From 9d9d415f0048e4f7a6109595e2d1657850569c6c Mon Sep 17 00:00:00 2001 From: "Radu Pirea (NXP OSS)" Date: Mon, 10 May 2021 18:34:32 +0300 Subject: ptp: ptp_clock: make scaled_ppm_to_ppb static inline Make scaled_ppm_to_ppb static inline to be able to build drivers that use this function even with PTP_1588_CLOCK disabled. Signed-off-by: Radu Pirea (NXP OSS) Signed-off-by: David S. Miller --- include/linux/ptp_clock_kernel.h | 34 ++++++++++++++++++++++++++-------- 1 file changed, 26 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 0d47fd33b228..a311bddd9e85 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -186,6 +186,32 @@ struct ptp_clock_event { }; }; +/** + * scaled_ppm_to_ppb() - convert scaled ppm to ppb + * + * @ppm: Parts per million, but with a 16 bit binary fractional field + */ +static inline s32 scaled_ppm_to_ppb(long ppm) +{ + /* + * The 'freq' field in the 'struct timex' is in parts per + * million, but with a 16 bit binary fractional field. + * + * We want to calculate + * + * ppb = scaled_ppm * 1000 / 2^16 + * + * which simplifies to + * + * ppb = scaled_ppm * 125 / 2^13 + */ + s64 ppb = 1 + ppm; + + ppb *= 125; + ppb >>= 13; + return (s32)ppb; +} + #if IS_REACHABLE(CONFIG_PTP_1588_CLOCK) /** @@ -229,14 +255,6 @@ extern void ptp_clock_event(struct ptp_clock *ptp, extern int ptp_clock_index(struct ptp_clock *ptp); -/** - * scaled_ppm_to_ppb() - convert scaled ppm to ppb - * - * @ppm: Parts per million, but with a 16 bit binary fractional field - */ - -extern s32 scaled_ppm_to_ppb(long ppm); - /** * ptp_find_pin() - obtain the pin index of a given auxiliary function * -- cgit v1.2.3-71-gd317 From c9e73e3d2b1eb1ea7ff068e05007eec3bd8ef1c9 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Thu, 29 Apr 2021 14:46:56 +0100 Subject: bpf: verifier: Allocate idmap scratch in verifier env func_states_equal makes a very short lived allocation for idmap, probably because it's too large to fit on the stack. However the function is called quite often, leading to a lot of alloc / free churn. Replace the temporary allocation with dedicated scratch space in struct bpf_verifier_env. Signed-off-by: Lorenz Bauer Signed-off-by: Alexei Starovoitov Acked-by: Edward Cree Link: https://lore.kernel.org/bpf/20210429134656.122225-4-lmb@cloudflare.com --- include/linux/bpf_verifier.h | 8 ++++++++ kernel/bpf/verifier.c | 46 +++++++++++++++----------------------------- 2 files changed, 23 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 06841517ab1e..d4632aa3ca50 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -215,6 +215,13 @@ struct bpf_idx_pair { u32 idx; }; +struct bpf_id_pair { + u32 old; + u32 cur; +}; + +/* Maximum number of register states that can exist at once */ +#define BPF_ID_MAP_SIZE (MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE) #define MAX_CALL_FRAMES 8 struct bpf_verifier_state { /* call stack tracking */ @@ -418,6 +425,7 @@ struct bpf_verifier_env { const struct bpf_line_info *prev_linfo; struct bpf_verifier_log log; struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1]; + struct bpf_id_pair idmap_scratch[BPF_ID_MAP_SIZE]; struct { int *insn_state; int *insn_stack; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 380c8ad49b7f..bdfdb54676ea 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -9748,13 +9748,6 @@ static bool range_within(struct bpf_reg_state *old, old->s32_max_value >= cur->s32_max_value; } -/* Maximum number of register states that can exist at once */ -#define ID_MAP_SIZE (MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE) -struct idpair { - u32 old; - u32 cur; -}; - /* If in the old state two registers had the same id, then they need to have * the same id in the new state as well. But that id could be different from * the old state, so we need to track the mapping from old to new ids. @@ -9765,11 +9758,11 @@ struct idpair { * So we look through our idmap to see if this old id has been seen before. If * so, we require the new id to match; otherwise, we add the id pair to the map. */ -static bool check_ids(u32 old_id, u32 cur_id, struct idpair *idmap) +static bool check_ids(u32 old_id, u32 cur_id, struct bpf_id_pair *idmap) { unsigned int i; - for (i = 0; i < ID_MAP_SIZE; i++) { + for (i = 0; i < BPF_ID_MAP_SIZE; i++) { if (!idmap[i].old) { /* Reached an empty slot; haven't seen this id before */ idmap[i].old = old_id; @@ -9882,7 +9875,7 @@ next: /* Returns true if (rold safe implies rcur safe) */ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, - struct idpair *idmap) + struct bpf_id_pair *idmap) { bool equal; @@ -10000,7 +9993,7 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, static bool stacksafe(struct bpf_func_state *old, struct bpf_func_state *cur, - struct idpair *idmap) + struct bpf_id_pair *idmap) { int i, spi; @@ -10097,32 +10090,23 @@ static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur) * whereas register type in current state is meaningful, it means that * the current state will reach 'bpf_exit' instruction safely */ -static bool func_states_equal(struct bpf_func_state *old, +static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_state *old, struct bpf_func_state *cur) { - struct idpair *idmap; - bool ret = false; int i; - idmap = kcalloc(ID_MAP_SIZE, sizeof(struct idpair), GFP_KERNEL); - /* If we failed to allocate the idmap, just say it's not safe */ - if (!idmap) - return false; - - for (i = 0; i < MAX_BPF_REG; i++) { - if (!regsafe(&old->regs[i], &cur->regs[i], idmap)) - goto out_free; - } + memset(env->idmap_scratch, 0, sizeof(env->idmap_scratch)); + for (i = 0; i < MAX_BPF_REG; i++) + if (!regsafe(&old->regs[i], &cur->regs[i], env->idmap_scratch)) + return false; - if (!stacksafe(old, cur, idmap)) - goto out_free; + if (!stacksafe(old, cur, env->idmap_scratch)) + return false; if (!refsafe(old, cur)) - goto out_free; - ret = true; -out_free: - kfree(idmap); - return ret; + return false; + + return true; } static bool states_equal(struct bpf_verifier_env *env, @@ -10149,7 +10133,7 @@ static bool states_equal(struct bpf_verifier_env *env, for (i = 0; i <= old->curframe; i++) { if (old->frame[i]->callsite != cur->frame[i]->callsite) return false; - if (!func_states_equal(old->frame[i], cur->frame[i])) + if (!func_states_equal(env, old->frame[i], cur->frame[i])) return false; } return true; -- cgit v1.2.3-71-gd317 From bf30396cdf8132a199af5f8f0e60367876f455df Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Tue, 11 May 2021 16:42:22 +0200 Subject: net: wwan: Add unknown port type Some devices may have ports with unknown type/protocol which need to be tagged (though not supported by WWAN core). This will be the case for cdc-wdm based drivers. Signed-off-by: Loic Poulain Signed-off-by: David S. Miller --- include/linux/wwan.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/wwan.h b/include/linux/wwan.h index aa05a253dcf9..7216c114d758 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -15,6 +15,7 @@ * @WWAN_PORT_QMI: Qcom modem/MSM interface for modem control * @WWAN_PORT_QCDM: Qcom Modem diagnostic interface * @WWAN_PORT_FIREHOSE: XML based command protocol + * @WWAN_PORT_UNKNOWN: Unknown port type * @WWAN_PORT_MAX: Number of supported port types */ enum wwan_port_type { @@ -23,7 +24,8 @@ enum wwan_port_type { WWAN_PORT_QMI, WWAN_PORT_QCDM, WWAN_PORT_FIREHOSE, - WWAN_PORT_MAX, + WWAN_PORT_UNKNOWN, + WWAN_PORT_MAX = WWAN_PORT_UNKNOWN, }; struct wwan_port; -- cgit v1.2.3-71-gd317 From cac6fb015f719104e60b1c68c15ca5b734f57b9c Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Tue, 11 May 2021 16:42:23 +0200 Subject: usb: class: cdc-wdm: WWAN framework integration The WWAN framework provides a unified way to handle WWAN/modems and its control port(s). It has initially been introduced to support MHI/PCI modems, offering the same control protocols as the USB variants such as MBIM, QMI, AT... The WWAN framework exposes these control protocols as character devices, similarly to cdc-wdm, but in a bus agnostic fashion. This change adds registration of the USB modem cdc-wdm control endpoints to the WWAN framework as standard control ports (wwanXpY...). Exposing cdc-wdm through WWAN framework normally maintains backward compatibility, e.g: $ qmicli --device-open-qmi -d /dev/wwan0p1QMI --dms-get-ids instead of $ qmicli --device-open-qmi -d /dev/cdc-wdm0 --dms-get-ids However, some tools may rely on cdc-wdm driver/device name for device detection. It is then safer to keep the 'legacy' cdc-wdm character device to prevent any breakage. This is handled in this change by API mutual exclusion, only one access method can be used at a time, either cdc-wdm chardev or WWAN API. Note that unknown channel types (other than MBIM, AT or MBIM) are not registered to the WWAN framework. Signed-off-by: Loic Poulain Signed-off-by: David S. Miller --- drivers/net/usb/cdc_mbim.c | 1 + drivers/net/usb/huawei_cdc_ncm.c | 1 + drivers/net/usb/qmi_wwan.c | 3 +- drivers/usb/class/cdc-wdm.c | 180 ++++++++++++++++++++++++++++++++++++++- include/linux/usb/cdc-wdm.h | 3 +- 5 files changed, 182 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c index 5db66272fc82..42fb75057c15 100644 --- a/drivers/net/usb/cdc_mbim.c +++ b/drivers/net/usb/cdc_mbim.c @@ -168,6 +168,7 @@ static int cdc_mbim_bind(struct usbnet *dev, struct usb_interface *intf) subdriver = usb_cdc_wdm_register(ctx->control, &dev->status->desc, le16_to_cpu(ctx->mbim_desc->wMaxControlMessage), + WWAN_PORT_MBIM, cdc_mbim_wdm_manage_power); if (IS_ERR(subdriver)) { ret = PTR_ERR(subdriver); diff --git a/drivers/net/usb/huawei_cdc_ncm.c b/drivers/net/usb/huawei_cdc_ncm.c index a87f0dabcdb7..849b77330bf2 100644 --- a/drivers/net/usb/huawei_cdc_ncm.c +++ b/drivers/net/usb/huawei_cdc_ncm.c @@ -96,6 +96,7 @@ static int huawei_cdc_ncm_bind(struct usbnet *usbnet_dev, subdriver = usb_cdc_wdm_register(ctx->control, &usbnet_dev->status->desc, 1024, /* wMaxCommand */ + WWAN_PORT_AT, huawei_cdc_ncm_wdm_manage_power); if (IS_ERR(subdriver)) { ret = PTR_ERR(subdriver); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 6700f1970b24..db157f21a322 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -710,7 +710,8 @@ static int qmi_wwan_register_subdriver(struct usbnet *dev) /* register subdriver */ subdriver = usb_cdc_wdm_register(info->control, &dev->status->desc, - 4096, &qmi_wwan_cdc_wdm_manage_power); + 4096, WWAN_PORT_QMI, + &qmi_wwan_cdc_wdm_manage_power); if (IS_ERR(subdriver)) { dev_err(&info->control->dev, "subdriver registration failed\n"); rv = PTR_ERR(subdriver); diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index 508b1c3f8b73..457b00c6e984 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -21,8 +21,10 @@ #include #include #include +#include #include #include +#include #include #include #include @@ -55,6 +57,7 @@ MODULE_DEVICE_TABLE (usb, wdm_ids); #define WDM_SUSPENDING 8 #define WDM_RESETTING 9 #define WDM_OVERFLOW 10 +#define WDM_WWAN_IN_USE 11 #define WDM_MAX 16 @@ -106,6 +109,9 @@ struct wdm_device { struct list_head device_list; int (*manage_power)(struct usb_interface *, int); + + enum wwan_port_type wwanp_type; + struct wwan_port *wwanp; }; static struct usb_driver wdm_driver; @@ -157,6 +163,8 @@ static void wdm_out_callback(struct urb *urb) wake_up_all(&desc->wait); } +static void wdm_wwan_rx(struct wdm_device *desc, int length); + static void wdm_in_callback(struct urb *urb) { unsigned long flags; @@ -192,6 +200,11 @@ static void wdm_in_callback(struct urb *urb) } } + if (test_bit(WDM_WWAN_IN_USE, &desc->flags)) { + wdm_wwan_rx(desc, length); + goto out; + } + /* * only set a new error if there is no previous error. * Errors are only cleared during read/open @@ -226,6 +239,7 @@ skip_error: set_bit(WDM_READ, &desc->flags); wake_up(&desc->wait); } +out: spin_unlock_irqrestore(&desc->iuspin, flags); } @@ -697,6 +711,11 @@ static int wdm_open(struct inode *inode, struct file *file) goto out; file->private_data = desc; + if (test_bit(WDM_WWAN_IN_USE, &desc->flags)) { + rv = -EBUSY; + goto out; + } + rv = usb_autopm_get_interface(desc->intf); if (rv < 0) { dev_err(&desc->intf->dev, "Error autopm - %d\n", rv); @@ -792,6 +811,151 @@ static struct usb_class_driver wdm_class = { .minor_base = WDM_MINOR_BASE, }; +/* --- WWAN framework integration --- */ +#ifdef CONFIG_WWAN +static int wdm_wwan_port_start(struct wwan_port *port) +{ + struct wdm_device *desc = wwan_port_get_drvdata(port); + + /* The interface is both exposed via the WWAN framework and as a + * legacy usbmisc chardev. If chardev is already open, just fail + * to prevent concurrent usage. Otherwise, switch to WWAN mode. + */ + mutex_lock(&wdm_mutex); + if (desc->count) { + mutex_unlock(&wdm_mutex); + return -EBUSY; + } + set_bit(WDM_WWAN_IN_USE, &desc->flags); + mutex_unlock(&wdm_mutex); + + desc->manage_power(desc->intf, 1); + + /* tx is allowed */ + wwan_port_txon(port); + + /* Start getting events */ + return usb_submit_urb(desc->validity, GFP_KERNEL); +} + +static void wdm_wwan_port_stop(struct wwan_port *port) +{ + struct wdm_device *desc = wwan_port_get_drvdata(port); + + /* Stop all transfers and disable WWAN mode */ + kill_urbs(desc); + desc->manage_power(desc->intf, 0); + clear_bit(WDM_READ, &desc->flags); + clear_bit(WDM_WWAN_IN_USE, &desc->flags); +} + +static void wdm_wwan_port_tx_complete(struct urb *urb) +{ + struct sk_buff *skb = urb->context; + struct wdm_device *desc = skb_shinfo(skb)->destructor_arg; + + usb_autopm_put_interface(desc->intf); + wwan_port_txon(desc->wwanp); + kfree_skb(skb); +} + +static int wdm_wwan_port_tx(struct wwan_port *port, struct sk_buff *skb) +{ + struct wdm_device *desc = wwan_port_get_drvdata(port); + struct usb_interface *intf = desc->intf; + struct usb_ctrlrequest *req = desc->orq; + int rv; + + rv = usb_autopm_get_interface(intf); + if (rv) + return rv; + + usb_fill_control_urb( + desc->command, + interface_to_usbdev(intf), + usb_sndctrlpipe(interface_to_usbdev(intf), 0), + (unsigned char *)req, + skb->data, + skb->len, + wdm_wwan_port_tx_complete, + skb + ); + + req->bRequestType = (USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE); + req->bRequest = USB_CDC_SEND_ENCAPSULATED_COMMAND; + req->wValue = 0; + req->wIndex = desc->inum; + req->wLength = cpu_to_le16(skb->len); + + skb_shinfo(skb)->destructor_arg = desc; + + rv = usb_submit_urb(desc->command, GFP_KERNEL); + if (rv) + usb_autopm_put_interface(intf); + else /* One transfer at a time, stop TX until URB completion */ + wwan_port_txoff(port); + + return rv; +} + +static struct wwan_port_ops wdm_wwan_port_ops = { + .start = wdm_wwan_port_start, + .stop = wdm_wwan_port_stop, + .tx = wdm_wwan_port_tx, +}; + +static void wdm_wwan_init(struct wdm_device *desc) +{ + struct usb_interface *intf = desc->intf; + struct wwan_port *port; + + /* Only register to WWAN core if protocol/type is known */ + if (desc->wwanp_type == WWAN_PORT_UNKNOWN) { + dev_info(&intf->dev, "Unknown control protocol\n"); + return; + } + + port = wwan_create_port(&intf->dev, desc->wwanp_type, &wdm_wwan_port_ops, desc); + if (IS_ERR(port)) { + dev_err(&intf->dev, "%s: Unable to create WWAN port\n", + dev_name(intf->usb_dev)); + return; + } + + desc->wwanp = port; +} + +static void wdm_wwan_deinit(struct wdm_device *desc) +{ + if (!desc->wwanp) + return; + + wwan_remove_port(desc->wwanp); + desc->wwanp = NULL; +} + +static void wdm_wwan_rx(struct wdm_device *desc, int length) +{ + struct wwan_port *port = desc->wwanp; + struct sk_buff *skb; + + /* Forward data to WWAN port */ + skb = alloc_skb(length, GFP_ATOMIC); + if (!skb) + return; + + memcpy(skb_put(skb, length), desc->inbuf, length); + wwan_port_rx(port, skb); + + /* inbuf has been copied, it is safe to check for outstanding data */ + schedule_work(&desc->service_outs_intr); +} +#else /* CONFIG_WWAN */ +static void wdm_wwan_init(struct wdm_device *desc) {} +static void wdm_wwan_deinit(struct wdm_device *desc) {} +static void wdm_wwan_rx(struct wdm_device *desc, int length) {} +#endif /* CONFIG_WWAN */ + /* --- error handling --- */ static void wdm_rxwork(struct work_struct *work) { @@ -836,7 +1000,8 @@ static void service_interrupt_work(struct work_struct *work) /* --- hotplug --- */ static int wdm_create(struct usb_interface *intf, struct usb_endpoint_descriptor *ep, - u16 bufsize, int (*manage_power)(struct usb_interface *, int)) + u16 bufsize, enum wwan_port_type type, + int (*manage_power)(struct usb_interface *, int)) { int rv = -ENOMEM; struct wdm_device *desc; @@ -853,6 +1018,7 @@ static int wdm_create(struct usb_interface *intf, struct usb_endpoint_descriptor /* this will be expanded and needed in hardware endianness */ desc->inum = cpu_to_le16((u16)intf->cur_altsetting->desc.bInterfaceNumber); desc->intf = intf; + desc->wwanp_type = type; INIT_WORK(&desc->rxwork, wdm_rxwork); INIT_WORK(&desc->service_outs_intr, service_interrupt_work); @@ -933,6 +1099,9 @@ static int wdm_create(struct usb_interface *intf, struct usb_endpoint_descriptor goto err; else dev_info(&intf->dev, "%s: USB WDM device\n", dev_name(intf->usb_dev)); + + wdm_wwan_init(desc); + out: return rv; err: @@ -977,7 +1146,7 @@ static int wdm_probe(struct usb_interface *intf, const struct usb_device_id *id) goto err; ep = &iface->endpoint[0].desc; - rv = wdm_create(intf, ep, maxcom, &wdm_manage_power); + rv = wdm_create(intf, ep, maxcom, WWAN_PORT_UNKNOWN, &wdm_manage_power); err: return rv; @@ -988,6 +1157,7 @@ err: * @intf: usb interface the subdriver will associate with * @ep: interrupt endpoint to monitor for notifications * @bufsize: maximum message size to support for read/write + * @type: Type/protocol of the transported data (MBIM, QMI...) * @manage_power: call-back invoked during open and release to * manage the device's power * Create WDM usb class character device and associate it with intf @@ -1005,12 +1175,12 @@ err: */ struct usb_driver *usb_cdc_wdm_register(struct usb_interface *intf, struct usb_endpoint_descriptor *ep, - int bufsize, + int bufsize, enum wwan_port_type type, int (*manage_power)(struct usb_interface *, int)) { int rv; - rv = wdm_create(intf, ep, bufsize, manage_power); + rv = wdm_create(intf, ep, bufsize, type, manage_power); if (rv < 0) goto err; @@ -1029,6 +1199,8 @@ static void wdm_disconnect(struct usb_interface *intf) desc = wdm_find_device(intf); mutex_lock(&wdm_mutex); + wdm_wwan_deinit(desc); + /* the spinlock makes sure no new urbs are generated in the callbacks */ spin_lock_irqsave(&desc->iuspin, flags); set_bit(WDM_DISCONNECTING, &desc->flags); diff --git a/include/linux/usb/cdc-wdm.h b/include/linux/usb/cdc-wdm.h index 9b895f93d8de..9f5a51f79ba5 100644 --- a/include/linux/usb/cdc-wdm.h +++ b/include/linux/usb/cdc-wdm.h @@ -12,11 +12,12 @@ #ifndef __LINUX_USB_CDC_WDM_H #define __LINUX_USB_CDC_WDM_H +#include #include extern struct usb_driver *usb_cdc_wdm_register(struct usb_interface *intf, struct usb_endpoint_descriptor *ep, - int bufsize, + int bufsize, enum wwan_port_type type, int (*manage_power)(struct usb_interface *, int)); #endif /* __LINUX_USB_CDC_WDM_H */ -- cgit v1.2.3-71-gd317 From 3b85f9ba3480c1bcbebb2bb490822bec0e7a1201 Mon Sep 17 00:00:00 2001 From: Linus Lüssing Date: Thu, 13 May 2021 15:20:53 +0200 Subject: net: bridge: mcast: export multicast router presence adjacent to a port MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To properly support routable multicast addresses in batman-adv in a group-aware way, a batman-adv node needs to know if it serves multicast routers. This adds a function to the bridge to export this so that batman-adv can then make full use of the Multicast Router Discovery capability of the bridge. Signed-off-by: Linus Lüssing Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 8 +++++++ net/bridge/br_multicast.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 63 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 2cc35038a8ca..12e9a32dbca0 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -67,6 +67,7 @@ int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list); bool br_multicast_has_querier_anywhere(struct net_device *dev, int proto); bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto); +bool br_multicast_has_router_adjacent(struct net_device *dev, int proto); bool br_multicast_enabled(const struct net_device *dev); bool br_multicast_router(const struct net_device *dev); int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, @@ -87,6 +88,13 @@ static inline bool br_multicast_has_querier_adjacent(struct net_device *dev, { return false; } + +static inline bool br_multicast_has_router_adjacent(struct net_device *dev, + int proto) +{ + return true; +} + static inline bool br_multicast_enabled(const struct net_device *dev) { return false; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index f234c48036c8..0703725527b3 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -4054,6 +4054,61 @@ unlock: } EXPORT_SYMBOL_GPL(br_multicast_has_querier_adjacent); +/** + * br_multicast_has_router_adjacent - Checks for a router behind a bridge port + * @dev: The bridge port adjacent to which to check for a multicast router + * @proto: The protocol family to check for: IGMP -> ETH_P_IP, MLD -> ETH_P_IPV6 + * + * Checks whether the given interface has a bridge on top and if so returns + * true if a multicast router is behind one of the other ports of this + * bridge. Otherwise returns false. + */ +bool br_multicast_has_router_adjacent(struct net_device *dev, int proto) +{ + struct net_bridge_port *port, *p; + bool ret = false; + + rcu_read_lock(); + port = br_port_get_check_rcu(dev); + if (!port) + goto unlock; + + switch (proto) { + case ETH_P_IP: + hlist_for_each_entry_rcu(p, &port->br->ip4_mc_router_list, + ip4_rlist) { + if (p == port) + continue; + + ret = true; + goto unlock; + } + break; +#if IS_ENABLED(CONFIG_IPV6) + case ETH_P_IPV6: + hlist_for_each_entry_rcu(p, &port->br->ip6_mc_router_list, + ip6_rlist) { + if (p == port) + continue; + + ret = true; + goto unlock; + } + break; +#endif + default: + /* when compiled without IPv6 support, be conservative and + * always assume presence of an IPv6 multicast router + */ + ret = true; + } + +unlock: + rcu_read_unlock(); + return ret; +} +EXPORT_SYMBOL_GPL(br_multicast_has_router_adjacent); + static void br_mcast_stats_add(struct bridge_mcast_stats __percpu *stats, const struct sk_buff *skb, u8 type, u8 dir) { -- cgit v1.2.3-71-gd317 From 7617af3d1a5e0938eb1fd2742f19bcea772c7f8d Mon Sep 17 00:00:00 2001 From: Michael Sit Wei Hong Date: Mon, 17 May 2021 17:43:31 +0800 Subject: net: pcs: Introducing support for DWC xpcs Energy Efficient Ethernet Add DWC xpcs EEE support callbacks.The callback function is used to set EEE registers on xpcs. xpcs transparent mode is enabled to allow PHY to detect MAC EEE status. Signed-off-by: Michael Sit Wei Hong Signed-off-by: David S. Miller --- drivers/net/pcs/pcs-xpcs.c | 51 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/pcs/pcs-xpcs.h | 2 ++ 2 files changed, 53 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 944ba105cac1..aa985a5aae8d 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -63,6 +63,9 @@ #define DW_VR_MII_DIG_CTRL1 0x8000 #define DW_VR_MII_AN_CTRL 0x8001 #define DW_VR_MII_AN_INTR_STS 0x8002 +/* EEE Mode Control Register */ +#define DW_VR_MII_EEE_MCTRL0 0x8006 +#define DW_VR_MII_EEE_MCTRL1 0x800b /* VR_MII_DIG_CTRL1 */ #define DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW BIT(9) @@ -86,6 +89,20 @@ #define DW_VR_MII_C37_ANSGM_SP_1000 0x2 #define DW_VR_MII_C37_ANSGM_SP_LNKSTS BIT(4) +/* VR MII EEE Control 0 defines */ +#define DW_VR_MII_EEE_LTX_EN BIT(0) /* LPI Tx Enable */ +#define DW_VR_MII_EEE_LRX_EN BIT(1) /* LPI Rx Enable */ +#define DW_VR_MII_EEE_TX_QUIET_EN BIT(2) /* Tx Quiet Enable */ +#define DW_VR_MII_EEE_RX_QUIET_EN BIT(3) /* Rx Quiet Enable */ +#define DW_VR_MII_EEE_TX_EN_CTRL BIT(4) /* Tx Control Enable */ +#define DW_VR_MII_EEE_RX_EN_CTRL BIT(7) /* Rx Control Enable */ + +#define DW_VR_MII_EEE_MULT_FACT_100NS_SHIFT 8 +#define DW_VR_MII_EEE_MULT_FACT_100NS GENMASK(11, 8) + +/* VR MII EEE Control 1 defines */ +#define DW_VR_MII_EEE_TRN_LPI BIT(0) /* Transparent Mode Enable */ + static const int xpcs_usxgmii_features[] = { ETHTOOL_LINK_MODE_Pause_BIT, ETHTOOL_LINK_MODE_Asym_Pause_BIT, @@ -650,6 +667,39 @@ static int xpcs_validate(struct mdio_xpcs_args *xpcs, return 0; } +static int xpcs_config_eee(struct mdio_xpcs_args *xpcs, int mult_fact_100ns, + int enable) +{ + int ret; + + if (enable) { + /* Enable EEE */ + ret = DW_VR_MII_EEE_LTX_EN | DW_VR_MII_EEE_LRX_EN | + DW_VR_MII_EEE_TX_QUIET_EN | DW_VR_MII_EEE_RX_QUIET_EN | + DW_VR_MII_EEE_TX_EN_CTRL | DW_VR_MII_EEE_RX_EN_CTRL | + mult_fact_100ns << DW_VR_MII_EEE_MULT_FACT_100NS_SHIFT; + } else { + ret = xpcs_read(xpcs, MDIO_MMD_VEND2, DW_VR_MII_EEE_MCTRL0); + if (ret < 0) + return ret; + ret &= ~(DW_VR_MII_EEE_LTX_EN | DW_VR_MII_EEE_LRX_EN | + DW_VR_MII_EEE_TX_QUIET_EN | DW_VR_MII_EEE_RX_QUIET_EN | + DW_VR_MII_EEE_TX_EN_CTRL | DW_VR_MII_EEE_RX_EN_CTRL | + DW_VR_MII_EEE_MULT_FACT_100NS); + } + + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_EEE_MCTRL0, ret); + if (ret < 0) + return ret; + + ret = xpcs_read(xpcs, MDIO_MMD_VEND2, DW_VR_MII_EEE_MCTRL1); + if (ret < 0) + return ret; + + ret |= DW_VR_MII_EEE_TRN_LPI; + return xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_EEE_MCTRL1, ret); +} + static int xpcs_config_aneg_c37_sgmii(struct mdio_xpcs_args *xpcs) { int ret; @@ -908,6 +958,7 @@ static struct mdio_xpcs_ops xpcs_ops = { .get_state = xpcs_get_state, .link_up = xpcs_link_up, .probe = xpcs_probe, + .config_eee = xpcs_config_eee, }; struct mdio_xpcs_ops *mdio_xpcs_get_ops(void) diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 2cb5188a7ef1..5938ced805f4 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -32,6 +32,8 @@ struct mdio_xpcs_ops { int (*link_up)(struct mdio_xpcs_args *xpcs, int speed, phy_interface_t interface); int (*probe)(struct mdio_xpcs_args *xpcs, phy_interface_t interface); + int (*config_eee)(struct mdio_xpcs_args *xpcs, int mult_fact_100ns, + int enable); }; #if IS_ENABLED(CONFIG_PCS_XPCS) -- cgit v1.2.3-71-gd317 From e80fe71b3ffe1ec31c4a9be60170f897bbdf1b92 Mon Sep 17 00:00:00 2001 From: Michael Sit Wei Hong Date: Mon, 17 May 2021 17:43:32 +0800 Subject: net: stmmac: Add callbacks for DWC xpcs Energy Efficient Ethernet Link xpcs callback functions for MAC to configure the xpcs EEE feature. The clk_eee frequency is used to calculate the MULT_FACT_100NS. This is to adjust the clock tic closer to 100ns. Signed-off-by: Michael Sit Wei Hong Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 11 +++++++++++ drivers/net/ethernet/stmicro/stmmac/hwif.h | 2 ++ drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 6 ++++++ include/linux/stmmac.h | 1 + 4 files changed, 20 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index 80728a4c0e3f..e36a8cc59ad0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -429,6 +429,17 @@ static int intel_mgbe_common_data(struct pci_dev *pdev, plat->force_sf_dma_mode = 0; plat->tso_en = 1; + /* Multiplying factor to the clk_eee_i clock time + * period to make it closer to 100 ns. This value + * should be programmed such that the clk_eee_time_period * + * (MULT_FACT_100NS + 1) should be within 80 ns to 120 ns + * clk_eee frequency is 19.2Mhz + * clk_eee_time_period is 52ns + * 52ns * (1 + 1) = 104ns + * MULT_FACT_100NS = 1 + */ + plat->mult_fact_100ns = 1; + plat->rx_sched_algorithm = MTL_RX_ALGORITHM_SP; for (i = 0; i < plat->rx_queues_to_use; i++) { diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index 6d5e0f2b03ce..75a8b90c202a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -623,6 +623,8 @@ struct stmmac_mmc_ops { stmmac_do_callback(__priv, xpcs, link_up, __args) #define stmmac_xpcs_probe(__priv, __args...) \ stmmac_do_callback(__priv, xpcs, probe, __args) +#define stmmac_xpcs_config_eee(__priv, __args...) \ + stmmac_do_callback(__priv, xpcs, config_eee, __args) struct stmmac_regs_off { u32 ptp_off; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 61b11639ee0c..1f6d749fd9a3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -720,6 +720,12 @@ static int stmmac_ethtool_op_set_eee(struct net_device *dev, netdev_warn(priv->dev, "Setting EEE tx-lpi is not supported\n"); + ret = stmmac_xpcs_config_eee(priv, &priv->hw->xpcs_args, + priv->plat->mult_fact_100ns, + edata->eee_enabled); + if (ret) + return ret; + if (!edata->eee_enabled) stmmac_disable_eee_mode(priv); diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 0db36360ef21..e14a12df381b 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -223,6 +223,7 @@ struct plat_stmmacenet_data { struct clk *clk_ptp_ref; unsigned int clk_ptp_rate; unsigned int clk_ref_rate; + unsigned int mult_fact_100ns; s32 ptp_max_adj; struct reset_control *stmmac_rst; struct stmmac_axi *axi; -- cgit v1.2.3-71-gd317 From c49661aa6f7097047b7e86ad37b1cf308a7a8d4f Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sun, 16 May 2021 19:23:48 -0700 Subject: skmsg: Remove unused parameters of sk_msg_wait_data() 'err' and 'flags' are not used, we can just get rid of them. Signed-off-by: Cong Wang Signed-off-by: Daniel Borkmann Acked-by: Song Liu Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20210517022348.50555-1-xiyou.wangcong@gmail.com --- include/linux/skmsg.h | 3 +-- net/core/skmsg.c | 3 +-- net/ipv4/tcp_bpf.c | 9 ++------- net/ipv4/udp_bpf.c | 8 ++------ 4 files changed, 6 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index aba0f0f429be..fcaa9a7996c8 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -126,8 +126,7 @@ int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); -int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags, - long timeo, int *err); +int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, long timeo); int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 43ce17a6a585..f0b9decdf279 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -399,8 +399,7 @@ out: } EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter); -int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags, - long timeo, int *err) +int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, long timeo) { DEFINE_WAIT_FUNC(wait, woken_wake_function); int ret = 0; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index ad9d17923fc5..a80de92ea3b6 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -184,11 +184,11 @@ static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, msg_bytes_ready: copied = sk_msg_recvmsg(sk, psock, msg, len, flags); if (!copied) { - int data, err = 0; long timeo; + int data; timeo = sock_rcvtimeo(sk, nonblock); - data = sk_msg_wait_data(sk, psock, flags, timeo, &err); + data = sk_msg_wait_data(sk, psock, timeo); if (data) { if (!sk_psock_queue_empty(psock)) goto msg_bytes_ready; @@ -196,14 +196,9 @@ msg_bytes_ready: sk_psock_put(sk, psock); return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); } - if (err) { - ret = err; - goto out; - } copied = -EAGAIN; } ret = copied; -out: release_sock(sk); sk_psock_put(sk, psock); return ret; diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c index 954c4591a6fd..b07e4b6dda25 100644 --- a/net/ipv4/udp_bpf.c +++ b/net/ipv4/udp_bpf.c @@ -43,21 +43,17 @@ static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, msg_bytes_ready: copied = sk_msg_recvmsg(sk, psock, msg, len, flags); if (!copied) { - int data, err = 0; long timeo; + int data; timeo = sock_rcvtimeo(sk, nonblock); - data = sk_msg_wait_data(sk, psock, flags, timeo, &err); + data = sk_msg_wait_data(sk, psock, timeo); if (data) { if (!sk_psock_queue_empty(psock)) goto msg_bytes_ready; ret = sk_udp_recvmsg(sk, msg, len, nonblock, flags, addr_len); goto out; } - if (err) { - ret = err; - goto out; - } copied = -EAGAIN; } ret = copied; -- cgit v1.2.3-71-gd317 From 86544c3de6a2185409c5a3d02f674ea223a14217 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 18 May 2021 20:49:24 +0300 Subject: net: mdio: provide shim implementation of devm_of_mdiobus_register Similar to the way in which of_mdiobus_register() has a fallback to the non-DT based mdiobus_register() when CONFIG_OF is not set, we can create a shim for the device-managed devm_of_mdiobus_register() which calls devm_mdiobus_register() and discards the struct device_node *. In particular, this solves a build issue with the qca8k DSA driver which uses devm_of_mdiobus_register and can be compiled without CONFIG_OF. Reported-by: Randy Dunlap Signed-off-by: Vladimir Oltean Acked-by: Randy Dunlap # build-tested Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/of_mdio.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 2b05e7f7c238..da633d34ab86 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -72,6 +72,13 @@ static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node * return mdiobus_register(mdio); } +static inline int devm_of_mdiobus_register(struct device *dev, + struct mii_bus *mdio, + struct device_node *np) +{ + return devm_mdiobus_register(dev, mdio); +} + static inline struct mdio_device *of_mdio_find_device(struct device_node *np) { return NULL; -- cgit v1.2.3-71-gd317 From 79a7f8bdb159d9914b58740f3d31d602a6e4aca8 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 13 May 2021 17:36:03 -0700 Subject: bpf: Introduce bpf_sys_bpf() helper and program type. Add placeholders for bpf_sys_bpf() helper and new program type. Make sure to check that expected_attach_type is zero for future extensibility. Allow tracing helper functions to be used in this program type, since they will only execute from user context via bpf_prog_test_run. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210514003623.28033-2-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 10 ++++++++ include/linux/bpf_types.h | 2 ++ include/uapi/linux/bpf.h | 8 +++++++ kernel/bpf/syscall.c | 53 ++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/verifier.c | 8 +++++++ net/bpf/test_run.c | 43 ++++++++++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 8 +++++++ 7 files changed, 132 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 02b02cb29ce2..04a2bf41ae72 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1826,6 +1826,9 @@ static inline bool bpf_map_is_dev_bound(struct bpf_map *map) struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr); void bpf_map_offload_map_free(struct bpf_map *map); +int bpf_prog_test_run_syscall(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr); #else static inline int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) @@ -1851,6 +1854,13 @@ static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) static inline void bpf_map_offload_map_free(struct bpf_map *map) { } + +static inline int bpf_prog_test_run_syscall(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + return -ENOTSUPP; +} #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index f883f01a5061..a9db1eae6796 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -77,6 +77,8 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LSM, lsm, void *, void *) #endif /* CONFIG_BPF_LSM */ #endif +BPF_PROG_TYPE(BPF_PROG_TYPE_SYSCALL, bpf_syscall, + void *, void *) 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/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index ec6d85a81744..c92648f38144 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -937,6 +937,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_EXT, BPF_PROG_TYPE_LSM, BPF_PROG_TYPE_SK_LOOKUP, + BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ }; enum bpf_attach_type { @@ -4735,6 +4736,12 @@ union bpf_attr { * be zero-terminated except when **str_size** is 0. * * Or **-EBUSY** if the per-CPU memory copy buffer is busy. + * + * long bpf_sys_bpf(u32 cmd, void *attr, u32 attr_size) + * Description + * Execute bpf syscall with given arguments. + * Return + * A syscall result. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -4903,6 +4910,7 @@ union bpf_attr { FN(check_mtu), \ FN(for_each_map_elem), \ FN(snprintf), \ + FN(sys_bpf), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 941ca06d9dfa..b1e7352919cb 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2014,6 +2014,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, if (expected_attach_type == BPF_SK_LOOKUP) return 0; return -EINVAL; + case BPF_PROG_TYPE_SYSCALL: case BPF_PROG_TYPE_EXT: if (expected_attach_type) return -EINVAL; @@ -4508,3 +4509,55 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz return err; } + +static bool syscall_prog_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + if (off < 0 || off >= U16_MAX) + return false; + if (off % size != 0) + return false; + return true; +} + +BPF_CALL_3(bpf_sys_bpf, int, cmd, void *, attr, u32, attr_size) +{ + return -EINVAL; +} + +const struct bpf_func_proto bpf_sys_bpf_proto = { + .func = bpf_sys_bpf, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, +}; + +const struct bpf_func_proto * __weak +tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + return bpf_base_func_proto(func_id); +} + +static const struct bpf_func_proto * +syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_sys_bpf: + return &bpf_sys_bpf_proto; + default: + return tracing_prog_func_proto(func_id, prog); + } +} + +const struct bpf_verifier_ops bpf_syscall_verifier_ops = { + .get_func_proto = syscall_prog_func_proto, + .is_valid_access = syscall_prog_is_valid_access, +}; + +const struct bpf_prog_ops bpf_syscall_prog_ops = { + .test_run = bpf_prog_test_run_syscall, +}; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index bdfdb54676ea..37407d8fbca4 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -13196,6 +13196,14 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) int ret; u64 key; + if (prog->type == BPF_PROG_TYPE_SYSCALL) { + if (prog->aux->sleepable) + /* attach_btf_id checked to be zero already */ + return 0; + verbose(env, "Syscall programs can only be sleepable\n"); + return -EINVAL; + } + if (prog->aux->sleepable && prog->type != BPF_PROG_TYPE_TRACING && prog->type != BPF_PROG_TYPE_LSM) { verbose(env, "Only fentry/fexit/fmod_ret and lsm programs can be sleepable\n"); diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index a5d72c48fb66..a6972d7ddf80 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -918,3 +918,46 @@ out: kfree(user_ctx); return ret; } + +int bpf_prog_test_run_syscall(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + void __user *ctx_in = u64_to_user_ptr(kattr->test.ctx_in); + __u32 ctx_size_in = kattr->test.ctx_size_in; + void *ctx = NULL; + u32 retval; + int err = 0; + + /* doesn't support data_in/out, ctx_out, duration, or repeat or flags */ + if (kattr->test.data_in || kattr->test.data_out || + kattr->test.ctx_out || kattr->test.duration || + kattr->test.repeat || kattr->test.flags) + return -EINVAL; + + if (ctx_size_in < prog->aux->max_ctx_offset || + ctx_size_in > U16_MAX) + return -EINVAL; + + if (ctx_size_in) { + ctx = kzalloc(ctx_size_in, GFP_USER); + if (!ctx) + return -ENOMEM; + if (copy_from_user(ctx, ctx_in, ctx_size_in)) { + err = -EFAULT; + goto out; + } + } + retval = bpf_prog_run_pin_on_cpu(prog, ctx); + + if (copy_to_user(&uattr->test.retval, &retval, sizeof(u32))) { + err = -EFAULT; + goto out; + } + if (ctx_size_in) + if (copy_to_user(ctx_in, ctx, ctx_size_in)) + err = -EFAULT; +out: + kfree(ctx); + return err; +} diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index ec6d85a81744..c92648f38144 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -937,6 +937,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_EXT, BPF_PROG_TYPE_LSM, BPF_PROG_TYPE_SK_LOOKUP, + BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ }; enum bpf_attach_type { @@ -4735,6 +4736,12 @@ union bpf_attr { * be zero-terminated except when **str_size** is 0. * * Or **-EBUSY** if the per-CPU memory copy buffer is busy. + * + * long bpf_sys_bpf(u32 cmd, void *attr, u32 attr_size) + * Description + * Execute bpf syscall with given arguments. + * Return + * A syscall result. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -4903,6 +4910,7 @@ union bpf_attr { FN(check_mtu), \ FN(for_each_map_elem), \ FN(snprintf), \ + FN(sys_bpf), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3-71-gd317 From cdf7fb0a9f3d36b279590ac41e61c6b655db0d4a Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 13 May 2021 17:36:04 -0700 Subject: bpf: Introduce bpfptr_t user/kernel pointer. Similar to sockptr_t introduce bpfptr_t with few additions: make_bpfptr() creates new user/kernel pointer in the same address space as existing user/kernel pointer. bpfptr_add() advances the user/kernel pointer. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210514003623.28033-3-alexei.starovoitov@gmail.com --- include/linux/bpfptr.h | 75 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 75 insertions(+) create mode 100644 include/linux/bpfptr.h (limited to 'include/linux') diff --git a/include/linux/bpfptr.h b/include/linux/bpfptr.h new file mode 100644 index 000000000000..5cdeab497cb3 --- /dev/null +++ b/include/linux/bpfptr.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* A pointer that can point to either kernel or userspace memory. */ +#ifndef _LINUX_BPFPTR_H +#define _LINUX_BPFPTR_H + +#include + +typedef sockptr_t bpfptr_t; + +static inline bool bpfptr_is_kernel(bpfptr_t bpfptr) +{ + return bpfptr.is_kernel; +} + +static inline bpfptr_t KERNEL_BPFPTR(void *p) +{ + return (bpfptr_t) { .kernel = p, .is_kernel = true }; +} + +static inline bpfptr_t USER_BPFPTR(void __user *p) +{ + return (bpfptr_t) { .user = p }; +} + +static inline bpfptr_t make_bpfptr(u64 addr, bool is_kernel) +{ + if (is_kernel) + return KERNEL_BPFPTR((void*) (uintptr_t) addr); + else + return USER_BPFPTR(u64_to_user_ptr(addr)); +} + +static inline bool bpfptr_is_null(bpfptr_t bpfptr) +{ + if (bpfptr_is_kernel(bpfptr)) + return !bpfptr.kernel; + return !bpfptr.user; +} + +static inline void bpfptr_add(bpfptr_t *bpfptr, size_t val) +{ + if (bpfptr_is_kernel(*bpfptr)) + bpfptr->kernel += val; + else + bpfptr->user += val; +} + +static inline int copy_from_bpfptr_offset(void *dst, bpfptr_t src, + size_t offset, size_t size) +{ + return copy_from_sockptr_offset(dst, (sockptr_t) src, offset, size); +} + +static inline int copy_from_bpfptr(void *dst, bpfptr_t src, size_t size) +{ + return copy_from_bpfptr_offset(dst, src, 0, size); +} + +static inline int copy_to_bpfptr_offset(bpfptr_t dst, size_t offset, + const void *src, size_t size) +{ + return copy_to_sockptr_offset((sockptr_t) dst, offset, src, size); +} + +static inline void *memdup_bpfptr(bpfptr_t src, size_t len) +{ + return memdup_sockptr((sockptr_t) src, len); +} + +static inline long strncpy_from_bpfptr(char *dst, bpfptr_t src, size_t count) +{ + return strncpy_from_sockptr(dst, (sockptr_t) src, count); +} + +#endif /* _LINUX_BPFPTR_H */ -- cgit v1.2.3-71-gd317 From af2ac3e13e45752af03c8a933f9b6e18841b128b Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 13 May 2021 17:36:05 -0700 Subject: bpf: Prepare bpf syscall to be used from kernel and user space. With the help from bpfptr_t prepare relevant bpf syscall commands to be used from kernel and user space. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210514003623.28033-4-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 8 ++-- kernel/bpf/bpf_iter.c | 13 +++--- kernel/bpf/syscall.c | 113 +++++++++++++++++++++++++++++++++----------------- kernel/bpf/verifier.c | 34 ++++++++------- net/bpf/test_run.c | 2 +- 5 files changed, 104 insertions(+), 66 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 04a2bf41ae72..7fd53380c981 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -22,6 +22,7 @@ #include #include #include +#include struct bpf_verifier_env; struct bpf_verifier_log; @@ -1428,7 +1429,7 @@ struct bpf_iter__bpf_map_elem { int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info); bool bpf_iter_prog_supported(struct bpf_prog *prog); -int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); +int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, struct bpf_prog *prog); int bpf_iter_new_fd(struct bpf_link *link); bool bpf_link_is_iter(struct bpf_link *link); struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop); @@ -1459,7 +1460,7 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); int bpf_get_file_flag(int flags); -int bpf_check_uarg_tail_zero(void __user *uaddr, size_t expected_size, +int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size, size_t actual_size); /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and @@ -1479,8 +1480,7 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) } /* verify correctness of eBPF program */ -int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, - union bpf_attr __user *uattr); +int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr); #ifndef CONFIG_BPF_JIT_ALWAYS_ON void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index 931870f9cf56..2d4fbdbb194e 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -473,15 +473,16 @@ bool bpf_link_is_iter(struct bpf_link *link) return link->ops == &bpf_iter_link_lops; } -int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, + struct bpf_prog *prog) { - union bpf_iter_link_info __user *ulinfo; struct bpf_link_primer link_primer; struct bpf_iter_target_info *tinfo; union bpf_iter_link_info linfo; struct bpf_iter_link *link; u32 prog_btf_id, linfo_len; bool existed = false; + bpfptr_t ulinfo; int err; if (attr->link_create.target_fd || attr->link_create.flags) @@ -489,18 +490,18 @@ int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) memset(&linfo, 0, sizeof(union bpf_iter_link_info)); - ulinfo = u64_to_user_ptr(attr->link_create.iter_info); + ulinfo = make_bpfptr(attr->link_create.iter_info, uattr.is_kernel); linfo_len = attr->link_create.iter_info_len; - if (!ulinfo ^ !linfo_len) + if (bpfptr_is_null(ulinfo) ^ !linfo_len) return -EINVAL; - if (ulinfo) { + if (!bpfptr_is_null(ulinfo)) { err = bpf_check_uarg_tail_zero(ulinfo, sizeof(linfo), linfo_len); if (err) return err; linfo_len = min_t(u32, linfo_len, sizeof(linfo)); - if (copy_from_user(&linfo, ulinfo, linfo_len)) + if (copy_from_bpfptr(&linfo, ulinfo, linfo_len)) return -EFAULT; } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b1e7352919cb..28387fe149ba 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -72,11 +72,10 @@ static const struct bpf_map_ops * const bpf_map_types[] = { * copy_from_user() call. However, this is not a concern since this function is * meant to be a future-proofing of bits. */ -int bpf_check_uarg_tail_zero(void __user *uaddr, +int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size, size_t actual_size) { - unsigned char __user *addr = uaddr + expected_size; int res; if (unlikely(actual_size > PAGE_SIZE)) /* silly large */ @@ -85,7 +84,12 @@ int bpf_check_uarg_tail_zero(void __user *uaddr, if (actual_size <= expected_size) return 0; - res = check_zeroed_user(addr, actual_size - expected_size); + if (uaddr.is_kernel) + res = memchr_inv(uaddr.kernel + expected_size, 0, + actual_size - expected_size) == NULL; + else + res = check_zeroed_user(uaddr.user + expected_size, + actual_size - expected_size); if (res < 0) return res; return res ? 0 : -E2BIG; @@ -1004,6 +1008,17 @@ static void *__bpf_copy_key(void __user *ukey, u64 key_size) return NULL; } +static void *___bpf_copy_key(bpfptr_t ukey, u64 key_size) +{ + if (key_size) + return memdup_bpfptr(ukey, key_size); + + if (!bpfptr_is_null(ukey)) + return ERR_PTR(-EINVAL); + + return NULL; +} + /* last field in 'union bpf_attr' used by this command */ #define BPF_MAP_LOOKUP_ELEM_LAST_FIELD flags @@ -1074,10 +1089,10 @@ err_put: #define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags -static int map_update_elem(union bpf_attr *attr) +static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) { - void __user *ukey = u64_to_user_ptr(attr->key); - void __user *uvalue = u64_to_user_ptr(attr->value); + bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel); + bpfptr_t uvalue = make_bpfptr(attr->value, uattr.is_kernel); int ufd = attr->map_fd; struct bpf_map *map; void *key, *value; @@ -1103,7 +1118,7 @@ static int map_update_elem(union bpf_attr *attr) goto err_put; } - key = __bpf_copy_key(ukey, map->key_size); + key = ___bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; @@ -1123,7 +1138,7 @@ static int map_update_elem(union bpf_attr *attr) goto free_key; err = -EFAULT; - if (copy_from_user(value, uvalue, value_size) != 0) + if (copy_from_bpfptr(value, uvalue, value_size) != 0) goto free_value; err = bpf_map_update_value(map, f, key, value, attr->flags); @@ -2076,7 +2091,7 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) /* last field in 'union bpf_attr' used by this command */ #define BPF_PROG_LOAD_LAST_FIELD attach_prog_fd -static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) +static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) { enum bpf_prog_type type = attr->prog_type; struct bpf_prog *prog, *dst_prog = NULL; @@ -2101,8 +2116,9 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) return -EPERM; /* copy eBPF program license from user space */ - if (strncpy_from_user(license, u64_to_user_ptr(attr->license), - sizeof(license) - 1) < 0) + if (strncpy_from_bpfptr(license, + make_bpfptr(attr->license, uattr.is_kernel), + sizeof(license) - 1) < 0) return -EFAULT; license[sizeof(license) - 1] = 0; @@ -2186,8 +2202,9 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) prog->len = attr->insn_cnt; err = -EFAULT; - if (copy_from_user(prog->insns, u64_to_user_ptr(attr->insns), - bpf_prog_insn_size(prog)) != 0) + if (copy_from_bpfptr(prog->insns, + make_bpfptr(attr->insns, uattr.is_kernel), + bpf_prog_insn_size(prog)) != 0) goto free_prog_sec; prog->orig_prog = NULL; @@ -3423,7 +3440,7 @@ static int bpf_prog_get_info_by_fd(struct file *file, u32 ulen; int err; - err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len); + err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); @@ -3702,7 +3719,7 @@ static int bpf_map_get_info_by_fd(struct file *file, u32 info_len = attr->info.info_len; int err; - err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len); + err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); @@ -3745,7 +3762,7 @@ static int bpf_btf_get_info_by_fd(struct file *file, u32 info_len = attr->info.info_len; int err; - err = bpf_check_uarg_tail_zero(uinfo, sizeof(*uinfo), info_len); + err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(*uinfo), info_len); if (err) return err; @@ -3762,7 +3779,7 @@ static int bpf_link_get_info_by_fd(struct file *file, u32 info_len = attr->info.info_len; int err; - err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len); + err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); @@ -4023,13 +4040,14 @@ err_put: return err; } -static int tracing_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +static int tracing_bpf_link_attach(const union bpf_attr *attr, bpfptr_t uattr, + struct bpf_prog *prog) { if (attr->link_create.attach_type != prog->expected_attach_type) return -EINVAL; if (prog->expected_attach_type == BPF_TRACE_ITER) - return bpf_iter_link_attach(attr, prog); + return bpf_iter_link_attach(attr, uattr, prog); else if (prog->type == BPF_PROG_TYPE_EXT) return bpf_tracing_prog_attach(prog, attr->link_create.target_fd, @@ -4038,7 +4056,7 @@ static int tracing_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog * } #define BPF_LINK_CREATE_LAST_FIELD link_create.iter_info_len -static int link_create(union bpf_attr *attr) +static int link_create(union bpf_attr *attr, bpfptr_t uattr) { enum bpf_prog_type ptype; struct bpf_prog *prog; @@ -4057,7 +4075,7 @@ static int link_create(union bpf_attr *attr) goto out; if (prog->type == BPF_PROG_TYPE_EXT) { - ret = tracing_bpf_link_attach(attr, prog); + ret = tracing_bpf_link_attach(attr, uattr, prog); goto out; } @@ -4078,7 +4096,7 @@ static int link_create(union bpf_attr *attr) ret = cgroup_bpf_link_attach(attr, prog); break; case BPF_PROG_TYPE_TRACING: - ret = tracing_bpf_link_attach(attr, prog); + ret = tracing_bpf_link_attach(attr, uattr, prog); break; case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_SK_LOOKUP: @@ -4366,7 +4384,7 @@ out_prog_put: return ret; } -SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) +static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) { union bpf_attr attr; int err; @@ -4381,7 +4399,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz /* copy attributes from user space, may be less than sizeof(bpf_attr) */ memset(&attr, 0, sizeof(attr)); - if (copy_from_user(&attr, uattr, size) != 0) + if (copy_from_bpfptr(&attr, uattr, size) != 0) return -EFAULT; err = security_bpf(cmd, &attr, size); @@ -4396,7 +4414,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz err = map_lookup_elem(&attr); break; case BPF_MAP_UPDATE_ELEM: - err = map_update_elem(&attr); + err = map_update_elem(&attr, uattr); break; case BPF_MAP_DELETE_ELEM: err = map_delete_elem(&attr); @@ -4423,21 +4441,21 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz err = bpf_prog_detach(&attr); break; case BPF_PROG_QUERY: - err = bpf_prog_query(&attr, uattr); + err = bpf_prog_query(&attr, uattr.user); break; case BPF_PROG_TEST_RUN: - err = bpf_prog_test_run(&attr, uattr); + err = bpf_prog_test_run(&attr, uattr.user); break; case BPF_PROG_GET_NEXT_ID: - err = bpf_obj_get_next_id(&attr, uattr, + err = bpf_obj_get_next_id(&attr, uattr.user, &prog_idr, &prog_idr_lock); break; case BPF_MAP_GET_NEXT_ID: - err = bpf_obj_get_next_id(&attr, uattr, + err = bpf_obj_get_next_id(&attr, uattr.user, &map_idr, &map_idr_lock); break; case BPF_BTF_GET_NEXT_ID: - err = bpf_obj_get_next_id(&attr, uattr, + err = bpf_obj_get_next_id(&attr, uattr.user, &btf_idr, &btf_idr_lock); break; case BPF_PROG_GET_FD_BY_ID: @@ -4447,7 +4465,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz err = bpf_map_get_fd_by_id(&attr); break; case BPF_OBJ_GET_INFO_BY_FD: - err = bpf_obj_get_info_by_fd(&attr, uattr); + err = bpf_obj_get_info_by_fd(&attr, uattr.user); break; case BPF_RAW_TRACEPOINT_OPEN: err = bpf_raw_tracepoint_open(&attr); @@ -4459,26 +4477,26 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz err = bpf_btf_get_fd_by_id(&attr); break; case BPF_TASK_FD_QUERY: - err = bpf_task_fd_query(&attr, uattr); + err = bpf_task_fd_query(&attr, uattr.user); break; case BPF_MAP_LOOKUP_AND_DELETE_ELEM: err = map_lookup_and_delete_elem(&attr); break; case BPF_MAP_LOOKUP_BATCH: - err = bpf_map_do_batch(&attr, uattr, BPF_MAP_LOOKUP_BATCH); + err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_LOOKUP_BATCH); break; case BPF_MAP_LOOKUP_AND_DELETE_BATCH: - err = bpf_map_do_batch(&attr, uattr, + err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_LOOKUP_AND_DELETE_BATCH); break; case BPF_MAP_UPDATE_BATCH: - err = bpf_map_do_batch(&attr, uattr, BPF_MAP_UPDATE_BATCH); + err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_UPDATE_BATCH); break; case BPF_MAP_DELETE_BATCH: - err = bpf_map_do_batch(&attr, uattr, BPF_MAP_DELETE_BATCH); + err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_DELETE_BATCH); break; case BPF_LINK_CREATE: - err = link_create(&attr); + err = link_create(&attr, uattr); break; case BPF_LINK_UPDATE: err = link_update(&attr); @@ -4487,7 +4505,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz err = bpf_link_get_fd_by_id(&attr); break; case BPF_LINK_GET_NEXT_ID: - err = bpf_obj_get_next_id(&attr, uattr, + err = bpf_obj_get_next_id(&attr, uattr.user, &link_idr, &link_idr_lock); break; case BPF_ENABLE_STATS: @@ -4510,6 +4528,11 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz return err; } +SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) +{ + return __sys_bpf(cmd, USER_BPFPTR(uattr), size); +} + static bool syscall_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, @@ -4524,7 +4547,19 @@ static bool syscall_prog_is_valid_access(int off, int size, BPF_CALL_3(bpf_sys_bpf, int, cmd, void *, attr, u32, attr_size) { - return -EINVAL; + switch (cmd) { + case BPF_MAP_CREATE: + case BPF_MAP_UPDATE_ELEM: + case BPF_MAP_FREEZE: + case BPF_PROG_LOAD: + break; + /* case BPF_PROG_TEST_RUN: + * is not part of this list to prevent recursive test_run + */ + default: + return -EINVAL; + } + return __sys_bpf(cmd, KERNEL_BPFPTR(attr), attr_size); } const struct bpf_func_proto bpf_sys_bpf_proto = { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 37407d8fbca4..e63c7d60e00d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -9436,7 +9436,7 @@ static int check_abnormal_return(struct bpf_verifier_env *env) static int check_btf_func(struct bpf_verifier_env *env, const union bpf_attr *attr, - union bpf_attr __user *uattr) + bpfptr_t uattr) { const struct btf_type *type, *func_proto, *ret_type; u32 i, nfuncs, urec_size, min_size; @@ -9445,7 +9445,7 @@ static int check_btf_func(struct bpf_verifier_env *env, struct bpf_func_info_aux *info_aux = NULL; struct bpf_prog *prog; const struct btf *btf; - void __user *urecord; + bpfptr_t urecord; u32 prev_offset = 0; bool scalar_return; int ret = -ENOMEM; @@ -9473,7 +9473,7 @@ static int check_btf_func(struct bpf_verifier_env *env, prog = env->prog; btf = prog->aux->btf; - urecord = u64_to_user_ptr(attr->func_info); + urecord = make_bpfptr(attr->func_info, uattr.is_kernel); min_size = min_t(u32, krec_size, urec_size); krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL | __GFP_NOWARN); @@ -9491,13 +9491,15 @@ static int check_btf_func(struct bpf_verifier_env *env, /* set the size kernel expects so loader can zero * out the rest of the record. */ - if (put_user(min_size, &uattr->func_info_rec_size)) + if (copy_to_bpfptr_offset(uattr, + offsetof(union bpf_attr, func_info_rec_size), + &min_size, sizeof(min_size))) ret = -EFAULT; } goto err_free; } - if (copy_from_user(&krecord[i], urecord, min_size)) { + if (copy_from_bpfptr(&krecord[i], urecord, min_size)) { ret = -EFAULT; goto err_free; } @@ -9549,7 +9551,7 @@ static int check_btf_func(struct bpf_verifier_env *env, } prev_offset = krecord[i].insn_off; - urecord += urec_size; + bpfptr_add(&urecord, urec_size); } prog->aux->func_info = krecord; @@ -9581,14 +9583,14 @@ static void adjust_btf_func(struct bpf_verifier_env *env) static int check_btf_line(struct bpf_verifier_env *env, const union bpf_attr *attr, - union bpf_attr __user *uattr) + bpfptr_t uattr) { u32 i, s, nr_linfo, ncopy, expected_size, rec_size, prev_offset = 0; struct bpf_subprog_info *sub; struct bpf_line_info *linfo; struct bpf_prog *prog; const struct btf *btf; - void __user *ulinfo; + bpfptr_t ulinfo; int err; nr_linfo = attr->line_info_cnt; @@ -9614,7 +9616,7 @@ static int check_btf_line(struct bpf_verifier_env *env, s = 0; sub = env->subprog_info; - ulinfo = u64_to_user_ptr(attr->line_info); + ulinfo = make_bpfptr(attr->line_info, uattr.is_kernel); expected_size = sizeof(struct bpf_line_info); ncopy = min_t(u32, expected_size, rec_size); for (i = 0; i < nr_linfo; i++) { @@ -9622,14 +9624,15 @@ static int check_btf_line(struct bpf_verifier_env *env, if (err) { if (err == -E2BIG) { verbose(env, "nonzero tailing record in line_info"); - if (put_user(expected_size, - &uattr->line_info_rec_size)) + if (copy_to_bpfptr_offset(uattr, + offsetof(union bpf_attr, line_info_rec_size), + &expected_size, sizeof(expected_size))) err = -EFAULT; } goto err_free; } - if (copy_from_user(&linfo[i], ulinfo, ncopy)) { + if (copy_from_bpfptr(&linfo[i], ulinfo, ncopy)) { err = -EFAULT; goto err_free; } @@ -9681,7 +9684,7 @@ static int check_btf_line(struct bpf_verifier_env *env, } prev_offset = linfo[i].insn_off; - ulinfo += rec_size; + bpfptr_add(&ulinfo, rec_size); } if (s != env->subprog_cnt) { @@ -9703,7 +9706,7 @@ err_free: static int check_btf_info(struct bpf_verifier_env *env, const union bpf_attr *attr, - union bpf_attr __user *uattr) + bpfptr_t uattr) { struct btf *btf; int err; @@ -13275,8 +13278,7 @@ struct btf *bpf_get_btf_vmlinux(void) return btf_vmlinux; } -int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, - union bpf_attr __user *uattr) +int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) { u64 start_time = ktime_get_ns(); struct bpf_verifier_env *env; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index a6972d7ddf80..aa47af349ba8 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -409,7 +409,7 @@ static void *bpf_ctx_init(const union bpf_attr *kattr, u32 max_size) return ERR_PTR(-ENOMEM); if (data_in) { - err = bpf_check_uarg_tail_zero(data_in, max_size, size); + err = bpf_check_uarg_tail_zero(USER_BPFPTR(data_in), max_size, size); if (err) { kfree(data); return ERR_PTR(err); -- cgit v1.2.3-71-gd317 From c571bd752e91602f092823b2f1ee685a74d2726c Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 13 May 2021 17:36:08 -0700 Subject: bpf: Make btf_load command to be bpfptr_t compatible. Similar to prog_load make btf_load command to be availble to bpf_prog_type_syscall program. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210514003623.28033-7-alexei.starovoitov@gmail.com --- include/linux/btf.h | 2 +- kernel/bpf/btf.c | 8 ++++---- kernel/bpf/syscall.c | 7 ++++--- 3 files changed, 9 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index 3bac66e0183a..94a0c976c90f 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -21,7 +21,7 @@ extern const struct file_operations btf_fops; void btf_get(struct btf *btf); void btf_put(struct btf *btf); -int btf_new_fd(const union bpf_attr *attr); +int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr); struct btf *btf_get_by_fd(int fd); int btf_get_info_by_fd(const struct btf *btf, const union bpf_attr *attr, diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 0600ed325fa0..fbf6c06a9d62 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -4257,7 +4257,7 @@ static int btf_parse_hdr(struct btf_verifier_env *env) return 0; } -static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size, +static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, u32 log_level, char __user *log_ubuf, u32 log_size) { struct btf_verifier_env *env = NULL; @@ -4306,7 +4306,7 @@ static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size, btf->data = data; btf->data_size = btf_data_size; - if (copy_from_user(data, btf_data, btf_data_size)) { + if (copy_from_bpfptr(data, btf_data, btf_data_size)) { err = -EFAULT; goto errout; } @@ -5780,12 +5780,12 @@ static int __btf_new_fd(struct btf *btf) return anon_inode_getfd("btf", &btf_fops, btf, O_RDONLY | O_CLOEXEC); } -int btf_new_fd(const union bpf_attr *attr) +int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr) { struct btf *btf; int ret; - btf = btf_parse(u64_to_user_ptr(attr->btf), + btf = btf_parse(make_bpfptr(attr->btf, uattr.is_kernel), attr->btf_size, attr->btf_log_level, u64_to_user_ptr(attr->btf_log_buf), attr->btf_log_size); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 28387fe149ba..415865c49dd4 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3842,7 +3842,7 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, #define BPF_BTF_LOAD_LAST_FIELD btf_log_level -static int bpf_btf_load(const union bpf_attr *attr) +static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr) { if (CHECK_ATTR(BPF_BTF_LOAD)) return -EINVAL; @@ -3850,7 +3850,7 @@ static int bpf_btf_load(const union bpf_attr *attr) if (!bpf_capable()) return -EPERM; - return btf_new_fd(attr); + return btf_new_fd(attr, uattr); } #define BPF_BTF_GET_FD_BY_ID_LAST_FIELD btf_id @@ -4471,7 +4471,7 @@ static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) err = bpf_raw_tracepoint_open(&attr); break; case BPF_BTF_LOAD: - err = bpf_btf_load(&attr); + err = bpf_btf_load(&attr, uattr); break; case BPF_BTF_GET_FD_BY_ID: err = bpf_btf_get_fd_by_id(&attr); @@ -4552,6 +4552,7 @@ BPF_CALL_3(bpf_sys_bpf, int, cmd, void *, attr, u32, attr_size) case BPF_MAP_UPDATE_ELEM: case BPF_MAP_FREEZE: case BPF_PROG_LOAD: + case BPF_BTF_LOAD: break; /* case BPF_PROG_TEST_RUN: * is not part of this list to prevent recursive test_run -- cgit v1.2.3-71-gd317 From 387544bfa291a22383d60b40f887360e2b931ec6 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 13 May 2021 17:36:10 -0700 Subject: bpf: Introduce fd_idx Typical program loading sequence involves creating bpf maps and applying map FDs into bpf instructions in various places in the bpf program. This job is done by libbpf that is using compiler generated ELF relocations to patch certain instruction after maps are created and BTFs are loaded. The goal of fd_idx is to allow bpf instructions to stay immutable after compilation. At load time the libbpf would still create maps as usual, but it wouldn't need to patch instructions. It would store map_fds into __u32 fd_array[] and would pass that pointer to sys_bpf(BPF_PROG_LOAD). Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210514003623.28033-9-alexei.starovoitov@gmail.com --- include/linux/bpf_verifier.h | 1 + include/uapi/linux/bpf.h | 16 +++++++++----- kernel/bpf/syscall.c | 2 +- kernel/bpf/verifier.c | 47 +++++++++++++++++++++++++++++++++--------- tools/include/uapi/linux/bpf.h | 16 +++++++++----- 5 files changed, 61 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index d4632aa3ca50..e774ecc1cd1f 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -450,6 +450,7 @@ struct bpf_verifier_env { u32 peak_states; /* longest register parentage chain walked for liveness marking */ u32 longest_mark_read_walk; + bpfptr_t fd_array; }; __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c92648f38144..de58a714ed36 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1098,8 +1098,8 @@ enum bpf_link_type { /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * the following extensions: * - * insn[0].src_reg: BPF_PSEUDO_MAP_FD - * insn[0].imm: map fd + * insn[0].src_reg: BPF_PSEUDO_MAP_[FD|IDX] + * insn[0].imm: map fd or fd_idx * insn[1].imm: 0 * insn[0].off: 0 * insn[1].off: 0 @@ -1107,15 +1107,19 @@ enum bpf_link_type { * verifier type: CONST_PTR_TO_MAP */ #define BPF_PSEUDO_MAP_FD 1 -/* insn[0].src_reg: BPF_PSEUDO_MAP_VALUE - * insn[0].imm: map fd +#define BPF_PSEUDO_MAP_IDX 5 + +/* insn[0].src_reg: BPF_PSEUDO_MAP_[IDX_]VALUE + * insn[0].imm: map fd or fd_idx * insn[1].imm: offset into value * insn[0].off: 0 * insn[1].off: 0 * ldimm64 rewrite: address of map[0]+offset * verifier type: PTR_TO_MAP_VALUE */ -#define BPF_PSEUDO_MAP_VALUE 2 +#define BPF_PSEUDO_MAP_VALUE 2 +#define BPF_PSEUDO_MAP_IDX_VALUE 6 + /* insn[0].src_reg: BPF_PSEUDO_BTF_ID * insn[0].imm: kernel btd id of VAR * insn[1].imm: 0 @@ -1315,6 +1319,8 @@ union bpf_attr { /* or valid module BTF object fd or 0 to attach to vmlinux */ __u32 attach_btf_obj_fd; }; + __u32 :32; /* pad */ + __aligned_u64 fd_array; /* array of FDs */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 415865c49dd4..da7dc2406470 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2089,7 +2089,7 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD attach_prog_fd +#define BPF_PROG_LOAD_LAST_FIELD fd_array static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e63c7d60e00d..9189eecb26dd 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8915,12 +8915,14 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) mark_reg_known_zero(env, regs, insn->dst_reg); dst_reg->map_ptr = map; - if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) { + if (insn->src_reg == BPF_PSEUDO_MAP_VALUE || + insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE) { dst_reg->type = PTR_TO_MAP_VALUE; dst_reg->off = aux->map_off; if (map_value_has_spin_lock(map)) dst_reg->id = ++env->id_gen; - } else if (insn->src_reg == BPF_PSEUDO_MAP_FD) { + } else if (insn->src_reg == BPF_PSEUDO_MAP_FD || + insn->src_reg == BPF_PSEUDO_MAP_IDX) { dst_reg->type = CONST_PTR_TO_MAP; } else { verbose(env, "bpf verifier is misconfigured\n"); @@ -11173,6 +11175,7 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) struct bpf_map *map; struct fd f; u64 addr; + u32 fd; if (i == insn_cnt - 1 || insn[1].code != 0 || insn[1].dst_reg != 0 || insn[1].src_reg != 0 || @@ -11202,16 +11205,38 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) /* In final convert_pseudo_ld_imm64() step, this is * converted into regular 64-bit imm load insn. */ - if ((insn[0].src_reg != BPF_PSEUDO_MAP_FD && - insn[0].src_reg != BPF_PSEUDO_MAP_VALUE) || - (insn[0].src_reg == BPF_PSEUDO_MAP_FD && - insn[1].imm != 0)) { - verbose(env, - "unrecognized bpf_ld_imm64 insn\n"); + switch (insn[0].src_reg) { + case BPF_PSEUDO_MAP_VALUE: + case BPF_PSEUDO_MAP_IDX_VALUE: + break; + case BPF_PSEUDO_MAP_FD: + case BPF_PSEUDO_MAP_IDX: + if (insn[1].imm == 0) + break; + fallthrough; + default: + verbose(env, "unrecognized bpf_ld_imm64 insn\n"); return -EINVAL; } - f = fdget(insn[0].imm); + switch (insn[0].src_reg) { + case BPF_PSEUDO_MAP_IDX_VALUE: + case BPF_PSEUDO_MAP_IDX: + if (bpfptr_is_null(env->fd_array)) { + verbose(env, "fd_idx without fd_array is invalid\n"); + return -EPROTO; + } + if (copy_from_bpfptr_offset(&fd, env->fd_array, + insn[0].imm * sizeof(fd), + sizeof(fd))) + return -EFAULT; + break; + default: + fd = insn[0].imm; + break; + } + + f = fdget(fd); map = __bpf_map_get(f); if (IS_ERR(map)) { verbose(env, "fd %d is not pointing to valid bpf_map\n", @@ -11226,7 +11251,8 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) } aux = &env->insn_aux_data[i]; - if (insn->src_reg == BPF_PSEUDO_MAP_FD) { + if (insn[0].src_reg == BPF_PSEUDO_MAP_FD || + insn[0].src_reg == BPF_PSEUDO_MAP_IDX) { addr = (unsigned long)map; } else { u32 off = insn[1].imm; @@ -13308,6 +13334,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) env->insn_aux_data[i].orig_idx = i; env->prog = *prog; env->ops = bpf_verifier_ops[env->prog->type]; + env->fd_array = make_bpfptr(attr->fd_array, uattr.is_kernel); is_priv = bpf_capable(); bpf_get_btf_vmlinux(); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index c92648f38144..de58a714ed36 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1098,8 +1098,8 @@ enum bpf_link_type { /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * the following extensions: * - * insn[0].src_reg: BPF_PSEUDO_MAP_FD - * insn[0].imm: map fd + * insn[0].src_reg: BPF_PSEUDO_MAP_[FD|IDX] + * insn[0].imm: map fd or fd_idx * insn[1].imm: 0 * insn[0].off: 0 * insn[1].off: 0 @@ -1107,15 +1107,19 @@ enum bpf_link_type { * verifier type: CONST_PTR_TO_MAP */ #define BPF_PSEUDO_MAP_FD 1 -/* insn[0].src_reg: BPF_PSEUDO_MAP_VALUE - * insn[0].imm: map fd +#define BPF_PSEUDO_MAP_IDX 5 + +/* insn[0].src_reg: BPF_PSEUDO_MAP_[IDX_]VALUE + * insn[0].imm: map fd or fd_idx * insn[1].imm: offset into value * insn[0].off: 0 * insn[1].off: 0 * ldimm64 rewrite: address of map[0]+offset * verifier type: PTR_TO_MAP_VALUE */ -#define BPF_PSEUDO_MAP_VALUE 2 +#define BPF_PSEUDO_MAP_VALUE 2 +#define BPF_PSEUDO_MAP_IDX_VALUE 6 + /* insn[0].src_reg: BPF_PSEUDO_BTF_ID * insn[0].imm: kernel btd id of VAR * insn[1].imm: 0 @@ -1315,6 +1319,8 @@ union bpf_attr { /* or valid module BTF object fd or 0 to attach to vmlinux */ __u32 attach_btf_obj_fd; }; + __u32 :32; /* pad */ + __aligned_u64 fd_array; /* array of FDs */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ -- cgit v1.2.3-71-gd317 From 3d78417b60fba249cc555468cb72d96f5cde2964 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 13 May 2021 17:36:11 -0700 Subject: bpf: Add bpf_btf_find_by_name_kind() helper. Add new helper: long bpf_btf_find_by_name_kind(char *name, int name_sz, u32 kind, int flags) Description Find BTF type with given name and kind in vmlinux BTF or in module's BTFs. Return Returns btf_id and btf_obj_fd in lower and upper 32 bits. It will be used by loader program to find btf_id to attach the program to and to find btf_ids of ksyms. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210514003623.28033-10-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 7 +++++ kernel/bpf/btf.c | 62 ++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 2 ++ tools/include/uapi/linux/bpf.h | 7 +++++ 5 files changed, 79 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7fd53380c981..9dc44ba97584 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1974,6 +1974,7 @@ extern const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto; extern const struct bpf_func_proto bpf_task_storage_get_proto; extern const struct bpf_func_proto bpf_task_storage_delete_proto; extern const struct bpf_func_proto bpf_for_each_map_elem_proto; +extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index de58a714ed36..3cc07351c1cf 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4748,6 +4748,12 @@ union bpf_attr { * Execute bpf syscall with given arguments. * Return * A syscall result. + * + * long bpf_btf_find_by_name_kind(char *name, int name_sz, u32 kind, int flags) + * Description + * Find BTF type with given name and kind in vmlinux BTF or in module's BTFs. + * Return + * Returns btf_id and btf_obj_fd in lower and upper 32 bits. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -4917,6 +4923,7 @@ union bpf_attr { FN(for_each_map_elem), \ FN(snprintf), \ FN(sys_bpf), \ + FN(btf_find_by_name_kind), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index fbf6c06a9d62..85716327c375 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6085,3 +6085,65 @@ struct module *btf_try_get_module(const struct btf *btf) return res; } + +BPF_CALL_4(bpf_btf_find_by_name_kind, char *, name, int, name_sz, u32, kind, int, flags) +{ + struct btf *btf; + long ret; + + if (flags) + return -EINVAL; + + if (name_sz <= 1 || name[name_sz - 1]) + return -EINVAL; + + btf = bpf_get_btf_vmlinux(); + if (IS_ERR(btf)) + return PTR_ERR(btf); + + ret = btf_find_by_name_kind(btf, name, kind); + /* ret is never zero, since btf_find_by_name_kind returns + * positive btf_id or negative error. + */ + if (ret < 0) { + struct btf *mod_btf; + int id; + + /* If name is not found in vmlinux's BTF then search in module's BTFs */ + spin_lock_bh(&btf_idr_lock); + idr_for_each_entry(&btf_idr, mod_btf, id) { + if (!btf_is_module(mod_btf)) + continue; + /* linear search could be slow hence unlock/lock + * the IDR to avoiding holding it for too long + */ + btf_get(mod_btf); + spin_unlock_bh(&btf_idr_lock); + ret = btf_find_by_name_kind(mod_btf, name, kind); + if (ret > 0) { + int btf_obj_fd; + + btf_obj_fd = __btf_new_fd(mod_btf); + if (btf_obj_fd < 0) { + btf_put(mod_btf); + return btf_obj_fd; + } + return ret | (((u64)btf_obj_fd) << 32); + } + spin_lock_bh(&btf_idr_lock); + btf_put(mod_btf); + } + spin_unlock_bh(&btf_idr_lock); + } + return ret; +} + +const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = { + .func = bpf_btf_find_by_name_kind, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_CONST_SIZE, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_ANYTHING, +}; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index da7dc2406470..f93ff2ebf96d 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -4584,6 +4584,8 @@ syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) switch (func_id) { case BPF_FUNC_sys_bpf: return &bpf_sys_bpf_proto; + case BPF_FUNC_btf_find_by_name_kind: + return &bpf_btf_find_by_name_kind_proto; default: return tracing_prog_func_proto(func_id, prog); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index de58a714ed36..3cc07351c1cf 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4748,6 +4748,12 @@ union bpf_attr { * Execute bpf syscall with given arguments. * Return * A syscall result. + * + * long bpf_btf_find_by_name_kind(char *name, int name_sz, u32 kind, int flags) + * Description + * Find BTF type with given name and kind in vmlinux BTF or in module's BTFs. + * Return + * Returns btf_id and btf_obj_fd in lower and upper 32 bits. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -4917,6 +4923,7 @@ union bpf_attr { FN(for_each_map_elem), \ FN(snprintf), \ FN(sys_bpf), \ + FN(btf_find_by_name_kind), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3-71-gd317 From 3e87f192b405960c0fe83e0925bd0dadf4f8cf43 Mon Sep 17 00:00:00 2001 From: Denis Salopek Date: Tue, 11 May 2021 23:00:04 +0200 Subject: bpf: Add lookup_and_delete_elem support to hashtab Extend the existing bpf_map_lookup_and_delete_elem() functionality to hashtab map types, in addition to stacks and queues. Create a new hashtab bpf_map_ops function that does lookup and deletion of the element under the same bucket lock and add the created map_ops to bpf.h. Signed-off-by: Denis Salopek Signed-off-by: Andrii Nakryiko Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/4d18480a3e990ffbf14751ddef0325eed3be2966.1620763117.git.denis.salopek@sartura.hr --- include/linux/bpf.h | 2 + include/uapi/linux/bpf.h | 13 ++++++ kernel/bpf/hashtab.c | 98 ++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 34 +++++++++++++-- tools/include/uapi/linux/bpf.h | 13 ++++++ 5 files changed, 156 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9dc44ba97584..1e9a0ff3217b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -70,6 +70,8 @@ struct bpf_map_ops { void *(*map_lookup_elem_sys_only)(struct bpf_map *map, void *key); int (*map_lookup_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); + int (*map_lookup_and_delete_elem)(struct bpf_map *map, void *key, + void *value, u64 flags); int (*map_lookup_and_delete_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 418b9b813d65..562adeac1d67 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -527,6 +527,15 @@ union bpf_iter_link_info { * Look up an element with the given *key* in the map referred to * by the file descriptor *fd*, and if found, delete the element. * + * For **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map + * types, the *flags* argument needs to be set to 0, but for other + * map types, it may be specified as: + * + * **BPF_F_LOCK** + * Look up and delete the value of a spin-locked map + * without returning the lock. This must be specified if + * the elements contain a spinlock. + * * The **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map types * implement this command as a "pop" operation, deleting the top * element rather than one corresponding to *key*. @@ -536,6 +545,10 @@ union bpf_iter_link_info { * This command is only valid for the following map types: * * **BPF_MAP_TYPE_QUEUE** * * **BPF_MAP_TYPE_STACK** + * * **BPF_MAP_TYPE_HASH** + * * **BPF_MAP_TYPE_PERCPU_HASH** + * * **BPF_MAP_TYPE_LRU_HASH** + * * **BPF_MAP_TYPE_LRU_PERCPU_HASH** * * Return * Returns zero on success. On error, -1 is returned and *errno* diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index d7ebb12ffffc..9da0a0413a53 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -1401,6 +1401,100 @@ static void htab_map_seq_show_elem(struct bpf_map *map, void *key, rcu_read_unlock(); } +static int __htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key, + void *value, bool is_lru_map, + bool is_percpu, u64 flags) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + struct hlist_nulls_head *head; + unsigned long bflags; + struct htab_elem *l; + u32 hash, key_size; + struct bucket *b; + int ret; + + key_size = map->key_size; + + hash = htab_map_hash(key, key_size, htab->hashrnd); + b = __select_bucket(htab, hash); + head = &b->head; + + ret = htab_lock_bucket(htab, b, hash, &bflags); + if (ret) + return ret; + + l = lookup_elem_raw(head, hash, key, key_size); + if (!l) { + ret = -ENOENT; + } else { + if (is_percpu) { + u32 roundup_value_size = round_up(map->value_size, 8); + void __percpu *pptr; + int off = 0, cpu; + + pptr = htab_elem_get_ptr(l, key_size); + for_each_possible_cpu(cpu) { + bpf_long_memcpy(value + off, + per_cpu_ptr(pptr, cpu), + roundup_value_size); + off += roundup_value_size; + } + } else { + u32 roundup_key_size = round_up(map->key_size, 8); + + if (flags & BPF_F_LOCK) + copy_map_value_locked(map, value, l->key + + roundup_key_size, + true); + else + copy_map_value(map, value, l->key + + roundup_key_size); + check_and_init_map_lock(map, value); + } + + hlist_nulls_del_rcu(&l->hash_node); + if (!is_lru_map) + free_htab_elem(htab, l); + } + + htab_unlock_bucket(htab, b, hash, bflags); + + if (is_lru_map && l) + bpf_lru_push_free(&htab->lru, &l->lru_node); + + return ret; +} + +static int htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + return __htab_map_lookup_and_delete_elem(map, key, value, false, false, + flags); +} + +static int htab_percpu_map_lookup_and_delete_elem(struct bpf_map *map, + void *key, void *value, + u64 flags) +{ + return __htab_map_lookup_and_delete_elem(map, key, value, false, true, + flags); +} + +static int htab_lru_map_lookup_and_delete_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + return __htab_map_lookup_and_delete_elem(map, key, value, true, false, + flags); +} + +static int htab_lru_percpu_map_lookup_and_delete_elem(struct bpf_map *map, + void *key, void *value, + u64 flags) +{ + return __htab_map_lookup_and_delete_elem(map, key, value, true, true, + flags); +} + static int __htab_map_lookup_and_delete_batch(struct bpf_map *map, const union bpf_attr *attr, @@ -1934,6 +2028,7 @@ const struct bpf_map_ops htab_map_ops = { .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, .map_lookup_elem = htab_map_lookup_elem, + .map_lookup_and_delete_elem = htab_map_lookup_and_delete_elem, .map_update_elem = htab_map_update_elem, .map_delete_elem = htab_map_delete_elem, .map_gen_lookup = htab_map_gen_lookup, @@ -1954,6 +2049,7 @@ const struct bpf_map_ops htab_lru_map_ops = { .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, .map_lookup_elem = htab_lru_map_lookup_elem, + .map_lookup_and_delete_elem = htab_lru_map_lookup_and_delete_elem, .map_lookup_elem_sys_only = htab_lru_map_lookup_elem_sys, .map_update_elem = htab_lru_map_update_elem, .map_delete_elem = htab_lru_map_delete_elem, @@ -2077,6 +2173,7 @@ const struct bpf_map_ops htab_percpu_map_ops = { .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, .map_lookup_elem = htab_percpu_map_lookup_elem, + .map_lookup_and_delete_elem = htab_percpu_map_lookup_and_delete_elem, .map_update_elem = htab_percpu_map_update_elem, .map_delete_elem = htab_map_delete_elem, .map_seq_show_elem = htab_percpu_map_seq_show_elem, @@ -2096,6 +2193,7 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = { .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, .map_lookup_elem = htab_lru_percpu_map_lookup_elem, + .map_lookup_and_delete_elem = htab_lru_percpu_map_lookup_and_delete_elem, .map_update_elem = htab_lru_percpu_map_update_elem, .map_delete_elem = htab_lru_map_delete_elem, .map_seq_show_elem = htab_percpu_map_seq_show_elem, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 1d1cd80a6e67..50457019da27 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1483,7 +1483,7 @@ free_buf: return err; } -#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD value +#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD flags static int map_lookup_and_delete_elem(union bpf_attr *attr) { @@ -1499,6 +1499,9 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) if (CHECK_ATTR(BPF_MAP_LOOKUP_AND_DELETE_ELEM)) return -EINVAL; + if (attr->flags & ~BPF_F_LOCK) + return -EINVAL; + f = fdget(ufd); map = __bpf_map_get(f); if (IS_ERR(map)) @@ -1509,24 +1512,47 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) goto err_put; } + if (attr->flags && + (map->map_type == BPF_MAP_TYPE_QUEUE || + map->map_type == BPF_MAP_TYPE_STACK)) { + err = -EINVAL; + goto err_put; + } + + if ((attr->flags & BPF_F_LOCK) && + !map_value_has_spin_lock(map)) { + err = -EINVAL; + goto err_put; + } + key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; } - value_size = map->value_size; + value_size = bpf_map_value_size(map); err = -ENOMEM; value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; + err = -ENOTSUPP; if (map->map_type == BPF_MAP_TYPE_QUEUE || map->map_type == BPF_MAP_TYPE_STACK) { err = map->ops->map_pop_elem(map, value); - } else { - err = -ENOTSUPP; + } else if (map->map_type == BPF_MAP_TYPE_HASH || + map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { + if (!bpf_map_is_dev_bound(map)) { + bpf_disable_instrumentation(); + rcu_read_lock(); + err = map->ops->map_lookup_and_delete_elem(map, key, value, attr->flags); + rcu_read_unlock(); + bpf_enable_instrumentation(); + } } if (err) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 418b9b813d65..562adeac1d67 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -527,6 +527,15 @@ union bpf_iter_link_info { * Look up an element with the given *key* in the map referred to * by the file descriptor *fd*, and if found, delete the element. * + * For **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map + * types, the *flags* argument needs to be set to 0, but for other + * map types, it may be specified as: + * + * **BPF_F_LOCK** + * Look up and delete the value of a spin-locked map + * without returning the lock. This must be specified if + * the elements contain a spinlock. + * * The **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map types * implement this command as a "pop" operation, deleting the top * element rather than one corresponding to *key*. @@ -536,6 +545,10 @@ union bpf_iter_link_info { * This command is only valid for the following map types: * * **BPF_MAP_TYPE_QUEUE** * * **BPF_MAP_TYPE_STACK** + * * **BPF_MAP_TYPE_HASH** + * * **BPF_MAP_TYPE_PERCPU_HASH** + * * **BPF_MAP_TYPE_LRU_HASH** + * * **BPF_MAP_TYPE_LRU_PERCPU_HASH** * * Return * Returns zero on success. On error, -1 is returned and *errno* -- cgit v1.2.3-71-gd317 From 8fb33b6055300a23f26868680c22a5726834785e Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Tue, 25 May 2021 10:56:59 +0800 Subject: bpf: Fix spelling mistakes Fix some spelling mistakes in comments: aother ==> another Netiher ==> Neither desribe ==> describe intializing ==> initializing funciton ==> function wont ==> won't and move the word 'the' at the end to the next line accross ==> across pathes ==> paths triggerred ==> triggered excute ==> execute ether ==> either conervative ==> conservative convetion ==> convention markes ==> marks interpeter ==> interpreter Signed-off-by: Zhen Lei Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210525025659.8898-2-thunder.leizhen@huawei.com --- include/linux/bpf_local_storage.h | 4 ++-- kernel/bpf/bpf_inode_storage.c | 2 +- kernel/bpf/btf.c | 6 +++--- kernel/bpf/devmap.c | 4 ++-- kernel/bpf/hashtab.c | 4 ++-- kernel/bpf/reuseport_array.c | 2 +- kernel/bpf/trampoline.c | 2 +- kernel/bpf/verifier.c | 12 ++++++------ 8 files changed, 18 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index b902c580c48d..24496bc28e7b 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -58,7 +58,7 @@ struct bpf_local_storage_data { * from the object's bpf_local_storage. * * Put it in the same cacheline as the data to minimize - * the number of cachelines access during the cache hit case. + * the number of cachelines accessed during the cache hit case. */ struct bpf_local_storage_map __rcu *smap; u8 data[] __aligned(8); @@ -71,7 +71,7 @@ struct bpf_local_storage_elem { struct bpf_local_storage __rcu *local_storage; struct rcu_head rcu; /* 8 bytes hole */ - /* The data is stored in aother cacheline to minimize + /* The data is stored in another cacheline to minimize * the number of cachelines access during a cache hit. */ struct bpf_local_storage_data sdata ____cacheline_aligned; diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c index 2921ca39a93e..96ceed0e0fb5 100644 --- a/kernel/bpf/bpf_inode_storage.c +++ b/kernel/bpf/bpf_inode_storage.c @@ -72,7 +72,7 @@ void bpf_inode_storage_free(struct inode *inode) return; } - /* Netiher the bpf_prog nor the bpf-map's syscall + /* Neither the bpf_prog nor the bpf-map's syscall * could be modifying the local_storage->list now. * Thus, no elem can be added-to or deleted-from the * local_storage->list by the bpf_prog or by the bpf-map's syscall. diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 85716327c375..a6e39c5ea0bf 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -51,7 +51,7 @@ * The BTF type section contains a list of 'struct btf_type' objects. * Each one describes a C type. Recall from the above section * that a 'struct btf_type' object could be immediately followed by extra - * data in order to desribe some particular C types. + * data in order to describe some particular C types. * * type_id: * ~~~~~~~ @@ -1143,7 +1143,7 @@ static void *btf_show_obj_safe(struct btf_show *show, /* * We need a new copy to our safe object, either because we haven't - * yet copied and are intializing safe data, or because the data + * yet copied and are initializing safe data, or because the data * we want falls outside the boundaries of the safe object. */ if (!safe) { @@ -3417,7 +3417,7 @@ static struct btf_kind_operations func_proto_ops = { * BTF_KIND_FUNC_PROTO cannot be directly referred by * a struct's member. * - * It should be a funciton pointer instead. + * It should be a function pointer instead. * (i.e. struct's member -> BTF_KIND_PTR -> BTF_KIND_FUNC_PROTO) * * Hence, there is no btf_func_check_member(). diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index aa516472ce46..d60d617ec0d7 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -382,8 +382,8 @@ void __dev_flush(void) } /* 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. + * update happens in parallel here a dev_put won't happen until after reading + * the ifindex. */ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key) { diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 9da0a0413a53..6f6681b07364 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -46,12 +46,12 @@ * events, kprobes and tracing to be invoked before the prior invocation * from one of these contexts completed. sys_bpf() uses the same mechanism * by pinning the task to the current CPU and incrementing the recursion - * protection accross the map operation. + * protection across the map operation. * * This has subtle implications on PREEMPT_RT. PREEMPT_RT forbids certain * operations like memory allocations (even with GFP_ATOMIC) from atomic * contexts. This is required because even with GFP_ATOMIC the memory - * allocator calls into code pathes which acquire locks with long held lock + * allocator calls into code paths which acquire locks with long held lock * sections. To ensure the deterministic behaviour these locks are regular * spinlocks, which are converted to 'sleepable' spinlocks on RT. The only * true atomic contexts on an RT kernel are the low level hardware diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c index 4838922f723d..93a55391791a 100644 --- a/kernel/bpf/reuseport_array.c +++ b/kernel/bpf/reuseport_array.c @@ -102,7 +102,7 @@ static void reuseport_array_free(struct bpf_map *map) /* * ops->map_*_elem() will not be able to access this * array now. Hence, this function only races with - * bpf_sk_reuseport_detach() which was triggerred by + * bpf_sk_reuseport_detach() which was triggered by * close() or disconnect(). * * This function and bpf_sk_reuseport_detach() are diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 2d44b5aa0057..28a3630c48ee 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -552,7 +552,7 @@ static void notrace inc_misses_counter(struct bpf_prog *prog) * __bpf_prog_enter returns: * 0 - skip execution of the bpf prog * 1 - execute bpf prog - * [2..MAX_U64] - excute bpf prog and record execution time. + * [2..MAX_U64] - execute bpf prog and record execution time. * This is start time. */ u64 notrace __bpf_prog_enter(struct bpf_prog *prog) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9189eecb26dd..1de4b8c6ee42 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -47,7 +47,7 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { * - unreachable insns exist (shouldn't be a forest. program = one function) * - out of bounds or malformed jumps * The second pass is all possible path descent from the 1st insn. - * Since it's analyzing all pathes through the program, the length of the + * Since it's analyzing all paths through the program, the length of the * analysis is limited to 64k insn, which may be hit even if total number of * insn is less then 4K, but there are too many branches that change stack/regs. * Number of 'branches to be analyzed' is limited to 1k @@ -132,7 +132,7 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { * If it's ok, then verifier allows this BPF_CALL insn and looks at * .ret_type which is RET_PTR_TO_MAP_VALUE_OR_NULL, so it sets * R0->type = PTR_TO_MAP_VALUE_OR_NULL which means bpf_map_lookup_elem() function - * returns ether pointer to map value or NULL. + * returns either pointer to map value or NULL. * * When type PTR_TO_MAP_VALUE_OR_NULL passes through 'if (reg != 0) goto +off' * insn, the register holding that pointer in the true branch changes state to @@ -2616,7 +2616,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, if (dst_reg != BPF_REG_FP) { /* The backtracking logic can only recognize explicit * stack slot address like [fp - 8]. Other spill of - * scalar via different register has to be conervative. + * scalar via different register has to be conservative. * Backtrack from here and mark all registers as precise * that contributed into 'reg' being a constant. */ @@ -9053,7 +9053,7 @@ static int check_return_code(struct bpf_verifier_env *env) !prog->aux->attach_func_proto->type) return 0; - /* eBPF calling convetion is such that R0 is used + /* eBPF calling convention is such that R0 is used * to return the value from eBPF program. * Make sure that it's readable at this time * of bpf_exit, which means that program wrote @@ -9844,7 +9844,7 @@ static void clean_verifier_state(struct bpf_verifier_env *env, * Since the verifier pushes the branch states as it sees them while exploring * the program the condition of walking the branch instruction for the second * time means that all states below this branch were already explored and - * their final liveness markes are already propagated. + * their final liveness marks are already propagated. * Hence when the verifier completes the search of state list in is_state_visited() * we can call this clean_live_states() function to mark all liveness states * as REG_LIVE_DONE to indicate that 'parent' pointers of 'struct bpf_reg_state' @@ -12464,7 +12464,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) prog->aux->max_pkt_offset = MAX_PACKET_OFF; /* mark bpf_tail_call as different opcode to avoid - * conditional branch in the interpeter for every normal + * conditional branch in the interpreter for every normal * call and to prevent accidental JITing by JIT compiler * that doesn't support bpf_tail_call yet */ -- cgit v1.2.3-71-gd317 From e624d4ed4aa8cc3c69d1359b0aaea539203ed266 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Wed, 19 May 2021 17:07:45 +0800 Subject: xdp: Extend xdp_redirect_map with broadcast support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend xdp_redirect_map for broadcast support. With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be excluded when do broadcasting. When getting the devices in dev hash map via dev_map_hash_get_next_key(), there is a possibility that we fall back to the first key when a device was removed. This will duplicate packets on some interfaces. So just walk the whole buckets to avoid this issue. For dev array map, we also walk the whole map to find valid interfaces. Function bpf_clear_redirect_map() was removed in commit ee75aef23afe ("bpf, xdp: Restructure redirect actions"). Add it back as we need to use ri->map again. With test topology: +-------------------+ +-------------------+ | Host A (i40e 10G) | ---------- | eno1(i40e 10G) | +-------------------+ | | | Host B | +-------------------+ | | | Host C (i40e 10G) | ---------- | eno2(i40e 10G) | +-------------------+ | | | +------+ | | veth0 -- | Peer | | | veth1 -- | | | | veth2 -- | NS | | | +------+ | +-------------------+ On Host A: # pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64 On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory): Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing. All the veth peers in the NS have a XDP_DROP program loaded. The forward_map max_entries in xdp_redirect_map_multi is modify to 4. Testing the performance impact on the regular xdp_redirect path with and without patch (to check impact of additional check for broadcast mode): 5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M 5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M 5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M 5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M Testing the performance when cloning packets with the redirect_map_multi test, using a redirect map size of 4, filled with 1-3 devices: 5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M 5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M 5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M Signed-off-by: Hangbin Liu Signed-off-by: Daniel Borkmann Acked-by: Toke Høiland-Jørgensen Acked-by: Martin KaFai Lau Acked-by: John Fastabend Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/bpf/20210519090747.1655268-3-liuhangbin@gmail.com --- include/linux/bpf.h | 20 +++++ include/linux/filter.h | 19 ++++- include/net/xdp.h | 1 + include/trace/events/xdp.h | 6 +- include/uapi/linux/bpf.h | 14 +++- kernel/bpf/cpumap.c | 3 +- kernel/bpf/devmap.c | 183 ++++++++++++++++++++++++++++++++++++++++- net/core/filter.c | 37 ++++++++- net/core/xdp.c | 28 +++++++ net/xdp/xskmap.c | 3 +- tools/include/uapi/linux/bpf.h | 14 +++- 11 files changed, 313 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1e9a0ff3217b..86dec5001ae2 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1501,8 +1501,13 @@ int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, struct net_device *dev_rx); int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, struct net_device *dev_rx); +int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, + struct bpf_map *map, bool exclude_ingress); int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog); +int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, + struct bpf_prog *xdp_prog, struct bpf_map *map, + bool exclude_ingress); bool dev_map_can_have_prog(struct bpf_map *map); void __cpu_map_flush(void); @@ -1670,6 +1675,13 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, return 0; } +static inline +int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, + struct bpf_map *map, bool exclude_ingress) +{ + return 0; +} + struct sk_buff; static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, @@ -1679,6 +1691,14 @@ static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, return 0; } +static inline +int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, + struct bpf_prog *xdp_prog, struct bpf_map *map, + bool exclude_ingress) +{ + return 0; +} + static inline void __cpu_map_flush(void) { } diff --git a/include/linux/filter.h b/include/linux/filter.h index 9a09547bc7ba..c5ad7df029ed 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -646,6 +646,7 @@ struct bpf_redirect_info { u32 flags; u32 tgt_index; void *tgt_value; + struct bpf_map *map; u32 map_id; enum bpf_map_type map_type; u32 kern_flags; @@ -1464,17 +1465,19 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, } #endif /* IS_ENABLED(CONFIG_IPV6) */ -static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifindex, u64 flags, +static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifindex, + u64 flags, const u64 flag_mask, void *lookup_elem(struct bpf_map *map, u32 key)) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + const u64 action_mask = XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX; /* Lower bits of the flags are used as return code on lookup failure */ - if (unlikely(flags > XDP_TX)) + if (unlikely(flags & ~(action_mask | flag_mask))) return XDP_ABORTED; ri->tgt_value = lookup_elem(map, ifindex); - if (unlikely(!ri->tgt_value)) { + if (unlikely(!ri->tgt_value) && !(flags & BPF_F_BROADCAST)) { /* If the lookup fails we want to clear out the state in the * redirect_info struct completely, so that if an eBPF program * performs multiple lookups, the last one always takes @@ -1482,13 +1485,21 @@ static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifind */ ri->map_id = INT_MAX; /* Valid map id idr range: [1,INT_MAX[ */ ri->map_type = BPF_MAP_TYPE_UNSPEC; - return flags; + return flags & action_mask; } ri->tgt_index = ifindex; ri->map_id = map->id; ri->map_type = map->map_type; + if (flags & BPF_F_BROADCAST) { + WRITE_ONCE(ri->map, map); + ri->flags = flags; + } else { + WRITE_ONCE(ri->map, NULL); + ri->flags = 0; + } + return XDP_REDIRECT; } diff --git a/include/net/xdp.h b/include/net/xdp.h index a5bc214a49d9..5533f0ab2afc 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -170,6 +170,7 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct net_device *dev); int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp); +struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf); static inline void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index fcad3645a70b..c40fc97f9417 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -110,7 +110,11 @@ DECLARE_EVENT_CLASS(xdp_redirect_template, u32 ifindex = 0, map_index = index; if (map_type == BPF_MAP_TYPE_DEVMAP || map_type == BPF_MAP_TYPE_DEVMAP_HASH) { - ifindex = ((struct _bpf_dtab_netdev *)tgt)->dev->ifindex; + /* Just leave to_ifindex to 0 if do broadcast redirect, + * as tgt will be NULL. + */ + if (tgt) + ifindex = ((struct _bpf_dtab_netdev *)tgt)->dev->ifindex; } else if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) { ifindex = index; map_index = 0; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 562adeac1d67..2c1ba70abbf1 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2555,8 +2555,12 @@ union bpf_attr { * The lower two bits of *flags* are used as the return code if * the map lookup fails. This is so that the return value can be * one of the XDP program return codes up to **XDP_TX**, as chosen - * by the caller. Any higher bits in the *flags* argument must be - * unset. + * by the caller. The higher bits of *flags* can be set to + * BPF_F_BROADCAST or BPF_F_EXCLUDE_INGRESS as defined below. + * + * With BPF_F_BROADCAST the packet will be broadcasted to all the + * interfaces in the map, with BPF_F_EXCLUDE_INGRESS the ingress + * interface will be excluded when do broadcasting. * * See also **bpf_redirect**\ (), which only supports redirecting * to an ifindex, but doesn't require a map to do so. @@ -5122,6 +5126,12 @@ enum { BPF_F_BPRM_SECUREEXEC = (1ULL << 0), }; +/* Flags for bpf_redirect_map helper */ +enum { + BPF_F_BROADCAST = (1ULL << 3), + BPF_F_EXCLUDE_INGRESS = (1ULL << 4), +}; + #define __bpf_md_ptr(type, name) \ union { \ type name; \ diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 5dd3e866599a..a1a0c4e791c6 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -601,7 +601,8 @@ static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key) static int cpu_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) { - return __bpf_xdp_redirect_map(map, ifindex, flags, __cpu_map_lookup_elem); + return __bpf_xdp_redirect_map(map, ifindex, flags, 0, + __cpu_map_lookup_elem); } static int cpu_map_btf_id; diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 642264e32abd..f9148daab0e3 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -198,6 +198,7 @@ static void dev_map_free(struct bpf_map *map) list_del_rcu(&dtab->list); spin_unlock(&dev_map_lock); + bpf_clear_redirect_map(map); synchronize_rcu(); /* Make sure prior __dev_map_entry_free() have completed. */ @@ -515,6 +516,99 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, return __xdp_enqueue(dev, xdp, dev_rx, dst->xdp_prog); } +static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_buff *xdp, + int exclude_ifindex) +{ + if (!obj || obj->dev->ifindex == exclude_ifindex || + !obj->dev->netdev_ops->ndo_xdp_xmit) + return false; + + if (xdp_ok_fwd_dev(obj->dev, xdp->data_end - xdp->data)) + return false; + + return true; +} + +static int dev_map_enqueue_clone(struct bpf_dtab_netdev *obj, + struct net_device *dev_rx, + struct xdp_frame *xdpf) +{ + struct xdp_frame *nxdpf; + + nxdpf = xdpf_clone(xdpf); + if (!nxdpf) + return -ENOMEM; + + bq_enqueue(obj->dev, nxdpf, dev_rx, obj->xdp_prog); + + return 0; +} + +int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, + struct bpf_map *map, bool exclude_ingress) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + int exclude_ifindex = exclude_ingress ? dev_rx->ifindex : 0; + struct bpf_dtab_netdev *dst, *last_dst = NULL; + struct hlist_head *head; + struct xdp_frame *xdpf; + unsigned int i; + int err; + + xdpf = xdp_convert_buff_to_frame(xdp); + if (unlikely(!xdpf)) + return -EOVERFLOW; + + if (map->map_type == BPF_MAP_TYPE_DEVMAP) { + for (i = 0; i < map->max_entries; i++) { + dst = READ_ONCE(dtab->netdev_map[i]); + if (!is_valid_dst(dst, xdp, exclude_ifindex)) + continue; + + /* we only need n-1 clones; last_dst enqueued below */ + if (!last_dst) { + last_dst = dst; + continue; + } + + err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf); + if (err) + return err; + + last_dst = dst; + } + } else { /* BPF_MAP_TYPE_DEVMAP_HASH */ + for (i = 0; i < dtab->n_buckets; i++) { + head = dev_map_index_hash(dtab, i); + hlist_for_each_entry_rcu(dst, head, index_hlist, + lockdep_is_held(&dtab->index_lock)) { + if (!is_valid_dst(dst, xdp, exclude_ifindex)) + continue; + + /* we only need n-1 clones; last_dst enqueued below */ + if (!last_dst) { + last_dst = dst; + continue; + } + + err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf); + if (err) + return err; + + last_dst = dst; + } + } + } + + /* consume the last copy of the frame */ + if (last_dst) + bq_enqueue(last_dst->dev, xdpf, dev_rx, last_dst->xdp_prog); + else + xdp_return_frame_rx_napi(xdpf); /* dtab is empty */ + + return 0; +} + int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog) { @@ -529,6 +623,87 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, return 0; } +static int dev_map_redirect_clone(struct bpf_dtab_netdev *dst, + struct sk_buff *skb, + struct bpf_prog *xdp_prog) +{ + struct sk_buff *nskb; + int err; + + nskb = skb_clone(skb, GFP_ATOMIC); + if (!nskb) + return -ENOMEM; + + err = dev_map_generic_redirect(dst, nskb, xdp_prog); + if (unlikely(err)) { + consume_skb(nskb); + return err; + } + + return 0; +} + +int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, + struct bpf_prog *xdp_prog, struct bpf_map *map, + bool exclude_ingress) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + int exclude_ifindex = exclude_ingress ? dev->ifindex : 0; + struct bpf_dtab_netdev *dst, *last_dst = NULL; + struct hlist_head *head; + struct hlist_node *next; + unsigned int i; + int err; + + if (map->map_type == BPF_MAP_TYPE_DEVMAP) { + for (i = 0; i < map->max_entries; i++) { + dst = READ_ONCE(dtab->netdev_map[i]); + if (!dst || dst->dev->ifindex == exclude_ifindex) + continue; + + /* we only need n-1 clones; last_dst enqueued below */ + if (!last_dst) { + last_dst = dst; + continue; + } + + err = dev_map_redirect_clone(last_dst, skb, xdp_prog); + if (err) + return err; + + last_dst = dst; + } + } else { /* BPF_MAP_TYPE_DEVMAP_HASH */ + for (i = 0; i < dtab->n_buckets; i++) { + head = dev_map_index_hash(dtab, i); + hlist_for_each_entry_safe(dst, next, head, index_hlist) { + if (!dst || dst->dev->ifindex == exclude_ifindex) + continue; + + /* we only need n-1 clones; last_dst enqueued below */ + if (!last_dst) { + last_dst = dst; + continue; + } + + err = dev_map_redirect_clone(last_dst, skb, xdp_prog); + if (err) + return err; + + last_dst = dst; + } + } + } + + /* consume the first skb and return */ + if (last_dst) + return dev_map_generic_redirect(last_dst, skb, xdp_prog); + + /* dtab is empty */ + consume_skb(skb); + return 0; +} + static void *dev_map_lookup_elem(struct bpf_map *map, void *key) { struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key); @@ -755,12 +930,16 @@ static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value, static int dev_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) { - return __bpf_xdp_redirect_map(map, ifindex, flags, __dev_map_lookup_elem); + return __bpf_xdp_redirect_map(map, ifindex, flags, + BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, + __dev_map_lookup_elem); } static int dev_hash_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) { - return __bpf_xdp_redirect_map(map, ifindex, flags, __dev_map_hash_lookup_elem); + return __bpf_xdp_redirect_map(map, ifindex, flags, + BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, + __dev_map_hash_lookup_elem); } static int dev_map_btf_id; diff --git a/net/core/filter.c b/net/core/filter.c index 582ac196fd94..caa88955562e 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3930,6 +3930,23 @@ void xdp_do_flush(void) } EXPORT_SYMBOL_GPL(xdp_do_flush); +void bpf_clear_redirect_map(struct bpf_map *map) +{ + struct bpf_redirect_info *ri; + int cpu; + + for_each_possible_cpu(cpu) { + ri = per_cpu_ptr(&bpf_redirect_info, cpu); + /* Avoid polluting remote cacheline due to writes if + * not needed. Once we pass this test, we need the + * cmpxchg() to make sure it hasn't been changed in + * the meantime by remote CPU. + */ + if (unlikely(READ_ONCE(ri->map) == map)) + cmpxchg(&ri->map, map, NULL); + } +} + int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { @@ -3937,6 +3954,7 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; + struct bpf_map *map; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ @@ -3946,7 +3964,14 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: - err = dev_map_enqueue(fwd, xdp, dev); + map = READ_ONCE(ri->map); + if (unlikely(map)) { + WRITE_ONCE(ri->map, NULL); + err = dev_map_enqueue_multi(xdp, dev, map, + ri->flags & BPF_F_EXCLUDE_INGRESS); + } else { + err = dev_map_enqueue(fwd, xdp, dev); + } break; case BPF_MAP_TYPE_CPUMAP: err = cpu_map_enqueue(fwd, xdp, dev); @@ -3988,13 +4013,21 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, enum bpf_map_type map_type, u32 map_id) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_map *map; int err; switch (map_type) { case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: - err = dev_map_generic_redirect(fwd, skb, xdp_prog); + map = READ_ONCE(ri->map); + if (unlikely(map)) { + WRITE_ONCE(ri->map, NULL); + err = dev_map_redirect_multi(dev, skb, xdp_prog, map, + ri->flags & BPF_F_EXCLUDE_INGRESS); + } else { + err = dev_map_generic_redirect(fwd, skb, xdp_prog); + } if (unlikely(err)) goto err; break; diff --git a/net/core/xdp.c b/net/core/xdp.c index 858276e72c68..725d20f1b100 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -584,3 +584,31 @@ struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, return __xdp_build_skb_from_frame(xdpf, skb, dev); } EXPORT_SYMBOL_GPL(xdp_build_skb_from_frame); + +struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf) +{ + unsigned int headroom, totalsize; + struct xdp_frame *nxdpf; + struct page *page; + void *addr; + + headroom = xdpf->headroom + sizeof(*xdpf); + totalsize = headroom + xdpf->len; + + if (unlikely(totalsize > PAGE_SIZE)) + return NULL; + page = dev_alloc_page(); + if (!page) + return NULL; + addr = page_to_virt(page); + + memcpy(addr, xdpf, totalsize); + + nxdpf = addr; + nxdpf->data = addr + headroom; + nxdpf->frame_sz = PAGE_SIZE; + nxdpf->mem.type = MEM_TYPE_PAGE_ORDER0; + nxdpf->mem.id = 0; + + return nxdpf; +} diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c index 67b4ce504852..9df75ea4a567 100644 --- a/net/xdp/xskmap.c +++ b/net/xdp/xskmap.c @@ -226,7 +226,8 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key) static int xsk_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) { - return __bpf_xdp_redirect_map(map, ifindex, flags, __xsk_map_lookup_elem); + return __bpf_xdp_redirect_map(map, ifindex, flags, 0, + __xsk_map_lookup_elem); } void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 562adeac1d67..2c1ba70abbf1 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2555,8 +2555,12 @@ union bpf_attr { * The lower two bits of *flags* are used as the return code if * the map lookup fails. This is so that the return value can be * one of the XDP program return codes up to **XDP_TX**, as chosen - * by the caller. Any higher bits in the *flags* argument must be - * unset. + * by the caller. The higher bits of *flags* can be set to + * BPF_F_BROADCAST or BPF_F_EXCLUDE_INGRESS as defined below. + * + * With BPF_F_BROADCAST the packet will be broadcasted to all the + * interfaces in the map, with BPF_F_EXCLUDE_INGRESS the ingress + * interface will be excluded when do broadcasting. * * See also **bpf_redirect**\ (), which only supports redirecting * to an ifindex, but doesn't require a map to do so. @@ -5122,6 +5126,12 @@ enum { BPF_F_BPRM_SECUREEXEC = (1ULL << 0), }; +/* Flags for bpf_redirect_map helper */ +enum { + BPF_F_BROADCAST = (1ULL << 3), + BPF_F_EXCLUDE_INGRESS = (1ULL << 4), +}; + #define __bpf_md_ptr(type, name) \ union { \ type name; \ -- cgit v1.2.3-71-gd317 From 125217e0967fc905be35a3b2c9ba4db9a8616b92 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 25 May 2021 18:00:38 -0500 Subject: i40e: Replace one-element array with flexible-array member MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. Refactor the code according to the use of a flexible-array member in struct i40e_qvlist_info instead of one-element array, and use the struct_size() helper. [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://www.kernel.org/doc/html/v5.10/process/deprecated.html#zero-length-and-one-element-arrays Link: https://github.com/KSPP/linux/issues/79 Signed-off-by: Gustavo A. R. Silva Acked-by: Shiraz Saleem Signed-off-by: Tony Nguyen --- drivers/infiniband/hw/i40iw/i40iw_main.c | 5 ++--- drivers/net/ethernet/intel/i40e/i40e_client.c | 2 +- include/linux/net/intel/i40e_client.h | 2 +- 3 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c index b496f30ce066..364f69cd620f 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_main.c +++ b/drivers/infiniband/hw/i40iw/i40iw_main.c @@ -1423,7 +1423,7 @@ static enum i40iw_status_code i40iw_save_msix_info(struct i40iw_device *iwdev, struct i40e_qv_info *iw_qvinfo; u32 ceq_idx; u32 i; - u32 size; + size_t size; if (!ldev->msix_count) { i40iw_pr_err("No MSI-X vectors\n"); @@ -1433,8 +1433,7 @@ static enum i40iw_status_code i40iw_save_msix_info(struct i40iw_device *iwdev, iwdev->msix_count = ldev->msix_count; size = sizeof(struct i40iw_msix_vector) * iwdev->msix_count; - size += sizeof(struct i40e_qvlist_info); - size += sizeof(struct i40e_qv_info) * iwdev->msix_count - 1; + size += struct_size(iw_qvlist, qv_info, iwdev->msix_count); iwdev->iw_msixtbl = kzalloc(size, GFP_KERNEL); if (!iwdev->iw_msixtbl) diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c index 32f3facbed1a..63eab14a26df 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.c +++ b/drivers/net/ethernet/intel/i40e/i40e_client.c @@ -579,7 +579,7 @@ static int i40e_client_setup_qvlist(struct i40e_info *ldev, u32 v_idx, i, reg_idx, reg; ldev->qvlist_info = kzalloc(struct_size(ldev->qvlist_info, qv_info, - qvlist_info->num_vectors - 1), GFP_KERNEL); + qvlist_info->num_vectors), GFP_KERNEL); if (!ldev->qvlist_info) return -ENOMEM; ldev->qvlist_info->num_vectors = qvlist_info->num_vectors; diff --git a/include/linux/net/intel/i40e_client.h b/include/linux/net/intel/i40e_client.h index f41387a8969f..fd7bc860a241 100644 --- a/include/linux/net/intel/i40e_client.h +++ b/include/linux/net/intel/i40e_client.h @@ -48,7 +48,7 @@ struct i40e_qv_info { struct i40e_qvlist_info { u32 num_vectors; - struct i40e_qv_info qv_info[1]; + struct i40e_qv_info qv_info[]; }; -- cgit v1.2.3-71-gd317 From b973cf32453f78d8661a640d0a0167d1d41ea331 Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Mon, 23 Nov 2020 14:48:22 -0600 Subject: net/mlx5e: TC: Reserved bit 31 of REG_C1 for IPsec offload Currently ASAP features fully utilize all the bits of the CQE's flow tag and ft_metadata field. The flow tag field cannot be used because the flow table tagging in FTE does not allow partial write. We agree to reserve bit 31 of CQE's ft_metadata for IPsec to avoid ASAP CT from dropping IPsec offloaded packet Here is the new bit layout of REG_C1. Tunnel option id is reduced to 11 bits: < IPSEC MARKER (1) | ESW_TUN_ID(12) | ESW_TUN_OPTS(11) | ESW_ZONE_ID(8) > Signed-off-by: Huy Nguyen Signed-off-by: Raed Salem Reviewed-by: Paul Blakey Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed Signed-off-by: Paul Blakey --- drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_tc.h | 2 +- include/linux/mlx5/eswitch.h | 17 ++++++++++------- 3 files changed, 12 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index 6cdc52d50a48..8cef4e7cfa4b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -617,7 +617,7 @@ static bool mlx5e_restore_skb(struct sk_buff *skb, u32 chain, u32 reg_c1, struct mlx5e_tc_update_priv *tc_priv) { struct mlx5e_priv *priv = netdev_priv(skb->dev); - u32 tunnel_id = reg_c1 >> ESW_TUN_OFFSET; + u32 tunnel_id = (reg_c1 >> ESW_TUN_OFFSET) & TUNNEL_ID_MASK; if (chain) { struct mlx5_rep_uplink_priv *uplink_priv; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 3534d14d7d5c..721093b55acc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -129,7 +129,7 @@ struct tunnel_match_enc_opts { */ #define TUNNEL_INFO_BITS 12 #define TUNNEL_INFO_BITS_MASK GENMASK(TUNNEL_INFO_BITS - 1, 0) -#define ENC_OPTS_BITS 12 +#define ENC_OPTS_BITS 11 #define ENC_OPTS_BITS_MASK GENMASK(ENC_OPTS_BITS - 1, 0) #define TUNNEL_ID_BITS (TUNNEL_INFO_BITS + ENC_OPTS_BITS) #define TUNNEL_ID_MASK GENMASK(TUNNEL_ID_BITS - 1, 0) diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 17109b65c1ac..bc7db2e059eb 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -98,10 +98,11 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, u16 vport_num); /* Reg C1 usage: - * Reg C1 = < ESW_TUN_ID(12) | ESW_TUN_OPTS(12) | ESW_ZONE_ID(8) > + * Reg C1 = < Reserved(1) | ESW_TUN_ID(12) | ESW_TUN_OPTS(11) | ESW_ZONE_ID(8) > * - * Highest 12 bits of reg c1 is the encapsulation tunnel id, next 12 bits is - * encapsulation tunnel options, and the lowest 8 bits are used for zone id. + * Highest bit is reserved for other offloads as marker bit, next 12 bits of reg c1 + * is the encapsulation tunnel id, next 11 bits is encapsulation tunnel options, + * and the lowest 8 bits are used for zone id. * * Zone id is used to restore CT flow when packet misses on chain. * @@ -109,16 +110,18 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, * on miss and to support inner header rewrite by means of implicit chain 0 * flows. */ +#define ESW_RESERVED_BITS 1 #define ESW_ZONE_ID_BITS 8 -#define ESW_TUN_OPTS_BITS 12 +#define ESW_TUN_OPTS_BITS 11 #define ESW_TUN_ID_BITS 12 #define ESW_TUN_OPTS_OFFSET ESW_ZONE_ID_BITS #define ESW_TUN_OFFSET ESW_TUN_OPTS_OFFSET #define ESW_ZONE_ID_MASK GENMASK(ESW_ZONE_ID_BITS - 1, 0) -#define ESW_TUN_OPTS_MASK GENMASK(32 - ESW_TUN_ID_BITS - 1, ESW_TUN_OPTS_OFFSET) -#define ESW_TUN_MASK GENMASK(31, ESW_TUN_OFFSET) +#define ESW_TUN_OPTS_MASK GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, ESW_TUN_OPTS_OFFSET) +#define ESW_TUN_MASK GENMASK(31 - ESW_RESERVED_BITS, ESW_TUN_OFFSET) #define ESW_TUN_ID_SLOW_TABLE_GOTO_VPORT 0 /* 0 is not a valid tunnel id */ -#define ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT 0xFFF /* 0xFFF is a reserved mapping */ +/* 0x7FF is a reserved mapping */ +#define ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT GENMASK(ESW_TUN_OPTS_BITS - 1, 0) #define ESW_TUN_SLOW_TABLE_GOTO_VPORT ((ESW_TUN_ID_SLOW_TABLE_GOTO_VPORT << ESW_TUN_OPTS_BITS) | \ ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT) #define ESW_TUN_SLOW_TABLE_GOTO_VPORT_MARK ESW_TUN_OPTS_MASK -- cgit v1.2.3-71-gd317 From 4a98544d182761873381d46bb1a498703ca85bf0 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Mon, 8 Mar 2021 14:16:02 +0200 Subject: net/mlx5: Move chains ft pool to be used by all firmware steering Firmware FT pool is per device, but the software tracking of this pool only services fs_chains users, and if another layer takes a flow table, the pool will not be updated, and fs_chains will fail creating a flow table, with no recovery till the flow table is returned. Move FT pool to be global per device, and stored at the cmd level, so all layers can use it. Signed-off-by: Paul Blakey Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/Makefile | 2 +- drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 25 ++++-- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 27 +++++-- .../net/ethernet/mellanox/mlx5/core/fs_ft_pool.c | 83 ++++++++++++++++++++ .../net/ethernet/mellanox/mlx5/core/fs_ft_pool.h | 21 +++++ .../ethernet/mellanox/mlx5/core/lib/fs_chains.c | 89 ++-------------------- include/linux/mlx5/driver.h | 2 + 7 files changed, 151 insertions(+), 98 deletions(-) create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index a1223e904190..8dbdf1aef00f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -14,7 +14,7 @@ obj-$(CONFIG_MLX5_CORE) += mlx5_core.o mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ health.o mcg.o cq.o alloc.o port.o mr.o pd.o \ transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \ - fs_counters.o rl.o lag.o dev.o events.o wq.o lib/gid.o \ + fs_counters.o fs_ft_pool.o rl.o lag.o dev.o events.o wq.o lib/gid.o \ lib/devcom.o lib/pci_vsc.o lib/dm.o diag/fs_tracepoint.o \ diag/fw_tracer.o diag/crdump.o devlink.o diag/rsc_dump.o \ fw_reset.o qos.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 94712a10ef9a..b7aae8b75760 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -36,6 +36,7 @@ #include "fs_core.h" #include "fs_cmd.h" +#include "fs_ft_pool.h" #include "mlx5_core.h" #include "eswitch.h" @@ -192,18 +193,20 @@ static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns, u32 out[MLX5_ST_SZ_DW(create_flow_table_out)] = {}; u32 in[MLX5_ST_SZ_DW(create_flow_table_in)] = {}; struct mlx5_core_dev *dev = ns->dev; - unsigned int log_size = 0; int err; - log_size = size ? ilog2(roundup_pow_of_two(size)) : 0; - ft->max_fte = 1 << log_size; + if (size != POOL_NEXT_SIZE) + size = roundup_pow_of_two(size); + size = mlx5_ft_pool_get_avail_sz(dev, ft->type, size); + if (!size) + return -ENOSPC; MLX5_SET(create_flow_table_in, in, opcode, MLX5_CMD_OP_CREATE_FLOW_TABLE); MLX5_SET(create_flow_table_in, in, table_type, ft->type); MLX5_SET(create_flow_table_in, in, flow_table_context.level, ft->level); - MLX5_SET(create_flow_table_in, in, flow_table_context.log_size, log_size); + MLX5_SET(create_flow_table_in, in, flow_table_context.log_size, size ? ilog2(size) : 0); MLX5_SET(create_flow_table_in, in, vport_number, ft->vport); MLX5_SET(create_flow_table_in, in, other_vport, !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); @@ -240,9 +243,14 @@ static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns, } err = mlx5_cmd_exec_inout(dev, create_flow_table, in, out); - if (!err) + if (!err) { ft->id = MLX5_GET(create_flow_table_out, out, table_id); + ft->max_fte = size; + } else { + mlx5_ft_pool_put_sz(ns->dev, size); + } + return err; } @@ -251,6 +259,7 @@ static int mlx5_cmd_destroy_flow_table(struct mlx5_flow_root_namespace *ns, { u32 in[MLX5_ST_SZ_DW(destroy_flow_table_in)] = {}; struct mlx5_core_dev *dev = ns->dev; + int err; MLX5_SET(destroy_flow_table_in, in, opcode, MLX5_CMD_OP_DESTROY_FLOW_TABLE); @@ -260,7 +269,11 @@ static int mlx5_cmd_destroy_flow_table(struct mlx5_flow_root_namespace *ns, MLX5_SET(destroy_flow_table_in, in, other_vport, !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); - return mlx5_cmd_exec_in(dev, destroy_flow_table, in); + err = mlx5_cmd_exec_in(dev, destroy_flow_table, in); + if (!err) + mlx5_ft_pool_put_sz(ns->dev, ft->max_fte); + + return err; } static int mlx5_cmd_modify_flow_table(struct mlx5_flow_root_namespace *ns, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 378990c933e5..6e20cbb4656a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -38,6 +38,7 @@ #include "mlx5_core.h" #include "fs_core.h" #include "fs_cmd.h" +#include "fs_ft_pool.h" #include "diag/fs_tracepoint.h" #include "accel/ipsec.h" #include "fpga/ipsec.h" @@ -1166,6 +1167,8 @@ mlx5_create_lag_demux_flow_table(struct mlx5_flow_namespace *ns, ft_attr.level = level; ft_attr.prio = prio; + ft_attr.max_fte = 1; + return __mlx5_create_flow_table(ns, &ft_attr, FS_FT_OP_MOD_LAG_DEMUX, 0); } EXPORT_SYMBOL(mlx5_create_lag_demux_flow_table); @@ -1175,19 +1178,20 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns, struct mlx5_flow_table_attr *ft_attr) { int num_reserved_entries = ft_attr->autogroup.num_reserved_entries; - int autogroups_max_fte = ft_attr->max_fte - num_reserved_entries; int max_num_groups = ft_attr->autogroup.max_num_groups; struct mlx5_flow_table *ft; - - if (max_num_groups > autogroups_max_fte) - return ERR_PTR(-EINVAL); - if (num_reserved_entries > ft_attr->max_fte) - return ERR_PTR(-EINVAL); + int autogroups_max_fte; ft = mlx5_create_flow_table(ns, ft_attr); if (IS_ERR(ft)) return ft; + autogroups_max_fte = ft->max_fte - num_reserved_entries; + if (max_num_groups > autogroups_max_fte) + goto err_validate; + if (num_reserved_entries > ft->max_fte) + goto err_validate; + ft->autogroup.active = true; ft->autogroup.required_groups = max_num_groups; ft->autogroup.max_fte = autogroups_max_fte; @@ -1195,6 +1199,10 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns, ft->autogroup.group_size = autogroups_max_fte / (max_num_groups + 1); return ft; + +err_validate: + mlx5_destroy_flow_table(ft); + return ERR_PTR(-ENOSPC); } EXPORT_SYMBOL(mlx5_create_auto_grouped_flow_table); @@ -2588,6 +2596,7 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev) mlx5_cleanup_fc_stats(dev); kmem_cache_destroy(steering->ftes_cache); kmem_cache_destroy(steering->fgs_cache); + mlx5_ft_pool_destroy(dev); kfree(steering); } @@ -2938,9 +2947,13 @@ int mlx5_init_fs(struct mlx5_core_dev *dev) if (err) return err; + err = mlx5_ft_pool_init(dev); + if (err) + return err; + steering = kzalloc(sizeof(*steering), GFP_KERNEL); if (!steering) - return -ENOMEM; + goto err; steering->dev = dev; dev->priv.steering = steering; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c new file mode 100644 index 000000000000..526fbb669142 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c @@ -0,0 +1,83 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2021 Mellanox Technologies. */ + +#include "fs_ft_pool.h" + +/* Firmware currently has 4 pool of 4 sizes that it supports (FT_POOLS), + * and a virtual memory region of 16M (MLX5_FT_SIZE), this region is duplicated + * for each flow table pool. We can allocate up to 16M of each pool, + * and we keep track of how much we used via mlx5_ft_pool_get_avail_sz. + * Firmware doesn't report any of this for now. + * ESW_POOL is expected to be sorted from large to small and match firmware + * pools. + */ +#define FT_SIZE (16 * 1024 * 1024) +static const unsigned int FT_POOLS[] = { 4 * 1024 * 1024, + 1 * 1024 * 1024, + 64 * 1024, + 128, + 1 /* size for termination tables */ }; +struct mlx5_ft_pool { + int ft_left[ARRAY_SIZE(FT_POOLS)]; +}; + +int mlx5_ft_pool_init(struct mlx5_core_dev *dev) +{ + struct mlx5_ft_pool *ft_pool; + int i; + + ft_pool = kzalloc(sizeof(*ft_pool), GFP_KERNEL); + + for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--) + ft_pool->ft_left[i] = FT_SIZE / FT_POOLS[i]; + + dev->priv.ft_pool = ft_pool; + return 0; +} + +void mlx5_ft_pool_destroy(struct mlx5_core_dev *dev) +{ + kfree(dev->priv.ft_pool); +} + +int +mlx5_ft_pool_get_avail_sz(struct mlx5_core_dev *dev, enum fs_flow_table_type table_type, + int desired_size) +{ + u32 max_ft_size = 1 << MLX5_CAP_FLOWTABLE_TYPE(dev, log_max_ft_size, table_type); + int i, found_i = -1; + + for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--) { + if (dev->priv.ft_pool->ft_left[i] && FT_POOLS[i] >= desired_size && + FT_POOLS[i] <= max_ft_size) { + found_i = i; + if (desired_size != POOL_NEXT_SIZE) + break; + } + } + + if (found_i != -1) { + --dev->priv.ft_pool->ft_left[found_i]; + return FT_POOLS[found_i]; + } + + return 0; +} + +void +mlx5_ft_pool_put_sz(struct mlx5_core_dev *dev, int sz) +{ + int i; + + if (!sz) + return; + + for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--) { + if (sz == FT_POOLS[i]) { + ++dev->priv.ft_pool->ft_left[i]; + return; + } + } + + WARN_ONCE(1, "Couldn't find size %d in flow table size pool", sz); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h new file mode 100644 index 000000000000..25f4274b372b --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021 Mellanox Technologies. */ + +#ifndef __MLX5_FS_FT_POOL_H__ +#define __MLX5_FS_FT_POOL_H__ + +#include +#include "fs_core.h" + +#define POOL_NEXT_SIZE 0 + +int mlx5_ft_pool_init(struct mlx5_core_dev *dev); +void mlx5_ft_pool_destroy(struct mlx5_core_dev *dev); + +int +mlx5_ft_pool_get_avail_sz(struct mlx5_core_dev *dev, enum fs_flow_table_type table_type, + int desired_size); +void +mlx5_ft_pool_put_sz(struct mlx5_core_dev *dev, int sz); + +#endif /* __MLX5_FS_FT_POOL_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c index 4c60c540bf9d..d0cfe7adb8a0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c @@ -6,6 +6,7 @@ #include #include "lib/fs_chains.h" +#include "fs_ft_pool.h" #include "en/mapping.h" #include "fs_core.h" #include "en_tc.h" @@ -13,25 +14,10 @@ #define chains_lock(chains) ((chains)->lock) #define chains_ht(chains) ((chains)->chains_ht) #define prios_ht(chains) ((chains)->prios_ht) -#define ft_pool_left(chains) ((chains)->ft_left) #define tc_default_ft(chains) ((chains)->tc_default_ft) #define tc_end_ft(chains) ((chains)->tc_end_ft) #define ns_to_chains_fs_prio(ns) ((ns) == MLX5_FLOW_NAMESPACE_FDB ? \ FDB_TC_OFFLOAD : MLX5E_TC_PRIO) - -/* Firmware currently has 4 pool of 4 sizes that it supports (FT_POOLS), - * and a virtual memory region of 16M (MLX5_FT_SIZE), this region is duplicated - * for each flow table pool. We can allocate up to 16M of each pool, - * and we keep track of how much we used via get_next_avail_sz_from_pool. - * Firmware doesn't report any of this for now. - * ESW_POOL is expected to be sorted from large to small and match firmware - * pools. - */ -#define FT_SIZE (16 * 1024 * 1024) -static const unsigned int FT_POOLS[] = { 4 * 1024 * 1024, - 1 * 1024 * 1024, - 64 * 1024, - 128 }; #define FT_TBL_SZ (64 * 1024) struct mlx5_fs_chains { @@ -49,8 +35,6 @@ struct mlx5_fs_chains { enum mlx5_flow_namespace_type ns; u32 group_num; u32 flags; - - int ft_left[ARRAY_SIZE(FT_POOLS)]; }; struct fs_chain { @@ -160,54 +144,6 @@ mlx5_chains_set_end_ft(struct mlx5_fs_chains *chains, tc_end_ft(chains) = ft; } -#define POOL_NEXT_SIZE 0 -static int -mlx5_chains_get_avail_sz_from_pool(struct mlx5_fs_chains *chains, - int desired_size) -{ - int i, found_i = -1; - - for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--) { - if (ft_pool_left(chains)[i] && FT_POOLS[i] > desired_size) { - found_i = i; - if (desired_size != POOL_NEXT_SIZE) - break; - } - } - - if (found_i != -1) { - --ft_pool_left(chains)[found_i]; - return FT_POOLS[found_i]; - } - - return 0; -} - -static void -mlx5_chains_put_sz_to_pool(struct mlx5_fs_chains *chains, int sz) -{ - int i; - - for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--) { - if (sz == FT_POOLS[i]) { - ++ft_pool_left(chains)[i]; - return; - } - } - - WARN_ONCE(1, "Couldn't find size %d in flow table size pool", sz); -} - -static void -mlx5_chains_init_sz_pool(struct mlx5_fs_chains *chains, u32 ft_max) -{ - int i; - - for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--) - ft_pool_left(chains)[i] = - FT_POOLS[i] <= ft_max ? FT_SIZE / FT_POOLS[i] : 0; -} - static struct mlx5_flow_table * mlx5_chains_create_table(struct mlx5_fs_chains *chains, u32 chain, u32 prio, u32 level) @@ -221,11 +157,7 @@ mlx5_chains_create_table(struct mlx5_fs_chains *chains, ft_attr.flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT | MLX5_FLOW_TABLE_TUNNEL_EN_DECAP); - sz = (chain == mlx5_chains_get_nf_ft_chain(chains)) ? - mlx5_chains_get_avail_sz_from_pool(chains, FT_TBL_SZ) : - mlx5_chains_get_avail_sz_from_pool(chains, POOL_NEXT_SIZE); - if (!sz) - return ERR_PTR(-ENOSPC); + sz = (chain == mlx5_chains_get_nf_ft_chain(chains)) ? FT_TBL_SZ : POOL_NEXT_SIZE; ft_attr.max_fte = sz; /* We use tc_default_ft(chains) as the table's next_ft till @@ -266,21 +198,12 @@ mlx5_chains_create_table(struct mlx5_fs_chains *chains, if (IS_ERR(ft)) { mlx5_core_warn(chains->dev, "Failed to create chains table err %d (chain: %d, prio: %d, level: %d, size: %d)\n", (int)PTR_ERR(ft), chain, prio, level, sz); - mlx5_chains_put_sz_to_pool(chains, sz); return ft; } return ft; } -static void -mlx5_chains_destroy_table(struct mlx5_fs_chains *chains, - struct mlx5_flow_table *ft) -{ - mlx5_chains_put_sz_to_pool(chains, ft->max_fte); - mlx5_destroy_flow_table(ft); -} - static int create_chain_restore(struct fs_chain *chain) { @@ -637,7 +560,7 @@ err_insert: err_miss_rule: mlx5_destroy_flow_group(miss_group); err_group: - mlx5_chains_destroy_table(chains, ft); + mlx5_destroy_flow_table(ft); err_create: err_alloc: kvfree(prio_s); @@ -660,7 +583,7 @@ mlx5_chains_destroy_prio(struct mlx5_fs_chains *chains, prio_params); mlx5_del_flow_rules(prio->miss_rule); mlx5_destroy_flow_group(prio->miss_group); - mlx5_chains_destroy_table(chains, prio->ft); + mlx5_destroy_flow_table(prio->ft); mlx5_chains_put_chain(chain); kvfree(prio); } @@ -785,7 +708,7 @@ void mlx5_chains_destroy_global_table(struct mlx5_fs_chains *chains, struct mlx5_flow_table *ft) { - mlx5_chains_destroy_table(chains, ft); + mlx5_destroy_flow_table(ft); } static struct mlx5_fs_chains * @@ -817,8 +740,6 @@ mlx5_chains_init(struct mlx5_core_dev *dev, struct mlx5_chains_attr *attr) mlx5_chains_get_chain_range(chains_priv), mlx5_chains_get_prio_range(chains_priv)); - mlx5_chains_init_sz_pool(chains_priv, attr->max_ft_sz); - err = rhashtable_init(&chains_ht(chains_priv), &chain_params); if (err) goto init_chains_ht_err; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f8e8d7e90616..6a7749c21b82 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -550,6 +550,7 @@ struct mlx5_adev { int idx; }; +struct mlx5_ft_pool; struct mlx5_priv { /* IRQ table valid only for real pci devices PF or VF */ struct mlx5_irq_table *irq_table; @@ -602,6 +603,7 @@ struct mlx5_priv { struct mlx5_core_roce roce; struct mlx5_fc_stats fc_stats; struct mlx5_rl_table rl_table; + struct mlx5_ft_pool *ft_pool; struct mlx5_bfreg_data bfregs; struct mlx5_uars_page *uar; -- cgit v1.2.3-71-gd317 From 586d5a8bcede47fda7bebf4b36be917c5010db16 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 28 May 2021 12:30:03 +0200 Subject: netfilter: x_tables: reduce xt_action_param by 8 byte The fragment offset in ipv4/ipv6 is a 16bit field, so use u16 instead of unsigned int. On 64bit: 40 bytes to 32 bytes. By extension this also reduces nft_pktinfo (56 to 48 byte). Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/x_tables.h | 2 +- net/ipv6/netfilter/ip6_tables.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 07c6ad8f2a02..28d7027cd460 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -36,8 +36,8 @@ struct xt_action_param { const void *matchinfo, *targinfo; }; const struct nf_hook_state *state; - int fragoff; unsigned int thoff; + u16 fragoff; bool hotdrop; }; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index e810a23baf99..de2cf3943b91 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -51,7 +51,7 @@ ip6_packet_match(const struct sk_buff *skb, const char *outdev, const struct ip6t_ip6 *ip6info, unsigned int *protoff, - int *fragoff, bool *hotdrop) + u16 *fragoff, bool *hotdrop) { unsigned long ret; const struct ipv6hdr *ipv6 = ipv6_hdr(skb); -- cgit v1.2.3-71-gd317 From 6802db48fc27b8d7f601e96a85771f2205702941 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 28 May 2021 12:30:04 +0200 Subject: netfilter: reduce size of nf_hook_state on 32bit platforms Reduce size from 28 to 24 bytes on 32bit platforms. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index f0f3a8354c3c..f161569fbe2f 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -65,8 +65,8 @@ struct nf_hook_ops; struct sock; struct nf_hook_state { - unsigned int hook; - u_int8_t pf; + u8 hook; + u8 pf; struct net_device *in; struct net_device *out; struct sock *sk; -- cgit v1.2.3-71-gd317 From e860fa9b69e1bf077ba4725ee4be7b9443a3682a Mon Sep 17 00:00:00 2001 From: Dave Ertman Date: Thu, 20 May 2021 09:37:48 -0500 Subject: iidc: Introduce iidc.h Introduce a shared header file used by the 'ice' Intel networking driver providing RDMA support and the 'irdma' driver to provide a private interface. Signed-off-by: Dave Ertman Signed-off-by: Shiraz Saleem Signed-off-by: Tony Nguyen --- MAINTAINERS | 1 + include/linux/net/intel/iidc.h | 100 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 101 insertions(+) create mode 100644 include/linux/net/intel/iidc.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index bd7aff0c120f..34d2bf36b5ad 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9130,6 +9130,7 @@ F: Documentation/networking/device_drivers/ethernet/intel/ F: drivers/net/ethernet/intel/ F: drivers/net/ethernet/intel/*/ F: include/linux/avf/virtchnl.h +F: include/linux/net/intel/iidc.h INTEL FRAMEBUFFER DRIVER (excluding 810 and 815) M: Maik Broemme diff --git a/include/linux/net/intel/iidc.h b/include/linux/net/intel/iidc.h new file mode 100644 index 000000000000..e32f6712aee0 --- /dev/null +++ b/include/linux/net/intel/iidc.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2021, Intel Corporation. */ + +#ifndef _IIDC_H_ +#define _IIDC_H_ + +#include +#include +#include +#include +#include +#include + +enum iidc_event_type { + IIDC_EVENT_BEFORE_MTU_CHANGE, + IIDC_EVENT_AFTER_MTU_CHANGE, + IIDC_EVENT_BEFORE_TC_CHANGE, + IIDC_EVENT_AFTER_TC_CHANGE, + IIDC_EVENT_CRIT_ERR, + IIDC_EVENT_NBITS /* must be last */ +}; + +enum iidc_reset_type { + IIDC_PFR, + IIDC_CORER, + IIDC_GLOBR, +}; + +#define IIDC_MAX_USER_PRIORITY 8 + +/* Struct to hold per RDMA Qset info */ +struct iidc_rdma_qset_params { + /* Qset TEID returned to the RDMA driver in + * ice_add_rdma_qset and used by RDMA driver + * for calls to ice_del_rdma_qset + */ + u32 teid; /* Qset TEID */ + u16 qs_handle; /* RDMA driver provides this */ + u16 vport_id; /* VSI index */ + u8 tc; /* TC branch the Qset should belong to */ +}; + +struct iidc_qos_info { + u64 tc_ctx; + u8 rel_bw; + u8 prio_type; + u8 egress_virt_up; + u8 ingress_virt_up; +}; + +/* Struct to pass QoS info */ +struct iidc_qos_params { + struct iidc_qos_info tc_info[IEEE_8021QAZ_MAX_TCS]; + u8 up2tc[IIDC_MAX_USER_PRIORITY]; + u8 vport_relative_bw; + u8 vport_priority_type; + u8 num_tc; +}; + +struct iidc_event { + DECLARE_BITMAP(type, IIDC_EVENT_NBITS); + u32 reg; +}; + +struct ice_pf; + +int ice_add_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset); +int ice_del_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset); +int ice_rdma_request_reset(struct ice_pf *pf, enum iidc_reset_type reset_type); +int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable); +void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos); + +#define IIDC_RDMA_ROCE_NAME "roce" + +/* Structure representing auxiliary driver tailored information about the core + * PCI dev, each auxiliary driver using the IIDC interface will have an + * instance of this struct dedicated to it. + */ + +struct iidc_auxiliary_dev { + struct auxiliary_device adev; + struct ice_pf *pf; +}; + +/* structure representing the auxiliary driver. This struct is to be + * allocated and populated by the auxiliary driver's owner. The core PCI + * driver will access these ops by performing a container_of on the + * auxiliary_device->dev.driver. + */ +struct iidc_auxiliary_drv { + struct auxiliary_driver adrv; + /* This event_handler is meant to be a blocking call. For instance, + * when a BEFORE_MTU_CHANGE event comes in, the event_handler will not + * return until the auxiliary driver is ready for the MTU change to + * happen. + */ + void (*event_handler)(struct ice_pf *pf, struct iidc_event *event); +}; + +#endif /* _IIDC_H_*/ -- cgit v1.2.3-71-gd317 From 9ed7533121219cb25408888cf7fbb929cedc033c Mon Sep 17 00:00:00 2001 From: Shiraz Saleem Date: Fri, 21 May 2021 10:10:59 -0700 Subject: i40e: Prep i40e header for aux bus conversion Add the definitions to the i40e client header file in preparation to convert i40e to use the new auxiliary bus infrastructure. This header is shared between the 'i40e' Intel networking driver providing RDMA support and the 'irdma' driver. Signed-off-by: Shiraz Saleem Signed-off-by: Tony Nguyen --- include/linux/net/intel/i40e_client.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/net/intel/i40e_client.h b/include/linux/net/intel/i40e_client.h index fd7bc860a241..41f24b5241ab 100644 --- a/include/linux/net/intel/i40e_client.h +++ b/include/linux/net/intel/i40e_client.h @@ -4,6 +4,8 @@ #ifndef _I40E_CLIENT_H_ #define _I40E_CLIENT_H_ +#include + #define I40E_CLIENT_STR_LENGTH 10 /* Client interface version should be updated anytime there is a change in the @@ -78,6 +80,7 @@ struct i40e_info { u8 lanmac[6]; struct net_device *netdev; struct pci_dev *pcidev; + struct auxiliary_device *aux_dev; u8 __iomem *hw_addr; u8 fid; /* function id, PF id or VF id */ #define I40E_CLIENT_FTYPE_PF 0 @@ -100,6 +103,11 @@ struct i40e_info { u32 fw_build; /* firmware build number */ }; +struct i40e_auxiliary_device { + struct auxiliary_device aux_dev; + struct i40e_info *ldev; +}; + #define I40E_CLIENT_RESET_LEVEL_PF 1 #define I40E_CLIENT_RESET_LEVEL_CORE 2 #define I40E_CLIENT_VSI_FLAG_TCP_ENABLE BIT(1) @@ -187,6 +195,8 @@ static inline bool i40e_client_is_registered(struct i40e_client *client) return test_bit(__I40E_CLIENT_REGISTERED, &client->state); } +void i40e_client_device_register(struct i40e_info *ldev, struct i40e_client *client); +void i40e_client_device_unregister(struct i40e_info *ldev); /* used by clients */ int i40e_register_client(struct i40e_client *client); int i40e_unregister_client(struct i40e_client *client); -- cgit v1.2.3-71-gd317 From 5ac712dcdfefb1a783384db85e0507d161e87812 Mon Sep 17 00:00:00 2001 From: Wong Vee Khee Date: Tue, 1 Jun 2021 21:52:35 +0800 Subject: net: stmmac: enable platform specific safety features On Intel platforms, not all safety features are enabled on the hardware. The current implementation enable all safety features by default. This will cause mass error and warning printouts after the module is loaded. Introduce platform specific safety features flag to enable or disable each safety features. Signed-off-by: Wong Vee Khee Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 26 +++++++++++++++++++ drivers/net/ethernet/stmicro/stmmac/dwmac5.c | 30 ++++++++++++++-------- drivers/net/ethernet/stmicro/stmmac/dwmac5.h | 3 ++- .../net/ethernet/stmicro/stmmac/dwxgmac2_core.c | 4 ++- drivers/net/ethernet/stmicro/stmmac/hwif.h | 3 ++- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 ++- drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c | 16 ++++++++++++ include/linux/stmmac.h | 13 ++++++++++ 8 files changed, 84 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index e36a8cc59ad0..2ecf93c84b9d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -568,6 +568,16 @@ static int ehl_common_data(struct pci_dev *pdev, plat->tx_queues_to_use = 8; plat->clk_ptp_rate = 200000000; + plat->safety_feat_cfg->tsoee = 1; + plat->safety_feat_cfg->mrxpee = 1; + plat->safety_feat_cfg->mestee = 1; + plat->safety_feat_cfg->mrxee = 1; + plat->safety_feat_cfg->mtxee = 1; + plat->safety_feat_cfg->epsi = 0; + plat->safety_feat_cfg->edpp = 0; + plat->safety_feat_cfg->prtyen = 0; + plat->safety_feat_cfg->tmouten = 0; + return intel_mgbe_common_data(pdev, plat); } @@ -683,6 +693,16 @@ static int tgl_common_data(struct pci_dev *pdev, plat->tx_queues_to_use = 4; plat->clk_ptp_rate = 200000000; + plat->safety_feat_cfg->tsoee = 1; + plat->safety_feat_cfg->mrxpee = 0; + plat->safety_feat_cfg->mestee = 1; + plat->safety_feat_cfg->mrxee = 1; + plat->safety_feat_cfg->mtxee = 1; + plat->safety_feat_cfg->epsi = 0; + plat->safety_feat_cfg->edpp = 0; + plat->safety_feat_cfg->prtyen = 0; + plat->safety_feat_cfg->tmouten = 0; + return intel_mgbe_common_data(pdev, plat); } @@ -959,6 +979,12 @@ static int intel_eth_pci_probe(struct pci_dev *pdev, if (!plat->dma_cfg) return -ENOMEM; + plat->safety_feat_cfg = devm_kzalloc(&pdev->dev, + sizeof(*plat->safety_feat_cfg), + GFP_KERNEL); + if (!plat->safety_feat_cfg) + return -ENOMEM; + /* Enable pci device */ ret = pcim_enable_device(pdev); if (ret) { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c index d8c6ff725237..9c2d40f853ed 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c @@ -183,7 +183,8 @@ static void dwmac5_handle_dma_err(struct net_device *ndev, STAT_OFF(dma_errors), stats); } -int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp) +int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp, + struct stmmac_safety_feature_cfg *safety_feat_cfg) { u32 value; @@ -193,11 +194,16 @@ int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp) /* 1. Enable Safety Features */ value = readl(ioaddr + MTL_ECC_CONTROL); value |= MEEAO; /* MTL ECC Error Addr Status Override */ - value |= TSOEE; /* TSO ECC */ - value |= MRXPEE; /* MTL RX Parser ECC */ - value |= MESTEE; /* MTL EST ECC */ - value |= MRXEE; /* MTL RX FIFO ECC */ - value |= MTXEE; /* MTL TX FIFO ECC */ + if (safety_feat_cfg->tsoee) + value |= TSOEE; /* TSO ECC */ + if (safety_feat_cfg->mrxpee) + value |= MRXPEE; /* MTL RX Parser ECC */ + if (safety_feat_cfg->mestee) + value |= MESTEE; /* MTL EST ECC */ + if (safety_feat_cfg->mrxee) + value |= MRXEE; /* MTL RX FIFO ECC */ + if (safety_feat_cfg->mtxee) + value |= MTXEE; /* MTL TX FIFO ECC */ writel(value, ioaddr + MTL_ECC_CONTROL); /* 2. Enable MTL Safety Interrupts */ @@ -219,13 +225,16 @@ int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp) /* 5. Enable Parity and Timeout for FSM */ value = readl(ioaddr + MAC_FSM_CONTROL); - value |= PRTYEN; /* FSM Parity Feature */ - value |= TMOUTEN; /* FSM Timeout Feature */ + if (safety_feat_cfg->prtyen) + value |= PRTYEN; /* FSM Parity Feature */ + if (safety_feat_cfg->tmouten) + value |= TMOUTEN; /* FSM Timeout Feature */ writel(value, ioaddr + MAC_FSM_CONTROL); /* 4. Enable Data Parity Protection */ value = readl(ioaddr + MTL_DPP_CONTROL); - value |= EDPP; + if (safety_feat_cfg->edpp) + value |= EDPP; writel(value, ioaddr + MTL_DPP_CONTROL); /* @@ -235,7 +244,8 @@ int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp) if (asp <= 0x2) return 0; - value |= EPSI; + if (safety_feat_cfg->epsi) + value |= EPSI; writel(value, ioaddr + MTL_DPP_CONTROL); return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h index 6b2fd37b29ad..53c138d0ff48 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h @@ -137,7 +137,8 @@ #define GMAC_INT_FPE_EN BIT(17) -int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp); +int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp, + struct stmmac_safety_feature_cfg *safety_cfg); int dwmac5_safety_feat_irq_status(struct net_device *ndev, void __iomem *ioaddr, unsigned int asp, struct stmmac_safety_stats *stats); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index ad4df9bddcf3..c4d78fa93663 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -801,7 +801,9 @@ static void dwxgmac3_handle_dma_err(struct net_device *ndev, dwxgmac3_dma_errors, STAT_OFF(dma_errors), stats); } -static int dwxgmac3_safety_feat_config(void __iomem *ioaddr, unsigned int asp) +static int +dwxgmac3_safety_feat_config(void __iomem *ioaddr, unsigned int asp, + struct stmmac_safety_feature_cfg *safety_cfg) { u32 value; diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index 75a8b90c202a..dbafedb24290 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -348,7 +348,8 @@ struct stmmac_ops { void (*pcs_rane)(void __iomem *ioaddr, bool restart); void (*pcs_get_adv_lp)(void __iomem *ioaddr, struct rgmii_adv *adv); /* Safety Features */ - int (*safety_feat_config)(void __iomem *ioaddr, unsigned int asp); + int (*safety_feat_config)(void __iomem *ioaddr, unsigned int asp, + struct stmmac_safety_feature_cfg *safety_cfg); int (*safety_feat_irq_status)(struct net_device *ndev, void __iomem *ioaddr, unsigned int asp, struct stmmac_safety_stats *stats); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 9962a1041d35..13720bf6f6ff 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3172,7 +3172,8 @@ static void stmmac_safety_feat_configuration(struct stmmac_priv *priv) { if (priv->dma_cap.asp) { netdev_info(priv->dev, "Enabling Safety Features\n"); - stmmac_safety_feat_config(priv, priv->ioaddr, priv->dma_cap.asp); + stmmac_safety_feat_config(priv, priv->ioaddr, priv->dma_cap.asp, + priv->plat->safety_feat_cfg); } else { netdev_info(priv->dev, "No Safety Features support found\n"); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index 95e0e4d6f74d..fcf17d8a0494 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -174,6 +174,12 @@ static int stmmac_pci_probe(struct pci_dev *pdev, if (!plat->dma_cfg) return -ENOMEM; + plat->safety_feat_cfg = devm_kzalloc(&pdev->dev, + sizeof(*plat->safety_feat_cfg), + GFP_KERNEL); + if (!plat->safety_feat_cfg) + return -ENOMEM; + /* Enable pci device */ ret = pci_enable_device(pdev); if (ret) { @@ -203,6 +209,16 @@ static int stmmac_pci_probe(struct pci_dev *pdev, res.wol_irq = pdev->irq; res.irq = pdev->irq; + plat->safety_feat_cfg->tsoee = 1; + plat->safety_feat_cfg->mrxpee = 1; + plat->safety_feat_cfg->mestee = 1; + plat->safety_feat_cfg->mrxee = 1; + plat->safety_feat_cfg->mtxee = 1; + plat->safety_feat_cfg->epsi = 1; + plat->safety_feat_cfg->edpp = 1; + plat->safety_feat_cfg->prtyen = 1; + plat->safety_feat_cfg->tmouten = 1; + return stmmac_dvr_probe(&pdev->dev, plat, &res); } diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index e14a12df381b..e55a4807e3ea 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -172,6 +172,18 @@ struct stmmac_fpe_cfg { enum stmmac_fpe_state lo_fpe_state; /* Local station FPE state */ }; +struct stmmac_safety_feature_cfg { + u32 tsoee; + u32 mrxpee; + u32 mestee; + u32 mrxee; + u32 mtxee; + u32 epsi; + u32 edpp; + u32 prtyen; + u32 tmouten; +}; + struct plat_stmmacenet_data { int bus_id; int phy_addr; @@ -184,6 +196,7 @@ struct plat_stmmacenet_data { struct stmmac_dma_cfg *dma_cfg; struct stmmac_est *est; struct stmmac_fpe_cfg *fpe_cfg; + struct stmmac_safety_feature_cfg *safety_feat_cfg; int clk_csr; int has_gmac; int enh_desc; -- cgit v1.2.3-71-gd317 From e1d9a90a9bfdb0735062d3adb16b07314b4b7b01 Mon Sep 17 00:00:00 2001 From: Sharath Chandra Vurukala Date: Wed, 2 Jun 2021 00:58:35 +0530 Subject: net: ethernet: rmnet: Support for ingress MAPv5 checksum offload Adding support for processing of MAPv5 downlink packets. It involves parsing the Mapv5 packet and checking the csum header to know whether the hardware has validated the checksum and is valid or not. Based on the checksum valid bit the corresponding stats are incremented and skb->ip_summed is marked either CHECKSUM_UNNECESSARY or left as CHEKSUM_NONE to let network stack revalidate the checksum and update the respective snmp stats. Current MAPV1 header has been modified, the reserved field in the Mapv1 header is now used for next header indication. Signed-off-by: Sharath Chandra Vurukala Signed-off-by: David S. Miller --- .../net/ethernet/qualcomm/rmnet/rmnet_handlers.c | 17 ++++--- drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h | 3 +- .../net/ethernet/qualcomm/rmnet/rmnet_map_data.c | 57 +++++++++++++++++++++- include/linux/if_rmnet.h | 30 ++++++++++-- include/uapi/linux/if_link.h | 1 + 5 files changed, 96 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c index 0be5ac7ab261..706a225075a3 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/* Copyright (c) 2013-2018, The Linux Foundation. All rights reserved. +/* Copyright (c) 2013-2018, 2021, The Linux Foundation. All rights reserved. * * RMNET Data ingress/egress handler */ @@ -82,11 +82,16 @@ __rmnet_map_ingress_handler(struct sk_buff *skb, skb->dev = ep->egress_dev; - /* Subtract MAP header */ - skb_pull(skb, sizeof(struct rmnet_map_header)); - rmnet_set_skb_proto(skb); - - if (port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV4) { + if ((port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV5) && + (map_header->flags & MAP_NEXT_HEADER_FLAG)) { + if (rmnet_map_process_next_hdr_packet(skb, len)) + goto free_skb; + skb_pull(skb, sizeof(*map_header)); + rmnet_set_skb_proto(skb); + } else if (port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV4) { + /* Subtract MAP header */ + skb_pull(skb, sizeof(*map_header)); + rmnet_set_skb_proto(skb); if (!rmnet_map_checksum_downlink_packet(skb, len + pad)) skb->ip_summed = CHECKSUM_UNNECESSARY; } diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h index 2aea153f4247..1a399bfa07d2 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ -/* Copyright (c) 2013-2018, The Linux Foundation. All rights reserved. +/* Copyright (c) 2013-2018, 2021, The Linux Foundation. All rights reserved. */ #ifndef _RMNET_MAP_H_ @@ -48,5 +48,6 @@ void rmnet_map_command(struct sk_buff *skb, struct rmnet_port *port); int rmnet_map_checksum_downlink_packet(struct sk_buff *skb, u16 len); void rmnet_map_checksum_uplink_packet(struct sk_buff *skb, struct net_device *orig_dev); +int rmnet_map_process_next_hdr_packet(struct sk_buff *skb, u16 len); #endif /* _RMNET_MAP_H_ */ diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c index 0ac2ff828320..5c018bd64689 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/* Copyright (c) 2013-2018, The Linux Foundation. All rights reserved. +/* Copyright (c) 2013-2018, 2021, The Linux Foundation. All rights reserved. * * RMNET Data MAP protocol */ @@ -8,6 +8,7 @@ #include #include #include +#include #include "rmnet_config.h" #include "rmnet_map.h" #include "rmnet_private.h" @@ -300,8 +301,11 @@ done: struct sk_buff *rmnet_map_deaggregate(struct sk_buff *skb, struct rmnet_port *port) { + struct rmnet_map_v5_csum_header *next_hdr = NULL; struct rmnet_map_header *maph; + void *data = skb->data; struct sk_buff *skbn; + u8 nexthdr_type; u32 packet_len; if (skb->len == 0) @@ -310,8 +314,18 @@ struct sk_buff *rmnet_map_deaggregate(struct sk_buff *skb, maph = (struct rmnet_map_header *)skb->data; packet_len = ntohs(maph->pkt_len) + sizeof(*maph); - if (port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV4) + if (port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV4) { packet_len += sizeof(struct rmnet_map_dl_csum_trailer); + } else if (port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV5) { + if (!(maph->flags & MAP_CMD_FLAG)) { + packet_len += sizeof(*next_hdr); + if (maph->flags & MAP_NEXT_HEADER_FLAG) + next_hdr = data + sizeof(*maph); + else + /* Mapv5 data pkt without csum hdr is invalid */ + return NULL; + } + } if (((int)skb->len - (int)packet_len) < 0) return NULL; @@ -320,6 +334,13 @@ struct sk_buff *rmnet_map_deaggregate(struct sk_buff *skb, if (!maph->pkt_len) return NULL; + if (next_hdr) { + nexthdr_type = u8_get_bits(next_hdr->header_info, + MAPV5_HDRINFO_HDR_TYPE_FMASK); + if (nexthdr_type != RMNET_MAP_HEADER_TYPE_CSUM_OFFLOAD) + return NULL; + } + skbn = alloc_skb(packet_len + RMNET_MAP_DEAGGR_SPACING, GFP_ATOMIC); if (!skbn) return NULL; @@ -414,3 +435,35 @@ sw_csum: priv->stats.csum_sw++; } + +/* Process a MAPv5 packet header */ +int rmnet_map_process_next_hdr_packet(struct sk_buff *skb, + u16 len) +{ + struct rmnet_priv *priv = netdev_priv(skb->dev); + struct rmnet_map_v5_csum_header *next_hdr; + u8 nexthdr_type; + + next_hdr = (struct rmnet_map_v5_csum_header *)(skb->data + + sizeof(struct rmnet_map_header)); + + nexthdr_type = u8_get_bits(next_hdr->header_info, + MAPV5_HDRINFO_HDR_TYPE_FMASK); + + if (nexthdr_type != RMNET_MAP_HEADER_TYPE_CSUM_OFFLOAD) + return -EINVAL; + + if (unlikely(!(skb->dev->features & NETIF_F_RXCSUM))) { + priv->stats.csum_sw++; + } else if (next_hdr->csum_info & MAPV5_CSUMINFO_VALID_FLAG) { + priv->stats.csum_ok++; + skb->ip_summed = CHECKSUM_UNNECESSARY; + } else { + priv->stats.csum_valid_unset++; + } + + /* Pull csum v5 header */ + skb_pull(skb, sizeof(*next_hdr)); + + return 0; +} diff --git a/include/linux/if_rmnet.h b/include/linux/if_rmnet.h index 4efb537f57f3..be17610a981e 100644 --- a/include/linux/if_rmnet.h +++ b/include/linux/if_rmnet.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only - * Copyright (c) 2013-2019, The Linux Foundation. All rights reserved. + * Copyright (c) 2013-2019, 2021 The Linux Foundation. All rights reserved. */ #ifndef _LINUX_IF_RMNET_H_ @@ -12,10 +12,12 @@ struct rmnet_map_header { } __aligned(1); /* rmnet_map_header flags field: - * PAD_LEN: number of pad bytes following packet data - * CMD: 1 = packet contains a MAP command; 0 = packet contains data + * PAD_LEN: number of pad bytes following packet data + * CMD: 1 = packet contains a MAP command; 0 = packet contains data + * NEXT_HEADER: 1 = packet contains V5 CSUM header 0 = no V5 CSUM header */ #define MAP_PAD_LEN_MASK GENMASK(5, 0) +#define MAP_NEXT_HEADER_FLAG BIT(6) #define MAP_CMD_FLAG BIT(7) struct rmnet_map_dl_csum_trailer { @@ -45,4 +47,26 @@ struct rmnet_map_ul_csum_header { #define MAP_CSUM_UL_UDP_FLAG BIT(14) #define MAP_CSUM_UL_ENABLED_FLAG BIT(15) +/* MAP CSUM headers */ +struct rmnet_map_v5_csum_header { + u8 header_info; + u8 csum_info; + __be16 reserved; +} __aligned(1); + +/* v5 header_info field + * NEXT_HEADER: represents whether there is any next header + * HEADER_TYPE: represents the type of this header + * + * csum_info field + * CSUM_VALID_OR_REQ: + * 1 = for UL, checksum computation is requested. + * 1 = for DL, validated the checksum and has found it valid + */ + +#define MAPV5_HDRINFO_NXT_HDR_FLAG BIT(0) +#define MAPV5_HDRINFO_HDR_TYPE_FMASK GENMASK(7, 1) +#define MAPV5_CSUMINFO_VALID_FLAG BIT(7) + +#define RMNET_MAP_HEADER_TYPE_CSUM_OFFLOAD 2 #endif /* !(_LINUX_IF_RMNET_H_) */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index cd5b382a4138..1f753dcd85e1 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1236,6 +1236,7 @@ enum { #define RMNET_FLAGS_INGRESS_MAP_COMMANDS (1U << 1) #define RMNET_FLAGS_INGRESS_MAP_CKSUMV4 (1U << 2) #define RMNET_FLAGS_EGRESS_MAP_CKSUMV4 (1U << 3) +#define RMNET_FLAGS_INGRESS_MAP_CKSUMV5 (1U << 4) enum { IFLA_RMNET_UNSPEC, -- cgit v1.2.3-71-gd317 From 490dcecabbf93e705006af498fa6815251404a54 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 19 May 2021 10:18:25 -0700 Subject: mlx5: count all link events mlx5 devices were observed generating MLX5_PORT_CHANGE_SUBTYPE_ACTIVE events without an intervening MLX5_PORT_CHANGE_SUBTYPE_DOWN. This breaks link flap detection based on Linux carrier state transition count as netif_carrier_on() does nothing if carrier is already on. Make sure we count such events. netif_carrier_event() increments the counters and fires the linkwatch events. The latter is not necessary for the use case but seems like the right thing to do. Signed-off-by: Jakub Kicinski Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 6 +++++- include/linux/netdevice.h | 2 +- net/sched/sch_generic.c | 18 ++++++++++++++++++ 3 files changed, 24 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index ad0f69480b9c..e36d0c6a08db 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -91,12 +91,16 @@ void mlx5e_update_carrier(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; u8 port_state; + bool up; port_state = mlx5_query_vport_state(mdev, MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT, 0); - if (port_state == VPORT_STATE_UP) { + up = port_state == VPORT_STATE_UP; + if (up == netif_carrier_ok(priv->netdev)) + netif_carrier_event(priv->netdev); + if (up) { netdev_info(priv->netdev, "Link up\n"); netif_carrier_on(priv->netdev); } else { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5cbc950b34df..be1dcceda5e4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4187,8 +4187,8 @@ unsigned long dev_trans_start(struct net_device *dev); void __netdev_watchdog_up(struct net_device *dev); void netif_carrier_on(struct net_device *dev); - void netif_carrier_off(struct net_device *dev); +void netif_carrier_event(struct net_device *dev); /** * netif_dormant_on - mark device as dormant. diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index fc8b56bcabf3..e9c0afc8becc 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -540,6 +540,24 @@ void netif_carrier_off(struct net_device *dev) } EXPORT_SYMBOL(netif_carrier_off); +/** + * netif_carrier_event - report carrier state event + * @dev: network device + * + * Device has detected a carrier event but the carrier state wasn't changed. + * Use in drivers when querying carrier state asynchronously, to avoid missing + * events (link flaps) if link recovers before it's queried. + */ +void netif_carrier_event(struct net_device *dev) +{ + if (dev->reg_state == NETREG_UNINITIALIZED) + return; + atomic_inc(&dev->carrier_up_count); + atomic_inc(&dev->carrier_down_count); + linkwatch_fire_event(dev); +} +EXPORT_SYMBOL_GPL(netif_carrier_event); + /* "NOOP" scheduler: the best scheduler, recommended for all interfaces under all circumstances. It is difficult to invent anything faster or cheaper. -- cgit v1.2.3-71-gd317 From b81017aeee4eb9159296cdb68889932649317b9b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 2 Jun 2021 19:20:11 +0300 Subject: net: pcs: xpcs: delete shim definition for mdio_xpcs_get_ops() CONFIG_STMMAC_ETH selects CONFIG_PCS_XPCS, so there should be no situation where the shim should be needed. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/pcs/pcs-xpcs.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 5938ced805f4..c4d0a2c469c7 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -36,13 +36,6 @@ struct mdio_xpcs_ops { int enable); }; -#if IS_ENABLED(CONFIG_PCS_XPCS) struct mdio_xpcs_ops *mdio_xpcs_get_ops(void); -#else -static inline struct mdio_xpcs_ops *mdio_xpcs_get_ops(void) -{ - return NULL; -} -#endif #endif /* __LINUX_PCS_XPCS_H */ -- cgit v1.2.3-71-gd317 From 9900074ecccec472c9d89929c3d37c235f45d33a Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 2 Jun 2021 19:20:13 +0300 Subject: net: pcs: xpcs: make the checks related to the PHY interface mode stateless The operating mode of the driver is currently to populate its struct mdio_xpcs_args::supported and struct mdio_xpcs_args::an_mode statically in xpcs_probe(), based on the passed phy_interface_t, and work with those. However this is not the operation that phylink expects from a PCS driver, because the port might be attached to an SFP cage that triggers changes of the phy_interface_t dynamically as one SFP module is unpluggged and another is plugged. To migrate towards that model, the struct mdio_xpcs_args should not cache anything related to the phy_interface_t, but just look up the statically defined, const struct xpcs_compat structure corresponding to the detected PCS OUI/model number. So we delete the "supported" and "an_mode" members of struct mdio_xpcs_args, and add the "id" structure there (since the ID is not expected to change at runtime). Since xpcs->supported is used deep in the code in _xpcs_config_aneg_c73(), we need to modify some function headers to pass the xpcs_compat from all callers. In turn, the xpcs_compat is always supplied externally to the xpcs module: - Most of the time by phylink - In xpcs_probe() it is needed because xpcs_soft_reset() writes to MDIO_MMD_PCS or to MDIO_MMD_VEND2 depending on whether an_mode is clause 37 or clause 73. In order to not introduce functional changes related to when the soft reset is issued, we continue to require the initial phy_interface_t argument to be passed to xpcs_probe() so we can pass this on to xpcs_soft_reset(). - stmmac_open() wants to know whether to call stmmac_init_phy() or not, and for that it looks inside xpcs->an_mode, because the clause 73 (backplane) AN modes supposedly do not have a PHY. Because we moved an_mode outside of struct mdio_xpcs_args, this is now no longer directly possible, so we introduce a helper function xpcs_get_an_mode() which protects the data encapsulation of the xpcs module and requires a phy_interface_t to be passed as argument. This function can look up the appropriate compat based on the phy_interface_t. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 +- drivers/net/pcs/pcs-xpcs.c | 175 ++++++++++++++-------- include/linux/pcs/pcs-xpcs.h | 6 +- 3 files changed, 120 insertions(+), 65 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 13720bf6f6ff..c96a89fa4e3c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3638,6 +3638,7 @@ static int stmmac_request_irq(struct net_device *dev) int stmmac_open(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); + int mode = priv->plat->phy_interface; int bfsize = 0; u32 chan; int ret; @@ -3650,7 +3651,8 @@ int stmmac_open(struct net_device *dev) if (priv->hw->pcs != STMMAC_PCS_TBI && priv->hw->pcs != STMMAC_PCS_RTBI && - priv->hw->xpcs_args.an_mode != DW_AN_C73) { + (!priv->hw->xpcs || + xpcs_get_an_mode(&priv->hw->xpcs_args, mode) != DW_AN_C73)) { ret = stmmac_init_phy(dev); if (ret) { netdev_err(priv->dev, diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 9f2da9e873c4..610073cb55d0 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -195,6 +195,49 @@ struct xpcs_id { const struct xpcs_compat *compat; }; +static const struct xpcs_compat *xpcs_find_compat(const struct xpcs_id *id, + phy_interface_t interface) +{ + int i, j; + + for (i = 0; i < DW_XPCS_INTERFACE_MAX; i++) { + const struct xpcs_compat *compat = &id->compat[i]; + + for (j = 0; j < compat->num_interfaces; j++) + if (compat->interface[j] == interface) + return compat; + } + + return NULL; +} + +int xpcs_get_an_mode(struct mdio_xpcs_args *xpcs, phy_interface_t interface) +{ + const struct xpcs_compat *compat; + + compat = xpcs_find_compat(xpcs->id, interface); + if (!compat) + return -ENODEV; + + return compat->an_mode; +} +EXPORT_SYMBOL_GPL(xpcs_get_an_mode); + +static bool __xpcs_linkmode_supported(const struct xpcs_compat *compat, + enum ethtool_link_mode_bit_indices linkmode) +{ + int i; + + for (i = 0; compat->supported[i] != __ETHTOOL_LINK_MODE_MASK_NBITS; i++) + if (compat->supported[i] == linkmode) + return true; + + return false; +} + +#define xpcs_linkmode_supported(compat, mode) \ + __xpcs_linkmode_supported(compat, ETHTOOL_LINK_MODE_ ## mode ## _BIT) + static int xpcs_read(struct mdio_xpcs_args *xpcs, int dev, u32 reg) { u32 reg_addr = MII_ADDR_C45 | dev << 16 | reg; @@ -246,11 +289,12 @@ static int xpcs_poll_reset(struct mdio_xpcs_args *xpcs, int dev) return (ret & MDIO_CTRL1_RESET) ? -ETIMEDOUT : 0; } -static int xpcs_soft_reset(struct mdio_xpcs_args *xpcs) +static int xpcs_soft_reset(struct mdio_xpcs_args *xpcs, + const struct xpcs_compat *compat) { int ret, dev; - switch (xpcs->an_mode) { + switch (compat->an_mode) { case DW_AN_C73: dev = MDIO_MMD_PCS; break; @@ -419,7 +463,8 @@ static int xpcs_config_usxgmii(struct mdio_xpcs_args *xpcs, int speed) return xpcs_write_vpcs(xpcs, MDIO_CTRL1, ret | DW_USXGMII_RST); } -static int _xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs) +static int _xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs, + const struct xpcs_compat *compat) { int ret, adv; @@ -431,7 +476,7 @@ static int _xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs) /* SR_AN_ADV3 */ adv = 0; - if (phylink_test(xpcs->supported, 2500baseX_Full)) + if (xpcs_linkmode_supported(compat, 2500baseX_Full)) adv |= DW_C73_2500KX; /* TODO: 5000baseKR */ @@ -442,11 +487,11 @@ static int _xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs) /* SR_AN_ADV2 */ adv = 0; - if (phylink_test(xpcs->supported, 1000baseKX_Full)) + if (xpcs_linkmode_supported(compat, 1000baseKX_Full)) adv |= DW_C73_1000KX; - if (phylink_test(xpcs->supported, 10000baseKX4_Full)) + if (xpcs_linkmode_supported(compat, 10000baseKX4_Full)) adv |= DW_C73_10000KX4; - if (phylink_test(xpcs->supported, 10000baseKR_Full)) + if (xpcs_linkmode_supported(compat, 10000baseKR_Full)) adv |= DW_C73_10000KR; ret = xpcs_write(xpcs, MDIO_MMD_AN, DW_SR_AN_ADV2, adv); @@ -455,19 +500,20 @@ static int _xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs) /* SR_AN_ADV1 */ adv = DW_C73_AN_ADV_SF; - if (phylink_test(xpcs->supported, Pause)) + if (xpcs_linkmode_supported(compat, Pause)) adv |= DW_C73_PAUSE; - if (phylink_test(xpcs->supported, Asym_Pause)) + if (xpcs_linkmode_supported(compat, Asym_Pause)) adv |= DW_C73_ASYM_PAUSE; return xpcs_write(xpcs, MDIO_MMD_AN, DW_SR_AN_ADV1, adv); } -static int xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs) +static int xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs, + const struct xpcs_compat *compat) { int ret; - ret = _xpcs_config_aneg_c73(xpcs); + ret = _xpcs_config_aneg_c73(xpcs, compat); if (ret < 0) return ret; @@ -481,7 +527,8 @@ static int xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs) } static int xpcs_aneg_done_c73(struct mdio_xpcs_args *xpcs, - struct phylink_link_state *state) + struct phylink_link_state *state, + const struct xpcs_compat *compat) { int ret; @@ -496,7 +543,7 @@ static int xpcs_aneg_done_c73(struct mdio_xpcs_args *xpcs, /* Check if Aneg outcome is valid */ if (!(ret & DW_C73_AN_ADV_SF)) { - xpcs_config_aneg_c73(xpcs); + xpcs_config_aneg_c73(xpcs, compat); return 0; } @@ -642,8 +689,31 @@ static int xpcs_validate(struct mdio_xpcs_args *xpcs, unsigned long *supported, struct phylink_link_state *state) { - linkmode_and(supported, supported, xpcs->supported); - linkmode_and(state->advertising, state->advertising, xpcs->supported); + __ETHTOOL_DECLARE_LINK_MODE_MASK(xpcs_supported); + const struct xpcs_compat *compat; + int i; + + /* phylink expects us to report all supported modes with + * PHY_INTERFACE_MODE_NA, just don't limit the supported and + * advertising masks and exit. + */ + if (state->interface == PHY_INTERFACE_MODE_NA) + return 0; + + bitmap_zero(xpcs_supported, __ETHTOOL_LINK_MODE_MASK_NBITS); + + compat = xpcs_find_compat(xpcs->id, state->interface); + + /* Populate the supported link modes for this + * PHY interface type + */ + if (compat) + for (i = 0; compat->supported[i] != __ETHTOOL_LINK_MODE_MASK_NBITS; i++) + set_bit(compat->supported[i], xpcs_supported); + + linkmode_and(supported, supported, xpcs_supported); + linkmode_and(state->advertising, state->advertising, xpcs_supported); + return 0; } @@ -724,12 +794,17 @@ static int xpcs_config_aneg_c37_sgmii(struct mdio_xpcs_args *xpcs) static int xpcs_config(struct mdio_xpcs_args *xpcs, const struct phylink_link_state *state) { + const struct xpcs_compat *compat; int ret; - switch (xpcs->an_mode) { + compat = xpcs_find_compat(xpcs->id, state->interface); + if (!compat) + return -ENODEV; + + switch (compat->an_mode) { case DW_AN_C73: if (state->an_enabled) { - ret = xpcs_config_aneg_c73(xpcs); + ret = xpcs_config_aneg_c73(xpcs, compat); if (ret) return ret; } @@ -747,7 +822,8 @@ static int xpcs_config(struct mdio_xpcs_args *xpcs, } static int xpcs_get_state_c73(struct mdio_xpcs_args *xpcs, - struct phylink_link_state *state) + struct phylink_link_state *state, + const struct xpcs_compat *compat) { int ret; @@ -757,7 +833,7 @@ static int xpcs_get_state_c73(struct mdio_xpcs_args *xpcs, /* ... and then we check the faults. */ ret = xpcs_read_fault_c73(xpcs, state); if (ret) { - ret = xpcs_soft_reset(xpcs); + ret = xpcs_soft_reset(xpcs, compat); if (ret) return ret; @@ -766,7 +842,7 @@ static int xpcs_get_state_c73(struct mdio_xpcs_args *xpcs, return xpcs_config(xpcs, state); } - if (state->an_enabled && xpcs_aneg_done_c73(xpcs, state)) { + if (state->an_enabled && xpcs_aneg_done_c73(xpcs, state, compat)) { state->an_complete = true; xpcs_read_lpa_c73(xpcs, state); xpcs_resolve_lpa_c73(xpcs, state); @@ -823,11 +899,16 @@ static int xpcs_get_state_c37_sgmii(struct mdio_xpcs_args *xpcs, static int xpcs_get_state(struct mdio_xpcs_args *xpcs, struct phylink_link_state *state) { + const struct xpcs_compat *compat; int ret; - switch (xpcs->an_mode) { + compat = xpcs_find_compat(xpcs->id, state->interface); + if (!compat) + return -ENODEV; + + switch (compat->an_mode) { case DW_AN_C73: - ret = xpcs_get_state_c73(xpcs, state); + ret = xpcs_get_state_c73(xpcs, state, compat); if (ret) return ret; break; @@ -890,40 +971,6 @@ static u32 xpcs_get_id(struct mdio_xpcs_args *xpcs) return 0xffffffff; } -static bool xpcs_check_features(struct mdio_xpcs_args *xpcs, - const struct xpcs_id *match, - phy_interface_t interface) -{ - int i, j; - - for (i = 0; i < DW_XPCS_INTERFACE_MAX; i++) { - const struct xpcs_compat *compat = &match->compat[i]; - bool supports_interface = false; - - for (j = 0; j < compat->num_interfaces; j++) { - if (compat->interface[j] == interface) { - supports_interface = true; - break; - } - } - - if (!supports_interface) - continue; - - /* Populate the supported link modes for this - * PHY interface type - */ - for (j = 0; compat->supported[j] != __ETHTOOL_LINK_MODE_MASK_NBITS; j++) - set_bit(compat->supported[j], xpcs->supported); - - xpcs->an_mode = compat->an_mode; - - return true; - } - - return false; -} - static const struct xpcs_compat synopsys_xpcs_compat[DW_XPCS_INTERFACE_MAX] = { [DW_XPCS_USXGMII] = { .supported = xpcs_usxgmii_features, @@ -961,19 +1008,23 @@ static const struct xpcs_id xpcs_id_list[] = { static int xpcs_probe(struct mdio_xpcs_args *xpcs, phy_interface_t interface) { - const struct xpcs_id *match = NULL; u32 xpcs_id = xpcs_get_id(xpcs); int i; for (i = 0; i < ARRAY_SIZE(xpcs_id_list); i++) { const struct xpcs_id *entry = &xpcs_id_list[i]; + const struct xpcs_compat *compat; - if ((xpcs_id & entry->mask) == entry->id) { - match = entry; + if ((xpcs_id & entry->mask) != entry->id) + continue; - if (xpcs_check_features(xpcs, match, interface)) - return xpcs_soft_reset(xpcs); - } + xpcs->id = entry; + + compat = xpcs_find_compat(entry, interface); + if (!compat) + return -ENODEV; + + return xpcs_soft_reset(xpcs, compat); } return -ENODEV; diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index c4d0a2c469c7..c2ec440d2c5d 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -14,11 +14,12 @@ #define DW_AN_C73 1 #define DW_AN_C37_SGMII 2 +struct xpcs_id; + struct mdio_xpcs_args { - __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); struct mii_bus *bus; + const struct xpcs_id *id; int addr; - int an_mode; }; struct mdio_xpcs_ops { @@ -36,6 +37,7 @@ struct mdio_xpcs_ops { int enable); }; +int xpcs_get_an_mode(struct mdio_xpcs_args *xpcs, phy_interface_t interface); struct mdio_xpcs_ops *mdio_xpcs_get_ops(void); #endif /* __LINUX_PCS_XPCS_H */ -- cgit v1.2.3-71-gd317 From a1a753ed1d4ae46c1c1874fb1af899f6579a7547 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 2 Jun 2021 19:20:14 +0300 Subject: net: pcs: xpcs: export xpcs_validate Calling a function pointer with a single implementation through struct mdio_xpcs_ops is clunky, and the stmmac_do_callback system forces this to return int, even though it always returns zero. Simply remove the "validate" function pointer from struct mdio_xpcs_ops and replace it with an exported xpcs_validate symbol which is called directly by stmmac. priv->hw->xpcs is of the type "const struct mdio_xpcs_ops *" and is used as a placeholder/synonym for priv->plat->mdio_bus_data->has_xpcs. It is done that way because the mdio_bus_data pointer might or might not be populated in all stmmac instantiations. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/hwif.h | 2 -- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 ++- drivers/net/pcs/pcs-xpcs.c | 11 ++++------- include/linux/pcs/pcs-xpcs.h | 5 ++--- 4 files changed, 8 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index dbafedb24290..441985f9cf49 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -614,8 +614,6 @@ struct stmmac_mmc_ops { stmmac_do_void_callback(__priv, mmc, read, __args) /* XPCS callbacks */ -#define stmmac_xpcs_validate(__priv, __args...) \ - stmmac_do_callback(__priv, xpcs, validate, __args) #define stmmac_xpcs_config(__priv, __args...) \ stmmac_do_callback(__priv, xpcs, config, __args) #define stmmac_xpcs_get_state(__priv, __args...) \ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index c96a89fa4e3c..b7e6ab05ddd9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -996,7 +996,8 @@ static void stmmac_validate(struct phylink_config *config, linkmode_andnot(state->advertising, state->advertising, mask); /* If PCS is supported, check which modes it supports. */ - stmmac_xpcs_validate(priv, &priv->hw->xpcs_args, supported, state); + if (priv->hw->xpcs) + xpcs_validate(&priv->hw->xpcs_args, supported, state); } static void stmmac_mac_pcs_get_state(struct phylink_config *config, diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 610073cb55d0..2f7791bcf07b 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -685,9 +685,8 @@ static void xpcs_resolve_pma(struct mdio_xpcs_args *xpcs, } } -static int xpcs_validate(struct mdio_xpcs_args *xpcs, - unsigned long *supported, - struct phylink_link_state *state) +void xpcs_validate(struct mdio_xpcs_args *xpcs, unsigned long *supported, + struct phylink_link_state *state) { __ETHTOOL_DECLARE_LINK_MODE_MASK(xpcs_supported); const struct xpcs_compat *compat; @@ -698,7 +697,7 @@ static int xpcs_validate(struct mdio_xpcs_args *xpcs, * advertising masks and exit. */ if (state->interface == PHY_INTERFACE_MODE_NA) - return 0; + return; bitmap_zero(xpcs_supported, __ETHTOOL_LINK_MODE_MASK_NBITS); @@ -713,9 +712,8 @@ static int xpcs_validate(struct mdio_xpcs_args *xpcs, linkmode_and(supported, supported, xpcs_supported); linkmode_and(state->advertising, state->advertising, xpcs_supported); - - return 0; } +EXPORT_SYMBOL_GPL(xpcs_validate); static int xpcs_config_eee(struct mdio_xpcs_args *xpcs, int mult_fact_100ns, int enable) @@ -1031,7 +1029,6 @@ static int xpcs_probe(struct mdio_xpcs_args *xpcs, phy_interface_t interface) } static struct mdio_xpcs_ops xpcs_ops = { - .validate = xpcs_validate, .config = xpcs_config, .get_state = xpcs_get_state, .link_up = xpcs_link_up, diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index c2ec440d2c5d..5ec9aaca01fe 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -23,9 +23,6 @@ struct mdio_xpcs_args { }; struct mdio_xpcs_ops { - int (*validate)(struct mdio_xpcs_args *xpcs, - unsigned long *supported, - struct phylink_link_state *state); int (*config)(struct mdio_xpcs_args *xpcs, const struct phylink_link_state *state); int (*get_state)(struct mdio_xpcs_args *xpcs, @@ -39,5 +36,7 @@ struct mdio_xpcs_ops { int xpcs_get_an_mode(struct mdio_xpcs_args *xpcs, phy_interface_t interface); struct mdio_xpcs_ops *mdio_xpcs_get_ops(void); +void xpcs_validate(struct mdio_xpcs_args *xpcs, unsigned long *supported, + struct phylink_link_state *state); #endif /* __LINUX_PCS_XPCS_H */ -- cgit v1.2.3-71-gd317 From 14b517cb62d6efc8866f176c922de03dfe1564f3 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 2 Jun 2021 19:20:15 +0300 Subject: net: pcs: xpcs: export xpcs_config_eee There is no good reason why we need to go through: stmmac_xpcs_config_eee -> stmmac_do_callback -> mdio_xpcs_ops->config_eee -> xpcs_config_eee when we can simply call xpcs_config_eee. priv->hw->xpcs is of the type "const struct mdio_xpcs_ops *" and is used as a placeholder/synonym for priv->plat->mdio_bus_data->has_xpcs. It is done that way because the mdio_bus_data pointer might or might not be populated in all stmmac instantiations. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/hwif.h | 2 -- drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 12 +++++++----- drivers/net/pcs/pcs-xpcs.c | 6 +++--- include/linux/pcs/pcs-xpcs.h | 4 ++-- 4 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index 441985f9cf49..c10d11dbde61 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -622,8 +622,6 @@ struct stmmac_mmc_ops { stmmac_do_callback(__priv, xpcs, link_up, __args) #define stmmac_xpcs_probe(__priv, __args...) \ stmmac_do_callback(__priv, xpcs, probe, __args) -#define stmmac_xpcs_config_eee(__priv, __args...) \ - stmmac_do_callback(__priv, xpcs, config_eee, __args) struct stmmac_regs_off { u32 ptp_off; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 1f6d749fd9a3..ba7d0f40723a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -720,11 +720,13 @@ static int stmmac_ethtool_op_set_eee(struct net_device *dev, netdev_warn(priv->dev, "Setting EEE tx-lpi is not supported\n"); - ret = stmmac_xpcs_config_eee(priv, &priv->hw->xpcs_args, - priv->plat->mult_fact_100ns, - edata->eee_enabled); - if (ret) - return ret; + if (priv->hw->xpcs) { + ret = xpcs_config_eee(&priv->hw->xpcs_args, + priv->plat->mult_fact_100ns, + edata->eee_enabled); + if (ret) + return ret; + } if (!edata->eee_enabled) stmmac_disable_eee_mode(priv); diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 2f7791bcf07b..2f2ffab855aa 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -715,8 +715,8 @@ void xpcs_validate(struct mdio_xpcs_args *xpcs, unsigned long *supported, } EXPORT_SYMBOL_GPL(xpcs_validate); -static int xpcs_config_eee(struct mdio_xpcs_args *xpcs, int mult_fact_100ns, - int enable) +int xpcs_config_eee(struct mdio_xpcs_args *xpcs, int mult_fact_100ns, + int enable) { int ret; @@ -747,6 +747,7 @@ static int xpcs_config_eee(struct mdio_xpcs_args *xpcs, int mult_fact_100ns, ret |= DW_VR_MII_EEE_TRN_LPI; return xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_EEE_MCTRL1, ret); } +EXPORT_SYMBOL_GPL(xpcs_config_eee); static int xpcs_config_aneg_c37_sgmii(struct mdio_xpcs_args *xpcs) { @@ -1033,7 +1034,6 @@ static struct mdio_xpcs_ops xpcs_ops = { .get_state = xpcs_get_state, .link_up = xpcs_link_up, .probe = xpcs_probe, - .config_eee = xpcs_config_eee, }; struct mdio_xpcs_ops *mdio_xpcs_get_ops(void) diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 5ec9aaca01fe..ae74a336dcb9 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -30,13 +30,13 @@ struct mdio_xpcs_ops { int (*link_up)(struct mdio_xpcs_args *xpcs, int speed, phy_interface_t interface); int (*probe)(struct mdio_xpcs_args *xpcs, phy_interface_t interface); - int (*config_eee)(struct mdio_xpcs_args *xpcs, int mult_fact_100ns, - int enable); }; int xpcs_get_an_mode(struct mdio_xpcs_args *xpcs, phy_interface_t interface); struct mdio_xpcs_ops *mdio_xpcs_get_ops(void); void xpcs_validate(struct mdio_xpcs_args *xpcs, unsigned long *supported, struct phylink_link_state *state); +int xpcs_config_eee(struct mdio_xpcs_args *xpcs, int mult_fact_100ns, + int enable); #endif /* __LINUX_PCS_XPCS_H */ -- cgit v1.2.3-71-gd317 From 8e2bb9569942f9cb2ef816dbf66fbf3e8d722720 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 2 Jun 2021 19:20:16 +0300 Subject: net: pcs: xpcs: export xpcs_probe Similar to the other recently functions, it is not necessary for xpcs_probe to be a function pointer, so export it so that it can be called directly. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/hwif.h | 2 -- drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c | 2 +- drivers/net/pcs/pcs-xpcs.c | 4 ++-- include/linux/pcs/pcs-xpcs.h | 2 +- 4 files changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index c10d11dbde61..3dc291ff9f32 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -620,8 +620,6 @@ struct stmmac_mmc_ops { stmmac_do_callback(__priv, xpcs, get_state, __args) #define stmmac_xpcs_link_up(__priv, __args...) \ stmmac_do_callback(__priv, xpcs, link_up, __args) -#define stmmac_xpcs_probe(__priv, __args...) \ - stmmac_do_callback(__priv, xpcs, probe, __args) struct stmmac_regs_off { u32 ptp_off; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index e293bf1ce9f3..56deb92a8430 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -521,7 +521,7 @@ int stmmac_mdio_register(struct net_device *ndev) for (addr = 0; addr < max_addr; addr++) { xpcs->addr = addr; - ret = stmmac_xpcs_probe(priv, xpcs, mode); + ret = xpcs_probe(xpcs, mode); if (!ret) { found = 1; break; diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 2f2ffab855aa..7f51eb4bbaa4 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -1005,7 +1005,7 @@ static const struct xpcs_id xpcs_id_list[] = { }, }; -static int xpcs_probe(struct mdio_xpcs_args *xpcs, phy_interface_t interface) +int xpcs_probe(struct mdio_xpcs_args *xpcs, phy_interface_t interface) { u32 xpcs_id = xpcs_get_id(xpcs); int i; @@ -1028,12 +1028,12 @@ static int xpcs_probe(struct mdio_xpcs_args *xpcs, phy_interface_t interface) return -ENODEV; } +EXPORT_SYMBOL_GPL(xpcs_probe); static struct mdio_xpcs_ops xpcs_ops = { .config = xpcs_config, .get_state = xpcs_get_state, .link_up = xpcs_link_up, - .probe = xpcs_probe, }; struct mdio_xpcs_ops *mdio_xpcs_get_ops(void) diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index ae74a336dcb9..1d8581b74d81 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -29,7 +29,6 @@ struct mdio_xpcs_ops { struct phylink_link_state *state); int (*link_up)(struct mdio_xpcs_args *xpcs, int speed, phy_interface_t interface); - int (*probe)(struct mdio_xpcs_args *xpcs, phy_interface_t interface); }; int xpcs_get_an_mode(struct mdio_xpcs_args *xpcs, phy_interface_t interface); @@ -38,5 +37,6 @@ void xpcs_validate(struct mdio_xpcs_args *xpcs, unsigned long *supported, struct phylink_link_state *state); int xpcs_config_eee(struct mdio_xpcs_args *xpcs, int mult_fact_100ns, int enable); +int xpcs_probe(struct mdio_xpcs_args *xpcs, phy_interface_t interface); #endif /* __LINUX_PCS_XPCS_H */ -- cgit v1.2.3-71-gd317 From 2cac15dae2f6e2f86bef1acc2a7f78fc97a0a060 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 2 Jun 2021 19:20:18 +0300 Subject: net: pcs: xpcs: convert to mdio_device Unify the 2 existing PCS drivers (lynx and xpcs) by doing a similar thing on probe, which is to have a *_create function that takes a struct mdio_device * given by the caller, and builds a private PCS structure around that. This changes stmmac to hold only a pointer to the xpcs, as opposed to the full structure. This will be used in the next patch when struct mdio_xpcs_ops is removed. Currently a pointer to struct mdio_xpcs_ops is used as a shorthand to determine whether the port has an XPCS or not. We can do the same now with the mdio_xpcs_args pointer. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 2 +- .../net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 10 ++-- drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c | 39 +++++++++------- drivers/net/pcs/pcs-xpcs.c | 53 +++++++++++++++++----- include/linux/pcs/pcs-xpcs.h | 7 +-- 6 files changed, 76 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 619e3c0760d6..4bcd1d340766 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -504,7 +504,7 @@ struct mac_device_info { const struct stmmac_tc_ops *tc; const struct stmmac_mmc_ops *mmc; const struct mdio_xpcs_ops *xpcs; - struct mdio_xpcs_args xpcs_args; + struct mdio_xpcs_args *xpcs_args; struct mii_regs mii; /* MII register Addresses */ struct mac_link link; void __iomem *pcsr; /* vpointer to device CSRs */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index ba7d0f40723a..050576ee704d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -721,7 +721,7 @@ static int stmmac_ethtool_op_set_eee(struct net_device *dev, "Setting EEE tx-lpi is not supported\n"); if (priv->hw->xpcs) { - ret = xpcs_config_eee(&priv->hw->xpcs_args, + ret = xpcs_config_eee(priv->hw->xpcs_args, priv->plat->mult_fact_100ns, edata->eee_enabled); if (ret) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index b7e6ab05ddd9..e9e5bcb79d48 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -997,7 +997,7 @@ static void stmmac_validate(struct phylink_config *config, /* If PCS is supported, check which modes it supports. */ if (priv->hw->xpcs) - xpcs_validate(&priv->hw->xpcs_args, supported, state); + xpcs_validate(priv->hw->xpcs_args, supported, state); } static void stmmac_mac_pcs_get_state(struct phylink_config *config, @@ -1006,7 +1006,7 @@ static void stmmac_mac_pcs_get_state(struct phylink_config *config, struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); state->link = 0; - stmmac_xpcs_get_state(priv, &priv->hw->xpcs_args, state); + stmmac_xpcs_get_state(priv, priv->hw->xpcs_args, state); } static void stmmac_mac_config(struct phylink_config *config, unsigned int mode, @@ -1014,7 +1014,7 @@ static void stmmac_mac_config(struct phylink_config *config, unsigned int mode, { struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); - stmmac_xpcs_config(priv, &priv->hw->xpcs_args, state); + stmmac_xpcs_config(priv, priv->hw->xpcs_args, state); } static void stmmac_mac_an_restart(struct phylink_config *config) @@ -1061,7 +1061,7 @@ static void stmmac_mac_link_up(struct phylink_config *config, struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); u32 ctrl; - stmmac_xpcs_link_up(priv, &priv->hw->xpcs_args, speed, interface); + stmmac_xpcs_link_up(priv, priv->hw->xpcs_args, speed, interface); ctrl = readl(priv->ioaddr + MAC_CTRL_REG); ctrl &= ~priv->hw->link.speed_mask; @@ -3653,7 +3653,7 @@ int stmmac_open(struct net_device *dev) if (priv->hw->pcs != STMMAC_PCS_TBI && priv->hw->pcs != STMMAC_PCS_RTBI && (!priv->hw->xpcs || - xpcs_get_an_mode(&priv->hw->xpcs_args, mode) != DW_AN_C73)) { + xpcs_get_an_mode(priv->hw->xpcs_args, mode) != DW_AN_C73)) { ret = stmmac_init_phy(dev); if (ret) { netdev_err(priv->dev, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index 56deb92a8430..9b4bf78d2eaa 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -510,25 +510,27 @@ int stmmac_mdio_register(struct net_device *ndev) } /* Try to probe the XPCS by scanning all addresses. */ - if (priv->hw->xpcs) { - struct mdio_xpcs_args *xpcs = &priv->hw->xpcs_args; - int ret, mode = priv->plat->phy_interface; - max_addr = PHY_MAX_ADDR; - - xpcs->bus = new_bus; - - found = 0; - for (addr = 0; addr < max_addr; addr++) { - xpcs->addr = addr; - - ret = xpcs_probe(xpcs, mode); - if (!ret) { - found = 1; - break; + if (mdio_bus_data->has_xpcs) { + int mode = priv->plat->phy_interface; + struct mdio_device *mdiodev; + struct mdio_xpcs_args *xpcs; + + for (addr = 0; addr < PHY_MAX_ADDR; addr++) { + mdiodev = mdio_device_create(new_bus, addr); + if (IS_ERR(mdiodev)) + continue; + + xpcs = xpcs_create(mdiodev, mode); + if (IS_ERR_OR_NULL(xpcs)) { + mdio_device_free(mdiodev); + continue; } + + priv->hw->xpcs_args = xpcs; + break; } - if (!found && !mdio_node) { + if (!priv->hw->xpcs_args) { dev_warn(dev, "No XPCS found\n"); err = -ENODEV; goto no_xpcs_found; @@ -560,6 +562,11 @@ int stmmac_mdio_unregister(struct net_device *ndev) if (!priv->mii) return 0; + if (priv->hw->xpcs) { + mdio_device_free(priv->hw->xpcs_args->mdiodev); + xpcs_destroy(priv->hw->xpcs_args); + } + mdiobus_unregister(priv->mii); priv->mii->priv = NULL; mdiobus_free(priv->mii); diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index afabb9209c52..e17e72175ebb 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -241,15 +241,19 @@ static bool __xpcs_linkmode_supported(const struct xpcs_compat *compat, static int xpcs_read(struct mdio_xpcs_args *xpcs, int dev, u32 reg) { u32 reg_addr = mdiobus_c45_addr(dev, reg); + struct mii_bus *bus = xpcs->mdiodev->bus; + int addr = xpcs->mdiodev->addr; - return mdiobus_read(xpcs->bus, xpcs->addr, reg_addr); + return mdiobus_read(bus, addr, reg_addr); } static int xpcs_write(struct mdio_xpcs_args *xpcs, int dev, u32 reg, u16 val) { u32 reg_addr = mdiobus_c45_addr(dev, reg); + struct mii_bus *bus = xpcs->mdiodev->bus; + int addr = xpcs->mdiodev->addr; - return mdiobus_write(xpcs->bus, xpcs->addr, reg_addr, val); + return mdiobus_write(bus, addr, reg_addr, val); } static int xpcs_read_vendor(struct mdio_xpcs_args *xpcs, int dev, u32 reg) @@ -315,7 +319,7 @@ static int xpcs_soft_reset(struct mdio_xpcs_args *xpcs, #define xpcs_warn(__xpcs, __state, __args...) \ ({ \ if ((__state)->link) \ - dev_warn(&(__xpcs)->bus->dev, ##__args); \ + dev_warn(&(__xpcs)->mdiodev->dev, ##__args); \ }) static int xpcs_read_fault_c73(struct mdio_xpcs_args *xpcs, @@ -1005,10 +1009,20 @@ static const struct xpcs_id xpcs_id_list[] = { }, }; -int xpcs_probe(struct mdio_xpcs_args *xpcs, phy_interface_t interface) +struct mdio_xpcs_args *xpcs_create(struct mdio_device *mdiodev, + phy_interface_t interface) { - u32 xpcs_id = xpcs_get_id(xpcs); - int i; + struct mdio_xpcs_args *xpcs; + u32 xpcs_id; + int i, ret; + + xpcs = kzalloc(sizeof(*xpcs), GFP_KERNEL); + if (!xpcs) + return NULL; + + xpcs->mdiodev = mdiodev; + + xpcs_id = xpcs_get_id(xpcs); for (i = 0; i < ARRAY_SIZE(xpcs_id_list); i++) { const struct xpcs_id *entry = &xpcs_id_list[i]; @@ -1020,15 +1034,32 @@ int xpcs_probe(struct mdio_xpcs_args *xpcs, phy_interface_t interface) xpcs->id = entry; compat = xpcs_find_compat(entry, interface); - if (!compat) - return -ENODEV; + if (!compat) { + ret = -ENODEV; + goto out; + } - return xpcs_soft_reset(xpcs, compat); + ret = xpcs_soft_reset(xpcs, compat); + if (ret) + goto out; + + return xpcs; } - return -ENODEV; + ret = -ENODEV; + +out: + kfree(xpcs); + + return ERR_PTR(ret); +} +EXPORT_SYMBOL_GPL(xpcs_create); + +void xpcs_destroy(struct mdio_xpcs_args *xpcs) +{ + kfree(xpcs); } -EXPORT_SYMBOL_GPL(xpcs_probe); +EXPORT_SYMBOL_GPL(xpcs_destroy); static struct mdio_xpcs_ops xpcs_ops = { .config = xpcs_config, diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 1d8581b74d81..57a199393d63 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -17,9 +17,8 @@ struct xpcs_id; struct mdio_xpcs_args { - struct mii_bus *bus; + struct mdio_device *mdiodev; const struct xpcs_id *id; - int addr; }; struct mdio_xpcs_ops { @@ -37,6 +36,8 @@ void xpcs_validate(struct mdio_xpcs_args *xpcs, unsigned long *supported, struct phylink_link_state *state); int xpcs_config_eee(struct mdio_xpcs_args *xpcs, int mult_fact_100ns, int enable); -int xpcs_probe(struct mdio_xpcs_args *xpcs, phy_interface_t interface); +struct mdio_xpcs_args *xpcs_create(struct mdio_device *mdiodev, + phy_interface_t interface); +void xpcs_destroy(struct mdio_xpcs_args *xpcs); #endif /* __LINUX_PCS_XPCS_H */ -- cgit v1.2.3-71-gd317 From 11059740e616f4d83d8d9e3f8a63dafefdc2ae5d Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 2 Jun 2021 19:20:19 +0300 Subject: net: pcs: xpcs: convert to phylink_pcs_ops Since all the remaining members of struct mdio_xpcs_ops have direct equivalents in struct phylink_pcs_ops, it is about time we remove it altogether. Since the phylink ops return void, we need to remove the error propagation from the various xpcs methods and simply print an error message where appropriate. Since xpcs_get_state_c73() detects link faults and attempts to reset the link on its own by calling xpcs_config(), but xpcs_config() now has a lot of phylink arguments which are not needed and cannot be simply fabricated by anybody else except phylink, the actual implementation has been moved into a smaller xpcs_do_config(). The const struct mdio_xpcs_ops *priv->hw->xpcs has been removed, so we need to look at the struct mdio_xpcs_args pointer now as an indication whether the port has an XPCS or not. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 3 +- drivers/net/ethernet/stmicro/stmmac/hwif.h | 8 -- .../net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 36 +++----- drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c | 16 +--- drivers/net/pcs/pcs-xpcs.c | 99 +++++++++++++--------- include/linux/pcs/pcs-xpcs.h | 11 +-- 7 files changed, 78 insertions(+), 97 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 4bcd1d340766..8a83f9e1e95b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -503,8 +503,7 @@ struct mac_device_info { const struct stmmac_hwtimestamp *ptp; const struct stmmac_tc_ops *tc; const struct stmmac_mmc_ops *mmc; - const struct mdio_xpcs_ops *xpcs; - struct mdio_xpcs_args *xpcs_args; + struct mdio_xpcs_args *xpcs; struct mii_regs mii; /* MII register Addresses */ struct mac_link link; void __iomem *pcsr; /* vpointer to device CSRs */ diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index 3dc291ff9f32..6dc1c98ebec8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -613,14 +613,6 @@ struct stmmac_mmc_ops { #define stmmac_mmc_read(__priv, __args...) \ stmmac_do_void_callback(__priv, mmc, read, __args) -/* XPCS callbacks */ -#define stmmac_xpcs_config(__priv, __args...) \ - stmmac_do_callback(__priv, xpcs, config, __args) -#define stmmac_xpcs_get_state(__priv, __args...) \ - stmmac_do_callback(__priv, xpcs, get_state, __args) -#define stmmac_xpcs_link_up(__priv, __args...) \ - stmmac_do_callback(__priv, xpcs, link_up, __args) - struct stmmac_regs_off { u32 ptp_off; u32 mmc_off; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 050576ee704d..d0ce608b81c3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -721,7 +721,7 @@ static int stmmac_ethtool_op_set_eee(struct net_device *dev, "Setting EEE tx-lpi is not supported\n"); if (priv->hw->xpcs) { - ret = xpcs_config_eee(priv->hw->xpcs_args, + ret = xpcs_config_eee(priv->hw->xpcs, priv->plat->mult_fact_100ns, edata->eee_enabled); if (ret) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index e9e5bcb79d48..6d41dd6f9f7a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -997,29 +997,13 @@ static void stmmac_validate(struct phylink_config *config, /* If PCS is supported, check which modes it supports. */ if (priv->hw->xpcs) - xpcs_validate(priv->hw->xpcs_args, supported, state); -} - -static void stmmac_mac_pcs_get_state(struct phylink_config *config, - struct phylink_link_state *state) -{ - struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); - - state->link = 0; - stmmac_xpcs_get_state(priv, priv->hw->xpcs_args, state); + xpcs_validate(priv->hw->xpcs, supported, state); } static void stmmac_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) { - struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); - - stmmac_xpcs_config(priv, priv->hw->xpcs_args, state); -} - -static void stmmac_mac_an_restart(struct phylink_config *config) -{ - /* Not Supported */ + /* Nothing to do, xpcs_config() handles everything */ } static void stmmac_fpe_link_state_handle(struct stmmac_priv *priv, bool is_up) @@ -1061,8 +1045,6 @@ static void stmmac_mac_link_up(struct phylink_config *config, struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); u32 ctrl; - stmmac_xpcs_link_up(priv, priv->hw->xpcs_args, speed, interface); - ctrl = readl(priv->ioaddr + MAC_CTRL_REG); ctrl &= ~priv->hw->link.speed_mask; @@ -1155,9 +1137,7 @@ static void stmmac_mac_link_up(struct phylink_config *config, static const struct phylink_mac_ops stmmac_phylink_mac_ops = { .validate = stmmac_validate, - .mac_pcs_get_state = stmmac_mac_pcs_get_state, .mac_config = stmmac_mac_config, - .mac_an_restart = stmmac_mac_an_restart, .mac_link_down = stmmac_mac_link_down, .mac_link_up = stmmac_mac_link_up, }; @@ -1234,6 +1214,7 @@ static int stmmac_init_phy(struct net_device *dev) static int stmmac_phy_setup(struct stmmac_priv *priv) { + struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data; struct fwnode_handle *fwnode = of_fwnode_handle(priv->plat->phylink_node); int mode = priv->plat->phy_interface; struct phylink *phylink; @@ -1241,8 +1222,7 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) priv->phylink_config.dev = &priv->dev->dev; priv->phylink_config.type = PHYLINK_NETDEV; priv->phylink_config.pcs_poll = true; - priv->phylink_config.ovr_an_inband = - priv->plat->mdio_bus_data->xpcs_an_inband; + priv->phylink_config.ovr_an_inband = mdio_bus_data->xpcs_an_inband; if (!fwnode) fwnode = dev_fwnode(priv->device); @@ -1252,6 +1232,12 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) if (IS_ERR(phylink)) return PTR_ERR(phylink); + if (mdio_bus_data->has_xpcs) { + struct mdio_xpcs_args *xpcs = priv->hw->xpcs; + + phylink_set_pcs(phylink, &xpcs->pcs); + } + priv->phylink = phylink; return 0; } @@ -3653,7 +3639,7 @@ int stmmac_open(struct net_device *dev) if (priv->hw->pcs != STMMAC_PCS_TBI && priv->hw->pcs != STMMAC_PCS_RTBI && (!priv->hw->xpcs || - xpcs_get_an_mode(priv->hw->xpcs_args, mode) != DW_AN_C73)) { + xpcs_get_an_mode(priv->hw->xpcs, mode) != DW_AN_C73)) { ret = stmmac_init_phy(dev); if (ret) { netdev_err(priv->dev, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index 9b4bf78d2eaa..6312a152c8ad 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -444,14 +444,6 @@ int stmmac_mdio_register(struct net_device *ndev) max_addr = PHY_MAX_ADDR; } - if (mdio_bus_data->has_xpcs) { - priv->hw->xpcs = mdio_xpcs_get_ops(); - if (!priv->hw->xpcs) { - err = -ENODEV; - goto bus_register_fail; - } - } - if (mdio_bus_data->needs_reset) new_bus->reset = &stmmac_mdio_reset; @@ -526,11 +518,11 @@ int stmmac_mdio_register(struct net_device *ndev) continue; } - priv->hw->xpcs_args = xpcs; + priv->hw->xpcs = xpcs; break; } - if (!priv->hw->xpcs_args) { + if (!priv->hw->xpcs) { dev_warn(dev, "No XPCS found\n"); err = -ENODEV; goto no_xpcs_found; @@ -563,8 +555,8 @@ int stmmac_mdio_unregister(struct net_device *ndev) return 0; if (priv->hw->xpcs) { - mdio_device_free(priv->hw->xpcs_args->mdiodev); - xpcs_destroy(priv->hw->xpcs_args); + mdio_device_free(priv->hw->xpcs->mdiodev); + xpcs_destroy(priv->hw->xpcs); } mdiobus_unregister(priv->mii); diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index e17e72175ebb..34164437c135 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -100,6 +100,9 @@ /* VR MII EEE Control 1 defines */ #define DW_VR_MII_EEE_TRN_LPI BIT(0) /* Transparent Mode Enable */ +#define phylink_pcs_to_xpcs(pl_pcs) \ + container_of((pl_pcs), struct mdio_xpcs_args, pcs) + static const int xpcs_usxgmii_features[] = { ETHTOOL_LINK_MODE_Pause_BIT, ETHTOOL_LINK_MODE_Asym_Pause_BIT, @@ -413,7 +416,7 @@ static int xpcs_get_max_usxgmii_speed(const unsigned long *supported) return max; } -static int xpcs_config_usxgmii(struct mdio_xpcs_args *xpcs, int speed) +static void xpcs_config_usxgmii(struct mdio_xpcs_args *xpcs, int speed) { int ret, speed_sel; @@ -438,33 +441,40 @@ static int xpcs_config_usxgmii(struct mdio_xpcs_args *xpcs, int speed) break; default: /* Nothing to do here */ - return -EINVAL; + return; } ret = xpcs_read_vpcs(xpcs, MDIO_CTRL1); if (ret < 0) - return ret; + goto out; ret = xpcs_write_vpcs(xpcs, MDIO_CTRL1, ret | DW_USXGMII_EN); if (ret < 0) - return ret; + goto out; ret = xpcs_read(xpcs, MDIO_MMD_VEND2, MDIO_CTRL1); if (ret < 0) - return ret; + goto out; ret &= ~DW_USXGMII_SS_MASK; ret |= speed_sel | DW_USXGMII_FULL; ret = xpcs_write(xpcs, MDIO_MMD_VEND2, MDIO_CTRL1, ret); if (ret < 0) - return ret; + goto out; ret = xpcs_read_vpcs(xpcs, MDIO_CTRL1); if (ret < 0) - return ret; + goto out; + + ret = xpcs_write_vpcs(xpcs, MDIO_CTRL1, ret | DW_USXGMII_RST); + if (ret < 0) + goto out; + + return; - return xpcs_write_vpcs(xpcs, MDIO_CTRL1, ret | DW_USXGMII_RST); +out: + pr_err("%s: XPCS access returned %pe\n", __func__, ERR_PTR(ret)); } static int _xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs, @@ -794,19 +804,19 @@ static int xpcs_config_aneg_c37_sgmii(struct mdio_xpcs_args *xpcs) return xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_DIG_CTRL1, ret); } -static int xpcs_config(struct mdio_xpcs_args *xpcs, - const struct phylink_link_state *state) +static int xpcs_do_config(struct mdio_xpcs_args *xpcs, + phy_interface_t interface, unsigned int mode) { const struct xpcs_compat *compat; int ret; - compat = xpcs_find_compat(xpcs->id, state->interface); + compat = xpcs_find_compat(xpcs->id, interface); if (!compat) return -ENODEV; switch (compat->an_mode) { case DW_AN_C73: - if (state->an_enabled) { + if (phylink_autoneg_inband(mode)) { ret = xpcs_config_aneg_c73(xpcs, compat); if (ret) return ret; @@ -824,6 +834,16 @@ static int xpcs_config(struct mdio_xpcs_args *xpcs, return 0; } +static int xpcs_config(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t interface, + const unsigned long *advertising, + bool permit_pause_to_mac) +{ + struct mdio_xpcs_args *xpcs = phylink_pcs_to_xpcs(pcs); + + return xpcs_do_config(xpcs, interface, mode); +} + static int xpcs_get_state_c73(struct mdio_xpcs_args *xpcs, struct phylink_link_state *state, const struct xpcs_compat *compat) @@ -842,7 +862,7 @@ static int xpcs_get_state_c73(struct mdio_xpcs_args *xpcs, state->link = 0; - return xpcs_config(xpcs, state); + return xpcs_do_config(xpcs, state->interface, MLO_AN_INBAND); } if (state->an_enabled && xpcs_aneg_done_c73(xpcs, state, compat)) { @@ -899,41 +919,45 @@ static int xpcs_get_state_c37_sgmii(struct mdio_xpcs_args *xpcs, return 0; } -static int xpcs_get_state(struct mdio_xpcs_args *xpcs, - struct phylink_link_state *state) +static void xpcs_get_state(struct phylink_pcs *pcs, + struct phylink_link_state *state) { + struct mdio_xpcs_args *xpcs = phylink_pcs_to_xpcs(pcs); const struct xpcs_compat *compat; int ret; compat = xpcs_find_compat(xpcs->id, state->interface); if (!compat) - return -ENODEV; + return; switch (compat->an_mode) { case DW_AN_C73: ret = xpcs_get_state_c73(xpcs, state, compat); - if (ret) - return ret; + if (ret) { + pr_err("xpcs_get_state_c73 returned %pe\n", + ERR_PTR(ret)); + return; + } break; case DW_AN_C37_SGMII: ret = xpcs_get_state_c37_sgmii(xpcs, state); - if (ret) - return ret; + if (ret) { + pr_err("xpcs_get_state_c37_sgmii returned %pe\n", + ERR_PTR(ret)); + } break; default: - return -1; + return; } - - return 0; } -static int xpcs_link_up(struct mdio_xpcs_args *xpcs, int speed, - phy_interface_t interface) +static void xpcs_link_up(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t interface, int speed, int duplex) { + struct mdio_xpcs_args *xpcs = phylink_pcs_to_xpcs(pcs); + if (interface == PHY_INTERFACE_MODE_USXGMII) return xpcs_config_usxgmii(xpcs, speed); - - return 0; } static u32 xpcs_get_id(struct mdio_xpcs_args *xpcs) @@ -1009,6 +1033,12 @@ static const struct xpcs_id xpcs_id_list[] = { }, }; +static const struct phylink_pcs_ops xpcs_phylink_ops = { + .pcs_config = xpcs_config, + .pcs_get_state = xpcs_get_state, + .pcs_link_up = xpcs_link_up, +}; + struct mdio_xpcs_args *xpcs_create(struct mdio_device *mdiodev, phy_interface_t interface) { @@ -1039,6 +1069,9 @@ struct mdio_xpcs_args *xpcs_create(struct mdio_device *mdiodev, goto out; } + xpcs->pcs.ops = &xpcs_phylink_ops; + xpcs->pcs.poll = true; + ret = xpcs_soft_reset(xpcs, compat); if (ret) goto out; @@ -1061,16 +1094,4 @@ void xpcs_destroy(struct mdio_xpcs_args *xpcs) } EXPORT_SYMBOL_GPL(xpcs_destroy); -static struct mdio_xpcs_ops xpcs_ops = { - .config = xpcs_config, - .get_state = xpcs_get_state, - .link_up = xpcs_link_up, -}; - -struct mdio_xpcs_ops *mdio_xpcs_get_ops(void) -{ - return &xpcs_ops; -} -EXPORT_SYMBOL_GPL(mdio_xpcs_get_ops); - MODULE_LICENSE("GPL v2"); diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 57a199393d63..0860a5b59f10 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -19,19 +19,10 @@ struct xpcs_id; struct mdio_xpcs_args { struct mdio_device *mdiodev; const struct xpcs_id *id; -}; - -struct mdio_xpcs_ops { - int (*config)(struct mdio_xpcs_args *xpcs, - const struct phylink_link_state *state); - int (*get_state)(struct mdio_xpcs_args *xpcs, - struct phylink_link_state *state); - int (*link_up)(struct mdio_xpcs_args *xpcs, int speed, - phy_interface_t interface); + struct phylink_pcs pcs; }; int xpcs_get_an_mode(struct mdio_xpcs_args *xpcs, phy_interface_t interface); -struct mdio_xpcs_ops *mdio_xpcs_get_ops(void); void xpcs_validate(struct mdio_xpcs_args *xpcs, unsigned long *supported, struct phylink_link_state *state); int xpcs_config_eee(struct mdio_xpcs_args *xpcs, int mult_fact_100ns, -- cgit v1.2.3-71-gd317 From 1bd4f5716fc3bb4882033fbeeb97472503f1c7e2 Mon Sep 17 00:00:00 2001 From: Omkar Kulkarni Date: Wed, 2 Jun 2021 20:16:49 +0300 Subject: qed: Add TCP_ULP FW resource layout Add TCP_ULP as a storage common TCP offload FW resource layout. This will be used by the core driver (QED) for both the NVMeTCP and iSCSI. Acked-by: Igor Russkikh Signed-off-by: Prabhakar Kushwaha Signed-off-by: Omkar Kulkarni Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Signed-off-by: Shai Malin Reviewed-by: Hannes Reinecke Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_cxt.c | 18 +++++++++--------- drivers/net/ethernet/qlogic/qed/qed_cxt.h | 2 +- drivers/net/ethernet/qlogic/qed/qed_dev.c | 2 +- drivers/net/ethernet/qlogic/qed/qed_hsi.h | 2 +- drivers/net/ethernet/qlogic/qed/qed_iscsi.c | 20 ++++++++++---------- drivers/net/ethernet/qlogic/qed/qed_ll2.c | 8 ++++---- drivers/net/ethernet/qlogic/qed/qed_ooo.c | 2 +- drivers/net/ethernet/qlogic/qed/qed_sp_commands.c | 2 +- include/linux/qed/common_hsi.h | 2 +- include/linux/qed/qed_ll2_if.h | 2 +- 10 files changed, 30 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index 0a22f8ce9a2c..fcabbaa518df 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -94,14 +94,14 @@ struct src_ent { static bool src_proto(enum protocol_type type) { - return type == PROTOCOLID_ISCSI || + return type == PROTOCOLID_TCP_ULP || type == PROTOCOLID_FCOE || type == PROTOCOLID_IWARP; } static bool tm_cid_proto(enum protocol_type type) { - return type == PROTOCOLID_ISCSI || + return type == PROTOCOLID_TCP_ULP || type == PROTOCOLID_FCOE || type == PROTOCOLID_ROCE || type == PROTOCOLID_IWARP; @@ -2090,13 +2090,13 @@ int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks) if (p_params->num_cons && p_params->num_tasks) { qed_cxt_set_proto_cid_count(p_hwfn, - PROTOCOLID_ISCSI, + PROTOCOLID_TCP_ULP, p_params->num_cons, 0); qed_cxt_set_proto_tid_count(p_hwfn, - PROTOCOLID_ISCSI, - QED_CXT_ISCSI_TID_SEG, + PROTOCOLID_TCP_ULP, + QED_CXT_TCP_ULP_TID_SEG, 0, p_params->num_tasks, true); @@ -2129,8 +2129,8 @@ int qed_cxt_get_tid_mem_info(struct qed_hwfn *p_hwfn, seg = QED_CXT_FCOE_TID_SEG; break; case QED_PCI_ISCSI: - proto = PROTOCOLID_ISCSI; - seg = QED_CXT_ISCSI_TID_SEG; + proto = PROTOCOLID_TCP_ULP; + seg = QED_CXT_TCP_ULP_TID_SEG; break; default: return -EINVAL; @@ -2455,8 +2455,8 @@ int qed_cxt_get_task_ctx(struct qed_hwfn *p_hwfn, seg = QED_CXT_FCOE_TID_SEG; break; case QED_PCI_ISCSI: - proto = PROTOCOLID_ISCSI; - seg = QED_CXT_ISCSI_TID_SEG; + proto = PROTOCOLID_TCP_ULP; + seg = QED_CXT_TCP_ULP_TID_SEG; break; default: return -EINVAL; diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.h b/drivers/net/ethernet/qlogic/qed/qed_cxt.h index 056e79620a0e..8adb7ed0c12d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.h +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.h @@ -50,7 +50,7 @@ int qed_cxt_get_cid_info(struct qed_hwfn *p_hwfn, int qed_cxt_get_tid_mem_info(struct qed_hwfn *p_hwfn, struct qed_tid_mem *p_info); -#define QED_CXT_ISCSI_TID_SEG PROTOCOLID_ISCSI +#define QED_CXT_TCP_ULP_TID_SEG PROTOCOLID_TCP_ULP #define QED_CXT_ROCE_TID_SEG PROTOCOLID_ROCE #define QED_CXT_FCOE_TID_SEG PROTOCOLID_FCOE enum qed_cxt_elem_type { diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index d2f5855b2ea7..c231d0e56571 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -2266,7 +2266,7 @@ int qed_resc_alloc(struct qed_dev *cdev) } else if (p_hwfn->hw_info.personality == QED_PCI_ISCSI) { num_cons = qed_cxt_get_proto_cid_count(p_hwfn, - PROTOCOLID_ISCSI, + PROTOCOLID_TCP_ULP, NULL); n_eqes += 2 * num_cons; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 559df9f4d656..9dbeb2efdc51 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -1118,7 +1118,7 @@ struct outer_tag_config_struct { /* personality per PF */ enum personality_type { BAD_PERSONALITY_TYP, - PERSONALITY_ISCSI, + PERSONALITY_TCP_ULP, PERSONALITY_FCOE, PERSONALITY_RDMA_AND_ETH, PERSONALITY_RDMA, diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c index 448567a1f520..db926d8b3033 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c @@ -158,7 +158,7 @@ qed_sp_iscsi_func_start(struct qed_hwfn *p_hwfn, rc = qed_sp_init_request(p_hwfn, &p_ent, ISCSI_RAMROD_CMD_ID_INIT_FUNC, - PROTOCOLID_ISCSI, &init_data); + PROTOCOLID_TCP_ULP, &init_data); if (rc) return rc; @@ -250,7 +250,7 @@ qed_sp_iscsi_func_start(struct qed_hwfn *p_hwfn, p_hwfn->p_iscsi_info->event_context = event_context; p_hwfn->p_iscsi_info->event_cb = async_event_cb; - qed_spq_register_async_cb(p_hwfn, PROTOCOLID_ISCSI, + qed_spq_register_async_cb(p_hwfn, PROTOCOLID_TCP_ULP, qed_iscsi_async_event); return qed_spq_post(p_hwfn, p_ent, NULL); @@ -286,7 +286,7 @@ static int qed_sp_iscsi_conn_offload(struct qed_hwfn *p_hwfn, rc = qed_sp_init_request(p_hwfn, &p_ent, ISCSI_RAMROD_CMD_ID_OFFLOAD_CONN, - PROTOCOLID_ISCSI, &init_data); + PROTOCOLID_TCP_ULP, &init_data); if (rc) return rc; @@ -465,7 +465,7 @@ static int qed_sp_iscsi_conn_update(struct qed_hwfn *p_hwfn, rc = qed_sp_init_request(p_hwfn, &p_ent, ISCSI_RAMROD_CMD_ID_UPDATE_CONN, - PROTOCOLID_ISCSI, &init_data); + PROTOCOLID_TCP_ULP, &init_data); if (rc) return rc; @@ -506,7 +506,7 @@ qed_sp_iscsi_mac_update(struct qed_hwfn *p_hwfn, rc = qed_sp_init_request(p_hwfn, &p_ent, ISCSI_RAMROD_CMD_ID_MAC_UPDATE, - PROTOCOLID_ISCSI, &init_data); + PROTOCOLID_TCP_ULP, &init_data); if (rc) return rc; @@ -548,7 +548,7 @@ static int qed_sp_iscsi_conn_terminate(struct qed_hwfn *p_hwfn, rc = qed_sp_init_request(p_hwfn, &p_ent, ISCSI_RAMROD_CMD_ID_TERMINATION_CONN, - PROTOCOLID_ISCSI, &init_data); + PROTOCOLID_TCP_ULP, &init_data); if (rc) return rc; @@ -582,7 +582,7 @@ static int qed_sp_iscsi_conn_clear_sq(struct qed_hwfn *p_hwfn, rc = qed_sp_init_request(p_hwfn, &p_ent, ISCSI_RAMROD_CMD_ID_CLEAR_SQ, - PROTOCOLID_ISCSI, &init_data); + PROTOCOLID_TCP_ULP, &init_data); if (rc) return rc; @@ -606,13 +606,13 @@ static int qed_sp_iscsi_func_stop(struct qed_hwfn *p_hwfn, rc = qed_sp_init_request(p_hwfn, &p_ent, ISCSI_RAMROD_CMD_ID_DESTROY_FUNC, - PROTOCOLID_ISCSI, &init_data); + PROTOCOLID_TCP_ULP, &init_data); if (rc) return rc; rc = qed_spq_post(p_hwfn, p_ent, NULL); - qed_spq_unregister_async_cb(p_hwfn, PROTOCOLID_ISCSI); + qed_spq_unregister_async_cb(p_hwfn, PROTOCOLID_TCP_ULP); return rc; } @@ -786,7 +786,7 @@ static int qed_iscsi_acquire_connection(struct qed_hwfn *p_hwfn, u32 icid; spin_lock_bh(&p_hwfn->p_iscsi_info->lock); - rc = qed_cxt_acquire_cid(p_hwfn, PROTOCOLID_ISCSI, &icid); + rc = qed_cxt_acquire_cid(p_hwfn, PROTOCOLID_TCP_ULP, &icid); spin_unlock_bh(&p_hwfn->p_iscsi_info->lock); if (rc) return rc; diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index 49783f365079..286e53927866 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -1037,8 +1037,8 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn, case QED_LL2_TYPE_FCOE: p_ramrod->conn_type = PROTOCOLID_FCOE; break; - case QED_LL2_TYPE_ISCSI: - p_ramrod->conn_type = PROTOCOLID_ISCSI; + case QED_LL2_TYPE_TCP_ULP: + p_ramrod->conn_type = PROTOCOLID_TCP_ULP; break; case QED_LL2_TYPE_ROCE: p_ramrod->conn_type = PROTOCOLID_ROCE; @@ -1048,7 +1048,7 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn, break; case QED_LL2_TYPE_OOO: if (p_hwfn->hw_info.personality == QED_PCI_ISCSI) - p_ramrod->conn_type = PROTOCOLID_ISCSI; + p_ramrod->conn_type = PROTOCOLID_TCP_ULP; else p_ramrod->conn_type = PROTOCOLID_IWARP; break; @@ -2442,7 +2442,7 @@ static int __qed_ll2_start(struct qed_hwfn *p_hwfn, conn_type = QED_LL2_TYPE_FCOE; break; case QED_PCI_ISCSI: - conn_type = QED_LL2_TYPE_ISCSI; + conn_type = QED_LL2_TYPE_TCP_ULP; break; case QED_PCI_ETH_ROCE: conn_type = QED_LL2_TYPE_ROCE; diff --git a/drivers/net/ethernet/qlogic/qed/qed_ooo.c b/drivers/net/ethernet/qlogic/qed/qed_ooo.c index 88353aa404dc..599da0d7366b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ooo.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ooo.c @@ -83,7 +83,7 @@ int qed_ooo_alloc(struct qed_hwfn *p_hwfn) switch (p_hwfn->hw_info.personality) { case QED_PCI_ISCSI: - proto = PROTOCOLID_ISCSI; + proto = PROTOCOLID_TCP_ULP; break; case QED_PCI_ETH_RDMA: case QED_PCI_ETH_IWARP: diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c index aa71adcf31ee..ee7dc0a7da6c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c @@ -385,7 +385,7 @@ int qed_sp_pf_start(struct qed_hwfn *p_hwfn, p_ramrod->personality = PERSONALITY_FCOE; break; case QED_PCI_ISCSI: - p_ramrod->personality = PERSONALITY_ISCSI; + p_ramrod->personality = PERSONALITY_TCP_ULP; break; case QED_PCI_ETH_ROCE: case QED_PCI_ETH_IWARP: diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 977807e1be53..0a3807e927c5 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -702,7 +702,7 @@ enum mf_mode { /* Per-protocol connection types */ enum protocol_type { - PROTOCOLID_ISCSI, + PROTOCOLID_TCP_ULP, PROTOCOLID_FCOE, PROTOCOLID_ROCE, PROTOCOLID_CORE, diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h index ea273ba1c991..ff808d248883 100644 --- a/include/linux/qed/qed_ll2_if.h +++ b/include/linux/qed/qed_ll2_if.h @@ -18,7 +18,7 @@ enum qed_ll2_conn_type { QED_LL2_TYPE_FCOE, - QED_LL2_TYPE_ISCSI, + QED_LL2_TYPE_TCP_ULP, QED_LL2_TYPE_TEST, QED_LL2_TYPE_OOO, QED_LL2_TYPE_RESERVED2, -- cgit v1.2.3-71-gd317 From 897e87a10c35fb37a20886af6f731748d92c1836 Mon Sep 17 00:00:00 2001 From: Shai Malin Date: Wed, 2 Jun 2021 20:16:50 +0300 Subject: qed: Add NVMeTCP Offload PF Level FW and HW HSI This patch introduces the NVMeTCP device and PF level HSI and HSI functionality in order to initialize and interact with the HW device. The patch also adds qed NVMeTCP personality. This patch is based on the qede, qedr, qedi, qedf drivers HSI. Acked-by: Igor Russkikh Signed-off-by: Dean Balandin Signed-off-by: Prabhakar Kushwaha Signed-off-by: Omkar Kulkarni Signed-off-by: Shai Malin Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Reviewed-by: Hannes Reinecke Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/Kconfig | 3 + drivers/net/ethernet/qlogic/qed/Makefile | 2 + drivers/net/ethernet/qlogic/qed/qed.h | 6 + drivers/net/ethernet/qlogic/qed/qed_cxt.c | 27 ++- drivers/net/ethernet/qlogic/qed/qed_dev.c | 48 +++- drivers/net/ethernet/qlogic/qed/qed_hsi.h | 4 +- drivers/net/ethernet/qlogic/qed/qed_ll2.c | 32 ++- drivers/net/ethernet/qlogic/qed/qed_mcp.c | 3 + drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c | 3 +- drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c | 266 ++++++++++++++++++++++ drivers/net/ethernet/qlogic/qed/qed_nvmetcp.h | 51 +++++ drivers/net/ethernet/qlogic/qed/qed_ooo.c | 3 +- drivers/net/ethernet/qlogic/qed/qed_sp.h | 2 + drivers/net/ethernet/qlogic/qed/qed_sp_commands.c | 1 + include/linux/qed/nvmetcp_common.h | 54 +++++ include/linux/qed/qed_if.h | 18 ++ include/linux/qed/qed_nvmetcp_if.h | 71 ++++++ 17 files changed, 572 insertions(+), 22 deletions(-) create mode 100644 drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c create mode 100644 drivers/net/ethernet/qlogic/qed/qed_nvmetcp.h create mode 100644 include/linux/qed/nvmetcp_common.h create mode 100644 include/linux/qed/qed_nvmetcp_if.h (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/Kconfig b/drivers/net/ethernet/qlogic/Kconfig index 6b5ddb07ee83..98f430905ffa 100644 --- a/drivers/net/ethernet/qlogic/Kconfig +++ b/drivers/net/ethernet/qlogic/Kconfig @@ -110,6 +110,9 @@ config QED_RDMA config QED_ISCSI bool +config QED_NVMETCP + bool + config QED_FCOE bool diff --git a/drivers/net/ethernet/qlogic/qed/Makefile b/drivers/net/ethernet/qlogic/qed/Makefile index 8251755ec18c..7cb0db67ba5b 100644 --- a/drivers/net/ethernet/qlogic/qed/Makefile +++ b/drivers/net/ethernet/qlogic/qed/Makefile @@ -28,6 +28,8 @@ qed-$(CONFIG_QED_ISCSI) += qed_iscsi.o qed-$(CONFIG_QED_LL2) += qed_ll2.o qed-$(CONFIG_QED_OOO) += qed_ooo.o +qed-$(CONFIG_QED_NVMETCP) += qed_nvmetcp.o + qed-$(CONFIG_QED_RDMA) += \ qed_iwarp.o \ qed_rdma.o \ diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index a20cb8a0c377..bc9bdb9d1bb9 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -200,6 +200,7 @@ enum qed_pci_personality { QED_PCI_ETH, QED_PCI_FCOE, QED_PCI_ISCSI, + QED_PCI_NVMETCP, QED_PCI_ETH_ROCE, QED_PCI_ETH_IWARP, QED_PCI_ETH_RDMA, @@ -239,6 +240,7 @@ enum QED_FEATURE { QED_PF_L2_QUE, QED_VF, QED_RDMA_CNQ, + QED_NVMETCP_CQ, QED_ISCSI_CQ, QED_FCOE_CQ, QED_VF_L2_QUE, @@ -284,6 +286,8 @@ struct qed_hw_info { ((dev)->hw_info.personality == QED_PCI_FCOE) #define QED_IS_ISCSI_PERSONALITY(dev) \ ((dev)->hw_info.personality == QED_PCI_ISCSI) +#define QED_IS_NVMETCP_PERSONALITY(dev) \ + ((dev)->hw_info.personality == QED_PCI_NVMETCP) /* Resource Allocation scheme results */ u32 resc_start[QED_MAX_RESC]; @@ -592,6 +596,7 @@ struct qed_hwfn { struct qed_ooo_info *p_ooo_info; struct qed_rdma_info *p_rdma_info; struct qed_iscsi_info *p_iscsi_info; + struct qed_nvmetcp_info *p_nvmetcp_info; struct qed_fcoe_info *p_fcoe_info; struct qed_pf_params pf_params; @@ -828,6 +833,7 @@ struct qed_dev { struct qed_eth_cb_ops *eth; struct qed_fcoe_cb_ops *fcoe; struct qed_iscsi_cb_ops *iscsi; + struct qed_nvmetcp_cb_ops *nvmetcp; } protocol_ops; void *ops_cookie; diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index fcabbaa518df..5a0a3cbcc1c1 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -2072,7 +2072,6 @@ int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks) PROTOCOLID_FCOE, p_params->num_cons, 0); - qed_cxt_set_proto_tid_count(p_hwfn, PROTOCOLID_FCOE, QED_CXT_FCOE_TID_SEG, 0, p_params->num_tasks, true); @@ -2093,7 +2092,6 @@ int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks) PROTOCOLID_TCP_ULP, p_params->num_cons, 0); - qed_cxt_set_proto_tid_count(p_hwfn, PROTOCOLID_TCP_ULP, QED_CXT_TCP_ULP_TID_SEG, @@ -2106,6 +2104,29 @@ int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks) } break; } + case QED_PCI_NVMETCP: + { + struct qed_nvmetcp_pf_params *p_params; + + p_params = &p_hwfn->pf_params.nvmetcp_pf_params; + + if (p_params->num_cons && p_params->num_tasks) { + qed_cxt_set_proto_cid_count(p_hwfn, + PROTOCOLID_TCP_ULP, + p_params->num_cons, + 0); + qed_cxt_set_proto_tid_count(p_hwfn, + PROTOCOLID_TCP_ULP, + QED_CXT_TCP_ULP_TID_SEG, + 0, + p_params->num_tasks, + true); + } else { + DP_INFO(p_hwfn->cdev, + "NvmeTCP personality used without setting params!\n"); + } + break; + } default: return -EINVAL; } @@ -2129,6 +2150,7 @@ int qed_cxt_get_tid_mem_info(struct qed_hwfn *p_hwfn, seg = QED_CXT_FCOE_TID_SEG; break; case QED_PCI_ISCSI: + case QED_PCI_NVMETCP: proto = PROTOCOLID_TCP_ULP; seg = QED_CXT_TCP_ULP_TID_SEG; break; @@ -2455,6 +2477,7 @@ int qed_cxt_get_task_ctx(struct qed_hwfn *p_hwfn, seg = QED_CXT_FCOE_TID_SEG; break; case QED_PCI_ISCSI: + case QED_PCI_NVMETCP: proto = PROTOCOLID_TCP_ULP; seg = QED_CXT_TCP_ULP_TID_SEG; break; diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index c231d0e56571..932b892f1ef1 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -37,6 +37,7 @@ #include "qed_sriov.h" #include "qed_vf.h" #include "qed_rdma.h" +#include "qed_nvmetcp.h" static DEFINE_SPINLOCK(qm_lock); @@ -667,7 +668,8 @@ qed_llh_set_engine_affin(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) } /* Storage PF is bound to a single engine while L2 PF uses both */ - if (QED_IS_FCOE_PERSONALITY(p_hwfn) || QED_IS_ISCSI_PERSONALITY(p_hwfn)) + if (QED_IS_FCOE_PERSONALITY(p_hwfn) || QED_IS_ISCSI_PERSONALITY(p_hwfn) || + QED_IS_NVMETCP_PERSONALITY(p_hwfn)) eng = cdev->fir_affin ? QED_ENG1 : QED_ENG0; else /* L2_PERSONALITY */ eng = QED_BOTH_ENG; @@ -1164,6 +1166,9 @@ void qed_llh_remove_mac_filter(struct qed_dev *cdev, if (!test_bit(QED_MF_LLH_MAC_CLSS, &cdev->mf_bits)) goto out; + if (QED_IS_NVMETCP_PERSONALITY(p_hwfn)) + return; + ether_addr_copy(filter.mac.addr, mac_addr); rc = qed_llh_shadow_remove_filter(cdev, ppfid, &filter, &filter_idx, &ref_cnt); @@ -1381,6 +1386,11 @@ void qed_resc_free(struct qed_dev *cdev) qed_ooo_free(p_hwfn); } + if (p_hwfn->hw_info.personality == QED_PCI_NVMETCP) { + qed_nvmetcp_free(p_hwfn); + qed_ooo_free(p_hwfn); + } + if (QED_IS_RDMA_PERSONALITY(p_hwfn) && rdma_info) { qed_spq_unregister_async_cb(p_hwfn, rdma_info->proto); qed_rdma_info_free(p_hwfn); @@ -1423,6 +1433,7 @@ static u32 qed_get_pq_flags(struct qed_hwfn *p_hwfn) flags |= PQ_FLAGS_OFLD; break; case QED_PCI_ISCSI: + case QED_PCI_NVMETCP: flags |= PQ_FLAGS_ACK | PQ_FLAGS_OOO | PQ_FLAGS_OFLD; break; case QED_PCI_ETH_ROCE: @@ -2263,7 +2274,8 @@ int qed_resc_alloc(struct qed_dev *cdev) * at the same time */ n_eqes += num_cons + 2 * MAX_NUM_VFS_BB + n_srq; - } else if (p_hwfn->hw_info.personality == QED_PCI_ISCSI) { + } else if (p_hwfn->hw_info.personality == QED_PCI_ISCSI || + p_hwfn->hw_info.personality == QED_PCI_NVMETCP) { num_cons = qed_cxt_get_proto_cid_count(p_hwfn, PROTOCOLID_TCP_ULP, @@ -2313,6 +2325,15 @@ int qed_resc_alloc(struct qed_dev *cdev) goto alloc_err; } + if (p_hwfn->hw_info.personality == QED_PCI_NVMETCP) { + rc = qed_nvmetcp_alloc(p_hwfn); + if (rc) + goto alloc_err; + rc = qed_ooo_alloc(p_hwfn); + if (rc) + goto alloc_err; + } + if (QED_IS_RDMA_PERSONALITY(p_hwfn)) { rc = qed_rdma_info_alloc(p_hwfn); if (rc) @@ -2393,6 +2414,11 @@ void qed_resc_setup(struct qed_dev *cdev) qed_iscsi_setup(p_hwfn); qed_ooo_setup(p_hwfn); } + + if (p_hwfn->hw_info.personality == QED_PCI_NVMETCP) { + qed_nvmetcp_setup(p_hwfn); + qed_ooo_setup(p_hwfn); + } } } @@ -2854,7 +2880,8 @@ static int qed_hw_init_pf(struct qed_hwfn *p_hwfn, /* Protocol Configuration */ STORE_RT_REG(p_hwfn, PRS_REG_SEARCH_TCP_RT_OFFSET, - (p_hwfn->hw_info.personality == QED_PCI_ISCSI) ? 1 : 0); + ((p_hwfn->hw_info.personality == QED_PCI_ISCSI) || + (p_hwfn->hw_info.personality == QED_PCI_NVMETCP)) ? 1 : 0); STORE_RT_REG(p_hwfn, PRS_REG_SEARCH_FCOE_RT_OFFSET, (p_hwfn->hw_info.personality == QED_PCI_FCOE) ? 1 : 0); STORE_RT_REG(p_hwfn, PRS_REG_SEARCH_ROCE_RT_OFFSET, 0); @@ -3535,14 +3562,21 @@ static void qed_hw_set_feat(struct qed_hwfn *p_hwfn) feat_num[QED_ISCSI_CQ] = min_t(u32, sb_cnt.cnt, RESC_NUM(p_hwfn, QED_CMDQS_CQS)); + + if (QED_IS_NVMETCP_PERSONALITY(p_hwfn)) + feat_num[QED_NVMETCP_CQ] = min_t(u32, sb_cnt.cnt, + RESC_NUM(p_hwfn, + QED_CMDQS_CQS)); + DP_VERBOSE(p_hwfn, NETIF_MSG_PROBE, - "#PF_L2_QUEUES=%d VF_L2_QUEUES=%d #ROCE_CNQ=%d FCOE_CQ=%d ISCSI_CQ=%d #SBS=%d\n", + "#PF_L2_QUEUES=%d VF_L2_QUEUES=%d #ROCE_CNQ=%d FCOE_CQ=%d ISCSI_CQ=%d NVMETCP_CQ=%d #SBS=%d\n", (int)FEAT_NUM(p_hwfn, QED_PF_L2_QUE), (int)FEAT_NUM(p_hwfn, QED_VF_L2_QUE), (int)FEAT_NUM(p_hwfn, QED_RDMA_CNQ), (int)FEAT_NUM(p_hwfn, QED_FCOE_CQ), (int)FEAT_NUM(p_hwfn, QED_ISCSI_CQ), + (int)FEAT_NUM(p_hwfn, QED_NVMETCP_CQ), (int)sb_cnt.cnt); } @@ -3734,7 +3768,8 @@ int qed_hw_get_dflt_resc(struct qed_hwfn *p_hwfn, break; case QED_BDQ: if (p_hwfn->hw_info.personality != QED_PCI_ISCSI && - p_hwfn->hw_info.personality != QED_PCI_FCOE) + p_hwfn->hw_info.personality != QED_PCI_FCOE && + p_hwfn->hw_info.personality != QED_PCI_NVMETCP) *p_resc_num = 0; else *p_resc_num = 1; @@ -3755,7 +3790,8 @@ int qed_hw_get_dflt_resc(struct qed_hwfn *p_hwfn, *p_resc_start = 0; else if (p_hwfn->cdev->num_ports_in_engine == 4) *p_resc_start = p_hwfn->port_id; - else if (p_hwfn->hw_info.personality == QED_PCI_ISCSI) + else if (p_hwfn->hw_info.personality == QED_PCI_ISCSI || + p_hwfn->hw_info.personality == QED_PCI_NVMETCP) *p_resc_start = p_hwfn->port_id; else if (p_hwfn->hw_info.personality == QED_PCI_FCOE) *p_resc_start = p_hwfn->port_id + 2; diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 9dbeb2efdc51..fb1baa2da2d0 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -12147,7 +12148,8 @@ struct public_func { #define FUNC_MF_CFG_PROTOCOL_ISCSI 0x00000010 #define FUNC_MF_CFG_PROTOCOL_FCOE 0x00000020 #define FUNC_MF_CFG_PROTOCOL_ROCE 0x00000030 -#define FUNC_MF_CFG_PROTOCOL_MAX 0x00000030 +#define FUNC_MF_CFG_PROTOCOL_NVMETCP 0x00000040 +#define FUNC_MF_CFG_PROTOCOL_MAX 0x00000040 #define FUNC_MF_CFG_MIN_BW_MASK 0x0000ff00 #define FUNC_MF_CFG_MIN_BW_SHIFT 8 diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index 286e53927866..02a4610d9330 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -960,7 +960,8 @@ static int qed_sp_ll2_rx_queue_start(struct qed_hwfn *p_hwfn, if (test_bit(QED_MF_LL2_NON_UNICAST, &p_hwfn->cdev->mf_bits) && p_ramrod->main_func_queue && conn_type != QED_LL2_TYPE_ROCE && - conn_type != QED_LL2_TYPE_IWARP) { + conn_type != QED_LL2_TYPE_IWARP && + (!QED_IS_NVMETCP_PERSONALITY(p_hwfn))) { p_ramrod->mf_si_bcast_accept_all = 1; p_ramrod->mf_si_mcast_accept_all = 1; } else { @@ -1047,7 +1048,8 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn, p_ramrod->conn_type = PROTOCOLID_IWARP; break; case QED_LL2_TYPE_OOO: - if (p_hwfn->hw_info.personality == QED_PCI_ISCSI) + if (p_hwfn->hw_info.personality == QED_PCI_ISCSI || + p_hwfn->hw_info.personality == QED_PCI_NVMETCP) p_ramrod->conn_type = PROTOCOLID_TCP_ULP; else p_ramrod->conn_type = PROTOCOLID_IWARP; @@ -1634,7 +1636,8 @@ int qed_ll2_establish_connection(void *cxt, u8 connection_handle) if (rc) goto out; - if (!QED_IS_RDMA_PERSONALITY(p_hwfn)) + if (!QED_IS_RDMA_PERSONALITY(p_hwfn) && + !QED_IS_NVMETCP_PERSONALITY(p_hwfn)) qed_wr(p_hwfn, p_ptt, PRS_REG_USE_LIGHT_L2, 1); qed_ll2_establish_connection_ooo(p_hwfn, p_ll2_conn); @@ -2376,7 +2379,8 @@ out: static bool qed_ll2_is_storage_eng1(struct qed_dev *cdev) { return (QED_IS_FCOE_PERSONALITY(QED_LEADING_HWFN(cdev)) || - QED_IS_ISCSI_PERSONALITY(QED_LEADING_HWFN(cdev))) && + QED_IS_ISCSI_PERSONALITY(QED_LEADING_HWFN(cdev)) || + QED_IS_NVMETCP_PERSONALITY(QED_LEADING_HWFN(cdev))) && (QED_AFFIN_HWFN(cdev) != QED_LEADING_HWFN(cdev)); } @@ -2402,11 +2406,13 @@ static int qed_ll2_stop(struct qed_dev *cdev) if (cdev->ll2->handle == QED_LL2_UNUSED_HANDLE) return 0; + if (!QED_IS_NVMETCP_PERSONALITY(p_hwfn)) + qed_llh_remove_mac_filter(cdev, 0, cdev->ll2_mac_address); qed_llh_remove_mac_filter(cdev, 0, cdev->ll2_mac_address); eth_zero_addr(cdev->ll2_mac_address); - if (QED_IS_ISCSI_PERSONALITY(p_hwfn)) + if (QED_IS_ISCSI_PERSONALITY(p_hwfn) || QED_IS_NVMETCP_PERSONALITY(p_hwfn)) qed_ll2_stop_ooo(p_hwfn); /* In CMT mode, LL2 is always started on engine 0 for a storage PF */ @@ -2442,6 +2448,7 @@ static int __qed_ll2_start(struct qed_hwfn *p_hwfn, conn_type = QED_LL2_TYPE_FCOE; break; case QED_PCI_ISCSI: + case QED_PCI_NVMETCP: conn_type = QED_LL2_TYPE_TCP_ULP; break; case QED_PCI_ETH_ROCE: @@ -2567,7 +2574,7 @@ static int qed_ll2_start(struct qed_dev *cdev, struct qed_ll2_params *params) } } - if (QED_IS_ISCSI_PERSONALITY(p_hwfn)) { + if (QED_IS_ISCSI_PERSONALITY(p_hwfn) || QED_IS_NVMETCP_PERSONALITY(p_hwfn)) { DP_VERBOSE(cdev, QED_MSG_STORAGE, "Starting OOO LL2 queue\n"); rc = qed_ll2_start_ooo(p_hwfn, params); if (rc) { @@ -2576,10 +2583,13 @@ static int qed_ll2_start(struct qed_dev *cdev, struct qed_ll2_params *params) } } - rc = qed_llh_add_mac_filter(cdev, 0, params->ll2_mac_address); - if (rc) { - DP_NOTICE(cdev, "Failed to add an LLH filter\n"); - goto err3; + if (!QED_IS_NVMETCP_PERSONALITY(p_hwfn)) { + rc = qed_llh_add_mac_filter(cdev, 0, params->ll2_mac_address); + if (rc) { + DP_NOTICE(cdev, "Failed to add an LLH filter\n"); + goto err3; + } + } ether_addr_copy(cdev->ll2_mac_address, params->ll2_mac_address); @@ -2587,7 +2597,7 @@ static int qed_ll2_start(struct qed_dev *cdev, struct qed_ll2_params *params) return 0; err3: - if (QED_IS_ISCSI_PERSONALITY(p_hwfn)) + if (QED_IS_ISCSI_PERSONALITY(p_hwfn) || QED_IS_NVMETCP_PERSONALITY(p_hwfn)) qed_ll2_stop_ooo(p_hwfn); err2: if (b_is_storage_eng1) diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index cd882c453394..4387292c37e2 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -2446,6 +2446,9 @@ qed_mcp_get_shmem_proto(struct qed_hwfn *p_hwfn, case FUNC_MF_CFG_PROTOCOL_ISCSI: *p_proto = QED_PCI_ISCSI; break; + case FUNC_MF_CFG_PROTOCOL_NVMETCP: + *p_proto = QED_PCI_NVMETCP; + break; case FUNC_MF_CFG_PROTOCOL_FCOE: *p_proto = QED_PCI_FCOE; break; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c b/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c index 3e3192a3ad9b..6190adf965bc 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c @@ -1306,7 +1306,8 @@ int qed_mfw_process_tlv_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) } if ((tlv_group & QED_MFW_TLV_ISCSI) && - p_hwfn->hw_info.personality != QED_PCI_ISCSI) { + p_hwfn->hw_info.personality != QED_PCI_ISCSI && + p_hwfn->hw_info.personality != QED_PCI_NVMETCP) { DP_VERBOSE(p_hwfn, QED_MSG_SP, "Skipping iSCSI TLVs for non-iSCSI function\n"); tlv_group &= ~QED_MFW_TLV_ISCSI; diff --git a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c new file mode 100644 index 000000000000..cb9c71109b2d --- /dev/null +++ b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c @@ -0,0 +1,266 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) +/* Copyright 2021 Marvell. All rights reserved. */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "qed.h" +#include "qed_cxt.h" +#include "qed_dev_api.h" +#include "qed_hsi.h" +#include "qed_hw.h" +#include "qed_int.h" +#include "qed_nvmetcp.h" +#include "qed_ll2.h" +#include "qed_mcp.h" +#include "qed_sp.h" +#include "qed_reg_addr.h" + +static int qed_nvmetcp_async_event(struct qed_hwfn *p_hwfn, u8 fw_event_code, + u16 echo, union event_ring_data *data, + u8 fw_return_code) +{ + if (p_hwfn->p_nvmetcp_info->event_cb) { + struct qed_nvmetcp_info *p_nvmetcp = p_hwfn->p_nvmetcp_info; + + return p_nvmetcp->event_cb(p_nvmetcp->event_context, + fw_event_code, data); + } else { + DP_NOTICE(p_hwfn, "nvmetcp async completion is not set\n"); + + return -EINVAL; + } +} + +static int qed_sp_nvmetcp_func_start(struct qed_hwfn *p_hwfn, + enum spq_mode comp_mode, + struct qed_spq_comp_cb *p_comp_addr, + void *event_context, + nvmetcp_event_cb_t async_event_cb) +{ + struct nvmetcp_init_ramrod_params *p_ramrod = NULL; + struct qed_nvmetcp_pf_params *p_params = NULL; + struct scsi_init_func_queues *p_queue = NULL; + struct nvmetcp_spe_func_init *p_init = NULL; + struct qed_sp_init_data init_data = {}; + struct qed_spq_entry *p_ent = NULL; + int rc = 0; + u16 val; + u8 i; + + /* Get SPQ entry */ + init_data.cid = qed_spq_get_cid(p_hwfn); + init_data.opaque_fid = p_hwfn->hw_info.opaque_fid; + init_data.comp_mode = comp_mode; + init_data.p_comp_data = p_comp_addr; + rc = qed_sp_init_request(p_hwfn, &p_ent, + NVMETCP_RAMROD_CMD_ID_INIT_FUNC, + PROTOCOLID_TCP_ULP, &init_data); + if (rc) + return rc; + + p_ramrod = &p_ent->ramrod.nvmetcp_init; + p_init = &p_ramrod->nvmetcp_init_spe; + p_params = &p_hwfn->pf_params.nvmetcp_pf_params; + p_queue = &p_init->q_params; + p_init->num_sq_pages_in_ring = p_params->num_sq_pages_in_ring; + p_init->num_r2tq_pages_in_ring = p_params->num_r2tq_pages_in_ring; + p_init->num_uhq_pages_in_ring = p_params->num_uhq_pages_in_ring; + p_init->ll2_rx_queue_id = RESC_START(p_hwfn, QED_LL2_RAM_QUEUE) + + p_params->ll2_ooo_queue_id; + SET_FIELD(p_init->flags, NVMETCP_SPE_FUNC_INIT_NVMETCP_MODE, 1); + p_init->func_params.log_page_size = ilog2(PAGE_SIZE); + p_init->func_params.num_tasks = cpu_to_le16(p_params->num_tasks); + p_init->debug_flags = p_params->debug_mode; + DMA_REGPAIR_LE(p_queue->glbl_q_params_addr, + p_params->glbl_q_params_addr); + p_queue->cq_num_entries = cpu_to_le16(QED_NVMETCP_FW_CQ_SIZE); + p_queue->num_queues = p_params->num_queues; + val = RESC_START(p_hwfn, QED_CMDQS_CQS); + p_queue->queue_relative_offset = cpu_to_le16((u16)val); + p_queue->cq_sb_pi = p_params->gl_rq_pi; + + for (i = 0; i < p_params->num_queues; i++) { + val = qed_get_igu_sb_id(p_hwfn, i); + p_queue->cq_cmdq_sb_num_arr[i] = cpu_to_le16(val); + } + + SET_FIELD(p_queue->q_validity, + SCSI_INIT_FUNC_QUEUES_CMD_VALID, 0); + p_queue->cmdq_num_entries = 0; + p_queue->bdq_resource_id = (u8)RESC_START(p_hwfn, QED_BDQ); + p_ramrod->tcp_init.two_msl_timer = cpu_to_le32(QED_TCP_TWO_MSL_TIMER); + p_ramrod->tcp_init.tx_sws_timer = cpu_to_le16(QED_TCP_SWS_TIMER); + p_init->half_way_close_timeout = cpu_to_le16(QED_TCP_HALF_WAY_CLOSE_TIMEOUT); + p_ramrod->tcp_init.max_fin_rt = QED_TCP_MAX_FIN_RT; + SET_FIELD(p_ramrod->nvmetcp_init_spe.params, + NVMETCP_SPE_FUNC_INIT_MAX_SYN_RT, QED_TCP_MAX_FIN_RT); + p_hwfn->p_nvmetcp_info->event_context = event_context; + p_hwfn->p_nvmetcp_info->event_cb = async_event_cb; + qed_spq_register_async_cb(p_hwfn, PROTOCOLID_TCP_ULP, + qed_nvmetcp_async_event); + + return qed_spq_post(p_hwfn, p_ent, NULL); +} + +static int qed_sp_nvmetcp_func_stop(struct qed_hwfn *p_hwfn, + enum spq_mode comp_mode, + struct qed_spq_comp_cb *p_comp_addr) +{ + struct qed_spq_entry *p_ent = NULL; + struct qed_sp_init_data init_data; + int rc; + + /* Get SPQ entry */ + memset(&init_data, 0, sizeof(init_data)); + init_data.cid = qed_spq_get_cid(p_hwfn); + init_data.opaque_fid = p_hwfn->hw_info.opaque_fid; + init_data.comp_mode = comp_mode; + init_data.p_comp_data = p_comp_addr; + rc = qed_sp_init_request(p_hwfn, &p_ent, + NVMETCP_RAMROD_CMD_ID_DESTROY_FUNC, + PROTOCOLID_TCP_ULP, &init_data); + if (rc) + return rc; + + rc = qed_spq_post(p_hwfn, p_ent, NULL); + qed_spq_unregister_async_cb(p_hwfn, PROTOCOLID_TCP_ULP); + + return rc; +} + +static int qed_fill_nvmetcp_dev_info(struct qed_dev *cdev, + struct qed_dev_nvmetcp_info *info) +{ + struct qed_hwfn *hwfn = QED_AFFIN_HWFN(cdev); + int rc; + + memset(info, 0, sizeof(*info)); + rc = qed_fill_dev_info(cdev, &info->common); + info->port_id = MFW_PORT(hwfn); + info->num_cqs = FEAT_NUM(hwfn, QED_NVMETCP_CQ); + + return rc; +} + +static void qed_register_nvmetcp_ops(struct qed_dev *cdev, + struct qed_nvmetcp_cb_ops *ops, + void *cookie) +{ + cdev->protocol_ops.nvmetcp = ops; + cdev->ops_cookie = cookie; +} + +static int qed_nvmetcp_stop(struct qed_dev *cdev) +{ + int rc; + + if (!(cdev->flags & QED_FLAG_STORAGE_STARTED)) { + DP_NOTICE(cdev, "nvmetcp already stopped\n"); + + return 0; + } + + if (!hash_empty(cdev->connections)) { + DP_NOTICE(cdev, + "Can't stop nvmetcp - not all connections were returned\n"); + + return -EINVAL; + } + + /* Stop the nvmetcp */ + rc = qed_sp_nvmetcp_func_stop(QED_AFFIN_HWFN(cdev), QED_SPQ_MODE_EBLOCK, + NULL); + cdev->flags &= ~QED_FLAG_STORAGE_STARTED; + + return rc; +} + +static int qed_nvmetcp_start(struct qed_dev *cdev, + struct qed_nvmetcp_tid *tasks, + void *event_context, + nvmetcp_event_cb_t async_event_cb) +{ + struct qed_tid_mem *tid_info; + int rc; + + if (cdev->flags & QED_FLAG_STORAGE_STARTED) { + DP_NOTICE(cdev, "nvmetcp already started;\n"); + + return 0; + } + + rc = qed_sp_nvmetcp_func_start(QED_AFFIN_HWFN(cdev), + QED_SPQ_MODE_EBLOCK, NULL, + event_context, async_event_cb); + if (rc) { + DP_NOTICE(cdev, "Failed to start nvmetcp\n"); + + return rc; + } + + cdev->flags |= QED_FLAG_STORAGE_STARTED; + hash_init(cdev->connections); + + if (!tasks) + return 0; + + tid_info = kzalloc(sizeof(*tid_info), GFP_KERNEL); + if (!tid_info) { + qed_nvmetcp_stop(cdev); + + return -ENOMEM; + } + + rc = qed_cxt_get_tid_mem_info(QED_AFFIN_HWFN(cdev), tid_info); + if (rc) { + DP_NOTICE(cdev, "Failed to gather task information\n"); + qed_nvmetcp_stop(cdev); + kfree(tid_info); + + return rc; + } + + /* Fill task information */ + tasks->size = tid_info->tid_size; + tasks->num_tids_per_block = tid_info->num_tids_per_block; + memcpy(tasks->blocks, tid_info->blocks, + MAX_TID_BLOCKS_NVMETCP * sizeof(u8 *)); + kfree(tid_info); + + return 0; +} + +static const struct qed_nvmetcp_ops qed_nvmetcp_ops_pass = { + .common = &qed_common_ops_pass, + .ll2 = &qed_ll2_ops_pass, + .fill_dev_info = &qed_fill_nvmetcp_dev_info, + .register_ops = &qed_register_nvmetcp_ops, + .start = &qed_nvmetcp_start, + .stop = &qed_nvmetcp_stop, + + /* Placeholder - Connection level ops */ +}; + +const struct qed_nvmetcp_ops *qed_get_nvmetcp_ops(void) +{ + return &qed_nvmetcp_ops_pass; +} +EXPORT_SYMBOL(qed_get_nvmetcp_ops); + +void qed_put_nvmetcp_ops(void) +{ +} +EXPORT_SYMBOL(qed_put_nvmetcp_ops); diff --git a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.h b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.h new file mode 100644 index 000000000000..774b46ade408 --- /dev/null +++ b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* Copyright 2021 Marvell. All rights reserved. */ + +#ifndef _QED_NVMETCP_H +#define _QED_NVMETCP_H + +#include +#include +#include +#include +#include +#include +#include +#include "qed.h" +#include "qed_hsi.h" +#include "qed_mcp.h" +#include "qed_sp.h" + +#define QED_NVMETCP_FW_CQ_SIZE (4 * 1024) + +/* tcp parameters */ +#define QED_TCP_TWO_MSL_TIMER 4000 +#define QED_TCP_HALF_WAY_CLOSE_TIMEOUT 10 +#define QED_TCP_MAX_FIN_RT 2 +#define QED_TCP_SWS_TIMER 5000 + +struct qed_nvmetcp_info { + spinlock_t lock; /* Connection resources. */ + struct list_head free_list; + u16 max_num_outstanding_tasks; + void *event_context; + nvmetcp_event_cb_t event_cb; +}; + +#if IS_ENABLED(CONFIG_QED_NVMETCP) +int qed_nvmetcp_alloc(struct qed_hwfn *p_hwfn); +void qed_nvmetcp_setup(struct qed_hwfn *p_hwfn); +void qed_nvmetcp_free(struct qed_hwfn *p_hwfn); + +#else /* IS_ENABLED(CONFIG_QED_NVMETCP) */ +static inline int qed_nvmetcp_alloc(struct qed_hwfn *p_hwfn) +{ + return -EINVAL; +} + +static inline void qed_nvmetcp_setup(struct qed_hwfn *p_hwfn) {} +static inline void qed_nvmetcp_free(struct qed_hwfn *p_hwfn) {} + +#endif /* IS_ENABLED(CONFIG_QED_NVMETCP) */ + +#endif diff --git a/drivers/net/ethernet/qlogic/qed/qed_ooo.c b/drivers/net/ethernet/qlogic/qed/qed_ooo.c index 599da0d7366b..b8c5641b29a8 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ooo.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ooo.c @@ -16,7 +16,7 @@ #include "qed_ll2.h" #include "qed_ooo.h" #include "qed_cxt.h" - +#include "qed_nvmetcp.h" static struct qed_ooo_archipelago *qed_ooo_seek_archipelago(struct qed_hwfn *p_hwfn, struct qed_ooo_info @@ -83,6 +83,7 @@ int qed_ooo_alloc(struct qed_hwfn *p_hwfn) switch (p_hwfn->hw_info.personality) { case QED_PCI_ISCSI: + case QED_PCI_NVMETCP: proto = PROTOCOLID_TCP_ULP; break; case QED_PCI_ETH_RDMA: diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h index 993f1357b6fc..525159e747a5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h @@ -100,6 +100,8 @@ union ramrod_data { struct iscsi_spe_conn_mac_update iscsi_conn_mac_update; struct iscsi_spe_conn_termination iscsi_conn_terminate; + struct nvmetcp_init_ramrod_params nvmetcp_init; + struct vf_start_ramrod_data vf_start; struct vf_stop_ramrod_data vf_stop; }; diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c index ee7dc0a7da6c..b4ed54ffef9b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c @@ -385,6 +385,7 @@ int qed_sp_pf_start(struct qed_hwfn *p_hwfn, p_ramrod->personality = PERSONALITY_FCOE; break; case QED_PCI_ISCSI: + case QED_PCI_NVMETCP: p_ramrod->personality = PERSONALITY_TCP_ULP; break; case QED_PCI_ETH_ROCE: diff --git a/include/linux/qed/nvmetcp_common.h b/include/linux/qed/nvmetcp_common.h new file mode 100644 index 000000000000..e9ccfc07041d --- /dev/null +++ b/include/linux/qed/nvmetcp_common.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* Copyright 2021 Marvell. All rights reserved. */ + +#ifndef __NVMETCP_COMMON__ +#define __NVMETCP_COMMON__ + +#include "tcp_common.h" + +/* NVMeTCP firmware function init parameters */ +struct nvmetcp_spe_func_init { + __le16 half_way_close_timeout; + u8 num_sq_pages_in_ring; + u8 num_r2tq_pages_in_ring; + u8 num_uhq_pages_in_ring; + u8 ll2_rx_queue_id; + u8 flags; +#define NVMETCP_SPE_FUNC_INIT_COUNTERS_EN_MASK 0x1 +#define NVMETCP_SPE_FUNC_INIT_COUNTERS_EN_SHIFT 0 +#define NVMETCP_SPE_FUNC_INIT_NVMETCP_MODE_MASK 0x1 +#define NVMETCP_SPE_FUNC_INIT_NVMETCP_MODE_SHIFT 1 +#define NVMETCP_SPE_FUNC_INIT_RESERVED0_MASK 0x3F +#define NVMETCP_SPE_FUNC_INIT_RESERVED0_SHIFT 2 + u8 debug_flags; + __le16 reserved1; + u8 params; +#define NVMETCP_SPE_FUNC_INIT_MAX_SYN_RT_MASK 0xF +#define NVMETCP_SPE_FUNC_INIT_MAX_SYN_RT_SHIFT 0 +#define NVMETCP_SPE_FUNC_INIT_RESERVED1_MASK 0xF +#define NVMETCP_SPE_FUNC_INIT_RESERVED1_SHIFT 4 + u8 reserved2[5]; + struct scsi_init_func_params func_params; + struct scsi_init_func_queues q_params; +}; + +/* NVMeTCP init params passed by driver to FW in NVMeTCP init ramrod. */ +struct nvmetcp_init_ramrod_params { + struct nvmetcp_spe_func_init nvmetcp_init_spe; + struct tcp_init_params tcp_init; +}; + +/* NVMeTCP Ramrod Command IDs */ +enum nvmetcp_ramrod_cmd_id { + NVMETCP_RAMROD_CMD_ID_UNUSED = 0, + NVMETCP_RAMROD_CMD_ID_INIT_FUNC = 1, + NVMETCP_RAMROD_CMD_ID_DESTROY_FUNC = 2, + MAX_NVMETCP_RAMROD_CMD_ID +}; + +struct nvmetcp_glbl_queue_entry { + struct regpair cq_pbl_addr; + struct regpair reserved; +}; + +#endif /* __NVMETCP_COMMON__ */ diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 68d17a4fbf20..850b98991670 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -542,6 +542,22 @@ struct qed_iscsi_pf_params { u8 bdq_pbl_num_entries[3]; }; +struct qed_nvmetcp_pf_params { + u64 glbl_q_params_addr; + u16 cq_num_entries; + u16 num_cons; + u16 num_tasks; + u8 num_sq_pages_in_ring; + u8 num_r2tq_pages_in_ring; + u8 num_uhq_pages_in_ring; + u8 num_queues; + u8 gl_rq_pi; + u8 gl_cmd_pi; + u8 debug_mode; + u8 ll2_ooo_queue_id; + u16 min_rto; +}; + struct qed_rdma_pf_params { /* Supplied to QED during resource allocation (may affect the ILT and * the doorbell BAR). @@ -560,6 +576,7 @@ struct qed_pf_params { struct qed_eth_pf_params eth_pf_params; struct qed_fcoe_pf_params fcoe_pf_params; struct qed_iscsi_pf_params iscsi_pf_params; + struct qed_nvmetcp_pf_params nvmetcp_pf_params; struct qed_rdma_pf_params rdma_pf_params; }; @@ -662,6 +679,7 @@ enum qed_sb_type { enum qed_protocol { QED_PROTOCOL_ETH, QED_PROTOCOL_ISCSI, + QED_PROTOCOL_NVMETCP = QED_PROTOCOL_ISCSI, QED_PROTOCOL_FCOE, }; diff --git a/include/linux/qed/qed_nvmetcp_if.h b/include/linux/qed/qed_nvmetcp_if.h new file mode 100644 index 000000000000..76868bdf0883 --- /dev/null +++ b/include/linux/qed/qed_nvmetcp_if.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* Copyright 2021 Marvell. All rights reserved. */ + +#ifndef _QED_NVMETCP_IF_H +#define _QED_NVMETCP_IF_H +#include +#include + +#define QED_NVMETCP_MAX_IO_SIZE 0x800000 + +typedef int (*nvmetcp_event_cb_t) (void *context, + u8 fw_event_code, void *fw_handle); + +struct qed_dev_nvmetcp_info { + struct qed_dev_info common; + u8 port_id; /* Physical port */ + u8 num_cqs; +}; + +#define MAX_TID_BLOCKS_NVMETCP (512) +struct qed_nvmetcp_tid { + u32 size; /* In bytes per task */ + u32 num_tids_per_block; + u8 *blocks[MAX_TID_BLOCKS_NVMETCP]; +}; + +struct qed_nvmetcp_cb_ops { + struct qed_common_cb_ops common; +}; + +/** + * struct qed_nvmetcp_ops - qed NVMeTCP operations. + * @common: common operations pointer + * @ll2: light L2 operations pointer + * @fill_dev_info: fills NVMeTCP specific information + * @param cdev + * @param info + * @return 0 on success, otherwise error value. + * @register_ops: register nvmetcp operations + * @param cdev + * @param ops - specified using qed_nvmetcp_cb_ops + * @param cookie - driver private + * @start: nvmetcp in FW + * @param cdev + * @param tasks - qed will fill information about tasks + * return 0 on success, otherwise error value. + * @stop: nvmetcp in FW + * @param cdev + * return 0 on success, otherwise error value. + */ +struct qed_nvmetcp_ops { + const struct qed_common_ops *common; + + const struct qed_ll2_ops *ll2; + + int (*fill_dev_info)(struct qed_dev *cdev, + struct qed_dev_nvmetcp_info *info); + + void (*register_ops)(struct qed_dev *cdev, + struct qed_nvmetcp_cb_ops *ops, void *cookie); + + int (*start)(struct qed_dev *cdev, + struct qed_nvmetcp_tid *tasks, + void *event_context, nvmetcp_event_cb_t async_event_cb); + + int (*stop)(struct qed_dev *cdev); +}; + +const struct qed_nvmetcp_ops *qed_get_nvmetcp_ops(void); +void qed_put_nvmetcp_ops(void); +#endif -- cgit v1.2.3-71-gd317 From 76684ab8f4f95394df6a752cee37b197b4c8732b Mon Sep 17 00:00:00 2001 From: Shai Malin Date: Wed, 2 Jun 2021 20:16:51 +0300 Subject: qed: Add NVMeTCP Offload Connection Level FW and HW HSI This patch introduces the NVMeTCP HSI and HSI functionality in order to initialize and interact with the HW device as part of the connection level HSI. This includes: - Connection offload: offload a TCP connection to the FW. - Connection update: update the ICReq-ICResp params - Connection clear SQ: outstanding IOs FW flush. - Connection termination: terminate the TCP connection and flush the FW. Acked-by: Igor Russkikh Signed-off-by: Prabhakar Kushwaha Signed-off-by: Omkar Kulkarni Signed-off-by: Shai Malin Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Reviewed-by: Hannes Reinecke Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c | 557 +++++++++++++++++++++++++- drivers/net/ethernet/qlogic/qed/qed_nvmetcp.h | 52 +++ drivers/net/ethernet/qlogic/qed/qed_sp.h | 3 + include/linux/qed/nvmetcp_common.h | 143 +++++++ include/linux/qed/qed_nvmetcp_if.h | 94 +++++ 5 files changed, 847 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c index cb9c71109b2d..7943804e88cd 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c @@ -243,6 +243,555 @@ static int qed_nvmetcp_start(struct qed_dev *cdev, return 0; } +static struct qed_hash_nvmetcp_con *qed_nvmetcp_get_hash(struct qed_dev *cdev, + u32 handle) +{ + struct qed_hash_nvmetcp_con *hash_con = NULL; + + if (!(cdev->flags & QED_FLAG_STORAGE_STARTED)) + return NULL; + + hash_for_each_possible(cdev->connections, hash_con, node, handle) { + if (hash_con->con->icid == handle) + break; + } + + if (!hash_con || hash_con->con->icid != handle) + return NULL; + + return hash_con; +} + +static int qed_sp_nvmetcp_conn_offload(struct qed_hwfn *p_hwfn, + struct qed_nvmetcp_conn *p_conn, + enum spq_mode comp_mode, + struct qed_spq_comp_cb *p_comp_addr) +{ + struct nvmetcp_spe_conn_offload *p_ramrod = NULL; + struct tcp_offload_params_opt2 *p_tcp = NULL; + struct qed_sp_init_data init_data = { 0 }; + struct qed_spq_entry *p_ent = NULL; + dma_addr_t r2tq_pbl_addr; + dma_addr_t xhq_pbl_addr; + dma_addr_t uhq_pbl_addr; + u16 physical_q; + int rc = 0; + u8 i; + + /* Get SPQ entry */ + init_data.cid = p_conn->icid; + init_data.opaque_fid = p_hwfn->hw_info.opaque_fid; + init_data.comp_mode = comp_mode; + init_data.p_comp_data = p_comp_addr; + rc = qed_sp_init_request(p_hwfn, &p_ent, + NVMETCP_RAMROD_CMD_ID_OFFLOAD_CONN, + PROTOCOLID_TCP_ULP, &init_data); + if (rc) + return rc; + + p_ramrod = &p_ent->ramrod.nvmetcp_conn_offload; + + /* Transmission PQ is the first of the PF */ + physical_q = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD); + p_conn->physical_q0 = cpu_to_le16(physical_q); + p_ramrod->nvmetcp.physical_q0 = cpu_to_le16(physical_q); + + /* nvmetcp Pure-ACK PQ */ + physical_q = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_ACK); + p_conn->physical_q1 = cpu_to_le16(physical_q); + p_ramrod->nvmetcp.physical_q1 = cpu_to_le16(physical_q); + p_ramrod->conn_id = cpu_to_le16(p_conn->conn_id); + DMA_REGPAIR_LE(p_ramrod->nvmetcp.sq_pbl_addr, p_conn->sq_pbl_addr); + r2tq_pbl_addr = qed_chain_get_pbl_phys(&p_conn->r2tq); + DMA_REGPAIR_LE(p_ramrod->nvmetcp.r2tq_pbl_addr, r2tq_pbl_addr); + xhq_pbl_addr = qed_chain_get_pbl_phys(&p_conn->xhq); + DMA_REGPAIR_LE(p_ramrod->nvmetcp.xhq_pbl_addr, xhq_pbl_addr); + uhq_pbl_addr = qed_chain_get_pbl_phys(&p_conn->uhq); + DMA_REGPAIR_LE(p_ramrod->nvmetcp.uhq_pbl_addr, uhq_pbl_addr); + p_ramrod->nvmetcp.flags = p_conn->offl_flags; + p_ramrod->nvmetcp.default_cq = p_conn->default_cq; + p_ramrod->nvmetcp.initial_ack = 0; + DMA_REGPAIR_LE(p_ramrod->nvmetcp.nvmetcp.cccid_itid_table_addr, + p_conn->nvmetcp_cccid_itid_table_addr); + p_ramrod->nvmetcp.nvmetcp.cccid_max_range = + cpu_to_le16(p_conn->nvmetcp_cccid_max_range); + p_tcp = &p_ramrod->tcp; + qed_set_fw_mac_addr(&p_tcp->remote_mac_addr_hi, + &p_tcp->remote_mac_addr_mid, + &p_tcp->remote_mac_addr_lo, p_conn->remote_mac); + qed_set_fw_mac_addr(&p_tcp->local_mac_addr_hi, + &p_tcp->local_mac_addr_mid, + &p_tcp->local_mac_addr_lo, p_conn->local_mac); + p_tcp->vlan_id = cpu_to_le16(p_conn->vlan_id); + p_tcp->flags = cpu_to_le16(p_conn->tcp_flags); + p_tcp->ip_version = p_conn->ip_version; + if (p_tcp->ip_version == TCP_IPV6) { + for (i = 0; i < 4; i++) { + p_tcp->remote_ip[i] = cpu_to_le32(p_conn->remote_ip[i]); + p_tcp->local_ip[i] = cpu_to_le32(p_conn->local_ip[i]); + } + } else { + p_tcp->remote_ip[0] = cpu_to_le32(p_conn->remote_ip[0]); + p_tcp->local_ip[0] = cpu_to_le32(p_conn->local_ip[0]); + } + + p_tcp->flow_label = cpu_to_le32(p_conn->flow_label); + p_tcp->ttl = p_conn->ttl; + p_tcp->tos_or_tc = p_conn->tos_or_tc; + p_tcp->remote_port = cpu_to_le16(p_conn->remote_port); + p_tcp->local_port = cpu_to_le16(p_conn->local_port); + p_tcp->mss = cpu_to_le16(p_conn->mss); + p_tcp->rcv_wnd_scale = p_conn->rcv_wnd_scale; + p_tcp->connect_mode = p_conn->connect_mode; + p_tcp->cwnd = cpu_to_le32(p_conn->cwnd); + p_tcp->ka_max_probe_cnt = p_conn->ka_max_probe_cnt; + p_tcp->ka_timeout = cpu_to_le32(p_conn->ka_timeout); + p_tcp->max_rt_time = cpu_to_le32(p_conn->max_rt_time); + p_tcp->ka_interval = cpu_to_le32(p_conn->ka_interval); + + return qed_spq_post(p_hwfn, p_ent, NULL); +} + +static int qed_sp_nvmetcp_conn_update(struct qed_hwfn *p_hwfn, + struct qed_nvmetcp_conn *p_conn, + enum spq_mode comp_mode, + struct qed_spq_comp_cb *p_comp_addr) +{ + struct nvmetcp_conn_update_ramrod_params *p_ramrod = NULL; + struct qed_spq_entry *p_ent = NULL; + struct qed_sp_init_data init_data; + int rc = -EINVAL; + u32 dval; + + /* Get SPQ entry */ + memset(&init_data, 0, sizeof(init_data)); + init_data.cid = p_conn->icid; + init_data.opaque_fid = p_hwfn->hw_info.opaque_fid; + init_data.comp_mode = comp_mode; + init_data.p_comp_data = p_comp_addr; + + rc = qed_sp_init_request(p_hwfn, &p_ent, + NVMETCP_RAMROD_CMD_ID_UPDATE_CONN, + PROTOCOLID_TCP_ULP, &init_data); + if (rc) + return rc; + + p_ramrod = &p_ent->ramrod.nvmetcp_conn_update; + p_ramrod->conn_id = cpu_to_le16(p_conn->conn_id); + p_ramrod->flags = p_conn->update_flag; + p_ramrod->max_seq_size = cpu_to_le32(p_conn->max_seq_size); + dval = p_conn->max_recv_pdu_length; + p_ramrod->max_recv_pdu_length = cpu_to_le32(dval); + dval = p_conn->max_send_pdu_length; + p_ramrod->max_send_pdu_length = cpu_to_le32(dval); + p_ramrod->first_seq_length = cpu_to_le32(p_conn->first_seq_length); + + return qed_spq_post(p_hwfn, p_ent, NULL); +} + +static int qed_sp_nvmetcp_conn_terminate(struct qed_hwfn *p_hwfn, + struct qed_nvmetcp_conn *p_conn, + enum spq_mode comp_mode, + struct qed_spq_comp_cb *p_comp_addr) +{ + struct nvmetcp_spe_conn_termination *p_ramrod = NULL; + struct qed_spq_entry *p_ent = NULL; + struct qed_sp_init_data init_data; + int rc = -EINVAL; + + /* Get SPQ entry */ + memset(&init_data, 0, sizeof(init_data)); + init_data.cid = p_conn->icid; + init_data.opaque_fid = p_hwfn->hw_info.opaque_fid; + init_data.comp_mode = comp_mode; + init_data.p_comp_data = p_comp_addr; + rc = qed_sp_init_request(p_hwfn, &p_ent, + NVMETCP_RAMROD_CMD_ID_TERMINATION_CONN, + PROTOCOLID_TCP_ULP, &init_data); + if (rc) + return rc; + + p_ramrod = &p_ent->ramrod.nvmetcp_conn_terminate; + p_ramrod->conn_id = cpu_to_le16(p_conn->conn_id); + p_ramrod->abortive = p_conn->abortive_dsconnect; + + return qed_spq_post(p_hwfn, p_ent, NULL); +} + +static int qed_sp_nvmetcp_conn_clear_sq(struct qed_hwfn *p_hwfn, + struct qed_nvmetcp_conn *p_conn, + enum spq_mode comp_mode, + struct qed_spq_comp_cb *p_comp_addr) +{ + struct qed_spq_entry *p_ent = NULL; + struct qed_sp_init_data init_data; + int rc = -EINVAL; + + /* Get SPQ entry */ + memset(&init_data, 0, sizeof(init_data)); + init_data.cid = p_conn->icid; + init_data.opaque_fid = p_hwfn->hw_info.opaque_fid; + init_data.comp_mode = comp_mode; + init_data.p_comp_data = p_comp_addr; + rc = qed_sp_init_request(p_hwfn, &p_ent, + NVMETCP_RAMROD_CMD_ID_CLEAR_SQ, + PROTOCOLID_TCP_ULP, &init_data); + if (rc) + return rc; + + return qed_spq_post(p_hwfn, p_ent, NULL); +} + +static void __iomem *qed_nvmetcp_get_db_addr(struct qed_hwfn *p_hwfn, u32 cid) +{ + return (u8 __iomem *)p_hwfn->doorbells + + qed_db_addr(cid, DQ_DEMS_LEGACY); +} + +static int qed_nvmetcp_allocate_connection(struct qed_hwfn *p_hwfn, + struct qed_nvmetcp_conn **p_out_conn) +{ + struct qed_chain_init_params params = { + .mode = QED_CHAIN_MODE_PBL, + .intended_use = QED_CHAIN_USE_TO_CONSUME_PRODUCE, + .cnt_type = QED_CHAIN_CNT_TYPE_U16, + }; + struct qed_nvmetcp_pf_params *p_params = NULL; + struct qed_nvmetcp_conn *p_conn = NULL; + int rc = 0; + + /* Try finding a free connection that can be used */ + spin_lock_bh(&p_hwfn->p_nvmetcp_info->lock); + if (!list_empty(&p_hwfn->p_nvmetcp_info->free_list)) + p_conn = list_first_entry(&p_hwfn->p_nvmetcp_info->free_list, + struct qed_nvmetcp_conn, list_entry); + if (p_conn) { + list_del(&p_conn->list_entry); + spin_unlock_bh(&p_hwfn->p_nvmetcp_info->lock); + *p_out_conn = p_conn; + + return 0; + } + spin_unlock_bh(&p_hwfn->p_nvmetcp_info->lock); + + /* Need to allocate a new connection */ + p_params = &p_hwfn->pf_params.nvmetcp_pf_params; + p_conn = kzalloc(sizeof(*p_conn), GFP_KERNEL); + if (!p_conn) + return -ENOMEM; + + params.num_elems = p_params->num_r2tq_pages_in_ring * + QED_CHAIN_PAGE_SIZE / sizeof(struct nvmetcp_wqe); + params.elem_size = sizeof(struct nvmetcp_wqe); + rc = qed_chain_alloc(p_hwfn->cdev, &p_conn->r2tq, ¶ms); + if (rc) + goto nomem_r2tq; + + params.num_elems = p_params->num_uhq_pages_in_ring * + QED_CHAIN_PAGE_SIZE / sizeof(struct iscsi_uhqe); + params.elem_size = sizeof(struct iscsi_uhqe); + rc = qed_chain_alloc(p_hwfn->cdev, &p_conn->uhq, ¶ms); + if (rc) + goto nomem_uhq; + + params.elem_size = sizeof(struct iscsi_xhqe); + rc = qed_chain_alloc(p_hwfn->cdev, &p_conn->xhq, ¶ms); + if (rc) + goto nomem; + + p_conn->free_on_delete = true; + *p_out_conn = p_conn; + + return 0; + +nomem: + qed_chain_free(p_hwfn->cdev, &p_conn->uhq); +nomem_uhq: + qed_chain_free(p_hwfn->cdev, &p_conn->r2tq); +nomem_r2tq: + kfree(p_conn); + + return -ENOMEM; +} + +static int qed_nvmetcp_acquire_connection(struct qed_hwfn *p_hwfn, + struct qed_nvmetcp_conn **p_out_conn) +{ + struct qed_nvmetcp_conn *p_conn = NULL; + int rc = 0; + u32 icid; + + spin_lock_bh(&p_hwfn->p_nvmetcp_info->lock); + rc = qed_cxt_acquire_cid(p_hwfn, PROTOCOLID_TCP_ULP, &icid); + spin_unlock_bh(&p_hwfn->p_nvmetcp_info->lock); + + if (rc) + return rc; + + rc = qed_nvmetcp_allocate_connection(p_hwfn, &p_conn); + if (rc) { + spin_lock_bh(&p_hwfn->p_nvmetcp_info->lock); + qed_cxt_release_cid(p_hwfn, icid); + spin_unlock_bh(&p_hwfn->p_nvmetcp_info->lock); + + return rc; + } + + p_conn->icid = icid; + p_conn->conn_id = (u16)icid; + p_conn->fw_cid = (p_hwfn->hw_info.opaque_fid << 16) | icid; + *p_out_conn = p_conn; + + return rc; +} + +static void qed_nvmetcp_release_connection(struct qed_hwfn *p_hwfn, + struct qed_nvmetcp_conn *p_conn) +{ + spin_lock_bh(&p_hwfn->p_nvmetcp_info->lock); + list_add_tail(&p_conn->list_entry, &p_hwfn->p_nvmetcp_info->free_list); + qed_cxt_release_cid(p_hwfn, p_conn->icid); + spin_unlock_bh(&p_hwfn->p_nvmetcp_info->lock); +} + +static void qed_nvmetcp_free_connection(struct qed_hwfn *p_hwfn, + struct qed_nvmetcp_conn *p_conn) +{ + qed_chain_free(p_hwfn->cdev, &p_conn->xhq); + qed_chain_free(p_hwfn->cdev, &p_conn->uhq); + qed_chain_free(p_hwfn->cdev, &p_conn->r2tq); + kfree(p_conn); +} + +int qed_nvmetcp_alloc(struct qed_hwfn *p_hwfn) +{ + struct qed_nvmetcp_info *p_nvmetcp_info; + + p_nvmetcp_info = kzalloc(sizeof(*p_nvmetcp_info), GFP_KERNEL); + if (!p_nvmetcp_info) + return -ENOMEM; + + INIT_LIST_HEAD(&p_nvmetcp_info->free_list); + p_hwfn->p_nvmetcp_info = p_nvmetcp_info; + + return 0; +} + +void qed_nvmetcp_setup(struct qed_hwfn *p_hwfn) +{ + spin_lock_init(&p_hwfn->p_nvmetcp_info->lock); +} + +void qed_nvmetcp_free(struct qed_hwfn *p_hwfn) +{ + struct qed_nvmetcp_conn *p_conn = NULL; + + if (!p_hwfn->p_nvmetcp_info) + return; + + while (!list_empty(&p_hwfn->p_nvmetcp_info->free_list)) { + p_conn = list_first_entry(&p_hwfn->p_nvmetcp_info->free_list, + struct qed_nvmetcp_conn, list_entry); + if (p_conn) { + list_del(&p_conn->list_entry); + qed_nvmetcp_free_connection(p_hwfn, p_conn); + } + } + + kfree(p_hwfn->p_nvmetcp_info); + p_hwfn->p_nvmetcp_info = NULL; +} + +static int qed_nvmetcp_acquire_conn(struct qed_dev *cdev, + u32 *handle, + u32 *fw_cid, void __iomem **p_doorbell) +{ + struct qed_hash_nvmetcp_con *hash_con; + int rc; + + /* Allocate a hashed connection */ + hash_con = kzalloc(sizeof(*hash_con), GFP_ATOMIC); + if (!hash_con) + return -ENOMEM; + + /* Acquire the connection */ + rc = qed_nvmetcp_acquire_connection(QED_AFFIN_HWFN(cdev), + &hash_con->con); + if (rc) { + DP_NOTICE(cdev, "Failed to acquire Connection\n"); + kfree(hash_con); + + return rc; + } + + /* Added the connection to hash table */ + *handle = hash_con->con->icid; + *fw_cid = hash_con->con->fw_cid; + hash_add(cdev->connections, &hash_con->node, *handle); + if (p_doorbell) + *p_doorbell = qed_nvmetcp_get_db_addr(QED_AFFIN_HWFN(cdev), + *handle); + + return 0; +} + +static int qed_nvmetcp_release_conn(struct qed_dev *cdev, u32 handle) +{ + struct qed_hash_nvmetcp_con *hash_con; + + hash_con = qed_nvmetcp_get_hash(cdev, handle); + if (!hash_con) { + DP_NOTICE(cdev, "Failed to find connection for handle %d\n", + handle); + + return -EINVAL; + } + + hlist_del(&hash_con->node); + qed_nvmetcp_release_connection(QED_AFFIN_HWFN(cdev), hash_con->con); + kfree(hash_con); + + return 0; +} + +static int qed_nvmetcp_offload_conn(struct qed_dev *cdev, u32 handle, + struct qed_nvmetcp_params_offload *conn_info) +{ + struct qed_hash_nvmetcp_con *hash_con; + struct qed_nvmetcp_conn *con; + + hash_con = qed_nvmetcp_get_hash(cdev, handle); + if (!hash_con) { + DP_NOTICE(cdev, "Failed to find connection for handle %d\n", + handle); + + return -EINVAL; + } + + /* Update the connection with information from the params */ + con = hash_con->con; + + /* FW initializations */ + con->layer_code = NVMETCP_SLOW_PATH_LAYER_CODE; + con->sq_pbl_addr = conn_info->sq_pbl_addr; + con->nvmetcp_cccid_max_range = conn_info->nvmetcp_cccid_max_range; + con->nvmetcp_cccid_itid_table_addr = conn_info->nvmetcp_cccid_itid_table_addr; + con->default_cq = conn_info->default_cq; + SET_FIELD(con->offl_flags, NVMETCP_CONN_OFFLOAD_PARAMS_TARGET_MODE, 0); + SET_FIELD(con->offl_flags, NVMETCP_CONN_OFFLOAD_PARAMS_NVMETCP_MODE, 1); + SET_FIELD(con->offl_flags, NVMETCP_CONN_OFFLOAD_PARAMS_TCP_ON_CHIP_1B, 1); + + /* Networking and TCP stack initializations */ + ether_addr_copy(con->local_mac, conn_info->src.mac); + ether_addr_copy(con->remote_mac, conn_info->dst.mac); + memcpy(con->local_ip, conn_info->src.ip, sizeof(con->local_ip)); + memcpy(con->remote_ip, conn_info->dst.ip, sizeof(con->remote_ip)); + con->local_port = conn_info->src.port; + con->remote_port = conn_info->dst.port; + con->vlan_id = conn_info->vlan_id; + + if (conn_info->timestamp_en) + SET_FIELD(con->tcp_flags, TCP_OFFLOAD_PARAMS_OPT2_TS_EN, 1); + + if (conn_info->delayed_ack_en) + SET_FIELD(con->tcp_flags, TCP_OFFLOAD_PARAMS_OPT2_DA_EN, 1); + + if (conn_info->tcp_keep_alive_en) + SET_FIELD(con->tcp_flags, TCP_OFFLOAD_PARAMS_OPT2_KA_EN, 1); + + if (conn_info->ecn_en) + SET_FIELD(con->tcp_flags, TCP_OFFLOAD_PARAMS_OPT2_ECN_EN, 1); + + con->ip_version = conn_info->ip_version; + con->flow_label = QED_TCP_FLOW_LABEL; + con->ka_max_probe_cnt = conn_info->ka_max_probe_cnt; + con->ka_timeout = conn_info->ka_timeout; + con->ka_interval = conn_info->ka_interval; + con->max_rt_time = conn_info->max_rt_time; + con->ttl = conn_info->ttl; + con->tos_or_tc = conn_info->tos_or_tc; + con->mss = conn_info->mss; + con->cwnd = conn_info->cwnd; + con->rcv_wnd_scale = conn_info->rcv_wnd_scale; + con->connect_mode = 0; + + return qed_sp_nvmetcp_conn_offload(QED_AFFIN_HWFN(cdev), con, + QED_SPQ_MODE_EBLOCK, NULL); +} + +static int qed_nvmetcp_update_conn(struct qed_dev *cdev, + u32 handle, + struct qed_nvmetcp_params_update *conn_info) +{ + struct qed_hash_nvmetcp_con *hash_con; + struct qed_nvmetcp_conn *con; + + hash_con = qed_nvmetcp_get_hash(cdev, handle); + if (!hash_con) { + DP_NOTICE(cdev, "Failed to find connection for handle %d\n", + handle); + + return -EINVAL; + } + + /* Update the connection with information from the params */ + con = hash_con->con; + SET_FIELD(con->update_flag, + ISCSI_CONN_UPDATE_RAMROD_PARAMS_INITIAL_R2T, 0); + SET_FIELD(con->update_flag, + ISCSI_CONN_UPDATE_RAMROD_PARAMS_IMMEDIATE_DATA, 1); + if (conn_info->hdr_digest_en) + SET_FIELD(con->update_flag, ISCSI_CONN_UPDATE_RAMROD_PARAMS_HD_EN, 1); + + if (conn_info->data_digest_en) + SET_FIELD(con->update_flag, ISCSI_CONN_UPDATE_RAMROD_PARAMS_DD_EN, 1); + + /* Placeholder - initialize pfv, cpda, hpda */ + + con->max_seq_size = conn_info->max_io_size; + con->max_recv_pdu_length = conn_info->max_recv_pdu_length; + con->max_send_pdu_length = conn_info->max_send_pdu_length; + con->first_seq_length = conn_info->max_io_size; + + return qed_sp_nvmetcp_conn_update(QED_AFFIN_HWFN(cdev), con, + QED_SPQ_MODE_EBLOCK, NULL); +} + +static int qed_nvmetcp_clear_conn_sq(struct qed_dev *cdev, u32 handle) +{ + struct qed_hash_nvmetcp_con *hash_con; + + hash_con = qed_nvmetcp_get_hash(cdev, handle); + if (!hash_con) { + DP_NOTICE(cdev, "Failed to find connection for handle %d\n", + handle); + + return -EINVAL; + } + + return qed_sp_nvmetcp_conn_clear_sq(QED_AFFIN_HWFN(cdev), hash_con->con, + QED_SPQ_MODE_EBLOCK, NULL); +} + +static int qed_nvmetcp_destroy_conn(struct qed_dev *cdev, + u32 handle, u8 abrt_conn) +{ + struct qed_hash_nvmetcp_con *hash_con; + + hash_con = qed_nvmetcp_get_hash(cdev, handle); + if (!hash_con) { + DP_NOTICE(cdev, "Failed to find connection for handle %d\n", + handle); + + return -EINVAL; + } + + hash_con->con->abortive_dsconnect = abrt_conn; + + return qed_sp_nvmetcp_conn_terminate(QED_AFFIN_HWFN(cdev), hash_con->con, + QED_SPQ_MODE_EBLOCK, NULL); +} + static const struct qed_nvmetcp_ops qed_nvmetcp_ops_pass = { .common = &qed_common_ops_pass, .ll2 = &qed_ll2_ops_pass, @@ -250,8 +799,12 @@ static const struct qed_nvmetcp_ops qed_nvmetcp_ops_pass = { .register_ops = &qed_register_nvmetcp_ops, .start = &qed_nvmetcp_start, .stop = &qed_nvmetcp_stop, - - /* Placeholder - Connection level ops */ + .acquire_conn = &qed_nvmetcp_acquire_conn, + .release_conn = &qed_nvmetcp_release_conn, + .offload_conn = &qed_nvmetcp_offload_conn, + .update_conn = &qed_nvmetcp_update_conn, + .destroy_conn = &qed_nvmetcp_destroy_conn, + .clear_sq = &qed_nvmetcp_clear_conn_sq, }; const struct qed_nvmetcp_ops *qed_get_nvmetcp_ops(void) diff --git a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.h b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.h index 774b46ade408..e5e9d075bf4f 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.h @@ -19,6 +19,7 @@ #define QED_NVMETCP_FW_CQ_SIZE (4 * 1024) /* tcp parameters */ +#define QED_TCP_FLOW_LABEL 0 #define QED_TCP_TWO_MSL_TIMER 4000 #define QED_TCP_HALF_WAY_CLOSE_TIMEOUT 10 #define QED_TCP_MAX_FIN_RT 2 @@ -32,6 +33,57 @@ struct qed_nvmetcp_info { nvmetcp_event_cb_t event_cb; }; +struct qed_hash_nvmetcp_con { + struct hlist_node node; + struct qed_nvmetcp_conn *con; +}; + +struct qed_nvmetcp_conn { + struct list_head list_entry; + bool free_on_delete; + u16 conn_id; + u32 icid; + u32 fw_cid; + u8 layer_code; + u8 offl_flags; + u8 connect_mode; + dma_addr_t sq_pbl_addr; + struct qed_chain r2tq; + struct qed_chain xhq; + struct qed_chain uhq; + u8 local_mac[6]; + u8 remote_mac[6]; + u8 ip_version; + u8 ka_max_probe_cnt; + u16 vlan_id; + u16 tcp_flags; + u32 remote_ip[4]; + u32 local_ip[4]; + u32 flow_label; + u32 ka_timeout; + u32 ka_interval; + u32 max_rt_time; + u8 ttl; + u8 tos_or_tc; + u16 remote_port; + u16 local_port; + u16 mss; + u8 rcv_wnd_scale; + u32 rcv_wnd; + u32 cwnd; + u8 update_flag; + u8 default_cq; + u8 abortive_dsconnect; + u32 max_seq_size; + u32 max_recv_pdu_length; + u32 max_send_pdu_length; + u32 first_seq_length; + u16 physical_q0; + u16 physical_q1; + u16 nvmetcp_cccid_max_range; + dma_addr_t nvmetcp_cccid_itid_table_addr; +}; + #if IS_ENABLED(CONFIG_QED_NVMETCP) int qed_nvmetcp_alloc(struct qed_hwfn *p_hwfn); void qed_nvmetcp_setup(struct qed_hwfn *p_hwfn); diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h index 525159e747a5..60ff3222bf55 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h @@ -101,6 +101,9 @@ union ramrod_data { struct iscsi_spe_conn_termination iscsi_conn_terminate; struct nvmetcp_init_ramrod_params nvmetcp_init; + struct nvmetcp_spe_conn_offload nvmetcp_conn_offload; + struct nvmetcp_conn_update_ramrod_params nvmetcp_conn_update; + struct nvmetcp_spe_conn_termination nvmetcp_conn_terminate; struct vf_start_ramrod_data vf_start; struct vf_stop_ramrod_data vf_stop; diff --git a/include/linux/qed/nvmetcp_common.h b/include/linux/qed/nvmetcp_common.h index e9ccfc07041d..c8836b71b866 100644 --- a/include/linux/qed/nvmetcp_common.h +++ b/include/linux/qed/nvmetcp_common.h @@ -6,6 +6,8 @@ #include "tcp_common.h" +#define NVMETCP_SLOW_PATH_LAYER_CODE (6) + /* NVMeTCP firmware function init parameters */ struct nvmetcp_spe_func_init { __le16 half_way_close_timeout; @@ -43,6 +45,10 @@ enum nvmetcp_ramrod_cmd_id { NVMETCP_RAMROD_CMD_ID_UNUSED = 0, NVMETCP_RAMROD_CMD_ID_INIT_FUNC = 1, NVMETCP_RAMROD_CMD_ID_DESTROY_FUNC = 2, + NVMETCP_RAMROD_CMD_ID_OFFLOAD_CONN = 3, + NVMETCP_RAMROD_CMD_ID_UPDATE_CONN = 4, + NVMETCP_RAMROD_CMD_ID_TERMINATION_CONN = 5, + NVMETCP_RAMROD_CMD_ID_CLEAR_SQ = 6, MAX_NVMETCP_RAMROD_CMD_ID }; @@ -51,4 +57,141 @@ struct nvmetcp_glbl_queue_entry { struct regpair reserved; }; +/* NVMeTCP conn level EQEs */ +enum nvmetcp_eqe_opcode { + NVMETCP_EVENT_TYPE_INIT_FUNC = 0, /* Response after init Ramrod */ + NVMETCP_EVENT_TYPE_DESTROY_FUNC, /* Response after destroy Ramrod */ + NVMETCP_EVENT_TYPE_OFFLOAD_CONN,/* Response after option 2 offload Ramrod */ + NVMETCP_EVENT_TYPE_UPDATE_CONN, /* Response after update Ramrod */ + NVMETCP_EVENT_TYPE_CLEAR_SQ, /* Response after clear sq Ramrod */ + NVMETCP_EVENT_TYPE_TERMINATE_CONN, /* Response after termination Ramrod */ + NVMETCP_EVENT_TYPE_RESERVED0, + NVMETCP_EVENT_TYPE_RESERVED1, + NVMETCP_EVENT_TYPE_ASYN_CONNECT_COMPLETE, /* Connect completed (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_TERMINATE_DONE, /* Termination completed (A-syn EQE) */ + NVMETCP_EVENT_TYPE_START_OF_ERROR_TYPES = 10, /* Separate EQs from err EQs */ + NVMETCP_EVENT_TYPE_ASYN_ABORT_RCVD, /* TCP RST packet receive (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_CLOSE_RCVD, /* TCP FIN packet receive (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_SYN_RCVD, /* TCP SYN+ACK packet receive (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_MAX_RT_TIME, /* TCP max retransmit time (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_MAX_RT_CNT, /* TCP max retransmit count (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_MAX_KA_PROBES_CNT, /* TCP ka probes count (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_FIN_WAIT2, /* TCP fin wait 2 (A-syn EQE) */ + NVMETCP_EVENT_TYPE_NVMETCP_CONN_ERROR, /* NVMeTCP error response (A-syn EQE) */ + NVMETCP_EVENT_TYPE_TCP_CONN_ERROR, /* NVMeTCP error - tcp error (A-syn EQE) */ + MAX_NVMETCP_EQE_OPCODE +}; + +struct nvmetcp_conn_offload_section { + struct regpair cccid_itid_table_addr; /* CCCID to iTID table address */ + __le16 cccid_max_range; /* CCCID max value - used for validation */ + __le16 reserved[3]; +}; + +/* NVMe TCP connection offload params passed by driver to FW in NVMeTCP offload ramrod */ +struct nvmetcp_conn_offload_params { + struct regpair sq_pbl_addr; + struct regpair r2tq_pbl_addr; + struct regpair xhq_pbl_addr; + struct regpair uhq_pbl_addr; + __le16 physical_q0; + __le16 physical_q1; + u8 flags; +#define NVMETCP_CONN_OFFLOAD_PARAMS_TCP_ON_CHIP_1B_MASK 0x1 +#define NVMETCP_CONN_OFFLOAD_PARAMS_TCP_ON_CHIP_1B_SHIFT 0 +#define NVMETCP_CONN_OFFLOAD_PARAMS_TARGET_MODE_MASK 0x1 +#define NVMETCP_CONN_OFFLOAD_PARAMS_TARGET_MODE_SHIFT 1 +#define NVMETCP_CONN_OFFLOAD_PARAMS_RESTRICTED_MODE_MASK 0x1 +#define NVMETCP_CONN_OFFLOAD_PARAMS_RESTRICTED_MODE_SHIFT 2 +#define NVMETCP_CONN_OFFLOAD_PARAMS_NVMETCP_MODE_MASK 0x1 +#define NVMETCP_CONN_OFFLOAD_PARAMS_NVMETCP_MODE_SHIFT 3 +#define NVMETCP_CONN_OFFLOAD_PARAMS_RESERVED1_MASK 0xF +#define NVMETCP_CONN_OFFLOAD_PARAMS_RESERVED1_SHIFT 4 + u8 default_cq; + __le16 reserved0; + __le32 reserved1; + __le32 initial_ack; + + struct nvmetcp_conn_offload_section nvmetcp; /* NVMe/TCP section */ +}; + +/* NVMe TCP and TCP connection offload params passed by driver to FW in NVMeTCP offload ramrod. */ +struct nvmetcp_spe_conn_offload { + __le16 reserved; + __le16 conn_id; + __le32 fw_cid; + struct nvmetcp_conn_offload_params nvmetcp; + struct tcp_offload_params_opt2 tcp; +}; + +/* NVMeTCP connection update params passed by driver to FW in NVMETCP update ramrod. */ +struct nvmetcp_conn_update_ramrod_params { + __le16 reserved0; + __le16 conn_id; + __le32 reserved1; + u8 flags; +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_HD_EN_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_HD_EN_SHIFT 0 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_DD_EN_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_DD_EN_SHIFT 1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED0_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED0_SHIFT 2 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_DATA_SHIFT 3 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED2_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED2_SHIFT 4 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED3_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED3_SHIFT 5 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED4_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED4_SHIFT 6 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED5_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED5_SHIFT 7 + u8 reserved3[3]; + __le32 max_seq_size; + __le32 max_send_pdu_length; + __le32 max_recv_pdu_length; + __le32 first_seq_length; + __le32 reserved4[5]; +}; + +/* NVMeTCP connection termination request */ +struct nvmetcp_spe_conn_termination { + __le16 reserved0; + __le16 conn_id; + __le32 reserved1; + u8 abortive; + u8 reserved2[7]; + struct regpair reserved3; + struct regpair reserved4; +}; + +struct nvmetcp_dif_flags { + u8 flags; +}; + +enum nvmetcp_wqe_type { + NVMETCP_WQE_TYPE_NORMAL, + NVMETCP_WQE_TYPE_TASK_CLEANUP, + NVMETCP_WQE_TYPE_MIDDLE_PATH, + NVMETCP_WQE_TYPE_IC, + MAX_NVMETCP_WQE_TYPE +}; + +struct nvmetcp_wqe { + __le16 task_id; + u8 flags; +#define NVMETCP_WQE_WQE_TYPE_MASK 0x7 /* [use nvmetcp_wqe_type] */ +#define NVMETCP_WQE_WQE_TYPE_SHIFT 0 +#define NVMETCP_WQE_NUM_SGES_MASK 0xF +#define NVMETCP_WQE_NUM_SGES_SHIFT 3 +#define NVMETCP_WQE_RESPONSE_MASK 0x1 +#define NVMETCP_WQE_RESPONSE_SHIFT 7 + struct nvmetcp_dif_flags prot_flags; + __le32 contlen_cdbsize; +#define NVMETCP_WQE_CONT_LEN_MASK 0xFFFFFF +#define NVMETCP_WQE_CONT_LEN_SHIFT 0 +#define NVMETCP_WQE_CDB_SIZE_OR_NVMETCP_CMD_MASK 0xFF +#define NVMETCP_WQE_CDB_SIZE_OR_NVMETCP_CMD_SHIFT 24 +}; + #endif /* __NVMETCP_COMMON__ */ diff --git a/include/linux/qed/qed_nvmetcp_if.h b/include/linux/qed/qed_nvmetcp_if.h index 76868bdf0883..5baf1c5ce798 100644 --- a/include/linux/qed/qed_nvmetcp_if.h +++ b/include/linux/qed/qed_nvmetcp_if.h @@ -24,6 +24,50 @@ struct qed_nvmetcp_tid { u8 *blocks[MAX_TID_BLOCKS_NVMETCP]; }; +struct qed_nvmetcp_id_params { + u8 mac[ETH_ALEN]; + u32 ip[4]; + u16 port; +}; + +struct qed_nvmetcp_params_offload { + /* FW initializations */ + dma_addr_t sq_pbl_addr; + dma_addr_t nvmetcp_cccid_itid_table_addr; + u16 nvmetcp_cccid_max_range; + u8 default_cq; + + /* Networking and TCP stack initializations */ + struct qed_nvmetcp_id_params src; + struct qed_nvmetcp_id_params dst; + u32 ka_timeout; + u32 ka_interval; + u32 max_rt_time; + u32 cwnd; + u16 mss; + u16 vlan_id; + bool timestamp_en; + bool delayed_ack_en; + bool tcp_keep_alive_en; + bool ecn_en; + u8 ip_version; + u8 ka_max_probe_cnt; + u8 ttl; + u8 tos_or_tc; + u8 rcv_wnd_scale; +}; + +struct qed_nvmetcp_params_update { + u32 max_io_size; + u32 max_recv_pdu_length; + u32 max_send_pdu_length; + + /* Placeholder: pfv, cpda, hpda */ + + bool hdr_digest_en; + bool data_digest_en; +}; + struct qed_nvmetcp_cb_ops { struct qed_common_cb_ops common; }; @@ -47,6 +91,38 @@ struct qed_nvmetcp_cb_ops { * @stop: nvmetcp in FW * @param cdev * return 0 on success, otherwise error value. + * @acquire_conn: acquire a new nvmetcp connection + * @param cdev + * @param handle - qed will fill handle that should be + * used henceforth as identifier of the + * connection. + * @param p_doorbell - qed will fill the address of the + * doorbell. + * @return 0 on sucesss, otherwise error value. + * @release_conn: release a previously acquired nvmetcp connection + * @param cdev + * @param handle - the connection handle. + * @return 0 on success, otherwise error value. + * @offload_conn: configures an offloaded connection + * @param cdev + * @param handle - the connection handle. + * @param conn_info - the configuration to use for the + * offload. + * @return 0 on success, otherwise error value. + * @update_conn: updates an offloaded connection + * @param cdev + * @param handle - the connection handle. + * @param conn_info - the configuration to use for the + * offload. + * @return 0 on success, otherwise error value. + * @destroy_conn: stops an offloaded connection + * @param cdev + * @param handle - the connection handle. + * @return 0 on success, otherwise error value. + * @clear_sq: clear all task in sq + * @param cdev + * @param handle - the connection handle. + * @return 0 on success, otherwise error value. */ struct qed_nvmetcp_ops { const struct qed_common_ops *common; @@ -64,6 +140,24 @@ struct qed_nvmetcp_ops { void *event_context, nvmetcp_event_cb_t async_event_cb); int (*stop)(struct qed_dev *cdev); + + int (*acquire_conn)(struct qed_dev *cdev, + u32 *handle, + u32 *fw_cid, void __iomem **p_doorbell); + + int (*release_conn)(struct qed_dev *cdev, u32 handle); + + int (*offload_conn)(struct qed_dev *cdev, + u32 handle, + struct qed_nvmetcp_params_offload *conn_info); + + int (*update_conn)(struct qed_dev *cdev, + u32 handle, + struct qed_nvmetcp_params_update *conn_info); + + int (*destroy_conn)(struct qed_dev *cdev, u32 handle, u8 abrt_conn); + + int (*clear_sq)(struct qed_dev *cdev, u32 handle); }; const struct qed_nvmetcp_ops *qed_get_nvmetcp_ops(void); -- cgit v1.2.3-71-gd317 From 203d136e8958a7c65834601f669bdd0fcaa6fcbd Mon Sep 17 00:00:00 2001 From: Prabhakar Kushwaha Date: Wed, 2 Jun 2021 20:16:52 +0300 Subject: qed: Add support of HW filter block This patch introduces the functionality of HW filter block. It adds and removes filters based on source and target TCP port. It also add functionality to clear all filters at once. Acked-by: Igor Russkikh Signed-off-by: Prabhakar Kushwaha Signed-off-by: Omkar Kulkarni Signed-off-by: Shai Malin Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Reviewed-by: Hannes Reinecke Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed.h | 8 +++ drivers/net/ethernet/qlogic/qed/qed_dev.c | 90 +++++++++++++++++++++++++++ drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c | 5 ++ include/linux/qed/qed_nvmetcp_if.h | 24 +++++++ 4 files changed, 127 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index bc9bdb9d1bb9..b590c70539b5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -49,6 +49,8 @@ extern const struct qed_common_ops qed_common_ops_pass; #define QED_MIN_WIDS (4) #define QED_PF_DEMS_SIZE (4) +#define QED_LLH_DONT_CARE 0 + /* cau states */ enum qed_coalescing_mode { QED_COAL_MODE_DISABLE, @@ -1005,4 +1007,10 @@ int qed_mfw_fill_tlv_data(struct qed_hwfn *hwfn, void qed_hw_info_set_offload_tc(struct qed_hw_info *p_info, u8 tc); void qed_periodic_db_rec_start(struct qed_hwfn *p_hwfn); + +int qed_llh_add_src_tcp_port_filter(struct qed_dev *cdev, u16 src_port); +int qed_llh_add_dst_tcp_port_filter(struct qed_dev *cdev, u16 dest_port); +void qed_llh_remove_src_tcp_port_filter(struct qed_dev *cdev, u16 src_port); +void qed_llh_remove_dst_tcp_port_filter(struct qed_dev *cdev, u16 src_port); +void qed_llh_clear_all_filters(struct qed_dev *cdev); #endif /* _QED_H */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 932b892f1ef1..0410c3604abd 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -5362,3 +5362,93 @@ void qed_set_fw_mac_addr(__le16 *fw_msb, ((u8 *)fw_lsb)[0] = mac[5]; ((u8 *)fw_lsb)[1] = mac[4]; } + +static int qed_llh_shadow_remove_all_filters(struct qed_dev *cdev, u8 ppfid) +{ + struct qed_llh_info *p_llh_info = cdev->p_llh_info; + struct qed_llh_filter_info *p_filters; + int rc; + + rc = qed_llh_shadow_sanity(cdev, ppfid, 0, "remove_all"); + if (rc) + return rc; + + p_filters = p_llh_info->pp_filters[ppfid]; + memset(p_filters, 0, NIG_REG_LLH_FUNC_FILTER_EN_SIZE * + sizeof(*p_filters)); + + return 0; +} + +static void qed_llh_clear_ppfid_filters(struct qed_dev *cdev, u8 ppfid) +{ + struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev); + struct qed_ptt *p_ptt = qed_ptt_acquire(p_hwfn); + u8 filter_idx, abs_ppfid; + int rc = 0; + + if (!p_ptt) + return; + + if (!test_bit(QED_MF_LLH_PROTO_CLSS, &cdev->mf_bits) && + !test_bit(QED_MF_LLH_MAC_CLSS, &cdev->mf_bits)) + goto out; + + rc = qed_llh_abs_ppfid(cdev, ppfid, &abs_ppfid); + if (rc) + goto out; + + rc = qed_llh_shadow_remove_all_filters(cdev, ppfid); + if (rc) + goto out; + + for (filter_idx = 0; filter_idx < NIG_REG_LLH_FUNC_FILTER_EN_SIZE; + filter_idx++) { + rc = qed_llh_remove_filter(p_hwfn, p_ptt, + abs_ppfid, filter_idx); + if (rc) + goto out; + } +out: + qed_ptt_release(p_hwfn, p_ptt); +} + +int qed_llh_add_src_tcp_port_filter(struct qed_dev *cdev, u16 src_port) +{ + return qed_llh_add_protocol_filter(cdev, 0, + QED_LLH_FILTER_TCP_SRC_PORT, + src_port, QED_LLH_DONT_CARE); +} + +void qed_llh_remove_src_tcp_port_filter(struct qed_dev *cdev, u16 src_port) +{ + qed_llh_remove_protocol_filter(cdev, 0, + QED_LLH_FILTER_TCP_SRC_PORT, + src_port, QED_LLH_DONT_CARE); +} + +int qed_llh_add_dst_tcp_port_filter(struct qed_dev *cdev, u16 dest_port) +{ + return qed_llh_add_protocol_filter(cdev, 0, + QED_LLH_FILTER_TCP_DEST_PORT, + QED_LLH_DONT_CARE, dest_port); +} + +void qed_llh_remove_dst_tcp_port_filter(struct qed_dev *cdev, u16 dest_port) +{ + qed_llh_remove_protocol_filter(cdev, 0, + QED_LLH_FILTER_TCP_DEST_PORT, + QED_LLH_DONT_CARE, dest_port); +} + +void qed_llh_clear_all_filters(struct qed_dev *cdev) +{ + u8 ppfid; + + if (!test_bit(QED_MF_LLH_PROTO_CLSS, &cdev->mf_bits) && + !test_bit(QED_MF_LLH_MAC_CLSS, &cdev->mf_bits)) + return; + + for (ppfid = 0; ppfid < cdev->p_llh_info->num_ppfid; ppfid++) + qed_llh_clear_ppfid_filters(cdev, ppfid); +} diff --git a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c index 7943804e88cd..d4d609a4d3a3 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c @@ -805,6 +805,11 @@ static const struct qed_nvmetcp_ops qed_nvmetcp_ops_pass = { .update_conn = &qed_nvmetcp_update_conn, .destroy_conn = &qed_nvmetcp_destroy_conn, .clear_sq = &qed_nvmetcp_clear_conn_sq, + .add_src_tcp_port_filter = &qed_llh_add_src_tcp_port_filter, + .remove_src_tcp_port_filter = &qed_llh_remove_src_tcp_port_filter, + .add_dst_tcp_port_filter = &qed_llh_add_dst_tcp_port_filter, + .remove_dst_tcp_port_filter = &qed_llh_remove_dst_tcp_port_filter, + .clear_all_filters = &qed_llh_clear_all_filters }; const struct qed_nvmetcp_ops *qed_get_nvmetcp_ops(void) diff --git a/include/linux/qed/qed_nvmetcp_if.h b/include/linux/qed/qed_nvmetcp_if.h index 5baf1c5ce798..5180edad24e5 100644 --- a/include/linux/qed/qed_nvmetcp_if.h +++ b/include/linux/qed/qed_nvmetcp_if.h @@ -123,6 +123,20 @@ struct qed_nvmetcp_cb_ops { * @param cdev * @param handle - the connection handle. * @return 0 on success, otherwise error value. + * @add_src_tcp_port_filter: Add source tcp port filter + * @param cdev + * @param src_port + * @remove_src_tcp_port_filter: Remove source tcp port filter + * @param cdev + * @param src_port + * @add_dst_tcp_port_filter: Add destination tcp port filter + * @param cdev + * @param dest_port + * @remove_dst_tcp_port_filter: Remove destination tcp port filter + * @param cdev + * @param dest_port + * @clear_all_filters: Clear all filters. + * @param cdev */ struct qed_nvmetcp_ops { const struct qed_common_ops *common; @@ -158,6 +172,16 @@ struct qed_nvmetcp_ops { int (*destroy_conn)(struct qed_dev *cdev, u32 handle, u8 abrt_conn); int (*clear_sq)(struct qed_dev *cdev, u32 handle); + + int (*add_src_tcp_port_filter)(struct qed_dev *cdev, u16 src_port); + + void (*remove_src_tcp_port_filter)(struct qed_dev *cdev, u16 src_port); + + int (*add_dst_tcp_port_filter)(struct qed_dev *cdev, u16 dest_port); + + void (*remove_dst_tcp_port_filter)(struct qed_dev *cdev, u16 dest_port); + + void (*clear_all_filters)(struct qed_dev *cdev); }; const struct qed_nvmetcp_ops *qed_get_nvmetcp_ops(void); -- cgit v1.2.3-71-gd317 From ab47bdfd2e2e9670172a737d12ebfc94bf9d299d Mon Sep 17 00:00:00 2001 From: Shai Malin Date: Wed, 2 Jun 2021 20:16:53 +0300 Subject: qed: Add NVMeTCP Offload IO Level FW and HW HSI This patch introduces the NVMeTCP Offload FW and HW HSI in order to initialize the IO level configuration into a per IO HW resource ("task") as part of the IO path flow. Acked-by: Igor Russkikh Signed-off-by: Prabhakar Kushwaha Signed-off-by: Omkar Kulkarni Signed-off-by: Shai Malin Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Reviewed-by: Hannes Reinecke Signed-off-by: David S. Miller --- include/linux/qed/nvmetcp_common.h | 335 ++++++++++++++++++++++++++++++++++++- include/linux/qed/qed_nvmetcp_if.h | 31 ++++ 2 files changed, 365 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/qed/nvmetcp_common.h b/include/linux/qed/nvmetcp_common.h index c8836b71b866..ad745a9c2264 100644 --- a/include/linux/qed/nvmetcp_common.h +++ b/include/linux/qed/nvmetcp_common.h @@ -7,6 +7,7 @@ #include "tcp_common.h" #define NVMETCP_SLOW_PATH_LAYER_CODE (6) +#define NVMETCP_WQE_NUM_SGES_SLOWIO (0xf) /* NVMeTCP firmware function init parameters */ struct nvmetcp_spe_func_init { @@ -194,4 +195,336 @@ struct nvmetcp_wqe { #define NVMETCP_WQE_CDB_SIZE_OR_NVMETCP_CMD_SHIFT 24 }; -#endif /* __NVMETCP_COMMON__ */ +struct nvmetcp_host_cccid_itid_entry { + __le16 itid; +}; + +struct nvmetcp_connect_done_results { + __le16 icid; + __le16 conn_id; + struct tcp_ulp_connect_done_params params; +}; + +struct nvmetcp_eqe_data { + __le16 icid; + __le16 conn_id; + __le16 reserved; + u8 error_code; + u8 error_pdu_opcode_reserved; +#define NVMETCP_EQE_DATA_ERROR_PDU_OPCODE_MASK 0x3F +#define NVMETCP_EQE_DATA_ERROR_PDU_OPCODE_SHIFT 0 +#define NVMETCP_EQE_DATA_ERROR_PDU_OPCODE_VALID_MASK 0x1 +#define NVMETCP_EQE_DATA_ERROR_PDU_OPCODE_VALID_SHIFT 6 +#define NVMETCP_EQE_DATA_RESERVED0_MASK 0x1 +#define NVMETCP_EQE_DATA_RESERVED0_SHIFT 7 +}; + +enum nvmetcp_task_type { + NVMETCP_TASK_TYPE_HOST_WRITE, + NVMETCP_TASK_TYPE_HOST_READ, + NVMETCP_TASK_TYPE_INIT_CONN_REQUEST, + NVMETCP_TASK_TYPE_RESERVED0, + NVMETCP_TASK_TYPE_CLEANUP, + NVMETCP_TASK_TYPE_HOST_READ_NO_CQE, + MAX_NVMETCP_TASK_TYPE +}; + +struct nvmetcp_db_data { + u8 params; +#define NVMETCP_DB_DATA_DEST_MASK 0x3 /* destination of doorbell (use enum db_dest) */ +#define NVMETCP_DB_DATA_DEST_SHIFT 0 +#define NVMETCP_DB_DATA_AGG_CMD_MASK 0x3 /* aggregative command to CM (use enum db_agg_cmd_sel) */ +#define NVMETCP_DB_DATA_AGG_CMD_SHIFT 2 +#define NVMETCP_DB_DATA_BYPASS_EN_MASK 0x1 /* enable QM bypass */ +#define NVMETCP_DB_DATA_BYPASS_EN_SHIFT 4 +#define NVMETCP_DB_DATA_RESERVED_MASK 0x1 +#define NVMETCP_DB_DATA_RESERVED_SHIFT 5 +#define NVMETCP_DB_DATA_AGG_VAL_SEL_MASK 0x3 /* aggregative value selection */ +#define NVMETCP_DB_DATA_AGG_VAL_SEL_SHIFT 6 + u8 agg_flags; /* bit for every DQ counter flags in CM context that DQ can increment */ + __le16 sq_prod; +}; + +struct nvmetcp_fw_nvmf_cqe { + __le32 reserved[4]; +}; + +struct nvmetcp_icresp_mdata { + u8 digest; + u8 cpda; + __le16 pfv; + __le32 maxdata; + __le16 rsvd[4]; +}; + +union nvmetcp_fw_cqe_data { + struct nvmetcp_fw_nvmf_cqe nvme_cqe; + struct nvmetcp_icresp_mdata icresp_mdata; +}; + +struct nvmetcp_fw_cqe { + __le16 conn_id; + u8 cqe_type; + u8 cqe_error_status_bits; +#define CQE_ERROR_BITMAP_DIF_ERR_BITS_MASK 0x7 +#define CQE_ERROR_BITMAP_DIF_ERR_BITS_SHIFT 0 +#define CQE_ERROR_BITMAP_DATA_DIGEST_ERR_MASK 0x1 +#define CQE_ERROR_BITMAP_DATA_DIGEST_ERR_SHIFT 3 +#define CQE_ERROR_BITMAP_RCV_ON_INVALID_CONN_MASK 0x1 +#define CQE_ERROR_BITMAP_RCV_ON_INVALID_CONN_SHIFT 4 + __le16 itid; + u8 task_type; + u8 fw_dbg_field; + u8 caused_conn_err; + u8 reserved0[3]; + __le32 reserved1; + union nvmetcp_fw_cqe_data cqe_data; + struct regpair task_opaque; + __le32 reserved[6]; +}; + +enum nvmetcp_fw_cqes_type { + NVMETCP_FW_CQE_TYPE_NORMAL = 1, + NVMETCP_FW_CQE_TYPE_RESERVED0, + NVMETCP_FW_CQE_TYPE_RESERVED1, + NVMETCP_FW_CQE_TYPE_CLEANUP, + NVMETCP_FW_CQE_TYPE_DUMMY, + MAX_NVMETCP_FW_CQES_TYPE +}; + +struct ystorm_nvmetcp_task_state { + struct scsi_cached_sges data_desc; + struct scsi_sgl_params sgl_params; + __le32 resrved0; + __le32 buffer_offset; + __le16 cccid; + struct nvmetcp_dif_flags dif_flags; + u8 flags; +#define YSTORM_NVMETCP_TASK_STATE_LOCAL_COMP_MASK 0x1 +#define YSTORM_NVMETCP_TASK_STATE_LOCAL_COMP_SHIFT 0 +#define YSTORM_NVMETCP_TASK_STATE_SLOW_IO_MASK 0x1 +#define YSTORM_NVMETCP_TASK_STATE_SLOW_IO_SHIFT 1 +#define YSTORM_NVMETCP_TASK_STATE_SET_DIF_OFFSET_MASK 0x1 +#define YSTORM_NVMETCP_TASK_STATE_SET_DIF_OFFSET_SHIFT 2 +#define YSTORM_NVMETCP_TASK_STATE_SEND_W_RSP_MASK 0x1 +#define YSTORM_NVMETCP_TASK_STATE_SEND_W_RSP_SHIFT 3 +}; + +struct ystorm_nvmetcp_task_rxmit_opt { + __le32 reserved[4]; +}; + +struct nvmetcp_task_hdr { + __le32 reg[18]; +}; + +struct nvmetcp_task_hdr_aligned { + struct nvmetcp_task_hdr task_hdr; + __le32 reserved[2]; /* HSI_COMMENT: Align to QREG */ +}; + +struct e5_tdif_task_context { + __le32 reserved[16]; +}; + +struct e5_rdif_task_context { + __le32 reserved[12]; +}; + +struct ystorm_nvmetcp_task_st_ctx { + struct ystorm_nvmetcp_task_state state; + struct ystorm_nvmetcp_task_rxmit_opt rxmit_opt; + struct nvmetcp_task_hdr_aligned pdu_hdr; +}; + +struct mstorm_nvmetcp_task_st_ctx { + struct scsi_cached_sges data_desc; + struct scsi_sgl_params sgl_params; + __le32 rem_task_size; + __le32 data_buffer_offset; + u8 task_type; + struct nvmetcp_dif_flags dif_flags; + __le16 dif_task_icid; + struct regpair reserved0; + __le32 expected_itt; + __le32 reserved1; +}; + +struct ustorm_nvmetcp_task_st_ctx { + __le32 rem_rcv_len; + __le32 exp_data_transfer_len; + __le32 exp_data_sn; + struct regpair reserved0; + __le32 reg1_map; +#define REG1_NUM_SGES_MASK 0xF +#define REG1_NUM_SGES_SHIFT 0 +#define REG1_RESERVED1_MASK 0xFFFFFFF +#define REG1_RESERVED1_SHIFT 4 + u8 flags2; +#define USTORM_NVMETCP_TASK_ST_CTX_AHS_EXIST_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_AHS_EXIST_SHIFT 0 +#define USTORM_NVMETCP_TASK_ST_CTX_RESERVED1_MASK 0x7F +#define USTORM_NVMETCP_TASK_ST_CTX_RESERVED1_SHIFT 1 + struct nvmetcp_dif_flags dif_flags; + __le16 reserved3; + __le16 tqe_opaque[2]; + __le32 reserved5; + __le32 nvme_tcp_opaque_lo; + __le32 nvme_tcp_opaque_hi; + u8 task_type; + u8 error_flags; +#define USTORM_NVMETCP_TASK_ST_CTX_DATA_DIGEST_ERROR_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_DATA_DIGEST_ERROR_SHIFT 0 +#define USTORM_NVMETCP_TASK_ST_CTX_DATA_TRUNCATED_ERROR_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_DATA_TRUNCATED_ERROR_SHIFT 1 +#define USTORM_NVMETCP_TASK_ST_CTX_UNDER_RUN_ERROR_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_UNDER_RUN_ERROR_SHIFT 2 +#define USTORM_NVMETCP_TASK_ST_CTX_NVME_TCP_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_NVME_TCP_SHIFT 3 + u8 flags; +#define USTORM_NVMETCP_TASK_ST_CTX_CQE_WRITE_MASK 0x3 +#define USTORM_NVMETCP_TASK_ST_CTX_CQE_WRITE_SHIFT 0 +#define USTORM_NVMETCP_TASK_ST_CTX_LOCAL_COMP_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_LOCAL_COMP_SHIFT 2 +#define USTORM_NVMETCP_TASK_ST_CTX_Q0_R2TQE_WRITE_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_Q0_R2TQE_WRITE_SHIFT 3 +#define USTORM_NVMETCP_TASK_ST_CTX_TOTAL_DATA_ACKED_DONE_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_TOTAL_DATA_ACKED_DONE_SHIFT 4 +#define USTORM_NVMETCP_TASK_ST_CTX_HQ_SCANNED_DONE_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_HQ_SCANNED_DONE_SHIFT 5 +#define USTORM_NVMETCP_TASK_ST_CTX_R2T2RECV_DONE_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_R2T2RECV_DONE_SHIFT 6 + u8 cq_rss_number; +}; + +struct e5_ystorm_nvmetcp_task_ag_ctx { + u8 reserved /* cdu_validation */; + u8 byte1 /* state_and_core_id */; + __le16 word0 /* icid */; + u8 flags0; + u8 flags1; + u8 flags2; + u8 flags3; + __le32 TTT; + u8 byte2; + u8 byte3; + u8 byte4; + u8 e4_reserved7; +}; + +struct e5_mstorm_nvmetcp_task_ag_ctx { + u8 cdu_validation; + u8 byte1; + __le16 task_cid; + u8 flags0; +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_MASK 0x1 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_SHIFT 5 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_VALID_MASK 0x1 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_VALID_SHIFT 6 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_FLAG_MASK 0x1 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_FLAG_SHIFT 7 + u8 flags1; +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_CF_MASK 0x3 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_CF_SHIFT 0 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF1_MASK 0x3 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF1_SHIFT 2 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF2_MASK 0x3 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF2_SHIFT 4 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_CF_EN_MASK 0x1 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_CF_EN_SHIFT 6 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF1EN_MASK 0x1 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF1EN_SHIFT 7 + u8 flags2; + u8 flags3; + __le32 reg0; + u8 byte2; + u8 byte3; + u8 byte4; + u8 e4_reserved7; +}; + +struct e5_ustorm_nvmetcp_task_ag_ctx { + u8 reserved; + u8 state_and_core_id; + __le16 icid; + u8 flags0; +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_SHIFT 5 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_HQ_SCANNED_CF_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_HQ_SCANNED_CF_SHIFT 6 + u8 flags1; +#define E5_USTORM_NVMETCP_TASK_AG_CTX_RESERVED1_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_RESERVED1_SHIFT 0 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_R2T2RECV_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_R2T2RECV_SHIFT 2 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CF3_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CF3_SHIFT 4 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_CF_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_CF_SHIFT 6 + u8 flags2; +#define E5_USTORM_NVMETCP_TASK_AG_CTX_HQ_SCANNED_CF_EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_HQ_SCANNED_CF_EN_SHIFT 0 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DISABLE_DATA_ACKED_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DISABLE_DATA_ACKED_SHIFT 1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_R2T2RECV_EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_R2T2RECV_EN_SHIFT 2 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CF3EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CF3EN_SHIFT 3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_CF_EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_CF_EN_SHIFT 4 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CMP_DATA_TOTAL_EXP_EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CMP_DATA_TOTAL_EXP_EN_SHIFT 5 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_RULE1EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_RULE1EN_SHIFT 6 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CMP_CONT_RCV_EXP_EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CMP_CONT_RCV_EXP_EN_SHIFT 7 + u8 flags3; + u8 flags4; +#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED5_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED5_SHIFT 0 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED6_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED6_SHIFT 2 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED7_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED7_SHIFT 3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_TYPE_MASK 0xF +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_TYPE_SHIFT 4 + u8 byte2; + u8 byte3; + u8 e4_reserved8; + __le32 dif_err_intervals; + __le32 dif_error_1st_interval; + __le32 rcv_cont_len; + __le32 exp_cont_len; + __le32 total_data_acked; + __le32 exp_data_acked; + __le16 word1; + __le16 next_tid; + __le32 hdr_residual_count; + __le32 exp_r2t_sn; +}; + +struct e5_nvmetcp_task_context { + struct ystorm_nvmetcp_task_st_ctx ystorm_st_context; + struct e5_ystorm_nvmetcp_task_ag_ctx ystorm_ag_context; + struct regpair ystorm_ag_padding[2]; + struct e5_tdif_task_context tdif_context; + struct e5_mstorm_nvmetcp_task_ag_ctx mstorm_ag_context; + struct regpair mstorm_ag_padding[2]; + struct e5_ustorm_nvmetcp_task_ag_ctx ustorm_ag_context; + struct regpair ustorm_ag_padding[2]; + struct mstorm_nvmetcp_task_st_ctx mstorm_st_context; + struct regpair mstorm_st_padding[2]; + struct ustorm_nvmetcp_task_st_ctx ustorm_st_context; + struct regpair ustorm_st_padding[2]; + struct e5_rdif_task_context rdif_context; +}; + +#endif /* __NVMETCP_COMMON__*/ diff --git a/include/linux/qed/qed_nvmetcp_if.h b/include/linux/qed/qed_nvmetcp_if.h index 5180edad24e5..606427ebb63c 100644 --- a/include/linux/qed/qed_nvmetcp_if.h +++ b/include/linux/qed/qed_nvmetcp_if.h @@ -5,6 +5,8 @@ #define _QED_NVMETCP_IF_H #include #include +#include +#include #define QED_NVMETCP_MAX_IO_SIZE 0x800000 @@ -72,6 +74,35 @@ struct qed_nvmetcp_cb_ops { struct qed_common_cb_ops common; }; +struct nvmetcp_sge { + struct regpair sge_addr; /* SGE address */ + __le32 sge_len; /* SGE length */ + __le32 reserved; +}; + +/* IO path HSI function SGL params */ +struct storage_sgl_task_params { + struct nvmetcp_sge *sgl; + struct regpair sgl_phys_addr; + u32 total_buffer_size; + u16 num_sges; + bool small_mid_sge; +}; + +/* IO path HSI function FW task context params */ +struct nvmetcp_task_params { + void *context; /* Output parameter - set/filled by the HSI function */ + struct nvmetcp_wqe *sqe; + u32 tx_io_size; /* in bytes (Without DIF, if exists) */ + u32 rx_io_size; /* in bytes (Without DIF, if exists) */ + u16 conn_icid; + u16 itid; + struct regpair opq; /* qedn_task_ctx address */ + u16 host_cccid; + u8 cq_rss_number; + bool send_write_incapsule; +}; + /** * struct qed_nvmetcp_ops - qed NVMeTCP operations. * @common: common operations pointer -- cgit v1.2.3-71-gd317 From 826da4861430898495fa49f072335e795e8adfd3 Mon Sep 17 00:00:00 2001 From: Shai Malin Date: Wed, 2 Jun 2021 20:16:54 +0300 Subject: qed: Add NVMeTCP Offload IO Level FW Initializations This patch introduces the NVMeTCP FW initializations which is used to initialize the IO level configuration into a per IO HW resource ("task") as part of the IO path flow. This includes: - Write IO FW initialization - Read IO FW initialization. - IC-Req and IC-Resp FW exchange. - FW Cleanup flow (Flush IO). Acked-by: Igor Russkikh Signed-off-by: Prabhakar Kushwaha Signed-off-by: Omkar Kulkarni Signed-off-by: Shai Malin Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Reviewed-by: Hannes Reinecke Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/Makefile | 5 +- drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c | 7 +- .../net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.c | 376 +++++++++++++++++++++ .../net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.h | 40 +++ include/linux/qed/nvmetcp_common.h | 1 + include/linux/qed/qed_nvmetcp_if.h | 20 ++ 6 files changed, 447 insertions(+), 2 deletions(-) create mode 100644 drivers/net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.c create mode 100644 drivers/net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.h (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/Makefile b/drivers/net/ethernet/qlogic/qed/Makefile index 7cb0db67ba5b..0d9c2fe0245d 100644 --- a/drivers/net/ethernet/qlogic/qed/Makefile +++ b/drivers/net/ethernet/qlogic/qed/Makefile @@ -28,7 +28,10 @@ qed-$(CONFIG_QED_ISCSI) += qed_iscsi.o qed-$(CONFIG_QED_LL2) += qed_ll2.o qed-$(CONFIG_QED_OOO) += qed_ooo.o -qed-$(CONFIG_QED_NVMETCP) += qed_nvmetcp.o +qed-$(CONFIG_QED_NVMETCP) += \ + qed_nvmetcp.o \ + qed_nvmetcp_fw_funcs.o \ + qed_nvmetcp_ip_services.o qed-$(CONFIG_QED_RDMA) += \ qed_iwarp.o \ diff --git a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c index d4d609a4d3a3..f19128c8d9cc 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c @@ -27,6 +27,7 @@ #include "qed_mcp.h" #include "qed_sp.h" #include "qed_reg_addr.h" +#include "qed_nvmetcp_fw_funcs.h" static int qed_nvmetcp_async_event(struct qed_hwfn *p_hwfn, u8 fw_event_code, u16 echo, union event_ring_data *data, @@ -809,7 +810,11 @@ static const struct qed_nvmetcp_ops qed_nvmetcp_ops_pass = { .remove_src_tcp_port_filter = &qed_llh_remove_src_tcp_port_filter, .add_dst_tcp_port_filter = &qed_llh_add_dst_tcp_port_filter, .remove_dst_tcp_port_filter = &qed_llh_remove_dst_tcp_port_filter, - .clear_all_filters = &qed_llh_clear_all_filters + .clear_all_filters = &qed_llh_clear_all_filters, + .init_read_io = &init_nvmetcp_host_read_task, + .init_write_io = &init_nvmetcp_host_write_task, + .init_icreq_exchange = &init_nvmetcp_init_conn_req_task, + .init_task_cleanup = &init_cleanup_task_nvmetcp }; const struct qed_nvmetcp_ops *qed_get_nvmetcp_ops(void) diff --git a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.c new file mode 100644 index 000000000000..c1dd71d19f3f --- /dev/null +++ b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.c @@ -0,0 +1,376 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) +/* Copyright 2021 Marvell. All rights reserved. */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "qed_nvmetcp_fw_funcs.h" + +#define NVMETCP_NUM_SGES_IN_CACHE 0x4 + +bool nvmetcp_is_slow_sgl(u16 num_sges, bool small_mid_sge) +{ + return (num_sges > SCSI_NUM_SGES_SLOW_SGL_THR && small_mid_sge); +} + +void init_scsi_sgl_context(struct scsi_sgl_params *ctx_sgl_params, + struct scsi_cached_sges *ctx_data_desc, + struct storage_sgl_task_params *sgl_params) +{ + u8 num_sges_to_init = (u8)(sgl_params->num_sges > NVMETCP_NUM_SGES_IN_CACHE ? + NVMETCP_NUM_SGES_IN_CACHE : sgl_params->num_sges); + u8 sge_index; + + /* sgl params */ + ctx_sgl_params->sgl_addr.lo = cpu_to_le32(sgl_params->sgl_phys_addr.lo); + ctx_sgl_params->sgl_addr.hi = cpu_to_le32(sgl_params->sgl_phys_addr.hi); + ctx_sgl_params->sgl_total_length = cpu_to_le32(sgl_params->total_buffer_size); + ctx_sgl_params->sgl_num_sges = cpu_to_le16(sgl_params->num_sges); + + for (sge_index = 0; sge_index < num_sges_to_init; sge_index++) { + ctx_data_desc->sge[sge_index].sge_addr.lo = + cpu_to_le32(sgl_params->sgl[sge_index].sge_addr.lo); + ctx_data_desc->sge[sge_index].sge_addr.hi = + cpu_to_le32(sgl_params->sgl[sge_index].sge_addr.hi); + ctx_data_desc->sge[sge_index].sge_len = + cpu_to_le32(sgl_params->sgl[sge_index].sge_len); + } +} + +static inline u32 calc_rw_task_size(struct nvmetcp_task_params *task_params, + enum nvmetcp_task_type task_type) +{ + u32 io_size; + + if (task_type == NVMETCP_TASK_TYPE_HOST_WRITE) + io_size = task_params->tx_io_size; + else + io_size = task_params->rx_io_size; + + if (unlikely(!io_size)) + return 0; + + return io_size; +} + +static inline void init_sqe(struct nvmetcp_task_params *task_params, + struct storage_sgl_task_params *sgl_task_params, + enum nvmetcp_task_type task_type) +{ + if (!task_params->sqe) + return; + + memset(task_params->sqe, 0, sizeof(*task_params->sqe)); + task_params->sqe->task_id = cpu_to_le16(task_params->itid); + + switch (task_type) { + case NVMETCP_TASK_TYPE_HOST_WRITE: { + u32 buf_size = 0; + u32 num_sges = 0; + + SET_FIELD(task_params->sqe->contlen_cdbsize, + NVMETCP_WQE_CDB_SIZE_OR_NVMETCP_CMD, 1); + SET_FIELD(task_params->sqe->flags, NVMETCP_WQE_WQE_TYPE, + NVMETCP_WQE_TYPE_NORMAL); + if (task_params->tx_io_size) { + if (task_params->send_write_incapsule) + buf_size = calc_rw_task_size(task_params, task_type); + + if (nvmetcp_is_slow_sgl(sgl_task_params->num_sges, + sgl_task_params->small_mid_sge)) + num_sges = NVMETCP_WQE_NUM_SGES_SLOWIO; + else + num_sges = min((u16)sgl_task_params->num_sges, + (u16)SCSI_NUM_SGES_SLOW_SGL_THR); + } + SET_FIELD(task_params->sqe->flags, NVMETCP_WQE_NUM_SGES, num_sges); + SET_FIELD(task_params->sqe->contlen_cdbsize, NVMETCP_WQE_CONT_LEN, buf_size); + } break; + + case NVMETCP_TASK_TYPE_HOST_READ: { + SET_FIELD(task_params->sqe->flags, NVMETCP_WQE_WQE_TYPE, + NVMETCP_WQE_TYPE_NORMAL); + SET_FIELD(task_params->sqe->contlen_cdbsize, + NVMETCP_WQE_CDB_SIZE_OR_NVMETCP_CMD, 1); + } break; + + case NVMETCP_TASK_TYPE_INIT_CONN_REQUEST: { + SET_FIELD(task_params->sqe->flags, NVMETCP_WQE_WQE_TYPE, + NVMETCP_WQE_TYPE_MIDDLE_PATH); + + if (task_params->tx_io_size) { + SET_FIELD(task_params->sqe->contlen_cdbsize, NVMETCP_WQE_CONT_LEN, + task_params->tx_io_size); + SET_FIELD(task_params->sqe->flags, NVMETCP_WQE_NUM_SGES, + min((u16)sgl_task_params->num_sges, + (u16)SCSI_NUM_SGES_SLOW_SGL_THR)); + } + } break; + + case NVMETCP_TASK_TYPE_CLEANUP: + SET_FIELD(task_params->sqe->flags, NVMETCP_WQE_WQE_TYPE, + NVMETCP_WQE_TYPE_TASK_CLEANUP); + + default: + break; + } +} + +/* The following function initializes of NVMeTCP task params */ +static inline void +init_nvmetcp_task_params(struct e5_nvmetcp_task_context *context, + struct nvmetcp_task_params *task_params, + enum nvmetcp_task_type task_type) +{ + context->ystorm_st_context.state.cccid = task_params->host_cccid; + SET_FIELD(context->ustorm_st_context.error_flags, USTORM_NVMETCP_TASK_ST_CTX_NVME_TCP, 1); + context->ustorm_st_context.nvme_tcp_opaque_lo = cpu_to_le32(task_params->opq.lo); + context->ustorm_st_context.nvme_tcp_opaque_hi = cpu_to_le32(task_params->opq.hi); +} + +/* The following function initializes default values to all tasks */ +static inline void +init_default_nvmetcp_task(struct nvmetcp_task_params *task_params, + void *pdu_header, void *nvme_cmd, + enum nvmetcp_task_type task_type) +{ + struct e5_nvmetcp_task_context *context = task_params->context; + const u8 val_byte = context->mstorm_ag_context.cdu_validation; + u8 dw_index; + + memset(context, 0, sizeof(*context)); + init_nvmetcp_task_params(context, task_params, + (enum nvmetcp_task_type)task_type); + + /* Swapping requirements used below, will be removed in future FW versions */ + if (task_type == NVMETCP_TASK_TYPE_HOST_WRITE || + task_type == NVMETCP_TASK_TYPE_HOST_READ) { + for (dw_index = 0; + dw_index < QED_NVMETCP_CMN_HDR_SIZE / sizeof(u32); + dw_index++) + context->ystorm_st_context.pdu_hdr.task_hdr.reg[dw_index] = + cpu_to_le32(__swab32(((u32 *)pdu_header)[dw_index])); + + for (dw_index = QED_NVMETCP_CMN_HDR_SIZE / sizeof(u32); + dw_index < QED_NVMETCP_CMD_HDR_SIZE / sizeof(u32); + dw_index++) + context->ystorm_st_context.pdu_hdr.task_hdr.reg[dw_index] = + cpu_to_le32(__swab32(((u32 *)nvme_cmd)[dw_index - 2])); + } else { + for (dw_index = 0; + dw_index < QED_NVMETCP_NON_IO_HDR_SIZE / sizeof(u32); + dw_index++) + context->ystorm_st_context.pdu_hdr.task_hdr.reg[dw_index] = + cpu_to_le32(__swab32(((u32 *)pdu_header)[dw_index])); + } + + /* M-Storm Context: */ + context->mstorm_ag_context.cdu_validation = val_byte; + context->mstorm_st_context.task_type = (u8)(task_type); + context->mstorm_ag_context.task_cid = cpu_to_le16(task_params->conn_icid); + + /* Ustorm Context: */ + SET_FIELD(context->ustorm_ag_context.flags1, E5_USTORM_NVMETCP_TASK_AG_CTX_R2T2RECV, 1); + context->ustorm_st_context.task_type = (u8)(task_type); + context->ustorm_st_context.cq_rss_number = task_params->cq_rss_number; + context->ustorm_ag_context.icid = cpu_to_le16(task_params->conn_icid); +} + +/* The following function initializes the U-Storm Task Contexts */ +static inline void +init_ustorm_task_contexts(struct ustorm_nvmetcp_task_st_ctx *ustorm_st_context, + struct e5_ustorm_nvmetcp_task_ag_ctx *ustorm_ag_context, + u32 remaining_recv_len, + u32 expected_data_transfer_len, u8 num_sges, + bool tx_dif_conn_err_en) +{ + /* Remaining data to be received in bytes. Used in validations*/ + ustorm_st_context->rem_rcv_len = cpu_to_le32(remaining_recv_len); + ustorm_ag_context->exp_data_acked = cpu_to_le32(expected_data_transfer_len); + ustorm_st_context->exp_data_transfer_len = cpu_to_le32(expected_data_transfer_len); + SET_FIELD(ustorm_st_context->reg1_map, REG1_NUM_SGES, num_sges); + SET_FIELD(ustorm_ag_context->flags2, E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_CF_EN, + tx_dif_conn_err_en ? 1 : 0); +} + +/* The following function initializes Local Completion Contexts: */ +static inline void +set_local_completion_context(struct e5_nvmetcp_task_context *context) +{ + SET_FIELD(context->ystorm_st_context.state.flags, + YSTORM_NVMETCP_TASK_STATE_LOCAL_COMP, 1); + SET_FIELD(context->ustorm_st_context.flags, + USTORM_NVMETCP_TASK_ST_CTX_LOCAL_COMP, 1); +} + +/* Common Fastpath task init function: */ +static inline void +init_rw_nvmetcp_task(struct nvmetcp_task_params *task_params, + enum nvmetcp_task_type task_type, + void *pdu_header, void *nvme_cmd, + struct storage_sgl_task_params *sgl_task_params) +{ + struct e5_nvmetcp_task_context *context = task_params->context; + u32 task_size = calc_rw_task_size(task_params, task_type); + bool slow_io = false; + u8 num_sges = 0; + + init_default_nvmetcp_task(task_params, pdu_header, nvme_cmd, task_type); + + /* Tx/Rx: */ + if (task_params->tx_io_size) { + /* if data to transmit: */ + init_scsi_sgl_context(&context->ystorm_st_context.state.sgl_params, + &context->ystorm_st_context.state.data_desc, + sgl_task_params); + slow_io = nvmetcp_is_slow_sgl(sgl_task_params->num_sges, + sgl_task_params->small_mid_sge); + num_sges = + (u8)(!slow_io ? min((u32)sgl_task_params->num_sges, + (u32)SCSI_NUM_SGES_SLOW_SGL_THR) : + NVMETCP_WQE_NUM_SGES_SLOWIO); + if (slow_io) { + SET_FIELD(context->ystorm_st_context.state.flags, + YSTORM_NVMETCP_TASK_STATE_SLOW_IO, 1); + } + } else if (task_params->rx_io_size) { + /* if data to receive: */ + init_scsi_sgl_context(&context->mstorm_st_context.sgl_params, + &context->mstorm_st_context.data_desc, + sgl_task_params); + num_sges = + (u8)(!nvmetcp_is_slow_sgl(sgl_task_params->num_sges, + sgl_task_params->small_mid_sge) ? + min((u32)sgl_task_params->num_sges, + (u32)SCSI_NUM_SGES_SLOW_SGL_THR) : + NVMETCP_WQE_NUM_SGES_SLOWIO); + context->mstorm_st_context.rem_task_size = cpu_to_le32(task_size); + } + + /* Ustorm context: */ + init_ustorm_task_contexts(&context->ustorm_st_context, + &context->ustorm_ag_context, + /* Remaining Receive length is the Task Size */ + task_size, + /* The size of the transmitted task */ + task_size, + /* num_sges */ + num_sges, + false); + + /* Set exp_data_acked */ + if (task_type == NVMETCP_TASK_TYPE_HOST_WRITE) { + if (task_params->send_write_incapsule) + context->ustorm_ag_context.exp_data_acked = task_size; + else + context->ustorm_ag_context.exp_data_acked = 0; + } else if (task_type == NVMETCP_TASK_TYPE_HOST_READ) { + context->ustorm_ag_context.exp_data_acked = 0; + } + + context->ustorm_ag_context.exp_cont_len = 0; + init_sqe(task_params, sgl_task_params, task_type); +} + +static void +init_common_initiator_read_task(struct nvmetcp_task_params *task_params, + struct nvme_tcp_cmd_pdu *cmd_pdu_header, + struct nvme_command *nvme_cmd, + struct storage_sgl_task_params *sgl_task_params) +{ + init_rw_nvmetcp_task(task_params, NVMETCP_TASK_TYPE_HOST_READ, + cmd_pdu_header, nvme_cmd, sgl_task_params); +} + +void init_nvmetcp_host_read_task(struct nvmetcp_task_params *task_params, + struct nvme_tcp_cmd_pdu *cmd_pdu_header, + struct nvme_command *nvme_cmd, + struct storage_sgl_task_params *sgl_task_params) +{ + init_common_initiator_read_task(task_params, (void *)cmd_pdu_header, + (void *)nvme_cmd, sgl_task_params); +} + +static void +init_common_initiator_write_task(struct nvmetcp_task_params *task_params, + struct nvme_tcp_cmd_pdu *cmd_pdu_header, + struct nvme_command *nvme_cmd, + struct storage_sgl_task_params *sgl_task_params) +{ + init_rw_nvmetcp_task(task_params, NVMETCP_TASK_TYPE_HOST_WRITE, + cmd_pdu_header, nvme_cmd, sgl_task_params); +} + +void init_nvmetcp_host_write_task(struct nvmetcp_task_params *task_params, + struct nvme_tcp_cmd_pdu *cmd_pdu_header, + struct nvme_command *nvme_cmd, + struct storage_sgl_task_params *sgl_task_params) +{ + init_common_initiator_write_task(task_params, (void *)cmd_pdu_header, + (void *)nvme_cmd, sgl_task_params); +} + +static void +init_common_login_request_task(struct nvmetcp_task_params *task_params, + void *login_req_pdu_header, + struct storage_sgl_task_params *tx_sgl_task_params, + struct storage_sgl_task_params *rx_sgl_task_params) +{ + struct e5_nvmetcp_task_context *context = task_params->context; + + init_default_nvmetcp_task(task_params, (void *)login_req_pdu_header, NULL, + NVMETCP_TASK_TYPE_INIT_CONN_REQUEST); + + /* Ustorm Context: */ + init_ustorm_task_contexts(&context->ustorm_st_context, + &context->ustorm_ag_context, + + /* Remaining Receive length is the Task Size */ + task_params->rx_io_size ? + rx_sgl_task_params->total_buffer_size : 0, + + /* The size of the transmitted task */ + task_params->tx_io_size ? + tx_sgl_task_params->total_buffer_size : 0, + 0, /* num_sges */ + 0); /* tx_dif_conn_err_en */ + + /* SGL context: */ + if (task_params->tx_io_size) + init_scsi_sgl_context(&context->ystorm_st_context.state.sgl_params, + &context->ystorm_st_context.state.data_desc, + tx_sgl_task_params); + if (task_params->rx_io_size) + init_scsi_sgl_context(&context->mstorm_st_context.sgl_params, + &context->mstorm_st_context.data_desc, + rx_sgl_task_params); + + context->mstorm_st_context.rem_task_size = + cpu_to_le32(task_params->rx_io_size ? + rx_sgl_task_params->total_buffer_size : 0); + init_sqe(task_params, tx_sgl_task_params, NVMETCP_TASK_TYPE_INIT_CONN_REQUEST); +} + +/* The following function initializes Login task in Host mode: */ +void init_nvmetcp_init_conn_req_task(struct nvmetcp_task_params *task_params, + struct nvme_tcp_icreq_pdu *init_conn_req_pdu_hdr, + struct storage_sgl_task_params *tx_sgl_task_params, + struct storage_sgl_task_params *rx_sgl_task_params) +{ + init_common_login_request_task(task_params, init_conn_req_pdu_hdr, + tx_sgl_task_params, rx_sgl_task_params); +} + +void init_cleanup_task_nvmetcp(struct nvmetcp_task_params *task_params) +{ + init_sqe(task_params, NULL, NVMETCP_TASK_TYPE_CLEANUP); +} diff --git a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.h b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.h new file mode 100644 index 000000000000..4c7ac2bd2ea5 --- /dev/null +++ b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* Copyright 2021 Marvell. All rights reserved. */ + +#ifndef _QED_NVMETCP_FW_FUNCS_H +#define _QED_NVMETCP_FW_FUNCS_H + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#if IS_ENABLED(CONFIG_QED_NVMETCP) + +void init_nvmetcp_host_read_task(struct nvmetcp_task_params *task_params, + struct nvme_tcp_cmd_pdu *cmd_pdu_header, + struct nvme_command *nvme_cmd, + struct storage_sgl_task_params *sgl_task_params); +void init_nvmetcp_host_write_task(struct nvmetcp_task_params *task_params, + struct nvme_tcp_cmd_pdu *cmd_pdu_header, + struct nvme_command *nvme_cmd, + struct storage_sgl_task_params *sgl_task_params); +void init_nvmetcp_init_conn_req_task(struct nvmetcp_task_params *task_params, + struct nvme_tcp_icreq_pdu *init_conn_req_pdu_hdr, + struct storage_sgl_task_params *tx_sgl_task_params, + struct storage_sgl_task_params *rx_sgl_task_params); +void init_cleanup_task_nvmetcp(struct nvmetcp_task_params *task_params); + +#else /* IS_ENABLED(CONFIG_QED_NVMETCP) */ + +#endif /* IS_ENABLED(CONFIG_QED_NVMETCP) */ + +#endif /* _QED_NVMETCP_FW_FUNCS_H */ diff --git a/include/linux/qed/nvmetcp_common.h b/include/linux/qed/nvmetcp_common.h index ad745a9c2264..5a2ab0606308 100644 --- a/include/linux/qed/nvmetcp_common.h +++ b/include/linux/qed/nvmetcp_common.h @@ -5,6 +5,7 @@ #define __NVMETCP_COMMON__ #include "tcp_common.h" +#include #define NVMETCP_SLOW_PATH_LAYER_CODE (6) #define NVMETCP_WQE_NUM_SGES_SLOWIO (0xf) diff --git a/include/linux/qed/qed_nvmetcp_if.h b/include/linux/qed/qed_nvmetcp_if.h index 606427ebb63c..14671bc19ed1 100644 --- a/include/linux/qed/qed_nvmetcp_if.h +++ b/include/linux/qed/qed_nvmetcp_if.h @@ -9,6 +9,9 @@ #include #define QED_NVMETCP_MAX_IO_SIZE 0x800000 +#define QED_NVMETCP_CMN_HDR_SIZE (sizeof(struct nvme_tcp_hdr)) +#define QED_NVMETCP_CMD_HDR_SIZE (sizeof(struct nvme_tcp_cmd_pdu)) +#define QED_NVMETCP_NON_IO_HDR_SIZE ((QED_NVMETCP_CMN_HDR_SIZE + 16)) typedef int (*nvmetcp_event_cb_t) (void *context, u8 fw_event_code, void *fw_handle); @@ -213,6 +216,23 @@ struct qed_nvmetcp_ops { void (*remove_dst_tcp_port_filter)(struct qed_dev *cdev, u16 dest_port); void (*clear_all_filters)(struct qed_dev *cdev); + + void (*init_read_io)(struct nvmetcp_task_params *task_params, + struct nvme_tcp_cmd_pdu *cmd_pdu_header, + struct nvme_command *nvme_cmd, + struct storage_sgl_task_params *sgl_task_params); + + void (*init_write_io)(struct nvmetcp_task_params *task_params, + struct nvme_tcp_cmd_pdu *cmd_pdu_header, + struct nvme_command *nvme_cmd, + struct storage_sgl_task_params *sgl_task_params); + + void (*init_icreq_exchange)(struct nvmetcp_task_params *task_params, + struct nvme_tcp_icreq_pdu *init_conn_req_pdu_hdr, + struct storage_sgl_task_params *tx_sgl_task_params, + struct storage_sgl_task_params *rx_sgl_task_params); + + void (*init_task_cleanup)(struct nvmetcp_task_params *task_params); }; const struct qed_nvmetcp_ops *qed_get_nvmetcp_ops(void); -- cgit v1.2.3-71-gd317 From 806ee7f81a2b037e3f57275adcdf974453cc3254 Mon Sep 17 00:00:00 2001 From: Nikolay Assa Date: Wed, 2 Jun 2021 20:16:55 +0300 Subject: qed: Add IP services APIs support This patch introduces APIs which the NVMeTCP Offload device (qedn) will use through the paired net-device (qede). It includes APIs for: - ipv4/ipv6 routing - get VLAN from net-device - TCP ports reservation Acked-by: Igor Russkikh Signed-off-by: Nikolay Assa Signed-off-by: Prabhakar Kushwaha Signed-off-by: Omkar Kulkarni Signed-off-by: Michal Kalderon Signed-off-by: Ariel Elior Signed-off-by: Shai Malin Reviewed-by: Hannes Reinecke Signed-off-by: David S. Miller --- .../ethernet/qlogic/qed/qed_nvmetcp_ip_services.c | 238 +++++++++++++++++++++ include/linux/qed/qed_nvmetcp_ip_services_if.h | 29 +++ 2 files changed, 267 insertions(+) create mode 100644 drivers/net/ethernet/qlogic/qed/qed_nvmetcp_ip_services.c create mode 100644 include/linux/qed/qed_nvmetcp_ip_services_if.h (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_ip_services.c b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_ip_services.c new file mode 100644 index 000000000000..96a2077fd315 --- /dev/null +++ b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_ip_services.c @@ -0,0 +1,238 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) +/* + * Copyright 2021 Marvell. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include + +#define QED_IP_RESOL_TIMEOUT 4 + +int qed_route_ipv4(struct sockaddr_storage *local_addr, + struct sockaddr_storage *remote_addr, + struct sockaddr *hardware_address, + struct net_device **ndev) +{ + struct neighbour *neigh = NULL; + __be32 *loc_ip, *rem_ip; + struct rtable *rt; + int rc = -ENXIO; + int retry; + + loc_ip = &((struct sockaddr_in *)local_addr)->sin_addr.s_addr; + rem_ip = &((struct sockaddr_in *)remote_addr)->sin_addr.s_addr; + *ndev = NULL; + rt = ip_route_output(&init_net, *rem_ip, *loc_ip, 0/*tos*/, 0/*oif*/); + if (IS_ERR(rt)) { + pr_err("lookup route failed\n"); + rc = PTR_ERR(rt); + goto return_err; + } + + neigh = dst_neigh_lookup(&rt->dst, rem_ip); + if (!neigh) { + rc = -ENOMEM; + ip_rt_put(rt); + goto return_err; + } + + *ndev = rt->dst.dev; + ip_rt_put(rt); + + /* If not resolved, kick-off state machine towards resolution */ + if (!(neigh->nud_state & NUD_VALID)) + neigh_event_send(neigh, NULL); + + /* query neighbor until resolved or timeout */ + retry = QED_IP_RESOL_TIMEOUT; + while (!(neigh->nud_state & NUD_VALID) && retry > 0) { + msleep(1000); + retry--; + } + + if (neigh->nud_state & NUD_VALID) { + /* copy resolved MAC address */ + neigh_ha_snapshot(hardware_address->sa_data, neigh, *ndev); + hardware_address->sa_family = (*ndev)->type; + rc = 0; + } + + neigh_release(neigh); + if (!(*loc_ip)) { + *loc_ip = inet_select_addr(*ndev, *rem_ip, RT_SCOPE_UNIVERSE); + local_addr->ss_family = AF_INET; + } + +return_err: + + return rc; +} +EXPORT_SYMBOL(qed_route_ipv4); + +int qed_route_ipv6(struct sockaddr_storage *local_addr, + struct sockaddr_storage *remote_addr, + struct sockaddr *hardware_address, + struct net_device **ndev) +{ + struct neighbour *neigh = NULL; + struct dst_entry *dst; + struct flowi6 fl6; + int rc = -ENXIO; + int retry; + + memset(&fl6, 0, sizeof(fl6)); + fl6.saddr = ((struct sockaddr_in6 *)local_addr)->sin6_addr; + fl6.daddr = ((struct sockaddr_in6 *)remote_addr)->sin6_addr; + dst = ip6_route_output(&init_net, NULL, &fl6); + if (!dst || dst->error) { + if (dst) { + dst_release(dst); + pr_err("lookup route failed %d\n", dst->error); + } + + goto out; + } + + neigh = dst_neigh_lookup(dst, &fl6.daddr); + if (neigh) { + *ndev = ip6_dst_idev(dst)->dev; + + /* If not resolved, kick-off state machine towards resolution */ + if (!(neigh->nud_state & NUD_VALID)) + neigh_event_send(neigh, NULL); + + /* query neighbor until resolved or timeout */ + retry = QED_IP_RESOL_TIMEOUT; + while (!(neigh->nud_state & NUD_VALID) && retry > 0) { + msleep(1000); + retry--; + } + + if (neigh->nud_state & NUD_VALID) { + neigh_ha_snapshot((u8 *)hardware_address->sa_data, + neigh, *ndev); + hardware_address->sa_family = (*ndev)->type; + rc = 0; + } + + neigh_release(neigh); + + if (ipv6_addr_any(&fl6.saddr)) { + if (ipv6_dev_get_saddr(dev_net(*ndev), *ndev, + &fl6.daddr, 0, &fl6.saddr)) { + pr_err("Unable to find source IP address\n"); + goto out; + } + + local_addr->ss_family = AF_INET6; + ((struct sockaddr_in6 *)local_addr)->sin6_addr = + fl6.saddr; + } + } + + dst_release(dst); + +out: + + return rc; +} +EXPORT_SYMBOL(qed_route_ipv6); + +void qed_vlan_get_ndev(struct net_device **ndev, u16 *vlan_id) +{ + if (is_vlan_dev(*ndev)) { + *vlan_id = vlan_dev_vlan_id(*ndev); + *ndev = vlan_dev_real_dev(*ndev); + } +} +EXPORT_SYMBOL(qed_vlan_get_ndev); + +struct pci_dev *qed_validate_ndev(struct net_device *ndev) +{ + struct pci_dev *pdev = NULL; + struct net_device *upper; + + for_each_pci_dev(pdev) { + if (pdev && pdev->driver && + !strcmp(pdev->driver->name, "qede")) { + upper = pci_get_drvdata(pdev); + if (upper->ifindex == ndev->ifindex) + return pdev; + } + } + + return NULL; +} +EXPORT_SYMBOL(qed_validate_ndev); + +__be16 qed_get_in_port(struct sockaddr_storage *sa) +{ + return sa->ss_family == AF_INET + ? ((struct sockaddr_in *)sa)->sin_port + : ((struct sockaddr_in6 *)sa)->sin6_port; +} +EXPORT_SYMBOL(qed_get_in_port); + +int qed_fetch_tcp_port(struct sockaddr_storage local_ip_addr, + struct socket **sock, u16 *port) +{ + struct sockaddr_storage sa; + int rc = 0; + + rc = sock_create(local_ip_addr.ss_family, SOCK_STREAM, IPPROTO_TCP, + sock); + if (rc) { + pr_warn("failed to create socket: %d\n", rc); + goto err; + } + + (*sock)->sk->sk_allocation = GFP_KERNEL; + sk_set_memalloc((*sock)->sk); + + rc = kernel_bind(*sock, (struct sockaddr *)&local_ip_addr, + sizeof(local_ip_addr)); + + if (rc) { + pr_warn("failed to bind socket: %d\n", rc); + goto err_sock; + } + + rc = kernel_getsockname(*sock, (struct sockaddr *)&sa); + if (rc < 0) { + pr_warn("getsockname() failed: %d\n", rc); + goto err_sock; + } + + *port = ntohs(qed_get_in_port(&sa)); + + return 0; + +err_sock: + sock_release(*sock); + sock = NULL; +err: + + return rc; +} +EXPORT_SYMBOL(qed_fetch_tcp_port); + +void qed_return_tcp_port(struct socket *sock) +{ + if (sock && sock->sk) { + tcp_set_state(sock->sk, TCP_CLOSE); + sock_release(sock); + } +} +EXPORT_SYMBOL(qed_return_tcp_port); diff --git a/include/linux/qed/qed_nvmetcp_ip_services_if.h b/include/linux/qed/qed_nvmetcp_ip_services_if.h new file mode 100644 index 000000000000..3604aee53796 --- /dev/null +++ b/include/linux/qed/qed_nvmetcp_ip_services_if.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* + * Copyright 2021 Marvell. All rights reserved. + */ + +#ifndef _QED_IP_SERVICES_IF_H +#define _QED_IP_SERVICES_IF_H + +#include +#include +#include +#include + +int qed_route_ipv4(struct sockaddr_storage *local_addr, + struct sockaddr_storage *remote_addr, + struct sockaddr *hardware_address, + struct net_device **ndev); +int qed_route_ipv6(struct sockaddr_storage *local_addr, + struct sockaddr_storage *remote_addr, + struct sockaddr *hardware_address, + struct net_device **ndev); +void qed_vlan_get_ndev(struct net_device **ndev, u16 *vlan_id); +struct pci_dev *qed_validate_ndev(struct net_device *ndev); +void qed_return_tcp_port(struct socket *sock); +int qed_fetch_tcp_port(struct sockaddr_storage local_ip_addr, + struct socket **sock, u16 *port); +__be16 qed_get_in_port(struct sockaddr_storage *sa); + +#endif /* _QED_IP_SERVICES_IF_H */ -- cgit v1.2.3-71-gd317 From ef4b65e53cc77e2b3ca4667b461047ad04fb45fa Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 31 May 2021 00:08:09 +0200 Subject: netfilter: nfnetlink: add struct nfgenmsg to struct nfnl_info and use it Update the nfnl_info structure to add a pointer to the nfnetlink header. This simplifies the existing codebase since this header is usually accessed. Update existing clients to use this new field. Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink.h | 1 + net/netfilter/nf_conntrack_netlink.c | 23 ++++++--------- net/netfilter/nf_tables_api.c | 55 +++++++++++++----------------------- net/netfilter/nfnetlink.c | 2 ++ net/netfilter/nfnetlink_log.c | 5 ++-- net/netfilter/nfnetlink_queue.c | 9 ++---- net/netfilter/nft_compat.c | 17 ++++------- 7 files changed, 42 insertions(+), 70 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 515ce53aa20d..241e005f290a 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -11,6 +11,7 @@ struct nfnl_info { struct net *net; struct sock *sk; const struct nlmsghdr *nlh; + const struct nfgenmsg *nfmsg; struct netlink_ext_ack *extack; }; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 220f51f055ab..4e1a9dba7077 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1528,7 +1528,7 @@ static int ctnetlink_del_conntrack(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + u8 family = info->nfmsg->nfgen_family; struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; struct nf_conntrack_zone zone; @@ -1541,12 +1541,12 @@ static int ctnetlink_del_conntrack(struct sk_buff *skb, if (cda[CTA_TUPLE_ORIG]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, - nfmsg->nfgen_family, &zone); + family, &zone); else if (cda[CTA_TUPLE_REPLY]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, - nfmsg->nfgen_family, &zone); + family, &zone); else { - u_int8_t u3 = nfmsg->version ? nfmsg->nfgen_family : AF_UNSPEC; + u_int8_t u3 = info->nfmsg->version ? family : AF_UNSPEC; return ctnetlink_flush_conntrack(info->net, cda, NETLINK_CB(skb).portid, @@ -1586,8 +1586,7 @@ static int ctnetlink_get_conntrack(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); - u_int8_t u3 = nfmsg->nfgen_family; + u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; struct nf_conntrack_zone zone; @@ -2363,10 +2362,9 @@ static int ctnetlink_new_conntrack(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct nf_conntrack_tuple otuple, rtuple; struct nf_conntrack_tuple_hash *h = NULL; - u_int8_t u3 = nfmsg->nfgen_family; + u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_zone zone; struct nf_conn *ct; int err; @@ -3259,8 +3257,7 @@ static int ctnetlink_get_expect(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); - u_int8_t u3 = nfmsg->nfgen_family; + u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; struct nf_conntrack_zone zone; @@ -3349,8 +3346,7 @@ static int ctnetlink_del_expect(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); - u_int8_t u3 = nfmsg->nfgen_family; + u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_expect *exp; struct nf_conntrack_tuple tuple; struct nf_conntrack_zone zone; @@ -3601,8 +3597,7 @@ static int ctnetlink_new_expect(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); - u_int8_t u3 = nfmsg->nfgen_family; + u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; struct nf_conntrack_zone zone; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d63d2d8f769c..b2b4e03ce036 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -861,10 +861,9 @@ static int nft_netlink_dump_start_rcu(struct sock *nlsk, struct sk_buff *skb, static int nf_tables_gettable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; const struct nft_table *table; struct net *net = info->net; struct sk_buff *skb2; @@ -1059,10 +1058,9 @@ static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct nftables_pernet *nft_net = nft_pernet(info->net); - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; @@ -1254,10 +1252,9 @@ out: static int nf_tables_deltable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; @@ -1627,10 +1624,9 @@ done: static int nf_tables_getchain(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; const struct nft_chain *chain; struct net *net = info->net; struct nft_table *table; @@ -2355,10 +2351,9 @@ static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct nftables_pernet *nft_net = nft_pernet(info->net); - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; struct nft_chain *chain = NULL; struct net *net = info->net; const struct nlattr *attr; @@ -2453,10 +2448,9 @@ static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info, static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; @@ -3080,10 +3074,9 @@ static int nf_tables_dump_rules_done(struct netlink_callback *cb) static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; const struct nft_chain *chain; const struct nft_rule *rule; struct net *net = info->net; @@ -3221,13 +3214,12 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct nftables_pernet *nft_net = nft_pernet(info->net); - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; unsigned int size, i, n, ulen = 0, usize = 0; u8 genmask = nft_genmask_next(info->net); struct nft_rule *rule, *old_rule = NULL; struct nft_expr_info *expr_info = NULL; - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; struct nft_flow_rule *flow; struct nft_userdata *udata; @@ -3459,15 +3451,15 @@ static struct nft_rule *nft_rule_lookup_byid(const struct net *net, static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; - int family = nfmsg->nfgen_family, err = 0; u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; struct nft_chain *chain = NULL; struct net *net = info->net; struct nft_table *table; struct nft_rule *rule; struct nft_ctx ctx; + int err = 0; table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask, NETLINK_CB(skb).portid); @@ -4050,7 +4042,6 @@ static int nf_tables_dump_sets_done(struct netlink_callback *cb) static int nf_tables_getset(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); struct net *net = info->net; @@ -4078,7 +4069,7 @@ static int nf_tables_getset(struct sk_buff *skb, const struct nfnl_info *info, } /* Only accept unspec with dump */ - if (nfmsg->nfgen_family == NFPROTO_UNSPEC) + if (info->nfmsg->nfgen_family == NFPROTO_UNSPEC) return -EAFNOSUPPORT; if (!nla[NFTA_SET_TABLE]) return -EINVAL; @@ -4171,11 +4162,10 @@ static int nf_tables_set_desc_parse(struct nft_set_desc *desc, static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); u32 ktype, dtype, flags, policy, gc_int, objtype; struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; const struct nft_set_ops *ops; struct nft_expr *expr = NULL; struct net *net = info->net; @@ -4475,7 +4465,6 @@ static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) static int nf_tables_delset(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); struct net *net = info->net; @@ -4484,7 +4473,7 @@ static int nf_tables_delset(struct sk_buff *skb, const struct nfnl_info *info, struct nft_ctx ctx; int err; - if (nfmsg->nfgen_family == NFPROTO_UNSPEC) + if (info->nfmsg->nfgen_family == NFPROTO_UNSPEC) return -EAFNOSUPPORT; if (nla[NFTA_SET_TABLE] == NULL) return -EINVAL; @@ -6527,11 +6516,10 @@ err_free_trans: static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; const struct nft_object_type *type; - int family = nfmsg->nfgen_family; struct net *net = info->net; struct nft_table *table; struct nft_object *obj; @@ -6783,10 +6771,9 @@ static int nf_tables_dump_obj_done(struct netlink_callback *cb) static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; const struct nft_table *table; struct net *net = info->net; struct nft_object *obj; @@ -6873,10 +6860,9 @@ static void nft_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) static int nf_tables_delobj(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; @@ -7304,12 +7290,11 @@ static int nf_tables_newflowtable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; struct nft_flowtable_hook flowtable_hook; u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; const struct nf_flowtable_type *type; - int family = nfmsg->nfgen_family; struct nft_flowtable *flowtable; struct nft_hook *hook, *next; struct net *net = info->net; @@ -7493,10 +7478,9 @@ static int nf_tables_delflowtable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; struct nft_flowtable *flowtable; struct net *net = info->net; const struct nlattr *attr; @@ -7688,9 +7672,8 @@ static int nf_tables_getflowtable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); u8 genmask = nft_genmask_cur(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; struct nft_flowtable *flowtable; const struct nft_table *table; struct net *net = info->net; diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index e8dbd8379027..028a1f39318b 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -256,6 +256,7 @@ replay: .net = net, .sk = nfnlnet->nfnl, .nlh = nlh, + .nfmsg = nlmsg_data(nlh), .extack = extack, }; @@ -491,6 +492,7 @@ replay_abort: .net = net, .sk = nfnlnet->nfnl, .nlh = nlh, + .nfmsg = nlmsg_data(nlh), .extack = &extack, }; diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 587086b18c36..691ef4cffdd9 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -871,15 +871,14 @@ static int nfulnl_recv_config(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nfula[]) { struct nfnl_log_net *log = nfnl_log_pernet(info->net); - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); - u_int16_t group_num = ntohs(nfmsg->res_id); + u_int16_t group_num = ntohs(info->nfmsg->res_id); struct nfulnl_msg_config_cmd *cmd = NULL; struct nfulnl_instance *inst; u16 flags = 0; int ret = 0; if (nfula[NFULA_CFG_CMD]) { - u_int8_t pf = nfmsg->nfgen_family; + u_int8_t pf = info->nfmsg->nfgen_family; cmd = nla_data(nfula[NFULA_CFG_CMD]); /* Commands without queue context */ diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index f37a575ebd7f..f774de0fc24f 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -1051,8 +1051,7 @@ static int nfqnl_recv_verdict_batch(struct sk_buff *skb, const struct nlattr * const nfqa[]) { struct nfnl_queue_net *q = nfnl_queue_pernet(info->net); - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); - u16 queue_num = ntohs(nfmsg->res_id); + u16 queue_num = ntohs(info->nfmsg->res_id); struct nf_queue_entry *entry, *tmp; struct nfqnl_msg_verdict_hdr *vhdr; struct nfqnl_instance *queue; @@ -1160,8 +1159,7 @@ static int nfqnl_recv_verdict(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nfqa[]) { struct nfnl_queue_net *q = nfnl_queue_pernet(info->net); - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); - u_int16_t queue_num = ntohs(nfmsg->res_id); + u_int16_t queue_num = ntohs(info->nfmsg->res_id); struct nfqnl_msg_verdict_hdr *vhdr; enum ip_conntrack_info ctinfo; struct nfqnl_instance *queue; @@ -1243,8 +1241,7 @@ static int nfqnl_recv_config(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nfqa[]) { struct nfnl_queue_net *q = nfnl_queue_pernet(info->net); - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); - u_int16_t queue_num = ntohs(nfmsg->res_id); + u_int16_t queue_num = ntohs(info->nfmsg->res_id); struct nfqnl_msg_config_cmd *cmd = NULL; struct nfqnl_instance *queue; __u32 flags = 0, mask = 0; diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 3144a9ad2f6a..639c337c885b 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -625,7 +625,7 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const tb[]) { - struct nfgenmsg *nfmsg; + u8 family = info->nfmsg->nfgen_family; const char *name, *fmt; struct sk_buff *skb2; int ret = 0, target; @@ -640,9 +640,7 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb, rev = ntohl(nla_get_be32(tb[NFTA_COMPAT_REV])); target = ntohl(nla_get_be32(tb[NFTA_COMPAT_TYPE])); - nfmsg = nlmsg_data(info->nlh); - - switch(nfmsg->nfgen_family) { + switch(family) { case AF_INET: fmt = "ipt_%s"; break; @@ -656,8 +654,7 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb, fmt = "arpt_%s"; break; default: - pr_err("nft_compat: unsupported protocol %d\n", - nfmsg->nfgen_family); + pr_err("nft_compat: unsupported protocol %d\n", family); return -EINVAL; } @@ -665,9 +662,8 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb, return -EINVAL; rcu_read_unlock(); - try_then_request_module(xt_find_revision(nfmsg->nfgen_family, name, - rev, target, &ret), - fmt, name); + try_then_request_module(xt_find_revision(family, name, rev, target, &ret), + fmt, name); if (ret < 0) goto out_put; @@ -682,8 +678,7 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb, info->nlh->nlmsg_seq, NFNL_MSG_TYPE(info->nlh->nlmsg_type), NFNL_MSG_COMPAT_GET, - nfmsg->nfgen_family, - name, ret, target) <= 0) { + family, name, ret, target) <= 0) { kfree_skb(skb2); goto out_put; } -- cgit v1.2.3-71-gd317 From 7b4b2fa37587394fb89fa51a4bea0820a1b37a5d Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 4 Jun 2021 12:27:06 +0200 Subject: netfilter: annotate nf_tables base hook ops This will allow a followup patch to treat the 'ops->priv' pointer as nft_chain argument without having to first walk the table/chains to check if there is a matching base chain pointer. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 8 +++++++- net/netfilter/nf_tables_api.c | 4 +++- 2 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index f161569fbe2f..3fda1a508733 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -77,12 +77,18 @@ struct nf_hook_state { typedef unsigned int nf_hookfn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); +enum nf_hook_ops_type { + NF_HOOK_OP_UNDEFINED, + NF_HOOK_OP_NF_TABLES, +}; + struct nf_hook_ops { /* User fills in from here down. */ nf_hookfn *hook; struct net_device *dev; void *priv; - u_int8_t pf; + u8 pf; + enum nf_hook_ops_type hook_ops_type:8; unsigned int hooknum; /* Hooks are ordered in ascending priority. */ int priority; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 6c2000a11c7e..c9308241b688 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2168,8 +2168,10 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, } nft_trans_chain_policy(trans) = NFT_CHAIN_POLICY_UNSET; - if (nft_is_base_chain(chain)) + if (nft_is_base_chain(chain)) { + basechain->ops.hook_ops_type = NF_HOOK_OP_NF_TABLES; nft_trans_chain_policy(trans) = policy; + } err = nft_chain_add(table, chain); if (err < 0) { -- cgit v1.2.3-71-gd317 From eb550f53099bf5ff8dc5de93e275378510c891c9 Mon Sep 17 00:00:00 2001 From: Brett Creeley Date: Thu, 17 Sep 2020 13:13:33 -0700 Subject: virtchnl: Use pad byte in virtchnl_ether_addr to specify MAC type Currently, there is no way for a VF driver to specify that it wants to change its device/primary unicast MAC address. This makes it difficult/impossible for the PF driver to track the VF's device/primary unicast MAC address, which is used for VM/VF reboot and displaying on the host. Fix this by using 2 bits of a pad byte in the virtchnl_ether_addr structure so the VF can specify what type of MAC it's adding/deleting. Below are the values that should be used by all VF drivers going forward. VIRTCHNL_ETHER_ADDR_LEGACY(0): - The type should only ever be 0 for legacy AVF drivers (i.e. drivers that don't support the new type bits). The PF drivers will track VF's device/primary unicast MAC, but this will only be a best effort. VIRTCHNL_ETHER_ADDR_PRIMARY(1): - This type should only be used when the VF is changing their device/primary unicast MAC. It should be used for both delete and add cases related to the device/primary unicast MAC. VIRTCHNL_ETHER_ADDR_EXTRA(2): - This type should be used when the VF is adding and/or deleting MAC addresses that are not the device/primary unicast MAC. For example, extra unicast addresses and multicast addresses assuming the PF supports "extra" addresses at all. If a PF is parsing the type field of the virtchnl_ether_addr, then it should use the VIRTCHNL_ETHER_ADDR_TYPE_MASK to mask the first two bits of the type field since 0, 1, and 2 are the only valid values. Signed-off-by: Brett Creeley Signed-off-by: Tony Nguyen --- include/linux/avf/virtchnl.h | 29 ++++++++++++++++++++++++++++- 1 file changed, 28 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 565deea6ffe8..1fc07f3f99ab 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -412,9 +412,36 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_queue_select); * PF removes the filters and returns status. */ +/* VIRTCHNL_ETHER_ADDR_LEGACY + * Prior to adding the @type member to virtchnl_ether_addr, there were 2 pad + * bytes. Moving forward all VF drivers should not set type to + * VIRTCHNL_ETHER_ADDR_LEGACY. This is only here to not break previous/legacy + * behavior. The control plane function (i.e. PF) can use a best effort method + * of tracking the primary/device unicast in this case, but there is no + * guarantee and functionality depends on the implementation of the PF. + */ + +/* VIRTCHNL_ETHER_ADDR_PRIMARY + * All VF drivers should set @type to VIRTCHNL_ETHER_ADDR_PRIMARY for the + * primary/device unicast MAC address filter for VIRTCHNL_OP_ADD_ETH_ADDR and + * VIRTCHNL_OP_DEL_ETH_ADDR. This allows for the underlying control plane + * function (i.e. PF) to accurately track and use this MAC address for + * displaying on the host and for VM/function reset. + */ + +/* VIRTCHNL_ETHER_ADDR_EXTRA + * All VF drivers should set @type to VIRTCHNL_ETHER_ADDR_EXTRA for any extra + * unicast and/or multicast filters that are being added/deleted via + * VIRTCHNL_OP_DEL_ETH_ADDR/VIRTCHNL_OP_ADD_ETH_ADDR respectively. + */ struct virtchnl_ether_addr { u8 addr[ETH_ALEN]; - u8 pad[2]; + u8 type; +#define VIRTCHNL_ETHER_ADDR_LEGACY 0 +#define VIRTCHNL_ETHER_ADDR_PRIMARY 1 +#define VIRTCHNL_ETHER_ADDR_EXTRA 2 +#define VIRTCHNL_ETHER_ADDR_TYPE_MASK 3 /* first two bits of type are valid */ + u8 pad; }; VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_ether_addr); -- cgit v1.2.3-71-gd317 From c858d436be8b949c368de0e079084acaff3d4aaf Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 4 Jun 2021 17:01:48 +0300 Subject: net: phy: introduce PHY_INTERFACE_MODE_REVRMII The "reverse RMII" protocol name is a personal invention, derived from "reverse MII". Just like MII, RMII is an asymmetric protocol in that a PHY behaves differently than a MAC. In the case of RMII, for example: - the 50 MHz clock signals are either driven by the MAC or by an external oscillator (but never by the PHY). - the PHY can transmit extra in-band control symbols via RXD[1:0] which the MAC is supposed to understand, but a PHY isn't. The "reverse MII" protocol is not standardized either, except for this web document: https://www.eetimes.com/reverse-media-independent-interface-revmii-block-architecture/# In short, it means that the Ethernet controller speaks the 4-bit data parallel protocol from the perspective of a PHY (it acts like a PHY). This might mean that it implements clause 22 compatible registers, although that is optional - the important bit is that its pins can be connected to an MII MAC and it will 'just work'. In this discussion thread: https://lore.kernel.org/netdev/20210201214515.cx6ivvme2tlquge2@skbuf/ we agreed that it would be an abuse of terms to use the "RevMII" name for anything than the 4-bit parallel MII protocol. But since all the same concepts can be applied to the 2-bit Reduced MII protocol as well, here we are introducing a "Reverse RMII" protocol. This means: "behave like an RMII PHY". Signed-off-by: Vladimir Oltean Acked-by: Florian Fainelli Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/ethernet-controller.yaml | 1 + include/linux/phy.h | 4 ++++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml index e8f04687a3e0..d97b561003ed 100644 --- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml +++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml @@ -68,6 +68,7 @@ properties: - tbi - rev-mii - rmii + - rev-rmii # RX and TX delays are added by the MAC when required - rgmii diff --git a/include/linux/phy.h b/include/linux/phy.h index 852743f07e3e..ed332ac92e25 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -93,6 +93,7 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_TBI: Ten Bit Interface * @PHY_INTERFACE_MODE_REVMII: Reverse Media Independent Interface * @PHY_INTERFACE_MODE_RMII: Reduced Media Independent Interface + * @PHY_INTERFACE_MODE_REVRMII: Reduced Media Independent Interface in PHY role * @PHY_INTERFACE_MODE_RGMII: Reduced gigabit media-independent interface * @PHY_INTERFACE_MODE_RGMII_ID: RGMII with Internal RX+TX delay * @PHY_INTERFACE_MODE_RGMII_RXID: RGMII with Internal RX delay @@ -126,6 +127,7 @@ typedef enum { PHY_INTERFACE_MODE_TBI, PHY_INTERFACE_MODE_REVMII, PHY_INTERFACE_MODE_RMII, + PHY_INTERFACE_MODE_REVRMII, PHY_INTERFACE_MODE_RGMII, PHY_INTERFACE_MODE_RGMII_ID, PHY_INTERFACE_MODE_RGMII_RXID, @@ -185,6 +187,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "rev-mii"; case PHY_INTERFACE_MODE_RMII: return "rmii"; + case PHY_INTERFACE_MODE_REVRMII: + return "rev-rmii"; case PHY_INTERFACE_MODE_RGMII: return "rgmii"; case PHY_INTERFACE_MODE_RGMII_ID: -- cgit v1.2.3-71-gd317 From c07aea3ef4d4076f18f567b98ed01e082e02ed51 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Mon, 7 Jun 2021 21:02:36 +0200 Subject: mm: add a signature in struct page This is needed by the page_pool to avoid recycling a page not allocated via page_pool. The page->signature field is aliased to page->lru.next and page->compound_head, but it can't be set by mistake because the signature value is a bad pointer, and can't trigger a false positive in PageTail() because the last bit is 0. Co-developed-by: Matthew Wilcox (Oracle) Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Matteo Croce Signed-off-by: David S. Miller --- include/linux/mm.h | 11 ++++++----- include/linux/mm_types.h | 7 +++++++ include/linux/poison.h | 3 +++ net/core/page_pool.c | 6 ++++++ 4 files changed, 22 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index c274f75efcf9..a0434e8c2617 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1668,10 +1668,11 @@ struct address_space *page_mapping(struct page *page); static inline bool page_is_pfmemalloc(const struct page *page) { /* - * Page index cannot be this large so this must be - * a pfmemalloc page. + * lru.next has bit 1 set if the page is allocated from the + * pfmemalloc reserves. Callers may simply overwrite it if + * they do not need to preserve that information. */ - return page->index == -1UL; + return (uintptr_t)page->lru.next & BIT(1); } /* @@ -1680,12 +1681,12 @@ static inline bool page_is_pfmemalloc(const struct page *page) */ static inline void set_page_pfmemalloc(struct page *page) { - page->index = -1UL; + page->lru.next = (void *)BIT(1); } static inline void clear_page_pfmemalloc(struct page *page) { - page->index = 0; + page->lru.next = NULL; } /* diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5aacc1c10a45..ed6862eacb52 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -96,6 +96,13 @@ struct page { unsigned long private; }; struct { /* page_pool used by netstack */ + /** + * @pp_magic: magic value to avoid recycling non + * page_pool allocated pages. + */ + unsigned long pp_magic; + struct page_pool *pp; + unsigned long _pp_mapping_pad; /** * @dma_addr: might require a 64-bit value on * 32-bit architectures. diff --git a/include/linux/poison.h b/include/linux/poison.h index aff1c9250c82..d62ef5a6b4e9 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -78,4 +78,7 @@ /********** security/ **********/ #define KEY_DESTROY 0xbd +/********** net/core/page_pool.c **********/ +#define PP_SIGNATURE (0x40 + POISON_POINTER_DELTA) + #endif diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 3c4c4c7a0402..e1321bc9d316 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -17,6 +17,7 @@ #include #include #include /* for __put_page() */ +#include #include @@ -221,6 +222,8 @@ static struct page *__page_pool_alloc_page_order(struct page_pool *pool, return NULL; } + page->pp_magic |= PP_SIGNATURE; + /* Track how many pages are held 'in-flight' */ pool->pages_state_hold_cnt++; trace_page_pool_state_hold(pool, page, pool->pages_state_hold_cnt); @@ -263,6 +266,7 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, put_page(page); continue; } + page->pp_magic |= PP_SIGNATURE; pool->alloc.cache[pool->alloc.count++] = page; /* Track how many pages are held 'in-flight' */ pool->pages_state_hold_cnt++; @@ -341,6 +345,8 @@ void page_pool_release_page(struct page_pool *pool, struct page *page) DMA_ATTR_SKIP_CPU_SYNC); page_pool_set_dma_addr(page, 0); skip_dma_unmap: + page->pp_magic = 0; + /* This may be the last page returned, releasing the pool, so * it is not safe to reference pool afterwards. */ -- cgit v1.2.3-71-gd317 From c420c98982fa9e749c99e022845d5f323d098b72 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Mon, 7 Jun 2021 21:02:37 +0200 Subject: skbuff: add a parameter to __skb_frag_unref This is a prerequisite patch, the next one is enabling recycling of skbs and fragments. Add an extra argument on __skb_frag_unref() to handle recycling, and update the current users of the function with that. Signed-off-by: Matteo Croce Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/sky2.c | 2 +- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 2 +- include/linux/skbuff.h | 8 +++++--- net/core/skbuff.c | 4 ++-- net/tls/tls_device.c | 2 +- 5 files changed, 10 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index 324c280cc22c..8b8bff59c8fe 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -2503,7 +2503,7 @@ static void skb_put_frags(struct sk_buff *skb, unsigned int hdr_space, if (length == 0) { /* don't need this page */ - __skb_frag_unref(frag); + __skb_frag_unref(frag, false); --skb_shinfo(skb)->nr_frags; } else { size = min(length, (unsigned) PAGE_SIZE); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index e35e4d7ef4d1..cea62b8f554c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -526,7 +526,7 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv, fail: while (nr > 0) { nr--; - __skb_frag_unref(skb_shinfo(skb)->frags + nr); + __skb_frag_unref(skb_shinfo(skb)->frags + nr, false); } return 0; } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index dbf820a50a39..7fcfea7e7b21 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3081,10 +3081,12 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f) /** * __skb_frag_unref - release a reference on a paged fragment. * @frag: the paged fragment + * @recycle: recycle the page if allocated via page_pool * - * Releases a reference on the paged fragment @frag. + * Releases a reference on the paged fragment @frag + * or recycles the page via the page_pool API. */ -static inline void __skb_frag_unref(skb_frag_t *frag) +static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) { put_page(skb_frag_page(frag)); } @@ -3098,7 +3100,7 @@ static inline void __skb_frag_unref(skb_frag_t *frag) */ static inline void skb_frag_unref(struct sk_buff *skb, int f) { - __skb_frag_unref(&skb_shinfo(skb)->frags[f]); + __skb_frag_unref(&skb_shinfo(skb)->frags[f], false); } /** diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 3ad22870298c..12b7e90dd2b5 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -664,7 +664,7 @@ static void skb_release_data(struct sk_buff *skb) skb_zcopy_clear(skb, true); for (i = 0; i < shinfo->nr_frags; i++) - __skb_frag_unref(&shinfo->frags[i]); + __skb_frag_unref(&shinfo->frags[i], false); if (shinfo->frag_list) kfree_skb_list(shinfo->frag_list); @@ -3495,7 +3495,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) fragto = &skb_shinfo(tgt)->frags[merge]; skb_frag_size_add(fragto, skb_frag_size(fragfrom)); - __skb_frag_unref(fragfrom); + __skb_frag_unref(fragfrom, false); } /* Reposition in the original skb */ diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index bd9f1567aa39..b932469ee69c 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -128,7 +128,7 @@ static void destroy_record(struct tls_record_info *record) int i; for (i = 0; i < record->num_frags; i++) - __skb_frag_unref(&record->frags[i]); + __skb_frag_unref(&record->frags[i], false); kfree(record); } -- cgit v1.2.3-71-gd317 From 6a5bcd84e886a9a91982e515c539529c28acdcc2 Mon Sep 17 00:00:00 2001 From: Ilias Apalodimas Date: Mon, 7 Jun 2021 21:02:38 +0200 Subject: page_pool: Allow drivers to hint on SKB recycling Up to now several high speed NICs have custom mechanisms of recycling the allocated memory they use for their payloads. Our page_pool API already has recycling capabilities that are always used when we are running in 'XDP mode'. So let's tweak the API and the kernel network stack slightly and allow the recycling to happen even during the standard operation. The API doesn't take into account 'split page' policies used by those drivers currently, but can be extended once we have users for that. The idea is to be able to intercept the packet on skb_release_data(). If it's a buffer coming from our page_pool API recycle it back to the pool for further usage or just release the packet entirely. To achieve that we introduce a bit in struct sk_buff (pp_recycle:1) and a field in struct page (page->pp) to store the page_pool pointer. Storing the information in page->pp allows us to recycle both SKBs and their fragments. We could have skipped the skb bit entirely, since identical information can bederived from struct page. However, in an effort to affect the free path as less as possible, reading a single bit in the skb which is already in cache, is better that trying to derive identical information for the page stored data. The driver or page_pool has to take care of the sync operations on it's own during the buffer recycling since the buffer is, after opting-in to the recycling, never unmapped. Since the gain on the drivers depends on the architecture, we are not enabling recycling by default if the page_pool API is used on a driver. In order to enable recycling the driver must call skb_mark_for_recycle() to store the information we need for recycling in page->pp and enabling the recycling bit, or page_pool_store_mem_info() for a fragment. Co-developed-by: Jesper Dangaard Brouer Signed-off-by: Jesper Dangaard Brouer Co-developed-by: Matteo Croce Signed-off-by: Matteo Croce Signed-off-by: Ilias Apalodimas Signed-off-by: David S. Miller --- include/linux/skbuff.h | 33 ++++++++++++++++++++++++++++++--- include/net/page_pool.h | 9 +++++++++ net/core/page_pool.c | 22 ++++++++++++++++++++++ net/core/skbuff.c | 20 ++++++++++++++++---- 4 files changed, 77 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7fcfea7e7b21..b2db9cd9a73f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -37,6 +37,7 @@ #include #include #include +#include #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include #endif @@ -667,6 +668,8 @@ typedef unsigned char *sk_buff_data_t; * @head_frag: skb was allocated from page fragments, * not allocated by kmalloc() or vmalloc(). * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves + * @pp_recycle: mark the packet for recycling instead of freeing (implies + * page_pool support on driver) * @active_extensions: active extensions (skb_ext_id types) * @ndisc_nodetype: router type (from link layer) * @ooo_okay: allow the mapping of a socket to a queue to be changed @@ -791,10 +794,12 @@ struct sk_buff { fclone:2, peeked:1, head_frag:1, - pfmemalloc:1; + pfmemalloc:1, + pp_recycle:1; /* page_pool recycle indicator */ #ifdef CONFIG_SKB_EXTENSIONS __u8 active_extensions; #endif + /* fields enclosed in headers_start/headers_end are copied * using a single memcpy() in __copy_skb_header() */ @@ -3088,7 +3093,13 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f) */ static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) { - put_page(skb_frag_page(frag)); + struct page *page = skb_frag_page(frag); + +#ifdef CONFIG_PAGE_POOL + if (recycle && page_pool_return_skb_page(page)) + return; +#endif + put_page(page); } /** @@ -3100,7 +3111,7 @@ static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) */ static inline void skb_frag_unref(struct sk_buff *skb, int f) { - __skb_frag_unref(&skb_shinfo(skb)->frags[f], false); + __skb_frag_unref(&skb_shinfo(skb)->frags[f], skb->pp_recycle); } /** @@ -4699,5 +4710,21 @@ static inline u64 skb_get_kcov_handle(struct sk_buff *skb) #endif } +#ifdef CONFIG_PAGE_POOL +static inline void skb_mark_for_recycle(struct sk_buff *skb, struct page *page, + struct page_pool *pp) +{ + skb->pp_recycle = 1; + page_pool_store_mem_info(page, pp); +} +#endif + +static inline bool skb_pp_recycle(struct sk_buff *skb, void *data) +{ + if (!IS_ENABLED(CONFIG_PAGE_POOL) || !skb->pp_recycle) + return false; + return page_pool_return_skb_page(virt_to_page(data)); +} + #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ diff --git a/include/net/page_pool.h b/include/net/page_pool.h index b4b6de909c93..3dd62dd73027 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -146,6 +146,8 @@ inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool) return pool->p.dma_dir; } +bool page_pool_return_skb_page(struct page *page); + struct page_pool *page_pool_create(const struct page_pool_params *params); #ifdef CONFIG_PAGE_POOL @@ -251,4 +253,11 @@ static inline void page_pool_ring_unlock(struct page_pool *pool) spin_unlock_bh(&pool->ring.producer_lock); } +/* Store mem_info on struct page and use it while recycling skb frags */ +static inline +void page_pool_store_mem_info(struct page *page, struct page_pool *pp) +{ + page->pp = pp; +} + #endif /* _NET_PAGE_POOL_H */ diff --git a/net/core/page_pool.c b/net/core/page_pool.c index e1321bc9d316..5e4eb45b139c 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -628,3 +628,25 @@ void page_pool_update_nid(struct page_pool *pool, int new_nid) } } EXPORT_SYMBOL(page_pool_update_nid); + +bool page_pool_return_skb_page(struct page *page) +{ + struct page_pool *pp; + + page = compound_head(page); + if (unlikely(page->pp_magic != PP_SIGNATURE)) + return false; + + pp = page->pp; + + /* Driver set this to memory recycling info. Reset it on recycle. + * This will *not* work for NIC using a split-page memory model. + * The page will be returned to the pool here regardless of the + * 'flipped' fragment being in use or not. + */ + page->pp = NULL; + page_pool_put_full_page(pp, page, false); + + return true; +} +EXPORT_SYMBOL(page_pool_return_skb_page); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 12b7e90dd2b5..a0b1d4847efe 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -70,6 +70,7 @@ #include #include #include +#include #include #include @@ -645,10 +646,13 @@ static void skb_free_head(struct sk_buff *skb) { unsigned char *head = skb->head; - if (skb->head_frag) + if (skb->head_frag) { + if (skb_pp_recycle(skb, head)) + return; skb_free_frag(head); - else + } else { kfree(head); + } } static void skb_release_data(struct sk_buff *skb) @@ -664,7 +668,7 @@ static void skb_release_data(struct sk_buff *skb) skb_zcopy_clear(skb, true); for (i = 0; i < shinfo->nr_frags; i++) - __skb_frag_unref(&shinfo->frags[i], false); + __skb_frag_unref(&shinfo->frags[i], skb->pp_recycle); if (shinfo->frag_list) kfree_skb_list(shinfo->frag_list); @@ -1046,6 +1050,7 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) n->nohdr = 0; n->peeked = 0; C(pfmemalloc); + C(pp_recycle); n->destructor = NULL; C(tail); C(end); @@ -3495,7 +3500,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) fragto = &skb_shinfo(tgt)->frags[merge]; skb_frag_size_add(fragto, skb_frag_size(fragfrom)); - __skb_frag_unref(fragfrom, false); + __skb_frag_unref(fragfrom, skb->pp_recycle); } /* Reposition in the original skb */ @@ -5285,6 +5290,13 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, if (skb_cloned(to)) return false; + /* The page pool signature of struct page will eventually figure out + * which pages can be recycled or not but for now let's prohibit slab + * allocated and page_pool allocated SKBs from being coalesced. + */ + if (to->pp_recycle != from->pp_recycle) + return false; + if (len <= skb_tailroom(to)) { if (len) BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len)); -- cgit v1.2.3-71-gd317 From f27abde3042ab4d30d0003eaf5e6641baef94a56 Mon Sep 17 00:00:00 2001 From: Voon Weifeng Date: Tue, 8 Jun 2021 11:51:57 +0800 Subject: net: pcs: add 2500BASEX support for Intel mGbE controller XPCS IP supports 2500BASEX as PHY interface. It is configured as autonegotiation disable to cater for PHYs that does not supports 2500BASEX autonegotiation. v2: Add supported link speed masking. v3: Restructure to introduce xpcs_config_2500basex() used to configure the xpcs for 2.5G speeds. Added 2500BASEX specific information for configuration. v4: Fix indentation error Signed-off-by: Voon Weifeng Signed-off-by: Michael Sit Wei Hong Signed-off-by: David S. Miller --- drivers/net/pcs/pcs-xpcs.c | 56 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/pcs/pcs-xpcs.h | 1 + 2 files changed, 57 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 34164437c135..98c4a3973402 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -57,9 +57,12 @@ /* Clause 37 Defines */ /* VR MII MMD registers offsets */ +#define DW_VR_MII_MMD_CTRL 0x0000 #define DW_VR_MII_DIG_CTRL1 0x8000 #define DW_VR_MII_AN_CTRL 0x8001 #define DW_VR_MII_AN_INTR_STS 0x8002 +/* Enable 2.5G Mode */ +#define DW_VR_MII_DIG_CTRL1_2G5_EN BIT(2) /* EEE Mode Control Register */ #define DW_VR_MII_EEE_MCTRL0 0x8006 #define DW_VR_MII_EEE_MCTRL1 0x800b @@ -86,6 +89,11 @@ #define DW_VR_MII_C37_ANSGM_SP_1000 0x2 #define DW_VR_MII_C37_ANSGM_SP_LNKSTS BIT(4) +/* SR MII MMD Control defines */ +#define AN_CL37_EN BIT(12) /* Enable Clause 37 auto-nego */ +#define SGMII_SPEED_SS13 BIT(13) /* SGMII speed along with SS6 */ +#define SGMII_SPEED_SS6 BIT(6) /* SGMII speed along with SS13 */ + /* VR MII EEE Control 0 defines */ #define DW_VR_MII_EEE_LTX_EN BIT(0) /* LPI Tx Enable */ #define DW_VR_MII_EEE_LRX_EN BIT(1) /* LPI Rx Enable */ @@ -161,6 +169,14 @@ static const int xpcs_sgmii_features[] = { __ETHTOOL_LINK_MODE_MASK_NBITS, }; +static const int xpcs_2500basex_features[] = { + ETHTOOL_LINK_MODE_Asym_Pause_BIT, + ETHTOOL_LINK_MODE_Autoneg_BIT, + ETHTOOL_LINK_MODE_2500baseX_Full_BIT, + ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + __ETHTOOL_LINK_MODE_MASK_NBITS, +}; + static const phy_interface_t xpcs_usxgmii_interfaces[] = { PHY_INTERFACE_MODE_USXGMII, }; @@ -177,11 +193,17 @@ static const phy_interface_t xpcs_sgmii_interfaces[] = { PHY_INTERFACE_MODE_SGMII, }; +static const phy_interface_t xpcs_2500basex_interfaces[] = { + PHY_INTERFACE_MODE_2500BASEX, + PHY_INTERFACE_MODE_MAX, +}; + enum { DW_XPCS_USXGMII, DW_XPCS_10GKR, DW_XPCS_XLGMII, DW_XPCS_SGMII, + DW_XPCS_2500BASEX, DW_XPCS_INTERFACE_MAX, }; @@ -306,6 +328,7 @@ static int xpcs_soft_reset(struct mdio_xpcs_args *xpcs, dev = MDIO_MMD_PCS; break; case DW_AN_C37_SGMII: + case DW_2500BASEX: dev = MDIO_MMD_VEND2; break; default: @@ -804,6 +827,28 @@ static int xpcs_config_aneg_c37_sgmii(struct mdio_xpcs_args *xpcs) return xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_DIG_CTRL1, ret); } +static int xpcs_config_2500basex(struct mdio_xpcs_args *xpcs) +{ + int ret; + + ret = xpcs_read(xpcs, MDIO_MMD_VEND2, DW_VR_MII_DIG_CTRL1); + if (ret < 0) + return ret; + ret |= DW_VR_MII_DIG_CTRL1_2G5_EN; + ret &= ~DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW; + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_DIG_CTRL1, ret); + if (ret < 0) + return ret; + + ret = xpcs_read(xpcs, MDIO_MMD_VEND2, DW_VR_MII_MMD_CTRL); + if (ret < 0) + return ret; + ret &= ~AN_CL37_EN; + ret |= SGMII_SPEED_SS6; + ret &= ~SGMII_SPEED_SS13; + return xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_MMD_CTRL, ret); +} + static int xpcs_do_config(struct mdio_xpcs_args *xpcs, phy_interface_t interface, unsigned int mode) { @@ -827,6 +872,11 @@ static int xpcs_do_config(struct mdio_xpcs_args *xpcs, if (ret) return ret; break; + case DW_2500BASEX: + ret = xpcs_config_2500basex(xpcs); + if (ret) + return ret; + break; default: return -1; } @@ -1023,6 +1073,12 @@ static const struct xpcs_compat synopsys_xpcs_compat[DW_XPCS_INTERFACE_MAX] = { .num_interfaces = ARRAY_SIZE(xpcs_sgmii_interfaces), .an_mode = DW_AN_C37_SGMII, }, + [DW_XPCS_2500BASEX] = { + .supported = xpcs_2500basex_features, + .interface = xpcs_2500basex_interfaces, + .num_interfaces = ARRAY_SIZE(xpcs_2500basex_features), + .an_mode = DW_2500BASEX, + }, }; static const struct xpcs_id xpcs_id_list[] = { diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 0860a5b59f10..4d815f03b4b2 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -13,6 +13,7 @@ /* AN mode */ #define DW_AN_C73 1 #define DW_AN_C37_SGMII 2 +#define DW_2500BASEX 3 struct xpcs_id; -- cgit v1.2.3-71-gd317 From 46682cb86a37da435e5668db98555a1de0f0448b Mon Sep 17 00:00:00 2001 From: Voon Weifeng Date: Tue, 8 Jun 2021 11:51:58 +0800 Subject: net: stmmac: enable Intel mGbE 2.5Gbps link speed The Intel mGbE supports 2.5Gbps link speed by increasing the clock rate by 2.5 times of the original rate. In this mode, the serdes/PHY operates at a serial baud rate of 3.125 Gbps and the PCS data path and GMII interface of the MAC operate at 312.5 MHz instead of 125 MHz. For Intel mGbE, the overclocking of 2.5 times clock rate to support 2.5G is only able to be configured in the BIOS during boot time. Kernel driver has no access to modify the clock rate for 1Gbps/2.5G mode. The way to determined the current 1G/2.5G mode is by reading a dedicated adhoc register through mdio bus. In short, after the system boot up, it is either in 1G mode or 2.5G mode which not able to be changed on the fly. Compared to 1G mode, the 2.5G mode selects the 2500BASEX as PHY interface and disables the xpcs_an_inband. This is to cater for some PHYs that only supports 2500BASEX PHY interface with no autonegotiation. v2: remove MAC supported link speed masking v3: Restructure to introduce intel_speed_mode_2500() to read serdes registers for max speed supported and select the appropritate configuration. Use max_speed to determine the supported link speed mask. Signed-off-by: Voon Weifeng Signed-off-by: Michael Sit Wei Hong Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 48 ++++++++++++++++++++++- drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h | 13 ++++++ drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 1 + drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 7 ++++ include/linux/stmmac.h | 1 + 5 files changed, 69 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index 2ecf93c84b9d..6a9a19b0844c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -102,6 +102,22 @@ static int intel_serdes_powerup(struct net_device *ndev, void *priv_data) serdes_phy_addr = intel_priv->mdio_adhoc_addr; + /* Set the serdes rate and the PCLK rate */ + data = mdiobus_read(priv->mii, serdes_phy_addr, + SERDES_GCR0); + + data &= ~SERDES_RATE_MASK; + data &= ~SERDES_PCLK_MASK; + + if (priv->plat->max_speed == 2500) + data |= SERDES_RATE_PCIE_GEN2 << SERDES_RATE_PCIE_SHIFT | + SERDES_PCLK_37p5MHZ << SERDES_PCLK_SHIFT; + else + data |= SERDES_RATE_PCIE_GEN1 << SERDES_RATE_PCIE_SHIFT | + SERDES_PCLK_70MHZ << SERDES_PCLK_SHIFT; + + mdiobus_write(priv->mii, serdes_phy_addr, SERDES_GCR0, data); + /* assert clk_req */ data = mdiobus_read(priv->mii, serdes_phy_addr, SERDES_GCR0); data |= SERDES_PLL_CLK; @@ -230,6 +246,32 @@ static void intel_serdes_powerdown(struct net_device *ndev, void *intel_data) } } +static void intel_speed_mode_2500(struct net_device *ndev, void *intel_data) +{ + struct intel_priv_data *intel_priv = intel_data; + struct stmmac_priv *priv = netdev_priv(ndev); + int serdes_phy_addr = 0; + u32 data = 0; + + serdes_phy_addr = intel_priv->mdio_adhoc_addr; + + /* Determine the link speed mode: 2.5Gbps/1Gbps */ + data = mdiobus_read(priv->mii, serdes_phy_addr, + SERDES_GCR); + + if (((data & SERDES_LINK_MODE_MASK) >> SERDES_LINK_MODE_SHIFT) == + SERDES_LINK_MODE_2G5) { + dev_info(priv->device, "Link Speed Mode: 2.5Gbps\n"); + priv->plat->max_speed = 2500; + priv->plat->phy_interface = PHY_INTERFACE_MODE_2500BASEX; + priv->plat->mdio_bus_data->xpcs_an_inband = false; + } else { + priv->plat->max_speed = 1000; + priv->plat->phy_interface = PHY_INTERFACE_MODE_SGMII; + priv->plat->mdio_bus_data->xpcs_an_inband = true; + } +} + /* Program PTP Clock Frequency for different variant of * Intel mGBE that has slightly different GPO mapping */ @@ -586,7 +628,7 @@ static int ehl_sgmii_data(struct pci_dev *pdev, { plat->bus_id = 1; plat->phy_interface = PHY_INTERFACE_MODE_SGMII; - + plat->speed_mode_2500 = intel_speed_mode_2500; plat->serdes_powerup = intel_serdes_powerup; plat->serdes_powerdown = intel_serdes_powerdown; @@ -639,6 +681,7 @@ static int ehl_pse0_sgmii1g_data(struct pci_dev *pdev, struct plat_stmmacenet_data *plat) { plat->phy_interface = PHY_INTERFACE_MODE_SGMII; + plat->speed_mode_2500 = intel_speed_mode_2500; plat->serdes_powerup = intel_serdes_powerup; plat->serdes_powerdown = intel_serdes_powerdown; return ehl_pse0_common_data(pdev, plat); @@ -677,6 +720,7 @@ static int ehl_pse1_sgmii1g_data(struct pci_dev *pdev, struct plat_stmmacenet_data *plat) { plat->phy_interface = PHY_INTERFACE_MODE_SGMII; + plat->speed_mode_2500 = intel_speed_mode_2500; plat->serdes_powerup = intel_serdes_powerup; plat->serdes_powerdown = intel_serdes_powerdown; return ehl_pse1_common_data(pdev, plat); @@ -711,6 +755,7 @@ static int tgl_sgmii_phy0_data(struct pci_dev *pdev, { plat->bus_id = 1; plat->phy_interface = PHY_INTERFACE_MODE_SGMII; + plat->speed_mode_2500 = intel_speed_mode_2500; plat->serdes_powerup = intel_serdes_powerup; plat->serdes_powerdown = intel_serdes_powerdown; return tgl_common_data(pdev, plat); @@ -725,6 +770,7 @@ static int tgl_sgmii_phy1_data(struct pci_dev *pdev, { plat->bus_id = 2; plat->phy_interface = PHY_INTERFACE_MODE_SGMII; + plat->speed_mode_2500 = intel_speed_mode_2500; plat->serdes_powerup = intel_serdes_powerup; plat->serdes_powerdown = intel_serdes_powerdown; return tgl_common_data(pdev, plat); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h index 542acb8ce467..20d14e588044 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h @@ -9,6 +9,7 @@ #define POLL_DELAY_US 8 /* SERDES Register */ +#define SERDES_GCR 0x0 /* Global Conguration */ #define SERDES_GSR0 0x5 /* Global Status Reg0 */ #define SERDES_GCR0 0xb /* Global Configuration Reg0 */ @@ -17,8 +18,20 @@ #define SERDES_PHY_RX_CLK BIT(1) /* PSE SGMII PHY rx clk */ #define SERDES_RST BIT(2) /* Serdes Reset */ #define SERDES_PWR_ST_MASK GENMASK(6, 4) /* Serdes Power state*/ +#define SERDES_RATE_MASK GENMASK(9, 8) +#define SERDES_PCLK_MASK GENMASK(14, 12) /* PCLK rate to PHY */ +#define SERDES_LINK_MODE_MASK GENMASK(2, 1) +#define SERDES_LINK_MODE_SHIFT 1 #define SERDES_PWR_ST_SHIFT 4 #define SERDES_PWR_ST_P0 0x0 #define SERDES_PWR_ST_P3 0x3 +#define SERDES_LINK_MODE_2G5 0x3 +#define SERSED_LINK_MODE_1G 0x2 +#define SERDES_PCLK_37p5MHZ 0x0 +#define SERDES_PCLK_70MHZ 0x1 +#define SERDES_RATE_PCIE_GEN1 0x0 +#define SERDES_RATE_PCIE_GEN2 0x1 +#define SERDES_RATE_PCIE_SHIFT 8 +#define SERDES_PCLK_SHIFT 12 #endif /* __DWMAC_INTEL_H__ */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index f35c03c9f91e..67ba083eb90c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -1358,6 +1358,7 @@ int dwmac4_setup(struct stmmac_priv *priv) mac->link.speed10 = GMAC_CONFIG_PS; mac->link.speed100 = GMAC_CONFIG_FES | GMAC_CONFIG_PS; mac->link.speed1000 = 0; + mac->link.speed2500 = GMAC_CONFIG_FES; mac->link.speed_mask = GMAC_CONFIG_FES | GMAC_CONFIG_PS; mac->mii.addr = GMAC_MDIO_ADDR; mac->mii.data = GMAC_MDIO_DATA; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index af406ea3dd46..1b12a2f8bfb5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -931,6 +931,10 @@ static void stmmac_validate(struct phylink_config *config, if ((max_speed > 0) && (max_speed < 1000)) { phylink_set(mask, 1000baseT_Full); phylink_set(mask, 1000baseX_Full); + } else if (priv->plat->has_gmac4) { + if (!max_speed || max_speed >= 2500) + phylink_set(mac_supported, 2500baseT_Full); + phylink_set(mac_supported, 2500baseX_Full); } else if (priv->plat->has_xgmac) { if (!max_speed || (max_speed >= 2500)) { phylink_set(mac_supported, 2500baseT_Full); @@ -6993,6 +6997,9 @@ int stmmac_dvr_probe(struct device *device, } } + if (priv->plat->speed_mode_2500) + priv->plat->speed_mode_2500(ndev, priv->plat->bsp_priv); + if (priv->plat->mdio_bus_data) { if (priv->plat->mdio_bus_data->has_xpcs) { ret = stmmac_xpcs_setup(priv->mii); diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index e55a4807e3ea..b10be3385a30 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -223,6 +223,7 @@ struct plat_stmmacenet_data { void (*fix_mac_speed)(void *priv, unsigned int speed); int (*serdes_powerup)(struct net_device *ndev, void *priv); void (*serdes_powerdown)(struct net_device *ndev, void *priv); + void (*speed_mode_2500)(struct net_device *ndev, void *priv); void (*ptp_clk_freq_config)(void *priv); int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); -- cgit v1.2.3-71-gd317 From b64d76b782264aa91c236c11c72646459b04c301 Mon Sep 17 00:00:00 2001 From: Sergey Ryazanov Date: Tue, 8 Jun 2021 07:02:34 +0300 Subject: net: wwan: make WWAN_PORT_MAX meaning less surprised It is quite unusual when some value can not be equal to a defined range max value. Also most subsystems defines FOO_TYPE_MAX as a maximum valid value. So turn the WAN_PORT_MAX meaning from the number of supported port types to the maximum valid port type. Signed-off-by: Sergey Ryazanov Reviewed-by: Loic Poulain Signed-off-by: David S. Miller --- drivers/net/wwan/wwan_core.c | 2 +- include/linux/wwan.h | 12 +++++++++--- 2 files changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c index 6e8f19c71a9e..632ff86398ac 100644 --- a/drivers/net/wwan/wwan_core.c +++ b/drivers/net/wwan/wwan_core.c @@ -250,7 +250,7 @@ struct wwan_port *wwan_create_port(struct device *parent, struct wwan_port *port; int minor, err = -ENOMEM; - if (type >= WWAN_PORT_MAX || !ops) + if (type > WWAN_PORT_MAX || !ops) return ERR_PTR(-EINVAL); /* A port is always a child of a WWAN device, retrieve (allocate or diff --git a/include/linux/wwan.h b/include/linux/wwan.h index 7216c114d758..fa33cc16d931 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -15,8 +15,10 @@ * @WWAN_PORT_QMI: Qcom modem/MSM interface for modem control * @WWAN_PORT_QCDM: Qcom Modem diagnostic interface * @WWAN_PORT_FIREHOSE: XML based command protocol - * @WWAN_PORT_UNKNOWN: Unknown port type - * @WWAN_PORT_MAX: Number of supported port types + * + * @WWAN_PORT_MAX: Highest supported port types + * @WWAN_PORT_UNKNOWN: Special value to indicate an unknown port type + * @__WWAN_PORT_MAX: Internal use */ enum wwan_port_type { WWAN_PORT_AT, @@ -24,8 +26,12 @@ enum wwan_port_type { WWAN_PORT_QMI, WWAN_PORT_QCDM, WWAN_PORT_FIREHOSE, + + /* Add new port types above this line */ + + __WWAN_PORT_MAX, + WWAN_PORT_MAX = __WWAN_PORT_MAX - 1, WWAN_PORT_UNKNOWN, - WWAN_PORT_MAX = WWAN_PORT_UNKNOWN, }; struct wwan_port; -- cgit v1.2.3-71-gd317 From e67f325e9cd67562b761e884680c0fec03a6f404 Mon Sep 17 00:00:00 2001 From: Matthew Hagan Date: Tue, 8 Jun 2021 19:59:06 +0100 Subject: net: stmmac: explicitly deassert GMAC_AHB_RESET We are currently assuming that GMAC_AHB_RESET will already be deasserted by the bootloader. However if this has not been done, probing of the GMAC will fail. To remedy this we must ensure GMAC_AHB_RESET has been deasserted prior to probing. v2 changes: - remove NULL condition check for stmmac_ahb_rst in stmmac_main.c - unwrap dev_err() message in stmmac_main.c - add PTR_ERR() around plat->stmmac_ahb_rst in stmmac_platform.c v3 changes: - add error pointer to dev_err() output - add reset_control_assert(stmmac_ahb_rst) in stmmac_dvr_remove - revert PTR_ERR() around plat->stmmac_ahb_rst since this is performed on the returned value of ret by the calling function Signed-off-by: Matthew Hagan Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 6 ++++++ drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 7 +++++++ include/linux/stmmac.h | 1 + 3 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index f2adff59b07d..1c881ec8cd04 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -6843,6 +6843,11 @@ int stmmac_dvr_probe(struct device *device, reset_control_reset(priv->plat->stmmac_rst); } + ret = reset_control_deassert(priv->plat->stmmac_ahb_rst); + if (ret == -ENOTSUPP) + dev_err(priv->device, "unable to bring out of ahb reset: %pe\n", + ERR_PTR(ret)); + /* Init MAC and get the capabilities */ ret = stmmac_hw_init(priv); if (ret) @@ -7086,6 +7091,7 @@ int stmmac_dvr_remove(struct device *dev) phylink_destroy(priv->phylink); if (priv->plat->stmmac_rst) reset_control_assert(priv->plat->stmmac_rst); + reset_control_assert(priv->plat->stmmac_ahb_rst); pm_runtime_put(dev); pm_runtime_disable(dev); if (priv->hw->pcs != STMMAC_PCS_TBI && diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 97a1fedcc9ac..d8ae58bdbbe3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -600,6 +600,13 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) goto error_hw_init; } + plat->stmmac_ahb_rst = devm_reset_control_get_optional_shared( + &pdev->dev, "ahb"); + if (IS_ERR(plat->stmmac_ahb_rst)) { + ret = plat->stmmac_ahb_rst; + goto error_hw_init; + } + return plat; error_hw_init: diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index b10be3385a30..3867980d1447 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -240,6 +240,7 @@ struct plat_stmmacenet_data { unsigned int mult_fact_100ns; s32 ptp_max_adj; struct reset_control *stmmac_rst; + struct reset_control *stmmac_ahb_rst; struct stmmac_axi *axi; int has_gmac4; bool has_sun8i; -- cgit v1.2.3-71-gd317 From 67133eaa93e810f5c510cd0ec6e2e7ca76fc1340 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Tue, 9 Mar 2021 03:29:16 +0200 Subject: net/mlx5: mlx5_ifc support for header insert/remove Add support for HCA caps 2 that contains capabilities for the new insert/remove header actions. Added the required definitions for supporting the new reformat type: added packet reformat parameters, reformat anchors and definitions to allow copy/set into the inserted EMD (Embedded MetaData) tag. Signed-off-by: Yevgeny Kliteynik Signed-off-by: Vlad Buslov Reviewed-by: Jianbo Liu Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fw.c | 6 +++++ include/linux/mlx5/device.h | 10 +++++++ include/linux/mlx5/mlx5_ifc.h | 40 +++++++++++++++++++++++----- 3 files changed, 50 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index 02558ac2ace6..016d26f809a5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -148,6 +148,12 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) if (err) return err; + if (MLX5_CAP_GEN(dev, hca_cap_2)) { + err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL_2); + if (err) + return err; + } + if (MLX5_CAP_GEN(dev, eth_net_offloads)) { err = mlx5_core_get_caps(dev, MLX5_CAP_ETHERNET_OFFLOADS); if (err) diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 578c4ccae91c..0025913505ab 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1179,6 +1179,7 @@ enum mlx5_cap_type { MLX5_CAP_VDPA_EMULATION = 0x13, MLX5_CAP_DEV_EVENT = 0x14, MLX5_CAP_IPSEC, + MLX5_CAP_GENERAL_2 = 0x20, /* NUM OF CAP Types */ MLX5_CAP_NUM }; @@ -1220,6 +1221,15 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_GEN_MAX(mdev, cap) \ MLX5_GET(cmd_hca_cap, mdev->caps.hca_max[MLX5_CAP_GENERAL], cap) +#define MLX5_CAP_GEN_2(mdev, cap) \ + MLX5_GET(cmd_hca_cap_2, mdev->caps.hca_cur[MLX5_CAP_GENERAL_2], cap) + +#define MLX5_CAP_GEN_2_64(mdev, cap) \ + MLX5_GET64(cmd_hca_cap_2, mdev->caps.hca_cur[MLX5_CAP_GENERAL_2], cap) + +#define MLX5_CAP_GEN_2_MAX(mdev, cap) \ + MLX5_GET(cmd_hca_cap_2, mdev->caps.hca_max[MLX5_CAP_GENERAL_2], cap) + #define MLX5_CAP_ETH(mdev, cap) \ MLX5_GET(per_protocol_networking_offload_caps,\ mdev->caps.hca_cur[MLX5_CAP_ETHERNET_OFFLOADS], cap) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index eb86e80e4643..057db0eaf195 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -435,7 +435,10 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reserved_at_40[0x20]; - u8 reserved_at_60[0x18]; + u8 reserved_at_60[0x2]; + u8 reformat_insert[0x1]; + u8 reformat_remove[0x1]; + u8 reserver_at_64[0x14]; u8 log_max_ft_num[0x8]; u8 reserved_at_80[0x10]; @@ -1312,7 +1315,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_0[0x1f]; u8 vhca_resource_manager[0x1]; - u8 reserved_at_20[0x3]; + u8 hca_cap_2[0x1]; + u8 reserved_at_21[0x2]; u8 event_on_vhca_state_teardown_request[0x1]; u8 event_on_vhca_state_in_use[0x1]; u8 event_on_vhca_state_active[0x1]; @@ -1732,6 +1736,17 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_7c0[0x40]; }; +struct mlx5_ifc_cmd_hca_cap_2_bits { + u8 reserved_at_0[0xa0]; + + u8 max_reformat_insert_size[0x8]; + u8 max_reformat_insert_offset[0x8]; + u8 max_reformat_remove_size[0x8]; + u8 max_reformat_remove_offset[0x8]; + + u8 reserved_at_c0[0x740]; +}; + enum mlx5_flow_destination_type { MLX5_FLOW_DESTINATION_TYPE_VPORT = 0x0, MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE = 0x1, @@ -3105,6 +3120,7 @@ struct mlx5_ifc_roce_addr_layout_bits { union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_cmd_hca_cap_bits cmd_hca_cap; + struct mlx5_ifc_cmd_hca_cap_2_bits cmd_hca_cap_2; struct mlx5_ifc_odp_cap_bits odp_cap; struct mlx5_ifc_atomic_caps_bits atomic_caps; struct mlx5_ifc_roce_cap_bits roce_cap; @@ -5785,12 +5801,14 @@ struct mlx5_ifc_query_eq_in_bits { }; struct mlx5_ifc_packet_reformat_context_in_bits { - u8 reserved_at_0[0x5]; - u8 reformat_type[0x3]; - u8 reserved_at_8[0xe]; + u8 reformat_type[0x8]; + u8 reserved_at_8[0x4]; + u8 reformat_param_0[0x4]; + u8 reserved_at_10[0x6]; u8 reformat_data_size[0xa]; - u8 reserved_at_20[0x10]; + u8 reformat_param_1[0x8]; + u8 reserved_at_28[0x8]; u8 reformat_data[2][0x8]; u8 more_reformat_data[][0x8]; @@ -5830,12 +5848,20 @@ struct mlx5_ifc_alloc_packet_reformat_context_out_bits { u8 reserved_at_60[0x20]; }; +enum { + MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START = 0x1, + MLX5_REFORMAT_CONTEXT_ANCHOR_IP_START = 0x7, + MLX5_REFORMAT_CONTEXT_ANCHOR_TCP_UDP_START = 0x9, +}; + enum mlx5_reformat_ctx_type { MLX5_REFORMAT_TYPE_L2_TO_VXLAN = 0x0, MLX5_REFORMAT_TYPE_L2_TO_NVGRE = 0x1, MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL = 0x2, MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2 = 0x3, MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL = 0x4, + MLX5_REFORMAT_TYPE_INSERT_HDR = 0xf, + MLX5_REFORMAT_TYPE_REMOVE_HDR = 0x10, }; struct mlx5_ifc_alloc_packet_reformat_context_in_bits { @@ -5956,6 +5982,8 @@ enum { MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM = 0x59, MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM = 0x5B, MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME = 0x5D, + MLX5_ACTION_IN_FIELD_OUT_EMD_47_32 = 0x6F, + MLX5_ACTION_IN_FIELD_OUT_EMD_31_0 = 0x70, }; struct mlx5_ifc_alloc_modify_header_context_out_bits { -- cgit v1.2.3-71-gd317 From 3f3f05ab88722224fef5b0b78a0969f6b54f2cba Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Tue, 9 Mar 2021 03:30:44 +0200 Subject: net/mlx5: Added new parameters to reformat context Adding new reformat context type (INSERT_HEADER) requires adding two new parameters to reformat context - reformat_param_0 and reformat_param_1. As defined by HW spec, these parameters have different meaning for different reformat context type. The first parameter (reformat_param_0) is not new to HW spec, but it wasn't used by any of the supported reformats. The second parameter (reformat_param_1) is new to the HW spec - it was added to allow supporting INSERT_HEADER. For NSERT_HEADER, reformat_param_0 indicates the header used to reference the location of the inserted header, and reformat_param_1 indicates the offset of the inserted header from the reference point defined by reformat_param_0. Signed-off-by: Yevgeny Kliteynik Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/fs.c | 9 +++-- .../net/ethernet/mellanox/mlx5/core/en/tc_tun.c | 38 +++++++++++++++------- .../ethernet/mellanox/mlx5/core/en/tc_tun_encap.c | 17 +++++++--- drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 29 +++++++++-------- drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h | 4 +-- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 9 ++--- .../mellanox/mlx5/core/steering/dr_action.c | 2 ++ .../ethernet/mellanox/mlx5/core/steering/fs_dr.c | 17 +++++----- .../ethernet/mellanox/mlx5/core/steering/mlx5dr.h | 2 ++ include/linux/mlx5/fs.h | 12 +++++-- 10 files changed, 86 insertions(+), 53 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/fs.c b/drivers/infiniband/hw/mlx5/fs.c index 2fc6a60c4e77..941adf5cf3d0 100644 --- a/drivers/infiniband/hw/mlx5/fs.c +++ b/drivers/infiniband/hw/mlx5/fs.c @@ -2280,6 +2280,7 @@ static int mlx5_ib_flow_action_create_packet_reformat_ctx( u8 ft_type, u8 dv_prt, void *in, size_t len) { + struct mlx5_pkt_reformat_params reformat_params; enum mlx5_flow_namespace_type namespace; u8 prm_prt; int ret; @@ -2292,9 +2293,13 @@ static int mlx5_ib_flow_action_create_packet_reformat_ctx( if (ret) return ret; + memset(&reformat_params, 0, sizeof(reformat_params)); + reformat_params.type = prm_prt; + reformat_params.size = len; + reformat_params.data = in; maction->flow_action_raw.pkt_reformat = - mlx5_packet_reformat_alloc(dev->mdev, prm_prt, len, - in, namespace); + mlx5_packet_reformat_alloc(dev->mdev, &reformat_params, + namespace); if (IS_ERR(maction->flow_action_raw.pkt_reformat)) { ret = PTR_ERR(maction->flow_action_raw.pkt_reformat); return ret; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 172e0474f2e6..8f79f04eccd6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -212,6 +212,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, { int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size); const struct ip_tunnel_key *tun_key = &e->tun_info->key; + struct mlx5_pkt_reformat_params reformat_params; struct mlx5e_neigh m_neigh = {}; TC_TUN_ROUTE_ATTR_INIT(attr); int ipv4_encap_size; @@ -295,9 +296,12 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, */ goto release_neigh; } - e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, - e->reformat_type, - ipv4_encap_size, encap_header, + + memset(&reformat_params, 0, sizeof(reformat_params)); + reformat_params.type = e->reformat_type; + reformat_params.size = ipv4_encap_size; + reformat_params.data = encap_header; + e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params, MLX5_FLOW_NAMESPACE_FDB); if (IS_ERR(e->pkt_reformat)) { err = PTR_ERR(e->pkt_reformat); @@ -324,6 +328,7 @@ int mlx5e_tc_tun_update_header_ipv4(struct mlx5e_priv *priv, { int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size); const struct ip_tunnel_key *tun_key = &e->tun_info->key; + struct mlx5_pkt_reformat_params reformat_params; TC_TUN_ROUTE_ATTR_INIT(attr); int ipv4_encap_size; char *encap_header; @@ -396,9 +401,12 @@ int mlx5e_tc_tun_update_header_ipv4(struct mlx5e_priv *priv, */ goto release_neigh; } - e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, - e->reformat_type, - ipv4_encap_size, encap_header, + + memset(&reformat_params, 0, sizeof(reformat_params)); + reformat_params.type = e->reformat_type; + reformat_params.size = ipv4_encap_size; + reformat_params.data = encap_header; + e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params, MLX5_FLOW_NAMESPACE_FDB); if (IS_ERR(e->pkt_reformat)) { err = PTR_ERR(e->pkt_reformat); @@ -471,6 +479,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, { int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size); const struct ip_tunnel_key *tun_key = &e->tun_info->key; + struct mlx5_pkt_reformat_params reformat_params; struct mlx5e_neigh m_neigh = {}; TC_TUN_ROUTE_ATTR_INIT(attr); struct ipv6hdr *ip6h; @@ -553,9 +562,11 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, goto release_neigh; } - e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, - e->reformat_type, - ipv6_encap_size, encap_header, + memset(&reformat_params, 0, sizeof(reformat_params)); + reformat_params.type = e->reformat_type; + reformat_params.size = ipv6_encap_size; + reformat_params.data = encap_header; + e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params, MLX5_FLOW_NAMESPACE_FDB); if (IS_ERR(e->pkt_reformat)) { err = PTR_ERR(e->pkt_reformat); @@ -582,6 +593,7 @@ int mlx5e_tc_tun_update_header_ipv6(struct mlx5e_priv *priv, { int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size); const struct ip_tunnel_key *tun_key = &e->tun_info->key; + struct mlx5_pkt_reformat_params reformat_params; TC_TUN_ROUTE_ATTR_INIT(attr); struct ipv6hdr *ip6h; int ipv6_encap_size; @@ -654,9 +666,11 @@ int mlx5e_tc_tun_update_header_ipv6(struct mlx5e_priv *priv, goto release_neigh; } - e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, - e->reformat_type, - ipv6_encap_size, encap_header, + memset(&reformat_params, 0, sizeof(reformat_params)); + reformat_params.type = e->reformat_type; + reformat_params.size = ipv6_encap_size; + reformat_params.data = encap_header; + e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params, MLX5_FLOW_NAMESPACE_FDB); if (IS_ERR(e->pkt_reformat)) { err = PTR_ERR(e->pkt_reformat); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index f1fb11680d20..0dfd51d2d178 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -120,6 +120,7 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, struct list_head *flow_list) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + struct mlx5_pkt_reformat_params reformat_params; struct mlx5_esw_flow_attr *esw_attr; struct mlx5_flow_handle *rule; struct mlx5_flow_attr *attr; @@ -130,9 +131,12 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, if (e->flags & MLX5_ENCAP_ENTRY_NO_ROUTE) return; + memset(&reformat_params, 0, sizeof(reformat_params)); + reformat_params.type = e->reformat_type; + reformat_params.size = e->encap_size; + reformat_params.data = e->encap_header; e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, - e->reformat_type, - e->encap_size, e->encap_header, + &reformat_params, MLX5_FLOW_NAMESPACE_FDB); if (IS_ERR(e->pkt_reformat)) { mlx5_core_warn(priv->mdev, "Failed to offload cached encapsulation header, %lu\n", @@ -812,6 +816,7 @@ int mlx5e_attach_decap(struct mlx5e_priv *priv, { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_esw_flow_attr *attr = flow->attr->esw_attr; + struct mlx5_pkt_reformat_params reformat_params; struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5e_decap_entry *d; struct mlx5e_decap_key key; @@ -853,10 +858,12 @@ int mlx5e_attach_decap(struct mlx5e_priv *priv, hash_add_rcu(esw->offloads.decap_tbl, &d->hlist, hash_key); mutex_unlock(&esw->offloads.decap_tbl_lock); + memset(&reformat_params, 0, sizeof(reformat_params)); + reformat_params.type = MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2; + reformat_params.size = sizeof(parse_attr->eth); + reformat_params.data = &parse_attr->eth; d->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, - MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2, - sizeof(parse_attr->eth), - &parse_attr->eth, + &reformat_params, MLX5_FLOW_NAMESPACE_FDB); if (IS_ERR(d->pkt_reformat)) { err = PTR_ERR(d->pkt_reformat); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index b7aae8b75760..896a6c3dbdb7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -111,9 +111,7 @@ static int mlx5_cmd_stub_delete_fte(struct mlx5_flow_root_namespace *ns, } static int mlx5_cmd_stub_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns, - int reformat_type, - size_t size, - void *reformat_data, + struct mlx5_pkt_reformat_params *params, enum mlx5_flow_namespace_type namespace, struct mlx5_pkt_reformat *pkt_reformat) { @@ -701,9 +699,7 @@ int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len, } static int mlx5_cmd_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns, - int reformat_type, - size_t size, - void *reformat_data, + struct mlx5_pkt_reformat_params *params, enum mlx5_flow_namespace_type namespace, struct mlx5_pkt_reformat *pkt_reformat) { @@ -721,14 +717,14 @@ static int mlx5_cmd_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns, else max_encap_size = MLX5_CAP_FLOWTABLE(dev, max_encap_header_size); - if (size > max_encap_size) { + if (params->size > max_encap_size) { mlx5_core_warn(dev, "encap size %zd too big, max supported is %d\n", - size, max_encap_size); + params->size, max_encap_size); return -EINVAL; } - in = kzalloc(MLX5_ST_SZ_BYTES(alloc_packet_reformat_context_in) + size, - GFP_KERNEL); + in = kzalloc(MLX5_ST_SZ_BYTES(alloc_packet_reformat_context_in) + + params->size, GFP_KERNEL); if (!in) return -ENOMEM; @@ -737,15 +733,20 @@ static int mlx5_cmd_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns, reformat = MLX5_ADDR_OF(packet_reformat_context_in, packet_reformat_context_in, reformat_data); - inlen = reformat - (void *)in + size; + inlen = reformat - (void *)in + params->size; MLX5_SET(alloc_packet_reformat_context_in, in, opcode, MLX5_CMD_OP_ALLOC_PACKET_REFORMAT_CONTEXT); MLX5_SET(packet_reformat_context_in, packet_reformat_context_in, - reformat_data_size, size); + reformat_data_size, params->size); MLX5_SET(packet_reformat_context_in, packet_reformat_context_in, - reformat_type, reformat_type); - memcpy(reformat, reformat_data, size); + reformat_type, params->type); + MLX5_SET(packet_reformat_context_in, packet_reformat_context_in, + reformat_param_0, params->param_0); + MLX5_SET(packet_reformat_context_in, packet_reformat_context_in, + reformat_param_1, params->param_1); + if (params->data && params->size) + memcpy(reformat, params->data, params->size); err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index c2e102ed82ad..5ecd33cdc087 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -77,9 +77,7 @@ struct mlx5_flow_cmds { bool disconnect); int (*packet_reformat_alloc)(struct mlx5_flow_root_namespace *ns, - int reformat_type, - size_t size, - void *reformat_data, + struct mlx5_pkt_reformat_params *params, enum mlx5_flow_namespace_type namespace, struct mlx5_pkt_reformat *pkt_reformat); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 1b7a1cde097c..c0936b4e53a9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -3165,9 +3165,7 @@ void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, EXPORT_SYMBOL(mlx5_modify_header_dealloc); struct mlx5_pkt_reformat *mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, - int reformat_type, - size_t size, - void *reformat_data, + struct mlx5_pkt_reformat_params *params, enum mlx5_flow_namespace_type ns_type) { struct mlx5_pkt_reformat *pkt_reformat; @@ -3183,9 +3181,8 @@ struct mlx5_pkt_reformat *mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, return ERR_PTR(-ENOMEM); pkt_reformat->ns_type = ns_type; - pkt_reformat->reformat_type = reformat_type; - err = root->cmds->packet_reformat_alloc(root, reformat_type, size, - reformat_data, ns_type, + pkt_reformat->reformat_type = params->type; + err = root->cmds->packet_reformat_alloc(root, params, ns_type, pkt_reformat); if (err) { kfree(pkt_reformat); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index 1b7a0e94d432..13fceba11d3f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -937,6 +937,8 @@ struct mlx5dr_action *mlx5dr_action_create_push_vlan(struct mlx5dr_domain *dmn, struct mlx5dr_action * mlx5dr_action_create_packet_reformat(struct mlx5dr_domain *dmn, enum mlx5dr_action_reformat_type reformat_type, + u8 reformat_param_0, + u8 reformat_param_1, size_t data_sz, void *data) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c index ee0e9d79aaec..d866cd609d0b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -289,7 +289,8 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, DR_ACTION_REFORMAT_TYP_TNL_L2_TO_L2; tmp_action = mlx5dr_action_create_packet_reformat(domain, - decap_type, 0, + decap_type, + 0, 0, 0, NULL); if (!tmp_action) { err = -ENOMEM; @@ -522,9 +523,7 @@ out_err: } static int mlx5_cmd_dr_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns, - int reformat_type, - size_t size, - void *reformat_data, + struct mlx5_pkt_reformat_params *params, enum mlx5_flow_namespace_type namespace, struct mlx5_pkt_reformat *pkt_reformat) { @@ -532,7 +531,7 @@ static int mlx5_cmd_dr_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns struct mlx5dr_action *action; int dr_reformat; - switch (reformat_type) { + switch (params->type) { case MLX5_REFORMAT_TYPE_L2_TO_VXLAN: case MLX5_REFORMAT_TYPE_L2_TO_NVGRE: case MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL: @@ -546,14 +545,16 @@ static int mlx5_cmd_dr_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns break; default: mlx5_core_err(ns->dev, "Packet-reformat not supported(%d)\n", - reformat_type); + params->type); return -EOPNOTSUPP; } action = mlx5dr_action_create_packet_reformat(dr_domain, dr_reformat, - size, - reformat_data); + params->param_0, + params->param_1, + params->size, + params->data); if (!action) { mlx5_core_err(ns->dev, "Failed allocating packet-reformat action\n"); return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h index 612b0ac31db2..8d821bbe3309 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -105,6 +105,8 @@ mlx5dr_action_create_flow_counter(u32 counter_id); struct mlx5dr_action * mlx5dr_action_create_packet_reformat(struct mlx5dr_domain *dmn, enum mlx5dr_action_reformat_type reformat_type, + u8 reformat_param_0, + u8 reformat_param_1, size_t data_sz, void *data); diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 1f51f4c3b1af..f69f68fba946 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -254,10 +254,16 @@ struct mlx5_modify_hdr *mlx5_modify_header_alloc(struct mlx5_core_dev *dev, void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, struct mlx5_modify_hdr *modify_hdr); +struct mlx5_pkt_reformat_params { + int type; + u8 param_0; + u8 param_1; + size_t size; + void *data; +}; + struct mlx5_pkt_reformat *mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, - int reformat_type, - size_t size, - void *reformat_data, + struct mlx5_pkt_reformat_params *params, enum mlx5_flow_namespace_type ns_type); void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, struct mlx5_pkt_reformat *reformat); -- cgit v1.2.3-71-gd317 From ec3be8873df3bf467ead27f7cedc896cbb2bd819 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Thu, 4 Mar 2021 13:09:53 +0200 Subject: net/mlx5: Create TC-miss priority and table In order to adhere to kernel software datapath model bridge offloads must come after TC and NF FDBs. Following patches in this series add new FDB priority for bridge after FDB_FT_OFFLOAD. However, since netfilter offload is implemented with unmanaged tables, its miss path is not automatically connected to next priority and requires the code to manually connect with slow table. To keep bridge offloads encapsulated and not mix it with eswitch offloads, create a new FDB_TC_MISS priority between FDB_FT_OFFLOAD and FDB_SLOW_PATH: + | +---------v----------+ | | | FDB_TC_OFFLOAD | | | +---------+----------+ | | | +---------v----------+ | | | FDB_FT_OFFLOAD | | | +---------+----------+ | | | +---------v----------+ | | | FDB_TC_MISS | | | +---------+----------+ | | | +---------v----------+ | | | FDB_SLOW_PATH | | | +---------+----------+ | v Initialize the new priority with single default empty managed table and use the table as TC/NF miss patch instead of slow table. This approach allows bridge offloads to be created as new FDB namespace priority between FDB_TC_MISS and FDB_SLOW_PATH without exposing its internal tables to any other modules since miss path of managed TC-miss table is automatically wired to next priority. Signed-off-by: Vlad Buslov Reviewed-by: Jianbo Liu Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 1 + .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 19 ++++++++++++++++++- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 6 ++++++ include/linux/mlx5/fs.h | 1 + 4 files changed, 26 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 64ccb2bc0b58..55404eabff39 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -196,6 +196,7 @@ struct mlx5_eswitch_fdb { struct offloads_fdb { struct mlx5_flow_namespace *ns; + struct mlx5_flow_table *tc_miss_table; struct mlx5_flow_table *slow_fdb; struct mlx5_flow_group *send_to_vport_grp; struct mlx5_flow_group *send_to_vport_meta_grp; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index d18a28a6e9a6..7579f3402776 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1634,7 +1634,21 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw) } esw->fdb_table.offloads.slow_fdb = fdb; - err = esw_chains_create(esw, fdb); + /* Create empty TC-miss managed table. This allows plugging in following + * priorities without directly exposing their level 0 table to + * eswitch_offloads and passing it as miss_fdb to following call to + * esw_chains_create(). + */ + memset(&ft_attr, 0, sizeof(ft_attr)); + ft_attr.prio = FDB_TC_MISS; + esw->fdb_table.offloads.tc_miss_table = mlx5_create_flow_table(root_ns, &ft_attr); + if (IS_ERR(esw->fdb_table.offloads.tc_miss_table)) { + err = PTR_ERR(esw->fdb_table.offloads.tc_miss_table); + esw_warn(dev, "Failed to create TC miss FDB Table err %d\n", err); + goto tc_miss_table_err; + } + + err = esw_chains_create(esw, esw->fdb_table.offloads.tc_miss_table); if (err) { esw_warn(dev, "Failed to open fdb chains err(%d)\n", err); goto fdb_chains_err; @@ -1779,6 +1793,8 @@ send_vport_meta_err: send_vport_err: esw_chains_destroy(esw, esw_chains(esw)); fdb_chains_err: + mlx5_destroy_flow_table(esw->fdb_table.offloads.tc_miss_table); +tc_miss_table_err: mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb); slow_fdb_err: /* Holds true only as long as DMFS is the default */ @@ -1806,6 +1822,7 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw) esw_chains_destroy(esw, esw_chains(esw)); + mlx5_destroy_flow_table(esw->fdb_table.offloads.tc_miss_table); mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb); /* Holds true only as long as DMFS is the default */ mlx5_flow_namespace_set_mode(esw->fdb_table.offloads.ns, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index c0936b4e53a9..fc70c4ed8469 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2780,6 +2780,12 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering) if (err) goto out_err; + maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_TC_MISS, 1); + if (IS_ERR(maj_prio)) { + err = PTR_ERR(maj_prio); + goto out_err; + } + maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_SLOW_PATH, 1); if (IS_ERR(maj_prio)) { err = PTR_ERR(maj_prio); diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index f69f68fba946..271f2f4d6b60 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -87,6 +87,7 @@ enum { FDB_BYPASS_PATH, FDB_TC_OFFLOAD, FDB_FT_OFFLOAD, + FDB_TC_MISS, FDB_SLOW_PATH, FDB_PER_VPORT, }; -- cgit v1.2.3-71-gd317 From 19e9bfa044f32655f1c14e95784be93da34e103e Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Fri, 2 Apr 2021 15:57:02 +0300 Subject: net/mlx5: Bridge, add offload infrastructure Create new files bridge.{c|h} in en/rep directory that implement bridge interaction with representor netdevices and handle required events/notifications, bridge.{c|h} in esw directory that implement all necessary eswitch offloading infrastructure and works on vport/eswitch level. Provide new kconfig MLX5_BRIDGE which is automatically selected when both kernel bridge and mlx5 eswitch configs are enabled. Provide basic infrastructure for bridge offloads: - struct mlx5_esw_bridge_offloads - per-eswitch bridge offload structure that encapsulates generic bridge-offloads data (notifier blocks, ingress flow table/group, etc.) that is created/deleted on enable/disable eswitch offloads. - struct mlx5_esw_bridge - per-bridge structure that encapsulates per-bridge data (reference counter, FDB, egress flow table/group, etc.) that is created when first eswitch represetor is attached to new bridge and deleted when last representor is removed from the bridge as a result of NETDEV_CHANGEUPPER event. The bridge tables are created with new priority FDB_BR_OFFLOAD in FDB namespace. The new priority is between tc-miss and slow path priorities. Priority consist of two levels: the ingress table that is global per eswitch and matches incoming packets by src_mac/vid and redirects them to next level (egress table) that is chosen according to ingress port bridge membership and matches on dst_mac/vid in order to redirect packet to vport according to the following diagram: + | +---------v----------+ | | | FDB_TC_OFFLOAD | | | +---------+----------+ | | +---------v----------+ | | | FDB_FT_OFFLOAD | | | +---------+----------+ | | +---------v----------+ | | | FDB_TC_MISS | | | +---------+----------+ | +--------------------------------------+ | | | | +------+ | | | | | +------v--------+ FDB_BR_OFFLOAD | | | INGRESS_TABLE | | | +------+---+----+ | | | | match | | | +---------+ | | | | | +-------+ | | +-------v-------+ match | | | | | | EGRESS_TABLE +------------> vport | | | +-------+-------+ | | | | | | | +-------+ | | miss | | | +------+------+ | | | | +--------------------------------------+ | | +---------v----------+ | | | FDB_SLOW_PATH | | | +---------+----------+ | v Signed-off-by: Vlad Buslov Reviewed-by: Jianbo Liu Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/Kconfig | 10 + drivers/net/ethernet/mellanox/mlx5/core/Makefile | 1 + .../ethernet/mellanox/mlx5/core/en/rep/bridge.c | 108 +++++++ .../ethernet/mellanox/mlx5/core/en/rep/bridge.h | 21 ++ drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 3 + .../net/ethernet/mellanox/mlx5/core/esw/bridge.c | 354 +++++++++++++++++++++ .../net/ethernet/mellanox/mlx5/core/esw/bridge.h | 30 ++ drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 6 + drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 6 + include/linux/mlx5/fs.h | 1 + 10 files changed, 540 insertions(+) create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.h create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index 461a43f338e6..d62f90aedade 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -79,6 +79,16 @@ config MLX5_ESWITCH Legacy SRIOV mode (L2 mac vlan steering based). Switchdev mode (eswitch offloads). +config MLX5_BRIDGE + bool + depends on MLX5_ESWITCH && BRIDGE + default y + help + mlx5 ConnectX offloads support for Ethernet Bridging (BRIDGE). + Enable adding representors of mlx5 uplink and VF ports to Bridge and + offloading rules for traffic between such ports. Supports VLANs (trunk and + access modes). + config MLX5_CLS_ACT bool "MLX5 TC classifier action support" depends on MLX5_ESWITCH && NET_CLS_ACT diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 8dbdf1aef00f..b5072a3a2585 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -56,6 +56,7 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH) += esw/acl/helper.o \ esw/acl/ingress_lgcy.o esw/acl/ingress_ofld.o \ esw/devlink_port.o esw/vporttbl.o mlx5_core-$(CONFIG_MLX5_TC_SAMPLE) += esw/sample.o +mlx5_core-$(CONFIG_MLX5_BRIDGE) += esw/bridge.o en/rep/bridge.o mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o mlx5_core-$(CONFIG_VXLAN) += lib/vxlan.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c new file mode 100644 index 000000000000..de7a68488a9d --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2021 Mellanox Technologies. */ + +#include +#include +#include +#include "bridge.h" +#include "esw/bridge.h" +#include "en_rep.h" + +static int mlx5_esw_bridge_port_changeupper(struct notifier_block *nb, void *ptr) +{ + struct mlx5_esw_bridge_offloads *br_offloads = container_of(nb, + struct mlx5_esw_bridge_offloads, + netdev_nb); + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_changeupper_info *info = ptr; + struct netlink_ext_ack *extack; + struct mlx5e_rep_priv *rpriv; + struct mlx5_eswitch *esw; + struct mlx5_vport *vport; + struct net_device *upper; + struct mlx5e_priv *priv; + u16 vport_num; + + if (!mlx5e_eswitch_rep(dev)) + return 0; + + upper = info->upper_dev; + if (!netif_is_bridge_master(upper)) + return 0; + + esw = br_offloads->esw; + priv = netdev_priv(dev); + if (esw != priv->mdev->priv.eswitch) + return 0; + + rpriv = priv->ppriv; + vport_num = rpriv->rep->vport; + vport = mlx5_eswitch_get_vport(esw, vport_num); + if (IS_ERR(vport)) + return PTR_ERR(vport); + + extack = netdev_notifier_info_to_extack(&info->info); + + return info->linking ? + mlx5_esw_bridge_vport_link(upper->ifindex, br_offloads, vport, extack) : + mlx5_esw_bridge_vport_unlink(upper->ifindex, br_offloads, vport, extack); +} + +static int mlx5_esw_bridge_switchdev_port_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + int err = 0; + + switch (event) { + case NETDEV_PRECHANGEUPPER: + break; + + case NETDEV_CHANGEUPPER: + err = mlx5_esw_bridge_port_changeupper(nb, ptr); + break; + } + + return notifier_from_errno(err); +} + +void mlx5e_rep_bridge_init(struct mlx5e_priv *priv) +{ + struct mlx5_esw_bridge_offloads *br_offloads; + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5_eswitch *esw = + mdev->priv.eswitch; + int err; + + rtnl_lock(); + br_offloads = mlx5_esw_bridge_init(esw); + rtnl_unlock(); + if (IS_ERR(br_offloads)) { + esw_warn(mdev, "Failed to init esw bridge (err=%ld)\n", PTR_ERR(br_offloads)); + return; + } + + br_offloads->netdev_nb.notifier_call = mlx5_esw_bridge_switchdev_port_event; + err = register_netdevice_notifier(&br_offloads->netdev_nb); + if (err) { + esw_warn(mdev, "Failed to register bridge offloads netdevice notifier (err=%d)\n", + err); + mlx5_esw_bridge_cleanup(esw); + } +} + +void mlx5e_rep_bridge_cleanup(struct mlx5e_priv *priv) +{ + struct mlx5_esw_bridge_offloads *br_offloads; + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5_eswitch *esw = + mdev->priv.eswitch; + + br_offloads = esw->br_offloads; + if (!br_offloads) + return; + + unregister_netdevice_notifier(&br_offloads->netdev_nb); + rtnl_lock(); + mlx5_esw_bridge_cleanup(esw); + rtnl_unlock(); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.h new file mode 100644 index 000000000000..fbeb64242831 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021 Mellanox Technologies. */ + +#ifndef __MLX5_EN_REP_BRIDGE__ +#define __MLX5_EN_REP_BRIDGE__ + +#include "en.h" + +#if IS_ENABLED(CONFIG_MLX5_BRIDGE) + +void mlx5e_rep_bridge_init(struct mlx5e_priv *priv); +void mlx5e_rep_bridge_cleanup(struct mlx5e_priv *priv); + +#else /* CONFIG_MLX5_BRIDGE */ + +static inline void mlx5e_rep_bridge_init(struct mlx5e_priv *priv) {} +static inline void mlx5e_rep_bridge_cleanup(struct mlx5e_priv *priv) {} + +#endif /* CONFIG_MLX5_BRIDGE */ + +#endif /* __MLX5_EN_REP_BRIDGE__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 40db54412041..8290e0086178 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -45,6 +45,7 @@ #include "en_tc.h" #include "en/rep/tc.h" #include "en/rep/neigh.h" +#include "en/rep/bridge.h" #include "en/devlink.h" #include "fs_core.h" #include "lib/mlx5.h" @@ -981,6 +982,7 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) mlx5e_dcbnl_initialize(priv); mlx5e_dcbnl_init_app(priv); mlx5e_rep_neigh_init(rpriv); + mlx5e_rep_bridge_init(priv); netdev->wanted_features |= NETIF_F_HW_TC; @@ -1002,6 +1004,7 @@ static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv) netif_device_detach(priv->netdev); rtnl_unlock(); + mlx5e_rep_bridge_cleanup(priv); mlx5e_rep_neigh_cleanup(rpriv); mlx5e_dcbnl_delete_app(priv); mlx5_notifier_unregister(mdev, &priv->events_nb); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c new file mode 100644 index 000000000000..b503562f97d0 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -0,0 +1,354 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2021 Mellanox Technologies. */ + +#include +#include +#include +#include "bridge.h" +#include "eswitch.h" +#include "fs_core.h" + +#define MLX5_ESW_BRIDGE_INGRESS_TABLE_SIZE 64000 +#define MLX5_ESW_BRIDGE_INGRESS_TABLE_MAC_GRP_IDX_FROM 0 +#define MLX5_ESW_BRIDGE_INGRESS_TABLE_MAC_GRP_IDX_TO (MLX5_ESW_BRIDGE_INGRESS_TABLE_SIZE - 1) + +#define MLX5_ESW_BRIDGE_EGRESS_TABLE_SIZE 64000 +#define MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_FROM 0 +#define MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_TO (MLX5_ESW_BRIDGE_EGRESS_TABLE_SIZE - 1) + +enum { + MLX5_ESW_BRIDGE_LEVEL_INGRESS_TABLE, + MLX5_ESW_BRIDGE_LEVEL_EGRESS_TABLE, +}; + +struct mlx5_esw_bridge { + int ifindex; + int refcnt; + struct list_head list; + + struct mlx5_flow_table *egress_ft; + struct mlx5_flow_group *egress_mac_fg; +}; + +static struct mlx5_flow_table * +mlx5_esw_bridge_table_create(int max_fte, u32 level, struct mlx5_eswitch *esw) +{ + struct mlx5_flow_table_attr ft_attr = {}; + struct mlx5_core_dev *dev = esw->dev; + struct mlx5_flow_namespace *ns; + struct mlx5_flow_table *fdb; + + ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB); + if (!ns) { + esw_warn(dev, "Failed to get FDB namespace\n"); + return ERR_PTR(-ENOENT); + } + + ft_attr.max_fte = max_fte; + ft_attr.level = level; + ft_attr.prio = FDB_BR_OFFLOAD; + fdb = mlx5_create_flow_table(ns, &ft_attr); + if (IS_ERR(fdb)) + esw_warn(dev, "Failed to create bridge FDB Table (err=%ld)\n", PTR_ERR(fdb)); + + return fdb; +} + +static struct mlx5_flow_group * +mlx5_esw_bridge_ingress_mac_fg_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *ingress_ft) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *fg; + u32 *in, *match; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return ERR_PTR(-ENOMEM); + + MLX5_SET(create_flow_group_in, in, match_criteria_enable, + MLX5_MATCH_OUTER_HEADERS | MLX5_MATCH_MISC_PARAMETERS_2); + match = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); + + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.smac_47_16); + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.smac_15_0); + + MLX5_SET(fte_match_param, match, misc_parameters_2.metadata_reg_c_0, + mlx5_eswitch_get_vport_metadata_mask()); + + MLX5_SET(create_flow_group_in, in, start_flow_index, + MLX5_ESW_BRIDGE_INGRESS_TABLE_MAC_GRP_IDX_FROM); + MLX5_SET(create_flow_group_in, in, end_flow_index, + MLX5_ESW_BRIDGE_INGRESS_TABLE_MAC_GRP_IDX_TO); + + fg = mlx5_create_flow_group(ingress_ft, in); + if (IS_ERR(fg)) + esw_warn(esw->dev, + "Failed to create bridge ingress table MAC flow group (err=%ld)\n", + PTR_ERR(fg)); + + kvfree(in); + return fg; +} + +static struct mlx5_flow_group * +mlx5_esw_bridge_egress_mac_fg_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *egress_ft) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *fg; + u32 *in, *match; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return ERR_PTR(-ENOMEM); + + MLX5_SET(create_flow_group_in, in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); + match = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); + + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.dmac_47_16); + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.dmac_15_0); + + MLX5_SET(create_flow_group_in, in, start_flow_index, + MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_FROM); + MLX5_SET(create_flow_group_in, in, end_flow_index, + MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_TO); + + fg = mlx5_create_flow_group(egress_ft, in); + if (IS_ERR(fg)) + esw_warn(esw->dev, + "Failed to create bridge egress table MAC flow group (err=%ld)\n", + PTR_ERR(fg)); + kvfree(in); + return fg; +} + +static int +mlx5_esw_bridge_ingress_table_init(struct mlx5_esw_bridge_offloads *br_offloads) +{ + struct mlx5_flow_table *ingress_ft; + struct mlx5_flow_group *mac_fg; + int err; + + ingress_ft = mlx5_esw_bridge_table_create(MLX5_ESW_BRIDGE_INGRESS_TABLE_SIZE, + MLX5_ESW_BRIDGE_LEVEL_INGRESS_TABLE, + br_offloads->esw); + if (IS_ERR(ingress_ft)) + return PTR_ERR(ingress_ft); + + mac_fg = mlx5_esw_bridge_ingress_mac_fg_create(br_offloads->esw, ingress_ft); + if (IS_ERR(mac_fg)) { + err = PTR_ERR(mac_fg); + goto err_mac_fg; + } + + br_offloads->ingress_ft = ingress_ft; + br_offloads->ingress_mac_fg = mac_fg; + return 0; + +err_mac_fg: + mlx5_destroy_flow_table(ingress_ft); + return err; +} + +static void +mlx5_esw_bridge_ingress_table_cleanup(struct mlx5_esw_bridge_offloads *br_offloads) +{ + mlx5_destroy_flow_group(br_offloads->ingress_mac_fg); + br_offloads->ingress_mac_fg = NULL; + mlx5_destroy_flow_table(br_offloads->ingress_ft); + br_offloads->ingress_ft = NULL; +} + +static int +mlx5_esw_bridge_egress_table_init(struct mlx5_esw_bridge_offloads *br_offloads, + struct mlx5_esw_bridge *bridge) +{ + struct mlx5_flow_table *egress_ft; + struct mlx5_flow_group *mac_fg; + int err; + + egress_ft = mlx5_esw_bridge_table_create(MLX5_ESW_BRIDGE_EGRESS_TABLE_SIZE, + MLX5_ESW_BRIDGE_LEVEL_EGRESS_TABLE, + br_offloads->esw); + if (IS_ERR(egress_ft)) + return PTR_ERR(egress_ft); + + mac_fg = mlx5_esw_bridge_egress_mac_fg_create(br_offloads->esw, egress_ft); + if (IS_ERR(mac_fg)) { + err = PTR_ERR(mac_fg); + goto err_mac_fg; + } + + bridge->egress_ft = egress_ft; + bridge->egress_mac_fg = mac_fg; + return 0; + +err_mac_fg: + mlx5_destroy_flow_table(egress_ft); + return err; +} + +static void +mlx5_esw_bridge_egress_table_cleanup(struct mlx5_esw_bridge *bridge) +{ + mlx5_destroy_flow_group(bridge->egress_mac_fg); + mlx5_destroy_flow_table(bridge->egress_ft); +} + +static struct mlx5_esw_bridge *mlx5_esw_bridge_create(int ifindex, + struct mlx5_esw_bridge_offloads *br_offloads) +{ + struct mlx5_esw_bridge *bridge; + int err; + + bridge = kvzalloc(sizeof(*bridge), GFP_KERNEL); + if (!bridge) + return ERR_PTR(-ENOMEM); + + err = mlx5_esw_bridge_egress_table_init(br_offloads, bridge); + if (err) + goto err_egress_tbl; + + bridge->ifindex = ifindex; + bridge->refcnt = 1; + list_add(&bridge->list, &br_offloads->bridges); + + return bridge; + +err_egress_tbl: + kvfree(bridge); + return ERR_PTR(err); +} + +static void mlx5_esw_bridge_get(struct mlx5_esw_bridge *bridge) +{ + bridge->refcnt++; +} + +static void mlx5_esw_bridge_put(struct mlx5_esw_bridge_offloads *br_offloads, + struct mlx5_esw_bridge *bridge) +{ + if (--bridge->refcnt) + return; + + mlx5_esw_bridge_egress_table_cleanup(bridge); + list_del(&bridge->list); + kvfree(bridge); + + if (list_empty(&br_offloads->bridges)) + mlx5_esw_bridge_ingress_table_cleanup(br_offloads); +} + +static struct mlx5_esw_bridge * +mlx5_esw_bridge_lookup(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads) +{ + struct mlx5_esw_bridge *bridge; + + ASSERT_RTNL(); + + list_for_each_entry(bridge, &br_offloads->bridges, list) { + if (bridge->ifindex == ifindex) { + mlx5_esw_bridge_get(bridge); + return bridge; + } + } + + if (!br_offloads->ingress_ft) { + int err = mlx5_esw_bridge_ingress_table_init(br_offloads); + + if (err) + return ERR_PTR(err); + } + + bridge = mlx5_esw_bridge_create(ifindex, br_offloads); + if (IS_ERR(bridge) && list_empty(&br_offloads->bridges)) + mlx5_esw_bridge_ingress_table_cleanup(br_offloads); + return bridge; +} + +static int mlx5_esw_bridge_vport_init(struct mlx5_esw_bridge *bridge, + struct mlx5_vport *vport) +{ + vport->bridge = bridge; + return 0; +} + +static int mlx5_esw_bridge_vport_cleanup(struct mlx5_esw_bridge_offloads *br_offloads, + struct mlx5_vport *vport) +{ + mlx5_esw_bridge_put(br_offloads, vport->bridge); + vport->bridge = NULL; + return 0; +} + +int mlx5_esw_bridge_vport_link(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads, + struct mlx5_vport *vport, struct netlink_ext_ack *extack) +{ + struct mlx5_esw_bridge *bridge; + + WARN_ON(vport->bridge); + + bridge = mlx5_esw_bridge_lookup(ifindex, br_offloads); + if (IS_ERR(bridge)) { + NL_SET_ERR_MSG_MOD(extack, "Error checking for existing bridge with same ifindex"); + return PTR_ERR(bridge); + } + + return mlx5_esw_bridge_vport_init(bridge, vport); +} + +int mlx5_esw_bridge_vport_unlink(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads, + struct mlx5_vport *vport, struct netlink_ext_ack *extack) +{ + if (!vport->bridge) { + NL_SET_ERR_MSG_MOD(extack, "Port is not attached to any bridge"); + return -EINVAL; + } + if (vport->bridge->ifindex != ifindex) { + NL_SET_ERR_MSG_MOD(extack, "Port is attached to another bridge"); + return -EINVAL; + } + + return mlx5_esw_bridge_vport_cleanup(br_offloads, vport); +} + +static void mlx5_esw_bridge_flush(struct mlx5_esw_bridge_offloads *br_offloads) +{ + struct mlx5_eswitch *esw = br_offloads->esw; + struct mlx5_vport *vport; + unsigned long i; + + mlx5_esw_for_each_vport(esw, i, vport) + if (vport->bridge) + mlx5_esw_bridge_vport_cleanup(br_offloads, vport); + + WARN_ONCE(!list_empty(&br_offloads->bridges), + "Cleaning up bridge offloads while still having bridges attached\n"); +} + +struct mlx5_esw_bridge_offloads *mlx5_esw_bridge_init(struct mlx5_eswitch *esw) +{ + struct mlx5_esw_bridge_offloads *br_offloads; + + br_offloads = kvzalloc(sizeof(*br_offloads), GFP_KERNEL); + if (!br_offloads) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&br_offloads->bridges); + br_offloads->esw = esw; + esw->br_offloads = br_offloads; + + return br_offloads; +} + +void mlx5_esw_bridge_cleanup(struct mlx5_eswitch *esw) +{ + struct mlx5_esw_bridge_offloads *br_offloads = esw->br_offloads; + + if (!br_offloads) + return; + + mlx5_esw_bridge_flush(br_offloads); + + esw->br_offloads = NULL; + kvfree(br_offloads); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h new file mode 100644 index 000000000000..319b6f1db0ba --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021 Mellanox Technologies. */ + +#ifndef __MLX5_ESW_BRIDGE_H__ +#define __MLX5_ESW_BRIDGE_H__ + +#include +#include +#include "eswitch.h" + +struct mlx5_flow_table; +struct mlx5_flow_group; + +struct mlx5_esw_bridge_offloads { + struct mlx5_eswitch *esw; + struct list_head bridges; + struct notifier_block netdev_nb; + + struct mlx5_flow_table *ingress_ft; + struct mlx5_flow_group *ingress_mac_fg; +}; + +struct mlx5_esw_bridge_offloads *mlx5_esw_bridge_init(struct mlx5_eswitch *esw); +void mlx5_esw_bridge_cleanup(struct mlx5_eswitch *esw); +int mlx5_esw_bridge_vport_link(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads, + struct mlx5_vport *vport, struct netlink_ext_ack *extack); +int mlx5_esw_bridge_vport_unlink(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads, + struct mlx5_vport *vport, struct netlink_ext_ack *extack); + +#endif /* __MLX5_ESW_BRIDGE_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 55404eabff39..48cac5bf606d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -150,6 +150,8 @@ enum mlx5_eswitch_vport_event { MLX5_VPORT_PROMISC_CHANGE = BIT(3), }; +struct mlx5_esw_bridge; + struct mlx5_vport { struct mlx5_core_dev *dev; struct hlist_head uc_list[MLX5_L2_ADDR_HASH_SIZE]; @@ -178,6 +180,7 @@ struct mlx5_vport { enum mlx5_eswitch_vport_event enabled_events; int index; struct devlink_port *dl_port; + struct mlx5_esw_bridge *bridge; }; struct mlx5_esw_indir_table; @@ -271,6 +274,8 @@ enum { MLX5_ESWITCH_REG_C1_LOOPBACK_ENABLED = BIT(1), }; +struct mlx5_esw_bridge_offloads; + struct mlx5_eswitch { struct mlx5_core_dev *dev; struct mlx5_nb nb; @@ -300,6 +305,7 @@ struct mlx5_eswitch { u32 root_tsar_id; } qos; + struct mlx5_esw_bridge_offloads *br_offloads; struct mlx5_esw_offload offloads; int mode; u16 manager_vport; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index fc70c4ed8469..fc37ac9eab12 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2786,6 +2786,12 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering) goto out_err; } + maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_BR_OFFLOAD, 2); + if (IS_ERR(maj_prio)) { + err = PTR_ERR(maj_prio); + goto out_err; + } + maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_SLOW_PATH, 1); if (IS_ERR(maj_prio)) { err = PTR_ERR(maj_prio); diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 271f2f4d6b60..77746f7e35b8 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -88,6 +88,7 @@ enum { FDB_TC_OFFLOAD, FDB_FT_OFFLOAD, FDB_TC_MISS, + FDB_BR_OFFLOAD, FDB_SLOW_PATH, FDB_PER_VPORT, }; -- cgit v1.2.3-71-gd317 From 03cb4473be92a4207a3d1df25186dafd1a5add4d Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Wed, 9 Jun 2021 09:39:49 -0700 Subject: ice: add low level PTP clock access functions Add the ice_ptp_hw.c file and some associated definitions to the ice driver folder. This file contains basic low level definitions for functions that interact with the device hardware. For now, only E810-based devices are supported. The ice hardware supports 2 major variants which have different PHYs with different procedures necessary for interacting with the device clock. Because the device captures timestamps in the PHY, each PHY has its own internal timer. The timers are synchronized in hardware by first preparing the source timer and the PHY timer shadow registers, and then issuing a synchronization command. This ensures that both the source timer and PHY timers are programmed simultaneously. The timers themselves are all driven from the same oscillator source. The functions in ice_ptp_hw.c abstract over the differences between how the PHYs in E810 are programmed vs how the PHYs in E822 devices are programmed. This series only implements E810 support, but E822 support will be added in a future change. Signed-off-by: Jacob Keller Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_hw_autogen.h | 17 + drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 653 ++++++++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_ptp_hw.h | 79 +++ drivers/net/ethernet/intel/ice/ice_type.h | 9 + include/linux/kernel.h | 12 + 5 files changed, 770 insertions(+) create mode 100644 drivers/net/ethernet/intel/ice/ice_ptp_hw.c create mode 100644 drivers/net/ethernet/intel/ice/ice_ptp_hw.h (limited to 'include/linux') diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index 84d5d43fe029..f6f5ced50be2 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -433,6 +433,23 @@ #define GLV_UPRCL(_i) (0x003B2000 + ((_i) * 8)) #define GLV_UPTCL(_i) (0x0030A000 + ((_i) * 8)) #define PRTRPB_RDPC 0x000AC260 +#define GLTSYN_CMD 0x00088810 +#define GLTSYN_CMD_SYNC 0x00088814 +#define GLTSYN_ENA(_i) (0x00088808 + ((_i) * 4)) +#define GLTSYN_ENA_TSYN_ENA_M BIT(0) +#define GLTSYN_INCVAL_H(_i) (0x00088920 + ((_i) * 4)) +#define GLTSYN_INCVAL_L(_i) (0x00088918 + ((_i) * 4)) +#define GLTSYN_SHADJ_H(_i) (0x00088910 + ((_i) * 4)) +#define GLTSYN_SHADJ_L(_i) (0x00088908 + ((_i) * 4)) +#define GLTSYN_SHTIME_0(_i) (0x000888E0 + ((_i) * 4)) +#define GLTSYN_SHTIME_H(_i) (0x000888F0 + ((_i) * 4)) +#define GLTSYN_SHTIME_L(_i) (0x000888E8 + ((_i) * 4)) +#define GLTSYN_STAT(_i) (0x000888C0 + ((_i) * 4)) +#define GLTSYN_SYNC_DLAY 0x00088818 +#define GLTSYN_TIME_H(_i) (0x000888D8 + ((_i) * 4)) +#define GLTSYN_TIME_L(_i) (0x000888D0 + ((_i) * 4)) +#define PFTSYN_SEM 0x00088880 +#define PFTSYN_SEM_BUSY_M BIT(0) #define VSIQF_FD_CNT(_VSI) (0x00464000 + ((_VSI) * 4)) #define VSIQF_FD_CNT_FD_GCNT_S 0 #define VSIQF_FD_CNT_FD_GCNT_M ICE_M(0x3FFF, 0) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c new file mode 100644 index 000000000000..267312fad59a --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -0,0 +1,653 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2021, Intel Corporation. */ + +#include "ice_common.h" +#include "ice_ptp_hw.h" + +/* Low level functions for interacting with and managing the device clock used + * for the Precision Time Protocol. + * + * The ice hardware represents the current time using three registers: + * + * GLTSYN_TIME_H GLTSYN_TIME_L GLTSYN_TIME_R + * +---------------+ +---------------+ +---------------+ + * | 32 bits | | 32 bits | | 32 bits | + * +---------------+ +---------------+ +---------------+ + * + * The registers are incremented every clock tick using a 40bit increment + * value defined over two registers: + * + * GLTSYN_INCVAL_H GLTSYN_INCVAL_L + * +---------------+ +---------------+ + * | 8 bit s | | 32 bits | + * +---------------+ +---------------+ + * + * The increment value is added to the GLSTYN_TIME_R and GLSTYN_TIME_L + * registers every clock source tick. Depending on the specific device + * configuration, the clock source frequency could be one of a number of + * values. + * + * For E810 devices, the increment frequency is 812.5 MHz + * + * The hardware captures timestamps in the PHY for incoming packets, and for + * outgoing packets on request. To support this, the PHY maintains a timer + * that matches the lower 64 bits of the global source timer. + * + * In order to ensure that the PHY timers and the source timer are equivalent, + * shadow registers are used to prepare the desired initial values. A special + * sync command is issued to trigger copying from the shadow registers into + * the appropriate source and PHY registers simultaneously. + */ + +/** + * ice_get_ptp_src_clock_index - determine source clock index + * @hw: pointer to HW struct + * + * Determine the source clock index currently in use, based on device + * capabilities reported during initialization. + */ +u8 ice_get_ptp_src_clock_index(struct ice_hw *hw) +{ + return hw->func_caps.ts_func_info.tmr_index_assoc; +} + +/* E810 functions + * + * The following functions operate on the E810 series devices which use + * a separate external PHY. + */ + +/** + * ice_read_phy_reg_e810 - Read register from external PHY on E810 + * @hw: pointer to the HW struct + * @addr: the address to read from + * @val: On return, the value read from the PHY + * + * Read a register from the external PHY on the E810 device. + */ +static int ice_read_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 *val) +{ + struct ice_sbq_msg_input msg = {0}; + int status; + + msg.msg_addr_low = lower_16_bits(addr); + msg.msg_addr_high = upper_16_bits(addr); + msg.opcode = ice_sbq_msg_rd; + msg.dest_dev = rmn_0; + + status = ice_sbq_rw_reg(hw, &msg); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, status %d\n", + status); + return status; + } + + *val = msg.data; + + return 0; +} + +/** + * ice_write_phy_reg_e810 - Write register on external PHY on E810 + * @hw: pointer to the HW struct + * @addr: the address to writem to + * @val: the value to write to the PHY + * + * Write a value to a register of the external PHY on the E810 device. + */ +static int ice_write_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 val) +{ + struct ice_sbq_msg_input msg = {0}; + int status; + + msg.msg_addr_low = lower_16_bits(addr); + msg.msg_addr_high = upper_16_bits(addr); + msg.opcode = ice_sbq_msg_wr; + msg.dest_dev = rmn_0; + msg.data = val; + + status = ice_sbq_rw_reg(hw, &msg); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, status %d\n", + status); + return status; + } + + return 0; +} + +/** + * ice_read_phy_tstamp_e810 - Read a PHY timestamp out of the external PHY + * @hw: pointer to the HW struct + * @lport: the lport to read from + * @idx: the timestamp index to read + * @tstamp: on return, the 40bit timestamp value + * + * Read a 40bit timestamp value out of the timestamp block of the external PHY + * on the E810 device. + */ +static int +ice_read_phy_tstamp_e810(struct ice_hw *hw, u8 lport, u8 idx, u64 *tstamp) +{ + u32 lo_addr, hi_addr, lo, hi; + int status; + + lo_addr = TS_EXT(LOW_TX_MEMORY_BANK_START, lport, idx); + hi_addr = TS_EXT(HIGH_TX_MEMORY_BANK_START, lport, idx); + + status = ice_read_phy_reg_e810(hw, lo_addr, &lo); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read low PTP timestamp register, status %d\n", + status); + return status; + } + + status = ice_read_phy_reg_e810(hw, hi_addr, &hi); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read high PTP timestamp register, status %d\n", + status); + return status; + } + + /* For E810 devices, the timestamp is reported with the lower 32 bits + * in the low register, and the upper 8 bits in the high register. + */ + *tstamp = ((u64)hi) << TS_HIGH_S | ((u64)lo & TS_LOW_M); + + return 0; +} + +/** + * ice_clear_phy_tstamp_e810 - Clear a timestamp from the external PHY + * @hw: pointer to the HW struct + * @lport: the lport to read from + * @idx: the timestamp index to reset + * + * Clear a timestamp, resetting its valid bit, from the timestamp block of the + * external PHY on the E810 device. + */ +static int ice_clear_phy_tstamp_e810(struct ice_hw *hw, u8 lport, u8 idx) +{ + u32 lo_addr, hi_addr; + int status; + + lo_addr = TS_EXT(LOW_TX_MEMORY_BANK_START, lport, idx); + hi_addr = TS_EXT(HIGH_TX_MEMORY_BANK_START, lport, idx); + + status = ice_write_phy_reg_e810(hw, lo_addr, 0); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to clear low PTP timestamp register, status %d\n", + status); + return status; + } + + status = ice_write_phy_reg_e810(hw, hi_addr, 0); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to clear high PTP timestamp register, status %d\n", + status); + return status; + } + + return 0; +} + +/** + * ice_ptp_init_phy_e810 - Enable PTP function on the external PHY + * @hw: pointer to HW struct + * + * Enable the timesync PTP functionality for the external PHY connected to + * this function. + */ +int ice_ptp_init_phy_e810(struct ice_hw *hw) +{ + int status; + u8 tmr_idx; + + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + status = ice_write_phy_reg_e810(hw, ETH_GLTSYN_ENA(tmr_idx), + GLTSYN_ENA_TSYN_ENA_M); + if (status) + ice_debug(hw, ICE_DBG_PTP, "PTP failed in ena_phy_time_syn %d\n", + status); + + return status; +} + +/** + * ice_ptp_prep_phy_time_e810 - Prepare PHY port with initial time + * @hw: Board private structure + * @time: Time to initialize the PHY port clock to + * + * Program the PHY port ETH_GLTSYN_SHTIME registers in preparation setting the + * initial clock time. The time will not actually be programmed until the + * driver issues an INIT_TIME command. + * + * The time value is the upper 32 bits of the PHY timer, usually in units of + * nominal nanoseconds. + */ +static int ice_ptp_prep_phy_time_e810(struct ice_hw *hw, u32 time) +{ + int status; + u8 tmr_idx; + + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + status = ice_write_phy_reg_e810(hw, ETH_GLTSYN_SHTIME_0(tmr_idx), 0); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write SHTIME_0, status %d\n", + status); + return status; + } + + status = ice_write_phy_reg_e810(hw, ETH_GLTSYN_SHTIME_L(tmr_idx), time); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write SHTIME_L, status %d\n", + status); + return status; + } + + return 0; +} + +/** + * ice_ptp_prep_phy_adj_e810 - Prep PHY port for a time adjustment + * @hw: pointer to HW struct + * @adj: adjustment value to program + * + * Prepare the PHY port for an atomic adjustment by programming the PHY + * ETH_GLTSYN_SHADJ_L and ETH_GLTSYN_SHADJ_H registers. The actual adjustment + * is completed by issuing an ADJ_TIME sync command. + * + * The adjustment value only contains the portion used for the upper 32bits of + * the PHY timer, usually in units of nominal nanoseconds. Negative + * adjustments are supported using 2s complement arithmetic. + */ +static int ice_ptp_prep_phy_adj_e810(struct ice_hw *hw, s32 adj) +{ + int status; + u8 tmr_idx; + + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + + /* Adjustments are represented as signed 2's complement values in + * nanoseconds. Sub-nanosecond adjustment is not supported. + */ + status = ice_write_phy_reg_e810(hw, ETH_GLTSYN_SHADJ_L(tmr_idx), 0); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write adj to PHY SHADJ_L, status %d\n", + status); + return status; + } + + status = ice_write_phy_reg_e810(hw, ETH_GLTSYN_SHADJ_H(tmr_idx), adj); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write adj to PHY SHADJ_H, status %d\n", + status); + return status; + } + + return 0; +} + +/** + * ice_ptp_prep_phy_incval_e810 - Prep PHY port increment value change + * @hw: pointer to HW struct + * @incval: The new 40bit increment value to prepare + * + * Prepare the PHY port for a new increment value by programming the PHY + * ETH_GLTSYN_SHADJ_L and ETH_GLTSYN_SHADJ_H registers. The actual change is + * completed by issuing an INIT_INCVAL command. + */ +static int ice_ptp_prep_phy_incval_e810(struct ice_hw *hw, u64 incval) +{ + u32 high, low; + int status; + u8 tmr_idx; + + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + low = lower_32_bits(incval); + high = upper_32_bits(incval); + + status = ice_write_phy_reg_e810(hw, ETH_GLTSYN_SHADJ_L(tmr_idx), low); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write incval to PHY SHADJ_L, status %d\n", + status); + return status; + } + + status = ice_write_phy_reg_e810(hw, ETH_GLTSYN_SHADJ_H(tmr_idx), high); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write incval PHY SHADJ_H, status %d\n", + status); + return status; + } + + return 0; +} + +/** + * ice_ptp_port_cmd_e810 - Prepare all external PHYs for a timer command + * @hw: pointer to HW struct + * @cmd: Command to be sent to the port + * + * Prepare the external PHYs connected to this device for a timer sync + * command. + */ +static int ice_ptp_port_cmd_e810(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) +{ + u32 cmd_val, val; + int status; + + switch (cmd) { + case INIT_TIME: + cmd_val = GLTSYN_CMD_INIT_TIME; + break; + case INIT_INCVAL: + cmd_val = GLTSYN_CMD_INIT_INCVAL; + break; + case ADJ_TIME: + cmd_val = GLTSYN_CMD_ADJ_TIME; + break; + case READ_TIME: + cmd_val = GLTSYN_CMD_READ_TIME; + break; + case ADJ_TIME_AT_TIME: + cmd_val = GLTSYN_CMD_ADJ_INIT_TIME; + break; + } + + /* Read, modify, write */ + status = ice_read_phy_reg_e810(hw, ETH_GLTSYN_CMD, &val); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read GLTSYN_CMD, status %d\n", status); + return status; + } + + /* Modify necessary bits only and perform write */ + val &= ~TS_CMD_MASK_E810; + val |= cmd_val; + + status = ice_write_phy_reg_e810(hw, ETH_GLTSYN_CMD, val); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write back GLTSYN_CMD, status %d\n", status); + return status; + } + + return 0; +} + +/* Device agnostic functions + * + * The following functions implement useful behavior to hide the differences + * between E810 and other devices. They call the device-specific + * implementations where necessary. + * + * Currently, the driver only supports E810, but future work will enable + * support for E822-based devices. + */ + +/** + * ice_ptp_lock - Acquire PTP global semaphore register lock + * @hw: pointer to the HW struct + * + * Acquire the global PTP hardware semaphore lock. Returns true if the lock + * was acquired, false otherwise. + * + * The PFTSYN_SEM register sets the busy bit on read, returning the previous + * value. If software sees the busy bit cleared, this means that this function + * acquired the lock (and the busy bit is now set). If software sees the busy + * bit set, it means that another function acquired the lock. + * + * Software must clear the busy bit with a write to release the lock for other + * functions when done. + */ +bool ice_ptp_lock(struct ice_hw *hw) +{ + u32 hw_lock; + int i; + +#define MAX_TRIES 5 + + for (i = 0; i < MAX_TRIES; i++) { + hw_lock = rd32(hw, PFTSYN_SEM + (PFTSYN_SEM_BYTES * hw->pf_id)); + hw_lock = hw_lock & PFTSYN_SEM_BUSY_M; + if (hw_lock) { + /* Somebody is holding the lock */ + usleep_range(10000, 20000); + continue; + } else { + break; + } + } + + return !hw_lock; +} + +/** + * ice_ptp_unlock - Release PTP global semaphore register lock + * @hw: pointer to the HW struct + * + * Release the global PTP hardware semaphore lock. This is done by writing to + * the PFTSYN_SEM register. + */ +void ice_ptp_unlock(struct ice_hw *hw) +{ + wr32(hw, PFTSYN_SEM + (PFTSYN_SEM_BYTES * hw->pf_id), 0); +} + +/** + * ice_ptp_src_cmd - Prepare source timer for a timer command + * @hw: pointer to HW structure + * @cmd: Timer command + * + * Prepare the source timer for an upcoming timer sync command. + */ +static void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) +{ + u32 cmd_val; + u8 tmr_idx; + + tmr_idx = ice_get_ptp_src_clock_index(hw); + cmd_val = tmr_idx << SEL_CPK_SRC; + + switch (cmd) { + case INIT_TIME: + cmd_val |= GLTSYN_CMD_INIT_TIME; + break; + case INIT_INCVAL: + cmd_val |= GLTSYN_CMD_INIT_INCVAL; + break; + case ADJ_TIME: + cmd_val |= GLTSYN_CMD_ADJ_TIME; + break; + case ADJ_TIME_AT_TIME: + cmd_val |= GLTSYN_CMD_ADJ_INIT_TIME; + break; + case READ_TIME: + cmd_val |= GLTSYN_CMD_READ_TIME; + break; + } + + wr32(hw, GLTSYN_CMD, cmd_val); +} + +/** + * ice_ptp_tmr_cmd - Prepare and trigger a timer sync command + * @hw: pointer to HW struct + * @cmd: the command to issue + * + * Prepare the source timer and PHY timers and then trigger the requested + * command. This causes the shadow registers previously written in preparation + * for the command to be synchronously applied to both the source and PHY + * timers. + */ +static int ice_ptp_tmr_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) +{ + int status; + + /* First, prepare the source timer */ + ice_ptp_src_cmd(hw, cmd); + + /* Next, prepare the ports */ + status = ice_ptp_port_cmd_e810(hw, cmd); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to prepare PHY ports for timer command %u, status %d\n", + cmd, status); + return status; + } + + /* Write the sync command register to drive both source and PHY timer commands + * synchronously + */ + wr32(hw, GLTSYN_CMD_SYNC, SYNC_EXEC_CMD); + + return 0; +} + +/** + * ice_ptp_init_time - Initialize device time to provided value + * @hw: pointer to HW struct + * @time: 64bits of time (GLTSYN_TIME_L and GLTSYN_TIME_H) + * + * Initialize the device to the specified time provided. This requires a three + * step process: + * + * 1) write the new init time to the source timer shadow registers + * 2) write the new init time to the PHY timer shadow registers + * 3) issue an init_time timer command to synchronously switch both the source + * and port timers to the new init time value at the next clock cycle. + */ +int ice_ptp_init_time(struct ice_hw *hw, u64 time) +{ + int status; + u8 tmr_idx; + + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + + /* Source timers */ + wr32(hw, GLTSYN_SHTIME_L(tmr_idx), lower_32_bits(time)); + wr32(hw, GLTSYN_SHTIME_H(tmr_idx), upper_32_bits(time)); + wr32(hw, GLTSYN_SHTIME_0(tmr_idx), 0); + + /* PHY timers */ + /* Fill Rx and Tx ports and send msg to PHY */ + status = ice_ptp_prep_phy_time_e810(hw, time & 0xFFFFFFFF); + if (status) + return status; + + return ice_ptp_tmr_cmd(hw, INIT_TIME); +} + +/** + * ice_ptp_write_incval - Program PHC with new increment value + * @hw: pointer to HW struct + * @incval: Source timer increment value per clock cycle + * + * Program the PHC with a new increment value. This requires a three-step + * process: + * + * 1) Write the increment value to the source timer shadow registers + * 2) Write the increment value to the PHY timer shadow registers + * 3) Issue an INIT_INCVAL timer command to synchronously switch both the + * source and port timers to the new increment value at the next clock + * cycle. + */ +int ice_ptp_write_incval(struct ice_hw *hw, u64 incval) +{ + int status; + u8 tmr_idx; + + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + + /* Shadow Adjust */ + wr32(hw, GLTSYN_SHADJ_L(tmr_idx), lower_32_bits(incval)); + wr32(hw, GLTSYN_SHADJ_H(tmr_idx), upper_32_bits(incval)); + + status = ice_ptp_prep_phy_incval_e810(hw, incval); + if (status) + return status; + + return ice_ptp_tmr_cmd(hw, INIT_INCVAL); +} + +/** + * ice_ptp_write_incval_locked - Program new incval while holding semaphore + * @hw: pointer to HW struct + * @incval: Source timer increment value per clock cycle + * + * Program a new PHC incval while holding the PTP semaphore. + */ +int ice_ptp_write_incval_locked(struct ice_hw *hw, u64 incval) +{ + int status; + + if (!ice_ptp_lock(hw)) + return -EBUSY; + + status = ice_ptp_write_incval(hw, incval); + + ice_ptp_unlock(hw); + + return status; +} + +/** + * ice_ptp_adj_clock - Adjust PHC clock time atomically + * @hw: pointer to HW struct + * @adj: Adjustment in nanoseconds + * + * Perform an atomic adjustment of the PHC time by the specified number of + * nanoseconds. This requires a three-step process: + * + * 1) Write the adjustment to the source timer shadow registers + * 2) Write the adjustment to the PHY timer shadow registers + * 3) Issue an ADJ_TIME timer command to synchronously apply the adjustment to + * both the source and port timers at the next clock cycle. + */ +int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj) +{ + int status; + u8 tmr_idx; + + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + + /* Write the desired clock adjustment into the GLTSYN_SHADJ register. + * For an ADJ_TIME command, this set of registers represents the value + * to add to the clock time. It supports subtraction by interpreting + * the value as a 2's complement integer. + */ + wr32(hw, GLTSYN_SHADJ_L(tmr_idx), 0); + wr32(hw, GLTSYN_SHADJ_H(tmr_idx), adj); + + status = ice_ptp_prep_phy_adj_e810(hw, adj); + if (status) + return status; + + return ice_ptp_tmr_cmd(hw, ADJ_TIME); +} + +/** + * ice_read_phy_tstamp - Read a PHY timestamp from the timestamo block + * @hw: pointer to the HW struct + * @block: the block to read from + * @idx: the timestamp index to read + * @tstamp: on return, the 40bit timestamp value + * + * Read a 40bit timestamp value out of the timestamp block. + */ +int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp) +{ + return ice_read_phy_tstamp_e810(hw, block, idx, tstamp); +} + +/** + * ice_clear_phy_tstamp - Clear a timestamp from the timestamp block + * @hw: pointer to the HW struct + * @block: the block to read from + * @idx: the timestamp index to reset + * + * Clear a timestamp, resetting its valid bit, from the timestamp block. + */ +int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx) +{ + return ice_clear_phy_tstamp_e810(hw, block, idx); +} diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h new file mode 100644 index 000000000000..55a414e87018 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -0,0 +1,79 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2021, Intel Corporation. */ + +#ifndef _ICE_PTP_HW_H_ +#define _ICE_PTP_HW_H_ + +enum ice_ptp_tmr_cmd { + INIT_TIME, + INIT_INCVAL, + ADJ_TIME, + ADJ_TIME_AT_TIME, + READ_TIME +}; + +/* Increment value to generate nanoseconds in the GLTSYN_TIME_L register for + * the E810 devices. Based off of a PLL with an 812.5 MHz frequency. + */ +#define ICE_PTP_NOMINAL_INCVAL_E810 0x13b13b13bULL + +/* Device agnostic functions */ +u8 ice_get_ptp_src_clock_index(struct ice_hw *hw); +bool ice_ptp_lock(struct ice_hw *hw); +void ice_ptp_unlock(struct ice_hw *hw); +int ice_ptp_init_time(struct ice_hw *hw, u64 time); +int ice_ptp_write_incval(struct ice_hw *hw, u64 incval); +int ice_ptp_write_incval_locked(struct ice_hw *hw, u64 incval); +int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj); +int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp); +int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx); + +/* E810 family functions */ +int ice_ptp_init_phy_e810(struct ice_hw *hw); + +#define PFTSYN_SEM_BYTES 4 + +/* PHY timer commands */ +#define SEL_CPK_SRC 8 + +/* Time Sync command Definitions */ +#define GLTSYN_CMD_INIT_TIME BIT(0) +#define GLTSYN_CMD_INIT_INCVAL BIT(1) +#define GLTSYN_CMD_ADJ_TIME BIT(2) +#define GLTSYN_CMD_ADJ_INIT_TIME (BIT(2) | BIT(3)) +#define GLTSYN_CMD_READ_TIME BIT(7) + +#define TS_CMD_MASK_E810 0xFF +#define SYNC_EXEC_CMD 0x3 + +/* E810 timesync enable register */ +#define ETH_GLTSYN_ENA(_i) (0x03000348 + ((_i) * 4)) + +/* E810 shadow init time registers */ +#define ETH_GLTSYN_SHTIME_0(i) (0x03000368 + ((i) * 32)) +#define ETH_GLTSYN_SHTIME_L(i) (0x0300036C + ((i) * 32)) + +/* E810 shadow time adjust registers */ +#define ETH_GLTSYN_SHADJ_L(_i) (0x03000378 + ((_i) * 32)) +#define ETH_GLTSYN_SHADJ_H(_i) (0x0300037C + ((_i) * 32)) + +/* E810 timer command register */ +#define ETH_GLTSYN_CMD 0x03000344 + +/* Source timer incval macros */ +#define INCVAL_HIGH_M 0xFF + +/* Timestamp block macros */ +#define TS_LOW_M 0xFFFFFFFF +#define TS_HIGH_S 32 + +#define BYTES_PER_IDX_ADDR_L_U 8 + +/* External PHY timestamp address */ +#define TS_EXT(a, port, idx) ((a) + (0x1000 * (port)) + \ + ((idx) * BYTES_PER_IDX_ADDR_L_U)) + +#define LOW_TX_MEMORY_BANK_START 0x03090000 +#define HIGH_TX_MEMORY_BANK_START 0x03090004 + +#endif /* _ICE_PTP_HW_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 0e5d8d52728b..d33d1906103c 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -49,6 +49,7 @@ static inline u32 ice_round_to_num(u32 N, u32 R) #define ICE_DBG_RDMA BIT_ULL(15) #define ICE_DBG_PKG BIT_ULL(16) #define ICE_DBG_RES BIT_ULL(17) +#define ICE_DBG_PTP BIT_ULL(19) #define ICE_DBG_AQ_MSG BIT_ULL(24) #define ICE_DBG_AQ_DESC BIT_ULL(25) #define ICE_DBG_AQ_DESC_BUF BIT_ULL(26) @@ -842,6 +843,14 @@ struct ice_hw { u8 ucast_shared; /* true if VSIs can share unicast addr */ +#define ICE_PHY_PER_NAC 1 +#define ICE_MAX_QUAD 2 +#define ICE_NUM_QUAD_TYPE 2 +#define ICE_PORTS_PER_QUAD 4 +#define ICE_PHY_0_LAST_QUAD 1 +#define ICE_PORTS_PER_PHY 8 +#define ICE_NUM_EXTERNAL_PORTS ICE_PORTS_PER_PHY + /* Active package version (currently active) */ struct ice_pkg_ver active_pkg_ver; u32 active_track_id; diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 15d8bad3d2f2..e73f3bc3dba5 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -71,6 +71,18 @@ */ #define lower_32_bits(n) ((u32)((n) & 0xffffffff)) +/** + * upper_16_bits - return bits 16-31 of a number + * @n: the number we're accessing + */ +#define upper_16_bits(n) ((u16)((n) >> 16)) + +/** + * lower_16_bits - return bits 0-15 of a number + * @n: the number we're accessing + */ +#define lower_16_bits(n) ((u16)((n) & 0xffff)) + struct completion; struct pt_regs; struct user; -- cgit v1.2.3-71-gd317 From ab6a303c5440156dd475b5884cff26a7245630f8 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 11 Jun 2021 22:01:26 +0300 Subject: net: dsa: tag_8021q: remove shim declarations All users of tag_8021q select it in Kconfig, so shim functions are not needed because it is not possible for it to be disabled and its callers enabled. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 76 ----------------------------------------------- 1 file changed, 76 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index b12b05f1c8b4..cbf2c9b1ee4f 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -37,8 +37,6 @@ struct dsa_8021q_context { #define DSA_8021Q_N_SUBVLAN 8 -#if IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) - int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled); int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, @@ -70,78 +68,4 @@ bool vid_is_dsa_8021q_txvlan(u16 vid); bool vid_is_dsa_8021q(u16 vid); -#else - -int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled) -{ - return 0; -} - -int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, - struct dsa_8021q_context *other_ctx, - int other_port) -{ - return 0; -} - -int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, - struct dsa_8021q_context *other_ctx, - int other_port) -{ - return 0; -} - -struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, - u16 tpid, u16 tci) -{ - return NULL; -} - -u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port) -{ - return 0; -} - -u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port) -{ - return 0; -} - -u16 dsa_8021q_rx_vid_subvlan(struct dsa_switch *ds, int port, u16 subvlan) -{ - return 0; -} - -int dsa_8021q_rx_switch_id(u16 vid) -{ - return 0; -} - -int dsa_8021q_rx_source_port(u16 vid) -{ - return 0; -} - -u16 dsa_8021q_rx_subvlan(u16 vid) -{ - return 0; -} - -bool vid_is_dsa_8021q_rxvlan(u16 vid) -{ - return false; -} - -bool vid_is_dsa_8021q_txvlan(u16 vid) -{ - return false; -} - -bool vid_is_dsa_8021q(u16 vid) -{ - return false; -} - -#endif /* IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) */ - #endif /* _NET_DSA_8021Q_H */ -- cgit v1.2.3-71-gd317 From 233697b3b3f60b17d02ca2a35230aee0ac6f1759 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 11 Jun 2021 22:01:27 +0300 Subject: net: dsa: tag_8021q: refactor RX VLAN parsing into a dedicated function The added value of this function is that it can deal with both the case where the VLAN header is in the skb head, as well as in the offload field. This is something I was not able to do using other functions in the network stack. Since both ocelot-8021q and sja1105 need to do the same stuff, let's make it a common service provided by tag_8021q. This is done as refactoring for the new SJA1110 tagger, which partly uses tag_8021q as well (just like SJA1105), and will be the third caller. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 3 +++ net/dsa/tag_8021q.c | 23 +++++++++++++++++++++++ net/dsa/tag_ocelot_8021q.c | 18 ++---------------- net/dsa/tag_sja1105.c | 33 +++++++++++---------------------- 4 files changed, 39 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index cbf2c9b1ee4f..1587961f1a7b 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -50,6 +50,9 @@ int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, u16 tpid, u16 tci); +void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, + int *subvlan); + u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port); u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port); diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 122ad5833fb1..4aa29f90ecea 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -471,4 +471,27 @@ struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, } EXPORT_SYMBOL_GPL(dsa_8021q_xmit); +void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, + int *subvlan) +{ + u16 vid, tci; + + skb_push_rcsum(skb, ETH_HLEN); + if (skb_vlan_tag_present(skb)) { + tci = skb_vlan_tag_get(skb); + __vlan_hwaccel_clear_tag(skb); + } else { + __skb_vlan_pop(skb, &tci); + } + skb_pull_rcsum(skb, ETH_HLEN); + + vid = tci & VLAN_VID_MASK; + + *source_port = dsa_8021q_rx_source_port(vid); + *switch_id = dsa_8021q_rx_switch_id(vid); + *subvlan = dsa_8021q_rx_subvlan(vid); + skb->priority = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; +} +EXPORT_SYMBOL_GPL(dsa_8021q_rcv); + MODULE_LICENSE("GPL v2"); diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c index 663b74793cfc..85ac85c3af8c 100644 --- a/net/dsa/tag_ocelot_8021q.c +++ b/net/dsa/tag_ocelot_8021q.c @@ -41,29 +41,15 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, struct net_device *netdev, struct packet_type *pt) { - int src_port, switch_id, qos_class; - u16 vid, tci; + int src_port, switch_id, subvlan; - skb_push_rcsum(skb, ETH_HLEN); - if (skb_vlan_tag_present(skb)) { - tci = skb_vlan_tag_get(skb); - __vlan_hwaccel_clear_tag(skb); - } else { - __skb_vlan_pop(skb, &tci); - } - skb_pull_rcsum(skb, ETH_HLEN); - - vid = tci & VLAN_VID_MASK; - src_port = dsa_8021q_rx_source_port(vid); - switch_id = dsa_8021q_rx_switch_id(vid); - qos_class = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; + dsa_8021q_rcv(skb, &src_port, &switch_id, &subvlan); skb->dev = dsa_master_find_slave(netdev, switch_id, src_port); if (!skb->dev) return NULL; skb->offload_fwd_mark = 1; - skb->priority = qos_class; return skb; } diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 92e147293acf..a70625fe64f7 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -275,44 +275,33 @@ static void sja1105_decode_subvlan(struct sk_buff *skb, u16 subvlan) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci); } +static bool sja1105_skb_has_tag_8021q(const struct sk_buff *skb) +{ + u16 tpid = ntohs(eth_hdr(skb)->h_proto); + + return tpid == ETH_P_SJA1105 || tpid == ETH_P_8021Q || + skb_vlan_tag_present(skb); +} + static struct sk_buff *sja1105_rcv(struct sk_buff *skb, struct net_device *netdev, struct packet_type *pt) { + int source_port, switch_id, subvlan = 0; struct sja1105_meta meta = {0}; - int source_port, switch_id; struct ethhdr *hdr; - u16 tpid, vid, tci; bool is_link_local; - u16 subvlan = 0; - bool is_tagged; bool is_meta; hdr = eth_hdr(skb); - tpid = ntohs(hdr->h_proto); - is_tagged = (tpid == ETH_P_SJA1105 || tpid == ETH_P_8021Q || - skb_vlan_tag_present(skb)); is_link_local = sja1105_is_link_local(skb); is_meta = sja1105_is_meta_frame(skb); skb->offload_fwd_mark = 1; - if (is_tagged) { + if (sja1105_skb_has_tag_8021q(skb)) { /* Normal traffic path. */ - skb_push_rcsum(skb, ETH_HLEN); - if (skb_vlan_tag_present(skb)) { - tci = skb_vlan_tag_get(skb); - __vlan_hwaccel_clear_tag(skb); - } else { - __skb_vlan_pop(skb, &tci); - } - skb_pull_rcsum(skb, ETH_HLEN); - - vid = tci & VLAN_VID_MASK; - source_port = dsa_8021q_rx_source_port(vid); - switch_id = dsa_8021q_rx_switch_id(vid); - skb->priority = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; - subvlan = dsa_8021q_rx_subvlan(vid); + dsa_8021q_rcv(skb, &source_port, &switch_id, &subvlan); } else if (is_link_local) { /* Management traffic path. Switch embeds the switch ID and * port ID into bytes of the destination MAC, courtesy of -- cgit v1.2.3-71-gd317 From 617ef8d9377b9aac381c023cd0823da264c2f463 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 11 Jun 2021 22:01:28 +0300 Subject: net: dsa: sja1105: make SJA1105_SKB_CB fit a full timestamp In SJA1105, RX timestamps for packets sent to the CPU are transmitted in separate follow-up packets (metadata frames). These contain partial timestamps (24 or 32 bits) which are kept in SJA1105_SKB_CB(skb)->meta_tstamp. Thankfully, SJA1110 improved that, and the RX timestamps are now transmitted in-band with the actual packet, in the timestamp trailer. The RX timestamps are now full-width 64 bits. Because we process the RX DSA tags in the rcv() method in the tagger, but we would like to preserve the DSA code structure in that we populate the skb timestamp in the port_rxtstamp() call which only happens later, the implication is that we must somehow pass the 64-bit timestamp from the rcv() method all the way to port_rxtstamp(). We can use the skb->cb for that. Rename the meta_tstamp from struct sja1105_skb_cb from "meta_tstamp" to "tstamp", and increase its size to 64 bits. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_ptp.c | 2 +- include/linux/dsa/sja1105.h | 2 +- net/dsa/tag_sja1105.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c index 0bc566b9e958..dea82f8a40c4 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.c +++ b/drivers/net/dsa/sja1105/sja1105_ptp.c @@ -397,7 +397,7 @@ static long sja1105_rxtstamp_work(struct ptp_clock_info *ptp) *shwt = (struct skb_shared_hwtstamps) {0}; - ts = SJA1105_SKB_CB(skb)->meta_tstamp; + ts = SJA1105_SKB_CB(skb)->tstamp; ts = sja1105_tstamp_reconstruct(ds, ticks, ts); shwt->hwtstamp = ns_to_ktime(sja1105_ticks_to_ns(ts)); diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 1eb84562b311..865a548a6ef2 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -48,7 +48,7 @@ struct sja1105_tagger_data { struct sja1105_skb_cb { struct sk_buff *clone; - u32 meta_tstamp; + u64 tstamp; }; #define SJA1105_SKB_CB(skb) \ diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index a70625fe64f7..11f555dd9566 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -147,7 +147,7 @@ static void sja1105_transfer_meta(struct sk_buff *skb, hdr->h_dest[3] = meta->dmac_byte_3; hdr->h_dest[4] = meta->dmac_byte_4; - SJA1105_SKB_CB(skb)->meta_tstamp = meta->tstamp; + SJA1105_SKB_CB(skb)->tstamp = meta->tstamp; } /* This is a simple state machine which follows the hardware mechanism of -- cgit v1.2.3-71-gd317 From 4913b8ebf8a9c56ce66466b4daa07d7d4678cdd8 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 11 Jun 2021 22:01:29 +0300 Subject: net: dsa: add support for the SJA1110 native tagging protocol The SJA1110 has improved a few things compared to SJA1105: - To send a control packet from the host port with SJA1105, one needed to program a one-shot "management route" over SPI. This is no longer true with SJA1110, you can actually send "in-band control extensions" in the packets sent by DSA, these are in fact DSA tags which contain the destination port and switch ID. - When receiving a control packet from the switch with SJA1105, the source port and switch ID were written in bytes 3 and 4 of the destination MAC address of the frame (which was a very poor shot at a DSA header). If the control packet also had an RX timestamp, that timestamp was sent in an actual follow-up packet, so there were reordering concerns on multi-core/multi-queue DSA masters, where the metadata frame with the RX timestamp might get processed before the actual packet to which that timestamp belonged (there is no way to pair a packet to its timestamp other than the order in which they were received). On SJA1110, this is no longer true, control packets have the source port, switch ID and timestamp all in the DSA tags. - Timestamps from the switch were partial: to get a 64-bit timestamp as required by PTP stacks, one would need to take the partial 24-bit or 32-bit timestamp from the packet, then read the current PTP time very quickly, and then patch in the high bits of the current PTP time into the captured partial timestamp, to reconstruct what the full 64-bit timestamp must have been. That is awful because packet processing is done in NAPI context, but reading the current PTP time is done over SPI and therefore needs sleepable context. But it also aggravated a few things: - Not only is there a DSA header in SJA1110, but there is a DSA trailer in fact, too. So DSA needs to be extended to support taggers which have both a header and a trailer. Very unconventional - my understanding is that the trailer exists because the timestamps couldn't be prepared in time for putting them in the header area. - Like SJA1105, not all packets sent to the CPU have the DSA tag added to them, only control packets do: * the ones which match the destination MAC filters/traps in MAC_FLTRES1 and MAC_FLTRES0 * the ones which match FDB entries which have TRAP or TAKETS bits set So we could in theory hack something up to request the switch to take timestamps for all packets that reach the CPU, and those would be DSA-tagged and contain the source port / switch ID by virtue of the fact that there needs to be a timestamp trailer provided. BUT: - The SJA1110 does not parse its own DSA tags in a way that is useful for routing in cross-chip topologies, a la Marvell. And the sja1105 driver already supports cross-chip bridging from the SJA1105 days. It does that by automatically setting up the DSA links as VLAN trunks which contain all the necessary tag_8021q RX VLANs that must be communicated between the switches that span the same bridge. So when using tag_8021q on sja1105, it is possible to have 2 switches with ports sw0p0, sw0p1, sw1p0, sw1p1, and 2 VLAN-unaware bridges br0 and br1, and br0 can take sw0p0 and sw1p0, and br1 can take sw0p1 and sw1p1, and forwarding will happen according to the expected rules of the Linux bridge. We like that, and we don't want that to go away, so as a matter of fact, the SJA1110 tagger still needs to support tag_8021q. So the sja1110 tagger is a hybrid between tag_8021q for data packets, and the native hardware support for control packets. On RX, packets have a 13-byte trailer if they contain an RX timestamp. That trailer is padded in such a way that its byte 8 (the start of the "residence time" field - not parsed by Linux because we don't care) is aligned on a 16 byte boundary. So the padding has a variable length between 0 and 15 bytes. The DSA header contains the offset of the beginning of the padding relative to the beginning of the frame (and the end of the padding is obviously the end of the packet minus 13 bytes, the length of the trailer). So we discard it. Packets which don't have a trailer contain the source port and switch ID information in the header (they are "trap-to-host" packets). Packets which have a trailer contain the source port and switch ID in the trailer. On TX, the destination port mask and switch ID is always in the trailer, so we always need to say in the header that a trailer is present. The header needs a custom EtherType and this was chosen as 0xdadc, after 0xdada which is for Marvell and 0xdadb which is for VLANs in VLAN-unaware mode on SJA1105 (and SJA1110 in fact too). Because we use tag_8021q in concert with the native tagging protocol, control packets will have 2 DSA tags. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105.h | 1 + drivers/net/dsa/sja1105/sja1105_main.c | 6 +- drivers/net/dsa/sja1105/sja1105_spi.c | 10 ++ drivers/net/dsa/sja1105/sja1105_static_config.c | 1 + drivers/net/dsa/sja1105/sja1105_static_config.h | 1 + include/linux/dsa/sja1105.h | 1 + include/net/dsa.h | 2 + net/dsa/tag_sja1105.c | 221 +++++++++++++++++++++++- 8 files changed, 240 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h index 4d192331754c..a6d64b27e6a9 100644 --- a/drivers/net/dsa/sja1105/sja1105.h +++ b/drivers/net/dsa/sja1105/sja1105.h @@ -110,6 +110,7 @@ struct sja1105_info { int max_frame_mem; int num_ports; bool multiple_cascade_ports; + enum dsa_tag_protocol tag_proto; const struct sja1105_dynamic_table_ops *dyn_ops; const struct sja1105_table_ops *static_ops; const struct sja1105_regs *regs; diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 850bbc793369..6e2cfbf605ef 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -667,6 +667,8 @@ static int sja1105_init_general_params(struct sja1105_private *priv) .tpid2 = ETH_P_SJA1105, /* Enable the TTEthernet engine on SJA1110 */ .tte_en = true, + /* Set up the EtherType for control packets on SJA1110 */ + .header_type = ETH_P_SJA1110, }; struct sja1105_general_params_entry *general_params; struct dsa_switch *ds = priv->ds; @@ -2174,7 +2176,9 @@ static enum dsa_tag_protocol sja1105_get_tag_protocol(struct dsa_switch *ds, int port, enum dsa_tag_protocol mp) { - return DSA_TAG_PROTO_SJA1105; + struct sja1105_private *priv = ds->priv; + + return priv->info->tag_proto; } static int sja1105_find_free_subvlan(u16 *subvlan_map, bool pvid) diff --git a/drivers/net/dsa/sja1105/sja1105_spi.c b/drivers/net/dsa/sja1105/sja1105_spi.c index e6c2a37aa617..9156f4cc11f2 100644 --- a/drivers/net/dsa/sja1105/sja1105_spi.c +++ b/drivers/net/dsa/sja1105/sja1105_spi.c @@ -569,6 +569,7 @@ const struct sja1105_info sja1105e_info = { .static_ops = sja1105e_table_ops, .dyn_ops = sja1105et_dyn_ops, .qinq_tpid = ETH_P_8021Q, + .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = false, .ptp_ts_bits = 24, .ptpegr_ts_bytes = 4, @@ -600,6 +601,7 @@ const struct sja1105_info sja1105t_info = { .static_ops = sja1105t_table_ops, .dyn_ops = sja1105et_dyn_ops, .qinq_tpid = ETH_P_8021Q, + .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = false, .ptp_ts_bits = 24, .ptpegr_ts_bytes = 4, @@ -631,6 +633,7 @@ const struct sja1105_info sja1105p_info = { .static_ops = sja1105p_table_ops, .dyn_ops = sja1105pqrs_dyn_ops, .qinq_tpid = ETH_P_8021AD, + .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = true, .ptp_ts_bits = 32, .ptpegr_ts_bytes = 8, @@ -663,6 +666,7 @@ const struct sja1105_info sja1105q_info = { .static_ops = sja1105q_table_ops, .dyn_ops = sja1105pqrs_dyn_ops, .qinq_tpid = ETH_P_8021AD, + .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = true, .ptp_ts_bits = 32, .ptpegr_ts_bytes = 8, @@ -695,6 +699,7 @@ const struct sja1105_info sja1105r_info = { .static_ops = sja1105r_table_ops, .dyn_ops = sja1105pqrs_dyn_ops, .qinq_tpid = ETH_P_8021AD, + .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = true, .ptp_ts_bits = 32, .ptpegr_ts_bytes = 8, @@ -729,6 +734,7 @@ const struct sja1105_info sja1105s_info = { .dyn_ops = sja1105pqrs_dyn_ops, .regs = &sja1105pqrs_regs, .qinq_tpid = ETH_P_8021AD, + .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = true, .ptp_ts_bits = 32, .ptpegr_ts_bytes = 8, @@ -762,6 +768,7 @@ const struct sja1105_info sja1110a_info = { .dyn_ops = sja1110_dyn_ops, .regs = &sja1110_regs, .qinq_tpid = ETH_P_8021AD, + .tag_proto = DSA_TAG_PROTO_SJA1110, .can_limit_mcast_flood = true, .multiple_cascade_ports = true, .ptp_ts_bits = 32, @@ -808,6 +815,7 @@ const struct sja1105_info sja1110b_info = { .dyn_ops = sja1110_dyn_ops, .regs = &sja1110_regs, .qinq_tpid = ETH_P_8021AD, + .tag_proto = DSA_TAG_PROTO_SJA1110, .can_limit_mcast_flood = true, .multiple_cascade_ports = true, .ptp_ts_bits = 32, @@ -854,6 +862,7 @@ const struct sja1105_info sja1110c_info = { .dyn_ops = sja1110_dyn_ops, .regs = &sja1110_regs, .qinq_tpid = ETH_P_8021AD, + .tag_proto = DSA_TAG_PROTO_SJA1110, .can_limit_mcast_flood = true, .multiple_cascade_ports = true, .ptp_ts_bits = 32, @@ -900,6 +909,7 @@ const struct sja1105_info sja1110d_info = { .dyn_ops = sja1110_dyn_ops, .regs = &sja1110_regs, .qinq_tpid = ETH_P_8021AD, + .tag_proto = DSA_TAG_PROTO_SJA1110, .can_limit_mcast_flood = true, .multiple_cascade_ports = true, .ptp_ts_bits = 32, diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.c b/drivers/net/dsa/sja1105/sja1105_static_config.c index eda571819d45..1491b72008f3 100644 --- a/drivers/net/dsa/sja1105/sja1105_static_config.c +++ b/drivers/net/dsa/sja1105/sja1105_static_config.c @@ -212,6 +212,7 @@ size_t sja1110_general_params_entry_packing(void *buf, void *entry_ptr, sja1105_packing(buf, &entry->egrmirrdei, 110, 110, size, op); sja1105_packing(buf, &entry->replay_port, 109, 106, size, op); sja1105_packing(buf, &entry->tdmaconfigidx, 70, 67, size, op); + sja1105_packing(buf, &entry->header_type, 64, 49, size, op); sja1105_packing(buf, &entry->tte_en, 16, 16, size, op); return size; } diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.h b/drivers/net/dsa/sja1105/sja1105_static_config.h index 9bef51791bff..bce0f5c03d0b 100644 --- a/drivers/net/dsa/sja1105/sja1105_static_config.h +++ b/drivers/net/dsa/sja1105/sja1105_static_config.h @@ -217,6 +217,7 @@ struct sja1105_general_params_entry { /* SJA1110 only */ u64 tte_en; u64 tdmaconfigidx; + u64 header_type; }; struct sja1105_schedule_entry_points_entry { diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 865a548a6ef2..b02cf7b515ae 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -14,6 +14,7 @@ #define ETH_P_SJA1105 ETH_P_DSA_8021Q #define ETH_P_SJA1105_META 0x0008 +#define ETH_P_SJA1110 0xdadc /* IEEE 802.3 Annex 57A: Slow Protocols PDUs (01:80:C2:xx:xx:xx) */ #define SJA1105_LINKLOCAL_FILTER_A 0x0180C2000000ull diff --git a/include/net/dsa.h b/include/net/dsa.h index 0a10f6fffc3d..289d68e82da0 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -50,6 +50,7 @@ struct phylink_link_state; #define DSA_TAG_PROTO_OCELOT_8021Q_VALUE 20 #define DSA_TAG_PROTO_SEVILLE_VALUE 21 #define DSA_TAG_PROTO_BRCM_LEGACY_VALUE 22 +#define DSA_TAG_PROTO_SJA1110_VALUE 23 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -75,6 +76,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_XRS700X = DSA_TAG_PROTO_XRS700X_VALUE, DSA_TAG_PROTO_OCELOT_8021Q = DSA_TAG_PROTO_OCELOT_8021Q_VALUE, DSA_TAG_PROTO_SEVILLE = DSA_TAG_PROTO_SEVILLE_VALUE, + DSA_TAG_PROTO_SJA1110 = DSA_TAG_PROTO_SJA1110_VALUE, }; struct packet_type; diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 11f555dd9566..37e1d64e07c6 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -7,6 +7,47 @@ #include #include "dsa_priv.h" +/* Is this a TX or an RX header? */ +#define SJA1110_HEADER_HOST_TO_SWITCH BIT(15) + +/* RX header */ +#define SJA1110_RX_HEADER_IS_METADATA BIT(14) +#define SJA1110_RX_HEADER_HOST_ONLY BIT(13) +#define SJA1110_RX_HEADER_HAS_TRAILER BIT(12) + +/* Trap-to-host format (no trailer present) */ +#define SJA1110_RX_HEADER_SRC_PORT(x) (((x) & GENMASK(7, 4)) >> 4) +#define SJA1110_RX_HEADER_SWITCH_ID(x) ((x) & GENMASK(3, 0)) + +/* Timestamp format (trailer present) */ +#define SJA1110_RX_HEADER_TRAILER_POS(x) ((x) & GENMASK(11, 0)) + +#define SJA1110_RX_TRAILER_SWITCH_ID(x) (((x) & GENMASK(7, 4)) >> 4) +#define SJA1110_RX_TRAILER_SRC_PORT(x) ((x) & GENMASK(3, 0)) + +/* TX header */ +#define SJA1110_TX_HEADER_UPDATE_TC BIT(14) +#define SJA1110_TX_HEADER_TAKE_TS BIT(13) +#define SJA1110_TX_HEADER_TAKE_TS_CASC BIT(12) +#define SJA1110_TX_HEADER_HAS_TRAILER BIT(11) + +/* Only valid if SJA1110_TX_HEADER_HAS_TRAILER is false */ +#define SJA1110_TX_HEADER_PRIO(x) (((x) << 7) & GENMASK(10, 7)) +#define SJA1110_TX_HEADER_TSTAMP_ID(x) ((x) & GENMASK(7, 0)) + +/* Only valid if SJA1110_TX_HEADER_HAS_TRAILER is true */ +#define SJA1110_TX_HEADER_TRAILER_POS(x) ((x) & GENMASK(10, 0)) + +#define SJA1110_TX_TRAILER_TSTAMP_ID(x) (((x) << 24) & GENMASK(31, 24)) +#define SJA1110_TX_TRAILER_PRIO(x) (((x) << 21) & GENMASK(23, 21)) +#define SJA1110_TX_TRAILER_SWITCHID(x) (((x) << 12) & GENMASK(15, 12)) +#define SJA1110_TX_TRAILER_DESTPORTS(x) (((x) << 1) & GENMASK(11, 1)) + +#define SJA1110_HEADER_LEN 4 +#define SJA1110_RX_TRAILER_LEN 13 +#define SJA1110_TX_TRAILER_LEN 4 +#define SJA1110_MAX_PADDING_LEN 15 + /* Similar to is_link_local_ether_addr(hdr->h_dest) but also covers PTP */ static inline bool sja1105_is_link_local(const struct sk_buff *skb) { @@ -140,6 +181,50 @@ static struct sk_buff *sja1105_xmit(struct sk_buff *skb, ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); } +static struct sk_buff *sja1110_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + struct dsa_port *dp = dsa_slave_to_port(netdev); + u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index); + u16 queue_mapping = skb_get_queue_mapping(skb); + u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); + struct ethhdr *eth_hdr; + __be32 *tx_trailer; + __be16 *tx_header; + int trailer_pos; + + /* Transmitting control packets is done using in-band control + * extensions, while data packets are transmitted using + * tag_8021q TX VLANs. + */ + if (likely(!sja1105_is_link_local(skb))) + return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp->priv), + ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); + + skb_push(skb, SJA1110_HEADER_LEN); + + /* Move Ethernet header to the left, making space for DSA tag */ + memmove(skb->data, skb->data + SJA1110_HEADER_LEN, 2 * ETH_ALEN); + + trailer_pos = skb->len; + + /* On TX, skb->data points to skb_mac_header(skb) */ + eth_hdr = (struct ethhdr *)skb->data; + tx_header = (__be16 *)(eth_hdr + 1); + tx_trailer = skb_put(skb, SJA1110_TX_TRAILER_LEN); + + eth_hdr->h_proto = htons(ETH_P_SJA1110); + + *tx_header = htons(SJA1110_HEADER_HOST_TO_SWITCH | + SJA1110_TX_HEADER_HAS_TRAILER | + SJA1110_TX_HEADER_TRAILER_POS(trailer_pos)); + *tx_trailer = cpu_to_be32(SJA1110_TX_TRAILER_PRIO(pcp) | + SJA1110_TX_TRAILER_SWITCHID(dp->ds->index) | + SJA1110_TX_TRAILER_DESTPORTS(BIT(dp->index))); + + return skb; +} + static void sja1105_transfer_meta(struct sk_buff *skb, const struct sja1105_meta *meta) { @@ -283,6 +368,11 @@ static bool sja1105_skb_has_tag_8021q(const struct sk_buff *skb) skb_vlan_tag_present(skb); } +static bool sja1110_skb_has_inband_control_extension(const struct sk_buff *skb) +{ + return ntohs(eth_hdr(skb)->h_proto) == ETH_P_SJA1110; +} + static struct sk_buff *sja1105_rcv(struct sk_buff *skb, struct net_device *netdev, struct packet_type *pt) @@ -333,6 +423,98 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, is_meta); } +static struct sk_buff *sja1110_rcv_inband_control_extension(struct sk_buff *skb, + int *source_port, + int *switch_id) +{ + u16 rx_header; + + if (unlikely(!pskb_may_pull(skb, SJA1110_HEADER_LEN))) + return NULL; + + /* skb->data points to skb_mac_header(skb) + ETH_HLEN, which is exactly + * what we need because the caller has checked the EtherType (which is + * located 2 bytes back) and we just need a pointer to the header that + * comes afterwards. + */ + rx_header = ntohs(*(__be16 *)skb->data); + + /* Timestamp frame, we have a trailer */ + if (rx_header & SJA1110_RX_HEADER_HAS_TRAILER) { + int start_of_padding = SJA1110_RX_HEADER_TRAILER_POS(rx_header); + u8 *rx_trailer = skb_tail_pointer(skb) - SJA1110_RX_TRAILER_LEN; + u64 *tstamp = &SJA1105_SKB_CB(skb)->tstamp; + u8 last_byte = rx_trailer[12]; + + /* The timestamp is unaligned, so we need to use packing() + * to get it + */ + packing(rx_trailer, tstamp, 63, 0, 8, UNPACK, 0); + + *source_port = SJA1110_RX_TRAILER_SRC_PORT(last_byte); + *switch_id = SJA1110_RX_TRAILER_SWITCH_ID(last_byte); + + /* skb->len counts from skb->data, while start_of_padding + * counts from the destination MAC address. Right now skb->data + * is still as set by the DSA master, so to trim away the + * padding and trailer we need to account for the fact that + * skb->data points to skb_mac_header(skb) + ETH_HLEN. + */ + pskb_trim_rcsum(skb, start_of_padding - ETH_HLEN); + /* Trap-to-host frame, no timestamp trailer */ + } else { + *source_port = SJA1110_RX_HEADER_SRC_PORT(rx_header); + *switch_id = SJA1110_RX_HEADER_SWITCH_ID(rx_header); + } + + /* Advance skb->data past the DSA header */ + skb_pull_rcsum(skb, SJA1110_HEADER_LEN); + + /* Remove the DSA header */ + memmove(skb->data - ETH_HLEN, skb->data - ETH_HLEN - SJA1110_HEADER_LEN, + 2 * ETH_ALEN); + + /* With skb->data in its final place, update the MAC header + * so that eth_hdr() continues to works properly. + */ + skb_set_mac_header(skb, -ETH_HLEN); + + return skb; +} + +static struct sk_buff *sja1110_rcv(struct sk_buff *skb, + struct net_device *netdev, + struct packet_type *pt) +{ + int source_port = -1, switch_id = -1, subvlan = 0; + + skb->offload_fwd_mark = 1; + + if (sja1110_skb_has_inband_control_extension(skb)) { + skb = sja1110_rcv_inband_control_extension(skb, &source_port, + &switch_id); + if (!skb) + return NULL; + } + + /* Packets with in-band control extensions might still have RX VLANs */ + if (likely(sja1105_skb_has_tag_8021q(skb))) + dsa_8021q_rcv(skb, &source_port, &switch_id, &subvlan); + + skb->dev = dsa_master_find_slave(netdev, switch_id, source_port); + if (!skb->dev) { + netdev_warn(netdev, + "Couldn't decode source port %d and switch id %d\n", + source_port, switch_id); + return NULL; + } + + if (subvlan) + sja1105_decode_subvlan(skb, subvlan); + + return skb; +} + static void sja1105_flow_dissect(const struct sk_buff *skb, __be16 *proto, int *offset) { @@ -343,6 +525,20 @@ static void sja1105_flow_dissect(const struct sk_buff *skb, __be16 *proto, dsa_tag_generic_flow_dissect(skb, proto, offset); } +static void sja1110_flow_dissect(const struct sk_buff *skb, __be16 *proto, + int *offset) +{ + /* Management frames have 2 DSA tags on RX, so the needed_headroom we + * declared is fine for the generic dissector adjustment procedure. + */ + if (unlikely(sja1105_is_link_local(skb))) + return dsa_tag_generic_flow_dissect(skb, proto, offset); + + /* For the rest, there is a single DSA tag, the tag_8021q one */ + *offset = VLAN_HLEN; + *proto = ((__be16 *)skb->data)[(VLAN_HLEN / 2) - 1]; +} + static const struct dsa_device_ops sja1105_netdev_ops = { .name = "sja1105", .proto = DSA_TAG_PROTO_SJA1105, @@ -354,7 +550,28 @@ static const struct dsa_device_ops sja1105_netdev_ops = { .promisc_on_master = true, }; -MODULE_LICENSE("GPL v2"); +DSA_TAG_DRIVER(sja1105_netdev_ops); MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SJA1105); -module_dsa_tag_driver(sja1105_netdev_ops); +static const struct dsa_device_ops sja1110_netdev_ops = { + .name = "sja1110", + .proto = DSA_TAG_PROTO_SJA1110, + .xmit = sja1110_xmit, + .rcv = sja1110_rcv, + .filter = sja1105_filter, + .flow_dissect = sja1110_flow_dissect, + .needed_headroom = SJA1110_HEADER_LEN + VLAN_HLEN, + .needed_tailroom = SJA1110_RX_TRAILER_LEN + SJA1110_MAX_PADDING_LEN, +}; + +DSA_TAG_DRIVER(sja1110_netdev_ops); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SJA1110); + +static struct dsa_tag_driver *sja1105_tag_driver_array[] = { + &DSA_TAG_DRIVER_NAME(sja1105_netdev_ops), + &DSA_TAG_DRIVER_NAME(sja1110_netdev_ops), +}; + +module_dsa_tag_drivers(sja1105_tag_driver_array); + +MODULE_LICENSE("GPL v2"); -- cgit v1.2.3-71-gd317 From 566b18c8b752f67c4e82f0eb4563dd71f84a8799 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 11 Jun 2021 22:01:31 +0300 Subject: net: dsa: sja1105: implement TX timestamping for SJA1110 The TX timestamping procedure for SJA1105 is a bit unconventional because the transmit procedure itself is unconventional. Control packets (and therefore PTP as well) are transmitted to a specific port in SJA1105 using "management routes" which must be written over SPI to the switch. These are one-shot rules that match by destination MAC address on traffic coming from the CPU port, and select the precise destination port for that packet. So to transmit a packet from NET_TX softirq context, we actually need to defer to a process context so that we can perform that SPI write before we send the packet. The DSA master dev_queue_xmit() runs in process context, and we poll until the switch confirms it took the TX timestamp, then we annotate the skb clone with that TX timestamp. This is why the sja1105 driver does not need an skb queue for TX timestamping. But the SJA1110 is a bit (not much!) more conventional, and you can request 2-step TX timestamping through the DSA header, as well as give the switch a cookie (timestamp ID) which it will give back to you when it has the timestamp. So now we do need a queue for keeping the skb clones until their TX timestamps become available. The interesting part is that the metadata frames from SJA1105 haven't disappeared completely. On SJA1105 they were used as follow-ups which contained RX timestamps, but on SJA1110 they are actually TX completion packets, which contain a variable (up to 32) array of timestamps. Why an array? Because: - not only is the TX timestamp on the egress port being communicated, but also the RX timestamp on the CPU port. Nice, but we don't care about that, so we ignore it. - because a packet could be multicast to multiple egress ports, each port takes its own timestamp, and the TX completion packet contains the individual timestamps on each port. This is unconventional because switches typically have a timestamping FIFO and raise an interrupt, but this one doesn't. So the tagger needs to detect and parse meta frames, and call into the main switch driver, which pairs the timestamps with the skbs in the TX timestamping queue which are waiting for one. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105.h | 1 + drivers/net/dsa/sja1105/sja1105_ptp.c | 69 +++++++++++++++++++++++++++++++++++ drivers/net/dsa/sja1105/sja1105_ptp.h | 7 ++++ drivers/net/dsa/sja1105/sja1105_spi.c | 4 ++ include/linux/dsa/sja1105.h | 23 ++++++++++++ net/dsa/tag_sja1105.c | 52 ++++++++++++++++++++++++++ 6 files changed, 156 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h index 201bca282884..5f3449351668 100644 --- a/drivers/net/dsa/sja1105/sja1105.h +++ b/drivers/net/dsa/sja1105/sja1105.h @@ -131,6 +131,7 @@ struct sja1105_info { void (*ptp_cmd_packing)(u8 *buf, struct sja1105_ptp_cmd *cmd, enum packing_op op); bool (*rxtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb); + void (*txtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb); int (*clocking_setup)(struct sja1105_private *priv); const char *name; bool supports_mii[SJA1105_MAX_NUM_PORTS]; diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c index 62fe05b4cb60..691f6dd7e669 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.c +++ b/drivers/net/dsa/sja1105/sja1105_ptp.c @@ -79,6 +79,7 @@ static int sja1105_change_rxtstamping(struct sja1105_private *priv, priv->tagger_data.stampable_skb = NULL; } ptp_cancel_worker_sync(ptp_data->clock); + skb_queue_purge(&ptp_data->skb_txtstamp_queue); skb_queue_purge(&ptp_data->skb_rxtstamp_queue); return sja1105_static_config_reload(priv, SJA1105_RX_HWTSTAMPING); @@ -451,6 +452,67 @@ bool sja1105_port_rxtstamp(struct dsa_switch *ds, int port, return priv->info->rxtstamp(ds, port, skb); } +void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, u8 ts_id, + enum sja1110_meta_tstamp dir, u64 tstamp) +{ + struct sja1105_private *priv = ds->priv; + struct sja1105_ptp_data *ptp_data = &priv->ptp_data; + struct sk_buff *skb, *skb_tmp, *skb_match = NULL; + struct skb_shared_hwtstamps shwt = {0}; + + /* We don't care about RX timestamps on the CPU port */ + if (dir == SJA1110_META_TSTAMP_RX) + return; + + spin_lock(&ptp_data->skb_txtstamp_queue.lock); + + skb_queue_walk_safe(&ptp_data->skb_txtstamp_queue, skb, skb_tmp) { + if (SJA1105_SKB_CB(skb)->ts_id != ts_id) + continue; + + __skb_unlink(skb, &ptp_data->skb_txtstamp_queue); + skb_match = skb; + + break; + } + + spin_unlock(&ptp_data->skb_txtstamp_queue.lock); + + if (WARN_ON(!skb_match)) + return; + + shwt.hwtstamp = ns_to_ktime(sja1105_ticks_to_ns(tstamp)); + skb_complete_tx_timestamp(skb_match, &shwt); +} +EXPORT_SYMBOL_GPL(sja1110_process_meta_tstamp); + +/* In addition to cloning the skb which is done by the common + * sja1105_port_txtstamp, we need to generate a timestamp ID and save the + * packet to the TX timestamping queue. + */ +void sja1110_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) +{ + struct sk_buff *clone = SJA1105_SKB_CB(skb)->clone; + struct sja1105_private *priv = ds->priv; + struct sja1105_ptp_data *ptp_data = &priv->ptp_data; + struct sja1105_port *sp = &priv->ports[port]; + u8 ts_id; + + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + + spin_lock(&sp->data->meta_lock); + + ts_id = sp->data->ts_id; + /* Deal automatically with 8-bit wraparound */ + sp->data->ts_id++; + + SJA1105_SKB_CB(clone)->ts_id = ts_id; + + spin_unlock(&sp->data->meta_lock); + + skb_queue_tail(&ptp_data->skb_txtstamp_queue, clone); +} + /* Called from dsa_skb_tx_timestamp. This callback is just to clone * the skb and have it available in SJA1105_SKB_CB in the .port_deferred_xmit * callback, where we will timestamp it synchronously. @@ -469,6 +531,9 @@ void sja1105_port_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) return; SJA1105_SKB_CB(skb)->clone = clone; + + if (priv->info->txtstamp) + priv->info->txtstamp(ds, port, skb); } static int sja1105_ptp_reset(struct dsa_switch *ds) @@ -885,7 +950,10 @@ int sja1105_ptp_clock_register(struct dsa_switch *ds) .n_per_out = 1, }; + /* Only used on SJA1105 */ skb_queue_head_init(&ptp_data->skb_rxtstamp_queue); + /* Only used on SJA1110 */ + skb_queue_head_init(&ptp_data->skb_txtstamp_queue); spin_lock_init(&tagger_data->meta_lock); ptp_data->clock = ptp_clock_register(&ptp_data->caps, ds->dev); @@ -910,6 +978,7 @@ void sja1105_ptp_clock_unregister(struct dsa_switch *ds) del_timer_sync(&ptp_data->extts_timer); ptp_cancel_worker_sync(ptp_data->clock); + skb_queue_purge(&ptp_data->skb_txtstamp_queue); skb_queue_purge(&ptp_data->skb_rxtstamp_queue); ptp_clock_unregister(ptp_data->clock); ptp_data->clock = NULL; diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.h b/drivers/net/dsa/sja1105/sja1105_ptp.h index bf0c4f1dfed7..3c874bb4c17b 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.h +++ b/drivers/net/dsa/sja1105/sja1105_ptp.h @@ -75,7 +75,12 @@ struct sja1105_ptp_cmd { struct sja1105_ptp_data { struct timer_list extts_timer; + /* Used only on SJA1105 to reconstruct partial timestamps */ struct sk_buff_head skb_rxtstamp_queue; + /* Used on SJA1110 where meta frames are generated only for + * 2-step TX timestamps + */ + struct sk_buff_head skb_txtstamp_queue; struct ptp_clock_info caps; struct ptp_clock *clock; struct sja1105_ptp_cmd cmd; @@ -124,6 +129,7 @@ int sja1105_ptp_commit(struct dsa_switch *ds, struct sja1105_ptp_cmd *cmd, bool sja1105_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb); bool sja1110_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb); +void sja1110_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb); #else @@ -189,6 +195,7 @@ static inline int sja1105_ptp_commit(struct dsa_switch *ds, #define sja1105_rxtstamp NULL #define sja1110_rxtstamp NULL +#define sja1110_txtstamp NULL #endif /* IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) */ diff --git a/drivers/net/dsa/sja1105/sja1105_spi.c b/drivers/net/dsa/sja1105/sja1105_spi.c index f7dd86271891..32d00212423c 100644 --- a/drivers/net/dsa/sja1105/sja1105_spi.c +++ b/drivers/net/dsa/sja1105/sja1105_spi.c @@ -788,6 +788,7 @@ const struct sja1105_info sja1110a_info = { .fdb_del_cmd = sja1105pqrs_fdb_del, .ptp_cmd_packing = sja1105pqrs_ptp_cmd_packing, .rxtstamp = sja1110_rxtstamp, + .txtstamp = sja1110_txtstamp, .clocking_setup = sja1110_clocking_setup, .port_speed = { [SJA1105_SPEED_AUTO] = 0, @@ -836,6 +837,7 @@ const struct sja1105_info sja1110b_info = { .fdb_del_cmd = sja1105pqrs_fdb_del, .ptp_cmd_packing = sja1105pqrs_ptp_cmd_packing, .rxtstamp = sja1110_rxtstamp, + .txtstamp = sja1110_txtstamp, .clocking_setup = sja1110_clocking_setup, .port_speed = { [SJA1105_SPEED_AUTO] = 0, @@ -884,6 +886,7 @@ const struct sja1105_info sja1110c_info = { .fdb_del_cmd = sja1105pqrs_fdb_del, .ptp_cmd_packing = sja1105pqrs_ptp_cmd_packing, .rxtstamp = sja1110_rxtstamp, + .txtstamp = sja1110_txtstamp, .clocking_setup = sja1110_clocking_setup, .port_speed = { [SJA1105_SPEED_AUTO] = 0, @@ -932,6 +935,7 @@ const struct sja1105_info sja1110d_info = { .fdb_del_cmd = sja1105pqrs_fdb_del, .ptp_cmd_packing = sja1105pqrs_ptp_cmd_packing, .rxtstamp = sja1110_rxtstamp, + .txtstamp = sja1110_txtstamp, .clocking_setup = sja1110_clocking_setup, .port_speed = { [SJA1105_SPEED_AUTO] = 0, diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index b02cf7b515ae..b6089b88314c 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -45,11 +45,14 @@ struct sja1105_tagger_data { */ spinlock_t meta_lock; unsigned long state; + u8 ts_id; }; struct sja1105_skb_cb { struct sk_buff *clone; u64 tstamp; + /* Only valid for packets cloned for 2-step TX timestamping */ + u8 ts_id; }; #define SJA1105_SKB_CB(skb) \ @@ -66,4 +69,24 @@ struct sja1105_port { u16 xmit_tpid; }; +enum sja1110_meta_tstamp { + SJA1110_META_TSTAMP_TX = 0, + SJA1110_META_TSTAMP_RX = 1, +}; + +#if IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) + +void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, u8 ts_id, + enum sja1110_meta_tstamp dir, u64 tstamp); + +#else + +static inline void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, + u8 ts_id, enum sja1110_meta_tstamp dir, + u64 tstamp) +{ +} + +#endif /* IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) */ + #endif /* _NET_DSA_SJA1105_H */ diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 37e1d64e07c6..9c2df9ece01b 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -25,6 +25,9 @@ #define SJA1110_RX_TRAILER_SWITCH_ID(x) (((x) & GENMASK(7, 4)) >> 4) #define SJA1110_RX_TRAILER_SRC_PORT(x) ((x) & GENMASK(3, 0)) +/* Meta frame format (for 2-step TX timestamps) */ +#define SJA1110_RX_HEADER_N_TS(x) (((x) & GENMASK(8, 4)) >> 4) + /* TX header */ #define SJA1110_TX_HEADER_UPDATE_TC BIT(14) #define SJA1110_TX_HEADER_TAKE_TS BIT(13) @@ -43,6 +46,8 @@ #define SJA1110_TX_TRAILER_SWITCHID(x) (((x) << 12) & GENMASK(15, 12)) #define SJA1110_TX_TRAILER_DESTPORTS(x) (((x) << 1) & GENMASK(11, 1)) +#define SJA1110_META_TSTAMP_SIZE 10 + #define SJA1110_HEADER_LEN 4 #define SJA1110_RX_TRAILER_LEN 13 #define SJA1110_TX_TRAILER_LEN 4 @@ -184,6 +189,7 @@ static struct sk_buff *sja1105_xmit(struct sk_buff *skb, static struct sk_buff *sja1110_xmit(struct sk_buff *skb, struct net_device *netdev) { + struct sk_buff *clone = SJA1105_SKB_CB(skb)->clone; struct dsa_port *dp = dsa_slave_to_port(netdev); u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index); u16 queue_mapping = skb_get_queue_mapping(skb); @@ -221,6 +227,12 @@ static struct sk_buff *sja1110_xmit(struct sk_buff *skb, *tx_trailer = cpu_to_be32(SJA1110_TX_TRAILER_PRIO(pcp) | SJA1110_TX_TRAILER_SWITCHID(dp->ds->index) | SJA1110_TX_TRAILER_DESTPORTS(BIT(dp->index))); + if (clone) { + u8 ts_id = SJA1105_SKB_CB(clone)->ts_id; + + *tx_header |= htons(SJA1110_TX_HEADER_TAKE_TS); + *tx_trailer |= cpu_to_be32(SJA1110_TX_TRAILER_TSTAMP_ID(ts_id)); + } return skb; } @@ -423,6 +435,43 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, is_meta); } +static struct sk_buff *sja1110_rcv_meta(struct sk_buff *skb, u16 rx_header) +{ + int switch_id = SJA1110_RX_HEADER_SWITCH_ID(rx_header); + int n_ts = SJA1110_RX_HEADER_N_TS(rx_header); + struct net_device *master = skb->dev; + struct dsa_port *cpu_dp; + u8 *buf = skb->data + 2; + struct dsa_switch *ds; + int i; + + cpu_dp = master->dsa_ptr; + ds = dsa_switch_find(cpu_dp->dst->index, switch_id); + if (!ds) { + net_err_ratelimited("%s: cannot find switch id %d\n", + master->name, switch_id); + return NULL; + } + + for (i = 0; i <= n_ts; i++) { + u8 ts_id, source_port, dir; + u64 tstamp; + + ts_id = buf[0]; + source_port = (buf[1] & GENMASK(7, 4)) >> 4; + dir = (buf[1] & BIT(3)) >> 3; + tstamp = be64_to_cpu(*(__be64 *)(buf + 2)); + + sja1110_process_meta_tstamp(ds, source_port, ts_id, dir, + tstamp); + + buf += SJA1110_META_TSTAMP_SIZE; + } + + /* Discard the meta frame, we've consumed the timestamps it contained */ + return NULL; +} + static struct sk_buff *sja1110_rcv_inband_control_extension(struct sk_buff *skb, int *source_port, int *switch_id) @@ -439,6 +488,9 @@ static struct sk_buff *sja1110_rcv_inband_control_extension(struct sk_buff *skb, */ rx_header = ntohs(*(__be16 *)skb->data); + if (rx_header & SJA1110_RX_HEADER_IS_METADATA) + return sja1110_rcv_meta(skb, rx_header); + /* Timestamp frame, we have a trailer */ if (rx_header & SJA1110_RX_HEADER_HAS_TRAILER) { int start_of_padding = SJA1110_RX_HEADER_TRAILER_POS(rx_header); -- cgit v1.2.3-71-gd317 From 0fb16976765143cf0d7d0dd78b3f406ab135c494 Mon Sep 17 00:00:00 2001 From: Calvin Johnson Date: Fri, 11 Jun 2021 13:53:48 +0300 Subject: net: phy: Introduce fwnode_mdio_find_device() Define fwnode_mdio_find_device() to get a pointer to the mdio_device from fwnode passed to the function. Refactor of_mdio_find_device() to use fwnode_mdio_find_device(). Signed-off-by: Calvin Johnson Signed-off-by: Ioana Ciornei Acked-by: Grant Likely Signed-off-by: David S. Miller --- drivers/net/mdio/of_mdio.c | 11 +---------- drivers/net/phy/phy_device.c | 23 +++++++++++++++++++++++ include/linux/phy.h | 7 +++++++ 3 files changed, 31 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/mdio/of_mdio.c b/drivers/net/mdio/of_mdio.c index 8e97d5b825f5..6ef8b6e40189 100644 --- a/drivers/net/mdio/of_mdio.c +++ b/drivers/net/mdio/of_mdio.c @@ -347,16 +347,7 @@ EXPORT_SYMBOL(of_mdiobus_register); */ struct mdio_device *of_mdio_find_device(struct device_node *np) { - struct device *d; - - if (!np) - return NULL; - - d = bus_find_device_by_of_node(&mdio_bus_type, np); - if (!d) - return NULL; - - return to_mdio_device(d); + return fwnode_mdio_find_device(of_fwnode_handle(np)); } EXPORT_SYMBOL(of_mdio_find_device); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 495d86b4af7c..dca454b5c209 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -2875,6 +2875,29 @@ static bool phy_drv_supports_irq(struct phy_driver *phydrv) return phydrv->config_intr && phydrv->handle_interrupt; } +/** + * fwnode_mdio_find_device - Given a fwnode, find the mdio_device + * @fwnode: pointer to the mdio_device's fwnode + * + * If successful, returns a pointer to the mdio_device with the embedded + * struct device refcount incremented by one, or NULL on failure. + * The caller should call put_device() on the mdio_device after its use. + */ +struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode) +{ + struct device *d; + + if (!fwnode) + return NULL; + + d = bus_find_device_by_fwnode(&mdio_bus_type, fwnode); + if (!d) + return NULL; + + return to_mdio_device(d); +} +EXPORT_SYMBOL(fwnode_mdio_find_device); + /** * phy_probe - probe and init a PHY device * @dev: device to probe and init diff --git a/include/linux/phy.h b/include/linux/phy.h index ed332ac92e25..7aa97f4e5387 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1377,10 +1377,17 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, bool is_c45, struct phy_c45_device_ids *c45_ids); #if IS_ENABLED(CONFIG_PHYLIB) +struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode); struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); void phy_device_free(struct phy_device *phydev); #else +static inline +struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode) +{ + return 0; +} + static inline struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45) { -- cgit v1.2.3-71-gd317 From 425775ed31a6fac8b66ab077f7936fafad895ef6 Mon Sep 17 00:00:00 2001 From: Calvin Johnson Date: Fri, 11 Jun 2021 13:53:49 +0300 Subject: net: phy: Introduce phy related fwnode functions Define fwnode_phy_find_device() to iterate an mdiobus and find the phy device of the provided phy fwnode. Additionally define device_phy_find_device() to find phy device of provided device. Define fwnode_get_phy_node() to get phy_node using named reference. Signed-off-by: Calvin Johnson Signed-off-by: Ioana Ciornei Acked-by: Grant Likely Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 62 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/phy.h | 20 ++++++++++++++ 2 files changed, 82 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index dca454b5c209..786f464216dd 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -9,6 +9,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include #include #include #include @@ -2898,6 +2899,67 @@ struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode) } EXPORT_SYMBOL(fwnode_mdio_find_device); +/** + * fwnode_phy_find_device - For provided phy_fwnode, find phy_device. + * + * @phy_fwnode: Pointer to the phy's fwnode. + * + * If successful, returns a pointer to the phy_device with the embedded + * struct device refcount incremented by one, or NULL on failure. + */ +struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode) +{ + struct mdio_device *mdiodev; + + mdiodev = fwnode_mdio_find_device(phy_fwnode); + if (!mdiodev) + return NULL; + + if (mdiodev->flags & MDIO_DEVICE_FLAG_PHY) + return to_phy_device(&mdiodev->dev); + + put_device(&mdiodev->dev); + + return NULL; +} +EXPORT_SYMBOL(fwnode_phy_find_device); + +/** + * device_phy_find_device - For the given device, get the phy_device + * @dev: Pointer to the given device + * + * Refer return conditions of fwnode_phy_find_device(). + */ +struct phy_device *device_phy_find_device(struct device *dev) +{ + return fwnode_phy_find_device(dev_fwnode(dev)); +} +EXPORT_SYMBOL_GPL(device_phy_find_device); + +/** + * fwnode_get_phy_node - Get the phy_node using the named reference. + * @fwnode: Pointer to fwnode from which phy_node has to be obtained. + * + * Refer return conditions of fwnode_find_reference(). + * For ACPI, only "phy-handle" is supported. Legacy DT properties "phy" + * and "phy-device" are not supported in ACPI. DT supports all the three + * named references to the phy node. + */ +struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode) +{ + struct fwnode_handle *phy_node; + + /* Only phy-handle is used for ACPI */ + phy_node = fwnode_find_reference(fwnode, "phy-handle", 0); + if (is_acpi_node(fwnode) || !IS_ERR(phy_node)) + return phy_node; + phy_node = fwnode_find_reference(fwnode, "phy", 0); + if (IS_ERR(phy_node)) + phy_node = fwnode_find_reference(fwnode, "phy-device", 0); + return phy_node; +} +EXPORT_SYMBOL_GPL(fwnode_get_phy_node); + /** * phy_probe - probe and init a PHY device * @dev: device to probe and init diff --git a/include/linux/phy.h b/include/linux/phy.h index 7aa97f4e5387..f9b5fb099fa6 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1378,6 +1378,9 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, struct phy_c45_device_ids *c45_ids); #if IS_ENABLED(CONFIG_PHYLIB) struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode); +struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode); +struct phy_device *device_phy_find_device(struct device *dev); +struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode); struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); void phy_device_free(struct phy_device *phydev); @@ -1388,6 +1391,23 @@ struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode) return 0; } +static inline +struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode) +{ + return NULL; +} + +static inline struct phy_device *device_phy_find_device(struct device *dev) +{ + return NULL; +} + +static inline +struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode) +{ + return NULL; +} + static inline struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45) { -- cgit v1.2.3-71-gd317 From 114dea60043b8f0c82c67dd281719ef8919c2416 Mon Sep 17 00:00:00 2001 From: Calvin Johnson Date: Fri, 11 Jun 2021 13:53:51 +0300 Subject: net: phy: Introduce fwnode_get_phy_id() Extract phy_id from compatible string. This will be used by fwnode_mdiobus_register_phy() to create phy device using the phy_id. Signed-off-by: Calvin Johnson Signed-off-by: Ioana Ciornei Acked-by: Grant Likely Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 21 +++++++++++++++++++++ include/linux/phy.h | 5 +++++ 2 files changed, 26 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 786f464216dd..f7472a0cf771 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -834,6 +834,27 @@ static int get_phy_c22_id(struct mii_bus *bus, int addr, u32 *phy_id) return 0; } +/* Extract the phy ID from the compatible string of the form + * ethernet-phy-idAAAA.BBBB. + */ +int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id) +{ + unsigned int upper, lower; + const char *cp; + int ret; + + ret = fwnode_property_read_string(fwnode, "compatible", &cp); + if (ret) + return ret; + + if (sscanf(cp, "ethernet-phy-id%4x.%4x", &upper, &lower) != 2) + return -EINVAL; + + *phy_id = ((upper & GENMASK(15, 0)) << 16) | (lower & GENMASK(15, 0)); + return 0; +} +EXPORT_SYMBOL(fwnode_get_phy_id); + /** * get_phy_device - reads the specified PHY device and returns its @phy_device * struct diff --git a/include/linux/phy.h b/include/linux/phy.h index f9b5fb099fa6..b60694734b07 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1377,6 +1377,7 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, bool is_c45, struct phy_c45_device_ids *c45_ids); #if IS_ENABLED(CONFIG_PHYLIB) +int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id); struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode); struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode); struct phy_device *device_phy_find_device(struct device *dev); @@ -1385,6 +1386,10 @@ struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); void phy_device_free(struct phy_device *phydev); #else +static inline int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id) +{ + return 0; +} static inline struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode) { -- cgit v1.2.3-71-gd317 From bc1bee3b87ee48bd97ef7fd306445132ba2041b0 Mon Sep 17 00:00:00 2001 From: Calvin Johnson Date: Fri, 11 Jun 2021 13:53:54 +0300 Subject: net: mdiobus: Introduce fwnode_mdiobus_register_phy() Introduce fwnode_mdiobus_register_phy() to register PHYs on the mdiobus. From the compatible string, identify whether the PHY is c45 and based on this create a PHY device instance which is registered on the mdiobus. Along with fwnode_mdiobus_register_phy() also introduce fwnode_find_mii_timestamper() and fwnode_mdiobus_phy_device_register() since they are needed. While at it, also use the newly introduced fwnode operation in of_mdiobus_phy_device_register(). Signed-off-by: Calvin Johnson Signed-off-by: Ioana Ciornei Acked-by: Grant Likely Signed-off-by: David S. Miller --- MAINTAINERS | 1 + drivers/net/mdio/Kconfig | 7 ++ drivers/net/mdio/Makefile | 3 +- drivers/net/mdio/fwnode_mdio.c | 144 +++++++++++++++++++++++++++++++++++++++++ drivers/net/mdio/of_mdio.c | 44 ++----------- include/linux/fwnode_mdio.h | 35 ++++++++++ 6 files changed, 194 insertions(+), 40 deletions(-) create mode 100644 drivers/net/mdio/fwnode_mdio.c create mode 100644 include/linux/fwnode_mdio.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index e69c1991ec3b..e8f8b6c33a51 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6811,6 +6811,7 @@ F: Documentation/devicetree/bindings/net/mdio* F: Documentation/devicetree/bindings/net/qca,ar803x.yaml F: Documentation/networking/phy.rst F: drivers/net/mdio/ +F: drivers/net/mdio/fwnode_mdio.c F: drivers/net/mdio/of_mdio.c F: drivers/net/pcs/ F: drivers/net/phy/ diff --git a/drivers/net/mdio/Kconfig b/drivers/net/mdio/Kconfig index d06e06f5e31a..422e9e042a3c 100644 --- a/drivers/net/mdio/Kconfig +++ b/drivers/net/mdio/Kconfig @@ -19,6 +19,13 @@ config MDIO_BUS reflects whether the mdio_bus/mdio_device code is built as a loadable module or built-in. +config FWNODE_MDIO + def_tristate PHYLIB + depends on (ACPI || OF) || COMPILE_TEST + select FIXED_PHY + help + FWNODE MDIO bus (Ethernet PHY) accessors + config OF_MDIO def_tristate PHYLIB depends on OF diff --git a/drivers/net/mdio/Makefile b/drivers/net/mdio/Makefile index c3ec0ef989df..2e6813c709eb 100644 --- a/drivers/net/mdio/Makefile +++ b/drivers/net/mdio/Makefile @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for Linux MDIO bus drivers -obj-$(CONFIG_OF_MDIO) += of_mdio.o +obj-$(CONFIG_FWNODE_MDIO) += fwnode_mdio.o +obj-$(CONFIG_OF_MDIO) += of_mdio.o obj-$(CONFIG_MDIO_ASPEED) += mdio-aspeed.o obj-$(CONFIG_MDIO_BCM_IPROC) += mdio-bcm-iproc.o diff --git a/drivers/net/mdio/fwnode_mdio.c b/drivers/net/mdio/fwnode_mdio.c new file mode 100644 index 000000000000..e96766da8de4 --- /dev/null +++ b/drivers/net/mdio/fwnode_mdio.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * fwnode helpers for the MDIO (Ethernet PHY) API + * + * This file provides helper functions for extracting PHY device information + * out of the fwnode and using it to populate an mii_bus. + */ + +#include +#include +#include +#include + +MODULE_AUTHOR("Calvin Johnson "); +MODULE_LICENSE("GPL"); + +static struct mii_timestamper * +fwnode_find_mii_timestamper(struct fwnode_handle *fwnode) +{ + struct of_phandle_args arg; + int err; + + if (is_acpi_node(fwnode)) + return NULL; + + err = of_parse_phandle_with_fixed_args(to_of_node(fwnode), + "timestamper", 1, 0, &arg); + if (err == -ENOENT) + return NULL; + else if (err) + return ERR_PTR(err); + + if (arg.args_count != 1) + return ERR_PTR(-EINVAL); + + return register_mii_timestamper(arg.np, arg.args[0]); +} + +int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, + struct phy_device *phy, + struct fwnode_handle *child, u32 addr) +{ + int rc; + + rc = fwnode_irq_get(child, 0); + if (rc == -EPROBE_DEFER) + return rc; + + if (rc > 0) { + phy->irq = rc; + mdio->irq[addr] = rc; + } else { + phy->irq = mdio->irq[addr]; + } + + if (fwnode_property_read_bool(child, "broken-turn-around")) + mdio->phy_ignore_ta_mask |= 1 << addr; + + fwnode_property_read_u32(child, "reset-assert-us", + &phy->mdio.reset_assert_delay); + fwnode_property_read_u32(child, "reset-deassert-us", + &phy->mdio.reset_deassert_delay); + + /* Associate the fwnode with the device structure so it + * can be looked up later + */ + fwnode_handle_get(child); + phy->mdio.dev.fwnode = child; + + /* All data is now stored in the phy struct; + * register it + */ + rc = phy_device_register(phy); + if (rc) { + fwnode_handle_put(child); + return rc; + } + + dev_dbg(&mdio->dev, "registered phy %p fwnode at address %i\n", + child, addr); + return 0; +} +EXPORT_SYMBOL(fwnode_mdiobus_phy_device_register); + +int fwnode_mdiobus_register_phy(struct mii_bus *bus, + struct fwnode_handle *child, u32 addr) +{ + struct mii_timestamper *mii_ts = NULL; + struct phy_device *phy; + bool is_c45 = false; + u32 phy_id; + int rc; + + mii_ts = fwnode_find_mii_timestamper(child); + if (IS_ERR(mii_ts)) + return PTR_ERR(mii_ts); + + rc = fwnode_property_match_string(child, "compatible", + "ethernet-phy-ieee802.3-c45"); + if (rc >= 0) + is_c45 = true; + + if (is_c45 || fwnode_get_phy_id(child, &phy_id)) + phy = get_phy_device(bus, addr, is_c45); + else + phy = phy_device_create(bus, addr, phy_id, 0, NULL); + if (IS_ERR(phy)) { + unregister_mii_timestamper(mii_ts); + return PTR_ERR(phy); + } + + if (is_acpi_node(child)) { + phy->irq = bus->irq[addr]; + + /* Associate the fwnode with the device structure so it + * can be looked up later. + */ + phy->mdio.dev.fwnode = child; + + /* All data is now stored in the phy struct, so register it */ + rc = phy_device_register(phy); + if (rc) { + phy_device_free(phy); + fwnode_handle_put(phy->mdio.dev.fwnode); + return rc; + } + } else if (is_of_node(child)) { + rc = fwnode_mdiobus_phy_device_register(bus, phy, child, addr); + if (rc) { + unregister_mii_timestamper(mii_ts); + phy_device_free(phy); + return rc; + } + } + + /* phy->mii_ts may already be defined by the PHY driver. A + * mii_timestamper probed via the device tree will still have + * precedence. + */ + if (mii_ts) + phy->mii_ts = mii_ts; + return 0; +} +EXPORT_SYMBOL(fwnode_mdiobus_register_phy); diff --git a/drivers/net/mdio/of_mdio.c b/drivers/net/mdio/of_mdio.c index d73c0570f19c..17327bbc1de4 100644 --- a/drivers/net/mdio/of_mdio.c +++ b/drivers/net/mdio/of_mdio.c @@ -10,6 +10,7 @@ #include #include +#include #include #include #include @@ -51,46 +52,11 @@ static struct mii_timestamper *of_find_mii_timestamper(struct device_node *node) } int of_mdiobus_phy_device_register(struct mii_bus *mdio, struct phy_device *phy, - struct device_node *child, u32 addr) + struct device_node *child, u32 addr) { - int rc; - - rc = of_irq_get(child, 0); - if (rc == -EPROBE_DEFER) - return rc; - - if (rc > 0) { - phy->irq = rc; - mdio->irq[addr] = rc; - } else { - phy->irq = mdio->irq[addr]; - } - - if (of_property_read_bool(child, "broken-turn-around")) - mdio->phy_ignore_ta_mask |= 1 << addr; - - of_property_read_u32(child, "reset-assert-us", - &phy->mdio.reset_assert_delay); - of_property_read_u32(child, "reset-deassert-us", - &phy->mdio.reset_deassert_delay); - - /* Associate the OF node with the device structure so it - * can be looked up later */ - of_node_get(child); - phy->mdio.dev.of_node = child; - phy->mdio.dev.fwnode = of_fwnode_handle(child); - - /* All data is now stored in the phy struct; - * register it */ - rc = phy_device_register(phy); - if (rc) { - of_node_put(child); - return rc; - } - - dev_dbg(&mdio->dev, "registered phy %pOFn at address %i\n", - child, addr); - return 0; + return fwnode_mdiobus_phy_device_register(mdio, phy, + of_fwnode_handle(child), + addr); } EXPORT_SYMBOL(of_mdiobus_phy_device_register); diff --git a/include/linux/fwnode_mdio.h b/include/linux/fwnode_mdio.h new file mode 100644 index 000000000000..faf603c48c86 --- /dev/null +++ b/include/linux/fwnode_mdio.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * FWNODE helper for the MDIO (Ethernet PHY) API + */ + +#ifndef __LINUX_FWNODE_MDIO_H +#define __LINUX_FWNODE_MDIO_H + +#include + +#if IS_ENABLED(CONFIG_FWNODE_MDIO) +int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, + struct phy_device *phy, + struct fwnode_handle *child, u32 addr); + +int fwnode_mdiobus_register_phy(struct mii_bus *bus, + struct fwnode_handle *child, u32 addr); + +#else /* CONFIG_FWNODE_MDIO */ +int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, + struct phy_device *phy, + struct fwnode_handle *child, u32 addr) +{ + return -EINVAL; +} + +static inline int fwnode_mdiobus_register_phy(struct mii_bus *bus, + struct fwnode_handle *child, + u32 addr) +{ + return -EINVAL; +} +#endif + +#endif /* __LINUX_FWNODE_MDIO_H */ -- cgit v1.2.3-71-gd317 From 7ec16433cf1e97cfc823e50e9ee4e2fd3abfc4ee Mon Sep 17 00:00:00 2001 From: Calvin Johnson Date: Fri, 11 Jun 2021 13:53:56 +0300 Subject: ACPI: utils: Introduce acpi_get_local_address() Introduce a wrapper around the _ADR evaluation. Signed-off-by: Calvin Johnson Reviewed-by: Andy Shevchenko Signed-off-by: Ioana Ciornei Acked-by: Rafael J. Wysocki Acked-by: Grant Likely Signed-off-by: David S. Miller --- drivers/acpi/utils.c | 14 ++++++++++++++ include/linux/acpi.h | 7 +++++++ 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c index 3b54b8fd7396..e7ddd281afff 100644 --- a/drivers/acpi/utils.c +++ b/drivers/acpi/utils.c @@ -277,6 +277,20 @@ acpi_evaluate_integer(acpi_handle handle, EXPORT_SYMBOL(acpi_evaluate_integer); +int acpi_get_local_address(acpi_handle handle, u32 *addr) +{ + unsigned long long adr; + acpi_status status; + + status = acpi_evaluate_integer(handle, METHOD_NAME__ADR, NULL, &adr); + if (ACPI_FAILURE(status)) + return -ENODATA; + + *addr = (u32)adr; + return 0; +} +EXPORT_SYMBOL(acpi_get_local_address); + acpi_status acpi_evaluate_reference(acpi_handle handle, acpi_string pathname, diff --git a/include/linux/acpi.h b/include/linux/acpi.h index c60745f657e9..6ace3a0f1415 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -710,6 +710,8 @@ static inline u64 acpi_arch_get_root_pointer(void) } #endif +int acpi_get_local_address(acpi_handle handle, u32 *addr); + #else /* !CONFIG_ACPI */ #define acpi_disabled 1 @@ -965,6 +967,11 @@ static inline struct acpi_device *acpi_resource_consumer(struct resource *res) return NULL; } +static inline int acpi_get_local_address(acpi_handle handle, u32 *addr) +{ + return -ENODEV; +} + #endif /* !CONFIG_ACPI */ #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC -- cgit v1.2.3-71-gd317 From 803ca24d2f92e2cf393df4705423f7b09a5eabd9 Mon Sep 17 00:00:00 2001 From: Calvin Johnson Date: Fri, 11 Jun 2021 13:53:57 +0300 Subject: net: mdio: Add ACPI support code for mdio Define acpi_mdiobus_register() to Register mii_bus and create PHYs for each ACPI child node. Signed-off-by: Calvin Johnson Signed-off-by: Ioana Ciornei Acked-by: Rafael J. Wysocki Acked-by: Grant Likely Signed-off-by: David S. Miller --- MAINTAINERS | 1 + drivers/net/mdio/Kconfig | 7 ++++++ drivers/net/mdio/Makefile | 1 + drivers/net/mdio/acpi_mdio.c | 58 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/acpi_mdio.h | 26 ++++++++++++++++++++ 5 files changed, 93 insertions(+) create mode 100644 drivers/net/mdio/acpi_mdio.c create mode 100644 include/linux/acpi_mdio.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index e8f8b6c33a51..2172f594be8f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6811,6 +6811,7 @@ F: Documentation/devicetree/bindings/net/mdio* F: Documentation/devicetree/bindings/net/qca,ar803x.yaml F: Documentation/networking/phy.rst F: drivers/net/mdio/ +F: drivers/net/mdio/acpi_mdio.c F: drivers/net/mdio/fwnode_mdio.c F: drivers/net/mdio/of_mdio.c F: drivers/net/pcs/ diff --git a/drivers/net/mdio/Kconfig b/drivers/net/mdio/Kconfig index 422e9e042a3c..99a6c13a11af 100644 --- a/drivers/net/mdio/Kconfig +++ b/drivers/net/mdio/Kconfig @@ -34,6 +34,13 @@ config OF_MDIO help OpenFirmware MDIO bus (Ethernet PHY) accessors +config ACPI_MDIO + def_tristate PHYLIB + depends on ACPI + depends on PHYLIB + help + ACPI MDIO bus (Ethernet PHY) accessors + if MDIO_BUS config MDIO_DEVRES diff --git a/drivers/net/mdio/Makefile b/drivers/net/mdio/Makefile index 2e6813c709eb..15f8dc4042ce 100644 --- a/drivers/net/mdio/Makefile +++ b/drivers/net/mdio/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for Linux MDIO bus drivers +obj-$(CONFIG_ACPI_MDIO) += acpi_mdio.o obj-$(CONFIG_FWNODE_MDIO) += fwnode_mdio.o obj-$(CONFIG_OF_MDIO) += of_mdio.o diff --git a/drivers/net/mdio/acpi_mdio.c b/drivers/net/mdio/acpi_mdio.c new file mode 100644 index 000000000000..d77c987fda9c --- /dev/null +++ b/drivers/net/mdio/acpi_mdio.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * ACPI helpers for the MDIO (Ethernet PHY) API + * + * This file provides helper functions for extracting PHY device information + * out of the ACPI ASL and using it to populate an mii_bus. + */ + +#include +#include +#include +#include +#include +#include +#include + +MODULE_AUTHOR("Calvin Johnson "); +MODULE_LICENSE("GPL"); + +/** + * acpi_mdiobus_register - Register mii_bus and create PHYs from the ACPI ASL. + * @mdio: pointer to mii_bus structure + * @fwnode: pointer to fwnode of MDIO bus. This fwnode is expected to represent + * an ACPI device object corresponding to the MDIO bus and its children are + * expected to correspond to the PHY devices on that bus. + * + * This function registers the mii_bus structure and registers a phy_device + * for each child node of @fwnode. + */ +int acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode) +{ + struct fwnode_handle *child; + u32 addr; + int ret; + + /* Mask out all PHYs from auto probing. */ + mdio->phy_mask = GENMASK(31, 0); + ret = mdiobus_register(mdio); + if (ret) + return ret; + + ACPI_COMPANION_SET(&mdio->dev, to_acpi_device_node(fwnode)); + + /* Loop over the child nodes and register a phy_device for each PHY */ + fwnode_for_each_child_node(fwnode, child) { + ret = acpi_get_local_address(ACPI_HANDLE_FWNODE(child), &addr); + if (ret || addr >= PHY_MAX_ADDR) + continue; + + ret = fwnode_mdiobus_register_phy(mdio, child, addr); + if (ret == -ENODEV) + dev_err(&mdio->dev, + "MDIO device at address %d is missing.\n", + addr); + } + return 0; +} +EXPORT_SYMBOL(acpi_mdiobus_register); diff --git a/include/linux/acpi_mdio.h b/include/linux/acpi_mdio.h new file mode 100644 index 000000000000..0a24ab7cb66f --- /dev/null +++ b/include/linux/acpi_mdio.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * ACPI helper for the MDIO (Ethernet PHY) API + */ + +#ifndef __LINUX_ACPI_MDIO_H +#define __LINUX_ACPI_MDIO_H + +#include + +#if IS_ENABLED(CONFIG_ACPI_MDIO) +int acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode); +#else /* CONFIG_ACPI_MDIO */ +static inline int +acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode) +{ + /* + * Fall back to mdiobus_register() function to register a bus. + * This way, we don't have to keep compat bits around in drivers. + */ + + return mdiobus_register(mdio); +} +#endif + +#endif /* __LINUX_ACPI_MDIO_H */ -- cgit v1.2.3-71-gd317 From 25396f680dd6257096c5dc6ceb90ce57caba8de1 Mon Sep 17 00:00:00 2001 From: Calvin Johnson Date: Fri, 11 Jun 2021 13:53:59 +0300 Subject: net: phylink: introduce phylink_fwnode_phy_connect() Define phylink_fwnode_phy_connect() to connect phy specified by a fwnode to a phylink instance. Signed-off-by: Calvin Johnson Signed-off-by: Ioana Ciornei Acked-by: Grant Likely Reviewed-by: Russell King (Oracle) Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 54 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/phylink.h | 3 +++ 2 files changed, 57 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 96d8e88b4e46..9cc0f69faafe 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -5,6 +5,7 @@ * * Copyright (C) 2015 Russell King */ +#include #include #include #include @@ -1125,6 +1126,59 @@ int phylink_of_phy_connect(struct phylink *pl, struct device_node *dn, } EXPORT_SYMBOL_GPL(phylink_of_phy_connect); +/** + * phylink_fwnode_phy_connect() - connect the PHY specified in the fwnode. + * @pl: a pointer to a &struct phylink returned from phylink_create() + * @fwnode: a pointer to a &struct fwnode_handle. + * @flags: PHY-specific flags to communicate to the PHY device driver + * + * Connect the phy specified @fwnode to the phylink instance specified + * by @pl. + * + * Returns 0 on success or a negative errno. + */ +int phylink_fwnode_phy_connect(struct phylink *pl, + struct fwnode_handle *fwnode, + u32 flags) +{ + struct fwnode_handle *phy_fwnode; + struct phy_device *phy_dev; + int ret; + + /* Fixed links and 802.3z are handled without needing a PHY */ + if (pl->cfg_link_an_mode == MLO_AN_FIXED || + (pl->cfg_link_an_mode == MLO_AN_INBAND && + phy_interface_mode_is_8023z(pl->link_interface))) + return 0; + + phy_fwnode = fwnode_get_phy_node(fwnode); + if (IS_ERR(phy_fwnode)) { + if (pl->cfg_link_an_mode == MLO_AN_PHY) + return -ENODEV; + return 0; + } + + phy_dev = fwnode_phy_find_device(phy_fwnode); + /* We're done with the phy_node handle */ + fwnode_handle_put(phy_fwnode); + if (!phy_dev) + return -ENODEV; + + ret = phy_attach_direct(pl->netdev, phy_dev, flags, + pl->link_interface); + if (ret) { + phy_device_free(phy_dev); + return ret; + } + + ret = phylink_bringup_phy(pl, phy_dev, pl->link_config.interface); + if (ret) + phy_detach(phy_dev); + + return ret; +} +EXPORT_SYMBOL_GPL(phylink_fwnode_phy_connect); + /** * phylink_disconnect_phy() - disconnect any PHY attached to the phylink * instance. diff --git a/include/linux/phylink.h b/include/linux/phylink.h index fd2acfd9b597..afb3ded0b691 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -441,6 +441,9 @@ void phylink_destroy(struct phylink *); int phylink_connect_phy(struct phylink *, struct phy_device *); int phylink_of_phy_connect(struct phylink *, struct device_node *, u32 flags); +int phylink_fwnode_phy_connect(struct phylink *pl, + struct fwnode_handle *fwnode, + u32 flags); void phylink_disconnect_phy(struct phylink *); void phylink_mac_change(struct phylink *, bool up); -- cgit v1.2.3-71-gd317 From 44931195a5412a97c46d299227fbabad4e09010d Mon Sep 17 00:00:00 2001 From: Arseny Krasnov Date: Fri, 11 Jun 2021 14:12:38 +0300 Subject: virtio/vsock: dequeue callback for SOCK_SEQPACKET Callback fetches RW packets from rx queue of socket until whole record is copied(if user's buffer is full, user is not woken up). This is done to not stall sender, because if we wake up user and it leaves syscall, nobody will send credit update for rest of record, and sender will wait for next enter of read syscall at receiver's side. So if user buffer is full, we just send credit update and drop data. Signed-off-by: Arseny Krasnov Signed-off-by: David S. Miller --- include/linux/virtio_vsock.h | 5 ++ net/vmw_vsock/virtio_transport_common.c | 84 +++++++++++++++++++++++++++++++++ 2 files changed, 89 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index dc636b727179..1d9a302cb91d 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -36,6 +36,7 @@ struct virtio_vsock_sock { u32 rx_bytes; u32 buf_alloc; struct list_head rx_queue; + u32 msg_count; }; struct virtio_vsock_pkt { @@ -80,6 +81,10 @@ virtio_transport_dgram_dequeue(struct vsock_sock *vsk, struct msghdr *msg, size_t len, int flags); +ssize_t +virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + int flags); s64 virtio_transport_stream_has_data(struct vsock_sock *vsk); s64 virtio_transport_stream_has_space(struct vsock_sock *vsk); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index ad0d34d41444..1e1df19ec164 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -393,6 +393,78 @@ out: return err; } +static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + int flags) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + struct virtio_vsock_pkt *pkt; + int dequeued_len = 0; + size_t user_buf_len = msg_data_left(msg); + bool copy_failed = false; + bool msg_ready = false; + + spin_lock_bh(&vvs->rx_lock); + + if (vvs->msg_count == 0) { + spin_unlock_bh(&vvs->rx_lock); + return 0; + } + + while (!msg_ready) { + pkt = list_first_entry(&vvs->rx_queue, struct virtio_vsock_pkt, list); + + if (!copy_failed) { + size_t pkt_len; + size_t bytes_to_copy; + + pkt_len = (size_t)le32_to_cpu(pkt->hdr.len); + bytes_to_copy = min(user_buf_len, pkt_len); + + if (bytes_to_copy) { + int err; + + /* sk_lock is held by caller so no one else can dequeue. + * Unlock rx_lock since memcpy_to_msg() may sleep. + */ + spin_unlock_bh(&vvs->rx_lock); + + err = memcpy_to_msg(msg, pkt->buf, bytes_to_copy); + if (err) { + /* Copy of message failed, set flag to skip + * copy path for rest of fragments. Rest of + * fragments will be freed without copy. + */ + copy_failed = true; + dequeued_len = err; + } else { + user_buf_len -= bytes_to_copy; + } + + spin_lock_bh(&vvs->rx_lock); + } + + if (dequeued_len >= 0) + dequeued_len += pkt_len; + } + + if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR) { + msg_ready = true; + vvs->msg_count--; + } + + virtio_transport_dec_rx_pkt(vvs, pkt); + list_del(&pkt->list); + virtio_transport_free_pkt(pkt); + } + + spin_unlock_bh(&vvs->rx_lock); + + virtio_transport_send_credit_update(vsk); + + return dequeued_len; +} + ssize_t virtio_transport_stream_dequeue(struct vsock_sock *vsk, struct msghdr *msg, @@ -405,6 +477,18 @@ virtio_transport_stream_dequeue(struct vsock_sock *vsk, } EXPORT_SYMBOL_GPL(virtio_transport_stream_dequeue); +ssize_t +virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + int flags) +{ + if (flags & MSG_PEEK) + return -EOPNOTSUPP; + + return virtio_transport_seqpacket_do_dequeue(vsk, msg, flags); +} +EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_dequeue); + int virtio_transport_dgram_dequeue(struct vsock_sock *vsk, struct msghdr *msg, -- cgit v1.2.3-71-gd317 From 9ac841f5e9f261245d9d2841ad123566bd160a6e Mon Sep 17 00:00:00 2001 From: Arseny Krasnov Date: Fri, 11 Jun 2021 14:13:06 +0300 Subject: virtio/vsock: rest of SOCK_SEQPACKET support Small updates to make SOCK_SEQPACKET work: 1) Send SHUTDOWN on socket close for SEQPACKET type. 2) Set SEQPACKET packet type during send. 3) Set 'VIRTIO_VSOCK_SEQ_EOR' bit in flags for last packet of message. 4) Implement data check function for SEQPACKET. 5) Check for max datagram size. Signed-off-by: Arseny Krasnov Signed-off-by: David S. Miller --- include/linux/virtio_vsock.h | 5 ++++ net/vmw_vsock/virtio_transport_common.c | 41 +++++++++++++++++++++++++++++++-- 2 files changed, 44 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 1d9a302cb91d..35d7eedb5e8e 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -81,12 +81,17 @@ virtio_transport_dgram_dequeue(struct vsock_sock *vsk, struct msghdr *msg, size_t len, int flags); +int +virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len); ssize_t virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk, struct msghdr *msg, int flags); s64 virtio_transport_stream_has_data(struct vsock_sock *vsk); s64 virtio_transport_stream_has_space(struct vsock_sock *vsk); +u32 virtio_transport_seqpacket_has_data(struct vsock_sock *vsk); int virtio_transport_do_socket_init(struct vsock_sock *vsk, struct vsock_sock *psk); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 3a658ff8fccb..23704a6bc437 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -74,6 +74,10 @@ virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info, err = memcpy_from_msg(pkt->buf, info->msg, len); if (err) goto out; + + if (msg_data_left(info->msg) == 0 && + info->type == VIRTIO_VSOCK_TYPE_SEQPACKET) + pkt->hdr.flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR); } trace_virtio_transport_alloc_pkt(src_cid, src_port, @@ -187,7 +191,7 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, struct virtio_vsock_pkt *pkt; u32 pkt_len = info->pkt_len; - info->type = VIRTIO_VSOCK_TYPE_STREAM; + info->type = virtio_transport_get_type(sk_vsock(vsk)); t_ops = virtio_transport_get_ops(vsk); if (unlikely(!t_ops)) @@ -497,6 +501,26 @@ virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk, } EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_dequeue); +int +virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + spin_lock_bh(&vvs->tx_lock); + + if (len > vvs->peer_buf_alloc) { + spin_unlock_bh(&vvs->tx_lock); + return -EMSGSIZE; + } + + spin_unlock_bh(&vvs->tx_lock); + + return virtio_transport_stream_enqueue(vsk, msg, len); +} +EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_enqueue); + int virtio_transport_dgram_dequeue(struct vsock_sock *vsk, struct msghdr *msg, @@ -519,6 +543,19 @@ s64 virtio_transport_stream_has_data(struct vsock_sock *vsk) } EXPORT_SYMBOL_GPL(virtio_transport_stream_has_data); +u32 virtio_transport_seqpacket_has_data(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + u32 msg_count; + + spin_lock_bh(&vvs->rx_lock); + msg_count = vvs->msg_count; + spin_unlock_bh(&vvs->rx_lock); + + return msg_count; +} +EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_has_data); + static s64 virtio_transport_has_space(struct vsock_sock *vsk) { struct virtio_vsock_sock *vvs = vsk->trans; @@ -931,7 +968,7 @@ void virtio_transport_release(struct vsock_sock *vsk) struct sock *sk = &vsk->sk; bool remove_sock = true; - if (sk->sk_type == SOCK_STREAM) + if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) remove_sock = virtio_transport_close(vsk); if (remove_sock) { -- cgit v1.2.3-71-gd317 From 5673ef86380414be1702ba2f1ef92526a14dd1e0 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 11 Jun 2021 23:05:19 +0300 Subject: net: pcs: xpcs: rename mdio_xpcs_args to dw_xpcs The struct mdio_xpcs_args is reminiscent of when a similarly named struct mdio_xpcs_ops existed. Now that that is removed, we can shorten the name to dw_xpcs (dw for DesignWare). Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c | 2 +- drivers/net/pcs/pcs-xpcs.c | 73 +++++++++++------------ include/linux/pcs/pcs-xpcs.h | 14 ++--- 4 files changed, 45 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 8a83f9e1e95b..5fecc83f175b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -503,7 +503,7 @@ struct mac_device_info { const struct stmmac_hwtimestamp *ptp; const struct stmmac_tc_ops *tc; const struct stmmac_mmc_ops *mmc; - struct mdio_xpcs_args *xpcs; + struct dw_xpcs *xpcs; struct mii_regs mii; /* MII register Addresses */ struct mac_link link; void __iomem *pcsr; /* vpointer to device CSRs */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index bc900e240da2..3b3033b20b1d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -401,7 +401,7 @@ int stmmac_xpcs_setup(struct mii_bus *bus) { int mode, addr; struct net_device *ndev = bus->priv; - struct mdio_xpcs_args *xpcs; + struct dw_xpcs *xpcs; struct stmmac_priv *priv; struct mdio_device *mdiodev; diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 98c4a3973402..a2cbb2d926b7 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -109,7 +109,7 @@ #define DW_VR_MII_EEE_TRN_LPI BIT(0) /* Transparent Mode Enable */ #define phylink_pcs_to_xpcs(pl_pcs) \ - container_of((pl_pcs), struct mdio_xpcs_args, pcs) + container_of((pl_pcs), struct dw_xpcs, pcs) static const int xpcs_usxgmii_features[] = { ETHTOOL_LINK_MODE_Pause_BIT, @@ -236,7 +236,7 @@ static const struct xpcs_compat *xpcs_find_compat(const struct xpcs_id *id, return NULL; } -int xpcs_get_an_mode(struct mdio_xpcs_args *xpcs, phy_interface_t interface) +int xpcs_get_an_mode(struct dw_xpcs *xpcs, phy_interface_t interface) { const struct xpcs_compat *compat; @@ -263,7 +263,7 @@ static bool __xpcs_linkmode_supported(const struct xpcs_compat *compat, #define xpcs_linkmode_supported(compat, mode) \ __xpcs_linkmode_supported(compat, ETHTOOL_LINK_MODE_ ## mode ## _BIT) -static int xpcs_read(struct mdio_xpcs_args *xpcs, int dev, u32 reg) +static int xpcs_read(struct dw_xpcs *xpcs, int dev, u32 reg) { u32 reg_addr = mdiobus_c45_addr(dev, reg); struct mii_bus *bus = xpcs->mdiodev->bus; @@ -272,7 +272,7 @@ static int xpcs_read(struct mdio_xpcs_args *xpcs, int dev, u32 reg) return mdiobus_read(bus, addr, reg_addr); } -static int xpcs_write(struct mdio_xpcs_args *xpcs, int dev, u32 reg, u16 val) +static int xpcs_write(struct dw_xpcs *xpcs, int dev, u32 reg, u16 val) { u32 reg_addr = mdiobus_c45_addr(dev, reg); struct mii_bus *bus = xpcs->mdiodev->bus; @@ -281,28 +281,28 @@ static int xpcs_write(struct mdio_xpcs_args *xpcs, int dev, u32 reg, u16 val) return mdiobus_write(bus, addr, reg_addr, val); } -static int xpcs_read_vendor(struct mdio_xpcs_args *xpcs, int dev, u32 reg) +static int xpcs_read_vendor(struct dw_xpcs *xpcs, int dev, u32 reg) { return xpcs_read(xpcs, dev, DW_VENDOR | reg); } -static int xpcs_write_vendor(struct mdio_xpcs_args *xpcs, int dev, int reg, +static int xpcs_write_vendor(struct dw_xpcs *xpcs, int dev, int reg, u16 val) { return xpcs_write(xpcs, dev, DW_VENDOR | reg, val); } -static int xpcs_read_vpcs(struct mdio_xpcs_args *xpcs, int reg) +static int xpcs_read_vpcs(struct dw_xpcs *xpcs, int reg) { return xpcs_read_vendor(xpcs, MDIO_MMD_PCS, reg); } -static int xpcs_write_vpcs(struct mdio_xpcs_args *xpcs, int reg, u16 val) +static int xpcs_write_vpcs(struct dw_xpcs *xpcs, int reg, u16 val) { return xpcs_write_vendor(xpcs, MDIO_MMD_PCS, reg, val); } -static int xpcs_poll_reset(struct mdio_xpcs_args *xpcs, int dev) +static int xpcs_poll_reset(struct dw_xpcs *xpcs, int dev) { /* Poll until the reset bit clears (50ms per retry == 0.6 sec) */ unsigned int retries = 12; @@ -318,7 +318,7 @@ static int xpcs_poll_reset(struct mdio_xpcs_args *xpcs, int dev) return (ret & MDIO_CTRL1_RESET) ? -ETIMEDOUT : 0; } -static int xpcs_soft_reset(struct mdio_xpcs_args *xpcs, +static int xpcs_soft_reset(struct dw_xpcs *xpcs, const struct xpcs_compat *compat) { int ret, dev; @@ -348,7 +348,7 @@ static int xpcs_soft_reset(struct mdio_xpcs_args *xpcs, dev_warn(&(__xpcs)->mdiodev->dev, ##__args); \ }) -static int xpcs_read_fault_c73(struct mdio_xpcs_args *xpcs, +static int xpcs_read_fault_c73(struct dw_xpcs *xpcs, struct phylink_link_state *state) { int ret; @@ -399,7 +399,7 @@ static int xpcs_read_fault_c73(struct mdio_xpcs_args *xpcs, return 0; } -static int xpcs_read_link_c73(struct mdio_xpcs_args *xpcs, bool an) +static int xpcs_read_link_c73(struct dw_xpcs *xpcs, bool an) { bool link = true; int ret; @@ -439,7 +439,7 @@ static int xpcs_get_max_usxgmii_speed(const unsigned long *supported) return max; } -static void xpcs_config_usxgmii(struct mdio_xpcs_args *xpcs, int speed) +static void xpcs_config_usxgmii(struct dw_xpcs *xpcs, int speed) { int ret, speed_sel; @@ -500,7 +500,7 @@ out: pr_err("%s: XPCS access returned %pe\n", __func__, ERR_PTR(ret)); } -static int _xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs, +static int _xpcs_config_aneg_c73(struct dw_xpcs *xpcs, const struct xpcs_compat *compat) { int ret, adv; @@ -545,7 +545,7 @@ static int _xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs, return xpcs_write(xpcs, MDIO_MMD_AN, DW_SR_AN_ADV1, adv); } -static int xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs, +static int xpcs_config_aneg_c73(struct dw_xpcs *xpcs, const struct xpcs_compat *compat) { int ret; @@ -563,7 +563,7 @@ static int xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs, return xpcs_write(xpcs, MDIO_MMD_AN, MDIO_CTRL1, ret); } -static int xpcs_aneg_done_c73(struct mdio_xpcs_args *xpcs, +static int xpcs_aneg_done_c73(struct dw_xpcs *xpcs, struct phylink_link_state *state, const struct xpcs_compat *compat) { @@ -590,7 +590,7 @@ static int xpcs_aneg_done_c73(struct mdio_xpcs_args *xpcs, return 0; } -static int xpcs_read_lpa_c73(struct mdio_xpcs_args *xpcs, +static int xpcs_read_lpa_c73(struct dw_xpcs *xpcs, struct phylink_link_state *state) { int ret; @@ -639,7 +639,7 @@ static int xpcs_read_lpa_c73(struct mdio_xpcs_args *xpcs, return 0; } -static void xpcs_resolve_lpa_c73(struct mdio_xpcs_args *xpcs, +static void xpcs_resolve_lpa_c73(struct dw_xpcs *xpcs, struct phylink_link_state *state) { int max_speed = xpcs_get_max_usxgmii_speed(state->lp_advertising); @@ -649,7 +649,7 @@ static void xpcs_resolve_lpa_c73(struct mdio_xpcs_args *xpcs, state->duplex = DUPLEX_FULL; } -static int xpcs_get_max_xlgmii_speed(struct mdio_xpcs_args *xpcs, +static int xpcs_get_max_xlgmii_speed(struct dw_xpcs *xpcs, struct phylink_link_state *state) { unsigned long *adv = state->advertising; @@ -703,7 +703,7 @@ static int xpcs_get_max_xlgmii_speed(struct mdio_xpcs_args *xpcs, return speed; } -static void xpcs_resolve_pma(struct mdio_xpcs_args *xpcs, +static void xpcs_resolve_pma(struct dw_xpcs *xpcs, struct phylink_link_state *state) { state->pause = MLO_PAUSE_TX | MLO_PAUSE_RX; @@ -722,7 +722,7 @@ static void xpcs_resolve_pma(struct mdio_xpcs_args *xpcs, } } -void xpcs_validate(struct mdio_xpcs_args *xpcs, unsigned long *supported, +void xpcs_validate(struct dw_xpcs *xpcs, unsigned long *supported, struct phylink_link_state *state) { __ETHTOOL_DECLARE_LINK_MODE_MASK(xpcs_supported); @@ -752,8 +752,7 @@ void xpcs_validate(struct mdio_xpcs_args *xpcs, unsigned long *supported, } EXPORT_SYMBOL_GPL(xpcs_validate); -int xpcs_config_eee(struct mdio_xpcs_args *xpcs, int mult_fact_100ns, - int enable) +int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable) { int ret; @@ -786,7 +785,7 @@ int xpcs_config_eee(struct mdio_xpcs_args *xpcs, int mult_fact_100ns, } EXPORT_SYMBOL_GPL(xpcs_config_eee); -static int xpcs_config_aneg_c37_sgmii(struct mdio_xpcs_args *xpcs) +static int xpcs_config_aneg_c37_sgmii(struct dw_xpcs *xpcs) { int ret; @@ -827,7 +826,7 @@ static int xpcs_config_aneg_c37_sgmii(struct mdio_xpcs_args *xpcs) return xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_DIG_CTRL1, ret); } -static int xpcs_config_2500basex(struct mdio_xpcs_args *xpcs) +static int xpcs_config_2500basex(struct dw_xpcs *xpcs) { int ret; @@ -849,8 +848,8 @@ static int xpcs_config_2500basex(struct mdio_xpcs_args *xpcs) return xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_MMD_CTRL, ret); } -static int xpcs_do_config(struct mdio_xpcs_args *xpcs, - phy_interface_t interface, unsigned int mode) +static int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, + unsigned int mode) { const struct xpcs_compat *compat; int ret; @@ -889,12 +888,12 @@ static int xpcs_config(struct phylink_pcs *pcs, unsigned int mode, const unsigned long *advertising, bool permit_pause_to_mac) { - struct mdio_xpcs_args *xpcs = phylink_pcs_to_xpcs(pcs); + struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs); return xpcs_do_config(xpcs, interface, mode); } -static int xpcs_get_state_c73(struct mdio_xpcs_args *xpcs, +static int xpcs_get_state_c73(struct dw_xpcs *xpcs, struct phylink_link_state *state, const struct xpcs_compat *compat) { @@ -928,7 +927,7 @@ static int xpcs_get_state_c73(struct mdio_xpcs_args *xpcs, return 0; } -static int xpcs_get_state_c37_sgmii(struct mdio_xpcs_args *xpcs, +static int xpcs_get_state_c37_sgmii(struct dw_xpcs *xpcs, struct phylink_link_state *state) { int ret; @@ -972,7 +971,7 @@ static int xpcs_get_state_c37_sgmii(struct mdio_xpcs_args *xpcs, static void xpcs_get_state(struct phylink_pcs *pcs, struct phylink_link_state *state) { - struct mdio_xpcs_args *xpcs = phylink_pcs_to_xpcs(pcs); + struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs); const struct xpcs_compat *compat; int ret; @@ -1004,13 +1003,13 @@ static void xpcs_get_state(struct phylink_pcs *pcs, static void xpcs_link_up(struct phylink_pcs *pcs, unsigned int mode, phy_interface_t interface, int speed, int duplex) { - struct mdio_xpcs_args *xpcs = phylink_pcs_to_xpcs(pcs); + struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs); if (interface == PHY_INTERFACE_MODE_USXGMII) return xpcs_config_usxgmii(xpcs, speed); } -static u32 xpcs_get_id(struct mdio_xpcs_args *xpcs) +static u32 xpcs_get_id(struct dw_xpcs *xpcs) { int ret; u32 id; @@ -1095,10 +1094,10 @@ static const struct phylink_pcs_ops xpcs_phylink_ops = { .pcs_link_up = xpcs_link_up, }; -struct mdio_xpcs_args *xpcs_create(struct mdio_device *mdiodev, - phy_interface_t interface) +struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev, + phy_interface_t interface) { - struct mdio_xpcs_args *xpcs; + struct dw_xpcs *xpcs; u32 xpcs_id; int i, ret; @@ -1144,7 +1143,7 @@ out: } EXPORT_SYMBOL_GPL(xpcs_create); -void xpcs_destroy(struct mdio_xpcs_args *xpcs) +void xpcs_destroy(struct dw_xpcs *xpcs) { kfree(xpcs); } diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 4d815f03b4b2..4f1cdf6f3d4c 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -17,19 +17,19 @@ struct xpcs_id; -struct mdio_xpcs_args { +struct dw_xpcs { struct mdio_device *mdiodev; const struct xpcs_id *id; struct phylink_pcs pcs; }; -int xpcs_get_an_mode(struct mdio_xpcs_args *xpcs, phy_interface_t interface); -void xpcs_validate(struct mdio_xpcs_args *xpcs, unsigned long *supported, +int xpcs_get_an_mode(struct dw_xpcs *xpcs, phy_interface_t interface); +void xpcs_validate(struct dw_xpcs *xpcs, unsigned long *supported, struct phylink_link_state *state); -int xpcs_config_eee(struct mdio_xpcs_args *xpcs, int mult_fact_100ns, +int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable); -struct mdio_xpcs_args *xpcs_create(struct mdio_device *mdiodev, - phy_interface_t interface); -void xpcs_destroy(struct mdio_xpcs_args *xpcs); +struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev, + phy_interface_t interface); +void xpcs_destroy(struct dw_xpcs *xpcs); #endif /* __LINUX_PCS_XPCS_H */ -- cgit v1.2.3-71-gd317 From dd0721ea4c7a6c2ec8b309ff57d74d88f08d4c23 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 11 Jun 2021 23:05:25 +0300 Subject: net: pcs: xpcs: add support for NXP SJA1105 The NXP SJA1105 DSA switch integrates a Synopsys SGMII XPCS on port 4. The generic code works fine, except there is an integration issue which needs to be dealt with: in this switch, the XPCS is integrated with a PMA that has the TX lane polarity inverted by default (PLUS is MINUS, MINUS is PLUS). To obtain normal non-inverted behavior, the TX lane polarity must be inverted in the PCS, via the DIGITAL_CONTROL_2 register. We introduce a pma_config() method in xpcs_compat which is called by the phylink_pcs_config() implementation. Also, the NXP SJA1105 returns all zeroes in the PHY ID registers 2 and 3. We need to hack up an ad-hoc PHY ID (OUI is zero, device ID is 1) in order for the XPCS driver to recognize it. This PHY ID is added to the public include/linux/pcs/pcs-xpcs.h for that reason (for the sja1105 driver to be able to use it in a later patch). Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- MAINTAINERS | 1 + drivers/net/pcs/Makefile | 4 +++- drivers/net/pcs/pcs-xpcs-nxp.c | 16 ++++++++++++++++ drivers/net/pcs/pcs-xpcs.c | 25 +++++++++++++++++++++++-- drivers/net/pcs/pcs-xpcs.h | 10 ++++++++++ include/linux/pcs/pcs-xpcs.h | 2 ++ 6 files changed, 55 insertions(+), 3 deletions(-) create mode 100644 drivers/net/pcs/pcs-xpcs-nxp.c (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index c8214235380e..349a87b42d3c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13203,6 +13203,7 @@ M: Vladimir Oltean L: linux-kernel@vger.kernel.org S: Maintained F: drivers/net/dsa/sja1105 +F: drivers/net/pcs/pcs-xpcs-nxp.c NXP TDA998X DRM DRIVER M: Russell King diff --git a/drivers/net/pcs/Makefile b/drivers/net/pcs/Makefile index c23146755972..0603d469bd57 100644 --- a/drivers/net/pcs/Makefile +++ b/drivers/net/pcs/Makefile @@ -1,5 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for Linux PCS drivers -obj-$(CONFIG_PCS_XPCS) += pcs-xpcs.o +pcs_xpcs-$(CONFIG_PCS_XPCS) := pcs-xpcs.o pcs-xpcs-nxp.o + +obj-$(CONFIG_PCS_XPCS) += pcs_xpcs.o obj-$(CONFIG_PCS_LYNX) += pcs-lynx.o diff --git a/drivers/net/pcs/pcs-xpcs-nxp.c b/drivers/net/pcs/pcs-xpcs-nxp.c new file mode 100644 index 000000000000..51b2fc7d36a9 --- /dev/null +++ b/drivers/net/pcs/pcs-xpcs-nxp.c @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2021 NXP Semiconductors + */ +#include +#include "pcs-xpcs.h" + +/* In NXP SJA1105, the PCS is integrated with a PMA that has the TX lane + * polarity inverted by default (PLUS is MINUS, MINUS is PLUS). To obtain + * normal non-inverted behavior, the TX lane polarity must be inverted in the + * PCS, via the DIGITAL_CONTROL_2 register. + */ +int nxp_sja1105_sgmii_pma_config(struct dw_xpcs *xpcs) +{ + return xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_DIG_CTRL2, + DW_VR_MII_DIG_CTRL2_TX_POL_INV); +} diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index ecf5011977d3..3b1baacfaf8f 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -117,6 +117,7 @@ struct xpcs_compat { const phy_interface_t *interface; int num_interfaces; int an_mode; + int (*pma_config)(struct dw_xpcs *xpcs); }; struct xpcs_id { @@ -168,7 +169,7 @@ static bool __xpcs_linkmode_supported(const struct xpcs_compat *compat, #define xpcs_linkmode_supported(compat, mode) \ __xpcs_linkmode_supported(compat, ETHTOOL_LINK_MODE_ ## mode ## _BIT) -static int xpcs_read(struct dw_xpcs *xpcs, int dev, u32 reg) +int xpcs_read(struct dw_xpcs *xpcs, int dev, u32 reg) { u32 reg_addr = mdiobus_c45_addr(dev, reg); struct mii_bus *bus = xpcs->mdiodev->bus; @@ -177,7 +178,7 @@ static int xpcs_read(struct dw_xpcs *xpcs, int dev, u32 reg) return mdiobus_read(bus, addr, reg_addr); } -static int xpcs_write(struct dw_xpcs *xpcs, int dev, u32 reg, u16 val) +int xpcs_write(struct dw_xpcs *xpcs, int dev, u32 reg, u16 val) { u32 reg_addr = mdiobus_c45_addr(dev, reg); struct mii_bus *bus = xpcs->mdiodev->bus; @@ -788,6 +789,12 @@ static int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, return -1; } + if (compat->pma_config) { + ret = compat->pma_config(xpcs); + if (ret) + return ret; + } + return 0; } @@ -1022,11 +1029,25 @@ static const struct xpcs_compat synopsys_xpcs_compat[DW_XPCS_INTERFACE_MAX] = { }, }; +static const struct xpcs_compat nxp_sja1105_xpcs_compat[DW_XPCS_INTERFACE_MAX] = { + [DW_XPCS_SGMII] = { + .supported = xpcs_sgmii_features, + .interface = xpcs_sgmii_interfaces, + .num_interfaces = ARRAY_SIZE(xpcs_sgmii_interfaces), + .an_mode = DW_AN_C37_SGMII, + .pma_config = nxp_sja1105_sgmii_pma_config, + }, +}; + static const struct xpcs_id xpcs_id_list[] = { { .id = SYNOPSYS_XPCS_ID, .mask = SYNOPSYS_XPCS_MASK, .compat = synopsys_xpcs_compat, + }, { + .id = NXP_SJA1105_XPCS_ID, + .mask = SYNOPSYS_XPCS_MASK, + .compat = nxp_sja1105_xpcs_compat, }, }; diff --git a/drivers/net/pcs/pcs-xpcs.h b/drivers/net/pcs/pcs-xpcs.h index 867537a68c63..3daf4276a158 100644 --- a/drivers/net/pcs/pcs-xpcs.h +++ b/drivers/net/pcs/pcs-xpcs.h @@ -60,10 +60,15 @@ /* EEE Mode Control Register */ #define DW_VR_MII_EEE_MCTRL0 0x8006 #define DW_VR_MII_EEE_MCTRL1 0x800b +#define DW_VR_MII_DIG_CTRL2 0x80e1 /* VR_MII_DIG_CTRL1 */ #define DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW BIT(9) +/* VR_MII_DIG_CTRL2 */ +#define DW_VR_MII_DIG_CTRL2_TX_POL_INV BIT(4) +#define DW_VR_MII_DIG_CTRL2_RX_POL_INV BIT(0) + /* VR_MII_AN_CTRL */ #define DW_VR_MII_AN_CTRL_TX_CONFIG_SHIFT 3 #define DW_VR_MII_TX_CONFIG_MASK BIT(3) @@ -101,3 +106,8 @@ /* VR MII EEE Control 1 defines */ #define DW_VR_MII_EEE_TRN_LPI BIT(0) /* Transparent Mode Enable */ + +int xpcs_read(struct dw_xpcs *xpcs, int dev, u32 reg); +int xpcs_write(struct dw_xpcs *xpcs, int dev, u32 reg, u16 val); + +int nxp_sja1105_sgmii_pma_config(struct dw_xpcs *xpcs); diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 4f1cdf6f3d4c..c594f7cdc304 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -10,6 +10,8 @@ #include #include +#define NXP_SJA1105_XPCS_ID 0x00000010 + /* AN mode */ #define DW_AN_C73 1 #define DW_AN_C37_SGMII 2 -- cgit v1.2.3-71-gd317 From f7380bba42fd0654bf8195fb741d5f92b0f46df9 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 11 Jun 2021 23:05:26 +0300 Subject: net: pcs: xpcs: add support for NXP SJA1110 The NXP SJA1110 switch integrates its own, non-Synopsys PMA, but it manages it through the register space of the XPCS itself, in a small register window inside MDIO_MMD_VEND2 from address 0x8030 to 0x806e. This coincides with where the registers for the default Synopsys PMA are, but the register definitions are of course not the same. This situation is an odd hardware quirk, but the simplest way to manage it is to drive the SJA1110's PMA from within the XPCS driver. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/pcs/pcs-xpcs-nxp.c | 169 +++++++++++++++++++++++++++++++++++++++++ drivers/net/pcs/pcs-xpcs.c | 21 +++++ drivers/net/pcs/pcs-xpcs.h | 2 + include/linux/pcs/pcs-xpcs.h | 1 + 4 files changed, 193 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/pcs/pcs-xpcs-nxp.c b/drivers/net/pcs/pcs-xpcs-nxp.c index 51b2fc7d36a9..de99c37cf2ae 100644 --- a/drivers/net/pcs/pcs-xpcs-nxp.c +++ b/drivers/net/pcs/pcs-xpcs-nxp.c @@ -4,6 +4,66 @@ #include #include "pcs-xpcs.h" +/* LANE_DRIVER1_0 register */ +#define SJA1110_LANE_DRIVER1_0 0x8038 +#define SJA1110_TXDRV(x) (((x) << 12) & GENMASK(14, 12)) + +/* LANE_DRIVER2_0 register */ +#define SJA1110_LANE_DRIVER2_0 0x803a +#define SJA1110_TXDRVTRIM_LSB(x) ((x) & GENMASK_ULL(15, 0)) + +/* LANE_DRIVER2_1 register */ +#define SJA1110_LANE_DRIVER2_1 0x803b +#define SJA1110_LANE_DRIVER2_1_RSV BIT(9) +#define SJA1110_TXDRVTRIM_MSB(x) (((x) & GENMASK_ULL(23, 16)) >> 16) + +/* LANE_TRIM register */ +#define SJA1110_LANE_TRIM 0x8040 +#define SJA1110_TXTEN BIT(11) +#define SJA1110_TXRTRIM(x) (((x) << 8) & GENMASK(10, 8)) +#define SJA1110_TXPLL_BWSEL BIT(7) +#define SJA1110_RXTEN BIT(6) +#define SJA1110_RXRTRIM(x) (((x) << 3) & GENMASK(5, 3)) +#define SJA1110_CDR_GAIN BIT(2) +#define SJA1110_ACCOUPLE_RXVCM_EN BIT(0) + +/* LANE_DATAPATH_1 register */ +#define SJA1110_LANE_DATAPATH_1 0x8037 + +/* POWERDOWN_ENABLE register */ +#define SJA1110_POWERDOWN_ENABLE 0x8041 +#define SJA1110_TXPLL_PD BIT(12) +#define SJA1110_TXPD BIT(11) +#define SJA1110_RXPKDETEN BIT(10) +#define SJA1110_RXCH_PD BIT(9) +#define SJA1110_RXBIAS_PD BIT(8) +#define SJA1110_RESET_SER_EN BIT(7) +#define SJA1110_RESET_SER BIT(6) +#define SJA1110_RESET_DES BIT(5) +#define SJA1110_RCVEN BIT(4) + +/* RXPLL_CTRL0 register */ +#define SJA1110_RXPLL_CTRL0 0x8065 +#define SJA1110_RXPLL_FBDIV(x) (((x) << 2) & GENMASK(9, 2)) + +/* RXPLL_CTRL1 register */ +#define SJA1110_RXPLL_CTRL1 0x8066 +#define SJA1110_RXPLL_REFDIV(x) ((x) & GENMASK(4, 0)) + +/* TXPLL_CTRL0 register */ +#define SJA1110_TXPLL_CTRL0 0x806d +#define SJA1110_TXPLL_FBDIV(x) ((x) & GENMASK(11, 0)) + +/* TXPLL_CTRL1 register */ +#define SJA1110_TXPLL_CTRL1 0x806e +#define SJA1110_TXPLL_REFDIV(x) ((x) & GENMASK(5, 0)) + +/* RX_DATA_DETECT register */ +#define SJA1110_RX_DATA_DETECT 0x8045 + +/* RX_CDR_CTLE register */ +#define SJA1110_RX_CDR_CTLE 0x8042 + /* In NXP SJA1105, the PCS is integrated with a PMA that has the TX lane * polarity inverted by default (PLUS is MINUS, MINUS is PLUS). To obtain * normal non-inverted behavior, the TX lane polarity must be inverted in the @@ -14,3 +74,112 @@ int nxp_sja1105_sgmii_pma_config(struct dw_xpcs *xpcs) return xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_DIG_CTRL2, DW_VR_MII_DIG_CTRL2_TX_POL_INV); } + +static int nxp_sja1110_pma_config(struct dw_xpcs *xpcs, + u16 txpll_fbdiv, u16 txpll_refdiv, + u16 rxpll_fbdiv, u16 rxpll_refdiv, + u16 rx_cdr_ctle) +{ + u16 val; + int ret; + + /* Program TX PLL feedback divider and reference divider settings for + * correct oscillation frequency. + */ + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_TXPLL_CTRL0, + SJA1110_TXPLL_FBDIV(txpll_fbdiv)); + if (ret < 0) + return ret; + + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_TXPLL_CTRL1, + SJA1110_TXPLL_REFDIV(txpll_refdiv)); + if (ret < 0) + return ret; + + /* Program transmitter amplitude and disable amplitude trimming */ + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_LANE_DRIVER1_0, + SJA1110_TXDRV(0x5)); + if (ret < 0) + return ret; + + val = SJA1110_TXDRVTRIM_LSB(0xffffffull); + + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_LANE_DRIVER2_0, val); + if (ret < 0) + return ret; + + val = SJA1110_TXDRVTRIM_MSB(0xffffffull) | SJA1110_LANE_DRIVER2_1_RSV; + + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_LANE_DRIVER2_1, val); + if (ret < 0) + return ret; + + /* Enable input and output resistor terminations for low BER. */ + val = SJA1110_ACCOUPLE_RXVCM_EN | SJA1110_CDR_GAIN | + SJA1110_RXRTRIM(4) | SJA1110_RXTEN | SJA1110_TXPLL_BWSEL | + SJA1110_TXRTRIM(3) | SJA1110_TXTEN; + + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_LANE_TRIM, val); + if (ret < 0) + return ret; + + /* Select PCS as transmitter data source. */ + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_LANE_DATAPATH_1, 0); + if (ret < 0) + return ret; + + /* Program RX PLL feedback divider and reference divider for correct + * oscillation frequency. + */ + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_RXPLL_CTRL0, + SJA1110_RXPLL_FBDIV(rxpll_fbdiv)); + if (ret < 0) + return ret; + + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_RXPLL_CTRL1, + SJA1110_RXPLL_REFDIV(rxpll_refdiv)); + if (ret < 0) + return ret; + + /* Program threshold for receiver signal detector. + * Enable control of RXPLL by receiver signal detector to disable RXPLL + * when an input signal is not present. + */ + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_RX_DATA_DETECT, 0x0005); + if (ret < 0) + return ret; + + /* Enable TX and RX PLLs and circuits. + * Release reset of PMA to enable data flow to/from PCS. + */ + val = xpcs_read(xpcs, MDIO_MMD_VEND2, SJA1110_POWERDOWN_ENABLE); + if (val < 0) + return val; + + val &= ~(SJA1110_TXPLL_PD | SJA1110_TXPD | SJA1110_RXCH_PD | + SJA1110_RXBIAS_PD | SJA1110_RESET_SER_EN | + SJA1110_RESET_SER | SJA1110_RESET_DES); + val |= SJA1110_RXPKDETEN | SJA1110_RCVEN; + + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_POWERDOWN_ENABLE, val); + if (ret < 0) + return ret; + + /* Program continuous-time linear equalizer (CTLE) settings. */ + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_RX_CDR_CTLE, + rx_cdr_ctle); + if (ret < 0) + return ret; + + return 0; +} + +int nxp_sja1110_sgmii_pma_config(struct dw_xpcs *xpcs) +{ + return nxp_sja1110_pma_config(xpcs, 0x19, 0x1, 0x19, 0x1, 0x212a); +} + +int nxp_sja1110_2500basex_pma_config(struct dw_xpcs *xpcs) +{ + return nxp_sja1110_pma_config(xpcs, 0x7d, 0x2, 0x7d, 0x2, 0x732a); +} diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 3b1baacfaf8f..b66e46fc88dc 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -1039,6 +1039,23 @@ static const struct xpcs_compat nxp_sja1105_xpcs_compat[DW_XPCS_INTERFACE_MAX] = }, }; +static const struct xpcs_compat nxp_sja1110_xpcs_compat[DW_XPCS_INTERFACE_MAX] = { + [DW_XPCS_SGMII] = { + .supported = xpcs_sgmii_features, + .interface = xpcs_sgmii_interfaces, + .num_interfaces = ARRAY_SIZE(xpcs_sgmii_interfaces), + .an_mode = DW_AN_C37_SGMII, + .pma_config = nxp_sja1110_sgmii_pma_config, + }, + [DW_XPCS_2500BASEX] = { + .supported = xpcs_2500basex_features, + .interface = xpcs_2500basex_interfaces, + .num_interfaces = ARRAY_SIZE(xpcs_2500basex_interfaces), + .an_mode = DW_2500BASEX, + .pma_config = nxp_sja1110_2500basex_pma_config, + }, +}; + static const struct xpcs_id xpcs_id_list[] = { { .id = SYNOPSYS_XPCS_ID, @@ -1048,6 +1065,10 @@ static const struct xpcs_id xpcs_id_list[] = { .id = NXP_SJA1105_XPCS_ID, .mask = SYNOPSYS_XPCS_MASK, .compat = nxp_sja1105_xpcs_compat, + }, { + .id = NXP_SJA1110_XPCS_ID, + .mask = SYNOPSYS_XPCS_MASK, + .compat = nxp_sja1110_xpcs_compat, }, }; diff --git a/drivers/net/pcs/pcs-xpcs.h b/drivers/net/pcs/pcs-xpcs.h index 3daf4276a158..35651d32a224 100644 --- a/drivers/net/pcs/pcs-xpcs.h +++ b/drivers/net/pcs/pcs-xpcs.h @@ -111,3 +111,5 @@ int xpcs_read(struct dw_xpcs *xpcs, int dev, u32 reg); int xpcs_write(struct dw_xpcs *xpcs, int dev, u32 reg, u16 val); int nxp_sja1105_sgmii_pma_config(struct dw_xpcs *xpcs); +int nxp_sja1110_sgmii_pma_config(struct dw_xpcs *xpcs); +int nxp_sja1110_2500basex_pma_config(struct dw_xpcs *xpcs); diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index c594f7cdc304..dae7dd8ac683 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -11,6 +11,7 @@ #include #define NXP_SJA1105_XPCS_ID 0x00000010 +#define NXP_SJA1110_XPCS_ID 0x00000020 /* AN mode */ #define DW_AN_C73 1 -- cgit v1.2.3-71-gd317 From a853c68e29bb974ca0cc0a8eaf88c333217556aa Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 11 Jun 2021 23:05:27 +0300 Subject: net: pcs: xpcs: export xpcs_do_config and xpcs_link_up The sja1105 hardware has a quirk in that some changes require a switch reset, which loses all configuration. When the reset is initiated, everything needs to be reprogrammed, including the MACs and the PCS. This is currently done in sja1105_static_config_reload() - we manually call sja1105_adjust_port_config(), sja1105_sgmii_pcs_config() and sja1105_sgmii_pcs_force_speed() which are all internal functions. There is a desire for sja1105 to use the common xpcs driver, and that means that the equivalents of those functions, xpcs_do_config() and xpcs_link_up() respectively, will no longer be local functions. Forcing phylink to retrigger a resolve somehow, say by doing dev_close() followed by dev_open() is not really an option, because the CPU port might have a PCS as well, and there is no net device which we can close and reopen for that. Additionally, the dev_close/dev_open sequence might force a renegotiation of the copper-side link for SGMII ports connected to a PHY, and this is undesirable as well, because the switch reset is much quicker than a PHY autoneg, so we would have a lot more downtime. The only solution I see is for the sja1105 driver to keep doing what it's doing, and that means we need to export the equivalents from xpcs for sja1105_sgmii_pcs_config and sja1105_sgmii_pcs_force_speed, and call them directly in sja1105_static_config_reload(). This will be done during the conversion patch. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/pcs/pcs-xpcs.c | 10 ++++++---- include/linux/pcs/pcs-xpcs.h | 4 ++++ 2 files changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index b66e46fc88dc..63fda3fc40aa 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -757,8 +757,8 @@ static int xpcs_config_2500basex(struct dw_xpcs *xpcs) return xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_MMD_CTRL, ret); } -static int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, - unsigned int mode) +int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, + unsigned int mode) { const struct xpcs_compat *compat; int ret; @@ -797,6 +797,7 @@ static int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, return 0; } +EXPORT_SYMBOL_GPL(xpcs_do_config); static int xpcs_config(struct phylink_pcs *pcs, unsigned int mode, phy_interface_t interface, @@ -945,8 +946,8 @@ static void xpcs_link_up_sgmii(struct dw_xpcs *xpcs, unsigned int mode, pr_err("%s: xpcs_write returned %pe\n", __func__, ERR_PTR(ret)); } -static void xpcs_link_up(struct phylink_pcs *pcs, unsigned int mode, - phy_interface_t interface, int speed, int duplex) +void xpcs_link_up(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t interface, int speed, int duplex) { struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs); @@ -955,6 +956,7 @@ static void xpcs_link_up(struct phylink_pcs *pcs, unsigned int mode, if (interface == PHY_INTERFACE_MODE_SGMII) return xpcs_link_up_sgmii(xpcs, mode, speed, duplex); } +EXPORT_SYMBOL_GPL(xpcs_link_up); static u32 xpcs_get_id(struct dw_xpcs *xpcs) { diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index dae7dd8ac683..add077a81b21 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -27,6 +27,10 @@ struct dw_xpcs { }; int xpcs_get_an_mode(struct dw_xpcs *xpcs, phy_interface_t interface); +void xpcs_link_up(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t interface, int speed, int duplex); +int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, + unsigned int mode); void xpcs_validate(struct dw_xpcs *xpcs, unsigned long *supported, struct phylink_link_state *state); int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, -- cgit v1.2.3-71-gd317 From a56c286865692ac12291afe4c66198915c6b08f9 Mon Sep 17 00:00:00 2001 From: Steen Hegelund Date: Fri, 11 Jun 2021 14:54:51 +0200 Subject: net: phy: Add 25G BASE-R interface mode Add 25gbase-r phy interface mode Signed-off-by: Steen Hegelund Signed-off-by: Bjarni Jonasson Reviewed-by: Andrew Lunn Reviewed-by: Russell King (Oracle) Signed-off-by: David S. Miller --- Documentation/networking/phy.rst | 6 ++++++ include/linux/phy.h | 4 ++++ 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/Documentation/networking/phy.rst b/Documentation/networking/phy.rst index 3f05d50ecd6e..571ba08386e7 100644 --- a/Documentation/networking/phy.rst +++ b/Documentation/networking/phy.rst @@ -292,6 +292,12 @@ Some of the interface modes are described below: Note: due to legacy usage, some 10GBASE-R usage incorrectly makes use of this definition. +``PHY_INTERFACE_MODE_25GBASER`` + This is the IEEE 802.3 PCS Clause 107 defined 25GBASE-R protocol. + The PCS is identical to 10GBASE-R, i.e. 64B/66B encoded + running 2.5 as fast, giving a fixed bit rate of 25.78125 Gbaud. + Please refer to the IEEE standard for further information. + ``PHY_INTERFACE_MODE_100BASEX`` This defines IEEE 802.3 Clause 24. The link operates at a fixed data rate of 125Mpbs using a 4B/5B encoding scheme, resulting in an underlying diff --git a/include/linux/phy.h b/include/linux/phy.h index b60694734b07..3b80dc3ed68b 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -112,6 +112,7 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_RXAUI: Reduced XAUI * @PHY_INTERFACE_MODE_XAUI: 10 Gigabit Attachment Unit Interface * @PHY_INTERFACE_MODE_10GBASER: 10G BaseR + * @PHY_INTERFACE_MODE_25GBASER: 25G BaseR * @PHY_INTERFACE_MODE_USXGMII: Universal Serial 10GE MII * @PHY_INTERFACE_MODE_10GKR: 10GBASE-KR - with Clause 73 AN * @PHY_INTERFACE_MODE_MAX: Book keeping @@ -147,6 +148,7 @@ typedef enum { PHY_INTERFACE_MODE_XAUI, /* 10GBASE-R, XFI, SFI - single lane 10G Serdes */ PHY_INTERFACE_MODE_10GBASER, + PHY_INTERFACE_MODE_25GBASER, PHY_INTERFACE_MODE_USXGMII, /* 10GBASE-KR - with Clause 73 AN */ PHY_INTERFACE_MODE_10GKR, @@ -223,6 +225,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "xaui"; case PHY_INTERFACE_MODE_10GBASER: return "10gbase-r"; + case PHY_INTERFACE_MODE_25GBASER: + return "25gbase-r"; case PHY_INTERFACE_MODE_USXGMII: return "usxgmii"; case PHY_INTERFACE_MODE_10GKR: -- cgit v1.2.3-71-gd317 From 88b710532e53de2466d1033fb1d5125aabf3215a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sat, 12 Jun 2021 10:20:56 +0200 Subject: wwan: add interface creation support Add support to create (and destroy) interfaces via a new rtnetlink kind "wwan". The responsible driver has to use the new wwan_register_ops() to make this possible. Signed-off-by: Johannes Berg Signed-off-by: Sergey Ryazanov Signed-off-by: Loic Poulain Signed-off-by: David S. Miller --- drivers/net/wwan/wwan_core.c | 245 +++++++++++++++++++++++++++++++++++++++++-- include/linux/wwan.h | 24 +++++ include/uapi/linux/wwan.h | 16 +++ net/core/rtnetlink.c | 1 + 4 files changed, 279 insertions(+), 7 deletions(-) create mode 100644 include/uapi/linux/wwan.h (limited to 'include/linux') diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c index 45a41aee8958..7e728042fc41 100644 --- a/drivers/net/wwan/wwan_core.c +++ b/drivers/net/wwan/wwan_core.c @@ -14,6 +14,8 @@ #include #include #include +#include +#include /* Maximum number of minors in use */ #define WWAN_MAX_MINORS (1 << MINORBITS) @@ -35,10 +37,16 @@ static int wwan_major; * * @id: WWAN device unique ID. * @dev: Underlying device. + * @port_id: Current available port ID to pick. + * @ops: wwan device ops + * @ops_ctxt: context to pass to ops */ struct wwan_device { unsigned int id; struct device dev; + atomic_t port_id; + const struct wwan_ops *ops; + void *ops_ctxt; }; /** @@ -102,7 +110,8 @@ static const struct device_type wwan_dev_type = { static int wwan_dev_parent_match(struct device *dev, const void *parent) { - return (dev->type == &wwan_dev_type && dev->parent == parent); + return (dev->type == &wwan_dev_type && + (dev->parent == parent || dev == parent)); } static struct wwan_device *wwan_dev_get_by_parent(struct device *parent) @@ -116,6 +125,23 @@ static struct wwan_device *wwan_dev_get_by_parent(struct device *parent) return to_wwan_dev(dev); } +static int wwan_dev_name_match(struct device *dev, const void *name) +{ + return dev->type == &wwan_dev_type && + strcmp(dev_name(dev), name) == 0; +} + +static struct wwan_device *wwan_dev_get_by_name(const char *name) +{ + struct device *dev; + + dev = class_find_device(wwan_class, NULL, name, wwan_dev_name_match); + if (!dev) + return ERR_PTR(-ENODEV); + + return to_wwan_dev(dev); +} + /* This function allocates and registers a new WWAN device OR if a WWAN device * already exist for the given parent, it gets a reference and return it. * This function is not exported (for now), it is called indirectly via @@ -180,9 +206,14 @@ static void wwan_remove_dev(struct wwan_device *wwandev) /* WWAN device is created and registered (get+add) along with its first * child port, and subsequent port registrations only grab a reference * (get). The WWAN device must then be unregistered (del+put) along with - * its latest port, and reference simply dropped (put) otherwise. + * its last port, and reference simply dropped (put) otherwise. In the + * same fashion, we must not unregister it when the ops are still there. */ - ret = device_for_each_child(&wwandev->dev, NULL, is_wwan_child); + if (wwandev->ops) + ret = 1; + else + ret = device_for_each_child(&wwandev->dev, NULL, is_wwan_child); + if (!ret) device_unregister(&wwandev->dev); else @@ -750,26 +781,226 @@ static const struct file_operations wwan_port_fops = { .llseek = noop_llseek, }; +/** + * wwan_register_ops - register WWAN device ops + * @parent: Device to use as parent and shared by all WWAN ports and + * created netdevs + * @ops: operations to register + * @ctxt: context to pass to operations + * + * Returns: 0 on success, a negative error code on failure + */ +int wwan_register_ops(struct device *parent, const struct wwan_ops *ops, + void *ctxt) +{ + struct wwan_device *wwandev; + + if (WARN_ON(!parent || !ops)) + return -EINVAL; + + wwandev = wwan_create_dev(parent); + if (!wwandev) + return -ENOMEM; + + if (WARN_ON(wwandev->ops)) { + wwan_remove_dev(wwandev); + return -EBUSY; + } + + if (!try_module_get(ops->owner)) { + wwan_remove_dev(wwandev); + return -ENODEV; + } + + wwandev->ops = ops; + wwandev->ops_ctxt = ctxt; + + return 0; +} +EXPORT_SYMBOL_GPL(wwan_register_ops); + +/** + * wwan_unregister_ops - remove WWAN device ops + * @parent: Device to use as parent and shared by all WWAN ports and + * created netdevs + */ +void wwan_unregister_ops(struct device *parent) +{ + struct wwan_device *wwandev = wwan_dev_get_by_parent(parent); + bool has_ops; + + if (WARN_ON(IS_ERR(wwandev))) + return; + + has_ops = wwandev->ops; + + /* put the reference obtained by wwan_dev_get_by_parent(), + * we should still have one (that the owner is giving back + * now) due to the ops being assigned, check that below + * and return if not. + */ + put_device(&wwandev->dev); + + if (WARN_ON(!has_ops)) + return; + + module_put(wwandev->ops->owner); + + wwandev->ops = NULL; + wwandev->ops_ctxt = NULL; + wwan_remove_dev(wwandev); +} +EXPORT_SYMBOL_GPL(wwan_unregister_ops); + +static int wwan_rtnl_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + if (!data) + return -EINVAL; + + if (!tb[IFLA_PARENT_DEV_NAME]) + return -EINVAL; + + if (!data[IFLA_WWAN_LINK_ID]) + return -EINVAL; + + return 0; +} + +static struct device_type wwan_type = { .name = "wwan" }; + +static struct net_device *wwan_rtnl_alloc(struct nlattr *tb[], + const char *ifname, + unsigned char name_assign_type, + unsigned int num_tx_queues, + unsigned int num_rx_queues) +{ + const char *devname = nla_data(tb[IFLA_PARENT_DEV_NAME]); + struct wwan_device *wwandev = wwan_dev_get_by_name(devname); + struct net_device *dev; + + if (IS_ERR(wwandev)) + return ERR_CAST(wwandev); + + /* only supported if ops were registered (not just ports) */ + if (!wwandev->ops) { + dev = ERR_PTR(-EOPNOTSUPP); + goto out; + } + + dev = alloc_netdev_mqs(wwandev->ops->priv_size, ifname, name_assign_type, + wwandev->ops->setup, num_tx_queues, num_rx_queues); + + if (dev) { + SET_NETDEV_DEV(dev, &wwandev->dev); + SET_NETDEV_DEVTYPE(dev, &wwan_type); + } + +out: + /* release the reference */ + put_device(&wwandev->dev); + return dev; +} + +static int wwan_rtnl_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct wwan_device *wwandev = wwan_dev_get_by_parent(dev->dev.parent); + u32 link_id = nla_get_u32(data[IFLA_WWAN_LINK_ID]); + int ret; + + if (IS_ERR(wwandev)) + return PTR_ERR(wwandev); + + /* shouldn't have a netdev (left) with us as parent so WARN */ + if (WARN_ON(!wwandev->ops)) { + ret = -EOPNOTSUPP; + goto out; + } + + if (wwandev->ops->newlink) + ret = wwandev->ops->newlink(wwandev->ops_ctxt, dev, + link_id, extack); + else + ret = register_netdevice(dev); + +out: + /* release the reference */ + put_device(&wwandev->dev); + return ret; +} + +static void wwan_rtnl_dellink(struct net_device *dev, struct list_head *head) +{ + struct wwan_device *wwandev = wwan_dev_get_by_parent(dev->dev.parent); + + if (IS_ERR(wwandev)) + return; + + /* shouldn't have a netdev (left) with us as parent so WARN */ + if (WARN_ON(!wwandev->ops)) + goto out; + + if (wwandev->ops->dellink) + wwandev->ops->dellink(wwandev->ops_ctxt, dev, head); + else + unregister_netdevice(dev); + +out: + /* release the reference */ + put_device(&wwandev->dev); +} + +static const struct nla_policy wwan_rtnl_policy[IFLA_WWAN_MAX + 1] = { + [IFLA_WWAN_LINK_ID] = { .type = NLA_U32 }, +}; + +static struct rtnl_link_ops wwan_rtnl_link_ops __read_mostly = { + .kind = "wwan", + .maxtype = __IFLA_WWAN_MAX, + .alloc = wwan_rtnl_alloc, + .validate = wwan_rtnl_validate, + .newlink = wwan_rtnl_newlink, + .dellink = wwan_rtnl_dellink, + .policy = wwan_rtnl_policy, +}; + static int __init wwan_init(void) { + int err; + + err = rtnl_link_register(&wwan_rtnl_link_ops); + if (err) + return err; + wwan_class = class_create(THIS_MODULE, "wwan"); - if (IS_ERR(wwan_class)) - return PTR_ERR(wwan_class); + if (IS_ERR(wwan_class)) { + err = PTR_ERR(wwan_class); + goto unregister; + } /* chrdev used for wwan ports */ wwan_major = __register_chrdev(0, 0, WWAN_MAX_MINORS, "wwan_port", &wwan_port_fops); if (wwan_major < 0) { - class_destroy(wwan_class); - return wwan_major; + err = wwan_major; + goto destroy; } return 0; + +destroy: + class_destroy(wwan_class); +unregister: + rtnl_link_unregister(&wwan_rtnl_link_ops); + return err; } static void __exit wwan_exit(void) { __unregister_chrdev(wwan_major, 0, WWAN_MAX_MINORS, "wwan_port"); + rtnl_link_unregister(&wwan_rtnl_link_ops); class_destroy(wwan_class); } diff --git a/include/linux/wwan.h b/include/linux/wwan.h index fa33cc16d931..430a3a0817de 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -7,6 +7,7 @@ #include #include #include +#include /** * enum wwan_port_type - WWAN port types @@ -116,4 +117,27 @@ void wwan_port_txon(struct wwan_port *port); */ void *wwan_port_get_drvdata(struct wwan_port *port); +/** + * struct wwan_ops - WWAN device ops + * @owner: module owner of the WWAN ops + * @priv_size: size of private netdev data area + * @setup: set up a new netdev + * @newlink: register the new netdev + * @dellink: remove the given netdev + */ +struct wwan_ops { + struct module *owner; + unsigned int priv_size; + void (*setup)(struct net_device *dev); + int (*newlink)(void *ctxt, struct net_device *dev, + u32 if_id, struct netlink_ext_ack *extack); + void (*dellink)(void *ctxt, struct net_device *dev, + struct list_head *head); +}; + +int wwan_register_ops(struct device *parent, const struct wwan_ops *ops, + void *ctxt); + +void wwan_unregister_ops(struct device *parent); + #endif /* __WWAN_H */ diff --git a/include/uapi/linux/wwan.h b/include/uapi/linux/wwan.h new file mode 100644 index 000000000000..32a2720b4d11 --- /dev/null +++ b/include/uapi/linux/wwan.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * Copyright (C) 2021 Intel Corporation. + */ +#ifndef _UAPI_WWAN_H_ +#define _UAPI_WWAN_H_ + +enum { + IFLA_WWAN_UNSPEC, + IFLA_WWAN_LINK_ID, /* u32 */ + + __IFLA_WWAN_MAX +}; +#define IFLA_WWAN_MAX (__IFLA_WWAN_MAX - 1) + +#endif /* _UAPI_WWAN_H_ */ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 170e97f3b3c6..5baa86bca876 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1890,6 +1890,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_PERM_ADDRESS] = { .type = NLA_REJECT }, [IFLA_PROTO_DOWN_REASON] = { .type = NLA_NESTED }, [IFLA_NEW_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 1), + [IFLA_PARENT_DEV_NAME] = { .type = NLA_NUL_STRING }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { -- cgit v1.2.3-71-gd317 From be754f6435936e78dafe0ebb9d1e9d52c3bde842 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Sat, 12 Jun 2021 09:37:34 -0500 Subject: net: qualcomm: rmnet: trailer value is a checksum The csum_value field in the rmnet_map_dl_csum_trailer structure is a "real" Internet checksum. It is a 16 bit value, in big endian format, which represents an inverted ones' complement sum over pairs of bytes. Make that clear by changing its type to __sum16. This makes a typecast in rmnet_map_ipv4_dl_csum_trailer() and another in rmnet_map_ipv6_dl_csum_trailer() unnecessary. Signed-off-by: Alex Elder Signed-off-by: David S. Miller --- drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c | 5 ++--- include/linux/if_rmnet.h | 2 +- 2 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c index 033b8ad3d735..610c8b5a8f46 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c @@ -87,7 +87,7 @@ rmnet_map_ipv4_dl_csum_trailer(struct sk_buff *skb, * header checksum value; it is already accounted for in the * checksum value found in the trailer. */ - ip_payload_csum = (__force __sum16)~csum_trailer->csum_value; + ip_payload_csum = ~csum_trailer->csum_value; pseudo_csum = ~csum_tcpudp_magic(ip4h->saddr, ip4h->daddr, ntohs(ip4h->tot_len) - ip4h->ihl * 4, @@ -132,8 +132,7 @@ rmnet_map_ipv6_dl_csum_trailer(struct sk_buff *skb, * checksum computed over the pseudo header. */ ip_header_csum = (__force __be16)ip_fast_csum(ip6h, sizeof(*ip6h) / 4); - ip6_payload_csum = ~csum16_sub((__force __sum16)csum_trailer->csum_value, - ip_header_csum); + ip6_payload_csum = ~csum16_sub(csum_trailer->csum_value, ip_header_csum); length = (ip6h->nexthdr == IPPROTO_UDP) ? ntohs(((struct udphdr *)txporthdr)->len) : diff --git a/include/linux/if_rmnet.h b/include/linux/if_rmnet.h index be17610a981e..10e7521ecb6c 100644 --- a/include/linux/if_rmnet.h +++ b/include/linux/if_rmnet.h @@ -25,7 +25,7 @@ struct rmnet_map_dl_csum_trailer { u8 flags; /* MAP_CSUM_DL_VALID_FLAG */ __be16 csum_start_offset; __be16 csum_length; - __be16 csum_value; + __sum16 csum_value; } __aligned(1); /* rmnet_map_dl_csum_trailer flags field: -- cgit v1.2.3-71-gd317 From ec4b94f9b37bf028cb9b9c39cd1c1cb5dd1ab40c Mon Sep 17 00:00:00 2001 From: Michael Grzeschik Date: Mon, 14 Jun 2021 06:31:18 +0200 Subject: net: phy: micrel: move phy reg offsets to common header Some micrel devices share the same PHY register defines. This patch moves them to one common header so other drivers can reuse them. And reuse generic MII_* defines where possible. Signed-off-by: Michael Grzeschik Signed-off-by: Oleksij Rempel Reviewed-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/microchip/ksz8795.c | 119 ++++++++++++++++---------------- drivers/net/dsa/microchip/ksz8795_reg.h | 62 ----------------- drivers/net/ethernet/micrel/ksz884x.c | 105 ++++------------------------ include/linux/micrel_phy.h | 13 ++++ 4 files changed, 88 insertions(+), 211 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index ad509a57a945..ba065003623f 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -731,88 +732,88 @@ static void ksz8_r_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 *val) u8 p = phy; switch (reg) { - case PHY_REG_CTRL: + case MII_BMCR: ksz_pread8(dev, p, regs[P_NEG_RESTART_CTRL], &restart); ksz_pread8(dev, p, regs[P_SPEED_STATUS], &speed); ksz_pread8(dev, p, regs[P_FORCE_CTRL], &ctrl); if (restart & PORT_PHY_LOOPBACK) - data |= PHY_LOOPBACK; + data |= BMCR_LOOPBACK; if (ctrl & PORT_FORCE_100_MBIT) - data |= PHY_SPEED_100MBIT; + data |= BMCR_SPEED100; if (ksz_is_ksz88x3(dev)) { if ((ctrl & PORT_AUTO_NEG_ENABLE)) - data |= PHY_AUTO_NEG_ENABLE; + data |= BMCR_ANENABLE; } else { if (!(ctrl & PORT_AUTO_NEG_DISABLE)) - data |= PHY_AUTO_NEG_ENABLE; + data |= BMCR_ANENABLE; } if (restart & PORT_POWER_DOWN) - data |= PHY_POWER_DOWN; + data |= BMCR_PDOWN; if (restart & PORT_AUTO_NEG_RESTART) - data |= PHY_AUTO_NEG_RESTART; + data |= BMCR_ANRESTART; if (ctrl & PORT_FORCE_FULL_DUPLEX) - data |= PHY_FULL_DUPLEX; + data |= BMCR_FULLDPLX; if (speed & PORT_HP_MDIX) - data |= PHY_HP_MDIX; + data |= KSZ886X_BMCR_HP_MDIX; if (restart & PORT_FORCE_MDIX) - data |= PHY_FORCE_MDIX; + data |= KSZ886X_BMCR_FORCE_MDI; if (restart & PORT_AUTO_MDIX_DISABLE) - data |= PHY_AUTO_MDIX_DISABLE; + data |= KSZ886X_BMCR_DISABLE_AUTO_MDIX; if (restart & PORT_TX_DISABLE) - data |= PHY_TRANSMIT_DISABLE; + data |= KSZ886X_BMCR_DISABLE_TRANSMIT; if (restart & PORT_LED_OFF) - data |= PHY_LED_DISABLE; + data |= KSZ886X_BMCR_DISABLE_LED; break; - case PHY_REG_STATUS: + case MII_BMSR: ksz_pread8(dev, p, regs[P_LINK_STATUS], &link); - data = PHY_100BTX_FD_CAPABLE | - PHY_100BTX_CAPABLE | - PHY_10BT_FD_CAPABLE | - PHY_10BT_CAPABLE | - PHY_AUTO_NEG_CAPABLE; + data = BMSR_100FULL | + BMSR_100HALF | + BMSR_10FULL | + BMSR_10HALF | + BMSR_ANEGCAPABLE; if (link & PORT_AUTO_NEG_COMPLETE) - data |= PHY_AUTO_NEG_ACKNOWLEDGE; + data |= BMSR_ANEGCOMPLETE; if (link & PORT_STAT_LINK_GOOD) - data |= PHY_LINK_STATUS; + data |= BMSR_LSTATUS; break; - case PHY_REG_ID_1: + case MII_PHYSID1: data = KSZ8795_ID_HI; break; - case PHY_REG_ID_2: + case MII_PHYSID2: if (ksz_is_ksz88x3(dev)) data = KSZ8863_ID_LO; else data = KSZ8795_ID_LO; break; - case PHY_REG_AUTO_NEGOTIATION: + case MII_ADVERTISE: ksz_pread8(dev, p, regs[P_LOCAL_CTRL], &ctrl); - data = PHY_AUTO_NEG_802_3; + data = ADVERTISE_CSMA; if (ctrl & PORT_AUTO_NEG_SYM_PAUSE) - data |= PHY_AUTO_NEG_SYM_PAUSE; + data |= ADVERTISE_PAUSE_CAP; if (ctrl & PORT_AUTO_NEG_100BTX_FD) - data |= PHY_AUTO_NEG_100BTX_FD; + data |= ADVERTISE_100FULL; if (ctrl & PORT_AUTO_NEG_100BTX) - data |= PHY_AUTO_NEG_100BTX; + data |= ADVERTISE_100HALF; if (ctrl & PORT_AUTO_NEG_10BT_FD) - data |= PHY_AUTO_NEG_10BT_FD; + data |= ADVERTISE_10FULL; if (ctrl & PORT_AUTO_NEG_10BT) - data |= PHY_AUTO_NEG_10BT; + data |= ADVERTISE_10HALF; break; - case PHY_REG_REMOTE_CAPABILITY: + case MII_LPA: ksz_pread8(dev, p, regs[P_REMOTE_STATUS], &link); - data = PHY_AUTO_NEG_802_3; + data = LPA_SLCT; if (link & PORT_REMOTE_SYM_PAUSE) - data |= PHY_AUTO_NEG_SYM_PAUSE; + data |= LPA_PAUSE_CAP; if (link & PORT_REMOTE_100BTX_FD) - data |= PHY_AUTO_NEG_100BTX_FD; + data |= LPA_100FULL; if (link & PORT_REMOTE_100BTX) - data |= PHY_AUTO_NEG_100BTX; + data |= LPA_100HALF; if (link & PORT_REMOTE_10BT_FD) - data |= PHY_AUTO_NEG_10BT_FD; + data |= LPA_10FULL; if (link & PORT_REMOTE_10BT) - data |= PHY_AUTO_NEG_10BT; - if (data & ~PHY_AUTO_NEG_802_3) - data |= PHY_REMOTE_ACKNOWLEDGE_NOT; + data |= LPA_10HALF; + if (data & ~LPA_SLCT) + data |= LPA_LPACK; break; default: processed = false; @@ -830,14 +831,14 @@ static void ksz8_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val) u8 p = phy; switch (reg) { - case PHY_REG_CTRL: + case MII_BMCR: /* Do not support PHY reset function. */ - if (val & PHY_RESET) + if (val & BMCR_RESET) break; ksz_pread8(dev, p, regs[P_SPEED_STATUS], &speed); data = speed; - if (val & PHY_HP_MDIX) + if (val & KSZ886X_BMCR_HP_MDIX) data |= PORT_HP_MDIX; else data &= ~PORT_HP_MDIX; @@ -846,12 +847,12 @@ static void ksz8_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val) ksz_pread8(dev, p, regs[P_FORCE_CTRL], &ctrl); data = ctrl; if (ksz_is_ksz88x3(dev)) { - if ((val & PHY_AUTO_NEG_ENABLE)) + if ((val & BMCR_ANENABLE)) data |= PORT_AUTO_NEG_ENABLE; else data &= ~PORT_AUTO_NEG_ENABLE; } else { - if (!(val & PHY_AUTO_NEG_ENABLE)) + if (!(val & BMCR_ANENABLE)) data |= PORT_AUTO_NEG_DISABLE; else data &= ~PORT_AUTO_NEG_DISABLE; @@ -861,11 +862,11 @@ static void ksz8_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val) data |= PORT_AUTO_NEG_DISABLE; } - if (val & PHY_SPEED_100MBIT) + if (val & BMCR_SPEED100) data |= PORT_FORCE_100_MBIT; else data &= ~PORT_FORCE_100_MBIT; - if (val & PHY_FULL_DUPLEX) + if (val & BMCR_FULLDPLX) data |= PORT_FORCE_FULL_DUPLEX; else data &= ~PORT_FORCE_FULL_DUPLEX; @@ -873,38 +874,38 @@ static void ksz8_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val) ksz_pwrite8(dev, p, regs[P_FORCE_CTRL], data); ksz_pread8(dev, p, regs[P_NEG_RESTART_CTRL], &restart); data = restart; - if (val & PHY_LED_DISABLE) + if (val & KSZ886X_BMCR_DISABLE_LED) data |= PORT_LED_OFF; else data &= ~PORT_LED_OFF; - if (val & PHY_TRANSMIT_DISABLE) + if (val & KSZ886X_BMCR_DISABLE_TRANSMIT) data |= PORT_TX_DISABLE; else data &= ~PORT_TX_DISABLE; - if (val & PHY_AUTO_NEG_RESTART) + if (val & BMCR_ANRESTART) data |= PORT_AUTO_NEG_RESTART; else data &= ~(PORT_AUTO_NEG_RESTART); - if (val & PHY_POWER_DOWN) + if (val & BMCR_PDOWN) data |= PORT_POWER_DOWN; else data &= ~PORT_POWER_DOWN; - if (val & PHY_AUTO_MDIX_DISABLE) + if (val & KSZ886X_BMCR_DISABLE_AUTO_MDIX) data |= PORT_AUTO_MDIX_DISABLE; else data &= ~PORT_AUTO_MDIX_DISABLE; - if (val & PHY_FORCE_MDIX) + if (val & KSZ886X_BMCR_FORCE_MDI) data |= PORT_FORCE_MDIX; else data &= ~PORT_FORCE_MDIX; - if (val & PHY_LOOPBACK) + if (val & BMCR_LOOPBACK) data |= PORT_PHY_LOOPBACK; else data &= ~PORT_PHY_LOOPBACK; if (data != restart) ksz_pwrite8(dev, p, regs[P_NEG_RESTART_CTRL], data); break; - case PHY_REG_AUTO_NEGOTIATION: + case MII_ADVERTISE: ksz_pread8(dev, p, regs[P_LOCAL_CTRL], &ctrl); data = ctrl; data &= ~(PORT_AUTO_NEG_SYM_PAUSE | @@ -912,15 +913,15 @@ static void ksz8_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val) PORT_AUTO_NEG_100BTX | PORT_AUTO_NEG_10BT_FD | PORT_AUTO_NEG_10BT); - if (val & PHY_AUTO_NEG_SYM_PAUSE) + if (val & ADVERTISE_PAUSE_CAP) data |= PORT_AUTO_NEG_SYM_PAUSE; - if (val & PHY_AUTO_NEG_100BTX_FD) + if (val & ADVERTISE_100FULL) data |= PORT_AUTO_NEG_100BTX_FD; - if (val & PHY_AUTO_NEG_100BTX) + if (val & ADVERTISE_100HALF) data |= PORT_AUTO_NEG_100BTX; - if (val & PHY_AUTO_NEG_10BT_FD) + if (val & ADVERTISE_10FULL) data |= PORT_AUTO_NEG_10BT_FD; - if (val & PHY_AUTO_NEG_10BT) + if (val & ADVERTISE_10HALF) data |= PORT_AUTO_NEG_10BT; if (data != ctrl) ksz_pwrite8(dev, p, regs[P_LOCAL_CTRL], data); diff --git a/drivers/net/dsa/microchip/ksz8795_reg.h b/drivers/net/dsa/microchip/ksz8795_reg.h index c2e52c40a54c..f925ddee5238 100644 --- a/drivers/net/dsa/microchip/ksz8795_reg.h +++ b/drivers/net/dsa/microchip/ksz8795_reg.h @@ -744,68 +744,6 @@ #define PORT_ACL_FORCE_DLR_MISS BIT(0) -#ifndef PHY_REG_CTRL -#define PHY_REG_CTRL 0 - -#define PHY_RESET BIT(15) -#define PHY_LOOPBACK BIT(14) -#define PHY_SPEED_100MBIT BIT(13) -#define PHY_AUTO_NEG_ENABLE BIT(12) -#define PHY_POWER_DOWN BIT(11) -#define PHY_MII_DISABLE BIT(10) -#define PHY_AUTO_NEG_RESTART BIT(9) -#define PHY_FULL_DUPLEX BIT(8) -#define PHY_COLLISION_TEST_NOT BIT(7) -#define PHY_HP_MDIX BIT(5) -#define PHY_FORCE_MDIX BIT(4) -#define PHY_AUTO_MDIX_DISABLE BIT(3) -#define PHY_REMOTE_FAULT_DISABLE BIT(2) -#define PHY_TRANSMIT_DISABLE BIT(1) -#define PHY_LED_DISABLE BIT(0) - -#define PHY_REG_STATUS 1 - -#define PHY_100BT4_CAPABLE BIT(15) -#define PHY_100BTX_FD_CAPABLE BIT(14) -#define PHY_100BTX_CAPABLE BIT(13) -#define PHY_10BT_FD_CAPABLE BIT(12) -#define PHY_10BT_CAPABLE BIT(11) -#define PHY_MII_SUPPRESS_CAPABLE_NOT BIT(6) -#define PHY_AUTO_NEG_ACKNOWLEDGE BIT(5) -#define PHY_REMOTE_FAULT BIT(4) -#define PHY_AUTO_NEG_CAPABLE BIT(3) -#define PHY_LINK_STATUS BIT(2) -#define PHY_JABBER_DETECT_NOT BIT(1) -#define PHY_EXTENDED_CAPABILITY BIT(0) - -#define PHY_REG_ID_1 2 -#define PHY_REG_ID_2 3 - -#define PHY_REG_AUTO_NEGOTIATION 4 - -#define PHY_AUTO_NEG_NEXT_PAGE_NOT BIT(15) -#define PHY_AUTO_NEG_REMOTE_FAULT_NOT BIT(13) -#define PHY_AUTO_NEG_SYM_PAUSE BIT(10) -#define PHY_AUTO_NEG_100BT4 BIT(9) -#define PHY_AUTO_NEG_100BTX_FD BIT(8) -#define PHY_AUTO_NEG_100BTX BIT(7) -#define PHY_AUTO_NEG_10BT_FD BIT(6) -#define PHY_AUTO_NEG_10BT BIT(5) -#define PHY_AUTO_NEG_SELECTOR 0x001F -#define PHY_AUTO_NEG_802_3 0x0001 - -#define PHY_REG_REMOTE_CAPABILITY 5 - -#define PHY_REMOTE_NEXT_PAGE_NOT BIT(15) -#define PHY_REMOTE_ACKNOWLEDGE_NOT BIT(14) -#define PHY_REMOTE_REMOTE_FAULT_NOT BIT(13) -#define PHY_REMOTE_SYM_PAUSE BIT(10) -#define PHY_REMOTE_100BTX_FD BIT(8) -#define PHY_REMOTE_100BTX BIT(7) -#define PHY_REMOTE_10BT_FD BIT(6) -#define PHY_REMOTE_10BT BIT(5) -#endif - #define KSZ8795_ID_HI 0x0022 #define KSZ8795_ID_LO 0x1550 #define KSZ8863_ID_LO 0x1430 diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c index 3532bfe936f6..7945eb5e2fe8 100644 --- a/drivers/net/ethernet/micrel/ksz884x.c +++ b/drivers/net/ethernet/micrel/ksz884x.c @@ -25,6 +25,7 @@ #include #include #include +#include /* DMA Registers */ @@ -271,84 +272,15 @@ #define KS884X_PHY_CTRL_OFFSET 0x00 -/* Mode Control Register */ -#define PHY_REG_CTRL 0 - -#define PHY_RESET 0x8000 -#define PHY_LOOPBACK 0x4000 -#define PHY_SPEED_100MBIT 0x2000 -#define PHY_AUTO_NEG_ENABLE 0x1000 -#define PHY_POWER_DOWN 0x0800 -#define PHY_MII_DISABLE 0x0400 -#define PHY_AUTO_NEG_RESTART 0x0200 -#define PHY_FULL_DUPLEX 0x0100 -#define PHY_COLLISION_TEST 0x0080 -#define PHY_HP_MDIX 0x0020 -#define PHY_FORCE_MDIX 0x0010 -#define PHY_AUTO_MDIX_DISABLE 0x0008 -#define PHY_REMOTE_FAULT_DISABLE 0x0004 -#define PHY_TRANSMIT_DISABLE 0x0002 -#define PHY_LED_DISABLE 0x0001 - #define KS884X_PHY_STATUS_OFFSET 0x02 -/* Mode Status Register */ -#define PHY_REG_STATUS 1 - -#define PHY_100BT4_CAPABLE 0x8000 -#define PHY_100BTX_FD_CAPABLE 0x4000 -#define PHY_100BTX_CAPABLE 0x2000 -#define PHY_10BT_FD_CAPABLE 0x1000 -#define PHY_10BT_CAPABLE 0x0800 -#define PHY_MII_SUPPRESS_CAPABLE 0x0040 -#define PHY_AUTO_NEG_ACKNOWLEDGE 0x0020 -#define PHY_REMOTE_FAULT 0x0010 -#define PHY_AUTO_NEG_CAPABLE 0x0008 -#define PHY_LINK_STATUS 0x0004 -#define PHY_JABBER_DETECT 0x0002 -#define PHY_EXTENDED_CAPABILITY 0x0001 - #define KS884X_PHY_ID_1_OFFSET 0x04 #define KS884X_PHY_ID_2_OFFSET 0x06 -/* PHY Identifier Registers */ -#define PHY_REG_ID_1 2 -#define PHY_REG_ID_2 3 - #define KS884X_PHY_AUTO_NEG_OFFSET 0x08 -/* Auto-Negotiation Advertisement Register */ -#define PHY_REG_AUTO_NEGOTIATION 4 - -#define PHY_AUTO_NEG_NEXT_PAGE 0x8000 -#define PHY_AUTO_NEG_REMOTE_FAULT 0x2000 -/* Not supported. */ -#define PHY_AUTO_NEG_ASYM_PAUSE 0x0800 -#define PHY_AUTO_NEG_SYM_PAUSE 0x0400 -#define PHY_AUTO_NEG_100BT4 0x0200 -#define PHY_AUTO_NEG_100BTX_FD 0x0100 -#define PHY_AUTO_NEG_100BTX 0x0080 -#define PHY_AUTO_NEG_10BT_FD 0x0040 -#define PHY_AUTO_NEG_10BT 0x0020 -#define PHY_AUTO_NEG_SELECTOR 0x001F -#define PHY_AUTO_NEG_802_3 0x0001 - -#define PHY_AUTO_NEG_PAUSE (PHY_AUTO_NEG_SYM_PAUSE | PHY_AUTO_NEG_ASYM_PAUSE) - #define KS884X_PHY_REMOTE_CAP_OFFSET 0x0A -/* Auto-Negotiation Link Partner Ability Register */ -#define PHY_REG_REMOTE_CAPABILITY 5 - -#define PHY_REMOTE_NEXT_PAGE 0x8000 -#define PHY_REMOTE_ACKNOWLEDGE 0x4000 -#define PHY_REMOTE_REMOTE_FAULT 0x2000 -#define PHY_REMOTE_SYM_PAUSE 0x0400 -#define PHY_REMOTE_100BTX_FD 0x0100 -#define PHY_REMOTE_100BTX 0x0080 -#define PHY_REMOTE_10BT_FD 0x0040 -#define PHY_REMOTE_10BT 0x0020 - /* P1VCT */ #define KS884X_P1VCT_P 0x04F0 #define KS884X_P1PHYCTRL_P 0x04F2 @@ -2886,15 +2818,6 @@ static void sw_block_addr(struct ksz_hw *hw) } } -#define PHY_LINK_SUPPORT \ - (PHY_AUTO_NEG_ASYM_PAUSE | \ - PHY_AUTO_NEG_SYM_PAUSE | \ - PHY_AUTO_NEG_100BT4 | \ - PHY_AUTO_NEG_100BTX_FD | \ - PHY_AUTO_NEG_100BTX | \ - PHY_AUTO_NEG_10BT_FD | \ - PHY_AUTO_NEG_10BT) - static inline void hw_r_phy_ctrl(struct ksz_hw *hw, int phy, u16 *data) { *data = readw(hw->io + phy + KS884X_PHY_CTRL_OFFSET); @@ -3238,16 +3161,18 @@ static void determine_flow_ctrl(struct ksz_hw *hw, struct ksz_port *port, rx = tx = 0; if (port->force_link) rx = tx = 1; - if (remote & PHY_AUTO_NEG_SYM_PAUSE) { - if (local & PHY_AUTO_NEG_SYM_PAUSE) { + if (remote & LPA_PAUSE_CAP) { + if (local & ADVERTISE_PAUSE_CAP) { rx = tx = 1; - } else if ((remote & PHY_AUTO_NEG_ASYM_PAUSE) && - (local & PHY_AUTO_NEG_PAUSE) == - PHY_AUTO_NEG_ASYM_PAUSE) { + } else if ((remote & LPA_PAUSE_ASYM) && + (local & + (ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM)) == + ADVERTISE_PAUSE_ASYM) { tx = 1; } - } else if (remote & PHY_AUTO_NEG_ASYM_PAUSE) { - if ((local & PHY_AUTO_NEG_PAUSE) == PHY_AUTO_NEG_PAUSE) + } else if (remote & LPA_PAUSE_ASYM) { + if ((local & (ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM)) + == (ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM)) rx = 1; } if (!hw->ksz_switch) @@ -3428,16 +3353,16 @@ static void port_force_link_speed(struct ksz_port *port) phy = KS884X_PHY_1_CTRL_OFFSET + p * PHY_CTRL_INTERVAL; hw_r_phy_ctrl(hw, phy, &data); - data &= ~PHY_AUTO_NEG_ENABLE; + data &= ~BMCR_ANENABLE; if (10 == port->speed) - data &= ~PHY_SPEED_100MBIT; + data &= ~BMCR_SPEED100; else if (100 == port->speed) - data |= PHY_SPEED_100MBIT; + data |= BMCR_SPEED100; if (1 == port->duplex) - data &= ~PHY_FULL_DUPLEX; + data &= ~BMCR_FULLDPLX; else if (2 == port->duplex) - data |= PHY_FULL_DUPLEX; + data |= BMCR_FULLDPLX; hw_w_phy_ctrl(hw, phy, data); } } diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 416ee6dd2574..b03e2afcb53f 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -45,4 +45,17 @@ #define MICREL_KSZ9021_RGMII_CLK_CTRL_PAD_SCEW 0x104 #define MICREL_KSZ9021_RGMII_RX_DATA_PAD_SCEW 0x105 +/* Device specific MII_BMCR (Reg 0) bits */ +/* 1 = HP Auto MDI/MDI-X mode, 0 = Microchip Auto MDI/MDI-X mode */ +#define KSZ886X_BMCR_HP_MDIX BIT(5) +/* 1 = Force MDI (transmit on RXP/RXM pins), 0 = Normal operation + * (transmit on TXP/TXM pins) + */ +#define KSZ886X_BMCR_FORCE_MDI BIT(4) +/* 1 = Disable auto MDI-X */ +#define KSZ886X_BMCR_DISABLE_AUTO_MDIX BIT(3) +#define KSZ886X_BMCR_DISABLE_FAR_END_FAULT BIT(2) +#define KSZ886X_BMCR_DISABLE_TRANSMIT BIT(1) +#define KSZ886X_BMCR_DISABLE_LED BIT(0) + #endif /* _MICREL_PHY_H */ -- cgit v1.2.3-71-gd317 From 52939393bd682248a415de4c0439280aafaccd66 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Mon, 14 Jun 2021 06:31:21 +0200 Subject: net: phy/dsa micrel/ksz886x add MDI-X support Add support for MDI-X status and configuration Signed-off-by: Oleksij Rempel Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/microchip/ksz8795.c | 5 +++ drivers/net/phy/micrel.c | 88 +++++++++++++++++++++++++++++++++++++ include/linux/micrel_phy.h | 2 + 3 files changed, 95 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index cfa2a5000cd3..690304c87b02 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -816,6 +816,11 @@ static void ksz8_r_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 *val) if (data & ~LPA_SLCT) data |= LPA_LPACK; break; + case PHY_REG_PHY_CTRL: + ksz_pread8(dev, p, regs[P_LINK_STATUS], &link); + if (link & PORT_MDIX_STATUS) + data |= KSZ886X_CTRL_MDIX_STAT; + break; default: processed = false; break; diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index a2755f2eb7db..9ffca754f6f7 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -1045,6 +1045,92 @@ static int ksz8873mll_config_aneg(struct phy_device *phydev) return 0; } +static int ksz886x_config_mdix(struct phy_device *phydev, u8 ctrl) +{ + u16 val; + + switch (ctrl) { + case ETH_TP_MDI: + val = KSZ886X_BMCR_DISABLE_AUTO_MDIX; + break; + case ETH_TP_MDI_X: + /* Note: The naming of the bit KSZ886X_BMCR_FORCE_MDI is bit + * counter intuitive, the "-X" in "1 = Force MDI" in the data + * sheet seems to be missing: + * 1 = Force MDI (sic!) (transmit on RX+/RX- pins) + * 0 = Normal operation (transmit on TX+/TX- pins) + */ + val = KSZ886X_BMCR_DISABLE_AUTO_MDIX | KSZ886X_BMCR_FORCE_MDI; + break; + case ETH_TP_MDI_AUTO: + val = 0; + break; + default: + return 0; + } + + return phy_modify(phydev, MII_BMCR, + KSZ886X_BMCR_HP_MDIX | KSZ886X_BMCR_FORCE_MDI | + KSZ886X_BMCR_DISABLE_AUTO_MDIX, + KSZ886X_BMCR_HP_MDIX | val); +} + +static int ksz886x_config_aneg(struct phy_device *phydev) +{ + int ret; + + ret = genphy_config_aneg(phydev); + if (ret) + return ret; + + /* The MDI-X configuration is automatically changed by the PHY after + * switching from autoneg off to on. So, take MDI-X configuration under + * own control and set it after autoneg configuration was done. + */ + return ksz886x_config_mdix(phydev, phydev->mdix_ctrl); +} + +static int ksz886x_mdix_update(struct phy_device *phydev) +{ + int ret; + + ret = phy_read(phydev, MII_BMCR); + if (ret < 0) + return ret; + + if (ret & KSZ886X_BMCR_DISABLE_AUTO_MDIX) { + if (ret & KSZ886X_BMCR_FORCE_MDI) + phydev->mdix_ctrl = ETH_TP_MDI_X; + else + phydev->mdix_ctrl = ETH_TP_MDI; + } else { + phydev->mdix_ctrl = ETH_TP_MDI_AUTO; + } + + ret = phy_read(phydev, MII_KSZPHY_CTRL); + if (ret < 0) + return ret; + + /* Same reverse logic as KSZ886X_BMCR_FORCE_MDI */ + if (ret & KSZ886X_CTRL_MDIX_STAT) + phydev->mdix = ETH_TP_MDI_X; + else + phydev->mdix = ETH_TP_MDI; + + return 0; +} + +static int ksz886x_read_status(struct phy_device *phydev) +{ + int ret; + + ret = ksz886x_mdix_update(phydev); + if (ret < 0) + return ret; + + return genphy_read_status(phydev); +} + static int kszphy_get_sset_count(struct phy_device *phydev) { return ARRAY_SIZE(kszphy_hw_stats); @@ -1397,6 +1483,8 @@ static struct phy_driver ksphy_driver[] = { .name = "Micrel KSZ8851 Ethernet MAC or KSZ886X Switch", /* PHY_BASIC_FEATURES */ .config_init = kszphy_config_init, + .config_aneg = ksz886x_config_aneg, + .read_status = ksz886x_read_status, .suspend = genphy_suspend, .resume = genphy_resume, }, { diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index b03e2afcb53f..58370abd9f4f 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -58,4 +58,6 @@ #define KSZ886X_BMCR_DISABLE_TRANSMIT BIT(1) #define KSZ886X_BMCR_DISABLE_LED BIT(0) +#define KSZ886X_CTRL_MDIX_STAT BIT(4) + #endif /* _MICREL_PHY_H */ -- cgit v1.2.3-71-gd317 From 49011e0c1555dd7a689d0f32fd78c1ecd43e59cd Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Mon, 14 Jun 2021 06:31:25 +0200 Subject: net: phy: micrel: ksz886x/ksz8081: add cabletest support This patch support for cable test for the ksz886x switches and the ksz8081 PHY. The patch was tested on a KSZ8873RLL switch with following results: - port 1: - provides invalid values, thus return -ENOTSUPP (Errata: DS80000830A: "LinkMD does not work on Port 1", http://ww1.microchip.com/downloads/en/DeviceDoc/KSZ8873-Errata-DS80000830A.pdf) - port 2: - can detect distance - can detect open on each wire of pair A (wire 1 and 2) - can detect open only on one wire of pair B (only wire 3) - can detect short between wires of a pair (wires 1 + 2 or 3 + 6) - short between pairs is detected as open. For example short between wires 2 + 3 is detected as open. Signed-off-by: Oleksij Rempel Signed-off-by: David S. Miller --- drivers/net/dsa/microchip/ksz8795.c | 13 +++ drivers/net/phy/micrel.c | 180 ++++++++++++++++++++++++++++++++++++ include/linux/micrel_phy.h | 1 + 3 files changed, 194 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index e1731ae4497d..560f6843bb65 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -970,6 +970,18 @@ static enum dsa_tag_protocol ksz8_get_tag_protocol(struct dsa_switch *ds, DSA_TAG_PROTO_KSZ9893 : DSA_TAG_PROTO_KSZ8795; } +static u32 ksz8_sw_get_phy_flags(struct dsa_switch *ds, int port) +{ + /* Silicon Errata Sheet (DS80000830A): + * Port 1 does not work with LinkMD Cable-Testing. + * Port 1 does not respond to received PAUSE control frames. + */ + if (!port) + return MICREL_KSZ8_P1_ERRATA; + + return 0; +} + static void ksz8_get_strings(struct dsa_switch *ds, int port, u32 stringset, uint8_t *buf) { @@ -1503,6 +1515,7 @@ unsupported: static const struct dsa_switch_ops ksz8_switch_ops = { .get_tag_protocol = ksz8_get_tag_protocol, + .get_phy_flags = ksz8_sw_get_phy_flags, .setup = ksz8_setup, .phy_read = ksz_phy_read16, .phy_write = ksz_phy_write16, diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 5ca39ce8db96..4d53886f7d51 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -20,6 +20,7 @@ */ #include +#include #include #include #include @@ -53,6 +54,18 @@ #define KSZPHY_INTCS_STATUS (KSZPHY_INTCS_LINK_DOWN_STATUS |\ KSZPHY_INTCS_LINK_UP_STATUS) +/* LinkMD Control/Status */ +#define KSZ8081_LMD 0x1d +#define KSZ8081_LMD_ENABLE_TEST BIT(15) +#define KSZ8081_LMD_STAT_NORMAL 0 +#define KSZ8081_LMD_STAT_OPEN 1 +#define KSZ8081_LMD_STAT_SHORT 2 +#define KSZ8081_LMD_STAT_FAIL 3 +#define KSZ8081_LMD_STAT_MASK GENMASK(14, 13) +/* Short cable (<10 meter) has been detected by LinkMD */ +#define KSZ8081_LMD_SHORT_INDICATOR BIT(12) +#define KSZ8081_LMD_DELTA_TIME_MASK GENMASK(8, 0) + /* PHY Control 1 */ #define MII_KSZPHY_CTRL_1 0x1e #define KSZ8081_CTRL1_MDIX_STAT BIT(4) @@ -1363,6 +1376,167 @@ static int kszphy_probe(struct phy_device *phydev) return 0; } +static int ksz886x_cable_test_start(struct phy_device *phydev) +{ + if (phydev->dev_flags & MICREL_KSZ8_P1_ERRATA) + return -EOPNOTSUPP; + + /* If autoneg is enabled, we won't be able to test cross pair + * short. In this case, the PHY will "detect" a link and + * confuse the internal state machine - disable auto neg here. + * If autoneg is disabled, we should set the speed to 10mbit. + */ + return phy_clear_bits(phydev, MII_BMCR, BMCR_ANENABLE | BMCR_SPEED100); +} + +static int ksz886x_cable_test_result_trans(u16 status) +{ + switch (FIELD_GET(KSZ8081_LMD_STAT_MASK, status)) { + case KSZ8081_LMD_STAT_NORMAL: + return ETHTOOL_A_CABLE_RESULT_CODE_OK; + case KSZ8081_LMD_STAT_SHORT: + return ETHTOOL_A_CABLE_RESULT_CODE_SAME_SHORT; + case KSZ8081_LMD_STAT_OPEN: + return ETHTOOL_A_CABLE_RESULT_CODE_OPEN; + case KSZ8081_LMD_STAT_FAIL: + fallthrough; + default: + return ETHTOOL_A_CABLE_RESULT_CODE_UNSPEC; + } +} + +static bool ksz886x_cable_test_failed(u16 status) +{ + return FIELD_GET(KSZ8081_LMD_STAT_MASK, status) == + KSZ8081_LMD_STAT_FAIL; +} + +static bool ksz886x_cable_test_fault_length_valid(u16 status) +{ + switch (FIELD_GET(KSZ8081_LMD_STAT_MASK, status)) { + case KSZ8081_LMD_STAT_OPEN: + fallthrough; + case KSZ8081_LMD_STAT_SHORT: + return true; + } + return false; +} + +static int ksz886x_cable_test_fault_length(u16 status) +{ + int dt; + + /* According to the data sheet the distance to the fault is + * DELTA_TIME * 0.4 meters. + */ + dt = FIELD_GET(KSZ8081_LMD_DELTA_TIME_MASK, status); + + return (dt * 400) / 10; +} + +static int ksz886x_cable_test_wait_for_completion(struct phy_device *phydev) +{ + int val, ret; + + ret = phy_read_poll_timeout(phydev, KSZ8081_LMD, val, + !(val & KSZ8081_LMD_ENABLE_TEST), + 30000, 100000, true); + + return ret < 0 ? ret : 0; +} + +static int ksz886x_cable_test_one_pair(struct phy_device *phydev, int pair) +{ + static const int ethtool_pair[] = { + ETHTOOL_A_CABLE_PAIR_A, + ETHTOOL_A_CABLE_PAIR_B, + }; + int ret, val, mdix; + + /* There is no way to choice the pair, like we do one ksz9031. + * We can workaround this limitation by using the MDI-X functionality. + */ + if (pair == 0) + mdix = ETH_TP_MDI; + else + mdix = ETH_TP_MDI_X; + + switch (phydev->phy_id & MICREL_PHY_ID_MASK) { + case PHY_ID_KSZ8081: + ret = ksz8081_config_mdix(phydev, mdix); + break; + case PHY_ID_KSZ886X: + ret = ksz886x_config_mdix(phydev, mdix); + break; + default: + ret = -ENODEV; + } + + if (ret) + return ret; + + /* Now we are ready to fire. This command will send a 100ns pulse + * to the pair. + */ + ret = phy_write(phydev, KSZ8081_LMD, KSZ8081_LMD_ENABLE_TEST); + if (ret) + return ret; + + ret = ksz886x_cable_test_wait_for_completion(phydev); + if (ret) + return ret; + + val = phy_read(phydev, KSZ8081_LMD); + if (val < 0) + return val; + + if (ksz886x_cable_test_failed(val)) + return -EAGAIN; + + ret = ethnl_cable_test_result(phydev, ethtool_pair[pair], + ksz886x_cable_test_result_trans(val)); + if (ret) + return ret; + + if (!ksz886x_cable_test_fault_length_valid(val)) + return 0; + + return ethnl_cable_test_fault_length(phydev, ethtool_pair[pair], + ksz886x_cable_test_fault_length(val)); +} + +static int ksz886x_cable_test_get_status(struct phy_device *phydev, + bool *finished) +{ + unsigned long pair_mask = 0x3; + int retries = 20; + int pair, ret; + + *finished = false; + + /* Try harder if link partner is active */ + while (pair_mask && retries--) { + for_each_set_bit(pair, &pair_mask, 4) { + ret = ksz886x_cable_test_one_pair(phydev, pair); + if (ret == -EAGAIN) + continue; + if (ret < 0) + return ret; + clear_bit(pair, &pair_mask); + } + /* If link partner is in autonegotiation mode it will send 2ms + * of FLPs with at least 6ms of silence. + * Add 2ms sleep to have better chances to hit this silence. + */ + if (pair_mask) + msleep(2); + } + + *finished = true; + + return ret; +} + static struct phy_driver ksphy_driver[] = { { .phy_id = PHY_ID_KS8737, @@ -1469,6 +1643,7 @@ static struct phy_driver ksphy_driver[] = { .phy_id = PHY_ID_KSZ8081, .name = "Micrel KSZ8081 or KSZ8091", .phy_id_mask = MICREL_PHY_ID_MASK, + .flags = PHY_POLL_CABLE_TEST, /* PHY_BASIC_FEATURES */ .driver_data = &ksz8081_type, .probe = kszphy_probe, @@ -1483,6 +1658,8 @@ static struct phy_driver ksphy_driver[] = { .get_stats = kszphy_get_stats, .suspend = kszphy_suspend, .resume = kszphy_resume, + .cable_test_start = ksz886x_cable_test_start, + .cable_test_get_status = ksz886x_cable_test_get_status, }, { .phy_id = PHY_ID_KSZ8061, .name = "Micrel KSZ8061", @@ -1571,11 +1748,14 @@ static struct phy_driver ksphy_driver[] = { .phy_id_mask = MICREL_PHY_ID_MASK, .name = "Micrel KSZ8851 Ethernet MAC or KSZ886X Switch", /* PHY_BASIC_FEATURES */ + .flags = PHY_POLL_CABLE_TEST, .config_init = kszphy_config_init, .config_aneg = ksz886x_config_aneg, .read_status = ksz886x_read_status, .suspend = genphy_suspend, .resume = genphy_resume, + .cable_test_start = ksz886x_cable_test_start, + .cable_test_get_status = ksz886x_cable_test_get_status, }, { .name = "Micrel KSZ87XX Switch", /* PHY_BASIC_FEATURES */ diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 58370abd9f4f..3d43c60b49fa 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -39,6 +39,7 @@ /* struct phy_device dev_flags definitions */ #define MICREL_PHY_50MHZ_CLK 0x00000001 #define MICREL_PHY_FXEN 0x00000002 +#define MICREL_KSZ8_P1_ERRATA 0x00000003 #define MICREL_KSZ9021_EXTREG_CTRL 0xB #define MICREL_KSZ9021_EXTREG_DATA_WRITE 0xC -- cgit v1.2.3-71-gd317 From e4e3f24b822f9dc9ae2427a8d686e8c1d80d6bd2 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 23 Feb 2021 10:37:05 +0200 Subject: net/mlx5: Provide cpumask at EQ creation phase The users of EQ are running their code on different CPUs and with various affinity patterns. Move the cpumask setting close to their actual usage. Signed-off-by: Leon Romanovsky Reviewed-by: Shay Drory Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/odp.c | 5 + drivers/net/ethernet/mellanox/mlx5/core/eq.c | 27 ++++-- drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h | 3 +- drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c | 103 +++++---------------- include/linux/mlx5/eq.h | 1 + 5 files changed, 49 insertions(+), 90 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 782b2af8f211..8f88b044ccbc 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -1564,7 +1564,12 @@ int mlx5r_odp_create_eq(struct mlx5_ib_dev *dev, struct mlx5_ib_pf_eq *eq) .nent = MLX5_IB_NUM_PF_EQE, }; param.mask[0] = 1ull << MLX5_EVENT_TYPE_PAGE_FAULT; + if (!zalloc_cpumask_var(¶m.affinity, GFP_KERNEL)) { + err = -ENOMEM; + goto err_wq; + } eq->core = mlx5_eq_create_generic(dev->mdev, ¶m); + free_cpumask_var(param.affinity); if (IS_ERR(eq->core)) { err = PTR_ERR(eq->core); goto err_wq; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 7e7bbed3763d..5a88887c1a58 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -310,7 +310,7 @@ create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, mlx5_init_fbc(eq->frag_buf.frags, log_eq_stride, log_eq_size, &eq->fbc); init_eq_buf(eq); - eq->irq = mlx5_irq_request(dev, vecidx); + eq->irq = mlx5_irq_request(dev, vecidx, param->affinity); if (IS_ERR(eq->irq)) { err = PTR_ERR(eq->irq); goto err_buf; @@ -621,8 +621,11 @@ setup_async_eq(struct mlx5_core_dev *dev, struct mlx5_eq_async *eq, eq->irq_nb.notifier_call = mlx5_eq_async_int; spin_lock_init(&eq->lock); + if (!zalloc_cpumask_var(¶m->affinity, GFP_KERNEL)) + return -ENOMEM; err = create_async_eq(dev, &eq->core, param); + free_cpumask_var(param->affinity); if (err) { mlx5_core_warn(dev, "failed to create %s EQ %d\n", name, err); return err; @@ -740,6 +743,9 @@ mlx5_eq_create_generic(struct mlx5_core_dev *dev, struct mlx5_eq *eq = kvzalloc(sizeof(*eq), GFP_KERNEL); int err; + if (!param->affinity) + return ERR_PTR(-EINVAL); + if (!eq) return ERR_PTR(-ENOMEM); @@ -850,16 +856,21 @@ static int create_comp_eqs(struct mlx5_core_dev *dev) .irq_index = vecidx, .nent = nent, }; - err = create_map_eq(dev, &eq->core, ¶m); - if (err) { - kfree(eq); - goto clean; + + if (!zalloc_cpumask_var(¶m.affinity, GFP_KERNEL)) { + err = -ENOMEM; + goto clean_eq; } + cpumask_set_cpu(cpumask_local_spread(i, dev->priv.numa_node), + param.affinity); + err = create_map_eq(dev, &eq->core, ¶m); + free_cpumask_var(param.affinity); + if (err) + goto clean_eq; err = mlx5_eq_enable(dev, &eq->core, &eq->irq_nb); if (err) { destroy_unmap_eq(dev, &eq->core); - kfree(eq); - goto clean; + goto clean_eq; } mlx5_core_dbg(dev, "allocated completion EQN %d\n", eq->core.eqn); @@ -868,6 +879,8 @@ static int create_comp_eqs(struct mlx5_core_dev *dev) } return 0; +clean_eq: + kfree(eq); clean: destroy_comp_eqs(dev); return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h index dd138b38bf36..81bfb5f0d332 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h @@ -20,7 +20,8 @@ int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int devfn, int msix_vec_count); int mlx5_get_default_msix_vec_count(struct mlx5_core_dev *dev, int num_vfs); -struct mlx5_irq *mlx5_irq_request(struct mlx5_core_dev *dev, int vecidx); +struct mlx5_irq *mlx5_irq_request(struct mlx5_core_dev *dev, int vecidx, + struct cpumask *affinity); void mlx5_irq_release(struct mlx5_irq *irq); int mlx5_irq_attach_nb(struct mlx5_irq *irq, struct notifier_block *nb); int mlx5_irq_detach_nb(struct mlx5_irq *irq, struct notifier_block *nb); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index ecace7ca4a01..81b06b5693cd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -17,6 +17,7 @@ struct mlx5_irq { struct atomic_notifier_head nh; cpumask_var_t mask; char name[MLX5_MAX_IRQ_NAME]; + spinlock_t lock; /* protects affinity assignment */ struct kref kref; int irqn; }; @@ -153,6 +154,8 @@ static void irq_release(struct kref *kref) { struct mlx5_irq *irq = container_of(kref, struct mlx5_irq, kref); + irq_set_affinity_hint(irq->irqn, NULL); + free_cpumask_var(irq->mask); free_irq(irq->irqn, &irq->nh); } @@ -189,7 +192,8 @@ void mlx5_irq_release(struct mlx5_irq *irq) irq_put(irq); } -struct mlx5_irq *mlx5_irq_request(struct mlx5_core_dev *dev, int vecidx) +struct mlx5_irq *mlx5_irq_request(struct mlx5_core_dev *dev, int vecidx, + struct cpumask *affinity) { struct mlx5_irq_table *table = mlx5_irq_table_get(dev); struct mlx5_irq *irq = &table->irq[vecidx]; @@ -199,6 +203,16 @@ struct mlx5_irq *mlx5_irq_request(struct mlx5_core_dev *dev, int vecidx) if (!err) return ERR_PTR(-ENOENT); + spin_lock(&irq->lock); + if (!cpumask_empty(irq->mask)) { + /* already configured */ + spin_unlock(&irq->lock); + return irq; + } + + cpumask_copy(irq->mask, affinity); + irq_set_affinity_hint(irq->irqn, irq->mask); + spin_unlock(&irq->lock); return irq; } @@ -239,6 +253,12 @@ static int request_irqs(struct mlx5_core_dev *dev, int nvec) mlx5_core_err(dev, "Failed to request irq\n"); goto err_request_irq; } + if (!zalloc_cpumask_var(&irq->mask, GFP_KERNEL)) { + mlx5_core_warn(dev, "zalloc_cpumask_var failed\n"); + err = -ENOMEM; + goto err_request_irq; + } + spin_lock_init(&irq->lock); kref_init(&irq->kref); } return 0; @@ -294,69 +314,6 @@ err_out: return err; } -/* Completion IRQ vectors */ - -static int set_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i) -{ - int vecidx = MLX5_IRQ_VEC_COMP_BASE + i; - struct mlx5_irq *irq; - - irq = mlx5_irq_get(mdev, vecidx); - if (!zalloc_cpumask_var(&irq->mask, GFP_KERNEL)) { - mlx5_core_warn(mdev, "zalloc_cpumask_var failed"); - return -ENOMEM; - } - - cpumask_set_cpu(cpumask_local_spread(i, mdev->priv.numa_node), - irq->mask); - if (IS_ENABLED(CONFIG_SMP) && - irq_set_affinity_hint(irq->irqn, irq->mask)) - mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x", - irq->irqn); - - return 0; -} - -static void clear_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i) -{ - int vecidx = MLX5_IRQ_VEC_COMP_BASE + i; - struct mlx5_irq *irq; - - irq = mlx5_irq_get(mdev, vecidx); - irq_set_affinity_hint(irq->irqn, NULL); - free_cpumask_var(irq->mask); -} - -static int set_comp_irq_affinity_hints(struct mlx5_core_dev *mdev) -{ - int nvec = mlx5_irq_get_num_comp(mdev->priv.irq_table); - int err; - int i; - - for (i = 0; i < nvec; i++) { - err = set_comp_irq_affinity_hint(mdev, i); - if (err) - goto err_out; - } - - return 0; - -err_out: - for (i--; i >= 0; i--) - clear_comp_irq_affinity_hint(mdev, i); - - return err; -} - -static void clear_comp_irqs_affinity_hints(struct mlx5_core_dev *mdev) -{ - int nvec = mlx5_irq_get_num_comp(mdev->priv.irq_table); - int i; - - for (i = 0; i < nvec; i++) - clear_comp_irq_affinity_hint(mdev, i); -} - struct cpumask * mlx5_irq_get_affinity_mask(struct mlx5_irq_table *irq_table, int vecidx) { @@ -370,15 +327,6 @@ struct cpu_rmap *mlx5_irq_get_rmap(struct mlx5_irq_table *irq_table) } #endif -static void unrequest_irqs(struct mlx5_core_dev *dev) -{ - struct mlx5_irq_table *table = dev->priv.irq_table; - int i; - - for (i = 0; i < table->nvec; i++) - irq_put(mlx5_irq_get(dev, i)); -} - int mlx5_irq_table_create(struct mlx5_core_dev *dev) { struct mlx5_priv *priv = &dev->priv; @@ -419,16 +367,8 @@ int mlx5_irq_table_create(struct mlx5_core_dev *dev) if (err) goto err_request_irqs; - err = set_comp_irq_affinity_hints(dev); - if (err) { - mlx5_core_err(dev, "Failed to alloc affinity hint cpumask\n"); - goto err_set_affinity; - } - return 0; -err_set_affinity: - unrequest_irqs(dev); err_request_irqs: irq_clear_rmap(dev); err_set_rmap: @@ -451,7 +391,6 @@ void mlx5_irq_table_destroy(struct mlx5_core_dev *dev) * which should be called after alloc_irq but before request_irq. */ irq_clear_rmap(dev); - clear_comp_irqs_affinity_hints(dev); for (i = 0; i < table->nvec; i++) irq_release(&mlx5_irq_get(dev, i)->kref); pci_free_irq_vectors(dev->pdev); diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h index e49d8c0d4f26..cea6ecb4b73e 100644 --- a/include/linux/mlx5/eq.h +++ b/include/linux/mlx5/eq.h @@ -16,6 +16,7 @@ struct mlx5_eq_param { u8 irq_index; int nent; u64 mask[4]; + cpumask_var_t affinity; }; struct mlx5_eq * -- cgit v1.2.3-71-gd317 From 3af26495a2473c95ada3674c6b4dfc658be0a6ec Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Mon, 10 May 2021 09:10:43 +0300 Subject: net/mlx5: Enlarge interrupt field in CREATE_EQ FW is now supporting more than 256 MSI-X per PF (up to 2K). Hence, enlarge interrupt field in CREATE_EQ to make use of the new MSI-X's. Signed-off-by: Shay Drory Reviewed-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 057db0eaf195..2d1ed78289ff 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -3806,8 +3806,8 @@ struct mlx5_ifc_eqc_bits { u8 reserved_at_80[0x20]; - u8 reserved_at_a0[0x18]; - u8 intr[0x8]; + u8 reserved_at_a0[0x14]; + u8 intr[0xc]; u8 reserved_at_c0[0x3]; u8 log_page_size[0x5]; -- cgit v1.2.3-71-gd317 From d5e4ddaeb6ab2c3c7fbb7b247a6d34bb0b18d87e Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Sat, 12 Jun 2021 21:32:22 +0900 Subject: bpf: Support socket migration by eBPF. This patch introduces a new bpf_attach_type for BPF_PROG_TYPE_SK_REUSEPORT to check if the attached eBPF program is capable of migrating sockets. When the eBPF program is attached, we run it for socket migration if the expected_attach_type is BPF_SK_REUSEPORT_SELECT_OR_MIGRATE or net.ipv4.tcp_migrate_req is enabled. Currently, the expected_attach_type is not enforced for the BPF_PROG_TYPE_SK_REUSEPORT type of program. Thus, this commit follows the earlier idea in the commit aac3fc320d94 ("bpf: Post-hooks for sys_bind") to fix up the zero expected_attach_type in bpf_prog_load_fixup_attach_type(). Moreover, this patch adds a new field (migrating_sk) to sk_reuseport_md to select a new listener based on the child socket. migrating_sk varies depending on if it is migrating a request in the accept queue or during 3WHS. - accept_queue : sock (ESTABLISHED/SYN_RECV) - 3WHS : request_sock (NEW_SYN_RECV) In the eBPF program, we can select a new listener by BPF_FUNC_sk_select_reuseport(). Also, we can cancel migration by returning SK_DROP. This feature is useful when listeners have different settings at the socket API level or when we want to free resources as soon as possible. - SK_PASS with selected_sk, select it as a new listener - SK_PASS with selected_sk NULL, fallbacks to the random selection - SK_DROP, cancel the migration. There is a noteworthy point. We select a listening socket in three places, but we do not have struct skb at closing a listener or retransmitting a SYN+ACK. On the other hand, some helper functions do not expect skb is NULL (e.g. skb_header_pointer() in BPF_FUNC_skb_load_bytes(), skb_tail_pointer() in BPF_FUNC_skb_load_bytes_relative()). So we allocate an empty skb temporarily before running the eBPF program. Suggested-by: Martin KaFai Lau Signed-off-by: Kuniyuki Iwashima Signed-off-by: Daniel Borkmann Reviewed-by: Eric Dumazet Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/netdev/20201123003828.xjpjdtk4ygl6tg6h@kafai-mbp.dhcp.thefacebook.com/ Link: https://lore.kernel.org/netdev/20201203042402.6cskdlit5f3mw4ru@kafai-mbp.dhcp.thefacebook.com/ Link: https://lore.kernel.org/netdev/20201209030903.hhow5r53l6fmozjn@kafai-mbp.dhcp.thefacebook.com/ Link: https://lore.kernel.org/bpf/20210612123224.12525-10-kuniyu@amazon.co.jp --- include/linux/bpf.h | 1 + include/linux/filter.h | 2 ++ include/uapi/linux/bpf.h | 15 +++++++++++++++ kernel/bpf/syscall.c | 13 +++++++++++++ net/core/filter.c | 13 ++++++++++++- net/core/sock_reuseport.c | 34 ++++++++++++++++++++++++++++++---- tools/include/uapi/linux/bpf.h | 15 +++++++++++++++ 7 files changed, 88 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 86dec5001ae2..f309fc1509f2 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2048,6 +2048,7 @@ struct sk_reuseport_kern { struct sk_buff *skb; struct sock *sk; struct sock *selected_sk; + struct sock *migrating_sk; void *data_end; u32 hash; u32 reuseport_id; diff --git a/include/linux/filter.h b/include/linux/filter.h index c5ad7df029ed..688856e0b28a 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -996,11 +996,13 @@ void bpf_warn_invalid_xdp_action(u32 act); #ifdef CONFIG_INET struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, + struct sock *migrating_sk, u32 hash); #else static inline struct sock * bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, + struct sock *migrating_sk, u32 hash) { return NULL; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f3b72588442b..bf9252c7381e 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -994,6 +994,8 @@ enum bpf_attach_type { BPF_SK_LOOKUP, BPF_XDP, BPF_SK_SKB_VERDICT, + BPF_SK_REUSEPORT_SELECT, + BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, __MAX_BPF_ATTACH_TYPE }; @@ -5416,7 +5418,20 @@ struct sk_reuseport_md { __u32 ip_protocol; /* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */ __u32 bind_inany; /* Is sock bound to an INANY address? */ __u32 hash; /* A hash of the packet 4 tuples */ + /* When reuse->migrating_sk is NULL, it is selecting a sk for the + * new incoming connection request (e.g. selecting a listen sk for + * the received SYN in the TCP case). reuse->sk is one of the sk + * in the reuseport group. The bpf prog can use reuse->sk to learn + * the local listening ip/port without looking into the skb. + * + * When reuse->migrating_sk is not NULL, reuse->sk is closed and + * reuse->migrating_sk is the socket that needs to be migrated + * to another listening socket. migrating_sk could be a fullsock + * sk that is fully established or a reqsk that is in-the-middle + * of 3-way handshake. + */ __bpf_md_ptr(struct bpf_sock *, sk); + __bpf_md_ptr(struct bpf_sock *, migrating_sk); }; #define BPF_TAG_SIZE 8 diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 50457019da27..dbbc5342f221 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1972,6 +1972,11 @@ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr) attr->expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE; break; + case BPF_PROG_TYPE_SK_REUSEPORT: + if (!attr->expected_attach_type) + attr->expected_attach_type = + BPF_SK_REUSEPORT_SELECT; + break; } } @@ -2055,6 +2060,14 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, if (expected_attach_type == BPF_SK_LOOKUP) return 0; return -EINVAL; + case BPF_PROG_TYPE_SK_REUSEPORT: + switch (expected_attach_type) { + case BPF_SK_REUSEPORT_SELECT: + case BPF_SK_REUSEPORT_SELECT_OR_MIGRATE: + return 0; + default: + return -EINVAL; + } case BPF_PROG_TYPE_SYSCALL: case BPF_PROG_TYPE_EXT: if (expected_attach_type) diff --git a/net/core/filter.c b/net/core/filter.c index f753ab550525..5b86e47ef079 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -10044,11 +10044,13 @@ out: static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern, struct sock_reuseport *reuse, struct sock *sk, struct sk_buff *skb, + struct sock *migrating_sk, u32 hash) { reuse_kern->skb = skb; reuse_kern->sk = sk; reuse_kern->selected_sk = NULL; + reuse_kern->migrating_sk = migrating_sk; reuse_kern->data_end = skb->data + skb_headlen(skb); reuse_kern->hash = hash; reuse_kern->reuseport_id = reuse->reuseport_id; @@ -10057,12 +10059,13 @@ static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern, struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, + struct sock *migrating_sk, u32 hash) { struct sk_reuseport_kern reuse_kern; enum sk_action action; - bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, hash); + bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, migrating_sk, hash); action = BPF_PROG_RUN(prog, &reuse_kern); if (action == SK_PASS) @@ -10207,6 +10210,10 @@ sk_reuseport_is_valid_access(int off, int size, info->reg_type = PTR_TO_SOCKET; return size == sizeof(__u64); + case offsetof(struct sk_reuseport_md, migrating_sk): + info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL; + return size == sizeof(__u64); + /* Fields that allow narrowing */ case bpf_ctx_range(struct sk_reuseport_md, eth_protocol): if (size < sizeof_field(struct sk_buff, protocol)) @@ -10283,6 +10290,10 @@ static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type, case offsetof(struct sk_reuseport_md, sk): SK_REUSEPORT_LOAD_FIELD(sk); break; + + case offsetof(struct sk_reuseport_md, migrating_sk): + SK_REUSEPORT_LOAD_FIELD(migrating_sk); + break; } return insn - insn_buf; diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index b239f8cd9d39..de5ee3ae86d5 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -377,13 +377,17 @@ void reuseport_stop_listen_sock(struct sock *sk) { if (sk->sk_protocol == IPPROTO_TCP) { struct sock_reuseport *reuse; + struct bpf_prog *prog; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); + prog = rcu_dereference_protected(reuse->prog, + lockdep_is_held(&reuseport_lock)); - if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req) { + if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req || + (prog && prog->expected_attach_type == BPF_SK_REUSEPORT_SELECT_OR_MIGRATE)) { /* Migration capable, move sk from the listening section * to the closed section. */ @@ -488,7 +492,7 @@ struct sock *reuseport_select_sock(struct sock *sk, goto select_by_hash; if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) - sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, hash); + sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, NULL, hash); else sk2 = run_bpf_filter(reuse, socks, prog, skb, hdr_len); @@ -519,6 +523,8 @@ struct sock *reuseport_migrate_sock(struct sock *sk, { struct sock_reuseport *reuse; struct sock *nsk = NULL; + bool allocated = false; + struct bpf_prog *prog; u16 socks; u32 hash; @@ -536,10 +542,30 @@ struct sock *reuseport_migrate_sock(struct sock *sk, smp_rmb(); hash = migrating_sk->sk_hash; - if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req) + prog = rcu_dereference(reuse->prog); + if (!prog || prog->expected_attach_type != BPF_SK_REUSEPORT_SELECT_OR_MIGRATE) { + if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req) + goto select_by_hash; + goto out; + } + + if (!skb) { + skb = alloc_skb(0, GFP_ATOMIC); + if (!skb) + goto out; + allocated = true; + } + + nsk = bpf_run_sk_reuseport(reuse, sk, prog, skb, migrating_sk, hash); + + if (allocated) + kfree_skb(skb); + +select_by_hash: + if (!nsk) nsk = reuseport_select_sock_by_hash(reuse, hash, socks); - if (nsk && unlikely(!refcount_inc_not_zero(&nsk->sk_refcnt))) + if (IS_ERR_OR_NULL(nsk) || unlikely(!refcount_inc_not_zero(&nsk->sk_refcnt))) nsk = NULL; out: diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index f3b72588442b..bf9252c7381e 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -994,6 +994,8 @@ enum bpf_attach_type { BPF_SK_LOOKUP, BPF_XDP, BPF_SK_SKB_VERDICT, + BPF_SK_REUSEPORT_SELECT, + BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, __MAX_BPF_ATTACH_TYPE }; @@ -5416,7 +5418,20 @@ struct sk_reuseport_md { __u32 ip_protocol; /* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */ __u32 bind_inany; /* Is sock bound to an INANY address? */ __u32 hash; /* A hash of the packet 4 tuples */ + /* When reuse->migrating_sk is NULL, it is selecting a sk for the + * new incoming connection request (e.g. selecting a listen sk for + * the received SYN in the TCP case). reuse->sk is one of the sk + * in the reuseport group. The bpf prog can use reuse->sk to learn + * the local listening ip/port without looking into the skb. + * + * When reuse->migrating_sk is not NULL, reuse->sk is closed and + * reuse->migrating_sk is the socket that needs to be migrated + * to another listening socket. migrating_sk could be a fullsock + * sk that is fully established or a reqsk that is in-the-middle + * of 3-way handshake. + */ __bpf_md_ptr(struct bpf_sock *, sk); + __bpf_md_ptr(struct bpf_sock *, migrating_sk); }; #define BPF_TAG_SIZE 8 -- cgit v1.2.3-71-gd317 From 2d8ea148e553e1dd4e80a87741abdfb229e2b323 Mon Sep 17 00:00:00 2001 From: Jian Shen Date: Thu, 17 Jun 2021 11:37:11 +0800 Subject: net: fix mistake path for netdev_features_strings Th_strings arrays netdev_features_strings, tunable_strings, and phy_tunable_strings has been moved to file net/ethtool/common.c. So fixes the comment. Signed-off-by: Jian Shen Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 2 +- include/uapi/linux/ethtool.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 3de38d6a0aea..2c6b9e416225 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -93,7 +93,7 @@ enum { /* * Add your fresh new feature above and remember to update - * netdev_features_strings[] in net/core/ethtool.c and maybe + * netdev_features_strings[] in net/ethtool/common.c and maybe * some feature mask #defines below. Please also describe it * in Documentation/networking/netdev-features.rst. */ diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index cfef6b08169a..67aa7134b301 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -233,7 +233,7 @@ enum tunable_id { ETHTOOL_PFC_PREVENTION_TOUT, /* timeout in msecs */ /* * Add your fresh new tunable attribute above and remember to update - * tunable_strings[] in net/core/ethtool.c + * tunable_strings[] in net/ethtool/common.c */ __ETHTOOL_TUNABLE_COUNT, }; @@ -297,7 +297,7 @@ enum phy_tunable_id { ETHTOOL_PHY_EDPD, /* * Add your fresh new phy tunable attribute above and remember to update - * phy_tunable_strings[] in net/core/ethtool.c + * phy_tunable_strings[] in net/ethtool/common.c */ __ETHTOOL_PHY_TUNABLE_COUNT, }; -- cgit v1.2.3-71-gd317 From 43e76d463c09a0272b84775bcc727c1eb8b384b2 Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Thu, 17 Jun 2021 15:29:04 +0300 Subject: driver core: add a helper to setup both the of_node and fwnode of a device There are many places where both the fwnode_handle and the of_node of a device need to be populated. Add a function which does both so that we have consistency. Suggested-by: Andrew Lunn Signed-off-by: Ioana Ciornei Reviewed-by: Greg Kroah-Hartman Signed-off-by: David S. Miller --- drivers/base/core.c | 7 +++++++ include/linux/device.h | 1 + 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index 628e33939aca..b6836bfa985c 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -4723,6 +4723,13 @@ void device_set_of_node_from_dev(struct device *dev, const struct device *dev2) } EXPORT_SYMBOL_GPL(device_set_of_node_from_dev); +void device_set_node(struct device *dev, struct fwnode_handle *fwnode) +{ + dev->fwnode = fwnode; + dev->of_node = to_of_node(fwnode); +} +EXPORT_SYMBOL_GPL(device_set_node); + int device_match_name(struct device *dev, const void *name) { return sysfs_streq(dev_name(dev), name); diff --git a/include/linux/device.h b/include/linux/device.h index 38a2071cf776..a1e7cab2c7bf 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -819,6 +819,7 @@ int device_online(struct device *dev); void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void device_set_of_node_from_dev(struct device *dev, const struct device *dev2); +void device_set_node(struct device *dev, struct fwnode_handle *fwnode); static inline int dev_num_vf(struct device *dev) { -- cgit v1.2.3-71-gd317 From 60302ce4ea075369641426ef407c110e36ea8ba1 Mon Sep 17 00:00:00 2001 From: Stephan Gerhold Date: Fri, 18 Jun 2021 19:36:09 +0200 Subject: rpmsg: core: Add driver_data for rpmsg_device_id Most device_id structs provide a driver_data field that can be used by drivers to associate data more easily for a particular device ID. Add the same for the rpmsg_device_id. Cc: Bjorn Andersson Signed-off-by: Stephan Gerhold Signed-off-by: David S. Miller --- drivers/rpmsg/rpmsg_core.c | 4 +++- include/linux/mod_devicetable.h | 1 + 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/rpmsg/rpmsg_core.c b/drivers/rpmsg/rpmsg_core.c index e5daee4f9373..c1404d3dae2c 100644 --- a/drivers/rpmsg/rpmsg_core.c +++ b/drivers/rpmsg/rpmsg_core.c @@ -459,8 +459,10 @@ static int rpmsg_dev_match(struct device *dev, struct device_driver *drv) if (ids) for (i = 0; ids[i].name[0]; i++) - if (rpmsg_id_match(rpdev, &ids[i])) + if (rpmsg_id_match(rpdev, &ids[i])) { + rpdev->id.driver_data = ids[i].driver_data; return 1; + } return of_driver_match_device(dev, drv); } diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 7d45b5f989b0..8e291cfdaf06 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -447,6 +447,7 @@ struct hv_vmbus_device_id { struct rpmsg_device_id { char name[RPMSG_NAME_SIZE]; + kernel_ulong_t driver_data; }; /* i2c */ -- cgit v1.2.3-71-gd317 From 31c143f712750143abaca396236bbe8707700111 Mon Sep 17 00:00:00 2001 From: Stephan Gerhold Date: Fri, 18 Jun 2021 19:36:11 +0200 Subject: net: wwan: Allow WWAN drivers to provide blocking tx and poll function At the moment, the WWAN core provides wwan_port_txon/off() to implement blocking writes. The tx() port operation should not block, instead wwan_port_txon/off() should be called when the TX queue is full or has free space again. However, in some cases it is not straightforward to make use of that functionality. For example, the RPMSG API used by rpmsg_wwan_ctrl.c does not provide any way to be notified when the TX queue has space again. Instead, it only provides the following operations: - rpmsg_send(): blocking write (wait until there is space) - rpmsg_trysend(): non-blocking write (return error if no space) - rpmsg_poll(): set poll flags depending on TX queue state Generally that's totally sufficient for implementing a char device, but it does not fit well to the currently provided WWAN port ops. Most of the time, using the non-blocking rpmsg_trysend() in the WWAN tx() port operation works just fine. However, with high-frequent writes to the char device it is possible to trigger a situation where this causes issues. For example, consider the following (somewhat unrealistic) example: # dd if=/dev/zero bs=1000 of=/dev/wwan0qmi0 dd: error writing '/dev/wwan0qmi0': Resource temporarily unavailable 1+0 records out This fails immediately after writing the first record. It's likely only a matter of time until this triggers issues for some real application (e.g. ModemManager sending a lot of large QMI packets). The rpmsg_char device does not have this problem, because it uses rpmsg_trysend() and rpmsg_poll() to support non-blocking operations. Make it possible to use the same in the RPMSG WWAN driver by adding two new optional wwan_port_ops: - tx_blocking(): send data blocking if allowed - tx_poll(): set additional TX poll flags This integrates nicely with the RPMSG API and does not require any change in existing WWAN drivers. With these changes, the dd example above blocks instead of exiting with an error. Cc: Loic Poulain Signed-off-by: Stephan Gerhold Signed-off-by: David S. Miller --- drivers/net/wwan/rpmsg_wwan_ctrl.c | 23 +++++++++++++++++++++++ drivers/net/wwan/wwan_core.c | 16 ++++++++++++---- include/linux/wwan.h | 13 +++++++++++-- 3 files changed, 46 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/wwan/rpmsg_wwan_ctrl.c b/drivers/net/wwan/rpmsg_wwan_ctrl.c index de226cdb69fd..31c24420ab2e 100644 --- a/drivers/net/wwan/rpmsg_wwan_ctrl.c +++ b/drivers/net/wwan/rpmsg_wwan_ctrl.c @@ -67,10 +67,33 @@ static int rpmsg_wwan_ctrl_tx(struct wwan_port *port, struct sk_buff *skb) return 0; } +static int rpmsg_wwan_ctrl_tx_blocking(struct wwan_port *port, struct sk_buff *skb) +{ + struct rpmsg_wwan_dev *rpwwan = wwan_port_get_drvdata(port); + int ret; + + ret = rpmsg_send(rpwwan->ept, skb->data, skb->len); + if (ret) + return ret; + + consume_skb(skb); + return 0; +} + +static __poll_t rpmsg_wwan_ctrl_tx_poll(struct wwan_port *port, + struct file *filp, poll_table *wait) +{ + struct rpmsg_wwan_dev *rpwwan = wwan_port_get_drvdata(port); + + return rpmsg_poll(rpwwan->ept, filp, wait); +} + static const struct wwan_port_ops rpmsg_wwan_pops = { .start = rpmsg_wwan_ctrl_start, .stop = rpmsg_wwan_ctrl_stop, .tx = rpmsg_wwan_ctrl_tx, + .tx_blocking = rpmsg_wwan_ctrl_tx_blocking, + .tx_poll = rpmsg_wwan_ctrl_tx_poll, }; static struct device *rpmsg_wwan_find_parent(struct device *dev) diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c index 7e728042fc41..165afec1dbd1 100644 --- a/drivers/net/wwan/wwan_core.c +++ b/drivers/net/wwan/wwan_core.c @@ -500,7 +500,8 @@ static void wwan_port_op_stop(struct wwan_port *port) mutex_unlock(&port->ops_lock); } -static int wwan_port_op_tx(struct wwan_port *port, struct sk_buff *skb) +static int wwan_port_op_tx(struct wwan_port *port, struct sk_buff *skb, + bool nonblock) { int ret; @@ -510,7 +511,10 @@ static int wwan_port_op_tx(struct wwan_port *port, struct sk_buff *skb) goto out_unlock; } - ret = port->ops->tx(port, skb); + if (nonblock || !port->ops->tx_blocking) + ret = port->ops->tx(port, skb); + else + ret = port->ops->tx_blocking(port, skb); out_unlock: mutex_unlock(&port->ops_lock); @@ -637,7 +641,7 @@ static ssize_t wwan_port_fops_write(struct file *filp, const char __user *buf, return -EFAULT; } - ret = wwan_port_op_tx(port, skb); + ret = wwan_port_op_tx(port, skb, !!(filp->f_flags & O_NONBLOCK)); if (ret) { kfree_skb(skb); return ret; @@ -653,12 +657,16 @@ static __poll_t wwan_port_fops_poll(struct file *filp, poll_table *wait) poll_wait(filp, &port->waitqueue, wait); - if (!is_write_blocked(port)) + mutex_lock(&port->ops_lock); + if (port->ops && port->ops->tx_poll) + mask |= port->ops->tx_poll(port, filp, wait); + else if (!is_write_blocked(port)) mask |= EPOLLOUT | EPOLLWRNORM; if (!is_read_blocked(port)) mask |= EPOLLIN | EPOLLRDNORM; if (!port->ops) mask |= EPOLLHUP | EPOLLERR; + mutex_unlock(&port->ops_lock); return mask; } diff --git a/include/linux/wwan.h b/include/linux/wwan.h index 430a3a0817de..34222230360c 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -6,6 +6,7 @@ #include #include +#include #include #include @@ -40,15 +41,23 @@ struct wwan_port; /** struct wwan_port_ops - The WWAN port operations * @start: The routine for starting the WWAN port device. * @stop: The routine for stopping the WWAN port device. - * @tx: The routine that sends WWAN port protocol data to the device. + * @tx: Non-blocking routine that sends WWAN port protocol data to the device. + * @tx_blocking: Optional blocking routine that sends WWAN port protocol data + * to the device. + * @tx_poll: Optional routine that sets additional TX poll flags. * * The wwan_port_ops structure contains a list of low-level operations - * that control a WWAN port device. All functions are mandatory. + * that control a WWAN port device. All functions are mandatory unless specified. */ struct wwan_port_ops { int (*start)(struct wwan_port *port); void (*stop)(struct wwan_port *port); int (*tx)(struct wwan_port *port, struct sk_buff *skb); + + /* Optional operations */ + int (*tx_blocking)(struct wwan_port *port, struct sk_buff *skb); + __poll_t (*tx_poll)(struct wwan_port *port, struct file *filp, + poll_table *wait); }; /** -- cgit v1.2.3-71-gd317 From 9f2470fbc4cb4583c080bb729a998933ba61aca4 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 14 Jun 2021 19:13:35 -0700 Subject: skmsg: Improve udp_bpf_recvmsg() accuracy I tried to reuse sk_msg_wait_data() for different protocols, but it turns out it can not be simply reused. For example, UDP actually uses two queues to receive skb: udp_sk(sk)->reader_queue and sk->sk_receive_queue. So we have to check both of them to know whether we have received any packet. Also, UDP does not lock the sock during BH Rx path, it makes no sense for its ->recvmsg() to lock the sock. It is always possible for ->recvmsg() to be called before packets actually arrive in the receive queue, we just use best effort to make it accurate here. Fixes: 1f5be6b3b063 ("udp: Implement udp_bpf_recvmsg() for sockmap") Signed-off-by: Cong Wang Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Acked-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20210615021342.7416-2-xiyou.wangcong@gmail.com --- include/linux/skmsg.h | 2 -- net/core/skmsg.c | 23 ----------------------- net/ipv4/tcp_bpf.c | 24 +++++++++++++++++++++++- net/ipv4/udp_bpf.c | 47 ++++++++++++++++++++++++++++++++++++++++++----- 4 files changed, 65 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index aba0f0f429be..e3d080c299f6 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -126,8 +126,6 @@ int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); -int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags, - long timeo, int *err); int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 43ce17a6a585..f9a81b314e4c 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -399,29 +399,6 @@ out: } EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter); -int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags, - long timeo, int *err) -{ - DEFINE_WAIT_FUNC(wait, woken_wake_function); - int ret = 0; - - if (sk->sk_shutdown & RCV_SHUTDOWN) - return 1; - - if (!timeo) - return ret; - - add_wait_queue(sk_sleep(sk), &wait); - sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); - ret = sk_wait_event(sk, &timeo, - !list_empty(&psock->ingress_msg) || - !skb_queue_empty(&sk->sk_receive_queue), &wait); - sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); - remove_wait_queue(sk_sleep(sk), &wait); - return ret; -} -EXPORT_SYMBOL_GPL(sk_msg_wait_data); - /* Receive sk_msg from psock->ingress_msg to @msg. */ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags) diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index ad9d17923fc5..bb49b52d7be8 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -163,6 +163,28 @@ static bool tcp_bpf_stream_read(const struct sock *sk) return !empty; } +static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags, + long timeo, int *err) +{ + DEFINE_WAIT_FUNC(wait, woken_wake_function); + int ret = 0; + + if (sk->sk_shutdown & RCV_SHUTDOWN) + return 1; + + if (!timeo) + return ret; + + add_wait_queue(sk_sleep(sk), &wait); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); + ret = sk_wait_event(sk, &timeo, + !list_empty(&psock->ingress_msg) || + !skb_queue_empty(&sk->sk_receive_queue), &wait); + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); + remove_wait_queue(sk_sleep(sk), &wait); + return ret; +} + static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len) { @@ -188,7 +210,7 @@ msg_bytes_ready: long timeo; timeo = sock_rcvtimeo(sk, nonblock); - data = sk_msg_wait_data(sk, psock, flags, timeo, &err); + data = tcp_msg_wait_data(sk, psock, flags, timeo, &err); if (data) { if (!sk_psock_queue_empty(psock)) goto msg_bytes_ready; diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c index 954c4591a6fd..565a70040c57 100644 --- a/net/ipv4/udp_bpf.c +++ b/net/ipv4/udp_bpf.c @@ -21,6 +21,45 @@ static int sk_udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, return udp_prot.recvmsg(sk, msg, len, noblock, flags, addr_len); } +static bool udp_sk_has_data(struct sock *sk) +{ + return !skb_queue_empty(&udp_sk(sk)->reader_queue) || + !skb_queue_empty(&sk->sk_receive_queue); +} + +static bool psock_has_data(struct sk_psock *psock) +{ + return !skb_queue_empty(&psock->ingress_skb) || + !sk_psock_queue_empty(psock); +} + +#define udp_msg_has_data(__sk, __psock) \ + ({ udp_sk_has_data(__sk) || psock_has_data(__psock); }) + +static int udp_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags, + long timeo, int *err) +{ + DEFINE_WAIT_FUNC(wait, woken_wake_function); + int ret = 0; + + if (sk->sk_shutdown & RCV_SHUTDOWN) + return 1; + + if (!timeo) + return ret; + + add_wait_queue(sk_sleep(sk), &wait); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); + ret = udp_msg_has_data(sk, psock); + if (!ret) { + wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); + ret = udp_msg_has_data(sk, psock); + } + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); + remove_wait_queue(sk_sleep(sk), &wait); + return ret; +} + static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len) { @@ -34,8 +73,7 @@ static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, if (unlikely(!psock)) return sk_udp_recvmsg(sk, msg, len, nonblock, flags, addr_len); - lock_sock(sk); - if (sk_psock_queue_empty(psock)) { + if (!psock_has_data(psock)) { ret = sk_udp_recvmsg(sk, msg, len, nonblock, flags, addr_len); goto out; } @@ -47,9 +85,9 @@ msg_bytes_ready: long timeo; timeo = sock_rcvtimeo(sk, nonblock); - data = sk_msg_wait_data(sk, psock, flags, timeo, &err); + data = udp_msg_wait_data(sk, psock, flags, timeo, &err); if (data) { - if (!sk_psock_queue_empty(psock)) + if (psock_has_data(psock)) goto msg_bytes_ready; ret = sk_udp_recvmsg(sk, msg, len, nonblock, flags, addr_len); goto out; @@ -62,7 +100,6 @@ msg_bytes_ready: } ret = copied; out: - release_sock(sk); sk_psock_put(sk, psock); return ret; } -- cgit v1.2.3-71-gd317 From a3fa449ffcf5bcf9c3dddf62c11599cdc79ef54a Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Mon, 21 Jun 2021 22:08:49 +0200 Subject: net: handle ARPHRD_IP6GRE in dev_is_mac_header_xmit() Similar to commit 3b707c3008ca ("net: dev_is_mac_header_xmit() true for ARPHRD_RAWIP"), add ARPHRD_IP6GRE to dev_is_mac_header_xmit(), to make ip6gre compatible with act_mirred and __bpf_redirect(). Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- include/linux/if_arp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h index bf5c5f32c65e..b712217f7030 100644 --- a/include/linux/if_arp.h +++ b/include/linux/if_arp.h @@ -48,6 +48,7 @@ static inline bool dev_is_mac_header_xmit(const struct net_device *dev) case ARPHRD_TUNNEL6: case ARPHRD_SIT: case ARPHRD_IPGRE: + case ARPHRD_IP6GRE: case ARPHRD_VOID: case ARPHRD_NONE: case ARPHRD_RAWIP: -- cgit v1.2.3-71-gd317 From 62a6ef6a996f5eec73d30d079573a1fa8f95fcd9 Mon Sep 17 00:00:00 2001 From: Marcin Wojtas Date: Mon, 21 Jun 2021 19:30:24 +0200 Subject: net: mdiobus: Introduce fwnode_mdbiobus_register() This patch introduces a new helper function that wraps acpi_/of_ mdiobus_register() and allows its usage via common fwnode_ interface. Fall back to raw mdiobus_register() in case CONFIG_FWNODE_MDIO is not enabled, in order to satisfy compatibility in all future user drivers. Signed-off-by: Marcin Wojtas Signed-off-by: David S. Miller --- drivers/net/mdio/fwnode_mdio.c | 22 ++++++++++++++++++++++ include/linux/fwnode_mdio.h | 12 ++++++++++++ 2 files changed, 34 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/mdio/fwnode_mdio.c b/drivers/net/mdio/fwnode_mdio.c index 1becb1a731f6..ae0bf71a9932 100644 --- a/drivers/net/mdio/fwnode_mdio.c +++ b/drivers/net/mdio/fwnode_mdio.c @@ -7,8 +7,10 @@ */ #include +#include #include #include +#include #include MODULE_AUTHOR("Calvin Johnson "); @@ -142,3 +144,23 @@ int fwnode_mdiobus_register_phy(struct mii_bus *bus, return 0; } EXPORT_SYMBOL(fwnode_mdiobus_register_phy); + +/** + * fwnode_mdiobus_register - bring up all the PHYs on a given MDIO bus and + * attach them to it. + * @bus: Target MDIO bus. + * @fwnode: Pointer to fwnode of the MDIO controller. + * + * Return values are determined accordingly to acpi_/of_ mdiobus_register() + * operation. + */ +int fwnode_mdiobus_register(struct mii_bus *bus, struct fwnode_handle *fwnode) +{ + if (is_acpi_node(fwnode)) + return acpi_mdiobus_register(bus, fwnode); + else if (is_of_node(fwnode)) + return of_mdiobus_register(bus, to_of_node(fwnode)); + else + return -EINVAL; +} +EXPORT_SYMBOL(fwnode_mdiobus_register); diff --git a/include/linux/fwnode_mdio.h b/include/linux/fwnode_mdio.h index faf603c48c86..13d4ae8fee0a 100644 --- a/include/linux/fwnode_mdio.h +++ b/include/linux/fwnode_mdio.h @@ -16,6 +16,7 @@ int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, int fwnode_mdiobus_register_phy(struct mii_bus *bus, struct fwnode_handle *child, u32 addr); +int fwnode_mdiobus_register(struct mii_bus *bus, struct fwnode_handle *fwnode); #else /* CONFIG_FWNODE_MDIO */ int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, struct phy_device *phy, @@ -30,6 +31,17 @@ static inline int fwnode_mdiobus_register_phy(struct mii_bus *bus, { return -EINVAL; } + +static inline int fwnode_mdiobus_register(struct mii_bus *bus, + struct fwnode_handle *fwnode) +{ + /* + * Fall back to mdiobus_register() function to register a bus. + * This way, we don't have to keep compat bits around in drivers. + */ + + return mdiobus_register(mdio); +} #endif #endif /* __LINUX_FWNODE_MDIO_H */ -- cgit v1.2.3-71-gd317 From 9f0248ea476ee59d336d7c8bf1a5d0919d93d030 Mon Sep 17 00:00:00 2001 From: Sergey Ryazanov Date: Tue, 22 Jun 2021 01:50:57 +0300 Subject: wwan: core: no more hold netdev ops owning module The WWAN netdev ops owner holding was used to protect from the unexpected memory disappear. This approach causes a dependency cycle (driver -> core -> driver) and effectively prevents a WWAN driver unloading. E.g. WWAN hwsim could not be unloaded until all simulated devices are removed: ~# modprobe wwan_hwsim devices=2 ~# lsmod | grep wwan wwan_hwsim 16384 2 wwan 20480 1 wwan_hwsim ~# rmmod wwan_hwsim rmmod: ERROR: Module wwan_hwsim is in use ~# echo > /sys/kernel/debug/wwan_hwsim/hwsim0/destroy ~# echo > /sys/kernel/debug/wwan_hwsim/hwsim1/destroy ~# lsmod | grep wwan wwan_hwsim 16384 0 wwan 20480 1 wwan_hwsim ~# rmmod wwan_hwsim For a real device driver this will cause an inability to unload module until a served device is physically detached. Since the last commit we are removing all child netdev(s) when a driver unregister the netdev ops. This allows us to permit the driver unloading, since any sane driver will call ops unregistering on a device deinitialization. So, remove the holding of an ops owner to make it easier to unload a driver module. The owner field has also beed removed from the ops structure as there are no more users of this field. Signed-off-by: Sergey Ryazanov Reviewed-by: Loic Poulain Signed-off-by: David S. Miller --- drivers/net/mhi/net.c | 3 +-- drivers/net/wwan/wwan_core.c | 10 ---------- drivers/net/wwan/wwan_hwsim.c | 1 - include/linux/wwan.h | 2 -- 4 files changed, 1 insertion(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/mhi/net.c b/drivers/net/mhi/net.c index 6aa753387372..ffd1c01b3f35 100644 --- a/drivers/net/mhi/net.c +++ b/drivers/net/mhi/net.c @@ -383,7 +383,6 @@ static void mhi_net_dellink(void *ctxt, struct net_device *ndev, } static const struct wwan_ops mhi_wwan_ops = { - .owner = THIS_MODULE, .priv_size = sizeof(struct mhi_net_dev), .setup = mhi_net_setup, .newlink = mhi_net_newlink, @@ -436,7 +435,7 @@ static void mhi_net_remove(struct mhi_device *mhi_dev) struct mhi_net_dev *mhi_netdev = dev_get_drvdata(&mhi_dev->dev); struct mhi_controller *cntrl = mhi_dev->mhi_cntrl; - /* rtnetlink takes care of removing remaining links */ + /* WWAN core takes care of removing remaining links */ wwan_unregister_ops(&cntrl->mhi_dev->dev); if (create_default_iface) diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c index ec6a69b23dd1..b634a0ba1196 100644 --- a/drivers/net/wwan/wwan_core.c +++ b/drivers/net/wwan/wwan_core.c @@ -929,11 +929,6 @@ int wwan_register_ops(struct device *parent, const struct wwan_ops *ops, return -EBUSY; } - if (!try_module_get(ops->owner)) { - wwan_remove_dev(wwandev); - return -ENODEV; - } - wwandev->ops = ops; wwandev->ops_ctxt = ctxt; @@ -960,7 +955,6 @@ static int wwan_child_dellink(struct device *dev, void *data) void wwan_unregister_ops(struct device *parent) { struct wwan_device *wwandev = wwan_dev_get_by_parent(parent); - struct module *owner; LIST_HEAD(kill_list); if (WARN_ON(IS_ERR(wwandev))) @@ -976,8 +970,6 @@ void wwan_unregister_ops(struct device *parent) */ put_device(&wwandev->dev); - owner = wwandev->ops->owner; /* Preserve ops owner */ - rtnl_lock(); /* Prevent concurent netdev(s) creation/destroying */ /* Remove all child netdev(s), using batch removing */ @@ -989,8 +981,6 @@ void wwan_unregister_ops(struct device *parent) rtnl_unlock(); - module_put(owner); - wwandev->ops_ctxt = NULL; wwan_remove_dev(wwandev); } diff --git a/drivers/net/wwan/wwan_hwsim.c b/drivers/net/wwan/wwan_hwsim.c index c1e850b9c087..a8582a58a385 100644 --- a/drivers/net/wwan/wwan_hwsim.c +++ b/drivers/net/wwan/wwan_hwsim.c @@ -94,7 +94,6 @@ static void wwan_hwsim_netdev_setup(struct net_device *ndev) } static const struct wwan_ops wwan_hwsim_wwan_rtnl_ops = { - .owner = THIS_MODULE, .priv_size = 0, /* No private data */ .setup = wwan_hwsim_netdev_setup, }; diff --git a/include/linux/wwan.h b/include/linux/wwan.h index 34222230360c..e1981ea3a2fd 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -128,14 +128,12 @@ void *wwan_port_get_drvdata(struct wwan_port *port); /** * struct wwan_ops - WWAN device ops - * @owner: module owner of the WWAN ops * @priv_size: size of private netdev data area * @setup: set up a new netdev * @newlink: register the new netdev * @dellink: remove the given netdev */ struct wwan_ops { - struct module *owner; unsigned int priv_size; void (*setup)(struct net_device *dev); int (*newlink)(void *ctxt, struct net_device *dev, -- cgit v1.2.3-71-gd317 From ca374290aaade741a4781ae5f6e1ba7515e4e5fa Mon Sep 17 00:00:00 2001 From: Sergey Ryazanov Date: Tue, 22 Jun 2021 01:50:58 +0300 Subject: wwan: core: support default netdev creation Most, if not each WWAN device driver will create a netdev for the default data channel. Therefore, add an option for the WWAN netdev ops registration function to create a default netdev for the WWAN device. A WWAN device driver should pass a default data channel link id to the ops registering function to request the creation of a default netdev, or a special value WWAN_NO_DEFAULT_LINK to inform the WWAN core that the default netdev should not be created. For now, only wwan_hwsim utilize the default link creation option. Other drivers will be reworked next. Signed-off-by: Sergey Ryazanov CC: M Chetan Kumar CC: Intel Corporation Signed-off-by: David S. Miller --- drivers/net/mhi/net.c | 3 +- drivers/net/wwan/iosm/iosm_ipc_wwan.c | 3 +- drivers/net/wwan/wwan_core.c | 75 ++++++++++++++++++++++++++++++++++- drivers/net/wwan/wwan_hwsim.c | 2 +- include/linux/wwan.h | 8 +++- 5 files changed, 86 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/mhi/net.c b/drivers/net/mhi/net.c index ffd1c01b3f35..f36ca5c0dfe9 100644 --- a/drivers/net/mhi/net.c +++ b/drivers/net/mhi/net.c @@ -397,7 +397,8 @@ static int mhi_net_probe(struct mhi_device *mhi_dev, struct net_device *ndev; int err; - err = wwan_register_ops(&cntrl->mhi_dev->dev, &mhi_wwan_ops, mhi_dev); + err = wwan_register_ops(&cntrl->mhi_dev->dev, &mhi_wwan_ops, mhi_dev, + WWAN_NO_DEFAULT_LINK); if (err) return err; diff --git a/drivers/net/wwan/iosm/iosm_ipc_wwan.c b/drivers/net/wwan/iosm/iosm_ipc_wwan.c index bee9b278223d..adb2bd40a404 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_wwan.c +++ b/drivers/net/wwan/iosm/iosm_ipc_wwan.c @@ -317,7 +317,8 @@ struct iosm_wwan *ipc_wwan_init(struct iosm_imem *ipc_imem, struct device *dev) ipc_wwan->dev = dev; ipc_wwan->ipc_imem = ipc_imem; - if (wwan_register_ops(ipc_wwan->dev, &iosm_wwan_ops, ipc_wwan)) { + if (wwan_register_ops(ipc_wwan->dev, &iosm_wwan_ops, ipc_wwan, + WWAN_NO_DEFAULT_LINK)) { kfree(ipc_wwan); return NULL; } diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c index b634a0ba1196..ef6ec641d877 100644 --- a/drivers/net/wwan/wwan_core.c +++ b/drivers/net/wwan/wwan_core.c @@ -903,17 +903,81 @@ static struct rtnl_link_ops wwan_rtnl_link_ops __read_mostly = { .policy = wwan_rtnl_policy, }; +static void wwan_create_default_link(struct wwan_device *wwandev, + u32 def_link_id) +{ + struct nlattr *tb[IFLA_MAX + 1], *linkinfo[IFLA_INFO_MAX + 1]; + struct nlattr *data[IFLA_WWAN_MAX + 1]; + struct net_device *dev; + struct nlmsghdr *nlh; + struct sk_buff *msg; + + /* Forge attributes required to create a WWAN netdev. We first + * build a netlink message and then parse it. This looks + * odd, but such approach is less error prone. + */ + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (WARN_ON(!msg)) + return; + nlh = nlmsg_put(msg, 0, 0, RTM_NEWLINK, 0, 0); + if (WARN_ON(!nlh)) + goto free_attrs; + + if (nla_put_string(msg, IFLA_PARENT_DEV_NAME, dev_name(&wwandev->dev))) + goto free_attrs; + tb[IFLA_LINKINFO] = nla_nest_start(msg, IFLA_LINKINFO); + if (!tb[IFLA_LINKINFO]) + goto free_attrs; + linkinfo[IFLA_INFO_DATA] = nla_nest_start(msg, IFLA_INFO_DATA); + if (!linkinfo[IFLA_INFO_DATA]) + goto free_attrs; + if (nla_put_u32(msg, IFLA_WWAN_LINK_ID, def_link_id)) + goto free_attrs; + nla_nest_end(msg, linkinfo[IFLA_INFO_DATA]); + nla_nest_end(msg, tb[IFLA_LINKINFO]); + + nlmsg_end(msg, nlh); + + /* The next three parsing calls can not fail */ + nlmsg_parse_deprecated(nlh, 0, tb, IFLA_MAX, NULL, NULL); + nla_parse_nested_deprecated(linkinfo, IFLA_INFO_MAX, tb[IFLA_LINKINFO], + NULL, NULL); + nla_parse_nested_deprecated(data, IFLA_WWAN_MAX, + linkinfo[IFLA_INFO_DATA], NULL, NULL); + + rtnl_lock(); + + dev = rtnl_create_link(&init_net, "wwan%d", NET_NAME_ENUM, + &wwan_rtnl_link_ops, tb, NULL); + if (WARN_ON(IS_ERR(dev))) + goto unlock; + + if (WARN_ON(wwan_rtnl_newlink(&init_net, dev, tb, data, NULL))) { + free_netdev(dev); + goto unlock; + } + +unlock: + rtnl_unlock(); + +free_attrs: + nlmsg_free(msg); +} + /** * wwan_register_ops - register WWAN device ops * @parent: Device to use as parent and shared by all WWAN ports and * created netdevs * @ops: operations to register * @ctxt: context to pass to operations + * @def_link_id: id of the default link that will be automatically created by + * the WWAN core for the WWAN device. The default link will not be created + * if the passed value is WWAN_NO_DEFAULT_LINK. * * Returns: 0 on success, a negative error code on failure */ int wwan_register_ops(struct device *parent, const struct wwan_ops *ops, - void *ctxt) + void *ctxt, u32 def_link_id) { struct wwan_device *wwandev; @@ -932,6 +996,15 @@ int wwan_register_ops(struct device *parent, const struct wwan_ops *ops, wwandev->ops = ops; wwandev->ops_ctxt = ctxt; + /* NB: we do not abort ops registration in case of default link + * creation failure. Link ops is the management interface, while the + * default link creation is a service option. And we should not prevent + * a user from manually creating a link latter if service option failed + * now. + */ + if (def_link_id != WWAN_NO_DEFAULT_LINK) + wwan_create_default_link(wwandev, def_link_id); + return 0; } EXPORT_SYMBOL_GPL(wwan_register_ops); diff --git a/drivers/net/wwan/wwan_hwsim.c b/drivers/net/wwan/wwan_hwsim.c index a8582a58a385..5b62cf3b3c42 100644 --- a/drivers/net/wwan/wwan_hwsim.c +++ b/drivers/net/wwan/wwan_hwsim.c @@ -288,7 +288,7 @@ static struct wwan_hwsim_dev *wwan_hwsim_dev_new(void) INIT_WORK(&dev->del_work, wwan_hwsim_dev_del_work); - err = wwan_register_ops(&dev->dev, &wwan_hwsim_wwan_rtnl_ops, dev); + err = wwan_register_ops(&dev->dev, &wwan_hwsim_wwan_rtnl_ops, dev, 1); if (err) goto err_unreg_dev; diff --git a/include/linux/wwan.h b/include/linux/wwan.h index e1981ea3a2fd..91590db70a12 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -126,6 +126,12 @@ void wwan_port_txon(struct wwan_port *port); */ void *wwan_port_get_drvdata(struct wwan_port *port); +/* + * Used to indicate that the WWAN core should not create a default network + * link. + */ +#define WWAN_NO_DEFAULT_LINK U32_MAX + /** * struct wwan_ops - WWAN device ops * @priv_size: size of private netdev data area @@ -143,7 +149,7 @@ struct wwan_ops { }; int wwan_register_ops(struct device *parent, const struct wwan_ops *ops, - void *ctxt); + void *ctxt, u32 def_link_id); void wwan_unregister_ops(struct device *parent); -- cgit v1.2.3-71-gd317 From 699409240389c2994e5fa1cb7d7599129bc7cfdf Mon Sep 17 00:00:00 2001 From: Sergey Ryazanov Date: Tue, 22 Jun 2021 01:51:00 +0300 Subject: wwan: core: add WWAN common private data for netdev The WWAN core not only multiplex the netdev configuration data, but process it too, and needs some space to store its private data associated with the netdev. Add a structure to keep common WWAN core data. The structure will be stored inside the netdev private data before WWAN driver private data and have a field to make it easier to access the driver data. Also add a helper function that simplifies drivers access to their data. At the moment we use the common WWAN private data to store the WWAN data link (channel) id at the time the link is created, and report it back to user using the .fill_info() RTNL callback. This should help the user to be aware which network interface is bound to which WWAN device data channel. Signed-off-by: Sergey Ryazanov CC: M Chetan Kumar CC: Intel Corporation Signed-off-by: David S. Miller --- drivers/net/mhi/net.c | 12 ++++++------ drivers/net/mhi/proto_mbim.c | 5 +++-- drivers/net/wwan/iosm/iosm_ipc_wwan.c | 12 ++++++------ drivers/net/wwan/wwan_core.c | 29 ++++++++++++++++++++++++++++- include/linux/wwan.h | 18 ++++++++++++++++++ 5 files changed, 61 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/mhi/net.c b/drivers/net/mhi/net.c index f36ca5c0dfe9..e60e38c1f09d 100644 --- a/drivers/net/mhi/net.c +++ b/drivers/net/mhi/net.c @@ -32,7 +32,7 @@ struct mhi_device_info { static int mhi_ndo_open(struct net_device *ndev) { - struct mhi_net_dev *mhi_netdev = netdev_priv(ndev); + struct mhi_net_dev *mhi_netdev = wwan_netdev_drvpriv(ndev); /* Feed the rx buffer pool */ schedule_delayed_work(&mhi_netdev->rx_refill, 0); @@ -47,7 +47,7 @@ static int mhi_ndo_open(struct net_device *ndev) static int mhi_ndo_stop(struct net_device *ndev) { - struct mhi_net_dev *mhi_netdev = netdev_priv(ndev); + struct mhi_net_dev *mhi_netdev = wwan_netdev_drvpriv(ndev); netif_stop_queue(ndev); netif_carrier_off(ndev); @@ -58,7 +58,7 @@ static int mhi_ndo_stop(struct net_device *ndev) static netdev_tx_t mhi_ndo_xmit(struct sk_buff *skb, struct net_device *ndev) { - struct mhi_net_dev *mhi_netdev = netdev_priv(ndev); + struct mhi_net_dev *mhi_netdev = wwan_netdev_drvpriv(ndev); const struct mhi_net_proto *proto = mhi_netdev->proto; struct mhi_device *mdev = mhi_netdev->mdev; int err; @@ -93,7 +93,7 @@ exit_drop: static void mhi_ndo_get_stats64(struct net_device *ndev, struct rtnl_link_stats64 *stats) { - struct mhi_net_dev *mhi_netdev = netdev_priv(ndev); + struct mhi_net_dev *mhi_netdev = wwan_netdev_drvpriv(ndev); unsigned int start; do { @@ -322,7 +322,7 @@ static int mhi_net_newlink(void *ctxt, struct net_device *ndev, u32 if_id, if (dev_get_drvdata(&mhi_dev->dev)) return -EBUSY; - mhi_netdev = netdev_priv(ndev); + mhi_netdev = wwan_netdev_drvpriv(ndev); dev_set_drvdata(&mhi_dev->dev, mhi_netdev); mhi_netdev->ndev = ndev; @@ -367,7 +367,7 @@ out_err: static void mhi_net_dellink(void *ctxt, struct net_device *ndev, struct list_head *head) { - struct mhi_net_dev *mhi_netdev = netdev_priv(ndev); + struct mhi_net_dev *mhi_netdev = wwan_netdev_drvpriv(ndev); struct mhi_device *mhi_dev = ctxt; if (head) diff --git a/drivers/net/mhi/proto_mbim.c b/drivers/net/mhi/proto_mbim.c index fc72b3f6ec9e..bf1ad863237d 100644 --- a/drivers/net/mhi/proto_mbim.c +++ b/drivers/net/mhi/proto_mbim.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -56,7 +57,7 @@ static void __mbim_errors_inc(struct mhi_net_dev *dev) static int mbim_rx_verify_nth16(struct sk_buff *skb) { - struct mhi_net_dev *dev = netdev_priv(skb->dev); + struct mhi_net_dev *dev = wwan_netdev_drvpriv(skb->dev); struct mbim_context *ctx = dev->proto_data; struct usb_cdc_ncm_nth16 *nth16; int len; @@ -102,7 +103,7 @@ static int mbim_rx_verify_nth16(struct sk_buff *skb) static int mbim_rx_verify_ndp16(struct sk_buff *skb, struct usb_cdc_ncm_ndp16 *ndp16) { - struct mhi_net_dev *dev = netdev_priv(skb->dev); + struct mhi_net_dev *dev = wwan_netdev_drvpriv(skb->dev); int ret; if (le16_to_cpu(ndp16->wLength) < USB_CDC_NCM_NDP16_LENGTH_MIN) { diff --git a/drivers/net/wwan/iosm/iosm_ipc_wwan.c b/drivers/net/wwan/iosm/iosm_ipc_wwan.c index d3cb28107836..c999c64001f4 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_wwan.c +++ b/drivers/net/wwan/iosm/iosm_ipc_wwan.c @@ -20,7 +20,7 @@ #define IOSM_IF_ID_PAYLOAD 2 /** - * struct iosm_netdev_priv - netdev private data + * struct iosm_netdev_priv - netdev WWAN driver specific private data * @ipc_wwan: Pointer to iosm_wwan struct * @netdev: Pointer to network interface device structure * @if_id: Interface id for device. @@ -51,7 +51,7 @@ struct iosm_wwan { /* Bring-up the wwan net link */ static int ipc_wwan_link_open(struct net_device *netdev) { - struct iosm_netdev_priv *priv = netdev_priv(netdev); + struct iosm_netdev_priv *priv = wwan_netdev_drvpriv(netdev); struct iosm_wwan *ipc_wwan = priv->ipc_wwan; int if_id = priv->if_id; int ret; @@ -88,7 +88,7 @@ out: /* Bring-down the wwan net link */ static int ipc_wwan_link_stop(struct net_device *netdev) { - struct iosm_netdev_priv *priv = netdev_priv(netdev); + struct iosm_netdev_priv *priv = wwan_netdev_drvpriv(netdev); netif_stop_queue(netdev); @@ -105,7 +105,7 @@ static int ipc_wwan_link_stop(struct net_device *netdev) static int ipc_wwan_link_transmit(struct sk_buff *skb, struct net_device *netdev) { - struct iosm_netdev_priv *priv = netdev_priv(netdev); + struct iosm_netdev_priv *priv = wwan_netdev_drvpriv(netdev); struct iosm_wwan *ipc_wwan = priv->ipc_wwan; int if_id = priv->if_id; int ret; @@ -178,7 +178,7 @@ static int ipc_wwan_newlink(void *ctxt, struct net_device *dev, if_id >= ARRAY_SIZE(ipc_wwan->sub_netlist)) return -EINVAL; - priv = netdev_priv(dev); + priv = wwan_netdev_drvpriv(dev); priv->if_id = if_id; priv->netdev = dev; priv->ipc_wwan = ipc_wwan; @@ -208,8 +208,8 @@ out_unlock: static void ipc_wwan_dellink(void *ctxt, struct net_device *dev, struct list_head *head) { + struct iosm_netdev_priv *priv = wwan_netdev_drvpriv(dev); struct iosm_wwan *ipc_wwan = ctxt; - struct iosm_netdev_priv *priv = netdev_priv(dev); int if_id = priv->if_id; if (WARN_ON(if_id < IP_MUX_SESSION_START || diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c index ef6ec641d877..3e16c318e705 100644 --- a/drivers/net/wwan/wwan_core.c +++ b/drivers/net/wwan/wwan_core.c @@ -815,6 +815,7 @@ static struct net_device *wwan_rtnl_alloc(struct nlattr *tb[], const char *devname = nla_data(tb[IFLA_PARENT_DEV_NAME]); struct wwan_device *wwandev = wwan_dev_get_by_name(devname); struct net_device *dev; + unsigned int priv_size; if (IS_ERR(wwandev)) return ERR_CAST(wwandev); @@ -825,7 +826,8 @@ static struct net_device *wwan_rtnl_alloc(struct nlattr *tb[], goto out; } - dev = alloc_netdev_mqs(wwandev->ops->priv_size, ifname, name_assign_type, + priv_size = sizeof(struct wwan_netdev_priv) + wwandev->ops->priv_size; + dev = alloc_netdev_mqs(priv_size, ifname, name_assign_type, wwandev->ops->setup, num_tx_queues, num_rx_queues); if (dev) { @@ -845,6 +847,7 @@ static int wwan_rtnl_newlink(struct net *src_net, struct net_device *dev, { struct wwan_device *wwandev = wwan_dev_get_by_parent(dev->dev.parent); u32 link_id = nla_get_u32(data[IFLA_WWAN_LINK_ID]); + struct wwan_netdev_priv *priv = netdev_priv(dev); int ret; if (IS_ERR(wwandev)) @@ -856,6 +859,7 @@ static int wwan_rtnl_newlink(struct net *src_net, struct net_device *dev, goto out; } + priv->link_id = link_id; if (wwandev->ops->newlink) ret = wwandev->ops->newlink(wwandev->ops_ctxt, dev, link_id, extack); @@ -889,6 +893,27 @@ out: put_device(&wwandev->dev); } +static size_t wwan_rtnl_get_size(const struct net_device *dev) +{ + return + nla_total_size(4) + /* IFLA_WWAN_LINK_ID */ + 0; +} + +static int wwan_rtnl_fill_info(struct sk_buff *skb, + const struct net_device *dev) +{ + struct wwan_netdev_priv *priv = netdev_priv(dev); + + if (nla_put_u32(skb, IFLA_WWAN_LINK_ID, priv->link_id)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + static const struct nla_policy wwan_rtnl_policy[IFLA_WWAN_MAX + 1] = { [IFLA_WWAN_LINK_ID] = { .type = NLA_U32 }, }; @@ -900,6 +925,8 @@ static struct rtnl_link_ops wwan_rtnl_link_ops __read_mostly = { .validate = wwan_rtnl_validate, .newlink = wwan_rtnl_newlink, .dellink = wwan_rtnl_dellink, + .get_size = wwan_rtnl_get_size, + .fill_info = wwan_rtnl_fill_info, .policy = wwan_rtnl_policy, }; diff --git a/include/linux/wwan.h b/include/linux/wwan.h index 91590db70a12..9fac819f92e3 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -9,6 +9,7 @@ #include #include #include +#include /** * enum wwan_port_type - WWAN port types @@ -126,6 +127,23 @@ void wwan_port_txon(struct wwan_port *port); */ void *wwan_port_get_drvdata(struct wwan_port *port); +/** + * struct wwan_netdev_priv - WWAN core network device private data + * @link_id: WWAN device data link id + * @drv_priv: driver private data area, size is determined in &wwan_ops + */ +struct wwan_netdev_priv { + u32 link_id; + + /* must be last */ + u8 drv_priv[] __aligned(sizeof(void *)); +}; + +static inline void *wwan_netdev_drvpriv(struct net_device *dev) +{ + return ((struct wwan_netdev_priv *)netdev_priv(dev))->drv_priv; +} + /* * Used to indicate that the WWAN core should not create a default network * link. -- cgit v1.2.3-71-gd317 From b8c48be23c2d03834fe01c3ea757d9df8b97013d Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 22 Jun 2021 09:50:50 +0300 Subject: ethtool: Use kernel data types for internal EEPROM struct The struct is not visible to user space and therefore should not use the user visible data types. Instead, use internal data types like other structures in the file. Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/ethtool.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index e030f7510cd3..29dbb603bc91 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -401,12 +401,12 @@ struct ethtool_rmon_stats { * required information to the driver. */ struct ethtool_module_eeprom { - __u32 offset; - __u32 length; - __u8 page; - __u8 bank; - __u8 i2c_address; - __u8 *data; + u32 offset; + u32 length; + u8 page; + u8 bank; + u8 i2c_address; + u8 *data; }; /** -- cgit v1.2.3-71-gd317 From 745a32117b5a0799ce1dd28d5a74dc2b7bf37692 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 22 Jun 2021 14:04:47 -0400 Subject: sctp: add pad chunk and its make function and event table This chunk is defined in rfc4820#section-3, and used to pad an SCTP packet. The receiver must discard this chunk and continue processing the rest of the chunks in the packet. Add it now, as it will be bundled with a heartbeat chunk to probe pmtu in the following patches. Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/linux/sctp.h | 7 +++++++ include/net/sctp/sm.h | 1 + net/sctp/sm_make_chunk.c | 26 ++++++++++++++++++++++++++ net/sctp/sm_statetable.c | 23 +++++++++++++++++++++++ 4 files changed, 57 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index bb1926589693..a86e852507b3 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -98,6 +98,7 @@ enum sctp_cid { SCTP_CID_I_FWD_TSN = 0xC2, SCTP_CID_ASCONF_ACK = 0x80, SCTP_CID_RECONF = 0x82, + SCTP_CID_PAD = 0x84, }; /* enum */ @@ -410,6 +411,12 @@ struct sctp_heartbeat_chunk { }; +/* PAD chunk could be bundled with heartbeat chunk to probe pmtu */ +struct sctp_pad_chunk { + struct sctp_chunkhdr uh; +}; + + /* For the abort and shutdown ACK we must carry the init tag in the * common header. Just the common header is all that is needed with a * chunk descriptor. diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index fd223c94589a..09c59154634d 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -230,6 +230,7 @@ struct sctp_chunk *sctp_make_heartbeat_ack(const struct sctp_association *asoc, const struct sctp_chunk *chunk, const void *payload, const size_t paylen); +struct sctp_chunk *sctp_make_pad(const struct sctp_association *asoc, int len); struct sctp_chunk *sctp_make_op_error(const struct sctp_association *asoc, const struct sctp_chunk *chunk, __be16 cause_code, const void *payload, diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 5b44d228b6ca..e5d470cd7c40 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1218,6 +1218,32 @@ nodata: return retval; } +/* RFC4820 3. Padding Chunk (PAD) + * 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 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Type = 0x84 | Flags=0 | Length | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | | + * \ Padding Data / + * / \ + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + */ +struct sctp_chunk *sctp_make_pad(const struct sctp_association *asoc, int len) +{ + struct sctp_chunk *retval; + + retval = sctp_make_control(asoc, SCTP_CID_PAD, 0, len, GFP_ATOMIC); + if (!retval) + return NULL; + + skb_put_zero(retval->skb, len); + retval->chunk_hdr->length = htons(ntohs(retval->chunk_hdr->length) + len); + retval->chunk_end = skb_tail_pointer(retval->skb); + + return retval; +} + /* Create an Operation Error chunk with the specified space reserved. * This routine can be used for containing multiple causes in the chunk. */ diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c index 88ea87f4f0e7..c82c4233ec6b 100644 --- a/net/sctp/sm_statetable.c +++ b/net/sctp/sm_statetable.c @@ -526,6 +526,26 @@ auth_chunk_event_table[SCTP_NUM_AUTH_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_AUTH, }; /*state_fn_t auth_chunk_event_table[][] */ +static const struct sctp_sm_table_entry +pad_chunk_event_table[SCTP_STATE_NUM_STATES] = { + /* SCTP_STATE_CLOSED */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_COOKIE_WAIT */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_COOKIE_ECHOED */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_ESTABLISHED */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_SHUTDOWN_PENDING */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_SHUTDOWN_SENT */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_SHUTDOWN_RECEIVED */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_SHUTDOWN_ACK_SENT */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), +}; /* chunk pad */ + static const struct sctp_sm_table_entry chunk_event_table_unknown[SCTP_STATE_NUM_STATES] = { /* SCTP_STATE_CLOSED */ @@ -992,6 +1012,9 @@ static const struct sctp_sm_table_entry *sctp_chunk_event_lookup( case SCTP_CID_AUTH: return &auth_chunk_event_table[0][state]; + + case SCTP_CID_PAD: + return &pad_chunk_event_table[state]; } return &chunk_event_table_unknown[state]; -- cgit v1.2.3-71-gd317 From 1806239dec0dacde373f0b53f076319f6c6d95cb Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 19 Jun 2021 15:36:30 +0200 Subject: ieee80211: add the value for Category '6' in "rtw_ieee80211_category" Preparation work for removing the "enum rtw_ieee80211_category" in "drivers/staging/rtl8188eu/include/ieee80211.h" and "drivers/staging/rtl8723bs/include/ieee80211.h". This enum is similar to "enum ieee80211_category" from "include/linux/ieee80211.h". However it defines the value '6' as RTW_WLAN_CATEGORY_FT. So add a corresponding value in "ieee80211_category" Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/66be0187869bd7dae1c0b0785a32db695ee9872e.1624108556.git.christophe.jaillet@wanadoo.fr Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 2967437f1b11..67f3e51e7ecc 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2933,6 +2933,7 @@ enum ieee80211_category { WLAN_CATEGORY_BACK = 3, WLAN_CATEGORY_PUBLIC = 4, WLAN_CATEGORY_RADIO_MEASUREMENT = 5, + WLAN_CATEGORY_FAST_BBS_TRANSITION = 6, WLAN_CATEGORY_HT = 7, WLAN_CATEGORY_SA_QUERY = 8, WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION = 9, -- cgit v1.2.3-71-gd317 From 7da70d6cdf0dbc2c62e4a5759db9b63ef8d90c32 Mon Sep 17 00:00:00 2001 From: Krishnanand Prabhu Date: Fri, 18 Jun 2021 13:41:28 +0300 Subject: ieee80211: define timing measurement in extended capabilities IE Define the bit used for timing measurement support in extended capabilities IE, used for time synchronization. Signed-off-by: Krishnanand Prabhu Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20210618133832.b75f40765538.I92b50e43e29272c97d17ed5f37f216f4caf0f205@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 67f3e51e7ecc..0a0aaa2d5d9e 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -9,7 +9,7 @@ * Copyright (c) 2006, Michael Wu * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH * Copyright (c) 2016 - 2017 Intel Deutschland GmbH - * Copyright (c) 2018 - 2020 Intel Corporation + * Copyright (c) 2018 - 2021 Intel Corporation */ #ifndef LINUX_IEEE80211_H @@ -3111,6 +3111,11 @@ enum ieee80211_tdls_actioncode { */ #define WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT BIT(6) +/* Timing Measurement protocol for time sync is set in the 7th bit of 3rd byte + * of the @WLAN_EID_EXT_CAPABILITY information element + */ +#define WLAN_EXT_CAPA3_TIMING_MEASUREMENT_SUPPORT BIT(7) + /* TDLS capabilities in the 4th byte of @WLAN_EID_EXT_CAPABILITY */ #define WLAN_EXT_CAPA4_TDLS_BUFFER_STA BIT(4) #define WLAN_EXT_CAPA4_TDLS_PEER_PSM BIT(5) -- cgit v1.2.3-71-gd317 From 9c7c637050b42b6e368bb39b8d0edff728268341 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 18 Jun 2021 13:41:38 +0300 Subject: ieee80211: add defines for HE PHY cap byte 10 One bit out of the previously completely reserved byte 10 in the PHY capabilities is used since 802.11ax D7.0, add a new define for it. Signed-off-by: Johannes Berg Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20210618133832.c026feb3873d.I380f52a05ddb4153bc77ff7f276a3484819f69b2@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 0a0aaa2d5d9e..a6730072d13a 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2179,6 +2179,8 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, #define IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_RESERVED 0xc0 #define IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_MASK 0xc0 +#define IEEE80211_HE_PHY_CAP10_HE_MU_M1RU_MAX_LTF 0x01 + /* 802.11ax HE TX/RX MCS NSS Support */ #define IEEE80211_TX_RX_MCS_NSS_SUPP_HIGHEST_MCS_POS (3) #define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_POS (6) -- cgit v1.2.3-71-gd317 From b9964ce74544ea6cbc4eabd2c89a531adf7f291d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 24 Jun 2021 18:05:51 +0200 Subject: rcu: Create an unrcu_pointer() to remove __rcu from a pointer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The xchg() and cmpxchg() functions are sometimes used to carry out RCU updates. Unfortunately, this can result in sparse warnings for both the old-value and new-value arguments, as well as for the return value. The arguments can be dealt with using RCU_INITIALIZER(): old_p = xchg(&p, RCU_INITIALIZER(new_p)); But a sparse warning still remains due to assigning the __rcu pointer returned from xchg to the (most likely) non-__rcu pointer old_p. This commit therefore provides an unrcu_pointer() macro that strips the __rcu. This macro can be used as follows: old_p = unrcu_pointer(xchg(&p, RCU_INITIALIZER(new_p))); Reported-by: Toke Høiland-Jørgensen Signed-off-by: Paul E. McKenney Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210624160609.292325-2-toke@redhat.com --- include/linux/rcupdate.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 9455476c5ba2..d7895b81264e 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -363,6 +363,20 @@ static inline void rcu_preempt_sleep_check(void) { } #define rcu_check_sparse(p, space) #endif /* #else #ifdef __CHECKER__ */ +/** + * unrcu_pointer - mark a pointer as not being RCU protected + * @p: pointer needing to lose its __rcu property + * + * Converts @p from an __rcu pointer to a __kernel pointer. + * This allows an __rcu pointer to be used with xchg() and friends. + */ +#define unrcu_pointer(p) \ +({ \ + typeof(*p) *_________p1 = (typeof(*p) *__force)(p); \ + rcu_check_sparse(p, __rcu); \ + ((typeof(*p) __force __kernel *)(_________p1)); \ +}) + #define __rcu_access_pointer(p, space) \ ({ \ typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \ -- cgit v1.2.3-71-gd317 From 782347b6bcad07ddb574422e01e22c92e05928c8 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Thu, 24 Jun 2021 18:05:55 +0200 Subject: xdp: Add proper __rcu annotations to redirect map entries MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit XDP_REDIRECT works by a three-step process: the bpf_redirect() and bpf_redirect_map() helpers will lookup the target of the redirect and store it (along with some other metadata) in a per-CPU struct bpf_redirect_info. Next, when the program returns the XDP_REDIRECT return code, the driver will call xdp_do_redirect() which will use the information thus stored to actually enqueue the frame into a bulk queue structure (that differs slightly by map type, but shares the same principle). Finally, before exiting its NAPI poll loop, the driver will call xdp_do_flush(), which will flush all the different bulk queues, thus completing the redirect. Pointers to the map entries will be kept around for this whole sequence of steps, protected by RCU. However, there is no top-level rcu_read_lock() in the core code; instead drivers add their own rcu_read_lock() around the XDP portions of the code, but somewhat inconsistently as Martin discovered[0]. However, things still work because everything happens inside a single NAPI poll sequence, which means it's between a pair of calls to local_bh_disable()/local_bh_enable(). So Paul suggested[1] that we could document this intention by using rcu_dereference_check() with rcu_read_lock_bh_held() as a second parameter, thus allowing sparse and lockdep to verify that everything is done correctly. This patch does just that: we add an __rcu annotation to the map entry pointers and remove the various comments explaining the NAPI poll assurance strewn through devmap.c in favour of a longer explanation in filter.c. The goal is to have one coherent documentation of the entire flow, and rely on the RCU annotations as a "standard" way of communicating the flow in the map code (which can additionally be understood by sparse and lockdep). The RCU annotation replacements result in a fairly straight-forward replacement where READ_ONCE() becomes rcu_dereference_check(), WRITE_ONCE() becomes rcu_assign_pointer() and xchg() and cmpxchg() gets wrapped in the proper constructs to cast the pointer back and forth between __rcu and __kernel address space (for the benefit of sparse). The one complication is that xskmap has a few constructions where double-pointers are passed back and forth; these simply all gain __rcu annotations, and only the final reference/dereference to the inner-most pointer gets changed. With this, everything can be run through sparse without eliciting complaints, and lockdep can verify correctness even without the use of rcu_read_lock() in the drivers. Subsequent patches will clean these up from the drivers. [0] https://lore.kernel.org/bpf/20210415173551.7ma4slcbqeyiba2r@kafai-mbp.dhcp.thefacebook.com/ [1] https://lore.kernel.org/bpf/20210419165837.GA975577@paulmck-ThinkPad-P17-Gen-1/ Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20210624160609.292325-6-toke@redhat.com --- include/linux/filter.h | 8 +++----- include/net/xdp_sock.h | 2 +- kernel/bpf/cpumap.c | 13 +++++++++---- kernel/bpf/devmap.c | 49 +++++++++++++++++++++---------------------------- net/core/filter.c | 28 ++++++++++++++++++++++++++++ net/xdp/xsk.c | 4 ++-- net/xdp/xsk.h | 4 ++-- net/xdp/xskmap.c | 29 +++++++++++++++++------------ 8 files changed, 83 insertions(+), 54 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 688856e0b28a..472f97074da0 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -763,11 +763,9 @@ DECLARE_BPF_DISPATCHER(xdp) static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, struct xdp_buff *xdp) { - /* Caller needs to hold rcu_read_lock() (!), otherwise program - * can be released while still running, or map elements could be - * freed early while still having concurrent users. XDP fastpath - * already takes rcu_read_lock() when fetching the program, so - * it's not necessary here anymore. + /* Driver XDP hooks are invoked within a single NAPI poll cycle and thus + * under local_bh_disable(), which provides the needed RCU protection + * for accessing map entries. */ return __BPF_PROG_RUN(prog, xdp, BPF_DISPATCHER_FUNC(xdp)); } diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 9c0722c6d7ac..fff069d2ed1b 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -37,7 +37,7 @@ struct xdp_umem { struct xsk_map { struct bpf_map map; spinlock_t lock; /* Synchronize map updates */ - struct xdp_sock *xsk_map[]; + struct xdp_sock __rcu *xsk_map[]; }; struct xdp_sock { diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index a1a0c4e791c6..480e936c54d0 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -74,7 +74,7 @@ struct bpf_cpu_map_entry { struct bpf_cpu_map { struct bpf_map map; /* Below members specific for map type */ - struct bpf_cpu_map_entry **cpu_map; + struct bpf_cpu_map_entry __rcu **cpu_map; }; static DEFINE_PER_CPU(struct list_head, cpu_map_flush_list); @@ -469,7 +469,7 @@ static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap, { struct bpf_cpu_map_entry *old_rcpu; - old_rcpu = xchg(&cmap->cpu_map[key_cpu], rcpu); + old_rcpu = unrcu_pointer(xchg(&cmap->cpu_map[key_cpu], RCU_INITIALIZER(rcpu))); if (old_rcpu) { call_rcu(&old_rcpu->rcu, __cpu_map_entry_free); INIT_WORK(&old_rcpu->kthread_stop_wq, cpu_map_kthread_stop); @@ -551,7 +551,7 @@ static void cpu_map_free(struct bpf_map *map) for (i = 0; i < cmap->map.max_entries; i++) { struct bpf_cpu_map_entry *rcpu; - rcpu = READ_ONCE(cmap->cpu_map[i]); + rcpu = rcu_dereference_raw(cmap->cpu_map[i]); if (!rcpu) continue; @@ -562,6 +562,10 @@ static void cpu_map_free(struct bpf_map *map) kfree(cmap); } +/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or + * by local_bh_disable() (from XDP calls inside NAPI). The + * rcu_read_lock_bh_held() below makes lockdep accept both. + */ static void *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); @@ -570,7 +574,8 @@ static void *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) if (key >= map->max_entries) return NULL; - rcpu = READ_ONCE(cmap->cpu_map[key]); + rcpu = rcu_dereference_check(cmap->cpu_map[key], + rcu_read_lock_bh_held()); return rcpu; } diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 2a75e6c2d27d..2f6bd75cd682 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -73,7 +73,7 @@ struct bpf_dtab_netdev { struct bpf_dtab { struct bpf_map map; - struct bpf_dtab_netdev **netdev_map; /* DEVMAP type only */ + struct bpf_dtab_netdev __rcu **netdev_map; /* DEVMAP type only */ struct list_head list; /* these are only used for DEVMAP_HASH type maps */ @@ -226,7 +226,7 @@ static void dev_map_free(struct bpf_map *map) for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev; - dev = dtab->netdev_map[i]; + dev = rcu_dereference_raw(dtab->netdev_map[i]); if (!dev) continue; @@ -259,6 +259,10 @@ static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key) return 0; } +/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or + * by local_bh_disable() (from XDP calls inside NAPI). The + * rcu_read_lock_bh_held() below makes lockdep accept both. + */ static void *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); @@ -410,15 +414,9 @@ out: trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, cnt - sent, err); } -/* __dev_flush is called from xdp_do_flush() which _must_ be signaled - * from the driver before returning from its napi->poll() routine. The poll() - * routine is called either from busy_poll context or net_rx_action signaled - * from NET_RX_SOFTIRQ. Either way the poll routine must complete before the - * net device can be torn down. On devmap tear down we ensure the flush list - * is empty before completing to ensure all flush operations have completed. - * When drivers update the bpf program they may need to ensure any flush ops - * are also complete. Using synchronize_rcu or call_rcu will suffice for this - * because both wait for napi context to exit. +/* __dev_flush is called from xdp_do_flush() which _must_ be signalled from the + * driver before returning from its napi->poll() routine. See the comment above + * xdp_do_flush() in filter.c. */ void __dev_flush(void) { @@ -433,9 +431,9 @@ void __dev_flush(void) } } -/* rcu_read_lock (from syscall and BPF contexts) ensures that if a delete and/or - * update happens in parallel here a dev_put won't happen until after reading - * the ifindex. +/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or + * by local_bh_disable() (from XDP calls inside NAPI). The + * rcu_read_lock_bh_held() below makes lockdep accept both. */ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key) { @@ -445,12 +443,14 @@ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key) if (key >= map->max_entries) return NULL; - obj = READ_ONCE(dtab->netdev_map[key]); + obj = rcu_dereference_check(dtab->netdev_map[key], + rcu_read_lock_bh_held()); return obj; } -/* Runs under RCU-read-side, plus in softirq under NAPI protection. - * Thus, safe percpu variable access. +/* Runs in NAPI, i.e., softirq under local_bh_disable(). Thus, safe percpu + * variable access, and map elements stick around. See comment above + * xdp_do_flush() in filter.c. */ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_prog *xdp_prog) @@ -735,14 +735,7 @@ static int dev_map_delete_elem(struct bpf_map *map, void *key) if (k >= map->max_entries) return -EINVAL; - /* Use call_rcu() here to ensure any rcu critical sections have - * completed as well as any flush operations because call_rcu - * will wait for preempt-disable region to complete, NAPI in this - * context. 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); + old_dev = unrcu_pointer(xchg(&dtab->netdev_map[k], NULL)); if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); return 0; @@ -851,7 +844,7 @@ static int __dev_map_update_elem(struct net *net, struct bpf_map *map, * Remembering the driver side flush operation will happen before the * net device is removed. */ - old_dev = xchg(&dtab->netdev_map[i], dev); + old_dev = unrcu_pointer(xchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev))); if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); @@ -1031,10 +1024,10 @@ static int dev_map_notification(struct notifier_block *notifier, for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev, *odev; - dev = READ_ONCE(dtab->netdev_map[i]); + dev = rcu_dereference(dtab->netdev_map[i]); if (!dev || netdev != dev->dev) continue; - odev = cmpxchg(&dtab->netdev_map[i], dev, NULL); + odev = unrcu_pointer(cmpxchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev), NULL)); if (dev == odev) call_rcu(&dev->rcu, __dev_map_entry_free); diff --git a/net/core/filter.c b/net/core/filter.c index d062053994c7..d22895caa164 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3897,6 +3897,34 @@ static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = { .arg2_type = ARG_ANYTHING, }; +/* XDP_REDIRECT works by a three-step process, implemented in the functions + * below: + * + * 1. The bpf_redirect() and bpf_redirect_map() helpers will lookup the target + * of the redirect and store it (along with some other metadata) in a per-CPU + * struct bpf_redirect_info. + * + * 2. When the program returns the XDP_REDIRECT return code, the driver will + * call xdp_do_redirect() which will use the information in struct + * bpf_redirect_info to actually enqueue the frame into a map type-specific + * bulk queue structure. + * + * 3. Before exiting its NAPI poll loop, the driver will call xdp_do_flush(), + * which will flush all the different bulk queues, thus completing the + * redirect. + * + * Pointers to the map entries will be kept around for this whole sequence of + * steps, protected by RCU. However, there is no top-level rcu_read_lock() in + * the core code; instead, the RCU protection relies on everything happening + * inside a single NAPI poll sequence, which means it's between a pair of calls + * to local_bh_disable()/local_bh_enable(). + * + * The map entries are marked as __rcu and the map code makes sure to + * dereference those pointers with rcu_dereference_check() in a way that works + * for both sections that to hold an rcu_read_lock() and sections that are + * called from NAPI without a separate rcu_read_lock(). The code below does not + * use RCU annotations, but relies on those in the map code. + */ void xdp_do_flush(void) { __dev_flush(); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index cd62d4ba87a9..996da915f520 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -749,7 +749,7 @@ static void xsk_unbind_dev(struct xdp_sock *xs) } static struct xsk_map *xsk_get_map_list_entry(struct xdp_sock *xs, - struct xdp_sock ***map_entry) + struct xdp_sock __rcu ***map_entry) { struct xsk_map *map = NULL; struct xsk_map_node *node; @@ -785,7 +785,7 @@ static void xsk_delete_from_maps(struct xdp_sock *xs) * might be updates to the map between * xsk_get_map_list_entry() and xsk_map_try_sock_delete(). */ - struct xdp_sock **map_entry = NULL; + struct xdp_sock __rcu **map_entry = NULL; struct xsk_map *map; while ((map = xsk_get_map_list_entry(xs, &map_entry))) { diff --git a/net/xdp/xsk.h b/net/xdp/xsk.h index edcf249ad1f1..a4bc4749faac 100644 --- a/net/xdp/xsk.h +++ b/net/xdp/xsk.h @@ -31,7 +31,7 @@ struct xdp_mmap_offsets_v1 { struct xsk_map_node { struct list_head node; struct xsk_map *map; - struct xdp_sock **map_entry; + struct xdp_sock __rcu **map_entry; }; static inline struct xdp_sock *xdp_sk(struct sock *sk) @@ -40,7 +40,7 @@ static inline struct xdp_sock *xdp_sk(struct sock *sk) } void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, - struct xdp_sock **map_entry); + struct xdp_sock __rcu **map_entry); void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id); int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool, u16 queue_id); diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c index 9df75ea4a567..2e48d0e094d9 100644 --- a/net/xdp/xskmap.c +++ b/net/xdp/xskmap.c @@ -12,7 +12,7 @@ #include "xsk.h" static struct xsk_map_node *xsk_map_node_alloc(struct xsk_map *map, - struct xdp_sock **map_entry) + struct xdp_sock __rcu **map_entry) { struct xsk_map_node *node; @@ -42,7 +42,7 @@ static void xsk_map_sock_add(struct xdp_sock *xs, struct xsk_map_node *node) } static void xsk_map_sock_delete(struct xdp_sock *xs, - struct xdp_sock **map_entry) + struct xdp_sock __rcu **map_entry) { struct xsk_map_node *n, *tmp; @@ -124,6 +124,10 @@ static int xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) return insn - insn_buf; } +/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or + * by local_bh_disable() (from XDP calls inside NAPI). The + * rcu_read_lock_bh_held() below makes lockdep accept both. + */ static void *__xsk_map_lookup_elem(struct bpf_map *map, u32 key) { struct xsk_map *m = container_of(map, struct xsk_map, map); @@ -131,12 +135,11 @@ static void *__xsk_map_lookup_elem(struct bpf_map *map, u32 key) if (key >= map->max_entries) return NULL; - return READ_ONCE(m->xsk_map[key]); + return rcu_dereference_check(m->xsk_map[key], rcu_read_lock_bh_held()); } static void *xsk_map_lookup_elem(struct bpf_map *map, void *key) { - WARN_ON_ONCE(!rcu_read_lock_held()); return __xsk_map_lookup_elem(map, *(u32 *)key); } @@ -149,7 +152,8 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { struct xsk_map *m = container_of(map, struct xsk_map, map); - struct xdp_sock *xs, *old_xs, **map_entry; + struct xdp_sock __rcu **map_entry; + struct xdp_sock *xs, *old_xs; u32 i = *(u32 *)key, fd = *(u32 *)value; struct xsk_map_node *node; struct socket *sock; @@ -179,7 +183,7 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, } spin_lock_bh(&m->lock); - old_xs = READ_ONCE(*map_entry); + old_xs = rcu_dereference_protected(*map_entry, lockdep_is_held(&m->lock)); if (old_xs == xs) { err = 0; goto out; @@ -191,7 +195,7 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, goto out; } xsk_map_sock_add(xs, node); - WRITE_ONCE(*map_entry, xs); + rcu_assign_pointer(*map_entry, xs); if (old_xs) xsk_map_sock_delete(old_xs, map_entry); spin_unlock_bh(&m->lock); @@ -208,7 +212,8 @@ out: static int xsk_map_delete_elem(struct bpf_map *map, void *key) { struct xsk_map *m = container_of(map, struct xsk_map, map); - struct xdp_sock *old_xs, **map_entry; + struct xdp_sock __rcu **map_entry; + struct xdp_sock *old_xs; int k = *(u32 *)key; if (k >= map->max_entries) @@ -216,7 +221,7 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key) spin_lock_bh(&m->lock); map_entry = &m->xsk_map[k]; - old_xs = xchg(map_entry, NULL); + old_xs = unrcu_pointer(xchg(map_entry, NULL)); if (old_xs) xsk_map_sock_delete(old_xs, map_entry); spin_unlock_bh(&m->lock); @@ -231,11 +236,11 @@ static int xsk_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) } void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, - struct xdp_sock **map_entry) + struct xdp_sock __rcu **map_entry) { spin_lock_bh(&map->lock); - if (READ_ONCE(*map_entry) == xs) { - WRITE_ONCE(*map_entry, NULL); + if (rcu_access_pointer(*map_entry) == xs) { + rcu_assign_pointer(*map_entry, NULL); xsk_map_sock_delete(xs, map_entry); } spin_unlock_bh(&map->lock); -- cgit v1.2.3-71-gd317 From c88c192dc3ea209694cc08f4ccf51f920d26bdae Mon Sep 17 00:00:00 2001 From: Marcin Wojtas Date: Thu, 24 Jun 2021 02:51:51 +0200 Subject: net: mdiobus: fix fwnode_mdbiobus_register() fallback case The fallback case of fwnode_mdbiobus_register() (relevant for !CONFIG_FWNODE_MDIO) was defined with wrong argument name, causing a compilation error. Fix that. Signed-off-by: Marcin Wojtas Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/fwnode_mdio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fwnode_mdio.h b/include/linux/fwnode_mdio.h index 13d4ae8fee0a..f62817c23137 100644 --- a/include/linux/fwnode_mdio.h +++ b/include/linux/fwnode_mdio.h @@ -40,7 +40,7 @@ static inline int fwnode_mdiobus_register(struct mii_bus *bus, * This way, we don't have to keep compat bits around in drivers. */ - return mdiobus_register(mdio); + return mdiobus_register(bus); } #endif -- cgit v1.2.3-71-gd317 From ff70202b2d1ad522275c6aadc8c53519b6a22c57 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 24 Jun 2021 10:05:05 +0200 Subject: dev_forward_skb: do not scrub skb mark within the same name space The goal is to keep the mark during a bpf_redirect(), like it is done for legacy encapsulation / decapsulation, when there is no x-netns. This was initially done in commit 213dd74aee76 ("skbuff: Do not scrub skb mark within the same name space"). When the call to skb_scrub_packet() was added in dev_forward_skb() (commit 8b27f27797ca ("skb: allow skb_scrub_packet() to be used by tunnels")), the second argument (xnet) was set to true to force a call to skb_orphan(). At this time, the mark was always cleanned up by skb_scrub_packet(), whatever xnet value was. This call to skb_orphan() was removed later in commit 9c4c325252c5 ("skbuff: preserve sock reference when scrubbing the skb."). But this 'true' stayed here without any real reason. Let's correctly set xnet in ____dev_forward_skb(), this function has access to the previous interface and to the new interface. Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5cbc950b34df..5ab2d1917ca1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4114,7 +4114,7 @@ static __always_inline int ____dev_forward_skb(struct net_device *dev, return NET_RX_DROP; } - skb_scrub_packet(skb, true); + skb_scrub_packet(skb, !net_eq(dev_net(dev), dev_net(skb->dev))); skb->priority = 0; return 0; } -- cgit v1.2.3-71-gd317 From ac53c26433b51f1835ce5a935970e427d83e3ec5 Mon Sep 17 00:00:00 2001 From: Marcin Wojtas Date: Fri, 25 Jun 2021 12:38:53 +0200 Subject: net: mdiobus: withdraw fwnode_mdbiobus_register The newly implemented fwnode_mdbiobus_register turned out to be problematic - in case the fwnode_/of_/acpi_mdio are built as modules, a dependency cycle can be observed during the depmod phase of modules_install, eg.: depmod: ERROR: Cycle detected: fwnode_mdio -> of_mdio -> fwnode_mdio depmod: ERROR: Found 2 modules in dependency cycles! OR: depmod: ERROR: Cycle detected: acpi_mdio -> fwnode_mdio -> acpi_mdio depmod: ERROR: Found 2 modules in dependency cycles! A possible solution could be to rework fwnode_mdiobus_register, so that to merge the contents of acpi_mdiobus_register and of_mdiobus_register. However feasible, such change would be very intrusive and affect huge amount of the of_mdiobus_register users. Since there are currently 2 users of ACPI and MDIO (xgmac_mdio and mvmdio), withdraw the fwnode_mdbiobus_register and roll back to a simple 'if' condition in affected drivers. Fixes: 62a6ef6a996f ("net: mdiobus: Introduce fwnode_mdbiobus_register()") Signed-off-by: Marcin Wojtas Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/Kconfig | 4 +++- drivers/net/ethernet/freescale/xgmac_mdio.c | 11 +++++++++-- drivers/net/ethernet/marvell/mvmdio.c | 10 ++++++++-- drivers/net/mdio/fwnode_mdio.c | 22 ---------------------- include/linux/fwnode_mdio.h | 12 ------------ 5 files changed, 20 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig index 92a390576b88..2d1abdd58fab 100644 --- a/drivers/net/ethernet/freescale/Kconfig +++ b/drivers/net/ethernet/freescale/Kconfig @@ -67,7 +67,9 @@ config FSL_PQ_MDIO config FSL_XGMAC_MDIO tristate "Freescale XGMAC MDIO" - depends on FWNODE_MDIO + select PHYLIB + depends on OF + select OF_MDIO help This driver supports the MDIO bus on the Fman 10G Ethernet MACs, and on the FMan mEMAC (which supports both Clauses 22 and 45) diff --git a/drivers/net/ethernet/freescale/xgmac_mdio.c b/drivers/net/ethernet/freescale/xgmac_mdio.c index 2d99edc8a647..0b68852379da 100644 --- a/drivers/net/ethernet/freescale/xgmac_mdio.c +++ b/drivers/net/ethernet/freescale/xgmac_mdio.c @@ -13,7 +13,7 @@ */ #include -#include +#include #include #include #include @@ -246,6 +246,7 @@ static int xgmac_mdio_read(struct mii_bus *bus, int phy_id, int regnum) static int xgmac_mdio_probe(struct platform_device *pdev) { + struct fwnode_handle *fwnode; struct mdio_fsl_priv *priv; struct resource *res; struct mii_bus *bus; @@ -290,7 +291,13 @@ static int xgmac_mdio_probe(struct platform_device *pdev) priv->has_a011043 = device_property_read_bool(&pdev->dev, "fsl,erratum-a011043"); - ret = fwnode_mdiobus_register(bus, pdev->dev.fwnode); + fwnode = pdev->dev.fwnode; + if (is_of_node(fwnode)) + ret = of_mdiobus_register(bus, to_of_node(fwnode)); + else if (is_acpi_node(fwnode)) + ret = acpi_mdiobus_register(bus, fwnode); + else + ret = -EINVAL; if (ret) { dev_err(&pdev->dev, "cannot register MDIO bus\n"); goto err_registration; diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c index 7537ee3f6622..62a97c46fba0 100644 --- a/drivers/net/ethernet/marvell/mvmdio.c +++ b/drivers/net/ethernet/marvell/mvmdio.c @@ -18,9 +18,9 @@ */ #include +#include #include #include -#include #include #include #include @@ -371,7 +371,13 @@ static int orion_mdio_probe(struct platform_device *pdev) goto out_mdio; } - ret = fwnode_mdiobus_register(bus, pdev->dev.fwnode); + /* For the platforms not supporting DT/ACPI fall-back + * to mdiobus_register via of_mdiobus_register. + */ + if (is_acpi_node(pdev->dev.fwnode)) + ret = acpi_mdiobus_register(bus, pdev->dev.fwnode); + else + ret = of_mdiobus_register(bus, pdev->dev.of_node); if (ret < 0) { dev_err(&pdev->dev, "Cannot register MDIO bus (%d)\n", ret); goto out_mdio; diff --git a/drivers/net/mdio/fwnode_mdio.c b/drivers/net/mdio/fwnode_mdio.c index ae0bf71a9932..1becb1a731f6 100644 --- a/drivers/net/mdio/fwnode_mdio.c +++ b/drivers/net/mdio/fwnode_mdio.c @@ -7,10 +7,8 @@ */ #include -#include #include #include -#include #include MODULE_AUTHOR("Calvin Johnson "); @@ -144,23 +142,3 @@ int fwnode_mdiobus_register_phy(struct mii_bus *bus, return 0; } EXPORT_SYMBOL(fwnode_mdiobus_register_phy); - -/** - * fwnode_mdiobus_register - bring up all the PHYs on a given MDIO bus and - * attach them to it. - * @bus: Target MDIO bus. - * @fwnode: Pointer to fwnode of the MDIO controller. - * - * Return values are determined accordingly to acpi_/of_ mdiobus_register() - * operation. - */ -int fwnode_mdiobus_register(struct mii_bus *bus, struct fwnode_handle *fwnode) -{ - if (is_acpi_node(fwnode)) - return acpi_mdiobus_register(bus, fwnode); - else if (is_of_node(fwnode)) - return of_mdiobus_register(bus, to_of_node(fwnode)); - else - return -EINVAL; -} -EXPORT_SYMBOL(fwnode_mdiobus_register); diff --git a/include/linux/fwnode_mdio.h b/include/linux/fwnode_mdio.h index f62817c23137..faf603c48c86 100644 --- a/include/linux/fwnode_mdio.h +++ b/include/linux/fwnode_mdio.h @@ -16,7 +16,6 @@ int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, int fwnode_mdiobus_register_phy(struct mii_bus *bus, struct fwnode_handle *child, u32 addr); -int fwnode_mdiobus_register(struct mii_bus *bus, struct fwnode_handle *fwnode); #else /* CONFIG_FWNODE_MDIO */ int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, struct phy_device *phy, @@ -31,17 +30,6 @@ static inline int fwnode_mdiobus_register_phy(struct mii_bus *bus, { return -EINVAL; } - -static inline int fwnode_mdiobus_register(struct mii_bus *bus, - struct fwnode_handle *fwnode) -{ - /* - * Fall back to mdiobus_register() function to register a bus. - * This way, we don't have to keep compat bits around in drivers. - */ - - return mdiobus_register(bus); -} #endif #endif /* __LINUX_FWNODE_MDIO_H */ -- cgit v1.2.3-71-gd317 From 1ab6dc35e9148e3cb4a837fdd08f1ca56b55eda0 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Mon, 19 Apr 2021 16:23:49 +0300 Subject: net/mlx5: DR, Add support for flow sampler offload Add SW steering support for sFlow / flow sampler action. Signed-off-by: Yevgeny Kliteynik Signed-off-by: Saeed Mahameed --- .../mellanox/mlx5/core/steering/dr_action.c | 55 ++++++++++++++++++++++ .../ethernet/mellanox/mlx5/core/steering/dr_cmd.c | 33 +++++++++++++ .../mellanox/mlx5/core/steering/dr_types.h | 14 ++++++ .../ethernet/mellanox/mlx5/core/steering/fs_dr.c | 17 +++++-- .../ethernet/mellanox/mlx5/core/steering/mlx5dr.h | 3 ++ include/linux/mlx5/mlx5_ifc.h | 5 ++ 6 files changed, 124 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index de68c0ec2143..6475ba35cf6b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -31,6 +31,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_NON_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_DECAP, @@ -45,6 +46,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_DECAP, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_DECAP, [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, @@ -57,6 +59,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_ENCAP, }, @@ -64,6 +67,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_MODIFY_HDR, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_HDR, [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, @@ -74,6 +78,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_MODIFY_VLAN, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_VLAN, [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, @@ -86,6 +91,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_NON_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_DECAP, @@ -104,6 +110,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_NO_ACTION] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, @@ -114,11 +121,13 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_ENCAP] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_ENCAP, }, [DR_ACTION_STATE_MODIFY_HDR] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_HDR, [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, @@ -128,6 +137,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_MODIFY_VLAN] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_VLAN, [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, @@ -137,6 +147,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_NON_TERM] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, @@ -152,6 +163,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_NO_ACTION] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_DECAP, [DR_ACTION_TYP_TNL_L3_TO_L2] = DR_ACTION_STATE_DECAP, @@ -166,6 +178,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_DECAP, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, @@ -178,11 +191,13 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_ENCAP, }, [DR_ACTION_STATE_MODIFY_HDR] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_HDR, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, @@ -192,6 +207,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_MODIFY_VLAN] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_VLAN, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, @@ -203,6 +219,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_NON_TERM] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_DECAP, [DR_ACTION_TYP_TNL_L3_TO_L2] = DR_ACTION_STATE_DECAP, @@ -221,6 +238,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_NO_ACTION] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, @@ -233,11 +251,13 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, }, [DR_ACTION_STATE_MODIFY_HDR] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_HDR, [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, @@ -248,6 +268,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_MODIFY_VLAN] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_VLAN, [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, @@ -258,6 +279,7 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_NON_TERM] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, @@ -519,6 +541,10 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, attr.reformat.size = action->reformat->size; attr.reformat.id = action->reformat->id; break; + case DR_ACTION_TYP_SAMPLER: + attr.final_icm_addr = rx_rule ? action->sampler->rx_icm_addr : + action->sampler->tx_icm_addr; + break; case DR_ACTION_TYP_VPORT: attr.hit_gvmi = action->vport->caps->vhca_gvmi; dest_action = action; @@ -612,6 +638,7 @@ static unsigned int action_size[DR_ACTION_TYP_MAX] = { [DR_ACTION_TYP_VPORT] = sizeof(struct mlx5dr_action_vport), [DR_ACTION_TYP_PUSH_VLAN] = sizeof(struct mlx5dr_action_push_vlan), [DR_ACTION_TYP_INSERT_HDR] = sizeof(struct mlx5dr_action_reformat), + [DR_ACTION_TYP_SAMPLER] = sizeof(struct mlx5dr_action_sampler), }; static struct mlx5dr_action * @@ -824,6 +851,31 @@ struct mlx5dr_action *mlx5dr_action_create_tag(u32 tag_value) return action; } +struct mlx5dr_action * +mlx5dr_action_create_flow_sampler(struct mlx5dr_domain *dmn, u32 sampler_id) +{ + struct mlx5dr_action *action; + u64 icm_rx, icm_tx; + int ret; + + ret = mlx5dr_cmd_query_flow_sampler(dmn->mdev, sampler_id, + &icm_rx, &icm_tx); + if (ret) + return NULL; + + action = dr_action_create_generic(DR_ACTION_TYP_SAMPLER); + if (!action) + return NULL; + + action->sampler->dmn = dmn; + action->sampler->sampler_id = sampler_id; + action->sampler->rx_icm_addr = icm_rx; + action->sampler->tx_icm_addr = icm_tx; + + refcount_inc(&dmn->refcount); + return action; +} + static int dr_action_verify_reformat_params(enum mlx5dr_action_type reformat_type, struct mlx5dr_domain *dmn, @@ -1624,6 +1676,9 @@ int mlx5dr_action_destroy(struct mlx5dr_action *action) kfree(action->rewrite->data); refcount_dec(&action->rewrite->dmn->refcount); break; + case DR_ACTION_TYP_SAMPLER: + refcount_dec(&action->sampler->dmn->refcount); + break; default: break; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c index 6314f50efbd4..54e1f5438bbe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c @@ -228,6 +228,36 @@ int mlx5dr_cmd_query_flow_table(struct mlx5_core_dev *dev, return 0; } +int mlx5dr_cmd_query_flow_sampler(struct mlx5_core_dev *dev, + u32 sampler_id, + u64 *rx_icm_addr, + u64 *tx_icm_addr) +{ + u32 out[MLX5_ST_SZ_DW(query_sampler_obj_out)] = {}; + u32 in[MLX5_ST_SZ_DW(general_obj_in_cmd_hdr)] = {}; + void *attr; + int ret; + + MLX5_SET(general_obj_in_cmd_hdr, in, opcode, + MLX5_CMD_OP_QUERY_GENERAL_OBJECT); + MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, + MLX5_GENERAL_OBJECT_TYPES_SAMPLER); + MLX5_SET(general_obj_in_cmd_hdr, in, obj_id, sampler_id); + + ret = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); + if (ret) + return ret; + + attr = MLX5_ADDR_OF(query_sampler_obj_out, out, sampler_object); + + *rx_icm_addr = MLX5_GET64(sampler_obj, attr, + sw_steering_icm_address_rx); + *tx_icm_addr = MLX5_GET64(sampler_obj, attr, + sw_steering_icm_address_tx); + + return 0; +} + int mlx5dr_cmd_sync_steering(struct mlx5_core_dev *mdev) { u32 in[MLX5_ST_SZ_DW(sync_steering_in)] = {}; @@ -711,6 +741,9 @@ int mlx5dr_cmd_set_fte(struct mlx5_core_dev *dev, fte->dest_arr[i].vport.reformat_id); } break; + case MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER: + id = fte->dest_arr[i].sampler_id; + break; default: id = fte->dest_arr[i].tir_num; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index 60b8c04e165e..f5e93fa87aff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -124,6 +124,7 @@ enum mlx5dr_action_type { DR_ACTION_TYP_POP_VLAN, DR_ACTION_TYP_PUSH_VLAN, DR_ACTION_TYP_INSERT_HDR, + DR_ACTION_TYP_SAMPLER, DR_ACTION_TYP_MAX, }; @@ -919,6 +920,13 @@ struct mlx5dr_action_reformat { u8 param_1; }; +struct mlx5dr_action_sampler { + struct mlx5dr_domain *dmn; + u64 rx_icm_addr; + u64 tx_icm_addr; + u32 sampler_id; +}; + struct mlx5dr_action_dest_tbl { u8 is_fw_tbl:1; union { @@ -962,6 +970,7 @@ struct mlx5dr_action { void *data; struct mlx5dr_action_rewrite *rewrite; struct mlx5dr_action_reformat *reformat; + struct mlx5dr_action_sampler *sampler; struct mlx5dr_action_dest_tbl *dest_tbl; struct mlx5dr_action_ctr *ctr; struct mlx5dr_action_vport *vport; @@ -1116,6 +1125,10 @@ int mlx5dr_cmd_query_gvmi(struct mlx5_core_dev *mdev, bool other_vport, u16 vport_number, u16 *gvmi); int mlx5dr_cmd_query_esw_caps(struct mlx5_core_dev *mdev, struct mlx5dr_esw_caps *caps); +int mlx5dr_cmd_query_flow_sampler(struct mlx5_core_dev *dev, + u32 sampler_id, + u64 *rx_icm_addr, + u64 *tx_icm_addr); int mlx5dr_cmd_sync_steering(struct mlx5_core_dev *mdev); int mlx5dr_cmd_set_fte_modify_and_vport(struct mlx5_core_dev *mdev, u32 table_type, @@ -1303,6 +1316,7 @@ struct mlx5dr_cmd_flow_destination_hw_info { u32 ft_num; u32 ft_id; u32 counter_id; + u32 sampler_id; struct { u16 num; u16 vhca_id; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c index 00b4c753cae2..d5926dd7e972 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -387,7 +387,7 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) { list_for_each_entry(dst, &fte->node.children, node.list) { enum mlx5_flow_destination_type type = dst->dest_attr.type; - u32 ft_id; + u32 id; if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX || num_term_actions >= MLX5_FLOW_CONTEXT_ACTION_MAX) { @@ -425,9 +425,20 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, num_term_actions++; break; case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM: - ft_id = dst->dest_attr.ft_num; + id = dst->dest_attr.ft_num; tmp_action = mlx5dr_action_create_dest_table_num(domain, - ft_id); + id); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + term_actions[num_term_actions++].dest = tmp_action; + break; + case MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER: + id = dst->dest_attr.sampler_id; + tmp_action = mlx5dr_action_create_flow_sampler(domain, + id); if (!tmp_action) { err = -ENOMEM; goto free_actions; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h index b2aa6c93c3a1..bbfe101d4e57 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -100,6 +100,9 @@ struct mlx5dr_action *mlx5dr_action_create_drop(void); struct mlx5dr_action *mlx5dr_action_create_tag(u32 tag_value); +struct mlx5dr_action * +mlx5dr_action_create_flow_sampler(struct mlx5dr_domain *dmn, u32 sampler_id); + struct mlx5dr_action * mlx5dr_action_create_flow_counter(u32 counter_id); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 2d1ed78289ff..e32a0d61929b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -11083,6 +11083,11 @@ struct mlx5_ifc_create_sampler_obj_in_bits { struct mlx5_ifc_sampler_obj_bits sampler_object; }; +struct mlx5_ifc_query_sampler_obj_out_bits { + struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr; + struct mlx5_ifc_sampler_obj_bits sampler_object; +}; + enum { MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_128 = 0x0, MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_256 = 0x1, -- cgit v1.2.3-71-gd317 From 0d2cfbd41c4a5a0ca5598d1874b1081138cd64c6 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 27 Jun 2021 14:54:25 +0300 Subject: net: bridge: ignore switchdev events for LAG ports which didn't request replay There is a slight inconvenience in the switchdev replay helpers added recently, and this is when: ip link add br0 type bridge ip link add bond0 type bond ip link set bond0 master br0 bridge vlan add dev bond0 vid 100 ip link set swp0 master bond0 ip link set swp1 master bond0 Since the underlying driver (currently only DSA) asks for a replay of VLANs when swp0 and swp1 join the LAG because it is bridged, what will happen is that DSA will try to react twice on the VLAN event for swp0. This is not really a huge problem right now, because most drivers accept duplicates since the bridge itself does, but it will become a problem when we add support for replaying switchdev object deletions. Let's fix this by adding a blank void *ctx in the replay helpers, which will be passed on by the bridge in the switchdev notifications. If the context is NULL, everything is the same as before. But if the context is populated with a valid pointer, the underlying switchdev driver (currently DSA) can use the pointer to 'see through' the bridge port (which in the example above is bond0) and 'know' that the event is only for a particular physical port offloading that bridge port, and not for all of them. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/mscc/ocelot_net.c | 19 +++++++++++++++++-- include/linux/if_bridge.h | 14 ++++++++------ net/bridge/br_fdb.c | 7 ++++--- net/bridge/br_mdb.c | 8 +++++--- net/bridge/br_vlan.c | 8 +++++--- net/dsa/port.c | 6 +++--- net/dsa/slave.c | 9 +++++++++ 7 files changed, 51 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index 456541640feb..166d851962d2 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -948,6 +948,9 @@ static int ocelot_port_attr_set(struct net_device *dev, const void *ctx, int port = priv->chip_port; int err = 0; + if (ctx && ctx != priv) + return 0; + switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_STP_STATE: ocelot_port_attr_stp_state_set(ocelot, port, attr->u.stp_state); @@ -1062,8 +1065,12 @@ static int ocelot_port_obj_add(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { + struct ocelot_port_private *priv = netdev_priv(dev); int ret = 0; + if (ctx && ctx != priv) + return 0; + switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_VLAN: ret = ocelot_port_obj_add_vlan(dev, @@ -1089,8 +1096,12 @@ static int ocelot_port_obj_add(struct net_device *dev, const void *ctx, static int ocelot_port_obj_del(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj) { + struct ocelot_port_private *priv = netdev_priv(dev); int ret = 0; + if (ctx && ctx != priv) + return 0; + switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_VLAN: ret = ocelot_vlan_vid_del(dev, @@ -1143,10 +1154,14 @@ static int ocelot_switchdev_sync(struct ocelot *ocelot, int port, struct net_device *bridge_dev, struct netlink_ext_ack *extack) { + struct ocelot_port *ocelot_port = ocelot->ports[port]; + struct ocelot_port_private *priv; clock_t ageing_time; u8 stp_state; int err; + priv = container_of(ocelot_port, struct ocelot_port_private, port); + ocelot_inherit_brport_flags(ocelot, port, brport_dev); stp_state = br_port_get_stp_state(brport_dev); @@ -1160,12 +1175,12 @@ static int ocelot_switchdev_sync(struct ocelot *ocelot, int port, ageing_time = br_get_ageing_time(bridge_dev); ocelot_port_attr_ageing_set(ocelot, port, ageing_time); - err = br_mdb_replay(bridge_dev, brport_dev, + err = br_mdb_replay(bridge_dev, brport_dev, priv, &ocelot_switchdev_blocking_nb, extack); if (err && err != -EOPNOTSUPP) return err; - err = br_vlan_replay(bridge_dev, brport_dev, + err = br_vlan_replay(bridge_dev, brport_dev, priv, &ocelot_switchdev_blocking_nb, extack); if (err && err != -EOPNOTSUPP) return err; diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 12e9a32dbca0..57df761b6f4a 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -71,7 +71,8 @@ bool br_multicast_has_router_adjacent(struct net_device *dev, int proto); bool br_multicast_enabled(const struct net_device *dev); bool br_multicast_router(const struct net_device *dev); int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, - struct notifier_block *nb, struct netlink_ext_ack *extack); + const void *ctx, struct notifier_block *nb, + struct netlink_ext_ack *extack); #else static inline int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list) @@ -104,7 +105,7 @@ static inline bool br_multicast_router(const struct net_device *dev) return false; } static inline int br_mdb_replay(struct net_device *br_dev, - struct net_device *dev, + struct net_device *dev, const void *ctx, struct notifier_block *nb, struct netlink_ext_ack *extack) { @@ -120,7 +121,8 @@ int br_vlan_get_proto(const struct net_device *dev, u16 *p_proto); int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo); int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, - struct notifier_block *nb, struct netlink_ext_ack *extack); + const void *ctx, struct notifier_block *nb, + struct netlink_ext_ack *extack); #else static inline bool br_vlan_enabled(const struct net_device *dev) { @@ -149,7 +151,7 @@ static inline int br_vlan_get_info(const struct net_device *dev, u16 vid, } static inline int br_vlan_replay(struct net_device *br_dev, - struct net_device *dev, + struct net_device *dev, const void *ctx, struct notifier_block *nb, struct netlink_ext_ack *extack) { @@ -166,7 +168,7 @@ bool br_port_flag_is_set(const struct net_device *dev, unsigned long flag); u8 br_port_get_stp_state(const struct net_device *dev); clock_t br_get_ageing_time(struct net_device *br_dev); int br_fdb_replay(struct net_device *br_dev, struct net_device *dev, - struct notifier_block *nb); + const void *ctx, struct notifier_block *nb); #else static inline struct net_device * br_fdb_find_port(const struct net_device *br_dev, @@ -197,7 +199,7 @@ static inline clock_t br_get_ageing_time(struct net_device *br_dev) } static inline int br_fdb_replay(struct net_device *br_dev, - struct net_device *dev, + struct net_device *dev, const void *ctx, struct notifier_block *nb) { return -EOPNOTSUPP; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index b8d3ddfe5853..9d164a518e38 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -728,7 +728,7 @@ static inline size_t fdb_nlmsg_size(void) static int br_fdb_replay_one(struct notifier_block *nb, struct net_bridge_fdb_entry *fdb, - struct net_device *dev) + struct net_device *dev, const void *ctx) { struct switchdev_notifier_fdb_info item; int err; @@ -739,13 +739,14 @@ static int br_fdb_replay_one(struct notifier_block *nb, item.offloaded = test_bit(BR_FDB_OFFLOADED, &fdb->flags); item.is_local = test_bit(BR_FDB_LOCAL, &fdb->flags); item.info.dev = dev; + item.info.ctx = ctx; err = nb->notifier_call(nb, SWITCHDEV_FDB_ADD_TO_DEVICE, &item); return notifier_to_errno(err); } int br_fdb_replay(struct net_device *br_dev, struct net_device *dev, - struct notifier_block *nb) + const void *ctx, struct notifier_block *nb) { struct net_bridge_fdb_entry *fdb; struct net_bridge *br; @@ -766,7 +767,7 @@ int br_fdb_replay(struct net_device *br_dev, struct net_device *dev, if (dst_dev != br_dev && dst_dev != dev) continue; - err = br_fdb_replay_one(nb, fdb, dst_dev); + err = br_fdb_replay_one(nb, fdb, dst_dev, ctx); if (err) break; } diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 3f839a8cc9fb..8bc6afca5e8c 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -568,12 +568,13 @@ static void br_switchdev_mdb_populate(struct switchdev_obj_port_mdb *mdb, static int br_mdb_replay_one(struct notifier_block *nb, struct net_device *dev, struct switchdev_obj_port_mdb *mdb, - struct netlink_ext_ack *extack) + const void *ctx, struct netlink_ext_ack *extack) { struct switchdev_notifier_port_obj_info obj_info = { .info = { .dev = dev, .extack = extack, + .ctx = ctx, }, .obj = &mdb->obj, }; @@ -603,7 +604,8 @@ static int br_mdb_queue_one(struct list_head *mdb_list, } int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, - struct notifier_block *nb, struct netlink_ext_ack *extack) + const void *ctx, struct notifier_block *nb, + struct netlink_ext_ack *extack) { struct net_bridge_mdb_entry *mp; struct switchdev_obj *obj, *tmp; @@ -664,7 +666,7 @@ int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, list_for_each_entry(obj, &mdb_list, list) { err = br_mdb_replay_one(nb, dev, SWITCHDEV_OBJ_PORT_MDB(obj), - extack); + ctx, extack); if (err) goto out_free_mdb; } diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 8789a57af543..2bfa2a00e193 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -1807,12 +1807,13 @@ out_kfree: static int br_vlan_replay_one(struct notifier_block *nb, struct net_device *dev, struct switchdev_obj_port_vlan *vlan, - struct netlink_ext_ack *extack) + const void *ctx, struct netlink_ext_ack *extack) { struct switchdev_notifier_port_obj_info obj_info = { .info = { .dev = dev, .extack = extack, + .ctx = ctx, }, .obj = &vlan->obj, }; @@ -1823,7 +1824,8 @@ static int br_vlan_replay_one(struct notifier_block *nb, } int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, - struct notifier_block *nb, struct netlink_ext_ack *extack) + const void *ctx, struct notifier_block *nb, + struct netlink_ext_ack *extack) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; @@ -1868,7 +1870,7 @@ int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, if (!br_vlan_should_use(v)) continue; - err = br_vlan_replay_one(nb, dev, &vlan, extack); + err = br_vlan_replay_one(nb, dev, &vlan, ctx, extack); if (err) return err; } diff --git a/net/dsa/port.c b/net/dsa/port.c index 5c93f1e1a03d..339781c98de1 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -194,17 +194,17 @@ static int dsa_port_switchdev_sync(struct dsa_port *dp, if (err && err != -EOPNOTSUPP) return err; - err = br_mdb_replay(br, brport_dev, + err = br_mdb_replay(br, brport_dev, dp, &dsa_slave_switchdev_blocking_notifier, extack); if (err && err != -EOPNOTSUPP) return err; - err = br_fdb_replay(br, brport_dev, &dsa_slave_switchdev_notifier); + err = br_fdb_replay(br, brport_dev, dp, &dsa_slave_switchdev_notifier); if (err && err != -EOPNOTSUPP) return err; - err = br_vlan_replay(br, brport_dev, + err = br_vlan_replay(br, brport_dev, dp, &dsa_slave_switchdev_blocking_notifier, extack); if (err && err != -EOPNOTSUPP) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 3692259a025f..2f0d0a6b1f9c 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -278,6 +278,9 @@ static int dsa_slave_port_attr_set(struct net_device *dev, const void *ctx, struct dsa_port *dp = dsa_slave_to_port(dev); int ret; + if (ctx && ctx != dp) + return 0; + switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_STP_STATE: if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) @@ -401,6 +404,9 @@ static int dsa_slave_port_obj_add(struct net_device *dev, const void *ctx, struct dsa_port *dp = dsa_slave_to_port(dev); int err; + if (ctx && ctx != dp) + return 0; + switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) @@ -475,6 +481,9 @@ static int dsa_slave_port_obj_del(struct net_device *dev, const void *ctx, struct dsa_port *dp = dsa_slave_to_port(dev); int err; + if (ctx && ctx != dp) + return 0; + switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) -- cgit v1.2.3-71-gd317 From bdf123b455ce596aec6e410ec36fe3687b6a2140 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 27 Jun 2021 14:54:26 +0300 Subject: net: bridge: constify variables in the replay helpers Some of the arguments and local variables for the newly added switchdev replay helpers can be const, so let's make them so. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 14 +++++++------- net/bridge/br_fdb.c | 6 +++--- net/bridge/br_mdb.c | 8 ++++---- net/bridge/br_stp.c | 4 ++-- 4 files changed, 16 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 57df761b6f4a..6b54da2c65ba 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -104,8 +104,8 @@ static inline bool br_multicast_router(const struct net_device *dev) { return false; } -static inline int br_mdb_replay(struct net_device *br_dev, - struct net_device *dev, const void *ctx, +static inline int br_mdb_replay(const struct net_device *br_dev, + const struct net_device *dev, const void *ctx, struct notifier_block *nb, struct netlink_ext_ack *extack) { @@ -166,8 +166,8 @@ struct net_device *br_fdb_find_port(const struct net_device *br_dev, void br_fdb_clear_offload(const struct net_device *dev, u16 vid); bool br_port_flag_is_set(const struct net_device *dev, unsigned long flag); u8 br_port_get_stp_state(const struct net_device *dev); -clock_t br_get_ageing_time(struct net_device *br_dev); -int br_fdb_replay(struct net_device *br_dev, struct net_device *dev, +clock_t br_get_ageing_time(const struct net_device *br_dev); +int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev, const void *ctx, struct notifier_block *nb); #else static inline struct net_device * @@ -193,13 +193,13 @@ static inline u8 br_port_get_stp_state(const struct net_device *dev) return BR_STATE_DISABLED; } -static inline clock_t br_get_ageing_time(struct net_device *br_dev) +static inline clock_t br_get_ageing_time(const struct net_device *br_dev) { return 0; } -static inline int br_fdb_replay(struct net_device *br_dev, - struct net_device *dev, const void *ctx, +static inline int br_fdb_replay(const struct net_device *br_dev, + const struct net_device *dev, const void *ctx, struct notifier_block *nb) { return -EOPNOTSUPP; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 9d164a518e38..2e777c8b0921 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -727,7 +727,7 @@ static inline size_t fdb_nlmsg_size(void) } static int br_fdb_replay_one(struct notifier_block *nb, - struct net_bridge_fdb_entry *fdb, + const struct net_bridge_fdb_entry *fdb, struct net_device *dev, const void *ctx) { struct switchdev_notifier_fdb_info item; @@ -745,7 +745,7 @@ static int br_fdb_replay_one(struct notifier_block *nb, return notifier_to_errno(err); } -int br_fdb_replay(struct net_device *br_dev, struct net_device *dev, +int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev, const void *ctx, struct notifier_block *nb) { struct net_bridge_fdb_entry *fdb; @@ -760,7 +760,7 @@ int br_fdb_replay(struct net_device *br_dev, struct net_device *dev, rcu_read_lock(); hlist_for_each_entry_rcu(fdb, &br->fdb_list, fdb_node) { - struct net_bridge_port *dst = READ_ONCE(fdb->dst); + const struct net_bridge_port *dst = READ_ONCE(fdb->dst); struct net_device *dst_dev; dst_dev = dst ? dst->dev : br->dev; diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 8bc6afca5e8c..cebdbff17b54 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -567,7 +567,7 @@ static void br_switchdev_mdb_populate(struct switchdev_obj_port_mdb *mdb, } static int br_mdb_replay_one(struct notifier_block *nb, struct net_device *dev, - struct switchdev_obj_port_mdb *mdb, + const struct switchdev_obj_port_mdb *mdb, const void *ctx, struct netlink_ext_ack *extack) { struct switchdev_notifier_port_obj_info obj_info = { @@ -607,7 +607,7 @@ int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, const void *ctx, struct notifier_block *nb, struct netlink_ext_ack *extack) { - struct net_bridge_mdb_entry *mp; + const struct net_bridge_mdb_entry *mp; struct switchdev_obj *obj, *tmp; struct net_bridge *br; LIST_HEAD(mdb_list); @@ -634,8 +634,8 @@ int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, rcu_read_lock(); hlist_for_each_entry_rcu(mp, &br->mdb_list, mdb_node) { - struct net_bridge_port_group __rcu **pp; - struct net_bridge_port_group *p; + struct net_bridge_port_group __rcu * const *pp; + const struct net_bridge_port_group *p; if (mp->host_joined) { err = br_mdb_queue_one(&mdb_list, diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 3dafb6143cff..1d80f34a139c 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -639,9 +639,9 @@ int br_set_ageing_time(struct net_bridge *br, clock_t ageing_time) return 0; } -clock_t br_get_ageing_time(struct net_device *br_dev) +clock_t br_get_ageing_time(const struct net_device *br_dev) { - struct net_bridge *br; + const struct net_bridge *br; if (!netif_is_bridge_master(br_dev)) return 0; -- cgit v1.2.3-71-gd317 From 7e8c18586daf7c1653c4b43a8119bc9662ed8fa6 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 27 Jun 2021 14:54:27 +0300 Subject: net: bridge: allow the switchdev replay functions to be called for deletion When a switchdev port leaves a LAG that is a bridge port, the switchdev objects and port attributes offloaded to that port are not removed: ip link add br0 type bridge ip link add bond0 type bond mode 802.3ad ip link set swp0 master bond0 ip link set bond0 master br0 bridge vlan add dev bond0 vid 100 ip link set swp0 nomaster VLAN 100 will remain installed on swp0 despite it going into standalone mode, because as far as the bridge is concerned, nothing ever happened to its bridge port. Let's extend the bridge vlan, fdb and mdb replay functions to take a 'bool adding' argument, and make DSA and ocelot call the replay functions with 'adding' as false from the switchdev unsync path, for the switch port that leaves the bridge. Note that this patch in itself does not salvage anything, because in the current pull mode of operation, DSA still needs to call the replay helpers with adding=false. This will be done in another patch. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/mscc/ocelot_net.c | 4 ++-- include/linux/if_bridge.h | 12 ++++++------ net/bridge/br_fdb.c | 15 +++++++++++---- net/bridge/br_mdb.c | 15 +++++++++++---- net/bridge/br_vlan.c | 15 +++++++++++---- net/dsa/port.c | 13 ++++++------- 6 files changed, 47 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index 166d851962d2..3e89e34f86d5 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -1175,12 +1175,12 @@ static int ocelot_switchdev_sync(struct ocelot *ocelot, int port, ageing_time = br_get_ageing_time(bridge_dev); ocelot_port_attr_ageing_set(ocelot, port, ageing_time); - err = br_mdb_replay(bridge_dev, brport_dev, priv, + err = br_mdb_replay(bridge_dev, brport_dev, priv, true, &ocelot_switchdev_blocking_nb, extack); if (err && err != -EOPNOTSUPP) return err; - err = br_vlan_replay(bridge_dev, brport_dev, priv, + err = br_vlan_replay(bridge_dev, brport_dev, priv, true, &ocelot_switchdev_blocking_nb, extack); if (err && err != -EOPNOTSUPP) return err; diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 6b54da2c65ba..b651c5e32a28 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -71,7 +71,7 @@ bool br_multicast_has_router_adjacent(struct net_device *dev, int proto); bool br_multicast_enabled(const struct net_device *dev); bool br_multicast_router(const struct net_device *dev); int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, - const void *ctx, struct notifier_block *nb, + const void *ctx, bool adding, struct notifier_block *nb, struct netlink_ext_ack *extack); #else static inline int br_multicast_list_adjacent(struct net_device *dev, @@ -106,7 +106,7 @@ static inline bool br_multicast_router(const struct net_device *dev) } static inline int br_mdb_replay(const struct net_device *br_dev, const struct net_device *dev, const void *ctx, - struct notifier_block *nb, + bool adding, struct notifier_block *nb, struct netlink_ext_ack *extack) { return -EOPNOTSUPP; @@ -121,7 +121,7 @@ int br_vlan_get_proto(const struct net_device *dev, u16 *p_proto); int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo); int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, - const void *ctx, struct notifier_block *nb, + const void *ctx, bool adding, struct notifier_block *nb, struct netlink_ext_ack *extack); #else static inline bool br_vlan_enabled(const struct net_device *dev) @@ -152,7 +152,7 @@ static inline int br_vlan_get_info(const struct net_device *dev, u16 vid, static inline int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, const void *ctx, - struct notifier_block *nb, + bool adding, struct notifier_block *nb, struct netlink_ext_ack *extack) { return -EOPNOTSUPP; @@ -168,7 +168,7 @@ bool br_port_flag_is_set(const struct net_device *dev, unsigned long flag); u8 br_port_get_stp_state(const struct net_device *dev); clock_t br_get_ageing_time(const struct net_device *br_dev); int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev, - const void *ctx, struct notifier_block *nb); + const void *ctx, bool adding, struct notifier_block *nb); #else static inline struct net_device * br_fdb_find_port(const struct net_device *br_dev, @@ -200,7 +200,7 @@ static inline clock_t br_get_ageing_time(const struct net_device *br_dev) static inline int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev, const void *ctx, - struct notifier_block *nb) + bool adding, struct notifier_block *nb) { return -EOPNOTSUPP; } diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 2e777c8b0921..16f9434fdb5d 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -728,7 +728,8 @@ static inline size_t fdb_nlmsg_size(void) static int br_fdb_replay_one(struct notifier_block *nb, const struct net_bridge_fdb_entry *fdb, - struct net_device *dev, const void *ctx) + struct net_device *dev, unsigned long action, + const void *ctx) { struct switchdev_notifier_fdb_info item; int err; @@ -741,15 +742,16 @@ static int br_fdb_replay_one(struct notifier_block *nb, item.info.dev = dev; item.info.ctx = ctx; - err = nb->notifier_call(nb, SWITCHDEV_FDB_ADD_TO_DEVICE, &item); + err = nb->notifier_call(nb, action, &item); return notifier_to_errno(err); } int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev, - const void *ctx, struct notifier_block *nb) + const void *ctx, bool adding, struct notifier_block *nb) { struct net_bridge_fdb_entry *fdb; struct net_bridge *br; + unsigned long action; int err = 0; if (!netif_is_bridge_master(br_dev) || !netif_is_bridge_port(dev)) @@ -757,6 +759,11 @@ int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev, br = netdev_priv(br_dev); + if (adding) + action = SWITCHDEV_FDB_ADD_TO_DEVICE; + else + action = SWITCHDEV_FDB_DEL_TO_DEVICE; + rcu_read_lock(); hlist_for_each_entry_rcu(fdb, &br->fdb_list, fdb_node) { @@ -767,7 +774,7 @@ int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev, if (dst_dev != br_dev && dst_dev != dev) continue; - err = br_fdb_replay_one(nb, fdb, dst_dev, ctx); + err = br_fdb_replay_one(nb, fdb, dst_dev, action, ctx); if (err) break; } diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index cebdbff17b54..17a720b4473f 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -568,7 +568,8 @@ static void br_switchdev_mdb_populate(struct switchdev_obj_port_mdb *mdb, static int br_mdb_replay_one(struct notifier_block *nb, struct net_device *dev, const struct switchdev_obj_port_mdb *mdb, - const void *ctx, struct netlink_ext_ack *extack) + unsigned long action, const void *ctx, + struct netlink_ext_ack *extack) { struct switchdev_notifier_port_obj_info obj_info = { .info = { @@ -580,7 +581,7 @@ static int br_mdb_replay_one(struct notifier_block *nb, struct net_device *dev, }; int err; - err = nb->notifier_call(nb, SWITCHDEV_PORT_OBJ_ADD, &obj_info); + err = nb->notifier_call(nb, action, &obj_info); return notifier_to_errno(err); } @@ -604,12 +605,13 @@ static int br_mdb_queue_one(struct list_head *mdb_list, } int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, - const void *ctx, struct notifier_block *nb, + const void *ctx, bool adding, struct notifier_block *nb, struct netlink_ext_ack *extack) { const struct net_bridge_mdb_entry *mp; struct switchdev_obj *obj, *tmp; struct net_bridge *br; + unsigned long action; LIST_HEAD(mdb_list); int err = 0; @@ -664,9 +666,14 @@ int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, rcu_read_unlock(); + if (adding) + action = SWITCHDEV_PORT_OBJ_ADD; + else + action = SWITCHDEV_PORT_OBJ_DEL; + list_for_each_entry(obj, &mdb_list, list) { err = br_mdb_replay_one(nb, dev, SWITCHDEV_OBJ_PORT_MDB(obj), - ctx, extack); + action, ctx, extack); if (err) goto out_free_mdb; } diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 2bfa2a00e193..a08e9f193009 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -1807,7 +1807,8 @@ out_kfree: static int br_vlan_replay_one(struct notifier_block *nb, struct net_device *dev, struct switchdev_obj_port_vlan *vlan, - const void *ctx, struct netlink_ext_ack *extack) + const void *ctx, unsigned long action, + struct netlink_ext_ack *extack) { struct switchdev_notifier_port_obj_info obj_info = { .info = { @@ -1819,18 +1820,19 @@ static int br_vlan_replay_one(struct notifier_block *nb, }; int err; - err = nb->notifier_call(nb, SWITCHDEV_PORT_OBJ_ADD, &obj_info); + err = nb->notifier_call(nb, action, &obj_info); return notifier_to_errno(err); } int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, - const void *ctx, struct notifier_block *nb, + const void *ctx, bool adding, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct net_bridge_port *p; struct net_bridge *br; + unsigned long action; int err = 0; u16 pvid; @@ -1857,6 +1859,11 @@ int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, if (!vg) return 0; + if (adding) + action = SWITCHDEV_PORT_OBJ_ADD; + else + action = SWITCHDEV_PORT_OBJ_DEL; + pvid = br_get_pvid(vg); list_for_each_entry(v, &vg->vlan_list, vlist) { @@ -1870,7 +1877,7 @@ int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, if (!br_vlan_should_use(v)) continue; - err = br_vlan_replay_one(nb, dev, &vlan, ctx, extack); + err = br_vlan_replay_one(nb, dev, &vlan, ctx, action, extack); if (err) return err; } diff --git a/net/dsa/port.c b/net/dsa/port.c index 339781c98de1..4e58d07ececd 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -194,19 +194,18 @@ static int dsa_port_switchdev_sync(struct dsa_port *dp, if (err && err != -EOPNOTSUPP) return err; - err = br_mdb_replay(br, brport_dev, dp, - &dsa_slave_switchdev_blocking_notifier, - extack); + err = br_mdb_replay(br, brport_dev, dp, true, + &dsa_slave_switchdev_blocking_notifier, extack); if (err && err != -EOPNOTSUPP) return err; - err = br_fdb_replay(br, brport_dev, dp, &dsa_slave_switchdev_notifier); + err = br_fdb_replay(br, brport_dev, dp, true, + &dsa_slave_switchdev_notifier); if (err && err != -EOPNOTSUPP) return err; - err = br_vlan_replay(br, brport_dev, dp, - &dsa_slave_switchdev_blocking_notifier, - extack); + err = br_vlan_replay(br, brport_dev, dp, true, + &dsa_slave_switchdev_blocking_notifier, extack); if (err && err != -EOPNOTSUPP) return err; -- cgit v1.2.3-71-gd317 From a358f40600b3b39ae3906b6118625b99c0aa7a34 Mon Sep 17 00:00:00 2001 From: Tanner Love Date: Mon, 28 Jun 2021 09:50:06 -0400 Subject: once: implement DO_ONCE_LITE for non-fast-path "do once" functionality Certain uses of "do once" functionality reside outside of fast path, and so do not require jump label patching via static keys, making existing DO_ONCE undesirable in such cases. Replace uses of __section(".data.once") with DO_ONCE_LITE(_IF)? This patch changes the return values of xfs_printk_once, printk_once, and printk_deferred_once. Before, they returned whether the print was performed, but now, they always return true. This is okay because the return values of the following macros are entirely ignored throughout the kernel: - xfs_printk_once - xfs_warn_once - xfs_notice_once - xfs_info_once - printk_once - pr_emerg_once - pr_alert_once - pr_crit_once - pr_err_once - pr_warn_once - pr_notice_once - pr_info_once - pr_devel_once - pr_debug_once - printk_deferred_once - orc_warn Changes v3: - Expand commit message to explain why changing return values of xfs_printk_once, printk_once, printk_deferred_once is benign v2: - Fix i386 build warnings Signed-off-by: Tanner Love Acked-by: Eric Dumazet Acked-by: Mahesh Bandewar Acked-by: Steven Rostedt (VMware) Signed-off-by: David S. Miller --- fs/xfs/xfs_message.h | 13 +++---------- include/asm-generic/bug.h | 37 +++++++------------------------------ include/linux/once_lite.h | 24 ++++++++++++++++++++++++ include/linux/printk.h | 23 +++-------------------- kernel/trace/trace.h | 13 +++---------- 5 files changed, 40 insertions(+), 70 deletions(-) create mode 100644 include/linux/once_lite.h (limited to 'include/linux') diff --git a/fs/xfs/xfs_message.h b/fs/xfs/xfs_message.h index 7ec1a9207517..bb9860ec9a93 100644 --- a/fs/xfs/xfs_message.h +++ b/fs/xfs/xfs_message.h @@ -2,6 +2,8 @@ #ifndef __XFS_MESSAGE_H #define __XFS_MESSAGE_H 1 +#include + struct xfs_mount; extern __printf(2, 3) @@ -41,16 +43,7 @@ do { \ } while (0) #define xfs_printk_once(func, dev, fmt, ...) \ -({ \ - static bool __section(".data.once") __print_once; \ - bool __ret_print_once = !__print_once; \ - \ - if (!__print_once) { \ - __print_once = true; \ - func(dev, fmt, ##__VA_ARGS__); \ - } \ - unlikely(__ret_print_once); \ -}) + DO_ONCE_LITE(func, dev, fmt, ##__VA_ARGS__) #define xfs_emerg_ratelimited(dev, fmt, ...) \ xfs_printk_ratelimited(xfs_emerg, dev, fmt, ##__VA_ARGS__) diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index b402494883b6..bafc51f483c4 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -4,6 +4,7 @@ #include #include +#include #define CUT_HERE "------------[ cut here ]------------\n" @@ -140,39 +141,15 @@ void __warn(const char *file, int line, void *caller, unsigned taint, }) #ifndef WARN_ON_ONCE -#define WARN_ON_ONCE(condition) ({ \ - static bool __section(".data.once") __warned; \ - int __ret_warn_once = !!(condition); \ - \ - if (unlikely(__ret_warn_once && !__warned)) { \ - __warned = true; \ - WARN_ON(1); \ - } \ - unlikely(__ret_warn_once); \ -}) +#define WARN_ON_ONCE(condition) \ + DO_ONCE_LITE_IF(condition, WARN_ON, 1) #endif -#define WARN_ONCE(condition, format...) ({ \ - static bool __section(".data.once") __warned; \ - int __ret_warn_once = !!(condition); \ - \ - if (unlikely(__ret_warn_once && !__warned)) { \ - __warned = true; \ - WARN(1, format); \ - } \ - unlikely(__ret_warn_once); \ -}) +#define WARN_ONCE(condition, format...) \ + DO_ONCE_LITE_IF(condition, WARN, 1, format) -#define WARN_TAINT_ONCE(condition, taint, format...) ({ \ - static bool __section(".data.once") __warned; \ - int __ret_warn_once = !!(condition); \ - \ - if (unlikely(__ret_warn_once && !__warned)) { \ - __warned = true; \ - WARN_TAINT(1, taint, format); \ - } \ - unlikely(__ret_warn_once); \ -}) +#define WARN_TAINT_ONCE(condition, taint, format...) \ + DO_ONCE_LITE_IF(condition, WARN_TAINT, 1, taint, format) #else /* !CONFIG_BUG */ #ifndef HAVE_ARCH_BUG diff --git a/include/linux/once_lite.h b/include/linux/once_lite.h new file mode 100644 index 000000000000..861e606b820f --- /dev/null +++ b/include/linux/once_lite.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_ONCE_LITE_H +#define _LINUX_ONCE_LITE_H + +#include + +/* Call a function once. Similar to DO_ONCE(), but does not use jump label + * patching via static keys. + */ +#define DO_ONCE_LITE(func, ...) \ + DO_ONCE_LITE_IF(true, func, ##__VA_ARGS__) +#define DO_ONCE_LITE_IF(condition, func, ...) \ + ({ \ + static bool __section(".data.once") __already_done; \ + bool __ret_do_once = !!(condition); \ + \ + if (unlikely(__ret_do_once && !__already_done)) { \ + __already_done = true; \ + func(__VA_ARGS__); \ + } \ + unlikely(__ret_do_once); \ + }) + +#endif /* _LINUX_ONCE_LITE_H */ diff --git a/include/linux/printk.h b/include/linux/printk.h index fe7eb2351610..885379a1c9a1 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -8,6 +8,7 @@ #include #include #include +#include extern const char linux_banner[]; extern const char linux_proc_banner[]; @@ -436,27 +437,9 @@ extern int kptr_restrict; #ifdef CONFIG_PRINTK #define printk_once(fmt, ...) \ -({ \ - static bool __section(".data.once") __print_once; \ - bool __ret_print_once = !__print_once; \ - \ - if (!__print_once) { \ - __print_once = true; \ - printk(fmt, ##__VA_ARGS__); \ - } \ - unlikely(__ret_print_once); \ -}) + DO_ONCE_LITE(printk, fmt, ##__VA_ARGS__) #define printk_deferred_once(fmt, ...) \ -({ \ - static bool __section(".data.once") __print_once; \ - bool __ret_print_once = !__print_once; \ - \ - if (!__print_once) { \ - __print_once = true; \ - printk_deferred(fmt, ##__VA_ARGS__); \ - } \ - unlikely(__ret_print_once); \ -}) + DO_ONCE_LITE(printk_deferred, fmt, ##__VA_ARGS__) #else #define printk_once(fmt, ...) \ no_printk(fmt, ##__VA_ARGS__) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index cd80d046c7a5..d5d8c088a55d 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -20,6 +20,7 @@ #include #include #include +#include #ifdef CONFIG_FTRACE_SYSCALLS #include /* For NR_SYSCALLS */ @@ -99,16 +100,8 @@ enum trace_type { #include "trace_entries.h" /* Use this for memory failure errors */ -#define MEM_FAIL(condition, fmt, ...) ({ \ - static bool __section(".data.once") __warned; \ - int __ret_warn_once = !!(condition); \ - \ - if (unlikely(__ret_warn_once && !__warned)) { \ - __warned = true; \ - pr_err("ERROR: " fmt, ##__VA_ARGS__); \ - } \ - unlikely(__ret_warn_once); \ -}) +#define MEM_FAIL(condition, fmt, ...) \ + DO_ONCE_LITE_IF(condition, pr_err, "ERROR: " fmt, ##__VA_ARGS__) /* * syscalls are special, and need special handling, this is why -- cgit v1.2.3-71-gd317 From e3ae2365efc14269170a6326477e669332271ab3 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Sun, 27 Jun 2021 18:48:21 -0400 Subject: net: sock: introduce sk_error_report This patch introduces a function wrapper to call the sk_error_report callback. That will prepare to add additional handling whenever sk_error_report is called, for example to trace socket errors. Signed-off-by: Alexander Aring Signed-off-by: David S. Miller --- .../ethernet/chelsio/inline_crypto/chtls/chtls_cm.c | 2 +- drivers/vhost/vsock.c | 2 +- include/linux/skmsg.h | 2 +- include/net/sock.h | 2 ++ include/net/tls.h | 2 +- net/caif/caif_socket.c | 2 +- net/can/bcm.c | 4 ++-- net/can/isotp.c | 20 ++++++++++---------- net/can/j1939/socket.c | 4 ++-- net/can/raw.c | 6 +++--- net/core/skbuff.c | 6 +++--- net/core/sock.c | 6 ++++++ net/dccp/ipv4.c | 4 ++-- net/dccp/ipv6.c | 4 ++-- net/dccp/proto.c | 2 +- net/dccp/timer.c | 2 +- net/ipv4/ping.c | 2 +- net/ipv4/raw.c | 4 ++-- net/ipv4/tcp.c | 4 ++-- net/ipv4/tcp_input.c | 2 +- net/ipv4/tcp_ipv4.c | 4 ++-- net/ipv4/tcp_timer.c | 2 +- net/ipv4/udp.c | 4 ++-- net/ipv6/raw.c | 2 +- net/ipv6/tcp_ipv6.c | 4 ++-- net/ipv6/udp.c | 2 +- net/kcm/kcmsock.c | 2 +- net/mptcp/subflow.c | 2 +- net/netlink/af_netlink.c | 8 ++++---- net/nfc/rawsock.c | 2 +- net/packet/af_packet.c | 4 ++-- net/qrtr/qrtr.c | 2 +- net/sctp/input.c | 2 +- net/sctp/ipv6.c | 2 +- net/smc/af_smc.c | 2 +- net/strparser/strparser.c | 2 +- net/unix/af_unix.c | 2 +- net/vmw_vsock/af_vsock.c | 2 +- net/vmw_vsock/virtio_transport.c | 2 +- net/vmw_vsock/virtio_transport_common.c | 2 +- net/vmw_vsock/vmci_transport.c | 4 ++-- net/xdp/xsk.c | 2 +- 42 files changed, 75 insertions(+), 67 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c index 19dc7dc054a2..bcad69c48074 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c @@ -2134,7 +2134,7 @@ static void chtls_abort_req_rss(struct sock *sk, struct sk_buff *skb) sk->sk_err = ETIMEDOUT; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); if (sk->sk_state == TCP_SYN_RECV && !abort_syn_rcv(sk, skb)) return; diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 119f08491d3c..d38c996b4f46 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -734,7 +734,7 @@ static void vhost_vsock_reset_orphans(struct sock *sk) vsk->peer_shutdown = SHUTDOWN_MASK; sk->sk_state = SS_UNCONNECTED; sk->sk_err = ECONNRESET; - sk->sk_error_report(sk); + sk_error_report(sk); } static int vhost_vsock_dev_release(struct inode *inode, struct file *file) diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index fcaa9a7996c8..31866031e370 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -347,7 +347,7 @@ static inline void sk_psock_report_error(struct sk_psock *psock, int err) struct sock *sk = psock->sk; sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } struct sk_psock *sk_psock_init(struct sock *sk, int node); diff --git a/include/net/sock.h b/include/net/sock.h index ced2fc965ec7..8bdd80027ffb 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2281,6 +2281,8 @@ static inline int sock_error(struct sock *sk) return -err; } +void sk_error_report(struct sock *sk); + static inline unsigned long sock_wspace(struct sock *sk) { int amt = 0; diff --git a/include/net/tls.h b/include/net/tls.h index 8d398a5de3ee..be4b3e1cac46 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -469,7 +469,7 @@ static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk) static inline void tls_err_abort(struct sock *sk, int err) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } static inline bool tls_bigint_increment(unsigned char *seq, int len) diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 3ad0a1df6712..647554c9813b 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -243,7 +243,7 @@ static void caif_ctrl_cb(struct cflayer *layr, cf_sk->sk.sk_shutdown = SHUTDOWN_MASK; cf_sk->sk.sk_err = ECONNRESET; set_rx_flow_on(cf_sk); - cf_sk->sk.sk_error_report(&cf_sk->sk); + sk_error_report(&cf_sk->sk); break; default: diff --git a/net/can/bcm.c b/net/can/bcm.c index f3e4d9528fa3..e15a7dbe5f6c 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1417,7 +1417,7 @@ static void bcm_notify(struct bcm_sock *bo, unsigned long msg, if (notify_enodev) { sk->sk_err = ENODEV; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); } break; @@ -1425,7 +1425,7 @@ static void bcm_notify(struct bcm_sock *bo, unsigned long msg, if (bo->bound && bo->ifindex == dev->ifindex) { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); } } } diff --git a/net/can/isotp.c b/net/can/isotp.c index bd49299319a1..9fd274cf166b 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -168,7 +168,7 @@ static enum hrtimer_restart isotp_rx_timer_handler(struct hrtimer *hrtimer) /* report 'connection timed out' */ sk->sk_err = ETIMEDOUT; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); /* reset rx state */ so->rx.state = ISOTP_IDLE; @@ -339,7 +339,7 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) /* malformed PDU - report 'not a data message' */ sk->sk_err = EBADMSG; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); so->tx.state = ISOTP_IDLE; wake_up_interruptible(&so->wait); @@ -392,7 +392,7 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) /* overflow on receiver side - report 'message too long' */ sk->sk_err = EMSGSIZE; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); fallthrough; default: @@ -420,7 +420,7 @@ static int isotp_rcv_sf(struct sock *sk, struct canfd_frame *cf, int pcilen, /* malformed PDU - report 'not a data message' */ sk->sk_err = EBADMSG; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); return 1; } @@ -535,7 +535,7 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae, /* wrong sn detected - report 'illegal byte sequence' */ sk->sk_err = EILSEQ; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); /* reset rx state */ so->rx.state = ISOTP_IDLE; @@ -559,7 +559,7 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae, /* malformed PDU - report 'not a data message' */ sk->sk_err = EBADMSG; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); return 1; } @@ -758,7 +758,7 @@ static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) /* report 'communication error on send' */ sk->sk_err = ECOMM; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); /* reset tx state */ so->tx.state = ISOTP_IDLE; @@ -1157,7 +1157,7 @@ out: if (notify_enetdown) { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); } return err; @@ -1356,13 +1356,13 @@ static void isotp_notify(struct isotp_sock *so, unsigned long msg, sk->sk_err = ENODEV; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); break; case NETDEV_DOWN: sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); break; } } diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 56aa66147d5a..bf18a32dc6ae 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -1009,7 +1009,7 @@ void j1939_sk_send_loop_abort(struct sock *sk, int err) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } static int j1939_sk_send_loop(struct j1939_priv *priv, struct sock *sk, @@ -1189,7 +1189,7 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv) list_for_each_entry(jsk, &priv->j1939_socks, list) { jsk->sk.sk_err = error_code; if (!sock_flag(&jsk->sk, SOCK_DEAD)) - jsk->sk.sk_error_report(&jsk->sk); + sk_error_report(&jsk->sk); j1939_sk_queue_drop_all(priv, jsk, error_code); } diff --git a/net/can/raw.c b/net/can/raw.c index ac96fc210025..ed4fcb7ab0c3 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -295,13 +295,13 @@ static void raw_notify(struct raw_sock *ro, unsigned long msg, sk->sk_err = ENODEV; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); break; case NETDEV_DOWN: sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); break; } } @@ -488,7 +488,7 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (notify_enetdown) { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); } return err; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2531ac4ffa69..12aabcda6db2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1294,7 +1294,7 @@ static void __msg_zerocopy_callback(struct ubuf_info *uarg) } spin_unlock_irqrestore(&q->lock, flags); - sk->sk_error_report(sk); + sk_error_report(sk); release: consume_skb(skb); @@ -4685,7 +4685,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) skb_queue_tail(&sk->sk_error_queue, skb); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); return 0; } EXPORT_SYMBOL(sock_queue_err_skb); @@ -4716,7 +4716,7 @@ struct sk_buff *sock_dequeue_err_skb(struct sock *sk) sk->sk_err = 0; if (skb_next) - sk->sk_error_report(sk); + sk_error_report(sk); return skb; } diff --git a/net/core/sock.c b/net/core/sock.c index a2337b37eba6..c30f8f4cbb22 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -331,6 +331,12 @@ int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(__sk_backlog_rcv); +void sk_error_report(struct sock *sk) +{ + sk->sk_error_report(sk); +} +EXPORT_SYMBOL(sk_error_report); + static int sock_get_timeout(long timeo, void *optval, bool old_timeval) { struct __kernel_sock_timeval tv; diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index f81c1df761d3..0ea29270d7e5 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -329,7 +329,7 @@ static int dccp_v4_err(struct sk_buff *skb, u32 info) __DCCP_INC_STATS(DCCP_MIB_ATTEMPTFAILS); sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); dccp_done(sk); } else @@ -356,7 +356,7 @@ static int dccp_v4_err(struct sk_buff *skb, u32 info) inet = inet_sk(sk); if (!sock_owned_by_user(sk) && inet->recverr) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } else /* Only an error on timeout */ sk->sk_err_soft = err; out: diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 6f5304db5a67..fa663518fa0e 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -172,7 +172,7 @@ static int dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, * Wake people up to see the error * (see connect in sock.c) */ - sk->sk_error_report(sk); + sk_error_report(sk); dccp_done(sk); } else sk->sk_err_soft = err; @@ -181,7 +181,7 @@ static int dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!sock_owned_by_user(sk) && np->recverr) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } else sk->sk_err_soft = err; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 6d705d90c614..7eb0fb231940 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -302,7 +302,7 @@ int dccp_disconnect(struct sock *sk, int flags) WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); - sk->sk_error_report(sk); + sk_error_report(sk); return 0; } diff --git a/net/dccp/timer.c b/net/dccp/timer.c index db768f223ef7..27a3b37acd2e 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -20,7 +20,7 @@ int sysctl_dccp_retries2 __read_mostly = TCP_RETR2; static void dccp_write_err(struct sock *sk) { sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT; - sk->sk_error_report(sk); + sk_error_report(sk); dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED); dccp_done(sk); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 95a718397fd1..1e44a43acfe2 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -573,7 +573,7 @@ void ping_err(struct sk_buff *skb, int offset, u32 info) } } sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); out: sock_put(sk); } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 50a73178d63a..bb446e60cf58 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -280,7 +280,7 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) if (inet->recverr || harderr) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } } @@ -929,7 +929,7 @@ int raw_abort(struct sock *sk, int err) lock_sock(sk); sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); __udp_disconnect(sk, 0); release_sock(sk); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0e3f0e0e5b51..a0a96eb826c4 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3059,7 +3059,7 @@ int tcp_disconnect(struct sock *sk, int flags) sk->sk_frag.offset = 0; } - sk->sk_error_report(sk); + sk_error_report(sk); return 0; } EXPORT_SYMBOL(tcp_disconnect); @@ -4448,7 +4448,7 @@ int tcp_abort(struct sock *sk, int err) sk->sk_err = err; /* This barrier is coupled with smp_rmb() in tcp_poll() */ smp_wmb(); - sk->sk_error_report(sk); + sk_error_report(sk); if (tcp_need_reset(sk->sk_state)) tcp_send_active_reset(sk, GFP_ATOMIC); tcp_done(sk); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 7d5e59f688de..e6ca5a1f3b59 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4270,7 +4270,7 @@ void tcp_reset(struct sock *sk, struct sk_buff *skb) tcp_done(sk); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); } /* diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 6cb8e269f1ab..e66ad6bfe808 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -585,7 +585,7 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) if (!sock_owned_by_user(sk)) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); tcp_done(sk); } else { @@ -613,7 +613,7 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) inet = inet_sk(sk); if (!sock_owned_by_user(sk) && inet->recverr) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } else { /* Only an error on timeout */ sk->sk_err_soft = err; } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 56b9d648f054..20cf4a98c69d 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -68,7 +68,7 @@ u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when) static void tcp_write_err(struct sock *sk) { sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT; - sk->sk_error_report(sk); + sk_error_report(sk); tcp_write_queue_purge(sk); tcp_done(sk); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1307ad0d3b9e..f86ccbf7c135 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -776,7 +776,7 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) ip_icmp_error(sk, skb, err, uh->dest, info, (u8 *)(uh+1)); sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); out: return 0; } @@ -2867,7 +2867,7 @@ int udp_abort(struct sock *sk, int err) goto out; sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); __udp_disconnect(sk, 0); out: diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index bf3646b57c68..60f1e4f5be5a 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -354,7 +354,7 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb, if (np->recverr || harderr) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 4d71464094b3..578ab6305c3f 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -467,7 +467,7 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!sock_owned_by_user(sk)) { sk->sk_err = err; - sk->sk_error_report(sk); /* Wake people up to see the error (see connect in sock.c) */ + sk_error_report(sk); /* Wake people up to see the error (see connect in sock.c) */ tcp_done(sk); } else @@ -486,7 +486,7 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!sock_owned_by_user(sk) && np->recverr) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } else sk->sk_err_soft = err; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 3fcd86f4dfdc..368972dbd919 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -610,7 +610,7 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); out: return 0; } diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 6201965bd822..11a715d76a4f 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -47,7 +47,7 @@ static inline struct kcm_tx_msg *kcm_tx_msg(struct sk_buff *skb) static void report_csk_error(struct sock *csk, int err) { csk->sk_err = EPIPE; - csk->sk_error_report(csk); + sk_error_report(csk); } static void kcm_abort_tx_psock(struct kcm_psock *psock, int err, diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index d55f4ef736a5..706a26a1b0fe 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1240,7 +1240,7 @@ void __mptcp_error_report(struct sock *sk) /* This barrier is coupled with smp_rmb() in mptcp_poll() */ smp_wmb(); - sk->sk_error_report(sk); + sk_error_report(sk); break; } } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 6133e412b948..d233ac4a91b6 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -351,7 +351,7 @@ static void netlink_overrun(struct sock *sk) if (!test_and_set_bit(NETLINK_S_CONGESTED, &nlk_sk(sk)->state)) { sk->sk_err = ENOBUFS; - sk->sk_error_report(sk); + sk_error_report(sk); } } atomic_inc(&sk->sk_drops); @@ -1576,7 +1576,7 @@ static int do_one_set_err(struct sock *sk, struct netlink_set_err_data *p) } sk->sk_err = p->code; - sk->sk_error_report(sk); + sk_error_report(sk); out: return ret; } @@ -2012,7 +2012,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, ret = netlink_dump(sk); if (ret) { sk->sk_err = -ret; - sk->sk_error_report(sk); + sk_error_report(sk); } } @@ -2439,7 +2439,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, skb = nlmsg_new(payload + tlvlen, GFP_KERNEL); if (!skb) { NETLINK_CB(in_skb).sk->sk_err = ENOBUFS; - NETLINK_CB(in_skb).sk->sk_error_report(NETLINK_CB(in_skb).sk); + sk_error_report(NETLINK_CB(in_skb).sk); return; } diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index 5f1d438a0a23..5e39640becdb 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -49,7 +49,7 @@ static void rawsock_report_error(struct sock *sk, int err) sk->sk_shutdown = SHUTDOWN_MASK; sk->sk_err = -err; - sk->sk_error_report(sk); + sk_error_report(sk); rawsock_write_queue_purge(sk); } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 77b0cdab3810..77476184741d 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3206,7 +3206,7 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, } else { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); } out_unlock: @@ -4103,7 +4103,7 @@ static int packet_notifier(struct notifier_block *this, __unregister_prot_hook(sk, false); sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); } if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index f2efaa4225f9..e6f4a6202f82 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -751,7 +751,7 @@ static void qrtr_reset_ports(void) xa_for_each_start(&qrtr_ports, index, ipc, 1) { sock_hold(&ipc->sk); ipc->sk.sk_err = ENETRESET; - ipc->sk.sk_error_report(&ipc->sk); + sk_error_report(&ipc->sk); sock_put(&ipc->sk); } rcu_read_unlock(); diff --git a/net/sctp/input.c b/net/sctp/input.c index fe6429cc012f..76dcc137f761 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -593,7 +593,7 @@ static void sctp_v4_err_handle(struct sctp_transport *t, struct sk_buff *skb, } if (!sock_owned_by_user(sk) && inet_sk(sk)->recverr) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } else { /* Only an error on timeout */ sk->sk_err_soft = err; } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 05f81a4d0ee7..d041bed86322 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -152,7 +152,7 @@ static void sctp_v6_err_handle(struct sctp_transport *t, struct sk_buff *skb, icmpv6_err_convert(type, code, &err); if (!sock_owned_by_user(sk) && np->recverr) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } else { sk->sk_err_soft = err; } diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index e41fdac606d4..898389611ae8 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2218,7 +2218,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, optval, optlen); if (smc->clcsock->sk->sk_err) { sk->sk_err = smc->clcsock->sk->sk_err; - sk->sk_error_report(sk); + sk_error_report(sk); } if (optlen < sizeof(int)) diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index b3815c1e8f2e..9c0343568d2a 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -58,7 +58,7 @@ static void strp_abort_strp(struct strparser *strp, int err) /* Report an error on the lower socket */ sk->sk_err = -err; - sk->sk_error_report(sk); + sk_error_report(sk); } } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 58c2f318b0a8..23c92ad15c61 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -491,7 +491,7 @@ static void unix_dgram_disconnected(struct sock *sk, struct sock *other) */ if (!sock_flag(other, SOCK_DEAD) && unix_peer(other) == sk) { other->sk_err = ECONNRESET; - other->sk_error_report(other); + sk_error_report(other); } } } diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 21ccf450e249..9f12da1ff406 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1281,7 +1281,7 @@ static void vsock_connect_timeout(struct work_struct *work) (sk->sk_shutdown != SHUTDOWN_MASK)) { sk->sk_state = TCP_CLOSE; sk->sk_err = ETIMEDOUT; - sk->sk_error_report(sk); + sk_error_report(sk); vsock_transport_cancel_pkt(vsk); } release_sock(sk); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index ed1664e7bd88..e0c2c992ad9c 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -360,7 +360,7 @@ static void virtio_vsock_reset_sock(struct sock *sk) lock_sock(sk); sk->sk_state = TCP_CLOSE; sk->sk_err = ECONNRESET; - sk->sk_error_report(sk); + sk_error_report(sk); release_sock(sk); } diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index f014ccfdd9c2..169ba8b72a63 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1007,7 +1007,7 @@ destroy: virtio_transport_reset(vsk, pkt); sk->sk_state = TCP_CLOSE; sk->sk_err = skerr; - sk->sk_error_report(sk); + sk_error_report(sk); return err; } diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index e617ed93f06b..7aef34e32bdf 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -831,7 +831,7 @@ static void vmci_transport_handle_detach(struct sock *sk) sk->sk_state = TCP_CLOSE; sk->sk_err = ECONNRESET; - sk->sk_error_report(sk); + sk_error_report(sk); return; } sk->sk_state = TCP_CLOSE; @@ -1365,7 +1365,7 @@ destroy: sk->sk_state = TCP_CLOSE; sk->sk_err = skerr; - sk->sk_error_report(sk); + sk_error_report(sk); return err; } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 996da915f520..d6b500dc4208 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -1313,7 +1313,7 @@ static int xsk_notifier(struct notifier_block *this, if (xs->dev == dev) { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); xsk_unbind_dev(xs); -- cgit v1.2.3-71-gd317 From 5a9b876e9d76810536bac70c78d961198612919c Mon Sep 17 00:00:00 2001 From: Ling Pei Lee Date: Tue, 29 Jun 2021 11:08:57 +0800 Subject: net: stmmac: option to enable PHY WOL with PMT enabled The current stmmac driver WOL implementation will enable MAC WOL if MAC HW PMT feature is on. Else, the driver will check for PHY WOL support. There is another case where MAC HW PMT is enabled but the platform still goes for the PHY WOL option. E.g, Intel platform are designed for PHY WOL but not MAC WOL although HW MAC PMT features are enabled. Introduce use_phy_wol platform data to select PHY WOL instead of depending on HW PMT features. Set use_phy_wol will disable the plat->pmt which currently used to determine the system to wake up by MAC WOL or PHY WOL. Signed-off-by: Ling Pei Lee Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 ++- include/linux/stmmac.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 219535ab2c0c..8d9d6ecf8c63 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -6529,7 +6529,8 @@ static int stmmac_hw_init(struct stmmac_priv *priv) * register (if supported). */ priv->plat->enh_desc = priv->dma_cap.enh_desc; - priv->plat->pmt = priv->dma_cap.pmt_remote_wake_up; + priv->plat->pmt = priv->dma_cap.pmt_remote_wake_up && + !priv->plat->use_phy_wol; priv->hw->pmt = priv->plat->pmt; if (priv->dma_cap.hash_tb_sz) { priv->hw->multicast_filter_bins = diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 3867980d1447..d5ae621d66ba 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -265,5 +265,6 @@ struct plat_stmmacenet_data { int msi_sfty_ue_vec; int msi_rx_base_vec; int msi_tx_base_vec; + bool use_phy_wol; }; #endif -- cgit v1.2.3-71-gd317