - case 3: return getreg(ebx) & mask; - case 4: return getreg(esp) & mask; - case 5: return getreg(ebp) & mask; - case 6: return getreg(esi) & mask; - case 7: return getreg(edi) & mask; - } - abort(); -} - -/* Set register by instruction encoding */ -static void setreg_num(unsigned regnum, u32 val, u32 mask) -{ - /* Don't try to set bits out of range */ - assert(~(val & ~mask)); - - /* 8 bit ops use regnums 4-7 for high parts of word */ - if (mask == 0xFF && (regnum & 0x4)) { - /* Construct the 16 bits we want. */ - val = (val << 8) | getreg_num(regnum & 0x3, 0xFF); - setreg_num(regnum & 0x3, val, 0xFFFF); - return; - } - - switch (regnum) { - case 0: setreg(eax, val | (getreg(eax) & ~mask)); return; - case 1: setreg(ecx, val | (getreg(ecx) & ~mask)); return; - case 2: setreg(edx, val | (getreg(edx) & ~mask)); return; - case 3: setreg(ebx, val | (getreg(ebx) & ~mask)); return; - case 4: setreg(esp, val | (getreg(esp) & ~mask)); return; - case 5: setreg(ebp, val | (getreg(ebp) & ~mask)); return; - case 6: setreg(esi, val | (getreg(esi) & ~mask)); return; - case 7: setreg(edi, val | (getreg(edi) & ~mask)); return; - } - abort(); -} - -/* Get bytes of displacement appended to instruction, from r/m encoding */ -static u32 insn_displacement_len(u8 mod_reg_rm) -{ - /* Switch on the mod bits */ - switch (mod_reg_rm >> 6) { - case 0: - /* If mod == 0, and r/m == 101, 16-bit displacement follows */ - if ((mod_reg_rm & 0x7) == 0x5) - return 2; - /* Normally, mod == 0 means no literal displacement */ - return 0; - case 1: - /* One byte displacement */ - return 1; - case 2: - /* Four byte displacement */ - return 4; - case 3: - /* Register mode */ - return 0; - } - abort(); -} - -static void emulate_insn(const u8 insn[]) -{ - unsigned long args[] = { LHREQ_TRAP, 13 }; - unsigned int insnlen = 0, in = 0, small_operand = 0, byte_access; - unsigned int eax, port, mask; - /* - * Default is to return all-ones on IO port reads, which traditionally - * means "there's nothing there". - */ - u32 val = 0xFFFFFFFF; - - /* - * This must be the Guest kernel trying to do something, not userspace! - * The bottom two bits of the CS segment register are the privilege - * level. - */ - if ((getreg(xcs) & 3) != 0x1) - goto no_emulate; - - /* Decoding x86 instructions is icky. */ - - /* - * Around 2.6.33, the kernel started using an emulation for the - * cmpxchg8b instruction in early boot on many configurations. This - * code isn't paravirtualized, and it tries to disable interrupts. - * Ignore it, which will Mostly Work. - */ - if (insn[insnlen] == 0xfa) { - /* "cli", or Clear Interrupt Enable instruction. Skip it. */ - insnlen = 1; - goto skip_insn; - } - - /* - * 0x66 is an "operand prefix". It means a 16, not 32 bit in/out. - */ - if (insn[insnlen] == 0x66) { - small_operand = 1; - /* The instruction is 1 byte so far, read the next byte. */ - insnlen = 1; - } - - /* If the lower bit isn't set, it's a single byte access */ - byte_access = !(insn[insnlen] & 1); - - /* - * Now we can ignore the lower bit and decode the 4 opcodes - * we need to emulate. - */ - switch (insn[insnlen] & 0xFE) { - case 0xE4: /* in ,%al */ - port = insn[insnlen+1]; - insnlen += 2; - in = 1; - break; - case 0xEC: /* in (%dx),%al */ - port = getreg(edx) & 0xFFFF; - insnlen += 1; - in = 1; - break; - case 0xE6: /* out %al, */ - port = insn[insnlen+1]; - insnlen += 2; - break; - case 0xEE: /* out %al,(%dx) */ - port = getreg(edx) & 0xFFFF; - insnlen += 1; - break; - default: - /* OK, we don't know what this is, can't emulate. */ - goto no_emulate; - } - - /* Set a mask of the 1, 2 or 4 bytes, depending on size of IO */ - if (byte_access) - mask = 0xFF; - else if (small_operand) - mask = 0xFFFF; - else - mask = 0xFFFFFFFF; - - /* - * If it was an "IN" instruction, they expect the result to be read - * into %eax, so we change %eax. - */ - eax = getreg(eax); - - if (in) { - /* This is the PS/2 keyboard status; 1 means ready for output */ - if (port == 0x64) - val = 1; - else if (is_pci_addr_port(port)) - pci_addr_ioread(port, mask, &val); - else if (is_pci_data_port(port)) - pci_data_ioread(port, mask, &val); - - /* Clear the bits we're about to read */ - eax &= ~mask; - /* Copy bits in from val. */ - eax |= val & mask; - /* Now update the register. */ - setreg(eax, eax); - } else { - if (is_pci_addr_port(port)) { - if (!pci_addr_iowrite(port, mask, eax)) - goto bad_io; - } else if (is_pci_data_port(port)) { - if (!pci_data_iowrite(port, mask, eax)) - goto bad_io; - } - /* There are many other ports, eg. CMOS clock, serial - * and parallel ports, so we ignore them all. */ - } - - verbose("IO %s of %x to %u: %#08x\n", - in ? "IN" : "OUT", mask, port, eax); -skip_insn: - /* Finally, we've "done" the instruction, so move past it. */ - setreg(eip, getreg(eip) + insnlen); - return; - -bad_io: - warnx("Attempt to %s port %u (%#x mask)", - in ? "read from" : "write to", port, mask); - -no_emulate: - /* Inject trap into Guest. */ - if (write(lguest_fd, args, sizeof(args)) < 0) - err(1, "Reinjecting trap 13 for fault at %#x", getreg(eip)); -} - -static struct device *find_mmio_region(unsigned long paddr, u32 *off) -{ - unsigned int i; - - for (i = 1; i < MAX_PCI_DEVICES; i++) { - struct device *d = devices.pci[i]; - - if (!d) - continue; - if (paddr < d->mmio_addr) - continue; - if (paddr >= d->mmio_addr + d->mmio_size) - continue; - *off = paddr - d->mmio_addr; - return d; - } - return NULL; -} - -/* FIXME: Use vq array. */ -static struct virtqueue *vq_by_num(struct device *d, u32 num) -{ - struct virtqueue *vq = d->vq; - - while (num-- && vq) - vq = vq->next; - - return vq; -} - -static void save_vq_config(const struct virtio_pci_common_cfg *cfg, - struct virtqueue *vq) -{ - vq->pci_config = *cfg; -} - -static void restore_vq_config(struct virtio_pci_common_cfg *cfg, - struct virtqueue *vq) -{ - /* Only restore the per-vq part */ - size_t off = offsetof(struct virtio_pci_common_cfg, queue_size); - - memcpy((void *)cfg + off, (void *)&vq->pci_config + off, - sizeof(*cfg) - off); -} - -/* - * 4.1.4.3.2: - * - * The driver MUST configure the other virtqueue fields before - * enabling the virtqueue with queue_enable. - * - * When they enable the virtqueue, we check that their setup is valid. - */ -static void check_virtqueue(struct device *d, struct virtqueue *vq) -{ - /* Because lguest is 32 bit, all the descriptor high bits must be 0 */ - if (vq->pci_config.queue_desc_hi - || vq->pci_config.queue_avail_hi - || vq->pci_config.queue_used_hi) - bad_driver_vq(vq, "invalid 64-bit queue address"); - - /* - * 2.4.1: - * - * The driver MUST ensure that the physical address of the first byte - * of each virtqueue part is a multiple of the specified alignment - * value in the above table. - */ - if (vq->pci_config.queue_desc_lo % 16 - || vq->pci_config.queue_avail_lo % 2 - || vq->pci_config.queue_used_lo % 4) - bad_driver_vq(vq, "invalid alignment in queue addresses"); - - /* Initialize the virtqueue and check they're all in range. */ - vq->vring.num = vq->pci_config.queue_size; - vq->vring.desc = check_pointer(vq->dev, - vq->pci_config.queue_desc_lo, - sizeof(*vq->vring.desc) * vq->vring.num); - vq->vring.avail = check_pointer(vq->dev, - vq->pci_config.queue_avail_lo, - sizeof(*vq->vring.avail) - + (sizeof(vq->vring.avail->ring[0]) - * vq->vring.num)); - vq->vring.used = check_pointer(vq->dev, - vq->pci_config.queue_used_lo, - sizeof(*vq->vring.used) - + (sizeof(vq->vring.used->ring[0]) - * vq->vring.num)); - - /* - * 2.4.9.1: - * - * The driver MUST initialize flags in the used ring to 0 - * when allocating the used ring. - */ - if (vq->vring.used->flags != 0) - bad_driver_vq(vq, "invalid initial used.flags %#x", - vq->vring.used->flags); -} - -static void start_virtqueue(struct virtqueue *vq) -{ - /* - * Create stack for thread. Since the stack grows upwards, we point - * the stack pointer to the end of this region. - */ - char *stack = malloc(32768); - - /* Create a zero-initialized eventfd. */ - vq->eventfd = eventfd(0, 0); - if (vq->eventfd < 0) - err(1, "Creating eventfd"); - - /* - * CLONE_VM: because it has to access the Guest memory, and SIGCHLD so - * we get a signal if it dies. - */ - vq->thread = clone(do_thread, stack + 32768, CLONE_VM | SIGCHLD, vq); - if (vq->thread == (pid_t)-1) - err(1, "Creating clone"); -} - -static void start_virtqueues(struct device *d) -{ - struct virtqueue *vq; - - for (vq = d->vq; vq; vq = vq->next) { - if (vq->pci_config.queue_enable) - start_virtqueue(vq); - } -} - -static void emulate_mmio_write(struct device *d, u32 off, u32 val, u32 mask) -{ - struct virtqueue *vq; - - switch (off) { - case offsetof(struct virtio_pci_mmio, cfg.device_feature_select): - /* - * 4.1.4.3.1: - * - * The device MUST present the feature bits it is offering in - * device_feature, starting at bit device_feature_select ∗ 32 - * for any device_feature_select written by the driver - */ - if (val == 0) - d->mmio->cfg.device_feature = d->features; - else if (val == 1) - d->mmio->cfg.device_feature = (d->features >> 32); - else - d->mmio->cfg.device_feature = 0; - goto feature_write_through32; - case offsetof(struct virtio_pci_mmio, cfg.guest_feature_select): - if (val > 1) - bad_driver(d, "Unexpected driver select %u", val); - goto feature_write_through32; - case offsetof(struct virtio_pci_mmio, cfg.guest_feature): - if (d->mmio->cfg.guest_feature_select == 0) { - d->features_accepted &= ~((u64)0xFFFFFFFF); - d->features_accepted |= val; - } else { - assert(d->mmio->cfg.guest_feature_select == 1); - d->features_accepted &= 0xFFFFFFFF; - d->features_accepted |= ((u64)val) << 32; - } - /* - * 2.2.1: - * - * The driver MUST NOT accept a feature which the device did - * not offer - */ - if (d->features_accepted & ~d->features) - bad_driver(d, "over-accepted features %#llx of %#llx", - d->features_accepted, d->features); - goto feature_write_through32; - case offsetof(struct virtio_pci_mmio, cfg.device_status): { - u8 prev; - - verbose("%s: device status -> %#x\n", d->name, val); - /* - * 4.1.4.3.1: - * - * The device MUST reset when 0 is written to device_status, - * and present a 0 in device_status once that is done. - */ - if (val == 0) { - reset_device(d); - goto write_through8; - } - - /* 2.1.1: The driver MUST NOT clear a device status bit. */ - if (d->mmio->cfg.device_status & ~val) - bad_driver(d, "unset of device status bit %#x -> %#x", - d->mmio->cfg.device_status, val); - - /* - * 2.1.2: - * - * The device MUST NOT consume buffers or notify the driver - * before DRIVER_OK. - */ - if (val & VIRTIO_CONFIG_S_DRIVER_OK - && !(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER_OK)) - start_virtqueues(d); - - /* - * 3.1.1: - * - * The driver MUST follow this sequence to initialize a device: - * - Reset the device. - * - Set the ACKNOWLEDGE status bit: the guest OS has - * notice the device. - * - Set the DRIVER status bit: the guest OS knows how - * to drive the device. - * - Read device feature bits, and write the subset - * of feature bits understood by the OS and driver - * to the device. During this step the driver MAY - * read (but MUST NOT write) the device-specific - * configuration fields to check that it can - * support the device before accepting it. - * - Set the FEATURES_OK status bit. The driver - * MUST not accept new feature bits after this - * step. - * - Re-read device status to ensure the FEATURES_OK - * bit is still set: otherwise, the device does - * not support our subset of features and the - * device is unusable. - * - Perform device-specific setup, including - * discovery of virtqueues for the device, - * optional per-bus setup, reading and possibly - * writing the device’s virtio configuration - * space, and population of virtqueues. - * - Set the DRIVER_OK status bit. At this point the - * device is “live”. - */ - prev = 0; - switch (val & ~d->mmio->cfg.device_status) { - case VIRTIO_CONFIG_S_DRIVER_OK: - prev |= VIRTIO_CONFIG_S_FEATURES_OK; /* fall thru */ - case VIRTIO_CONFIG_S_FEATURES_OK: - prev |= VIRTIO_CONFIG_S_DRIVER; /* fall thru */ - case VIRTIO_CONFIG_S_DRIVER: - prev |= VIRTIO_CONFIG_S_ACKNOWLEDGE; /* fall thru */ - case VIRTIO_CONFIG_S_ACKNOWLEDGE: - break; - default: - bad_driver(d, "unknown device status bit %#x -> %#x", - d->mmio->cfg.device_status, val); - } - if (d->mmio->cfg.device_status != prev) - bad_driver(d, "unexpected status transition %#x -> %#x", - d->mmio->cfg.device_status, val); - - /* If they just wrote FEATURES_OK, we make sure they read */ - switch (val & ~d->mmio->cfg.device_status) { - case VIRTIO_CONFIG_S_FEATURES_OK: - d->wrote_features_ok = true; - break; - case VIRTIO_CONFIG_S_DRIVER_OK: - if (d->wrote_features_ok) - bad_driver(d, "did not re-read FEATURES_OK"); - break; - } - goto write_through8; - } - case offsetof(struct virtio_pci_mmio, cfg.queue_select): - vq = vq_by_num(d, val); - /* - * 4.1.4.3.1: - * - * The device MUST present a 0 in queue_size if the virtqueue - * corresponding to the current queue_select is unavailable. - */ - if (!vq) { - d->mmio->cfg.queue_size = 0; - goto write_through16; - } - /* Save registers for old vq, if it was a valid vq */ - if (d->mmio->cfg.queue_size) - save_vq_config(&d->mmio->cfg, - vq_by_num(d, d->mmio->cfg.queue_select)); - /* Restore the registers for the queue they asked for */ - restore_vq_config(&d->mmio->cfg, vq); - goto write_through16; - case offsetof(struct virtio_pci_mmio, cfg.queue_size): - /* - * 4.1.4.3.2: - * - * The driver MUST NOT write a value which is not a power of 2 - * to queue_size. - */ - if (val & (val-1)) - bad_driver(d, "invalid queue size %u", val); - if (d->mmio->cfg.queue_enable) - bad_driver(d, "changing queue size on live device"); - goto write_through16; - case offsetof(struct virtio_pci_mmio, cfg.queue_msix_vector): - bad_driver(d, "attempt to set MSIX vector to %u", val); - case offsetof(struct virtio_pci_mmio, cfg.queue_enable): { - struct virtqueue *vq = vq_by_num(d, d->mmio->cfg.queue_select); - - /* - * 4.1.4.3.2: - * - * The driver MUST NOT write a 0 to queue_enable. - */ - if (val != 1) - bad_driver(d, "setting queue_enable to %u", val); - - /* - * 3.1.1: - * - * 7. Perform device-specific setup, including discovery of - * virtqueues for the device, optional per-bus setup, - * reading and possibly writing the device’s virtio - * configuration space, and population of virtqueues. - * 8. Set the DRIVER_OK status bit. - * - * All our devices require all virtqueues to be enabled, so - * they should have done that before setting DRIVER_OK. - */ - if (d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER_OK) - bad_driver(d, "enabling vq after DRIVER_OK"); - - d->mmio->cfg.queue_enable = val; - save_vq_config(&d->mmio->cfg, vq); - check_virtqueue(d, vq); - goto write_through16; - } - case offsetof(struct virtio_pci_mmio, cfg.queue_notify_off): - bad_driver(d, "attempt to write to queue_notify_off"); - case offsetof(struct virtio_pci_mmio, cfg.queue_desc_lo): - case offsetof(struct virtio_pci_mmio, cfg.queue_desc_hi): - case offsetof(struct virtio_pci_mmio, cfg.queue_avail_lo): - case offsetof(struct virtio_pci_mmio, cfg.queue_avail_hi): - case offsetof(struct virtio_pci_mmio, cfg.queue_used_lo): - case offsetof(struct virtio_pci_mmio, cfg.queue_used_hi): - /* - * 4.1.4.3.2: - * - * The driver MUST configure the other virtqueue fields before - * enabling the virtqueue with queue_enable. - */ - if (d->mmio->cfg.queue_enable) - bad_driver(d, "changing queue on live device"); - - /* - * 3.1.1: - * - * The driver MUST follow this sequence to initialize a device: - *... - * 5. Set the FEATURES_OK status bit. The driver MUST not - * accept new feature bits after this step. - */ - if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_FEATURES_OK)) - bad_driver(d, "setting up vq before FEATURES_OK"); - - /* - * 6. Re-read device status to ensure the FEATURES_OK bit is - * still set... - */ - if (d->wrote_features_ok) - bad_driver(d, "didn't re-read FEATURES_OK before setup"); - - goto write_through32; - case offsetof(struct virtio_pci_mmio, notify): - vq = vq_by_num(d, val); - if (!vq) - bad_driver(d, "Invalid vq notification on %u", val); - /* Notify the process handling this vq by adding 1 to eventfd */ - write(vq->eventfd, "\1\0\0\0\0\0\0\0", 8); - goto write_through16; - case offsetof(struct virtio_pci_mmio, isr): - bad_driver(d, "Unexpected write to isr"); - /* Weird corner case: write to emerg_wr of console */ - case sizeof(struct virtio_pci_mmio) - + offsetof(struct virtio_console_config, emerg_wr): - if (strcmp(d->name, "console") == 0) { - char c = val; - write(STDOUT_FILENO, &c, 1); - goto write_through32; - } - /* Fall through... */ - default: - /* - * 4.1.4.3.2: - * - * The driver MUST NOT write to device_feature, num_queues, - * config_generation or queue_notify_off. - */ - bad_driver(d, "Unexpected write to offset %u", off); - } - -feature_write_through32: - /* - * 3.1.1: - * - * The driver MUST follow this sequence to initialize a device: - *... - * - Set the DRIVER status bit: the guest OS knows how - * to drive the device. - * - Read device feature bits, and write the subset - * of feature bits understood by the OS and driver - * to the device. - *... - * - Set the FEATURES_OK status bit. The driver MUST not - * accept new feature bits after this step. - */ - if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER)) - bad_driver(d, "feature write before VIRTIO_CONFIG_S_DRIVER"); - if (d->mmio->cfg.device_status & VIRTIO_CONFIG_S_FEATURES_OK) - bad_driver(d, "feature write after VIRTIO_CONFIG_S_FEATURES_OK"); - - /* - * 4.1.3.1: - * - * The driver MUST access each field using the “natural” access - * method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses for - * 16-bit fields and 8-bit accesses for 8-bit fields. - */ -write_through32: - if (mask != 0xFFFFFFFF) { - bad_driver(d, "non-32-bit write to offset %u (%#x)", - off, getreg(eip)); - return; - } - memcpy((char *)d->mmio + off, &val, 4); - return; - -write_through16: - if (mask != 0xFFFF) - bad_driver(d, "non-16-bit write to offset %u (%#x)", - off, getreg(eip)); - memcpy((char *)d->mmio + off, &val, 2); - return; - -write_through8: - if (mask != 0xFF) - bad_driver(d, "non-8-bit write to offset %u (%#x)", - off, getreg(eip)); - memcpy((char *)d->mmio + off, &val, 1); - return; -} - -static u32 emulate_mmio_read(struct device *d, u32 off, u32 mask) -{ - u8 isr; - u32 val = 0; - - switch (off) { - case offsetof(struct virtio_pci_mmio, cfg.device_feature_select): - case offsetof(struct virtio_pci_mmio, cfg.device_feature): - case offsetof(struct virtio_pci_mmio, cfg.guest_feature_select): - case offsetof(struct virtio_pci_mmio, cfg.guest_feature): - /* - * 3.1.1: - * - * The driver MUST follow this sequence to initialize a device: - *... - * - Set the DRIVER status bit: the guest OS knows how - * to drive the device. - * - Read device feature bits, and write the subset - * of feature bits understood by the OS and driver - * to the device. - */ - if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER)) - bad_driver(d, - "feature read before VIRTIO_CONFIG_S_DRIVER"); - goto read_through32; - case offsetof(struct virtio_pci_mmio, cfg.msix_config): - bad_driver(d, "read of msix_config"); - case offsetof(struct virtio_pci_mmio, cfg.num_queues): - goto read_through16; - case offsetof(struct virtio_pci_mmio, cfg.device_status): - /* As they did read, any write of FEATURES_OK is now fine. */ - d->wrote_features_ok = false; - goto read_through8; - case offsetof(struct virtio_pci_mmio, cfg.config_generation): - /* - * 4.1.4.3.1: - * - * The device MUST present a changed config_generation after - * the driver has read a device-specific configuration value - * which has changed since any part of the device-specific - * configuration was last read. - * - * This is simple: none of our devices change config, so this - * is always 0. - */ - goto read_through8; - case offsetof(struct virtio_pci_mmio, notify): - /* - * 3.1.1: - * - * The driver MUST NOT notify the device before setting - * DRIVER_OK. - */ - if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER_OK)) - bad_driver(d, "notify before VIRTIO_CONFIG_S_DRIVER_OK"); - goto read_through16; - case offsetof(struct virtio_pci_mmio, isr): - if (mask != 0xFF) - bad_driver(d, "non-8-bit read from offset %u (%#x)", - off, getreg(eip)); - isr = d->mmio->isr; - /* - * 4.1.4.5.1: - * - * The device MUST reset ISR status to 0 on driver read. - */ - d->mmio->isr = 0; - return isr; - case offsetof(struct virtio_pci_mmio, padding): - bad_driver(d, "read from padding (%#x)", getreg(eip)); - default: - /* Read from device config space, beware unaligned overflow */ - if (off > d->mmio_size - 4) - bad_driver(d, "read past end (%#x)", getreg(eip)); - - /* - * 3.1.1: - * The driver MUST follow this sequence to initialize a device: - *... - * 3. Set the DRIVER status bit: the guest OS knows how to - * drive the device. - * 4. Read device feature bits, and write the subset of - * feature bits understood by the OS and driver to the - * device. During this step the driver MAY read (but MUST NOT - * write) the device-specific configuration fields to check - * that it can support the device before accepting it. - */ - if (!(d->mmio->cfg.device_status & VIRTIO_CONFIG_S_DRIVER)) - bad_driver(d, - "config read before VIRTIO_CONFIG_S_DRIVER"); - - if (mask == 0xFFFFFFFF) - goto read_through32; - else if (mask == 0xFFFF) - goto read_through16; - else - goto read_through8; - } - - /* - * 4.1.3.1: - * - * The driver MUST access each field using the “natural” access - * method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses for - * 16-bit fields and 8-bit accesses for 8-bit fields. - */ -read_through32: - if (mask != 0xFFFFFFFF) - bad_driver(d, "non-32-bit read to offset %u (%#x)", - off, getreg(eip)); - memcpy(&val, (char *)d->mmio + off, 4); - return val; - -read_through16: - if (mask != 0xFFFF) - bad_driver(d, "non-16-bit read to offset %u (%#x)", - off, getreg(eip)); - memcpy(&val, (char *)d->mmio + off, 2); - return val; - -read_through8: - if (mask != 0xFF) - bad_driver(d, "non-8-bit read to offset %u (%#x)", - off, getreg(eip)); - memcpy(&val, (char *)d->mmio + off, 1); - return val; -} - -static void emulate_mmio(unsigned long paddr, const u8 *insn) -{ - u32 val, off, mask = 0xFFFFFFFF, insnlen = 0; - struct device *d = find_mmio_region(paddr, &off); - unsigned long args[] = { LHREQ_TRAP, 14 }; - - if (!d) { - warnx("MMIO touching %#08lx (not a device)", paddr); - goto reinject; - } - - /* Prefix makes it a 16 bit op */ - if (insn[0] == 0x66) { - mask = 0xFFFF; - insnlen++; - } - - /* iowrite */ - if (insn[insnlen] == 0x89) { - /* Next byte is r/m byte: bits 3-5 are register. */ - val = getreg_num((insn[insnlen+1] >> 3) & 0x7, mask); - emulate_mmio_write(d, off, val, mask); - insnlen += 2 + insn_displacement_len(insn[insnlen+1]); - } else if (insn[insnlen] == 0x8b) { /* ioread */ - /* Next byte is r/m byte: bits 3-5 are register. */ - val = emulate_mmio_read(d, off, mask); - setreg_num((insn[insnlen+1] >> 3) & 0x7, val, mask); - insnlen += 2 + insn_displacement_len(insn[insnlen+1]); - } else if (insn[0] == 0x88) { /* 8-bit iowrite */ - mask = 0xff; - /* Next byte is r/m byte: bits 3-5 are register. */ - val = getreg_num((insn[1] >> 3) & 0x7, mask); - emulate_mmio_write(d, off, val, mask); - insnlen = 2 + insn_displacement_len(insn[1]); - } else if (insn[0] == 0x8a) { /* 8-bit ioread */ - mask = 0xff; - val = emulate_mmio_read(d, off, mask); - setreg_num((insn[1] >> 3) & 0x7, val, mask); - insnlen = 2 + insn_displacement_len(insn[1]); - } else { - warnx("Unknown MMIO instruction touching %#08lx:" - " %02x %02x %02x %02x at %u", - paddr, insn[0], insn[1], insn[2], insn[3], getreg(eip)); - reinject: - /* Inject trap into Guest. */ - if (write(lguest_fd, args, sizeof(args)) < 0) - err(1, "Reinjecting trap 14 for fault at %#x", - getreg(eip)); - return; - } - - /* Finally, we've "done" the instruction, so move past it. */ - setreg(eip, getreg(eip) + insnlen); -} - -/*L:190 - * Device Setup - * - * All devices need a descriptor so the Guest knows it exists, and a "struct - * device" so the Launcher can keep track of it. We have common helper - * routines to allocate and manage them. - */ -static void add_pci_virtqueue(struct device *dev, - void (*service)(struct virtqueue *), - const char *name) -{ - struct virtqueue **i, *vq = malloc(sizeof(*vq)); - - /* Initialize the virtqueue */ - vq->next = NULL; - vq->last_avail_idx = 0; - vq->dev = dev; - vq->name = name; - - /* - * This is the routine the service thread will run, and its Process ID - * once it's running. - */ - vq->service = service; - vq->thread = (pid_t)-1; - - /* Initialize the configuration. */ - reset_vq_pci_config(vq); - vq->pci_config.queue_notify_off = 0; - - /* Add one to the number of queues */ - vq->dev->mmio->cfg.num_queues++; - - /* - * Add to tail of list, so dev->vq is first vq, dev->vq->next is - * second. - */ - for (i = &dev->vq; *i; i = &(*i)->next); - *i = vq; -} - -/* The Guest accesses the feature bits via the PCI common config MMIO region */ -static void add_pci_feature(struct device *dev, unsigned bit) -{ - dev->features |= (1ULL << bit); -} - -/* For devices with no config. */ -static void no_device_config(struct device *dev) -{ - dev->mmio_addr = get_mmio_region(dev->mmio_size); - - dev->config.bar[0] = dev->mmio_addr; - /* Bottom 4 bits must be zero */ - assert(~(dev->config.bar[0] & 0xF)); -} - -/* This puts the device config into BAR0 */ -static void set_device_config(struct device *dev, const void *conf, size_t len) -{ - /* Set up BAR 0 */ - dev->mmio_size += len; - dev->mmio = realloc(dev->mmio, dev->mmio_size); - memcpy(dev->mmio + 1, conf, len); - - /* - * 4.1.4.6: - * - * The device MUST present at least one VIRTIO_PCI_CAP_DEVICE_CFG - * capability for any device type which has a device-specific - * configuration. - */ - /* Hook up device cfg */ - dev->config.cfg_access.cap.cap_next - = offsetof(struct pci_config, device); - - /* - * 4.1.4.6.1: - * - * The offset for the device-specific configuration MUST be 4-byte - * aligned. - */ - assert(dev->config.cfg_access.cap.cap_next % 4 == 0); - - /* Fix up device cfg field length. */ - dev->config.device.length = len; - - /* The rest is the same as the no-config case */ - no_device_config(dev); -} - -static void init_cap(struct virtio_pci_cap *cap, size_t caplen, int type, - size_t bar_offset, size_t bar_bytes, u8 next) -{ - cap->cap_vndr = PCI_CAP_ID_VNDR; - cap->cap_next = next; - cap->cap_len = caplen; - cap->cfg_type = type; - cap->bar = 0; - memset(cap->padding, 0, sizeof(cap->padding)); - cap->offset = bar_offset; - cap->length = bar_bytes; -} - -/* - * This sets up the pci_config structure, as defined in the virtio 1.0 - * standard (and PCI standard). - */ -static void init_pci_config(struct pci_config *pci, u16 type, - u8 class, u8 subclass) -{ - size_t bar_offset, bar_len; - - /* - * 4.1.4.4.1: - * - * The device MUST either present notify_off_multiplier as an even - * power of 2, or present notify_off_multiplier as 0. - * - * 2.1.2: - * - * The device MUST initialize device status to 0 upon reset. - */ - memset(pci, 0, sizeof(*pci)); - - /* 4.1.2.1: Devices MUST have the PCI Vendor ID 0x1AF4 */ - pci->vendor_id = 0x1AF4; - /* 4.1.2.1: ... PCI Device ID calculated by adding 0x1040 ... */ - pci->device_id = 0x1040 + type; - - /* - * PCI have specific codes for different types of devices. - * Linux doesn't care, but it's a good clue for people looking - * at the device. - */ - pci->class = class; - pci->subclass = subclass; - - /* - * 4.1.2.1: - * - * Non-transitional devices SHOULD have a PCI Revision ID of 1 or - * higher - */ - pci->revid = 1; - - /* - * 4.1.2.1: - * - * Non-transitional devices SHOULD have a PCI Subsystem Device ID of - * 0x40 or higher. - */ - pci->subsystem_device_id = 0x40; - - /* We use our dummy interrupt controller, and irq_line is the irq */ - pci->irq_line = devices.next_irq++; - pci->irq_pin = 0; - - /* Support for extended capabilities. */ - pci->status = (1 << 4); - - /* Link them in. */ - /* - * 4.1.4.3.1: - * - * The device MUST present at least one common configuration - * capability. - */ - pci->capabilities = offsetof(struct pci_config, common); - - /* 4.1.4.3.1 ... offset MUST be 4-byte aligned. */ - assert(pci->capabilities % 4 == 0); - - bar_offset = offsetof(struct virtio_pci_mmio, cfg); - bar_len = sizeof(((struct virtio_pci_mmio *)0)->cfg); - init_cap(&pci->common, sizeof(pci->common), VIRTIO_PCI_CAP_COMMON_CFG, - bar_offset, bar_len, - offsetof(struct pci_config, notify)); - - /* - * 4.1.4.4.1: - * - * The device MUST present at least one notification capability. - */ - bar_offset += bar_len; - bar_len = sizeof(((struct virtio_pci_mmio *)0)->notify); - - /* - * 4.1.4.4.1: - * - * The cap.offset MUST be 2-byte aligned. - */ - assert(pci->common.cap_next % 2 == 0); - - /* FIXME: Use a non-zero notify_off, for per-queue notification? */ - /* - * 4.1.4.4.1: - * - * The value cap.length presented by the device MUST be at least 2 and - * MUST be large enough to support queue notification offsets for all - * supported queues in all possible configurations. - */ - assert(bar_len >= 2); - - init_cap(&pci->notify.cap, sizeof(pci->notify), - VIRTIO_PCI_CAP_NOTIFY_CFG, - bar_offset, bar_len, - offsetof(struct pci_config, isr)); - - bar_offset += bar_len; - bar_len = sizeof(((struct virtio_pci_mmio *)0)->isr); - /* - * 4.1.4.5.1: - * - * The device MUST present at least one VIRTIO_PCI_CAP_ISR_CFG - * capability. - */ - init_cap(&pci->isr, sizeof(pci->isr), - VIRTIO_PCI_CAP_ISR_CFG, - bar_offset, bar_len, - offsetof(struct pci_config, cfg_access)); - - /* - * 4.1.4.7.1: - * - * The device MUST present at least one VIRTIO_PCI_CAP_PCI_CFG - * capability. - */ - /* This doesn't have any presence in the BAR */ - init_cap(&pci->cfg_access.cap, sizeof(pci->cfg_access), - VIRTIO_PCI_CAP_PCI_CFG, - 0, 0, 0); - - bar_offset += bar_len + sizeof(((struct virtio_pci_mmio *)0)->padding); - assert(bar_offset == sizeof(struct virtio_pci_mmio)); - - /* - * This gets sewn in and length set in set_device_config(). - * Some devices don't have a device configuration interface, so - * we never expose this if we don't call set_device_config(). - */ - init_cap(&pci->device, sizeof(pci->device), VIRTIO_PCI_CAP_DEVICE_CFG, - bar_offset, 0, 0); -} - -/* - * This routine does all the creation and setup of a new device, but we don't - * actually place the MMIO region until we know the size (if any) of the - * device-specific config. And we don't actually start the service threads - * until later. - * - * See what I mean about userspace being boring? - */ -static struct device *new_pci_device(const char *name, u16 type, - u8 class, u8 subclass) -{ - struct device *dev = malloc(sizeof(*dev)); - - /* Now we populate the fields one at a time. */ - dev->name = name; - dev->vq = NULL; - dev->running = false; - dev->wrote_features_ok = false; - dev->mmio_size = sizeof(struct virtio_pci_mmio); - dev->mmio = calloc(1, dev->mmio_size); - dev->features = (u64)1 << VIRTIO_F_VERSION_1; - dev->features_accepted = 0; - - if (devices.device_num + 1 >= MAX_PCI_DEVICES) - errx(1, "Can only handle 31 PCI devices"); - - init_pci_config(&dev->config, type, class, subclass); - assert(!devices.pci[devices.device_num+1]); - devices.pci[++devices.device_num] = dev; - - return dev; -} - -/* - * Our first setup routine is the console. It's a fairly simple device, but - * UNIX tty handling makes it uglier than it could be. - */ -static void setup_console(void) -{ - struct device *dev; - struct virtio_console_config conf; - - /* If we can save the initial standard input settings... */ - if (tcgetattr(STDIN_FILENO, &orig_term) == 0) { - struct termios term = orig_term; - /* - * Then we turn off echo, line buffering and ^C etc: We want a - * raw input stream to the Guest. - */ - term.c_lflag &= ~(ISIG|ICANON|ECHO); - tcsetattr(STDIN_FILENO, TCSANOW, &term); - } - - dev = new_pci_device("console", VIRTIO_ID_CONSOLE, 0x07, 0x00); - - /* We store the console state in dev->priv, and initialize it. */ - dev->priv = malloc(sizeof(struct console_abort)); - ((struct console_abort *)dev->priv)->count = 0; - - /* - * The console needs two virtqueues: the input then the output. When - * they put something the input queue, we make sure we're listening to - * stdin. When they put something in the output queue, we write it to - * stdout. - */ - add_pci_virtqueue(dev, console_input, "input"); - add_pci_virtqueue(dev, console_output, "output"); - - /* We need a configuration area for the emerg_wr early writes. */ - add_pci_feature(dev, VIRTIO_CONSOLE_F_EMERG_WRITE); - set_device_config(dev, &conf, sizeof(conf)); - - verbose("device %u: console\n", devices.device_num); -} -/*:*/ - -/*M:010 - * Inter-guest networking is an interesting area. Simplest is to have a - * --sharenet= option which opens or creates a named pipe. This can be - * used to send packets to another guest in a 1:1 manner. - * - * More sophisticated is to use one of the tools developed for project like UML - * to do networking. - * - * Faster is to do virtio bonding in kernel. Doing this 1:1 would be - * completely generic ("here's my vring, attach to your vring") and would work - * for any traffic. Of course, namespace and permissions issues need to be - * dealt with. A more sophisticated "multi-channel" virtio_net.c could hide - * multiple inter-guest channels behind one interface, although it would - * require some manner of hotplugging new virtio channels. - * - * Finally, we could use a virtio network switch in the kernel, ie. vhost. -:*/ - -static u32 str2ip(const char *ipaddr) -{ - unsigned int b[4]; - - if (sscanf(ipaddr, "%u.%u.%u.%u", &b[0], &b[1], &b[2], &b[3]) != 4) - errx(1, "Failed to parse IP address '%s'", ipaddr); - return (b[0] << 24) | (b[1] << 16) | (b[2] << 8) | b[3]; -} - -static void str2mac(const char *macaddr, unsigned char mac[6]) -{ - unsigned int m[6]; - if (sscanf(macaddr, "%02x:%02x:%02x:%02x:%02x:%02x", - &m[0], &m[1], &m[2], &m[3], &m[4], &m[5]) != 6) - errx(1, "Failed to parse mac address '%s'", macaddr); - mac[0] = m[0]; - mac[1] = m[1]; - mac[2] = m[2]; - mac[3] = m[3]; - mac[4] = m[4]; - mac[5] = m[5]; -} - -/* - * This code is "adapted" from libbridge: it attaches the Host end of the - * network device to the bridge device specified by the command line. - * - * This is yet another James Morris contribution (I'm an IP-level guy, so I - * dislike bridging), and I just try not to break it. - */ -static void add_to_bridge(int fd, const char *if_name, const char *br_name) -{ - int ifidx; - struct ifreq ifr; - - if (!*br_name) - errx(1, "must specify bridge name"); - - ifidx = if_nametoindex(if_name); - if (!ifidx) - errx(1, "interface %s does not exist!", if_name); - - strncpy(ifr.ifr_name, br_name, IFNAMSIZ); - ifr.ifr_name[IFNAMSIZ-1] = '\0'; - ifr.ifr_ifindex = ifidx; - if (ioctl(fd, SIOCBRADDIF, &ifr) < 0) - err(1, "can't add %s to bridge %s", if_name, br_name); -} - -/* - * This sets up the Host end of the network device with an IP address, brings - * it up so packets will flow, the copies the MAC address into the hwaddr - * pointer. - */ -static void configure_device(int fd, const char *tapif, u32 ipaddr) -{ - struct ifreq ifr; - struct sockaddr_in sin; - - memset(&ifr, 0, sizeof(ifr)); - strcpy(ifr.ifr_name, tapif); - - /* Don't read these incantations. Just cut & paste them like I did! */ - sin.sin_family = AF_INET; - sin.sin_addr.s_addr = htonl(ipaddr); - memcpy(&ifr.ifr_addr, &sin, sizeof(sin)); - if (ioctl(fd, SIOCSIFADDR, &ifr) != 0) - err(1, "Setting %s interface address", tapif); - ifr.ifr_flags = IFF_UP; - if (ioctl(fd, SIOCSIFFLAGS, &ifr) != 0) - err(1, "Bringing interface %s up", tapif); -} - -static int get_tun_device(char tapif[IFNAMSIZ]) -{ - struct ifreq ifr; - int vnet_hdr_sz; - int netfd; - - /* Start with this zeroed. Messy but sure. */ - memset(&ifr, 0, sizeof(ifr)); - - /* - * We open the /dev/net/tun device and tell it we want a tap device. A - * tap device is like a tun device, only somehow different. To tell - * the truth, I completely blundered my way through this code, but it - * works now! - */ - netfd = open_or_die("/dev/net/tun", O_RDWR); - ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR; - strcpy(ifr.ifr_name, "tap%d"); - if (ioctl(netfd, TUNSETIFF, &ifr) != 0) - err(1, "configuring /dev/net/tun"); - - if (ioctl(netfd, TUNSETOFFLOAD, - TUN_F_CSUM|TUN_F_TSO4|TUN_F_TSO6|TUN_F_TSO_ECN) != 0) - err(1, "Could not set features for tun device"); - - /* - * We don't need checksums calculated for packets coming in this - * device: trust us! - */ - ioctl(netfd, TUNSETNOCSUM, 1); - - /* - * In virtio before 1.0 (aka legacy virtio), we added a 16-bit - * field at the end of the network header iff - * VIRTIO_NET_F_MRG_RXBUF was negotiated. For virtio 1.0, - * that became the norm, but we need to tell the tun device - * about our expanded header (which is called - * virtio_net_hdr_mrg_rxbuf in the legacy system). - */ - vnet_hdr_sz = sizeof(struct virtio_net_hdr_v1); - if (ioctl(netfd, TUNSETVNETHDRSZ, &vnet_hdr_sz) != 0) - err(1, "Setting tun header size to %u", vnet_hdr_sz); - - memcpy(tapif, ifr.ifr_name, IFNAMSIZ); - return netfd; -} - -/*L:195 - * Our network is a Host<->Guest network. This can either use bridging or - * routing, but the principle is the same: it uses the "tun" device to inject - * packets into the Host as if they came in from a normal network card. We - * just shunt packets between the Guest and the tun device. - */ -static void setup_tun_net(char *arg) -{ - struct device *dev; - struct net_info *net_info = malloc(sizeof(*net_info)); - int ipfd; - u32 ip = INADDR_ANY; - bool bridging = false; - char tapif[IFNAMSIZ], *p; - struct virtio_net_config conf; - - net_info->tunfd = get_tun_device(tapif); - - /* First we create a new network device. */ - dev = new_pci_device("net", VIRTIO_ID_NET, 0x02, 0x00); - dev->priv = net_info; - - /* Network devices need a recv and a send queue, just like console. */ - add_pci_virtqueue(dev, net_input, "rx"); - add_pci_virtqueue(dev, net_output, "tx"); - - /* - * We need a socket to perform the magic network ioctls to bring up the - * tap interface, connect to the bridge etc. Any socket will do! - */ - ipfd = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP); - if (ipfd < 0) - err(1, "opening IP socket"); - - /* If the command line was --tunnet=bridge: do bridging. */ - if (!strncmp(BRIDGE_PFX, arg, strlen(BRIDGE_PFX))) { - arg += strlen(BRIDGE_PFX); - bridging = true; - } - - /* A mac address may follow the bridge name or IP address */ - p = strchr(arg, ':'); - if (p) { - str2mac(p+1, conf.mac); - add_pci_feature(dev, VIRTIO_NET_F_MAC); - *p = '\0'; - } - - /* arg is now either an IP address or a bridge name */ - if (bridging) - add_to_bridge(ipfd, tapif, arg); - else - ip = str2ip(arg); - - /* Set up the tun device. */ - configure_device(ipfd, tapif, ip); - - /* Expect Guest to handle everything except UFO */ - add_pci_feature(dev, VIRTIO_NET_F_CSUM); - add_pci_feature(dev, VIRTIO_NET_F_GUEST_CSUM); - add_pci_feature(dev, VIRTIO_NET_F_GUEST_TSO4); - add_pci_feature(dev, VIRTIO_NET_F_GUEST_TSO6); - add_pci_feature(dev, VIRTIO_NET_F_GUEST_ECN); - add_pci_feature(dev, VIRTIO_NET_F_HOST_TSO4); - add_pci_feature(dev, VIRTIO_NET_F_HOST_TSO6); - add_pci_feature(dev, VIRTIO_NET_F_HOST_ECN); - /* We handle indirect ring entries */ - add_pci_feature(dev, VIRTIO_RING_F_INDIRECT_DESC); - set_device_config(dev, &conf, sizeof(conf)); - - /* We don't need the socket any more; setup is done. */ - close(ipfd); - - if (bridging) - verbose("device %u: tun %s attached to bridge: %s\n", - devices.device_num, tapif, arg); - else - verbose("device %u: tun %s: %s\n", - devices.device_num, tapif, arg); -} -/*:*/ - -/* This hangs off device->priv. */ -struct vblk_info { - /* The size of the file. */ - off64_t len; - - /* The file descriptor for the file. */ - int fd; - -}; - -/*L:210 - * The Disk - * - * The disk only has one virtqueue, so it only has one thread. It is really - * simple: the Guest asks for a block number and we read or write that position - * in the file. - * - * Before we serviced each virtqueue in a separate thread, that was unacceptably - * slow: the Guest waits until the read is finished before running anything - * else, even if it could have been doing useful work. - * - * We could have used async I/O, except it's reputed to suck so hard that - * characters actually go missing from your code when you try to use it. - */ -static void blk_request(struct virtqueue *vq) -{ - struct vblk_info *vblk = vq->dev->priv; - unsigned int head, out_num, in_num, wlen; - int ret, i; - u8 *in; - struct virtio_blk_outhdr out; - struct iovec iov[vq->vring.num]; - off64_t off; - - /* - * Get the next request, where we normally wait. It triggers the - * interrupt to acknowledge previously serviced requests (if any). - */ - head = wait_for_vq_desc(vq, iov, &out_num, &in_num); - - /* Copy the output header from the front of the iov (adjusts iov) */ - iov_consume(vq->dev, iov, out_num, &out, sizeof(out)); - - /* Find and trim end of iov input array, for our status byte. */ - in = NULL; - for (i = out_num + in_num - 1; i >= out_num; i--) { - if (iov[i].iov_len > 0) { - in = iov[i].iov_base + iov[i].iov_len - 1; - iov[i].iov_len--; - break; - } - } - if (!in) - bad_driver_vq(vq, "Bad virtblk cmd with no room for status"); - - /* - * For historical reasons, block operations are expressed in 512 byte - * "sectors". - */ - off = out.sector * 512; - - if (out.type & VIRTIO_BLK_T_OUT) { - /* - * Write - * - * Move to the right location in the block file. This can fail - * if they try to write past end. - */ - if (lseek64(vblk->fd, off, SEEK_SET) != off) - err(1, "Bad seek to sector %llu", out.sector); - - ret = writev(vblk->fd, iov, out_num); - verbose("WRITE to sector %llu: %i\n", out.sector, ret); - - /* - * Grr... Now we know how long the descriptor they sent was, we - * make sure they didn't try to write over the end of the block - * file (possibly extending it). - */ - if (ret > 0 && off + ret > vblk->len) { - /* Trim it back to the correct length */ - ftruncate64(vblk->fd, vblk->len); - /* Die, bad Guest, die. */ - bad_driver_vq(vq, "Write past end %llu+%u", off, ret); - } - - wlen = sizeof(*in); - *in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR); - } else if (out.type & VIRTIO_BLK_T_FLUSH) { - /* Flush */ - ret = fdatasync(vblk->fd); - verbose("FLUSH fdatasync: %i\n", ret); - wlen = sizeof(*in); - *in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR); - } else { - /* - * Read - * - * Move to the right location in the block file. This can fail - * if they try to read past end. - */ - if (lseek64(vblk->fd, off, SEEK_SET) != off) - err(1, "Bad seek to sector %llu", out.sector); - - ret = readv(vblk->fd, iov + out_num, in_num); - if (ret >= 0) { - wlen = sizeof(*in) + ret; - *in = VIRTIO_BLK_S_OK; - } else { - wlen = sizeof(*in); - *in = VIRTIO_BLK_S_IOERR; - } - } - - /* Finished that request. */ - add_used(vq, head, wlen); -} - -/*L:198 This actually sets up a virtual block device. */ -static void setup_block_file(const char *filename) -{ - struct device *dev; - struct vblk_info *vblk; - struct virtio_blk_config conf; - - /* Create the device. */ - dev = new_pci_device("block", VIRTIO_ID_BLOCK, 0x01, 0x80); - - /* The device has one virtqueue, where the Guest places requests. */ - add_pci_virtqueue(dev, blk_request, "request"); - - /* Allocate the room for our own bookkeeping */ - vblk = dev->priv = malloc(sizeof(*vblk)); - - /* First we open the file and store the length. */ - vblk->fd = open_or_die(filename, O_RDWR|O_LARGEFILE); - vblk->len = lseek64(vblk->fd, 0, SEEK_END); - - /* Tell Guest how many sectors this device has. */ - conf.capacity = cpu_to_le64(vblk->len / 512); - - /* - * Tell Guest not to put in too many descriptors at once: two are used - * for the in and out elements. - */ - add_pci_feature(dev, VIRTIO_BLK_F_SEG_MAX); - conf.seg_max = cpu_to_le32(VIRTQUEUE_NUM - 2); - - set_device_config(dev, &conf, sizeof(struct virtio_blk_config)); - - verbose("device %u: virtblock %llu sectors\n", - devices.device_num, le64_to_cpu(conf.capacity)); -} - -/*L:211 - * Our random number generator device reads from /dev/urandom into the Guest's - * input buffers. The usual case is that the Guest doesn't want random numbers - * and so has no buffers although /dev/urandom is still readable, whereas - * console is the reverse. - * - * The same logic applies, however. - */ -struct rng_info { - int rfd; -}; - -static void rng_input(struct virtqueue *vq) -{ - int len; - unsigned int head, in_num, out_num, totlen = 0; - struct rng_info *rng_info = vq->dev->priv; - struct iovec iov[vq->vring.num]; - - /* First we need a buffer from the Guests's virtqueue. */ - head = wait_for_vq_desc(vq, iov, &out_num, &in_num); - if (out_num) - bad_driver_vq(vq, "Output buffers in rng?"); - - /* - * Just like the console write, we loop to cover the whole iovec. - * In this case, short reads actually happen quite a bit. - */ - while (!iov_empty(iov, in_num)) { - len = readv(rng_info->rfd, iov, in_num); - if (len <= 0) - err(1, "Read from /dev/urandom gave %i", len); - iov_consume(vq->dev, iov, in_num, NULL, len); - totlen += len; - } - - /* Tell the Guest about the new input. */ - add_used(vq, head, totlen); -} - -/*L:199 - * This creates a "hardware" random number device for the Guest. - */ -static void setup_rng(void) -{ - struct device *dev; - struct rng_info *rng_info = malloc(sizeof(*rng_info)); - - /* Our device's private info simply contains the /dev/urandom fd. */ - rng_info->rfd = open_or_die("/dev/urandom", O_RDONLY); - - /* Create the new device. */ - dev = new_pci_device("rng", VIRTIO_ID_RNG, 0xff, 0); - dev->priv = rng_info; - - /* The device has one virtqueue, where the Guest places inbufs. */ - add_pci_virtqueue(dev, rng_input, "input"); - - /* We don't have any configuration space */ - no_device_config(dev); - - verbose("device %u: rng\n", devices.device_num); -} -/* That's the end of device setup. */ - -/*L:230 Reboot is pretty easy: clean up and exec() the Launcher afresh. */ -static void __attribute__((noreturn)) restart_guest(void) -{ - unsigned int i; - - /* - * Since we don't track all open fds, we simply close everything beyond - * stderr. - */ - for (i = 3; i < FD_SETSIZE; i++) - close(i); - - /* Reset all the devices (kills all threads). */ - cleanup_devices(); - - execv(main_args[0], main_args); - err(1, "Could not exec %s", main_args[0]); -} - -/*L:220 - * Finally we reach the core of the Launcher which runs the Guest, serves - * its input and output, and finally, lays it to rest. - */ -static void __attribute__((noreturn)) run_guest(void) -{ - for (;;) { - struct lguest_pending notify; - int readval; - - /* We read from the /dev/lguest device to run the Guest. */ - readval = pread(lguest_fd, ¬ify, sizeof(notify), cpu_id); - if (readval == sizeof(notify)) { - if (notify.trap == 13) { - verbose("Emulating instruction at %#x\n", - getreg(eip)); - emulate_insn(notify.insn); - } else if (notify.trap == 14) { - verbose("Emulating MMIO at %#x\n", - getreg(eip)); - emulate_mmio(notify.addr, notify.insn); - } else - errx(1, "Unknown trap %i addr %#08x\n", - notify.trap, notify.addr); - /* ENOENT means the Guest died. Reading tells us why. */ - } else if (errno == ENOENT) { - char reason[1024] = { 0 }; - pread(lguest_fd, reason, sizeof(reason)-1, cpu_id); - errx(1, "%s", reason); - /* ERESTART means that we need to reboot the guest */ - } else if (errno == ERESTART) { - restart_guest(); - /* Anything else means a bug or incompatible change. */ - } else - err(1, "Running guest failed"); - } -} -/*L:240 - * This is the end of the Launcher. The good news: we are over halfway - * through! The bad news: the most fiendish part of the code still lies ahead - * of us. - * - * Are you ready? Take a deep breath and join me in the core of the Host, in - * "make Host". -:*/ - -static struct option opts[] = { - { "verbose", 0, NULL, 'v' }, - { "tunnet", 1, NULL, 't' }, - { "block", 1, NULL, 'b' }, - { "rng", 0, NULL, 'r' }, - { "initrd", 1, NULL, 'i' }, - { "username", 1, NULL, 'u' }, - { "chroot", 1, NULL, 'c' }, - { NULL }, -}; -static void usage(void) -{ - errx(1, "Usage: lguest [--verbose] " - "[--tunnet=(:|bridge::)\n" - "|--block=|--initrd=]...\n" - " vmlinux [args...]"); -} - -/*L:105 The main routine is where the real work begins: */ -int main(int argc, char *argv[]) -{ - /* Memory, code startpoint and size of the (optional) initrd. */ - unsigned long mem = 0, start, initrd_size = 0; - /* Two temporaries. */ - int i, c; - /* The boot information for the Guest. */ - struct boot_params *boot; - /* If they specify an initrd file to load. */ - const char *initrd_name = NULL; - - /* Password structure for initgroups/setres[gu]id */ - struct passwd *user_details = NULL; - - /* Directory to chroot to */ - char *chroot_path = NULL; - - /* Save the args: we "reboot" by execing ourselves again. */ - main_args = argv; - - /* - * First we initialize the device list. We remember next interrupt - * number to use for devices (1: remember that 0 is used by the timer). - */ - devices.next_irq = 1; - - /* We're CPU 0. In fact, that's the only CPU possible right now. */ - cpu_id = 0; - - /* - * We need to know how much memory so we can set up the device - * descriptor and memory pages for the devices as we parse the command - * line. So we quickly look through the arguments to find the amount - * of memory now. - */ - for (i = 1; i < argc; i++) { - if (argv[i][0] != '-') { - mem = atoi(argv[i]) * 1024 * 1024; - /* - * We start by mapping anonymous pages over all of - * guest-physical memory range. This fills it with 0, - * and ensures that the Guest won't be killed when it - * tries to access it. - */ - guest_base = map_zeroed_pages(mem / getpagesize() - + DEVICE_PAGES); - guest_limit = mem; - guest_max = guest_mmio = mem + DEVICE_PAGES*getpagesize(); - break; - } - } - - /* If we exit via err(), this kills all the threads, restores tty. */ - atexit(cleanup_devices); - - /* We always have a console device, and it's always device 1. */ - setup_console(); - - /* The options are fairly straight-forward */ - while ((c = getopt_long(argc, argv, "v", opts, NULL)) != EOF) { - switch (c) { - case 'v': - verbose = true; - break; - case 't': - setup_tun_net(optarg); - break; - case 'b': - setup_block_file(optarg); - break; - case 'r': - setup_rng(); - break; - case 'i': - initrd_name = optarg; - break; - case 'u': - user_details = getpwnam(optarg); - if (!user_details) - err(1, "getpwnam failed, incorrect username?"); - break; - case 'c': - chroot_path = optarg; - break; - default: - warnx("Unknown argument %s", argv[optind]); - usage(); - } - } - /* - * After the other arguments we expect memory and kernel image name, - * followed by command line arguments for the kernel. - */ - if (optind + 2 > argc) - usage(); - - verbose("Guest base is at %p\n", guest_base); - - /* Initialize the (fake) PCI host bridge device. */ - init_pci_host_bridge(); - - /* Now we load the kernel */ - start = load_kernel(open_or_die(argv[optind+1], O_RDONLY)); - - /* Boot information is stashed at physical address 0 */ - boot = from_guest_phys(0); - - /* Map the initrd image if requested (at top of physical memory) */ - if (initrd_name) { - initrd_size = load_initrd(initrd_name, mem); - /* - * These are the location in the Linux boot header where the - * start and size of the initrd are expected to be found. - */ - boot->hdr.ramdisk_image = mem - initrd_size; - boot->hdr.ramdisk_size = initrd_size; - /* The bootloader type 0xFF means "unknown"; that's OK. */ - boot->hdr.type_of_loader = 0xFF; - } - - /* - * The Linux boot header contains an "E820" memory map: ours is a - * simple, single region. - */ - boot->e820_entries = 1; - boot->e820_table[0] = ((struct e820_entry) { 0, mem, E820_TYPE_RAM }); - /* - * The boot header contains a command line pointer: we put the command - * line after the boot header. - */ - boot->hdr.cmd_line_ptr = to_guest_phys(boot + 1); - /* We use a simple helper to copy the arguments separated by spaces. */ - concat((char *)(boot + 1), argv+optind+2); - - /* Set kernel alignment to 16M (CONFIG_PHYSICAL_ALIGN) */ - boot->hdr.kernel_alignment = 0x1000000; - - /* Boot protocol version: 2.07 supports the fields for lguest. */ - boot->hdr.version = 0x207; - - /* X86_SUBARCH_LGUEST tells the Guest it's an lguest. */ - boot->hdr.hardware_subarch = X86_SUBARCH_LGUEST; - - /* Tell the entry path not to try to reload segment registers. */ - boot->hdr.loadflags |= KEEP_SEGMENTS; - - /* We don't support tboot: */ - boot->tboot_addr = 0; - - /* Ensure this is 0 to prevent APM from loading: */ - boot->apm_bios_info.version = 0; - - /* We tell the kernel to initialize the Guest. */ - tell_kernel(start); - - /* Ensure that we terminate if a device-servicing child dies. */ - signal(SIGCHLD, kill_launcher); - - /* If requested, chroot to a directory */ - if (chroot_path) { - if (chroot(chroot_path) != 0) - err(1, "chroot(\"%s\") failed", chroot_path); - - if (chdir("/") != 0) - err(1, "chdir(\"/\") failed"); - - verbose("chroot done\n"); - } - - /* If requested, drop privileges */ - if (user_details) { - uid_t u; - gid_t g; - - u = user_details->pw_uid; - g = user_details->pw_gid; - - if (initgroups(user_details->pw_name, g) != 0) - err(1, "initgroups failed"); - - if (setresgid(g, g, g) != 0) - err(1, "setresgid failed"); - - if (setresuid(u, u, u) != 0) - err(1, "setresuid failed"); - - verbose("Dropping privileges completed\n"); - } - - /* Finally, run the Guest. This doesn't return. */ - run_guest(); -} -/*:*/ - -/*M:999 - * Mastery is done: you now know everything I do. - * - * But surely you have seen code, features and bugs in your wanderings which - * you now yearn to attack? That is the real game, and I look forward to you - * patching and forking lguest into the Your-Name-Here-visor. - * - * Farewell, and good coding! - * Rusty Russell. - */ diff --git a/tools/lguest/lguest.txt b/tools/lguest/lguest.txt deleted file mode 100644 index 06e1f4649511..000000000000 --- a/tools/lguest/lguest.txt +++ /dev/null @@ -1,125 +0,0 @@ - __ - (___()'`; Rusty's Remarkably Unreliable Guide to Lguest - /, /` - or, A Young Coder's Illustrated Hypervisor - \\"--\\ http://lguest.ozlabs.org - -Lguest is designed to be a minimal 32-bit x86 hypervisor for the Linux kernel, -for Linux developers and users to experiment with virtualization with the -minimum of complexity. Nonetheless, it should have sufficient features to -make it useful for specific tasks, and, of course, you are encouraged to fork -and enhance it (see drivers/lguest/README). - -Features: - -- Kernel module which runs in a normal kernel. -- Simple I/O model for communication. -- Simple program to create new guests. -- Logo contains cute puppies: http://lguest.ozlabs.org - -Developer features: - -- Fun to hack on. -- No ABI: being tied to a specific kernel anyway, you can change anything. -- Many opportunities for improvement or feature implementation. - -Running Lguest: - -- The easiest way to run lguest is to use same kernel as guest and host. - You can configure them differently, but usually it's easiest not to. - - You will need to configure your kernel with the following options: - - "Processor type and features": - "Paravirtualized guest support" = Y - "Lguest guest support" = Y - "High Memory Support" = off/4GB - "Alignment value to which kernel should be aligned" = 0x100000 - (CONFIG_PARAVIRT=y, CONFIG_LGUEST_GUEST=y, CONFIG_HIGHMEM64G=n and - CONFIG_PHYSICAL_ALIGN=0x100000) - - "Device Drivers": - "Block devices" - "Virtio block driver" = M/Y - "Network device support" - "Universal TUN/TAP device driver support" = M/Y - "Virtio network driver" = M/Y - (CONFIG_VIRTIO_BLK=m, CONFIG_VIRTIO_NET=m and CONFIG_TUN=m) - - "Virtualization" - "Linux hypervisor example code" = M/Y - (CONFIG_LGUEST=m) - -- A tool called "lguest" is available in this directory: type "make" - to build it. If you didn't build your kernel in-tree, use "make - O=". - -- Create or find a root disk image. There are several useful ones - around, such as the xm-test tiny root image at - http://xm-test.xensource.com/ramdisks/initrd-1.1-i386.img - - For more serious work, I usually use a distribution ISO image and - install it under qemu, then make multiple copies: - - dd if=/dev/zero of=rootfile bs=1M count=2048 - qemu -cdrom image.iso -hda rootfile -net user -net nic -boot d - - Make sure that you install a getty on /dev/hvc0 if you want to log in on the - console! - -- "modprobe lg" if you built it as a module. - -- Run an lguest as root: - - tools/lguest/lguest 64 vmlinux --tunnet=192.168.19.1 \ - --block=rootfile root=/dev/vda - - Explanation: - 64: the amount of memory to use, in MB. - - vmlinux: the kernel image found in the top of your build directory. You - can also use a standard bzImage. - - --tunnet=192.168.19.1: configures a "tap" device for networking with this - IP address. - - --block=rootfile: a file or block device which becomes /dev/vda - inside the guest. - - root=/dev/vda: this (and anything else on the command line) are - kernel boot parameters. - -- Configuring networking. I usually have the host masquerade, using - "iptables -t nat -A POSTROUTING -o eth0 -j MASQUERADE" and "echo 1 > - /proc/sys/net/ipv4/ip_forward". In this example, I would configure - eth0 inside the guest at 192.168.19.2. - - Another method is to bridge the tap device to an external interface - using --tunnet=bridge:, and perhaps run dhcp on the guest - to obtain an IP address. The bridge needs to be configured first: - this option simply adds the tap interface to it. - - A simple example on my system: - - ifconfig eth0 0.0.0.0 - brctl addbr lg0 - ifconfig lg0 up - brctl addif lg0 eth0 - dhclient lg0 - - Then use --tunnet=bridge:lg0 when launching the guest. - - See: - - http://www.linuxfoundation.org/collaborate/workgroups/networking/bridge - - for general information on how to get bridging to work. - -- Random number generation. Using the --rng option will provide a - /dev/hwrng in the guest that will read from the host's /dev/random. - Use this option in conjunction with rng-tools (see ../hw_random.txt) - to provide entropy to the guest kernel's /dev/random. - -There is a helpful mailing list at http://ozlabs.org/mailman/listinfo/lguest - -Good luck! -Rusty Russell rusty@rustcorp.com.au. -- cgit v1.2.3-71-gd317 From ea5311c7e752dbec9bfbdd79992a8772b37f32fa Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Thu, 10 Aug 2017 10:54:31 -0600 Subject: PCI: Fix PCIe capability sizes PCI_CAP_EXP_ENDPOINT_SIZEOF_V1 defines the size of the PCIe capability structure for v1 devices with link, but we also have a need in the vfio code for sizing the capability for devices without link, such as Root Complex Integrated Endpoints. Create a separate define for this ending the structure before the link fields. Additionally, this reveals that PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 is currently incorrect, ending the capability length before the v2 link fields. Rename this to specify an RC Integrated Endpoint (no link) capability length and move PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 to include the link fields as we have for the v1 version. Signed-off-by: Alex Williamson [bhelgaas: add "_" in "PCI_CAP_EXP_RC ENDPOINT_SIZEOF_V2 44"] Signed-off-by: Bjorn Helgaas Reviewed-by: Eric Auger --- include/uapi/linux/pci_regs.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index c22d3ebaca20..e185d2d39ea6 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -513,6 +513,7 @@ #define PCI_EXP_DEVSTA_URD 0x0008 /* Unsupported Request Detected */ #define PCI_EXP_DEVSTA_AUXPD 0x0010 /* AUX Power Detected */ #define PCI_EXP_DEVSTA_TRPND 0x0020 /* Transactions Pending */ +#define PCI_CAP_EXP_RC_ENDPOINT_SIZEOF_V1 12 /* v1 endpoints without link end here */ #define PCI_EXP_LNKCAP 12 /* Link Capabilities */ #define PCI_EXP_LNKCAP_SLS 0x0000000f /* Supported Link Speeds */ #define PCI_EXP_LNKCAP_SLS_2_5GB 0x00000001 /* LNKCAP2 SLS Vector bit 0 */ @@ -556,7 +557,7 @@ #define PCI_EXP_LNKSTA_DLLLA 0x2000 /* Data Link Layer Link Active */ #define PCI_EXP_LNKSTA_LBMS 0x4000 /* Link Bandwidth Management Status */ #define PCI_EXP_LNKSTA_LABS 0x8000 /* Link Autonomous Bandwidth Status */ -#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V1 20 /* v1 endpoints end here */ +#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V1 20 /* v1 endpoints with link end here */ #define PCI_EXP_SLTCAP 20 /* Slot Capabilities */ #define PCI_EXP_SLTCAP_ABP 0x00000001 /* Attention Button Present */ #define PCI_EXP_SLTCAP_PCP 0x00000002 /* Power Controller Present */ @@ -639,7 +640,7 @@ #define PCI_EXP_DEVCTL2_OBFF_MSGB_EN 0x4000 /* Enable OBFF Message type B */ #define PCI_EXP_DEVCTL2_OBFF_WAKE_EN 0x6000 /* OBFF using WAKE# signaling */ #define PCI_EXP_DEVSTA2 42 /* Device Status 2 */ -#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 44 /* v2 endpoints end here */ +#define PCI_CAP_EXP_RC_ENDPOINT_SIZEOF_V2 44 /* v2 endpoints without link end here */ #define PCI_EXP_LNKCAP2 44 /* Link Capabilities 2 */ #define PCI_EXP_LNKCAP2_SLS_2_5GB 0x00000002 /* Supported Speed 2.5GT/s */ #define PCI_EXP_LNKCAP2_SLS_5_0GB 0x00000004 /* Supported Speed 5.0GT/s */ @@ -647,6 +648,7 @@ #define PCI_EXP_LNKCAP2_CROSSLINK 0x00000100 /* Crosslink supported */ #define PCI_EXP_LNKCTL2 48 /* Link Control 2 */ #define PCI_EXP_LNKSTA2 50 /* Link Status 2 */ +#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 52 /* v2 endpoints with link end here */ #define PCI_EXP_SLTCAP2 52 /* Slot Capabilities 2 */ #define PCI_EXP_SLTCTL2 56 /* Slot Control 2 */ #define PCI_EXP_SLTSTA2 58 /* Slot Status 2 */ -- cgit v1.2.3-71-gd317 From f20c4ea49ec4708de97248927ac6138c2d14eba9 Mon Sep 17 00:00:00 2001 From: Dongdong Liu Date: Sat, 19 Aug 2017 17:07:20 +0800 Subject: PCI/DPC: Add eDPC support Add eDPC support. Get and print the RP PIO error information when the trigger condition is RP PIO error. For more information on eDPC, please see PCI Express Base Specification Revision 3.1, section 6.2.10.3, or view the PCI-SIG eDPC ECN here: https://pcisig.com/sites/default/files/specification_documents/ECN_Enhanced_DPC_2012-11-19_final.pdf Signed-off-by: Dongdong Liu Signed-off-by: Bjorn Helgaas Reviewed-by: Keith Busch --- drivers/pci/pcie/pcie-dpc.c | 162 ++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/pci_regs.h | 10 +++ 2 files changed, 172 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/pci/pcie/pcie-dpc.c b/drivers/pci/pcie/pcie-dpc.c index c39f32e42b4d..8428d7455e49 100644 --- a/drivers/pci/pcie/pcie-dpc.c +++ b/drivers/pci/pcie/pcie-dpc.c @@ -16,11 +16,55 @@ #include #include "../pci.h" +struct rp_pio_header_log_regs { + u32 dw0; + u32 dw1; + u32 dw2; + u32 dw3; +}; + +struct dpc_rp_pio_regs { + u32 status; + u32 mask; + u32 severity; + u32 syserror; + u32 exception; + + struct rp_pio_header_log_regs header_log; + u32 impspec_log; + u32 tlp_prefix_log[4]; + u32 log_size; + u16 first_error; +}; + struct dpc_dev { struct pcie_device *dev; struct work_struct work; int cap_pos; bool rp; + u32 rp_pio_status; +}; + +static const char * const rp_pio_error_string[] = { + "Configuration Request received UR Completion", /* Bit Position 0 */ + "Configuration Request received CA Completion", /* Bit Position 1 */ + "Configuration Request Completion Timeout", /* Bit Position 2 */ + NULL, + NULL, + NULL, + NULL, + NULL, + "I/O Request received UR Completion", /* Bit Position 8 */ + "I/O Request received CA Completion", /* Bit Position 9 */ + "I/O Request Completion Timeout", /* Bit Position 10 */ + NULL, + NULL, + NULL, + NULL, + NULL, + "Memory Request received UR Completion", /* Bit Position 16 */ + "Memory Request received CA Completion", /* Bit Position 17 */ + "Memory Request Completion Timeout", /* Bit Position 18 */ }; static int dpc_wait_rp_inactive(struct dpc_dev *dpc) @@ -79,10 +123,124 @@ static void interrupt_event_handler(struct work_struct *work) dpc_wait_link_inactive(pdev); if (dpc->rp && dpc_wait_rp_inactive(dpc)) return; + if (dpc->rp && dpc->rp_pio_status) { + pci_write_config_dword(pdev, + dpc->cap_pos + PCI_EXP_DPC_RP_PIO_STATUS, + dpc->rp_pio_status); + dpc->rp_pio_status = 0; + } + pci_write_config_word(pdev, dpc->cap_pos + PCI_EXP_DPC_STATUS, PCI_EXP_DPC_STATUS_TRIGGER | PCI_EXP_DPC_STATUS_INTERRUPT); } +static void dpc_rp_pio_print_tlp_header(struct device *dev, + struct rp_pio_header_log_regs *t) +{ + dev_err(dev, "TLP Header: %#010x %#010x %#010x %#010x\n", + t->dw0, t->dw1, t->dw2, t->dw3); +} + +static void dpc_rp_pio_print_error(struct dpc_dev *dpc, + struct dpc_rp_pio_regs *rp_pio) +{ + struct device *dev = &dpc->dev->device; + int i; + u32 status; + + dev_err(dev, "rp_pio_status: %#010x, rp_pio_mask: %#010x\n", + rp_pio->status, rp_pio->mask); + + dev_err(dev, "RP PIO severity=%#010x, syserror=%#010x, exception=%#010x\n", + rp_pio->severity, rp_pio->syserror, rp_pio->exception); + + status = (rp_pio->status & ~rp_pio->mask); + + for (i = 0; i < ARRAY_SIZE(rp_pio_error_string); i++) { + if (!(status & (1 << i))) + continue; + + dev_err(dev, "[%2d] %s%s\n", i, rp_pio_error_string[i], + rp_pio->first_error == i ? " (First)" : ""); + } + + dpc_rp_pio_print_tlp_header(dev, &rp_pio->header_log); + if (rp_pio->log_size == 4) + return; + dev_err(dev, "RP PIO ImpSpec Log %#010x\n", rp_pio->impspec_log); + + for (i = 0; i < rp_pio->log_size - 5; i++) + dev_err(dev, "TLP Prefix Header: dw%d, %#010x\n", i, + rp_pio->tlp_prefix_log[i]); +} + +static void dpc_rp_pio_get_info(struct dpc_dev *dpc, + struct dpc_rp_pio_regs *rp_pio) +{ + struct pci_dev *pdev = dpc->dev->port; + struct device *dev = &dpc->dev->device; + int i; + u16 cap; + u16 status; + + pci_read_config_dword(pdev, dpc->cap_pos + PCI_EXP_DPC_RP_PIO_STATUS, + &rp_pio->status); + pci_read_config_dword(pdev, dpc->cap_pos + PCI_EXP_DPC_RP_PIO_MASK, + &rp_pio->mask); + + pci_read_config_dword(pdev, dpc->cap_pos + PCI_EXP_DPC_RP_PIO_SEVERITY, + &rp_pio->severity); + pci_read_config_dword(pdev, dpc->cap_pos + PCI_EXP_DPC_RP_PIO_SYSERROR, + &rp_pio->syserror); + pci_read_config_dword(pdev, dpc->cap_pos + PCI_EXP_DPC_RP_PIO_EXCEPTION, + &rp_pio->exception); + + /* Get First Error Pointer */ + pci_read_config_word(pdev, dpc->cap_pos + PCI_EXP_DPC_STATUS, &status); + rp_pio->first_error = (status & 0x1f00) >> 8; + + pci_read_config_word(pdev, dpc->cap_pos + PCI_EXP_DPC_CAP, &cap); + rp_pio->log_size = (cap & PCI_EXP_DPC_RP_PIO_LOG_SIZE) >> 8; + if (rp_pio->log_size < 4 || rp_pio->log_size > 9) { + dev_err(dev, "RP PIO log size %u is invalid\n", + rp_pio->log_size); + return; + } + + pci_read_config_dword(pdev, + dpc->cap_pos + PCI_EXP_DPC_RP_PIO_HEADER_LOG, + &rp_pio->header_log.dw0); + pci_read_config_dword(pdev, + dpc->cap_pos + PCI_EXP_DPC_RP_PIO_HEADER_LOG + 4, + &rp_pio->header_log.dw1); + pci_read_config_dword(pdev, + dpc->cap_pos + PCI_EXP_DPC_RP_PIO_HEADER_LOG + 8, + &rp_pio->header_log.dw2); + pci_read_config_dword(pdev, + dpc->cap_pos + PCI_EXP_DPC_RP_PIO_HEADER_LOG + 12, + &rp_pio->header_log.dw3); + if (rp_pio->log_size == 4) + return; + + pci_read_config_dword(pdev, + dpc->cap_pos + PCI_EXP_DPC_RP_PIO_IMPSPEC_LOG, + &rp_pio->impspec_log); + for (i = 0; i < rp_pio->log_size - 5; i++) + pci_read_config_dword(pdev, + dpc->cap_pos + PCI_EXP_DPC_RP_PIO_TLPPREFIX_LOG, + &rp_pio->tlp_prefix_log[i]); +} + +static void dpc_process_rp_pio_error(struct dpc_dev *dpc) +{ + struct dpc_rp_pio_regs rp_pio_regs; + + dpc_rp_pio_get_info(dpc, &rp_pio_regs); + dpc_rp_pio_print_error(dpc, &rp_pio_regs); + + dpc->rp_pio_status = rp_pio_regs.status; +} + static irqreturn_t dpc_irq(int irq, void *context) { struct dpc_dev *dpc = (struct dpc_dev *)context; @@ -109,6 +267,10 @@ static irqreturn_t dpc_irq(int irq, void *context) (ext_reason == 0) ? "RP PIO error" : (ext_reason == 1) ? "software trigger" : "reserved error"); + /* show RP PIO error detail information */ + if (reason == 3 && ext_reason == 0) + dpc_process_rp_pio_error(dpc); + schedule_work(&dpc->work); } return IRQ_HANDLED; diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index c22d3ebaca20..1ce96275531c 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -967,6 +967,7 @@ #define PCI_EXP_DPC_CAP_RP_EXT 0x20 /* Root Port Extensions for DPC */ #define PCI_EXP_DPC_CAP_POISONED_TLP 0x40 /* Poisoned TLP Egress Blocking Supported */ #define PCI_EXP_DPC_CAP_SW_TRIGGER 0x80 /* Software Triggering Supported */ +#define PCI_EXP_DPC_RP_PIO_LOG_SIZE 0xF00 /* RP PIO log size */ #define PCI_EXP_DPC_CAP_DL_ACTIVE 0x1000 /* ERR_COR signal on DL_Active supported */ #define PCI_EXP_DPC_CTL 6 /* DPC control */ @@ -980,6 +981,15 @@ #define PCI_EXP_DPC_SOURCE_ID 10 /* DPC Source Identifier */ +#define PCI_EXP_DPC_RP_PIO_STATUS 0x0C /* RP PIO Status */ +#define PCI_EXP_DPC_RP_PIO_MASK 0x10 /* RP PIO MASK */ +#define PCI_EXP_DPC_RP_PIO_SEVERITY 0x14 /* RP PIO Severity */ +#define PCI_EXP_DPC_RP_PIO_SYSERROR 0x18 /* RP PIO SysError */ +#define PCI_EXP_DPC_RP_PIO_EXCEPTION 0x1C /* RP PIO Exception */ +#define PCI_EXP_DPC_RP_PIO_HEADER_LOG 0x20 /* RP PIO Header Log */ +#define PCI_EXP_DPC_RP_PIO_IMPSPEC_LOG 0x30 /* RP PIO ImpSpec Log */ +#define PCI_EXP_DPC_RP_PIO_TLPPREFIX_LOG 0x34 /* RP PIO TLP Prefix Log */ + /* Precision Time Measurement */ #define PCI_PTM_CAP 0x04 /* PTM Capability */ #define PCI_PTM_CAP_REQ 0x00000001 /* Requester capable */ -- cgit v1.2.3-71-gd317 From 1177009131bee310421f5c04c43d3777cbacbdc8 Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Thu, 24 Aug 2017 08:39:59 +0200 Subject: devlink: Add Ethernet header for dpipe This will be used by the IPv4 host table which will be introduced in the following patches. This header is global and can be reused by many drivers. Signed-off-by: Arkadi Sharshevsky Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 1 + include/uapi/linux/devlink.h | 8 ++++++++ net/core/devlink.c | 17 +++++++++++++++++ 3 files changed, 26 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/devlink.h b/include/net/devlink.h index ed7687bbf5d0..ddb8b5227580 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -328,6 +328,7 @@ int devlink_dpipe_action_put(struct sk_buff *skb, struct devlink_dpipe_action *action); int devlink_dpipe_match_put(struct sk_buff *skb, struct devlink_dpipe_match *match); +extern struct devlink_dpipe_header devlink_dpipe_header_ethernet; #else diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index b0e807ac53bb..a855f8dcc8ee 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -226,4 +226,12 @@ enum devlink_dpipe_action_type { DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY, }; +enum devlink_dpipe_field_ethernet_id { + DEVLINK_DPIPE_FIELD_ETHERNET_DST_MAC, +}; + +enum devlink_dpipe_header_id { + DEVLINK_DPIPE_HEADER_ETHERNET, +}; + #endif /* _UAPI_LINUX_DEVLINK_H_ */ diff --git a/net/core/devlink.c b/net/core/devlink.c index a0adfc31a3fe..4f6f3d601785 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -29,6 +29,23 @@ #define CREATE_TRACE_POINTS #include +static struct devlink_dpipe_field devlink_dpipe_fields_ethernet[] = { + { + .name = "destination_mac", + .id = DEVLINK_DPIPE_FIELD_ETHERNET_DST_MAC, + .bitwidth = 48, + }, +}; + +struct devlink_dpipe_header devlink_dpipe_header_ethernet = { + .name = "ethernet", + .id = DEVLINK_DPIPE_HEADER_ETHERNET, + .fields = devlink_dpipe_fields_ethernet, + .fields_count = ARRAY_SIZE(devlink_dpipe_fields_ethernet), + .global = true, +}; +EXPORT_SYMBOL(devlink_dpipe_header_ethernet); + EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg); static LIST_HEAD(devlink_list); -- cgit v1.2.3-71-gd317 From 3fb886ecea93605a8ea14e258ff3158b8966781e Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Thu, 24 Aug 2017 08:40:00 +0200 Subject: devlink: Add IPv4 header for dpipe This will be used by the IPv4 host table which will be introduced in the following patches. This header is global and can be reused by many drivers. Signed-off-by: Arkadi Sharshevsky Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 1 + include/uapi/linux/devlink.h | 5 +++++ net/core/devlink.c | 17 +++++++++++++++++ 3 files changed, 23 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/devlink.h b/include/net/devlink.h index ddb8b5227580..8ff8a6f77f29 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -329,6 +329,7 @@ int devlink_dpipe_action_put(struct sk_buff *skb, int devlink_dpipe_match_put(struct sk_buff *skb, struct devlink_dpipe_match *match); extern struct devlink_dpipe_header devlink_dpipe_header_ethernet; +extern struct devlink_dpipe_header devlink_dpipe_header_ipv4; #else diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index a855f8dcc8ee..6c172548589d 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -230,8 +230,13 @@ enum devlink_dpipe_field_ethernet_id { DEVLINK_DPIPE_FIELD_ETHERNET_DST_MAC, }; +enum devlink_dpipe_field_ipv4_id { + DEVLINK_DPIPE_FIELD_IPV4_DST_IP, +}; + enum devlink_dpipe_header_id { DEVLINK_DPIPE_HEADER_ETHERNET, + DEVLINK_DPIPE_HEADER_IPV4, }; #endif /* _UAPI_LINUX_DEVLINK_H_ */ diff --git a/net/core/devlink.c b/net/core/devlink.c index 4f6f3d601785..fcf5dd662882 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -46,6 +46,23 @@ struct devlink_dpipe_header devlink_dpipe_header_ethernet = { }; EXPORT_SYMBOL(devlink_dpipe_header_ethernet); +static struct devlink_dpipe_field devlink_dpipe_fields_ipv4[] = { + { + .name = "destination ip", + .id = DEVLINK_DPIPE_FIELD_IPV4_DST_IP, + .bitwidth = 32, + }, +}; + +struct devlink_dpipe_header devlink_dpipe_header_ipv4 = { + .name = "ipv4", + .id = DEVLINK_DPIPE_HEADER_IPV4, + .fields = devlink_dpipe_fields_ipv4, + .fields_count = ARRAY_SIZE(devlink_dpipe_fields_ipv4), + .global = true, +}; +EXPORT_SYMBOL(devlink_dpipe_header_ipv4); + EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg); static LIST_HEAD(devlink_list); -- cgit v1.2.3-71-gd317 From 6ae5fa61d27dcb055f4198bcf6c8dbbf1bb33f52 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Wed, 16 Aug 2017 15:21:54 -0700 Subject: perf/x86: Fix data source decoding for Skylake Skylake changed the encoding of the PEBS data source field. Some combinations are not available anymore, but some new cases e.g. for L4 cache hit are added. Fix up the conversion table for Skylake, similar as had been done for Nehalem. On Skylake server the encoding for L4 actually means persistent memory. Handle this case too. To properly describe it in the abstracted perf format I had to add some new fields. Since a hit can have only one level add a new field that is an enumeration, not a bit field to describe the level. It can describe any level. Some numbers are also used to describe PMEM and LFB. Also add a new generic remote flag that can be combined with the generic level to signify a remote cache. And there is an extension field for the snoop indication to handle the Forward state. I didn't add a generic flag for hops because it's not needed for Skylake. I changed the existing encodings for older CPUs to also fill in the new level and remote fields. Signed-off-by: Andi Kleen Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Madhavan Srinivasan Cc: Michael Ellerman Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: acme@kernel.org Cc: jolsa@kernel.org Link: http://lkml.kernel.org/r/20170816222156.19953-3-andi@firstfloor.org Signed-off-by: Ingo Molnar --- arch/x86/events/intel/core.c | 2 ++ arch/x86/events/intel/ds.c | 51 ++++++++++++++++++++++++++--------------- arch/x86/events/perf_event.h | 2 ++ include/uapi/linux/perf_event.h | 30 ++++++++++++++++++++++-- 4 files changed, 64 insertions(+), 21 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index c3439a36dcf9..6f342001ec6a 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4208,6 +4208,8 @@ __init int intel_pmu_init(void) skl_format_attr); WARN_ON(!x86_pmu.format_attrs); x86_pmu.cpu_events = hsw_events_attrs; + intel_pmu_pebs_data_source_skl( + boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X); pr_cont("Skylake events, "); break; diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 3ccdf8cb4495..98e36e0c791c 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -49,34 +49,47 @@ union intel_x86_pebs_dse { */ #define P(a, b) PERF_MEM_S(a, b) #define OP_LH (P(OP, LOAD) | P(LVL, HIT)) +#define LEVEL(x) P(LVLNUM, x) +#define REM P(REMOTE, REMOTE) #define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS)) /* Version for Sandy Bridge and later */ static u64 pebs_data_source[] = { - P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | P(SNOOP, NA),/* 0x00:ukn L3 */ - OP_LH | P(LVL, L1) | P(SNOOP, NONE), /* 0x01: L1 local */ - OP_LH | P(LVL, LFB) | P(SNOOP, NONE), /* 0x02: LFB hit */ - OP_LH | P(LVL, L2) | P(SNOOP, NONE), /* 0x03: L2 hit */ - OP_LH | P(LVL, L3) | P(SNOOP, NONE), /* 0x04: L3 hit */ - OP_LH | P(LVL, L3) | P(SNOOP, MISS), /* 0x05: L3 hit, snoop miss */ - OP_LH | P(LVL, L3) | P(SNOOP, HIT), /* 0x06: L3 hit, snoop hit */ - OP_LH | P(LVL, L3) | P(SNOOP, HITM), /* 0x07: L3 hit, snoop hitm */ - OP_LH | P(LVL, REM_CCE1) | P(SNOOP, HIT), /* 0x08: L3 miss snoop hit */ - OP_LH | P(LVL, REM_CCE1) | P(SNOOP, HITM), /* 0x09: L3 miss snoop hitm*/ - OP_LH | P(LVL, LOC_RAM) | P(SNOOP, HIT), /* 0x0a: L3 miss, shared */ - OP_LH | P(LVL, REM_RAM1) | P(SNOOP, HIT), /* 0x0b: L3 miss, shared */ - OP_LH | P(LVL, LOC_RAM) | SNOOP_NONE_MISS,/* 0x0c: L3 miss, excl */ - OP_LH | P(LVL, REM_RAM1) | SNOOP_NONE_MISS,/* 0x0d: L3 miss, excl */ - OP_LH | P(LVL, IO) | P(SNOOP, NONE), /* 0x0e: I/O */ - OP_LH | P(LVL, UNC) | P(SNOOP, NONE), /* 0x0f: uncached */ + P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA),/* 0x00:ukn L3 */ + OP_LH | P(LVL, L1) | LEVEL(L1) | P(SNOOP, NONE), /* 0x01: L1 local */ + OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE), /* 0x02: LFB hit */ + OP_LH | P(LVL, L2) | LEVEL(L2) | P(SNOOP, NONE), /* 0x03: L2 hit */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, NONE), /* 0x04: L3 hit */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, MISS), /* 0x05: L3 hit, snoop miss */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT), /* 0x06: L3 hit, snoop hit */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM), /* 0x07: L3 hit, snoop hitm */ + OP_LH | P(LVL, REM_CCE1) | REM | LEVEL(L3) | P(SNOOP, HIT), /* 0x08: L3 miss snoop hit */ + OP_LH | P(LVL, REM_CCE1) | REM | LEVEL(L3) | P(SNOOP, HITM), /* 0x09: L3 miss snoop hitm*/ + OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | P(SNOOP, HIT), /* 0x0a: L3 miss, shared */ + OP_LH | P(LVL, REM_RAM1) | REM | LEVEL(L3) | P(SNOOP, HIT), /* 0x0b: L3 miss, shared */ + OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | SNOOP_NONE_MISS, /* 0x0c: L3 miss, excl */ + OP_LH | P(LVL, REM_RAM1) | LEVEL(RAM) | REM | SNOOP_NONE_MISS, /* 0x0d: L3 miss, excl */ + OP_LH | P(LVL, IO) | LEVEL(NA) | P(SNOOP, NONE), /* 0x0e: I/O */ + OP_LH | P(LVL, UNC) | LEVEL(NA) | P(SNOOP, NONE), /* 0x0f: uncached */ }; /* Patch up minor differences in the bits */ void __init intel_pmu_pebs_data_source_nhm(void) { - pebs_data_source[0x05] = OP_LH | P(LVL, L3) | P(SNOOP, HIT); - pebs_data_source[0x06] = OP_LH | P(LVL, L3) | P(SNOOP, HITM); - pebs_data_source[0x07] = OP_LH | P(LVL, L3) | P(SNOOP, HITM); + pebs_data_source[0x05] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT); + pebs_data_source[0x06] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM); + pebs_data_source[0x07] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM); +} + +void __init intel_pmu_pebs_data_source_skl(bool pmem) +{ + u64 pmem_or_l4 = pmem ? LEVEL(PMEM) : LEVEL(L4); + + pebs_data_source[0x08] = OP_LH | pmem_or_l4 | P(SNOOP, HIT); + pebs_data_source[0x09] = OP_LH | pmem_or_l4 | REM | P(SNOOP, HIT); + pebs_data_source[0x0b] = OP_LH | LEVEL(RAM) | REM | P(SNOOP, NONE); + pebs_data_source[0x0c] = OP_LH | LEVEL(ANY_CACHE) | REM | P(SNOOPX, FWD); + pebs_data_source[0x0d] = OP_LH | LEVEL(ANY_CACHE) | REM | P(SNOOP, HITM); } static u64 precise_store_data(u64 status) diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 2e9636e4068f..0f7dad8bd358 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -948,6 +948,8 @@ void intel_pmu_lbr_init_knl(void); void intel_pmu_pebs_data_source_nhm(void); +void intel_pmu_pebs_data_source_skl(bool pmem); + int intel_pmu_setup_lbr_filter(struct perf_event *event); void intel_pt_interrupt(void); diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 642db5fa3286..2a37ae925d85 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -954,14 +954,20 @@ union perf_mem_data_src { mem_snoop:5, /* snoop mode */ mem_lock:2, /* lock instr */ mem_dtlb:7, /* tlb access */ - mem_rsvd:31; + mem_lvl_num:4, /* memory hierarchy level number */ + mem_remote:1, /* remote */ + mem_snoopx:2, /* snoop mode, ext */ + mem_rsvd:24; }; }; #elif defined(__BIG_ENDIAN_BITFIELD) union perf_mem_data_src { __u64 val; struct { - __u64 mem_rsvd:31, + __u64 mem_rsvd:24, + mem_snoopx:2, /* snoop mode, ext */ + mem_remote:1, /* remote */ + mem_lvl_num:4, /* memory hierarchy level number */ mem_dtlb:7, /* tlb access */ mem_lock:2, /* lock instr */ mem_snoop:5, /* snoop mode */ @@ -998,6 +1004,22 @@ union perf_mem_data_src { #define PERF_MEM_LVL_UNC 0x2000 /* Uncached memory */ #define PERF_MEM_LVL_SHIFT 5 +#define PERF_MEM_REMOTE_REMOTE 0x01 /* Remote */ +#define PERF_MEM_REMOTE_SHIFT 37 + +#define PERF_MEM_LVLNUM_L1 0x01 /* L1 */ +#define PERF_MEM_LVLNUM_L2 0x02 /* L2 */ +#define PERF_MEM_LVLNUM_L3 0x03 /* L3 */ +#define PERF_MEM_LVLNUM_L4 0x04 /* L4 */ +/* 5-0xa available */ +#define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */ +#define PERF_MEM_LVLNUM_LFB 0x0c /* LFB */ +#define PERF_MEM_LVLNUM_RAM 0x0d /* RAM */ +#define PERF_MEM_LVLNUM_PMEM 0x0e /* PMEM */ +#define PERF_MEM_LVLNUM_NA 0x0f /* N/A */ + +#define PERF_MEM_LVLNUM_SHIFT 33 + /* snoop mode */ #define PERF_MEM_SNOOP_NA 0x01 /* not available */ #define PERF_MEM_SNOOP_NONE 0x02 /* no snoop */ @@ -1006,6 +1028,10 @@ union perf_mem_data_src { #define PERF_MEM_SNOOP_HITM 0x10 /* snoop hit modified */ #define PERF_MEM_SNOOP_SHIFT 19 +#define PERF_MEM_SNOOPX_FWD 0x01 /* forward */ +/* 1 free */ +#define PERF_MEM_SNOOPX_SHIFT 37 + /* locked instruction */ #define PERF_MEM_LOCK_NA 0x01 /* not available */ #define PERF_MEM_LOCK_LOCKED 0x02 /* locked transaction */ -- cgit v1.2.3-71-gd317 From 38ee7f2d47565689f35662d488d25e7afc43477d Mon Sep 17 00:00:00 2001 From: David Lebrun Date: Fri, 25 Aug 2017 09:56:45 +0200 Subject: ipv6: sr: add support for encapsulation of L2 frames This patch implements the L2 frame encapsulation mechanism, referred to as T.Encaps.L2 in the SRv6 specifications [1]. A new type of SRv6 tunnel mode is added (SEG6_IPTUN_MODE_L2ENCAP). It only accepts packets with an existing MAC header (i.e., it will not work for locally generated packets). The resulting packet looks like IPv6 -> SRH -> Ethernet -> original L3 payload. The next header field of the SRH is set to NEXTHDR_NONE. [1] https://tools.ietf.org/html/draft-filsfils-spring-srv6-network-programming-01 Signed-off-by: David Lebrun Signed-off-by: David S. Miller --- include/uapi/linux/seg6_iptunnel.h | 18 ++++++++++++++---- net/ipv6/seg6_iptunnel.c | 25 +++++++++++++++++++++++-- 2 files changed, 37 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/seg6_iptunnel.h b/include/uapi/linux/seg6_iptunnel.h index b6e5a0a1afd7..b23df9f58354 100644 --- a/include/uapi/linux/seg6_iptunnel.h +++ b/include/uapi/linux/seg6_iptunnel.h @@ -33,16 +33,26 @@ struct seg6_iptunnel_encap { enum { SEG6_IPTUN_MODE_INLINE, SEG6_IPTUN_MODE_ENCAP, + SEG6_IPTUN_MODE_L2ENCAP, }; #ifdef __KERNEL__ static inline size_t seg6_lwt_headroom(struct seg6_iptunnel_encap *tuninfo) { - int encap = (tuninfo->mode == SEG6_IPTUN_MODE_ENCAP); - - return ((tuninfo->srh->hdrlen + 1) << 3) + - (encap * sizeof(struct ipv6hdr)); + int head = 0; + + switch (tuninfo->mode) { + case SEG6_IPTUN_MODE_INLINE: + break; + case SEG6_IPTUN_MODE_ENCAP: + head = sizeof(struct ipv6hdr); + break; + case SEG6_IPTUN_MODE_L2ENCAP: + return 0; + } + + return ((tuninfo->srh->hdrlen + 1) << 3) + head; } #endif diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 5bec7817a7b9..bd6cc688bd19 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -238,6 +238,22 @@ static int seg6_do_srh(struct sk_buff *skb) if (err) return err; + skb->protocol = htons(ETH_P_IPV6); + break; + case SEG6_IPTUN_MODE_L2ENCAP: + if (!skb_mac_header_was_set(skb)) + return -EINVAL; + + if (pskb_expand_head(skb, skb->mac_len, 0, GFP_ATOMIC) < 0) + return -ENOMEM; + + skb_mac_header_rebuild(skb); + skb_push(skb, skb->mac_len); + + err = seg6_do_srh_encap(skb, tinfo->srh, NEXTHDR_NONE); + if (err) + return err; + skb->protocol = htons(ETH_P_IPV6); break; } @@ -386,6 +402,8 @@ static int seg6_build_state(struct nlattr *nla, break; case SEG6_IPTUN_MODE_ENCAP: break; + case SEG6_IPTUN_MODE_L2ENCAP: + break; default: return -EINVAL; } @@ -409,8 +427,11 @@ static int seg6_build_state(struct nlattr *nla, memcpy(&slwt->tuninfo, tuninfo, tuninfo_len); newts->type = LWTUNNEL_ENCAP_SEG6; - newts->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT | - LWTUNNEL_STATE_INPUT_REDIRECT; + newts->flags |= LWTUNNEL_STATE_INPUT_REDIRECT; + + if (tuninfo->mode != SEG6_IPTUN_MODE_L2ENCAP) + newts->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT; + newts->headroom = seg6_lwt_headroom(tuninfo); *ts = newts; -- cgit v1.2.3-71-gd317 From d1b3437ed780cd97b4b1300db96a4d8faae6fea1 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Tue, 8 Aug 2017 09:29:58 -0400 Subject: media: v4l: Add packed Bayer raw12 pixel formats These formats are compressed 12-bit raw bayer formats with four different pixel orders. They are similar to 10-bit variants. The formats added by this patch are V4L2_PIX_FMT_SBGGR12P V4L2_PIX_FMT_SGBRG12P V4L2_PIX_FMT_SGRBG12P V4L2_PIX_FMT_SRGGB12P Signed-off-by: Sakari Ailus Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/v4l/pixfmt-rgb.rst | 1 + Documentation/media/uapi/v4l/pixfmt-srggb12p.rst | 103 +++++++++++++++++++++++ drivers/media/v4l2-core/v4l2-ioctl.c | 12 ++- include/uapi/linux/videodev2.h | 5 ++ 4 files changed, 117 insertions(+), 4 deletions(-) create mode 100644 Documentation/media/uapi/v4l/pixfmt-srggb12p.rst (limited to 'include/uapi/linux') diff --git a/Documentation/media/uapi/v4l/pixfmt-rgb.rst b/Documentation/media/uapi/v4l/pixfmt-rgb.rst index b0f35136021e..4cc27195dc79 100644 --- a/Documentation/media/uapi/v4l/pixfmt-rgb.rst +++ b/Documentation/media/uapi/v4l/pixfmt-rgb.rst @@ -17,4 +17,5 @@ RGB Formats pixfmt-srggb10alaw8 pixfmt-srggb10dpcm8 pixfmt-srggb12 + pixfmt-srggb12p pixfmt-srggb16 diff --git a/Documentation/media/uapi/v4l/pixfmt-srggb12p.rst b/Documentation/media/uapi/v4l/pixfmt-srggb12p.rst new file mode 100644 index 000000000000..c0541e5acd01 --- /dev/null +++ b/Documentation/media/uapi/v4l/pixfmt-srggb12p.rst @@ -0,0 +1,103 @@ +.. -*- coding: utf-8; mode: rst -*- + +.. _V4L2-PIX-FMT-SRGGB12P: +.. _v4l2-pix-fmt-sbggr12p: +.. _v4l2-pix-fmt-sgbrg12p: +.. _v4l2-pix-fmt-sgrbg12p: + +******************************************************************************************************************************* +V4L2_PIX_FMT_SRGGB12P ('pRAA'), V4L2_PIX_FMT_SGRBG12P ('pgAA'), V4L2_PIX_FMT_SGBRG12P ('pGAA'), V4L2_PIX_FMT_SBGGR12P ('pBAA'), +******************************************************************************************************************************* + + +12-bit packed Bayer formats + + +Description +=========== + +These four pixel formats are packed raw sRGB / Bayer formats with 12 +bits per colour. Every two consecutive samples are packed into three +bytes. Each of the first two bytes contain the 8 high order bits of +the pixels, and the third byte contains the four least significants +bits of each pixel, in the same order. + +Each n-pixel row contains n/2 green samples and n/2 blue or red +samples, with alternating green-red and green-blue rows. They are +conventionally described as GRGR... BGBG..., RGRG... GBGB..., etc. +Below is an example of a small V4L2_PIX_FMT_SBGGR12P image: + +**Byte Order.** +Each cell is one byte. + + + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 2 1 1 1 1 1 1 + + + - .. row 1 + + - start + 0: + + - B\ :sub:`00high` + + - G\ :sub:`01high` + + - G\ :sub:`01low`\ (bits 7--4) B\ :sub:`00low`\ (bits 3--0) + + - B\ :sub:`02high` + + - G\ :sub:`03high` + + - G\ :sub:`03low`\ (bits 7--4) B\ :sub:`02low`\ (bits 3--0) + + - .. row 2 + + - start + 6: + + - G\ :sub:`10high` + + - R\ :sub:`11high` + + - R\ :sub:`11low`\ (bits 7--4) G\ :sub:`10low`\ (bits 3--0) + + - G\ :sub:`12high` + + - R\ :sub:`13high` + + - R\ :sub:`13low`\ (bits 3--2) G\ :sub:`12low`\ (bits 3--0) + + - .. row 3 + + - start + 12: + + - B\ :sub:`20high` + + - G\ :sub:`21high` + + - G\ :sub:`21low`\ (bits 7--4) B\ :sub:`20low`\ (bits 3--0) + + - B\ :sub:`22high` + + - G\ :sub:`23high` + + - G\ :sub:`23low`\ (bits 7--4) B\ :sub:`22low`\ (bits 3--0) + + - .. row 4 + + - start + 18: + + - G\ :sub:`30high` + + - R\ :sub:`31high` + + - R\ :sub:`31low`\ (bits 7--4) G\ :sub:`30low`\ (bits 3--0) + + - G\ :sub:`32high` + + - R\ :sub:`33high` + + - R\ :sub:`33low`\ (bits 3--2) G\ :sub:`32low`\ (bits 3--0) diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index cab63bb49c97..b60a6b0841d1 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1195,10 +1195,6 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_SGBRG10: descr = "10-bit Bayer GBGB/RGRG"; break; case V4L2_PIX_FMT_SGRBG10: descr = "10-bit Bayer GRGR/BGBG"; break; case V4L2_PIX_FMT_SRGGB10: descr = "10-bit Bayer RGRG/GBGB"; break; - case V4L2_PIX_FMT_SBGGR12: descr = "12-bit Bayer BGBG/GRGR"; break; - case V4L2_PIX_FMT_SGBRG12: descr = "12-bit Bayer GBGB/RGRG"; break; - case V4L2_PIX_FMT_SGRBG12: descr = "12-bit Bayer GRGR/BGBG"; break; - case V4L2_PIX_FMT_SRGGB12: descr = "12-bit Bayer RGRG/GBGB"; break; case V4L2_PIX_FMT_SBGGR10P: descr = "10-bit Bayer BGBG/GRGR Packed"; break; case V4L2_PIX_FMT_SGBRG10P: descr = "10-bit Bayer GBGB/RGRG Packed"; break; case V4L2_PIX_FMT_SGRBG10P: descr = "10-bit Bayer GRGR/BGBG Packed"; break; @@ -1211,6 +1207,14 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_SGBRG10DPCM8: descr = "8-bit Bayer GBGB/RGRG (DPCM)"; break; case V4L2_PIX_FMT_SGRBG10DPCM8: descr = "8-bit Bayer GRGR/BGBG (DPCM)"; break; case V4L2_PIX_FMT_SRGGB10DPCM8: descr = "8-bit Bayer RGRG/GBGB (DPCM)"; break; + case V4L2_PIX_FMT_SBGGR12: descr = "12-bit Bayer BGBG/GRGR"; break; + case V4L2_PIX_FMT_SGBRG12: descr = "12-bit Bayer GBGB/RGRG"; break; + case V4L2_PIX_FMT_SGRBG12: descr = "12-bit Bayer GRGR/BGBG"; break; + case V4L2_PIX_FMT_SRGGB12: descr = "12-bit Bayer RGRG/GBGB"; break; + case V4L2_PIX_FMT_SBGGR12P: descr = "12-bit Bayer BGBG/GRGR Packed"; break; + case V4L2_PIX_FMT_SGBRG12P: descr = "12-bit Bayer GBGB/RGRG Packed"; break; + case V4L2_PIX_FMT_SGRBG12P: descr = "12-bit Bayer GRGR/BGBG Packed"; break; + case V4L2_PIX_FMT_SRGGB12P: descr = "12-bit Bayer RGRG/GBGB Packed"; break; case V4L2_PIX_FMT_SBGGR16: descr = "16-bit Bayer BGBG/GRGR"; break; case V4L2_PIX_FMT_SGBRG16: descr = "16-bit Bayer GBGB/RGRG"; break; case V4L2_PIX_FMT_SGRBG16: descr = "16-bit Bayer GRGR/BGBG"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 45cf7359822c..185d6a0acc06 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -603,6 +603,11 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_SGBRG12 v4l2_fourcc('G', 'B', '1', '2') /* 12 GBGB.. RGRG.. */ #define V4L2_PIX_FMT_SGRBG12 v4l2_fourcc('B', 'A', '1', '2') /* 12 GRGR.. BGBG.. */ #define V4L2_PIX_FMT_SRGGB12 v4l2_fourcc('R', 'G', '1', '2') /* 12 RGRG.. GBGB.. */ + /* 12bit raw bayer packed, 6 bytes for every 4 pixels */ +#define V4L2_PIX_FMT_SBGGR12P v4l2_fourcc('p', 'B', 'C', 'C') +#define V4L2_PIX_FMT_SGBRG12P v4l2_fourcc('p', 'G', 'C', 'C') +#define V4L2_PIX_FMT_SGRBG12P v4l2_fourcc('p', 'g', 'C', 'C') +#define V4L2_PIX_FMT_SRGGB12P v4l2_fourcc('p', 'R', 'C', 'C') #define V4L2_PIX_FMT_SBGGR16 v4l2_fourcc('B', 'Y', 'R', '2') /* 16 BGBG.. GRGR.. */ #define V4L2_PIX_FMT_SGBRG16 v4l2_fourcc('G', 'B', '1', '6') /* 16 GBGB.. RGRG.. */ #define V4L2_PIX_FMT_SGRBG16 v4l2_fourcc('G', 'R', '1', '6') /* 16 GRGR.. BGBG.. */ -- cgit v1.2.3-71-gd317 From a9e4998073d49a762a154a6b48a332ec6cb8e6b1 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 20 Jul 2017 18:12:07 -0400 Subject: media: dvb_frontend: ensure that inital front end status initialized The fe_status variable s is not initialized meaning it can have any random garbage status. This could be problematic if fe->ops.tune is false as s is not updated by the call to fe->ops.tune() and a subsequent check on the change status will using a garbage value. Fix this by adding FE_NONE to the enum fe_status and initializing s to this. Detected by CoverityScan, CID#112887 ("Uninitialized scalar variable") Signed-off-by: Colin Ian King Reviewed-by: Shuah Khan Signed-off-by: Mauro Carvalho Chehab --- drivers/media/dvb-core/dvb_frontend.c | 2 +- include/uapi/linux/dvb/frontend.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c index e3fff8f64d37..18cc3bbc699c 100644 --- a/drivers/media/dvb-core/dvb_frontend.c +++ b/drivers/media/dvb-core/dvb_frontend.c @@ -631,7 +631,7 @@ static int dvb_frontend_thread(void *data) struct dvb_frontend *fe = data; struct dtv_frontend_properties *c = &fe->dtv_property_cache; struct dvb_frontend_private *fepriv = fe->frontend_priv; - enum fe_status s; + enum fe_status s = FE_NONE; enum dvbfe_algo algo; bool re_tune = false; bool semheld = false; diff --git a/include/uapi/linux/dvb/frontend.h b/include/uapi/linux/dvb/frontend.h index 00a20cd21ee2..afc3972b0879 100644 --- a/include/uapi/linux/dvb/frontend.h +++ b/include/uapi/linux/dvb/frontend.h @@ -127,6 +127,7 @@ enum fe_sec_mini_cmd { * to reset DiSEqC, tone and parameters */ enum fe_status { + FE_NONE = 0x00, FE_HAS_SIGNAL = 0x01, FE_HAS_CARRIER = 0x02, FE_HAS_VITERBI = 0x04, -- cgit v1.2.3-71-gd317 From ddc088238cd6988bb4ac3776f403d7ff9d3c7a63 Mon Sep 17 00:00:00 2001 From: Pawel Baldysiak Date: Wed, 16 Aug 2017 17:13:45 +0200 Subject: md: Runtime support for multiple ppls Increase PPL area to 1MB and use it as circular buffer to store PPL. The entry with highest generation number is the latest one. If PPL to be written is larger then space left in a buffer, rewind the buffer to the start (don't wrap it). Signed-off-by: Pawel Baldysiak Signed-off-by: Artur Paszkiewicz Signed-off-by: Shaohua Li --- drivers/md/md.c | 16 +++++++++++++--- drivers/md/md.h | 1 + drivers/md/raid0.c | 3 ++- drivers/md/raid1.c | 3 ++- drivers/md/raid5-ppl.c | 43 +++++++++++++++++++++++++++++++++++++++--- drivers/md/raid5.c | 1 + include/uapi/linux/raid/md_p.h | 4 +++- 7 files changed, 62 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/md/md.c b/drivers/md/md.c index a74dc9963822..a7876237de10 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1536,7 +1536,8 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ } else if (sb->bblog_offset != 0) rdev->badblocks.shift = 0; - if (le32_to_cpu(sb->feature_map) & MD_FEATURE_PPL) { + if ((le32_to_cpu(sb->feature_map) & + (MD_FEATURE_PPL | MD_FEATURE_MULTIPLE_PPLS))) { rdev->ppl.offset = (__s16)le16_to_cpu(sb->ppl.offset); rdev->ppl.size = le16_to_cpu(sb->ppl.size); rdev->ppl.sector = rdev->sb_start + rdev->ppl.offset; @@ -1655,10 +1656,15 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL) set_bit(MD_HAS_JOURNAL, &mddev->flags); - if (le32_to_cpu(sb->feature_map) & MD_FEATURE_PPL) { + if (le32_to_cpu(sb->feature_map) & + (MD_FEATURE_PPL | MD_FEATURE_MULTIPLE_PPLS)) { if (le32_to_cpu(sb->feature_map) & (MD_FEATURE_BITMAP_OFFSET | MD_FEATURE_JOURNAL)) return -EINVAL; + if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_PPL) && + (le32_to_cpu(sb->feature_map) & + MD_FEATURE_MULTIPLE_PPLS)) + return -EINVAL; set_bit(MD_HAS_PPL, &mddev->flags); } } else if (mddev->pers == NULL) { @@ -1875,7 +1881,11 @@ retry: sb->feature_map |= cpu_to_le32(MD_FEATURE_JOURNAL); if (test_bit(MD_HAS_PPL, &mddev->flags)) { - sb->feature_map |= cpu_to_le32(MD_FEATURE_PPL); + if (test_bit(MD_HAS_MULTIPLE_PPLS, &mddev->flags)) + sb->feature_map |= + cpu_to_le32(MD_FEATURE_MULTIPLE_PPLS); + else + sb->feature_map |= cpu_to_le32(MD_FEATURE_PPL); sb->ppl.offset = cpu_to_le16(rdev->ppl.offset); sb->ppl.size = cpu_to_le16(rdev->ppl.size); } diff --git a/drivers/md/md.h b/drivers/md/md.h index 09db03455801..d4bdfa5c223b 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -236,6 +236,7 @@ enum mddev_flags { * never cause the array to become failed. */ MD_HAS_PPL, /* The raid array has PPL feature set */ + MD_HAS_MULTIPLE_PPLS, /* The raid array has multiple PPLs feature set */ }; enum mddev_sb_flags { diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 6fb81704aff4..fd5e8e5efbef 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -30,7 +30,8 @@ ((1L << MD_HAS_JOURNAL) | \ (1L << MD_JOURNAL_CLEAN) | \ (1L << MD_FAILFAST_SUPPORTED) |\ - (1L << MD_HAS_PPL)) + (1L << MD_HAS_PPL) | \ + (1L << MD_HAS_MULTIPLE_PPLS)) static int raid0_congested(struct mddev *mddev, int bits) { diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 79474f47eeef..1f5bd9475dc1 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -48,7 +48,8 @@ #define UNSUPPORTED_MDDEV_FLAGS \ ((1L << MD_HAS_JOURNAL) | \ (1L << MD_JOURNAL_CLEAN) | \ - (1L << MD_HAS_PPL)) + (1L << MD_HAS_PPL) | \ + (1L << MD_HAS_MULTIPLE_PPLS)) /* * Number of guaranteed r1bios in case of extreme VM load: diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index 44ad5baf3206..b313f17a6260 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -87,6 +87,8 @@ * The current io_unit accepting new stripes is always at the end of the list. */ +#define PPL_SPACE_SIZE (128 * 1024) + struct ppl_conf { struct mddev *mddev; @@ -122,6 +124,10 @@ struct ppl_log { * always at the end of io_list */ spinlock_t io_list_lock; struct list_head io_list; /* all io_units of this log */ + + sector_t next_io_sector; + unsigned int entry_space; + bool use_multippl; }; #define PPL_IO_INLINE_BVECS 32 @@ -264,13 +270,12 @@ static int ppl_log_stripe(struct ppl_log *log, struct stripe_head *sh) int i; sector_t data_sector = 0; int data_disks = 0; - unsigned int entry_space = (log->rdev->ppl.size << 9) - PPL_HEADER_SIZE; struct r5conf *conf = sh->raid_conf; pr_debug("%s: stripe: %llu\n", __func__, (unsigned long long)sh->sector); /* check if current io_unit is full */ - if (io && (io->pp_size == entry_space || + if (io && (io->pp_size == log->entry_space || io->entries_count == PPL_HDR_MAX_ENTRIES)) { pr_debug("%s: add io_unit blocked by seq: %llu\n", __func__, io->seq); @@ -451,12 +456,25 @@ static void ppl_submit_iounit(struct ppl_io_unit *io) pplhdr->entries_count = cpu_to_le32(io->entries_count); pplhdr->checksum = cpu_to_le32(~crc32c_le(~0, pplhdr, PPL_HEADER_SIZE)); + /* Rewind the buffer if current PPL is larger then remaining space */ + if (log->use_multippl && + log->rdev->ppl.sector + log->rdev->ppl.size - log->next_io_sector < + (PPL_HEADER_SIZE + io->pp_size) >> 9) + log->next_io_sector = log->rdev->ppl.sector; + + bio->bi_end_io = ppl_log_endio; bio->bi_opf = REQ_OP_WRITE | REQ_FUA; bio->bi_bdev = log->rdev->bdev; - bio->bi_iter.bi_sector = log->rdev->ppl.sector; + bio->bi_iter.bi_sector = log->next_io_sector; bio_add_page(bio, io->header_page, PAGE_SIZE, 0); + pr_debug("%s: log->current_io_sector: %llu\n", __func__, + (unsigned long long)log->next_io_sector); + + if (log->use_multippl) + log->next_io_sector += (PPL_HEADER_SIZE + io->pp_size) >> 9; + list_for_each_entry(sh, &io->stripe_list, log_list) { /* entries for full stripe writes have no partial parity */ if (test_bit(STRIPE_FULL_WRITE, &sh->state)) @@ -1031,6 +1049,7 @@ static int ppl_load(struct ppl_conf *ppl_conf) static void __ppl_exit_log(struct ppl_conf *ppl_conf) { clear_bit(MD_HAS_PPL, &ppl_conf->mddev->flags); + clear_bit(MD_HAS_MULTIPLE_PPLS, &ppl_conf->mddev->flags); kfree(ppl_conf->child_logs); @@ -1099,6 +1118,22 @@ static int ppl_validate_rdev(struct md_rdev *rdev) return 0; } +static void ppl_init_child_log(struct ppl_log *log, struct md_rdev *rdev) +{ + if ((rdev->ppl.size << 9) >= (PPL_SPACE_SIZE + + PPL_HEADER_SIZE) * 2) { + log->use_multippl = true; + set_bit(MD_HAS_MULTIPLE_PPLS, + &log->ppl_conf->mddev->flags); + log->entry_space = PPL_SPACE_SIZE; + } else { + log->use_multippl = false; + log->entry_space = (log->rdev->ppl.size << 9) - + PPL_HEADER_SIZE; + } + log->next_io_sector = rdev->ppl.sector; +} + int ppl_init_log(struct r5conf *conf) { struct ppl_conf *ppl_conf; @@ -1196,6 +1231,7 @@ int ppl_init_log(struct r5conf *conf) q = bdev_get_queue(rdev->bdev); if (test_bit(QUEUE_FLAG_WC, &q->queue_flags)) need_cache_flush = true; + ppl_init_child_log(log, rdev); } } @@ -1261,6 +1297,7 @@ int ppl_modify_log(struct r5conf *conf, struct md_rdev *rdev, bool add) if (!ret) { log->rdev = rdev; ret = ppl_write_empty_header(log); + ppl_init_child_log(log, rdev); } } else { log->rdev = NULL; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 6af57c6c0533..049a958d3c1e 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -7236,6 +7236,7 @@ static int raid5_run(struct mddev *mddev) pr_warn("md/raid:%s: using journal device and PPL not allowed - disabling PPL\n", mdname(mddev)); clear_bit(MD_HAS_PPL, &mddev->flags); + clear_bit(MD_HAS_MULTIPLE_PPLS, &mddev->flags); } if (mddev->private == NULL) diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h index d500bd224979..b9197976b660 100644 --- a/include/uapi/linux/raid/md_p.h +++ b/include/uapi/linux/raid/md_p.h @@ -324,9 +324,10 @@ struct mdp_superblock_1 { #define MD_FEATURE_RECOVERY_BITMAP 128 /* recovery that is happening * is guided by bitmap. */ -#define MD_FEATURE_CLUSTERED 256 /* clustered MD */ +#define MD_FEATURE_CLUSTERED 256 /* clustered MD */ #define MD_FEATURE_JOURNAL 512 /* support write cache */ #define MD_FEATURE_PPL 1024 /* support PPL */ +#define MD_FEATURE_MULTIPLE_PPLS 2048 /* support for multiple PPLs */ #define MD_FEATURE_ALL (MD_FEATURE_BITMAP_OFFSET \ |MD_FEATURE_RECOVERY_OFFSET \ |MD_FEATURE_RESHAPE_ACTIVE \ @@ -338,6 +339,7 @@ struct mdp_superblock_1 { |MD_FEATURE_CLUSTERED \ |MD_FEATURE_JOURNAL \ |MD_FEATURE_PPL \ + |MD_FEATURE_MULTIPLE_PPLS \ ) struct r5l_payload_header { -- cgit v1.2.3-71-gd317 From 7a14724f54bf9889fcb1a9f1d4aa4e1d2e969d93 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 28 Aug 2017 08:33:20 -0700 Subject: libnvdimm: clean up command definitions Remove the command payloads that do not have an associated libnvdimm ioctl. I.e. remove the payloads that would only ever be carried in the ND_CMD_CALL envelope. This prevents userspace from growing unnecessary dependencies on this kernel header when userspace already has everything it needs to craft and send these commands. Cc: Jerry Hoemann Reported-by: Yasunori Goto Signed-off-by: Dan Williams --- include/uapi/linux/ndctl.h | 37 ------------------------------------- 1 file changed, 37 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h index 6d3c54264d8e..3f03567631cb 100644 --- a/include/uapi/linux/ndctl.h +++ b/include/uapi/linux/ndctl.h @@ -145,43 +145,6 @@ struct nd_cmd_clear_error { __u64 cleared; } __packed; -struct nd_cmd_trans_spa { - __u64 spa; - __u32 status; - __u8 flags; - __u8 _reserved[3]; - __u64 trans_length; - __u32 num_nvdimms; - struct nd_nvdimm_device { - __u32 nfit_device_handle; - __u32 _reserved; - __u64 dpa; - } __packed devices[0]; - -} __packed; - -struct nd_cmd_ars_err_inj { - __u64 err_inj_spa_range_base; - __u64 err_inj_spa_range_length; - __u8 err_inj_options; - __u32 status; -} __packed; - -struct nd_cmd_ars_err_inj_clr { - __u64 err_inj_clr_spa_range_base; - __u64 err_inj_clr_spa_range_length; - __u32 status; -} __packed; - -struct nd_cmd_ars_err_inj_stat { - __u32 status; - __u32 inj_err_rec_count; - struct nd_error_stat_query_record { - __u64 err_inj_stat_spa_range_base; - __u64 err_inj_stat_spa_range_length; - } __packed record[0]; -} __packed; - enum { ND_CMD_IMPLEMENTED = 0, -- cgit v1.2.3-71-gd317 From 464bc0fd6273d518aee79fbd37211dd9bc35d863 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 28 Aug 2017 07:10:04 -0700 Subject: bpf: convert sockmap field attach_bpf_fd2 to type In the initial sockmap API we provided strparser and verdict programs using a single attach command by extending the attach API with a the attach_bpf_fd2 field. However, if we add other programs in the future we will be adding a field for every new possible type, attach_bpf_fd(3,4,..). This seems a bit clumsy for an API. So lets push the programs using two new type fields. BPF_SK_SKB_STREAM_PARSER BPF_SK_SKB_STREAM_VERDICT This has the advantage of having a readable name and can easily be extended in the future. Updates to samples and sockmap included here also generalize tests slightly to support upcoming patch for multiple map support. Signed-off-by: John Fastabend Fixes: 174a79ff9515 ("bpf: sockmap with sk redirect support") Suggested-by: Alexei Starovoitov Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 10 +- include/uapi/linux/bpf.h | 9 +- kernel/bpf/sockmap.c | 25 ++-- kernel/bpf/syscall.c | 38 ++---- samples/sockmap/sockmap_kern.c | 6 +- samples/sockmap/sockmap_user.c | 12 +- tools/include/uapi/linux/bpf.h | 9 +- tools/lib/bpf/bpf.c | 14 +-- tools/lib/bpf/bpf.h | 4 - tools/testing/selftests/bpf/bpf_helpers.h | 3 +- tools/testing/selftests/bpf/sockmap_parse_prog.c | 2 +- tools/testing/selftests/bpf/sockmap_verdict_prog.c | 2 +- tools/testing/selftests/bpf/test_maps.c | 133 +++++++++------------ 13 files changed, 116 insertions(+), 151 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 830f472d8df5..c2cb1b5c094e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -39,8 +39,6 @@ struct bpf_map_ops { void (*map_fd_put_ptr)(void *ptr); u32 (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); u32 (*map_fd_sys_lookup_elem)(void *ptr); - int (*map_attach)(struct bpf_map *map, - struct bpf_prog *p1, struct bpf_prog *p2); }; struct bpf_map { @@ -387,11 +385,19 @@ static inline void __dev_map_flush(struct bpf_map *map) #if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL) struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key); +int sock_map_attach_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type); #else static inline struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key) { return NULL; } + +static inline int sock_map_attach_prog(struct bpf_map *map, + struct bpf_prog *prog, + u32 type) +{ + return -EOPNOTSUPP; +} #endif /* verifier prototypes for helper functions called from eBPF programs */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 843818dff96d..97227be3690c 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -136,7 +136,8 @@ enum bpf_attach_type { BPF_CGROUP_INET_EGRESS, BPF_CGROUP_INET_SOCK_CREATE, BPF_CGROUP_SOCK_OPS, - BPF_CGROUP_SMAP_INGRESS, + BPF_SK_SKB_STREAM_PARSER, + BPF_SK_SKB_STREAM_VERDICT, __MAX_BPF_ATTACH_TYPE }; @@ -224,7 +225,6 @@ union bpf_attr { __u32 attach_bpf_fd; /* eBPF program to attach */ __u32 attach_type; __u32 attach_flags; - __u32 attach_bpf_fd2; }; struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */ @@ -580,14 +580,11 @@ union bpf_attr { * @flags: reserved for future use * Return: SK_REDIRECT * - * int bpf_sock_map_update(skops, map, key, flags, map_flags) + * int bpf_sock_map_update(skops, map, key, flags) * @skops: pointer to bpf_sock_ops * @map: pointer to sockmap to update * @key: key to insert/update sock in map * @flags: same flags as map update elem - * @map_flags: sock map specific flags - * bit 1: Enable strparser - * other bits: reserved */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 617c239590c2..cf570d108fd5 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -723,20 +723,24 @@ out: return err; } -static int sock_map_attach_prog(struct bpf_map *map, - struct bpf_prog *parse, - struct bpf_prog *verdict) +int sock_map_attach_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); - struct bpf_prog *_parse, *_verdict; + struct bpf_prog *orig; - _parse = xchg(&stab->bpf_parse, parse); - _verdict = xchg(&stab->bpf_verdict, verdict); + switch (type) { + case BPF_SK_SKB_STREAM_PARSER: + orig = xchg(&stab->bpf_parse, prog); + break; + case BPF_SK_SKB_STREAM_VERDICT: + orig = xchg(&stab->bpf_verdict, prog); + break; + default: + return -EOPNOTSUPP; + } - if (_parse) - bpf_prog_put(_parse); - if (_verdict) - bpf_prog_put(_verdict); + if (orig) + bpf_prog_put(orig); return 0; } @@ -777,7 +781,6 @@ const struct bpf_map_ops sock_map_ops = { .map_get_next_key = sock_map_get_next_key, .map_update_elem = sock_map_update_elem, .map_delete_elem = sock_map_delete_elem, - .map_attach = sock_map_attach_prog, }; BPF_CALL_5(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 9378f3ba2cbf..021a05d9d800 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1093,12 +1093,12 @@ static int bpf_obj_get(const union bpf_attr *attr) #ifdef CONFIG_CGROUP_BPF -#define BPF_PROG_ATTACH_LAST_FIELD attach_bpf_fd2 +#define BPF_PROG_ATTACH_LAST_FIELD attach_flags -static int sockmap_get_from_fd(const union bpf_attr *attr, int ptype) +static int sockmap_get_from_fd(const union bpf_attr *attr) { - struct bpf_prog *prog1, *prog2; int ufd = attr->target_fd; + struct bpf_prog *prog; struct bpf_map *map; struct fd f; int err; @@ -1108,29 +1108,16 @@ static int sockmap_get_from_fd(const union bpf_attr *attr, int ptype) if (IS_ERR(map)) return PTR_ERR(map); - if (!map->ops->map_attach) { - fdput(f); - return -EOPNOTSUPP; - } - - prog1 = bpf_prog_get_type(attr->attach_bpf_fd, ptype); - if (IS_ERR(prog1)) { + prog = bpf_prog_get_type(attr->attach_bpf_fd, BPF_PROG_TYPE_SK_SKB); + if (IS_ERR(prog)) { fdput(f); - return PTR_ERR(prog1); - } - - prog2 = bpf_prog_get_type(attr->attach_bpf_fd2, ptype); - if (IS_ERR(prog2)) { - fdput(f); - bpf_prog_put(prog1); - return PTR_ERR(prog2); + return PTR_ERR(prog); } - err = map->ops->map_attach(map, prog1, prog2); + err = sock_map_attach_prog(map, prog, attr->attach_type); if (err) { fdput(f); - bpf_prog_put(prog1); - bpf_prog_put(prog2); + bpf_prog_put(prog); return err; } @@ -1165,16 +1152,13 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_CGROUP_SOCK_OPS: ptype = BPF_PROG_TYPE_SOCK_OPS; break; - case BPF_CGROUP_SMAP_INGRESS: - ptype = BPF_PROG_TYPE_SK_SKB; - break; + case BPF_SK_SKB_STREAM_PARSER: + case BPF_SK_SKB_STREAM_VERDICT: + return sockmap_get_from_fd(attr); default: return -EINVAL; } - if (attr->attach_type == BPF_CGROUP_SMAP_INGRESS) - return sockmap_get_from_fd(attr, ptype); - prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); if (IS_ERR(prog)) return PTR_ERR(prog); diff --git a/samples/sockmap/sockmap_kern.c b/samples/sockmap/sockmap_kern.c index 6ff986f7059b..f9b38ef82dc2 100644 --- a/samples/sockmap/sockmap_kern.c +++ b/samples/sockmap/sockmap_kern.c @@ -82,8 +82,7 @@ int bpf_sockmap(struct bpf_sock_ops *skops) if (lport == 10000) { ret = 1; err = bpf_sock_map_update(skops, &sock_map, &ret, - BPF_NOEXIST, - BPF_SOCKMAP_STRPARSER); + BPF_NOEXIST); bpf_printk("passive(%i -> %i) map ctx update err: %d\n", lport, bpf_ntohl(rport), err); } @@ -95,8 +94,7 @@ int bpf_sockmap(struct bpf_sock_ops *skops) if (bpf_ntohl(rport) == 10001) { ret = 10; err = bpf_sock_map_update(skops, &sock_map, &ret, - BPF_NOEXIST, - BPF_SOCKMAP_STRPARSER); + BPF_NOEXIST); bpf_printk("active(%i -> %i) map ctx update err: %d\n", lport, bpf_ntohl(rport), err); } diff --git a/samples/sockmap/sockmap_user.c b/samples/sockmap/sockmap_user.c index fb78f5abefb4..7cc9d228216f 100644 --- a/samples/sockmap/sockmap_user.c +++ b/samples/sockmap/sockmap_user.c @@ -256,8 +256,16 @@ int main(int argc, char **argv) } /* Attach programs to sockmap */ - err = __bpf_prog_attach(prog_fd[0], prog_fd[1], map_fd[0], - BPF_CGROUP_SMAP_INGRESS, 0); + err = bpf_prog_attach(prog_fd[0], map_fd[0], + BPF_SK_SKB_STREAM_PARSER, 0); + if (err) { + fprintf(stderr, "ERROR: bpf_prog_attach (sockmap): %d (%s)\n", + err, strerror(errno)); + return err; + } + + err = bpf_prog_attach(prog_fd[1], map_fd[0], + BPF_SK_SKB_STREAM_VERDICT, 0); if (err) { fprintf(stderr, "ERROR: bpf_prog_attach (sockmap): %d (%s)\n", err, strerror(errno)); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index f8f6377fd541..09ac590eefb1 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -136,7 +136,8 @@ enum bpf_attach_type { BPF_CGROUP_INET_EGRESS, BPF_CGROUP_INET_SOCK_CREATE, BPF_CGROUP_SOCK_OPS, - BPF_CGROUP_SMAP_INGRESS, + BPF_SK_SKB_STREAM_PARSER, + BPF_SK_SKB_STREAM_VERDICT, __MAX_BPF_ATTACH_TYPE }; @@ -227,7 +228,6 @@ union bpf_attr { __u32 attach_bpf_fd; /* eBPF program to attach */ __u32 attach_type; __u32 attach_flags; - __u32 attach_bpf_fd2; }; struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */ @@ -572,14 +572,11 @@ union bpf_attr { * @flags: reserved for future use * Return: SK_REDIRECT * - * int bpf_sock_map_update(skops, map, key, flags, map_flags) + * int bpf_sock_map_update(skops, map, key, flags) * @skops: pointer to bpf_sock_ops * @map: pointer to sockmap to update * @key: key to insert/update sock in map * @flags: same flags as map update elem - * @map_flags: sock map specific flags - * bit 1: Enable strparser - * other bits: reserved */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index a0717610b116..1d6907d379c9 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -235,28 +235,20 @@ int bpf_obj_get(const char *pathname) return sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr)); } -int __bpf_prog_attach(int prog_fd1, int prog_fd2, int target_fd, - enum bpf_attach_type type, - unsigned int flags) +int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type, + unsigned int flags) { union bpf_attr attr; bzero(&attr, sizeof(attr)); attr.target_fd = target_fd; - attr.attach_bpf_fd = prog_fd1; - attr.attach_bpf_fd2 = prog_fd2; + attr.attach_bpf_fd = prog_fd; attr.attach_type = type; attr.attach_flags = flags; return sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr)); } -int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type, - unsigned int flags) -{ - return __bpf_prog_attach(prog_fd, 0, target_fd, type, flags); -} - int bpf_prog_detach(int target_fd, enum bpf_attach_type type) { union bpf_attr attr; diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 90e9d4e85d08..b8ea5843c39e 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -56,10 +56,6 @@ int bpf_obj_pin(int fd, const char *pathname); int bpf_obj_get(const char *pathname); int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type, unsigned int flags); -int __bpf_prog_attach(int prog1, int prog2, - int attachable_fd, - enum bpf_attach_type type, - unsigned int flags); int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type); int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size, void *data_out, __u32 *size_out, __u32 *retval, diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index 98f3be26d390..36fb9161b34a 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -68,8 +68,7 @@ static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval, static int (*bpf_sk_redirect_map)(void *map, int key, int flags) = (void *) BPF_FUNC_sk_redirect_map; static int (*bpf_sock_map_update)(void *map, void *key, void *value, - unsigned long long flags, - unsigned long long map_lags) = + unsigned long long flags) = (void *) BPF_FUNC_sock_map_update; diff --git a/tools/testing/selftests/bpf/sockmap_parse_prog.c b/tools/testing/selftests/bpf/sockmap_parse_prog.c index 8b5453158399..710f43f42dc4 100644 --- a/tools/testing/selftests/bpf/sockmap_parse_prog.c +++ b/tools/testing/selftests/bpf/sockmap_parse_prog.c @@ -30,7 +30,7 @@ int bpf_prog1(struct __sk_buff *skb) */ d[0] = 1; - bpf_printk("data[0] = (%u): local_port %i remote %i\n", + bpf_printk("parse: data[0] = (%u): local_port %i remote %i\n", d[0], lport, bpf_ntohl(rport)); return skb->len; } diff --git a/tools/testing/selftests/bpf/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/sockmap_verdict_prog.c index d5f9447b3808..0573c1db2519 100644 --- a/tools/testing/selftests/bpf/sockmap_verdict_prog.c +++ b/tools/testing/selftests/bpf/sockmap_verdict_prog.c @@ -40,7 +40,7 @@ int bpf_prog2(struct __sk_buff *skb) d[6] = 0xe; d[7] = 0xf; - bpf_printk("data[0] = (%u): local_port %i remote %i\n", + bpf_printk("verdict: data[0] = (%u): local_port %i remote %i redirect 5\n", d[0], lport, bpf_ntohl(rport)); return bpf_sk_redirect_map(&sock_map, 5, 0); } diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 40b2d1faf02b..6df6e6257424 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -547,20 +547,26 @@ static void test_sockmap(int task, void *data) goto out_sockmap; } - /* Nothing attached so these should fail */ + /* Test update without programs */ for (i = 0; i < 6; i++) { err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY); - if (!err) { - printf("Failed invalid update sockmap '%i:%i'\n", + if (err) { + printf("Failed noprog update sockmap '%i:%i'\n", i, sfd[i]); goto out_sockmap; } } /* Test attaching bad fds */ - err = __bpf_prog_attach(-1, -2, fd, BPF_CGROUP_SMAP_INGRESS, 0); + err = bpf_prog_attach(-1, fd, BPF_SK_SKB_STREAM_PARSER, 0); if (!err) { - printf("Failed invalid prog attach\n"); + printf("Failed invalid parser prog attach\n"); + goto out_sockmap; + } + + err = bpf_prog_attach(-1, fd, BPF_SK_SKB_STREAM_VERDICT, 0); + if (!err) { + printf("Failed invalid verdict prog attach\n"); goto out_sockmap; } @@ -591,14 +597,21 @@ static void test_sockmap(int task, void *data) goto out_sockmap; } - err = __bpf_prog_attach(parse_prog, verdict_prog, map_fd, - BPF_CGROUP_SMAP_INGRESS, 0); + err = bpf_prog_attach(parse_prog, map_fd, + BPF_SK_SKB_STREAM_PARSER, 0); + if (err) { + printf("Failed bpf prog attach\n"); + goto out_sockmap; + } + + err = bpf_prog_attach(verdict_prog, map_fd, + BPF_SK_SKB_STREAM_VERDICT, 0); if (err) { printf("Failed bpf prog attach\n"); goto out_sockmap; } - /* Test map update elem */ + /* Test map update elem afterwards fd lives in fd and map_fd */ for (i = 0; i < 6; i++) { err = bpf_map_update_elem(map_fd, &i, &sfd[i], BPF_ANY); if (err) { @@ -649,96 +662,68 @@ static void test_sockmap(int task, void *data) goto out_sockmap; } - /* Delete the reset of the elems include some NULL elems */ - for (i = 0; i < 6; i++) { - err = bpf_map_delete_elem(map_fd, &i); - if (err && (i == 0 || i == 1 || i >= 4)) { - printf("Failed delete sockmap %i '%i:%i'\n", - err, i, sfd[i]); - goto out_sockmap; - } else if (!err && (i == 2 || i == 3)) { - printf("Failed null delete sockmap %i '%i:%i'\n", - err, i, sfd[i]); - goto out_sockmap; - } - } - - /* Test having multiple SMAPs open and active on same fds */ - err = __bpf_prog_attach(parse_prog, verdict_prog, fd, - BPF_CGROUP_SMAP_INGRESS, 0); - if (err) { - printf("Failed fd bpf prog attach\n"); - goto out_sockmap; - } - - for (i = 0; i < 6; i++) { - err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY); - if (err) { - printf("Failed fd update sockmap %i '%i:%i'\n", - err, i, sfd[i]); - goto out_sockmap; - } - } - - /* Test duplicate socket add of NOEXIST, ANY and EXIST */ - i = 0; + /* Push fd into same slot */ + i = 2; err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_NOEXIST); if (!err) { - printf("Failed BPF_NOEXIST create\n"); + printf("Failed allowed sockmap dup slot BPF_NOEXIST\n"); goto out_sockmap; } err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY); if (err) { - printf("Failed sockmap update BPF_ANY\n"); + printf("Failed sockmap update new slot BPF_ANY\n"); goto out_sockmap; } err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_EXIST); if (err) { - printf("Failed sockmap update BPF_EXIST\n"); + printf("Failed sockmap update new slot BPF_EXIST\n"); goto out_sockmap; } - /* The above were pushing fd into same slot try different slot now */ - i = 2; - err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_NOEXIST); - if (!err) { - printf("Failed BPF_NOEXIST create\n"); - goto out_sockmap; + /* Delete the elems without programs */ + for (i = 0; i < 6; i++) { + err = bpf_map_delete_elem(fd, &i); + if (err) { + printf("Failed delete sockmap %i '%i:%i'\n", + err, i, sfd[i]); + } } - err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY); + /* Test having multiple maps open and set with programs on same fds */ + err = bpf_prog_attach(parse_prog, fd, + BPF_SK_SKB_STREAM_PARSER, 0); if (err) { - printf("Failed sockmap update BPF_ANY\n"); + printf("Failed fd bpf parse prog attach\n"); goto out_sockmap; } - - err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_EXIST); + err = bpf_prog_attach(verdict_prog, fd, + BPF_SK_SKB_STREAM_VERDICT, 0); if (err) { - printf("Failed sockmap update BPF_EXIST\n"); + printf("Failed fd bpf verdict prog attach\n"); goto out_sockmap; } - /* Try pushing fd into different map, this is not allowed at the - * moment. Which programs would we use? - */ - err = bpf_map_update_elem(map_fd, &i, &sfd[i], BPF_NOEXIST); - if (!err) { - printf("Failed BPF_NOEXIST create\n"); - goto out_sockmap; - } - - err = bpf_map_update_elem(map_fd, &i, &sfd[i], BPF_ANY); - if (!err) { - printf("Failed sockmap update BPF_ANY\n"); - goto out_sockmap; - } - - err = bpf_map_update_elem(map_fd, &i, &sfd[i], BPF_EXIST); - if (!err) { - printf("Failed sockmap update BPF_EXIST\n"); - goto out_sockmap; + for (i = 4; i < 6; i++) { + err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY); + if (!err) { + printf("Failed allowed duplicate programs in update ANY sockmap %i '%i:%i'\n", + err, i, sfd[i]); + goto out_sockmap; + } + err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_NOEXIST); + if (!err) { + printf("Failed allowed duplicate program in update NOEXIST sockmap %i '%i:%i'\n", + err, i, sfd[i]); + goto out_sockmap; + } + err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_EXIST); + if (!err) { + printf("Failed allowed duplicate program in update EXIST sockmap %i '%i:%i'\n", + err, i, sfd[i]); + goto out_sockmap; + } } /* Test map close sockets */ -- cgit v1.2.3-71-gd317 From 2f857d04601a1bb56958b95a9f180bce0e91e5e6 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 28 Aug 2017 07:10:25 -0700 Subject: bpf: sockmap, remove STRPARSER map_flags and add multi-map support The addition of map_flags BPF_SOCKMAP_STRPARSER flags was to handle a specific use case where we want to have BPF parse program disabled on an entry in a sockmap. However, Alexei found the API a bit cumbersome and I agreed. Lets remove the STRPARSER flag and support the use case by allowing socks to be in multiple maps. This allows users to create two maps one with programs attached and one without. When socks are added to maps they now inherit any programs attached to the map. This is a nice generalization and IMO improves the API. The API rules are less ambiguous and do not need a flag: - When a sock is added to a sockmap we have two cases, i. The sock map does not have any attached programs so we can add sock to map without inheriting bpf programs. The sock may exist in 0 or more other maps. ii. The sock map has an attached BPF program. To avoid duplicate bpf programs we only add the sock entry if it does not have an existing strparser/verdict attached, returning -EBUSY if a program is already attached. Otherwise attach the program and inherit strparser/verdict programs from the sock map. This allows for socks to be in a multiple maps for redirects and inherit a BPF program from a single map. Also this patch simplifies the logic around BPF_{EXIST|NOEXIST|ANY} flags. In the original patch I tried to be extra clever and only update map entries when necessary. Now I've decided the complexity is not worth it. If users constantly update an entry with the same sock for no reason (i.e. update an entry without actually changing any parameters on map or sock) we still do an alloc/release. Using this and allowing multiple entries of a sock to exist in a map the logic becomes much simpler. Note: Now that multiple maps are supported the "maps" pointer called when a socket is closed becomes a list of maps to remove the sock from. To keep the map up to date when a sock is added to the sockmap we must add the map/elem in the list. Likewise when it is removed we must remove it from the list. This results in searching the per psock list on delete operation. On TCP_CLOSE events we walk the list and remove the psock from all map/entry locations. I don't see any perf implications in this because at most I have a psock in two maps. If a psock were to be in many maps its possibly this might be noticeable on delete but I can't think of a reason to dup a psock in many maps. The sk_callback_lock is used to protect read/writes to the list. This was convenient because in all locations we were taking the lock anyways just after working on the list. Also the lock is per sock so in normal cases we shouldn't see any contention. Suggested-by: Alexei Starovoitov Fixes: 174a79ff9515 ("bpf: sockmap with sk redirect support") Signed-off-by: John Fastabend Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 3 - kernel/bpf/sockmap.c | 269 +++++++++++++++++++++++++++++------------------ 2 files changed, 165 insertions(+), 107 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 97227be3690c..08c206a863e1 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -143,9 +143,6 @@ enum bpf_attach_type { #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE -/* If BPF_SOCKMAP_STRPARSER is used sockmap will use strparser on receive */ -#define BPF_SOCKMAP_STRPARSER (1U << 0) - /* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command * to the given target_fd cgroup the descendent cgroup will be able to * override effective bpf program that was inherited from this cgroup diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index cf570d108fd5..a6882e54930b 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -13,15 +13,16 @@ /* A BPF sock_map is used to store sock objects. This is primarly used * for doing socket redirect with BPF helper routines. * - * A sock map may have two BPF programs attached to it, a program used - * to parse packets and a program to provide a verdict and redirect - * decision on the packet. If no BPF parse program is provided it is - * assumed that every skb is a "message" (skb->len). Otherwise the - * parse program is attached to strparser and used to build messages - * that may span multiple skbs. The verdict program will either select - * a socket to send/receive the skb on or provide the drop code indicating - * the skb should be dropped. More actions may be added later as needed. - * The default program will drop packets. + * A sock map may have BPF programs attached to it, currently a program + * used to parse packets and a program to provide a verdict and redirect + * decision on the packet are supported. Any programs attached to a sock + * map are inherited by sock objects when they are added to the map. If + * no BPF programs are attached the sock object may only be used for sock + * redirect. + * + * A sock object may be in multiple maps, but can only inherit a single + * parse or verdict program. If adding a sock object to a map would result + * in having multiple parsing programs the update will return an EBUSY error. * * For reference this program is similar to devmap used in XDP context * reviewing these together may be useful. For an example please review @@ -44,15 +45,21 @@ struct bpf_stab { struct sock **sock_map; struct bpf_prog *bpf_parse; struct bpf_prog *bpf_verdict; - refcount_t refcnt; }; enum smap_psock_state { SMAP_TX_RUNNING, }; +struct smap_psock_map_entry { + struct list_head list; + struct sock **entry; +}; + struct smap_psock { struct rcu_head rcu; + /* refcnt is used inside sk_callback_lock */ + u32 refcnt; /* datapath variables */ struct sk_buff_head rxqueue; @@ -66,10 +73,9 @@ struct smap_psock { struct strparser strp; struct bpf_prog *bpf_parse; struct bpf_prog *bpf_verdict; - struct bpf_stab *stab; + struct list_head maps; /* Back reference used when sock callback trigger sockmap operations */ - int key; struct sock *sock; unsigned long state; @@ -83,7 +89,7 @@ struct smap_psock { static inline struct smap_psock *smap_psock_sk(const struct sock *sk) { - return (struct smap_psock *)rcu_dereference_sk_user_data(sk); + return rcu_dereference_sk_user_data(sk); } static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) @@ -149,11 +155,12 @@ static void smap_report_sk_error(struct smap_psock *psock, int err) sk->sk_error_report(sk); } -static void smap_release_sock(struct sock *sock); +static void smap_release_sock(struct smap_psock *psock, struct sock *sock); /* Called with lock_sock(sk) held */ static void smap_state_change(struct sock *sk) { + struct smap_psock_map_entry *e, *tmp; struct smap_psock *psock; struct sock *osk; @@ -184,9 +191,15 @@ static void smap_state_change(struct sock *sk) psock = smap_psock_sk(sk); if (unlikely(!psock)) break; - osk = cmpxchg(&psock->stab->sock_map[psock->key], sk, NULL); - if (osk == sk) - smap_release_sock(sk); + write_lock_bh(&sk->sk_callback_lock); + list_for_each_entry_safe(e, tmp, &psock->maps, list) { + osk = cmpxchg(e->entry, sk, NULL); + if (osk == sk) { + list_del(&e->list); + smap_release_sock(psock, sk); + } + } + write_unlock_bh(&sk->sk_callback_lock); break; default: psock = smap_psock_sk(sk); @@ -289,9 +302,8 @@ static void smap_write_space(struct sock *sk) static void smap_stop_sock(struct smap_psock *psock, struct sock *sk) { - write_lock_bh(&sk->sk_callback_lock); if (!psock->strp_enabled) - goto out; + return; sk->sk_data_ready = psock->save_data_ready; sk->sk_write_space = psock->save_write_space; sk->sk_state_change = psock->save_state_change; @@ -300,8 +312,6 @@ static void smap_stop_sock(struct smap_psock *psock, struct sock *sk) psock->save_state_change = NULL; strp_stop(&psock->strp); psock->strp_enabled = false; -out: - write_unlock_bh(&sk->sk_callback_lock); } static void smap_destroy_psock(struct rcu_head *rcu) @@ -318,9 +328,11 @@ static void smap_destroy_psock(struct rcu_head *rcu) schedule_work(&psock->gc_work); } -static void smap_release_sock(struct sock *sock) +static void smap_release_sock(struct smap_psock *psock, struct sock *sock) { - struct smap_psock *psock = smap_psock_sk(sock); + psock->refcnt--; + if (psock->refcnt) + return; smap_stop_sock(psock, sock); clear_bit(SMAP_TX_RUNNING, &psock->state); @@ -414,6 +426,7 @@ static void sock_map_remove_complete(struct bpf_stab *stab) static void smap_gc_work(struct work_struct *w) { + struct smap_psock_map_entry *e, *tmp; struct smap_psock *psock; psock = container_of(w, struct smap_psock, gc_work); @@ -431,8 +444,10 @@ static void smap_gc_work(struct work_struct *w) if (psock->bpf_verdict) bpf_prog_put(psock->bpf_verdict); - if (refcount_dec_and_test(&psock->stab->refcnt)) - sock_map_remove_complete(psock->stab); + list_for_each_entry_safe(e, tmp, &psock->maps, list) { + list_del(&e->list); + kfree(e); + } sock_put(psock->sock); kfree(psock); @@ -453,6 +468,8 @@ static struct smap_psock *smap_init_psock(struct sock *sock, skb_queue_head_init(&psock->rxqueue); INIT_WORK(&psock->tx_work, smap_tx_work); INIT_WORK(&psock->gc_work, smap_gc_work); + INIT_LIST_HEAD(&psock->maps); + psock->refcnt = 1; rcu_assign_sk_user_data(sock, psock); sock_hold(sock); @@ -503,13 +520,24 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) if (!stab->sock_map) goto free_stab; - refcount_set(&stab->refcnt, 1); return &stab->map; free_stab: kfree(stab); return ERR_PTR(err); } +static void smap_list_remove(struct smap_psock *psock, struct sock **entry) +{ + struct smap_psock_map_entry *e, *tmp; + + list_for_each_entry_safe(e, tmp, &psock->maps, list) { + if (e->entry == entry) { + list_del(&e->list); + break; + } + } +} + static void sock_map_free(struct bpf_map *map) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); @@ -526,13 +554,18 @@ static void sock_map_free(struct bpf_map *map) */ rcu_read_lock(); for (i = 0; i < stab->map.max_entries; i++) { + struct smap_psock *psock; struct sock *sock; sock = xchg(&stab->sock_map[i], NULL); if (!sock) continue; - smap_release_sock(sock); + write_lock_bh(&sock->sk_callback_lock); + psock = smap_psock_sk(sock); + smap_list_remove(psock, &stab->sock_map[i]); + smap_release_sock(psock, sock); + write_unlock_bh(&sock->sk_callback_lock); } rcu_read_unlock(); @@ -541,8 +574,7 @@ static void sock_map_free(struct bpf_map *map) if (stab->bpf_parse) bpf_prog_put(stab->bpf_parse); - if (refcount_dec_and_test(&stab->refcnt)) - sock_map_remove_complete(stab); + sock_map_remove_complete(stab); } static int sock_map_get_next_key(struct bpf_map *map, void *key, void *next_key) @@ -576,6 +608,7 @@ struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key) static int sock_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + struct smap_psock *psock; int k = *(u32 *)key; struct sock *sock; @@ -586,7 +619,17 @@ static int sock_map_delete_elem(struct bpf_map *map, void *key) if (!sock) return -EINVAL; - smap_release_sock(sock); + write_lock_bh(&sock->sk_callback_lock); + psock = smap_psock_sk(sock); + if (!psock) + goto out; + + if (psock->bpf_parse) + smap_stop_sock(psock, sock); + smap_list_remove(psock, &stab->sock_map[k]); + smap_release_sock(psock, sock); +out: + write_unlock_bh(&sock->sk_callback_lock); return 0; } @@ -601,29 +644,34 @@ static int sock_map_delete_elem(struct bpf_map *map, void *key) * and syncd so we are certain all references from the update/lookup/delete * operations as well as references in the data path are no longer in use. * - * A psock object holds a refcnt on the sockmap it is attached to and this is - * not decremented until after a RCU grace period and garbage collection occurs. - * This ensures the map is not free'd until psocks linked to it are removed. The - * map link is used when the independent sock events trigger map deletion. + * Psocks may exist in multiple maps, but only a single set of parse/verdict + * programs may be inherited from the maps it belongs to. A reference count + * is kept with the total number of references to the psock from all maps. The + * psock will not be released until this reaches zero. The psock and sock + * user data data use the sk_callback_lock to protect critical data structures + * from concurrent access. This allows us to avoid two updates from modifying + * the user data in sock and the lock is required anyways for modifying + * callbacks, we simply increase its scope slightly. * - * Psocks may only participate in one sockmap at a time. Users that try to - * join a single sock to multiple maps will get an error. - * - * Last, but not least, it is possible the socket is closed while running - * an update on an existing psock. This will release the psock, but again - * not until the update has completed due to rcu grace period rules. + * Rules to follow, + * - psock must always be read inside RCU critical section + * - sk_user_data must only be modified inside sk_callback_lock and read + * inside RCU critical section. + * - psock->maps list must only be read & modified inside sk_callback_lock + * - sock_map must use READ_ONCE and (cmp)xchg operations + * - BPF verdict/parse programs must use READ_ONCE and xchg operations */ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, struct bpf_map *map, - void *key, u64 flags, u64 map_flags) + void *key, u64 flags) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + struct smap_psock_map_entry *e = NULL; struct bpf_prog *verdict, *parse; - struct smap_psock *psock = NULL; - struct sock *old_sock, *sock; + struct sock *osock, *sock; + struct smap_psock *psock; u32 i = *(u32 *)key; - bool update = false; - int err = 0; + int err; if (unlikely(flags > BPF_EXIST)) return -EINVAL; @@ -631,35 +679,22 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, if (unlikely(i >= stab->map.max_entries)) return -E2BIG; - if (unlikely(map_flags > BPF_SOCKMAP_STRPARSER)) - return -EINVAL; - - verdict = parse = NULL; sock = READ_ONCE(stab->sock_map[i]); - - if (flags == BPF_EXIST || flags == BPF_ANY) { - if (!sock && flags == BPF_EXIST) { - return -ENOENT; - } else if (sock && sock != skops->sk) { - return -EINVAL; - } else if (sock) { - psock = smap_psock_sk(sock); - if (unlikely(!psock)) - return -EBUSY; - update = true; - } - } else if (sock && BPF_NOEXIST) { + if (flags == BPF_EXIST && !sock) + return -ENOENT; + else if (flags == BPF_NOEXIST && sock) return -EEXIST; - } - /* reserve BPF programs early so can abort easily on failures */ - if (map_flags & BPF_SOCKMAP_STRPARSER) { - verdict = READ_ONCE(stab->bpf_verdict); - parse = READ_ONCE(stab->bpf_parse); + sock = skops->sk; - if (!verdict || !parse) - return -ENOENT; + /* 1. If sock map has BPF programs those will be inherited by the + * sock being added. If the sock is already attached to BPF programs + * this results in an error. + */ + verdict = READ_ONCE(stab->bpf_verdict); + parse = READ_ONCE(stab->bpf_parse); + if (parse && verdict) { /* bpf prog refcnt may be zero if a concurrent attach operation * removes the program after the above READ_ONCE() but before * we increment the refcnt. If this is the case abort with an @@ -676,50 +711,78 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, } } - if (!psock) { - sock = skops->sk; - if (rcu_dereference_sk_user_data(sock)) - return -EEXIST; + write_lock_bh(&sock->sk_callback_lock); + psock = smap_psock_sk(sock); + + /* 2. Do not allow inheriting programs if psock exists and has + * already inherited programs. This would create confusion on + * which parser/verdict program is running. If no psock exists + * create one. Inside sk_callback_lock to ensure concurrent create + * doesn't update user data. + */ + if (psock) { + if (READ_ONCE(psock->bpf_parse) && parse) { + err = -EBUSY; + goto out_progs; + } + psock->refcnt++; + } else { psock = smap_init_psock(sock, stab); if (IS_ERR(psock)) { - if (verdict) - bpf_prog_put(verdict); - if (parse) - bpf_prog_put(parse); - return PTR_ERR(psock); + err = PTR_ERR(psock); + goto out_progs; } - psock->key = i; - psock->stab = stab; - refcount_inc(&stab->refcnt); + set_bit(SMAP_TX_RUNNING, &psock->state); } - if (map_flags & BPF_SOCKMAP_STRPARSER) { - write_lock_bh(&sock->sk_callback_lock); - if (psock->strp_enabled) - goto start_done; + e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN); + if (!e) { + err = -ENOMEM; + goto out_progs; + } + e->entry = &stab->sock_map[i]; + + /* 3. At this point we have a reference to a valid psock that is + * running. Attach any BPF programs needed. + */ + if (parse && verdict && !psock->strp_enabled) { err = smap_init_sock(psock, sock); if (err) - goto out; + goto out_free; smap_init_progs(psock, stab, verdict, parse); smap_start_sock(psock, sock); -start_done: - write_unlock_bh(&sock->sk_callback_lock); - } else if (update) { - smap_stop_sock(psock, sock); } - if (!update) { - old_sock = xchg(&stab->sock_map[i], skops->sk); - if (old_sock) - smap_release_sock(old_sock); - } + /* 4. Place psock in sockmap for use and stop any programs on + * the old sock assuming its not the same sock we are replacing + * it with. Because we can only have a single set of programs if + * old_sock has a strp we can stop it. + */ + list_add_tail(&e->list, &psock->maps); + write_unlock_bh(&sock->sk_callback_lock); + osock = xchg(&stab->sock_map[i], sock); + if (osock) { + struct smap_psock *opsock = smap_psock_sk(osock); + + write_lock_bh(&osock->sk_callback_lock); + if (osock != sock && parse) + smap_stop_sock(opsock, osock); + smap_list_remove(opsock, &stab->sock_map[i]); + smap_release_sock(opsock, osock); + write_unlock_bh(&osock->sk_callback_lock); + } return 0; -out: +out_free: + smap_release_sock(psock, sock); +out_progs: + if (verdict) + bpf_prog_put(verdict); + if (parse) + bpf_prog_put(parse); write_unlock_bh(&sock->sk_callback_lock); - if (!update) - smap_release_sock(sock); + kfree(e); return err; } @@ -768,8 +831,7 @@ static int sock_map_update_elem(struct bpf_map *map, return -EINVAL; } - err = sock_map_ctx_update_elem(&skops, map, key, - flags, BPF_SOCKMAP_STRPARSER); + err = sock_map_ctx_update_elem(&skops, map, key, flags); fput(socket->file); return err; } @@ -783,11 +845,11 @@ const struct bpf_map_ops sock_map_ops = { .map_delete_elem = sock_map_delete_elem, }; -BPF_CALL_5(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock, - struct bpf_map *, map, void *, key, u64, flags, u64, map_flags) +BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock, + struct bpf_map *, map, void *, key, u64, flags) { WARN_ON_ONCE(!rcu_read_lock_held()); - return sock_map_ctx_update_elem(bpf_sock, map, key, flags, map_flags); + return sock_map_ctx_update_elem(bpf_sock, map, key, flags); } const struct bpf_func_proto bpf_sock_map_update_proto = { @@ -799,5 +861,4 @@ const struct bpf_func_proto bpf_sock_map_update_proto = { .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_PTR_TO_MAP_KEY, .arg4_type = ARG_ANYTHING, - .arg5_type = ARG_ANYTHING, }; -- cgit v1.2.3-71-gd317 From 63e8d4394a2d226803f47abd7287dbb6d21bf8e4 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 22 Aug 2017 16:58:20 +0300 Subject: serial: pch_uart: Make port type explicit It used to be a gap in port definitions after PORT_MAX_8250. Since the new drivers are coming the gap become shorter and shorter until the commit a2d6a987bfe4 ("serial: 8250: Add new port type for TI DA8xx/66AK2x") completely removed it. So, while type here is just a formality, make things a little bit more explicit for this driver and move port types to UAPI header. Note, it uses two types for now. Fixes: fddceb8b5399 ("tty: 8250: Add 64byte UART support for FSL platforms") Cc: Priyanka Jain Cc: Poonam Aggrwal Signed-off-by: Andy Shevchenko Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/pch_uart.c | 35 +++++++++++++++-------------------- include/uapi/linux/serial_core.h | 5 ++++- 2 files changed, 19 insertions(+), 21 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c index 3788198f105b..ae8cfc81ffc5 100644 --- a/drivers/tty/serial/pch_uart.c +++ b/drivers/tty/serial/pch_uart.c @@ -46,11 +46,6 @@ enum { PCH_UART_HANDLED_LS_INT_SHIFT, }; -enum { - PCH_UART_8LINE, - PCH_UART_2LINE, -}; - #define PCH_UART_DRIVER_DEVICE "ttyPCH" /* Set the max number of UART port @@ -267,7 +262,7 @@ struct eg20t_port { /** * struct pch_uart_driver_data - private data structure for UART-DMA - * @port_type: The number of DMA channel + * @port_type: The type of UART port * @line_no: UART port line number (0, 1, 2...) */ struct pch_uart_driver_data { @@ -290,17 +285,17 @@ enum pch_uart_num_t { }; static struct pch_uart_driver_data drv_dat[] = { - [pch_et20t_uart0] = {PCH_UART_8LINE, 0}, - [pch_et20t_uart1] = {PCH_UART_2LINE, 1}, - [pch_et20t_uart2] = {PCH_UART_2LINE, 2}, - [pch_et20t_uart3] = {PCH_UART_2LINE, 3}, - [pch_ml7213_uart0] = {PCH_UART_8LINE, 0}, - [pch_ml7213_uart1] = {PCH_UART_2LINE, 1}, - [pch_ml7213_uart2] = {PCH_UART_2LINE, 2}, - [pch_ml7223_uart0] = {PCH_UART_8LINE, 0}, - [pch_ml7223_uart1] = {PCH_UART_2LINE, 1}, - [pch_ml7831_uart0] = {PCH_UART_8LINE, 0}, - [pch_ml7831_uart1] = {PCH_UART_2LINE, 1}, + [pch_et20t_uart0] = {PORT_PCH_8LINE, 0}, + [pch_et20t_uart1] = {PORT_PCH_2LINE, 1}, + [pch_et20t_uart2] = {PORT_PCH_2LINE, 2}, + [pch_et20t_uart3] = {PORT_PCH_2LINE, 3}, + [pch_ml7213_uart0] = {PORT_PCH_8LINE, 0}, + [pch_ml7213_uart1] = {PORT_PCH_2LINE, 1}, + [pch_ml7213_uart2] = {PORT_PCH_2LINE, 2}, + [pch_ml7223_uart0] = {PORT_PCH_8LINE, 0}, + [pch_ml7223_uart1] = {PORT_PCH_2LINE, 1}, + [pch_ml7831_uart0] = {PORT_PCH_8LINE, 0}, + [pch_ml7831_uart1] = {PORT_PCH_2LINE, 1}, }; #ifdef CONFIG_SERIAL_PCH_UART_CONSOLE @@ -1777,10 +1772,10 @@ static struct eg20t_port *pch_uart_init_port(struct pci_dev *pdev, goto init_port_free_txbuf; switch (port_type) { - case PORT_UNKNOWN: + case PORT_PCH_8LINE: fifosize = 256; /* EG20T/ML7213: UART0 */ break; - case PORT_8250: + case PORT_PCH_2LINE: fifosize = 64; /* EG20T:UART1~3 ML7213: UART1~2*/ break; default: @@ -1804,7 +1799,7 @@ static struct eg20t_port *pch_uart_init_port(struct pci_dev *pdev, priv->fifo_size = fifosize; priv->uartclk = pch_uart_get_uartclk(); - priv->port_type = PORT_MAX_8250 + port_type + 1; + priv->port_type = port_type; priv->port.dev = &pdev->dev; priv->port.iobase = iobase; priv->port.membase = NULL; diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index 38bea3217ead..502aa23c7e15 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -57,7 +57,6 @@ #define PORT_RT2880 29 /* Ralink RT2880 internal UART */ #define PORT_16550A_FSL64 30 /* Freescale 16550 UART with 64 FIFOs */ #define PORT_DA830 31 /* TI DA8xx/66AK2x */ -#define PORT_MAX_8250 31 /* max port ID */ /* * ARM specific type numbers. These are not currently guaranteed @@ -77,6 +76,10 @@ #define PORT_SUNZILOG 38 #define PORT_SUNSAB 39 +/* Intel EG20 */ +#define PORT_PCH_8LINE 44 +#define PORT_PCH_2LINE 45 + /* DEC */ #define PORT_DZ 46 #define PORT_ZS 47 -- cgit v1.2.3-71-gd317 From 3f3dac7e4d815cb7f929c0ed98c3a45a86852e53 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 22 Aug 2017 16:58:21 +0300 Subject: serial: Remove unused port type PORT_MFD is not in use since commit 1bd187de5364 ("x86, intel-mid: remove Intel MID specific serial support") Remove leftover. Fixes: 1bd187de5364 ("x86, intel-mid: remove Intel MID specific serial support") Signed-off-by: Andy Shevchenko Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/serial_core.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index 502aa23c7e15..00d335634271 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -209,9 +209,6 @@ /* MAX310X */ #define PORT_MAX310X 94 -/* High Speed UART for Medfield */ -#define PORT_MFD 95 - /* TI OMAP-UART */ #define PORT_OMAP 96 -- cgit v1.2.3-71-gd317 From ee1c90cc2cea80638f559c552371ee6893ca9d9e Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 22 Aug 2017 16:58:22 +0300 Subject: serial: Fix port type numbering for TI DA8xx The UAPI has a global list of unique numbers for different port types. The commit a2d6a987bfe4 ("serial: 8250: Add new port type for TI DA8xx/66AK2x") introduced a new port type and brought the collision with two other port types. Reuse 95 for it instead. Fixes: a2d6a987bfe4 ("serial: 8250: Add new port type for TI DA8xx/66AK2x") Cc: David Lechner Cc: Sekhar Nori Signed-off-by: Andy Shevchenko Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/serial_core.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index 00d335634271..dc2d7cb766ab 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -56,7 +56,6 @@ #define PORT_ALTR_16550_F128 28 /* Altera 16550 UART with 128 FIFOs */ #define PORT_RT2880 29 /* Ralink RT2880 internal UART */ #define PORT_16550A_FSL64 30 /* Freescale 16550 UART with 64 FIFOs */ -#define PORT_DA830 31 /* TI DA8xx/66AK2x */ /* * ARM specific type numbers. These are not currently guaranteed @@ -209,6 +208,9 @@ /* MAX310X */ #define PORT_MAX310X 94 +/* TI DA8xx/66AK2x */ +#define PORT_DA830 95 + /* TI OMAP-UART */ #define PORT_OMAP 96 -- cgit v1.2.3-71-gd317 From 1c16ae65e2502da05310b2ec56b3a1fd3efe6f4d Mon Sep 17 00:00:00 2001 From: Sean Wang Date: Mon, 21 Aug 2017 01:17:56 +0800 Subject: serial: 8250: of: Add new port type for MediaTek BTIF controller on MT7622/23 SoC MediaTek BTIF controller is the serial interface similar to UART but it works only as the digital device which is mainly used to communicate with the connectivity module called CONNSYS inside the SoC which could be mostly found on those MediaTek SoCs with Bluetooth feature such as MT7622 and MT7623 SoCs. And the controller is made as being compatible with the 8250 register layout with extra registers such as DMA enablement so it tends to be integrated with reusing 8250 OF driver. However, DMA mode is not being supported yet in the current driver. Signed-off-by: Sean Wang Suggested-by: Andy Shevchenko Acked-by: Arnd Bergmann Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_of.c | 2 ++ drivers/tty/serial/8250/8250_port.c | 8 ++++++++ include/uapi/linux/serial_core.h | 3 +++ 3 files changed, 13 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/tty/serial/8250/8250_of.c b/drivers/tty/serial/8250/8250_of.c index 30eacbffaa51..1222c005fb98 100644 --- a/drivers/tty/serial/8250/8250_of.c +++ b/drivers/tty/serial/8250/8250_of.c @@ -313,6 +313,8 @@ static const struct of_device_id of_platform_serial_table[] = { .data = (void *)PORT_ALTR_16550_F64, }, { .compatible = "altr,16550-FIFO128", .data = (void *)PORT_ALTR_16550_F128, }, + { .compatible = "mediatek,mtk-btif", + .data = (void *)PORT_MTK_BTIF, }, { .compatible = "mrvl,mmp-uart", .data = (void *)PORT_XSCALE, }, { .compatible = "ti,da830-uart", .data = (void *)PORT_DA830, }, diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 6b745e440b81..4726aa276968 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -289,6 +289,14 @@ static const struct serial8250_config uart_config[] = { .rxtrig_bytes = {1, 4, 8, 14}, .flags = UART_CAP_FIFO | UART_CAP_AFE, }, + [PORT_MTK_BTIF] = { + .name = "MediaTek BTIF", + .fifo_size = 16, + .tx_loadsz = 16, + .fcr = UART_FCR_ENABLE_FIFO | + UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT, + .flags = UART_CAP_FIFO, + }, }; /* Uart divisor latch read */ diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index dc2d7cb766ab..50d71c436323 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -274,4 +274,7 @@ /* MPS2 UART */ #define PORT_MPS2UART 116 +/* MediaTek BTIF */ +#define PORT_MTK_BTIF 117 + #endif /* _UAPILINUX_SERIAL_CORE_H */ -- cgit v1.2.3-71-gd317 From fc7ce9c74c3ad232b084d80148654f926d01ece7 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Mon, 28 Aug 2017 20:52:49 -0400 Subject: perf/core, x86: Add PERF_SAMPLE_PHYS_ADDR For understanding how the workload maps to memory channels and hardware behavior, it's very important to collect address maps with physical addresses. For example, 3D XPoint access can only be found by filtering the physical address. Add a new sample type for physical address. perf already has a facility to collect data virtual address. This patch introduces a function to convert the virtual address to physical address. The function is quite generic and can be extended to any architecture as long as a virtual address is provided. - For kernel direct mapping addresses, virt_to_phys is used to convert the virtual addresses to physical address. - For user virtual addresses, __get_user_pages_fast is used to walk the pages tables for user physical address. - This does not work for vmalloc addresses right now. These are not resolved, but code to do that could be added. The new sample type requires collecting the virtual address. The virtual address will not be output unless SAMPLE_ADDR is applied. For security, the physical address can only be exposed to root or privileged user. Tested-by: Madhavan Srinivasan Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: acme@kernel.org Cc: mpe@ellerman.id.au Link: http://lkml.kernel.org/r/1503967969-48278-1-git-send-email-kan.liang@intel.com Signed-off-by: Ingo Molnar --- arch/powerpc/perf/core-book3s.c | 3 ++- arch/x86/events/intel/ds.c | 2 +- arch/x86/events/perf_event.h | 2 +- include/linux/perf_event.h | 2 ++ include/uapi/linux/perf_event.h | 4 +++- kernel/events/core.c | 46 +++++++++++++++++++++++++++++++++++++++++ 6 files changed, 55 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 6c2d4168daec..2e3eb7431571 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -2039,7 +2039,8 @@ static void record_and_restart(struct perf_event *event, unsigned long val, perf_sample_data_init(&data, ~0ULL, event->hw.last_period); - if (event->attr.sample_type & PERF_SAMPLE_ADDR) + if (event->attr.sample_type & + (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR)) perf_get_data_addr(regs, &data.addr); if (event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK) { diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 98e36e0c791c..e1965e5ff570 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1185,7 +1185,7 @@ static void setup_pebs_sample_data(struct perf_event *event, else regs->flags &= ~PERF_EFLAGS_EXACT; - if ((sample_type & PERF_SAMPLE_ADDR) && + if ((sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR)) && x86_pmu.intel_cap.pebs_format >= 1) data->addr = pebs->dla; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 9337589014cc..4196f81ec0e1 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -91,7 +91,7 @@ struct amd_nb { (PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \ PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \ PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \ - PERF_SAMPLE_TRANSACTION) + PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR) /* * A debug store configuration. diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index adda0aaae6c8..718ba163c1b9 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -943,6 +943,8 @@ struct perf_sample_data { struct perf_regs regs_intr; u64 stack_user_size; + + u64 phys_addr; } ____cacheline_aligned; /* default value for data source */ diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 2a37ae925d85..140ae638cfd6 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -139,8 +139,9 @@ enum perf_event_sample_format { PERF_SAMPLE_IDENTIFIER = 1U << 16, PERF_SAMPLE_TRANSACTION = 1U << 17, PERF_SAMPLE_REGS_INTR = 1U << 18, + PERF_SAMPLE_PHYS_ADDR = 1U << 19, - PERF_SAMPLE_MAX = 1U << 19, /* non-ABI */ + PERF_SAMPLE_MAX = 1U << 20, /* non-ABI */ }; /* @@ -814,6 +815,7 @@ enum perf_event_type { * { u64 transaction; } && PERF_SAMPLE_TRANSACTION * { u64 abi; # enum perf_sample_regs_abi * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR + * { u64 phys_addr;} && PERF_SAMPLE_PHYS_ADDR * }; */ PERF_RECORD_SAMPLE = 9, diff --git a/kernel/events/core.c b/kernel/events/core.c index 77fd6b11ef22..ce64f3fed5c6 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1575,6 +1575,9 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type) if (sample_type & PERF_SAMPLE_TRANSACTION) size += sizeof(data->txn); + if (sample_type & PERF_SAMPLE_PHYS_ADDR) + size += sizeof(data->phys_addr); + event->header_size = size; } @@ -6017,6 +6020,9 @@ void perf_output_sample(struct perf_output_handle *handle, } } + if (sample_type & PERF_SAMPLE_PHYS_ADDR) + perf_output_put(handle, data->phys_addr); + if (!event->attr.watermark) { int wakeup_events = event->attr.wakeup_events; @@ -6032,6 +6038,38 @@ void perf_output_sample(struct perf_output_handle *handle, } } +static u64 perf_virt_to_phys(u64 virt) +{ + u64 phys_addr = 0; + struct page *p = NULL; + + if (!virt) + return 0; + + if (virt >= TASK_SIZE) { + /* If it's vmalloc()d memory, leave phys_addr as 0 */ + if (virt_addr_valid((void *)(uintptr_t)virt) && + !(virt >= VMALLOC_START && virt < VMALLOC_END)) + phys_addr = (u64)virt_to_phys((void *)(uintptr_t)virt); + } else { + /* + * Walking the pages tables for user address. + * Interrupts are disabled, so it prevents any tear down + * of the page tables. + * Try IRQ-safe __get_user_pages_fast first. + * If failed, leave phys_addr as 0. + */ + if ((current->mm != NULL) && + (__get_user_pages_fast(virt, 1, 0, &p) == 1)) + phys_addr = page_to_phys(p) + virt % PAGE_SIZE; + + if (p) + put_page(p); + } + + return phys_addr; +} + void perf_prepare_sample(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event, @@ -6150,6 +6188,9 @@ void perf_prepare_sample(struct perf_event_header *header, header->size += size; } + + if (sample_type & PERF_SAMPLE_PHYS_ADDR) + data->phys_addr = perf_virt_to_phys(data->addr); } static void __always_inline @@ -9909,6 +9950,11 @@ SYSCALL_DEFINE5(perf_event_open, return -EINVAL; } + /* 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_max_stack) attr.sample_max_stack = sysctl_perf_event_max_stack; -- cgit v1.2.3-71-gd317 From 2804fd3af6ba5ae5737705b27146455eabe2e2f8 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Mon, 28 Aug 2017 15:03:13 -0400 Subject: if_ether: add forces ife lfb type This patch adds the forces IFE lfb type according to IEEE registered ethertypes. See http://standards-oui.ieee.org/ethertype/eth.txt for more information. Since there exists the IFE subsystem it can be used there. This patch also use the correct word "ForCES" instead of "FoRCES" which is a spelling error inside the IEEE ethertype specification. Signed-off-by: Alexander Aring Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/uapi/linux/if_ether.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index efeb1190c2ca..f68f6bf4a253 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -104,6 +104,7 @@ #define ETH_P_QINQ2 0x9200 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_QINQ3 0x9300 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_EDSA 0xDADA /* Ethertype DSA [ NOT AN OFFICIALLY REGISTERED ID ] */ +#define ETH_P_IFE 0xED3E /* ForCES inter-FE LFB type */ #define ETH_P_AF_IUCV 0xFBFB /* IBM af_iucv [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_802_3_MIN 0x0600 /* If the value in the ethernet type is less than this value -- cgit v1.2.3-71-gd317 From 155e6f649757c902901e599c268f8b575ddac1f8 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Mon, 28 Aug 2017 21:43:21 +0200 Subject: ether: add NSH ethertype The NSH draft says: An IEEE EtherType, 0x894F, has been allocated for NSH. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- include/uapi/linux/if_ether.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index f68f6bf4a253..61f7ccce5b69 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -99,6 +99,7 @@ #define ETH_P_FIP 0x8914 /* FCoE Initialization Protocol */ #define ETH_P_80221 0x8917 /* IEEE 802.21 Media Independent Handover Protocol */ #define ETH_P_HSR 0x892F /* IEC 62439-3 HSRv1 */ +#define ETH_P_NSH 0x894F /* Network Service Header */ #define ETH_P_LOOPBACK 0x9000 /* Ethernet loopback packet, per IEEE 802.3 */ #define ETH_P_QINQ1 0x9100 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_QINQ2 0x9200 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */ -- cgit v1.2.3-71-gd317 From 31770e34e43d6c8dee129bfee77e56c34e61f0e5 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 30 Aug 2017 19:24:58 +0200 Subject: tcp: Revert "tcp: remove header prediction" This reverts commit 45f119bf936b1f9f546a0b139c5b56f9bb2bdc78. Eric Dumazet says: We found at Google a significant regression caused by 45f119bf936b1f9f546a0b139c5b56f9bb2bdc78 tcp: remove header prediction In typical RPC (TCP_RR), when a TCP socket receives data, we now call tcp_ack() while we used to not call it. This touches enough cache lines to cause a slowdown. so problem does not seem to be HP removal itself but the tcp_ack() call. Therefore, it might be possible to remove HP after all, provided one finds a way to elide tcp_ack for most cases. Reported-by: Eric Dumazet Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/tcp.h | 6 ++ include/net/tcp.h | 23 ++++++ include/uapi/linux/snmp.h | 2 + net/ipv4/proc.c | 2 + net/ipv4/tcp.c | 4 +- net/ipv4/tcp_input.c | 188 ++++++++++++++++++++++++++++++++++++++++++++-- net/ipv4/tcp_minisocks.c | 2 + net/ipv4/tcp_output.c | 2 + 8 files changed, 223 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 267164a1d559..4aa40ef02d32 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -147,6 +147,12 @@ struct tcp_sock { u16 tcp_header_len; /* Bytes of tcp header to send */ u16 gso_segs; /* Max number of segs per GSO packet */ +/* + * Header prediction flags + * 0x5?10 << 16 + snd_wnd in net byte order + */ + __be32 pred_flags; + /* * RFC793 variables by their proper names. This means you can * read the code and the spec side by side (and laugh ...) diff --git a/include/net/tcp.h b/include/net/tcp.h index c546d13ffbca..9c3db054e47f 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -634,6 +634,29 @@ static inline u32 __tcp_set_rto(const struct tcp_sock *tp) return usecs_to_jiffies((tp->srtt_us >> 3) + tp->rttvar_us); } +static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd) +{ + tp->pred_flags = htonl((tp->tcp_header_len << 26) | + ntohl(TCP_FLAG_ACK) | + snd_wnd); +} + +static inline void tcp_fast_path_on(struct tcp_sock *tp) +{ + __tcp_fast_path_on(tp, tp->snd_wnd >> tp->rx_opt.snd_wscale); +} + +static inline void tcp_fast_path_check(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (RB_EMPTY_ROOT(&tp->out_of_order_queue) && + tp->rcv_wnd && + atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf && + !tp->urg_data) + tcp_fast_path_on(tp); +} + /* Compute the actual rto_min value */ static inline u32 tcp_rto_min(struct sock *sk) { diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index b3f346fb9fe3..758f12b58541 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -184,7 +184,9 @@ enum LINUX_MIB_DELAYEDACKLOST, /* DelayedACKLost */ LINUX_MIB_LISTENOVERFLOWS, /* ListenOverflows */ LINUX_MIB_LISTENDROPS, /* ListenDrops */ + LINUX_MIB_TCPHPHITS, /* TCPHPHits */ LINUX_MIB_TCPPUREACKS, /* TCPPureAcks */ + LINUX_MIB_TCPHPACKS, /* TCPHPAcks */ LINUX_MIB_TCPRENORECOVERY, /* TCPRenoRecovery */ LINUX_MIB_TCPSACKRECOVERY, /* TCPSackRecovery */ LINUX_MIB_TCPSACKRENEGING, /* TCPSACKReneging */ diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index b6d3fe03feb3..127153f1ed8a 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -206,7 +206,9 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("DelayedACKLost", LINUX_MIB_DELAYEDACKLOST), SNMP_MIB_ITEM("ListenOverflows", LINUX_MIB_LISTENOVERFLOWS), SNMP_MIB_ITEM("ListenDrops", LINUX_MIB_LISTENDROPS), + SNMP_MIB_ITEM("TCPHPHits", LINUX_MIB_TCPHPHITS), SNMP_MIB_ITEM("TCPPureAcks", LINUX_MIB_TCPPUREACKS), + SNMP_MIB_ITEM("TCPHPAcks", LINUX_MIB_TCPHPACKS), SNMP_MIB_ITEM("TCPRenoRecovery", LINUX_MIB_TCPRENORECOVERY), SNMP_MIB_ITEM("TCPSackRecovery", LINUX_MIB_TCPSACKRECOVERY), SNMP_MIB_ITEM("TCPSACKReneging", LINUX_MIB_TCPSACKRENEGING), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 566083ee2654..21ca2df274c5 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1963,8 +1963,10 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, tcp_rcv_space_adjust(sk); skip_copy: - if (tp->urg_data && after(tp->copied_seq, tp->urg_seq)) + if (tp->urg_data && after(tp->copied_seq, tp->urg_seq)) { tp->urg_data = 0; + tcp_fast_path_check(sk); + } if (used + offset < skb->len) continue; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a0e436366d31..c5d7656beeee 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -103,6 +103,7 @@ int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2; #define FLAG_DATA_SACKED 0x20 /* New SACK. */ #define FLAG_ECE 0x40 /* ECE in this ACK */ #define FLAG_LOST_RETRANS 0x80 /* This ACK marks some retransmission lost */ +#define FLAG_SLOWPATH 0x100 /* Do not skip RFC checks for window update.*/ #define FLAG_ORIG_SACK_ACKED 0x200 /* Never retransmitted data are (s)acked */ #define FLAG_SND_UNA_ADVANCED 0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */ #define FLAG_DSACKING_ACK 0x800 /* SACK blocks contained D-SACK info */ @@ -3371,6 +3372,12 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 if (tp->snd_wnd != nwin) { tp->snd_wnd = nwin; + /* Note, it is the only place, where + * fast path is recovered for sending TCP. + */ + tp->pred_flags = 0; + tcp_fast_path_check(sk); + if (tcp_send_head(sk)) tcp_slow_start_after_idle_check(sk); @@ -3592,7 +3599,19 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (flag & FLAG_UPDATE_TS_RECENT) tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); - { + if (!(flag & FLAG_SLOWPATH) && after(ack, prior_snd_una)) { + /* Window is constant, pure forward advance. + * No more checks are required. + * Note, we use the fact that SND.UNA>=SND.WL2. + */ + tcp_update_wl(tp, ack_seq); + tcp_snd_una_update(tp, ack); + flag |= FLAG_WIN_UPDATE; + + tcp_in_ack_event(sk, CA_ACK_WIN_UPDATE); + + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPACKS); + } else { u32 ack_ev_flags = CA_ACK_SLOWPATH; if (ack_seq != TCP_SKB_CB(skb)->end_seq) @@ -4407,6 +4426,8 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) if (TCP_SKB_CB(skb)->has_rxtstamp) TCP_SKB_CB(skb)->swtstamp = skb->tstamp; + /* Disable header prediction. */ + tp->pred_flags = 0; inet_csk_schedule_ack(sk); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOQUEUE); @@ -4647,6 +4668,8 @@ queue_and_out: if (tp->rx_opt.num_sacks) tcp_sack_remove(tp); + tcp_fast_path_check(sk); + if (eaten > 0) kfree_skb_partial(skb, fragstolen); if (!sock_flag(sk, SOCK_DEAD)) @@ -4972,6 +4995,7 @@ static int tcp_prune_queue(struct sock *sk) NET_INC_STATS(sock_net(sk), LINUX_MIB_RCVPRUNED); /* Massive buffer overcommit. */ + tp->pred_flags = 0; return -1; } @@ -5143,6 +5167,9 @@ static void tcp_check_urg(struct sock *sk, const struct tcphdr *th) tp->urg_data = TCP_URG_NOTYET; tp->urg_seq = ptr; + + /* Disable header prediction. */ + tp->pred_flags = 0; } /* This is the 'fast' part of urgent handling. */ @@ -5301,6 +5328,26 @@ discard: /* * TCP receive function for the ESTABLISHED state. + * + * It is split into a fast path and a slow path. The fast path is + * disabled when: + * - A zero window was announced from us - zero window probing + * is only handled properly in the slow path. + * - Out of order segments arrived. + * - Urgent data is expected. + * - There is no buffer space left + * - Unexpected TCP flags/window values/header lengths are received + * (detected by checking the TCP header against pred_flags) + * - Data is sent in both directions. Fast path only supports pure senders + * or pure receivers (this means either the sequence number or the ack + * value must stay constant) + * - Unexpected TCP option. + * + * When these conditions are not satisfied it drops into a standard + * receive procedure patterned after RFC793 to handle all cases. + * The first three cases are guaranteed by proper pred_flags setting, + * the rest is checked inline. Fast processing is turned on in + * tcp_data_queue when everything is OK. */ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th) @@ -5311,19 +5358,144 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, tcp_mstamp_refresh(tp); if (unlikely(!sk->sk_rx_dst)) inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb); + /* + * Header prediction. + * The code loosely follows the one in the famous + * "30 instruction TCP receive" Van Jacobson mail. + * + * Van's trick is to deposit buffers into socket queue + * on a device interrupt, to call tcp_recv function + * on the receive process context and checksum and copy + * the buffer to user space. smart... + * + * Our current scheme is not silly either but we take the + * extra cost of the net_bh soft interrupt processing... + * We do checksum and copy also but from device to kernel. + */ tp->rx_opt.saw_tstamp = 0; + /* pred_flags is 0xS?10 << 16 + snd_wnd + * if header_prediction is to be made + * 'S' will always be tp->tcp_header_len >> 2 + * '?' will be 0 for the fast path, otherwise pred_flags is 0 to + * turn it off (when there are holes in the receive + * space for instance) + * PSH flag is ignored. + */ + + if ((tcp_flag_word(th) & TCP_HP_BITS) == tp->pred_flags && + TCP_SKB_CB(skb)->seq == tp->rcv_nxt && + !after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt)) { + int tcp_header_len = tp->tcp_header_len; + + /* Timestamp header prediction: tcp_header_len + * is automatically equal to th->doff*4 due to pred_flags + * match. + */ + + /* Check timestamp */ + if (tcp_header_len == sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) { + /* No? Slow path! */ + if (!tcp_parse_aligned_timestamp(tp, th)) + goto slow_path; + + /* If PAWS failed, check it more carefully in slow path */ + if ((s32)(tp->rx_opt.rcv_tsval - tp->rx_opt.ts_recent) < 0) + goto slow_path; + + /* DO NOT update ts_recent here, if checksum fails + * and timestamp was corrupted part, it will result + * in a hung connection since we will drop all + * future packets due to the PAWS test. + */ + } + + if (len <= tcp_header_len) { + /* Bulk data transfer: sender */ + if (len == tcp_header_len) { + /* Predicted packet is in window by definition. + * seq == rcv_nxt and rcv_wup <= rcv_nxt. + * Hence, check seq<=rcv_wup reduces to: + */ + if (tcp_header_len == + (sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) && + tp->rcv_nxt == tp->rcv_wup) + tcp_store_ts_recent(tp); + + /* We know that such packets are checksummed + * on entry. + */ + tcp_ack(sk, skb, 0); + __kfree_skb(skb); + tcp_data_snd_check(sk); + return; + } else { /* Header too small */ + TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); + goto discard; + } + } else { + int eaten = 0; + bool fragstolen = false; + + if (tcp_checksum_complete(skb)) + goto csum_error; + + if ((int)skb->truesize > sk->sk_forward_alloc) + goto step5; + + /* Predicted packet is in window by definition. + * seq == rcv_nxt and rcv_wup <= rcv_nxt. + * Hence, check seq<=rcv_wup reduces to: + */ + if (tcp_header_len == + (sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) && + tp->rcv_nxt == tp->rcv_wup) + tcp_store_ts_recent(tp); + + tcp_rcv_rtt_measure_ts(sk, skb); + + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPHITS); + + /* Bulk data transfer: receiver */ + eaten = tcp_queue_rcv(sk, skb, tcp_header_len, + &fragstolen); + + tcp_event_data_recv(sk, skb); + + if (TCP_SKB_CB(skb)->ack_seq != tp->snd_una) { + /* Well, only one small jumplet in fast path... */ + tcp_ack(sk, skb, FLAG_DATA); + tcp_data_snd_check(sk); + if (!inet_csk_ack_scheduled(sk)) + goto no_ack; + } + + __tcp_ack_snd_check(sk, 0); +no_ack: + if (eaten) + kfree_skb_partial(skb, fragstolen); + sk->sk_data_ready(sk); + return; + } + } + +slow_path: if (len < (th->doff << 2) || tcp_checksum_complete(skb)) goto csum_error; if (!th->ack && !th->rst && !th->syn) goto discard; + /* + * Standard slow path. + */ + if (!tcp_validate_incoming(sk, skb, th, 1)) return; - if (tcp_ack(sk, skb, FLAG_UPDATE_TS_RECENT) < 0) +step5: + if (tcp_ack(sk, skb, FLAG_SLOWPATH | FLAG_UPDATE_TS_RECENT) < 0) goto discard; tcp_rcv_rtt_measure_ts(sk, skb); @@ -5376,6 +5548,11 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) if (sock_flag(sk, SOCK_KEEPOPEN)) inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tp)); + + if (!tp->rx_opt.snd_wscale) + __tcp_fast_path_on(tp, tp->snd_wnd); + else + tp->pred_flags = 0; } static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, @@ -5504,7 +5681,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, tcp_ecn_rcv_synack(tp, th); tcp_init_wl(tp, TCP_SKB_CB(skb)->seq); - tcp_ack(sk, skb, 0); + tcp_ack(sk, skb, FLAG_SLOWPATH); /* Ok.. it's good. Set up sequence numbers and * move to established. @@ -5740,8 +5917,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) return 0; /* step 5: check the ACK field */ - - acceptable = tcp_ack(sk, skb, FLAG_UPDATE_TS_RECENT | + acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH | + FLAG_UPDATE_TS_RECENT | FLAG_NO_CHALLENGE_ACK) > 0; if (!acceptable) { @@ -5809,6 +5986,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tp->lsndtime = tcp_jiffies32; tcp_initialize_rcv_mss(sk); + tcp_fast_path_on(tp); break; case TCP_FIN_WAIT1: { diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 1537b87c657f..188a6f31356d 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -436,6 +436,8 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, struct tcp_sock *newtp = tcp_sk(newsk); /* Now setup tcp_sock */ + newtp->pred_flags = 0; + newtp->rcv_wup = newtp->copied_seq = newtp->rcv_nxt = treq->rcv_isn + 1; newtp->segs_in = 1; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 3e0d19631534..5b6690d05abb 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -295,7 +295,9 @@ static u16 tcp_select_window(struct sock *sk) /* RFC1323 scaling applied */ new_win >>= tp->rx_opt.rcv_wscale; + /* If we advertise zero window, disable fast path. */ if (new_win == 0) { + tp->pred_flags = 0; if (old_win) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTOZEROWINDOWADV); -- cgit v1.2.3-71-gd317 From 7373ae7e8f0bf2c0718422481da986db5058b005 Mon Sep 17 00:00:00 2001 From: Subash Abhinov Kasiviswanathan Date: Tue, 29 Aug 2017 22:44:16 -0600 Subject: net: ether: Add support for multiplexing and aggregation type Define the Qualcomm multiplexing and aggregation (MAP) ether type 0x00F9. This is needed for receiving data in the MAP protocol like RMNET. This is not an officially registered ID. Signed-off-by: Subash Abhinov Kasiviswanathan Signed-off-by: David S. Miller --- include/uapi/linux/if_ether.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 61f7ccce5b69..9037065e23d0 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -140,6 +140,9 @@ #define ETH_P_IEEE802154 0x00F6 /* IEEE802.15.4 frame */ #define ETH_P_CAIF 0x00F7 /* ST-Ericsson CAIF protocol */ #define ETH_P_XDSA 0x00F8 /* Multiplexed DSA protocol */ +#define ETH_P_MAP 0x00F9 /* Qualcomm multiplexing and + * aggregation protocol + */ /* * This is an Ethernet frame header. -- cgit v1.2.3-71-gd317 From cdf4969c42a6c1a376dd03a9e846cf638d3cd4b1 Mon Sep 17 00:00:00 2001 From: Subash Abhinov Kasiviswanathan Date: Tue, 29 Aug 2017 22:44:17 -0600 Subject: net: arp: Add support for raw IP device Define the raw IP type. This is needed for raw IP net devices like rmnet. Signed-off-by: Subash Abhinov Kasiviswanathan Signed-off-by: David S. Miller --- include/uapi/linux/if_arp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_arp.h b/include/uapi/linux/if_arp.h index cf73510b9238..a2a635620600 100644 --- a/include/uapi/linux/if_arp.h +++ b/include/uapi/linux/if_arp.h @@ -59,6 +59,7 @@ #define ARPHRD_LAPB 516 /* LAPB */ #define ARPHRD_DDCMP 517 /* Digital's DDCMP protocol */ #define ARPHRD_RAWHDLC 518 /* Raw HDLC */ +#define ARPHRD_RAWIP 519 /* Raw IP */ #define ARPHRD_TUNNEL 768 /* IPIP tunnel */ #define ARPHRD_TUNNEL6 769 /* IP6IP6 tunnel */ -- cgit v1.2.3-71-gd317 From e3bfed1df379c18f20feb06427d952b766e2c00f Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Fri, 25 Aug 2017 19:53:39 +1000 Subject: KVM: PPC: Book3S HV: Report storage key support to userspace This adds information about storage keys to the struct returned by the KVM_PPC_GET_SMMU_INFO ioctl. The new fields replace a pad field, which was zeroed by previous kernel versions. Thus userspace that knows about the new fields will see zeroes when running on an older kernel, indicating that storage keys are not supported. The size of the structure has not changed. The number of keys is hard-coded for the CPUs supported by HV KVM, which is just POWER7, POWER8 and POWER9. Signed-off-by: Paul Mackerras Reviewed-by: David Gibson Signed-off-by: Paul Mackerras --- arch/powerpc/kvm/book3s_hv.c | 8 ++++++++ include/uapi/linux/kvm.h | 3 ++- 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 1182cfd79857..f62ad2e9085f 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3331,6 +3331,14 @@ static int kvm_vm_ioctl_get_smmu_info_hv(struct kvm *kvm, if (radix_enabled()) return -EINVAL; + /* + * POWER7, POWER8 and POWER9 all support 32 storage keys for data. + * POWER7 doesn't support keys for instruction accesses, + * POWER8 and POWER9 do. + */ + info->data_keys = 32; + info->instr_keys = cpu_has_feature(CPU_FTR_ARCH_207S) ? 32 : 0; + info->flags = KVM_PPC_PAGE_SIZES_REAL; if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) info->flags |= KVM_PPC_1T_SEGMENTS; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 6cd63c18708a..838887587411 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -711,7 +711,8 @@ struct kvm_ppc_one_seg_page_size { struct kvm_ppc_smmu_info { __u64 flags; __u32 slb_size; - __u32 pad; + __u16 data_keys; /* # storage keys supported for data */ + __u16 instr_keys; /* # storage keys supported for instructions */ struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; }; -- cgit v1.2.3-71-gd317 From 8fc614c0ae5cb5df11d6aa9559e63baacf20a840 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 31 Aug 2017 14:12:39 -0500 Subject: PCI/AER: Reformat AER register definitions Reformat so comments fit on same line as definition. No functional change intended. Signed-off-by: Bjorn Helgaas --- include/uapi/linux/pci_regs.h | 26 ++++++++++---------------- 1 file changed, 10 insertions(+), 16 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index c22d3ebaca20..46632aaee1c0 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -733,23 +733,17 @@ #define PCI_ERR_CAP_ECRC_CHKE 0x00000100 /* ECRC Check Enable */ #define PCI_ERR_HEADER_LOG 28 /* Header Log Register (16 bytes) */ #define PCI_ERR_ROOT_COMMAND 44 /* Root Error Command */ -/* Correctable Err Reporting Enable */ -#define PCI_ERR_ROOT_CMD_COR_EN 0x00000001 -/* Non-fatal Err Reporting Enable */ -#define PCI_ERR_ROOT_CMD_NONFATAL_EN 0x00000002 -/* Fatal Err Reporting Enable */ -#define PCI_ERR_ROOT_CMD_FATAL_EN 0x00000004 +#define PCI_ERR_ROOT_CMD_COR_EN 0x00000001 /* Correctable Err Reporting Enable */ +#define PCI_ERR_ROOT_CMD_NONFATAL_EN 0x00000002 /* Non-Fatal Err Reporting Enable */ +#define PCI_ERR_ROOT_CMD_FATAL_EN 0x00000004 /* Fatal Err Reporting Enable */ #define PCI_ERR_ROOT_STATUS 48 -#define PCI_ERR_ROOT_COR_RCV 0x00000001 /* ERR_COR Received */ -/* Multi ERR_COR Received */ -#define PCI_ERR_ROOT_MULTI_COR_RCV 0x00000002 -/* ERR_FATAL/NONFATAL Received */ -#define PCI_ERR_ROOT_UNCOR_RCV 0x00000004 -/* Multi ERR_FATAL/NONFATAL Received */ -#define PCI_ERR_ROOT_MULTI_UNCOR_RCV 0x00000008 -#define PCI_ERR_ROOT_FIRST_FATAL 0x00000010 /* First Fatal */ -#define PCI_ERR_ROOT_NONFATAL_RCV 0x00000020 /* Non-Fatal Received */ -#define PCI_ERR_ROOT_FATAL_RCV 0x00000040 /* Fatal Received */ +#define PCI_ERR_ROOT_COR_RCV 0x00000001 /* ERR_COR Received */ +#define PCI_ERR_ROOT_MULTI_COR_RCV 0x00000002 /* Multiple ERR_COR */ +#define PCI_ERR_ROOT_UNCOR_RCV 0x00000004 /* ERR_FATAL/NONFATAL */ +#define PCI_ERR_ROOT_MULTI_UNCOR_RCV 0x00000008 /* Multiple FATAL/NONFATAL */ +#define PCI_ERR_ROOT_FIRST_FATAL 0x00000010 /* First UNC is Fatal */ +#define PCI_ERR_ROOT_NONFATAL_RCV 0x00000020 /* Non-Fatal Received */ +#define PCI_ERR_ROOT_FATAL_RCV 0x00000040 /* Fatal Received */ #define PCI_ERR_ROOT_ERR_SRC 52 /* Error Source Identification */ /* Virtual Channel */ -- cgit v1.2.3-71-gd317 From 89e4fdecb51cf5535867026274bc97de9480ade5 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Thu, 24 Aug 2017 00:03:43 -0700 Subject: loop: add ioctl for changing logical block size This is a different approach from the first attempt in f2c6df7dbf9a ("loop: support 4k physical blocksize"). Rather than extending LOOP_{GET,SET}_STATUS, add a separate ioctl just for setting the block size. Reviewed-by: Ming Lei Reviewed-by: Hannes Reinecke Signed-off-by: Omar Sandoval Signed-off-by: Jens Axboe --- drivers/block/loop.c | 24 ++++++++++++++++++++++++ include/uapi/linux/loop.h | 1 + 2 files changed, 25 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/block/loop.c b/drivers/block/loop.c index e3f190016d4f..ac106b287d75 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1047,6 +1047,7 @@ static int loop_clr_fd(struct loop_device *lo) memset(lo->lo_encrypt_key, 0, LO_KEY_SIZE); memset(lo->lo_crypt_name, 0, LO_NAME_SIZE); memset(lo->lo_file_name, 0, LO_NAME_SIZE); + blk_queue_logical_block_size(lo->lo_queue, 512); if (bdev) { bdput(bdev); invalidate_bdev(bdev); @@ -1330,6 +1331,24 @@ static int loop_set_dio(struct loop_device *lo, unsigned long arg) return error; } +static int loop_set_block_size(struct loop_device *lo, unsigned long arg) +{ + if (lo->lo_state != Lo_bound) + return -ENXIO; + + if (arg < 512 || arg > PAGE_SIZE || !is_power_of_2(arg)) + return -EINVAL; + + blk_mq_freeze_queue(lo->lo_queue); + + blk_queue_logical_block_size(lo->lo_queue, arg); + loop_update_dio(lo); + + blk_mq_unfreeze_queue(lo->lo_queue); + + return 0; +} + static int lo_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { @@ -1378,6 +1397,11 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) err = loop_set_dio(lo, arg); break; + case LOOP_SET_BLOCK_SIZE: + err = -EPERM; + if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) + err = loop_set_block_size(lo, arg); + break; default: err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL; } diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h index c8125ec1f4f2..23158dbe2424 100644 --- a/include/uapi/linux/loop.h +++ b/include/uapi/linux/loop.h @@ -88,6 +88,7 @@ struct loop_info64 { #define LOOP_CHANGE_FD 0x4C06 #define LOOP_SET_CAPACITY 0x4C07 #define LOOP_SET_DIRECT_IO 0x4C08 +#define LOOP_SET_BLOCK_SIZE 0x4C09 /* /dev/loop-control interface */ #define LOOP_CTL_ADD 0x4C80 -- cgit v1.2.3-71-gd317 From ddef7ed2b5cbafae692d1d580bb5a07808926a9c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 6 Jul 2017 18:58:37 +0200 Subject: annotate RWF_... flags [AV: added missing annotations in syscalls.h/compat.h] Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- fs/nfsd/vfs.c | 2 +- fs/read_write.c | 50 ++++++++++++++++++++++---------------------- include/linux/compat.h | 16 ++++++++++++-- include/linux/fs.h | 12 ++++++----- include/linux/syscalls.h | 4 ++-- include/uapi/linux/aio_abi.h | 21 ++++++++++--------- include/uapi/linux/fs.h | 28 ++++++++++++++++++------- 7 files changed, 80 insertions(+), 53 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 38d0383dc7f9..bc69d40c4e8b 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -969,7 +969,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, int use_wgather; loff_t pos = offset; unsigned int pflags = current->flags; - int flags = 0; + rwf_t flags = 0; if (test_bit(RQ_LOCAL, &rqstp->rq_flags)) /* diff --git a/fs/read_write.c b/fs/read_write.c index 0cc7033aa413..61b58c7b6531 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -33,7 +33,7 @@ const struct file_operations generic_ro_fops = { EXPORT_SYMBOL(generic_ro_fops); -static inline int unsigned_offsets(struct file *file) +static inline bool unsigned_offsets(struct file *file) { return file->f_mode & FMODE_UNSIGNED_OFFSET; } @@ -633,7 +633,7 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to) EXPORT_SYMBOL(iov_shorten); static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, - loff_t *ppos, int type, int flags) + loff_t *ppos, int type, rwf_t flags) { struct kiocb kiocb; ssize_t ret; @@ -655,7 +655,7 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, /* Do it by hand, with file-ops */ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, - loff_t *ppos, int type, int flags) + loff_t *ppos, int type, rwf_t flags) { ssize_t ret = 0; @@ -871,7 +871,7 @@ out: #endif static ssize_t do_iter_read(struct file *file, struct iov_iter *iter, - loff_t *pos, int flags) + loff_t *pos, rwf_t flags) { size_t tot_len; ssize_t ret = 0; @@ -899,7 +899,7 @@ out: } ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, - int flags) + rwf_t flags) { if (!file->f_op->read_iter) return -EINVAL; @@ -908,7 +908,7 @@ ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, EXPORT_SYMBOL(vfs_iter_read); static ssize_t do_iter_write(struct file *file, struct iov_iter *iter, - loff_t *pos, int flags) + loff_t *pos, rwf_t flags) { size_t tot_len; ssize_t ret = 0; @@ -935,7 +935,7 @@ static ssize_t do_iter_write(struct file *file, struct iov_iter *iter, } ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, - int flags) + rwf_t flags) { if (!file->f_op->write_iter) return -EINVAL; @@ -944,7 +944,7 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, EXPORT_SYMBOL(vfs_iter_write); ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, - unsigned long vlen, loff_t *pos, int flags) + unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; @@ -962,7 +962,7 @@ ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, EXPORT_SYMBOL(vfs_readv); ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, - unsigned long vlen, loff_t *pos, int flags) + unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; @@ -981,7 +981,7 @@ ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, EXPORT_SYMBOL(vfs_writev); static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec, - unsigned long vlen, int flags) + unsigned long vlen, rwf_t flags) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; @@ -1001,7 +1001,7 @@ static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec, } static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec, - unsigned long vlen, int flags) + unsigned long vlen, rwf_t flags) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; @@ -1027,7 +1027,7 @@ static inline loff_t pos_from_hilo(unsigned long high, unsigned long low) } static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec, - unsigned long vlen, loff_t pos, int flags) + unsigned long vlen, loff_t pos, rwf_t flags) { struct fd f; ssize_t ret = -EBADF; @@ -1050,7 +1050,7 @@ static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec, } static ssize_t do_pwritev(unsigned long fd, const struct iovec __user *vec, - unsigned long vlen, loff_t pos, int flags) + unsigned long vlen, loff_t pos, rwf_t flags) { struct fd f; ssize_t ret = -EBADF; @@ -1094,7 +1094,7 @@ SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, SYSCALL_DEFINE6(preadv2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, - int, flags) + rwf_t, flags) { loff_t pos = pos_from_hilo(pos_h, pos_l); @@ -1114,7 +1114,7 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, - int, flags) + rwf_t, flags) { loff_t pos = pos_from_hilo(pos_h, pos_l); @@ -1127,7 +1127,7 @@ SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec, #ifdef CONFIG_COMPAT static size_t compat_readv(struct file *file, const struct compat_iovec __user *vec, - unsigned long vlen, loff_t *pos, int flags) + unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; @@ -1147,7 +1147,7 @@ static size_t compat_readv(struct file *file, static size_t do_compat_readv(compat_ulong_t fd, const struct compat_iovec __user *vec, - compat_ulong_t vlen, int flags) + compat_ulong_t vlen, rwf_t flags) { struct fd f = fdget_pos(fd); ssize_t ret; @@ -1173,7 +1173,7 @@ COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd, static long do_compat_preadv64(unsigned long fd, const struct compat_iovec __user *vec, - unsigned long vlen, loff_t pos, int flags) + unsigned long vlen, loff_t pos, rwf_t flags) { struct fd f; ssize_t ret; @@ -1211,7 +1211,7 @@ COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd, #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd, const struct compat_iovec __user *,vec, - unsigned long, vlen, loff_t, pos, int, flags) + unsigned long, vlen, loff_t, pos, rwf_t, flags) { return do_compat_preadv64(fd, vec, vlen, pos, flags); } @@ -1220,7 +1220,7 @@ COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd, COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd, const struct compat_iovec __user *,vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high, - int, flags) + rwf_t, flags) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; @@ -1232,7 +1232,7 @@ COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd, static size_t compat_writev(struct file *file, const struct compat_iovec __user *vec, - unsigned long vlen, loff_t *pos, int flags) + unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; @@ -1254,7 +1254,7 @@ static size_t compat_writev(struct file *file, static size_t do_compat_writev(compat_ulong_t fd, const struct compat_iovec __user* vec, - compat_ulong_t vlen, int flags) + compat_ulong_t vlen, rwf_t flags) { struct fd f = fdget_pos(fd); ssize_t ret; @@ -1279,7 +1279,7 @@ COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd, static long do_compat_pwritev64(unsigned long fd, const struct compat_iovec __user *vec, - unsigned long vlen, loff_t pos, int flags) + unsigned long vlen, loff_t pos, rwf_t flags) { struct fd f; ssize_t ret; @@ -1317,7 +1317,7 @@ COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd, #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd, const struct compat_iovec __user *,vec, - unsigned long, vlen, loff_t, pos, int, flags) + unsigned long, vlen, loff_t, pos, rwf_t, flags) { return do_compat_pwritev64(fd, vec, vlen, pos, flags); } @@ -1325,7 +1325,7 @@ COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd, COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd, const struct compat_iovec __user *,vec, - compat_ulong_t, vlen, u32, pos_low, u32, pos_high, int, flags) + compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; diff --git a/include/linux/compat.h b/include/linux/compat.h index e5d3fbe24f7d..3fc433303d7a 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -365,10 +365,10 @@ asmlinkage ssize_t compat_sys_pwritev(compat_ulong_t fd, compat_ulong_t vlen, u32 pos_low, u32 pos_high); asmlinkage ssize_t compat_sys_preadv2(compat_ulong_t fd, const struct compat_iovec __user *vec, - compat_ulong_t vlen, u32 pos_low, u32 pos_high, int flags); + compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags); asmlinkage ssize_t compat_sys_pwritev2(compat_ulong_t fd, const struct compat_iovec __user *vec, - compat_ulong_t vlen, u32 pos_low, u32 pos_high, int flags); + compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags); #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 asmlinkage long compat_sys_preadv64(unsigned long fd, @@ -382,6 +382,18 @@ asmlinkage long compat_sys_pwritev64(unsigned long fd, unsigned long vlen, loff_t pos); #endif +#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 +asmlinkage long compat_sys_readv64v2(unsigned long fd, + const struct compat_iovec __user *vec, + unsigned long vlen, loff_t pos, rwf_t flags); +#endif + +#ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 +asmlinkage long compat_sys_pwritev64v2(unsigned long fd, + const struct compat_iovec __user *vec, + unsigned long vlen, loff_t pos, rwf_t flags); +#endif + asmlinkage long compat_sys_lseek(unsigned int, compat_off_t, unsigned int); asmlinkage long compat_sys_execve(const char __user *filename, const compat_uptr_t __user *argv, diff --git a/include/linux/fs.h b/include/linux/fs.h index cbfe127bccf8..2625fc47c7e5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -72,6 +72,8 @@ extern int leases_enable, lease_break_time; extern int sysctl_protected_symlinks; extern int sysctl_protected_hardlinks; +typedef __kernel_rwf_t rwf_t; + struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); @@ -1758,9 +1760,9 @@ extern ssize_t __vfs_write(struct file *, const char __user *, size_t, loff_t *) extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_readv(struct file *, const struct iovec __user *, - unsigned long, loff_t *, int); + unsigned long, loff_t *, rwf_t); extern ssize_t vfs_writev(struct file *, const struct iovec __user *, - unsigned long, loff_t *, int); + unsigned long, loff_t *, rwf_t); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); extern int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, @@ -2874,9 +2876,9 @@ extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *); extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, - int flags); + rwf_t flags); ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, - int flags); + rwf_t flags); /* fs/block_dev.c */ extern ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to); @@ -3143,7 +3145,7 @@ static inline int iocb_flags(struct file *file) return res; } -static inline int kiocb_set_rw_flags(struct kiocb *ki, int flags) +static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) { if (unlikely(flags & ~RWF_SUPPORTED)) return -EOPNOTSUPP; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 0bc1d2e8cc17..138c94535864 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -579,12 +579,12 @@ asmlinkage long sys_preadv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, unsigned long pos_l, unsigned long pos_h); asmlinkage long sys_preadv2(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, unsigned long pos_l, unsigned long pos_h, - int flags); + rwf_t flags); asmlinkage long sys_pwritev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, unsigned long pos_l, unsigned long pos_h); asmlinkage long sys_pwritev2(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, unsigned long pos_l, unsigned long pos_h, - int flags); + rwf_t flags); asmlinkage long sys_getcwd(char __user *buf, unsigned long size); asmlinkage long sys_mkdir(const char __user *pathname, umode_t mode); asmlinkage long sys_chdir(const char __user *filename); diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h index a2d4a8ac94ca..a04adbc70ddf 100644 --- a/include/uapi/linux/aio_abi.h +++ b/include/uapi/linux/aio_abi.h @@ -28,6 +28,7 @@ #define __LINUX__AIO_ABI_H #include +#include #include typedef __kernel_ulong_t aio_context_t; @@ -62,14 +63,6 @@ struct io_event { __s64 res2; /* secondary result */ }; -#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN) -#define PADDED(x,y) x, y -#elif defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN) -#define PADDED(x,y) y, x -#else -#error edit for your odd byteorder. -#endif - /* * we always use a 64bit off_t when communicating * with userland. its up to libraries to do the @@ -79,8 +72,16 @@ struct io_event { struct iocb { /* these are internal to the kernel/libc. */ __u64 aio_data; /* data to be returned in event's data */ - __u32 PADDED(aio_key, aio_rw_flags); - /* the kernel sets aio_key to the req # */ + +#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN) + __u32 aio_key; /* the kernel sets aio_key to the req # */ + __kernel_rwf_t aio_rw_flags; /* RWF_* flags */ +#elif defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN) + __kernel_rwf_t aio_rw_flags; /* RWF_* flags */ + __u32 aio_key; /* the kernel sets aio_key to the req # */ +#else +#error edit for your odd byteorder. +#endif /* common fields */ __u16 aio_lio_opcode; /* see IOCB_CMD_ above */ diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index b7495d05e8de..56235dddea7d 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -358,13 +358,25 @@ struct fscrypt_key { #define SYNC_FILE_RANGE_WRITE 2 #define SYNC_FILE_RANGE_WAIT_AFTER 4 -/* flags for preadv2/pwritev2: */ -#define RWF_HIPRI 0x00000001 /* high priority request, poll if possible */ -#define RWF_DSYNC 0x00000002 /* per-IO O_DSYNC */ -#define RWF_SYNC 0x00000004 /* per-IO O_SYNC */ -#define RWF_NOWAIT 0x00000008 /* per-IO, return -EAGAIN if operation would block */ - -#define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC |\ - RWF_NOWAIT) +/* + * Flags for preadv2/pwritev2: + */ + +typedef int __bitwise __kernel_rwf_t; + +/* high priority request, poll if possible */ +#define RWF_HIPRI ((__force __kernel_rwf_t)0x00000001) + +/* per-IO O_DSYNC */ +#define RWF_DSYNC ((__force __kernel_rwf_t)0x00000002) + +/* per-IO O_SYNC */ +#define RWF_SYNC ((__force __kernel_rwf_t)0x00000004) + +/* per-IO, return -EAGAIN if operation would block */ +#define RWF_NOWAIT ((__force __kernel_rwf_t)0x00000008) + +/* mask of flags supported by the kernel */ +#define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT) #endif /* _UAPI_LINUX_FS_H */ -- cgit v1.2.3-71-gd317 From 1797f5b3cf0b3a73c42b89f7a8fd897417373730 Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Thu, 31 Aug 2017 17:59:12 +0200 Subject: devlink: Add IPv6 header for dpipe This will be used by the IPv6 host table which will be introduced in the following patches. The fields in the header are added per-use. This header is global and can be reused by many drivers. Signed-off-by: Arkadi Sharshevsky Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 1 + include/uapi/linux/devlink.h | 5 +++++ net/core/devlink.c | 17 +++++++++++++++++ 3 files changed, 23 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/devlink.h b/include/net/devlink.h index aaf7178127a2..b9654e133599 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -330,6 +330,7 @@ int devlink_dpipe_match_put(struct sk_buff *skb, struct devlink_dpipe_match *match); extern struct devlink_dpipe_header devlink_dpipe_header_ethernet; extern struct devlink_dpipe_header devlink_dpipe_header_ipv4; +extern struct devlink_dpipe_header devlink_dpipe_header_ipv6; #else diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 6c172548589d..0cbca96c66b9 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -234,9 +234,14 @@ enum devlink_dpipe_field_ipv4_id { DEVLINK_DPIPE_FIELD_IPV4_DST_IP, }; +enum devlink_dpipe_field_ipv6_id { + DEVLINK_DPIPE_FIELD_IPV6_DST_IP, +}; + enum devlink_dpipe_header_id { DEVLINK_DPIPE_HEADER_ETHERNET, DEVLINK_DPIPE_HEADER_IPV4, + DEVLINK_DPIPE_HEADER_IPV6, }; #endif /* _UAPI_LINUX_DEVLINK_H_ */ diff --git a/net/core/devlink.c b/net/core/devlink.c index cbc4b0461b0f..7d430c1d9c3e 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -63,6 +63,23 @@ struct devlink_dpipe_header devlink_dpipe_header_ipv4 = { }; EXPORT_SYMBOL(devlink_dpipe_header_ipv4); +static struct devlink_dpipe_field devlink_dpipe_fields_ipv6[] = { + { + .name = "destination ip", + .id = DEVLINK_DPIPE_FIELD_IPV6_DST_IP, + .bitwidth = 128, + }, +}; + +struct devlink_dpipe_header devlink_dpipe_header_ipv6 = { + .name = "ipv6", + .id = DEVLINK_DPIPE_HEADER_IPV6, + .fields = devlink_dpipe_fields_ipv6, + .fields_count = ARRAY_SIZE(devlink_dpipe_fields_ipv6), + .global = true, +}; +EXPORT_SYMBOL(devlink_dpipe_header_ipv6); + EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg); static LIST_HEAD(devlink_list); -- cgit v1.2.3-71-gd317 From 482dca939fb7ee35ba20b944b4c2476133dbf0df Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 31 Aug 2017 15:05:44 -0700 Subject: bpf: Add mark and priority to sock options that can be set Add socket mark and priority to fields that can be set by ebpf program when a socket is created. Signed-off-by: David Ahern Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 2 ++ net/core/filter.c | 26 ++++++++++++++++++++++++++ 2 files changed, 28 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 08c206a863e1..ba848b761cfb 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -758,6 +758,8 @@ struct bpf_sock { __u32 family; __u32 type; __u32 protocol; + __u32 mark; + __u32 priority; }; #define XDP_PACKET_HEADROOM 256 diff --git a/net/core/filter.c b/net/core/filter.c index c6a37fe0285b..f51b9690adf3 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3455,6 +3455,10 @@ static bool sock_filter_is_valid_access(int off, int size, switch (off) { case offsetof(struct bpf_sock, bound_dev_if): break; + case offsetof(struct bpf_sock, mark): + break; + case offsetof(struct bpf_sock, priority): + break; default: return false; } @@ -3958,6 +3962,28 @@ static u32 sock_filter_convert_ctx_access(enum bpf_access_type type, offsetof(struct sock, sk_bound_dev_if)); break; + case offsetof(struct bpf_sock, mark): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_mark) != 4); + + if (type == BPF_WRITE) + *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, + offsetof(struct sock, sk_mark)); + else + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, + offsetof(struct sock, sk_mark)); + break; + + case offsetof(struct bpf_sock, priority): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_priority) != 4); + + if (type == BPF_WRITE) + *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, + offsetof(struct sock, sk_priority)); + else + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, + offsetof(struct sock, sk_priority)); + break; + case offsetof(struct bpf_sock, family): BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_family) != 2); -- cgit v1.2.3-71-gd317 From abcc61537e3566cae7f1fd225f2dcb82b3595fe3 Mon Sep 17 00:00:00 2001 From: Colin Cross Date: Thu, 31 Aug 2017 10:04:24 +0200 Subject: ANDROID: binder: Add BINDER_GET_NODE_DEBUG_INFO ioctl The BINDER_GET_NODE_DEBUG_INFO ioctl will return debug info on a node. Each successive call reusing the previous return value will return the next node. The data will be used by libmemunreachable to mark the pointers with kernel references as reachable. Signed-off-by: Colin Cross Signed-off-by: Martijn Coenen Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 43 +++++++++++++++++++++++++++++++++++++ include/uapi/linux/android/binder.h | 14 ++++++++++++ 2 files changed, 57 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 8f2031c52ea4..eb8bd8d7c4c9 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -4389,6 +4389,31 @@ out: return ret; } +static int binder_ioctl_get_node_debug_info(struct binder_proc *proc, + struct binder_node_debug_info *info) +{ + struct rb_node *n; + binder_uintptr_t ptr = info->ptr; + + memset(info, 0, sizeof(*info)); + + binder_inner_proc_lock(proc); + for (n = rb_first(&proc->nodes); n != NULL; n = rb_next(n)) { + struct binder_node *node = rb_entry(n, struct binder_node, + rb_node); + if (node->ptr > ptr) { + info->ptr = node->ptr; + info->cookie = node->cookie; + info->has_strong_ref = node->has_strong_ref; + info->has_weak_ref = node->has_weak_ref; + break; + } + } + binder_inner_proc_unlock(proc); + + return 0; +} + static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { int ret; @@ -4458,6 +4483,24 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) } break; } + case BINDER_GET_NODE_DEBUG_INFO: { + struct binder_node_debug_info info; + + if (copy_from_user(&info, ubuf, sizeof(info))) { + ret = -EFAULT; + goto err; + } + + ret = binder_ioctl_get_node_debug_info(proc, &info); + if (ret < 0) + goto err; + + if (copy_to_user(ubuf, &info, sizeof(info))) { + ret = -EFAULT; + goto err; + } + break; + } default: ret = -EINVAL; goto err; diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h index 7668b5791c91..84a9a0944e13 100644 --- a/include/uapi/linux/android/binder.h +++ b/include/uapi/linux/android/binder.h @@ -186,6 +186,19 @@ struct binder_version { #define BINDER_CURRENT_PROTOCOL_VERSION 8 #endif +/* + * Use with BINDER_GET_NODE_DEBUG_INFO, driver reads ptr, writes to all fields. + * Set ptr to NULL for the first call to get the info for the first node, and + * then repeat the call passing the previously returned value to get the next + * nodes. ptr will be 0 when there are no more nodes. + */ +struct binder_node_debug_info { + binder_uintptr_t ptr; + binder_uintptr_t cookie; + __u32 has_strong_ref; + __u32 has_weak_ref; +}; + #define BINDER_WRITE_READ _IOWR('b', 1, struct binder_write_read) #define BINDER_SET_IDLE_TIMEOUT _IOW('b', 3, __s64) #define BINDER_SET_MAX_THREADS _IOW('b', 5, __u32) @@ -193,6 +206,7 @@ struct binder_version { #define BINDER_SET_CONTEXT_MGR _IOW('b', 7, __s32) #define BINDER_THREAD_EXIT _IOW('b', 8, __s32) #define BINDER_VERSION _IOWR('b', 9, struct binder_version) +#define BINDER_GET_NODE_DEBUG_INFO _IOWR('b', 11, struct binder_node_debug_info) /* * NOTE: Two special error codes you should check for when calling -- cgit v1.2.3-71-gd317 From 8db6c34f1dbc8e06aa016a9b829b06902c3e1340 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Mon, 8 May 2017 13:11:56 -0500 Subject: Introduce v3 namespaced file capabilities Root in a non-initial user ns cannot be trusted to write a traditional security.capability xattr. If it were allowed to do so, then any unprivileged user on the host could map his own uid to root in a private namespace, write the xattr, and execute the file with privilege on the host. However supporting file capabilities in a user namespace is very desirable. Not doing so means that any programs designed to run with limited privilege must continue to support other methods of gaining and dropping privilege. For instance a program installer must detect whether file capabilities can be assigned, and assign them if so but set setuid-root otherwise. The program in turn must know how to drop partial capabilities, and do so only if setuid-root. This patch introduces v3 of the security.capability xattr. It builds a vfs_ns_cap_data struct by appending a uid_t rootid to struct vfs_cap_data. This is the absolute uid_t (that is, the uid_t in user namespace which mounted the filesystem, usually init_user_ns) of the root id in whose namespaces the file capabilities may take effect. When a task asks to write a v2 security.capability xattr, if it is privileged with respect to the userns which mounted the filesystem, then nothing should change. Otherwise, the kernel will transparently rewrite the xattr as a v3 with the appropriate rootid. This is done during the execution of setxattr() to catch user-space-initiated capability writes. Subsequently, any task executing the file which has the noted kuid as its root uid, or which is in a descendent user_ns of such a user_ns, will run the file with capabilities. Similarly when asking to read file capabilities, a v3 capability will be presented as v2 if it applies to the caller's namespace. If a task writes a v3 security.capability, then it can provide a uid for the xattr so long as the uid is valid in its own user namespace, and it is privileged with CAP_SETFCAP over its namespace. The kernel will translate that rootid to an absolute uid, and write that to disk. After this, a task in the writer's namespace will not be able to use those capabilities (unless rootid was 0), but a task in a namespace where the given uid is root will. Only a single security.capability xattr may exist at a time for a given file. A task may overwrite an existing xattr so long as it is privileged over the inode. Note this is a departure from previous semantics, which required privilege to remove a security.capability xattr. This check can be re-added if deemed useful. This allows a simple setxattr to work, allows tar/untar to work, and allows us to tar in one namespace and untar in another while preserving the capability, without risking leaking privilege into a parent namespace. Example using tar: $ cp /bin/sleep sleepx $ mkdir b1 b2 $ lxc-usernsexec -m b:0:100000:1 -m b:1:$(id -u):1 -- chown 0:0 b1 $ lxc-usernsexec -m b:0:100001:1 -m b:1:$(id -u):1 -- chown 0:0 b2 $ lxc-usernsexec -m b:0:100000:1000 -- tar --xattrs-include=security.capability --xattrs -cf b1/sleepx.tar sleepx $ lxc-usernsexec -m b:0:100001:1000 -- tar --xattrs-include=security.capability --xattrs -C b2 -xf b1/sleepx.tar $ lxc-usernsexec -m b:0:100001:1000 -- getcap b2/sleepx b2/sleepx = cap_sys_admin+ep # /opt/ltp/testcases/bin/getv3xattr b2/sleepx v3 xattr, rootid is 100001 A patch to linux-test-project adding a new set of tests for this functionality is in the nsfscaps branch at github.com/hallyn/ltp Changelog: Nov 02 2016: fix invalid check at refuse_fcap_overwrite() Nov 07 2016: convert rootid from and to fs user_ns (From ebiederm: mar 28 2017) commoncap.c: fix typos - s/v4/v3 get_vfs_caps_from_disk: clarify the fs_ns root access check nsfscaps: change the code split for cap_inode_setxattr() Apr 09 2017: don't return v3 cap for caps owned by current root. return a v2 cap for a true v2 cap in non-init ns Apr 18 2017: . Change the flow of fscap writing to support s_user_ns writing. . Remove refuse_fcap_overwrite(). The value of the previous xattr doesn't matter. Apr 24 2017: . incorporate Eric's incremental diff . move cap_convert_nscap to setxattr and simplify its usage May 8, 2017: . fix leaking dentry refcount in cap_inode_getsecurity Signed-off-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- fs/xattr.c | 6 + include/linux/capability.h | 2 + include/linux/security.h | 2 + include/uapi/linux/capability.h | 22 +++- security/commoncap.c | 270 +++++++++++++++++++++++++++++++++++++--- 5 files changed, 280 insertions(+), 22 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/xattr.c b/fs/xattr.c index 464c94bf65f9..7b03df6b8be2 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -441,6 +441,12 @@ setxattr(struct dentry *d, const char __user *name, const void __user *value, if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) posix_acl_fix_xattr_from_user(kvalue, size); + else if (strcmp(kname, XATTR_NAME_CAPS) == 0) { + error = cap_convert_nscap(d, &kvalue, size); + if (error < 0) + goto out; + size = error; + } } error = vfs_setxattr(d, kname, kvalue, size, flags); diff --git a/include/linux/capability.h b/include/linux/capability.h index 6ffb67e10c06..b52e278e4744 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -248,4 +248,6 @@ extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns); /* audit system wants to get cap info from files as well */ extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); +extern int cap_convert_nscap(struct dentry *dentry, void **ivalue, size_t size); + #endif /* !_LINUX_CAPABILITY_H */ diff --git a/include/linux/security.h b/include/linux/security.h index b6ea1dc9cc9d..6fff8c924718 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -91,6 +91,8 @@ extern int cap_inode_setxattr(struct dentry *dentry, const char *name, extern int cap_inode_removexattr(struct dentry *dentry, const char *name); extern int cap_inode_need_killpriv(struct dentry *dentry); extern int cap_inode_killpriv(struct dentry *dentry); +extern int cap_inode_getsecurity(struct inode *inode, const char *name, + void **buffer, bool alloc); extern int cap_mmap_addr(unsigned long addr); extern int cap_mmap_file(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags); diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h index 6fe14d001f68..230e05d35191 100644 --- a/include/uapi/linux/capability.h +++ b/include/uapi/linux/capability.h @@ -60,9 +60,13 @@ typedef struct __user_cap_data_struct { #define VFS_CAP_U32_2 2 #define XATTR_CAPS_SZ_2 (sizeof(__le32)*(1 + 2*VFS_CAP_U32_2)) -#define XATTR_CAPS_SZ XATTR_CAPS_SZ_2 -#define VFS_CAP_U32 VFS_CAP_U32_2 -#define VFS_CAP_REVISION VFS_CAP_REVISION_2 +#define VFS_CAP_REVISION_3 0x03000000 +#define VFS_CAP_U32_3 2 +#define XATTR_CAPS_SZ_3 (sizeof(__le32)*(2 + 2*VFS_CAP_U32_3)) + +#define XATTR_CAPS_SZ XATTR_CAPS_SZ_3 +#define VFS_CAP_U32 VFS_CAP_U32_3 +#define VFS_CAP_REVISION VFS_CAP_REVISION_3 struct vfs_cap_data { __le32 magic_etc; /* Little endian */ @@ -72,6 +76,18 @@ struct vfs_cap_data { } data[VFS_CAP_U32]; }; +/* + * same as vfs_cap_data but with a rootid at the end + */ +struct vfs_ns_cap_data { + __le32 magic_etc; + struct { + __le32 permitted; /* Little endian */ + __le32 inheritable; /* Little endian */ + } data[VFS_CAP_U32]; + __le32 rootid; +}; + #ifndef __KERNEL__ /* diff --git a/security/commoncap.c b/security/commoncap.c index d59320282294..c37d27dd1e2c 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -335,6 +335,209 @@ int cap_inode_killpriv(struct dentry *dentry) return error; } +static bool rootid_owns_currentns(kuid_t kroot) +{ + struct user_namespace *ns; + + if (!uid_valid(kroot)) + return false; + + for (ns = current_user_ns(); ; ns = ns->parent) { + if (from_kuid(ns, kroot) == 0) + return true; + if (ns == &init_user_ns) + break; + } + + return false; +} + +static __u32 sansflags(__u32 m) +{ + return m & ~VFS_CAP_FLAGS_EFFECTIVE; +} + +static bool is_v2header(size_t size, __le32 magic) +{ + __u32 m = le32_to_cpu(magic); + if (size != XATTR_CAPS_SZ_2) + return false; + return sansflags(m) == VFS_CAP_REVISION_2; +} + +static bool is_v3header(size_t size, __le32 magic) +{ + __u32 m = le32_to_cpu(magic); + + if (size != XATTR_CAPS_SZ_3) + return false; + return sansflags(m) == VFS_CAP_REVISION_3; +} + +/* + * getsecurity: We are called for security.* before any attempt to read the + * xattr from the inode itself. + * + * This gives us a chance to read the on-disk value and convert it. If we + * return -EOPNOTSUPP, then vfs_getxattr() will call the i_op handler. + * + * Note we are not called by vfs_getxattr_alloc(), but that is only called + * by the integrity subsystem, which really wants the unconverted values - + * so that's good. + */ +int cap_inode_getsecurity(struct inode *inode, const char *name, void **buffer, + bool alloc) +{ + int size, ret; + kuid_t kroot; + uid_t root, mappedroot; + char *tmpbuf = NULL; + struct vfs_cap_data *cap; + struct vfs_ns_cap_data *nscap; + struct dentry *dentry; + struct user_namespace *fs_ns; + + if (strcmp(name, "capability") != 0) + return -EOPNOTSUPP; + + dentry = d_find_alias(inode); + if (!dentry) + return -EINVAL; + + size = sizeof(struct vfs_ns_cap_data); + ret = (int) vfs_getxattr_alloc(dentry, XATTR_NAME_CAPS, + &tmpbuf, size, GFP_NOFS); + dput(dentry); + + if (ret < 0) + return ret; + + fs_ns = inode->i_sb->s_user_ns; + cap = (struct vfs_cap_data *) tmpbuf; + if (is_v2header((size_t) ret, cap->magic_etc)) { + /* If this is sizeof(vfs_cap_data) then we're ok with the + * on-disk value, so return that. */ + if (alloc) + *buffer = tmpbuf; + else + kfree(tmpbuf); + return ret; + } else if (!is_v3header((size_t) ret, cap->magic_etc)) { + kfree(tmpbuf); + return -EINVAL; + } + + nscap = (struct vfs_ns_cap_data *) tmpbuf; + root = le32_to_cpu(nscap->rootid); + kroot = make_kuid(fs_ns, root); + + /* If the root kuid maps to a valid uid in current ns, then return + * this as a nscap. */ + mappedroot = from_kuid(current_user_ns(), kroot); + if (mappedroot != (uid_t)-1 && mappedroot != (uid_t)0) { + if (alloc) { + *buffer = tmpbuf; + nscap->rootid = cpu_to_le32(mappedroot); + } else + kfree(tmpbuf); + return size; + } + + if (!rootid_owns_currentns(kroot)) { + kfree(tmpbuf); + return -EOPNOTSUPP; + } + + /* This comes from a parent namespace. Return as a v2 capability */ + size = sizeof(struct vfs_cap_data); + if (alloc) { + *buffer = kmalloc(size, GFP_ATOMIC); + if (*buffer) { + struct vfs_cap_data *cap = *buffer; + __le32 nsmagic, magic; + magic = VFS_CAP_REVISION_2; + nsmagic = le32_to_cpu(nscap->magic_etc); + if (nsmagic & VFS_CAP_FLAGS_EFFECTIVE) + magic |= VFS_CAP_FLAGS_EFFECTIVE; + memcpy(&cap->data, &nscap->data, sizeof(__le32) * 2 * VFS_CAP_U32); + cap->magic_etc = cpu_to_le32(magic); + } + } + kfree(tmpbuf); + return size; +} + +static kuid_t rootid_from_xattr(const void *value, size_t size, + struct user_namespace *task_ns) +{ + const struct vfs_ns_cap_data *nscap = value; + uid_t rootid = 0; + + if (size == XATTR_CAPS_SZ_3) + rootid = le32_to_cpu(nscap->rootid); + + return make_kuid(task_ns, rootid); +} + +static bool validheader(size_t size, __le32 magic) +{ + return is_v2header(size, magic) || is_v3header(size, magic); +} + +/* + * User requested a write of security.capability. If needed, update the + * xattr to change from v2 to v3, or to fixup the v3 rootid. + * + * If all is ok, we return the new size, on error return < 0. + */ +int cap_convert_nscap(struct dentry *dentry, void **ivalue, size_t size) +{ + struct vfs_ns_cap_data *nscap; + uid_t nsrootid; + const struct vfs_cap_data *cap = *ivalue; + __u32 magic, nsmagic; + struct inode *inode = d_backing_inode(dentry); + struct user_namespace *task_ns = current_user_ns(), + *fs_ns = inode->i_sb->s_user_ns; + kuid_t rootid; + size_t newsize; + + if (!*ivalue) + return -EINVAL; + if (!validheader(size, cap->magic_etc)) + return -EINVAL; + if (!capable_wrt_inode_uidgid(inode, CAP_SETFCAP)) + return -EPERM; + if (size == XATTR_CAPS_SZ_2) + if (ns_capable(inode->i_sb->s_user_ns, CAP_SETFCAP)) + /* user is privileged, just write the v2 */ + return size; + + rootid = rootid_from_xattr(*ivalue, size, task_ns); + if (!uid_valid(rootid)) + return -EINVAL; + + nsrootid = from_kuid(fs_ns, rootid); + if (nsrootid == -1) + return -EINVAL; + + newsize = sizeof(struct vfs_ns_cap_data); + nscap = kmalloc(newsize, GFP_ATOMIC); + if (!nscap) + return -ENOMEM; + nscap->rootid = cpu_to_le32(nsrootid); + nsmagic = VFS_CAP_REVISION_3; + magic = le32_to_cpu(cap->magic_etc); + if (magic & VFS_CAP_FLAGS_EFFECTIVE) + nsmagic |= VFS_CAP_FLAGS_EFFECTIVE; + nscap->magic_etc = cpu_to_le32(nsmagic); + memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32); + + kvfree(*ivalue); + *ivalue = nscap; + return newsize; +} + /* * Calculate the new process capability sets from the capability sets attached * to a file. @@ -388,7 +591,10 @@ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data __u32 magic_etc; unsigned tocopy, i; int size; - struct vfs_cap_data caps; + struct vfs_ns_cap_data data, *nscaps = &data; + struct vfs_cap_data *caps = (struct vfs_cap_data *) &data; + kuid_t rootkuid; + struct user_namespace *fs_ns = inode->i_sb->s_user_ns; memset(cpu_caps, 0, sizeof(struct cpu_vfs_cap_data)); @@ -396,18 +602,20 @@ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data return -ENODATA; size = __vfs_getxattr((struct dentry *)dentry, inode, - XATTR_NAME_CAPS, &caps, XATTR_CAPS_SZ); + XATTR_NAME_CAPS, &data, XATTR_CAPS_SZ); if (size == -ENODATA || size == -EOPNOTSUPP) /* no data, that's ok */ return -ENODATA; + if (size < 0) return size; if (size < sizeof(magic_etc)) return -EINVAL; - cpu_caps->magic_etc = magic_etc = le32_to_cpu(caps.magic_etc); + cpu_caps->magic_etc = magic_etc = le32_to_cpu(caps->magic_etc); + rootkuid = make_kuid(fs_ns, 0); switch (magic_etc & VFS_CAP_REVISION_MASK) { case VFS_CAP_REVISION_1: if (size != XATTR_CAPS_SZ_1) @@ -419,15 +627,27 @@ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data return -EINVAL; tocopy = VFS_CAP_U32_2; break; + case VFS_CAP_REVISION_3: + if (size != XATTR_CAPS_SZ_3) + return -EINVAL; + tocopy = VFS_CAP_U32_3; + rootkuid = make_kuid(fs_ns, le32_to_cpu(nscaps->rootid)); + break; + default: return -EINVAL; } + /* Limit the caps to the mounter of the filesystem + * or the more limited uid specified in the xattr. + */ + if (!rootid_owns_currentns(rootkuid)) + return -ENODATA; CAP_FOR_EACH_U32(i) { if (i >= tocopy) break; - cpu_caps->permitted.cap[i] = le32_to_cpu(caps.data[i].permitted); - cpu_caps->inheritable.cap[i] = le32_to_cpu(caps.data[i].inheritable); + cpu_caps->permitted.cap[i] = le32_to_cpu(caps->data[i].permitted); + cpu_caps->inheritable.cap[i] = le32_to_cpu(caps->data[i].inheritable); } cpu_caps->permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; @@ -465,8 +685,8 @@ static int get_file_caps(struct linux_binprm *bprm, bool *effective, bool *has_c rc = get_vfs_caps_from_disk(bprm->file->f_path.dentry, &vcaps); if (rc < 0) { if (rc == -EINVAL) - printk(KERN_NOTICE "%s: get_vfs_caps_from_disk returned %d for %s\n", - __func__, rc, bprm->filename); + printk(KERN_NOTICE "Invalid argument reading file caps for %s\n", + bprm->filename); else if (rc == -ENODATA) rc = 0; goto out; @@ -663,15 +883,19 @@ int cap_bprm_secureexec(struct linux_binprm *bprm) int cap_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { - if (!strcmp(name, XATTR_NAME_CAPS)) { - if (!capable(CAP_SETFCAP)) - return -EPERM; + /* Ignore non-security xattrs */ + if (strncmp(name, XATTR_SECURITY_PREFIX, + sizeof(XATTR_SECURITY_PREFIX) - 1) != 0) + return 0; + + /* + * For XATTR_NAME_CAPS the check will be done in + * cap_convert_nscap(), called by setxattr() + */ + if (strcmp(name, XATTR_NAME_CAPS) == 0) return 0; - } - if (!strncmp(name, XATTR_SECURITY_PREFIX, - sizeof(XATTR_SECURITY_PREFIX) - 1) && - !capable(CAP_SYS_ADMIN)) + if (!capable(CAP_SYS_ADMIN)) return -EPERM; return 0; } @@ -689,15 +913,22 @@ int cap_inode_setxattr(struct dentry *dentry, const char *name, */ int cap_inode_removexattr(struct dentry *dentry, const char *name) { - if (!strcmp(name, XATTR_NAME_CAPS)) { - if (!capable(CAP_SETFCAP)) + /* Ignore non-security xattrs */ + if (strncmp(name, XATTR_SECURITY_PREFIX, + sizeof(XATTR_SECURITY_PREFIX) - 1) != 0) + return 0; + + if (strcmp(name, XATTR_NAME_CAPS) == 0) { + /* security.capability gets namespaced */ + struct inode *inode = d_backing_inode(dentry); + if (!inode) + return -EINVAL; + if (!capable_wrt_inode_uidgid(inode, CAP_SETFCAP)) return -EPERM; return 0; } - if (!strncmp(name, XATTR_SECURITY_PREFIX, - sizeof(XATTR_SECURITY_PREFIX) - 1) && - !capable(CAP_SYS_ADMIN)) + if (!capable(CAP_SYS_ADMIN)) return -EPERM; return 0; } @@ -1085,6 +1316,7 @@ struct security_hook_list capability_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(bprm_secureexec, cap_bprm_secureexec), LSM_HOOK_INIT(inode_need_killpriv, cap_inode_need_killpriv), LSM_HOOK_INIT(inode_killpriv, cap_inode_killpriv), + LSM_HOOK_INIT(inode_getsecurity, cap_inode_getsecurity), LSM_HOOK_INIT(mmap_addr, cap_mmap_addr), LSM_HOOK_INIT(mmap_file, cap_mmap_file), LSM_HOOK_INIT(task_fix_setuid, cap_task_fix_setuid), -- cgit v1.2.3-71-gd317 From d897246df9fc0a5df97a784bf7b072be4a6ae479 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Thu, 31 Aug 2017 13:47:35 -0700 Subject: fsmap: fix documentation of FMR_OF_LAST The FMR_OF_LAST flag is set on the last fsmap record being returned for the dataset requested, contrary to what the header file says. Fix the docs to reflect the behavior of all fsmap implementations. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- include/uapi/linux/fsmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/fsmap.h b/include/uapi/linux/fsmap.h index 7e8e5f0bd6d2..e5213c3e38b2 100644 --- a/include/uapi/linux/fsmap.h +++ b/include/uapi/linux/fsmap.h @@ -96,7 +96,7 @@ fsmap_advance( #define FMR_OF_EXTENT_MAP 0x4 /* segment = extent map */ #define FMR_OF_SHARED 0x8 /* segment = shared with another file */ #define FMR_OF_SPECIAL_OWNER 0x10 /* owner is a special value */ -#define FMR_OF_LAST 0x20 /* segment is the last in the FS */ +#define FMR_OF_LAST 0x20 /* segment is the last in the dataset */ /* Each FS gets to define its own special owner codes. */ #define FMR_OWNER(type, code) (((__u64)type << 32) | \ -- cgit v1.2.3-71-gd317 From c03fa9bcacd9ac04595cc13f34f3445f0a5ecf13 Mon Sep 17 00:00:00 2001 From: Ivan Delalande Date: Thu, 31 Aug 2017 09:59:39 -0700 Subject: tcp_diag: report TCP MD5 signing keys and addresses Report TCP MD5 (RFC2385) signing keys, addresses and address prefixes to processes with CAP_NET_ADMIN requesting INET_DIAG_INFO. Currently it is not possible to retrieve these from the kernel once they have been configured on sockets. Signed-off-by: Ivan Delalande Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/uapi/linux/inet_diag.h | 1 + include/uapi/linux/tcp.h | 9 ++++ net/ipv4/tcp_diag.c | 109 ++++++++++++++++++++++++++++++++++++++--- 3 files changed, 113 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h index 678496897a68..f52ff62bfabe 100644 --- a/include/uapi/linux/inet_diag.h +++ b/include/uapi/linux/inet_diag.h @@ -143,6 +143,7 @@ enum { INET_DIAG_MARK, INET_DIAG_BBRINFO, INET_DIAG_CLASS_ID, + INET_DIAG_MD5SIG, __INET_DIAG_MAX, }; diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 030e594bab45..15c25eccab2b 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -256,4 +256,13 @@ struct tcp_md5sig { __u8 tcpm_key[TCP_MD5SIG_MAXKEYLEN]; /* key (binary) */ }; +/* INET_DIAG_MD5SIG */ +struct tcp_diag_md5sig { + __u8 tcpm_family; + __u8 tcpm_prefixlen; + __u16 tcpm_keylen; + __be32 tcpm_addr[4]; + __u8 tcpm_key[TCP_MD5SIG_MAXKEYLEN]; +}; + #endif /* _UAPI_LINUX_TCP_H */ diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index a748c74aa8b7..abbf0edcf6c2 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -16,6 +16,7 @@ #include +#include #include static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, @@ -36,6 +37,100 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, tcp_get_info(sk, info); } +#ifdef CONFIG_TCP_MD5SIG +static void tcp_diag_md5sig_fill(struct tcp_diag_md5sig *info, + const struct tcp_md5sig_key *key) +{ + info->tcpm_family = key->family; + info->tcpm_prefixlen = key->prefixlen; + info->tcpm_keylen = key->keylen; + memcpy(info->tcpm_key, key->key, key->keylen); + + if (key->family == AF_INET) + info->tcpm_addr[0] = key->addr.a4.s_addr; + #if IS_ENABLED(CONFIG_IPV6) + else if (key->family == AF_INET6) + memcpy(&info->tcpm_addr, &key->addr.a6, + sizeof(info->tcpm_addr)); + #endif +} + +static int tcp_diag_put_md5sig(struct sk_buff *skb, + const struct tcp_md5sig_info *md5sig) +{ + const struct tcp_md5sig_key *key; + struct tcp_diag_md5sig *info; + struct nlattr *attr; + int md5sig_count = 0; + + hlist_for_each_entry_rcu(key, &md5sig->head, node) + md5sig_count++; + if (md5sig_count == 0) + return 0; + + attr = nla_reserve(skb, INET_DIAG_MD5SIG, + md5sig_count * sizeof(struct tcp_diag_md5sig)); + if (!attr) + return -EMSGSIZE; + + info = nla_data(attr); + memset(info, 0, md5sig_count * sizeof(struct tcp_diag_md5sig)); + hlist_for_each_entry_rcu(key, &md5sig->head, node) { + tcp_diag_md5sig_fill(info++, key); + if (--md5sig_count == 0) + break; + } + + return 0; +} +#endif + +static int tcp_diag_get_aux(struct sock *sk, bool net_admin, + struct sk_buff *skb) +{ +#ifdef CONFIG_TCP_MD5SIG + if (net_admin) { + struct tcp_md5sig_info *md5sig; + int err = 0; + + rcu_read_lock(); + md5sig = rcu_dereference(tcp_sk(sk)->md5sig_info); + if (md5sig) + err = tcp_diag_put_md5sig(skb, md5sig); + rcu_read_unlock(); + if (err < 0) + return err; + } +#endif + + return 0; +} + +static size_t tcp_diag_get_aux_size(struct sock *sk, bool net_admin) +{ + size_t size = 0; + +#ifdef CONFIG_TCP_MD5SIG + if (net_admin && sk_fullsock(sk)) { + const struct tcp_md5sig_info *md5sig; + const struct tcp_md5sig_key *key; + size_t md5sig_count = 0; + + rcu_read_lock(); + md5sig = rcu_dereference(tcp_sk(sk)->md5sig_info); + if (md5sig) { + hlist_for_each_entry_rcu(key, &md5sig->head, node) + md5sig_count++; + } + rcu_read_unlock(); + size += nla_total_size(md5sig_count * + sizeof(struct tcp_diag_md5sig)); + } +#endif + + return size; +} + static void tcp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r, struct nlattr *bc) { @@ -68,13 +163,15 @@ static int tcp_diag_destroy(struct sk_buff *in_skb, #endif static const struct inet_diag_handler tcp_diag_handler = { - .dump = tcp_diag_dump, - .dump_one = tcp_diag_dump_one, - .idiag_get_info = tcp_diag_get_info, - .idiag_type = IPPROTO_TCP, - .idiag_info_size = sizeof(struct tcp_info), + .dump = tcp_diag_dump, + .dump_one = tcp_diag_dump_one, + .idiag_get_info = tcp_diag_get_info, + .idiag_get_aux = tcp_diag_get_aux, + .idiag_get_aux_size = tcp_diag_get_aux_size, + .idiag_type = IPPROTO_TCP, + .idiag_info_size = sizeof(struct tcp_info), #ifdef CONFIG_INET_DIAG_DESTROY - .destroy = tcp_diag_destroy, + .destroy = tcp_diag_destroy, #endif }; -- cgit v1.2.3-71-gd317 From bea74641e3786d51dcf1175527cc1781420961c9 Mon Sep 17 00:00:00 2001 From: Vishwanath Pai Date: Fri, 18 Aug 2017 20:58:59 +0200 Subject: netfilter: xt_hashlimit: add rate match mode This patch adds a new feature to hashlimit that allows matching on the current packet/byte rate without rate limiting. This can be enabled with a new flag --hashlimit-rate-match. The match returns true if the current rate of packets is above/below the user specified value. The main difference between the existing algorithm and the new one is that the existing algorithm rate-limits the flow whereas the new algorithm does not. Instead it *classifies* the flow based on whether it is above or below a certain rate. I will demonstrate this with an example below. Let us assume this rule: iptables -A INPUT -m hashlimit --hashlimit-above 10/s -j new_chain If the packet rate is 15/s, the existing algorithm would ACCEPT 10 packets every second and send 5 packets to "new_chain". But with the new algorithm, as long as the rate of 15/s is sustained, all packets will continue to match and every packet is sent to new_chain. This new functionality will let us classify different flows based on their current rate, so that further decisions can be made on them based on what the current rate is. This is how the new algorithm works: We divide time into intervals of 1 (sec/min/hour) as specified by the user. We keep track of the number of packets/bytes processed in the current interval. After each interval we reset the counter to 0. When we receive a packet for match, we look at the packet rate during the current interval and the previous interval to make a decision: if [ prev_rate < user and cur_rate < user ] return Below else return Above Where cur_rate is the number of packets/bytes seen in the current interval, prev is the number of packets/bytes seen in the previous interval and 'user' is the rate specified by the user. We also provide flexibility to the user for choosing the time interval using the option --hashilmit-interval. For example the user can keep a low rate like x/hour but still keep the interval as small as 1 second. To preserve backwards compatibility we have to add this feature in a new revision, so I've created revision 3 for hashlimit. The two new options we add are: --hashlimit-rate-match --hashlimit-rate-interval I have updated the help text to add these new options. Also added a few tests for the new options. Suggested-by: Igor Lubashev Reviewed-by: Josh Hunt Signed-off-by: Vishwanath Pai Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/xt_hashlimit.h | 3 +- include/uapi/linux/netfilter/xt_hashlimit.h | 36 +++- net/netfilter/xt_hashlimit.c | 277 +++++++++++++++++++++++++--- 3 files changed, 285 insertions(+), 31 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/netfilter/xt_hashlimit.h b/include/linux/netfilter/xt_hashlimit.h index 074790c0cf74..0fc458bde80b 100644 --- a/include/linux/netfilter/xt_hashlimit.h +++ b/include/linux/netfilter/xt_hashlimit.h @@ -5,5 +5,6 @@ #define XT_HASHLIMIT_ALL (XT_HASHLIMIT_HASH_DIP | XT_HASHLIMIT_HASH_DPT | \ XT_HASHLIMIT_HASH_SIP | XT_HASHLIMIT_HASH_SPT | \ - XT_HASHLIMIT_INVERT | XT_HASHLIMIT_BYTES) + XT_HASHLIMIT_INVERT | XT_HASHLIMIT_BYTES |\ + XT_HASHLIMIT_RATE_MATCH) #endif /*_XT_HASHLIMIT_H*/ diff --git a/include/uapi/linux/netfilter/xt_hashlimit.h b/include/uapi/linux/netfilter/xt_hashlimit.h index 79da349f1060..aa98573248b1 100644 --- a/include/uapi/linux/netfilter/xt_hashlimit.h +++ b/include/uapi/linux/netfilter/xt_hashlimit.h @@ -19,12 +19,13 @@ struct xt_hashlimit_htable; enum { - XT_HASHLIMIT_HASH_DIP = 1 << 0, - XT_HASHLIMIT_HASH_DPT = 1 << 1, - XT_HASHLIMIT_HASH_SIP = 1 << 2, - XT_HASHLIMIT_HASH_SPT = 1 << 3, - XT_HASHLIMIT_INVERT = 1 << 4, - XT_HASHLIMIT_BYTES = 1 << 5, + XT_HASHLIMIT_HASH_DIP = 1 << 0, + XT_HASHLIMIT_HASH_DPT = 1 << 1, + XT_HASHLIMIT_HASH_SIP = 1 << 2, + XT_HASHLIMIT_HASH_SPT = 1 << 3, + XT_HASHLIMIT_INVERT = 1 << 4, + XT_HASHLIMIT_BYTES = 1 << 5, + XT_HASHLIMIT_RATE_MATCH = 1 << 6, }; struct hashlimit_cfg { @@ -79,6 +80,21 @@ struct hashlimit_cfg2 { __u8 srcmask, dstmask; }; +struct hashlimit_cfg3 { + __u64 avg; /* Average secs between packets * scale */ + __u64 burst; /* Period multiplier for upper limit. */ + __u32 mode; /* bitmask of XT_HASHLIMIT_HASH_* */ + + /* user specified */ + __u32 size; /* how many buckets */ + __u32 max; /* max number of entries */ + __u32 gc_interval; /* gc interval */ + __u32 expire; /* when do entries expire? */ + + __u32 interval; + __u8 srcmask, dstmask; +}; + struct xt_hashlimit_mtinfo1 { char name[IFNAMSIZ]; struct hashlimit_cfg1 cfg; @@ -95,4 +111,12 @@ struct xt_hashlimit_mtinfo2 { struct xt_hashlimit_htable *hinfo __attribute__((aligned(8))); }; +struct xt_hashlimit_mtinfo3 { + char name[NAME_MAX]; + struct hashlimit_cfg3 cfg; + + /* Used internally by the kernel */ + struct xt_hashlimit_htable *hinfo __attribute__((aligned(8))); +}; + #endif /* _UAPI_XT_HASHLIMIT_H */ diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index ffdb611e54a2..10d48234f5f4 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -56,6 +56,7 @@ static inline struct hashlimit_net *hashlimit_pernet(struct net *net) } /* need to declare this at the top */ +static const struct file_operations dl_file_ops_v2; static const struct file_operations dl_file_ops_v1; static const struct file_operations dl_file_ops; @@ -87,8 +88,19 @@ struct dsthash_ent { unsigned long expires; /* precalculated expiry time */ struct { unsigned long prev; /* last modification */ - u_int64_t credit; - u_int64_t credit_cap, cost; + union { + struct { + u_int64_t credit; + u_int64_t credit_cap; + u_int64_t cost; + }; + struct { + u_int32_t interval, prev_window; + u_int64_t current_rate; + u_int64_t rate; + int64_t burst; + }; + }; } rateinfo; struct rcu_head rcu; }; @@ -99,7 +111,7 @@ struct xt_hashlimit_htable { u_int8_t family; bool rnd_initialized; - struct hashlimit_cfg2 cfg; /* config */ + struct hashlimit_cfg3 cfg; /* config */ /* used internally */ spinlock_t lock; /* lock for list_head */ @@ -116,10 +128,10 @@ struct xt_hashlimit_htable { }; static int -cfg_copy(struct hashlimit_cfg2 *to, void *from, int revision) +cfg_copy(struct hashlimit_cfg3 *to, const void *from, int revision) { if (revision == 1) { - struct hashlimit_cfg1 *cfg = from; + struct hashlimit_cfg1 *cfg = (struct hashlimit_cfg1 *)from; to->mode = cfg->mode; to->avg = cfg->avg; @@ -131,7 +143,19 @@ cfg_copy(struct hashlimit_cfg2 *to, void *from, int revision) to->srcmask = cfg->srcmask; to->dstmask = cfg->dstmask; } else if (revision == 2) { - memcpy(to, from, sizeof(struct hashlimit_cfg2)); + struct hashlimit_cfg2 *cfg = (struct hashlimit_cfg2 *)from; + + to->mode = cfg->mode; + to->avg = cfg->avg; + to->burst = cfg->burst; + to->size = cfg->size; + to->max = cfg->max; + to->gc_interval = cfg->gc_interval; + to->expire = cfg->expire; + to->srcmask = cfg->srcmask; + to->dstmask = cfg->dstmask; + } else if (revision == 3) { + memcpy(to, from, sizeof(struct hashlimit_cfg3)); } else { return -EINVAL; } @@ -240,13 +264,14 @@ dsthash_free(struct xt_hashlimit_htable *ht, struct dsthash_ent *ent) } static void htable_gc(struct work_struct *work); -static int htable_create(struct net *net, struct hashlimit_cfg2 *cfg, +static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg, const char *name, u_int8_t family, struct xt_hashlimit_htable **out_hinfo, int revision) { struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); struct xt_hashlimit_htable *hinfo; + const struct file_operations *fops; unsigned int size, i; int ret; @@ -268,7 +293,7 @@ static int htable_create(struct net *net, struct hashlimit_cfg2 *cfg, *out_hinfo = hinfo; /* copy match config into hashtable config */ - ret = cfg_copy(&hinfo->cfg, (void *)cfg, 2); + ret = cfg_copy(&hinfo->cfg, (void *)cfg, 3); if (ret) return ret; @@ -293,11 +318,21 @@ static int htable_create(struct net *net, struct hashlimit_cfg2 *cfg, } spin_lock_init(&hinfo->lock); + switch (revision) { + case 1: + fops = &dl_file_ops_v1; + break; + case 2: + fops = &dl_file_ops_v2; + break; + default: + fops = &dl_file_ops; + } + hinfo->pde = proc_create_data(name, 0, (family == NFPROTO_IPV4) ? hashlimit_net->ipt_hashlimit : hashlimit_net->ip6t_hashlimit, - (revision == 1) ? &dl_file_ops_v1 : &dl_file_ops, - hinfo); + fops, hinfo); if (hinfo->pde == NULL) { kfree(hinfo->name); vfree(hinfo); @@ -482,6 +517,25 @@ static u32 user2credits_byte(u32 user) return (u32) (us >> 32); } +static u64 user2rate(u64 user) +{ + if (user != 0) { + return div64_u64(XT_HASHLIMIT_SCALE_v2, user); + } else { + pr_warn("invalid rate from userspace: %llu\n", user); + return 0; + } +} + +static u64 user2rate_bytes(u64 user) +{ + u64 r; + + r = user ? 0xFFFFFFFFULL / user : 0xFFFFFFFFULL; + r = (r - 1) << 4; + return r; +} + static void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now, u32 mode, int revision) { @@ -491,6 +545,21 @@ static void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now, if (delta == 0) return; + if (revision >= 3 && mode & XT_HASHLIMIT_RATE_MATCH) { + u64 interval = dh->rateinfo.interval * HZ; + + if (delta < interval) + return; + + dh->rateinfo.prev = now; + dh->rateinfo.prev_window = + ((dh->rateinfo.current_rate * interval) > + (delta * dh->rateinfo.rate)); + dh->rateinfo.current_rate = 0; + + return; + } + dh->rateinfo.prev = now; if (mode & XT_HASHLIMIT_BYTES) { @@ -515,7 +584,23 @@ static void rateinfo_init(struct dsthash_ent *dh, struct xt_hashlimit_htable *hinfo, int revision) { dh->rateinfo.prev = jiffies; - if (hinfo->cfg.mode & XT_HASHLIMIT_BYTES) { + if (revision >= 3 && hinfo->cfg.mode & XT_HASHLIMIT_RATE_MATCH) { + dh->rateinfo.prev_window = 0; + dh->rateinfo.current_rate = 0; + if (hinfo->cfg.mode & XT_HASHLIMIT_BYTES) { + dh->rateinfo.rate = user2rate_bytes(hinfo->cfg.avg); + if (hinfo->cfg.burst) + dh->rateinfo.burst = + hinfo->cfg.burst * dh->rateinfo.rate; + else + dh->rateinfo.burst = dh->rateinfo.rate; + } else { + dh->rateinfo.rate = user2rate(hinfo->cfg.avg); + dh->rateinfo.burst = + hinfo->cfg.burst + dh->rateinfo.rate; + } + dh->rateinfo.interval = hinfo->cfg.interval; + } else if (hinfo->cfg.mode & XT_HASHLIMIT_BYTES) { dh->rateinfo.credit = CREDITS_PER_JIFFY_BYTES * HZ; dh->rateinfo.cost = user2credits_byte(hinfo->cfg.avg); dh->rateinfo.credit_cap = hinfo->cfg.burst; @@ -648,7 +733,7 @@ static u32 hashlimit_byte_cost(unsigned int len, struct dsthash_ent *dh) static bool hashlimit_mt_common(const struct sk_buff *skb, struct xt_action_param *par, struct xt_hashlimit_htable *hinfo, - const struct hashlimit_cfg2 *cfg, int revision) + const struct hashlimit_cfg3 *cfg, int revision) { unsigned long now = jiffies; struct dsthash_ent *dh; @@ -680,6 +765,20 @@ hashlimit_mt_common(const struct sk_buff *skb, struct xt_action_param *par, rateinfo_recalc(dh, now, hinfo->cfg.mode, revision); } + if (cfg->mode & XT_HASHLIMIT_RATE_MATCH) { + cost = (cfg->mode & XT_HASHLIMIT_BYTES) ? skb->len : 1; + dh->rateinfo.current_rate += cost; + + if (!dh->rateinfo.prev_window && + (dh->rateinfo.current_rate <= dh->rateinfo.burst)) { + spin_unlock(&dh->lock); + rcu_read_unlock_bh(); + return !(cfg->mode & XT_HASHLIMIT_INVERT); + } else { + goto overlimit; + } + } + if (cfg->mode & XT_HASHLIMIT_BYTES) cost = hashlimit_byte_cost(skb->len, dh); else @@ -693,6 +792,7 @@ hashlimit_mt_common(const struct sk_buff *skb, struct xt_action_param *par, return !(cfg->mode & XT_HASHLIMIT_INVERT); } +overlimit: spin_unlock(&dh->lock); local_bh_enable(); /* default match is underlimit - so over the limit, we need to invert */ @@ -708,7 +808,7 @@ hashlimit_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_hashlimit_mtinfo1 *info = par->matchinfo; struct xt_hashlimit_htable *hinfo = info->hinfo; - struct hashlimit_cfg2 cfg = {}; + struct hashlimit_cfg3 cfg = {}; int ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 1); @@ -720,17 +820,33 @@ hashlimit_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) } static bool -hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) +hashlimit_mt_v2(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_hashlimit_mtinfo2 *info = par->matchinfo; struct xt_hashlimit_htable *hinfo = info->hinfo; + struct hashlimit_cfg3 cfg = {}; + int ret; + + ret = cfg_copy(&cfg, (void *)&info->cfg, 2); + + if (ret) + return ret; + + return hashlimit_mt_common(skb, par, hinfo, &cfg, 2); +} + +static bool +hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_hashlimit_mtinfo3 *info = par->matchinfo; + struct xt_hashlimit_htable *hinfo = info->hinfo; - return hashlimit_mt_common(skb, par, hinfo, &info->cfg, 2); + return hashlimit_mt_common(skb, par, hinfo, &info->cfg, 3); } static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, struct xt_hashlimit_htable **hinfo, - struct hashlimit_cfg2 *cfg, + struct hashlimit_cfg3 *cfg, const char *name, int revision) { struct net *net = par->net; @@ -753,7 +869,17 @@ static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, } /* Check for overflow. */ - if (cfg->mode & XT_HASHLIMIT_BYTES) { + if (revision >= 3 && cfg->mode & XT_HASHLIMIT_RATE_MATCH) { + if (cfg->avg == 0) { + pr_info("hashlimit invalid rate\n"); + return -ERANGE; + } + + if (cfg->interval == 0) { + pr_info("hashlimit invalid interval\n"); + return -EINVAL; + } + } else if (cfg->mode & XT_HASHLIMIT_BYTES) { if (user2credits_byte(cfg->avg) == 0) { pr_info("overflow, rate too high: %llu\n", cfg->avg); return -EINVAL; @@ -784,7 +910,7 @@ static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, static int hashlimit_mt_check_v1(const struct xt_mtchk_param *par) { struct xt_hashlimit_mtinfo1 *info = par->matchinfo; - struct hashlimit_cfg2 cfg = {}; + struct hashlimit_cfg3 cfg = {}; int ret; if (info->name[sizeof(info->name) - 1] != '\0') @@ -799,15 +925,40 @@ static int hashlimit_mt_check_v1(const struct xt_mtchk_param *par) &cfg, info->name, 1); } -static int hashlimit_mt_check(const struct xt_mtchk_param *par) +static int hashlimit_mt_check_v2(const struct xt_mtchk_param *par) { struct xt_hashlimit_mtinfo2 *info = par->matchinfo; + struct hashlimit_cfg3 cfg = {}; + int ret; + + if (info->name[sizeof(info->name) - 1] != '\0') + return -EINVAL; + + ret = cfg_copy(&cfg, (void *)&info->cfg, 2); + + if (ret) + return ret; + + return hashlimit_mt_check_common(par, &info->hinfo, + &cfg, info->name, 2); +} + +static int hashlimit_mt_check(const struct xt_mtchk_param *par) +{ + struct xt_hashlimit_mtinfo3 *info = par->matchinfo; if (info->name[sizeof(info->name) - 1] != '\0') return -EINVAL; return hashlimit_mt_check_common(par, &info->hinfo, &info->cfg, - info->name, 2); + info->name, 3); +} + +static void hashlimit_mt_destroy_v2(const struct xt_mtdtor_param *par) +{ + const struct xt_hashlimit_mtinfo2 *info = par->matchinfo; + + htable_put(info->hinfo); } static void hashlimit_mt_destroy_v1(const struct xt_mtdtor_param *par) @@ -819,7 +970,7 @@ static void hashlimit_mt_destroy_v1(const struct xt_mtdtor_param *par) static void hashlimit_mt_destroy(const struct xt_mtdtor_param *par) { - const struct xt_hashlimit_mtinfo2 *info = par->matchinfo; + const struct xt_hashlimit_mtinfo3 *info = par->matchinfo; htable_put(info->hinfo); } @@ -840,9 +991,20 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = { .name = "hashlimit", .revision = 2, .family = NFPROTO_IPV4, - .match = hashlimit_mt, + .match = hashlimit_mt_v2, .matchsize = sizeof(struct xt_hashlimit_mtinfo2), .usersize = offsetof(struct xt_hashlimit_mtinfo2, hinfo), + .checkentry = hashlimit_mt_check_v2, + .destroy = hashlimit_mt_destroy_v2, + .me = THIS_MODULE, + }, + { + .name = "hashlimit", + .revision = 3, + .family = NFPROTO_IPV4, + .match = hashlimit_mt, + .matchsize = sizeof(struct xt_hashlimit_mtinfo3), + .usersize = offsetof(struct xt_hashlimit_mtinfo3, hinfo), .checkentry = hashlimit_mt_check, .destroy = hashlimit_mt_destroy, .me = THIS_MODULE, @@ -863,9 +1025,20 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = { .name = "hashlimit", .revision = 2, .family = NFPROTO_IPV6, - .match = hashlimit_mt, + .match = hashlimit_mt_v2, .matchsize = sizeof(struct xt_hashlimit_mtinfo2), .usersize = offsetof(struct xt_hashlimit_mtinfo2, hinfo), + .checkentry = hashlimit_mt_check_v2, + .destroy = hashlimit_mt_destroy_v2, + .me = THIS_MODULE, + }, + { + .name = "hashlimit", + .revision = 3, + .family = NFPROTO_IPV6, + .match = hashlimit_mt, + .matchsize = sizeof(struct xt_hashlimit_mtinfo3), + .usersize = offsetof(struct xt_hashlimit_mtinfo3, hinfo), .checkentry = hashlimit_mt_check, .destroy = hashlimit_mt_destroy, .me = THIS_MODULE, @@ -947,6 +1120,21 @@ static void dl_seq_print(struct dsthash_ent *ent, u_int8_t family, } } +static int dl_seq_real_show_v2(struct dsthash_ent *ent, u_int8_t family, + struct seq_file *s) +{ + const struct xt_hashlimit_htable *ht = s->private; + + spin_lock(&ent->lock); + /* recalculate to show accurate numbers */ + rateinfo_recalc(ent, jiffies, ht->cfg.mode, 2); + + dl_seq_print(ent, family, s); + + spin_unlock(&ent->lock); + return seq_has_overflowed(s); +} + static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { @@ -969,7 +1157,7 @@ static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, spin_lock(&ent->lock); /* recalculate to show accurate numbers */ - rateinfo_recalc(ent, jiffies, ht->cfg.mode, 2); + rateinfo_recalc(ent, jiffies, ht->cfg.mode, 3); dl_seq_print(ent, family, s); @@ -977,6 +1165,20 @@ static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, return seq_has_overflowed(s); } +static int dl_seq_show_v2(struct seq_file *s, void *v) +{ + struct xt_hashlimit_htable *htable = s->private; + unsigned int *bucket = (unsigned int *)v; + struct dsthash_ent *ent; + + if (!hlist_empty(&htable->hash[*bucket])) { + hlist_for_each_entry(ent, &htable->hash[*bucket], node) + if (dl_seq_real_show_v2(ent, htable->family, s)) + return -1; + } + return 0; +} + static int dl_seq_show_v1(struct seq_file *s, void *v) { struct xt_hashlimit_htable *htable = s->private; @@ -1012,6 +1214,13 @@ static const struct seq_operations dl_seq_ops_v1 = { .show = dl_seq_show_v1 }; +static const struct seq_operations dl_seq_ops_v2 = { + .start = dl_seq_start, + .next = dl_seq_next, + .stop = dl_seq_stop, + .show = dl_seq_show_v2 +}; + static const struct seq_operations dl_seq_ops = { .start = dl_seq_start, .next = dl_seq_next, @@ -1019,6 +1228,18 @@ static const struct seq_operations dl_seq_ops = { .show = dl_seq_show }; +static int dl_proc_open_v2(struct inode *inode, struct file *file) +{ + int ret = seq_open(file, &dl_seq_ops_v2); + + if (!ret) { + struct seq_file *sf = file->private_data; + + sf->private = PDE_DATA(inode); + } + return ret; +} + static int dl_proc_open_v1(struct inode *inode, struct file *file) { int ret = seq_open(file, &dl_seq_ops_v1); @@ -1042,6 +1263,14 @@ static int dl_proc_open(struct inode *inode, struct file *file) return ret; } +static const struct file_operations dl_file_ops_v2 = { + .owner = THIS_MODULE, + .open = dl_proc_open_v2, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release +}; + static const struct file_operations dl_file_ops_v1 = { .owner = THIS_MODULE, .open = dl_proc_open_v1, -- cgit v1.2.3-71-gd317 From a691205571723cb0544110ca91653ac4b0eb5b17 Mon Sep 17 00:00:00 2001 From: "Pablo M. Bermudo Garay" Date: Wed, 23 Aug 2017 22:41:25 +0200 Subject: netfilter: nft_limit: add stateful object type Register a new limit stateful object type into the stateful object infrastructure. Signed-off-by: Pablo M. Bermudo Garay Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 3 +- net/netfilter/nft_limit.c | 122 ++++++++++++++++++++++++++++++- 2 files changed, 123 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index b49da72efa68..871afa4871bf 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1282,7 +1282,8 @@ enum nft_ct_helper_attributes { #define NFT_OBJECT_COUNTER 1 #define NFT_OBJECT_QUOTA 2 #define NFT_OBJECT_CT_HELPER 3 -#define __NFT_OBJECT_MAX 4 +#define NFT_OBJECT_LIMIT 4 +#define __NFT_OBJECT_MAX 5 #define NFT_OBJECT_MAX (__NFT_OBJECT_MAX - 1) /** diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index aae2d1ec27f3..a9fc298ef4c3 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -229,14 +229,133 @@ static struct nft_expr_type nft_limit_type __read_mostly = { .owner = THIS_MODULE, }; +static void nft_limit_obj_pkts_eval(struct nft_object *obj, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_limit_pkts *priv = nft_obj_data(obj); + + if (nft_limit_eval(&priv->limit, priv->cost)) + regs->verdict.code = NFT_BREAK; +} + +static int nft_limit_obj_pkts_init(const struct nft_ctx *ctx, + const struct nlattr * const tb[], + struct nft_object *obj) +{ + struct nft_limit_pkts *priv = nft_obj_data(obj); + int err; + + err = nft_limit_init(&priv->limit, tb); + if (err < 0) + return err; + + priv->cost = div64_u64(priv->limit.nsecs, priv->limit.rate); + return 0; +} + +static int nft_limit_obj_pkts_dump(struct sk_buff *skb, + struct nft_object *obj, + bool reset) +{ + const struct nft_limit_pkts *priv = nft_obj_data(obj); + + return nft_limit_dump(skb, &priv->limit, NFT_LIMIT_PKTS); +} + +static struct nft_object_type nft_limit_obj_type; +static const struct nft_object_ops nft_limit_obj_pkts_ops = { + .type = &nft_limit_obj_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_limit_pkts)), + .init = nft_limit_obj_pkts_init, + .eval = nft_limit_obj_pkts_eval, + .dump = nft_limit_obj_pkts_dump, +}; + +static void nft_limit_obj_bytes_eval(struct nft_object *obj, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_limit *priv = nft_obj_data(obj); + u64 cost = div64_u64(priv->nsecs * pkt->skb->len, priv->rate); + + if (nft_limit_eval(priv, cost)) + regs->verdict.code = NFT_BREAK; +} + +static int nft_limit_obj_bytes_init(const struct nft_ctx *ctx, + const struct nlattr * const tb[], + struct nft_object *obj) +{ + struct nft_limit *priv = nft_obj_data(obj); + + return nft_limit_init(priv, tb); +} + +static int nft_limit_obj_bytes_dump(struct sk_buff *skb, + struct nft_object *obj, + bool reset) +{ + const struct nft_limit *priv = nft_obj_data(obj); + + return nft_limit_dump(skb, priv, NFT_LIMIT_PKT_BYTES); +} + +static struct nft_object_type nft_limit_obj_type; +static const struct nft_object_ops nft_limit_obj_bytes_ops = { + .type = &nft_limit_obj_type, + .size = sizeof(struct nft_limit), + .init = nft_limit_obj_bytes_init, + .eval = nft_limit_obj_bytes_eval, + .dump = nft_limit_obj_bytes_dump, +}; + +static const struct nft_object_ops * +nft_limit_obj_select_ops(const struct nft_ctx *ctx, + const struct nlattr * const tb[]) +{ + if (!tb[NFTA_LIMIT_TYPE]) + return &nft_limit_obj_pkts_ops; + + switch (ntohl(nla_get_be32(tb[NFTA_LIMIT_TYPE]))) { + case NFT_LIMIT_PKTS: + return &nft_limit_obj_pkts_ops; + case NFT_LIMIT_PKT_BYTES: + return &nft_limit_obj_bytes_ops; + } + return ERR_PTR(-EOPNOTSUPP); +} + +static struct nft_object_type nft_limit_obj_type __read_mostly = { + .select_ops = nft_limit_obj_select_ops, + .type = NFT_OBJECT_LIMIT, + .maxattr = NFTA_LIMIT_MAX, + .policy = nft_limit_policy, + .owner = THIS_MODULE, +}; + static int __init nft_limit_module_init(void) { - return nft_register_expr(&nft_limit_type); + int err; + + err = nft_register_obj(&nft_limit_obj_type); + if (err < 0) + return err; + + err = nft_register_expr(&nft_limit_type); + if (err < 0) + goto err1; + + return 0; +err1: + nft_unregister_obj(&nft_limit_obj_type); + return err; } static void __exit nft_limit_module_exit(void) { nft_unregister_expr(&nft_limit_type); + nft_unregister_obj(&nft_limit_obj_type); } module_init(nft_limit_module_init); @@ -245,3 +364,4 @@ module_exit(nft_limit_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy "); MODULE_ALIAS_NFT_EXPR("limit"); +MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_LIMIT); -- cgit v1.2.3-71-gd317 From 2335ba704f32b855651d0cd15dd9b271ec565fb6 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sun, 3 Sep 2017 23:55:59 +0200 Subject: netlink: add NLM_F_NONREC flag for deletion requests In the last NFWS in Faro, Portugal, we discussed that netlink is lacking the semantics to request non recursive deletions, ie. do not delete an object iff it has child objects that hang from this parent object that the user requests to be deleted. We need this new flag to solve a problem for the iptables-compat backward compatibility utility, that runs iptables commands using the existing nf_tables netlink interface. Specifically, custom chains in iptables cannot be deleted if there are rules in it, however, nf_tables allows to remove any chain that is populated with content. To sort out this asymmetry, iptables-compat userspace sets this new NLM_F_NONREC flag to obtain the same semantics that iptables provides. This new flag should only be used for deletion requests. Note this new flag value overlaps with the existing: * NLM_F_ROOT for get requests. * NLM_F_REPLACE for new requests. However, those flags should not ever be used in deletion requests. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netlink.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index f4fc9c9e123d..e8af60a7c56d 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -69,6 +69,9 @@ struct nlmsghdr { #define NLM_F_CREATE 0x400 /* Create, if it does not exist */ #define NLM_F_APPEND 0x800 /* Add to end of list */ +/* Modifiers to DELETE request */ +#define NLM_F_NONREC 0x100 /* Do not delete recursively */ + /* Flags for ACK message */ #define NLM_F_CAPPED 0x100 /* request was capped */ #define NLM_F_ACK_TLVS 0x200 /* extended ACK TVLs were included */ -- cgit v1.2.3-71-gd317 From c93022a72f01f8e53d6e1bc2a8d2c2824c2f36bc Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 1 Sep 2017 05:43:39 -0400 Subject: media: ca.h: split typedefs from structs Using typedefs inside the Kernel is against CodingStyle, and there's no good usage here. Just like we did at frontend.h, at commit 0df289a209e0 ("[media] dvb: Get rid of typedev usage for enums"), let's keep those typedefs only to provide userspace backward compatibility. No functional changes. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/pci/ttpci/av7110.h | 2 +- drivers/media/pci/ttpci/av7110_ca.c | 12 ++++----- include/uapi/linux/dvb/ca.h | 51 +++++++++++++++++++++++-------------- 3 files changed, 39 insertions(+), 26 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/media/pci/ttpci/av7110.h b/drivers/media/pci/ttpci/av7110.h index 824c1e262fbb..347827925c14 100644 --- a/drivers/media/pci/ttpci/av7110.h +++ b/drivers/media/pci/ttpci/av7110.h @@ -177,7 +177,7 @@ struct av7110 { /* CA */ - ca_slot_info_t ci_slot[2]; + struct ca_slot_info ci_slot[2]; enum av7110_video_mode vidmode; struct dmxdev dmxdev; diff --git a/drivers/media/pci/ttpci/av7110_ca.c b/drivers/media/pci/ttpci/av7110_ca.c index f64723aea56b..1fe49171d823 100644 --- a/drivers/media/pci/ttpci/av7110_ca.c +++ b/drivers/media/pci/ttpci/av7110_ca.c @@ -119,7 +119,7 @@ static void ci_ll_release(struct dvb_ringbuffer *cirbuf, struct dvb_ringbuffer * } static int ci_ll_reset(struct dvb_ringbuffer *cibuf, struct file *file, - int slots, ca_slot_info_t *slot) + int slots, struct ca_slot_info *slot) { int i; int len = 0; @@ -264,7 +264,7 @@ static int dvb_ca_ioctl(struct file *file, unsigned int cmd, void *parg) break; case CA_GET_CAP: { - ca_caps_t cap; + struct ca_caps cap; cap.slot_num = 2; cap.slot_type = (FW_CI_LL_SUPPORT(av7110->arm_app) ? @@ -277,7 +277,7 @@ static int dvb_ca_ioctl(struct file *file, unsigned int cmd, void *parg) case CA_GET_SLOT_INFO: { - ca_slot_info_t *info=(ca_slot_info_t *)parg; + struct ca_slot_info *info=(struct ca_slot_info *)parg; if (info->num < 0 || info->num > 1) { mutex_unlock(&av7110->ioctl_mutex); @@ -286,7 +286,7 @@ static int dvb_ca_ioctl(struct file *file, unsigned int cmd, void *parg) av7110->ci_slot[info->num].num = info->num; av7110->ci_slot[info->num].type = FW_CI_LL_SUPPORT(av7110->arm_app) ? CA_CI_LINK : CA_CI; - memcpy(info, &av7110->ci_slot[info->num], sizeof(ca_slot_info_t)); + memcpy(info, &av7110->ci_slot[info->num], sizeof(struct ca_slot_info)); break; } @@ -298,7 +298,7 @@ static int dvb_ca_ioctl(struct file *file, unsigned int cmd, void *parg) case CA_GET_DESCR_INFO: { - ca_descr_info_t info; + struct ca_descr_info info; info.num = 16; info.type = CA_ECD; @@ -308,7 +308,7 @@ static int dvb_ca_ioctl(struct file *file, unsigned int cmd, void *parg) case CA_SET_DESCR: { - ca_descr_t *descr = (ca_descr_t*) parg; + struct ca_descr *descr = (struct ca_descr*) parg; if (descr->index >= 16 || descr->parity > 1) { mutex_unlock(&av7110->ioctl_mutex); diff --git a/include/uapi/linux/dvb/ca.h b/include/uapi/linux/dvb/ca.h index c18537f3e449..00cf24587bea 100644 --- a/include/uapi/linux/dvb/ca.h +++ b/include/uapi/linux/dvb/ca.h @@ -26,7 +26,7 @@ /* slot interface types and info */ -typedef struct ca_slot_info { +struct ca_slot_info { int num; /* slot number */ int type; /* CA interface this slot supports */ @@ -39,52 +39,65 @@ typedef struct ca_slot_info { unsigned int flags; #define CA_CI_MODULE_PRESENT 1 /* module (or card) inserted */ #define CA_CI_MODULE_READY 2 -} ca_slot_info_t; +}; /* descrambler types and info */ -typedef struct ca_descr_info { +struct ca_descr_info { unsigned int num; /* number of available descramblers (keys) */ unsigned int type; /* type of supported scrambling system */ #define CA_ECD 1 #define CA_NDS 2 #define CA_DSS 4 -} ca_descr_info_t; +}; -typedef struct ca_caps { +struct ca_caps { unsigned int slot_num; /* total number of CA card and module slots */ unsigned int slot_type; /* OR of all supported types */ unsigned int descr_num; /* total number of descrambler slots (keys) */ unsigned int descr_type; /* OR of all supported types */ -} ca_caps_t; +}; /* a message to/from a CI-CAM */ -typedef struct ca_msg { +struct ca_msg { unsigned int index; unsigned int type; unsigned int length; unsigned char msg[256]; -} ca_msg_t; +}; -typedef struct ca_descr { +struct ca_descr { unsigned int index; unsigned int parity; /* 0 == even, 1 == odd */ unsigned char cw[8]; -} ca_descr_t; +}; -typedef struct ca_pid { +struct ca_pid { unsigned int pid; int index; /* -1 == disable*/ -} ca_pid_t; +}; #define CA_RESET _IO('o', 128) -#define CA_GET_CAP _IOR('o', 129, ca_caps_t) -#define CA_GET_SLOT_INFO _IOR('o', 130, ca_slot_info_t) -#define CA_GET_DESCR_INFO _IOR('o', 131, ca_descr_info_t) -#define CA_GET_MSG _IOR('o', 132, ca_msg_t) -#define CA_SEND_MSG _IOW('o', 133, ca_msg_t) -#define CA_SET_DESCR _IOW('o', 134, ca_descr_t) -#define CA_SET_PID _IOW('o', 135, ca_pid_t) +#define CA_GET_CAP _IOR('o', 129, struct ca_caps) +#define CA_GET_SLOT_INFO _IOR('o', 130, struct ca_slot_info) +#define CA_GET_DESCR_INFO _IOR('o', 131, struct ca_descr_info) +#define CA_GET_MSG _IOR('o', 132, struct ca_msg) +#define CA_SEND_MSG _IOW('o', 133, struct ca_msg) +#define CA_SET_DESCR _IOW('o', 134, struct ca_descr) +#define CA_SET_PID _IOW('o', 135, struct ca_pid) + +#if !defined (__KERNEL__) + +/* This is needed for legacy userspace support */ +typedef struct ca_slot_info ca_slot_info_t; +typedef struct ca_descr_info ca_descr_info_t; +typedef struct ca_caps ca_caps_t; +typedef struct ca_msg ca_msg_t; +typedef struct ca_descr ca_descr_t; +typedef struct ca_pid ca_pid_t; + +#endif + #endif -- cgit v1.2.3-71-gd317 From 3256b36ea36525945d8575c0100752819a309aaa Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 1 Sep 2017 06:09:14 -0400 Subject: media: dmx.h: split typedefs from structs Using typedefs inside the Kernel is against CodingStyle, and there's no good usage here. Just like we did at frontend.h, at commit 0df289a209e0 ("[media] dvb: Get rid of typedev usage for enums"), let's keep those typedefs only to provide userspace backward compatibility. No functional changes. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/dvb-core/dmxdev.c | 4 +-- include/uapi/linux/dvb/dmx.h | 56 ++++++++++++++++++++++++----------------- 2 files changed, 35 insertions(+), 25 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/media/dvb-core/dmxdev.c b/drivers/media/dvb-core/dmxdev.c index 45e91add73ba..16b0b74c3114 100644 --- a/drivers/media/dvb-core/dmxdev.c +++ b/drivers/media/dvb-core/dmxdev.c @@ -562,7 +562,7 @@ static int dvb_dmxdev_start_feed(struct dmxdev *dmxdev, { ktime_t timeout = 0; struct dmx_pes_filter_params *para = &filter->params.pes; - dmx_output_t otype; + enum dmx_output otype; int ret; int ts_type; enum dmx_ts_pes ts_pes; @@ -787,7 +787,7 @@ static int dvb_dmxdev_filter_free(struct dmxdev *dmxdev, return 0; } -static inline void invert_mode(dmx_filter_t *filter) +static inline void invert_mode(struct dmx_filter *filter) { int i; diff --git a/include/uapi/linux/dvb/dmx.h b/include/uapi/linux/dvb/dmx.h index 427e4899ed69..1bc4d6fb0f01 100644 --- a/include/uapi/linux/dvb/dmx.h +++ b/include/uapi/linux/dvb/dmx.h @@ -43,16 +43,14 @@ enum dmx_output DMX_OUT_TSDEMUX_TAP /* Like TS_TAP but retrieved from the DMX device */ }; -typedef enum dmx_output dmx_output_t; - -typedef enum dmx_input +enum dmx_input { DMX_IN_FRONTEND, /* Input from a front-end device. */ DMX_IN_DVR /* Input from the logical DVR device. */ -} dmx_input_t; +}; -typedef enum dmx_ts_pes +enum dmx_ts_pes { DMX_PES_AUDIO0, DMX_PES_VIDEO0, @@ -79,7 +77,7 @@ typedef enum dmx_ts_pes DMX_PES_PCR3, DMX_PES_OTHER -} dmx_pes_type_t; +}; #define DMX_PES_AUDIO DMX_PES_AUDIO0 #define DMX_PES_VIDEO DMX_PES_VIDEO0 @@ -88,20 +86,20 @@ typedef enum dmx_ts_pes #define DMX_PES_PCR DMX_PES_PCR0 -typedef struct dmx_filter +struct dmx_filter { __u8 filter[DMX_FILTER_SIZE]; __u8 mask[DMX_FILTER_SIZE]; __u8 mode[DMX_FILTER_SIZE]; -} dmx_filter_t; +}; struct dmx_sct_filter_params { - __u16 pid; - dmx_filter_t filter; - __u32 timeout; - __u32 flags; + __u16 pid; + struct dmx_filter filter; + __u32 timeout; + __u32 flags; #define DMX_CHECK_CRC 1 #define DMX_ONESHOT 2 #define DMX_IMMEDIATE_START 4 @@ -111,19 +109,19 @@ struct dmx_sct_filter_params struct dmx_pes_filter_params { - __u16 pid; - dmx_input_t input; - dmx_output_t output; - dmx_pes_type_t pes_type; - __u32 flags; + __u16 pid; + enum dmx_input input; + enum dmx_output output; + enum dmx_ts_pes pes_type; + __u32 flags; }; -typedef struct dmx_caps { +struct dmx_caps { __u32 caps; int num_decoders; -} dmx_caps_t; +}; -typedef enum dmx_source { +enum dmx_source { DMX_SOURCE_FRONT0 = 0, DMX_SOURCE_FRONT1, DMX_SOURCE_FRONT2, @@ -132,7 +130,7 @@ typedef enum dmx_source { DMX_SOURCE_DVR1, DMX_SOURCE_DVR2, DMX_SOURCE_DVR3 -} dmx_source_t; +}; struct dmx_stc { unsigned int num; /* input : which STC? 0..N */ @@ -146,10 +144,22 @@ struct dmx_stc { #define DMX_SET_PES_FILTER _IOW('o', 44, struct dmx_pes_filter_params) #define DMX_SET_BUFFER_SIZE _IO('o', 45) #define DMX_GET_PES_PIDS _IOR('o', 47, __u16[5]) -#define DMX_GET_CAPS _IOR('o', 48, dmx_caps_t) -#define DMX_SET_SOURCE _IOW('o', 49, dmx_source_t) +#define DMX_GET_CAPS _IOR('o', 48, struct dmx_caps) +#define DMX_SET_SOURCE _IOW('o', 49, enum dmx_source) #define DMX_GET_STC _IOWR('o', 50, struct dmx_stc) #define DMX_ADD_PID _IOW('o', 51, __u16) #define DMX_REMOVE_PID _IOW('o', 52, __u16) +#if !defined (__KERNEL__) + +/* This is needed for legacy userspace support */ +typedef enum dmx_output dmx_output_t; +typedef enum dmx_input dmx_input_t; +typedef enum dmx_ts_pes dmx_pes_type_t; +typedef struct dmx_filter dmx_filter_t; +typedef struct dmx_caps dmx_caps_t; +typedef enum dmx_source dmx_source_t; + +#endif + #endif /* _UAPI_DVBDMX_H_ */ -- cgit v1.2.3-71-gd317 From f35afa4f60c868d7c7811ba747133acbf39410ac Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 30 Aug 2017 07:55:47 -0400 Subject: media: dvb/frontend.h: move out a private internal structure struct dtv_cmds_h is just an ancillary struct used by the dvb_frontend.c to internally store frontend commands. It doesn't belong to the userspace header, nor it is used anywhere, except inside the DVB core. So, remove it from the header. Signed-off-by: Mauro Carvalho Chehab --- drivers/media/dvb-core/dvb_frontend.c | 11 +++++++++++ include/uapi/linux/dvb/frontend.h | 11 ----------- 2 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c index 114994ca0929..2fcba1616168 100644 --- a/drivers/media/dvb-core/dvb_frontend.c +++ b/drivers/media/dvb-core/dvb_frontend.c @@ -1000,6 +1000,17 @@ static int dvb_frontend_clear_cache(struct dvb_frontend *fe) .buffer = b \ } +struct dtv_cmds_h { + char *name; /* A display name for debugging purposes */ + + __u32 cmd; /* A unique ID */ + + /* Flags */ + __u32 set:1; /* Either a set or get property */ + __u32 buffer:1; /* Does this property use the buffer? */ + __u32 reserved:30; /* Align */ +}; + static struct dtv_cmds_h dtv_cmds[DTV_MAX_COMMAND + 1] = { _DTV_CMD(DTV_TUNE, 1, 0), _DTV_CMD(DTV_CLEAR, 1, 0), diff --git a/include/uapi/linux/dvb/frontend.h b/include/uapi/linux/dvb/frontend.h index afc3972b0879..3a80f3d1da1c 100644 --- a/include/uapi/linux/dvb/frontend.h +++ b/include/uapi/linux/dvb/frontend.h @@ -384,17 +384,6 @@ enum atscmh_rs_code_mode { #define NO_STREAM_ID_FILTER (~0U) #define LNA_AUTO (~0U) -struct dtv_cmds_h { - char *name; /* A display name for debugging purposes */ - - __u32 cmd; /* A unique ID */ - - /* Flags */ - __u32 set:1; /* Either a set or get property */ - __u32 buffer:1; /* Does this property use the buffer? */ - __u32 reserved:30; /* Align */ -}; - /** * Scale types for the quality parameters. * @FE_SCALE_NOT_AVAILABLE: That QoS measure is not available. That -- cgit v1.2.3-71-gd317 From 8220ead805b6bab4ade2839857a198e9708b07de Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 30 Aug 2017 08:12:38 -0400 Subject: media: dvb/frontend.h: document the uAPI file Most of the stuff at the Digital TV frontend header file are documented only at the Documentation. However, a few kernel-doc markups are there, several of them with parsing issues. Add the missing documentation, copying definitions from the Documentation when it applies, fixing some bugs. Please notice that DVBv3 stuff that were deprecated weren't commented by purpose. Instead, they were clearly tagged as such. This patch prepares to move part of the documentation from Documentation/ to kernel-doc comments. Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/dvb/frontend.h | 580 ++++++++++++++++++++++++++++++++------ 1 file changed, 498 insertions(+), 82 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/dvb/frontend.h b/include/uapi/linux/dvb/frontend.h index 3a80f3d1da1c..16a318fc469a 100644 --- a/include/uapi/linux/dvb/frontend.h +++ b/include/uapi/linux/dvb/frontend.h @@ -28,13 +28,46 @@ #include -enum fe_type { - FE_QPSK, - FE_QAM, - FE_OFDM, - FE_ATSC -}; - +/** + * enum fe_caps - Frontend capabilities + * + * @FE_IS_STUPID: There's something wrong at the + * frontend, and it can't report its + * capabilities. + * @FE_CAN_INVERSION_AUTO: Can auto-detect frequency spectral + * band inversion + * @FE_CAN_FEC_1_2: Supports FEC 1/2 + * @FE_CAN_FEC_2_3: Supports FEC 2/3 + * @FE_CAN_FEC_3_4: Supports FEC 3/4 + * @FE_CAN_FEC_4_5: Supports FEC 4/5 + * @FE_CAN_FEC_5_6: Supports FEC 5/6 + * @FE_CAN_FEC_6_7: Supports FEC 6/7 + * @FE_CAN_FEC_7_8: Supports FEC 7/8 + * @FE_CAN_FEC_8_9: Supports FEC 8/9 + * @FE_CAN_FEC_AUTO: Can auto-detect FEC + * @FE_CAN_QPSK: Supports QPSK modulation + * @FE_CAN_QAM_16: Supports 16-QAM modulation + * @FE_CAN_QAM_32: Supports 32-QAM modulation + * @FE_CAN_QAM_64: Supports 64-QAM modulation + * @FE_CAN_QAM_128: Supports 128-QAM modulation + * @FE_CAN_QAM_256: Supports 256-QAM modulation + * @FE_CAN_QAM_AUTO: Can auto-detect QAM modulation + * @FE_CAN_TRANSMISSION_MODE_AUTO: Can auto-detect transmission mode + * @FE_CAN_BANDWIDTH_AUTO: Can auto-detect bandwidth + * @FE_CAN_GUARD_INTERVAL_AUTO: Can auto-detect guard interval + * @FE_CAN_HIERARCHY_AUTO: Can auto-detect hierarchy + * @FE_CAN_8VSB: Supports 8-VSB modulation + * @FE_CAN_16VSB: Supporta 16-VSB modulation + * @FE_HAS_EXTENDED_CAPS: Unused + * @FE_CAN_MULTISTREAM: Supports multistream filtering + * @FE_CAN_TURBO_FEC: Supports "turbo FEC" modulation + * @FE_CAN_2G_MODULATION: Supports "2nd generation" modulation, + * e. g. DVB-S2, DVB-T2, DVB-C2 + * @FE_NEEDS_BENDING: Unused + * @FE_CAN_RECOVER: Can recover from a cable unplug + * automatically + * @FE_CAN_MUTE_TS: Can stop spurious TS data output + */ enum fe_caps { FE_IS_STUPID = 0, FE_CAN_INVERSION_AUTO = 0x1, @@ -60,15 +93,55 @@ enum fe_caps { FE_CAN_HIERARCHY_AUTO = 0x100000, FE_CAN_8VSB = 0x200000, FE_CAN_16VSB = 0x400000, - FE_HAS_EXTENDED_CAPS = 0x800000, /* We need more bitspace for newer APIs, indicate this. */ - FE_CAN_MULTISTREAM = 0x4000000, /* frontend supports multistream filtering */ - FE_CAN_TURBO_FEC = 0x8000000, /* frontend supports "turbo fec modulation" */ - FE_CAN_2G_MODULATION = 0x10000000, /* frontend supports "2nd generation modulation" (DVB-S2) */ - FE_NEEDS_BENDING = 0x20000000, /* not supported anymore, don't use (frontend requires frequency bending) */ - FE_CAN_RECOVER = 0x40000000, /* frontend can recover from a cable unplug automatically */ - FE_CAN_MUTE_TS = 0x80000000 /* frontend can stop spurious TS data output */ + FE_HAS_EXTENDED_CAPS = 0x800000, + FE_CAN_MULTISTREAM = 0x4000000, + FE_CAN_TURBO_FEC = 0x8000000, + FE_CAN_2G_MODULATION = 0x10000000, + FE_NEEDS_BENDING = 0x20000000, + FE_CAN_RECOVER = 0x40000000, + FE_CAN_MUTE_TS = 0x80000000 +}; + +/* + * DEPRECATED: Should be kept just due to backward compatibility. + */ +enum fe_type { + FE_QPSK, + FE_QAM, + FE_OFDM, + FE_ATSC }; +/** + * struct dvb_frontend_info - Frontend properties and capabilities + * + * @name: Name of the frontend + * @type: **DEPRECATED**. + * Should not be used on modern programs, + * as a frontend may have more than one type. + * In order to get the support types of a given + * frontend, use :c:type:`DTV_ENUM_DELSYS` + * instead. + * @frequency_min: Minimal frequency supported by the frontend. + * @frequency_max: Minimal frequency supported by the frontend. + * @frequency_stepsize: All frequencies are multiple of this value. + * @frequency_tolerance: Frequency tolerance. + * @symbol_rate_min: Minimal symbol rate, in bauds + * (for Cable/Satellite systems). + * @symbol_rate_max: Maximal symbol rate, in bauds + * (for Cable/Satellite systems). + * @symbol_rate_tolerance: Maximal symbol rate tolerance, in ppm + * (for Cable/Satellite systems). + * @notifier_delay: **DEPRECATED**. Not used by any driver. + * @caps: Capabilities supported by the frontend, + * as specified in &enum fe_caps. + * + * .. note: + * + * #. The frequencies are specified in Hz for Terrestrial and Cable + * systems. + * #. The frequencies are specified in kHz for Satellite systems. + */ struct dvb_frontend_info { char name[128]; enum fe_type type; /* DEPRECATED. Use DTV_ENUM_DELSYS instead */ @@ -78,53 +151,102 @@ struct dvb_frontend_info { __u32 frequency_tolerance; __u32 symbol_rate_min; __u32 symbol_rate_max; - __u32 symbol_rate_tolerance; /* ppm */ + __u32 symbol_rate_tolerance; __u32 notifier_delay; /* DEPRECATED */ enum fe_caps caps; }; - /** - * Check out the DiSEqC bus spec available on http://www.eutelsat.org/ for - * the meaning of this struct... + * struct dvb_diseqc_master_cmd - DiSEqC master command + * + * @msg: + * DiSEqC message to be sent. It contains a 3 bytes header with: + * framing + address + command, and an optional argument + * of up to 3 bytes of data. + * @msg_len: + * Length of the DiSEqC message. Valid values are 3 to 6. + * + * Check out the DiSEqC bus spec available on http://www.eutelsat.org/ for + * the possible messages that can be used. */ struct dvb_diseqc_master_cmd { - __u8 msg [6]; /* { framing, address, command, data [3] } */ - __u8 msg_len; /* valid values are 3...6 */ + __u8 msg[6]; + __u8 msg_len; }; +/** + * struct dvb_diseqc_slave_reply - DiSEqC received data + * + * @msg: + * DiSEqC message buffer to store a message received via DiSEqC. + * It contains one byte header with: framing and + * an optional argument of up to 3 bytes of data. + * @msg_len: + * Length of the DiSEqC message. Valid values are 0 to 4, + * where 0 means no message. + * @timeout: + * Return from ioctl after timeout ms with errorcode when + * no message was received. + * + * Check out the DiSEqC bus spec available on http://www.eutelsat.org/ for + * the possible messages that can be used. + */ struct dvb_diseqc_slave_reply { - __u8 msg [4]; /* { framing, data [3] } */ - __u8 msg_len; /* valid values are 0...4, 0 means no msg */ - int timeout; /* return from ioctl after timeout ms with */ -}; /* errorcode when no message was received */ + __u8 msg[4]; + __u8 msg_len; + int timeout; +}; +/** + * enum fe_sec_voltage - DC Voltage used to feed the LNBf + * + * @SEC_VOLTAGE_13: Output 13V to the LNBf + * @SEC_VOLTAGE_18: Output 18V to the LNBf + * @SEC_VOLTAGE_OFF: Don't feed the LNBf with a DC voltage + */ enum fe_sec_voltage { SEC_VOLTAGE_13, SEC_VOLTAGE_18, SEC_VOLTAGE_OFF }; +/** + * enum fe_sec_tone_mode - Type of tone to be send to the LNBf. + * @SEC_TONE_ON: Sends a 22kHz tone burst to the antenna. + * @SEC_TONE_OFF: Don't send a 22kHz tone to the antenna (except + * if the ``FE_DISEQC_*`` ioctls are called). + */ enum fe_sec_tone_mode { SEC_TONE_ON, SEC_TONE_OFF }; +/** + * enum fe_sec_mini_cmd - Type of mini burst to be sent + * + * @SEC_MINI_A: Sends a mini-DiSEqC 22kHz '0' Tone Burst to select + * satellite-A + * @SEC_MINI_B: Sends a mini-DiSEqC 22kHz '1' Data Burst to select + * satellite-B + */ enum fe_sec_mini_cmd { SEC_MINI_A, SEC_MINI_B }; /** - * enum fe_status - enumerates the possible frontend status - * @FE_HAS_SIGNAL: found something above the noise level - * @FE_HAS_CARRIER: found a DVB signal - * @FE_HAS_VITERBI: FEC is stable - * @FE_HAS_SYNC: found sync bytes - * @FE_HAS_LOCK: everything's working - * @FE_TIMEDOUT: no lock within the last ~2 seconds - * @FE_REINIT: frontend was reinitialized, application is recommended - * to reset DiSEqC, tone and parameters + * enum fe_status - Enumerates the possible frontend status. + * @FE_NONE: The frontend doesn't have any kind of lock. + * That's the initial frontend status + * @FE_HAS_SIGNAL: Has found something above the noise level. + * @FE_HAS_CARRIER: Has found a DVB signal. + * @FE_HAS_VITERBI: FEC inner coding (Viterbi, LDPC or other inner code). + * is stable. + * @FE_HAS_SYNC: Synchronization bytes was found. + * @FE_HAS_LOCK: DVB were locked and everything is working. + * @FE_TIMEDOUT: Fo lock within the last about 2 seconds. + * @FE_REINIT: Frontend was reinitialized, application is recommended + * to reset DiSEqC, tone and parameters. */ enum fe_status { FE_NONE = 0x00, @@ -137,12 +259,45 @@ enum fe_status { FE_REINIT = 0x40, }; +/** + * enum fe_spectral_inversion - Type of inversion band + * + * @INVERSION_OFF: Don't do spectral band inversion. + * @INVERSION_ON: Do spectral band inversion. + * @INVERSION_AUTO: Autodetect spectral band inversion. + * + * This parameter indicates if spectral inversion should be presumed or + * not. In the automatic setting (``INVERSION_AUTO``) the hardware will try + * to figure out the correct setting by itself. If the hardware doesn't + * support, the DVB core will try to lock at the carrier first with + * inversion off. If it fails, it will try to enable inversion. + */ enum fe_spectral_inversion { INVERSION_OFF, INVERSION_ON, INVERSION_AUTO }; +/** + * enum fe_code_rate - Type of Forward Error Correction (FEC) + * + * + * @FEC_NONE: No Forward Error Correction Code + * @FEC_1_2: Forward Error Correction Code 1/2 + * @FEC_2_3: Forward Error Correction Code 2/3 + * @FEC_3_4: Forward Error Correction Code 3/4 + * @FEC_4_5: Forward Error Correction Code 4/5 + * @FEC_5_6: Forward Error Correction Code 5/6 + * @FEC_6_7: Forward Error Correction Code 6/7 + * @FEC_7_8: Forward Error Correction Code 7/8 + * @FEC_8_9: Forward Error Correction Code 8/9 + * @FEC_AUTO: Autodetect Error Correction Code + * @FEC_3_5: Forward Error Correction Code 3/5 + * @FEC_9_10: Forward Error Correction Code 9/10 + * @FEC_2_5: Forward Error Correction Code 2/5 + * + * Please note that not all FEC types are supported by a given standard. + */ enum fe_code_rate { FEC_NONE = 0, FEC_1_2, @@ -159,6 +314,26 @@ enum fe_code_rate { FEC_2_5, }; +/** + * enum fe_modulation - Type of modulation/constellation + * @QPSK: QPSK modulation + * @QAM_16: 16-QAM modulation + * @QAM_32: 32-QAM modulation + * @QAM_64: 64-QAM modulation + * @QAM_128: 128-QAM modulation + * @QAM_256: 256-QAM modulation + * @QAM_AUTO: Autodetect QAM modulation + * @VSB_8: 8-VSB modulation + * @VSB_16: 16-VSB modulation + * @PSK_8: 8-PSK modulation + * @APSK_16: 16-APSK modulation + * @APSK_32: 32-APSK modulation + * @DQPSK: DQPSK modulation + * @QAM_4_NR: 4-QAM-NR modulation + * + * Please note that not all modulations are supported by a given standard. + * + */ enum fe_modulation { QPSK, QAM_16, @@ -176,6 +351,32 @@ enum fe_modulation { QAM_4_NR, }; +/** + * enum fe_transmit_mode - Transmission mode + * + * @TRANSMISSION_MODE_AUTO: + * Autodetect transmission mode. The hardware will try to find the + * correct FFT-size (if capable) to fill in the missing parameters. + * @TRANSMISSION_MODE_1K: + * Transmission mode 1K + * @TRANSMISSION_MODE_2K: + * Transmission mode 2K + * @TRANSMISSION_MODE_8K: + * Transmission mode 8K + * @TRANSMISSION_MODE_4K: + * Transmission mode 4K + * @TRANSMISSION_MODE_16K: + * Transmission mode 16K + * @TRANSMISSION_MODE_32K: + * Transmission mode 32K + * @TRANSMISSION_MODE_C1: + * Single Carrier (C=1) transmission mode (DTMB only) + * @TRANSMISSION_MODE_C3780: + * Multi Carrier (C=3780) transmission mode (DTMB only) + * + * Please note that not all transmission modes are supported by a given + * standard. + */ enum fe_transmit_mode { TRANSMISSION_MODE_2K, TRANSMISSION_MODE_8K, @@ -188,6 +389,23 @@ enum fe_transmit_mode { TRANSMISSION_MODE_C3780, }; +/** + * enum fe_guard_interval - Guard interval + * + * @GUARD_INTERVAL_AUTO: Autodetect the guard interval + * @GUARD_INTERVAL_1_128: Guard interval 1/128 + * @GUARD_INTERVAL_1_32: Guard interval 1/32 + * @GUARD_INTERVAL_1_16: Guard interval 1/16 + * @GUARD_INTERVAL_1_8: Guard interval 1/8 + * @GUARD_INTERVAL_1_4: Guard interval 1/4 + * @GUARD_INTERVAL_19_128: Guard interval 19/128 + * @GUARD_INTERVAL_19_256: Guard interval 19/256 + * @GUARD_INTERVAL_PN420: PN length 420 (1/4) + * @GUARD_INTERVAL_PN595: PN length 595 (1/6) + * @GUARD_INTERVAL_PN945: PN length 945 (1/9) + * + * Please note that not all guard intervals are supported by a given standard. + */ enum fe_guard_interval { GUARD_INTERVAL_1_32, GUARD_INTERVAL_1_16, @@ -202,6 +420,16 @@ enum fe_guard_interval { GUARD_INTERVAL_PN945, }; +/** + * enum fe_hierarchy - Hierarchy + * @HIERARCHY_NONE: No hierarchy + * @HIERARCHY_AUTO: Autodetect hierarchy (if supported) + * @HIERARCHY_1: Hierarchy 1 + * @HIERARCHY_2: Hierarchy 2 + * @HIERARCHY_4: Hierarchy 4 + * + * Please note that not all hierarchy types are supported by a given standard. + */ enum fe_hierarchy { HIERARCHY_NONE, HIERARCHY_1, @@ -210,6 +438,15 @@ enum fe_hierarchy { HIERARCHY_AUTO }; +/** + * enum fe_interleaving - Interleaving + * @INTERLEAVING_NONE: No interleaving. + * @INTERLEAVING_AUTO: Auto-detect interleaving. + * @INTERLEAVING_240: Interleaving of 240 symbols. + * @INTERLEAVING_720: Interleaving of 720 symbols. + * + * Please note that, currently, only DTMB uses it. + */ enum fe_interleaving { INTERLEAVING_NONE, INTERLEAVING_AUTO, @@ -217,7 +454,8 @@ enum fe_interleaving { INTERLEAVING_720, }; -/* S2API Commands */ +/* DVBv5 property Commands */ + #define DTV_UNDEFINED 0 #define DTV_TUNE 1 #define DTV_CLEAR 2 @@ -310,19 +548,79 @@ enum fe_interleaving { #define DTV_MAX_COMMAND DTV_STAT_TOTAL_BLOCK_COUNT +/** + * enum fe_pilot - Type of pilot tone + * + * @PILOT_ON: Pilot tones enabled + * @PILOT_OFF: Pilot tones disabled + * @PILOT_AUTO: Autodetect pilot tones + */ enum fe_pilot { PILOT_ON, PILOT_OFF, PILOT_AUTO, }; +/** + * enum fe_rolloff - Rolloff factor (also known as alpha) + * @ROLLOFF_35: Roloff factor: 35% + * @ROLLOFF_20: Roloff factor: 20% + * @ROLLOFF_25: Roloff factor: 25% + * @ROLLOFF_AUTO: Auto-detect the roloff factor. + * + * .. note: + * + * Roloff factor of 35% is implied on DVB-S. On DVB-S2, it is default. + */ enum fe_rolloff { - ROLLOFF_35, /* Implied value in DVB-S, default for DVB-S2 */ + ROLLOFF_35, ROLLOFF_20, ROLLOFF_25, ROLLOFF_AUTO, }; +/** + * enum fe_delivery_system - Type of the delivery system + * + * @SYS_UNDEFINED: + * Undefined standard. Generally, indicates an error + * @SYS_DVBC_ANNEX_A: + * Cable TV: DVB-C following ITU-T J.83 Annex A spec + * @SYS_DVBC_ANNEX_B: + * Cable TV: DVB-C following ITU-T J.83 Annex B spec (ClearQAM) + * @SYS_DVBC_ANNEX_C: + * Cable TV: DVB-C following ITU-T J.83 Annex C spec + * @SYS_ISDBC: + * Cable TV: ISDB-C (no drivers yet) + * @SYS_DVBT: + * Terrestrial TV: DVB-T + * @SYS_DVBT2: + * Terrestrial TV: DVB-T2 + * @SYS_ISDBT: + * Terrestrial TV: ISDB-T + * @SYS_ATSC: + * Terrestrial TV: ATSC + * @SYS_ATSCMH: + * Terrestrial TV (mobile): ATSC-M/H + * @SYS_DTMB: + * Terrestrial TV: DTMB + * @SYS_DVBS: + * Satellite TV: DVB-S + * @SYS_DVBS2: + * Satellite TV: DVB-S2 + * @SYS_TURBO: + * Satellite TV: DVB-S Turbo + * @SYS_ISDBS: + * Satellite TV: ISDB-S + * @SYS_DAB: + * Digital audio: DAB (not fully supported) + * @SYS_DSS: + * Satellite TV: DSS (not fully supported) + * @SYS_CMMB: + * Terrestrial TV (mobile): CMMB (not fully supported) + * @SYS_DVBH: + * Terrestrial TV (mobile): DVB-H (standard deprecated) + */ enum fe_delivery_system { SYS_UNDEFINED, SYS_DVBC_ANNEX_A, @@ -345,35 +643,85 @@ enum fe_delivery_system { SYS_DVBC_ANNEX_C, }; -/* backward compatibility */ +/* backward compatibility definitions for delivery systems */ #define SYS_DVBC_ANNEX_AC SYS_DVBC_ANNEX_A -#define SYS_DMBTH SYS_DTMB /* DMB-TH is legacy name, use DTMB instead */ +#define SYS_DMBTH SYS_DTMB /* DMB-TH is legacy name, use DTMB */ -/* ATSC-MH */ +/* ATSC-MH specific parameters */ +/** + * enum atscmh_sccc_block_mode - Type of Series Concatenated Convolutional + * Code Block Mode. + * + * @ATSCMH_SCCC_BLK_SEP: + * Separate SCCC: the SCCC outer code mode shall be set independently + * for each Group Region (A, B, C, D) + * @ATSCMH_SCCC_BLK_COMB: + * Combined SCCC: all four Regions shall have the same SCCC outer + * code mode. + * @ATSCMH_SCCC_BLK_RES: + * Reserved. Shouldn't be used. + */ enum atscmh_sccc_block_mode { ATSCMH_SCCC_BLK_SEP = 0, ATSCMH_SCCC_BLK_COMB = 1, ATSCMH_SCCC_BLK_RES = 2, }; +/** + * enum atscmh_sccc_code_mode - Type of Series Concatenated Convolutional + * Code Rate. + * + * @ATSCMH_SCCC_CODE_HLF: + * The outer code rate of a SCCC Block is 1/2 rate. + * @ATSCMH_SCCC_CODE_QTR: + * The outer code rate of a SCCC Block is 1/4 rate. + * @ATSCMH_SCCC_CODE_RES: + * Reserved. Should not be used. + */ enum atscmh_sccc_code_mode { ATSCMH_SCCC_CODE_HLF = 0, ATSCMH_SCCC_CODE_QTR = 1, ATSCMH_SCCC_CODE_RES = 2, }; +/** + * enum atscmh_rs_frame_ensemble - Reed Solomon(RS) frame ensemble. + * + * @ATSCMH_RSFRAME_ENS_PRI: Primary Ensemble. + * @ATSCMH_RSFRAME_ENS_SEC: Secondary Ensemble. + */ enum atscmh_rs_frame_ensemble { ATSCMH_RSFRAME_ENS_PRI = 0, ATSCMH_RSFRAME_ENS_SEC = 1, }; +/** + * enum atscmh_rs_frame_mode - Reed Solomon (RS) frame mode. + * + * @ATSCMH_RSFRAME_PRI_ONLY: + * Single Frame: There is only a primary RS Frame for all Group + * Regions. + * @ATSCMH_RSFRAME_PRI_SEC: + * Dual Frame: There are two separate RS Frames: Primary RS Frame for + * Group Region A and B and Secondary RS Frame for Group Region C and + * D. + * @ATSCMH_RSFRAME_RES: + * Reserved. Shouldn't be used. + */ enum atscmh_rs_frame_mode { ATSCMH_RSFRAME_PRI_ONLY = 0, ATSCMH_RSFRAME_PRI_SEC = 1, ATSCMH_RSFRAME_RES = 2, }; +/** + * enum atscmh_rs_code_mode + * @ATSCMH_RSCODE_211_187: Reed Solomon code (211,187). + * @ATSCMH_RSCODE_223_187: Reed Solomon code (223,187). + * @ATSCMH_RSCODE_235_187: Reed Solomon code (235,187). + * @ATSCMH_RSCODE_RES: Reserved. Shouldn't be used. + */ enum atscmh_rs_code_mode { ATSCMH_RSCODE_211_187 = 0, ATSCMH_RSCODE_223_187 = 1, @@ -385,16 +733,17 @@ enum atscmh_rs_code_mode { #define LNA_AUTO (~0U) /** - * Scale types for the quality parameters. + * enum fecap_scale_params - scale types for the quality parameters. + * * @FE_SCALE_NOT_AVAILABLE: That QoS measure is not available. That * could indicate a temporary or a permanent * condition. * @FE_SCALE_DECIBEL: The scale is measured in 0.001 dB steps, typically - * used on signal measures. + * used on signal measures. * @FE_SCALE_RELATIVE: The scale is a relative percentual measure, - * ranging from 0 (0%) to 0xffff (100%). + * ranging from 0 (0%) to 0xffff (100%). * @FE_SCALE_COUNTER: The scale counts the occurrence of an event, like - * bit error, block error, lapsed time. + * bit error, block error, lapsed time. */ enum fecap_scale_params { FE_SCALE_NOT_AVAILABLE = 0, @@ -406,24 +755,38 @@ enum fecap_scale_params { /** * struct dtv_stats - Used for reading a DTV status property * - * @value: value of the measure. Should range from 0 to 0xffff; * @scale: Filled with enum fecap_scale_params - the scale * in usage for that parameter * + * The ``{unnamed_union}`` may have either one of the values below: + * + * %svalue + * integer value of the measure, for %FE_SCALE_DECIBEL, + * used for dB measures. The unit is 0.001 dB. + * + * %uvalue + * unsigned integer value of the measure, used when @scale is + * either %FE_SCALE_RELATIVE or %FE_SCALE_COUNTER. + * * For most delivery systems, this will return a single value for each * parameter. + * * It should be noticed, however, that new OFDM delivery systems like * ISDB can use different modulation types for each group of carriers. * On such standards, up to 8 groups of statistics can be provided, one * for each carrier group (called "layer" on ISDB). + * * In order to be consistent with other delivery systems, the first * value refers to the entire set of carriers ("global"). - * dtv_status:scale should use the value FE_SCALE_NOT_AVAILABLE when + * + * @scale should use the value %FE_SCALE_NOT_AVAILABLE when * the value for the entire group of carriers or from one specific layer * is not provided by the hardware. - * st.len should be filled with the latest filled status + 1. * - * In other words, for ISDB, those values should be filled like: + * @len should be filled with the latest filled status + 1. + * + * In other words, for ISDB, those values should be filled like:: + * * u.st.stat.svalue[0] = global statistics; * u.st.stat.scale[0] = FE_SCALE_DECIBEL; * u.st.stat.value[1] = layer A statistics; @@ -445,11 +808,39 @@ struct dtv_stats { #define MAX_DTV_STATS 4 +/** + * struct dtv_fe_stats - store Digital TV frontend statistics + * + * @len: length of the statistics - if zero, stats is disabled. + * @stat: array with digital TV statistics. + * + * On most standards, @len can either be 0 or 1. However, for ISDB, each + * layer is modulated in separate. So, each layer may have its own set + * of statistics. If so, stat[0] carries on a global value for the property. + * Indexes 1 to 3 means layer A to B. + */ struct dtv_fe_stats { __u8 len; struct dtv_stats stat[MAX_DTV_STATS]; } __attribute__ ((packed)); +/** + * struct dtv_property - store one of frontend command and its value + * + * @cmd: Digital TV command. + * @reserved: Not used. + * @u: Union with the values for the command. + * @result: Result of the command set (currently unused). + * + * The @u union may have either one of the values below: + * + * %data + * an unsigned 32-bits number. + * %st + * a &struct dtv_fe_stats array of statistics. + * %buffer + * a buffer of up to 32 characters (currently unused). + */ struct dtv_property { __u32 cmd; __u32 reserved[3]; @@ -469,17 +860,70 @@ struct dtv_property { /* num of properties cannot exceed DTV_IOCTL_MAX_MSGS per ioctl */ #define DTV_IOCTL_MAX_MSGS 64 +/** + * struct dtv_properties - a set of command/value pairs. + * + * @num: amount of commands stored at the struct. + * @props: a pointer to &struct dtv_property. + */ struct dtv_properties { __u32 num; struct dtv_property *props; }; +/* + * When set, this flag will disable any zigzagging or other "normal" tuning + * behavior. Additionally, there will be no automatic monitoring of the lock + * status, and hence no frontend events will be generated. If a frontend device + * is closed, this flag will be automatically turned off when the device is + * reopened read-write. + */ +#define FE_TUNE_MODE_ONESHOT 0x01 + +/* Digital TV Frontend API calls */ + +#define FE_GET_INFO _IOR('o', 61, struct dvb_frontend_info) + +#define FE_DISEQC_RESET_OVERLOAD _IO('o', 62) +#define FE_DISEQC_SEND_MASTER_CMD _IOW('o', 63, struct dvb_diseqc_master_cmd) +#define FE_DISEQC_RECV_SLAVE_REPLY _IOR('o', 64, struct dvb_diseqc_slave_reply) +#define FE_DISEQC_SEND_BURST _IO('o', 65) /* fe_sec_mini_cmd_t */ + +#define FE_SET_TONE _IO('o', 66) /* fe_sec_tone_mode_t */ +#define FE_SET_VOLTAGE _IO('o', 67) /* fe_sec_voltage_t */ +#define FE_ENABLE_HIGH_LNB_VOLTAGE _IO('o', 68) /* int */ + +#define FE_READ_STATUS _IOR('o', 69, fe_status_t) +#define FE_READ_BER _IOR('o', 70, __u32) +#define FE_READ_SIGNAL_STRENGTH _IOR('o', 71, __u16) +#define FE_READ_SNR _IOR('o', 72, __u16) +#define FE_READ_UNCORRECTED_BLOCKS _IOR('o', 73, __u32) + +#define FE_SET_FRONTEND_TUNE_MODE _IO('o', 81) /* unsigned int */ +#define FE_GET_EVENT _IOR('o', 78, struct dvb_frontend_event) + +#define FE_DISHNETWORK_SEND_LEGACY_CMD _IO('o', 80) /* unsigned int */ + +#define FE_SET_PROPERTY _IOW('o', 82, struct dtv_properties) +#define FE_GET_PROPERTY _IOR('o', 83, struct dtv_properties) + #if defined(__DVB_CORE__) || !defined (__KERNEL__) /* - * DEPRECATED: The DVBv3 ioctls, structs and enums should not be used on - * newer programs, as it doesn't support the second generation of digital - * TV standards, nor supports newer delivery systems. + * DEPRECATED: Everything below is deprecated in favor of DVBv5 API + * + * The DVBv3 only ioctls, structs and enums should not be used on + * newer programs, as it doesn't support the second generation of + * digital TV standards, nor supports newer delivery systems. + * They also don't support modern frontends with usually support multiple + * delivery systems. + * + * Drivers shouldn't use them. + * + * New applications should use DVBv5 delivery system instead + */ + +/* */ enum fe_bandwidth { @@ -492,7 +936,7 @@ enum fe_bandwidth { BANDWIDTH_1_712_MHZ, }; -/* This is needed for legacy userspace support */ +/* This is kept for legacy userspace support */ typedef enum fe_sec_voltage fe_sec_voltage_t; typedef enum fe_caps fe_caps_t; typedef enum fe_type fe_type_t; @@ -510,6 +954,8 @@ typedef enum fe_pilot fe_pilot_t; typedef enum fe_rolloff fe_rolloff_t; typedef enum fe_delivery_system fe_delivery_system_t; +/* DVBv3 structs */ + struct dvb_qpsk_parameters { __u32 symbol_rate; /* symbol rate in Symbols per second */ fe_code_rate_t fec_inner; /* forward error correction (see above) */ @@ -551,42 +997,12 @@ struct dvb_frontend_event { fe_status_t status; struct dvb_frontend_parameters parameters; }; -#endif - -#define FE_SET_PROPERTY _IOW('o', 82, struct dtv_properties) -#define FE_GET_PROPERTY _IOR('o', 83, struct dtv_properties) - -/** - * When set, this flag will disable any zigzagging or other "normal" tuning - * behaviour. Additionally, there will be no automatic monitoring of the lock - * status, and hence no frontend events will be generated. If a frontend device - * is closed, this flag will be automatically turned off when the device is - * reopened read-write. - */ -#define FE_TUNE_MODE_ONESHOT 0x01 -#define FE_GET_INFO _IOR('o', 61, struct dvb_frontend_info) - -#define FE_DISEQC_RESET_OVERLOAD _IO('o', 62) -#define FE_DISEQC_SEND_MASTER_CMD _IOW('o', 63, struct dvb_diseqc_master_cmd) -#define FE_DISEQC_RECV_SLAVE_REPLY _IOR('o', 64, struct dvb_diseqc_slave_reply) -#define FE_DISEQC_SEND_BURST _IO('o', 65) /* fe_sec_mini_cmd_t */ - -#define FE_SET_TONE _IO('o', 66) /* fe_sec_tone_mode_t */ -#define FE_SET_VOLTAGE _IO('o', 67) /* fe_sec_voltage_t */ -#define FE_ENABLE_HIGH_LNB_VOLTAGE _IO('o', 68) /* int */ - -#define FE_READ_STATUS _IOR('o', 69, fe_status_t) -#define FE_READ_BER _IOR('o', 70, __u32) -#define FE_READ_SIGNAL_STRENGTH _IOR('o', 71, __u16) -#define FE_READ_SNR _IOR('o', 72, __u16) -#define FE_READ_UNCORRECTED_BLOCKS _IOR('o', 73, __u32) +/* DVBv3 API calls */ #define FE_SET_FRONTEND _IOW('o', 76, struct dvb_frontend_parameters) #define FE_GET_FRONTEND _IOR('o', 77, struct dvb_frontend_parameters) -#define FE_SET_FRONTEND_TUNE_MODE _IO('o', 81) /* unsigned int */ -#define FE_GET_EVENT _IOR('o', 78, struct dvb_frontend_event) -#define FE_DISHNETWORK_SEND_LEGACY_CMD _IO('o', 80) /* unsigned int */ +#endif #endif /*_DVBFRONTEND_H_*/ -- cgit v1.2.3-71-gd317 From 9d5e27cbc117671959a9f625e51c754f5a0666e3 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 30 Aug 2017 13:45:20 -0400 Subject: media: dvb frontend docs: use kernel-doc documentation Now that frontend.h contains most documentation for the frontend, remove the duplicated information from Documentation/ and use the kernel-doc auto-generated one instead. That should simplify maintainership of DVB frontend uAPI, as most of the documentation will stick with the header file. Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/frontend.h.rst.exceptions | 185 +- Documentation/media/uapi/dvb/dtv-fe-stats.rst | 17 - Documentation/media/uapi/dvb/dtv-properties.rst | 15 - Documentation/media/uapi/dvb/dtv-property.rst | 31 - Documentation/media/uapi/dvb/dtv-stats.rst | 18 - Documentation/media/uapi/dvb/dvbproperty-006.rst | 12 - Documentation/media/uapi/dvb/dvbproperty.rst | 28 +- .../media/uapi/dvb/fe-diseqc-recv-slave-reply.rst | 40 +- .../media/uapi/dvb/fe-diseqc-send-burst.rst | 31 +- .../media/uapi/dvb/fe-diseqc-send-master-cmd.rst | 29 +- Documentation/media/uapi/dvb/fe-get-info.rst | 370 +--- Documentation/media/uapi/dvb/fe-get-property.rst | 2 +- Documentation/media/uapi/dvb/fe-read-status.rst | 83 - Documentation/media/uapi/dvb/fe-set-tone.rst | 30 - .../media/uapi/dvb/fe_property_parameters.rst | 1847 +++++--------------- Documentation/media/uapi/dvb/frontend-header.rst | 4 + include/uapi/linux/dvb/frontend.h | 8 +- 17 files changed, 602 insertions(+), 2148 deletions(-) delete mode 100644 Documentation/media/uapi/dvb/dtv-fe-stats.rst delete mode 100644 Documentation/media/uapi/dvb/dtv-properties.rst delete mode 100644 Documentation/media/uapi/dvb/dtv-property.rst delete mode 100644 Documentation/media/uapi/dvb/dtv-stats.rst delete mode 100644 Documentation/media/uapi/dvb/dvbproperty-006.rst create mode 100644 Documentation/media/uapi/dvb/frontend-header.rst (limited to 'include/uapi/linux') diff --git a/Documentation/media/frontend.h.rst.exceptions b/Documentation/media/frontend.h.rst.exceptions index 7656770f1936..f7c4df620a52 100644 --- a/Documentation/media/frontend.h.rst.exceptions +++ b/Documentation/media/frontend.h.rst.exceptions @@ -25,19 +25,9 @@ ignore define DTV_MAX_COMMAND ignore define MAX_DTV_STATS ignore define DTV_IOCTL_MAX_MSGS -# Stats enum is documented altogether -replace enum fecap_scale_params :ref:`frontend-stat-properties` -replace symbol FE_SCALE_COUNTER frontend-stat-properties -replace symbol FE_SCALE_DECIBEL frontend-stat-properties -replace symbol FE_SCALE_NOT_AVAILABLE frontend-stat-properties -replace symbol FE_SCALE_RELATIVE frontend-stat-properties - # the same reference is used for both get and set ioctls replace ioctl FE_SET_PROPERTY :c:type:`FE_GET_PROPERTY` -# Ignore struct used only internally at Kernel -ignore struct dtv_cmds_h - # Typedefs that use the enum reference replace typedef fe_sec_voltage_t :c:type:`fe_sec_voltage` @@ -45,3 +35,178 @@ replace typedef fe_sec_voltage_t :c:type:`fe_sec_voltage` replace define FE_TUNE_MODE_ONESHOT :c:func:`FE_SET_FRONTEND_TUNE_MODE` replace define LNA_AUTO dtv-lna replace define NO_STREAM_ID_FILTER dtv-stream-id + +# Those enums are defined at the frontend.h header, and not externally + +ignore symbol FE_IS_STUPID +ignore symbol FE_CAN_INVERSION_AUTO +ignore symbol FE_CAN_FEC_1_2 +ignore symbol FE_CAN_FEC_2_3 +ignore symbol FE_CAN_FEC_3_4 +ignore symbol FE_CAN_FEC_4_5 +ignore symbol FE_CAN_FEC_5_6 +ignore symbol FE_CAN_FEC_6_7 +ignore symbol FE_CAN_FEC_7_8 +ignore symbol FE_CAN_FEC_8_9 +ignore symbol FE_CAN_FEC_AUTO +ignore symbol FE_CAN_QPSK +ignore symbol FE_CAN_QAM_16 +ignore symbol FE_CAN_QAM_32 +ignore symbol FE_CAN_QAM_64 +ignore symbol FE_CAN_QAM_128 +ignore symbol FE_CAN_QAM_256 +ignore symbol FE_CAN_QAM_AUTO +ignore symbol FE_CAN_TRANSMISSION_MODE_AUTO +ignore symbol FE_CAN_BANDWIDTH_AUTO +ignore symbol FE_CAN_GUARD_INTERVAL_AUTO +ignore symbol FE_CAN_HIERARCHY_AUTO +ignore symbol FE_CAN_8VSB +ignore symbol FE_CAN_16VSB +ignore symbol FE_HAS_EXTENDED_CAPS +ignore symbol FE_CAN_MULTISTREAM +ignore symbol FE_CAN_TURBO_FEC +ignore symbol FE_CAN_2G_MODULATION +ignore symbol FE_NEEDS_BENDING +ignore symbol FE_CAN_RECOVER +ignore symbol FE_CAN_MUTE_TS + +ignore symbol QPSK +ignore symbol QAM_16 +ignore symbol QAM_32 +ignore symbol QAM_64 +ignore symbol QAM_128 +ignore symbol QAM_256 +ignore symbol QAM_AUTO +ignore symbol VSB_8 +ignore symbol VSB_16 +ignore symbol PSK_8 +ignore symbol APSK_16 +ignore symbol APSK_32 +ignore symbol DQPSK +ignore symbol QAM_4_NR + +ignore symbol SEC_VOLTAGE_13 +ignore symbol SEC_VOLTAGE_18 +ignore symbol SEC_VOLTAGE_OFF + +ignore symbol SEC_TONE_ON +ignore symbol SEC_TONE_OFF + +ignore symbol SEC_MINI_A +ignore symbol SEC_MINI_B + +ignore symbol FE_NONE +ignore symbol FE_HAS_SIGNAL +ignore symbol FE_HAS_CARRIER +ignore symbol FE_HAS_VITERBI +ignore symbol FE_HAS_SYNC +ignore symbol FE_HAS_LOCK +ignore symbol FE_REINIT +ignore symbol FE_TIMEDOUT + +ignore symbol FEC_NONE +ignore symbol FEC_1_2 +ignore symbol FEC_2_3 +ignore symbol FEC_3_4 +ignore symbol FEC_4_5 +ignore symbol FEC_5_6 +ignore symbol FEC_6_7 +ignore symbol FEC_7_8 +ignore symbol FEC_8_9 +ignore symbol FEC_AUTO +ignore symbol FEC_3_5 +ignore symbol FEC_9_10 +ignore symbol FEC_2_5 + +ignore symbol TRANSMISSION_MODE_AUTO +ignore symbol TRANSMISSION_MODE_1K +ignore symbol TRANSMISSION_MODE_2K +ignore symbol TRANSMISSION_MODE_8K +ignore symbol TRANSMISSION_MODE_4K +ignore symbol TRANSMISSION_MODE_16K +ignore symbol TRANSMISSION_MODE_32K +ignore symbol TRANSMISSION_MODE_C1 +ignore symbol TRANSMISSION_MODE_C3780 +ignore symbol TRANSMISSION_MODE_2K +ignore symbol TRANSMISSION_MODE_8K + +ignore symbol GUARD_INTERVAL_AUTO +ignore symbol GUARD_INTERVAL_1_128 +ignore symbol GUARD_INTERVAL_1_32 +ignore symbol GUARD_INTERVAL_1_16 +ignore symbol GUARD_INTERVAL_1_8 +ignore symbol GUARD_INTERVAL_1_4 +ignore symbol GUARD_INTERVAL_19_128 +ignore symbol GUARD_INTERVAL_19_256 +ignore symbol GUARD_INTERVAL_PN420 +ignore symbol GUARD_INTERVAL_PN595 +ignore symbol GUARD_INTERVAL_PN945 + +ignore symbol HIERARCHY_NONE +ignore symbol HIERARCHY_AUTO +ignore symbol HIERARCHY_1 +ignore symbol HIERARCHY_2 +ignore symbol HIERARCHY_4 + +ignore symbol INTERLEAVING_NONE +ignore symbol INTERLEAVING_AUTO +ignore symbol INTERLEAVING_240 +ignore symbol INTERLEAVING_720 + +ignore symbol PILOT_ON +ignore symbol PILOT_OFF +ignore symbol PILOT_AUTO + +ignore symbol ROLLOFF_35 +ignore symbol ROLLOFF_20 +ignore symbol ROLLOFF_25 +ignore symbol ROLLOFF_AUTO + +ignore symbol INVERSION_ON +ignore symbol INVERSION_OFF +ignore symbol INVERSION_AUTO + +ignore symbol SYS_UNDEFINED +ignore symbol SYS_DVBC_ANNEX_A +ignore symbol SYS_DVBC_ANNEX_B +ignore symbol SYS_DVBC_ANNEX_C +ignore symbol SYS_ISDBC +ignore symbol SYS_DVBT +ignore symbol SYS_DVBT2 +ignore symbol SYS_ISDBT +ignore symbol SYS_ATSC +ignore symbol SYS_ATSCMH +ignore symbol SYS_DTMB +ignore symbol SYS_DVBS +ignore symbol SYS_DVBS2 +ignore symbol SYS_TURBO +ignore symbol SYS_ISDBS +ignore symbol SYS_DAB +ignore symbol SYS_DSS +ignore symbol SYS_CMMB +ignore symbol SYS_DVBH + +ignore symbol ATSCMH_SCCC_BLK_SEP +ignore symbol ATSCMH_SCCC_BLK_COMB +ignore symbol ATSCMH_SCCC_BLK_RES + +ignore symbol ATSCMH_SCCC_CODE_HLF +ignore symbol ATSCMH_SCCC_CODE_QTR +ignore symbol ATSCMH_SCCC_CODE_RES + +ignore symbol ATSCMH_RSFRAME_ENS_PRI +ignore symbol ATSCMH_RSFRAME_ENS_SEC + +ignore symbol ATSCMH_RSFRAME_PRI_ONLY +ignore symbol ATSCMH_RSFRAME_PRI_SEC +ignore symbol ATSCMH_RSFRAME_RES + +ignore symbol ATSCMH_RSCODE_211_187 +ignore symbol ATSCMH_RSCODE_223_187 +ignore symbol ATSCMH_RSCODE_235_187 +ignore symbol ATSCMH_RSCODE_RES + +ignore symbol FE_SCALE_NOT_AVAILABLE +ignore symbol FE_SCALE_DECIBEL +ignore symbol FE_SCALE_RELATIVE +ignore symbol FE_SCALE_COUNTER diff --git a/Documentation/media/uapi/dvb/dtv-fe-stats.rst b/Documentation/media/uapi/dvb/dtv-fe-stats.rst deleted file mode 100644 index e8a02a1f138d..000000000000 --- a/Documentation/media/uapi/dvb/dtv-fe-stats.rst +++ /dev/null @@ -1,17 +0,0 @@ -.. -*- coding: utf-8; mode: rst -*- - -.. c:type:: dtv_fe_stats - -******************* -struct dtv_fe_stats -******************* - - -.. code-block:: c - - #define MAX_DTV_STATS 4 - - struct dtv_fe_stats { - __u8 len; - struct dtv_stats stat[MAX_DTV_STATS]; - } __packed; diff --git a/Documentation/media/uapi/dvb/dtv-properties.rst b/Documentation/media/uapi/dvb/dtv-properties.rst deleted file mode 100644 index 48c4e834ad11..000000000000 --- a/Documentation/media/uapi/dvb/dtv-properties.rst +++ /dev/null @@ -1,15 +0,0 @@ -.. -*- coding: utf-8; mode: rst -*- - -.. c:type:: dtv_properties - -********************* -struct dtv_properties -********************* - - -.. code-block:: c - - struct dtv_properties { - __u32 num; - struct dtv_property *props; - }; diff --git a/Documentation/media/uapi/dvb/dtv-property.rst b/Documentation/media/uapi/dvb/dtv-property.rst deleted file mode 100644 index 3ddc3474b00e..000000000000 --- a/Documentation/media/uapi/dvb/dtv-property.rst +++ /dev/null @@ -1,31 +0,0 @@ -.. -*- coding: utf-8; mode: rst -*- - -.. c:type:: dtv_property - -******************* -struct dtv_property -******************* - - -.. code-block:: c - - /* Reserved fields should be set to 0 */ - - struct dtv_property { - __u32 cmd; - __u32 reserved[3]; - union { - __u32 data; - struct dtv_fe_stats st; - struct { - __u8 data[32]; - __u32 len; - __u32 reserved1[3]; - void *reserved2; - } buffer; - } u; - int result; - } __attribute__ ((packed)); - - /* num of properties cannot exceed DTV_IOCTL_MAX_MSGS per ioctl */ - #define DTV_IOCTL_MAX_MSGS 64 diff --git a/Documentation/media/uapi/dvb/dtv-stats.rst b/Documentation/media/uapi/dvb/dtv-stats.rst deleted file mode 100644 index 35239e72bf74..000000000000 --- a/Documentation/media/uapi/dvb/dtv-stats.rst +++ /dev/null @@ -1,18 +0,0 @@ -.. -*- coding: utf-8; mode: rst -*- - -.. c:type:: dtv_stats - -**************** -struct dtv_stats -**************** - - -.. code-block:: c - - struct dtv_stats { - __u8 scale; /* enum fecap_scale_params type */ - union { - __u64 uvalue; /* for counters and relative scales */ - __s64 svalue; /* for 1/1000 dB measures */ - }; - } __packed; diff --git a/Documentation/media/uapi/dvb/dvbproperty-006.rst b/Documentation/media/uapi/dvb/dvbproperty-006.rst deleted file mode 100644 index 3343a0f306fe..000000000000 --- a/Documentation/media/uapi/dvb/dvbproperty-006.rst +++ /dev/null @@ -1,12 +0,0 @@ -.. -*- coding: utf-8; mode: rst -*- - -************** -Property types -************** - -On :ref:`FE_GET_PROPERTY and FE_SET_PROPERTY `, -the actual action is determined by the dtv_property cmd/data pairs. -With one single ioctl, is possible to get/set up to 64 properties. The -actual meaning of each property is described on the next sections. - -The available frontend property types are shown on the next section. diff --git a/Documentation/media/uapi/dvb/dvbproperty.rst b/Documentation/media/uapi/dvb/dvbproperty.rst index 843f1d70aff0..c40943be5925 100644 --- a/Documentation/media/uapi/dvb/dvbproperty.rst +++ b/Documentation/media/uapi/dvb/dvbproperty.rst @@ -2,8 +2,9 @@ .. _frontend-properties: -DVB Frontend properties -======================= +************** +Property types +************** Tuning into a Digital TV physical channel and starting decoding it requires changing a set of parameters, in order to control the tuner, @@ -20,10 +21,15 @@ enough to group the structs that would be required for those new standards. Also, extending it would break userspace. So, the legacy union/struct based approach was deprecated, in favor -of a properties set approach. +of a properties set approach. On such approach, +:ref:`FE_GET_PROPERTY and FE_SET_PROPERTY ` are used +to setup the frontend and read its status. + +The actual action is determined by a set of dtv_property cmd/data pairs. +With one single ioctl, is possible to get/set up to 64 properties. This section describes the new and recommended way to set the frontend, -with suppports all digital TV delivery systems. +with supports all digital TV delivery systems. .. note:: @@ -63,12 +69,9 @@ Mbauds, those properties should be sent to The code that would that would do the above is show in :ref:`dtv-prop-example`. -.. _dtv-prop-example: - -Example: Setting digital TV frontend properties -=============================================== - .. code-block:: c + :caption: Example: Setting digital TV frontend properties + :name: dtv-prop-example #include #include @@ -112,17 +115,12 @@ Example: Setting digital TV frontend properties provides methods for usual operations like program scanning and to read/write channel descriptor files. - .. toctree:: :maxdepth: 1 - dtv-stats - dtv-fe-stats - dtv-property - dtv-properties - dvbproperty-006 fe_property_parameters frontend-stat-properties frontend-property-terrestrial-systems frontend-property-cable-systems frontend-property-satellite-systems + frontend-header diff --git a/Documentation/media/uapi/dvb/fe-diseqc-recv-slave-reply.rst b/Documentation/media/uapi/dvb/fe-diseqc-recv-slave-reply.rst index 302db2857f90..473855584d7f 100644 --- a/Documentation/media/uapi/dvb/fe-diseqc-recv-slave-reply.rst +++ b/Documentation/media/uapi/dvb/fe-diseqc-recv-slave-reply.rst @@ -26,8 +26,7 @@ Arguments File descriptor returned by :ref:`open() `. ``argp`` - pointer to struct - :c:type:`dvb_diseqc_slave_reply` + pointer to struct :c:type:`dvb_diseqc_slave_reply`. Description @@ -35,42 +34,7 @@ Description Receives reply from a DiSEqC 2.0 command. -.. c:type:: dvb_diseqc_slave_reply - -.. tabularcolumns:: |p{4.4cm}|p{4.4cm}|p{8.7cm}| - -.. flat-table:: struct dvb_diseqc_slave_reply - :header-rows: 0 - :stub-columns: 0 - :widths: 1 1 2 - - - - .. row 1 - - - uint8_t - - - msg[4] - - - DiSEqC message (framing, data[3]) - - - .. row 2 - - - uint8_t - - - msg_len - - - Length of the DiSEqC message. Valid values are 0 to 4, where 0 - means no msg - - - .. row 3 - - - int - - - timeout - - - Return from ioctl after timeout ms with errorcode when no message - was received - +The received message is stored at the buffer pointed by ``argp``. Return Value ============ diff --git a/Documentation/media/uapi/dvb/fe-diseqc-send-burst.rst b/Documentation/media/uapi/dvb/fe-diseqc-send-burst.rst index e962f6ec5aaf..54d35517e784 100644 --- a/Documentation/media/uapi/dvb/fe-diseqc-send-burst.rst +++ b/Documentation/media/uapi/dvb/fe-diseqc-send-burst.rst @@ -26,7 +26,7 @@ Arguments File descriptor returned by :ref:`open() `. ``tone`` - an integer enumered value described at :c:type:`fe_sec_mini_cmd` + An integer enumered value described at :c:type:`fe_sec_mini_cmd`. Description @@ -39,35 +39,6 @@ read/write permissions. It provides support for what's specified at `Digital Satellite Equipment Control (DiSEqC) - Simple "ToneBurst" Detection Circuit specification. `__ -.. c:type:: fe_sec_mini_cmd - -.. flat-table:: enum fe_sec_mini_cmd - :header-rows: 1 - :stub-columns: 0 - - - - .. row 1 - - - ID - - - Description - - - .. row 2 - - - .. _SEC-MINI-A: - - ``SEC_MINI_A`` - - - Sends a mini-DiSEqC 22kHz '0' Tone Burst to select satellite-A - - - .. row 3 - - - .. _SEC-MINI-B: - - ``SEC_MINI_B`` - - - Sends a mini-DiSEqC 22kHz '1' Data Burst to select satellite-B - Return Value ============ diff --git a/Documentation/media/uapi/dvb/fe-diseqc-send-master-cmd.rst b/Documentation/media/uapi/dvb/fe-diseqc-send-master-cmd.rst index bbcab3df39b5..7392d6747ad6 100644 --- a/Documentation/media/uapi/dvb/fe-diseqc-send-master-cmd.rst +++ b/Documentation/media/uapi/dvb/fe-diseqc-send-master-cmd.rst @@ -33,34 +33,7 @@ Arguments Description =========== -Sends a DiSEqC command to the antenna subsystem. - - -.. c:type:: dvb_diseqc_master_cmd - -.. tabularcolumns:: |p{4.4cm}|p{4.4cm}|p{8.7cm}| - -.. flat-table:: struct dvb_diseqc_master_cmd - :header-rows: 0 - :stub-columns: 0 - :widths: 1 1 2 - - - - .. row 1 - - - uint8_t - - - msg[6] - - - DiSEqC message (framing, address, command, data[3]) - - - .. row 2 - - - uint8_t - - - msg_len - - - Length of the DiSEqC message. Valid values are 3 to 6 +Sends the DiSEqC command pointed by ``argp`` to the antenna subsystem. Return Value ============ diff --git a/Documentation/media/uapi/dvb/fe-get-info.rst b/Documentation/media/uapi/dvb/fe-get-info.rst index e3d64b251f61..30dde8a791f3 100644 --- a/Documentation/media/uapi/dvb/fe-get-info.rst +++ b/Documentation/media/uapi/dvb/fe-get-info.rst @@ -40,112 +40,6 @@ takes a pointer to dvb_frontend_info which is filled by the driver. When the driver is not compatible with this specification the ioctl returns an error. -.. c:type:: dvb_frontend_info - -.. tabularcolumns:: |p{4.4cm}|p{4.4cm}|p{8.7cm}| - -.. flat-table:: struct dvb_frontend_info - :header-rows: 0 - :stub-columns: 0 - :widths: 1 1 2 - - - - .. row 1 - - - char - - - name[128] - - - Name of the frontend - - - .. row 2 - - - fe_type_t - - - type - - - **DEPRECATED**. DVBv3 type. Should not be used on modern programs, - as a frontend may have more than one type. So, the DVBv5 API - should be used instead to enumerate and select the frontend type. - - - .. row 3 - - - uint32_t - - - frequency_min - - - Minimal frequency supported by the frontend - - - .. row 4 - - - uint32_t - - - frequency_max - - - Maximal frequency supported by the frontend - - - .. row 5 - - - uint32_t - - - frequency_stepsize - - - Frequency step - all frequencies are multiple of this value - - - .. row 6 - - - uint32_t - - - frequency_tolerance - - - Tolerance of the frequency - - - .. row 7 - - - uint32_t - - - symbol_rate_min - - - Minimal symbol rate (for Cable/Satellite systems), in bauds - - - .. row 8 - - - uint32_t - - - symbol_rate_max - - - Maximal symbol rate (for Cable/Satellite systems), in bauds - - - .. row 9 - - - uint32_t - - - symbol_rate_tolerance - - - Maximal symbol rate tolerance, in ppm - - - .. row 10 - - - uint32_t - - - notifier_delay - - - **DEPRECATED**. Not used by any driver. - - - .. row 11 - - - enum :c:type:`fe_caps` - - - caps - - - Capabilities supported by the frontend - - -.. note:: - - The frequencies are specified in Hz for Terrestrial and Cable - systems. They're specified in kHz for Satellite systems - frontend capabilities ===================== @@ -153,269 +47,7 @@ frontend capabilities Capabilities describe what a frontend can do. Some capabilities are supported only on some specific frontend types. -.. c:type:: fe_caps - -.. tabularcolumns:: |p{6.5cm}|p{11.0cm}| - -.. flat-table:: enum fe_caps - :header-rows: 1 - :stub-columns: 0 - - - - .. row 1 - - - ID - - - Description - - - .. row 2 - - - .. _FE-IS-STUPID: - - ``FE_IS_STUPID`` - - - There's something wrong at the frontend, and it can't report its - capabilities - - - .. row 3 - - - .. _FE-CAN-INVERSION-AUTO: - - ``FE_CAN_INVERSION_AUTO`` - - - The frontend is capable of auto-detecting inversion - - - .. row 4 - - - .. _FE-CAN-FEC-1-2: - - ``FE_CAN_FEC_1_2`` - - - The frontend supports FEC 1/2 - - - .. row 5 - - - .. _FE-CAN-FEC-2-3: - - ``FE_CAN_FEC_2_3`` - - - The frontend supports FEC 2/3 - - - .. row 6 - - - .. _FE-CAN-FEC-3-4: - - ``FE_CAN_FEC_3_4`` - - - The frontend supports FEC 3/4 - - - .. row 7 - - - .. _FE-CAN-FEC-4-5: - - ``FE_CAN_FEC_4_5`` - - - The frontend supports FEC 4/5 - - - .. row 8 - - - .. _FE-CAN-FEC-5-6: - - ``FE_CAN_FEC_5_6`` - - - The frontend supports FEC 5/6 - - - .. row 9 - - - .. _FE-CAN-FEC-6-7: - - ``FE_CAN_FEC_6_7`` - - - The frontend supports FEC 6/7 - - - .. row 10 - - - .. _FE-CAN-FEC-7-8: - - ``FE_CAN_FEC_7_8`` - - - The frontend supports FEC 7/8 - - - .. row 11 - - - .. _FE-CAN-FEC-8-9: - - ``FE_CAN_FEC_8_9`` - - - The frontend supports FEC 8/9 - - - .. row 12 - - - .. _FE-CAN-FEC-AUTO: - - ``FE_CAN_FEC_AUTO`` - - - The frontend can autodetect FEC. - - - .. row 13 - - - .. _FE-CAN-QPSK: - - ``FE_CAN_QPSK`` - - - The frontend supports QPSK modulation - - - .. row 14 - - - .. _FE-CAN-QAM-16: - - ``FE_CAN_QAM_16`` - - - The frontend supports 16-QAM modulation - - - .. row 15 - - - .. _FE-CAN-QAM-32: - - ``FE_CAN_QAM_32`` - - - The frontend supports 32-QAM modulation - - - .. row 16 - - - .. _FE-CAN-QAM-64: - - ``FE_CAN_QAM_64`` - - - The frontend supports 64-QAM modulation - - - .. row 17 - - - .. _FE-CAN-QAM-128: - - ``FE_CAN_QAM_128`` - - - The frontend supports 128-QAM modulation - - - .. row 18 - - - .. _FE-CAN-QAM-256: - - ``FE_CAN_QAM_256`` - - - The frontend supports 256-QAM modulation - - - .. row 19 - - - .. _FE-CAN-QAM-AUTO: - - ``FE_CAN_QAM_AUTO`` - - - The frontend can autodetect modulation - - - .. row 20 - - - .. _FE-CAN-TRANSMISSION-MODE-AUTO: - - ``FE_CAN_TRANSMISSION_MODE_AUTO`` - - - The frontend can autodetect the transmission mode - - - .. row 21 - - - .. _FE-CAN-BANDWIDTH-AUTO: - - ``FE_CAN_BANDWIDTH_AUTO`` - - - The frontend can autodetect the bandwidth - - - .. row 22 - - - .. _FE-CAN-GUARD-INTERVAL-AUTO: - - ``FE_CAN_GUARD_INTERVAL_AUTO`` - - - The frontend can autodetect the guard interval - - - .. row 23 - - - .. _FE-CAN-HIERARCHY-AUTO: - - ``FE_CAN_HIERARCHY_AUTO`` - - - The frontend can autodetect hierarch - - - .. row 24 - - - .. _FE-CAN-8VSB: - - ``FE_CAN_8VSB`` - - - The frontend supports 8-VSB modulation - - - .. row 25 - - - .. _FE-CAN-16VSB: - - ``FE_CAN_16VSB`` - - - The frontend supports 16-VSB modulation - - - .. row 26 - - - .. _FE-HAS-EXTENDED-CAPS: - - ``FE_HAS_EXTENDED_CAPS`` - - - Currently, unused - - - .. row 27 - - - .. _FE-CAN-MULTISTREAM: - - ``FE_CAN_MULTISTREAM`` - - - The frontend supports multistream filtering - - - .. row 28 - - - .. _FE-CAN-TURBO-FEC: - - ``FE_CAN_TURBO_FEC`` - - - The frontend supports turbo FEC modulation - - - .. row 29 - - - .. _FE-CAN-2G-MODULATION: - - ``FE_CAN_2G_MODULATION`` - - - The frontend supports "2nd generation modulation" (DVB-S2/T2)> - - - .. row 30 - - - .. _FE-NEEDS-BENDING: - - ``FE_NEEDS_BENDING`` - - - Not supported anymore, don't use it - - - .. row 31 - - - .. _FE-CAN-RECOVER: - - ``FE_CAN_RECOVER`` - - - The frontend can recover from a cable unplug automatically - - - .. row 32 - - - .. _FE-CAN-MUTE-TS: - - ``FE_CAN_MUTE_TS`` - - - The frontend can stop spurious TS data output +The frontend capabilities are described at :c:type:`fe_caps`. Return Value diff --git a/Documentation/media/uapi/dvb/fe-get-property.rst b/Documentation/media/uapi/dvb/fe-get-property.rst index 015d4db597b5..b22e37c4a787 100644 --- a/Documentation/media/uapi/dvb/fe-get-property.rst +++ b/Documentation/media/uapi/dvb/fe-get-property.rst @@ -29,7 +29,7 @@ Arguments File descriptor returned by :ref:`open() `. ``argp`` - pointer to struct :c:type:`dtv_properties` + Pointer to struct :c:type:`dtv_properties`. Description diff --git a/Documentation/media/uapi/dvb/fe-read-status.rst b/Documentation/media/uapi/dvb/fe-read-status.rst index 76b93e386552..21b2db3591fd 100644 --- a/Documentation/media/uapi/dvb/fe-read-status.rst +++ b/Documentation/media/uapi/dvb/fe-read-status.rst @@ -52,89 +52,6 @@ The fe_status parameter is used to indicate the current state and/or state changes of the frontend hardware. It is produced using the enum :c:type:`fe_status` values on a bitmask -.. c:type:: fe_status - -.. tabularcolumns:: |p{3.5cm}|p{14.0cm}| - -.. _fe-status: - -.. flat-table:: enum fe_status - :header-rows: 1 - :stub-columns: 0 - - - - .. row 1 - - - ID - - - Description - - - .. row 2 - - - .. _FE-NONE: - - ``FE_NONE`` - - - The frontend doesn't have any kind of lock. That's the initial frontend status - - - .. row 3 - - - .. _FE-HAS-SIGNAL: - - ``FE_HAS_SIGNAL`` - - - The frontend has found something above the noise level - - - .. row 4 - - - .. _FE-HAS-CARRIER: - - ``FE_HAS_CARRIER`` - - - The frontend has found a DVB signal - - - .. row 5 - - - .. _FE-HAS-VITERBI: - - ``FE_HAS_VITERBI`` - - - The frontend FEC inner coding (Viterbi, LDPC or other inner code) - is stable - - - .. row 6 - - - .. _FE-HAS-SYNC: - - ``FE_HAS_SYNC`` - - - Synchronization bytes was found - - - .. row 7 - - - .. _FE-HAS-LOCK: - - ``FE_HAS_LOCK`` - - - The DVB were locked and everything is working - - - .. row 8 - - - .. _FE-TIMEDOUT: - - ``FE_TIMEDOUT`` - - - no lock within the last about 2 seconds - - - .. row 9 - - - .. _FE-REINIT: - - ``FE_REINIT`` - - - The frontend was reinitialized, application is recommended to - reset DiSEqC, tone and parameters - Return Value ============ diff --git a/Documentation/media/uapi/dvb/fe-set-tone.rst b/Documentation/media/uapi/dvb/fe-set-tone.rst index 84e4da3fd4c9..d0950acbbe64 100644 --- a/Documentation/media/uapi/dvb/fe-set-tone.rst +++ b/Documentation/media/uapi/dvb/fe-set-tone.rst @@ -45,36 +45,6 @@ this is done using the DiSEqC ioctls. capability of selecting the band. So, it is recommended that applications would change to SEC_TONE_OFF when the device is not used. -.. c:type:: fe_sec_tone_mode - -.. flat-table:: enum fe_sec_tone_mode - :header-rows: 1 - :stub-columns: 0 - - - - .. row 1 - - - ID - - - Description - - - .. row 2 - - - .. _SEC-TONE-ON: - - ``SEC_TONE_ON`` - - - Sends a 22kHz tone burst to the antenna - - - .. row 3 - - - .. _SEC-TONE-OFF: - - ``SEC_TONE_OFF`` - - - Don't send a 22kHz tone to the antenna (except if the - FE_DISEQC_* ioctls are called) - Return Value ============ diff --git a/Documentation/media/uapi/dvb/fe_property_parameters.rst b/Documentation/media/uapi/dvb/fe_property_parameters.rst index 7bb7559c4500..c6eb74f59b00 100644 --- a/Documentation/media/uapi/dvb/fe_property_parameters.rst +++ b/Documentation/media/uapi/dvb/fe_property_parameters.rst @@ -6,6 +6,11 @@ Digital TV property parameters ****************************** +There are several different Digital TV parameters that can be used by +:ref:`FE_SET_PROPERTY and FE_GET_PROPERTY ioctls`. +This section describes each of them. Please notice, however, that only +a subset of them are needed to setup a frontend. + .. _DTV-UNDEFINED: @@ -67,144 +72,36 @@ DTV_MODULATION ============== Specifies the frontend modulation type for delivery systems that -supports more than one modulation type. The modulation can be one of the -types defined by enum :c:type:`fe_modulation`. - - -.. c:type:: fe_modulation - -Modulation property -------------------- - -Most of the digital TV standards currently offers more than one possible -modulation (sometimes called as "constellation" on some standards). This -enum contains the values used by the Kernel. Please note that not all -modulations are supported by a given standard. - - -.. flat-table:: enum fe_modulation - :header-rows: 1 - :stub-columns: 0 - - - - .. row 1 - - - ID - - - Description - - - .. row 2 - - - .. _QPSK: - - ``QPSK`` - - - QPSK modulation - - - .. row 3 - - - .. _QAM-16: - - ``QAM_16`` - - - 16-QAM modulation - - - .. row 4 - - - .. _QAM-32: - - ``QAM_32`` - - - 32-QAM modulation - - - .. row 5 - - - .. _QAM-64: - - ``QAM_64`` - - - 64-QAM modulation - - - .. row 6 - - - .. _QAM-128: - - ``QAM_128`` - - - 128-QAM modulation - - - .. row 7 - - - .. _QAM-256: - - ``QAM_256`` - - - 256-QAM modulation - - - .. row 8 - - - .. _QAM-AUTO: - - ``QAM_AUTO`` - - - Autodetect QAM modulation - - - .. row 9 - - - .. _VSB-8: - - ``VSB_8`` - - - 8-VSB modulation - - - .. row 10 - - - .. _VSB-16: - - ``VSB_16`` - - - 16-VSB modulation - - - .. row 11 - - - .. _PSK-8: - - ``PSK_8`` - - - 8-PSK modulation - - - .. row 12 - - - .. _APSK-16: - - ``APSK_16`` - - - 16-APSK modulation - - - .. row 13 - - - .. _APSK-32: +supports more multiple modulations. + +The modulation can be one of the types defined by enum :c:type:`fe_modulation`. + +Most of the digital TV standards offers more than one possible +modulation type. + +The table below presents a summary of the types of modulation types +supported by each delivery system, as currently defined by specs. + +======================= ======================================================= +Standard Modulation types +======================= ======================================================= +ATSC (version 1) 8-VSB and 16-VSB. +DMTB 4-QAM, 16-QAM, 32-QAM, 64-QAM and 4-QAM-NR. +DVB-C Annex A/C 16-QAM, 32-QAM, 64-QAM and 256-QAM. +DVB-C Annex B 64-QAM. +DVB-T QPSK, 16-QAM and 64-QAM. +DVB-T2 QPSK, 16-QAM, 64-QAM and 256-QAM. +DVB-S No need to set. It supports only QPSK. +DVB-S2 QPSK, 8-PSK, 16-APSK and 32-APSK. +ISDB-T QPSK, DQPSK, 16-QAM and 64-QAM. +ISDB-S 8-PSK, QPSK and BPSK. +======================= ======================================================= - ``APSK_32`` - - - 32-APSK modulation - - - .. row 14 - - - .. _DQPSK: - - ``DQPSK`` - - - DQPSK modulation - - - .. row 15 - - - .. _QAM-4-NR: - - ``QAM_4_NR`` - - - 4-QAM-NR modulation +.. note:: + Please notice that some of the above modulation types may not be + defined currently at the Kernel. The reason is simple: no driver + needed such definition yet. .. _DTV-BANDWIDTH-HZ: @@ -249,54 +146,7 @@ DTV_INVERSION Specifies if the frontend should do spectral inversion or not. -.. c:type:: fe_spectral_inversion - -enum fe_modulation: Frontend spectral inversion ------------------------------------------------ - -This parameter indicates if spectral inversion should be presumed or -not. In the automatic setting (``INVERSION_AUTO``) the hardware will try -to figure out the correct setting by itself. If the hardware doesn't -support, the DVB core will try to lock at the carrier first with -inversion off. If it fails, it will try to enable inversion. - - -.. flat-table:: enum fe_modulation - :header-rows: 1 - :stub-columns: 0 - - - - .. row 1 - - - ID - - - Description - - - .. row 2 - - - .. _INVERSION-OFF: - - ``INVERSION_OFF`` - - - Don't do spectral band inversion. - - - .. row 3 - - - .. _INVERSION-ON: - - ``INVERSION_ON`` - - - Do spectral band inversion. - - - .. row 4 - - - .. _INVERSION-AUTO: - - ``INVERSION_AUTO`` - - - Autodetect spectral band inversion. - - +The acceptable values are defined by :c:type:`fe_spectral_inversion`. .. _DTV-DISEQC-MASTER: @@ -320,1525 +170,671 @@ standards. DTV_INNER_FEC ============= -Used cable/satellite transmissions. The acceptable values are: +Used cable/satellite transmissions. -.. c:type:: fe_code_rate +The acceptable values are defined by :c:type:`fe_code_rate`. -enum fe_code_rate: type of the Forward Error Correction. --------------------------------------------------------- -.. flat-table:: enum fe_code_rate - :header-rows: 1 - :stub-columns: 0 +.. _DTV-VOLTAGE: +DTV_VOLTAGE +=========== - - .. row 1 +The voltage is usually used with non-DiSEqC capable LNBs to switch the +polarzation (horizontal/vertical). When using DiSEqC epuipment this +voltage has to be switched consistently to the DiSEqC commands as +described in the DiSEqC spec. - - ID +The acceptable values are defined by :c:type:`fe_sec_voltage`. - - Description - - .. row 2 +.. _DTV-TONE: - - .. _FEC-NONE: +DTV_TONE +======== - ``FEC_NONE`` +Currently not used. - - No Forward Error Correction Code - - .. row 3 +.. _DTV-PILOT: - - .. _FEC-AUTO: +DTV_PILOT +========= - ``FEC_AUTO`` +Sets DVB-S2 pilot. - - Autodetect Error Correction Code +The acceptable values are defined by :c:type:`fe_pilot`. - - .. row 4 - - .. _FEC-1-2: +.. _DTV-ROLLOFF: - ``FEC_1_2`` +DTV_ROLLOFF +=========== - - Forward Error Correction Code 1/2 +Sets DVB-S2 rolloff - - .. row 5 +The acceptable values are defined by :c:type:`fe_rolloff`. - - .. _FEC-2-3: - ``FEC_2_3`` +.. _DTV-DISEQC-SLAVE-REPLY: - - Forward Error Correction Code 2/3 +DTV_DISEQC_SLAVE_REPLY +====================== - - .. row 6 +Currently not implemented. - - .. _FEC-3-4: - ``FEC_3_4`` +.. _DTV-FE-CAPABILITY-COUNT: - - Forward Error Correction Code 3/4 +DTV_FE_CAPABILITY_COUNT +======================= - - .. row 7 +Currently not implemented. - - .. _FEC-4-5: - ``FEC_4_5`` +.. _DTV-FE-CAPABILITY: - - Forward Error Correction Code 4/5 +DTV_FE_CAPABILITY +================= - - .. row 8 +Currently not implemented. - - .. _FEC-5-6: - ``FEC_5_6`` +.. _DTV-DELIVERY-SYSTEM: - - Forward Error Correction Code 5/6 +DTV_DELIVERY_SYSTEM +=================== - - .. row 9 +Specifies the type of Delivery system. - - .. _FEC-6-7: +The acceptable values are defined by :c:type:`fe_delivery_system`. - ``FEC_6_7`` - - Forward Error Correction Code 6/7 +.. _DTV-ISDBT-PARTIAL-RECEPTION: - - .. row 10 +DTV_ISDBT_PARTIAL_RECEPTION +=========================== - - .. _FEC-7-8: +If ``DTV_ISDBT_SOUND_BROADCASTING`` is '0' this bit-field represents +whether the channel is in partial reception mode or not. - ``FEC_7_8`` +If '1' ``DTV_ISDBT_LAYERA_*`` values are assigned to the center segment +and ``DTV_ISDBT_LAYERA_SEGMENT_COUNT`` has to be '1'. - - Forward Error Correction Code 7/8 +If in addition ``DTV_ISDBT_SOUND_BROADCASTING`` is '1' +``DTV_ISDBT_PARTIAL_RECEPTION`` represents whether this ISDB-Tsb channel +is consisting of one segment and layer or three segments and two layers. - - .. row 11 +Possible values: 0, 1, -1 (AUTO) - - .. _FEC-8-9: - ``FEC_8_9`` +.. _DTV-ISDBT-SOUND-BROADCASTING: - - Forward Error Correction Code 8/9 +DTV_ISDBT_SOUND_BROADCASTING +============================ - - .. row 12 +This field represents whether the other DTV_ISDBT_*-parameters are +referring to an ISDB-T and an ISDB-Tsb channel. (See also +``DTV_ISDBT_PARTIAL_RECEPTION``). - - .. _FEC-9-10: +Possible values: 0, 1, -1 (AUTO) - ``FEC_9_10`` - - Forward Error Correction Code 9/10 +.. _DTV-ISDBT-SB-SUBCHANNEL-ID: - - .. row 13 +DTV_ISDBT_SB_SUBCHANNEL_ID +========================== - - .. _FEC-2-5: +This field only applies if ``DTV_ISDBT_SOUND_BROADCASTING`` is '1'. - ``FEC_2_5`` +(Note of the author: This might not be the correct description of the +``SUBCHANNEL-ID`` in all details, but it is my understanding of the +technical background needed to program a device) - - Forward Error Correction Code 2/5 +An ISDB-Tsb channel (1 or 3 segments) can be broadcasted alone or in a +set of connected ISDB-Tsb channels. In this set of channels every +channel can be received independently. The number of connected ISDB-Tsb +segment can vary, e.g. depending on the frequency spectrum bandwidth +available. - - .. row 14 +Example: Assume 8 ISDB-Tsb connected segments are broadcasted. The +broadcaster has several possibilities to put those channels in the air: +Assuming a normal 13-segment ISDB-T spectrum he can align the 8 segments +from position 1-8 to 5-13 or anything in between. - - .. _FEC-3-5: +The underlying layer of segments are subchannels: each segment is +consisting of several subchannels with a predefined IDs. A sub-channel +is used to help the demodulator to synchronize on the channel. - ``FEC_3_5`` +An ISDB-T channel is always centered over all sub-channels. As for the +example above, in ISDB-Tsb it is no longer as simple as that. - - Forward Error Correction Code 3/5 +``The DTV_ISDBT_SB_SUBCHANNEL_ID`` parameter is used to give the +sub-channel ID of the segment to be demodulated. +Possible values: 0 .. 41, -1 (AUTO) -.. _DTV-VOLTAGE: +.. _DTV-ISDBT-SB-SEGMENT-IDX: -DTV_VOLTAGE -=========== +DTV_ISDBT_SB_SEGMENT_IDX +======================== -The voltage is usually used with non-DiSEqC capable LNBs to switch the -polarzation (horizontal/vertical). When using DiSEqC epuipment this -voltage has to be switched consistently to the DiSEqC commands as -described in the DiSEqC spec. +This field only applies if ``DTV_ISDBT_SOUND_BROADCASTING`` is '1'. +``DTV_ISDBT_SB_SEGMENT_IDX`` gives the index of the segment to be +demodulated for an ISDB-Tsb channel where several of them are +transmitted in the connected manner. -.. c:type:: fe_sec_voltage +Possible values: 0 .. ``DTV_ISDBT_SB_SEGMENT_COUNT`` - 1 -.. flat-table:: enum fe_sec_voltage - :header-rows: 1 - :stub-columns: 0 +Note: This value cannot be determined by an automatic channel search. - - .. row 1 +.. _DTV-ISDBT-SB-SEGMENT-COUNT: - - ID +DTV_ISDBT_SB_SEGMENT_COUNT +========================== - - Description +This field only applies if ``DTV_ISDBT_SOUND_BROADCASTING`` is '1'. - - .. row 2 +``DTV_ISDBT_SB_SEGMENT_COUNT`` gives the total count of connected +ISDB-Tsb channels. - - .. _SEC-VOLTAGE-13: +Possible values: 1 .. 13 - ``SEC_VOLTAGE_13`` +Note: This value cannot be determined by an automatic channel search. - - Set DC voltage level to 13V - - .. row 3 +.. _isdb-hierq-layers: - - .. _SEC-VOLTAGE-18: +DTV-ISDBT-LAYER[A-C] parameters +=============================== - ``SEC_VOLTAGE_18`` +ISDB-T channels can be coded hierarchically. As opposed to DVB-T in +ISDB-T hierarchical layers can be decoded simultaneously. For that +reason a ISDB-T demodulator has 3 Viterbi and 3 Reed-Solomon decoders. - - Set DC voltage level to 18V +ISDB-T has 3 hierarchical layers which each can use a part of the +available segments. The total number of segments over all layers has to +13 in ISDB-T. - - .. row 4 +There are 3 parameter sets, for Layers A, B and C. - - .. _SEC-VOLTAGE-OFF: - ``SEC_VOLTAGE_OFF`` +.. _DTV-ISDBT-LAYER-ENABLED: - - Don't send any voltage to the antenna +DTV_ISDBT_LAYER_ENABLED +----------------------- +Hierarchical reception in ISDB-T is achieved by enabling or disabling +layers in the decoding process. Setting all bits of +``DTV_ISDBT_LAYER_ENABLED`` to '1' forces all layers (if applicable) to +be demodulated. This is the default. +If the channel is in the partial reception mode +(``DTV_ISDBT_PARTIAL_RECEPTION`` = 1) the central segment can be decoded +independently of the other 12 segments. In that mode layer A has to have +a ``SEGMENT_COUNT`` of 1. -.. _DTV-TONE: +In ISDB-Tsb only layer A is used, it can be 1 or 3 in ISDB-Tsb according +to ``DTV_ISDBT_PARTIAL_RECEPTION``. ``SEGMENT_COUNT`` must be filled +accordingly. -DTV_TONE -======== +Only the values of the first 3 bits are used. Other bits will be silently ignored: -Currently not used. +``DTV_ISDBT_LAYER_ENABLED`` bit 0: layer A enabled +``DTV_ISDBT_LAYER_ENABLED`` bit 1: layer B enabled -.. _DTV-PILOT: +``DTV_ISDBT_LAYER_ENABLED`` bit 2: layer C enabled -DTV_PILOT -========= +``DTV_ISDBT_LAYER_ENABLED`` bits 3-31: unused -Sets DVB-S2 pilot +.. _DTV-ISDBT-LAYER-FEC: -.. c:type:: fe_pilot +DTV_ISDBT_LAYER[A-C]_FEC +------------------------ -fe_pilot type -------------- +The Forward Error Correction mechanism used by a given ISDB Layer, as +defined by :c:type:`fe_code_rate`. -.. flat-table:: enum fe_pilot - :header-rows: 1 - :stub-columns: 0 +Possible values are: ``FEC_AUTO``, ``FEC_1_2``, ``FEC_2_3``, ``FEC_3_4``, +``FEC_5_6``, ``FEC_7_8`` - - .. row 1 - - - ID - - - Description - - - .. row 2 - - - .. _PILOT-ON: - - ``PILOT_ON`` - - - Pilot tones enabled - - - .. row 3 - - - .. _PILOT-OFF: - - ``PILOT_OFF`` - - - Pilot tones disabled - - - .. row 4 - - - .. _PILOT-AUTO: - - ``PILOT_AUTO`` - - - Autodetect pilot tones - - - -.. _DTV-ROLLOFF: - -DTV_ROLLOFF -=========== - -Sets DVB-S2 rolloff - - -.. c:type:: fe_rolloff - -fe_rolloff type ---------------- - - -.. flat-table:: enum fe_rolloff - :header-rows: 1 - :stub-columns: 0 - - - - .. row 1 - - - ID - - - Description - - - .. row 2 - - - .. _ROLLOFF-35: - - ``ROLLOFF_35`` - - - Roloff factor: α=35% - - - .. row 3 - - - .. _ROLLOFF-20: - - ``ROLLOFF_20`` - - - Roloff factor: α=20% - - - .. row 4 - - - .. _ROLLOFF-25: - - ``ROLLOFF_25`` - - - Roloff factor: α=25% - - - .. row 5 - - - .. _ROLLOFF-AUTO: - - ``ROLLOFF_AUTO`` - - - Auto-detect the roloff factor. - - - -.. _DTV-DISEQC-SLAVE-REPLY: - -DTV_DISEQC_SLAVE_REPLY -====================== - -Currently not implemented. - - -.. _DTV-FE-CAPABILITY-COUNT: - -DTV_FE_CAPABILITY_COUNT -======================= - -Currently not implemented. - - -.. _DTV-FE-CAPABILITY: - -DTV_FE_CAPABILITY -================= - -Currently not implemented. - - -.. _DTV-DELIVERY-SYSTEM: - -DTV_DELIVERY_SYSTEM -=================== - -Specifies the type of Delivery system - - -.. c:type:: fe_delivery_system - -fe_delivery_system type ------------------------ - -Possible values: - - -.. flat-table:: enum fe_delivery_system - :header-rows: 1 - :stub-columns: 0 - - - - .. row 1 - - - ID - - - Description - - - .. row 2 - - - .. _SYS-UNDEFINED: - - ``SYS_UNDEFINED`` - - - Undefined standard. Generally, indicates an error - - - .. row 3 - - - .. _SYS-DVBC-ANNEX-A: - - ``SYS_DVBC_ANNEX_A`` - - - Cable TV: DVB-C following ITU-T J.83 Annex A spec - - - .. row 4 - - - .. _SYS-DVBC-ANNEX-B: - - ``SYS_DVBC_ANNEX_B`` - - - Cable TV: DVB-C following ITU-T J.83 Annex B spec (ClearQAM) - - - .. row 5 - - - .. _SYS-DVBC-ANNEX-C: - - ``SYS_DVBC_ANNEX_C`` - - - Cable TV: DVB-C following ITU-T J.83 Annex C spec - - - .. row 6 - - - .. _SYS-ISDBC: - - ``SYS_ISDBC`` - - - Cable TV: ISDB-C (no drivers yet) - - - .. row 7 - - - .. _SYS-DVBT: - - ``SYS_DVBT`` - - - Terrestral TV: DVB-T - - - .. row 8 - - - .. _SYS-DVBT2: - - ``SYS_DVBT2`` - - - Terrestral TV: DVB-T2 - - - .. row 9 - - - .. _SYS-ISDBT: - - ``SYS_ISDBT`` - - - Terrestral TV: ISDB-T - - - .. row 10 - - - .. _SYS-ATSC: - - ``SYS_ATSC`` - - - Terrestral TV: ATSC - - - .. row 11 - - - .. _SYS-ATSCMH: - - ``SYS_ATSCMH`` - - - Terrestral TV (mobile): ATSC-M/H - - - .. row 12 - - - .. _SYS-DTMB: - - ``SYS_DTMB`` - - - Terrestrial TV: DTMB - - - .. row 13 - - - .. _SYS-DVBS: - - ``SYS_DVBS`` - - - Satellite TV: DVB-S - - - .. row 14 - - - .. _SYS-DVBS2: - - ``SYS_DVBS2`` - - - Satellite TV: DVB-S2 - - - .. row 15 - - - .. _SYS-TURBO: - - ``SYS_TURBO`` - - - Satellite TV: DVB-S Turbo - - - .. row 16 - - - .. _SYS-ISDBS: - - ``SYS_ISDBS`` - - - Satellite TV: ISDB-S - - - .. row 17 - - - .. _SYS-DAB: - - ``SYS_DAB`` - - - Digital audio: DAB (not fully supported) - - - .. row 18 - - - .. _SYS-DSS: - - ``SYS_DSS`` - - - Satellite TV:"DSS (not fully supported) - - - .. row 19 - - - .. _SYS-CMMB: - - ``SYS_CMMB`` - - - Terrestral TV (mobile):CMMB (not fully supported) - - - .. row 20 - - - .. _SYS-DVBH: - - ``SYS_DVBH`` - - - Terrestral TV (mobile): DVB-H (standard deprecated) - - - -.. _DTV-ISDBT-PARTIAL-RECEPTION: - -DTV_ISDBT_PARTIAL_RECEPTION -=========================== - -If ``DTV_ISDBT_SOUND_BROADCASTING`` is '0' this bit-field represents -whether the channel is in partial reception mode or not. - -If '1' ``DTV_ISDBT_LAYERA_*`` values are assigned to the center segment -and ``DTV_ISDBT_LAYERA_SEGMENT_COUNT`` has to be '1'. - -If in addition ``DTV_ISDBT_SOUND_BROADCASTING`` is '1' -``DTV_ISDBT_PARTIAL_RECEPTION`` represents whether this ISDB-Tsb channel -is consisting of one segment and layer or three segments and two layers. - -Possible values: 0, 1, -1 (AUTO) - - -.. _DTV-ISDBT-SOUND-BROADCASTING: - -DTV_ISDBT_SOUND_BROADCASTING -============================ - -This field represents whether the other DTV_ISDBT_*-parameters are -referring to an ISDB-T and an ISDB-Tsb channel. (See also -``DTV_ISDBT_PARTIAL_RECEPTION``). - -Possible values: 0, 1, -1 (AUTO) - - -.. _DTV-ISDBT-SB-SUBCHANNEL-ID: - -DTV_ISDBT_SB_SUBCHANNEL_ID -========================== - -This field only applies if ``DTV_ISDBT_SOUND_BROADCASTING`` is '1'. - -(Note of the author: This might not be the correct description of the -``SUBCHANNEL-ID`` in all details, but it is my understanding of the -technical background needed to program a device) - -An ISDB-Tsb channel (1 or 3 segments) can be broadcasted alone or in a -set of connected ISDB-Tsb channels. In this set of channels every -channel can be received independently. The number of connected ISDB-Tsb -segment can vary, e.g. depending on the frequency spectrum bandwidth -available. - -Example: Assume 8 ISDB-Tsb connected segments are broadcasted. The -broadcaster has several possibilities to put those channels in the air: -Assuming a normal 13-segment ISDB-T spectrum he can align the 8 segments -from position 1-8 to 5-13 or anything in between. - -The underlying layer of segments are subchannels: each segment is -consisting of several subchannels with a predefined IDs. A sub-channel -is used to help the demodulator to synchronize on the channel. - -An ISDB-T channel is always centered over all sub-channels. As for the -example above, in ISDB-Tsb it is no longer as simple as that. - -``The DTV_ISDBT_SB_SUBCHANNEL_ID`` parameter is used to give the -sub-channel ID of the segment to be demodulated. - -Possible values: 0 .. 41, -1 (AUTO) - - -.. _DTV-ISDBT-SB-SEGMENT-IDX: - -DTV_ISDBT_SB_SEGMENT_IDX -======================== - -This field only applies if ``DTV_ISDBT_SOUND_BROADCASTING`` is '1'. - -``DTV_ISDBT_SB_SEGMENT_IDX`` gives the index of the segment to be -demodulated for an ISDB-Tsb channel where several of them are -transmitted in the connected manner. - -Possible values: 0 .. ``DTV_ISDBT_SB_SEGMENT_COUNT`` - 1 - -Note: This value cannot be determined by an automatic channel search. - - -.. _DTV-ISDBT-SB-SEGMENT-COUNT: - -DTV_ISDBT_SB_SEGMENT_COUNT -========================== - -This field only applies if ``DTV_ISDBT_SOUND_BROADCASTING`` is '1'. - -``DTV_ISDBT_SB_SEGMENT_COUNT`` gives the total count of connected -ISDB-Tsb channels. - -Possible values: 1 .. 13 - -Note: This value cannot be determined by an automatic channel search. - - -.. _isdb-hierq-layers: - -DTV-ISDBT-LAYER[A-C] parameters -=============================== - -ISDB-T channels can be coded hierarchically. As opposed to DVB-T in -ISDB-T hierarchical layers can be decoded simultaneously. For that -reason a ISDB-T demodulator has 3 Viterbi and 3 Reed-Solomon decoders. - -ISDB-T has 3 hierarchical layers which each can use a part of the -available segments. The total number of segments over all layers has to -13 in ISDB-T. - -There are 3 parameter sets, for Layers A, B and C. - - -.. _DTV-ISDBT-LAYER-ENABLED: - -DTV_ISDBT_LAYER_ENABLED ------------------------ - -Hierarchical reception in ISDB-T is achieved by enabling or disabling -layers in the decoding process. Setting all bits of -``DTV_ISDBT_LAYER_ENABLED`` to '1' forces all layers (if applicable) to -be demodulated. This is the default. - -If the channel is in the partial reception mode -(``DTV_ISDBT_PARTIAL_RECEPTION`` = 1) the central segment can be decoded -independently of the other 12 segments. In that mode layer A has to have -a ``SEGMENT_COUNT`` of 1. - -In ISDB-Tsb only layer A is used, it can be 1 or 3 in ISDB-Tsb according -to ``DTV_ISDBT_PARTIAL_RECEPTION``. ``SEGMENT_COUNT`` must be filled -accordingly. - -Only the values of the first 3 bits are used. Other bits will be silently ignored: - -``DTV_ISDBT_LAYER_ENABLED`` bit 0: layer A enabled - -``DTV_ISDBT_LAYER_ENABLED`` bit 1: layer B enabled - -``DTV_ISDBT_LAYER_ENABLED`` bit 2: layer C enabled - -``DTV_ISDBT_LAYER_ENABLED`` bits 3-31: unused - - -.. _DTV-ISDBT-LAYER-FEC: - -DTV_ISDBT_LAYER[A-C]_FEC ------------------------- - -Possible values: ``FEC_AUTO``, ``FEC_1_2``, ``FEC_2_3``, ``FEC_3_4``, -``FEC_5_6``, ``FEC_7_8`` - - -.. _DTV-ISDBT-LAYER-MODULATION: - -DTV_ISDBT_LAYER[A-C]_MODULATION -------------------------------- - -Possible values: ``QAM_AUTO``, QP\ ``SK, QAM_16``, ``QAM_64``, ``DQPSK`` - -Note: If layer C is ``DQPSK`` layer B has to be ``DQPSK``. If layer B is -``DQPSK`` and ``DTV_ISDBT_PARTIAL_RECEPTION``\ =0 layer has to be -``DQPSK``. - - -.. _DTV-ISDBT-LAYER-SEGMENT-COUNT: - -DTV_ISDBT_LAYER[A-C]_SEGMENT_COUNT ----------------------------------- - -Possible values: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, -1 (AUTO) - -Note: Truth table for ``DTV_ISDBT_SOUND_BROADCASTING`` and -``DTV_ISDBT_PARTIAL_RECEPTION`` and ``LAYER[A-C]_SEGMENT_COUNT`` - -.. _isdbt-layer_seg-cnt-table: - -.. flat-table:: Truth table for ISDB-T Sound Broadcasting - :header-rows: 0 - :stub-columns: 0 - - - - .. row 1 - - - PR - - - SB - - - Layer A width - - - Layer B width - - - Layer C width - - - total width - - - .. row 2 - - - 0 - - - 0 - - - 1 .. 13 - - - 1 .. 13 - - - 1 .. 13 - - - 13 - - - .. row 3 - - - 1 - - - 0 - - - 1 - - - 1 .. 13 - - - 1 .. 13 - - - 13 - - - .. row 4 - - - 0 - - - 1 - - - 1 - - - 0 - - - 0 - - - 1 - - - .. row 5 - - - 1 - - - 1 - - - 1 - - - 2 - - - 0 - - - 13 - - - -.. _DTV-ISDBT-LAYER-TIME-INTERLEAVING: - -DTV_ISDBT_LAYER[A-C]_TIME_INTERLEAVING --------------------------------------- - -Valid values: 0, 1, 2, 4, -1 (AUTO) - -when DTV_ISDBT_SOUND_BROADCASTING is active, value 8 is also valid. - -Note: The real time interleaving length depends on the mode (fft-size). -The values here are referring to what can be found in the -TMCC-structure, as shown in the table below. - - -.. c:type:: isdbt_layer_interleaving_table - -.. flat-table:: ISDB-T time interleaving modes - :header-rows: 0 - :stub-columns: 0 - - - - .. row 1 - - - ``DTV_ISDBT_LAYER[A-C]_TIME_INTERLEAVING`` - - - Mode 1 (2K FFT) - - - Mode 2 (4K FFT) - - - Mode 3 (8K FFT) - - - .. row 2 - - - 0 - - - 0 - - - 0 - - - 0 - - - .. row 3 - - - 1 - - - 4 - - - 2 - - - 1 - - - .. row 4 - - - 2 - - - 8 - - - 4 - - - 2 - - - .. row 5 - - - 4 - - - 16 - - - 8 - - - 4 - - - -.. _DTV-ATSCMH-FIC-VER: - -DTV_ATSCMH_FIC_VER ------------------- - -Version number of the FIC (Fast Information Channel) signaling data. - -FIC is used for relaying information to allow rapid service acquisition -by the receiver. - -Possible values: 0, 1, 2, 3, ..., 30, 31 - - -.. _DTV-ATSCMH-PARADE-ID: - -DTV_ATSCMH_PARADE_ID --------------------- - -Parade identification number - -A parade is a collection of up to eight MH groups, conveying one or two -ensembles. - -Possible values: 0, 1, 2, 3, ..., 126, 127 - - -.. _DTV-ATSCMH-NOG: - -DTV_ATSCMH_NOG --------------- - -Number of MH groups per MH subframe for a designated parade. - -Possible values: 1, 2, 3, 4, 5, 6, 7, 8 - - -.. _DTV-ATSCMH-TNOG: - -DTV_ATSCMH_TNOG ---------------- - -Total number of MH groups including all MH groups belonging to all MH -parades in one MH subframe. - -Possible values: 0, 1, 2, 3, ..., 30, 31 - - -.. _DTV-ATSCMH-SGN: - -DTV_ATSCMH_SGN --------------- - -Start group number. - -Possible values: 0, 1, 2, 3, ..., 14, 15 - - -.. _DTV-ATSCMH-PRC: - -DTV_ATSCMH_PRC --------------- - -Parade repetition cycle. - -Possible values: 1, 2, 3, 4, 5, 6, 7, 8 - - -.. _DTV-ATSCMH-RS-FRAME-MODE: - -DTV_ATSCMH_RS_FRAME_MODE ------------------------- - -Reed Solomon (RS) frame mode. - -Possible values are: - -.. tabularcolumns:: |p{5.0cm}|p{12.5cm}| - -.. c:type:: atscmh_rs_frame_mode - -.. flat-table:: enum atscmh_rs_frame_mode - :header-rows: 1 - :stub-columns: 0 - - - - .. row 1 - - - ID - - - Description - - - .. row 2 - - - .. _ATSCMH-RSFRAME-PRI-ONLY: - - ``ATSCMH_RSFRAME_PRI_ONLY`` - - - Single Frame: There is only a primary RS Frame for all Group - Regions. - - - .. row 3 - - - .. _ATSCMH-RSFRAME-PRI-SEC: - - ``ATSCMH_RSFRAME_PRI_SEC`` - - - Dual Frame: There are two separate RS Frames: Primary RS Frame for - Group Region A and B and Secondary RS Frame for Group Region C and - D. - - - -.. _DTV-ATSCMH-RS-FRAME-ENSEMBLE: - -DTV_ATSCMH_RS_FRAME_ENSEMBLE ----------------------------- - -Reed Solomon(RS) frame ensemble. - -Possible values are: - - -.. c:type:: atscmh_rs_frame_ensemble - -.. flat-table:: enum atscmh_rs_frame_ensemble - :header-rows: 1 - :stub-columns: 0 - - - - .. row 1 - - - ID - - - Description - - - .. row 2 - - - .. _ATSCMH-RSFRAME-ENS-PRI: - - ``ATSCMH_RSFRAME_ENS_PRI`` - - - Primary Ensemble. - - - .. row 3 - - - .. _ATSCMH-RSFRAME-ENS-SEC: - - ``AATSCMH_RSFRAME_PRI_SEC`` - - - Secondary Ensemble. - - - .. row 4 - - - .. _ATSCMH-RSFRAME-RES: - - ``AATSCMH_RSFRAME_RES`` - - - Reserved. Shouldn't be used. - - - -.. _DTV-ATSCMH-RS-CODE-MODE-PRI: - -DTV_ATSCMH_RS_CODE_MODE_PRI ---------------------------- - -Reed Solomon (RS) code mode (primary). - -Possible values are: - - -.. c:type:: atscmh_rs_code_mode - -.. flat-table:: enum atscmh_rs_code_mode - :header-rows: 1 - :stub-columns: 0 - - - - .. row 1 - - - ID - - - Description - - - .. row 2 - - - .. _ATSCMH-RSCODE-211-187: - - ``ATSCMH_RSCODE_211_187`` - - - Reed Solomon code (211,187). - - - .. row 3 - - - .. _ATSCMH-RSCODE-223-187: - - ``ATSCMH_RSCODE_223_187`` - - - Reed Solomon code (223,187). - - - .. row 4 - - - .. _ATSCMH-RSCODE-235-187: - - ``ATSCMH_RSCODE_235_187`` - - - Reed Solomon code (235,187). - - - .. row 5 - - - .. _ATSCMH-RSCODE-RES: - - ``ATSCMH_RSCODE_RES`` - - - Reserved. Shouldn't be used. - - - -.. _DTV-ATSCMH-RS-CODE-MODE-SEC: - -DTV_ATSCMH_RS_CODE_MODE_SEC ---------------------------- - -Reed Solomon (RS) code mode (secondary). - -Possible values are the same as documented on enum -:c:type:`atscmh_rs_code_mode`: - - -.. _DTV-ATSCMH-SCCC-BLOCK-MODE: - -DTV_ATSCMH_SCCC_BLOCK_MODE --------------------------- - -Series Concatenated Convolutional Code Block Mode. - -Possible values are: - -.. tabularcolumns:: |p{4.5cm}|p{13.0cm}| - -.. c:type:: atscmh_sccc_block_mode - -.. flat-table:: enum atscmh_scc_block_mode - :header-rows: 1 - :stub-columns: 0 - - - - .. row 1 - - - ID - - - Description - - - .. row 2 - - - .. _ATSCMH-SCCC-BLK-SEP: - - ``ATSCMH_SCCC_BLK_SEP`` - - - Separate SCCC: the SCCC outer code mode shall be set independently - for each Group Region (A, B, C, D) - - - .. row 3 - - - .. _ATSCMH-SCCC-BLK-COMB: - - ``ATSCMH_SCCC_BLK_COMB`` - - - Combined SCCC: all four Regions shall have the same SCCC outer - code mode. +.. _DTV-ISDBT-LAYER-MODULATION: - - .. row 4 +DTV_ISDBT_LAYER[A-C]_MODULATION +------------------------------- - - .. _ATSCMH-SCCC-BLK-RES: +The modulation used by a given ISDB Layer, as defined by +:c:type:`fe_modulation`. - ``ATSCMH_SCCC_BLK_RES`` +Possible values are: ``QAM_AUTO``, ``QPSK``, ``QAM_16``, ``QAM_64``, ``DQPSK`` - - Reserved. Shouldn't be used. +.. note:: + #. If layer C is ``DQPSK``, then layer B has to be ``DQPSK``. + #. If layer B is ``DQPSK`` and ``DTV_ISDBT_PARTIAL_RECEPTION``\ = 0, + then layer has to be ``DQPSK``. -.. _DTV-ATSCMH-SCCC-CODE-MODE-A: -DTV_ATSCMH_SCCC_CODE_MODE_A ---------------------------- +.. _DTV-ISDBT-LAYER-SEGMENT-COUNT: -Series Concatenated Convolutional Code Rate. +DTV_ISDBT_LAYER[A-C]_SEGMENT_COUNT +---------------------------------- -Possible values are: +Possible values: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, -1 (AUTO) +Note: Truth table for ``DTV_ISDBT_SOUND_BROADCASTING`` and +``DTV_ISDBT_PARTIAL_RECEPTION`` and ``LAYER[A-C]_SEGMENT_COUNT`` -.. c:type:: atscmh_sccc_code_mode +.. _isdbt-layer_seg-cnt-table: -.. flat-table:: enum atscmh_sccc_code_mode +.. flat-table:: Truth table for ISDB-T Sound Broadcasting :header-rows: 1 :stub-columns: 0 - .. row 1 - - ID - - - Description - - - .. row 2 - - - .. _ATSCMH-SCCC-CODE-HLF: - - ``ATSCMH_SCCC_CODE_HLF`` - - - The outer code rate of a SCCC Block is 1/2 rate. - - - .. row 3 - - - .. _ATSCMH-SCCC-CODE-QTR: + - Partial Reception - ``ATSCMH_SCCC_CODE_QTR`` + - Sound Broadcasting - - The outer code rate of a SCCC Block is 1/4 rate. + - Layer A width - - .. row 4 + - Layer B width - - .. _ATSCMH-SCCC-CODE-RES: + - Layer C width - ``ATSCMH_SCCC_CODE_RES`` + - total width - - to be documented. + - .. row 2 + - 0 + - 0 -.. _DTV-ATSCMH-SCCC-CODE-MODE-B: + - 1 .. 13 -DTV_ATSCMH_SCCC_CODE_MODE_B ---------------------------- + - 1 .. 13 -Series Concatenated Convolutional Code Rate. + - 1 .. 13 -Possible values are the same as documented on enum -:c:type:`atscmh_sccc_code_mode`. + - 13 + - .. row 3 -.. _DTV-ATSCMH-SCCC-CODE-MODE-C: + - 1 -DTV_ATSCMH_SCCC_CODE_MODE_C ---------------------------- + - 0 -Series Concatenated Convolutional Code Rate. + - 1 -Possible values are the same as documented on enum -:c:type:`atscmh_sccc_code_mode`. + - 1 .. 13 + - 1 .. 13 -.. _DTV-ATSCMH-SCCC-CODE-MODE-D: + - 13 -DTV_ATSCMH_SCCC_CODE_MODE_D ---------------------------- + - .. row 4 -Series Concatenated Convolutional Code Rate. + - 0 -Possible values are the same as documented on enum -:c:type:`atscmh_sccc_code_mode`. + - 1 + - 1 -.. _DTV-API-VERSION: + - 0 -DTV_API_VERSION -=============== + - 0 -Returns the major/minor version of the DVB API + - 1 + - .. row 5 -.. _DTV-CODE-RATE-HP: + - 1 -DTV_CODE_RATE_HP -================ + - 1 -Used on terrestrial transmissions. The acceptable values are the ones -described at :c:type:`fe_transmit_mode`. + - 1 + - 2 -.. _DTV-CODE-RATE-LP: + - 0 -DTV_CODE_RATE_LP -================ + - 13 -Used on terrestrial transmissions. The acceptable values are the ones -described at :c:type:`fe_transmit_mode`. -.. _DTV-GUARD-INTERVAL: +.. _DTV-ISDBT-LAYER-TIME-INTERLEAVING: -DTV_GUARD_INTERVAL -================== +DTV_ISDBT_LAYER[A-C]_TIME_INTERLEAVING +-------------------------------------- -Possible values are: +Valid values: 0, 1, 2, 4, -1 (AUTO) +when DTV_ISDBT_SOUND_BROADCASTING is active, value 8 is also valid. -.. c:type:: fe_guard_interval +Note: The real time interleaving length depends on the mode (fft-size). +The values here are referring to what can be found in the +TMCC-structure, as shown in the table below. -Modulation guard interval -------------------------- +.. c:type:: isdbt_layer_interleaving_table -.. flat-table:: enum fe_guard_interval +.. flat-table:: ISDB-T time interleaving modes :header-rows: 1 :stub-columns: 0 - .. row 1 - - ID - - - Description - - - .. row 2 - - - .. _GUARD-INTERVAL-AUTO: - - ``GUARD_INTERVAL_AUTO`` + - ``DTV_ISDBT_LAYER[A-C]_TIME_INTERLEAVING`` - - Autodetect the guard interval + - Mode 1 (2K FFT) - - .. row 3 + - Mode 2 (4K FFT) - - .. _GUARD-INTERVAL-1-128: + - Mode 3 (8K FFT) - ``GUARD_INTERVAL_1_128`` + - .. row 2 - - Guard interval 1/128 + - 0 - - .. row 4 + - 0 - - .. _GUARD-INTERVAL-1-32: + - 0 - ``GUARD_INTERVAL_1_32`` + - 0 - - Guard interval 1/32 + - .. row 3 - - .. row 5 + - 1 - - .. _GUARD-INTERVAL-1-16: + - 4 - ``GUARD_INTERVAL_1_16`` + - 2 - - Guard interval 1/16 + - 1 - - .. row 6 + - .. row 4 - - .. _GUARD-INTERVAL-1-8: + - 2 - ``GUARD_INTERVAL_1_8`` + - 8 - - Guard interval 1/8 + - 4 - - .. row 7 + - 2 - - .. _GUARD-INTERVAL-1-4: + - .. row 5 - ``GUARD_INTERVAL_1_4`` + - 4 - - Guard interval 1/4 + - 16 - - .. row 8 + - 8 - - .. _GUARD-INTERVAL-19-128: + - 4 - ``GUARD_INTERVAL_19_128`` - - Guard interval 19/128 - - .. row 9 +.. _DTV-ATSCMH-FIC-VER: - - .. _GUARD-INTERVAL-19-256: +DTV_ATSCMH_FIC_VER +------------------ - ``GUARD_INTERVAL_19_256`` +Version number of the FIC (Fast Information Channel) signaling data. - - Guard interval 19/256 +FIC is used for relaying information to allow rapid service acquisition +by the receiver. - - .. row 10 +Possible values: 0, 1, 2, 3, ..., 30, 31 - - .. _GUARD-INTERVAL-PN420: - ``GUARD_INTERVAL_PN420`` +.. _DTV-ATSCMH-PARADE-ID: - - PN length 420 (1/4) +DTV_ATSCMH_PARADE_ID +-------------------- - - .. row 11 +Parade identification number - - .. _GUARD-INTERVAL-PN595: +A parade is a collection of up to eight MH groups, conveying one or two +ensembles. - ``GUARD_INTERVAL_PN595`` +Possible values: 0, 1, 2, 3, ..., 126, 127 - - PN length 595 (1/6) - - .. row 12 +.. _DTV-ATSCMH-NOG: - - .. _GUARD-INTERVAL-PN945: +DTV_ATSCMH_NOG +-------------- - ``GUARD_INTERVAL_PN945`` +Number of MH groups per MH subframe for a designated parade. - - PN length 945 (1/9) +Possible values: 1, 2, 3, 4, 5, 6, 7, 8 -Notes: +.. _DTV-ATSCMH-TNOG: -1) If ``DTV_GUARD_INTERVAL`` is set the ``GUARD_INTERVAL_AUTO`` the -hardware will try to find the correct guard interval (if capable) and -will use TMCC to fill in the missing parameters. +DTV_ATSCMH_TNOG +--------------- -2) Intervals 1/128, 19/128 and 19/256 are used only for DVB-T2 at -present +Total number of MH groups including all MH groups belonging to all MH +parades in one MH subframe. -3) DTMB specifies PN420, PN595 and PN945. +Possible values: 0, 1, 2, 3, ..., 30, 31 -.. _DTV-TRANSMISSION-MODE: +.. _DTV-ATSCMH-SGN: -DTV_TRANSMISSION_MODE -===================== +DTV_ATSCMH_SGN +-------------- -Specifies the number of carriers used by the standard. This is used only -on OFTM-based standards, e. g. DVB-T/T2, ISDB-T, DTMB +Start group number. +Possible values: 0, 1, 2, 3, ..., 14, 15 -.. c:type:: fe_transmit_mode -enum fe_transmit_mode: Number of carriers per channel ------------------------------------------------------ +.. _DTV-ATSCMH-PRC: -.. tabularcolumns:: |p{5.0cm}|p{12.5cm}| +DTV_ATSCMH_PRC +-------------- -.. flat-table:: enum fe_transmit_mode - :header-rows: 1 - :stub-columns: 0 +Parade repetition cycle. +Possible values: 1, 2, 3, 4, 5, 6, 7, 8 - - .. row 1 - - ID +.. _DTV-ATSCMH-RS-FRAME-MODE: - - Description +DTV_ATSCMH_RS_FRAME_MODE +------------------------ - - .. row 2 +Reed Solomon (RS) frame mode. - - .. _TRANSMISSION-MODE-AUTO: +The acceptable values are defined by :c:type:`atscmh_rs_frame_mode`. - ``TRANSMISSION_MODE_AUTO`` - - Autodetect transmission mode. The hardware will try to find the - correct FFT-size (if capable) to fill in the missing parameters. +.. _DTV-ATSCMH-RS-FRAME-ENSEMBLE: - - .. row 3 +DTV_ATSCMH_RS_FRAME_ENSEMBLE +---------------------------- - - .. _TRANSMISSION-MODE-1K: +Reed Solomon(RS) frame ensemble. - ``TRANSMISSION_MODE_1K`` +The acceptable values are defined by :c:type:`atscmh_rs_frame_ensemble`. - - Transmission mode 1K - - .. row 4 +.. _DTV-ATSCMH-RS-CODE-MODE-PRI: - - .. _TRANSMISSION-MODE-2K: +DTV_ATSCMH_RS_CODE_MODE_PRI +--------------------------- - ``TRANSMISSION_MODE_2K`` +Reed Solomon (RS) code mode (primary). - - Transmission mode 2K +The acceptable values are defined by :c:type:`atscmh_rs_code_mode`. - - .. row 5 - - .. _TRANSMISSION-MODE-8K: +.. _DTV-ATSCMH-RS-CODE-MODE-SEC: - ``TRANSMISSION_MODE_8K`` +DTV_ATSCMH_RS_CODE_MODE_SEC +--------------------------- - - Transmission mode 8K +Reed Solomon (RS) code mode (secondary). - - .. row 6 +The acceptable values are defined by :c:type:`atscmh_rs_code_mode`. - - .. _TRANSMISSION-MODE-4K: - ``TRANSMISSION_MODE_4K`` +.. _DTV-ATSCMH-SCCC-BLOCK-MODE: - - Transmission mode 4K +DTV_ATSCMH_SCCC_BLOCK_MODE +-------------------------- - - .. row 7 +Series Concatenated Convolutional Code Block Mode. - - .. _TRANSMISSION-MODE-16K: +The acceptable values are defined by :c:type:`atscmh_sccc_block_mode`. - ``TRANSMISSION_MODE_16K`` - - Transmission mode 16K +.. _DTV-ATSCMH-SCCC-CODE-MODE-A: - - .. row 8 +DTV_ATSCMH_SCCC_CODE_MODE_A +--------------------------- - - .. _TRANSMISSION-MODE-32K: +Series Concatenated Convolutional Code Rate. - ``TRANSMISSION_MODE_32K`` +The acceptable values are defined by :c:type:`atscmh_sccc_code_mode`. - - Transmission mode 32K +.. _DTV-ATSCMH-SCCC-CODE-MODE-B: - - .. row 9 +DTV_ATSCMH_SCCC_CODE_MODE_B +--------------------------- - - .. _TRANSMISSION-MODE-C1: +Series Concatenated Convolutional Code Rate. - ``TRANSMISSION_MODE_C1`` +Possible values are the same as documented on enum +:c:type:`atscmh_sccc_code_mode`. - - Single Carrier (C=1) transmission mode (DTMB) - - .. row 10 +.. _DTV-ATSCMH-SCCC-CODE-MODE-C: - - .. _TRANSMISSION-MODE-C3780: +DTV_ATSCMH_SCCC_CODE_MODE_C +--------------------------- - ``TRANSMISSION_MODE_C3780`` +Series Concatenated Convolutional Code Rate. - - Multi Carrier (C=3780) transmission mode (DTMB) +Possible values are the same as documented on enum +:c:type:`atscmh_sccc_code_mode`. -Notes: +.. _DTV-ATSCMH-SCCC-CODE-MODE-D: -1) ISDB-T supports three carrier/symbol-size: 8K, 4K, 2K. It is called -'mode' in the standard: Mode 1 is 2K, mode 2 is 4K, mode 3 is 8K +DTV_ATSCMH_SCCC_CODE_MODE_D +--------------------------- -2) If ``DTV_TRANSMISSION_MODE`` is set the ``TRANSMISSION_MODE_AUTO`` -the hardware will try to find the correct FFT-size (if capable) and will -use TMCC to fill in the missing parameters. +Series Concatenated Convolutional Code Rate. -3) DVB-T specifies 2K and 8K as valid sizes. +Possible values are the same as documented on enum +:c:type:`atscmh_sccc_code_mode`. -4) DVB-T2 specifies 1K, 2K, 4K, 8K, 16K and 32K. -5) DTMB specifies C1 and C3780. +.. _DTV-API-VERSION: +DTV_API_VERSION +=============== -.. _DTV-HIERARCHY: +Returns the major/minor version of the DVB API -DTV_HIERARCHY -============= -Frontend hierarchy +.. _DTV-CODE-RATE-HP: +DTV_CODE_RATE_HP +================ -.. c:type:: fe_hierarchy +Used on terrestrial transmissions. -Frontend hierarchy ------------------- +The acceptable values are defined by :c:type:`fe_transmit_mode`. -.. flat-table:: enum fe_hierarchy - :header-rows: 1 - :stub-columns: 0 +.. _DTV-CODE-RATE-LP: +DTV_CODE_RATE_LP +================ - - .. row 1 +Used on terrestrial transmissions. - - ID +The acceptable values are defined by :c:type:`fe_transmit_mode`. - - Description - - .. row 2 +.. _DTV-GUARD-INTERVAL: - - .. _HIERARCHY-NONE: +DTV_GUARD_INTERVAL +================== - ``HIERARCHY_NONE`` +The acceptable values are defined by :c:type:`fe_guard_interval`. - - No hierarchy +.. note:: - - .. row 3 + #. If ``DTV_GUARD_INTERVAL`` is set the ``GUARD_INTERVAL_AUTO`` the + hardware will try to find the correct guard interval (if capable) and + will use TMCC to fill in the missing parameters. + #. Intervals ``GUARD_INTERVAL_1_128``, ``GUARD_INTERVAL_19_128`` + and ``GUARD_INTERVAL_19_256`` are used only for DVB-T2 at + present. + #. Intervals ``GUARD_INTERVAL_PN420``, ``GUARD_INTERVAL_PN595`` and + ``GUARD_INTERVAL_PN945`` are used only for DMTB at the present. + On such standard, only those intervals and ``GUARD_INTERVAL_AUTO`` + are valid. - - .. _HIERARCHY-AUTO: +.. _DTV-TRANSMISSION-MODE: - ``HIERARCHY_AUTO`` +DTV_TRANSMISSION_MODE +===================== - - Autodetect hierarchy (if supported) +Specifies the FFT size (with corresponds to the approximate number of +carriers) used by the standard. This is used only on OFTM-based standards, +e. g. DVB-T/T2, ISDB-T, DTMB. - - .. row 4 +The acceptable values are defined by :c:type:`fe_transmit_mode`. - - .. _HIERARCHY-1: +.. note:: - ``HIERARCHY_1`` + #. ISDB-T supports three carrier/symbol-size: 8K, 4K, 2K. It is called + **mode** on such standard, and are numbered from 1 to 3: - - Hierarchy 1 + ==== ======== ======================== + Mode FFT size Transmission mode + ==== ======== ======================== + 1 2K ``TRANSMISSION_MODE_2K`` + 2 4K ``TRANSMISSION_MODE_4K`` + 3 8K ``TRANSMISSION_MODE_8K`` + ==== ======== ======================== - - .. row 5 + #. If ``DTV_TRANSMISSION_MODE`` is set the ``TRANSMISSION_MODE_AUTO`` + the hardware will try to find the correct FFT-size (if capable) and + will use TMCC to fill in the missing parameters. - - .. _HIERARCHY-2: + #. DVB-T specifies 2K and 8K as valid sizes. - ``HIERARCHY_2`` + #. DVB-T2 specifies 1K, 2K, 4K, 8K, 16K and 32K. - - Hierarchy 2 + #. DTMB specifies C1 and C3780. - - .. row 6 - - .. _HIERARCHY-4: +.. _DTV-HIERARCHY: - ``HIERARCHY_4`` +DTV_HIERARCHY +============= - - Hierarchy 4 +Frontend hierarchy. +The acceptable values are defined by :c:type:`fe_hierarchy`. .. _DTV-STREAM-ID: @@ -1884,60 +880,17 @@ with it, rather than trying to use FE_GET_INFO. In the case of a legacy frontend, the result is just the same as with FE_GET_INFO, but in a more structured format +The acceptable values are defined by :c:type:`fe_delivery_system`. + .. _DTV-INTERLEAVING: DTV_INTERLEAVING ================ -Time interleaving to be used. Currently, used only on DTMB. - - -.. c:type:: fe_interleaving - -.. flat-table:: enum fe_interleaving - :header-rows: 1 - :stub-columns: 0 - - - - .. row 1 - - - ID - - - Description - - - .. row 2 - - - .. _INTERLEAVING-NONE: - - ``INTERLEAVING_NONE`` - - - No interleaving. - - - .. row 3 - - - .. _INTERLEAVING-AUTO: - - ``INTERLEAVING_AUTO`` - - - Auto-detect interleaving. - - - .. row 4 - - - .. _INTERLEAVING-240: - - ``INTERLEAVING_240`` - - - Interleaving of 240 symbols. - - - .. row 5 - - - .. _INTERLEAVING-720: - - ``INTERLEAVING_720`` - - - Interleaving of 720 symbols. +Time interleaving to be used. +The acceptable values are defined by :c:type:`fe_interleaving`. .. _DTV-LNA: diff --git a/Documentation/media/uapi/dvb/frontend-header.rst b/Documentation/media/uapi/dvb/frontend-header.rst new file mode 100644 index 000000000000..8d8433cf1e12 --- /dev/null +++ b/Documentation/media/uapi/dvb/frontend-header.rst @@ -0,0 +1,4 @@ +Frontend uAPI data types +======================== + +.. kernel-doc:: include/uapi/linux/dvb/frontend.h diff --git a/include/uapi/linux/dvb/frontend.h b/include/uapi/linux/dvb/frontend.h index 16a318fc469a..e7c29d0bdee4 100644 --- a/include/uapi/linux/dvb/frontend.h +++ b/include/uapi/linux/dvb/frontend.h @@ -562,10 +562,10 @@ enum fe_pilot { }; /** - * enum fe_rolloff - Rolloff factor (also known as alpha) - * @ROLLOFF_35: Roloff factor: 35% - * @ROLLOFF_20: Roloff factor: 20% - * @ROLLOFF_25: Roloff factor: 25% + * enum fe_rolloff - Rolloff factor + * @ROLLOFF_35: Roloff factor: α=35% + * @ROLLOFF_20: Roloff factor: α=20% + * @ROLLOFF_25: Roloff factor: α=25% * @ROLLOFF_AUTO: Auto-detect the roloff factor. * * .. note: -- cgit v1.2.3-71-gd317 From 791edca5685b26d4575e59f5420ba3e206f5cebb Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 31 Aug 2017 12:52:45 -0400 Subject: media: dmx.h: get rid of unused DMX_KERNEL_CLIENT There's a flag defined for Digital TV demux that is not used anywhere, called DMX_KERNEL_CLIENT. Get rid of it. Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/dmx.h.rst.exceptions | 1 - Documentation/media/uapi/dvb/dmx_types.rst | 1 - include/uapi/linux/dvb/dmx.h | 1 - 3 files changed, 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/media/dmx.h.rst.exceptions b/Documentation/media/dmx.h.rst.exceptions index 2fdb458564ba..933ca5a61ce1 100644 --- a/Documentation/media/dmx.h.rst.exceptions +++ b/Documentation/media/dmx.h.rst.exceptions @@ -56,7 +56,6 @@ replace symbol DMX_SOURCE_DVR3 :c:type:`dmx_source` replace define DMX_CHECK_CRC :c:type:`dmx_sct_filter_params` replace define DMX_ONESHOT :c:type:`dmx_sct_filter_params` replace define DMX_IMMEDIATE_START :c:type:`dmx_sct_filter_params` -replace define DMX_KERNEL_CLIENT :c:type:`dmx_sct_filter_params` # some typedefs should point to struct/enums replace typedef dmx_caps_t :c:type:`dmx_caps` diff --git a/Documentation/media/uapi/dvb/dmx_types.rst b/Documentation/media/uapi/dvb/dmx_types.rst index 80dd659860d7..0f0113205c94 100644 --- a/Documentation/media/uapi/dvb/dmx_types.rst +++ b/Documentation/media/uapi/dvb/dmx_types.rst @@ -147,7 +147,6 @@ struct dmx_sct_filter_params #define DMX_CHECK_CRC 1 #define DMX_ONESHOT 2 #define DMX_IMMEDIATE_START 4 - #define DMX_KERNEL_CLIENT 0x8000 }; diff --git a/include/uapi/linux/dvb/dmx.h b/include/uapi/linux/dvb/dmx.h index 1bc4d6fb0f01..1702f923d425 100644 --- a/include/uapi/linux/dvb/dmx.h +++ b/include/uapi/linux/dvb/dmx.h @@ -103,7 +103,6 @@ struct dmx_sct_filter_params #define DMX_CHECK_CRC 1 #define DMX_ONESHOT 2 #define DMX_IMMEDIATE_START 4 -#define DMX_KERNEL_CLIENT 0x8000 }; -- cgit v1.2.3-71-gd317 From 286fe1ca3fa1b6fcc7ce8695b7c8d681e6e1c3b7 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 31 Aug 2017 14:11:34 -0400 Subject: media: dmx.h: get rid of DMX_GET_CAPS There's no driver currently using it; it is also not documented about what it would be supposed to do. So, get rid of it. Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/dmx.h.rst.exceptions | 1 - Documentation/media/uapi/dvb/dmx-get-caps.rst | 41 --------------------------- Documentation/media/uapi/dvb/dmx_fcalls.rst | 1 - Documentation/media/uapi/dvb/dmx_types.rst | 12 -------- include/uapi/linux/dvb/dmx.h | 7 ----- 5 files changed, 62 deletions(-) delete mode 100644 Documentation/media/uapi/dvb/dmx-get-caps.rst (limited to 'include/uapi/linux') diff --git a/Documentation/media/dmx.h.rst.exceptions b/Documentation/media/dmx.h.rst.exceptions index 933ca5a61ce1..5572d2dc9d0e 100644 --- a/Documentation/media/dmx.h.rst.exceptions +++ b/Documentation/media/dmx.h.rst.exceptions @@ -58,7 +58,6 @@ replace define DMX_ONESHOT :c:type:`dmx_sct_filter_params` replace define DMX_IMMEDIATE_START :c:type:`dmx_sct_filter_params` # some typedefs should point to struct/enums -replace typedef dmx_caps_t :c:type:`dmx_caps` replace typedef dmx_filter_t :c:type:`dmx_filter` replace typedef dmx_pes_type_t :c:type:`dmx_pes_type` replace typedef dmx_input_t :c:type:`dmx_input` diff --git a/Documentation/media/uapi/dvb/dmx-get-caps.rst b/Documentation/media/uapi/dvb/dmx-get-caps.rst deleted file mode 100644 index 145fb520d779..000000000000 --- a/Documentation/media/uapi/dvb/dmx-get-caps.rst +++ /dev/null @@ -1,41 +0,0 @@ -.. -*- coding: utf-8; mode: rst -*- - -.. _DMX_GET_CAPS: - -============ -DMX_GET_CAPS -============ - -Name ----- - -DMX_GET_CAPS - - -Synopsis --------- - -.. c:function:: int ioctl(fd, DMX_GET_CAPS, struct dmx_caps *caps) - :name: DMX_GET_CAPS - -Arguments ---------- - -``fd`` - File descriptor returned by :c:func:`open() `. - -``caps`` - Pointer to struct :c:type:`dmx_caps` - - -Description ------------ - -.. note:: This ioctl is undocumented. Documentation is welcome. - -Return Value ------------- - -On success 0 is returned, on error -1 and the ``errno`` variable is set -appropriately. The generic error codes are described at the -:ref:`Generic Error Codes ` chapter. diff --git a/Documentation/media/uapi/dvb/dmx_fcalls.rst b/Documentation/media/uapi/dvb/dmx_fcalls.rst index 77a1554d9834..49e013d4540f 100644 --- a/Documentation/media/uapi/dvb/dmx_fcalls.rst +++ b/Documentation/media/uapi/dvb/dmx_fcalls.rst @@ -21,7 +21,6 @@ Demux Function Calls dmx-get-event dmx-get-stc dmx-get-pes-pids - dmx-get-caps dmx-set-source dmx-add-pid dmx-remove-pid diff --git a/Documentation/media/uapi/dvb/dmx_types.rst b/Documentation/media/uapi/dvb/dmx_types.rst index 0f0113205c94..9e907b85cf16 100644 --- a/Documentation/media/uapi/dvb/dmx_types.rst +++ b/Documentation/media/uapi/dvb/dmx_types.rst @@ -199,18 +199,6 @@ struct dmx_stc }; -struct dmx_caps -=============== - -.. c:type:: dmx_caps - -.. code-block:: c - - typedef struct dmx_caps { - __u32 caps; - int num_decoders; - } dmx_caps_t; - enum dmx_source =============== diff --git a/include/uapi/linux/dvb/dmx.h b/include/uapi/linux/dvb/dmx.h index 1702f923d425..db8bd00c93de 100644 --- a/include/uapi/linux/dvb/dmx.h +++ b/include/uapi/linux/dvb/dmx.h @@ -115,11 +115,6 @@ struct dmx_pes_filter_params __u32 flags; }; -struct dmx_caps { - __u32 caps; - int num_decoders; -}; - enum dmx_source { DMX_SOURCE_FRONT0 = 0, DMX_SOURCE_FRONT1, @@ -143,7 +138,6 @@ struct dmx_stc { #define DMX_SET_PES_FILTER _IOW('o', 44, struct dmx_pes_filter_params) #define DMX_SET_BUFFER_SIZE _IO('o', 45) #define DMX_GET_PES_PIDS _IOR('o', 47, __u16[5]) -#define DMX_GET_CAPS _IOR('o', 48, struct dmx_caps) #define DMX_SET_SOURCE _IOW('o', 49, enum dmx_source) #define DMX_GET_STC _IOWR('o', 50, struct dmx_stc) #define DMX_ADD_PID _IOW('o', 51, __u16) @@ -156,7 +150,6 @@ typedef enum dmx_output dmx_output_t; typedef enum dmx_input dmx_input_t; typedef enum dmx_ts_pes dmx_pes_type_t; typedef struct dmx_filter dmx_filter_t; -typedef struct dmx_caps dmx_caps_t; typedef enum dmx_source dmx_source_t; #endif -- cgit v1.2.3-71-gd317 From 13adefbe9e566c6db91579e4ce17f1e5193d6f2c Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 31 Aug 2017 14:21:43 -0400 Subject: media: dmx.h: get rid of DMX_SET_SOURCE No driver uses this ioctl, nor it is documented anywhere. So, get rid of it. Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/dmx.h.rst.exceptions | 13 -------- Documentation/media/uapi/dvb/dmx-set-source.rst | 44 ------------------------- Documentation/media/uapi/dvb/dmx_fcalls.rst | 1 - Documentation/media/uapi/dvb/dmx_types.rst | 20 ----------- include/uapi/linux/dvb/dmx.h | 12 ------- 5 files changed, 90 deletions(-) delete mode 100644 Documentation/media/uapi/dvb/dmx-set-source.rst (limited to 'include/uapi/linux') diff --git a/Documentation/media/dmx.h.rst.exceptions b/Documentation/media/dmx.h.rst.exceptions index 5572d2dc9d0e..d2dac35bb84b 100644 --- a/Documentation/media/dmx.h.rst.exceptions +++ b/Documentation/media/dmx.h.rst.exceptions @@ -40,18 +40,6 @@ replace enum dmx_input :c:type:`dmx_input` replace symbol DMX_IN_FRONTEND :c:type:`dmx_input` replace symbol DMX_IN_DVR :c:type:`dmx_input` -# dmx_source_t symbols -replace enum dmx_source :c:type:`dmx_source` -replace symbol DMX_SOURCE_FRONT0 :c:type:`dmx_source` -replace symbol DMX_SOURCE_FRONT1 :c:type:`dmx_source` -replace symbol DMX_SOURCE_FRONT2 :c:type:`dmx_source` -replace symbol DMX_SOURCE_FRONT3 :c:type:`dmx_source` -replace symbol DMX_SOURCE_DVR0 :c:type:`dmx_source` -replace symbol DMX_SOURCE_DVR1 :c:type:`dmx_source` -replace symbol DMX_SOURCE_DVR2 :c:type:`dmx_source` -replace symbol DMX_SOURCE_DVR3 :c:type:`dmx_source` - - # Flags for struct dmx_sct_filter_params replace define DMX_CHECK_CRC :c:type:`dmx_sct_filter_params` replace define DMX_ONESHOT :c:type:`dmx_sct_filter_params` @@ -61,4 +49,3 @@ replace define DMX_IMMEDIATE_START :c:type:`dmx_sct_filter_params` replace typedef dmx_filter_t :c:type:`dmx_filter` replace typedef dmx_pes_type_t :c:type:`dmx_pes_type` replace typedef dmx_input_t :c:type:`dmx_input` -replace typedef dmx_source_t :c:type:`dmx_source` diff --git a/Documentation/media/uapi/dvb/dmx-set-source.rst b/Documentation/media/uapi/dvb/dmx-set-source.rst deleted file mode 100644 index ac7f77b25e06..000000000000 --- a/Documentation/media/uapi/dvb/dmx-set-source.rst +++ /dev/null @@ -1,44 +0,0 @@ -.. -*- coding: utf-8; mode: rst -*- - -.. _DMX_SET_SOURCE: - -============== -DMX_SET_SOURCE -============== - -Name ----- - -DMX_SET_SOURCE - - -Synopsis --------- - -.. c:function:: int ioctl(fd, DMX_SET_SOURCE, struct dmx_source *src) - :name: DMX_SET_SOURCE - - -Arguments ---------- - - -``fd`` - File descriptor returned by :c:func:`open() `. - -``src`` - Undocumented. - - -Description ------------ - -.. note:: This ioctl is undocumented. Documentation is welcome. - - -Return Value ------------- - -On success 0 is returned, on error -1 and the ``errno`` variable is set -appropriately. The generic error codes are described at the -:ref:`Generic Error Codes ` chapter. diff --git a/Documentation/media/uapi/dvb/dmx_fcalls.rst b/Documentation/media/uapi/dvb/dmx_fcalls.rst index 49e013d4540f..be98d60877f2 100644 --- a/Documentation/media/uapi/dvb/dmx_fcalls.rst +++ b/Documentation/media/uapi/dvb/dmx_fcalls.rst @@ -21,6 +21,5 @@ Demux Function Calls dmx-get-event dmx-get-stc dmx-get-pes-pids - dmx-set-source dmx-add-pid dmx-remove-pid diff --git a/Documentation/media/uapi/dvb/dmx_types.rst b/Documentation/media/uapi/dvb/dmx_types.rst index 9e907b85cf16..a205c02ccdc1 100644 --- a/Documentation/media/uapi/dvb/dmx_types.rst +++ b/Documentation/media/uapi/dvb/dmx_types.rst @@ -197,23 +197,3 @@ struct dmx_stc unsigned int base; /* output: divisor for stc to get 90 kHz clock */ __u64 stc; /* output: stc in 'base'*90 kHz units */ }; - - - -enum dmx_source -=============== - -.. c:type:: dmx_source - -.. code-block:: c - - typedef enum dmx_source { - DMX_SOURCE_FRONT0 = 0, - DMX_SOURCE_FRONT1, - DMX_SOURCE_FRONT2, - DMX_SOURCE_FRONT3, - DMX_SOURCE_DVR0 = 16, - DMX_SOURCE_DVR1, - DMX_SOURCE_DVR2, - DMX_SOURCE_DVR3 - } dmx_source_t; diff --git a/include/uapi/linux/dvb/dmx.h b/include/uapi/linux/dvb/dmx.h index db8bd00c93de..08dc17060321 100644 --- a/include/uapi/linux/dvb/dmx.h +++ b/include/uapi/linux/dvb/dmx.h @@ -115,16 +115,6 @@ struct dmx_pes_filter_params __u32 flags; }; -enum dmx_source { - DMX_SOURCE_FRONT0 = 0, - DMX_SOURCE_FRONT1, - DMX_SOURCE_FRONT2, - DMX_SOURCE_FRONT3, - DMX_SOURCE_DVR0 = 16, - DMX_SOURCE_DVR1, - DMX_SOURCE_DVR2, - DMX_SOURCE_DVR3 -}; struct dmx_stc { unsigned int num; /* input : which STC? 0..N */ @@ -138,7 +128,6 @@ struct dmx_stc { #define DMX_SET_PES_FILTER _IOW('o', 44, struct dmx_pes_filter_params) #define DMX_SET_BUFFER_SIZE _IO('o', 45) #define DMX_GET_PES_PIDS _IOR('o', 47, __u16[5]) -#define DMX_SET_SOURCE _IOW('o', 49, enum dmx_source) #define DMX_GET_STC _IOWR('o', 50, struct dmx_stc) #define DMX_ADD_PID _IOW('o', 51, __u16) #define DMX_REMOVE_PID _IOW('o', 52, __u16) @@ -150,7 +139,6 @@ typedef enum dmx_output dmx_output_t; typedef enum dmx_input dmx_input_t; typedef enum dmx_ts_pes dmx_pes_type_t; typedef struct dmx_filter dmx_filter_t; -typedef enum dmx_source dmx_source_t; #endif -- cgit v1.2.3-71-gd317 From bb98e6d280e00a1180f47d3391ee0bd1f312b5f6 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 31 Aug 2017 12:28:52 -0400 Subject: media: dmx.h: add kernel-doc markups and use it at Documentation/ The demux documentation is pretty poor nowadays: most of the structs and enums aren't documented at all. Add proper kernel-doc markups for them and use it. Now, the demux API data structures are fully documented :-) Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/dmx.h.rst.exceptions | 5 + Documentation/media/uapi/dvb/dmx_types.rst | 173 +---------------------------- include/uapi/linux/dvb/dmx.h | 139 ++++++++++++++++++----- 3 files changed, 120 insertions(+), 197 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/media/dmx.h.rst.exceptions b/Documentation/media/dmx.h.rst.exceptions index d2dac35bb84b..629db384104a 100644 --- a/Documentation/media/dmx.h.rst.exceptions +++ b/Documentation/media/dmx.h.rst.exceptions @@ -49,3 +49,8 @@ replace define DMX_IMMEDIATE_START :c:type:`dmx_sct_filter_params` replace typedef dmx_filter_t :c:type:`dmx_filter` replace typedef dmx_pes_type_t :c:type:`dmx_pes_type` replace typedef dmx_input_t :c:type:`dmx_input` + +ignore symbol DMX_OUT_DECODER +ignore symbol DMX_OUT_TAP +ignore symbol DMX_OUT_TS_TAP +ignore symbol DMX_OUT_TSDEMUX_TAP diff --git a/Documentation/media/uapi/dvb/dmx_types.rst b/Documentation/media/uapi/dvb/dmx_types.rst index 171205ed86a4..2a023a4f516c 100644 --- a/Documentation/media/uapi/dvb/dmx_types.rst +++ b/Documentation/media/uapi/dvb/dmx_types.rst @@ -6,175 +6,4 @@ Demux Data Types **************** -Output for the demux -==================== - -.. c:type:: dmx_output - -.. tabularcolumns:: |p{5.0cm}|p{12.5cm}| - -.. flat-table:: enum dmx_output - :header-rows: 1 - :stub-columns: 0 - - - - .. row 1 - - - ID - - - Description - - - .. row 2 - - - .. _DMX-OUT-DECODER: - - DMX_OUT_DECODER - - - Streaming directly to decoder. - - - .. row 3 - - - .. _DMX-OUT-TAP: - - DMX_OUT_TAP - - - Output going to a memory buffer (to be retrieved via the read - command). Delivers the stream output to the demux device on which - the ioctl is called. - - - .. row 4 - - - .. _DMX-OUT-TS-TAP: - - DMX_OUT_TS_TAP - - - Output multiplexed into a new TS (to be retrieved by reading from - the logical DVR device). Routes output to the logical DVR device - ``/dev/dvb/adapter?/dvr?``, which delivers a TS multiplexed from - all filters for which ``DMX_OUT_TS_TAP`` was specified. - - - .. row 5 - - - .. _DMX-OUT-TSDEMUX-TAP: - - DMX_OUT_TSDEMUX_TAP - - - Like :ref:`DMX_OUT_TS_TAP ` but retrieved - from the DMX device. - - -dmx_input_t -=========== - -.. c:type:: dmx_input - -.. code-block:: c - - typedef enum - { - DMX_IN_FRONTEND, /* Input from a front-end device. */ - DMX_IN_DVR /* Input from the logical DVR device. */ - } dmx_input_t; - - -dmx_pes_type_t -============== - -.. c:type:: dmx_pes_type - - -.. code-block:: c - - typedef enum - { - DMX_PES_AUDIO0, - DMX_PES_VIDEO0, - DMX_PES_TELETEXT0, - DMX_PES_SUBTITLE0, - DMX_PES_PCR0, - - DMX_PES_AUDIO1, - DMX_PES_VIDEO1, - DMX_PES_TELETEXT1, - DMX_PES_SUBTITLE1, - DMX_PES_PCR1, - - DMX_PES_AUDIO2, - DMX_PES_VIDEO2, - DMX_PES_TELETEXT2, - DMX_PES_SUBTITLE2, - DMX_PES_PCR2, - - DMX_PES_AUDIO3, - DMX_PES_VIDEO3, - DMX_PES_TELETEXT3, - DMX_PES_SUBTITLE3, - DMX_PES_PCR3, - - DMX_PES_OTHER - } dmx_pes_type_t; - - -struct dmx_filter -================= - -.. c:type:: dmx_filter - -.. code-block:: c - - typedef struct dmx_filter - { - __u8 filter[DMX_FILTER_SIZE]; - __u8 mask[DMX_FILTER_SIZE]; - __u8 mode[DMX_FILTER_SIZE]; - } dmx_filter_t; - - -.. c:type:: dmx_sct_filter_params - -struct dmx_sct_filter_params -============================ - - -.. code-block:: c - - struct dmx_sct_filter_params - { - __u16 pid; - dmx_filter_t filter; - __u32 timeout; - __u32 flags; - #define DMX_CHECK_CRC 1 - #define DMX_ONESHOT 2 - #define DMX_IMMEDIATE_START 4 - }; - - -struct dmx_pes_filter_params -============================ - -.. c:type:: dmx_pes_filter_params - -.. code-block:: c - - struct dmx_pes_filter_params - { - __u16 pid; - dmx_input_t input; - dmx_output_t output; - dmx_pes_type_t pes_type; - __u32 flags; - }; - -struct dmx_stc -============== - -.. c:type:: dmx_stc - -.. code-block:: c - - struct dmx_stc { - unsigned int num; /* input : which STC? 0..N */ - unsigned int base; /* output: divisor for stc to get 90 kHz clock */ - __u64 stc; /* output: stc in 'base'*90 kHz units */ - }; +.. kernel-doc:: include/uapi/linux/dvb/dmx.h diff --git a/include/uapi/linux/dvb/dmx.h b/include/uapi/linux/dvb/dmx.h index 08dc17060321..4e3f3a2fe83f 100644 --- a/include/uapi/linux/dvb/dmx.h +++ b/include/uapi/linux/dvb/dmx.h @@ -32,26 +32,74 @@ #define DMX_FILTER_SIZE 16 -enum dmx_output -{ - DMX_OUT_DECODER, /* Streaming directly to decoder. */ - DMX_OUT_TAP, /* Output going to a memory buffer */ - /* (to be retrieved via the read command).*/ - DMX_OUT_TS_TAP, /* Output multiplexed into a new TS */ - /* (to be retrieved by reading from the */ - /* logical DVR device). */ - DMX_OUT_TSDEMUX_TAP /* Like TS_TAP but retrieved from the DMX device */ +/** + * enum dmx_output - Output for the demux. + * + * @DMX_OUT_DECODER: + * Streaming directly to decoder. + * @DMX_OUT_TAP: + * Output going to a memory buffer (to be retrieved via the read command). + * Delivers the stream output to the demux device on which the ioctl + * is called. + * @DMX_OUT_TS_TAP: + * Output multiplexed into a new TS (to be retrieved by reading from the + * logical DVR device). Routes output to the logical DVR device + * ``/dev/dvb/adapter?/dvr?``, which delivers a TS multiplexed from all + * filters for which @DMX_OUT_TS_TAP was specified. + * @DMX_OUT_TSDEMUX_TAP: + * Like @DMX_OUT_TS_TAP but retrieved from the DMX device. + */ +enum dmx_output { + DMX_OUT_DECODER, + DMX_OUT_TAP, + DMX_OUT_TS_TAP, + DMX_OUT_TSDEMUX_TAP }; -enum dmx_input -{ - DMX_IN_FRONTEND, /* Input from a front-end device. */ - DMX_IN_DVR /* Input from the logical DVR device. */ + +/** + * enum dmx_input - Input from the demux. + * + * @DMX_IN_FRONTEND: Input from a front-end device. + * @DMX_IN_DVR: Input from the logical DVR device. + */ +enum dmx_input { + DMX_IN_FRONTEND, + DMX_IN_DVR }; +/** + * enum dmx_ts_pes - type of the PES filter. + * + * @DMX_PES_AUDIO0: first audio PID. Also referred as @DMX_PES_AUDIO. + * @DMX_PES_VIDEO0: first video PID. Also referred as @DMX_PES_VIDEO. + * @DMX_PES_TELETEXT0: first teletext PID. Also referred as @DMX_PES_TELETEXT. + * @DMX_PES_SUBTITLE0: first subtitle PID. Also referred as @DMX_PES_SUBTITLE. + * @DMX_PES_PCR0: first Program Clock Reference PID. + * Also referred as @DMX_PES_PCR. + * + * @DMX_PES_AUDIO1: second audio PID. + * @DMX_PES_VIDEO1: second video PID. + * @DMX_PES_TELETEXT1: second teletext PID. + * @DMX_PES_SUBTITLE1: second subtitle PID. + * @DMX_PES_PCR1: second Program Clock Reference PID. + * + * @DMX_PES_AUDIO2: third audio PID. + * @DMX_PES_VIDEO2: third video PID. + * @DMX_PES_TELETEXT2: third teletext PID. + * @DMX_PES_SUBTITLE2: third subtitle PID. + * @DMX_PES_PCR2: third Program Clock Reference PID. + * + * @DMX_PES_AUDIO3: fourth audio PID. + * @DMX_PES_VIDEO3: fourth video PID. + * @DMX_PES_TELETEXT3: fourth teletext PID. + * @DMX_PES_SUBTITLE3: fourth subtitle PID. + * @DMX_PES_PCR3: fourth Program Clock Reference PID. + * + * @DMX_PES_OTHER: any other PID. + */ -enum dmx_ts_pes -{ +enum dmx_ts_pes { DMX_PES_AUDIO0, DMX_PES_VIDEO0, DMX_PES_TELETEXT0, @@ -86,16 +134,42 @@ enum dmx_ts_pes #define DMX_PES_PCR DMX_PES_PCR0 -struct dmx_filter -{ + +/** + * struct dmx_filter - Specifies a section header filter. + * + * @filter: bit array with bits to be matched at the section header. + * @mask: bits that are valid at the filter bit array. + * @mode: mode of match: if bit is zero, it will match if equal (positive + * match); if bit is one, it will match if the bit is negated. + * + * Note: All arrays in this struct have a size of DMX_FILTER_SIZE (16 bytes). + */ +struct dmx_filter { __u8 filter[DMX_FILTER_SIZE]; __u8 mask[DMX_FILTER_SIZE]; __u8 mode[DMX_FILTER_SIZE]; }; - -struct dmx_sct_filter_params -{ +/** + * struct dmx_sct_filter_params - Specifies a section filter. + * + * @pid: PID to be filtered. + * @filter: section header filter, as defined by &struct dmx_filter. + * @timeout: maximum time to filter, in milliseconds. + * @flags: extra flags for the section filter. + * + * Carries the configuration for a MPEG-TS section filter. + * + * The @flags can be: + * + * - %DMX_CHECK_CRC - only deliver sections where the CRC check succeeded; + * - %DMX_ONESHOT - disable the section filter after one section + * has been delivered; + * - %DMX_IMMEDIATE_START - Start filter immediately without requiring a + * :ref:`DMX_START`. + */ +struct dmx_sct_filter_params { __u16 pid; struct dmx_filter filter; __u32 timeout; @@ -105,7 +179,16 @@ struct dmx_sct_filter_params #define DMX_IMMEDIATE_START 4 }; - +/** + * struct dmx_pes_filter_params - Specifies Packetized Elementary Stream (PES) + * filter parameters. + * + * @pid: PID to be filtered. + * @input: Demux input, as specified by &enum dmx_input. + * @output: Demux output, as specified by &enum dmx_output. + * @pes_type: Type of the pes filter, as specified by &enum dmx_pes_type. + * @flags: Demux PES flags. + */ struct dmx_pes_filter_params { __u16 pid; @@ -115,11 +198,17 @@ struct dmx_pes_filter_params __u32 flags; }; - +/** + * struct dmx_stc - Stores System Time Counter (STC) information. + * + * @num: input data: number of the STC, from 0 to N. + * @base: output: divisor for STC to get 90 kHz clock. + * @stc: output: stc in @base * 90 kHz units. + */ struct dmx_stc { - unsigned int num; /* input : which STC? 0..N */ - unsigned int base; /* output: divisor for stc to get 90 kHz clock */ - __u64 stc; /* output: stc in 'base'*90 kHz units */ + unsigned int num; + unsigned int base; + __u64 stc; }; #define DMX_START _IO('o', 41) -- cgit v1.2.3-71-gd317 From 833ff5e7feda1a042b83e82208cef3d212ca0ef1 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 1 Sep 2017 07:41:49 -0400 Subject: media: ca.h: get rid of CA_SET_PID This ioctl seems to be some attempt to support a feature at the bt8xx dst_ca driver. Yet, as said there, it "needs more work". Right now, the code there is just a boilerplate. At the end of the day, no driver uses this ioctl, nor it is documented anywhere (except for "needs more work"). So, get rid of it. Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/ca.h.rst.exceptions | 1 - Documentation/media/dvb-drivers/ci.rst | 1 - Documentation/media/uapi/dvb/ca-set-pid.rst | 60 ---------------------- Documentation/media/uapi/dvb/ca_data_types.rst | 14 ----- Documentation/media/uapi/dvb/ca_function_calls.rst | 1 - drivers/media/pci/bt8xx/dst_ca.c | 16 ------ include/uapi/linux/dvb/ca.h | 7 --- 7 files changed, 100 deletions(-) delete mode 100644 Documentation/media/uapi/dvb/ca-set-pid.rst (limited to 'include/uapi/linux') diff --git a/Documentation/media/ca.h.rst.exceptions b/Documentation/media/ca.h.rst.exceptions index d7c9fed8c004..553559cc6ad7 100644 --- a/Documentation/media/ca.h.rst.exceptions +++ b/Documentation/media/ca.h.rst.exceptions @@ -16,7 +16,6 @@ replace define CA_NDS :c:type:`ca_descr_info` replace define CA_DSS :c:type:`ca_descr_info` # some typedefs should point to struct/enums -replace typedef ca_pid_t :c:type:`ca_pid` replace typedef ca_slot_info_t :c:type:`ca_slot_info` replace typedef ca_descr_info_t :c:type:`ca_descr_info` replace typedef ca_caps_t :c:type:`ca_caps` diff --git a/Documentation/media/dvb-drivers/ci.rst b/Documentation/media/dvb-drivers/ci.rst index 69b07e9d1816..87f3748c49b9 100644 --- a/Documentation/media/dvb-drivers/ci.rst +++ b/Documentation/media/dvb-drivers/ci.rst @@ -143,7 +143,6 @@ All these ioctls are also valid for the High level CI interface #define CA_GET_MSG _IOR('o', 132, ca_msg_t) #define CA_SEND_MSG _IOW('o', 133, ca_msg_t) #define CA_SET_DESCR _IOW('o', 134, ca_descr_t) -#define CA_SET_PID _IOW('o', 135, ca_pid_t) On querying the device, the device yields information thus: diff --git a/Documentation/media/uapi/dvb/ca-set-pid.rst b/Documentation/media/uapi/dvb/ca-set-pid.rst deleted file mode 100644 index 891c1c72ef24..000000000000 --- a/Documentation/media/uapi/dvb/ca-set-pid.rst +++ /dev/null @@ -1,60 +0,0 @@ -.. -*- coding: utf-8; mode: rst -*- - -.. _CA_SET_PID: - -========== -CA_SET_PID -========== - -Name ----- - -CA_SET_PID - - -Synopsis --------- - -.. c:function:: int ioctl(fd, CA_SET_PID, struct ca_pid *pid) - :name: CA_SET_PID - - -Arguments ---------- - -``fd`` - File descriptor returned by a previous call to :c:func:`open() `. - -``pid`` - Pointer to struct :c:type:`ca_pid`. - -.. c:type:: ca_pid - -.. flat-table:: struct ca_pid - :header-rows: 1 - :stub-columns: 0 - - - - - unsigned int - - pid - - Program ID - - - - - int - - index - - PID index. Use -1 to disable. - - - -Description ------------ - -.. note:: This ioctl is undocumented. Documentation is welcome. - - -Return Value ------------- - -On success 0 is returned, on error -1 and the ``errno`` variable is set -appropriately. The generic error codes are described at the -:ref:`Generic Error Codes ` chapter. diff --git a/Documentation/media/uapi/dvb/ca_data_types.rst b/Documentation/media/uapi/dvb/ca_data_types.rst index d9e27c77426c..555b5137936b 100644 --- a/Documentation/media/uapi/dvb/ca_data_types.rst +++ b/Documentation/media/uapi/dvb/ca_data_types.rst @@ -94,17 +94,3 @@ ca_descr_t unsigned int parity; unsigned char cw[8]; } ca_descr_t; - - -.. c:type:: ca_pid - -ca-pid -====== - - -.. code-block:: c - - typedef struct ca_pid { - unsigned int pid; - int index; /* -1 == disable*/ - } ca_pid_t; diff --git a/Documentation/media/uapi/dvb/ca_function_calls.rst b/Documentation/media/uapi/dvb/ca_function_calls.rst index c085a0ebbc05..87d697851e82 100644 --- a/Documentation/media/uapi/dvb/ca_function_calls.rst +++ b/Documentation/media/uapi/dvb/ca_function_calls.rst @@ -18,4 +18,3 @@ CA Function Calls ca-get-msg ca-send-msg ca-set-descr - ca-set-pid diff --git a/drivers/media/pci/bt8xx/dst_ca.c b/drivers/media/pci/bt8xx/dst_ca.c index 90f4263452d3..7db47d8bbe15 100644 --- a/drivers/media/pci/bt8xx/dst_ca.c +++ b/drivers/media/pci/bt8xx/dst_ca.c @@ -64,13 +64,6 @@ static int ca_set_slot_descr(void) return -EOPNOTSUPP; } -/* Need some more work */ -static int ca_set_pid(void) -{ - /* We could make this more graceful ? */ - return -EOPNOTSUPP; -} - static void put_command_and_length(u8 *data, int command, int length) { data[0] = (command >> 16) & 0xff; @@ -629,15 +622,6 @@ static long dst_ca_ioctl(struct file *file, unsigned int cmd, unsigned long ioct } dprintk(verbose, DST_CA_INFO, 1, " -->CA_SET_DESCR Success !"); break; - case CA_SET_PID: - dprintk(verbose, DST_CA_INFO, 1, " Setting PID"); - if ((ca_set_pid()) < 0) { - dprintk(verbose, DST_CA_ERROR, 1, " -->CA_SET_PID Failed !"); - result = -1; - goto free_mem_and_exit; - } - dprintk(verbose, DST_CA_INFO, 1, " -->CA_SET_PID Success !"); - break; default: result = -EOPNOTSUPP; } diff --git a/include/uapi/linux/dvb/ca.h b/include/uapi/linux/dvb/ca.h index 00cf24587bea..859f6c0c4751 100644 --- a/include/uapi/linux/dvb/ca.h +++ b/include/uapi/linux/dvb/ca.h @@ -73,11 +73,6 @@ struct ca_descr { unsigned char cw[8]; }; -struct ca_pid { - unsigned int pid; - int index; /* -1 == disable*/ -}; - #define CA_RESET _IO('o', 128) #define CA_GET_CAP _IOR('o', 129, struct ca_caps) #define CA_GET_SLOT_INFO _IOR('o', 130, struct ca_slot_info) @@ -85,7 +80,6 @@ struct ca_pid { #define CA_GET_MSG _IOR('o', 132, struct ca_msg) #define CA_SEND_MSG _IOW('o', 133, struct ca_msg) #define CA_SET_DESCR _IOW('o', 134, struct ca_descr) -#define CA_SET_PID _IOW('o', 135, struct ca_pid) #if !defined (__KERNEL__) @@ -95,7 +89,6 @@ typedef struct ca_descr_info ca_descr_info_t; typedef struct ca_caps ca_caps_t; typedef struct ca_msg ca_msg_t; typedef struct ca_descr ca_descr_t; -typedef struct ca_pid ca_pid_t; #endif -- cgit v1.2.3-71-gd317 From fed7c4fe8bd0b131cc3f19ba2744061935cdcdb7 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 1 Sep 2017 07:48:02 -0400 Subject: media: ca.h: document most CA data types For most of the stuff there, documenting is easy, as the header file contains information. Yet, I was unable to document two data structs: ca_msg and ca_descr As those two structs are used by a few drivers, keep them. Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/dvb/ca_data_types.rst | 75 ++++--------------------- include/uapi/linux/dvb/ca.h | 78 ++++++++++++++++++++------ 2 files changed, 70 insertions(+), 83 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/media/uapi/dvb/ca_data_types.rst b/Documentation/media/uapi/dvb/ca_data_types.rst index 555b5137936b..aa57dd176825 100644 --- a/Documentation/media/uapi/dvb/ca_data_types.rst +++ b/Documentation/media/uapi/dvb/ca_data_types.rst @@ -6,91 +6,36 @@ CA Data Types ************* +.. kernel-doc:: include/uapi/linux/dvb/ca.h -.. c:type:: ca_slot_info - -ca_slot_info_t -============== - - -.. code-block:: c - - typedef struct ca_slot_info { - int num; /* slot number */ - - int type; /* CA interface this slot supports */ - #define CA_CI 1 /* CI high level interface */ - #define CA_CI_LINK 2 /* CI link layer level interface */ - #define CA_CI_PHYS 4 /* CI physical layer level interface */ - #define CA_DESCR 8 /* built-in descrambler */ - #define CA_SC 128 /* simple smart card interface */ - - unsigned int flags; - #define CA_CI_MODULE_PRESENT 1 /* module (or card) inserted */ - #define CA_CI_MODULE_READY 2 - } ca_slot_info_t; - - -.. c:type:: ca_descr_info - -ca_descr_info_t -=============== - - -.. code-block:: c - - typedef struct ca_descr_info { - unsigned int num; /* number of available descramblers (keys) */ - unsigned int type; /* type of supported scrambling system */ - #define CA_ECD 1 - #define CA_NDS 2 - #define CA_DSS 4 - } ca_descr_info_t; - - -.. c:type:: ca_caps - -ca_caps_t -========= - +.. c:type:: ca_msg -.. code-block:: c +Undocumented data types +======================= - typedef struct ca_caps { - unsigned int slot_num; /* total number of CA card and module slots */ - unsigned int slot_type; /* OR of all supported types */ - unsigned int descr_num; /* total number of descrambler slots (keys) */ - unsigned int descr_type;/* OR of all supported types */ - } ca_cap_t; +.. note:: + Those data types are undocumented. Documentation is welcome. .. c:type:: ca_msg -ca_msg_t -======== - - .. code-block:: c /* a message to/from a CI-CAM */ - typedef struct ca_msg { + struct ca_msg { unsigned int index; unsigned int type; unsigned int length; unsigned char msg[256]; - } ca_msg_t; + }; .. c:type:: ca_descr -ca_descr_t -========== - - .. code-block:: c - typedef struct ca_descr { + struct ca_descr { unsigned int index; unsigned int parity; unsigned char cw[8]; - } ca_descr_t; + }; diff --git a/include/uapi/linux/dvb/ca.h b/include/uapi/linux/dvb/ca.h index 859f6c0c4751..7ee641b4124c 100644 --- a/include/uapi/linux/dvb/ca.h +++ b/include/uapi/linux/dvb/ca.h @@ -24,39 +24,81 @@ #ifndef _DVBCA_H_ #define _DVBCA_H_ -/* slot interface types and info */ +/** + * struct ca_slot_info - CA slot interface types and info. + * + * @num: slot number. + * @type: slot type. + * @flags: flags applicable to the slot. + * + * This struct stores the CA slot information. + * + * @type can be: + * + * - %CA_CI - CI high level interface; + * - %CA_CI_LINK - CI link layer level interface; + * - %CA_CI_PHYS - CI physical layer level interface; + * - %CA_DESCR - built-in descrambler; + * - %CA_SC -simple smart card interface. + * + * @flags can be: + * + * - %CA_CI_MODULE_PRESENT - module (or card) inserted; + * - %CA_CI_MODULE_READY - module is ready for usage. + */ struct ca_slot_info { - int num; /* slot number */ - - int type; /* CA interface this slot supports */ -#define CA_CI 1 /* CI high level interface */ -#define CA_CI_LINK 2 /* CI link layer level interface */ -#define CA_CI_PHYS 4 /* CI physical layer level interface */ -#define CA_DESCR 8 /* built-in descrambler */ -#define CA_SC 128 /* simple smart card interface */ + int num; + int type; +#define CA_CI 1 +#define CA_CI_LINK 2 +#define CA_CI_PHYS 4 +#define CA_DESCR 8 +#define CA_SC 128 unsigned int flags; -#define CA_CI_MODULE_PRESENT 1 /* module (or card) inserted */ +#define CA_CI_MODULE_PRESENT 1 #define CA_CI_MODULE_READY 2 }; -/* descrambler types and info */ - +/** + * struct ca_descr_info - descrambler types and info. + * + * @num: number of available descramblers (keys). + * @type: type of supported scrambling system. + * + * Identifies the number of descramblers and their type. + * + * @type can be: + * + * - %CA_ECD - European Common Descrambler (ECD) hardware; + * - %CA_NDS - Videoguard (NDS) hardware; + * - %CA_DSS - Distributed Sample Scrambling (DSS) hardware. + */ struct ca_descr_info { - unsigned int num; /* number of available descramblers (keys) */ - unsigned int type; /* type of supported scrambling system */ + unsigned int num; + unsigned int type; #define CA_ECD 1 #define CA_NDS 2 #define CA_DSS 4 }; +/** + * struct ca_caps - CA slot interface capabilities. + * + * @slot_num: total number of CA card and module slots. + * @slot_type: bitmap with all supported types as defined at + * &struct ca_slot_info (e. g. %CA_CI, %CA_CI_LINK, etc). + * @descr_num: total number of descrambler slots (keys) + * @descr_type: bitmap with all supported types as defined at + * &struct ca_descr_info (e. g. %CA_ECD, %CA_NDS, etc). + */ struct ca_caps { - unsigned int slot_num; /* total number of CA card and module slots */ - unsigned int slot_type; /* OR of all supported types */ - unsigned int descr_num; /* total number of descrambler slots (keys) */ - unsigned int descr_type; /* OR of all supported types */ + unsigned int slot_num; + unsigned int slot_type; + unsigned int descr_num; + unsigned int descr_type; }; /* a message to/from a CI-CAM */ -- cgit v1.2.3-71-gd317 From 5176d6eefd5d58fbb787f96c2140cffb2e826b17 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 1 Sep 2017 15:05:28 -0400 Subject: media: frontend.h: Avoid the term DVB when doesn't refer to a delivery system The DVB term can either refer to the subsystem or to a delivery system. Avoid it in the first case at the kernel-doc markups. Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/dvb/frontend.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/dvb/frontend.h b/include/uapi/linux/dvb/frontend.h index e7c29d0bdee4..fc2edb6014fe 100644 --- a/include/uapi/linux/dvb/frontend.h +++ b/include/uapi/linux/dvb/frontend.h @@ -239,11 +239,11 @@ enum fe_sec_mini_cmd { * @FE_NONE: The frontend doesn't have any kind of lock. * That's the initial frontend status * @FE_HAS_SIGNAL: Has found something above the noise level. - * @FE_HAS_CARRIER: Has found a DVB signal. + * @FE_HAS_CARRIER: Has found a signal. * @FE_HAS_VITERBI: FEC inner coding (Viterbi, LDPC or other inner code). * is stable. * @FE_HAS_SYNC: Synchronization bytes was found. - * @FE_HAS_LOCK: DVB were locked and everything is working. + * @FE_HAS_LOCK: Digital TV were locked and everything is working. * @FE_TIMEDOUT: Fo lock within the last about 2 seconds. * @FE_REINIT: Frontend was reinitialized, application is recommended * to reset DiSEqC, tone and parameters. @@ -269,7 +269,7 @@ enum fe_status { * This parameter indicates if spectral inversion should be presumed or * not. In the automatic setting (``INVERSION_AUTO``) the hardware will try * to figure out the correct setting by itself. If the hardware doesn't - * support, the DVB core will try to lock at the carrier first with + * support, the %dvb_frontend will try to lock at the carrier first with * inversion off. If it fails, it will try to enable inversion. */ enum fe_spectral_inversion { -- cgit v1.2.3-71-gd317 From 56d51b65bcc7a5780663abd579fb6f039616b347 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 1 Sep 2017 15:45:47 -0400 Subject: media: net.h: add kernel-doc and use it at Documentation/ As we did with frontend.h, ca.h and dmx.h, move the struct definition to net.h. That should help to keep it updated, as more stuff gets added there. Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/dvb/net-add-if.rst | 34 ----------------------------- Documentation/media/uapi/dvb/net-types.rst | 9 ++++++++ Documentation/media/uapi/dvb/net.rst | 1 + include/uapi/linux/dvb/net.h | 15 +++++++++++++ 4 files changed, 25 insertions(+), 34 deletions(-) create mode 100644 Documentation/media/uapi/dvb/net-types.rst (limited to 'include/uapi/linux') diff --git a/Documentation/media/uapi/dvb/net-add-if.rst b/Documentation/media/uapi/dvb/net-add-if.rst index 1087efb9baa0..6749b70246c5 100644 --- a/Documentation/media/uapi/dvb/net-add-if.rst +++ b/Documentation/media/uapi/dvb/net-add-if.rst @@ -41,40 +41,6 @@ created. The struct :c:type:`dvb_net_if`::ifnum field will be filled with the number of the created interface. -.. c:type:: dvb_net_if - -.. flat-table:: struct dvb_net_if - :header-rows: 1 - :stub-columns: 0 - - - - .. row 1 - - - ID - - - Description - - - .. row 2 - - - pid - - - Packet ID (PID) of the MPEG-TS that contains data - - - .. row 3 - - - ifnum - - - number of the Digital TV interface. - - - .. row 4 - - - feedtype - - - Encapsulation type of the feed. It can be: - ``DVB_NET_FEEDTYPE_MPE`` for MPE encoding or - ``DVB_NET_FEEDTYPE_ULE`` for ULE encoding. - - Return Value ============ diff --git a/Documentation/media/uapi/dvb/net-types.rst b/Documentation/media/uapi/dvb/net-types.rst new file mode 100644 index 000000000000..e1177bdcd623 --- /dev/null +++ b/Documentation/media/uapi/dvb/net-types.rst @@ -0,0 +1,9 @@ +.. -*- coding: utf-8; mode: rst -*- + +.. _dmx_types: + +************** +Net Data Types +************** + +.. kernel-doc:: include/uapi/linux/dvb/net.h diff --git a/Documentation/media/uapi/dvb/net.rst b/Documentation/media/uapi/dvb/net.rst index fdb5301a4b1f..e0cd4e402627 100644 --- a/Documentation/media/uapi/dvb/net.rst +++ b/Documentation/media/uapi/dvb/net.rst @@ -35,6 +35,7 @@ Digital TV net Function Calls .. toctree:: :maxdepth: 1 + net-types net-add-if net-remove-if net-get-if diff --git a/include/uapi/linux/dvb/net.h b/include/uapi/linux/dvb/net.h index f451e7eb0b0b..89d805f9a5a6 100644 --- a/include/uapi/linux/dvb/net.h +++ b/include/uapi/linux/dvb/net.h @@ -26,6 +26,21 @@ #include +/** + * struct dvb_net_if - describes a DVB network interface + * + * @pid: Packet ID (PID) of the MPEG-TS that contains data + * @if_num: number of the Digital TV interface. + * @feedtype: Encapsulation type of the feed. + * + * A MPEG-TS stream may contain packet IDs with IP packages on it. + * This struct describes it, and the type of encoding. + * + * @feedtype can be: + * + * - %DVB_NET_FEEDTYPE_MPE for MPE encoding + * - %DVB_NET_FEEDTYPE_ULE for ULE encoding. + */ struct dvb_net_if { __u16 pid; __u16 if_num; -- cgit v1.2.3-71-gd317 From bd9049edc66e13e868f819c39844f60443e70817 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sun, 3 Sep 2017 20:50:17 -0400 Subject: media: ca docs: document CA_SET_DESCR ioctl and structs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The av7110 driver uses CA_SET_DESCR to store the descrambler control words at the CA descrambler slots. Document it. Thanks-to: Honza Petrouš Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/dvb/ca-set-descr.rst | 15 ++------------- include/uapi/linux/dvb/ca.h | 9 ++++++++- 2 files changed, 10 insertions(+), 14 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/media/uapi/dvb/ca-set-descr.rst b/Documentation/media/uapi/dvb/ca-set-descr.rst index 9c484317d55c..a6c47205ffd8 100644 --- a/Documentation/media/uapi/dvb/ca-set-descr.rst +++ b/Documentation/media/uapi/dvb/ca-set-descr.rst @@ -28,22 +28,11 @@ Arguments ``msg`` Pointer to struct :c:type:`ca_descr`. -.. c:type:: ca_descr - -.. code-block:: c - - struct ca_descr { - unsigned int index; - unsigned int parity; - unsigned char cw[8]; - }; - - Description ----------- -.. note:: This ioctl is undocumented. Documentation is welcome. - +CA_SET_DESCR is used for feeding descrambler CA slots with descrambling +keys (refered as control words). Return Value ------------ diff --git a/include/uapi/linux/dvb/ca.h b/include/uapi/linux/dvb/ca.h index 7ee641b4124c..c36fdb8e2733 100644 --- a/include/uapi/linux/dvb/ca.h +++ b/include/uapi/linux/dvb/ca.h @@ -109,9 +109,16 @@ struct ca_msg { unsigned char msg[256]; }; +/** + * struct ca_descr - CA descrambler control words info + * + * @index: CA Descrambler slot + * @parity: control words parity, where 0 means even and 1 means odd + * @cw: CA Descrambler control words + */ struct ca_descr { unsigned int index; - unsigned int parity; /* 0 == even, 1 == odd */ + unsigned int parity; unsigned char cw[8]; }; -- cgit v1.2.3-71-gd317 From 7e6854a9bfea9ed6553acd0204da5101c9a2e6a0 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 4 Sep 2017 08:03:40 -0400 Subject: media: ca.h: document ca_msg and the corresponding ioctls Usually, CA messages are sent/received via reading/writing at the CA device node. However, two drivers (dst_ca and firedtv-ci) also implement it via ioctls. Apparently, on both cases, the net result is the same. Anyway, let's document it. Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/dvb/ca-get-msg.rst | 19 ++++++------------- Documentation/media/uapi/dvb/ca-send-msg.rst | 6 +++++- include/uapi/linux/dvb/ca.h | 11 ++++++++++- 3 files changed, 21 insertions(+), 15 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/media/uapi/dvb/ca-get-msg.rst b/Documentation/media/uapi/dvb/ca-get-msg.rst index bdb116552068..ceeda623ce93 100644 --- a/Documentation/media/uapi/dvb/ca-get-msg.rst +++ b/Documentation/media/uapi/dvb/ca-get-msg.rst @@ -28,22 +28,15 @@ Arguments ``msg`` Pointer to struct :c:type:`ca_msg`. -.. c:type:: ca_msg - -.. code-block:: c - - /* a message to/from a CI-CAM */ - struct ca_msg { - unsigned int index; - unsigned int type; - unsigned int length; - unsigned char msg[256]; - }; - Description ----------- -.. note:: This ioctl is undocumented. Documentation is welcome. +Receives a message via a CI CA module. + +.. note:: + + Please notice that, on most drivers, this is done by reading from + the /dev/adapter?/ca? device node. Return Value diff --git a/Documentation/media/uapi/dvb/ca-send-msg.rst b/Documentation/media/uapi/dvb/ca-send-msg.rst index 644b6bda1aea..9e91287b7bbc 100644 --- a/Documentation/media/uapi/dvb/ca-send-msg.rst +++ b/Documentation/media/uapi/dvb/ca-send-msg.rst @@ -32,8 +32,12 @@ Arguments Description ----------- -.. note:: This ioctl is undocumented. Documentation is welcome. +Sends a message via a CI CA module. +.. note:: + + Please notice that, on most drivers, this is done by writing + to the /dev/adapter?/ca? device node. Return Value ------------ diff --git a/include/uapi/linux/dvb/ca.h b/include/uapi/linux/dvb/ca.h index c36fdb8e2733..24fc38efbc2b 100644 --- a/include/uapi/linux/dvb/ca.h +++ b/include/uapi/linux/dvb/ca.h @@ -101,7 +101,16 @@ struct ca_caps { unsigned int descr_type; }; -/* a message to/from a CI-CAM */ +/** + * struct ca_msg - a message to/from a CI-CAM + * + * @index: unused + * @type: unused + * @length: length of the message + * @msg: message + * + * This struct carries a message to be send/received from a CI CA module. + */ struct ca_msg { unsigned int index; unsigned int type; -- cgit v1.2.3-71-gd317 From e4faa09b0dae4f8f429922190e9aa99a564ff785 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 5 Sep 2017 07:02:44 -0400 Subject: media: dvb headers: make checkpatch happier Adjust dvb ca.h, dmx.h and frontend.h in order to make checkpatch happier. Now, it only complains about the typedefs, and those are there just to provide backward userspace compatibility. Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/dvb/ca.h | 2 +- include/uapi/linux/dvb/dmx.h | 5 ++--- include/uapi/linux/dvb/frontend.h | 6 +++--- 3 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/dvb/ca.h b/include/uapi/linux/dvb/ca.h index 24fc38efbc2b..cb150029fdff 100644 --- a/include/uapi/linux/dvb/ca.h +++ b/include/uapi/linux/dvb/ca.h @@ -139,7 +139,7 @@ struct ca_descr { #define CA_SEND_MSG _IOW('o', 133, struct ca_msg) #define CA_SET_DESCR _IOW('o', 134, struct ca_descr) -#if !defined (__KERNEL__) +#if !defined(__KERNEL__) /* This is needed for legacy userspace support */ typedef struct ca_slot_info ca_slot_info_t; diff --git a/include/uapi/linux/dvb/dmx.h b/include/uapi/linux/dvb/dmx.h index 4e3f3a2fe83f..4aa5f6a1815a 100644 --- a/include/uapi/linux/dvb/dmx.h +++ b/include/uapi/linux/dvb/dmx.h @@ -189,8 +189,7 @@ struct dmx_sct_filter_params { * @pes_type: Type of the pes filter, as specified by &enum dmx_pes_type. * @flags: Demux PES flags. */ -struct dmx_pes_filter_params -{ +struct dmx_pes_filter_params { __u16 pid; enum dmx_input input; enum dmx_output output; @@ -221,7 +220,7 @@ struct dmx_stc { #define DMX_ADD_PID _IOW('o', 51, __u16) #define DMX_REMOVE_PID _IOW('o', 52, __u16) -#if !defined (__KERNEL__) +#if !defined(__KERNEL__) /* This is needed for legacy userspace support */ typedef enum dmx_output dmx_output_t; diff --git a/include/uapi/linux/dvb/frontend.h b/include/uapi/linux/dvb/frontend.h index fc2edb6014fe..861cacd5711f 100644 --- a/include/uapi/linux/dvb/frontend.h +++ b/include/uapi/linux/dvb/frontend.h @@ -907,7 +907,7 @@ struct dtv_properties { #define FE_SET_PROPERTY _IOW('o', 82, struct dtv_properties) #define FE_GET_PROPERTY _IOR('o', 83, struct dtv_properties) -#if defined(__DVB_CORE__) || !defined (__KERNEL__) +#if defined(__DVB_CORE__) || !defined(__KERNEL__) /* * DEPRECATED: Everything below is deprecated in favor of DVBv5 API @@ -982,8 +982,8 @@ struct dvb_ofdm_parameters { }; struct dvb_frontend_parameters { - __u32 frequency; /* (absolute) frequency in Hz for DVB-C/DVB-T/ATSC */ - /* intermediate frequency in kHz for DVB-S */ + __u32 frequency; /* (absolute) frequency in Hz for DVB-C/DVB-T/ATSC */ + /* intermediate frequency in kHz for DVB-S */ fe_spectral_inversion_t inversion; union { struct dvb_qpsk_parameters qpsk; /* DVB-S */ -- cgit v1.2.3-71-gd317 From aafd4562dfee81a40ba21b5ea3cf5e06664bc7f6 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 6 Sep 2017 16:23:29 -0700 Subject: mm: arch: consolidate mmap hugetlb size encodings A non-default huge page size can be encoded in the flags argument of the mmap system call. The definitions for these encodings are in arch specific header files. However, all architectures use the same values. Consolidate all the definitions in the primary user header file (uapi/linux/mman.h). Include definitions for all known huge page sizes. Use the generic encoding definitions in hugetlb_encode.h as the basis for these definitions. Link: http://lkml.kernel.org/r/1501527386-10736-3-git-send-email-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Acked-by: Michal Hocko Cc: Andi Kleen Cc: Andrea Arcangeli Cc: Aneesh Kumar K.V Cc: Anshuman Khandual Cc: Arnd Bergmann Cc: Davidlohr Bueso Cc: Matthew Wilcox Cc: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/include/uapi/asm/mman.h | 11 ----------- arch/mips/include/uapi/asm/mman.h | 11 ----------- arch/parisc/include/uapi/asm/mman.h | 11 ----------- arch/powerpc/include/uapi/asm/mman.h | 16 ---------------- arch/x86/include/uapi/asm/mman.h | 3 --- arch/xtensa/include/uapi/asm/mman.h | 11 ----------- include/uapi/asm-generic/mman-common.h | 11 ----------- include/uapi/linux/mman.h | 22 ++++++++++++++++++++++ 8 files changed, 22 insertions(+), 74 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h index 02760f6e6ca4..13b52aad3c43 100644 --- a/arch/alpha/include/uapi/asm/mman.h +++ b/arch/alpha/include/uapi/asm/mman.h @@ -67,17 +67,6 @@ /* compatibility flags */ #define MAP_FILE 0 -/* - * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size. - * This gives us 6 bits, which is enough until someone invents 128 bit address - * spaces. - * - * Assume these are all power of twos. - * When 0 use the default page size. - */ -#define MAP_HUGE_SHIFT 26 -#define MAP_HUGE_MASK 0x3f - #define PKEY_DISABLE_ACCESS 0x1 #define PKEY_DISABLE_WRITE 0x2 #define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h index 655e2fb5395b..398eebcc3541 100644 --- a/arch/mips/include/uapi/asm/mman.h +++ b/arch/mips/include/uapi/asm/mman.h @@ -94,17 +94,6 @@ /* compatibility flags */ #define MAP_FILE 0 -/* - * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size. - * This gives us 6 bits, which is enough until someone invents 128 bit address - * spaces. - * - * Assume these are all power of twos. - * When 0 use the default page size. - */ -#define MAP_HUGE_SHIFT 26 -#define MAP_HUGE_MASK 0x3f - #define PKEY_DISABLE_ACCESS 0x1 #define PKEY_DISABLE_WRITE 0x2 #define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h index 9a9c2fe4be50..b87fbe3f338a 100644 --- a/arch/parisc/include/uapi/asm/mman.h +++ b/arch/parisc/include/uapi/asm/mman.h @@ -64,17 +64,6 @@ #define MAP_FILE 0 #define MAP_VARIABLE 0 -/* - * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size. - * This gives us 6 bits, which is enough until someone invents 128 bit address - * spaces. - * - * Assume these are all power of twos. - * When 0 use the default page size. - */ -#define MAP_HUGE_SHIFT 26 -#define MAP_HUGE_MASK 0x3f - #define PKEY_DISABLE_ACCESS 0x1 #define PKEY_DISABLE_WRITE 0x2 #define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ diff --git a/arch/powerpc/include/uapi/asm/mman.h b/arch/powerpc/include/uapi/asm/mman.h index ab45cc2f3101..03c06ba7464f 100644 --- a/arch/powerpc/include/uapi/asm/mman.h +++ b/arch/powerpc/include/uapi/asm/mman.h @@ -29,20 +29,4 @@ #define MAP_STACK 0x20000 /* give out an address that is best suited for process/thread stacks */ #define MAP_HUGETLB 0x40000 /* create a huge page mapping */ -/* - * When MAP_HUGETLB is set, bits [26:31] of the flags argument to mmap(2), - * encode the log2 of the huge page size. A value of zero indicates that the - * default huge page size should be used. To use a non-default huge page size, - * one of these defines can be used, or the size can be encoded by hand. Note - * that on most systems only a subset, or possibly none, of these sizes will be - * available. - */ -#define MAP_HUGE_512KB (19 << MAP_HUGE_SHIFT) /* 512KB HugeTLB Page */ -#define MAP_HUGE_1MB (20 << MAP_HUGE_SHIFT) /* 1MB HugeTLB Page */ -#define MAP_HUGE_2MB (21 << MAP_HUGE_SHIFT) /* 2MB HugeTLB Page */ -#define MAP_HUGE_8MB (23 << MAP_HUGE_SHIFT) /* 8MB HugeTLB Page */ -#define MAP_HUGE_16MB (24 << MAP_HUGE_SHIFT) /* 16MB HugeTLB Page */ -#define MAP_HUGE_1GB (30 << MAP_HUGE_SHIFT) /* 1GB HugeTLB Page */ -#define MAP_HUGE_16GB (34 << MAP_HUGE_SHIFT) /* 16GB HugeTLB Page */ - #endif /* _UAPI_ASM_POWERPC_MMAN_H */ diff --git a/arch/x86/include/uapi/asm/mman.h b/arch/x86/include/uapi/asm/mman.h index 39bca7fac087..3be08f07695c 100644 --- a/arch/x86/include/uapi/asm/mman.h +++ b/arch/x86/include/uapi/asm/mman.h @@ -3,9 +3,6 @@ #define MAP_32BIT 0x40 /* only give out 32bit addresses */ -#define MAP_HUGE_2MB (21 << MAP_HUGE_SHIFT) -#define MAP_HUGE_1GB (30 << MAP_HUGE_SHIFT) - #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS /* * Take the 4 protection key bits out of the vma->vm_flags diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h index 24365b30aae9..8ce77a2e9bab 100644 --- a/arch/xtensa/include/uapi/asm/mman.h +++ b/arch/xtensa/include/uapi/asm/mman.h @@ -106,17 +106,6 @@ /* compatibility flags */ #define MAP_FILE 0 -/* - * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size. - * This gives us 6 bits, which is enough until someone invents 128 bit address - * spaces. - * - * Assume these are all power of twos. - * When 0 use the default page size. - */ -#define MAP_HUGE_SHIFT 26 -#define MAP_HUGE_MASK 0x3f - #define PKEY_DISABLE_ACCESS 0x1 #define PKEY_DISABLE_WRITE 0x2 #define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h index 8c27db0c5c08..d248f3c335b5 100644 --- a/include/uapi/asm-generic/mman-common.h +++ b/include/uapi/asm-generic/mman-common.h @@ -61,17 +61,6 @@ /* compatibility flags */ #define MAP_FILE 0 -/* - * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size. - * This gives us 6 bits, which is enough until someone invents 128 bit address - * spaces. - * - * Assume these are all power of twos. - * When 0 use the default page size. - */ -#define MAP_HUGE_SHIFT 26 -#define MAP_HUGE_MASK 0x3f - #define PKEY_DISABLE_ACCESS 0x1 #define PKEY_DISABLE_WRITE 0x2 #define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ diff --git a/include/uapi/linux/mman.h b/include/uapi/linux/mman.h index ade4acd3a90c..a937480d7cd3 100644 --- a/include/uapi/linux/mman.h +++ b/include/uapi/linux/mman.h @@ -2,6 +2,7 @@ #define _UAPI_LINUX_MMAN_H #include +#include #define MREMAP_MAYMOVE 1 #define MREMAP_FIXED 2 @@ -10,4 +11,25 @@ #define OVERCOMMIT_ALWAYS 1 #define OVERCOMMIT_NEVER 2 +/* + * Huge page size encoding when MAP_HUGETLB is specified, and a huge page + * size other than the default is desired. See hugetlb_encode.h. + * All known huge page size encodings are provided here. It is the + * responsibility of the application to know which sizes are supported on + * the running system. See mmap(2) man page for details. + */ +#define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT +#define MAP_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK + +#define MAP_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB +#define MAP_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB +#define MAP_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB +#define MAP_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB +#define MAP_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB +#define MAP_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB +#define MAP_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB +#define MAP_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB +#define MAP_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB +#define MAP_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB + #endif /* _UAPI_LINUX_MMAN_H */ -- cgit v1.2.3-71-gd317 From 4da243ac1cf6aeb30b7c555d56208982d66d6d33 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 6 Sep 2017 16:23:33 -0700 Subject: mm: shm: use new hugetlb size encoding definitions Use the common definitions from hugetlb_encode.h header file for encoding hugetlb size definitions in shmget system call flags. In addition, move these definitions from the internal (kernel) to user (uapi) header file. Link: http://lkml.kernel.org/r/1501527386-10736-4-git-send-email-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Suggested-by: Matthew Wilcox Acked-by: Michal Hocko Cc: Andi Kleen Cc: Andrea Arcangeli Cc: Aneesh Kumar K.V Cc: Anshuman Khandual Cc: Arnd Bergmann Cc: Davidlohr Bueso Cc: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shm.h | 17 ----------------- include/uapi/linux/shm.h | 31 +++++++++++++++++++++++++++++-- 2 files changed, 29 insertions(+), 19 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/shm.h b/include/linux/shm.h index 0fb7061ec54c..21a5e6c43385 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -27,23 +27,6 @@ struct shmid_kernel /* private to the kernel */ /* shm_mode upper byte flags */ #define SHM_DEST 01000 /* segment will be destroyed on last detach */ #define SHM_LOCKED 02000 /* segment will not be swapped */ -#define SHM_HUGETLB 04000 /* segment will use huge TLB pages */ -#define SHM_NORESERVE 010000 /* don't check for reservations */ - -/* Bits [26:31] are reserved */ - -/* - * When SHM_HUGETLB is set bits [26:31] encode the log2 of the huge page size. - * This gives us 6 bits, which is enough until someone invents 128 bit address - * spaces. - * - * Assume these are all power of twos. - * When 0 use the default page size. - */ -#define SHM_HUGE_SHIFT 26 -#define SHM_HUGE_MASK 0x3f -#define SHM_HUGE_2MB (21 << SHM_HUGE_SHIFT) -#define SHM_HUGE_1GB (30 << SHM_HUGE_SHIFT) #ifdef CONFIG_SYSVIPC struct sysv_shm { diff --git a/include/uapi/linux/shm.h b/include/uapi/linux/shm.h index 1fbf24ea37fd..cf23c873719d 100644 --- a/include/uapi/linux/shm.h +++ b/include/uapi/linux/shm.h @@ -3,6 +3,7 @@ #include #include +#include #ifndef __KERNEL__ #include #endif @@ -40,11 +41,37 @@ struct shmid_ds { /* Include the definition of shmid64_ds and shminfo64 */ #include -/* permission flag for shmget */ +/* + * shmget() shmflg values. + */ +/* The bottom nine bits are the same as open(2) mode flags */ #define SHM_R 0400 /* or S_IRUGO from */ #define SHM_W 0200 /* or S_IWUGO from */ +/* Bits 9 & 10 are IPC_CREAT and IPC_EXCL */ +#define SHM_HUGETLB 04000 /* segment will use huge TLB pages */ +#define SHM_NORESERVE 010000 /* don't check for reservations */ + +/* + * Huge page size encoding when SHM_HUGETLB is specified, and a huge page + * size other than the default is desired. See hugetlb_encode.h + */ +#define SHM_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT +#define SHM_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK + +#define SHM_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB +#define SHM_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB +#define SHM_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB +#define SHM_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB +#define SHM_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB +#define SHM_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB +#define SHM_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB +#define SHM_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB +#define SHM_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB +#define SHM_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB -/* mode for attach */ +/* + * shmat() shmflg values + */ #define SHM_RDONLY 010000 /* read-only access */ #define SHM_RND 020000 /* round attach address to SHMLBA boundary */ #define SHM_REMAP 040000 /* take-over region on attach */ -- cgit v1.2.3-71-gd317 From 2d6d6f5a09a96cc1fec7ed992b825e05f64cb50e Mon Sep 17 00:00:00 2001 From: Prakash Sangappa Date: Wed, 6 Sep 2017 16:23:39 -0700 Subject: mm: userfaultfd: add feature to request for a signal delivery In some cases, userfaultfd mechanism should just deliver a SIGBUS signal to the faulting process, instead of the page-fault event. Dealing with page-fault event using a monitor thread can be an overhead in these cases. For example applications like the database could use the signaling mechanism for robustness purpose. Database uses hugetlbfs for performance reason. Files on hugetlbfs filesystem are created and huge pages allocated using fallocate() API. Pages are deallocated/freed using fallocate() hole punching support. These files are mmapped and accessed by many processes as shared memory. The database keeps track of which offsets in the hugetlbfs file have pages allocated. Any access to mapped address over holes in the file, which can occur due to bugs in the application, is considered invalid and expect the process to simply receive a SIGBUS. However, currently when a hole in the file is accessed via the mapped address, kernel/mm attempts to automatically allocate a page at page fault time, resulting in implicitly filling the hole in the file. This may not be the desired behavior for applications like the database that want to explicitly manage page allocations of hugetlbfs files. Using userfaultfd mechanism with this support to get a signal, database application can prevent pages from being allocated implicitly when processes access mapped address over holes in the file. This patch adds UFFD_FEATURE_SIGBUS feature to userfaultfd mechnism to request for a SIGBUS signal. See following for previous discussion about the database requirement leading to this proposal as suggested by Andrea. http://www.spinics.net/lists/linux-mm/msg129224.html Link: http://lkml.kernel.org/r/1501552446-748335-2-git-send-email-prakash.sangappa@oracle.com Signed-off-by: Prakash Sangappa Reviewed-by: Mike Rapoport Reviewed-by: Andrea Arcangeli Cc: Mike Kravetz Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/userfaultfd.c | 3 +++ include/uapi/linux/userfaultfd.h | 10 +++++++++- 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 01a85e2660b8..5fd4d846691f 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -370,6 +370,9 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason) VM_BUG_ON(reason & ~(VM_UFFD_MISSING|VM_UFFD_WP)); VM_BUG_ON(!(reason & VM_UFFD_MISSING) ^ !!(reason & VM_UFFD_WP)); + if (ctx->features & UFFD_FEATURE_SIGBUS) + goto out; + /* * If it's already released don't get it. This avoids to loop * in __get_user_pages if userfaultfd_release waits on the diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index 3b059530dac9..d39d5db56771 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -23,7 +23,8 @@ UFFD_FEATURE_EVENT_REMOVE | \ UFFD_FEATURE_EVENT_UNMAP | \ UFFD_FEATURE_MISSING_HUGETLBFS | \ - UFFD_FEATURE_MISSING_SHMEM) + UFFD_FEATURE_MISSING_SHMEM | \ + UFFD_FEATURE_SIGBUS) #define UFFD_API_IOCTLS \ ((__u64)1 << _UFFDIO_REGISTER | \ (__u64)1 << _UFFDIO_UNREGISTER | \ @@ -153,6 +154,12 @@ struct uffdio_api { * UFFD_FEATURE_MISSING_SHMEM works the same as * UFFD_FEATURE_MISSING_HUGETLBFS, but it applies to shmem * (i.e. tmpfs and other shmem based APIs). + * + * UFFD_FEATURE_SIGBUS feature means no page-fault + * (UFFD_EVENT_PAGEFAULT) event will be delivered, instead + * a SIGBUS signal will be sent to the faulting process. + * The application process can enable this behavior by adding + * it to uffdio_api.features. */ #define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0) #define UFFD_FEATURE_EVENT_FORK (1<<1) @@ -161,6 +168,7 @@ struct uffdio_api { #define UFFD_FEATURE_MISSING_HUGETLBFS (1<<4) #define UFFD_FEATURE_MISSING_SHMEM (1<<5) #define UFFD_FEATURE_EVENT_UNMAP (1<<6) +#define UFFD_FEATURE_SIGBUS (1<<7) __u64 features; __u64 ioctls; -- cgit v1.2.3-71-gd317 From 9d4ac934829ac58c5109c49e6dfe677300e5e652 Mon Sep 17 00:00:00 2001 From: Alexey Perevalov Date: Wed, 6 Sep 2017 16:23:56 -0700 Subject: userfaultfd: provide pid in userfault msg It could be useful for calculating downtime during postcopy live migration per vCPU. Side observer or application itself will be informed about proper task's sleep during userfaultfd processing. Process's thread id is being provided when user requeste it by setting UFFD_FEATURE_THREAD_ID bit into uffdio_api.features. Link: http://lkml.kernel.org/r/20170802165145.22628-6-aarcange@redhat.com Signed-off-by: Alexey Perevalov Signed-off-by: Andrea Arcangeli Cc: "Dr. David Alan Gilbert" Cc: Maxime Coquelin Cc: Mike Kravetz Cc: Mike Rapoport Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/userfaultfd.c | 8 ++++++-- include/uapi/linux/userfaultfd.h | 10 +++++++--- 2 files changed, 13 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 5fd4d846691f..665bf7a930b2 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -178,7 +178,8 @@ static inline void msg_init(struct uffd_msg *msg) static inline struct uffd_msg userfault_msg(unsigned long address, unsigned int flags, - unsigned long reason) + unsigned long reason, + unsigned int features) { struct uffd_msg msg; msg_init(&msg); @@ -202,6 +203,8 @@ static inline struct uffd_msg userfault_msg(unsigned long address, * write protect fault. */ msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP; + if (features & UFFD_FEATURE_THREAD_ID) + msg.arg.pagefault.ptid = task_pid_vnr(current); return msg; } @@ -422,7 +425,8 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason) init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function); uwq.wq.private = current; - uwq.msg = userfault_msg(vmf->address, vmf->flags, reason); + uwq.msg = userfault_msg(vmf->address, vmf->flags, reason, + ctx->features); uwq.ctx = ctx; uwq.waken = false; diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index d39d5db56771..2b24c28d99a7 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -24,7 +24,8 @@ UFFD_FEATURE_EVENT_UNMAP | \ UFFD_FEATURE_MISSING_HUGETLBFS | \ UFFD_FEATURE_MISSING_SHMEM | \ - UFFD_FEATURE_SIGBUS) + UFFD_FEATURE_SIGBUS | \ + UFFD_FEATURE_THREAD_ID) #define UFFD_API_IOCTLS \ ((__u64)1 << _UFFDIO_REGISTER | \ (__u64)1 << _UFFDIO_UNREGISTER | \ @@ -79,6 +80,7 @@ struct uffd_msg { struct { __u64 flags; __u64 address; + __u32 ptid; } pagefault; struct { @@ -158,8 +160,9 @@ struct uffdio_api { * UFFD_FEATURE_SIGBUS feature means no page-fault * (UFFD_EVENT_PAGEFAULT) event will be delivered, instead * a SIGBUS signal will be sent to the faulting process. - * The application process can enable this behavior by adding - * it to uffdio_api.features. + * + * UFFD_FEATURE_THREAD_ID pid of the page faulted task_struct will + * be returned, if feature is not requested 0 will be returned. */ #define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0) #define UFFD_FEATURE_EVENT_FORK (1<<1) @@ -169,6 +172,7 @@ struct uffdio_api { #define UFFD_FEATURE_MISSING_SHMEM (1<<5) #define UFFD_FEATURE_EVENT_UNMAP (1<<6) #define UFFD_FEATURE_SIGBUS (1<<7) +#define UFFD_FEATURE_THREAD_ID (1<<8) __u64 features; __u64 ioctls; -- cgit v1.2.3-71-gd317 From a36985d31a65d5c0559fb582719e32eaf0ccec3b Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Wed, 6 Sep 2017 16:23:59 -0700 Subject: userfaultfd: provide pid in userfault msg - add feat union No ABI change, but this will make it more explicit to software that ptid is only available if requested by passing UFFD_FEATURE_THREAD_ID to UFFDIO_API. The fact it's a union will also self document it shouldn't be taken for granted there's a tpid there. Link: http://lkml.kernel.org/r/20170802165145.22628-7-aarcange@redhat.com Signed-off-by: Andrea Arcangeli Cc: "Dr. David Alan Gilbert" Cc: Alexey Perevalov Cc: Maxime Coquelin Cc: Mike Kravetz Cc: Mike Rapoport Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/userfaultfd.c | 2 +- include/uapi/linux/userfaultfd.h | 4 +++- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 665bf7a930b2..5419e7da82ba 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -204,7 +204,7 @@ static inline struct uffd_msg userfault_msg(unsigned long address, */ msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP; if (features & UFFD_FEATURE_THREAD_ID) - msg.arg.pagefault.ptid = task_pid_vnr(current); + msg.arg.pagefault.feat.ptid = task_pid_vnr(current); return msg; } diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index 2b24c28d99a7..d6d1f65cb3c3 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -80,7 +80,9 @@ struct uffd_msg { struct { __u64 flags; __u64 address; - __u32 ptid; + union { + __u32 ptid; + } feat; } pagefault; struct { -- cgit v1.2.3-71-gd317 From 749df87bd7bee5a79cef073f5d032ddb2b211de8 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 6 Sep 2017 16:24:16 -0700 Subject: mm/shmem: add hugetlbfs support to memfd_create() This patch came out of discussions in this e-mail thread: http://lkml.kernel.org/r/1499357846-7481-1-git-send-email-mike.kravetz%40oracle.com The Oracle JVM team is developing a new garbage collection model. This new model requires multiple mappings of the same anonymous memory. One straight forward way to accomplish this is with memfd_create. They can use the returned fd to create multiple mappings of the same memory. The JVM today has an option to use (static hugetlb) huge pages. If this option is specified, they would like to use the same garbage collection model requiring multiple mappings to the same memory. Using hugetlbfs, it is possible to explicitly mount a filesystem and specify file paths in order to get an fd that can be used for multiple mappings. However, this introduces additional system admin work and coordination. Ideally they would like to get a hugetlbfs fd without requiring explicit mounting of a filesystem. Today, mmap and shmget can make use of hugetlbfs without explicitly mounting a filesystem. The patch adds this functionality to memfd_create. Add a new flag MFD_HUGETLB to memfd_create() that will specify the file to be created resides in the hugetlbfs filesystem. This is the generic hugetlbfs filesystem not associated with any specific mount point. As with other system calls that request hugetlbfs backed pages, there is the ability to encode huge page size in the flag arguments. hugetlbfs does not support sealing operations, therefore specifying MFD_ALLOW_SEALING with MFD_HUGETLB will result in EINVAL. Of course, the memfd_man page would need updating if this type of functionality moves forward. Link: http://lkml.kernel.org/r/1502149672-7759-2-git-send-email-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Acked-by: Michal Hocko Cc: Hugh Dickins Cc: Andrea Arcangeli Cc: "Kirill A . Shutemov" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/memfd.h | 24 ++++++++++++++++++++++++ mm/shmem.c | 37 +++++++++++++++++++++++++++++++------ 2 files changed, 55 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/memfd.h b/include/uapi/linux/memfd.h index 534e364bda92..7f3a722dbd72 100644 --- a/include/uapi/linux/memfd.h +++ b/include/uapi/linux/memfd.h @@ -1,8 +1,32 @@ #ifndef _UAPI_LINUX_MEMFD_H #define _UAPI_LINUX_MEMFD_H +#include + /* flags for memfd_create(2) (unsigned int) */ #define MFD_CLOEXEC 0x0001U #define MFD_ALLOW_SEALING 0x0002U +#define MFD_HUGETLB 0x0004U + +/* + * Huge page size encoding when MFD_HUGETLB is specified, and a huge page + * size other than the default is desired. See hugetlb_encode.h. + * All known huge page size encodings are provided here. It is the + * responsibility of the application to know which sizes are supported on + * the running system. See mmap(2) man page for details. + */ +#define MFD_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT +#define MFD_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK + +#define MFD_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB +#define MFD_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB +#define MFD_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB +#define MFD_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB +#define MFD_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB +#define MFD_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB +#define MFD_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB +#define MFD_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB +#define MFD_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB +#define MFD_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB #endif /* _UAPI_LINUX_MEMFD_H */ diff --git a/mm/shmem.c b/mm/shmem.c index 64bdc91187f7..47179bbe9ee7 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -34,6 +34,7 @@ #include #include #include +#include #include /* for arch/microblaze update_mmu_cache() */ @@ -3652,7 +3653,7 @@ static int shmem_show_options(struct seq_file *seq, struct dentry *root) #define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1) #define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN) -#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING) +#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB) SYSCALL_DEFINE2(memfd_create, const char __user *, uname, @@ -3664,8 +3665,18 @@ SYSCALL_DEFINE2(memfd_create, char *name; long len; - if (flags & ~(unsigned int)MFD_ALL_FLAGS) - return -EINVAL; + if (!(flags & MFD_HUGETLB)) { + if (flags & ~(unsigned int)MFD_ALL_FLAGS) + return -EINVAL; + } else { + /* Sealing not supported in hugetlbfs (MFD_HUGETLB) */ + if (flags & MFD_ALLOW_SEALING) + return -EINVAL; + /* Allow huge page size encoding in flags. */ + if (flags & ~(unsigned int)(MFD_ALL_FLAGS | + (MFD_HUGE_MASK << MFD_HUGE_SHIFT))) + return -EINVAL; + } /* length includes terminating zero */ len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1); @@ -3696,16 +3707,30 @@ SYSCALL_DEFINE2(memfd_create, goto err_name; } - file = shmem_file_setup(name, 0, VM_NORESERVE); + if (flags & MFD_HUGETLB) { + struct user_struct *user = NULL; + + file = hugetlb_file_setup(name, 0, VM_NORESERVE, &user, + HUGETLB_ANONHUGE_INODE, + (flags >> MFD_HUGE_SHIFT) & + MFD_HUGE_MASK); + } else + file = shmem_file_setup(name, 0, VM_NORESERVE); if (IS_ERR(file)) { error = PTR_ERR(file); goto err_fd; } - info = SHMEM_I(file_inode(file)); file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; file->f_flags |= O_RDWR | O_LARGEFILE; - if (flags & MFD_ALLOW_SEALING) + + if (flags & MFD_ALLOW_SEALING) { + /* + * flags check at beginning of function ensures + * this is not a hugetlbfs (MFD_HUGETLB) file. + */ + info = SHMEM_I(file_inode(file)); info->seals &= ~F_SEAL_SEAL; + } fd_install(fd, file); kfree(name); -- cgit v1.2.3-71-gd317 From 3dd8f7c3b78b9556582fd64bf5c9986723f9dca1 Mon Sep 17 00:00:00 2001 From: Ian Kent Date: Fri, 8 Sep 2017 16:16:30 -0700 Subject: autofs: make dev ioctl version and ismountpoint user accessible Some of the autofs miscellaneous device ioctls need to be accessable to user space applications without CAP_SYS_ADMIN to get information about autofs mounts. Link: http://lkml.kernel.org/r/150216642517.11652.2338933266137331637.stgit@pluto.themaw.net Signed-off-by: Ian Kent Cc: Colin Walters Cc: Ondrej Holy Cc: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/autofs4/dev-ioctl.c | 12 ++++++++---- include/uapi/linux/auto_dev-ioctl.h | 2 +- 2 files changed, 9 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c index 218a4ecc75cc..ea8b3a1cddd2 100644 --- a/fs/autofs4/dev-ioctl.c +++ b/fs/autofs4/dev-ioctl.c @@ -628,10 +628,6 @@ static int _autofs_dev_ioctl(unsigned int command, ioctl_fn fn = NULL; int err = 0; - /* only root can play with this */ - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - cmd_first = _IOC_NR(AUTOFS_DEV_IOCTL_IOC_FIRST); cmd = _IOC_NR(command); @@ -640,6 +636,14 @@ static int _autofs_dev_ioctl(unsigned int command, return -ENOTTY; } + /* Only root can use ioctls other than AUTOFS_DEV_IOCTL_VERSION_CMD + * and AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD + */ + if (cmd != AUTOFS_DEV_IOCTL_VERSION_CMD && + cmd != AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD && + !capable(CAP_SYS_ADMIN)) + return -EPERM; + /* Copy the parameters into kernel space. */ param = copy_dev_ioctl(user); if (IS_ERR(param)) diff --git a/include/uapi/linux/auto_dev-ioctl.h b/include/uapi/linux/auto_dev-ioctl.h index 744b3d060968..5558db8e6646 100644 --- a/include/uapi/linux/auto_dev-ioctl.h +++ b/include/uapi/linux/auto_dev-ioctl.h @@ -16,7 +16,7 @@ #define AUTOFS_DEVICE_NAME "autofs" #define AUTOFS_DEV_IOCTL_VERSION_MAJOR 1 -#define AUTOFS_DEV_IOCTL_VERSION_MINOR 0 +#define AUTOFS_DEV_IOCTL_VERSION_MINOR 1 #define AUTOFS_DEV_IOCTL_SIZE sizeof(struct autofs_dev_ioctl) -- cgit v1.2.3-71-gd317 From 1f28c5d055032e7e8ee5e48198dca7e125d0eec6 Mon Sep 17 00:00:00 2001 From: Tomohiro Kusumi Date: Fri, 8 Sep 2017 16:16:34 -0700 Subject: autofs: remove unused AUTOFS_IOC_EXPIRE_DIRECT/INDIRECT These are not used by either kernel or userspace, although AUTOFS_IOC_EXPIRE_DIRECT once seems to have been used by userspace in around 2006-2008, which was technically just an alias of the existing ioctl AUTOFS_IOC_EXPIRE_MULTI. ioctls for autofs are already complicated enough that they could be removed unless these are staying here to be able to compile userspace code of certain period of time from a decade ago. Edit: raven@themaw.net Yes, this is indeed very old and anything that still uses must be updated becuase it will be using broken functionality. End edit: raven@themaw.net Link: http://lkml.kernel.org/r/150285067347.4670.11494624644273072003.stgit@pluto.themaw.net Signed-off-by: Tomohiro Kusumi Signed-off-by: Ian Kent Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/auto_fs4.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/auto_fs4.h b/include/uapi/linux/auto_fs4.h index 7c6da423d54e..9453e9a07c9d 100644 --- a/include/uapi/linux/auto_fs4.h +++ b/include/uapi/linux/auto_fs4.h @@ -155,8 +155,6 @@ enum { }; #define AUTOFS_IOC_EXPIRE_MULTI _IOW(AUTOFS_IOCTL, AUTOFS_IOC_EXPIRE_MULTI_CMD, int) -#define AUTOFS_IOC_EXPIRE_INDIRECT AUTOFS_IOC_EXPIRE_MULTI -#define AUTOFS_IOC_EXPIRE_DIRECT AUTOFS_IOC_EXPIRE_MULTI #define AUTOFS_IOC_PROTOSUBVER _IOR(AUTOFS_IOCTL, AUTOFS_IOC_PROTOSUBVER_CMD, int) #define AUTOFS_IOC_ASKUMOUNT _IOR(AUTOFS_IOCTL, AUTOFS_IOC_ASKUMOUNT_CMD, int) -- cgit v1.2.3-71-gd317 From a2d818030135c293f878fbb772cf40e7a14c5acc Mon Sep 17 00:00:00 2001 From: "Robert P. J. Day" Date: Fri, 8 Sep 2017 16:17:19 -0700 Subject: drivers/pps: aesthetic tweaks to PPS-related content Collection of aesthetic adjustments to various PPS-related files, directories and Documentation, some quite minor just for the sake of consistency, including: * Updated example of pps device tree node (courtesy Rodolfo G.) * "PPS-API" -> "PPS API" * "pps_source_info_s" -> "pps_source_info" * "ktimer driver" -> "pps-ktimer driver" * "ppstest /dev/pps0" -> "ppstest /dev/pps1" to match example * Add missing PPS-related entries to MAINTAINERS file * Other trivialities Link: http://lkml.kernel.org/r/alpine.LFD.2.20.1708261048220.8106@localhost.localdomain Signed-off-by: Robert P. J. Day Acked-by: Rodolfo Giometti Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/devicetree/bindings/pps/pps-gpio.txt | 8 +++- Documentation/pps/pps.txt | 44 +++++++++++----------- MAINTAINERS | 3 ++ include/linux/pps-gpio.h | 2 +- include/linux/pps_kernel.h | 16 ++++---- include/uapi/linux/pps.h | 4 +- kernel/time/timekeeping.c | 2 +- 7 files changed, 43 insertions(+), 36 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/devicetree/bindings/pps/pps-gpio.txt b/Documentation/devicetree/bindings/pps/pps-gpio.txt index 40bf9c3564a5..0de23b793657 100644 --- a/Documentation/devicetree/bindings/pps/pps-gpio.txt +++ b/Documentation/devicetree/bindings/pps/pps-gpio.txt @@ -13,8 +13,12 @@ Optional properties: Example: pps { - compatible = "pps-gpio"; - gpios = <&gpio2 6 0>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_pps>; + gpios = <&gpio1 26 GPIO_ACTIVE_HIGH>; assert-falling-edge; + + compatible = "pps-gpio"; + status = "okay"; }; diff --git a/Documentation/pps/pps.txt b/Documentation/pps/pps.txt index 1fdbd5447216..99f5d8c4c652 100644 --- a/Documentation/pps/pps.txt +++ b/Documentation/pps/pps.txt @@ -48,12 +48,12 @@ problem: time_pps_create(). This implies that the source has a /dev/... entry. This assumption is -ok for the serial and parallel port, where you can do something +OK for the serial and parallel port, where you can do something useful besides(!) the gathering of timestamps as it is the central -task for a PPS-API. But this assumption does not work for a single +task for a PPS API. But this assumption does not work for a single purpose GPIO line. In this case even basic file-related functionality (like read() and write()) makes no sense at all and should not be a -precondition for the use of a PPS-API. +precondition for the use of a PPS API. The problem can be simply solved if you consider that a PPS source is not always connected with a GPS data source. @@ -88,13 +88,13 @@ Coding example -------------- To register a PPS source into the kernel you should define a struct -pps_source_info_s as follows: +pps_source_info as follows: static struct pps_source_info pps_ktimer_info = { .name = "ktimer", .path = "", - .mode = PPS_CAPTUREASSERT | PPS_OFFSETASSERT | \ - PPS_ECHOASSERT | \ + .mode = PPS_CAPTUREASSERT | PPS_OFFSETASSERT | + PPS_ECHOASSERT | PPS_CANWAIT | PPS_TSFMT_TSPEC, .echo = pps_ktimer_echo, .owner = THIS_MODULE, @@ -108,13 +108,13 @@ initialization routine as follows: The pps_register_source() prototype is: - int pps_register_source(struct pps_source_info_s *info, int default_params) + int pps_register_source(struct pps_source_info *info, int default_params) where "info" is a pointer to a structure that describes a particular PPS source, "default_params" tells the system what the initial default parameters for the device should be (it is obvious that these parameters must be a subset of ones defined in the struct -pps_source_info_s which describe the capabilities of the driver). +pps_source_info which describe the capabilities of the driver). Once you have registered a new PPS source into the system you can signal an assert event (for example in the interrupt handler routine) @@ -142,8 +142,10 @@ If the SYSFS filesystem is enabled in the kernel it provides a new class: Every directory is the ID of a PPS sources defined in the system and inside you find several files: - $ ls /sys/class/pps/pps0/ - assert clear echo mode name path subsystem@ uevent + $ ls -F /sys/class/pps/pps0/ + assert dev mode path subsystem@ + clear echo name power/ uevent + Inside each "assert" and "clear" file you can find the timestamp and a sequence number: @@ -154,32 +156,32 @@ sequence number: Where before the "#" is the timestamp in seconds; after it is the sequence number. Other files are: -* echo: reports if the PPS source has an echo function or not; + * echo: reports if the PPS source has an echo function or not; -* mode: reports available PPS functioning modes; + * mode: reports available PPS functioning modes; -* name: reports the PPS source's name; + * name: reports the PPS source's name; -* path: reports the PPS source's device path, that is the device the - PPS source is connected to (if it exists). + * path: reports the PPS source's device path, that is the device the + PPS source is connected to (if it exists). Testing the PPS support ----------------------- In order to test the PPS support even without specific hardware you can use -the ktimer driver (see the client subsection in the PPS configuration menu) +the pps-ktimer driver (see the client subsection in the PPS configuration menu) and the userland tools available in your distribution's pps-tools package, -http://linuxpps.org , or https://github.com/ago/pps-tools . +http://linuxpps.org , or https://github.com/redlab-i/pps-tools. -Once you have enabled the compilation of ktimer just modprobe it (if +Once you have enabled the compilation of pps-ktimer just modprobe it (if not statically compiled): - # modprobe ktimer + # modprobe pps-ktimer and the run ppstest as follow: - $ ./ppstest /dev/pps0 + $ ./ppstest /dev/pps1 trying PPS source "/dev/pps1" found PPS source "/dev/pps1" ok, found 1 source(s), now start fetching data... @@ -187,7 +189,7 @@ and the run ppstest as follow: source 0 - assert 1186592700.388931295, sequence: 365 - clear 0.000000000, sequence: 0 source 0 - assert 1186592701.389032765, sequence: 366 - clear 0.000000000, sequence: 0 -Please, note that to compile userland programs you need the file timepps.h . +Please note that to compile userland programs, you need the file timepps.h. This is available in the pps-tools repository mentioned above. diff --git a/MAINTAINERS b/MAINTAINERS index ff3a349f24e4..109c5d9a04c4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10725,8 +10725,11 @@ W: http://wiki.enneenne.com/index.php/LinuxPPS_support L: linuxpps@ml.enneenne.com (subscribers-only) S: Maintained F: Documentation/pps/ +F: Documentation/devicetree/bindings/pps/pps-gpio.txt +F: Documentation/ABI/testing/sysfs-pps F: drivers/pps/ F: include/linux/pps*.h +F: include/uapi/linux/pps.h PPTP DRIVER M: Dmitry Kozlov diff --git a/include/linux/pps-gpio.h b/include/linux/pps-gpio.h index 0035abe41b9a..56f35dd3d01d 100644 --- a/include/linux/pps-gpio.h +++ b/include/linux/pps-gpio.h @@ -29,4 +29,4 @@ struct pps_gpio_platform_data { const char *gpio_label; }; -#endif +#endif /* _PPS_GPIO_H */ diff --git a/include/linux/pps_kernel.h b/include/linux/pps_kernel.h index 35ac903956c7..80a980cc8d95 100644 --- a/include/linux/pps_kernel.h +++ b/include/linux/pps_kernel.h @@ -22,7 +22,6 @@ #define LINUX_PPS_KERNEL_H #include - #include #include #include @@ -35,9 +34,9 @@ struct pps_device; /* The specific PPS source info */ struct pps_source_info { - char name[PPS_MAX_NAME_LEN]; /* simbolic name */ + char name[PPS_MAX_NAME_LEN]; /* symbolic name */ char path[PPS_MAX_NAME_LEN]; /* path of connected device */ - int mode; /* PPS's allowed mode */ + int mode; /* PPS allowed mode */ void (*echo)(struct pps_device *pps, int event, void *data); /* PPS echo function */ @@ -57,10 +56,10 @@ struct pps_event_time { struct pps_device { struct pps_source_info info; /* PSS source info */ - struct pps_kparams params; /* PPS's current params */ + struct pps_kparams params; /* PPS current params */ - __u32 assert_sequence; /* PPS' assert event seq # */ - __u32 clear_sequence; /* PPS' clear event seq # */ + __u32 assert_sequence; /* PPS assert event seq # */ + __u32 clear_sequence; /* PPS clear event seq # */ struct pps_ktime assert_tu; struct pps_ktime clear_tu; int current_mode; /* PPS mode at event time */ @@ -69,7 +68,7 @@ struct pps_device { wait_queue_head_t queue; /* PPS event queue */ unsigned int id; /* PPS source unique ID */ - void const *lookup_cookie; /* pps_lookup_dev only */ + void const *lookup_cookie; /* For pps_lookup_dev() only */ struct cdev cdev; struct device *dev; struct fasync_struct *async_queue; /* fasync method */ @@ -101,7 +100,7 @@ extern struct pps_device *pps_register_source( extern void pps_unregister_source(struct pps_device *pps); extern void pps_event(struct pps_device *pps, struct pps_event_time *ts, int event, void *data); -/* Look up a pps device by magic cookie */ +/* Look up a pps_device by magic cookie */ struct pps_device *pps_lookup_dev(void const *cookie); static inline void timespec_to_pps_ktime(struct pps_ktime *kt, @@ -132,4 +131,3 @@ static inline void pps_sub_ts(struct pps_event_time *ts, struct timespec64 delta } #endif /* LINUX_PPS_KERNEL_H */ - diff --git a/include/uapi/linux/pps.h b/include/uapi/linux/pps.h index c1cb3825a8bc..c29d6b791c08 100644 --- a/include/uapi/linux/pps.h +++ b/include/uapi/linux/pps.h @@ -95,8 +95,8 @@ struct pps_kparams { #define PPS_CAPTURECLEAR 0x02 /* capture clear events */ #define PPS_CAPTUREBOTH 0x03 /* capture assert and clear events */ -#define PPS_OFFSETASSERT 0x10 /* apply compensation for assert ev. */ -#define PPS_OFFSETCLEAR 0x20 /* apply compensation for clear ev. */ +#define PPS_OFFSETASSERT 0x10 /* apply compensation for assert event */ +#define PPS_OFFSETCLEAR 0x20 /* apply compensation for clear event */ #define PPS_CANWAIT 0x100 /* can we wait for an event? */ #define PPS_CANPOLL 0x200 /* bit reserved for future use */ diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 8ea4fb315719..2cafb49aa65e 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -2316,7 +2316,7 @@ void hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts) raw_spin_unlock_irqrestore(&timekeeper_lock, flags); } EXPORT_SYMBOL(hardpps); -#endif +#endif /* CONFIG_NTP_PPS */ /** * xtime_update() - advances the timekeeping infrastructure -- cgit v1.2.3-71-gd317 From 9beb8bedb05c5f3a353dba62b8fa7cbbb9ec685e Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 9 Sep 2017 01:40:35 +0200 Subject: bpf: make error reporting in bpf_warn_invalid_xdp_action more clear Differ between illegal XDP action code and just driver unsupported one to provide better feedback when we throw a one-time warning here. Reason is that with 814abfabef3c ("xdp: add bpf_redirect helper function") not all drivers support the new XDP return code yet and thus they will fall into their 'default' case when checking for return codes after program return, which then triggers a bpf_warn_invalid_xdp_action() stating that the return code is illegal, but from XDP perspective it's not. I decided not to place something like a XDP_ACT_MAX define into uapi i) given we don't have this either for all other program types, ii) future action codes could have further encoding there, which would render such define unsuitable and we wouldn't be able to rip it out again, and iii) we rarely add new action codes. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 4 ++-- net/core/filter.c | 6 +++++- 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index ba848b761cfb..43ab5c402f98 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -766,8 +766,8 @@ struct bpf_sock { /* User return codes for XDP prog type. * A valid XDP program must return one of these defined values. All other - * return codes are reserved for future use. Unknown return codes will result - * in packet drop. + * return codes are reserved for future use. Unknown return codes will + * result in packet drops and a warning via bpf_warn_invalid_xdp_action(). */ enum xdp_action { XDP_ABORTED = 0, diff --git a/net/core/filter.c b/net/core/filter.c index 0848df2cd9bf..3a50a9b021e2 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3609,7 +3609,11 @@ static bool xdp_is_valid_access(int off, int size, void bpf_warn_invalid_xdp_action(u32 act) { - WARN_ONCE(1, "Illegal XDP return value %u, expect packet loss\n", act); + const u32 act_max = XDP_REDIRECT; + + WARN_ONCE(1, "%s XDP return value %u, expect packet loss!\n", + act > act_max ? "Illegal" : "Driver unsupported", + act); } EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action); -- cgit v1.2.3-71-gd317 From a2b4a79b88b24c49d98d45a06a014ffd22ada1a4 Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Sun, 10 Sep 2017 20:29:45 +0300 Subject: spi: uapi: spidev: add missing ioctl header The SPI_IOC_MESSAGE() macro references _IOC_SIZEBITS. Add linux/ioctl.h to make sure this macro is defined. This fixes the following build failure of lcdproc with the musl libc: In file included from .../sysroot/usr/include/sys/ioctl.h:7:0, from hd44780-spi.c:31: hd44780-spi.c: In function 'spi_transfer': hd44780-spi.c:89:24: error: '_IOC_SIZEBITS' undeclared (first use in this function) status = ioctl(p->fd, SPI_IOC_MESSAGE(1), &xfer); ^ Signed-off-by: Baruch Siach Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- include/uapi/linux/spi/spidev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/spi/spidev.h b/include/uapi/linux/spi/spidev.h index dd5f21e75805..856de39d0b89 100644 --- a/include/uapi/linux/spi/spidev.h +++ b/include/uapi/linux/spi/spidev.h @@ -23,6 +23,7 @@ #define SPIDEV_H #include +#include /* User space versions of kernel symbols for SPI clocking modes, * matching -- cgit v1.2.3-71-gd317 From bd7a3fe770ebd8391d1c7d072ff88e9e76d063eb Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 19 Sep 2017 15:07:17 +0200 Subject: USB: fix out-of-bounds in usb_set_configuration Andrey Konovalov reported a possible out-of-bounds problem for a USB interface association descriptor. He writes: It seems there's no proper size check of a USB_DT_INTERFACE_ASSOCIATION descriptor. It's only checked that the size is >= 2 in usb_parse_configuration(), so find_iad() might do out-of-bounds access to intf_assoc->bInterfaceCount. And he's right, we don't check for crazy descriptors of this type very well, so resolve this problem. Yet another issue found by syzkaller... Reported-by: Andrey Konovalov Tested-by: Andrey Konovalov Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/config.c | 14 +++++++++++--- include/uapi/linux/usb/ch9.h | 1 + 2 files changed, 12 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index 854c8d66cfbe..68b54bd88d1e 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -643,15 +643,23 @@ static int usb_parse_configuration(struct usb_device *dev, int cfgidx, } else if (header->bDescriptorType == USB_DT_INTERFACE_ASSOCIATION) { + struct usb_interface_assoc_descriptor *d; + + d = (struct usb_interface_assoc_descriptor *)header; + if (d->bLength < USB_DT_INTERFACE_ASSOCIATION_SIZE) { + dev_warn(ddev, + "config %d has an invalid interface association descriptor of length %d, skipping\n", + cfgno, d->bLength); + continue; + } + if (iad_num == USB_MAXIADS) { dev_warn(ddev, "found more Interface " "Association Descriptors " "than allocated for in " "configuration %d\n", cfgno); } else { - config->intf_assoc[iad_num] = - (struct usb_interface_assoc_descriptor - *)header; + config->intf_assoc[iad_num] = d; iad_num++; } diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h index ce1169af39d7..2a5d63040a0b 100644 --- a/include/uapi/linux/usb/ch9.h +++ b/include/uapi/linux/usb/ch9.h @@ -780,6 +780,7 @@ struct usb_interface_assoc_descriptor { __u8 iFunction; } __attribute__ ((packed)); +#define USB_DT_INTERFACE_ASSOCIATION_SIZE 8 /*-------------------------------------------------------------------------*/ -- cgit v1.2.3-71-gd317 From 2d23d0736e3a4a0fdb92b8e46ea476639f16aae8 Mon Sep 17 00:00:00 2001 From: Roee Zamir Date: Sun, 6 Aug 2017 11:38:22 +0300 Subject: nl80211: add OCE scan and capability flags Add Optimized Connectivity Experience (OCE) scan and capability flags. Some of them unique to OCE and some are stand alone. And add scan flags to enable/disable them. Signed-off-by: Roee Zamir Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 37 ++++++++++-- net/wireless/nl80211.c | 137 ++++++++++++++++++++++++------------------- 2 files changed, 111 insertions(+), 63 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 51626b4175c0..76404d8a8863 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4914,6 +4914,15 @@ enum nl80211_feature_flags { * handshake with 802.1X in station mode (will pass EAP frames to the host * and accept the set_pmk/del_pmk commands), doing it in the host might not * be supported. + * @NL80211_EXT_FEATURE_FILS_MAX_CHANNEL_TIME: Driver is capable of overriding + * the max channel attribute in the FILS request params IE with the + * actual dwell time. + * @NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP: Driver accepts broadcast probe + * response + * @NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE: Driver supports sending + * the first probe request in each channel at rate of at least 5.5Mbps. + * @NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION: Driver supports + * probe request tx deferral and suppression * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. @@ -4936,6 +4945,10 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_FILS_SK_OFFLOAD, NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_PSK, NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_1X, + NL80211_EXT_FEATURE_FILS_MAX_CHANNEL_TIME, + NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP, + NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE, + NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, @@ -5012,12 +5025,28 @@ enum nl80211_timeout_reason { * locally administered 1, multicast 0) is assumed. * This flag must not be requested when the feature isn't supported, check * the nl80211 feature flags for the device. + * @NL80211_SCAN_FLAG_FILS_MAX_CHANNEL_TIME: fill the dwell time in the FILS + * request parameters IE in the probe request + * @NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP: accept broadcast probe responses + * @NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE: send probe request frames at + * rate of at least 5.5M. In case non OCE AP is dicovered in the channel, + * only the first probe req in the channel will be sent in high rate. + * @NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION: allow probe request + * tx deferral (dot11FILSProbeDelay shall be set to 15ms) + * and suppression (if it has received a broadcast Probe Response frame, + * Beacon frame or FILS Discovery frame from an AP that the STA considers + * a suitable candidate for (re-)association - suitable in terms of + * SSID and/or RSSI */ enum nl80211_scan_flags { - NL80211_SCAN_FLAG_LOW_PRIORITY = 1<<0, - NL80211_SCAN_FLAG_FLUSH = 1<<1, - NL80211_SCAN_FLAG_AP = 1<<2, - NL80211_SCAN_FLAG_RANDOM_ADDR = 1<<3, + NL80211_SCAN_FLAG_LOW_PRIORITY = 1<<0, + NL80211_SCAN_FLAG_FLUSH = 1<<1, + NL80211_SCAN_FLAG_AP = 1<<2, + NL80211_SCAN_FLAG_RANDOM_ADDR = 1<<3, + NL80211_SCAN_FLAG_FILS_MAX_CHANNEL_TIME = 1<<4, + NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP = 1<<5, + NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE = 1<<6, + NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION = 1<<7, }; /** diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 66e97136ab44..2e6f5f4065f9 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -6619,6 +6619,77 @@ static bool cfg80211_off_channel_oper_allowed(struct wireless_dev *wdev) return regulatory_pre_cac_allowed(wdev->wiphy); } +static int +nl80211_check_scan_flags(struct wiphy *wiphy, struct wireless_dev *wdev, + void *request, struct nlattr **attrs, + bool is_sched_scan) +{ + u8 *mac_addr, *mac_addr_mask; + u32 *flags; + enum nl80211_feature_flags randomness_flag; + + if (!attrs[NL80211_ATTR_SCAN_FLAGS]) + return 0; + + if (is_sched_scan) { + struct cfg80211_sched_scan_request *req = request; + + randomness_flag = wdev ? + NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR : + NL80211_FEATURE_ND_RANDOM_MAC_ADDR; + flags = &req->flags; + mac_addr = req->mac_addr; + mac_addr_mask = req->mac_addr_mask; + } else { + struct cfg80211_scan_request *req = request; + + randomness_flag = NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR; + flags = &req->flags; + mac_addr = req->mac_addr; + mac_addr_mask = req->mac_addr_mask; + } + + *flags = nla_get_u32(attrs[NL80211_ATTR_SCAN_FLAGS]); + + if ((*flags & NL80211_SCAN_FLAG_LOW_PRIORITY) && + !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) + return -EOPNOTSUPP; + + if (*flags & NL80211_SCAN_FLAG_RANDOM_ADDR) { + int err; + + if (!(wiphy->features & randomness_flag) || + (wdev && wdev->current_bss)) + return -EOPNOTSUPP; + + err = nl80211_parse_random_mac(attrs, mac_addr, mac_addr_mask); + if (err) + return err; + } + + if ((*flags & NL80211_SCAN_FLAG_FILS_MAX_CHANNEL_TIME) && + !wiphy_ext_feature_isset(wiphy, + NL80211_EXT_FEATURE_FILS_MAX_CHANNEL_TIME)) + return -EOPNOTSUPP; + + if ((*flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP) && + !wiphy_ext_feature_isset(wiphy, + NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP)) + return -EOPNOTSUPP; + + if ((*flags & NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION) && + !wiphy_ext_feature_isset(wiphy, + NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION)) + return -EOPNOTSUPP; + + if ((*flags & NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE) && + !wiphy_ext_feature_isset(wiphy, + NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE)) + return -EOPNOTSUPP; + + return 0; +} + static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; @@ -6824,34 +6895,10 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) nla_get_flag(info->attrs[NL80211_ATTR_MEASUREMENT_DURATION_MANDATORY]); } - if (info->attrs[NL80211_ATTR_SCAN_FLAGS]) { - request->flags = nla_get_u32( - info->attrs[NL80211_ATTR_SCAN_FLAGS]); - if ((request->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) && - !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) { - err = -EOPNOTSUPP; - goto out_free; - } - - if (request->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) { - if (!(wiphy->features & - NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR)) { - err = -EOPNOTSUPP; - goto out_free; - } - - if (wdev->current_bss) { - err = -EOPNOTSUPP; - goto out_free; - } - - err = nl80211_parse_random_mac(info->attrs, - request->mac_addr, - request->mac_addr_mask); - if (err) - goto out_free; - } - } + err = nl80211_check_scan_flags(wiphy, wdev, request, info->attrs, + false); + if (err) + goto out_free; request->no_cck = nla_get_flag(info->attrs[NL80211_ATTR_TX_NO_CCK_RATE]); @@ -7299,37 +7346,9 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, request->ie_len); } - if (attrs[NL80211_ATTR_SCAN_FLAGS]) { - request->flags = nla_get_u32( - attrs[NL80211_ATTR_SCAN_FLAGS]); - if ((request->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) && - !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) { - err = -EOPNOTSUPP; - goto out_free; - } - - if (request->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) { - u32 flg = NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR; - - if (!wdev) /* must be net-detect */ - flg = NL80211_FEATURE_ND_RANDOM_MAC_ADDR; - - if (!(wiphy->features & flg)) { - err = -EOPNOTSUPP; - goto out_free; - } - - if (wdev && wdev->current_bss) { - err = -EOPNOTSUPP; - goto out_free; - } - - err = nl80211_parse_random_mac(attrs, request->mac_addr, - request->mac_addr_mask); - if (err) - goto out_free; - } - } + err = nl80211_check_scan_flags(wiphy, wdev, request, attrs, true); + if (err) + goto out_free; if (attrs[NL80211_ATTR_SCHED_SCAN_DELAY]) request->delay = -- cgit v1.2.3-71-gd317 From 65026002d69de006e273749bb799d3b01b757eb0 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Fri, 18 Aug 2017 15:31:41 +0300 Subject: nl80211: add an option to allow MFP without requiring it The user space can now allow the kernel to associate to an AP that requires MFP or that doesn't have MFP enabled in the same NL80211_CMD_CONNECT command, by using a new NL80211_MFP_OPTIONAL flag. The driver / firmware will decide whether to use it or not. Include a feature bit to advertise support for NL80211_MFP_OPTIONAL. This allows new user space to run on old kernels and know that it cannot use the new attribute if it isn't supported. Signed-off-by: Emmanuel Grumbach Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 13 +++++++++++-- net/wireless/nl80211.c | 8 +++++++- 2 files changed, 18 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 76404d8a8863..59ba6ca66a0d 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1407,8 +1407,12 @@ enum nl80211_commands { * * @NL80211_ATTR_USE_MFP: Whether management frame protection (IEEE 802.11w) is * used for the association (&enum nl80211_mfp, represented as a u32); - * this attribute can be used - * with %NL80211_CMD_ASSOCIATE and %NL80211_CMD_CONNECT requests + * this attribute can be used with %NL80211_CMD_ASSOCIATE and + * %NL80211_CMD_CONNECT requests. %NL80211_MFP_OPTIONAL is not allowed for + * %NL80211_CMD_ASSOCIATE since user space SME is expected and hence, it + * must have decided whether to use management frame protection or not. + * Setting %NL80211_MFP_OPTIONAL with a %NL80211_CMD_CONNECT request will + * let the driver (or the firmware) decide whether to use MFP or not. * * @NL80211_ATTR_STA_FLAGS2: Attribute containing a * &struct nl80211_sta_flag_update. @@ -3947,10 +3951,12 @@ enum nl80211_key_type { * enum nl80211_mfp - Management frame protection state * @NL80211_MFP_NO: Management frame protection not used * @NL80211_MFP_REQUIRED: Management frame protection required + * @NL80211_MFP_OPTIONAL: Management frame protection is optional */ enum nl80211_mfp { NL80211_MFP_NO, NL80211_MFP_REQUIRED, + NL80211_MFP_OPTIONAL, }; enum nl80211_wpa_versions { @@ -4923,6 +4929,8 @@ enum nl80211_feature_flags { * the first probe request in each channel at rate of at least 5.5Mbps. * @NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION: Driver supports * probe request tx deferral and suppression + * @NL80211_EXT_FEATURE_MFP_OPTIONAL: Driver supports the %NL80211_MFP_OPTIONAL + * value in %NL80211_ATTR_USE_MFP. * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. @@ -4949,6 +4957,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP, NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE, NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION, + NL80211_EXT_FEATURE_MFP_OPTIONAL, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 2e6f5f4065f9..1e39ba3cfd06 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -8952,8 +8952,14 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_USE_MFP]) { connect.mfp = nla_get_u32(info->attrs[NL80211_ATTR_USE_MFP]); + if (connect.mfp == NL80211_MFP_OPTIONAL && + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_MFP_OPTIONAL)) + return -EOPNOTSUPP; + if (connect.mfp != NL80211_MFP_REQUIRED && - connect.mfp != NL80211_MFP_NO) + connect.mfp != NL80211_MFP_NO && + connect.mfp != NL80211_MFP_OPTIONAL) return -EINVAL; } else { connect.mfp = NL80211_MFP_NO; -- cgit v1.2.3-71-gd317 From 19cab8872692960535aa6d12e3a295ac51d1a648 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 20 Sep 2017 15:52:13 -0700 Subject: net: ethtool: Add back transceiver type Commit 3f1ac7a700d0 ("net: ethtool: add new ETHTOOL_xLINKSETTINGS API") deprecated the ethtool_cmd::transceiver field, which was fine in premise, except that the PHY library was actually using it to report the type of transceiver: internal or external. Use the first word of the reserved field to put this __u8 transceiver field back in. It is made read-only, and we don't expect the ETHTOOL_xLINKSETTINGS API to be doing anything with this anyway, so this is mostly for the legacy path where we do: ethtool_get_settings() -> dev->ethtool_ops->get_link_ksettings() -> convert_link_ksettings_to_legacy_settings() to have no information loss compared to the legacy get_settings API. Fixes: 3f1ac7a700d0 ("net: ethtool: add new ETHTOOL_xLINKSETTINGS API") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/uapi/linux/ethtool.h | 6 +++++- net/core/ethtool.c | 2 ++ 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 9c041dae8e2c..5bd1b1de4ea0 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1753,6 +1753,8 @@ enum ethtool_reset_flags { * %ethtool_link_mode_bit_indices for the link modes, and other * link features that the link partner advertised through * autonegotiation; 0 if unknown or not applicable. Read-only. + * @transceiver: Used to distinguish different possible PHY types, + * reported consistently by PHYLIB. Read-only. * * If autonegotiation is disabled, the speed and @duplex represent the * fixed link mode and are writable if the driver supports multiple @@ -1804,7 +1806,9 @@ struct ethtool_link_settings { __u8 eth_tp_mdix; __u8 eth_tp_mdix_ctrl; __s8 link_mode_masks_nwords; - __u32 reserved[8]; + __u8 transceiver; + __u8 reserved1[3]; + __u32 reserved[7]; __u32 link_mode_masks[0]; /* layout of link_mode_masks fields: * __u32 map_supported[link_mode_masks_nwords]; diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 6a582ae4c5d9..3228411ada0f 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -525,6 +525,8 @@ convert_link_ksettings_to_legacy_settings( = link_ksettings->base.eth_tp_mdix; legacy_settings->eth_tp_mdix_ctrl = link_ksettings->base.eth_tp_mdix_ctrl; + legacy_settings->transceiver + = link_ksettings->base.transceiver; return retval; } -- cgit v1.2.3-71-gd317 From 333ef6bd10c3ffdaf6da94e34dc6cae675ed27fc Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 15 Aug 2017 10:07:25 -0400 Subject: media: cec: add CEC_EVENT_PIN_HPD_LOW/HIGH events Add support for two new low-level events: PIN_HPD_LOW and PIN_HPD_HIGH. This is specifically meant for use with the upcoming cec-gpio driver and makes it possible to trace when the HPD pin changes. Some HDMI sinks do strange things with the HPD and this makes it easy to debug this. Note that this also moves the initialization of a devnode mutex and list to the allocate_adapter function: if the HPD is high, then as soon as the HPD interrupt is created an interrupt occurs and cec_queue_pin_hpd_event() is called which requires that the devnode mutex and list are initialized. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/cec/cec-adap.c | 18 +++++++++++++++++- drivers/media/cec/cec-api.c | 18 ++++++++++++++---- drivers/media/cec/cec-core.c | 8 ++++---- include/media/cec-pin.h | 4 ++++ include/media/cec.h | 12 +++++++++++- include/uapi/linux/cec.h | 2 ++ 6 files changed, 52 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/media/cec/cec-adap.c b/drivers/media/cec/cec-adap.c index 84d1b67f850c..dd0c9cacd1d0 100644 --- a/drivers/media/cec/cec-adap.c +++ b/drivers/media/cec/cec-adap.c @@ -86,7 +86,7 @@ void cec_queue_event_fh(struct cec_fh *fh, const struct cec_event *new_ev, u64 ts) { static const u8 max_events[CEC_NUM_EVENTS] = { - 1, 1, 64, 64, + 1, 1, 64, 64, 8, 8, }; struct cec_event_entry *entry; unsigned int ev_idx = new_ev->event - 1; @@ -170,6 +170,22 @@ void cec_queue_pin_cec_event(struct cec_adapter *adap, bool is_high, ktime_t ts) } EXPORT_SYMBOL_GPL(cec_queue_pin_cec_event); +/* Notify userspace that the HPD pin changed state at the given time. */ +void cec_queue_pin_hpd_event(struct cec_adapter *adap, bool is_high, ktime_t ts) +{ + struct cec_event ev = { + .event = is_high ? CEC_EVENT_PIN_HPD_HIGH : + CEC_EVENT_PIN_HPD_LOW, + }; + struct cec_fh *fh; + + mutex_lock(&adap->devnode.lock); + list_for_each_entry(fh, &adap->devnode.fhs, list) + cec_queue_event_fh(fh, &ev, ktime_to_ns(ts)); + mutex_unlock(&adap->devnode.lock); +} +EXPORT_SYMBOL_GPL(cec_queue_pin_hpd_event); + /* * Queue a new message for this filehandle. * diff --git a/drivers/media/cec/cec-api.c b/drivers/media/cec/cec-api.c index a079f7fe018c..465bb3ec21f6 100644 --- a/drivers/media/cec/cec-api.c +++ b/drivers/media/cec/cec-api.c @@ -529,7 +529,7 @@ static int cec_open(struct inode *inode, struct file *filp) * Initial events that are automatically sent when the cec device is * opened. */ - struct cec_event ev_state = { + struct cec_event ev = { .event = CEC_EVENT_STATE_CHANGE, .flags = CEC_EVENT_FL_INITIAL_STATE, }; @@ -569,9 +569,19 @@ static int cec_open(struct inode *inode, struct file *filp) filp->private_data = fh; /* Queue up initial state events */ - ev_state.state_change.phys_addr = adap->phys_addr; - ev_state.state_change.log_addr_mask = adap->log_addrs.log_addr_mask; - cec_queue_event_fh(fh, &ev_state, 0); + ev.state_change.phys_addr = adap->phys_addr; + ev.state_change.log_addr_mask = adap->log_addrs.log_addr_mask; + cec_queue_event_fh(fh, &ev, 0); +#ifdef CONFIG_CEC_PIN + if (adap->pin && adap->pin->ops->read_hpd) { + err = adap->pin->ops->read_hpd(adap); + if (err >= 0) { + ev.event = err ? CEC_EVENT_PIN_HPD_HIGH : + CEC_EVENT_PIN_HPD_LOW; + cec_queue_event_fh(fh, &ev, 0); + } + } +#endif list_add(&fh->list, &devnode->fhs); mutex_unlock(&devnode->lock); diff --git a/drivers/media/cec/cec-core.c b/drivers/media/cec/cec-core.c index 648136e552d5..e3a1fb6d6690 100644 --- a/drivers/media/cec/cec-core.c +++ b/drivers/media/cec/cec-core.c @@ -112,10 +112,6 @@ static int __must_check cec_devnode_register(struct cec_devnode *devnode, int minor; int ret; - /* Initialization */ - INIT_LIST_HEAD(&devnode->fhs); - mutex_init(&devnode->lock); - /* Part 1: Find a free minor number */ mutex_lock(&cec_devnode_lock); minor = find_next_zero_bit(cec_devnode_nums, CEC_NUM_DEVICES, 0); @@ -242,6 +238,10 @@ struct cec_adapter *cec_allocate_adapter(const struct cec_adap_ops *ops, INIT_LIST_HEAD(&adap->wait_queue); init_waitqueue_head(&adap->kthread_waitq); + /* adap->devnode initialization */ + INIT_LIST_HEAD(&adap->devnode.fhs); + mutex_init(&adap->devnode.lock); + adap->kthread = kthread_run(cec_thread_func, adap, "cec-%s", name); if (IS_ERR(adap->kthread)) { pr_err("cec-%s: kernel_thread() failed\n", name); diff --git a/include/media/cec-pin.h b/include/media/cec-pin.h index f09cc9579d53..ea84b9c9e0c3 100644 --- a/include/media/cec-pin.h +++ b/include/media/cec-pin.h @@ -97,6 +97,9 @@ enum cec_pin_state { * @free: optional. Free any allocated resources. Called when the * adapter is deleted. * @status: optional, log status information. + * @read_hpd: read the HPD pin. Return true if high, false if low or + * an error if negative. If NULL or -ENOTTY is returned, + * then this is not supported. * * These operations are used by the cec pin framework to manipulate * the CEC pin. @@ -109,6 +112,7 @@ struct cec_pin_ops { void (*disable_irq)(struct cec_adapter *adap); void (*free)(struct cec_adapter *adap); void (*status)(struct cec_adapter *adap, struct seq_file *file); + int (*read_hpd)(struct cec_adapter *adap); }; #define CEC_NUM_PIN_EVENTS 128 diff --git a/include/media/cec.h b/include/media/cec.h index df6b3bd31284..9d0f983faea9 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -91,7 +91,7 @@ struct cec_event_entry { }; #define CEC_NUM_CORE_EVENTS 2 -#define CEC_NUM_EVENTS CEC_EVENT_PIN_CEC_HIGH +#define CEC_NUM_EVENTS CEC_EVENT_PIN_HPD_HIGH struct cec_fh { struct list_head list; @@ -296,6 +296,16 @@ static inline void cec_received_msg(struct cec_adapter *adap, void cec_queue_pin_cec_event(struct cec_adapter *adap, bool is_high, ktime_t ts); +/** + * cec_queue_pin_hpd_event() - queue a pin event with a given timestamp. + * + * @adap: pointer to the cec adapter + * @is_high: when true the HPD pin is high, otherwise it is low + * @ts: the timestamp for this event + * + */ +void cec_queue_pin_hpd_event(struct cec_adapter *adap, bool is_high, ktime_t ts); + /** * cec_get_edid_phys_addr() - find and return the physical address * diff --git a/include/uapi/linux/cec.h b/include/uapi/linux/cec.h index 4351c3481aea..b9f8df3a0477 100644 --- a/include/uapi/linux/cec.h +++ b/include/uapi/linux/cec.h @@ -410,6 +410,8 @@ struct cec_log_addrs { #define CEC_EVENT_LOST_MSGS 2 #define CEC_EVENT_PIN_CEC_LOW 3 #define CEC_EVENT_PIN_CEC_HIGH 4 +#define CEC_EVENT_PIN_HPD_LOW 5 +#define CEC_EVENT_PIN_HPD_HIGH 6 #define CEC_EVENT_FL_INITIAL_STATE (1 << 0) #define CEC_EVENT_FL_DROPPED_EVENTS (1 << 1) -- cgit v1.2.3-71-gd317 From 62e082430ea4bb5b28909ca4375bb683931e22aa Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Wed, 20 Sep 2017 07:29:49 -0400 Subject: dm ioctl: fix alignment of event number in the device list The size of struct dm_name_list is different on 32-bit and 64-bit kernels (so "(nl + 1)" differs between 32-bit and 64-bit kernels). This mismatch caused some harmless difference in padding when using 32-bit or 64-bit kernel. Commit 23d70c5e52dd ("dm ioctl: report event number in DM_LIST_DEVICES") added reporting event number in the output of DM_LIST_DEVICES_CMD. This difference in padding makes it impossible for userspace to determine the location of the event number (the location would be different when running on 32-bit and 64-bit kernels). Fix the padding by using offsetof(struct dm_name_list, name) instead of sizeof(struct dm_name_list) to determine the location of entries. Also, the ioctl version number is incremented to 37 so that userspace can use the version number to determine that the event number is present and correctly located. In addition, a global event is now raised when a DM device is created, removed, renamed or when table is swapped, so that the user can monitor for device changes. Reported-by: Eugene Syromiatnikov Fixes: 23d70c5e52dd ("dm ioctl: report event number in DM_LIST_DEVICES") Cc: stable@vger.kernel.org # 4.13 Signed-off-by: Mikulas Patocka Signed-off-by: Mike Snitzer --- drivers/md/dm-core.h | 1 + drivers/md/dm-ioctl.c | 37 ++++++++++++++++++++++++------------- drivers/md/dm.c | 10 ++++++++-- include/uapi/linux/dm-ioctl.h | 4 ++-- 4 files changed, 35 insertions(+), 17 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 24eddbdf2ab4..203144762f36 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -149,5 +149,6 @@ static inline bool dm_message_test_buffer_overflow(char *result, unsigned maxlen extern atomic_t dm_global_event_nr; extern wait_queue_head_t dm_global_eventq; +void dm_issue_global_event(void); #endif diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 8756a6850431..e52676fa9832 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -477,9 +477,13 @@ static int remove_all(struct file *filp, struct dm_ioctl *param, size_t param_si * Round up the ptr to an 8-byte boundary. */ #define ALIGN_MASK 7 +static inline size_t align_val(size_t val) +{ + return (val + ALIGN_MASK) & ~ALIGN_MASK; +} static inline void *align_ptr(void *ptr) { - return (void *) (((size_t) (ptr + ALIGN_MASK)) & ~ALIGN_MASK); + return (void *)align_val((size_t)ptr); } /* @@ -505,7 +509,7 @@ static int list_devices(struct file *filp, struct dm_ioctl *param, size_t param_ struct hash_cell *hc; size_t len, needed = 0; struct gendisk *disk; - struct dm_name_list *nl, *old_nl = NULL; + struct dm_name_list *orig_nl, *nl, *old_nl = NULL; uint32_t *event_nr; down_write(&_hash_lock); @@ -516,17 +520,15 @@ static int list_devices(struct file *filp, struct dm_ioctl *param, size_t param_ */ for (i = 0; i < NUM_BUCKETS; i++) { list_for_each_entry (hc, _name_buckets + i, name_list) { - needed += sizeof(struct dm_name_list); - needed += strlen(hc->name) + 1; - needed += ALIGN_MASK; - needed += (sizeof(uint32_t) + ALIGN_MASK) & ~ALIGN_MASK; + needed += align_val(offsetof(struct dm_name_list, name) + strlen(hc->name) + 1); + needed += align_val(sizeof(uint32_t)); } } /* * Grab our output buffer. */ - nl = get_result_buffer(param, param_size, &len); + nl = orig_nl = get_result_buffer(param, param_size, &len); if (len < needed) { param->flags |= DM_BUFFER_FULL_FLAG; goto out; @@ -549,11 +551,16 @@ static int list_devices(struct file *filp, struct dm_ioctl *param, size_t param_ strcpy(nl->name, hc->name); old_nl = nl; - event_nr = align_ptr(((void *) (nl + 1)) + strlen(hc->name) + 1); + event_nr = align_ptr(nl->name + strlen(hc->name) + 1); *event_nr = dm_get_event_nr(hc->md); nl = align_ptr(event_nr + 1); } } + /* + * If mismatch happens, security may be compromised due to buffer + * overflow, so it's better to crash. + */ + BUG_ON((char *)nl - (char *)orig_nl != needed); out: up_write(&_hash_lock); @@ -1621,7 +1628,8 @@ static int target_message(struct file *filp, struct dm_ioctl *param, size_t para * which has a variable size, is not used by the function processing * the ioctl. */ -#define IOCTL_FLAGS_NO_PARAMS 1 +#define IOCTL_FLAGS_NO_PARAMS 1 +#define IOCTL_FLAGS_ISSUE_GLOBAL_EVENT 2 /*----------------------------------------------------------------- * Implementation of open/close/ioctl on the special char @@ -1635,12 +1643,12 @@ static ioctl_fn lookup_ioctl(unsigned int cmd, int *ioctl_flags) ioctl_fn fn; } _ioctls[] = { {DM_VERSION_CMD, 0, NULL}, /* version is dealt with elsewhere */ - {DM_REMOVE_ALL_CMD, IOCTL_FLAGS_NO_PARAMS, remove_all}, + {DM_REMOVE_ALL_CMD, IOCTL_FLAGS_NO_PARAMS | IOCTL_FLAGS_ISSUE_GLOBAL_EVENT, remove_all}, {DM_LIST_DEVICES_CMD, 0, list_devices}, - {DM_DEV_CREATE_CMD, IOCTL_FLAGS_NO_PARAMS, dev_create}, - {DM_DEV_REMOVE_CMD, IOCTL_FLAGS_NO_PARAMS, dev_remove}, - {DM_DEV_RENAME_CMD, 0, dev_rename}, + {DM_DEV_CREATE_CMD, IOCTL_FLAGS_NO_PARAMS | IOCTL_FLAGS_ISSUE_GLOBAL_EVENT, dev_create}, + {DM_DEV_REMOVE_CMD, IOCTL_FLAGS_NO_PARAMS | IOCTL_FLAGS_ISSUE_GLOBAL_EVENT, dev_remove}, + {DM_DEV_RENAME_CMD, IOCTL_FLAGS_ISSUE_GLOBAL_EVENT, dev_rename}, {DM_DEV_SUSPEND_CMD, IOCTL_FLAGS_NO_PARAMS, dev_suspend}, {DM_DEV_STATUS_CMD, IOCTL_FLAGS_NO_PARAMS, dev_status}, {DM_DEV_WAIT_CMD, 0, dev_wait}, @@ -1869,6 +1877,9 @@ static int ctl_ioctl(struct file *file, uint command, struct dm_ioctl __user *us unlikely(ioctl_flags & IOCTL_FLAGS_NO_PARAMS)) DMERR("ioctl %d tried to output some data but has IOCTL_FLAGS_NO_PARAMS set", cmd); + if (!r && ioctl_flags & IOCTL_FLAGS_ISSUE_GLOBAL_EVENT) + dm_issue_global_event(); + /* * Copy the results back to userland. */ diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 6e54145969c5..4be85324f44d 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -52,6 +52,12 @@ static struct workqueue_struct *deferred_remove_workqueue; atomic_t dm_global_event_nr = ATOMIC_INIT(0); DECLARE_WAIT_QUEUE_HEAD(dm_global_eventq); +void dm_issue_global_event(void) +{ + atomic_inc(&dm_global_event_nr); + wake_up(&dm_global_eventq); +} + /* * One of these is allocated per bio. */ @@ -1865,9 +1871,8 @@ static void event_callback(void *context) dm_send_uevents(&uevents, &disk_to_dev(md->disk)->kobj); atomic_inc(&md->event_nr); - atomic_inc(&dm_global_event_nr); wake_up(&md->eventq); - wake_up(&dm_global_eventq); + dm_issue_global_event(); } /* @@ -2283,6 +2288,7 @@ struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *table) } map = __bind(md, table, &limits); + dm_issue_global_event(); out: mutex_unlock(&md->suspend_lock); diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h index 412c06a624c8..ccaea525340b 100644 --- a/include/uapi/linux/dm-ioctl.h +++ b/include/uapi/linux/dm-ioctl.h @@ -269,9 +269,9 @@ enum { #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 36 +#define DM_VERSION_MINOR 37 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2017-06-09)" +#define DM_VERSION_EXTRA "-ioctl (2017-09-20)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ -- cgit v1.2.3-71-gd317 From 943170998b200190f99d3fe7e771437e2c51f319 Mon Sep 17 00:00:00 2001 From: Petar Penkov Date: Fri, 22 Sep 2017 13:49:14 -0700 Subject: tun: enable NAPI for TUN/TAP driver Changes TUN driver to use napi_gro_receive() upon receiving packets rather than netif_rx_ni(). Adds flag IFF_NAPI that enables these changes and operation is not affected if the flag is disabled. SKBs are constructed upon packet arrival and are queued to be processed later. The new path was evaluated with a benchmark with the following setup: Open two tap devices and a receiver thread that reads in a loop for each device. Start one sender thread and pin all threads to different CPUs. Send 1M minimum UDP packets to each device and measure sending time for each of the sending methods: napi_gro_receive(): 4.90s netif_rx_ni(): 4.90s netif_receive_skb(): 7.20s Signed-off-by: Petar Penkov Cc: Eric Dumazet Cc: Mahesh Bandewar Cc: Willem de Bruijn Cc: davem@davemloft.net Cc: ppenkov@stanford.edu Acked-by: Mahesh Bandewar Signed-off-by: David S. Miller --- drivers/net/tun.c | 133 +++++++++++++++++++++++++++++++++++++++----- include/uapi/linux/if_tun.h | 1 + 2 files changed, 119 insertions(+), 15 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 3c9985f29950..f16407242b18 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -121,7 +121,7 @@ do { \ #define TUN_VNET_BE 0x40000000 #define TUN_FEATURES (IFF_NO_PI | IFF_ONE_QUEUE | IFF_VNET_HDR | \ - IFF_MULTI_QUEUE) + IFF_MULTI_QUEUE | IFF_NAPI) #define GOODCOPY_LEN 128 #define FLT_EXACT_COUNT 8 @@ -172,6 +172,7 @@ struct tun_file { u16 queue_index; unsigned int ifindex; }; + struct napi_struct napi; struct list_head next; struct tun_struct *detached; struct skb_array tx_array; @@ -229,6 +230,68 @@ struct tun_struct { struct bpf_prog __rcu *xdp_prog; }; +static int tun_napi_receive(struct napi_struct *napi, int budget) +{ + struct tun_file *tfile = container_of(napi, struct tun_file, napi); + struct sk_buff_head *queue = &tfile->sk.sk_write_queue; + struct sk_buff_head process_queue; + struct sk_buff *skb; + int received = 0; + + __skb_queue_head_init(&process_queue); + + spin_lock(&queue->lock); + skb_queue_splice_tail_init(queue, &process_queue); + spin_unlock(&queue->lock); + + while (received < budget && (skb = __skb_dequeue(&process_queue))) { + napi_gro_receive(napi, skb); + ++received; + } + + if (!skb_queue_empty(&process_queue)) { + spin_lock(&queue->lock); + skb_queue_splice(&process_queue, queue); + spin_unlock(&queue->lock); + } + + return received; +} + +static int tun_napi_poll(struct napi_struct *napi, int budget) +{ + unsigned int received; + + received = tun_napi_receive(napi, budget); + + if (received < budget) + napi_complete_done(napi, received); + + return received; +} + +static void tun_napi_init(struct tun_struct *tun, struct tun_file *tfile, + bool napi_en) +{ + if (napi_en) { + netif_napi_add(tun->dev, &tfile->napi, tun_napi_poll, + NAPI_POLL_WEIGHT); + napi_enable(&tfile->napi); + } +} + +static void tun_napi_disable(struct tun_struct *tun, struct tun_file *tfile) +{ + if (tun->flags & IFF_NAPI) + napi_disable(&tfile->napi); +} + +static void tun_napi_del(struct tun_struct *tun, struct tun_file *tfile) +{ + if (tun->flags & IFF_NAPI) + netif_napi_del(&tfile->napi); +} + #ifdef CONFIG_TUN_VNET_CROSS_LE static inline bool tun_legacy_is_little_endian(struct tun_struct *tun) { @@ -541,6 +604,11 @@ static void __tun_detach(struct tun_file *tfile, bool clean) tun = rtnl_dereference(tfile->tun); + if (tun && clean) { + tun_napi_disable(tun, tfile); + tun_napi_del(tun, tfile); + } + if (tun && !tfile->detached) { u16 index = tfile->queue_index; BUG_ON(index >= tun->numqueues); @@ -598,6 +666,7 @@ static void tun_detach_all(struct net_device *dev) for (i = 0; i < n; i++) { tfile = rtnl_dereference(tun->tfiles[i]); BUG_ON(!tfile); + tun_napi_disable(tun, tfile); tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN; tfile->socket.sk->sk_data_ready(tfile->socket.sk); RCU_INIT_POINTER(tfile->tun, NULL); @@ -613,6 +682,7 @@ static void tun_detach_all(struct net_device *dev) synchronize_net(); for (i = 0; i < n; i++) { tfile = rtnl_dereference(tun->tfiles[i]); + tun_napi_del(tun, tfile); /* Drop read queue */ tun_queue_purge(tfile); sock_put(&tfile->sk); @@ -631,7 +701,8 @@ static void tun_detach_all(struct net_device *dev) module_put(THIS_MODULE); } -static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filter) +static int tun_attach(struct tun_struct *tun, struct file *file, + bool skip_filter, bool napi) { struct tun_file *tfile = file->private_data; struct net_device *dev = tun->dev; @@ -677,10 +748,12 @@ static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filte rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile); tun->numqueues++; - if (tfile->detached) + if (tfile->detached) { tun_enable_queue(tfile); - else + } else { sock_hold(&tfile->sk); + tun_napi_init(tun, tfile, napi); + } tun_set_real_num_queues(tun); @@ -956,13 +1029,28 @@ static void tun_poll_controller(struct net_device *dev) * Tun only receives frames when: * 1) the char device endpoint gets data from user space * 2) the tun socket gets a sendmsg call from user space - * Since both of those are synchronous operations, we are guaranteed - * never to have pending data when we poll for it - * so there is nothing to do here but return. + * If NAPI is not enabled, since both of those are synchronous + * operations, we are guaranteed never to have pending data when we poll + * for it so there is nothing to do here but return. * We need this though so netpoll recognizes us as an interface that * supports polling, which enables bridge devices in virt setups to * still use netconsole + * If NAPI is enabled, however, we need to schedule polling for all + * queues. */ + struct tun_struct *tun = netdev_priv(dev); + + if (tun->flags & IFF_NAPI) { + struct tun_file *tfile; + int i; + + rcu_read_lock(); + for (i = 0; i < tun->numqueues; i++) { + tfile = rcu_dereference(tun->tfiles[i]); + napi_schedule(&tfile->napi); + } + rcu_read_unlock(); + } return; } #endif @@ -1549,11 +1637,25 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, } rxhash = __skb_get_hash_symmetric(skb); -#ifndef CONFIG_4KSTACKS - tun_rx_batched(tun, tfile, skb, more); -#else - netif_rx_ni(skb); -#endif + + if (tun->flags & IFF_NAPI) { + struct sk_buff_head *queue = &tfile->sk.sk_write_queue; + int queue_len; + + spin_lock_bh(&queue->lock); + __skb_queue_tail(queue, skb); + queue_len = skb_queue_len(queue); + spin_unlock(&queue->lock); + + if (!more || queue_len > NAPI_POLL_WEIGHT) + napi_schedule(&tfile->napi); + + local_bh_enable(); + } else if (!IS_ENABLED(CONFIG_4KSTACKS)) { + tun_rx_batched(tun, tfile, skb, more); + } else { + netif_rx_ni(skb); + } stats = get_cpu_ptr(tun->pcpu_stats); u64_stats_update_begin(&stats->syncp); @@ -1980,7 +2082,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) if (err < 0) return err; - err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER); + err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER, + ifr->ifr_flags & IFF_NAPI); if (err < 0) return err; @@ -2066,7 +2169,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) NETIF_F_HW_VLAN_STAG_TX); INIT_LIST_HEAD(&tun->disabled); - err = tun_attach(tun, file, false); + err = tun_attach(tun, file, false, ifr->ifr_flags & IFF_NAPI); if (err < 0) goto err_free_flow; @@ -2216,7 +2319,7 @@ static int tun_set_queue(struct file *file, struct ifreq *ifr) ret = security_tun_dev_attach_queue(tun->security); if (ret < 0) goto unlock; - ret = tun_attach(tun, file, false); + ret = tun_attach(tun, file, false, tun->flags & IFF_NAPI); } else if (ifr->ifr_flags & IFF_DETACH_QUEUE) { tun = rtnl_dereference(tfile->tun); if (!tun || !(tun->flags & IFF_MULTI_QUEUE) || tfile->detached) diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h index 3cb5e1d85ddd..30b6184884eb 100644 --- a/include/uapi/linux/if_tun.h +++ b/include/uapi/linux/if_tun.h @@ -60,6 +60,7 @@ /* TUNSETIFF ifr flags */ #define IFF_TUN 0x0001 #define IFF_TAP 0x0002 +#define IFF_NAPI 0x0010 #define IFF_NO_PI 0x1000 /* This flag has no real effect */ #define IFF_ONE_QUEUE 0x2000 -- cgit v1.2.3-71-gd317 From 90e33d45940793def6f773b2d528e9f3c84ffdc7 Mon Sep 17 00:00:00 2001 From: Petar Penkov Date: Fri, 22 Sep 2017 13:49:15 -0700 Subject: tun: enable napi_gro_frags() for TUN/TAP driver Add a TUN/TAP receive mode that exercises the napi_gro_frags() interface. This mode is available only in TAP mode, as the interface expects packets with Ethernet headers. Furthermore, packets follow the layout of the iovec_iter that was received. The first iovec is the linear data, and every one after the first is a fragment. If there are more fragments than the max number, drop the packet. Additionally, invoke eth_get_headlen() to exercise flow dissector code and to verify that the header resides in the linear data. The napi_gro_frags() mode requires setting the IFF_NAPI_FRAGS option. This is imposed because this mode is intended for testing via tools like syzkaller and packetdrill, and the increased flexibility it provides can introduce security vulnerabilities. This flag is accepted only if the device is in TAP mode and has the IFF_NAPI flag set as well. This is done because both of these are explicit requirements for correct operation in this mode. Signed-off-by: Petar Penkov Cc: Eric Dumazet Cc: Mahesh Bandewar Cc: Willem de Bruijn Cc: davem@davemloft.net Cc: ppenkov@stanford.edu Acked-by: Mahesh Bandewar Signed-off-by: David S. Miller --- drivers/net/tun.c | 134 ++++++++++++++++++++++++++++++++++++++++++-- include/uapi/linux/if_tun.h | 1 + 2 files changed, 129 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/tun.c b/drivers/net/tun.c index f16407242b18..9880b3bc8fa5 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -75,6 +75,7 @@ #include #include #include +#include #include @@ -121,7 +122,8 @@ do { \ #define TUN_VNET_BE 0x40000000 #define TUN_FEATURES (IFF_NO_PI | IFF_ONE_QUEUE | IFF_VNET_HDR | \ - IFF_MULTI_QUEUE | IFF_NAPI) + IFF_MULTI_QUEUE | IFF_NAPI | IFF_NAPI_FRAGS) + #define GOODCOPY_LEN 128 #define FLT_EXACT_COUNT 8 @@ -173,6 +175,7 @@ struct tun_file { unsigned int ifindex; }; struct napi_struct napi; + struct mutex napi_mutex; /* Protects access to the above napi */ struct list_head next; struct tun_struct *detached; struct skb_array tx_array; @@ -277,6 +280,7 @@ static void tun_napi_init(struct tun_struct *tun, struct tun_file *tfile, netif_napi_add(tun->dev, &tfile->napi, tun_napi_poll, NAPI_POLL_WEIGHT); napi_enable(&tfile->napi); + mutex_init(&tfile->napi_mutex); } } @@ -292,6 +296,11 @@ static void tun_napi_del(struct tun_struct *tun, struct tun_file *tfile) netif_napi_del(&tfile->napi); } +static bool tun_napi_frags_enabled(const struct tun_struct *tun) +{ + return READ_ONCE(tun->flags) & IFF_NAPI_FRAGS; +} + #ifdef CONFIG_TUN_VNET_CROSS_LE static inline bool tun_legacy_is_little_endian(struct tun_struct *tun) { @@ -1036,7 +1045,8 @@ static void tun_poll_controller(struct net_device *dev) * supports polling, which enables bridge devices in virt setups to * still use netconsole * If NAPI is enabled, however, we need to schedule polling for all - * queues. + * queues unless we are using napi_gro_frags(), which we call in + * process context and not in NAPI context. */ struct tun_struct *tun = netdev_priv(dev); @@ -1044,6 +1054,9 @@ static void tun_poll_controller(struct net_device *dev) struct tun_file *tfile; int i; + if (tun_napi_frags_enabled(tun)) + return; + rcu_read_lock(); for (i = 0; i < tun->numqueues; i++) { tfile = rcu_dereference(tun->tfiles[i]); @@ -1266,6 +1279,64 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait) return mask; } +static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile, + size_t len, + const struct iov_iter *it) +{ + struct sk_buff *skb; + size_t linear; + int err; + int i; + + if (it->nr_segs > MAX_SKB_FRAGS + 1) + return ERR_PTR(-ENOMEM); + + local_bh_disable(); + skb = napi_get_frags(&tfile->napi); + local_bh_enable(); + if (!skb) + return ERR_PTR(-ENOMEM); + + linear = iov_iter_single_seg_count(it); + err = __skb_grow(skb, linear); + if (err) + goto free; + + skb->len = len; + skb->data_len = len - linear; + skb->truesize += skb->data_len; + + for (i = 1; i < it->nr_segs; i++) { + size_t fragsz = it->iov[i].iov_len; + unsigned long offset; + struct page *page; + void *data; + + if (fragsz == 0 || fragsz > PAGE_SIZE) { + err = -EINVAL; + goto free; + } + + local_bh_disable(); + data = napi_alloc_frag(fragsz); + local_bh_enable(); + if (!data) { + err = -ENOMEM; + goto free; + } + + page = virt_to_head_page(data); + offset = data - page_address(page); + skb_fill_page_desc(skb, i - 1, page, offset, fragsz); + } + + return skb; +free: + /* frees skb and all frags allocated with napi_alloc_frag() */ + napi_free_frags(&tfile->napi); + return ERR_PTR(err); +} + /* prepad is the amount to reserve at front. len is length after that. * linear is a hint as to how much to copy (usually headers). */ static struct sk_buff *tun_alloc_skb(struct tun_file *tfile, @@ -1478,6 +1549,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, int err; u32 rxhash; int skb_xdp = 1; + bool frags = tun_napi_frags_enabled(tun); if (!(tun->dev->flags & IFF_UP)) return -EIO; @@ -1535,7 +1607,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, zerocopy = true; } - if (tun_can_build_skb(tun, tfile, len, noblock, zerocopy)) { + if (!frags && tun_can_build_skb(tun, tfile, len, noblock, zerocopy)) { /* For the packet that is not easy to be processed * (e.g gso or jumbo packet), we will do it at after * skb was created with generic XDP routine. @@ -1556,10 +1628,24 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, linear = tun16_to_cpu(tun, gso.hdr_len); } - skb = tun_alloc_skb(tfile, align, copylen, linear, noblock); + if (frags) { + mutex_lock(&tfile->napi_mutex); + skb = tun_napi_alloc_frags(tfile, copylen, from); + /* tun_napi_alloc_frags() enforces a layout for the skb. + * If zerocopy is enabled, then this layout will be + * overwritten by zerocopy_sg_from_iter(). + */ + zerocopy = false; + } else { + skb = tun_alloc_skb(tfile, align, copylen, linear, + noblock); + } + if (IS_ERR(skb)) { if (PTR_ERR(skb) != -EAGAIN) this_cpu_inc(tun->pcpu_stats->rx_dropped); + if (frags) + mutex_unlock(&tfile->napi_mutex); return PTR_ERR(skb); } @@ -1571,6 +1657,11 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, if (err) { this_cpu_inc(tun->pcpu_stats->rx_dropped); kfree_skb(skb); + if (frags) { + tfile->napi.skb = NULL; + mutex_unlock(&tfile->napi_mutex); + } + return -EFAULT; } } @@ -1578,6 +1669,11 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, if (virtio_net_hdr_to_skb(skb, &gso, tun_is_little_endian(tun))) { this_cpu_inc(tun->pcpu_stats->rx_frame_errors); kfree_skb(skb); + if (frags) { + tfile->napi.skb = NULL; + mutex_unlock(&tfile->napi_mutex); + } + return -EINVAL; } @@ -1603,7 +1699,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, skb->dev = tun->dev; break; case IFF_TAP: - skb->protocol = eth_type_trans(skb, tun->dev); + if (!frags) + skb->protocol = eth_type_trans(skb, tun->dev); break; } @@ -1638,7 +1735,23 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, rxhash = __skb_get_hash_symmetric(skb); - if (tun->flags & IFF_NAPI) { + if (frags) { + /* Exercise flow dissector code path. */ + u32 headlen = eth_get_headlen(skb->data, skb_headlen(skb)); + + if (headlen > skb_headlen(skb) || headlen < ETH_HLEN) { + this_cpu_inc(tun->pcpu_stats->rx_dropped); + napi_free_frags(&tfile->napi); + mutex_unlock(&tfile->napi_mutex); + WARN_ON(1); + return -ENOMEM; + } + + local_bh_disable(); + napi_gro_frags(&tfile->napi); + local_bh_enable(); + mutex_unlock(&tfile->napi_mutex); + } else if (tun->flags & IFF_NAPI) { struct sk_buff_head *queue = &tfile->sk.sk_write_queue; int queue_len; @@ -2061,6 +2174,15 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) if (tfile->detached) return -EINVAL; + if ((ifr->ifr_flags & IFF_NAPI_FRAGS)) { + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (!(ifr->ifr_flags & IFF_NAPI) || + (ifr->ifr_flags & TUN_TYPE_MASK) != IFF_TAP) + return -EINVAL; + } + dev = __dev_get_by_name(net, ifr->ifr_name); if (dev) { if (ifr->ifr_flags & IFF_TUN_EXCL) diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h index 30b6184884eb..365ade5685c9 100644 --- a/include/uapi/linux/if_tun.h +++ b/include/uapi/linux/if_tun.h @@ -61,6 +61,7 @@ #define IFF_TUN 0x0001 #define IFF_TAP 0x0002 #define IFF_NAPI 0x0010 +#define IFF_NAPI_FRAGS 0x0020 #define IFF_NO_PI 0x1000 /* This flag has no real effect */ #define IFF_ONE_QUEUE 0x2000 -- cgit v1.2.3-71-gd317 From de8f3a83b0a0fddb2cf56e7a718127e9619ea3da Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 25 Sep 2017 02:25:51 +0200 Subject: bpf: add meta pointer for direct access This work enables generic transfer of metadata from XDP into skb. The basic idea is that we can make use of the fact that the resulting skb must be linear and already comes with a larger headroom for supporting bpf_xdp_adjust_head(), which mangles xdp->data. Here, we base our work on a similar principle and introduce a small helper bpf_xdp_adjust_meta() for adjusting a new pointer called xdp->data_meta. Thus, the packet has a flexible and programmable room for meta data, followed by the actual packet data. struct xdp_buff is therefore laid out that we first point to data_hard_start, then data_meta directly prepended to data followed by data_end marking the end of packet. bpf_xdp_adjust_head() takes into account whether we have meta data already prepended and if so, memmove()s this along with the given offset provided there's enough room. xdp->data_meta is optional and programs are not required to use it. The rationale is that when we process the packet in XDP (e.g. as DoS filter), we can push further meta data along with it for the XDP_PASS case, and give the guarantee that a clsact ingress BPF program on the same device can pick this up for further post-processing. Since we work with skb there, we can also set skb->mark, skb->priority or other skb meta data out of BPF, thus having this scratch space generic and programmable allows for more flexibility than defining a direct 1:1 transfer of potentially new XDP members into skb (it's also more efficient as we don't need to initialize/handle each of such new members). The facility also works together with GRO aggregation. The scratch space at the head of the packet can be multiple of 4 byte up to 32 byte large. Drivers not yet supporting xdp->data_meta can simply be set up with xdp->data_meta as xdp->data + 1 as bpf_xdp_adjust_meta() will detect this and bail out, such that the subsequent match against xdp->data for later access is guaranteed to fail. The verifier treats xdp->data_meta/xdp->data the same way as we treat xdp->data/xdp->data_end pointer comparisons. The requirement for doing the compare against xdp->data is that it hasn't been modified from it's original address we got from ctx access. It may have a range marking already from prior successful xdp->data/xdp->data_end pointer comparisons though. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: John Fastabend Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 1 + drivers/net/ethernet/cavium/thunder/nicvf_main.c | 1 + drivers/net/ethernet/intel/i40e/i40e_txrx.c | 1 + drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 1 + drivers/net/ethernet/mellanox/mlx4/en_rx.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 1 + .../net/ethernet/netronome/nfp/nfp_net_common.c | 1 + drivers/net/ethernet/qlogic/qede/qede_fp.c | 1 + drivers/net/tun.c | 1 + drivers/net/virtio_net.c | 2 + include/linux/bpf.h | 1 + include/linux/filter.h | 21 +++- include/linux/skbuff.h | 68 +++++++++++- include/uapi/linux/bpf.h | 13 ++- kernel/bpf/verifier.c | 114 ++++++++++++++++----- net/bpf/test_run.c | 1 + net/core/dev.c | 31 +++++- net/core/filter.c | 77 +++++++++++++- net/core/skbuff.c | 2 + 19 files changed, 297 insertions(+), 42 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index d8f0c837b72c..06ce63c00821 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -94,6 +94,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, xdp.data_hard_start = *data_ptr - offset; xdp.data = *data_ptr; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = *data_ptr + *len; orig_data = xdp.data; mapping = rx_buf->mapping - bp->rx_dma_offset; diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 49b80da51ba7..d68478afccbf 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -523,6 +523,7 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog, xdp.data_hard_start = page_address(page); xdp.data = (void *)cpu_addr; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + len; orig_data = xdp.data; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 1519dfb851d0..f426762bd83a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2107,6 +2107,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) if (!skb) { xdp.data = page_address(rx_buffer->page) + rx_buffer->page_offset; + xdp_set_data_meta_invalid(&xdp); xdp.data_hard_start = xdp.data - i40e_rx_offset(rx_ring); xdp.data_end = xdp.data + size; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index d962368d08d0..04bb03bda1cd 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2326,6 +2326,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, if (!skb) { xdp.data = page_address(rx_buffer->page) + rx_buffer->page_offset; + xdp_set_data_meta_invalid(&xdp); xdp.data_hard_start = xdp.data - ixgbe_rx_offset(rx_ring); xdp.data_end = xdp.data + size; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index b97a55c827eb..8f9cb8abc497 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -762,6 +762,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud xdp.data_hard_start = va - frags[0].page_offset; xdp.data = va; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + length; orig_data = xdp.data; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index f1dd638384d3..30b3f3fbd719 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -794,6 +794,7 @@ static inline int mlx5e_xdp_handle(struct mlx5e_rq *rq, return false; xdp.data = va + *rx_headroom; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + *len; xdp.data_hard_start = va; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 1c0187f0af51..e3a38be3600a 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -1583,6 +1583,7 @@ static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, void *hard_start, xdp.data_hard_start = hard_start; xdp.data = data + *off; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = data + *off + *len; orig_data = xdp.data; diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index 6fc854b120b0..48ec4c56cddf 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -1004,6 +1004,7 @@ static bool qede_rx_xdp(struct qede_dev *edev, xdp.data_hard_start = page_address(bd->data); xdp.data = xdp.data_hard_start + *data_offset; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + *len; /* Queues always have a full reset currently, so for the time diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 2c36f6ebad79..a6e0bffe3d29 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1468,6 +1468,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, xdp.data_hard_start = buf; xdp.data = buf + pad; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + len; orig_data = xdp.data; act = bpf_prog_run_xdp(xdp_prog, &xdp); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index dd14a4547932..fc059f193e7d 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -554,6 +554,7 @@ static struct sk_buff *receive_small(struct net_device *dev, xdp.data_hard_start = buf + VIRTNET_RX_PAD + vi->hdr_len; xdp.data = xdp.data_hard_start + xdp_headroom; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + len; orig_data = xdp.data; act = bpf_prog_run_xdp(xdp_prog, &xdp); @@ -686,6 +687,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, data = page_address(xdp_page) + offset; xdp.data_hard_start = data - VIRTIO_XDP_HEADROOM + vi->hdr_len; xdp.data = data + vi->hdr_len; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + (len - vi->hdr_len); act = bpf_prog_run_xdp(xdp_prog, &xdp); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8390859e79e7..2b672c50f160 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -137,6 +137,7 @@ enum bpf_reg_type { PTR_TO_MAP_VALUE, /* reg points to map element value */ PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */ PTR_TO_STACK, /* reg == frame_pointer + offset */ + PTR_TO_PACKET_META, /* skb->data - meta_len */ PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ }; diff --git a/include/linux/filter.h b/include/linux/filter.h index 052bab3d62e7..911d454af107 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -487,12 +487,14 @@ struct sk_filter { struct bpf_skb_data_end { struct qdisc_skb_cb qdisc_cb; + void *data_meta; void *data_end; }; struct xdp_buff { void *data; void *data_end; + void *data_meta; void *data_hard_start; }; @@ -507,7 +509,8 @@ 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)); - cb->data_end = skb->data + skb_headlen(skb); + cb->data_meta = skb->data - skb_metadata_len(skb); + cb->data_end = skb->data + skb_headlen(skb); } static inline u8 *bpf_skb_cb(struct sk_buff *skb) @@ -728,8 +731,22 @@ int xdp_do_redirect(struct net_device *dev, struct bpf_prog *prog); void xdp_do_flush_map(void); +/* Drivers not supporting XDP metadata can use this helper, which + * rejects any room expansion for metadata as a result. + */ +static __always_inline void +xdp_set_data_meta_invalid(struct xdp_buff *xdp) +{ + xdp->data_meta = xdp->data + 1; +} + +static __always_inline bool +xdp_data_meta_unsupported(const struct xdp_buff *xdp) +{ + return unlikely(xdp->data_meta > xdp->data); +} + void bpf_warn_invalid_xdp_action(u32 act); -void bpf_warn_invalid_xdp_redirect(u32 ifindex); struct sock *do_sk_redirect_map(void); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f9db5539a6fb..19e64bfb1a66 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -489,8 +489,9 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, * the end of the header data, ie. at skb->end. */ struct skb_shared_info { - unsigned short _unused; - unsigned char nr_frags; + __u8 __unused; + __u8 meta_len; + __u8 nr_frags; __u8 tx_flags; unsigned short gso_size; /* Warning: this field is not always filled in (UFO)! */ @@ -3400,6 +3401,69 @@ static inline ktime_t net_invalid_timestamp(void) return 0; } +static inline u8 skb_metadata_len(const struct sk_buff *skb) +{ + return skb_shinfo(skb)->meta_len; +} + +static inline void *skb_metadata_end(const struct sk_buff *skb) +{ + return skb_mac_header(skb); +} + +static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, + const struct sk_buff *skb_b, + u8 meta_len) +{ + const void *a = skb_metadata_end(skb_a); + const void *b = skb_metadata_end(skb_b); + /* Using more efficient varaiant than plain call to memcmp(). */ +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 + u64 diffs = 0; + + switch (meta_len) { +#define __it(x, op) (x -= sizeof(u##op)) +#define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op)) + case 32: diffs |= __it_diff(a, b, 64); + case 24: diffs |= __it_diff(a, b, 64); + case 16: diffs |= __it_diff(a, b, 64); + case 8: diffs |= __it_diff(a, b, 64); + break; + case 28: diffs |= __it_diff(a, b, 64); + case 20: diffs |= __it_diff(a, b, 64); + case 12: diffs |= __it_diff(a, b, 64); + case 4: diffs |= __it_diff(a, b, 32); + break; + } + return diffs; +#else + return memcmp(a - meta_len, b - meta_len, meta_len); +#endif +} + +static inline bool skb_metadata_differs(const struct sk_buff *skb_a, + const struct sk_buff *skb_b) +{ + u8 len_a = skb_metadata_len(skb_a); + u8 len_b = skb_metadata_len(skb_b); + + if (!(len_a | len_b)) + return false; + + return len_a != len_b ? + true : __skb_metadata_differs(skb_a, skb_b, len_a); +} + +static inline void skb_metadata_set(struct sk_buff *skb, u8 meta_len) +{ + skb_shinfo(skb)->meta_len = meta_len; +} + +static inline void skb_metadata_clear(struct sk_buff *skb) +{ + skb_metadata_set(skb, 0); +} + struct sk_buff *skb_clone_sk(struct sk_buff *skb); #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 43ab5c402f98..e43491ac4823 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -582,6 +582,12 @@ union bpf_attr { * @map: pointer to sockmap to update * @key: key to insert/update sock in map * @flags: same flags as map update elem + * + * int bpf_xdp_adjust_meta(xdp_md, delta) + * Adjust the xdp_md.data_meta by delta + * @xdp_md: pointer to xdp_md + * @delta: An positive/negative integer to be added to xdp_md.data_meta + * Return: 0 on success or negative on error */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -638,6 +644,7 @@ union bpf_attr { FN(redirect_map), \ FN(sk_redirect_map), \ FN(sock_map_update), \ + FN(xdp_adjust_meta), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -715,7 +722,7 @@ struct __sk_buff { __u32 data_end; __u32 napi_id; - /* accessed by BPF_PROG_TYPE_sk_skb types */ + /* Accessed by BPF_PROG_TYPE_sk_skb types from here to ... */ __u32 family; __u32 remote_ip4; /* Stored in network byte order */ __u32 local_ip4; /* Stored in network byte order */ @@ -723,6 +730,9 @@ struct __sk_buff { __u32 local_ip6[4]; /* Stored in network byte order */ __u32 remote_port; /* Stored in network byte order */ __u32 local_port; /* stored in host byte order */ + /* ... here. */ + + __u32 data_meta; }; struct bpf_tunnel_key { @@ -783,6 +793,7 @@ enum xdp_action { struct xdp_md { __u32 data; __u32 data_end; + __u32 data_meta; }; enum sk_action { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b914fbe1383e..f849eca36052 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -177,6 +177,12 @@ static __printf(1, 2) void verbose(const char *fmt, ...) va_end(args); } +static bool type_is_pkt_pointer(enum bpf_reg_type type) +{ + return type == PTR_TO_PACKET || + type == PTR_TO_PACKET_META; +} + /* string representation of 'enum bpf_reg_type' */ static const char * const reg_type_str[] = { [NOT_INIT] = "?", @@ -187,6 +193,7 @@ static const char * const reg_type_str[] = { [PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null", [PTR_TO_STACK] = "fp", [PTR_TO_PACKET] = "pkt", + [PTR_TO_PACKET_META] = "pkt_meta", [PTR_TO_PACKET_END] = "pkt_end", }; @@ -226,7 +233,7 @@ static void print_verifier_state(struct bpf_verifier_state *state) verbose("(id=%d", reg->id); if (t != SCALAR_VALUE) verbose(",off=%d", reg->off); - if (t == PTR_TO_PACKET) + if (type_is_pkt_pointer(t)) verbose(",r=%d", reg->range); else if (t == CONST_PTR_TO_MAP || t == PTR_TO_MAP_VALUE || @@ -519,6 +526,31 @@ static void mark_reg_known_zero(struct bpf_reg_state *regs, u32 regno) __mark_reg_known_zero(regs + regno); } +static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg) +{ + return type_is_pkt_pointer(reg->type); +} + +static bool reg_is_pkt_pointer_any(const struct bpf_reg_state *reg) +{ + return reg_is_pkt_pointer(reg) || + reg->type == PTR_TO_PACKET_END; +} + +/* Unmodified PTR_TO_PACKET[_META,_END] register from ctx access. */ +static bool reg_is_init_pkt_pointer(const struct bpf_reg_state *reg, + enum bpf_reg_type which) +{ + /* The register can already have a range from prior markings. + * This is fine as long as it hasn't been advanced from its + * origin. + */ + return reg->type == which && + reg->id == 0 && + reg->off == 0 && + tnum_equals_const(reg->var_off, 0); +} + /* Attempts to improve min/max values based on var_off information */ static void __update_reg_bounds(struct bpf_reg_state *reg) { @@ -702,6 +734,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_STACK: case PTR_TO_CTX: case PTR_TO_PACKET: + case PTR_TO_PACKET_META: case PTR_TO_PACKET_END: case CONST_PTR_TO_MAP: return true; @@ -1047,7 +1080,10 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, switch (reg->type) { case PTR_TO_PACKET: - /* special case, because of NET_IP_ALIGN */ + case PTR_TO_PACKET_META: + /* Special case, because of NET_IP_ALIGN. Given metadata sits + * right in front, treat it the very same way. + */ return check_pkt_ptr_alignment(reg, off, size, strict); case PTR_TO_MAP_VALUE: pointer_desc = "value "; @@ -1124,8 +1160,8 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn err = check_ctx_access(env, insn_idx, off, size, t, ®_type); if (!err && t == BPF_READ && value_regno >= 0) { /* ctx access returns either a scalar, or a - * PTR_TO_PACKET[_END]. In the latter case, we know - * the offset is zero. + * PTR_TO_PACKET[_META,_END]. In the latter + * case, we know the offset is zero. */ if (reg_type == SCALAR_VALUE) mark_reg_unknown(state->regs, value_regno); @@ -1170,7 +1206,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn } else { err = check_stack_read(state, off, size, value_regno); } - } else if (reg->type == PTR_TO_PACKET) { + } else if (reg_is_pkt_pointer(reg)) { if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) { verbose("cannot write into packet\n"); return -EACCES; @@ -1310,6 +1346,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, switch (reg->type) { case PTR_TO_PACKET: + case PTR_TO_PACKET_META: return check_packet_access(env, regno, reg->off, access_size); case PTR_TO_MAP_VALUE: return check_map_access(env, regno, reg->off, access_size); @@ -1342,7 +1379,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, return 0; } - if (type == PTR_TO_PACKET && + if (type_is_pkt_pointer(type) && !may_access_direct_pkt_data(env, meta, BPF_READ)) { verbose("helper access to the packet is not allowed\n"); return -EACCES; @@ -1351,7 +1388,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, if (arg_type == ARG_PTR_TO_MAP_KEY || arg_type == ARG_PTR_TO_MAP_VALUE) { expected_type = PTR_TO_STACK; - if (type != PTR_TO_PACKET && type != expected_type) + if (!type_is_pkt_pointer(type) && + type != expected_type) goto err_type; } else if (arg_type == ARG_CONST_SIZE || arg_type == ARG_CONST_SIZE_OR_ZERO) { @@ -1375,7 +1413,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, */ if (register_is_null(*reg)) /* final test in check_stack_boundary() */; - else if (type != PTR_TO_PACKET && type != PTR_TO_MAP_VALUE && + else if (!type_is_pkt_pointer(type) && + type != PTR_TO_MAP_VALUE && type != expected_type) goto err_type; meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM; @@ -1401,7 +1440,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, verbose("invalid map_ptr to access map->key\n"); return -EACCES; } - if (type == PTR_TO_PACKET) + if (type_is_pkt_pointer(type)) err = check_packet_access(env, regno, reg->off, meta->map_ptr->key_size); else @@ -1417,7 +1456,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, verbose("invalid map_ptr to access map->value\n"); return -EACCES; } - if (type == PTR_TO_PACKET) + if (type_is_pkt_pointer(type)) err = check_packet_access(env, regno, reg->off, meta->map_ptr->value_size); else @@ -1590,8 +1629,8 @@ static int check_raw_mode(const struct bpf_func_proto *fn) return count > 1 ? -EINVAL : 0; } -/* Packet data might have moved, any old PTR_TO_PACKET[_END] are now invalid, - * so turn them into unknown SCALAR_VALUE. +/* Packet data might have moved, any old PTR_TO_PACKET[_META,_END] + * are now invalid, so turn them into unknown SCALAR_VALUE. */ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) { @@ -1600,18 +1639,15 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) int i; for (i = 0; i < MAX_BPF_REG; i++) - if (regs[i].type == PTR_TO_PACKET || - regs[i].type == PTR_TO_PACKET_END) + if (reg_is_pkt_pointer_any(®s[i])) mark_reg_unknown(regs, i); for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { if (state->stack_slot_type[i] != STACK_SPILL) continue; reg = &state->spilled_regs[i / BPF_REG_SIZE]; - if (reg->type != PTR_TO_PACKET && - reg->type != PTR_TO_PACKET_END) - continue; - __mark_reg_unknown(reg); + if (reg_is_pkt_pointer_any(reg)) + __mark_reg_unknown(reg); } } @@ -1871,7 +1907,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; - if (ptr_reg->type == PTR_TO_PACKET) { + if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ dst_reg->range = 0; @@ -1931,7 +1967,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; - if (ptr_reg->type == PTR_TO_PACKET) { + if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ if (smin_val < 0) @@ -2421,7 +2457,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } static void find_good_pkt_pointers(struct bpf_verifier_state *state, - struct bpf_reg_state *dst_reg) + struct bpf_reg_state *dst_reg, + enum bpf_reg_type type) { struct bpf_reg_state *regs = state->regs, *reg; int i; @@ -2483,7 +2520,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, * dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16. */ for (i = 0; i < MAX_BPF_REG; i++) - if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id) + if (regs[i].type == type && regs[i].id == dst_reg->id) /* keep the maximum range already checked */ regs[i].range = max_t(u16, regs[i].range, dst_reg->off); @@ -2491,7 +2528,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, if (state->stack_slot_type[i] != STACK_SPILL) continue; reg = &state->spilled_regs[i / BPF_REG_SIZE]; - if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id) + if (reg->type == type && reg->id == dst_reg->id) reg->range = max_t(u16, reg->range, dst_reg->off); } } @@ -2856,19 +2893,39 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT && dst_reg->type == PTR_TO_PACKET && regs[insn->src_reg].type == PTR_TO_PACKET_END) { - find_good_pkt_pointers(this_branch, dst_reg); + find_good_pkt_pointers(this_branch, dst_reg, PTR_TO_PACKET); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT && dst_reg->type == PTR_TO_PACKET && regs[insn->src_reg].type == PTR_TO_PACKET_END) { - find_good_pkt_pointers(other_branch, dst_reg); + find_good_pkt_pointers(other_branch, dst_reg, PTR_TO_PACKET); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE && dst_reg->type == PTR_TO_PACKET_END && regs[insn->src_reg].type == PTR_TO_PACKET) { - find_good_pkt_pointers(other_branch, ®s[insn->src_reg]); + find_good_pkt_pointers(other_branch, ®s[insn->src_reg], + PTR_TO_PACKET); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE && dst_reg->type == PTR_TO_PACKET_END && regs[insn->src_reg].type == PTR_TO_PACKET) { - find_good_pkt_pointers(this_branch, ®s[insn->src_reg]); + find_good_pkt_pointers(this_branch, ®s[insn->src_reg], + PTR_TO_PACKET); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT && + dst_reg->type == PTR_TO_PACKET_META && + reg_is_init_pkt_pointer(®s[insn->src_reg], PTR_TO_PACKET)) { + find_good_pkt_pointers(this_branch, dst_reg, PTR_TO_PACKET_META); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT && + dst_reg->type == PTR_TO_PACKET_META && + reg_is_init_pkt_pointer(®s[insn->src_reg], PTR_TO_PACKET)) { + find_good_pkt_pointers(other_branch, dst_reg, PTR_TO_PACKET_META); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE && + reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && + regs[insn->src_reg].type == PTR_TO_PACKET_META) { + find_good_pkt_pointers(other_branch, ®s[insn->src_reg], + PTR_TO_PACKET_META); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE && + reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && + regs[insn->src_reg].type == PTR_TO_PACKET_META) { + find_good_pkt_pointers(this_branch, ®s[insn->src_reg], + PTR_TO_PACKET_META); } else if (is_pointer_value(env, insn->dst_reg)) { verbose("R%d pointer comparison prohibited\n", insn->dst_reg); return -EACCES; @@ -3298,8 +3355,9 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, return false; /* Check our ids match any regs they're supposed to */ return check_ids(rold->id, rcur->id, idmap); + case PTR_TO_PACKET_META: case PTR_TO_PACKET: - if (rcur->type != PTR_TO_PACKET) + if (rcur->type != rold->type) return false; /* We must have at least as much range as the old ptr * did, so that any accesses which were safe before are diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index df672517b4fd..a86e6687026e 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -162,6 +162,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, xdp.data_hard_start = data; xdp.data = data + XDP_PACKET_HEADROOM + NET_IP_ALIGN; + xdp.data_meta = xdp.data; xdp.data_end = xdp.data + size; retval = bpf_test_run(prog, &xdp, repeat, &duration); diff --git a/net/core/dev.c b/net/core/dev.c index 97abddd9039a..e350c768d4b5 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3864,8 +3864,8 @@ drop: static u32 netif_receive_generic_xdp(struct sk_buff *skb, struct bpf_prog *xdp_prog) { + u32 metalen, act = XDP_DROP; struct xdp_buff xdp; - u32 act = XDP_DROP; void *orig_data; int hlen, off; u32 mac_len; @@ -3876,8 +3876,25 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, if (skb_cloned(skb)) return XDP_PASS; - if (skb_linearize(skb)) - goto do_drop; + /* XDP packets must be linear and must have sufficient headroom + * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also + * native XDP provides, thus we need to do it here as well. + */ + if (skb_is_nonlinear(skb) || + skb_headroom(skb) < XDP_PACKET_HEADROOM) { + int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb); + int troom = skb->tail + skb->data_len - skb->end; + + /* In case we have to go down the path and also linearize, + * then lets do the pskb_expand_head() work just once here. + */ + if (pskb_expand_head(skb, + hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0, + troom > 0 ? troom + 128 : 0, GFP_ATOMIC)) + goto do_drop; + if (troom > 0 && __skb_linearize(skb)) + goto do_drop; + } /* The XDP program wants to see the packet starting at the MAC * header. @@ -3885,6 +3902,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, mac_len = skb->data - skb_mac_header(skb); hlen = skb_headlen(skb) + mac_len; xdp.data = skb->data - mac_len; + xdp.data_meta = xdp.data; xdp.data_end = xdp.data + hlen; xdp.data_hard_start = skb->data - skb_headroom(skb); orig_data = xdp.data; @@ -3902,10 +3920,12 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, case XDP_REDIRECT: case XDP_TX: __skb_push(skb, mac_len); - /* fall through */ + break; case XDP_PASS: + metalen = xdp.data - xdp.data_meta; + if (metalen) + skb_metadata_set(skb, metalen); break; - default: bpf_warn_invalid_xdp_action(act); /* fall through */ @@ -4695,6 +4715,7 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; diffs |= p->vlan_tci ^ skb->vlan_tci; diffs |= skb_metadata_dst_cmp(p, skb); + diffs |= skb_metadata_differs(p, skb); if (maclen == ETH_HLEN) diffs |= compare_ether_header(skb_mac_header(p), skb_mac_header(skb)); diff --git a/net/core/filter.c b/net/core/filter.c index c468e7cfad19..9b6e7e84aafd 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2447,14 +2447,26 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = { .arg3_type = ARG_ANYTHING, }; +static unsigned long xdp_get_metalen(const struct xdp_buff *xdp) +{ + return xdp_data_meta_unsupported(xdp) ? 0 : + xdp->data - xdp->data_meta; +} + BPF_CALL_2(bpf_xdp_adjust_head, struct xdp_buff *, xdp, int, offset) { + unsigned long metalen = xdp_get_metalen(xdp); + void *data_start = xdp->data_hard_start + metalen; void *data = xdp->data + offset; - if (unlikely(data < xdp->data_hard_start || + if (unlikely(data < data_start || data > xdp->data_end - ETH_HLEN)) return -EINVAL; + if (metalen) + memmove(xdp->data_meta + offset, + xdp->data_meta, metalen); + xdp->data_meta += offset; xdp->data = data; return 0; @@ -2468,6 +2480,33 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = { .arg2_type = ARG_ANYTHING, }; +BPF_CALL_2(bpf_xdp_adjust_meta, struct xdp_buff *, xdp, int, offset) +{ + void *meta = xdp->data_meta + offset; + unsigned long metalen = xdp->data - meta; + + if (xdp_data_meta_unsupported(xdp)) + return -ENOTSUPP; + if (unlikely(meta < xdp->data_hard_start || + meta > xdp->data)) + return -EINVAL; + if (unlikely((metalen & (sizeof(__u32) - 1)) || + (metalen > 32))) + return -EACCES; + + xdp->data_meta = meta; + + return 0; +} + +static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = { + .func = bpf_xdp_adjust_meta, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; + static int __bpf_tx_xdp(struct net_device *dev, struct bpf_map *map, struct xdp_buff *xdp, @@ -2692,7 +2731,8 @@ bool bpf_helper_changes_pkt_data(void *func) func == bpf_clone_redirect || func == bpf_l3_csum_replace || func == bpf_l4_csum_replace || - func == bpf_xdp_adjust_head) + func == bpf_xdp_adjust_head || + func == bpf_xdp_adjust_meta) return true; return false; @@ -3288,6 +3328,8 @@ xdp_func_proto(enum bpf_func_id func_id) return &bpf_get_smp_processor_id_proto; case BPF_FUNC_xdp_adjust_head: return &bpf_xdp_adjust_head_proto; + case BPF_FUNC_xdp_adjust_meta: + return &bpf_xdp_adjust_meta_proto; case BPF_FUNC_redirect: return &bpf_xdp_redirect_proto; case BPF_FUNC_redirect_map: @@ -3418,6 +3460,7 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type case bpf_ctx_range_till(struct __sk_buff, remote_ip4, remote_ip4): case bpf_ctx_range_till(struct __sk_buff, local_ip4, local_ip4): case bpf_ctx_range(struct __sk_buff, data): + case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): if (size != size_default) return false; @@ -3444,6 +3487,7 @@ static bool sk_filter_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data): + case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; @@ -3468,6 +3512,7 @@ static bool lwt_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range_till(struct __sk_buff, family, local_port): + case bpf_ctx_range(struct __sk_buff, data_meta): return false; } @@ -3586,6 +3631,9 @@ static bool tc_cls_act_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; + case bpf_ctx_range(struct __sk_buff, data_meta): + info->reg_type = PTR_TO_PACKET_META; + break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; @@ -3619,6 +3667,9 @@ static bool xdp_is_valid_access(int off, int size, case offsetof(struct xdp_md, data): info->reg_type = PTR_TO_PACKET; break; + case offsetof(struct xdp_md, data_meta): + info->reg_type = PTR_TO_PACKET_META; + break; case offsetof(struct xdp_md, data_end): info->reg_type = PTR_TO_PACKET_END; break; @@ -3677,6 +3728,12 @@ static bool sk_skb_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { + switch (off) { + case bpf_ctx_range(struct __sk_buff, tc_classid): + case bpf_ctx_range(struct __sk_buff, data_meta): + return false; + } + if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, mark): @@ -3689,8 +3746,6 @@ static bool sk_skb_is_valid_access(int off, int size, } switch (off) { - case bpf_ctx_range(struct __sk_buff, tc_classid): - return false; case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; @@ -3847,6 +3902,15 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, offsetof(struct sk_buff, data)); break; + case offsetof(struct __sk_buff, data_meta): + off = si->off; + off -= offsetof(struct __sk_buff, data_meta); + off += offsetof(struct sk_buff, cb); + off += offsetof(struct bpf_skb_data_end, data_meta); + *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, + si->src_reg, off); + break; + case offsetof(struct __sk_buff, data_end): off = si->off; off -= offsetof(struct __sk_buff, data_end); @@ -4095,6 +4159,11 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type, si->dst_reg, si->src_reg, offsetof(struct xdp_buff, data)); break; + case offsetof(struct xdp_md, data_meta): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_meta), + si->dst_reg, si->src_reg, + offsetof(struct xdp_buff, data_meta)); + break; case offsetof(struct xdp_md, data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_end), si->dst_reg, si->src_reg, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 000ce735fa8d..d98c2e3ce2bf 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1509,6 +1509,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, skb->nohdr = 0; atomic_set(&skb_shinfo(skb)->dataref, 1); + skb_metadata_clear(skb); + /* It is not generally safe to change skb->truesize. * For the moment, we really care of rx path, or * when skb is orphaned (not attached to a socket). -- cgit v1.2.3-71-gd317 From 262832bc5acda76fd8f901d39f4da1121d951222 Mon Sep 17 00:00:00 2001 From: Alice Frosi Date: Thu, 14 Sep 2017 12:36:03 +0200 Subject: s390/ptrace: add runtime instrumention register get/set Add runtime instrumention register get and set which allows to read and modify the runtime instrumention control block. Signed-off-by: Alice Frosi Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/ptrace.c | 109 ++++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/elf.h | 1 + 2 files changed, 110 insertions(+) (limited to 'include/uapi/linux') diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index a5f8f0c8ccf0..ea711f141bb8 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -30,6 +30,9 @@ #include #include #include +#include +#include + #include "entry.h" #ifdef CONFIG_COMPAT @@ -1239,6 +1242,96 @@ static int s390_gs_bc_set(struct task_struct *target, data, 0, sizeof(struct gs_cb)); } +static bool is_ri_cb_valid(struct runtime_instr_cb *cb) +{ + return (cb->rca & 0x1f) == 0 && + (cb->roa & 0xfff) == 0 && + (cb->rla & 0xfff) == 0xfff && + cb->s == 1 && + cb->k == 1 && + cb->h == 0 && + cb->reserved1 == 0 && + cb->ps == 1 && + cb->qs == 0 && + cb->pc == 1 && + cb->qc == 0 && + cb->reserved2 == 0 && + cb->key == PAGE_DEFAULT_KEY && + cb->reserved3 == 0 && + cb->reserved4 == 0 && + cb->reserved5 == 0 && + cb->reserved6 == 0 && + cb->reserved7 == 0 && + cb->reserved8 == 0 && + cb->rla >= cb->roa && + cb->rca >= cb->roa && + cb->rca <= cb->rla+1 && + cb->m < 3; +} + +static int s390_runtime_instr_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + struct runtime_instr_cb *data = target->thread.ri_cb; + + if (!test_facility(64)) + return -ENODEV; + if (!data) + return -ENODATA; + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + data, 0, sizeof(struct runtime_instr_cb)); +} + +static int s390_runtime_instr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct runtime_instr_cb ri_cb = { }, *data = NULL; + int rc; + + if (!test_facility(64)) + return -ENODEV; + + if (!target->thread.ri_cb) { + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + } + + if (target->thread.ri_cb) { + if (target == current) + store_runtime_instr_cb(&ri_cb); + else + ri_cb = *target->thread.ri_cb; + } + + rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &ri_cb, 0, sizeof(struct runtime_instr_cb)); + if (rc) { + kfree(data); + return -EFAULT; + } + + if (!is_ri_cb_valid(&ri_cb)) { + kfree(data); + return -EINVAL; + } + + preempt_disable(); + if (!target->thread.ri_cb) + target->thread.ri_cb = data; + *target->thread.ri_cb = ri_cb; + if (target == current) + load_runtime_instr_cb(target->thread.ri_cb); + preempt_enable(); + + return 0; +} + static const struct user_regset s390_regsets[] = { { .core_note_type = NT_PRSTATUS, @@ -1312,6 +1405,14 @@ static const struct user_regset s390_regsets[] = { .get = s390_gs_bc_get, .set = s390_gs_bc_set, }, + { + .core_note_type = NT_S390_RI_CB, + .n = sizeof(struct runtime_instr_cb) / sizeof(__u64), + .size = sizeof(__u64), + .align = sizeof(__u64), + .get = s390_runtime_instr_get, + .set = s390_runtime_instr_set, + }, }; static const struct user_regset_view user_s390_view = { @@ -1548,6 +1649,14 @@ static const struct user_regset s390_compat_regsets[] = { .get = s390_gs_cb_get, .set = s390_gs_cb_set, }, + { + .core_note_type = NT_S390_RI_CB, + .n = sizeof(struct runtime_instr_cb) / sizeof(__u64), + .size = sizeof(__u64), + .align = sizeof(__u64), + .get = s390_runtime_instr_get, + .set = s390_runtime_instr_set, + }, }; static const struct user_regset_view user_s390_compat_view = { diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index b5280db9ef6a..e3739c330c15 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -411,6 +411,7 @@ typedef struct elf64_shdr { #define NT_S390_VXRS_HIGH 0x30a /* s390 vector registers 16-31 */ #define NT_S390_GS_CB 0x30b /* s390 guarded storage registers */ #define NT_S390_GS_BC 0x30c /* s390 guarded storage broadcast control block */ +#define NT_S390_RI_CB 0x30d /* s390 runtime instrumentation */ #define NT_ARM_VFP 0x400 /* ARM VFP/NEON registers */ #define NT_ARM_TLS 0x401 /* ARM TLS register */ #define NT_ARM_HW_BREAK 0x402 /* ARM hardware breakpoint registers */ -- cgit v1.2.3-71-gd317 From 5af48b59f35cf712793badabe1a574a0d0ce3bd3 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 27 Sep 2017 16:12:44 +0300 Subject: net: bridge: add per-port group_fwd_mask with less restrictions We need to be able to transparently forward most link-local frames via tunnels (e.g. vxlan, qinq). Currently the bridge's group_fwd_mask has a mask which restricts the forwarding of STP and LACP, but we need to be able to forward these over tunnels and control that forwarding on a per-port basis thus add a new per-port group_fwd_mask option which only disallows mac pause frames to be forwarded (they're always dropped anyway). The patch does not change the current default situation - all of the others are still restricted unless configured for forwarding. We have successfully tested this patch with LACP and STP forwarding over VxLAN and qinq tunnels. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_input.c | 1 + net/bridge/br_netlink.c | 14 +++++++++++++- net/bridge/br_private.h | 10 +++++++++- net/bridge/br_sysfs_if.c | 18 ++++++++++++++++++ 5 files changed, 42 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 8d062c58d5cb..ea87bd708ee9 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -325,6 +325,7 @@ enum { IFLA_BRPORT_MCAST_TO_UCAST, IFLA_BRPORT_VLAN_TUNNEL, IFLA_BRPORT_BCAST_FLOOD, + IFLA_BRPORT_GROUP_FWD_MASK, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 7637f58c1226..7cb613776b31 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -289,6 +289,7 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb) * * Others reserved for future standardization */ + fwd_mask |= p->group_fwd_mask; switch (dest[5]) { case 0x00: /* Bridge Group Address */ /* If STP is turned off, diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 3bc890716c89..dea88a255d26 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -152,6 +152,7 @@ static inline size_t br_port_info_size(void) #ifdef CONFIG_BRIDGE_IGMP_SNOOPING + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MULTICAST_ROUTER */ #endif + + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_GROUP_FWD_MASK */ + 0; } @@ -208,7 +209,8 @@ static int br_port_fill_attrs(struct sk_buff *skb, p->topology_change_ack) || nla_put_u8(skb, IFLA_BRPORT_CONFIG_PENDING, p->config_pending) || nla_put_u8(skb, IFLA_BRPORT_VLAN_TUNNEL, !!(p->flags & - BR_VLAN_TUNNEL))) + BR_VLAN_TUNNEL)) || + nla_put_u16(skb, IFLA_BRPORT_GROUP_FWD_MASK, p->group_fwd_mask)) return -EMSGSIZE; timerval = br_timer_value(&p->message_age_timer); @@ -637,6 +639,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_MCAST_TO_UCAST] = { .type = NLA_U8 }, [IFLA_BRPORT_MCAST_FLOOD] = { .type = NLA_U8 }, [IFLA_BRPORT_BCAST_FLOOD] = { .type = NLA_U8 }, + [IFLA_BRPORT_GROUP_FWD_MASK] = { .type = NLA_U16 }, }; /* Change the state of the port and notify spanning tree */ @@ -773,6 +776,15 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) return err; } #endif + + if (tb[IFLA_BRPORT_GROUP_FWD_MASK]) { + u16 fwd_mask = nla_get_u16(tb[IFLA_BRPORT_GROUP_FWD_MASK]); + + if (fwd_mask & BR_GROUPFWD_MACPAUSE) + return -EINVAL; + p->group_fwd_mask = fwd_mask; + } + br_port_flags_change(p, old_flags ^ p->flags); return 0; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index e870cfc85b14..020c709a017f 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -36,7 +36,14 @@ /* Control of forwarding link local multicast */ #define BR_GROUPFWD_DEFAULT 0 /* Don't allow forwarding of control protocols like STP, MAC PAUSE and LACP */ -#define BR_GROUPFWD_RESTRICTED 0x0007u +enum { + BR_GROUPFWD_STP = BIT(0), + BR_GROUPFWD_MACPAUSE = BIT(1), + BR_GROUPFWD_LACP = BIT(2), +}; + +#define BR_GROUPFWD_RESTRICTED (BR_GROUPFWD_STP | BR_GROUPFWD_MACPAUSE | \ + BR_GROUPFWD_LACP) /* The Nearest Customer Bridge Group Address, 01-80-C2-00-00-[00,0B,0C,0D,0F] */ #define BR_GROUPFWD_8021AD 0xB801u @@ -268,6 +275,7 @@ struct net_bridge_port { #ifdef CONFIG_NET_SWITCHDEV int offload_fwd_mark; #endif + u16 group_fwd_mask; }; #define br_auto_port(p) ((p)->flags & BR_AUTO_MASK) diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 5d5d413a6cf8..9110d5e56085 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -165,6 +165,23 @@ static int store_flush(struct net_bridge_port *p, unsigned long v) } static BRPORT_ATTR(flush, S_IWUSR, NULL, store_flush); +static ssize_t show_group_fwd_mask(struct net_bridge_port *p, char *buf) +{ + return sprintf(buf, "%#x\n", p->group_fwd_mask); +} + +static int store_group_fwd_mask(struct net_bridge_port *p, + unsigned long v) +{ + if (v & BR_GROUPFWD_MACPAUSE) + return -EINVAL; + p->group_fwd_mask = v; + + return 0; +} +static BRPORT_ATTR(group_fwd_mask, S_IRUGO | S_IWUSR, show_group_fwd_mask, + store_group_fwd_mask); + BRPORT_ATTR_FLAG(hairpin_mode, BR_HAIRPIN_MODE); BRPORT_ATTR_FLAG(bpdu_guard, BR_BPDU_GUARD); BRPORT_ATTR_FLAG(root_block, BR_ROOT_BLOCK); @@ -223,6 +240,7 @@ static const struct brport_attribute *brport_attrs[] = { &brport_attr_proxyarp_wifi, &brport_attr_multicast_flood, &brport_attr_broadcast_flood, + &brport_attr_group_fwd_mask, NULL }; -- cgit v1.2.3-71-gd317 From cb4d2b3f03d8eed90be3a194e5b54b734ec4bbe9 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 27 Sep 2017 14:37:52 -0700 Subject: bpf: Add name, load_time, uid and map_ids to bpf_prog_info The patch adds name and load_time to struct bpf_prog_aux. They are also exported to bpf_prog_info. The bpf_prog's name is passed by userspace during BPF_PROG_LOAD. The kernel only stores the first (BPF_PROG_NAME_LEN - 1) bytes and the name stored in the kernel is always \0 terminated. The kernel will reject name that contains characters other than isalnum() and '_'. It will also reject name that is not null terminated. The existing 'user->uid' of the bpf_prog_aux is also exported to the bpf_prog_info as created_by_uid. The existing 'used_maps' of the bpf_prog_aux is exported to the newly added members 'nr_map_ids' and 'map_ids' of the bpf_prog_info. On the input, nr_map_ids tells how big the userspace's map_ids buffer is. On the output, nr_map_ids tells the exact user_map_cnt and it will only copy up to the userspace's map_ids buffer is allowed. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf.h | 2 ++ include/uapi/linux/bpf.h | 8 ++++++++ kernel/bpf/syscall.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 60 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2b672c50f160..33ccc474fb04 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -187,6 +187,8 @@ struct bpf_prog_aux { struct bpf_map **used_maps; struct bpf_prog *prog; struct user_struct *user; + u64 load_time; /* ns since boottime */ + u8 name[BPF_OBJ_NAME_LEN]; union { struct work_struct work; struct rcu_head rcu; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e43491ac4823..bd6348269bf5 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -175,6 +175,8 @@ enum bpf_attach_type { /* Specify numa node during map creation */ #define BPF_F_NUMA_NODE (1U << 2) +#define BPF_OBJ_NAME_LEN 16U + union bpf_attr { struct { /* anonymous struct used by BPF_MAP_CREATE command */ __u32 map_type; /* one of enum bpf_map_type */ @@ -210,6 +212,7 @@ union bpf_attr { __aligned_u64 log_buf; /* user supplied buffer */ __u32 kern_version; /* checked when prog_type=kprobe */ __u32 prog_flags; + __u8 prog_name[BPF_OBJ_NAME_LEN]; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -812,6 +815,11 @@ struct bpf_prog_info { __u32 xlated_prog_len; __aligned_u64 jited_prog_insns; __aligned_u64 xlated_prog_insns; + __u64 load_time; /* ns since boottime */ + __u32 created_by_uid; + __u32 nr_map_ids; + __aligned_u64 map_ids; + __u8 name[BPF_OBJ_NAME_LEN]; } __attribute__((aligned(8))); struct bpf_map_info { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 25d074920a00..45970df3f820 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -23,6 +23,9 @@ #include #include #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 || \ @@ -312,6 +315,30 @@ int bpf_map_new_fd(struct bpf_map *map) offsetof(union bpf_attr, CMD##_LAST_FIELD) - \ sizeof(attr->CMD##_LAST_FIELD)) != NULL +/* dst and src must have at least BPF_OBJ_NAME_LEN number of bytes. + * Return 0 on success and < 0 on error. + */ +static int bpf_obj_name_cpy(char *dst, const char *src) +{ + const char *end = src + BPF_OBJ_NAME_LEN; + + /* Copy all isalnum() and '_' char */ + while (src < end && *src) { + if (!isalnum(*src) && *src != '_') + return -EINVAL; + *dst++ = *src++; + } + + /* No '\0' found in BPF_OBJ_NAME_LEN number of bytes */ + if (src == end) + return -EINVAL; + + /* '\0' terminates dst */ + *dst = 0; + + return 0; +} + #define BPF_MAP_CREATE_LAST_FIELD numa_node /* called via syscall */ static int map_create(union bpf_attr *attr) @@ -973,7 +1000,7 @@ struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) EXPORT_SYMBOL_GPL(bpf_prog_get_type); /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD prog_flags +#define BPF_PROG_LOAD_LAST_FIELD prog_name static int bpf_prog_load(union bpf_attr *attr) { @@ -1037,6 +1064,11 @@ static int bpf_prog_load(union bpf_attr *attr) if (err < 0) goto free_prog; + prog->aux->load_time = ktime_get_boot_ns(); + err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name); + if (err) + goto free_prog; + /* run eBPF verifier */ err = bpf_check(&prog, attr); if (err < 0) @@ -1358,8 +1390,25 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, info.type = prog->type; info.id = prog->aux->id; + info.load_time = prog->aux->load_time; + info.created_by_uid = from_kuid_munged(current_user_ns(), + prog->aux->user->uid); memcpy(info.tag, prog->tag, sizeof(prog->tag)); + memcpy(info.name, prog->aux->name, sizeof(prog->aux->name)); + + ulen = info.nr_map_ids; + info.nr_map_ids = prog->aux->used_map_cnt; + ulen = min_t(u32, info.nr_map_ids, ulen); + if (ulen) { + u32 *user_map_ids = (u32 *)info.map_ids; + u32 i; + + for (i = 0; i < ulen; i++) + if (put_user(prog->aux->used_maps[i]->id, + &user_map_ids[i])) + return -EFAULT; + } if (!capable(CAP_SYS_ADMIN)) { info.jited_prog_len = 0; -- cgit v1.2.3-71-gd317 From ad5b177bd73f5107d97c36f56395c4281fb6f089 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 27 Sep 2017 14:37:53 -0700 Subject: bpf: Add map_name to bpf_map_info This patch allows userspace to specify a name for a map during BPF_MAP_CREATE. The map's name can later be exported to user space via BPF_OBJ_GET_INFO_BY_FD. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 2 ++ kernel/bpf/syscall.c | 7 ++++++- 3 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 33ccc474fb04..252f4bc9eb25 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -56,6 +56,7 @@ struct bpf_map { struct work_struct work; atomic_t usercnt; struct bpf_map *inner_map_meta; + u8 name[BPF_OBJ_NAME_LEN]; }; /* function argument constraints */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index bd6348269bf5..6d2137b4cf38 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -190,6 +190,7 @@ union bpf_attr { __u32 numa_node; /* numa node (effective only if * BPF_F_NUMA_NODE is set). */ + __u8 map_name[BPF_OBJ_NAME_LEN]; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -829,6 +830,7 @@ struct bpf_map_info { __u32 value_size; __u32 max_entries; __u32 map_flags; + __u8 name[BPF_OBJ_NAME_LEN]; } __attribute__((aligned(8))); /* User bpf_sock_ops struct to access socket values and specify request ops diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 45970df3f820..11a7f82a55d1 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -339,7 +339,7 @@ static int bpf_obj_name_cpy(char *dst, const char *src) return 0; } -#define BPF_MAP_CREATE_LAST_FIELD numa_node +#define BPF_MAP_CREATE_LAST_FIELD map_name /* called via syscall */ static int map_create(union bpf_attr *attr) { @@ -361,6 +361,10 @@ static int map_create(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + err = bpf_obj_name_cpy(map->name, attr->map_name); + if (err) + goto free_map_nouncharge; + atomic_set(&map->refcnt, 1); atomic_set(&map->usercnt, 1); @@ -1462,6 +1466,7 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map, info.value_size = map->value_size; info.max_entries = map->max_entries; info.map_flags = map->map_flags; + memcpy(info.name, map->name, sizeof(map->name)); if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) -- cgit v1.2.3-71-gd317 From 84e14fe353de7624872e582887712079ba0b2d56 Mon Sep 17 00:00:00 2001 From: Maciej Żenczykowski Date: Tue, 26 Sep 2017 21:32:42 -0700 Subject: net-ipv6: add support for sockopt(SOL_IPV6, IPV6_FREEBIND) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit So far we've been relying on sockopt(SOL_IP, IP_FREEBIND) being usable even on IPv6 sockets. However, it turns out it is perfectly reasonable to want to set freebind on an AF_INET6 SOCK_RAW socket - but there is no way to set any SOL_IP socket option on such a socket (they're all blindly errored out). One use case for this is to allow spoofing src ip on a raw socket via sendmsg cmsg. Tested: built, and booted # python >>> import socket >>> SOL_IP = socket.SOL_IP >>> SOL_IPV6 = socket.IPPROTO_IPV6 >>> IP_FREEBIND = 15 >>> IPV6_FREEBIND = 78 >>> s = socket.socket(socket.AF_INET6, socket.SOCK_DGRAM, 0) >>> s.getsockopt(SOL_IP, IP_FREEBIND) 0 >>> s.getsockopt(SOL_IPV6, IPV6_FREEBIND) 0 >>> s.setsockopt(SOL_IPV6, IPV6_FREEBIND, 1) >>> s.getsockopt(SOL_IP, IP_FREEBIND) 1 >>> s.getsockopt(SOL_IPV6, IPV6_FREEBIND) 1 Signed-off-by: Maciej Żenczykowski Signed-off-by: David S. Miller --- include/uapi/linux/in6.h | 1 + net/ipv6/ipv6_sockglue.c | 12 ++++++++++++ 2 files changed, 13 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h index 46444f8fbee4..4f8f3eb0699f 100644 --- a/include/uapi/linux/in6.h +++ b/include/uapi/linux/in6.h @@ -284,6 +284,7 @@ struct in6_flowlabel_req { #define IPV6_TRANSPARENT 75 #define IPV6_UNICAST_IF 76 #define IPV6_RECVFRAGSIZE 77 +#define IPV6_FREEBIND 78 /* * Multicast Routing: diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index a5e466d4e093..b9404feabd78 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -377,6 +377,14 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, retv = 0; break; + case IPV6_FREEBIND: + if (optlen < sizeof(int)) + goto e_inval; + /* we also don't have a separate freebind bit for IPV6 */ + inet_sk(sk)->freebind = valbool; + retv = 0; + break; + case IPV6_RECVORIGDSTADDR: if (optlen < sizeof(int)) goto e_inval; @@ -1214,6 +1222,10 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, val = inet_sk(sk)->transparent; break; + case IPV6_FREEBIND: + val = inet_sk(sk)->freebind; + break; + case IPV6_RECVORIGDSTADDR: val = np->rxopt.bits.rxorigdstaddr; break; -- cgit v1.2.3-71-gd317 From 503c1fb98ba3859c13863957c7c65c92371a9e50 Mon Sep 17 00:00:00 2001 From: Avraham Stern Date: Fri, 29 Sep 2017 14:21:49 +0200 Subject: cfg80211/nl80211: add a port authorized event Add an event that indicates that a connection is authorized (i.e. the 4 way handshake was performed by the driver). This event should be sent by the driver after sending a connect/roamed event. This is useful for networks that require 802.1X authentication. In cases that the driver supports 4 way handshake offload, but the 802.1X authentication is managed by user space, the driver needs to inform user space right after the 802.11 association was completed so user space can initialize its 802.1X state machine etc. However, it is also possible that the AP will choose to skip the 802.1X authentication (e.g. when PMKSA caching is used) and proceed with the 4 way handshake immediately. In this case the driver needs to inform user space that 802.1X authentication is no longer required (e.g. to prevent user space from disconnecting since it did not get any EAPOLs from the AP). This is also useful for roaming, in which case it is possible that the driver used the Fast Transition protocol so 802.1X is not required. Since there will now be a dedicated notification indicating that the connection is authorized, the authorized flag can be removed from the roamed event. Drivers can send the new port authorized event right after sending the roamed event to indicate the new AP is already authorized. This therefore reserves the old PORT_AUTHORIZED attribute. Signed-off-by: Avraham Stern Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 21 +++++++++++++++++---- include/uapi/linux/nl80211.h | 28 ++++++++++++++++----------- net/wireless/core.h | 5 +++++ net/wireless/nl80211.c | 34 ++++++++++++++++++++++++++++++--- net/wireless/nl80211.h | 2 ++ net/wireless/sme.c | 45 +++++++++++++++++++++++++++++++++++++++++++- net/wireless/util.c | 3 +++ 7 files changed, 119 insertions(+), 19 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index cc1996081463..8b8118a7fadb 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5428,9 +5428,6 @@ cfg80211_connect_timeout(struct net_device *dev, const u8 *bssid, * @req_ie_len: association request IEs length * @resp_ie: association response IEs (may be %NULL) * @resp_ie_len: assoc response IEs length - * @authorized: true if the 802.1X authentication was done by the driver or is - * not needed (e.g., when Fast Transition protocol was used), false - * otherwise. Ignored for networks that don't use 802.1X authentication. */ struct cfg80211_roam_info { struct ieee80211_channel *channel; @@ -5440,7 +5437,6 @@ struct cfg80211_roam_info { size_t req_ie_len; const u8 *resp_ie; size_t resp_ie_len; - bool authorized; }; /** @@ -5464,6 +5460,23 @@ struct cfg80211_roam_info { void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, gfp_t gfp); +/** + * cfg80211_port_authorized - notify cfg80211 of successful security association + * + * @dev: network device + * @bssid: the BSSID of the AP + * @gfp: allocation flags + * + * This function should be called by a driver that supports 4 way handshake + * offload after a security association was successfully established (i.e., + * the 4 way handshake was completed successfully). The call to this function + * should be preceded with a call to cfg80211_connect_result(), + * cfg80211_connect_done(), cfg80211_connect_bss() or cfg80211_roamed() to + * indicate the 802.11 association. + */ +void cfg80211_port_authorized(struct net_device *dev, const u8 *bssid, + gfp_t gfp); + /** * cfg80211_disconnected - notify cfg80211 that connection was dropped * diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 59ba6ca66a0d..95832ce03a44 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -569,13 +569,14 @@ * authentication/association or not receiving a response from the AP. * Non-zero %NL80211_ATTR_STATUS_CODE value is indicated in that case as * well to remain backwards compatible. - * @NL80211_CMD_ROAM: notifcation indicating the card/driver roamed by itself. - * When the driver roamed in a network that requires 802.1X authentication, - * %NL80211_ATTR_PORT_AUTHORIZED should be set if the 802.1X authentication - * was done by the driver or if roaming was done using Fast Transition - * protocol (in which case 802.1X authentication is not needed). If - * %NL80211_ATTR_PORT_AUTHORIZED is not set, user space is responsible for - * the 802.1X authentication. + * When establishing a security association, drivers that support 4 way + * handshake offload should send %NL80211_CMD_PORT_AUTHORIZED event when + * the 4 way handshake is completed successfully. + * @NL80211_CMD_ROAM: Notification indicating the card/driver roamed by itself. + * When a security association was established with the new AP (e.g. if + * the FT protocol was used for roaming or the driver completed the 4 way + * handshake), this event should be followed by an + * %NL80211_CMD_PORT_AUTHORIZED event. * @NL80211_CMD_DISCONNECT: drop a given connection; also used to notify * userspace that a connection was dropped by the AP or due to other * reasons, for this the %NL80211_ATTR_DISCONNECTED_BY_AP and @@ -982,6 +983,12 @@ * @NL80211_CMD_DEL_PMK: For offloaded 4-Way handshake, delete the previously * configured PMK for the authenticator address identified by * &NL80211_ATTR_MAC. + * @NL80211_CMD_PORT_AUTHORIZED: An event that indicates that the 4 way + * handshake was completed successfully by the driver. The BSSID is + * specified with &NL80211_ATTR_MAC. Drivers that support 4 way handshake + * offload should send this event after indicating 802.11 association with + * &NL80211_CMD_CONNECT or &NL80211_CMD_ROAM. If the 4 way handshake failed + * &NL80211_CMD_DISCONNECT should be indicated instead. * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use @@ -1185,6 +1192,8 @@ enum nl80211_commands { NL80211_CMD_SET_PMK, NL80211_CMD_DEL_PMK, + NL80211_CMD_PORT_AUTHORIZED, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -2138,10 +2147,7 @@ enum nl80211_commands { * in %NL80211_CMD_CONNECT to indicate that for 802.1X authentication it * wants to use the supported offload of the 4-way handshake. * @NL80211_ATTR_PMKR0_NAME: PMK-R0 Name for offloaded FT. - * @NL80211_ATTR_PORT_AUTHORIZED: flag attribute used in %NL80211_CMD_ROAMED - * notification indicating that that 802.1X authentication was done by - * the driver or is not needed (because roaming used the Fast Transition - * protocol). + * @NL80211_ATTR_PORT_AUTHORIZED: (reserved) * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined diff --git a/net/wireless/core.h b/net/wireless/core.h index 6e809325af3b..35165f42c2a8 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -216,6 +216,7 @@ enum cfg80211_event_type { EVENT_DISCONNECTED, EVENT_IBSS_JOINED, EVENT_STOPPED, + EVENT_PORT_AUTHORIZED, }; struct cfg80211_event { @@ -235,6 +236,9 @@ struct cfg80211_event { u8 bssid[ETH_ALEN]; struct ieee80211_channel *channel; } ij; + struct { + u8 bssid[ETH_ALEN]; + } pa; }; }; @@ -385,6 +389,7 @@ int cfg80211_disconnect(struct cfg80211_registered_device *rdev, bool wextev); void __cfg80211_roamed(struct wireless_dev *wdev, struct cfg80211_roam_info *info); +void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid); int cfg80211_mgd_wext_connect(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); void cfg80211_autodisconnect_wk(struct work_struct *work); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 1e39ba3cfd06..90e212db6889 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -13830,9 +13830,7 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, info->req_ie)) || (info->resp_ie && nla_put(msg, NL80211_ATTR_RESP_IE, info->resp_ie_len, - info->resp_ie)) || - (info->authorized && - nla_put_flag(msg, NL80211_ATTR_PORT_AUTHORIZED))) + info->resp_ie))) goto nla_put_failure; genlmsg_end(msg, hdr); @@ -13846,6 +13844,36 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, nlmsg_free(msg); } +void nl80211_send_port_authorized(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *bssid) +{ + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_PORT_AUTHORIZED); + if (!hdr) { + nlmsg_free(msg); + return; + } + + if (nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0, + NL80211_MCGRP_MLME, GFP_KERNEL); + return; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + nlmsg_free(msg); +} + void nl80211_send_disconnected(struct cfg80211_registered_device *rdev, struct net_device *netdev, u16 reason, const u8 *ie, size_t ie_len, bool from_ap) diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index b96933322077..bf9e772a30b9 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -58,6 +58,8 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev, void nl80211_send_roamed(struct cfg80211_registered_device *rdev, struct net_device *netdev, struct cfg80211_roam_info *info, gfp_t gfp); +void nl80211_send_port_authorized(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *bssid); void nl80211_send_disconnected(struct cfg80211_registered_device *rdev, struct net_device *netdev, u16 reason, const u8 *ie, size_t ie_len, bool from_ap); diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 0a49b88070d0..f38ed490e42b 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -960,7 +960,6 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, ev->rm.resp_ie_len = info->resp_ie_len; memcpy((void *)ev->rm.resp_ie, info->resp_ie, info->resp_ie_len); ev->rm.bss = info->bss; - ev->rm.authorized = info->authorized; spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); @@ -969,6 +968,50 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, } EXPORT_SYMBOL(cfg80211_roamed); +void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid) +{ + ASSERT_WDEV_LOCK(wdev); + + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) + return; + + if (WARN_ON(!wdev->current_bss) || + WARN_ON(!ether_addr_equal(wdev->current_bss->pub.bssid, bssid))) + return; + + nl80211_send_port_authorized(wiphy_to_rdev(wdev->wiphy), wdev->netdev, + bssid); +} + +void cfg80211_port_authorized(struct net_device *dev, const u8 *bssid, + gfp_t gfp) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + struct cfg80211_event *ev; + unsigned long flags; + + if (WARN_ON(!bssid)) + return; + + ev = kzalloc(sizeof(*ev), gfp); + if (!ev) + return; + + ev->type = EVENT_PORT_AUTHORIZED; + memcpy(ev->pa.bssid, bssid, ETH_ALEN); + + /* + * Use the wdev event list so that if there are pending + * connected/roamed events, they will be reported first. + */ + spin_lock_irqsave(&wdev->event_lock, flags); + list_add_tail(&ev->list, &wdev->event_list); + spin_unlock_irqrestore(&wdev->event_lock, flags); + queue_work(cfg80211_wq, &rdev->event_work); +} +EXPORT_SYMBOL(cfg80211_port_authorized); + void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, size_t ie_len, u16 reason, bool from_ap) { diff --git a/net/wireless/util.c b/net/wireless/util.c index 7a1fcc6ee060..ff21c314a609 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -846,6 +846,9 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev) case EVENT_STOPPED: __cfg80211_leave(wiphy_to_rdev(wdev->wiphy), wdev); break; + case EVENT_PORT_AUTHORIZED: + __cfg80211_port_authorized(wdev, ev->pa.bssid); + break; } wdev_unlock(wdev); -- cgit v1.2.3-71-gd317 From 90caccdd8cc0215705f18b92771b449b01e2474a Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 3 Oct 2017 15:37:20 -0700 Subject: bpf: fix bpf_tail_call() x64 JIT - bpf prog_array just like all other types of bpf array accepts 32-bit index. Clarify that in the comment. - fix x64 JIT of bpf_tail_call which was incorrectly loading 8 instead of 4 bytes - tighten corresponding check in the interpreter to stay consistent The JIT bug can be triggered after introduction of BPF_F_NUMA_NODE flag in commit 96eabe7a40aa in 4.14. Before that the map_flags would stay zero and though JIT code is wrong it will check bounds correctly. Hence two fixes tags. All other JITs don't have this problem. Signed-off-by: Alexei Starovoitov Fixes: 96eabe7a40aa ("bpf: Allow selecting numa node during map creation") Fixes: b52f00e6a715 ("x86: bpf_jit: implement bpf_tail_call() helper") Acked-by: Daniel Borkmann Acked-by: Martin KaFai Lau Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- arch/x86/net/bpf_jit_comp.c | 4 ++-- include/uapi/linux/bpf.h | 2 +- kernel/bpf/core.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 8c9573660d51..0554e8aef4d5 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -284,9 +284,9 @@ static void emit_bpf_tail_call(u8 **pprog) /* if (index >= array->map.max_entries) * goto out; */ - EMIT4(0x48, 0x8B, 0x46, /* mov rax, qword ptr [rsi + 16] */ + EMIT2(0x89, 0xD2); /* mov edx, edx */ + EMIT3(0x39, 0x56, /* cmp dword ptr [rsi + 16], edx */ offsetof(struct bpf_array, map.max_entries)); - EMIT3(0x48, 0x39, 0xD0); /* cmp rax, rdx */ #define OFFSET1 43 /* number of bytes to jump */ EMIT2(X86_JBE, OFFSET1); /* jbe out */ label1 = cnt; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 43ab5c402f98..f90860d1f897 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -312,7 +312,7 @@ union bpf_attr { * jump into another BPF program * @ctx: context pointer passed to next program * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY - * @index: index inside array that selects specific program to run + * @index: 32-bit index inside array that selects specific program to run * Return: 0 on success or negative error * * int bpf_clone_redirect(skb, ifindex, flags) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 917cc04a0a94..7b62df86be1d 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1022,7 +1022,7 @@ select_insn: struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2; struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_prog *prog; - u64 index = BPF_R3; + u32 index = BPF_R3; if (unlikely(index >= array->map.max_entries)) goto out; -- cgit v1.2.3-71-gd317 From 5bbbbe32a43199c2b9ea5ea66fab6241c64beb51 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Tue, 3 Oct 2017 19:20:13 -0300 Subject: sctp: introduce stream scheduler foundations This patch introduces the hooks necessary to do stream scheduling, as per RFC Draft ndata. It also introduces the first scheduler, which is what we do today but now factored out: first come first served (FCFS). With stream scheduling now we have to track which chunk was enqueued on which stream and be able to select another other than the in front of the main outqueue. So we introduce a list on sctp_stream_out_ext structure for this purpose. We reuse sctp_chunk->transmitted_list space for the list above, as the chunk cannot belong to the two lists at the same time. By using the union in there, we can have distinct names for these moments. sctp_sched_ops are the operations expected to be implemented by each scheduler. The dequeueing is a bit particular to this implementation but it is to match how we dequeue packets today. We first dequeue and then check if it fits the packet and if not, we requeue it at head. Thus why we don't have a peek operation but have dequeue_done instead, which is called once the chunk can be safely considered as transmitted. The check removed from sctp_outq_flush is now performed by sctp_stream_outq_migrate, which is only called during assoc setup. (sctp_sendmsg() also checks for it) The only operation that is foreseen but not yet added here is a way to signalize that a new packet is starting or that the packet is done, for round robin scheduler per packet, but is intentionally left to the patch that actually implements it. Support for I-DATA chunks, also described in this RFC, with user message interleaving is straightforward as it just requires the schedulers to probe for the feature and ignore datamsg boundaries when dequeueing. See-also: https://tools.ietf.org/html/draft-ietf-tsvwg-sctp-ndata-13 Tested-by: Xin Long Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/sctp/stream_sched.h | 72 +++++++++++ include/net/sctp/structs.h | 15 ++- include/uapi/linux/sctp.h | 6 + net/sctp/Makefile | 2 +- net/sctp/outqueue.c | 59 +++++---- net/sctp/sm_sideeffect.c | 3 + net/sctp/stream.c | 88 +++++++++++-- net/sctp/stream_sched.c | 270 ++++++++++++++++++++++++++++++++++++++++ 8 files changed, 477 insertions(+), 38 deletions(-) create mode 100644 include/net/sctp/stream_sched.h create mode 100644 net/sctp/stream_sched.c (limited to 'include/uapi/linux') diff --git a/include/net/sctp/stream_sched.h b/include/net/sctp/stream_sched.h new file mode 100644 index 000000000000..c676550a4c7d --- /dev/null +++ b/include/net/sctp/stream_sched.h @@ -0,0 +1,72 @@ +/* SCTP kernel implementation + * (C) Copyright Red Hat Inc. 2017 + * + * These are definitions used by the stream schedulers, defined in RFC + * draft ndata (https://tools.ietf.org/html/draft-ietf-tsvwg-sctp-ndata-11) + * + * This SCTP implementation is free software; + * you can redistribute it and/or modify it under the terms of + * the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + * This SCTP implementation is distributed in the hope that it + * will be useful, but WITHOUT ANY WARRANTY; without even the implied + * ************************ + * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * See the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with GNU CC; see the file COPYING. If not, see + * . + * + * Please send any bug reports or fixes you make to the + * email addresses: + * lksctp developers + * + * Written or modified by: + * Marcelo Ricardo Leitner + */ + +#ifndef __sctp_stream_sched_h__ +#define __sctp_stream_sched_h__ + +struct sctp_sched_ops { + /* Property handling for a given stream */ + int (*set)(struct sctp_stream *stream, __u16 sid, __u16 value, + gfp_t gfp); + int (*get)(struct sctp_stream *stream, __u16 sid, __u16 *value); + + /* Init the specific scheduler */ + int (*init)(struct sctp_stream *stream); + /* Init a stream */ + int (*init_sid)(struct sctp_stream *stream, __u16 sid, gfp_t gfp); + /* Frees the entire thing */ + void (*free)(struct sctp_stream *stream); + + /* Enqueue a chunk */ + void (*enqueue)(struct sctp_outq *q, struct sctp_datamsg *msg); + /* Dequeue a chunk */ + struct sctp_chunk *(*dequeue)(struct sctp_outq *q); + /* Called only if the chunk fit the packet */ + void (*dequeue_done)(struct sctp_outq *q, struct sctp_chunk *chunk); + /* Sched all chunks already enqueued */ + void (*sched_all)(struct sctp_stream *steam); + /* Unched all chunks already enqueued */ + void (*unsched_all)(struct sctp_stream *steam); +}; + +int sctp_sched_set_sched(struct sctp_association *asoc, + enum sctp_sched_type sched); +int sctp_sched_get_sched(struct sctp_association *asoc); +int sctp_sched_set_value(struct sctp_association *asoc, __u16 sid, + __u16 value, gfp_t gfp); +int sctp_sched_get_value(struct sctp_association *asoc, __u16 sid, + __u16 *value); +void sctp_sched_dequeue_done(struct sctp_outq *q, struct sctp_chunk *ch); + +void sctp_sched_dequeue_common(struct sctp_outq *q, struct sctp_chunk *ch); +int sctp_sched_init_sid(struct sctp_stream *stream, __u16 sid, gfp_t gfp); +struct sctp_sched_ops *sctp_sched_ops_from_stream(struct sctp_stream *stream); + +#endif /* __sctp_stream_sched_h__ */ diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index c48f7999fe9b..3c22a30fd71b 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -84,7 +84,6 @@ struct sctp_ulpq; struct sctp_ep_common; struct crypto_shash; struct sctp_stream; -struct sctp_stream_out; #include @@ -531,8 +530,12 @@ struct sctp_chunk { /* How many times this chunk have been sent, for prsctp RTX policy */ int sent_count; - /* This is our link to the per-transport transmitted list. */ - struct list_head transmitted_list; + union { + /* This is our link to the per-transport transmitted list. */ + struct list_head transmitted_list; + /* List in specific stream outq */ + struct list_head stream_list; + }; /* This field is used by chunks that hold fragmented data. * For the first fragment this is the list that holds the rest of @@ -1019,6 +1022,9 @@ struct sctp_outq { /* Data pending that has never been transmitted. */ struct list_head out_chunk_list; + /* Stream scheduler being used */ + struct sctp_sched_ops *sched; + unsigned int out_qlen; /* Total length of queued data chunks. */ /* Error of send failed, may used in SCTP_SEND_FAILED event. */ @@ -1325,6 +1331,7 @@ struct sctp_inithdr_host { struct sctp_stream_out_ext { __u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1]; __u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1]; + struct list_head outq; /* chunks enqueued by this stream */ }; struct sctp_stream_out { @@ -1342,6 +1349,8 @@ struct sctp_stream { struct sctp_stream_in *in; __u16 outcnt; __u16 incnt; + /* Current stream being sent, if any */ + struct sctp_stream_out *out_curr; }; #define SCTP_STREAM_CLOSED 0x00 diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 6217ff8500a1..4487e7625ddb 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -1088,4 +1088,10 @@ struct sctp_add_streams { uint16_t sas_outstrms; }; +/* SCTP Stream schedulers */ +enum sctp_sched_type { + SCTP_SS_FCFS, + SCTP_SS_MAX = SCTP_SS_FCFS +}; + #endif /* _UAPI_SCTP_H */ diff --git a/net/sctp/Makefile b/net/sctp/Makefile index 70f1b570bab9..0f6e6d1d69fd 100644 --- a/net/sctp/Makefile +++ b/net/sctp/Makefile @@ -12,7 +12,7 @@ sctp-y := sm_statetable.o sm_statefuns.o sm_sideeffect.o \ inqueue.o outqueue.o ulpqueue.o \ tsnmap.o bind_addr.o socket.o primitive.o \ output.o input.o debug.o stream.o auth.o \ - offload.o + offload.o stream_sched.o sctp_probe-y := probe.o diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 746b07b7937d..4db012aa25f7 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -50,6 +50,7 @@ #include #include +#include /* Declare internal functions here. */ static int sctp_acked(struct sctp_sackhdr *sack, __u32 tsn); @@ -72,32 +73,38 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp); /* Add data to the front of the queue. */ static inline void sctp_outq_head_data(struct sctp_outq *q, - struct sctp_chunk *ch) + struct sctp_chunk *ch) { + struct sctp_stream_out_ext *oute; + __u16 stream; + list_add(&ch->list, &q->out_chunk_list); q->out_qlen += ch->skb->len; + + stream = sctp_chunk_stream_no(ch); + oute = q->asoc->stream.out[stream].ext; + list_add(&ch->stream_list, &oute->outq); } /* Take data from the front of the queue. */ static inline struct sctp_chunk *sctp_outq_dequeue_data(struct sctp_outq *q) { - struct sctp_chunk *ch = NULL; - - if (!list_empty(&q->out_chunk_list)) { - struct list_head *entry = q->out_chunk_list.next; - - ch = list_entry(entry, struct sctp_chunk, list); - list_del_init(entry); - q->out_qlen -= ch->skb->len; - } - return ch; + return q->sched->dequeue(q); } + /* Add data chunk to the end of the queue. */ static inline void sctp_outq_tail_data(struct sctp_outq *q, struct sctp_chunk *ch) { + struct sctp_stream_out_ext *oute; + __u16 stream; + list_add_tail(&ch->list, &q->out_chunk_list); q->out_qlen += ch->skb->len; + + stream = sctp_chunk_stream_no(ch); + oute = q->asoc->stream.out[stream].ext; + list_add_tail(&ch->stream_list, &oute->outq); } /* @@ -207,6 +214,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) INIT_LIST_HEAD(&q->retransmit); INIT_LIST_HEAD(&q->sacked); INIT_LIST_HEAD(&q->abandoned); + sctp_sched_set_sched(asoc, SCTP_SS_FCFS); } /* Free the outqueue structure and any related pending chunks. @@ -258,6 +266,7 @@ static void __sctp_outq_teardown(struct sctp_outq *q) /* Throw away any leftover data chunks. */ while ((chunk = sctp_outq_dequeue_data(q)) != NULL) { + sctp_sched_dequeue_done(q, chunk); /* Mark as send failure. */ sctp_chunk_fail(chunk, q->error); @@ -391,13 +400,14 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, struct sctp_outq *q = &asoc->outqueue; struct sctp_chunk *chk, *temp; + q->sched->unsched_all(&asoc->stream); + list_for_each_entry_safe(chk, temp, &q->out_chunk_list, list) { if (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive) continue; - list_del_init(&chk->list); - q->out_qlen -= chk->skb->len; + sctp_sched_dequeue_common(q, chk); asoc->sent_cnt_removable--; asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; if (chk->sinfo.sinfo_stream < asoc->stream.outcnt) { @@ -415,6 +425,8 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, break; } + q->sched->sched_all(&asoc->stream); + return msg_len; } @@ -1033,22 +1045,9 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) while ((chunk = sctp_outq_dequeue_data(q)) != NULL) { __u32 sid = ntohs(chunk->subh.data_hdr->stream); - /* RFC 2960 6.5 Every DATA chunk MUST carry a valid - * stream identifier. - */ - if (chunk->sinfo.sinfo_stream >= asoc->stream.outcnt) { - - /* Mark as failed send. */ - sctp_chunk_fail(chunk, SCTP_ERROR_INV_STRM); - if (asoc->peer.prsctp_capable && - SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags)) - asoc->sent_cnt_removable--; - sctp_chunk_free(chunk); - continue; - } - /* Has this chunk expired? */ if (sctp_chunk_abandoned(chunk)) { + sctp_sched_dequeue_done(q, chunk); sctp_chunk_fail(chunk, 0); sctp_chunk_free(chunk); continue; @@ -1070,6 +1069,7 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) new_transport = asoc->peer.active_path; if (new_transport->state == SCTP_UNCONFIRMED) { WARN_ONCE(1, "Attempt to send packet on unconfirmed path."); + sctp_sched_dequeue_done(q, chunk); sctp_chunk_fail(chunk, 0); sctp_chunk_free(chunk); continue; @@ -1133,6 +1133,11 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) else asoc->stats.oodchunks++; + /* Only now it's safe to consider this + * chunk as sent, sched-wise. + */ + sctp_sched_dequeue_done(q, chunk); + break; default: diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index e6a2974e020e..402bfbb888cd 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -50,6 +50,7 @@ #include #include #include +#include static int sctp_cmd_interpreter(enum sctp_event event_type, union sctp_subtype subtype, @@ -1089,6 +1090,8 @@ static void sctp_cmd_send_msg(struct sctp_association *asoc, list_for_each_entry(chunk, &msg->chunks, frag_list) sctp_outq_tail(&asoc->outqueue, chunk, gfp); + + asoc->outqueue.sched->enqueue(&asoc->outqueue, msg); } diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 055ca25bbc91..5ea33a2c453b 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -32,8 +32,61 @@ * Xin Long */ +#include #include #include +#include + +/* Migrates chunks from stream queues to new stream queues if needed, + * but not across associations. Also, removes those chunks to streams + * higher than the new max. + */ +static void sctp_stream_outq_migrate(struct sctp_stream *stream, + struct sctp_stream *new, __u16 outcnt) +{ + struct sctp_association *asoc; + struct sctp_chunk *ch, *temp; + struct sctp_outq *outq; + int i; + + asoc = container_of(stream, struct sctp_association, stream); + outq = &asoc->outqueue; + + list_for_each_entry_safe(ch, temp, &outq->out_chunk_list, list) { + __u16 sid = sctp_chunk_stream_no(ch); + + if (sid < outcnt) + continue; + + sctp_sched_dequeue_common(outq, ch); + /* No need to call dequeue_done here because + * the chunks are not scheduled by now. + */ + + /* Mark as failed send. */ + sctp_chunk_fail(ch, SCTP_ERROR_INV_STRM); + if (asoc->peer.prsctp_capable && + SCTP_PR_PRIO_ENABLED(ch->sinfo.sinfo_flags)) + asoc->sent_cnt_removable--; + + sctp_chunk_free(ch); + } + + if (new) { + /* Here we actually move the old ext stuff into the new + * buffer, because we want to keep it. Then + * sctp_stream_update will swap ->out pointers. + */ + for (i = 0; i < outcnt; i++) { + kfree(new->out[i].ext); + new->out[i].ext = stream->out[i].ext; + stream->out[i].ext = NULL; + } + } + + for (i = outcnt; i < stream->outcnt; i++) + kfree(stream->out[i].ext); +} static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, gfp_t gfp) @@ -87,7 +140,8 @@ static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt, int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, gfp_t gfp) { - int i; + struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); + int i, ret = 0; gfp |= __GFP_NOWARN; @@ -97,6 +151,11 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, if (outcnt == stream->outcnt) goto in; + /* Filter out chunks queued on streams that won't exist anymore */ + sched->unsched_all(stream); + sctp_stream_outq_migrate(stream, NULL, outcnt); + sched->sched_all(stream); + i = sctp_stream_alloc_out(stream, outcnt, gfp); if (i) return i; @@ -105,20 +164,27 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, for (i = 0; i < stream->outcnt; i++) stream->out[i].state = SCTP_STREAM_OPEN; + sched->init(stream); + in: if (!incnt) - return 0; + goto out; i = sctp_stream_alloc_in(stream, incnt, gfp); if (i) { - kfree(stream->out); - stream->out = NULL; - return -ENOMEM; + ret = -ENOMEM; + goto free; } stream->incnt = incnt; + goto out; - return 0; +free: + sched->free(stream); + kfree(stream->out); + stream->out = NULL; +out: + return ret; } int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid) @@ -130,13 +196,15 @@ int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid) return -ENOMEM; stream->out[sid].ext = soute; - return 0; + return sctp_sched_init_sid(stream, sid, GFP_KERNEL); } void sctp_stream_free(struct sctp_stream *stream) { + struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); int i; + sched->free(stream); for (i = 0; i < stream->outcnt; i++) kfree(stream->out[i].ext); kfree(stream->out); @@ -156,6 +224,10 @@ void sctp_stream_clear(struct sctp_stream *stream) void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new) { + struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); + + sched->unsched_all(stream); + sctp_stream_outq_migrate(stream, new, new->outcnt); sctp_stream_free(stream); stream->out = new->out; @@ -163,6 +235,8 @@ void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new) stream->outcnt = new->outcnt; stream->incnt = new->incnt; + sched->sched_all(stream); + new->out = NULL; new->in = NULL; } diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c new file mode 100644 index 000000000000..40a9a9de2b98 --- /dev/null +++ b/net/sctp/stream_sched.c @@ -0,0 +1,270 @@ +/* SCTP kernel implementation + * (C) Copyright Red Hat Inc. 2017 + * + * This file is part of the SCTP kernel implementation + * + * These functions manipulate sctp stream queue/scheduling. + * + * This SCTP implementation is free software; + * you can redistribute it and/or modify it under the terms of + * the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + * This SCTP implementation is distributed in the hope that it + * will be useful, but WITHOUT ANY WARRANTY; without even the implied + * ************************ + * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * See the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with GNU CC; see the file COPYING. If not, see + * . + * + * Please send any bug reports or fixes you make to the + * email addresched(es): + * lksctp developers + * + * Written or modified by: + * Marcelo Ricardo Leitner + */ + +#include +#include +#include +#include + +/* First Come First Serve (a.k.a. FIFO) + * RFC DRAFT ndata Section 3.1 + */ +static int sctp_sched_fcfs_set(struct sctp_stream *stream, __u16 sid, + __u16 value, gfp_t gfp) +{ + return 0; +} + +static int sctp_sched_fcfs_get(struct sctp_stream *stream, __u16 sid, + __u16 *value) +{ + *value = 0; + return 0; +} + +static int sctp_sched_fcfs_init(struct sctp_stream *stream) +{ + return 0; +} + +static int sctp_sched_fcfs_init_sid(struct sctp_stream *stream, __u16 sid, + gfp_t gfp) +{ + return 0; +} + +static void sctp_sched_fcfs_free(struct sctp_stream *stream) +{ +} + +static void sctp_sched_fcfs_enqueue(struct sctp_outq *q, + struct sctp_datamsg *msg) +{ +} + +static struct sctp_chunk *sctp_sched_fcfs_dequeue(struct sctp_outq *q) +{ + struct sctp_stream *stream = &q->asoc->stream; + struct sctp_chunk *ch = NULL; + struct list_head *entry; + + if (list_empty(&q->out_chunk_list)) + goto out; + + if (stream->out_curr) { + ch = list_entry(stream->out_curr->ext->outq.next, + struct sctp_chunk, stream_list); + } else { + entry = q->out_chunk_list.next; + ch = list_entry(entry, struct sctp_chunk, list); + } + + sctp_sched_dequeue_common(q, ch); + +out: + return ch; +} + +static void sctp_sched_fcfs_dequeue_done(struct sctp_outq *q, + struct sctp_chunk *chunk) +{ +} + +static void sctp_sched_fcfs_sched_all(struct sctp_stream *stream) +{ +} + +static void sctp_sched_fcfs_unsched_all(struct sctp_stream *stream) +{ +} + +static struct sctp_sched_ops sctp_sched_fcfs = { + .set = sctp_sched_fcfs_set, + .get = sctp_sched_fcfs_get, + .init = sctp_sched_fcfs_init, + .init_sid = sctp_sched_fcfs_init_sid, + .free = sctp_sched_fcfs_free, + .enqueue = sctp_sched_fcfs_enqueue, + .dequeue = sctp_sched_fcfs_dequeue, + .dequeue_done = sctp_sched_fcfs_dequeue_done, + .sched_all = sctp_sched_fcfs_sched_all, + .unsched_all = sctp_sched_fcfs_unsched_all, +}; + +/* API to other parts of the stack */ + +struct sctp_sched_ops *sctp_sched_ops[] = { + &sctp_sched_fcfs, +}; + +int sctp_sched_set_sched(struct sctp_association *asoc, + enum sctp_sched_type sched) +{ + struct sctp_sched_ops *n = sctp_sched_ops[sched]; + struct sctp_sched_ops *old = asoc->outqueue.sched; + struct sctp_datamsg *msg = NULL; + struct sctp_chunk *ch; + int i, ret = 0; + + if (old == n) + return ret; + + if (sched > SCTP_SS_MAX) + return -EINVAL; + + if (old) { + old->free(&asoc->stream); + + /* Give the next scheduler a clean slate. */ + for (i = 0; i < asoc->stream.outcnt; i++) { + void *p = asoc->stream.out[i].ext; + + if (!p) + continue; + + p += offsetofend(struct sctp_stream_out_ext, outq); + memset(p, 0, sizeof(struct sctp_stream_out_ext) - + offsetofend(struct sctp_stream_out_ext, outq)); + } + } + + asoc->outqueue.sched = n; + n->init(&asoc->stream); + for (i = 0; i < asoc->stream.outcnt; i++) { + if (!asoc->stream.out[i].ext) + continue; + + ret = n->init_sid(&asoc->stream, i, GFP_KERNEL); + if (ret) + goto err; + } + + /* We have to requeue all chunks already queued. */ + list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) { + if (ch->msg == msg) + continue; + msg = ch->msg; + n->enqueue(&asoc->outqueue, msg); + } + + return ret; + +err: + n->free(&asoc->stream); + asoc->outqueue.sched = &sctp_sched_fcfs; /* Always safe */ + + return ret; +} + +int sctp_sched_get_sched(struct sctp_association *asoc) +{ + int i; + + for (i = 0; i <= SCTP_SS_MAX; i++) + if (asoc->outqueue.sched == sctp_sched_ops[i]) + return i; + + return 0; +} + +int sctp_sched_set_value(struct sctp_association *asoc, __u16 sid, + __u16 value, gfp_t gfp) +{ + if (sid >= asoc->stream.outcnt) + return -EINVAL; + + if (!asoc->stream.out[sid].ext) { + int ret; + + ret = sctp_stream_init_ext(&asoc->stream, sid); + if (ret) + return ret; + } + + return asoc->outqueue.sched->set(&asoc->stream, sid, value, gfp); +} + +int sctp_sched_get_value(struct sctp_association *asoc, __u16 sid, + __u16 *value) +{ + if (sid >= asoc->stream.outcnt) + return -EINVAL; + + if (!asoc->stream.out[sid].ext) + return 0; + + return asoc->outqueue.sched->get(&asoc->stream, sid, value); +} + +void sctp_sched_dequeue_done(struct sctp_outq *q, struct sctp_chunk *ch) +{ + if (!list_is_last(&ch->frag_list, &ch->msg->chunks)) { + struct sctp_stream_out *sout; + __u16 sid; + + /* datamsg is not finish, so save it as current one, + * in case application switch scheduler or a higher + * priority stream comes in. + */ + sid = sctp_chunk_stream_no(ch); + sout = &q->asoc->stream.out[sid]; + q->asoc->stream.out_curr = sout; + return; + } + + q->asoc->stream.out_curr = NULL; + q->sched->dequeue_done(q, ch); +} + +/* Auxiliary functions for the schedulers */ +void sctp_sched_dequeue_common(struct sctp_outq *q, struct sctp_chunk *ch) +{ + list_del_init(&ch->list); + list_del_init(&ch->stream_list); + q->out_qlen -= ch->skb->len; +} + +int sctp_sched_init_sid(struct sctp_stream *stream, __u16 sid, gfp_t gfp) +{ + struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); + + INIT_LIST_HEAD(&stream->out[sid].ext->outq); + return sched->init_sid(stream, sid, gfp); +} + +struct sctp_sched_ops *sctp_sched_ops_from_stream(struct sctp_stream *stream) +{ + struct sctp_association *asoc; + + asoc = container_of(stream, struct sctp_association, stream); + + return asoc->outqueue.sched; +} -- cgit v1.2.3-71-gd317 From 13aa8770fe42d246c6f3a8eb814b85bccb428011 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Tue, 3 Oct 2017 19:20:14 -0300 Subject: sctp: add sockopt to get/set stream scheduler As defined per RFC Draft ndata Section 4.3.2, named as SCTP_STREAM_SCHEDULER. See-also: https://tools.ietf.org/html/draft-ietf-tsvwg-sctp-ndata-13 Tested-by: Xin Long Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/uapi/linux/sctp.h | 1 + net/sctp/socket.c | 75 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 76 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 4487e7625ddb..0050f10087d2 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -122,6 +122,7 @@ typedef __s32 sctp_assoc_t; #define SCTP_RESET_ASSOC 120 #define SCTP_ADD_STREAMS 121 #define SCTP_SOCKOPT_PEELOFF_FLAGS 122 +#define SCTP_STREAM_SCHEDULER 123 /* PR-SCTP policies */ #define SCTP_PR_SCTP_NONE 0x0000 diff --git a/net/sctp/socket.c b/net/sctp/socket.c index d207734326b0..ae35dbf2810f 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -79,6 +79,7 @@ #include #include #include +#include /* Forward declarations for internal helper functions. */ static int sctp_writeable(struct sock *sk); @@ -3914,6 +3915,36 @@ out: return retval; } +static int sctp_setsockopt_scheduler(struct sock *sk, + char __user *optval, + unsigned int optlen) +{ + struct sctp_association *asoc; + struct sctp_assoc_value params; + int retval = -EINVAL; + + if (optlen < sizeof(params)) + goto out; + + optlen = sizeof(params); + if (copy_from_user(¶ms, optval, optlen)) { + retval = -EFAULT; + goto out; + } + + if (params.assoc_value > SCTP_SS_MAX) + goto out; + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc) + goto out; + + retval = sctp_sched_set_sched(asoc, params.assoc_value); + +out: + return retval; +} + /* API 6.2 setsockopt(), getsockopt() * * Applications use setsockopt() and getsockopt() to set or retrieve @@ -4095,6 +4126,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, case SCTP_ADD_STREAMS: retval = sctp_setsockopt_add_streams(sk, optval, optlen); break; + case SCTP_STREAM_SCHEDULER: + retval = sctp_setsockopt_scheduler(sk, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -6793,6 +6827,43 @@ out: return retval; } +static int sctp_getsockopt_scheduler(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + struct sctp_assoc_value params; + struct sctp_association *asoc; + int retval = -EFAULT; + + if (len < sizeof(params)) { + retval = -EINVAL; + goto out; + } + + len = sizeof(params); + if (copy_from_user(¶ms, optval, len)) + goto out; + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc) { + retval = -EINVAL; + goto out; + } + + params.assoc_value = sctp_sched_get_sched(asoc); + + if (put_user(len, optlen)) + goto out; + + if (copy_to_user(optval, ¶ms, len)) + goto out; + + retval = 0; + +out: + return retval; +} + static int sctp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -6975,6 +7046,10 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, retval = sctp_getsockopt_enable_strreset(sk, len, optval, optlen); break; + case SCTP_STREAM_SCHEDULER: + retval = sctp_getsockopt_scheduler(sk, len, optval, + optlen); + break; default: retval = -ENOPROTOOPT; break; -- cgit v1.2.3-71-gd317 From 0ccdf3c7fdeda511b10def19505178a9d2d3fccd Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Tue, 3 Oct 2017 19:20:15 -0300 Subject: sctp: add sockopt to get/set stream scheduler parameters As defined per RFC Draft ndata Section 4.3.3, named as SCTP_STREAM_SCHEDULER_VALUE. See-also: https://tools.ietf.org/html/draft-ietf-tsvwg-sctp-ndata-13 Tested-by: Xin Long Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/uapi/linux/sctp.h | 7 +++++ net/sctp/socket.c | 77 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 84 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 0050f10087d2..00ac417d2c4f 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -123,6 +123,7 @@ typedef __s32 sctp_assoc_t; #define SCTP_ADD_STREAMS 121 #define SCTP_SOCKOPT_PEELOFF_FLAGS 122 #define SCTP_STREAM_SCHEDULER 123 +#define SCTP_STREAM_SCHEDULER_VALUE 124 /* PR-SCTP policies */ #define SCTP_PR_SCTP_NONE 0x0000 @@ -815,6 +816,12 @@ struct sctp_assoc_value { uint32_t assoc_value; }; +struct sctp_stream_value { + sctp_assoc_t assoc_id; + uint16_t stream_id; + uint16_t stream_value; +}; + /* * 7.2.2 Peer Address Information * diff --git a/net/sctp/socket.c b/net/sctp/socket.c index ae35dbf2810f..88c28421ec15 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -3945,6 +3945,34 @@ out: return retval; } +static int sctp_setsockopt_scheduler_value(struct sock *sk, + char __user *optval, + unsigned int optlen) +{ + struct sctp_association *asoc; + struct sctp_stream_value params; + int retval = -EINVAL; + + if (optlen < sizeof(params)) + goto out; + + optlen = sizeof(params); + if (copy_from_user(¶ms, optval, optlen)) { + retval = -EFAULT; + goto out; + } + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc) + goto out; + + retval = sctp_sched_set_value(asoc, params.stream_id, + params.stream_value, GFP_KERNEL); + +out: + return retval; +} + /* API 6.2 setsockopt(), getsockopt() * * Applications use setsockopt() and getsockopt() to set or retrieve @@ -4129,6 +4157,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, case SCTP_STREAM_SCHEDULER: retval = sctp_setsockopt_scheduler(sk, optval, optlen); break; + case SCTP_STREAM_SCHEDULER_VALUE: + retval = sctp_setsockopt_scheduler_value(sk, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -6864,6 +6895,48 @@ out: return retval; } +static int sctp_getsockopt_scheduler_value(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + struct sctp_stream_value params; + struct sctp_association *asoc; + int retval = -EFAULT; + + if (len < sizeof(params)) { + retval = -EINVAL; + goto out; + } + + len = sizeof(params); + if (copy_from_user(¶ms, optval, len)) + goto out; + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc) { + retval = -EINVAL; + goto out; + } + + retval = sctp_sched_get_value(asoc, params.stream_id, + ¶ms.stream_value); + if (retval) + goto out; + + if (put_user(len, optlen)) { + retval = -EFAULT; + goto out; + } + + if (copy_to_user(optval, ¶ms, len)) { + retval = -EFAULT; + goto out; + } + +out: + return retval; +} + static int sctp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -7050,6 +7123,10 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, retval = sctp_getsockopt_scheduler(sk, len, optval, optlen); break; + case SCTP_STREAM_SCHEDULER_VALUE: + retval = sctp_getsockopt_scheduler_value(sk, len, optval, + optlen); + break; default: retval = -ENOPROTOOPT; break; -- cgit v1.2.3-71-gd317 From 637784ade221a3c8a7ecd0f583eddd95d6276b9a Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Tue, 3 Oct 2017 19:20:16 -0300 Subject: sctp: introduce priority based stream scheduler This patch introduces RFC Draft ndata section 3.4 Priority Based Scheduler (SCTP_SS_PRIO). It works by having a struct sctp_stream_priority for each priority configured. This struct is then enlisted on a queue ordered per priority if, and only if, there is a stream with data queued, so that dequeueing is very straightforward: either finish current datamsg or simply dequeue from the highest priority queued, which is the next stream pointed, and that's it. If there are multiple streams assigned with the same priority and with data queued, it will do round robin amongst them while respecting datamsgs boundaries (when not using idata chunks), to be reasonably fair. We intentionally don't maintain a list of priorities nor a list of all streams with the same priority to save memory. The first would mean at least 2 other pointers per priority (which, for 1000 priorities, that can mean 16kB) and the second would also mean 2 other pointers but per stream. As SCTP supports up to 65535 streams on a given asoc, that's 1MB. This impacts when giving a priority to some stream, as we have to find out if the new priority is already being used and if we can free the old one, and also when tearing down. The new fields in struct sctp_stream_out_ext and sctp_stream are added under a union because that memory is to be shared with other schedulers. See-also: https://tools.ietf.org/html/draft-ietf-tsvwg-sctp-ndata-13 Tested-by: Xin Long Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 24 +++ include/uapi/linux/sctp.h | 3 +- net/sctp/Makefile | 2 +- net/sctp/stream_sched.c | 3 + net/sctp/stream_sched_prio.c | 347 +++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 377 insertions(+), 2 deletions(-) create mode 100644 net/sctp/stream_sched_prio.c (limited to 'include/uapi/linux') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 3c22a30fd71b..40eb8d66a37c 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1328,10 +1328,27 @@ struct sctp_inithdr_host { __u32 initial_tsn; }; +struct sctp_stream_priorities { + /* List of priorities scheduled */ + struct list_head prio_sched; + /* List of streams scheduled */ + struct list_head active; + /* The next stream stream in line */ + struct sctp_stream_out_ext *next; + __u16 prio; +}; + struct sctp_stream_out_ext { __u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1]; __u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1]; struct list_head outq; /* chunks enqueued by this stream */ + union { + struct { + /* Scheduled streams list */ + struct list_head prio_list; + struct sctp_stream_priorities *prio_head; + }; + }; }; struct sctp_stream_out { @@ -1351,6 +1368,13 @@ struct sctp_stream { __u16 incnt; /* Current stream being sent, if any */ struct sctp_stream_out *out_curr; + union { + /* Fields used by priority scheduler */ + struct { + /* List of priorities scheduled */ + struct list_head prio_list; + }; + }; }; #define SCTP_STREAM_CLOSED 0x00 diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 00ac417d2c4f..850fa8b29d7e 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -1099,7 +1099,8 @@ struct sctp_add_streams { /* SCTP Stream schedulers */ enum sctp_sched_type { SCTP_SS_FCFS, - SCTP_SS_MAX = SCTP_SS_FCFS + SCTP_SS_PRIO, + SCTP_SS_MAX = SCTP_SS_PRIO }; #endif /* _UAPI_SCTP_H */ diff --git a/net/sctp/Makefile b/net/sctp/Makefile index 0f6e6d1d69fd..647c9cfd4e95 100644 --- a/net/sctp/Makefile +++ b/net/sctp/Makefile @@ -12,7 +12,7 @@ sctp-y := sm_statetable.o sm_statefuns.o sm_sideeffect.o \ inqueue.o outqueue.o ulpqueue.o \ tsnmap.o bind_addr.o socket.o primitive.o \ output.o input.o debug.o stream.o auth.o \ - offload.o stream_sched.o + offload.o stream_sched.o stream_sched_prio.o sctp_probe-y := probe.o diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c index 40a9a9de2b98..115ddb765169 100644 --- a/net/sctp/stream_sched.c +++ b/net/sctp/stream_sched.c @@ -121,8 +121,11 @@ static struct sctp_sched_ops sctp_sched_fcfs = { /* API to other parts of the stack */ +extern struct sctp_sched_ops sctp_sched_prio; + struct sctp_sched_ops *sctp_sched_ops[] = { &sctp_sched_fcfs, + &sctp_sched_prio, }; int sctp_sched_set_sched(struct sctp_association *asoc, diff --git a/net/sctp/stream_sched_prio.c b/net/sctp/stream_sched_prio.c new file mode 100644 index 000000000000..384dbf3c8760 --- /dev/null +++ b/net/sctp/stream_sched_prio.c @@ -0,0 +1,347 @@ +/* SCTP kernel implementation + * (C) Copyright Red Hat Inc. 2017 + * + * This file is part of the SCTP kernel implementation + * + * These functions manipulate sctp stream queue/scheduling. + * + * This SCTP implementation is free software; + * you can redistribute it and/or modify it under the terms of + * the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + * This SCTP implementation is distributed in the hope that it + * will be useful, but WITHOUT ANY WARRANTY; without even the implied + * ************************ + * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * See the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with GNU CC; see the file COPYING. If not, see + * . + * + * Please send any bug reports or fixes you make to the + * email addresched(es): + * lksctp developers + * + * Written or modified by: + * Marcelo Ricardo Leitner + */ + +#include +#include +#include +#include + +/* Priority handling + * RFC DRAFT ndata section 3.4 + */ + +static void sctp_sched_prio_unsched_all(struct sctp_stream *stream); + +static struct sctp_stream_priorities *sctp_sched_prio_new_head( + struct sctp_stream *stream, int prio, gfp_t gfp) +{ + struct sctp_stream_priorities *p; + + p = kmalloc(sizeof(*p), gfp); + if (!p) + return NULL; + + INIT_LIST_HEAD(&p->prio_sched); + INIT_LIST_HEAD(&p->active); + p->next = NULL; + p->prio = prio; + + return p; +} + +static struct sctp_stream_priorities *sctp_sched_prio_get_head( + struct sctp_stream *stream, int prio, gfp_t gfp) +{ + struct sctp_stream_priorities *p; + int i; + + /* Look into scheduled priorities first, as they are sorted and + * we can find it fast IF it's scheduled. + */ + list_for_each_entry(p, &stream->prio_list, prio_sched) { + if (p->prio == prio) + return p; + if (p->prio > prio) + break; + } + + /* No luck. So we search on all streams now. */ + for (i = 0; i < stream->outcnt; i++) { + if (!stream->out[i].ext) + continue; + + p = stream->out[i].ext->prio_head; + if (!p) + /* Means all other streams won't be initialized + * as well. + */ + break; + if (p->prio == prio) + return p; + } + + /* If not even there, allocate a new one. */ + return sctp_sched_prio_new_head(stream, prio, gfp); +} + +static void sctp_sched_prio_next_stream(struct sctp_stream_priorities *p) +{ + struct list_head *pos; + + pos = p->next->prio_list.next; + if (pos == &p->active) + pos = pos->next; + p->next = list_entry(pos, struct sctp_stream_out_ext, prio_list); +} + +static bool sctp_sched_prio_unsched(struct sctp_stream_out_ext *soute) +{ + bool scheduled = false; + + if (!list_empty(&soute->prio_list)) { + struct sctp_stream_priorities *prio_head = soute->prio_head; + + /* Scheduled */ + scheduled = true; + + if (prio_head->next == soute) + /* Try to move to the next stream */ + sctp_sched_prio_next_stream(prio_head); + + list_del_init(&soute->prio_list); + + /* Also unsched the priority if this was the last stream */ + if (list_empty(&prio_head->active)) { + list_del_init(&prio_head->prio_sched); + /* If there is no stream left, clear next */ + prio_head->next = NULL; + } + } + + return scheduled; +} + +static void sctp_sched_prio_sched(struct sctp_stream *stream, + struct sctp_stream_out_ext *soute) +{ + struct sctp_stream_priorities *prio, *prio_head; + + prio_head = soute->prio_head; + + /* Nothing to do if already scheduled */ + if (!list_empty(&soute->prio_list)) + return; + + /* Schedule the stream. If there is a next, we schedule the new + * one before it, so it's the last in round robin order. + * If there isn't, we also have to schedule the priority. + */ + if (prio_head->next) { + list_add(&soute->prio_list, prio_head->next->prio_list.prev); + return; + } + + list_add(&soute->prio_list, &prio_head->active); + prio_head->next = soute; + + list_for_each_entry(prio, &stream->prio_list, prio_sched) { + if (prio->prio > prio_head->prio) { + list_add(&prio_head->prio_sched, prio->prio_sched.prev); + return; + } + } + + list_add_tail(&prio_head->prio_sched, &stream->prio_list); +} + +static int sctp_sched_prio_set(struct sctp_stream *stream, __u16 sid, + __u16 prio, gfp_t gfp) +{ + struct sctp_stream_out *sout = &stream->out[sid]; + struct sctp_stream_out_ext *soute = sout->ext; + struct sctp_stream_priorities *prio_head, *old; + bool reschedule = false; + int i; + + prio_head = sctp_sched_prio_get_head(stream, prio, gfp); + if (!prio_head) + return -ENOMEM; + + reschedule = sctp_sched_prio_unsched(soute); + old = soute->prio_head; + soute->prio_head = prio_head; + if (reschedule) + sctp_sched_prio_sched(stream, soute); + + if (!old) + /* Happens when we set the priority for the first time */ + return 0; + + for (i = 0; i < stream->outcnt; i++) { + soute = stream->out[i].ext; + if (soute && soute->prio_head == old) + /* It's still in use, nothing else to do here. */ + return 0; + } + + /* No hits, we are good to free it. */ + kfree(old); + + return 0; +} + +static int sctp_sched_prio_get(struct sctp_stream *stream, __u16 sid, + __u16 *value) +{ + *value = stream->out[sid].ext->prio_head->prio; + return 0; +} + +static int sctp_sched_prio_init(struct sctp_stream *stream) +{ + INIT_LIST_HEAD(&stream->prio_list); + + return 0; +} + +static int sctp_sched_prio_init_sid(struct sctp_stream *stream, __u16 sid, + gfp_t gfp) +{ + INIT_LIST_HEAD(&stream->out[sid].ext->prio_list); + return sctp_sched_prio_set(stream, sid, 0, gfp); +} + +static void sctp_sched_prio_free(struct sctp_stream *stream) +{ + struct sctp_stream_priorities *prio, *n; + LIST_HEAD(list); + int i; + + /* As we don't keep a list of priorities, to avoid multiple + * frees we have to do it in 3 steps: + * 1. unsched everyone, so the lists are free to use in 2. + * 2. build the list of the priorities + * 3. free the list + */ + sctp_sched_prio_unsched_all(stream); + for (i = 0; i < stream->outcnt; i++) { + if (!stream->out[i].ext) + continue; + prio = stream->out[i].ext->prio_head; + if (prio && list_empty(&prio->prio_sched)) + list_add(&prio->prio_sched, &list); + } + list_for_each_entry_safe(prio, n, &list, prio_sched) { + list_del_init(&prio->prio_sched); + kfree(prio); + } +} + +static void sctp_sched_prio_enqueue(struct sctp_outq *q, + struct sctp_datamsg *msg) +{ + struct sctp_stream *stream; + struct sctp_chunk *ch; + __u16 sid; + + ch = list_first_entry(&msg->chunks, struct sctp_chunk, frag_list); + sid = sctp_chunk_stream_no(ch); + stream = &q->asoc->stream; + sctp_sched_prio_sched(stream, stream->out[sid].ext); +} + +static struct sctp_chunk *sctp_sched_prio_dequeue(struct sctp_outq *q) +{ + struct sctp_stream *stream = &q->asoc->stream; + struct sctp_stream_priorities *prio; + struct sctp_stream_out_ext *soute; + struct sctp_chunk *ch = NULL; + + /* Bail out quickly if queue is empty */ + if (list_empty(&q->out_chunk_list)) + goto out; + + /* Find which chunk is next. It's easy, it's either the current + * one or the first chunk on the next active stream. + */ + if (stream->out_curr) { + soute = stream->out_curr->ext; + } else { + prio = list_entry(stream->prio_list.next, + struct sctp_stream_priorities, prio_sched); + soute = prio->next; + } + ch = list_entry(soute->outq.next, struct sctp_chunk, stream_list); + sctp_sched_dequeue_common(q, ch); + +out: + return ch; +} + +static void sctp_sched_prio_dequeue_done(struct sctp_outq *q, + struct sctp_chunk *ch) +{ + struct sctp_stream_priorities *prio; + struct sctp_stream_out_ext *soute; + __u16 sid; + + /* Last chunk on that msg, move to the next stream on + * this priority. + */ + sid = sctp_chunk_stream_no(ch); + soute = q->asoc->stream.out[sid].ext; + prio = soute->prio_head; + + sctp_sched_prio_next_stream(prio); + + if (list_empty(&soute->outq)) + sctp_sched_prio_unsched(soute); +} + +static void sctp_sched_prio_sched_all(struct sctp_stream *stream) +{ + struct sctp_association *asoc; + struct sctp_stream_out *sout; + struct sctp_chunk *ch; + + asoc = container_of(stream, struct sctp_association, stream); + list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) { + __u16 sid; + + sid = sctp_chunk_stream_no(ch); + sout = &stream->out[sid]; + if (sout->ext) + sctp_sched_prio_sched(stream, sout->ext); + } +} + +static void sctp_sched_prio_unsched_all(struct sctp_stream *stream) +{ + struct sctp_stream_priorities *p, *tmp; + struct sctp_stream_out_ext *soute, *souttmp; + + list_for_each_entry_safe(p, tmp, &stream->prio_list, prio_sched) + list_for_each_entry_safe(soute, souttmp, &p->active, prio_list) + sctp_sched_prio_unsched(soute); +} + +struct sctp_sched_ops sctp_sched_prio = { + .set = sctp_sched_prio_set, + .get = sctp_sched_prio_get, + .init = sctp_sched_prio_init, + .init_sid = sctp_sched_prio_init_sid, + .free = sctp_sched_prio_free, + .enqueue = sctp_sched_prio_enqueue, + .dequeue = sctp_sched_prio_dequeue, + .dequeue_done = sctp_sched_prio_dequeue_done, + .sched_all = sctp_sched_prio_sched_all, + .unsched_all = sctp_sched_prio_unsched_all, +}; -- cgit v1.2.3-71-gd317 From ac1ed8b82cd60ba8e7d84103ac1414b8c577c485 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Tue, 3 Oct 2017 19:20:17 -0300 Subject: sctp: introduce round robin stream scheduler This patch introduces RFC Draft ndata section 3.2 Priority Based Scheduler (SCTP_SS_RR). Works by maintaining a list of enqueued streams and tracking the last one used to send data. When the datamsg is done, it switches to the next stream. See-also: https://tools.ietf.org/html/draft-ietf-tsvwg-sctp-ndata-13 Tested-by: Xin Long Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 11 +++ include/uapi/linux/sctp.h | 3 +- net/sctp/Makefile | 3 +- net/sctp/stream_sched.c | 2 + net/sctp/stream_sched_rr.c | 201 +++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 218 insertions(+), 2 deletions(-) create mode 100644 net/sctp/stream_sched_rr.c (limited to 'include/uapi/linux') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 40eb8d66a37c..16f949eef52f 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1348,6 +1348,10 @@ struct sctp_stream_out_ext { struct list_head prio_list; struct sctp_stream_priorities *prio_head; }; + /* Fields used by RR scheduler */ + struct { + struct list_head rr_list; + }; }; }; @@ -1374,6 +1378,13 @@ struct sctp_stream { /* List of priorities scheduled */ struct list_head prio_list; }; + /* Fields used by RR scheduler */ + struct { + /* List of streams scheduled */ + struct list_head rr_list; + /* The next stream stream in line */ + struct sctp_stream_out_ext *rr_next; + }; }; }; diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 850fa8b29d7e..6cd7d416ca40 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -1100,7 +1100,8 @@ struct sctp_add_streams { enum sctp_sched_type { SCTP_SS_FCFS, SCTP_SS_PRIO, - SCTP_SS_MAX = SCTP_SS_PRIO + SCTP_SS_RR, + SCTP_SS_MAX = SCTP_SS_RR }; #endif /* _UAPI_SCTP_H */ diff --git a/net/sctp/Makefile b/net/sctp/Makefile index 647c9cfd4e95..bf90c5397719 100644 --- a/net/sctp/Makefile +++ b/net/sctp/Makefile @@ -12,7 +12,8 @@ sctp-y := sm_statetable.o sm_statefuns.o sm_sideeffect.o \ inqueue.o outqueue.o ulpqueue.o \ tsnmap.o bind_addr.o socket.o primitive.o \ output.o input.o debug.o stream.o auth.o \ - offload.o stream_sched.o stream_sched_prio.o + offload.o stream_sched.o stream_sched_prio.o \ + stream_sched_rr.o sctp_probe-y := probe.o diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c index 115ddb765169..03513a9fa110 100644 --- a/net/sctp/stream_sched.c +++ b/net/sctp/stream_sched.c @@ -122,10 +122,12 @@ static struct sctp_sched_ops sctp_sched_fcfs = { /* API to other parts of the stack */ extern struct sctp_sched_ops sctp_sched_prio; +extern struct sctp_sched_ops sctp_sched_rr; struct sctp_sched_ops *sctp_sched_ops[] = { &sctp_sched_fcfs, &sctp_sched_prio, + &sctp_sched_rr, }; int sctp_sched_set_sched(struct sctp_association *asoc, diff --git a/net/sctp/stream_sched_rr.c b/net/sctp/stream_sched_rr.c new file mode 100644 index 000000000000..7612a438c5b9 --- /dev/null +++ b/net/sctp/stream_sched_rr.c @@ -0,0 +1,201 @@ +/* SCTP kernel implementation + * (C) Copyright Red Hat Inc. 2017 + * + * This file is part of the SCTP kernel implementation + * + * These functions manipulate sctp stream queue/scheduling. + * + * This SCTP implementation is free software; + * you can redistribute it and/or modify it under the terms of + * the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + * This SCTP implementation is distributed in the hope that it + * will be useful, but WITHOUT ANY WARRANTY; without even the implied + * ************************ + * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * See the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with GNU CC; see the file COPYING. If not, see + * . + * + * Please send any bug reports or fixes you make to the + * email addresched(es): + * lksctp developers + * + * Written or modified by: + * Marcelo Ricardo Leitner + */ + +#include +#include +#include +#include + +/* Priority handling + * RFC DRAFT ndata section 3.2 + */ +static void sctp_sched_rr_unsched_all(struct sctp_stream *stream); + +static void sctp_sched_rr_next_stream(struct sctp_stream *stream) +{ + struct list_head *pos; + + pos = stream->rr_next->rr_list.next; + if (pos == &stream->rr_list) + pos = pos->next; + stream->rr_next = list_entry(pos, struct sctp_stream_out_ext, rr_list); +} + +static void sctp_sched_rr_unsched(struct sctp_stream *stream, + struct sctp_stream_out_ext *soute) +{ + if (stream->rr_next == soute) + /* Try to move to the next stream */ + sctp_sched_rr_next_stream(stream); + + list_del_init(&soute->rr_list); + + /* If we have no other stream queued, clear next */ + if (list_empty(&stream->rr_list)) + stream->rr_next = NULL; +} + +static void sctp_sched_rr_sched(struct sctp_stream *stream, + struct sctp_stream_out_ext *soute) +{ + if (!list_empty(&soute->rr_list)) + /* Already scheduled. */ + return; + + /* Schedule the stream */ + list_add_tail(&soute->rr_list, &stream->rr_list); + + if (!stream->rr_next) + stream->rr_next = soute; +} + +static int sctp_sched_rr_set(struct sctp_stream *stream, __u16 sid, + __u16 prio, gfp_t gfp) +{ + return 0; +} + +static int sctp_sched_rr_get(struct sctp_stream *stream, __u16 sid, + __u16 *value) +{ + return 0; +} + +static int sctp_sched_rr_init(struct sctp_stream *stream) +{ + INIT_LIST_HEAD(&stream->rr_list); + stream->rr_next = NULL; + + return 0; +} + +static int sctp_sched_rr_init_sid(struct sctp_stream *stream, __u16 sid, + gfp_t gfp) +{ + INIT_LIST_HEAD(&stream->out[sid].ext->rr_list); + + return 0; +} + +static void sctp_sched_rr_free(struct sctp_stream *stream) +{ + sctp_sched_rr_unsched_all(stream); +} + +static void sctp_sched_rr_enqueue(struct sctp_outq *q, + struct sctp_datamsg *msg) +{ + struct sctp_stream *stream; + struct sctp_chunk *ch; + __u16 sid; + + ch = list_first_entry(&msg->chunks, struct sctp_chunk, frag_list); + sid = sctp_chunk_stream_no(ch); + stream = &q->asoc->stream; + sctp_sched_rr_sched(stream, stream->out[sid].ext); +} + +static struct sctp_chunk *sctp_sched_rr_dequeue(struct sctp_outq *q) +{ + struct sctp_stream *stream = &q->asoc->stream; + struct sctp_stream_out_ext *soute; + struct sctp_chunk *ch = NULL; + + /* Bail out quickly if queue is empty */ + if (list_empty(&q->out_chunk_list)) + goto out; + + /* Find which chunk is next */ + if (stream->out_curr) + soute = stream->out_curr->ext; + else + soute = stream->rr_next; + ch = list_entry(soute->outq.next, struct sctp_chunk, stream_list); + + sctp_sched_dequeue_common(q, ch); + +out: + return ch; +} + +static void sctp_sched_rr_dequeue_done(struct sctp_outq *q, + struct sctp_chunk *ch) +{ + struct sctp_stream_out_ext *soute; + __u16 sid; + + /* Last chunk on that msg, move to the next stream */ + sid = sctp_chunk_stream_no(ch); + soute = q->asoc->stream.out[sid].ext; + + sctp_sched_rr_next_stream(&q->asoc->stream); + + if (list_empty(&soute->outq)) + sctp_sched_rr_unsched(&q->asoc->stream, soute); +} + +static void sctp_sched_rr_sched_all(struct sctp_stream *stream) +{ + struct sctp_association *asoc; + struct sctp_stream_out_ext *soute; + struct sctp_chunk *ch; + + asoc = container_of(stream, struct sctp_association, stream); + list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) { + __u16 sid; + + sid = sctp_chunk_stream_no(ch); + soute = stream->out[sid].ext; + if (soute) + sctp_sched_rr_sched(stream, soute); + } +} + +static void sctp_sched_rr_unsched_all(struct sctp_stream *stream) +{ + struct sctp_stream_out_ext *soute, *tmp; + + list_for_each_entry_safe(soute, tmp, &stream->rr_list, rr_list) + sctp_sched_rr_unsched(stream, soute); +} + +struct sctp_sched_ops sctp_sched_rr = { + .set = sctp_sched_rr_set, + .get = sctp_sched_rr_get, + .init = sctp_sched_rr_init, + .init_sid = sctp_sched_rr_init_sid, + .free = sctp_sched_rr_free, + .enqueue = sctp_sched_rr_enqueue, + .dequeue = sctp_sched_rr_dequeue, + .dequeue_done = sctp_sched_rr_dequeue_done, + .sched_all = sctp_sched_rr_sched_all, + .unsched_all = sctp_sched_rr_unsched_all, +}; -- cgit v1.2.3-71-gd317 From 6263368c5b0b758d8639cad37a2a6493c9370425 Mon Sep 17 00:00:00 2001 From: Ed Blake Date: Tue, 26 Sep 2017 11:40:02 +0100 Subject: serial: Add define for max baud rate divisor Add a define for the maximum baud rate divisor, to improve code readability. Signed-off-by: Ed Blake Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_mtk.c | 2 +- drivers/tty/serial/8250/8250_omap.c | 4 ++-- drivers/tty/serial/8250/8250_port.c | 2 +- include/uapi/linux/serial_reg.h | 1 + 4 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/tty/serial/8250/8250_mtk.c b/drivers/tty/serial/8250/8250_mtk.c index fb45770d47aa..fef9823d7b4c 100644 --- a/drivers/tty/serial/8250/8250_mtk.c +++ b/drivers/tty/serial/8250/8250_mtk.c @@ -61,7 +61,7 @@ mtk8250_set_termios(struct uart_port *port, struct ktermios *termios, * registers to their default values. */ baud = uart_get_baud_rate(port, termios, old, - port->uartclk / 16 / 0xffff, + port->uartclk / 16 / UART_DIV_MAX, port->uartclk); if (baud <= 115200) { diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c index 833771bca0a5..4938d338e01f 100644 --- a/drivers/tty/serial/8250/8250_omap.c +++ b/drivers/tty/serial/8250/8250_omap.c @@ -199,7 +199,7 @@ static void omap_8250_get_divisor(struct uart_port *port, unsigned int baud, * Old custom speed handling. */ if (baud == 38400 && (port->flags & UPF_SPD_MASK) == UPF_SPD_CUST) { - priv->quot = port->custom_divisor & 0xffff; + priv->quot = port->custom_divisor & UART_DIV_MAX; /* * I assume that nobody is using this. But hey, if somebody * would like to specify the divisor _and_ the mode then the @@ -358,7 +358,7 @@ static void omap_8250_set_termios(struct uart_port *port, * Ask the core to calculate the divisor for us. */ baud = uart_get_baud_rate(port, termios, old, - port->uartclk / 16 / 0xffff, + port->uartclk / 16 / UART_DIV_MAX, port->uartclk / 13); omap_8250_get_divisor(port, baud, priv); diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index f0cc04f62b67..01ab2188a151 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -2601,7 +2601,7 @@ static unsigned int serial8250_get_baud_rate(struct uart_port *port, * causing transmission errors. */ return uart_get_baud_rate(port, termios, old, - port->uartclk / 16 / 0xffff, + port->uartclk / 16 / UART_DIV_MAX, port->uartclk); } diff --git a/include/uapi/linux/serial_reg.h b/include/uapi/linux/serial_reg.h index 5db76880b4ad..dea05724c760 100644 --- a/include/uapi/linux/serial_reg.h +++ b/include/uapi/linux/serial_reg.h @@ -157,6 +157,7 @@ */ #define UART_DLL 0 /* Out: Divisor Latch Low */ #define UART_DLM 1 /* Out: Divisor Latch High */ +#define UART_DIV_MAX 0xFFFF /* Max divisor value */ /* * LCR=0xBF (or DLAB=1 for 16C660) -- cgit v1.2.3-71-gd317 From 324bda9e6c5add86ba2e1066476481c48132aca0 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 2 Oct 2017 22:50:21 -0700 Subject: bpf: multi program support for cgroup+bpf introduce BPF_F_ALLOW_MULTI flag that can be used to attach multiple bpf programs to a cgroup. The difference between three possible flags for BPF_PROG_ATTACH command: - NONE(default): No further bpf programs allowed in the subtree. - BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program, the program in this cgroup yields to sub-cgroup program. - BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program, that cgroup program gets run in addition to the program in this cgroup. NONE and BPF_F_ALLOW_OVERRIDE existed before. This patch doesn't change their behavior. It only clarifies the semantics in relation to new flag. Only one program is allowed to be attached to a cgroup with NONE or BPF_F_ALLOW_OVERRIDE flag. Multiple programs are allowed to be attached to a cgroup with BPF_F_ALLOW_MULTI flag. They are executed in FIFO order (those that were attached first, run first) The programs of sub-cgroup are executed first, then programs of this cgroup and then programs of parent cgroup. All eligible programs are executed regardless of return code from earlier programs. To allow efficient execution of multiple programs attached to a cgroup and to avoid penalizing cgroups without any programs attached introduce 'struct bpf_prog_array' which is RCU protected array of pointers to bpf programs. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Acked-by: Martin KaFai Lau for cgroup bits Acked-by: Tejun Heo Signed-off-by: David S. Miller --- include/linux/bpf-cgroup.h | 46 +++-- include/linux/bpf.h | 32 ++++ include/linux/filter.h | 2 +- include/uapi/linux/bpf.h | 42 +++- kernel/bpf/cgroup.c | 467 ++++++++++++++++++++++++++++++++------------- kernel/bpf/core.c | 31 +++ kernel/bpf/syscall.c | 37 ++-- kernel/cgroup/cgroup.c | 28 ++- 8 files changed, 516 insertions(+), 169 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index d41d40ac3efd..102e56fbb6de 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -14,27 +14,42 @@ struct bpf_sock_ops_kern; extern struct static_key_false cgroup_bpf_enabled_key; #define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key) +struct bpf_prog_list { + struct list_head node; + struct bpf_prog *prog; +}; + +struct bpf_prog_array; + struct cgroup_bpf { - /* - * Store two sets of bpf_prog pointers, one for programs that are - * pinned directly to this cgroup, and one for those that are effective - * when this cgroup is accessed. + /* array of effective progs in this cgroup */ + struct bpf_prog_array __rcu *effective[MAX_BPF_ATTACH_TYPE]; + + /* attached progs to this cgroup and attach flags + * when flags == 0 or BPF_F_ALLOW_OVERRIDE the progs list will + * have either zero or one element + * when BPF_F_ALLOW_MULTI the list can have up to BPF_CGROUP_MAX_PROGS */ - struct bpf_prog *prog[MAX_BPF_ATTACH_TYPE]; - struct bpf_prog __rcu *effective[MAX_BPF_ATTACH_TYPE]; - bool disallow_override[MAX_BPF_ATTACH_TYPE]; + struct list_head progs[MAX_BPF_ATTACH_TYPE]; + u32 flags[MAX_BPF_ATTACH_TYPE]; + + /* temp storage for effective prog array used by prog_attach/detach */ + struct bpf_prog_array __rcu *inactive; }; void cgroup_bpf_put(struct cgroup *cgrp); -void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent); +int cgroup_bpf_inherit(struct cgroup *cgrp); -int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent, - struct bpf_prog *prog, enum bpf_attach_type type, - bool overridable); +int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags); +int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags); -/* Wrapper for __cgroup_bpf_update() protected by cgroup_mutex */ -int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type, bool overridable); +/* Wrapper for __cgroup_bpf_*() protected by cgroup_mutex */ +int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags); +int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags); int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, @@ -96,8 +111,7 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, struct cgroup_bpf {}; static inline void cgroup_bpf_put(struct cgroup *cgrp) {} -static inline void cgroup_bpf_inherit(struct cgroup *cgrp, - struct cgroup *parent) {} +static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 252f4bc9eb25..a6964b75f070 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -241,6 +241,38 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); +/* an array of programs to be executed under rcu_lock. + * + * Typical usage: + * ret = BPF_PROG_RUN_ARRAY(&bpf_prog_array, ctx, BPF_PROG_RUN); + * + * the structure returned by bpf_prog_array_alloc() should be populated + * with program pointers and the last pointer must be NULL. + * The user has to keep refcnt on the program and make sure the program + * is removed from the array before bpf_prog_put(). + * The 'struct bpf_prog_array *' should only be replaced with xchg() + * since other cpus are walking the array of pointers in parallel. + */ +struct bpf_prog_array { + struct rcu_head rcu; + struct bpf_prog *progs[0]; +}; + +struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); +void bpf_prog_array_free(struct bpf_prog_array __rcu *progs); + +#define BPF_PROG_RUN_ARRAY(array, ctx, func) \ + ({ \ + struct bpf_prog **_prog; \ + u32 _ret = 1; \ + rcu_read_lock(); \ + _prog = rcu_dereference(array)->progs; \ + for (; *_prog; _prog++) \ + _ret &= func(*_prog, ctx); \ + rcu_read_unlock(); \ + _ret; \ + }) + #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); diff --git a/include/linux/filter.h b/include/linux/filter.h index 911d454af107..2d2db394b0ca 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -481,7 +481,7 @@ struct sk_filter { struct bpf_prog *prog; }; -#define BPF_PROG_RUN(filter, ctx) (*filter->bpf_func)(ctx, filter->insnsi) +#define BPF_PROG_RUN(filter, ctx) (*(filter)->bpf_func)(ctx, (filter)->insnsi) #define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6d2137b4cf38..762f74bc6c47 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -143,11 +143,47 @@ enum bpf_attach_type { #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE -/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command - * to the given target_fd cgroup the descendent cgroup will be able to - * override effective bpf program that was inherited from this cgroup +/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command + * + * NONE(default): No further bpf programs allowed in the subtree. + * + * BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program, + * the program in this cgroup yields to sub-cgroup program. + * + * BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program, + * that cgroup program gets run in addition to the program in this cgroup. + * + * Only one program is allowed to be attached to a cgroup with + * NONE or BPF_F_ALLOW_OVERRIDE flag. + * Attaching another program on top of NONE or BPF_F_ALLOW_OVERRIDE will + * release old program and attach the new one. Attach flags has to match. + * + * Multiple programs are allowed to be attached to a cgroup with + * BPF_F_ALLOW_MULTI flag. They are executed in FIFO order + * (those that were attached first, run first) + * The programs of sub-cgroup are executed first, then programs of + * this cgroup and then programs of parent cgroup. + * When children program makes decision (like picking TCP CA or sock bind) + * parent program has a chance to override it. + * + * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups. + * A cgroup with NONE doesn't allow any programs in sub-cgroups. + * Ex1: + * cgrp1 (MULTI progs A, B) -> + * cgrp2 (OVERRIDE prog C) -> + * cgrp3 (MULTI prog D) -> + * cgrp4 (OVERRIDE prog E) -> + * cgrp5 (NONE prog F) + * the event in cgrp5 triggers execution of F,D,A,B in that order. + * if prog F is detached, the execution is E,D,A,B + * if prog F and D are detached, the execution is E,A,B + * if prog F, E and D are detached, the execution is C,A,B + * + * All eligible programs are executed regardless of return code from + * earlier programs. */ #define BPF_F_ALLOW_OVERRIDE (1U << 0) +#define BPF_F_ALLOW_MULTI (1U << 1) /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the * verifier will perform strict alignment checking as if the kernel diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 546113430049..6b7500bbdb53 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -27,129 +27,361 @@ void cgroup_bpf_put(struct cgroup *cgrp) { unsigned int type; - for (type = 0; type < ARRAY_SIZE(cgrp->bpf.prog); type++) { - struct bpf_prog *prog = cgrp->bpf.prog[type]; - - if (prog) { - bpf_prog_put(prog); + for (type = 0; type < ARRAY_SIZE(cgrp->bpf.progs); type++) { + struct list_head *progs = &cgrp->bpf.progs[type]; + struct bpf_prog_list *pl, *tmp; + + list_for_each_entry_safe(pl, tmp, progs, node) { + list_del(&pl->node); + bpf_prog_put(pl->prog); + kfree(pl); static_branch_dec(&cgroup_bpf_enabled_key); } + bpf_prog_array_free(cgrp->bpf.effective[type]); + } +} + +/* count number of elements in the list. + * it's slow but the list cannot be long + */ +static u32 prog_list_length(struct list_head *head) +{ + struct bpf_prog_list *pl; + u32 cnt = 0; + + list_for_each_entry(pl, head, node) { + if (!pl->prog) + continue; + cnt++; } + return cnt; +} + +/* if parent has non-overridable prog attached, + * disallow attaching new programs to the descendent cgroup. + * if parent has overridable or multi-prog, allow attaching + */ +static bool hierarchy_allows_attach(struct cgroup *cgrp, + enum bpf_attach_type type, + u32 new_flags) +{ + struct cgroup *p; + + p = cgroup_parent(cgrp); + if (!p) + return true; + do { + u32 flags = p->bpf.flags[type]; + u32 cnt; + + if (flags & BPF_F_ALLOW_MULTI) + return true; + cnt = prog_list_length(&p->bpf.progs[type]); + WARN_ON_ONCE(cnt > 1); + if (cnt == 1) + return !!(flags & BPF_F_ALLOW_OVERRIDE); + p = cgroup_parent(p); + } while (p); + return true; +} + +/* compute a chain of effective programs for a given cgroup: + * start from the list of programs in this cgroup and add + * all parent programs. + * Note that parent's F_ALLOW_OVERRIDE-type program is yielding + * to programs in this cgroup + */ +static int compute_effective_progs(struct cgroup *cgrp, + enum bpf_attach_type type, + struct bpf_prog_array __rcu **array) +{ + struct bpf_prog_array __rcu *progs; + struct bpf_prog_list *pl; + struct cgroup *p = cgrp; + int cnt = 0; + + /* count number of effective programs by walking parents */ + do { + if (cnt == 0 || (p->bpf.flags[type] & BPF_F_ALLOW_MULTI)) + cnt += prog_list_length(&p->bpf.progs[type]); + p = cgroup_parent(p); + } while (p); + + progs = bpf_prog_array_alloc(cnt, GFP_KERNEL); + if (!progs) + return -ENOMEM; + + /* populate the array with effective progs */ + cnt = 0; + p = cgrp; + do { + if (cnt == 0 || (p->bpf.flags[type] & BPF_F_ALLOW_MULTI)) + list_for_each_entry(pl, + &p->bpf.progs[type], node) { + if (!pl->prog) + continue; + rcu_dereference_protected(progs, 1)-> + progs[cnt++] = pl->prog; + } + p = cgroup_parent(p); + } while (p); + + *array = progs; + return 0; +} + +static void activate_effective_progs(struct cgroup *cgrp, + enum bpf_attach_type type, + struct bpf_prog_array __rcu *array) +{ + struct bpf_prog_array __rcu *old_array; + + old_array = xchg(&cgrp->bpf.effective[type], array); + /* free prog array after grace period, since __cgroup_bpf_run_*() + * might be still walking the array + */ + bpf_prog_array_free(old_array); } /** * cgroup_bpf_inherit() - inherit effective programs from parent * @cgrp: the cgroup to modify - * @parent: the parent to inherit from */ -void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent) +int cgroup_bpf_inherit(struct cgroup *cgrp) { - unsigned int type; +/* has to use marco instead of const int, since compiler thinks + * that array below is variable length + */ +#define NR ARRAY_SIZE(cgrp->bpf.effective) + struct bpf_prog_array __rcu *arrays[NR] = {}; + int i; - for (type = 0; type < ARRAY_SIZE(cgrp->bpf.effective); type++) { - struct bpf_prog *e; + for (i = 0; i < NR; i++) + INIT_LIST_HEAD(&cgrp->bpf.progs[i]); - e = rcu_dereference_protected(parent->bpf.effective[type], - lockdep_is_held(&cgroup_mutex)); - rcu_assign_pointer(cgrp->bpf.effective[type], e); - cgrp->bpf.disallow_override[type] = parent->bpf.disallow_override[type]; - } + for (i = 0; i < NR; i++) + if (compute_effective_progs(cgrp, i, &arrays[i])) + goto cleanup; + + for (i = 0; i < NR; i++) + activate_effective_progs(cgrp, i, arrays[i]); + + return 0; +cleanup: + for (i = 0; i < NR; i++) + bpf_prog_array_free(arrays[i]); + return -ENOMEM; } +#define BPF_CGROUP_MAX_PROGS 64 + /** - * __cgroup_bpf_update() - Update the pinned program of a cgroup, and + * __cgroup_bpf_attach() - Attach the program to a cgroup, and * propagate the change to descendants * @cgrp: The cgroup which descendants to traverse - * @parent: The parent of @cgrp, or %NULL if @cgrp is the root - * @prog: A new program to pin - * @type: Type of pinning operation (ingress/egress) - * - * Each cgroup has a set of two pointers for bpf programs; one for eBPF - * programs it owns, and which is effective for execution. - * - * If @prog is not %NULL, this function attaches a new program to the cgroup - * and releases the one that is currently attached, if any. @prog is then made - * the effective program of type @type in that cgroup. - * - * If @prog is %NULL, the currently attached program of type @type is released, - * and the effective program of the parent cgroup (if any) is inherited to - * @cgrp. - * - * Then, the descendants of @cgrp are walked and the effective program for - * each of them is set to the effective program of @cgrp unless the - * descendant has its own program attached, in which case the subbranch is - * skipped. This ensures that delegated subcgroups with own programs are left - * untouched. + * @prog: A program to attach + * @type: Type of attach operation * * Must be called with cgroup_mutex held. */ -int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent, - struct bpf_prog *prog, enum bpf_attach_type type, - bool new_overridable) +int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags) { - struct bpf_prog *old_prog, *effective = NULL; - struct cgroup_subsys_state *pos; - bool overridable = true; - - if (parent) { - overridable = !parent->bpf.disallow_override[type]; - effective = rcu_dereference_protected(parent->bpf.effective[type], - lockdep_is_held(&cgroup_mutex)); - } - - if (prog && effective && !overridable) - /* if parent has non-overridable prog attached, disallow - * attaching new programs to descendent cgroup - */ + struct list_head *progs = &cgrp->bpf.progs[type]; + struct bpf_prog *old_prog = NULL; + struct cgroup_subsys_state *css; + struct bpf_prog_list *pl; + bool pl_was_allocated; + u32 old_flags; + int err; + + if ((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI)) + /* invalid combination */ + return -EINVAL; + + if (!hierarchy_allows_attach(cgrp, type, flags)) return -EPERM; - if (prog && effective && overridable != new_overridable) - /* if parent has overridable prog attached, only - * allow overridable programs in descendent cgroup + if (!list_empty(progs) && cgrp->bpf.flags[type] != flags) + /* Disallow attaching non-overridable on top + * of existing overridable in this cgroup. + * Disallow attaching multi-prog if overridable or none */ return -EPERM; - old_prog = cgrp->bpf.prog[type]; - - if (prog) { - overridable = new_overridable; - effective = prog; - if (old_prog && - cgrp->bpf.disallow_override[type] == new_overridable) - /* disallow attaching non-overridable on top - * of existing overridable in this cgroup - * and vice versa - */ - return -EPERM; + if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS) + return -E2BIG; + + if (flags & BPF_F_ALLOW_MULTI) { + list_for_each_entry(pl, progs, node) + if (pl->prog == prog) + /* disallow attaching the same prog twice */ + return -EINVAL; + + pl = kmalloc(sizeof(*pl), GFP_KERNEL); + if (!pl) + return -ENOMEM; + pl_was_allocated = true; + pl->prog = prog; + list_add_tail(&pl->node, progs); + } else { + if (list_empty(progs)) { + pl = kmalloc(sizeof(*pl), GFP_KERNEL); + if (!pl) + return -ENOMEM; + pl_was_allocated = true; + list_add_tail(&pl->node, progs); + } else { + pl = list_first_entry(progs, typeof(*pl), node); + old_prog = pl->prog; + pl_was_allocated = false; + } + pl->prog = prog; } - if (!prog && !old_prog) - /* report error when trying to detach and nothing is attached */ - return -ENOENT; + old_flags = cgrp->bpf.flags[type]; + cgrp->bpf.flags[type] = flags; - cgrp->bpf.prog[type] = prog; + /* allocate and recompute effective prog arrays */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); - css_for_each_descendant_pre(pos, &cgrp->self) { - struct cgroup *desc = container_of(pos, struct cgroup, self); - - /* skip the subtree if the descendant has its own program */ - if (desc->bpf.prog[type] && desc != cgrp) { - pos = css_rightmost_descendant(pos); - } else { - rcu_assign_pointer(desc->bpf.effective[type], - effective); - desc->bpf.disallow_override[type] = !overridable; - } + err = compute_effective_progs(desc, type, &desc->bpf.inactive); + if (err) + goto cleanup; } - if (prog) - static_branch_inc(&cgroup_bpf_enabled_key); + /* all allocations were successful. Activate all prog arrays */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); + activate_effective_progs(desc, type, desc->bpf.inactive); + desc->bpf.inactive = NULL; + } + + static_branch_inc(&cgroup_bpf_enabled_key); if (old_prog) { bpf_prog_put(old_prog); static_branch_dec(&cgroup_bpf_enabled_key); } return 0; + +cleanup: + /* oom while computing effective. Free all computed effective arrays + * since they were not activated + */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); + + bpf_prog_array_free(desc->bpf.inactive); + desc->bpf.inactive = NULL; + } + + /* and cleanup the prog list */ + pl->prog = old_prog; + if (pl_was_allocated) { + list_del(&pl->node); + kfree(pl); + } + return err; +} + +/** + * __cgroup_bpf_detach() - Detach the program from a cgroup, and + * propagate the change to descendants + * @cgrp: The cgroup which descendants to traverse + * @prog: A program to detach or NULL + * @type: Type of detach operation + * + * Must be called with cgroup_mutex held. + */ +int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 unused_flags) +{ + struct list_head *progs = &cgrp->bpf.progs[type]; + u32 flags = cgrp->bpf.flags[type]; + struct bpf_prog *old_prog = NULL; + struct cgroup_subsys_state *css; + struct bpf_prog_list *pl; + int err; + + if (flags & BPF_F_ALLOW_MULTI) { + if (!prog) + /* to detach MULTI prog the user has to specify valid FD + * of the program to be detached + */ + return -EINVAL; + } else { + if (list_empty(progs)) + /* report error when trying to detach and nothing is attached */ + return -ENOENT; + } + + if (flags & BPF_F_ALLOW_MULTI) { + /* find the prog and detach it */ + list_for_each_entry(pl, progs, node) { + if (pl->prog != prog) + continue; + old_prog = prog; + /* mark it deleted, so it's ignored while + * recomputing effective + */ + pl->prog = NULL; + break; + } + if (!old_prog) + return -ENOENT; + } else { + /* to maintain backward compatibility NONE and OVERRIDE cgroups + * allow detaching with invalid FD (prog==NULL) + */ + pl = list_first_entry(progs, typeof(*pl), node); + old_prog = pl->prog; + pl->prog = NULL; + } + + /* allocate and recompute effective prog arrays */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); + + err = compute_effective_progs(desc, type, &desc->bpf.inactive); + if (err) + goto cleanup; + } + + /* all allocations were successful. Activate all prog arrays */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); + + activate_effective_progs(desc, type, desc->bpf.inactive); + desc->bpf.inactive = NULL; + } + + /* now can actually delete it from this cgroup list */ + list_del(&pl->node); + kfree(pl); + if (list_empty(progs)) + /* last program was detached, reset flags to zero */ + cgrp->bpf.flags[type] = 0; + + bpf_prog_put(old_prog); + static_branch_dec(&cgroup_bpf_enabled_key); + return 0; + +cleanup: + /* oom while computing effective. Free all computed effective arrays + * since they were not activated + */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); + + bpf_prog_array_free(desc->bpf.inactive); + desc->bpf.inactive = NULL; + } + + /* and restore back old_prog */ + pl->prog = old_prog; + return err; } /** @@ -171,36 +403,26 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, enum bpf_attach_type type) { - struct bpf_prog *prog; + unsigned int offset = skb->data - skb_network_header(skb); + struct sock *save_sk; struct cgroup *cgrp; - int ret = 0; + int ret; if (!sk || !sk_fullsock(sk)) return 0; - if (sk->sk_family != AF_INET && - sk->sk_family != AF_INET6) + if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6) return 0; cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - - rcu_read_lock(); - - prog = rcu_dereference(cgrp->bpf.effective[type]); - if (prog) { - unsigned int offset = skb->data - skb_network_header(skb); - struct sock *save_sk = skb->sk; - - skb->sk = sk; - __skb_push(skb, offset); - ret = bpf_prog_run_save_cb(prog, skb) == 1 ? 0 : -EPERM; - __skb_pull(skb, offset); - skb->sk = save_sk; - } - - rcu_read_unlock(); - - return ret; + save_sk = skb->sk; + skb->sk = sk; + __skb_push(skb, offset); + ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb, + bpf_prog_run_save_cb); + __skb_pull(skb, offset); + skb->sk = save_sk; + return ret == 1 ? 0 : -EPERM; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb); @@ -221,19 +443,10 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, enum bpf_attach_type type) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - struct bpf_prog *prog; - int ret = 0; - - - rcu_read_lock(); - - prog = rcu_dereference(cgrp->bpf.effective[type]); - if (prog) - ret = BPF_PROG_RUN(prog, sk) == 1 ? 0 : -EPERM; + int ret; - rcu_read_unlock(); - - return ret; + ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], sk, BPF_PROG_RUN); + return ret == 1 ? 0 : -EPERM; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); @@ -258,18 +471,10 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, enum bpf_attach_type type) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - struct bpf_prog *prog; - int ret = 0; - - - rcu_read_lock(); - - prog = rcu_dereference(cgrp->bpf.effective[type]); - if (prog) - ret = BPF_PROG_RUN(prog, sock_ops) == 1 ? 0 : -EPERM; - - rcu_read_unlock(); + int ret; - return ret; + ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], sock_ops, + BPF_PROG_RUN); + return ret == 1 ? 0 : -EPERM; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 917cc04a0a94..6b49e1991ae7 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1381,6 +1381,37 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) } EXPORT_SYMBOL_GPL(bpf_prog_select_runtime); +/* to avoid allocating empty bpf_prog_array for cgroups that + * don't have bpf program attached use one global 'empty_prog_array' + * It will not be modified the caller of bpf_prog_array_alloc() + * (since caller requested prog_cnt == 0) + * that pointer should be 'freed' by bpf_prog_array_free() + */ +static struct { + struct bpf_prog_array hdr; + struct bpf_prog *null_prog; +} empty_prog_array = { + .null_prog = NULL, +}; + +struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags) +{ + if (prog_cnt) + return kzalloc(sizeof(struct bpf_prog_array) + + sizeof(struct bpf_prog *) * (prog_cnt + 1), + flags); + + return &empty_prog_array.hdr; +} + +void bpf_prog_array_free(struct bpf_prog_array __rcu *progs) +{ + if (!progs || + progs == (struct bpf_prog_array __rcu *)&empty_prog_array.hdr) + return; + kfree_rcu(progs, rcu); +} + static void bpf_prog_free_deferred(struct work_struct *work) { struct bpf_prog_aux *aux; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b927da66f653..51bee695d32c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1168,6 +1168,9 @@ static int sockmap_get_from_fd(const union bpf_attr *attr, bool attach) return 0; } +#define BPF_F_ATTACH_MASK \ + (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI) + static int bpf_prog_attach(const union bpf_attr *attr) { enum bpf_prog_type ptype; @@ -1181,7 +1184,7 @@ static int bpf_prog_attach(const union bpf_attr *attr) if (CHECK_ATTR(BPF_PROG_ATTACH)) return -EINVAL; - if (attr->attach_flags & ~BPF_F_ALLOW_OVERRIDE) + if (attr->attach_flags & ~BPF_F_ATTACH_MASK) return -EINVAL; switch (attr->attach_type) { @@ -1212,8 +1215,8 @@ static int bpf_prog_attach(const union bpf_attr *attr) return PTR_ERR(cgrp); } - ret = cgroup_bpf_update(cgrp, prog, attr->attach_type, - attr->attach_flags & BPF_F_ALLOW_OVERRIDE); + ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type, + attr->attach_flags); if (ret) bpf_prog_put(prog); cgroup_put(cgrp); @@ -1225,6 +1228,8 @@ static int bpf_prog_attach(const union bpf_attr *attr) static int bpf_prog_detach(const union bpf_attr *attr) { + enum bpf_prog_type ptype; + struct bpf_prog *prog; struct cgroup *cgrp; int ret; @@ -1237,23 +1242,33 @@ static int bpf_prog_detach(const union bpf_attr *attr) switch (attr->attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: + ptype = BPF_PROG_TYPE_CGROUP_SKB; + break; case BPF_CGROUP_INET_SOCK_CREATE: + ptype = BPF_PROG_TYPE_CGROUP_SOCK; + break; case BPF_CGROUP_SOCK_OPS: - cgrp = cgroup_get_from_fd(attr->target_fd); - if (IS_ERR(cgrp)) - return PTR_ERR(cgrp); - - ret = cgroup_bpf_update(cgrp, NULL, attr->attach_type, false); - cgroup_put(cgrp); + ptype = BPF_PROG_TYPE_SOCK_OPS; break; case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: - ret = sockmap_get_from_fd(attr, false); - break; + return sockmap_get_from_fd(attr, false); default: return -EINVAL; } + cgrp = cgroup_get_from_fd(attr->target_fd); + if (IS_ERR(cgrp)) + return PTR_ERR(cgrp); + + prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); + if (IS_ERR(prog)) + prog = NULL; + + ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0); + if (prog) + bpf_prog_put(prog); + cgroup_put(cgrp); return ret; } diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index d6551cd45238..57eb866ae78d 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1896,6 +1896,9 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask, int ref_flags) if (ret) goto destroy_root; + ret = cgroup_bpf_inherit(root_cgrp); + WARN_ON_ONCE(ret); + trace_cgroup_setup_root(root); /* @@ -4713,6 +4716,9 @@ static struct cgroup *cgroup_create(struct cgroup *parent) cgrp->self.parent = &parent->self; cgrp->root = root; cgrp->level = level; + ret = cgroup_bpf_inherit(cgrp); + if (ret) + goto out_idr_free; for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) { cgrp->ancestor_ids[tcgrp->level] = tcgrp->id; @@ -4747,13 +4753,12 @@ static struct cgroup *cgroup_create(struct cgroup *parent) if (!cgroup_on_dfl(cgrp)) cgrp->subtree_control = cgroup_control(cgrp); - if (parent) - cgroup_bpf_inherit(cgrp, parent); - cgroup_propagate_control(cgrp); return cgrp; +out_idr_free: + cgroup_idr_remove(&root->cgroup_idr, cgrp->id); out_cancel_ref: percpu_ref_exit(&cgrp->self.refcnt); out_free_cgrp: @@ -5736,14 +5741,23 @@ void cgroup_sk_free(struct sock_cgroup_data *skcd) #endif /* CONFIG_SOCK_CGROUP_DATA */ #ifdef CONFIG_CGROUP_BPF -int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type, bool overridable) +int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags) +{ + int ret; + + mutex_lock(&cgroup_mutex); + ret = __cgroup_bpf_attach(cgrp, prog, type, flags); + mutex_unlock(&cgroup_mutex); + return ret; +} +int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags) { - struct cgroup *parent = cgroup_parent(cgrp); int ret; mutex_lock(&cgroup_mutex); - ret = __cgroup_bpf_update(cgrp, parent, prog, type, overridable); + ret = __cgroup_bpf_detach(cgrp, prog, type, flags); mutex_unlock(&cgroup_mutex); return ret; } -- cgit v1.2.3-71-gd317 From 468e2f64d220fe2dc11caa2bcb9b3a1e50fc7321 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 2 Oct 2017 22:50:22 -0700 Subject: bpf: introduce BPF_PROG_QUERY command introduce BPF_PROG_QUERY command to retrieve a set of either attached programs to given cgroup or a set of effective programs that will execute for events within a cgroup Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Acked-by: Martin KaFai Lau for cgroup bits Acked-by: Tejun Heo Signed-off-by: David S. Miller --- include/linux/bpf-cgroup.h | 4 ++++ include/linux/bpf.h | 3 +++ include/uapi/linux/bpf.h | 13 +++++++++++++ kernel/bpf/cgroup.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/core.c | 38 ++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 34 ++++++++++++++++++++++++++++++++++ kernel/cgroup/cgroup.c | 10 ++++++++++ 7 files changed, 148 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 102e56fbb6de..359b6f5d3d90 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -44,12 +44,16 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type, u32 flags); int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type, u32 flags); +int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, + union bpf_attr __user *uattr); /* Wrapper for __cgroup_bpf_*() protected by cgroup_mutex */ int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type, u32 flags); int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type, u32 flags); +int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, + union bpf_attr __user *uattr); int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a6964b75f070..a67daea731ab 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -260,6 +260,9 @@ struct bpf_prog_array { struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); void bpf_prog_array_free(struct bpf_prog_array __rcu *progs); +int bpf_prog_array_length(struct bpf_prog_array __rcu *progs); +int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, + __u32 __user *prog_ids, u32 cnt); #define BPF_PROG_RUN_ARRAY(array, ctx, func) \ ({ \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 762f74bc6c47..cb2b9f95160a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -92,6 +92,7 @@ enum bpf_cmd { BPF_PROG_GET_FD_BY_ID, BPF_MAP_GET_FD_BY_ID, BPF_OBJ_GET_INFO_BY_FD, + BPF_PROG_QUERY, }; enum bpf_map_type { @@ -211,6 +212,9 @@ enum bpf_attach_type { /* Specify numa node during map creation */ #define BPF_F_NUMA_NODE (1U << 2) +/* flags for BPF_PROG_QUERY */ +#define BPF_F_QUERY_EFFECTIVE (1U << 0) + #define BPF_OBJ_NAME_LEN 16U union bpf_attr { @@ -289,6 +293,15 @@ union bpf_attr { __u32 info_len; __aligned_u64 info; } info; + + struct { /* anonymous struct used by BPF_PROG_QUERY command */ + __u32 target_fd; /* container object to query */ + __u32 attach_type; + __u32 query_flags; + __u32 attach_flags; + __aligned_u64 prog_ids; + __u32 prog_cnt; + } query; } __attribute__((aligned(8))); /* BPF helper function descriptions: diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 6b7500bbdb53..e88abc0865d5 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -384,6 +384,52 @@ cleanup: return err; } +/* Must be called with cgroup_mutex held to avoid races. */ +int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); + enum bpf_attach_type type = attr->query.attach_type; + struct list_head *progs = &cgrp->bpf.progs[type]; + u32 flags = cgrp->bpf.flags[type]; + int cnt, ret = 0, i; + + if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) + cnt = bpf_prog_array_length(cgrp->bpf.effective[type]); + else + cnt = prog_list_length(progs); + + if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) + return -EFAULT; + if (copy_to_user(&uattr->query.prog_cnt, &cnt, sizeof(cnt))) + return -EFAULT; + if (attr->query.prog_cnt == 0 || !prog_ids || !cnt) + /* return early if user requested only program count + flags */ + return 0; + if (attr->query.prog_cnt < cnt) { + cnt = attr->query.prog_cnt; + ret = -ENOSPC; + } + + if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) { + return bpf_prog_array_copy_to_user(cgrp->bpf.effective[type], + prog_ids, cnt); + } else { + struct bpf_prog_list *pl; + u32 id; + + i = 0; + list_for_each_entry(pl, progs, node) { + id = pl->prog->aux->id; + if (copy_to_user(prog_ids + i, &id, sizeof(id))) + return -EFAULT; + if (++i == cnt) + break; + } + } + return ret; +} + /** * __cgroup_bpf_run_filter_skb() - Run a program for packet filtering * @sk: The socket sending or receiving traffic diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 6b49e1991ae7..eba966c09053 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1412,6 +1412,44 @@ void bpf_prog_array_free(struct bpf_prog_array __rcu *progs) kfree_rcu(progs, rcu); } +int bpf_prog_array_length(struct bpf_prog_array __rcu *progs) +{ + struct bpf_prog **prog; + u32 cnt = 0; + + rcu_read_lock(); + prog = rcu_dereference(progs)->progs; + for (; *prog; prog++) + cnt++; + rcu_read_unlock(); + return cnt; +} + +int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, + __u32 __user *prog_ids, u32 cnt) +{ + struct bpf_prog **prog; + u32 i = 0, id; + + rcu_read_lock(); + prog = rcu_dereference(progs)->progs; + for (; *prog; prog++) { + id = (*prog)->aux->id; + if (copy_to_user(prog_ids + i, &id, sizeof(id))) { + rcu_read_unlock(); + return -EFAULT; + } + if (++i == cnt) { + prog++; + break; + } + } + rcu_read_unlock(); + if (*prog) + return -ENOSPC; + return 0; +} + static void bpf_prog_free_deferred(struct work_struct *work) { struct bpf_prog_aux *aux; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 51bee695d32c..0048cb24ba7b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1272,6 +1272,37 @@ static int bpf_prog_detach(const union bpf_attr *attr) return ret; } +#define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt + +static int bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + struct cgroup *cgrp; + int ret; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (CHECK_ATTR(BPF_PROG_QUERY)) + return -EINVAL; + if (attr->query.query_flags & ~BPF_F_QUERY_EFFECTIVE) + return -EINVAL; + + switch (attr->query.attach_type) { + case BPF_CGROUP_INET_INGRESS: + case BPF_CGROUP_INET_EGRESS: + case BPF_CGROUP_INET_SOCK_CREATE: + case BPF_CGROUP_SOCK_OPS: + break; + default: + return -EINVAL; + } + cgrp = cgroup_get_from_fd(attr->query.target_fd); + if (IS_ERR(cgrp)) + return PTR_ERR(cgrp); + ret = cgroup_bpf_query(cgrp, attr, uattr); + cgroup_put(cgrp); + return ret; +} #endif /* CONFIG_CGROUP_BPF */ #define BPF_PROG_TEST_RUN_LAST_FIELD test.duration @@ -1568,6 +1599,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_PROG_DETACH: err = bpf_prog_detach(&attr); break; + case BPF_PROG_QUERY: + err = bpf_prog_query(&attr, uattr); + break; #endif case BPF_PROG_TEST_RUN: err = bpf_prog_test_run(&attr, uattr); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 57eb866ae78d..269512b94a94 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5761,4 +5761,14 @@ int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, mutex_unlock(&cgroup_mutex); return ret; } +int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + int ret; + + mutex_lock(&cgroup_mutex); + ret = __cgroup_bpf_query(cgrp, attr, uattr); + mutex_unlock(&cgroup_mutex); + return ret; +} #endif /* CONFIG_CGROUP_BPF */ -- cgit v1.2.3-71-gd317 From 6621dd29eb9b5e6774ec7a9a75161352fdea47fc Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Tue, 3 Oct 2017 13:53:23 +0200 Subject: dev: advertise the new nsid when the netns iface changes x-netns interfaces are bound to two netns: the link netns and the upper netns. Usually, this kind of interfaces is created in the link netns and then moved to the upper netns. At the end, the interface is visible only in the upper netns. The link nsid is advertised via netlink in the upper netns, thus the user always knows where is the link part. There is no such mechanism in the link netns. When the interface is moved to another netns, the user cannot "follow" it. This patch adds a new netlink attribute which helps to follow an interface which moves to another netns. When the interface is unregistered, the new nsid is advertised. If the interface is a x-netns interface (ie rtnl_link_ops->get_link_net is defined), the nsid is allocated if needed. CC: Jason A. Donenfeld Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 4 +++- include/uapi/linux/if_link.h | 1 + net/core/dev.c | 11 ++++++++--- net/core/rtnetlink.c | 31 ++++++++++++++++++++++--------- 4 files changed, 34 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index dea59c8eec54..1251638e60d3 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -17,9 +17,11 @@ extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, long expires, u32 error); void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change, gfp_t flags); +void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change, + gfp_t flags, int *new_nsid); struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned change, u32 event, - gfp_t flags); + gfp_t flags, int *new_nsid); void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags); diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index ea87bd708ee9..cd580fc0e58f 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -158,6 +158,7 @@ enum { IFLA_PAD, IFLA_XDP, IFLA_EVENT, + IFLA_NEW_NETNSID, __IFLA_MAX }; diff --git a/net/core/dev.c b/net/core/dev.c index 454f05441546..bffc75429184 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -145,6 +145,7 @@ #include #include #include +#include #include "net-sysfs.h" @@ -7204,7 +7205,7 @@ static void rollback_registered_many(struct list_head *head) if (!dev->rtnl_link_ops || dev->rtnl_link_state == RTNL_LINK_INITIALIZED) skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, - GFP_KERNEL); + GFP_KERNEL, NULL); /* * Flush the unicast and multicast chains @@ -8291,7 +8292,7 @@ EXPORT_SYMBOL(unregister_netdev); int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat) { - int err; + int err, new_nsid; ASSERT_RTNL(); @@ -8347,7 +8348,11 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char call_netdevice_notifiers(NETDEV_UNREGISTER, dev); rcu_barrier(); call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); - rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL); + if (dev->rtnl_link_ops && dev->rtnl_link_ops->get_link_net) + new_nsid = peernet2id_alloc(dev_net(dev), net); + else + new_nsid = peernet2id(dev_net(dev), net); + rtmsg_ifinfo_newnet(RTM_DELLINK, dev, ~0U, GFP_KERNEL, &new_nsid); /* * Flush the unicast and multicast chains diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 3fb1ca33cba4..1ee98b1369d5 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -915,6 +915,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */ + rtnl_xdp_size() /* IFLA_XDP */ + nla_total_size(4) /* IFLA_EVENT */ + + nla_total_size(4) /* IFLA_NEW_NETNSID */ + nla_total_size(1); /* IFLA_PROTO_DOWN */ } @@ -1384,7 +1385,7 @@ static int rtnl_fill_link_netnsid(struct sk_buff *skb, static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, unsigned int flags, u32 ext_filter_mask, - u32 event) + u32 event, int *new_nsid) { struct ifinfomsg *ifm; struct nlmsghdr *nlh; @@ -1472,6 +1473,10 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, if (rtnl_fill_link_netnsid(skb, dev)) goto nla_put_failure; + if (new_nsid && + nla_put_s32(skb, IFLA_NEW_NETNSID, *new_nsid) < 0) + goto nla_put_failure; + if (!(af_spec = nla_nest_start(skb, IFLA_AF_SPEC))) goto nla_put_failure; @@ -1701,7 +1706,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, 0, flags, - ext_filter_mask, 0); + ext_filter_mask, 0, NULL); if (err < 0) { if (likely(skb->len)) @@ -2808,7 +2813,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh, return -ENOBUFS; err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, 0, 0, ext_filter_mask, 0); + nlh->nlmsg_seq, 0, 0, ext_filter_mask, 0, NULL); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size */ WARN_ON(err == -EMSGSIZE); @@ -2893,7 +2898,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned int change, - u32 event, gfp_t flags) + u32 event, gfp_t flags, int *new_nsid) { struct net *net = dev_net(dev); struct sk_buff *skb; @@ -2904,7 +2909,8 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, if (skb == NULL) goto errout; - err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0, event); + err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0, event, + new_nsid); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -2927,14 +2933,14 @@ void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags) static void rtmsg_ifinfo_event(int type, struct net_device *dev, unsigned int change, u32 event, - gfp_t flags) + gfp_t flags, int *new_nsid) { struct sk_buff *skb; if (dev->reg_state != NETREG_REGISTERED) return; - skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags); + skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags, new_nsid); if (skb) rtmsg_ifinfo_send(skb, dev, flags); } @@ -2942,10 +2948,17 @@ static void rtmsg_ifinfo_event(int type, struct net_device *dev, void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change, gfp_t flags) { - rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags); + rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags, NULL); } EXPORT_SYMBOL(rtmsg_ifinfo); +void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change, + gfp_t flags, int *new_nsid) +{ + rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags, + new_nsid); +} + static int nlmsg_populate_fdb_fill(struct sk_buff *skb, struct net_device *dev, u8 *addr, u16 vid, u32 pid, u32 seq, @@ -4321,7 +4334,7 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi case NETDEV_RESEND_IGMP: case NETDEV_CHANGEINFODATA: rtmsg_ifinfo_event(RTM_NEWLINK, dev, 0, rtnl_get_event(event), - GFP_KERNEL); + GFP_KERNEL, NULL); break; default: break; -- cgit v1.2.3-71-gd317 From 413a4317aca7d6367d57a5971b0c461f03851207 Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Thu, 5 Oct 2017 16:46:53 -0400 Subject: VSOCK: add sock_diag interface This patch adds the sock_diag interface for querying sockets from userspace. Tools like ss(8) and netstat(8) can use this interface to list open sockets. The userspace ABI is defined in and includes netlink request and response structs. The request can query sockets based on their sk_state (e.g. listening sockets only) and the response contains socket information fields including the local/remote addresses, inode number, etc. This patch does not dump VMCI pending sockets because I have only tested the virtio transport, which does not use pending sockets. Support can be added later by extending vsock_diag_dump() if needed by VMCI users. Signed-off-by: Stefan Hajnoczi Signed-off-by: David S. Miller --- MAINTAINERS | 2 + include/uapi/linux/vm_sockets_diag.h | 33 +++++++ net/vmw_vsock/Kconfig | 10 ++ net/vmw_vsock/Makefile | 3 + net/vmw_vsock/diag.c | 186 +++++++++++++++++++++++++++++++++++ 5 files changed, 234 insertions(+) create mode 100644 include/uapi/linux/vm_sockets_diag.h create mode 100644 net/vmw_vsock/diag.c (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index d0cbb3d7a0ca..0fd9121953bb 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14286,6 +14286,8 @@ S: Maintained F: include/linux/virtio_vsock.h F: include/uapi/linux/virtio_vsock.h F: include/uapi/linux/vsockmon.h +F: include/uapi/linux/vm_sockets_diag.h +F: net/vmw_vsock/diag.c F: net/vmw_vsock/af_vsock_tap.c F: net/vmw_vsock/virtio_transport_common.c F: net/vmw_vsock/virtio_transport.c diff --git a/include/uapi/linux/vm_sockets_diag.h b/include/uapi/linux/vm_sockets_diag.h new file mode 100644 index 000000000000..14cd7dc5a187 --- /dev/null +++ b/include/uapi/linux/vm_sockets_diag.h @@ -0,0 +1,33 @@ +/* AF_VSOCK sock_diag(7) interface for querying open sockets */ + +#ifndef _UAPI__VM_SOCKETS_DIAG_H__ +#define _UAPI__VM_SOCKETS_DIAG_H__ + +#include + +/* Request */ +struct vsock_diag_req { + __u8 sdiag_family; /* must be AF_VSOCK */ + __u8 sdiag_protocol; /* must be 0 */ + __u16 pad; /* must be 0 */ + __u32 vdiag_states; /* query bitmap (e.g. 1 << TCP_LISTEN) */ + __u32 vdiag_ino; /* must be 0 (reserved) */ + __u32 vdiag_show; /* must be 0 (reserved) */ + __u32 vdiag_cookie[2]; +}; + +/* Response */ +struct vsock_diag_msg { + __u8 vdiag_family; /* AF_VSOCK */ + __u8 vdiag_type; /* SOCK_STREAM or SOCK_DGRAM */ + __u8 vdiag_state; /* sk_state (e.g. TCP_LISTEN) */ + __u8 vdiag_shutdown; /* local RCV_SHUTDOWN | SEND_SHUTDOWN */ + __u32 vdiag_src_cid; + __u32 vdiag_src_port; + __u32 vdiag_dst_cid; + __u32 vdiag_dst_port; + __u32 vdiag_ino; + __u32 vdiag_cookie[2]; +}; + +#endif /* _UAPI__VM_SOCKETS_DIAG_H__ */ diff --git a/net/vmw_vsock/Kconfig b/net/vmw_vsock/Kconfig index a24369d175fd..970f96489fe7 100644 --- a/net/vmw_vsock/Kconfig +++ b/net/vmw_vsock/Kconfig @@ -15,6 +15,16 @@ config VSOCKETS To compile this driver as a module, choose M here: the module will be called vsock. If unsure, say N. +config VSOCKETS_DIAG + tristate "Virtual Sockets monitoring interface" + depends on VSOCKETS + default y + help + Support for PF_VSOCK sockets monitoring interface used by the ss tool. + If unsure, say Y. + + Enable this module so userspace applications can query open sockets. + config VMWARE_VMCI_VSOCKETS tristate "VMware VMCI transport for Virtual Sockets" depends on VSOCKETS && VMWARE_VMCI diff --git a/net/vmw_vsock/Makefile b/net/vmw_vsock/Makefile index e63d574234a9..64afc06805da 100644 --- a/net/vmw_vsock/Makefile +++ b/net/vmw_vsock/Makefile @@ -1,4 +1,5 @@ obj-$(CONFIG_VSOCKETS) += vsock.o +obj-$(CONFIG_VSOCKETS_DIAG) += vsock_diag.o obj-$(CONFIG_VMWARE_VMCI_VSOCKETS) += vmw_vsock_vmci_transport.o obj-$(CONFIG_VIRTIO_VSOCKETS) += vmw_vsock_virtio_transport.o obj-$(CONFIG_VIRTIO_VSOCKETS_COMMON) += vmw_vsock_virtio_transport_common.o @@ -6,6 +7,8 @@ obj-$(CONFIG_HYPERV_VSOCKETS) += hv_sock.o vsock-y += af_vsock.o af_vsock_tap.o vsock_addr.o +vsock_diag-y += diag.o + vmw_vsock_vmci_transport-y += vmci_transport.o vmci_transport_notify.o \ vmci_transport_notify_qstate.o diff --git a/net/vmw_vsock/diag.c b/net/vmw_vsock/diag.c new file mode 100644 index 000000000000..31b567652250 --- /dev/null +++ b/net/vmw_vsock/diag.c @@ -0,0 +1,186 @@ +/* + * vsock sock_diag(7) module + * + * Copyright (C) 2017 Red Hat, Inc. + * Author: Stefan Hajnoczi + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation version 2 and no later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include +#include +#include +#include + +static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, + u32 portid, u32 seq, u32 flags) +{ + struct vsock_sock *vsk = vsock_sk(sk); + struct vsock_diag_msg *rep; + struct nlmsghdr *nlh; + + nlh = nlmsg_put(skb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rep), + flags); + if (!nlh) + return -EMSGSIZE; + + rep = nlmsg_data(nlh); + rep->vdiag_family = AF_VSOCK; + + /* Lock order dictates that sk_lock is acquired before + * vsock_table_lock, so we cannot lock here. Simply don't take + * sk_lock; sk is guaranteed to stay alive since vsock_table_lock is + * held. + */ + rep->vdiag_type = sk->sk_type; + rep->vdiag_state = sk->sk_state; + rep->vdiag_shutdown = sk->sk_shutdown; + rep->vdiag_src_cid = vsk->local_addr.svm_cid; + rep->vdiag_src_port = vsk->local_addr.svm_port; + rep->vdiag_dst_cid = vsk->remote_addr.svm_cid; + rep->vdiag_dst_port = vsk->remote_addr.svm_port; + rep->vdiag_ino = sock_i_ino(sk); + + sock_diag_save_cookie(sk, rep->vdiag_cookie); + + return 0; +} + +static int vsock_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct vsock_diag_req *req; + struct vsock_sock *vsk; + unsigned int bucket; + unsigned int last_i; + unsigned int table; + struct net *net; + unsigned int i; + + req = nlmsg_data(cb->nlh); + net = sock_net(skb->sk); + + /* State saved between calls: */ + table = cb->args[0]; + bucket = cb->args[1]; + i = last_i = cb->args[2]; + + /* TODO VMCI pending sockets? */ + + spin_lock_bh(&vsock_table_lock); + + /* Bind table (locally created sockets) */ + if (table == 0) { + while (bucket < ARRAY_SIZE(vsock_bind_table)) { + struct list_head *head = &vsock_bind_table[bucket]; + + i = 0; + list_for_each_entry(vsk, head, bound_table) { + struct sock *sk = sk_vsock(vsk); + + if (!net_eq(sock_net(sk), net)) + continue; + if (i < last_i) + goto next_bind; + if (!(req->vdiag_states & (1 << sk->sk_state))) + goto next_bind; + if (sk_diag_fill(sk, skb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI) < 0) + goto done; +next_bind: + i++; + } + last_i = 0; + bucket++; + } + + table++; + bucket = 0; + } + + /* Connected table (accepted connections) */ + while (bucket < ARRAY_SIZE(vsock_connected_table)) { + struct list_head *head = &vsock_connected_table[bucket]; + + i = 0; + list_for_each_entry(vsk, head, connected_table) { + struct sock *sk = sk_vsock(vsk); + + /* Skip sockets we've already seen above */ + if (__vsock_in_bound_table(vsk)) + continue; + + if (!net_eq(sock_net(sk), net)) + continue; + if (i < last_i) + goto next_connected; + if (!(req->vdiag_states & (1 << sk->sk_state))) + goto next_connected; + if (sk_diag_fill(sk, skb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI) < 0) + goto done; +next_connected: + i++; + } + last_i = 0; + bucket++; + } + +done: + spin_unlock_bh(&vsock_table_lock); + + cb->args[0] = table; + cb->args[1] = bucket; + cb->args[2] = i; + + return skb->len; +} + +static int vsock_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) +{ + int hdrlen = sizeof(struct vsock_diag_req); + struct net *net = sock_net(skb->sk); + + if (nlmsg_len(h) < hdrlen) + return -EINVAL; + + if (h->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .dump = vsock_diag_dump, + }; + return netlink_dump_start(net->diag_nlsk, skb, h, &c); + } + + return -EOPNOTSUPP; +} + +static const struct sock_diag_handler vsock_diag_handler = { + .family = AF_VSOCK, + .dump = vsock_diag_handler_dump, +}; + +static int __init vsock_diag_init(void) +{ + return sock_diag_register(&vsock_diag_handler); +} + +static void __exit vsock_diag_exit(void) +{ + sock_diag_unregister(&vsock_diag_handler); +} + +module_init(vsock_diag_init); +module_exit(vsock_diag_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, + 40 /* AF_VSOCK */); -- cgit v1.2.3-71-gd317 From bdc476413dcdb5c38a7dec90fb2bca327021273a Mon Sep 17 00:00:00 2001 From: Amine Kherbouche Date: Wed, 4 Oct 2017 19:35:57 +0200 Subject: ip_tunnel: add mpls over gre support This commit introduces the MPLSoGRE support (RFC 4023), using ip tunnel API by simply adding ipgre_tunnel_encap_(add|del)_mpls_ops() and the new tunnel type TUNNEL_ENCAP_MPLS. Signed-off-by: Amine Kherbouche Signed-off-by: David S. Miller --- include/uapi/linux/if_tunnel.h | 1 + net/mpls/af_mpls.c | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 2e520883c054..a2f48c01365e 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -84,6 +84,7 @@ enum tunnel_encap_types { TUNNEL_ENCAP_NONE, TUNNEL_ENCAP_FOU, TUNNEL_ENCAP_GUE, + TUNNEL_ENCAP_MPLS, }; #define TUNNEL_ENCAP_FLAG_CSUM (1<<0) diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index c5b9ce41d66f..9745e8f69810 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #if IS_ENABLED(CONFIG_IPV6) #include @@ -39,6 +40,36 @@ static int one = 1; static int label_limit = (1 << 20) - 1; static int ttl_max = 255; +#if IS_ENABLED(CONFIG_NET_IP_TUNNEL) +size_t ipgre_mpls_encap_hlen(struct ip_tunnel_encap *e) +{ + return sizeof(struct mpls_shim_hdr); +} + +static const struct ip_tunnel_encap_ops mpls_iptun_ops = { + .encap_hlen = ipgre_mpls_encap_hlen, +}; + +static int ipgre_tunnel_encap_add_mpls_ops(void) +{ + return ip_tunnel_encap_add_ops(&mpls_iptun_ops, TUNNEL_ENCAP_MPLS); +} + +static void ipgre_tunnel_encap_del_mpls_ops(void) +{ + ip_tunnel_encap_del_ops(&mpls_iptun_ops, TUNNEL_ENCAP_MPLS); +} +#else +static int ipgre_tunnel_encap_add_mpls_ops(void) +{ + return 0; +} + +static void ipgre_tunnel_encap_del_mpls_ops(void) +{ +} +#endif + static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt, struct nlmsghdr *nlh, struct net *net, u32 portid, unsigned int nlm_flags); @@ -2485,6 +2516,10 @@ static int __init mpls_init(void) 0); rtnl_register(PF_MPLS, RTM_GETNETCONF, mpls_netconf_get_devconf, mpls_netconf_dump_devconf, 0); + err = ipgre_tunnel_encap_add_mpls_ops(); + if (err) + pr_err("Can't add mpls over gre tunnel ops\n"); + err = 0; out: return err; @@ -2502,6 +2537,7 @@ static void __exit mpls_exit(void) dev_remove_pack(&mpls_packet_type); unregister_netdevice_notifier(&mpls_dev_notifier); unregister_pernet_subsys(&mpls_net_ops); + ipgre_tunnel_encap_del_mpls_ops(); } module_exit(mpls_exit); -- cgit v1.2.3-71-gd317 From 908432ca84fc229e906ba164219e9ad0fe56f755 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 5 Oct 2017 09:19:20 -0700 Subject: bpf: add helper bpf_perf_event_read_value for perf event array map Hardware pmu counters are limited resources. When there are more pmu based perf events opened than available counters, kernel will multiplex these events so each event gets certain percentage (but not 100%) of the pmu time. In case that multiplexing happens, the number of samples or counter value will not reflect the case compared to no multiplexing. This makes comparison between different runs difficult. Typically, the number of samples or counter value should be normalized before comparing to other experiments. The typical normalization is done like: normalized_num_samples = num_samples * time_enabled / time_running normalized_counter_value = counter_value * time_enabled / time_running where time_enabled is the time enabled for event and time_running is the time running for event since last normalization. This patch adds helper bpf_perf_event_read_value for kprobed based perf event array map, to read perf counter and enabled/running time. The enabled/running time is accumulated since the perf event open. To achieve scaling factor between two bpf invocations, users can can use cpu_id as the key (which is typical for perf array usage model) to remember the previous value and do the calculation inside the bpf program. Signed-off-by: Yonghong Song Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 21 +++++++++++++++++++-- kernel/bpf/verifier.c | 4 +++- kernel/trace/bpf_trace.c | 45 +++++++++++++++++++++++++++++++++++++++++---- 3 files changed, 63 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6082faf5fd2a..7b57a212c7d7 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -641,6 +641,14 @@ union bpf_attr { * @xdp_md: pointer to xdp_md * @delta: An positive/negative integer to be added to xdp_md.data_meta * Return: 0 on success or negative on error + * + * int bpf_perf_event_read_value(map, flags, buf, buf_size) + * read perf event counter value and perf event enabled/running time + * @map: pointer to perf_event_array map + * @flags: index of event in the map or bitmask flags + * @buf: buf to fill + * @buf_size: size of the buf + * Return: 0 on success or negative error code */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -697,7 +705,8 @@ union bpf_attr { FN(redirect_map), \ FN(sk_redirect_map), \ FN(sock_map_update), \ - FN(xdp_adjust_meta), + FN(xdp_adjust_meta), \ + FN(perf_event_read_value), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -741,7 +750,9 @@ enum bpf_func_id { #define BPF_F_ZERO_CSUM_TX (1ULL << 1) #define BPF_F_DONT_FRAGMENT (1ULL << 2) -/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */ +/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and + * BPF_FUNC_perf_event_read_value flags. + */ #define BPF_F_INDEX_MASK 0xffffffffULL #define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK /* BPF_FUNC_perf_event_output for sk_buff input context. */ @@ -934,4 +945,10 @@ enum { #define TCP_BPF_IW 1001 /* Set TCP initial congestion window */ #define TCP_BPF_SNDCWND_CLAMP 1002 /* Set sndcwnd_clamp */ +struct bpf_perf_event_value { + __u64 counter; + __u64 enabled; + __u64 running; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 52b022310f6a..590125e29161 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1552,7 +1552,8 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) break; 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_perf_event_output && + func_id != BPF_FUNC_perf_event_read_value) goto error; break; case BPF_MAP_TYPE_STACK_TRACE: @@ -1595,6 +1596,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) break; case BPF_FUNC_perf_event_read: case BPF_FUNC_perf_event_output: + case BPF_FUNC_perf_event_read_value: if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) goto error; break; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 95888ae6c263..0be86cc0130e 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -255,14 +255,14 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void) return &bpf_trace_printk_proto; } -BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) +static __always_inline int +get_map_perf_counter(struct bpf_map *map, u64 flags, + u64 *value, u64 *enabled, u64 *running) { struct bpf_array *array = container_of(map, struct bpf_array, map); unsigned int cpu = smp_processor_id(); u64 index = flags & BPF_F_INDEX_MASK; struct bpf_event_entry *ee; - u64 value = 0; - int err; if (unlikely(flags & ~(BPF_F_INDEX_MASK))) return -EINVAL; @@ -275,7 +275,15 @@ BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) if (!ee) return -ENOENT; - err = perf_event_read_local(ee->event, &value, NULL, NULL); + return perf_event_read_local(ee->event, value, enabled, running); +} + +BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) +{ + u64 value = 0; + int err; + + err = get_map_perf_counter(map, flags, &value, NULL, NULL); /* * this api is ugly since we miss [-22..-2] range of valid * counter values, but that's uapi @@ -293,6 +301,33 @@ static const struct bpf_func_proto bpf_perf_event_read_proto = { .arg2_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_perf_event_read_value, struct bpf_map *, map, u64, flags, + struct bpf_perf_event_value *, buf, u32, size) +{ + int err = -EINVAL; + + if (unlikely(size != sizeof(struct bpf_perf_event_value))) + goto clear; + err = get_map_perf_counter(map, flags, &buf->counter, &buf->enabled, + &buf->running); + if (unlikely(err)) + goto clear; + return 0; +clear: + memset(buf, 0, size); + return err; +} + +static const struct bpf_func_proto bpf_perf_event_read_value_proto = { + .func = bpf_perf_event_read_value, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg4_type = ARG_CONST_SIZE, +}; + static DEFINE_PER_CPU(struct perf_sample_data, bpf_sd); static __always_inline u64 @@ -499,6 +534,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func return &bpf_perf_event_output_proto; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto; + case BPF_FUNC_perf_event_read_value: + return &bpf_perf_event_read_value_proto; default: return tracing_func_proto(func_id); } -- cgit v1.2.3-71-gd317 From 4bebdc7a85aa400c0222b5329861e4ad9252f1e5 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 5 Oct 2017 09:19:22 -0700 Subject: bpf: add helper bpf_perf_prog_read_value This patch adds helper bpf_perf_prog_read_cvalue for perf event based bpf programs, to read event counter and enabled/running time. The enabled/running time is accumulated since the perf event open. The typical use case for perf event based bpf program is to attach itself to a single event. In such cases, if it is desirable to get scaling factor between two bpf invocations, users can can save the time values in a map, and use the value from the map and the current value to calculate the scaling factor. Signed-off-by: Yonghong Song Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 10 +++++++++- kernel/trace/bpf_trace.c | 28 ++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7b57a212c7d7..5bbbec17aa5a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -649,6 +649,13 @@ union bpf_attr { * @buf: buf to fill * @buf_size: size of the buf * Return: 0 on success or negative error code + * + * int bpf_perf_prog_read_value(ctx, buf, buf_size) + * read perf prog attached perf event counter and enabled/running time + * @ctx: pointer to ctx + * @buf: buf to fill + * @buf_size: size of the buf + * Return : 0 on success or negative error code */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -706,7 +713,8 @@ union bpf_attr { FN(sk_redirect_map), \ FN(sock_map_update), \ FN(xdp_adjust_meta), \ - FN(perf_event_read_value), + FN(perf_event_read_value), \ + FN(perf_prog_read_value), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 0be86cc0130e..04ea5314f2bc 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -613,6 +613,32 @@ static const struct bpf_func_proto bpf_get_stackid_proto_tp = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_3(bpf_perf_prog_read_value_tp, struct bpf_perf_event_data_kern *, ctx, + struct bpf_perf_event_value *, buf, u32, size) +{ + int err = -EINVAL; + + if (unlikely(size != sizeof(struct bpf_perf_event_value))) + goto clear; + err = perf_event_read_local(ctx->event, &buf->counter, &buf->enabled, + &buf->running); + if (unlikely(err)) + goto clear; + return 0; +clear: + memset(buf, 0, size); + return err; +} + +static const struct bpf_func_proto bpf_perf_prog_read_value_proto_tp = { + .func = bpf_perf_prog_read_value_tp, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE, +}; + static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id) { switch (func_id) { @@ -620,6 +646,8 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id) return &bpf_perf_event_output_proto_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_tp; + case BPF_FUNC_perf_prog_read_value: + return &bpf_perf_prog_read_value_proto_tp; default: return tracing_func_proto(func_id); } -- cgit v1.2.3-71-gd317 From 067cae47771c864604969fd902efe10916e0d79c Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 5 Oct 2017 21:52:12 -0700 Subject: bpf: Use char in prog and map name Instead of u8, use char for prog and map name. It can avoid the userspace tool getting compiler's signess warning. The bpf_prog_aux, bpf_map, bpf_attr, bpf_prog_info and bpf_map_info are changed. Signed-off-by: Martin KaFai Lau Cc: Jakub Kicinski Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 4 ++-- include/uapi/linux/bpf.h | 8 ++++---- tools/include/uapi/linux/bpf.h | 8 ++++---- 3 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a67daea731ab..bc7da2ddfcaf 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -56,7 +56,7 @@ struct bpf_map { struct work_struct work; atomic_t usercnt; struct bpf_map *inner_map_meta; - u8 name[BPF_OBJ_NAME_LEN]; + char name[BPF_OBJ_NAME_LEN]; }; /* function argument constraints */ @@ -189,7 +189,7 @@ struct bpf_prog_aux { struct bpf_prog *prog; struct user_struct *user; u64 load_time; /* ns since boottime */ - u8 name[BPF_OBJ_NAME_LEN]; + char name[BPF_OBJ_NAME_LEN]; union { struct work_struct work; struct rcu_head rcu; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 5bbbec17aa5a..6db9e1d679cd 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -230,7 +230,7 @@ union bpf_attr { __u32 numa_node; /* numa node (effective only if * BPF_F_NUMA_NODE is set). */ - __u8 map_name[BPF_OBJ_NAME_LEN]; + char map_name[BPF_OBJ_NAME_LEN]; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -253,7 +253,7 @@ union bpf_attr { __aligned_u64 log_buf; /* user supplied buffer */ __u32 kern_version; /* checked when prog_type=kprobe */ __u32 prog_flags; - __u8 prog_name[BPF_OBJ_NAME_LEN]; + char prog_name[BPF_OBJ_NAME_LEN]; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -888,7 +888,7 @@ struct bpf_prog_info { __u32 created_by_uid; __u32 nr_map_ids; __aligned_u64 map_ids; - __u8 name[BPF_OBJ_NAME_LEN]; + char name[BPF_OBJ_NAME_LEN]; } __attribute__((aligned(8))); struct bpf_map_info { @@ -898,7 +898,7 @@ struct bpf_map_info { __u32 value_size; __u32 max_entries; __u32 map_flags; - __u8 name[BPF_OBJ_NAME_LEN]; + char name[BPF_OBJ_NAME_LEN]; } __attribute__((aligned(8))); /* User bpf_sock_ops struct to access socket values and specify request ops diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 0894fd20b12b..fb4fb81ce5b0 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -230,7 +230,7 @@ union bpf_attr { __u32 numa_node; /* numa node (effective only if * BPF_F_NUMA_NODE is set). */ - __u8 map_name[BPF_OBJ_NAME_LEN]; + char map_name[BPF_OBJ_NAME_LEN]; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -253,7 +253,7 @@ union bpf_attr { __aligned_u64 log_buf; /* user supplied buffer */ __u32 kern_version; /* checked when prog_type=kprobe */ __u32 prog_flags; - __u8 prog_name[BPF_OBJ_NAME_LEN]; + char prog_name[BPF_OBJ_NAME_LEN]; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -871,7 +871,7 @@ struct bpf_prog_info { __u32 created_by_uid; __u32 nr_map_ids; __aligned_u64 map_ids; - __u8 name[BPF_OBJ_NAME_LEN]; + char name[BPF_OBJ_NAME_LEN]; } __attribute__((aligned(8))); struct bpf_map_info { @@ -881,7 +881,7 @@ struct bpf_map_info { __u32 value_size; __u32 max_entries; __u32 map_flags; - __u8 name[BPF_OBJ_NAME_LEN]; + char name[BPF_OBJ_NAME_LEN]; } __attribute__((aligned(8))); /* User bpf_sock_ops struct to access socket values and specify request ops -- cgit v1.2.3-71-gd317 From 821f1b21cabb46827ce39ddf82e2789680b5042a Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Fri, 6 Oct 2017 22:12:37 -0700 Subject: bridge: add new BR_NEIGH_SUPPRESS port flag to suppress arp and nd flood This patch adds a new bridge port flag BR_NEIGH_SUPPRESS to suppress arp and nd flood on bridge ports. It implements rfc7432, section 10. https://tools.ietf.org/html/rfc7432#section-10 for ethernet VPN deployments. It is similar to the existing BR_PROXYARP* flags but has a few semantic differences to conform to EVPN standard. Unlike the existing flags, this new flag suppresses flood of all neigh discovery packets (arp and nd) to tunnel ports. Supports both vlan filtering and non-vlan filtering bridges. In case of EVPN, it is mainly used to avoid flooding of arp and nd packets to tunnel ports like vxlan. This patch adds netlink and sysfs support to set this bridge port flag. Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 1 + include/uapi/linux/if_link.h | 1 + net/bridge/Makefile | 2 +- net/bridge/br_arp_nd_proxy.c | 32 ++++++++++++++++++++++++++++++++ net/bridge/br_forward.c | 2 +- net/bridge/br_if.c | 5 +++++ net/bridge/br_netlink.c | 10 +++++++++- net/bridge/br_private.h | 2 ++ net/bridge/br_sysfs_if.c | 2 ++ 9 files changed, 54 insertions(+), 3 deletions(-) create mode 100644 net/bridge/br_arp_nd_proxy.c (limited to 'include/uapi/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 3cd18ac0697f..316ee113a220 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -49,6 +49,7 @@ struct br_ip_list { #define BR_MULTICAST_TO_UNICAST BIT(12) #define BR_VLAN_TUNNEL BIT(13) #define BR_BCAST_FLOOD BIT(14) +#define BR_NEIGH_SUPPRESS BIT(15) #define BR_DEFAULT_AGEING_TIME (300 * HZ) diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index cd580fc0e58f..b037e0ab1975 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -327,6 +327,7 @@ enum { IFLA_BRPORT_VLAN_TUNNEL, IFLA_BRPORT_BCAST_FLOOD, IFLA_BRPORT_GROUP_FWD_MASK, + IFLA_BRPORT_NEIGH_SUPPRESS, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/Makefile b/net/bridge/Makefile index 40b1ede527ca..4aee55fdcc92 100644 --- a/net/bridge/Makefile +++ b/net/bridge/Makefile @@ -7,7 +7,7 @@ obj-$(CONFIG_BRIDGE) += bridge.o bridge-y := br.o br_device.o br_fdb.o br_forward.o br_if.o br_input.o \ br_ioctl.o br_stp.o br_stp_bpdu.o \ br_stp_if.o br_stp_timer.o br_netlink.o \ - br_netlink_tunnel.o + br_netlink_tunnel.o br_arp_nd_proxy.o bridge-$(CONFIG_SYSFS) += br_sysfs_if.o br_sysfs_br.o diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c new file mode 100644 index 000000000000..f889ad5f0048 --- /dev/null +++ b/net/bridge/br_arp_nd_proxy.c @@ -0,0 +1,32 @@ +/* + * Handle bridge arp/nd proxy/suppress + * + * Copyright (C) 2017 Cumulus Networks + * Copyright (c) 2017 Roopa Prabhu + * + * Authors: + * Roopa Prabhu + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include +#include "br_private.h" + +void br_recalculate_neigh_suppress_enabled(struct net_bridge *br) +{ + struct net_bridge_port *p; + bool neigh_suppress = false; + + list_for_each_entry(p, &br->port_list, list) { + if (p->flags & BR_NEIGH_SUPPRESS) { + neigh_suppress = true; + break; + } + } + + br->neigh_suppress_enabled = neigh_suppress; +} diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 48fb17417fac..b4eed113d2ec 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -204,7 +204,7 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb, /* Do not flood to ports that enable proxy ARP */ if (p->flags & BR_PROXYARP) continue; - if ((p->flags & BR_PROXYARP_WIFI) && + if ((p->flags & (BR_PROXYARP_WIFI | BR_NEIGH_SUPPRESS)) && BR_INPUT_SKB_CB(skb)->proxyarp_replied) continue; diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 59a74a414e20..ae38547bbf91 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -310,6 +310,8 @@ void br_dev_delete(struct net_device *dev, struct list_head *head) del_nbp(p); } + br_recalculate_neigh_suppress_enabled(br); + br_fdb_delete_by_port(br, NULL, 0, 1); cancel_delayed_work_sync(&br->gc_work); @@ -660,4 +662,7 @@ void br_port_flags_change(struct net_bridge_port *p, unsigned long mask) if (mask & BR_AUTO_MASK) nbp_update_port_count(br); + + if (mask & BR_NEIGH_SUPPRESS) + br_recalculate_neigh_suppress_enabled(br); } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index dea88a255d26..f0e82682e071 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -138,6 +138,7 @@ static inline size_t br_port_info_size(void) + nla_total_size(1) /* IFLA_BRPORT_PROXYARP */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */ + nla_total_size(1) /* IFLA_BRPORT_VLAN_TUNNEL */ + + nla_total_size(1) /* IFLA_BRPORT_NEIGH_SUPPRESS */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */ @@ -210,7 +211,9 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u8(skb, IFLA_BRPORT_CONFIG_PENDING, p->config_pending) || nla_put_u8(skb, IFLA_BRPORT_VLAN_TUNNEL, !!(p->flags & BR_VLAN_TUNNEL)) || - nla_put_u16(skb, IFLA_BRPORT_GROUP_FWD_MASK, p->group_fwd_mask)) + nla_put_u16(skb, IFLA_BRPORT_GROUP_FWD_MASK, p->group_fwd_mask) || + nla_put_u8(skb, IFLA_BRPORT_NEIGH_SUPPRESS, + !!(p->flags & BR_NEIGH_SUPPRESS))) return -EMSGSIZE; timerval = br_timer_value(&p->message_age_timer); @@ -785,6 +788,11 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) p->group_fwd_mask = fwd_mask; } + err = br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_SUPPRESS, + BR_NEIGH_SUPPRESS); + if (err) + return err; + br_port_flags_change(p, old_flags ^ p->flags); return 0; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index ab4df24f7bba..00fa371b1fb2 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -404,6 +404,7 @@ struct net_bridge { #ifdef CONFIG_NET_SWITCHDEV int offload_fwd_mark; #endif + bool neigh_suppress_enabled; }; struct br_input_skb_cb { @@ -1139,4 +1140,5 @@ static inline void br_switchdev_frame_unmark(struct sk_buff *skb) } #endif /* CONFIG_NET_SWITCHDEV */ +void br_recalculate_neigh_suppress_enabled(struct net_bridge *br); #endif diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 9110d5e56085..0a1fa9ccd8b7 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -191,6 +191,7 @@ BRPORT_ATTR_FLAG(proxyarp, BR_PROXYARP); BRPORT_ATTR_FLAG(proxyarp_wifi, BR_PROXYARP_WIFI); BRPORT_ATTR_FLAG(multicast_flood, BR_MCAST_FLOOD); BRPORT_ATTR_FLAG(broadcast_flood, BR_BCAST_FLOOD); +BRPORT_ATTR_FLAG(neigh_suppress, BR_NEIGH_SUPPRESS); #ifdef CONFIG_BRIDGE_IGMP_SNOOPING static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf) @@ -241,6 +242,7 @@ static const struct brport_attribute *brport_attrs[] = { &brport_attr_multicast_flood, &brport_attr_broadcast_flood, &brport_attr_group_fwd_mask, + &brport_attr_neigh_suppress, NULL }; -- cgit v1.2.3-71-gd317 From 98589a0998b8b13c4a8fa1ccb0e62751a019faa5 Mon Sep 17 00:00:00 2001 From: Shmulik Ladkani Date: Mon, 9 Oct 2017 15:27:15 +0300 Subject: netfilter: xt_bpf: Fix XT_BPF_MODE_FD_PINNED mode of 'xt_bpf_info_v1' Commit 2c16d6033264 ("netfilter: xt_bpf: support ebpf") introduced support for attaching an eBPF object by an fd, with the 'bpf_mt_check_v1' ABI expecting the '.fd' to be specified upon each IPT_SO_SET_REPLACE call. However this breaks subsequent iptables calls: # iptables -A INPUT -m bpf --object-pinned /sys/fs/bpf/xxx -j ACCEPT # iptables -A INPUT -s 5.6.7.8 -j ACCEPT iptables: Invalid argument. Run `dmesg' for more information. That's because iptables works by loading existing rules using IPT_SO_GET_ENTRIES to userspace, then issuing IPT_SO_SET_REPLACE with the replacement set. However, the loaded 'xt_bpf_info_v1' has an arbitrary '.fd' number (from the initial "iptables -m bpf" invocation) - so when 2nd invocation occurs, userspace passes a bogus fd number, which leads to 'bpf_mt_check_v1' to fail. One suggested solution [1] was to hack iptables userspace, to perform a "entries fixup" immediatley after IPT_SO_GET_ENTRIES, by opening a new, process-local fd per every 'xt_bpf_info_v1' entry seen. However, in [2] both Pablo Neira Ayuso and Willem de Bruijn suggested to depricate the xt_bpf_info_v1 ABI dealing with pinned ebpf objects. This fix changes the XT_BPF_MODE_FD_PINNED behavior to ignore the given '.fd' and instead perform an in-kernel lookup for the bpf object given the provided '.path'. It also defines an alias for the XT_BPF_MODE_FD_PINNED mode, named XT_BPF_MODE_PATH_PINNED, to better reflect the fact that the user is expected to provide the path of the pinned object. Existing XT_BPF_MODE_FD_ELF behavior (non-pinned fd mode) is preserved. References: [1] https://marc.info/?l=netfilter-devel&m=150564724607440&w=2 [2] https://marc.info/?l=netfilter-devel&m=150575727129880&w=2 Reported-by: Rafael Buchbinder Signed-off-by: Shmulik Ladkani Acked-by: Willem de Bruijn Acked-by: Daniel Borkmann Signed-off-by: Pablo Neira Ayuso --- include/linux/bpf.h | 5 +++++ include/uapi/linux/netfilter/xt_bpf.h | 1 + kernel/bpf/inode.c | 1 + net/netfilter/xt_bpf.c | 22 ++++++++++++++++++++-- 4 files changed, 27 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8390859e79e7..f1af7d63d678 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -368,6 +368,11 @@ static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages) { } +static inline int bpf_obj_get_user(const char __user *pathname) +{ + return -EOPNOTSUPP; +} + static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key) { diff --git a/include/uapi/linux/netfilter/xt_bpf.h b/include/uapi/linux/netfilter/xt_bpf.h index b97725af2ac0..da161b56c79e 100644 --- a/include/uapi/linux/netfilter/xt_bpf.h +++ b/include/uapi/linux/netfilter/xt_bpf.h @@ -23,6 +23,7 @@ enum xt_bpf_modes { XT_BPF_MODE_FD_PINNED, XT_BPF_MODE_FD_ELF, }; +#define XT_BPF_MODE_PATH_PINNED XT_BPF_MODE_FD_PINNED struct xt_bpf_info_v1 { __u16 mode; diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index e833ed914358..be1dde967208 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -363,6 +363,7 @@ out: putname(pname); return ret; } +EXPORT_SYMBOL_GPL(bpf_obj_get_user); static void bpf_evict_inode(struct inode *inode) { diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c index 38986a95216c..29123934887b 100644 --- a/net/netfilter/xt_bpf.c +++ b/net/netfilter/xt_bpf.c @@ -8,6 +8,7 @@ */ #include +#include #include #include #include @@ -49,6 +50,22 @@ static int __bpf_mt_check_fd(int fd, struct bpf_prog **ret) return 0; } +static int __bpf_mt_check_path(const char *path, struct bpf_prog **ret) +{ + mm_segment_t oldfs = get_fs(); + int retval, fd; + + set_fs(KERNEL_DS); + fd = bpf_obj_get_user(path); + set_fs(oldfs); + if (fd < 0) + return fd; + + retval = __bpf_mt_check_fd(fd, ret); + sys_close(fd); + return retval; +} + static int bpf_mt_check(const struct xt_mtchk_param *par) { struct xt_bpf_info *info = par->matchinfo; @@ -66,9 +83,10 @@ static int bpf_mt_check_v1(const struct xt_mtchk_param *par) return __bpf_mt_check_bytecode(info->bpf_program, info->bpf_program_num_elem, &info->filter); - else if (info->mode == XT_BPF_MODE_FD_PINNED || - info->mode == XT_BPF_MODE_FD_ELF) + else if (info->mode == XT_BPF_MODE_FD_ELF) return __bpf_mt_check_fd(info->fd, &info->filter); + else if (info->mode == XT_BPF_MODE_PATH_PINNED) + return __bpf_mt_check_path(info->path, &info->filter); else return -EINVAL; } -- cgit v1.2.3-71-gd317 From ceaa001a170e43608854d5290a48064f57b565ed Mon Sep 17 00:00:00 2001 From: William Tu Date: Wed, 4 Oct 2017 17:03:12 -0700 Subject: openvswitch: Add erspan tunnel support. Add erspan netlink interface for OVS. Signed-off-by: William Tu Cc: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 1 + net/openvswitch/flow_netlink.c | 51 +++++++++++++++++++++++++++++++++++++++- 2 files changed, 51 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 156ee4cab82e..efdbfbfd3ee2 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -359,6 +359,7 @@ enum ovs_tunnel_key_attr { OVS_TUNNEL_KEY_ATTR_IPV6_SRC, /* struct in6_addr src IPv6 address. */ OVS_TUNNEL_KEY_ATTR_IPV6_DST, /* struct in6_addr dst IPv6 address. */ OVS_TUNNEL_KEY_ATTR_PAD, + OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS, /* be32 ERSPAN index. */ __OVS_TUNNEL_KEY_ATTR_MAX }; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index e8eb427ce6d1..fc0ca9a89b8e 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -48,6 +48,7 @@ #include #include #include +#include #include "flow_netlink.h" @@ -319,7 +320,8 @@ size_t ovs_tun_key_attr_size(void) * OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS and covered by it. */ + nla_total_size(2) /* OVS_TUNNEL_KEY_ATTR_TP_SRC */ - + nla_total_size(2); /* OVS_TUNNEL_KEY_ATTR_TP_DST */ + + nla_total_size(2) /* OVS_TUNNEL_KEY_ATTR_TP_DST */ + + nla_total_size(4); /* OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS */ } size_t ovs_key_attr_size(void) @@ -371,6 +373,7 @@ static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] .next = ovs_vxlan_ext_key_lens }, [OVS_TUNNEL_KEY_ATTR_IPV6_SRC] = { .len = sizeof(struct in6_addr) }, [OVS_TUNNEL_KEY_ATTR_IPV6_DST] = { .len = sizeof(struct in6_addr) }, + [OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS] = { .len = sizeof(u32) }, }; /* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute. */ @@ -593,6 +596,33 @@ static int vxlan_tun_opt_from_nlattr(const struct nlattr *attr, return 0; } +static int erspan_tun_opt_from_nlattr(const struct nlattr *attr, + struct sw_flow_match *match, bool is_mask, + bool log) +{ + unsigned long opt_key_offset; + struct erspan_metadata opts; + + BUILD_BUG_ON(sizeof(opts) > sizeof(match->key->tun_opts)); + + memset(&opts, 0, sizeof(opts)); + opts.index = nla_get_be32(attr); + + /* Index has only 20-bit */ + if (ntohl(opts.index) & ~INDEX_MASK) { + OVS_NLERR(log, "ERSPAN index number %x too large.", + ntohl(opts.index)); + return -EINVAL; + } + + SW_FLOW_KEY_PUT(match, tun_opts_len, sizeof(opts), is_mask); + opt_key_offset = TUN_METADATA_OFFSET(sizeof(opts)); + SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, &opts, sizeof(opts), + is_mask); + + return 0; +} + static int ip_tun_from_nlattr(const struct nlattr *attr, struct sw_flow_match *match, bool is_mask, bool log) @@ -700,6 +730,19 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, break; case OVS_TUNNEL_KEY_ATTR_PAD: break; + case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS: + if (opts_type) { + OVS_NLERR(log, "Multiple metadata blocks provided"); + return -EINVAL; + } + + err = erspan_tun_opt_from_nlattr(a, match, is_mask, log); + if (err) + return err; + + tun_flags |= TUNNEL_ERSPAN_OPT; + opts_type = type; + break; default: OVS_NLERR(log, "Unknown IP tunnel attribute %d", type); @@ -824,6 +867,10 @@ static int __ip_tun_to_nlattr(struct sk_buff *skb, else if (output->tun_flags & TUNNEL_VXLAN_OPT && vxlan_opt_to_nlattr(skb, tun_opts, swkey_tun_opts_len)) return -EMSGSIZE; + else if (output->tun_flags & TUNNEL_ERSPAN_OPT && + nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS, + ((struct erspan_metadata *)tun_opts)->index)) + return -EMSGSIZE; } return 0; @@ -2195,6 +2242,8 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, break; case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS: break; + case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS: + break; } }; -- cgit v1.2.3-71-gd317 From de8cd83e91bc3ee212b3e6ec6e4283af9e4ab269 Mon Sep 17 00:00:00 2001 From: Steve Grubb Date: Mon, 2 Oct 2017 20:21:39 -0400 Subject: audit: Record fanotify access control decisions The fanotify interface allows user space daemons to make access control decisions. Under common criteria requirements, we need to optionally record decisions based on policy. This patch adds a bit mask, FAN_AUDIT, that a user space daemon can 'or' into the response decision which will tell the kernel that it made a decision and record it. It would be used something like this in user space code: response.response = FAN_DENY | FAN_AUDIT; write(fd, &response, sizeof(struct fanotify_response)); When the syscall ends, the audit system will record the decision as a AUDIT_FANOTIFY auxiliary record to denote that the reason this event occurred is the result of an access control decision from fanotify rather than DAC or MAC policy. A sample event looks like this: type=PATH msg=audit(1504310584.332:290): item=0 name="./evil-ls" inode=1319561 dev=fc:03 mode=0100755 ouid=1000 ogid=1000 rdev=00:00 obj=unconfined_u:object_r:user_home_t:s0 nametype=NORMAL type=CWD msg=audit(1504310584.332:290): cwd="/home/sgrubb" type=SYSCALL msg=audit(1504310584.332:290): arch=c000003e syscall=2 success=no exit=-1 a0=32cb3fca90 a1=0 a2=43 a3=8 items=1 ppid=901 pid=959 auid=1000 uid=1000 gid=1000 euid=1000 suid=1000 fsuid=1000 egid=1000 sgid=1000 fsgid=1000 tty=pts1 ses=3 comm="bash" exe="/usr/bin/bash" subj=unconfined_u:unconfined_r:unconfined_t: s0-s0:c0.c1023 key=(null) type=FANOTIFY msg=audit(1504310584.332:290): resp=2 Prior to using the audit flag, the developer needs to call fanotify_init or'ing in FAN_ENABLE_AUDIT to ensure that the kernel supports auditing. The calling process must also have the CAP_AUDIT_WRITE capability. Signed-off-by: sgrubb Reviewed-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 8 +++++++- fs/notify/fanotify/fanotify_user.c | 16 +++++++++++++++- fs/notify/fdinfo.c | 3 +++ include/linux/audit.h | 10 ++++++++++ include/linux/fsnotify_backend.h | 1 + include/uapi/linux/audit.h | 1 + include/uapi/linux/fanotify.h | 3 +++ kernel/auditsc.c | 6 ++++++ 8 files changed, 46 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 2fa99aeaa095..1968d21a3f37 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -9,6 +9,7 @@ #include #include #include +#include #include "fanotify.h" @@ -78,7 +79,7 @@ static int fanotify_get_response(struct fsnotify_group *group, fsnotify_finish_user_wait(iter_info); out: /* userspace responded, convert to something usable */ - switch (event->response) { + switch (event->response & ~FAN_AUDIT) { case FAN_ALLOW: ret = 0; break; @@ -86,6 +87,11 @@ out: default: ret = -EPERM; } + + /* Check if the response should be audited */ + if (event->response & FAN_AUDIT) + audit_fanotify(event->response & ~FAN_AUDIT); + event->response = 0; pr_debug("%s: group=%p event=%p about to return ret=%d\n", __func__, diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 907a481ac781..0455ea729384 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -179,7 +179,7 @@ static int process_access_response(struct fsnotify_group *group, * userspace can send a valid response or we will clean it up after the * timeout */ - switch (response) { + switch (response & ~FAN_AUDIT) { case FAN_ALLOW: case FAN_DENY: break; @@ -190,6 +190,9 @@ static int process_access_response(struct fsnotify_group *group, if (fd < 0) return -EINVAL; + if ((response & FAN_AUDIT) && !group->fanotify_data.audit) + return -EINVAL; + event = dequeue_event(group, fd); if (!event) return -ENOENT; @@ -721,7 +724,11 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) if (!capable(CAP_SYS_ADMIN)) return -EPERM; +#ifdef CONFIG_AUDITSYSCALL + if (flags & ~(FAN_ALL_INIT_FLAGS | FAN_ENABLE_AUDIT)) +#else if (flags & ~FAN_ALL_INIT_FLAGS) +#endif return -EINVAL; if (event_f_flags & ~FANOTIFY_INIT_ALL_EVENT_F_BITS) @@ -805,6 +812,13 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) group->fanotify_data.max_marks = FANOTIFY_DEFAULT_MAX_MARKS; } + if (flags & FAN_ENABLE_AUDIT) { + fd = -EPERM; + if (!capable(CAP_AUDIT_WRITE)) + goto out_destroy_group; + group->fanotify_data.audit = true; + } + fd = anon_inode_getfd("[fanotify]", &fanotify_fops, group, f_flags); if (fd < 0) goto out_destroy_group; diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c index dd63aa9a6f9a..645ab561e790 100644 --- a/fs/notify/fdinfo.c +++ b/fs/notify/fdinfo.c @@ -156,6 +156,9 @@ void fanotify_show_fdinfo(struct seq_file *m, struct file *f) if (group->fanotify_data.max_marks == UINT_MAX) flags |= FAN_UNLIMITED_MARKS; + if (group->fanotify_data.audit) + flags |= FAN_ENABLE_AUDIT; + seq_printf(m, "fanotify flags:%x event-flags:%x\n", flags, group->fanotify_data.f_flags); diff --git a/include/linux/audit.h b/include/linux/audit.h index cb708eb8accc..d66220dac364 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -356,6 +356,7 @@ extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm, extern void __audit_log_capset(const struct cred *new, const struct cred *old); extern void __audit_mmap_fd(int fd, int flags); extern void __audit_log_kern_module(char *name); +extern void __audit_fanotify(unsigned int response); static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { @@ -452,6 +453,12 @@ static inline void audit_log_kern_module(char *name) __audit_log_kern_module(name); } +static inline void audit_fanotify(unsigned int response) +{ + if (!audit_dummy_context()) + __audit_fanotify(response); +} + extern int audit_n_rules; extern int audit_signals; #else /* CONFIG_AUDITSYSCALL */ @@ -568,6 +575,9 @@ static inline void audit_log_kern_module(char *name) { } +static inline void audit_fanotify(unsigned int response) +{ } + static inline void audit_ptrace(struct task_struct *t) { } #define audit_n_rules 0 diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index c6c69318752b..4a474f972910 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -190,6 +190,7 @@ struct fsnotify_group { int f_flags; unsigned int max_marks; struct user_struct *user; + bool audit; } fanotify_data; #endif /* CONFIG_FANOTIFY */ }; diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index 0714a66f0e0c..221f8b7f01b2 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -112,6 +112,7 @@ #define AUDIT_FEATURE_CHANGE 1328 /* audit log listing feature changes */ #define AUDIT_REPLACE 1329 /* Replace auditd if this packet unanswerd */ #define AUDIT_KERN_MODULE 1330 /* Kernel Module events */ +#define AUDIT_FANOTIFY 1331 /* Fanotify access decision */ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index 030508d195d3..5dda19a9a947 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -35,6 +35,7 @@ #define FAN_UNLIMITED_QUEUE 0x00000010 #define FAN_UNLIMITED_MARKS 0x00000020 +#define FAN_ENABLE_AUDIT 0x00000040 #define FAN_ALL_INIT_FLAGS (FAN_CLOEXEC | FAN_NONBLOCK | \ FAN_ALL_CLASS_BITS | FAN_UNLIMITED_QUEUE |\ @@ -99,6 +100,8 @@ struct fanotify_response { /* Legit userspace responses to a _PERM event */ #define FAN_ALLOW 0x01 #define FAN_DENY 0x02 +#define FAN_AUDIT 0x10 /* Bit mask to create audit record for result */ + /* No fd set in event */ #define FAN_NOFD -1 diff --git a/kernel/auditsc.c b/kernel/auditsc.c index ecc23e25c9eb..9c723e978245 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -2390,6 +2390,12 @@ void __audit_log_kern_module(char *name) context->type = AUDIT_KERN_MODULE; } +void __audit_fanotify(unsigned int response) +{ + audit_log(current->audit_context, GFP_KERNEL, + AUDIT_FANOTIFY, "resp=%u", response); +} + static void audit_log_task(struct audit_buffer *ab) { kuid_t auid, uid; -- cgit v1.2.3-71-gd317 From b8226962b1c49c784aeddb9d2fafbf53dfdc2190 Mon Sep 17 00:00:00 2001 From: Eric Garver Date: Tue, 10 Oct 2017 16:54:44 -0400 Subject: openvswitch: add ct_clear action This adds a ct_clear action for clearing conntrack state. ct_clear is currently implemented in OVS userspace, but is not backed by an action in the kernel datapath. This is useful for flows that may modify a packet tuple after a ct lookup has already occurred. Signed-off-by: Eric Garver Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 2 ++ net/openvswitch/actions.c | 4 ++++ net/openvswitch/conntrack.c | 11 +++++++++++ net/openvswitch/conntrack.h | 7 +++++++ net/openvswitch/flow_netlink.c | 5 +++++ 5 files changed, 29 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index efdbfbfd3ee2..0cd6f8833147 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -807,6 +807,7 @@ struct ovs_action_push_eth { * packet. * @OVS_ACTION_ATTR_POP_ETH: Pop the outermost Ethernet header off the * packet. + * @OVS_ACTION_ATTR_CT_CLEAR: Clear conntrack state from the packet. * * Only a single header can be set with a single %OVS_ACTION_ATTR_SET. Not all * fields within a header are modifiable, e.g. the IPv4 protocol and fragment @@ -836,6 +837,7 @@ enum ovs_action_attr { OVS_ACTION_ATTR_TRUNC, /* u32 struct ovs_action_trunc. */ OVS_ACTION_ATTR_PUSH_ETH, /* struct ovs_action_push_eth. */ OVS_ACTION_ATTR_POP_ETH, /* No argument. */ + OVS_ACTION_ATTR_CT_CLEAR, /* No argument. */ __OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted * from userspace. */ diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index a54a556fcdb5..a551232daf61 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1203,6 +1203,10 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, return err == -EINPROGRESS ? 0 : err; break; + case OVS_ACTION_ATTR_CT_CLEAR: + err = ovs_ct_clear(skb, key); + break; + case OVS_ACTION_ATTR_PUSH_ETH: err = push_eth(skb, key, nla_data(a)); break; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index d558e882ca0c..fe861e2f0deb 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1129,6 +1129,17 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, return err; } +int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key) +{ + if (skb_nfct(skb)) { + nf_conntrack_put(skb_nfct(skb)); + nf_ct_set(skb, NULL, IP_CT_UNTRACKED); + ovs_ct_fill_key(skb, key); + } + + return 0; +} + static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name, const struct sw_flow_key *key, bool log) { diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h index bc7efd1867ab..399dfdd2c4f9 100644 --- a/net/openvswitch/conntrack.h +++ b/net/openvswitch/conntrack.h @@ -30,6 +30,7 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *, struct sk_buff *); int ovs_ct_execute(struct net *, struct sk_buff *, struct sw_flow_key *, const struct ovs_conntrack_info *); +int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key); void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key); int ovs_ct_put_key(const struct sw_flow_key *swkey, @@ -73,6 +74,12 @@ static inline int ovs_ct_execute(struct net *net, struct sk_buff *skb, return -ENOTSUPP; } +static inline int ovs_ct_clear(struct sk_buff *skb, + struct sw_flow_key *key) +{ + return -ENOTSUPP; +} + static inline void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key) { diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index fc0ca9a89b8e..dc0d79092e74 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -76,6 +76,7 @@ static bool actions_may_change_flow(const struct nlattr *actions) break; case OVS_ACTION_ATTR_CT: + case OVS_ACTION_ATTR_CT_CLEAR: case OVS_ACTION_ATTR_HASH: case OVS_ACTION_ATTR_POP_ETH: case OVS_ACTION_ATTR_POP_MPLS: @@ -2528,6 +2529,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, [OVS_ACTION_ATTR_SAMPLE] = (u32)-1, [OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash), [OVS_ACTION_ATTR_CT] = (u32)-1, + [OVS_ACTION_ATTR_CT_CLEAR] = 0, [OVS_ACTION_ATTR_TRUNC] = sizeof(struct ovs_action_trunc), [OVS_ACTION_ATTR_PUSH_ETH] = sizeof(struct ovs_action_push_eth), [OVS_ACTION_ATTR_POP_ETH] = 0, @@ -2669,6 +2671,9 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, skip_copy = true; break; + case OVS_ACTION_ATTR_CT_CLEAR: + break; + case OVS_ACTION_ATTR_PUSH_ETH: /* Disallow pushing an Ethernet header if one * is already present */ -- cgit v1.2.3-71-gd317 From 1ea4ff3e9f0b8d53e680a2bb9e8e644bf03aeb4d Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 13 Sep 2017 16:07:22 +0200 Subject: cfg80211: support reloading regulatory database If the regulatory database is loaded, and then updated, it may be necessary to reload it. Add an nl80211 command to do this. Note that this just reloads the database, it doesn't re-apply the rules from it immediately. Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 4 +++ net/wireless/nl80211.c | 11 ++++++ net/wireless/reg.c | 80 +++++++++++++++++++++++++++++++++----------- net/wireless/reg.h | 6 ++++ 4 files changed, 81 insertions(+), 20 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 95832ce03a44..f882fe1f9709 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -990,6 +990,8 @@ * &NL80211_CMD_CONNECT or &NL80211_CMD_ROAM. If the 4 way handshake failed * &NL80211_CMD_DISCONNECT should be indicated instead. * + * @NL80211_CMD_RELOAD_REGDB: Request that the regdb firmware file is reloaded. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -1194,6 +1196,8 @@ enum nl80211_commands { NL80211_CMD_PORT_AUTHORIZED, + NL80211_CMD_RELOAD_REGDB, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5129342151e6..67a03f2885a4 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5678,6 +5678,11 @@ static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info) } } +static int nl80211_reload_regdb(struct sk_buff *skb, struct genl_info *info) +{ + return reg_reload_regdb(); +} + static int nl80211_get_mesh_config(struct sk_buff *skb, struct genl_info *info) { @@ -12708,6 +12713,12 @@ static const struct genl_ops nl80211_ops[] = { .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, }, + { + .cmd = NL80211_CMD_RELOAD_REGDB, + .doit = nl80211_reload_regdb, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + }, { .cmd = NL80211_CMD_GET_MESH_CONFIG, .doit = nl80211_get_mesh_config, diff --git a/net/wireless/reg.c b/net/wireless/reg.c index e9aeb05aaf3e..180addda52af 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -781,6 +781,8 @@ static int query_regdb(const char *alpha2) const struct fwdb_header *hdr = regdb; const struct fwdb_country *country; + ASSERT_RTNL(); + if (IS_ERR(regdb)) return PTR_ERR(regdb); @@ -796,41 +798,47 @@ static int query_regdb(const char *alpha2) static void regdb_fw_cb(const struct firmware *fw, void *context) { + int set_error = 0; + bool restore = true; void *db; if (!fw) { pr_info("failed to load regulatory.db\n"); - regdb = ERR_PTR(-ENODATA); - goto restore; - } - - if (!valid_regdb(fw->data, fw->size)) { + set_error = -ENODATA; + } else if (!valid_regdb(fw->data, fw->size)) { pr_info("loaded regulatory.db is malformed\n"); - release_firmware(fw); - regdb = ERR_PTR(-EINVAL); - goto restore; + set_error = -EINVAL; } - db = kmemdup(fw->data, fw->size, GFP_KERNEL); - release_firmware(fw); + rtnl_lock(); + if (WARN_ON(regdb && !IS_ERR(regdb))) { + /* just restore and free new db */ + } else if (set_error) { + regdb = ERR_PTR(set_error); + } else if (fw) { + db = kmemdup(fw->data, fw->size, GFP_KERNEL); + if (db) { + regdb = db; + restore = context && query_regdb(context); + } else { + restore = true; + } + } - if (!db) - goto restore; - regdb = db; + if (restore) + restore_regulatory_settings(true); - if (query_regdb(context)) - goto restore; - goto free; - restore: - rtnl_lock(); - restore_regulatory_settings(true); rtnl_unlock(); - free: + kfree(context); + + release_firmware(fw); } static int query_regdb_file(const char *alpha2) { + ASSERT_RTNL(); + if (regdb) return query_regdb(alpha2); @@ -843,6 +851,38 @@ static int query_regdb_file(const char *alpha2) (void *)alpha2, regdb_fw_cb); } +int reg_reload_regdb(void) +{ + const struct firmware *fw; + void *db; + int err; + + err = request_firmware(&fw, "regulatory.db", ®_pdev->dev); + if (err) + return err; + + if (!valid_regdb(fw->data, fw->size)) { + err = -ENODATA; + goto out; + } + + db = kmemdup(fw->data, fw->size, GFP_KERNEL); + if (!db) { + err = -ENOMEM; + goto out; + } + + rtnl_lock(); + if (!IS_ERR_OR_NULL(regdb)) + kfree(regdb); + regdb = db; + rtnl_unlock(); + + out: + release_firmware(fw); + return err; +} + static bool reg_query_database(struct regulatory_request *request) { /* query internal regulatory database (if it exists) */ diff --git a/net/wireless/reg.h b/net/wireless/reg.h index ca7fedf2e7a1..9529c522611a 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -179,4 +179,10 @@ void regulatory_propagate_dfs_state(struct wiphy *wiphy, * @wiphy2 - wiphy it's dfs_region to be checked against that of wiphy1 */ bool reg_dfs_domain_same(struct wiphy *wiphy1, struct wiphy *wiphy2); + +/** + * reg_reload_regdb - reload the regulatory.db firmware file + */ +int reg_reload_regdb(void); + #endif /* __NET_WIRELESS_REG_H */ -- cgit v1.2.3-71-gd317 From 259a41d9ae8f3689742267f340ad2b159d00b302 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 18 Sep 2017 08:21:37 -0400 Subject: media: dvb_frontend: fix return values for FE_SET_PROPERTY There are several problems with regards to the return of FE_SET_PROPERTY. The original idea were to return per-property return codes via tvp->result field, and to return an updated set of values. However, that never worked. What's actually implemented is: - the FE_SET_PROPERTY implementation doesn't call .get_frontend callback in order to get the actual parameters after return; - the tvp->result field is only filled if there's no error. So, it is always filled with zero; - FE_SET_PROPERTY doesn't call memdup_user() nor any other copy_to_user() function. So, any changes to the properties will be lost; - FE_SET_PROPERTY is declared as a write-only ioctl (IOW). While we could fix the above, it could cause regressions. So, let's just assume what the code really does, updating the documentation accordingly and removing the logic that would update the discarded tvp->result. Reviewed-by: Shuah Khan Signed-off-by: Mauro Carvalho Chehab --- Documentation/media/uapi/dvb/fe-get-property.rst | 7 +++++-- drivers/media/dvb-core/dvb_frontend.c | 2 -- include/uapi/linux/dvb/frontend.h | 2 +- 3 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/media/uapi/dvb/fe-get-property.rst b/Documentation/media/uapi/dvb/fe-get-property.rst index 948d2ba84f2c..b69741d9cedf 100644 --- a/Documentation/media/uapi/dvb/fe-get-property.rst +++ b/Documentation/media/uapi/dvb/fe-get-property.rst @@ -48,8 +48,11 @@ depends on the delivery system and on the device: - This call requires read/write access to the device. - - At return, the values are updated to reflect the actual parameters - used. +.. note:: + + At return, the values aren't updated to reflect the actual + parameters used. If the actual parameters are needed, an explicit + call to ``FE_GET_PROPERTY`` is needed. - ``FE_GET_PROPERTY:`` diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c index b19f40be0ab2..5e3bcae477d2 100644 --- a/drivers/media/dvb-core/dvb_frontend.c +++ b/drivers/media/dvb-core/dvb_frontend.c @@ -2125,7 +2125,6 @@ static int dvb_frontend_handle_ioctl(struct file *file, kfree(tvp); return err; } - (tvp + i)->result = err; } kfree(tvp); break; @@ -2170,7 +2169,6 @@ static int dvb_frontend_handle_ioctl(struct file *file, kfree(tvp); return err; } - (tvp + i)->result = err; } if (copy_to_user((void __user *)tvps->props, tvp, diff --git a/include/uapi/linux/dvb/frontend.h b/include/uapi/linux/dvb/frontend.h index 861cacd5711f..6bc26f35217b 100644 --- a/include/uapi/linux/dvb/frontend.h +++ b/include/uapi/linux/dvb/frontend.h @@ -830,7 +830,7 @@ struct dtv_fe_stats { * @cmd: Digital TV command. * @reserved: Not used. * @u: Union with the values for the command. - * @result: Result of the command set (currently unused). + * @result: Unused * * The @u union may have either one of the values below: * -- cgit v1.2.3-71-gd317 From 28978713c51b0a70acf748f76f9d6d2d20dcf980 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 10 Oct 2017 23:45:18 -0700 Subject: net: qrtr: Move constants to header file The constants are used by both the name server and clients, so clarify their value and move them to the uapi header. Signed-off-by: Bjorn Andersson Signed-off-by: David S. Miller --- include/uapi/linux/qrtr.h | 3 +++ net/qrtr/qrtr.c | 2 -- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/qrtr.h b/include/uapi/linux/qrtr.h index 9d76c566f66e..63e8803e4d90 100644 --- a/include/uapi/linux/qrtr.h +++ b/include/uapi/linux/qrtr.h @@ -4,6 +4,9 @@ #include #include +#define QRTR_NODE_BCAST 0xffffffffu +#define QRTR_PORT_CTRL 0xfffffffeu + struct sockaddr_qrtr { __kernel_sa_family_t sq_family; __u32 sq_node; diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 7e4b49a8349e..15981abc042c 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -61,8 +61,6 @@ struct qrtr_hdr { } __packed; #define QRTR_HDR_SIZE sizeof(struct qrtr_hdr) -#define QRTR_NODE_BCAST ((unsigned int)-1) -#define QRTR_PORT_CTRL ((unsigned int)-2) struct qrtr_sock { /* WARNING: sk must be the first member */ -- cgit v1.2.3-71-gd317 From da7653f0faabbe45eb2d3fd6e4b400fe003e81ae Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 10 Oct 2017 23:45:19 -0700 Subject: net: qrtr: Add control packet definition to uapi The QMUX protocol specification defines structure of the special control packet messages being sent between handlers of the control port. Add these to the uapi header, as this structure and the associated types are shared between the kernel and all userspace handlers of control messages. Signed-off-by: Bjorn Andersson Signed-off-by: David S. Miller --- include/uapi/linux/qrtr.h | 32 ++++++++++++++++++++++++++++++++ net/qrtr/qrtr.c | 12 ------------ 2 files changed, 32 insertions(+), 12 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/qrtr.h b/include/uapi/linux/qrtr.h index 63e8803e4d90..179af64846e0 100644 --- a/include/uapi/linux/qrtr.h +++ b/include/uapi/linux/qrtr.h @@ -13,4 +13,36 @@ struct sockaddr_qrtr { __u32 sq_port; }; +enum qrtr_pkt_type { + QRTR_TYPE_DATA = 1, + QRTR_TYPE_HELLO = 2, + QRTR_TYPE_BYE = 3, + QRTR_TYPE_NEW_SERVER = 4, + QRTR_TYPE_DEL_SERVER = 5, + QRTR_TYPE_DEL_CLIENT = 6, + QRTR_TYPE_RESUME_TX = 7, + QRTR_TYPE_EXIT = 8, + QRTR_TYPE_PING = 9, + QRTR_TYPE_NEW_LOOKUP = 10, + QRTR_TYPE_DEL_LOOKUP = 11, +}; + +struct qrtr_ctrl_pkt { + __le32 cmd; + + union { + struct { + __le32 service; + __le32 instance; + __le32 node; + __le32 port; + } server; + + struct { + __le32 node; + __le32 port; + } client; + }; +} __packed; + #endif /* _LINUX_QRTR_H */ diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 15981abc042c..d85ca7170b8f 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -26,18 +26,6 @@ #define QRTR_MIN_EPH_SOCKET 0x4000 #define QRTR_MAX_EPH_SOCKET 0x7fff -enum qrtr_pkt_type { - QRTR_TYPE_DATA = 1, - QRTR_TYPE_HELLO = 2, - QRTR_TYPE_BYE = 3, - QRTR_TYPE_NEW_SERVER = 4, - QRTR_TYPE_DEL_SERVER = 5, - QRTR_TYPE_DEL_CLIENT = 6, - QRTR_TYPE_RESUME_TX = 7, - QRTR_TYPE_EXIT = 8, - QRTR_TYPE_PING = 9, -}; - /** * struct qrtr_hdr - (I|R)PCrouter packet header * @version: protocol version -- cgit v1.2.3-71-gd317 From ad2d116c5242875bba27522682ec5ba7f0df75f0 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 11 Oct 2017 11:14:49 -0700 Subject: sched: tc_mirred: Remove whitespaces This file contains unnecessary whitespaces as newlines, remove them, found by looking at what struct tc_mirred looks like. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/uapi/linux/tc_act/tc_mirred.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tc_act/tc_mirred.h b/include/uapi/linux/tc_act/tc_mirred.h index 3d7a2b352a62..69038c29e8a9 100644 --- a/include/uapi/linux/tc_act/tc_mirred.h +++ b/include/uapi/linux/tc_act/tc_mirred.h @@ -9,13 +9,13 @@ #define TCA_EGRESS_MIRROR 2 /* mirror packet to EGRESS */ #define TCA_INGRESS_REDIR 3 /* packet redirect to INGRESS*/ #define TCA_INGRESS_MIRROR 4 /* mirror packet to INGRESS */ - + struct tc_mirred { tc_gen; int eaction; /* one of IN/EGRESS_MIRROR/REDIR */ __u32 ifindex; /* ifindex of egress port */ }; - + enum { TCA_MIRRED_UNSPEC, TCA_MIRRED_TM, @@ -24,5 +24,5 @@ enum { __TCA_MIRRED_MAX }; #define TCA_MIRRED_MAX (__TCA_MIRRED_MAX - 1) - + #endif -- cgit v1.2.3-71-gd317 From 75da2163dbb6af9f2dce1d80056d11d290dd19a5 Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Fri, 13 Oct 2017 11:04:23 +0200 Subject: tipc: introduce communication groups As a preparation for introducing flow control for multicast and datagram messaging we need a more strictly defined framework than we have now. A socket must be able keep track of exactly how many and which other sockets it is allowed to communicate with at any moment, and keep the necessary state for those. We therefore introduce a new concept we have named Communication Group. Sockets can join a group via a new setsockopt() call TIPC_GROUP_JOIN. The call takes four parameters: 'type' serves as group identifier, 'instance' serves as an logical member identifier, and 'scope' indicates the visibility of the group (node/cluster/zone). Finally, 'flags' makes it possible to set certain properties for the member. For now, there is only one flag, indicating if the creator of the socket wants to receive a copy of broadcast or multicast messages it is sending via the socket, and if wants to be eligible as destination for its own anycasts. A group is closed, i.e., sockets which have not joined a group will not be able to send messages to or receive messages from members of the group, and vice versa. Any member of a group can send multicast ('group broadcast') messages to all group members, optionally including itself, using the primitive send(). The messages are received via the recvmsg() primitive. A socket can only be member of one group at a time. Signed-off-by: Jon Maloy Acked-by: Ying Xue Signed-off-by: David S. Miller --- include/uapi/linux/tipc.h | 14 ++ net/tipc/Makefile | 2 +- net/tipc/group.c | 404 ++++++++++++++++++++++++++++++++++++++++++++++ net/tipc/group.h | 64 ++++++++ net/tipc/link.c | 3 +- net/tipc/msg.h | 50 +++++- net/tipc/name_table.c | 44 +++-- net/tipc/name_table.h | 3 + net/tipc/node.h | 3 +- net/tipc/socket.c | 209 ++++++++++++++++++++---- 10 files changed, 748 insertions(+), 48 deletions(-) create mode 100644 net/tipc/group.c create mode 100644 net/tipc/group.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tipc.h b/include/uapi/linux/tipc.h index 5351b08c897a..5f7b2c4a09ab 100644 --- a/include/uapi/linux/tipc.h +++ b/include/uapi/linux/tipc.h @@ -231,6 +231,20 @@ struct sockaddr_tipc { #define TIPC_SOCK_RECVQ_DEPTH 132 /* Default: none (read only) */ #define TIPC_MCAST_BROADCAST 133 /* Default: TIPC selects. No arg */ #define TIPC_MCAST_REPLICAST 134 /* Default: TIPC selects. No arg */ +#define TIPC_GROUP_JOIN 135 /* Takes struct tipc_group_req* */ +#define TIPC_GROUP_LEAVE 136 /* No argument */ + +/* + * Flag values + */ +#define TIPC_GROUP_LOOPBACK 0x1 /* Receive copy of sent msg when match */ + +struct tipc_group_req { + __u32 type; /* group id */ + __u32 instance; /* member id */ + __u32 scope; /* zone/cluster/node */ + __u32 flags; +}; /* * Maximum sizes of TIPC bearer-related names (including terminating NULL) diff --git a/net/tipc/Makefile b/net/tipc/Makefile index 31b9f9c52974..a3af73ec0b78 100644 --- a/net/tipc/Makefile +++ b/net/tipc/Makefile @@ -8,7 +8,7 @@ tipc-y += addr.o bcast.o bearer.o \ core.o link.o discover.o msg.o \ name_distr.o subscr.o monitor.o name_table.o net.o \ netlink.o netlink_compat.o node.o socket.o eth_media.o \ - server.o socket.o + server.o socket.o group.o tipc-$(CONFIG_TIPC_MEDIA_UDP) += udp_media.o tipc-$(CONFIG_TIPC_MEDIA_IB) += ib_media.o diff --git a/net/tipc/group.c b/net/tipc/group.c new file mode 100644 index 000000000000..3f0e1ce1e3b9 --- /dev/null +++ b/net/tipc/group.c @@ -0,0 +1,404 @@ +/* + * net/tipc/group.c: TIPC group messaging code + * + * Copyright (c) 2017, Ericsson AB + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "addr.h" +#include "group.h" +#include "bcast.h" +#include "server.h" +#include "msg.h" +#include "socket.h" +#include "node.h" +#include "name_table.h" +#include "subscr.h" + +#define ADV_UNIT (((MAX_MSG_SIZE + MAX_H_SIZE) / FLOWCTL_BLK_SZ) + 1) +#define ADV_IDLE ADV_UNIT + +enum mbr_state { + MBR_QUARANTINED, + MBR_DISCOVERED, + MBR_JOINING, + MBR_PUBLISHED, + MBR_JOINED, + MBR_LEAVING +}; + +struct tipc_member { + struct rb_node tree_node; + struct list_head list; + u32 node; + u32 port; + enum mbr_state state; + u16 bc_rcv_nxt; +}; + +struct tipc_group { + struct rb_root members; + struct tipc_nlist dests; + struct net *net; + int subid; + u32 type; + u32 instance; + u32 domain; + u32 scope; + u32 portid; + u16 member_cnt; + u16 bc_snd_nxt; + bool loopback; +}; + +static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, + int mtyp, struct sk_buff_head *xmitq); + +u16 tipc_group_bc_snd_nxt(struct tipc_group *grp) +{ + return grp->bc_snd_nxt; +} + +static bool tipc_group_is_receiver(struct tipc_member *m) +{ + return m && m->state >= MBR_JOINED; +} + +int tipc_group_size(struct tipc_group *grp) +{ + return grp->member_cnt; +} + +struct tipc_group *tipc_group_create(struct net *net, u32 portid, + struct tipc_group_req *mreq) +{ + struct tipc_group *grp; + u32 type = mreq->type; + + grp = kzalloc(sizeof(*grp), GFP_ATOMIC); + if (!grp) + return NULL; + tipc_nlist_init(&grp->dests, tipc_own_addr(net)); + grp->members = RB_ROOT; + grp->net = net; + grp->portid = portid; + grp->domain = addr_domain(net, mreq->scope); + grp->type = type; + grp->instance = mreq->instance; + grp->scope = mreq->scope; + grp->loopback = mreq->flags & TIPC_GROUP_LOOPBACK; + if (tipc_topsrv_kern_subscr(net, portid, type, 0, ~0, &grp->subid)) + return grp; + kfree(grp); + return NULL; +} + +void tipc_group_delete(struct net *net, struct tipc_group *grp) +{ + struct rb_root *tree = &grp->members; + struct tipc_member *m, *tmp; + struct sk_buff_head xmitq; + + __skb_queue_head_init(&xmitq); + + rbtree_postorder_for_each_entry_safe(m, tmp, tree, tree_node) { + tipc_group_proto_xmit(grp, m, GRP_LEAVE_MSG, &xmitq); + list_del(&m->list); + kfree(m); + } + tipc_node_distr_xmit(net, &xmitq); + tipc_nlist_purge(&grp->dests); + tipc_topsrv_kern_unsubscr(net, grp->subid); + kfree(grp); +} + +struct tipc_member *tipc_group_find_member(struct tipc_group *grp, + u32 node, u32 port) +{ + struct rb_node *n = grp->members.rb_node; + u64 nkey, key = (u64)node << 32 | port; + struct tipc_member *m; + + while (n) { + m = container_of(n, struct tipc_member, tree_node); + nkey = (u64)m->node << 32 | m->port; + if (key < nkey) + n = n->rb_left; + else if (key > nkey) + n = n->rb_right; + else + return m; + } + return NULL; +} + +static struct tipc_member *tipc_group_find_node(struct tipc_group *grp, + u32 node) +{ + struct tipc_member *m; + struct rb_node *n; + + for (n = rb_first(&grp->members); n; n = rb_next(n)) { + m = container_of(n, struct tipc_member, tree_node); + if (m->node == node) + return m; + } + return NULL; +} + +static void tipc_group_add_to_tree(struct tipc_group *grp, + struct tipc_member *m) +{ + u64 nkey, key = (u64)m->node << 32 | m->port; + struct rb_node **n, *parent = NULL; + struct tipc_member *tmp; + + n = &grp->members.rb_node; + while (*n) { + tmp = container_of(*n, struct tipc_member, tree_node); + parent = *n; + tmp = container_of(parent, struct tipc_member, tree_node); + nkey = (u64)tmp->node << 32 | tmp->port; + if (key < nkey) + n = &(*n)->rb_left; + else if (key > nkey) + n = &(*n)->rb_right; + else + return; + } + rb_link_node(&m->tree_node, parent, n); + rb_insert_color(&m->tree_node, &grp->members); +} + +static struct tipc_member *tipc_group_create_member(struct tipc_group *grp, + u32 node, u32 port, + int state) +{ + struct tipc_member *m; + + m = kzalloc(sizeof(*m), GFP_ATOMIC); + if (!m) + return NULL; + INIT_LIST_HEAD(&m->list); + m->node = node; + m->port = port; + grp->member_cnt++; + tipc_group_add_to_tree(grp, m); + tipc_nlist_add(&grp->dests, m->node); + m->state = state; + return m; +} + +void tipc_group_add_member(struct tipc_group *grp, u32 node, u32 port) +{ + tipc_group_create_member(grp, node, port, MBR_DISCOVERED); +} + +static void tipc_group_delete_member(struct tipc_group *grp, + struct tipc_member *m) +{ + rb_erase(&m->tree_node, &grp->members); + grp->member_cnt--; + list_del_init(&m->list); + + /* If last member on a node, remove node from dest list */ + if (!tipc_group_find_node(grp, m->node)) + tipc_nlist_del(&grp->dests, m->node); + + kfree(m); +} + +struct tipc_nlist *tipc_group_dests(struct tipc_group *grp) +{ + return &grp->dests; +} + +void tipc_group_self(struct tipc_group *grp, struct tipc_name_seq *seq, + int *scope) +{ + seq->type = grp->type; + seq->lower = grp->instance; + seq->upper = grp->instance; + *scope = grp->scope; +} + +void tipc_group_update_bc_members(struct tipc_group *grp) +{ + grp->bc_snd_nxt++; +} + +/* tipc_group_filter_msg() - determine if we should accept arriving message + */ +void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, + struct sk_buff_head *xmitq) +{ + struct sk_buff *skb = __skb_dequeue(inputq); + struct tipc_member *m; + struct tipc_msg *hdr; + u32 node, port; + int mtyp; + + if (!skb) + return; + + hdr = buf_msg(skb); + mtyp = msg_type(hdr); + node = msg_orignode(hdr); + port = msg_origport(hdr); + + if (!msg_in_group(hdr)) + goto drop; + + m = tipc_group_find_member(grp, node, port); + if (!tipc_group_is_receiver(m)) + goto drop; + + __skb_queue_tail(inputq, skb); + + m->bc_rcv_nxt = msg_grp_bc_seqno(hdr) + 1; + return; +drop: + kfree_skb(skb); +} + +static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, + int mtyp, struct sk_buff_head *xmitq) +{ + struct tipc_msg *hdr; + struct sk_buff *skb; + + skb = tipc_msg_create(GROUP_PROTOCOL, mtyp, INT_H_SIZE, 0, + m->node, tipc_own_addr(grp->net), + m->port, grp->portid, 0); + if (!skb) + return; + + hdr = buf_msg(skb); + if (mtyp == GRP_JOIN_MSG) + msg_set_grp_bc_syncpt(hdr, grp->bc_snd_nxt); + __skb_queue_tail(xmitq, skb); +} + +void tipc_group_proto_rcv(struct tipc_group *grp, struct tipc_msg *hdr, + struct sk_buff_head *xmitq) +{ + u32 node = msg_orignode(hdr); + u32 port = msg_origport(hdr); + struct tipc_member *m; + + if (!grp) + return; + + m = tipc_group_find_member(grp, node, port); + + switch (msg_type(hdr)) { + case GRP_JOIN_MSG: + if (!m) + m = tipc_group_create_member(grp, node, port, + MBR_QUARANTINED); + if (!m) + return; + m->bc_rcv_nxt = msg_grp_bc_syncpt(hdr); + + /* Wait until PUBLISH event is received */ + if (m->state == MBR_DISCOVERED) + m->state = MBR_JOINING; + else if (m->state == MBR_PUBLISHED) + m->state = MBR_JOINED; + return; + case GRP_LEAVE_MSG: + if (!m) + return; + + /* Wait until WITHDRAW event is received */ + if (m->state != MBR_LEAVING) { + m->state = MBR_LEAVING; + return; + } + /* Otherwise deliver already received WITHDRAW event */ + tipc_group_delete_member(grp, m); + return; + default: + pr_warn("Received unknown GROUP_PROTO message\n"); + } +} + +/* tipc_group_member_evt() - receive and handle a member up/down event + */ +void tipc_group_member_evt(struct tipc_group *grp, + struct sk_buff *skb, + struct sk_buff_head *xmitq) +{ + struct tipc_msg *hdr = buf_msg(skb); + struct tipc_event *evt = (void *)msg_data(hdr); + u32 node = evt->port.node; + u32 port = evt->port.ref; + struct tipc_member *m; + struct net *net; + u32 self; + + if (!grp) + goto drop; + + net = grp->net; + self = tipc_own_addr(net); + if (!grp->loopback && node == self && port == grp->portid) + goto drop; + + m = tipc_group_find_member(grp, node, port); + + if (evt->event == TIPC_PUBLISHED) { + if (!m) + m = tipc_group_create_member(grp, node, port, + MBR_DISCOVERED); + if (!m) + goto drop; + + /* Wait if JOIN message not yet received */ + if (m->state == MBR_DISCOVERED) + m->state = MBR_PUBLISHED; + else + m->state = MBR_JOINED; + tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, xmitq); + } else if (evt->event == TIPC_WITHDRAWN) { + if (!m) + goto drop; + + /* Keep back event if more messages might be expected */ + if (m->state != MBR_LEAVING && tipc_node_is_up(net, node)) + m->state = MBR_LEAVING; + else + tipc_group_delete_member(grp, m); + } +drop: + kfree_skb(skb); +} diff --git a/net/tipc/group.h b/net/tipc/group.h new file mode 100644 index 000000000000..9bdf4479fc03 --- /dev/null +++ b/net/tipc/group.h @@ -0,0 +1,64 @@ +/* + * net/tipc/group.h: Include file for TIPC group unicast/multicast functions + * + * Copyright (c) 2017, Ericsson AB + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_GROUP_H +#define _TIPC_GROUP_H + +#include "core.h" + +struct tipc_group; +struct tipc_member; +struct tipc_msg; + +struct tipc_group *tipc_group_create(struct net *net, u32 portid, + struct tipc_group_req *mreq); +void tipc_group_delete(struct net *net, struct tipc_group *grp); +void tipc_group_add_member(struct tipc_group *grp, u32 node, u32 port); +struct tipc_nlist *tipc_group_dests(struct tipc_group *grp); +void tipc_group_self(struct tipc_group *grp, struct tipc_name_seq *seq, + int *scope); +void tipc_group_filter_msg(struct tipc_group *grp, + struct sk_buff_head *inputq, + struct sk_buff_head *xmitq); +void tipc_group_member_evt(struct tipc_group *grp, + struct sk_buff *skb, + struct sk_buff_head *xmitq); +void tipc_group_proto_rcv(struct tipc_group *grp, + struct tipc_msg *hdr, + struct sk_buff_head *xmitq); +void tipc_group_update_bc_members(struct tipc_group *grp); +u16 tipc_group_bc_snd_nxt(struct tipc_group *grp); +int tipc_group_size(struct tipc_group *grp); +#endif diff --git a/net/tipc/link.c b/net/tipc/link.c index ac0144f532aa..bd25bff63925 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1046,11 +1046,12 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, case TIPC_MEDIUM_IMPORTANCE: case TIPC_HIGH_IMPORTANCE: case TIPC_CRITICAL_IMPORTANCE: - if (unlikely(msg_type(hdr) == TIPC_MCAST_MSG)) { + if (unlikely(msg_mcast(hdr))) { skb_queue_tail(l->bc_rcvlink->inputq, skb); return true; } case CONN_MANAGER: + case GROUP_PROTOCOL: skb_queue_tail(inputq, skb); return true; case NAME_DISTRIBUTOR: diff --git a/net/tipc/msg.h b/net/tipc/msg.h index be3e38aa9dd2..dad400935405 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -1,7 +1,7 @@ /* * net/tipc/msg.h: Include file for TIPC message header routines * - * Copyright (c) 2000-2007, 2014-2015 Ericsson AB + * Copyright (c) 2000-2007, 2014-2017 Ericsson AB * Copyright (c) 2005-2008, 2010-2011, Wind River Systems * All rights reserved. * @@ -61,10 +61,11 @@ struct plist; /* * Payload message types */ -#define TIPC_CONN_MSG 0 -#define TIPC_MCAST_MSG 1 -#define TIPC_NAMED_MSG 2 -#define TIPC_DIRECT_MSG 3 +#define TIPC_CONN_MSG 0 +#define TIPC_MCAST_MSG 1 +#define TIPC_NAMED_MSG 2 +#define TIPC_DIRECT_MSG 3 +#define TIPC_GRP_BCAST_MSG 4 /* * Internal message users @@ -73,6 +74,7 @@ struct plist; #define MSG_BUNDLER 6 #define LINK_PROTOCOL 7 #define CONN_MANAGER 8 +#define GROUP_PROTOCOL 9 #define TUNNEL_PROTOCOL 10 #define NAME_DISTRIBUTOR 11 #define MSG_FRAGMENTER 12 @@ -87,6 +89,7 @@ struct plist; #define BASIC_H_SIZE 32 /* Basic payload message */ #define NAMED_H_SIZE 40 /* Named payload message */ #define MCAST_H_SIZE 44 /* Multicast payload message */ +#define GROUP_H_SIZE 44 /* Group payload message */ #define INT_H_SIZE 40 /* Internal messages */ #define MIN_H_SIZE 24 /* Smallest legal TIPC header size */ #define MAX_H_SIZE 60 /* Largest possible TIPC header size */ @@ -252,6 +255,11 @@ static inline void msg_set_type(struct tipc_msg *m, u32 n) msg_set_bits(m, 1, 29, 0x7, n); } +static inline int msg_in_group(struct tipc_msg *m) +{ + return (msg_type(m) == TIPC_GRP_BCAST_MSG); +} + static inline u32 msg_named(struct tipc_msg *m) { return msg_type(m) == TIPC_NAMED_MSG; @@ -259,7 +267,9 @@ static inline u32 msg_named(struct tipc_msg *m) static inline u32 msg_mcast(struct tipc_msg *m) { - return msg_type(m) == TIPC_MCAST_MSG; + int mtyp = msg_type(m); + + return ((mtyp == TIPC_MCAST_MSG) || (mtyp == TIPC_GRP_BCAST_MSG)); } static inline u32 msg_connected(struct tipc_msg *m) @@ -514,6 +524,12 @@ static inline void msg_set_nameupper(struct tipc_msg *m, u32 n) #define DSC_REQ_MSG 0 #define DSC_RESP_MSG 1 +/* + * Group protocol message types + */ +#define GRP_JOIN_MSG 0 +#define GRP_LEAVE_MSG 1 + /* * Word 1 */ @@ -795,6 +811,28 @@ static inline void msg_set_link_tolerance(struct tipc_msg *m, u32 n) msg_set_bits(m, 9, 0, 0xffff, n); } +static inline u16 msg_grp_bc_syncpt(struct tipc_msg *m) +{ + return msg_bits(m, 9, 16, 0xffff); +} + +static inline void msg_set_grp_bc_syncpt(struct tipc_msg *m, u16 n) +{ + msg_set_bits(m, 9, 16, 0xffff, n); +} + +/* Word 10 + */ +static inline u16 msg_grp_bc_seqno(struct tipc_msg *m) +{ + return msg_bits(m, 10, 16, 0xffff); +} + +static inline void msg_set_grp_bc_seqno(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 10, 16, 0xffff, n); +} + static inline bool msg_peer_link_is_up(struct tipc_msg *m) { if (likely(msg_user(m) != LINK_PROTOCOL)) diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 76bd2777baaf..114d72bab827 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -43,6 +43,7 @@ #include "bcast.h" #include "addr.h" #include "node.h" +#include "group.h" #include #define TIPC_NAMETBL_SIZE 1024 /* must be a power of 2 */ @@ -596,18 +597,6 @@ not_found: return ref; } -/** - * tipc_nametbl_mc_translate - find multicast destinations - * - * Creates list of all local ports that overlap the given multicast address; - * also determines if any off-node ports overlap. - * - * Note: Publications with a scope narrower than 'limit' are ignored. - * (i.e. local node-scope publications mustn't receive messages arriving - * from another node, even if the multcast link brought it here) - * - * Returns non-zero if any off-node ports overlap - */ int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper, u32 limit, struct list_head *dports) { @@ -679,6 +668,37 @@ exit: rcu_read_unlock(); } +/* tipc_nametbl_build_group - build list of communication group members + */ +void tipc_nametbl_build_group(struct net *net, struct tipc_group *grp, + u32 type, u32 domain) +{ + struct sub_seq *sseq, *stop; + struct name_info *info; + struct publication *p; + struct name_seq *seq; + + rcu_read_lock(); + seq = nametbl_find_seq(net, type); + if (!seq) + goto exit; + + spin_lock_bh(&seq->lock); + sseq = seq->sseqs; + stop = seq->sseqs + seq->first_free; + for (; sseq != stop; sseq++) { + info = sseq->info; + list_for_each_entry(p, &info->zone_list, zone_list) { + if (!tipc_in_scope(domain, p->node)) + continue; + tipc_group_add_member(grp, p->node, p->ref); + } + } + spin_unlock_bh(&seq->lock); +exit: + rcu_read_unlock(); +} + /* * tipc_nametbl_publish - add name publication to network name tables */ diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index d121175a92b5..97646b17a4a2 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -40,6 +40,7 @@ struct tipc_subscription; struct tipc_plist; struct tipc_nlist; +struct tipc_group; /* * TIPC name types reserved for internal TIPC use (both current and planned) @@ -101,6 +102,8 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb); u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, u32 *node); int tipc_nametbl_mc_translate(struct net *net, u32 type, u32 lower, u32 upper, u32 limit, struct list_head *dports); +void tipc_nametbl_build_group(struct net *net, struct tipc_group *grp, + u32 type, u32 domain); void tipc_nametbl_lookup_dst_nodes(struct net *net, u32 type, u32 lower, u32 upper, u32 domain, struct tipc_nlist *nodes); diff --git a/net/tipc/node.h b/net/tipc/node.h index df2f2197c4ad..acd58d23a70e 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -48,7 +48,8 @@ enum { TIPC_BCAST_SYNCH = (1 << 1), TIPC_BCAST_STATE_NACK = (1 << 2), TIPC_BLOCK_FLOWCTL = (1 << 3), - TIPC_BCAST_RCAST = (1 << 4) + TIPC_BCAST_RCAST = (1 << 4), + TIPC_MCAST_GROUPS = (1 << 5) }; #define TIPC_NODE_CAPABILITIES (TIPC_BCAST_SYNCH | \ diff --git a/net/tipc/socket.c b/net/tipc/socket.c index daf7c4df4531..64bbf9d03629 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1,7 +1,7 @@ /* * net/tipc/socket.c: TIPC socket API * - * Copyright (c) 2001-2007, 2012-2016, Ericsson AB + * Copyright (c) 2001-2007, 2012-2017, Ericsson AB * Copyright (c) 2004-2008, 2010-2013, Wind River Systems * All rights reserved. * @@ -45,6 +45,7 @@ #include "socket.h" #include "bcast.h" #include "netlink.h" +#include "group.h" #define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */ #define CONN_PROBING_INTERVAL msecs_to_jiffies(3600000) /* [ms] => 1 h */ @@ -78,7 +79,7 @@ enum { * @conn_timeout: the time we can wait for an unresponded setup request * @dupl_rcvcnt: number of bytes counted twice, in both backlog and rcv queue * @cong_link_cnt: number of congested links - * @sent_unacked: # messages sent by socket, and not yet acked by peer + * @snt_unacked: # messages sent by socket, and not yet acked by peer * @rcv_unacked: # messages read by user, but not yet acked back to peer * @peer: 'connected' peer for dgram/rdm * @node: hash table node @@ -109,6 +110,7 @@ struct tipc_sock { struct rhash_head node; struct tipc_mc_method mc_method; struct rcu_head rcu; + struct tipc_group *group; }; static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb); @@ -123,6 +125,7 @@ static int tipc_sk_publish(struct tipc_sock *tsk, uint scope, struct tipc_name_seq const *seq); static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope, struct tipc_name_seq const *seq); +static int tipc_sk_leave(struct tipc_sock *tsk); static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid); static int tipc_sk_insert(struct tipc_sock *tsk); static void tipc_sk_remove(struct tipc_sock *tsk); @@ -559,6 +562,7 @@ static int tipc_release(struct socket *sock) __tipc_shutdown(sock, TIPC_ERR_NO_PORT); sk->sk_shutdown = SHUTDOWN_MASK; + tipc_sk_leave(tsk); tipc_sk_withdraw(tsk, 0, NULL); sk_stop_timer(sk, &sk->sk_timer); tipc_sk_remove(tsk); @@ -601,7 +605,10 @@ static int tipc_bind(struct socket *sock, struct sockaddr *uaddr, res = tipc_sk_withdraw(tsk, 0, NULL); goto exit; } - + if (tsk->group) { + res = -EACCES; + goto exit; + } if (uaddr_len < sizeof(struct sockaddr_tipc)) { res = -EINVAL; goto exit; @@ -698,6 +705,7 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock, { struct sock *sk = sock->sk; struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_group *grp = tsk->group; u32 mask = 0; sock_poll_wait(file, sk_sleep(sk), wait); @@ -718,8 +726,9 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock, mask |= (POLLIN | POLLRDNORM); break; case TIPC_OPEN: - if (!tsk->cong_link_cnt) - mask |= POLLOUT; + if (!grp || tipc_group_size(grp)) + if (!tsk->cong_link_cnt) + mask |= POLLOUT; if (tipc_sk_type_connectionless(sk) && (!skb_queue_empty(&sk->sk_receive_queue))) mask |= (POLLIN | POLLRDNORM); @@ -757,6 +766,9 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, struct tipc_nlist dsts; int rc; + if (tsk->group) + return -EACCES; + /* Block or return if any destination link is congested */ rc = tipc_wait_for_cond(sock, &timeout, !tsk->cong_link_cnt); if (unlikely(rc)) @@ -793,6 +805,64 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, return rc ? rc : dlen; } +/** + * tipc_send_group_bcast - send message to all members in communication group + * @sk: socket structure + * @m: message to send + * @dlen: total length of message data + * @timeout: timeout to wait for wakeup + * + * Called from function tipc_sendmsg(), which has done all sanity checks + * Returns the number of bytes sent on success, or errno + */ +static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, + int dlen, long timeout) +{ + struct sock *sk = sock->sk; + struct net *net = sock_net(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_group *grp = tsk->group; + struct tipc_nlist *dsts = tipc_group_dests(grp); + struct tipc_mc_method *method = &tsk->mc_method; + struct tipc_msg *hdr = &tsk->phdr; + int mtu = tipc_bcast_get_mtu(net); + struct sk_buff_head pkts; + int rc = -EHOSTUNREACH; + + if (!dsts->local && !dsts->remote) + return -EHOSTUNREACH; + + /* Block or return if any destination link is congested */ + rc = tipc_wait_for_cond(sock, &timeout, !tsk->cong_link_cnt); + if (unlikely(rc)) + return rc; + + /* Complete message header */ + msg_set_type(hdr, TIPC_GRP_BCAST_MSG); + msg_set_hdr_sz(hdr, MCAST_H_SIZE); + msg_set_destport(hdr, 0); + msg_set_destnode(hdr, 0); + msg_set_nameinst(hdr, 0); + msg_set_grp_bc_seqno(hdr, tipc_group_bc_snd_nxt(grp)); + + /* Build message as chain of buffers */ + skb_queue_head_init(&pkts); + rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts); + if (unlikely(rc != dlen)) + return rc; + + /* Send message */ + rc = tipc_mcast_xmit(net, &pkts, method, dsts, + &tsk->cong_link_cnt); + if (unlikely(rc)) + return rc; + + /* Update broadcast sequence number */ + tipc_group_update_bc_members(tsk->group); + + return dlen; +} + /** * tipc_sk_mcast_rcv - Deliver multicast messages to all destination sockets * @arrvq: queue with arriving messages, to be cloned after destination lookup @@ -803,13 +873,15 @@ static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq, void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, struct sk_buff_head *inputq) { - struct tipc_msg *msg; - struct list_head dports; - u32 portid; u32 scope = TIPC_CLUSTER_SCOPE; - struct sk_buff_head tmpq; - uint hsz; + u32 self = tipc_own_addr(net); struct sk_buff *skb, *_skb; + u32 lower = 0, upper = ~0; + struct sk_buff_head tmpq; + u32 portid, oport, onode; + struct list_head dports; + struct tipc_msg *msg; + int hsz; __skb_queue_head_init(&tmpq); INIT_LIST_HEAD(&dports); @@ -818,14 +890,18 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, for (; skb; skb = tipc_skb_peek(arrvq, &inputq->lock)) { msg = buf_msg(skb); hsz = skb_headroom(skb) + msg_hdr_sz(msg); - - if (in_own_node(net, msg_orignode(msg))) + oport = msg_origport(msg); + onode = msg_orignode(msg); + if (onode == self) scope = TIPC_NODE_SCOPE; /* Create destination port list and message clones: */ - tipc_nametbl_mc_translate(net, - msg_nametype(msg), msg_namelower(msg), - msg_nameupper(msg), scope, &dports); + if (!msg_in_group(msg)) { + lower = msg_namelower(msg); + upper = msg_nameupper(msg); + } + tipc_nametbl_mc_translate(net, msg_nametype(msg), lower, upper, + scope, &dports); while (tipc_dest_pop(&dports, NULL, &portid)) { _skb = __pskb_copy(skb, hsz, GFP_ATOMIC); if (_skb) { @@ -895,10 +971,6 @@ exit: kfree_skb(skb); } -static void tipc_sk_top_evt(struct tipc_sock *tsk, struct tipc_event *evt) -{ -} - /** * tipc_sendmsg - send message in connectionless manner * @sock: socket structure @@ -934,6 +1006,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) long timeout = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT); struct list_head *clinks = &tsk->cong_links; bool syn = !tipc_sk_type_connectionless(sk); + struct tipc_group *grp = tsk->group; struct tipc_msg *hdr = &tsk->phdr; struct tipc_name_seq *seq; struct sk_buff_head pkts; @@ -944,6 +1017,9 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) if (unlikely(dlen > TIPC_MAX_USER_MSG_SIZE)) return -EMSGSIZE; + if (unlikely(grp)) + return tipc_send_group_bcast(sock, m, dlen, timeout); + if (unlikely(!dest)) { dest = &tsk->peer; if (!syn || dest->family != AF_TIPC) @@ -1543,6 +1619,7 @@ static void tipc_sk_proto_rcv(struct sock *sk, struct sk_buff *skb = __skb_dequeue(inputq); struct tipc_sock *tsk = tipc_sk(sk); struct tipc_msg *hdr = buf_msg(skb); + struct tipc_group *grp = tsk->group; switch (msg_user(hdr)) { case CONN_MANAGER: @@ -1553,8 +1630,12 @@ static void tipc_sk_proto_rcv(struct sock *sk, tsk->cong_link_cnt--; sk->sk_write_space(sk); break; + case GROUP_PROTOCOL: + tipc_group_proto_rcv(grp, hdr, xmitq); + break; case TOP_SRV: - tipc_sk_top_evt(tsk, (void *)msg_data(hdr)); + tipc_group_member_evt(tsk->group, skb, xmitq); + skb = NULL; break; default: break; @@ -1699,6 +1780,7 @@ static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb, { bool sk_conn = !tipc_sk_type_connectionless(sk); struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_group *grp = tsk->group; struct tipc_msg *hdr = buf_msg(skb); struct net *net = sock_net(sk); struct sk_buff_head inputq; @@ -1710,15 +1792,19 @@ static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb, if (unlikely(!msg_isdata(hdr))) tipc_sk_proto_rcv(sk, &inputq, xmitq); - else if (unlikely(msg_type(hdr) > TIPC_DIRECT_MSG)) + else if (unlikely(msg_type(hdr) > TIPC_GRP_BCAST_MSG)) return kfree_skb(skb); + if (unlikely(grp)) + tipc_group_filter_msg(grp, &inputq, xmitq); + /* Validate and add to receive buffer if there is space */ while ((skb = __skb_dequeue(&inputq))) { hdr = buf_msg(skb); limit = rcvbuf_limit(sk, skb); if ((sk_conn && !tipc_sk_filter_connect(tsk, skb)) || - (!sk_conn && msg_connected(hdr))) + (!sk_conn && msg_connected(hdr)) || + (!grp && msg_in_group(hdr))) err = TIPC_ERR_NO_PORT; else if (sk_rmem_alloc_get(sk) + skb->truesize >= limit) err = TIPC_ERR_OVERLOAD; @@ -1837,7 +1923,6 @@ void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq) sock_put(sk); continue; } - /* No destination socket => dequeue skb if still there */ skb = tipc_skb_dequeue(inputq, dport); if (!skb) @@ -1905,6 +1990,11 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest, lock_sock(sk); + if (tsk->group) { + res = -EINVAL; + goto exit; + } + if (dst->family == AF_UNSPEC) { memset(&tsk->peer, 0, sizeof(struct sockaddr_tipc)); if (!tipc_sk_type_connectionless(sk)) @@ -2341,6 +2431,52 @@ void tipc_sk_rht_destroy(struct net *net) rhashtable_destroy(&tn->sk_rht); } +static int tipc_sk_join(struct tipc_sock *tsk, struct tipc_group_req *mreq) +{ + struct net *net = sock_net(&tsk->sk); + u32 domain = addr_domain(net, mreq->scope); + struct tipc_group *grp = tsk->group; + struct tipc_msg *hdr = &tsk->phdr; + struct tipc_name_seq seq; + int rc; + + if (mreq->type < TIPC_RESERVED_TYPES) + return -EACCES; + if (grp) + return -EACCES; + grp = tipc_group_create(net, tsk->portid, mreq); + if (!grp) + return -ENOMEM; + tsk->group = grp; + msg_set_lookup_scope(hdr, mreq->scope); + msg_set_nametype(hdr, mreq->type); + msg_set_dest_droppable(hdr, true); + seq.type = mreq->type; + seq.lower = mreq->instance; + seq.upper = seq.lower; + tipc_nametbl_build_group(net, grp, mreq->type, domain); + rc = tipc_sk_publish(tsk, mreq->scope, &seq); + if (rc) + tipc_group_delete(net, grp); + return rc; +} + +static int tipc_sk_leave(struct tipc_sock *tsk) +{ + struct net *net = sock_net(&tsk->sk); + struct tipc_group *grp = tsk->group; + struct tipc_name_seq seq; + int scope; + + if (!grp) + return -EINVAL; + tipc_group_self(grp, &seq, &scope); + tipc_group_delete(net, grp); + tsk->group = NULL; + tipc_sk_withdraw(tsk, scope, &seq); + return 0; +} + /** * tipc_setsockopt - set socket option * @sock: socket structure @@ -2359,6 +2495,7 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt, { struct sock *sk = sock->sk; struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_group_req mreq; u32 value = 0; int res = 0; @@ -2374,9 +2511,14 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt, case TIPC_CONN_TIMEOUT: if (ol < sizeof(value)) return -EINVAL; - res = get_user(value, (u32 __user *)ov); - if (res) - return res; + if (get_user(value, (u32 __user *)ov)) + return -EFAULT; + break; + case TIPC_GROUP_JOIN: + if (ol < sizeof(mreq)) + return -EINVAL; + if (copy_from_user(&mreq, ov, sizeof(mreq))) + return -EFAULT; break; default: if (ov || ol) @@ -2409,6 +2551,12 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt, tsk->mc_method.rcast = true; tsk->mc_method.mandatory = true; break; + case TIPC_GROUP_JOIN: + res = tipc_sk_join(tsk, &mreq); + break; + case TIPC_GROUP_LEAVE: + res = tipc_sk_leave(tsk); + break; default: res = -EINVAL; } @@ -2436,7 +2584,8 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt, { struct sock *sk = sock->sk; struct tipc_sock *tsk = tipc_sk(sk); - int len; + struct tipc_name_seq seq; + int len, scope; u32 value; int res; @@ -2470,6 +2619,12 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt, case TIPC_SOCK_RECVQ_DEPTH: value = skb_queue_len(&sk->sk_receive_queue); break; + case TIPC_GROUP_JOIN: + seq.type = 0; + if (tsk->group) + tipc_group_self(tsk->group, &seq, &scope); + value = seq.type; + break; default: res = -EINVAL; } -- cgit v1.2.3-71-gd317 From ae236fb208a6fbbd2e7a6913385e8fb78ac807f8 Mon Sep 17 00:00:00 2001 From: Jon Maloy Date: Fri, 13 Oct 2017 11:04:25 +0200 Subject: tipc: receive group membership events via member socket Like with any other service, group members' availability can be subscribed for by connecting to be topology server. However, because the events arrive via a different socket than the member socket, there is a real risk that membership events my arrive out of synch with the actual JOIN/LEAVE action. I.e., it is possible to receive the first messages from a new member before the corresponding JOIN event arrives, just as it is possible to receive the last messages from a leaving member after the LEAVE event has already been received. Since each member socket is internally also subscribing for membership events, we now fix this problem by passing those events on to the user via the member socket. We leverage the already present member synch- ronization protocol to guarantee correct message/event order. An event is delivered to the user as an empty message where the two source addresses identify the new/lost member. Furthermore, we set the MSG_OOB bit in the message flags to mark it as an event. If the event is an indication about a member loss we also set the MSG_EOR bit, so it can be distinguished from a member addition event. Signed-off-by: Jon Maloy Acked-by: Ying Xue Signed-off-by: David S. Miller --- include/uapi/linux/tipc.h | 1 + net/tipc/group.c | 60 +++++++++++++++++++++++++++++++++++++---------- net/tipc/group.h | 2 ++ net/tipc/msg.h | 22 +++++++++++++++-- net/tipc/socket.c | 49 ++++++++++++++++++++++++-------------- 5 files changed, 101 insertions(+), 33 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tipc.h b/include/uapi/linux/tipc.h index 5f7b2c4a09ab..ef41c11a7f38 100644 --- a/include/uapi/linux/tipc.h +++ b/include/uapi/linux/tipc.h @@ -238,6 +238,7 @@ struct sockaddr_tipc { * Flag values */ #define TIPC_GROUP_LOOPBACK 0x1 /* Receive copy of sent msg when match */ +#define TIPC_GROUP_MEMBER_EVTS 0x2 /* Receive membership events in socket */ struct tipc_group_req { __u32 type; /* group id */ diff --git a/net/tipc/group.c b/net/tipc/group.c index beb214a3420c..1bfa9348b26d 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -59,6 +59,7 @@ enum mbr_state { struct tipc_member { struct rb_node tree_node; struct list_head list; + struct sk_buff *event_msg; u32 node; u32 port; u32 instance; @@ -79,6 +80,7 @@ struct tipc_group { u16 member_cnt; u16 bc_snd_nxt; bool loopback; + bool events; }; static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, @@ -117,6 +119,7 @@ struct tipc_group *tipc_group_create(struct net *net, u32 portid, grp->instance = mreq->instance; grp->scope = mreq->scope; grp->loopback = mreq->flags & TIPC_GROUP_LOOPBACK; + grp->events = mreq->flags & TIPC_GROUP_MEMBER_EVTS; if (tipc_topsrv_kern_subscr(net, portid, type, 0, ~0, &grp->subid)) return grp; kfree(grp); @@ -279,6 +282,13 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, if (!msg_in_group(hdr)) goto drop; + if (mtyp == TIPC_GRP_MEMBER_EVT) { + if (!grp->events) + goto drop; + __skb_queue_tail(inputq, skb); + return; + } + m = tipc_group_find_member(grp, node, port); if (!tipc_group_is_receiver(m)) goto drop; @@ -311,6 +321,7 @@ static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, } void tipc_group_proto_rcv(struct tipc_group *grp, struct tipc_msg *hdr, + struct sk_buff_head *inputq, struct sk_buff_head *xmitq) { u32 node = msg_orignode(hdr); @@ -332,10 +343,12 @@ void tipc_group_proto_rcv(struct tipc_group *grp, struct tipc_msg *hdr, m->bc_rcv_nxt = msg_grp_bc_syncpt(hdr); /* Wait until PUBLISH event is received */ - if (m->state == MBR_DISCOVERED) + if (m->state == MBR_DISCOVERED) { m->state = MBR_JOINING; - else if (m->state == MBR_PUBLISHED) + } else if (m->state == MBR_PUBLISHED) { m->state = MBR_JOINED; + __skb_queue_tail(inputq, m->event_msg); + } return; case GRP_LEAVE_MSG: if (!m) @@ -347,6 +360,7 @@ void tipc_group_proto_rcv(struct tipc_group *grp, struct tipc_msg *hdr, return; } /* Otherwise deliver already received WITHDRAW event */ + __skb_queue_tail(inputq, m->event_msg); tipc_group_delete_member(grp, m); return; default: @@ -354,16 +368,17 @@ void tipc_group_proto_rcv(struct tipc_group *grp, struct tipc_msg *hdr, } } -/* tipc_group_member_evt() - receive and handle a member up/down event - */ void tipc_group_member_evt(struct tipc_group *grp, struct sk_buff *skb, + struct sk_buff_head *inputq, struct sk_buff_head *xmitq) { struct tipc_msg *hdr = buf_msg(skb); struct tipc_event *evt = (void *)msg_data(hdr); + u32 instance = evt->found_lower; u32 node = evt->port.node; u32 port = evt->port.ref; + int event = evt->event; struct tipc_member *m; struct net *net; u32 self; @@ -376,32 +391,51 @@ void tipc_group_member_evt(struct tipc_group *grp, if (!grp->loopback && node == self && port == grp->portid) goto drop; + /* Convert message before delivery to user */ + msg_set_hdr_sz(hdr, GROUP_H_SIZE); + msg_set_user(hdr, TIPC_CRITICAL_IMPORTANCE); + msg_set_type(hdr, TIPC_GRP_MEMBER_EVT); + msg_set_origport(hdr, port); + msg_set_orignode(hdr, node); + msg_set_nametype(hdr, grp->type); + msg_set_grp_evt(hdr, event); + m = tipc_group_find_member(grp, node, port); - if (evt->event == TIPC_PUBLISHED) { + if (event == TIPC_PUBLISHED) { if (!m) m = tipc_group_create_member(grp, node, port, MBR_DISCOVERED); if (!m) goto drop; - /* Wait if JOIN message not yet received */ - if (m->state == MBR_DISCOVERED) + /* Hold back event if JOIN message not yet received */ + if (m->state == MBR_DISCOVERED) { + m->event_msg = skb; m->state = MBR_PUBLISHED; - else + } else { + __skb_queue_tail(inputq, skb); m->state = MBR_JOINED; - m->instance = evt->found_lower; + } + m->instance = instance; + TIPC_SKB_CB(skb)->orig_member = m->instance; tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, xmitq); - } else if (evt->event == TIPC_WITHDRAWN) { + } else if (event == TIPC_WITHDRAWN) { if (!m) goto drop; - /* Keep back event if more messages might be expected */ - if (m->state != MBR_LEAVING && tipc_node_is_up(net, node)) + TIPC_SKB_CB(skb)->orig_member = m->instance; + + /* Hold back event if more messages might be expected */ + if (m->state != MBR_LEAVING && tipc_node_is_up(net, node)) { + m->event_msg = skb; m->state = MBR_LEAVING; - else + } else { + __skb_queue_tail(inputq, skb); tipc_group_delete_member(grp, m); + } } + return; drop: kfree_skb(skb); } diff --git a/net/tipc/group.h b/net/tipc/group.h index 9bdf4479fc03..5d3f10d28967 100644 --- a/net/tipc/group.h +++ b/net/tipc/group.h @@ -54,9 +54,11 @@ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *xmitq); void tipc_group_member_evt(struct tipc_group *grp, struct sk_buff *skb, + struct sk_buff_head *inputq, struct sk_buff_head *xmitq); void tipc_group_proto_rcv(struct tipc_group *grp, struct tipc_msg *hdr, + struct sk_buff_head *inputq, struct sk_buff_head *xmitq); void tipc_group_update_bc_members(struct tipc_group *grp); u16 tipc_group_bc_snd_nxt(struct tipc_group *grp); diff --git a/net/tipc/msg.h b/net/tipc/msg.h index e438716d2372..1b527b154e46 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -65,7 +65,8 @@ struct plist; #define TIPC_MCAST_MSG 1 #define TIPC_NAMED_MSG 2 #define TIPC_DIRECT_MSG 3 -#define TIPC_GRP_BCAST_MSG 4 +#define TIPC_GRP_MEMBER_EVT 4 +#define TIPC_GRP_BCAST_MSG 5 /* * Internal message users @@ -258,7 +259,14 @@ static inline void msg_set_type(struct tipc_msg *m, u32 n) static inline int msg_in_group(struct tipc_msg *m) { - return (msg_type(m) == TIPC_GRP_BCAST_MSG); + int mtyp = msg_type(m); + + return (mtyp == TIPC_GRP_BCAST_MSG) || (mtyp == TIPC_GRP_MEMBER_EVT); +} + +static inline bool msg_is_grp_evt(struct tipc_msg *m) +{ + return msg_type(m) == TIPC_GRP_MEMBER_EVT; } static inline u32 msg_named(struct tipc_msg *m) @@ -824,6 +832,16 @@ static inline void msg_set_grp_bc_syncpt(struct tipc_msg *m, u16 n) /* Word 10 */ +static inline u16 msg_grp_evt(struct tipc_msg *m) +{ + return msg_bits(m, 10, 0, 0x3); +} + +static inline void msg_set_grp_evt(struct tipc_msg *m, int n) +{ + msg_set_bits(m, 10, 0, 0x3, n); +} + static inline u16 msg_grp_bc_seqno(struct tipc_msg *m) { return msg_bits(m, 10, 16, 0xffff); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 25ecf1201527..0a2eac309177 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -709,41 +709,43 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; + struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); struct tipc_sock *tsk = tipc_sk(sk); struct tipc_group *grp = tsk->group; - u32 mask = 0; + u32 revents = 0; sock_poll_wait(file, sk_sleep(sk), wait); if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= POLLRDHUP | POLLIN | POLLRDNORM; + revents |= POLLRDHUP | POLLIN | POLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) - mask |= POLLHUP; + revents |= POLLHUP; switch (sk->sk_state) { case TIPC_ESTABLISHED: if (!tsk->cong_link_cnt && !tsk_conn_cong(tsk)) - mask |= POLLOUT; + revents |= POLLOUT; /* fall thru' */ case TIPC_LISTEN: case TIPC_CONNECTING: - if (!skb_queue_empty(&sk->sk_receive_queue)) - mask |= (POLLIN | POLLRDNORM); + if (skb) + revents |= POLLIN | POLLRDNORM; break; case TIPC_OPEN: if (!grp || tipc_group_size(grp)) if (!tsk->cong_link_cnt) - mask |= POLLOUT; - if (tipc_sk_type_connectionless(sk) && - (!skb_queue_empty(&sk->sk_receive_queue))) - mask |= (POLLIN | POLLRDNORM); + revents |= POLLOUT; + if (!tipc_sk_type_connectionless(sk)) + break; + if (!skb) + break; + revents |= POLLIN | POLLRDNORM; break; case TIPC_DISCONNECTING: - mask = (POLLIN | POLLRDNORM | POLLHUP); + revents = POLLIN | POLLRDNORM | POLLHUP; break; } - - return mask; + return revents; } /** @@ -1415,11 +1417,12 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, size_t buflen, int flags) { struct sock *sk = sock->sk; - struct tipc_sock *tsk = tipc_sk(sk); - struct sk_buff *skb; - struct tipc_msg *hdr; bool connected = !tipc_sk_type_connectionless(sk); + struct tipc_sock *tsk = tipc_sk(sk); int rc, err, hlen, dlen, copy; + struct tipc_msg *hdr; + struct sk_buff *skb; + bool grp_evt; long timeout; /* Catch invalid receive requests */ @@ -1443,6 +1446,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, dlen = msg_data_sz(hdr); hlen = msg_hdr_sz(hdr); err = msg_errcode(hdr); + grp_evt = msg_is_grp_evt(hdr); if (likely(dlen || err)) break; tsk_advance_rx_queue(sk); @@ -1469,11 +1473,20 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, if (unlikely(rc)) goto exit; + /* Mark message as group event if applicable */ + if (unlikely(grp_evt)) { + if (msg_grp_evt(hdr) == TIPC_WITHDRAWN) + m->msg_flags |= MSG_EOR; + m->msg_flags |= MSG_OOB; + copy = 0; + } + /* Caption of data or error code/rejected data was successful */ if (unlikely(flags & MSG_PEEK)) goto exit; tsk_advance_rx_queue(sk); + if (likely(!connected)) goto exit; @@ -1648,10 +1661,10 @@ static void tipc_sk_proto_rcv(struct sock *sk, sk->sk_write_space(sk); break; case GROUP_PROTOCOL: - tipc_group_proto_rcv(grp, hdr, xmitq); + tipc_group_proto_rcv(grp, hdr, inputq, xmitq); break; case TOP_SRV: - tipc_group_member_evt(tsk->group, skb, xmitq); + tipc_group_member_evt(tsk->group, skb, inputq, xmitq); skb = NULL; break; default: -- cgit v1.2.3-71-gd317 From 4e8b86c062695454df0b76f3fee4fab8dc4bb716 Mon Sep 17 00:00:00 2001 From: Amritha Nambiar Date: Thu, 7 Sep 2017 04:00:06 -0700 Subject: mqprio: Introduce new hardware offload mode and shaper in mqprio The offload types currently supported in mqprio are 0 (no offload) and 1 (offload only TCs) by setting these values for the 'hw' option. If offloads are supported by setting the 'hw' option to 1, the default offload mode is 'dcb' where only the TC values are offloaded to the device. This patch introduces a new hardware offload mode called 'channel' with 'hw' set to 1 in mqprio which makes full use of the mqprio options, the TCs, the queue configurations and the QoS parameters for the TCs. This is achieved through a new netlink attribute for the 'mode' option which takes values such as 'dcb' (default) and 'channel'. The 'channel' mode also supports QoS attributes for traffic class such as minimum and maximum values for bandwidth rate limits. This patch enables configuring additional HW shaper attributes associated with a traffic class. Currently the shaper for bandwidth rate limiting is supported which takes options such as minimum and maximum bandwidth rates and are offloaded to the hardware in the 'channel' mode. The min and max limits for bandwidth rates are provided by the user along with the TCs and the queue configurations when creating the mqprio qdisc. The interface can be extended to support new HW shapers in future through the 'shaper' attribute. Introduces a new data structure 'tc_mqprio_qopt_offload' for offloading mqprio queue options and use this to be shared between the kernel and device driver. This contains a copy of the existing data structure for mqprio queue options. This new data structure can be extended when adding new attributes for traffic class such as mode, shaper, shaper parameters (bandwidth rate limits). The existing data structure for mqprio queue options will be shared between the kernel and userspace. Example: queues 4@0 4@4 hw 1 mode channel shaper bw_rlimit\ min_rate 1Gbit 2Gbit max_rate 4Gbit 5Gbit To dump the bandwidth rates: qdisc mqprio 804a: root tc 2 map 0 0 0 0 1 1 1 1 0 0 0 0 0 0 0 0 queues:(0:3) (4:7) mode:channel shaper:bw_rlimit min_rate:1Gbit 2Gbit max_rate:4Gbit 5Gbit Signed-off-by: Amritha Nambiar Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/net/pkt_cls.h | 9 ++ include/uapi/linux/pkt_sched.h | 32 +++++++ net/sched/sch_mqprio.c | 183 +++++++++++++++++++++++++++++++++++++++-- 3 files changed, 215 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index f5263743076b..60d39789e4f0 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -546,6 +546,15 @@ struct tc_cls_bpf_offload { u32 gen_flags; }; +struct tc_mqprio_qopt_offload { + /* struct tc_mqprio_qopt must always be the first element */ + struct tc_mqprio_qopt qopt; + u16 mode; + u16 shaper; + u32 flags; + u64 min_rate[TC_QOPT_MAX_QUEUE]; + u64 max_rate[TC_QOPT_MAX_QUEUE]; +}; /* This structure holds cookie structure that is passed from user * to the kernel for actions and classifiers diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 099bf5528fed..e95b5c9b9fad 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -625,6 +625,22 @@ enum { #define TC_MQPRIO_HW_OFFLOAD_MAX (__TC_MQPRIO_HW_OFFLOAD_MAX - 1) +enum { + TC_MQPRIO_MODE_DCB, + TC_MQPRIO_MODE_CHANNEL, + __TC_MQPRIO_MODE_MAX +}; + +#define __TC_MQPRIO_MODE_MAX (__TC_MQPRIO_MODE_MAX - 1) + +enum { + TC_MQPRIO_SHAPER_DCB, + TC_MQPRIO_SHAPER_BW_RATE, /* Add new shapers below */ + __TC_MQPRIO_SHAPER_MAX +}; + +#define __TC_MQPRIO_SHAPER_MAX (__TC_MQPRIO_SHAPER_MAX - 1) + struct tc_mqprio_qopt { __u8 num_tc; __u8 prio_tc_map[TC_QOPT_BITMASK + 1]; @@ -633,6 +649,22 @@ struct tc_mqprio_qopt { __u16 offset[TC_QOPT_MAX_QUEUE]; }; +#define TC_MQPRIO_F_MODE 0x1 +#define TC_MQPRIO_F_SHAPER 0x2 +#define TC_MQPRIO_F_MIN_RATE 0x4 +#define TC_MQPRIO_F_MAX_RATE 0x8 + +enum { + TCA_MQPRIO_UNSPEC, + TCA_MQPRIO_MODE, + TCA_MQPRIO_SHAPER, + TCA_MQPRIO_MIN_RATE64, + TCA_MQPRIO_MAX_RATE64, + __TCA_MQPRIO_MAX, +}; + +#define TCA_MQPRIO_MAX (__TCA_MQPRIO_MAX - 1) + /* SFB */ enum { diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 6bcdfe6e7b63..f1ae9be83934 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -18,10 +18,16 @@ #include #include #include +#include struct mqprio_sched { struct Qdisc **qdiscs; + u16 mode; + u16 shaper; int hw_offload; + u32 flags; + u64 min_rate[TC_QOPT_MAX_QUEUE]; + u64 max_rate[TC_QOPT_MAX_QUEUE]; }; static void mqprio_destroy(struct Qdisc *sch) @@ -39,9 +45,17 @@ static void mqprio_destroy(struct Qdisc *sch) } if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc) { - struct tc_mqprio_qopt mqprio = {}; + struct tc_mqprio_qopt_offload mqprio = { { 0 } }; - dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_MQPRIO, &mqprio); + switch (priv->mode) { + case TC_MQPRIO_MODE_DCB: + case TC_MQPRIO_MODE_CHANNEL: + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_MQPRIO, + &mqprio); + break; + default: + return; + } } else { netdev_set_num_tc(dev, 0); } @@ -97,6 +111,26 @@ static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt) return 0; } +static const struct nla_policy mqprio_policy[TCA_MQPRIO_MAX + 1] = { + [TCA_MQPRIO_MODE] = { .len = sizeof(u16) }, + [TCA_MQPRIO_SHAPER] = { .len = sizeof(u16) }, + [TCA_MQPRIO_MIN_RATE64] = { .type = NLA_NESTED }, + [TCA_MQPRIO_MAX_RATE64] = { .type = NLA_NESTED }, +}; + +static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, + const struct nla_policy *policy, int len) +{ + int nested_len = nla_len(nla) - NLA_ALIGN(len); + + if (nested_len >= nla_attr_size(0)) + return nla_parse(tb, maxtype, nla_data(nla) + NLA_ALIGN(len), + nested_len, policy, NULL); + + memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1)); + return 0; +} + static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) { struct net_device *dev = qdisc_dev(sch); @@ -105,6 +139,10 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) struct Qdisc *qdisc; int i, err = -EOPNOTSUPP; struct tc_mqprio_qopt *qopt = NULL; + struct nlattr *tb[TCA_MQPRIO_MAX + 1]; + struct nlattr *attr; + int rem; + int len = nla_len(opt) - NLA_ALIGN(sizeof(*qopt)); BUILD_BUG_ON(TC_MAX_QUEUE != TC_QOPT_MAX_QUEUE); BUILD_BUG_ON(TC_BITMASK != TC_QOPT_BITMASK); @@ -122,6 +160,58 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) if (mqprio_parse_opt(dev, qopt)) return -EINVAL; + if (len > 0) { + err = parse_attr(tb, TCA_MQPRIO_MAX, opt, mqprio_policy, + sizeof(*qopt)); + if (err < 0) + return err; + + if (!qopt->hw) + return -EINVAL; + + if (tb[TCA_MQPRIO_MODE]) { + priv->flags |= TC_MQPRIO_F_MODE; + priv->mode = *(u16 *)nla_data(tb[TCA_MQPRIO_MODE]); + } + + if (tb[TCA_MQPRIO_SHAPER]) { + priv->flags |= TC_MQPRIO_F_SHAPER; + priv->shaper = *(u16 *)nla_data(tb[TCA_MQPRIO_SHAPER]); + } + + if (tb[TCA_MQPRIO_MIN_RATE64]) { + if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) + return -EINVAL; + i = 0; + nla_for_each_nested(attr, tb[TCA_MQPRIO_MIN_RATE64], + rem) { + if (nla_type(attr) != TCA_MQPRIO_MIN_RATE64) + return -EINVAL; + if (i >= qopt->num_tc) + break; + priv->min_rate[i] = *(u64 *)nla_data(attr); + i++; + } + priv->flags |= TC_MQPRIO_F_MIN_RATE; + } + + if (tb[TCA_MQPRIO_MAX_RATE64]) { + if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) + return -EINVAL; + i = 0; + nla_for_each_nested(attr, tb[TCA_MQPRIO_MAX_RATE64], + rem) { + if (nla_type(attr) != TCA_MQPRIO_MAX_RATE64) + return -EINVAL; + if (i >= qopt->num_tc) + break; + priv->max_rate[i] = *(u64 *)nla_data(attr); + i++; + } + priv->flags |= TC_MQPRIO_F_MAX_RATE; + } + } + /* pre-allocate qdisc, attachment can't fail */ priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]), GFP_KERNEL); @@ -146,14 +236,36 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) * supplied and verified mapping */ if (qopt->hw) { - struct tc_mqprio_qopt mqprio = *qopt; + struct tc_mqprio_qopt_offload mqprio = {.qopt = *qopt}; - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_MQPRIO, + switch (priv->mode) { + case TC_MQPRIO_MODE_DCB: + if (priv->shaper != TC_MQPRIO_SHAPER_DCB) + return -EINVAL; + break; + case TC_MQPRIO_MODE_CHANNEL: + mqprio.flags = priv->flags; + if (priv->flags & TC_MQPRIO_F_MODE) + mqprio.mode = priv->mode; + if (priv->flags & TC_MQPRIO_F_SHAPER) + mqprio.shaper = priv->shaper; + if (priv->flags & TC_MQPRIO_F_MIN_RATE) + for (i = 0; i < mqprio.qopt.num_tc; i++) + mqprio.min_rate[i] = priv->min_rate[i]; + if (priv->flags & TC_MQPRIO_F_MAX_RATE) + for (i = 0; i < mqprio.qopt.num_tc; i++) + mqprio.max_rate[i] = priv->max_rate[i]; + break; + default: + return -EINVAL; + } + err = dev->netdev_ops->ndo_setup_tc(dev, + TC_SETUP_MQPRIO, &mqprio); if (err) return err; - priv->hw_offload = mqprio.hw; + priv->hw_offload = mqprio.qopt.hw; } else { netdev_set_num_tc(dev, qopt->num_tc); for (i = 0; i < qopt->num_tc; i++) @@ -223,11 +335,51 @@ static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, return 0; } +static int dump_rates(struct mqprio_sched *priv, + struct tc_mqprio_qopt *opt, struct sk_buff *skb) +{ + struct nlattr *nest; + int i; + + if (priv->flags & TC_MQPRIO_F_MIN_RATE) { + nest = nla_nest_start(skb, TCA_MQPRIO_MIN_RATE64); + if (!nest) + goto nla_put_failure; + + for (i = 0; i < opt->num_tc; i++) { + if (nla_put(skb, TCA_MQPRIO_MIN_RATE64, + sizeof(priv->min_rate[i]), + &priv->min_rate[i])) + goto nla_put_failure; + } + nla_nest_end(skb, nest); + } + + if (priv->flags & TC_MQPRIO_F_MAX_RATE) { + nest = nla_nest_start(skb, TCA_MQPRIO_MAX_RATE64); + if (!nest) + goto nla_put_failure; + + for (i = 0; i < opt->num_tc; i++) { + if (nla_put(skb, TCA_MQPRIO_MAX_RATE64, + sizeof(priv->max_rate[i]), + &priv->max_rate[i])) + goto nla_put_failure; + } + nla_nest_end(skb, nest); + } + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -1; +} + static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) { struct net_device *dev = qdisc_dev(sch); struct mqprio_sched *priv = qdisc_priv(sch); - unsigned char *b = skb_tail_pointer(skb); + struct nlattr *nla = (struct nlattr *)skb_tail_pointer(skb); struct tc_mqprio_qopt opt = { 0 }; struct Qdisc *qdisc; unsigned int i; @@ -258,12 +410,25 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) opt.offset[i] = dev->tc_to_txq[i].offset; } - if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) + if (nla_put(skb, TCA_OPTIONS, NLA_ALIGN(sizeof(opt)), &opt)) + goto nla_put_failure; + + if ((priv->flags & TC_MQPRIO_F_MODE) && + nla_put_u16(skb, TCA_MQPRIO_MODE, priv->mode)) + goto nla_put_failure; + + if ((priv->flags & TC_MQPRIO_F_SHAPER) && + nla_put_u16(skb, TCA_MQPRIO_SHAPER, priv->shaper)) + goto nla_put_failure; + + if ((priv->flags & TC_MQPRIO_F_MIN_RATE || + priv->flags & TC_MQPRIO_F_MAX_RATE) && + (dump_rates(priv, &opt, skb) != 0)) goto nla_put_failure; - return skb->len; + return nla_nest_end(skb, nla); nla_put_failure: - nlmsg_trim(skb, b); + nlmsg_trim(skb, nla); return -1; } -- cgit v1.2.3-71-gd317 From fd4f6f2a78aeaebb7094c1bb9b30623d18a86e4c Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Thu, 12 Oct 2017 02:16:11 -0400 Subject: cramfs: implement uncompressed and arbitrary data block positioning Two new capabilities are introduced here: - The ability to store some blocks uncompressed. - The ability to locate blocks anywhere. Those capabilities can be used independently, but the combination opens the possibility for execute-in-place (XIP) of program text segments that must remain uncompressed, and in the MMU case, must have a specific alignment. It is even possible to still have the writable data segments from the same file compressed as they have to be copied into RAM anyway. This is achieved by giving special meanings to some unused block pointer bits while remaining compatible with legacy cramfs images. Signed-off-by: Nicolas Pitre Tested-by: Chris Brandt Signed-off-by: Al Viro --- fs/cramfs/README | 31 ++++++++++++++- fs/cramfs/inode.c | 90 +++++++++++++++++++++++++++++++++--------- include/uapi/linux/cramfs_fs.h | 26 +++++++++++- 3 files changed, 126 insertions(+), 21 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/cramfs/README b/fs/cramfs/README index 9d4e7ea311f4..d71b27e0ff15 100644 --- a/fs/cramfs/README +++ b/fs/cramfs/README @@ -49,17 +49,46 @@ same as the start of the (i+1)'th if there is one). The first immediately follows the last for the file. s are each 32 bits long. +When the CRAMFS_FLAG_EXT_BLOCK_POINTERS capability bit is set, each +'s top bits may contain special flags as follows: + +CRAMFS_BLK_FLAG_UNCOMPRESSED (bit 31): + The block data is not compressed and should be copied verbatim. + +CRAMFS_BLK_FLAG_DIRECT_PTR (bit 30): + The stores the actual block start offset and not + its end, shifted right by 2 bits. The block must therefore be + aligned to a 4-byte boundary. The block size is either blksize + if CRAMFS_BLK_FLAG_UNCOMPRESSED is also specified, otherwise + the compressed data length is included in the first 2 bytes of + the block data. This is used to allow discontiguous data layout + and specific data block alignments e.g. for XIP applications. + + The order of 's is a depth-first descent of the directory tree, i.e. the same order as `find -size +0 \( -type f -o -type l \) -print'. : The i'th is the output of zlib's compress function -applied to the i'th blksize-sized chunk of the input data. +applied to the i'th blksize-sized chunk of the input data if the +corresponding CRAMFS_BLK_FLAG_UNCOMPRESSED bit is not set, +otherwise it is the input data directly. (For the last of the file, the input may of course be smaller.) Each may be a different size. (See above.) + s are merely byte-aligned, not generally u32-aligned. +When CRAMFS_BLK_FLAG_DIRECT_PTR is specified then the corresponding + may be located anywhere and not necessarily contiguous with +the previous/next blocks. In that case it is minimally u32-aligned. +If CRAMFS_BLK_FLAG_UNCOMPRESSED is also specified then the size is always +blksize except for the last block which is limited by the file length. +If CRAMFS_BLK_FLAG_DIRECT_PTR is set and CRAMFS_BLK_FLAG_UNCOMPRESSED +is not set then the first 2 bytes of the block contains the size of the +remaining block data as this cannot be determined from the placement of +logically adjacent blocks. + Holes ----- diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index bcdccb7a820b..19045453a8f3 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -618,34 +618,86 @@ static int cramfs_readpage(struct file *file, struct page *page) if (page->index < maxblock) { struct super_block *sb = inode->i_sb; - u32 blkptr_offset = OFFSET(inode) + page->index*4; - u32 start_offset, compr_len; + u32 blkptr_offset = OFFSET(inode) + page->index * 4; + u32 block_ptr, block_start, block_len; + bool uncompressed, direct; - start_offset = OFFSET(inode) + maxblock*4; mutex_lock(&read_mutex); - if (page->index) - start_offset = *(u32 *) cramfs_read(sb, blkptr_offset-4, - 4); - compr_len = (*(u32 *) cramfs_read(sb, blkptr_offset, 4) - - start_offset); - mutex_unlock(&read_mutex); + block_ptr = *(u32 *) cramfs_read(sb, blkptr_offset, 4); + uncompressed = (block_ptr & CRAMFS_BLK_FLAG_UNCOMPRESSED); + direct = (block_ptr & CRAMFS_BLK_FLAG_DIRECT_PTR); + block_ptr &= ~CRAMFS_BLK_FLAGS; + + if (direct) { + /* + * The block pointer is an absolute start pointer, + * shifted by 2 bits. The size is included in the + * first 2 bytes of the data block when compressed, + * or PAGE_SIZE otherwise. + */ + block_start = block_ptr << CRAMFS_BLK_DIRECT_PTR_SHIFT; + if (uncompressed) { + block_len = PAGE_SIZE; + /* if last block: cap to file length */ + if (page->index == maxblock - 1) + block_len = + offset_in_page(inode->i_size); + } else { + block_len = *(u16 *) + cramfs_read(sb, block_start, 2); + block_start += 2; + } + } else { + /* + * The block pointer indicates one past the end of + * the current block (start of next block). If this + * is the first block then it starts where the block + * pointer table ends, otherwise its start comes + * from the previous block's pointer. + */ + block_start = OFFSET(inode) + maxblock * 4; + if (page->index) + block_start = *(u32 *) + cramfs_read(sb, blkptr_offset - 4, 4); + /* Beware... previous ptr might be a direct ptr */ + if (unlikely(block_start & CRAMFS_BLK_FLAG_DIRECT_PTR)) { + /* See comments on earlier code. */ + u32 prev_start = block_start; + block_start = prev_start & ~CRAMFS_BLK_FLAGS; + block_start <<= CRAMFS_BLK_DIRECT_PTR_SHIFT; + if (prev_start & CRAMFS_BLK_FLAG_UNCOMPRESSED) { + block_start += PAGE_SIZE; + } else { + block_len = *(u16 *) + cramfs_read(sb, block_start, 2); + block_start += 2 + block_len; + } + } + block_start &= ~CRAMFS_BLK_FLAGS; + block_len = block_ptr - block_start; + } - if (compr_len == 0) + if (block_len == 0) ; /* hole */ - else if (unlikely(compr_len > (PAGE_SIZE << 1))) { - pr_err("bad compressed blocksize %u\n", - compr_len); + else if (unlikely(block_len > 2*PAGE_SIZE || + (uncompressed && block_len > PAGE_SIZE))) { + mutex_unlock(&read_mutex); + pr_err("bad data blocksize %u\n", block_len); goto err; + } else if (uncompressed) { + memcpy(pgdata, + cramfs_read(sb, block_start, block_len), + block_len); + bytes_filled = block_len; } else { - mutex_lock(&read_mutex); bytes_filled = cramfs_uncompress_block(pgdata, PAGE_SIZE, - cramfs_read(sb, start_offset, compr_len), - compr_len); - mutex_unlock(&read_mutex); - if (unlikely(bytes_filled < 0)) - goto err; + cramfs_read(sb, block_start, block_len), + block_len); } + mutex_unlock(&read_mutex); + if (unlikely(bytes_filled < 0)) + goto err; } memset(pgdata + bytes_filled, 0, PAGE_SIZE - bytes_filled); diff --git a/include/uapi/linux/cramfs_fs.h b/include/uapi/linux/cramfs_fs.h index e4611a9b9243..ce2c885133e2 100644 --- a/include/uapi/linux/cramfs_fs.h +++ b/include/uapi/linux/cramfs_fs.h @@ -73,6 +73,7 @@ struct cramfs_super { #define CRAMFS_FLAG_HOLES 0x00000100 /* support for holes */ #define CRAMFS_FLAG_WRONG_SIGNATURE 0x00000200 /* reserved */ #define CRAMFS_FLAG_SHIFTED_ROOT_OFFSET 0x00000400 /* shifted root fs */ +#define CRAMFS_FLAG_EXT_BLOCK_POINTERS 0x00000800 /* block pointer extensions */ /* * Valid values in super.flags. Currently we refuse to mount @@ -82,7 +83,30 @@ struct cramfs_super { #define CRAMFS_SUPPORTED_FLAGS ( 0x000000ff \ | CRAMFS_FLAG_HOLES \ | CRAMFS_FLAG_WRONG_SIGNATURE \ - | CRAMFS_FLAG_SHIFTED_ROOT_OFFSET ) + | CRAMFS_FLAG_SHIFTED_ROOT_OFFSET \ + | CRAMFS_FLAG_EXT_BLOCK_POINTERS ) +/* + * Block pointer flags + * + * The maximum block offset that needs to be represented is roughly: + * + * (1 << CRAMFS_OFFSET_WIDTH) * 4 + + * (1 << CRAMFS_SIZE_WIDTH) / PAGE_SIZE * (4 + PAGE_SIZE) + * = 0x11004000 + * + * That leaves room for 3 flag bits in the block pointer table. + */ +#define CRAMFS_BLK_FLAG_UNCOMPRESSED (1 << 31) +#define CRAMFS_BLK_FLAG_DIRECT_PTR (1 << 30) + +#define CRAMFS_BLK_FLAGS ( CRAMFS_BLK_FLAG_UNCOMPRESSED \ + | CRAMFS_BLK_FLAG_DIRECT_PTR ) + +/* + * Direct blocks are at least 4-byte aligned. + * Pointers to direct blocks are shifted down by 2 bits. + */ +#define CRAMFS_BLK_DIRECT_PTR_SHIFT 2 #endif /* _UAPI__CRAMFS_H */ -- cgit v1.2.3-71-gd317 From 32302902ff093891d8e64439cbb8ceae83e21ef8 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 12 Oct 2017 11:38:45 -0700 Subject: mqprio: Reserve last 32 classid values for HW traffic classes and misc IDs This patch makes a slight tweak to mqprio in order to bring the classid values used back in line with what is used for mq. The general idea is to reserve values :ffe0 - :ffef to identify hardware traffic classes normally reported via dev->num_tc. By doing this we can maintain a consistent behavior with mq for classid where :1 - :ffdf will represent a physical qdisc mapped onto a Tx queue represented by classid - 1, and the traffic classes will be mapped onto a known subset of classid values reserved for our virtual qdiscs. Note I reserved the range from :fff0 - :ffff since this way we might be able to reuse these classid values with clsact and ingress which would mean that for mq, mqprio, ingress, and clsact we should be able to maintain a similar classid layout. Signed-off-by: Alexander Duyck Tested-by: Jesus Sanchez-Palencia Signed-off-by: David S. Miller --- include/uapi/linux/pkt_sched.h | 1 + net/sched/sch_mqprio.c | 79 ++++++++++++++++++++++++------------------ 2 files changed, 47 insertions(+), 33 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index e95b5c9b9fad..e7cc3d3c7421 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -74,6 +74,7 @@ struct tc_estimator { #define TC_H_INGRESS (0xFFFFFFF1U) #define TC_H_CLSACT TC_H_INGRESS +#define TC_H_MIN_PRIORITY 0xFFE0U #define TC_H_MIN_INGRESS 0xFFF2U #define TC_H_MIN_EGRESS 0xFFF3U diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index f1ae9be83934..cae91b4b08a6 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -153,6 +153,10 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) if (!netif_is_multiqueue(dev)) return -EOPNOTSUPP; + /* make certain can allocate enough classids to handle queues */ + if (dev->num_tx_queues >= TC_H_MIN_PRIORITY) + return -ENOMEM; + if (!opt || nla_len(opt) < sizeof(*qopt)) return -EINVAL; @@ -305,7 +309,7 @@ static struct netdev_queue *mqprio_queue_get(struct Qdisc *sch, unsigned long cl) { struct net_device *dev = qdisc_dev(sch); - unsigned long ntx = cl - 1 - netdev_get_num_tc(dev); + unsigned long ntx = cl - 1; if (ntx >= dev->num_tx_queues) return NULL; @@ -447,38 +451,35 @@ static unsigned long mqprio_find(struct Qdisc *sch, u32 classid) struct net_device *dev = qdisc_dev(sch); unsigned int ntx = TC_H_MIN(classid); - if (ntx > dev->num_tx_queues + netdev_get_num_tc(dev)) - return 0; - return ntx; + /* There are essentially two regions here that have valid classid + * values. The first region will have a classid value of 1 through + * num_tx_queues. All of these are backed by actual Qdiscs. + */ + if (ntx < TC_H_MIN_PRIORITY) + return (ntx <= dev->num_tx_queues) ? ntx : 0; + + /* The second region represents the hardware traffic classes. These + * are represented by classid values of TC_H_MIN_PRIORITY through + * TC_H_MIN_PRIORITY + netdev_get_num_tc - 1 + */ + return ((ntx - TC_H_MIN_PRIORITY) < netdev_get_num_tc(dev)) ? ntx : 0; } static int mqprio_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { - struct net_device *dev = qdisc_dev(sch); + if (cl < TC_H_MIN_PRIORITY) { + struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); + struct net_device *dev = qdisc_dev(sch); + int tc = netdev_txq_to_tc(dev, cl - 1); - if (cl <= netdev_get_num_tc(dev)) { + tcm->tcm_parent = (tc < 0) ? 0 : + TC_H_MAKE(TC_H_MAJ(sch->handle), + TC_H_MIN(tc + TC_H_MIN_PRIORITY)); + tcm->tcm_info = dev_queue->qdisc_sleeping->handle; + } else { tcm->tcm_parent = TC_H_ROOT; tcm->tcm_info = 0; - } else { - int i; - struct netdev_queue *dev_queue; - - dev_queue = mqprio_queue_get(sch, cl); - tcm->tcm_parent = 0; - for (i = 0; i < netdev_get_num_tc(dev); i++) { - struct netdev_tc_txq tc = dev->tc_to_txq[i]; - int q_idx = cl - netdev_get_num_tc(dev); - - if (q_idx > tc.offset && - q_idx <= tc.offset + tc.count) { - tcm->tcm_parent = - TC_H_MAKE(TC_H_MAJ(sch->handle), - TC_H_MIN(i + 1)); - break; - } - } - tcm->tcm_info = dev_queue->qdisc_sleeping->handle; } tcm->tcm_handle |= TC_H_MIN(cl); return 0; @@ -489,15 +490,14 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, __releases(d->lock) __acquires(d->lock) { - struct net_device *dev = qdisc_dev(sch); - - if (cl <= netdev_get_num_tc(dev)) { + if (cl >= TC_H_MIN_PRIORITY) { int i; __u32 qlen = 0; struct Qdisc *qdisc; struct gnet_stats_queue qstats = {0}; struct gnet_stats_basic_packed bstats = {0}; - struct netdev_tc_txq tc = dev->tc_to_txq[cl - 1]; + struct net_device *dev = qdisc_dev(sch); + struct netdev_tc_txq tc = dev->tc_to_txq[cl & TC_BITMASK]; /* Drop lock here it will be reclaimed before touching * statistics this is required because the d->lock we @@ -550,12 +550,25 @@ static void mqprio_walk(struct Qdisc *sch, struct qdisc_walker *arg) /* Walk hierarchy with a virtual class per tc */ arg->count = arg->skip; - for (ntx = arg->skip; - ntx < dev->num_tx_queues + netdev_get_num_tc(dev); - ntx++) { + for (ntx = arg->skip; ntx < netdev_get_num_tc(dev); ntx++) { + if (arg->fn(sch, ntx + TC_H_MIN_PRIORITY, arg) < 0) { + arg->stop = 1; + return; + } + arg->count++; + } + + /* Pad the values and skip over unused traffic classes */ + if (ntx < TC_MAX_QUEUE) { + arg->count = TC_MAX_QUEUE; + ntx = TC_MAX_QUEUE; + } + + /* Reset offset, sort out remaining per-queue qdiscs */ + for (ntx -= TC_MAX_QUEUE; ntx < dev->num_tx_queues; ntx++) { if (arg->fn(sch, ntx + 1, arg) < 0) { arg->stop = 1; - break; + return; } arg->count++; } -- cgit v1.2.3-71-gd317 From 6710e1126934d8b4372b4d2f9ae1646cd3f151bf Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Mon, 16 Oct 2017 12:19:28 +0200 Subject: bpf: introduce new bpf cpu map type BPF_MAP_TYPE_CPUMAP The 'cpumap' is primarily used as a backend map for XDP BPF helper call bpf_redirect_map() and XDP_REDIRECT action, like 'devmap'. This patch implement the main part of the map. It is not connected to the XDP redirect system yet, and no SKB allocation are done yet. The main concern in this patch is to ensure the datapath can run without any locking. This adds complexity to the setup and tear-down procedure, which assumptions are extra carefully documented in the code comments. V2: - make sure array isn't larger than NR_CPUS - make sure CPUs added is a valid possible CPU V3: fix nitpicks from Jakub Kicinski V5: - Restrict map allocation to root / CAP_SYS_ADMIN - WARN_ON_ONCE if queue is not empty on tear-down - Return -EPERM on memlock limit instead of -ENOMEM - Error code in __cpu_map_entry_alloc() also handle ptr_ring_cleanup() - Moved cpu_map_enqueue() to next patch V6: all notice by Daniel Borkmann - Fix err return code in cpu_map_alloc() introduced in V5 - Move cpu_possible() check after max_entries boundary check - Forbid usage initially in check_map_func_compatibility() V7: - Fix alloc error path spotted by Daniel Borkmann - Did stress test adding+removing CPUs from the map concurrently - Fixed refcnt issue on cpu_map_entry, kthread started too soon - Make sure packets are flushed during tear-down, involved use of rcu_barrier() and kthread_run only exit after queue is empty - Fix alloc error path in __cpu_map_entry_alloc() for ptr_ring V8: - Nitpicking comments and gramma by Edward Cree - Fix missing semi-colon introduced in V7 due to rebasing - Move struct bpf_cpu_map_entry members cpu+map_id to tracepoint patch Signed-off-by: Jesper Dangaard Brouer Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf_types.h | 1 + include/uapi/linux/bpf.h | 1 + kernel/bpf/Makefile | 1 + kernel/bpf/cpumap.c | 560 +++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 8 +- kernel/bpf/verifier.c | 5 + tools/include/uapi/linux/bpf.h | 1 + 7 files changed, 576 insertions(+), 1 deletion(-) create mode 100644 kernel/bpf/cpumap.c (limited to 'include/uapi/linux') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 6f1a567667b8..814c1081a4a9 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -41,4 +41,5 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) #ifdef CONFIG_STREAM_PARSER BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) #endif +BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops) #endif diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6db9e1d679cd..4303fb6c3817 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -112,6 +112,7 @@ enum bpf_map_type { BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_DEVMAP, BPF_MAP_TYPE_SOCKMAP, + BPF_MAP_TYPE_CPUMAP, }; enum bpf_prog_type { diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 53fb09f92e3f..e597daae6120 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -5,6 +5,7 @@ obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list obj-$(CONFIG_BPF_SYSCALL) += disasm.o ifeq ($(CONFIG_NET),y) obj-$(CONFIG_BPF_SYSCALL) += devmap.o +obj-$(CONFIG_BPF_SYSCALL) += cpumap.o ifeq ($(CONFIG_STREAM_PARSER),y) obj-$(CONFIG_BPF_SYSCALL) += sockmap.o endif diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c new file mode 100644 index 000000000000..e1e25ddba038 --- /dev/null +++ b/kernel/bpf/cpumap.c @@ -0,0 +1,560 @@ +/* bpf/cpumap.c + * + * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. + * Released under terms in GPL version 2. See COPYING. + */ + +/* The 'cpumap' is primarily used as a backend map for XDP BPF helper + * call bpf_redirect_map() and XDP_REDIRECT action, like 'devmap'. + * + * Unlike devmap which redirects XDP frames out another NIC device, + * this map type redirects raw XDP frames to another CPU. The remote + * CPU will do SKB-allocation and call the normal network stack. + * + * This is a scalability and isolation mechanism, that allow + * separating the early driver network XDP layer, from the rest of the + * netstack, and assigning dedicated CPUs for this stage. This + * basically allows for 10G wirespeed pre-filtering via bpf. + */ +#include +#include +#include + +#include +#include +#include +#include + +/* General idea: XDP packets getting XDP redirected to another CPU, + * will maximum be stored/queued for one driver ->poll() call. It is + * guaranteed that setting flush bit and flush operation happen on + * same CPU. Thus, cpu_map_flush operation can deduct via this_cpu_ptr() + * which queue in bpf_cpu_map_entry contains packets. + */ + +#define CPU_MAP_BULK_SIZE 8 /* 8 == one cacheline on 64-bit archs */ +struct xdp_bulk_queue { + void *q[CPU_MAP_BULK_SIZE]; + unsigned int count; +}; + +/* Struct for every remote "destination" CPU in map */ +struct bpf_cpu_map_entry { + u32 qsize; /* Queue size placeholder for map lookup */ + + /* XDP can run multiple RX-ring queues, need __percpu enqueue store */ + struct xdp_bulk_queue __percpu *bulkq; + + /* Queue with potential multi-producers, and single-consumer kthread */ + struct ptr_ring *queue; + struct task_struct *kthread; + struct work_struct kthread_stop_wq; + + atomic_t refcnt; /* Control when this struct can be free'ed */ + struct rcu_head rcu; +}; + +struct bpf_cpu_map { + struct bpf_map map; + /* Below members specific for map type */ + struct bpf_cpu_map_entry **cpu_map; + unsigned long __percpu *flush_needed; +}; + +static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, + struct xdp_bulk_queue *bq); + +static u64 cpu_map_bitmap_size(const union bpf_attr *attr) +{ + return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long); +} + +static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) +{ + struct bpf_cpu_map *cmap; + int err = -ENOMEM; + u64 cost; + int ret; + + if (!capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + + /* check sanity of attributes */ + if (attr->max_entries == 0 || attr->key_size != 4 || + attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) + return ERR_PTR(-EINVAL); + + cmap = kzalloc(sizeof(*cmap), GFP_USER); + if (!cmap) + return ERR_PTR(-ENOMEM); + + /* mandatory map attributes */ + cmap->map.map_type = attr->map_type; + cmap->map.key_size = attr->key_size; + cmap->map.value_size = attr->value_size; + cmap->map.max_entries = attr->max_entries; + cmap->map.map_flags = attr->map_flags; + cmap->map.numa_node = bpf_map_attr_numa_node(attr); + + /* Pre-limit array size based on NR_CPUS, not final CPU check */ + if (cmap->map.max_entries > NR_CPUS) { + err = -E2BIG; + goto free_cmap; + } + + /* make sure page count doesn't overflow */ + cost = (u64) cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *); + cost += cpu_map_bitmap_size(attr) * num_possible_cpus(); + if (cost >= U32_MAX - PAGE_SIZE) + goto free_cmap; + cmap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + /* Notice returns -EPERM on if map size is larger than memlock limit */ + ret = bpf_map_precharge_memlock(cmap->map.pages); + if (ret) { + err = ret; + goto free_cmap; + } + + /* A per cpu bitfield with a bit per possible CPU in map */ + cmap->flush_needed = __alloc_percpu(cpu_map_bitmap_size(attr), + __alignof__(unsigned long)); + if (!cmap->flush_needed) + goto free_cmap; + + /* Alloc array for possible remote "destination" CPUs */ + cmap->cpu_map = bpf_map_area_alloc(cmap->map.max_entries * + sizeof(struct bpf_cpu_map_entry *), + cmap->map.numa_node); + if (!cmap->cpu_map) + goto free_percpu; + + return &cmap->map; +free_percpu: + free_percpu(cmap->flush_needed); +free_cmap: + kfree(cmap); + return ERR_PTR(err); +} + +void __cpu_map_queue_destructor(void *ptr) +{ + /* The tear-down procedure should have made sure that queue is + * empty. See __cpu_map_entry_replace() and work-queue + * invoked cpu_map_kthread_stop(). Catch any broken behaviour + * gracefully and warn once. + */ + if (WARN_ON_ONCE(ptr)) + page_frag_free(ptr); +} + +static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) +{ + if (atomic_dec_and_test(&rcpu->refcnt)) { + /* The queue should be empty at this point */ + ptr_ring_cleanup(rcpu->queue, __cpu_map_queue_destructor); + kfree(rcpu->queue); + kfree(rcpu); + } +} + +static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) +{ + atomic_inc(&rcpu->refcnt); +} + +/* called from workqueue, to workaround syscall using preempt_disable */ +static void cpu_map_kthread_stop(struct work_struct *work) +{ + struct bpf_cpu_map_entry *rcpu; + + rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq); + + /* Wait for flush in __cpu_map_entry_free(), via full RCU barrier, + * as it waits until all in-flight call_rcu() callbacks complete. + */ + rcu_barrier(); + + /* kthread_stop will wake_up_process and wait for it to complete */ + kthread_stop(rcpu->kthread); +} + +static int cpu_map_kthread_run(void *data) +{ + struct bpf_cpu_map_entry *rcpu = data; + + set_current_state(TASK_INTERRUPTIBLE); + + /* When kthread gives stop order, then rcpu have been disconnected + * from map, thus no new packets can enter. Remaining in-flight + * per CPU stored packets are flushed to this queue. Wait honoring + * kthread_stop signal until queue is empty. + */ + while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) { + struct xdp_pkt *xdp_pkt; + + schedule(); + /* Do work */ + while ((xdp_pkt = ptr_ring_consume(rcpu->queue))) { + /* For now just "refcnt-free" */ + page_frag_free(xdp_pkt); + } + __set_current_state(TASK_INTERRUPTIBLE); + } + __set_current_state(TASK_RUNNING); + + put_cpu_map_entry(rcpu); + return 0; +} + +struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu, int map_id) +{ + gfp_t gfp = GFP_ATOMIC|__GFP_NOWARN; + struct bpf_cpu_map_entry *rcpu; + int numa, err; + + /* Have map->numa_node, but choose node of redirect target CPU */ + numa = cpu_to_node(cpu); + + rcpu = kzalloc_node(sizeof(*rcpu), gfp, numa); + if (!rcpu) + return NULL; + + /* Alloc percpu bulkq */ + rcpu->bulkq = __alloc_percpu_gfp(sizeof(*rcpu->bulkq), + sizeof(void *), gfp); + if (!rcpu->bulkq) + goto free_rcu; + + /* Alloc queue */ + rcpu->queue = kzalloc_node(sizeof(*rcpu->queue), gfp, numa); + if (!rcpu->queue) + goto free_bulkq; + + err = ptr_ring_init(rcpu->queue, qsize, gfp); + if (err) + goto free_queue; + + rcpu->qsize = qsize; + + /* Setup kthread */ + rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa, + "cpumap/%d/map:%d", cpu, map_id); + if (IS_ERR(rcpu->kthread)) + goto free_ptr_ring; + + get_cpu_map_entry(rcpu); /* 1-refcnt for being in cmap->cpu_map[] */ + get_cpu_map_entry(rcpu); /* 1-refcnt for kthread */ + + /* Make sure kthread runs on a single CPU */ + kthread_bind(rcpu->kthread, cpu); + wake_up_process(rcpu->kthread); + + return rcpu; + +free_ptr_ring: + ptr_ring_cleanup(rcpu->queue, NULL); +free_queue: + kfree(rcpu->queue); +free_bulkq: + free_percpu(rcpu->bulkq); +free_rcu: + kfree(rcpu); + return NULL; +} + +void __cpu_map_entry_free(struct rcu_head *rcu) +{ + struct bpf_cpu_map_entry *rcpu; + int cpu; + + /* This cpu_map_entry have been disconnected from map and one + * RCU graze-period have elapsed. Thus, XDP cannot queue any + * new packets and cannot change/set flush_needed that can + * find this entry. + */ + rcpu = container_of(rcu, struct bpf_cpu_map_entry, rcu); + + /* Flush remaining packets in percpu bulkq */ + for_each_online_cpu(cpu) { + struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu); + + /* No concurrent bq_enqueue can run at this point */ + bq_flush_to_queue(rcpu, bq); + } + free_percpu(rcpu->bulkq); + /* Cannot kthread_stop() here, last put free rcpu resources */ + put_cpu_map_entry(rcpu); +} + +/* After xchg pointer to bpf_cpu_map_entry, use the call_rcu() to + * ensure any driver rcu critical sections have completed, but this + * does not guarantee a flush has happened yet. Because driver side + * rcu_read_lock/unlock only protects the running XDP program. The + * atomic xchg and NULL-ptr check in __cpu_map_flush() makes sure a + * pending flush op doesn't fail. + * + * The bpf_cpu_map_entry is still used by the kthread, and there can + * still be pending packets (in queue and percpu bulkq). A refcnt + * makes sure to last user (kthread_stop vs. call_rcu) free memory + * resources. + * + * The rcu callback __cpu_map_entry_free flush remaining packets in + * percpu bulkq to queue. Due to caller map_delete_elem() disable + * preemption, cannot call kthread_stop() to make sure queue is empty. + * Instead a work_queue is started for stopping kthread, + * cpu_map_kthread_stop, which waits for an RCU graze period before + * stopping kthread, emptying the queue. + */ +void __cpu_map_entry_replace(struct bpf_cpu_map *cmap, + u32 key_cpu, struct bpf_cpu_map_entry *rcpu) +{ + struct bpf_cpu_map_entry *old_rcpu; + + old_rcpu = xchg(&cmap->cpu_map[key_cpu], rcpu); + if (old_rcpu) { + call_rcu(&old_rcpu->rcu, __cpu_map_entry_free); + INIT_WORK(&old_rcpu->kthread_stop_wq, cpu_map_kthread_stop); + schedule_work(&old_rcpu->kthread_stop_wq); + } +} + +int cpu_map_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + u32 key_cpu = *(u32 *)key; + + if (key_cpu >= map->max_entries) + return -EINVAL; + + /* notice caller map_delete_elem() use preempt_disable() */ + __cpu_map_entry_replace(cmap, key_cpu, NULL); + return 0; +} + +int cpu_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + struct bpf_cpu_map_entry *rcpu; + + /* Array index key correspond to CPU number */ + u32 key_cpu = *(u32 *)key; + /* Value is the queue size */ + u32 qsize = *(u32 *)value; + + if (unlikely(map_flags > BPF_EXIST)) + return -EINVAL; + if (unlikely(key_cpu >= cmap->map.max_entries)) + return -E2BIG; + if (unlikely(map_flags == BPF_NOEXIST)) + return -EEXIST; + if (unlikely(qsize > 16384)) /* sanity limit on qsize */ + return -EOVERFLOW; + + /* Make sure CPU is a valid possible cpu */ + if (!cpu_possible(key_cpu)) + return -ENODEV; + + if (qsize == 0) { + rcpu = NULL; /* Same as deleting */ + } else { + /* Updating qsize cause re-allocation of bpf_cpu_map_entry */ + rcpu = __cpu_map_entry_alloc(qsize, key_cpu, map->id); + if (!rcpu) + return -ENOMEM; + } + rcu_read_lock(); + __cpu_map_entry_replace(cmap, key_cpu, rcpu); + rcu_read_unlock(); + return 0; +} + +void cpu_map_free(struct bpf_map *map) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + int cpu; + u32 i; + + /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, + * so the bpf programs (can be more than one that used this map) were + * disconnected from events. Wait for outstanding critical sections in + * these programs to complete. The rcu critical section only guarantees + * no further "XDP/bpf-side" reads against bpf_cpu_map->cpu_map. + * It does __not__ ensure pending flush operations (if any) are + * complete. + */ + synchronize_rcu(); + + /* To ensure all pending flush operations have completed wait for flush + * bitmap to indicate all flush_needed bits to be zero on _all_ cpus. + * Because the above synchronize_rcu() ensures the map is disconnected + * from the program we can assume no new bits will be set. + */ + for_each_online_cpu(cpu) { + unsigned long *bitmap = per_cpu_ptr(cmap->flush_needed, cpu); + + while (!bitmap_empty(bitmap, cmap->map.max_entries)) + cond_resched(); + } + + /* For cpu_map the remote CPUs can still be using the entries + * (struct bpf_cpu_map_entry). + */ + for (i = 0; i < cmap->map.max_entries; i++) { + struct bpf_cpu_map_entry *rcpu; + + rcpu = READ_ONCE(cmap->cpu_map[i]); + if (!rcpu) + continue; + + /* bq flush and cleanup happens after RCU graze-period */ + __cpu_map_entry_replace(cmap, i, NULL); /* call_rcu */ + } + free_percpu(cmap->flush_needed); + bpf_map_area_free(cmap->cpu_map); + kfree(cmap); +} + +struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + struct bpf_cpu_map_entry *rcpu; + + if (key >= map->max_entries) + return NULL; + + rcpu = READ_ONCE(cmap->cpu_map[key]); + return rcpu; +} + +static void *cpu_map_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_cpu_map_entry *rcpu = + __cpu_map_lookup_elem(map, *(u32 *)key); + + return rcpu ? &rcpu->qsize : NULL; +} + +static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + u32 index = key ? *(u32 *)key : U32_MAX; + u32 *next = next_key; + + if (index >= cmap->map.max_entries) { + *next = 0; + return 0; + } + + if (index == cmap->map.max_entries - 1) + return -ENOENT; + *next = index + 1; + return 0; +} + +const struct bpf_map_ops cpu_map_ops = { + .map_alloc = cpu_map_alloc, + .map_free = cpu_map_free, + .map_delete_elem = cpu_map_delete_elem, + .map_update_elem = cpu_map_update_elem, + .map_lookup_elem = cpu_map_lookup_elem, + .map_get_next_key = cpu_map_get_next_key, +}; + +static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, + struct xdp_bulk_queue *bq) +{ + struct ptr_ring *q; + int i; + + if (unlikely(!bq->count)) + return 0; + + q = rcpu->queue; + spin_lock(&q->producer_lock); + + for (i = 0; i < bq->count; i++) { + void *xdp_pkt = bq->q[i]; + int err; + + err = __ptr_ring_produce(q, xdp_pkt); + if (err) { + /* Free xdp_pkt */ + page_frag_free(xdp_pkt); + } + } + bq->count = 0; + spin_unlock(&q->producer_lock); + + return 0; +} + +/* Notice: Will change in later patch */ +struct xdp_pkt { + void *data; + u16 len; + u16 headroom; +}; + +/* Runs under RCU-read-side, plus in softirq under NAPI protection. + * Thus, safe percpu variable access. + */ +int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_pkt *xdp_pkt) +{ + struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq); + + if (unlikely(bq->count == CPU_MAP_BULK_SIZE)) + bq_flush_to_queue(rcpu, bq); + + /* Notice, xdp_buff/page MUST be queued here, long enough for + * driver to code invoking us to finished, due to driver + * (e.g. ixgbe) recycle tricks based on page-refcnt. + * + * Thus, incoming xdp_pkt is always queued here (else we race + * with another CPU on page-refcnt and remaining driver code). + * Queue time is very short, as driver will invoke flush + * operation, when completing napi->poll call. + */ + bq->q[bq->count++] = xdp_pkt; + return 0; +} + +void __cpu_map_insert_ctx(struct bpf_map *map, u32 bit) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + unsigned long *bitmap = this_cpu_ptr(cmap->flush_needed); + + __set_bit(bit, bitmap); +} + +void __cpu_map_flush(struct bpf_map *map) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + unsigned long *bitmap = this_cpu_ptr(cmap->flush_needed); + u32 bit; + + /* The napi->poll softirq makes sure __cpu_map_insert_ctx() + * and __cpu_map_flush() happen on same CPU. Thus, the percpu + * bitmap indicate which percpu bulkq have packets. + */ + for_each_set_bit(bit, bitmap, map->max_entries) { + struct bpf_cpu_map_entry *rcpu = READ_ONCE(cmap->cpu_map[bit]); + struct xdp_bulk_queue *bq; + + /* This is possible if entry is removed by user space + * between xdp redirect and flush op. + */ + if (unlikely(!rcpu)) + continue; + + __clear_bit(bit, bitmap); + + /* Flush all frames in bulkq to real queue */ + bq = this_cpu_ptr(rcpu->bulkq); + bq_flush_to_queue(rcpu, bq); + + /* If already running, costs spin_lock_irqsave + smb_mb */ + wake_up_process(rcpu->kthread); + } +} diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index d124e702e040..54fba06942f5 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -592,6 +592,12 @@ static int map_update_elem(union bpf_attr *attr) if (copy_from_user(value, uvalue, value_size) != 0) goto free_value; + /* Need to create a kthread, thus must support schedule */ + if (map->map_type == BPF_MAP_TYPE_CPUMAP) { + err = map->ops->map_update_elem(map, key, value, attr->flags); + goto out; + } + /* must increment bpf_prog_active to avoid kprobe+bpf triggering from * inside bpf map update or delete otherwise deadlocks are possible */ @@ -622,7 +628,7 @@ static int map_update_elem(union bpf_attr *attr) } __this_cpu_dec(bpf_prog_active); preempt_enable(); - +out: if (!err) trace_bpf_map_update_elem(map, ufd, key, value); free_value: diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9755279d94cb..cefa64be9a2f 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1444,6 +1444,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (func_id != BPF_FUNC_redirect_map) goto error; break; + /* Restrict bpf side of cpumap, open when use-cases appear */ + case BPF_MAP_TYPE_CPUMAP: + if (func_id != BPF_FUNC_redirect_map) + goto error; + break; case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH_OF_MAPS: if (func_id != BPF_FUNC_map_lookup_elem) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index fb4fb81ce5b0..fa93033dc521 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -112,6 +112,7 @@ enum bpf_map_type { BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_DEVMAP, BPF_MAP_TYPE_SOCKMAP, + BPF_MAP_TYPE_CPUMAP, }; enum bpf_prog_type { -- cgit v1.2.3-71-gd317 From 085b30625e39df67d7320f22269796276c6b0c11 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 23 Sep 2016 14:05:12 +0100 Subject: perf/core: Add PERF_AUX_FLAG_COLLISION to report colliding samples The ARM SPE architecture permits an implementation to ignore a sample if the sample is due to be taken whilst another sample is already being produced. In this case, it is desirable to report the collision to userspace, as they may want to lower the sample period. This patch adds a PERF_AUX_FLAG_COLLISION flag, so that such events can be relayed to userspace. Acked-by: Peter Zijlstra Signed-off-by: Will Deacon --- include/uapi/linux/perf_event.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 140ae638cfd6..7ca1b22ea417 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -941,6 +941,7 @@ enum perf_callchain_context { #define PERF_AUX_FLAG_TRUNCATED 0x01 /* record was truncated to fit */ #define PERF_AUX_FLAG_OVERWRITE 0x02 /* snapshot from overwrite mode */ #define PERF_AUX_FLAG_PARTIAL 0x04 /* record contains gaps */ +#define PERF_AUX_FLAG_COLLISION 0x08 /* sample collided with another */ #define PERF_FLAG_FD_NO_GROUP (1UL << 0) #define PERF_FLAG_FD_OUTPUT (1UL << 1) -- cgit v1.2.3-71-gd317 From 7c950b9e53732f574e3a46d37c62f1f33d0b218c Mon Sep 17 00:00:00 2001 From: Dongdong Liu Date: Wed, 11 Oct 2017 18:52:58 +0800 Subject: PCI/portdrv: Add #defines for AER and DPC Interrupt Message Number masks In the AER case, the mask isn't strictly necessary because there are no higher-order bits above the Interrupt Message Number, but using a #define will make it possible to grep for it. Suggested-by: Bjorn Helgaas Signed-off-by: Dongdong Liu Signed-off-by: Bjorn Helgaas Reviewed-by: Christoph Hellwig --- drivers/pci/pcie/portdrv_core.c | 4 ++-- include/uapi/linux/pci_regs.h | 2 ++ 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c index 313a21df1692..72fcbe5567dd 100644 --- a/drivers/pci/pcie/portdrv_core.c +++ b/drivers/pci/pcie/portdrv_core.c @@ -114,7 +114,7 @@ static int pcie_port_enable_irq_vec(struct pci_dev *dev, int *irqs, int mask) */ pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); pci_read_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, ®32); - entry = reg32 >> 27; + entry = (reg32 & PCI_ERR_ROOT_AER_IRQ) >> 27; if (entry >= nr_entries) goto out_free_irqs; @@ -141,7 +141,7 @@ static int pcie_port_enable_irq_vec(struct pci_dev *dev, int *irqs, int mask) */ pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_DPC); pci_read_config_word(dev, pos + PCI_EXP_DPC_CAP, ®16); - entry = reg16 & 0x1f; + entry = reg16 & PCI_EXP_DPC_IRQ; if (entry >= nr_entries) goto out_free_irqs; diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index f8d58045926f..f7c09a4c494a 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -746,6 +746,7 @@ #define PCI_ERR_ROOT_FIRST_FATAL 0x00000010 /* First UNC is Fatal */ #define PCI_ERR_ROOT_NONFATAL_RCV 0x00000020 /* Non-Fatal Received */ #define PCI_ERR_ROOT_FATAL_RCV 0x00000040 /* Fatal Received */ +#define PCI_ERR_ROOT_AER_IRQ 0xf8000000 /* Advanced Error Interrupt Message Number */ #define PCI_ERR_ROOT_ERR_SRC 52 /* Error Source Identification */ /* Virtual Channel */ @@ -960,6 +961,7 @@ /* Downstream Port Containment */ #define PCI_EXP_DPC_CAP 4 /* DPC Capability */ +#define PCI_EXP_DPC_IRQ 0x1f /* DPC Interrupt Message Number */ #define PCI_EXP_DPC_CAP_RP_EXT 0x20 /* Root Port Extensions for DPC */ #define PCI_EXP_DPC_CAP_POISONED_TLP 0x40 /* Poisoned TLP Egress Blocking Supported */ #define PCI_EXP_DPC_CAP_SW_TRIGGER 0x80 /* Software Triggering Supported */ -- cgit v1.2.3-71-gd317 From a961e40917fb14614d368d8bc9782ca4d6a8cd11 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Thu, 19 Oct 2017 13:30:15 -0400 Subject: membarrier: Provide register expedited private command This introduces a "register private expedited" membarrier command which allows eventual removal of important memory barrier constraints on the scheduler fast-paths. It changes how the "private expedited" membarrier command (new to 4.14) is used from user-space. This new command allows processes to register their intent to use the private expedited command. This affects how the expedited private command introduced in 4.14-rc is meant to be used, and should be merged before 4.14 final. Processes are now required to register before using MEMBARRIER_CMD_PRIVATE_EXPEDITED, otherwise that command returns EPERM. This fixes a problem that arose when designing requested extensions to sys_membarrier() to allow JITs to efficiently flush old code from instruction caches. Several potential algorithms are much less painful if the user register intent to use this functionality early on, for example, before the process spawns the second thread. Registering at this time removes the need to interrupt each and every thread in that process at the first expedited sys_membarrier() system call. Signed-off-by: Mathieu Desnoyers Acked-by: Paul E. McKenney Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Alexander Viro Signed-off-by: Linus Torvalds --- fs/exec.c | 1 + include/linux/mm_types.h | 3 +++ include/linux/sched/mm.h | 16 ++++++++++++++++ include/uapi/linux/membarrier.h | 23 ++++++++++++++++------- kernel/sched/membarrier.c | 34 ++++++++++++++++++++++++++++++---- 5 files changed, 66 insertions(+), 11 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/exec.c b/fs/exec.c index 5470d3c1892a..3e14ba25f678 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1802,6 +1802,7 @@ static int do_execveat_common(int fd, struct filename *filename, /* execve succeeded */ current->fs->in_exec = 0; current->in_execve = 0; + membarrier_execve(current); acct_update_integrals(current); task_numa_free(current); free_bprm(bprm); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 46f4ecf5479a..1861ea8dba77 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -445,6 +445,9 @@ struct mm_struct { unsigned long flags; /* Must use atomic bitops to access the bits */ struct core_state *core_state; /* coredumping support */ +#ifdef CONFIG_MEMBARRIER + atomic_t membarrier_state; +#endif #ifdef CONFIG_AIO spinlock_t ioctx_lock; struct kioctx_table __rcu *ioctx_table; diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index ae53e413fb13..ab9bf7b73954 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -211,4 +211,20 @@ static inline void memalloc_noreclaim_restore(unsigned int flags) current->flags = (current->flags & ~PF_MEMALLOC) | flags; } +#ifdef CONFIG_MEMBARRIER +enum { + MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY = (1U << 0), + MEMBARRIER_STATE_SWITCH_MM = (1U << 1), +}; + +static inline void membarrier_execve(struct task_struct *t) +{ + atomic_set(&t->mm->membarrier_state, 0); +} +#else +static inline void membarrier_execve(struct task_struct *t) +{ +} +#endif + #endif /* _LINUX_SCHED_MM_H */ diff --git a/include/uapi/linux/membarrier.h b/include/uapi/linux/membarrier.h index 6d47b3249d8a..4e01ad7ffe98 100644 --- a/include/uapi/linux/membarrier.h +++ b/include/uapi/linux/membarrier.h @@ -52,21 +52,30 @@ * (non-running threads are de facto in such a * state). This only covers threads from the * same processes as the caller thread. This - * command returns 0. The "expedited" commands - * complete faster than the non-expedited ones, - * they never block, but have the downside of - * causing extra overhead. + * command returns 0 on success. The + * "expedited" commands complete faster than + * the non-expedited ones, they never block, + * but have the downside of causing extra + * overhead. A process needs to register its + * intent to use the private expedited command + * prior to using it, otherwise this command + * returns -EPERM. + * @MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED: + * Register the process intent to use + * MEMBARRIER_CMD_PRIVATE_EXPEDITED. Always + * returns 0. * * Command to be passed to the membarrier system call. The commands need to * be a single bit each, except for MEMBARRIER_CMD_QUERY which is assigned to * the value 0. */ enum membarrier_cmd { - MEMBARRIER_CMD_QUERY = 0, - MEMBARRIER_CMD_SHARED = (1 << 0), + MEMBARRIER_CMD_QUERY = 0, + MEMBARRIER_CMD_SHARED = (1 << 0), /* reserved for MEMBARRIER_CMD_SHARED_EXPEDITED (1 << 1) */ /* reserved for MEMBARRIER_CMD_PRIVATE (1 << 2) */ - MEMBARRIER_CMD_PRIVATE_EXPEDITED = (1 << 3), + MEMBARRIER_CMD_PRIVATE_EXPEDITED = (1 << 3), + MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED = (1 << 4), }; #endif /* _UAPI_LINUX_MEMBARRIER_H */ diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index a92fddc22747..dd7908743dab 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -18,6 +18,7 @@ #include #include #include +#include #include "sched.h" /* for cpu_rq(). */ @@ -26,21 +27,26 @@ * except MEMBARRIER_CMD_QUERY. */ #define MEMBARRIER_CMD_BITMASK \ - (MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED) + (MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED \ + | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED) static void ipi_mb(void *info) { smp_mb(); /* IPIs should be serializing but paranoid. */ } -static void membarrier_private_expedited(void) +static int membarrier_private_expedited(void) { int cpu; bool fallback = false; cpumask_var_t tmpmask; + if (!(atomic_read(¤t->mm->membarrier_state) + & MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY)) + return -EPERM; + if (num_online_cpus() == 1) - return; + return 0; /* * Matches memory barriers around rq->curr modification in @@ -94,6 +100,24 @@ static void membarrier_private_expedited(void) * rq->curr modification in scheduler. */ smp_mb(); /* exit from system call is not a mb */ + return 0; +} + +static void membarrier_register_private_expedited(void) +{ + struct task_struct *p = current; + struct mm_struct *mm = p->mm; + + /* + * We need to consider threads belonging to different thread + * groups, which use the same mm. (CLONE_VM but not + * CLONE_THREAD). + */ + if (atomic_read(&mm->membarrier_state) + & MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY) + return; + atomic_or(MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY, + &mm->membarrier_state); } /** @@ -144,7 +168,9 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags) synchronize_sched(); return 0; case MEMBARRIER_CMD_PRIVATE_EXPEDITED: - membarrier_private_expedited(); + return membarrier_private_expedited(); + case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED: + membarrier_register_private_expedited(); return 0; default: return -EINVAL; -- cgit v1.2.3-71-gd317 From 1fba70e5b6bed53496ba1f1f16127f5be01b5fb6 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 18 Oct 2017 11:22:51 -0700 Subject: tcp: socket option to set TCP fast open key New socket option TCP_FASTOPEN_KEY to allow different keys per listener. The listener by default uses the global key until the socket option is set. The key is a 16 bytes long binary data. This option has no effect on regular non-listener TCP sockets. Signed-off-by: Yuchung Cheng Reviewed-by: Eric Dumazet Reviewed-by: Christoph Paasch Signed-off-by: David S. Miller --- include/net/request_sock.h | 2 ++ include/net/tcp.h | 5 +++-- include/uapi/linux/tcp.h | 1 + net/ipv4/sysctl_net_ipv4.c | 3 ++- net/ipv4/tcp.c | 33 +++++++++++++++++++++++++++ net/ipv4/tcp_fastopen.c | 56 +++++++++++++++++++++++++++++++++------------- net/ipv4/tcp_ipv4.c | 1 + 7 files changed, 82 insertions(+), 19 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 23e22054aa60..347015515a7d 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -150,6 +150,8 @@ struct fastopen_queue { spinlock_t lock; int qlen; /* # of pending (TCP_SYN_RECV) reqs */ int max_qlen; /* != 0 iff TFO is currently enabled */ + + struct tcp_fastopen_context __rcu *ctx; /* cipher context for cookie */ }; /** struct request_sock_queue - queue of request_socks diff --git a/include/net/tcp.h b/include/net/tcp.h index 3b3b9b968e2d..1efe8365cb28 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1555,9 +1555,10 @@ struct tcp_fastopen_request { int copied; /* queued in tcp_connect() */ }; void tcp_free_fastopen_req(struct tcp_sock *tp); - +void tcp_fastopen_destroy_cipher(struct sock *sk); void tcp_fastopen_ctx_destroy(struct net *net); -int tcp_fastopen_reset_cipher(struct net *net, void *key, unsigned int len); +int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk, + void *key, unsigned int len); void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb); struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 15c25eccab2b..69c7493e42f8 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -119,6 +119,7 @@ enum { #define TCP_FASTOPEN_CONNECT 30 /* Attempt FastOpen with connect */ #define TCP_ULP 31 /* Attach a ULP to a TCP connection */ #define TCP_MD5SIG_EXT 32 /* TCP MD5 Signature with extensions */ +#define TCP_FASTOPEN_KEY 33 /* Set the key for Fast Open (cookie) */ struct tcp_repair_opt { __u32 opt_code; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index cac8dd309f39..81d218346cf7 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -284,7 +284,8 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write, ret = -EINVAL; goto bad_key; } - tcp_fastopen_reset_cipher(net, user_key, TCP_FASTOPEN_KEY_LENGTH); + tcp_fastopen_reset_cipher(net, NULL, user_key, + TCP_FASTOPEN_KEY_LENGTH); } bad_key: diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3b34850d361f..8b1fa4dd4538 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2571,6 +2571,17 @@ static int do_tcp_setsockopt(struct sock *sk, int level, release_sock(sk); return err; } + case TCP_FASTOPEN_KEY: { + __u8 key[TCP_FASTOPEN_KEY_LENGTH]; + + if (optlen != sizeof(key)) + return -EINVAL; + + if (copy_from_user(key, optval, optlen)) + return -EFAULT; + + return tcp_fastopen_reset_cipher(net, sk, key, sizeof(key)); + } default: /* fallthru */ break; @@ -3157,6 +3168,28 @@ static int do_tcp_getsockopt(struct sock *sk, int level, return -EFAULT; return 0; + case TCP_FASTOPEN_KEY: { + __u8 key[TCP_FASTOPEN_KEY_LENGTH]; + struct tcp_fastopen_context *ctx; + + if (get_user(len, optlen)) + return -EFAULT; + + rcu_read_lock(); + ctx = rcu_dereference(icsk->icsk_accept_queue.fastopenq.ctx); + if (ctx) + memcpy(key, ctx->key, sizeof(key)); + else + len = 0; + rcu_read_unlock(); + + len = min_t(unsigned int, len, sizeof(key)); + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, key, len)) + return -EFAULT; + return 0; + } case TCP_THIN_LINEAR_TIMEOUTS: val = tp->thin_lto; break; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 7ee4aadcdd71..21075ce19cb6 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -29,7 +29,7 @@ void tcp_fastopen_init_key_once(struct net *net) * for a valid cookie, so this is an acceptable risk. */ get_random_bytes(key, sizeof(key)); - tcp_fastopen_reset_cipher(net, key, sizeof(key)); + tcp_fastopen_reset_cipher(net, NULL, key, sizeof(key)); } static void tcp_fastopen_ctx_free(struct rcu_head *head) @@ -40,6 +40,16 @@ static void tcp_fastopen_ctx_free(struct rcu_head *head) kfree(ctx); } +void tcp_fastopen_destroy_cipher(struct sock *sk) +{ + struct tcp_fastopen_context *ctx; + + ctx = rcu_dereference_protected( + inet_csk(sk)->icsk_accept_queue.fastopenq.ctx, 1); + if (ctx) + call_rcu(&ctx->rcu, tcp_fastopen_ctx_free); +} + void tcp_fastopen_ctx_destroy(struct net *net) { struct tcp_fastopen_context *ctxt; @@ -55,10 +65,12 @@ void tcp_fastopen_ctx_destroy(struct net *net) call_rcu(&ctxt->rcu, tcp_fastopen_ctx_free); } -int tcp_fastopen_reset_cipher(struct net *net, void *key, unsigned int len) +int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk, + void *key, unsigned int len) { - int err; struct tcp_fastopen_context *ctx, *octx; + struct fastopen_queue *q; + int err; ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) @@ -79,27 +91,39 @@ error: kfree(ctx); } memcpy(ctx->key, key, len); - spin_lock(&net->ipv4.tcp_fastopen_ctx_lock); - octx = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx, - lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock)); - rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, ctx); - spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock); + if (sk) { + q = &inet_csk(sk)->icsk_accept_queue.fastopenq; + spin_lock_bh(&q->lock); + octx = rcu_dereference_protected(q->ctx, + lockdep_is_held(&q->lock)); + rcu_assign_pointer(q->ctx, ctx); + spin_unlock_bh(&q->lock); + } else { + spin_lock(&net->ipv4.tcp_fastopen_ctx_lock); + octx = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx, + lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock)); + rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, ctx); + spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock); + } if (octx) call_rcu(&octx->rcu, tcp_fastopen_ctx_free); return err; } -static bool __tcp_fastopen_cookie_gen(struct net *net, - const void *path, +static bool __tcp_fastopen_cookie_gen(struct sock *sk, const void *path, struct tcp_fastopen_cookie *foc) { struct tcp_fastopen_context *ctx; bool ok = false; rcu_read_lock(); - ctx = rcu_dereference(net->ipv4.tcp_fastopen_ctx); + + ctx = rcu_dereference(inet_csk(sk)->icsk_accept_queue.fastopenq.ctx); + if (!ctx) + ctx = rcu_dereference(sock_net(sk)->ipv4.tcp_fastopen_ctx); + if (ctx) { crypto_cipher_encrypt_one(ctx->tfm, foc->val, path); foc->len = TCP_FASTOPEN_COOKIE_SIZE; @@ -115,7 +139,7 @@ static bool __tcp_fastopen_cookie_gen(struct net *net, * * XXX (TFO) - refactor when TCP_FASTOPEN_COOKIE_SIZE != AES_BLOCK_SIZE. */ -static bool tcp_fastopen_cookie_gen(struct net *net, +static bool tcp_fastopen_cookie_gen(struct sock *sk, struct request_sock *req, struct sk_buff *syn, struct tcp_fastopen_cookie *foc) @@ -124,7 +148,7 @@ static bool tcp_fastopen_cookie_gen(struct net *net, const struct iphdr *iph = ip_hdr(syn); __be32 path[4] = { iph->saddr, iph->daddr, 0, 0 }; - return __tcp_fastopen_cookie_gen(net, path, foc); + return __tcp_fastopen_cookie_gen(sk, path, foc); } #if IS_ENABLED(CONFIG_IPV6) @@ -132,13 +156,13 @@ static bool tcp_fastopen_cookie_gen(struct net *net, const struct ipv6hdr *ip6h = ipv6_hdr(syn); struct tcp_fastopen_cookie tmp; - if (__tcp_fastopen_cookie_gen(net, &ip6h->saddr, &tmp)) { + if (__tcp_fastopen_cookie_gen(sk, &ip6h->saddr, &tmp)) { struct in6_addr *buf = &tmp.addr; int i; for (i = 0; i < 4; i++) buf->s6_addr32[i] ^= ip6h->daddr.s6_addr32[i]; - return __tcp_fastopen_cookie_gen(net, buf, foc); + return __tcp_fastopen_cookie_gen(sk, buf, foc); } } #endif @@ -313,7 +337,7 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, goto fastopen; if (foc->len >= 0 && /* Client presents or requests a cookie */ - tcp_fastopen_cookie_gen(sock_net(sk), req, skb, &valid_foc) && + tcp_fastopen_cookie_gen(sk, req, skb, &valid_foc) && foc->len == TCP_FASTOPEN_COOKIE_SIZE && foc->len == valid_foc.len && !memcmp(foc->val, valid_foc.val, foc->len)) { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ecee4ddb24c5..28ca4e177047 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1893,6 +1893,7 @@ void tcp_v4_destroy_sock(struct sock *sk) /* If socket is aborted during connect operation */ tcp_free_fastopen_req(tp); + tcp_fastopen_destroy_cipher(sk); tcp_saved_syn_free(tp); sk_sockets_allocated_dec(sk); -- cgit v1.2.3-71-gd317 From 6e71b04a82248ccf13a94b85cbc674a9fefe53f5 Mon Sep 17 00:00:00 2001 From: Chenbo Feng Date: Wed, 18 Oct 2017 13:00:22 -0700 Subject: bpf: Add file mode configuration into bpf maps Introduce the map read/write flags to the eBPF syscalls that returns the map fd. The flags is used to set up the file mode when construct a new file descriptor for bpf maps. To not break the backward capability, the f_flags is set to O_RDWR if the flag passed by syscall is 0. Otherwise it should be O_RDONLY or O_WRONLY. When the userspace want to modify or read the map content, it will check the file mode to see if it is allowed to make the change. Signed-off-by: Chenbo Feng Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf.h | 8 +++-- include/uapi/linux/bpf.h | 6 ++++ kernel/bpf/arraymap.c | 6 +++- kernel/bpf/devmap.c | 5 ++- kernel/bpf/hashtab.c | 5 +-- kernel/bpf/inode.c | 15 ++++++--- kernel/bpf/lpm_trie.c | 3 +- kernel/bpf/sockmap.c | 5 ++- kernel/bpf/stackmap.c | 5 ++- kernel/bpf/syscall.c | 88 ++++++++++++++++++++++++++++++++++++++++++------ net/netfilter/xt_bpf.c | 2 +- 11 files changed, 122 insertions(+), 26 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d67ccdc0099f..3e5508f2fa87 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -315,11 +315,11 @@ void bpf_map_area_free(void *base); extern int sysctl_unprivileged_bpf_disabled; -int bpf_map_new_fd(struct bpf_map *map); +int bpf_map_new_fd(struct bpf_map *map, int flags); int bpf_prog_new_fd(struct bpf_prog *prog); int bpf_obj_pin_user(u32 ufd, const char __user *pathname); -int bpf_obj_get_user(const char __user *pathname); +int bpf_obj_get_user(const char __user *pathname, int flags); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); @@ -338,6 +338,8 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags); int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); +int bpf_get_file_flag(int flags); + /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and * forced to use 'long' read/writes to try to atomically copy long counters. * Best-effort only. No barriers here, since it _will_ race with concurrent @@ -421,7 +423,7 @@ static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages) { } -static inline int bpf_obj_get_user(const char __user *pathname) +static inline int bpf_obj_get_user(const char __user *pathname, int flags) { return -EOPNOTSUPP; } diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4303fb6c3817..d83f95ea6a1b 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -218,6 +218,10 @@ enum bpf_attach_type { #define BPF_OBJ_NAME_LEN 16U +/* Flags for accessing BPF object */ +#define BPF_F_RDONLY (1U << 3) +#define BPF_F_WRONLY (1U << 4) + union bpf_attr { struct { /* anonymous struct used by BPF_MAP_CREATE command */ __u32 map_type; /* one of enum bpf_map_type */ @@ -260,6 +264,7 @@ union bpf_attr { struct { /* anonymous struct used by BPF_OBJ_* commands */ __aligned_u64 pathname; __u32 bpf_fd; + __u32 file_flags; }; struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ @@ -287,6 +292,7 @@ union bpf_attr { __u32 map_id; }; __u32 next_id; + __u32 open_flags; }; struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */ diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 68d866628be0..988c04c91e10 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -19,6 +19,9 @@ #include "map_in_map.h" +#define ARRAY_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + static void bpf_array_free_percpu(struct bpf_array *array) { int i; @@ -56,7 +59,8 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size == 0 || attr->map_flags & ~BPF_F_NUMA_NODE || + attr->value_size == 0 || + attr->map_flags & ~ARRAY_CREATE_FLAG_MASK || (percpu && numa_node != NUMA_NO_NODE)) return ERR_PTR(-EINVAL); diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index e093d9a2c4dd..e5d3de7cff2e 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -50,6 +50,9 @@ #include #include +#define DEV_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + struct bpf_dtab_netdev { struct net_device *dev; struct bpf_dtab *dtab; @@ -80,7 +83,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) + attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); dtab = kzalloc(sizeof(*dtab), GFP_USER); diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 431126f31ea3..919955236e63 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -18,8 +18,9 @@ #include "bpf_lru_list.h" #include "map_in_map.h" -#define HTAB_CREATE_FLAG_MASK \ - (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE) +#define HTAB_CREATE_FLAG_MASK \ + (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \ + BPF_F_RDONLY | BPF_F_WRONLY) struct bucket { struct hlist_nulls_head head; diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index be1dde967208..01aaef1a77c5 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -295,7 +295,7 @@ out: } static void *bpf_obj_do_get(const struct filename *pathname, - enum bpf_type *type) + enum bpf_type *type, int flags) { struct inode *inode; struct path path; @@ -307,7 +307,7 @@ static void *bpf_obj_do_get(const struct filename *pathname, return ERR_PTR(ret); inode = d_backing_inode(path.dentry); - ret = inode_permission(inode, MAY_WRITE); + ret = inode_permission(inode, ACC_MODE(flags)); if (ret) goto out; @@ -326,18 +326,23 @@ out: return ERR_PTR(ret); } -int bpf_obj_get_user(const char __user *pathname) +int bpf_obj_get_user(const char __user *pathname, int flags) { enum bpf_type type = BPF_TYPE_UNSPEC; struct filename *pname; int ret = -ENOENT; + int f_flags; void *raw; + f_flags = bpf_get_file_flag(flags); + if (f_flags < 0) + return f_flags; + pname = getname(pathname); if (IS_ERR(pname)) return PTR_ERR(pname); - raw = bpf_obj_do_get(pname, &type); + raw = bpf_obj_do_get(pname, &type, f_flags); if (IS_ERR(raw)) { ret = PTR_ERR(raw); goto out; @@ -346,7 +351,7 @@ int bpf_obj_get_user(const char __user *pathname) if (type == BPF_TYPE_PROG) ret = bpf_prog_new_fd(raw); else if (type == BPF_TYPE_MAP) - ret = bpf_map_new_fd(raw); + ret = bpf_map_new_fd(raw, f_flags); else goto out; diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 34d8a690ea05..885e45479680 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -495,7 +495,8 @@ out: #define LPM_KEY_SIZE_MAX LPM_KEY_SIZE(LPM_DATA_SIZE_MAX) #define LPM_KEY_SIZE_MIN LPM_KEY_SIZE(LPM_DATA_SIZE_MIN) -#define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE) +#define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE | \ + BPF_F_RDONLY | BPF_F_WRONLY) static struct bpf_map *trie_alloc(union bpf_attr *attr) { diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index a298d6666698..86ec846f2d5e 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -40,6 +40,9 @@ #include #include +#define SOCK_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + struct bpf_stab { struct bpf_map map; struct sock **sock_map; @@ -489,7 +492,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) + attr->value_size != 4 || attr->map_flags & ~SOCK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); if (attr->value_size > KMALLOC_MAX_SIZE) diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 135be433e9a0..a15bc636cc98 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -11,6 +11,9 @@ #include #include "percpu_freelist.h" +#define STACK_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + struct stack_map_bucket { struct pcpu_freelist_node fnode; u32 hash; @@ -60,7 +63,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) if (!capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); - if (attr->map_flags & ~BPF_F_NUMA_NODE) + if (attr->map_flags & ~STACK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); /* check sanity of attributes */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0e893cac6795..676a06e6b322 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -34,6 +34,8 @@ #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 BPF_OBJ_FLAG_MASK (BPF_F_RDONLY | BPF_F_WRONLY) + DEFINE_PER_CPU(int, bpf_prog_active); static DEFINE_IDR(prog_idr); static DEFINE_SPINLOCK(prog_idr_lock); @@ -294,17 +296,48 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) } #endif +static ssize_t bpf_dummy_read(struct file *filp, char __user *buf, size_t siz, + loff_t *ppos) +{ + /* We need this handler such that alloc_file() enables + * f_mode with FMODE_CAN_READ. + */ + return -EINVAL; +} + +static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf, + size_t siz, loff_t *ppos) +{ + /* We need this handler such that alloc_file() enables + * f_mode with FMODE_CAN_WRITE. + */ + return -EINVAL; +} + static const struct file_operations bpf_map_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_map_show_fdinfo, #endif .release = bpf_map_release, + .read = bpf_dummy_read, + .write = bpf_dummy_write, }; -int bpf_map_new_fd(struct bpf_map *map) +int bpf_map_new_fd(struct bpf_map *map, int flags) { return anon_inode_getfd("bpf-map", &bpf_map_fops, map, - O_RDWR | O_CLOEXEC); + flags | O_CLOEXEC); +} + +int bpf_get_file_flag(int flags) +{ + if ((flags & BPF_F_RDONLY) && (flags & BPF_F_WRONLY)) + return -EINVAL; + if (flags & BPF_F_RDONLY) + return O_RDONLY; + if (flags & BPF_F_WRONLY) + return O_WRONLY; + return O_RDWR; } /* helper macro to check that unused fields 'union bpf_attr' are zero */ @@ -344,12 +377,17 @@ static int map_create(union bpf_attr *attr) { int numa_node = bpf_map_attr_numa_node(attr); struct bpf_map *map; + int f_flags; int err; err = CHECK_ATTR(BPF_MAP_CREATE); if (err) return -EINVAL; + f_flags = bpf_get_file_flag(attr->map_flags); + if (f_flags < 0) + return f_flags; + if (numa_node != NUMA_NO_NODE && ((unsigned int)numa_node >= nr_node_ids || !node_online(numa_node))) @@ -375,7 +413,7 @@ static int map_create(union bpf_attr *attr) if (err) goto free_map; - err = bpf_map_new_fd(map); + err = bpf_map_new_fd(map, f_flags); if (err < 0) { /* failed to allocate fd. * bpf_map_put() is needed because the above @@ -490,6 +528,11 @@ static int map_lookup_elem(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + if (!(f.file->f_mode & FMODE_CAN_READ)) { + err = -EPERM; + goto err_put; + } + key = memdup_user(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); @@ -570,6 +613,11 @@ static int map_update_elem(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + if (!(f.file->f_mode & FMODE_CAN_WRITE)) { + err = -EPERM; + goto err_put; + } + key = memdup_user(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); @@ -659,6 +707,11 @@ static int map_delete_elem(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + if (!(f.file->f_mode & FMODE_CAN_WRITE)) { + err = -EPERM; + goto err_put; + } + key = memdup_user(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); @@ -702,6 +755,11 @@ static int map_get_next_key(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + if (!(f.file->f_mode & FMODE_CAN_READ)) { + err = -EPERM; + goto err_put; + } + if (ukey) { key = memdup_user(ukey, map->key_size); if (IS_ERR(key)) { @@ -908,6 +966,8 @@ static const struct file_operations bpf_prog_fops = { .show_fdinfo = bpf_prog_show_fdinfo, #endif .release = bpf_prog_release, + .read = bpf_dummy_read, + .write = bpf_dummy_write, }; int bpf_prog_new_fd(struct bpf_prog *prog) @@ -1117,11 +1177,11 @@ free_prog_nouncharge: return err; } -#define BPF_OBJ_LAST_FIELD bpf_fd +#define BPF_OBJ_LAST_FIELD file_flags static int bpf_obj_pin(const union bpf_attr *attr) { - if (CHECK_ATTR(BPF_OBJ)) + if (CHECK_ATTR(BPF_OBJ) || attr->file_flags != 0) return -EINVAL; return bpf_obj_pin_user(attr->bpf_fd, u64_to_user_ptr(attr->pathname)); @@ -1129,10 +1189,12 @@ static int bpf_obj_pin(const union bpf_attr *attr) static int bpf_obj_get(const union bpf_attr *attr) { - if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0) + if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0 || + attr->file_flags & ~BPF_OBJ_FLAG_MASK) return -EINVAL; - return bpf_obj_get_user(u64_to_user_ptr(attr->pathname)); + return bpf_obj_get_user(u64_to_user_ptr(attr->pathname), + attr->file_flags); } #ifdef CONFIG_CGROUP_BPF @@ -1392,20 +1454,26 @@ static int bpf_prog_get_fd_by_id(const union bpf_attr *attr) return fd; } -#define BPF_MAP_GET_FD_BY_ID_LAST_FIELD map_id +#define BPF_MAP_GET_FD_BY_ID_LAST_FIELD open_flags static int bpf_map_get_fd_by_id(const union bpf_attr *attr) { struct bpf_map *map; u32 id = attr->map_id; + int f_flags; int fd; - if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID)) + if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID) || + attr->open_flags & ~BPF_OBJ_FLAG_MASK) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; + f_flags = bpf_get_file_flag(attr->open_flags); + if (f_flags < 0) + return f_flags; + spin_lock_bh(&map_idr_lock); map = idr_find(&map_idr, id); if (map) @@ -1417,7 +1485,7 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); - fd = bpf_map_new_fd(map); + fd = bpf_map_new_fd(map, f_flags); if (fd < 0) bpf_map_put(map); diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c index 29123934887b..041da0d9c06f 100644 --- a/net/netfilter/xt_bpf.c +++ b/net/netfilter/xt_bpf.c @@ -56,7 +56,7 @@ static int __bpf_mt_check_path(const char *path, struct bpf_prog **ret) int retval, fd; set_fs(KERNEL_DS); - fd = bpf_obj_get_user(path); + fd = bpf_obj_get_user(path, 0); set_fs(oldfs); if (fd < 0) return fd; -- cgit v1.2.3-71-gd317 From e6546ef6d86d0fc38e0e84ccae80e641f3fc0087 Mon Sep 17 00:00:00 2001 From: Lawrence Brakmo Date: Fri, 20 Oct 2017 11:05:39 -0700 Subject: bpf: add support for BPF_SOCK_OPS_BASE_RTT A congestion control algorithm can make a call to the BPF socket_ops program to request the base RTT. The base RTT can be congestion control dependent and is meant to represent a congestion threshold such that RTTs above it indicate congestion. This is especially useful for flows within a DC where the base RTT is easy to obtain. Being provided a base RTT solves a basic problem in RTT based congestion avoidance algorithms (such as Vegas, NV and BBR). Although it is easy to get the base RTT when the network is not congested, it is very diffcult to do when it is very congested. Newer connections get an inflated value of the base RTT leading to unfariness (newer flows with a larger base RTT get more bandwidth). As a result, RTT based congestion avoidance algorithms tend to update their base RTTs to improve fairness. In very congested networks this can lead to base RTT inflation, reducing the ability of these RTT based congestion control algorithms to prevent congestion. Note that in my experiments with TCP-NV, the base RTT provided can be much larger than the actual hardware RTT. For example, experimenting with hosts within a rack where the hardware RTT is 16-20us, I've used base RTTs up to 150us. The effect of using a larger base RTT is that the congestion avoidance algorithm will allow more queueing. When there are only a few flows the main effect is larger measured RTTs and RPC latencies due to the increased queueing. When there are a lot of flows, a larger base RTT can lead to more congestion and more packet drops. For this case, where the hardware RTT is 20us, a base RTT of 80us produces good results. This patch only introduces BPF_SOCK_OPS_BASE_RTT, a later patch in this set adds support for using it in TCP-NV. Further study and testing is needed before support can be added to other delay based congestion avoidance algorithms. Signed-off-by: Lawrence Brakmo Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d83f95ea6a1b..1aca744c220f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -955,6 +955,13 @@ enum { BPF_SOCK_OPS_NEEDS_ECN, /* If connection's congestion control * needs ECN */ + BPF_SOCK_OPS_BASE_RTT, /* Get base RTT. The correct value is + * based on the path and may be + * dependent on the congestion control + * algorithm. In general it indicates + * a congestion threshold. RTTs above + * this indicate congestion + */ }; #define TCP_BPF_IW 1001 /* Set TCP initial congestion window */ -- cgit v1.2.3-71-gd317 From cd86d1fd21025fdd6daf23d1288da405e7ad0ec6 Mon Sep 17 00:00:00 2001 From: Lawrence Brakmo Date: Fri, 20 Oct 2017 11:05:40 -0700 Subject: bpf: Adding helper function bpf_getsockops Adding support for helper function bpf_getsockops to socket_ops BPF programs. This patch only supports TCP_CONGESTION. Signed-off-by: Vlad Vysotsky Acked-by: Lawrence Brakmo Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 19 ++++++++++--- net/core/filter.c | 46 ++++++++++++++++++++++++++++++- tools/testing/selftests/bpf/bpf_helpers.h | 3 ++ 3 files changed, 63 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1aca744c220f..f650346aaa1a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -613,12 +613,22 @@ union bpf_attr { * int bpf_setsockopt(bpf_socket, level, optname, optval, optlen) * Calls setsockopt. Not all opts are available, only those with * integer optvals plus TCP_CONGESTION. - * Supported levels: SOL_SOCKET and IPROTO_TCP + * Supported levels: SOL_SOCKET and IPPROTO_TCP * @bpf_socket: pointer to bpf_socket - * @level: SOL_SOCKET or IPROTO_TCP + * @level: SOL_SOCKET or IPPROTO_TCP * @optname: option name * @optval: pointer to option value - * @optlen: length of optval in byes + * @optlen: length of optval in bytes + * Return: 0 or negative error + * + * int bpf_getsockopt(bpf_socket, level, optname, optval, optlen) + * Calls getsockopt. Not all opts are available. + * Supported levels: IPPROTO_TCP + * @bpf_socket: pointer to bpf_socket + * @level: IPPROTO_TCP + * @optname: option name + * @optval: pointer to option value + * @optlen: length of optval in bytes * Return: 0 or negative error * * int bpf_skb_adjust_room(skb, len_diff, mode, flags) @@ -721,7 +731,8 @@ union bpf_attr { FN(sock_map_update), \ FN(xdp_adjust_meta), \ FN(perf_event_read_value), \ - FN(perf_prog_read_value), + FN(perf_prog_read_value), \ + FN(getsockopt), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/net/core/filter.c b/net/core/filter.c index 09e011f20291..ccf62f44140a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3273,7 +3273,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, static const struct bpf_func_proto bpf_setsockopt_proto = { .func = bpf_setsockopt, - .gpl_only = true, + .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, @@ -3282,6 +3282,48 @@ static const struct bpf_func_proto bpf_setsockopt_proto = { .arg5_type = ARG_CONST_SIZE, }; +BPF_CALL_5(bpf_getsockopt, struct bpf_sock_ops_kern *, bpf_sock, + int, level, int, optname, char *, optval, int, optlen) +{ + struct sock *sk = bpf_sock->sk; + int ret = 0; + + if (!sk_fullsock(sk)) + goto err_clear; + +#ifdef CONFIG_INET + if (level == SOL_TCP && sk->sk_prot->getsockopt == tcp_getsockopt) { + if (optname == TCP_CONGESTION) { + struct inet_connection_sock *icsk = inet_csk(sk); + + if (!icsk->icsk_ca_ops || optlen <= 1) + goto err_clear; + strncpy(optval, icsk->icsk_ca_ops->name, optlen); + optval[optlen - 1] = 0; + } else { + goto err_clear; + } + } else { + goto err_clear; + } + return ret; +#endif +err_clear: + memset(optval, 0, optlen); + return -EINVAL; +} + +static const struct bpf_func_proto bpf_getsockopt_proto = { + .func = bpf_getsockopt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_UNINIT_MEM, + .arg5_type = ARG_CONST_SIZE, +}; + static const struct bpf_func_proto * bpf_base_func_proto(enum bpf_func_id func_id) { @@ -3460,6 +3502,8 @@ static const struct bpf_func_proto * switch (func_id) { case BPF_FUNC_setsockopt: return &bpf_setsockopt_proto; + case BPF_FUNC_getsockopt: + return &bpf_getsockopt_proto; case BPF_FUNC_sock_map_update: return &bpf_sock_map_update_proto; default: diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index e25dbf6038cf..609514f74482 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -67,6 +67,9 @@ static int (*bpf_xdp_adjust_meta)(void *ctx, int offset) = static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval, int optlen) = (void *) BPF_FUNC_setsockopt; +static int (*bpf_getsockopt)(void *ctx, int level, int optname, void *optval, + int optlen) = + (void *) BPF_FUNC_getsockopt; static int (*bpf_sk_redirect_map)(void *map, int key, int flags) = (void *) BPF_FUNC_sk_redirect_map; static int (*bpf_sock_map_update)(void *map, void *key, void *value, -- cgit v1.2.3-71-gd317 From 40b16b9be5773a314948656c96adf7bf7cfdbd0b Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Sat, 21 Oct 2017 11:45:46 +0200 Subject: batman-adv: use inline kernel-doc for uapi constants The enums of constants for netlink tends to become rather large over time. Documenting them is easier when the kernel-doc is actually next to constant and not in a different block above the enum. Also inline kernel-doc allows multi-paragraph description. This could be required to better document the netlink command types and the expected return values. Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich --- include/uapi/linux/batman_adv.h | 369 +++++++++++++++++++++++++++++++--------- 1 file changed, 290 insertions(+), 79 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h index a83ddb7b63db..efd641c8a5d6 100644 --- a/include/uapi/linux/batman_adv.h +++ b/include/uapi/linux/batman_adv.h @@ -24,20 +24,6 @@ /** * enum batadv_tt_client_flags - TT client specific flags - * @BATADV_TT_CLIENT_DEL: the client has to be deleted from the table - * @BATADV_TT_CLIENT_ROAM: the client roamed to/from another node and the new - * update telling its new real location has not been received/sent yet - * @BATADV_TT_CLIENT_WIFI: this client is connected through a wifi interface. - * This information is used by the "AP Isolation" feature - * @BATADV_TT_CLIENT_ISOLA: this client is considered "isolated". This - * information is used by the Extended Isolation feature - * @BATADV_TT_CLIENT_NOPURGE: this client should never be removed from the table - * @BATADV_TT_CLIENT_NEW: this client has been added to the local table but has - * not been announced yet - * @BATADV_TT_CLIENT_PENDING: this client is marked for removal but it is kept - * in the table for one more originator interval for consistency purposes - * @BATADV_TT_CLIENT_TEMP: this global client has been detected to be part of - * the network but no nnode has already announced it * * Bits from 0 to 7 are called _remote flags_ because they are sent on the wire. * Bits from 8 to 15 are called _local flags_ because they are used for local @@ -48,160 +34,385 @@ * in the TT CRC computation. */ enum batadv_tt_client_flags { + /** + * @BATADV_TT_CLIENT_DEL: the client has to be deleted from the table + */ BATADV_TT_CLIENT_DEL = (1 << 0), + + /** + * @BATADV_TT_CLIENT_ROAM: the client roamed to/from another node and + * the new update telling its new real location has not been + * received/sent yet + */ BATADV_TT_CLIENT_ROAM = (1 << 1), + + /** + * @BATADV_TT_CLIENT_WIFI: this client is connected through a wifi + * interface. This information is used by the "AP Isolation" feature + */ BATADV_TT_CLIENT_WIFI = (1 << 4), + + /** + * @BATADV_TT_CLIENT_ISOLA: this client is considered "isolated". This + * information is used by the Extended Isolation feature + */ BATADV_TT_CLIENT_ISOLA = (1 << 5), + + /** + * @BATADV_TT_CLIENT_NOPURGE: this client should never be removed from + * the table + */ BATADV_TT_CLIENT_NOPURGE = (1 << 8), + + /** + * @BATADV_TT_CLIENT_NEW: this client has been added to the local table + * but has not been announced yet + */ BATADV_TT_CLIENT_NEW = (1 << 9), + + /** + * @BATADV_TT_CLIENT_PENDING: this client is marked for removal but it + * is kept in the table for one more originator interval for consistency + * purposes + */ BATADV_TT_CLIENT_PENDING = (1 << 10), + + /** + * @BATADV_TT_CLIENT_TEMP: this global client has been detected to be + * part of the network but no nnode has already announced it + */ BATADV_TT_CLIENT_TEMP = (1 << 11), }; /** * enum batadv_nl_attrs - batman-adv netlink attributes - * - * @BATADV_ATTR_UNSPEC: unspecified attribute to catch errors - * @BATADV_ATTR_VERSION: batman-adv version string - * @BATADV_ATTR_ALGO_NAME: name of routing algorithm - * @BATADV_ATTR_MESH_IFINDEX: index of the batman-adv interface - * @BATADV_ATTR_MESH_IFNAME: name of the batman-adv interface - * @BATADV_ATTR_MESH_ADDRESS: mac address of the batman-adv interface - * @BATADV_ATTR_HARD_IFINDEX: index of the non-batman-adv interface - * @BATADV_ATTR_HARD_IFNAME: name of the non-batman-adv interface - * @BATADV_ATTR_HARD_ADDRESS: mac address of the non-batman-adv interface - * @BATADV_ATTR_ORIG_ADDRESS: originator mac address - * @BATADV_ATTR_TPMETER_RESULT: result of run (see batadv_tp_meter_status) - * @BATADV_ATTR_TPMETER_TEST_TIME: time (msec) the run took - * @BATADV_ATTR_TPMETER_BYTES: amount of acked bytes during run - * @BATADV_ATTR_TPMETER_COOKIE: session cookie to match tp_meter session - * @BATADV_ATTR_PAD: attribute used for padding for 64-bit alignment - * @BATADV_ATTR_ACTIVE: Flag indicating if the hard interface is active - * @BATADV_ATTR_TT_ADDRESS: Client MAC address - * @BATADV_ATTR_TT_TTVN: Translation table version - * @BATADV_ATTR_TT_LAST_TTVN: Previous translation table version - * @BATADV_ATTR_TT_CRC32: CRC32 over translation table - * @BATADV_ATTR_TT_VID: VLAN ID - * @BATADV_ATTR_TT_FLAGS: Translation table client flags - * @BATADV_ATTR_FLAG_BEST: Flags indicating entry is the best - * @BATADV_ATTR_LAST_SEEN_MSECS: Time in milliseconds since last seen - * @BATADV_ATTR_NEIGH_ADDRESS: Neighbour MAC address - * @BATADV_ATTR_TQ: TQ to neighbour - * @BATADV_ATTR_THROUGHPUT: Estimated throughput to Neighbour - * @BATADV_ATTR_BANDWIDTH_UP: Reported uplink bandwidth - * @BATADV_ATTR_BANDWIDTH_DOWN: Reported downlink bandwidth - * @BATADV_ATTR_ROUTER: Gateway router MAC address - * @BATADV_ATTR_BLA_OWN: Flag indicating own originator - * @BATADV_ATTR_BLA_ADDRESS: Bridge loop avoidance claim MAC address - * @BATADV_ATTR_BLA_VID: BLA VLAN ID - * @BATADV_ATTR_BLA_BACKBONE: BLA gateway originator MAC address - * @BATADV_ATTR_BLA_CRC: BLA CRC - * @__BATADV_ATTR_AFTER_LAST: internal use - * @NUM_BATADV_ATTR: total number of batadv_nl_attrs available - * @BATADV_ATTR_MAX: highest attribute number currently defined */ enum batadv_nl_attrs { + /** + * @BATADV_ATTR_UNSPEC: unspecified attribute to catch errors + */ BATADV_ATTR_UNSPEC, + + /** + * @BATADV_ATTR_VERSION: batman-adv version string + */ BATADV_ATTR_VERSION, + + /** + * @BATADV_ATTR_ALGO_NAME: name of routing algorithm + */ BATADV_ATTR_ALGO_NAME, + + /** + * @BATADV_ATTR_MESH_IFINDEX: index of the batman-adv interface + */ BATADV_ATTR_MESH_IFINDEX, + + /** + * @BATADV_ATTR_MESH_IFNAME: name of the batman-adv interface + */ BATADV_ATTR_MESH_IFNAME, + + /** + * @BATADV_ATTR_MESH_ADDRESS: mac address of the batman-adv interface + */ BATADV_ATTR_MESH_ADDRESS, + + /** + * @BATADV_ATTR_HARD_IFINDEX: index of the non-batman-adv interface + */ BATADV_ATTR_HARD_IFINDEX, + + /** + * @BATADV_ATTR_HARD_IFNAME: name of the non-batman-adv interface + */ BATADV_ATTR_HARD_IFNAME, + + /** + * @BATADV_ATTR_HARD_ADDRESS: mac address of the non-batman-adv + * interface + */ BATADV_ATTR_HARD_ADDRESS, + + /** + * @BATADV_ATTR_ORIG_ADDRESS: originator mac address + */ BATADV_ATTR_ORIG_ADDRESS, + + /** + * @BATADV_ATTR_TPMETER_RESULT: result of run (see + * batadv_tp_meter_status) + */ BATADV_ATTR_TPMETER_RESULT, + + /** + * @BATADV_ATTR_TPMETER_TEST_TIME: time (msec) the run took + */ BATADV_ATTR_TPMETER_TEST_TIME, + + /** + * @BATADV_ATTR_TPMETER_BYTES: amount of acked bytes during run + */ BATADV_ATTR_TPMETER_BYTES, + + /** + * @BATADV_ATTR_TPMETER_COOKIE: session cookie to match tp_meter session + */ BATADV_ATTR_TPMETER_COOKIE, + + /** + * @BATADV_ATTR_PAD: attribute used for padding for 64-bit alignment + */ BATADV_ATTR_PAD, + + /** + * @BATADV_ATTR_ACTIVE: Flag indicating if the hard interface is active + */ BATADV_ATTR_ACTIVE, + + /** + * @BATADV_ATTR_TT_ADDRESS: Client MAC address + */ BATADV_ATTR_TT_ADDRESS, + + /** + * @BATADV_ATTR_TT_TTVN: Translation table version + */ BATADV_ATTR_TT_TTVN, + + /** + * @BATADV_ATTR_TT_LAST_TTVN: Previous translation table version + */ BATADV_ATTR_TT_LAST_TTVN, + + /** + * @BATADV_ATTR_TT_CRC32: CRC32 over translation table + */ BATADV_ATTR_TT_CRC32, + + /** + * @BATADV_ATTR_TT_VID: VLAN ID + */ BATADV_ATTR_TT_VID, + + /** + * @BATADV_ATTR_TT_FLAGS: Translation table client flags + */ BATADV_ATTR_TT_FLAGS, + + /** + * @BATADV_ATTR_FLAG_BEST: Flags indicating entry is the best + */ BATADV_ATTR_FLAG_BEST, + + /** + * @BATADV_ATTR_LAST_SEEN_MSECS: Time in milliseconds since last seen + */ BATADV_ATTR_LAST_SEEN_MSECS, + + /** + * @BATADV_ATTR_NEIGH_ADDRESS: Neighbour MAC address + */ BATADV_ATTR_NEIGH_ADDRESS, + + /** + * @BATADV_ATTR_TQ: TQ to neighbour + */ BATADV_ATTR_TQ, + + /** + * @BATADV_ATTR_THROUGHPUT: Estimated throughput to Neighbour + */ BATADV_ATTR_THROUGHPUT, + + /** + * @BATADV_ATTR_BANDWIDTH_UP: Reported uplink bandwidth + */ BATADV_ATTR_BANDWIDTH_UP, + + /** + * @BATADV_ATTR_BANDWIDTH_DOWN: Reported downlink bandwidth + */ BATADV_ATTR_BANDWIDTH_DOWN, + + /** + * @BATADV_ATTR_ROUTER: Gateway router MAC address + */ BATADV_ATTR_ROUTER, + + /** + * @BATADV_ATTR_BLA_OWN: Flag indicating own originator + */ BATADV_ATTR_BLA_OWN, + + /** + * @BATADV_ATTR_BLA_ADDRESS: Bridge loop avoidance claim MAC address + */ BATADV_ATTR_BLA_ADDRESS, + + /** + * @BATADV_ATTR_BLA_VID: BLA VLAN ID + */ BATADV_ATTR_BLA_VID, + + /** + * @BATADV_ATTR_BLA_BACKBONE: BLA gateway originator MAC address + */ BATADV_ATTR_BLA_BACKBONE, + + /** + * @BATADV_ATTR_BLA_CRC: BLA CRC + */ BATADV_ATTR_BLA_CRC, + /* add attributes above here, update the policy in netlink.c */ + + /** + * @__BATADV_ATTR_AFTER_LAST: internal use + */ __BATADV_ATTR_AFTER_LAST, + + /** + * @NUM_BATADV_ATTR: total number of batadv_nl_attrs available + */ NUM_BATADV_ATTR = __BATADV_ATTR_AFTER_LAST, + + /** + * @BATADV_ATTR_MAX: highest attribute number currently defined + */ BATADV_ATTR_MAX = __BATADV_ATTR_AFTER_LAST - 1 }; /** * enum batadv_nl_commands - supported batman-adv netlink commands - * - * @BATADV_CMD_UNSPEC: unspecified command to catch errors - * @BATADV_CMD_GET_MESH_INFO: Query basic information about batman-adv device - * @BATADV_CMD_TP_METER: Start a tp meter session - * @BATADV_CMD_TP_METER_CANCEL: Cancel a tp meter session - * @BATADV_CMD_GET_ROUTING_ALGOS: Query the list of routing algorithms. - * @BATADV_CMD_GET_HARDIFS: Query list of hard interfaces - * @BATADV_CMD_GET_TRANSTABLE_LOCAL: Query list of local translations - * @BATADV_CMD_GET_TRANSTABLE_GLOBAL Query list of global translations - * @BATADV_CMD_GET_ORIGINATORS: Query list of originators - * @BATADV_CMD_GET_NEIGHBORS: Query list of neighbours - * @BATADV_CMD_GET_GATEWAYS: Query list of gateways - * @BATADV_CMD_GET_BLA_CLAIM: Query list of bridge loop avoidance claims - * @BATADV_CMD_GET_BLA_BACKBONE: Query list of bridge loop avoidance backbones - * @__BATADV_CMD_AFTER_LAST: internal use - * @BATADV_CMD_MAX: highest used command number */ enum batadv_nl_commands { + /** + * @BATADV_CMD_UNSPEC: unspecified command to catch errors + */ BATADV_CMD_UNSPEC, + + /** + * @BATADV_CMD_GET_MESH_INFO: Query basic information about batman-adv + * device + */ BATADV_CMD_GET_MESH_INFO, + + /** + * @BATADV_CMD_TP_METER: Start a tp meter session + */ BATADV_CMD_TP_METER, + + /** + * @BATADV_CMD_TP_METER_CANCEL: Cancel a tp meter session + */ BATADV_CMD_TP_METER_CANCEL, + + /** + * @BATADV_CMD_GET_ROUTING_ALGOS: Query the list of routing algorithms. + */ BATADV_CMD_GET_ROUTING_ALGOS, + + /** + * @BATADV_CMD_GET_HARDIFS: Query list of hard interfaces + */ BATADV_CMD_GET_HARDIFS, + + /** + * @BATADV_CMD_GET_TRANSTABLE_LOCAL: Query list of local translations + */ BATADV_CMD_GET_TRANSTABLE_LOCAL, + + /** + * @BATADV_CMD_GET_TRANSTABLE_GLOBAL: Query list of global translations + */ BATADV_CMD_GET_TRANSTABLE_GLOBAL, + + /** + * @BATADV_CMD_GET_ORIGINATORS: Query list of originators + */ BATADV_CMD_GET_ORIGINATORS, + + /** + * @BATADV_CMD_GET_NEIGHBORS: Query list of neighbours + */ BATADV_CMD_GET_NEIGHBORS, + + /** + * @BATADV_CMD_GET_GATEWAYS: Query list of gateways + */ BATADV_CMD_GET_GATEWAYS, + + /** + * @BATADV_CMD_GET_BLA_CLAIM: Query list of bridge loop avoidance claims + */ BATADV_CMD_GET_BLA_CLAIM, + + /** + * @BATADV_CMD_GET_BLA_BACKBONE: Query list of bridge loop avoidance + * backbones + */ BATADV_CMD_GET_BLA_BACKBONE, + /* add new commands above here */ + + /** + * @__BATADV_CMD_AFTER_LAST: internal use + */ __BATADV_CMD_AFTER_LAST, + + /** + * @BATADV_CMD_MAX: highest used command number + */ BATADV_CMD_MAX = __BATADV_CMD_AFTER_LAST - 1 }; /** * enum batadv_tp_meter_reason - reason of a tp meter test run stop - * @BATADV_TP_REASON_COMPLETE: sender finished tp run - * @BATADV_TP_REASON_CANCEL: sender was stopped during run - * @BATADV_TP_REASON_DST_UNREACHABLE: receiver could not be reached or didn't - * answer - * @BATADV_TP_REASON_RESEND_LIMIT: (unused) sender retry reached limit - * @BATADV_TP_REASON_ALREADY_ONGOING: test to or from the same node already - * ongoing - * @BATADV_TP_REASON_MEMORY_ERROR: test was stopped due to low memory - * @BATADV_TP_REASON_CANT_SEND: failed to send via outgoing interface - * @BATADV_TP_REASON_TOO_MANY: too many ongoing sessions */ enum batadv_tp_meter_reason { + /** + * @BATADV_TP_REASON_COMPLETE: sender finished tp run + */ BATADV_TP_REASON_COMPLETE = 3, + + /** + * @BATADV_TP_REASON_CANCEL: sender was stopped during run + */ BATADV_TP_REASON_CANCEL = 4, + /* error status >= 128 */ + + /** + * @BATADV_TP_REASON_DST_UNREACHABLE: receiver could not be reached or + * didn't answer + */ BATADV_TP_REASON_DST_UNREACHABLE = 128, + + /** + * @BATADV_TP_REASON_RESEND_LIMIT: (unused) sender retry reached limit + */ BATADV_TP_REASON_RESEND_LIMIT = 129, + + /** + * @BATADV_TP_REASON_ALREADY_ONGOING: test to or from the same node + * already ongoing + */ BATADV_TP_REASON_ALREADY_ONGOING = 130, + + /** + * @BATADV_TP_REASON_MEMORY_ERROR: test was stopped due to low memory + */ BATADV_TP_REASON_MEMORY_ERROR = 131, + + /** + * @BATADV_TP_REASON_CANT_SEND: failed to send via outgoing interface + */ BATADV_TP_REASON_CANT_SEND = 132, + + /** + * @BATADV_TP_REASON_TOO_MANY: too many ongoing sessions + */ BATADV_TP_REASON_TOO_MANY = 133, }; -- cgit v1.2.3-71-gd317 From 71c02379c762cb616c00fd5c4ed253fbf6bbe11b Mon Sep 17 00:00:00 2001 From: Christoph Paasch Date: Mon, 23 Oct 2017 13:22:23 -0700 Subject: tcp: Configure TFO without cookie per socket and/or per route We already allow to enable TFO without a cookie by using the fastopen-sysctl and setting it to TFO_SERVER_COOKIE_NOT_REQD (or TFO_CLIENT_NO_COOKIE). This is safe to do in certain environments where we know that there isn't a malicous host (aka., data-centers) or when the application-protocol already provides an authentication mechanism in the first flight of data. A server however might be providing multiple services or talking to both sides (public Internet and data-center). So, this server would want to enable cookie-less TFO for certain services and/or for connections that go to the data-center. This patch exposes a socket-option and a per-route attribute to enable such fine-grained configurations. Signed-off-by: Christoph Paasch Reviewed-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/linux/tcp.h | 3 ++- include/net/tcp.h | 3 ++- include/uapi/linux/rtnetlink.h | 2 ++ include/uapi/linux/tcp.h | 1 + net/ipv4/tcp.c | 12 ++++++++++++ net/ipv4/tcp_fastopen.c | 20 +++++++++++++++++--- net/ipv4/tcp_input.c | 2 +- 7 files changed, 37 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 1d2c44e09e31..173a7c2f9636 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -215,7 +215,8 @@ struct tcp_sock { u8 chrono_type:2, /* current chronograph type */ rate_app_limited:1, /* rate_{delivered,interval_us} limited? */ fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */ - unused:4; + fastopen_no_cookie:1, /* Allow send/recv SYN+data without a cookie */ + unused:3; u8 nonagle : 4,/* Disable Nagle algorithm? */ thin_lto : 1,/* Use linear timeouts for thin streams */ unused1 : 1, diff --git a/include/net/tcp.h b/include/net/tcp.h index 2c13484704cb..2392f74074e7 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1567,7 +1567,8 @@ int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk, void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb); struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, - struct tcp_fastopen_cookie *foc); + struct tcp_fastopen_cookie *foc, + const struct dst_entry *dst); void tcp_fastopen_init_key_once(struct net *net); bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie); diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index dab7dad9e01a..fe6679268901 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -430,6 +430,8 @@ enum { #define RTAX_QUICKACK RTAX_QUICKACK RTAX_CC_ALGO, #define RTAX_CC_ALGO RTAX_CC_ALGO + RTAX_FASTOPEN_NO_COOKIE, +#define RTAX_FASTOPEN_NO_COOKIE RTAX_FASTOPEN_NO_COOKIE __RTAX_MAX }; diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 69c7493e42f8..d67e1d40c6d6 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -120,6 +120,7 @@ enum { #define TCP_ULP 31 /* Attach a ULP to a TCP connection */ #define TCP_MD5SIG_EXT 32 /* TCP MD5 Signature with extensions */ #define TCP_FASTOPEN_KEY 33 /* Set the key for Fast Open (cookie) */ +#define TCP_FASTOPEN_NO_COOKIE 34 /* Enable TFO without a TFO cookie */ struct tcp_repair_opt { __u32 opt_code; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index be07e9b6dbdd..8f36277e82e9 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2836,6 +2836,14 @@ static int do_tcp_setsockopt(struct sock *sk, int level, err = -EOPNOTSUPP; } break; + case TCP_FASTOPEN_NO_COOKIE: + if (val > 1 || val < 0) + err = -EINVAL; + else if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) + err = -EINVAL; + else + tp->fastopen_no_cookie = val; + break; case TCP_TIMESTAMP: if (!tp->repair) err = -EPERM; @@ -3256,6 +3264,10 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = tp->fastopen_connect; break; + case TCP_FASTOPEN_NO_COOKIE: + val = tp->fastopen_no_cookie; + break; + case TCP_TIMESTAMP: val = tcp_time_stamp_raw() + tp->tsoffset; break; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 21075ce19cb6..e0a4b56644aa 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -310,13 +310,23 @@ static bool tcp_fastopen_queue_check(struct sock *sk) return true; } +static bool tcp_fastopen_no_cookie(const struct sock *sk, + const struct dst_entry *dst, + int flag) +{ + return (sock_net(sk)->ipv4.sysctl_tcp_fastopen & flag) || + tcp_sk(sk)->fastopen_no_cookie || + (dst && dst_metric(dst, RTAX_FASTOPEN_NO_COOKIE)); +} + /* Returns true if we should perform Fast Open on the SYN. The cookie (foc) * may be updated and return the client in the SYN-ACK later. E.g., Fast Open * cookie request (foc->len == 0). */ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, - struct tcp_fastopen_cookie *foc) + struct tcp_fastopen_cookie *foc, + const struct dst_entry *dst) { bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1; int tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen; @@ -333,7 +343,8 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, return NULL; } - if (syn_data && (tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD)) + if (syn_data && + tcp_fastopen_no_cookie(sk, dst, TFO_SERVER_COOKIE_NOT_REQD)) goto fastopen; if (foc->len >= 0 && /* Client presents or requests a cookie */ @@ -370,6 +381,7 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie) { unsigned long last_syn_loss = 0; + const struct dst_entry *dst; int syn_loss = 0; tcp_fastopen_cache_get(sk, mss, cookie, &syn_loss, &last_syn_loss); @@ -387,7 +399,9 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, return false; } - if (sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE) { + dst = __sk_dst_get(sk); + + if (tcp_fastopen_no_cookie(sk, dst, TFO_CLIENT_NO_COOKIE)) { cookie->len = -1; return true; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c5e64d4b5839..893286db4623 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6332,7 +6332,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_openreq_init_rwin(req, sk, dst); if (!want_cookie) { tcp_reqsk_record_syn(sk, req, skb); - fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc); + fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc, dst); } if (fastopen_sk) { af_ops->send_synack(fastopen_sk, dst, &fl, req, -- cgit v1.2.3-71-gd317 From d15155824c5014803d91b829736d249c500bdda6 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 24 Oct 2017 11:22:46 +0100 Subject: linux/compiler.h: Split into compiler.h and compiler_types.h linux/compiler.h is included indirectly by linux/types.h via uapi/linux/types.h -> uapi/linux/posix_types.h -> linux/stddef.h -> uapi/linux/stddef.h and is needed to provide a proper definition of offsetof. Unfortunately, compiler.h requires a definition of smp_read_barrier_depends() for defining lockless_dereference() and soon for defining READ_ONCE(), which means that all users of READ_ONCE() will need to include asm/barrier.h to avoid splats such as: In file included from include/uapi/linux/stddef.h:1:0, from include/linux/stddef.h:4, from arch/h8300/kernel/asm-offsets.c:11: include/linux/list.h: In function 'list_empty': >> include/linux/compiler.h:343:2: error: implicit declaration of function 'smp_read_barrier_depends' [-Werror=implicit-function-declaration] smp_read_barrier_depends(); /* Enforce dependency ordering from x */ \ ^ A better alternative is to include asm/barrier.h in linux/compiler.h, but this requires a type definition for "bool" on some architectures (e.g. x86), which is defined later by linux/types.h. Type "bool" is also used directly in linux/compiler.h, so the whole thing is pretty fragile. This patch splits compiler.h in two: compiler_types.h contains type annotations, definitions and the compiler-specific parts, whereas compiler.h #includes compiler-types.h and additionally defines macros such as {READ,WRITE.ACCESS}_ONCE(). uapi/linux/stddef.h and linux/linkage.h are then moved over to include linux/compiler_types.h, which fixes the build for h8 and blackfin. Signed-off-by: Will Deacon Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1508840570-22169-2-git-send-email-will.deacon@arm.com Signed-off-by: Ingo Molnar --- arch/arm/include/asm/ptrace.h | 3 +- arch/sparc/include/asm/ptrace.h | 1 + arch/um/include/shared/init.h | 2 +- include/linux/compiler-clang.h | 2 +- include/linux/compiler-gcc.h | 2 +- include/linux/compiler-intel.h | 2 +- include/linux/compiler.h | 265 +------------------------------------- include/linux/compiler_types.h | 274 ++++++++++++++++++++++++++++++++++++++++ include/linux/linkage.h | 2 +- include/uapi/linux/stddef.h | 2 +- scripts/headers_install.sh | 2 +- 11 files changed, 286 insertions(+), 271 deletions(-) create mode 100644 include/linux/compiler_types.h (limited to 'include/uapi/linux') diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h index e9c9a117bd25..c7cdbb43ae7c 100644 --- a/arch/arm/include/asm/ptrace.h +++ b/arch/arm/include/asm/ptrace.h @@ -126,8 +126,7 @@ extern unsigned long profile_pc(struct pt_regs *regs); /* * kprobe-based event tracer support */ -#include -#include +#include #define MAX_REG_OFFSET (offsetof(struct pt_regs, ARM_ORIG_r0)) extern int regs_query_register_offset(const char *name); diff --git a/arch/sparc/include/asm/ptrace.h b/arch/sparc/include/asm/ptrace.h index d73428e4333c..b383484edcd3 100644 --- a/arch/sparc/include/asm/ptrace.h +++ b/arch/sparc/include/asm/ptrace.h @@ -6,6 +6,7 @@ #if defined(__sparc__) && defined(__arch64__) #ifndef __ASSEMBLY__ +#include #include #include diff --git a/arch/um/include/shared/init.h b/arch/um/include/shared/init.h index 233e2593eee0..094e96ce653b 100644 --- a/arch/um/include/shared/init.h +++ b/arch/um/include/shared/init.h @@ -40,7 +40,7 @@ typedef int (*initcall_t)(void); typedef void (*exitcall_t)(void); -#include +#include /* These are for everybody (although not all archs will actually discard it in modules) */ diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index de179993e039..5947a3e6c0e6 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -1,4 +1,4 @@ -#ifndef __LINUX_COMPILER_H +#ifndef __LINUX_COMPILER_TYPES_H #error "Please don't include directly, include instead." #endif diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 16d41de92ee3..ce8e965646ef 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -1,4 +1,4 @@ -#ifndef __LINUX_COMPILER_H +#ifndef __LINUX_COMPILER_TYPES_H #error "Please don't include directly, include instead." #endif diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h index d4c71132d07f..e438ac89c692 100644 --- a/include/linux/compiler-intel.h +++ b/include/linux/compiler-intel.h @@ -1,4 +1,4 @@ -#ifndef __LINUX_COMPILER_H +#ifndef __LINUX_COMPILER_TYPES_H #error "Please don't include directly, include instead." #endif diff --git a/include/linux/compiler.h b/include/linux/compiler.h index e95a2631e545..08083186e54f 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -1,111 +1,12 @@ #ifndef __LINUX_COMPILER_H #define __LINUX_COMPILER_H -#ifndef __ASSEMBLY__ +#include -#ifdef __CHECKER__ -# define __user __attribute__((noderef, address_space(1))) -# define __kernel __attribute__((address_space(0))) -# define __safe __attribute__((safe)) -# define __force __attribute__((force)) -# define __nocast __attribute__((nocast)) -# define __iomem __attribute__((noderef, address_space(2))) -# define __must_hold(x) __attribute__((context(x,1,1))) -# define __acquires(x) __attribute__((context(x,0,1))) -# define __releases(x) __attribute__((context(x,1,0))) -# define __acquire(x) __context__(x,1) -# define __release(x) __context__(x,-1) -# define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) -# define __percpu __attribute__((noderef, address_space(3))) -# define __rcu __attribute__((noderef, address_space(4))) -# define __private __attribute__((noderef)) -extern void __chk_user_ptr(const volatile void __user *); -extern void __chk_io_ptr(const volatile void __iomem *); -# define ACCESS_PRIVATE(p, member) (*((typeof((p)->member) __force *) &(p)->member)) -#else /* __CHECKER__ */ -# ifdef STRUCTLEAK_PLUGIN -# define __user __attribute__((user)) -# else -# define __user -# endif -# define __kernel -# define __safe -# define __force -# define __nocast -# define __iomem -# define __chk_user_ptr(x) (void)0 -# define __chk_io_ptr(x) (void)0 -# define __builtin_warning(x, y...) (1) -# define __must_hold(x) -# define __acquires(x) -# define __releases(x) -# define __acquire(x) (void)0 -# define __release(x) (void)0 -# define __cond_lock(x,c) (c) -# define __percpu -# define __rcu -# define __private -# define ACCESS_PRIVATE(p, member) ((p)->member) -#endif /* __CHECKER__ */ - -/* Indirect macros required for expanded argument pasting, eg. __LINE__. */ -#define ___PASTE(a,b) a##b -#define __PASTE(a,b) ___PASTE(a,b) +#ifndef __ASSEMBLY__ #ifdef __KERNEL__ -#ifdef __GNUC__ -#include -#endif - -#if defined(CC_USING_HOTPATCH) && !defined(__CHECKER__) -#define notrace __attribute__((hotpatch(0,0))) -#else -#define notrace __attribute__((no_instrument_function)) -#endif - -/* Intel compiler defines __GNUC__. So we will overwrite implementations - * coming from above header files here - */ -#ifdef __INTEL_COMPILER -# include -#endif - -/* Clang compiler defines __GNUC__. So we will overwrite implementations - * coming from above header files here - */ -#ifdef __clang__ -#include -#endif - -/* - * Generic compiler-dependent macros required for kernel - * build go below this comment. Actual compiler/compiler version - * specific implementations come from the above header files - */ - -struct ftrace_branch_data { - const char *func; - const char *file; - unsigned line; - union { - struct { - unsigned long correct; - unsigned long incorrect; - }; - struct { - unsigned long miss; - unsigned long hit; - }; - unsigned long miss_hit[2]; - }; -}; - -struct ftrace_likely_data { - struct ftrace_branch_data data; - unsigned long constant; -}; - /* * Note: DISABLE_BRANCH_PROFILING can be used by special lowlevel code * to disable branch tracing on a per file basis. @@ -332,6 +233,7 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s * with an explicit memory barrier or atomic instruction that provides the * required ordering. */ +#include #define __READ_ONCE(x, check) \ ({ \ @@ -362,167 +264,6 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s #endif /* __ASSEMBLY__ */ -#ifdef __KERNEL__ -/* - * Allow us to mark functions as 'deprecated' and have gcc emit a nice - * warning for each use, in hopes of speeding the functions removal. - * Usage is: - * int __deprecated foo(void) - */ -#ifndef __deprecated -# define __deprecated /* unimplemented */ -#endif - -#ifdef MODULE -#define __deprecated_for_modules __deprecated -#else -#define __deprecated_for_modules -#endif - -#ifndef __must_check -#define __must_check -#endif - -#ifndef CONFIG_ENABLE_MUST_CHECK -#undef __must_check -#define __must_check -#endif -#ifndef CONFIG_ENABLE_WARN_DEPRECATED -#undef __deprecated -#undef __deprecated_for_modules -#define __deprecated -#define __deprecated_for_modules -#endif - -#ifndef __malloc -#define __malloc -#endif - -/* - * Allow us to avoid 'defined but not used' warnings on functions and data, - * as well as force them to be emitted to the assembly file. - * - * As of gcc 3.4, static functions that are not marked with attribute((used)) - * may be elided from the assembly file. As of gcc 3.4, static data not so - * marked will not be elided, but this may change in a future gcc version. - * - * NOTE: Because distributions shipped with a backported unit-at-a-time - * compiler in gcc 3.3, we must define __used to be __attribute__((used)) - * for gcc >=3.3 instead of 3.4. - * - * In prior versions of gcc, such functions and data would be emitted, but - * would be warned about except with attribute((unused)). - * - * Mark functions that are referenced only in inline assembly as __used so - * the code is emitted even though it appears to be unreferenced. - */ -#ifndef __used -# define __used /* unimplemented */ -#endif - -#ifndef __maybe_unused -# define __maybe_unused /* unimplemented */ -#endif - -#ifndef __always_unused -# define __always_unused /* unimplemented */ -#endif - -#ifndef noinline -#define noinline -#endif - -/* - * Rather then using noinline to prevent stack consumption, use - * noinline_for_stack instead. For documentation reasons. - */ -#define noinline_for_stack noinline - -#ifndef __always_inline -#define __always_inline inline -#endif - -#endif /* __KERNEL__ */ - -/* - * From the GCC manual: - * - * Many functions do not examine any values except their arguments, - * and have no effects except the return value. Basically this is - * just slightly more strict class than the `pure' attribute above, - * since function is not allowed to read global memory. - * - * Note that a function that has pointer arguments and examines the - * data pointed to must _not_ be declared `const'. Likewise, a - * function that calls a non-`const' function usually must not be - * `const'. It does not make sense for a `const' function to return - * `void'. - */ -#ifndef __attribute_const__ -# define __attribute_const__ /* unimplemented */ -#endif - -#ifndef __designated_init -# define __designated_init -#endif - -#ifndef __latent_entropy -# define __latent_entropy -#endif - -#ifndef __randomize_layout -# define __randomize_layout __designated_init -#endif - -#ifndef __no_randomize_layout -# define __no_randomize_layout -#endif - -#ifndef randomized_struct_fields_start -# define randomized_struct_fields_start -# define randomized_struct_fields_end -#endif - -/* - * Tell gcc if a function is cold. The compiler will assume any path - * directly leading to the call is unlikely. - */ - -#ifndef __cold -#define __cold -#endif - -/* Simple shorthand for a section definition */ -#ifndef __section -# define __section(S) __attribute__ ((__section__(#S))) -#endif - -#ifndef __visible -#define __visible -#endif - -#ifndef __nostackprotector -# define __nostackprotector -#endif - -/* - * Assume alignment of return value. - */ -#ifndef __assume_aligned -#define __assume_aligned(a, ...) -#endif - - -/* Are two types/vars the same type (ignoring qualifiers)? */ -#ifndef __same_type -# define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) -#endif - -/* Is this type a native word size -- useful for atomic operations */ -#ifndef __native_word -# define __native_word(t) (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long)) -#endif - /* Compile time object size, -1 for unknown */ #ifndef __compiletime_object_size # define __compiletime_object_size(obj) -1 diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h new file mode 100644 index 000000000000..6b79a9bba9a7 --- /dev/null +++ b/include/linux/compiler_types.h @@ -0,0 +1,274 @@ +#ifndef __LINUX_COMPILER_TYPES_H +#define __LINUX_COMPILER_TYPES_H + +#ifndef __ASSEMBLY__ + +#ifdef __CHECKER__ +# define __user __attribute__((noderef, address_space(1))) +# define __kernel __attribute__((address_space(0))) +# define __safe __attribute__((safe)) +# define __force __attribute__((force)) +# define __nocast __attribute__((nocast)) +# define __iomem __attribute__((noderef, address_space(2))) +# define __must_hold(x) __attribute__((context(x,1,1))) +# define __acquires(x) __attribute__((context(x,0,1))) +# define __releases(x) __attribute__((context(x,1,0))) +# define __acquire(x) __context__(x,1) +# define __release(x) __context__(x,-1) +# define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) +# define __percpu __attribute__((noderef, address_space(3))) +# define __rcu __attribute__((noderef, address_space(4))) +# define __private __attribute__((noderef)) +extern void __chk_user_ptr(const volatile void __user *); +extern void __chk_io_ptr(const volatile void __iomem *); +# define ACCESS_PRIVATE(p, member) (*((typeof((p)->member) __force *) &(p)->member)) +#else /* __CHECKER__ */ +# ifdef STRUCTLEAK_PLUGIN +# define __user __attribute__((user)) +# else +# define __user +# endif +# define __kernel +# define __safe +# define __force +# define __nocast +# define __iomem +# define __chk_user_ptr(x) (void)0 +# define __chk_io_ptr(x) (void)0 +# define __builtin_warning(x, y...) (1) +# define __must_hold(x) +# define __acquires(x) +# define __releases(x) +# define __acquire(x) (void)0 +# define __release(x) (void)0 +# define __cond_lock(x,c) (c) +# define __percpu +# define __rcu +# define __private +# define ACCESS_PRIVATE(p, member) ((p)->member) +#endif /* __CHECKER__ */ + +/* Indirect macros required for expanded argument pasting, eg. __LINE__. */ +#define ___PASTE(a,b) a##b +#define __PASTE(a,b) ___PASTE(a,b) + +#ifdef __KERNEL__ + +#ifdef __GNUC__ +#include +#endif + +#if defined(CC_USING_HOTPATCH) && !defined(__CHECKER__) +#define notrace __attribute__((hotpatch(0,0))) +#else +#define notrace __attribute__((no_instrument_function)) +#endif + +/* Intel compiler defines __GNUC__. So we will overwrite implementations + * coming from above header files here + */ +#ifdef __INTEL_COMPILER +# include +#endif + +/* Clang compiler defines __GNUC__. So we will overwrite implementations + * coming from above header files here + */ +#ifdef __clang__ +#include +#endif + +/* + * Generic compiler-dependent macros required for kernel + * build go below this comment. Actual compiler/compiler version + * specific implementations come from the above header files + */ + +struct ftrace_branch_data { + const char *func; + const char *file; + unsigned line; + union { + struct { + unsigned long correct; + unsigned long incorrect; + }; + struct { + unsigned long miss; + unsigned long hit; + }; + unsigned long miss_hit[2]; + }; +}; + +struct ftrace_likely_data { + struct ftrace_branch_data data; + unsigned long constant; +}; + +#endif /* __KERNEL__ */ + +#endif /* __ASSEMBLY__ */ + +#ifdef __KERNEL__ +/* + * Allow us to mark functions as 'deprecated' and have gcc emit a nice + * warning for each use, in hopes of speeding the functions removal. + * Usage is: + * int __deprecated foo(void) + */ +#ifndef __deprecated +# define __deprecated /* unimplemented */ +#endif + +#ifdef MODULE +#define __deprecated_for_modules __deprecated +#else +#define __deprecated_for_modules +#endif + +#ifndef __must_check +#define __must_check +#endif + +#ifndef CONFIG_ENABLE_MUST_CHECK +#undef __must_check +#define __must_check +#endif +#ifndef CONFIG_ENABLE_WARN_DEPRECATED +#undef __deprecated +#undef __deprecated_for_modules +#define __deprecated +#define __deprecated_for_modules +#endif + +#ifndef __malloc +#define __malloc +#endif + +/* + * Allow us to avoid 'defined but not used' warnings on functions and data, + * as well as force them to be emitted to the assembly file. + * + * As of gcc 3.4, static functions that are not marked with attribute((used)) + * may be elided from the assembly file. As of gcc 3.4, static data not so + * marked will not be elided, but this may change in a future gcc version. + * + * NOTE: Because distributions shipped with a backported unit-at-a-time + * compiler in gcc 3.3, we must define __used to be __attribute__((used)) + * for gcc >=3.3 instead of 3.4. + * + * In prior versions of gcc, such functions and data would be emitted, but + * would be warned about except with attribute((unused)). + * + * Mark functions that are referenced only in inline assembly as __used so + * the code is emitted even though it appears to be unreferenced. + */ +#ifndef __used +# define __used /* unimplemented */ +#endif + +#ifndef __maybe_unused +# define __maybe_unused /* unimplemented */ +#endif + +#ifndef __always_unused +# define __always_unused /* unimplemented */ +#endif + +#ifndef noinline +#define noinline +#endif + +/* + * Rather then using noinline to prevent stack consumption, use + * noinline_for_stack instead. For documentation reasons. + */ +#define noinline_for_stack noinline + +#ifndef __always_inline +#define __always_inline inline +#endif + +#endif /* __KERNEL__ */ + +/* + * From the GCC manual: + * + * Many functions do not examine any values except their arguments, + * and have no effects except the return value. Basically this is + * just slightly more strict class than the `pure' attribute above, + * since function is not allowed to read global memory. + * + * Note that a function that has pointer arguments and examines the + * data pointed to must _not_ be declared `const'. Likewise, a + * function that calls a non-`const' function usually must not be + * `const'. It does not make sense for a `const' function to return + * `void'. + */ +#ifndef __attribute_const__ +# define __attribute_const__ /* unimplemented */ +#endif + +#ifndef __designated_init +# define __designated_init +#endif + +#ifndef __latent_entropy +# define __latent_entropy +#endif + +#ifndef __randomize_layout +# define __randomize_layout __designated_init +#endif + +#ifndef __no_randomize_layout +# define __no_randomize_layout +#endif + +#ifndef randomized_struct_fields_start +# define randomized_struct_fields_start +# define randomized_struct_fields_end +#endif + +/* + * Tell gcc if a function is cold. The compiler will assume any path + * directly leading to the call is unlikely. + */ + +#ifndef __cold +#define __cold +#endif + +/* Simple shorthand for a section definition */ +#ifndef __section +# define __section(S) __attribute__ ((__section__(#S))) +#endif + +#ifndef __visible +#define __visible +#endif + +#ifndef __nostackprotector +# define __nostackprotector +#endif + +/* + * Assume alignment of return value. + */ +#ifndef __assume_aligned +#define __assume_aligned(a, ...) +#endif + + +/* Are two types/vars the same type (ignoring qualifiers)? */ +#ifndef __same_type +# define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) +#endif + +/* Is this type a native word size -- useful for atomic operations */ +#ifndef __native_word +# define __native_word(t) (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long)) +#endif + +#endif /* __LINUX_COMPILER_TYPES_H */ diff --git a/include/linux/linkage.h b/include/linux/linkage.h index a6a42dd02466..ebd61b80fed4 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -1,7 +1,7 @@ #ifndef _LINUX_LINKAGE_H #define _LINUX_LINKAGE_H -#include +#include #include #include #include diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index 621fa8ac4425..d1f7cb732dfc 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -1,4 +1,4 @@ -#include +#include #ifndef __always_inline #define __always_inline inline diff --git a/scripts/headers_install.sh b/scripts/headers_install.sh index fdebd66f8fc1..63b8cc26456a 100755 --- a/scripts/headers_install.sh +++ b/scripts/headers_install.sh @@ -33,7 +33,7 @@ do sed -r \ -e 's/([ \t(])(__user|__force|__iomem)[ \t]/\1/g' \ -e 's/__attribute_const__([ \t]|$)/\1/g' \ - -e 's@^#include @@' \ + -e 's@^#include @@' \ -e 's/(^|[^a-zA-Z0-9])__packed([^a-zA-Z0-9_]|$)/\1__attribute__((packed))\2/g' \ -e 's/(^|[ \t(])(inline|asm|volatile)([ \t(]|$)/\1__\2__\3/g' \ -e 's@#(ifndef|define|endif[ \t]*/[*])[ \t]*_UAPI@#\1 @' \ -- cgit v1.2.3-71-gd317 From 276b738deb5bf856b9f6049fcd92a967f52643d7 Mon Sep 17 00:00:00 2001 From: Christian König Date: Tue, 24 Oct 2017 14:40:20 -0500 Subject: PCI: Add resizable BAR infrastructure MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add resizable BAR infrastructure, including defines and helper functions to read the possible sizes of a BAR and update its size. See PCIe r3.1, sec 7.22. Link: https://pcisig.com/sites/default/files/specification_documents/ECN_Resizable-BAR_24Apr2008.pdf Signed-off-by: Christian König [bhelgaas: rename to functions with "rebar" (to match #defines), drop shift #defines, drop "_MASK" suffixes, fix typos, fix kerneldoc] Signed-off-by: Bjorn Helgaas Reviewed-by: Andy Shevchenko --- drivers/pci/pci.c | 101 ++++++++++++++++++++++++++++++++++++++++++ drivers/pci/pci.h | 8 ++++ include/uapi/linux/pci_regs.h | 8 +++- 3 files changed, 115 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 6078dfc11b11..832b96756e83 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -2965,6 +2965,107 @@ bool pci_acs_path_enabled(struct pci_dev *start, return true; } +/** + * pci_rebar_find_pos - find position of resize ctrl reg for BAR + * @pdev: PCI device + * @bar: BAR to find + * + * Helper to find the position of the ctrl register for a BAR. + * Returns -ENOTSUPP if resizable BARs are not supported at all. + * Returns -ENOENT if no ctrl register for the BAR could be found. + */ +static int pci_rebar_find_pos(struct pci_dev *pdev, int bar) +{ + unsigned int pos, nbars, i; + u32 ctrl; + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_REBAR); + if (!pos) + return -ENOTSUPP; + + pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); + nbars = (ctrl & PCI_REBAR_CTRL_NBAR_MASK) >> + PCI_REBAR_CTRL_NBAR_SHIFT; + + for (i = 0; i < nbars; i++, pos += 8) { + int bar_idx; + + pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); + bar_idx = ctrl & PCI_REBAR_CTRL_BAR_IDX; + if (bar_idx == bar) + return pos; + } + + return -ENOENT; +} + +/** + * pci_rebar_get_possible_sizes - get possible sizes for BAR + * @pdev: PCI device + * @bar: BAR to query + * + * Get the possible sizes of a resizable BAR as bitmask defined in the spec + * (bit 0=1MB, bit 19=512GB). Returns 0 if BAR isn't resizable. + */ +u32 pci_rebar_get_possible_sizes(struct pci_dev *pdev, int bar) +{ + int pos; + u32 cap; + + pos = pci_rebar_find_pos(pdev, bar); + if (pos < 0) + return 0; + + pci_read_config_dword(pdev, pos + PCI_REBAR_CAP, &cap); + return (cap & PCI_REBAR_CAP_SIZES) >> 4; +} + +/** + * pci_rebar_get_current_size - get the current size of a BAR + * @pdev: PCI device + * @bar: BAR to set size to + * + * Read the size of a BAR from the resizable BAR config. + * Returns size if found or negative error code. + */ +int pci_rebar_get_current_size(struct pci_dev *pdev, int bar) +{ + int pos; + u32 ctrl; + + pos = pci_rebar_find_pos(pdev, bar); + if (pos < 0) + return pos; + + pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); + return (ctrl & PCI_REBAR_CTRL_BAR_SIZE) >> 8; +} + +/** + * pci_rebar_set_size - set a new size for a BAR + * @pdev: PCI device + * @bar: BAR to set size to + * @size: new size as defined in the spec (0=1MB, 19=512GB) + * + * Set the new size of a BAR as defined in the spec. + * Returns zero if resizing was successful, error code otherwise. + */ +int pci_rebar_set_size(struct pci_dev *pdev, int bar, int size) +{ + int pos; + u32 ctrl; + + pos = pci_rebar_find_pos(pdev, bar); + if (pos < 0) + return pos; + + pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); + ctrl &= ~PCI_REBAR_CTRL_BAR_SIZE; + ctrl |= size << 8; + pci_write_config_dword(pdev, pos + PCI_REBAR_CTRL, ctrl); + return 0; +} + /** * pci_swizzle_interrupt_pin - swizzle INTx for device behind bridge * @dev: the PCI device diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index a6560c9baa52..33469a33738d 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -366,4 +366,12 @@ int acpi_get_rc_resources(struct device *dev, const char *hid, u16 segment, struct resource *res); #endif +u32 pci_rebar_get_possible_sizes(struct pci_dev *pdev, int bar); +int pci_rebar_get_current_size(struct pci_dev *pdev, int bar); +int pci_rebar_set_size(struct pci_dev *pdev, int bar, int size); +static inline u64 pci_rebar_size_to_bytes(int size) +{ + return 1ULL << (size + 20); +} + #endif /* DRIVERS_PCI_H */ diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index f8d58045926f..d34000a59f24 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -939,9 +939,13 @@ #define PCI_SATA_SIZEOF_LONG 16 /* Resizable BARs */ +#define PCI_REBAR_CAP 4 /* capability register */ +#define PCI_REBAR_CAP_SIZES 0x00FFFFF0 /* supported BAR sizes */ #define PCI_REBAR_CTRL 8 /* control register */ -#define PCI_REBAR_CTRL_NBAR_MASK (7 << 5) /* mask for # bars */ -#define PCI_REBAR_CTRL_NBAR_SHIFT 5 /* shift for # bars */ +#define PCI_REBAR_CTRL_BAR_IDX 0x00000007 /* BAR index */ +#define PCI_REBAR_CTRL_NBAR_MASK 0x000000E0 /* # of resizable BARs */ +#define PCI_REBAR_CTRL_NBAR_SHIFT 5 /* shift for # of BARs */ +#define PCI_REBAR_CTRL_BAR_SIZE 0x00001F00 /* BAR size */ /* Dynamic Power Allocation */ #define PCI_DPA_CAP 4 /* capability register */ -- cgit v1.2.3-71-gd317 From 908d140a87a794bf89717ceae54aba5ce86c52e4 Mon Sep 17 00:00:00 2001 From: Shmulik Ladkani Date: Sat, 21 Oct 2017 00:25:15 +0300 Subject: ip6_tunnel: Allow rcv/xmit even if remote address is a local address Currently, ip6_tnl_xmit_ctl drops tunneled packets if the remote address (outer v6 destination) is one of host's locally configured addresses. Same applies to ip6_tnl_rcv_ctl: it drops packets if the remote address (outer v6 source) is a local address. This prevents using ipxip6 (and ip6_gre) tunnels whose local/remote endpoints are on same host; OTOH v4 tunnels (ipip or gre) allow such configurations. An example where this proves useful is a system where entities are identified by their unique v6 addresses, and use tunnels to encapsulate traffic between them. The limitation prevents placing several entities on same host. Introduce IP6_TNL_F_ALLOW_LOCAL_REMOTE which allows to bypass this restriction. Signed-off-by: Shmulik Ladkani Signed-off-by: David S. Miller --- include/uapi/linux/ip6_tunnel.h | 2 ++ net/ipv6/ip6_tunnel.c | 6 ++++-- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ip6_tunnel.h b/include/uapi/linux/ip6_tunnel.h index 425926c467d7..ffebbe365478 100644 --- a/include/uapi/linux/ip6_tunnel.h +++ b/include/uapi/linux/ip6_tunnel.h @@ -20,6 +20,8 @@ #define IP6_TNL_F_RCV_DSCP_COPY 0x10 /* copy fwmark from inner packet */ #define IP6_TNL_F_USE_ORIG_FWMARK 0x20 +/* allow remote endpoint on the local node */ +#define IP6_TNL_F_ALLOW_LOCAL_REMOTE 0x40 struct ip6_tnl_parm { char name[IFNAMSIZ]; /* name of tunnel device */ diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 4212879ff35e..439d65f7e094 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -770,7 +770,8 @@ int ip6_tnl_rcv_ctl(struct ip6_tnl *t, if ((ipv6_addr_is_multicast(laddr) || likely(ipv6_chk_addr(net, laddr, ldev, 0))) && - likely(!ipv6_chk_addr(net, raddr, NULL, 0))) + ((p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) || + likely(!ipv6_chk_addr(net, raddr, NULL, 0)))) ret = 1; } return ret; @@ -1000,7 +1001,8 @@ int ip6_tnl_xmit_ctl(struct ip6_tnl *t, if (unlikely(!ipv6_chk_addr(net, laddr, ldev, 0))) pr_warn("%s xmit: Local address not yet configured!\n", p->name); - else if (!ipv6_addr_is_multicast(raddr) && + else if (!(p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) && + !ipv6_addr_is_multicast(raddr) && unlikely(ipv6_chk_addr(net, raddr, NULL, 0))) pr_warn("%s xmit: Routing loop! Remote address found on this node!\n", p->name); -- cgit v1.2.3-71-gd317 From 585d763af09cc21daf48ecc873604ccdb70f6014 Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Mon, 16 Oct 2017 18:01:26 -0700 Subject: net/sched: Introduce Credit Based Shaper (CBS) qdisc This queueing discipline implements the shaper algorithm defined by the 802.1Q-2014 Section 8.6.8.2 and detailed in Annex L. It's primary usage is to apply some bandwidth reservation to user defined traffic classes, which are mapped to different queues via the mqprio qdisc. Only a simple software implementation is added for now. Signed-off-by: Vinicius Costa Gomes Signed-off-by: Jesus Sanchez-Palencia Tested-by: Henrik Austad Signed-off-by: Jeff Kirsher --- include/uapi/linux/pkt_sched.h | 19 +++ net/sched/Kconfig | 11 ++ net/sched/Makefile | 1 + net/sched/sch_cbs.c | 293 +++++++++++++++++++++++++++++++++++++++++ 4 files changed, 324 insertions(+) create mode 100644 net/sched/sch_cbs.c (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index e7cc3d3c7421..0e88cc262ca0 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -904,4 +904,23 @@ struct tc_pie_xstats { __u32 maxq; /* maximum queue size */ __u32 ecn_mark; /* packets marked with ecn*/ }; + +/* CBS */ +struct tc_cbs_qopt { + __u8 offload; + __u8 _pad[3]; + __s32 hicredit; + __s32 locredit; + __s32 idleslope; + __s32 sendslope; +}; + +enum { + TCA_CBS_UNSPEC, + TCA_CBS_PARMS, + __TCA_CBS_MAX, +}; + +#define TCA_CBS_MAX (__TCA_CBS_MAX - 1) + #endif diff --git a/net/sched/Kconfig b/net/sched/Kconfig index e70ed26485a2..c03d86a7775e 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -172,6 +172,17 @@ config NET_SCH_TBF To compile this code as a module, choose M here: the module will be called sch_tbf. +config NET_SCH_CBS + tristate "Credit Based Shaper (CBS)" + ---help--- + Say Y here if you want to use the Credit Based Shaper (CBS) packet + scheduling algorithm. + + See the top of for more details. + + To compile this code as a module, choose M here: the + module will be called sch_cbs. + config NET_SCH_GRED tristate "Generic Random Early Detection (GRED)" ---help--- diff --git a/net/sched/Makefile b/net/sched/Makefile index 7b915d226de7..80c8f92d162d 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -52,6 +52,7 @@ obj-$(CONFIG_NET_SCH_FQ_CODEL) += sch_fq_codel.o obj-$(CONFIG_NET_SCH_FQ) += sch_fq.o obj-$(CONFIG_NET_SCH_HHF) += sch_hhf.o obj-$(CONFIG_NET_SCH_PIE) += sch_pie.o +obj-$(CONFIG_NET_SCH_CBS) += sch_cbs.o obj-$(CONFIG_NET_CLS_U32) += cls_u32.o obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c new file mode 100644 index 000000000000..0e85133c5653 --- /dev/null +++ b/net/sched/sch_cbs.c @@ -0,0 +1,293 @@ +/* + * net/sched/sch_cbs.c Credit Based Shaper + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Authors: Vinicius Costa Gomes + * + */ + +/* Credit Based Shaper (CBS) + * ========================= + * + * This is a simple rate-limiting shaper aimed at TSN applications on + * systems with known traffic workloads. + * + * Its algorithm is defined by the IEEE 802.1Q-2014 Specification, + * Section 8.6.8.2, and explained in more detail in the Annex L of the + * same specification. + * + * There are four tunables to be considered: + * + * 'idleslope': Idleslope is the rate of credits that is + * accumulated (in kilobits per second) when there is at least + * one packet waiting for transmission. Packets are transmitted + * when the current value of credits is equal or greater than + * zero. When there is no packet to be transmitted the amount of + * credits is set to zero. This is the main tunable of the CBS + * algorithm. + * + * 'sendslope': + * Sendslope is the rate of credits that is depleted (it should be a + * negative number of kilobits per second) when a transmission is + * ocurring. It can be calculated as follows, (IEEE 802.1Q-2014 Section + * 8.6.8.2 item g): + * + * sendslope = idleslope - port_transmit_rate + * + * 'hicredit': Hicredit defines the maximum amount of credits (in + * bytes) that can be accumulated. Hicredit depends on the + * characteristics of interfering traffic, + * 'max_interference_size' is the maximum size of any burst of + * traffic that can delay the transmission of a frame that is + * available for transmission for this traffic class, (IEEE + * 802.1Q-2014 Annex L, Equation L-3): + * + * hicredit = max_interference_size * (idleslope / port_transmit_rate) + * + * 'locredit': Locredit is the minimum amount of credits that can + * be reached. It is a function of the traffic flowing through + * this qdisc (IEEE 802.1Q-2014 Annex L, Equation L-2): + * + * locredit = max_frame_size * (sendslope / port_transmit_rate) + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define BYTES_PER_KBIT (1000LL / 8) + +struct cbs_sched_data { + s64 port_rate; /* in bytes/s */ + s64 last; /* timestamp in ns */ + s64 credits; /* in bytes */ + s32 locredit; /* in bytes */ + s32 hicredit; /* in bytes */ + s64 sendslope; /* in bytes/s */ + s64 idleslope; /* in bytes/s */ + struct qdisc_watchdog watchdog; + int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch); + struct sk_buff *(*dequeue)(struct Qdisc *sch); +}; + +static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + + if (sch->q.qlen == 0 && q->credits > 0) { + /* We need to stop accumulating credits when there's + * no enqueued packets and q->credits is positive. + */ + q->credits = 0; + q->last = ktime_get_ns(); + } + + return qdisc_enqueue_tail(skb, sch); +} + +static int cbs_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + + return q->enqueue(skb, sch); +} + +/* timediff is in ns, slope is in bytes/s */ +static s64 timediff_to_credits(s64 timediff, s64 slope) +{ + return div64_s64(timediff * slope, NSEC_PER_SEC); +} + +static s64 delay_from_credits(s64 credits, s64 slope) +{ + if (unlikely(slope == 0)) + return S64_MAX; + + return div64_s64(-credits * NSEC_PER_SEC, slope); +} + +static s64 credits_from_len(unsigned int len, s64 slope, s64 port_rate) +{ + if (unlikely(port_rate == 0)) + return S64_MAX; + + return div64_s64(len * slope, port_rate); +} + +static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + s64 now = ktime_get_ns(); + struct sk_buff *skb; + s64 credits; + int len; + + if (q->credits < 0) { + credits = timediff_to_credits(now - q->last, q->idleslope); + + credits = q->credits + credits; + q->credits = min_t(s64, credits, q->hicredit); + + if (q->credits < 0) { + s64 delay; + + delay = delay_from_credits(q->credits, q->idleslope); + qdisc_watchdog_schedule_ns(&q->watchdog, now + delay); + + q->last = now; + + return NULL; + } + } + + skb = qdisc_dequeue_head(sch); + if (!skb) + return NULL; + + len = qdisc_pkt_len(skb); + + /* As sendslope is a negative number, this will decrease the + * amount of q->credits. + */ + credits = credits_from_len(len, q->sendslope, q->port_rate); + credits += q->credits; + + q->credits = max_t(s64, credits, q->locredit); + q->last = now; + + return skb; +} + +static struct sk_buff *cbs_dequeue(struct Qdisc *sch) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + + return q->dequeue(sch); +} + +static const struct nla_policy cbs_policy[TCA_CBS_MAX + 1] = { + [TCA_CBS_PARMS] = { .len = sizeof(struct tc_cbs_qopt) }, +}; + +static int cbs_change(struct Qdisc *sch, struct nlattr *opt) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct nlattr *tb[TCA_CBS_MAX + 1]; + struct ethtool_link_ksettings ecmd; + struct tc_cbs_qopt *qopt; + s64 link_speed; + int err; + + err = nla_parse_nested(tb, TCA_CBS_MAX, opt, cbs_policy, NULL); + if (err < 0) + return err; + + if (!tb[TCA_CBS_PARMS]) + return -EINVAL; + + qopt = nla_data(tb[TCA_CBS_PARMS]); + + if (qopt->offload) + return -EOPNOTSUPP; + + if (!__ethtool_get_link_ksettings(dev, &ecmd)) + link_speed = ecmd.base.speed; + else + link_speed = SPEED_1000; + + q->port_rate = link_speed * 1000 * BYTES_PER_KBIT; + + q->enqueue = cbs_enqueue_soft; + q->dequeue = cbs_dequeue_soft; + + q->hicredit = qopt->hicredit; + q->locredit = qopt->locredit; + q->idleslope = qopt->idleslope * BYTES_PER_KBIT; + q->sendslope = qopt->sendslope * BYTES_PER_KBIT; + + return 0; +} + +static int cbs_init(struct Qdisc *sch, struct nlattr *opt) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + + if (!opt) + return -EINVAL; + + qdisc_watchdog_init(&q->watchdog, sch); + + return cbs_change(sch, opt); +} + +static void cbs_destroy(struct Qdisc *sch) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + + qdisc_watchdog_cancel(&q->watchdog); +} + +static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct cbs_sched_data *q = qdisc_priv(sch); + struct tc_cbs_qopt opt = { }; + struct nlattr *nest; + + nest = nla_nest_start(skb, TCA_OPTIONS); + if (!nest) + goto nla_put_failure; + + opt.hicredit = q->hicredit; + opt.locredit = q->locredit; + opt.sendslope = div64_s64(q->sendslope, BYTES_PER_KBIT); + opt.idleslope = div64_s64(q->idleslope, BYTES_PER_KBIT); + opt.offload = 0; + + if (nla_put(skb, TCA_CBS_PARMS, sizeof(opt), &opt)) + goto nla_put_failure; + + return nla_nest_end(skb, nest); + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -1; +} + +static struct Qdisc_ops cbs_qdisc_ops __read_mostly = { + .id = "cbs", + .priv_size = sizeof(struct cbs_sched_data), + .enqueue = cbs_enqueue, + .dequeue = cbs_dequeue, + .peek = qdisc_peek_dequeued, + .init = cbs_init, + .reset = qdisc_reset_queue, + .destroy = cbs_destroy, + .change = cbs_change, + .dump = cbs_dump, + .owner = THIS_MODULE, +}; + +static int __init cbs_module_init(void) +{ + return register_qdisc(&cbs_qdisc_ops); +} + +static void __exit cbs_module_exit(void) +{ + unregister_qdisc(&cbs_qdisc_ops); +} +module_init(cbs_module_init) +module_exit(cbs_module_exit) +MODULE_LICENSE("GPL"); -- cgit v1.2.3-71-gd317 From 7e86a365a8319970e002f83c73701a86d95a69e6 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Fri, 27 Oct 2017 19:35:30 -0400 Subject: drm/amdkfd: increase limit of signal events to 4096 per process Signed-off-by: Oded Gabbay Reviewed-by: Ben Goz Signed-off-by: Felix Kuehling --- include/uapi/linux/kfd_ioctl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 26283fefdf5f..731d0df722e3 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -169,7 +169,7 @@ struct kfd_ioctl_dbg_wave_control_args { #define KFD_IOC_WAIT_RESULT_TIMEOUT 1 #define KFD_IOC_WAIT_RESULT_FAIL 2 -#define KFD_SIGNAL_EVENT_LIMIT 256 +#define KFD_SIGNAL_EVENT_LIMIT 4096 struct kfd_ioctl_create_event_args { __u64 event_page_offset; /* from KFD */ -- cgit v1.2.3-71-gd317 From bfa640757e9378c2f26867e723f1287e94f5a7ad Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 27 Oct 2017 09:45:53 -0700 Subject: bpf: rename sk_actions to align with bpf infrastructure Recent additions to support multiple programs in cgroups impose a strict requirement, "all yes is yes, any no is no". To enforce this the infrastructure requires the 'no' return code, SK_DROP in this case, to be 0. To apply these rules to SK_SKB program types the sk_actions return codes need to be adjusted. This fix adds SK_PASS and makes 'SK_DROP = 0'. Finally, remove SK_ABORTED to remove any chance that the API may allow aborted program flows to be passed up the stack. This would be incorrect behavior and allow programs to break existing policies. Signed-off-by: John Fastabend Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 6 +++--- kernel/bpf/sockmap.c | 3 ++- net/core/filter.c | 5 +++-- tools/include/uapi/linux/bpf.h | 4 ++-- 4 files changed, 10 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f90860d1f897..0d7948ce2128 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -575,7 +575,7 @@ union bpf_attr { * @map: pointer to sockmap * @key: key to lookup sock in map * @flags: reserved for future use - * Return: SK_REDIRECT + * Return: SK_PASS * * int bpf_sock_map_update(skops, map, key, flags) * @skops: pointer to bpf_sock_ops @@ -786,8 +786,8 @@ struct xdp_md { }; enum sk_action { - SK_ABORTED = 0, - SK_DROP, + SK_DROP = 0, + SK_PASS, SK_REDIRECT, }; diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 6778fb773934..66f00a2b27f4 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -122,7 +122,8 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) preempt_enable(); skb->sk = NULL; - return rc; + return rc == SK_PASS ? + (TCP_SKB_CB(skb)->bpf.map ? SK_REDIRECT : SK_PASS) : SK_DROP; } static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb) diff --git a/net/core/filter.c b/net/core/filter.c index 68eaa2f81a8e..6ae94f825f72 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1844,14 +1844,15 @@ BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb, { struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); + /* If user passes invalid input drop the packet. */ if (unlikely(flags)) - return SK_ABORTED; + return SK_DROP; tcb->bpf.key = key; tcb->bpf.flags = flags; tcb->bpf.map = map; - return SK_REDIRECT; + return SK_PASS; } struct sock *do_sk_redirect_map(struct sk_buff *skb) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 24b35a1fd4d6..c174971afbe6 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -787,8 +787,8 @@ struct xdp_md { }; enum sk_action { - SK_ABORTED = 0, - SK_DROP, + SK_DROP = 0, + SK_PASS, SK_REDIRECT, }; -- cgit v1.2.3-71-gd317 From 2ea2352ede9d97585164a7e19224955f4e4ca8db Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 27 Oct 2017 17:30:12 -0700 Subject: ipv6: prevent user from adding cached routes Cached routes should only be created by the system when receiving pmtu discovery or ip redirect msg. Users should not be allowed to create cached routes. Furthermore, after the patch series to move cached routes into exception table, user added cached routes will trigger the following warning in fib6_add(): WARNING: CPU: 0 PID: 2985 at net/ipv6/ip6_fib.c:1137 fib6_add+0x20d9/0x2c10 net/ipv6/ip6_fib.c:1137 Kernel panic - not syncing: panic_on_warn set ... CPU: 0 PID: 2985 Comm: syzkaller320388 Not tainted 4.14.0-rc3+ #74 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:16 [inline] dump_stack+0x194/0x257 lib/dump_stack.c:52 panic+0x1e4/0x417 kernel/panic.c:181 __warn+0x1c4/0x1d9 kernel/panic.c:542 report_bug+0x211/0x2d0 lib/bug.c:183 fixup_bug+0x40/0x90 arch/x86/kernel/traps.c:178 do_trap_no_signal arch/x86/kernel/traps.c:212 [inline] do_trap+0x260/0x390 arch/x86/kernel/traps.c:261 do_error_trap+0x120/0x390 arch/x86/kernel/traps.c:298 do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:311 invalid_op+0x18/0x20 arch/x86/entry/entry_64.S:905 RIP: 0010:fib6_add+0x20d9/0x2c10 net/ipv6/ip6_fib.c:1137 RSP: 0018:ffff8801cf09f6a0 EFLAGS: 00010297 RAX: ffff8801ce45e340 RBX: 1ffff10039e13eec RCX: ffff8801d749c814 RDX: 0000000000000000 RSI: ffff8801d749c700 RDI: ffff8801d749c780 RBP: ffff8801cf09fa08 R08: 0000000000000000 R09: ffff8801cf09f360 R10: ffff8801cf09f2d8 R11: 1ffff10039c8befb R12: 0000000000000001 R13: dffffc0000000000 R14: ffff8801d749c700 R15: ffffffff860655c0 __ip6_ins_rt+0x6c/0x90 net/ipv6/route.c:1011 ip6_route_add+0x148/0x1a0 net/ipv6/route.c:2782 ipv6_route_ioctl+0x4d5/0x690 net/ipv6/route.c:3291 inet6_ioctl+0xef/0x1e0 net/ipv6/af_inet6.c:521 sock_do_ioctl+0x65/0xb0 net/socket.c:961 sock_ioctl+0x2c2/0x440 net/socket.c:1058 vfs_ioctl fs/ioctl.c:45 [inline] do_vfs_ioctl+0x1b1/0x1530 fs/ioctl.c:685 SYSC_ioctl fs/ioctl.c:700 [inline] SyS_ioctl+0x8f/0xc0 fs/ioctl.c:691 entry_SYSCALL_64_fastpath+0x1f/0xbe So we fix this by failing the attemp to add cached routes from userspace with returning EINVAL error. Fixes: 2b760fcf5cfb ("ipv6: hook up exception table to store dst cache") Signed-off-by: Wei Wang Signed-off-by: Eric Dumazet Acked-by: Martin KaFai Lau Signed-off-by: David S. Miller --- include/uapi/linux/ipv6_route.h | 2 +- net/ipv6/route.c | 6 ++++++ 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ipv6_route.h b/include/uapi/linux/ipv6_route.h index d496c02e14bc..c15d8054905c 100644 --- a/include/uapi/linux/ipv6_route.h +++ b/include/uapi/linux/ipv6_route.h @@ -28,7 +28,7 @@ #define RTF_ROUTEINFO 0x00800000 /* route information - RA */ -#define RTF_CACHE 0x01000000 /* cache entry */ +#define RTF_CACHE 0x01000000 /* read-only: can not be set by user */ #define RTF_FLOW 0x02000000 /* flow significant route */ #define RTF_POLICY 0x04000000 /* policy route */ diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 605e5dc1c010..70d9659fc1e9 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2478,6 +2478,12 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, goto out; } + /* RTF_CACHE is an internal flag; can not be set by userspace */ + if (cfg->fc_flags & RTF_CACHE) { + NL_SET_ERR_MSG(extack, "Userspace can not set RTF_CACHE"); + goto out; + } + if (cfg->fc_dst_len > 128) { NL_SET_ERR_MSG(extack, "Invalid prefix length"); goto out; -- cgit v1.2.3-71-gd317 From 978aa0474115f3f5848949f2efce4def0766a5cb Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 28 Oct 2017 19:43:57 +0800 Subject: sctp: fix some type cast warnings introduced since very beginning These warnings were found by running 'make C=2 M=net/sctp/'. They are there since very beginning. Note after this patch, there still one warning left in sctp_outq_flush(): sctp_chunk_fail(chunk, SCTP_ERROR_INV_STRM) Since it has been moved to sctp_stream_outq_migrate on net-next, to avoid the extra job when merging net-next to net, I will post the fix for it after the merging is done. Reported-by: Eric Dumazet Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 2 +- include/uapi/linux/sctp.h | 2 +- net/sctp/ipv6.c | 2 +- net/sctp/sm_make_chunk.c | 4 ++-- net/sctp/sm_sideeffect.c | 4 ++-- 5 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 09d7412e9cb0..da803dfc7a39 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -231,7 +231,7 @@ struct sctp_datahdr { __be32 tsn; __be16 stream; __be16 ssn; - __be32 ppid; + __u32 ppid; __u8 payload[0]; }; diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 6217ff8500a1..84fc2914b7fb 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -376,7 +376,7 @@ struct sctp_remote_error { __u16 sre_type; __u16 sre_flags; __u32 sre_length; - __u16 sre_error; + __be16 sre_error; sctp_assoc_t sre_assoc_id; __u8 sre_data[0]; }; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 7fe9e1d1b7ec..a6dfa86c0201 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -738,7 +738,7 @@ static int sctp_v6_skb_iif(const struct sk_buff *skb) /* Was this packet marked by Explicit Congestion Notification? */ static int sctp_v6_is_ce(const struct sk_buff *skb) { - return *((__u32 *)(ipv6_hdr(skb))) & htonl(1 << 20); + return *((__u32 *)(ipv6_hdr(skb))) & (__force __u32)htonl(1 << 20); } /* Dump the v6 addr to the seq file. */ diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 57c55045f5a7..514465b03829 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2854,7 +2854,7 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *asoc, addr_param_len = af->to_addr_param(addr, &addr_param); param.param_hdr.type = flags; param.param_hdr.length = htons(paramlen + addr_param_len); - param.crr_id = i; + param.crr_id = htonl(i); sctp_addto_chunk(retval, paramlen, ¶m); sctp_addto_chunk(retval, addr_param_len, &addr_param); @@ -2867,7 +2867,7 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *asoc, addr_param_len = af->to_addr_param(addr, &addr_param); param.param_hdr.type = SCTP_PARAM_DEL_IP; param.param_hdr.length = htons(paramlen + addr_param_len); - param.crr_id = i; + param.crr_id = htonl(i); sctp_addto_chunk(retval, paramlen, ¶m); sctp_addto_chunk(retval, addr_param_len, &addr_param); diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 8f2762bba879..e2d9a4b49c9c 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1607,12 +1607,12 @@ static int sctp_cmd_interpreter(enum sctp_event event_type, break; case SCTP_CMD_INIT_FAILED: - sctp_cmd_init_failed(commands, asoc, cmd->obj.err); + sctp_cmd_init_failed(commands, asoc, cmd->obj.u32); break; case SCTP_CMD_ASSOC_FAILED: sctp_cmd_assoc_failed(commands, asoc, event_type, - subtype, chunk, cmd->obj.err); + subtype, chunk, cmd->obj.u32); break; case SCTP_CMD_INIT_COUNTER_INC: -- cgit v1.2.3-71-gd317 From a190d04db93710ae166749055b6985397c6d13f5 Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Thu, 26 Oct 2017 15:09:21 -0700 Subject: ipvlan: introduce 'private' attribute for all existing modes. IPvlan has always operated in bridge mode. However there are scenarios where each slave should be able to talk through the master device but not necessarily across each other. Think of an environment where each of a namespace is a private and independant customer. In this scenario the machine which is hosting these namespaces neither want to tell who their neighbor is nor the individual namespaces care to talk to neighbor on short-circuited network path. This patch implements the mode that is very similar to the 'private' mode in macvlan where individual slaves can send and receive traffic through the master device, just that they can not talk among slave devices. Signed-off-by: Mahesh Bandewar Signed-off-by: David S. Miller --- Documentation/networking/ipvlan.txt | 30 ++++++++++++++++++++++++++--- drivers/net/ipvlan/ipvlan.h | 16 ++++++++++++++++ drivers/net/ipvlan/ipvlan_core.c | 15 ++++++++++++--- drivers/net/ipvlan/ipvlan_main.c | 38 +++++++++++++++++++++++++++++++++++-- include/uapi/linux/if_link.h | 3 +++ 5 files changed, 94 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ipvlan.txt b/Documentation/networking/ipvlan.txt index 1fe42a874aae..bfa91c77a4c9 100644 --- a/Documentation/networking/ipvlan.txt +++ b/Documentation/networking/ipvlan.txt @@ -22,9 +22,19 @@ The driver can be built into the kernel (CONFIG_IPVLAN=y) or as a module There are no module parameters for this driver and it can be configured using IProute2/ip utility. - ip link add link name type ipvlan mode { l2 | l3 | l3s } + ip link add link name type ipvlan [ mode MODE ] [ FLAGS ] + where + MODE: l3 (default) | l3s | l2 + FLAGS: bridge (default) | private - e.g. ip link add link eth0 name ipvl0 type ipvlan mode l2 + e.g. + (a) Following will create IPvlan link with eth0 as master in + L3 bridge mode + bash# ip link add link eth0 name ipvl0 type ipvlan + (b) This command will create IPvlan link in L2 bridge mode. + bash# ip link add link eth0 name ipvl0 type ipvlan mode l2 bridge + (c) This command will create an IPvlan device in L2 private mode. + bash# ip link add link eth0 name ipvlan type ipvlan mode l2 private 4. Operating modes: @@ -54,7 +64,21 @@ works in this mode and hence it is L3-symmetric (L3s). This will have slightly l performance but that shouldn't matter since you are choosing this mode over plain-L3 mode to make conn-tracking work. -5. What to choose (macvlan vs. ipvlan)? +5. Mode flags: + At this time following mode flags are available + +5.1 bridge: + This is the default option. To configure the IPvlan port in this mode, +user can choose to either add this option on the command-line or don't specify +anything. This is the traditional mode where slaves can cross-talk among +themseleves apart from talking through the master device. + +5.2 private: + If this option is added to the command-line, the port is set in private +mode. i.e. port wont allow cross communication between slaves. + + +6. What to choose (macvlan vs. ipvlan)? These two devices are very similar in many regards and the specific use case could very well define which device to choose. if one of the following situations defines your use case then you can choose to use ipvlan - diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h index ba8173a0b62e..9941851bcc13 100644 --- a/drivers/net/ipvlan/ipvlan.h +++ b/drivers/net/ipvlan/ipvlan.h @@ -96,6 +96,7 @@ struct ipvl_port { struct hlist_head hlhead[IPVLAN_HASH_SIZE]; struct list_head ipvlans; u16 mode; + u16 flags; u16 dev_id_start; struct work_struct wq; struct sk_buff_head backlog; @@ -123,6 +124,21 @@ static inline struct ipvl_port *ipvlan_port_get_rtnl(const struct net_device *d) return rtnl_dereference(d->rx_handler_data); } +static inline bool ipvlan_is_private(const struct ipvl_port *port) +{ + return !!(port->flags & IPVLAN_F_PRIVATE); +} + +static inline void ipvlan_mark_private(struct ipvl_port *port) +{ + port->flags |= IPVLAN_F_PRIVATE; +} + +static inline void ipvlan_clear_private(struct ipvl_port *port) +{ + port->flags &= ~IPVLAN_F_PRIVATE; +} + void ipvlan_init_secret(void); unsigned int ipvlan_mac_hash(const unsigned char *addr); rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb); diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 1f3295e274d0..72fd56de9c00 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -515,9 +515,13 @@ static int ipvlan_xmit_mode_l3(struct sk_buff *skb, struct net_device *dev) goto out; addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true); - if (addr) + if (addr) { + if (ipvlan_is_private(ipvlan->port)) { + consume_skb(skb); + return NET_XMIT_DROP; + } return ipvlan_rcv_frame(addr, &skb, true); - + } out: ipvlan_skb_crossing_ns(skb, ipvlan->phy_dev); return ipvlan_process_outbound(skb); @@ -535,8 +539,13 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev) lyr3h = ipvlan_get_L3_hdr(skb, &addr_type); if (lyr3h) { addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true); - if (addr) + if (addr) { + if (ipvlan_is_private(ipvlan->port)) { + consume_skb(skb); + return NET_XMIT_DROP; + } return ipvlan_rcv_frame(addr, &skb, true); + } } skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index f0ab55df57f1..4368afb1934c 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -462,11 +462,24 @@ static int ipvlan_nl_changelink(struct net_device *dev, struct ipvl_port *port = ipvlan_port_get_rtnl(ipvlan->phy_dev); int err = 0; - if (data && data[IFLA_IPVLAN_MODE]) { + if (!data) + return 0; + + if (data[IFLA_IPVLAN_MODE]) { u16 nmode = nla_get_u16(data[IFLA_IPVLAN_MODE]); err = ipvlan_set_port_mode(port, nmode); } + + if (!err && data[IFLA_IPVLAN_FLAGS]) { + u16 flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]); + + if (flags & IPVLAN_F_PRIVATE) + ipvlan_mark_private(port); + else + ipvlan_clear_private(port); + } + return err; } @@ -474,18 +487,30 @@ static size_t ipvlan_nl_getsize(const struct net_device *dev) { return (0 + nla_total_size(2) /* IFLA_IPVLAN_MODE */ + + nla_total_size(2) /* IFLA_IPVLAN_FLAGS */ ); } static int ipvlan_nl_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { - if (data && data[IFLA_IPVLAN_MODE]) { + if (!data) + return 0; + + if (data[IFLA_IPVLAN_MODE]) { u16 mode = nla_get_u16(data[IFLA_IPVLAN_MODE]); if (mode < IPVLAN_MODE_L2 || mode >= IPVLAN_MODE_MAX) return -EINVAL; } + if (data[IFLA_IPVLAN_FLAGS]) { + u16 flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]); + + /* Only one bit is used at this moment. */ + if (flags & ~IPVLAN_F_PRIVATE) + return -EINVAL; + } + return 0; } @@ -502,6 +527,8 @@ static int ipvlan_nl_fillinfo(struct sk_buff *skb, ret = -EMSGSIZE; if (nla_put_u16(skb, IFLA_IPVLAN_MODE, port->mode)) goto err; + if (nla_put_u16(skb, IFLA_IPVLAN_FLAGS, port->flags)) + goto err; return 0; @@ -549,6 +576,12 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev, ipvlan_adjust_mtu(ipvlan, phy_dev); INIT_LIST_HEAD(&ipvlan->addrs); + /* Flags are per port and latest update overrides. User has + * to be consistent in setting it just like the mode attribute. + */ + if (data && data[IFLA_IPVLAN_FLAGS]) + ipvlan->port->flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]); + /* If the port-id base is at the MAX value, then wrap it around and * begin from 0x1 again. This may be due to a busy system where lots * of slaves are getting created and deleted. @@ -644,6 +677,7 @@ EXPORT_SYMBOL_GPL(ipvlan_link_setup); static const struct nla_policy ipvlan_nl_policy[IFLA_IPVLAN_MAX + 1] = { [IFLA_IPVLAN_MODE] = { .type = NLA_U16 }, + [IFLA_IPVLAN_FLAGS] = { .type = NLA_U16 }, }; static struct rtnl_link_ops ipvlan_link_ops = { diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index b037e0ab1975..052e32cd584c 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -465,6 +465,7 @@ enum macsec_validation_type { enum { IFLA_IPVLAN_UNSPEC, IFLA_IPVLAN_MODE, + IFLA_IPVLAN_FLAGS, __IFLA_IPVLAN_MAX }; @@ -477,6 +478,8 @@ enum ipvlan_mode { IPVLAN_MODE_MAX }; +#define IPVLAN_F_PRIVATE 0x01 + /* VXLAN section */ enum { IFLA_VXLAN_UNSPEC, -- cgit v1.2.3-71-gd317 From fe89aa6b250c1011ccf425fbb7998e96bd54263f Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Thu, 26 Oct 2017 15:09:25 -0700 Subject: ipvlan: implement VEPA mode This is very similar to the Macvlan VEPA mode, however, there is some difference. IPvlan uses the mac-address of the lower device, so the VEPA mode has implications of ICMP-redirects for packets destined for its immediate neighbors sharing same master since the packets will have same source and dest mac. The external switch/router will send redirect msg. Having said that, this will be useful tool in terms of debugging since IPvlan will not switch packets within its slaves and rely completely on the external entity as intended in 802.1Qbg. Signed-off-by: Mahesh Bandewar Signed-off-by: David S. Miller --- Documentation/networking/ipvlan.txt | 12 +++++++++++- drivers/net/ipvlan/ipvlan.h | 15 +++++++++++++++ drivers/net/ipvlan/ipvlan_core.c | 17 ++++++++++------- drivers/net/ipvlan/ipvlan_main.c | 13 +++++++++++-- include/uapi/linux/if_link.h | 1 + 5 files changed, 48 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ipvlan.txt b/Documentation/networking/ipvlan.txt index bfa91c77a4c9..812ef003e0a8 100644 --- a/Documentation/networking/ipvlan.txt +++ b/Documentation/networking/ipvlan.txt @@ -25,7 +25,7 @@ using IProute2/ip utility. ip link add link name type ipvlan [ mode MODE ] [ FLAGS ] where MODE: l3 (default) | l3s | l2 - FLAGS: bridge (default) | private + FLAGS: bridge (default) | private | vepa e.g. (a) Following will create IPvlan link with eth0 as master in @@ -35,6 +35,8 @@ using IProute2/ip utility. bash# ip link add link eth0 name ipvl0 type ipvlan mode l2 bridge (c) This command will create an IPvlan device in L2 private mode. bash# ip link add link eth0 name ipvlan type ipvlan mode l2 private + (d) This command will create an IPvlan device in L2 vepa mode. + bash# ip link add link eth0 name ipvlan type ipvlan mode l2 vepa 4. Operating modes: @@ -77,6 +79,14 @@ themseleves apart from talking through the master device. If this option is added to the command-line, the port is set in private mode. i.e. port wont allow cross communication between slaves. +5.3 vepa: + If this is added to the command-line, the port is set in VEPA mode. +i.e. port will offload switching functionality to the external entity as +described in 802.1Qbg +Note: VEPA mode in IPvlan has limitations. IPvlan uses the mac-address of the +master-device, so the packets which are emitted in this mode for the adjacent +neighbor will have source and destination mac same. This will make the switch / +router send the redirect message. 6. What to choose (macvlan vs. ipvlan)? These two devices are very similar in many regards and the specific use diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h index 9941851bcc13..5166575a164d 100644 --- a/drivers/net/ipvlan/ipvlan.h +++ b/drivers/net/ipvlan/ipvlan.h @@ -139,6 +139,21 @@ static inline void ipvlan_clear_private(struct ipvl_port *port) port->flags &= ~IPVLAN_F_PRIVATE; } +static inline bool ipvlan_is_vepa(const struct ipvl_port *port) +{ + return !!(port->flags & IPVLAN_F_VEPA); +} + +static inline void ipvlan_mark_vepa(struct ipvl_port *port) +{ + port->flags |= IPVLAN_F_VEPA; +} + +static inline void ipvlan_clear_vepa(struct ipvl_port *port) +{ + port->flags &= ~IPVLAN_F_VEPA; +} + void ipvlan_init_secret(void); unsigned int ipvlan_mac_hash(const unsigned char *addr); rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb); diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 72fd56de9c00..034ae4c57196 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -514,13 +514,15 @@ static int ipvlan_xmit_mode_l3(struct sk_buff *skb, struct net_device *dev) if (!lyr3h) goto out; - addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true); - if (addr) { - if (ipvlan_is_private(ipvlan->port)) { - consume_skb(skb); - return NET_XMIT_DROP; + if (!ipvlan_is_vepa(ipvlan->port)) { + addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true); + if (addr) { + if (ipvlan_is_private(ipvlan->port)) { + consume_skb(skb); + return NET_XMIT_DROP; + } + return ipvlan_rcv_frame(addr, &skb, true); } - return ipvlan_rcv_frame(addr, &skb, true); } out: ipvlan_skb_crossing_ns(skb, ipvlan->phy_dev); @@ -535,7 +537,8 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev) void *lyr3h; int addr_type; - if (ether_addr_equal(eth->h_dest, eth->h_source)) { + if (!ipvlan_is_vepa(ipvlan->port) && + ether_addr_equal(eth->h_dest, eth->h_source)) { lyr3h = ipvlan_get_L3_hdr(skb, &addr_type); if (lyr3h) { addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true); diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 4368afb1934c..a266aa435d4d 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -478,6 +478,11 @@ static int ipvlan_nl_changelink(struct net_device *dev, ipvlan_mark_private(port); else ipvlan_clear_private(port); + + if (flags & IPVLAN_F_VEPA) + ipvlan_mark_vepa(port); + else + ipvlan_clear_vepa(port); } return err; @@ -506,8 +511,12 @@ static int ipvlan_nl_validate(struct nlattr *tb[], struct nlattr *data[], if (data[IFLA_IPVLAN_FLAGS]) { u16 flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]); - /* Only one bit is used at this moment. */ - if (flags & ~IPVLAN_F_PRIVATE) + /* Only two bits are used at this moment. */ + if (flags & ~(IPVLAN_F_PRIVATE | IPVLAN_F_VEPA)) + return -EINVAL; + /* Also both flags can't be active at the same time. */ + if ((flags & (IPVLAN_F_PRIVATE | IPVLAN_F_VEPA)) == + (IPVLAN_F_PRIVATE | IPVLAN_F_VEPA)) return -EINVAL; } diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 052e32cd584c..81f26473d728 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -479,6 +479,7 @@ enum ipvlan_mode { }; #define IPVLAN_F_PRIVATE 0x01 +#define IPVLAN_F_VEPA 0x02 /* VXLAN section */ enum { -- cgit v1.2.3-71-gd317 From 40c3c40947324d9f40bf47830c92c59a9bbadf4a Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Wed, 23 Aug 2017 16:57:58 +0900 Subject: btrfs: Add sanity check for EXTENT_DATA when reading out leaf Add extra checks for item with EXTENT_DATA type. This checks the following thing: 0) Key offset All key offsets must be aligned to sectorsize. Inline extent must have 0 for key offset. 1) Item size Uncompressed inline file extent size must match item size. (Compressed inline file extent has no information about its on-disk size.) Regular/preallocated file extent size must be a fixed value. 2) Every member of regular file extent item Including alignment for bytenr and offset, possible value for compression/encryption/type. 3) Type/compression/encode must be one of the valid values. This should be the most comprehensive and strict check in the context of btrfs_item for EXTENT_DATA. Signed-off-by: Qu Wenruo Reviewed-by: Nikolay Borisov Reviewed-by: David Sterba [ switch to BTRFS_FILE_EXTENT_TYPES, similar to what BTRFS_COMPRESS_TYPES does ] Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 103 ++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/btrfs_tree.h | 1 + 2 files changed, 104 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index d1770b3e0385..b863d41f7d0a 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -549,6 +549,100 @@ static int check_tree_block_fsid(struct btrfs_fs_info *fs_info, btrfs_header_level(eb) == 0 ? "leaf" : "node", \ reason, btrfs_header_bytenr(eb), root->objectid, slot) +static int check_extent_data_item(struct btrfs_root *root, + struct extent_buffer *leaf, + struct btrfs_key *key, int slot) +{ + struct btrfs_file_extent_item *fi; + u32 sectorsize = root->fs_info->sectorsize; + u32 item_size = btrfs_item_size_nr(leaf, slot); + + if (!IS_ALIGNED(key->offset, sectorsize)) { + CORRUPT("unaligned key offset for file extent", + leaf, root, slot); + return -EUCLEAN; + } + + fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); + + if (btrfs_file_extent_type(leaf, fi) > BTRFS_FILE_EXTENT_TYPES) { + CORRUPT("invalid file extent type", leaf, root, slot); + return -EUCLEAN; + } + + /* + * Support for new compression/encrption must introduce incompat flag, + * and must be caught in open_ctree(). + */ + if (btrfs_file_extent_compression(leaf, fi) > BTRFS_COMPRESS_TYPES) { + CORRUPT("invalid file extent compression", leaf, root, slot); + return -EUCLEAN; + } + if (btrfs_file_extent_encryption(leaf, fi)) { + CORRUPT("invalid file extent encryption", leaf, root, slot); + return -EUCLEAN; + } + if (btrfs_file_extent_type(leaf, fi) == BTRFS_FILE_EXTENT_INLINE) { + /* Inline extent must have 0 as key offset */ + if (key->offset) { + CORRUPT("inline extent has non-zero key offset", + leaf, root, slot); + return -EUCLEAN; + } + + /* Compressed inline extent has no on-disk size, skip it */ + if (btrfs_file_extent_compression(leaf, fi) != + BTRFS_COMPRESS_NONE) + return 0; + + /* Uncompressed inline extent size must match item size */ + if (item_size != BTRFS_FILE_EXTENT_INLINE_DATA_START + + btrfs_file_extent_ram_bytes(leaf, fi)) { + CORRUPT("plaintext inline extent has invalid size", + leaf, root, slot); + return -EUCLEAN; + } + return 0; + } + + /* Regular or preallocated extent has fixed item size */ + if (item_size != sizeof(*fi)) { + CORRUPT( + "regluar or preallocated extent data item size is invalid", + leaf, root, slot); + return -EUCLEAN; + } + if (!IS_ALIGNED(btrfs_file_extent_ram_bytes(leaf, fi), sectorsize) || + !IS_ALIGNED(btrfs_file_extent_disk_bytenr(leaf, fi), sectorsize) || + !IS_ALIGNED(btrfs_file_extent_disk_num_bytes(leaf, fi), sectorsize) || + !IS_ALIGNED(btrfs_file_extent_offset(leaf, fi), sectorsize) || + !IS_ALIGNED(btrfs_file_extent_num_bytes(leaf, fi), sectorsize)) { + CORRUPT( + "regular or preallocated extent data item has unaligned value", + leaf, root, slot); + return -EUCLEAN; + } + + return 0; +} + +/* + * Common point to switch the item-specific validation. + */ +static int check_leaf_item(struct btrfs_root *root, + struct extent_buffer *leaf, + struct btrfs_key *key, int slot) +{ + int ret = 0; + + switch (key->type) { + case BTRFS_EXTENT_DATA_KEY: + ret = check_extent_data_item(root, leaf, key, slot); + break; + } + return ret; +} + static noinline int check_leaf(struct btrfs_root *root, struct extent_buffer *leaf) { @@ -605,9 +699,13 @@ static noinline int check_leaf(struct btrfs_root *root, * 1) key order * 2) item offset and size * No overlap, no hole, all inside the leaf. + * 3) item content + * If possible, do comprehensive sanity check. + * NOTE: All checks must only rely on the item data itself. */ for (slot = 0; slot < nritems; slot++) { u32 item_end_expected; + int ret; btrfs_item_key_to_cpu(leaf, &key, slot); @@ -650,6 +748,11 @@ static noinline int check_leaf(struct btrfs_root *root, return -EUCLEAN; } + /* Check if the item size and content meet other criteria */ + ret = check_leaf_item(root, leaf, &key, slot); + if (ret < 0) + return ret; + prev_key.objectid = key.objectid; prev_key.type = key.type; prev_key.offset = key.offset; diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index 10689e1fdf11..3142645a27f5 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -732,6 +732,7 @@ struct btrfs_balance_item { #define BTRFS_FILE_EXTENT_INLINE 0 #define BTRFS_FILE_EXTENT_REG 1 #define BTRFS_FILE_EXTENT_PREALLOC 2 +#define BTRFS_FILE_EXTENT_TYPES 2 struct btrfs_file_extent_item { /* -- cgit v1.2.3-71-gd317 From cb91775711b2f3f7adea8d33aa83104baf75ee07 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 19 Oct 2017 16:47:49 +0200 Subject: isofs: use unsigned char types consistently Based on the discussion about the signed character field for the year, I went through all fields in the iso9660 and rockridge standards to see whether they should used signed or unsigned characters. Only a single 8-bit value is defined as signed per 'section 7.1.2': the timezone offset in a timestamp, this has always been handled correctly through explicit sign-extension. All others are either '7.1.1 8-bit unsigned numerical values' or composite fields. I also read the linux source code and came to the same conclusion, also I could not find any other part of the implementation that actually behaves differently for signed or unsigned values. Since it is still ambigous to use plain 'char' in interface definitions, I'm changing all fields representing numbers and reserved bytes to the unambiguous '__u8'. Fields that hold actual strings are left as 'char' arrays. I built the code with '-Wpointer-sign -Wsign-compare' to see if anything got left out, but couldn't find anything wrong with the remaining warnings. This patch should not change runtime behavior and does not need to be backported. Signed-off-by: Arnd Bergmann Signed-off-by: Jan Kara --- fs/isofs/isofs.h | 20 +++--- fs/isofs/rock.h | 62 ++++++++--------- include/uapi/linux/iso_fs.h | 162 ++++++++++++++++++++++---------------------- 3 files changed, 122 insertions(+), 122 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/isofs/isofs.h b/fs/isofs/isofs.h index bd4047585431..c882f207dd5c 100644 --- a/fs/isofs/isofs.h +++ b/fs/isofs/isofs.h @@ -72,36 +72,36 @@ static inline struct iso_inode_info *ISOFS_I(struct inode *inode) return container_of(inode, struct iso_inode_info, vfs_inode); } -static inline int isonum_711(char *p) +static inline int isonum_711(u8 *p) { - return *(u8 *)p; + return *p; } -static inline int isonum_712(char *p) +static inline int isonum_712(s8 *p) { - return *(s8 *)p; + return *p; } -static inline unsigned int isonum_721(char *p) +static inline unsigned int isonum_721(u8 *p) { return get_unaligned_le16(p); } -static inline unsigned int isonum_722(char *p) +static inline unsigned int isonum_722(u8 *p) { return get_unaligned_be16(p); } -static inline unsigned int isonum_723(char *p) +static inline unsigned int isonum_723(u8 *p) { /* Ignore bigendian datum due to broken mastering programs */ return get_unaligned_le16(p); } -static inline unsigned int isonum_731(char *p) +static inline unsigned int isonum_731(u8 *p) { return get_unaligned_le32(p); } -static inline unsigned int isonum_732(char *p) +static inline unsigned int isonum_732(u8 *p) { return get_unaligned_be32(p); } -static inline unsigned int isonum_733(char *p) +static inline unsigned int isonum_733(u8 *p) { /* Ignore bigendian datum due to broken mastering programs */ return get_unaligned_le32(p); diff --git a/fs/isofs/rock.h b/fs/isofs/rock.h index f835976ce033..8780d67c6ca5 100644 --- a/fs/isofs/rock.h +++ b/fs/isofs/rock.h @@ -6,62 +6,62 @@ */ struct SU_SP_s { - unsigned char magic[2]; - unsigned char skip; + __u8 magic[2]; + __u8 skip; } __attribute__ ((packed)); struct SU_CE_s { - char extent[8]; - char offset[8]; - char size[8]; + __u8 extent[8]; + __u8 offset[8]; + __u8 size[8]; }; struct SU_ER_s { - unsigned char len_id; - unsigned char len_des; - unsigned char len_src; - unsigned char ext_ver; - char data[0]; + __u8 len_id; + __u8 len_des; + __u8 len_src; + __u8 ext_ver; + __u8 data[0]; } __attribute__ ((packed)); struct RR_RR_s { - char flags[1]; + __u8 flags[1]; } __attribute__ ((packed)); struct RR_PX_s { - char mode[8]; - char n_links[8]; - char uid[8]; - char gid[8]; + __u8 mode[8]; + __u8 n_links[8]; + __u8 uid[8]; + __u8 gid[8]; }; struct RR_PN_s { - char dev_high[8]; - char dev_low[8]; + __u8 dev_high[8]; + __u8 dev_low[8]; }; struct SL_component { - unsigned char flags; - unsigned char len; - char text[0]; + __u8 flags; + __u8 len; + __u8 text[0]; } __attribute__ ((packed)); struct RR_SL_s { - unsigned char flags; + __u8 flags; struct SL_component link; } __attribute__ ((packed)); struct RR_NM_s { - unsigned char flags; + __u8 flags; char name[0]; } __attribute__ ((packed)); struct RR_CL_s { - char location[8]; + __u8 location[8]; }; struct RR_PL_s { - char location[8]; + __u8 location[8]; }; struct stamp { @@ -69,15 +69,15 @@ struct stamp { } __attribute__ ((packed)); struct RR_TF_s { - char flags; + __u8 flags; struct stamp times[0]; /* Variable number of these beasts */ } __attribute__ ((packed)); /* Linux-specific extension for transparent decompression */ struct RR_ZF_s { - char algorithm[2]; - char parms[2]; - char real_size[8]; + __u8 algorithm[2]; + __u8 parms[2]; + __u8 real_size[8]; }; /* @@ -93,9 +93,9 @@ struct RR_ZF_s { #define TF_LONG_FORM 128 struct rock_ridge { - char signature[2]; - unsigned char len; - unsigned char version; + __u8 signature[2]; + __u8 len; + __u8 version; union { struct SU_SP_s SP; struct SU_CE_s CE; diff --git a/include/uapi/linux/iso_fs.h b/include/uapi/linux/iso_fs.h index 4688ac4284e2..07c4c6405b3c 100644 --- a/include/uapi/linux/iso_fs.h +++ b/include/uapi/linux/iso_fs.h @@ -12,10 +12,10 @@ #define ISODCL(from, to) (to - from + 1) struct iso_volume_descriptor { - char type[ISODCL(1,1)]; /* 711 */ + __u8 type[ISODCL(1,1)]; /* 711 */ char id[ISODCL(2,6)]; - char version[ISODCL(7,7)]; - char data[ISODCL(8,2048)]; + __u8 version[ISODCL(7,7)]; + __u8 data[ISODCL(8,2048)]; }; /* volume descriptor types */ @@ -26,24 +26,24 @@ struct iso_volume_descriptor { #define ISO_STANDARD_ID "CD001" struct iso_primary_descriptor { - char type [ISODCL ( 1, 1)]; /* 711 */ + __u8 type [ISODCL ( 1, 1)]; /* 711 */ char id [ISODCL ( 2, 6)]; - char version [ISODCL ( 7, 7)]; /* 711 */ - char unused1 [ISODCL ( 8, 8)]; + __u8 version [ISODCL ( 7, 7)]; /* 711 */ + __u8 unused1 [ISODCL ( 8, 8)]; char system_id [ISODCL ( 9, 40)]; /* achars */ char volume_id [ISODCL ( 41, 72)]; /* dchars */ - char unused2 [ISODCL ( 73, 80)]; - char volume_space_size [ISODCL ( 81, 88)]; /* 733 */ - char unused3 [ISODCL ( 89, 120)]; - char volume_set_size [ISODCL (121, 124)]; /* 723 */ - char volume_sequence_number [ISODCL (125, 128)]; /* 723 */ - char logical_block_size [ISODCL (129, 132)]; /* 723 */ - char path_table_size [ISODCL (133, 140)]; /* 733 */ - char type_l_path_table [ISODCL (141, 144)]; /* 731 */ - char opt_type_l_path_table [ISODCL (145, 148)]; /* 731 */ - char type_m_path_table [ISODCL (149, 152)]; /* 732 */ - char opt_type_m_path_table [ISODCL (153, 156)]; /* 732 */ - char root_directory_record [ISODCL (157, 190)]; /* 9.1 */ + __u8 unused2 [ISODCL ( 73, 80)]; + __u8 volume_space_size [ISODCL ( 81, 88)]; /* 733 */ + __u8 unused3 [ISODCL ( 89, 120)]; + __u8 volume_set_size [ISODCL (121, 124)]; /* 723 */ + __u8 volume_sequence_number [ISODCL (125, 128)]; /* 723 */ + __u8 logical_block_size [ISODCL (129, 132)]; /* 723 */ + __u8 path_table_size [ISODCL (133, 140)]; /* 733 */ + __u8 type_l_path_table [ISODCL (141, 144)]; /* 731 */ + __u8 opt_type_l_path_table [ISODCL (145, 148)]; /* 731 */ + __u8 type_m_path_table [ISODCL (149, 152)]; /* 732 */ + __u8 opt_type_m_path_table [ISODCL (153, 156)]; /* 732 */ + __u8 root_directory_record [ISODCL (157, 190)]; /* 9.1 */ char volume_set_id [ISODCL (191, 318)]; /* dchars */ char publisher_id [ISODCL (319, 446)]; /* achars */ char preparer_id [ISODCL (447, 574)]; /* achars */ @@ -51,36 +51,36 @@ struct iso_primary_descriptor { char copyright_file_id [ISODCL (703, 739)]; /* 7.5 dchars */ char abstract_file_id [ISODCL (740, 776)]; /* 7.5 dchars */ char bibliographic_file_id [ISODCL (777, 813)]; /* 7.5 dchars */ - char creation_date [ISODCL (814, 830)]; /* 8.4.26.1 */ - char modification_date [ISODCL (831, 847)]; /* 8.4.26.1 */ - char expiration_date [ISODCL (848, 864)]; /* 8.4.26.1 */ - char effective_date [ISODCL (865, 881)]; /* 8.4.26.1 */ - char file_structure_version [ISODCL (882, 882)]; /* 711 */ - char unused4 [ISODCL (883, 883)]; - char application_data [ISODCL (884, 1395)]; - char unused5 [ISODCL (1396, 2048)]; + __u8 creation_date [ISODCL (814, 830)]; /* 8.4.26.1 */ + __u8 modification_date [ISODCL (831, 847)]; /* 8.4.26.1 */ + __u8 expiration_date [ISODCL (848, 864)]; /* 8.4.26.1 */ + __u8 effective_date [ISODCL (865, 881)]; /* 8.4.26.1 */ + __u8 file_structure_version [ISODCL (882, 882)]; /* 711 */ + __u8 unused4 [ISODCL (883, 883)]; + __u8 application_data [ISODCL (884, 1395)]; + __u8 unused5 [ISODCL (1396, 2048)]; }; /* Almost the same as the primary descriptor but two fields are specified */ struct iso_supplementary_descriptor { - char type [ISODCL ( 1, 1)]; /* 711 */ + __u8 type [ISODCL ( 1, 1)]; /* 711 */ char id [ISODCL ( 2, 6)]; - char version [ISODCL ( 7, 7)]; /* 711 */ - char flags [ISODCL ( 8, 8)]; /* 853 */ + __u8 version [ISODCL ( 7, 7)]; /* 711 */ + __u8 flags [ISODCL ( 8, 8)]; /* 853 */ char system_id [ISODCL ( 9, 40)]; /* achars */ char volume_id [ISODCL ( 41, 72)]; /* dchars */ - char unused2 [ISODCL ( 73, 80)]; - char volume_space_size [ISODCL ( 81, 88)]; /* 733 */ - char escape [ISODCL ( 89, 120)]; /* 856 */ - char volume_set_size [ISODCL (121, 124)]; /* 723 */ - char volume_sequence_number [ISODCL (125, 128)]; /* 723 */ - char logical_block_size [ISODCL (129, 132)]; /* 723 */ - char path_table_size [ISODCL (133, 140)]; /* 733 */ - char type_l_path_table [ISODCL (141, 144)]; /* 731 */ - char opt_type_l_path_table [ISODCL (145, 148)]; /* 731 */ - char type_m_path_table [ISODCL (149, 152)]; /* 732 */ - char opt_type_m_path_table [ISODCL (153, 156)]; /* 732 */ - char root_directory_record [ISODCL (157, 190)]; /* 9.1 */ + __u8 unused2 [ISODCL ( 73, 80)]; + __u8 volume_space_size [ISODCL ( 81, 88)]; /* 733 */ + __u8 escape [ISODCL ( 89, 120)]; /* 856 */ + __u8 volume_set_size [ISODCL (121, 124)]; /* 723 */ + __u8 volume_sequence_number [ISODCL (125, 128)]; /* 723 */ + __u8 logical_block_size [ISODCL (129, 132)]; /* 723 */ + __u8 path_table_size [ISODCL (133, 140)]; /* 733 */ + __u8 type_l_path_table [ISODCL (141, 144)]; /* 731 */ + __u8 opt_type_l_path_table [ISODCL (145, 148)]; /* 731 */ + __u8 type_m_path_table [ISODCL (149, 152)]; /* 732 */ + __u8 opt_type_m_path_table [ISODCL (153, 156)]; /* 732 */ + __u8 root_directory_record [ISODCL (157, 190)]; /* 9.1 */ char volume_set_id [ISODCL (191, 318)]; /* dchars */ char publisher_id [ISODCL (319, 446)]; /* achars */ char preparer_id [ISODCL (447, 574)]; /* achars */ @@ -88,54 +88,54 @@ struct iso_supplementary_descriptor { char copyright_file_id [ISODCL (703, 739)]; /* 7.5 dchars */ char abstract_file_id [ISODCL (740, 776)]; /* 7.5 dchars */ char bibliographic_file_id [ISODCL (777, 813)]; /* 7.5 dchars */ - char creation_date [ISODCL (814, 830)]; /* 8.4.26.1 */ - char modification_date [ISODCL (831, 847)]; /* 8.4.26.1 */ - char expiration_date [ISODCL (848, 864)]; /* 8.4.26.1 */ - char effective_date [ISODCL (865, 881)]; /* 8.4.26.1 */ - char file_structure_version [ISODCL (882, 882)]; /* 711 */ - char unused4 [ISODCL (883, 883)]; - char application_data [ISODCL (884, 1395)]; - char unused5 [ISODCL (1396, 2048)]; + __u8 creation_date [ISODCL (814, 830)]; /* 8.4.26.1 */ + __u8 modification_date [ISODCL (831, 847)]; /* 8.4.26.1 */ + __u8 expiration_date [ISODCL (848, 864)]; /* 8.4.26.1 */ + __u8 effective_date [ISODCL (865, 881)]; /* 8.4.26.1 */ + __u8 file_structure_version [ISODCL (882, 882)]; /* 711 */ + __u8 unused4 [ISODCL (883, 883)]; + __u8 application_data [ISODCL (884, 1395)]; + __u8 unused5 [ISODCL (1396, 2048)]; }; #define HS_STANDARD_ID "CDROM" struct hs_volume_descriptor { - char foo [ISODCL ( 1, 8)]; /* 733 */ - char type [ISODCL ( 9, 9)]; /* 711 */ + __u8 foo [ISODCL ( 1, 8)]; /* 733 */ + __u8 type [ISODCL ( 9, 9)]; /* 711 */ char id [ISODCL ( 10, 14)]; - char version [ISODCL ( 15, 15)]; /* 711 */ - char data[ISODCL(16,2048)]; + __u8 version [ISODCL ( 15, 15)]; /* 711 */ + __u8 data[ISODCL(16,2048)]; }; struct hs_primary_descriptor { - char foo [ISODCL ( 1, 8)]; /* 733 */ - char type [ISODCL ( 9, 9)]; /* 711 */ - char id [ISODCL ( 10, 14)]; - char version [ISODCL ( 15, 15)]; /* 711 */ - char unused1 [ISODCL ( 16, 16)]; /* 711 */ + __u8 foo [ISODCL ( 1, 8)]; /* 733 */ + __u8 type [ISODCL ( 9, 9)]; /* 711 */ + __u8 id [ISODCL ( 10, 14)]; + __u8 version [ISODCL ( 15, 15)]; /* 711 */ + __u8 unused1 [ISODCL ( 16, 16)]; /* 711 */ char system_id [ISODCL ( 17, 48)]; /* achars */ char volume_id [ISODCL ( 49, 80)]; /* dchars */ - char unused2 [ISODCL ( 81, 88)]; /* 733 */ - char volume_space_size [ISODCL ( 89, 96)]; /* 733 */ - char unused3 [ISODCL ( 97, 128)]; /* 733 */ - char volume_set_size [ISODCL (129, 132)]; /* 723 */ - char volume_sequence_number [ISODCL (133, 136)]; /* 723 */ - char logical_block_size [ISODCL (137, 140)]; /* 723 */ - char path_table_size [ISODCL (141, 148)]; /* 733 */ - char type_l_path_table [ISODCL (149, 152)]; /* 731 */ - char unused4 [ISODCL (153, 180)]; /* 733 */ - char root_directory_record [ISODCL (181, 214)]; /* 9.1 */ + __u8 unused2 [ISODCL ( 81, 88)]; /* 733 */ + __u8 volume_space_size [ISODCL ( 89, 96)]; /* 733 */ + __u8 unused3 [ISODCL ( 97, 128)]; /* 733 */ + __u8 volume_set_size [ISODCL (129, 132)]; /* 723 */ + __u8 volume_sequence_number [ISODCL (133, 136)]; /* 723 */ + __u8 logical_block_size [ISODCL (137, 140)]; /* 723 */ + __u8 path_table_size [ISODCL (141, 148)]; /* 733 */ + __u8 type_l_path_table [ISODCL (149, 152)]; /* 731 */ + __u8 unused4 [ISODCL (153, 180)]; /* 733 */ + __u8 root_directory_record [ISODCL (181, 214)]; /* 9.1 */ }; /* We use this to help us look up the parent inode numbers. */ struct iso_path_table{ - unsigned char name_len[2]; /* 721 */ - char extent[4]; /* 731 */ - char parent[2]; /* 721 */ + __u8 name_len[2]; /* 721 */ + __u8 extent[4]; /* 731 */ + __u8 parent[2]; /* 721 */ char name[0]; } __attribute__((packed)); @@ -143,16 +143,16 @@ struct iso_path_table{ there is an extra reserved byte after the flags */ struct iso_directory_record { - char length [ISODCL (1, 1)]; /* 711 */ - char ext_attr_length [ISODCL (2, 2)]; /* 711 */ - char extent [ISODCL (3, 10)]; /* 733 */ - char size [ISODCL (11, 18)]; /* 733 */ - char date [ISODCL (19, 25)]; /* 7 by 711 */ - char flags [ISODCL (26, 26)]; - char file_unit_size [ISODCL (27, 27)]; /* 711 */ - char interleave [ISODCL (28, 28)]; /* 711 */ - char volume_sequence_number [ISODCL (29, 32)]; /* 723 */ - unsigned char name_len [ISODCL (33, 33)]; /* 711 */ + __u8 length [ISODCL (1, 1)]; /* 711 */ + __u8 ext_attr_length [ISODCL (2, 2)]; /* 711 */ + __u8 extent [ISODCL (3, 10)]; /* 733 */ + __u8 size [ISODCL (11, 18)]; /* 733 */ + __u8 date [ISODCL (19, 25)]; /* 7 by 711 */ + __u8 flags [ISODCL (26, 26)]; + __u8 file_unit_size [ISODCL (27, 27)]; /* 711 */ + __u8 interleave [ISODCL (28, 28)]; /* 711 */ + __u8 volume_sequence_number [ISODCL (29, 32)]; /* 723 */ + __u8 name_len [ISODCL (33, 33)]; /* 711 */ char name [0]; } __attribute__((packed)); -- cgit v1.2.3-71-gd317 From 04686ef299db5ff299bfc5a4504b189e46842078 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 31 Oct 2017 19:17:31 -0700 Subject: bpf: remove SK_REDIRECT from UAPI Now that SK_REDIRECT is no longer a valid return code. Remove it from the UAPI completely. Then do a namespace remapping internal to sockmap so SK_REDIRECT is no longer externally visible. Patchs primary change is to do a namechange from SK_REDIRECT to __SK_REDIRECT Reported-by: Alexei Starovoitov Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 1 - kernel/bpf/sockmap.c | 16 ++++++++++++---- tools/include/uapi/linux/bpf.h | 3 +-- 3 files changed, 13 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0d7948ce2128..7bf4c750dd3a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -788,7 +788,6 @@ struct xdp_md { enum sk_action { SK_DROP = 0, SK_PASS, - SK_REDIRECT, }; #define BPF_TAG_SIZE 8 diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 66f00a2b27f4..dbd7b322a86b 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -101,13 +101,19 @@ static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb) TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb); } +enum __sk_action { + __SK_DROP = 0, + __SK_PASS, + __SK_REDIRECT, +}; + static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) { struct bpf_prog *prog = READ_ONCE(psock->bpf_verdict); int rc; if (unlikely(!prog)) - return SK_DROP; + return __SK_DROP; skb_orphan(skb); /* We need to ensure that BPF metadata for maps is also cleared @@ -122,8 +128,10 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) preempt_enable(); skb->sk = NULL; + /* Moving return codes from UAPI namespace into internal namespace */ return rc == SK_PASS ? - (TCP_SKB_CB(skb)->bpf.map ? SK_REDIRECT : SK_PASS) : SK_DROP; + (TCP_SKB_CB(skb)->bpf.map ? __SK_REDIRECT : __SK_PASS) : + __SK_DROP; } static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb) @@ -133,7 +141,7 @@ static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb) rc = smap_verdict_func(psock, skb); switch (rc) { - case SK_REDIRECT: + case __SK_REDIRECT: sk = do_sk_redirect_map(skb); if (likely(sk)) { struct smap_psock *peer = smap_psock_sk(sk); @@ -149,7 +157,7 @@ static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb) } } /* Fall through and free skb otherwise */ - case SK_DROP: + case __SK_DROP: default: kfree_skb(skb); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index c174971afbe6..01cc7ba39924 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -576,7 +576,7 @@ union bpf_attr { * @map: pointer to sockmap * @key: key to lookup sock in map * @flags: reserved for future use - * Return: SK_REDIRECT + * Return: SK_PASS * * int bpf_sock_map_update(skops, map, key, flags) * @skops: pointer to bpf_sock_ops @@ -789,7 +789,6 @@ struct xdp_md { enum sk_action { SK_DROP = 0, SK_PASS, - SK_REDIRECT, }; #define BPF_TAG_SIZE 8 -- cgit v1.2.3-71-gd317 From d24a67b2d997c860a42516076f3315c2ad2d2884 Mon Sep 17 00:00:00 2001 From: Zygo Blaxell Date: Fri, 22 Sep 2017 13:58:46 -0400 Subject: btrfs: add a flags argument to LOGICAL_INO and call it LOGICAL_INO_V2 Now that check_extent_in_eb()'s extent offset filter can be turned off, we need a way to do it from userspace. Add a 'flags' field to the btrfs_logical_ino_args structure to disable extent offset filtering, taking the place of one of the existing reserved[] fields. Previous versions of LOGICAL_INO neglected to check whether any of the reserved fields have non-zero values. Assigning meaning to those fields now may change the behavior of existing programs that left these fields uninitialized. The lack of a zero check also means that new programs have no way to know whether the kernel is honoring the flags field. To avoid these problems, define a new ioctl LOGICAL_INO_V2. We can use the same argument layout as LOGICAL_INO, but shorten the reserved[] array by one element and turn it into the 'flags' field. The V2 ioctl explicitly checks that reserved fields and unsupported flag bits are zero so that userspace can negotiate future feature bits as they are defined. Since the memory layouts of the two ioctls' arguments are compatible, there is no need for a separate function for logical_to_ino_v2 (contrast with tree_search_v2 vs tree_search where the layout and code are quite different). A version parameter and an 'if' statement will suffice. Now that we have a flags field in logical_ino_args, add a flag BTRFS_LOGICAL_INO_ARGS_IGNORE_OFFSET to get the behavior we want, and pass it down the stack to iterate_inodes_from_logical. Motivation and background, copied from the patchset cover letter: Suppose we have a file with one extent: root@tester:~# zcat /usr/share/doc/cpio/changelog.gz > /test/a root@tester:~# sync Split the extent by overwriting it in the middle: root@tester:~# cat /dev/urandom | dd bs=4k seek=2 skip=2 count=1 conv=notrunc of=/test/a We should now have 3 extent refs to 2 extents, with one block unreachable. The extent tree looks like: root@tester:~# btrfs-debug-tree /dev/vdc -t 2 [...] item 9 key (1103101952 EXTENT_ITEM 73728) itemoff 15942 itemsize 53 extent refs 2 gen 29 flags DATA extent data backref root 5 objectid 261 offset 0 count 2 [...] item 11 key (1103175680 EXTENT_ITEM 4096) itemoff 15865 itemsize 53 extent refs 1 gen 30 flags DATA extent data backref root 5 objectid 261 offset 8192 count 1 [...] and the ref tree looks like: root@tester:~# btrfs-debug-tree /dev/vdc -t 5 [...] item 6 key (261 EXTENT_DATA 0) itemoff 15825 itemsize 53 extent data disk byte 1103101952 nr 73728 extent data offset 0 nr 8192 ram 73728 extent compression(none) item 7 key (261 EXTENT_DATA 8192) itemoff 15772 itemsize 53 extent data disk byte 1103175680 nr 4096 extent data offset 0 nr 4096 ram 4096 extent compression(none) item 8 key (261 EXTENT_DATA 12288) itemoff 15719 itemsize 53 extent data disk byte 1103101952 nr 73728 extent data offset 12288 nr 61440 ram 73728 extent compression(none) [...] There are two references to the same extent with different, non-overlapping byte offsets: [------------------72K extent at 1103101952----------------------] [--8K----------------|--4K unreachable----|--60K-----------------] ^ ^ | | [--8K ref offset 0--][--4K ref offset 0--][--60K ref offset 12K--] | v [-----4K extent-----] at 1103175680 We want to find all of the references to extent bytenr 1103101952. Without the patch (and without running btrfs-debug-tree), we have to do it with 18 LOGICAL_INO calls: root@tester:~# btrfs ins log 1103101952 -P /test/ Using LOGICAL_INO inode 261 offset 0 root 5 root@tester:~# for x in $(seq 0 17); do btrfs ins log $((1103101952 + x * 4096)) -P /test/; done 2>&1 | grep inode inode 261 offset 0 root 5 inode 261 offset 4096 root 5 <- same extent ref as offset 0 (offset 8192 returns empty set, not reachable) inode 261 offset 12288 root 5 inode 261 offset 16384 root 5 \ inode 261 offset 20480 root 5 | inode 261 offset 24576 root 5 | inode 261 offset 28672 root 5 | inode 261 offset 32768 root 5 | inode 261 offset 36864 root 5 \ inode 261 offset 40960 root 5 > all the same extent ref as offset 12288. inode 261 offset 45056 root 5 / More processing required in userspace inode 261 offset 49152 root 5 | to figure out these are all duplicates. inode 261 offset 53248 root 5 | inode 261 offset 57344 root 5 | inode 261 offset 61440 root 5 | inode 261 offset 65536 root 5 | inode 261 offset 69632 root 5 / In the worst case the extents are 128MB long, and we have to do 32768 iterations of the loop to find one 4K extent ref. With the patch, we just use one call to map all refs to the extent at once: root@tester:~# btrfs ins log 1103101952 -P /test/ Using LOGICAL_INO_V2 inode 261 offset 0 root 5 inode 261 offset 12288 root 5 The TREE_SEARCH ioctl allows userspace to retrieve the offset and extent bytenr fields easily once the root, inode and offset are known. This is sufficient information to build a complete map of the extent and all of its references. Userspace can use this information to make better choices to dedup or defrag. Signed-off-by: Zygo Blaxell Reviewed-by: Hans van Kranenburg Tested-by: Hans van Kranenburg [ copy background and motivation from cover letter ] Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 26 +++++++++++++++++++++++--- include/uapi/linux/btrfs.h | 8 +++++++- 2 files changed, 30 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 2497a5d45d9c..fa9996ab3da6 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4530,13 +4530,14 @@ static int build_ino_list(u64 inum, u64 offset, u64 root, void *ctx) } static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info, - void __user *arg) + void __user *arg, int version) { int ret = 0; int size; struct btrfs_ioctl_logical_ino_args *loi; struct btrfs_data_container *inodes = NULL; struct btrfs_path *path = NULL; + bool ignore_offset; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -4545,6 +4546,22 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info, if (IS_ERR(loi)) return PTR_ERR(loi); + if (version == 1) { + ignore_offset = false; + } else { + /* All reserved bits must be 0 for now */ + if (memchr_inv(loi->reserved, 0, sizeof(loi->reserved))) { + ret = -EINVAL; + goto out_loi; + } + /* Only accept flags we have defined so far */ + if (loi->flags & ~(BTRFS_LOGICAL_INO_ARGS_IGNORE_OFFSET)) { + ret = -EINVAL; + goto out_loi; + } + ignore_offset = loi->flags & BTRFS_LOGICAL_INO_ARGS_IGNORE_OFFSET; + } + path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; @@ -4560,7 +4577,7 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info, } ret = iterate_inodes_from_logical(loi->logical, fs_info, path, - build_ino_list, inodes, false); + build_ino_list, inodes, ignore_offset); if (ret == -EINVAL) ret = -ENOENT; if (ret < 0) @@ -4574,6 +4591,7 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info, out: btrfs_free_path(path); kvfree(inodes); +out_loi: kfree(loi); return ret; @@ -5575,7 +5593,9 @@ long btrfs_ioctl(struct file *file, unsigned int case BTRFS_IOC_INO_PATHS: return btrfs_ioctl_ino_to_path(root, argp); case BTRFS_IOC_LOGICAL_INO: - return btrfs_ioctl_logical_to_ino(fs_info, argp); + return btrfs_ioctl_logical_to_ino(fs_info, argp, 1); + case BTRFS_IOC_LOGICAL_INO_V2: + return btrfs_ioctl_logical_to_ino(fs_info, argp, 2); case BTRFS_IOC_SPACE_INFO: return btrfs_ioctl_space_info(fs_info, argp); case BTRFS_IOC_SYNC: { diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 378230c163d5..99bb7988e6fe 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -608,10 +608,14 @@ struct btrfs_ioctl_ino_path_args { struct btrfs_ioctl_logical_ino_args { __u64 logical; /* in */ __u64 size; /* in */ - __u64 reserved[4]; + __u64 reserved[3]; /* must be 0 for now */ + __u64 flags; /* in, v2 only */ /* struct btrfs_data_container *inodes; out */ __u64 inodes; }; +/* Return every ref to the extent, not just those containing logical block. + * Requires logical == extent bytenr. */ +#define BTRFS_LOGICAL_INO_ARGS_IGNORE_OFFSET (1ULL << 0) enum btrfs_dev_stat_values { /* disk I/O failure stats */ @@ -835,5 +839,7 @@ enum btrfs_err_code { struct btrfs_ioctl_feature_flags[3]) #define BTRFS_IOC_RM_DEV_V2 _IOW(BTRFS_IOCTL_MAGIC, 58, \ struct btrfs_ioctl_vol_args_v2) +#define BTRFS_IOC_LOGICAL_INO_V2 _IOWR(BTRFS_IOCTL_MAGIC, 59, \ + struct btrfs_ioctl_logical_ino_args) #endif /* _UAPI_LINUX_BTRFS_H */ -- cgit v1.2.3-71-gd317 From 6f52b16c5b29b89d92c0e7236f4655dc8491ad70 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 1 Nov 2017 15:08:43 +0100 Subject: License cleanup: add SPDX license identifier to uapi header files with no license Many user space API headers are missing licensing information, which makes it hard for compliance tools to determine the correct license. By default are files without license information under the default license of the kernel, which is GPLV2. Marking them GPLV2 would exclude them from being included in non GPLV2 code, which is obviously not intended. The user space API headers fall under the syscall exception which is in the kernels COPYING file: NOTE! This copyright does *not* cover user programs that use kernel services by normal system calls - this is merely considered normal use of the kernel, and does *not* fall under the heading of "derived work". otherwise syscall usage would not be possible. Update the files which contain no license information with an SPDX license identifier. The chosen identifier is 'GPL-2.0 WITH Linux-syscall-note' which is the officially assigned identifier for the Linux syscall exception. SPDX license identifiers are a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. See the previous patch in this series for the methodology of how this patch was researched. Reviewed-by: Kate Stewart Reviewed-by: Philippe Ombredanne Reviewed-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- arch/alpha/include/uapi/asm/a.out.h | 1 + arch/alpha/include/uapi/asm/auxvec.h | 1 + arch/alpha/include/uapi/asm/bitsperlong.h | 1 + arch/alpha/include/uapi/asm/byteorder.h | 1 + arch/alpha/include/uapi/asm/compiler.h | 1 + arch/alpha/include/uapi/asm/console.h | 1 + arch/alpha/include/uapi/asm/errno.h | 1 + arch/alpha/include/uapi/asm/fcntl.h | 1 + arch/alpha/include/uapi/asm/fpu.h | 1 + arch/alpha/include/uapi/asm/gentrap.h | 1 + arch/alpha/include/uapi/asm/ioctl.h | 1 + arch/alpha/include/uapi/asm/ioctls.h | 1 + arch/alpha/include/uapi/asm/ipcbuf.h | 1 + arch/alpha/include/uapi/asm/kvm_para.h | 1 + arch/alpha/include/uapi/asm/mman.h | 1 + arch/alpha/include/uapi/asm/msgbuf.h | 1 + arch/alpha/include/uapi/asm/pal.h | 1 + arch/alpha/include/uapi/asm/param.h | 1 + arch/alpha/include/uapi/asm/posix_types.h | 1 + arch/alpha/include/uapi/asm/ptrace.h | 1 + arch/alpha/include/uapi/asm/reg.h | 1 + arch/alpha/include/uapi/asm/regdef.h | 1 + arch/alpha/include/uapi/asm/resource.h | 1 + arch/alpha/include/uapi/asm/sembuf.h | 1 + arch/alpha/include/uapi/asm/setup.h | 1 + arch/alpha/include/uapi/asm/shmbuf.h | 1 + arch/alpha/include/uapi/asm/sigcontext.h | 1 + arch/alpha/include/uapi/asm/siginfo.h | 1 + arch/alpha/include/uapi/asm/signal.h | 1 + arch/alpha/include/uapi/asm/socket.h | 1 + arch/alpha/include/uapi/asm/sockios.h | 1 + arch/alpha/include/uapi/asm/stat.h | 1 + arch/alpha/include/uapi/asm/statfs.h | 1 + arch/alpha/include/uapi/asm/swab.h | 1 + arch/alpha/include/uapi/asm/sysinfo.h | 1 + arch/alpha/include/uapi/asm/termbits.h | 1 + arch/alpha/include/uapi/asm/termios.h | 1 + arch/alpha/include/uapi/asm/types.h | 1 + arch/alpha/include/uapi/asm/unistd.h | 1 + arch/arm/include/uapi/asm/auxvec.h | 1 + arch/arm/include/uapi/asm/byteorder.h | 1 + arch/arm/include/uapi/asm/fcntl.h | 1 + arch/arm/include/uapi/asm/hwcap.h | 1 + arch/arm/include/uapi/asm/ioctls.h | 1 + arch/arm/include/uapi/asm/kvm_para.h | 1 + arch/arm/include/uapi/asm/perf_regs.h | 1 + arch/arm/include/uapi/asm/sigcontext.h | 1 + arch/arm/include/uapi/asm/signal.h | 1 + arch/arm/include/uapi/asm/stat.h | 1 + arch/arm/include/uapi/asm/statfs.h | 1 + arch/arm/include/uapi/asm/swab.h | 1 + arch/arm/include/uapi/asm/types.h | 1 + arch/arm64/include/uapi/asm/perf_regs.h | 1 + arch/arm64/include/uapi/asm/posix_types.h | 1 + arch/blackfin/include/uapi/asm/byteorder.h | 1 + arch/blackfin/include/uapi/asm/ioctls.h | 1 + arch/blackfin/include/uapi/asm/signal.h | 1 + arch/c6x/include/uapi/asm/byteorder.h | 1 + arch/c6x/include/uapi/asm/setup.h | 1 + arch/cris/include/uapi/arch-v10/arch/sv_addr_ag.h | 1 + arch/cris/include/uapi/arch-v10/arch/svinto.h | 1 + arch/cris/include/uapi/arch-v10/arch/user.h | 1 + arch/cris/include/uapi/arch-v32/arch/cryptocop.h | 1 + arch/cris/include/uapi/arch-v32/arch/user.h | 1 + arch/cris/include/uapi/asm/byteorder.h | 1 + arch/cris/include/uapi/asm/elf.h | 1 + arch/cris/include/uapi/asm/elf_v10.h | 1 + arch/cris/include/uapi/asm/elf_v32.h | 1 + arch/cris/include/uapi/asm/ethernet.h | 1 + arch/cris/include/uapi/asm/etraxgpio.h | 1 + arch/cris/include/uapi/asm/ioctls.h | 1 + arch/cris/include/uapi/asm/param.h | 1 + arch/cris/include/uapi/asm/posix_types.h | 1 + arch/cris/include/uapi/asm/ptrace.h | 1 + arch/cris/include/uapi/asm/ptrace_v10.h | 1 + arch/cris/include/uapi/asm/ptrace_v32.h | 1 + arch/cris/include/uapi/asm/rs485.h | 1 + arch/cris/include/uapi/asm/setup.h | 1 + arch/cris/include/uapi/asm/sigcontext.h | 1 + arch/cris/include/uapi/asm/signal.h | 1 + arch/cris/include/uapi/asm/stat.h | 1 + arch/cris/include/uapi/asm/sync_serial.h | 1 + arch/cris/include/uapi/asm/termbits.h | 1 + arch/cris/include/uapi/asm/termios.h | 1 + arch/cris/include/uapi/asm/unistd.h | 1 + arch/frv/include/uapi/asm/bitsperlong.h | 1 + arch/frv/include/uapi/asm/byteorder.h | 1 + arch/frv/include/uapi/asm/errno.h | 1 + arch/frv/include/uapi/asm/fcntl.h | 1 + arch/frv/include/uapi/asm/ioctl.h | 1 + arch/frv/include/uapi/asm/ioctls.h | 1 + arch/frv/include/uapi/asm/kvm_para.h | 1 + arch/frv/include/uapi/asm/mman.h | 1 + arch/frv/include/uapi/asm/msgbuf.h | 1 + arch/frv/include/uapi/asm/param.h | 1 + arch/frv/include/uapi/asm/poll.h | 1 + arch/frv/include/uapi/asm/posix_types.h | 1 + arch/frv/include/uapi/asm/resource.h | 1 + arch/frv/include/uapi/asm/sembuf.h | 1 + arch/frv/include/uapi/asm/shmbuf.h | 1 + arch/frv/include/uapi/asm/siginfo.h | 1 + arch/frv/include/uapi/asm/signal.h | 1 + arch/frv/include/uapi/asm/socket.h | 1 + arch/frv/include/uapi/asm/sockios.h | 1 + arch/frv/include/uapi/asm/stat.h | 1 + arch/frv/include/uapi/asm/statfs.h | 1 + arch/frv/include/uapi/asm/swab.h | 1 + arch/frv/include/uapi/asm/termbits.h | 1 + arch/frv/include/uapi/asm/termios.h | 1 + arch/frv/include/uapi/asm/unistd.h | 1 + arch/h8300/include/uapi/asm/bitsperlong.h | 1 + arch/h8300/include/uapi/asm/byteorder.h | 1 + arch/h8300/include/uapi/asm/ptrace.h | 1 + arch/h8300/include/uapi/asm/sigcontext.h | 1 + arch/h8300/include/uapi/asm/signal.h | 1 + arch/hexagon/include/uapi/asm/kvm_para.h | 1 + arch/hexagon/include/uapi/asm/registers.h | 1 + arch/hexagon/include/uapi/asm/user.h | 1 + arch/ia64/include/uapi/asm/auxvec.h | 1 + arch/ia64/include/uapi/asm/bitsperlong.h | 1 + arch/ia64/include/uapi/asm/break.h | 1 + arch/ia64/include/uapi/asm/byteorder.h | 1 + arch/ia64/include/uapi/asm/cmpxchg.h | 1 + arch/ia64/include/uapi/asm/errno.h | 1 + arch/ia64/include/uapi/asm/fcntl.h | 1 + arch/ia64/include/uapi/asm/fpu.h | 1 + arch/ia64/include/uapi/asm/gcc_intrin.h | 1 + arch/ia64/include/uapi/asm/ia64regs.h | 1 + arch/ia64/include/uapi/asm/intel_intrin.h | 1 + arch/ia64/include/uapi/asm/intrinsics.h | 1 + arch/ia64/include/uapi/asm/ioctl.h | 1 + arch/ia64/include/uapi/asm/ioctls.h | 1 + arch/ia64/include/uapi/asm/ipcbuf.h | 1 + arch/ia64/include/uapi/asm/mman.h | 1 + arch/ia64/include/uapi/asm/msgbuf.h | 1 + arch/ia64/include/uapi/asm/param.h | 1 + arch/ia64/include/uapi/asm/perfmon.h | 1 + arch/ia64/include/uapi/asm/perfmon_default_smpl.h | 1 + arch/ia64/include/uapi/asm/posix_types.h | 1 + arch/ia64/include/uapi/asm/ptrace.h | 1 + arch/ia64/include/uapi/asm/ptrace_offsets.h | 1 + arch/ia64/include/uapi/asm/resource.h | 1 + arch/ia64/include/uapi/asm/rse.h | 1 + arch/ia64/include/uapi/asm/sembuf.h | 1 + arch/ia64/include/uapi/asm/setup.h | 1 + arch/ia64/include/uapi/asm/shmbuf.h | 1 + arch/ia64/include/uapi/asm/sigcontext.h | 1 + arch/ia64/include/uapi/asm/siginfo.h | 1 + arch/ia64/include/uapi/asm/signal.h | 1 + arch/ia64/include/uapi/asm/socket.h | 1 + arch/ia64/include/uapi/asm/sockios.h | 1 + arch/ia64/include/uapi/asm/stat.h | 1 + arch/ia64/include/uapi/asm/statfs.h | 1 + arch/ia64/include/uapi/asm/swab.h | 1 + arch/ia64/include/uapi/asm/termbits.h | 1 + arch/ia64/include/uapi/asm/termios.h | 1 + arch/ia64/include/uapi/asm/types.h | 1 + arch/ia64/include/uapi/asm/ucontext.h | 1 + arch/ia64/include/uapi/asm/unistd.h | 1 + arch/ia64/include/uapi/asm/ustack.h | 1 + arch/m32r/include/uapi/asm/bitsperlong.h | 1 + arch/m32r/include/uapi/asm/byteorder.h | 1 + arch/m32r/include/uapi/asm/errno.h | 1 + arch/m32r/include/uapi/asm/fcntl.h | 1 + arch/m32r/include/uapi/asm/ioctl.h | 1 + arch/m32r/include/uapi/asm/ioctls.h | 1 + arch/m32r/include/uapi/asm/ipcbuf.h | 1 + arch/m32r/include/uapi/asm/msgbuf.h | 1 + arch/m32r/include/uapi/asm/param.h | 1 + arch/m32r/include/uapi/asm/poll.h | 1 + arch/m32r/include/uapi/asm/posix_types.h | 1 + arch/m32r/include/uapi/asm/resource.h | 1 + arch/m32r/include/uapi/asm/sembuf.h | 1 + arch/m32r/include/uapi/asm/setup.h | 1 + arch/m32r/include/uapi/asm/shmbuf.h | 1 + arch/m32r/include/uapi/asm/sigcontext.h | 1 + arch/m32r/include/uapi/asm/signal.h | 1 + arch/m32r/include/uapi/asm/socket.h | 1 + arch/m32r/include/uapi/asm/sockios.h | 1 + arch/m32r/include/uapi/asm/stat.h | 1 + arch/m32r/include/uapi/asm/statfs.h | 1 + arch/m32r/include/uapi/asm/swab.h | 1 + arch/m32r/include/uapi/asm/termbits.h | 1 + arch/m32r/include/uapi/asm/termios.h | 1 + arch/m32r/include/uapi/asm/unistd.h | 1 + arch/m68k/include/uapi/asm/a.out.h | 1 + arch/m68k/include/uapi/asm/bootinfo-amiga.h | 1 + arch/m68k/include/uapi/asm/bootinfo-apollo.h | 1 + arch/m68k/include/uapi/asm/bootinfo-atari.h | 1 + arch/m68k/include/uapi/asm/bootinfo-hp300.h | 1 + arch/m68k/include/uapi/asm/bootinfo-mac.h | 1 + arch/m68k/include/uapi/asm/bootinfo-q40.h | 1 + arch/m68k/include/uapi/asm/bootinfo-vme.h | 1 + arch/m68k/include/uapi/asm/byteorder.h | 1 + arch/m68k/include/uapi/asm/cachectl.h | 1 + arch/m68k/include/uapi/asm/fcntl.h | 1 + arch/m68k/include/uapi/asm/ioctls.h | 1 + arch/m68k/include/uapi/asm/param.h | 1 + arch/m68k/include/uapi/asm/poll.h | 1 + arch/m68k/include/uapi/asm/posix_types.h | 1 + arch/m68k/include/uapi/asm/ptrace.h | 1 + arch/m68k/include/uapi/asm/sigcontext.h | 1 + arch/m68k/include/uapi/asm/signal.h | 1 + arch/m68k/include/uapi/asm/stat.h | 1 + arch/m68k/include/uapi/asm/swab.h | 1 + arch/m68k/include/uapi/asm/unistd.h | 1 + arch/metag/include/uapi/asm/byteorder.h | 1 + arch/metag/include/uapi/asm/ech.h | 1 + arch/metag/include/uapi/asm/ptrace.h | 1 + arch/metag/include/uapi/asm/sigcontext.h | 1 + arch/metag/include/uapi/asm/siginfo.h | 1 + arch/metag/include/uapi/asm/swab.h | 1 + arch/microblaze/include/uapi/asm/auxvec.h | 1 + arch/microblaze/include/uapi/asm/byteorder.h | 1 + arch/microblaze/include/uapi/asm/posix_types.h | 1 + arch/mips/include/uapi/asm/bitsperlong.h | 1 + arch/mips/include/uapi/asm/hwcap.h | 1 + arch/mips/include/uapi/asm/msgbuf.h | 1 + arch/mips/include/uapi/asm/poll.h | 1 + arch/mips/include/uapi/asm/sembuf.h | 1 + arch/mips/include/uapi/asm/setup.h | 1 + arch/mips/include/uapi/asm/shmbuf.h | 1 + arch/mips/include/uapi/asm/ucontext.h | 1 + arch/mn10300/include/uapi/asm/bitsperlong.h | 1 + arch/mn10300/include/uapi/asm/byteorder.h | 1 + arch/mn10300/include/uapi/asm/errno.h | 1 + arch/mn10300/include/uapi/asm/fcntl.h | 1 + arch/mn10300/include/uapi/asm/ioctls.h | 1 + arch/mn10300/include/uapi/asm/ipcbuf.h | 1 + arch/mn10300/include/uapi/asm/kvm_para.h | 1 + arch/mn10300/include/uapi/asm/mman.h | 1 + arch/mn10300/include/uapi/asm/msgbuf.h | 1 + arch/mn10300/include/uapi/asm/poll.h | 1 + arch/mn10300/include/uapi/asm/resource.h | 1 + arch/mn10300/include/uapi/asm/sembuf.h | 1 + arch/mn10300/include/uapi/asm/setup.h | 1 + arch/mn10300/include/uapi/asm/shmbuf.h | 1 + arch/mn10300/include/uapi/asm/socket.h | 1 + arch/mn10300/include/uapi/asm/sockios.h | 1 + arch/mn10300/include/uapi/asm/stat.h | 1 + arch/mn10300/include/uapi/asm/termbits.h | 1 + arch/mn10300/include/uapi/asm/termios.h | 1 + arch/parisc/include/uapi/asm/bitsperlong.h | 1 + arch/parisc/include/uapi/asm/byteorder.h | 1 + arch/parisc/include/uapi/asm/errno.h | 1 + arch/parisc/include/uapi/asm/fcntl.h | 1 + arch/parisc/include/uapi/asm/ioctls.h | 1 + arch/parisc/include/uapi/asm/ipcbuf.h | 1 + arch/parisc/include/uapi/asm/mman.h | 1 + arch/parisc/include/uapi/asm/msgbuf.h | 1 + arch/parisc/include/uapi/asm/pdc.h | 1 + arch/parisc/include/uapi/asm/posix_types.h | 1 + arch/parisc/include/uapi/asm/ptrace.h | 1 + arch/parisc/include/uapi/asm/sembuf.h | 1 + arch/parisc/include/uapi/asm/setup.h | 1 + arch/parisc/include/uapi/asm/shmbuf.h | 1 + arch/parisc/include/uapi/asm/sigcontext.h | 1 + arch/parisc/include/uapi/asm/siginfo.h | 1 + arch/parisc/include/uapi/asm/signal.h | 1 + arch/parisc/include/uapi/asm/socket.h | 1 + arch/parisc/include/uapi/asm/sockios.h | 1 + arch/parisc/include/uapi/asm/stat.h | 1 + arch/parisc/include/uapi/asm/statfs.h | 1 + arch/parisc/include/uapi/asm/swab.h | 1 + arch/parisc/include/uapi/asm/termbits.h | 1 + arch/parisc/include/uapi/asm/termios.h | 1 + arch/parisc/include/uapi/asm/types.h | 1 + arch/parisc/include/uapi/asm/unistd.h | 1 + arch/powerpc/include/uapi/asm/auxvec.h | 1 + arch/powerpc/include/uapi/asm/bitsperlong.h | 1 + arch/powerpc/include/uapi/asm/bootx.h | 1 + arch/powerpc/include/uapi/asm/cputable.h | 1 + arch/powerpc/include/uapi/asm/errno.h | 1 + arch/powerpc/include/uapi/asm/fcntl.h | 1 + arch/powerpc/include/uapi/asm/ioctl.h | 1 + arch/powerpc/include/uapi/asm/ioctls.h | 1 + arch/powerpc/include/uapi/asm/msgbuf.h | 1 + arch/powerpc/include/uapi/asm/perf_regs.h | 1 + arch/powerpc/include/uapi/asm/posix_types.h | 1 + arch/powerpc/include/uapi/asm/setup.h | 1 + arch/powerpc/include/uapi/asm/signal.h | 1 + arch/powerpc/include/uapi/asm/tm.h | 1 + arch/powerpc/include/uapi/asm/ucontext.h | 1 + arch/s390/include/uapi/asm/auxvec.h | 1 + arch/s390/include/uapi/asm/bitsperlong.h | 1 + arch/s390/include/uapi/asm/byteorder.h | 1 + arch/s390/include/uapi/asm/chpid.h | 1 + arch/s390/include/uapi/asm/chsc.h | 1 + arch/s390/include/uapi/asm/clp.h | 1 + arch/s390/include/uapi/asm/cmb.h | 1 + arch/s390/include/uapi/asm/dasd.h | 1 + arch/s390/include/uapi/asm/debug.h | 1 + arch/s390/include/uapi/asm/guarded_storage.h | 1 + arch/s390/include/uapi/asm/hypfs.h | 1 + arch/s390/include/uapi/asm/ioctls.h | 1 + arch/s390/include/uapi/asm/ipcbuf.h | 1 + arch/s390/include/uapi/asm/monwriter.h | 1 + arch/s390/include/uapi/asm/msgbuf.h | 1 + arch/s390/include/uapi/asm/pkey.h | 1 + arch/s390/include/uapi/asm/posix_types.h | 1 + arch/s390/include/uapi/asm/ptrace.h | 1 + arch/s390/include/uapi/asm/qeth.h | 1 + arch/s390/include/uapi/asm/schid.h | 1 + arch/s390/include/uapi/asm/sclp_ctl.h | 1 + arch/s390/include/uapi/asm/sembuf.h | 1 + arch/s390/include/uapi/asm/setup.h | 1 + arch/s390/include/uapi/asm/shmbuf.h | 1 + arch/s390/include/uapi/asm/sie.h | 1 + arch/s390/include/uapi/asm/sigcontext.h | 1 + arch/s390/include/uapi/asm/siginfo.h | 1 + arch/s390/include/uapi/asm/signal.h | 1 + arch/s390/include/uapi/asm/socket.h | 1 + arch/s390/include/uapi/asm/stat.h | 1 + arch/s390/include/uapi/asm/statfs.h | 1 + arch/s390/include/uapi/asm/tape390.h | 1 + arch/s390/include/uapi/asm/termios.h | 1 + arch/s390/include/uapi/asm/types.h | 1 + arch/s390/include/uapi/asm/ucontext.h | 1 + arch/s390/include/uapi/asm/unistd.h | 1 + arch/s390/include/uapi/asm/vtoc.h | 1 + arch/score/include/uapi/asm/bitsperlong.h | 1 + arch/score/include/uapi/asm/byteorder.h | 1 + arch/score/include/uapi/asm/errno.h | 1 + arch/score/include/uapi/asm/fcntl.h | 1 + arch/score/include/uapi/asm/ioctl.h | 1 + arch/score/include/uapi/asm/ioctls.h | 1 + arch/score/include/uapi/asm/ipcbuf.h | 1 + arch/score/include/uapi/asm/kvm_para.h | 1 + arch/score/include/uapi/asm/mman.h | 1 + arch/score/include/uapi/asm/msgbuf.h | 1 + arch/score/include/uapi/asm/param.h | 1 + arch/score/include/uapi/asm/poll.h | 1 + arch/score/include/uapi/asm/posix_types.h | 1 + arch/score/include/uapi/asm/ptrace.h | 1 + arch/score/include/uapi/asm/resource.h | 1 + arch/score/include/uapi/asm/sembuf.h | 1 + arch/score/include/uapi/asm/setup.h | 1 + arch/score/include/uapi/asm/shmbuf.h | 1 + arch/score/include/uapi/asm/sigcontext.h | 1 + arch/score/include/uapi/asm/signal.h | 1 + arch/score/include/uapi/asm/socket.h | 1 + arch/score/include/uapi/asm/sockios.h | 1 + arch/score/include/uapi/asm/stat.h | 1 + arch/score/include/uapi/asm/statfs.h | 1 + arch/score/include/uapi/asm/swab.h | 1 + arch/score/include/uapi/asm/termbits.h | 1 + arch/score/include/uapi/asm/termios.h | 1 + arch/score/include/uapi/asm/types.h | 1 + arch/score/include/uapi/asm/unistd.h | 1 + arch/sh/include/uapi/asm/auxvec.h | 1 + arch/sh/include/uapi/asm/byteorder.h | 1 + arch/sh/include/uapi/asm/cachectl.h | 1 + arch/sh/include/uapi/asm/cpu-features.h | 1 + arch/sh/include/uapi/asm/hw_breakpoint.h | 1 + arch/sh/include/uapi/asm/ioctls.h | 1 + arch/sh/include/uapi/asm/posix_types.h | 1 + arch/sh/include/uapi/asm/posix_types_32.h | 1 + arch/sh/include/uapi/asm/posix_types_64.h | 1 + arch/sh/include/uapi/asm/ptrace.h | 1 + arch/sh/include/uapi/asm/ptrace_32.h | 1 + arch/sh/include/uapi/asm/ptrace_64.h | 1 + arch/sh/include/uapi/asm/sigcontext.h | 1 + arch/sh/include/uapi/asm/signal.h | 1 + arch/sh/include/uapi/asm/sockios.h | 1 + arch/sh/include/uapi/asm/stat.h | 1 + arch/sh/include/uapi/asm/swab.h | 1 + arch/sh/include/uapi/asm/unistd.h | 1 + arch/sh/include/uapi/asm/unistd_32.h | 1 + arch/sparc/include/uapi/asm/apc.h | 1 + arch/sparc/include/uapi/asm/asi.h | 1 + arch/sparc/include/uapi/asm/bitsperlong.h | 1 + arch/sparc/include/uapi/asm/byteorder.h | 1 + arch/sparc/include/uapi/asm/display7seg.h | 1 + arch/sparc/include/uapi/asm/envctrl.h | 1 + arch/sparc/include/uapi/asm/errno.h | 1 + arch/sparc/include/uapi/asm/fbio.h | 1 + arch/sparc/include/uapi/asm/fcntl.h | 1 + arch/sparc/include/uapi/asm/ioctl.h | 1 + arch/sparc/include/uapi/asm/ioctls.h | 1 + arch/sparc/include/uapi/asm/ipcbuf.h | 1 + arch/sparc/include/uapi/asm/jsflash.h | 1 + arch/sparc/include/uapi/asm/kvm_para.h | 1 + arch/sparc/include/uapi/asm/mman.h | 1 + arch/sparc/include/uapi/asm/msgbuf.h | 1 + arch/sparc/include/uapi/asm/openpromio.h | 1 + arch/sparc/include/uapi/asm/param.h | 1 + arch/sparc/include/uapi/asm/perfctr.h | 1 + arch/sparc/include/uapi/asm/poll.h | 1 + arch/sparc/include/uapi/asm/posix_types.h | 1 + arch/sparc/include/uapi/asm/psr.h | 1 + arch/sparc/include/uapi/asm/psrcompat.h | 1 + arch/sparc/include/uapi/asm/pstate.h | 1 + arch/sparc/include/uapi/asm/ptrace.h | 1 + arch/sparc/include/uapi/asm/resource.h | 1 + arch/sparc/include/uapi/asm/sembuf.h | 1 + arch/sparc/include/uapi/asm/setup.h | 1 + arch/sparc/include/uapi/asm/shmbuf.h | 1 + arch/sparc/include/uapi/asm/sigcontext.h | 1 + arch/sparc/include/uapi/asm/siginfo.h | 1 + arch/sparc/include/uapi/asm/signal.h | 1 + arch/sparc/include/uapi/asm/socket.h | 1 + arch/sparc/include/uapi/asm/sockios.h | 1 + arch/sparc/include/uapi/asm/stat.h | 1 + arch/sparc/include/uapi/asm/statfs.h | 1 + arch/sparc/include/uapi/asm/swab.h | 1 + arch/sparc/include/uapi/asm/termbits.h | 1 + arch/sparc/include/uapi/asm/termios.h | 1 + arch/sparc/include/uapi/asm/traps.h | 1 + arch/sparc/include/uapi/asm/uctx.h | 1 + arch/sparc/include/uapi/asm/unistd.h | 1 + arch/sparc/include/uapi/asm/utrap.h | 1 + arch/sparc/include/uapi/asm/watchdog.h | 1 + arch/tile/include/uapi/asm/kvm_para.h | 1 + arch/tile/include/uapi/asm/stat.h | 1 + arch/x86/include/uapi/asm/a.out.h | 1 + arch/x86/include/uapi/asm/auxvec.h | 1 + arch/x86/include/uapi/asm/bitsperlong.h | 1 + arch/x86/include/uapi/asm/boot.h | 1 + arch/x86/include/uapi/asm/bootparam.h | 1 + arch/x86/include/uapi/asm/debugreg.h | 1 + arch/x86/include/uapi/asm/e820.h | 1 + arch/x86/include/uapi/asm/hw_breakpoint.h | 1 + arch/x86/include/uapi/asm/hyperv.h | 1 + arch/x86/include/uapi/asm/kvm.h | 1 + arch/x86/include/uapi/asm/kvm_para.h | 1 + arch/x86/include/uapi/asm/kvm_perf.h | 1 + arch/x86/include/uapi/asm/ldt.h | 1 + arch/x86/include/uapi/asm/mce.h | 1 + arch/x86/include/uapi/asm/mman.h | 1 + arch/x86/include/uapi/asm/msr.h | 1 + arch/x86/include/uapi/asm/perf_regs.h | 1 + arch/x86/include/uapi/asm/posix_types.h | 1 + arch/x86/include/uapi/asm/posix_types_32.h | 1 + arch/x86/include/uapi/asm/posix_types_64.h | 1 + arch/x86/include/uapi/asm/posix_types_x32.h | 1 + arch/x86/include/uapi/asm/prctl.h | 1 + arch/x86/include/uapi/asm/processor-flags.h | 1 + arch/x86/include/uapi/asm/ptrace-abi.h | 1 + arch/x86/include/uapi/asm/ptrace.h | 1 + arch/x86/include/uapi/asm/sembuf.h | 1 + arch/x86/include/uapi/asm/sigcontext.h | 1 + arch/x86/include/uapi/asm/siginfo.h | 1 + arch/x86/include/uapi/asm/signal.h | 1 + arch/x86/include/uapi/asm/stat.h | 1 + arch/x86/include/uapi/asm/statfs.h | 1 + arch/x86/include/uapi/asm/svm.h | 1 + arch/x86/include/uapi/asm/swab.h | 1 + arch/x86/include/uapi/asm/ucontext.h | 1 + arch/x86/include/uapi/asm/unistd.h | 1 + arch/x86/include/uapi/asm/vm86.h | 1 + arch/x86/include/uapi/asm/vsyscall.h | 1 + arch/xtensa/include/uapi/asm/byteorder.h | 1 + arch/xtensa/include/uapi/asm/unistd.h | 1 + include/uapi/asm-generic/bitsperlong.h | 1 + include/uapi/asm-generic/errno-base.h | 1 + include/uapi/asm-generic/errno.h | 1 + include/uapi/asm-generic/fcntl.h | 1 + include/uapi/asm-generic/int-l64.h | 1 + include/uapi/asm-generic/int-ll64.h | 1 + include/uapi/asm-generic/ioctl.h | 1 + include/uapi/asm-generic/ioctls.h | 1 + include/uapi/asm-generic/ipcbuf.h | 1 + include/uapi/asm-generic/mman-common.h | 1 + include/uapi/asm-generic/mman.h | 1 + include/uapi/asm-generic/msgbuf.h | 1 + include/uapi/asm-generic/param.h | 1 + include/uapi/asm-generic/poll.h | 1 + include/uapi/asm-generic/posix_types.h | 1 + include/uapi/asm-generic/resource.h | 1 + include/uapi/asm-generic/sembuf.h | 1 + include/uapi/asm-generic/setup.h | 1 + include/uapi/asm-generic/shmbuf.h | 1 + include/uapi/asm-generic/shmparam.h | 1 + include/uapi/asm-generic/siginfo.h | 1 + include/uapi/asm-generic/signal-defs.h | 1 + include/uapi/asm-generic/signal.h | 1 + include/uapi/asm-generic/socket.h | 1 + include/uapi/asm-generic/sockios.h | 1 + include/uapi/asm-generic/stat.h | 1 + include/uapi/asm-generic/statfs.h | 1 + include/uapi/asm-generic/swab.h | 1 + include/uapi/asm-generic/termbits.h | 1 + include/uapi/asm-generic/termios.h | 1 + include/uapi/asm-generic/types.h | 1 + include/uapi/asm-generic/ucontext.h | 1 + include/uapi/asm-generic/unistd.h | 1 + include/uapi/drm/i810_drm.h | 1 + include/uapi/linux/a.out.h | 1 + include/uapi/linux/acct.h | 1 + include/uapi/linux/adb.h | 1 + include/uapi/linux/adfs_fs.h | 1 + include/uapi/linux/affs_hardblocks.h | 1 + include/uapi/linux/arcfb.h | 1 + include/uapi/linux/atalk.h | 1 + include/uapi/linux/atm.h | 1 + include/uapi/linux/atm_eni.h | 1 + include/uapi/linux/atm_he.h | 1 + include/uapi/linux/atm_idt77105.h | 1 + include/uapi/linux/atm_nicstar.h | 1 + include/uapi/linux/atm_tcp.h | 1 + include/uapi/linux/atm_zatm.h | 1 + include/uapi/linux/atmapi.h | 1 + include/uapi/linux/atmarp.h | 1 + include/uapi/linux/atmbr2684.h | 1 + include/uapi/linux/atmclip.h | 1 + include/uapi/linux/atmdev.h | 1 + include/uapi/linux/atmioc.h | 1 + include/uapi/linux/atmlec.h | 1 + include/uapi/linux/atmmpc.h | 1 + include/uapi/linux/atmppp.h | 1 + include/uapi/linux/atmsap.h | 1 + include/uapi/linux/atmsvc.h | 1 + include/uapi/linux/auxvec.h | 1 + include/uapi/linux/ax25.h | 1 + include/uapi/linux/baycom.h | 1 + include/uapi/linux/bcache.h | 1 + include/uapi/linux/bcm933xx_hcs.h | 1 + include/uapi/linux/bfs_fs.h | 1 + include/uapi/linux/binfmts.h | 1 + include/uapi/linux/blkpg.h | 1 + include/uapi/linux/blktrace_api.h | 1 + include/uapi/linux/bpf_common.h | 1 + include/uapi/linux/bpqether.h | 1 + include/uapi/linux/bsg.h | 1 + include/uapi/linux/btrfs_tree.h | 1 + include/uapi/linux/byteorder/big_endian.h | 1 + include/uapi/linux/byteorder/little_endian.h | 1 + include/uapi/linux/can/vxcan.h | 1 + include/uapi/linux/capability.h | 1 + include/uapi/linux/cciss_defs.h | 1 + include/uapi/linux/cciss_ioctl.h | 1 + include/uapi/linux/cdrom.h | 1 + include/uapi/linux/chio.h | 1 + include/uapi/linux/cm4000_cs.h | 1 + include/uapi/linux/coda_psdev.h | 1 + include/uapi/linux/const.h | 1 + include/uapi/linux/coresight-stm.h | 1 + include/uapi/linux/cramfs_fs.h | 1 + include/uapi/linux/cuda.h | 1 + include/uapi/linux/cyclades.h | 1 + include/uapi/linux/dccp.h | 1 + include/uapi/linux/dn.h | 1 + include/uapi/linux/efs_fs_sb.h | 1 + include/uapi/linux/elf-em.h | 1 + include/uapi/linux/elf.h | 1 + include/uapi/linux/elfcore.h | 1 + include/uapi/linux/errqueue.h | 1 + include/uapi/linux/ethtool.h | 1 + include/uapi/linux/fadvise.h | 1 + include/uapi/linux/falloc.h | 1 + include/uapi/linux/fanotify.h | 1 + include/uapi/linux/fb.h | 1 + include/uapi/linux/fcntl.h | 1 + include/uapi/linux/fd.h | 1 + include/uapi/linux/fdreg.h | 1 + include/uapi/linux/fib_rules.h | 1 + include/uapi/linux/fiemap.h | 1 + include/uapi/linux/filter.h | 1 + include/uapi/linux/flat.h | 1 + include/uapi/linux/fou.h | 1 + include/uapi/linux/fs.h | 1 + include/uapi/linux/fsmap.h | 1 + include/uapi/linux/futex.h | 1 + include/uapi/linux/gen_stats.h | 1 + include/uapi/linux/genetlink.h | 1 + include/uapi/linux/gsmmux.h | 1 + include/uapi/linux/gtp.h | 1 + include/uapi/linux/hdlc/ioctl.h | 1 + include/uapi/linux/hdlcdrv.h | 1 + include/uapi/linux/hdreg.h | 1 + include/uapi/linux/hpet.h | 1 + include/uapi/linux/hw_breakpoint.h | 1 + include/uapi/linux/icmpv6.h | 1 + include/uapi/linux/if_addr.h | 1 + include/uapi/linux/if_addrlabel.h | 1 + include/uapi/linux/if_link.h | 1 + include/uapi/linux/if_ltalk.h | 1 + include/uapi/linux/if_packet.h | 1 + include/uapi/linux/if_phonet.h | 1 + include/uapi/linux/if_slip.h | 1 + include/uapi/linux/if_tunnel.h | 1 + include/uapi/linux/ife.h | 1 + include/uapi/linux/ila.h | 1 + include/uapi/linux/in_route.h | 1 + include/uapi/linux/inet_diag.h | 1 + include/uapi/linux/inotify.h | 1 + include/uapi/linux/ioctl.h | 1 + include/uapi/linux/ip6_tunnel.h | 1 + include/uapi/linux/ip_vs.h | 1 + include/uapi/linux/ipc.h | 1 + include/uapi/linux/ipsec.h | 1 + include/uapi/linux/ipv6.h | 1 + include/uapi/linux/ipx.h | 1 + include/uapi/linux/iso_fs.h | 1 + include/uapi/linux/kcmp.h | 1 + include/uapi/linux/kcov.h | 1 + include/uapi/linux/kd.h | 1 + include/uapi/linux/kdev_t.h | 1 + include/uapi/linux/kernel-page-flags.h | 1 + include/uapi/linux/kernel.h | 1 + include/uapi/linux/kernelcapi.h | 1 + include/uapi/linux/kexec.h | 1 + include/uapi/linux/keyboard.h | 1 + include/uapi/linux/kvm.h | 1 + include/uapi/linux/kvm_para.h | 1 + include/uapi/linux/l2tp.h | 1 + include/uapi/linux/libc-compat.h | 1 + include/uapi/linux/limits.h | 1 + include/uapi/linux/lirc.h | 1 + include/uapi/linux/lp.h | 1 + include/uapi/linux/lwtunnel.h | 1 + include/uapi/linux/magic.h | 1 + include/uapi/linux/major.h | 1 + include/uapi/linux/matroxfb.h | 1 + include/uapi/linux/memfd.h | 1 + include/uapi/linux/mempolicy.h | 1 + include/uapi/linux/mii.h | 1 + include/uapi/linux/minix_fs.h | 1 + include/uapi/linux/mman.h | 1 + include/uapi/linux/mmc/ioctl.h | 1 + include/uapi/linux/module.h | 1 + include/uapi/linux/mpls.h | 1 + include/uapi/linux/mroute.h | 1 + include/uapi/linux/mroute6.h | 1 + include/uapi/linux/msdos_fs.h | 1 + include/uapi/linux/msg.h | 1 + include/uapi/linux/mtio.h | 1 + include/uapi/linux/ncp.h | 1 + include/uapi/linux/ncp_fs.h | 1 + include/uapi/linux/ncp_mount.h | 1 + include/uapi/linux/ncp_no.h | 1 + include/uapi/linux/neighbour.h | 1 + include/uapi/linux/net_dropmon.h | 1 + include/uapi/linux/net_tstamp.h | 1 + include/uapi/linux/netconf.h | 1 + include/uapi/linux/netfilter.h | 1 + include/uapi/linux/netfilter/ipset/ip_set_bitmap.h | 1 + include/uapi/linux/netfilter/ipset/ip_set_hash.h | 1 + include/uapi/linux/netfilter/ipset/ip_set_list.h | 1 + include/uapi/linux/netfilter/nf_conntrack_common.h | 1 + include/uapi/linux/netfilter/nf_conntrack_ftp.h | 1 + include/uapi/linux/netfilter/nf_conntrack_sctp.h | 1 + include/uapi/linux/netfilter/nf_conntrack_tcp.h | 1 + include/uapi/linux/netfilter/nf_conntrack_tuple_common.h | 1 + include/uapi/linux/netfilter/nf_log.h | 1 + include/uapi/linux/netfilter/nf_nat.h | 1 + include/uapi/linux/netfilter/nf_tables.h | 1 + include/uapi/linux/netfilter/nf_tables_compat.h | 1 + include/uapi/linux/netfilter/nfnetlink.h | 1 + include/uapi/linux/netfilter/nfnetlink_acct.h | 1 + include/uapi/linux/netfilter/nfnetlink_compat.h | 1 + include/uapi/linux/netfilter/nfnetlink_conntrack.h | 1 + include/uapi/linux/netfilter/nfnetlink_cthelper.h | 1 + include/uapi/linux/netfilter/nfnetlink_cttimeout.h | 1 + include/uapi/linux/netfilter/nfnetlink_log.h | 1 + include/uapi/linux/netfilter/nfnetlink_queue.h | 1 + include/uapi/linux/netfilter/x_tables.h | 1 + include/uapi/linux/netfilter/xt_CLASSIFY.h | 1 + include/uapi/linux/netfilter/xt_CONNMARK.h | 1 + include/uapi/linux/netfilter/xt_CONNSECMARK.h | 1 + include/uapi/linux/netfilter/xt_CT.h | 1 + include/uapi/linux/netfilter/xt_HMARK.h | 1 + include/uapi/linux/netfilter/xt_LED.h | 1 + include/uapi/linux/netfilter/xt_LOG.h | 1 + include/uapi/linux/netfilter/xt_MARK.h | 1 + include/uapi/linux/netfilter/xt_NFLOG.h | 1 + include/uapi/linux/netfilter/xt_RATEEST.h | 1 + include/uapi/linux/netfilter/xt_SECMARK.h | 1 + include/uapi/linux/netfilter/xt_SYNPROXY.h | 1 + include/uapi/linux/netfilter/xt_TCPMSS.h | 1 + include/uapi/linux/netfilter/xt_TCPOPTSTRIP.h | 1 + include/uapi/linux/netfilter/xt_TEE.h | 1 + include/uapi/linux/netfilter/xt_TPROXY.h | 1 + include/uapi/linux/netfilter/xt_addrtype.h | 1 + include/uapi/linux/netfilter/xt_bpf.h | 1 + include/uapi/linux/netfilter/xt_cgroup.h | 1 + include/uapi/linux/netfilter/xt_cluster.h | 1 + include/uapi/linux/netfilter/xt_comment.h | 1 + include/uapi/linux/netfilter/xt_connbytes.h | 1 + include/uapi/linux/netfilter/xt_connlabel.h | 1 + include/uapi/linux/netfilter/xt_connlimit.h | 1 + include/uapi/linux/netfilter/xt_cpu.h | 1 + include/uapi/linux/netfilter/xt_dccp.h | 1 + include/uapi/linux/netfilter/xt_devgroup.h | 1 + include/uapi/linux/netfilter/xt_esp.h | 1 + include/uapi/linux/netfilter/xt_hashlimit.h | 1 + include/uapi/linux/netfilter/xt_helper.h | 1 + include/uapi/linux/netfilter/xt_ipcomp.h | 1 + include/uapi/linux/netfilter/xt_iprange.h | 1 + include/uapi/linux/netfilter/xt_ipvs.h | 1 + include/uapi/linux/netfilter/xt_l2tp.h | 1 + include/uapi/linux/netfilter/xt_length.h | 1 + include/uapi/linux/netfilter/xt_limit.h | 1 + include/uapi/linux/netfilter/xt_mac.h | 1 + include/uapi/linux/netfilter/xt_mark.h | 1 + include/uapi/linux/netfilter/xt_multiport.h | 1 + include/uapi/linux/netfilter/xt_nfacct.h | 1 + include/uapi/linux/netfilter/xt_owner.h | 1 + include/uapi/linux/netfilter/xt_physdev.h | 1 + include/uapi/linux/netfilter/xt_pkttype.h | 1 + include/uapi/linux/netfilter/xt_policy.h | 1 + include/uapi/linux/netfilter/xt_quota.h | 1 + include/uapi/linux/netfilter/xt_rateest.h | 1 + include/uapi/linux/netfilter/xt_realm.h | 1 + include/uapi/linux/netfilter/xt_recent.h | 1 + include/uapi/linux/netfilter/xt_rpfilter.h | 1 + include/uapi/linux/netfilter/xt_sctp.h | 1 + include/uapi/linux/netfilter/xt_set.h | 1 + include/uapi/linux/netfilter/xt_socket.h | 1 + include/uapi/linux/netfilter/xt_state.h | 1 + include/uapi/linux/netfilter/xt_statistic.h | 1 + include/uapi/linux/netfilter/xt_string.h | 1 + include/uapi/linux/netfilter/xt_tcpmss.h | 1 + include/uapi/linux/netfilter/xt_tcpudp.h | 1 + include/uapi/linux/netfilter/xt_time.h | 1 + include/uapi/linux/netfilter/xt_u32.h | 1 + include/uapi/linux/netfilter_arp/arp_tables.h | 1 + include/uapi/linux/netfilter_arp/arpt_mangle.h | 1 + include/uapi/linux/netfilter_bridge.h | 1 + include/uapi/linux/netfilter_bridge/ebt_802_3.h | 1 + include/uapi/linux/netfilter_bridge/ebt_among.h | 1 + include/uapi/linux/netfilter_bridge/ebt_arp.h | 1 + include/uapi/linux/netfilter_bridge/ebt_arpreply.h | 1 + include/uapi/linux/netfilter_bridge/ebt_ip.h | 1 + include/uapi/linux/netfilter_bridge/ebt_ip6.h | 1 + include/uapi/linux/netfilter_bridge/ebt_limit.h | 1 + include/uapi/linux/netfilter_bridge/ebt_log.h | 1 + include/uapi/linux/netfilter_bridge/ebt_mark_m.h | 1 + include/uapi/linux/netfilter_bridge/ebt_mark_t.h | 1 + include/uapi/linux/netfilter_bridge/ebt_nat.h | 1 + include/uapi/linux/netfilter_bridge/ebt_nflog.h | 1 + include/uapi/linux/netfilter_bridge/ebt_pkttype.h | 1 + include/uapi/linux/netfilter_bridge/ebt_redirect.h | 1 + include/uapi/linux/netfilter_bridge/ebt_stp.h | 1 + include/uapi/linux/netfilter_bridge/ebt_vlan.h | 1 + include/uapi/linux/netfilter_bridge/ebtables.h | 1 + include/uapi/linux/netfilter_ipv4/ip_tables.h | 1 + include/uapi/linux/netfilter_ipv4/ipt_CLUSTERIP.h | 1 + include/uapi/linux/netfilter_ipv4/ipt_LOG.h | 1 + include/uapi/linux/netfilter_ipv4/ipt_REJECT.h | 1 + include/uapi/linux/netfilter_ipv4/ipt_TTL.h | 1 + include/uapi/linux/netfilter_ipv4/ipt_ah.h | 1 + include/uapi/linux/netfilter_ipv4/ipt_ecn.h | 1 + include/uapi/linux/netfilter_ipv4/ipt_ttl.h | 1 + include/uapi/linux/netfilter_ipv6/ip6_tables.h | 1 + include/uapi/linux/netfilter_ipv6/ip6t_HL.h | 1 + include/uapi/linux/netfilter_ipv6/ip6t_LOG.h | 1 + include/uapi/linux/netfilter_ipv6/ip6t_NPT.h | 1 + include/uapi/linux/netfilter_ipv6/ip6t_REJECT.h | 1 + include/uapi/linux/netfilter_ipv6/ip6t_ah.h | 1 + include/uapi/linux/netfilter_ipv6/ip6t_frag.h | 1 + include/uapi/linux/netfilter_ipv6/ip6t_hl.h | 1 + include/uapi/linux/netfilter_ipv6/ip6t_ipv6header.h | 1 + include/uapi/linux/netfilter_ipv6/ip6t_mh.h | 1 + include/uapi/linux/netfilter_ipv6/ip6t_opts.h | 1 + include/uapi/linux/netfilter_ipv6/ip6t_rt.h | 1 + include/uapi/linux/netlink.h | 1 + include/uapi/linux/netlink_diag.h | 1 + include/uapi/linux/netrom.h | 1 + include/uapi/linux/nfs.h | 1 + include/uapi/linux/nfs2.h | 1 + include/uapi/linux/nfs3.h | 1 + include/uapi/linux/nfs4.h | 1 + include/uapi/linux/nfs4_mount.h | 1 + include/uapi/linux/nfs_fs.h | 1 + include/uapi/linux/nfs_mount.h | 1 + include/uapi/linux/nfsacl.h | 1 + include/uapi/linux/nfsd/debug.h | 1 + include/uapi/linux/nfsd/export.h | 1 + include/uapi/linux/nfsd/nfsfh.h | 1 + include/uapi/linux/nfsd/stats.h | 1 + include/uapi/linux/nsfs.h | 1 + include/uapi/linux/nubus.h | 1 + include/uapi/linux/nvram.h | 1 + include/uapi/linux/oom.h | 1 + include/uapi/linux/packet_diag.h | 1 + include/uapi/linux/param.h | 1 + include/uapi/linux/patchkey.h | 1 + include/uapi/linux/pci.h | 1 + include/uapi/linux/pci_regs.h | 1 + include/uapi/linux/pcitest.h | 1 + include/uapi/linux/personality.h | 1 + include/uapi/linux/pfkeyv2.h | 1 + include/uapi/linux/pkt_cls.h | 1 + include/uapi/linux/pkt_sched.h | 1 + include/uapi/linux/pmu.h | 1 + include/uapi/linux/posix_types.h | 1 + include/uapi/linux/pr.h | 1 + include/uapi/linux/prctl.h | 1 + include/uapi/linux/psample.h | 1 + include/uapi/linux/psci.h | 1 + include/uapi/linux/ptrace.h | 1 + include/uapi/linux/qnx4_fs.h | 1 + include/uapi/linux/qnxtypes.h | 1 + include/uapi/linux/qrtr.h | 1 + include/uapi/linux/radeonfb.h | 1 + include/uapi/linux/random.h | 1 + include/uapi/linux/raw.h | 1 + include/uapi/linux/reboot.h | 1 + include/uapi/linux/reiserfs_fs.h | 1 + include/uapi/linux/reiserfs_xattr.h | 1 + include/uapi/linux/resource.h | 1 + include/uapi/linux/romfs_fs.h | 1 + include/uapi/linux/rose.h | 1 + include/uapi/linux/rtc.h | 1 + include/uapi/linux/rtnetlink.h | 1 + include/uapi/linux/scc.h | 1 + include/uapi/linux/sched.h | 1 + include/uapi/linux/sched/types.h | 1 + include/uapi/linux/screen_info.h | 1 + include/uapi/linux/seccomp.h | 1 + include/uapi/linux/securebits.h | 1 + include/uapi/linux/seg6_genl.h | 1 + include/uapi/linux/seg6_hmac.h | 1 + include/uapi/linux/sem.h | 1 + include/uapi/linux/shm.h | 1 + include/uapi/linux/signal.h | 1 + include/uapi/linux/signalfd.h | 1 + include/uapi/linux/smc.h | 1 + include/uapi/linux/smc_diag.h | 1 + include/uapi/linux/snmp.h | 1 + include/uapi/linux/sock_diag.h | 1 + include/uapi/linux/socket.h | 1 + include/uapi/linux/sonet.h | 1 + include/uapi/linux/sound.h | 1 + include/uapi/linux/stat.h | 1 + include/uapi/linux/stddef.h | 1 + include/uapi/linux/string.h | 1 + include/uapi/linux/sunrpc/debug.h | 1 + include/uapi/linux/suspend_ioctls.h | 1 + include/uapi/linux/swab.h | 1 + include/uapi/linux/sysctl.h | 1 + include/uapi/linux/sysinfo.h | 1 + include/uapi/linux/target_core_user.h | 1 + include/uapi/linux/tc_act/tc_connmark.h | 1 + include/uapi/linux/tc_act/tc_csum.h | 1 + include/uapi/linux/tc_act/tc_defact.h | 1 + include/uapi/linux/tc_act/tc_gact.h | 1 + include/uapi/linux/tc_act/tc_ife.h | 1 + include/uapi/linux/tc_act/tc_ipt.h | 1 + include/uapi/linux/tc_act/tc_mirred.h | 1 + include/uapi/linux/tc_act/tc_nat.h | 1 + include/uapi/linux/tc_act/tc_pedit.h | 1 + include/uapi/linux/tc_act/tc_sample.h | 1 + include/uapi/linux/tc_ematch/tc_em_cmp.h | 1 + include/uapi/linux/tc_ematch/tc_em_meta.h | 1 + include/uapi/linux/tc_ematch/tc_em_nbyte.h | 1 + include/uapi/linux/tc_ematch/tc_em_text.h | 1 + include/uapi/linux/tcp_metrics.h | 1 + include/uapi/linux/termios.h | 1 + include/uapi/linux/thermal.h | 1 + include/uapi/linux/time.h | 1 + include/uapi/linux/timerfd.h | 1 + include/uapi/linux/times.h | 1 + include/uapi/linux/tiocl.h | 1 + include/uapi/linux/tty.h | 1 + include/uapi/linux/tty_flags.h | 1 + include/uapi/linux/types.h | 1 + include/uapi/linux/un.h | 1 + include/uapi/linux/unistd.h | 1 + include/uapi/linux/unix_diag.h | 1 + include/uapi/linux/usb/cdc.h | 1 + include/uapi/linux/usb/ch11.h | 1 + include/uapi/linux/usb/ch9.h | 1 + include/uapi/linux/usb/functionfs.h | 1 + include/uapi/linux/usb/gadgetfs.h | 1 + include/uapi/linux/usb/tmc.h | 1 + include/uapi/linux/usb/video.h | 1 + include/uapi/linux/usbip.h | 1 + include/uapi/linux/userfaultfd.h | 1 + include/uapi/linux/utime.h | 1 + include/uapi/linux/utsname.h | 1 + include/uapi/linux/uvcvideo.h | 1 + include/uapi/linux/veth.h | 1 + include/uapi/linux/vfio_ccw.h | 1 + include/uapi/linux/vhost.h | 1 + include/uapi/linux/vsockmon.h | 1 + include/uapi/linux/vt.h | 1 + include/uapi/linux/wait.h | 1 + include/uapi/linux/wanrouter.h | 1 + include/uapi/linux/watchdog.h | 1 + include/uapi/linux/wireless.h | 1 + include/uapi/linux/x25.h | 1 + include/uapi/linux/xattr.h | 1 + include/uapi/linux/xfrm.h | 1 + include/uapi/linux/zorro_ids.h | 1 + include/uapi/mtd/inftl-user.h | 1 + include/uapi/rdma/rdma_netlink.h | 1 + include/uapi/sound/firewire.h | 1 + include/uapi/video/edid.h | 1 + include/uapi/video/uvesafb.h | 1 + tools/arch/alpha/include/uapi/asm/bitsperlong.h | 1 + tools/arch/alpha/include/uapi/asm/mman.h | 1 + tools/arch/arc/include/uapi/asm/mman.h | 1 + tools/arch/arm/include/uapi/asm/mman.h | 1 + tools/arch/arm/include/uapi/asm/perf_regs.h | 1 + tools/arch/arm64/include/uapi/asm/mman.h | 1 + tools/arch/arm64/include/uapi/asm/perf_regs.h | 1 + tools/arch/frv/include/uapi/asm/bitsperlong.h | 1 + tools/arch/frv/include/uapi/asm/mman.h | 1 + tools/arch/h8300/include/uapi/asm/mman.h | 1 + tools/arch/hexagon/include/uapi/asm/mman.h | 1 + tools/arch/ia64/include/uapi/asm/bitsperlong.h | 1 + tools/arch/ia64/include/uapi/asm/mman.h | 1 + tools/arch/m32r/include/uapi/asm/bitsperlong.h | 1 + tools/arch/m32r/include/uapi/asm/mman.h | 1 + tools/arch/microblaze/include/uapi/asm/bitsperlong.h | 1 + tools/arch/microblaze/include/uapi/asm/mman.h | 1 + tools/arch/mips/include/uapi/asm/mman.h | 1 + tools/arch/mn10300/include/uapi/asm/mman.h | 1 + tools/arch/parisc/include/uapi/asm/bitsperlong.h | 1 + tools/arch/parisc/include/uapi/asm/mman.h | 1 + tools/arch/powerpc/include/uapi/asm/bitsperlong.h | 1 + tools/arch/powerpc/include/uapi/asm/mman.h | 1 + tools/arch/powerpc/include/uapi/asm/perf_regs.h | 1 + tools/arch/s390/include/uapi/asm/bitsperlong.h | 1 + tools/arch/s390/include/uapi/asm/mman.h | 1 + tools/arch/s390/include/uapi/asm/sie.h | 1 + tools/arch/score/include/uapi/asm/bitsperlong.h | 1 + tools/arch/score/include/uapi/asm/mman.h | 1 + tools/arch/sh/include/uapi/asm/mman.h | 1 + tools/arch/sparc/include/uapi/asm/bitsperlong.h | 1 + tools/arch/sparc/include/uapi/asm/mman.h | 1 + tools/arch/tile/include/uapi/asm/mman.h | 1 + tools/arch/x86/include/uapi/asm/bitsperlong.h | 1 + tools/arch/x86/include/uapi/asm/kvm.h | 1 + tools/arch/x86/include/uapi/asm/kvm_perf.h | 1 + tools/arch/x86/include/uapi/asm/mman.h | 1 + tools/arch/x86/include/uapi/asm/perf_regs.h | 1 + tools/arch/xtensa/include/uapi/asm/mman.h | 1 + 930 files changed, 930 insertions(+) (limited to 'include/uapi/linux') diff --git a/arch/alpha/include/uapi/asm/a.out.h b/arch/alpha/include/uapi/asm/a.out.h index 547707246f63..7d692df04ba9 100644 --- a/arch/alpha/include/uapi/asm/a.out.h +++ b/arch/alpha/include/uapi/asm/a.out.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__ALPHA_A_OUT_H__ #define _UAPI__ALPHA_A_OUT_H__ diff --git a/arch/alpha/include/uapi/asm/auxvec.h b/arch/alpha/include/uapi/asm/auxvec.h index a3a579dfdb4d..57cae8780d81 100644 --- a/arch/alpha/include/uapi/asm/auxvec.h +++ b/arch/alpha/include/uapi/asm/auxvec.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_ALPHA_AUXVEC_H #define __ASM_ALPHA_AUXVEC_H diff --git a/arch/alpha/include/uapi/asm/bitsperlong.h b/arch/alpha/include/uapi/asm/bitsperlong.h index ad57f7868203..6c5bf7d03f4e 100644 --- a/arch/alpha/include/uapi/asm/bitsperlong.h +++ b/arch/alpha/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_ALPHA_BITSPERLONG_H #define __ASM_ALPHA_BITSPERLONG_H diff --git a/arch/alpha/include/uapi/asm/byteorder.h b/arch/alpha/include/uapi/asm/byteorder.h index 73683093202d..efa9b51b4595 100644 --- a/arch/alpha/include/uapi/asm/byteorder.h +++ b/arch/alpha/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ALPHA_BYTEORDER_H #define _ALPHA_BYTEORDER_H diff --git a/arch/alpha/include/uapi/asm/compiler.h b/arch/alpha/include/uapi/asm/compiler.h index 32cc7833f0c1..0e00c0e13374 100644 --- a/arch/alpha/include/uapi/asm/compiler.h +++ b/arch/alpha/include/uapi/asm/compiler.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__ALPHA_COMPILER_H #define _UAPI__ALPHA_COMPILER_H diff --git a/arch/alpha/include/uapi/asm/console.h b/arch/alpha/include/uapi/asm/console.h index fd08a191f360..5fcb65300b56 100644 --- a/arch/alpha/include/uapi/asm/console.h +++ b/arch/alpha/include/uapi/asm/console.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__AXP_CONSOLE_H #define _UAPI__AXP_CONSOLE_H diff --git a/arch/alpha/include/uapi/asm/errno.h b/arch/alpha/include/uapi/asm/errno.h index 17f92aa76b2f..3d265f6babaf 100644 --- a/arch/alpha/include/uapi/asm/errno.h +++ b/arch/alpha/include/uapi/asm/errno.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ALPHA_ERRNO_H #define _ALPHA_ERRNO_H diff --git a/arch/alpha/include/uapi/asm/fcntl.h b/arch/alpha/include/uapi/asm/fcntl.h index 09f49a6b87d1..50bdc8e8a271 100644 --- a/arch/alpha/include/uapi/asm/fcntl.h +++ b/arch/alpha/include/uapi/asm/fcntl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ALPHA_FCNTL_H #define _ALPHA_FCNTL_H diff --git a/arch/alpha/include/uapi/asm/fpu.h b/arch/alpha/include/uapi/asm/fpu.h index 21a053ca2233..cea9eafa056f 100644 --- a/arch/alpha/include/uapi/asm/fpu.h +++ b/arch/alpha/include/uapi/asm/fpu.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__ASM_ALPHA_FPU_H #define _UAPI__ASM_ALPHA_FPU_H diff --git a/arch/alpha/include/uapi/asm/gentrap.h b/arch/alpha/include/uapi/asm/gentrap.h index ae50cc3192c7..c02ccc5ecec0 100644 --- a/arch/alpha/include/uapi/asm/gentrap.h +++ b/arch/alpha/include/uapi/asm/gentrap.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASMAXP_GENTRAP_H #define _ASMAXP_GENTRAP_H diff --git a/arch/alpha/include/uapi/asm/ioctl.h b/arch/alpha/include/uapi/asm/ioctl.h index fc63727f4178..a9d68a08ee84 100644 --- a/arch/alpha/include/uapi/asm/ioctl.h +++ b/arch/alpha/include/uapi/asm/ioctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ALPHA_IOCTL_H #define _ALPHA_IOCTL_H diff --git a/arch/alpha/include/uapi/asm/ioctls.h b/arch/alpha/include/uapi/asm/ioctls.h index 1cd7dc7d4870..3729d92d3fa8 100644 --- a/arch/alpha/include/uapi/asm/ioctls.h +++ b/arch/alpha/include/uapi/asm/ioctls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_ALPHA_IOCTLS_H #define _ASM_ALPHA_IOCTLS_H diff --git a/arch/alpha/include/uapi/asm/ipcbuf.h b/arch/alpha/include/uapi/asm/ipcbuf.h index 84c7e51cb6d0..90d6445a14df 100644 --- a/arch/alpha/include/uapi/asm/ipcbuf.h +++ b/arch/alpha/include/uapi/asm/ipcbuf.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/alpha/include/uapi/asm/kvm_para.h b/arch/alpha/include/uapi/asm/kvm_para.h index 14fab8f0b957..baacc4996d18 100644 --- a/arch/alpha/include/uapi/asm/kvm_para.h +++ b/arch/alpha/include/uapi/asm/kvm_para.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h index 3b26cc62dadb..6bf730063e3f 100644 --- a/arch/alpha/include/uapi/asm/mman.h +++ b/arch/alpha/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ALPHA_MMAN_H__ #define __ALPHA_MMAN_H__ diff --git a/arch/alpha/include/uapi/asm/msgbuf.h b/arch/alpha/include/uapi/asm/msgbuf.h index 98496501a2bb..8c5d4d8c1b16 100644 --- a/arch/alpha/include/uapi/asm/msgbuf.h +++ b/arch/alpha/include/uapi/asm/msgbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ALPHA_MSGBUF_H #define _ALPHA_MSGBUF_H diff --git a/arch/alpha/include/uapi/asm/pal.h b/arch/alpha/include/uapi/asm/pal.h index dfc8140b9088..7427e028db64 100644 --- a/arch/alpha/include/uapi/asm/pal.h +++ b/arch/alpha/include/uapi/asm/pal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__ALPHA_PAL_H #define _UAPI__ALPHA_PAL_H diff --git a/arch/alpha/include/uapi/asm/param.h b/arch/alpha/include/uapi/asm/param.h index dbcd9834af6d..49c7119934e2 100644 --- a/arch/alpha/include/uapi/asm/param.h +++ b/arch/alpha/include/uapi/asm/param.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_ALPHA_PARAM_H #define _UAPI_ASM_ALPHA_PARAM_H diff --git a/arch/alpha/include/uapi/asm/posix_types.h b/arch/alpha/include/uapi/asm/posix_types.h index 5a8a48320efe..04f1ea57505b 100644 --- a/arch/alpha/include/uapi/asm/posix_types.h +++ b/arch/alpha/include/uapi/asm/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ALPHA_POSIX_TYPES_H #define _ALPHA_POSIX_TYPES_H diff --git a/arch/alpha/include/uapi/asm/ptrace.h b/arch/alpha/include/uapi/asm/ptrace.h index 5ce83fa9a05b..1dfd065e45b1 100644 --- a/arch/alpha/include/uapi/asm/ptrace.h +++ b/arch/alpha/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASMAXP_PTRACE_H #define _UAPI_ASMAXP_PTRACE_H diff --git a/arch/alpha/include/uapi/asm/reg.h b/arch/alpha/include/uapi/asm/reg.h index 86ff916fb069..2652f3a385f7 100644 --- a/arch/alpha/include/uapi/asm/reg.h +++ b/arch/alpha/include/uapi/asm/reg.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __reg_h__ #define __reg_h__ diff --git a/arch/alpha/include/uapi/asm/regdef.h b/arch/alpha/include/uapi/asm/regdef.h index 142df9c4f8b8..cc99df0c60a5 100644 --- a/arch/alpha/include/uapi/asm/regdef.h +++ b/arch/alpha/include/uapi/asm/regdef.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __alpha_regdef_h__ #define __alpha_regdef_h__ diff --git a/arch/alpha/include/uapi/asm/resource.h b/arch/alpha/include/uapi/asm/resource.h index c10874ff5973..362423ffe10b 100644 --- a/arch/alpha/include/uapi/asm/resource.h +++ b/arch/alpha/include/uapi/asm/resource.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ALPHA_RESOURCE_H #define _ALPHA_RESOURCE_H diff --git a/arch/alpha/include/uapi/asm/sembuf.h b/arch/alpha/include/uapi/asm/sembuf.h index 7b38b1534784..f28ffa668b2f 100644 --- a/arch/alpha/include/uapi/asm/sembuf.h +++ b/arch/alpha/include/uapi/asm/sembuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ALPHA_SEMBUF_H #define _ALPHA_SEMBUF_H diff --git a/arch/alpha/include/uapi/asm/setup.h b/arch/alpha/include/uapi/asm/setup.h index b50014b30909..13b7ee465b0e 100644 --- a/arch/alpha/include/uapi/asm/setup.h +++ b/arch/alpha/include/uapi/asm/setup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ALPHA_SETUP_H #define __ALPHA_SETUP_H diff --git a/arch/alpha/include/uapi/asm/shmbuf.h b/arch/alpha/include/uapi/asm/shmbuf.h index 37ee84f05085..7e041ca2eb40 100644 --- a/arch/alpha/include/uapi/asm/shmbuf.h +++ b/arch/alpha/include/uapi/asm/shmbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ALPHA_SHMBUF_H #define _ALPHA_SHMBUF_H diff --git a/arch/alpha/include/uapi/asm/sigcontext.h b/arch/alpha/include/uapi/asm/sigcontext.h index 323cdb026198..5428c42567e6 100644 --- a/arch/alpha/include/uapi/asm/sigcontext.h +++ b/arch/alpha/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASMAXP_SIGCONTEXT_H #define _ASMAXP_SIGCONTEXT_H diff --git a/arch/alpha/include/uapi/asm/siginfo.h b/arch/alpha/include/uapi/asm/siginfo.h index 70494d1d8f29..0cf3b527b274 100644 --- a/arch/alpha/include/uapi/asm/siginfo.h +++ b/arch/alpha/include/uapi/asm/siginfo.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ALPHA_SIGINFO_H #define _ALPHA_SIGINFO_H diff --git a/arch/alpha/include/uapi/asm/signal.h b/arch/alpha/include/uapi/asm/signal.h index dd4ca4bcbb4a..74c750bf1c1a 100644 --- a/arch/alpha/include/uapi/asm/signal.h +++ b/arch/alpha/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASMAXP_SIGNAL_H #define _UAPI_ASMAXP_SIGNAL_H diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index c6133a045352..be14f16149d5 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_SOCKET_H #define _UAPI_ASM_SOCKET_H diff --git a/arch/alpha/include/uapi/asm/sockios.h b/arch/alpha/include/uapi/asm/sockios.h index 7932c7ab4a4d..ba287e4b01bf 100644 --- a/arch/alpha/include/uapi/asm/sockios.h +++ b/arch/alpha/include/uapi/asm/sockios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_ALPHA_SOCKIOS_H #define _ASM_ALPHA_SOCKIOS_H diff --git a/arch/alpha/include/uapi/asm/stat.h b/arch/alpha/include/uapi/asm/stat.h index 07ad3e6b3f3e..3f454fbd307a 100644 --- a/arch/alpha/include/uapi/asm/stat.h +++ b/arch/alpha/include/uapi/asm/stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ALPHA_STAT_H #define _ALPHA_STAT_H diff --git a/arch/alpha/include/uapi/asm/statfs.h b/arch/alpha/include/uapi/asm/statfs.h index ccd2e186bfd8..95852a4f576d 100644 --- a/arch/alpha/include/uapi/asm/statfs.h +++ b/arch/alpha/include/uapi/asm/statfs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ALPHA_STATFS_H #define _ALPHA_STATFS_H diff --git a/arch/alpha/include/uapi/asm/swab.h b/arch/alpha/include/uapi/asm/swab.h index 4d682b16c7c4..1cc70d2727f7 100644 --- a/arch/alpha/include/uapi/asm/swab.h +++ b/arch/alpha/include/uapi/asm/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ALPHA_SWAB_H #define _ALPHA_SWAB_H diff --git a/arch/alpha/include/uapi/asm/sysinfo.h b/arch/alpha/include/uapi/asm/sysinfo.h index 0b80e79d75e5..188ea76c7f2f 100644 --- a/arch/alpha/include/uapi/asm/sysinfo.h +++ b/arch/alpha/include/uapi/asm/sysinfo.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/asm-alpha/sysinfo.h */ diff --git a/arch/alpha/include/uapi/asm/termbits.h b/arch/alpha/include/uapi/asm/termbits.h index 879dd3589921..05e0398a83a6 100644 --- a/arch/alpha/include/uapi/asm/termbits.h +++ b/arch/alpha/include/uapi/asm/termbits.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ALPHA_TERMBITS_H #define _ALPHA_TERMBITS_H diff --git a/arch/alpha/include/uapi/asm/termios.h b/arch/alpha/include/uapi/asm/termios.h index 580ed1e4854c..e1b981222a24 100644 --- a/arch/alpha/include/uapi/asm/termios.h +++ b/arch/alpha/include/uapi/asm/termios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ALPHA_TERMIOS_H #define _UAPI_ALPHA_TERMIOS_H diff --git a/arch/alpha/include/uapi/asm/types.h b/arch/alpha/include/uapi/asm/types.h index 8d1024d7be05..6c3d49938126 100644 --- a/arch/alpha/include/uapi/asm/types.h +++ b/arch/alpha/include/uapi/asm/types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ALPHA_TYPES_H #define _UAPI_ALPHA_TYPES_H diff --git a/arch/alpha/include/uapi/asm/unistd.h b/arch/alpha/include/uapi/asm/unistd.h index 53de540e39a7..e153ca6e15d6 100644 --- a/arch/alpha/include/uapi/asm/unistd.h +++ b/arch/alpha/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ALPHA_UNISTD_H #define _UAPI_ALPHA_UNISTD_H diff --git a/arch/arm/include/uapi/asm/auxvec.h b/arch/arm/include/uapi/asm/auxvec.h index cb02a767a500..5c09da5965d4 100644 --- a/arch/arm/include/uapi/asm/auxvec.h +++ b/arch/arm/include/uapi/asm/auxvec.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_AUXVEC_H #define __ASM_AUXVEC_H diff --git a/arch/arm/include/uapi/asm/byteorder.h b/arch/arm/include/uapi/asm/byteorder.h index 77379748b171..cb8406afe162 100644 --- a/arch/arm/include/uapi/asm/byteorder.h +++ b/arch/arm/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * arch/arm/include/asm/byteorder.h * diff --git a/arch/arm/include/uapi/asm/fcntl.h b/arch/arm/include/uapi/asm/fcntl.h index a80b6607b2ef..e6b5d7141c05 100644 --- a/arch/arm/include/uapi/asm/fcntl.h +++ b/arch/arm/include/uapi/asm/fcntl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ARM_FCNTL_H #define _ARM_FCNTL_H diff --git a/arch/arm/include/uapi/asm/hwcap.h b/arch/arm/include/uapi/asm/hwcap.h index 20d12f230a2f..b5971dfa4b8c 100644 --- a/arch/arm/include/uapi/asm/hwcap.h +++ b/arch/arm/include/uapi/asm/hwcap.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__ASMARM_HWCAP_H #define _UAPI__ASMARM_HWCAP_H diff --git a/arch/arm/include/uapi/asm/ioctls.h b/arch/arm/include/uapi/asm/ioctls.h index 9c9629816128..1bfe2854fb51 100644 --- a/arch/arm/include/uapi/asm/ioctls.h +++ b/arch/arm/include/uapi/asm/ioctls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_ARM_IOCTLS_H #define __ASM_ARM_IOCTLS_H diff --git a/arch/arm/include/uapi/asm/kvm_para.h b/arch/arm/include/uapi/asm/kvm_para.h index 14fab8f0b957..baacc4996d18 100644 --- a/arch/arm/include/uapi/asm/kvm_para.h +++ b/arch/arm/include/uapi/asm/kvm_para.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/arm/include/uapi/asm/perf_regs.h b/arch/arm/include/uapi/asm/perf_regs.h index ce59448458b2..a3c046174e6b 100644 --- a/arch/arm/include/uapi/asm/perf_regs.h +++ b/arch/arm/include/uapi/asm/perf_regs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_ARM_PERF_REGS_H #define _ASM_ARM_PERF_REGS_H diff --git a/arch/arm/include/uapi/asm/sigcontext.h b/arch/arm/include/uapi/asm/sigcontext.h index fc0b80b6a6fc..e223c65adabd 100644 --- a/arch/arm/include/uapi/asm/sigcontext.h +++ b/arch/arm/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASMARM_SIGCONTEXT_H #define _ASMARM_SIGCONTEXT_H diff --git a/arch/arm/include/uapi/asm/signal.h b/arch/arm/include/uapi/asm/signal.h index 33073bdcf091..9b4185ba4f8a 100644 --- a/arch/arm/include/uapi/asm/signal.h +++ b/arch/arm/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASMARM_SIGNAL_H #define _UAPI_ASMARM_SIGNAL_H diff --git a/arch/arm/include/uapi/asm/stat.h b/arch/arm/include/uapi/asm/stat.h index 42c0c13999d5..9c6580bfc04d 100644 --- a/arch/arm/include/uapi/asm/stat.h +++ b/arch/arm/include/uapi/asm/stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASMARM_STAT_H #define _ASMARM_STAT_H diff --git a/arch/arm/include/uapi/asm/statfs.h b/arch/arm/include/uapi/asm/statfs.h index 079447c05ba7..177f08540079 100644 --- a/arch/arm/include/uapi/asm/statfs.h +++ b/arch/arm/include/uapi/asm/statfs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASMARM_STATFS_H #define _ASMARM_STATFS_H diff --git a/arch/arm/include/uapi/asm/swab.h b/arch/arm/include/uapi/asm/swab.h index 6fcb32a5c453..301aa8d8e320 100644 --- a/arch/arm/include/uapi/asm/swab.h +++ b/arch/arm/include/uapi/asm/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * arch/arm/include/asm/byteorder.h * diff --git a/arch/arm/include/uapi/asm/types.h b/arch/arm/include/uapi/asm/types.h index 9435a42f575e..1a667bc26510 100644 --- a/arch/arm/include/uapi/asm/types.h +++ b/arch/arm/include/uapi/asm/types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_TYPES_H #define _UAPI_ASM_TYPES_H diff --git a/arch/arm64/include/uapi/asm/perf_regs.h b/arch/arm64/include/uapi/asm/perf_regs.h index 172b8317ee49..d54daafa89e3 100644 --- a/arch/arm64/include/uapi/asm/perf_regs.h +++ b/arch/arm64/include/uapi/asm/perf_regs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_ARM64_PERF_REGS_H #define _ASM_ARM64_PERF_REGS_H diff --git a/arch/arm64/include/uapi/asm/posix_types.h b/arch/arm64/include/uapi/asm/posix_types.h index 7985ff60ca3f..b1c2e0df92dc 100644 --- a/arch/arm64/include/uapi/asm/posix_types.h +++ b/arch/arm64/include/uapi/asm/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_POSIX_TYPES_H #define __ASM_POSIX_TYPES_H diff --git a/arch/blackfin/include/uapi/asm/byteorder.h b/arch/blackfin/include/uapi/asm/byteorder.h index 3b125da5dcb2..bcab6670c7fe 100644 --- a/arch/blackfin/include/uapi/asm/byteorder.h +++ b/arch/blackfin/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__BFIN_ASM_BYTEORDER_H #define _UAPI__BFIN_ASM_BYTEORDER_H diff --git a/arch/blackfin/include/uapi/asm/ioctls.h b/arch/blackfin/include/uapi/asm/ioctls.h index 9a41c20fc83d..422fee3e4776 100644 --- a/arch/blackfin/include/uapi/asm/ioctls.h +++ b/arch/blackfin/include/uapi/asm/ioctls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__ARCH_BFIN_IOCTLS_H__ #define _UAPI__ARCH_BFIN_IOCTLS_H__ diff --git a/arch/blackfin/include/uapi/asm/signal.h b/arch/blackfin/include/uapi/asm/signal.h index f0a0d8b6663a..f8e3b99ba0a2 100644 --- a/arch/blackfin/include/uapi/asm/signal.h +++ b/arch/blackfin/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_BLACKFIN_SIGNAL_H #define _UAPI_BLACKFIN_SIGNAL_H diff --git a/arch/c6x/include/uapi/asm/byteorder.h b/arch/c6x/include/uapi/asm/byteorder.h index 166038db342b..ab61f867391c 100644 --- a/arch/c6x/include/uapi/asm/byteorder.h +++ b/arch/c6x/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_C6X_BYTEORDER_H #define _ASM_C6X_BYTEORDER_H diff --git a/arch/c6x/include/uapi/asm/setup.h b/arch/c6x/include/uapi/asm/setup.h index ad9ac97a8dad..e90548cebec3 100644 --- a/arch/c6x/include/uapi/asm/setup.h +++ b/arch/c6x/include/uapi/asm/setup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_C6X_SETUP_H #define _UAPI_ASM_C6X_SETUP_H diff --git a/arch/cris/include/uapi/arch-v10/arch/sv_addr_ag.h b/arch/cris/include/uapi/arch-v10/arch/sv_addr_ag.h index c4b6b0e9b1da..2644bcbe4490 100644 --- a/arch/cris/include/uapi/arch-v10/arch/sv_addr_ag.h +++ b/arch/cris/include/uapi/arch-v10/arch/sv_addr_ag.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /*!************************************************************************** *! *! MACROS: diff --git a/arch/cris/include/uapi/arch-v10/arch/svinto.h b/arch/cris/include/uapi/arch-v10/arch/svinto.h index da5c15272652..793a4275d26a 100644 --- a/arch/cris/include/uapi/arch-v10/arch/svinto.h +++ b/arch/cris/include/uapi/arch-v10/arch/svinto.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_CRIS_SVINTO_H #define _ASM_CRIS_SVINTO_H diff --git a/arch/cris/include/uapi/arch-v10/arch/user.h b/arch/cris/include/uapi/arch-v10/arch/user.h index 9303ea77c915..5b9288527b98 100644 --- a/arch/cris/include/uapi/arch-v10/arch/user.h +++ b/arch/cris/include/uapi/arch-v10/arch/user.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_CRIS_ARCH_USER_H #define __ASM_CRIS_ARCH_USER_H diff --git a/arch/cris/include/uapi/arch-v32/arch/cryptocop.h b/arch/cris/include/uapi/arch-v32/arch/cryptocop.h index 694fd13ce1cf..1072d5bf7d4f 100644 --- a/arch/cris/include/uapi/arch-v32/arch/cryptocop.h +++ b/arch/cris/include/uapi/arch-v32/arch/cryptocop.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * The device /dev/cryptocop is accessible using this driver using * CRYPTOCOP_MAJOR (254) and minor number 0. diff --git a/arch/cris/include/uapi/arch-v32/arch/user.h b/arch/cris/include/uapi/arch-v32/arch/user.h index 03fa1f3c3c00..3576b540ba78 100644 --- a/arch/cris/include/uapi/arch-v32/arch/user.h +++ b/arch/cris/include/uapi/arch-v32/arch/user.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_CRIS_ARCH_USER_H #define _ASM_CRIS_ARCH_USER_H diff --git a/arch/cris/include/uapi/asm/byteorder.h b/arch/cris/include/uapi/asm/byteorder.h index bcd189798e26..6e19891e06ee 100644 --- a/arch/cris/include/uapi/asm/byteorder.h +++ b/arch/cris/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _CRIS_BYTEORDER_H #define _CRIS_BYTEORDER_H diff --git a/arch/cris/include/uapi/asm/elf.h b/arch/cris/include/uapi/asm/elf.h index a5df05bfee66..ea4cbdafe885 100644 --- a/arch/cris/include/uapi/asm/elf.h +++ b/arch/cris/include/uapi/asm/elf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASMCRIS_ELF_H #define __ASMCRIS_ELF_H diff --git a/arch/cris/include/uapi/asm/elf_v10.h b/arch/cris/include/uapi/asm/elf_v10.h index 3ea65cef529d..b1515f2684da 100644 --- a/arch/cris/include/uapi/asm/elf_v10.h +++ b/arch/cris/include/uapi/asm/elf_v10.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASMCRIS_ARCH_ELF_H #define __ASMCRIS_ARCH_ELF_H diff --git a/arch/cris/include/uapi/asm/elf_v32.h b/arch/cris/include/uapi/asm/elf_v32.h index f09fe49005c0..cc00ffdb7f9c 100644 --- a/arch/cris/include/uapi/asm/elf_v32.h +++ b/arch/cris/include/uapi/asm/elf_v32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_CRIS_ELF_H #define _ASM_CRIS_ELF_H diff --git a/arch/cris/include/uapi/asm/ethernet.h b/arch/cris/include/uapi/asm/ethernet.h index 4d58652c3a49..e0c1a6322824 100644 --- a/arch/cris/include/uapi/asm/ethernet.h +++ b/arch/cris/include/uapi/asm/ethernet.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * ioctl defines for ethernet driver * diff --git a/arch/cris/include/uapi/asm/etraxgpio.h b/arch/cris/include/uapi/asm/etraxgpio.h index c6e7d57c8b24..10ab0dd45bfe 100644 --- a/arch/cris/include/uapi/asm/etraxgpio.h +++ b/arch/cris/include/uapi/asm/etraxgpio.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * The following devices are accessible using this driver using * GPIO_MAJOR (120) and a couple of minor numbers. diff --git a/arch/cris/include/uapi/asm/ioctls.h b/arch/cris/include/uapi/asm/ioctls.h index 488fbb3f5e84..92d654ce3d84 100644 --- a/arch/cris/include/uapi/asm/ioctls.h +++ b/arch/cris/include/uapi/asm/ioctls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ARCH_CRIS_IOCTLS_H__ #define __ARCH_CRIS_IOCTLS_H__ diff --git a/arch/cris/include/uapi/asm/param.h b/arch/cris/include/uapi/asm/param.h index 484fcf8667c0..ae296115c7c9 100644 --- a/arch/cris/include/uapi/asm/param.h +++ b/arch/cris/include/uapi/asm/param.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASMCRIS_PARAM_H #define _ASMCRIS_PARAM_H diff --git a/arch/cris/include/uapi/asm/posix_types.h b/arch/cris/include/uapi/asm/posix_types.h index 0f22e6a67ea5..c75d8b0acc99 100644 --- a/arch/cris/include/uapi/asm/posix_types.h +++ b/arch/cris/include/uapi/asm/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* $Id: posix_types.h,v 1.1 2000/07/10 16:32:31 bjornw Exp $ */ /* We cheat a bit and use our C-coded bitops functions from asm/bitops.h */ diff --git a/arch/cris/include/uapi/asm/ptrace.h b/arch/cris/include/uapi/asm/ptrace.h index bd8946f83ed3..99de59e54613 100644 --- a/arch/cris/include/uapi/asm/ptrace.h +++ b/arch/cris/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifdef __arch_v32 #include #else diff --git a/arch/cris/include/uapi/asm/ptrace_v10.h b/arch/cris/include/uapi/asm/ptrace_v10.h index 1a232739565e..4ffffb7ab102 100644 --- a/arch/cris/include/uapi/asm/ptrace_v10.h +++ b/arch/cris/include/uapi/asm/ptrace_v10.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _CRIS_ARCH_PTRACE_H #define _CRIS_ARCH_PTRACE_H diff --git a/arch/cris/include/uapi/asm/ptrace_v32.h b/arch/cris/include/uapi/asm/ptrace_v32.h index 19773d3bd4c4..a91c4aacb14f 100644 --- a/arch/cris/include/uapi/asm/ptrace_v32.h +++ b/arch/cris/include/uapi/asm/ptrace_v32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _CRIS_ARCH_PTRACE_H #define _CRIS_ARCH_PTRACE_H diff --git a/arch/cris/include/uapi/asm/rs485.h b/arch/cris/include/uapi/asm/rs485.h index ad40f9fbcb8a..041d31fa33d5 100644 --- a/arch/cris/include/uapi/asm/rs485.h +++ b/arch/cris/include/uapi/asm/rs485.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* RS-485 structures */ /* Used with ioctl() TIOCSERSETRS485 for backward compatibility! diff --git a/arch/cris/include/uapi/asm/setup.h b/arch/cris/include/uapi/asm/setup.h index b90728652d1a..4854ace9db76 100644 --- a/arch/cris/include/uapi/asm/setup.h +++ b/arch/cris/include/uapi/asm/setup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _CRIS_SETUP_H #define _CRIS_SETUP_H diff --git a/arch/cris/include/uapi/asm/sigcontext.h b/arch/cris/include/uapi/asm/sigcontext.h index a1d634e120df..97565ce3f0b9 100644 --- a/arch/cris/include/uapi/asm/sigcontext.h +++ b/arch/cris/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* $Id: sigcontext.h,v 1.1 2000/07/10 16:32:31 bjornw Exp $ */ #ifndef _ASM_CRIS_SIGCONTEXT_H diff --git a/arch/cris/include/uapi/asm/signal.h b/arch/cris/include/uapi/asm/signal.h index ce42fa7c32ad..e4ab00f00111 100644 --- a/arch/cris/include/uapi/asm/signal.h +++ b/arch/cris/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_CRIS_SIGNAL_H #define _UAPI_ASM_CRIS_SIGNAL_H diff --git a/arch/cris/include/uapi/asm/stat.h b/arch/cris/include/uapi/asm/stat.h index 9e558cc3c43b..cdb74d5862e4 100644 --- a/arch/cris/include/uapi/asm/stat.h +++ b/arch/cris/include/uapi/asm/stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _CRIS_STAT_H #define _CRIS_STAT_H diff --git a/arch/cris/include/uapi/asm/sync_serial.h b/arch/cris/include/uapi/asm/sync_serial.h index 7f827fea30e7..f2d468889ba9 100644 --- a/arch/cris/include/uapi/asm/sync_serial.h +++ b/arch/cris/include/uapi/asm/sync_serial.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * ioctl defines for synchronous serial port driver * diff --git a/arch/cris/include/uapi/asm/termbits.h b/arch/cris/include/uapi/asm/termbits.h index 1c43bc874ccf..86925dc1fcae 100644 --- a/arch/cris/include/uapi/asm/termbits.h +++ b/arch/cris/include/uapi/asm/termbits.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* $Id: termbits.h,v 1.1 2000/07/10 16:32:31 bjornw Exp $ */ #ifndef __ARCH_ETRAX100_TERMBITS_H__ diff --git a/arch/cris/include/uapi/asm/termios.h b/arch/cris/include/uapi/asm/termios.h index 0a0386a55027..d87800a6d854 100644 --- a/arch/cris/include/uapi/asm/termios.h +++ b/arch/cris/include/uapi/asm/termios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_CRIS_TERMIOS_H #define _UAPI_CRIS_TERMIOS_H diff --git a/arch/cris/include/uapi/asm/unistd.h b/arch/cris/include/uapi/asm/unistd.h index 062b648b27e1..7aba513b082d 100644 --- a/arch/cris/include/uapi/asm/unistd.h +++ b/arch/cris/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_CRIS_UNISTD_H_ #define _UAPI_ASM_CRIS_UNISTD_H_ diff --git a/arch/frv/include/uapi/asm/bitsperlong.h b/arch/frv/include/uapi/asm/bitsperlong.h index 6dc0bb0c13b2..76da34b10f59 100644 --- a/arch/frv/include/uapi/asm/bitsperlong.h +++ b/arch/frv/include/uapi/asm/bitsperlong.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/frv/include/uapi/asm/byteorder.h b/arch/frv/include/uapi/asm/byteorder.h index f29b7593e088..a46f6472acdc 100644 --- a/arch/frv/include/uapi/asm/byteorder.h +++ b/arch/frv/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_BYTEORDER_H #define _ASM_BYTEORDER_H diff --git a/arch/frv/include/uapi/asm/errno.h b/arch/frv/include/uapi/asm/errno.h index d010795ceefe..c5b82f2f2970 100644 --- a/arch/frv/include/uapi/asm/errno.h +++ b/arch/frv/include/uapi/asm/errno.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_ERRNO_H #define _ASM_ERRNO_H diff --git a/arch/frv/include/uapi/asm/fcntl.h b/arch/frv/include/uapi/asm/fcntl.h index 46ab12db5739..a77648c505d1 100644 --- a/arch/frv/include/uapi/asm/fcntl.h +++ b/arch/frv/include/uapi/asm/fcntl.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/frv/include/uapi/asm/ioctl.h b/arch/frv/include/uapi/asm/ioctl.h index b279fe06dfe5..b809c4566e5f 100644 --- a/arch/frv/include/uapi/asm/ioctl.h +++ b/arch/frv/include/uapi/asm/ioctl.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/frv/include/uapi/asm/ioctls.h b/arch/frv/include/uapi/asm/ioctls.h index 2f9fb436ec3c..dd9f5eb9feda 100644 --- a/arch/frv/include/uapi/asm/ioctls.h +++ b/arch/frv/include/uapi/asm/ioctls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_IOCTLS_H__ #define __ASM_IOCTLS_H__ diff --git a/arch/frv/include/uapi/asm/kvm_para.h b/arch/frv/include/uapi/asm/kvm_para.h index 14fab8f0b957..baacc4996d18 100644 --- a/arch/frv/include/uapi/asm/kvm_para.h +++ b/arch/frv/include/uapi/asm/kvm_para.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/frv/include/uapi/asm/mman.h b/arch/frv/include/uapi/asm/mman.h index 8eebf89f5ab1..306fc0460b80 100644 --- a/arch/frv/include/uapi/asm/mman.h +++ b/arch/frv/include/uapi/asm/mman.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/frv/include/uapi/asm/msgbuf.h b/arch/frv/include/uapi/asm/msgbuf.h index 97ceb55a06fb..156c81bb46d7 100644 --- a/arch/frv/include/uapi/asm/msgbuf.h +++ b/arch/frv/include/uapi/asm/msgbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_MSGBUF_H #define _ASM_MSGBUF_H diff --git a/arch/frv/include/uapi/asm/param.h b/arch/frv/include/uapi/asm/param.h index a52dca9a9566..d3e0168d8937 100644 --- a/arch/frv/include/uapi/asm/param.h +++ b/arch/frv/include/uapi/asm/param.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_PARAM_H #define _ASM_PARAM_H diff --git a/arch/frv/include/uapi/asm/poll.h b/arch/frv/include/uapi/asm/poll.h index 0d01479ccc56..887b67288340 100644 --- a/arch/frv/include/uapi/asm/poll.h +++ b/arch/frv/include/uapi/asm/poll.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_POLL_H #define _ASM_POLL_H diff --git a/arch/frv/include/uapi/asm/posix_types.h b/arch/frv/include/uapi/asm/posix_types.h index fe512af74a5a..2995777227b3 100644 --- a/arch/frv/include/uapi/asm/posix_types.h +++ b/arch/frv/include/uapi/asm/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_POSIX_TYPES_H #define _ASM_POSIX_TYPES_H diff --git a/arch/frv/include/uapi/asm/resource.h b/arch/frv/include/uapi/asm/resource.h index 5fc60548fd02..2100305f9b3e 100644 --- a/arch/frv/include/uapi/asm/resource.h +++ b/arch/frv/include/uapi/asm/resource.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_RESOURCE_H #define _ASM_RESOURCE_H diff --git a/arch/frv/include/uapi/asm/sembuf.h b/arch/frv/include/uapi/asm/sembuf.h index 164b12786d6d..d5477f95832b 100644 --- a/arch/frv/include/uapi/asm/sembuf.h +++ b/arch/frv/include/uapi/asm/sembuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SEMBUF_H #define _ASM_SEMBUF_H diff --git a/arch/frv/include/uapi/asm/shmbuf.h b/arch/frv/include/uapi/asm/shmbuf.h index 4c6e711a4779..1de8f892e412 100644 --- a/arch/frv/include/uapi/asm/shmbuf.h +++ b/arch/frv/include/uapi/asm/shmbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SHMBUF_H #define _ASM_SHMBUF_H diff --git a/arch/frv/include/uapi/asm/siginfo.h b/arch/frv/include/uapi/asm/siginfo.h index f55d9e0e9068..4c8c975747ac 100644 --- a/arch/frv/include/uapi/asm/siginfo.h +++ b/arch/frv/include/uapi/asm/siginfo.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SIGINFO_H #define _ASM_SIGINFO_H diff --git a/arch/frv/include/uapi/asm/signal.h b/arch/frv/include/uapi/asm/signal.h index bf3b162f9bea..603bb796cf46 100644 --- a/arch/frv/include/uapi/asm/signal.h +++ b/arch/frv/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_SIGNAL_H #define _UAPI_ASM_SIGNAL_H diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h index 9abf02d6855a..9168e78fa32a 100644 --- a/arch/frv/include/uapi/asm/socket.h +++ b/arch/frv/include/uapi/asm/socket.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SOCKET_H #define _ASM_SOCKET_H diff --git a/arch/frv/include/uapi/asm/sockios.h b/arch/frv/include/uapi/asm/sockios.h index 5dbdd13e6de3..2f62caf1ce84 100644 --- a/arch/frv/include/uapi/asm/sockios.h +++ b/arch/frv/include/uapi/asm/sockios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SOCKIOS__ #define _ASM_SOCKIOS__ diff --git a/arch/frv/include/uapi/asm/stat.h b/arch/frv/include/uapi/asm/stat.h index ce56de9b37ba..0ff9fab915a4 100644 --- a/arch/frv/include/uapi/asm/stat.h +++ b/arch/frv/include/uapi/asm/stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_STAT_H #define _ASM_STAT_H diff --git a/arch/frv/include/uapi/asm/statfs.h b/arch/frv/include/uapi/asm/statfs.h index 741f586045ba..2a378cbff07f 100644 --- a/arch/frv/include/uapi/asm/statfs.h +++ b/arch/frv/include/uapi/asm/statfs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_STATFS_H #define _ASM_STATFS_H diff --git a/arch/frv/include/uapi/asm/swab.h b/arch/frv/include/uapi/asm/swab.h index f305834b4799..c78257d172e5 100644 --- a/arch/frv/include/uapi/asm/swab.h +++ b/arch/frv/include/uapi/asm/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SWAB_H #define _ASM_SWAB_H diff --git a/arch/frv/include/uapi/asm/termbits.h b/arch/frv/include/uapi/asm/termbits.h index 7722e19cc349..b1dcd8d0ff78 100644 --- a/arch/frv/include/uapi/asm/termbits.h +++ b/arch/frv/include/uapi/asm/termbits.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_TERMBITS_H__ #define _ASM_TERMBITS_H__ diff --git a/arch/frv/include/uapi/asm/termios.h b/arch/frv/include/uapi/asm/termios.h index edcc08a22382..ae35bedae6a2 100644 --- a/arch/frv/include/uapi/asm/termios.h +++ b/arch/frv/include/uapi/asm/termios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_TERMIOS_H #define _UAPI_ASM_TERMIOS_H diff --git a/arch/frv/include/uapi/asm/unistd.h b/arch/frv/include/uapi/asm/unistd.h index 9e2612ff1c9d..4b46acaf832b 100644 --- a/arch/frv/include/uapi/asm/unistd.h +++ b/arch/frv/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_UNISTD_H_ #define _UAPI_ASM_UNISTD_H_ diff --git a/arch/h8300/include/uapi/asm/bitsperlong.h b/arch/h8300/include/uapi/asm/bitsperlong.h index 34212608371e..a33e358f1c1b 100644 --- a/arch/h8300/include/uapi/asm/bitsperlong.h +++ b/arch/h8300/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__ASM_H8300_BITS_PER_LONG #define _UAPI__ASM_H8300_BITS_PER_LONG diff --git a/arch/h8300/include/uapi/asm/byteorder.h b/arch/h8300/include/uapi/asm/byteorder.h index 13539da99efd..1fe2f9344458 100644 --- a/arch/h8300/include/uapi/asm/byteorder.h +++ b/arch/h8300/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _H8300_BYTEORDER_H #define _H8300_BYTEORDER_H diff --git a/arch/h8300/include/uapi/asm/ptrace.h b/arch/h8300/include/uapi/asm/ptrace.h index e132670d70ec..78167f517ca4 100644 --- a/arch/h8300/include/uapi/asm/ptrace.h +++ b/arch/h8300/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_H8300_PTRACE_H #define _UAPI_H8300_PTRACE_H diff --git a/arch/h8300/include/uapi/asm/sigcontext.h b/arch/h8300/include/uapi/asm/sigcontext.h index c41fdaa04657..f77273c857d7 100644 --- a/arch/h8300/include/uapi/asm/sigcontext.h +++ b/arch/h8300/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_H8300_SIGCONTEXT_H #define _ASM_H8300_SIGCONTEXT_H diff --git a/arch/h8300/include/uapi/asm/signal.h b/arch/h8300/include/uapi/asm/signal.h index af3a6c37fee6..e15521037348 100644 --- a/arch/h8300/include/uapi/asm/signal.h +++ b/arch/h8300/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_H8300_SIGNAL_H #define _UAPI_H8300_SIGNAL_H diff --git a/arch/hexagon/include/uapi/asm/kvm_para.h b/arch/hexagon/include/uapi/asm/kvm_para.h index 14fab8f0b957..baacc4996d18 100644 --- a/arch/hexagon/include/uapi/asm/kvm_para.h +++ b/arch/hexagon/include/uapi/asm/kvm_para.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/hexagon/include/uapi/asm/registers.h b/arch/hexagon/include/uapi/asm/registers.h index e7be31840a90..d51270f3b358 100644 --- a/arch/hexagon/include/uapi/asm/registers.h +++ b/arch/hexagon/include/uapi/asm/registers.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Register definitions for the Hexagon architecture */ diff --git a/arch/hexagon/include/uapi/asm/user.h b/arch/hexagon/include/uapi/asm/user.h index 3dae94d9ced7..7327ec59b22f 100644 --- a/arch/hexagon/include/uapi/asm/user.h +++ b/arch/hexagon/include/uapi/asm/user.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef HEXAGON_ASM_USER_H #define HEXAGON_ASM_USER_H diff --git a/arch/ia64/include/uapi/asm/auxvec.h b/arch/ia64/include/uapi/asm/auxvec.h index 58277fc650ef..09969a5d2e0a 100644 --- a/arch/ia64/include/uapi/asm/auxvec.h +++ b/arch/ia64/include/uapi/asm/auxvec.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_IA64_AUXVEC_H #define _ASM_IA64_AUXVEC_H diff --git a/arch/ia64/include/uapi/asm/bitsperlong.h b/arch/ia64/include/uapi/asm/bitsperlong.h index ec4db3c970b7..1146d55563db 100644 --- a/arch/ia64/include/uapi/asm/bitsperlong.h +++ b/arch/ia64/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_IA64_BITSPERLONG_H #define __ASM_IA64_BITSPERLONG_H diff --git a/arch/ia64/include/uapi/asm/break.h b/arch/ia64/include/uapi/asm/break.h index f03402039896..5d742bcb0018 100644 --- a/arch/ia64/include/uapi/asm/break.h +++ b/arch/ia64/include/uapi/asm/break.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_IA64_BREAK_H #define _ASM_IA64_BREAK_H diff --git a/arch/ia64/include/uapi/asm/byteorder.h b/arch/ia64/include/uapi/asm/byteorder.h index a8dd73558150..f85d0faaaf34 100644 --- a/arch/ia64/include/uapi/asm/byteorder.h +++ b/arch/ia64/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_IA64_BYTEORDER_H #define _ASM_IA64_BYTEORDER_H diff --git a/arch/ia64/include/uapi/asm/cmpxchg.h b/arch/ia64/include/uapi/asm/cmpxchg.h index a0e3620f8f13..d69c979936d4 100644 --- a/arch/ia64/include/uapi/asm/cmpxchg.h +++ b/arch/ia64/include/uapi/asm/cmpxchg.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_IA64_CMPXCHG_H #define _ASM_IA64_CMPXCHG_H diff --git a/arch/ia64/include/uapi/asm/errno.h b/arch/ia64/include/uapi/asm/errno.h index 4c82b503d92f..9addba592646 100644 --- a/arch/ia64/include/uapi/asm/errno.h +++ b/arch/ia64/include/uapi/asm/errno.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/ia64/include/uapi/asm/fcntl.h b/arch/ia64/include/uapi/asm/fcntl.h index 7b485876cad4..7b95523efe5a 100644 --- a/arch/ia64/include/uapi/asm/fcntl.h +++ b/arch/ia64/include/uapi/asm/fcntl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_IA64_FCNTL_H #define _ASM_IA64_FCNTL_H /* diff --git a/arch/ia64/include/uapi/asm/fpu.h b/arch/ia64/include/uapi/asm/fpu.h index b6395ad1500a..0df392982ce8 100644 --- a/arch/ia64/include/uapi/asm/fpu.h +++ b/arch/ia64/include/uapi/asm/fpu.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_IA64_FPU_H #define _ASM_IA64_FPU_H diff --git a/arch/ia64/include/uapi/asm/gcc_intrin.h b/arch/ia64/include/uapi/asm/gcc_intrin.h index 61d0d0111978..c60696fd1e37 100644 --- a/arch/ia64/include/uapi/asm/gcc_intrin.h +++ b/arch/ia64/include/uapi/asm/gcc_intrin.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * * Copyright (C) 2002,2003 Jun Nakajima diff --git a/arch/ia64/include/uapi/asm/ia64regs.h b/arch/ia64/include/uapi/asm/ia64regs.h index 1757f1c11ad4..d7d10cec8b9f 100644 --- a/arch/ia64/include/uapi/asm/ia64regs.h +++ b/arch/ia64/include/uapi/asm/ia64regs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2002,2003 Intel Corp. * Jun Nakajima diff --git a/arch/ia64/include/uapi/asm/intel_intrin.h b/arch/ia64/include/uapi/asm/intel_intrin.h index 53cec577558a..ab649691545a 100644 --- a/arch/ia64/include/uapi/asm/intel_intrin.h +++ b/arch/ia64/include/uapi/asm/intel_intrin.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_IA64_INTEL_INTRIN_H #define _ASM_IA64_INTEL_INTRIN_H /* diff --git a/arch/ia64/include/uapi/asm/intrinsics.h b/arch/ia64/include/uapi/asm/intrinsics.h index 5829978ff466..aecc217eca63 100644 --- a/arch/ia64/include/uapi/asm/intrinsics.h +++ b/arch/ia64/include/uapi/asm/intrinsics.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Compiler-dependent intrinsics. * diff --git a/arch/ia64/include/uapi/asm/ioctl.h b/arch/ia64/include/uapi/asm/ioctl.h index b279fe06dfe5..b809c4566e5f 100644 --- a/arch/ia64/include/uapi/asm/ioctl.h +++ b/arch/ia64/include/uapi/asm/ioctl.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/ia64/include/uapi/asm/ioctls.h b/arch/ia64/include/uapi/asm/ioctls.h index f3aab5512e98..b86001940209 100644 --- a/arch/ia64/include/uapi/asm/ioctls.h +++ b/arch/ia64/include/uapi/asm/ioctls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_IA64_IOCTLS_H #define _ASM_IA64_IOCTLS_H diff --git a/arch/ia64/include/uapi/asm/ipcbuf.h b/arch/ia64/include/uapi/asm/ipcbuf.h index 84c7e51cb6d0..90d6445a14df 100644 --- a/arch/ia64/include/uapi/asm/ipcbuf.h +++ b/arch/ia64/include/uapi/asm/ipcbuf.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/ia64/include/uapi/asm/mman.h b/arch/ia64/include/uapi/asm/mman.h index 8740819adc54..ce0cc3d7509e 100644 --- a/arch/ia64/include/uapi/asm/mman.h +++ b/arch/ia64/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Based on . * diff --git a/arch/ia64/include/uapi/asm/msgbuf.h b/arch/ia64/include/uapi/asm/msgbuf.h index 6c64c0d2aae1..aa25df92d9dc 100644 --- a/arch/ia64/include/uapi/asm/msgbuf.h +++ b/arch/ia64/include/uapi/asm/msgbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_IA64_MSGBUF_H #define _ASM_IA64_MSGBUF_H diff --git a/arch/ia64/include/uapi/asm/param.h b/arch/ia64/include/uapi/asm/param.h index d7da41d9497d..123ab45940b4 100644 --- a/arch/ia64/include/uapi/asm/param.h +++ b/arch/ia64/include/uapi/asm/param.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Fundamental kernel parameters. * diff --git a/arch/ia64/include/uapi/asm/perfmon.h b/arch/ia64/include/uapi/asm/perfmon.h index 1a10a2dd58a1..017548365e5c 100644 --- a/arch/ia64/include/uapi/asm/perfmon.h +++ b/arch/ia64/include/uapi/asm/perfmon.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2001-2003 Hewlett-Packard Co * Stephane Eranian diff --git a/arch/ia64/include/uapi/asm/perfmon_default_smpl.h b/arch/ia64/include/uapi/asm/perfmon_default_smpl.h index a2d560c67230..d3f36aff0e1f 100644 --- a/arch/ia64/include/uapi/asm/perfmon_default_smpl.h +++ b/arch/ia64/include/uapi/asm/perfmon_default_smpl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2002-2003 Hewlett-Packard Co * Stephane Eranian diff --git a/arch/ia64/include/uapi/asm/posix_types.h b/arch/ia64/include/uapi/asm/posix_types.h index 99ee1d6510cf..bded40f7defe 100644 --- a/arch/ia64/include/uapi/asm/posix_types.h +++ b/arch/ia64/include/uapi/asm/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_IA64_POSIX_TYPES_H #define _ASM_IA64_POSIX_TYPES_H diff --git a/arch/ia64/include/uapi/asm/ptrace.h b/arch/ia64/include/uapi/asm/ptrace.h index 0a02f634e12b..f52655b44414 100644 --- a/arch/ia64/include/uapi/asm/ptrace.h +++ b/arch/ia64/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 1998-2004 Hewlett-Packard Co * David Mosberger-Tang diff --git a/arch/ia64/include/uapi/asm/ptrace_offsets.h b/arch/ia64/include/uapi/asm/ptrace_offsets.h index b712773c759e..2847c18139ef 100644 --- a/arch/ia64/include/uapi/asm/ptrace_offsets.h +++ b/arch/ia64/include/uapi/asm/ptrace_offsets.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_IA64_PTRACE_OFFSETS_H #define _ASM_IA64_PTRACE_OFFSETS_H diff --git a/arch/ia64/include/uapi/asm/resource.h b/arch/ia64/include/uapi/asm/resource.h index ba2272a87fc7..d488d2b22ac4 100644 --- a/arch/ia64/include/uapi/asm/resource.h +++ b/arch/ia64/include/uapi/asm/resource.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_IA64_RESOURCE_H #define _ASM_IA64_RESOURCE_H diff --git a/arch/ia64/include/uapi/asm/rse.h b/arch/ia64/include/uapi/asm/rse.h index 02830a3b0196..6d260af571c5 100644 --- a/arch/ia64/include/uapi/asm/rse.h +++ b/arch/ia64/include/uapi/asm/rse.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_IA64_RSE_H #define _ASM_IA64_RSE_H diff --git a/arch/ia64/include/uapi/asm/sembuf.h b/arch/ia64/include/uapi/asm/sembuf.h index 1340fbc04d3e..6ed058760afc 100644 --- a/arch/ia64/include/uapi/asm/sembuf.h +++ b/arch/ia64/include/uapi/asm/sembuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_IA64_SEMBUF_H #define _ASM_IA64_SEMBUF_H diff --git a/arch/ia64/include/uapi/asm/setup.h b/arch/ia64/include/uapi/asm/setup.h index 8d56458310b3..8d13ce8fb03a 100644 --- a/arch/ia64/include/uapi/asm/setup.h +++ b/arch/ia64/include/uapi/asm/setup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __IA64_SETUP_H #define __IA64_SETUP_H diff --git a/arch/ia64/include/uapi/asm/shmbuf.h b/arch/ia64/include/uapi/asm/shmbuf.h index 585002a77acd..6ef57cb70dee 100644 --- a/arch/ia64/include/uapi/asm/shmbuf.h +++ b/arch/ia64/include/uapi/asm/shmbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_IA64_SHMBUF_H #define _ASM_IA64_SHMBUF_H diff --git a/arch/ia64/include/uapi/asm/sigcontext.h b/arch/ia64/include/uapi/asm/sigcontext.h index 57ff777bcc40..1bb6f0f2bd73 100644 --- a/arch/ia64/include/uapi/asm/sigcontext.h +++ b/arch/ia64/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_IA64_SIGCONTEXT_H #define _ASM_IA64_SIGCONTEXT_H diff --git a/arch/ia64/include/uapi/asm/siginfo.h b/arch/ia64/include/uapi/asm/siginfo.h index 33389fc36f23..f3a02a10c3a3 100644 --- a/arch/ia64/include/uapi/asm/siginfo.h +++ b/arch/ia64/include/uapi/asm/siginfo.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Based on . * diff --git a/arch/ia64/include/uapi/asm/signal.h b/arch/ia64/include/uapi/asm/signal.h index c0ea2855e96b..aa98ff1b9e22 100644 --- a/arch/ia64/include/uapi/asm/signal.h +++ b/arch/ia64/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Modified 1998-2001, 2003 * David Mosberger-Tang , Hewlett-Packard Co diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h index 002eb85a6941..3efba40adc54 100644 --- a/arch/ia64/include/uapi/asm/socket.h +++ b/arch/ia64/include/uapi/asm/socket.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_IA64_SOCKET_H #define _ASM_IA64_SOCKET_H diff --git a/arch/ia64/include/uapi/asm/sockios.h b/arch/ia64/include/uapi/asm/sockios.h index 15c92468ad38..f27a12f95d20 100644 --- a/arch/ia64/include/uapi/asm/sockios.h +++ b/arch/ia64/include/uapi/asm/sockios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_IA64_SOCKIOS_H #define _ASM_IA64_SOCKIOS_H diff --git a/arch/ia64/include/uapi/asm/stat.h b/arch/ia64/include/uapi/asm/stat.h index 367bb90cdffa..3265ed5aac0f 100644 --- a/arch/ia64/include/uapi/asm/stat.h +++ b/arch/ia64/include/uapi/asm/stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_IA64_STAT_H #define _ASM_IA64_STAT_H diff --git a/arch/ia64/include/uapi/asm/statfs.h b/arch/ia64/include/uapi/asm/statfs.h index 1e589669de56..de3bae4f137d 100644 --- a/arch/ia64/include/uapi/asm/statfs.h +++ b/arch/ia64/include/uapi/asm/statfs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_IA64_STATFS_H #define _ASM_IA64_STATFS_H diff --git a/arch/ia64/include/uapi/asm/swab.h b/arch/ia64/include/uapi/asm/swab.h index c89a8cb5d8a5..79f3fef1a05e 100644 --- a/arch/ia64/include/uapi/asm/swab.h +++ b/arch/ia64/include/uapi/asm/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_IA64_SWAB_H #define _ASM_IA64_SWAB_H diff --git a/arch/ia64/include/uapi/asm/termbits.h b/arch/ia64/include/uapi/asm/termbits.h index c009b94e58d9..000a1a297c75 100644 --- a/arch/ia64/include/uapi/asm/termbits.h +++ b/arch/ia64/include/uapi/asm/termbits.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_IA64_TERMBITS_H #define _ASM_IA64_TERMBITS_H diff --git a/arch/ia64/include/uapi/asm/termios.h b/arch/ia64/include/uapi/asm/termios.h index d59b48c307f8..199742d08f2c 100644 --- a/arch/ia64/include/uapi/asm/termios.h +++ b/arch/ia64/include/uapi/asm/termios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Modified 1999 * David Mosberger-Tang , Hewlett-Packard Co diff --git a/arch/ia64/include/uapi/asm/types.h b/arch/ia64/include/uapi/asm/types.h index 321193b05eed..2000de474be6 100644 --- a/arch/ia64/include/uapi/asm/types.h +++ b/arch/ia64/include/uapi/asm/types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is never included by application software unless explicitly * requested (e.g., via linux/types.h) in which case the application is diff --git a/arch/ia64/include/uapi/asm/ucontext.h b/arch/ia64/include/uapi/asm/ucontext.h index bf573dc8ca6a..46f51e535e04 100644 --- a/arch/ia64/include/uapi/asm/ucontext.h +++ b/arch/ia64/include/uapi/asm/ucontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_IA64_UCONTEXT_H #define _ASM_IA64_UCONTEXT_H diff --git a/arch/ia64/include/uapi/asm/unistd.h b/arch/ia64/include/uapi/asm/unistd.h index ea5363daa7bd..5fe71d4a43de 100644 --- a/arch/ia64/include/uapi/asm/unistd.h +++ b/arch/ia64/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * IA-64 Linux syscall numbers and inline-functions. * diff --git a/arch/ia64/include/uapi/asm/ustack.h b/arch/ia64/include/uapi/asm/ustack.h index 1dfebc622692..703cc5f546ff 100644 --- a/arch/ia64/include/uapi/asm/ustack.h +++ b/arch/ia64/include/uapi/asm/ustack.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_IA64_USTACK_H #define _UAPI_ASM_IA64_USTACK_H diff --git a/arch/m32r/include/uapi/asm/bitsperlong.h b/arch/m32r/include/uapi/asm/bitsperlong.h index 6dc0bb0c13b2..76da34b10f59 100644 --- a/arch/m32r/include/uapi/asm/bitsperlong.h +++ b/arch/m32r/include/uapi/asm/bitsperlong.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/m32r/include/uapi/asm/byteorder.h b/arch/m32r/include/uapi/asm/byteorder.h index 21855d8b028b..9b4a8ba483cd 100644 --- a/arch/m32r/include/uapi/asm/byteorder.h +++ b/arch/m32r/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_M32R_BYTEORDER_H #define _ASM_M32R_BYTEORDER_H diff --git a/arch/m32r/include/uapi/asm/errno.h b/arch/m32r/include/uapi/asm/errno.h index 777149262aad..ab38ef607882 100644 --- a/arch/m32r/include/uapi/asm/errno.h +++ b/arch/m32r/include/uapi/asm/errno.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_M32R_ERRNO_H #define _ASM_M32R_ERRNO_H diff --git a/arch/m32r/include/uapi/asm/fcntl.h b/arch/m32r/include/uapi/asm/fcntl.h index 46ab12db5739..a77648c505d1 100644 --- a/arch/m32r/include/uapi/asm/fcntl.h +++ b/arch/m32r/include/uapi/asm/fcntl.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/m32r/include/uapi/asm/ioctl.h b/arch/m32r/include/uapi/asm/ioctl.h index b279fe06dfe5..b809c4566e5f 100644 --- a/arch/m32r/include/uapi/asm/ioctl.h +++ b/arch/m32r/include/uapi/asm/ioctl.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/m32r/include/uapi/asm/ioctls.h b/arch/m32r/include/uapi/asm/ioctls.h index 349bf87bfbd0..31da4c3bab94 100644 --- a/arch/m32r/include/uapi/asm/ioctls.h +++ b/arch/m32r/include/uapi/asm/ioctls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ARCH_M32R_IOCTLS_H__ #define __ARCH_M32R_IOCTLS_H__ diff --git a/arch/m32r/include/uapi/asm/ipcbuf.h b/arch/m32r/include/uapi/asm/ipcbuf.h index 84c7e51cb6d0..90d6445a14df 100644 --- a/arch/m32r/include/uapi/asm/ipcbuf.h +++ b/arch/m32r/include/uapi/asm/ipcbuf.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/m32r/include/uapi/asm/msgbuf.h b/arch/m32r/include/uapi/asm/msgbuf.h index 0d5a877b813e..4386ff2735ba 100644 --- a/arch/m32r/include/uapi/asm/msgbuf.h +++ b/arch/m32r/include/uapi/asm/msgbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_M32R_MSGBUF_H #define _ASM_M32R_MSGBUF_H diff --git a/arch/m32r/include/uapi/asm/param.h b/arch/m32r/include/uapi/asm/param.h index fa207bdf96e7..0bff6d6133f5 100644 --- a/arch/m32r/include/uapi/asm/param.h +++ b/arch/m32r/include/uapi/asm/param.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_M32R_PARAM_H #define _ASM_M32R_PARAM_H diff --git a/arch/m32r/include/uapi/asm/poll.h b/arch/m32r/include/uapi/asm/poll.h index c98509d3149e..b7132a305a47 100644 --- a/arch/m32r/include/uapi/asm/poll.h +++ b/arch/m32r/include/uapi/asm/poll.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/m32r/include/uapi/asm/posix_types.h b/arch/m32r/include/uapi/asm/posix_types.h index 236de26a409b..63316fcb1b57 100644 --- a/arch/m32r/include/uapi/asm/posix_types.h +++ b/arch/m32r/include/uapi/asm/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_M32R_POSIX_TYPES_H #define _ASM_M32R_POSIX_TYPES_H diff --git a/arch/m32r/include/uapi/asm/resource.h b/arch/m32r/include/uapi/asm/resource.h index b1ce766e37a0..3282f3c4a5ca 100644 --- a/arch/m32r/include/uapi/asm/resource.h +++ b/arch/m32r/include/uapi/asm/resource.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_M32R_RESOURCE_H #define _ASM_M32R_RESOURCE_H diff --git a/arch/m32r/include/uapi/asm/sembuf.h b/arch/m32r/include/uapi/asm/sembuf.h index c9873d6890e2..de34664d8cd7 100644 --- a/arch/m32r/include/uapi/asm/sembuf.h +++ b/arch/m32r/include/uapi/asm/sembuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_M32R_SEMBUF_H #define _ASM_M32R_SEMBUF_H diff --git a/arch/m32r/include/uapi/asm/setup.h b/arch/m32r/include/uapi/asm/setup.h index 96961a42e5f4..d936a64bbafd 100644 --- a/arch/m32r/include/uapi/asm/setup.h +++ b/arch/m32r/include/uapi/asm/setup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_M32R_SETUP_H #define _UAPI_ASM_M32R_SETUP_H diff --git a/arch/m32r/include/uapi/asm/shmbuf.h b/arch/m32r/include/uapi/asm/shmbuf.h index b0cdf0aa7d65..44c2ea924829 100644 --- a/arch/m32r/include/uapi/asm/shmbuf.h +++ b/arch/m32r/include/uapi/asm/shmbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_M32R_SHMBUF_H #define _ASM_M32R_SHMBUF_H diff --git a/arch/m32r/include/uapi/asm/sigcontext.h b/arch/m32r/include/uapi/asm/sigcontext.h index da4a9c36d09b..cc9ee73525ff 100644 --- a/arch/m32r/include/uapi/asm/sigcontext.h +++ b/arch/m32r/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_M32R_SIGCONTEXT_H #define _ASM_M32R_SIGCONTEXT_H diff --git a/arch/m32r/include/uapi/asm/signal.h b/arch/m32r/include/uapi/asm/signal.h index 54acacb1f1f7..c2ac3417fb98 100644 --- a/arch/m32r/include/uapi/asm/signal.h +++ b/arch/m32r/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_M32R_SIGNAL_H #define _UAPI_ASM_M32R_SIGNAL_H diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h index e268e51a38d1..cf5018e82c3d 100644 --- a/arch/m32r/include/uapi/asm/socket.h +++ b/arch/m32r/include/uapi/asm/socket.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_M32R_SOCKET_H #define _ASM_M32R_SOCKET_H diff --git a/arch/m32r/include/uapi/asm/sockios.h b/arch/m32r/include/uapi/asm/sockios.h index 6c1fb9b43bdb..948229e474c5 100644 --- a/arch/m32r/include/uapi/asm/sockios.h +++ b/arch/m32r/include/uapi/asm/sockios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_M32R_SOCKIOS_H #define _ASM_M32R_SOCKIOS_H diff --git a/arch/m32r/include/uapi/asm/stat.h b/arch/m32r/include/uapi/asm/stat.h index 98470fe483b6..0fe9f96ce8f0 100644 --- a/arch/m32r/include/uapi/asm/stat.h +++ b/arch/m32r/include/uapi/asm/stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_M32R_STAT_H #define _ASM_M32R_STAT_H diff --git a/arch/m32r/include/uapi/asm/statfs.h b/arch/m32r/include/uapi/asm/statfs.h index 6eb4c6007e6b..d42ae20dbb2b 100644 --- a/arch/m32r/include/uapi/asm/statfs.h +++ b/arch/m32r/include/uapi/asm/statfs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_M32R_STATFS_H #define _ASM_M32R_STATFS_H diff --git a/arch/m32r/include/uapi/asm/swab.h b/arch/m32r/include/uapi/asm/swab.h index 54dab001d6d1..18dce47d2841 100644 --- a/arch/m32r/include/uapi/asm/swab.h +++ b/arch/m32r/include/uapi/asm/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_M32R_SWAB_H #define _ASM_M32R_SWAB_H diff --git a/arch/m32r/include/uapi/asm/termbits.h b/arch/m32r/include/uapi/asm/termbits.h index 957a3c688549..6cbbae9695b4 100644 --- a/arch/m32r/include/uapi/asm/termbits.h +++ b/arch/m32r/include/uapi/asm/termbits.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_M32R_TERMBITS_H #define _ASM_M32R_TERMBITS_H diff --git a/arch/m32r/include/uapi/asm/termios.h b/arch/m32r/include/uapi/asm/termios.h index 07ad27b8f7db..9b80a85e83ac 100644 --- a/arch/m32r/include/uapi/asm/termios.h +++ b/arch/m32r/include/uapi/asm/termios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_M32R_TERMIOS_H #define _UAPI_M32R_TERMIOS_H diff --git a/arch/m32r/include/uapi/asm/unistd.h b/arch/m32r/include/uapi/asm/unistd.h index 5a54f2ae3b51..adf8666a68ef 100644 --- a/arch/m32r/include/uapi/asm/unistd.h +++ b/arch/m32r/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_M32R_UNISTD_H #define _UAPI_ASM_M32R_UNISTD_H diff --git a/arch/m68k/include/uapi/asm/a.out.h b/arch/m68k/include/uapi/asm/a.out.h index 3885fe43432a..3eb24fd8b810 100644 --- a/arch/m68k/include/uapi/asm/a.out.h +++ b/arch/m68k/include/uapi/asm/a.out.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __M68K_A_OUT_H__ #define __M68K_A_OUT_H__ diff --git a/arch/m68k/include/uapi/asm/bootinfo-amiga.h b/arch/m68k/include/uapi/asm/bootinfo-amiga.h index daad3c58d2da..69bf4dda341e 100644 --- a/arch/m68k/include/uapi/asm/bootinfo-amiga.h +++ b/arch/m68k/include/uapi/asm/bootinfo-amiga.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* ** asm/bootinfo-amiga.h -- Amiga-specific boot information definitions */ diff --git a/arch/m68k/include/uapi/asm/bootinfo-apollo.h b/arch/m68k/include/uapi/asm/bootinfo-apollo.h index a93e0af1c6fe..c226f7957938 100644 --- a/arch/m68k/include/uapi/asm/bootinfo-apollo.h +++ b/arch/m68k/include/uapi/asm/bootinfo-apollo.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* ** asm/bootinfo-apollo.h -- Apollo-specific boot information definitions */ diff --git a/arch/m68k/include/uapi/asm/bootinfo-atari.h b/arch/m68k/include/uapi/asm/bootinfo-atari.h index a817854049bb..f2218a090fdb 100644 --- a/arch/m68k/include/uapi/asm/bootinfo-atari.h +++ b/arch/m68k/include/uapi/asm/bootinfo-atari.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* ** asm/bootinfo-atari.h -- Atari-specific boot information definitions */ diff --git a/arch/m68k/include/uapi/asm/bootinfo-hp300.h b/arch/m68k/include/uapi/asm/bootinfo-hp300.h index c90cb71ed89a..2141c4f5f0a7 100644 --- a/arch/m68k/include/uapi/asm/bootinfo-hp300.h +++ b/arch/m68k/include/uapi/asm/bootinfo-hp300.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* ** asm/bootinfo-hp300.h -- HP9000/300-specific boot information definitions */ diff --git a/arch/m68k/include/uapi/asm/bootinfo-mac.h b/arch/m68k/include/uapi/asm/bootinfo-mac.h index b44ff73898a9..449928cfcbf2 100644 --- a/arch/m68k/include/uapi/asm/bootinfo-mac.h +++ b/arch/m68k/include/uapi/asm/bootinfo-mac.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* ** asm/bootinfo-mac.h -- Macintosh-specific boot information definitions */ diff --git a/arch/m68k/include/uapi/asm/bootinfo-q40.h b/arch/m68k/include/uapi/asm/bootinfo-q40.h index c79fea7e555b..78bda04bf788 100644 --- a/arch/m68k/include/uapi/asm/bootinfo-q40.h +++ b/arch/m68k/include/uapi/asm/bootinfo-q40.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* ** asm/bootinfo-q40.h -- Q40-specific boot information definitions */ diff --git a/arch/m68k/include/uapi/asm/bootinfo-vme.h b/arch/m68k/include/uapi/asm/bootinfo-vme.h index a135eb41d672..f36a09ab5e79 100644 --- a/arch/m68k/include/uapi/asm/bootinfo-vme.h +++ b/arch/m68k/include/uapi/asm/bootinfo-vme.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* ** asm/bootinfo-vme.h -- VME-specific boot information definitions */ diff --git a/arch/m68k/include/uapi/asm/byteorder.h b/arch/m68k/include/uapi/asm/byteorder.h index 31b260a88803..1fb5732f4a91 100644 --- a/arch/m68k/include/uapi/asm/byteorder.h +++ b/arch/m68k/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _M68K_BYTEORDER_H #define _M68K_BYTEORDER_H diff --git a/arch/m68k/include/uapi/asm/cachectl.h b/arch/m68k/include/uapi/asm/cachectl.h index 525978e959e3..6171e246ca7b 100644 --- a/arch/m68k/include/uapi/asm/cachectl.h +++ b/arch/m68k/include/uapi/asm/cachectl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _M68K_CACHECTL_H #define _M68K_CACHECTL_H diff --git a/arch/m68k/include/uapi/asm/fcntl.h b/arch/m68k/include/uapi/asm/fcntl.h index 1c369b20dc45..c6861e6ee313 100644 --- a/arch/m68k/include/uapi/asm/fcntl.h +++ b/arch/m68k/include/uapi/asm/fcntl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _M68K_FCNTL_H #define _M68K_FCNTL_H diff --git a/arch/m68k/include/uapi/asm/ioctls.h b/arch/m68k/include/uapi/asm/ioctls.h index 1332bb4ca5b0..d92d7c7786bf 100644 --- a/arch/m68k/include/uapi/asm/ioctls.h +++ b/arch/m68k/include/uapi/asm/ioctls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ARCH_M68K_IOCTLS_H__ #define __ARCH_M68K_IOCTLS_H__ diff --git a/arch/m68k/include/uapi/asm/param.h b/arch/m68k/include/uapi/asm/param.h index 36265ccf5c7b..726b2e7ec70d 100644 --- a/arch/m68k/include/uapi/asm/param.h +++ b/arch/m68k/include/uapi/asm/param.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _M68K_PARAM_H #define _M68K_PARAM_H diff --git a/arch/m68k/include/uapi/asm/poll.h b/arch/m68k/include/uapi/asm/poll.h index f080fcdb61bf..c3e3fcc15e1d 100644 --- a/arch/m68k/include/uapi/asm/poll.h +++ b/arch/m68k/include/uapi/asm/poll.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __m68k_POLL_H #define __m68k_POLL_H diff --git a/arch/m68k/include/uapi/asm/posix_types.h b/arch/m68k/include/uapi/asm/posix_types.h index cf4dbf70fdc7..10a65149b5f2 100644 --- a/arch/m68k/include/uapi/asm/posix_types.h +++ b/arch/m68k/include/uapi/asm/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ARCH_M68K_POSIX_TYPES_H #define __ARCH_M68K_POSIX_TYPES_H diff --git a/arch/m68k/include/uapi/asm/ptrace.h b/arch/m68k/include/uapi/asm/ptrace.h index caf92fd34939..19a1b9d0d858 100644 --- a/arch/m68k/include/uapi/asm/ptrace.h +++ b/arch/m68k/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_M68K_PTRACE_H #define _UAPI_M68K_PTRACE_H diff --git a/arch/m68k/include/uapi/asm/sigcontext.h b/arch/m68k/include/uapi/asm/sigcontext.h index 523db2a51cf3..6cc8421c8a73 100644 --- a/arch/m68k/include/uapi/asm/sigcontext.h +++ b/arch/m68k/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_M68k_SIGCONTEXT_H #define _ASM_M68k_SIGCONTEXT_H diff --git a/arch/m68k/include/uapi/asm/signal.h b/arch/m68k/include/uapi/asm/signal.h index cba6f858bb46..915cc755a184 100644 --- a/arch/m68k/include/uapi/asm/signal.h +++ b/arch/m68k/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_M68K_SIGNAL_H #define _UAPI_M68K_SIGNAL_H diff --git a/arch/m68k/include/uapi/asm/stat.h b/arch/m68k/include/uapi/asm/stat.h index dd38bc2e9f98..1e15e6517b9c 100644 --- a/arch/m68k/include/uapi/asm/stat.h +++ b/arch/m68k/include/uapi/asm/stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _M68K_STAT_H #define _M68K_STAT_H diff --git a/arch/m68k/include/uapi/asm/swab.h b/arch/m68k/include/uapi/asm/swab.h index b7b37a40defc..9ef4fafba7d4 100644 --- a/arch/m68k/include/uapi/asm/swab.h +++ b/arch/m68k/include/uapi/asm/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _M68K_SWAB_H #define _M68K_SWAB_H diff --git a/arch/m68k/include/uapi/asm/unistd.h b/arch/m68k/include/uapi/asm/unistd.h index 25589f5b8669..de3054f8a681 100644 --- a/arch/m68k/include/uapi/asm/unistd.h +++ b/arch/m68k/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_M68K_UNISTD_H_ #define _UAPI_ASM_M68K_UNISTD_H_ diff --git a/arch/metag/include/uapi/asm/byteorder.h b/arch/metag/include/uapi/asm/byteorder.h index 9558416d578b..e5e03ff7e20d 100644 --- a/arch/metag/include/uapi/asm/byteorder.h +++ b/arch/metag/include/uapi/asm/byteorder.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/metag/include/uapi/asm/ech.h b/arch/metag/include/uapi/asm/ech.h index ac94d1cf9be4..1e09f1ea4f7f 100644 --- a/arch/metag/include/uapi/asm/ech.h +++ b/arch/metag/include/uapi/asm/ech.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_METAG_ECH_H #define _UAPI_METAG_ECH_H diff --git a/arch/metag/include/uapi/asm/ptrace.h b/arch/metag/include/uapi/asm/ptrace.h index 45d97809d33e..8ad9daa841c3 100644 --- a/arch/metag/include/uapi/asm/ptrace.h +++ b/arch/metag/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_METAG_PTRACE_H #define _UAPI_METAG_PTRACE_H diff --git a/arch/metag/include/uapi/asm/sigcontext.h b/arch/metag/include/uapi/asm/sigcontext.h index ef79a910c1c4..ac7e1f28d584 100644 --- a/arch/metag/include/uapi/asm/sigcontext.h +++ b/arch/metag/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_METAG_SIGCONTEXT_H #define _ASM_METAG_SIGCONTEXT_H diff --git a/arch/metag/include/uapi/asm/siginfo.h b/arch/metag/include/uapi/asm/siginfo.h index b2e0c8b62aef..b54ef7186ca3 100644 --- a/arch/metag/include/uapi/asm/siginfo.h +++ b/arch/metag/include/uapi/asm/siginfo.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _METAG_SIGINFO_H #define _METAG_SIGINFO_H diff --git a/arch/metag/include/uapi/asm/swab.h b/arch/metag/include/uapi/asm/swab.h index 1076b3a6387a..30d696fcc237 100644 --- a/arch/metag/include/uapi/asm/swab.h +++ b/arch/metag/include/uapi/asm/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_METAG_SWAB_H #define __ASM_METAG_SWAB_H diff --git a/arch/microblaze/include/uapi/asm/auxvec.h b/arch/microblaze/include/uapi/asm/auxvec.h index 8b137891791f..93dd07bd0af7 100644 --- a/arch/microblaze/include/uapi/asm/auxvec.h +++ b/arch/microblaze/include/uapi/asm/auxvec.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ diff --git a/arch/microblaze/include/uapi/asm/byteorder.h b/arch/microblaze/include/uapi/asm/byteorder.h index 31902762a426..763660169456 100644 --- a/arch/microblaze/include/uapi/asm/byteorder.h +++ b/arch/microblaze/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_MICROBLAZE_BYTEORDER_H #define _ASM_MICROBLAZE_BYTEORDER_H diff --git a/arch/microblaze/include/uapi/asm/posix_types.h b/arch/microblaze/include/uapi/asm/posix_types.h index 0e15039673e3..f3249da69121 100644 --- a/arch/microblaze/include/uapi/asm/posix_types.h +++ b/arch/microblaze/include/uapi/asm/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_MICROBLAZE_POSIX_TYPES_H #define _ASM_MICROBLAZE_POSIX_TYPES_H diff --git a/arch/mips/include/uapi/asm/bitsperlong.h b/arch/mips/include/uapi/asm/bitsperlong.h index 3e4c10a8e787..7268380d8d28 100644 --- a/arch/mips/include/uapi/asm/bitsperlong.h +++ b/arch/mips/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_MIPS_BITSPERLONG_H #define __ASM_MIPS_BITSPERLONG_H diff --git a/arch/mips/include/uapi/asm/hwcap.h b/arch/mips/include/uapi/asm/hwcap.h index c7484a7ca686..600ad8fd6835 100644 --- a/arch/mips/include/uapi/asm/hwcap.h +++ b/arch/mips/include/uapi/asm/hwcap.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_HWCAP_H #define _UAPI_ASM_HWCAP_H diff --git a/arch/mips/include/uapi/asm/msgbuf.h b/arch/mips/include/uapi/asm/msgbuf.h index df849e87d9ae..eb4d0f9d7364 100644 --- a/arch/mips/include/uapi/asm/msgbuf.h +++ b/arch/mips/include/uapi/asm/msgbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_MSGBUF_H #define _ASM_MSGBUF_H diff --git a/arch/mips/include/uapi/asm/poll.h b/arch/mips/include/uapi/asm/poll.h index 47b952080431..ad289d7b7434 100644 --- a/arch/mips/include/uapi/asm/poll.h +++ b/arch/mips/include/uapi/asm/poll.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_POLL_H #define __ASM_POLL_H diff --git a/arch/mips/include/uapi/asm/sembuf.h b/arch/mips/include/uapi/asm/sembuf.h index e1085ac880f2..2c0f507ab7d1 100644 --- a/arch/mips/include/uapi/asm/sembuf.h +++ b/arch/mips/include/uapi/asm/sembuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SEMBUF_H #define _ASM_SEMBUF_H diff --git a/arch/mips/include/uapi/asm/setup.h b/arch/mips/include/uapi/asm/setup.h index 93f237bb1353..7d48c433b0c2 100644 --- a/arch/mips/include/uapi/asm/setup.h +++ b/arch/mips/include/uapi/asm/setup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_MIPS_SETUP_H #define _UAPI_MIPS_SETUP_H diff --git a/arch/mips/include/uapi/asm/shmbuf.h b/arch/mips/include/uapi/asm/shmbuf.h index f994438277bf..379e6bca518b 100644 --- a/arch/mips/include/uapi/asm/shmbuf.h +++ b/arch/mips/include/uapi/asm/shmbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SHMBUF_H #define _ASM_SHMBUF_H diff --git a/arch/mips/include/uapi/asm/ucontext.h b/arch/mips/include/uapi/asm/ucontext.h index 2320144ce858..2d3bf8eebf1f 100644 --- a/arch/mips/include/uapi/asm/ucontext.h +++ b/arch/mips/include/uapi/asm/ucontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __MIPS_UAPI_ASM_UCONTEXT_H #define __MIPS_UAPI_ASM_UCONTEXT_H diff --git a/arch/mn10300/include/uapi/asm/bitsperlong.h b/arch/mn10300/include/uapi/asm/bitsperlong.h index 6dc0bb0c13b2..76da34b10f59 100644 --- a/arch/mn10300/include/uapi/asm/bitsperlong.h +++ b/arch/mn10300/include/uapi/asm/bitsperlong.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/mn10300/include/uapi/asm/byteorder.h b/arch/mn10300/include/uapi/asm/byteorder.h index 5dd0bdd9feee..3467df91216c 100644 --- a/arch/mn10300/include/uapi/asm/byteorder.h +++ b/arch/mn10300/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_BYTEORDER_H #define _ASM_BYTEORDER_H diff --git a/arch/mn10300/include/uapi/asm/errno.h b/arch/mn10300/include/uapi/asm/errno.h index 4c82b503d92f..9addba592646 100644 --- a/arch/mn10300/include/uapi/asm/errno.h +++ b/arch/mn10300/include/uapi/asm/errno.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/mn10300/include/uapi/asm/fcntl.h b/arch/mn10300/include/uapi/asm/fcntl.h index 46ab12db5739..a77648c505d1 100644 --- a/arch/mn10300/include/uapi/asm/fcntl.h +++ b/arch/mn10300/include/uapi/asm/fcntl.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/mn10300/include/uapi/asm/ioctls.h b/arch/mn10300/include/uapi/asm/ioctls.h index 0212f4b22557..0955d4f854e9 100644 --- a/arch/mn10300/include/uapi/asm/ioctls.h +++ b/arch/mn10300/include/uapi/asm/ioctls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_IOCTLS_H #define _ASM_IOCTLS_H diff --git a/arch/mn10300/include/uapi/asm/ipcbuf.h b/arch/mn10300/include/uapi/asm/ipcbuf.h index 84c7e51cb6d0..90d6445a14df 100644 --- a/arch/mn10300/include/uapi/asm/ipcbuf.h +++ b/arch/mn10300/include/uapi/asm/ipcbuf.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/mn10300/include/uapi/asm/kvm_para.h b/arch/mn10300/include/uapi/asm/kvm_para.h index 14fab8f0b957..baacc4996d18 100644 --- a/arch/mn10300/include/uapi/asm/kvm_para.h +++ b/arch/mn10300/include/uapi/asm/kvm_para.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/mn10300/include/uapi/asm/mman.h b/arch/mn10300/include/uapi/asm/mman.h index db5c53da73ce..eb7f4798c036 100644 --- a/arch/mn10300/include/uapi/asm/mman.h +++ b/arch/mn10300/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include #define MIN_MAP_ADDR PAGE_SIZE /* minimum fixed mmap address */ diff --git a/arch/mn10300/include/uapi/asm/msgbuf.h b/arch/mn10300/include/uapi/asm/msgbuf.h index 8b602450cc4a..5982def83355 100644 --- a/arch/mn10300/include/uapi/asm/msgbuf.h +++ b/arch/mn10300/include/uapi/asm/msgbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_MSGBUF_H #define _ASM_MSGBUF_H diff --git a/arch/mn10300/include/uapi/asm/poll.h b/arch/mn10300/include/uapi/asm/poll.h index c98509d3149e..b7132a305a47 100644 --- a/arch/mn10300/include/uapi/asm/poll.h +++ b/arch/mn10300/include/uapi/asm/poll.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/mn10300/include/uapi/asm/resource.h b/arch/mn10300/include/uapi/asm/resource.h index 04bc4db8921b..49a81fbab43d 100644 --- a/arch/mn10300/include/uapi/asm/resource.h +++ b/arch/mn10300/include/uapi/asm/resource.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/mn10300/include/uapi/asm/sembuf.h b/arch/mn10300/include/uapi/asm/sembuf.h index 301f3f9d8aa9..ef44c42c7e0f 100644 --- a/arch/mn10300/include/uapi/asm/sembuf.h +++ b/arch/mn10300/include/uapi/asm/sembuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SEMBUF_H #define _ASM_SEMBUF_H diff --git a/arch/mn10300/include/uapi/asm/setup.h b/arch/mn10300/include/uapi/asm/setup.h index ae5704fa77ad..043dd4b92026 100644 --- a/arch/mn10300/include/uapi/asm/setup.h +++ b/arch/mn10300/include/uapi/asm/setup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * There isn't anything here anymore, but the file must not be empty or patch * will delete it. diff --git a/arch/mn10300/include/uapi/asm/shmbuf.h b/arch/mn10300/include/uapi/asm/shmbuf.h index 8f300cc35d6c..6e81f74f51c6 100644 --- a/arch/mn10300/include/uapi/asm/shmbuf.h +++ b/arch/mn10300/include/uapi/asm/shmbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SHMBUF_H #define _ASM_SHMBUF_H diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h index ac82a3f26dbf..b35eee132142 100644 --- a/arch/mn10300/include/uapi/asm/socket.h +++ b/arch/mn10300/include/uapi/asm/socket.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SOCKET_H #define _ASM_SOCKET_H diff --git a/arch/mn10300/include/uapi/asm/sockios.h b/arch/mn10300/include/uapi/asm/sockios.h index b03043a1c564..5706baa3cd0d 100644 --- a/arch/mn10300/include/uapi/asm/sockios.h +++ b/arch/mn10300/include/uapi/asm/sockios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SOCKIOS_H #define _ASM_SOCKIOS_H diff --git a/arch/mn10300/include/uapi/asm/stat.h b/arch/mn10300/include/uapi/asm/stat.h index 63ff8371cf2c..769f5f8829d4 100644 --- a/arch/mn10300/include/uapi/asm/stat.h +++ b/arch/mn10300/include/uapi/asm/stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_STAT_H #define _ASM_STAT_H diff --git a/arch/mn10300/include/uapi/asm/termbits.h b/arch/mn10300/include/uapi/asm/termbits.h index 130d42495972..fca82ea2ca2c 100644 --- a/arch/mn10300/include/uapi/asm/termbits.h +++ b/arch/mn10300/include/uapi/asm/termbits.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_TERMBITS_H #define _ASM_TERMBITS_H diff --git a/arch/mn10300/include/uapi/asm/termios.h b/arch/mn10300/include/uapi/asm/termios.h index 11d3cc9d3162..25981aadb8cd 100644 --- a/arch/mn10300/include/uapi/asm/termios.h +++ b/arch/mn10300/include/uapi/asm/termios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_TERMIOS_H #define _UAPI_ASM_TERMIOS_H diff --git a/arch/parisc/include/uapi/asm/bitsperlong.h b/arch/parisc/include/uapi/asm/bitsperlong.h index 07fa7e50bdc0..307e2ef1c62d 100644 --- a/arch/parisc/include/uapi/asm/bitsperlong.h +++ b/arch/parisc/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_PARISC_BITSPERLONG_H #define __ASM_PARISC_BITSPERLONG_H diff --git a/arch/parisc/include/uapi/asm/byteorder.h b/arch/parisc/include/uapi/asm/byteorder.h index 58af2c5f5d61..a59d9b7e35a8 100644 --- a/arch/parisc/include/uapi/asm/byteorder.h +++ b/arch/parisc/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _PARISC_BYTEORDER_H #define _PARISC_BYTEORDER_H diff --git a/arch/parisc/include/uapi/asm/errno.h b/arch/parisc/include/uapi/asm/errno.h index 274d5bc6ecce..fc0df353ff0d 100644 --- a/arch/parisc/include/uapi/asm/errno.h +++ b/arch/parisc/include/uapi/asm/errno.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _PARISC_ERRNO_H #define _PARISC_ERRNO_H diff --git a/arch/parisc/include/uapi/asm/fcntl.h b/arch/parisc/include/uapi/asm/fcntl.h index 34a46cbc76ed..03ce20e5ad7d 100644 --- a/arch/parisc/include/uapi/asm/fcntl.h +++ b/arch/parisc/include/uapi/asm/fcntl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _PARISC_FCNTL_H #define _PARISC_FCNTL_H diff --git a/arch/parisc/include/uapi/asm/ioctls.h b/arch/parisc/include/uapi/asm/ioctls.h index d0e3321403be..aafb1c0ca0af 100644 --- a/arch/parisc/include/uapi/asm/ioctls.h +++ b/arch/parisc/include/uapi/asm/ioctls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ARCH_PARISC_IOCTLS_H__ #define __ARCH_PARISC_IOCTLS_H__ diff --git a/arch/parisc/include/uapi/asm/ipcbuf.h b/arch/parisc/include/uapi/asm/ipcbuf.h index 790c4119f647..edf266204b49 100644 --- a/arch/parisc/include/uapi/asm/ipcbuf.h +++ b/arch/parisc/include/uapi/asm/ipcbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __PARISC_IPCBUF_H__ #define __PARISC_IPCBUF_H__ diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h index 775b5d5e41a1..d1af0d74a188 100644 --- a/arch/parisc/include/uapi/asm/mman.h +++ b/arch/parisc/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __PARISC_MMAN_H__ #define __PARISC_MMAN_H__ diff --git a/arch/parisc/include/uapi/asm/msgbuf.h b/arch/parisc/include/uapi/asm/msgbuf.h index 2e83ac758e19..b48b810e626b 100644 --- a/arch/parisc/include/uapi/asm/msgbuf.h +++ b/arch/parisc/include/uapi/asm/msgbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _PARISC_MSGBUF_H #define _PARISC_MSGBUF_H diff --git a/arch/parisc/include/uapi/asm/pdc.h b/arch/parisc/include/uapi/asm/pdc.h index 1f30b49772aa..0ad117617f1a 100644 --- a/arch/parisc/include/uapi/asm/pdc.h +++ b/arch/parisc/include/uapi/asm/pdc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_PARISC_PDC_H #define _UAPI_PARISC_PDC_H diff --git a/arch/parisc/include/uapi/asm/posix_types.h b/arch/parisc/include/uapi/asm/posix_types.h index f3b5f70b9a5f..2785632c85e7 100644 --- a/arch/parisc/include/uapi/asm/posix_types.h +++ b/arch/parisc/include/uapi/asm/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ARCH_PARISC_POSIX_TYPES_H #define __ARCH_PARISC_POSIX_TYPES_H diff --git a/arch/parisc/include/uapi/asm/ptrace.h b/arch/parisc/include/uapi/asm/ptrace.h index 02ce2eb99a7f..e72e06247f51 100644 --- a/arch/parisc/include/uapi/asm/ptrace.h +++ b/arch/parisc/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* written by Philipp Rumpf, Copyright (C) 1999 SuSE GmbH Nuernberg ** Copyright (C) 2000 Grant Grundler, Hewlett-Packard */ diff --git a/arch/parisc/include/uapi/asm/sembuf.h b/arch/parisc/include/uapi/asm/sembuf.h index c20971bf520f..746c5d86a9b1 100644 --- a/arch/parisc/include/uapi/asm/sembuf.h +++ b/arch/parisc/include/uapi/asm/sembuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _PARISC_SEMBUF_H #define _PARISC_SEMBUF_H diff --git a/arch/parisc/include/uapi/asm/setup.h b/arch/parisc/include/uapi/asm/setup.h index 7da2e5b8747e..78b2f4ec7d65 100644 --- a/arch/parisc/include/uapi/asm/setup.h +++ b/arch/parisc/include/uapi/asm/setup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _PARISC_SETUP_H #define _PARISC_SETUP_H diff --git a/arch/parisc/include/uapi/asm/shmbuf.h b/arch/parisc/include/uapi/asm/shmbuf.h index 750e13e77991..cd4dbce55d0b 100644 --- a/arch/parisc/include/uapi/asm/shmbuf.h +++ b/arch/parisc/include/uapi/asm/shmbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _PARISC_SHMBUF_H #define _PARISC_SHMBUF_H diff --git a/arch/parisc/include/uapi/asm/sigcontext.h b/arch/parisc/include/uapi/asm/sigcontext.h index 27ef31bb3b6e..be404bb0f8e3 100644 --- a/arch/parisc/include/uapi/asm/sigcontext.h +++ b/arch/parisc/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASMPARISC_SIGCONTEXT_H #define _ASMPARISC_SIGCONTEXT_H diff --git a/arch/parisc/include/uapi/asm/siginfo.h b/arch/parisc/include/uapi/asm/siginfo.h index 8fd10f85c50e..4a1062e05aaf 100644 --- a/arch/parisc/include/uapi/asm/siginfo.h +++ b/arch/parisc/include/uapi/asm/siginfo.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _PARISC_SIGINFO_H #define _PARISC_SIGINFO_H diff --git a/arch/parisc/include/uapi/asm/signal.h b/arch/parisc/include/uapi/asm/signal.h index e26043b73f5d..d38563a394f2 100644 --- a/arch/parisc/include/uapi/asm/signal.h +++ b/arch/parisc/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_PARISC_SIGNAL_H #define _UAPI_ASM_PARISC_SIGNAL_H diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index 3b2bf7ae703b..1d0fdc3b5d22 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_SOCKET_H #define _UAPI_ASM_SOCKET_H diff --git a/arch/parisc/include/uapi/asm/sockios.h b/arch/parisc/include/uapi/asm/sockios.h index dabfbc7483f6..66a3ba64d53f 100644 --- a/arch/parisc/include/uapi/asm/sockios.h +++ b/arch/parisc/include/uapi/asm/sockios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ARCH_PARISC_SOCKIOS__ #define __ARCH_PARISC_SOCKIOS__ diff --git a/arch/parisc/include/uapi/asm/stat.h b/arch/parisc/include/uapi/asm/stat.h index 3310d2a49759..b5bbf6704cae 100644 --- a/arch/parisc/include/uapi/asm/stat.h +++ b/arch/parisc/include/uapi/asm/stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _PARISC_STAT_H #define _PARISC_STAT_H diff --git a/arch/parisc/include/uapi/asm/statfs.h b/arch/parisc/include/uapi/asm/statfs.h index 324bea905dc6..e5de020c21ab 100644 --- a/arch/parisc/include/uapi/asm/statfs.h +++ b/arch/parisc/include/uapi/asm/statfs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _PARISC_STATFS_H #define _PARISC_STATFS_H diff --git a/arch/parisc/include/uapi/asm/swab.h b/arch/parisc/include/uapi/asm/swab.h index 928e1bbac98f..35fb2d1bfbbd 100644 --- a/arch/parisc/include/uapi/asm/swab.h +++ b/arch/parisc/include/uapi/asm/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _PARISC_SWAB_H #define _PARISC_SWAB_H diff --git a/arch/parisc/include/uapi/asm/termbits.h b/arch/parisc/include/uapi/asm/termbits.h index d1ab92177a5c..40e920f8d683 100644 --- a/arch/parisc/include/uapi/asm/termbits.h +++ b/arch/parisc/include/uapi/asm/termbits.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ARCH_PARISC_TERMBITS_H__ #define __ARCH_PARISC_TERMBITS_H__ diff --git a/arch/parisc/include/uapi/asm/termios.h b/arch/parisc/include/uapi/asm/termios.h index f3377395070d..aba174f23ef0 100644 --- a/arch/parisc/include/uapi/asm/termios.h +++ b/arch/parisc/include/uapi/asm/termios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_PARISC_TERMIOS_H #define _UAPI_PARISC_TERMIOS_H diff --git a/arch/parisc/include/uapi/asm/types.h b/arch/parisc/include/uapi/asm/types.h index 8866f9bbdeaf..28c7d7453b10 100644 --- a/arch/parisc/include/uapi/asm/types.h +++ b/arch/parisc/include/uapi/asm/types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _PARISC_TYPES_H #define _PARISC_TYPES_H diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h index 667c99421003..4872e77aa96b 100644 --- a/arch/parisc/include/uapi/asm/unistd.h +++ b/arch/parisc/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_PARISC_UNISTD_H_ #define _UAPI_ASM_PARISC_UNISTD_H_ diff --git a/arch/powerpc/include/uapi/asm/auxvec.h b/arch/powerpc/include/uapi/asm/auxvec.h index be6e94ecec42..7af21dc0e320 100644 --- a/arch/powerpc/include/uapi/asm/auxvec.h +++ b/arch/powerpc/include/uapi/asm/auxvec.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_POWERPC_AUXVEC_H #define _ASM_POWERPC_AUXVEC_H diff --git a/arch/powerpc/include/uapi/asm/bitsperlong.h b/arch/powerpc/include/uapi/asm/bitsperlong.h index 5f1659032c40..46ece3ecff31 100644 --- a/arch/powerpc/include/uapi/asm/bitsperlong.h +++ b/arch/powerpc/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_POWERPC_BITSPERLONG_H #define __ASM_POWERPC_BITSPERLONG_H diff --git a/arch/powerpc/include/uapi/asm/bootx.h b/arch/powerpc/include/uapi/asm/bootx.h index 6e51cf0708a1..6728c7e24e58 100644 --- a/arch/powerpc/include/uapi/asm/bootx.h +++ b/arch/powerpc/include/uapi/asm/bootx.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file describes the structure passed from the BootX application * (for MacOS) when it is used to boot Linux. diff --git a/arch/powerpc/include/uapi/asm/cputable.h b/arch/powerpc/include/uapi/asm/cputable.h index 4d877144f377..50bcb4295de4 100644 --- a/arch/powerpc/include/uapi/asm/cputable.h +++ b/arch/powerpc/include/uapi/asm/cputable.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__ASM_POWERPC_CPUTABLE_H #define _UAPI__ASM_POWERPC_CPUTABLE_H diff --git a/arch/powerpc/include/uapi/asm/errno.h b/arch/powerpc/include/uapi/asm/errno.h index e8b6b5f7de7c..cc79856896a1 100644 --- a/arch/powerpc/include/uapi/asm/errno.h +++ b/arch/powerpc/include/uapi/asm/errno.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_POWERPC_ERRNO_H #define _ASM_POWERPC_ERRNO_H diff --git a/arch/powerpc/include/uapi/asm/fcntl.h b/arch/powerpc/include/uapi/asm/fcntl.h index ce5c4516d404..65ce08322a89 100644 --- a/arch/powerpc/include/uapi/asm/fcntl.h +++ b/arch/powerpc/include/uapi/asm/fcntl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_FCNTL_H #define _ASM_FCNTL_H diff --git a/arch/powerpc/include/uapi/asm/ioctl.h b/arch/powerpc/include/uapi/asm/ioctl.h index 57d68304218b..d623af4b9cd6 100644 --- a/arch/powerpc/include/uapi/asm/ioctl.h +++ b/arch/powerpc/include/uapi/asm/ioctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_POWERPC_IOCTL_H #define _ASM_POWERPC_IOCTL_H diff --git a/arch/powerpc/include/uapi/asm/ioctls.h b/arch/powerpc/include/uapi/asm/ioctls.h index e3b10469f787..41b1a5c15734 100644 --- a/arch/powerpc/include/uapi/asm/ioctls.h +++ b/arch/powerpc/include/uapi/asm/ioctls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_POWERPC_IOCTLS_H #define _ASM_POWERPC_IOCTLS_H diff --git a/arch/powerpc/include/uapi/asm/msgbuf.h b/arch/powerpc/include/uapi/asm/msgbuf.h index dd76743c7537..65beb0942500 100644 --- a/arch/powerpc/include/uapi/asm/msgbuf.h +++ b/arch/powerpc/include/uapi/asm/msgbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_POWERPC_MSGBUF_H #define _ASM_POWERPC_MSGBUF_H diff --git a/arch/powerpc/include/uapi/asm/perf_regs.h b/arch/powerpc/include/uapi/asm/perf_regs.h index 6a93209748a1..9e52c86ccbd3 100644 --- a/arch/powerpc/include/uapi/asm/perf_regs.h +++ b/arch/powerpc/include/uapi/asm/perf_regs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_POWERPC_PERF_REGS_H #define _UAPI_ASM_POWERPC_PERF_REGS_H diff --git a/arch/powerpc/include/uapi/asm/posix_types.h b/arch/powerpc/include/uapi/asm/posix_types.h index 2958c5b97b2d..f698400e4bb0 100644 --- a/arch/powerpc/include/uapi/asm/posix_types.h +++ b/arch/powerpc/include/uapi/asm/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_POWERPC_POSIX_TYPES_H #define _ASM_POWERPC_POSIX_TYPES_H diff --git a/arch/powerpc/include/uapi/asm/setup.h b/arch/powerpc/include/uapi/asm/setup.h index ae3fb68cb28e..c54940b09d06 100644 --- a/arch/powerpc/include/uapi/asm/setup.h +++ b/arch/powerpc/include/uapi/asm/setup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_POWERPC_SETUP_H #define _UAPI_ASM_POWERPC_SETUP_H diff --git a/arch/powerpc/include/uapi/asm/signal.h b/arch/powerpc/include/uapi/asm/signal.h index 6c69ee94fd8d..85b0a7aa43e7 100644 --- a/arch/powerpc/include/uapi/asm/signal.h +++ b/arch/powerpc/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_POWERPC_SIGNAL_H #define _UAPI_ASM_POWERPC_SIGNAL_H diff --git a/arch/powerpc/include/uapi/asm/tm.h b/arch/powerpc/include/uapi/asm/tm.h index 5047659815a5..e1bf0e2fac43 100644 --- a/arch/powerpc/include/uapi/asm/tm.h +++ b/arch/powerpc/include/uapi/asm/tm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_POWERPC_TM_H #define _ASM_POWERPC_TM_H diff --git a/arch/powerpc/include/uapi/asm/ucontext.h b/arch/powerpc/include/uapi/asm/ucontext.h index d9a4ddf0cc86..6f14a96d4985 100644 --- a/arch/powerpc/include/uapi/asm/ucontext.h +++ b/arch/powerpc/include/uapi/asm/ucontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_POWERPC_UCONTEXT_H #define _ASM_POWERPC_UCONTEXT_H diff --git a/arch/s390/include/uapi/asm/auxvec.h b/arch/s390/include/uapi/asm/auxvec.h index c53e08442255..a056c4637ffc 100644 --- a/arch/s390/include/uapi/asm/auxvec.h +++ b/arch/s390/include/uapi/asm/auxvec.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASMS390_AUXVEC_H #define __ASMS390_AUXVEC_H diff --git a/arch/s390/include/uapi/asm/bitsperlong.h b/arch/s390/include/uapi/asm/bitsperlong.h index 6b235aea9c66..cceaf47b021a 100644 --- a/arch/s390/include/uapi/asm/bitsperlong.h +++ b/arch/s390/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_S390_BITSPERLONG_H #define __ASM_S390_BITSPERLONG_H diff --git a/arch/s390/include/uapi/asm/byteorder.h b/arch/s390/include/uapi/asm/byteorder.h index a332e59e26fc..1442b57dd91b 100644 --- a/arch/s390/include/uapi/asm/byteorder.h +++ b/arch/s390/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _S390_BYTEORDER_H #define _S390_BYTEORDER_H diff --git a/arch/s390/include/uapi/asm/chpid.h b/arch/s390/include/uapi/asm/chpid.h index 6b4fb29cc197..2ae2ed8c0963 100644 --- a/arch/s390/include/uapi/asm/chpid.h +++ b/arch/s390/include/uapi/asm/chpid.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright IBM Corp. 2007, 2012 * Author(s): Peter Oberparleiter diff --git a/arch/s390/include/uapi/asm/chsc.h b/arch/s390/include/uapi/asm/chsc.h index 65dc694725a8..dc329aa03f76 100644 --- a/arch/s390/include/uapi/asm/chsc.h +++ b/arch/s390/include/uapi/asm/chsc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * ioctl interface for /dev/chsc * diff --git a/arch/s390/include/uapi/asm/clp.h b/arch/s390/include/uapi/asm/clp.h index ab72d9d24373..b36d9e9cdde6 100644 --- a/arch/s390/include/uapi/asm/clp.h +++ b/arch/s390/include/uapi/asm/clp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * ioctl interface for /dev/clp * diff --git a/arch/s390/include/uapi/asm/cmb.h b/arch/s390/include/uapi/asm/cmb.h index 0c086d00d89e..ecbe94941403 100644 --- a/arch/s390/include/uapi/asm/cmb.h +++ b/arch/s390/include/uapi/asm/cmb.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPIS390_CMB_H #define _UAPIS390_CMB_H diff --git a/arch/s390/include/uapi/asm/dasd.h b/arch/s390/include/uapi/asm/dasd.h index ab5797cdc1b7..451c601406b6 100644 --- a/arch/s390/include/uapi/asm/dasd.h +++ b/arch/s390/include/uapi/asm/dasd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Author(s)......: Holger Smolinski * Bugreports.to..: diff --git a/arch/s390/include/uapi/asm/debug.h b/arch/s390/include/uapi/asm/debug.h index c59fc79125f2..c7c564d9aea4 100644 --- a/arch/s390/include/uapi/asm/debug.h +++ b/arch/s390/include/uapi/asm/debug.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * S/390 debug facility * diff --git a/arch/s390/include/uapi/asm/guarded_storage.h b/arch/s390/include/uapi/asm/guarded_storage.h index 852850e8e17e..666af1c33b59 100644 --- a/arch/s390/include/uapi/asm/guarded_storage.h +++ b/arch/s390/include/uapi/asm/guarded_storage.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _GUARDED_STORAGE_H #define _GUARDED_STORAGE_H diff --git a/arch/s390/include/uapi/asm/hypfs.h b/arch/s390/include/uapi/asm/hypfs.h index b3fe12d8dd87..fe6174e142cf 100644 --- a/arch/s390/include/uapi/asm/hypfs.h +++ b/arch/s390/include/uapi/asm/hypfs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Structures for hypfs interface * diff --git a/arch/s390/include/uapi/asm/ioctls.h b/arch/s390/include/uapi/asm/ioctls.h index 960a4c1ebdf1..342a3284e69a 100644 --- a/arch/s390/include/uapi/asm/ioctls.h +++ b/arch/s390/include/uapi/asm/ioctls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ARCH_S390_IOCTLS_H__ #define __ARCH_S390_IOCTLS_H__ diff --git a/arch/s390/include/uapi/asm/ipcbuf.h b/arch/s390/include/uapi/asm/ipcbuf.h index 37f293d12c8f..5b1c4f47c656 100644 --- a/arch/s390/include/uapi/asm/ipcbuf.h +++ b/arch/s390/include/uapi/asm/ipcbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __S390_IPCBUF_H__ #define __S390_IPCBUF_H__ diff --git a/arch/s390/include/uapi/asm/monwriter.h b/arch/s390/include/uapi/asm/monwriter.h index f845c8e2f861..03d172f314a3 100644 --- a/arch/s390/include/uapi/asm/monwriter.h +++ b/arch/s390/include/uapi/asm/monwriter.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright IBM Corp. 2006 * Character device driver for writing z/VM APPLDATA monitor records diff --git a/arch/s390/include/uapi/asm/msgbuf.h b/arch/s390/include/uapi/asm/msgbuf.h index 1bbdee927924..604f847cd68c 100644 --- a/arch/s390/include/uapi/asm/msgbuf.h +++ b/arch/s390/include/uapi/asm/msgbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _S390_MSGBUF_H #define _S390_MSGBUF_H diff --git a/arch/s390/include/uapi/asm/pkey.h b/arch/s390/include/uapi/asm/pkey.h index e6c04faf8a6c..6f84a53c3270 100644 --- a/arch/s390/include/uapi/asm/pkey.h +++ b/arch/s390/include/uapi/asm/pkey.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Userspace interface to the pkey device driver * diff --git a/arch/s390/include/uapi/asm/posix_types.h b/arch/s390/include/uapi/asm/posix_types.h index bf2a2ad2f800..2a3fc638414b 100644 --- a/arch/s390/include/uapi/asm/posix_types.h +++ b/arch/s390/include/uapi/asm/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * S390 version * diff --git a/arch/s390/include/uapi/asm/ptrace.h b/arch/s390/include/uapi/asm/ptrace.h index 77630c74f13b..0d23c8ff2900 100644 --- a/arch/s390/include/uapi/asm/ptrace.h +++ b/arch/s390/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * S390 version * Copyright IBM Corp. 1999, 2000 diff --git a/arch/s390/include/uapi/asm/qeth.h b/arch/s390/include/uapi/asm/qeth.h index 3a896cf52589..fac9995dfe33 100644 --- a/arch/s390/include/uapi/asm/qeth.h +++ b/arch/s390/include/uapi/asm/qeth.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * ioctl definitions for qeth driver * diff --git a/arch/s390/include/uapi/asm/schid.h b/arch/s390/include/uapi/asm/schid.h index 32f3ab2a8200..58fca6f48410 100644 --- a/arch/s390/include/uapi/asm/schid.h +++ b/arch/s390/include/uapi/asm/schid.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPIASM_SCHID_H #define _UAPIASM_SCHID_H diff --git a/arch/s390/include/uapi/asm/sclp_ctl.h b/arch/s390/include/uapi/asm/sclp_ctl.h index f2818613ee41..e4e8c4dcd126 100644 --- a/arch/s390/include/uapi/asm/sclp_ctl.h +++ b/arch/s390/include/uapi/asm/sclp_ctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * IOCTL interface for SCLP * diff --git a/arch/s390/include/uapi/asm/sembuf.h b/arch/s390/include/uapi/asm/sembuf.h index 32626b0cac4b..3e917697b668 100644 --- a/arch/s390/include/uapi/asm/sembuf.h +++ b/arch/s390/include/uapi/asm/sembuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _S390_SEMBUF_H #define _S390_SEMBUF_H diff --git a/arch/s390/include/uapi/asm/setup.h b/arch/s390/include/uapi/asm/setup.h index 5a637e3e385e..1f8803a31079 100644 --- a/arch/s390/include/uapi/asm/setup.h +++ b/arch/s390/include/uapi/asm/setup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * S390 version * Copyright IBM Corp. 1999, 2010 diff --git a/arch/s390/include/uapi/asm/shmbuf.h b/arch/s390/include/uapi/asm/shmbuf.h index eed2e280ce37..9cdce8d7ce60 100644 --- a/arch/s390/include/uapi/asm/shmbuf.h +++ b/arch/s390/include/uapi/asm/shmbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _S390_SHMBUF_H #define _S390_SHMBUF_H diff --git a/arch/s390/include/uapi/asm/sie.h b/arch/s390/include/uapi/asm/sie.h index 3ac634368939..6ca1e68d7103 100644 --- a/arch/s390/include/uapi/asm/sie.h +++ b/arch/s390/include/uapi/asm/sie.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_S390_SIE_H #define _UAPI_ASM_S390_SIE_H diff --git a/arch/s390/include/uapi/asm/sigcontext.h b/arch/s390/include/uapi/asm/sigcontext.h index 5f0b8d7ddb0b..8b35033334c4 100644 --- a/arch/s390/include/uapi/asm/sigcontext.h +++ b/arch/s390/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * S390 version * Copyright IBM Corp. 1999, 2000 diff --git a/arch/s390/include/uapi/asm/siginfo.h b/arch/s390/include/uapi/asm/siginfo.h index 91fd3e4b70ce..6984820f2f1c 100644 --- a/arch/s390/include/uapi/asm/siginfo.h +++ b/arch/s390/include/uapi/asm/siginfo.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * S390 version * diff --git a/arch/s390/include/uapi/asm/signal.h b/arch/s390/include/uapi/asm/signal.h index 2f43cfbf5f1a..c57f9d28d894 100644 --- a/arch/s390/include/uapi/asm/signal.h +++ b/arch/s390/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * S390 version * diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h index a56916c83565..3510c0fd06f4 100644 --- a/arch/s390/include/uapi/asm/socket.h +++ b/arch/s390/include/uapi/asm/socket.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * S390 version * diff --git a/arch/s390/include/uapi/asm/stat.h b/arch/s390/include/uapi/asm/stat.h index b4ca97d91466..ac253d23606b 100644 --- a/arch/s390/include/uapi/asm/stat.h +++ b/arch/s390/include/uapi/asm/stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * S390 version * diff --git a/arch/s390/include/uapi/asm/statfs.h b/arch/s390/include/uapi/asm/statfs.h index 471eb09184d4..72604f7792c3 100644 --- a/arch/s390/include/uapi/asm/statfs.h +++ b/arch/s390/include/uapi/asm/statfs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * S390 version * diff --git a/arch/s390/include/uapi/asm/tape390.h b/arch/s390/include/uapi/asm/tape390.h index b2bc4bab7929..90266c696486 100644 --- a/arch/s390/include/uapi/asm/tape390.h +++ b/arch/s390/include/uapi/asm/tape390.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /************************************************************************* * * enables user programs to display messages and control encryption diff --git a/arch/s390/include/uapi/asm/termios.h b/arch/s390/include/uapi/asm/termios.h index 554f973db1e6..54223169c806 100644 --- a/arch/s390/include/uapi/asm/termios.h +++ b/arch/s390/include/uapi/asm/termios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * S390 version * diff --git a/arch/s390/include/uapi/asm/types.h b/arch/s390/include/uapi/asm/types.h index 3c3951e3415b..da034c606314 100644 --- a/arch/s390/include/uapi/asm/types.h +++ b/arch/s390/include/uapi/asm/types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * S390 version * diff --git a/arch/s390/include/uapi/asm/ucontext.h b/arch/s390/include/uapi/asm/ucontext.h index 64a69aa5dde0..c95f42e85337 100644 --- a/arch/s390/include/uapi/asm/ucontext.h +++ b/arch/s390/include/uapi/asm/ucontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * S390 version * diff --git a/arch/s390/include/uapi/asm/unistd.h b/arch/s390/include/uapi/asm/unistd.h index ea42290e7d51..b52bce8ee941 100644 --- a/arch/s390/include/uapi/asm/unistd.h +++ b/arch/s390/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * S390 version * diff --git a/arch/s390/include/uapi/asm/vtoc.h b/arch/s390/include/uapi/asm/vtoc.h index 221419de275e..50c1d7b9e844 100644 --- a/arch/s390/include/uapi/asm/vtoc.h +++ b/arch/s390/include/uapi/asm/vtoc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file contains volume label definitions for DASD devices. * diff --git a/arch/score/include/uapi/asm/bitsperlong.h b/arch/score/include/uapi/asm/bitsperlong.h index 86ff337aa459..df48f2717da2 100644 --- a/arch/score/include/uapi/asm/bitsperlong.h +++ b/arch/score/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_BITSPERLONG_H #define _ASM_SCORE_BITSPERLONG_H diff --git a/arch/score/include/uapi/asm/byteorder.h b/arch/score/include/uapi/asm/byteorder.h index 88cbebc79212..a5247ea66c03 100644 --- a/arch/score/include/uapi/asm/byteorder.h +++ b/arch/score/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_BYTEORDER_H #define _ASM_SCORE_BYTEORDER_H diff --git a/arch/score/include/uapi/asm/errno.h b/arch/score/include/uapi/asm/errno.h index 29ff39d5ab47..1b914865714f 100644 --- a/arch/score/include/uapi/asm/errno.h +++ b/arch/score/include/uapi/asm/errno.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_ERRNO_H #define _ASM_SCORE_ERRNO_H diff --git a/arch/score/include/uapi/asm/fcntl.h b/arch/score/include/uapi/asm/fcntl.h index 03968a3103a4..9c5053b87c66 100644 --- a/arch/score/include/uapi/asm/fcntl.h +++ b/arch/score/include/uapi/asm/fcntl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_FCNTL_H #define _ASM_SCORE_FCNTL_H diff --git a/arch/score/include/uapi/asm/ioctl.h b/arch/score/include/uapi/asm/ioctl.h index a351d2194bfd..d6cb6dc33d5f 100644 --- a/arch/score/include/uapi/asm/ioctl.h +++ b/arch/score/include/uapi/asm/ioctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_IOCTL_H #define _ASM_SCORE_IOCTL_H diff --git a/arch/score/include/uapi/asm/ioctls.h b/arch/score/include/uapi/asm/ioctls.h index ed01d2b9aeab..b93b011f02aa 100644 --- a/arch/score/include/uapi/asm/ioctls.h +++ b/arch/score/include/uapi/asm/ioctls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_IOCTLS_H #define _ASM_SCORE_IOCTLS_H diff --git a/arch/score/include/uapi/asm/ipcbuf.h b/arch/score/include/uapi/asm/ipcbuf.h index e082ceff1818..195ee525308d 100644 --- a/arch/score/include/uapi/asm/ipcbuf.h +++ b/arch/score/include/uapi/asm/ipcbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_IPCBUF_H #define _ASM_SCORE_IPCBUF_H diff --git a/arch/score/include/uapi/asm/kvm_para.h b/arch/score/include/uapi/asm/kvm_para.h index 14fab8f0b957..baacc4996d18 100644 --- a/arch/score/include/uapi/asm/kvm_para.h +++ b/arch/score/include/uapi/asm/kvm_para.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/score/include/uapi/asm/mman.h b/arch/score/include/uapi/asm/mman.h index 84d85ddfed8d..b22b83809432 100644 --- a/arch/score/include/uapi/asm/mman.h +++ b/arch/score/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_MMAN_H #define _ASM_SCORE_MMAN_H diff --git a/arch/score/include/uapi/asm/msgbuf.h b/arch/score/include/uapi/asm/msgbuf.h index 7506721e29fa..b05a238756ab 100644 --- a/arch/score/include/uapi/asm/msgbuf.h +++ b/arch/score/include/uapi/asm/msgbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_MSGBUF_H #define _ASM_SCORE_MSGBUF_H diff --git a/arch/score/include/uapi/asm/param.h b/arch/score/include/uapi/asm/param.h index 916b8690b6aa..ce09e2632681 100644 --- a/arch/score/include/uapi/asm/param.h +++ b/arch/score/include/uapi/asm/param.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_PARAM_H #define _ASM_SCORE_PARAM_H diff --git a/arch/score/include/uapi/asm/poll.h b/arch/score/include/uapi/asm/poll.h index 18532db02861..c636b85843cd 100644 --- a/arch/score/include/uapi/asm/poll.h +++ b/arch/score/include/uapi/asm/poll.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_POLL_H #define _ASM_SCORE_POLL_H diff --git a/arch/score/include/uapi/asm/posix_types.h b/arch/score/include/uapi/asm/posix_types.h index b88acf80048a..63200d56a4a9 100644 --- a/arch/score/include/uapi/asm/posix_types.h +++ b/arch/score/include/uapi/asm/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_POSIX_TYPES_H #define _ASM_SCORE_POSIX_TYPES_H diff --git a/arch/score/include/uapi/asm/ptrace.h b/arch/score/include/uapi/asm/ptrace.h index 5c5e794058be..e8bd4923f96e 100644 --- a/arch/score/include/uapi/asm/ptrace.h +++ b/arch/score/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_SCORE_PTRACE_H #define _UAPI_ASM_SCORE_PTRACE_H diff --git a/arch/score/include/uapi/asm/resource.h b/arch/score/include/uapi/asm/resource.h index 9ce22bc7b475..df3fb9c942c4 100644 --- a/arch/score/include/uapi/asm/resource.h +++ b/arch/score/include/uapi/asm/resource.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_RESOURCE_H #define _ASM_SCORE_RESOURCE_H diff --git a/arch/score/include/uapi/asm/sembuf.h b/arch/score/include/uapi/asm/sembuf.h index dae5e835ce9e..c16e7a94725d 100644 --- a/arch/score/include/uapi/asm/sembuf.h +++ b/arch/score/include/uapi/asm/sembuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_SEMBUF_H #define _ASM_SCORE_SEMBUF_H diff --git a/arch/score/include/uapi/asm/setup.h b/arch/score/include/uapi/asm/setup.h index ab9dbdb59bba..dee58323847e 100644 --- a/arch/score/include/uapi/asm/setup.h +++ b/arch/score/include/uapi/asm/setup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_SCORE_SETUP_H #define _UAPI_ASM_SCORE_SETUP_H diff --git a/arch/score/include/uapi/asm/shmbuf.h b/arch/score/include/uapi/asm/shmbuf.h index c85b2429ba21..f38acfe733cd 100644 --- a/arch/score/include/uapi/asm/shmbuf.h +++ b/arch/score/include/uapi/asm/shmbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_SHMBUF_H #define _ASM_SCORE_SHMBUF_H diff --git a/arch/score/include/uapi/asm/sigcontext.h b/arch/score/include/uapi/asm/sigcontext.h index 5ffda39ddb90..2b0cd93a71f6 100644 --- a/arch/score/include/uapi/asm/sigcontext.h +++ b/arch/score/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_SIGCONTEXT_H #define _ASM_SCORE_SIGCONTEXT_H diff --git a/arch/score/include/uapi/asm/signal.h b/arch/score/include/uapi/asm/signal.h index 2605bc06b64f..7fb694972302 100644 --- a/arch/score/include/uapi/asm/signal.h +++ b/arch/score/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_SIGNAL_H #define _ASM_SCORE_SIGNAL_H diff --git a/arch/score/include/uapi/asm/socket.h b/arch/score/include/uapi/asm/socket.h index 612a70e385ba..f76ba1f72354 100644 --- a/arch/score/include/uapi/asm/socket.h +++ b/arch/score/include/uapi/asm/socket.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_SOCKET_H #define _ASM_SCORE_SOCKET_H diff --git a/arch/score/include/uapi/asm/sockios.h b/arch/score/include/uapi/asm/sockios.h index ba8256480189..d0af8ce4373b 100644 --- a/arch/score/include/uapi/asm/sockios.h +++ b/arch/score/include/uapi/asm/sockios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_SOCKIOS_H #define _ASM_SCORE_SOCKIOS_H diff --git a/arch/score/include/uapi/asm/stat.h b/arch/score/include/uapi/asm/stat.h index 5037055500a2..669b69f764df 100644 --- a/arch/score/include/uapi/asm/stat.h +++ b/arch/score/include/uapi/asm/stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_STAT_H #define _ASM_SCORE_STAT_H diff --git a/arch/score/include/uapi/asm/statfs.h b/arch/score/include/uapi/asm/statfs.h index 36e41004e996..bb92b3e5525d 100644 --- a/arch/score/include/uapi/asm/statfs.h +++ b/arch/score/include/uapi/asm/statfs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_STATFS_H #define _ASM_SCORE_STATFS_H diff --git a/arch/score/include/uapi/asm/swab.h b/arch/score/include/uapi/asm/swab.h index fadc3cc6d8a2..52b0927282b1 100644 --- a/arch/score/include/uapi/asm/swab.h +++ b/arch/score/include/uapi/asm/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_SWAB_H #define _ASM_SCORE_SWAB_H diff --git a/arch/score/include/uapi/asm/termbits.h b/arch/score/include/uapi/asm/termbits.h index 9a95c1412437..4a6f5511cd56 100644 --- a/arch/score/include/uapi/asm/termbits.h +++ b/arch/score/include/uapi/asm/termbits.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_TERMBITS_H #define _ASM_SCORE_TERMBITS_H diff --git a/arch/score/include/uapi/asm/termios.h b/arch/score/include/uapi/asm/termios.h index 40984e811ad6..fabb598ecfa3 100644 --- a/arch/score/include/uapi/asm/termios.h +++ b/arch/score/include/uapi/asm/termios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_TERMIOS_H #define _ASM_SCORE_TERMIOS_H diff --git a/arch/score/include/uapi/asm/types.h b/arch/score/include/uapi/asm/types.h index 2140032778ee..8515287f412a 100644 --- a/arch/score/include/uapi/asm/types.h +++ b/arch/score/include/uapi/asm/types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_TYPES_H #define _ASM_SCORE_TYPES_H diff --git a/arch/score/include/uapi/asm/unistd.h b/arch/score/include/uapi/asm/unistd.h index d4008c339e89..04da47bd3d46 100644 --- a/arch/score/include/uapi/asm/unistd.h +++ b/arch/score/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #define __ARCH_HAVE_MMU #define __ARCH_WANT_RENAMEAT diff --git a/arch/sh/include/uapi/asm/auxvec.h b/arch/sh/include/uapi/asm/auxvec.h index 8bcc51af9367..8eb47ede7193 100644 --- a/arch/sh/include/uapi/asm/auxvec.h +++ b/arch/sh/include/uapi/asm/auxvec.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_SH_AUXVEC_H #define __ASM_SH_AUXVEC_H diff --git a/arch/sh/include/uapi/asm/byteorder.h b/arch/sh/include/uapi/asm/byteorder.h index db2f5d7cb17d..e27d6da3212c 100644 --- a/arch/sh/include/uapi/asm/byteorder.h +++ b/arch/sh/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_SH_BYTEORDER_H #define __ASM_SH_BYTEORDER_H diff --git a/arch/sh/include/uapi/asm/cachectl.h b/arch/sh/include/uapi/asm/cachectl.h index 6ffb4b7a212e..79c5663251a5 100644 --- a/arch/sh/include/uapi/asm/cachectl.h +++ b/arch/sh/include/uapi/asm/cachectl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _SH_CACHECTL_H #define _SH_CACHECTL_H diff --git a/arch/sh/include/uapi/asm/cpu-features.h b/arch/sh/include/uapi/asm/cpu-features.h index 2f1bc851042a..6de5f65194e6 100644 --- a/arch/sh/include/uapi/asm/cpu-features.h +++ b/arch/sh/include/uapi/asm/cpu-features.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_SH_CPU_FEATURES_H #define __ASM_SH_CPU_FEATURES_H diff --git a/arch/sh/include/uapi/asm/hw_breakpoint.h b/arch/sh/include/uapi/asm/hw_breakpoint.h index ae5704fa77ad..043dd4b92026 100644 --- a/arch/sh/include/uapi/asm/hw_breakpoint.h +++ b/arch/sh/include/uapi/asm/hw_breakpoint.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * There isn't anything here anymore, but the file must not be empty or patch * will delete it. diff --git a/arch/sh/include/uapi/asm/ioctls.h b/arch/sh/include/uapi/asm/ioctls.h index 787bac9f67da..cc62f6f98103 100644 --- a/arch/sh/include/uapi/asm/ioctls.h +++ b/arch/sh/include/uapi/asm/ioctls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_SH_IOCTLS_H #define __ASM_SH_IOCTLS_H diff --git a/arch/sh/include/uapi/asm/posix_types.h b/arch/sh/include/uapi/asm/posix_types.h index dc55e5adfe1e..2644fdd444e6 100644 --- a/arch/sh/include/uapi/asm/posix_types.h +++ b/arch/sh/include/uapi/asm/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __KERNEL__ # ifdef __SH5__ # include diff --git a/arch/sh/include/uapi/asm/posix_types_32.h b/arch/sh/include/uapi/asm/posix_types_32.h index ba0bdc423b07..ea0f51d1ac55 100644 --- a/arch/sh/include/uapi/asm/posix_types_32.h +++ b/arch/sh/include/uapi/asm/posix_types_32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_SH_POSIX_TYPES_32_H #define __ASM_SH_POSIX_TYPES_32_H diff --git a/arch/sh/include/uapi/asm/posix_types_64.h b/arch/sh/include/uapi/asm/posix_types_64.h index 244f7e950e17..3a9128d4aee3 100644 --- a/arch/sh/include/uapi/asm/posix_types_64.h +++ b/arch/sh/include/uapi/asm/posix_types_64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_SH_POSIX_TYPES_64_H #define __ASM_SH_POSIX_TYPES_64_H diff --git a/arch/sh/include/uapi/asm/ptrace.h b/arch/sh/include/uapi/asm/ptrace.h index 8b8c5aca9c28..4ec9c2b65fdb 100644 --- a/arch/sh/include/uapi/asm/ptrace.h +++ b/arch/sh/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 1999, 2000 Niibe Yutaka */ diff --git a/arch/sh/include/uapi/asm/ptrace_32.h b/arch/sh/include/uapi/asm/ptrace_32.h index 926e0cefc2bb..dc8a26015018 100644 --- a/arch/sh/include/uapi/asm/ptrace_32.h +++ b/arch/sh/include/uapi/asm/ptrace_32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__ASM_SH_PTRACE_32_H #define _UAPI__ASM_SH_PTRACE_32_H diff --git a/arch/sh/include/uapi/asm/ptrace_64.h b/arch/sh/include/uapi/asm/ptrace_64.h index 0e52ee83e946..a6f84eba5277 100644 --- a/arch/sh/include/uapi/asm/ptrace_64.h +++ b/arch/sh/include/uapi/asm/ptrace_64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__ASM_SH_PTRACE_64_H #define _UAPI__ASM_SH_PTRACE_64_H diff --git a/arch/sh/include/uapi/asm/sigcontext.h b/arch/sh/include/uapi/asm/sigcontext.h index faa5d0833412..d2b7e4f033c0 100644 --- a/arch/sh/include/uapi/asm/sigcontext.h +++ b/arch/sh/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_SH_SIGCONTEXT_H #define __ASM_SH_SIGCONTEXT_H diff --git a/arch/sh/include/uapi/asm/signal.h b/arch/sh/include/uapi/asm/signal.h index cb96d02f55a4..97299daddef5 100644 --- a/arch/sh/include/uapi/asm/signal.h +++ b/arch/sh/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_SH_SIGNAL_H #define __ASM_SH_SIGNAL_H diff --git a/arch/sh/include/uapi/asm/sockios.h b/arch/sh/include/uapi/asm/sockios.h index cf8b96b1f9ab..17313d2c3527 100644 --- a/arch/sh/include/uapi/asm/sockios.h +++ b/arch/sh/include/uapi/asm/sockios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_SH_SOCKIOS_H #define __ASM_SH_SOCKIOS_H diff --git a/arch/sh/include/uapi/asm/stat.h b/arch/sh/include/uapi/asm/stat.h index e1810cc6e3da..659b87c7c25a 100644 --- a/arch/sh/include/uapi/asm/stat.h +++ b/arch/sh/include/uapi/asm/stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_SH_STAT_H #define __ASM_SH_STAT_H diff --git a/arch/sh/include/uapi/asm/swab.h b/arch/sh/include/uapi/asm/swab.h index 1cd09767a7a3..f0b02152745c 100644 --- a/arch/sh/include/uapi/asm/swab.h +++ b/arch/sh/include/uapi/asm/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_SH_SWAB_H #define __ASM_SH_SWAB_H diff --git a/arch/sh/include/uapi/asm/unistd.h b/arch/sh/include/uapi/asm/unistd.h index eeef88dd53ce..9e0b4e5e6da2 100644 --- a/arch/sh/include/uapi/asm/unistd.h +++ b/arch/sh/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __KERNEL__ # ifdef __SH5__ # include diff --git a/arch/sh/include/uapi/asm/unistd_32.h b/arch/sh/include/uapi/asm/unistd_32.h index c801bde9e6f5..58f04cf3d1d9 100644 --- a/arch/sh/include/uapi/asm/unistd_32.h +++ b/arch/sh/include/uapi/asm/unistd_32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_SH_UNISTD_32_H #define __ASM_SH_UNISTD_32_H diff --git a/arch/sparc/include/uapi/asm/apc.h b/arch/sparc/include/uapi/asm/apc.h index 24e9a7d4d97e..aeb369b87fcd 100644 --- a/arch/sparc/include/uapi/asm/apc.h +++ b/arch/sparc/include/uapi/asm/apc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* apc - Driver definitions for power management functions * of Aurora Personality Chip (APC) on SPARCstation-4/5 and * derivatives diff --git a/arch/sparc/include/uapi/asm/asi.h b/arch/sparc/include/uapi/asm/asi.h index 7ad7203deaec..d371b269571a 100644 --- a/arch/sparc/include/uapi/asm/asi.h +++ b/arch/sparc/include/uapi/asm/asi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _SPARC_ASI_H #define _SPARC_ASI_H diff --git a/arch/sparc/include/uapi/asm/bitsperlong.h b/arch/sparc/include/uapi/asm/bitsperlong.h index 40dcaa3aaa56..cd9a432278d2 100644 --- a/arch/sparc/include/uapi/asm/bitsperlong.h +++ b/arch/sparc/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_ALPHA_BITSPERLONG_H #define __ASM_ALPHA_BITSPERLONG_H diff --git a/arch/sparc/include/uapi/asm/byteorder.h b/arch/sparc/include/uapi/asm/byteorder.h index ccc1b6b7de6c..216b8e59372f 100644 --- a/arch/sparc/include/uapi/asm/byteorder.h +++ b/arch/sparc/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _SPARC_BYTEORDER_H #define _SPARC_BYTEORDER_H diff --git a/arch/sparc/include/uapi/asm/display7seg.h b/arch/sparc/include/uapi/asm/display7seg.h index 86d4a901df24..7e9fef0c6efe 100644 --- a/arch/sparc/include/uapi/asm/display7seg.h +++ b/arch/sparc/include/uapi/asm/display7seg.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * * display7seg - Driver interface for the 7-segment display diff --git a/arch/sparc/include/uapi/asm/envctrl.h b/arch/sparc/include/uapi/asm/envctrl.h index 624fa7e2da8e..cf8aa0a14f40 100644 --- a/arch/sparc/include/uapi/asm/envctrl.h +++ b/arch/sparc/include/uapi/asm/envctrl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * * envctrl.h: Definitions for access to the i2c environment diff --git a/arch/sparc/include/uapi/asm/errno.h b/arch/sparc/include/uapi/asm/errno.h index 20423e172853..81a732b902ee 100644 --- a/arch/sparc/include/uapi/asm/errno.h +++ b/arch/sparc/include/uapi/asm/errno.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _SPARC_ERRNO_H #define _SPARC_ERRNO_H diff --git a/arch/sparc/include/uapi/asm/fbio.h b/arch/sparc/include/uapi/asm/fbio.h index d6cea07afb61..0dafe2c1eab7 100644 --- a/arch/sparc/include/uapi/asm/fbio.h +++ b/arch/sparc/include/uapi/asm/fbio.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__LINUX_FBIO_H #define _UAPI__LINUX_FBIO_H diff --git a/arch/sparc/include/uapi/asm/fcntl.h b/arch/sparc/include/uapi/asm/fcntl.h index 7e8ace5bf760..67dae75e5274 100644 --- a/arch/sparc/include/uapi/asm/fcntl.h +++ b/arch/sparc/include/uapi/asm/fcntl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _SPARC_FCNTL_H #define _SPARC_FCNTL_H diff --git a/arch/sparc/include/uapi/asm/ioctl.h b/arch/sparc/include/uapi/asm/ioctl.h index 7d6bd51321b9..96c598fe746e 100644 --- a/arch/sparc/include/uapi/asm/ioctl.h +++ b/arch/sparc/include/uapi/asm/ioctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _SPARC_IOCTL_H #define _SPARC_IOCTL_H diff --git a/arch/sparc/include/uapi/asm/ioctls.h b/arch/sparc/include/uapi/asm/ioctls.h index f5df72b93bb2..2df52711e170 100644 --- a/arch/sparc/include/uapi/asm/ioctls.h +++ b/arch/sparc/include/uapi/asm/ioctls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_SPARC_IOCTLS_H #define _UAPI_ASM_SPARC_IOCTLS_H diff --git a/arch/sparc/include/uapi/asm/ipcbuf.h b/arch/sparc/include/uapi/asm/ipcbuf.h index 66013b4fe10d..9d0d125500e2 100644 --- a/arch/sparc/include/uapi/asm/ipcbuf.h +++ b/arch/sparc/include/uapi/asm/ipcbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __SPARC_IPCBUF_H #define __SPARC_IPCBUF_H diff --git a/arch/sparc/include/uapi/asm/jsflash.h b/arch/sparc/include/uapi/asm/jsflash.h index 0717d9e39d2d..68c98a54281a 100644 --- a/arch/sparc/include/uapi/asm/jsflash.h +++ b/arch/sparc/include/uapi/asm/jsflash.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * jsflash.h: OS Flash SIMM support for JavaStations. * diff --git a/arch/sparc/include/uapi/asm/kvm_para.h b/arch/sparc/include/uapi/asm/kvm_para.h index 14fab8f0b957..baacc4996d18 100644 --- a/arch/sparc/include/uapi/asm/kvm_para.h +++ b/arch/sparc/include/uapi/asm/kvm_para.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/sparc/include/uapi/asm/mman.h b/arch/sparc/include/uapi/asm/mman.h index 9765896ecb2c..715a2c927e79 100644 --- a/arch/sparc/include/uapi/asm/mman.h +++ b/arch/sparc/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__SPARC_MMAN_H__ #define _UAPI__SPARC_MMAN_H__ diff --git a/arch/sparc/include/uapi/asm/msgbuf.h b/arch/sparc/include/uapi/asm/msgbuf.h index efc7cbe9788f..b601c4f4d956 100644 --- a/arch/sparc/include/uapi/asm/msgbuf.h +++ b/arch/sparc/include/uapi/asm/msgbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _SPARC_MSGBUF_H #define _SPARC_MSGBUF_H diff --git a/arch/sparc/include/uapi/asm/openpromio.h b/arch/sparc/include/uapi/asm/openpromio.h index 917fb8e9c633..8817f7d1a70c 100644 --- a/arch/sparc/include/uapi/asm/openpromio.h +++ b/arch/sparc/include/uapi/asm/openpromio.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _SPARC_OPENPROMIO_H #define _SPARC_OPENPROMIO_H diff --git a/arch/sparc/include/uapi/asm/param.h b/arch/sparc/include/uapi/asm/param.h index 0bc356bf8c50..057d7135e4d0 100644 --- a/arch/sparc/include/uapi/asm/param.h +++ b/arch/sparc/include/uapi/asm/param.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASMSPARC_PARAM_H #define _ASMSPARC_PARAM_H diff --git a/arch/sparc/include/uapi/asm/perfctr.h b/arch/sparc/include/uapi/asm/perfctr.h index 214feefa577c..316b837bcb8f 100644 --- a/arch/sparc/include/uapi/asm/perfctr.h +++ b/arch/sparc/include/uapi/asm/perfctr.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /*---------------------------------------- PERFORMANCE INSTRUMENTATION Guillaume Thouvenin 08/10/98 diff --git a/arch/sparc/include/uapi/asm/poll.h b/arch/sparc/include/uapi/asm/poll.h index 091d3ad2e830..72356c999125 100644 --- a/arch/sparc/include/uapi/asm/poll.h +++ b/arch/sparc/include/uapi/asm/poll.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __SPARC_POLL_H #define __SPARC_POLL_H diff --git a/arch/sparc/include/uapi/asm/posix_types.h b/arch/sparc/include/uapi/asm/posix_types.h index 156220ed99eb..fec499d6efb7 100644 --- a/arch/sparc/include/uapi/asm/posix_types.h +++ b/arch/sparc/include/uapi/asm/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is generally used by user-level software, so you need to * be a little careful about namespace pollution etc. Also, we cannot diff --git a/arch/sparc/include/uapi/asm/psr.h b/arch/sparc/include/uapi/asm/psr.h index 2f0ed856530b..e41f65f0aebd 100644 --- a/arch/sparc/include/uapi/asm/psr.h +++ b/arch/sparc/include/uapi/asm/psr.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * psr.h: This file holds the macros for masking off various parts of * the processor status register on the Sparc. This is valid diff --git a/arch/sparc/include/uapi/asm/psrcompat.h b/arch/sparc/include/uapi/asm/psrcompat.h index 44b6327dbbf5..1eaffbe0d1e2 100644 --- a/arch/sparc/include/uapi/asm/psrcompat.h +++ b/arch/sparc/include/uapi/asm/psrcompat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _SPARC64_PSRCOMPAT_H #define _SPARC64_PSRCOMPAT_H diff --git a/arch/sparc/include/uapi/asm/pstate.h b/arch/sparc/include/uapi/asm/pstate.h index cf832e14aa05..b6999c9e7e86 100644 --- a/arch/sparc/include/uapi/asm/pstate.h +++ b/arch/sparc/include/uapi/asm/pstate.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _SPARC64_PSTATE_H #define _SPARC64_PSTATE_H diff --git a/arch/sparc/include/uapi/asm/ptrace.h b/arch/sparc/include/uapi/asm/ptrace.h index 56fe4ea73feb..abe640037a55 100644 --- a/arch/sparc/include/uapi/asm/ptrace.h +++ b/arch/sparc/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__SPARC_PTRACE_H #define _UAPI__SPARC_PTRACE_H diff --git a/arch/sparc/include/uapi/asm/resource.h b/arch/sparc/include/uapi/asm/resource.h index fe163cafb4c7..cbe2de778838 100644 --- a/arch/sparc/include/uapi/asm/resource.h +++ b/arch/sparc/include/uapi/asm/resource.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * resource.h: Resource definitions. * diff --git a/arch/sparc/include/uapi/asm/sembuf.h b/arch/sparc/include/uapi/asm/sembuf.h index faee1be08d67..f49b0ffa0ab8 100644 --- a/arch/sparc/include/uapi/asm/sembuf.h +++ b/arch/sparc/include/uapi/asm/sembuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _SPARC_SEMBUF_H #define _SPARC_SEMBUF_H diff --git a/arch/sparc/include/uapi/asm/setup.h b/arch/sparc/include/uapi/asm/setup.h index 533768450872..3c208a4dd464 100644 --- a/arch/sparc/include/uapi/asm/setup.h +++ b/arch/sparc/include/uapi/asm/setup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Just a place holder. */ diff --git a/arch/sparc/include/uapi/asm/shmbuf.h b/arch/sparc/include/uapi/asm/shmbuf.h index 83a16055363f..286631db705c 100644 --- a/arch/sparc/include/uapi/asm/shmbuf.h +++ b/arch/sparc/include/uapi/asm/shmbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _SPARC_SHMBUF_H #define _SPARC_SHMBUF_H diff --git a/arch/sparc/include/uapi/asm/sigcontext.h b/arch/sparc/include/uapi/asm/sigcontext.h index ae5704fa77ad..043dd4b92026 100644 --- a/arch/sparc/include/uapi/asm/sigcontext.h +++ b/arch/sparc/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * There isn't anything here anymore, but the file must not be empty or patch * will delete it. diff --git a/arch/sparc/include/uapi/asm/siginfo.h b/arch/sparc/include/uapi/asm/siginfo.h index 157f46fe374f..896ce447d16a 100644 --- a/arch/sparc/include/uapi/asm/siginfo.h +++ b/arch/sparc/include/uapi/asm/siginfo.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__SPARC_SIGINFO_H #define _UAPI__SPARC_SIGINFO_H diff --git a/arch/sparc/include/uapi/asm/signal.h b/arch/sparc/include/uapi/asm/signal.h index f387400fcfdf..ff9505923b9a 100644 --- a/arch/sparc/include/uapi/asm/signal.h +++ b/arch/sparc/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__SPARC_SIGNAL_H #define _UAPI__SPARC_SIGNAL_H diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index b2f5c50d0947..d58520c2e6ff 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SOCKET_H #define _ASM_SOCKET_H diff --git a/arch/sparc/include/uapi/asm/sockios.h b/arch/sparc/include/uapi/asm/sockios.h index 990ea746486b..18a3ec14a847 100644 --- a/arch/sparc/include/uapi/asm/sockios.h +++ b/arch/sparc/include/uapi/asm/sockios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SPARC_SOCKIOS_H #define _ASM_SPARC_SOCKIOS_H diff --git a/arch/sparc/include/uapi/asm/stat.h b/arch/sparc/include/uapi/asm/stat.h index 2f0583a2c689..b6ec4eb217f7 100644 --- a/arch/sparc/include/uapi/asm/stat.h +++ b/arch/sparc/include/uapi/asm/stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __SPARC_STAT_H #define __SPARC_STAT_H diff --git a/arch/sparc/include/uapi/asm/statfs.h b/arch/sparc/include/uapi/asm/statfs.h index 55e607ad461d..20c8f5bd340e 100644 --- a/arch/sparc/include/uapi/asm/statfs.h +++ b/arch/sparc/include/uapi/asm/statfs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef ___ASM_SPARC_STATFS_H #define ___ASM_SPARC_STATFS_H diff --git a/arch/sparc/include/uapi/asm/swab.h b/arch/sparc/include/uapi/asm/swab.h index 4c7c12d69bea..6b1b3f1ad725 100644 --- a/arch/sparc/include/uapi/asm/swab.h +++ b/arch/sparc/include/uapi/asm/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _SPARC_SWAB_H #define _SPARC_SWAB_H diff --git a/arch/sparc/include/uapi/asm/termbits.h b/arch/sparc/include/uapi/asm/termbits.h index dd91642fcca7..ce5ad5d0f105 100644 --- a/arch/sparc/include/uapi/asm/termbits.h +++ b/arch/sparc/include/uapi/asm/termbits.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_SPARC_TERMBITS_H #define _UAPI_SPARC_TERMBITS_H diff --git a/arch/sparc/include/uapi/asm/termios.h b/arch/sparc/include/uapi/asm/termios.h index ea6f09e51e53..ee86f4093d83 100644 --- a/arch/sparc/include/uapi/asm/termios.h +++ b/arch/sparc/include/uapi/asm/termios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_SPARC_TERMIOS_H #define _UAPI_SPARC_TERMIOS_H diff --git a/arch/sparc/include/uapi/asm/traps.h b/arch/sparc/include/uapi/asm/traps.h index a4eceace6ccf..930db746f8bd 100644 --- a/arch/sparc/include/uapi/asm/traps.h +++ b/arch/sparc/include/uapi/asm/traps.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * traps.h: Format of entries for the Sparc trap table. * diff --git a/arch/sparc/include/uapi/asm/uctx.h b/arch/sparc/include/uapi/asm/uctx.h index dc937c75ffdd..13a13198e04f 100644 --- a/arch/sparc/include/uapi/asm/uctx.h +++ b/arch/sparc/include/uapi/asm/uctx.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * uctx.h: Sparc64 {set,get}context() register state layouts. * diff --git a/arch/sparc/include/uapi/asm/unistd.h b/arch/sparc/include/uapi/asm/unistd.h index ae77df75bffa..09acf0ddec10 100644 --- a/arch/sparc/include/uapi/asm/unistd.h +++ b/arch/sparc/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * System calls under the Sparc. * diff --git a/arch/sparc/include/uapi/asm/utrap.h b/arch/sparc/include/uapi/asm/utrap.h index b10e527c22d9..d890b7fc6e83 100644 --- a/arch/sparc/include/uapi/asm/utrap.h +++ b/arch/sparc/include/uapi/asm/utrap.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/asm/utrap.h * diff --git a/arch/sparc/include/uapi/asm/watchdog.h b/arch/sparc/include/uapi/asm/watchdog.h index 5baf2d3919cf..497ac19a9e4e 100644 --- a/arch/sparc/include/uapi/asm/watchdog.h +++ b/arch/sparc/include/uapi/asm/watchdog.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * * watchdog - Driver interface for the hardware watchdog timers diff --git a/arch/tile/include/uapi/asm/kvm_para.h b/arch/tile/include/uapi/asm/kvm_para.h index 14fab8f0b957..baacc4996d18 100644 --- a/arch/tile/include/uapi/asm/kvm_para.h +++ b/arch/tile/include/uapi/asm/kvm_para.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/tile/include/uapi/asm/stat.h b/arch/tile/include/uapi/asm/stat.h index c0db34d56be3..ea03de7d67aa 100644 --- a/arch/tile/include/uapi/asm/stat.h +++ b/arch/tile/include/uapi/asm/stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #if defined(__KERNEL__) && defined(CONFIG_COMPAT) #define __ARCH_WANT_STAT64 /* Used for compat_sys_stat64() etc. */ #endif diff --git a/arch/x86/include/uapi/asm/a.out.h b/arch/x86/include/uapi/asm/a.out.h index 4684f97a5bbd..094c49d8ea8e 100644 --- a/arch/x86/include/uapi/asm/a.out.h +++ b/arch/x86/include/uapi/asm/a.out.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_A_OUT_H #define _ASM_X86_A_OUT_H diff --git a/arch/x86/include/uapi/asm/auxvec.h b/arch/x86/include/uapi/asm/auxvec.h index 77203ac352de..580e3c567046 100644 --- a/arch/x86/include/uapi/asm/auxvec.h +++ b/arch/x86/include/uapi/asm/auxvec.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_AUXVEC_H #define _ASM_X86_AUXVEC_H /* diff --git a/arch/x86/include/uapi/asm/bitsperlong.h b/arch/x86/include/uapi/asm/bitsperlong.h index 217909b4d6f5..5d72c8458838 100644 --- a/arch/x86/include/uapi/asm/bitsperlong.h +++ b/arch/x86/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_X86_BITSPERLONG_H #define __ASM_X86_BITSPERLONG_H diff --git a/arch/x86/include/uapi/asm/boot.h b/arch/x86/include/uapi/asm/boot.h index 94292c4c8122..88ffc5aee087 100644 --- a/arch/x86/include/uapi/asm/boot.h +++ b/arch/x86/include/uapi/asm/boot.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_BOOT_H #define _UAPI_ASM_X86_BOOT_H diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index 66b8f93333d1..afdd5ae0fcc4 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_BOOTPARAM_H #define _ASM_X86_BOOTPARAM_H diff --git a/arch/x86/include/uapi/asm/debugreg.h b/arch/x86/include/uapi/asm/debugreg.h index 3c0874dd9861..d95d080b30e3 100644 --- a/arch/x86/include/uapi/asm/debugreg.h +++ b/arch/x86/include/uapi/asm/debugreg.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_DEBUGREG_H #define _UAPI_ASM_X86_DEBUGREG_H diff --git a/arch/x86/include/uapi/asm/e820.h b/arch/x86/include/uapi/asm/e820.h index 9dafe59cf6e2..2f491efe3a12 100644 --- a/arch/x86/include/uapi/asm/e820.h +++ b/arch/x86/include/uapi/asm/e820.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_E820_H #define _UAPI_ASM_X86_E820_H #define E820MAP 0x2d0 /* our map */ diff --git a/arch/x86/include/uapi/asm/hw_breakpoint.h b/arch/x86/include/uapi/asm/hw_breakpoint.h index 79a9626b5500..6789884c7701 100644 --- a/arch/x86/include/uapi/asm/hw_breakpoint.h +++ b/arch/x86/include/uapi/asm/hw_breakpoint.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* */ diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h index f65d12504e80..1a5bfead93b4 100644 --- a/arch/x86/include/uapi/asm/hyperv.h +++ b/arch/x86/include/uapi/asm/hyperv.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_HYPERV_H #define _ASM_X86_HYPERV_H diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index c2824d02ba37..f3a960488eae 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_KVM_H #define _ASM_X86_KVM_H diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index a965e5b0d328..554aa8f24f91 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_KVM_PARA_H #define _UAPI_ASM_X86_KVM_PARA_H diff --git a/arch/x86/include/uapi/asm/kvm_perf.h b/arch/x86/include/uapi/asm/kvm_perf.h index 3bb964f88aa1..125cf5cdf6c5 100644 --- a/arch/x86/include/uapi/asm/kvm_perf.h +++ b/arch/x86/include/uapi/asm/kvm_perf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_KVM_PERF_H #define _ASM_X86_KVM_PERF_H diff --git a/arch/x86/include/uapi/asm/ldt.h b/arch/x86/include/uapi/asm/ldt.h index 6e1aaf73852a..d62ac5db093b 100644 --- a/arch/x86/include/uapi/asm/ldt.h +++ b/arch/x86/include/uapi/asm/ldt.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * ldt.h * diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h index eb6247a7009b..91723461dc1f 100644 --- a/arch/x86/include/uapi/asm/mce.h +++ b/arch/x86/include/uapi/asm/mce.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_MCE_H #define _UAPI_ASM_X86_MCE_H diff --git a/arch/x86/include/uapi/asm/mman.h b/arch/x86/include/uapi/asm/mman.h index 3be08f07695c..d4a8d0424bfb 100644 --- a/arch/x86/include/uapi/asm/mman.h +++ b/arch/x86/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_MMAN_H #define _ASM_X86_MMAN_H diff --git a/arch/x86/include/uapi/asm/msr.h b/arch/x86/include/uapi/asm/msr.h index c41f4fe25483..e7516b402a00 100644 --- a/arch/x86/include/uapi/asm/msr.h +++ b/arch/x86/include/uapi/asm/msr.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_MSR_H #define _UAPI_ASM_X86_MSR_H diff --git a/arch/x86/include/uapi/asm/perf_regs.h b/arch/x86/include/uapi/asm/perf_regs.h index 3f2207bfd17b..f3329cabce5c 100644 --- a/arch/x86/include/uapi/asm/perf_regs.h +++ b/arch/x86/include/uapi/asm/perf_regs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_PERF_REGS_H #define _ASM_X86_PERF_REGS_H diff --git a/arch/x86/include/uapi/asm/posix_types.h b/arch/x86/include/uapi/asm/posix_types.h index 85506b383627..c661e95f0134 100644 --- a/arch/x86/include/uapi/asm/posix_types.h +++ b/arch/x86/include/uapi/asm/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __KERNEL__ # ifdef __i386__ # include diff --git a/arch/x86/include/uapi/asm/posix_types_32.h b/arch/x86/include/uapi/asm/posix_types_32.h index 8e525059e7d8..840659f4b96f 100644 --- a/arch/x86/include/uapi/asm/posix_types_32.h +++ b/arch/x86/include/uapi/asm/posix_types_32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_POSIX_TYPES_32_H #define _ASM_X86_POSIX_TYPES_32_H diff --git a/arch/x86/include/uapi/asm/posix_types_64.h b/arch/x86/include/uapi/asm/posix_types_64.h index cba0c1ead162..515afb8059ce 100644 --- a/arch/x86/include/uapi/asm/posix_types_64.h +++ b/arch/x86/include/uapi/asm/posix_types_64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_POSIX_TYPES_64_H #define _ASM_X86_POSIX_TYPES_64_H diff --git a/arch/x86/include/uapi/asm/posix_types_x32.h b/arch/x86/include/uapi/asm/posix_types_x32.h index 85f9bdafa93c..f60479b07fc8 100644 --- a/arch/x86/include/uapi/asm/posix_types_x32.h +++ b/arch/x86/include/uapi/asm/posix_types_x32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_POSIX_TYPES_X32_H #define _ASM_X86_POSIX_TYPES_X32_H diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h index c45765517092..5a6aac9fa41f 100644 --- a/arch/x86/include/uapi/asm/prctl.h +++ b/arch/x86/include/uapi/asm/prctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_PRCTL_H #define _ASM_X86_PRCTL_H diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h index 185f3d10c194..6f3355399665 100644 --- a/arch/x86/include/uapi/asm/processor-flags.h +++ b/arch/x86/include/uapi/asm/processor-flags.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_PROCESSOR_FLAGS_H #define _UAPI_ASM_X86_PROCESSOR_FLAGS_H /* Various flags defined: can be included from assembler. */ diff --git a/arch/x86/include/uapi/asm/ptrace-abi.h b/arch/x86/include/uapi/asm/ptrace-abi.h index 580aee3072e0..16074b9c93bb 100644 --- a/arch/x86/include/uapi/asm/ptrace-abi.h +++ b/arch/x86/include/uapi/asm/ptrace-abi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_PTRACE_ABI_H #define _ASM_X86_PTRACE_ABI_H diff --git a/arch/x86/include/uapi/asm/ptrace.h b/arch/x86/include/uapi/asm/ptrace.h index bc16115af39b..85165c0edafc 100644 --- a/arch/x86/include/uapi/asm/ptrace.h +++ b/arch/x86/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_PTRACE_H #define _UAPI_ASM_X86_PTRACE_H diff --git a/arch/x86/include/uapi/asm/sembuf.h b/arch/x86/include/uapi/asm/sembuf.h index cc2d6a3aeae7..cabd7476bd6c 100644 --- a/arch/x86/include/uapi/asm/sembuf.h +++ b/arch/x86/include/uapi/asm/sembuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_SEMBUF_H #define _ASM_X86_SEMBUF_H diff --git a/arch/x86/include/uapi/asm/sigcontext.h b/arch/x86/include/uapi/asm/sigcontext.h index 62d4111c1c54..844d60eb1882 100644 --- a/arch/x86/include/uapi/asm/sigcontext.h +++ b/arch/x86/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_SIGCONTEXT_H #define _UAPI_ASM_X86_SIGCONTEXT_H diff --git a/arch/x86/include/uapi/asm/siginfo.h b/arch/x86/include/uapi/asm/siginfo.h index 34c47b3341c0..b3d157957177 100644 --- a/arch/x86/include/uapi/asm/siginfo.h +++ b/arch/x86/include/uapi/asm/siginfo.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_SIGINFO_H #define _ASM_X86_SIGINFO_H diff --git a/arch/x86/include/uapi/asm/signal.h b/arch/x86/include/uapi/asm/signal.h index 8264f47cf53e..e5745d593dc7 100644 --- a/arch/x86/include/uapi/asm/signal.h +++ b/arch/x86/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_SIGNAL_H #define _UAPI_ASM_X86_SIGNAL_H diff --git a/arch/x86/include/uapi/asm/stat.h b/arch/x86/include/uapi/asm/stat.h index bc03eb5d6360..9e3982d95d0f 100644 --- a/arch/x86/include/uapi/asm/stat.h +++ b/arch/x86/include/uapi/asm/stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_STAT_H #define _ASM_X86_STAT_H diff --git a/arch/x86/include/uapi/asm/statfs.h b/arch/x86/include/uapi/asm/statfs.h index 2d0adbf99a8e..13c2464cd2c4 100644 --- a/arch/x86/include/uapi/asm/statfs.h +++ b/arch/x86/include/uapi/asm/statfs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_STATFS_H #define _ASM_X86_STATFS_H diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index 3725e145aa58..a9731f8a480f 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__SVM_H #define _UAPI__SVM_H diff --git a/arch/x86/include/uapi/asm/swab.h b/arch/x86/include/uapi/asm/swab.h index 7f235c7105c1..cd3fd8ddbe9a 100644 --- a/arch/x86/include/uapi/asm/swab.h +++ b/arch/x86/include/uapi/asm/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_SWAB_H #define _ASM_X86_SWAB_H diff --git a/arch/x86/include/uapi/asm/ucontext.h b/arch/x86/include/uapi/asm/ucontext.h index e3d1ec90616e..5657b7a49f03 100644 --- a/arch/x86/include/uapi/asm/ucontext.h +++ b/arch/x86/include/uapi/asm/ucontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_UCONTEXT_H #define _ASM_X86_UCONTEXT_H diff --git a/arch/x86/include/uapi/asm/unistd.h b/arch/x86/include/uapi/asm/unistd.h index a26df0d75cd0..30d7d04d72d6 100644 --- a/arch/x86/include/uapi/asm/unistd.h +++ b/arch/x86/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_UNISTD_H #define _UAPI_ASM_X86_UNISTD_H diff --git a/arch/x86/include/uapi/asm/vm86.h b/arch/x86/include/uapi/asm/vm86.h index e0b243e9d859..d2ee4e307ef8 100644 --- a/arch/x86/include/uapi/asm/vm86.h +++ b/arch/x86/include/uapi/asm/vm86.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_VM86_H #define _UAPI_ASM_X86_VM86_H diff --git a/arch/x86/include/uapi/asm/vsyscall.h b/arch/x86/include/uapi/asm/vsyscall.h index b97dd6e263d2..75275f547444 100644 --- a/arch/x86/include/uapi/asm/vsyscall.h +++ b/arch/x86/include/uapi/asm/vsyscall.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_X86_VSYSCALL_H #define _UAPI_ASM_X86_VSYSCALL_H diff --git a/arch/xtensa/include/uapi/asm/byteorder.h b/arch/xtensa/include/uapi/asm/byteorder.h index 54eb6315349c..5b9f832c2e77 100644 --- a/arch/xtensa/include/uapi/asm/byteorder.h +++ b/arch/xtensa/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XTENSA_BYTEORDER_H #define _XTENSA_BYTEORDER_H diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h index 6be7eb27fd29..bc3f62db5c5f 100644 --- a/arch/xtensa/include/uapi/asm/unistd.h +++ b/arch/xtensa/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #if !defined(_UAPI_XTENSA_UNISTD_H) || defined(__SYSCALL) #define _UAPI_XTENSA_UNISTD_H diff --git a/include/uapi/asm-generic/bitsperlong.h b/include/uapi/asm-generic/bitsperlong.h index 23e6c416b85f..693d9a40eb7b 100644 --- a/include/uapi/asm-generic/bitsperlong.h +++ b/include/uapi/asm-generic/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__ASM_GENERIC_BITS_PER_LONG #define _UAPI__ASM_GENERIC_BITS_PER_LONG diff --git a/include/uapi/asm-generic/errno-base.h b/include/uapi/asm-generic/errno-base.h index 65115978510f..9653140bff92 100644 --- a/include/uapi/asm-generic/errno-base.h +++ b/include/uapi/asm-generic/errno-base.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_GENERIC_ERRNO_BASE_H #define _ASM_GENERIC_ERRNO_BASE_H diff --git a/include/uapi/asm-generic/errno.h b/include/uapi/asm-generic/errno.h index 88e0914cf2d9..cf9c51ac49f9 100644 --- a/include/uapi/asm-generic/errno.h +++ b/include/uapi/asm-generic/errno.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_GENERIC_ERRNO_H #define _ASM_GENERIC_ERRNO_H diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h index e063effe0cc1..9dc0bf0c5a6e 100644 --- a/include/uapi/asm-generic/fcntl.h +++ b/include/uapi/asm-generic/fcntl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_GENERIC_FCNTL_H #define _ASM_GENERIC_FCNTL_H diff --git a/include/uapi/asm-generic/int-l64.h b/include/uapi/asm-generic/int-l64.h index 978f21cae2f4..ed8bcd99c34d 100644 --- a/include/uapi/asm-generic/int-l64.h +++ b/include/uapi/asm-generic/int-l64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * asm-generic/int-l64.h * diff --git a/include/uapi/asm-generic/int-ll64.h b/include/uapi/asm-generic/int-ll64.h index a8658b2423ba..1ed06964257c 100644 --- a/include/uapi/asm-generic/int-ll64.h +++ b/include/uapi/asm-generic/int-ll64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * asm-generic/int-ll64.h * diff --git a/include/uapi/asm-generic/ioctl.h b/include/uapi/asm-generic/ioctl.h index 749b32fe5623..a84f4db8a250 100644 --- a/include/uapi/asm-generic/ioctl.h +++ b/include/uapi/asm-generic/ioctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_GENERIC_IOCTL_H #define _UAPI_ASM_GENERIC_IOCTL_H diff --git a/include/uapi/asm-generic/ioctls.h b/include/uapi/asm-generic/ioctls.h index 14baf9f23a14..040651735662 100644 --- a/include/uapi/asm-generic/ioctls.h +++ b/include/uapi/asm-generic/ioctls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_GENERIC_IOCTLS_H #define __ASM_GENERIC_IOCTLS_H diff --git a/include/uapi/asm-generic/ipcbuf.h b/include/uapi/asm-generic/ipcbuf.h index 3dbcc1e771c0..7d80dbd336fb 100644 --- a/include/uapi/asm-generic/ipcbuf.h +++ b/include/uapi/asm-generic/ipcbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_GENERIC_IPCBUF_H #define __ASM_GENERIC_IPCBUF_H diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h index 203268f9231e..6d319c46fd90 100644 --- a/include/uapi/asm-generic/mman-common.h +++ b/include/uapi/asm-generic/mman-common.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_GENERIC_MMAN_COMMON_H #define __ASM_GENERIC_MMAN_COMMON_H diff --git a/include/uapi/asm-generic/mman.h b/include/uapi/asm-generic/mman.h index 7162cd4cca73..2dffcbf705b3 100644 --- a/include/uapi/asm-generic/mman.h +++ b/include/uapi/asm-generic/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_GENERIC_MMAN_H #define __ASM_GENERIC_MMAN_H diff --git a/include/uapi/asm-generic/msgbuf.h b/include/uapi/asm-generic/msgbuf.h index f55ecc43c60f..fb306ebdb36f 100644 --- a/include/uapi/asm-generic/msgbuf.h +++ b/include/uapi/asm-generic/msgbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_GENERIC_MSGBUF_H #define __ASM_GENERIC_MSGBUF_H diff --git a/include/uapi/asm-generic/param.h b/include/uapi/asm-generic/param.h index 5becc84396b8..baad02ea7f93 100644 --- a/include/uapi/asm-generic/param.h +++ b/include/uapi/asm-generic/param.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__ASM_GENERIC_PARAM_H #define _UAPI__ASM_GENERIC_PARAM_H diff --git a/include/uapi/asm-generic/poll.h b/include/uapi/asm-generic/poll.h index a9694982689f..fefb3d2c3fac 100644 --- a/include/uapi/asm-generic/poll.h +++ b/include/uapi/asm-generic/poll.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_GENERIC_POLL_H #define __ASM_GENERIC_POLL_H diff --git a/include/uapi/asm-generic/posix_types.h b/include/uapi/asm-generic/posix_types.h index fe74fccf18db..5e6ea22bd525 100644 --- a/include/uapi/asm-generic/posix_types.h +++ b/include/uapi/asm-generic/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_GENERIC_POSIX_TYPES_H #define __ASM_GENERIC_POSIX_TYPES_H diff --git a/include/uapi/asm-generic/resource.h b/include/uapi/asm-generic/resource.h index c6d10af50123..f12db7a0da64 100644 --- a/include/uapi/asm-generic/resource.h +++ b/include/uapi/asm-generic/resource.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_GENERIC_RESOURCE_H #define _UAPI_ASM_GENERIC_RESOURCE_H diff --git a/include/uapi/asm-generic/sembuf.h b/include/uapi/asm-generic/sembuf.h index 4cb2c13e5090..cbf9cfe977d6 100644 --- a/include/uapi/asm-generic/sembuf.h +++ b/include/uapi/asm-generic/sembuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_GENERIC_SEMBUF_H #define __ASM_GENERIC_SEMBUF_H diff --git a/include/uapi/asm-generic/setup.h b/include/uapi/asm-generic/setup.h index 6fc26a51003c..88ac5100df35 100644 --- a/include/uapi/asm-generic/setup.h +++ b/include/uapi/asm-generic/setup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_GENERIC_SETUP_H #define __ASM_GENERIC_SETUP_H diff --git a/include/uapi/asm-generic/shmbuf.h b/include/uapi/asm-generic/shmbuf.h index 7e9fb2f0853b..2b6c3bb97f97 100644 --- a/include/uapi/asm-generic/shmbuf.h +++ b/include/uapi/asm-generic/shmbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_GENERIC_SHMBUF_H #define __ASM_GENERIC_SHMBUF_H diff --git a/include/uapi/asm-generic/shmparam.h b/include/uapi/asm-generic/shmparam.h index 51a3852de733..8b78c0ba08b1 100644 --- a/include/uapi/asm-generic/shmparam.h +++ b/include/uapi/asm-generic/shmparam.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_GENERIC_SHMPARAM_H #define __ASM_GENERIC_SHMPARAM_H diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h index e5aa6794cea4..e447283b8f52 100644 --- a/include/uapi/asm-generic/siginfo.h +++ b/include/uapi/asm-generic/siginfo.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_GENERIC_SIGINFO_H #define _UAPI_ASM_GENERIC_SIGINFO_H diff --git a/include/uapi/asm-generic/signal-defs.h b/include/uapi/asm-generic/signal-defs.h index 00f95df54297..e9304c95ceea 100644 --- a/include/uapi/asm-generic/signal-defs.h +++ b/include/uapi/asm-generic/signal-defs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_GENERIC_SIGNAL_DEFS_H #define __ASM_GENERIC_SIGNAL_DEFS_H diff --git a/include/uapi/asm-generic/signal.h b/include/uapi/asm-generic/signal.h index 3094618d382f..5c716a952cbe 100644 --- a/include/uapi/asm-generic/signal.h +++ b/include/uapi/asm-generic/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__ASM_GENERIC_SIGNAL_H #define _UAPI__ASM_GENERIC_SIGNAL_H diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index e47c9e436221..0ae758c90e54 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_GENERIC_SOCKET_H #define __ASM_GENERIC_SOCKET_H diff --git a/include/uapi/asm-generic/sockios.h b/include/uapi/asm-generic/sockios.h index 9a61a369b901..64f658c7cec2 100644 --- a/include/uapi/asm-generic/sockios.h +++ b/include/uapi/asm-generic/sockios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_GENERIC_SOCKIOS_H #define __ASM_GENERIC_SOCKIOS_H diff --git a/include/uapi/asm-generic/stat.h b/include/uapi/asm-generic/stat.h index bd8cad21998e..0d962ecd1663 100644 --- a/include/uapi/asm-generic/stat.h +++ b/include/uapi/asm-generic/stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_GENERIC_STAT_H #define __ASM_GENERIC_STAT_H diff --git a/include/uapi/asm-generic/statfs.h b/include/uapi/asm-generic/statfs.h index cb89cc730f0b..bd35c7619ca2 100644 --- a/include/uapi/asm-generic/statfs.h +++ b/include/uapi/asm-generic/statfs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_GENERIC_STATFS_H #define _UAPI_GENERIC_STATFS_H diff --git a/include/uapi/asm-generic/swab.h b/include/uapi/asm-generic/swab.h index a8e9029d9eba..f2da4e4fd4d1 100644 --- a/include/uapi/asm-generic/swab.h +++ b/include/uapi/asm-generic/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_GENERIC_SWAB_H #define _ASM_GENERIC_SWAB_H diff --git a/include/uapi/asm-generic/termbits.h b/include/uapi/asm-generic/termbits.h index 232b4781aef3..2fbaf9ae89dd 100644 --- a/include/uapi/asm-generic/termbits.h +++ b/include/uapi/asm-generic/termbits.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_GENERIC_TERMBITS_H #define __ASM_GENERIC_TERMBITS_H diff --git a/include/uapi/asm-generic/termios.h b/include/uapi/asm-generic/termios.h index 088176062133..cf892933a363 100644 --- a/include/uapi/asm-generic/termios.h +++ b/include/uapi/asm-generic/termios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_GENERIC_TERMIOS_H #define _UAPI_ASM_GENERIC_TERMIOS_H /* diff --git a/include/uapi/asm-generic/types.h b/include/uapi/asm-generic/types.h index a3877926b0d4..dfaa50d99d8f 100644 --- a/include/uapi/asm-generic/types.h +++ b/include/uapi/asm-generic/types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_GENERIC_TYPES_H #define _ASM_GENERIC_TYPES_H /* diff --git a/include/uapi/asm-generic/ucontext.h b/include/uapi/asm-generic/ucontext.h index ad77343e8a9a..351868a72168 100644 --- a/include/uapi/asm-generic/ucontext.h +++ b/include/uapi/asm-generic/ucontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_GENERIC_UCONTEXT_H #define __ASM_GENERIC_UCONTEXT_H diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 061185a5eb51..8b87de067bc7 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include /* diff --git a/include/uapi/drm/i810_drm.h b/include/uapi/drm/i810_drm.h index 6e6cf86b75b0..d285d5e72e6a 100644 --- a/include/uapi/drm/i810_drm.h +++ b/include/uapi/drm/i810_drm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _I810_DRM_H_ #define _I810_DRM_H_ diff --git a/include/uapi/linux/a.out.h b/include/uapi/linux/a.out.h index 295cd3ef6330..5fafde3798e5 100644 --- a/include/uapi/linux/a.out.h +++ b/include/uapi/linux/a.out.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__A_OUT_GNU_H__ #define _UAPI__A_OUT_GNU_H__ diff --git a/include/uapi/linux/acct.h b/include/uapi/linux/acct.h index df2f9a0bba6a..0e72172cd23a 100644 --- a/include/uapi/linux/acct.h +++ b/include/uapi/linux/acct.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * BSD Process Accounting for Linux - Definitions * diff --git a/include/uapi/linux/adb.h b/include/uapi/linux/adb.h index 0ea1075fc4a0..12b6db148ea9 100644 --- a/include/uapi/linux/adb.h +++ b/include/uapi/linux/adb.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Definitions for ADB (Apple Desktop Bus) support. */ diff --git a/include/uapi/linux/adfs_fs.h b/include/uapi/linux/adfs_fs.h index a1bf43754ddd..151d93e27ed4 100644 --- a/include/uapi/linux/adfs_fs.h +++ b/include/uapi/linux/adfs_fs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ADFS_FS_H #define _UAPI_ADFS_FS_H diff --git a/include/uapi/linux/affs_hardblocks.h b/include/uapi/linux/affs_hardblocks.h index f1b948c1f592..5e2fb8481252 100644 --- a/include/uapi/linux/affs_hardblocks.h +++ b/include/uapi/linux/affs_hardblocks.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef AFFS_HARDBLOCKS_H #define AFFS_HARDBLOCKS_H diff --git a/include/uapi/linux/arcfb.h b/include/uapi/linux/arcfb.h index 721e7654daeb..7a9008b365df 100644 --- a/include/uapi/linux/arcfb.h +++ b/include/uapi/linux/arcfb.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_ARCFB_H__ #define __LINUX_ARCFB_H__ diff --git a/include/uapi/linux/atalk.h b/include/uapi/linux/atalk.h index 4bcd596e6388..8b96460b46b1 100644 --- a/include/uapi/linux/atalk.h +++ b/include/uapi/linux/atalk.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__LINUX_ATALK_H__ #define _UAPI__LINUX_ATALK_H__ diff --git a/include/uapi/linux/atm.h b/include/uapi/linux/atm.h index 88399db602ac..95ebdcf4fe88 100644 --- a/include/uapi/linux/atm.h +++ b/include/uapi/linux/atm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* atm.h - general ATM declarations */ /* Written 1995-2000 by Werner Almesberger, EPFL LRC/ICA */ diff --git a/include/uapi/linux/atm_eni.h b/include/uapi/linux/atm_eni.h index 34f317972551..cf5bfd1a2691 100644 --- a/include/uapi/linux/atm_eni.h +++ b/include/uapi/linux/atm_eni.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* atm_eni.h - Driver-specific declarations of the ENI driver (for use by driver-specific utilities) */ diff --git a/include/uapi/linux/atm_he.h b/include/uapi/linux/atm_he.h index 2a7713b597cf..9f4b43293988 100644 --- a/include/uapi/linux/atm_he.h +++ b/include/uapi/linux/atm_he.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* atm_he.h */ #ifndef LINUX_ATM_HE_H diff --git a/include/uapi/linux/atm_idt77105.h b/include/uapi/linux/atm_idt77105.h index 8b724000aa50..f0fd6912a14b 100644 --- a/include/uapi/linux/atm_idt77105.h +++ b/include/uapi/linux/atm_idt77105.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* atm_idt77105.h - Driver-specific declarations of the IDT77105 driver (for * use by driver-specific utilities) */ diff --git a/include/uapi/linux/atm_nicstar.h b/include/uapi/linux/atm_nicstar.h index 577b79f33e8d..880d368b5b9a 100644 --- a/include/uapi/linux/atm_nicstar.h +++ b/include/uapi/linux/atm_nicstar.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /****************************************************************************** * * atm_nicstar.h diff --git a/include/uapi/linux/atm_tcp.h b/include/uapi/linux/atm_tcp.h index 914e821da64d..7309e1bc8867 100644 --- a/include/uapi/linux/atm_tcp.h +++ b/include/uapi/linux/atm_tcp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* atm_tcp.h - Driver-specific declarations of the ATMTCP driver (for use by driver-specific utilities) */ diff --git a/include/uapi/linux/atm_zatm.h b/include/uapi/linux/atm_zatm.h index 9c9c6ad55f14..5135027b93c1 100644 --- a/include/uapi/linux/atm_zatm.h +++ b/include/uapi/linux/atm_zatm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* atm_zatm.h - Driver-specific declarations of the ZATM driver (for use by driver-specific utilities) */ diff --git a/include/uapi/linux/atmapi.h b/include/uapi/linux/atmapi.h index 8fe54d90d95b..c9bf5c23a71f 100644 --- a/include/uapi/linux/atmapi.h +++ b/include/uapi/linux/atmapi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* atmapi.h - ATM API user space/kernel compatibility */ /* Written 1999,2000 by Werner Almesberger, EPFL ICA */ diff --git a/include/uapi/linux/atmarp.h b/include/uapi/linux/atmarp.h index 231f4bdec730..8e44d121fde1 100644 --- a/include/uapi/linux/atmarp.h +++ b/include/uapi/linux/atmarp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* atmarp.h - ATM ARP protocol and kernel-demon interface definitions */ /* Written 1995-1999 by Werner Almesberger, EPFL LRC/ICA */ diff --git a/include/uapi/linux/atmbr2684.h b/include/uapi/linux/atmbr2684.h index fdb2629b6189..a9e2250cd720 100644 --- a/include/uapi/linux/atmbr2684.h +++ b/include/uapi/linux/atmbr2684.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_ATMBR2684_H #define _LINUX_ATMBR2684_H diff --git a/include/uapi/linux/atmclip.h b/include/uapi/linux/atmclip.h index 02c94c448dd6..c818bb82b4e6 100644 --- a/include/uapi/linux/atmclip.h +++ b/include/uapi/linux/atmclip.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* atmclip.h - Classical IP over ATM */ /* Written 1995-1998 by Werner Almesberger, EPFL LRC/ICA */ diff --git a/include/uapi/linux/atmdev.h b/include/uapi/linux/atmdev.h index 93e0ec008ca8..a5c15cf23bd7 100644 --- a/include/uapi/linux/atmdev.h +++ b/include/uapi/linux/atmdev.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* atmdev.h - ATM device driver declarations and various related items */ /* Written 1995-2000 by Werner Almesberger, EPFL LRC/ICA */ diff --git a/include/uapi/linux/atmioc.h b/include/uapi/linux/atmioc.h index 37f67aa8f1c1..cd7655e40c77 100644 --- a/include/uapi/linux/atmioc.h +++ b/include/uapi/linux/atmioc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* atmioc.h - ranges for ATM-related ioctl numbers */ /* Written 1995-1999 by Werner Almesberger, EPFL LRC/ICA */ diff --git a/include/uapi/linux/atmlec.h b/include/uapi/linux/atmlec.h index 302791e3ab2b..c68346bb40e6 100644 --- a/include/uapi/linux/atmlec.h +++ b/include/uapi/linux/atmlec.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * ATM Lan Emulation Daemon driver interface * diff --git a/include/uapi/linux/atmmpc.h b/include/uapi/linux/atmmpc.h index 2aba5787fa63..cc17f4304839 100644 --- a/include/uapi/linux/atmmpc.h +++ b/include/uapi/linux/atmmpc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ATMMPC_H_ #define _ATMMPC_H_ diff --git a/include/uapi/linux/atmppp.h b/include/uapi/linux/atmppp.h index 300dcce0c83f..504b9989675b 100644 --- a/include/uapi/linux/atmppp.h +++ b/include/uapi/linux/atmppp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* atmppp.h - RFC2364 PPPoATM */ /* Written 2000 by Mitchell Blank Jr */ diff --git a/include/uapi/linux/atmsap.h b/include/uapi/linux/atmsap.h index 799b104515d7..fc052481eae0 100644 --- a/include/uapi/linux/atmsap.h +++ b/include/uapi/linux/atmsap.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* atmsap.h - ATM Service Access Point addressing definitions */ /* Written 1995-1999 by Werner Almesberger, EPFL LRC/ICA */ diff --git a/include/uapi/linux/atmsvc.h b/include/uapi/linux/atmsvc.h index aa71583b8da7..137b5f853449 100644 --- a/include/uapi/linux/atmsvc.h +++ b/include/uapi/linux/atmsvc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* atmsvc.h - ATM signaling kernel-demon interface definitions */ /* Written 1995-2000 by Werner Almesberger, EPFL LRC/ICA */ diff --git a/include/uapi/linux/auxvec.h b/include/uapi/linux/auxvec.h index 835c065cc7e1..abe5f2b6581b 100644 --- a/include/uapi/linux/auxvec.h +++ b/include/uapi/linux/auxvec.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_AUXVEC_H #define _UAPI_LINUX_AUXVEC_H diff --git a/include/uapi/linux/ax25.h b/include/uapi/linux/ax25.h index 74c89a41732d..b496b9d8452f 100644 --- a/include/uapi/linux/ax25.h +++ b/include/uapi/linux/ax25.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * These are the public elements of the Linux kernel AX.25 code. A similar * file netrom.h exists for the NET/ROM protocol. diff --git a/include/uapi/linux/baycom.h b/include/uapi/linux/baycom.h index 81249e029dad..478cb565ae52 100644 --- a/include/uapi/linux/baycom.h +++ b/include/uapi/linux/baycom.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * The Linux BAYCOM driver for the Baycom serial 1200 baud modem * and the parallel 9600 baud modem diff --git a/include/uapi/linux/bcache.h b/include/uapi/linux/bcache.h index e3bb0635e94a..90fc490f973f 100644 --- a/include/uapi/linux/bcache.h +++ b/include/uapi/linux/bcache.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_BCACHE_H #define _LINUX_BCACHE_H diff --git a/include/uapi/linux/bcm933xx_hcs.h b/include/uapi/linux/bcm933xx_hcs.h index d22821831549..f9fccf3c3654 100644 --- a/include/uapi/linux/bcm933xx_hcs.h +++ b/include/uapi/linux/bcm933xx_hcs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Broadcom Cable Modem firmware format */ diff --git a/include/uapi/linux/bfs_fs.h b/include/uapi/linux/bfs_fs.h index 1c0b355aa515..73445ef07dda 100644 --- a/include/uapi/linux/bfs_fs.h +++ b/include/uapi/linux/bfs_fs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/linux/bfs_fs.h - BFS data structures on disk. * Copyright (C) 1999 Tigran Aivazian diff --git a/include/uapi/linux/binfmts.h b/include/uapi/linux/binfmts.h index 4eb5972867c0..4abad03a8853 100644 --- a/include/uapi/linux/binfmts.h +++ b/include/uapi/linux/binfmts.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_BINFMTS_H #define _UAPI_LINUX_BINFMTS_H diff --git a/include/uapi/linux/blkpg.h b/include/uapi/linux/blkpg.h index 63739a035085..ac6474e4f29d 100644 --- a/include/uapi/linux/blkpg.h +++ b/include/uapi/linux/blkpg.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__LINUX_BLKPG_H #define _UAPI__LINUX_BLKPG_H diff --git a/include/uapi/linux/blktrace_api.h b/include/uapi/linux/blktrace_api.h index 9cdaedeadb84..20d1490d6377 100644 --- a/include/uapi/linux/blktrace_api.h +++ b/include/uapi/linux/blktrace_api.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPIBLKTRACE_H #define _UAPIBLKTRACE_H diff --git a/include/uapi/linux/bpf_common.h b/include/uapi/linux/bpf_common.h index a5c220e0828f..18be90725ab0 100644 --- a/include/uapi/linux/bpf_common.h +++ b/include/uapi/linux/bpf_common.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__LINUX_BPF_COMMON_H__ #define _UAPI__LINUX_BPF_COMMON_H__ diff --git a/include/uapi/linux/bpqether.h b/include/uapi/linux/bpqether.h index 05865edaefda..d1d63e2acdeb 100644 --- a/include/uapi/linux/bpqether.h +++ b/include/uapi/linux/bpqether.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __BPQETHER_H #define __BPQETHER_H diff --git a/include/uapi/linux/bsg.h b/include/uapi/linux/bsg.h index 02986cf8b6f1..cd6302def5ed 100644 --- a/include/uapi/linux/bsg.h +++ b/include/uapi/linux/bsg.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPIBSG_H #define _UAPIBSG_H diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index 10689e1fdf11..8f659bb7badc 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _BTRFS_CTREE_H_ #define _BTRFS_CTREE_H_ diff --git a/include/uapi/linux/byteorder/big_endian.h b/include/uapi/linux/byteorder/big_endian.h index cdab17ab907c..2199adc6a6c2 100644 --- a/include/uapi/linux/byteorder/big_endian.h +++ b/include/uapi/linux/byteorder/big_endian.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_BYTEORDER_BIG_ENDIAN_H #define _UAPI_LINUX_BYTEORDER_BIG_ENDIAN_H diff --git a/include/uapi/linux/byteorder/little_endian.h b/include/uapi/linux/byteorder/little_endian.h index 4b93f2b260dd..601c904fd5cd 100644 --- a/include/uapi/linux/byteorder/little_endian.h +++ b/include/uapi/linux/byteorder/little_endian.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_BYTEORDER_LITTLE_ENDIAN_H #define _UAPI_LINUX_BYTEORDER_LITTLE_ENDIAN_H diff --git a/include/uapi/linux/can/vxcan.h b/include/uapi/linux/can/vxcan.h index ffb0b7156f7e..066812d118a2 100644 --- a/include/uapi/linux/can/vxcan.h +++ b/include/uapi/linux/can/vxcan.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_CAN_VXCAN_H #define _UAPI_CAN_VXCAN_H diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h index 230e05d35191..240fdb9a60f6 100644 --- a/include/uapi/linux/capability.h +++ b/include/uapi/linux/capability.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This is * diff --git a/include/uapi/linux/cciss_defs.h b/include/uapi/linux/cciss_defs.h index 316b670d4e33..5cbdfe993365 100644 --- a/include/uapi/linux/cciss_defs.h +++ b/include/uapi/linux/cciss_defs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef CCISS_DEFS_H #define CCISS_DEFS_H diff --git a/include/uapi/linux/cciss_ioctl.h b/include/uapi/linux/cciss_ioctl.h index bb0b9ddf7eeb..562230199461 100644 --- a/include/uapi/linux/cciss_ioctl.h +++ b/include/uapi/linux/cciss_ioctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPICCISS_IOCTLH #define _UAPICCISS_IOCTLH diff --git a/include/uapi/linux/cdrom.h b/include/uapi/linux/cdrom.h index bd17ad5aa06d..2817230148fd 100644 --- a/include/uapi/linux/cdrom.h +++ b/include/uapi/linux/cdrom.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * -- * General header file for linux CD-ROM drivers diff --git a/include/uapi/linux/chio.h b/include/uapi/linux/chio.h index d9bac7f97282..689fc93fafda 100644 --- a/include/uapi/linux/chio.h +++ b/include/uapi/linux/chio.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * ioctl interface for the scsi media changer driver */ diff --git a/include/uapi/linux/cm4000_cs.h b/include/uapi/linux/cm4000_cs.h index 1217f751a1bc..c70a62ec8a49 100644 --- a/include/uapi/linux/cm4000_cs.h +++ b/include/uapi/linux/cm4000_cs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_CM4000_H_ #define _UAPI_CM4000_H_ diff --git a/include/uapi/linux/coda_psdev.h b/include/uapi/linux/coda_psdev.h index 79d05981fc4b..aa6623efd2dd 100644 --- a/include/uapi/linux/coda_psdev.h +++ b/include/uapi/linux/coda_psdev.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__CODA_PSDEV_H #define _UAPI__CODA_PSDEV_H diff --git a/include/uapi/linux/const.h b/include/uapi/linux/const.h index c872bfd25e13..92537757590a 100644 --- a/include/uapi/linux/const.h +++ b/include/uapi/linux/const.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* const.h: Macros for dealing with constants. */ #ifndef _LINUX_CONST_H diff --git a/include/uapi/linux/coresight-stm.h b/include/uapi/linux/coresight-stm.h index 7e4272cf1fb2..aac550a52f80 100644 --- a/include/uapi/linux/coresight-stm.h +++ b/include/uapi/linux/coresight-stm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __UAPI_CORESIGHT_STM_H_ #define __UAPI_CORESIGHT_STM_H_ diff --git a/include/uapi/linux/cramfs_fs.h b/include/uapi/linux/cramfs_fs.h index e4611a9b9243..5519504199e6 100644 --- a/include/uapi/linux/cramfs_fs.h +++ b/include/uapi/linux/cramfs_fs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__CRAMFS_H #define _UAPI__CRAMFS_H diff --git a/include/uapi/linux/cuda.h b/include/uapi/linux/cuda.h index 286f9f10fce8..28182557748d 100644 --- a/include/uapi/linux/cuda.h +++ b/include/uapi/linux/cuda.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Definitions for talking to the CUDA. The CUDA is a microcontroller * which controls the ADB, system power, RTC, and various other things. diff --git a/include/uapi/linux/cyclades.h b/include/uapi/linux/cyclades.h index 12b587aa361c..8279bc3d60ca 100644 --- a/include/uapi/linux/cyclades.h +++ b/include/uapi/linux/cyclades.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* $Revision: 3.0 $$Date: 1998/11/02 14:20:59 $ * linux/include/linux/cyclades.h * diff --git a/include/uapi/linux/dccp.h b/include/uapi/linux/dccp.h index 52a9cd7307e7..6e1978dbcf7c 100644 --- a/include/uapi/linux/dccp.h +++ b/include/uapi/linux/dccp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_DCCP_H #define _UAPI_LINUX_DCCP_H diff --git a/include/uapi/linux/dn.h b/include/uapi/linux/dn.h index 4295c745f342..36ca71bd8bbe 100644 --- a/include/uapi/linux/dn.h +++ b/include/uapi/linux/dn.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_DN_H #define _LINUX_DN_H diff --git a/include/uapi/linux/efs_fs_sb.h b/include/uapi/linux/efs_fs_sb.h index a01be90c58cc..6bad29a10faa 100644 --- a/include/uapi/linux/efs_fs_sb.h +++ b/include/uapi/linux/efs_fs_sb.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * efs_fs_sb.h * diff --git a/include/uapi/linux/elf-em.h b/include/uapi/linux/elf-em.h index 9cd1de954c0a..31aa10178335 100644 --- a/include/uapi/linux/elf-em.h +++ b/include/uapi/linux/elf-em.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_ELF_EM_H #define _LINUX_ELF_EM_H diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index b5280db9ef6a..c58627c0d6fb 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_ELF_H #define _UAPI_LINUX_ELF_H diff --git a/include/uapi/linux/elfcore.h b/include/uapi/linux/elfcore.h index 569737cfb557..0b2c9e16e345 100644 --- a/include/uapi/linux/elfcore.h +++ b/include/uapi/linux/elfcore.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_ELFCORE_H #define _UAPI_LINUX_ELFCORE_H diff --git a/include/uapi/linux/errqueue.h b/include/uapi/linux/errqueue.h index 78fdf52d6b2f..dc64cfaf13da 100644 --- a/include/uapi/linux/errqueue.h +++ b/include/uapi/linux/errqueue.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_ERRQUEUE_H #define _UAPI_LINUX_ERRQUEUE_H diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 5bd1b1de4ea0..ac71559314e7 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * ethtool.h: Defines for Linux ethtool. * diff --git a/include/uapi/linux/fadvise.h b/include/uapi/linux/fadvise.h index e8e747139b9a..0862b87434c2 100644 --- a/include/uapi/linux/fadvise.h +++ b/include/uapi/linux/fadvise.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef FADVISE_H_INCLUDED #define FADVISE_H_INCLUDED diff --git a/include/uapi/linux/falloc.h b/include/uapi/linux/falloc.h index b075f601919b..51398fa57f6c 100644 --- a/include/uapi/linux/falloc.h +++ b/include/uapi/linux/falloc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_FALLOC_H_ #define _UAPI_FALLOC_H_ diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index 030508d195d3..f79c4e1a84b9 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_FANOTIFY_H #define _UAPI_LINUX_FANOTIFY_H diff --git a/include/uapi/linux/fb.h b/include/uapi/linux/fb.h index fb795c3b3c17..6cd9b198b7c6 100644 --- a/include/uapi/linux/fb.h +++ b/include/uapi/linux/fb.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_FB_H #define _UAPI_LINUX_FB_H diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index ec69d55bcec7..6448cdd9a350 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_FCNTL_H #define _UAPI_LINUX_FCNTL_H diff --git a/include/uapi/linux/fd.h b/include/uapi/linux/fd.h index 84c517cbce90..90fb94712c41 100644 --- a/include/uapi/linux/fd.h +++ b/include/uapi/linux/fd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_FD_H #define _UAPI_LINUX_FD_H diff --git a/include/uapi/linux/fdreg.h b/include/uapi/linux/fdreg.h index 61ce64169004..5e2981d5c523 100644 --- a/include/uapi/linux/fdreg.h +++ b/include/uapi/linux/fdreg.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_FDREG_H #define _LINUX_FDREG_H /* diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h index bbf02a63a011..2b642bf9b5a0 100644 --- a/include/uapi/linux/fib_rules.h +++ b/include/uapi/linux/fib_rules.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_FIB_RULES_H #define __LINUX_FIB_RULES_H diff --git a/include/uapi/linux/fiemap.h b/include/uapi/linux/fiemap.h index 0c51d617dae9..8c0bc24d5d95 100644 --- a/include/uapi/linux/fiemap.h +++ b/include/uapi/linux/fiemap.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * FS_IOC_FIEMAP ioctl infrastructure. * diff --git a/include/uapi/linux/filter.h b/include/uapi/linux/filter.h index c97340e43dd6..13f5b65a888f 100644 --- a/include/uapi/linux/filter.h +++ b/include/uapi/linux/filter.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Linux Socket Filter Data Structures */ diff --git a/include/uapi/linux/flat.h b/include/uapi/linux/flat.h index 88cd6baba8f3..27e595e44fb7 100644 --- a/include/uapi/linux/flat.h +++ b/include/uapi/linux/flat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2002-2003 David McCullough * Copyright (C) 1998 Kenneth Albanowski diff --git a/include/uapi/linux/fou.h b/include/uapi/linux/fou.h index d2947c52dc67..f2ea833a2812 100644 --- a/include/uapi/linux/fou.h +++ b/include/uapi/linux/fou.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* fou.h - FOU Interface */ #ifndef _UAPI_LINUX_FOU_H diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 56235dddea7d..4199f8acbce5 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_FS_H #define _UAPI_LINUX_FS_H diff --git a/include/uapi/linux/fsmap.h b/include/uapi/linux/fsmap.h index e5213c3e38b2..91fd519a3f7d 100644 --- a/include/uapi/linux/fsmap.h +++ b/include/uapi/linux/fsmap.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * FS_IOC_GETFSMAP ioctl infrastructure. * diff --git a/include/uapi/linux/futex.h b/include/uapi/linux/futex.h index 0b1f716373c7..a89eb0accd5e 100644 --- a/include/uapi/linux/futex.h +++ b/include/uapi/linux/futex.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_FUTEX_H #define _UAPI_LINUX_FUTEX_H diff --git a/include/uapi/linux/gen_stats.h b/include/uapi/linux/gen_stats.h index 52deccc2128e..24a861c0d29d 100644 --- a/include/uapi/linux/gen_stats.h +++ b/include/uapi/linux/gen_stats.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_GEN_STATS_H #define __LINUX_GEN_STATS_H diff --git a/include/uapi/linux/genetlink.h b/include/uapi/linux/genetlink.h index adc899381e0d..877f7fa95466 100644 --- a/include/uapi/linux/genetlink.h +++ b/include/uapi/linux/genetlink.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__LINUX_GENERIC_NETLINK_H #define _UAPI__LINUX_GENERIC_NETLINK_H diff --git a/include/uapi/linux/gsmmux.h b/include/uapi/linux/gsmmux.h index ab055d8cddef..101d3c469acb 100644 --- a/include/uapi/linux/gsmmux.h +++ b/include/uapi/linux/gsmmux.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_GSMMUX_H #define _LINUX_GSMMUX_H diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h index 57d1edb8efd9..c7d66755d212 100644 --- a/include/uapi/linux/gtp.h +++ b/include/uapi/linux/gtp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_GTP_H_ #define _UAPI_LINUX_GTP_H_ diff --git a/include/uapi/linux/hdlc/ioctl.h b/include/uapi/linux/hdlc/ioctl.h index 04bc0274a189..0fe4238e8246 100644 --- a/include/uapi/linux/hdlc/ioctl.h +++ b/include/uapi/linux/hdlc/ioctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __HDLC_IOCTL_H__ #define __HDLC_IOCTL_H__ diff --git a/include/uapi/linux/hdlcdrv.h b/include/uapi/linux/hdlcdrv.h index ffc79c0b44a8..9fe9499403a6 100644 --- a/include/uapi/linux/hdlcdrv.h +++ b/include/uapi/linux/hdlcdrv.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * hdlcdrv.h -- HDLC packet radio network driver. * The Linux soundcard driver for 1200 baud and 9600 baud packet radio diff --git a/include/uapi/linux/hdreg.h b/include/uapi/linux/hdreg.h index 29ee2873f4a8..aeee62ebf83c 100644 --- a/include/uapi/linux/hdreg.h +++ b/include/uapi/linux/hdreg.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_HDREG_H #define _LINUX_HDREG_H diff --git a/include/uapi/linux/hpet.h b/include/uapi/linux/hpet.h index 8af3c70abc8c..30e535644b43 100644 --- a/include/uapi/linux/hpet.h +++ b/include/uapi/linux/hpet.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__HPET__ #define _UAPI__HPET__ diff --git a/include/uapi/linux/hw_breakpoint.h b/include/uapi/linux/hw_breakpoint.h index 2b65efd19a46..965e4d8606d8 100644 --- a/include/uapi/linux/hw_breakpoint.h +++ b/include/uapi/linux/hw_breakpoint.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_HW_BREAKPOINT_H #define _UAPI_LINUX_HW_BREAKPOINT_H diff --git a/include/uapi/linux/icmpv6.h b/include/uapi/linux/icmpv6.h index 590beda78ea0..caf8dc019250 100644 --- a/include/uapi/linux/icmpv6.h +++ b/include/uapi/linux/icmpv6.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_ICMPV6_H #define _UAPI_LINUX_ICMPV6_H diff --git a/include/uapi/linux/if_addr.h b/include/uapi/linux/if_addr.h index 4318ab1635ce..2ef053d265de 100644 --- a/include/uapi/linux/if_addr.h +++ b/include/uapi/linux/if_addr.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_IF_ADDR_H #define __LINUX_IF_ADDR_H diff --git a/include/uapi/linux/if_addrlabel.h b/include/uapi/linux/if_addrlabel.h index 54580c298187..d1f5974c76e1 100644 --- a/include/uapi/linux/if_addrlabel.h +++ b/include/uapi/linux/if_addrlabel.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * if_addrlabel.h - netlink interface for address labels * diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 8d062c58d5cb..1f00f0cd6790 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_IF_LINK_H #define _UAPI_LINUX_IF_LINK_H diff --git a/include/uapi/linux/if_ltalk.h b/include/uapi/linux/if_ltalk.h index b92c1fb6ac16..fa61e776f598 100644 --- a/include/uapi/linux/if_ltalk.h +++ b/include/uapi/linux/if_ltalk.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__LINUX_LTALK_H #define _UAPI__LINUX_LTALK_H diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h index 4df96a7dd4fa..67b61d91d89b 100644 --- a/include/uapi/linux/if_packet.h +++ b/include/uapi/linux/if_packet.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_IF_PACKET_H #define __LINUX_IF_PACKET_H diff --git a/include/uapi/linux/if_phonet.h b/include/uapi/linux/if_phonet.h index f7ad9e24eb3d..9c22c969ec69 100644 --- a/include/uapi/linux/if_phonet.h +++ b/include/uapi/linux/if_phonet.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * File: if_phonet.h * diff --git a/include/uapi/linux/if_slip.h b/include/uapi/linux/if_slip.h index 1eb4e3a8397a..65937be53103 100644 --- a/include/uapi/linux/if_slip.h +++ b/include/uapi/linux/if_slip.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Swansea University Computer Society NET3 * diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 2e520883c054..383b850aeb88 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_IF_TUNNEL_H_ #define _UAPI_IF_TUNNEL_H_ diff --git a/include/uapi/linux/ife.h b/include/uapi/linux/ife.h index 2954da32e012..bdd953c67db1 100644 --- a/include/uapi/linux/ife.h +++ b/include/uapi/linux/ife.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __UAPI_IFE_H #define __UAPI_IFE_H diff --git a/include/uapi/linux/ila.h b/include/uapi/linux/ila.h index 948c0a91e11b..f54853288f99 100644 --- a/include/uapi/linux/ila.h +++ b/include/uapi/linux/ila.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* ila.h - ILA Interface */ #ifndef _UAPI_LINUX_ILA_H diff --git a/include/uapi/linux/in_route.h b/include/uapi/linux/in_route.h index b261b8c915f0..0cc2c23b47f8 100644 --- a/include/uapi/linux/in_route.h +++ b/include/uapi/linux/in_route.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_IN_ROUTE_H #define _LINUX_IN_ROUTE_H diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h index f52ff62bfabe..817d807e9481 100644 --- a/include/uapi/linux/inet_diag.h +++ b/include/uapi/linux/inet_diag.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_INET_DIAG_H_ #define _UAPI_INET_DIAG_H_ diff --git a/include/uapi/linux/inotify.h b/include/uapi/linux/inotify.h index e6bf35b2dd34..5474461683db 100644 --- a/include/uapi/linux/inotify.h +++ b/include/uapi/linux/inotify.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Inode based directory notification for Linux * diff --git a/include/uapi/linux/ioctl.h b/include/uapi/linux/ioctl.h index aa91eb3951ef..b292e8093b24 100644 --- a/include/uapi/linux/ioctl.h +++ b/include/uapi/linux/ioctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_IOCTL_H #define _LINUX_IOCTL_H diff --git a/include/uapi/linux/ip6_tunnel.h b/include/uapi/linux/ip6_tunnel.h index 425926c467d7..51f29308ac6d 100644 --- a/include/uapi/linux/ip6_tunnel.h +++ b/include/uapi/linux/ip6_tunnel.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _IP6_TUNNEL_H #define _IP6_TUNNEL_H diff --git a/include/uapi/linux/ip_vs.h b/include/uapi/linux/ip_vs.h index 22d69894bc92..1c916b2f89dc 100644 --- a/include/uapi/linux/ip_vs.h +++ b/include/uapi/linux/ip_vs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * IP Virtual Server * data structure and functionality definitions diff --git a/include/uapi/linux/ipc.h b/include/uapi/linux/ipc.h index de08dd46ddae..5995fc9d675e 100644 --- a/include/uapi/linux/ipc.h +++ b/include/uapi/linux/ipc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_IPC_H #define _UAPI_LINUX_IPC_H diff --git a/include/uapi/linux/ipsec.h b/include/uapi/linux/ipsec.h index d17a6302a0e9..50d8ee1791e2 100644 --- a/include/uapi/linux/ipsec.h +++ b/include/uapi/linux/ipsec.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_IPSEC_H #define _LINUX_IPSEC_H diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 2ae59178189d..b22a9c4e1b12 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_IPV6_H #define _UAPI_IPV6_H diff --git a/include/uapi/linux/ipx.h b/include/uapi/linux/ipx.h index 30f031db12f6..3168137adae8 100644 --- a/include/uapi/linux/ipx.h +++ b/include/uapi/linux/ipx.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _IPX_H_ #define _IPX_H_ #include /* for compatibility with glibc netipx/ipx.h */ diff --git a/include/uapi/linux/iso_fs.h b/include/uapi/linux/iso_fs.h index 4688ac4284e2..78b4ebcf8ab0 100644 --- a/include/uapi/linux/iso_fs.h +++ b/include/uapi/linux/iso_fs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ISOFS_FS_H #define _ISOFS_FS_H diff --git a/include/uapi/linux/kcmp.h b/include/uapi/linux/kcmp.h index 481e103da78e..ef1305010925 100644 --- a/include/uapi/linux/kcmp.h +++ b/include/uapi/linux/kcmp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_KCMP_H #define _UAPI_LINUX_KCMP_H diff --git a/include/uapi/linux/kcov.h b/include/uapi/linux/kcov.h index 574e22ec640d..33eabbb8ada1 100644 --- a/include/uapi/linux/kcov.h +++ b/include/uapi/linux/kcov.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_KCOV_IOCTLS_H #define _LINUX_KCOV_IOCTLS_H diff --git a/include/uapi/linux/kd.h b/include/uapi/linux/kd.h index 87b7cc439d7c..4616b31f84da 100644 --- a/include/uapi/linux/kd.h +++ b/include/uapi/linux/kd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_KD_H #define _UAPI_LINUX_KD_H #include diff --git a/include/uapi/linux/kdev_t.h b/include/uapi/linux/kdev_t.h index 0d881fa7eb9c..e1990f2e9777 100644 --- a/include/uapi/linux/kdev_t.h +++ b/include/uapi/linux/kdev_t.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_KDEV_T_H #define _UAPI_LINUX_KDEV_T_H #ifndef __KERNEL__ diff --git a/include/uapi/linux/kernel-page-flags.h b/include/uapi/linux/kernel-page-flags.h index 5da5f8751ce7..fa139841ec18 100644 --- a/include/uapi/linux/kernel-page-flags.h +++ b/include/uapi/linux/kernel-page-flags.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPILINUX_KERNEL_PAGE_FLAGS_H #define _UAPILINUX_KERNEL_PAGE_FLAGS_H diff --git a/include/uapi/linux/kernel.h b/include/uapi/linux/kernel.h index 466073f0ce46..0ff8f7477847 100644 --- a/include/uapi/linux/kernel.h +++ b/include/uapi/linux/kernel.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_KERNEL_H #define _UAPI_LINUX_KERNEL_H diff --git a/include/uapi/linux/kernelcapi.h b/include/uapi/linux/kernelcapi.h index 89bf40d36d2a..325a856e0e20 100644 --- a/include/uapi/linux/kernelcapi.h +++ b/include/uapi/linux/kernelcapi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * $Id: kernelcapi.h,v 1.8.6.2 2001/02/07 11:31:31 kai Exp $ * diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h index aae5ebf2022b..6d112868272d 100644 --- a/include/uapi/linux/kexec.h +++ b/include/uapi/linux/kexec.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPILINUX_KEXEC_H #define _UAPILINUX_KEXEC_H diff --git a/include/uapi/linux/keyboard.h b/include/uapi/linux/keyboard.h index 5a6849721ab6..ab4108c83186 100644 --- a/include/uapi/linux/keyboard.h +++ b/include/uapi/linux/keyboard.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__LINUX_KEYBOARD_H #define _UAPI__LINUX_KEYBOARD_H diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 838887587411..7e99999d6236 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_KVM_H #define __LINUX_KVM_H diff --git a/include/uapi/linux/kvm_para.h b/include/uapi/linux/kvm_para.h index fed506aeff62..dcf629dd2889 100644 --- a/include/uapi/linux/kvm_para.h +++ b/include/uapi/linux/kvm_para.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__LINUX_KVM_PARA_H #define _UAPI__LINUX_KVM_PARA_H diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h index b23c1914a182..d84ce5c1c9aa 100644 --- a/include/uapi/linux/l2tp.h +++ b/include/uapi/linux/l2tp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * L2TP-over-IP socket for L2TPv3. * diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h index 44b8a6bd5fe1..282875cf8056 100644 --- a/include/uapi/linux/libc-compat.h +++ b/include/uapi/linux/libc-compat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Compatibility interface for userspace libc header coordination: * diff --git a/include/uapi/linux/limits.h b/include/uapi/linux/limits.h index 2d0f94162fb3..c3547f07605c 100644 --- a/include/uapi/linux/limits.h +++ b/include/uapi/linux/limits.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_LIMITS_H #define _LINUX_LIMITS_H diff --git a/include/uapi/linux/lirc.h b/include/uapi/linux/lirc.h index 991ab4570b8e..c3aef4316fbf 100644 --- a/include/uapi/linux/lirc.h +++ b/include/uapi/linux/lirc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * lirc.h - linux infrared remote control header file * last modified 2010/07/13 by Jarod Wilson diff --git a/include/uapi/linux/lp.h b/include/uapi/linux/lp.h index a3406a51f196..dafcfe4e4834 100644 --- a/include/uapi/linux/lp.h +++ b/include/uapi/linux/lp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * usr/include/linux/lp.h c.1991-1992 James Wiegand * many modifications copyright (C) 1992 Michael K. Johnson diff --git a/include/uapi/linux/lwtunnel.h b/include/uapi/linux/lwtunnel.h index 7fdd19ca7511..de696ca12f2c 100644 --- a/include/uapi/linux/lwtunnel.h +++ b/include/uapi/linux/lwtunnel.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LWTUNNEL_H_ #define _UAPI_LWTUNNEL_H_ diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index e439565df838..aa50113ebe5b 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_MAGIC_H__ #define __LINUX_MAGIC_H__ diff --git a/include/uapi/linux/major.h b/include/uapi/linux/major.h index 19e195bee990..7e5fa8e15c43 100644 --- a/include/uapi/linux/major.h +++ b/include/uapi/linux/major.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_MAJOR_H #define _LINUX_MAJOR_H diff --git a/include/uapi/linux/matroxfb.h b/include/uapi/linux/matroxfb.h index 8c22a8938642..23e025b7e362 100644 --- a/include/uapi/linux/matroxfb.h +++ b/include/uapi/linux/matroxfb.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_MATROXFB_H__ #define __LINUX_MATROXFB_H__ diff --git a/include/uapi/linux/memfd.h b/include/uapi/linux/memfd.h index 7f3a722dbd72..015a4c0bbb47 100644 --- a/include/uapi/linux/memfd.h +++ b/include/uapi/linux/memfd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_MEMFD_H #define _UAPI_LINUX_MEMFD_H diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h index 2a4d89508fec..3354774af61e 100644 --- a/include/uapi/linux/mempolicy.h +++ b/include/uapi/linux/mempolicy.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * NUMA memory policies for Linux. * Copyright 2003,2004 Andi Kleen SuSE Labs diff --git a/include/uapi/linux/mii.h b/include/uapi/linux/mii.h index 15d8510cdae0..b5c2fdcf23fd 100644 --- a/include/uapi/linux/mii.h +++ b/include/uapi/linux/mii.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * linux/mii.h: definitions for MII-compatible transceivers * Originally drivers/net/sunhme.h. diff --git a/include/uapi/linux/minix_fs.h b/include/uapi/linux/minix_fs.h index 13fe09e0576a..95dbcb17eacd 100644 --- a/include/uapi/linux/minix_fs.h +++ b/include/uapi/linux/minix_fs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_MINIX_FS_H #define _LINUX_MINIX_FS_H diff --git a/include/uapi/linux/mman.h b/include/uapi/linux/mman.h index a937480d7cd3..bfd5938fede6 100644 --- a/include/uapi/linux/mman.h +++ b/include/uapi/linux/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_MMAN_H #define _UAPI_LINUX_MMAN_H diff --git a/include/uapi/linux/mmc/ioctl.h b/include/uapi/linux/mmc/ioctl.h index 700a55156eee..45f369dc0a42 100644 --- a/include/uapi/linux/mmc/ioctl.h +++ b/include/uapi/linux/mmc/ioctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef LINUX_MMC_IOCTL_H #define LINUX_MMC_IOCTL_H diff --git a/include/uapi/linux/module.h b/include/uapi/linux/module.h index 38da4258b12f..50d98ec5e866 100644 --- a/include/uapi/linux/module.h +++ b/include/uapi/linux/module.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_MODULE_H #define _UAPI_LINUX_MODULE_H diff --git a/include/uapi/linux/mpls.h b/include/uapi/linux/mpls.h index 77a19dfe3990..1ef5d6002a4a 100644 --- a/include/uapi/linux/mpls.h +++ b/include/uapi/linux/mpls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_MPLS_H #define _UAPI_MPLS_H diff --git a/include/uapi/linux/mroute.h b/include/uapi/linux/mroute.h index e8e5041dea8e..10f9ff9426a2 100644 --- a/include/uapi/linux/mroute.h +++ b/include/uapi/linux/mroute.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__LINUX_MROUTE_H #define _UAPI__LINUX_MROUTE_H diff --git a/include/uapi/linux/mroute6.h b/include/uapi/linux/mroute6.h index e4746816c855..9999cc006390 100644 --- a/include/uapi/linux/mroute6.h +++ b/include/uapi/linux/mroute6.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__LINUX_MROUTE6_H #define _UAPI__LINUX_MROUTE6_H diff --git a/include/uapi/linux/msdos_fs.h b/include/uapi/linux/msdos_fs.h index e956704f5fb1..a45d0754102e 100644 --- a/include/uapi/linux/msdos_fs.h +++ b/include/uapi/linux/msdos_fs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_MSDOS_FS_H #define _UAPI_LINUX_MSDOS_FS_H diff --git a/include/uapi/linux/msg.h b/include/uapi/linux/msg.h index f51c8001dbe5..5d5ab81dc9be 100644 --- a/include/uapi/linux/msg.h +++ b/include/uapi/linux/msg.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_MSG_H #define _UAPI_LINUX_MSG_H diff --git a/include/uapi/linux/mtio.h b/include/uapi/linux/mtio.h index 18543e2db06f..a1191fecc592 100644 --- a/include/uapi/linux/mtio.h +++ b/include/uapi/linux/mtio.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * linux/mtio.h header file for Linux. Written by H. Bergman * diff --git a/include/uapi/linux/ncp.h b/include/uapi/linux/ncp.h index 99f0adeeb3f3..ca6f3d42c88f 100644 --- a/include/uapi/linux/ncp.h +++ b/include/uapi/linux/ncp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * ncp.h * diff --git a/include/uapi/linux/ncp_fs.h b/include/uapi/linux/ncp_fs.h index e13eefef0653..e76a44229d2f 100644 --- a/include/uapi/linux/ncp_fs.h +++ b/include/uapi/linux/ncp_fs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * ncp_fs.h * diff --git a/include/uapi/linux/ncp_mount.h b/include/uapi/linux/ncp_mount.h index dfcbea2d889f..9bdbcd68c329 100644 --- a/include/uapi/linux/ncp_mount.h +++ b/include/uapi/linux/ncp_mount.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * ncp_mount.h * diff --git a/include/uapi/linux/ncp_no.h b/include/uapi/linux/ncp_no.h index cddaa48fb182..654d7c7f5d92 100644 --- a/include/uapi/linux/ncp_no.h +++ b/include/uapi/linux/ncp_no.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _NCP_NO #define _NCP_NO diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index 3199d28980b3..904db6148476 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_NEIGHBOUR_H #define __LINUX_NEIGHBOUR_H diff --git a/include/uapi/linux/net_dropmon.h b/include/uapi/linux/net_dropmon.h index 2a739462caeb..5edbd0a675fd 100644 --- a/include/uapi/linux/net_dropmon.h +++ b/include/uapi/linux/net_dropmon.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __NET_DROPMON_H #define __NET_DROPMON_H diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index 3d421d912193..4fe104b2411f 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Userspace API for hardware time stamping of network packets * diff --git a/include/uapi/linux/netconf.h b/include/uapi/linux/netconf.h index 7e5f0f3e31bf..c84fcdfca862 100644 --- a/include/uapi/linux/netconf.h +++ b/include/uapi/linux/netconf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_NETCONF_H_ #define _UAPI_LINUX_NETCONF_H_ diff --git a/include/uapi/linux/netfilter.h b/include/uapi/linux/netfilter.h index c111a91adcc0..cca10e767cd8 100644 --- a/include/uapi/linux/netfilter.h +++ b/include/uapi/linux/netfilter.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__LINUX_NETFILTER_H #define _UAPI__LINUX_NETFILTER_H diff --git a/include/uapi/linux/netfilter/ipset/ip_set_bitmap.h b/include/uapi/linux/netfilter/ipset/ip_set_bitmap.h index fd5024d26269..c6b146db9693 100644 --- a/include/uapi/linux/netfilter/ipset/ip_set_bitmap.h +++ b/include/uapi/linux/netfilter/ipset/ip_set_bitmap.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__IP_SET_BITMAP_H #define _UAPI__IP_SET_BITMAP_H diff --git a/include/uapi/linux/netfilter/ipset/ip_set_hash.h b/include/uapi/linux/netfilter/ipset/ip_set_hash.h index 82deeb883ac4..880749ace798 100644 --- a/include/uapi/linux/netfilter/ipset/ip_set_hash.h +++ b/include/uapi/linux/netfilter/ipset/ip_set_hash.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__IP_SET_HASH_H #define _UAPI__IP_SET_HASH_H diff --git a/include/uapi/linux/netfilter/ipset/ip_set_list.h b/include/uapi/linux/netfilter/ipset/ip_set_list.h index 84d430368266..e6d7feb522cd 100644 --- a/include/uapi/linux/netfilter/ipset/ip_set_list.h +++ b/include/uapi/linux/netfilter/ipset/ip_set_list.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__IP_SET_LIST_H #define _UAPI__IP_SET_LIST_H diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h index dc947e59d03a..3fea7709a441 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_common.h +++ b/include/uapi/linux/netfilter/nf_conntrack_common.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_NF_CONNTRACK_COMMON_H #define _UAPI_NF_CONNTRACK_COMMON_H /* Connection state tracking for netfilter. This is separated from, diff --git a/include/uapi/linux/netfilter/nf_conntrack_ftp.h b/include/uapi/linux/netfilter/nf_conntrack_ftp.h index 1030315a41b5..8eb6b9ef2071 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_ftp.h +++ b/include/uapi/linux/netfilter/nf_conntrack_ftp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_NF_CONNTRACK_FTP_H #define _UAPI_NF_CONNTRACK_FTP_H /* FTP tracking. */ diff --git a/include/uapi/linux/netfilter/nf_conntrack_sctp.h b/include/uapi/linux/netfilter/nf_conntrack_sctp.h index 2cbc366c3fb4..edc6ddab0de6 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_sctp.h +++ b/include/uapi/linux/netfilter/nf_conntrack_sctp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_NF_CONNTRACK_SCTP_H #define _UAPI_NF_CONNTRACK_SCTP_H /* SCTP tracking. */ diff --git a/include/uapi/linux/netfilter/nf_conntrack_tcp.h b/include/uapi/linux/netfilter/nf_conntrack_tcp.h index ef9f80f0f529..74b91151d494 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_tcp.h +++ b/include/uapi/linux/netfilter/nf_conntrack_tcp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_NF_CONNTRACK_TCP_H #define _UAPI_NF_CONNTRACK_TCP_H /* TCP tracking. */ diff --git a/include/uapi/linux/netfilter/nf_conntrack_tuple_common.h b/include/uapi/linux/netfilter/nf_conntrack_tuple_common.h index 526b42496b78..64390fac6f7e 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_tuple_common.h +++ b/include/uapi/linux/netfilter/nf_conntrack_tuple_common.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _NF_CONNTRACK_TUPLE_COMMON_H #define _NF_CONNTRACK_TUPLE_COMMON_H diff --git a/include/uapi/linux/netfilter/nf_log.h b/include/uapi/linux/netfilter/nf_log.h index d0b5fa91ff54..2ae00932d3d2 100644 --- a/include/uapi/linux/netfilter/nf_log.h +++ b/include/uapi/linux/netfilter/nf_log.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _NETFILTER_NF_LOG_H #define _NETFILTER_NF_LOG_H diff --git a/include/uapi/linux/netfilter/nf_nat.h b/include/uapi/linux/netfilter/nf_nat.h index 0880781ad7b6..a33000da7229 100644 --- a/include/uapi/linux/netfilter/nf_nat.h +++ b/include/uapi/linux/netfilter/nf_nat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _NETFILTER_NF_NAT_H #define _NETFILTER_NF_NAT_H diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 871afa4871bf..a3ee277b17a1 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_NF_TABLES_H #define _LINUX_NF_TABLES_H diff --git a/include/uapi/linux/netfilter/nf_tables_compat.h b/include/uapi/linux/netfilter/nf_tables_compat.h index 8310f5f76551..0e2b9fcb71b7 100644 --- a/include/uapi/linux/netfilter/nf_tables_compat.h +++ b/include/uapi/linux/netfilter/nf_tables_compat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _NFT_COMPAT_NFNETLINK_H_ #define _NFT_COMPAT_NFNETLINK_H_ diff --git a/include/uapi/linux/netfilter/nfnetlink.h b/include/uapi/linux/netfilter/nfnetlink.h index a09906a30d77..5bc960f220b3 100644 --- a/include/uapi/linux/netfilter/nfnetlink.h +++ b/include/uapi/linux/netfilter/nfnetlink.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_NFNETLINK_H #define _UAPI_NFNETLINK_H #include diff --git a/include/uapi/linux/netfilter/nfnetlink_acct.h b/include/uapi/linux/netfilter/nfnetlink_acct.h index 36047ec70f37..7cb66d3218fc 100644 --- a/include/uapi/linux/netfilter/nfnetlink_acct.h +++ b/include/uapi/linux/netfilter/nfnetlink_acct.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_NFNL_ACCT_H_ #define _UAPI_NFNL_ACCT_H_ diff --git a/include/uapi/linux/netfilter/nfnetlink_compat.h b/include/uapi/linux/netfilter/nfnetlink_compat.h index ffb95036bbd4..93bcdccef81d 100644 --- a/include/uapi/linux/netfilter/nfnetlink_compat.h +++ b/include/uapi/linux/netfilter/nfnetlink_compat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _NFNETLINK_COMPAT_H #define _NFNETLINK_COMPAT_H diff --git a/include/uapi/linux/netfilter/nfnetlink_conntrack.h b/include/uapi/linux/netfilter/nfnetlink_conntrack.h index 6deb8867c5fc..7397e022ce6e 100644 --- a/include/uapi/linux/netfilter/nfnetlink_conntrack.h +++ b/include/uapi/linux/netfilter/nfnetlink_conntrack.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _IPCONNTRACK_NETLINK_H #define _IPCONNTRACK_NETLINK_H #include diff --git a/include/uapi/linux/netfilter/nfnetlink_cthelper.h b/include/uapi/linux/netfilter/nfnetlink_cthelper.h index 33659f6fad3e..a13137afc429 100644 --- a/include/uapi/linux/netfilter/nfnetlink_cthelper.h +++ b/include/uapi/linux/netfilter/nfnetlink_cthelper.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _NFNL_CTHELPER_H_ #define _NFNL_CTHELPER_H_ diff --git a/include/uapi/linux/netfilter/nfnetlink_cttimeout.h b/include/uapi/linux/netfilter/nfnetlink_cttimeout.h index f2c10dc140d6..6b20fb22717b 100644 --- a/include/uapi/linux/netfilter/nfnetlink_cttimeout.h +++ b/include/uapi/linux/netfilter/nfnetlink_cttimeout.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _CTTIMEOUT_NETLINK_H #define _CTTIMEOUT_NETLINK_H #include diff --git a/include/uapi/linux/netfilter/nfnetlink_log.h b/include/uapi/linux/netfilter/nfnetlink_log.h index fb21f0c717a1..20983cb195a0 100644 --- a/include/uapi/linux/netfilter/nfnetlink_log.h +++ b/include/uapi/linux/netfilter/nfnetlink_log.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _NFNETLINK_LOG_H #define _NFNETLINK_LOG_H diff --git a/include/uapi/linux/netfilter/nfnetlink_queue.h b/include/uapi/linux/netfilter/nfnetlink_queue.h index d42f0396fe30..bcb2cb5d40b9 100644 --- a/include/uapi/linux/netfilter/nfnetlink_queue.h +++ b/include/uapi/linux/netfilter/nfnetlink_queue.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _NFNETLINK_QUEUE_H #define _NFNETLINK_QUEUE_H diff --git a/include/uapi/linux/netfilter/x_tables.h b/include/uapi/linux/netfilter/x_tables.h index c36969b91533..a8283f7dbc51 100644 --- a/include/uapi/linux/netfilter/x_tables.h +++ b/include/uapi/linux/netfilter/x_tables.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_X_TABLES_H #define _UAPI_X_TABLES_H #include diff --git a/include/uapi/linux/netfilter/xt_CLASSIFY.h b/include/uapi/linux/netfilter/xt_CLASSIFY.h index a813bf14dd63..fe059a98c1d3 100644 --- a/include/uapi/linux/netfilter/xt_CLASSIFY.h +++ b/include/uapi/linux/netfilter/xt_CLASSIFY.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_CLASSIFY_H #define _XT_CLASSIFY_H diff --git a/include/uapi/linux/netfilter/xt_CONNMARK.h b/include/uapi/linux/netfilter/xt_CONNMARK.h index 2f2e48ec8023..36cc956ead1a 100644 --- a/include/uapi/linux/netfilter/xt_CONNMARK.h +++ b/include/uapi/linux/netfilter/xt_CONNMARK.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_CONNMARK_H_target #define _XT_CONNMARK_H_target diff --git a/include/uapi/linux/netfilter/xt_CONNSECMARK.h b/include/uapi/linux/netfilter/xt_CONNSECMARK.h index b973ff80fa1e..ca078bb3c584 100644 --- a/include/uapi/linux/netfilter/xt_CONNSECMARK.h +++ b/include/uapi/linux/netfilter/xt_CONNSECMARK.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_CONNSECMARK_H_target #define _XT_CONNSECMARK_H_target diff --git a/include/uapi/linux/netfilter/xt_CT.h b/include/uapi/linux/netfilter/xt_CT.h index 9e520418b858..868fa08e1fbb 100644 --- a/include/uapi/linux/netfilter/xt_CT.h +++ b/include/uapi/linux/netfilter/xt_CT.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_CT_H #define _XT_CT_H diff --git a/include/uapi/linux/netfilter/xt_HMARK.h b/include/uapi/linux/netfilter/xt_HMARK.h index 3fb48c8d8d78..2d4b751a7115 100644 --- a/include/uapi/linux/netfilter/xt_HMARK.h +++ b/include/uapi/linux/netfilter/xt_HMARK.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef XT_HMARK_H_ #define XT_HMARK_H_ diff --git a/include/uapi/linux/netfilter/xt_LED.h b/include/uapi/linux/netfilter/xt_LED.h index f5509e7524d3..4fe0f1395807 100644 --- a/include/uapi/linux/netfilter/xt_LED.h +++ b/include/uapi/linux/netfilter/xt_LED.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_LED_H #define _XT_LED_H diff --git a/include/uapi/linux/netfilter/xt_LOG.h b/include/uapi/linux/netfilter/xt_LOG.h index cac079095305..167d4ddd2476 100644 --- a/include/uapi/linux/netfilter/xt_LOG.h +++ b/include/uapi/linux/netfilter/xt_LOG.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_LOG_H #define _XT_LOG_H diff --git a/include/uapi/linux/netfilter/xt_MARK.h b/include/uapi/linux/netfilter/xt_MARK.h index 41c456deba22..f1fe2b4be933 100644 --- a/include/uapi/linux/netfilter/xt_MARK.h +++ b/include/uapi/linux/netfilter/xt_MARK.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_MARK_H_target #define _XT_MARK_H_target diff --git a/include/uapi/linux/netfilter/xt_NFLOG.h b/include/uapi/linux/netfilter/xt_NFLOG.h index f33070730fc8..517809771909 100644 --- a/include/uapi/linux/netfilter/xt_NFLOG.h +++ b/include/uapi/linux/netfilter/xt_NFLOG.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_NFLOG_TARGET #define _XT_NFLOG_TARGET diff --git a/include/uapi/linux/netfilter/xt_RATEEST.h b/include/uapi/linux/netfilter/xt_RATEEST.h index ec1b57047e03..2b87a71e6266 100644 --- a/include/uapi/linux/netfilter/xt_RATEEST.h +++ b/include/uapi/linux/netfilter/xt_RATEEST.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_RATEEST_TARGET_H #define _XT_RATEEST_TARGET_H diff --git a/include/uapi/linux/netfilter/xt_SECMARK.h b/include/uapi/linux/netfilter/xt_SECMARK.h index 989092bd6274..1f2a708413f5 100644 --- a/include/uapi/linux/netfilter/xt_SECMARK.h +++ b/include/uapi/linux/netfilter/xt_SECMARK.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_SECMARK_H_target #define _XT_SECMARK_H_target diff --git a/include/uapi/linux/netfilter/xt_SYNPROXY.h b/include/uapi/linux/netfilter/xt_SYNPROXY.h index ca67e61d2a61..ea5eba15d4c1 100644 --- a/include/uapi/linux/netfilter/xt_SYNPROXY.h +++ b/include/uapi/linux/netfilter/xt_SYNPROXY.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_SYNPROXY_H #define _XT_SYNPROXY_H diff --git a/include/uapi/linux/netfilter/xt_TCPMSS.h b/include/uapi/linux/netfilter/xt_TCPMSS.h index 9a6960afc134..65ea6c9dab4b 100644 --- a/include/uapi/linux/netfilter/xt_TCPMSS.h +++ b/include/uapi/linux/netfilter/xt_TCPMSS.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_TCPMSS_H #define _XT_TCPMSS_H diff --git a/include/uapi/linux/netfilter/xt_TCPOPTSTRIP.h b/include/uapi/linux/netfilter/xt_TCPOPTSTRIP.h index 7157318499c2..6bd51cd6f8da 100644 --- a/include/uapi/linux/netfilter/xt_TCPOPTSTRIP.h +++ b/include/uapi/linux/netfilter/xt_TCPOPTSTRIP.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_TCPOPTSTRIP_H #define _XT_TCPOPTSTRIP_H diff --git a/include/uapi/linux/netfilter/xt_TEE.h b/include/uapi/linux/netfilter/xt_TEE.h index 01092023404b..eb854917f828 100644 --- a/include/uapi/linux/netfilter/xt_TEE.h +++ b/include/uapi/linux/netfilter/xt_TEE.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_TEE_TARGET_H #define _XT_TEE_TARGET_H diff --git a/include/uapi/linux/netfilter/xt_TPROXY.h b/include/uapi/linux/netfilter/xt_TPROXY.h index 8d693eefdc1f..348957b02a82 100644 --- a/include/uapi/linux/netfilter/xt_TPROXY.h +++ b/include/uapi/linux/netfilter/xt_TPROXY.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_TPROXY_H #define _XT_TPROXY_H diff --git a/include/uapi/linux/netfilter/xt_addrtype.h b/include/uapi/linux/netfilter/xt_addrtype.h index b156baa9d55e..2102dff74c31 100644 --- a/include/uapi/linux/netfilter/xt_addrtype.h +++ b/include/uapi/linux/netfilter/xt_addrtype.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_ADDRTYPE_H #define _XT_ADDRTYPE_H diff --git a/include/uapi/linux/netfilter/xt_bpf.h b/include/uapi/linux/netfilter/xt_bpf.h index da161b56c79e..a05adda26d3e 100644 --- a/include/uapi/linux/netfilter/xt_bpf.h +++ b/include/uapi/linux/netfilter/xt_bpf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_BPF_H #define _XT_BPF_H diff --git a/include/uapi/linux/netfilter/xt_cgroup.h b/include/uapi/linux/netfilter/xt_cgroup.h index 1e4b37b93bef..e96dfa1b34f7 100644 --- a/include/uapi/linux/netfilter/xt_cgroup.h +++ b/include/uapi/linux/netfilter/xt_cgroup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_XT_CGROUP_H #define _UAPI_XT_CGROUP_H diff --git a/include/uapi/linux/netfilter/xt_cluster.h b/include/uapi/linux/netfilter/xt_cluster.h index 9b883c8fbf54..ed8e0561f99c 100644 --- a/include/uapi/linux/netfilter/xt_cluster.h +++ b/include/uapi/linux/netfilter/xt_cluster.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_CLUSTER_MATCH_H #define _XT_CLUSTER_MATCH_H diff --git a/include/uapi/linux/netfilter/xt_comment.h b/include/uapi/linux/netfilter/xt_comment.h index 0ea5e79f5bd7..85d284082542 100644 --- a/include/uapi/linux/netfilter/xt_comment.h +++ b/include/uapi/linux/netfilter/xt_comment.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_COMMENT_H #define _XT_COMMENT_H diff --git a/include/uapi/linux/netfilter/xt_connbytes.h b/include/uapi/linux/netfilter/xt_connbytes.h index f1d6c15bd9e3..0bae507db23e 100644 --- a/include/uapi/linux/netfilter/xt_connbytes.h +++ b/include/uapi/linux/netfilter/xt_connbytes.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_CONNBYTES_H #define _XT_CONNBYTES_H diff --git a/include/uapi/linux/netfilter/xt_connlabel.h b/include/uapi/linux/netfilter/xt_connlabel.h index c4bc9ee9b330..2312f0ec07b2 100644 --- a/include/uapi/linux/netfilter/xt_connlabel.h +++ b/include/uapi/linux/netfilter/xt_connlabel.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include #define XT_CONNLABEL_MAXBIT 127 diff --git a/include/uapi/linux/netfilter/xt_connlimit.h b/include/uapi/linux/netfilter/xt_connlimit.h index f1656096121e..07e5e9d47882 100644 --- a/include/uapi/linux/netfilter/xt_connlimit.h +++ b/include/uapi/linux/netfilter/xt_connlimit.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_CONNLIMIT_H #define _XT_CONNLIMIT_H diff --git a/include/uapi/linux/netfilter/xt_cpu.h b/include/uapi/linux/netfilter/xt_cpu.h index 93c7f11d8f42..b442e1f6f598 100644 --- a/include/uapi/linux/netfilter/xt_cpu.h +++ b/include/uapi/linux/netfilter/xt_cpu.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_CPU_H #define _XT_CPU_H diff --git a/include/uapi/linux/netfilter/xt_dccp.h b/include/uapi/linux/netfilter/xt_dccp.h index a579e1b6f040..564e61c5703f 100644 --- a/include/uapi/linux/netfilter/xt_dccp.h +++ b/include/uapi/linux/netfilter/xt_dccp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_DCCP_H_ #define _XT_DCCP_H_ diff --git a/include/uapi/linux/netfilter/xt_devgroup.h b/include/uapi/linux/netfilter/xt_devgroup.h index 1babde0ec900..79ed351a4525 100644 --- a/include/uapi/linux/netfilter/xt_devgroup.h +++ b/include/uapi/linux/netfilter/xt_devgroup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_DEVGROUP_H #define _XT_DEVGROUP_H diff --git a/include/uapi/linux/netfilter/xt_esp.h b/include/uapi/linux/netfilter/xt_esp.h index ee6882408000..fa57a208f684 100644 --- a/include/uapi/linux/netfilter/xt_esp.h +++ b/include/uapi/linux/netfilter/xt_esp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_ESP_H #define _XT_ESP_H diff --git a/include/uapi/linux/netfilter/xt_hashlimit.h b/include/uapi/linux/netfilter/xt_hashlimit.h index aa98573248b1..721a8de6c5b3 100644 --- a/include/uapi/linux/netfilter/xt_hashlimit.h +++ b/include/uapi/linux/netfilter/xt_hashlimit.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_XT_HASHLIMIT_H #define _UAPI_XT_HASHLIMIT_H diff --git a/include/uapi/linux/netfilter/xt_helper.h b/include/uapi/linux/netfilter/xt_helper.h index 6b42763f999d..53aa1458d6b7 100644 --- a/include/uapi/linux/netfilter/xt_helper.h +++ b/include/uapi/linux/netfilter/xt_helper.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_HELPER_H #define _XT_HELPER_H diff --git a/include/uapi/linux/netfilter/xt_ipcomp.h b/include/uapi/linux/netfilter/xt_ipcomp.h index 45c7e40eb8e1..69b12e76eaf7 100644 --- a/include/uapi/linux/netfilter/xt_ipcomp.h +++ b/include/uapi/linux/netfilter/xt_ipcomp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_IPCOMP_H #define _XT_IPCOMP_H diff --git a/include/uapi/linux/netfilter/xt_iprange.h b/include/uapi/linux/netfilter/xt_iprange.h index 25fd7cf851f0..551bec7a22fc 100644 --- a/include/uapi/linux/netfilter/xt_iprange.h +++ b/include/uapi/linux/netfilter/xt_iprange.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_NETFILTER_XT_IPRANGE_H #define _LINUX_NETFILTER_XT_IPRANGE_H 1 diff --git a/include/uapi/linux/netfilter/xt_ipvs.h b/include/uapi/linux/netfilter/xt_ipvs.h index e03b9c31a39d..925c76996dc4 100644 --- a/include/uapi/linux/netfilter/xt_ipvs.h +++ b/include/uapi/linux/netfilter/xt_ipvs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_IPVS_H #define _XT_IPVS_H diff --git a/include/uapi/linux/netfilter/xt_l2tp.h b/include/uapi/linux/netfilter/xt_l2tp.h index 7dccfa0acbfa..990b52a49fab 100644 --- a/include/uapi/linux/netfilter/xt_l2tp.h +++ b/include/uapi/linux/netfilter/xt_l2tp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_NETFILTER_XT_L2TP_H #define _LINUX_NETFILTER_XT_L2TP_H diff --git a/include/uapi/linux/netfilter/xt_length.h b/include/uapi/linux/netfilter/xt_length.h index b82ed7c4b1e0..513f653e2f6b 100644 --- a/include/uapi/linux/netfilter/xt_length.h +++ b/include/uapi/linux/netfilter/xt_length.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_LENGTH_H #define _XT_LENGTH_H diff --git a/include/uapi/linux/netfilter/xt_limit.h b/include/uapi/linux/netfilter/xt_limit.h index bb47fc4d2ade..1d6e4ce9a646 100644 --- a/include/uapi/linux/netfilter/xt_limit.h +++ b/include/uapi/linux/netfilter/xt_limit.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_RATE_H #define _XT_RATE_H diff --git a/include/uapi/linux/netfilter/xt_mac.h b/include/uapi/linux/netfilter/xt_mac.h index 9a19a08a9181..c4dd5185cfc4 100644 --- a/include/uapi/linux/netfilter/xt_mac.h +++ b/include/uapi/linux/netfilter/xt_mac.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_MAC_H #define _XT_MAC_H diff --git a/include/uapi/linux/netfilter/xt_mark.h b/include/uapi/linux/netfilter/xt_mark.h index ecadc40d5cde..9d0526ced8f0 100644 --- a/include/uapi/linux/netfilter/xt_mark.h +++ b/include/uapi/linux/netfilter/xt_mark.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_MARK_H #define _XT_MARK_H diff --git a/include/uapi/linux/netfilter/xt_multiport.h b/include/uapi/linux/netfilter/xt_multiport.h index 5b7e72dfffc5..ffecf696454b 100644 --- a/include/uapi/linux/netfilter/xt_multiport.h +++ b/include/uapi/linux/netfilter/xt_multiport.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_MULTIPORT_H #define _XT_MULTIPORT_H diff --git a/include/uapi/linux/netfilter/xt_nfacct.h b/include/uapi/linux/netfilter/xt_nfacct.h index 3e19c8a86576..5c8a4d760ee3 100644 --- a/include/uapi/linux/netfilter/xt_nfacct.h +++ b/include/uapi/linux/netfilter/xt_nfacct.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_NFACCT_MATCH_H #define _XT_NFACCT_MATCH_H diff --git a/include/uapi/linux/netfilter/xt_owner.h b/include/uapi/linux/netfilter/xt_owner.h index 2081761714b5..fa3ad84957d5 100644 --- a/include/uapi/linux/netfilter/xt_owner.h +++ b/include/uapi/linux/netfilter/xt_owner.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_OWNER_MATCH_H #define _XT_OWNER_MATCH_H diff --git a/include/uapi/linux/netfilter/xt_physdev.h b/include/uapi/linux/netfilter/xt_physdev.h index ccdde87da214..06ae115e9a91 100644 --- a/include/uapi/linux/netfilter/xt_physdev.h +++ b/include/uapi/linux/netfilter/xt_physdev.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_XT_PHYSDEV_H #define _UAPI_XT_PHYSDEV_H diff --git a/include/uapi/linux/netfilter/xt_pkttype.h b/include/uapi/linux/netfilter/xt_pkttype.h index f265cf52faea..c31f29d2e723 100644 --- a/include/uapi/linux/netfilter/xt_pkttype.h +++ b/include/uapi/linux/netfilter/xt_pkttype.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_PKTTYPE_H #define _XT_PKTTYPE_H diff --git a/include/uapi/linux/netfilter/xt_policy.h b/include/uapi/linux/netfilter/xt_policy.h index d8a9800dce61..323bfa3074c5 100644 --- a/include/uapi/linux/netfilter/xt_policy.h +++ b/include/uapi/linux/netfilter/xt_policy.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_POLICY_H #define _XT_POLICY_H diff --git a/include/uapi/linux/netfilter/xt_quota.h b/include/uapi/linux/netfilter/xt_quota.h index 9314723f39ca..f3ba5d9e58b6 100644 --- a/include/uapi/linux/netfilter/xt_quota.h +++ b/include/uapi/linux/netfilter/xt_quota.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_QUOTA_H #define _XT_QUOTA_H diff --git a/include/uapi/linux/netfilter/xt_rateest.h b/include/uapi/linux/netfilter/xt_rateest.h index 13fe50d4e4b3..52a37bdc1837 100644 --- a/include/uapi/linux/netfilter/xt_rateest.h +++ b/include/uapi/linux/netfilter/xt_rateest.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_RATEEST_MATCH_H #define _XT_RATEEST_MATCH_H diff --git a/include/uapi/linux/netfilter/xt_realm.h b/include/uapi/linux/netfilter/xt_realm.h index d4a82ee56a02..252aa9f79cf8 100644 --- a/include/uapi/linux/netfilter/xt_realm.h +++ b/include/uapi/linux/netfilter/xt_realm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_REALM_H #define _XT_REALM_H diff --git a/include/uapi/linux/netfilter/xt_recent.h b/include/uapi/linux/netfilter/xt_recent.h index 955d562031cc..e2c33996a802 100644 --- a/include/uapi/linux/netfilter/xt_recent.h +++ b/include/uapi/linux/netfilter/xt_recent.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_NETFILTER_XT_RECENT_H #define _LINUX_NETFILTER_XT_RECENT_H 1 diff --git a/include/uapi/linux/netfilter/xt_rpfilter.h b/include/uapi/linux/netfilter/xt_rpfilter.h index 8358d4f71952..9b3d0f25a39c 100644 --- a/include/uapi/linux/netfilter/xt_rpfilter.h +++ b/include/uapi/linux/netfilter/xt_rpfilter.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_RPATH_H #define _XT_RPATH_H diff --git a/include/uapi/linux/netfilter/xt_sctp.h b/include/uapi/linux/netfilter/xt_sctp.h index 58ffcfb7978e..4bc6d1a08781 100644 --- a/include/uapi/linux/netfilter/xt_sctp.h +++ b/include/uapi/linux/netfilter/xt_sctp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_SCTP_H_ #define _XT_SCTP_H_ diff --git a/include/uapi/linux/netfilter/xt_set.h b/include/uapi/linux/netfilter/xt_set.h index d4e02348384c..8c1ca66c8a06 100644 --- a/include/uapi/linux/netfilter/xt_set.h +++ b/include/uapi/linux/netfilter/xt_set.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_SET_H #define _XT_SET_H diff --git a/include/uapi/linux/netfilter/xt_socket.h b/include/uapi/linux/netfilter/xt_socket.h index 87644f832494..a7bdc9d882b0 100644 --- a/include/uapi/linux/netfilter/xt_socket.h +++ b/include/uapi/linux/netfilter/xt_socket.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_SOCKET_H #define _XT_SOCKET_H diff --git a/include/uapi/linux/netfilter/xt_state.h b/include/uapi/linux/netfilter/xt_state.h index 7b32de886613..fe5670ef6aad 100644 --- a/include/uapi/linux/netfilter/xt_state.h +++ b/include/uapi/linux/netfilter/xt_state.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_STATE_H #define _XT_STATE_H diff --git a/include/uapi/linux/netfilter/xt_statistic.h b/include/uapi/linux/netfilter/xt_statistic.h index 4e983ef0c968..bbce6fcb26e3 100644 --- a/include/uapi/linux/netfilter/xt_statistic.h +++ b/include/uapi/linux/netfilter/xt_statistic.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_STATISTIC_H #define _XT_STATISTIC_H diff --git a/include/uapi/linux/netfilter/xt_string.h b/include/uapi/linux/netfilter/xt_string.h index 235347c02eab..bedb015d54dd 100644 --- a/include/uapi/linux/netfilter/xt_string.h +++ b/include/uapi/linux/netfilter/xt_string.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_STRING_H #define _XT_STRING_H diff --git a/include/uapi/linux/netfilter/xt_tcpmss.h b/include/uapi/linux/netfilter/xt_tcpmss.h index fbac56b9e667..2268f58b4dec 100644 --- a/include/uapi/linux/netfilter/xt_tcpmss.h +++ b/include/uapi/linux/netfilter/xt_tcpmss.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_TCPMSS_MATCH_H #define _XT_TCPMSS_MATCH_H diff --git a/include/uapi/linux/netfilter/xt_tcpudp.h b/include/uapi/linux/netfilter/xt_tcpudp.h index 38aa7b399021..658c16999819 100644 --- a/include/uapi/linux/netfilter/xt_tcpudp.h +++ b/include/uapi/linux/netfilter/xt_tcpudp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_TCPUDP_H #define _XT_TCPUDP_H diff --git a/include/uapi/linux/netfilter/xt_time.h b/include/uapi/linux/netfilter/xt_time.h index 095886019396..7f707c7ec858 100644 --- a/include/uapi/linux/netfilter/xt_time.h +++ b/include/uapi/linux/netfilter/xt_time.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_TIME_H #define _XT_TIME_H 1 diff --git a/include/uapi/linux/netfilter/xt_u32.h b/include/uapi/linux/netfilter/xt_u32.h index 04d1bfea03c2..a88505ca72f8 100644 --- a/include/uapi/linux/netfilter/xt_u32.h +++ b/include/uapi/linux/netfilter/xt_u32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _XT_U32_H #define _XT_U32_H 1 diff --git a/include/uapi/linux/netfilter_arp/arp_tables.h b/include/uapi/linux/netfilter_arp/arp_tables.h index ece3ad4eecda..a2a0927d9bd6 100644 --- a/include/uapi/linux/netfilter_arp/arp_tables.h +++ b/include/uapi/linux/netfilter_arp/arp_tables.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Format of an ARP firewall descriptor * diff --git a/include/uapi/linux/netfilter_arp/arpt_mangle.h b/include/uapi/linux/netfilter_arp/arpt_mangle.h index 8c2b16a1f5a0..60135d5cc223 100644 --- a/include/uapi/linux/netfilter_arp/arpt_mangle.h +++ b/include/uapi/linux/netfilter_arp/arpt_mangle.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ARPT_MANGLE_H #define _ARPT_MANGLE_H #include diff --git a/include/uapi/linux/netfilter_bridge.h b/include/uapi/linux/netfilter_bridge.h index 514519b47651..12fb77633f83 100644 --- a/include/uapi/linux/netfilter_bridge.h +++ b/include/uapi/linux/netfilter_bridge.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__LINUX_BRIDGE_NETFILTER_H #define _UAPI__LINUX_BRIDGE_NETFILTER_H diff --git a/include/uapi/linux/netfilter_bridge/ebt_802_3.h b/include/uapi/linux/netfilter_bridge/ebt_802_3.h index f37522aade24..03463e4b0246 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_802_3.h +++ b/include/uapi/linux/netfilter_bridge/ebt_802_3.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__LINUX_BRIDGE_EBT_802_3_H #define _UAPI__LINUX_BRIDGE_EBT_802_3_H diff --git a/include/uapi/linux/netfilter_bridge/ebt_among.h b/include/uapi/linux/netfilter_bridge/ebt_among.h index bd4e3ad0b706..9acf757bc1f7 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_among.h +++ b/include/uapi/linux/netfilter_bridge/ebt_among.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_BRIDGE_EBT_AMONG_H #define __LINUX_BRIDGE_EBT_AMONG_H diff --git a/include/uapi/linux/netfilter_bridge/ebt_arp.h b/include/uapi/linux/netfilter_bridge/ebt_arp.h index dd4df25330e8..628b4fdae542 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_arp.h +++ b/include/uapi/linux/netfilter_bridge/ebt_arp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_BRIDGE_EBT_ARP_H #define __LINUX_BRIDGE_EBT_ARP_H diff --git a/include/uapi/linux/netfilter_bridge/ebt_arpreply.h b/include/uapi/linux/netfilter_bridge/ebt_arpreply.h index 6fee3402e307..ed41ae053597 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_arpreply.h +++ b/include/uapi/linux/netfilter_bridge/ebt_arpreply.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_BRIDGE_EBT_ARPREPLY_H #define __LINUX_BRIDGE_EBT_ARPREPLY_H diff --git a/include/uapi/linux/netfilter_bridge/ebt_ip.h b/include/uapi/linux/netfilter_bridge/ebt_ip.h index c4bbc41b0ea4..8e462fb1983f 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_ip.h +++ b/include/uapi/linux/netfilter_bridge/ebt_ip.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * ebt_ip * diff --git a/include/uapi/linux/netfilter_bridge/ebt_ip6.h b/include/uapi/linux/netfilter_bridge/ebt_ip6.h index a062f0ce95f9..057945dd66bc 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_ip6.h +++ b/include/uapi/linux/netfilter_bridge/ebt_ip6.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * ebt_ip6 * diff --git a/include/uapi/linux/netfilter_bridge/ebt_limit.h b/include/uapi/linux/netfilter_bridge/ebt_limit.h index 66d80b30ba0e..c2ac02e1fab6 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_limit.h +++ b/include/uapi/linux/netfilter_bridge/ebt_limit.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_BRIDGE_EBT_LIMIT_H #define __LINUX_BRIDGE_EBT_LIMIT_H diff --git a/include/uapi/linux/netfilter_bridge/ebt_log.h b/include/uapi/linux/netfilter_bridge/ebt_log.h index 7e7f1d1fe494..f6724155af91 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_log.h +++ b/include/uapi/linux/netfilter_bridge/ebt_log.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_BRIDGE_EBT_LOG_H #define __LINUX_BRIDGE_EBT_LOG_H diff --git a/include/uapi/linux/netfilter_bridge/ebt_mark_m.h b/include/uapi/linux/netfilter_bridge/ebt_mark_m.h index 410f9e5a71d4..098ac78cd1e6 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_mark_m.h +++ b/include/uapi/linux/netfilter_bridge/ebt_mark_m.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_BRIDGE_EBT_MARK_M_H #define __LINUX_BRIDGE_EBT_MARK_M_H diff --git a/include/uapi/linux/netfilter_bridge/ebt_mark_t.h b/include/uapi/linux/netfilter_bridge/ebt_mark_t.h index 7d5a268a4311..8810f1c12af3 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_mark_t.h +++ b/include/uapi/linux/netfilter_bridge/ebt_mark_t.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_BRIDGE_EBT_MARK_T_H #define __LINUX_BRIDGE_EBT_MARK_T_H diff --git a/include/uapi/linux/netfilter_bridge/ebt_nat.h b/include/uapi/linux/netfilter_bridge/ebt_nat.h index c990d74ee966..49da2f9be021 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_nat.h +++ b/include/uapi/linux/netfilter_bridge/ebt_nat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_BRIDGE_EBT_NAT_H #define __LINUX_BRIDGE_EBT_NAT_H diff --git a/include/uapi/linux/netfilter_bridge/ebt_nflog.h b/include/uapi/linux/netfilter_bridge/ebt_nflog.h index df829fce9125..f5cdc068c264 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_nflog.h +++ b/include/uapi/linux/netfilter_bridge/ebt_nflog.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_BRIDGE_EBT_NFLOG_H #define __LINUX_BRIDGE_EBT_NFLOG_H diff --git a/include/uapi/linux/netfilter_bridge/ebt_pkttype.h b/include/uapi/linux/netfilter_bridge/ebt_pkttype.h index c241badcd036..32c5d08b31d3 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_pkttype.h +++ b/include/uapi/linux/netfilter_bridge/ebt_pkttype.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_BRIDGE_EBT_PKTTYPE_H #define __LINUX_BRIDGE_EBT_PKTTYPE_H diff --git a/include/uapi/linux/netfilter_bridge/ebt_redirect.h b/include/uapi/linux/netfilter_bridge/ebt_redirect.h index dd9622ce8488..dc7a7ce25902 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_redirect.h +++ b/include/uapi/linux/netfilter_bridge/ebt_redirect.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_BRIDGE_EBT_REDIRECT_H #define __LINUX_BRIDGE_EBT_REDIRECT_H diff --git a/include/uapi/linux/netfilter_bridge/ebt_stp.h b/include/uapi/linux/netfilter_bridge/ebt_stp.h index 1025b9f5fb7d..94f68dedc3f6 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_stp.h +++ b/include/uapi/linux/netfilter_bridge/ebt_stp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_BRIDGE_EBT_STP_H #define __LINUX_BRIDGE_EBT_STP_H diff --git a/include/uapi/linux/netfilter_bridge/ebt_vlan.h b/include/uapi/linux/netfilter_bridge/ebt_vlan.h index 967d1d5cf98d..fb0d8f604c23 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_vlan.h +++ b/include/uapi/linux/netfilter_bridge/ebt_vlan.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_BRIDGE_EBT_VLAN_H #define __LINUX_BRIDGE_EBT_VLAN_H diff --git a/include/uapi/linux/netfilter_bridge/ebtables.h b/include/uapi/linux/netfilter_bridge/ebtables.h index e3cdf9f1a259..9ff57c0a0199 100644 --- a/include/uapi/linux/netfilter_bridge/ebtables.h +++ b/include/uapi/linux/netfilter_bridge/ebtables.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * ebtables * diff --git a/include/uapi/linux/netfilter_ipv4/ip_tables.h b/include/uapi/linux/netfilter_ipv4/ip_tables.h index d0da53d96d93..6aaeb14bfce1 100644 --- a/include/uapi/linux/netfilter_ipv4/ip_tables.h +++ b/include/uapi/linux/netfilter_ipv4/ip_tables.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * 25-Jul-1998 Major changes to allow for ip chain table * diff --git a/include/uapi/linux/netfilter_ipv4/ipt_CLUSTERIP.h b/include/uapi/linux/netfilter_ipv4/ipt_CLUSTERIP.h index eac0f6548f47..ff6599494fe6 100644 --- a/include/uapi/linux/netfilter_ipv4/ipt_CLUSTERIP.h +++ b/include/uapi/linux/netfilter_ipv4/ipt_CLUSTERIP.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _IPT_CLUSTERIP_H_target #define _IPT_CLUSTERIP_H_target diff --git a/include/uapi/linux/netfilter_ipv4/ipt_LOG.h b/include/uapi/linux/netfilter_ipv4/ipt_LOG.h index 5d8152077d71..6dec14ba851b 100644 --- a/include/uapi/linux/netfilter_ipv4/ipt_LOG.h +++ b/include/uapi/linux/netfilter_ipv4/ipt_LOG.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _IPT_LOG_H #define _IPT_LOG_H diff --git a/include/uapi/linux/netfilter_ipv4/ipt_REJECT.h b/include/uapi/linux/netfilter_ipv4/ipt_REJECT.h index 4293a1ad1b01..ae61ddd328b0 100644 --- a/include/uapi/linux/netfilter_ipv4/ipt_REJECT.h +++ b/include/uapi/linux/netfilter_ipv4/ipt_REJECT.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _IPT_REJECT_H #define _IPT_REJECT_H diff --git a/include/uapi/linux/netfilter_ipv4/ipt_TTL.h b/include/uapi/linux/netfilter_ipv4/ipt_TTL.h index f6ac169d92f9..57d2fc67a943 100644 --- a/include/uapi/linux/netfilter_ipv4/ipt_TTL.h +++ b/include/uapi/linux/netfilter_ipv4/ipt_TTL.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* TTL modification module for IP tables * (C) 2000 by Harald Welte */ diff --git a/include/uapi/linux/netfilter_ipv4/ipt_ah.h b/include/uapi/linux/netfilter_ipv4/ipt_ah.h index 4e02bb0119e3..606ce90dbf83 100644 --- a/include/uapi/linux/netfilter_ipv4/ipt_ah.h +++ b/include/uapi/linux/netfilter_ipv4/ipt_ah.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _IPT_AH_H #define _IPT_AH_H diff --git a/include/uapi/linux/netfilter_ipv4/ipt_ecn.h b/include/uapi/linux/netfilter_ipv4/ipt_ecn.h index 0e0c063dbf60..8121bec47026 100644 --- a/include/uapi/linux/netfilter_ipv4/ipt_ecn.h +++ b/include/uapi/linux/netfilter_ipv4/ipt_ecn.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _IPT_ECN_H #define _IPT_ECN_H diff --git a/include/uapi/linux/netfilter_ipv4/ipt_ttl.h b/include/uapi/linux/netfilter_ipv4/ipt_ttl.h index 37bee4442486..ad0226a8629b 100644 --- a/include/uapi/linux/netfilter_ipv4/ipt_ttl.h +++ b/include/uapi/linux/netfilter_ipv4/ipt_ttl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* IP tables module for matching the value of the TTL * (C) 2000 by Harald Welte */ diff --git a/include/uapi/linux/netfilter_ipv6/ip6_tables.h b/include/uapi/linux/netfilter_ipv6/ip6_tables.h index d1b22653daf2..031d0a43bed2 100644 --- a/include/uapi/linux/netfilter_ipv6/ip6_tables.h +++ b/include/uapi/linux/netfilter_ipv6/ip6_tables.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * 25-Jul-1998 Major changes to allow for ip chain table * diff --git a/include/uapi/linux/netfilter_ipv6/ip6t_HL.h b/include/uapi/linux/netfilter_ipv6/ip6t_HL.h index ebd8ead1bb63..eaed56a287b4 100644 --- a/include/uapi/linux/netfilter_ipv6/ip6t_HL.h +++ b/include/uapi/linux/netfilter_ipv6/ip6t_HL.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* Hop Limit modification module for ip6tables * Maciej Soltysiak * Based on HW's TTL module */ diff --git a/include/uapi/linux/netfilter_ipv6/ip6t_LOG.h b/include/uapi/linux/netfilter_ipv6/ip6t_LOG.h index 3dd0bc4e0735..7553a434e4da 100644 --- a/include/uapi/linux/netfilter_ipv6/ip6t_LOG.h +++ b/include/uapi/linux/netfilter_ipv6/ip6t_LOG.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _IP6T_LOG_H #define _IP6T_LOG_H diff --git a/include/uapi/linux/netfilter_ipv6/ip6t_NPT.h b/include/uapi/linux/netfilter_ipv6/ip6t_NPT.h index f763355481b5..422aef07657a 100644 --- a/include/uapi/linux/netfilter_ipv6/ip6t_NPT.h +++ b/include/uapi/linux/netfilter_ipv6/ip6t_NPT.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __NETFILTER_IP6T_NPT #define __NETFILTER_IP6T_NPT diff --git a/include/uapi/linux/netfilter_ipv6/ip6t_REJECT.h b/include/uapi/linux/netfilter_ipv6/ip6t_REJECT.h index cd2e940c8bf5..158ffa5f45b7 100644 --- a/include/uapi/linux/netfilter_ipv6/ip6t_REJECT.h +++ b/include/uapi/linux/netfilter_ipv6/ip6t_REJECT.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _IP6T_REJECT_H #define _IP6T_REJECT_H diff --git a/include/uapi/linux/netfilter_ipv6/ip6t_ah.h b/include/uapi/linux/netfilter_ipv6/ip6t_ah.h index 5da2b65cb3ad..9a4174e08f9c 100644 --- a/include/uapi/linux/netfilter_ipv6/ip6t_ah.h +++ b/include/uapi/linux/netfilter_ipv6/ip6t_ah.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _IP6T_AH_H #define _IP6T_AH_H diff --git a/include/uapi/linux/netfilter_ipv6/ip6t_frag.h b/include/uapi/linux/netfilter_ipv6/ip6t_frag.h index dfd8bc2268cf..9acac816bba3 100644 --- a/include/uapi/linux/netfilter_ipv6/ip6t_frag.h +++ b/include/uapi/linux/netfilter_ipv6/ip6t_frag.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _IP6T_FRAG_H #define _IP6T_FRAG_H diff --git a/include/uapi/linux/netfilter_ipv6/ip6t_hl.h b/include/uapi/linux/netfilter_ipv6/ip6t_hl.h index 6e76dbc6c19a..6b62f9418eb2 100644 --- a/include/uapi/linux/netfilter_ipv6/ip6t_hl.h +++ b/include/uapi/linux/netfilter_ipv6/ip6t_hl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* ip6tables module for matching the Hop Limit value * Maciej Soltysiak * Based on HW's ttl module */ diff --git a/include/uapi/linux/netfilter_ipv6/ip6t_ipv6header.h b/include/uapi/linux/netfilter_ipv6/ip6t_ipv6header.h index efae3a20c214..5a5196914764 100644 --- a/include/uapi/linux/netfilter_ipv6/ip6t_ipv6header.h +++ b/include/uapi/linux/netfilter_ipv6/ip6t_ipv6header.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* ipv6header match - matches IPv6 packets based on whether they contain certain headers */ diff --git a/include/uapi/linux/netfilter_ipv6/ip6t_mh.h b/include/uapi/linux/netfilter_ipv6/ip6t_mh.h index a7729a5025cd..906196283185 100644 --- a/include/uapi/linux/netfilter_ipv6/ip6t_mh.h +++ b/include/uapi/linux/netfilter_ipv6/ip6t_mh.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _IP6T_MH_H #define _IP6T_MH_H diff --git a/include/uapi/linux/netfilter_ipv6/ip6t_opts.h b/include/uapi/linux/netfilter_ipv6/ip6t_opts.h index 17d419a811fd..79f9a477c5ac 100644 --- a/include/uapi/linux/netfilter_ipv6/ip6t_opts.h +++ b/include/uapi/linux/netfilter_ipv6/ip6t_opts.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _IP6T_OPTS_H #define _IP6T_OPTS_H diff --git a/include/uapi/linux/netfilter_ipv6/ip6t_rt.h b/include/uapi/linux/netfilter_ipv6/ip6t_rt.h index 558f81e46fb9..9c23e8ad20b9 100644 --- a/include/uapi/linux/netfilter_ipv6/ip6t_rt.h +++ b/include/uapi/linux/netfilter_ipv6/ip6t_rt.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _IP6T_RT_H #define _IP6T_RT_H diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index e8af60a7c56d..776bc92e9118 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__LINUX_NETLINK_H #define _UAPI__LINUX_NETLINK_H diff --git a/include/uapi/linux/netlink_diag.h b/include/uapi/linux/netlink_diag.h index 6dcd4de3397b..dfa61be43d2f 100644 --- a/include/uapi/linux/netlink_diag.h +++ b/include/uapi/linux/netlink_diag.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __NETLINK_DIAG_H__ #define __NETLINK_DIAG_H__ diff --git a/include/uapi/linux/netrom.h b/include/uapi/linux/netrom.h index af7313cc9cb6..7498ea3c3940 100644 --- a/include/uapi/linux/netrom.h +++ b/include/uapi/linux/netrom.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * These are the public elements of the Linux kernel NET/ROM implementation. * For kernel AX.25 see the file ax25.h. This file requires ax25.h for the diff --git a/include/uapi/linux/nfs.h b/include/uapi/linux/nfs.h index 5e6296160361..057d22a48416 100644 --- a/include/uapi/linux/nfs.h +++ b/include/uapi/linux/nfs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * NFS protocol definitions * diff --git a/include/uapi/linux/nfs2.h b/include/uapi/linux/nfs2.h index fde24b30cc9e..e0237e0985b9 100644 --- a/include/uapi/linux/nfs2.h +++ b/include/uapi/linux/nfs2.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * NFS protocol definitions * diff --git a/include/uapi/linux/nfs3.h b/include/uapi/linux/nfs3.h index 231ef4e69829..37e4b34e6b43 100644 --- a/include/uapi/linux/nfs3.h +++ b/include/uapi/linux/nfs3.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * NFSv3 protocol definitions */ diff --git a/include/uapi/linux/nfs4.h b/include/uapi/linux/nfs4.h index 4ae62796bfde..8572930cf5b0 100644 --- a/include/uapi/linux/nfs4.h +++ b/include/uapi/linux/nfs4.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/linux/nfs4.h * diff --git a/include/uapi/linux/nfs4_mount.h b/include/uapi/linux/nfs4_mount.h index a0dcf6655657..d20bb869bb99 100644 --- a/include/uapi/linux/nfs4_mount.h +++ b/include/uapi/linux/nfs4_mount.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_NFS4_MOUNT_H #define _LINUX_NFS4_MOUNT_H diff --git a/include/uapi/linux/nfs_fs.h b/include/uapi/linux/nfs_fs.h index 49142287999c..7bcc8cd6831d 100644 --- a/include/uapi/linux/nfs_fs.h +++ b/include/uapi/linux/nfs_fs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * linux/include/linux/nfs_fs.h * diff --git a/include/uapi/linux/nfs_mount.h b/include/uapi/linux/nfs_mount.h index 64b0f22f5c4c..e44e00616ab5 100644 --- a/include/uapi/linux/nfs_mount.h +++ b/include/uapi/linux/nfs_mount.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_NFS_MOUNT_H #define _LINUX_NFS_MOUNT_H diff --git a/include/uapi/linux/nfsacl.h b/include/uapi/linux/nfsacl.h index 552726631162..ca9a8501ff30 100644 --- a/include/uapi/linux/nfsacl.h +++ b/include/uapi/linux/nfsacl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * File: linux/nfsacl.h * diff --git a/include/uapi/linux/nfsd/debug.h b/include/uapi/linux/nfsd/debug.h index 28ec6c9c421a..7301cdc79a33 100644 --- a/include/uapi/linux/nfsd/debug.h +++ b/include/uapi/linux/nfsd/debug.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * linux/include/linux/nfsd/debug.h * diff --git a/include/uapi/linux/nfsd/export.h b/include/uapi/linux/nfsd/export.h index c3be256107c6..2124ba904779 100644 --- a/include/uapi/linux/nfsd/export.h +++ b/include/uapi/linux/nfsd/export.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/linux/nfsd/export.h * diff --git a/include/uapi/linux/nfsd/nfsfh.h b/include/uapi/linux/nfsd/nfsfh.h index 20391235d088..ff0ca88b1c8f 100644 --- a/include/uapi/linux/nfsd/nfsfh.h +++ b/include/uapi/linux/nfsd/nfsfh.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file describes the layout of the file handles as passed * over the wire. diff --git a/include/uapi/linux/nfsd/stats.h b/include/uapi/linux/nfsd/stats.h index 9fb7a0644263..b1a38ae14a02 100644 --- a/include/uapi/linux/nfsd/stats.h +++ b/include/uapi/linux/nfsd/stats.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * linux/include/linux/nfsd/stats.h * diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h index 1a3ca79f466b..a0c8552b64ee 100644 --- a/include/uapi/linux/nsfs.h +++ b/include/uapi/linux/nsfs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_NSFS_H #define __LINUX_NSFS_H diff --git a/include/uapi/linux/nubus.h b/include/uapi/linux/nubus.h index ac516064f0ee..f3776cc80f4d 100644 --- a/include/uapi/linux/nubus.h +++ b/include/uapi/linux/nubus.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* nubus.h: various definitions and prototypes for NuBus drivers to use. diff --git a/include/uapi/linux/nvram.h b/include/uapi/linux/nvram.h index 0986c4337383..4bee8e72dab4 100644 --- a/include/uapi/linux/nvram.h +++ b/include/uapi/linux/nvram.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_NVRAM_H #define _UAPI_LINUX_NVRAM_H diff --git a/include/uapi/linux/oom.h b/include/uapi/linux/oom.h index b29272d621ce..750b1c5a4dec 100644 --- a/include/uapi/linux/oom.h +++ b/include/uapi/linux/oom.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__INCLUDE_LINUX_OOM_H #define _UAPI__INCLUDE_LINUX_OOM_H diff --git a/include/uapi/linux/packet_diag.h b/include/uapi/linux/packet_diag.h index 0c5d5dd61b6a..349ddf0a96af 100644 --- a/include/uapi/linux/packet_diag.h +++ b/include/uapi/linux/packet_diag.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __PACKET_DIAG_H__ #define __PACKET_DIAG_H__ diff --git a/include/uapi/linux/param.h b/include/uapi/linux/param.h index 092e92f67b50..94e0c57a75b7 100644 --- a/include/uapi/linux/param.h +++ b/include/uapi/linux/param.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_PARAM_H #define _LINUX_PARAM_H diff --git a/include/uapi/linux/patchkey.h b/include/uapi/linux/patchkey.h index 1bda0e56bc5e..3eb246e94733 100644 --- a/include/uapi/linux/patchkey.h +++ b/include/uapi/linux/patchkey.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * -- definition of _PATCHKEY macro * diff --git a/include/uapi/linux/pci.h b/include/uapi/linux/pci.h index 3c292bc0d1c1..a769eefc5139 100644 --- a/include/uapi/linux/pci.h +++ b/include/uapi/linux/pci.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * pci.h * diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index f8d58045926f..87c2c840b27d 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * pci_regs.h * diff --git a/include/uapi/linux/pcitest.h b/include/uapi/linux/pcitest.h index a6aa10c45ad1..953cf036cb26 100644 --- a/include/uapi/linux/pcitest.h +++ b/include/uapi/linux/pcitest.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /** * pcitest.h - PCI test uapi defines * diff --git a/include/uapi/linux/personality.h b/include/uapi/linux/personality.h index aa169c4339d2..49796b7756af 100644 --- a/include/uapi/linux/personality.h +++ b/include/uapi/linux/personality.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_PERSONALITY_H #define _UAPI_LINUX_PERSONALITY_H diff --git a/include/uapi/linux/pfkeyv2.h b/include/uapi/linux/pfkeyv2.h index ada7f0171ccc..d65b11785260 100644 --- a/include/uapi/linux/pfkeyv2.h +++ b/include/uapi/linux/pfkeyv2.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* PF_KEY user interface, this is defined by rfc2367 so * do not make arbitrary modifications or else this header * file will not be compliant. diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index d5e2bf68d0d4..46c506615f4a 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_PKT_CLS_H #define __LINUX_PKT_CLS_H diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 099bf5528fed..703cd9df6cef 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_PKT_SCHED_H #define __LINUX_PKT_SCHED_H diff --git a/include/uapi/linux/pmu.h b/include/uapi/linux/pmu.h index caead364b6eb..89cb1acea93a 100644 --- a/include/uapi/linux/pmu.h +++ b/include/uapi/linux/pmu.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Definitions for talking to the PMU. The PMU is a microcontroller * which controls battery charging and system power on PowerBook 3400 diff --git a/include/uapi/linux/posix_types.h b/include/uapi/linux/posix_types.h index 988f76e636e3..9a7a740b35a2 100644 --- a/include/uapi/linux/posix_types.h +++ b/include/uapi/linux/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_POSIX_TYPES_H #define _LINUX_POSIX_TYPES_H diff --git a/include/uapi/linux/pr.h b/include/uapi/linux/pr.h index 645ef3cf3dd0..ccc78cbf1221 100644 --- a/include/uapi/linux/pr.h +++ b/include/uapi/linux/pr.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_PR_H #define _UAPI_PR_H diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index a8d0759a9e40..b640071421f7 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_PRCTL_H #define _LINUX_PRCTL_H diff --git a/include/uapi/linux/psample.h b/include/uapi/linux/psample.h index ed48996ec0e8..ce1116cff53d 100644 --- a/include/uapi/linux/psample.h +++ b/include/uapi/linux/psample.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __UAPI_PSAMPLE_H #define __UAPI_PSAMPLE_H diff --git a/include/uapi/linux/psci.h b/include/uapi/linux/psci.h index 3d7a0fc021a7..760e52a9640f 100644 --- a/include/uapi/linux/psci.h +++ b/include/uapi/linux/psci.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * ARM Power State and Coordination Interface (PSCI) header * diff --git a/include/uapi/linux/ptrace.h b/include/uapi/linux/ptrace.h index fb8106509000..e3939e00980b 100644 --- a/include/uapi/linux/ptrace.h +++ b/include/uapi/linux/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_PTRACE_H #define _UAPI_LINUX_PTRACE_H /* ptrace.h */ diff --git a/include/uapi/linux/qnx4_fs.h b/include/uapi/linux/qnx4_fs.h index 8b9aee1a9ce3..31487325d265 100644 --- a/include/uapi/linux/qnx4_fs.h +++ b/include/uapi/linux/qnx4_fs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Name : qnx4_fs.h * Author : Richard Frowijn diff --git a/include/uapi/linux/qnxtypes.h b/include/uapi/linux/qnxtypes.h index bebbe5cc4fb8..eacfab10e821 100644 --- a/include/uapi/linux/qnxtypes.h +++ b/include/uapi/linux/qnxtypes.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Name : qnxtypes.h * Author : Richard Frowijn diff --git a/include/uapi/linux/qrtr.h b/include/uapi/linux/qrtr.h index 9d76c566f66e..5d9aab1f1893 100644 --- a/include/uapi/linux/qrtr.h +++ b/include/uapi/linux/qrtr.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_QRTR_H #define _LINUX_QRTR_H diff --git a/include/uapi/linux/radeonfb.h b/include/uapi/linux/radeonfb.h index 8c4bbdecc44f..86eafb805ed9 100644 --- a/include/uapi/linux/radeonfb.h +++ b/include/uapi/linux/radeonfb.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_RADEONFB_H__ #define __LINUX_RADEONFB_H__ diff --git a/include/uapi/linux/random.h b/include/uapi/linux/random.h index 3f93d1695e7f..c34f4490d025 100644 --- a/include/uapi/linux/random.h +++ b/include/uapi/linux/random.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/linux/random.h * diff --git a/include/uapi/linux/raw.h b/include/uapi/linux/raw.h index 62d543e70603..dc96dda479d6 100644 --- a/include/uapi/linux/raw.h +++ b/include/uapi/linux/raw.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_RAW_H #define __LINUX_RAW_H diff --git a/include/uapi/linux/reboot.h b/include/uapi/linux/reboot.h index 09d056d4fc50..58e64398efc5 100644 --- a/include/uapi/linux/reboot.h +++ b/include/uapi/linux/reboot.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_REBOOT_H #define _UAPI_LINUX_REBOOT_H diff --git a/include/uapi/linux/reiserfs_fs.h b/include/uapi/linux/reiserfs_fs.h index ea3700cd7367..5bb921409f2b 100644 --- a/include/uapi/linux/reiserfs_fs.h +++ b/include/uapi/linux/reiserfs_fs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 1996, 1997, 1998 Hans Reiser, see reiserfs/README for licensing and copyright details */ diff --git a/include/uapi/linux/reiserfs_xattr.h b/include/uapi/linux/reiserfs_xattr.h index 38fdd648be21..28f10842f047 100644 --- a/include/uapi/linux/reiserfs_xattr.h +++ b/include/uapi/linux/reiserfs_xattr.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* File: linux/reiserfs_xattr.h */ diff --git a/include/uapi/linux/resource.h b/include/uapi/linux/resource.h index 36fb3b5fb181..cc00fd079631 100644 --- a/include/uapi/linux/resource.h +++ b/include/uapi/linux/resource.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_RESOURCE_H #define _UAPI_LINUX_RESOURCE_H diff --git a/include/uapi/linux/romfs_fs.h b/include/uapi/linux/romfs_fs.h index 5f57f93b284f..a7f1585accef 100644 --- a/include/uapi/linux/romfs_fs.h +++ b/include/uapi/linux/romfs_fs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_ROMFS_FS_H #define __LINUX_ROMFS_FS_H diff --git a/include/uapi/linux/rose.h b/include/uapi/linux/rose.h index 1fcfe95893b8..19aa4693c8fc 100644 --- a/include/uapi/linux/rose.h +++ b/include/uapi/linux/rose.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * These are the public elements of the Linux kernel Rose implementation. * For kernel AX.25 see the file ax25.h. This file requires ax25.h for the diff --git a/include/uapi/linux/rtc.h b/include/uapi/linux/rtc.h index f8c82e6f25d5..2ad1788968d0 100644 --- a/include/uapi/linux/rtc.h +++ b/include/uapi/linux/rtc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Generic RTC interface. * This version contains the part of the user interface to the Real Time Clock diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index dab7dad9e01a..a6d37c2ea355 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__LINUX_RTNETLINK_H #define _UAPI__LINUX_RTNETLINK_H diff --git a/include/uapi/linux/scc.h b/include/uapi/linux/scc.h index 72b6b8153374..c5bc7f747755 100644 --- a/include/uapi/linux/scc.h +++ b/include/uapi/linux/scc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* $Id: scc.h,v 1.29 1997/04/02 14:56:45 jreuter Exp jreuter $ */ #ifndef _UAPI_SCC_H diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h index e2a6c7b3510b..30a9e51bbb1e 100644 --- a/include/uapi/linux/sched.h +++ b/include/uapi/linux/sched.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_SCHED_H #define _UAPI_LINUX_SCHED_H diff --git a/include/uapi/linux/sched/types.h b/include/uapi/linux/sched/types.h index 34b81aa1a2f7..10fbb8031930 100644 --- a/include/uapi/linux/sched/types.h +++ b/include/uapi/linux/sched/types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_SCHED_TYPES_H #define _UAPI_LINUX_SCHED_TYPES_H diff --git a/include/uapi/linux/screen_info.h b/include/uapi/linux/screen_info.h index 8b8d39dfb67f..87e5c086938e 100644 --- a/include/uapi/linux/screen_info.h +++ b/include/uapi/linux/screen_info.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_SCREEN_INFO_H #define _UAPI_SCREEN_INFO_H diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h index f6bc1dea3247..2a0bd9dd104d 100644 --- a/include/uapi/linux/seccomp.h +++ b/include/uapi/linux/seccomp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_SECCOMP_H #define _UAPI_LINUX_SECCOMP_H diff --git a/include/uapi/linux/securebits.h b/include/uapi/linux/securebits.h index 35ac35cef217..d6d98877ff1a 100644 --- a/include/uapi/linux/securebits.h +++ b/include/uapi/linux/securebits.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_SECUREBITS_H #define _UAPI_LINUX_SECUREBITS_H diff --git a/include/uapi/linux/seg6_genl.h b/include/uapi/linux/seg6_genl.h index fcf1c60d7df3..d995d48daebb 100644 --- a/include/uapi/linux/seg6_genl.h +++ b/include/uapi/linux/seg6_genl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_SEG6_GENL_H #define _UAPI_LINUX_SEG6_GENL_H diff --git a/include/uapi/linux/seg6_hmac.h b/include/uapi/linux/seg6_hmac.h index e691c753fc3f..b877c782158a 100644 --- a/include/uapi/linux/seg6_hmac.h +++ b/include/uapi/linux/seg6_hmac.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_SEG6_HMAC_H #define _UAPI_LINUX_SEG6_HMAC_H diff --git a/include/uapi/linux/sem.h b/include/uapi/linux/sem.h index 67eb90361692..9c3e745b0656 100644 --- a/include/uapi/linux/sem.h +++ b/include/uapi/linux/sem.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_SEM_H #define _UAPI_LINUX_SEM_H diff --git a/include/uapi/linux/shm.h b/include/uapi/linux/shm.h index cf23c873719d..4de12a39b075 100644 --- a/include/uapi/linux/shm.h +++ b/include/uapi/linux/shm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_SHM_H_ #define _UAPI_LINUX_SHM_H_ diff --git a/include/uapi/linux/signal.h b/include/uapi/linux/signal.h index cd0804b6bfa2..e03238f8d478 100644 --- a/include/uapi/linux/signal.h +++ b/include/uapi/linux/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_SIGNAL_H #define _UAPI_LINUX_SIGNAL_H diff --git a/include/uapi/linux/signalfd.h b/include/uapi/linux/signalfd.h index 492c6def340d..6f0da42fc5ef 100644 --- a/include/uapi/linux/signalfd.h +++ b/include/uapi/linux/signalfd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/linux/signalfd.h * diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index ab1dea8e53ee..0e11ca421ca4 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * diff --git a/include/uapi/linux/smc_diag.h b/include/uapi/linux/smc_diag.h index 87712bfaa9dd..0ae5d4685ba3 100644 --- a/include/uapi/linux/smc_diag.h +++ b/include/uapi/linux/smc_diag.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_SMC_DIAG_H_ #define _UAPI_SMC_DIAG_H_ diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 758f12b58541..0d941cdd8e8c 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Definitions for MIBs * diff --git a/include/uapi/linux/sock_diag.h b/include/uapi/linux/sock_diag.h index 7ff505d8a47b..e5925009a652 100644 --- a/include/uapi/linux/sock_diag.h +++ b/include/uapi/linux/sock_diag.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__SOCK_DIAG_H__ #define _UAPI__SOCK_DIAG_H__ diff --git a/include/uapi/linux/socket.h b/include/uapi/linux/socket.h index 76ab0c68561e..8eb96021709c 100644 --- a/include/uapi/linux/socket.h +++ b/include/uapi/linux/socket.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_SOCKET_H #define _UAPI_LINUX_SOCKET_H diff --git a/include/uapi/linux/sonet.h b/include/uapi/linux/sonet.h index cc54acee81ba..9d02357c6c6f 100644 --- a/include/uapi/linux/sonet.h +++ b/include/uapi/linux/sonet.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* sonet.h - SONET/SHD physical layer control */ /* Written 1995-2000 by Werner Almesberger, EPFL LRC/ICA */ diff --git a/include/uapi/linux/sound.h b/include/uapi/linux/sound.h index 014c9117c224..a62d74042f47 100644 --- a/include/uapi/linux/sound.h +++ b/include/uapi/linux/sound.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_SOUND_H #define _UAPI_LINUX_SOUND_H diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index 17b10304c393..7b35e98d3c58 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_STAT_H #define _UAPI_LINUX_STAT_H diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index 621fa8ac4425..f65b92e0e1f9 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include #ifndef __always_inline diff --git a/include/uapi/linux/string.h b/include/uapi/linux/string.h index e32e545cff5a..9d129c13fe9d 100644 --- a/include/uapi/linux/string.h +++ b/include/uapi/linux/string.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_STRING_H_ #define _UAPI_LINUX_STRING_H_ diff --git a/include/uapi/linux/sunrpc/debug.h b/include/uapi/linux/sunrpc/debug.h index 830e34493a8c..ae54af3d3fd6 100644 --- a/include/uapi/linux/sunrpc/debug.h +++ b/include/uapi/linux/sunrpc/debug.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * linux/include/linux/sunrpc/debug.h * diff --git a/include/uapi/linux/suspend_ioctls.h b/include/uapi/linux/suspend_ioctls.h index 0b30382984fe..bcce04e21c0d 100644 --- a/include/uapi/linux/suspend_ioctls.h +++ b/include/uapi/linux/suspend_ioctls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_SUSPEND_IOCTLS_H #define _LINUX_SUSPEND_IOCTLS_H diff --git a/include/uapi/linux/swab.h b/include/uapi/linux/swab.h index 8f3a8f606fd9..23cd84868cc3 100644 --- a/include/uapi/linux/swab.h +++ b/include/uapi/linux/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_SWAB_H #define _UAPI_LINUX_SWAB_H diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h index e13d48058b8d..0f272818a4d2 100644 --- a/include/uapi/linux/sysctl.h +++ b/include/uapi/linux/sysctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * sysctl.h: General linux system control interface * diff --git a/include/uapi/linux/sysinfo.h b/include/uapi/linux/sysinfo.h index 934335a22522..435d5c23f0c0 100644 --- a/include/uapi/linux/sysinfo.h +++ b/include/uapi/linux/sysinfo.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_SYSINFO_H #define _LINUX_SYSINFO_H diff --git a/include/uapi/linux/target_core_user.h b/include/uapi/linux/target_core_user.h index 24a1c4ec2248..0be80f72646b 100644 --- a/include/uapi/linux/target_core_user.h +++ b/include/uapi/linux/target_core_user.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __TARGET_CORE_USER_H #define __TARGET_CORE_USER_H diff --git a/include/uapi/linux/tc_act/tc_connmark.h b/include/uapi/linux/tc_act/tc_connmark.h index 62a5e944c554..80caa47b1933 100644 --- a/include/uapi/linux/tc_act/tc_connmark.h +++ b/include/uapi/linux/tc_act/tc_connmark.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __UAPI_TC_CONNMARK_H #define __UAPI_TC_CONNMARK_H diff --git a/include/uapi/linux/tc_act/tc_csum.h b/include/uapi/linux/tc_act/tc_csum.h index a11bb355dbfb..0ecf4d29e2f3 100644 --- a/include/uapi/linux/tc_act/tc_csum.h +++ b/include/uapi/linux/tc_act/tc_csum.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_TC_CSUM_H #define __LINUX_TC_CSUM_H diff --git a/include/uapi/linux/tc_act/tc_defact.h b/include/uapi/linux/tc_act/tc_defact.h index d2a3abb77aeb..e3ecd8bf37de 100644 --- a/include/uapi/linux/tc_act/tc_defact.h +++ b/include/uapi/linux/tc_act/tc_defact.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_TC_DEF_H #define __LINUX_TC_DEF_H diff --git a/include/uapi/linux/tc_act/tc_gact.h b/include/uapi/linux/tc_act/tc_gact.h index 70b536a8f8b2..94273c3b81b0 100644 --- a/include/uapi/linux/tc_act/tc_gact.h +++ b/include/uapi/linux/tc_act/tc_gact.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_TC_GACT_H #define __LINUX_TC_GACT_H diff --git a/include/uapi/linux/tc_act/tc_ife.h b/include/uapi/linux/tc_act/tc_ife.h index 7c2817866c97..2f48490ef386 100644 --- a/include/uapi/linux/tc_act/tc_ife.h +++ b/include/uapi/linux/tc_act/tc_ife.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __UAPI_TC_IFE_H #define __UAPI_TC_IFE_H diff --git a/include/uapi/linux/tc_act/tc_ipt.h b/include/uapi/linux/tc_act/tc_ipt.h index 7c6e155dd981..b743c8bddd13 100644 --- a/include/uapi/linux/tc_act/tc_ipt.h +++ b/include/uapi/linux/tc_act/tc_ipt.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_TC_IPT_H #define __LINUX_TC_IPT_H diff --git a/include/uapi/linux/tc_act/tc_mirred.h b/include/uapi/linux/tc_act/tc_mirred.h index 3d7a2b352a62..020696e07345 100644 --- a/include/uapi/linux/tc_act/tc_mirred.h +++ b/include/uapi/linux/tc_act/tc_mirred.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_TC_MIR_H #define __LINUX_TC_MIR_H diff --git a/include/uapi/linux/tc_act/tc_nat.h b/include/uapi/linux/tc_act/tc_nat.h index 923457c9ebf0..086be842587b 100644 --- a/include/uapi/linux/tc_act/tc_nat.h +++ b/include/uapi/linux/tc_act/tc_nat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_TC_NAT_H #define __LINUX_TC_NAT_H diff --git a/include/uapi/linux/tc_act/tc_pedit.h b/include/uapi/linux/tc_act/tc_pedit.h index 143d2b31a316..162d1094c41c 100644 --- a/include/uapi/linux/tc_act/tc_pedit.h +++ b/include/uapi/linux/tc_act/tc_pedit.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_TC_PED_H #define __LINUX_TC_PED_H diff --git a/include/uapi/linux/tc_act/tc_sample.h b/include/uapi/linux/tc_act/tc_sample.h index edc9058bb30d..bd7e9f03abd2 100644 --- a/include/uapi/linux/tc_act/tc_sample.h +++ b/include/uapi/linux/tc_act/tc_sample.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_TC_SAMPLE_H #define __LINUX_TC_SAMPLE_H diff --git a/include/uapi/linux/tc_ematch/tc_em_cmp.h b/include/uapi/linux/tc_ematch/tc_em_cmp.h index f34bb1bae083..2549d9d6e031 100644 --- a/include/uapi/linux/tc_ematch/tc_em_cmp.h +++ b/include/uapi/linux/tc_ematch/tc_em_cmp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_TC_EM_CMP_H #define __LINUX_TC_EM_CMP_H diff --git a/include/uapi/linux/tc_ematch/tc_em_meta.h b/include/uapi/linux/tc_ematch/tc_em_meta.h index b11f8ce2d3c0..cf30b5bc4eaf 100644 --- a/include/uapi/linux/tc_ematch/tc_em_meta.h +++ b/include/uapi/linux/tc_ematch/tc_em_meta.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_TC_EM_META_H #define __LINUX_TC_EM_META_H diff --git a/include/uapi/linux/tc_ematch/tc_em_nbyte.h b/include/uapi/linux/tc_ematch/tc_em_nbyte.h index 7172cfb999c1..c76333f7f6f2 100644 --- a/include/uapi/linux/tc_ematch/tc_em_nbyte.h +++ b/include/uapi/linux/tc_ematch/tc_em_nbyte.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_TC_EM_NBYTE_H #define __LINUX_TC_EM_NBYTE_H diff --git a/include/uapi/linux/tc_ematch/tc_em_text.h b/include/uapi/linux/tc_ematch/tc_em_text.h index 5aac4045ba88..b0a92257964e 100644 --- a/include/uapi/linux/tc_ematch/tc_em_text.h +++ b/include/uapi/linux/tc_ematch/tc_em_text.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_TC_EM_TEXT_H #define __LINUX_TC_EM_TEXT_H diff --git a/include/uapi/linux/tcp_metrics.h b/include/uapi/linux/tcp_metrics.h index 80ad90d0cfc2..7cb4a172feed 100644 --- a/include/uapi/linux/tcp_metrics.h +++ b/include/uapi/linux/tcp_metrics.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* tcp_metrics.h - TCP Metrics Interface */ #ifndef _LINUX_TCP_METRICS_H diff --git a/include/uapi/linux/termios.h b/include/uapi/linux/termios.h index 2acd0c1f8a2a..33961d4e4de0 100644 --- a/include/uapi/linux/termios.h +++ b/include/uapi/linux/termios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_TERMIOS_H #define _LINUX_TERMIOS_H diff --git a/include/uapi/linux/thermal.h b/include/uapi/linux/thermal.h index ac5535855982..96218378dda8 100644 --- a/include/uapi/linux/thermal.h +++ b/include/uapi/linux/thermal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_THERMAL_H #define _UAPI_LINUX_THERMAL_H diff --git a/include/uapi/linux/time.h b/include/uapi/linux/time.h index 09299fcb842a..53f8dd84beb5 100644 --- a/include/uapi/linux/time.h +++ b/include/uapi/linux/time.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_TIME_H #define _UAPI_LINUX_TIME_H diff --git a/include/uapi/linux/timerfd.h b/include/uapi/linux/timerfd.h index 6fcfaa8da173..dd469944db02 100644 --- a/include/uapi/linux/timerfd.h +++ b/include/uapi/linux/timerfd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/linux/timerfd.h * diff --git a/include/uapi/linux/times.h b/include/uapi/linux/times.h index 87b62615cedd..9c72df662f5f 100644 --- a/include/uapi/linux/times.h +++ b/include/uapi/linux/times.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_TIMES_H #define _LINUX_TIMES_H diff --git a/include/uapi/linux/tiocl.h b/include/uapi/linux/tiocl.h index 4756862c4ed4..b32acc229024 100644 --- a/include/uapi/linux/tiocl.h +++ b/include/uapi/linux/tiocl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_TIOCL_H #define _LINUX_TIOCL_H diff --git a/include/uapi/linux/tty.h b/include/uapi/linux/tty.h index cf1455396df0..376cccf397be 100644 --- a/include/uapi/linux/tty.h +++ b/include/uapi/linux/tty.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_TTY_H #define _UAPI_LINUX_TTY_H diff --git a/include/uapi/linux/tty_flags.h b/include/uapi/linux/tty_flags.h index 66e4d8bcb16f..6ac609a00dea 100644 --- a/include/uapi/linux/tty_flags.h +++ b/include/uapi/linux/tty_flags.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_TTY_FLAGS_H #define _LINUX_TTY_FLAGS_H diff --git a/include/uapi/linux/types.h b/include/uapi/linux/types.h index 41e5914f0a8e..e3d1d0c78f3c 100644 --- a/include/uapi/linux/types.h +++ b/include/uapi/linux/types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_TYPES_H #define _UAPI_LINUX_TYPES_H diff --git a/include/uapi/linux/un.h b/include/uapi/linux/un.h index 4f0ab3a548ad..0ad59dc8b686 100644 --- a/include/uapi/linux/un.h +++ b/include/uapi/linux/un.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_UN_H #define _LINUX_UN_H diff --git a/include/uapi/linux/unistd.h b/include/uapi/linux/unistd.h index aa8d5b5e2e3e..a92361f5d32d 100644 --- a/include/uapi/linux/unistd.h +++ b/include/uapi/linux/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_UNISTD_H_ #define _LINUX_UNISTD_H_ diff --git a/include/uapi/linux/unix_diag.h b/include/uapi/linux/unix_diag.h index 1eb0b8dd1830..5c502fdf7a42 100644 --- a/include/uapi/linux/unix_diag.h +++ b/include/uapi/linux/unix_diag.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __UNIX_DIAG_H__ #define __UNIX_DIAG_H__ diff --git a/include/uapi/linux/usb/cdc.h b/include/uapi/linux/usb/cdc.h index e2bc417b243b..6d61550959ef 100644 --- a/include/uapi/linux/usb/cdc.h +++ b/include/uapi/linux/usb/cdc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * USB Communications Device Class (CDC) definitions * diff --git a/include/uapi/linux/usb/ch11.h b/include/uapi/linux/usb/ch11.h index 576c704e3fb8..29c120c88747 100644 --- a/include/uapi/linux/usb/ch11.h +++ b/include/uapi/linux/usb/ch11.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file holds Hub protocol constants and data structures that are * defined in chapter 11 (Hub Specification) of the USB 2.0 specification. diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h index 2a5d63040a0b..cec06625f407 100644 --- a/include/uapi/linux/usb/ch9.h +++ b/include/uapi/linux/usb/ch9.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file holds USB constants and structures that are needed for * USB device APIs. These are used by the USB device model, which is diff --git a/include/uapi/linux/usb/functionfs.h b/include/uapi/linux/usb/functionfs.h index f913d08ab7bb..d77ee6b65328 100644 --- a/include/uapi/linux/usb/functionfs.h +++ b/include/uapi/linux/usb/functionfs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__LINUX_FUNCTIONFS_H__ #define _UAPI__LINUX_FUNCTIONFS_H__ diff --git a/include/uapi/linux/usb/gadgetfs.h b/include/uapi/linux/usb/gadgetfs.h index 0bb12e0d4f8f..835473910a49 100644 --- a/include/uapi/linux/usb/gadgetfs.h +++ b/include/uapi/linux/usb/gadgetfs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Filesystem based user-mode API to USB Gadget controller hardware * diff --git a/include/uapi/linux/usb/tmc.h b/include/uapi/linux/usb/tmc.h index 2e59d9c50b8d..03f6adc8f35b 100644 --- a/include/uapi/linux/usb/tmc.h +++ b/include/uapi/linux/usb/tmc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2007 Stefan Kopp, Gechingen, Germany * Copyright (C) 2008 Novell, Inc. diff --git a/include/uapi/linux/usb/video.h b/include/uapi/linux/usb/video.h index 69ab695fad2e..ff6cc6cb4227 100644 --- a/include/uapi/linux/usb/video.h +++ b/include/uapi/linux/usb/video.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * USB Video Class definitions. * diff --git a/include/uapi/linux/usbip.h b/include/uapi/linux/usbip.h index fa5db30ede36..fd393d908d8a 100644 --- a/include/uapi/linux/usbip.h +++ b/include/uapi/linux/usbip.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * usbip.h * diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index d6d1f65cb3c3..48f1a7c2f1f0 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/linux/userfaultfd.h * diff --git a/include/uapi/linux/utime.h b/include/uapi/linux/utime.h index 5cdf673afbdb..fd9aa26b6860 100644 --- a/include/uapi/linux/utime.h +++ b/include/uapi/linux/utime.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_UTIME_H #define _LINUX_UTIME_H diff --git a/include/uapi/linux/utsname.h b/include/uapi/linux/utsname.h index 872c2df10de7..c99edc662536 100644 --- a/include/uapi/linux/utsname.h +++ b/include/uapi/linux/utsname.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_UTSNAME_H #define _UAPI_LINUX_UTSNAME_H diff --git a/include/uapi/linux/uvcvideo.h b/include/uapi/linux/uvcvideo.h index 3b081862b9e8..e80b4655d8cd 100644 --- a/include/uapi/linux/uvcvideo.h +++ b/include/uapi/linux/uvcvideo.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_UVCVIDEO_H_ #define __LINUX_UVCVIDEO_H_ diff --git a/include/uapi/linux/veth.h b/include/uapi/linux/veth.h index 3354c1eb424e..52b58e587e23 100644 --- a/include/uapi/linux/veth.h +++ b/include/uapi/linux/veth.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __NET_VETH_H_ #define __NET_VETH_H_ diff --git a/include/uapi/linux/vfio_ccw.h b/include/uapi/linux/vfio_ccw.h index 34a7f6f9e065..2ec5f367ff78 100644 --- a/include/uapi/linux/vfio_ccw.h +++ b/include/uapi/linux/vfio_ccw.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Interfaces for vfio-ccw * diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index 60180c0b5dc6..c51f8e5cc608 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_VHOST_H #define _LINUX_VHOST_H /* Userspace interface for in-kernel virtio accelerators. */ diff --git a/include/uapi/linux/vsockmon.h b/include/uapi/linux/vsockmon.h index a08b522ef597..4a03b893a957 100644 --- a/include/uapi/linux/vsockmon.h +++ b/include/uapi/linux/vsockmon.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_VSOCKMON_H #define _UAPI_VSOCKMON_H diff --git a/include/uapi/linux/vt.h b/include/uapi/linux/vt.h index f69034887e68..e9d39c48520a 100644 --- a/include/uapi/linux/vt.h +++ b/include/uapi/linux/vt.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_VT_H #define _UAPI_LINUX_VT_H diff --git a/include/uapi/linux/wait.h b/include/uapi/linux/wait.h index 9393eead23e2..ac49a220cf2a 100644 --- a/include/uapi/linux/wait.h +++ b/include/uapi/linux/wait.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_LINUX_WAIT_H #define _UAPI_LINUX_WAIT_H diff --git a/include/uapi/linux/wanrouter.h b/include/uapi/linux/wanrouter.h index 498d6c12c666..2f1216d00caa 100644 --- a/include/uapi/linux/wanrouter.h +++ b/include/uapi/linux/wanrouter.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * wanrouter.h Legacy declarations kept around until X25 is removed */ diff --git a/include/uapi/linux/watchdog.h b/include/uapi/linux/watchdog.h index 2babe72870ba..b15cde5c9054 100644 --- a/include/uapi/linux/watchdog.h +++ b/include/uapi/linux/watchdog.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Generic watchdog defines. Derived from.. * diff --git a/include/uapi/linux/wireless.h b/include/uapi/linux/wireless.h index d9ecd7c6d691..86eca3208b6b 100644 --- a/include/uapi/linux/wireless.h +++ b/include/uapi/linux/wireless.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file define a set of standard wireless extensions * diff --git a/include/uapi/linux/x25.h b/include/uapi/linux/x25.h index 810cce6737ea..034b7dc5593a 100644 --- a/include/uapi/linux/x25.h +++ b/include/uapi/linux/x25.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * These are the public elements of the Linux kernel X.25 implementation. * diff --git a/include/uapi/linux/xattr.h b/include/uapi/linux/xattr.h index 1590c49cae57..a92be0f492a9 100644 --- a/include/uapi/linux/xattr.h +++ b/include/uapi/linux/xattr.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* File: linux/xattr.h diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index 5fe7370a2bef..e3af2859188b 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _LINUX_XFRM_H #define _LINUX_XFRM_H diff --git a/include/uapi/linux/zorro_ids.h b/include/uapi/linux/zorro_ids.h index 74bc53bcfdcf..6e574d7b7d79 100644 --- a/include/uapi/linux/zorro_ids.h +++ b/include/uapi/linux/zorro_ids.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Zorro board IDs * diff --git a/include/uapi/mtd/inftl-user.h b/include/uapi/mtd/inftl-user.h index 8376bd1a9e01..8d5044e32e53 100644 --- a/include/uapi/mtd/inftl-user.h +++ b/include/uapi/mtd/inftl-user.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Parts of INFTL headers shared with userspace * diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h index 861440a87e7c..cc002e316d09 100644 --- a/include/uapi/rdma/rdma_netlink.h +++ b/include/uapi/rdma/rdma_netlink.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_RDMA_NETLINK_H #define _UAPI_RDMA_NETLINK_H diff --git a/include/uapi/sound/firewire.h b/include/uapi/sound/firewire.h index 622900488bdc..f0a547d86679 100644 --- a/include/uapi/sound/firewire.h +++ b/include/uapi/sound/firewire.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_SOUND_FIREWIRE_H_INCLUDED #define _UAPI_SOUND_FIREWIRE_H_INCLUDED diff --git a/include/uapi/video/edid.h b/include/uapi/video/edid.h index 8c0f032014c9..c6030dc10d6b 100644 --- a/include/uapi/video/edid.h +++ b/include/uapi/video/edid.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__linux_video_edid_h__ #define _UAPI__linux_video_edid_h__ diff --git a/include/uapi/video/uvesafb.h b/include/uapi/video/uvesafb.h index cee063d723ad..a0d5c9213e92 100644 --- a/include/uapi/video/uvesafb.h +++ b/include/uapi/video/uvesafb.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_UVESAFB_H #define _UAPI_UVESAFB_H diff --git a/tools/arch/alpha/include/uapi/asm/bitsperlong.h b/tools/arch/alpha/include/uapi/asm/bitsperlong.h index ad57f7868203..6c5bf7d03f4e 100644 --- a/tools/arch/alpha/include/uapi/asm/bitsperlong.h +++ b/tools/arch/alpha/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_ALPHA_BITSPERLONG_H #define __ASM_ALPHA_BITSPERLONG_H diff --git a/tools/arch/alpha/include/uapi/asm/mman.h b/tools/arch/alpha/include/uapi/asm/mman.h index e38b64c82b97..c317d3e6867a 100644 --- a/tools/arch/alpha/include/uapi/asm/mman.h +++ b/tools/arch/alpha/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef TOOLS_ARCH_ALPHA_UAPI_ASM_MMAN_FIX_H #define TOOLS_ARCH_ALPHA_UAPI_ASM_MMAN_FIX_H #define MADV_DODUMP 17 diff --git a/tools/arch/arc/include/uapi/asm/mman.h b/tools/arch/arc/include/uapi/asm/mman.h index aa3acd2aa9af..81f0f9bf0c25 100644 --- a/tools/arch/arc/include/uapi/asm/mman.h +++ b/tools/arch/arc/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef TOOLS_ARCH_ARC_UAPI_ASM_MMAN_FIX_H #define TOOLS_ARCH_ARC_UAPI_ASM_MMAN_FIX_H #include diff --git a/tools/arch/arm/include/uapi/asm/mman.h b/tools/arch/arm/include/uapi/asm/mman.h index 478f699f56fd..a6d46321e330 100644 --- a/tools/arch/arm/include/uapi/asm/mman.h +++ b/tools/arch/arm/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef TOOLS_ARCH_ARM_UAPI_ASM_MMAN_FIX_H #define TOOLS_ARCH_ARM_UAPI_ASM_MMAN_FIX_H #include diff --git a/tools/arch/arm/include/uapi/asm/perf_regs.h b/tools/arch/arm/include/uapi/asm/perf_regs.h index ce59448458b2..a3c046174e6b 100644 --- a/tools/arch/arm/include/uapi/asm/perf_regs.h +++ b/tools/arch/arm/include/uapi/asm/perf_regs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_ARM_PERF_REGS_H #define _ASM_ARM_PERF_REGS_H diff --git a/tools/arch/arm64/include/uapi/asm/mman.h b/tools/arch/arm64/include/uapi/asm/mman.h index 70fd3113710a..2ee288e447ec 100644 --- a/tools/arch/arm64/include/uapi/asm/mman.h +++ b/tools/arch/arm64/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef TOOLS_ARCH_ARM64_UAPI_ASM_MMAN_FIX_H #define TOOLS_ARCH_ARM64_UAPI_ASM_MMAN_FIX_H #include diff --git a/tools/arch/arm64/include/uapi/asm/perf_regs.h b/tools/arch/arm64/include/uapi/asm/perf_regs.h index 172b8317ee49..d54daafa89e3 100644 --- a/tools/arch/arm64/include/uapi/asm/perf_regs.h +++ b/tools/arch/arm64/include/uapi/asm/perf_regs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_ARM64_PERF_REGS_H #define _ASM_ARM64_PERF_REGS_H diff --git a/tools/arch/frv/include/uapi/asm/bitsperlong.h b/tools/arch/frv/include/uapi/asm/bitsperlong.h index 6dc0bb0c13b2..76da34b10f59 100644 --- a/tools/arch/frv/include/uapi/asm/bitsperlong.h +++ b/tools/arch/frv/include/uapi/asm/bitsperlong.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/tools/arch/frv/include/uapi/asm/mman.h b/tools/arch/frv/include/uapi/asm/mman.h index 5be78ac12464..5bc900b0bc78 100644 --- a/tools/arch/frv/include/uapi/asm/mman.h +++ b/tools/arch/frv/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef TOOLS_ARCH_FRV_UAPI_ASM_MMAN_FIX_H #define TOOLS_ARCH_FRV_UAPI_ASM_MMAN_FIX_H #include diff --git a/tools/arch/h8300/include/uapi/asm/mman.h b/tools/arch/h8300/include/uapi/asm/mman.h index 9d9ac54d3c5a..be7bbe0528d1 100644 --- a/tools/arch/h8300/include/uapi/asm/mman.h +++ b/tools/arch/h8300/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef TOOLS_ARCH_H8300_UAPI_ASM_MMAN_FIX_H #define TOOLS_ARCH_H8300_UAPI_ASM_MMAN_FIX_H #include diff --git a/tools/arch/hexagon/include/uapi/asm/mman.h b/tools/arch/hexagon/include/uapi/asm/mman.h index 102f3fae6085..cd59ba932b3a 100644 --- a/tools/arch/hexagon/include/uapi/asm/mman.h +++ b/tools/arch/hexagon/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef TOOLS_ARCH_HEXAGON_UAPI_ASM_MMAN_FIX_H #define TOOLS_ARCH_HEXAGON_UAPI_ASM_MMAN_FIX_H #include diff --git a/tools/arch/ia64/include/uapi/asm/bitsperlong.h b/tools/arch/ia64/include/uapi/asm/bitsperlong.h index ec4db3c970b7..1146d55563db 100644 --- a/tools/arch/ia64/include/uapi/asm/bitsperlong.h +++ b/tools/arch/ia64/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_IA64_BITSPERLONG_H #define __ASM_IA64_BITSPERLONG_H diff --git a/tools/arch/ia64/include/uapi/asm/mman.h b/tools/arch/ia64/include/uapi/asm/mman.h index 1d6e5ac6442d..2a19bb1db4ab 100644 --- a/tools/arch/ia64/include/uapi/asm/mman.h +++ b/tools/arch/ia64/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef TOOLS_ARCH_IA64_UAPI_ASM_MMAN_FIX_H #define TOOLS_ARCH_IA64_UAPI_ASM_MMAN_FIX_H #include diff --git a/tools/arch/m32r/include/uapi/asm/bitsperlong.h b/tools/arch/m32r/include/uapi/asm/bitsperlong.h index 6dc0bb0c13b2..76da34b10f59 100644 --- a/tools/arch/m32r/include/uapi/asm/bitsperlong.h +++ b/tools/arch/m32r/include/uapi/asm/bitsperlong.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/tools/arch/m32r/include/uapi/asm/mman.h b/tools/arch/m32r/include/uapi/asm/mman.h index 1c29635bb73b..d19b82c9c290 100644 --- a/tools/arch/m32r/include/uapi/asm/mman.h +++ b/tools/arch/m32r/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef TOOLS_ARCH_M32R_UAPI_ASM_MMAN_FIX_H #define TOOLS_ARCH_M32R_UAPI_ASM_MMAN_FIX_H #include diff --git a/tools/arch/microblaze/include/uapi/asm/bitsperlong.h b/tools/arch/microblaze/include/uapi/asm/bitsperlong.h index 6dc0bb0c13b2..76da34b10f59 100644 --- a/tools/arch/microblaze/include/uapi/asm/bitsperlong.h +++ b/tools/arch/microblaze/include/uapi/asm/bitsperlong.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/tools/arch/microblaze/include/uapi/asm/mman.h b/tools/arch/microblaze/include/uapi/asm/mman.h index 005cd50b50e1..f3f2103fd02c 100644 --- a/tools/arch/microblaze/include/uapi/asm/mman.h +++ b/tools/arch/microblaze/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef TOOLS_ARCH_MICROBLAZE_UAPI_ASM_MMAN_FIX_H #define TOOLS_ARCH_MICROBLAZE_UAPI_ASM_MMAN_FIX_H #include diff --git a/tools/arch/mips/include/uapi/asm/mman.h b/tools/arch/mips/include/uapi/asm/mman.h index c02052965d50..de2206883abc 100644 --- a/tools/arch/mips/include/uapi/asm/mman.h +++ b/tools/arch/mips/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef TOOLS_ARCH_MIPS_UAPI_ASM_MMAN_FIX_H #define TOOLS_ARCH_MIPS_UAPI_ASM_MMAN_FIX_H #define MADV_DODUMP 17 diff --git a/tools/arch/mn10300/include/uapi/asm/mman.h b/tools/arch/mn10300/include/uapi/asm/mman.h index c1ea36d83acc..b9360639974f 100644 --- a/tools/arch/mn10300/include/uapi/asm/mman.h +++ b/tools/arch/mn10300/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef TOOLS_ARCH_MN10300_UAPI_ASM_MMAN_FIX_H #define TOOLS_ARCH_MN10300_UAPI_ASM_MMAN_FIX_H #include diff --git a/tools/arch/parisc/include/uapi/asm/bitsperlong.h b/tools/arch/parisc/include/uapi/asm/bitsperlong.h index e0a23c7bdd43..23ac7562927a 100644 --- a/tools/arch/parisc/include/uapi/asm/bitsperlong.h +++ b/tools/arch/parisc/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_PARISC_BITSPERLONG_H #define __ASM_PARISC_BITSPERLONG_H diff --git a/tools/arch/parisc/include/uapi/asm/mman.h b/tools/arch/parisc/include/uapi/asm/mman.h index 286c0bd74573..1bd78758bde9 100644 --- a/tools/arch/parisc/include/uapi/asm/mman.h +++ b/tools/arch/parisc/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef TOOLS_ARCH_PARISC_UAPI_ASM_MMAN_FIX_H #define TOOLS_ARCH_PARISC_UAPI_ASM_MMAN_FIX_H #define MADV_DODUMP 70 diff --git a/tools/arch/powerpc/include/uapi/asm/bitsperlong.h b/tools/arch/powerpc/include/uapi/asm/bitsperlong.h index 5f1659032c40..46ece3ecff31 100644 --- a/tools/arch/powerpc/include/uapi/asm/bitsperlong.h +++ b/tools/arch/powerpc/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_POWERPC_BITSPERLONG_H #define __ASM_POWERPC_BITSPERLONG_H diff --git a/tools/arch/powerpc/include/uapi/asm/mman.h b/tools/arch/powerpc/include/uapi/asm/mman.h index 761db43172fe..f33105bc5ca6 100644 --- a/tools/arch/powerpc/include/uapi/asm/mman.h +++ b/tools/arch/powerpc/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef TOOLS_ARCH_POWERPC_UAPI_ASM_MMAN_FIX_H #define TOOLS_ARCH_POWERPC_UAPI_ASM_MMAN_FIX_H #define MAP_DENYWRITE 0x0800 diff --git a/tools/arch/powerpc/include/uapi/asm/perf_regs.h b/tools/arch/powerpc/include/uapi/asm/perf_regs.h index 6a93209748a1..9e52c86ccbd3 100644 --- a/tools/arch/powerpc/include/uapi/asm/perf_regs.h +++ b/tools/arch/powerpc/include/uapi/asm/perf_regs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_POWERPC_PERF_REGS_H #define _UAPI_ASM_POWERPC_PERF_REGS_H diff --git a/tools/arch/s390/include/uapi/asm/bitsperlong.h b/tools/arch/s390/include/uapi/asm/bitsperlong.h index e351ea2ad43e..d2bb620119bf 100644 --- a/tools/arch/s390/include/uapi/asm/bitsperlong.h +++ b/tools/arch/s390/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_S390_BITSPERLONG_H #define __ASM_S390_BITSPERLONG_H diff --git a/tools/arch/s390/include/uapi/asm/mman.h b/tools/arch/s390/include/uapi/asm/mman.h index b03dea9e1f56..4ec32e4251a4 100644 --- a/tools/arch/s390/include/uapi/asm/mman.h +++ b/tools/arch/s390/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef TOOLS_ARCH_S390_UAPI_ASM_MMAN_FIX_H #define TOOLS_ARCH_S390_UAPI_ASM_MMAN_FIX_H #include diff --git a/tools/arch/s390/include/uapi/asm/sie.h b/tools/arch/s390/include/uapi/asm/sie.h index 3ac634368939..6ca1e68d7103 100644 --- a/tools/arch/s390/include/uapi/asm/sie.h +++ b/tools/arch/s390/include/uapi/asm/sie.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI_ASM_S390_SIE_H #define _UAPI_ASM_S390_SIE_H diff --git a/tools/arch/score/include/uapi/asm/bitsperlong.h b/tools/arch/score/include/uapi/asm/bitsperlong.h index 86ff337aa459..df48f2717da2 100644 --- a/tools/arch/score/include/uapi/asm/bitsperlong.h +++ b/tools/arch/score/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_SCORE_BITSPERLONG_H #define _ASM_SCORE_BITSPERLONG_H diff --git a/tools/arch/score/include/uapi/asm/mman.h b/tools/arch/score/include/uapi/asm/mman.h index 2f8fb89944fd..b4bd195a8586 100644 --- a/tools/arch/score/include/uapi/asm/mman.h +++ b/tools/arch/score/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef TOOLS_ARCH_SCORE_UAPI_ASM_MMAN_FIX_H #define TOOLS_ARCH_SCORE_UAPI_ASM_MMAN_FIX_H #include diff --git a/tools/arch/sh/include/uapi/asm/mman.h b/tools/arch/sh/include/uapi/asm/mman.h index 26504f6f060e..88c0e2930c47 100644 --- a/tools/arch/sh/include/uapi/asm/mman.h +++ b/tools/arch/sh/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef TOOLS_ARCH_SH_UAPI_ASM_MMAN_FIX_H #define TOOLS_ARCH_SH_UAPI_ASM_MMAN_FIX_H #include diff --git a/tools/arch/sparc/include/uapi/asm/bitsperlong.h b/tools/arch/sparc/include/uapi/asm/bitsperlong.h index b62dd907d7c3..3b4e61740b75 100644 --- a/tools/arch/sparc/include/uapi/asm/bitsperlong.h +++ b/tools/arch/sparc/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_ALPHA_BITSPERLONG_H #define __ASM_ALPHA_BITSPERLONG_H diff --git a/tools/arch/sparc/include/uapi/asm/mman.h b/tools/arch/sparc/include/uapi/asm/mman.h index 8640525de991..38920eed8cbf 100644 --- a/tools/arch/sparc/include/uapi/asm/mman.h +++ b/tools/arch/sparc/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef TOOLS_ARCH_SPARC_UAPI_ASM_MMAN_FIX_H #define TOOLS_ARCH_SPARC_UAPI_ASM_MMAN_FIX_H #define MAP_DENYWRITE 0x0800 diff --git a/tools/arch/tile/include/uapi/asm/mman.h b/tools/arch/tile/include/uapi/asm/mman.h index 7116c4b928b3..65ec92925c6c 100644 --- a/tools/arch/tile/include/uapi/asm/mman.h +++ b/tools/arch/tile/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef TOOLS_ARCH_TILE_UAPI_ASM_MMAN_FIX_H #define TOOLS_ARCH_TILE_UAPI_ASM_MMAN_FIX_H #define MAP_DENYWRITE 0x0800 diff --git a/tools/arch/x86/include/uapi/asm/bitsperlong.h b/tools/arch/x86/include/uapi/asm/bitsperlong.h index 6e23c543cd80..f8a92e0009d6 100644 --- a/tools/arch/x86/include/uapi/asm/bitsperlong.h +++ b/tools/arch/x86/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_X86_BITSPERLONG_H #define __ASM_X86_BITSPERLONG_H diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index c2824d02ba37..f3a960488eae 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_KVM_H #define _ASM_X86_KVM_H diff --git a/tools/arch/x86/include/uapi/asm/kvm_perf.h b/tools/arch/x86/include/uapi/asm/kvm_perf.h index 3bb964f88aa1..125cf5cdf6c5 100644 --- a/tools/arch/x86/include/uapi/asm/kvm_perf.h +++ b/tools/arch/x86/include/uapi/asm/kvm_perf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_KVM_PERF_H #define _ASM_X86_KVM_PERF_H diff --git a/tools/arch/x86/include/uapi/asm/mman.h b/tools/arch/x86/include/uapi/asm/mman.h index b73c1af8b1dd..8449778de2ed 100644 --- a/tools/arch/x86/include/uapi/asm/mman.h +++ b/tools/arch/x86/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef TOOLS_ARCH_X86_UAPI_ASM_MMAN_FIX_H #define TOOLS_ARCH_X86_UAPI_ASM_MMAN_FIX_H #define MAP_32BIT 0x40 diff --git a/tools/arch/x86/include/uapi/asm/perf_regs.h b/tools/arch/x86/include/uapi/asm/perf_regs.h index 3f2207bfd17b..f3329cabce5c 100644 --- a/tools/arch/x86/include/uapi/asm/perf_regs.h +++ b/tools/arch/x86/include/uapi/asm/perf_regs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ASM_X86_PERF_REGS_H #define _ASM_X86_PERF_REGS_H diff --git a/tools/arch/xtensa/include/uapi/asm/mman.h b/tools/arch/xtensa/include/uapi/asm/mman.h index 4453195c450c..34dde6f44dae 100644 --- a/tools/arch/xtensa/include/uapi/asm/mman.h +++ b/tools/arch/xtensa/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef TOOLS_ARCH_XTENSA_UAPI_ASM_MMAN_FIX_H #define TOOLS_ARCH_XTENSA_UAPI_ASM_MMAN_FIX_H #define MADV_DODUMP 17 -- cgit v1.2.3-71-gd317 From e2be04c7f9958dde770eeb8b30e829ca969b37bb Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 1 Nov 2017 15:09:13 +0100 Subject: License cleanup: add SPDX license identifier to uapi header files with a license Many user space API headers have licensing information, which is either incomplete, badly formatted or just a shorthand for referring to the license under which the file is supposed to be. This makes it hard for compliance tools to determine the correct license. Update these files with an SPDX license identifier. The identifier was chosen based on the license information in the file. GPL/LGPL licensed headers get the matching GPL/LGPL SPDX license identifier with the added 'WITH Linux-syscall-note' exception, which is the officially assigned exception identifier for the kernel syscall exception: NOTE! This copyright does *not* cover user programs that use kernel services by normal system calls - this is merely considered normal use of the kernel, and does *not* fall under the heading of "derived work". This exception makes it possible to include GPL headers into non GPL code, without confusing license compliance tools. Headers which have either explicit dual licensing or are just licensed under a non GPL license are updated with the corresponding SPDX identifier and the GPLv2 with syscall exception identifier. The format is: ((GPL-2.0 WITH Linux-syscall-note) OR SPDX-ID-OF-OTHER-LICENSE) SPDX license identifiers are a legally binding shorthand, which can be used instead of the full boiler plate text. The update does not remove existing license information as this has to be done on a case by case basis and the copyright holders might have to be consulted. This will happen in a separate step. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. See the previous patch in this series for the methodology of how this patch was researched. Reviewed-by: Kate Stewart Reviewed-by: Philippe Ombredanne Reviewed-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- arch/alpha/include/uapi/asm/poll.h | 1 + arch/arc/include/uapi/asm/byteorder.h | 1 + arch/arc/include/uapi/asm/cachectl.h | 1 + arch/arc/include/uapi/asm/elf.h | 1 + arch/arc/include/uapi/asm/page.h | 1 + arch/arc/include/uapi/asm/ptrace.h | 1 + arch/arc/include/uapi/asm/sigcontext.h | 1 + arch/arc/include/uapi/asm/signal.h | 1 + arch/arc/include/uapi/asm/swab.h | 1 + arch/arc/include/uapi/asm/unistd.h | 1 + arch/arm/include/uapi/asm/kvm.h | 1 + arch/arm/include/uapi/asm/posix_types.h | 1 + arch/arm/include/uapi/asm/ptrace.h | 1 + arch/arm/include/uapi/asm/setup.h | 1 + arch/arm/include/uapi/asm/unistd.h | 1 + arch/arm64/include/uapi/asm/auxvec.h | 1 + arch/arm64/include/uapi/asm/bitsperlong.h | 1 + arch/arm64/include/uapi/asm/byteorder.h | 1 + arch/arm64/include/uapi/asm/fcntl.h | 1 + arch/arm64/include/uapi/asm/hwcap.h | 1 + arch/arm64/include/uapi/asm/kvm.h | 1 + arch/arm64/include/uapi/asm/param.h | 1 + arch/arm64/include/uapi/asm/ptrace.h | 1 + arch/arm64/include/uapi/asm/setup.h | 1 + arch/arm64/include/uapi/asm/sigcontext.h | 1 + arch/arm64/include/uapi/asm/siginfo.h | 1 + arch/arm64/include/uapi/asm/signal.h | 1 + arch/arm64/include/uapi/asm/stat.h | 1 + arch/arm64/include/uapi/asm/statfs.h | 1 + arch/arm64/include/uapi/asm/ucontext.h | 1 + arch/arm64/include/uapi/asm/unistd.h | 1 + arch/blackfin/include/uapi/asm/bfin_sport.h | 1 + arch/blackfin/include/uapi/asm/cachectl.h | 1 + arch/blackfin/include/uapi/asm/fcntl.h | 1 + arch/blackfin/include/uapi/asm/fixed_code.h | 1 + arch/blackfin/include/uapi/asm/poll.h | 1 + arch/blackfin/include/uapi/asm/posix_types.h | 1 + arch/blackfin/include/uapi/asm/ptrace.h | 1 + arch/blackfin/include/uapi/asm/sigcontext.h | 1 + arch/blackfin/include/uapi/asm/siginfo.h | 1 + arch/blackfin/include/uapi/asm/stat.h | 1 + arch/blackfin/include/uapi/asm/swab.h | 1 + arch/blackfin/include/uapi/asm/unistd.h | 1 + arch/c6x/include/uapi/asm/ptrace.h | 1 + arch/c6x/include/uapi/asm/sigcontext.h | 1 + arch/c6x/include/uapi/asm/swab.h | 1 + arch/c6x/include/uapi/asm/unistd.h | 1 + arch/frv/include/uapi/asm/ipcbuf.h | 1 + arch/frv/include/uapi/asm/ptrace.h | 1 + arch/frv/include/uapi/asm/registers.h | 1 + arch/frv/include/uapi/asm/setup.h | 1 + arch/frv/include/uapi/asm/sigcontext.h | 1 + arch/frv/include/uapi/asm/types.h | 1 + arch/hexagon/include/uapi/asm/bitsperlong.h | 1 + arch/hexagon/include/uapi/asm/byteorder.h | 1 + arch/hexagon/include/uapi/asm/param.h | 1 + arch/hexagon/include/uapi/asm/ptrace.h | 1 + arch/hexagon/include/uapi/asm/setup.h | 1 + arch/hexagon/include/uapi/asm/sigcontext.h | 1 + arch/hexagon/include/uapi/asm/signal.h | 1 + arch/hexagon/include/uapi/asm/swab.h | 1 + arch/hexagon/include/uapi/asm/unistd.h | 1 + arch/ia64/include/uapi/asm/poll.h | 1 + arch/m32r/include/uapi/asm/ptrace.h | 1 + arch/m68k/include/uapi/asm/bootinfo.h | 1 + arch/m68k/include/uapi/asm/setup.h | 1 + arch/metag/include/uapi/asm/unistd.h | 1 + arch/microblaze/include/uapi/asm/elf.h | 1 + arch/microblaze/include/uapi/asm/ptrace.h | 1 + arch/microblaze/include/uapi/asm/setup.h | 1 + arch/microblaze/include/uapi/asm/sigcontext.h | 1 + arch/microblaze/include/uapi/asm/unistd.h | 1 + arch/mips/include/uapi/asm/auxvec.h | 1 + arch/mips/include/uapi/asm/bitfield.h | 1 + arch/mips/include/uapi/asm/break.h | 1 + arch/mips/include/uapi/asm/byteorder.h | 1 + arch/mips/include/uapi/asm/cachectl.h | 1 + arch/mips/include/uapi/asm/errno.h | 1 + arch/mips/include/uapi/asm/fcntl.h | 1 + arch/mips/include/uapi/asm/inst.h | 1 + arch/mips/include/uapi/asm/ioctl.h | 1 + arch/mips/include/uapi/asm/ioctls.h | 1 + arch/mips/include/uapi/asm/kvm.h | 1 + arch/mips/include/uapi/asm/mman.h | 1 + arch/mips/include/uapi/asm/param.h | 1 + arch/mips/include/uapi/asm/posix_types.h | 1 + arch/mips/include/uapi/asm/ptrace.h | 1 + arch/mips/include/uapi/asm/reg.h | 1 + arch/mips/include/uapi/asm/resource.h | 1 + arch/mips/include/uapi/asm/sgidefs.h | 1 + arch/mips/include/uapi/asm/sigcontext.h | 1 + arch/mips/include/uapi/asm/siginfo.h | 1 + arch/mips/include/uapi/asm/signal.h | 1 + arch/mips/include/uapi/asm/socket.h | 1 + arch/mips/include/uapi/asm/sockios.h | 1 + arch/mips/include/uapi/asm/stat.h | 1 + arch/mips/include/uapi/asm/statfs.h | 1 + arch/mips/include/uapi/asm/swab.h | 1 + arch/mips/include/uapi/asm/sysmips.h | 1 + arch/mips/include/uapi/asm/termbits.h | 1 + arch/mips/include/uapi/asm/termios.h | 1 + arch/mips/include/uapi/asm/types.h | 1 + arch/mips/include/uapi/asm/unistd.h | 1 + arch/mn10300/include/uapi/asm/ioctl.h | 1 + arch/mn10300/include/uapi/asm/param.h | 1 + arch/mn10300/include/uapi/asm/posix_types.h | 1 + arch/mn10300/include/uapi/asm/ptrace.h | 1 + arch/mn10300/include/uapi/asm/sigcontext.h | 1 + arch/mn10300/include/uapi/asm/signal.h | 1 + arch/mn10300/include/uapi/asm/swab.h | 1 + arch/mn10300/include/uapi/asm/types.h | 1 + arch/mn10300/include/uapi/asm/unistd.h | 1 + arch/nios2/include/uapi/asm/byteorder.h | 1 + arch/nios2/include/uapi/asm/elf.h | 1 + arch/nios2/include/uapi/asm/ptrace.h | 1 + arch/nios2/include/uapi/asm/sigcontext.h | 1 + arch/nios2/include/uapi/asm/signal.h | 1 + arch/nios2/include/uapi/asm/swab.h | 1 + arch/nios2/include/uapi/asm/unistd.h | 1 + arch/openrisc/include/uapi/asm/elf.h | 1 + arch/openrisc/include/uapi/asm/param.h | 1 + arch/openrisc/include/uapi/asm/ptrace.h | 1 + arch/openrisc/include/uapi/asm/sigcontext.h | 1 + arch/openrisc/include/uapi/asm/unistd.h | 1 + arch/parisc/include/uapi/asm/ioctl.h | 1 + arch/powerpc/include/uapi/asm/byteorder.h | 1 + arch/powerpc/include/uapi/asm/eeh.h | 1 + arch/powerpc/include/uapi/asm/elf.h | 1 + arch/powerpc/include/uapi/asm/epapr_hcalls.h | 1 + arch/powerpc/include/uapi/asm/ipcbuf.h | 1 + arch/powerpc/include/uapi/asm/kvm.h | 1 + arch/powerpc/include/uapi/asm/kvm_para.h | 1 + arch/powerpc/include/uapi/asm/mman.h | 1 + arch/powerpc/include/uapi/asm/nvram.h | 1 + arch/powerpc/include/uapi/asm/opal-prd.h | 1 + arch/powerpc/include/uapi/asm/perf_event.h | 1 + arch/powerpc/include/uapi/asm/ps3fb.h | 1 + arch/powerpc/include/uapi/asm/ptrace.h | 1 + arch/powerpc/include/uapi/asm/sembuf.h | 1 + arch/powerpc/include/uapi/asm/shmbuf.h | 1 + arch/powerpc/include/uapi/asm/sigcontext.h | 1 + arch/powerpc/include/uapi/asm/siginfo.h | 1 + arch/powerpc/include/uapi/asm/socket.h | 1 + arch/powerpc/include/uapi/asm/spu_info.h | 1 + arch/powerpc/include/uapi/asm/stat.h | 1 + arch/powerpc/include/uapi/asm/swab.h | 1 + arch/powerpc/include/uapi/asm/termbits.h | 1 + arch/powerpc/include/uapi/asm/termios.h | 1 + arch/powerpc/include/uapi/asm/types.h | 1 + arch/powerpc/include/uapi/asm/unistd.h | 1 + arch/s390/include/uapi/asm/kvm.h | 1 + arch/s390/include/uapi/asm/kvm_para.h | 1 + arch/s390/include/uapi/asm/kvm_perf.h | 1 + arch/s390/include/uapi/asm/kvm_virtio.h | 1 + arch/s390/include/uapi/asm/virtio-ccw.h | 1 + arch/s390/include/uapi/asm/zcrypt.h | 1 + arch/sh/include/uapi/asm/unistd_64.h | 1 + arch/tile/include/uapi/arch/abi.h | 1 + arch/tile/include/uapi/arch/chip.h | 1 + arch/tile/include/uapi/arch/chip_tilegx.h | 1 + arch/tile/include/uapi/arch/chip_tilepro.h | 1 + arch/tile/include/uapi/arch/icache.h | 1 + arch/tile/include/uapi/arch/interrupts.h | 1 + arch/tile/include/uapi/arch/interrupts_32.h | 1 + arch/tile/include/uapi/arch/interrupts_64.h | 1 + arch/tile/include/uapi/arch/intreg.h | 1 + arch/tile/include/uapi/arch/opcode.h | 1 + arch/tile/include/uapi/arch/opcode_tilegx.h | 1 + arch/tile/include/uapi/arch/opcode_tilepro.h | 1 + arch/tile/include/uapi/arch/sim.h | 1 + arch/tile/include/uapi/arch/sim_def.h | 1 + arch/tile/include/uapi/arch/spr_def.h | 1 + arch/tile/include/uapi/arch/spr_def_32.h | 1 + arch/tile/include/uapi/arch/spr_def_64.h | 1 + arch/tile/include/uapi/asm/auxvec.h | 1 + arch/tile/include/uapi/asm/bitsperlong.h | 1 + arch/tile/include/uapi/asm/byteorder.h | 1 + arch/tile/include/uapi/asm/cachectl.h | 1 + arch/tile/include/uapi/asm/hardwall.h | 1 + arch/tile/include/uapi/asm/mman.h | 1 + arch/tile/include/uapi/asm/ptrace.h | 1 + arch/tile/include/uapi/asm/setup.h | 1 + arch/tile/include/uapi/asm/sigcontext.h | 1 + arch/tile/include/uapi/asm/siginfo.h | 1 + arch/tile/include/uapi/asm/signal.h | 1 + arch/tile/include/uapi/asm/swab.h | 1 + arch/tile/include/uapi/asm/unistd.h | 1 + arch/unicore32/include/uapi/asm/byteorder.h | 1 + arch/unicore32/include/uapi/asm/ptrace.h | 1 + arch/unicore32/include/uapi/asm/sigcontext.h | 1 + arch/unicore32/include/uapi/asm/unistd.h | 1 + arch/x86/include/uapi/asm/ist.h | 1 + arch/x86/include/uapi/asm/mtrr.h | 1 + arch/x86/include/uapi/asm/vmx.h | 1 + arch/xtensa/include/uapi/asm/ioctls.h | 1 + arch/xtensa/include/uapi/asm/ipcbuf.h | 1 + arch/xtensa/include/uapi/asm/mman.h | 1 + arch/xtensa/include/uapi/asm/msgbuf.h | 1 + arch/xtensa/include/uapi/asm/param.h | 1 + arch/xtensa/include/uapi/asm/poll.h | 1 + arch/xtensa/include/uapi/asm/posix_types.h | 1 + arch/xtensa/include/uapi/asm/ptrace.h | 1 + arch/xtensa/include/uapi/asm/sembuf.h | 1 + arch/xtensa/include/uapi/asm/setup.h | 1 + arch/xtensa/include/uapi/asm/shmbuf.h | 1 + arch/xtensa/include/uapi/asm/sigcontext.h | 1 + arch/xtensa/include/uapi/asm/signal.h | 1 + arch/xtensa/include/uapi/asm/socket.h | 1 + arch/xtensa/include/uapi/asm/sockios.h | 1 + arch/xtensa/include/uapi/asm/stat.h | 1 + arch/xtensa/include/uapi/asm/swab.h | 1 + arch/xtensa/include/uapi/asm/termbits.h | 1 + arch/xtensa/include/uapi/asm/types.h | 1 + include/uapi/drm/armada_drm.h | 1 + include/uapi/drm/etnaviv_drm.h | 1 + include/uapi/drm/exynos_drm.h | 1 + include/uapi/drm/omap_drm.h | 1 + include/uapi/linux/am437x-vpfe.h | 1 + include/uapi/linux/android/binder.h | 1 + include/uapi/linux/apm_bios.h | 1 + include/uapi/linux/aspeed-lpc-ctrl.h | 1 + include/uapi/linux/audit.h | 1 + include/uapi/linux/auto_dev-ioctl.h | 1 + include/uapi/linux/auto_fs.h | 1 + include/uapi/linux/auto_fs4.h | 1 + include/uapi/linux/b1lli.h | 1 + include/uapi/linux/blkzoned.h | 1 + include/uapi/linux/bpf.h | 1 + include/uapi/linux/bpf_perf_event.h | 1 + include/uapi/linux/bt-bmc.h | 1 + include/uapi/linux/btrfs.h | 1 + include/uapi/linux/caif/caif_socket.h | 1 + include/uapi/linux/caif/if_caif.h | 1 + include/uapi/linux/can.h | 1 + include/uapi/linux/can/bcm.h | 1 + include/uapi/linux/can/error.h | 1 + include/uapi/linux/can/gw.h | 1 + include/uapi/linux/can/netlink.h | 1 + include/uapi/linux/can/raw.h | 1 + include/uapi/linux/capi.h | 1 + include/uapi/linux/cec-funcs.h | 1 + include/uapi/linux/cec.h | 1 + include/uapi/linux/cgroupstats.h | 1 + include/uapi/linux/cifs/cifs_mount.h | 1 + include/uapi/linux/cn_proc.h | 1 + include/uapi/linux/coff.h | 1 + include/uapi/linux/connector.h | 1 + include/uapi/linux/cryptouser.h | 1 + include/uapi/linux/cycx_cfm.h | 1 + include/uapi/linux/dcbnl.h | 1 + include/uapi/linux/devlink.h | 1 + include/uapi/linux/dlm.h | 1 + include/uapi/linux/dlm_device.h | 1 + include/uapi/linux/dlm_netlink.h | 1 + include/uapi/linux/dlm_plock.h | 1 + include/uapi/linux/dlmconstants.h | 1 + include/uapi/linux/dm-ioctl.h | 1 + include/uapi/linux/dm-log-userspace.h | 1 + include/uapi/linux/dma-buf.h | 1 + include/uapi/linux/dqblk_xfs.h | 1 + include/uapi/linux/dvb/audio.h | 1 + include/uapi/linux/dvb/ca.h | 1 + include/uapi/linux/dvb/dmx.h | 1 + include/uapi/linux/dvb/frontend.h | 1 + include/uapi/linux/dvb/net.h | 1 + include/uapi/linux/dvb/osd.h | 1 + include/uapi/linux/dvb/version.h | 1 + include/uapi/linux/dvb/video.h | 1 + include/uapi/linux/edd.h | 1 + include/uapi/linux/elf-fdpic.h | 1 + include/uapi/linux/eventpoll.h | 1 + include/uapi/linux/fsl_hypervisor.h | 1 + include/uapi/linux/fuse.h | 1 + include/uapi/linux/gameport.h | 1 + include/uapi/linux/genwqe/genwqe_card.h | 1 + include/uapi/linux/gfs2_ondisk.h | 1 + include/uapi/linux/gigaset_dev.h | 1 + include/uapi/linux/gpio.h | 1 + include/uapi/linux/hash_info.h | 1 + include/uapi/linux/hdlc.h | 1 + include/uapi/linux/hid.h | 1 + include/uapi/linux/hiddev.h | 1 + include/uapi/linux/hidraw.h | 1 + include/uapi/linux/hsi/cs-protocol.h | 1 + include/uapi/linux/hsi/hsi_char.h | 1 + include/uapi/linux/hsr_netlink.h | 1 + include/uapi/linux/hyperv.h | 1 + include/uapi/linux/hysdn_if.h | 1 + include/uapi/linux/i2c-dev.h | 1 + include/uapi/linux/i2c.h | 1 + include/uapi/linux/i2o-dev.h | 1 + include/uapi/linux/i8k.h | 1 + include/uapi/linux/icmp.h | 1 + include/uapi/linux/if.h | 1 + include/uapi/linux/if_alg.h | 1 + include/uapi/linux/if_arcnet.h | 1 + include/uapi/linux/if_arp.h | 1 + include/uapi/linux/if_bonding.h | 1 + include/uapi/linux/if_bridge.h | 1 + include/uapi/linux/if_cablemodem.h | 1 + include/uapi/linux/if_eql.h | 1 + include/uapi/linux/if_ether.h | 1 + include/uapi/linux/if_fc.h | 1 + include/uapi/linux/if_fddi.h | 1 + include/uapi/linux/if_frad.h | 1 + include/uapi/linux/if_hippi.h | 1 + include/uapi/linux/if_infiniband.h | 1 + include/uapi/linux/if_macsec.h | 1 + include/uapi/linux/if_plip.h | 1 + include/uapi/linux/if_pppol2tp.h | 1 + include/uapi/linux/if_pppox.h | 1 + include/uapi/linux/if_team.h | 1 + include/uapi/linux/if_tun.h | 1 + include/uapi/linux/if_vlan.h | 1 + include/uapi/linux/if_x25.h | 1 + include/uapi/linux/igmp.h | 1 + include/uapi/linux/iio/events.h | 1 + include/uapi/linux/iio/types.h | 1 + include/uapi/linux/in.h | 1 + include/uapi/linux/in6.h | 1 + include/uapi/linux/input-event-codes.h | 1 + include/uapi/linux/input.h | 1 + include/uapi/linux/ip.h | 1 + include/uapi/linux/ipmi.h | 1 + include/uapi/linux/ipmi_msgdefs.h | 1 + include/uapi/linux/ipv6_route.h | 1 + include/uapi/linux/irda.h | 1 + include/uapi/linux/isdn.h | 1 + include/uapi/linux/isdn/capicmd.h | 1 + include/uapi/linux/isdn_divertif.h | 1 + include/uapi/linux/isdn_ppp.h | 1 + include/uapi/linux/isdnif.h | 1 + include/uapi/linux/ivtv.h | 1 + include/uapi/linux/ivtvfb.h | 1 + include/uapi/linux/ixjuser.h | 1 + include/uapi/linux/joystick.h | 1 + include/uapi/linux/kcm.h | 1 + include/uapi/linux/keyctl.h | 1 + include/uapi/linux/lightnvm.h | 1 + include/uapi/linux/llc.h | 1 + include/uapi/linux/loop.h | 1 + include/uapi/linux/map_to_7segment.h | 1 + include/uapi/linux/max2175.h | 1 + include/uapi/linux/mdio.h | 1 + include/uapi/linux/media-bus-format.h | 1 + include/uapi/linux/media.h | 1 + include/uapi/linux/mei.h | 1 + include/uapi/linux/meye.h | 1 + include/uapi/linux/mic_common.h | 1 + include/uapi/linux/mic_ioctl.h | 1 + include/uapi/linux/mmtimer.h | 1 + include/uapi/linux/mpls_iptunnel.h | 1 + include/uapi/linux/mqueue.h | 1 + include/uapi/linux/n_r3964.h | 1 + include/uapi/linux/nbd-netlink.h | 1 + include/uapi/linux/nbd.h | 1 + include/uapi/linux/net.h | 1 + include/uapi/linux/net_namespace.h | 1 + include/uapi/linux/netdevice.h | 1 + include/uapi/linux/netfilter/ipset/ip_set.h | 1 + include/uapi/linux/netfilter/xt_AUDIT.h | 1 + include/uapi/linux/netfilter/xt_CHECKSUM.h | 1 + include/uapi/linux/netfilter/xt_DSCP.h | 1 + include/uapi/linux/netfilter/xt_IDLETIMER.h | 1 + include/uapi/linux/netfilter/xt_NFQUEUE.h | 1 + include/uapi/linux/netfilter/xt_connmark.h | 1 + include/uapi/linux/netfilter/xt_conntrack.h | 1 + include/uapi/linux/netfilter/xt_dscp.h | 1 + include/uapi/linux/netfilter/xt_ecn.h | 1 + include/uapi/linux/netfilter/xt_osf.h | 1 + include/uapi/linux/netfilter_arp.h | 1 + include/uapi/linux/netfilter_decnet.h | 1 + include/uapi/linux/netfilter_ipv4.h | 1 + include/uapi/linux/netfilter_ipv4/ipt_ECN.h | 1 + include/uapi/linux/netfilter_ipv6.h | 1 + include/uapi/linux/nfsd/cld.h | 1 + include/uapi/linux/nilfs2_api.h | 1 + include/uapi/linux/nilfs2_ondisk.h | 1 + include/uapi/linux/nvme_ioctl.h | 1 + include/uapi/linux/omap3isp.h | 1 + include/uapi/linux/omapfb.h | 1 + include/uapi/linux/openvswitch.h | 1 + include/uapi/linux/perf_event.h | 1 + include/uapi/linux/pg.h | 1 + include/uapi/linux/phantom.h | 1 + include/uapi/linux/phonet.h | 1 + include/uapi/linux/pktcdvd.h | 1 + include/uapi/linux/posix_acl.h | 1 + include/uapi/linux/posix_acl_xattr.h | 1 + include/uapi/linux/ppdev.h | 1 + include/uapi/linux/ppp-comp.h | 1 + include/uapi/linux/ppp-ioctl.h | 1 + include/uapi/linux/ppp_defs.h | 1 + include/uapi/linux/pps.h | 1 + include/uapi/linux/ptp_clock.h | 1 + include/uapi/linux/raid/md_p.h | 1 + include/uapi/linux/raid/md_u.h | 1 + include/uapi/linux/rds.h | 1 + include/uapi/linux/rio_cm_cdev.h | 1 + include/uapi/linux/rio_mport_cdev.h | 1 + include/uapi/linux/route.h | 1 + include/uapi/linux/rpmsg.h | 1 + include/uapi/linux/scif_ioctl.h | 1 + include/uapi/linux/sctp.h | 1 + include/uapi/linux/sdla.h | 1 + include/uapi/linux/sed-opal.h | 1 + include/uapi/linux/seg6.h | 1 + include/uapi/linux/seg6_iptunnel.h | 1 + include/uapi/linux/selinux_netlink.h | 1 + include/uapi/linux/serial.h | 1 + include/uapi/linux/serial_core.h | 1 + include/uapi/linux/serial_reg.h | 1 + include/uapi/linux/serio.h | 1 + include/uapi/linux/smiapp.h | 1 + include/uapi/linux/sockios.h | 1 + include/uapi/linux/sonypi.h | 1 + include/uapi/linux/spi/spidev.h | 1 + include/uapi/linux/stm.h | 1 + include/uapi/linux/switchtec_ioctl.h | 1 + include/uapi/linux/sync_file.h | 1 + include/uapi/linux/synclink.h | 1 + include/uapi/linux/taskstats.h | 1 + include/uapi/linux/tc_act/tc_bpf.h | 1 + include/uapi/linux/tc_act/tc_skbedit.h | 1 + include/uapi/linux/tc_act/tc_skbmod.h | 1 + include/uapi/linux/tc_act/tc_tunnel_key.h | 1 + include/uapi/linux/tc_act/tc_vlan.h | 1 + include/uapi/linux/tcp.h | 1 + include/uapi/linux/telephony.h | 1 + include/uapi/linux/tipc.h | 1 + include/uapi/linux/tipc_config.h | 1 + include/uapi/linux/tipc_netlink.h | 1 + include/uapi/linux/tls.h | 1 + include/uapi/linux/toshiba.h | 1 + include/uapi/linux/udf_fs_i.h | 1 + include/uapi/linux/udp.h | 1 + include/uapi/linux/uhid.h | 1 + include/uapi/linux/uinput.h | 1 + include/uapi/linux/uio.h | 1 + include/uapi/linux/uleds.h | 1 + include/uapi/linux/ultrasound.h | 1 + include/uapi/linux/usb/audio.h | 1 + include/uapi/linux/usb/cdc-wdm.h | 1 + include/uapi/linux/usb/g_printer.h | 1 + include/uapi/linux/usb/midi.h | 1 + include/uapi/linux/usbdevice_fs.h | 1 + include/uapi/linux/userio.h | 1 + include/uapi/linux/uuid.h | 1 + include/uapi/linux/v4l2-common.h | 1 + include/uapi/linux/v4l2-controls.h | 1 + include/uapi/linux/v4l2-dv-timings.h | 1 + include/uapi/linux/v4l2-mediabus.h | 1 + include/uapi/linux/v4l2-subdev.h | 1 + include/uapi/linux/vfio.h | 1 + include/uapi/linux/videodev2.h | 1 + include/uapi/linux/vm_sockets.h | 1 + include/uapi/linux/vtpm_proxy.h | 1 + include/uapi/linux/xilinx-v4l2-controls.h | 1 + include/uapi/linux/zorro.h | 1 + include/uapi/misc/cxl.h | 1 + include/uapi/mtd/mtd-abi.h | 1 + include/uapi/mtd/mtd-user.h | 1 + include/uapi/mtd/nftl-user.h | 1 + include/uapi/mtd/ubi-user.h | 1 + include/uapi/rdma/bnxt_re-abi.h | 1 + include/uapi/rdma/cxgb3-abi.h | 1 + include/uapi/rdma/cxgb4-abi.h | 1 + include/uapi/rdma/hfi/hfi1_ioctl.h | 1 + include/uapi/rdma/hfi/hfi1_user.h | 1 + include/uapi/rdma/hns-abi.h | 1 + include/uapi/rdma/ib_user_cm.h | 1 + include/uapi/rdma/ib_user_mad.h | 1 + include/uapi/rdma/ib_user_sa.h | 1 + include/uapi/rdma/ib_user_verbs.h | 1 + include/uapi/rdma/mlx4-abi.h | 1 + include/uapi/rdma/mlx5-abi.h | 1 + include/uapi/rdma/mthca-abi.h | 1 + include/uapi/rdma/nes-abi.h | 1 + include/uapi/rdma/ocrdma-abi.h | 1 + include/uapi/rdma/qedr-abi.h | 1 + include/uapi/rdma/rdma_user_cm.h | 1 + include/uapi/rdma/rdma_user_ioctl.h | 1 + include/uapi/rdma/rdma_user_rxe.h | 1 + include/uapi/rdma/vmw_pvrdma-abi.h | 1 + include/uapi/scsi/cxlflash_ioctl.h | 1 + include/uapi/scsi/fc/fc_els.h | 1 + include/uapi/scsi/fc/fc_fs.h | 1 + include/uapi/scsi/fc/fc_gs.h | 1 + include/uapi/scsi/fc/fc_ns.h | 1 + include/uapi/scsi/scsi_bsg_fc.h | 1 + include/uapi/scsi/scsi_netlink.h | 1 + include/uapi/scsi/scsi_netlink_fc.h | 1 + include/uapi/sound/asequencer.h | 1 + include/uapi/sound/asoc.h | 1 + include/uapi/sound/asound.h | 1 + include/uapi/sound/asound_fm.h | 1 + include/uapi/sound/compress_offload.h | 1 + include/uapi/sound/compress_params.h | 1 + include/uapi/sound/emu10k1.h | 1 + include/uapi/sound/hdsp.h | 1 + include/uapi/sound/hdspm.h | 1 + include/uapi/sound/sb16_csp.h | 1 + include/uapi/sound/sfnt_info.h | 1 + include/uapi/sound/snd_sst_tokens.h | 1 + include/uapi/sound/tlv.h | 1 + include/uapi/sound/usb_stream.h | 1 + include/uapi/video/sisfb.h | 1 + include/uapi/xen/evtchn.h | 1 + include/uapi/xen/gntdev.h | 1 + include/uapi/xen/privcmd.h | 1 + tools/arch/arm/include/uapi/asm/kvm.h | 1 + tools/arch/arm64/include/uapi/asm/bitsperlong.h | 1 + tools/arch/arm64/include/uapi/asm/kvm.h | 1 + tools/arch/hexagon/include/uapi/asm/bitsperlong.h | 1 + tools/arch/mips/include/uapi/asm/bitsperlong.h | 1 + tools/arch/mips/include/uapi/asm/kvm.h | 1 + tools/arch/powerpc/include/uapi/asm/kvm.h | 1 + tools/arch/s390/include/uapi/asm/kvm.h | 1 + tools/arch/s390/include/uapi/asm/kvm_perf.h | 1 + tools/arch/tile/include/uapi/asm/bitsperlong.h | 1 + tools/arch/x86/include/uapi/asm/svm.h | 1 + tools/arch/x86/include/uapi/asm/vmx.h | 1 + 522 files changed, 522 insertions(+) (limited to 'include/uapi/linux') diff --git a/arch/alpha/include/uapi/asm/poll.h b/arch/alpha/include/uapi/asm/poll.h index c98509d3149e..b7132a305a47 100644 --- a/arch/alpha/include/uapi/asm/poll.h +++ b/arch/alpha/include/uapi/asm/poll.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/arc/include/uapi/asm/byteorder.h b/arch/arc/include/uapi/asm/byteorder.h index ea5ca444c7e3..5540111531c7 100644 --- a/arch/arc/include/uapi/asm/byteorder.h +++ b/arch/arc/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) * diff --git a/arch/arc/include/uapi/asm/cachectl.h b/arch/arc/include/uapi/asm/cachectl.h index 51c73f0255b3..0e4f2affc7e9 100644 --- a/arch/arc/include/uapi/asm/cachectl.h +++ b/arch/arc/include/uapi/asm/cachectl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) * diff --git a/arch/arc/include/uapi/asm/elf.h b/arch/arc/include/uapi/asm/elf.h index 06d95e611616..3c1dae4e5aad 100644 --- a/arch/arc/include/uapi/asm/elf.h +++ b/arch/arc/include/uapi/asm/elf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) * diff --git a/arch/arc/include/uapi/asm/page.h b/arch/arc/include/uapi/asm/page.h index 059aff38f10a..2a97e2718a21 100644 --- a/arch/arc/include/uapi/asm/page.h +++ b/arch/arc/include/uapi/asm/page.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) * diff --git a/arch/arc/include/uapi/asm/ptrace.h b/arch/arc/include/uapi/asm/ptrace.h index dd206e6b482c..2a6eff57f6dd 100644 --- a/arch/arc/include/uapi/asm/ptrace.h +++ b/arch/arc/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) * diff --git a/arch/arc/include/uapi/asm/sigcontext.h b/arch/arc/include/uapi/asm/sigcontext.h index 9678a11fc158..95f8a4380e11 100644 --- a/arch/arc/include/uapi/asm/sigcontext.h +++ b/arch/arc/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) * diff --git a/arch/arc/include/uapi/asm/signal.h b/arch/arc/include/uapi/asm/signal.h index fad62f7f42d6..ba3143a1b375 100644 --- a/arch/arc/include/uapi/asm/signal.h +++ b/arch/arc/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) * diff --git a/arch/arc/include/uapi/asm/swab.h b/arch/arc/include/uapi/asm/swab.h index 71f3918b0fc3..02109cd48ee1 100644 --- a/arch/arc/include/uapi/asm/swab.h +++ b/arch/arc/include/uapi/asm/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) * diff --git a/arch/arc/include/uapi/asm/unistd.h b/arch/arc/include/uapi/asm/unistd.h index 9a34136d84b2..517178b1daef 100644 --- a/arch/arc/include/uapi/asm/unistd.h +++ b/arch/arc/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) * diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h index 5db2d4c6a55f..1f57bbe82b6f 100644 --- a/arch/arm/include/uapi/asm/kvm.h +++ b/arch/arm/include/uapi/asm/kvm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2012 - Virtual Open Systems and Columbia University * Author: Christoffer Dall diff --git a/arch/arm/include/uapi/asm/posix_types.h b/arch/arm/include/uapi/asm/posix_types.h index d2de9cbbcd9b..6bf11ad5d6ba 100644 --- a/arch/arm/include/uapi/asm/posix_types.h +++ b/arch/arm/include/uapi/asm/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * arch/arm/include/asm/posix_types.h * diff --git a/arch/arm/include/uapi/asm/ptrace.h b/arch/arm/include/uapi/asm/ptrace.h index 5af0ed1b825a..b67cda536c25 100644 --- a/arch/arm/include/uapi/asm/ptrace.h +++ b/arch/arm/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * arch/arm/include/asm/ptrace.h * diff --git a/arch/arm/include/uapi/asm/setup.h b/arch/arm/include/uapi/asm/setup.h index 979ff4016404..6b335a9ff8c8 100644 --- a/arch/arm/include/uapi/asm/setup.h +++ b/arch/arm/include/uapi/asm/setup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * linux/include/asm/setup.h * diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h index 28bd456494a3..39b2ad997e91 100644 --- a/arch/arm/include/uapi/asm/unistd.h +++ b/arch/arm/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * arch/arm/include/asm/unistd.h * diff --git a/arch/arm64/include/uapi/asm/auxvec.h b/arch/arm64/include/uapi/asm/auxvec.h index 4cf0c17787a8..ec0a86d484e1 100644 --- a/arch/arm64/include/uapi/asm/auxvec.h +++ b/arch/arm64/include/uapi/asm/auxvec.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2012 ARM Ltd. * diff --git a/arch/arm64/include/uapi/asm/bitsperlong.h b/arch/arm64/include/uapi/asm/bitsperlong.h index fce9c2924fa3..485d60bee26c 100644 --- a/arch/arm64/include/uapi/asm/bitsperlong.h +++ b/arch/arm64/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2012 ARM Ltd. * diff --git a/arch/arm64/include/uapi/asm/byteorder.h b/arch/arm64/include/uapi/asm/byteorder.h index dc19e9537f0d..ca9cfdab33fc 100644 --- a/arch/arm64/include/uapi/asm/byteorder.h +++ b/arch/arm64/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2012 ARM Ltd. * diff --git a/arch/arm64/include/uapi/asm/fcntl.h b/arch/arm64/include/uapi/asm/fcntl.h index cd2e630c235e..f8db34f2622d 100644 --- a/arch/arm64/include/uapi/asm/fcntl.h +++ b/arch/arm64/include/uapi/asm/fcntl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2012 ARM Ltd. * diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index 4b9344cba83a..b3fdeee739ea 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2012 ARM Ltd. * diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 9f3ca24bbcc6..51149ec75fe4 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2012,2013 - ARM Ltd * Author: Marc Zyngier diff --git a/arch/arm64/include/uapi/asm/param.h b/arch/arm64/include/uapi/asm/param.h index 8e3a281d448a..b115c5557781 100644 --- a/arch/arm64/include/uapi/asm/param.h +++ b/arch/arm64/include/uapi/asm/param.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2012 ARM Ltd. * diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h index d1ff83dfe5de..67d4c33974e8 100644 --- a/arch/arm64/include/uapi/asm/ptrace.h +++ b/arch/arm64/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Based on arch/arm/include/asm/ptrace.h * diff --git a/arch/arm64/include/uapi/asm/setup.h b/arch/arm64/include/uapi/asm/setup.h index 9cf2e46fbbdf..5d703888f351 100644 --- a/arch/arm64/include/uapi/asm/setup.h +++ b/arch/arm64/include/uapi/asm/setup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Based on arch/arm/include/asm/setup.h * diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h index f0a76b9fcd6e..f6cc3061b1ae 100644 --- a/arch/arm64/include/uapi/asm/sigcontext.h +++ b/arch/arm64/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2012 ARM Ltd. * diff --git a/arch/arm64/include/uapi/asm/siginfo.h b/arch/arm64/include/uapi/asm/siginfo.h index 5a74a0853db0..574d12f86039 100644 --- a/arch/arm64/include/uapi/asm/siginfo.h +++ b/arch/arm64/include/uapi/asm/siginfo.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2012 ARM Ltd. * diff --git a/arch/arm64/include/uapi/asm/signal.h b/arch/arm64/include/uapi/asm/signal.h index 991bf5db2ca1..bdf0cfb046c9 100644 --- a/arch/arm64/include/uapi/asm/signal.h +++ b/arch/arm64/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2012 ARM Ltd. * diff --git a/arch/arm64/include/uapi/asm/stat.h b/arch/arm64/include/uapi/asm/stat.h index eeb702e5074a..313325fa22fa 100644 --- a/arch/arm64/include/uapi/asm/stat.h +++ b/arch/arm64/include/uapi/asm/stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2012 ARM Ltd. * diff --git a/arch/arm64/include/uapi/asm/statfs.h b/arch/arm64/include/uapi/asm/statfs.h index 6f6219050978..615357b6ba89 100644 --- a/arch/arm64/include/uapi/asm/statfs.h +++ b/arch/arm64/include/uapi/asm/statfs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2012 ARM Ltd. * diff --git a/arch/arm64/include/uapi/asm/ucontext.h b/arch/arm64/include/uapi/asm/ucontext.h index 791de8e89e35..ee02721a704d 100644 --- a/arch/arm64/include/uapi/asm/ucontext.h +++ b/arch/arm64/include/uapi/asm/ucontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2012 ARM Ltd. * diff --git a/arch/arm64/include/uapi/asm/unistd.h b/arch/arm64/include/uapi/asm/unistd.h index 043d17a21342..5072cbd15c82 100644 --- a/arch/arm64/include/uapi/asm/unistd.h +++ b/arch/arm64/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2012 ARM Ltd. * diff --git a/arch/blackfin/include/uapi/asm/bfin_sport.h b/arch/blackfin/include/uapi/asm/bfin_sport.h index c086de87ee61..86c36a208dc5 100644 --- a/arch/blackfin/include/uapi/asm/bfin_sport.h +++ b/arch/blackfin/include/uapi/asm/bfin_sport.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * bfin_sport.h - interface to Blackfin SPORTs * diff --git a/arch/blackfin/include/uapi/asm/cachectl.h b/arch/blackfin/include/uapi/asm/cachectl.h index 4fdab75dee15..b5c86fbbca94 100644 --- a/arch/blackfin/include/uapi/asm/cachectl.h +++ b/arch/blackfin/include/uapi/asm/cachectl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * based on the mips/cachectl.h * diff --git a/arch/blackfin/include/uapi/asm/fcntl.h b/arch/blackfin/include/uapi/asm/fcntl.h index f51ad9a4f617..0b02954f06c3 100644 --- a/arch/blackfin/include/uapi/asm/fcntl.h +++ b/arch/blackfin/include/uapi/asm/fcntl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright 2004-2008 Analog Devices Inc. * diff --git a/arch/blackfin/include/uapi/asm/fixed_code.h b/arch/blackfin/include/uapi/asm/fixed_code.h index 3bef1dca379f..707b9214bb26 100644 --- a/arch/blackfin/include/uapi/asm/fixed_code.h +++ b/arch/blackfin/include/uapi/asm/fixed_code.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * This file defines the fixed addresses where userspace programs * can find atomic code sequences. diff --git a/arch/blackfin/include/uapi/asm/poll.h b/arch/blackfin/include/uapi/asm/poll.h index 99c7d6816da0..8b094d43e9b7 100644 --- a/arch/blackfin/include/uapi/asm/poll.h +++ b/arch/blackfin/include/uapi/asm/poll.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright 2004-2009 Analog Devices Inc. * diff --git a/arch/blackfin/include/uapi/asm/posix_types.h b/arch/blackfin/include/uapi/asm/posix_types.h index 9608ef64dc47..8947c75cf638 100644 --- a/arch/blackfin/include/uapi/asm/posix_types.h +++ b/arch/blackfin/include/uapi/asm/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright 2004-2009 Analog Devices Inc. * diff --git a/arch/blackfin/include/uapi/asm/ptrace.h b/arch/blackfin/include/uapi/asm/ptrace.h index fd48bd0739d2..e4423d5560da 100644 --- a/arch/blackfin/include/uapi/asm/ptrace.h +++ b/arch/blackfin/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright 2004-2008 Analog Devices Inc. * diff --git a/arch/blackfin/include/uapi/asm/sigcontext.h b/arch/blackfin/include/uapi/asm/sigcontext.h index b58f12dc27bd..66b4d32af89c 100644 --- a/arch/blackfin/include/uapi/asm/sigcontext.h +++ b/arch/blackfin/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright 2004-2008 Analog Devices Inc. * diff --git a/arch/blackfin/include/uapi/asm/siginfo.h b/arch/blackfin/include/uapi/asm/siginfo.h index 79dfe3979123..b1db506c8d2e 100644 --- a/arch/blackfin/include/uapi/asm/siginfo.h +++ b/arch/blackfin/include/uapi/asm/siginfo.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright 2004-2008 Analog Devices Inc. * diff --git a/arch/blackfin/include/uapi/asm/stat.h b/arch/blackfin/include/uapi/asm/stat.h index d3068a750b94..458959d1a5ec 100644 --- a/arch/blackfin/include/uapi/asm/stat.h +++ b/arch/blackfin/include/uapi/asm/stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2004-2006 Analog Devices Inc. * diff --git a/arch/blackfin/include/uapi/asm/swab.h b/arch/blackfin/include/uapi/asm/swab.h index f5626b77684a..d3437933b95f 100644 --- a/arch/blackfin/include/uapi/asm/swab.h +++ b/arch/blackfin/include/uapi/asm/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright 2009 Analog Devices Inc. * diff --git a/arch/blackfin/include/uapi/asm/unistd.h b/arch/blackfin/include/uapi/asm/unistd.h index 0cb9078ef482..2d392c09323c 100644 --- a/arch/blackfin/include/uapi/asm/unistd.h +++ b/arch/blackfin/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright 2004-2009 Analog Devices Inc. * diff --git a/arch/c6x/include/uapi/asm/ptrace.h b/arch/c6x/include/uapi/asm/ptrace.h index cc0a4d99151e..9b51110a0842 100644 --- a/arch/c6x/include/uapi/asm/ptrace.h +++ b/arch/c6x/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2004, 2006, 2009, 2010 Texas Instruments Incorporated * Author: Aurelien Jacquiot (aurelien.jacquiot@jaluna.com) diff --git a/arch/c6x/include/uapi/asm/sigcontext.h b/arch/c6x/include/uapi/asm/sigcontext.h index eb702f39cde7..4e5a9a260861 100644 --- a/arch/c6x/include/uapi/asm/sigcontext.h +++ b/arch/c6x/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Port on Texas Instruments TMS320C6x architecture * diff --git a/arch/c6x/include/uapi/asm/swab.h b/arch/c6x/include/uapi/asm/swab.h index fd4bb0520e5e..c407c0497718 100644 --- a/arch/c6x/include/uapi/asm/swab.h +++ b/arch/c6x/include/uapi/asm/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2011 Texas Instruments Incorporated * Author: Mark Salter diff --git a/arch/c6x/include/uapi/asm/unistd.h b/arch/c6x/include/uapi/asm/unistd.h index 12d73d9d81f5..0d2daf7f9809 100644 --- a/arch/c6x/include/uapi/asm/unistd.h +++ b/arch/c6x/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2011 Texas Instruments Incorporated * diff --git a/arch/frv/include/uapi/asm/ipcbuf.h b/arch/frv/include/uapi/asm/ipcbuf.h index 84c7e51cb6d0..90d6445a14df 100644 --- a/arch/frv/include/uapi/asm/ipcbuf.h +++ b/arch/frv/include/uapi/asm/ipcbuf.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/frv/include/uapi/asm/ptrace.h b/arch/frv/include/uapi/asm/ptrace.h index 3887e4934683..f1d2f652d083 100644 --- a/arch/frv/include/uapi/asm/ptrace.h +++ b/arch/frv/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* ptrace.h: ptrace() relevant definitions * * Copyright (C) 2003 Red Hat, Inc. All Rights Reserved. diff --git a/arch/frv/include/uapi/asm/registers.h b/arch/frv/include/uapi/asm/registers.h index 9666119fcf6e..4caf09b6c193 100644 --- a/arch/frv/include/uapi/asm/registers.h +++ b/arch/frv/include/uapi/asm/registers.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* registers.h: register frame declarations * * Copyright (C) 2003 Red Hat, Inc. All Rights Reserved. diff --git a/arch/frv/include/uapi/asm/setup.h b/arch/frv/include/uapi/asm/setup.h index fbf3fc96aae9..f54957047900 100644 --- a/arch/frv/include/uapi/asm/setup.h +++ b/arch/frv/include/uapi/asm/setup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* setup.h: setup stuff * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. diff --git a/arch/frv/include/uapi/asm/sigcontext.h b/arch/frv/include/uapi/asm/sigcontext.h index 3b263f3cc96f..8fbb0b00afdd 100644 --- a/arch/frv/include/uapi/asm/sigcontext.h +++ b/arch/frv/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* sigcontext.h: FRV signal context * * Copyright (C) 2003 Red Hat, Inc. All Rights Reserved. diff --git a/arch/frv/include/uapi/asm/types.h b/arch/frv/include/uapi/asm/types.h index cf23149943f9..db74ad9ba6c0 100644 --- a/arch/frv/include/uapi/asm/types.h +++ b/arch/frv/include/uapi/asm/types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* types.h: FRV types * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. diff --git a/arch/hexagon/include/uapi/asm/bitsperlong.h b/arch/hexagon/include/uapi/asm/bitsperlong.h index 4a658151383d..5adca0d26913 100644 --- a/arch/hexagon/include/uapi/asm/bitsperlong.h +++ b/arch/hexagon/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved. * diff --git a/arch/hexagon/include/uapi/asm/byteorder.h b/arch/hexagon/include/uapi/asm/byteorder.h index e31f3f7d9a45..1364fa4b27e8 100644 --- a/arch/hexagon/include/uapi/asm/byteorder.h +++ b/arch/hexagon/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved. * diff --git a/arch/hexagon/include/uapi/asm/param.h b/arch/hexagon/include/uapi/asm/param.h index 5cec8c0417fb..a1283866d599 100644 --- a/arch/hexagon/include/uapi/asm/param.h +++ b/arch/hexagon/include/uapi/asm/param.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved. * diff --git a/arch/hexagon/include/uapi/asm/ptrace.h b/arch/hexagon/include/uapi/asm/ptrace.h index 065e5b32313f..f79de05b8689 100644 --- a/arch/hexagon/include/uapi/asm/ptrace.h +++ b/arch/hexagon/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Ptrace definitions for the Hexagon architecture * diff --git a/arch/hexagon/include/uapi/asm/setup.h b/arch/hexagon/include/uapi/asm/setup.h index 7e3952d6221c..8ce9428b1583 100644 --- a/arch/hexagon/include/uapi/asm/setup.h +++ b/arch/hexagon/include/uapi/asm/setup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved. * diff --git a/arch/hexagon/include/uapi/asm/sigcontext.h b/arch/hexagon/include/uapi/asm/sigcontext.h index b6ba5369ccc6..7171edb1b8b7 100644 --- a/arch/hexagon/include/uapi/asm/sigcontext.h +++ b/arch/hexagon/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved. * diff --git a/arch/hexagon/include/uapi/asm/signal.h b/arch/hexagon/include/uapi/asm/signal.h index 24b998888916..a08fc425387d 100644 --- a/arch/hexagon/include/uapi/asm/signal.h +++ b/arch/hexagon/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved. * diff --git a/arch/hexagon/include/uapi/asm/swab.h b/arch/hexagon/include/uapi/asm/swab.h index 9069e9247a2e..b39f12104da4 100644 --- a/arch/hexagon/include/uapi/asm/swab.h +++ b/arch/hexagon/include/uapi/asm/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved. * diff --git a/arch/hexagon/include/uapi/asm/unistd.h b/arch/hexagon/include/uapi/asm/unistd.h index 21517600432b..ea181e79162e 100644 --- a/arch/hexagon/include/uapi/asm/unistd.h +++ b/arch/hexagon/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Syscall support for Hexagon * diff --git a/arch/ia64/include/uapi/asm/poll.h b/arch/ia64/include/uapi/asm/poll.h index c98509d3149e..b7132a305a47 100644 --- a/arch/ia64/include/uapi/asm/poll.h +++ b/arch/ia64/include/uapi/asm/poll.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/m32r/include/uapi/asm/ptrace.h b/arch/m32r/include/uapi/asm/ptrace.h index f6930a822517..99aec86cf5c0 100644 --- a/arch/m32r/include/uapi/asm/ptrace.h +++ b/arch/m32r/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * linux/include/asm-m32r/ptrace.h * diff --git a/arch/m68k/include/uapi/asm/bootinfo.h b/arch/m68k/include/uapi/asm/bootinfo.h index a48cf544c762..38d3140381fa 100644 --- a/arch/m68k/include/uapi/asm/bootinfo.h +++ b/arch/m68k/include/uapi/asm/bootinfo.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * asm/bootinfo.h -- Definition of the Linux/m68k boot information structure * diff --git a/arch/m68k/include/uapi/asm/setup.h b/arch/m68k/include/uapi/asm/setup.h index 6a6dc636761e..25fe26d5597c 100644 --- a/arch/m68k/include/uapi/asm/setup.h +++ b/arch/m68k/include/uapi/asm/setup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* ** asm/setup.h -- Definition of the Linux/m68k setup information ** diff --git a/arch/metag/include/uapi/asm/unistd.h b/arch/metag/include/uapi/asm/unistd.h index 459b6ec15848..9f72c4cfcfb5 100644 --- a/arch/metag/include/uapi/asm/unistd.h +++ b/arch/metag/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (C) 2012 Imagination Technologies Ltd. * diff --git a/arch/microblaze/include/uapi/asm/elf.h b/arch/microblaze/include/uapi/asm/elf.h index e9bcdb6e0086..6b656de29f00 100644 --- a/arch/microblaze/include/uapi/asm/elf.h +++ b/arch/microblaze/include/uapi/asm/elf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2008-2009 Michal Simek * Copyright (C) 2008-2009 PetaLogix diff --git a/arch/microblaze/include/uapi/asm/ptrace.h b/arch/microblaze/include/uapi/asm/ptrace.h index d31238a5f946..46dd94cb7802 100644 --- a/arch/microblaze/include/uapi/asm/ptrace.h +++ b/arch/microblaze/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2006 Atmark Techno, Inc. * diff --git a/arch/microblaze/include/uapi/asm/setup.h b/arch/microblaze/include/uapi/asm/setup.h index 76bc2acee6af..6831794e6f2c 100644 --- a/arch/microblaze/include/uapi/asm/setup.h +++ b/arch/microblaze/include/uapi/asm/setup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2007-2009 Michal Simek * Copyright (C) 2007-2009 PetaLogix diff --git a/arch/microblaze/include/uapi/asm/sigcontext.h b/arch/microblaze/include/uapi/asm/sigcontext.h index 55873c80c917..47eb2e2111bb 100644 --- a/arch/microblaze/include/uapi/asm/sigcontext.h +++ b/arch/microblaze/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2006 Atmark Techno, Inc. * diff --git a/arch/microblaze/include/uapi/asm/unistd.h b/arch/microblaze/include/uapi/asm/unistd.h index a88b3c11cc20..eb156f914793 100644 --- a/arch/microblaze/include/uapi/asm/unistd.h +++ b/arch/microblaze/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2007-2008 Michal Simek * Copyright (C) 2006 Atmark Techno, Inc. diff --git a/arch/mips/include/uapi/asm/auxvec.h b/arch/mips/include/uapi/asm/auxvec.h index 45ba259a3618..612c2c41f60b 100644 --- a/arch/mips/include/uapi/asm/auxvec.h +++ b/arch/mips/include/uapi/asm/auxvec.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (C) 2015 Imagination Technologies * Author: Alex Smith diff --git a/arch/mips/include/uapi/asm/bitfield.h b/arch/mips/include/uapi/asm/bitfield.h index ad9861359cea..b11713d8743e 100644 --- a/arch/mips/include/uapi/asm/bitfield.h +++ b/arch/mips/include/uapi/asm/bitfield.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/break.h b/arch/mips/include/uapi/asm/break.h index 9c4265cbf151..10380b1bc601 100644 --- a/arch/mips/include/uapi/asm/break.h +++ b/arch/mips/include/uapi/asm/break.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/byteorder.h b/arch/mips/include/uapi/asm/byteorder.h index 9579051ff1c7..b4edc85f9c30 100644 --- a/arch/mips/include/uapi/asm/byteorder.h +++ b/arch/mips/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/cachectl.h b/arch/mips/include/uapi/asm/cachectl.h index 230390908773..af7639ff423b 100644 --- a/arch/mips/include/uapi/asm/cachectl.h +++ b/arch/mips/include/uapi/asm/cachectl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/errno.h b/arch/mips/include/uapi/asm/errno.h index 02d645d7aa9a..2fb714e2d6d8 100644 --- a/arch/mips/include/uapi/asm/errno.h +++ b/arch/mips/include/uapi/asm/errno.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/fcntl.h b/arch/mips/include/uapi/asm/fcntl.h index 6ca432f00860..42e13dead543 100644 --- a/arch/mips/include/uapi/asm/fcntl.h +++ b/arch/mips/include/uapi/asm/fcntl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/inst.h b/arch/mips/include/uapi/asm/inst.h index 6abea5183d7c..c05dcf5ab414 100644 --- a/arch/mips/include/uapi/asm/inst.h +++ b/arch/mips/include/uapi/asm/inst.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Format of an instruction in memory. * diff --git a/arch/mips/include/uapi/asm/ioctl.h b/arch/mips/include/uapi/asm/ioctl.h index c515a1a4c47c..1050a6ea211c 100644 --- a/arch/mips/include/uapi/asm/ioctl.h +++ b/arch/mips/include/uapi/asm/ioctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/ioctls.h b/arch/mips/include/uapi/asm/ioctls.h index 1609cb0907ac..890245a9f0c4 100644 --- a/arch/mips/include/uapi/asm/ioctls.h +++ b/arch/mips/include/uapi/asm/ioctls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/kvm.h b/arch/mips/include/uapi/asm/kvm.h index 0318c6b442ab..edcf717c4327 100644 --- a/arch/mips/include/uapi/asm/kvm.h +++ b/arch/mips/include/uapi/asm/kvm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h index da3216007fe0..20c3df7a8fdd 100644 --- a/arch/mips/include/uapi/asm/mman.h +++ b/arch/mips/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/param.h b/arch/mips/include/uapi/asm/param.h index da3920fce9ad..3f337ed66f6a 100644 --- a/arch/mips/include/uapi/asm/param.h +++ b/arch/mips/include/uapi/asm/param.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/posix_types.h b/arch/mips/include/uapi/asm/posix_types.h index fa03ec3fbf89..6aa49c10f88f 100644 --- a/arch/mips/include/uapi/asm/posix_types.h +++ b/arch/mips/include/uapi/asm/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/ptrace.h b/arch/mips/include/uapi/asm/ptrace.h index 91a3d197ede3..f3c025445e45 100644 --- a/arch/mips/include/uapi/asm/ptrace.h +++ b/arch/mips/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/reg.h b/arch/mips/include/uapi/asm/reg.h index 081e377f4f02..56d15cb8109f 100644 --- a/arch/mips/include/uapi/asm/reg.h +++ b/arch/mips/include/uapi/asm/reg.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Various register offset definitions for debuggers, core file * examiners and whatnot. diff --git a/arch/mips/include/uapi/asm/resource.h b/arch/mips/include/uapi/asm/resource.h index b26439d4ab0b..372ff8f4bc06 100644 --- a/arch/mips/include/uapi/asm/resource.h +++ b/arch/mips/include/uapi/asm/resource.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/sgidefs.h b/arch/mips/include/uapi/asm/sgidefs.h index 876442fcfb32..26143e3b7c26 100644 --- a/arch/mips/include/uapi/asm/sgidefs.h +++ b/arch/mips/include/uapi/asm/sgidefs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/sigcontext.h b/arch/mips/include/uapi/asm/sigcontext.h index 5cbd9ae6421f..d0a540e88bb4 100644 --- a/arch/mips/include/uapi/asm/sigcontext.h +++ b/arch/mips/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/siginfo.h b/arch/mips/include/uapi/asm/siginfo.h index cf6113bbcb98..f17d8163dec6 100644 --- a/arch/mips/include/uapi/asm/siginfo.h +++ b/arch/mips/include/uapi/asm/siginfo.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/signal.h b/arch/mips/include/uapi/asm/signal.h index addb9f556b71..53104b10aae2 100644 --- a/arch/mips/include/uapi/asm/signal.h +++ b/arch/mips/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 6c755bc07975..49c3d4795963 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/sockios.h b/arch/mips/include/uapi/asm/sockios.h index 419fbe661da3..5b40a88593fa 100644 --- a/arch/mips/include/uapi/asm/sockios.h +++ b/arch/mips/include/uapi/asm/sockios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Socket-level I/O control calls. * diff --git a/arch/mips/include/uapi/asm/stat.h b/arch/mips/include/uapi/asm/stat.h index b47bc541bbc0..95416f366d7f 100644 --- a/arch/mips/include/uapi/asm/stat.h +++ b/arch/mips/include/uapi/asm/stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/statfs.h b/arch/mips/include/uapi/asm/statfs.h index 3305c834fc16..f4174dcaef5e 100644 --- a/arch/mips/include/uapi/asm/statfs.h +++ b/arch/mips/include/uapi/asm/statfs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/swab.h b/arch/mips/include/uapi/asm/swab.h index 23cd9b118c9e..d6795fe4ec59 100644 --- a/arch/mips/include/uapi/asm/swab.h +++ b/arch/mips/include/uapi/asm/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/sysmips.h b/arch/mips/include/uapi/asm/sysmips.h index ae637e907856..4c009e10dfd2 100644 --- a/arch/mips/include/uapi/asm/sysmips.h +++ b/arch/mips/include/uapi/asm/sysmips.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Definitions for the MIPS sysmips(2) call * diff --git a/arch/mips/include/uapi/asm/termbits.h b/arch/mips/include/uapi/asm/termbits.h index 2750203e1e7d..dfeffba729b7 100644 --- a/arch/mips/include/uapi/asm/termbits.h +++ b/arch/mips/include/uapi/asm/termbits.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/termios.h b/arch/mips/include/uapi/asm/termios.h index baeb2fa87451..d6c576794178 100644 --- a/arch/mips/include/uapi/asm/termios.h +++ b/arch/mips/include/uapi/asm/termios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/types.h b/arch/mips/include/uapi/asm/types.h index f3dd9ff0cc0c..6b21504842a4 100644 --- a/arch/mips/include/uapi/asm/types.h +++ b/arch/mips/include/uapi/asm/types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h index 78faf4292e90..bb05e9916a5f 100644 --- a/arch/mips/include/uapi/asm/unistd.h +++ b/arch/mips/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/arch/mn10300/include/uapi/asm/ioctl.h b/arch/mn10300/include/uapi/asm/ioctl.h index b279fe06dfe5..b809c4566e5f 100644 --- a/arch/mn10300/include/uapi/asm/ioctl.h +++ b/arch/mn10300/include/uapi/asm/ioctl.h @@ -1 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #include diff --git a/arch/mn10300/include/uapi/asm/param.h b/arch/mn10300/include/uapi/asm/param.h index 02a0ca6f13ce..e0020d7742bd 100644 --- a/arch/mn10300/include/uapi/asm/param.h +++ b/arch/mn10300/include/uapi/asm/param.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* MN10300 Kernel parameters * * Copyright (C) 2007 Matsushita Electric Industrial Co., Ltd. diff --git a/arch/mn10300/include/uapi/asm/posix_types.h b/arch/mn10300/include/uapi/asm/posix_types.h index d31eeea480cf..6b4cfc7136e9 100644 --- a/arch/mn10300/include/uapi/asm/posix_types.h +++ b/arch/mn10300/include/uapi/asm/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* MN10300 POSIX types * * Copyright (C) 2007 Matsushita Electric Industrial Co., Ltd. diff --git a/arch/mn10300/include/uapi/asm/ptrace.h b/arch/mn10300/include/uapi/asm/ptrace.h index 71b2251b7bff..f485c481a266 100644 --- a/arch/mn10300/include/uapi/asm/ptrace.h +++ b/arch/mn10300/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* MN10300 Exception frame layout and ptrace constants * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. diff --git a/arch/mn10300/include/uapi/asm/sigcontext.h b/arch/mn10300/include/uapi/asm/sigcontext.h index 4de3afff4ad7..1c361fabb977 100644 --- a/arch/mn10300/include/uapi/asm/sigcontext.h +++ b/arch/mn10300/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* MN10300 Userspace signal context * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. diff --git a/arch/mn10300/include/uapi/asm/signal.h b/arch/mn10300/include/uapi/asm/signal.h index f423a08d7eeb..566cb199d5ac 100644 --- a/arch/mn10300/include/uapi/asm/signal.h +++ b/arch/mn10300/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* MN10300 Signal definitions * * Copyright (C) 2007 Matsushita Electric Industrial Co., Ltd. diff --git a/arch/mn10300/include/uapi/asm/swab.h b/arch/mn10300/include/uapi/asm/swab.h index bd818a820ca8..d2284dd27ad4 100644 --- a/arch/mn10300/include/uapi/asm/swab.h +++ b/arch/mn10300/include/uapi/asm/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* MN10300 Byte-order primitive construction * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. diff --git a/arch/mn10300/include/uapi/asm/types.h b/arch/mn10300/include/uapi/asm/types.h index 8b3f0501b9bc..7d2a697e2937 100644 --- a/arch/mn10300/include/uapi/asm/types.h +++ b/arch/mn10300/include/uapi/asm/types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* MN10300 Basic type definitions * * Copyright (C) 2007 Matsushita Electric Industrial Co., Ltd. diff --git a/arch/mn10300/include/uapi/asm/unistd.h b/arch/mn10300/include/uapi/asm/unistd.h index e28ac3f42479..c0c96b650692 100644 --- a/arch/mn10300/include/uapi/asm/unistd.h +++ b/arch/mn10300/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* MN10300 System call number list * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. diff --git a/arch/nios2/include/uapi/asm/byteorder.h b/arch/nios2/include/uapi/asm/byteorder.h index 3ab5dc20d757..639007a5544e 100644 --- a/arch/nios2/include/uapi/asm/byteorder.h +++ b/arch/nios2/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (C) 2009 Thomas Chou * Copyright (C) 2004 Microtronix Datacom Ltd diff --git a/arch/nios2/include/uapi/asm/elf.h b/arch/nios2/include/uapi/asm/elf.h index 6f06d3b2949e..ab0df71f81b2 100644 --- a/arch/nios2/include/uapi/asm/elf.h +++ b/arch/nios2/include/uapi/asm/elf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (C) 2011 Tobias Klauser * diff --git a/arch/nios2/include/uapi/asm/ptrace.h b/arch/nios2/include/uapi/asm/ptrace.h index 1d35de90a977..2b91dbe5bcfe 100644 --- a/arch/nios2/include/uapi/asm/ptrace.h +++ b/arch/nios2/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2010 Tobias Klauser * Copyright (C) 2004 Microtronix Datacom Ltd diff --git a/arch/nios2/include/uapi/asm/sigcontext.h b/arch/nios2/include/uapi/asm/sigcontext.h index b67944a50927..204ae3475b4e 100644 --- a/arch/nios2/include/uapi/asm/sigcontext.h +++ b/arch/nios2/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (C) 2004, Microtronix Datacom Ltd. * diff --git a/arch/nios2/include/uapi/asm/signal.h b/arch/nios2/include/uapi/asm/signal.h index f29ee6314481..b0d983068fa5 100644 --- a/arch/nios2/include/uapi/asm/signal.h +++ b/arch/nios2/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright Altera Corporation (C) 2013. All rights reserved * diff --git a/arch/nios2/include/uapi/asm/swab.h b/arch/nios2/include/uapi/asm/swab.h index b4e22ebaeb17..9750547a5f82 100644 --- a/arch/nios2/include/uapi/asm/swab.h +++ b/arch/nios2/include/uapi/asm/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2012 Tobias Klauser * Copyright (C) 2011 Pyramid Technical Consultants, Inc. diff --git a/arch/nios2/include/uapi/asm/unistd.h b/arch/nios2/include/uapi/asm/unistd.h index 51a32c71ce2b..b6bdae04bc84 100644 --- a/arch/nios2/include/uapi/asm/unistd.h +++ b/arch/nios2/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2013 Altera Corporation * diff --git a/arch/openrisc/include/uapi/asm/elf.h b/arch/openrisc/include/uapi/asm/elf.h index 88842760e66f..e892d5061685 100644 --- a/arch/openrisc/include/uapi/asm/elf.h +++ b/arch/openrisc/include/uapi/asm/elf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * OpenRISC Linux * diff --git a/arch/openrisc/include/uapi/asm/param.h b/arch/openrisc/include/uapi/asm/param.h index c39a336610e2..103471e310ca 100644 --- a/arch/openrisc/include/uapi/asm/param.h +++ b/arch/openrisc/include/uapi/asm/param.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * OpenRISC Linux * diff --git a/arch/openrisc/include/uapi/asm/ptrace.h b/arch/openrisc/include/uapi/asm/ptrace.h index 9760bd17fbcc..d4fab268f6aa 100644 --- a/arch/openrisc/include/uapi/asm/ptrace.h +++ b/arch/openrisc/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * OpenRISC Linux * diff --git a/arch/openrisc/include/uapi/asm/sigcontext.h b/arch/openrisc/include/uapi/asm/sigcontext.h index b79c2b19afbe..8ab775fc3450 100644 --- a/arch/openrisc/include/uapi/asm/sigcontext.h +++ b/arch/openrisc/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * OpenRISC Linux * diff --git a/arch/openrisc/include/uapi/asm/unistd.h b/arch/openrisc/include/uapi/asm/unistd.h index 471905bd7745..9a3ee389631e 100644 --- a/arch/openrisc/include/uapi/asm/unistd.h +++ b/arch/openrisc/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * OpenRISC Linux * diff --git a/arch/parisc/include/uapi/asm/ioctl.h b/arch/parisc/include/uapi/asm/ioctl.h index ec8efa02beda..b509bcc94a03 100644 --- a/arch/parisc/include/uapi/asm/ioctl.h +++ b/arch/parisc/include/uapi/asm/ioctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Linux/PA-RISC Project (http://www.parisc-linux.org/) * Copyright (C) 1999,2003 Matthew Wilcox < willy at debian . org > diff --git a/arch/powerpc/include/uapi/asm/byteorder.h b/arch/powerpc/include/uapi/asm/byteorder.h index ca931d074000..8ef66f7d9db9 100644 --- a/arch/powerpc/include/uapi/asm/byteorder.h +++ b/arch/powerpc/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ #ifndef _ASM_POWERPC_BYTEORDER_H #define _ASM_POWERPC_BYTEORDER_H diff --git a/arch/powerpc/include/uapi/asm/eeh.h b/arch/powerpc/include/uapi/asm/eeh.h index 291b7d1814a6..28186071fafc 100644 --- a/arch/powerpc/include/uapi/asm/eeh.h +++ b/arch/powerpc/include/uapi/asm/eeh.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License, version 2, as diff --git a/arch/powerpc/include/uapi/asm/elf.h b/arch/powerpc/include/uapi/asm/elf.h index b2c6fdd5ac30..5f201d40bcca 100644 --- a/arch/powerpc/include/uapi/asm/elf.h +++ b/arch/powerpc/include/uapi/asm/elf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * ELF register definitions.. * diff --git a/arch/powerpc/include/uapi/asm/epapr_hcalls.h b/arch/powerpc/include/uapi/asm/epapr_hcalls.h index b4504f394427..90a0ee6d0bb3 100644 --- a/arch/powerpc/include/uapi/asm/epapr_hcalls.h +++ b/arch/powerpc/include/uapi/asm/epapr_hcalls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * ePAPR hcall interface * diff --git a/arch/powerpc/include/uapi/asm/ipcbuf.h b/arch/powerpc/include/uapi/asm/ipcbuf.h index 2c3e1d94db1d..21e1e0ec0ba2 100644 --- a/arch/powerpc/include/uapi/asm/ipcbuf.h +++ b/arch/powerpc/include/uapi/asm/ipcbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ #ifndef _ASM_POWERPC_IPCBUF_H #define _ASM_POWERPC_IPCBUF_H diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h index 8cf8f0c96906..61d6049f4c1e 100644 --- a/arch/powerpc/include/uapi/asm/kvm.h +++ b/arch/powerpc/include/uapi/asm/kvm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License, version 2, as diff --git a/arch/powerpc/include/uapi/asm/kvm_para.h b/arch/powerpc/include/uapi/asm/kvm_para.h index 91e42f09b323..01555c6ae0f5 100644 --- a/arch/powerpc/include/uapi/asm/kvm_para.h +++ b/arch/powerpc/include/uapi/asm/kvm_para.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License, version 2, as diff --git a/arch/powerpc/include/uapi/asm/mman.h b/arch/powerpc/include/uapi/asm/mman.h index 03c06ba7464f..e63bc37e33af 100644 --- a/arch/powerpc/include/uapi/asm/mman.h +++ b/arch/powerpc/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License diff --git a/arch/powerpc/include/uapi/asm/nvram.h b/arch/powerpc/include/uapi/asm/nvram.h index 608bdc8aedd1..c92c7f056a91 100644 --- a/arch/powerpc/include/uapi/asm/nvram.h +++ b/arch/powerpc/include/uapi/asm/nvram.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * NVRAM definitions and access functions. * diff --git a/arch/powerpc/include/uapi/asm/opal-prd.h b/arch/powerpc/include/uapi/asm/opal-prd.h index 319ff4a26158..1869cf83a870 100644 --- a/arch/powerpc/include/uapi/asm/opal-prd.h +++ b/arch/powerpc/include/uapi/asm/opal-prd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * OPAL Runtime Diagnostics interface driver * Supported on POWERNV platform diff --git a/arch/powerpc/include/uapi/asm/perf_event.h b/arch/powerpc/include/uapi/asm/perf_event.h index 80a4d40cf5bc..ce488e48db44 100644 --- a/arch/powerpc/include/uapi/asm/perf_event.h +++ b/arch/powerpc/include/uapi/asm/perf_event.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2013 Michael Ellerman, IBM Corp. * diff --git a/arch/powerpc/include/uapi/asm/ps3fb.h b/arch/powerpc/include/uapi/asm/ps3fb.h index e7233a849680..fd7e3a0d35d5 100644 --- a/arch/powerpc/include/uapi/asm/ps3fb.h +++ b/arch/powerpc/include/uapi/asm/ps3fb.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2006 Sony Computer Entertainment Inc. * Copyright 2006, 2007 Sony Corporation diff --git a/arch/powerpc/include/uapi/asm/ptrace.h b/arch/powerpc/include/uapi/asm/ptrace.h index 8036b385417d..5e3edc2a7634 100644 --- a/arch/powerpc/include/uapi/asm/ptrace.h +++ b/arch/powerpc/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (C) 2001 PPC64 Team, IBM Corp * diff --git a/arch/powerpc/include/uapi/asm/sembuf.h b/arch/powerpc/include/uapi/asm/sembuf.h index 99a41938ae3d..8f393d60f02d 100644 --- a/arch/powerpc/include/uapi/asm/sembuf.h +++ b/arch/powerpc/include/uapi/asm/sembuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ #ifndef _ASM_POWERPC_SEMBUF_H #define _ASM_POWERPC_SEMBUF_H diff --git a/arch/powerpc/include/uapi/asm/shmbuf.h b/arch/powerpc/include/uapi/asm/shmbuf.h index 8efa39698b6c..deb1c3e503d3 100644 --- a/arch/powerpc/include/uapi/asm/shmbuf.h +++ b/arch/powerpc/include/uapi/asm/shmbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ #ifndef _ASM_POWERPC_SHMBUF_H #define _ASM_POWERPC_SHMBUF_H diff --git a/arch/powerpc/include/uapi/asm/sigcontext.h b/arch/powerpc/include/uapi/asm/sigcontext.h index 3ad0c7f001a9..2fbe485acdb4 100644 --- a/arch/powerpc/include/uapi/asm/sigcontext.h +++ b/arch/powerpc/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ #ifndef _ASM_POWERPC_SIGCONTEXT_H #define _ASM_POWERPC_SIGCONTEXT_H diff --git a/arch/powerpc/include/uapi/asm/siginfo.h b/arch/powerpc/include/uapi/asm/siginfo.h index ccce3ef5cd86..1a691141e49f 100644 --- a/arch/powerpc/include/uapi/asm/siginfo.h +++ b/arch/powerpc/include/uapi/asm/siginfo.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ #ifndef _ASM_POWERPC_SIGINFO_H #define _ASM_POWERPC_SIGINFO_H diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h index 3c590c7c42c0..94de465e0920 100644 --- a/arch/powerpc/include/uapi/asm/socket.h +++ b/arch/powerpc/include/uapi/asm/socket.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ #ifndef _ASM_POWERPC_SOCKET_H #define _ASM_POWERPC_SOCKET_H diff --git a/arch/powerpc/include/uapi/asm/spu_info.h b/arch/powerpc/include/uapi/asm/spu_info.h index ed071bf97707..cabfcbba9eac 100644 --- a/arch/powerpc/include/uapi/asm/spu_info.h +++ b/arch/powerpc/include/uapi/asm/spu_info.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * SPU info structures * diff --git a/arch/powerpc/include/uapi/asm/stat.h b/arch/powerpc/include/uapi/asm/stat.h index 84880b80cc1c..afd25f2ff4e8 100644 --- a/arch/powerpc/include/uapi/asm/stat.h +++ b/arch/powerpc/include/uapi/asm/stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ #ifndef _ASM_POWERPC_STAT_H #define _ASM_POWERPC_STAT_H /* diff --git a/arch/powerpc/include/uapi/asm/swab.h b/arch/powerpc/include/uapi/asm/swab.h index b6c368aa5c05..17b16c44d20c 100644 --- a/arch/powerpc/include/uapi/asm/swab.h +++ b/arch/powerpc/include/uapi/asm/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License diff --git a/arch/powerpc/include/uapi/asm/termbits.h b/arch/powerpc/include/uapi/asm/termbits.h index 549d700e18f2..ed18bc61f63d 100644 --- a/arch/powerpc/include/uapi/asm/termbits.h +++ b/arch/powerpc/include/uapi/asm/termbits.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ #ifndef _ASM_POWERPC_TERMBITS_H #define _ASM_POWERPC_TERMBITS_H diff --git a/arch/powerpc/include/uapi/asm/termios.h b/arch/powerpc/include/uapi/asm/termios.h index 6cca5cdfec04..5d07fc89bcb6 100644 --- a/arch/powerpc/include/uapi/asm/termios.h +++ b/arch/powerpc/include/uapi/asm/termios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Liberally adapted from alpha/termios.h. In particular, the c_cc[] * fields have been reordered so that termio & termios share the diff --git a/arch/powerpc/include/uapi/asm/types.h b/arch/powerpc/include/uapi/asm/types.h index 4b8ab990a3c1..327616fb70e4 100644 --- a/arch/powerpc/include/uapi/asm/types.h +++ b/arch/powerpc/include/uapi/asm/types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * This file is never included by application software unless * explicitly requested (e.g., via linux/types.h) in which case the diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h index b85f14228857..df8684f31919 100644 --- a/arch/powerpc/include/uapi/asm/unistd.h +++ b/arch/powerpc/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * This file contains the system call numbers. * diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h index cd7359e23d86..9ad172dcd912 100644 --- a/arch/s390/include/uapi/asm/kvm.h +++ b/arch/s390/include/uapi/asm/kvm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_KVM_S390_H #define __LINUX_KVM_S390_H /* diff --git a/arch/s390/include/uapi/asm/kvm_para.h b/arch/s390/include/uapi/asm/kvm_para.h index ff1f4e7b3015..0dc86b3a7cb0 100644 --- a/arch/s390/include/uapi/asm/kvm_para.h +++ b/arch/s390/include/uapi/asm/kvm_para.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * User API definitions for paravirtual devices on s390 * diff --git a/arch/s390/include/uapi/asm/kvm_perf.h b/arch/s390/include/uapi/asm/kvm_perf.h index 397282727e21..c36c97ffdc6f 100644 --- a/arch/s390/include/uapi/asm/kvm_perf.h +++ b/arch/s390/include/uapi/asm/kvm_perf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Definitions for perf-kvm on s390 * diff --git a/arch/s390/include/uapi/asm/kvm_virtio.h b/arch/s390/include/uapi/asm/kvm_virtio.h index 44a438ca9e72..73283677a132 100644 --- a/arch/s390/include/uapi/asm/kvm_virtio.h +++ b/arch/s390/include/uapi/asm/kvm_virtio.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * definition for virtio for kvm on s390 * diff --git a/arch/s390/include/uapi/asm/virtio-ccw.h b/arch/s390/include/uapi/asm/virtio-ccw.h index a9a4ebf79fa7..967aad390105 100644 --- a/arch/s390/include/uapi/asm/virtio-ccw.h +++ b/arch/s390/include/uapi/asm/virtio-ccw.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Definitions for virtio-ccw devices. * diff --git a/arch/s390/include/uapi/asm/zcrypt.h b/arch/s390/include/uapi/asm/zcrypt.h index a777f87ef889..137ef473584e 100644 --- a/arch/s390/include/uapi/asm/zcrypt.h +++ b/arch/s390/include/uapi/asm/zcrypt.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * include/asm-s390/zcrypt.h * diff --git a/arch/sh/include/uapi/asm/unistd_64.h b/arch/sh/include/uapi/asm/unistd_64.h index ce0cb3598b62..6f809a53aa24 100644 --- a/arch/sh/include/uapi/asm/unistd_64.h +++ b/arch/sh/include/uapi/asm/unistd_64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_SH_UNISTD_64_H #define __ASM_SH_UNISTD_64_H diff --git a/arch/tile/include/uapi/arch/abi.h b/arch/tile/include/uapi/arch/abi.h index 328e62260272..df161a484730 100644 --- a/arch/tile/include/uapi/arch/abi.h +++ b/arch/tile/include/uapi/arch/abi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2010 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/arch/chip.h b/arch/tile/include/uapi/arch/chip.h index 4c91f90b9369..7f55c6856c89 100644 --- a/arch/tile/include/uapi/arch/chip.h +++ b/arch/tile/include/uapi/arch/chip.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2010 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/arch/chip_tilegx.h b/arch/tile/include/uapi/arch/chip_tilegx.h index ea8e4f2c9483..c2a71a43b21c 100644 --- a/arch/tile/include/uapi/arch/chip_tilegx.h +++ b/arch/tile/include/uapi/arch/chip_tilegx.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2011 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/arch/chip_tilepro.h b/arch/tile/include/uapi/arch/chip_tilepro.h index 70017699a74c..a8a3ed144dfe 100644 --- a/arch/tile/include/uapi/arch/chip_tilepro.h +++ b/arch/tile/include/uapi/arch/chip_tilepro.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2010 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/arch/icache.h b/arch/tile/include/uapi/arch/icache.h index 762eafa8a11e..ff85a5d77f16 100644 --- a/arch/tile/include/uapi/arch/icache.h +++ b/arch/tile/include/uapi/arch/icache.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2010 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/arch/interrupts.h b/arch/tile/include/uapi/arch/interrupts.h index 20f8f07d2de9..c288b5d82b4d 100644 --- a/arch/tile/include/uapi/arch/interrupts.h +++ b/arch/tile/include/uapi/arch/interrupts.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2010 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/arch/interrupts_32.h b/arch/tile/include/uapi/arch/interrupts_32.h index 2efe3f68b2d6..a748752cec16 100644 --- a/arch/tile/include/uapi/arch/interrupts_32.h +++ b/arch/tile/include/uapi/arch/interrupts_32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2010 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/arch/interrupts_64.h b/arch/tile/include/uapi/arch/interrupts_64.h index 13c9f9182348..142eaff3c244 100644 --- a/arch/tile/include/uapi/arch/interrupts_64.h +++ b/arch/tile/include/uapi/arch/interrupts_64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2011 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/arch/intreg.h b/arch/tile/include/uapi/arch/intreg.h index 1cf2fbf74306..5387fb645bb8 100644 --- a/arch/tile/include/uapi/arch/intreg.h +++ b/arch/tile/include/uapi/arch/intreg.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2017 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/arch/opcode.h b/arch/tile/include/uapi/arch/opcode.h index 92d15229ecec..a9ce5961a028 100644 --- a/arch/tile/include/uapi/arch/opcode.h +++ b/arch/tile/include/uapi/arch/opcode.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2011 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/arch/opcode_tilegx.h b/arch/tile/include/uapi/arch/opcode_tilegx.h index 9e46eaa847d4..948ea544567f 100644 --- a/arch/tile/include/uapi/arch/opcode_tilegx.h +++ b/arch/tile/include/uapi/arch/opcode_tilegx.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* TILE-Gx opcode information. * * Copyright 2011 Tilera Corporation. All Rights Reserved. diff --git a/arch/tile/include/uapi/arch/opcode_tilepro.h b/arch/tile/include/uapi/arch/opcode_tilepro.h index 4451cff1a861..0d633688de63 100644 --- a/arch/tile/include/uapi/arch/opcode_tilepro.h +++ b/arch/tile/include/uapi/arch/opcode_tilepro.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* TILEPro opcode information. * * Copyright 2011 Tilera Corporation. All Rights Reserved. diff --git a/arch/tile/include/uapi/arch/sim.h b/arch/tile/include/uapi/arch/sim.h index e54b7b0527f3..c4183dcd2ea7 100644 --- a/arch/tile/include/uapi/arch/sim.h +++ b/arch/tile/include/uapi/arch/sim.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2010 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/arch/sim_def.h b/arch/tile/include/uapi/arch/sim_def.h index 1c069537ae41..f74f9943770d 100644 --- a/arch/tile/include/uapi/arch/sim_def.h +++ b/arch/tile/include/uapi/arch/sim_def.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2010 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/arch/spr_def.h b/arch/tile/include/uapi/arch/spr_def.h index c250c5adb1a6..743428615cda 100644 --- a/arch/tile/include/uapi/arch/spr_def.h +++ b/arch/tile/include/uapi/arch/spr_def.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2010 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/arch/spr_def_32.h b/arch/tile/include/uapi/arch/spr_def_32.h index 78daa3146d25..64122d6160e1 100644 --- a/arch/tile/include/uapi/arch/spr_def_32.h +++ b/arch/tile/include/uapi/arch/spr_def_32.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2010 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/arch/spr_def_64.h b/arch/tile/include/uapi/arch/spr_def_64.h index 67a6c1751e3b..d183cbb31aa7 100644 --- a/arch/tile/include/uapi/arch/spr_def_64.h +++ b/arch/tile/include/uapi/arch/spr_def_64.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2011 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/asm/auxvec.h b/arch/tile/include/uapi/asm/auxvec.h index f497123ed980..922383ce8f4f 100644 --- a/arch/tile/include/uapi/asm/auxvec.h +++ b/arch/tile/include/uapi/asm/auxvec.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2010 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/asm/bitsperlong.h b/arch/tile/include/uapi/asm/bitsperlong.h index 58c771f2af2f..57cca78c0fbb 100644 --- a/arch/tile/include/uapi/asm/bitsperlong.h +++ b/arch/tile/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2010 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/asm/byteorder.h b/arch/tile/include/uapi/asm/byteorder.h index 6b8fa2e1cf6e..d508e61c1e56 100644 --- a/arch/tile/include/uapi/asm/byteorder.h +++ b/arch/tile/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2011 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/asm/cachectl.h b/arch/tile/include/uapi/asm/cachectl.h index 572ddcad2090..ed8bac28a1b9 100644 --- a/arch/tile/include/uapi/asm/cachectl.h +++ b/arch/tile/include/uapi/asm/cachectl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2011 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/asm/hardwall.h b/arch/tile/include/uapi/asm/hardwall.h index c2169d4f4010..f02e9132ae71 100644 --- a/arch/tile/include/uapi/asm/hardwall.h +++ b/arch/tile/include/uapi/asm/hardwall.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2010 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/asm/mman.h b/arch/tile/include/uapi/asm/mman.h index 63ee13faf17d..9b7add95926b 100644 --- a/arch/tile/include/uapi/asm/mman.h +++ b/arch/tile/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2010 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/asm/ptrace.h b/arch/tile/include/uapi/asm/ptrace.h index d03b829857e8..667ed742f4dd 100644 --- a/arch/tile/include/uapi/asm/ptrace.h +++ b/arch/tile/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2010 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/asm/setup.h b/arch/tile/include/uapi/asm/setup.h index e6f7da265ac3..6d1dfdddad6c 100644 --- a/arch/tile/include/uapi/asm/setup.h +++ b/arch/tile/include/uapi/asm/setup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2010 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/asm/sigcontext.h b/arch/tile/include/uapi/asm/sigcontext.h index 39ff5d1a232d..4003d5cc9202 100644 --- a/arch/tile/include/uapi/asm/sigcontext.h +++ b/arch/tile/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2010 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/asm/siginfo.h b/arch/tile/include/uapi/asm/siginfo.h index e83f931aa1f0..f234d24fff55 100644 --- a/arch/tile/include/uapi/asm/siginfo.h +++ b/arch/tile/include/uapi/asm/siginfo.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2010 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/asm/signal.h b/arch/tile/include/uapi/asm/signal.h index ef0d32d84a4c..7b3c814e00f0 100644 --- a/arch/tile/include/uapi/asm/signal.h +++ b/arch/tile/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2010 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/asm/swab.h b/arch/tile/include/uapi/asm/swab.h index 7c37b38f6c8d..36952353a31d 100644 --- a/arch/tile/include/uapi/asm/swab.h +++ b/arch/tile/include/uapi/asm/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2010 Tilera Corporation. All Rights Reserved. * diff --git a/arch/tile/include/uapi/asm/unistd.h b/arch/tile/include/uapi/asm/unistd.h index 24e9187e85a8..1a169ec92ef8 100644 --- a/arch/tile/include/uapi/asm/unistd.h +++ b/arch/tile/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2010 Tilera Corporation. All Rights Reserved. * diff --git a/arch/unicore32/include/uapi/asm/byteorder.h b/arch/unicore32/include/uapi/asm/byteorder.h index ebe1b3fef3e3..864fe4814cf4 100644 --- a/arch/unicore32/include/uapi/asm/byteorder.h +++ b/arch/unicore32/include/uapi/asm/byteorder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * linux/arch/unicore32/include/asm/byteorder.h * diff --git a/arch/unicore32/include/uapi/asm/ptrace.h b/arch/unicore32/include/uapi/asm/ptrace.h index 187aa2e98a53..2820de83e37d 100644 --- a/arch/unicore32/include/uapi/asm/ptrace.h +++ b/arch/unicore32/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * linux/arch/unicore32/include/asm/ptrace.h * diff --git a/arch/unicore32/include/uapi/asm/sigcontext.h b/arch/unicore32/include/uapi/asm/sigcontext.h index 6a2d7671c052..79e56f28e4b5 100644 --- a/arch/unicore32/include/uapi/asm/sigcontext.h +++ b/arch/unicore32/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * linux/arch/unicore32/include/asm/sigcontext.h * diff --git a/arch/unicore32/include/uapi/asm/unistd.h b/arch/unicore32/include/uapi/asm/unistd.h index 1f63c476528e..65856eaab163 100644 --- a/arch/unicore32/include/uapi/asm/unistd.h +++ b/arch/unicore32/include/uapi/asm/unistd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * linux/arch/unicore32/include/asm/unistd.h * diff --git a/arch/x86/include/uapi/asm/ist.h b/arch/x86/include/uapi/asm/ist.h index bad9f5ea4070..eac5b207939d 100644 --- a/arch/x86/include/uapi/asm/ist.h +++ b/arch/x86/include/uapi/asm/ist.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Include file for the interface to IST BIOS * Copyright 2002 Andy Grover diff --git a/arch/x86/include/uapi/asm/mtrr.h b/arch/x86/include/uapi/asm/mtrr.h index 7528dcf59691..376563f2bac1 100644 --- a/arch/x86/include/uapi/asm/mtrr.h +++ b/arch/x86/include/uapi/asm/mtrr.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.0+ WITH Linux-syscall-note */ /* Generic MTRR (Memory Type Range Register) ioctls. Copyright (C) 1997-1999 Richard Gooch diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index 690a2dcf4078..f0b0c90dd398 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * vmx.h: VMX Architecture related definitions * Copyright (c) 2004, Intel Corporation. diff --git a/arch/xtensa/include/uapi/asm/ioctls.h b/arch/xtensa/include/uapi/asm/ioctls.h index 47d82c09be7b..ec43609cbfc5 100644 --- a/arch/xtensa/include/uapi/asm/ioctls.h +++ b/arch/xtensa/include/uapi/asm/ioctls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/asm-xtensa/ioctls.h * diff --git a/arch/xtensa/include/uapi/asm/ipcbuf.h b/arch/xtensa/include/uapi/asm/ipcbuf.h index c33aa6a42145..a57afa0b606f 100644 --- a/arch/xtensa/include/uapi/asm/ipcbuf.h +++ b/arch/xtensa/include/uapi/asm/ipcbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/asm-xtensa/ipcbuf.h * diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h index b15b278aa314..2bfe590694fc 100644 --- a/arch/xtensa/include/uapi/asm/mman.h +++ b/arch/xtensa/include/uapi/asm/mman.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/asm-xtensa/mman.h * diff --git a/arch/xtensa/include/uapi/asm/msgbuf.h b/arch/xtensa/include/uapi/asm/msgbuf.h index 693c96755280..36e2e103ca38 100644 --- a/arch/xtensa/include/uapi/asm/msgbuf.h +++ b/arch/xtensa/include/uapi/asm/msgbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/asm-xtensa/msgbuf.h * diff --git a/arch/xtensa/include/uapi/asm/param.h b/arch/xtensa/include/uapi/asm/param.h index 87bc2eae630e..e6feb4ee0590 100644 --- a/arch/xtensa/include/uapi/asm/param.h +++ b/arch/xtensa/include/uapi/asm/param.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/asm-xtensa/param.h * diff --git a/arch/xtensa/include/uapi/asm/poll.h b/arch/xtensa/include/uapi/asm/poll.h index 9d2d5993f068..4d249040b33d 100644 --- a/arch/xtensa/include/uapi/asm/poll.h +++ b/arch/xtensa/include/uapi/asm/poll.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/asm-xtensa/poll.h * diff --git a/arch/xtensa/include/uapi/asm/posix_types.h b/arch/xtensa/include/uapi/asm/posix_types.h index 6e96be0d02d3..1dc67592881f 100644 --- a/arch/xtensa/include/uapi/asm/posix_types.h +++ b/arch/xtensa/include/uapi/asm/posix_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/asm-xtensa/posix_types.h * diff --git a/arch/xtensa/include/uapi/asm/ptrace.h b/arch/xtensa/include/uapi/asm/ptrace.h index 8853a0d544c8..a10b42963703 100644 --- a/arch/xtensa/include/uapi/asm/ptrace.h +++ b/arch/xtensa/include/uapi/asm/ptrace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/asm-xtensa/ptrace.h * diff --git a/arch/xtensa/include/uapi/asm/sembuf.h b/arch/xtensa/include/uapi/asm/sembuf.h index c15870493b33..f61b6331a10c 100644 --- a/arch/xtensa/include/uapi/asm/sembuf.h +++ b/arch/xtensa/include/uapi/asm/sembuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/asm-xtensa/sembuf.h * diff --git a/arch/xtensa/include/uapi/asm/setup.h b/arch/xtensa/include/uapi/asm/setup.h index 9fa8ad979361..57e6c210e84f 100644 --- a/arch/xtensa/include/uapi/asm/setup.h +++ b/arch/xtensa/include/uapi/asm/setup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/asm-xtensa/setup.h * diff --git a/arch/xtensa/include/uapi/asm/shmbuf.h b/arch/xtensa/include/uapi/asm/shmbuf.h index ad4b0121782c..26550bdc8430 100644 --- a/arch/xtensa/include/uapi/asm/shmbuf.h +++ b/arch/xtensa/include/uapi/asm/shmbuf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/asm-xtensa/shmbuf.h * diff --git a/arch/xtensa/include/uapi/asm/sigcontext.h b/arch/xtensa/include/uapi/asm/sigcontext.h index 03383af8c3b7..9cbf39e63f74 100644 --- a/arch/xtensa/include/uapi/asm/sigcontext.h +++ b/arch/xtensa/include/uapi/asm/sigcontext.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/asm-xtensa/sigcontext.h * diff --git a/arch/xtensa/include/uapi/asm/signal.h b/arch/xtensa/include/uapi/asm/signal.h index 586756ee267a..005dec5bfde4 100644 --- a/arch/xtensa/include/uapi/asm/signal.h +++ b/arch/xtensa/include/uapi/asm/signal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/asm-xtensa/signal.h * diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h index 220059999e74..75a07b8119a9 100644 --- a/arch/xtensa/include/uapi/asm/socket.h +++ b/arch/xtensa/include/uapi/asm/socket.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/asm-xtensa/socket.h * diff --git a/arch/xtensa/include/uapi/asm/sockios.h b/arch/xtensa/include/uapi/asm/sockios.h index efe0af379f01..fb8ac3607189 100644 --- a/arch/xtensa/include/uapi/asm/sockios.h +++ b/arch/xtensa/include/uapi/asm/sockios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/asm-xtensa/sockios.h * diff --git a/arch/xtensa/include/uapi/asm/stat.h b/arch/xtensa/include/uapi/asm/stat.h index c4992038cee0..7b4d90d6d771 100644 --- a/arch/xtensa/include/uapi/asm/stat.h +++ b/arch/xtensa/include/uapi/asm/stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/asm-xtensa/stat.h * diff --git a/arch/xtensa/include/uapi/asm/swab.h b/arch/xtensa/include/uapi/asm/swab.h index 226a39162310..e677cf4cc092 100644 --- a/arch/xtensa/include/uapi/asm/swab.h +++ b/arch/xtensa/include/uapi/asm/swab.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/asm-xtensa/swab.h * diff --git a/arch/xtensa/include/uapi/asm/termbits.h b/arch/xtensa/include/uapi/asm/termbits.h index 0d6c8715b24f..d4206a7c5138 100644 --- a/arch/xtensa/include/uapi/asm/termbits.h +++ b/arch/xtensa/include/uapi/asm/termbits.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/asm-xtensa/termbits.h * diff --git a/arch/xtensa/include/uapi/asm/types.h b/arch/xtensa/include/uapi/asm/types.h index 2efc921506c4..12db8ac38750 100644 --- a/arch/xtensa/include/uapi/asm/types.h +++ b/arch/xtensa/include/uapi/asm/types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/asm-xtensa/types.h * diff --git a/include/uapi/drm/armada_drm.h b/include/uapi/drm/armada_drm.h index 0cb932416cfe..af1c14c837c5 100644 --- a/include/uapi/drm/armada_drm.h +++ b/include/uapi/drm/armada_drm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2012 Russell King * With inspiration from the i915 driver diff --git a/include/uapi/drm/etnaviv_drm.h b/include/uapi/drm/etnaviv_drm.h index 76f6f78a352b..d4463f3fa427 100644 --- a/include/uapi/drm/etnaviv_drm.h +++ b/include/uapi/drm/etnaviv_drm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2015 Etnaviv Project * diff --git a/include/uapi/drm/exynos_drm.h b/include/uapi/drm/exynos_drm.h index cb3e9f9d029f..d01087b2a651 100644 --- a/include/uapi/drm/exynos_drm.h +++ b/include/uapi/drm/exynos_drm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* exynos_drm.h * * Copyright (c) 2011 Samsung Electronics Co., Ltd. diff --git a/include/uapi/drm/omap_drm.h b/include/uapi/drm/omap_drm.h index fd5e3ea53f2b..1fccffef9e27 100644 --- a/include/uapi/drm/omap_drm.h +++ b/include/uapi/drm/omap_drm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/uapi/drm/omap_drm.h * diff --git a/include/uapi/linux/am437x-vpfe.h b/include/uapi/linux/am437x-vpfe.h index d75774317b9b..beae3521ca91 100644 --- a/include/uapi/linux/am437x-vpfe.h +++ b/include/uapi/linux/am437x-vpfe.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2013 - 2014 Texas Instruments, Inc. * diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h index 84a9a0944e13..bfaec6903b8b 100644 --- a/include/uapi/linux/android/binder.h +++ b/include/uapi/linux/android/binder.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2008 Google, Inc. * diff --git a/include/uapi/linux/apm_bios.h b/include/uapi/linux/apm_bios.h index df79bca1b898..37ee11dba94c 100644 --- a/include/uapi/linux/apm_bios.h +++ b/include/uapi/linux/apm_bios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Include file for the interface to an APM BIOS * Copyright 1994-2001 Stephen Rothwell (sfr@canb.auug.org.au) diff --git a/include/uapi/linux/aspeed-lpc-ctrl.h b/include/uapi/linux/aspeed-lpc-ctrl.h index c328c976c684..53abffcde3c6 100644 --- a/include/uapi/linux/aspeed-lpc-ctrl.h +++ b/include/uapi/linux/aspeed-lpc-ctrl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright 2017 IBM Corp. * diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index 0714a66f0e0c..7668582db6ba 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* audit.h -- Auditing support * * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina. diff --git a/include/uapi/linux/auto_dev-ioctl.h b/include/uapi/linux/auto_dev-ioctl.h index 5558db8e6646..374742651c30 100644 --- a/include/uapi/linux/auto_dev-ioctl.h +++ b/include/uapi/linux/auto_dev-ioctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright 2008 Red Hat, Inc. All rights reserved. * Copyright 2008 Ian Kent diff --git a/include/uapi/linux/auto_fs.h b/include/uapi/linux/auto_fs.h index aa63451ef20a..2a4432c7a4b4 100644 --- a/include/uapi/linux/auto_fs.h +++ b/include/uapi/linux/auto_fs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright 1997 Transmeta Corporation - All Rights Reserved * diff --git a/include/uapi/linux/auto_fs4.h b/include/uapi/linux/auto_fs4.h index 9453e9a07c9d..1f608e27a06f 100644 --- a/include/uapi/linux/auto_fs4.h +++ b/include/uapi/linux/auto_fs4.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright 1999-2000 Jeremy Fitzhardinge * diff --git a/include/uapi/linux/b1lli.h b/include/uapi/linux/b1lli.h index 713f712685d3..4ae6ac9950df 100644 --- a/include/uapi/linux/b1lli.h +++ b/include/uapi/linux/b1lli.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* $Id: b1lli.h,v 1.8.8.3 2001/09/23 22:25:05 kai Exp $ * * ISDN lowlevel-module for AVM B1-card. diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h index 40d1d7bff537..e3c70fe6bf0f 100644 --- a/include/uapi/linux/blkzoned.h +++ b/include/uapi/linux/blkzoned.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Zoned block devices handling. * diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f90860d1f897..8012b4ff959b 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * * This program is free software; you can redistribute it and/or diff --git a/include/uapi/linux/bpf_perf_event.h b/include/uapi/linux/bpf_perf_event.h index 067427259820..af549d4ecf1b 100644 --- a/include/uapi/linux/bpf_perf_event.h +++ b/include/uapi/linux/bpf_perf_event.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* Copyright (c) 2016 Facebook * * This program is free software; you can redistribute it and/or diff --git a/include/uapi/linux/bt-bmc.h b/include/uapi/linux/bt-bmc.h index d9ec766a63d0..2ffdccfccc1d 100644 --- a/include/uapi/linux/bt-bmc.h +++ b/include/uapi/linux/bt-bmc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (c) 2015-2016, IBM Corporation. * diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 378230c163d5..6cdfd12cd14c 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2007 Oracle. All rights reserved. * diff --git a/include/uapi/linux/caif/caif_socket.h b/include/uapi/linux/caif/caif_socket.h index 586e9f98184f..10ec1d1cf68e 100644 --- a/include/uapi/linux/caif/caif_socket.h +++ b/include/uapi/linux/caif/caif_socket.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* linux/caif_socket.h * CAIF Definitions for CAIF socket and network layer * Copyright (C) ST-Ericsson AB 2010 diff --git a/include/uapi/linux/caif/if_caif.h b/include/uapi/linux/caif/if_caif.h index 7618aabe8c6b..74bca19403fa 100644 --- a/include/uapi/linux/caif/if_caif.h +++ b/include/uapi/linux/caif/if_caif.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) ST-Ericsson AB 2010 * Author: Sjur Brendeland diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h index c48d93a28d1a..d7f97ac197a9 100644 --- a/include/uapi/linux/can.h +++ b/include/uapi/linux/can.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * linux/can.h * diff --git a/include/uapi/linux/can/bcm.h b/include/uapi/linux/can/bcm.h index cefb304414ba..0fb328d93148 100644 --- a/include/uapi/linux/can/bcm.h +++ b/include/uapi/linux/can/bcm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * linux/can/bcm.h * diff --git a/include/uapi/linux/can/error.h b/include/uapi/linux/can/error.h index 1c508be9687f..bfc4b5d22a5e 100644 --- a/include/uapi/linux/can/error.h +++ b/include/uapi/linux/can/error.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * linux/can/error.h * diff --git a/include/uapi/linux/can/gw.h b/include/uapi/linux/can/gw.h index 5079b9d57e31..7bee7a0b9800 100644 --- a/include/uapi/linux/can/gw.h +++ b/include/uapi/linux/can/gw.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * linux/can/gw.h * diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index fdf75f74fdaf..96710e76d5ce 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * linux/can/netlink.h * diff --git a/include/uapi/linux/can/raw.h b/include/uapi/linux/can/raw.h index 8735f1080385..be3b36e7ff61 100644 --- a/include/uapi/linux/can/raw.h +++ b/include/uapi/linux/can/raw.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * linux/can/raw.h * diff --git a/include/uapi/linux/capi.h b/include/uapi/linux/capi.h index 7b145fd7afb6..31f946f8a88d 100644 --- a/include/uapi/linux/capi.h +++ b/include/uapi/linux/capi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* $Id: capi.h,v 1.4.6.1 2001/09/23 22:25:05 kai Exp $ * * CAPI 2.0 Interface for Linux diff --git a/include/uapi/linux/cec-funcs.h b/include/uapi/linux/cec-funcs.h index 270b251a3d9b..28e8a2a86e16 100644 --- a/include/uapi/linux/cec-funcs.h +++ b/include/uapi/linux/cec-funcs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * cec - HDMI Consumer Electronics Control message functions * diff --git a/include/uapi/linux/cec.h b/include/uapi/linux/cec.h index 4351c3481aea..c3114c989e91 100644 --- a/include/uapi/linux/cec.h +++ b/include/uapi/linux/cec.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * cec - HDMI Consumer Electronics Control public header * diff --git a/include/uapi/linux/cgroupstats.h b/include/uapi/linux/cgroupstats.h index 3753c33160d1..aa306e4cd6c1 100644 --- a/include/uapi/linux/cgroupstats.h +++ b/include/uapi/linux/cgroupstats.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1 WITH Linux-syscall-note */ /* cgroupstats.h - exporting per-cgroup statistics * * Copyright IBM Corporation, 2007 diff --git a/include/uapi/linux/cifs/cifs_mount.h b/include/uapi/linux/cifs/cifs_mount.h index d7e4c6ce6171..69829205fdb5 100644 --- a/include/uapi/linux/cifs/cifs_mount.h +++ b/include/uapi/linux/cifs/cifs_mount.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1+ WITH Linux-syscall-note */ /* * include/uapi/linux/cifs/cifs_mount.h * diff --git a/include/uapi/linux/cn_proc.h b/include/uapi/linux/cn_proc.h index f6c271035bbd..68ff25414700 100644 --- a/include/uapi/linux/cn_proc.h +++ b/include/uapi/linux/cn_proc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1 WITH Linux-syscall-note */ /* * cn_proc.h - process events connector * diff --git a/include/uapi/linux/coff.h b/include/uapi/linux/coff.h index 6354a7fe22b2..e4a79f80b9a0 100644 --- a/include/uapi/linux/coff.h +++ b/include/uapi/linux/coff.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* This file is derived from the GAS 2.1.4 assembler control file. The GAS product is under the GNU General Public License, version 2 or later. As such, this file is also under that license. diff --git a/include/uapi/linux/connector.h b/include/uapi/linux/connector.h index 4cb283505e45..3738936149a2 100644 --- a/include/uapi/linux/connector.h +++ b/include/uapi/linux/connector.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * connector.h * diff --git a/include/uapi/linux/cryptouser.h b/include/uapi/linux/cryptouser.h index fdcbb3c29083..19bf0ca6d635 100644 --- a/include/uapi/linux/cryptouser.h +++ b/include/uapi/linux/cryptouser.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Crypto user configuration API. * diff --git a/include/uapi/linux/cycx_cfm.h b/include/uapi/linux/cycx_cfm.h index 032d26ed8384..51f541942ff9 100644 --- a/include/uapi/linux/cycx_cfm.h +++ b/include/uapi/linux/cycx_cfm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * cycx_cfm.h Cyclom 2X WAN Link Driver. * Definitions for the Cyclom 2X Firmware Module (CFM). diff --git a/include/uapi/linux/dcbnl.h b/include/uapi/linux/dcbnl.h index 3ea470f35e40..b6170a6af7c2 100644 --- a/include/uapi/linux/dcbnl.h +++ b/include/uapi/linux/dcbnl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (c) 2008-2011, Intel Corporation. * diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 0cbca96c66b9..6665df69e26a 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * include/uapi/linux/devlink.h - Network physical device Netlink interface * Copyright (c) 2016 Mellanox Technologies. All rights reserved. diff --git a/include/uapi/linux/dlm.h b/include/uapi/linux/dlm.h index 1f73cc06168f..0d2eca287567 100644 --- a/include/uapi/linux/dlm.h +++ b/include/uapi/linux/dlm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /****************************************************************************** ******************************************************************************* ** diff --git a/include/uapi/linux/dlm_device.h b/include/uapi/linux/dlm_device.h index df56c8ff0769..f880d2831160 100644 --- a/include/uapi/linux/dlm_device.h +++ b/include/uapi/linux/dlm_device.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /****************************************************************************** ******************************************************************************* ** diff --git a/include/uapi/linux/dlm_netlink.h b/include/uapi/linux/dlm_netlink.h index ef1e2e08769a..5dc3a67d353d 100644 --- a/include/uapi/linux/dlm_netlink.h +++ b/include/uapi/linux/dlm_netlink.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2007 Red Hat, Inc. All rights reserved. * diff --git a/include/uapi/linux/dlm_plock.h b/include/uapi/linux/dlm_plock.h index 6ae692c909cb..63b6c1fd9169 100644 --- a/include/uapi/linux/dlm_plock.h +++ b/include/uapi/linux/dlm_plock.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2005-2008 Red Hat, Inc. All rights reserved. * diff --git a/include/uapi/linux/dlmconstants.h b/include/uapi/linux/dlmconstants.h index 2857bdc5b27b..a8ae47c32a37 100644 --- a/include/uapi/linux/dlmconstants.h +++ b/include/uapi/linux/dlmconstants.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /****************************************************************************** ******************************************************************************* ** diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h index ccaea525340b..14c44ec8b622 100644 --- a/include/uapi/linux/dm-ioctl.h +++ b/include/uapi/linux/dm-ioctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (C) 2001 - 2003 Sistina Software (UK) Limited. * Copyright (C) 2004 - 2009 Red Hat, Inc. All rights reserved. diff --git a/include/uapi/linux/dm-log-userspace.h b/include/uapi/linux/dm-log-userspace.h index 05e91e14c501..5c47a8603376 100644 --- a/include/uapi/linux/dm-log-userspace.h +++ b/include/uapi/linux/dm-log-userspace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (C) 2006-2009 Red Hat, Inc. * diff --git a/include/uapi/linux/dma-buf.h b/include/uapi/linux/dma-buf.h index fb0dedb7c121..d75df5210a4a 100644 --- a/include/uapi/linux/dma-buf.h +++ b/include/uapi/linux/dma-buf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Framework for buffer objects that can be shared across devices/subsystems. * diff --git a/include/uapi/linux/dqblk_xfs.h b/include/uapi/linux/dqblk_xfs.h index 11b3b31faf14..03d890b80ebc 100644 --- a/include/uapi/linux/dqblk_xfs.h +++ b/include/uapi/linux/dqblk_xfs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1+ WITH Linux-syscall-note */ /* * Copyright (c) 1995-2001,2004 Silicon Graphics, Inc. All Rights Reserved. * diff --git a/include/uapi/linux/dvb/audio.h b/include/uapi/linux/dvb/audio.h index d47bccd604e4..69f7a85d81b1 100644 --- a/include/uapi/linux/dvb/audio.h +++ b/include/uapi/linux/dvb/audio.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1+ WITH Linux-syscall-note */ /* * audio.h * diff --git a/include/uapi/linux/dvb/ca.h b/include/uapi/linux/dvb/ca.h index cb150029fdff..dffa59e95ebb 100644 --- a/include/uapi/linux/dvb/ca.h +++ b/include/uapi/linux/dvb/ca.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1+ WITH Linux-syscall-note */ /* * ca.h * diff --git a/include/uapi/linux/dvb/dmx.h b/include/uapi/linux/dvb/dmx.h index 4aa5f6a1815a..c10f1324b4ca 100644 --- a/include/uapi/linux/dvb/dmx.h +++ b/include/uapi/linux/dvb/dmx.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1+ WITH Linux-syscall-note */ /* * dmx.h * diff --git a/include/uapi/linux/dvb/frontend.h b/include/uapi/linux/dvb/frontend.h index 861cacd5711f..f46de499b51b 100644 --- a/include/uapi/linux/dvb/frontend.h +++ b/include/uapi/linux/dvb/frontend.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1+ WITH Linux-syscall-note */ /* * frontend.h * diff --git a/include/uapi/linux/dvb/net.h b/include/uapi/linux/dvb/net.h index 89d805f9a5a6..0c550ef93f2c 100644 --- a/include/uapi/linux/dvb/net.h +++ b/include/uapi/linux/dvb/net.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1+ WITH Linux-syscall-note */ /* * net.h * diff --git a/include/uapi/linux/dvb/osd.h b/include/uapi/linux/dvb/osd.h index 880e68435832..e163508b9ae8 100644 --- a/include/uapi/linux/dvb/osd.h +++ b/include/uapi/linux/dvb/osd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1+ WITH Linux-syscall-note */ /* * osd.h * diff --git a/include/uapi/linux/dvb/version.h b/include/uapi/linux/dvb/version.h index e53e2ad4444f..02e32ea83984 100644 --- a/include/uapi/linux/dvb/version.h +++ b/include/uapi/linux/dvb/version.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1+ WITH Linux-syscall-note */ /* * version.h * diff --git a/include/uapi/linux/dvb/video.h b/include/uapi/linux/dvb/video.h index c83d40b8a8a4..4d51f98182bb 100644 --- a/include/uapi/linux/dvb/video.h +++ b/include/uapi/linux/dvb/video.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1+ WITH Linux-syscall-note */ /* * video.h * diff --git a/include/uapi/linux/edd.h b/include/uapi/linux/edd.h index 89240a04e4c8..0fe3e02aec65 100644 --- a/include/uapi/linux/edd.h +++ b/include/uapi/linux/edd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * linux/include/linux/edd.h * Copyright (C) 2002, 2003, 2004 Dell Inc. diff --git a/include/uapi/linux/elf-fdpic.h b/include/uapi/linux/elf-fdpic.h index 3921e33aec8e..4fcc6cfebe18 100644 --- a/include/uapi/linux/elf-fdpic.h +++ b/include/uapi/linux/elf-fdpic.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* elf-fdpic.h: FDPIC ELF load map * * Copyright (C) 2003 Red Hat, Inc. All Rights Reserved. diff --git a/include/uapi/linux/eventpoll.h b/include/uapi/linux/eventpoll.h index f4d5c998cc2b..63e21be30f15 100644 --- a/include/uapi/linux/eventpoll.h +++ b/include/uapi/linux/eventpoll.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * include/linux/eventpoll.h ( Efficient event polling implementation ) * Copyright (C) 2001,...,2006 Davide Libenzi diff --git a/include/uapi/linux/fsl_hypervisor.h b/include/uapi/linux/fsl_hypervisor.h index 1bf04967fec4..1e237fba951f 100644 --- a/include/uapi/linux/fsl_hypervisor.h +++ b/include/uapi/linux/fsl_hypervisor.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * Freescale hypervisor ioctl and kernel interface * diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 42fa977e3b14..4b5001c57f46 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ /* This file defines the kernel interface of FUSE Copyright (C) 2001-2008 Miklos Szeredi diff --git a/include/uapi/linux/gameport.h b/include/uapi/linux/gameport.h index 49b29b068f40..8fb40b4930ac 100644 --- a/include/uapi/linux/gameport.h +++ b/include/uapi/linux/gameport.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (c) 1999-2002 Vojtech Pavlik * diff --git a/include/uapi/linux/genwqe/genwqe_card.h b/include/uapi/linux/genwqe/genwqe_card.h index baa93fb4cd4f..bc779a5d258d 100644 --- a/include/uapi/linux/genwqe/genwqe_card.h +++ b/include/uapi/linux/genwqe/genwqe_card.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __GENWQE_CARD_H__ #define __GENWQE_CARD_H__ diff --git a/include/uapi/linux/gfs2_ondisk.h b/include/uapi/linux/gfs2_ondisk.h index 7c4be7711c81..5156bad77b47 100644 --- a/include/uapi/linux/gfs2_ondisk.h +++ b/include/uapi/linux/gfs2_ondisk.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. diff --git a/include/uapi/linux/gigaset_dev.h b/include/uapi/linux/gigaset_dev.h index 258ba82937e7..279551af8ebf 100644 --- a/include/uapi/linux/gigaset_dev.h +++ b/include/uapi/linux/gigaset_dev.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * interface to user space for the gigaset driver * diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h index 333d3544c964..1bf6e6df084b 100644 --- a/include/uapi/linux/gpio.h +++ b/include/uapi/linux/gpio.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * - userspace ABI for the GPIO character devices * diff --git a/include/uapi/linux/hash_info.h b/include/uapi/linux/hash_info.h index ebf8fd885dd5..eea5d02c58de 100644 --- a/include/uapi/linux/hash_info.h +++ b/include/uapi/linux/hash_info.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Hash Info: Hash algorithms information * diff --git a/include/uapi/linux/hdlc.h b/include/uapi/linux/hdlc.h index 2c5f0aff4cf9..d89cb3ee7c70 100644 --- a/include/uapi/linux/hdlc.h +++ b/include/uapi/linux/hdlc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Generic HDLC support routines for Linux * diff --git a/include/uapi/linux/hid.h b/include/uapi/linux/hid.h index b60f4842bd97..b34492a87a8a 100644 --- a/include/uapi/linux/hid.h +++ b/include/uapi/linux/hid.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (c) 1999 Andreas Gal * Copyright (c) 2000-2001 Vojtech Pavlik diff --git a/include/uapi/linux/hiddev.h b/include/uapi/linux/hiddev.h index 7df7884bf5c4..53d6cad7a999 100644 --- a/include/uapi/linux/hiddev.h +++ b/include/uapi/linux/hiddev.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (c) 1999-2000 Vojtech Pavlik * diff --git a/include/uapi/linux/hidraw.h b/include/uapi/linux/hidraw.h index f5b732979a7c..98e2c493de85 100644 --- a/include/uapi/linux/hidraw.h +++ b/include/uapi/linux/hidraw.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (c) 2007 Jiri Kosina */ diff --git a/include/uapi/linux/hsi/cs-protocol.h b/include/uapi/linux/hsi/cs-protocol.h index f153d6ea7c62..c7f6e7672cb5 100644 --- a/include/uapi/linux/hsi/cs-protocol.h +++ b/include/uapi/linux/hsi/cs-protocol.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * cmt-speech interface definitions * diff --git a/include/uapi/linux/hsi/hsi_char.h b/include/uapi/linux/hsi/hsi_char.h index c00a463d55f9..91623b0398b1 100644 --- a/include/uapi/linux/hsi/hsi_char.h +++ b/include/uapi/linux/hsi/hsi_char.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Part of the HSI character device driver. * diff --git a/include/uapi/linux/hsr_netlink.h b/include/uapi/linux/hsr_netlink.h index 2475cb8a53af..c218ef9c35dd 100644 --- a/include/uapi/linux/hsr_netlink.h +++ b/include/uapi/linux/hsr_netlink.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright 2011-2013 Autronica Fire and Security AS * diff --git a/include/uapi/linux/hyperv.h b/include/uapi/linux/hyperv.h index e347b24ef9fb..991b2b7ada7a 100644 --- a/include/uapi/linux/hyperv.h +++ b/include/uapi/linux/hyperv.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * * Copyright (c) 2011, Microsoft Corporation. diff --git a/include/uapi/linux/hysdn_if.h b/include/uapi/linux/hysdn_if.h index 00236ae3b04e..99f77c517e6d 100644 --- a/include/uapi/linux/hysdn_if.h +++ b/include/uapi/linux/hysdn_if.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* $Id: hysdn_if.h,v 1.1.8.3 2001/09/23 22:25:05 kai Exp $ * * Linux driver for HYSDN cards diff --git a/include/uapi/linux/i2c-dev.h b/include/uapi/linux/i2c-dev.h index 2f05e66de01e..85f8047afcf2 100644 --- a/include/uapi/linux/i2c-dev.h +++ b/include/uapi/linux/i2c-dev.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* i2c-dev.h - i2c-bus driver, char device interface diff --git a/include/uapi/linux/i2c.h b/include/uapi/linux/i2c.h index 009e27bb9abe..fe648032d6b9 100644 --- a/include/uapi/linux/i2c.h +++ b/include/uapi/linux/i2c.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* ------------------------------------------------------------------------- */ /* */ /* i2c.h - definitions for the i2c-bus interface */ diff --git a/include/uapi/linux/i2o-dev.h b/include/uapi/linux/i2o-dev.h index a8093bfec3a6..b1cd407c47d5 100644 --- a/include/uapi/linux/i2o-dev.h +++ b/include/uapi/linux/i2o-dev.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * I2O user space accessible structures/APIs * diff --git a/include/uapi/linux/i8k.h b/include/uapi/linux/i8k.h index 133d02f03c25..268e6268f6c8 100644 --- a/include/uapi/linux/i8k.h +++ b/include/uapi/linux/i8k.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * i8k.h -- Linux driver for accessing the SMM BIOS on Dell laptops * diff --git a/include/uapi/linux/icmp.h b/include/uapi/linux/icmp.h index fddd9d736284..5589eeb791ca 100644 --- a/include/uapi/linux/icmp.h +++ b/include/uapi/linux/icmp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket diff --git a/include/uapi/linux/if.h b/include/uapi/linux/if.h index 259617a551f2..7fea0fd7d6f5 100644 --- a/include/uapi/linux/if.h +++ b/include/uapi/linux/if.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket diff --git a/include/uapi/linux/if_alg.h b/include/uapi/linux/if_alg.h index f2acd2fde1f3..bc2bcdec377b 100644 --- a/include/uapi/linux/if_alg.h +++ b/include/uapi/linux/if_alg.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * if_alg: User-space algorithm interface * diff --git a/include/uapi/linux/if_arcnet.h b/include/uapi/linux/if_arcnet.h index cfb642f8e7bd..683878036d76 100644 --- a/include/uapi/linux/if_arcnet.h +++ b/include/uapi/linux/if_arcnet.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket diff --git a/include/uapi/linux/if_arp.h b/include/uapi/linux/if_arp.h index a2a635620600..4605527ca41b 100644 --- a/include/uapi/linux/if_arp.h +++ b/include/uapi/linux/if_arp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket diff --git a/include/uapi/linux/if_bonding.h b/include/uapi/linux/if_bonding.h index 9635a62f6f89..61a1bf6e865e 100644 --- a/include/uapi/linux/if_bonding.h +++ b/include/uapi/linux/if_bonding.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ /* * Bond several ethernet interfaces into a Cisco, running 'Etherchannel'. * diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index a9e6244ce438..e41eda3c71f1 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Linux ethernet bridge * diff --git a/include/uapi/linux/if_cablemodem.h b/include/uapi/linux/if_cablemodem.h index ee6b3c442baf..1f65130bf2a6 100644 --- a/include/uapi/linux/if_cablemodem.h +++ b/include/uapi/linux/if_cablemodem.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ #ifndef _LINUX_CABLEMODEM_H_ #define _LINUX_CABLEMODEM_H_ /* diff --git a/include/uapi/linux/if_eql.h b/include/uapi/linux/if_eql.h index 06e818c9e7cb..d6865a2d8cdd 100644 --- a/include/uapi/linux/if_eql.h +++ b/include/uapi/linux/if_eql.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Equalizer Load-balancer for serial network interfaces. * diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 9037065e23d0..3ee3bf7c8526 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket diff --git a/include/uapi/linux/if_fc.h b/include/uapi/linux/if_fc.h index 6ed7f1bf35c8..3e3173282cc3 100644 --- a/include/uapi/linux/if_fc.h +++ b/include/uapi/linux/if_fc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket diff --git a/include/uapi/linux/if_fddi.h b/include/uapi/linux/if_fddi.h index 1086cd9f6754..75eed8b62823 100644 --- a/include/uapi/linux/if_fddi.h +++ b/include/uapi/linux/if_fddi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket diff --git a/include/uapi/linux/if_frad.h b/include/uapi/linux/if_frad.h index f25b08d5eb6b..3c6ee85f6262 100644 --- a/include/uapi/linux/if_frad.h +++ b/include/uapi/linux/if_frad.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * DLCI/FRAD Definitions for Frame Relay Access Devices. DLCI devices are * created for each DLCI associated with a FRAD. The FRAD driver diff --git a/include/uapi/linux/if_hippi.h b/include/uapi/linux/if_hippi.h index cdc049f1829a..785a1452a66c 100644 --- a/include/uapi/linux/if_hippi.h +++ b/include/uapi/linux/if_hippi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket diff --git a/include/uapi/linux/if_infiniband.h b/include/uapi/linux/if_infiniband.h index 7d958475d4ac..050b92dcf8cf 100644 --- a/include/uapi/linux/if_infiniband.h +++ b/include/uapi/linux/if_infiniband.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU diff --git a/include/uapi/linux/if_macsec.h b/include/uapi/linux/if_macsec.h index 02fc49cb72d8..719d243471f4 100644 --- a/include/uapi/linux/if_macsec.h +++ b/include/uapi/linux/if_macsec.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * include/uapi/linux/if_macsec.h - MACsec device * diff --git a/include/uapi/linux/if_plip.h b/include/uapi/linux/if_plip.h index 6298c7e88b2b..495a366112f2 100644 --- a/include/uapi/linux/if_plip.h +++ b/include/uapi/linux/if_plip.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * NET3 PLIP tuning facilities for the new Niibe PLIP. * diff --git a/include/uapi/linux/if_pppol2tp.h b/include/uapi/linux/if_pppol2tp.h index 6418c4d10241..060b4d1f3129 100644 --- a/include/uapi/linux/if_pppol2tp.h +++ b/include/uapi/linux/if_pppol2tp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /*************************************************************************** * Linux PPP over L2TP (PPPoL2TP) Socket Implementation (RFC 2661) * diff --git a/include/uapi/linux/if_pppox.h b/include/uapi/linux/if_pppox.h index d37bbb17a007..e7a693c28f16 100644 --- a/include/uapi/linux/if_pppox.h +++ b/include/uapi/linux/if_pppox.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /*************************************************************************** * Linux PPP over X - Generic PPP transport layer sockets * Linux PPP over Ethernet (PPPoE) Socket Implementation (RFC 2516) diff --git a/include/uapi/linux/if_team.h b/include/uapi/linux/if_team.h index 7b8fa339de30..13c61fecb78b 100644 --- a/include/uapi/linux/if_team.h +++ b/include/uapi/linux/if_team.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * include/linux/if_team.h - Network team device driver header * Copyright (c) 2011 Jiri Pirko diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h index 3cb5e1d85ddd..47ab4bc62e31 100644 --- a/include/uapi/linux/if_tun.h +++ b/include/uapi/linux/if_tun.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Universal TUN/TAP device driver. * Copyright (C) 1999-2000 Maxim Krasnyansky diff --git a/include/uapi/linux/if_vlan.h b/include/uapi/linux/if_vlan.h index 7e5e6b397332..7a0e8bd65b6b 100644 --- a/include/uapi/linux/if_vlan.h +++ b/include/uapi/linux/if_vlan.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * VLAN An implementation of 802.1Q VLAN tagging. * diff --git a/include/uapi/linux/if_x25.h b/include/uapi/linux/if_x25.h index 897765f5feb8..5d962448345f 100644 --- a/include/uapi/linux/if_x25.h +++ b/include/uapi/linux/if_x25.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Linux X.25 packet to device interface * diff --git a/include/uapi/linux/igmp.h b/include/uapi/linux/igmp.h index a97f9a7568cf..7e44ac02ca18 100644 --- a/include/uapi/linux/igmp.h +++ b/include/uapi/linux/igmp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Linux NET3: Internet Group Management Protocol [IGMP] * diff --git a/include/uapi/linux/iio/events.h b/include/uapi/linux/iio/events.h index 00bbdaed2f97..6ef413452dce 100644 --- a/include/uapi/linux/iio/events.h +++ b/include/uapi/linux/iio/events.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* The industrial I/O - event passing to userspace * * Copyright (c) 2008-2011 Jonathan Cameron diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h index ffafd6c25a48..4213cdf88e3c 100644 --- a/include/uapi/linux/iio/types.h +++ b/include/uapi/linux/iio/types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* industrial I/O data types needed both in and out of kernel * * Copyright (c) 2008 Jonathan Cameron diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index 4e557f4e9553..48e8a225b985 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h index 46444f8fbee4..2c002ffa9d6f 100644 --- a/include/uapi/linux/in6.h +++ b/include/uapi/linux/in6.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Types and definitions for AF_INET6 * Linux INET6 implementation diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 179891074b3c..f4058bd4c373 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Input event codes * diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h index f561c0eb7d63..8c5a0bf6ee35 100644 --- a/include/uapi/linux/input.h +++ b/include/uapi/linux/input.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (c) 1999-2002 Vojtech Pavlik * diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h index f291569768dd..b24a742beae5 100644 --- a/include/uapi/linux/ip.h +++ b/include/uapi/linux/ip.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket diff --git a/include/uapi/linux/ipmi.h b/include/uapi/linux/ipmi.h index b9095a27a08a..b076f7a47407 100644 --- a/include/uapi/linux/ipmi.h +++ b/include/uapi/linux/ipmi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * ipmi.h * diff --git a/include/uapi/linux/ipmi_msgdefs.h b/include/uapi/linux/ipmi_msgdefs.h index df97e6e31e87..17f349459587 100644 --- a/include/uapi/linux/ipmi_msgdefs.h +++ b/include/uapi/linux/ipmi_msgdefs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * ipmi_smi.h * diff --git a/include/uapi/linux/ipv6_route.h b/include/uapi/linux/ipv6_route.h index d496c02e14bc..a96eb17ad6fc 100644 --- a/include/uapi/linux/ipv6_route.h +++ b/include/uapi/linux/ipv6_route.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Linux INET6 implementation * diff --git a/include/uapi/linux/irda.h b/include/uapi/linux/irda.h index a014c3252311..2105c266aa6e 100644 --- a/include/uapi/linux/irda.h +++ b/include/uapi/linux/irda.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /********************************************************************* * * Filename: irda.h diff --git a/include/uapi/linux/isdn.h b/include/uapi/linux/isdn.h index eb1995fffc39..f371fd52ed75 100644 --- a/include/uapi/linux/isdn.h +++ b/include/uapi/linux/isdn.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* $Id: isdn.h,v 1.125.2.3 2004/02/10 01:07:14 keil Exp $ * * Main header for the Linux ISDN subsystem (linklevel). diff --git a/include/uapi/linux/isdn/capicmd.h b/include/uapi/linux/isdn/capicmd.h index b58635f722da..4941628a4fb9 100644 --- a/include/uapi/linux/isdn/capicmd.h +++ b/include/uapi/linux/isdn/capicmd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* $Id: capicmd.h,v 1.2.6.2 2001/09/23 22:24:33 kai Exp $ * * CAPI 2.0 Interface for Linux diff --git a/include/uapi/linux/isdn_divertif.h b/include/uapi/linux/isdn_divertif.h index 3e3c2d898416..0a17bb1bcb1b 100644 --- a/include/uapi/linux/isdn_divertif.h +++ b/include/uapi/linux/isdn_divertif.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* $Id: isdn_divertif.h,v 1.4.6.1 2001/09/23 22:25:05 kai Exp $ * * Header for the diversion supplementary interface for i4l. diff --git a/include/uapi/linux/isdn_ppp.h b/include/uapi/linux/isdn_ppp.h index e7d7bd2aed3f..0bdc4efaacb2 100644 --- a/include/uapi/linux/isdn_ppp.h +++ b/include/uapi/linux/isdn_ppp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ /* Linux ISDN subsystem, sync PPP, interface to ipppd * * Copyright 1994-1999 by Fritz Elfert (fritz@isdn4linux.de) diff --git a/include/uapi/linux/isdnif.h b/include/uapi/linux/isdnif.h index 246138c01c4d..611a69196738 100644 --- a/include/uapi/linux/isdnif.h +++ b/include/uapi/linux/isdnif.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ /* $Id: isdnif.h,v 1.43.2.2 2004/01/12 23:08:35 keil Exp $ * * Linux ISDN subsystem diff --git a/include/uapi/linux/ivtv.h b/include/uapi/linux/ivtv.h index 42bf725751af..e74f18642b11 100644 --- a/include/uapi/linux/ivtv.h +++ b/include/uapi/linux/ivtv.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* Public ivtv API header Copyright (C) 2003-2004 Kevin Thayer diff --git a/include/uapi/linux/ivtvfb.h b/include/uapi/linux/ivtvfb.h index e8b92f67f10d..9e9b072375de 100644 --- a/include/uapi/linux/ivtvfb.h +++ b/include/uapi/linux/ivtvfb.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* On Screen Display cx23415 Framebuffer driver diff --git a/include/uapi/linux/ixjuser.h b/include/uapi/linux/ixjuser.h index 94ab5e942e53..ba245007cfe7 100644 --- a/include/uapi/linux/ixjuser.h +++ b/include/uapi/linux/ixjuser.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ #ifndef __LINUX_IXJUSER_H #define __LINUX_IXJUSER_H diff --git a/include/uapi/linux/joystick.h b/include/uapi/linux/joystick.h index b856fd11c70e..64aabb84a66d 100644 --- a/include/uapi/linux/joystick.h +++ b/include/uapi/linux/joystick.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (C) 1996-2000 Vojtech Pavlik * diff --git a/include/uapi/linux/kcm.h b/include/uapi/linux/kcm.h index a5a530940b99..01361ea359c4 100644 --- a/include/uapi/linux/kcm.h +++ b/include/uapi/linux/kcm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Kernel Connection Multiplexor * diff --git a/include/uapi/linux/keyctl.h b/include/uapi/linux/keyctl.h index ef16df06642a..7b8c9e19bad1 100644 --- a/include/uapi/linux/keyctl.h +++ b/include/uapi/linux/keyctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* keyctl.h: keyctl command IDs * * Copyright (C) 2004, 2008 Red Hat, Inc. All Rights Reserved. diff --git a/include/uapi/linux/lightnvm.h b/include/uapi/linux/lightnvm.h index c8aec4b9e73b..42d1a434af29 100644 --- a/include/uapi/linux/lightnvm.h +++ b/include/uapi/linux/lightnvm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2015 CNEX Labs. All rights reserved. * diff --git a/include/uapi/linux/llc.h b/include/uapi/linux/llc.h index a6c17f66ee94..cf8806b14d5f 100644 --- a/include/uapi/linux/llc.h +++ b/include/uapi/linux/llc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ /* * IEEE 802.2 User Interface SAPs for Linux, data structures and indicators. * diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h index 23158dbe2424..080a8df134ef 100644 --- a/include/uapi/linux/loop.h +++ b/include/uapi/linux/loop.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ /* * include/linux/loop.h * diff --git a/include/uapi/linux/map_to_7segment.h b/include/uapi/linux/map_to_7segment.h index 12d62a54d470..f9ed18134b83 100644 --- a/include/uapi/linux/map_to_7segment.h +++ b/include/uapi/linux/map_to_7segment.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (c) 2005 Henk Vergonet * diff --git a/include/uapi/linux/max2175.h b/include/uapi/linux/max2175.h index 3ef5d264440f..daedc4eb9b6b 100644 --- a/include/uapi/linux/max2175.h +++ b/include/uapi/linux/max2175.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * max2175.h * diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index c94a510a577e..d435b00d64ad 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * linux/mdio.h: definitions for MDIO (clause 45) transceivers * Copyright 2006-2009 Solarflare Communications Inc. diff --git a/include/uapi/linux/media-bus-format.h b/include/uapi/linux/media-bus-format.h index ef6fb307d2ce..9e3511742fdc 100644 --- a/include/uapi/linux/media-bus-format.h +++ b/include/uapi/linux/media-bus-format.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Media Bus API header * diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index 4865f1e71339..b9b9446095e9 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Multimedia device API * diff --git a/include/uapi/linux/mei.h b/include/uapi/linux/mei.h index 7c3b64f6a215..0f681cbd38d3 100644 --- a/include/uapi/linux/mei.h +++ b/include/uapi/linux/mei.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /****************************************************************************** * Intel Management Engine Interface (Intel MEI) Linux driver * Intel MEI Interface Header diff --git a/include/uapi/linux/meye.h b/include/uapi/linux/meye.h index 8ff50fe9e481..de9e3a954f3d 100644 --- a/include/uapi/linux/meye.h +++ b/include/uapi/linux/meye.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Motion Eye video4linux driver for Sony Vaio PictureBook * diff --git a/include/uapi/linux/mic_common.h b/include/uapi/linux/mic_common.h index e9686372029d..504e523f702c 100644 --- a/include/uapi/linux/mic_common.h +++ b/include/uapi/linux/mic_common.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Intel MIC Platform Software Stack (MPSS) * diff --git a/include/uapi/linux/mic_ioctl.h b/include/uapi/linux/mic_ioctl.h index feb0b4c0814c..687b9cd9d3e2 100644 --- a/include/uapi/linux/mic_ioctl.h +++ b/include/uapi/linux/mic_ioctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Intel MIC Platform Software Stack (MPSS) * diff --git a/include/uapi/linux/mmtimer.h b/include/uapi/linux/mmtimer.h index 884cabf16088..409fae1de383 100644 --- a/include/uapi/linux/mmtimer.h +++ b/include/uapi/linux/mmtimer.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Intel Multimedia Timer device interface * diff --git a/include/uapi/linux/mpls_iptunnel.h b/include/uapi/linux/mpls_iptunnel.h index f5e45095b0bb..521f2e605f13 100644 --- a/include/uapi/linux/mpls_iptunnel.h +++ b/include/uapi/linux/mpls_iptunnel.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * mpls tunnel api * diff --git a/include/uapi/linux/mqueue.h b/include/uapi/linux/mqueue.h index bbd5116ea739..b516b66840ad 100644 --- a/include/uapi/linux/mqueue.h +++ b/include/uapi/linux/mqueue.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1+ WITH Linux-syscall-note */ /* Copyright (C) 2003 Krzysztof Benedyczak & Michal Wronski This program is free software; you can redistribute it and/or diff --git a/include/uapi/linux/n_r3964.h b/include/uapi/linux/n_r3964.h index 81337cbf40b7..6bbd18520f30 100644 --- a/include/uapi/linux/n_r3964.h +++ b/include/uapi/linux/n_r3964.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ /* r3964 linediscipline for linux * * ----------------------------------------------------------- diff --git a/include/uapi/linux/nbd-netlink.h b/include/uapi/linux/nbd-netlink.h index 6f7ca3d63a65..c5d0ef7aa7d5 100644 --- a/include/uapi/linux/nbd-netlink.h +++ b/include/uapi/linux/nbd-netlink.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2017 Facebook. All rights reserved. * diff --git a/include/uapi/linux/nbd.h b/include/uapi/linux/nbd.h index a50527ebf671..85a3fb65e40a 100644 --- a/include/uapi/linux/nbd.h +++ b/include/uapi/linux/nbd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ /* * 1999 Copyright (C) Pavel Machek, pavel@ucw.cz. This code is GPL. * 1999/11/04 Copyright (C) 1999 VMware, Inc. (Regis "HPReg" Duchesne) diff --git a/include/uapi/linux/net.h b/include/uapi/linux/net.h index 9457239ed219..4dabec6bd957 100644 --- a/include/uapi/linux/net.h +++ b/include/uapi/linux/net.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * NET An implementation of the SOCKET network access protocol. * This is the master header file for the Linux NET layer, diff --git a/include/uapi/linux/net_namespace.h b/include/uapi/linux/net_namespace.h index 778cd2c3ebf4..0187c74d8889 100644 --- a/include/uapi/linux/net_namespace.h +++ b/include/uapi/linux/net_namespace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* Copyright (c) 2015 6WIND S.A. * Author: Nicolas Dichtel * diff --git a/include/uapi/linux/netdevice.h b/include/uapi/linux/netdevice.h index 55818543342d..f3770c5b0fac 100644 --- a/include/uapi/linux/netdevice.h +++ b/include/uapi/linux/netdevice.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket diff --git a/include/uapi/linux/netfilter/ipset/ip_set.h b/include/uapi/linux/netfilter/ipset/ip_set.h index ebb5154976de..60236f694143 100644 --- a/include/uapi/linux/netfilter/ipset/ip_set.h +++ b/include/uapi/linux/netfilter/ipset/ip_set.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* Copyright (C) 2000-2002 Joakim Axelsson * Patrick Schaaf * Martin Josefsson diff --git a/include/uapi/linux/netfilter/xt_AUDIT.h b/include/uapi/linux/netfilter/xt_AUDIT.h index 38751d2ea52b..1b314e2f84ac 100644 --- a/include/uapi/linux/netfilter/xt_AUDIT.h +++ b/include/uapi/linux/netfilter/xt_AUDIT.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Header file for iptables xt_AUDIT target * diff --git a/include/uapi/linux/netfilter/xt_CHECKSUM.h b/include/uapi/linux/netfilter/xt_CHECKSUM.h index 9a2e4661654e..c578088e61b9 100644 --- a/include/uapi/linux/netfilter/xt_CHECKSUM.h +++ b/include/uapi/linux/netfilter/xt_CHECKSUM.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* Header file for iptables ipt_CHECKSUM target * * (C) 2002 by Harald Welte diff --git a/include/uapi/linux/netfilter/xt_DSCP.h b/include/uapi/linux/netfilter/xt_DSCP.h index 648e0b3bed29..223d635e8b6f 100644 --- a/include/uapi/linux/netfilter/xt_DSCP.h +++ b/include/uapi/linux/netfilter/xt_DSCP.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* x_tables module for setting the IPv4/IPv6 DSCP field * * (C) 2002 Harald Welte diff --git a/include/uapi/linux/netfilter/xt_IDLETIMER.h b/include/uapi/linux/netfilter/xt_IDLETIMER.h index 208ae9387331..3c586a19baea 100644 --- a/include/uapi/linux/netfilter/xt_IDLETIMER.h +++ b/include/uapi/linux/netfilter/xt_IDLETIMER.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * linux/include/linux/netfilter/xt_IDLETIMER.h * diff --git a/include/uapi/linux/netfilter/xt_NFQUEUE.h b/include/uapi/linux/netfilter/xt_NFQUEUE.h index 8bb5fe657d34..bb767fd73ed1 100644 --- a/include/uapi/linux/netfilter/xt_NFQUEUE.h +++ b/include/uapi/linux/netfilter/xt_NFQUEUE.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* iptables module for using NFQUEUE mechanism * * (C) 2005 Harald Welte diff --git a/include/uapi/linux/netfilter/xt_connmark.h b/include/uapi/linux/netfilter/xt_connmark.h index efc17a8305fb..408a9654f05c 100644 --- a/include/uapi/linux/netfilter/xt_connmark.h +++ b/include/uapi/linux/netfilter/xt_connmark.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ #ifndef _XT_CONNMARK_H #define _XT_CONNMARK_H diff --git a/include/uapi/linux/netfilter/xt_conntrack.h b/include/uapi/linux/netfilter/xt_conntrack.h index e5bd3083a843..cdd14a83d29d 100644 --- a/include/uapi/linux/netfilter/xt_conntrack.h +++ b/include/uapi/linux/netfilter/xt_conntrack.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ /* Header file for kernel module to match connection tracking information. * GPL (C) 2001 Marc Boucher (marc@mbsi.ca). */ diff --git a/include/uapi/linux/netfilter/xt_dscp.h b/include/uapi/linux/netfilter/xt_dscp.h index 15f8932ad5ce..7594e4df8587 100644 --- a/include/uapi/linux/netfilter/xt_dscp.h +++ b/include/uapi/linux/netfilter/xt_dscp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* x_tables module for matching the IPv4/IPv6 DSCP field * * (C) 2002 Harald Welte diff --git a/include/uapi/linux/netfilter/xt_ecn.h b/include/uapi/linux/netfilter/xt_ecn.h index 7158fca364f2..2c301c1cbff2 100644 --- a/include/uapi/linux/netfilter/xt_ecn.h +++ b/include/uapi/linux/netfilter/xt_ecn.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* iptables module for matching the ECN header in IPv4 and TCP header * * (C) 2002 Harald Welte diff --git a/include/uapi/linux/netfilter/xt_osf.h b/include/uapi/linux/netfilter/xt_osf.h index e6159958b2fb..dad197e2ab99 100644 --- a/include/uapi/linux/netfilter/xt_osf.h +++ b/include/uapi/linux/netfilter/xt_osf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (c) 2003+ Evgeniy Polyakov * diff --git a/include/uapi/linux/netfilter_arp.h b/include/uapi/linux/netfilter_arp.h index 92bc6ddcbf73..81b6a4cbcb72 100644 --- a/include/uapi/linux/netfilter_arp.h +++ b/include/uapi/linux/netfilter_arp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ #ifndef __LINUX_ARP_NETFILTER_H #define __LINUX_ARP_NETFILTER_H diff --git a/include/uapi/linux/netfilter_decnet.h b/include/uapi/linux/netfilter_decnet.h index 0b09732aacd5..9089c38f6abe 100644 --- a/include/uapi/linux/netfilter_decnet.h +++ b/include/uapi/linux/netfilter_decnet.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_DECNET_NETFILTER_H #define __LINUX_DECNET_NETFILTER_H diff --git a/include/uapi/linux/netfilter_ipv4.h b/include/uapi/linux/netfilter_ipv4.h index 91ddd1f6fd4b..e6b1a84f5dd3 100644 --- a/include/uapi/linux/netfilter_ipv4.h +++ b/include/uapi/linux/netfilter_ipv4.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* IPv4-specific defines for netfilter. * (C)1998 Rusty Russell -- This code is GPL. */ diff --git a/include/uapi/linux/netfilter_ipv4/ipt_ECN.h b/include/uapi/linux/netfilter_ipv4/ipt_ECN.h index bb88d5315a4d..e3630fd045b8 100644 --- a/include/uapi/linux/netfilter_ipv4/ipt_ECN.h +++ b/include/uapi/linux/netfilter_ipv4/ipt_ECN.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* Header file for iptables ipt_ECN target * * (C) 2002 by Harald Welte diff --git a/include/uapi/linux/netfilter_ipv6.h b/include/uapi/linux/netfilter_ipv6.h index 12497c6c7949..2f9724611cc2 100644 --- a/include/uapi/linux/netfilter_ipv6.h +++ b/include/uapi/linux/netfilter_ipv6.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* IPv6-specific defines for netfilter. * (C)1998 Rusty Russell -- This code is GPL. * (C)1999 David Jeffery diff --git a/include/uapi/linux/nfsd/cld.h b/include/uapi/linux/nfsd/cld.h index ec260274be0c..f8f5cccad749 100644 --- a/include/uapi/linux/nfsd/cld.h +++ b/include/uapi/linux/nfsd/cld.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Upcall description for nfsdcld communication * diff --git a/include/uapi/linux/nilfs2_api.h b/include/uapi/linux/nilfs2_api.h index ef4c1de89b11..8b9b89104f3d 100644 --- a/include/uapi/linux/nilfs2_api.h +++ b/include/uapi/linux/nilfs2_api.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1+ WITH Linux-syscall-note */ /* * nilfs2_api.h - NILFS2 user space API * diff --git a/include/uapi/linux/nilfs2_ondisk.h b/include/uapi/linux/nilfs2_ondisk.h index 2a8a3addb675..a7e66ab11d1d 100644 --- a/include/uapi/linux/nilfs2_ondisk.h +++ b/include/uapi/linux/nilfs2_ondisk.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1+ WITH Linux-syscall-note */ /* * nilfs2_ondisk.h - NILFS2 on-disk structures * diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h index 50ff21f748b6..6e74b1eaf541 100644 --- a/include/uapi/linux/nvme_ioctl.h +++ b/include/uapi/linux/nvme_ioctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Definitions for the NVM Express ioctl interface * Copyright (c) 2011-2014, Intel Corporation. diff --git a/include/uapi/linux/omap3isp.h b/include/uapi/linux/omap3isp.h index c090cf9249bb..1a920145db04 100644 --- a/include/uapi/linux/omap3isp.h +++ b/include/uapi/linux/omap3isp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * omap3isp.h * diff --git a/include/uapi/linux/omapfb.h b/include/uapi/linux/omapfb.h index 7c97bc00ac6d..44f43af4c699 100644 --- a/include/uapi/linux/omapfb.h +++ b/include/uapi/linux/omapfb.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * File: include/linux/omapfb.h * diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 156ee4cab82e..36d0b161e066 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (c) 2007-2017 Nicira, Inc. diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 140ae638cfd6..362493a2f950 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Performance events: * diff --git a/include/uapi/linux/pg.h b/include/uapi/linux/pg.h index db994bb0c794..364c350e85cd 100644 --- a/include/uapi/linux/pg.h +++ b/include/uapi/linux/pg.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ /* pg.h (c) 1998 Grant R. Guenther Under the terms of the GNU General Public License diff --git a/include/uapi/linux/phantom.h b/include/uapi/linux/phantom.h index 94dd6645c60a..dbef708ab3b4 100644 --- a/include/uapi/linux/phantom.h +++ b/include/uapi/linux/phantom.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (C) 2005-2007 Jiri Slaby * diff --git a/include/uapi/linux/phonet.h b/include/uapi/linux/phonet.h index a3e1d65b3ed9..a2f6b37a5937 100644 --- a/include/uapi/linux/phonet.h +++ b/include/uapi/linux/phonet.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /** * file phonet.h * diff --git a/include/uapi/linux/pktcdvd.h b/include/uapi/linux/pktcdvd.h index 2640b9d4e243..9cbb55d21c94 100644 --- a/include/uapi/linux/pktcdvd.h +++ b/include/uapi/linux/pktcdvd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2000 Jens Axboe * Copyright (C) 2001-2004 Peter Osterlund diff --git a/include/uapi/linux/posix_acl.h b/include/uapi/linux/posix_acl.h index 1037cb19aa17..217e4e26ab60 100644 --- a/include/uapi/linux/posix_acl.h +++ b/include/uapi/linux/posix_acl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1+ WITH Linux-syscall-note */ /* * Copyright (C) 2002 Andreas Gruenbacher * Copyright (C) 2016 Red Hat, Inc. diff --git a/include/uapi/linux/posix_acl_xattr.h b/include/uapi/linux/posix_acl_xattr.h index 8b579844109b..506380f0b91b 100644 --- a/include/uapi/linux/posix_acl_xattr.h +++ b/include/uapi/linux/posix_acl_xattr.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1+ WITH Linux-syscall-note */ /* * Copyright (C) 2002 Andreas Gruenbacher * Copyright (C) 2016 Red Hat, Inc. diff --git a/include/uapi/linux/ppdev.h b/include/uapi/linux/ppdev.h index dc18c5d23ebe..8fe3c64d149e 100644 --- a/include/uapi/linux/ppdev.h +++ b/include/uapi/linux/ppdev.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * linux/include/linux/ppdev.h * diff --git a/include/uapi/linux/ppp-comp.h b/include/uapi/linux/ppp-comp.h index 0a15bbb04e19..0fb7623e9548 100644 --- a/include/uapi/linux/ppp-comp.h +++ b/include/uapi/linux/ppp-comp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * ppp-comp.h - Definitions for doing PPP packet compression. * diff --git a/include/uapi/linux/ppp-ioctl.h b/include/uapi/linux/ppp-ioctl.h index 63a23a3b8bb7..b19a9c249b15 100644 --- a/include/uapi/linux/ppp-ioctl.h +++ b/include/uapi/linux/ppp-ioctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * ppp-ioctl.h - PPP ioctl definitions. * diff --git a/include/uapi/linux/ppp_defs.h b/include/uapi/linux/ppp_defs.h index 283fc05dbbda..fff51b91b409 100644 --- a/include/uapi/linux/ppp_defs.h +++ b/include/uapi/linux/ppp_defs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * ppp_defs.h - PPP definitions. * diff --git a/include/uapi/linux/pps.h b/include/uapi/linux/pps.h index c29d6b791c08..009ebcd8ced5 100644 --- a/include/uapi/linux/pps.h +++ b/include/uapi/linux/pps.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * PPS API header * diff --git a/include/uapi/linux/ptp_clock.h b/include/uapi/linux/ptp_clock.h index ac6dded80ffa..3039bf6a742e 100644 --- a/include/uapi/linux/ptp_clock.h +++ b/include/uapi/linux/ptp_clock.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * PTP 1588 clock support - user space interface * diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h index b9197976b660..b0d15c73f6d7 100644 --- a/include/uapi/linux/raid/md_p.h +++ b/include/uapi/linux/raid/md_p.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* md_p.h : physical layout of Linux RAID devices Copyright (C) 1996-98 Ingo Molnar, Gadi Oxman diff --git a/include/uapi/linux/raid/md_u.h b/include/uapi/linux/raid/md_u.h index 36cd8210a5d1..105307244961 100644 --- a/include/uapi/linux/raid/md_u.h +++ b/include/uapi/linux/raid/md_u.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* md_u.h : user <=> kernel API between Linux raidtools and RAID drivers Copyright (C) 1998 Ingo Molnar diff --git a/include/uapi/linux/rds.h b/include/uapi/linux/rds.h index 198892b95f09..e71d4491f225 100644 --- a/include/uapi/linux/rds.h +++ b/include/uapi/linux/rds.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ /* * Copyright (c) 2008 Oracle. All rights reserved. * diff --git a/include/uapi/linux/rio_cm_cdev.h b/include/uapi/linux/rio_cm_cdev.h index 6edb900d318d..d05dc3226f8e 100644 --- a/include/uapi/linux/rio_cm_cdev.h +++ b/include/uapi/linux/rio_cm_cdev.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * Copyright (c) 2015, Integrated Device Technology Inc. * Copyright (c) 2015, Prodrive Technologies diff --git a/include/uapi/linux/rio_mport_cdev.h b/include/uapi/linux/rio_mport_cdev.h index 5796bf1d06ad..9bc9f98e353a 100644 --- a/include/uapi/linux/rio_mport_cdev.h +++ b/include/uapi/linux/rio_mport_cdev.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * Copyright (c) 2015-2016, Integrated Device Technology Inc. * Copyright (c) 2015, Prodrive Technologies diff --git a/include/uapi/linux/route.h b/include/uapi/linux/route.h index 6600708311c8..a0de9a7331a2 100644 --- a/include/uapi/linux/route.h +++ b/include/uapi/linux/route.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket diff --git a/include/uapi/linux/rpmsg.h b/include/uapi/linux/rpmsg.h index dedc226e0d3f..225eb38705dc 100644 --- a/include/uapi/linux/rpmsg.h +++ b/include/uapi/linux/rpmsg.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (c) 2016, Linaro Ltd. * diff --git a/include/uapi/linux/scif_ioctl.h b/include/uapi/linux/scif_ioctl.h index d9048918be52..862a4cc908f7 100644 --- a/include/uapi/linux/scif_ioctl.h +++ b/include/uapi/linux/scif_ioctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * Intel MIC Platform Software Stack (MPSS) * diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 6217ff8500a1..32df53012cbd 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* SCTP kernel implementation * (C) Copyright IBM Corp. 2001, 2004 * Copyright (c) 1999-2000 Cisco, Inc. diff --git a/include/uapi/linux/sdla.h b/include/uapi/linux/sdla.h index 95eaff9c9e49..1e3735be6511 100644 --- a/include/uapi/linux/sdla.h +++ b/include/uapi/linux/sdla.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket diff --git a/include/uapi/linux/sed-opal.h b/include/uapi/linux/sed-opal.h index c72e0735532d..627624d35030 100644 --- a/include/uapi/linux/sed-opal.h +++ b/include/uapi/linux/sed-opal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright © 2016 Intel Corporation * diff --git a/include/uapi/linux/seg6.h b/include/uapi/linux/seg6.h index 7278511d339e..2f6fb0dd613c 100644 --- a/include/uapi/linux/seg6.h +++ b/include/uapi/linux/seg6.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * SR-IPv6 implementation * diff --git a/include/uapi/linux/seg6_iptunnel.h b/include/uapi/linux/seg6_iptunnel.h index b23df9f58354..09fb608a35ec 100644 --- a/include/uapi/linux/seg6_iptunnel.h +++ b/include/uapi/linux/seg6_iptunnel.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * SR-IPv6 implementation * diff --git a/include/uapi/linux/selinux_netlink.h b/include/uapi/linux/selinux_netlink.h index d239797785cf..2fc0542171cd 100644 --- a/include/uapi/linux/selinux_netlink.h +++ b/include/uapi/linux/selinux_netlink.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Netlink event notifications for SELinux. * diff --git a/include/uapi/linux/serial.h b/include/uapi/linux/serial.h index d2667ecd54ac..3fdd0dee8b41 100644 --- a/include/uapi/linux/serial.h +++ b/include/uapi/linux/serial.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ /* * include/linux/serial.h * diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index 50d71c436323..1c8413f93e3d 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * linux/drivers/char/serial_core.h * diff --git a/include/uapi/linux/serial_reg.h b/include/uapi/linux/serial_reg.h index 5db76880b4ad..619fe6111dc9 100644 --- a/include/uapi/linux/serial_reg.h +++ b/include/uapi/linux/serial_reg.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ /* * include/linux/serial_reg.h * diff --git a/include/uapi/linux/serio.h b/include/uapi/linux/serio.h index ac217c6f0151..a0cac1d8670d 100644 --- a/include/uapi/linux/serio.h +++ b/include/uapi/linux/serio.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 1999-2002 Vojtech Pavlik * diff --git a/include/uapi/linux/smiapp.h b/include/uapi/linux/smiapp.h index 53938f4412ee..50438f8d9647 100644 --- a/include/uapi/linux/smiapp.h +++ b/include/uapi/linux/smiapp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * include/uapi/linux/smiapp.h * diff --git a/include/uapi/linux/sockios.h b/include/uapi/linux/sockios.h index 79d029d25310..d393e9ed3964 100644 --- a/include/uapi/linux/sockios.h +++ b/include/uapi/linux/sockios.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket diff --git a/include/uapi/linux/sonypi.h b/include/uapi/linux/sonypi.h index 85078a283573..88f122451776 100644 --- a/include/uapi/linux/sonypi.h +++ b/include/uapi/linux/sonypi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Sony Programmable I/O Control Device driver for VAIO * diff --git a/include/uapi/linux/spi/spidev.h b/include/uapi/linux/spi/spidev.h index dd5f21e75805..ff0e381e7a77 100644 --- a/include/uapi/linux/spi/spidev.h +++ b/include/uapi/linux/spi/spidev.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * include/linux/spi/spidev.h * diff --git a/include/uapi/linux/stm.h b/include/uapi/linux/stm.h index 626a8d3f63b5..dbffdc23d804 100644 --- a/include/uapi/linux/stm.h +++ b/include/uapi/linux/stm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * System Trace Module (STM) userspace interfaces * Copyright (c) 2014, Intel Corporation. diff --git a/include/uapi/linux/switchtec_ioctl.h b/include/uapi/linux/switchtec_ioctl.h index 5e392968bad2..75df44373034 100644 --- a/include/uapi/linux/switchtec_ioctl.h +++ b/include/uapi/linux/switchtec_ioctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Microsemi Switchtec PCIe Driver * Copyright (c) 2017, Microsemi Corporation diff --git a/include/uapi/linux/sync_file.h b/include/uapi/linux/sync_file.h index 5b287d6970b3..ee2dcfb3d660 100644 --- a/include/uapi/linux/sync_file.h +++ b/include/uapi/linux/sync_file.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ /* * Copyright (C) 2012 Google, Inc. * diff --git a/include/uapi/linux/synclink.h b/include/uapi/linux/synclink.h index 7dcb065a5f76..62f32d4e1021 100644 --- a/include/uapi/linux/synclink.h +++ b/include/uapi/linux/synclink.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ /* * SyncLink Multiprotocol Serial Adapter Driver * diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index 2466e550a41d..b7aa7bb2349f 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1 WITH Linux-syscall-note */ /* taskstats.h - exporting per-task statistics * * Copyright (C) Shailabh Nagar, IBM Corp. 2006 diff --git a/include/uapi/linux/tc_act/tc_bpf.h b/include/uapi/linux/tc_act/tc_bpf.h index 8dc2ac05eecf..6e89a5df49a4 100644 --- a/include/uapi/linux/tc_act/tc_bpf.h +++ b/include/uapi/linux/tc_act/tc_bpf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (c) 2015 Jiri Pirko * diff --git a/include/uapi/linux/tc_act/tc_skbedit.h b/include/uapi/linux/tc_act/tc_skbedit.h index 2884425738ce..fbcfe27a4e6c 100644 --- a/include/uapi/linux/tc_act/tc_skbedit.h +++ b/include/uapi/linux/tc_act/tc_skbedit.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (c) 2008, Intel Corporation. * diff --git a/include/uapi/linux/tc_act/tc_skbmod.h b/include/uapi/linux/tc_act/tc_skbmod.h index 10fc07da6c69..38c072f66f2f 100644 --- a/include/uapi/linux/tc_act/tc_skbmod.h +++ b/include/uapi/linux/tc_act/tc_skbmod.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (c) 2016, Jamal Hadi Salim * diff --git a/include/uapi/linux/tc_act/tc_tunnel_key.h b/include/uapi/linux/tc_act/tc_tunnel_key.h index afcd4be953e2..72bbefe5d1d1 100644 --- a/include/uapi/linux/tc_act/tc_tunnel_key.h +++ b/include/uapi/linux/tc_act/tc_tunnel_key.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (c) 2016, Amir Vadai * Copyright (c) 2016, Mellanox Technologies. All rights reserved. diff --git a/include/uapi/linux/tc_act/tc_vlan.h b/include/uapi/linux/tc_act/tc_vlan.h index bddb272b843f..0d7b5fd6605b 100644 --- a/include/uapi/linux/tc_act/tc_vlan.h +++ b/include/uapi/linux/tc_act/tc_vlan.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (c) 2014 Jiri Pirko * diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 15c25eccab2b..6a64beeecfad 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket diff --git a/include/uapi/linux/telephony.h b/include/uapi/linux/telephony.h index f63afe330add..d2c9f7105f4b 100644 --- a/include/uapi/linux/telephony.h +++ b/include/uapi/linux/telephony.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /****************************************************************************** * * telephony.h diff --git a/include/uapi/linux/tipc.h b/include/uapi/linux/tipc.h index 5351b08c897a..77123614e973 100644 --- a/include/uapi/linux/tipc.h +++ b/include/uapi/linux/tipc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * include/uapi/linux/tipc.h: Header for TIPC socket interface * diff --git a/include/uapi/linux/tipc_config.h b/include/uapi/linux/tipc_config.h index 087b0ef82c07..3f29e3c8ed06 100644 --- a/include/uapi/linux/tipc_config.h +++ b/include/uapi/linux/tipc_config.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * include/uapi/linux/tipc_config.h: Header for TIPC configuration interface * diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h index f9edd20fe9ba..469aa67a5ecb 100644 --- a/include/uapi/linux/tipc_netlink.h +++ b/include/uapi/linux/tipc_netlink.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * Copyright (c) 2014, Ericsson AB * All rights reserved. diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h index cc1d21db35d8..d5e0682ab837 100644 --- a/include/uapi/linux/tls.h +++ b/include/uapi/linux/tls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ /* * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved. * diff --git a/include/uapi/linux/toshiba.h b/include/uapi/linux/toshiba.h index c58bf4b5bb26..7f1941935f98 100644 --- a/include/uapi/linux/toshiba.h +++ b/include/uapi/linux/toshiba.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* toshiba.h -- Linux driver for accessing the SMM on Toshiba laptops * * Copyright (c) 1996-2000 Jonathan A. Buzzard (jonathan@buzzard.org.uk) diff --git a/include/uapi/linux/udf_fs_i.h b/include/uapi/linux/udf_fs_i.h index 3536965913b0..c50863080399 100644 --- a/include/uapi/linux/udf_fs_i.h +++ b/include/uapi/linux/udf_fs_i.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * udf_fs_i.h * diff --git a/include/uapi/linux/udp.h b/include/uapi/linux/udp.h index 2c8180f9156f..efb7b5991c2f 100644 --- a/include/uapi/linux/udp.h +++ b/include/uapi/linux/udp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket diff --git a/include/uapi/linux/uhid.h b/include/uapi/linux/uhid.h index aaa86d6bd1dd..cef7534d2d19 100644 --- a/include/uapi/linux/uhid.h +++ b/include/uapi/linux/uhid.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ #ifndef __UHID_H_ #define __UHID_H_ diff --git a/include/uapi/linux/uinput.h b/include/uapi/linux/uinput.h index dc652e224b67..c9e677e3af1d 100644 --- a/include/uapi/linux/uinput.h +++ b/include/uapi/linux/uinput.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * User level driver support for input subsystem * diff --git a/include/uapi/linux/uio.h b/include/uapi/linux/uio.h index 2731d56a5484..059b1a9147f4 100644 --- a/include/uapi/linux/uio.h +++ b/include/uapi/linux/uio.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Berkeley style UIO structures - Alan Cox 1994. * diff --git a/include/uapi/linux/uleds.h b/include/uapi/linux/uleds.h index 95186578c46e..4d32a39965f8 100644 --- a/include/uapi/linux/uleds.h +++ b/include/uapi/linux/uleds.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Userspace driver support for the LED subsystem * diff --git a/include/uapi/linux/ultrasound.h b/include/uapi/linux/ultrasound.h index 71339dc531c5..73305bd1dc5a 100644 --- a/include/uapi/linux/ultrasound.h +++ b/include/uapi/linux/ultrasound.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _ULTRASOUND_H_ #define _ULTRASOUND_H_ /* diff --git a/include/uapi/linux/usb/audio.h b/include/uapi/linux/usb/audio.h index a4680a5bf5dd..17a022c5b414 100644 --- a/include/uapi/linux/usb/audio.h +++ b/include/uapi/linux/usb/audio.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * -- USB Audio definitions. * diff --git a/include/uapi/linux/usb/cdc-wdm.h b/include/uapi/linux/usb/cdc-wdm.h index 0dc132e75030..a927c7f6f68a 100644 --- a/include/uapi/linux/usb/cdc-wdm.h +++ b/include/uapi/linux/usb/cdc-wdm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * USB CDC Device Management userspace API definitions * diff --git a/include/uapi/linux/usb/g_printer.h b/include/uapi/linux/usb/g_printer.h index 6178fde50f74..7fc20e4b82f5 100644 --- a/include/uapi/linux/usb/g_printer.h +++ b/include/uapi/linux/usb/g_printer.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * g_printer.h -- Header file for USB Printer gadget driver * diff --git a/include/uapi/linux/usb/midi.h b/include/uapi/linux/usb/midi.h index c8c52e3c91de..de6941ef70ad 100644 --- a/include/uapi/linux/usb/midi.h +++ b/include/uapi/linux/usb/midi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * -- USB MIDI definitions. * diff --git a/include/uapi/linux/usbdevice_fs.h b/include/uapi/linux/usbdevice_fs.h index 0bbfd4abd2e3..70ed5338d447 100644 --- a/include/uapi/linux/usbdevice_fs.h +++ b/include/uapi/linux/usbdevice_fs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /*****************************************************************************/ /* diff --git a/include/uapi/linux/userio.h b/include/uapi/linux/userio.h index 37d147f0a13a..74c9951d2cd0 100644 --- a/include/uapi/linux/userio.h +++ b/include/uapi/linux/userio.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.0+ WITH Linux-syscall-note */ /* * userio: virtual serio device support * Copyright (C) 2015 Red Hat diff --git a/include/uapi/linux/uuid.h b/include/uapi/linux/uuid.h index 8ef82f433877..5c04130bb524 100644 --- a/include/uapi/linux/uuid.h +++ b/include/uapi/linux/uuid.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * UUID/GUID definition * diff --git a/include/uapi/linux/v4l2-common.h b/include/uapi/linux/v4l2-common.h index 5b3f685a2d50..4f7b892377cd 100644 --- a/include/uapi/linux/v4l2-common.h +++ b/include/uapi/linux/v4l2-common.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * include/linux/v4l2-common.h * diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 31bfc68f86d6..a692623e0236 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * Video for Linux Two controls header file * diff --git a/include/uapi/linux/v4l2-dv-timings.h b/include/uapi/linux/v4l2-dv-timings.h index da2955154381..b52b67c62562 100644 --- a/include/uapi/linux/v4l2-dv-timings.h +++ b/include/uapi/linux/v4l2-dv-timings.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * V4L2 DV timings header. * diff --git a/include/uapi/linux/v4l2-mediabus.h b/include/uapi/linux/v4l2-mediabus.h index 9cac6325cc7e..6e20de63ec59 100644 --- a/include/uapi/linux/v4l2-mediabus.h +++ b/include/uapi/linux/v4l2-mediabus.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Media Bus API header * diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h index dbce2b554e02..c95a53e6743c 100644 --- a/include/uapi/linux/v4l2-subdev.h +++ b/include/uapi/linux/v4l2-subdev.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * V4L2 subdev userspace API * diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index ae461050661a..e3301dbd27d4 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * VFIO API definition * diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 185d6a0acc06..1c095b5a99c5 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * Video for Linux Two header file * diff --git a/include/uapi/linux/vm_sockets.h b/include/uapi/linux/vm_sockets.h index b4ed5d895699..68d57c5e99bc 100644 --- a/include/uapi/linux/vm_sockets.h +++ b/include/uapi/linux/vm_sockets.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * VMware vSockets Driver * diff --git a/include/uapi/linux/vtpm_proxy.h b/include/uapi/linux/vtpm_proxy.h index 58ac73cd38fe..31a30f33ac46 100644 --- a/include/uapi/linux/vtpm_proxy.h +++ b/include/uapi/linux/vtpm_proxy.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Definitions for the VTPM proxy driver * Copyright (c) 2015, 2016, IBM Corporation diff --git a/include/uapi/linux/xilinx-v4l2-controls.h b/include/uapi/linux/xilinx-v4l2-controls.h index fb495b91e800..b6441fe705c5 100644 --- a/include/uapi/linux/xilinx-v4l2-controls.h +++ b/include/uapi/linux/xilinx-v4l2-controls.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Xilinx Controls Header * diff --git a/include/uapi/linux/zorro.h b/include/uapi/linux/zorro.h index 59d021b242ed..9798d1864fd9 100644 --- a/include/uapi/linux/zorro.h +++ b/include/uapi/linux/zorro.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * linux/zorro.h -- Amiga AutoConfig (Zorro) Bus Definitions * diff --git a/include/uapi/misc/cxl.h b/include/uapi/misc/cxl.h index 180d526a55c3..49e8fd08855a 100644 --- a/include/uapi/misc/cxl.h +++ b/include/uapi/misc/cxl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright 2014 IBM Corp. * diff --git a/include/uapi/mtd/mtd-abi.h b/include/uapi/mtd/mtd-abi.h index 0ec1da2ef652..aff5b5e59845 100644 --- a/include/uapi/mtd/mtd-abi.h +++ b/include/uapi/mtd/mtd-abi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright © 1999-2010 David Woodhouse et al. * diff --git a/include/uapi/mtd/mtd-user.h b/include/uapi/mtd/mtd-user.h index e71d5558cc23..7eca1b3f6b43 100644 --- a/include/uapi/mtd/mtd-user.h +++ b/include/uapi/mtd/mtd-user.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright © 1999-2010 David Woodhouse * diff --git a/include/uapi/mtd/nftl-user.h b/include/uapi/mtd/nftl-user.h index bdeabd86ad99..b23bdc91c9f1 100644 --- a/include/uapi/mtd/nftl-user.h +++ b/include/uapi/mtd/nftl-user.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright © 1999-2010 David Woodhouse * diff --git a/include/uapi/mtd/ubi-user.h b/include/uapi/mtd/ubi-user.h index 1927b0d78a99..5b04a494d139 100644 --- a/include/uapi/mtd/ubi-user.h +++ b/include/uapi/mtd/ubi-user.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright © International Business Machines Corp., 2006 * diff --git a/include/uapi/rdma/bnxt_re-abi.h b/include/uapi/rdma/bnxt_re-abi.h index 74018bd18d72..398a514ee446 100644 --- a/include/uapi/rdma/bnxt_re-abi.h +++ b/include/uapi/rdma/bnxt_re-abi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ /* * Broadcom NetXtreme-E RoCE driver. * diff --git a/include/uapi/rdma/cxgb3-abi.h b/include/uapi/rdma/cxgb3-abi.h index d24eee12128f..d5745e43ae85 100644 --- a/include/uapi/rdma/cxgb3-abi.h +++ b/include/uapi/rdma/cxgb3-abi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ /* * Copyright (c) 2006 Chelsio, Inc. All rights reserved. * diff --git a/include/uapi/rdma/cxgb4-abi.h b/include/uapi/rdma/cxgb4-abi.h index 472b15990894..05f71f1bc119 100644 --- a/include/uapi/rdma/cxgb4-abi.h +++ b/include/uapi/rdma/cxgb4-abi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ /* * Copyright (c) 2009-2010 Chelsio, Inc. All rights reserved. * diff --git a/include/uapi/rdma/hfi/hfi1_ioctl.h b/include/uapi/rdma/hfi/hfi1_ioctl.h index 4791cc8cb09b..9de78c5ee913 100644 --- a/include/uapi/rdma/hfi/hfi1_ioctl.h +++ b/include/uapi/rdma/hfi/hfi1_ioctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * * This file is provided under a dual BSD/GPLv2 license. When using or diff --git a/include/uapi/rdma/hfi/hfi1_user.h b/include/uapi/rdma/hfi/hfi1_user.h index 3f4ee93ae5eb..791bea2f8297 100644 --- a/include/uapi/rdma/hfi/hfi1_user.h +++ b/include/uapi/rdma/hfi/hfi1_user.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * * This file is provided under a dual BSD/GPLv2 license. When using or diff --git a/include/uapi/rdma/hns-abi.h b/include/uapi/rdma/hns-abi.h index 5d7401963e35..a9c03b0eed57 100644 --- a/include/uapi/rdma/hns-abi.h +++ b/include/uapi/rdma/hns-abi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ /* * Copyright (c) 2016 Hisilicon Limited. * diff --git a/include/uapi/rdma/ib_user_cm.h b/include/uapi/rdma/ib_user_cm.h index f79014aa28f9..f4041bdc4d08 100644 --- a/include/uapi/rdma/ib_user_cm.h +++ b/include/uapi/rdma/ib_user_cm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ /* * Copyright (c) 2005 Topspin Communications. All rights reserved. * Copyright (c) 2005 Intel Corporation. All rights reserved. diff --git a/include/uapi/rdma/ib_user_mad.h b/include/uapi/rdma/ib_user_mad.h index 5c7abd859e0f..330a3c5f1aa8 100644 --- a/include/uapi/rdma/ib_user_mad.h +++ b/include/uapi/rdma/ib_user_mad.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ /* * Copyright (c) 2004 Topspin Communications. All rights reserved. * Copyright (c) 2005 Voltaire, Inc. All rights reserved. diff --git a/include/uapi/rdma/ib_user_sa.h b/include/uapi/rdma/ib_user_sa.h index cfc7c9ba781e..0d2607f0cd20 100644 --- a/include/uapi/rdma/ib_user_sa.h +++ b/include/uapi/rdma/ib_user_sa.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ /* * Copyright (c) 2005 Intel Corporation. All rights reserved. * diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h index d4e0b53bfc75..e0e83a105953 100644 --- a/include/uapi/rdma/ib_user_verbs.h +++ b/include/uapi/rdma/ib_user_verbs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ /* * Copyright (c) 2005 Topspin Communications. All rights reserved. * Copyright (c) 2005, 2006 Cisco Systems. All rights reserved. diff --git a/include/uapi/rdma/mlx4-abi.h b/include/uapi/rdma/mlx4-abi.h index c55f60e05f86..224b52b6279c 100644 --- a/include/uapi/rdma/mlx4-abi.h +++ b/include/uapi/rdma/mlx4-abi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ /* * Copyright (c) 2007 Cisco Systems, Inc. All rights reserved. * Copyright (c) 2007, 2008 Mellanox Technologies. All rights reserved. diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h index 1791bf123ba9..23dba2d40907 100644 --- a/include/uapi/rdma/mlx5-abi.h +++ b/include/uapi/rdma/mlx5-abi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ /* * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved. * diff --git a/include/uapi/rdma/mthca-abi.h b/include/uapi/rdma/mthca-abi.h index bcbf4ff2f6d1..3020d8a907a7 100644 --- a/include/uapi/rdma/mthca-abi.h +++ b/include/uapi/rdma/mthca-abi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ /* * Copyright (c) 2005 Topspin Communications. All rights reserved. * Copyright (c) 2005, 2006 Cisco Systems. All rights reserved. diff --git a/include/uapi/rdma/nes-abi.h b/include/uapi/rdma/nes-abi.h index 6eb3734394a2..f5b2437aab28 100644 --- a/include/uapi/rdma/nes-abi.h +++ b/include/uapi/rdma/nes-abi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ /* * Copyright (c) 2006 - 2011 Intel Corporation. All rights reserved. * Copyright (c) 2005 Topspin Communications. All rights reserved. diff --git a/include/uapi/rdma/ocrdma-abi.h b/include/uapi/rdma/ocrdma-abi.h index 9f28191bef4d..ad64a3cea1cd 100644 --- a/include/uapi/rdma/ocrdma-abi.h +++ b/include/uapi/rdma/ocrdma-abi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ /* This file is part of the Emulex RoCE Device Driver for * RoCE (RDMA over Converged Ethernet) adapters. * Copyright (C) 2012-2015 Emulex. All rights reserved. diff --git a/include/uapi/rdma/qedr-abi.h b/include/uapi/rdma/qedr-abi.h index 54b64357ab24..261c6db4623e 100644 --- a/include/uapi/rdma/qedr-abi.h +++ b/include/uapi/rdma/qedr-abi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ /* QLogic qedr NIC Driver * Copyright (c) 2015-2016 QLogic Corporation * diff --git a/include/uapi/rdma/rdma_user_cm.h b/include/uapi/rdma/rdma_user_cm.h index d71da36e3cd6..c83ef0026079 100644 --- a/include/uapi/rdma/rdma_user_cm.h +++ b/include/uapi/rdma/rdma_user_cm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ /* * Copyright (c) 2005-2006 Intel Corporation. All rights reserved. * diff --git a/include/uapi/rdma/rdma_user_ioctl.h b/include/uapi/rdma/rdma_user_ioctl.h index 165a27e969d5..03557b5f9aa6 100644 --- a/include/uapi/rdma/rdma_user_ioctl.h +++ b/include/uapi/rdma/rdma_user_ioctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ /* * Copyright (c) 2016 Mellanox Technologies, LTD. All rights reserved. * diff --git a/include/uapi/rdma/rdma_user_rxe.h b/include/uapi/rdma/rdma_user_rxe.h index 1de99cfdaf7d..bdeea948b2f3 100644 --- a/include/uapi/rdma/rdma_user_rxe.h +++ b/include/uapi/rdma/rdma_user_rxe.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ /* * Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved. * diff --git a/include/uapi/rdma/vmw_pvrdma-abi.h b/include/uapi/rdma/vmw_pvrdma-abi.h index c6569b0032ec..912ea1556a0b 100644 --- a/include/uapi/rdma/vmw_pvrdma-abi.h +++ b/include/uapi/rdma/vmw_pvrdma-abi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ /* * Copyright (c) 2012-2016 VMware, Inc. All rights reserved. * diff --git a/include/uapi/scsi/cxlflash_ioctl.h b/include/uapi/scsi/cxlflash_ioctl.h index 48d107e75cf2..513da47aa5ab 100644 --- a/include/uapi/scsi/cxlflash_ioctl.h +++ b/include/uapi/scsi/cxlflash_ioctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * CXL Flash Device Driver * diff --git a/include/uapi/scsi/fc/fc_els.h b/include/uapi/scsi/fc/fc_els.h index 481abbd48e39..b7e0a5ed40de 100644 --- a/include/uapi/scsi/fc/fc_els.h +++ b/include/uapi/scsi/fc/fc_els.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright(c) 2007 Intel Corporation. All rights reserved. * diff --git a/include/uapi/scsi/fc/fc_fs.h b/include/uapi/scsi/fc/fc_fs.h index dcf314dc2a27..8c0a292a61ed 100644 --- a/include/uapi/scsi/fc/fc_fs.h +++ b/include/uapi/scsi/fc/fc_fs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright(c) 2007 Intel Corporation. All rights reserved. * diff --git a/include/uapi/scsi/fc/fc_gs.h b/include/uapi/scsi/fc/fc_gs.h index a37346d47eb1..2153f3524555 100644 --- a/include/uapi/scsi/fc/fc_gs.h +++ b/include/uapi/scsi/fc/fc_gs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright(c) 2007 Intel Corporation. All rights reserved. * diff --git a/include/uapi/scsi/fc/fc_ns.h b/include/uapi/scsi/fc/fc_ns.h index f7751d53f1d3..015e5e1ce8f1 100644 --- a/include/uapi/scsi/fc/fc_ns.h +++ b/include/uapi/scsi/fc/fc_ns.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright(c) 2007 Intel Corporation. All rights reserved. * diff --git a/include/uapi/scsi/scsi_bsg_fc.h b/include/uapi/scsi/scsi_bsg_fc.h index 3031b900b087..62597d86beed 100644 --- a/include/uapi/scsi/scsi_bsg_fc.h +++ b/include/uapi/scsi/scsi_bsg_fc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * FC Transport BSG Interface * diff --git a/include/uapi/scsi/scsi_netlink.h b/include/uapi/scsi/scsi_netlink.h index 62b4edab15d3..5ccc2333acab 100644 --- a/include/uapi/scsi/scsi_netlink.h +++ b/include/uapi/scsi/scsi_netlink.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * SCSI Transport Netlink Interface * Used for the posting of outbound SCSI transport events diff --git a/include/uapi/scsi/scsi_netlink_fc.h b/include/uapi/scsi/scsi_netlink_fc.h index cbf76e479761..060f563c38a2 100644 --- a/include/uapi/scsi/scsi_netlink_fc.h +++ b/include/uapi/scsi/scsi_netlink_fc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * FC Transport Netlink Interface * diff --git a/include/uapi/sound/asequencer.h b/include/uapi/sound/asequencer.h index 7b7659a79ac4..a75e14edc957 100644 --- a/include/uapi/sound/asequencer.h +++ b/include/uapi/sound/asequencer.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Main header file for the ALSA sequencer * Copyright (c) 1998-1999 by Frank van de Pol diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h index 78014ec56357..69c37ecbff7e 100644 --- a/include/uapi/sound/asoc.h +++ b/include/uapi/sound/asoc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * uapi/sound/asoc.h -- ALSA SoC Firmware Controls and DAPM * diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index 1949923a40bf..299a822d2c4e 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Advanced Linux Sound Architecture - ALSA - Driver * Copyright (c) 1994-2003 by Jaroslav Kysela , diff --git a/include/uapi/sound/asound_fm.h b/include/uapi/sound/asound_fm.h index c2a4b967d5be..8471f404ff0b 100644 --- a/include/uapi/sound/asound_fm.h +++ b/include/uapi/sound/asound_fm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ #ifndef __SOUND_ASOUND_FM_H #define __SOUND_ASOUND_FM_H diff --git a/include/uapi/sound/compress_offload.h b/include/uapi/sound/compress_offload.h index e00d8cbfc628..56d95673ce0f 100644 --- a/include/uapi/sound/compress_offload.h +++ b/include/uapi/sound/compress_offload.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * compress_offload.h - compress offload header definations * diff --git a/include/uapi/sound/compress_params.h b/include/uapi/sound/compress_params.h index 9625484a4a2a..3d4d6de66a17 100644 --- a/include/uapi/sound/compress_params.h +++ b/include/uapi/sound/compress_params.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) AND MIT) */ /* * compress_params.h - codec types and parameters for compressed data * streaming interface diff --git a/include/uapi/sound/emu10k1.h b/include/uapi/sound/emu10k1.h index 5175e166987d..042c5a6f16ee 100644 --- a/include/uapi/sound/emu10k1.h +++ b/include/uapi/sound/emu10k1.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (c) by Jaroslav Kysela , * Creative Labs, Inc. diff --git a/include/uapi/sound/hdsp.h b/include/uapi/sound/hdsp.h index 0909a3843479..5dc0c3db0a4c 100644 --- a/include/uapi/sound/hdsp.h +++ b/include/uapi/sound/hdsp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ #ifndef __SOUND_HDSP_H #define __SOUND_HDSP_H diff --git a/include/uapi/sound/hdspm.h b/include/uapi/sound/hdspm.h index c4db6f5b306e..a38f3f79beb7 100644 --- a/include/uapi/sound/hdspm.h +++ b/include/uapi/sound/hdspm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ #ifndef __SOUND_HDSPM_H #define __SOUND_HDSPM_H /* diff --git a/include/uapi/sound/sb16_csp.h b/include/uapi/sound/sb16_csp.h index 3b96907e2afb..e64851481d88 100644 --- a/include/uapi/sound/sb16_csp.h +++ b/include/uapi/sound/sb16_csp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (c) 1999 by Uros Bizjak * Takashi Iwai diff --git a/include/uapi/sound/sfnt_info.h b/include/uapi/sound/sfnt_info.h index 1bce7fd1725f..c9a810a6ef48 100644 --- a/include/uapi/sound/sfnt_info.h +++ b/include/uapi/sound/sfnt_info.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ #ifndef __SOUND_SFNT_INFO_H #define __SOUND_SFNT_INFO_H diff --git a/include/uapi/sound/snd_sst_tokens.h b/include/uapi/sound/snd_sst_tokens.h index f691e421f5e8..326054a72bc7 100644 --- a/include/uapi/sound/snd_sst_tokens.h +++ b/include/uapi/sound/snd_sst_tokens.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * snd_sst_tokens.h - Intel SST tokens definition * diff --git a/include/uapi/sound/tlv.h b/include/uapi/sound/tlv.h index b4df440c015b..be5371f09a62 100644 --- a/include/uapi/sound/tlv.h +++ b/include/uapi/sound/tlv.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by diff --git a/include/uapi/sound/usb_stream.h b/include/uapi/sound/usb_stream.h index cfe8fba00714..95419d8bbc16 100644 --- a/include/uapi/sound/usb_stream.h +++ b/include/uapi/sound/usb_stream.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * Copyright (C) 2007, 2008 Karsten Wiese * diff --git a/include/uapi/video/sisfb.h b/include/uapi/video/sisfb.h index 9250b22b10f8..f1e811951288 100644 --- a/include/uapi/video/sisfb.h +++ b/include/uapi/video/sisfb.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * sisfb.h - definitions for the SiS framebuffer driver * diff --git a/include/uapi/xen/evtchn.h b/include/uapi/xen/evtchn.h index cb4aa4bb905e..7fbf732f168f 100644 --- a/include/uapi/xen/evtchn.h +++ b/include/uapi/xen/evtchn.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR MIT) */ /****************************************************************************** * evtchn.h * diff --git a/include/uapi/xen/gntdev.h b/include/uapi/xen/gntdev.h index d0661977667e..6d1163456c03 100644 --- a/include/uapi/xen/gntdev.h +++ b/include/uapi/xen/gntdev.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR MIT) */ /****************************************************************************** * gntdev.h * diff --git a/include/uapi/xen/privcmd.h b/include/uapi/xen/privcmd.h index 63ee95c9dabb..39d3e7b8e993 100644 --- a/include/uapi/xen/privcmd.h +++ b/include/uapi/xen/privcmd.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR MIT) */ /****************************************************************************** * privcmd.h * diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h index 5db2d4c6a55f..1f57bbe82b6f 100644 --- a/tools/arch/arm/include/uapi/asm/kvm.h +++ b/tools/arch/arm/include/uapi/asm/kvm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2012 - Virtual Open Systems and Columbia University * Author: Christoffer Dall diff --git a/tools/arch/arm64/include/uapi/asm/bitsperlong.h b/tools/arch/arm64/include/uapi/asm/bitsperlong.h index fce9c2924fa3..485d60bee26c 100644 --- a/tools/arch/arm64/include/uapi/asm/bitsperlong.h +++ b/tools/arch/arm64/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2012 ARM Ltd. * diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 9f3ca24bbcc6..51149ec75fe4 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (C) 2012,2013 - ARM Ltd * Author: Marc Zyngier diff --git a/tools/arch/hexagon/include/uapi/asm/bitsperlong.h b/tools/arch/hexagon/include/uapi/asm/bitsperlong.h index 4a658151383d..5adca0d26913 100644 --- a/tools/arch/hexagon/include/uapi/asm/bitsperlong.h +++ b/tools/arch/hexagon/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved. * diff --git a/tools/arch/mips/include/uapi/asm/bitsperlong.h b/tools/arch/mips/include/uapi/asm/bitsperlong.h index 3e4c10a8e787..7268380d8d28 100644 --- a/tools/arch/mips/include/uapi/asm/bitsperlong.h +++ b/tools/arch/mips/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __ASM_MIPS_BITSPERLONG_H #define __ASM_MIPS_BITSPERLONG_H diff --git a/tools/arch/mips/include/uapi/asm/kvm.h b/tools/arch/mips/include/uapi/asm/kvm.h index 6985eb59b085..d2714cc1cd93 100644 --- a/tools/arch/mips/include/uapi/asm/kvm.h +++ b/tools/arch/mips/include/uapi/asm/kvm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h index 8cf8f0c96906..61d6049f4c1e 100644 --- a/tools/arch/powerpc/include/uapi/asm/kvm.h +++ b/tools/arch/powerpc/include/uapi/asm/kvm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License, version 2, as diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index cd7359e23d86..9ad172dcd912 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_KVM_S390_H #define __LINUX_KVM_S390_H /* diff --git a/tools/arch/s390/include/uapi/asm/kvm_perf.h b/tools/arch/s390/include/uapi/asm/kvm_perf.h index 397282727e21..c36c97ffdc6f 100644 --- a/tools/arch/s390/include/uapi/asm/kvm_perf.h +++ b/tools/arch/s390/include/uapi/asm/kvm_perf.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Definitions for perf-kvm on s390 * diff --git a/tools/arch/tile/include/uapi/asm/bitsperlong.h b/tools/arch/tile/include/uapi/asm/bitsperlong.h index 58c771f2af2f..57cca78c0fbb 100644 --- a/tools/arch/tile/include/uapi/asm/bitsperlong.h +++ b/tools/arch/tile/include/uapi/asm/bitsperlong.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * Copyright 2010 Tilera Corporation. All Rights Reserved. * diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h index 3725e145aa58..a9731f8a480f 100644 --- a/tools/arch/x86/include/uapi/asm/svm.h +++ b/tools/arch/x86/include/uapi/asm/svm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef _UAPI__SVM_H #define _UAPI__SVM_H diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h index 690a2dcf4078..f0b0c90dd398 100644 --- a/tools/arch/x86/include/uapi/asm/vmx.h +++ b/tools/arch/x86/include/uapi/asm/vmx.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* * vmx.h: VMX Architecture related definitions * Copyright (c) 2004, Intel Corporation. -- cgit v1.2.3-71-gd317 From 7582e22038a266444eb87bc07c372592ad647439 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Tue, 31 Oct 2017 15:51:08 +0000 Subject: arm64/sve: Backend logic for setting the vector length MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch implements the core logic for changing a task's vector length on request from userspace. This will be used by the ptrace and prctl frontends that are implemented in later patches. The SVE architecture permits, but does not require, implementations to support vector lengths that are not a power of two. To handle this, logic is added to check a requested vector length against a possibly sparse bitmap of available vector lengths at runtime, so that the best supported value can be chosen. Signed-off-by: Dave Martin Reviewed-by: Catalin Marinas Cc: Alex Bennée Signed-off-by: Will Deacon --- arch/arm64/include/asm/fpsimd.h | 8 +++ arch/arm64/kernel/fpsimd.c | 137 +++++++++++++++++++++++++++++++++++++++- include/uapi/linux/prctl.h | 5 ++ 3 files changed, 149 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index 9bbd74c0ea6b..86f550ce7b4d 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -20,6 +20,7 @@ #ifndef __ASSEMBLY__ +#include #include /* @@ -70,17 +71,24 @@ extern void fpsimd_update_current_state(struct fpsimd_state *state); extern void fpsimd_flush_task_state(struct task_struct *target); +/* Maximum VL that SVE VL-agnostic software can transparently support */ +#define SVE_VL_ARCH_MAX 0x100 + extern void sve_save_state(void *state, u32 *pfpsr); extern void sve_load_state(void const *state, u32 const *pfpsr, unsigned long vq_minus_1); extern unsigned int sve_get_vl(void); +extern int __ro_after_init sve_max_vl; + #ifdef CONFIG_ARM64_SVE extern size_t sve_state_size(struct task_struct const *task); extern void sve_alloc(struct task_struct *task); extern void fpsimd_release_task(struct task_struct *task); +extern int sve_set_vector_length(struct task_struct *task, + unsigned long vl, unsigned long flags); #else /* ! CONFIG_ARM64_SVE */ diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index e7733fb19388..667be3472114 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -17,8 +17,10 @@ * along with this program. If not, see . */ +#include #include #include +#include #include #include #include @@ -28,6 +30,7 @@ #include #include #include +#include #include #include #include @@ -114,6 +117,20 @@ static DEFINE_PER_CPU(struct fpsimd_state *, fpsimd_last_state); /* Default VL for tasks that don't set it explicitly: */ static int sve_default_vl = SVE_VL_MIN; +#ifdef CONFIG_ARM64_SVE + +/* Maximum supported vector length across all CPUs (initially poisoned) */ +int __ro_after_init sve_max_vl = -1; +/* Set of available vector lengths, as vq_to_bit(vq): */ +static DECLARE_BITMAP(sve_vq_map, SVE_VQ_MAX); + +#else /* ! CONFIG_ARM64_SVE */ + +/* Dummy declaration for code that will be optimised out: */ +extern DECLARE_BITMAP(sve_vq_map, SVE_VQ_MAX); + +#endif /* ! CONFIG_ARM64_SVE */ + /* * Call __sve_free() directly only if you know task can't be scheduled * or preempted. @@ -271,6 +288,50 @@ static void task_fpsimd_save(void) } } +/* + * Helpers to translate bit indices in sve_vq_map to VQ values (and + * vice versa). This allows find_next_bit() to be used to find the + * _maximum_ VQ not exceeding a certain value. + */ + +static unsigned int vq_to_bit(unsigned int vq) +{ + return SVE_VQ_MAX - vq; +} + +static unsigned int bit_to_vq(unsigned int bit) +{ + if (WARN_ON(bit >= SVE_VQ_MAX)) + bit = SVE_VQ_MAX - 1; + + return SVE_VQ_MAX - bit; +} + +/* + * All vector length selection from userspace comes through here. + * We're on a slow path, so some sanity-checks are included. + * If things go wrong there's a bug somewhere, but try to fall back to a + * safe choice. + */ +static unsigned int find_supported_vector_length(unsigned int vl) +{ + int bit; + int max_vl = sve_max_vl; + + if (WARN_ON(!sve_vl_valid(vl))) + vl = SVE_VL_MIN; + + if (WARN_ON(!sve_vl_valid(max_vl))) + max_vl = SVE_VL_MIN; + + if (vl > max_vl) + vl = max_vl; + + bit = find_next_bit(sve_vq_map, SVE_VQ_MAX, + vq_to_bit(sve_vq_from_vl(vl))); + return sve_vl_from_vq(bit_to_vq(bit)); +} + #define ZREG(sve_state, vq, n) ((char *)(sve_state) + \ (SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET)) @@ -365,6 +426,76 @@ void sve_alloc(struct task_struct *task) BUG_ON(!task->thread.sve_state); } +int sve_set_vector_length(struct task_struct *task, + unsigned long vl, unsigned long flags) +{ + if (flags & ~(unsigned long)(PR_SVE_VL_INHERIT | + PR_SVE_SET_VL_ONEXEC)) + return -EINVAL; + + if (!sve_vl_valid(vl)) + return -EINVAL; + + /* + * Clamp to the maximum vector length that VL-agnostic SVE code can + * work with. A flag may be assigned in the future to allow setting + * of larger vector lengths without confusing older software. + */ + if (vl > SVE_VL_ARCH_MAX) + vl = SVE_VL_ARCH_MAX; + + vl = find_supported_vector_length(vl); + + if (flags & (PR_SVE_VL_INHERIT | + PR_SVE_SET_VL_ONEXEC)) + task->thread.sve_vl_onexec = vl; + else + /* Reset VL to system default on next exec: */ + task->thread.sve_vl_onexec = 0; + + /* Only actually set the VL if not deferred: */ + if (flags & PR_SVE_SET_VL_ONEXEC) + goto out; + + if (vl == task->thread.sve_vl) + goto out; + + /* + * To ensure the FPSIMD bits of the SVE vector registers are preserved, + * write any live register state back to task_struct, and convert to a + * non-SVE thread. + */ + if (task == current) { + local_bh_disable(); + + task_fpsimd_save(); + set_thread_flag(TIF_FOREIGN_FPSTATE); + } + + fpsimd_flush_task_state(task); + if (test_and_clear_tsk_thread_flag(task, TIF_SVE)) + sve_to_fpsimd(task); + + if (task == current) + local_bh_enable(); + + /* + * Force reallocation of task SVE state to the correct size + * on next use: + */ + sve_free(task); + + task->thread.sve_vl = vl; + +out: + if (flags & PR_SVE_VL_INHERIT) + set_tsk_thread_flag(task, TIF_SVE_VL_INHERIT); + else + clear_tsk_thread_flag(task, TIF_SVE_VL_INHERIT); + + return 0; +} + /* * Called from the put_task_struct() path, which cannot get here * unless dead_task is really dead and not schedulable. @@ -481,7 +612,7 @@ void fpsimd_thread_switch(struct task_struct *next) void fpsimd_flush_thread(void) { - int vl; + int vl, supported_vl; if (!system_supports_fpsimd()) return; @@ -509,6 +640,10 @@ void fpsimd_flush_thread(void) if (WARN_ON(!sve_vl_valid(vl))) vl = SVE_VL_MIN; + supported_vl = find_supported_vector_length(vl); + if (WARN_ON(supported_vl != vl)) + vl = supported_vl; + current->thread.sve_vl = vl; /* diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index a8d0759a9e40..1b64901ca6b3 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -197,4 +197,9 @@ struct prctl_mm_map { # define PR_CAP_AMBIENT_LOWER 3 # define PR_CAP_AMBIENT_CLEAR_ALL 4 +/* arm64 Scalable Vector Extension controls */ +# define PR_SVE_SET_VL_ONEXEC (1 << 18) /* defer effect until exec */ +# define PR_SVE_VL_LEN_MASK 0xffff +# define PR_SVE_VL_INHERIT (1 << 17) /* inherit across exec */ + #endif /* _LINUX_PRCTL_H */ -- cgit v1.2.3-71-gd317 From 43d4da2c45b2f5d62f8a79ff7c6f95089bb24656 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Tue, 31 Oct 2017 15:51:13 +0000 Subject: arm64/sve: ptrace and ELF coredump support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch defines and implements a new regset NT_ARM_SVE, which describes a thread's SVE register state. This allows a debugger to manipulate the SVE state, as well as being included in ELF coredumps for post-mortem debugging. Because the regset size and layout are dependent on the thread's current vector length, it is not possible to define a C struct to describe the regset contents as is done for existing regsets. Instead, and for the same reasons, NT_ARM_SVE is based on the freeform variable-layout approach used for the SVE signal frame. Additionally, to reduce debug overhead when debugging threads that might or might not have live SVE register state, NT_ARM_SVE may be presented in one of two different formats: the old struct user_fpsimd_state format is embedded for describing the state of a thread with no live SVE state, whereas a new variable-layout structure is embedded for describing live SVE state. This avoids a debugger needing to poll NT_PRFPREG in addition to NT_ARM_SVE, and allows existing userspace code to handle the non-SVE case without too much modification. For this to work, NT_ARM_SVE is defined with a fixed-format header of type struct user_sve_header, which the recipient can use to figure out the content, size and layout of the reset of the regset. Accessor macros are defined to allow the vector-length-dependent parts of the regset to be manipulated. Signed-off-by: Alan Hayward Signed-off-by: Dave Martin Reviewed-by: Catalin Marinas Cc: Alex Bennée Cc: Okamoto Takayuki Signed-off-by: Will Deacon --- arch/arm64/include/asm/fpsimd.h | 12 +- arch/arm64/include/uapi/asm/ptrace.h | 138 +++++++++++++++++ arch/arm64/kernel/fpsimd.c | 60 ++++++++ arch/arm64/kernel/ptrace.c | 280 ++++++++++++++++++++++++++++++++++- include/uapi/linux/elf.h | 1 + 5 files changed, 482 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index d8e0dc9f65a1..d754e5a6949c 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -38,13 +38,16 @@ struct fpsimd_state { __uint128_t vregs[32]; u32 fpsr; u32 fpcr; + /* + * For ptrace compatibility, pad to next 128-bit + * boundary here if extending this struct. + */ }; }; /* the id of the last cpu to have restored this state */ unsigned int cpu; }; - #if defined(__KERNEL__) && defined(CONFIG_COMPAT) /* Masks for extracting the FPSR and FPCR from the FPSCR */ #define VFP_FPSCR_STAT_MASK 0xf800009f @@ -88,6 +91,10 @@ extern size_t sve_state_size(struct task_struct const *task); extern void sve_alloc(struct task_struct *task); extern void fpsimd_release_task(struct task_struct *task); +extern void fpsimd_sync_to_sve(struct task_struct *task); +extern void sve_sync_to_fpsimd(struct task_struct *task); +extern void sve_sync_from_fpsimd_zeropad(struct task_struct *task); + extern int sve_set_vector_length(struct task_struct *task, unsigned long vl, unsigned long flags); @@ -104,6 +111,9 @@ extern void __init sve_setup(void); static inline void sve_alloc(struct task_struct *task) { } static inline void fpsimd_release_task(struct task_struct *task) { } +static inline void sve_sync_to_fpsimd(struct task_struct *task) { } +static inline void sve_sync_from_fpsimd_zeropad(struct task_struct *task) { } + static inline void sve_init_vq_map(void) { } static inline void sve_update_vq_map(void) { } static inline int sve_verify_vq_map(void) { return 0; } diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h index 3697d95ba0a1..e7085589f81c 100644 --- a/arch/arm64/include/uapi/asm/ptrace.h +++ b/arch/arm64/include/uapi/asm/ptrace.h @@ -22,6 +22,7 @@ #include #include +#include /* @@ -62,6 +63,8 @@ #ifndef __ASSEMBLY__ +#include + /* * User structures for general purpose, floating point and debug registers. */ @@ -89,6 +92,141 @@ struct user_hwdebug_state { } dbg_regs[16]; }; +/* SVE/FP/SIMD state (NT_ARM_SVE) */ + +struct user_sve_header { + __u32 size; /* total meaningful regset content in bytes */ + __u32 max_size; /* maxmium possible size for this thread */ + __u16 vl; /* current vector length */ + __u16 max_vl; /* maximum possible vector length */ + __u16 flags; + __u16 __reserved; +}; + +/* Definitions for user_sve_header.flags: */ +#define SVE_PT_REGS_MASK (1 << 0) + +#define SVE_PT_REGS_FPSIMD 0 +#define SVE_PT_REGS_SVE SVE_PT_REGS_MASK + +/* + * Common SVE_PT_* flags: + * These must be kept in sync with prctl interface in + */ +#define SVE_PT_VL_INHERIT (PR_SVE_VL_INHERIT >> 16) +#define SVE_PT_VL_ONEXEC (PR_SVE_SET_VL_ONEXEC >> 16) + + +/* + * The remainder of the SVE state follows struct user_sve_header. The + * total size of the SVE state (including header) depends on the + * metadata in the header: SVE_PT_SIZE(vq, flags) gives the total size + * of the state in bytes, including the header. + * + * Refer to for details of how to pass the correct + * "vq" argument to these macros. + */ + +/* Offset from the start of struct user_sve_header to the register data */ +#define SVE_PT_REGS_OFFSET \ + ((sizeof(struct sve_context) + (SVE_VQ_BYTES - 1)) \ + / SVE_VQ_BYTES * SVE_VQ_BYTES) + +/* + * The register data content and layout depends on the value of the + * flags field. + */ + +/* + * (flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD case: + * + * The payload starts at offset SVE_PT_FPSIMD_OFFSET, and is of type + * struct user_fpsimd_state. Additional data might be appended in the + * future: use SVE_PT_FPSIMD_SIZE(vq, flags) to compute the total size. + * SVE_PT_FPSIMD_SIZE(vq, flags) will never be less than + * sizeof(struct user_fpsimd_state). + */ + +#define SVE_PT_FPSIMD_OFFSET SVE_PT_REGS_OFFSET + +#define SVE_PT_FPSIMD_SIZE(vq, flags) (sizeof(struct user_fpsimd_state)) + +/* + * (flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE case: + * + * The payload starts at offset SVE_PT_SVE_OFFSET, and is of size + * SVE_PT_SVE_SIZE(vq, flags). + * + * Additional macros describe the contents and layout of the payload. + * For each, SVE_PT_SVE_x_OFFSET(args) is the start offset relative to + * the start of struct user_sve_header, and SVE_PT_SVE_x_SIZE(args) is + * the size in bytes: + * + * x type description + * - ---- ----------- + * ZREGS \ + * ZREG | + * PREGS | refer to + * PREG | + * FFR / + * + * FPSR uint32_t FPSR + * FPCR uint32_t FPCR + * + * Additional data might be appended in the future. + */ + +#define SVE_PT_SVE_ZREG_SIZE(vq) SVE_SIG_ZREG_SIZE(vq) +#define SVE_PT_SVE_PREG_SIZE(vq) SVE_SIG_PREG_SIZE(vq) +#define SVE_PT_SVE_FFR_SIZE(vq) SVE_SIG_FFR_SIZE(vq) +#define SVE_PT_SVE_FPSR_SIZE sizeof(__u32) +#define SVE_PT_SVE_FPCR_SIZE sizeof(__u32) + +#define __SVE_SIG_TO_PT(offset) \ + ((offset) - SVE_SIG_REGS_OFFSET + SVE_PT_REGS_OFFSET) + +#define SVE_PT_SVE_OFFSET SVE_PT_REGS_OFFSET + +#define SVE_PT_SVE_ZREGS_OFFSET \ + __SVE_SIG_TO_PT(SVE_SIG_ZREGS_OFFSET) +#define SVE_PT_SVE_ZREG_OFFSET(vq, n) \ + __SVE_SIG_TO_PT(SVE_SIG_ZREG_OFFSET(vq, n)) +#define SVE_PT_SVE_ZREGS_SIZE(vq) \ + (SVE_PT_SVE_ZREG_OFFSET(vq, SVE_NUM_ZREGS) - SVE_PT_SVE_ZREGS_OFFSET) + +#define SVE_PT_SVE_PREGS_OFFSET(vq) \ + __SVE_SIG_TO_PT(SVE_SIG_PREGS_OFFSET(vq)) +#define SVE_PT_SVE_PREG_OFFSET(vq, n) \ + __SVE_SIG_TO_PT(SVE_SIG_PREG_OFFSET(vq, n)) +#define SVE_PT_SVE_PREGS_SIZE(vq) \ + (SVE_PT_SVE_PREG_OFFSET(vq, SVE_NUM_PREGS) - \ + SVE_PT_SVE_PREGS_OFFSET(vq)) + +#define SVE_PT_SVE_FFR_OFFSET(vq) \ + __SVE_SIG_TO_PT(SVE_SIG_FFR_OFFSET(vq)) + +#define SVE_PT_SVE_FPSR_OFFSET(vq) \ + ((SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq) + \ + (SVE_VQ_BYTES - 1)) \ + / SVE_VQ_BYTES * SVE_VQ_BYTES) +#define SVE_PT_SVE_FPCR_OFFSET(vq) \ + (SVE_PT_SVE_FPSR_OFFSET(vq) + SVE_PT_SVE_FPSR_SIZE) + +/* + * Any future extension appended after FPCR must be aligned to the next + * 128-bit boundary. + */ + +#define SVE_PT_SVE_SIZE(vq, flags) \ + ((SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE \ + - SVE_PT_SVE_OFFSET + (SVE_VQ_BYTES - 1)) \ + / SVE_VQ_BYTES * SVE_VQ_BYTES) + +#define SVE_PT_SIZE(vq, flags) \ + (((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE ? \ + SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, flags) \ + : SVE_PT_FPSIMD_OFFSET + SVE_PT_FPSIMD_SIZE(vq, flags)) + #endif /* __ASSEMBLY__ */ #endif /* _UAPI__ASM_PTRACE_H */ diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 1e531156f1d7..b82d44693b9d 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -428,6 +428,66 @@ void sve_alloc(struct task_struct *task) BUG_ON(!task->thread.sve_state); } + +/* + * Ensure that task->thread.sve_state is up to date with respect to + * the user task, irrespective of when SVE is in use or not. + * + * This should only be called by ptrace. task must be non-runnable. + * task->thread.sve_state must point to at least sve_state_size(task) + * bytes of allocated kernel memory. + */ +void fpsimd_sync_to_sve(struct task_struct *task) +{ + if (!test_tsk_thread_flag(task, TIF_SVE)) + fpsimd_to_sve(task); +} + +/* + * Ensure that task->thread.fpsimd_state is up to date with respect to + * the user task, irrespective of whether SVE is in use or not. + * + * This should only be called by ptrace. task must be non-runnable. + * task->thread.sve_state must point to at least sve_state_size(task) + * bytes of allocated kernel memory. + */ +void sve_sync_to_fpsimd(struct task_struct *task) +{ + if (test_tsk_thread_flag(task, TIF_SVE)) + sve_to_fpsimd(task); +} + +/* + * Ensure that task->thread.sve_state is up to date with respect to + * the task->thread.fpsimd_state. + * + * This should only be called by ptrace to merge new FPSIMD register + * values into a task for which SVE is currently active. + * task must be non-runnable. + * task->thread.sve_state must point to at least sve_state_size(task) + * bytes of allocated kernel memory. + * task->thread.fpsimd_state must already have been initialised with + * the new FPSIMD register values to be merged in. + */ +void sve_sync_from_fpsimd_zeropad(struct task_struct *task) +{ + unsigned int vq; + void *sst = task->thread.sve_state; + struct fpsimd_state const *fst = &task->thread.fpsimd_state; + unsigned int i; + + if (!test_tsk_thread_flag(task, TIF_SVE)) + return; + + vq = sve_vq_from_vl(task->thread.sve_vl); + + memset(sst, 0, SVE_SIG_REGS_SIZE(vq)); + + for (i = 0; i < 32; ++i) + memcpy(ZREG(sst, vq, i), &fst->vregs[i], + sizeof(fst->vregs[i])); +} + int sve_set_vector_length(struct task_struct *task, unsigned long vl, unsigned long flags) { diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 9cbb6123208f..7c44658b316d 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include #include @@ -40,6 +41,7 @@ #include #include +#include #include #include #include @@ -618,17 +620,56 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset, /* * TODO: update fp accessors for lazy context switching (sync/flush hwstate) */ -static int fpr_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) +static int __fpr_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf, unsigned int start_pos) { struct user_fpsimd_state *uregs; + + sve_sync_to_fpsimd(target); + uregs = &target->thread.fpsimd_state.user_fpsimd; + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, uregs, + start_pos, start_pos + sizeof(*uregs)); +} + +static int fpr_get(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ if (target == current) fpsimd_preserve_current_state(); - return user_regset_copyout(&pos, &count, &kbuf, &ubuf, uregs, 0, -1); + return __fpr_get(target, regset, pos, count, kbuf, ubuf, 0); +} + +static int __fpr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf, + unsigned int start_pos) +{ + int ret; + struct user_fpsimd_state newstate; + + /* + * Ensure target->thread.fpsimd_state is up to date, so that a + * short copyin can't resurrect stale data. + */ + sve_sync_to_fpsimd(target); + + newstate = target->thread.fpsimd_state.user_fpsimd; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newstate, + start_pos, start_pos + sizeof(newstate)); + if (ret) + return ret; + + target->thread.fpsimd_state.user_fpsimd = newstate; + + return ret; } static int fpr_set(struct task_struct *target, const struct user_regset *regset, @@ -636,15 +677,14 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset, const void *kbuf, const void __user *ubuf) { int ret; - struct user_fpsimd_state newstate = - target->thread.fpsimd_state.user_fpsimd; - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newstate, 0, -1); + ret = __fpr_set(target, regset, pos, count, kbuf, ubuf, 0); if (ret) return ret; - target->thread.fpsimd_state.user_fpsimd = newstate; + sve_sync_from_fpsimd_zeropad(target); fpsimd_flush_task_state(target); + return ret; } @@ -702,6 +742,215 @@ static int system_call_set(struct task_struct *target, return ret; } +#ifdef CONFIG_ARM64_SVE + +static void sve_init_header_from_task(struct user_sve_header *header, + struct task_struct *target) +{ + unsigned int vq; + + memset(header, 0, sizeof(*header)); + + header->flags = test_tsk_thread_flag(target, TIF_SVE) ? + SVE_PT_REGS_SVE : SVE_PT_REGS_FPSIMD; + if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT)) + header->flags |= SVE_PT_VL_INHERIT; + + header->vl = target->thread.sve_vl; + vq = sve_vq_from_vl(header->vl); + + header->max_vl = sve_max_vl; + if (WARN_ON(!sve_vl_valid(sve_max_vl))) + header->max_vl = header->vl; + + header->size = SVE_PT_SIZE(vq, header->flags); + header->max_size = SVE_PT_SIZE(sve_vq_from_vl(header->max_vl), + SVE_PT_REGS_SVE); +} + +static unsigned int sve_size_from_header(struct user_sve_header const *header) +{ + return ALIGN(header->size, SVE_VQ_BYTES); +} + +static unsigned int sve_get_size(struct task_struct *target, + const struct user_regset *regset) +{ + struct user_sve_header header; + + if (!system_supports_sve()) + return 0; + + sve_init_header_from_task(&header, target); + return sve_size_from_header(&header); +} + +static int sve_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + struct user_sve_header header; + unsigned int vq; + unsigned long start, end; + + if (!system_supports_sve()) + return -EINVAL; + + /* Header */ + sve_init_header_from_task(&header, target); + vq = sve_vq_from_vl(header.vl); + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &header, + 0, sizeof(header)); + if (ret) + return ret; + + if (target == current) + fpsimd_preserve_current_state(); + + /* Registers: FPSIMD-only case */ + + BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header)); + if ((header.flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD) + return __fpr_get(target, regset, pos, count, kbuf, ubuf, + SVE_PT_FPSIMD_OFFSET); + + /* Otherwise: full SVE case */ + + BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header)); + start = SVE_PT_SVE_OFFSET; + end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq); + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + target->thread.sve_state, + start, end); + if (ret) + return ret; + + start = end; + end = SVE_PT_SVE_FPSR_OFFSET(vq); + ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf, + start, end); + if (ret) + return ret; + + /* + * Copy fpsr, and fpcr which must follow contiguously in + * struct fpsimd_state: + */ + start = end; + end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE; + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.fpsimd_state.fpsr, + start, end); + if (ret) + return ret; + + start = end; + end = sve_size_from_header(&header); + return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf, + start, end); +} + +static int sve_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + struct user_sve_header header; + unsigned int vq; + unsigned long start, end; + + if (!system_supports_sve()) + return -EINVAL; + + /* Header */ + if (count < sizeof(header)) + return -EINVAL; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &header, + 0, sizeof(header)); + if (ret) + goto out; + + /* + * Apart from PT_SVE_REGS_MASK, all PT_SVE_* flags are consumed by + * sve_set_vector_length(), which will also validate them for us: + */ + ret = sve_set_vector_length(target, header.vl, + ((unsigned long)header.flags & ~SVE_PT_REGS_MASK) << 16); + if (ret) + goto out; + + /* Actual VL set may be less than the user asked for: */ + vq = sve_vq_from_vl(target->thread.sve_vl); + + /* Registers: FPSIMD-only case */ + + BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header)); + if ((header.flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD) { + ret = __fpr_set(target, regset, pos, count, kbuf, ubuf, + SVE_PT_FPSIMD_OFFSET); + clear_tsk_thread_flag(target, TIF_SVE); + goto out; + } + + /* Otherwise: full SVE case */ + + /* + * If setting a different VL from the requested VL and there is + * register data, the data layout will be wrong: don't even + * try to set the registers in this case. + */ + if (count && vq != sve_vq_from_vl(header.vl)) { + ret = -EIO; + goto out; + } + + sve_alloc(target); + + /* + * Ensure target->thread.sve_state is up to date with target's + * FPSIMD regs, so that a short copyin leaves trailing registers + * unmodified. + */ + fpsimd_sync_to_sve(target); + set_tsk_thread_flag(target, TIF_SVE); + + BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header)); + start = SVE_PT_SVE_OFFSET; + end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq); + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + target->thread.sve_state, + start, end); + if (ret) + goto out; + + start = end; + end = SVE_PT_SVE_FPSR_OFFSET(vq); + ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, + start, end); + if (ret) + goto out; + + /* + * Copy fpsr, and fpcr which must follow contiguously in + * struct fpsimd_state: + */ + start = end; + end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.fpsimd_state.fpsr, + start, end); + +out: + fpsimd_flush_task_state(target); + return ret; +} + +#endif /* CONFIG_ARM64_SVE */ + enum aarch64_regset { REGSET_GPR, REGSET_FPR, @@ -711,6 +960,9 @@ enum aarch64_regset { REGSET_HW_WATCH, #endif REGSET_SYSTEM_CALL, +#ifdef CONFIG_ARM64_SVE + REGSET_SVE, +#endif }; static const struct user_regset aarch64_regsets[] = { @@ -768,6 +1020,18 @@ static const struct user_regset aarch64_regsets[] = { .get = system_call_get, .set = system_call_set, }, +#ifdef CONFIG_ARM64_SVE + [REGSET_SVE] = { /* Scalable Vector Extension */ + .core_note_type = NT_ARM_SVE, + .n = DIV_ROUND_UP(SVE_PT_SIZE(SVE_VQ_MAX, SVE_PT_REGS_SVE), + SVE_VQ_BYTES), + .size = SVE_VQ_BYTES, + .align = SVE_VQ_BYTES, + .get = sve_get, + .set = sve_set, + .get_size = sve_get_size, + }, +#endif }; static const struct user_regset_view user_aarch64_view = { diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index b5280db9ef6a..735b8f4d12fc 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -416,6 +416,7 @@ typedef struct elf64_shdr { #define NT_ARM_HW_BREAK 0x402 /* ARM hardware breakpoint registers */ #define NT_ARM_HW_WATCH 0x403 /* ARM hardware watchpoint registers */ #define NT_ARM_SYSTEM_CALL 0x404 /* ARM system call number */ +#define NT_ARM_SVE 0x405 /* ARM Scalable Vector Extension registers */ #define NT_METAG_CBUF 0x500 /* Metag catch buffer registers */ #define NT_METAG_RPIPE 0x501 /* Metag read pipeline state */ #define NT_METAG_TLS 0x502 /* Metag TLS pointer */ -- cgit v1.2.3-71-gd317 From 2d2123bc7c7f843aa9db87720de159a049839862 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Tue, 31 Oct 2017 15:51:14 +0000 Subject: arm64/sve: Add prctl controls for userspace vector length management MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds two arm64-specific prctls, to permit userspace to control its vector length: * PR_SVE_SET_VL: set the thread's SVE vector length and vector length inheritance mode. * PR_SVE_GET_VL: get the same information. Although these prctls resemble instruction set features in the SVE architecture, they provide additional control: the vector length inheritance mode is Linux-specific and nothing to do with the architecture, and the architecture does not permit EL0 to set its own vector length directly. Both can be used in portable tools without requiring the use of SVE instructions. Signed-off-by: Dave Martin Reviewed-by: Catalin Marinas Cc: Alex Bennée [will: Fixed up prctl constants to avoid clash with PDEATHSIG] Signed-off-by: Will Deacon --- arch/arm64/include/asm/fpsimd.h | 14 +++++++++++ arch/arm64/include/asm/processor.h | 4 +++ arch/arm64/kernel/fpsimd.c | 50 ++++++++++++++++++++++++++++++++++++++ include/uapi/linux/prctl.h | 4 +++ kernel/sys.c | 12 +++++++++ 5 files changed, 84 insertions(+) (limited to 'include/uapi/linux') diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index d754e5a6949c..b868412c815c 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -17,6 +17,7 @@ #define __ASM_FP_H #include +#include #ifndef __ASSEMBLY__ @@ -98,6 +99,9 @@ extern void sve_sync_from_fpsimd_zeropad(struct task_struct *task); extern int sve_set_vector_length(struct task_struct *task, unsigned long vl, unsigned long flags); +extern int sve_set_current_vl(unsigned long arg); +extern int sve_get_current_vl(void); + /* * Probing and setup functions. * Calls to these functions must be serialised with one another. @@ -114,6 +118,16 @@ static inline void fpsimd_release_task(struct task_struct *task) { } static inline void sve_sync_to_fpsimd(struct task_struct *task) { } static inline void sve_sync_from_fpsimd_zeropad(struct task_struct *task) { } +static inline int sve_set_current_vl(unsigned long arg) +{ + return -EINVAL; +} + +static inline int sve_get_current_vl(void) +{ + return -EINVAL; +} + static inline void sve_init_vq_map(void) { } static inline void sve_update_vq_map(void) { } static inline int sve_verify_vq_map(void) { return 0; } diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index c6fddb005dc2..023cacb946c3 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -217,5 +217,9 @@ static inline void spin_lock_prefetch(const void *ptr) int cpu_enable_pan(void *__unused); int cpu_enable_cache_maint_trap(void *__unused); +/* Userspace interface for PR_SVE_{SET,GET}_VL prctl()s: */ +#define SVE_SET_VL(arg) sve_set_current_vl(arg) +#define SVE_GET_VL() sve_get_current_vl() + #endif /* __ASSEMBLY__ */ #endif /* __ASM_PROCESSOR_H */ diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index b82d44693b9d..fd3cfdd7f9be 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include #include @@ -558,6 +559,55 @@ out: return 0; } +/* + * Encode the current vector length and flags for return. + * This is only required for prctl(): ptrace has separate fields + * + * flags are as for sve_set_vector_length(). + */ +static int sve_prctl_status(unsigned long flags) +{ + int ret; + + if (flags & PR_SVE_SET_VL_ONEXEC) + ret = current->thread.sve_vl_onexec; + else + ret = current->thread.sve_vl; + + if (test_thread_flag(TIF_SVE_VL_INHERIT)) + ret |= PR_SVE_VL_INHERIT; + + return ret; +} + +/* PR_SVE_SET_VL */ +int sve_set_current_vl(unsigned long arg) +{ + unsigned long vl, flags; + int ret; + + vl = arg & PR_SVE_VL_LEN_MASK; + flags = arg & ~vl; + + if (!system_supports_sve()) + return -EINVAL; + + ret = sve_set_vector_length(current, vl, flags); + if (ret) + return ret; + + return sve_prctl_status(flags); +} + +/* PR_SVE_GET_VL */ +int sve_get_current_vl(void) +{ + if (!system_supports_sve()) + return -EINVAL; + + return sve_prctl_status(0); +} + /* * Bitmap for temporary storage of the per-CPU set of supported vector lengths * during secondary boot. diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 1b64901ca6b3..f60db5db6e8e 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -198,7 +198,11 @@ struct prctl_mm_map { # define PR_CAP_AMBIENT_CLEAR_ALL 4 /* arm64 Scalable Vector Extension controls */ +/* Flag values must be kept in sync with ptrace NT_ARM_SVE interface */ +#define PR_SVE_SET_VL 50 /* set task vector length */ # define PR_SVE_SET_VL_ONEXEC (1 << 18) /* defer effect until exec */ +#define PR_SVE_GET_VL 51 /* get task vector length */ +/* Bits common to PR_SVE_SET_VL and PR_SVE_GET_VL */ # define PR_SVE_VL_LEN_MASK 0xffff # define PR_SVE_VL_INHERIT (1 << 17) /* inherit across exec */ diff --git a/kernel/sys.c b/kernel/sys.c index 9aebc2935013..c541916b38c6 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -110,6 +110,12 @@ #ifndef SET_FP_MODE # define SET_FP_MODE(a,b) (-EINVAL) #endif +#ifndef SVE_SET_VL +# define SVE_SET_VL(a) (-EINVAL) +#endif +#ifndef SVE_GET_VL +# define SVE_GET_VL() (-EINVAL) +#endif /* * this is where the system-wide overflow UID and GID are defined, for @@ -2385,6 +2391,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_GET_FP_MODE: error = GET_FP_MODE(me); break; + case PR_SVE_SET_VL: + error = SVE_SET_VL(arg2); + break; + case PR_SVE_GET_VL: + error = SVE_GET_VL(); + break; default: error = -EINVAL; break; -- cgit v1.2.3-71-gd317 From 44b6b7661132b1b0e5fd3147ded66f1e4a817ca9 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Wed, 1 Nov 2017 14:25:35 -0500 Subject: platform/x86: wmi: create userspace interface for drivers For WMI operations that are only Set or Query readable and writable sysfs attributes created by WMI vendor drivers or the bus driver makes sense. For other WMI operations that are run on Method, there needs to be a way to guarantee to userspace that the results from the method call belong to the data request to the method call. Sysfs attributes don't work well in this scenario because two userspace processes may be competing at reading/writing an attribute and step on each other's data. When a WMI vendor driver declares a callback method in the wmi_driver the WMI bus driver will create a character device that maps to that function. This callback method will be responsible for filtering invalid requests and performing the actual call. That character device will correspond to this path: /dev/wmi/$driver Performing read() on this character device will provide the size of the buffer that the character device needs to perform calls. This buffer size can be set by vendor drivers through a new symbol or when MOF parsing is available by the MOF. Performing ioctl() on this character device will be interpretd by the WMI bus driver. It will perform sanity tests for size of data, test them for a valid instance, copy the data from userspace and pass iton to the vendor driver to further process and run. This creates an implicit policy that each driver will only be allowed a single character device. If a module matches multiple GUID's, the wmi_devices will need to be all handled by the same wmi_driver. The WMI vendor drivers will be responsible for managing inappropriate access to this character device and proper locking on data used by it. When a WMI vendor driver is unloaded the WMI bus driver will clean up the character device and any memory allocated for the call. Signed-off-by: Mario Limonciello Reviewed-by: Edward O'Callaghan Signed-off-by: Darren Hart (VMware) --- MAINTAINERS | 1 + drivers/platform/x86/wmi.c | 189 ++++++++++++++++++++++++++++++++++++++++++++- include/linux/wmi.h | 5 ++ include/uapi/linux/wmi.h | 26 +++++++ 4 files changed, 219 insertions(+), 2 deletions(-) create mode 100644 include/uapi/linux/wmi.h (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index aede236d10f1..3af07502220a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -384,6 +384,7 @@ ACPI WMI DRIVER L: platform-driver-x86@vger.kernel.org S: Orphan F: drivers/platform/x86/wmi.c +F: include/uapi/linux/wmi.h AD1889 ALSA SOUND DRIVER M: Thibaut Varene diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index bcb41c1c7f52..8c31ed4f0e1b 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -38,12 +38,15 @@ #include #include #include +#include #include #include #include #include +#include #include #include +#include ACPI_MODULE_NAME("wmi"); MODULE_AUTHOR("Carlos Corbacho"); @@ -69,9 +72,12 @@ struct wmi_block { struct wmi_device dev; struct list_head list; struct guid_block gblock; + struct miscdevice char_dev; + struct mutex char_mutex; struct acpi_device *acpi_device; wmi_notify_handler handler; void *handler_data; + u64 req_buf_size; bool read_takes_no_args; }; @@ -188,6 +194,25 @@ static acpi_status wmi_method_enable(struct wmi_block *wblock, int enable) /* * Exported WMI functions */ + +/** + * set_required_buffer_size - Sets the buffer size needed for performing IOCTL + * @wdev: A wmi bus device from a driver + * @instance: Instance index + * + * Allocates memory needed for buffer, stores the buffer size in that memory + */ +int set_required_buffer_size(struct wmi_device *wdev, u64 length) +{ + struct wmi_block *wblock; + + wblock = container_of(wdev, struct wmi_block, dev); + wblock->req_buf_size = length; + + return 0; +} +EXPORT_SYMBOL_GPL(set_required_buffer_size); + /** * wmi_evaluate_method - Evaluate a WMI method * @guid_string: 36 char string of the form fa50ff2b-f2e8-45de-83fa-65417f2f49ba @@ -764,6 +789,111 @@ static int wmi_dev_match(struct device *dev, struct device_driver *driver) return 0; } +static int wmi_char_open(struct inode *inode, struct file *filp) +{ + const char *driver_name = filp->f_path.dentry->d_iname; + struct wmi_block *wblock = NULL; + struct wmi_block *next = NULL; + + list_for_each_entry_safe(wblock, next, &wmi_block_list, list) { + if (!wblock->dev.dev.driver) + continue; + if (strcmp(driver_name, wblock->dev.dev.driver->name) == 0) { + filp->private_data = wblock; + break; + } + } + + if (!filp->private_data) + return -ENODEV; + + return nonseekable_open(inode, filp); +} + +static ssize_t wmi_char_read(struct file *filp, char __user *buffer, + size_t length, loff_t *offset) +{ + struct wmi_block *wblock = filp->private_data; + + return simple_read_from_buffer(buffer, length, offset, + &wblock->req_buf_size, + sizeof(wblock->req_buf_size)); +} + +static long wmi_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) +{ + struct wmi_ioctl_buffer __user *input = + (struct wmi_ioctl_buffer __user *) arg; + struct wmi_block *wblock = filp->private_data; + struct wmi_ioctl_buffer *buf = NULL; + struct wmi_driver *wdriver = NULL; + int ret; + + if (_IOC_TYPE(cmd) != WMI_IOC) + return -ENOTTY; + + /* make sure we're not calling a higher instance than exists*/ + if (_IOC_NR(cmd) >= wblock->gblock.instance_count) + return -EINVAL; + + mutex_lock(&wblock->char_mutex); + buf = wblock->handler_data; + if (get_user(buf->length, &input->length)) { + dev_dbg(&wblock->dev.dev, "Read length from user failed\n"); + ret = -EFAULT; + goto out_ioctl; + } + /* if it's too small, abort */ + if (buf->length < wblock->req_buf_size) { + dev_err(&wblock->dev.dev, + "Buffer %lld too small, need at least %lld\n", + buf->length, wblock->req_buf_size); + ret = -EINVAL; + goto out_ioctl; + } + /* if it's too big, warn, driver will only use what is needed */ + if (buf->length > wblock->req_buf_size) + dev_warn(&wblock->dev.dev, + "Buffer %lld is bigger than required %lld\n", + buf->length, wblock->req_buf_size); + + /* copy the structure from userspace */ + if (copy_from_user(buf, input, wblock->req_buf_size)) { + dev_dbg(&wblock->dev.dev, "Copy %llu from user failed\n", + wblock->req_buf_size); + ret = -EFAULT; + goto out_ioctl; + } + + /* let the driver do any filtering and do the call */ + wdriver = container_of(wblock->dev.dev.driver, + struct wmi_driver, driver); + if (!try_module_get(wdriver->driver.owner)) + return -EBUSY; + ret = wdriver->filter_callback(&wblock->dev, cmd, buf); + module_put(wdriver->driver.owner); + if (ret) + goto out_ioctl; + + /* return the result (only up to our internal buffer size) */ + if (copy_to_user(input, buf, wblock->req_buf_size)) { + dev_dbg(&wblock->dev.dev, "Copy %llu to user failed\n", + wblock->req_buf_size); + ret = -EFAULT; + } + +out_ioctl: + mutex_unlock(&wblock->char_mutex); + return ret; +} + +static const struct file_operations wmi_fops = { + .owner = THIS_MODULE, + .read = wmi_char_read, + .open = wmi_char_open, + .unlocked_ioctl = wmi_ioctl, + .compat_ioctl = wmi_ioctl, +}; static int wmi_dev_probe(struct device *dev) { @@ -771,16 +901,63 @@ static int wmi_dev_probe(struct device *dev) struct wmi_driver *wdriver = container_of(dev->driver, struct wmi_driver, driver); int ret = 0; + int count; + char *buf; if (ACPI_FAILURE(wmi_method_enable(wblock, 1))) dev_warn(dev, "failed to enable device -- probing anyway\n"); if (wdriver->probe) { ret = wdriver->probe(dev_to_wdev(dev)); - if (ret != 0 && ACPI_FAILURE(wmi_method_enable(wblock, 0))) - dev_warn(dev, "failed to disable device\n"); + if (ret != 0) + goto probe_failure; } + /* driver wants a character device made */ + if (wdriver->filter_callback) { + /* check that required buffer size declared by driver or MOF */ + if (!wblock->req_buf_size) { + dev_err(&wblock->dev.dev, + "Required buffer size not set\n"); + ret = -EINVAL; + goto probe_failure; + } + + count = get_order(wblock->req_buf_size); + wblock->handler_data = (void *)__get_free_pages(GFP_KERNEL, + count); + if (!wblock->handler_data) { + ret = -ENOMEM; + goto probe_failure; + } + + buf = kmalloc(strlen(wdriver->driver.name) + 4, GFP_KERNEL); + if (!buf) { + ret = -ENOMEM; + goto probe_string_failure; + } + sprintf(buf, "wmi/%s", wdriver->driver.name); + wblock->char_dev.minor = MISC_DYNAMIC_MINOR; + wblock->char_dev.name = buf; + wblock->char_dev.fops = &wmi_fops; + wblock->char_dev.mode = 0444; + ret = misc_register(&wblock->char_dev); + if (ret) { + dev_warn(dev, "failed to register char dev: %d", ret); + ret = -ENOMEM; + goto probe_misc_failure; + } + } + + return 0; + +probe_misc_failure: + kfree(buf); +probe_string_failure: + kfree(wblock->handler_data); +probe_failure: + if (ACPI_FAILURE(wmi_method_enable(wblock, 0))) + dev_warn(dev, "failed to disable device\n"); return ret; } @@ -791,6 +968,13 @@ static int wmi_dev_remove(struct device *dev) container_of(dev->driver, struct wmi_driver, driver); int ret = 0; + if (wdriver->filter_callback) { + misc_deregister(&wblock->char_dev); + kfree(wblock->char_dev.name); + free_pages((unsigned long)wblock->handler_data, + get_order(wblock->req_buf_size)); + } + if (wdriver->remove) ret = wdriver->remove(dev_to_wdev(dev)); @@ -847,6 +1031,7 @@ static int wmi_create_device(struct device *wmi_bus_dev, if (gblock->flags & ACPI_WMI_METHOD) { wblock->dev.dev.type = &wmi_type_method; + mutex_init(&wblock->char_mutex); goto out_init; } diff --git a/include/linux/wmi.h b/include/linux/wmi.h index ddee427e0721..4757cb5077e5 100644 --- a/include/linux/wmi.h +++ b/include/linux/wmi.h @@ -18,6 +18,7 @@ #include #include +#include struct wmi_device { struct device dev; @@ -36,6 +37,8 @@ extern acpi_status wmidev_evaluate_method(struct wmi_device *wdev, extern union acpi_object *wmidev_block_query(struct wmi_device *wdev, u8 instance); +extern int set_required_buffer_size(struct wmi_device *wdev, u64 length); + struct wmi_device_id { const char *guid_string; }; @@ -47,6 +50,8 @@ struct wmi_driver { int (*probe)(struct wmi_device *wdev); int (*remove)(struct wmi_device *wdev); void (*notify)(struct wmi_device *device, union acpi_object *data); + long (*filter_callback)(struct wmi_device *wdev, unsigned int cmd, + struct wmi_ioctl_buffer *arg); }; extern int __must_check __wmi_driver_register(struct wmi_driver *driver, diff --git a/include/uapi/linux/wmi.h b/include/uapi/linux/wmi.h new file mode 100644 index 000000000000..7e52350ac9b3 --- /dev/null +++ b/include/uapi/linux/wmi.h @@ -0,0 +1,26 @@ +/* + * User API methods for ACPI-WMI mapping driver + * + * Copyright (C) 2017 Dell, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef _UAPI_LINUX_WMI_H +#define _UAPI_LINUX_WMI_H + +#include + +/* WMI bus will filter all WMI vendor driver requests through this IOC */ +#define WMI_IOC 'W' + +/* All ioctl requests through WMI should declare their size followed by + * relevant data objects + */ +struct wmi_ioctl_buffer { + __u64 length; + __u8 data[]; +}; + +#endif -- cgit v1.2.3-71-gd317 From f2645fa317b8905b8934f06a0601d5b7fa66aba0 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Wed, 1 Nov 2017 14:25:36 -0500 Subject: platform/x86: dell-smbios-wmi: introduce userspace interface It's important for the driver to provide a R/W ioctl to ensure that two competing userspace processes don't race to provide or read each others data. This userspace character device will be used to perform SMBIOS calls from any applications. It provides an ioctl that will allow passing the WMI calling interface buffer between userspace and kernel space. This character device is intended to deprecate the dcdbas kernel module and the interface that it provides to userspace. To perform an SMBIOS IOCTL call using the character device userspace will perform a read() on the the character device. The WMI bus will provide a u64 variable containing the necessary size of the IOCTL buffer. The API for interacting with this interface is defined in documentation as well as the WMI uapi header provides the format of the structures. Not all userspace requests will be accepted. The dell-smbios filtering functionality will be used to prevent access to certain tokens and calls. All whitelisted commands and tokens are now shared out to userspace so applications don't need to define them in their own headers. Signed-off-by: Mario Limonciello Reviewed-by: Edward O'Callaghan Signed-off-by: Darren Hart (VMware) --- Documentation/ABI/testing/dell-smbios-wmi | 41 +++++++++++++++++++++++ drivers/platform/x86/dell-smbios-wmi.c | 54 ++++++++++++++++++++++++------- drivers/platform/x86/dell-smbios.h | 32 ++---------------- include/uapi/linux/wmi.h | 47 +++++++++++++++++++++++++++ 4 files changed, 133 insertions(+), 41 deletions(-) create mode 100644 Documentation/ABI/testing/dell-smbios-wmi (limited to 'include/uapi/linux') diff --git a/Documentation/ABI/testing/dell-smbios-wmi b/Documentation/ABI/testing/dell-smbios-wmi new file mode 100644 index 000000000000..fc919ce16008 --- /dev/null +++ b/Documentation/ABI/testing/dell-smbios-wmi @@ -0,0 +1,41 @@ +What: /dev/wmi/dell-smbios +Date: November 2017 +KernelVersion: 4.15 +Contact: "Mario Limonciello" +Description: + Perform SMBIOS calls on supported Dell machines. + through the Dell ACPI-WMI interface. + + IOCTL's and buffer formats are defined in: + + + 1) To perform an SMBIOS call from userspace, you'll need to + first determine the minimum size of the calling interface + buffer for your machine. + Platforms that contain larger buffers can return larger + objects from the system firmware. + Commonly this size is either 4k or 32k. + + To determine the size of the buffer read() a u64 dword from + the WMI character device /dev/wmi/dell-smbios. + + 2) After you've determined the minimum size of the calling + interface buffer, you can allocate a structure that represents + the structure documented above. + + 3) In the 'length' object store the size of the buffer you + determined above and allocated. + + 4) In this buffer object, prepare as necessary for the SMBIOS + call you're interested in. Typically SMBIOS buffers have + "class", "select", and "input" defined to values that coincide + with the data you are interested in. + Documenting class/select/input values is outside of the scope + of this documentation. Check with the libsmbios project for + further documentation on these values. + + 6) Run the call by using ioctl() as described in the header. + + 7) The output will be returned in the buffer object. + + 8) Be sure to free up your allocated object. diff --git a/drivers/platform/x86/dell-smbios-wmi.c b/drivers/platform/x86/dell-smbios-wmi.c index b31f457e58c3..35c13815b24c 100644 --- a/drivers/platform/x86/dell-smbios-wmi.c +++ b/drivers/platform/x86/dell-smbios-wmi.c @@ -30,17 +30,6 @@ struct misc_bios_flags_structure { #define DELL_WMI_SMBIOS_GUID "A80593CE-A997-11DA-B012-B622A1EF5492" -struct dell_wmi_extensions { - __u32 argattrib; - __u32 blength; - __u8 data[]; -} __packed; - -struct dell_wmi_smbios_buffer { - struct calling_interface_buffer std; - struct dell_wmi_extensions ext; -} __packed; - struct wmi_smbios_priv { struct dell_wmi_smbios_buffer *buf; struct list_head list; @@ -117,6 +106,42 @@ int dell_smbios_wmi_call(struct calling_interface_buffer *buffer) return ret; } +static long dell_smbios_wmi_filter(struct wmi_device *wdev, unsigned int cmd, + struct wmi_ioctl_buffer *arg) +{ + struct wmi_smbios_priv *priv; + int ret = 0; + + switch (cmd) { + case DELL_WMI_SMBIOS_CMD: + mutex_lock(&call_mutex); + priv = dev_get_drvdata(&wdev->dev); + if (!priv) { + ret = -ENODEV; + goto fail_smbios_cmd; + } + memcpy(priv->buf, arg, priv->req_buf_size); + if (dell_smbios_call_filter(&wdev->dev, &priv->buf->std)) { + dev_err(&wdev->dev, "Invalid call %d/%d:%8x\n", + priv->buf->std.cmd_class, + priv->buf->std.cmd_select, + priv->buf->std.input[0]); + ret = -EFAULT; + goto fail_smbios_cmd; + } + ret = run_smbios_call(priv->wdev); + if (ret) + goto fail_smbios_cmd; + memcpy(arg, priv->buf, priv->req_buf_size); +fail_smbios_cmd: + mutex_unlock(&call_mutex); + break; + default: + ret = -ENOIOCTLCMD; + } + return ret; +} + static int dell_smbios_wmi_probe(struct wmi_device *wdev) { struct wmi_smbios_priv *priv; @@ -135,6 +160,12 @@ static int dell_smbios_wmi_probe(struct wmi_device *wdev) if (!dell_wmi_get_size(&priv->req_buf_size)) return -EPROBE_DEFER; + /* add in the length object we will use internally with ioctl */ + priv->req_buf_size += sizeof(u64); + ret = set_required_buffer_size(wdev, priv->req_buf_size); + if (ret) + return ret; + count = get_order(priv->req_buf_size); priv->buf = (void *)__get_free_pages(GFP_KERNEL, count); if (!priv->buf) @@ -210,6 +241,7 @@ static struct wmi_driver dell_smbios_wmi_driver = { .probe = dell_smbios_wmi_probe, .remove = dell_smbios_wmi_remove, .id_table = dell_smbios_wmi_id_table, + .filter_callback = dell_smbios_wmi_filter, }; static int __init init_dell_smbios_wmi(void) diff --git a/drivers/platform/x86/dell-smbios.h b/drivers/platform/x86/dell-smbios.h index 91e8004d48ba..138d478d9adc 100644 --- a/drivers/platform/x86/dell-smbios.h +++ b/drivers/platform/x86/dell-smbios.h @@ -17,23 +17,11 @@ #define _DELL_SMBIOS_H_ #include +#include -/* Classes and selects used in kernel drivers */ -#define CLASS_TOKEN_READ 0 -#define CLASS_TOKEN_WRITE 1 -#define SELECT_TOKEN_STD 0 -#define SELECT_TOKEN_BAT 1 -#define SELECT_TOKEN_AC 2 +/* Classes and selects used only in kernel drivers */ #define CLASS_KBD_BACKLIGHT 4 #define SELECT_KBD_BACKLIGHT 11 -#define CLASS_FLASH_INTERFACE 7 -#define SELECT_FLASH_INTERFACE 3 -#define CLASS_ADMIN_PROP 10 -#define SELECT_ADMIN_PROP 3 -#define CLASS_INFO 17 -#define SELECT_RFKILL 11 -#define SELECT_APP_REGISTRATION 3 -#define SELECT_DOCK 22 /* Tokens used in kernel drivers, any of these * should be filtered from userspace access @@ -50,24 +38,8 @@ #define GLOBAL_MIC_MUTE_ENABLE 0x0364 #define GLOBAL_MIC_MUTE_DISABLE 0x0365 -/* tokens whitelisted to userspace use */ -#define CAPSULE_EN_TOKEN 0x0461 -#define CAPSULE_DIS_TOKEN 0x0462 -#define WSMT_EN_TOKEN 0x04EC -#define WSMT_DIS_TOKEN 0x04ED - struct notifier_block; -/* This structure will be modified by the firmware when we enter - * system management mode, hence the volatiles */ - -struct calling_interface_buffer { - u16 cmd_class; - u16 cmd_select; - volatile u32 input[4]; - volatile u32 output[4]; -} __packed; - struct calling_interface_token { u16 tokenID; u16 location; diff --git a/include/uapi/linux/wmi.h b/include/uapi/linux/wmi.h index 7e52350ac9b3..7a92e9e3d1c0 100644 --- a/include/uapi/linux/wmi.h +++ b/include/uapi/linux/wmi.h @@ -10,6 +10,7 @@ #ifndef _UAPI_LINUX_WMI_H #define _UAPI_LINUX_WMI_H +#include #include /* WMI bus will filter all WMI vendor driver requests through this IOC */ @@ -23,4 +24,50 @@ struct wmi_ioctl_buffer { __u8 data[]; }; +/* This structure may be modified by the firmware when we enter + * system management mode through SMM, hence the volatiles + */ +struct calling_interface_buffer { + __u16 cmd_class; + __u16 cmd_select; + volatile __u32 input[4]; + volatile __u32 output[4]; +} __packed; + +struct dell_wmi_extensions { + __u32 argattrib; + __u32 blength; + __u8 data[]; +} __packed; + +struct dell_wmi_smbios_buffer { + __u64 length; + struct calling_interface_buffer std; + struct dell_wmi_extensions ext; +} __packed; + +/* Whitelisted smbios class/select commands */ +#define CLASS_TOKEN_READ 0 +#define CLASS_TOKEN_WRITE 1 +#define SELECT_TOKEN_STD 0 +#define SELECT_TOKEN_BAT 1 +#define SELECT_TOKEN_AC 2 +#define CLASS_FLASH_INTERFACE 7 +#define SELECT_FLASH_INTERFACE 3 +#define CLASS_ADMIN_PROP 10 +#define SELECT_ADMIN_PROP 3 +#define CLASS_INFO 17 +#define SELECT_RFKILL 11 +#define SELECT_APP_REGISTRATION 3 +#define SELECT_DOCK 22 + +/* whitelisted tokens */ +#define CAPSULE_EN_TOKEN 0x0461 +#define CAPSULE_DIS_TOKEN 0x0462 +#define WSMT_EN_TOKEN 0x04EC +#define WSMT_DIS_TOKEN 0x04ED + +/* Dell SMBIOS calling IOCTL command used by dell-smbios-wmi */ +#define DELL_WMI_SMBIOS_CMD _IOWR(WMI_IOC, 0, struct dell_wmi_smbios_buffer) + #endif -- cgit v1.2.3-71-gd317 From ee20598194500e82c477cf13e52b58e569446ed0 Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Tue, 18 Jul 2017 15:42:15 -0500 Subject: net/dcb: Add dscp to priority selector type IEEE specification P802.1Qcd/D2.1 defines priority selector 5. This APP TLV selector defines DSCP to priority map. This patch defines such DSCP selector. Signed-off-by: Huy Nguyen Reviewed-by: Parav Pandit Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- include/uapi/linux/dcbnl.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/dcbnl.h b/include/uapi/linux/dcbnl.h index b6170a6af7c2..2c0c6453c3f4 100644 --- a/include/uapi/linux/dcbnl.h +++ b/include/uapi/linux/dcbnl.h @@ -206,6 +206,7 @@ struct cee_pfc { #define IEEE_8021QAZ_APP_SEL_STREAM 2 #define IEEE_8021QAZ_APP_SEL_DGRAM 3 #define IEEE_8021QAZ_APP_SEL_ANY 4 +#define IEEE_8021QAZ_APP_SEL_DSCP 5 /* This structure contains the IEEE 802.1Qaz APP managed object. This * object is also used for the CEE std as well. -- cgit v1.2.3-71-gd317 From 9354d452034273a50a4fd703bea31e5d6b1fc20b Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Thu, 2 Nov 2017 17:04:37 -0200 Subject: openvswitch: reliable interface indentification in port dumps This patch allows reliable identification of netdevice interfaces connected to openvswitch bridges. In particular, user space queries the netdev interfaces belonging to the ports for statistics, up/down state, etc. Datapath dump needs to provide enough information for the user space to be able to do that. Currently, only interface names are returned. This is not sufficient, as openvswitch allows its ports to be in different name spaces and the interface name is valid only in its name space. What is needed and generally used in other netlink APIs, is the pair ifindex+netnsid. The solution is addition of the ifindex+netnsid pair (or only ifindex if in the same name space) to vport get/dump operation. On request side, ideally the ifindex+netnsid pair could be used to get/set/del the corresponding vport. This is not implemented by this patch and can be added later if needed. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 2 ++ net/openvswitch/datapath.c | 47 +++++++++++++++++++++++++++++----------- net/openvswitch/datapath.h | 4 ++-- net/openvswitch/dp_notify.c | 4 ++-- 4 files changed, 40 insertions(+), 17 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index ffe397daad49..501e4c4e2a03 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -258,6 +258,8 @@ enum ovs_vport_attr { /* receiving upcalls */ OVS_VPORT_ATTR_STATS, /* struct ovs_vport_stats */ OVS_VPORT_ATTR_PAD, + OVS_VPORT_ATTR_IFINDEX, + OVS_VPORT_ATTR_NETNSID, __OVS_VPORT_ATTR_MAX }; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index c3aec6227c91..4d38ac044cee 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1848,7 +1848,8 @@ static struct genl_family dp_datapath_genl_family __ro_after_init = { /* Called with ovs_mutex or RCU read lock. */ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, - u32 portid, u32 seq, u32 flags, u8 cmd) + struct net *net, u32 portid, u32 seq, + u32 flags, u8 cmd) { struct ovs_header *ovs_header; struct ovs_vport_stats vport_stats; @@ -1864,9 +1865,17 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, if (nla_put_u32(skb, OVS_VPORT_ATTR_PORT_NO, vport->port_no) || nla_put_u32(skb, OVS_VPORT_ATTR_TYPE, vport->ops->type) || nla_put_string(skb, OVS_VPORT_ATTR_NAME, - ovs_vport_name(vport))) + ovs_vport_name(vport)) || + nla_put_u32(skb, OVS_VPORT_ATTR_IFINDEX, vport->dev->ifindex)) goto nla_put_failure; + if (!net_eq(net, dev_net(vport->dev))) { + int id = peernet2id_alloc(net, dev_net(vport->dev)); + + if (nla_put_s32(skb, OVS_VPORT_ATTR_NETNSID, id)) + goto nla_put_failure; + } + ovs_vport_get_stats(vport, &vport_stats); if (nla_put_64bit(skb, OVS_VPORT_ATTR_STATS, sizeof(struct ovs_vport_stats), &vport_stats, @@ -1896,8 +1905,8 @@ static struct sk_buff *ovs_vport_cmd_alloc_info(void) } /* Called with ovs_mutex, only via ovs_dp_notify_wq(). */ -struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid, - u32 seq, u8 cmd) +struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, struct net *net, + u32 portid, u32 seq, u8 cmd) { struct sk_buff *skb; int retval; @@ -1906,7 +1915,7 @@ struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid, if (!skb) return ERR_PTR(-ENOMEM); - retval = ovs_vport_cmd_fill_info(vport, skb, portid, seq, 0, cmd); + retval = ovs_vport_cmd_fill_info(vport, skb, net, portid, seq, 0, cmd); BUG_ON(retval < 0); return skb; @@ -1920,6 +1929,8 @@ static struct vport *lookup_vport(struct net *net, struct datapath *dp; struct vport *vport; + if (a[OVS_VPORT_ATTR_IFINDEX]) + return ERR_PTR(-EOPNOTSUPP); if (a[OVS_VPORT_ATTR_NAME]) { vport = ovs_vport_locate(net, nla_data(a[OVS_VPORT_ATTR_NAME])); if (!vport) @@ -1944,6 +1955,7 @@ static struct vport *lookup_vport(struct net *net, return vport; } else return ERR_PTR(-EINVAL); + } /* Called with ovs_mutex */ @@ -1983,6 +1995,8 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info) if (!a[OVS_VPORT_ATTR_NAME] || !a[OVS_VPORT_ATTR_TYPE] || !a[OVS_VPORT_ATTR_UPCALL_PID]) return -EINVAL; + if (a[OVS_VPORT_ATTR_IFINDEX]) + return -EOPNOTSUPP; port_no = a[OVS_VPORT_ATTR_PORT_NO] ? nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]) : 0; @@ -2032,8 +2046,9 @@ restart: goto exit_unlock_free; } - err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid, - info->snd_seq, 0, OVS_VPORT_CMD_NEW); + err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), + info->snd_portid, info->snd_seq, 0, + OVS_VPORT_CMD_NEW); if (netdev_get_fwd_headroom(vport->dev) > dp->max_headroom) update_headroom(dp); @@ -2090,8 +2105,9 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info) goto exit_unlock_free; } - err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid, - info->snd_seq, 0, OVS_VPORT_CMD_NEW); + err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), + info->snd_portid, info->snd_seq, 0, + OVS_VPORT_CMD_NEW); BUG_ON(err < 0); ovs_unlock(); @@ -2128,8 +2144,9 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info) goto exit_unlock_free; } - err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid, - info->snd_seq, 0, OVS_VPORT_CMD_DEL); + err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), + info->snd_portid, info->snd_seq, 0, + OVS_VPORT_CMD_DEL); BUG_ON(err < 0); /* the vport deletion may trigger dp headroom update */ @@ -2169,8 +2186,9 @@ static int ovs_vport_cmd_get(struct sk_buff *skb, struct genl_info *info) err = PTR_ERR(vport); if (IS_ERR(vport)) goto exit_unlock_free; - err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid, - info->snd_seq, 0, OVS_VPORT_CMD_NEW); + err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), + info->snd_portid, info->snd_seq, 0, + OVS_VPORT_CMD_NEW); BUG_ON(err < 0); rcu_read_unlock(); @@ -2202,6 +2220,7 @@ static int ovs_vport_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node) { if (j >= skip && ovs_vport_cmd_fill_info(vport, skb, + sock_net(skb->sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, @@ -2228,6 +2247,8 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = { [OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 }, [OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_U32 }, [OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED }, + [OVS_VPORT_ATTR_IFINDEX] = { .type = NLA_U32 }, + [OVS_VPORT_ATTR_NETNSID] = { .type = NLA_S32 }, }; static const struct genl_ops dp_vport_genl_ops[] = { diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 480600649d0b..4a104ef9e12c 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -200,8 +200,8 @@ int ovs_dp_upcall(struct datapath *, struct sk_buff *, uint32_t cutlen); const char *ovs_dp_name(const struct datapath *dp); -struct sk_buff *ovs_vport_cmd_build_info(struct vport *, u32 pid, u32 seq, - u8 cmd); +struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, struct net *net, + u32 portid, u32 seq, u8 cmd); int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb, const struct sw_flow_actions *, struct sw_flow_key *); diff --git a/net/openvswitch/dp_notify.c b/net/openvswitch/dp_notify.c index 653d073bae45..f3ee2f2825c0 100644 --- a/net/openvswitch/dp_notify.c +++ b/net/openvswitch/dp_notify.c @@ -30,8 +30,8 @@ static void dp_detach_port_notify(struct vport *vport) struct datapath *dp; dp = vport->dp; - notify = ovs_vport_cmd_build_info(vport, 0, 0, - OVS_VPORT_CMD_DEL); + notify = ovs_vport_cmd_build_info(vport, ovs_dp_get_net(dp), + 0, 0, OVS_VPORT_CMD_DEL); ovs_dp_detach_port(vport); if (IS_ERR(notify)) { genl_set_err(&dp_vport_genl_family, ovs_dp_get_net(dp), 0, -- cgit v1.2.3-71-gd317 From 79e1ad148c844f5c8b9d76b36b26e3886dca95ae Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Thu, 2 Nov 2017 17:04:38 -0200 Subject: rtnetlink: use netnsid to query interface Currently, when an application gets netnsid from the kernel (for example as the result of RTM_GETLINK call on one end of the veth pair), it's not much useful. There's no reliable way to get to the netns fd from the netnsid, nor does any kernel API accept netnsid. Extend the RTM_GETLINK call to also accept netnsid. It will operate on the netns with the given netnsid in such case. Of course, the calling process needs to have enough capabilities in the target name space; for now, require CAP_NET_ADMIN. This can be relaxed in the future. To signal to the calling process that the kernel understood the new IFLA_IF_NETNSID attribute in the query, it will include it in the response. This is needed to detect older kernels, as they will just ignore IFLA_IF_NETNSID and query in the current name space. This patch implemetns IFLA_IF_NETNSID only for get and dump. For set operations, this can be extended later. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/core/rtnetlink.c | 103 +++++++++++++++++++++++++++++++++++-------- 2 files changed, 86 insertions(+), 18 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index b3cf5639ac8f..19fc02660e0c 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -160,6 +160,7 @@ enum { IFLA_XDP, IFLA_EVENT, IFLA_NEW_NETNSID, + IFLA_IF_NETNSID, __IFLA_MAX }; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index de24d394c69e..8a8c51937edf 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -921,7 +921,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_EVENT */ + nla_total_size(4) /* IFLA_NEW_NETNSID */ + nla_total_size(1); /* IFLA_PROTO_DOWN */ - + + nla_total_size(4) /* IFLA_IF_NETNSID */ + + 0; } static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev) @@ -1370,13 +1371,14 @@ static noinline_for_stack int nla_put_ifalias(struct sk_buff *skb, } static int rtnl_fill_link_netnsid(struct sk_buff *skb, - const struct net_device *dev) + const struct net_device *dev, + struct net *src_net) { if (dev->rtnl_link_ops && dev->rtnl_link_ops->get_link_net) { struct net *link_net = dev->rtnl_link_ops->get_link_net(dev); if (!net_eq(dev_net(dev), link_net)) { - int id = peernet2id_alloc(dev_net(dev), link_net); + int id = peernet2id_alloc(src_net, link_net); if (nla_put_s32(skb, IFLA_LINK_NETNSID, id)) return -EMSGSIZE; @@ -1427,10 +1429,11 @@ static int rtnl_fill_link_af(struct sk_buff *skb, return 0; } -static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, +static int rtnl_fill_ifinfo(struct sk_buff *skb, + struct net_device *dev, struct net *src_net, int type, u32 pid, u32 seq, u32 change, unsigned int flags, u32 ext_filter_mask, - u32 event, int *new_nsid) + u32 event, int *new_nsid, int tgt_netnsid) { struct ifinfomsg *ifm; struct nlmsghdr *nlh; @@ -1448,6 +1451,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, ifm->ifi_flags = dev_get_flags(dev); ifm->ifi_change = change; + if (tgt_netnsid >= 0 && nla_put_s32(skb, IFLA_IF_NETNSID, tgt_netnsid)) + goto nla_put_failure; + if (nla_put_string(skb, IFLA_IFNAME, dev->name) || nla_put_u32(skb, IFLA_TXQLEN, dev->tx_queue_len) || nla_put_u8(skb, IFLA_OPERSTATE, @@ -1513,7 +1519,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, goto nla_put_failure; } - if (rtnl_fill_link_netnsid(skb, dev)) + if (rtnl_fill_link_netnsid(skb, dev, src_net)) goto nla_put_failure; if (new_nsid && @@ -1571,6 +1577,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_XDP] = { .type = NLA_NESTED }, [IFLA_EVENT] = { .type = NLA_U32 }, [IFLA_GROUP] = { .type = NLA_U32 }, + [IFLA_IF_NETNSID] = { .type = NLA_S32 }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { @@ -1674,9 +1681,28 @@ static bool link_dump_filtered(struct net_device *dev, return false; } +static struct net *get_target_net(struct sk_buff *skb, int netnsid) +{ + struct net *net; + + net = get_net_ns_by_id(sock_net(skb->sk), netnsid); + if (!net) + return ERR_PTR(-EINVAL); + + /* For now, the caller is required to have CAP_NET_ADMIN in + * the user namespace owning the target net ns. + */ + if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { + put_net(net); + return ERR_PTR(-EACCES); + } + return net; +} + static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); + struct net *tgt_net = net; int h, s_h; int idx = 0, s_idx; struct net_device *dev; @@ -1686,6 +1712,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) const struct rtnl_link_ops *kind_ops = NULL; unsigned int flags = NLM_F_MULTI; int master_idx = 0; + int netnsid = -1; int err; int hdrlen; @@ -1704,6 +1731,15 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX, ifla_policy, NULL) >= 0) { + if (tb[IFLA_IF_NETNSID]) { + netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]); + tgt_net = get_target_net(skb, netnsid); + if (IS_ERR(tgt_net)) { + tgt_net = net; + netnsid = -1; + } + } + if (tb[IFLA_EXT_MASK]) ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); @@ -1719,17 +1755,19 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; - head = &net->dev_index_head[h]; + head = &tgt_net->dev_index_head[h]; hlist_for_each_entry(dev, head, index_hlist) { if (link_dump_filtered(dev, master_idx, kind_ops)) goto cont; if (idx < s_idx) goto cont; - err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, + err = rtnl_fill_ifinfo(skb, dev, net, + RTM_NEWLINK, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, 0, flags, - ext_filter_mask, 0, NULL); + ext_filter_mask, 0, NULL, + netnsid); if (err < 0) { if (likely(skb->len)) @@ -1748,6 +1786,8 @@ out_err: cb->args[0] = h; cb->seq = net->dev_base_seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); + if (netnsid >= 0) + put_net(tgt_net); return err; } @@ -2360,6 +2400,9 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) goto errout; + if (tb[IFLA_IF_NETNSID]) + return -EOPNOTSUPP; + if (tb[IFLA_IFNAME]) nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); else @@ -2454,6 +2497,9 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) return err; + if (tb[IFLA_IF_NETNSID]) + return -EOPNOTSUPP; + if (tb[IFLA_IFNAME]) nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); @@ -2585,6 +2631,9 @@ replay: if (err < 0) return err; + if (tb[IFLA_IF_NETNSID]) + return -EOPNOTSUPP; + if (tb[IFLA_IFNAME]) nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); else @@ -2818,11 +2867,13 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); + struct net *tgt_net = net; struct ifinfomsg *ifm; char ifname[IFNAMSIZ]; struct nlattr *tb[IFLA_MAX+1]; struct net_device *dev = NULL; struct sk_buff *nskb; + int netnsid = -1; int err; u32 ext_filter_mask = 0; @@ -2830,35 +2881,50 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) return err; + if (tb[IFLA_IF_NETNSID]) { + netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]); + tgt_net = get_target_net(skb, netnsid); + if (IS_ERR(tgt_net)) + return PTR_ERR(tgt_net); + } + if (tb[IFLA_IFNAME]) nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); if (tb[IFLA_EXT_MASK]) ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); + err = -EINVAL; ifm = nlmsg_data(nlh); if (ifm->ifi_index > 0) - dev = __dev_get_by_index(net, ifm->ifi_index); + dev = __dev_get_by_index(tgt_net, ifm->ifi_index); else if (tb[IFLA_IFNAME]) - dev = __dev_get_by_name(net, ifname); + dev = __dev_get_by_name(tgt_net, ifname); else - return -EINVAL; + goto out; + err = -ENODEV; if (dev == NULL) - return -ENODEV; + goto out; + err = -ENOBUFS; nskb = nlmsg_new(if_nlmsg_size(dev, ext_filter_mask), GFP_KERNEL); if (nskb == NULL) - return -ENOBUFS; + goto out; - err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).portid, - nlh->nlmsg_seq, 0, 0, ext_filter_mask, 0, NULL); + err = rtnl_fill_ifinfo(nskb, dev, net, + RTM_NEWLINK, NETLINK_CB(skb).portid, + nlh->nlmsg_seq, 0, 0, ext_filter_mask, + 0, NULL, netnsid); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size */ WARN_ON(err == -EMSGSIZE); kfree_skb(nskb); } else err = rtnl_unicast(nskb, net, NETLINK_CB(skb).portid); +out: + if (netnsid >= 0) + put_net(tgt_net); return err; } @@ -2948,8 +3014,9 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, if (skb == NULL) goto errout; - err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0, event, - new_nsid); + err = rtnl_fill_ifinfo(skb, dev, dev_net(dev), + type, 0, 0, change, 0, 0, event, + new_nsid, -1); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); -- cgit v1.2.3-71-gd317 From ab3f0063c48c26c927851b6767824e35a716d878 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 3 Nov 2017 13:56:17 -0700 Subject: bpf: offload: add infrastructure for loading programs for a specific netdev The fact that we don't know which device the program is going to be used on is quite limiting in current eBPF infrastructure. We have to reverse or limit the changes which kernel makes to the loaded bytecode if we want it to be offloaded to a networking device. We also have to invent new APIs for debugging and troubleshooting support. Make it possible to load programs for a specific netdev. This helps us to bring the debug information closer to the core eBPF infrastructure (e.g. we will be able to reuse the verifer log in device JIT). It allows device JITs to perform translation on the original bytecode. __bpf_prog_get() when called to get a reference for an attachment point will now refuse to give it if program has a device assigned. Following patches will add a version of that function which passes the expected netdev in. @type argument in __bpf_prog_get() is renamed to attach_type to make it clearer that it's only set on attachment. All calls to ndo_bpf are protected by rtnl, only verifier callbacks are not. We need a wait queue to make sure netdev doesn't get destroyed while verifier is still running and calling its driver. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Reviewed-by: Quentin Monnet Signed-off-by: David S. Miller --- include/linux/bpf.h | 36 +++++++++ include/linux/bpf_verifier.h | 10 +++ include/linux/netdevice.h | 14 ++++ include/uapi/linux/bpf.h | 1 + kernel/bpf/Makefile | 1 + kernel/bpf/core.c | 10 ++- kernel/bpf/offload.c | 182 +++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 17 +++- kernel/bpf/verifier.c | 15 +++- 9 files changed, 278 insertions(+), 8 deletions(-) create mode 100644 kernel/bpf/offload.c (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 520aeebe0d93..e45d43f9ec92 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -15,6 +15,7 @@ #include #include #include +#include struct perf_event; struct bpf_prog; @@ -182,6 +183,16 @@ struct bpf_verifier_ops { struct bpf_prog *prog, u32 *target_size); }; +struct bpf_dev_offload { + struct bpf_prog *prog; + struct net_device *netdev; + void *dev_priv; + struct list_head offloads; + bool dev_state; + bool verifier_running; + wait_queue_head_t verifier_done; +}; + struct bpf_prog_aux { atomic_t refcnt; u32 used_map_cnt; @@ -199,6 +210,7 @@ struct bpf_prog_aux { #ifdef CONFIG_SECURITY void *security; #endif + struct bpf_dev_offload *offload; union { struct work_struct work; struct rcu_head rcu; @@ -317,6 +329,7 @@ extern const struct file_operations bpf_prog_fops; #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE +extern const struct bpf_prog_ops bpf_offload_prog_ops; extern const struct bpf_verifier_ops tc_cls_act_analyzer_ops; extern const struct bpf_verifier_ops xdp_analyzer_ops; @@ -491,6 +504,29 @@ static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, } #endif /* CONFIG_BPF_SYSCALL */ +int bpf_prog_offload_compile(struct bpf_prog *prog); +void bpf_prog_offload_destroy(struct bpf_prog *prog); + +#if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) +int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); + +static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux) +{ + return aux->offload; +} +#else +static inline int bpf_prog_offload_init(struct bpf_prog *prog, + union bpf_attr *attr) +{ + return -EOPNOTSUPP; +} + +static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux) +{ + return false; +} +#endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ + #if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL) struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key); int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 3b0976aaac75..e45011dbc02d 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -153,6 +153,7 @@ struct bpf_verifier_env { struct bpf_verifier_state *cur_state; /* current verifier state */ struct bpf_verifier_state_list **explored_states; /* search pruning optimization */ const struct bpf_ext_analyzer_ops *analyzer_ops; /* external analyzer ops */ + const struct bpf_ext_analyzer_ops *dev_ops; /* device analyzer ops */ void *analyzer_priv; /* pointer to external analyzer's private data */ struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */ u32 used_map_cnt; /* number of used maps */ @@ -169,6 +170,15 @@ static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env) return env->cur_state->regs; } +#if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) +int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env); +#else +int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env) +{ + return -EOPNOTSUPP; +} +#endif + int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops, void *priv); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9af9feaaeb64..fda527ccb263 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -797,8 +797,13 @@ enum bpf_netdev_command { * is equivalent to XDP_ATTACHED_DRV. */ XDP_QUERY_PROG, + /* BPF program for offload callbacks, invoked at program load time. */ + BPF_OFFLOAD_VERIFIER_PREP, + BPF_OFFLOAD_TRANSLATE, + BPF_OFFLOAD_DESTROY, }; +struct bpf_ext_analyzer_ops; struct netlink_ext_ack; struct netdev_bpf { @@ -815,6 +820,15 @@ struct netdev_bpf { u8 prog_attached; u32 prog_id; }; + /* BPF_OFFLOAD_VERIFIER_PREP */ + struct { + struct bpf_prog *prog; + const struct bpf_ext_analyzer_ops *ops; /* callee set */ + } verifier; + /* BPF_OFFLOAD_TRANSLATE, BPF_OFFLOAD_DESTROY */ + struct { + struct bpf_prog *prog; + } offload; }; }; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a9820677c2ff..80d191a93fb0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -260,6 +260,7 @@ union bpf_attr { __u32 kern_version; /* checked when prog_type=kprobe */ __u32 prog_flags; char prog_name[BPF_OBJ_NAME_LEN]; + __u32 prog_target_ifindex; /* ifindex of netdev to prep for */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 16e95c8e749e..e691da0b3bab 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -7,6 +7,7 @@ obj-$(CONFIG_BPF_SYSCALL) += disasm.o ifeq ($(CONFIG_NET),y) obj-$(CONFIG_BPF_SYSCALL) += devmap.o obj-$(CONFIG_BPF_SYSCALL) += cpumap.o +obj-$(CONFIG_BPF_SYSCALL) += offload.o ifeq ($(CONFIG_STREAM_PARSER),y) obj-$(CONFIG_BPF_SYSCALL) += sockmap.o endif diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 7fe448799d76..8a6c37762330 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1380,7 +1380,13 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) * valid program, which in this case would simply not * be JITed, but falls back to the interpreter. */ - fp = bpf_int_jit_compile(fp); + if (!bpf_prog_is_dev_bound(fp->aux)) { + fp = bpf_int_jit_compile(fp); + } else { + *err = bpf_prog_offload_compile(fp); + if (*err) + return fp; + } bpf_prog_lock_ro(fp); /* The tail call compatibility check can only be done at @@ -1549,6 +1555,8 @@ static void bpf_prog_free_deferred(struct work_struct *work) struct bpf_prog_aux *aux; aux = container_of(work, struct bpf_prog_aux, work); + if (bpf_prog_is_dev_bound(aux)) + bpf_prog_offload_destroy(aux->prog); bpf_jit_free(aux->prog); } diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c new file mode 100644 index 000000000000..5553e0e2f8b1 --- /dev/null +++ b/kernel/bpf/offload.c @@ -0,0 +1,182 @@ +#include +#include +#include +#include +#include +#include +#include + +/* protected by RTNL */ +static LIST_HEAD(bpf_prog_offload_devs); + +int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) +{ + struct net *net = current->nsproxy->net_ns; + struct bpf_dev_offload *offload; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (attr->prog_flags) + return -EINVAL; + + offload = kzalloc(sizeof(*offload), GFP_USER); + if (!offload) + return -ENOMEM; + + offload->prog = prog; + init_waitqueue_head(&offload->verifier_done); + + rtnl_lock(); + offload->netdev = __dev_get_by_index(net, attr->prog_target_ifindex); + if (!offload->netdev) { + rtnl_unlock(); + kfree(offload); + return -EINVAL; + } + + prog->aux->offload = offload; + list_add_tail(&offload->offloads, &bpf_prog_offload_devs); + rtnl_unlock(); + + return 0; +} + +static int __bpf_offload_ndo(struct bpf_prog *prog, enum bpf_netdev_command cmd, + struct netdev_bpf *data) +{ + struct net_device *netdev = prog->aux->offload->netdev; + + ASSERT_RTNL(); + + if (!netdev) + return -ENODEV; + if (!netdev->netdev_ops->ndo_bpf) + return -EOPNOTSUPP; + + data->command = cmd; + + return netdev->netdev_ops->ndo_bpf(netdev, data); +} + +int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env) +{ + struct netdev_bpf data = {}; + int err; + + data.verifier.prog = env->prog; + + rtnl_lock(); + err = __bpf_offload_ndo(env->prog, BPF_OFFLOAD_VERIFIER_PREP, &data); + if (err) + goto exit_unlock; + + env->dev_ops = data.verifier.ops; + + env->prog->aux->offload->dev_state = true; + env->prog->aux->offload->verifier_running = true; +exit_unlock: + rtnl_unlock(); + return err; +} + +static void __bpf_prog_offload_destroy(struct bpf_prog *prog) +{ + struct bpf_dev_offload *offload = prog->aux->offload; + struct netdev_bpf data = {}; + + data.offload.prog = prog; + + if (offload->verifier_running) + wait_event(offload->verifier_done, !offload->verifier_running); + + if (offload->dev_state) + WARN_ON(__bpf_offload_ndo(prog, BPF_OFFLOAD_DESTROY, &data)); + + offload->dev_state = false; + list_del_init(&offload->offloads); + offload->netdev = NULL; +} + +void bpf_prog_offload_destroy(struct bpf_prog *prog) +{ + struct bpf_dev_offload *offload = prog->aux->offload; + + offload->verifier_running = false; + wake_up(&offload->verifier_done); + + rtnl_lock(); + __bpf_prog_offload_destroy(prog); + rtnl_unlock(); + + kfree(offload); +} + +static int bpf_prog_offload_translate(struct bpf_prog *prog) +{ + struct bpf_dev_offload *offload = prog->aux->offload; + struct netdev_bpf data = {}; + int ret; + + data.offload.prog = prog; + + offload->verifier_running = false; + wake_up(&offload->verifier_done); + + rtnl_lock(); + ret = __bpf_offload_ndo(prog, BPF_OFFLOAD_TRANSLATE, &data); + rtnl_unlock(); + + return ret; +} + +static unsigned int bpf_prog_warn_on_exec(const void *ctx, + const struct bpf_insn *insn) +{ + WARN(1, "attempt to execute device eBPF program on the host!"); + return 0; +} + +int bpf_prog_offload_compile(struct bpf_prog *prog) +{ + prog->bpf_func = bpf_prog_warn_on_exec; + + return bpf_prog_offload_translate(prog); +} + +const struct bpf_prog_ops bpf_offload_prog_ops = { +}; + +static int bpf_offload_notification(struct notifier_block *notifier, + ulong event, void *ptr) +{ + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct bpf_dev_offload *offload, *tmp; + + ASSERT_RTNL(); + + switch (event) { + case NETDEV_UNREGISTER: + list_for_each_entry_safe(offload, tmp, &bpf_prog_offload_devs, + offloads) { + if (offload->netdev == netdev) + __bpf_prog_offload_destroy(offload->prog); + } + break; + default: + break; + } + return NOTIFY_OK; +} + +static struct notifier_block bpf_offload_notifier = { + .notifier_call = bpf_offload_notification, +}; + +static int __init bpf_offload_init(void) +{ + register_netdevice_notifier(&bpf_offload_notifier); + return 0; +} + +subsys_initcall(bpf_offload_init); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 323be2473c4b..1574b9f0f24e 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -824,7 +824,10 @@ static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) if (type >= ARRAY_SIZE(bpf_prog_types) || !bpf_prog_types[type]) return -EINVAL; - prog->aux->ops = bpf_prog_types[type]; + if (!bpf_prog_is_dev_bound(prog->aux)) + prog->aux->ops = bpf_prog_types[type]; + else + prog->aux->ops = &bpf_offload_prog_ops; prog->type = type; return 0; } @@ -1054,7 +1057,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) } EXPORT_SYMBOL_GPL(bpf_prog_inc_not_zero); -static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *type) +static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type) { struct fd f = fdget(ufd); struct bpf_prog *prog; @@ -1062,7 +1065,7 @@ static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *type) prog = ____bpf_prog_get(f); if (IS_ERR(prog)) return prog; - if (type && prog->type != *type) { + if (attach_type && (prog->type != *attach_type || prog->aux->offload)) { prog = ERR_PTR(-EINVAL); goto out; } @@ -1089,7 +1092,7 @@ struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) EXPORT_SYMBOL_GPL(bpf_prog_get_type); /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD prog_name +#define BPF_PROG_LOAD_LAST_FIELD prog_target_ifindex static int bpf_prog_load(union bpf_attr *attr) { @@ -1152,6 +1155,12 @@ static int bpf_prog_load(union bpf_attr *attr) atomic_set(&prog->aux->refcnt, 1); prog->gpl_compatible = is_gpl ? 1 : 0; + if (attr->prog_target_ifindex) { + err = bpf_prog_offload_init(prog, attr); + if (err) + goto free_prog; + } + /* find program type: socket_filter vs tracing_filter */ err = find_prog_type(type, prog); if (err < 0) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 04357ad5a812..51aabb32ad67 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3736,10 +3736,13 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) static int ext_analyzer_insn_hook(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx) { - if (!env->analyzer_ops || !env->analyzer_ops->insn_hook) - return 0; + if (env->analyzer_ops && env->analyzer_ops->insn_hook) + return env->analyzer_ops->insn_hook(env, insn_idx, + prev_insn_idx); + if (env->dev_ops && env->dev_ops->insn_hook) + return env->dev_ops->insn_hook(env, insn_idx, prev_insn_idx); - return env->analyzer_ops->insn_hook(env, insn_idx, prev_insn_idx); + return 0; } static int do_check(struct bpf_verifier_env *env) @@ -4516,6 +4519,12 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) env->strict_alignment = true; + if (env->prog->aux->offload) { + ret = bpf_prog_offload_verifier_prep(env); + if (ret) + goto err_unlock; + } + ret = replace_map_fd_with_map_ptr(env); if (ret < 0) goto skip_full_check; -- cgit v1.2.3-71-gd317 From bd601b6ada11fdfb9e277f24ad2eb54bc599156b Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 3 Nov 2017 13:56:18 -0700 Subject: bpf: report offload info to user space Extend struct bpf_prog_info to contain information about program being bound to a device. Since the netdev may get destroyed while program still exists we need a flag to indicate the program is loaded for a device, even if the device is gone. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Reviewed-by: Quentin Monnet Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 6 ++++++ kernel/bpf/offload.c | 12 ++++++++++++ kernel/bpf/syscall.c | 5 +++++ 4 files changed, 24 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e45d43f9ec92..98bacd0fa5cc 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -506,6 +506,7 @@ static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, int bpf_prog_offload_compile(struct bpf_prog *prog); void bpf_prog_offload_destroy(struct bpf_prog *prog); +u32 bpf_prog_offload_ifindex(struct bpf_prog *prog); #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 80d191a93fb0..4455dd195201 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -895,6 +895,10 @@ enum sk_action { #define BPF_TAG_SIZE 8 +enum bpf_prog_status { + BPF_PROG_STATUS_DEV_BOUND = (1 << 0), +}; + struct bpf_prog_info { __u32 type; __u32 id; @@ -908,6 +912,8 @@ struct bpf_prog_info { __u32 nr_map_ids; __aligned_u64 map_ids; char name[BPF_OBJ_NAME_LEN]; + __u32 ifindex; + __u32 status; } __attribute__((aligned(8))); struct bpf_map_info { diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 5553e0e2f8b1..2816feb38be1 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -144,6 +144,18 @@ int bpf_prog_offload_compile(struct bpf_prog *prog) return bpf_prog_offload_translate(prog); } +u32 bpf_prog_offload_ifindex(struct bpf_prog *prog) +{ + struct bpf_dev_offload *offload = prog->aux->offload; + u32 ifindex; + + rtnl_lock(); + ifindex = offload->netdev ? offload->netdev->ifindex : 0; + rtnl_unlock(); + + return ifindex; +} + const struct bpf_prog_ops bpf_offload_prog_ops = { }; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 1574b9f0f24e..3217c20ea91b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1592,6 +1592,11 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, return -EFAULT; } + if (bpf_prog_is_dev_bound(prog->aux)) { + info.status |= BPF_PROG_STATUS_DEV_BOUND; + info.ifindex = bpf_prog_offload_ifindex(prog); + } + done: if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) -- cgit v1.2.3-71-gd317 From ebc614f687369f9df99828572b1d85a7c2de3d92 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Sun, 5 Nov 2017 08:15:32 -0500 Subject: bpf, cgroup: implement eBPF-based device controller for cgroup v2 Cgroup v2 lacks the device controller, provided by cgroup v1. This patch adds a new eBPF program type, which in combination of previously added ability to attach multiple eBPF programs to a cgroup, will provide a similar functionality, but with some additional flexibility. This patch introduces a BPF_PROG_TYPE_CGROUP_DEVICE program type. A program takes major and minor device numbers, device type (block/character) and access type (mknod/read/write) as parameters and returns an integer which defines if the operation should be allowed or terminated with -EPERM. Signed-off-by: Roman Gushchin Acked-by: Alexei Starovoitov Acked-by: Tejun Heo Cc: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf-cgroup.h | 15 ++++++++++ include/linux/bpf_types.h | 3 ++ include/linux/device_cgroup.h | 8 ++++- include/uapi/linux/bpf.h | 15 ++++++++++ kernel/bpf/cgroup.c | 67 ++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 7 +++++ kernel/bpf/verifier.c | 1 + tools/include/uapi/linux/bpf.h | 15 ++++++++++ 8 files changed, 130 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 87a7db9feb38..a7f16e0f8d68 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -67,6 +67,9 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, struct bpf_sock_ops_kern *sock_ops, enum bpf_attach_type type); +int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, + short access, enum bpf_attach_type type); + /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */ #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ @@ -112,6 +115,17 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, } \ __ret; \ }) + +#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled) \ + __ret = __cgroup_bpf_check_dev_permission(type, major, minor, \ + access, \ + BPF_CGROUP_DEVICE); \ + \ + __ret; \ +}) #else struct cgroup_bpf {}; @@ -122,6 +136,7 @@ static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; }) #endif /* CONFIG_CGROUP_BPF */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 53c5b9ad7220..978c1d9c9383 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -19,6 +19,9 @@ 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) #endif +#ifdef CONFIG_CGROUP_BPF +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev) +#endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops) diff --git a/include/linux/device_cgroup.h b/include/linux/device_cgroup.h index 2d93d7ecd479..8557efe096dc 100644 --- a/include/linux/device_cgroup.h +++ b/include/linux/device_cgroup.h @@ -1,5 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include +#include #define DEVCG_ACC_MKNOD 1 #define DEVCG_ACC_READ 2 @@ -19,10 +20,15 @@ static inline int __devcgroup_check_permission(short type, u32 major, u32 minor, { return 0; } #endif -#ifdef CONFIG_CGROUP_DEVICE +#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); } diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4455dd195201..e880ae6434ee 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -132,6 +132,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_LWT_XMIT, BPF_PROG_TYPE_SOCK_OPS, BPF_PROG_TYPE_SK_SKB, + BPF_PROG_TYPE_CGROUP_DEVICE, }; enum bpf_attach_type { @@ -141,6 +142,7 @@ enum bpf_attach_type { BPF_CGROUP_SOCK_OPS, BPF_SK_SKB_STREAM_PARSER, BPF_SK_SKB_STREAM_VERDICT, + BPF_CGROUP_DEVICE, __MAX_BPF_ATTACH_TYPE }; @@ -991,4 +993,17 @@ struct bpf_perf_event_value { __u64 running; }; +#define BPF_DEVCG_ACC_MKNOD (1ULL << 0) +#define BPF_DEVCG_ACC_READ (1ULL << 1) +#define BPF_DEVCG_ACC_WRITE (1ULL << 2) + +#define BPF_DEVCG_DEV_BLOCK (1ULL << 0) +#define BPF_DEVCG_DEV_CHAR (1ULL << 1) + +struct bpf_cgroup_dev_ctx { + __u32 access_type; /* (access << 16) | type */ + __u32 major; + __u32 minor; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 3db5a17fcfe8..b789ab78d28f 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -522,3 +522,70 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, return ret == 1 ? 0 : -EPERM; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops); + +int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, + short access, enum bpf_attach_type type) +{ + struct cgroup *cgrp; + struct bpf_cgroup_dev_ctx ctx = { + .access_type = (access << 16) | dev_type, + .major = major, + .minor = minor, + }; + int allow = 1; + + rcu_read_lock(); + cgrp = task_dfl_cgroup(current); + allow = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, + BPF_PROG_RUN); + rcu_read_unlock(); + + return !allow; +} +EXPORT_SYMBOL(__cgroup_bpf_check_dev_permission); + +static const struct bpf_func_proto * +cgroup_dev_func_proto(enum bpf_func_id func_id) +{ + switch (func_id) { + case BPF_FUNC_map_lookup_elem: + return &bpf_map_lookup_elem_proto; + case BPF_FUNC_map_update_elem: + return &bpf_map_update_elem_proto; + case BPF_FUNC_map_delete_elem: + return &bpf_map_delete_elem_proto; + case BPF_FUNC_get_current_uid_gid: + return &bpf_get_current_uid_gid_proto; + case BPF_FUNC_trace_printk: + if (capable(CAP_SYS_ADMIN)) + return bpf_get_trace_printk_proto(); + default: + return NULL; + } +} + +static bool cgroup_dev_is_valid_access(int off, int size, + enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + if (type == BPF_WRITE) + return false; + + if (off < 0 || off + size > sizeof(struct bpf_cgroup_dev_ctx)) + return false; + /* The verifier guarantees that size > 0. */ + if (off % size != 0) + return false; + if (size != sizeof(__u32)) + return false; + + return true; +} + +const struct bpf_prog_ops cg_dev_prog_ops = { +}; + +const struct bpf_verifier_ops cg_dev_verifier_ops = { + .get_func_proto = cgroup_dev_func_proto, + .is_valid_access = cgroup_dev_is_valid_access, +}; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 416d70cdfc76..09badc37e864 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1326,6 +1326,9 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_CGROUP_SOCK_OPS: ptype = BPF_PROG_TYPE_SOCK_OPS; break; + case BPF_CGROUP_DEVICE: + ptype = BPF_PROG_TYPE_CGROUP_DEVICE; + break; case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: return sockmap_get_from_fd(attr, true); @@ -1378,6 +1381,9 @@ static int bpf_prog_detach(const union bpf_attr *attr) case BPF_CGROUP_SOCK_OPS: ptype = BPF_PROG_TYPE_SOCK_OPS; break; + case BPF_CGROUP_DEVICE: + ptype = BPF_PROG_TYPE_CGROUP_DEVICE; + break; case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: return sockmap_get_from_fd(attr, false); @@ -1420,6 +1426,7 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_CGROUP_INET_EGRESS: case BPF_CGROUP_INET_SOCK_CREATE: case BPF_CGROUP_SOCK_OPS: + case BPF_CGROUP_DEVICE: break; default: return -EINVAL; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index add845fe788a..4a942e2e753d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3124,6 +3124,7 @@ static int check_return_code(struct bpf_verifier_env *env) case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_SOCK_OPS: + case BPF_PROG_TYPE_CGROUP_DEVICE: break; default: return 0; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e92f62cf933a..b280f37cd057 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -131,6 +131,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_LWT_XMIT, BPF_PROG_TYPE_SOCK_OPS, BPF_PROG_TYPE_SK_SKB, + BPF_PROG_TYPE_CGROUP_DEVICE, }; enum bpf_attach_type { @@ -140,6 +141,7 @@ enum bpf_attach_type { BPF_CGROUP_SOCK_OPS, BPF_SK_SKB_STREAM_PARSER, BPF_SK_SKB_STREAM_VERDICT, + BPF_CGROUP_DEVICE, __MAX_BPF_ATTACH_TYPE }; @@ -990,4 +992,17 @@ struct bpf_perf_event_value { __u64 running; }; +#define BPF_DEVCG_ACC_MKNOD (1ULL << 0) +#define BPF_DEVCG_ACC_READ (1ULL << 1) +#define BPF_DEVCG_ACC_WRITE (1ULL << 2) + +#define BPF_DEVCG_DEV_BLOCK (1ULL << 0) +#define BPF_DEVCG_DEV_CHAR (1ULL << 1) + +struct bpf_cgroup_dev_ctx { + __u32 access_type; /* (access << 16) | type */ + __u32 major; + __u32 minor; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ -- cgit v1.2.3-71-gd317 From 6f27f4f97ee8cbec99b429b653333f4e781a47a1 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Thu, 2 Nov 2017 10:57:38 +0200 Subject: usb: core: add Status Type definitions USB 3.1 added a PTM_STATUS type. Let's add a define for it and following patches will let usb_get_status() accept the new argument. Signed-off-by: Felipe Balbi Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/message.c | 4 ++-- include/uapi/linux/usb/ch9.h | 4 ++++ 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c index 5e8379b42f47..f35cbfa2b87b 100644 --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -946,8 +946,8 @@ int usb_get_status(struct usb_device *dev, int type, int target, void *data) return -ENOMEM; ret = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), - USB_REQ_GET_STATUS, USB_DIR_IN | type, 0, target, status, - sizeof(*status), USB_CTRL_GET_TIMEOUT); + USB_REQ_GET_STATUS, USB_DIR_IN | type, USB_STATUS_TYPE_STANDARD, + target, status, sizeof(*status), USB_CTRL_GET_TIMEOUT); if (ret == 2) { *(u16 *) data = le16_to_cpu(*status); diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h index 2a5d63040a0b..b2167e89ae6e 100644 --- a/include/uapi/linux/usb/ch9.h +++ b/include/uapi/linux/usb/ch9.h @@ -143,6 +143,10 @@ #define TEST_PACKET 4 #define TEST_FORCE_EN 5 +/* Status Type */ +#define USB_STATUS_TYPE_STANDARD 0 +#define USB_STATUS_TYPE_PTM 1 + /* * New Feature Selectors as added by USB 3.0 * See USB 3.0 spec Table 9-7 -- cgit v1.2.3-71-gd317 From 84287bb3285634b60c55c00a1d5ed843b44fde92 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Sun, 5 Nov 2017 15:58:23 -0800 Subject: ila: add checksum neutral map auto Add checksum neutral auto that performs checksum neutral mapping without using the C-bit. This is enabled by configuration of a mapping. The checksum neutral function has been split into ila_csum_do_neutral_fmt and ila_csum_do_neutral_nofmt. The former handles the C-bit and includes it in the adjustment value. The latter just sets the adjustment value on the locator diff only. Added configuration for checksum neutral map aut in ila_lwt and ila_xlat. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/uapi/linux/ila.h | 1 + net/ipv6/ila/ila_common.c | 65 ++++++++++++++++++++++++++++------------------- net/ipv6/ila/ila_lwt.c | 29 +++++++++++---------- net/ipv6/ila/ila_xlat.c | 10 +++++--- 4 files changed, 61 insertions(+), 44 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ila.h b/include/uapi/linux/ila.h index f54853288f99..0744881dcef3 100644 --- a/include/uapi/linux/ila.h +++ b/include/uapi/linux/ila.h @@ -41,6 +41,7 @@ enum { ILA_CSUM_ADJUST_TRANSPORT, ILA_CSUM_NEUTRAL_MAP, ILA_CSUM_NO_ACTION, + ILA_CSUM_NEUTRAL_MAP_AUTO, }; #endif /* _UAPI_LINUX_ILA_H */ diff --git a/net/ipv6/ila/ila_common.c b/net/ipv6/ila/ila_common.c index f1d9248d8b86..8c88ecf29b93 100644 --- a/net/ipv6/ila/ila_common.c +++ b/net/ipv6/ila/ila_common.c @@ -37,8 +37,8 @@ static __wsum get_csum_diff(struct ipv6hdr *ip6h, struct ila_params *p) return get_csum_diff_iaddr(ila_a2i(&ip6h->daddr), p); } -static void ila_csum_do_neutral(struct ila_addr *iaddr, - struct ila_params *p) +static void ila_csum_do_neutral_fmt(struct ila_addr *iaddr, + struct ila_params *p) { __sum16 *adjust = (__force __sum16 *)&iaddr->ident.v16[3]; __wsum diff, fval; @@ -60,13 +60,23 @@ static void ila_csum_do_neutral(struct ila_addr *iaddr, iaddr->ident.csum_neutral ^= 1; } -static void ila_csum_adjust_transport(struct sk_buff *skb, +static void ila_csum_do_neutral_nofmt(struct ila_addr *iaddr, struct ila_params *p) { + __sum16 *adjust = (__force __sum16 *)&iaddr->ident.v16[3]; __wsum diff; - struct ipv6hdr *ip6h = ipv6_hdr(skb); - struct ila_addr *iaddr = ila_a2i(&ip6h->daddr); + + diff = get_csum_diff_iaddr(iaddr, p); + + *adjust = ~csum_fold(csum_add(diff, csum_unfold(*adjust))); +} + +static void ila_csum_adjust_transport(struct sk_buff *skb, + struct ila_params *p) +{ size_t nhoff = sizeof(struct ipv6hdr); + struct ipv6hdr *ip6h = ipv6_hdr(skb); + __wsum diff; switch (ip6h->nexthdr) { case NEXTHDR_TCP: @@ -105,36 +115,39 @@ static void ila_csum_adjust_transport(struct sk_buff *skb, } break; } - - /* Now change destination address */ - iaddr->loc = p->locator; } void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p, - bool set_csum_neutral) + bool sir2ila) { struct ipv6hdr *ip6h = ipv6_hdr(skb); struct ila_addr *iaddr = ila_a2i(&ip6h->daddr); - /* First deal with the transport checksum */ - if (ila_csum_neutral_set(iaddr->ident)) { - /* C-bit is set in the locator indicating that this - * is a locator being translated to a SIR address. - * Perform (receiver) checksum-neutral translation. - */ - if (!set_csum_neutral) - ila_csum_do_neutral(iaddr, p); - } else { - switch (p->csum_mode) { - case ILA_CSUM_ADJUST_TRANSPORT: - ila_csum_adjust_transport(skb, p); - break; - case ILA_CSUM_NEUTRAL_MAP: - ila_csum_do_neutral(iaddr, p); - break; - case ILA_CSUM_NO_ACTION: + switch (p->csum_mode) { + case ILA_CSUM_ADJUST_TRANSPORT: + ila_csum_adjust_transport(skb, p); + break; + case ILA_CSUM_NEUTRAL_MAP: + if (sir2ila) { + if (WARN_ON(ila_csum_neutral_set(iaddr->ident))) { + /* Checksum flag should never be + * set in a formatted SIR address. + */ + break; + } + } else if (!ila_csum_neutral_set(iaddr->ident)) { + /* ILA to SIR translation and C-bit isn't + * set so we're good. + */ break; } + ila_csum_do_neutral_fmt(iaddr, p); + break; + case ILA_CSUM_NEUTRAL_MAP_AUTO: + ila_csum_do_neutral_nofmt(iaddr, p); + break; + case ILA_CSUM_NO_ACTION: + break; } /* Now change destination address */ diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c index 696281b4bca2..104af07d83a6 100644 --- a/net/ipv6/ila/ila_lwt.c +++ b/net/ipv6/ila/ila_lwt.c @@ -127,6 +127,7 @@ static int ila_build_state(struct nlattr *nla, struct lwtunnel_state *newts; const struct fib6_config *cfg6 = cfg; struct ila_addr *iaddr; + u8 csum_mode = ILA_CSUM_NO_ACTION; int ret; if (family != AF_INET6) @@ -139,15 +140,6 @@ static int ila_build_state(struct nlattr *nla, return -EINVAL; } - iaddr = (struct ila_addr *)&cfg6->fc_dst; - - if (!ila_addr_is_ila(iaddr) || ila_csum_neutral_set(iaddr->ident)) { - /* Don't allow translation for a non-ILA address or checksum - * neutral flag to be set. - */ - return -EINVAL; - } - ret = nla_parse_nested(tb, ILA_ATTR_MAX, nla, ila_nl_policy, extack); if (ret < 0) return ret; @@ -155,6 +147,19 @@ static int ila_build_state(struct nlattr *nla, if (!tb[ILA_ATTR_LOCATOR]) return -EINVAL; + iaddr = (struct ila_addr *)&cfg6->fc_dst; + + if (tb[ILA_ATTR_CSUM_MODE]) + csum_mode = nla_get_u8(tb[ILA_ATTR_CSUM_MODE]); + + if (csum_mode == ILA_CSUM_NEUTRAL_MAP && + ila_csum_neutral_set(iaddr->ident)) { + /* Don't allow translation if checksum neutral bit is + * configured and it's set in the SIR address. + */ + return -EINVAL; + } + newts = lwtunnel_state_alloc(sizeof(*ilwt)); if (!newts) return -ENOMEM; @@ -168,17 +173,13 @@ static int ila_build_state(struct nlattr *nla, p = ila_params_lwtunnel(newts); + p->csum_mode = csum_mode; p->locator.v64 = (__force __be64)nla_get_u64(tb[ILA_ATTR_LOCATOR]); /* Precompute checksum difference for translation since we * know both the old locator and the new one. */ p->locator_match = iaddr->loc; - p->csum_diff = compute_csum_diff8( - (__be32 *)&p->locator_match, (__be32 *)&p->locator); - - if (tb[ILA_ATTR_CSUM_MODE]) - p->csum_mode = nla_get_u8(tb[ILA_ATTR_CSUM_MODE]); ila_init_saved_csum(p); diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index 3123b9de91b5..213259629e66 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -138,6 +138,8 @@ static int parse_nl_config(struct genl_info *info, if (info->attrs[ILA_ATTR_CSUM_MODE]) xp->ip.csum_mode = nla_get_u8(info->attrs[ILA_ATTR_CSUM_MODE]); + else + xp->ip.csum_mode = ILA_CSUM_NO_ACTION; if (info->attrs[ILA_ATTR_IFINDEX]) xp->ifindex = nla_get_s32(info->attrs[ILA_ATTR_IFINDEX]); @@ -198,7 +200,7 @@ static void ila_free_cb(void *ptr, void *arg) } } -static int ila_xlat_addr(struct sk_buff *skb, bool set_csum_neutral); +static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila); static unsigned int ila_nf_input(void *priv, @@ -396,7 +398,7 @@ static int ila_fill_info(struct ila_map *ila, struct sk_buff *msg) (__force u64)ila->xp.ip.locator_match.v64, ILA_ATTR_PAD) || nla_put_s32(msg, ILA_ATTR_IFINDEX, ila->xp.ifindex) || - nla_put_u32(msg, ILA_ATTR_CSUM_MODE, ila->xp.ip.csum_mode)) + nla_put_u8(msg, ILA_ATTR_CSUM_MODE, ila->xp.ip.csum_mode)) return -1; return 0; @@ -607,7 +609,7 @@ static struct pernet_operations ila_net_ops = { .size = sizeof(struct ila_net), }; -static int ila_xlat_addr(struct sk_buff *skb, bool set_csum_neutral) +static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila) { struct ila_map *ila; struct ipv6hdr *ip6h = ipv6_hdr(skb); @@ -626,7 +628,7 @@ static int ila_xlat_addr(struct sk_buff *skb, bool set_csum_neutral) ila = ila_lookup_wildcards(iaddr, skb->dev->ifindex, ilan); if (ila) - ila_update_ipv6_locator(skb, &ila->xp.ip, set_csum_neutral); + ila_update_ipv6_locator(skb, &ila->xp.ip, sir2ila); rcu_read_unlock(); -- cgit v1.2.3-71-gd317 From 70d5aef48a421a68bd9d1bf8f8267af406681580 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Sun, 5 Nov 2017 15:58:24 -0800 Subject: ila: allow configuration of identifier type Allow identifier to be explicitly configured for a mapping. This can either be one of the identifier types specified in the ILA draft or a value of ILA_ATYPE_USE_FORMAT which means the identifier type is inferred from the identifier type field. If a value other than ILA_ATYPE_USE_FORMAT is set for a mapping then it is assumed that the identifier type field is not present in an identifier. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/uapi/linux/ila.h | 13 ++++++++++++ net/ipv6/ila/ila.h | 12 +----------- net/ipv6/ila/ila_lwt.c | 51 +++++++++++++++++++++++++++++++++++++++++------- net/ipv6/ila/ila_xlat.c | 18 ++++++++++++----- 4 files changed, 71 insertions(+), 23 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ila.h b/include/uapi/linux/ila.h index 0744881dcef3..8353c78a7781 100644 --- a/include/uapi/linux/ila.h +++ b/include/uapi/linux/ila.h @@ -17,6 +17,7 @@ enum { ILA_ATTR_DIR, /* u32 */ ILA_ATTR_PAD, ILA_ATTR_CSUM_MODE, /* u8 */ + ILA_ATTR_IDENT_TYPE, /* u8 */ __ILA_ATTR_MAX, }; @@ -44,4 +45,16 @@ enum { ILA_CSUM_NEUTRAL_MAP_AUTO, }; +enum { + ILA_ATYPE_IID = 0, + ILA_ATYPE_LUID, + ILA_ATYPE_VIRT_V4, + ILA_ATYPE_VIRT_UNI_V6, + ILA_ATYPE_VIRT_MULTI_V6, + ILA_ATYPE_NONLOCAL_ADDR, + ILA_ATYPE_RSVD_1, + ILA_ATYPE_RSVD_2, + + ILA_ATYPE_USE_FORMAT = 32, /* Get type from type field in identifier */ +}; #endif /* _UAPI_LINUX_ILA_H */ diff --git a/net/ipv6/ila/ila.h b/net/ipv6/ila/ila.h index e0170f62bc39..3c7a11b62334 100644 --- a/net/ipv6/ila/ila.h +++ b/net/ipv6/ila/ila.h @@ -55,17 +55,6 @@ struct ila_identifier { }; }; -enum { - ILA_ATYPE_IID = 0, - ILA_ATYPE_LUID, - ILA_ATYPE_VIRT_V4, - ILA_ATYPE_VIRT_UNI_V6, - ILA_ATYPE_VIRT_MULTI_V6, - ILA_ATYPE_RSVD_1, - ILA_ATYPE_RSVD_2, - ILA_ATYPE_RSVD_3, -}; - #define CSUM_NEUTRAL_FLAG htonl(0x10000000) struct ila_addr { @@ -93,6 +82,7 @@ struct ila_params { struct ila_locator locator_match; __wsum csum_diff; u8 csum_mode; + u8 ident_type; }; static inline __wsum compute_csum_diff8(const __be32 *from, const __be32 *to) diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c index 104af07d83a6..4b97d573f223 100644 --- a/net/ipv6/ila/ila_lwt.c +++ b/net/ipv6/ila/ila_lwt.c @@ -114,6 +114,7 @@ drop: static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = { [ILA_ATTR_LOCATOR] = { .type = NLA_U64, }, [ILA_ATTR_CSUM_MODE] = { .type = NLA_U8, }, + [ILA_ATTR_IDENT_TYPE] = { .type = NLA_U8, }, }; static int ila_build_state(struct nlattr *nla, @@ -127,19 +128,14 @@ static int ila_build_state(struct nlattr *nla, struct lwtunnel_state *newts; const struct fib6_config *cfg6 = cfg; struct ila_addr *iaddr; + u8 ident_type = ILA_ATYPE_USE_FORMAT; u8 csum_mode = ILA_CSUM_NO_ACTION; + u8 eff_ident_type; int ret; if (family != AF_INET6) return -EINVAL; - if (cfg6->fc_dst_len < 8 * sizeof(struct ila_locator) + 3) { - /* Need to have full locator and at least type field - * included in destination - */ - return -EINVAL; - } - ret = nla_parse_nested(tb, ILA_ATTR_MAX, nla, ila_nl_policy, extack); if (ret < 0) return ret; @@ -149,6 +145,41 @@ static int ila_build_state(struct nlattr *nla, iaddr = (struct ila_addr *)&cfg6->fc_dst; + if (tb[ILA_ATTR_IDENT_TYPE]) + ident_type = nla_get_u8(tb[ILA_ATTR_IDENT_TYPE]); + + if (ident_type == ILA_ATYPE_USE_FORMAT) { + /* Infer identifier type from type field in formatted + * identifier. + */ + + if (cfg6->fc_dst_len < 8 * sizeof(struct ila_locator) + 3) { + /* Need to have full locator and at least type field + * included in destination + */ + return -EINVAL; + } + + eff_ident_type = iaddr->ident.type; + } else { + eff_ident_type = ident_type; + } + + switch (eff_ident_type) { + case ILA_ATYPE_IID: + /* Don't allow ILA for IID type */ + return -EINVAL; + case ILA_ATYPE_LUID: + break; + case ILA_ATYPE_VIRT_V4: + case ILA_ATYPE_VIRT_UNI_V6: + case ILA_ATYPE_VIRT_MULTI_V6: + case ILA_ATYPE_NONLOCAL_ADDR: + /* These ILA formats are not supported yet. */ + default: + return -EINVAL; + } + if (tb[ILA_ATTR_CSUM_MODE]) csum_mode = nla_get_u8(tb[ILA_ATTR_CSUM_MODE]); @@ -174,6 +205,7 @@ static int ila_build_state(struct nlattr *nla, p = ila_params_lwtunnel(newts); p->csum_mode = csum_mode; + p->ident_type = ident_type; p->locator.v64 = (__force __be64)nla_get_u64(tb[ILA_ATTR_LOCATOR]); /* Precompute checksum difference for translation since we @@ -208,9 +240,13 @@ static int ila_fill_encap_info(struct sk_buff *skb, if (nla_put_u64_64bit(skb, ILA_ATTR_LOCATOR, (__force u64)p->locator.v64, ILA_ATTR_PAD)) goto nla_put_failure; + if (nla_put_u8(skb, ILA_ATTR_CSUM_MODE, (__force u8)p->csum_mode)) goto nla_put_failure; + if (nla_put_u8(skb, ILA_ATTR_IDENT_TYPE, (__force u8)p->ident_type)) + goto nla_put_failure; + return 0; nla_put_failure: @@ -221,6 +257,7 @@ static int ila_encap_nlsize(struct lwtunnel_state *lwtstate) { return nla_total_size_64bit(sizeof(u64)) + /* ILA_ATTR_LOCATOR */ nla_total_size(sizeof(u8)) + /* ILA_ATTR_CSUM_MODE */ + nla_total_size(sizeof(u8)) + /* ILA_ATTR_IDENT_TYPE */ 0; } diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index 213259629e66..6eb5e68f112a 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -121,6 +121,7 @@ static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = { [ILA_ATTR_LOCATOR_MATCH] = { .type = NLA_U64, }, [ILA_ATTR_IFINDEX] = { .type = NLA_U32, }, [ILA_ATTR_CSUM_MODE] = { .type = NLA_U8, }, + [ILA_ATTR_IDENT_TYPE] = { .type = NLA_U8, }, }; static int parse_nl_config(struct genl_info *info, @@ -141,6 +142,12 @@ static int parse_nl_config(struct genl_info *info, else xp->ip.csum_mode = ILA_CSUM_NO_ACTION; + if (info->attrs[ILA_ATTR_IDENT_TYPE]) + xp->ip.ident_type = nla_get_u8( + info->attrs[ILA_ATTR_IDENT_TYPE]); + else + xp->ip.ident_type = ILA_ATYPE_USE_FORMAT; + if (info->attrs[ILA_ATTR_IFINDEX]) xp->ifindex = nla_get_s32(info->attrs[ILA_ATTR_IFINDEX]); @@ -398,7 +405,8 @@ static int ila_fill_info(struct ila_map *ila, struct sk_buff *msg) (__force u64)ila->xp.ip.locator_match.v64, ILA_ATTR_PAD) || nla_put_s32(msg, ILA_ATTR_IFINDEX, ila->xp.ifindex) || - nla_put_u8(msg, ILA_ATTR_CSUM_MODE, ila->xp.ip.csum_mode)) + nla_put_u8(msg, ILA_ATTR_CSUM_MODE, ila->xp.ip.csum_mode) || + nla_put_u8(msg, ILA_ATTR_IDENT_TYPE, ila->xp.ip.ident_type)) return -1; return 0; @@ -619,10 +627,10 @@ static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila) /* Assumes skb contains a valid IPv6 header that is pulled */ - if (!ila_addr_is_ila(iaddr)) { - /* Type indicates this is not an ILA address */ - return 0; - } + /* No check here that ILA type in the mapping matches what is in the + * address. We assume that whatever sender gaves us can be translated. + * The checksum mode however is relevant. + */ rcu_read_lock(); -- cgit v1.2.3-71-gd317 From fddb231ebe647749782a9ebf11106a81f7168ba7 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Sun, 5 Nov 2017 15:58:25 -0800 Subject: ila: Add a hook type for LWT routes In LWT tunnels both an input and output route method is defined. If both of these are executed in the same path then double translation happens and the effect is not correct. This patch adds a new attribute that indicates the hook type. Two values are defined for route output and route output. ILA translation is only done for the one that is set. The default is to enable ILA on route output. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/uapi/linux/ila.h | 7 +++++++ net/ipv6/ila/ila_lwt.c | 39 ++++++++++++++++++++++++++++++++++++--- 2 files changed, 43 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ila.h b/include/uapi/linux/ila.h index 8353c78a7781..483b77af4eb8 100644 --- a/include/uapi/linux/ila.h +++ b/include/uapi/linux/ila.h @@ -18,6 +18,7 @@ enum { ILA_ATTR_PAD, ILA_ATTR_CSUM_MODE, /* u8 */ ILA_ATTR_IDENT_TYPE, /* u8 */ + ILA_ATTR_HOOK_TYPE, /* u8 */ __ILA_ATTR_MAX, }; @@ -57,4 +58,10 @@ enum { ILA_ATYPE_USE_FORMAT = 32, /* Get type from type field in identifier */ }; + +enum { + ILA_HOOK_ROUTE_OUTPUT, + ILA_HOOK_ROUTE_INPUT, +}; + #endif /* _UAPI_LINUX_ILA_H */ diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c index 4b97d573f223..3d56a2fb6f86 100644 --- a/net/ipv6/ila/ila_lwt.c +++ b/net/ipv6/ila/ila_lwt.c @@ -20,6 +20,7 @@ struct ila_lwt { struct ila_params p; struct dst_cache dst_cache; u32 connected : 1; + u32 lwt_output : 1; }; static inline struct ila_lwt *ila_lwt_lwtunnel( @@ -45,8 +46,10 @@ static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb) if (skb->protocol != htons(ETH_P_IPV6)) goto drop; - ila_update_ipv6_locator(skb, ila_params_lwtunnel(orig_dst->lwtstate), - true); + if (ilwt->lwt_output) + ila_update_ipv6_locator(skb, + ila_params_lwtunnel(orig_dst->lwtstate), + true); if (rt->rt6i_flags & (RTF_GATEWAY | RTF_CACHE)) { /* Already have a next hop address in route, no need for @@ -98,11 +101,15 @@ drop: static int ila_input(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); + struct ila_lwt *ilwt = ila_lwt_lwtunnel(dst->lwtstate); if (skb->protocol != htons(ETH_P_IPV6)) goto drop; - ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate), false); + if (!ilwt->lwt_output) + ila_update_ipv6_locator(skb, + ila_params_lwtunnel(dst->lwtstate), + false); return dst->lwtstate->orig_input(skb); @@ -115,6 +122,7 @@ static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = { [ILA_ATTR_LOCATOR] = { .type = NLA_U64, }, [ILA_ATTR_CSUM_MODE] = { .type = NLA_U8, }, [ILA_ATTR_IDENT_TYPE] = { .type = NLA_U8, }, + [ILA_ATTR_HOOK_TYPE] = { .type = NLA_U8, }, }; static int ila_build_state(struct nlattr *nla, @@ -129,7 +137,9 @@ static int ila_build_state(struct nlattr *nla, const struct fib6_config *cfg6 = cfg; struct ila_addr *iaddr; u8 ident_type = ILA_ATYPE_USE_FORMAT; + u8 hook_type = ILA_HOOK_ROUTE_OUTPUT; u8 csum_mode = ILA_CSUM_NO_ACTION; + bool lwt_output = true; u8 eff_ident_type; int ret; @@ -180,6 +190,20 @@ static int ila_build_state(struct nlattr *nla, return -EINVAL; } + if (tb[ILA_ATTR_HOOK_TYPE]) + hook_type = nla_get_u8(tb[ILA_ATTR_HOOK_TYPE]); + + switch (hook_type) { + case ILA_HOOK_ROUTE_OUTPUT: + lwt_output = true; + break; + case ILA_HOOK_ROUTE_INPUT: + lwt_output = false; + break; + default: + return -EINVAL; + } + if (tb[ILA_ATTR_CSUM_MODE]) csum_mode = nla_get_u8(tb[ILA_ATTR_CSUM_MODE]); @@ -202,6 +226,8 @@ static int ila_build_state(struct nlattr *nla, return ret; } + ilwt->lwt_output = !!lwt_output; + p = ila_params_lwtunnel(newts); p->csum_mode = csum_mode; @@ -236,6 +262,7 @@ static int ila_fill_encap_info(struct sk_buff *skb, struct lwtunnel_state *lwtstate) { struct ila_params *p = ila_params_lwtunnel(lwtstate); + struct ila_lwt *ilwt = ila_lwt_lwtunnel(lwtstate); if (nla_put_u64_64bit(skb, ILA_ATTR_LOCATOR, (__force u64)p->locator.v64, ILA_ATTR_PAD)) @@ -247,6 +274,11 @@ static int ila_fill_encap_info(struct sk_buff *skb, if (nla_put_u8(skb, ILA_ATTR_IDENT_TYPE, (__force u8)p->ident_type)) goto nla_put_failure; + if (nla_put_u8(skb, ILA_ATTR_HOOK_TYPE, + ilwt->lwt_output ? ILA_HOOK_ROUTE_OUTPUT : + ILA_HOOK_ROUTE_INPUT)) + goto nla_put_failure; + return 0; nla_put_failure: @@ -258,6 +290,7 @@ static int ila_encap_nlsize(struct lwtunnel_state *lwtstate) return nla_total_size_64bit(sizeof(u64)) + /* ILA_ATTR_LOCATOR */ nla_total_size(sizeof(u8)) + /* ILA_ATTR_CSUM_MODE */ nla_total_size(sizeof(u8)) + /* ILA_ATTR_IDENT_TYPE */ + nla_total_size(sizeof(u8)) + /* ILA_ATTR_HOOK_TYPE */ 0; } -- cgit v1.2.3-71-gd317 From 602f3baf22188aad24b9a58be3209ab774b97d74 Mon Sep 17 00:00:00 2001 From: Nogah Frankel Date: Mon, 6 Nov 2017 07:23:41 +0100 Subject: net_sch: red: Add offload ability to RED qdisc Add the ability to offload RED qdisc by using ndo_setup_tc. There are four commands for RED offloading: * TC_RED_SET: handles set and change. * TC_RED_DESTROY: handle qdisc destroy. * TC_RED_STATS: update the qdiscs counters (given as reference) * TC_RED_XSTAT: returns red xstats. Whether RED is being offloaded is being determined every time dump action is being called because parent change of this qdisc could change its offload state but doesn't require any RED function to be called. Signed-off-by: Nogah Frankel Signed-off-by: Jiri Pirko Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + include/net/pkt_cls.h | 30 ++++++++++++++++ include/uapi/linux/pkt_sched.h | 1 + net/sched/sch_red.c | 79 ++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 111 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fda527ccb263..71968a2ca9f3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -777,6 +777,7 @@ enum tc_setup_type { TC_SETUP_CLSBPF, TC_SETUP_BLOCK, TC_SETUP_CBS, + TC_SETUP_QDISC_RED, }; /* These structures hold the attributes of bpf state that are being passed diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 98fef3221227..03c208d3c922 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -703,4 +703,34 @@ struct tc_cookie { u8 *data; u32 len; }; + +enum tc_red_command { + TC_RED_REPLACE, + TC_RED_DESTROY, + TC_RED_STATS, + TC_RED_XSTATS, +}; + +struct tc_red_qopt_offload_params { + u32 min; + u32 max; + u32 probability; + bool is_ecn; +}; +struct tc_red_qopt_offload_stats { + struct gnet_stats_basic_packed *bstats; + struct gnet_stats_queue *qstats; +}; + +struct tc_red_qopt_offload { + enum tc_red_command command; + u32 handle; + u32 parent; + union { + struct tc_red_qopt_offload_params set; + struct tc_red_qopt_offload_stats stats; + struct red_stats *xstats; + }; +}; + #endif diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 5002562868cc..6a2c5ea7e9c4 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -256,6 +256,7 @@ struct tc_red_qopt { #define TC_RED_ECN 1 #define TC_RED_HARDDROP 2 #define TC_RED_ADAPTATIVE 4 +#define TC_RED_OFFLOADED 8 }; struct tc_red_xstats { diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index fdfdb56aaae2..007dd8ef8aac 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -148,11 +149,37 @@ static void red_reset(struct Qdisc *sch) red_restart(&q->vars); } +static int red_offload(struct Qdisc *sch, bool enable) +{ + struct red_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct tc_red_qopt_offload opt = { + .handle = sch->handle, + .parent = sch->parent, + }; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return -EOPNOTSUPP; + + if (enable) { + opt.command = TC_RED_REPLACE; + opt.set.min = q->parms.qth_min >> q->parms.Wlog; + opt.set.max = q->parms.qth_max >> q->parms.Wlog; + opt.set.probability = q->parms.max_P; + opt.set.is_ecn = red_use_ecn(q); + } else { + opt.command = TC_RED_DESTROY; + } + + return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, &opt); +} + static void red_destroy(struct Qdisc *sch) { struct red_sched_data *q = qdisc_priv(sch); del_timer_sync(&q->adapt_timer); + red_offload(sch, false); qdisc_destroy(q->qdisc); } @@ -219,6 +246,7 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt) red_start_of_idle_period(&q->vars); sch_tree_unlock(sch); + red_offload(sch, true); return 0; } @@ -244,6 +272,33 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt) return red_change(sch, opt); } +static int red_dump_offload(struct Qdisc *sch, struct tc_red_qopt *opt) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_red_qopt_offload hw_stats = { + .handle = sch->handle, + .parent = sch->parent, + .command = TC_RED_STATS, + .stats.bstats = &sch->bstats, + .stats.qstats = &sch->qstats, + }; + int err; + + opt->flags &= ~TC_RED_OFFLOADED; + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return 0; + + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_RED, + &hw_stats); + if (err == -EOPNOTSUPP) + return 0; + + if (!err) + opt->flags |= TC_RED_OFFLOADED; + + return err; +} + static int red_dump(struct Qdisc *sch, struct sk_buff *skb) { struct red_sched_data *q = qdisc_priv(sch); @@ -257,8 +312,13 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb) .Plog = q->parms.Plog, .Scell_log = q->parms.Scell_log, }; + int err; sch->qstats.backlog = q->qdisc->qstats.backlog; + err = red_dump_offload(sch, &opt); + if (err) + goto nla_put_failure; + opts = nla_nest_start(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; @@ -275,6 +335,7 @@ nla_put_failure: static int red_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct red_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); struct tc_red_xstats st = { .early = q->stats.prob_drop + q->stats.forced_drop, .pdrop = q->stats.pdrop, @@ -282,6 +343,24 @@ static int red_dump_stats(struct Qdisc *sch, struct gnet_dump *d) .marked = q->stats.prob_mark + q->stats.forced_mark, }; + if (tc_can_offload(dev) && dev->netdev_ops->ndo_setup_tc) { + struct red_stats hw_stats = {0}; + struct tc_red_qopt_offload hw_stats_request = { + .handle = sch->handle, + .parent = sch->parent, + .command = TC_RED_XSTATS, + .xstats = &hw_stats, + }; + if (!dev->netdev_ops->ndo_setup_tc(dev, + TC_SETUP_QDISC_RED, + &hw_stats_request)) { + st.early += hw_stats.prob_drop + hw_stats.forced_drop; + st.pdrop += hw_stats.pdrop; + st.other += hw_stats.other; + st.marked += hw_stats.prob_mark + hw_stats.forced_mark; + } + } + return gnet_stats_copy_app(d, &st, sizeof(st)); } -- cgit v1.2.3-71-gd317 From b2d0f5d5dc53532e6f07bc546a476a55ebdfe0f3 Mon Sep 17 00:00:00 2001 From: Yi Yang Date: Tue, 7 Nov 2017 21:07:02 +0800 Subject: openvswitch: enable NSH support v16->17 - Fixed disputed check code: keep them in nsh_push and nsh_pop but also add them in __ovs_nla_copy_actions v15->v16 - Add csum recalculation for nsh_push, nsh_pop and set_nsh pointed out by Pravin - Move nsh key into the union with ipv4 and ipv6 and add check for nsh key in match_validate pointed out by Pravin - Add nsh check in validate_set and __ovs_nla_copy_actions v14->v15 - Check size in nsh_hdr_from_nlattr - Fixed four small issues pointed out By Jiri and Eric v13->v14 - Rename skb_push_nsh to nsh_push per Dave's comment - Rename skb_pop_nsh to nsh_pop per Dave's comment v12->v13 - Fix NSH header length check in set_nsh v11->v12 - Fix missing changes old comments pointed out - Fix new comments for v11 v10->v11 - Fix the left three disputable comments for v9 but not fixed in v10. v9->v10 - Change struct ovs_key_nsh to struct ovs_nsh_key_base base; __be32 context[NSH_MD1_CONTEXT_SIZE]; - Fix new comments for v9 v8->v9 - Fix build error reported by daily intel build because nsh module isn't selected by openvswitch v7->v8 - Rework nested value and mask for OVS_KEY_ATTR_NSH - Change pop_nsh to adapt to nsh kernel module - Fix many issues per comments from Jiri Benc v6->v7 - Remove NSH GSO patches in v6 because Jiri Benc reworked it as another patch series and they have been merged. - Change it to adapt to nsh kernel module added by NSH GSO patch series v5->v6 - Fix the rest comments for v4. - Add NSH GSO support for VxLAN-gpe + NSH and Eth + NSH. v4->v5 - Fix many comments by Jiri Benc and Eric Garver for v4. v3->v4 - Add new NSH match field ttl - Update NSH header to the latest format which will be final format and won't change per its author's confirmation. - Fix comments for v3. v2->v3 - Change OVS_KEY_ATTR_NSH to nested key to handle length-fixed attributes and length-variable attriubte more flexibly. - Remove struct ovs_action_push_nsh completely - Add code to handle nested attribute for SET_MASKED - Change PUSH_NSH to use the nested OVS_KEY_ATTR_NSH to transfer NSH header data. - Fix comments and coding style issues by Jiri and Eric v1->v2 - Change encap_nsh and decap_nsh to push_nsh and pop_nsh - Dynamically allocate struct ovs_action_push_nsh for length-variable metadata. OVS master and 2.8 branch has merged NSH userspace patch series, this patch is to enable NSH support in kernel data path in order that OVS can support NSH in compat mode by porting this. Signed-off-by: Yi Yang Acked-by: Jiri Benc Acked-by: Eric Garver Acked-by: Pravin Shelar Signed-off-by: David S. Miller --- include/net/nsh.h | 3 + include/uapi/linux/openvswitch.h | 29 ++++ net/nsh/nsh.c | 60 +++++++ net/openvswitch/Kconfig | 1 + net/openvswitch/actions.c | 116 +++++++++++++ net/openvswitch/flow.c | 51 ++++++ net/openvswitch/flow.h | 7 + net/openvswitch/flow_netlink.c | 343 ++++++++++++++++++++++++++++++++++++++- net/openvswitch/flow_netlink.h | 5 + 9 files changed, 613 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/nsh.h b/include/net/nsh.h index a1eaea20be96..350b1ad11c7f 100644 --- a/include/net/nsh.h +++ b/include/net/nsh.h @@ -304,4 +304,7 @@ static inline void nsh_set_flags_ttl_len(struct nshhdr *nsh, u8 flags, NSH_FLAGS_MASK | NSH_TTL_MASK | NSH_LEN_MASK); } +int nsh_push(struct sk_buff *skb, const struct nshhdr *pushed_nh); +int nsh_pop(struct sk_buff *skb); + #endif /* __NET_NSH_H */ diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 501e4c4e2a03..ec75a685f1dd 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -336,6 +336,7 @@ enum ovs_key_attr { OVS_KEY_ATTR_CT_LABELS, /* 16-octet connection tracking label */ OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4, /* struct ovs_key_ct_tuple_ipv4 */ OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6, /* struct ovs_key_ct_tuple_ipv6 */ + OVS_KEY_ATTR_NSH, /* Nested set of ovs_nsh_key_* */ #ifdef __KERNEL__ OVS_KEY_ATTR_TUNNEL_INFO, /* struct ip_tunnel_info */ @@ -495,6 +496,30 @@ struct ovs_key_ct_tuple_ipv6 { __u8 ipv6_proto; }; +enum ovs_nsh_key_attr { + OVS_NSH_KEY_ATTR_UNSPEC, + OVS_NSH_KEY_ATTR_BASE, /* struct ovs_nsh_key_base. */ + OVS_NSH_KEY_ATTR_MD1, /* struct ovs_nsh_key_md1. */ + OVS_NSH_KEY_ATTR_MD2, /* variable-length octets for MD type 2. */ + __OVS_NSH_KEY_ATTR_MAX +}; + +#define OVS_NSH_KEY_ATTR_MAX (__OVS_NSH_KEY_ATTR_MAX - 1) + +struct ovs_nsh_key_base { + __u8 flags; + __u8 ttl; + __u8 mdtype; + __u8 np; + __be32 path_hdr; +}; + +#define NSH_MD1_CONTEXT_SIZE 4 + +struct ovs_nsh_key_md1 { + __be32 context[NSH_MD1_CONTEXT_SIZE]; +}; + /** * enum ovs_flow_attr - attributes for %OVS_FLOW_* commands. * @OVS_FLOW_ATTR_KEY: Nested %OVS_KEY_ATTR_* attributes specifying the flow @@ -811,6 +836,8 @@ struct ovs_action_push_eth { * @OVS_ACTION_ATTR_POP_ETH: Pop the outermost Ethernet header off the * packet. * @OVS_ACTION_ATTR_CT_CLEAR: Clear conntrack state from the packet. + * @OVS_ACTION_ATTR_PUSH_NSH: push NSH header to the packet. + * @OVS_ACTION_ATTR_POP_NSH: pop the outermost NSH header off the packet. * * Only a single header can be set with a single %OVS_ACTION_ATTR_SET. Not all * fields within a header are modifiable, e.g. the IPv4 protocol and fragment @@ -841,6 +868,8 @@ enum ovs_action_attr { OVS_ACTION_ATTR_PUSH_ETH, /* struct ovs_action_push_eth. */ OVS_ACTION_ATTR_POP_ETH, /* No argument. */ OVS_ACTION_ATTR_CT_CLEAR, /* No argument. */ + OVS_ACTION_ATTR_PUSH_NSH, /* Nested OVS_NSH_KEY_ATTR_*. */ + OVS_ACTION_ATTR_POP_NSH, /* No argument. */ __OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted * from userspace. */ diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c index 58fb827439a8..d7da99a0b0b8 100644 --- a/net/nsh/nsh.c +++ b/net/nsh/nsh.c @@ -14,6 +14,66 @@ #include #include +int nsh_push(struct sk_buff *skb, const struct nshhdr *pushed_nh) +{ + struct nshhdr *nh; + size_t length = nsh_hdr_len(pushed_nh); + u8 next_proto; + + if (skb->mac_len) { + next_proto = TUN_P_ETHERNET; + } else { + next_proto = tun_p_from_eth_p(skb->protocol); + if (!next_proto) + return -EAFNOSUPPORT; + } + + /* Add the NSH header */ + if (skb_cow_head(skb, length) < 0) + return -ENOMEM; + + skb_push(skb, length); + nh = (struct nshhdr *)(skb->data); + memcpy(nh, pushed_nh, length); + nh->np = next_proto; + skb_postpush_rcsum(skb, nh, length); + + skb->protocol = htons(ETH_P_NSH); + skb_reset_mac_header(skb); + skb_reset_network_header(skb); + skb_reset_mac_len(skb); + + return 0; +} +EXPORT_SYMBOL_GPL(nsh_push); + +int nsh_pop(struct sk_buff *skb) +{ + struct nshhdr *nh; + size_t length; + __be16 inner_proto; + + if (!pskb_may_pull(skb, NSH_BASE_HDR_LEN)) + return -ENOMEM; + nh = (struct nshhdr *)(skb->data); + length = nsh_hdr_len(nh); + inner_proto = tun_p_to_eth_p(nh->np); + if (!pskb_may_pull(skb, length)) + return -ENOMEM; + + if (!inner_proto) + return -EAFNOSUPPORT; + + skb_pull_rcsum(skb, length); + skb_reset_mac_header(skb); + skb_reset_network_header(skb); + skb_reset_mac_len(skb); + skb->protocol = inner_proto; + + return 0; +} +EXPORT_SYMBOL_GPL(nsh_pop); + static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, netdev_features_t features) { diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index ce947292ae77..2650205cdaf9 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -14,6 +14,7 @@ config OPENVSWITCH select MPLS select NET_MPLS_GSO select DST_CACHE + select NET_NSH ---help--- Open vSwitch is a multilayer Ethernet switch targeted at virtualized environments. In addition to supporting a variety of features diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index a551232daf61..9a6a6d51e421 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -43,6 +43,7 @@ #include "flow.h" #include "conntrack.h" #include "vport.h" +#include "flow_netlink.h" struct deferred_action { struct sk_buff *skb; @@ -380,6 +381,38 @@ static int push_eth(struct sk_buff *skb, struct sw_flow_key *key, return 0; } +static int push_nsh(struct sk_buff *skb, struct sw_flow_key *key, + const struct nshhdr *nh) +{ + int err; + + err = nsh_push(skb, nh); + if (err) + return err; + + /* safe right before invalidate_flow_key */ + key->mac_proto = MAC_PROTO_NONE; + invalidate_flow_key(key); + return 0; +} + +static int pop_nsh(struct sk_buff *skb, struct sw_flow_key *key) +{ + int err; + + err = nsh_pop(skb); + if (err) + return err; + + /* safe right before invalidate_flow_key */ + if (skb->protocol == htons(ETH_P_TEB)) + key->mac_proto = MAC_PROTO_ETHERNET; + else + key->mac_proto = MAC_PROTO_NONE; + invalidate_flow_key(key); + return 0; +} + static void update_ip_l4_checksum(struct sk_buff *skb, struct iphdr *nh, __be32 addr, __be32 new_addr) { @@ -602,6 +635,69 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key, return 0; } +static int set_nsh(struct sk_buff *skb, struct sw_flow_key *flow_key, + const struct nlattr *a) +{ + struct nshhdr *nh; + size_t length; + int err; + u8 flags; + u8 ttl; + int i; + + struct ovs_key_nsh key; + struct ovs_key_nsh mask; + + err = nsh_key_from_nlattr(a, &key, &mask); + if (err) + return err; + + /* Make sure the NSH base header is there */ + if (!pskb_may_pull(skb, skb_network_offset(skb) + NSH_BASE_HDR_LEN)) + return -ENOMEM; + + nh = nsh_hdr(skb); + length = nsh_hdr_len(nh); + + /* Make sure the whole NSH header is there */ + err = skb_ensure_writable(skb, skb_network_offset(skb) + + length); + if (unlikely(err)) + return err; + + nh = nsh_hdr(skb); + skb_postpull_rcsum(skb, nh, length); + flags = nsh_get_flags(nh); + flags = OVS_MASKED(flags, key.base.flags, mask.base.flags); + flow_key->nsh.base.flags = flags; + ttl = nsh_get_ttl(nh); + ttl = OVS_MASKED(ttl, key.base.ttl, mask.base.ttl); + flow_key->nsh.base.ttl = ttl; + nsh_set_flags_and_ttl(nh, flags, ttl); + nh->path_hdr = OVS_MASKED(nh->path_hdr, key.base.path_hdr, + mask.base.path_hdr); + flow_key->nsh.base.path_hdr = nh->path_hdr; + switch (nh->mdtype) { + case NSH_M_TYPE1: + for (i = 0; i < NSH_MD1_CONTEXT_SIZE; i++) { + nh->md1.context[i] = + OVS_MASKED(nh->md1.context[i], key.context[i], + mask.context[i]); + } + memcpy(flow_key->nsh.context, nh->md1.context, + sizeof(nh->md1.context)); + break; + case NSH_M_TYPE2: + memset(flow_key->nsh.context, 0, + sizeof(flow_key->nsh.context)); + break; + default: + return -EINVAL; + } + skb_postpush_rcsum(skb, nh, length); + return 0; +} + /* Must follow skb_ensure_writable() since that can move the skb data. */ static void set_tp_port(struct sk_buff *skb, __be16 *port, __be16 new_port, __sum16 *check) @@ -1024,6 +1120,10 @@ static int execute_masked_set_action(struct sk_buff *skb, get_mask(a, struct ovs_key_ethernet *)); break; + case OVS_KEY_ATTR_NSH: + err = set_nsh(skb, flow_key, a); + break; + case OVS_KEY_ATTR_IPV4: err = set_ipv4(skb, flow_key, nla_data(a), get_mask(a, struct ovs_key_ipv4 *)); @@ -1214,6 +1314,22 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, case OVS_ACTION_ATTR_POP_ETH: err = pop_eth(skb, key); break; + + case OVS_ACTION_ATTR_PUSH_NSH: { + u8 buffer[NSH_HDR_MAX_LEN]; + struct nshhdr *nh = (struct nshhdr *)buffer; + + err = nsh_hdr_from_nlattr(nla_data(a), nh, + NSH_HDR_MAX_LEN); + if (unlikely(err)) + break; + err = push_nsh(skb, key, nh); + break; + } + + case OVS_ACTION_ATTR_POP_NSH: + err = pop_nsh(skb, key); + break; } if (unlikely(err)) { diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 8c94cef25a72..864ddb1e3642 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -46,6 +46,7 @@ #include #include #include +#include #include "conntrack.h" #include "datapath.h" @@ -490,6 +491,52 @@ invalid: return 0; } +static int parse_nsh(struct sk_buff *skb, struct sw_flow_key *key) +{ + struct nshhdr *nh; + unsigned int nh_ofs = skb_network_offset(skb); + u8 version, length; + int err; + + err = check_header(skb, nh_ofs + NSH_BASE_HDR_LEN); + if (unlikely(err)) + return err; + + nh = nsh_hdr(skb); + version = nsh_get_ver(nh); + length = nsh_hdr_len(nh); + + if (version != 0) + return -EINVAL; + + err = check_header(skb, nh_ofs + length); + if (unlikely(err)) + return err; + + nh = nsh_hdr(skb); + key->nsh.base.flags = nsh_get_flags(nh); + key->nsh.base.ttl = nsh_get_ttl(nh); + key->nsh.base.mdtype = nh->mdtype; + key->nsh.base.np = nh->np; + key->nsh.base.path_hdr = nh->path_hdr; + switch (key->nsh.base.mdtype) { + case NSH_M_TYPE1: + if (length != NSH_M_TYPE1_LEN) + return -EINVAL; + memcpy(key->nsh.context, nh->md1.context, + sizeof(nh->md1)); + break; + case NSH_M_TYPE2: + memset(key->nsh.context, 0, + sizeof(nh->md1)); + break; + default: + return -EINVAL; + } + + return 0; +} + /** * key_extract - extracts a flow key from an Ethernet frame. * @skb: sk_buff that contains the frame, with skb->data pointing to the @@ -735,6 +782,10 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) memset(&key->tp, 0, sizeof(key->tp)); } } + } else if (key->eth.type == htons(ETH_P_NSH)) { + error = parse_nsh(skb, key); + if (error) + return error; } return 0; } diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index 1875bba4f865..c670dd24b8b7 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -35,6 +35,7 @@ #include #include #include +#include struct sk_buff; @@ -66,6 +67,11 @@ struct vlan_head { (offsetof(struct sw_flow_key, recirc_id) + \ FIELD_SIZEOF(struct sw_flow_key, recirc_id)) +struct ovs_key_nsh { + struct ovs_nsh_key_base base; + __be32 context[NSH_MD1_CONTEXT_SIZE]; +}; + struct sw_flow_key { u8 tun_opts[IP_TUNNEL_OPTS_MAX]; u8 tun_opts_len; @@ -143,6 +149,7 @@ struct sw_flow_key { } nd; }; } ipv6; + struct ovs_key_nsh nsh; /* network service header */ }; struct { /* Connection tracking fields not packed above. */ diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index dc0d79092e74..4201f9293af3 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -48,6 +48,7 @@ #include #include #include +#include #include #include "flow_netlink.h" @@ -80,9 +81,11 @@ static bool actions_may_change_flow(const struct nlattr *actions) case OVS_ACTION_ATTR_HASH: case OVS_ACTION_ATTR_POP_ETH: case OVS_ACTION_ATTR_POP_MPLS: + case OVS_ACTION_ATTR_POP_NSH: case OVS_ACTION_ATTR_POP_VLAN: case OVS_ACTION_ATTR_PUSH_ETH: case OVS_ACTION_ATTR_PUSH_MPLS: + case OVS_ACTION_ATTR_PUSH_NSH: case OVS_ACTION_ATTR_PUSH_VLAN: case OVS_ACTION_ATTR_SAMPLE: case OVS_ACTION_ATTR_SET: @@ -175,7 +178,8 @@ static bool match_validate(const struct sw_flow_match *match, | (1 << OVS_KEY_ATTR_ICMPV6) | (1 << OVS_KEY_ATTR_ARP) | (1 << OVS_KEY_ATTR_ND) - | (1 << OVS_KEY_ATTR_MPLS)); + | (1 << OVS_KEY_ATTR_MPLS) + | (1 << OVS_KEY_ATTR_NSH)); /* Always allowed mask fields. */ mask_allowed |= ((1 << OVS_KEY_ATTR_TUNNEL) @@ -284,6 +288,14 @@ static bool match_validate(const struct sw_flow_match *match, } } + if (match->key->eth.type == htons(ETH_P_NSH)) { + key_expected |= 1 << OVS_KEY_ATTR_NSH; + if (match->mask && + match->mask->key.eth.type == htons(0xffff)) { + mask_allowed |= 1 << OVS_KEY_ATTR_NSH; + } + } + if ((key_attrs & key_expected) != key_expected) { /* Key attributes check failed. */ OVS_NLERR(log, "Missing key (keys=%llx, expected=%llx)", @@ -325,12 +337,25 @@ size_t ovs_tun_key_attr_size(void) + nla_total_size(4); /* OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS */ } +size_t ovs_nsh_key_attr_size(void) +{ + /* Whenever adding new OVS_NSH_KEY_ FIELDS, we should consider + * updating this function. + */ + return nla_total_size(NSH_BASE_HDR_LEN) /* OVS_NSH_KEY_ATTR_BASE */ + /* OVS_NSH_KEY_ATTR_MD1 and OVS_NSH_KEY_ATTR_MD2 are + * mutually exclusive, so the bigger one can cover + * the small one. + */ + + nla_total_size(NSH_CTX_HDRS_MAX_LEN); +} + size_t ovs_key_attr_size(void) { /* Whenever adding new OVS_KEY_ FIELDS, we should consider * updating this function. */ - BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 28); + BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 29); return nla_total_size(4) /* OVS_KEY_ATTR_PRIORITY */ + nla_total_size(0) /* OVS_KEY_ATTR_TUNNEL */ @@ -344,6 +369,8 @@ size_t ovs_key_attr_size(void) + nla_total_size(4) /* OVS_KEY_ATTR_CT_MARK */ + nla_total_size(16) /* OVS_KEY_ATTR_CT_LABELS */ + nla_total_size(40) /* OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6 */ + + nla_total_size(0) /* OVS_KEY_ATTR_NSH */ + + ovs_nsh_key_attr_size() + nla_total_size(12) /* OVS_KEY_ATTR_ETHERNET */ + nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */ + nla_total_size(4) /* OVS_KEY_ATTR_VLAN */ @@ -377,6 +404,13 @@ static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] [OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS] = { .len = sizeof(u32) }, }; +static const struct ovs_len_tbl +ovs_nsh_key_attr_lens[OVS_NSH_KEY_ATTR_MAX + 1] = { + [OVS_NSH_KEY_ATTR_BASE] = { .len = sizeof(struct ovs_nsh_key_base) }, + [OVS_NSH_KEY_ATTR_MD1] = { .len = sizeof(struct ovs_nsh_key_md1) }, + [OVS_NSH_KEY_ATTR_MD2] = { .len = OVS_ATTR_VARIABLE }, +}; + /* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute. */ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = { [OVS_KEY_ATTR_ENCAP] = { .len = OVS_ATTR_NESTED }, @@ -409,6 +443,8 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = { .len = sizeof(struct ovs_key_ct_tuple_ipv4) }, [OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6] = { .len = sizeof(struct ovs_key_ct_tuple_ipv6) }, + [OVS_KEY_ATTR_NSH] = { .len = OVS_ATTR_NESTED, + .next = ovs_nsh_key_attr_lens, }, }; static bool check_attr_len(unsigned int attr_len, unsigned int expected_len) @@ -1227,6 +1263,221 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, return 0; } +int nsh_hdr_from_nlattr(const struct nlattr *attr, + struct nshhdr *nh, size_t size) +{ + struct nlattr *a; + int rem; + u8 flags = 0; + u8 ttl = 0; + int mdlen = 0; + + /* validate_nsh has check this, so we needn't do duplicate check here + */ + if (size < NSH_BASE_HDR_LEN) + return -ENOBUFS; + + nla_for_each_nested(a, attr, rem) { + int type = nla_type(a); + + switch (type) { + case OVS_NSH_KEY_ATTR_BASE: { + const struct ovs_nsh_key_base *base = nla_data(a); + + flags = base->flags; + ttl = base->ttl; + nh->np = base->np; + nh->mdtype = base->mdtype; + nh->path_hdr = base->path_hdr; + break; + } + case OVS_NSH_KEY_ATTR_MD1: + mdlen = nla_len(a); + if (mdlen > size - NSH_BASE_HDR_LEN) + return -ENOBUFS; + memcpy(&nh->md1, nla_data(a), mdlen); + break; + + case OVS_NSH_KEY_ATTR_MD2: + mdlen = nla_len(a); + if (mdlen > size - NSH_BASE_HDR_LEN) + return -ENOBUFS; + memcpy(&nh->md2, nla_data(a), mdlen); + break; + + default: + return -EINVAL; + } + } + + /* nsh header length = NSH_BASE_HDR_LEN + mdlen */ + nh->ver_flags_ttl_len = 0; + nsh_set_flags_ttl_len(nh, flags, ttl, NSH_BASE_HDR_LEN + mdlen); + + return 0; +} + +int nsh_key_from_nlattr(const struct nlattr *attr, + struct ovs_key_nsh *nsh, struct ovs_key_nsh *nsh_mask) +{ + struct nlattr *a; + int rem; + + /* validate_nsh has check this, so we needn't do duplicate check here + */ + nla_for_each_nested(a, attr, rem) { + int type = nla_type(a); + + switch (type) { + case OVS_NSH_KEY_ATTR_BASE: { + const struct ovs_nsh_key_base *base = nla_data(a); + const struct ovs_nsh_key_base *base_mask = base + 1; + + nsh->base = *base; + nsh_mask->base = *base_mask; + break; + } + case OVS_NSH_KEY_ATTR_MD1: { + const struct ovs_nsh_key_md1 *md1 = nla_data(a); + const struct ovs_nsh_key_md1 *md1_mask = md1 + 1; + + memcpy(nsh->context, md1->context, sizeof(*md1)); + memcpy(nsh_mask->context, md1_mask->context, + sizeof(*md1_mask)); + break; + } + case OVS_NSH_KEY_ATTR_MD2: + /* Not supported yet */ + return -ENOTSUPP; + default: + return -EINVAL; + } + } + + return 0; +} + +static int nsh_key_put_from_nlattr(const struct nlattr *attr, + struct sw_flow_match *match, bool is_mask, + bool is_push_nsh, bool log) +{ + struct nlattr *a; + int rem; + bool has_base = false; + bool has_md1 = false; + bool has_md2 = false; + u8 mdtype = 0; + int mdlen = 0; + + if (WARN_ON(is_push_nsh && is_mask)) + return -EINVAL; + + nla_for_each_nested(a, attr, rem) { + int type = nla_type(a); + int i; + + if (type > OVS_NSH_KEY_ATTR_MAX) { + OVS_NLERR(log, "nsh attr %d is out of range max %d", + type, OVS_NSH_KEY_ATTR_MAX); + return -EINVAL; + } + + if (!check_attr_len(nla_len(a), + ovs_nsh_key_attr_lens[type].len)) { + OVS_NLERR( + log, + "nsh attr %d has unexpected len %d expected %d", + type, + nla_len(a), + ovs_nsh_key_attr_lens[type].len + ); + return -EINVAL; + } + + switch (type) { + case OVS_NSH_KEY_ATTR_BASE: { + const struct ovs_nsh_key_base *base = nla_data(a); + + has_base = true; + mdtype = base->mdtype; + SW_FLOW_KEY_PUT(match, nsh.base.flags, + base->flags, is_mask); + SW_FLOW_KEY_PUT(match, nsh.base.ttl, + base->ttl, is_mask); + SW_FLOW_KEY_PUT(match, nsh.base.mdtype, + base->mdtype, is_mask); + SW_FLOW_KEY_PUT(match, nsh.base.np, + base->np, is_mask); + SW_FLOW_KEY_PUT(match, nsh.base.path_hdr, + base->path_hdr, is_mask); + break; + } + case OVS_NSH_KEY_ATTR_MD1: { + const struct ovs_nsh_key_md1 *md1 = nla_data(a); + + has_md1 = true; + for (i = 0; i < NSH_MD1_CONTEXT_SIZE; i++) + SW_FLOW_KEY_PUT(match, nsh.context[i], + md1->context[i], is_mask); + break; + } + case OVS_NSH_KEY_ATTR_MD2: + if (!is_push_nsh) /* Not supported MD type 2 yet */ + return -ENOTSUPP; + + has_md2 = true; + mdlen = nla_len(a); + if (mdlen > NSH_CTX_HDRS_MAX_LEN || mdlen <= 0) { + OVS_NLERR( + log, + "Invalid MD length %d for MD type %d", + mdlen, + mdtype + ); + return -EINVAL; + } + break; + default: + OVS_NLERR(log, "Unknown nsh attribute %d", + type); + return -EINVAL; + } + } + + if (rem > 0) { + OVS_NLERR(log, "nsh attribute has %d unknown bytes.", rem); + return -EINVAL; + } + + if (has_md1 && has_md2) { + OVS_NLERR( + 1, + "invalid nsh attribute: md1 and md2 are exclusive." + ); + return -EINVAL; + } + + if (!is_mask) { + if ((has_md1 && mdtype != NSH_M_TYPE1) || + (has_md2 && mdtype != NSH_M_TYPE2)) { + OVS_NLERR(1, "nsh attribute has unmatched MD type %d.", + mdtype); + return -EINVAL; + } + + if (is_push_nsh && + (!has_base || (!has_md1 && !has_md2))) { + OVS_NLERR( + 1, + "push_nsh: missing base or metadata attributes" + ); + return -EINVAL; + } + } + + return 0; +} + static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match, u64 attrs, const struct nlattr **a, bool is_mask, bool log) @@ -1354,6 +1605,13 @@ static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match, attrs &= ~(1 << OVS_KEY_ATTR_ARP); } + if (attrs & (1 << OVS_KEY_ATTR_NSH)) { + if (nsh_key_put_from_nlattr(a[OVS_KEY_ATTR_NSH], match, + is_mask, false, log) < 0) + return -EINVAL; + attrs &= ~(1 << OVS_KEY_ATTR_NSH); + } + if (attrs & (1 << OVS_KEY_ATTR_MPLS)) { const struct ovs_key_mpls *mpls_key; @@ -1670,6 +1928,34 @@ static int ovs_nla_put_vlan(struct sk_buff *skb, const struct vlan_head *vh, return 0; } +static int nsh_key_to_nlattr(const struct ovs_key_nsh *nsh, bool is_mask, + struct sk_buff *skb) +{ + struct nlattr *start; + + start = nla_nest_start(skb, OVS_KEY_ATTR_NSH); + if (!start) + return -EMSGSIZE; + + if (nla_put(skb, OVS_NSH_KEY_ATTR_BASE, sizeof(nsh->base), &nsh->base)) + goto nla_put_failure; + + if (is_mask || nsh->base.mdtype == NSH_M_TYPE1) { + if (nla_put(skb, OVS_NSH_KEY_ATTR_MD1, + sizeof(nsh->context), nsh->context)) + goto nla_put_failure; + } + + /* Don't support MD type 2 yet */ + + nla_nest_end(skb, start); + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + static int __ovs_nla_put_key(const struct sw_flow_key *swkey, const struct sw_flow_key *output, bool is_mask, struct sk_buff *skb) @@ -1798,6 +2084,9 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, ipv6_key->ipv6_tclass = output->ip.tos; ipv6_key->ipv6_hlimit = output->ip.ttl; ipv6_key->ipv6_frag = output->ip.frag; + } else if (swkey->eth.type == htons(ETH_P_NSH)) { + if (nsh_key_to_nlattr(&output->nsh, is_mask, skb)) + goto nla_put_failure; } else if (swkey->eth.type == htons(ETH_P_ARP) || swkey->eth.type == htons(ETH_P_RARP)) { struct ovs_key_arp *arp_key; @@ -2292,6 +2581,19 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, return err; } +static bool validate_nsh(const struct nlattr *attr, bool is_mask, + bool is_push_nsh, bool log) +{ + struct sw_flow_match match; + struct sw_flow_key key; + int ret = 0; + + ovs_match_init(&match, &key, true, NULL); + ret = nsh_key_put_from_nlattr(attr, &match, is_mask, + is_push_nsh, log); + return !ret; +} + /* Return false if there are any non-masked bits set. * Mask follows data immediately, before any netlink padding. */ @@ -2434,6 +2736,13 @@ static int validate_set(const struct nlattr *a, break; + case OVS_KEY_ATTR_NSH: + if (eth_type != htons(ETH_P_NSH)) + return -EINVAL; + if (!validate_nsh(nla_data(a), masked, false, log)) + return -EINVAL; + break; + default: return -EINVAL; } @@ -2533,6 +2842,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, [OVS_ACTION_ATTR_TRUNC] = sizeof(struct ovs_action_trunc), [OVS_ACTION_ATTR_PUSH_ETH] = sizeof(struct ovs_action_push_eth), [OVS_ACTION_ATTR_POP_ETH] = 0, + [OVS_ACTION_ATTR_PUSH_NSH] = (u32)-1, + [OVS_ACTION_ATTR_POP_NSH] = 0, }; const struct ovs_action_push_vlan *vlan; int type = nla_type(a); @@ -2690,6 +3001,34 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, mac_proto = MAC_PROTO_ETHERNET; break; + case OVS_ACTION_ATTR_PUSH_NSH: + if (mac_proto != MAC_PROTO_ETHERNET) { + u8 next_proto; + + next_proto = tun_p_from_eth_p(eth_type); + if (!next_proto) + return -EINVAL; + } + mac_proto = MAC_PROTO_NONE; + if (!validate_nsh(nla_data(a), false, true, true)) + return -EINVAL; + break; + + case OVS_ACTION_ATTR_POP_NSH: { + __be16 inner_proto; + + if (eth_type != htons(ETH_P_NSH)) + return -EINVAL; + inner_proto = tun_p_to_eth_p(key->nsh.base.np); + if (!inner_proto) + return -EINVAL; + if (key->nsh.base.np == TUN_P_ETHERNET) + mac_proto = MAC_PROTO_ETHERNET; + else + mac_proto = MAC_PROTO_NONE; + break; + } + default: OVS_NLERR(log, "Unknown Action type %d", type); return -EINVAL; diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h index 929c665ac3aa..6657606b2b47 100644 --- a/net/openvswitch/flow_netlink.h +++ b/net/openvswitch/flow_netlink.h @@ -79,4 +79,9 @@ int ovs_nla_put_actions(const struct nlattr *attr, void ovs_nla_free_flow_actions(struct sw_flow_actions *); void ovs_nla_free_flow_actions_rcu(struct sw_flow_actions *); +int nsh_key_from_nlattr(const struct nlattr *attr, struct ovs_key_nsh *nsh, + struct ovs_key_nsh *nsh_mask); +int nsh_hdr_from_nlattr(const struct nlattr *attr, struct nshhdr *nh, + size_t size); + #endif /* flow_netlink.h */ -- cgit v1.2.3-71-gd317 From 096b85464832d2a7bd7bd6d4db2fafed2ab77244 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Fri, 13 Oct 2017 15:09:25 -0700 Subject: EVM: Include security.apparmor in EVM measurements Apparmor will be gaining support for security.apparmor labels, and it would be helpful to include these in EVM validation now so appropriate signatures can be generated even before full support is merged. Signed-off-by: Matthew Garrett Acked-by: John Johansen Signed-off-by: Mimi Zohar --- include/uapi/linux/xattr.h | 3 +++ security/integrity/evm/evm_main.c | 3 +++ 2 files changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/xattr.h b/include/uapi/linux/xattr.h index 1590c49cae57..e630b9cd70cb 100644 --- a/include/uapi/linux/xattr.h +++ b/include/uapi/linux/xattr.h @@ -65,6 +65,9 @@ #define XATTR_NAME_SMACKTRANSMUTE XATTR_SECURITY_PREFIX XATTR_SMACK_TRANSMUTE #define XATTR_NAME_SMACKMMAP XATTR_SECURITY_PREFIX XATTR_SMACK_MMAP +#define XATTR_APPARMOR_SUFFIX "apparmor" +#define XATTR_NAME_APPARMOR XATTR_SECURITY_PREFIX XATTR_APPARMOR_SUFFIX + #define XATTR_CAPS_SUFFIX "capability" #define XATTR_NAME_CAPS XATTR_SECURITY_PREFIX XATTR_CAPS_SUFFIX diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c index 063d38aef64e..9826c02e2db8 100644 --- a/security/integrity/evm/evm_main.c +++ b/security/integrity/evm/evm_main.c @@ -49,6 +49,9 @@ char *evm_config_xattrnames[] = { XATTR_NAME_SMACKMMAP, #endif #endif +#ifdef CONFIG_SECURITY_APPARMOR + XATTR_NAME_APPARMOR, +#endif #ifdef CONFIG_IMA_APPRAISE XATTR_NAME_IMA, #endif -- cgit v1.2.3-71-gd317 From 9e429d564926d3bca49907fa03031da705ad6f2c Mon Sep 17 00:00:00 2001 From: Jason Gerecke Date: Tue, 7 Nov 2017 08:25:17 -0800 Subject: HID: wacom: generic: Send BTN_STYLUS3 when both barrel switches are set The Wacom Pro Pen 3D includes a third barrel switch which is intended to be particularly useful in applications where one frequency uses pan, zoom, and rotate to navigate around a scene or model. The pen is compatible with the MobileStudio Pro, 2nd-gen Intuos Pro, and Cintiq Pro. When the third button is pressed, these devices set both the HID_DG_BARRELSWITCH and HID_DG_BARRELSWITCH2 usages since their HID descriptors do not include a usage specific to the button. Rather than send both BTN_STYLUS and BTN_STYLUS2 when the third button is pressed, userspace (libinput) has requested that we detect this condition and report a newly-defined BTN_STYLUS3 event instead. We could define a quirk specific to devices compatible with the Pro Pen 3D, but the liklihood of seeing both barrel switch bits set with other pens/devices is low enough to not worry about (pens mechanically prevent accidental activation of multiple switches). Signed-off-by: Jason Gerecke Acked-by: Dmitry Torokhov Acked-by: Peter Hutterer Acked-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- drivers/hid/wacom_wac.c | 18 ++++++++++++++++-- drivers/hid/wacom_wac.h | 2 ++ include/uapi/linux/input-event-codes.h | 1 + 3 files changed, 19 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index e3223b0c4f90..16af6886e828 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -2140,6 +2140,12 @@ static void wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field case HID_DG_TIPSWITCH: wacom_wac->hid_data.tipswitch |= value; return; + case HID_DG_BARRELSWITCH: + wacom_wac->hid_data.barrelswitch = value; + return; + case HID_DG_BARRELSWITCH2: + wacom_wac->hid_data.barrelswitch2 = value; + return; case HID_DG_TOOLSERIALNUMBER: if (value) { wacom_wac->serial[0] = (wacom_wac->serial[0] & ~0xFFFFFFFFULL); @@ -2254,6 +2260,12 @@ static void wacom_wac_pen_report(struct hid_device *hdev, if (!delay_pen_events(wacom_wac) && wacom_wac->tool[0]) { int id = wacom_wac->id[0]; + int sw_state = wacom_wac->hid_data.barrelswitch | + (wacom_wac->hid_data.barrelswitch2 << 1); + + input_report_key(input, BTN_STYLUS, sw_state == 1); + input_report_key(input, BTN_STYLUS2, sw_state == 2); + input_report_key(input, BTN_STYLUS3, sw_state == 3); /* * Non-USI EMR tools should have their IDs mangled to @@ -3300,9 +3312,11 @@ int wacom_setup_pen_input_capabilities(struct input_dev *input_dev, else __set_bit(INPUT_PROP_POINTER, input_dev->propbit); - if (features->type == HID_GENERIC) - /* setup has already been done */ + if (features->type == HID_GENERIC) { + /* setup has already been done; apply otherwise-undetectible quirks */ + input_set_capability(input_dev, EV_KEY, BTN_STYLUS3); return 0; + } __set_bit(BTN_TOUCH, input_dev->keybit); __set_bit(ABS_MISC, input_dev->absbit); diff --git a/drivers/hid/wacom_wac.h b/drivers/hid/wacom_wac.h index 8a03654048bf..69dda27e8dde 100644 --- a/drivers/hid/wacom_wac.h +++ b/drivers/hid/wacom_wac.h @@ -291,6 +291,8 @@ struct hid_data { bool inrange_state; bool invert_state; bool tipswitch; + bool barrelswitch; + bool barrelswitch2; int x; int y; int pressure; diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 179891074b3c..9b3a522f50d1 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -406,6 +406,7 @@ #define BTN_TOOL_MOUSE 0x146 #define BTN_TOOL_LENS 0x147 #define BTN_TOOL_QUINTTAP 0x148 /* Five fingers on trackpad */ +#define BTN_STYLUS3 0x149 #define BTN_TOUCH 0x14a #define BTN_STYLUS 0x14b #define BTN_STYLUS2 0x14c -- cgit v1.2.3-71-gd317 From da9a1446d248f673a8560ce46251ff620214ab7b Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Thu, 9 Nov 2017 10:00:45 +0100 Subject: KVM: s390: provide a capability for AIS state migration The AIS capability was introduced in 4.12, while the interface to migrate the state was added in 4.13. Unfortunately it is not possible for userspace to detect the migration capability without creating a flic kvm device. As in QEMU the cpu model detection runs on the "none" machine this will result in cpu model issues regarding the "ais" capability. To get the "ais" capability properly let's add a new KVM capability that tells userspace that AIS states can be migrated. Signed-off-by: Christian Borntraeger Reviewed-by: Cornelia Huck Reviewed-by: David Hildenbrand Acked-by: Halil Pasic --- Documentation/virtual/kvm/api.txt | 9 +++++++++ Documentation/virtual/kvm/devices/s390_flic.txt | 2 ++ arch/s390/kvm/kvm-s390.c | 1 + include/uapi/linux/kvm.h | 1 + 4 files changed, 13 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index e63a35fafef0..49540e53c4bd 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -4347,3 +4347,12 @@ This capability indicates that userspace can load HV_X64_MSR_VP_INDEX msr. Its value is used to denote the target vcpu for a SynIC interrupt. For compatibilty, KVM initializes this msr to KVM's internal vcpu index. When this capability is absent, userspace can still query this msr's value. + +8.13 KVM_CAP_S390_AIS_MIGRATION + +Architectures: s390 +Parameters: none + +This capability indicates if the flic device will be able to get/set the +AIS states for migration via the KVM_DEV_FLIC_AISM_ALL attribute and allows +to discover this without having to create a flic device. diff --git a/Documentation/virtual/kvm/devices/s390_flic.txt b/Documentation/virtual/kvm/devices/s390_flic.txt index 27ad53c7149d..a4e20a090174 100644 --- a/Documentation/virtual/kvm/devices/s390_flic.txt +++ b/Documentation/virtual/kvm/devices/s390_flic.txt @@ -151,6 +151,8 @@ struct kvm_s390_ais_all { to an ISC (MSB0 bit 0 to ISC 0 and so on). The combination of simm bit and nimm bit presents AIS mode for a ISC. + KVM_DEV_FLIC_AISM_ALL is indicated by KVM_CAP_S390_AIS_MIGRATION. + Note: The KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR device ioctls executed on FLIC with an unknown group or attribute gives the error code EINVAL (instead of ENXIO, as specified in the API documentation). It is not possible to conclude diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index de6a5b790da0..8f4b655f65d7 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -395,6 +395,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_USER_INSTR0: case KVM_CAP_S390_CMMA_MIGRATION: case KVM_CAP_S390_AIS: + case KVM_CAP_S390_AIS_MIGRATION: r = 1; break; case KVM_CAP_S390_MEM_OP: diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 838887587411..b60595696836 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -930,6 +930,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_PPC_SMT_POSSIBLE 147 #define KVM_CAP_HYPERV_SYNIC2 148 #define KVM_CAP_HYPERV_VP_INDEX 149 +#define KVM_CAP_S390_AIS_MIGRATION 150 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3-71-gd317 From 4d63adfe12dd9cb61ed8badb4d798955399048c2 Mon Sep 17 00:00:00 2001 From: Mark Greer Date: Thu, 15 Jun 2017 20:34:22 -0700 Subject: NFC: Add NFC_CMD_DEACTIVATE_TARGET support Once an NFC target (i.e., a tag) is found, it remains active until there is a failure reading or writing it (often caused by the target moving out of range). While the target is active, the NFC adapter and antenna must remain powered. This wastes power when the target remains in range but the client application no longer cares whether it is there or not. To mitigate this, add a new netlink command that allows userspace to deactivate an active target. When issued, this command will cause the NFC subsystem to act as though the target was moved out of range. Once the command has been executed, the client application can power off the NFC adapter to reduce power consumption. Signed-off-by: Mark Greer Signed-off-by: Samuel Ortiz --- include/uapi/linux/nfc.h | 2 ++ net/nfc/netlink.c | 29 +++++++++++++++++++++++++++++ 2 files changed, 31 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nfc.h b/include/uapi/linux/nfc.h index 399f39ff8048..f6e3c8c9c744 100644 --- a/include/uapi/linux/nfc.h +++ b/include/uapi/linux/nfc.h @@ -89,6 +89,7 @@ * @NFC_CMD_ACTIVATE_TARGET: Request NFC controller to reactivate target. * @NFC_CMD_VENDOR: Vendor specific command, to be implemented directly * from the driver in order to support hardware specific operations. + * @NFC_CMD_DEACTIVATE_TARGET: Request NFC controller to deactivate target. */ enum nfc_commands { NFC_CMD_UNSPEC, @@ -121,6 +122,7 @@ enum nfc_commands { NFC_CMD_SE_IO, NFC_CMD_ACTIVATE_TARGET, NFC_CMD_VENDOR, + NFC_CMD_DEACTIVATE_TARGET, /* private: internal use only */ __NFC_CMD_AFTER_LAST }; diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index b251fb936a27..f6359c277212 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -928,6 +928,30 @@ static int nfc_genl_activate_target(struct sk_buff *skb, struct genl_info *info) return rc; } +static int nfc_genl_deactivate_target(struct sk_buff *skb, + struct genl_info *info) +{ + struct nfc_dev *dev; + u32 device_idx, target_idx; + int rc; + + if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) + return -EINVAL; + + device_idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); + + dev = nfc_get_device(device_idx); + if (!dev) + return -ENODEV; + + target_idx = nla_get_u32(info->attrs[NFC_ATTR_TARGET_INDEX]); + + rc = nfc_deactivate_target(dev, target_idx, NFC_TARGET_MODE_SLEEP); + + nfc_put_device(dev); + return rc; +} + static int nfc_genl_dep_link_up(struct sk_buff *skb, struct genl_info *info) { struct nfc_dev *dev; @@ -1751,6 +1775,11 @@ static const struct genl_ops nfc_genl_ops[] = { .doit = nfc_genl_vendor_cmd, .policy = nfc_genl_policy, }, + { + .cmd = NFC_CMD_DEACTIVATE_TARGET, + .doit = nfc_genl_deactivate_target, + .policy = nfc_genl_policy, + }, }; static struct genl_family nfc_genl_family __ro_after_init = { -- cgit v1.2.3-71-gd317 From 42d5e37654e4cdb9fb2e2f3ab30045fee35c42d8 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Wed, 23 Aug 2017 07:03:39 -0400 Subject: audit: filter PATH records keyed on filesystem magic Tracefs or debugfs were causing hundreds to thousands of PATH records to be associated with the init_module and finit_module SYSCALL records on a few modules when the following rule was in place for startup: -a always,exit -F arch=x86_64 -S init_module -F key=mod-load Provide a method to ignore these large number of PATH records from overwhelming the logs if they are not of interest. Introduce a new filter list "AUDIT_FILTER_FS", with a new field type AUDIT_FSTYPE, which keys off the filesystem 4-octet hexadecimal magic identifier to filter specific filesystem PATH records. An example rule would look like: -a never,filesystem -F fstype=0x74726163 -F key=ignore_tracefs -a never,filesystem -F fstype=0x64626720 -F key=ignore_debugfs Arguably the better way to address this issue is to disable tracefs and debugfs on boot from production systems. See: https://github.com/linux-audit/audit-kernel/issues/16 See: https://github.com/linux-audit/audit-userspace/issues/8 Test case: https://github.com/linux-audit/audit-testsuite/issues/42 Signed-off-by: Richard Guy Briggs [PM: fixed the whitespace damage in kernel/auditsc.c] Signed-off-by: Paul Moore --- include/uapi/linux/audit.h | 8 ++++++-- kernel/auditfilter.c | 39 ++++++++++++++++++++++++++++++++------- kernel/auditsc.c | 23 +++++++++++++++++++++++ 3 files changed, 61 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index 0714a66f0e0c..be711341938e 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -155,8 +155,9 @@ #define AUDIT_FILTER_WATCH 0x03 /* Apply rule to file system watches */ #define AUDIT_FILTER_EXIT 0x04 /* Apply rule at syscall exit */ #define AUDIT_FILTER_TYPE 0x05 /* Apply rule at audit_log_start */ +#define AUDIT_FILTER_FS 0x06 /* Apply rule at __audit_inode_child */ -#define AUDIT_NR_FILTERS 6 +#define AUDIT_NR_FILTERS 7 #define AUDIT_FILTER_PREPEND 0x10 /* Prepend to front of list */ @@ -256,6 +257,7 @@ #define AUDIT_OBJ_LEV_HIGH 23 #define AUDIT_LOGINUID_SET 24 #define AUDIT_SESSIONID 25 /* Session ID */ +#define AUDIT_FSTYPE 26 /* FileSystem Type */ /* These are ONLY useful when checking * at syscall exit time (AUDIT_AT_EXIT). */ @@ -335,13 +337,15 @@ enum { #define AUDIT_FEATURE_BITMAP_EXCLUDE_EXTEND 0x00000008 #define AUDIT_FEATURE_BITMAP_SESSIONID_FILTER 0x00000010 #define AUDIT_FEATURE_BITMAP_LOST_RESET 0x00000020 +#define AUDIT_FEATURE_BITMAP_FILTER_FS 0x00000040 #define AUDIT_FEATURE_BITMAP_ALL (AUDIT_FEATURE_BITMAP_BACKLOG_LIMIT | \ AUDIT_FEATURE_BITMAP_BACKLOG_WAIT_TIME | \ AUDIT_FEATURE_BITMAP_EXECUTABLE_PATH | \ AUDIT_FEATURE_BITMAP_EXCLUDE_EXTEND | \ AUDIT_FEATURE_BITMAP_SESSIONID_FILTER | \ - AUDIT_FEATURE_BITMAP_LOST_RESET) + AUDIT_FEATURE_BITMAP_LOST_RESET | \ + AUDIT_FEATURE_BITMAP_FILTER_FS) /* deprecated: AUDIT_VERSION_* */ #define AUDIT_VERSION_LATEST AUDIT_FEATURE_BITMAP_ALL diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 0b0aa5854dac..4a1758adb222 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -56,7 +56,8 @@ struct list_head audit_filter_list[AUDIT_NR_FILTERS] = { LIST_HEAD_INIT(audit_filter_list[3]), LIST_HEAD_INIT(audit_filter_list[4]), LIST_HEAD_INIT(audit_filter_list[5]), -#if AUDIT_NR_FILTERS != 6 + LIST_HEAD_INIT(audit_filter_list[6]), +#if AUDIT_NR_FILTERS != 7 #error Fix audit_filter_list initialiser #endif }; @@ -67,6 +68,7 @@ static struct list_head audit_rules_list[AUDIT_NR_FILTERS] = { LIST_HEAD_INIT(audit_rules_list[3]), LIST_HEAD_INIT(audit_rules_list[4]), LIST_HEAD_INIT(audit_rules_list[5]), + LIST_HEAD_INIT(audit_rules_list[6]), }; DEFINE_MUTEX(audit_filter_mutex); @@ -263,6 +265,7 @@ static inline struct audit_entry *audit_to_entry_common(struct audit_rule_data * #endif case AUDIT_FILTER_USER: case AUDIT_FILTER_TYPE: + case AUDIT_FILTER_FS: ; } if (unlikely(rule->action == AUDIT_POSSIBLE)) { @@ -338,6 +341,21 @@ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f) entry->rule.listnr != AUDIT_FILTER_USER) return -EINVAL; break; + case AUDIT_FSTYPE: + if (entry->rule.listnr != AUDIT_FILTER_FS) + return -EINVAL; + break; + } + + switch(entry->rule.listnr) { + case AUDIT_FILTER_FS: + switch(f->type) { + case AUDIT_FSTYPE: + case AUDIT_FILTERKEY: + break; + default: + return -EINVAL; + } } switch(f->type) { @@ -391,6 +409,7 @@ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f) return -EINVAL; /* FALL THROUGH */ case AUDIT_ARCH: + case AUDIT_FSTYPE: if (f->op != Audit_not_equal && f->op != Audit_equal) return -EINVAL; break; @@ -910,10 +929,13 @@ static inline int audit_add_rule(struct audit_entry *entry) #ifdef CONFIG_AUDITSYSCALL int dont_count = 0; - /* If either of these, don't count towards total */ - if (entry->rule.listnr == AUDIT_FILTER_USER || - entry->rule.listnr == AUDIT_FILTER_TYPE) + /* If any of these, don't count towards total */ + switch(entry->rule.listnr) { + case AUDIT_FILTER_USER: + case AUDIT_FILTER_TYPE: + case AUDIT_FILTER_FS: dont_count = 1; + } #endif mutex_lock(&audit_filter_mutex); @@ -989,10 +1011,13 @@ int audit_del_rule(struct audit_entry *entry) #ifdef CONFIG_AUDITSYSCALL int dont_count = 0; - /* If either of these, don't count towards total */ - if (entry->rule.listnr == AUDIT_FILTER_USER || - entry->rule.listnr == AUDIT_FILTER_TYPE) + /* If any of these, don't count towards total */ + switch(entry->rule.listnr) { + case AUDIT_FILTER_USER: + case AUDIT_FILTER_TYPE: + case AUDIT_FILTER_FS: dont_count = 1; + } #endif mutex_lock(&audit_filter_mutex); diff --git a/kernel/auditsc.c b/kernel/auditsc.c index aac1a41f82bd..c9bb29e17335 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1869,10 +1869,33 @@ void __audit_inode_child(struct inode *parent, struct inode *inode = d_backing_inode(dentry); const char *dname = dentry->d_name.name; struct audit_names *n, *found_parent = NULL, *found_child = NULL; + struct audit_entry *e; + struct list_head *list = &audit_filter_list[AUDIT_FILTER_FS]; + int i; if (!context->in_syscall) return; + rcu_read_lock(); + if (!list_empty(list)) { + list_for_each_entry_rcu(e, list, list) { + for (i = 0; i < e->rule.field_count; i++) { + struct audit_field *f = &e->rule.fields[i]; + + if (f->type == AUDIT_FSTYPE) { + if (audit_comparator(parent->i_sb->s_magic, + f->op, f->val)) { + if (e->rule.action == AUDIT_NEVER) { + rcu_read_unlock(); + return; + } + } + } + } + } + } + rcu_read_unlock(); + if (inode) handle_one(inode); -- cgit v1.2.3-71-gd317 From dd0bb688eaa241b5655d396d45366cba9225aed9 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 7 Nov 2017 15:28:42 -0500 Subject: bpf: add a bpf_override_function helper Error injection is sloppy and very ad-hoc. BPF could fill this niche perfectly with it's kprobe functionality. We could make sure errors are only triggered in specific call chains that we care about with very specific situations. Accomplish this with the bpf_override_funciton helper. This will modify the probe'd callers return value to the specified value and set the PC to an override function that simply returns, bypassing the originally probed function. This gives us a nice clean way to implement systematic error injection for all of our code paths. Acked-by: Alexei Starovoitov Signed-off-by: Josef Bacik Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- arch/Kconfig | 3 +++ arch/x86/Kconfig | 1 + arch/x86/include/asm/kprobes.h | 4 ++++ arch/x86/include/asm/ptrace.h | 5 +++++ arch/x86/kernel/kprobes/ftrace.c | 14 ++++++++++++++ include/linux/filter.h | 3 ++- include/linux/trace_events.h | 1 + include/uapi/linux/bpf.h | 7 ++++++- kernel/bpf/core.c | 3 +++ kernel/bpf/verifier.c | 2 ++ kernel/events/core.c | 7 +++++++ kernel/trace/Kconfig | 11 +++++++++++ kernel/trace/bpf_trace.c | 35 +++++++++++++++++++++++++++++++++++ kernel/trace/trace_kprobe.c | 40 +++++++++++++++++++++++++++++++++------- kernel/trace/trace_probe.h | 6 ++++++ 15 files changed, 133 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/Kconfig b/arch/Kconfig index 057370a0ac4e..6e8520f09bc1 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -196,6 +196,9 @@ config HAVE_OPTPROBES config HAVE_KPROBES_ON_FTRACE bool +config HAVE_KPROBE_OVERRIDE + bool + config HAVE_NMI bool diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 2fdb23313dd5..51458c1a0b4a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -153,6 +153,7 @@ config X86 select HAVE_KERNEL_XZ select HAVE_KPROBES select HAVE_KPROBES_ON_FTRACE + select HAVE_KPROBE_OVERRIDE select HAVE_KRETPROBES select HAVE_KVM select HAVE_LIVEPATCH if X86_64 diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 6cf65437b5e5..c6c3b1f4306a 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -67,6 +67,10 @@ extern const int kretprobe_blacklist_size; void arch_remove_kprobe(struct kprobe *p); asmlinkage void kretprobe_trampoline(void); +#ifdef CONFIG_KPROBES_ON_FTRACE +extern void arch_ftrace_kprobe_override_function(struct pt_regs *regs); +#endif + /* Architecture specific copy of original instruction*/ struct arch_specific_insn { /* copy of the original instruction */ diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index c0e3c45cf6ab..2370bb0149cc 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -109,6 +109,11 @@ static inline unsigned long regs_return_value(struct pt_regs *regs) return regs->ax; } +static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc) +{ + regs->ax = rc; +} + /* * user_mode(regs) determines whether a register set came from user * mode. On x86_32, this is true if V8086 mode was enabled OR if the diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c index 041f7b6dfa0f..3c455bf490cb 100644 --- a/arch/x86/kernel/kprobes/ftrace.c +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -97,3 +97,17 @@ int arch_prepare_kprobe_ftrace(struct kprobe *p) p->ainsn.boostable = false; return 0; } + +asmlinkage void override_func(void); +asm( + ".type override_func, @function\n" + "override_func:\n" + " ret\n" + ".size override_func, .-override_func\n" +); + +void arch_ftrace_kprobe_override_function(struct pt_regs *regs) +{ + regs->ip = (unsigned long)&override_func; +} +NOKPROBE_SYMBOL(arch_ftrace_kprobe_override_function); diff --git a/include/linux/filter.h b/include/linux/filter.h index 0cd02ff4ae30..eaec066f99e8 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -459,7 +459,8 @@ struct bpf_prog { locked:1, /* Program image locked? */ gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ - dst_needed:1; /* Do we need dst entry? */ + dst_needed:1, /* Do we need dst entry? */ + kprobe_override:1; /* Do we override a kprobe? */ kmemcheck_bitfield_end(meta); enum bpf_prog_type type; /* Type of BPF program */ u32 len; /* Number of filter blocks */ diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 84014ecfa67f..17e5e820a84c 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -523,6 +523,7 @@ do { \ struct perf_event; DECLARE_PER_CPU(struct pt_regs, perf_trace_regs); +DECLARE_PER_CPU(int, bpf_kprobe_override); extern int perf_trace_init(struct perf_event *event); extern void perf_trace_destroy(struct perf_event *event); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e880ae6434ee..adb66f78b674 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -677,6 +677,10 @@ union bpf_attr { * @buf: buf to fill * @buf_size: size of the buf * Return : 0 on success or negative error code + * + * int bpf_override_return(pt_regs, rc) + * @pt_regs: pointer to struct pt_regs + * @rc: the return value to set */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -736,7 +740,8 @@ union bpf_attr { FN(xdp_adjust_meta), \ FN(perf_event_read_value), \ FN(perf_prog_read_value), \ - FN(getsockopt), + FN(getsockopt), \ + FN(override_return), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 8a6c37762330..271daad31f37 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1326,6 +1326,9 @@ EVAL4(PROG_NAME_LIST, 416, 448, 480, 512) bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp) { + if (fp->kprobe_override) + return false; + if (!array->owner_prog_type) { /* There's no owner yet where we could check for * compatibility. diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 4a942e2e753d..bc464b8ec91e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4357,6 +4357,8 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) prog->dst_needed = 1; if (insn->imm == BPF_FUNC_get_prandom_u32) bpf_user_rnd_init_once(); + if (insn->imm == BPF_FUNC_override_return) + prog->kprobe_override = 1; if (insn->imm == BPF_FUNC_tail_call) { /* If we tail call into other programs, we * cannot make any assumptions since they can diff --git a/kernel/events/core.c b/kernel/events/core.c index 42d24bd64ea4..ac240d31b5bf 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8171,6 +8171,13 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd) return -EINVAL; } + /* Kprobe override only works for kprobes, not uprobes. */ + if (prog->kprobe_override && + !(event->tp_event->flags & TRACE_EVENT_FL_KPROBE)) { + bpf_prog_put(prog); + return -EINVAL; + } + if (is_tracepoint || is_syscall_tp) { int off = trace_event_get_offsets(event->tp_event); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 434c840e2d82..9dc0deeaad2b 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -518,6 +518,17 @@ config FUNCTION_PROFILER If in doubt, say N. +config BPF_KPROBE_OVERRIDE + bool "Enable BPF programs to override a kprobed function" + depends on BPF_EVENTS + depends on KPROBES_ON_FTRACE + depends on HAVE_KPROBE_OVERRIDE + depends on DYNAMIC_FTRACE_WITH_REGS + default n + help + Allows BPF to override the execution of a probed function and + set a different return value. This is used for error injection. + config FTRACE_MCOUNT_RECORD def_bool y depends on DYNAMIC_FTRACE diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 506efe6e8ed9..1865b0d4cdeb 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -13,6 +13,10 @@ #include #include #include +#include +#include + +#include "trace_probe.h" #include "trace.h" u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); @@ -76,6 +80,29 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) } EXPORT_SYMBOL_GPL(trace_call_bpf); +#ifdef CONFIG_BPF_KPROBE_OVERRIDE +BPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc) +{ + __this_cpu_write(bpf_kprobe_override, 1); + regs_set_return_value(regs, rc); + arch_ftrace_kprobe_override_function(regs); + return 0; +} +#else +BPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc) +{ + return -EINVAL; +} +#endif + +static const struct bpf_func_proto bpf_override_return_proto = { + .func = bpf_override_return, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; + BPF_CALL_3(bpf_probe_read, void *, dst, u32, size, const void *, unsafe_ptr) { int ret; @@ -551,6 +578,10 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func return &bpf_get_stackid_proto; case BPF_FUNC_perf_event_read_value: return &bpf_perf_event_read_value_proto; + case BPF_FUNC_override_return: + pr_warn_ratelimited("%s[%d] is installing a program with bpf_override_return helper that may cause unexpected behavior!", + current->comm, task_pid_nr(current)); + return &bpf_override_return_proto; default: return tracing_func_proto(func_id); } @@ -766,6 +797,10 @@ int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog_array *new_array; int ret = -EEXIST; + /* Kprobe override only works for ftrace based kprobes. */ + if (prog->kprobe_override && !trace_kprobe_ftrace(event->tp_event)) + return -EINVAL; + mutex_lock(&bpf_event_mutex); if (event->prog) diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index abf92e478cfb..8e3c9ec1faf7 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -42,6 +42,7 @@ struct trace_kprobe { (offsetof(struct trace_kprobe, tp.args) + \ (sizeof(struct probe_arg) * (n))) +DEFINE_PER_CPU(int, bpf_kprobe_override); static nokprobe_inline bool trace_kprobe_is_return(struct trace_kprobe *tk) { @@ -87,6 +88,12 @@ static nokprobe_inline unsigned long trace_kprobe_nhit(struct trace_kprobe *tk) return nhit; } +int trace_kprobe_ftrace(struct trace_event_call *call) +{ + struct trace_kprobe *tk = (struct trace_kprobe *)call->data; + return kprobe_ftrace(&tk->rp.kp); +} + static int register_kprobe_event(struct trace_kprobe *tk); static int unregister_kprobe_event(struct trace_kprobe *tk); @@ -1170,7 +1177,7 @@ static int kretprobe_event_define_fields(struct trace_event_call *event_call) #ifdef CONFIG_PERF_EVENTS /* Kprobe profile handler */ -static void +static int kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) { struct trace_event_call *call = &tk->tp.call; @@ -1179,12 +1186,29 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) int size, __size, dsize; int rctx; - if (bpf_prog_array_valid(call) && !trace_call_bpf(call, regs)) - return; + if (bpf_prog_array_valid(call)) { + int ret; + + ret = trace_call_bpf(call, regs); + + /* + * We need to check and see if we modified the pc of the + * pt_regs, and if so clear the kprobe and return 1 so that we + * don't do the instruction skipping. Also reset our state so + * we are clean the next pass through. + */ + if (__this_cpu_read(bpf_kprobe_override)) { + __this_cpu_write(bpf_kprobe_override, 0); + reset_current_kprobe(); + return 1; + } + if (!ret) + return 0; + } head = this_cpu_ptr(call->perf_events); if (hlist_empty(head)) - return; + return 0; dsize = __get_data_size(&tk->tp, regs); __size = sizeof(*entry) + tk->tp.size + dsize; @@ -1193,13 +1217,14 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) entry = perf_trace_buf_alloc(size, NULL, &rctx); if (!entry) - return; + return 0; entry->ip = (unsigned long)tk->rp.kp.addr; memset(&entry[1], 0, dsize); store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL, NULL); + return 0; } NOKPROBE_SYMBOL(kprobe_perf_func); @@ -1275,6 +1300,7 @@ static int kprobe_register(struct trace_event_call *event, static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs) { struct trace_kprobe *tk = container_of(kp, struct trace_kprobe, rp.kp); + int ret = 0; raw_cpu_inc(*tk->nhit); @@ -1282,9 +1308,9 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs) kprobe_trace_func(tk, regs); #ifdef CONFIG_PERF_EVENTS if (tk->tp.flags & TP_FLAG_PROFILE) - kprobe_perf_func(tk, regs); + ret = kprobe_perf_func(tk, regs); #endif - return 0; /* We don't tweek kernel, so just return 0 */ + return ret; } NOKPROBE_SYMBOL(kprobe_dispatcher); diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 903273c93e61..adbb3f7d1fb5 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -253,6 +253,7 @@ struct symbol_cache; unsigned long update_symbol_cache(struct symbol_cache *sc); void free_symbol_cache(struct symbol_cache *sc); struct symbol_cache *alloc_symbol_cache(const char *sym, long offset); +int trace_kprobe_ftrace(struct trace_event_call *call); #else /* uprobes do not support symbol fetch methods */ #define fetch_symbol_u8 NULL @@ -278,6 +279,11 @@ alloc_symbol_cache(const char *sym, long offset) { return NULL; } + +static inline int trace_kprobe_ftrace(struct trace_event_call *call) +{ + return 0; +} #endif /* CONFIG_KPROBE_EVENTS */ struct probe_arg { -- cgit v1.2.3-71-gd317 From 2210d6b2f287d738eddf6b75f432126ce05450f8 Mon Sep 17 00:00:00 2001 From: Maciej Żenczykowski Date: Tue, 7 Nov 2017 21:52:09 -0800 Subject: net: ipv6: sysctl to specify IPv6 ND traffic class MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a per-device sysctl to specify the default traffic class to use for kernel originated IPv6 Neighbour Discovery packets. Currently this includes: - Router Solicitation (ICMPv6 type 133) ndisc_send_rs() -> ndisc_send_skb() -> ip6_nd_hdr() - Neighbour Solicitation (ICMPv6 type 135) ndisc_send_ns() -> ndisc_send_skb() -> ip6_nd_hdr() - Neighbour Advertisement (ICMPv6 type 136) ndisc_send_na() -> ndisc_send_skb() -> ip6_nd_hdr() - Redirect (ICMPv6 type 137) ndisc_send_redirect() -> ndisc_send_skb() -> ip6_nd_hdr() and if the kernel ever gets around to generating RA's, it would presumably also include: - Router Advertisement (ICMPv6 type 134) (radvd daemon could pick up on the kernel setting and use it) Interface drivers may examine the Traffic Class value and translate the DiffServ Code Point into a link-layer appropriate traffic prioritization scheme. An example of mapping IETF DSCP values to IEEE 802.11 User Priority values can be found here: https://tools.ietf.org/html/draft-ietf-tsvwg-ieee-802-11 The expected primary use case is to properly prioritize ND over wifi. Testing: jzem22:~# cat /proc/sys/net/ipv6/conf/eth0/ndisc_tclass 0 jzem22:~# echo -1 > /proc/sys/net/ipv6/conf/eth0/ndisc_tclass -bash: echo: write error: Invalid argument jzem22:~# echo 256 > /proc/sys/net/ipv6/conf/eth0/ndisc_tclass -bash: echo: write error: Invalid argument jzem22:~# echo 0 > /proc/sys/net/ipv6/conf/eth0/ndisc_tclass jzem22:~# echo 255 > /proc/sys/net/ipv6/conf/eth0/ndisc_tclass jzem22:~# cat /proc/sys/net/ipv6/conf/eth0/ndisc_tclass 255 jzem22:~# echo 34 > /proc/sys/net/ipv6/conf/eth0/ndisc_tclass jzem22:~# cat /proc/sys/net/ipv6/conf/eth0/ndisc_tclass 34 jzem22:~# echo $[0xDC] > /proc/sys/net/ipv6/conf/eth0/ndisc_tclass jzem22:~# tcpdump -v -i eth0 icmp6 and src host jzem22.pgc and dst host fe80::1 tcpdump: listening on eth0, link-type EN10MB (Ethernet), capture size 262144 bytes IP6 (class 0xdc, hlim 255, next-header ICMPv6 (58) payload length: 24) jzem22.pgc > fe80::1: [icmp6 sum ok] ICMP6, neighbor advertisement, length 24, tgt is jzem22.pgc, Flags [solicited] (based on original change written by Erik Kline, with minor changes) v2: fix 'suspicious rcu_dereference_check() usage' by explicitly grabbing the rcu_read_lock. Cc: Lorenzo Colitti Signed-off-by: Erik Kline Signed-off-by: Maciej Żenczykowski Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 9 +++++++++ include/linux/ipv6.h | 1 + include/uapi/linux/ipv6.h | 1 + net/ipv6/addrconf.c | 11 +++++++++++ net/ipv6/ndisc.c | 9 ++++++++- 5 files changed, 30 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 54410a1d4065..d8676dda7fa6 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -1732,6 +1732,15 @@ ndisc_notify - BOOLEAN 1 - Generate unsolicited neighbour advertisements when device is brought up or hardware address changes. +ndisc_tclass - INTEGER + The IPv6 Traffic Class to use by default when sending IPv6 Neighbor + Discovery (Router Solicitation, Router Advertisement, Neighbor + Solicitation, Neighbor Advertisement, Redirect) messages. + These 8 bits can be interpreted as 6 high order bits holding the DSCP + value and 2 low order bits representing ECN (which you probably want + to leave cleared). + 0 - (default) + mldv1_unsolicited_report_interval - INTEGER The interval in milliseconds in which the next unsolicited MLDv1 report retransmit will take place. diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index ea04ca024f0d..cb18c6290ca8 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -73,6 +73,7 @@ struct ipv6_devconf { __u32 enhanced_dad; __u32 addr_gen_mode; __s32 disable_policy; + __s32 ndisc_tclass; struct ctl_table_header *sysctl_header; }; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index b22a9c4e1b12..9c0f4a92bcff 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -186,6 +186,7 @@ enum { DEVCONF_ADDR_GEN_MODE, DEVCONF_DISABLE_POLICY, DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN, + DEVCONF_NDISC_TCLASS, DEVCONF_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 6233e06fa35c..a6dffd65eb9d 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5059,6 +5059,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_ENHANCED_DAD] = cnf->enhanced_dad; array[DEVCONF_ADDR_GEN_MODE] = cnf->addr_gen_mode; array[DEVCONF_DISABLE_POLICY] = cnf->disable_policy; + array[DEVCONF_NDISC_TCLASS] = cnf->ndisc_tclass; } static inline size_t inet6_ifla6_size(void) @@ -5986,6 +5987,7 @@ int addrconf_sysctl_disable_policy(struct ctl_table *ctl, int write, } static int minus_one = -1; +static const int zero = 0; static const int one = 1; static const int two_five_five = 255; @@ -6356,6 +6358,15 @@ static const struct ctl_table addrconf_sysctl[] = { .mode = 0644, .proc_handler = addrconf_sysctl_disable_policy, }, + { + .procname = "ndisc_tclass", + .data = &ipv6_devconf.ndisc_tclass, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&zero, + .extra2 = (void *)&two_five_five, + }, { /* sentinel */ } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index f9c3ffe04382..b3cea200c85e 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -427,12 +427,19 @@ static void ip6_nd_hdr(struct sk_buff *skb, int hop_limit, int len) { struct ipv6hdr *hdr; + struct inet6_dev *idev; + unsigned tclass; + + rcu_read_lock(); + idev = __in6_dev_get(skb->dev); + tclass = idev ? idev->cnf.ndisc_tclass : 0; + rcu_read_unlock(); skb_push(skb, sizeof(*hdr)); skb_reset_network_header(skb); hdr = ipv6_hdr(skb); - ip6_flow_hdr(hdr, 0, 0); + ip6_flow_hdr(hdr, tclass, 0); hdr->payload_len = htons(len); hdr->nexthdr = IPPROTO_ICMPV6; -- cgit v1.2.3-71-gd317 From f3edacbd697f94a743fff1a3d26910ab99948ba7 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sat, 11 Nov 2017 18:24:55 +0900 Subject: bpf: Revert bpf_overrid_function() helper changes. NACK'd by x86 maintainer. Signed-off-by: David S. Miller --- arch/Kconfig | 3 --- arch/x86/Kconfig | 1 - arch/x86/include/asm/kprobes.h | 4 ---- arch/x86/include/asm/ptrace.h | 5 ---- arch/x86/kernel/kprobes/ftrace.c | 14 ----------- include/linux/filter.h | 3 +-- include/linux/trace_events.h | 1 - include/uapi/linux/bpf.h | 7 +----- kernel/bpf/core.c | 3 --- kernel/bpf/verifier.c | 2 -- kernel/events/core.c | 7 ------ kernel/trace/Kconfig | 11 --------- kernel/trace/bpf_trace.c | 35 --------------------------- kernel/trace/trace_kprobe.c | 40 ++++++------------------------- kernel/trace/trace_probe.h | 6 ----- samples/bpf/Makefile | 4 ---- samples/bpf/test_override_return.sh | 15 ------------ samples/bpf/tracex7_kern.c | 16 ------------- samples/bpf/tracex7_user.c | 28 ---------------------- tools/include/uapi/linux/bpf.h | 7 +----- tools/testing/selftests/bpf/bpf_helpers.h | 3 +-- 21 files changed, 11 insertions(+), 204 deletions(-) delete mode 100755 samples/bpf/test_override_return.sh delete mode 100644 samples/bpf/tracex7_kern.c delete mode 100644 samples/bpf/tracex7_user.c (limited to 'include/uapi/linux') diff --git a/arch/Kconfig b/arch/Kconfig index 6e8520f09bc1..057370a0ac4e 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -196,9 +196,6 @@ config HAVE_OPTPROBES config HAVE_KPROBES_ON_FTRACE bool -config HAVE_KPROBE_OVERRIDE - bool - config HAVE_NMI bool diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 51458c1a0b4a..2fdb23313dd5 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -153,7 +153,6 @@ config X86 select HAVE_KERNEL_XZ select HAVE_KPROBES select HAVE_KPROBES_ON_FTRACE - select HAVE_KPROBE_OVERRIDE select HAVE_KRETPROBES select HAVE_KVM select HAVE_LIVEPATCH if X86_64 diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index c6c3b1f4306a..6cf65437b5e5 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -67,10 +67,6 @@ extern const int kretprobe_blacklist_size; void arch_remove_kprobe(struct kprobe *p); asmlinkage void kretprobe_trampoline(void); -#ifdef CONFIG_KPROBES_ON_FTRACE -extern void arch_ftrace_kprobe_override_function(struct pt_regs *regs); -#endif - /* Architecture specific copy of original instruction*/ struct arch_specific_insn { /* copy of the original instruction */ diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 2370bb0149cc..c0e3c45cf6ab 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -109,11 +109,6 @@ static inline unsigned long regs_return_value(struct pt_regs *regs) return regs->ax; } -static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc) -{ - regs->ax = rc; -} - /* * user_mode(regs) determines whether a register set came from user * mode. On x86_32, this is true if V8086 mode was enabled OR if the diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c index 3c455bf490cb..041f7b6dfa0f 100644 --- a/arch/x86/kernel/kprobes/ftrace.c +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -97,17 +97,3 @@ int arch_prepare_kprobe_ftrace(struct kprobe *p) p->ainsn.boostable = false; return 0; } - -asmlinkage void override_func(void); -asm( - ".type override_func, @function\n" - "override_func:\n" - " ret\n" - ".size override_func, .-override_func\n" -); - -void arch_ftrace_kprobe_override_function(struct pt_regs *regs) -{ - regs->ip = (unsigned long)&override_func; -} -NOKPROBE_SYMBOL(arch_ftrace_kprobe_override_function); diff --git a/include/linux/filter.h b/include/linux/filter.h index eaec066f99e8..0cd02ff4ae30 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -459,8 +459,7 @@ struct bpf_prog { locked:1, /* Program image locked? */ gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ - dst_needed:1, /* Do we need dst entry? */ - kprobe_override:1; /* Do we override a kprobe? */ + dst_needed:1; /* Do we need dst entry? */ kmemcheck_bitfield_end(meta); enum bpf_prog_type type; /* Type of BPF program */ u32 len; /* Number of filter blocks */ diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 17e5e820a84c..84014ecfa67f 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -523,7 +523,6 @@ do { \ struct perf_event; DECLARE_PER_CPU(struct pt_regs, perf_trace_regs); -DECLARE_PER_CPU(int, bpf_kprobe_override); extern int perf_trace_init(struct perf_event *event); extern void perf_trace_destroy(struct perf_event *event); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index adb66f78b674..e880ae6434ee 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -677,10 +677,6 @@ union bpf_attr { * @buf: buf to fill * @buf_size: size of the buf * Return : 0 on success or negative error code - * - * int bpf_override_return(pt_regs, rc) - * @pt_regs: pointer to struct pt_regs - * @rc: the return value to set */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -740,8 +736,7 @@ union bpf_attr { FN(xdp_adjust_meta), \ FN(perf_event_read_value), \ FN(perf_prog_read_value), \ - FN(getsockopt), \ - FN(override_return), + FN(getsockopt), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 271daad31f37..8a6c37762330 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1326,9 +1326,6 @@ EVAL4(PROG_NAME_LIST, 416, 448, 480, 512) bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp) { - if (fp->kprobe_override) - return false; - if (!array->owner_prog_type) { /* There's no owner yet where we could check for * compatibility. diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index bc464b8ec91e..4a942e2e753d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4357,8 +4357,6 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) prog->dst_needed = 1; if (insn->imm == BPF_FUNC_get_prandom_u32) bpf_user_rnd_init_once(); - if (insn->imm == BPF_FUNC_override_return) - prog->kprobe_override = 1; if (insn->imm == BPF_FUNC_tail_call) { /* If we tail call into other programs, we * cannot make any assumptions since they can diff --git a/kernel/events/core.c b/kernel/events/core.c index ac240d31b5bf..42d24bd64ea4 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8171,13 +8171,6 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd) return -EINVAL; } - /* Kprobe override only works for kprobes, not uprobes. */ - if (prog->kprobe_override && - !(event->tp_event->flags & TRACE_EVENT_FL_KPROBE)) { - bpf_prog_put(prog); - return -EINVAL; - } - if (is_tracepoint || is_syscall_tp) { int off = trace_event_get_offsets(event->tp_event); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 9dc0deeaad2b..434c840e2d82 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -518,17 +518,6 @@ config FUNCTION_PROFILER If in doubt, say N. -config BPF_KPROBE_OVERRIDE - bool "Enable BPF programs to override a kprobed function" - depends on BPF_EVENTS - depends on KPROBES_ON_FTRACE - depends on HAVE_KPROBE_OVERRIDE - depends on DYNAMIC_FTRACE_WITH_REGS - default n - help - Allows BPF to override the execution of a probed function and - set a different return value. This is used for error injection. - config FTRACE_MCOUNT_RECORD def_bool y depends on DYNAMIC_FTRACE diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 1865b0d4cdeb..506efe6e8ed9 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -13,10 +13,6 @@ #include #include #include -#include -#include - -#include "trace_probe.h" #include "trace.h" u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); @@ -80,29 +76,6 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) } EXPORT_SYMBOL_GPL(trace_call_bpf); -#ifdef CONFIG_BPF_KPROBE_OVERRIDE -BPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc) -{ - __this_cpu_write(bpf_kprobe_override, 1); - regs_set_return_value(regs, rc); - arch_ftrace_kprobe_override_function(regs); - return 0; -} -#else -BPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc) -{ - return -EINVAL; -} -#endif - -static const struct bpf_func_proto bpf_override_return_proto = { - .func = bpf_override_return, - .gpl_only = true, - .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_ANYTHING, -}; - BPF_CALL_3(bpf_probe_read, void *, dst, u32, size, const void *, unsafe_ptr) { int ret; @@ -578,10 +551,6 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func return &bpf_get_stackid_proto; case BPF_FUNC_perf_event_read_value: return &bpf_perf_event_read_value_proto; - case BPF_FUNC_override_return: - pr_warn_ratelimited("%s[%d] is installing a program with bpf_override_return helper that may cause unexpected behavior!", - current->comm, task_pid_nr(current)); - return &bpf_override_return_proto; default: return tracing_func_proto(func_id); } @@ -797,10 +766,6 @@ int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog_array *new_array; int ret = -EEXIST; - /* Kprobe override only works for ftrace based kprobes. */ - if (prog->kprobe_override && !trace_kprobe_ftrace(event->tp_event)) - return -EINVAL; - mutex_lock(&bpf_event_mutex); if (event->prog) diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 8e3c9ec1faf7..abf92e478cfb 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -42,7 +42,6 @@ struct trace_kprobe { (offsetof(struct trace_kprobe, tp.args) + \ (sizeof(struct probe_arg) * (n))) -DEFINE_PER_CPU(int, bpf_kprobe_override); static nokprobe_inline bool trace_kprobe_is_return(struct trace_kprobe *tk) { @@ -88,12 +87,6 @@ static nokprobe_inline unsigned long trace_kprobe_nhit(struct trace_kprobe *tk) return nhit; } -int trace_kprobe_ftrace(struct trace_event_call *call) -{ - struct trace_kprobe *tk = (struct trace_kprobe *)call->data; - return kprobe_ftrace(&tk->rp.kp); -} - static int register_kprobe_event(struct trace_kprobe *tk); static int unregister_kprobe_event(struct trace_kprobe *tk); @@ -1177,7 +1170,7 @@ static int kretprobe_event_define_fields(struct trace_event_call *event_call) #ifdef CONFIG_PERF_EVENTS /* Kprobe profile handler */ -static int +static void kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) { struct trace_event_call *call = &tk->tp.call; @@ -1186,29 +1179,12 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) int size, __size, dsize; int rctx; - if (bpf_prog_array_valid(call)) { - int ret; - - ret = trace_call_bpf(call, regs); - - /* - * We need to check and see if we modified the pc of the - * pt_regs, and if so clear the kprobe and return 1 so that we - * don't do the instruction skipping. Also reset our state so - * we are clean the next pass through. - */ - if (__this_cpu_read(bpf_kprobe_override)) { - __this_cpu_write(bpf_kprobe_override, 0); - reset_current_kprobe(); - return 1; - } - if (!ret) - return 0; - } + if (bpf_prog_array_valid(call) && !trace_call_bpf(call, regs)) + return; head = this_cpu_ptr(call->perf_events); if (hlist_empty(head)) - return 0; + return; dsize = __get_data_size(&tk->tp, regs); __size = sizeof(*entry) + tk->tp.size + dsize; @@ -1217,14 +1193,13 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) entry = perf_trace_buf_alloc(size, NULL, &rctx); if (!entry) - return 0; + return; entry->ip = (unsigned long)tk->rp.kp.addr; memset(&entry[1], 0, dsize); store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL, NULL); - return 0; } NOKPROBE_SYMBOL(kprobe_perf_func); @@ -1300,7 +1275,6 @@ static int kprobe_register(struct trace_event_call *event, static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs) { struct trace_kprobe *tk = container_of(kp, struct trace_kprobe, rp.kp); - int ret = 0; raw_cpu_inc(*tk->nhit); @@ -1308,9 +1282,9 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs) kprobe_trace_func(tk, regs); #ifdef CONFIG_PERF_EVENTS if (tk->tp.flags & TP_FLAG_PROFILE) - ret = kprobe_perf_func(tk, regs); + kprobe_perf_func(tk, regs); #endif - return ret; + return 0; /* We don't tweek kernel, so just return 0 */ } NOKPROBE_SYMBOL(kprobe_dispatcher); diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index adbb3f7d1fb5..903273c93e61 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -253,7 +253,6 @@ struct symbol_cache; unsigned long update_symbol_cache(struct symbol_cache *sc); void free_symbol_cache(struct symbol_cache *sc); struct symbol_cache *alloc_symbol_cache(const char *sym, long offset); -int trace_kprobe_ftrace(struct trace_event_call *call); #else /* uprobes do not support symbol fetch methods */ #define fetch_symbol_u8 NULL @@ -279,11 +278,6 @@ alloc_symbol_cache(const char *sym, long offset) { return NULL; } - -static inline int trace_kprobe_ftrace(struct trace_event_call *call) -{ - return 0; -} #endif /* CONFIG_KPROBE_EVENTS */ struct probe_arg { diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 87db0f9a4c15..3b4945c1eab0 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -15,7 +15,6 @@ hostprogs-y += tracex3 hostprogs-y += tracex4 hostprogs-y += tracex5 hostprogs-y += tracex6 -hostprogs-y += tracex7 hostprogs-y += test_probe_write_user hostprogs-y += trace_output hostprogs-y += lathist @@ -62,7 +61,6 @@ tracex3-objs := bpf_load.o $(LIBBPF) tracex3_user.o tracex4-objs := bpf_load.o $(LIBBPF) tracex4_user.o tracex5-objs := bpf_load.o $(LIBBPF) tracex5_user.o tracex6-objs := bpf_load.o $(LIBBPF) tracex6_user.o -tracex7-objs := bpf_load.o $(LIBBPF) tracex7_user.o load_sock_ops-objs := bpf_load.o $(LIBBPF) load_sock_ops.o test_probe_write_user-objs := bpf_load.o $(LIBBPF) test_probe_write_user_user.o trace_output-objs := bpf_load.o $(LIBBPF) trace_output_user.o @@ -106,7 +104,6 @@ always += tracex3_kern.o always += tracex4_kern.o always += tracex5_kern.o always += tracex6_kern.o -always += tracex7_kern.o always += sock_flags_kern.o always += test_probe_write_user_kern.o always += trace_output_kern.o @@ -161,7 +158,6 @@ HOSTLOADLIBES_tracex3 += -lelf HOSTLOADLIBES_tracex4 += -lelf -lrt HOSTLOADLIBES_tracex5 += -lelf HOSTLOADLIBES_tracex6 += -lelf -HOSTLOADLIBES_tracex7 += -lelf HOSTLOADLIBES_test_cgrp2_sock2 += -lelf HOSTLOADLIBES_load_sock_ops += -lelf HOSTLOADLIBES_test_probe_write_user += -lelf diff --git a/samples/bpf/test_override_return.sh b/samples/bpf/test_override_return.sh deleted file mode 100755 index e68b9ee6814b..000000000000 --- a/samples/bpf/test_override_return.sh +++ /dev/null @@ -1,15 +0,0 @@ -#!/bin/bash - -rm -f testfile.img -dd if=/dev/zero of=testfile.img bs=1M seek=1000 count=1 -DEVICE=$(losetup --show -f testfile.img) -mkfs.btrfs -f $DEVICE -mkdir tmpmnt -./tracex7 $DEVICE -if [ $? -eq 0 ] -then - echo "SUCCESS!" -else - echo "FAILED!" -fi -losetup -d $DEVICE diff --git a/samples/bpf/tracex7_kern.c b/samples/bpf/tracex7_kern.c deleted file mode 100644 index 1ab308a43e0f..000000000000 --- a/samples/bpf/tracex7_kern.c +++ /dev/null @@ -1,16 +0,0 @@ -#include -#include -#include -#include "bpf_helpers.h" - -SEC("kprobe/open_ctree") -int bpf_prog1(struct pt_regs *ctx) -{ - unsigned long rc = -12; - - bpf_override_return(ctx, rc); - return 0; -} - -char _license[] SEC("license") = "GPL"; -u32 _version SEC("version") = LINUX_VERSION_CODE; diff --git a/samples/bpf/tracex7_user.c b/samples/bpf/tracex7_user.c deleted file mode 100644 index 8a52ac492e8b..000000000000 --- a/samples/bpf/tracex7_user.c +++ /dev/null @@ -1,28 +0,0 @@ -#define _GNU_SOURCE - -#include -#include -#include -#include "libbpf.h" -#include "bpf_load.h" - -int main(int argc, char **argv) -{ - FILE *f; - char filename[256]; - char command[256]; - int ret; - - snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); - return 1; - } - - snprintf(command, 256, "mount %s tmpmnt/", argv[1]); - f = popen(command, "r"); - ret = pclose(f); - - return ret ? 0 : 1; -} diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index adb66f78b674..e880ae6434ee 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -677,10 +677,6 @@ union bpf_attr { * @buf: buf to fill * @buf_size: size of the buf * Return : 0 on success or negative error code - * - * int bpf_override_return(pt_regs, rc) - * @pt_regs: pointer to struct pt_regs - * @rc: the return value to set */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -740,8 +736,7 @@ union bpf_attr { FN(xdp_adjust_meta), \ FN(perf_event_read_value), \ FN(perf_prog_read_value), \ - FN(getsockopt), \ - FN(override_return), + FN(getsockopt), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index 33cb00e46c49..fd9a17fa8a8b 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -82,8 +82,7 @@ static int (*bpf_perf_event_read_value)(void *map, unsigned long long flags, static int (*bpf_perf_prog_read_value)(void *ctx, void *buf, unsigned int buf_size) = (void *) BPF_FUNC_perf_prog_read_value; -static int (*bpf_override_return)(void *ctx, unsigned long rc) = - (void *) BPF_FUNC_override_return; + /* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions -- cgit v1.2.3-71-gd317 From 713bafea92920103cd3d361657406cf04d0e22dd Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 8 Nov 2017 13:01:26 -0800 Subject: tcp: retire FACK loss detection FACK loss detection has been disabled by default and the successor RACK subsumed FACK and can handle reordering better. This patch removes FACK to simplify TCP loss recovery. Signed-off-by: Yuchung Cheng Reviewed-by: Eric Dumazet Reviewed-by: Neal Cardwell Reviewed-by: Soheil Hassas Yeganeh Reviewed-by: Priyaranjan Jha Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 3 +- include/linux/tcp.h | 1 - include/net/tcp.h | 14 +-------- include/uapi/linux/snmp.h | 1 - net/ipv4/proc.c | 1 - net/ipv4/tcp.c | 2 -- net/ipv4/tcp_input.c | 53 +++++----------------------------- net/ipv4/tcp_metrics.c | 4 +-- net/ipv4/tcp_minisocks.c | 5 +--- net/ipv4/tcp_output.c | 5 +--- 10 files changed, 12 insertions(+), 77 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index d8676dda7fa6..46c7e1085efc 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -289,8 +289,7 @@ tcp_ecn_fallback - BOOLEAN Default: 1 (fallback enabled) tcp_fack - BOOLEAN - Enable FACK congestion avoidance and fast retransmission. - The value is not used, if tcp_sack is not enabled. + This is a legacy option, it has no effect anymore. tcp_fin_timeout - INTEGER The length of time an orphaned (no longer referenced by any diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 22f40c96a15b..9574936fe041 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -85,7 +85,6 @@ struct tcp_sack_block { /*These are used to set the sack_ok field in struct tcp_options_received */ #define TCP_SACK_SEEN (1 << 0) /*1 = peer is SACK capable, */ -#define TCP_FACK_ENABLED (1 << 1) /*1 = FACK is enabled locally*/ #define TCP_DSACK_SEEN (1 << 2) /*1 = DSACK was received from peer*/ struct tcp_options_received { diff --git a/include/net/tcp.h b/include/net/tcp.h index 2f2c69ad31b2..ed71511e67a6 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -384,7 +384,6 @@ void tcp_update_metrics(struct sock *sk); void tcp_init_metrics(struct sock *sk); void tcp_metrics_init(void); bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst); -void tcp_disable_fack(struct tcp_sock *tp); void tcp_close(struct sock *sk, long timeout); void tcp_init_sock(struct sock *sk); void tcp_init_transfer(struct sock *sk, int bpf_op); @@ -776,7 +775,7 @@ struct tcp_skb_cb { }; __u8 tcp_flags; /* TCP header flags. (tcp[13]) */ - __u8 sacked; /* State flags for SACK/FACK. */ + __u8 sacked; /* State flags for SACK. */ #define TCPCB_SACKED_ACKED 0x01 /* SKB ACK'd by a SACK block */ #define TCPCB_SACKED_RETRANS 0x02 /* SKB retransmitted */ #define TCPCB_LOST 0x04 /* SKB is lost */ @@ -1066,7 +1065,6 @@ void tcp_rate_check_app_limited(struct sock *sk); * * tcp_is_sack - SACK enabled * tcp_is_reno - No SACK - * tcp_is_fack - FACK enabled, implies SACK enabled */ static inline int tcp_is_sack(const struct tcp_sock *tp) { @@ -1078,16 +1076,6 @@ static inline bool tcp_is_reno(const struct tcp_sock *tp) return !tcp_is_sack(tp); } -static inline bool tcp_is_fack(const struct tcp_sock *tp) -{ - return tp->rx_opt.sack_ok & TCP_FACK_ENABLED; -} - -static inline void tcp_enable_fack(struct tcp_sock *tp) -{ - tp->rx_opt.sack_ok |= TCP_FACK_ENABLED; -} - static inline unsigned int tcp_left_out(const struct tcp_sock *tp) { return tp->sacked_out + tp->lost_out; diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 0d941cdd8e8c..33a70ece462f 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -191,7 +191,6 @@ enum LINUX_MIB_TCPRENORECOVERY, /* TCPRenoRecovery */ LINUX_MIB_TCPSACKRECOVERY, /* TCPSackRecovery */ LINUX_MIB_TCPSACKRENEGING, /* TCPSACKReneging */ - LINUX_MIB_TCPFACKREORDER, /* TCPFACKReorder */ LINUX_MIB_TCPSACKREORDER, /* TCPSACKReorder */ LINUX_MIB_TCPRENOREORDER, /* TCPRenoReorder */ LINUX_MIB_TCPTSREORDER, /* TCPTSReorder */ diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 127153f1ed8a..9f37c4727861 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -212,7 +212,6 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPRenoRecovery", LINUX_MIB_TCPRENORECOVERY), SNMP_MIB_ITEM("TCPSackRecovery", LINUX_MIB_TCPSACKRECOVERY), SNMP_MIB_ITEM("TCPSACKReneging", LINUX_MIB_TCPSACKRENEGING), - SNMP_MIB_ITEM("TCPFACKReorder", LINUX_MIB_TCPFACKREORDER), SNMP_MIB_ITEM("TCPSACKReorder", LINUX_MIB_TCPSACKREORDER), SNMP_MIB_ITEM("TCPRenoReorder", LINUX_MIB_TCPRENOREORDER), SNMP_MIB_ITEM("TCPTSReorder", LINUX_MIB_TCPTSREORDER), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index bc71a27d5ad9..337555076043 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2509,8 +2509,6 @@ static int tcp_repair_options_est(struct sock *sk, return -EINVAL; tp->rx_opt.sack_ok |= TCP_SACK_SEEN; - if (sock_net(sk)->ipv4.sysctl_tcp_fack) - tcp_enable_fack(tp); break; case TCPOPT_TIMESTAMP: if (opt.opt_val != 0) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 9ceaa1fdc3ab..487e181cff86 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -842,18 +842,6 @@ __u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst) return min_t(__u32, cwnd, tp->snd_cwnd_clamp); } -/* - * Packet counting of FACK is based on in-order assumptions, therefore TCP - * disables it when reordering is detected - */ -void tcp_disable_fack(struct tcp_sock *tp) -{ - /* RFC3517 uses different metric in lost marker => reset on change */ - if (tcp_is_fack(tp)) - tp->lost_skb_hint = NULL; - tp->rx_opt.sack_ok &= ~TCP_FACK_ENABLED; -} - /* Take a notice that peer is sending D-SACKs */ static void tcp_dsack_seen(struct tcp_sock *tp) { @@ -881,7 +869,6 @@ static void tcp_update_reordering(struct sock *sk, const int metric, tp->sacked_out, tp->undo_marker ? tp->undo_retrans : 0); #endif - tcp_disable_fack(tp); } tp->rack.reord = 1; @@ -891,8 +878,6 @@ static void tcp_update_reordering(struct sock *sk, const int metric, mib_idx = LINUX_MIB_TCPTSREORDER; else if (tcp_is_reno(tp)) mib_idx = LINUX_MIB_TCPRENOREORDER; - else if (tcp_is_fack(tp)) - mib_idx = LINUX_MIB_TCPFACKREORDER; else mib_idx = LINUX_MIB_TCPSACKREORDER; @@ -970,7 +955,6 @@ void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb) * 3. Loss detection event of two flavors: * A. Scoreboard estimator decided the packet is lost. * A'. Reno "three dupacks" marks head of queue lost. - * A''. Its FACK modification, head until snd.fack is lost. * B. SACK arrives sacking SND.NXT at the moment, when the * segment was retransmitted. * 4. D-SACK added new rule: D-SACK changes any tag to S. @@ -1248,7 +1232,7 @@ static u8 tcp_sacktag_one(struct sock *sk, fack_count += pcount; /* Lost marker hint past SACKed? Tweak RFC3517 cnt */ - if (!tcp_is_fack(tp) && tp->lost_skb_hint && + if (tp->lost_skb_hint && before(start_seq, TCP_SKB_CB(tp->lost_skb_hint)->seq)) tp->lost_cnt_hint += pcount; @@ -2051,10 +2035,6 @@ static inline int tcp_fackets_out(const struct tcp_sock *tp) * counter when SACK is enabled (without SACK, sacked_out is used for * that purpose). * - * Instead, with FACK TCP uses fackets_out that includes both SACKed - * segments up to the highest received SACK block so far and holes in - * between them. - * * With reordering, holes may still be in flight, so RFC3517 recovery * uses pure sacked_out (total number of SACKed segments) even though * it violates the RFC that uses duplicate ACKs, often these are equal @@ -2064,10 +2044,10 @@ static inline int tcp_fackets_out(const struct tcp_sock *tp) */ static inline int tcp_dupack_heuristics(const struct tcp_sock *tp) { - return tcp_is_fack(tp) ? tp->fackets_out : tp->sacked_out + 1; + return tp->sacked_out + 1; } -/* Linux NewReno/SACK/FACK/ECN state machine. +/* Linux NewReno/SACK/ECN state machine. * -------------------------------------- * * "Open" Normal state, no dubious events, fast path. @@ -2132,16 +2112,6 @@ static inline int tcp_dupack_heuristics(const struct tcp_sock *tp) * dynamically measured and adjusted. This is implemented in * tcp_rack_mark_lost. * - * FACK (Disabled by default. Subsumbed by RACK): - * It is the simplest heuristics. As soon as we decided - * that something is lost, we decide that _all_ not SACKed - * packets until the most forward SACK are lost. I.e. - * lost_out = fackets_out - sacked_out and left_out = fackets_out. - * It is absolutely correct estimate, if network does not reorder - * packets. And it loses any connection to reality when reordering - * takes place. We use FACK by default until reordering - * is suspected on the path to this destination. - * * If the receiver does not support SACK: * * NewReno (RFC6582): in Recovery we assume that one segment @@ -2190,7 +2160,7 @@ static bool tcp_time_to_recover(struct sock *sk, int flag) } /* Detect loss in event "A" above by marking head of queue up as lost. - * For FACK or non-SACK(Reno) senders, the first "packets" number of segments + * For non-SACK(Reno) senders, the first "packets" number of segments * are considered lost. For RFC3517 SACK, a segment is considered lost if it * has at least tp->reordering SACKed seqments above it; "packets" refers to * the maximum SACKed segments to pass before reaching this limit. @@ -2226,12 +2196,12 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) break; oldcnt = cnt; - if (tcp_is_fack(tp) || tcp_is_reno(tp) || + if (tcp_is_reno(tp) || (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) cnt += tcp_skb_pcount(skb); if (cnt > packets) { - if ((tcp_is_sack(tp) && !tcp_is_fack(tp)) || + if (tcp_is_sack(tp) || (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) || (oldcnt >= packets)) break; @@ -2262,11 +2232,6 @@ static void tcp_update_scoreboard(struct sock *sk, int fast_rexmit) if (tcp_is_reno(tp)) { tcp_mark_head_lost(sk, 1, 1); - } else if (tcp_is_fack(tp)) { - int lost = tp->fackets_out - tp->reordering; - if (lost <= 0) - lost = 1; - tcp_mark_head_lost(sk, lost, 0); } else { int sacked_upto = tp->sacked_out - tp->reordering; if (sacked_upto >= 0) @@ -3199,8 +3164,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (reord < prior_fackets && reord <= tp->fackets_out) tcp_update_reordering(sk, tp->fackets_out - reord, 0); - delta = tcp_is_fack(tp) ? pkts_acked : - prior_sacked - tp->sacked_out; + delta = prior_sacked - tp->sacked_out; tp->lost_cnt_hint -= min(tp->lost_cnt_hint, delta); } @@ -5708,9 +5672,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, tp->tcp_header_len = sizeof(struct tcphdr); } - if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_fack) - tcp_enable_fack(tp); - tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); tcp_initialize_rcv_mss(sk); diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 9d5ddebfd831..7097f92d16e5 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -470,10 +470,8 @@ void tcp_init_metrics(struct sock *sk) tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; } val = tcp_metric_get(tm, TCP_METRIC_REORDERING); - if (val && tp->reordering != val) { - tcp_disable_fack(tp); + if (val && tp->reordering != val) tp->reordering = val; - } crtt = tcp_metric_get(tm, TCP_METRIC_RTT); rcu_read_unlock(); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 4bb86580decd..326c9282bf94 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -509,10 +509,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, keepalive_time_when(newtp)); newtp->rx_opt.tstamp_ok = ireq->tstamp_ok; - if ((newtp->rx_opt.sack_ok = ireq->sack_ok) != 0) { - if (sock_net(sk)->ipv4.sysctl_tcp_fack) - tcp_enable_fack(newtp); - } + newtp->rx_opt.sack_ok = ireq->sack_ok; newtp->window_clamp = req->rsk_window_clamp; newtp->rcv_ssthresh = req->rsk_rcv_wnd; newtp->rcv_wnd = req->rsk_rcv_wnd; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 9b98d35aa0d8..094c429b4401 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1257,7 +1257,7 @@ static void tcp_adjust_pcount(struct sock *sk, const struct sk_buff *skb, int de if (tp->lost_skb_hint && before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(tp->lost_skb_hint)->seq) && - (tcp_is_fack(tp) || (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))) + (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) tp->lost_cnt_hint -= decr; tcp_verify_left_out(tp); @@ -2961,9 +2961,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) * retransmitted data is acknowledged. It tries to continue * resending the rest of the retransmit queue, until either * we've sent it all or the congestion window limit is reached. - * If doing SACK, the first ACK which comes back for a timeout - * based retransmit packet might feed us FACK information again. - * If so, we use it to avoid unnecessarily retransmissions. */ void tcp_xmit_retransmit_queue(struct sock *sk) { -- cgit v1.2.3-71-gd317 From 99803171ef04037092bf5eb29ae801e8b4d49a75 Mon Sep 17 00:00:00 2001 From: Dave Taht Date: Wed, 8 Nov 2017 15:12:27 -0800 Subject: netem: add uapi to express delay and jitter in nanoseconds netem userspace has long relied on a horrible /proc/net/psched hack to translate the current notion of "ticks" to nanoseconds. Expressing latency and jitter instead, in well defined nanoseconds, increases the dynamic range of emulated delays and jitter in netem. It will also ease a transition where reducing a tick to nsec equivalence would constrain the max delay in prior versions of netem to only 4.3 seconds. Signed-off-by: Dave Taht Suggested-by: Eric Dumazet Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/uapi/linux/pkt_sched.h | 2 ++ net/sched/sch_netem.c | 14 ++++++++++++++ 2 files changed, 16 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 6a2c5ea7e9c4..8fe6d1842bee 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -537,6 +537,8 @@ enum { TCA_NETEM_ECN, TCA_NETEM_RATE64, TCA_NETEM_PAD, + TCA_NETEM_LATENCY64, + TCA_NETEM_JITTER64, __TCA_NETEM_MAX, }; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index e64e0e0d94ff..47d6decba0ea 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -819,6 +819,8 @@ static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = { [TCA_NETEM_LOSS] = { .type = NLA_NESTED }, [TCA_NETEM_ECN] = { .type = NLA_U32 }, [TCA_NETEM_RATE64] = { .type = NLA_U64 }, + [TCA_NETEM_LATENCY64] = { .type = NLA_S64 }, + [TCA_NETEM_JITTER64] = { .type = NLA_S64 }, }; static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, @@ -916,6 +918,12 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt) q->rate = max_t(u64, q->rate, nla_get_u64(tb[TCA_NETEM_RATE64])); + if (tb[TCA_NETEM_LATENCY64]) + q->latency = nla_get_s64(tb[TCA_NETEM_LATENCY64]); + + if (tb[TCA_NETEM_JITTER64]) + q->jitter = nla_get_s64(tb[TCA_NETEM_JITTER64]); + if (tb[TCA_NETEM_ECN]) q->ecn = nla_get_u32(tb[TCA_NETEM_ECN]); @@ -1020,6 +1028,12 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) if (nla_put(skb, TCA_OPTIONS, sizeof(qopt), &qopt)) goto nla_put_failure; + if (nla_put(skb, TCA_NETEM_LATENCY64, sizeof(q->latency), &q->latency)) + goto nla_put_failure; + + if (nla_put(skb, TCA_NETEM_JITTER64, sizeof(q->jitter), &q->jitter)) + goto nla_put_failure; + cor.delay_corr = q->delay_cor.rho; cor.loss_corr = q->loss_cor.rho; cor.dup_corr = q->dup_cor.rho; -- cgit v1.2.3-71-gd317 From 836af83b54e3e285c4a0cc06c24aeb737d3e0e18 Mon Sep 17 00:00:00 2001 From: Dave Taht Date: Wed, 8 Nov 2017 15:12:28 -0800 Subject: netem: support delivering packets in delayed time slots Slotting is a crude approximation of the behaviors of shared media such as cable, wifi, and LTE, which gather up a bunch of packets within a varying delay window and deliver them, relative to that, nearly all at once. It works within the existing loss, duplication, jitter and delay parameters of netem. Some amount of inherent latency must be specified, regardless. The new "slot" parameter specifies a minimum and maximum delay between transmission attempts. The "bytes" and "packets" parameters can be used to limit the amount of information transferred per slot. Examples of use: tc qdisc add dev eth0 root netem delay 200us \ slot 800us 10ms bytes 64k packets 42 A more correct example, using stacked netem instances and a packet limit to emulate a tail drop wifi queue with slots and variable packet delivery, with a 200Mbit isochronous underlying rate, and 20ms path delay: tc qdisc add dev eth0 root handle 1: netem delay 20ms rate 200mbit \ limit 10000 tc qdisc add dev eth0 parent 1:1 handle 10:1 netem delay 200us \ slot 800us 10ms bytes 64k packets 42 limit 512 Signed-off-by: Dave Taht Signed-off-by: David S. Miller --- include/uapi/linux/pkt_sched.h | 8 +++++ net/sched/sch_netem.c | 74 ++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 79 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 8fe6d1842bee..af3cc2f4e1ad 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -539,6 +539,7 @@ enum { TCA_NETEM_PAD, TCA_NETEM_LATENCY64, TCA_NETEM_JITTER64, + TCA_NETEM_SLOT, __TCA_NETEM_MAX, }; @@ -576,6 +577,13 @@ struct tc_netem_rate { __s32 cell_overhead; }; +struct tc_netem_slot { + __s64 min_delay; /* nsec */ + __s64 max_delay; + __s32 max_packets; + __s32 max_bytes; +}; + enum { NETEM_LOSS_UNSPEC, NETEM_LOSS_GI, /* General Intuitive - 4 state model */ diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 47d6decba0ea..b686e755fda9 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -135,6 +135,13 @@ struct netem_sched_data { u32 a5; /* p23 used only in 4-states */ } clg; + struct tc_netem_slot slot_config; + struct slotstate { + u64 slot_next; + s32 packets_left; + s32 bytes_left; + } slot; + }; /* Time stamp put into socket buffer control block @@ -591,6 +598,20 @@ finish_segs: return NET_XMIT_SUCCESS; } +/* Delay the next round with a new future slot with a + * correct number of bytes and packets. + */ + +static void get_slot_next(struct netem_sched_data *q, u64 now) +{ + q->slot.slot_next = now + q->slot_config.min_delay + + (prandom_u32() * + (q->slot_config.max_delay - + q->slot_config.min_delay) >> 32); + q->slot.packets_left = q->slot_config.max_packets; + q->slot.bytes_left = q->slot_config.max_bytes; +} + static struct sk_buff *netem_dequeue(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); @@ -608,14 +629,17 @@ deliver: p = rb_first(&q->t_root); if (p) { u64 time_to_send; + u64 now = ktime_get_ns(); skb = rb_to_skb(p); /* if more time remaining? */ time_to_send = netem_skb_cb(skb)->time_to_send; - if (time_to_send <= ktime_get_ns()) { - rb_erase(p, &q->t_root); + if (q->slot.slot_next && q->slot.slot_next < time_to_send) + get_slot_next(q, now); + if (time_to_send <= now && q->slot.slot_next <= now) { + rb_erase(p, &q->t_root); sch->q.qlen--; qdisc_qstats_backlog_dec(sch, skb); skb->next = NULL; @@ -634,6 +658,14 @@ deliver: skb->tstamp = 0; #endif + if (q->slot.slot_next) { + q->slot.packets_left--; + q->slot.bytes_left -= qdisc_pkt_len(skb); + if (q->slot.packets_left <= 0 || + q->slot.bytes_left <= 0) + get_slot_next(q, now); + } + if (q->qdisc) { unsigned int pkt_len = qdisc_pkt_len(skb); struct sk_buff *to_free = NULL; @@ -657,7 +689,10 @@ deliver: if (skb) goto deliver; } - qdisc_watchdog_schedule_ns(&q->watchdog, time_to_send); + + qdisc_watchdog_schedule_ns(&q->watchdog, + max(time_to_send, + q->slot.slot_next)); } if (q->qdisc) { @@ -688,6 +723,7 @@ static void dist_free(struct disttable *d) * Distribution data is a variable size payload containing * signed 16 bit values. */ + static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr) { struct netem_sched_data *q = qdisc_priv(sch); @@ -718,6 +754,23 @@ static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr) return 0; } +static void get_slot(struct netem_sched_data *q, const struct nlattr *attr) +{ + const struct tc_netem_slot *c = nla_data(attr); + + q->slot_config = *c; + if (q->slot_config.max_packets == 0) + q->slot_config.max_packets = INT_MAX; + if (q->slot_config.max_bytes == 0) + q->slot_config.max_bytes = INT_MAX; + q->slot.packets_left = q->slot_config.max_packets; + q->slot.bytes_left = q->slot_config.max_bytes; + if (q->slot_config.min_delay | q->slot_config.max_delay) + q->slot.slot_next = ktime_get_ns(); + else + q->slot.slot_next = 0; +} + static void get_correlation(struct netem_sched_data *q, const struct nlattr *attr) { const struct tc_netem_corr *c = nla_data(attr); @@ -821,6 +874,7 @@ static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = { [TCA_NETEM_RATE64] = { .type = NLA_U64 }, [TCA_NETEM_LATENCY64] = { .type = NLA_S64 }, [TCA_NETEM_JITTER64] = { .type = NLA_S64 }, + [TCA_NETEM_SLOT] = { .len = sizeof(struct tc_netem_slot) }, }; static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, @@ -927,6 +981,9 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt) if (tb[TCA_NETEM_ECN]) q->ecn = nla_get_u32(tb[TCA_NETEM_ECN]); + if (tb[TCA_NETEM_SLOT]) + get_slot(q, tb[TCA_NETEM_SLOT]); + return ret; } @@ -1016,6 +1073,7 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) struct tc_netem_reorder reorder; struct tc_netem_corrupt corrupt; struct tc_netem_rate rate; + struct tc_netem_slot slot; qopt.latency = min_t(psched_tdiff_t, PSCHED_NS2TICKS(q->latency), UINT_MAX); @@ -1070,6 +1128,16 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) if (dump_loss_model(q, skb) != 0) goto nla_put_failure; + if (q->slot_config.min_delay | q->slot_config.max_delay) { + slot = q->slot_config; + if (slot.max_packets == INT_MAX) + slot.max_packets = 0; + if (slot.max_bytes == INT_MAX) + slot.max_bytes = 0; + if (nla_put(skb, TCA_NETEM_SLOT, sizeof(slot), &slot)) + goto nla_put_failure; + } + return nla_nest_end(skb, nla); nla_put_failure: -- cgit v1.2.3-71-gd317 From 5794040647de4011598a6d005fdad95d24fd385b Mon Sep 17 00:00:00 2001 From: Andy Zhou Date: Fri, 10 Nov 2017 12:09:40 -0800 Subject: openvswitch: Add meter netlink definitions Meter has its own netlink family. Define netlink messages and attributes for communicating with the user space programs. Signed-off-by: Andy Zhou Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 51 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index ec75a685f1dd..d60b9a4cf3d1 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -883,4 +883,55 @@ enum ovs_action_attr { #define OVS_ACTION_ATTR_MAX (__OVS_ACTION_ATTR_MAX - 1) +/* Meters. */ +#define OVS_METER_FAMILY "ovs_meter" +#define OVS_METER_MCGROUP "ovs_meter" +#define OVS_METER_VERSION 0x1 + +enum ovs_meter_cmd { + OVS_METER_CMD_UNSPEC, + OVS_METER_CMD_FEATURES, /* Get features supported by the datapath. */ + OVS_METER_CMD_SET, /* Add or modify a meter. */ + OVS_METER_CMD_DEL, /* Delete a meter. */ + OVS_METER_CMD_GET /* Get meter stats. */ +}; + +enum ovs_meter_attr { + OVS_METER_ATTR_UNSPEC, + OVS_METER_ATTR_ID, /* u32 meter ID within datapath. */ + OVS_METER_ATTR_KBPS, /* No argument. If set, units in kilobits + * per second. Otherwise, units in + * packets per second. + */ + OVS_METER_ATTR_STATS, /* struct ovs_flow_stats for the meter. */ + OVS_METER_ATTR_BANDS, /* Nested attributes for meter bands. */ + OVS_METER_ATTR_USED, /* u64 msecs last used in monotonic time. */ + OVS_METER_ATTR_CLEAR, /* Flag to clear stats, used. */ + OVS_METER_ATTR_MAX_METERS, /* u32 number of meters supported. */ + OVS_METER_ATTR_MAX_BANDS, /* u32 max number of bands per meter. */ + OVS_METER_ATTR_PAD, + __OVS_METER_ATTR_MAX +}; + +#define OVS_METER_ATTR_MAX (__OVS_METER_ATTR_MAX - 1) + +enum ovs_band_attr { + OVS_BAND_ATTR_UNSPEC, + OVS_BAND_ATTR_TYPE, /* u32 OVS_METER_BAND_TYPE_* constant. */ + OVS_BAND_ATTR_RATE, /* u32 band rate in meter units (see above). */ + OVS_BAND_ATTR_BURST, /* u32 burst size in meter units. */ + OVS_BAND_ATTR_STATS, /* struct ovs_flow_stats for the band. */ + __OVS_BAND_ATTR_MAX +}; + +#define OVS_BAND_ATTR_MAX (__OVS_BAND_ATTR_MAX - 1) + +enum ovs_meter_band_type { + OVS_METER_BAND_TYPE_UNSPEC, + OVS_METER_BAND_TYPE_DROP, /* Drop exceeding packets. */ + __OVS_METER_BAND_TYPE_MAX +}; + +#define OVS_METER_BAND_TYPE_MAX (__OVS_METER_BAND_TYPE_MAX - 1) + #endif /* _LINUX_OPENVSWITCH_H */ -- cgit v1.2.3-71-gd317 From cd8a6c33693c1b89d2737ffdbf9611564e9ac907 Mon Sep 17 00:00:00 2001 From: Andy Zhou Date: Fri, 10 Nov 2017 12:09:43 -0800 Subject: openvswitch: Add meter action support Implements OVS kernel meter action support. Signed-off-by: Andy Zhou Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 3 +++ net/openvswitch/actions.c | 6 ++++++ net/openvswitch/datapath.h | 1 + net/openvswitch/flow_netlink.c | 6 ++++++ 4 files changed, 16 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index d60b9a4cf3d1..4265d7f9e1f2 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -838,6 +838,8 @@ struct ovs_action_push_eth { * @OVS_ACTION_ATTR_CT_CLEAR: Clear conntrack state from the packet. * @OVS_ACTION_ATTR_PUSH_NSH: push NSH header to the packet. * @OVS_ACTION_ATTR_POP_NSH: pop the outermost NSH header off the packet. + * @OVS_ACTION_ATTR_METER: Run packet through a meter, which may drop the + * packet, or modify the packet (e.g., change the DSCP field). * * Only a single header can be set with a single %OVS_ACTION_ATTR_SET. Not all * fields within a header are modifiable, e.g. the IPv4 protocol and fragment @@ -870,6 +872,7 @@ enum ovs_action_attr { OVS_ACTION_ATTR_CT_CLEAR, /* No argument. */ OVS_ACTION_ATTR_PUSH_NSH, /* Nested OVS_NSH_KEY_ATTR_*. */ OVS_ACTION_ATTR_POP_NSH, /* No argument. */ + OVS_ACTION_ATTR_METER, /* u32 meter ID. */ __OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted * from userspace. */ diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 9a6a6d51e421..30a5df27116e 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1330,6 +1330,12 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, case OVS_ACTION_ATTR_POP_NSH: err = pop_nsh(skb, key); break; + + case OVS_ACTION_ATTR_METER: + if (ovs_meter_execute(dp, skb, key, nla_get_u32(a))) { + consume_skb(skb); + return 0; + } } if (unlikely(err)) { diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 5d2997b42460..523d65526766 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -30,6 +30,7 @@ #include "conntrack.h" #include "flow.h" #include "flow_table.h" +#include "meter.h" #include "vport-internal_dev.h" #define DP_MAX_PORTS USHRT_MAX diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 4201f9293af3..bb4dae198c78 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -90,6 +90,7 @@ static bool actions_may_change_flow(const struct nlattr *actions) case OVS_ACTION_ATTR_SAMPLE: case OVS_ACTION_ATTR_SET: case OVS_ACTION_ATTR_SET_MASKED: + case OVS_ACTION_ATTR_METER: default: return true; } @@ -2844,6 +2845,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, [OVS_ACTION_ATTR_POP_ETH] = 0, [OVS_ACTION_ATTR_PUSH_NSH] = (u32)-1, [OVS_ACTION_ATTR_POP_NSH] = 0, + [OVS_ACTION_ATTR_METER] = sizeof(u32), }; const struct ovs_action_push_vlan *vlan; int type = nla_type(a); @@ -3029,6 +3031,10 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, break; } + case OVS_ACTION_ATTR_METER: + /* Non-existent meters are simply ignored. */ + break; + default: OVS_NLERR(log, "Unknown Action type %d", type); return -EINVAL; -- cgit v1.2.3-71-gd317 From f044c8847bb61eff5e1e95b6f6bb950e7f4a73a4 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 2 Nov 2017 15:27:45 +0000 Subject: afs: Lay the groundwork for supporting network namespaces Lay the groundwork for supporting network namespaces (netns) to the AFS filesystem by moving various global features to a network-namespace struct (afs_net) and providing an instance of this as a temporary global variable that everything uses via accessor functions for the moment. The following changes have been made: (1) Store the netns in the superblock info. This will be obtained from the mounter's nsproxy on a manual mount and inherited from the parent superblock on an automount. (2) The cell list is made per-netns. It can be viewed through /proc/net/afs/cells and also be modified by writing commands to that file. (3) The local workstation cell is set per-ns in /proc/net/afs/rootcell. This is unset by default. (4) The 'rootcell' module parameter, which sets a cell and VL server list modifies the init net namespace, thereby allowing an AFS root fs to be theoretically used. (5) The volume location lists and the file lock manager are made per-netns. (6) The AF_RXRPC socket and associated I/O bits are made per-ns. The various workqueues remain global for the moment. Changes still to be made: (1) /proc/fs/afs/ should be moved to /proc/net/afs/ and a symlink emplaced from the old name. (2) A per-netns subsys needs to be registered for AFS into which it can store its per-netns data. (3) Rather than the AF_RXRPC socket being opened on module init, it needs to be opened on the creation of a superblock in that netns. (4) The socket needs to be closed when the last superblock using it is destroyed and all outstanding client calls on it have been completed. This prevents a reference loop on the namespace. (5) It is possible that several namespaces will want to use AFS, in which case each one will need its own UDP port. These can either be set through /proc/net/afs/cm_port or the kernel can pick one at random. The init_ns gets 7001 by default. Other issues that need resolving: (1) The DNS keyring needs net-namespacing. (2) Where do upcalls go (eg. DNS request-key upcall)? (3) Need something like open_socket_in_file_ns() syscall so that AFS command line tools attempting to operate on an AFS file/volume have their RPC calls go to the right place. Signed-off-by: David Howells --- fs/afs/afs.h | 9 +++ fs/afs/callback.c | 24 +------ fs/afs/cell.c | 130 ++++++++++++++++++------------------ fs/afs/cmservice.c | 26 ++++---- fs/afs/flock.c | 39 +---------- fs/afs/fsclient.c | 56 ++++++++++------ fs/afs/internal.h | 163 +++++++++++++++++++++++++++++++++------------ fs/afs/main.c | 153 +++++++++++++++++++++++++++++------------- fs/afs/proc.c | 64 +++++++++++------- fs/afs/rxrpc.c | 132 ++++++++++++++++++------------------ fs/afs/server.c | 82 +++++++++++------------ fs/afs/super.c | 45 +++++++------ fs/afs/vlclient.c | 10 +-- fs/afs/vlocation.c | 151 +++++++++++++++++++---------------------- fs/afs/volume.c | 10 +-- include/uapi/linux/magic.h | 1 + 16 files changed, 603 insertions(+), 492 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/afs/afs.h b/fs/afs/afs.h index 3c462ff6db63..93053115bcfc 100644 --- a/fs/afs/afs.h +++ b/fs/afs/afs.h @@ -72,6 +72,15 @@ struct afs_callback { #define AFSCBMAX 50 /* maximum callbacks transferred per bulk op */ +struct afs_uuid { + __be32 time_low; /* low part of timestamp */ + __be16 time_mid; /* mid part of timestamp */ + __be16 time_hi_and_version; /* high part of timestamp and version */ + __u8 clock_seq_hi_and_reserved; /* clock seq hi and variant */ + __u8 clock_seq_low; /* clock seq low */ + __u8 node[6]; /* spatially unique node ID (MAC addr) */ +}; + /* * AFS volume information */ diff --git a/fs/afs/callback.c b/fs/afs/callback.c index 25d404d22cae..d12dffb76b67 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -28,9 +28,7 @@ unsigned afs_vnode_update_timeout = 10; CIRC_SPACE((server)->cb_break_head, (server)->cb_break_tail, \ ARRAY_SIZE((server)->cb_break)) -//static void afs_callback_updater(struct work_struct *); - -static struct workqueue_struct *afs_callback_update_worker; +struct workqueue_struct *afs_callback_update_worker; /* * allow the fileserver to request callback state (re-)initialisation @@ -343,7 +341,7 @@ void afs_dispatch_give_up_callbacks(struct work_struct *work) * had callbacks entirely, and the server will call us later to break * them */ - afs_fs_give_up_callbacks(server, true); + afs_fs_give_up_callbacks(server->cell->net, server, true); } /* @@ -456,21 +454,3 @@ static void afs_callback_updater(struct work_struct *work) afs_put_vnode(vl); } #endif - -/* - * initialise the callback update process - */ -int __init afs_callback_update_init(void) -{ - afs_callback_update_worker = alloc_ordered_workqueue("kafs_callbackd", - WQ_MEM_RECLAIM); - return afs_callback_update_worker ? 0 : -ENOMEM; -} - -/* - * shut down the callback update process - */ -void afs_callback_update_kill(void) -{ - destroy_workqueue(afs_callback_update_worker); -} diff --git a/fs/afs/cell.c b/fs/afs/cell.c index ca0a3cf93791..bd570fa539a0 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -18,20 +18,12 @@ #include #include "internal.h" -DECLARE_RWSEM(afs_proc_cells_sem); -LIST_HEAD(afs_proc_cells); - -static LIST_HEAD(afs_cells); -static DEFINE_RWLOCK(afs_cells_lock); -static DECLARE_RWSEM(afs_cells_sem); /* add/remove serialisation */ -static DECLARE_WAIT_QUEUE_HEAD(afs_cells_freeable_wq); -static struct afs_cell *afs_cell_root; - /* * allocate a cell record and fill in its name, VL server address list and * allocate an anonymous key */ -static struct afs_cell *afs_cell_alloc(const char *name, unsigned namelen, +static struct afs_cell *afs_cell_alloc(struct afs_net *net, + const char *name, unsigned namelen, char *vllist) { struct afs_cell *cell; @@ -62,6 +54,7 @@ static struct afs_cell *afs_cell_alloc(const char *name, unsigned namelen, atomic_set(&cell->usage, 1); INIT_LIST_HEAD(&cell->link); + cell->net = net; rwlock_init(&cell->servers_lock); INIT_LIST_HEAD(&cell->servers); init_rwsem(&cell->vl_sem); @@ -142,12 +135,14 @@ error: /* * afs_cell_crate() - create a cell record + * @net: The network namespace * @name: is the name of the cell. * @namsesz: is the strlen of the cell name. * @vllist: is a colon separated list of IP addresses in "a.b.c.d" format. * @retref: is T to return the cell reference when the cell exists. */ -struct afs_cell *afs_cell_create(const char *name, unsigned namesz, +struct afs_cell *afs_cell_create(struct afs_net *net, + const char *name, unsigned namesz, char *vllist, bool retref) { struct afs_cell *cell; @@ -155,23 +150,23 @@ struct afs_cell *afs_cell_create(const char *name, unsigned namesz, _enter("%*.*s,%s", namesz, namesz, name ?: "", vllist); - down_write(&afs_cells_sem); - read_lock(&afs_cells_lock); - list_for_each_entry(cell, &afs_cells, link) { + down_write(&net->cells_sem); + read_lock(&net->cells_lock); + list_for_each_entry(cell, &net->cells, link) { if (strncasecmp(cell->name, name, namesz) == 0) goto duplicate_name; } - read_unlock(&afs_cells_lock); + read_unlock(&net->cells_lock); - cell = afs_cell_alloc(name, namesz, vllist); + cell = afs_cell_alloc(net, name, namesz, vllist); if (IS_ERR(cell)) { _leave(" = %ld", PTR_ERR(cell)); - up_write(&afs_cells_sem); + up_write(&net->cells_sem); return cell; } /* add a proc directory for this cell */ - ret = afs_proc_cell_setup(cell); + ret = afs_proc_cell_setup(net, cell); if (ret < 0) goto error; @@ -183,20 +178,20 @@ struct afs_cell *afs_cell_create(const char *name, unsigned namesz, #endif /* add to the cell lists */ - write_lock(&afs_cells_lock); - list_add_tail(&cell->link, &afs_cells); - write_unlock(&afs_cells_lock); + write_lock(&net->cells_lock); + list_add_tail(&cell->link, &net->cells); + write_unlock(&net->cells_lock); - down_write(&afs_proc_cells_sem); - list_add_tail(&cell->proc_link, &afs_proc_cells); - up_write(&afs_proc_cells_sem); - up_write(&afs_cells_sem); + down_write(&net->proc_cells_sem); + list_add_tail(&cell->proc_link, &net->proc_cells); + up_write(&net->proc_cells_sem); + up_write(&net->cells_sem); _leave(" = %p", cell); return cell; error: - up_write(&afs_cells_sem); + up_write(&net->cells_sem); key_put(cell->anonymous_key); kfree(cell); _leave(" = %d", ret); @@ -206,8 +201,8 @@ duplicate_name: if (retref && !IS_ERR(cell)) afs_get_cell(cell); - read_unlock(&afs_cells_lock); - up_write(&afs_cells_sem); + read_unlock(&net->cells_lock); + up_write(&net->cells_sem); if (retref) { _leave(" = %p", cell); @@ -223,7 +218,7 @@ duplicate_name: * - can be called with a module parameter string * - can be called from a write to /proc/fs/afs/rootcell */ -int afs_cell_init(char *rootcell) +int afs_cell_init(struct afs_net *net, char *rootcell) { struct afs_cell *old_root, *new_root; char *cp; @@ -245,17 +240,17 @@ int afs_cell_init(char *rootcell) *cp++ = 0; /* allocate a cell record for the root cell */ - new_root = afs_cell_create(rootcell, strlen(rootcell), cp, false); + new_root = afs_cell_create(net, rootcell, strlen(rootcell), cp, false); if (IS_ERR(new_root)) { _leave(" = %ld", PTR_ERR(new_root)); return PTR_ERR(new_root); } /* install the new cell */ - write_lock(&afs_cells_lock); - old_root = afs_cell_root; - afs_cell_root = new_root; - write_unlock(&afs_cells_lock); + write_lock(&net->cells_lock); + old_root = net->ws_cell; + net->ws_cell = new_root; + write_unlock(&net->cells_lock); afs_put_cell(old_root); _leave(" = 0"); @@ -265,19 +260,20 @@ int afs_cell_init(char *rootcell) /* * lookup a cell record */ -struct afs_cell *afs_cell_lookup(const char *name, unsigned namesz, +struct afs_cell *afs_cell_lookup(struct afs_net *net, + const char *name, unsigned namesz, bool dns_cell) { struct afs_cell *cell; _enter("\"%*.*s\",", namesz, namesz, name ?: ""); - down_read(&afs_cells_sem); - read_lock(&afs_cells_lock); + down_read(&net->cells_sem); + read_lock(&net->cells_lock); if (name) { /* if the cell was named, look for it in the cell record list */ - list_for_each_entry(cell, &afs_cells, link) { + list_for_each_entry(cell, &net->cells, link) { if (strncmp(cell->name, name, namesz) == 0) { afs_get_cell(cell); goto found; @@ -289,7 +285,7 @@ struct afs_cell *afs_cell_lookup(const char *name, unsigned namesz, found: ; } else { - cell = afs_cell_root; + cell = net->ws_cell; if (!cell) { /* this should not happen unless user tries to mount * when root cell is not set. Return an impossibly @@ -304,16 +300,16 @@ struct afs_cell *afs_cell_lookup(const char *name, unsigned namesz, } - read_unlock(&afs_cells_lock); - up_read(&afs_cells_sem); + read_unlock(&net->cells_lock); + up_read(&net->cells_sem); _leave(" = %p", cell); return cell; create_cell: - read_unlock(&afs_cells_lock); - up_read(&afs_cells_sem); + read_unlock(&net->cells_lock); + up_read(&net->cells_sem); - cell = afs_cell_create(name, namesz, NULL, true); + cell = afs_cell_create(net, name, namesz, NULL, true); _leave(" = %p", cell); return cell; @@ -325,14 +321,14 @@ create_cell: */ struct afs_cell *afs_get_cell_maybe(struct afs_cell *cell) { - write_lock(&afs_cells_lock); + write_lock(&net->cells_lock); if (cell && !list_empty(&cell->link)) afs_get_cell(cell); else cell = NULL; - write_unlock(&afs_cells_lock); + write_unlock(&net->cells_lock); return cell; } #endif /* 0 */ @@ -351,10 +347,10 @@ void afs_put_cell(struct afs_cell *cell) /* to prevent a race, the decrement and the dequeue must be effectively * atomic */ - write_lock(&afs_cells_lock); + write_lock(&cell->net->cells_lock); if (likely(!atomic_dec_and_test(&cell->usage))) { - write_unlock(&afs_cells_lock); + write_unlock(&cell->net->cells_lock); _leave(""); return; } @@ -362,19 +358,19 @@ void afs_put_cell(struct afs_cell *cell) ASSERT(list_empty(&cell->servers)); ASSERT(list_empty(&cell->vl_list)); - write_unlock(&afs_cells_lock); + wake_up(&cell->net->cells_freeable_wq); - wake_up(&afs_cells_freeable_wq); + write_unlock(&cell->net->cells_lock); _leave(" [unused]"); } /* * destroy a cell record - * - must be called with the afs_cells_sem write-locked + * - must be called with the net->cells_sem write-locked * - cell->link should have been broken by the caller */ -static void afs_cell_destroy(struct afs_cell *cell) +static void afs_cell_destroy(struct afs_net *net, struct afs_cell *cell) { _enter("%p{%d,%s}", cell, atomic_read(&cell->usage), cell->name); @@ -387,14 +383,14 @@ static void afs_cell_destroy(struct afs_cell *cell) _debug("wait for cell %s", cell->name); set_current_state(TASK_UNINTERRUPTIBLE); - add_wait_queue(&afs_cells_freeable_wq, &myself); + add_wait_queue(&net->cells_freeable_wq, &myself); while (atomic_read(&cell->usage) > 0) { schedule(); set_current_state(TASK_UNINTERRUPTIBLE); } - remove_wait_queue(&afs_cells_freeable_wq, &myself); + remove_wait_queue(&net->cells_freeable_wq, &myself); set_current_state(TASK_RUNNING); } @@ -403,11 +399,11 @@ static void afs_cell_destroy(struct afs_cell *cell) ASSERT(list_empty(&cell->servers)); ASSERT(list_empty(&cell->vl_list)); - afs_proc_cell_remove(cell); + afs_proc_cell_remove(net, cell); - down_write(&afs_proc_cells_sem); + down_write(&net->proc_cells_sem); list_del_init(&cell->proc_link); - up_write(&afs_proc_cells_sem); + up_write(&net->proc_cells_sem); #ifdef CONFIG_AFS_FSCACHE fscache_relinquish_cookie(cell->cache, 0); @@ -422,39 +418,39 @@ static void afs_cell_destroy(struct afs_cell *cell) * purge in-memory cell database on module unload or afs_init() failure * - the timeout daemon is stopped before calling this */ -void afs_cell_purge(void) +void afs_cell_purge(struct afs_net *net) { struct afs_cell *cell; _enter(""); - afs_put_cell(afs_cell_root); + afs_put_cell(net->ws_cell); - down_write(&afs_cells_sem); + down_write(&net->cells_sem); - while (!list_empty(&afs_cells)) { + while (!list_empty(&net->cells)) { cell = NULL; /* remove the next cell from the front of the list */ - write_lock(&afs_cells_lock); + write_lock(&net->cells_lock); - if (!list_empty(&afs_cells)) { - cell = list_entry(afs_cells.next, + if (!list_empty(&net->cells)) { + cell = list_entry(net->cells.next, struct afs_cell, link); list_del_init(&cell->link); } - write_unlock(&afs_cells_lock); + write_unlock(&net->cells_lock); if (cell) { _debug("PURGING CELL %s (%d)", cell->name, atomic_read(&cell->usage)); /* now the cell should be left with no references */ - afs_cell_destroy(cell); + afs_cell_destroy(net, cell); } } - up_write(&afs_cells_sem); + up_write(&net->cells_sem); _leave(""); } diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index 782d4d05a53b..30ce4be4165f 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -193,7 +193,7 @@ static int afs_deliver_cb_callback(struct afs_call *call) switch (call->unmarshall) { case 0: - rxrpc_kernel_get_peer(afs_socket, call->rxcall, &srx); + rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx); call->offset = 0; call->unmarshall++; @@ -290,7 +290,7 @@ static int afs_deliver_cb_callback(struct afs_call *call) /* we'll need the file server record as that tells us which set of * vnodes to operate upon */ - server = afs_find_server(&srx); + server = afs_find_server(call->net, &srx); if (!server) return -ENOTCONN; call->server = server; @@ -324,7 +324,7 @@ static int afs_deliver_cb_init_call_back_state(struct afs_call *call) _enter(""); - rxrpc_kernel_get_peer(afs_socket, call->rxcall, &srx); + rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx); ret = afs_extract_data(call, NULL, 0, false); if (ret < 0) @@ -335,7 +335,7 @@ static int afs_deliver_cb_init_call_back_state(struct afs_call *call) /* we'll need the file server record as that tells us which set of * vnodes to operate upon */ - server = afs_find_server(&srx); + server = afs_find_server(call->net, &srx); if (!server) return -ENOTCONN; call->server = server; @@ -357,7 +357,7 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call) _enter(""); - rxrpc_kernel_get_peer(afs_socket, call->rxcall, &srx); + rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx); _enter("{%u}", call->unmarshall); @@ -407,7 +407,7 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call) /* we'll need the file server record as that tells us which set of * vnodes to operate upon */ - server = afs_find_server(&srx); + server = afs_find_server(call->net, &srx); if (!server) return -ENOTCONN; call->server = server; @@ -461,7 +461,7 @@ static void SRXAFSCB_ProbeUuid(struct work_struct *work) _enter(""); - if (memcmp(r, &afs_uuid, sizeof(afs_uuid)) == 0) + if (memcmp(r, &call->net->uuid, sizeof(call->net->uuid)) == 0) reply.match = htonl(0); else reply.match = htonl(1); @@ -568,13 +568,13 @@ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *work) memset(&reply, 0, sizeof(reply)); reply.ia.nifs = htonl(nifs); - reply.ia.uuid[0] = afs_uuid.time_low; - reply.ia.uuid[1] = htonl(ntohs(afs_uuid.time_mid)); - reply.ia.uuid[2] = htonl(ntohs(afs_uuid.time_hi_and_version)); - reply.ia.uuid[3] = htonl((s8) afs_uuid.clock_seq_hi_and_reserved); - reply.ia.uuid[4] = htonl((s8) afs_uuid.clock_seq_low); + reply.ia.uuid[0] = call->net->uuid.time_low; + reply.ia.uuid[1] = htonl(ntohs(call->net->uuid.time_mid)); + reply.ia.uuid[2] = htonl(ntohs(call->net->uuid.time_hi_and_version)); + reply.ia.uuid[3] = htonl((s8) call->net->uuid.clock_seq_hi_and_reserved); + reply.ia.uuid[4] = htonl((s8) call->net->uuid.clock_seq_low); for (loop = 0; loop < 6; loop++) - reply.ia.uuid[loop + 5] = htonl((s8) afs_uuid.node[loop]); + reply.ia.uuid[loop + 5] = htonl((s8) call->net->uuid.node[loop]); if (ifs) { for (loop = 0; loop < nifs; loop++) { diff --git a/fs/afs/flock.c b/fs/afs/flock.c index 3191dff2c156..559ac00af5f7 100644 --- a/fs/afs/flock.c +++ b/fs/afs/flock.c @@ -14,47 +14,16 @@ #define AFS_LOCK_GRANTED 0 #define AFS_LOCK_PENDING 1 +struct workqueue_struct *afs_lock_manager; + static void afs_fl_copy_lock(struct file_lock *new, struct file_lock *fl); static void afs_fl_release_private(struct file_lock *fl); -static struct workqueue_struct *afs_lock_manager; -static DEFINE_MUTEX(afs_lock_manager_mutex); - static const struct file_lock_operations afs_lock_ops = { .fl_copy_lock = afs_fl_copy_lock, .fl_release_private = afs_fl_release_private, }; -/* - * initialise the lock manager thread if it isn't already running - */ -static int afs_init_lock_manager(void) -{ - int ret; - - ret = 0; - if (!afs_lock_manager) { - mutex_lock(&afs_lock_manager_mutex); - if (!afs_lock_manager) { - afs_lock_manager = alloc_workqueue("kafs_lockd", - WQ_MEM_RECLAIM, 0); - if (!afs_lock_manager) - ret = -ENOMEM; - } - mutex_unlock(&afs_lock_manager_mutex); - } - return ret; -} - -/* - * destroy the lock manager thread if it's running - */ -void __exit afs_kill_lock_manager(void) -{ - if (afs_lock_manager) - destroy_workqueue(afs_lock_manager); -} - /* * if the callback is broken on this vnode, then the lock may now be available */ @@ -264,10 +233,6 @@ static int afs_do_setlk(struct file *file, struct file_lock *fl) if (fl->fl_start != 0 || fl->fl_end != OFFSET_MAX) return -EINVAL; - ret = afs_init_lock_manager(); - if (ret < 0) - return ret; - fl->fl_ops = &afs_lock_ops; INIT_LIST_HEAD(&fl->fl_u.afs.link); fl->fl_u.afs.state = AFS_LOCK_PENDING; diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 19f76ae36982..ce6f0159e1d4 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -284,12 +284,13 @@ int afs_fs_fetch_file_status(struct afs_server *server, bool async) { struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); __be32 *bp; _enter(",%x,{%x:%u},,", key_serial(key), vnode->fid.vid, vnode->fid.vnode); - call = afs_alloc_flat_call(&afs_RXFSFetchStatus, 16, (21 + 3 + 6) * 4); + call = afs_alloc_flat_call(net, &afs_RXFSFetchStatus, 16, (21 + 3 + 6) * 4); if (!call) return -ENOMEM; @@ -490,11 +491,12 @@ static int afs_fs_fetch_data64(struct afs_server *server, bool async) { struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); __be32 *bp; _enter(""); - call = afs_alloc_flat_call(&afs_RXFSFetchData64, 32, (21 + 3 + 6) * 4); + call = afs_alloc_flat_call(net, &afs_RXFSFetchData64, 32, (21 + 3 + 6) * 4); if (!call) return -ENOMEM; @@ -531,6 +533,7 @@ int afs_fs_fetch_data(struct afs_server *server, bool async) { struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); __be32 *bp; if (upper_32_bits(req->pos) || @@ -540,7 +543,7 @@ int afs_fs_fetch_data(struct afs_server *server, _enter(""); - call = afs_alloc_flat_call(&afs_RXFSFetchData, 24, (21 + 3 + 6) * 4); + call = afs_alloc_flat_call(net, &afs_RXFSFetchData, 24, (21 + 3 + 6) * 4); if (!call) return -ENOMEM; @@ -590,7 +593,8 @@ static const struct afs_call_type afs_RXFSGiveUpCallBacks = { * give up a set of callbacks * - the callbacks are held in the server->cb_break ring */ -int afs_fs_give_up_callbacks(struct afs_server *server, +int afs_fs_give_up_callbacks(struct afs_net *net, + struct afs_server *server, bool async) { struct afs_call *call; @@ -610,7 +614,7 @@ int afs_fs_give_up_callbacks(struct afs_server *server, _debug("break %zu callbacks", ncallbacks); - call = afs_alloc_flat_call(&afs_RXFSGiveUpCallBacks, + call = afs_alloc_flat_call(net, &afs_RXFSGiveUpCallBacks, 12 + ncallbacks * 6 * 4, 0); if (!call) return -ENOMEM; @@ -699,6 +703,7 @@ int afs_fs_create(struct afs_server *server, bool async) { struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); size_t namesz, reqsz, padsz; __be32 *bp; @@ -708,7 +713,7 @@ int afs_fs_create(struct afs_server *server, padsz = (4 - (namesz & 3)) & 3; reqsz = (5 * 4) + namesz + padsz + (6 * 4); - call = afs_alloc_flat_call(&afs_RXFSCreateXXXX, reqsz, + call = afs_alloc_flat_call(net, &afs_RXFSCreateXXXX, reqsz, (3 + 21 + 21 + 3 + 6) * 4); if (!call) return -ENOMEM; @@ -789,6 +794,7 @@ int afs_fs_remove(struct afs_server *server, bool async) { struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); size_t namesz, reqsz, padsz; __be32 *bp; @@ -798,7 +804,7 @@ int afs_fs_remove(struct afs_server *server, padsz = (4 - (namesz & 3)) & 3; reqsz = (5 * 4) + namesz + padsz; - call = afs_alloc_flat_call(&afs_RXFSRemoveXXXX, reqsz, (21 + 6) * 4); + call = afs_alloc_flat_call(net, &afs_RXFSRemoveXXXX, reqsz, (21 + 6) * 4); if (!call) return -ENOMEM; @@ -870,6 +876,7 @@ int afs_fs_link(struct afs_server *server, bool async) { struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); size_t namesz, reqsz, padsz; __be32 *bp; @@ -879,7 +886,7 @@ int afs_fs_link(struct afs_server *server, padsz = (4 - (namesz & 3)) & 3; reqsz = (5 * 4) + namesz + padsz + (3 * 4); - call = afs_alloc_flat_call(&afs_RXFSLink, reqsz, (21 + 21 + 6) * 4); + call = afs_alloc_flat_call(net, &afs_RXFSLink, reqsz, (21 + 21 + 6) * 4); if (!call) return -ENOMEM; @@ -958,6 +965,7 @@ int afs_fs_symlink(struct afs_server *server, bool async) { struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); size_t namesz, reqsz, padsz, c_namesz, c_padsz; __be32 *bp; @@ -971,7 +979,7 @@ int afs_fs_symlink(struct afs_server *server, reqsz = (6 * 4) + namesz + padsz + c_namesz + c_padsz + (6 * 4); - call = afs_alloc_flat_call(&afs_RXFSSymlink, reqsz, + call = afs_alloc_flat_call(net, &afs_RXFSSymlink, reqsz, (3 + 21 + 21 + 6) * 4); if (!call) return -ENOMEM; @@ -1062,6 +1070,7 @@ int afs_fs_rename(struct afs_server *server, bool async) { struct afs_call *call; + struct afs_net *net = afs_v2net(orig_dvnode); size_t reqsz, o_namesz, o_padsz, n_namesz, n_padsz; __be32 *bp; @@ -1078,7 +1087,7 @@ int afs_fs_rename(struct afs_server *server, (3 * 4) + 4 + n_namesz + n_padsz; - call = afs_alloc_flat_call(&afs_RXFSRename, reqsz, (21 + 21 + 6) * 4); + call = afs_alloc_flat_call(net, &afs_RXFSRename, reqsz, (21 + 21 + 6) * 4); if (!call) return -ENOMEM; @@ -1172,12 +1181,13 @@ static int afs_fs_store_data64(struct afs_server *server, { struct afs_vnode *vnode = wb->vnode; struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); __be32 *bp; _enter(",%x,{%x:%u},,", key_serial(wb->key), vnode->fid.vid, vnode->fid.vnode); - call = afs_alloc_flat_call(&afs_RXFSStoreData64, + call = afs_alloc_flat_call(net, &afs_RXFSStoreData64, (4 + 6 + 3 * 2) * 4, (21 + 6) * 4); if (!call) @@ -1230,6 +1240,7 @@ int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb, { struct afs_vnode *vnode = wb->vnode; struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); loff_t size, pos, i_size; __be32 *bp; @@ -1254,7 +1265,7 @@ int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb, return afs_fs_store_data64(server, wb, first, last, offset, to, size, pos, i_size, async); - call = afs_alloc_flat_call(&afs_RXFSStoreData, + call = afs_alloc_flat_call(net, &afs_RXFSStoreData, (4 + 6 + 3) * 4, (21 + 6) * 4); if (!call) @@ -1356,6 +1367,7 @@ static int afs_fs_setattr_size64(struct afs_server *server, struct key *key, bool async) { struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); __be32 *bp; _enter(",%x,{%x:%u},,", @@ -1363,7 +1375,7 @@ static int afs_fs_setattr_size64(struct afs_server *server, struct key *key, ASSERT(attr->ia_valid & ATTR_SIZE); - call = afs_alloc_flat_call(&afs_RXFSStoreData64_as_Status, + call = afs_alloc_flat_call(net, &afs_RXFSStoreData64_as_Status, (4 + 6 + 3 * 2) * 4, (21 + 6) * 4); if (!call) @@ -1404,6 +1416,7 @@ static int afs_fs_setattr_size(struct afs_server *server, struct key *key, bool async) { struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); __be32 *bp; _enter(",%x,{%x:%u},,", @@ -1414,7 +1427,7 @@ static int afs_fs_setattr_size(struct afs_server *server, struct key *key, return afs_fs_setattr_size64(server, key, vnode, attr, async); - call = afs_alloc_flat_call(&afs_RXFSStoreData_as_Status, + call = afs_alloc_flat_call(net, &afs_RXFSStoreData_as_Status, (4 + 6 + 3) * 4, (21 + 6) * 4); if (!call) @@ -1452,6 +1465,7 @@ int afs_fs_setattr(struct afs_server *server, struct key *key, bool async) { struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); __be32 *bp; if (attr->ia_valid & ATTR_SIZE) @@ -1461,7 +1475,7 @@ int afs_fs_setattr(struct afs_server *server, struct key *key, _enter(",%x,{%x:%u},,", key_serial(key), vnode->fid.vid, vnode->fid.vnode); - call = afs_alloc_flat_call(&afs_RXFSStoreStatus, + call = afs_alloc_flat_call(net, &afs_RXFSStoreStatus, (4 + 6) * 4, (21 + 6) * 4); if (!call) @@ -1687,6 +1701,7 @@ int afs_fs_get_volume_status(struct afs_server *server, bool async) { struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); __be32 *bp; void *tmpbuf; @@ -1696,7 +1711,7 @@ int afs_fs_get_volume_status(struct afs_server *server, if (!tmpbuf) return -ENOMEM; - call = afs_alloc_flat_call(&afs_RXFSGetVolumeStatus, 2 * 4, 12 * 4); + call = afs_alloc_flat_call(net, &afs_RXFSGetVolumeStatus, 2 * 4, 12 * 4); if (!call) { kfree(tmpbuf); return -ENOMEM; @@ -1779,11 +1794,12 @@ int afs_fs_set_lock(struct afs_server *server, bool async) { struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); __be32 *bp; _enter(""); - call = afs_alloc_flat_call(&afs_RXFSSetLock, 5 * 4, 6 * 4); + call = afs_alloc_flat_call(net, &afs_RXFSSetLock, 5 * 4, 6 * 4); if (!call) return -ENOMEM; @@ -1812,11 +1828,12 @@ int afs_fs_extend_lock(struct afs_server *server, bool async) { struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); __be32 *bp; _enter(""); - call = afs_alloc_flat_call(&afs_RXFSExtendLock, 4 * 4, 6 * 4); + call = afs_alloc_flat_call(net, &afs_RXFSExtendLock, 4 * 4, 6 * 4); if (!call) return -ENOMEM; @@ -1844,11 +1861,12 @@ int afs_fs_release_lock(struct afs_server *server, bool async) { struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); __be32 *bp; _enter(""); - call = afs_alloc_flat_call(&afs_RXFSReleaseLock, 4 * 4, 6 * 4); + call = afs_alloc_flat_call(net, &afs_RXFSReleaseLock, 4 * 4, 6 * 4); if (!call) return -ENOMEM; diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 3f03f7888302..53bd11d73469 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -21,6 +21,7 @@ #include #include #include +#include #include #include "afs.h" @@ -48,6 +49,7 @@ struct afs_mount_params { afs_voltype_t type; /* type of volume requested */ int volnamesz; /* size of volume name */ const char *volname; /* name of volume to mount */ + struct afs_net *net; /* Network namespace in effect */ struct afs_cell *cell; /* cell in which to find volume */ struct afs_volume *volume; /* volume record */ struct key *key; /* key to use for secure mounting */ @@ -62,6 +64,7 @@ enum afs_call_state { AFS_CALL_AWAIT_ACK, /* awaiting final ACK of incoming call */ AFS_CALL_COMPLETE, /* Completed or failed */ }; + /* * a record of an in-progress RxRPC call */ @@ -72,6 +75,7 @@ struct afs_call { struct work_struct work; /* actual work processor */ struct rxrpc_call *rxcall; /* RxRPC call handle */ struct key *key; /* security for this call */ + struct afs_net *net; /* The network namespace */ struct afs_server *server; /* server affected by incoming CM call */ void *request; /* request data (first part) */ struct address_space *mapping; /* page set */ @@ -173,6 +177,7 @@ struct afs_writeback { * - there's one superblock per volume */ struct afs_super_info { + struct afs_net *net; /* Network namespace */ struct afs_volume *volume; /* volume record */ char rwparent; /* T if parent is R/W AFS volume */ }; @@ -192,12 +197,62 @@ struct afs_cache_cell { struct in_addr vl_servers[15]; /* cached cell VL servers */ }; +/* + * AFS network namespace record. + */ +struct afs_net { + struct afs_uuid uuid; + bool live; /* F if this namespace is being removed */ + + /* AF_RXRPC I/O stuff */ + struct socket *socket; + struct afs_call *spare_incoming_call; + struct work_struct charge_preallocation_work; + struct mutex socket_mutex; + atomic_t nr_outstanding_calls; + atomic_t nr_superblocks; + + /* Cell database */ + struct list_head cells; + struct afs_cell *ws_cell; + rwlock_t cells_lock; + struct rw_semaphore cells_sem; + wait_queue_head_t cells_freeable_wq; + + struct rw_semaphore proc_cells_sem; + struct list_head proc_cells; + + /* Volume location database */ + struct list_head vl_updates; /* VL records in need-update order */ + struct list_head vl_graveyard; /* Inactive VL records */ + struct delayed_work vl_reaper; + struct delayed_work vl_updater; + spinlock_t vl_updates_lock; + spinlock_t vl_graveyard_lock; + + /* File locking renewal management */ + struct mutex lock_manager_mutex; + + /* Server database */ + struct rb_root servers; /* Active servers */ + rwlock_t servers_lock; + struct list_head server_graveyard; /* Inactive server LRU list */ + spinlock_t server_graveyard_lock; + struct delayed_work server_reaper; + + /* Misc */ + struct proc_dir_entry *proc_afs; /* /proc/net/afs directory */ +}; + +extern struct afs_net __afs_net;// Dummy AFS network namespace; TODO: replace with real netns + /* * AFS cell record */ struct afs_cell { atomic_t usage; struct list_head link; /* main cell list link */ + struct afs_net *net; /* The network namespace */ struct key *anonymous_key; /* anonymous user key for this cell */ struct list_head proc_link; /* /proc cell list link */ #ifdef CONFIG_AFS_FSCACHE @@ -411,15 +466,6 @@ struct afs_interface { unsigned mtu; /* MTU of interface */ }; -struct afs_uuid { - __be32 time_low; /* low part of timestamp */ - __be16 time_mid; /* mid part of timestamp */ - __be16 time_hi_and_version; /* high part of timestamp and version */ - __u8 clock_seq_hi_and_reserved; /* clock seq hi and variant */ - __u8 clock_seq_low; /* clock seq low */ - __u8 node[6]; /* spatially unique node ID (MAC addr) */ -}; - /*****************************************************************************/ /* * cache.c @@ -440,6 +486,8 @@ extern struct fscache_cookie_def afs_vnode_cache_index_def; /* * callback.c */ +extern struct workqueue_struct *afs_callback_update_worker; + extern void afs_init_callback_state(struct afs_server *); extern void afs_broken_callback_work(struct work_struct *); extern void afs_break_callbacks(struct afs_server *, size_t, @@ -448,22 +496,17 @@ extern void afs_discard_callback_on_delete(struct afs_vnode *); extern void afs_give_up_callback(struct afs_vnode *); extern void afs_dispatch_give_up_callbacks(struct work_struct *); extern void afs_flush_callback_breaks(struct afs_server *); -extern int __init afs_callback_update_init(void); -extern void afs_callback_update_kill(void); /* * cell.c */ -extern struct rw_semaphore afs_proc_cells_sem; -extern struct list_head afs_proc_cells; - #define afs_get_cell(C) do { atomic_inc(&(C)->usage); } while(0) -extern int afs_cell_init(char *); -extern struct afs_cell *afs_cell_create(const char *, unsigned, char *, bool); -extern struct afs_cell *afs_cell_lookup(const char *, unsigned, bool); +extern int afs_cell_init(struct afs_net *, char *); +extern struct afs_cell *afs_cell_create(struct afs_net *, const char *, unsigned, char *, bool); +extern struct afs_cell *afs_cell_lookup(struct afs_net *, const char *, unsigned, bool); extern struct afs_cell *afs_grab_cell(struct afs_cell *); extern void afs_put_cell(struct afs_cell *); -extern void afs_cell_purge(void); +extern void __net_exit afs_cell_purge(struct afs_net *); /* * cmservice.c @@ -492,7 +535,8 @@ extern void afs_put_read(struct afs_read *); /* * flock.c */ -extern void __exit afs_kill_lock_manager(void); +extern struct workqueue_struct *afs_lock_manager; + extern void afs_lock_work(struct work_struct *); extern void afs_lock_may_be_available(struct afs_vnode *); extern int afs_lock(struct file *, int, struct file_lock *); @@ -504,7 +548,7 @@ extern int afs_flock(struct file *, int, struct file_lock *); extern int afs_fs_fetch_file_status(struct afs_server *, struct key *, struct afs_vnode *, struct afs_volsync *, bool); -extern int afs_fs_give_up_callbacks(struct afs_server *, bool); +extern int afs_fs_give_up_callbacks(struct afs_net *, struct afs_server *, bool); extern int afs_fs_fetch_data(struct afs_server *, struct key *, struct afs_vnode *, struct afs_read *, bool); extern int afs_fs_create(struct afs_server *, struct key *, @@ -554,7 +598,35 @@ extern int afs_drop_inode(struct inode *); * main.c */ extern struct workqueue_struct *afs_wq; -extern struct afs_uuid afs_uuid; + +static inline struct afs_net *afs_d2net(struct dentry *dentry) +{ + return &__afs_net; +} + +static inline struct afs_net *afs_i2net(struct inode *inode) +{ + return &__afs_net; +} + +static inline struct afs_net *afs_v2net(struct afs_vnode *vnode) +{ + return &__afs_net; +} + +static inline struct afs_net *afs_sock2net(struct sock *sk) +{ + return &__afs_net; +} + +static inline struct afs_net *afs_get_net(struct afs_net *net) +{ + return net; +} + +static inline void afs_put_net(struct afs_net *net) +{ +} /* * misc.c @@ -579,23 +651,24 @@ extern int afs_get_ipv4_interfaces(struct afs_interface *, size_t, bool); /* * proc.c */ -extern int afs_proc_init(void); -extern void afs_proc_cleanup(void); -extern int afs_proc_cell_setup(struct afs_cell *); -extern void afs_proc_cell_remove(struct afs_cell *); +extern int __net_init afs_proc_init(struct afs_net *); +extern void __net_exit afs_proc_cleanup(struct afs_net *); +extern int afs_proc_cell_setup(struct afs_net *, struct afs_cell *); +extern void afs_proc_cell_remove(struct afs_net *, struct afs_cell *); /* * rxrpc.c */ -extern struct socket *afs_socket; -extern atomic_t afs_outstanding_calls; +extern struct workqueue_struct *afs_async_calls; -extern int afs_open_socket(void); -extern void afs_close_socket(void); +extern int __net_init afs_open_socket(struct afs_net *); +extern void __net_exit afs_close_socket(struct afs_net *); +extern void afs_charge_preallocation(struct work_struct *); extern void afs_put_call(struct afs_call *); extern int afs_queue_call_work(struct afs_call *); extern int afs_make_call(struct in_addr *, struct afs_call *, gfp_t, bool); -extern struct afs_call *afs_alloc_flat_call(const struct afs_call_type *, +extern struct afs_call *afs_alloc_flat_call(struct afs_net *, + const struct afs_call_type *, size_t, size_t); extern void afs_flat_call_destructor(struct afs_call *); extern void afs_send_empty_reply(struct afs_call *); @@ -629,37 +702,45 @@ do { \ extern struct afs_server *afs_lookup_server(struct afs_cell *, const struct in_addr *); -extern struct afs_server *afs_find_server(const struct sockaddr_rxrpc *); +extern struct afs_server *afs_find_server(struct afs_net *, + const struct sockaddr_rxrpc *); extern void afs_put_server(struct afs_server *); -extern void __exit afs_purge_servers(void); +extern void afs_reap_server(struct work_struct *); +extern void __net_exit afs_purge_servers(struct afs_net *); /* * super.c */ -extern int afs_fs_init(void); -extern void afs_fs_exit(void); +extern int __init afs_fs_init(void); +extern void __exit afs_fs_exit(void); /* * vlclient.c */ -extern int afs_vl_get_entry_by_name(struct in_addr *, struct key *, +extern int afs_vl_get_entry_by_name(struct afs_net *, + struct in_addr *, struct key *, const char *, struct afs_cache_vlocation *, bool); -extern int afs_vl_get_entry_by_id(struct in_addr *, struct key *, +extern int afs_vl_get_entry_by_id(struct afs_net *, + struct in_addr *, struct key *, afs_volid_t, afs_voltype_t, struct afs_cache_vlocation *, bool); /* * vlocation.c */ +extern struct workqueue_struct *afs_vlocation_update_worker; + #define afs_get_vlocation(V) do { atomic_inc(&(V)->usage); } while(0) -extern int __init afs_vlocation_update_init(void); -extern struct afs_vlocation *afs_vlocation_lookup(struct afs_cell *, +extern struct afs_vlocation *afs_vlocation_lookup(struct afs_net *, + struct afs_cell *, struct key *, const char *, size_t); -extern void afs_put_vlocation(struct afs_vlocation *); -extern void afs_vlocation_purge(void); +extern void afs_put_vlocation(struct afs_net *, struct afs_vlocation *); +extern void afs_vlocation_updater(struct work_struct *); +extern void afs_vlocation_reaper(struct work_struct *); +extern void __net_exit afs_vlocation_purge(struct afs_net *); /* * vnode.c @@ -707,7 +788,7 @@ extern int afs_vnode_release_lock(struct afs_vnode *, struct key *); */ #define afs_get_volume(V) do { atomic_inc(&(V)->usage); } while(0) -extern void afs_put_volume(struct afs_volume *); +extern void afs_put_volume(struct afs_net *, struct afs_volume *); extern struct afs_volume *afs_volume_lookup(struct afs_mount_params *); extern struct afs_server *afs_volume_pick_fileserver(struct afs_vnode *); extern int afs_volume_release_fileserver(struct afs_vnode *, diff --git a/fs/afs/main.c b/fs/afs/main.c index 9944770849da..87b1a9c8000d 100644 --- a/fs/afs/main.c +++ b/fs/afs/main.c @@ -31,30 +31,104 @@ static char *rootcell; module_param(rootcell, charp, 0); MODULE_PARM_DESC(rootcell, "root AFS cell name and VL server IP addr list"); -struct afs_uuid afs_uuid; struct workqueue_struct *afs_wq; +struct afs_net __afs_net; + +/* + * Initialise an AFS network namespace record. + */ +static int __net_init afs_net_init(struct afs_net *net) +{ + int ret; + + net->live = true; + generate_random_uuid((unsigned char *)&net->uuid); + + INIT_WORK(&net->charge_preallocation_work, afs_charge_preallocation); + mutex_init(&net->socket_mutex); + INIT_LIST_HEAD(&net->cells); + rwlock_init(&net->cells_lock); + init_rwsem(&net->cells_sem); + init_waitqueue_head(&net->cells_freeable_wq); + init_rwsem(&net->proc_cells_sem); + INIT_LIST_HEAD(&net->proc_cells); + INIT_LIST_HEAD(&net->vl_updates); + INIT_LIST_HEAD(&net->vl_graveyard); + INIT_DELAYED_WORK(&net->vl_reaper, afs_vlocation_reaper); + INIT_DELAYED_WORK(&net->vl_updater, afs_vlocation_updater); + spin_lock_init(&net->vl_updates_lock); + spin_lock_init(&net->vl_graveyard_lock); + net->servers = RB_ROOT; + rwlock_init(&net->servers_lock); + INIT_LIST_HEAD(&net->server_graveyard); + spin_lock_init(&net->server_graveyard_lock); + INIT_DELAYED_WORK(&net->server_reaper, afs_reap_server); + + /* Register the /proc stuff */ + ret = afs_proc_init(net); + if (ret < 0) + goto error_proc; + + /* Initialise the cell DB */ + ret = afs_cell_init(net, rootcell); + if (ret < 0) + goto error_cell_init; + + /* Create the RxRPC transport */ + ret = afs_open_socket(net); + if (ret < 0) + goto error_open_socket; + + return 0; + +error_open_socket: + afs_vlocation_purge(net); + afs_cell_purge(net); +error_cell_init: + afs_proc_cleanup(net); +error_proc: + return ret; +} + +/* + * Clean up and destroy an AFS network namespace record. + */ +static void __net_exit afs_net_exit(struct afs_net *net) +{ + net->live = false; + afs_close_socket(net); + afs_purge_servers(net); + afs_vlocation_purge(net); + afs_cell_purge(net); + afs_proc_cleanup(net); +} /* * initialise the AFS client FS module */ static int __init afs_init(void) { - int ret; + int ret = -ENOMEM; printk(KERN_INFO "kAFS: Red Hat AFS client v0.1 registering.\n"); - generate_random_uuid((unsigned char *)&afs_uuid); - - /* create workqueue */ - ret = -ENOMEM; afs_wq = alloc_workqueue("afs", 0, 0); if (!afs_wq) - return ret; - - /* register the /proc stuff */ - ret = afs_proc_init(); - if (ret < 0) - goto error_proc; + goto error_afs_wq; + afs_async_calls = alloc_workqueue("kafsd", WQ_MEM_RECLAIM, 0); + if (!afs_async_calls) + goto error_async; + afs_vlocation_update_worker = + alloc_workqueue("kafs_vlupdated", WQ_MEM_RECLAIM, 0); + if (!afs_vlocation_update_worker) + goto error_vl_up; + afs_callback_update_worker = + alloc_ordered_workqueue("kafs_callbackd", WQ_MEM_RECLAIM); + if (!afs_callback_update_worker) + goto error_callback; + afs_lock_manager = alloc_workqueue("kafs_lockd", WQ_MEM_RECLAIM, 0); + if (!afs_lock_manager) + goto error_lockmgr; #ifdef CONFIG_AFS_FSCACHE /* we want to be able to cache */ @@ -63,25 +137,9 @@ static int __init afs_init(void) goto error_cache; #endif - /* initialise the cell DB */ - ret = afs_cell_init(rootcell); - if (ret < 0) - goto error_cell_init; - - /* initialise the VL update process */ - ret = afs_vlocation_update_init(); - if (ret < 0) - goto error_vl_update_init; - - /* initialise the callback update process */ - ret = afs_callback_update_init(); + ret = afs_net_init(&__afs_net); if (ret < 0) - goto error_callback_update_init; - - /* create the RxRPC transport */ - ret = afs_open_socket(); - if (ret < 0) - goto error_open_socket; + goto error_net; /* register the filesystems */ ret = afs_fs_init(); @@ -91,21 +149,22 @@ static int __init afs_init(void) return ret; error_fs: - afs_close_socket(); -error_open_socket: - afs_callback_update_kill(); -error_callback_update_init: - afs_vlocation_purge(); -error_vl_update_init: - afs_cell_purge(); -error_cell_init: + afs_net_exit(&__afs_net); +error_net: #ifdef CONFIG_AFS_FSCACHE fscache_unregister_netfs(&afs_cache_netfs); error_cache: #endif - afs_proc_cleanup(); -error_proc: + destroy_workqueue(afs_lock_manager); +error_lockmgr: + destroy_workqueue(afs_callback_update_worker); +error_callback: + destroy_workqueue(afs_vlocation_update_worker); +error_vl_up: + destroy_workqueue(afs_async_calls); +error_async: destroy_workqueue(afs_wq); +error_afs_wq: rcu_barrier(); printk(KERN_ERR "kAFS: failed to register: %d\n", ret); return ret; @@ -124,17 +183,15 @@ static void __exit afs_exit(void) printk(KERN_INFO "kAFS: Red Hat AFS client v0.1 unregistering.\n"); afs_fs_exit(); - afs_kill_lock_manager(); - afs_close_socket(); - afs_purge_servers(); - afs_callback_update_kill(); - afs_vlocation_purge(); - destroy_workqueue(afs_wq); - afs_cell_purge(); + afs_net_exit(&__afs_net); #ifdef CONFIG_AFS_FSCACHE fscache_unregister_netfs(&afs_cache_netfs); #endif - afs_proc_cleanup(); + destroy_workqueue(afs_lock_manager); + destroy_workqueue(afs_callback_update_worker); + destroy_workqueue(afs_vlocation_update_worker); + destroy_workqueue(afs_async_calls); + destroy_workqueue(afs_wq); rcu_barrier(); } diff --git a/fs/afs/proc.c b/fs/afs/proc.c index 35efb9a31dd7..c93433460348 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -17,8 +17,15 @@ #include #include "internal.h" -static struct proc_dir_entry *proc_afs; +static inline struct afs_net *afs_proc2net(struct file *f) +{ + return &__afs_net; +} +static inline struct afs_net *afs_seq2net(struct seq_file *m) +{ + return &__afs_net; // TODO: use seq_file_net(m) +} static int afs_proc_cells_open(struct inode *inode, struct file *file); static void *afs_proc_cells_start(struct seq_file *p, loff_t *pos); @@ -122,23 +129,23 @@ static const struct file_operations afs_proc_cell_servers_fops = { /* * initialise the /proc/fs/afs/ directory */ -int afs_proc_init(void) +int afs_proc_init(struct afs_net *net) { _enter(""); - proc_afs = proc_mkdir("fs/afs", NULL); - if (!proc_afs) + net->proc_afs = proc_mkdir("fs/afs", NULL); + if (!net->proc_afs) goto error_dir; - if (!proc_create("cells", 0644, proc_afs, &afs_proc_cells_fops) || - !proc_create("rootcell", 0644, proc_afs, &afs_proc_rootcell_fops)) + if (!proc_create("cells", 0644, net->proc_afs, &afs_proc_cells_fops) || + !proc_create("rootcell", 0644, net->proc_afs, &afs_proc_rootcell_fops)) goto error_tree; _leave(" = 0"); return 0; error_tree: - remove_proc_subtree("fs/afs", NULL); + proc_remove(net->proc_afs); error_dir: _leave(" = -ENOMEM"); return -ENOMEM; @@ -147,9 +154,10 @@ error_dir: /* * clean up the /proc/fs/afs/ directory */ -void afs_proc_cleanup(void) +void afs_proc_cleanup(struct afs_net *net) { - remove_proc_subtree("fs/afs", NULL); + proc_remove(net->proc_afs); + net->proc_afs = NULL; } /* @@ -176,25 +184,30 @@ static int afs_proc_cells_open(struct inode *inode, struct file *file) */ static void *afs_proc_cells_start(struct seq_file *m, loff_t *_pos) { - /* lock the list against modification */ - down_read(&afs_proc_cells_sem); - return seq_list_start_head(&afs_proc_cells, *_pos); + struct afs_net *net = afs_seq2net(m); + + down_read(&net->proc_cells_sem); + return seq_list_start_head(&net->proc_cells, *_pos); } /* * move to next cell in cells list */ -static void *afs_proc_cells_next(struct seq_file *p, void *v, loff_t *pos) +static void *afs_proc_cells_next(struct seq_file *m, void *v, loff_t *pos) { - return seq_list_next(v, &afs_proc_cells, pos); + struct afs_net *net = afs_seq2net(m); + + return seq_list_next(v, &net->proc_cells, pos); } /* * clean up after reading from the cells list */ -static void afs_proc_cells_stop(struct seq_file *p, void *v) +static void afs_proc_cells_stop(struct seq_file *m, void *v) { - up_read(&afs_proc_cells_sem); + struct afs_net *net = afs_seq2net(m); + + up_read(&net->proc_cells_sem); } /* @@ -203,8 +216,9 @@ static void afs_proc_cells_stop(struct seq_file *p, void *v) static int afs_proc_cells_show(struct seq_file *m, void *v) { struct afs_cell *cell = list_entry(v, struct afs_cell, proc_link); + struct afs_net *net = afs_seq2net(m); - if (v == &afs_proc_cells) { + if (v == &net->proc_cells) { /* display header on line 1 */ seq_puts(m, "USE NAME\n"); return 0; @@ -223,6 +237,7 @@ static int afs_proc_cells_show(struct seq_file *m, void *v) static ssize_t afs_proc_cells_write(struct file *file, const char __user *buf, size_t size, loff_t *_pos) { + struct afs_net *net = afs_proc2net(file); char *kbuf, *name, *args; int ret; @@ -264,7 +279,7 @@ static ssize_t afs_proc_cells_write(struct file *file, const char __user *buf, if (strcmp(kbuf, "add") == 0) { struct afs_cell *cell; - cell = afs_cell_create(name, strlen(name), args, false); + cell = afs_cell_create(net, name, strlen(name), args, false); if (IS_ERR(cell)) { ret = PTR_ERR(cell); goto done; @@ -303,6 +318,7 @@ static ssize_t afs_proc_rootcell_write(struct file *file, const char __user *buf, size_t size, loff_t *_pos) { + struct afs_net *net = afs_proc2net(file); char *kbuf, *s; int ret; @@ -322,7 +338,7 @@ static ssize_t afs_proc_rootcell_write(struct file *file, /* determine command to perform */ _debug("rootcell=%s", kbuf); - ret = afs_cell_init(kbuf); + ret = afs_cell_init(net, kbuf); if (ret >= 0) ret = size; /* consume everything, always */ @@ -334,13 +350,13 @@ static ssize_t afs_proc_rootcell_write(struct file *file, /* * initialise /proc/fs/afs// */ -int afs_proc_cell_setup(struct afs_cell *cell) +int afs_proc_cell_setup(struct afs_net *net, struct afs_cell *cell) { struct proc_dir_entry *dir; _enter("%p{%s}", cell, cell->name); - dir = proc_mkdir(cell->name, proc_afs); + dir = proc_mkdir(cell->name, net->proc_afs); if (!dir) goto error_dir; @@ -356,7 +372,7 @@ int afs_proc_cell_setup(struct afs_cell *cell) return 0; error_tree: - remove_proc_subtree(cell->name, proc_afs); + remove_proc_subtree(cell->name, net->proc_afs); error_dir: _leave(" = -ENOMEM"); return -ENOMEM; @@ -365,11 +381,11 @@ error_dir: /* * remove /proc/fs/afs// */ -void afs_proc_cell_remove(struct afs_cell *cell) +void afs_proc_cell_remove(struct afs_net *net, struct afs_cell *cell) { _enter(""); - remove_proc_subtree(cell->name, proc_afs); + remove_proc_subtree(cell->name, net->proc_afs); _leave(""); } diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 77f5420a1a24..656ceb285b85 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -17,10 +17,7 @@ #include "internal.h" #include "afs_cm.h" -struct socket *afs_socket; /* my RxRPC socket */ -static struct workqueue_struct *afs_async_calls; -static struct afs_call *afs_spare_incoming_call; -atomic_t afs_outstanding_calls; +struct workqueue_struct *afs_async_calls; static void afs_wake_up_call_waiter(struct sock *, struct rxrpc_call *, unsigned long); static int afs_wait_for_call_to_complete(struct afs_call *); @@ -37,15 +34,11 @@ static const struct afs_call_type afs_RXCMxxxx = { .abort_to_error = afs_abort_to_error, }; -static void afs_charge_preallocation(struct work_struct *); - -static DECLARE_WORK(afs_charge_preallocation_work, afs_charge_preallocation); - /* * open an RxRPC socket and bind it to be a server for callback notifications * - the socket is left in blocking mode and non-blocking ops use MSG_DONTWAIT */ -int afs_open_socket(void) +int afs_open_socket(struct afs_net *net) { struct sockaddr_rxrpc srx; struct socket *socket; @@ -53,11 +46,6 @@ int afs_open_socket(void) _enter(""); - ret = -ENOMEM; - afs_async_calls = alloc_workqueue("kafsd", WQ_MEM_RECLAIM, 0); - if (!afs_async_calls) - goto error_0; - ret = sock_create_kern(&init_net, AF_RXRPC, SOCK_DGRAM, PF_INET, &socket); if (ret < 0) goto error_1; @@ -85,16 +73,14 @@ int afs_open_socket(void) if (ret < 0) goto error_2; - afs_socket = socket; - afs_charge_preallocation(NULL); + net->socket = socket; + afs_charge_preallocation(&net->charge_preallocation_work); _leave(" = 0"); return 0; error_2: sock_release(socket); error_1: - destroy_workqueue(afs_async_calls); -error_0: _leave(" = %d", ret); return ret; } @@ -102,36 +88,36 @@ error_0: /* * close the RxRPC socket AFS was using */ -void afs_close_socket(void) +void afs_close_socket(struct afs_net *net) { _enter(""); - kernel_listen(afs_socket, 0); + kernel_listen(net->socket, 0); flush_workqueue(afs_async_calls); - if (afs_spare_incoming_call) { - afs_put_call(afs_spare_incoming_call); - afs_spare_incoming_call = NULL; + if (net->spare_incoming_call) { + afs_put_call(net->spare_incoming_call); + net->spare_incoming_call = NULL; } - _debug("outstanding %u", atomic_read(&afs_outstanding_calls)); - wait_on_atomic_t(&afs_outstanding_calls, atomic_t_wait, + _debug("outstanding %u", atomic_read(&net->nr_outstanding_calls)); + wait_on_atomic_t(&net->nr_outstanding_calls, atomic_t_wait, TASK_UNINTERRUPTIBLE); _debug("no outstanding calls"); - kernel_sock_shutdown(afs_socket, SHUT_RDWR); + kernel_sock_shutdown(net->socket, SHUT_RDWR); flush_workqueue(afs_async_calls); - sock_release(afs_socket); + sock_release(net->socket); _debug("dework"); - destroy_workqueue(afs_async_calls); _leave(""); } /* * Allocate a call. */ -static struct afs_call *afs_alloc_call(const struct afs_call_type *type, +static struct afs_call *afs_alloc_call(struct afs_net *net, + const struct afs_call_type *type, gfp_t gfp) { struct afs_call *call; @@ -142,11 +128,12 @@ static struct afs_call *afs_alloc_call(const struct afs_call_type *type, return NULL; call->type = type; + call->net = net; atomic_set(&call->usage, 1); INIT_WORK(&call->async_work, afs_process_async_call); init_waitqueue_head(&call->waitq); - o = atomic_inc_return(&afs_outstanding_calls); + o = atomic_inc_return(&net->nr_outstanding_calls); trace_afs_call(call, afs_call_trace_alloc, 1, o, __builtin_return_address(0)); return call; @@ -157,8 +144,9 @@ static struct afs_call *afs_alloc_call(const struct afs_call_type *type, */ void afs_put_call(struct afs_call *call) { + struct afs_net *net = call->net; int n = atomic_dec_return(&call->usage); - int o = atomic_read(&afs_outstanding_calls); + int o = atomic_read(&net->nr_outstanding_calls); trace_afs_call(call, afs_call_trace_put, n + 1, o, __builtin_return_address(0)); @@ -169,7 +157,7 @@ void afs_put_call(struct afs_call *call) ASSERT(call->type->name != NULL); if (call->rxcall) { - rxrpc_kernel_end_call(afs_socket, call->rxcall); + rxrpc_kernel_end_call(net->socket, call->rxcall); call->rxcall = NULL; } if (call->type->destructor) @@ -178,11 +166,11 @@ void afs_put_call(struct afs_call *call) kfree(call->request); kfree(call); - o = atomic_dec_return(&afs_outstanding_calls); + o = atomic_dec_return(&net->nr_outstanding_calls); trace_afs_call(call, afs_call_trace_free, 0, o, __builtin_return_address(0)); if (o == 0) - wake_up_atomic_t(&afs_outstanding_calls); + wake_up_atomic_t(&net->nr_outstanding_calls); } } @@ -194,7 +182,7 @@ int afs_queue_call_work(struct afs_call *call) int u = atomic_inc_return(&call->usage); trace_afs_call(call, afs_call_trace_work, u, - atomic_read(&afs_outstanding_calls), + atomic_read(&call->net->nr_outstanding_calls), __builtin_return_address(0)); INIT_WORK(&call->work, call->type->work); @@ -207,12 +195,13 @@ int afs_queue_call_work(struct afs_call *call) /* * allocate a call with flat request and reply buffers */ -struct afs_call *afs_alloc_flat_call(const struct afs_call_type *type, +struct afs_call *afs_alloc_flat_call(struct afs_net *net, + const struct afs_call_type *type, size_t request_size, size_t reply_max) { struct afs_call *call; - call = afs_alloc_call(type, GFP_NOFS); + call = afs_alloc_call(net, type, GFP_NOFS); if (!call) goto nomem_call; @@ -317,7 +306,7 @@ static int afs_send_pages(struct afs_call *call, struct msghdr *msg) bytes = msg->msg_iter.count; nr = msg->msg_iter.nr_segs; - ret = rxrpc_kernel_send_data(afs_socket, call->rxcall, msg, + ret = rxrpc_kernel_send_data(call->net->socket, call->rxcall, msg, bytes, afs_notify_end_request_tx); for (loop = 0; loop < nr; loop++) put_page(bv[loop].bv_page); @@ -352,7 +341,7 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, _debug("____MAKE %p{%s,%x} [%d]____", call, call->type->name, key_serial(call->key), - atomic_read(&afs_outstanding_calls)); + atomic_read(&call->net->nr_outstanding_calls)); call->async = async; @@ -376,7 +365,7 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, } /* create a call */ - rxcall = rxrpc_kernel_begin_call(afs_socket, &srx, call->key, + rxcall = rxrpc_kernel_begin_call(call->net->socket, &srx, call->key, (unsigned long)call, tx_total_len, gfp, (async ? @@ -410,7 +399,7 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, */ if (!call->send_pages) call->state = AFS_CALL_AWAIT_REPLY; - ret = rxrpc_kernel_send_data(afs_socket, rxcall, + ret = rxrpc_kernel_send_data(call->net->socket, rxcall, &msg, call->request_size, afs_notify_end_request_tx); if (ret < 0) @@ -432,13 +421,14 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, error_do_abort: call->state = AFS_CALL_COMPLETE; if (ret != -ECONNABORTED) { - rxrpc_kernel_abort_call(afs_socket, rxcall, RX_USER_ABORT, - ret, "KSD"); + rxrpc_kernel_abort_call(call->net->socket, rxcall, + RX_USER_ABORT, ret, "KSD"); } else { abort_code = 0; offset = 0; - rxrpc_kernel_recv_data(afs_socket, rxcall, NULL, 0, &offset, - false, &abort_code, &call->service_id); + rxrpc_kernel_recv_data(call->net->socket, rxcall, NULL, + 0, &offset, false, &abort_code, + &call->service_id); ret = call->type->abort_to_error(abort_code); } error_kill_call: @@ -464,7 +454,8 @@ static void afs_deliver_to_call(struct afs_call *call) ) { if (call->state == AFS_CALL_AWAIT_ACK) { size_t offset = 0; - ret = rxrpc_kernel_recv_data(afs_socket, call->rxcall, + ret = rxrpc_kernel_recv_data(call->net->socket, + call->rxcall, NULL, 0, &offset, false, &call->abort_code, &call->service_id); @@ -492,12 +483,12 @@ static void afs_deliver_to_call(struct afs_call *call) goto call_complete; case -ENOTCONN: abort_code = RX_CALL_DEAD; - rxrpc_kernel_abort_call(afs_socket, call->rxcall, + rxrpc_kernel_abort_call(call->net->socket, call->rxcall, abort_code, ret, "KNC"); goto save_error; case -ENOTSUPP: abort_code = RXGEN_OPCODE; - rxrpc_kernel_abort_call(afs_socket, call->rxcall, + rxrpc_kernel_abort_call(call->net->socket, call->rxcall, abort_code, ret, "KIV"); goto save_error; case -ENODATA: @@ -507,7 +498,7 @@ static void afs_deliver_to_call(struct afs_call *call) abort_code = RXGEN_CC_UNMARSHAL; if (call->state != AFS_CALL_AWAIT_REPLY) abort_code = RXGEN_SS_UNMARSHAL; - rxrpc_kernel_abort_call(afs_socket, call->rxcall, + rxrpc_kernel_abort_call(call->net->socket, call->rxcall, abort_code, -EBADMSG, "KUM"); goto save_error; } @@ -541,13 +532,13 @@ static int afs_wait_for_call_to_complete(struct afs_call *call) _enter(""); - rtt = rxrpc_kernel_get_rtt(afs_socket, call->rxcall); + rtt = rxrpc_kernel_get_rtt(call->net->socket, call->rxcall); rtt2 = nsecs_to_jiffies64(rtt) * 2; if (rtt2 < 2) rtt2 = 2; timeout = rtt2; - last_life = rxrpc_kernel_check_life(afs_socket, call->rxcall); + last_life = rxrpc_kernel_check_life(call->net->socket, call->rxcall); add_wait_queue(&call->waitq, &myself); for (;;) { @@ -564,7 +555,7 @@ static int afs_wait_for_call_to_complete(struct afs_call *call) if (call->state == AFS_CALL_COMPLETE) break; - life = rxrpc_kernel_check_life(afs_socket, call->rxcall); + life = rxrpc_kernel_check_life(call->net->socket, call->rxcall); if (timeout == 0 && life == last_life && signal_pending(current)) break; @@ -583,7 +574,7 @@ static int afs_wait_for_call_to_complete(struct afs_call *call) /* Kill off the call if it's still live. */ if (call->state < AFS_CALL_COMPLETE) { _debug("call interrupted"); - rxrpc_kernel_abort_call(afs_socket, call->rxcall, + rxrpc_kernel_abort_call(call->net->socket, call->rxcall, RX_USER_ABORT, -EINTR, "KWI"); } @@ -621,7 +612,7 @@ static void afs_wake_up_async_call(struct sock *sk, struct rxrpc_call *rxcall, u = __atomic_add_unless(&call->usage, 1, 0); if (u != 0) { trace_afs_call(call, afs_call_trace_wake, u, - atomic_read(&afs_outstanding_calls), + atomic_read(&call->net->nr_outstanding_calls), __builtin_return_address(0)); if (!queue_work(afs_async_calls, &call->async_work)) @@ -685,13 +676,15 @@ static void afs_rx_attach(struct rxrpc_call *rxcall, unsigned long user_call_ID) /* * Charge the incoming call preallocation. */ -static void afs_charge_preallocation(struct work_struct *work) +void afs_charge_preallocation(struct work_struct *work) { - struct afs_call *call = afs_spare_incoming_call; + struct afs_net *net = + container_of(work, struct afs_net, charge_preallocation_work); + struct afs_call *call = net->spare_incoming_call; for (;;) { if (!call) { - call = afs_alloc_call(&afs_RXCMxxxx, GFP_KERNEL); + call = afs_alloc_call(net, &afs_RXCMxxxx, GFP_KERNEL); if (!call) break; @@ -700,7 +693,7 @@ static void afs_charge_preallocation(struct work_struct *work) init_waitqueue_head(&call->waitq); } - if (rxrpc_kernel_charge_accept(afs_socket, + if (rxrpc_kernel_charge_accept(net->socket, afs_wake_up_async_call, afs_rx_attach, (unsigned long)call, @@ -708,7 +701,7 @@ static void afs_charge_preallocation(struct work_struct *work) break; call = NULL; } - afs_spare_incoming_call = call; + net->spare_incoming_call = call; } /* @@ -729,7 +722,9 @@ static void afs_rx_discard_new_call(struct rxrpc_call *rxcall, static void afs_rx_new_call(struct sock *sk, struct rxrpc_call *rxcall, unsigned long user_call_ID) { - queue_work(afs_wq, &afs_charge_preallocation_work); + struct afs_net *net = afs_sock2net(sk); + + queue_work(afs_wq, &net->charge_preallocation_work); } /* @@ -784,11 +779,12 @@ static void afs_notify_end_reply_tx(struct sock *sock, */ void afs_send_empty_reply(struct afs_call *call) { + struct afs_net *net = call->net; struct msghdr msg; _enter(""); - rxrpc_kernel_set_tx_length(afs_socket, call->rxcall, 0); + rxrpc_kernel_set_tx_length(net->socket, call->rxcall, 0); msg.msg_name = NULL; msg.msg_namelen = 0; @@ -798,7 +794,7 @@ void afs_send_empty_reply(struct afs_call *call) msg.msg_flags = 0; call->state = AFS_CALL_AWAIT_ACK; - switch (rxrpc_kernel_send_data(afs_socket, call->rxcall, &msg, 0, + switch (rxrpc_kernel_send_data(net->socket, call->rxcall, &msg, 0, afs_notify_end_reply_tx)) { case 0: _leave(" [replied]"); @@ -806,7 +802,7 @@ void afs_send_empty_reply(struct afs_call *call) case -ENOMEM: _debug("oom"); - rxrpc_kernel_abort_call(afs_socket, call->rxcall, + rxrpc_kernel_abort_call(net->socket, call->rxcall, RX_USER_ABORT, -ENOMEM, "KOO"); default: _leave(" [error]"); @@ -819,13 +815,14 @@ void afs_send_empty_reply(struct afs_call *call) */ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) { + struct afs_net *net = call->net; struct msghdr msg; struct kvec iov[1]; int n; _enter(""); - rxrpc_kernel_set_tx_length(afs_socket, call->rxcall, len); + rxrpc_kernel_set_tx_length(net->socket, call->rxcall, len); iov[0].iov_base = (void *) buf; iov[0].iov_len = len; @@ -837,7 +834,7 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) msg.msg_flags = 0; call->state = AFS_CALL_AWAIT_ACK; - n = rxrpc_kernel_send_data(afs_socket, call->rxcall, &msg, len, + n = rxrpc_kernel_send_data(net->socket, call->rxcall, &msg, len, afs_notify_end_reply_tx); if (n >= 0) { /* Success */ @@ -847,7 +844,7 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) if (n == -ENOMEM) { _debug("oom"); - rxrpc_kernel_abort_call(afs_socket, call->rxcall, + rxrpc_kernel_abort_call(net->socket, call->rxcall, RX_USER_ABORT, -ENOMEM, "KOO"); } _leave(" [error]"); @@ -859,6 +856,7 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) int afs_extract_data(struct afs_call *call, void *buf, size_t count, bool want_more) { + struct afs_net *net = call->net; int ret; _enter("{%s,%zu},,%zu,%d", @@ -866,7 +864,7 @@ int afs_extract_data(struct afs_call *call, void *buf, size_t count, ASSERTCMP(call->offset, <=, count); - ret = rxrpc_kernel_recv_data(afs_socket, call->rxcall, + ret = rxrpc_kernel_recv_data(net->socket, call->rxcall, buf, count, &call->offset, want_more, &call->abort_code, &call->service_id); diff --git a/fs/afs/server.c b/fs/afs/server.c index c001b1f2455f..e47fd9bc0ddc 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -15,32 +15,22 @@ static unsigned afs_server_timeout = 10; /* server timeout in seconds */ -static void afs_reap_server(struct work_struct *); - -/* tree of all the servers, indexed by IP address */ -static struct rb_root afs_servers = RB_ROOT; -static DEFINE_RWLOCK(afs_servers_lock); - -/* LRU list of all the servers not currently in use */ -static LIST_HEAD(afs_server_graveyard); -static DEFINE_SPINLOCK(afs_server_graveyard_lock); -static DECLARE_DELAYED_WORK(afs_server_reaper, afs_reap_server); - /* * install a server record in the master tree */ static int afs_install_server(struct afs_server *server) { struct afs_server *xserver; + struct afs_net *net = server->cell->net; struct rb_node **pp, *p; int ret; _enter("%p", server); - write_lock(&afs_servers_lock); + write_lock(&net->servers_lock); ret = -EEXIST; - pp = &afs_servers.rb_node; + pp = &net->servers.rb_node; p = NULL; while (*pp) { p = *pp; @@ -55,11 +45,11 @@ static int afs_install_server(struct afs_server *server) } rb_link_node(&server->master_rb, p, pp); - rb_insert_color(&server->master_rb, &afs_servers); + rb_insert_color(&server->master_rb, &net->servers); ret = 0; error: - write_unlock(&afs_servers_lock); + write_unlock(&net->servers_lock); return ret; } @@ -150,9 +140,9 @@ found_server_quickly: read_unlock(&cell->servers_lock); no_longer_unused: if (!list_empty(&server->grave)) { - spin_lock(&afs_server_graveyard_lock); + spin_lock(&cell->net->server_graveyard_lock); list_del_init(&server->grave); - spin_unlock(&afs_server_graveyard_lock); + spin_unlock(&cell->net->server_graveyard_lock); } _leave(" = %p{%d}", server, atomic_read(&server->usage)); return server; @@ -178,7 +168,8 @@ server_in_two_cells: /* * look up a server by its IP address */ -struct afs_server *afs_find_server(const struct sockaddr_rxrpc *srx) +struct afs_server *afs_find_server(struct afs_net *net, + const struct sockaddr_rxrpc *srx) { struct afs_server *server = NULL; struct rb_node *p; @@ -191,9 +182,9 @@ struct afs_server *afs_find_server(const struct sockaddr_rxrpc *srx) return NULL; } - read_lock(&afs_servers_lock); + read_lock(&net->servers_lock); - p = afs_servers.rb_node; + p = net->servers.rb_node; while (p) { server = rb_entry(p, struct afs_server, master_rb); @@ -211,7 +202,7 @@ struct afs_server *afs_find_server(const struct sockaddr_rxrpc *srx) server = NULL; found: - read_unlock(&afs_servers_lock); + read_unlock(&net->servers_lock); ASSERTIFCMP(server, server->addr.s_addr, ==, addr.s_addr); _leave(" = %p", server); return server; @@ -223,6 +214,8 @@ found: */ void afs_put_server(struct afs_server *server) { + struct afs_net *net = server->cell->net; + if (!server) return; @@ -239,14 +232,14 @@ void afs_put_server(struct afs_server *server) afs_flush_callback_breaks(server); - spin_lock(&afs_server_graveyard_lock); + spin_lock(&net->server_graveyard_lock); if (atomic_read(&server->usage) == 0) { - list_move_tail(&server->grave, &afs_server_graveyard); + list_move_tail(&server->grave, &net->server_graveyard); server->time_of_death = ktime_get_real_seconds(); - queue_delayed_work(afs_wq, &afs_server_reaper, - afs_server_timeout * HZ); + queue_delayed_work(afs_wq, &net->server_reaper, + net->live ? afs_server_timeout * HZ : 0); } - spin_unlock(&afs_server_graveyard_lock); + spin_unlock(&net->server_graveyard_lock); _leave(" [dead]"); } @@ -272,42 +265,45 @@ static void afs_destroy_server(struct afs_server *server) /* * reap dead server records */ -static void afs_reap_server(struct work_struct *work) +void afs_reap_server(struct work_struct *work) { LIST_HEAD(corpses); struct afs_server *server; + struct afs_net *net = container_of(work, struct afs_net, server_reaper.work); unsigned long delay, expiry; time64_t now; now = ktime_get_real_seconds(); - spin_lock(&afs_server_graveyard_lock); + spin_lock(&net->server_graveyard_lock); - while (!list_empty(&afs_server_graveyard)) { - server = list_entry(afs_server_graveyard.next, + while (!list_empty(&net->server_graveyard)) { + server = list_entry(net->server_graveyard.next, struct afs_server, grave); /* the queue is ordered most dead first */ - expiry = server->time_of_death + afs_server_timeout; - if (expiry > now) { - delay = (expiry - now) * HZ; - mod_delayed_work(afs_wq, &afs_server_reaper, delay); - break; + if (net->live) { + expiry = server->time_of_death + afs_server_timeout; + if (expiry > now) { + delay = (expiry - now) * HZ; + mod_delayed_work(afs_wq, &net->server_reaper, delay); + break; + } } write_lock(&server->cell->servers_lock); - write_lock(&afs_servers_lock); + write_lock(&net->servers_lock); if (atomic_read(&server->usage) > 0) { list_del_init(&server->grave); } else { list_move_tail(&server->grave, &corpses); list_del_init(&server->link); - rb_erase(&server->master_rb, &afs_servers); + rb_erase(&server->master_rb, &net->servers); } - write_unlock(&afs_servers_lock); + write_unlock(&net->servers_lock); write_unlock(&server->cell->servers_lock); } - spin_unlock(&afs_server_graveyard_lock); + spin_unlock(&net->server_graveyard_lock); /* now reap the corpses we've extracted */ while (!list_empty(&corpses)) { @@ -318,10 +314,10 @@ static void afs_reap_server(struct work_struct *work) } /* - * discard all the server records for rmmod + * Discard all the server records from a net namespace when it is destroyed or + * the afs module is removed. */ -void __exit afs_purge_servers(void) +void __net_exit afs_purge_servers(struct afs_net *net) { - afs_server_timeout = 0; - mod_delayed_work(afs_wq, &afs_server_reaper, 0); + mod_delayed_work(afs_wq, &net->server_reaper, 0); } diff --git a/fs/afs/super.c b/fs/afs/super.c index 689173c0a682..d47a9bc46a69 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -25,11 +25,10 @@ #include #include #include +#include #include #include "internal.h" -#define AFS_FS_MAGIC 0x6B414653 /* 'kAFS' */ - static void afs_i_init_once(void *foo); static struct dentry *afs_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data); @@ -201,7 +200,8 @@ static int afs_parse_options(struct afs_mount_params *params, token = match_token(p, afs_options_list, args); switch (token) { case afs_opt_cell: - cell = afs_cell_lookup(args[0].from, + cell = afs_cell_lookup(params->net, + args[0].from, args[0].to - args[0].from, false); if (IS_ERR(cell)) @@ -308,7 +308,7 @@ static int afs_parse_device_name(struct afs_mount_params *params, /* lookup the cell record */ if (cellname || !params->cell) { - cell = afs_cell_lookup(cellname, cellnamesz, true); + cell = afs_cell_lookup(params->net, cellname, cellnamesz, true); if (IS_ERR(cell)) { printk(KERN_ERR "kAFS: unable to lookup cell '%*.*s'\n", cellnamesz, cellnamesz, cellname ?: ""); @@ -334,7 +334,7 @@ static int afs_test_super(struct super_block *sb, void *data) struct afs_super_info *as1 = data; struct afs_super_info *as = sb->s_fs_info; - return as->volume == as1->volume; + return as->net == as1->net && as->volume == as1->volume; } static int afs_set_super(struct super_block *sb, void *data) @@ -411,6 +411,7 @@ static struct dentry *afs_mount(struct file_system_type *fs_type, _enter(",,%s,%p", dev_name, options); memset(¶ms, 0, sizeof(params)); + params.net = &__afs_net; ret = -EINVAL; if (current->nsproxy->net_ns != &init_net) @@ -444,36 +445,32 @@ static struct dentry *afs_mount(struct file_system_type *fs_type, } /* allocate a superblock info record */ + ret = -ENOMEM; as = kzalloc(sizeof(struct afs_super_info), GFP_KERNEL); - if (!as) { - ret = -ENOMEM; - afs_put_volume(vol); - goto error; - } + if (!as) + goto error_vol; + + as->net = afs_get_net(params.net); as->volume = vol; /* allocate a deviceless superblock */ sb = sget(fs_type, afs_test_super, afs_set_super, flags, as); if (IS_ERR(sb)) { ret = PTR_ERR(sb); - afs_put_volume(vol); - kfree(as); - goto error; + goto error_as; } if (!sb->s_root) { /* initial superblock/root creation */ _debug("create"); ret = afs_fill_super(sb, ¶ms); - if (ret < 0) { - deactivate_locked_super(sb); - goto error; - } + if (ret < 0) + goto error_sb; sb->s_flags |= MS_ACTIVE; } else { _debug("reuse"); ASSERTCMP(sb->s_flags, &, MS_ACTIVE); - afs_put_volume(vol); + afs_put_volume(params.net, vol); kfree(as); } @@ -482,6 +479,14 @@ static struct dentry *afs_mount(struct file_system_type *fs_type, _leave(" = 0 [%p]", sb); return dget(sb->s_root); +error_sb: + deactivate_locked_super(sb); + goto error; +error_as: + afs_put_net(as->net); + kfree(as); +error_vol: + afs_put_volume(params.net, vol); error: afs_put_cell(params.cell); key_put(params.key); @@ -493,8 +498,10 @@ error: static void afs_kill_super(struct super_block *sb) { struct afs_super_info *as = sb->s_fs_info; + struct afs_net *net = as->net; + kill_anon_super(sb); - afs_put_volume(as->volume); + afs_put_volume(net, as->volume); kfree(as); } diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c index a5e4cc561b6c..f5a043a9ba61 100644 --- a/fs/afs/vlclient.c +++ b/fs/afs/vlclient.c @@ -143,7 +143,8 @@ static const struct afs_call_type afs_RXVLGetEntryById = { /* * dispatch a get volume entry by name operation */ -int afs_vl_get_entry_by_name(struct in_addr *addr, +int afs_vl_get_entry_by_name(struct afs_net *net, + struct in_addr *addr, struct key *key, const char *volname, struct afs_cache_vlocation *entry, @@ -159,7 +160,7 @@ int afs_vl_get_entry_by_name(struct in_addr *addr, padsz = (4 - (volnamesz & 3)) & 3; reqsz = 8 + volnamesz + padsz; - call = afs_alloc_flat_call(&afs_RXVLGetEntryByName, reqsz, 384); + call = afs_alloc_flat_call(net, &afs_RXVLGetEntryByName, reqsz, 384); if (!call) return -ENOMEM; @@ -183,7 +184,8 @@ int afs_vl_get_entry_by_name(struct in_addr *addr, /* * dispatch a get volume entry by ID operation */ -int afs_vl_get_entry_by_id(struct in_addr *addr, +int afs_vl_get_entry_by_id(struct afs_net *net, + struct in_addr *addr, struct key *key, afs_volid_t volid, afs_voltype_t voltype, @@ -195,7 +197,7 @@ int afs_vl_get_entry_by_id(struct in_addr *addr, _enter(""); - call = afs_alloc_flat_call(&afs_RXVLGetEntryById, 12, 384); + call = afs_alloc_flat_call(net, &afs_RXVLGetEntryById, 12, 384); if (!call) return -ENOMEM; diff --git a/fs/afs/vlocation.c b/fs/afs/vlocation.c index 37b7c3b342a6..ccb7aacfbeca 100644 --- a/fs/afs/vlocation.c +++ b/fs/afs/vlocation.c @@ -16,20 +16,11 @@ #include #include "internal.h" +struct workqueue_struct *afs_vlocation_update_worker; + static unsigned afs_vlocation_timeout = 10; /* volume location timeout in seconds */ static unsigned afs_vlocation_update_timeout = 10 * 60; -static void afs_vlocation_reaper(struct work_struct *); -static void afs_vlocation_updater(struct work_struct *); - -static LIST_HEAD(afs_vlocation_updates); -static LIST_HEAD(afs_vlocation_graveyard); -static DEFINE_SPINLOCK(afs_vlocation_updates_lock); -static DEFINE_SPINLOCK(afs_vlocation_graveyard_lock); -static DECLARE_DELAYED_WORK(afs_vlocation_reap, afs_vlocation_reaper); -static DECLARE_DELAYED_WORK(afs_vlocation_update, afs_vlocation_updater); -static struct workqueue_struct *afs_vlocation_update_worker; - /* * iterate through the VL servers in a cell until one of them admits knowing * about the volume in question @@ -52,8 +43,8 @@ static int afs_vlocation_access_vl_by_name(struct afs_vlocation *vl, _debug("CellServ[%hu]: %08x", cell->vl_curr_svix, addr.s_addr); /* attempt to access the VL server */ - ret = afs_vl_get_entry_by_name(&addr, key, vl->vldb.name, vldb, - false); + ret = afs_vl_get_entry_by_name(cell->net, &addr, key, + vl->vldb.name, vldb, false); switch (ret) { case 0: goto out; @@ -110,8 +101,8 @@ static int afs_vlocation_access_vl_by_id(struct afs_vlocation *vl, _debug("CellServ[%hu]: %08x", cell->vl_curr_svix, addr.s_addr); /* attempt to access the VL server */ - ret = afs_vl_get_entry_by_id(&addr, key, volid, voltype, vldb, - false); + ret = afs_vl_get_entry_by_id(cell->net, &addr, key, volid, + voltype, vldb, false); switch (ret) { case 0: goto out; @@ -335,7 +326,8 @@ static int afs_vlocation_fill_in_record(struct afs_vlocation *vl, /* * queue a vlocation record for updates */ -static void afs_vlocation_queue_for_updates(struct afs_vlocation *vl) +static void afs_vlocation_queue_for_updates(struct afs_net *net, + struct afs_vlocation *vl) { struct afs_vlocation *xvl; @@ -343,25 +335,25 @@ static void afs_vlocation_queue_for_updates(struct afs_vlocation *vl) vl->update_at = ktime_get_real_seconds() + afs_vlocation_update_timeout; - spin_lock(&afs_vlocation_updates_lock); + spin_lock(&net->vl_updates_lock); - if (!list_empty(&afs_vlocation_updates)) { + if (!list_empty(&net->vl_updates)) { /* ... but wait at least 1 second more than the newest record * already queued so that we don't spam the VL server suddenly * with lots of requests */ - xvl = list_entry(afs_vlocation_updates.prev, + xvl = list_entry(net->vl_updates.prev, struct afs_vlocation, update); if (vl->update_at <= xvl->update_at) vl->update_at = xvl->update_at + 1; - } else { + } else if (net->live) { queue_delayed_work(afs_vlocation_update_worker, - &afs_vlocation_update, + &net->vl_updater, afs_vlocation_update_timeout * HZ); } - list_add_tail(&vl->update, &afs_vlocation_updates); - spin_unlock(&afs_vlocation_updates_lock); + list_add_tail(&vl->update, &net->vl_updates); + spin_unlock(&net->vl_updates_lock); } /* @@ -371,7 +363,8 @@ static void afs_vlocation_queue_for_updates(struct afs_vlocation *vl) * - lookup in the local cache if not able to find on the VL server * - insert/update in the local cache if did get a VL response */ -struct afs_vlocation *afs_vlocation_lookup(struct afs_cell *cell, +struct afs_vlocation *afs_vlocation_lookup(struct afs_net *net, + struct afs_cell *cell, struct key *key, const char *name, size_t namesz) @@ -427,7 +420,7 @@ fill_in_record: #endif /* schedule for regular updates */ - afs_vlocation_queue_for_updates(vl); + afs_vlocation_queue_for_updates(net, vl); goto success; found_in_memory: @@ -436,9 +429,9 @@ found_in_memory: atomic_inc(&vl->usage); spin_unlock(&cell->vl_lock); if (!list_empty(&vl->grave)) { - spin_lock(&afs_vlocation_graveyard_lock); + spin_lock(&net->vl_graveyard_lock); list_del_init(&vl->grave); - spin_unlock(&afs_vlocation_graveyard_lock); + spin_unlock(&net->vl_graveyard_lock); } up_write(&cell->vl_sem); @@ -481,7 +474,7 @@ error_abandon: wake_up(&vl->waitq); error: ASSERT(vl != NULL); - afs_put_vlocation(vl); + afs_put_vlocation(net, vl); _leave(" = %d", ret); return ERR_PTR(ret); } @@ -489,7 +482,7 @@ error: /* * finish using a volume location record */ -void afs_put_vlocation(struct afs_vlocation *vl) +void afs_put_vlocation(struct afs_net *net, struct afs_vlocation *vl) { if (!vl) return; @@ -503,22 +496,22 @@ void afs_put_vlocation(struct afs_vlocation *vl) return; } - spin_lock(&afs_vlocation_graveyard_lock); + spin_lock(&net->vl_graveyard_lock); if (atomic_read(&vl->usage) == 0) { _debug("buried"); - list_move_tail(&vl->grave, &afs_vlocation_graveyard); + list_move_tail(&vl->grave, &net->vl_graveyard); vl->time_of_death = ktime_get_real_seconds(); - queue_delayed_work(afs_wq, &afs_vlocation_reap, + queue_delayed_work(afs_wq, &net->vl_reaper, afs_vlocation_timeout * HZ); /* suspend updates on this record */ if (!list_empty(&vl->update)) { - spin_lock(&afs_vlocation_updates_lock); + spin_lock(&net->vl_updates_lock); list_del_init(&vl->update); - spin_unlock(&afs_vlocation_updates_lock); + spin_unlock(&net->vl_updates_lock); } } - spin_unlock(&afs_vlocation_graveyard_lock); + spin_unlock(&net->vl_graveyard_lock); _leave(" [killed?]"); } @@ -539,31 +532,34 @@ static void afs_vlocation_destroy(struct afs_vlocation *vl) /* * reap dead volume location records */ -static void afs_vlocation_reaper(struct work_struct *work) +void afs_vlocation_reaper(struct work_struct *work) { LIST_HEAD(corpses); struct afs_vlocation *vl; + struct afs_net *net = container_of(work, struct afs_net, vl_reaper.work); unsigned long delay, expiry; time64_t now; _enter(""); now = ktime_get_real_seconds(); - spin_lock(&afs_vlocation_graveyard_lock); + spin_lock(&net->vl_graveyard_lock); - while (!list_empty(&afs_vlocation_graveyard)) { - vl = list_entry(afs_vlocation_graveyard.next, + while (!list_empty(&net->vl_graveyard)) { + vl = list_entry(net->vl_graveyard.next, struct afs_vlocation, grave); _debug("check %p", vl); /* the queue is ordered most dead first */ - expiry = vl->time_of_death + afs_vlocation_timeout; - if (expiry > now) { - delay = (expiry - now) * HZ; - _debug("delay %lu", delay); - mod_delayed_work(afs_wq, &afs_vlocation_reap, delay); - break; + if (net->live) { + expiry = vl->time_of_death + afs_vlocation_timeout; + if (expiry > now) { + delay = (expiry - now) * HZ; + _debug("delay %lu", delay); + mod_delayed_work(afs_wq, &net->vl_reaper, delay); + break; + } } spin_lock(&vl->cell->vl_lock); @@ -578,7 +574,7 @@ static void afs_vlocation_reaper(struct work_struct *work) spin_unlock(&vl->cell->vl_lock); } - spin_unlock(&afs_vlocation_graveyard_lock); + spin_unlock(&net->vl_graveyard_lock); /* now reap the corpses we've extracted */ while (!list_empty(&corpses)) { @@ -590,57 +586,47 @@ static void afs_vlocation_reaper(struct work_struct *work) _leave(""); } -/* - * initialise the VL update process - */ -int __init afs_vlocation_update_init(void) -{ - afs_vlocation_update_worker = alloc_workqueue("kafs_vlupdated", - WQ_MEM_RECLAIM, 0); - return afs_vlocation_update_worker ? 0 : -ENOMEM; -} - /* * discard all the volume location records for rmmod */ -void afs_vlocation_purge(void) +void __net_exit afs_vlocation_purge(struct afs_net *net) { - afs_vlocation_timeout = 0; - - spin_lock(&afs_vlocation_updates_lock); - list_del_init(&afs_vlocation_updates); - spin_unlock(&afs_vlocation_updates_lock); - mod_delayed_work(afs_vlocation_update_worker, &afs_vlocation_update, 0); - destroy_workqueue(afs_vlocation_update_worker); - - mod_delayed_work(afs_wq, &afs_vlocation_reap, 0); + spin_lock(&net->vl_updates_lock); + list_del_init(&net->vl_updates); + spin_unlock(&net->vl_updates_lock); + mod_delayed_work(afs_vlocation_update_worker, &net->vl_updater, 0); + mod_delayed_work(afs_wq, &net->vl_reaper, 0); } /* * update a volume location */ -static void afs_vlocation_updater(struct work_struct *work) +void afs_vlocation_updater(struct work_struct *work) { struct afs_cache_vlocation vldb; struct afs_vlocation *vl, *xvl; + struct afs_net *net = container_of(work, struct afs_net, vl_updater.work); time64_t now; long timeout; int ret; + if (!net->live) + return; + _enter(""); now = ktime_get_real_seconds(); /* find a record to update */ - spin_lock(&afs_vlocation_updates_lock); + spin_lock(&net->vl_updates_lock); for (;;) { - if (list_empty(&afs_vlocation_updates)) { - spin_unlock(&afs_vlocation_updates_lock); + if (list_empty(&net->vl_updates) || !net->live) { + spin_unlock(&net->vl_updates_lock); _leave(" [nothing]"); return; } - vl = list_entry(afs_vlocation_updates.next, + vl = list_entry(net->vl_updates.next, struct afs_vlocation, update); if (atomic_read(&vl->usage) > 0) break; @@ -650,15 +636,15 @@ static void afs_vlocation_updater(struct work_struct *work) timeout = vl->update_at - now; if (timeout > 0) { queue_delayed_work(afs_vlocation_update_worker, - &afs_vlocation_update, timeout * HZ); - spin_unlock(&afs_vlocation_updates_lock); + &net->vl_updater, timeout * HZ); + spin_unlock(&net->vl_updates_lock); _leave(" [nothing]"); return; } list_del_init(&vl->update); atomic_inc(&vl->usage); - spin_unlock(&afs_vlocation_updates_lock); + spin_unlock(&net->vl_updates_lock); /* we can now perform the update */ _debug("update %s", vl->vldb.name); @@ -688,18 +674,18 @@ static void afs_vlocation_updater(struct work_struct *work) vl->update_at = ktime_get_real_seconds() + afs_vlocation_update_timeout; - spin_lock(&afs_vlocation_updates_lock); + spin_lock(&net->vl_updates_lock); - if (!list_empty(&afs_vlocation_updates)) { + if (!list_empty(&net->vl_updates)) { /* next update in 10 minutes, but wait at least 1 second more * than the newest record already queued so that we don't spam * the VL server suddenly with lots of requests */ - xvl = list_entry(afs_vlocation_updates.prev, + xvl = list_entry(net->vl_updates.prev, struct afs_vlocation, update); if (vl->update_at <= xvl->update_at) vl->update_at = xvl->update_at + 1; - xvl = list_entry(afs_vlocation_updates.next, + xvl = list_entry(net->vl_updates.next, struct afs_vlocation, update); timeout = xvl->update_at - now; if (timeout < 0) @@ -710,11 +696,10 @@ static void afs_vlocation_updater(struct work_struct *work) ASSERT(list_empty(&vl->update)); - list_add_tail(&vl->update, &afs_vlocation_updates); + list_add_tail(&vl->update, &net->vl_updates); _debug("timeout %ld", timeout); - queue_delayed_work(afs_vlocation_update_worker, - &afs_vlocation_update, timeout * HZ); - spin_unlock(&afs_vlocation_updates_lock); - afs_put_vlocation(vl); + queue_delayed_work(afs_vlocation_update_worker, &net->vl_updater, timeout * HZ); + spin_unlock(&net->vl_updates_lock); + afs_put_vlocation(net, vl); } diff --git a/fs/afs/volume.c b/fs/afs/volume.c index db73d6dad02b..3d5363e0b7e1 100644 --- a/fs/afs/volume.c +++ b/fs/afs/volume.c @@ -54,7 +54,7 @@ struct afs_volume *afs_volume_lookup(struct afs_mount_params *params) params->volnamesz, params->volnamesz, params->volname, params->rwpath); /* lookup the volume location record */ - vlocation = afs_vlocation_lookup(params->cell, params->key, + vlocation = afs_vlocation_lookup(params->net, params->cell, params->key, params->volname, params->volnamesz); if (IS_ERR(vlocation)) { ret = PTR_ERR(vlocation); @@ -138,7 +138,7 @@ success: _debug("kAFS selected %s volume %08x", afs_voltypes[volume->type], volume->vid); up_write(¶ms->cell->vl_sem); - afs_put_vlocation(vlocation); + afs_put_vlocation(params->net, vlocation); _leave(" = %p", volume); return volume; @@ -146,7 +146,7 @@ success: error_up: up_write(¶ms->cell->vl_sem); error: - afs_put_vlocation(vlocation); + afs_put_vlocation(params->net, vlocation); _leave(" = %d", ret); return ERR_PTR(ret); @@ -163,7 +163,7 @@ error_discard: /* * destroy a volume record */ -void afs_put_volume(struct afs_volume *volume) +void afs_put_volume(struct afs_net *net, struct afs_volume *volume) { struct afs_vlocation *vlocation; int loop; @@ -195,7 +195,7 @@ void afs_put_volume(struct afs_volume *volume) #ifdef CONFIG_AFS_FSCACHE fscache_relinquish_cookie(volume->cache, 0); #endif - afs_put_vlocation(vlocation); + afs_put_vlocation(net, vlocation); for (loop = volume->nservers - 1; loop >= 0; loop--) afs_put_server(volume->servers[loop]); diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index aa50113ebe5b..1a6fee974116 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -47,6 +47,7 @@ #define OPENPROM_SUPER_MAGIC 0x9fa1 #define QNX4_SUPER_MAGIC 0x002f /* qnx4 fs detection */ #define QNX6_SUPER_MAGIC 0x68191122 /* qnx6 fs detection */ +#define AFS_FS_MAGIC 0x6B414653 #define REISERFS_SUPER_MAGIC 0x52654973 /* used by gcc */ /* used by file system utilities that -- cgit v1.2.3-71-gd317 From 7f88ba4a19b91d310eca836b647edeb100c61c8d Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Fri, 10 Nov 2017 15:13:10 -0600 Subject: PCI/ASPM: Reformat ASPM register definitions Reformat register field definitions in the style used elsewhere and align comments with names used in the spec. No functional change intended. Signed-off-by: Bjorn Helgaas Reviewed-by: Vidya Sagar --- include/uapi/linux/pci_regs.h | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index f8d58045926f..4150acb4cccb 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -995,19 +995,19 @@ #define PCI_PTM_CTRL_ENABLE 0x00000001 /* PTM enable */ #define PCI_PTM_CTRL_ROOT 0x00000002 /* Root select */ -/* L1 PM Substates */ -#define PCI_L1SS_CAP 4 /* capability register */ -#define PCI_L1SS_CAP_PCIPM_L1_2 1 /* PCI PM L1.2 Support */ -#define PCI_L1SS_CAP_PCIPM_L1_1 2 /* PCI PM L1.1 Support */ -#define PCI_L1SS_CAP_ASPM_L1_2 4 /* ASPM L1.2 Support */ -#define PCI_L1SS_CAP_ASPM_L1_1 8 /* ASPM L1.1 Support */ -#define PCI_L1SS_CAP_L1_PM_SS 16 /* L1 PM Substates Support */ -#define PCI_L1SS_CTL1 8 /* Control Register 1 */ -#define PCI_L1SS_CTL1_PCIPM_L1_2 1 /* PCI PM L1.2 Enable */ -#define PCI_L1SS_CTL1_PCIPM_L1_1 2 /* PCI PM L1.1 Support */ -#define PCI_L1SS_CTL1_ASPM_L1_2 4 /* ASPM L1.2 Support */ -#define PCI_L1SS_CTL1_ASPM_L1_1 8 /* ASPM L1.1 Support */ -#define PCI_L1SS_CTL1_L1SS_MASK 0x0000000F -#define PCI_L1SS_CTL2 0xC /* Control Register 2 */ +/* ASPM L1 PM Substates */ +#define PCI_L1SS_CAP 0x04 /* Capabilities Register */ +#define PCI_L1SS_CAP_PCIPM_L1_2 0x00000001 /* PCI-PM L1.2 Supported */ +#define PCI_L1SS_CAP_PCIPM_L1_1 0x00000002 /* PCI-PM L1.1 Supported */ +#define PCI_L1SS_CAP_ASPM_L1_2 0x00000004 /* ASPM L1.2 Supported */ +#define PCI_L1SS_CAP_ASPM_L1_1 0x00000008 /* ASPM L1.1 Supported */ +#define PCI_L1SS_CAP_L1_PM_SS 0x00000010 /* L1 PM Substates Supported */ +#define PCI_L1SS_CTL1 0x08 /* Control 1 Register */ +#define PCI_L1SS_CTL1_PCIPM_L1_2 0x00000001 /* PCI-PM L1.2 Enable */ +#define PCI_L1SS_CTL1_PCIPM_L1_1 0x00000002 /* PCI-PM L1.1 Enable */ +#define PCI_L1SS_CTL1_ASPM_L1_2 0x00000004 /* ASPM L1.2 Enable */ +#define PCI_L1SS_CTL1_ASPM_L1_1 0x00000008 /* ASPM L1.1 Enable */ +#define PCI_L1SS_CTL1_L1SS_MASK 0x0000000f +#define PCI_L1SS_CTL2 0x0c /* Control 2 Register */ #endif /* LINUX_PCI_REGS_H */ -- cgit v1.2.3-71-gd317 From a48f3d5b197494d903c97ff7bc0909dac65740f8 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Mon, 13 Nov 2017 08:36:40 -0600 Subject: PCI/ASPM: Add L1 Substates definitions Add and use #defines for L1 Substate register fields instead of hard-coding the masks. Also update comments to use names from the spec. No functional change intended. Signed-off-by: Bjorn Helgaas Reviewed-by: Vidya Sagar --- drivers/pci/pcie/aspm.c | 34 ++++++++++++++++++++-------------- include/uapi/linux/pci_regs.h | 6 ++++++ 2 files changed, 26 insertions(+), 14 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index a378dd9d2473..d240ffab24c1 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -450,24 +450,25 @@ static void aspm_calc_l1ss_info(struct pcie_link_state *link, if (!(link->aspm_support & ASPM_STATE_L1_2_MASK)) return; - /* Choose the greater of the two T_cmn_mode_rstr_time */ - val1 = (upreg->l1ss_cap >> 8) & 0xFF; - val2 = (dwreg->l1ss_cap >> 8) & 0xFF; + /* Choose the greater of the two Port Common_Mode_Restore_Times */ + val1 = (upreg->l1ss_cap & PCI_L1SS_CAP_CM_RESTORE_TIME) >> 8; + val2 = (dwreg->l1ss_cap & PCI_L1SS_CAP_CM_RESTORE_TIME) >> 8; if (val1 > val2) link->l1ss.ctl1 |= val1 << 8; else link->l1ss.ctl1 |= val2 << 8; + /* * We currently use LTR L1.2 threshold to be fixed constant picked from * Intel's coreboot. */ link->l1ss.ctl1 |= LTR_L1_2_THRESHOLD_BITS; - /* Choose the greater of the two T_pwr_on */ - val1 = (upreg->l1ss_cap >> 19) & 0x1F; - scale1 = (upreg->l1ss_cap >> 16) & 0x03; - val2 = (dwreg->l1ss_cap >> 19) & 0x1F; - scale2 = (dwreg->l1ss_cap >> 16) & 0x03; + /* Choose the greater of the two Port T_POWER_ON times */ + val1 = (upreg->l1ss_cap & PCI_L1SS_CAP_P_PWR_ON_VALUE) >> 19; + scale1 = (upreg->l1ss_cap & PCI_L1SS_CAP_P_PWR_ON_SCALE) >> 16; + val2 = (dwreg->l1ss_cap & PCI_L1SS_CAP_P_PWR_ON_VALUE) >> 19; + scale2 = (dwreg->l1ss_cap & PCI_L1SS_CAP_P_PWR_ON_SCALE) >> 16; if (calc_l1ss_pwron(link->pdev, scale1, val1) > calc_l1ss_pwron(link->downstream, scale2, val2)) @@ -646,21 +647,26 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state) if (enable_req & ASPM_STATE_L1_2_MASK) { - /* Program T_pwr_on in both ports */ + /* Program T_POWER_ON times in both ports */ pci_write_config_dword(parent, up_cap_ptr + PCI_L1SS_CTL2, link->l1ss.ctl2); pci_write_config_dword(child, dw_cap_ptr + PCI_L1SS_CTL2, link->l1ss.ctl2); - /* Program T_cmn_mode in parent */ + /* Program Common_Mode_Restore_Time in upstream device */ pci_clear_and_set_dword(parent, up_cap_ptr + PCI_L1SS_CTL1, - 0xFF00, link->l1ss.ctl1); + PCI_L1SS_CTL1_CM_RESTORE_TIME, + link->l1ss.ctl1); - /* Program LTR L1.2 threshold in both ports */ + /* Program LTR_L1.2_THRESHOLD time in both ports */ pci_clear_and_set_dword(parent, up_cap_ptr + PCI_L1SS_CTL1, - 0xE3FF0000, link->l1ss.ctl1); + PCI_L1SS_CTL1_LTR_L12_TH_VALUE | + PCI_L1SS_CTL1_LTR_L12_TH_SCALE, + link->l1ss.ctl1); pci_clear_and_set_dword(child, dw_cap_ptr + PCI_L1SS_CTL1, - 0xE3FF0000, link->l1ss.ctl1); + PCI_L1SS_CTL1_LTR_L12_TH_VALUE | + PCI_L1SS_CTL1_LTR_L12_TH_SCALE, + link->l1ss.ctl1); } val = 0; diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 4150acb4cccb..85a4014de42e 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -1002,12 +1002,18 @@ #define PCI_L1SS_CAP_ASPM_L1_2 0x00000004 /* ASPM L1.2 Supported */ #define PCI_L1SS_CAP_ASPM_L1_1 0x00000008 /* ASPM L1.1 Supported */ #define PCI_L1SS_CAP_L1_PM_SS 0x00000010 /* L1 PM Substates Supported */ +#define PCI_L1SS_CAP_CM_RESTORE_TIME 0x0000ff00 /* Port Common_Mode_Restore_Time */ +#define PCI_L1SS_CAP_P_PWR_ON_SCALE 0x00030000 /* Port T_POWER_ON scale */ +#define PCI_L1SS_CAP_P_PWR_ON_VALUE 0x00f80000 /* Port T_POWER_ON value */ #define PCI_L1SS_CTL1 0x08 /* Control 1 Register */ #define PCI_L1SS_CTL1_PCIPM_L1_2 0x00000001 /* PCI-PM L1.2 Enable */ #define PCI_L1SS_CTL1_PCIPM_L1_1 0x00000002 /* PCI-PM L1.1 Enable */ #define PCI_L1SS_CTL1_ASPM_L1_2 0x00000004 /* ASPM L1.2 Enable */ #define PCI_L1SS_CTL1_ASPM_L1_1 0x00000008 /* ASPM L1.1 Enable */ #define PCI_L1SS_CTL1_L1SS_MASK 0x0000000f +#define PCI_L1SS_CTL1_CM_RESTORE_TIME 0x0000ff00 /* Common_Mode_Restore_Time */ +#define PCI_L1SS_CTL1_LTR_L12_TH_VALUE 0x03ff0000 /* LTR_L1.2_THRESHOLD_Value */ +#define PCI_L1SS_CTL1_LTR_L12_TH_SCALE 0xe0000000 /* LTR_L1.2_THRESHOLD_Scale */ #define PCI_L1SS_CTL2 0x0c /* Control 2 Register */ #endif /* LINUX_PCI_REGS_H */ -- cgit v1.2.3-71-gd317 From 0eef304bc9f7d079a1165e8cd2f24b078e9e1f2a Mon Sep 17 00:00:00 2001 From: "Dmitry V. Levin" Date: Mon, 13 Nov 2017 03:37:06 +0300 Subject: uapi: fix linux/rxrpc.h userspace compilation errors Consistently use types provided by to fix the following linux/rxrpc.h userspace compilation errors: /usr/include/linux/rxrpc.h:24:2: error: unknown type name 'u16' u16 srx_service; /* service desired */ /usr/include/linux/rxrpc.h:25:2: error: unknown type name 'u16' u16 transport_type; /* type of transport socket (SOCK_DGRAM) */ /usr/include/linux/rxrpc.h:26:2: error: unknown type name 'u16' u16 transport_len; /* length of transport address */ Use __kernel_sa_family_t instead of sa_family_t the same way as uapi/linux/in.h does, to fix the following linux/rxrpc.h userspace compilation errors: /usr/include/linux/rxrpc.h:23:2: error: unknown type name 'sa_family_t' sa_family_t srx_family; /* address family */ /usr/include/linux/rxrpc.h:28:3: error: unknown type name 'sa_family_t' sa_family_t family; /* transport address family */ Fixes: 727f8914477e ("rxrpc: Expose UAPI definitions to userspace") Cc: # v4.14 Signed-off-by: Dmitry V. Levin Signed-off-by: David S. Miller --- include/uapi/linux/rxrpc.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rxrpc.h b/include/uapi/linux/rxrpc.h index 9656aad8f8f7..9d4afea308a4 100644 --- a/include/uapi/linux/rxrpc.h +++ b/include/uapi/linux/rxrpc.h @@ -20,12 +20,12 @@ * RxRPC socket address */ struct sockaddr_rxrpc { - sa_family_t srx_family; /* address family */ - u16 srx_service; /* service desired */ - u16 transport_type; /* type of transport socket (SOCK_DGRAM) */ - u16 transport_len; /* length of transport address */ + __kernel_sa_family_t srx_family; /* address family */ + __u16 srx_service; /* service desired */ + __u16 transport_type; /* type of transport socket (SOCK_DGRAM) */ + __u16 transport_len; /* length of transport address */ union { - sa_family_t family; /* transport address family */ + __kernel_sa_family_t family; /* transport address family */ struct sockaddr_in sin; /* IPv4 transport address */ struct sockaddr_in6 sin6; /* IPv6 transport address */ } transport; -- cgit v1.2.3-71-gd317 From b9f3eb499d84f8d4adcb2f9212ec655700b28228 Mon Sep 17 00:00:00 2001 From: "Dmitry V. Levin" Date: Tue, 14 Nov 2017 06:30:11 +0300 Subject: uapi: fix linux/tls.h userspace compilation error Move inclusion of a private kernel header from uapi/linux/tls.h to its only user - net/tls.h, to fix the following linux/tls.h userspace compilation error: /usr/include/linux/tls.h:41:21: fatal error: net/tcp.h: No such file or directory As to this point uapi/linux/tls.h was totaly unusuable for userspace, cleanup this header file further by moving other redundant includes to net/tls.h. Fixes: 3c4d7559159b ("tls: kernel TLS support") Cc: # v4.13+ Signed-off-by: Dmitry V. Levin Signed-off-by: David S. Miller --- include/net/tls.h | 4 ++++ include/uapi/linux/tls.h | 4 ---- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/tls.h b/include/net/tls.h index 70becd0a9299..936cfc5cab7d 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -35,6 +35,10 @@ #define _TLS_OFFLOAD_H #include +#include +#include +#include +#include #include diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h index d5e0682ab837..293b2cdad88d 100644 --- a/include/uapi/linux/tls.h +++ b/include/uapi/linux/tls.h @@ -35,10 +35,6 @@ #define _UAPI_LINUX_TLS_H #include -#include -#include -#include -#include /* TLS socket options */ #define TLS_TX 1 /* Set transmit parameters */ -- cgit v1.2.3-71-gd317 From 6ab6a0dd228220bd00d745f8eb8ca497e522f4b6 Mon Sep 17 00:00:00 2001 From: Ahmed Abdelsalam Date: Wed, 15 Nov 2017 15:34:23 +0100 Subject: ipv6: sr: update the struct ipv6_sr_hdr The IPv6 Segment Routing Header (SRH) format has been updated (revision 6 of the SRH ietf draft). The update includes the following SRH fields: (1) The "First Segment" field changed to be "Last Entry" which contains the index, in the Segment List, of the last element of the Segment List. (2) The 16 bit "reserved" field now is used as a "tag" which tags a packet as part of a class or group of packets, e.g.,packets sharing the same set of properties. This patch updates the struct ipv6_sr_hdr, so it complies with the updated SRH draft. The 16 bit "reserved" field is changed to be "tag", In addition a comment is added to the "first_segment" field, showing that it represents the "Last Entry" field of the SRH. Signed-off-by: Ahmed Abdelsalam Signed-off-by: David S. Miller --- include/uapi/linux/seg6.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/seg6.h b/include/uapi/linux/seg6.h index 2f6fb0dd613c..286e8d6a8e98 100644 --- a/include/uapi/linux/seg6.h +++ b/include/uapi/linux/seg6.h @@ -26,9 +26,9 @@ struct ipv6_sr_hdr { __u8 hdrlen; __u8 type; __u8 segments_left; - __u8 first_segment; + __u8 first_segment; /* Represents the last_entry field of SRH */ __u8 flags; - __u16 reserved; + __u16 tag; struct in6_addr segments[0]; }; -- cgit v1.2.3-71-gd317 From ded97d2c2b2c5f1dcced0bc57133f7753b037dfc Mon Sep 17 00:00:00 2001 From: Victor Chibotaru Date: Fri, 17 Nov 2017 15:30:46 -0800 Subject: kcov: support comparison operands collection Enables kcov to collect comparison operands from instrumented code. This is done by using Clang's -fsanitize=trace-cmp instrumentation (currently not available for GCC). The comparison operands help a lot in fuzz testing. E.g. they are used in Syzkaller to cover the interiors of conditional statements with way less attempts and thus make previously unreachable code reachable. To allow separate collection of coverage and comparison operands two different work modes are implemented. Mode selection is now done via a KCOV_ENABLE ioctl call with corresponding argument value. Link: http://lkml.kernel.org/r/20171011095459.70721-1-glider@google.com Signed-off-by: Victor Chibotaru Signed-off-by: Alexander Potapenko Cc: Dmitry Vyukov Cc: Andrey Konovalov Cc: Mark Rutland Cc: Alexander Popov Cc: Andrey Ryabinin Cc: Kees Cook Cc: Vegard Nossum Cc: Quentin Casasnovas Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kcov.h | 12 ++- include/uapi/linux/kcov.h | 24 ++++++ kernel/kcov.c | 214 ++++++++++++++++++++++++++++++++++++++-------- 3 files changed, 211 insertions(+), 39 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/kcov.h b/include/linux/kcov.h index f5d8ce4f4f86..3ecf6f5e3a5f 100644 --- a/include/linux/kcov.h +++ b/include/linux/kcov.h @@ -8,19 +8,23 @@ struct task_struct; #ifdef CONFIG_KCOV -void kcov_task_init(struct task_struct *t); -void kcov_task_exit(struct task_struct *t); - enum kcov_mode { /* Coverage collection is not enabled yet. */ KCOV_MODE_DISABLED = 0, + /* KCOV was initialized, but tracing mode hasn't been chosen yet. */ + KCOV_MODE_INIT = 1, /* * Tracing coverage collection mode. * Covered PCs are collected in a per-task buffer. */ - KCOV_MODE_TRACE = 1, + KCOV_MODE_TRACE_PC = 2, + /* Collecting comparison operands mode. */ + KCOV_MODE_TRACE_CMP = 3, }; +void kcov_task_init(struct task_struct *t); +void kcov_task_exit(struct task_struct *t); + #else static inline void kcov_task_init(struct task_struct *t) {} diff --git a/include/uapi/linux/kcov.h b/include/uapi/linux/kcov.h index 33eabbb8ada1..9529867717a8 100644 --- a/include/uapi/linux/kcov.h +++ b/include/uapi/linux/kcov.h @@ -8,4 +8,28 @@ #define KCOV_ENABLE _IO('c', 100) #define KCOV_DISABLE _IO('c', 101) +enum { + /* + * Tracing coverage collection mode. + * Covered PCs are collected in a per-task buffer. + * In new KCOV version the mode is chosen by calling + * ioctl(fd, KCOV_ENABLE, mode). In older versions the mode argument + * was supposed to be 0 in such a call. So, for reasons of backward + * compatibility, we have chosen the value KCOV_TRACE_PC to be 0. + */ + KCOV_TRACE_PC = 0, + /* Collecting comparison operands mode. */ + KCOV_TRACE_CMP = 1, +}; + +/* + * The format for the types of collected comparisons. + * + * Bit 0 shows whether one of the arguments is a compile-time constant. + * Bits 1 & 2 contain log2 of the argument size, up to 8 bytes. + */ +#define KCOV_CMP_CONST (1 << 0) +#define KCOV_CMP_SIZE(n) ((n) << 1) +#define KCOV_CMP_MASK KCOV_CMP_SIZE(3) + #endif /* _LINUX_KCOV_IOCTLS_H */ diff --git a/kernel/kcov.c b/kernel/kcov.c index d9f9fa9cacc6..15f33faf4013 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -22,13 +22,21 @@ #include #include +/* Number of 64-bit words written per one comparison: */ +#define KCOV_WORDS_PER_CMP 4 + /* * kcov descriptor (one per opened debugfs file). * State transitions of the descriptor: * - initial state after open() * - then there must be a single ioctl(KCOV_INIT_TRACE) call * - then, mmap() call (several calls are allowed but not useful) - * - then, repeated enable/disable for a task (only one task a time allowed) + * - then, ioctl(KCOV_ENABLE, arg), where arg is + * KCOV_TRACE_PC - to trace only the PCs + * or + * KCOV_TRACE_CMP - to trace only the comparison operands + * - then, ioctl(KCOV_DISABLE) to disable the task. + * Enabling/disabling ioctls can be repeated (only one task a time allowed). */ struct kcov { /* @@ -48,51 +56,176 @@ struct kcov { struct task_struct *t; }; -/* - * Entry point from instrumented code. - * This is called once per basic-block/edge. - */ -void notrace __sanitizer_cov_trace_pc(void) +static bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t) { - struct task_struct *t; enum kcov_mode mode; - t = current; /* * We are interested in code coverage as a function of a syscall inputs, * so we ignore code executed in interrupts. */ if (!in_task()) - return; + return false; mode = READ_ONCE(t->kcov_mode); - if (mode == KCOV_MODE_TRACE) { - unsigned long *area; - unsigned long pos; - unsigned long ip = _RET_IP_; + /* + * There is some code that runs in interrupts but for which + * 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(). + */ + barrier(); + return mode == needed_mode; +} +static unsigned long canonicalize_ip(unsigned long ip) +{ #ifdef CONFIG_RANDOMIZE_BASE - ip -= kaslr_offset(); + ip -= kaslr_offset(); #endif + return ip; +} - /* - * There is some code that runs in interrupts but for which - * 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(). - */ - barrier(); - area = t->kcov_area; - /* The first word is number of subsequent PCs. */ - pos = READ_ONCE(area[0]) + 1; - if (likely(pos < t->kcov_size)) { - area[pos] = ip; - WRITE_ONCE(area[0], pos); - } +/* + * Entry point from instrumented code. + * This is called once per basic-block/edge. + */ +void notrace __sanitizer_cov_trace_pc(void) +{ + struct task_struct *t; + unsigned long *area; + unsigned long ip = canonicalize_ip(_RET_IP_); + unsigned long pos; + + t = current; + if (!check_kcov_mode(KCOV_MODE_TRACE_PC, t)) + return; + + area = t->kcov_area; + /* The first 64-bit word is the number of subsequent PCs. */ + pos = READ_ONCE(area[0]) + 1; + if (likely(pos < t->kcov_size)) { + area[pos] = ip; + WRITE_ONCE(area[0], pos); } } EXPORT_SYMBOL(__sanitizer_cov_trace_pc); +#ifdef CONFIG_KCOV_ENABLE_COMPARISONS +static void write_comp_data(u64 type, u64 arg1, u64 arg2, u64 ip) +{ + struct task_struct *t; + u64 *area; + u64 count, start_index, end_pos, max_pos; + + t = current; + if (!check_kcov_mode(KCOV_MODE_TRACE_CMP, t)) + return; + + ip = canonicalize_ip(ip); + + /* + * We write all comparison arguments and types as u64. + * The buffer was allocated for t->kcov_size unsigned longs. + */ + area = (u64 *)t->kcov_area; + max_pos = t->kcov_size * sizeof(unsigned long); + + count = READ_ONCE(area[0]); + + /* Every record is KCOV_WORDS_PER_CMP 64-bit words. */ + start_index = 1 + count * KCOV_WORDS_PER_CMP; + end_pos = (start_index + KCOV_WORDS_PER_CMP) * sizeof(u64); + if (likely(end_pos <= max_pos)) { + area[start_index] = type; + area[start_index + 1] = arg1; + area[start_index + 2] = arg2; + area[start_index + 3] = ip; + WRITE_ONCE(area[0], count + 1); + } +} + +void notrace __sanitizer_cov_trace_cmp1(u8 arg1, u8 arg2) +{ + write_comp_data(KCOV_CMP_SIZE(0), arg1, arg2, _RET_IP_); +} +EXPORT_SYMBOL(__sanitizer_cov_trace_cmp1); + +void notrace __sanitizer_cov_trace_cmp2(u16 arg1, u16 arg2) +{ + write_comp_data(KCOV_CMP_SIZE(1), arg1, arg2, _RET_IP_); +} +EXPORT_SYMBOL(__sanitizer_cov_trace_cmp2); + +void notrace __sanitizer_cov_trace_cmp4(u16 arg1, u16 arg2) +{ + write_comp_data(KCOV_CMP_SIZE(2), arg1, arg2, _RET_IP_); +} +EXPORT_SYMBOL(__sanitizer_cov_trace_cmp4); + +void notrace __sanitizer_cov_trace_cmp8(u64 arg1, u64 arg2) +{ + write_comp_data(KCOV_CMP_SIZE(3), arg1, arg2, _RET_IP_); +} +EXPORT_SYMBOL(__sanitizer_cov_trace_cmp8); + +void notrace __sanitizer_cov_trace_const_cmp1(u8 arg1, u8 arg2) +{ + write_comp_data(KCOV_CMP_SIZE(0) | KCOV_CMP_CONST, arg1, arg2, + _RET_IP_); +} +EXPORT_SYMBOL(__sanitizer_cov_trace_const_cmp1); + +void notrace __sanitizer_cov_trace_const_cmp2(u16 arg1, u16 arg2) +{ + write_comp_data(KCOV_CMP_SIZE(1) | KCOV_CMP_CONST, arg1, arg2, + _RET_IP_); +} +EXPORT_SYMBOL(__sanitizer_cov_trace_const_cmp2); + +void notrace __sanitizer_cov_trace_const_cmp4(u16 arg1, u16 arg2) +{ + write_comp_data(KCOV_CMP_SIZE(2) | KCOV_CMP_CONST, arg1, arg2, + _RET_IP_); +} +EXPORT_SYMBOL(__sanitizer_cov_trace_const_cmp4); + +void notrace __sanitizer_cov_trace_const_cmp8(u64 arg1, u64 arg2) +{ + write_comp_data(KCOV_CMP_SIZE(3) | KCOV_CMP_CONST, arg1, arg2, + _RET_IP_); +} +EXPORT_SYMBOL(__sanitizer_cov_trace_const_cmp8); + +void notrace __sanitizer_cov_trace_switch(u64 val, u64 *cases) +{ + u64 i; + u64 count = cases[0]; + u64 size = cases[1]; + u64 type = KCOV_CMP_CONST; + + switch (size) { + case 8: + type |= KCOV_CMP_SIZE(0); + break; + case 16: + type |= KCOV_CMP_SIZE(1); + break; + case 32: + type |= KCOV_CMP_SIZE(2); + break; + case 64: + type |= KCOV_CMP_SIZE(3); + break; + default: + return; + } + for (i = 0; i < count; i++) + write_comp_data(type, cases[i + 2], val, _RET_IP_); +} +EXPORT_SYMBOL(__sanitizer_cov_trace_switch); +#endif /* ifdef CONFIG_KCOV_ENABLE_COMPARISONS */ + static void kcov_get(struct kcov *kcov) { atomic_inc(&kcov->refcount); @@ -129,6 +262,7 @@ void kcov_task_exit(struct task_struct *t) /* Just to not leave dangling references behind. */ kcov_task_init(t); kcov->t = NULL; + kcov->mode = KCOV_MODE_INIT; spin_unlock(&kcov->lock); kcov_put(kcov); } @@ -147,7 +281,7 @@ static int kcov_mmap(struct file *filep, struct vm_area_struct *vma) spin_lock(&kcov->lock); size = kcov->size * sizeof(unsigned long); - if (kcov->mode == KCOV_MODE_DISABLED || vma->vm_pgoff != 0 || + if (kcov->mode != KCOV_MODE_INIT || vma->vm_pgoff != 0 || vma->vm_end - vma->vm_start != size) { res = -EINVAL; goto exit; @@ -176,6 +310,7 @@ static int kcov_open(struct inode *inode, struct file *filep) kcov = kzalloc(sizeof(*kcov), GFP_KERNEL); if (!kcov) return -ENOMEM; + kcov->mode = KCOV_MODE_DISABLED; atomic_set(&kcov->refcount, 1); spin_lock_init(&kcov->lock); filep->private_data = kcov; @@ -211,7 +346,7 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, if (size < 2 || size > INT_MAX / sizeof(unsigned long)) return -EINVAL; kcov->size = size; - kcov->mode = KCOV_MODE_TRACE; + kcov->mode = KCOV_MODE_INIT; return 0; case KCOV_ENABLE: /* @@ -221,17 +356,25 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, * at task exit or voluntary by KCOV_DISABLE. After that it can * be enabled for another task. */ - unused = arg; - if (unused != 0 || kcov->mode == KCOV_MODE_DISABLED || - kcov->area == NULL) + if (kcov->mode != KCOV_MODE_INIT || !kcov->area) return -EINVAL; if (kcov->t != 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; t = current; /* Cache in task struct for performance. */ t->kcov_size = kcov->size; t->kcov_area = kcov->area; - /* See comment in __sanitizer_cov_trace_pc(). */ + /* See comment in check_kcov_mode(). */ barrier(); WRITE_ONCE(t->kcov_mode, kcov->mode); t->kcov = kcov; @@ -249,6 +392,7 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, return -EINVAL; kcov_task_init(t); kcov->t = NULL; + kcov->mode = KCOV_MODE_INIT; kcov_put(kcov); return 0; default: -- cgit v1.2.3-71-gd317 From 1f6f4cb7ba219b00a3fa9afe8049fa16444d8b52 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 20 Nov 2017 15:21:53 -0800 Subject: bpf: offload: rename the ifindex field bpf_target_prog seems long and clunky, rename it to prog_ifindex. We don't want to call this field just ifindex, because maps may need a similar field in the future and bpf_attr members for programs and maps are unnamed. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: Daniel Borkmann --- include/uapi/linux/bpf.h | 2 +- kernel/bpf/offload.c | 2 +- kernel/bpf/syscall.c | 4 ++-- tools/include/uapi/linux/bpf.h | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e880ae6434ee..3f626df42516 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -262,7 +262,7 @@ union bpf_attr { __u32 kern_version; /* checked when prog_type=kprobe */ __u32 prog_flags; char prog_name[BPF_OBJ_NAME_LEN]; - __u32 prog_target_ifindex; /* ifindex of netdev to prep for */ + __u32 prog_ifindex; /* ifindex of netdev to prep for */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index ac187f9ee182..a778e5df7e26 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -29,7 +29,7 @@ int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) init_waitqueue_head(&offload->verifier_done); rtnl_lock(); - offload->netdev = __dev_get_by_index(net, attr->prog_target_ifindex); + offload->netdev = __dev_get_by_index(net, attr->prog_ifindex); if (!offload->netdev) { rtnl_unlock(); kfree(offload); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 09badc37e864..8e9d065bb7cd 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1118,7 +1118,7 @@ struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, EXPORT_SYMBOL_GPL(bpf_prog_get_type_dev); /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD prog_target_ifindex +#define BPF_PROG_LOAD_LAST_FIELD prog_ifindex static int bpf_prog_load(union bpf_attr *attr) { @@ -1181,7 +1181,7 @@ static int bpf_prog_load(union bpf_attr *attr) atomic_set(&prog->aux->refcnt, 1); prog->gpl_compatible = is_gpl ? 1 : 0; - if (attr->prog_target_ifindex) { + if (attr->prog_ifindex) { err = bpf_prog_offload_init(prog, attr); if (err) goto free_prog; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e880ae6434ee..3f626df42516 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -262,7 +262,7 @@ union bpf_attr { __u32 kern_version; /* checked when prog_type=kprobe */ __u32 prog_flags; char prog_name[BPF_OBJ_NAME_LEN]; - __u32 prog_target_ifindex; /* ifindex of netdev to prep for */ + __u32 prog_ifindex; /* ifindex of netdev to prep for */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ -- cgit v1.2.3-71-gd317 From 1ee640095f049e7ac4ec36b985abada497b98cc2 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 20 Nov 2017 15:21:59 -0800 Subject: bpf: revert report offload info to user space This reverts commit bd601b6ada11 ("bpf: report offload info to user space"). The ifindex by itself is not sufficient, we should provide information on which network namespace this ifindex belongs to. After considering some options we concluded that it's best to just remove this API for now, and rework it in -next. Signed-off-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 1 - include/uapi/linux/bpf.h | 6 ------ kernel/bpf/offload.c | 12 ------------ kernel/bpf/syscall.c | 5 ----- 4 files changed, 24 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 37bbab8c0f56..76c577281d78 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -515,7 +515,6 @@ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, int bpf_prog_offload_compile(struct bpf_prog *prog); void bpf_prog_offload_destroy(struct bpf_prog *prog); -u32 bpf_prog_offload_ifindex(struct bpf_prog *prog); #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 3f626df42516..4c223ab30293 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -897,10 +897,6 @@ enum sk_action { #define BPF_TAG_SIZE 8 -enum bpf_prog_status { - BPF_PROG_STATUS_DEV_BOUND = (1 << 0), -}; - struct bpf_prog_info { __u32 type; __u32 id; @@ -914,8 +910,6 @@ struct bpf_prog_info { __u32 nr_map_ids; __aligned_u64 map_ids; char name[BPF_OBJ_NAME_LEN]; - __u32 ifindex; - __u32 status; } __attribute__((aligned(8))); struct bpf_map_info { diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index d4267c674fec..68ec884440b7 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -149,18 +149,6 @@ int bpf_prog_offload_compile(struct bpf_prog *prog) return bpf_prog_offload_translate(prog); } -u32 bpf_prog_offload_ifindex(struct bpf_prog *prog) -{ - struct bpf_dev_offload *offload = prog->aux->offload; - u32 ifindex; - - rtnl_lock(); - ifindex = offload->netdev ? offload->netdev->ifindex : 0; - rtnl_unlock(); - - return ifindex; -} - const struct bpf_prog_ops bpf_offload_prog_ops = { }; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 41509cf825d8..2c4cfeaa8d5e 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1616,11 +1616,6 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, return -EFAULT; } - if (bpf_prog_is_dev_bound(prog->aux)) { - info.status |= BPF_PROG_STATUS_DEV_BOUND; - info.ifindex = bpf_prog_offload_ifindex(prog); - } - done: if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) -- cgit v1.2.3-71-gd317