From 23a1f8d44c0bca48f04fc2a2f1edafd826ce6133 Mon Sep 17 00:00:00 2001 From: Sara Sharon Date: Tue, 8 Dec 2015 16:04:31 +0200 Subject: mac80211: process and save VHT MU-MIMO group frame The Group ID Management frame is an Action frame of category VHT. It is transmitted by the AP to assign or change the user position of a STA for one or more group IDs. Process and save the group membership data. Notify underlying driver of changes. Signed-off-by: Sara Sharon Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 452c0b0d2f32..d9ddb89533a7 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -843,6 +843,8 @@ enum ieee80211_vht_opmode_bits { }; #define WLAN_SA_QUERY_TR_ID_LEN 2 +#define WLAN_MEMBERSHIP_LEN 8 +#define WLAN_USER_POSITION_LEN 16 /** * struct ieee80211_tpc_report_ie @@ -989,6 +991,11 @@ struct ieee80211_mgmt { u8 action_code; u8 operating_mode; } __packed vht_opmode_notif; + struct { + u8 action_code; + u8 membership[WLAN_MEMBERSHIP_LEN]; + u8 position[WLAN_USER_POSITION_LEN]; + } __packed vht_group_notif; struct { u8 action_code; u8 dialog_token; -- cgit v1.2.3 From 6a84f57241e1fb9fb6772256f538d1073359a32d Mon Sep 17 00:00:00 2001 From: Gayatri Kammela Date: Thu, 21 Jan 2016 14:02:39 -0800 Subject: raid6/algos.c : bug fix : Add the missing definitions to the pq.h file Adding these pr_info and pr_err definitions so as to allow code to be compiled successfully for testing in userspace, since the printk has been replaced by pr_info and pr_err in algos.c Absence of these definitions result in the compilation errors such as ' undefined reference to `pr_info' ' ' undefined reference to `pr_err' ' Cc: NeilBrown Cc: Anton Blanchard Cc: Fenghua Yu Signed-off-by: Gayatri Kammela Signed-off-by: Shaohua Li --- include/linux/raid/pq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h index a7a06d1dcf9c..a0118d5929a9 100644 --- a/include/linux/raid/pq.h +++ b/include/linux/raid/pq.h @@ -152,6 +152,8 @@ void raid6_dual_recov(int disks, size_t bytes, int faila, int failb, # define jiffies raid6_jiffies() # define printk printf +# define pr_err(format, ...) fprintf(stderr, format, ## __VA_ARGS__) +# define pr_info(format, ...) fprintf(stdout, format, ## __VA_ARGS__) # define GFP_KERNEL 0 # define __get_free_pages(x, y) ((unsigned long)mmap(NULL, PAGE_SIZE << (y), \ PROT_READ|PROT_WRITE, \ -- cgit v1.2.3 From e93ad19d05648397ef3bcb838d26aec06c245dc0 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 19 Jan 2016 12:18:41 -0500 Subject: cpuset: make mm migration asynchronous If "cpuset.memory_migrate" is set, when a process is moved from one cpuset to another with a different memory node mask, pages in used by the process are migrated to the new set of nodes. This was performed synchronously in the ->attach() callback, which is synchronized against process management. Recently, the synchronization was changed from per-process rwsem to global percpu rwsem for simplicity and optimization. Combined with the synchronous mm migration, this led to deadlocks because mm migration could schedule a work item which may in turn try to create a new worker blocking on the process management lock held from cgroup process migration path. This heavy an operation shouldn't be performed synchronously from that deep inside cgroup migration in the first place. This patch punts the actual migration to an ordered workqueue and updates cgroup process migration and cpuset config update paths to flush the workqueue after all locks are released. This way, the operations still seem synchronous to userland without entangling mm migration with process management synchronization. CPU hotplug can also invoke mm migration but there's no reason for it to wait for mm migrations and thus doesn't synchronize against their completions. Signed-off-by: Tejun Heo Reported-and-tested-by: Christian Borntraeger Cc: stable@vger.kernel.org # v4.4+ --- include/linux/cpuset.h | 6 +++++ kernel/cgroup.c | 2 ++ kernel/cpuset.c | 71 ++++++++++++++++++++++++++++++++++---------------- 3 files changed, 57 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 85a868ccb493..fea160ee5803 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -137,6 +137,8 @@ static inline void set_mems_allowed(nodemask_t nodemask) task_unlock(current); } +extern void cpuset_post_attach_flush(void); + #else /* !CONFIG_CPUSETS */ static inline bool cpusets_enabled(void) { return false; } @@ -243,6 +245,10 @@ static inline bool read_mems_allowed_retry(unsigned int seq) return false; } +static inline void cpuset_post_attach_flush(void) +{ +} + #endif /* !CONFIG_CPUSETS */ #endif /* _LINUX_CPUSET_H */ diff --git a/kernel/cgroup.c b/kernel/cgroup.c index c03a640ef6da..88abd4d076d8 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -58,6 +58,7 @@ #include #include #include +#include #include /* @@ -2739,6 +2740,7 @@ out_unlock_rcu: out_unlock_threadgroup: percpu_up_write(&cgroup_threadgroup_rwsem); cgroup_kn_unlock(of->kn); + cpuset_post_attach_flush(); return ret ?: nbytes; } diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 3e945fcd8179..41989ab4db57 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -287,6 +287,8 @@ static struct cpuset top_cpuset = { static DEFINE_MUTEX(cpuset_mutex); static DEFINE_SPINLOCK(callback_lock); +static struct workqueue_struct *cpuset_migrate_mm_wq; + /* * CPU / memory hotplug is handled asynchronously. */ @@ -972,31 +974,51 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, } /* - * cpuset_migrate_mm - * - * Migrate memory region from one set of nodes to another. - * - * Temporarilly set tasks mems_allowed to target nodes of migration, - * so that the migration code can allocate pages on these nodes. - * - * While the mm_struct we are migrating is typically from some - * other task, the task_struct mems_allowed that we are hacking - * is for our current task, which must allocate new pages for that - * migrating memory region. + * Migrate memory region from one set of nodes to another. This is + * performed asynchronously as it can be called from process migration path + * holding locks involved in process management. All mm migrations are + * performed in the queued order and can be waited for by flushing + * cpuset_migrate_mm_wq. */ +struct cpuset_migrate_mm_work { + struct work_struct work; + struct mm_struct *mm; + nodemask_t from; + nodemask_t to; +}; + +static void cpuset_migrate_mm_workfn(struct work_struct *work) +{ + struct cpuset_migrate_mm_work *mwork = + container_of(work, struct cpuset_migrate_mm_work, work); + + /* on a wq worker, no need to worry about %current's mems_allowed */ + do_migrate_pages(mwork->mm, &mwork->from, &mwork->to, MPOL_MF_MOVE_ALL); + mmput(mwork->mm); + kfree(mwork); +} + static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to) { - struct task_struct *tsk = current; - - tsk->mems_allowed = *to; + struct cpuset_migrate_mm_work *mwork; - do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL); + mwork = kzalloc(sizeof(*mwork), GFP_KERNEL); + if (mwork) { + mwork->mm = mm; + mwork->from = *from; + mwork->to = *to; + INIT_WORK(&mwork->work, cpuset_migrate_mm_workfn); + queue_work(cpuset_migrate_mm_wq, &mwork->work); + } else { + mmput(mm); + } +} - rcu_read_lock(); - guarantee_online_mems(task_cs(tsk), &tsk->mems_allowed); - rcu_read_unlock(); +void cpuset_post_attach_flush(void) +{ + flush_workqueue(cpuset_migrate_mm_wq); } /* @@ -1097,7 +1119,8 @@ static void update_tasks_nodemask(struct cpuset *cs) mpol_rebind_mm(mm, &cs->mems_allowed); if (migrate) cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems); - mmput(mm); + else + mmput(mm); } css_task_iter_end(&it); @@ -1545,11 +1568,11 @@ static void cpuset_attach(struct cgroup_taskset *tset) * @old_mems_allowed is the right nodesets that we * migrate mm from. */ - if (is_memory_migrate(cs)) { + if (is_memory_migrate(cs)) cpuset_migrate_mm(mm, &oldcs->old_mems_allowed, &cpuset_attach_nodemask_to); - } - mmput(mm); + else + mmput(mm); } } @@ -1714,6 +1737,7 @@ out_unlock: mutex_unlock(&cpuset_mutex); kernfs_unbreak_active_protection(of->kn); css_put(&cs->css); + flush_workqueue(cpuset_migrate_mm_wq); return retval ?: nbytes; } @@ -2359,6 +2383,9 @@ void __init cpuset_init_smp(void) top_cpuset.effective_mems = node_states[N_MEMORY]; register_hotmemory_notifier(&cpuset_track_online_nodes_nb); + + cpuset_migrate_mm_wq = alloc_ordered_workqueue("cpuset_migrate_mm", 0); + BUG_ON(!cpuset_migrate_mm_wq); } /** -- cgit v1.2.3 From aa226ff4a1ce79f229c6b7a4c0a14e17fececd01 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 21 Jan 2016 15:31:11 -0500 Subject: cgroup: make sure a parent css isn't offlined before its children There are three subsystem callbacks in css shutdown path - css_offline(), css_released() and css_free(). Except for css_released(), cgroup core didn't guarantee the order of invocation. css_offline() or css_free() could be called on a parent css before its children. This behavior is unexpected and led to bugs in cpu and memory controller. This patch updates offline path so that a parent css is never offlined before its children. Each css keeps online_cnt which reaches zero iff itself and all its children are offline and offline_css() is invoked only after online_cnt reaches zero. This fixes the memory controller bug and allows the fix for cpu controller. Signed-off-by: Tejun Heo Reported-and-tested-by: Christian Borntraeger Reported-by: Brian Christiansen Link: http://lkml.kernel.org/g/5698A023.9070703@de.ibm.com Link: http://lkml.kernel.org/g/CAKB58ikDkzc8REt31WBkD99+hxNzjK4+FBmhkgS+NVrC9vjMSg@mail.gmail.com Cc: Heiko Carstens Cc: Peter Zijlstra Cc: stable@vger.kernel.org --- include/linux/cgroup-defs.h | 6 ++++++ kernel/cgroup.c | 22 +++++++++++++++++----- 2 files changed, 23 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 7f540f7f588d..789471dba6fb 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -127,6 +127,12 @@ struct cgroup_subsys_state { */ u64 serial_nr; + /* + * Incremented by online self and children. Used to guarantee that + * parents are not offlined before their children. + */ + atomic_t online_cnt; + /* percpu_ref killing and RCU release */ struct rcu_head rcu_head; struct work_struct destroy_work; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 88abd4d076d8..d01587793865 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -4760,6 +4760,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css, INIT_LIST_HEAD(&css->sibling); INIT_LIST_HEAD(&css->children); css->serial_nr = css_serial_nr_next++; + atomic_set(&css->online_cnt, 0); if (cgroup_parent(cgrp)) { css->parent = cgroup_css(cgroup_parent(cgrp), ss); @@ -4782,6 +4783,10 @@ static int online_css(struct cgroup_subsys_state *css) if (!ret) { css->flags |= CSS_ONLINE; rcu_assign_pointer(css->cgroup->subsys[ss->id], css); + + atomic_inc(&css->online_cnt); + if (css->parent) + atomic_inc(&css->parent->online_cnt); } return ret; } @@ -5019,10 +5024,15 @@ static void css_killed_work_fn(struct work_struct *work) container_of(work, struct cgroup_subsys_state, destroy_work); mutex_lock(&cgroup_mutex); - offline_css(css); - mutex_unlock(&cgroup_mutex); - css_put(css); + do { + offline_css(css); + css_put(css); + /* @css can't go away while we're holding cgroup_mutex */ + css = css->parent; + } while (css && atomic_dec_and_test(&css->online_cnt)); + + mutex_unlock(&cgroup_mutex); } /* css kill confirmation processing requires process context, bounce */ @@ -5031,8 +5041,10 @@ static void css_killed_ref_fn(struct percpu_ref *ref) struct cgroup_subsys_state *css = container_of(ref, struct cgroup_subsys_state, refcnt); - INIT_WORK(&css->destroy_work, css_killed_work_fn); - queue_work(cgroup_destroy_wq, &css->destroy_work); + if (atomic_dec_and_test(&css->online_cnt)) { + INIT_WORK(&css->destroy_work, css_killed_work_fn); + queue_work(cgroup_destroy_wq, &css->destroy_work); + } } /** -- cgit v1.2.3 From 71f50c6d9a2276f3ec85384bffe2aee1962f4669 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 22 Jan 2016 01:33:51 +0900 Subject: of: drop symbols declared by _OF_DECLARE() from modules The users of this macro (OF_EARLYCON_DECLARE, CLK_OF_DECLARE, IRQCHIP_DECLARE, etc.) are only parsed in the early boot stage. Such symbols contained in modules are never used. This commit fixes the link error introduced by commit b8d20e06eaad ("serial: 8250_uniphier: add earlycon support"); the combination of CONFIG_SERIAL_8250_UNIPHIER=m and CONFIG_SERIAL_8250_CONSOLE=y fails to link: ERROR: "early_serial8250_setup" [drivers/tty/serial/8250/8250_uniphier.ko] undefined! Fixes: b8d20e06eaad ("serial: 8250_uniphier: add earlycon support") Signed-off-by: Masahiro Yamada Acked-by: Arnd Bergmann Signed-off-by: Rob Herring --- include/linux/of.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index dd10626a615f..dc6e39696b64 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -929,7 +929,7 @@ static inline int of_get_available_child_count(const struct device_node *np) return num; } -#ifdef CONFIG_OF +#if defined(CONFIG_OF) && !defined(MODULE) #define _OF_DECLARE(table, name, compat, fn, fn_type) \ static const struct of_device_id __of_table_##name \ __used __section(__##table##_of_table) \ -- cgit v1.2.3 From fb3296335500aaff61333df8eabbccf28761c79d Mon Sep 17 00:00:00 2001 From: Danesh Petigara Date: Mon, 11 Jan 2016 13:22:26 -0800 Subject: drivers: ata: wake port before DMA stop for ALPM The AHCI driver code stops and starts port DMA engines at will without considering the power state of the particular port. The AHCI specification isn't very clear on how to handle this scenario, leaving implementation open to interpretation. Broadcom's STB SATA host controller is unable to handle port DMA controller restarts when the port in question is in low power mode. When a port enters partial or slumber mode, its PHY is powered down. When a controller restart is requested, the controller's internal state machine expects the PHY to be brought back up by software which never happens in this case, resulting in failures. To avoid this situation, logic is added to manually wake up the port just before its DMA engine is stopped, if the port happens to be in a low power state. HBA initiated power management ensures that the port eventually returns to its configured low power state, when the link is idle (as per the conditions listed in the spec). A new host flag is also added to ensure this logic is only exercised for hosts with the above limitation. tj: Formatting changes. Signed-off-by: Danesh Petigara Reviewed-by: Markus Mayer Signed-off-by: Tejun Heo --- drivers/ata/ahci.h | 1 + drivers/ata/ahci_brcmstb.c | 1 + drivers/ata/libahci.c | 23 ++++++++++++++++++++++- include/linux/libata.h | 1 + 4 files changed, 25 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index a4faa438889c..a44c75d4c284 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -250,6 +250,7 @@ enum { AHCI_HFLAG_MULTI_MSI = 0, AHCI_HFLAG_MULTI_MSIX = 0, #endif + AHCI_HFLAG_WAKE_BEFORE_STOP = (1 << 22), /* wake before DMA stop */ /* ap->flags bits */ diff --git a/drivers/ata/ahci_brcmstb.c b/drivers/ata/ahci_brcmstb.c index b36cae2fd04b..e87bcec0fd7c 100644 --- a/drivers/ata/ahci_brcmstb.c +++ b/drivers/ata/ahci_brcmstb.c @@ -317,6 +317,7 @@ static int brcm_ahci_probe(struct platform_device *pdev) if (IS_ERR(hpriv)) return PTR_ERR(hpriv); hpriv->plat_data = priv; + hpriv->flags = AHCI_HFLAG_WAKE_BEFORE_STOP; brcm_sata_alpm_init(hpriv); diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index d61740e78d6d..284a176076f5 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -593,8 +593,22 @@ EXPORT_SYMBOL_GPL(ahci_start_engine); int ahci_stop_engine(struct ata_port *ap) { void __iomem *port_mmio = ahci_port_base(ap); + struct ahci_host_priv *hpriv = ap->host->private_data; u32 tmp; + /* + * On some controllers, stopping a port's DMA engine while the port + * is in ALPM state (partial or slumber) results in failures on + * subsequent DMA engine starts. For those controllers, put the + * port back in active state before stopping its DMA engine. + */ + if ((hpriv->flags & AHCI_HFLAG_WAKE_BEFORE_STOP) && + (ap->link.lpm_policy > ATA_LPM_MAX_POWER) && + ahci_set_lpm(&ap->link, ATA_LPM_MAX_POWER, ATA_LPM_WAKE_ONLY)) { + dev_err(ap->host->dev, "Failed to wake up port before engine stop\n"); + return -EIO; + } + tmp = readl(port_mmio + PORT_CMD); /* check if the HBA is idle */ @@ -689,6 +703,9 @@ static int ahci_set_lpm(struct ata_link *link, enum ata_lpm_policy policy, void __iomem *port_mmio = ahci_port_base(ap); if (policy != ATA_LPM_MAX_POWER) { + /* wakeup flag only applies to the max power policy */ + hints &= ~ATA_LPM_WAKE_ONLY; + /* * Disable interrupts on Phy Ready. This keeps us from * getting woken up due to spurious phy ready @@ -704,7 +721,8 @@ static int ahci_set_lpm(struct ata_link *link, enum ata_lpm_policy policy, u32 cmd = readl(port_mmio + PORT_CMD); if (policy == ATA_LPM_MAX_POWER || !(hints & ATA_LPM_HIPM)) { - cmd &= ~(PORT_CMD_ASP | PORT_CMD_ALPE); + if (!(hints & ATA_LPM_WAKE_ONLY)) + cmd &= ~(PORT_CMD_ASP | PORT_CMD_ALPE); cmd |= PORT_CMD_ICC_ACTIVE; writel(cmd, port_mmio + PORT_CMD); @@ -712,6 +730,9 @@ static int ahci_set_lpm(struct ata_link *link, enum ata_lpm_policy policy, /* wait 10ms to be sure we've come out of LPM state */ ata_msleep(ap, 10); + + if (hints & ATA_LPM_WAKE_ONLY) + return 0; } else { cmd |= PORT_CMD_ALPE; if (policy == ATA_LPM_MIN_POWER) diff --git a/include/linux/libata.h b/include/linux/libata.h index 851821bfd553..bec2abbd7ab2 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -526,6 +526,7 @@ enum ata_lpm_policy { enum ata_lpm_hints { ATA_LPM_EMPTY = (1 << 0), /* port empty/probing */ ATA_LPM_HIPM = (1 << 1), /* may use HIPM */ + ATA_LPM_WAKE_ONLY = (1 << 2), /* only wake up link */ }; /* forward declarations */ -- cgit v1.2.3 From 23d11a58a9a60dcb52c8fc6494efce908b24c295 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 29 Jan 2016 05:59:46 -0500 Subject: workqueue: skip flush dependency checks for legacy workqueues fca839c00a12 ("workqueue: warn if memory reclaim tries to flush !WQ_MEM_RECLAIM workqueue") implemented flush dependency warning which triggers if a PF_MEMALLOC task or WQ_MEM_RECLAIM workqueue tries to flush a !WQ_MEM_RECLAIM workquee. This assumes that workqueues marked with WQ_MEM_RECLAIM sit in memory reclaim path and making it depend on something which may need more memory to make forward progress can lead to deadlocks. Unfortunately, workqueues created with the legacy create*_workqueue() interface always have WQ_MEM_RECLAIM regardless of whether they are depended upon memory reclaim or not. These spurious WQ_MEM_RECLAIM markings cause spurious triggering of the flush dependency checks. WARNING: CPU: 0 PID: 6 at kernel/workqueue.c:2361 check_flush_dependency+0x138/0x144() workqueue: WQ_MEM_RECLAIM deferwq:deferred_probe_work_func is flushing !WQ_MEM_RECLAIM events:lru_add_drain_per_cpu ... Workqueue: deferwq deferred_probe_work_func [] (unwind_backtrace) from [] (show_stack+0x10/0x14) [] (show_stack) from [] (dump_stack+0x94/0xd4) [] (dump_stack) from [] (warn_slowpath_common+0x80/0xb0) [] (warn_slowpath_common) from [] (warn_slowpath_fmt+0x30/0x40) [] (warn_slowpath_fmt) from [] (check_flush_dependency+0x138/0x144) [] (check_flush_dependency) from [] (flush_work+0x50/0x15c) [] (flush_work) from [] (lru_add_drain_all+0x130/0x180) [] (lru_add_drain_all) from [] (migrate_prep+0x8/0x10) [] (migrate_prep) from [] (alloc_contig_range+0xd8/0x338) [] (alloc_contig_range) from [] (cma_alloc+0xe0/0x1ac) [] (cma_alloc) from [] (__alloc_from_contiguous+0x38/0xd8) [] (__alloc_from_contiguous) from [] (__dma_alloc+0x240/0x278) [] (__dma_alloc) from [] (arm_dma_alloc+0x54/0x5c) [] (arm_dma_alloc) from [] (dmam_alloc_coherent+0xc0/0xec) [] (dmam_alloc_coherent) from [] (ahci_port_start+0x150/0x1dc) [] (ahci_port_start) from [] (ata_host_start.part.3+0xc8/0x1c8) [] (ata_host_start.part.3) from [] (ata_host_activate+0x50/0x148) [] (ata_host_activate) from [] (ahci_host_activate+0x44/0x114) [] (ahci_host_activate) from [] (ahci_platform_init_host+0x1d8/0x3c8) [] (ahci_platform_init_host) from [] (tegra_ahci_probe+0x448/0x4e8) [] (tegra_ahci_probe) from [] (platform_drv_probe+0x50/0xac) [] (platform_drv_probe) from [] (driver_probe_device+0x214/0x2c0) [] (driver_probe_device) from [] (bus_for_each_drv+0x60/0x94) [] (bus_for_each_drv) from [] (__device_attach+0xb0/0x114) [] (__device_attach) from [] (bus_probe_device+0x84/0x8c) [] (bus_probe_device) from [] (deferred_probe_work_func+0x68/0x98) [] (deferred_probe_work_func) from [] (process_one_work+0x120/0x3f8) [] (process_one_work) from [] (worker_thread+0x38/0x55c) [] (worker_thread) from [] (kthread+0xdc/0xf4) [] (kthread) from [] (ret_from_fork+0x14/0x3c) Fix it by marking workqueues created via create*_workqueue() with __WQ_LEGACY and disabling flush dependency checks on them. Signed-off-by: Tejun Heo Reported-and-tested-by: Thierry Reding Link: http://lkml.kernel.org/g/20160126173843.GA11115@ulmo.nvidia.com Fixes: fca839c00a12 ("workqueue: warn if memory reclaim tries to flush !WQ_MEM_RECLAIM workqueue") --- include/linux/workqueue.h | 9 +++++---- kernel/workqueue.c | 3 ++- 2 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 0e32bc71245e..ca73c503b92a 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -311,6 +311,7 @@ enum { __WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */ __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */ + __WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ @@ -411,12 +412,12 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args) #define create_workqueue(name) \ - alloc_workqueue("%s", WQ_MEM_RECLAIM, 1, (name)) + alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name)) #define create_freezable_workqueue(name) \ - alloc_workqueue("%s", WQ_FREEZABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, \ - 1, (name)) + alloc_workqueue("%s", __WQ_LEGACY | WQ_FREEZABLE | WQ_UNBOUND | \ + WQ_MEM_RECLAIM, 1, (name)) #define create_singlethread_workqueue(name) \ - alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, name) + alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name) extern void destroy_workqueue(struct workqueue_struct *wq); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 61a0264e28f9..dc7faad63646 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2355,7 +2355,8 @@ static void check_flush_dependency(struct workqueue_struct *target_wq, WARN_ONCE(current->flags & PF_MEMALLOC, "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%pf", current->pid, current->comm, target_wq->name, target_func); - WARN_ONCE(worker && (worker->current_pwq->wq->flags & WQ_MEM_RECLAIM), + WARN_ONCE(worker && ((worker->current_pwq->wq->flags & + (WQ_MEM_RECLAIM | __WQ_LEGACY)) == WQ_MEM_RECLAIM), "workqueue: WQ_MEM_RECLAIM %s:%pf is flushing !WQ_MEM_RECLAIM %s:%pf", worker->current_pwq->wq->name, worker->current_func, target_wq->name, target_func); -- cgit v1.2.3 From 8244062ef1e54502ef55f54cced659913f244c3e Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 3 Feb 2016 16:55:26 +1030 Subject: modules: fix longstanding /proc/kallsyms vs module insertion race. For CONFIG_KALLSYMS, we keep two symbol tables and two string tables. There's one full copy, marked SHF_ALLOC and laid out at the end of the module's init section. There's also a cut-down version that only contains core symbols and strings, and lives in the module's core section. After module init (and before we free the module memory), we switch the mod->symtab, mod->num_symtab and mod->strtab to point to the core versions. We do this under the module_mutex. However, kallsyms doesn't take the module_mutex: it uses preempt_disable() and rcu tricks to walk through the modules, because it's used in the oops path. It's also used in /proc/kallsyms. There's nothing atomic about the change of these variables, so we can get the old (larger!) num_symtab and the new symtab pointer; in fact this is what I saw when trying to reproduce. By grouping these variables together, we can use a carefully-dereferenced pointer to ensure we always get one or the other (the free of the module init section is already done in an RCU callback, so that's safe). We allocate the init one at the end of the module init section, and keep the core one inside the struct module itself (it could also have been allocated at the end of the module core, but that's probably overkill). Reported-by: Weilong Chen Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=111541 Cc: stable@kernel.org Signed-off-by: Rusty Russell --- include/linux/module.h | 19 +++++---- kernel/module.c | 112 ++++++++++++++++++++++++++++++------------------- 2 files changed, 79 insertions(+), 52 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 4560d8f1545d..2bb0c3085706 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -324,6 +324,12 @@ struct module_layout { #define __module_layout_align #endif +struct mod_kallsyms { + Elf_Sym *symtab; + unsigned int num_symtab; + char *strtab; +}; + struct module { enum module_state state; @@ -405,15 +411,10 @@ struct module { #endif #ifdef CONFIG_KALLSYMS - /* - * We keep the symbol and string tables for kallsyms. - * The core_* fields below are temporary, loader-only (they - * could really be discarded after module init). - */ - Elf_Sym *symtab, *core_symtab; - unsigned int num_symtab, core_num_syms; - char *strtab, *core_strtab; - + /* Protected by RCU and/or module_mutex: use rcu_dereference() */ + struct mod_kallsyms *kallsyms; + struct mod_kallsyms core_kallsyms; + /* Section attributes */ struct module_sect_attrs *sect_attrs; diff --git a/kernel/module.c b/kernel/module.c index 1e79d8157712..9537da37ce87 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -303,6 +303,9 @@ struct load_info { struct _ddebug *debug; unsigned int num_debug; bool sig_ok; +#ifdef CONFIG_KALLSYMS + unsigned long mod_kallsyms_init_off; +#endif struct { unsigned int sym, str, mod, vers, info, pcpu; } index; @@ -2480,10 +2483,21 @@ static void layout_symtab(struct module *mod, struct load_info *info) strsect->sh_flags |= SHF_ALLOC; strsect->sh_entsize = get_offset(mod, &mod->init_layout.size, strsect, info->index.str) | INIT_OFFSET_MASK; - mod->init_layout.size = debug_align(mod->init_layout.size); pr_debug("\t%s\n", info->secstrings + strsect->sh_name); + + /* We'll tack temporary mod_kallsyms on the end. */ + mod->init_layout.size = ALIGN(mod->init_layout.size, + __alignof__(struct mod_kallsyms)); + info->mod_kallsyms_init_off = mod->init_layout.size; + mod->init_layout.size += sizeof(struct mod_kallsyms); + mod->init_layout.size = debug_align(mod->init_layout.size); } +/* + * We use the full symtab and strtab which layout_symtab arranged to + * be appended to the init section. Later we switch to the cut-down + * core-only ones. + */ static void add_kallsyms(struct module *mod, const struct load_info *info) { unsigned int i, ndst; @@ -2492,29 +2506,34 @@ static void add_kallsyms(struct module *mod, const struct load_info *info) char *s; Elf_Shdr *symsec = &info->sechdrs[info->index.sym]; - mod->symtab = (void *)symsec->sh_addr; - mod->num_symtab = symsec->sh_size / sizeof(Elf_Sym); + /* Set up to point into init section. */ + mod->kallsyms = mod->init_layout.base + info->mod_kallsyms_init_off; + + mod->kallsyms->symtab = (void *)symsec->sh_addr; + mod->kallsyms->num_symtab = symsec->sh_size / sizeof(Elf_Sym); /* Make sure we get permanent strtab: don't use info->strtab. */ - mod->strtab = (void *)info->sechdrs[info->index.str].sh_addr; + mod->kallsyms->strtab = (void *)info->sechdrs[info->index.str].sh_addr; /* Set types up while we still have access to sections. */ - for (i = 0; i < mod->num_symtab; i++) - mod->symtab[i].st_info = elf_type(&mod->symtab[i], info); - - mod->core_symtab = dst = mod->core_layout.base + info->symoffs; - mod->core_strtab = s = mod->core_layout.base + info->stroffs; - src = mod->symtab; - for (ndst = i = 0; i < mod->num_symtab; i++) { + for (i = 0; i < mod->kallsyms->num_symtab; i++) + mod->kallsyms->symtab[i].st_info + = elf_type(&mod->kallsyms->symtab[i], info); + + /* Now populate the cut down core kallsyms for after init. */ + mod->core_kallsyms.symtab = dst = mod->core_layout.base + info->symoffs; + mod->core_kallsyms.strtab = s = mod->core_layout.base + info->stroffs; + src = mod->kallsyms->symtab; + for (ndst = i = 0; i < mod->kallsyms->num_symtab; i++) { if (i == 0 || is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum, info->index.pcpu)) { dst[ndst] = src[i]; - dst[ndst++].st_name = s - mod->core_strtab; - s += strlcpy(s, &mod->strtab[src[i].st_name], + dst[ndst++].st_name = s - mod->core_kallsyms.strtab; + s += strlcpy(s, &mod->kallsyms->strtab[src[i].st_name], KSYM_NAME_LEN) + 1; } } - mod->core_num_syms = ndst; + mod->core_kallsyms.num_symtab = ndst; } #else static inline void layout_symtab(struct module *mod, struct load_info *info) @@ -3263,9 +3282,8 @@ static noinline int do_init_module(struct module *mod) module_put(mod); trim_init_extable(mod); #ifdef CONFIG_KALLSYMS - mod->num_symtab = mod->core_num_syms; - mod->symtab = mod->core_symtab; - mod->strtab = mod->core_strtab; + /* Switch to core kallsyms now init is done: kallsyms may be walking! */ + rcu_assign_pointer(mod->kallsyms, &mod->core_kallsyms); #endif mod_tree_remove_init(mod); disable_ro_nx(&mod->init_layout); @@ -3627,9 +3645,9 @@ static inline int is_arm_mapping_symbol(const char *str) && (str[2] == '\0' || str[2] == '.'); } -static const char *symname(struct module *mod, unsigned int symnum) +static const char *symname(struct mod_kallsyms *kallsyms, unsigned int symnum) { - return mod->strtab + mod->symtab[symnum].st_name; + return kallsyms->strtab + kallsyms->symtab[symnum].st_name; } static const char *get_ksymbol(struct module *mod, @@ -3639,6 +3657,7 @@ static const char *get_ksymbol(struct module *mod, { unsigned int i, best = 0; unsigned long nextval; + struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms); /* At worse, next value is at end of module */ if (within_module_init(addr, mod)) @@ -3648,32 +3667,32 @@ static const char *get_ksymbol(struct module *mod, /* Scan for closest preceding symbol, and next symbol. (ELF starts real symbols at 1). */ - for (i = 1; i < mod->num_symtab; i++) { - if (mod->symtab[i].st_shndx == SHN_UNDEF) + for (i = 1; i < kallsyms->num_symtab; i++) { + if (kallsyms->symtab[i].st_shndx == SHN_UNDEF) continue; /* We ignore unnamed symbols: they're uninformative * and inserted at a whim. */ - if (*symname(mod, i) == '\0' - || is_arm_mapping_symbol(symname(mod, i))) + if (*symname(kallsyms, i) == '\0' + || is_arm_mapping_symbol(symname(kallsyms, i))) continue; - if (mod->symtab[i].st_value <= addr - && mod->symtab[i].st_value > mod->symtab[best].st_value) + if (kallsyms->symtab[i].st_value <= addr + && kallsyms->symtab[i].st_value > kallsyms->symtab[best].st_value) best = i; - if (mod->symtab[i].st_value > addr - && mod->symtab[i].st_value < nextval) - nextval = mod->symtab[i].st_value; + if (kallsyms->symtab[i].st_value > addr + && kallsyms->symtab[i].st_value < nextval) + nextval = kallsyms->symtab[i].st_value; } if (!best) return NULL; if (size) - *size = nextval - mod->symtab[best].st_value; + *size = nextval - kallsyms->symtab[best].st_value; if (offset) - *offset = addr - mod->symtab[best].st_value; - return symname(mod, best); + *offset = addr - kallsyms->symtab[best].st_value; + return symname(kallsyms, best); } /* For kallsyms to ask for address resolution. NULL means not found. Careful @@ -3763,18 +3782,21 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, preempt_disable(); list_for_each_entry_rcu(mod, &modules, list) { + struct mod_kallsyms *kallsyms; + if (mod->state == MODULE_STATE_UNFORMED) continue; - if (symnum < mod->num_symtab) { - *value = mod->symtab[symnum].st_value; - *type = mod->symtab[symnum].st_info; - strlcpy(name, symname(mod, symnum), KSYM_NAME_LEN); + kallsyms = rcu_dereference_sched(mod->kallsyms); + if (symnum < kallsyms->num_symtab) { + *value = kallsyms->symtab[symnum].st_value; + *type = kallsyms->symtab[symnum].st_info; + strlcpy(name, symname(kallsyms, symnum), KSYM_NAME_LEN); strlcpy(module_name, mod->name, MODULE_NAME_LEN); *exported = is_exported(name, *value, mod); preempt_enable(); return 0; } - symnum -= mod->num_symtab; + symnum -= kallsyms->num_symtab; } preempt_enable(); return -ERANGE; @@ -3783,11 +3805,12 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, static unsigned long mod_find_symname(struct module *mod, const char *name) { unsigned int i; + struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms); - for (i = 0; i < mod->num_symtab; i++) - if (strcmp(name, symname(mod, i)) == 0 && - mod->symtab[i].st_info != 'U') - return mod->symtab[i].st_value; + for (i = 0; i < kallsyms->num_symtab; i++) + if (strcmp(name, symname(kallsyms, i)) == 0 && + kallsyms->symtab[i].st_info != 'U') + return kallsyms->symtab[i].st_value; return 0; } @@ -3826,11 +3849,14 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, module_assert_mutex(); list_for_each_entry(mod, &modules, list) { + /* We hold module_mutex: no need for rcu_dereference_sched */ + struct mod_kallsyms *kallsyms = mod->kallsyms; + if (mod->state == MODULE_STATE_UNFORMED) continue; - for (i = 0; i < mod->num_symtab; i++) { - ret = fn(data, symname(mod, i), - mod, mod->symtab[i].st_value); + for (i = 0; i < kallsyms->num_symtab; i++) { + ret = fn(data, symname(kallsyms, i), + mod, kallsyms->symtab[i].st_value); if (ret != 0) return ret; } -- cgit v1.2.3 From a3d0a918502cc73af4f60da2cc4c5cac5573f183 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 2 Feb 2016 16:57:08 -0800 Subject: thp: make split_queue per-node Andrea Arcangeli suggested to make split queue per-node to improve scalability. Let's do it. Signed-off-by: Kirill A. Shutemov Suggested-by: Andrea Arcangeli Reviewed-by: Andrea Arcangeli Cc: Hugh Dickins Cc: Dave Hansen Cc: Mel Gorman Cc: Rik van Riel Cc: Vlastimil Babka Cc: "Aneesh Kumar K.V" Cc: Johannes Weiner Cc: Michal Hocko Cc: Jerome Marchand Cc: Sasha Levin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 6 ++++++ mm/huge_memory.c | 49 ++++++++++++++++++++++++++----------------------- mm/page_alloc.c | 5 +++++ 3 files changed, 37 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 33bb1b19273e..7b6c2cfee390 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -682,6 +682,12 @@ typedef struct pglist_data { */ unsigned long first_deferred_pfn; #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + spinlock_t split_queue_lock; + struct list_head split_queue; + unsigned long split_queue_len; +#endif } pg_data_t; #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index fd3a07b3e6f4..253a25e007d7 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -138,9 +138,6 @@ static struct khugepaged_scan khugepaged_scan = { .mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head), }; -static DEFINE_SPINLOCK(split_queue_lock); -static LIST_HEAD(split_queue); -static unsigned long split_queue_len; static struct shrinker deferred_split_shrinker; static void set_recommended_min_free_kbytes(void) @@ -3358,6 +3355,7 @@ int total_mapcount(struct page *page) int split_huge_page_to_list(struct page *page, struct list_head *list) { struct page *head = compound_head(page); + struct pglist_data *pgdata = NODE_DATA(page_to_nid(head)); struct anon_vma *anon_vma; int count, mapcount, ret; bool mlocked; @@ -3401,19 +3399,19 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) lru_add_drain(); /* Prevent deferred_split_scan() touching ->_count */ - spin_lock_irqsave(&split_queue_lock, flags); + spin_lock_irqsave(&pgdata->split_queue_lock, flags); count = page_count(head); mapcount = total_mapcount(head); if (!mapcount && count == 1) { if (!list_empty(page_deferred_list(head))) { - split_queue_len--; + pgdata->split_queue_len--; list_del(page_deferred_list(head)); } - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); __split_huge_page(page, list); ret = 0; } else if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) { - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); pr_alert("total_mapcount: %u, page_count(): %u\n", mapcount, count); if (PageTail(page)) @@ -3421,7 +3419,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) dump_page(page, "total_mapcount(head) > 0"); BUG(); } else { - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); unfreeze_page(anon_vma, head); ret = -EBUSY; } @@ -3436,52 +3434,56 @@ out: void free_transhuge_page(struct page *page) { + struct pglist_data *pgdata = NODE_DATA(page_to_nid(page)); unsigned long flags; - spin_lock_irqsave(&split_queue_lock, flags); + spin_lock_irqsave(&pgdata->split_queue_lock, flags); if (!list_empty(page_deferred_list(page))) { - split_queue_len--; + pgdata->split_queue_len--; list_del(page_deferred_list(page)); } - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); free_compound_page(page); } void deferred_split_huge_page(struct page *page) { + struct pglist_data *pgdata = NODE_DATA(page_to_nid(page)); unsigned long flags; VM_BUG_ON_PAGE(!PageTransHuge(page), page); - spin_lock_irqsave(&split_queue_lock, flags); + spin_lock_irqsave(&pgdata->split_queue_lock, flags); if (list_empty(page_deferred_list(page))) { - list_add_tail(page_deferred_list(page), &split_queue); - split_queue_len++; + list_add_tail(page_deferred_list(page), &pgdata->split_queue); + pgdata->split_queue_len++; } - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); } static unsigned long deferred_split_count(struct shrinker *shrink, struct shrink_control *sc) { + struct pglist_data *pgdata = NODE_DATA(sc->nid); /* * Split a page from split_queue will free up at least one page, * at most HPAGE_PMD_NR - 1. We don't track exact number. * Let's use HPAGE_PMD_NR / 2 as ballpark. */ - return ACCESS_ONCE(split_queue_len) * HPAGE_PMD_NR / 2; + return ACCESS_ONCE(pgdata->split_queue_len) * HPAGE_PMD_NR / 2; } static unsigned long deferred_split_scan(struct shrinker *shrink, struct shrink_control *sc) { + struct pglist_data *pgdata = NODE_DATA(sc->nid); unsigned long flags; LIST_HEAD(list), *pos, *next; struct page *page; int split = 0; - spin_lock_irqsave(&split_queue_lock, flags); - list_splice_init(&split_queue, &list); + spin_lock_irqsave(&pgdata->split_queue_lock, flags); + list_splice_init(&pgdata->split_queue, &list); /* Take pin on all head pages to avoid freeing them under us */ list_for_each_safe(pos, next, &list) { @@ -3490,10 +3492,10 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, /* race with put_compound_page() */ if (!get_page_unless_zero(page)) { list_del_init(page_deferred_list(page)); - split_queue_len--; + pgdata->split_queue_len--; } } - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); list_for_each_safe(pos, next, &list) { page = list_entry((void *)pos, struct page, mapping); @@ -3505,9 +3507,9 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, put_page(page); } - spin_lock_irqsave(&split_queue_lock, flags); - list_splice_tail(&list, &split_queue); - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_lock_irqsave(&pgdata->split_queue_lock, flags); + list_splice_tail(&list, &pgdata->split_queue); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); return split * HPAGE_PMD_NR / 2; } @@ -3516,6 +3518,7 @@ static struct shrinker deferred_split_shrinker = { .count_objects = deferred_split_count, .scan_objects = deferred_split_scan, .seeks = DEFAULT_SEEKS, + .flags = SHRINKER_NUMA_AWARE, }; #ifdef CONFIG_DEBUG_FS diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 63358d9f9aa9..ea2c4d3e0c03 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5209,6 +5209,11 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat) spin_lock_init(&pgdat->numabalancing_migrate_lock); pgdat->numabalancing_migrate_nr_pages = 0; pgdat->numabalancing_migrate_next_window = jiffies; +#endif +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + spin_lock_init(&pgdat->split_queue_lock); + INIT_LIST_HEAD(&pgdat->split_queue); + pgdat->split_queue_len = 0; #endif init_waitqueue_head(&pgdat->kswapd_wait); init_waitqueue_head(&pgdat->pfmemalloc_wait); -- cgit v1.2.3 From 65376df582174ffcec9e6471bf5b0dd79ba05e4a Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 2 Feb 2016 16:57:29 -0800 Subject: proc: revert /proc//maps [stack:TID] annotation Commit b76437579d13 ("procfs: mark thread stack correctly in proc//maps") added [stack:TID] annotation to /proc//maps. Finding the task of a stack VMA requires walking the entire thread list, turning this into quadratic behavior: a thousand threads means a thousand stacks, so the rendering of /proc//maps needs to look at a million combinations. The cost is not in proportion to the usefulness as described in the patch. Drop the [stack:TID] annotation to make /proc//maps (and /proc//numa_maps) usable again for higher thread counts. The [stack] annotation inside /proc//task//maps is retained, as identifying the stack VMA there is an O(1) operation. Siddesh said: "The end users needed a way to identify thread stacks programmatically and there wasn't a way to do that. I'm afraid I no longer remember (or have access to the resources that would aid my memory since I changed employers) the details of their requirement. However, I did do this on my own time because I thought it was an interesting project for me and nobody really gave any feedback then as to its utility, so as far as I am concerned you could roll back the main thread maps information since the information is available in the thread-specific files" Signed-off-by: Johannes Weiner Cc: "Kirill A. Shutemov" Cc: Siddhesh Poyarekar Cc: Shaohua Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/proc.txt | 9 ++---- fs/proc/task_mmu.c | 66 +++++++++++++------------------------- fs/proc/task_nommu.c | 49 ++++++++++++---------------- include/linux/mm.h | 3 +- mm/util.c | 27 +--------------- 5 files changed, 48 insertions(+), 106 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index fde9fd06fa98..eaebf27539f5 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -356,7 +356,7 @@ address perms offset dev inode pathname a7cb1000-a7cb2000 ---p 00000000 00:00 0 a7cb2000-a7eb2000 rw-p 00000000 00:00 0 a7eb2000-a7eb3000 ---p 00000000 00:00 0 -a7eb3000-a7ed5000 rw-p 00000000 00:00 0 [stack:1001] +a7eb3000-a7ed5000 rw-p 00000000 00:00 0 a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6 a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6 a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6 @@ -388,7 +388,6 @@ is not associated with a file: [heap] = the heap of the program [stack] = the stack of the main process - [stack:1001] = the stack of the thread with tid 1001 [vdso] = the "virtual dynamic shared object", the kernel system call handler @@ -396,10 +395,8 @@ is not associated with a file: The /proc/PID/task/TID/maps is a view of the virtual memory from the viewpoint of the individual tasks of a process. In this file you will see a mapping marked -as [stack] if that task sees it as a stack. This is a key difference from the -content of /proc/PID/maps, where you will see all mappings that are being used -as stack by all of those tasks. Hence, for the example above, the task-level -map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this: +as [stack] if that task sees it as a stack. Hence, for the example above, the +task-level map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this: 08048000-08049000 r-xp 00000000 03:00 8312 /opt/test 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 4a0c31f904a6..fa95ab2d3674 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -259,23 +259,29 @@ static int do_maps_open(struct inode *inode, struct file *file, sizeof(struct proc_maps_private)); } -static pid_t pid_of_stack(struct proc_maps_private *priv, - struct vm_area_struct *vma, bool is_pid) +/* + * Indicate if the VMA is a stack for the given task; for + * /proc/PID/maps that is the stack of the main task. + */ +static int is_stack(struct proc_maps_private *priv, + struct vm_area_struct *vma, int is_pid) { - struct inode *inode = priv->inode; - struct task_struct *task; - pid_t ret = 0; + int stack = 0; + + if (is_pid) { + stack = vma->vm_start <= vma->vm_mm->start_stack && + vma->vm_end >= vma->vm_mm->start_stack; + } else { + struct inode *inode = priv->inode; + struct task_struct *task; - rcu_read_lock(); - task = pid_task(proc_pid(inode), PIDTYPE_PID); - if (task) { - task = task_of_stack(task, vma, is_pid); + rcu_read_lock(); + task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) - ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info); + stack = vma_is_stack_for_task(vma, task); + rcu_read_unlock(); } - rcu_read_unlock(); - - return ret; + return stack; } static void @@ -335,8 +341,6 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) name = arch_vma_name(vma); if (!name) { - pid_t tid; - if (!mm) { name = "[vdso]"; goto done; @@ -348,21 +352,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) goto done; } - tid = pid_of_stack(priv, vma, is_pid); - if (tid != 0) { - /* - * Thread stack in /proc/PID/task/TID/maps or - * the main process stack. - */ - if (!is_pid || (vma->vm_start <= mm->start_stack && - vma->vm_end >= mm->start_stack)) { - name = "[stack]"; - } else { - /* Thread stack in /proc/PID/maps */ - seq_pad(m, ' '); - seq_printf(m, "[stack:%d]", tid); - } - } + if (is_stack(priv, vma, is_pid)) + name = "[stack]"; } done: @@ -1618,19 +1609,8 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) seq_file_path(m, file, "\n\t= "); } else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) { seq_puts(m, " heap"); - } else { - pid_t tid = pid_of_stack(proc_priv, vma, is_pid); - if (tid != 0) { - /* - * Thread stack in /proc/PID/task/TID/maps or - * the main process stack. - */ - if (!is_pid || (vma->vm_start <= mm->start_stack && - vma->vm_end >= mm->start_stack)) - seq_puts(m, " stack"); - else - seq_printf(m, " stack:%d", tid); - } + } else if (is_stack(proc_priv, vma, is_pid)) { + seq_puts(m, " stack"); } if (is_vm_hugetlb_page(vma)) diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index e0d64c92e4f6..faacb0c0d857 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -123,23 +123,26 @@ unsigned long task_statm(struct mm_struct *mm, return size; } -static pid_t pid_of_stack(struct proc_maps_private *priv, - struct vm_area_struct *vma, bool is_pid) +static int is_stack(struct proc_maps_private *priv, + struct vm_area_struct *vma, int is_pid) { - struct inode *inode = priv->inode; - struct task_struct *task; - pid_t ret = 0; - - rcu_read_lock(); - task = pid_task(proc_pid(inode), PIDTYPE_PID); - if (task) { - task = task_of_stack(task, vma, is_pid); + struct mm_struct *mm = vma->vm_mm; + int stack = 0; + + if (is_pid) { + stack = vma->vm_start <= mm->start_stack && + vma->vm_end >= mm->start_stack; + } else { + struct inode *inode = priv->inode; + struct task_struct *task; + + rcu_read_lock(); + task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) - ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info); + stack = vma_is_stack_for_task(vma, task); + rcu_read_unlock(); } - rcu_read_unlock(); - - return ret; + return stack; } /* @@ -181,21 +184,9 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma, if (file) { seq_pad(m, ' '); seq_file_path(m, file, ""); - } else if (mm) { - pid_t tid = pid_of_stack(priv, vma, is_pid); - - if (tid != 0) { - seq_pad(m, ' '); - /* - * Thread stack in /proc/PID/task/TID/maps or - * the main process stack. - */ - if (!is_pid || (vma->vm_start <= mm->start_stack && - vma->vm_end >= mm->start_stack)) - seq_printf(m, "[stack]"); - else - seq_printf(m, "[stack:%d]", tid); - } + } else if (mm && is_stack(priv, vma, is_pid)) { + seq_pad(m, ' '); + seq_printf(m, "[stack]"); } seq_putc(m, '\n'); diff --git a/include/linux/mm.h b/include/linux/mm.h index f1cd22f2df1a..0b50d7848e3a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1341,8 +1341,7 @@ static inline int stack_guard_page_end(struct vm_area_struct *vma, !vma_growsup(vma->vm_next, addr); } -extern struct task_struct *task_of_stack(struct task_struct *task, - struct vm_area_struct *vma, bool in_group); +int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t); extern unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, diff --git a/mm/util.c b/mm/util.c index c108a6542d05..4fb14ca5a419 100644 --- a/mm/util.c +++ b/mm/util.c @@ -230,36 +230,11 @@ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, } /* Check if the vma is being used as a stack by this task */ -static int vm_is_stack_for_task(struct task_struct *t, - struct vm_area_struct *vma) +int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t) { return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t)); } -/* - * Check if the vma is being used as a stack. - * If is_group is non-zero, check in the entire thread group or else - * just check in the current task. Returns the task_struct of the task - * that the vma is stack for. Must be called under rcu_read_lock(). - */ -struct task_struct *task_of_stack(struct task_struct *task, - struct vm_area_struct *vma, bool in_group) -{ - if (vm_is_stack_for_task(task, vma)) - return task; - - if (in_group) { - struct task_struct *t; - - for_each_thread(task, t) { - if (vm_is_stack_for_task(t, vma)) - return t; - } - } - - return NULL; -} - #if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT) void arch_pick_mmap_layout(struct mm_struct *mm) { -- cgit v1.2.3 From c792e8240338e41eda4d06a3a71a7bb7af4e6156 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 2 Feb 2016 16:57:38 -0800 Subject: mm: memcontrol: drop superfluous entry in the per-memcg stats array MEM_CGROUP_STAT_NSTATS is just a delimiter for cgroup1 statistics, not an actual array entry. Reuse it for the first cgroup2 stat entry, like in the event array. Fixes: b2807f07f4f8 ("mm: memcontrol: add "sock" to cgroup2 memory.stat") Signed-off-by: Johannes Weiner Cc: Vladimir Davydov Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 9ae48d4aeb5e..792c8981e633 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -51,7 +51,7 @@ enum mem_cgroup_stat_index { MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */ MEM_CGROUP_STAT_NSTATS, /* default hierarchy stats */ - MEMCG_SOCK, + MEMCG_SOCK = MEM_CGROUP_STAT_NSTATS, MEMCG_NR_STAT, }; -- cgit v1.2.3 From 30bdbb78009e67767983085e302bec6d97afc679 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Tue, 2 Feb 2016 16:57:46 -0800 Subject: mm: polish virtual memory accounting * add VM_STACK as alias for VM_GROWSUP/DOWN depending on architecture * always account VMAs with flag VM_STACK as stack (as it was before) * cleanup classifying helpers * update comments and documentation Signed-off-by: Konstantin Khlebnikov Tested-by: Sudip Mukherjee Cc: Cyrill Gorcunov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/proc.txt | 4 ++-- include/linux/mm.h | 6 ++++-- include/linux/mm_types.h | 6 +++--- mm/internal.h | 23 +++++++++++++++++++---- 4 files changed, 28 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index eaebf27539f5..843b045b4069 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -240,8 +240,8 @@ Table 1-2: Contents of the status files (as of 4.1) RssFile size of resident file mappings RssShmem size of resident shmem memory (includes SysV shm, mapping of tmpfs and shared anonymous mappings) - VmData size of data, stack, and text segments - VmStk size of data, stack, and text segments + VmData size of private data segments + VmStk size of stack segments VmExe size of text segment VmLib size of shared library code VmPTE size of page table entries diff --git a/include/linux/mm.h b/include/linux/mm.h index 0b50d7848e3a..516e14944339 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -201,11 +201,13 @@ extern unsigned int kobjsize(const void *objp); #endif #ifdef CONFIG_STACK_GROWSUP -#define VM_STACK_FLAGS (VM_GROWSUP | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT) +#define VM_STACK VM_GROWSUP #else -#define VM_STACK_FLAGS (VM_GROWSDOWN | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT) +#define VM_STACK VM_GROWSDOWN #endif +#define VM_STACK_FLAGS (VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT) + /* * Special vmas that are non-mergable, non-mlock()able. * Note: mm/huge_memory.c VM_NO_THP depends on this definition. diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index d3ebb9d21a53..624b78b848b8 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -424,9 +424,9 @@ struct mm_struct { unsigned long total_vm; /* Total pages mapped */ unsigned long locked_vm; /* Pages that have PG_mlocked set */ unsigned long pinned_vm; /* Refcount permanently increased */ - unsigned long data_vm; /* VM_WRITE & ~VM_SHARED/GROWSDOWN */ - unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE */ - unsigned long stack_vm; /* VM_GROWSUP/DOWN */ + unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */ + unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */ + unsigned long stack_vm; /* VM_STACK */ unsigned long def_flags; unsigned long start_code, end_code, start_data, end_data; unsigned long start_brk, brk, start_stack; diff --git a/mm/internal.h b/mm/internal.h index 6e976302ddd8..a38a21ebddb4 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -216,20 +216,35 @@ static inline bool is_cow_mapping(vm_flags_t flags) return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; } +/* + * These three helpers classifies VMAs for virtual memory accounting. + */ + +/* + * Executable code area - executable, not writable, not stack + */ static inline bool is_exec_mapping(vm_flags_t flags) { - return (flags & (VM_EXEC | VM_WRITE)) == VM_EXEC; + return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC; } +/* + * Stack area - atomatically grows in one direction + * + * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous: + * do_mmap() forbids all other combinations. + */ static inline bool is_stack_mapping(vm_flags_t flags) { - return (flags & (VM_STACK_FLAGS & (VM_GROWSUP | VM_GROWSDOWN))) != 0; + return (flags & VM_STACK) == VM_STACK; } +/* + * Data area - private, writable, not stack + */ static inline bool is_data_mapping(vm_flags_t flags) { - return (flags & ((VM_STACK_FLAGS & (VM_GROWSUP | VM_GROWSDOWN)) | - VM_WRITE | VM_SHARED)) == VM_WRITE; + return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE; } /* mm/util.c */ -- cgit v1.2.3 From 46437f9a554fbe3e110580ca08ab703b59f2f95a Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 2 Feb 2016 16:57:52 -0800 Subject: radix-tree: fix race in gang lookup If the indirect_ptr bit is set on a slot, that indicates we need to redo the lookup. Introduce a new function radix_tree_iter_retry() which forces the loop to retry the lookup by setting 'slot' to NULL and turning the iterator back to point at the problematic entry. This is a pretty rare problem to hit at the moment; the lookup has to race with a grow of the radix tree from a height of 0. The consequences of hitting this race are that gang lookup could return a pointer to a radix_tree_node instead of a pointer to whatever the user had inserted in the tree. Fixes: cebbd29e1c2f ("radix-tree: rewrite gang lookup using iterator") Signed-off-by: Matthew Wilcox Cc: Hugh Dickins Cc: Ohad Ben-Cohen Cc: Konstantin Khlebnikov Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 16 ++++++++++++++++ lib/radix-tree.c | 12 ++++++++++-- 2 files changed, 26 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 7c88ad156a29..00b17c526c1f 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -378,6 +378,22 @@ radix_tree_iter_init(struct radix_tree_iter *iter, unsigned long start) void **radix_tree_next_chunk(struct radix_tree_root *root, struct radix_tree_iter *iter, unsigned flags); +/** + * radix_tree_iter_retry - retry this chunk of the iteration + * @iter: iterator state + * + * If we iterate over a tree protected only by the RCU lock, a race + * against deletion or creation may result in seeing a slot for which + * radix_tree_deref_retry() returns true. If so, call this function + * and continue the iteration. + */ +static inline __must_check +void **radix_tree_iter_retry(struct radix_tree_iter *iter) +{ + iter->next_index = iter->index; + return NULL; +} + /** * radix_tree_chunk_size - get current chunk size * diff --git a/lib/radix-tree.c b/lib/radix-tree.c index fcf5d98574ce..6b79e9026e24 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1019,9 +1019,13 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results, return 0; radix_tree_for_each_slot(slot, root, &iter, first_index) { - results[ret] = indirect_to_ptr(rcu_dereference_raw(*slot)); + results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; + if (radix_tree_is_indirect_ptr(results[ret])) { + slot = radix_tree_iter_retry(&iter); + continue; + } if (++ret == max_items) break; } @@ -1098,9 +1102,13 @@ radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results, return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { - results[ret] = indirect_to_ptr(rcu_dereference_raw(*slot)); + results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; + if (radix_tree_is_indirect_ptr(results[ret])) { + slot = radix_tree_iter_retry(&iter); + continue; + } if (++ret == max_items) break; } -- cgit v1.2.3 From bf64318564c43385ffc3d3dfedab5287bdf3dfdd Mon Sep 17 00:00:00 2001 From: Matias Bjørling Date: Thu, 4 Feb 2016 15:13:27 +0100 Subject: lightnvm: allow to force mm initialization MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit System block allows the device to initialize with its configured media manager. The system blocks is written to disk, and read again when media manager is determined. For this to work, the backend must store the data. Device drivers, such as null_blk, does not have any backend storage. This patch allows the media manager to be initialized without a storage backend. It also fix incorrect configuration of capabilities in null_blk, as it does not support get/set bad block interface. Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- drivers/block/null_blk.c | 2 +- drivers/lightnvm/core.c | 25 ++++++++++++++++--------- include/linux/lightnvm.h | 4 ++++ 3 files changed, 21 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c index 8ba1e97d573c..ae05d31c0559 100644 --- a/drivers/block/null_blk.c +++ b/drivers/block/null_blk.c @@ -478,7 +478,7 @@ static int null_lnvm_id(struct nvm_dev *dev, struct nvm_id *id) id->ver_id = 0x1; id->vmnt = 0; id->cgrps = 1; - id->cap = 0x3; + id->cap = 0x2; id->dom = 0x1; id->ppaf.blk_offset = 0; diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c index 33224cb91c5b..9f6acd5d1d2e 100644 --- a/drivers/lightnvm/core.c +++ b/drivers/lightnvm/core.c @@ -572,11 +572,13 @@ int nvm_register(struct request_queue *q, char *disk_name, } } - ret = nvm_get_sysblock(dev, &dev->sb); - if (!ret) - pr_err("nvm: device not initialized.\n"); - else if (ret < 0) - pr_err("nvm: err (%d) on device initialization\n", ret); + if (dev->identity.cap & NVM_ID_DCAP_BBLKMGMT) { + ret = nvm_get_sysblock(dev, &dev->sb); + if (!ret) + pr_err("nvm: device not initialized.\n"); + else if (ret < 0) + pr_err("nvm: err (%d) on device initialization\n", ret); + } /* register device with a supported media manager */ down_write(&nvm_lock); @@ -1055,9 +1057,11 @@ static long __nvm_ioctl_dev_init(struct nvm_ioctl_dev_init *init) strncpy(info.mmtype, init->mmtype, NVM_MMTYPE_LEN); info.fs_ppa.ppa = -1; - ret = nvm_init_sysblock(dev, &info); - if (ret) - return ret; + if (dev->identity.cap & NVM_ID_DCAP_BBLKMGMT) { + ret = nvm_init_sysblock(dev, &info); + if (ret) + return ret; + } memcpy(&dev->sb, &info, sizeof(struct nvm_sb_info)); @@ -1117,7 +1121,10 @@ static long nvm_ioctl_dev_factory(struct file *file, void __user *arg) dev->mt = NULL; } - return nvm_dev_factory(dev, fact.flags); + if (dev->identity.cap & NVM_ID_DCAP_BBLKMGMT) + return nvm_dev_factory(dev, fact.flags); + + return 0; } static long nvm_ctl_ioctl(struct file *file, uint cmd, unsigned long arg) diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index d6750111e48e..2190419bdf0a 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -135,6 +135,10 @@ enum { /* Memory types */ NVM_ID_FMTYPE_SLC = 0, NVM_ID_FMTYPE_MLC = 1, + + /* Device capabilities */ + NVM_ID_DCAP_BBLKMGMT = 0x1, + NVM_UD_DCAP_ECC = 0x2, }; struct nvm_id_lp_mlc { -- cgit v1.2.3 From dc6ae6d8e7726bad4f1c87244b49cac851746c65 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Sun, 31 Jan 2016 14:36:07 +0100 Subject: crush: add chooseleaf_stable tunable Add a tunable to fix the bug that chooseleaf may cause unnecessary pg migrations when some device fails. Reflects ceph.git commit fdb3f664448e80d984470f32f04e2e6f03ab52ec. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/crush/crush.h | 8 +++++++- net/ceph/crush/mapper.c | 18 ++++++++++++++---- 2 files changed, 21 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index 48b49305716b..be8f12b8f195 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -59,7 +59,8 @@ enum { CRUSH_RULE_SET_CHOOSELEAF_TRIES = 9, /* override chooseleaf_descend_once */ CRUSH_RULE_SET_CHOOSE_LOCAL_TRIES = 10, CRUSH_RULE_SET_CHOOSE_LOCAL_FALLBACK_TRIES = 11, - CRUSH_RULE_SET_CHOOSELEAF_VARY_R = 12 + CRUSH_RULE_SET_CHOOSELEAF_VARY_R = 12, + CRUSH_RULE_SET_CHOOSELEAF_STABLE = 13 }; /* @@ -205,6 +206,11 @@ struct crush_map { * mappings line up a bit better with previous mappings. */ __u8 chooseleaf_vary_r; + /* if true, it makes chooseleaf firstn to return stable results (if + * no local retry) so that data migrations would be optimal when some + * device fails. */ + __u8 chooseleaf_stable; + #ifndef __KERNEL__ /* * version 0 (original) of straw_calc has various flaws. version 1 diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c index abb700621e4a..5fcfb98f309e 100644 --- a/net/ceph/crush/mapper.c +++ b/net/ceph/crush/mapper.c @@ -403,6 +403,7 @@ static int is_out(const struct crush_map *map, * @local_retries: localized retries * @local_fallback_retries: localized fallback retries * @recurse_to_leaf: true if we want one device under each item of given type (chooseleaf instead of choose) + * @stable: stable mode starts rep=0 in the recursive call for all replicas * @vary_r: pass r to recursive calls * @out2: second output vector for leaf items (if @recurse_to_leaf) * @parent_r: r value passed from the parent @@ -419,6 +420,7 @@ static int crush_choose_firstn(const struct crush_map *map, unsigned int local_fallback_retries, int recurse_to_leaf, unsigned int vary_r, + unsigned int stable, int *out2, int parent_r) { @@ -433,13 +435,13 @@ static int crush_choose_firstn(const struct crush_map *map, int collide, reject; int count = out_size; - dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d tries %d recurse_tries %d local_retries %d local_fallback_retries %d parent_r %d\n", + dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d tries %d recurse_tries %d local_retries %d local_fallback_retries %d parent_r %d stable %d\n", recurse_to_leaf ? "_LEAF" : "", bucket->id, x, outpos, numrep, tries, recurse_tries, local_retries, local_fallback_retries, - parent_r); + parent_r, stable); - for (rep = outpos; rep < numrep && count > 0 ; rep++) { + for (rep = stable ? 0 : outpos; rep < numrep && count > 0 ; rep++) { /* keep trying until we get a non-out, non-colliding item */ ftotal = 0; skip_rep = 0; @@ -512,13 +514,14 @@ static int crush_choose_firstn(const struct crush_map *map, if (crush_choose_firstn(map, map->buckets[-1-item], weight, weight_max, - x, outpos+1, 0, + x, stable ? 1 : outpos+1, 0, out2, outpos, count, recurse_tries, 0, local_retries, local_fallback_retries, 0, vary_r, + stable, NULL, sub_r) <= outpos) /* didn't get leaf */ @@ -816,6 +819,7 @@ int crush_do_rule(const struct crush_map *map, int choose_local_fallback_retries = map->choose_local_fallback_tries; int vary_r = map->chooseleaf_vary_r; + int stable = map->chooseleaf_stable; if ((__u32)ruleno >= map->max_rules) { dprintk(" bad ruleno %d\n", ruleno); @@ -870,6 +874,11 @@ int crush_do_rule(const struct crush_map *map, vary_r = curstep->arg1; break; + case CRUSH_RULE_SET_CHOOSELEAF_STABLE: + if (curstep->arg1 >= 0) + stable = curstep->arg1; + break; + case CRUSH_RULE_CHOOSELEAF_FIRSTN: case CRUSH_RULE_CHOOSE_FIRSTN: firstn = 1; @@ -932,6 +941,7 @@ int crush_do_rule(const struct crush_map *map, choose_local_fallback_retries, recurse_to_leaf, vary_r, + stable, c+osize, 0); } else { -- cgit v1.2.3 From 97db9a88186e3a7d3a1942370c836bf221d3ab90 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 1 Feb 2016 17:08:33 +0100 Subject: libceph: advertise support for TUNABLES5 Add TUNABLES5 feature (chooseleaf_stable tunable) to a set of features supported by default. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/ceph_features.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index f89b31d45cc8..c3b211c9fe83 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -63,6 +63,16 @@ #define CEPH_FEATURE_OSD_MIN_SIZE_RECOVERY (1ULL<<49) // duplicated since it was introduced at the same time as MIN_SIZE_RECOVERY #define CEPH_FEATURE_OSD_PROXY_FEATURES (1ULL<<49) /* overlap w/ above */ +#define CEPH_FEATURE_MON_METADATA (1ULL<<50) +#define CEPH_FEATURE_OSD_BITWISE_HOBJ_SORT (1ULL<<51) /* can sort objs bitwise */ +#define CEPH_FEATURE_OSD_PROXY_WRITE_FEATURES (1ULL<<52) +#define CEPH_FEATURE_ERASURE_CODE_PLUGINS_V3 (1ULL<<53) +#define CEPH_FEATURE_OSD_HITSET_GMT (1ULL<<54) +#define CEPH_FEATURE_HAMMER_0_94_4 (1ULL<<55) +#define CEPH_FEATURE_NEW_OSDOP_ENCODING (1ULL<<56) /* New, v7 encoding */ +#define CEPH_FEATURE_MON_STATEFUL_SUB (1ULL<<57) /* stateful mon subscription */ +#define CEPH_FEATURE_MON_ROUTE_OSDMAP (1ULL<<57) /* peon sends osdmaps */ +#define CEPH_FEATURE_CRUSH_TUNABLES5 (1ULL<<58) /* chooseleaf stable mode */ /* * The introduction of CEPH_FEATURE_OSD_SNAPMAPPER caused the feature @@ -108,7 +118,8 @@ static inline u64 ceph_sanitize_features(u64 features) CEPH_FEATURE_CRUSH_TUNABLES3 | \ CEPH_FEATURE_OSD_PRIMARY_AFFINITY | \ CEPH_FEATURE_MSGR_KEEPALIVE2 | \ - CEPH_FEATURE_CRUSH_V4) + CEPH_FEATURE_CRUSH_V4 | \ + CEPH_FEATURE_CRUSH_TUNABLES5) #define CEPH_FEATURES_REQUIRED_DEFAULT \ (CEPH_FEATURE_NOSRCADDR | \ -- cgit v1.2.3 From b0b31a8ffe54abf0a455bcaee54dd92f08817164 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 3 Feb 2016 15:25:48 +0100 Subject: libceph: MOSDOpReply v7 encoding Empty request_redirect_t (struct ceph_request_redirect in the kernel client) is now encoded with a bool. NEW_OSDOPREPLY_ENCODING feature bit overlaps with already supported CRUSH_TUNABLES5. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/ceph_features.h | 5 ++++- net/ceph/osd_client.c | 10 ++++++++++ 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index c3b211c9fe83..c1ef6f14e7be 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -73,6 +73,8 @@ #define CEPH_FEATURE_MON_STATEFUL_SUB (1ULL<<57) /* stateful mon subscription */ #define CEPH_FEATURE_MON_ROUTE_OSDMAP (1ULL<<57) /* peon sends osdmaps */ #define CEPH_FEATURE_CRUSH_TUNABLES5 (1ULL<<58) /* chooseleaf stable mode */ +// duplicated since it was introduced at the same time as CEPH_FEATURE_CRUSH_TUNABLES5 +#define CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING (1ULL<<58) /* New, v7 encoding */ /* * The introduction of CEPH_FEATURE_OSD_SNAPMAPPER caused the feature @@ -119,7 +121,8 @@ static inline u64 ceph_sanitize_features(u64 features) CEPH_FEATURE_OSD_PRIMARY_AFFINITY | \ CEPH_FEATURE_MSGR_KEEPALIVE2 | \ CEPH_FEATURE_CRUSH_V4 | \ - CEPH_FEATURE_CRUSH_TUNABLES5) + CEPH_FEATURE_CRUSH_TUNABLES5 | \ + CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING) #define CEPH_FEATURES_REQUIRED_DEFAULT \ (CEPH_FEATURE_NOSRCADDR | \ diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index f8f235930d88..3534e12683d3 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1770,6 +1770,7 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg) u32 osdmap_epoch; int already_completed; u32 bytes; + u8 decode_redir; unsigned int i; tid = le64_to_cpu(msg->hdr.tid); @@ -1841,6 +1842,15 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg) p += 8 + 4; /* skip replay_version */ p += 8; /* skip user_version */ + if (le16_to_cpu(msg->hdr.version) >= 7) + ceph_decode_8_safe(&p, end, decode_redir, bad_put); + else + decode_redir = 1; + } else { + decode_redir = 0; + } + + if (decode_redir) { err = ceph_redirect_decode(&p, end, &redir); if (err) goto bad_put; -- cgit v1.2.3 From 0fb5b1fb30fba3671dd5b1489d78e93e08d62e4e Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Thu, 4 Feb 2016 00:52:12 -0500 Subject: block/sd: Return -EREMOTEIO when WRITE SAME and DISCARD are disabled When a storage device rejects a WRITE SAME command we will disable write same functionality for the device and return -EREMOTEIO to the block layer. -EREMOTEIO will in turn prevent DM from retrying the I/O and/or failing the path. Yiwen Jiang discovered a small race where WRITE SAME requests issued simultaneously would cause -EIO to be returned. This happened because any requests being prepared after WRITE SAME had been disabled for the device caused us to return BLKPREP_KILL. The latter caused the block layer to return -EIO upon completion. To overcome this we introduce BLKPREP_INVALID which indicates that this is an invalid request for the device. blk_peek_request() is modified to return -EREMOTEIO in that case. Reported-by: Yiwen Jiang Suggested-by: Mike Snitzer Reviewed-by: Hannes Reinicke Reviewed-by: Ewan Milne Reviewed-by: Yiwen Jiang Signed-off-by: Martin K. Petersen --- block/blk-core.c | 6 ++++-- drivers/scsi/sd.c | 4 ++-- include/linux/blkdev.h | 9 ++++++--- 3 files changed, 12 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index 476244d59309..35607dd0223b 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2447,14 +2447,16 @@ struct request *blk_peek_request(struct request_queue *q) rq = NULL; break; - } else if (ret == BLKPREP_KILL) { + } else if (ret == BLKPREP_KILL || ret == BLKPREP_INVALID) { + int err = (ret == BLKPREP_INVALID) ? -EREMOTEIO : -EIO; + rq->cmd_flags |= REQ_QUIET; /* * Mark this request as started so we don't trigger * any debug logic in the end I/O path. */ blk_start_request(rq); - __blk_end_request_all(rq, -EIO); + __blk_end_request_all(rq, err); } else { printk(KERN_ERR "%s: bad return=%d\n", __func__, ret); break; diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index ec163d08f6c3..6e841c6da632 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -761,7 +761,7 @@ static int sd_setup_discard_cmnd(struct scsi_cmnd *cmd) break; default: - ret = BLKPREP_KILL; + ret = BLKPREP_INVALID; goto out; } @@ -839,7 +839,7 @@ static int sd_setup_write_same_cmnd(struct scsi_cmnd *cmd) int ret; if (sdkp->device->no_write_same) - return BLKPREP_KILL; + return BLKPREP_INVALID; BUG_ON(bio_offset(bio) || bio_iovec(bio).bv_len != sdp->sector_size); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d372ea87ead5..a9b643a0647f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -681,9 +681,12 @@ static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b) /* * q->prep_rq_fn return values */ -#define BLKPREP_OK 0 /* serve it */ -#define BLKPREP_KILL 1 /* fatal error, kill */ -#define BLKPREP_DEFER 2 /* leave on queue */ +enum { + BLKPREP_OK, /* serve it */ + BLKPREP_KILL, /* fatal error, kill, return -EIO */ + BLKPREP_DEFER, /* leave on queue */ + BLKPREP_INVALID, /* invalid command, kill, return -EREMOTEIO */ +}; extern unsigned long blk_max_low_pfn, blk_max_pfn; -- cgit v1.2.3 From 080fe2068e1c7f19f565b30b78baf78edf16a980 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 5 Feb 2016 15:36:41 -0800 Subject: mm, hugetlb: don't require CMA for runtime gigantic pages Commit 944d9fec8d7a ("hugetlb: add support for gigantic page allocation at runtime") has added the runtime gigantic page allocation via alloc_contig_range(), making this support available only when CONFIG_CMA is enabled. Because it doesn't depend on MIGRATE_CMA pageblocks and the associated infrastructure, it is possible with few simple adjustments to require only CONFIG_MEMORY_ISOLATION instead of full CONFIG_CMA. After this patch, alloc_contig_range() and related functions are available and used for gigantic pages with just CONFIG_MEMORY_ISOLATION enabled. Note CONFIG_CMA selects CONFIG_MEMORY_ISOLATION. This allows supporting runtime gigantic pages without the CMA-specific checks in page allocator fastpaths. Signed-off-by: Vlastimil Babka Cc: Luiz Capitulino Cc: Kirill A. Shutemov Cc: Zhang Yanfei Cc: Yasuaki Ishimatsu Cc: Joonsoo Kim Cc: Naoya Horiguchi Cc: Mel Gorman Cc: Davidlohr Bueso Cc: Hillf Danton Cc: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/mm/hugetlbpage.c | 4 ++-- include/linux/gfp.h | 6 +++--- mm/hugetlb.c | 2 +- mm/page_alloc.c | 2 +- 4 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 42982b26e32b..740d7ac03a55 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -173,10 +173,10 @@ static __init int setup_hugepagesz(char *opt) } __setup("hugepagesz=", setup_hugepagesz); -#ifdef CONFIG_CMA +#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA) static __init int gigantic_pages_init(void) { - /* With CMA we can allocate gigantic pages at runtime */ + /* With compaction or CMA we can allocate gigantic pages at runtime */ if (cpu_has_gbpages && !size_to_hstate(1UL << PUD_SHIFT)) hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); return 0; diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 28ad5f6494b0..af1f2b24bbe4 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -547,16 +547,16 @@ static inline bool pm_suspended_storage(void) } #endif /* CONFIG_PM_SLEEP */ -#ifdef CONFIG_CMA - +#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA) /* The below functions must be run on a range from a single zone. */ extern int alloc_contig_range(unsigned long start, unsigned long end, unsigned migratetype); extern void free_contig_range(unsigned long pfn, unsigned nr_pages); +#endif +#ifdef CONFIG_CMA /* CMA stuff */ extern void init_cma_reserved_pageblock(struct page *page); - #endif #endif /* __LINUX_GFP_H */ diff --git a/mm/hugetlb.c b/mm/hugetlb.c index d7a802427ea8..06ae13e869d0 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1001,7 +1001,7 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) ((node = hstate_next_node_to_free(hs, mask)) || 1); \ nr_nodes--) -#if defined(CONFIG_CMA) && defined(CONFIG_X86_64) +#if defined(CONFIG_X86_64) && ((defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)) static void destroy_compound_gigantic_page(struct page *page, unsigned int order) { diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ea2c4d3e0c03..838ca8bb64f7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6620,7 +6620,7 @@ bool is_pageblock_removable_nolock(struct page *page) return !has_unmovable_pages(zone, page, 0, true); } -#ifdef CONFIG_CMA +#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA) static unsigned long pfn_max_align_down(unsigned long pfn) { -- cgit v1.2.3 From 12352d3cae2cebe18805a91fab34b534d7444231 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Fri, 5 Feb 2016 15:36:50 -0800 Subject: mm: replace vma_lock_anon_vma with anon_vma_lock_read/write Sequence vma_lock_anon_vma() - vma_unlock_anon_vma() isn't safe if anon_vma appeared between lock and unlock. We have to check anon_vma first or call anon_vma_prepare() to be sure that it's here. There are only few users of these legacy helpers. Let's get rid of them. This patch fixes anon_vma lock imbalance in validate_mm(). Write lock isn't required here, read lock is enough. And reorders expand_downwards/expand_upwards: security_mmap_addr() and wrapping-around check don't have to be under anon vma lock. Link: https://lkml.kernel.org/r/CACT4Y+Y908EjM2z=706dv4rV6dWtxTLK9nFg9_7DhRMLppBo2g@mail.gmail.com Signed-off-by: Konstantin Khlebnikov Reported-by: Dmitry Vyukov Acked-by: Kirill A. Shutemov Cc: Andrea Arcangeli Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 14 ------------- mm/mmap.c | 55 ++++++++++++++++++++++++---------------------------- 2 files changed, 25 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index bdf597c4f0be..a07f42bedda3 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -109,20 +109,6 @@ static inline void put_anon_vma(struct anon_vma *anon_vma) __put_anon_vma(anon_vma); } -static inline void vma_lock_anon_vma(struct vm_area_struct *vma) -{ - struct anon_vma *anon_vma = vma->anon_vma; - if (anon_vma) - down_write(&anon_vma->root->rwsem); -} - -static inline void vma_unlock_anon_vma(struct vm_area_struct *vma) -{ - struct anon_vma *anon_vma = vma->anon_vma; - if (anon_vma) - up_write(&anon_vma->root->rwsem); -} - static inline void anon_vma_lock_write(struct anon_vma *anon_vma) { down_write(&anon_vma->root->rwsem); diff --git a/mm/mmap.c b/mm/mmap.c index 918c9ec5043f..2f2415a7a688 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -459,12 +459,16 @@ static void validate_mm(struct mm_struct *mm) struct vm_area_struct *vma = mm->mmap; while (vma) { + struct anon_vma *anon_vma = vma->anon_vma; struct anon_vma_chain *avc; - vma_lock_anon_vma(vma); - list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) - anon_vma_interval_tree_verify(avc); - vma_unlock_anon_vma(vma); + if (anon_vma) { + anon_vma_lock_read(anon_vma); + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + anon_vma_interval_tree_verify(avc); + anon_vma_unlock_read(anon_vma); + } + highest_address = vma->vm_end; vma = vma->vm_next; i++; @@ -2145,32 +2149,27 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns int expand_upwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; - int error; + int error = 0; if (!(vma->vm_flags & VM_GROWSUP)) return -EFAULT; - /* - * We must make sure the anon_vma is allocated - * so that the anon_vma locking is not a noop. - */ + /* Guard against wrapping around to address 0. */ + if (address < PAGE_ALIGN(address+4)) + address = PAGE_ALIGN(address+4); + else + return -ENOMEM; + + /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) return -ENOMEM; - vma_lock_anon_vma(vma); /* * vma->vm_start/vm_end cannot change under us because the caller * is required to hold the mmap_sem in read mode. We need the * anon_vma lock to serialize against concurrent expand_stacks. - * Also guard against wrapping around to address 0. */ - if (address < PAGE_ALIGN(address+4)) - address = PAGE_ALIGN(address+4); - else { - vma_unlock_anon_vma(vma); - return -ENOMEM; - } - error = 0; + anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ if (address > vma->vm_end) { @@ -2188,7 +2187,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) * updates, but we only hold a shared mmap_sem * lock here, so we need to protect against * concurrent vma expansions. - * vma_lock_anon_vma() doesn't help here, as + * anon_vma_lock_write() doesn't help here, as * we don't guarantee that all growable vmas * in a mm share the same root anon vma. * So, we reuse mm->page_table_lock to guard @@ -2211,7 +2210,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) } } } - vma_unlock_anon_vma(vma); + anon_vma_unlock_write(vma->anon_vma); khugepaged_enter_vma_merge(vma, vma->vm_flags); validate_mm(mm); return error; @@ -2227,25 +2226,21 @@ int expand_downwards(struct vm_area_struct *vma, struct mm_struct *mm = vma->vm_mm; int error; - /* - * We must make sure the anon_vma is allocated - * so that the anon_vma locking is not a noop. - */ - if (unlikely(anon_vma_prepare(vma))) - return -ENOMEM; - address &= PAGE_MASK; error = security_mmap_addr(address); if (error) return error; - vma_lock_anon_vma(vma); + /* We must make sure the anon_vma is allocated. */ + if (unlikely(anon_vma_prepare(vma))) + return -ENOMEM; /* * vma->vm_start/vm_end cannot change under us because the caller * is required to hold the mmap_sem in read mode. We need the * anon_vma lock to serialize against concurrent expand_stacks. */ + anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ if (address < vma->vm_start) { @@ -2263,7 +2258,7 @@ int expand_downwards(struct vm_area_struct *vma, * updates, but we only hold a shared mmap_sem * lock here, so we need to protect against * concurrent vma expansions. - * vma_lock_anon_vma() doesn't help here, as + * anon_vma_lock_write() doesn't help here, as * we don't guarantee that all growable vmas * in a mm share the same root anon vma. * So, we reuse mm->page_table_lock to guard @@ -2284,7 +2279,7 @@ int expand_downwards(struct vm_area_struct *vma, } } } - vma_unlock_anon_vma(vma); + anon_vma_unlock_write(vma->anon_vma); khugepaged_enter_vma_merge(vma, vma->vm_flags); validate_mm(mm); return error; -- cgit v1.2.3 From 732042821cfa106b3c20b9780e4c60fee9d68900 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Fri, 5 Feb 2016 15:37:01 -0800 Subject: radix-tree: fix oops after radix_tree_iter_retry Helper radix_tree_iter_retry() resets next_index to the current index. In following radix_tree_next_slot current chunk size becomes zero. This isn't checked and it tries to dereference null pointer in slot. Tagged iterator is fine because retry happens only at slot 0 where tag bitmask in iter->tags is filled with single bit. Fixes: 46437f9a554f ("radix-tree: fix race in gang lookup") Signed-off-by: Konstantin Khlebnikov Cc: Matthew Wilcox Cc: Hugh Dickins Cc: Ohad Ben-Cohen Cc: Jeremiah Mahler Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 00b17c526c1f..f54be7082207 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -400,7 +400,7 @@ void **radix_tree_iter_retry(struct radix_tree_iter *iter) * @iter: pointer to radix tree iterator * Returns: current chunk size */ -static __always_inline unsigned +static __always_inline long radix_tree_chunk_size(struct radix_tree_iter *iter) { return iter->next_index - iter->index; @@ -434,9 +434,9 @@ radix_tree_next_slot(void **slot, struct radix_tree_iter *iter, unsigned flags) return slot + offset + 1; } } else { - unsigned size = radix_tree_chunk_size(iter) - 1; + long size = radix_tree_chunk_size(iter); - while (size--) { + while (--size > 0) { slot++; iter->index++; if (likely(*slot)) -- cgit v1.2.3 From 1f55c718c290616889c04946864a13ef30f64929 Mon Sep 17 00:00:00 2001 From: "Herton R. Krzesinski" Date: Thu, 14 Jan 2016 17:56:58 -0200 Subject: pty: make sure super_block is still valid in final /dev/tty close Considering current pty code and multiple devpts instances, it's possible to umount a devpts file system while a program still has /dev/tty opened pointing to a previosuly closed pty pair in that instance. In the case all ptmx and pts/N files are closed, umount can be done. If the program closes /dev/tty after umount is done, devpts_kill_index will use now an invalid super_block, which was already destroyed in the umount operation after running ->kill_sb. This is another "use after free" type of issue, but now related to the allocated super_block instance. To avoid the problem (warning at ida_remove and potential crashes) for this specific case, I added two functions in devpts which grabs additional references to the super_block, which pty code now uses so it makes sure the super block structure is still valid until pty shutdown is done. I also moved the additional inode references to the same functions, which also covered similar case with inode being freed before /dev/tty final close/shutdown. Signed-off-by: Herton R. Krzesinski Cc: stable@vger.kernel.org # 2.6.29+ Reviewed-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/pty.c | 9 ++++++--- fs/devpts/inode.c | 20 ++++++++++++++++++++ include/linux/devpts_fs.h | 4 ++++ 3 files changed, 30 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index 3b5cde833ee5..2348fa613707 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -688,7 +688,7 @@ static void pty_unix98_shutdown(struct tty_struct *tty) else ptmx_inode = tty->link->driver_data; devpts_kill_index(ptmx_inode, tty->index); - iput(ptmx_inode); /* drop reference we acquired at ptmx_open */ + devpts_del_ref(ptmx_inode); } static const struct tty_operations ptm_unix98_ops = { @@ -785,9 +785,12 @@ static int ptmx_open(struct inode *inode, struct file *filp) * still have /dev/tty opened pointing to the master/slave pair (ptmx * is closed/released before /dev/tty), we must make sure that the inode * is still valid when we call the final pty_unix98_shutdown, thus we - * hold an additional reference to the ptmx inode + * hold an additional reference to the ptmx inode. For the same /dev/tty + * last close case, we also need to make sure the super_block isn't + * destroyed (devpts instance unmounted), before /dev/tty is closed and + * on its release devpts_kill_index is called. */ - ihold(inode); + devpts_add_ref(inode); tty_add_file(tty, filp); diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 1f107fd51328..655f21f99160 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -575,6 +575,26 @@ void devpts_kill_index(struct inode *ptmx_inode, int idx) mutex_unlock(&allocated_ptys_lock); } +/* + * pty code needs to hold extra references in case of last /dev/tty close + */ + +void devpts_add_ref(struct inode *ptmx_inode) +{ + struct super_block *sb = pts_sb_from_inode(ptmx_inode); + + atomic_inc(&sb->s_active); + ihold(ptmx_inode); +} + +void devpts_del_ref(struct inode *ptmx_inode) +{ + struct super_block *sb = pts_sb_from_inode(ptmx_inode); + + iput(ptmx_inode); + deactivate_super(sb); +} + /** * devpts_pty_new -- create a new inode in /dev/pts/ * @ptmx_inode: inode of the master diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h index 251a2090a554..e0ee0b3000b2 100644 --- a/include/linux/devpts_fs.h +++ b/include/linux/devpts_fs.h @@ -19,6 +19,8 @@ int devpts_new_index(struct inode *ptmx_inode); void devpts_kill_index(struct inode *ptmx_inode, int idx); +void devpts_add_ref(struct inode *ptmx_inode); +void devpts_del_ref(struct inode *ptmx_inode); /* mknod in devpts */ struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index, void *priv); @@ -32,6 +34,8 @@ void devpts_pty_kill(struct inode *inode); /* Dummy stubs in the no-pty case */ static inline int devpts_new_index(struct inode *ptmx_inode) { return -EINVAL; } static inline void devpts_kill_index(struct inode *ptmx_inode, int idx) { } +static inline void devpts_add_ref(struct inode *ptmx_inode) { } +static inline void devpts_del_ref(struct inode *ptmx_inode) { } static inline struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index, void *priv) { -- cgit v1.2.3 From 5f74f82ea34c0da80ea0b49192bb5ea06e063593 Mon Sep 17 00:00:00 2001 From: Hans Westgaard Ry Date: Wed, 3 Feb 2016 09:26:57 +0100 Subject: net:Add sysctl_max_skb_frags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Devices may have limits on the number of fragments in an skb they support. Current codebase uses a constant as maximum for number of fragments one skb can hold and use. When enabling scatter/gather and running traffic with many small messages the codebase uses the maximum number of fragments and may thereby violate the max for certain devices. The patch introduces a global variable as max number of fragments. Signed-off-by: Hans Westgaard Ry Reviewed-by: Håkon Bugge Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + net/core/skbuff.c | 2 ++ net/core/sysctl_net_core.c | 10 ++++++++++ net/ipv4/tcp.c | 4 ++-- 4 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 11f935c1a090..4ce9ff7086f4 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -299,6 +299,7 @@ struct sk_buff; #else #define MAX_SKB_FRAGS (65536/PAGE_SIZE + 1) #endif +extern int sysctl_max_skb_frags; typedef struct skb_frag_struct skb_frag_t; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b2df375ec9c2..5bf88f58bee7 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -79,6 +79,8 @@ struct kmem_cache *skbuff_head_cache __read_mostly; static struct kmem_cache *skbuff_fclone_cache __read_mostly; +int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS; +EXPORT_SYMBOL(sysctl_max_skb_frags); /** * skb_panic - private function for out-of-line support diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 95b6139d710c..a6beb7b6ae55 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -26,6 +26,7 @@ static int zero = 0; static int one = 1; static int min_sndbuf = SOCK_MIN_SNDBUF; static int min_rcvbuf = SOCK_MIN_RCVBUF; +static int max_skb_frags = MAX_SKB_FRAGS; static int net_msg_warn; /* Unused, but still a sysctl */ @@ -392,6 +393,15 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "max_skb_frags", + .data = &sysctl_max_skb_frags, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + .extra2 = &max_skb_frags, + }, { } }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 19746b3fcbbe..0c36ef4a3f86 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -940,7 +940,7 @@ new_segment: i = skb_shinfo(skb)->nr_frags; can_coalesce = skb_can_coalesce(skb, i, page, offset); - if (!can_coalesce && i >= MAX_SKB_FRAGS) { + if (!can_coalesce && i >= sysctl_max_skb_frags) { tcp_mark_push(tp, skb); goto new_segment; } @@ -1213,7 +1213,7 @@ new_segment: if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { - if (i == MAX_SKB_FRAGS || !sg) { + if (i == sysctl_max_skb_frags || !sg) { tcp_mark_push(tp, skb); goto new_segment; } -- cgit v1.2.3 From 73500267c930baadadb0d02284909731baf151f7 Mon Sep 17 00:00:00 2001 From: Peter Jones Date: Mon, 8 Feb 2016 14:48:11 -0500 Subject: lib/ucs2_string: Add ucs2 -> utf8 helper functions This adds ucs2_utf8size(), which tells us how big our ucs2 string is in bytes, and ucs2_as_utf8, which translates from ucs2 to utf8.. Signed-off-by: Peter Jones Tested-by: Lee, Chun-Yi Acked-by: Matthew Garrett Signed-off-by: Matt Fleming --- include/linux/ucs2_string.h | 4 +++ lib/ucs2_string.c | 62 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 66 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ucs2_string.h b/include/linux/ucs2_string.h index cbb20afdbc01..bb679b48f408 100644 --- a/include/linux/ucs2_string.h +++ b/include/linux/ucs2_string.h @@ -11,4 +11,8 @@ unsigned long ucs2_strlen(const ucs2_char_t *s); unsigned long ucs2_strsize(const ucs2_char_t *data, unsigned long maxlength); int ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len); +unsigned long ucs2_utf8size(const ucs2_char_t *src); +unsigned long ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, + unsigned long maxlength); + #endif /* _LINUX_UCS2_STRING_H_ */ diff --git a/lib/ucs2_string.c b/lib/ucs2_string.c index 6f500ef2301d..17dd74e21ef9 100644 --- a/lib/ucs2_string.c +++ b/lib/ucs2_string.c @@ -49,3 +49,65 @@ ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len) } } EXPORT_SYMBOL(ucs2_strncmp); + +unsigned long +ucs2_utf8size(const ucs2_char_t *src) +{ + unsigned long i; + unsigned long j = 0; + + for (i = 0; i < ucs2_strlen(src); i++) { + u16 c = src[i]; + + if (c > 0x800) + j += 3; + else if (c > 0x80) + j += 2; + else + j += 1; + } + + return j; +} +EXPORT_SYMBOL(ucs2_utf8size); + +/* + * copy at most maxlength bytes of whole utf8 characters to dest from the + * ucs2 string src. + * + * The return value is the number of characters copied, not including the + * final NUL character. + */ +unsigned long +ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, unsigned long maxlength) +{ + unsigned int i; + unsigned long j = 0; + unsigned long limit = ucs2_strnlen(src, maxlength); + + for (i = 0; maxlength && i < limit; i++) { + u16 c = src[i]; + + if (c > 0x800) { + if (maxlength < 3) + break; + maxlength -= 3; + dest[j++] = 0xe0 | (c & 0xf000) >> 12; + dest[j++] = 0x80 | (c & 0x0fc0) >> 8; + dest[j++] = 0x80 | (c & 0x003f); + } else if (c > 0x80) { + if (maxlength < 2) + break; + maxlength -= 2; + dest[j++] = 0xc0 | (c & 0xfe0) >> 5; + dest[j++] = 0x80 | (c & 0x01f); + } else { + maxlength -= 1; + dest[j++] = c & 0x7f; + } + } + if (maxlength) + dest[j] = '\0'; + return j; +} +EXPORT_SYMBOL(ucs2_as_utf8); -- cgit v1.2.3 From 8282f5d9c17fe15a9e658c06e3f343efae1a2a2f Mon Sep 17 00:00:00 2001 From: Peter Jones Date: Mon, 8 Feb 2016 14:48:14 -0500 Subject: efi: Make our variable validation list include the guid All the variables in this list so far are defined to be in the global namespace in the UEFI spec, so this just further ensures we're validating the variables we think we are. Including the guid for entries will become more important in future patches when we decide whether or not to allow deletion of variables based on presence in this list. Signed-off-by: Peter Jones Tested-by: Lee, Chun-Yi Acked-by: Matthew Garrett Signed-off-by: Matt Fleming --- drivers/firmware/efi/efivars.c | 5 ++-- drivers/firmware/efi/vars.c | 52 +++++++++++++++++++++++++++--------------- include/linux/efi.h | 3 ++- 3 files changed, 38 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c index f4ff8abc5f3e..10e6774ab2a2 100644 --- a/drivers/firmware/efi/efivars.c +++ b/drivers/firmware/efi/efivars.c @@ -221,7 +221,7 @@ sanity_check(struct efi_variable *var, efi_char16_t *name, efi_guid_t vendor, } if ((attributes & ~EFI_VARIABLE_MASK) != 0 || - efivar_validate(name, data, size) == false) { + efivar_validate(vendor, name, data, size) == false) { printk(KERN_ERR "efivars: Malformed variable content\n"); return -EINVAL; } @@ -447,7 +447,8 @@ static ssize_t efivar_create(struct file *filp, struct kobject *kobj, } if ((attributes & ~EFI_VARIABLE_MASK) != 0 || - efivar_validate(name, data, size) == false) { + efivar_validate(new_var->VendorGuid, name, data, + size) == false) { printk(KERN_ERR "efivars: Malformed variable content\n"); return -EINVAL; } diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index 5c5fde3e6c37..9a53da21e7b6 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -165,31 +165,42 @@ validate_ascii_string(efi_char16_t *var_name, int match, u8 *buffer, } struct variable_validate { + efi_guid_t vendor; char *name; bool (*validate)(efi_char16_t *var_name, int match, u8 *data, unsigned long len); }; +/* + * This is the list of variables we need to validate. + * + * If it has a validate() method that's not NULL, it'll go into the + * validation routine. If not, it is assumed valid. + * + * Note that it's sorted by {vendor,name}, but globbed names must come after + * any other name with the same prefix. + */ static const struct variable_validate variable_validate[] = { - { "BootNext", validate_uint16 }, - { "BootOrder", validate_boot_order }, - { "DriverOrder", validate_boot_order }, - { "Boot*", validate_load_option }, - { "Driver*", validate_load_option }, - { "ConIn", validate_device_path }, - { "ConInDev", validate_device_path }, - { "ConOut", validate_device_path }, - { "ConOutDev", validate_device_path }, - { "ErrOut", validate_device_path }, - { "ErrOutDev", validate_device_path }, - { "Timeout", validate_uint16 }, - { "Lang", validate_ascii_string }, - { "PlatformLang", validate_ascii_string }, - { "", NULL }, + { EFI_GLOBAL_VARIABLE_GUID, "BootNext", validate_uint16 }, + { EFI_GLOBAL_VARIABLE_GUID, "BootOrder", validate_boot_order }, + { EFI_GLOBAL_VARIABLE_GUID, "Boot*", validate_load_option }, + { EFI_GLOBAL_VARIABLE_GUID, "DriverOrder", validate_boot_order }, + { EFI_GLOBAL_VARIABLE_GUID, "Driver*", validate_load_option }, + { EFI_GLOBAL_VARIABLE_GUID, "ConIn", validate_device_path }, + { EFI_GLOBAL_VARIABLE_GUID, "ConInDev", validate_device_path }, + { EFI_GLOBAL_VARIABLE_GUID, "ConOut", validate_device_path }, + { EFI_GLOBAL_VARIABLE_GUID, "ConOutDev", validate_device_path }, + { EFI_GLOBAL_VARIABLE_GUID, "ErrOut", validate_device_path }, + { EFI_GLOBAL_VARIABLE_GUID, "ErrOutDev", validate_device_path }, + { EFI_GLOBAL_VARIABLE_GUID, "Lang", validate_ascii_string }, + { EFI_GLOBAL_VARIABLE_GUID, "PlatformLang", validate_ascii_string }, + { EFI_GLOBAL_VARIABLE_GUID, "Timeout", validate_uint16 }, + { NULL_GUID, "", NULL }, }; bool -efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long data_size) +efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data, + unsigned long data_size) { int i; unsigned long utf8_size; @@ -203,9 +214,12 @@ efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long data_size) ucs2_as_utf8(utf8_name, var_name, utf8_size); utf8_name[utf8_size] = '\0'; - for (i = 0; variable_validate[i].validate != NULL; i++) { + for (i = 0; variable_validate[i].name[0] != '\0'; i++) { const char *name = variable_validate[i].name; - int match; + int match = 0; + + if (efi_guidcmp(vendor, variable_validate[i].vendor)) + continue; for (match = 0; ; match++) { char c = name[match]; @@ -862,7 +876,7 @@ int efivar_entry_set_get_size(struct efivar_entry *entry, u32 attributes, *set = false; - if (efivar_validate(name, data, *size) == false) + if (efivar_validate(*vendor, name, data, *size) == false) return -EINVAL; /* diff --git a/include/linux/efi.h b/include/linux/efi.h index 569b5a866bb1..16ca611aabc8 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1199,7 +1199,8 @@ int efivar_entry_iter(int (*func)(struct efivar_entry *, void *), struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid, struct list_head *head, bool remove); -bool efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len); +bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data, + unsigned long data_size); extern struct work_struct efivar_work; void efivar_run_worker(void); -- cgit v1.2.3 From ed8b0de5a33d2a2557dce7f9429dca8cb5bc5879 Mon Sep 17 00:00:00 2001 From: Peter Jones Date: Mon, 8 Feb 2016 14:48:15 -0500 Subject: efi: Make efivarfs entries immutable by default "rm -rf" is bricking some peoples' laptops because of variables being used to store non-reinitializable firmware driver data that's required to POST the hardware. These are 100% bugs, and they need to be fixed, but in the mean time it shouldn't be easy to *accidentally* brick machines. We have to have delete working, and picking which variables do and don't work for deletion is quite intractable, so instead make everything immutable by default (except for a whitelist), and make tools that aren't quite so broad-spectrum unset the immutable flag. Signed-off-by: Peter Jones Tested-by: Lee, Chun-Yi Acked-by: Matthew Garrett Signed-off-by: Matt Fleming --- Documentation/filesystems/efivarfs.txt | 7 +++ drivers/firmware/efi/vars.c | 87 +++++++++++++++++++------- fs/efivarfs/file.c | 70 +++++++++++++++++++++ fs/efivarfs/inode.c | 30 +++++---- fs/efivarfs/internal.h | 3 +- fs/efivarfs/super.c | 9 ++- include/linux/efi.h | 2 + tools/testing/selftests/efivarfs/efivarfs.sh | 19 +++++- tools/testing/selftests/efivarfs/open-unlink.c | 72 ++++++++++++++++++++- 9 files changed, 258 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/efivarfs.txt b/Documentation/filesystems/efivarfs.txt index c477af086e65..686a64bba775 100644 --- a/Documentation/filesystems/efivarfs.txt +++ b/Documentation/filesystems/efivarfs.txt @@ -14,3 +14,10 @@ filesystem. efivarfs is typically mounted like this, mount -t efivarfs none /sys/firmware/efi/efivars + +Due to the presence of numerous firmware bugs where removing non-standard +UEFI variables causes the system firmware to fail to POST, efivarfs +files that are not well-known standardized variables are created +as immutable files. This doesn't prevent removal - "chattr -i" will work - +but it does prevent this kind of failure from being accomplished +accidentally. diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index 9a53da21e7b6..50f10bad2604 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -172,10 +172,12 @@ struct variable_validate { }; /* - * This is the list of variables we need to validate. + * This is the list of variables we need to validate, as well as the + * whitelist for what we think is safe not to default to immutable. * * If it has a validate() method that's not NULL, it'll go into the - * validation routine. If not, it is assumed valid. + * validation routine. If not, it is assumed valid, but still used for + * whitelisting. * * Note that it's sorted by {vendor,name}, but globbed names must come after * any other name with the same prefix. @@ -193,11 +195,37 @@ static const struct variable_validate variable_validate[] = { { EFI_GLOBAL_VARIABLE_GUID, "ErrOut", validate_device_path }, { EFI_GLOBAL_VARIABLE_GUID, "ErrOutDev", validate_device_path }, { EFI_GLOBAL_VARIABLE_GUID, "Lang", validate_ascii_string }, + { EFI_GLOBAL_VARIABLE_GUID, "OsIndications", NULL }, { EFI_GLOBAL_VARIABLE_GUID, "PlatformLang", validate_ascii_string }, { EFI_GLOBAL_VARIABLE_GUID, "Timeout", validate_uint16 }, { NULL_GUID, "", NULL }, }; +static bool +variable_matches(const char *var_name, size_t len, const char *match_name, + int *match) +{ + for (*match = 0; ; (*match)++) { + char c = match_name[*match]; + char u = var_name[*match]; + + /* Wildcard in the matching name means we've matched */ + if (c == '*') + return true; + + /* Case sensitive match */ + if (!c && *match == len) + return true; + + if (c != u) + return false; + + if (!c) + return true; + } + return true; +} + bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data, unsigned long data_size) @@ -221,35 +249,48 @@ efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data, if (efi_guidcmp(vendor, variable_validate[i].vendor)) continue; - for (match = 0; ; match++) { - char c = name[match]; - char u = utf8_name[match]; - - /* Wildcard in the matching name means we've matched */ - if (c == '*') { - kfree(utf8_name); - return variable_validate[i].validate(var_name, - match, data, data_size); - } - - /* Case sensitive match */ - if (c != u) + if (variable_matches(utf8_name, utf8_size+1, name, &match)) { + if (variable_validate[i].validate == NULL) break; - - /* Reached the end of the string while matching */ - if (!c) { - kfree(utf8_name); - return variable_validate[i].validate(var_name, - match, data, data_size); - } + kfree(utf8_name); + return variable_validate[i].validate(var_name, match, + data, data_size); } } - kfree(utf8_name); return true; } EXPORT_SYMBOL_GPL(efivar_validate); +bool +efivar_variable_is_removable(efi_guid_t vendor, const char *var_name, + size_t len) +{ + int i; + bool found = false; + int match = 0; + + /* + * Check if our variable is in the validated variables list + */ + for (i = 0; variable_validate[i].name[0] != '\0'; i++) { + if (efi_guidcmp(variable_validate[i].vendor, vendor)) + continue; + + if (variable_matches(var_name, len, + variable_validate[i].name, &match)) { + found = true; + break; + } + } + + /* + * If it's in our list, it is removable. + */ + return found; +} +EXPORT_SYMBOL_GPL(efivar_variable_is_removable); + static efi_status_t check_var_size(u32 attributes, unsigned long size) { diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c index c424e4813ec8..d48e0d261d78 100644 --- a/fs/efivarfs/file.c +++ b/fs/efivarfs/file.c @@ -10,6 +10,7 @@ #include #include #include +#include #include "internal.h" @@ -103,9 +104,78 @@ out_free: return size; } +static int +efivarfs_ioc_getxflags(struct file *file, void __user *arg) +{ + struct inode *inode = file->f_mapping->host; + unsigned int i_flags; + unsigned int flags = 0; + + i_flags = inode->i_flags; + if (i_flags & S_IMMUTABLE) + flags |= FS_IMMUTABLE_FL; + + if (copy_to_user(arg, &flags, sizeof(flags))) + return -EFAULT; + return 0; +} + +static int +efivarfs_ioc_setxflags(struct file *file, void __user *arg) +{ + struct inode *inode = file->f_mapping->host; + unsigned int flags; + unsigned int i_flags = 0; + int error; + + if (!inode_owner_or_capable(inode)) + return -EACCES; + + if (copy_from_user(&flags, arg, sizeof(flags))) + return -EFAULT; + + if (flags & ~FS_IMMUTABLE_FL) + return -EOPNOTSUPP; + + if (!capable(CAP_LINUX_IMMUTABLE)) + return -EPERM; + + if (flags & FS_IMMUTABLE_FL) + i_flags |= S_IMMUTABLE; + + + error = mnt_want_write_file(file); + if (error) + return error; + + inode_lock(inode); + inode_set_flags(inode, i_flags, S_IMMUTABLE); + inode_unlock(inode); + + mnt_drop_write_file(file); + + return 0; +} + +long +efivarfs_file_ioctl(struct file *file, unsigned int cmd, unsigned long p) +{ + void __user *arg = (void __user *)p; + + switch (cmd) { + case FS_IOC_GETFLAGS: + return efivarfs_ioc_getxflags(file, arg); + case FS_IOC_SETFLAGS: + return efivarfs_ioc_setxflags(file, arg); + } + + return -ENOTTY; +} + const struct file_operations efivarfs_file_operations = { .open = simple_open, .read = efivarfs_file_read, .write = efivarfs_file_write, .llseek = no_llseek, + .unlocked_ioctl = efivarfs_file_ioctl, }; diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c index 3381b9da9ee6..e2ab6d0497f2 100644 --- a/fs/efivarfs/inode.c +++ b/fs/efivarfs/inode.c @@ -15,7 +15,8 @@ #include "internal.h" struct inode *efivarfs_get_inode(struct super_block *sb, - const struct inode *dir, int mode, dev_t dev) + const struct inode *dir, int mode, + dev_t dev, bool is_removable) { struct inode *inode = new_inode(sb); @@ -23,6 +24,7 @@ struct inode *efivarfs_get_inode(struct super_block *sb, inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; + inode->i_flags = is_removable ? 0 : S_IMMUTABLE; switch (mode & S_IFMT) { case S_IFREG: inode->i_fop = &efivarfs_file_operations; @@ -102,22 +104,17 @@ static void efivarfs_hex_to_guid(const char *str, efi_guid_t *guid) static int efivarfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { - struct inode *inode; + struct inode *inode = NULL; struct efivar_entry *var; int namelen, i = 0, err = 0; + bool is_removable = false; if (!efivarfs_valid_name(dentry->d_name.name, dentry->d_name.len)) return -EINVAL; - inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0); - if (!inode) - return -ENOMEM; - var = kzalloc(sizeof(struct efivar_entry), GFP_KERNEL); - if (!var) { - err = -ENOMEM; - goto out; - } + if (!var) + return -ENOMEM; /* length of the variable name itself: remove GUID and separator */ namelen = dentry->d_name.len - EFI_VARIABLE_GUID_LEN - 1; @@ -125,6 +122,16 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry, efivarfs_hex_to_guid(dentry->d_name.name + namelen + 1, &var->var.VendorGuid); + if (efivar_variable_is_removable(var->var.VendorGuid, + dentry->d_name.name, namelen)) + is_removable = true; + + inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0, is_removable); + if (!inode) { + err = -ENOMEM; + goto out; + } + for (i = 0; i < namelen; i++) var->var.VariableName[i] = dentry->d_name.name[i]; @@ -138,7 +145,8 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry, out: if (err) { kfree(var); - iput(inode); + if (inode) + iput(inode); } return err; } diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h index b5ff16addb7c..b4505188e799 100644 --- a/fs/efivarfs/internal.h +++ b/fs/efivarfs/internal.h @@ -15,7 +15,8 @@ extern const struct file_operations efivarfs_file_operations; extern const struct inode_operations efivarfs_dir_inode_operations; extern bool efivarfs_valid_name(const char *str, int len); extern struct inode *efivarfs_get_inode(struct super_block *sb, - const struct inode *dir, int mode, dev_t dev); + const struct inode *dir, int mode, dev_t dev, + bool is_removable); extern struct list_head efivarfs_list; diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 8651ac28ec0d..dd029d13ea61 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -120,6 +120,7 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, char *name; int len; int err = -ENOMEM; + bool is_removable = false; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) @@ -137,13 +138,17 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, ucs2_as_utf8(name, entry->var.VariableName, len); + if (efivar_variable_is_removable(entry->var.VendorGuid, name, len)) + is_removable = true; + name[len] = '-'; efi_guid_to_str(&entry->var.VendorGuid, name + len + 1); name[len + EFI_VARIABLE_GUID_LEN+1] = '\0'; - inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0); + inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0, + is_removable); if (!inode) goto fail_name; @@ -199,7 +204,7 @@ static int efivarfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_d_op = &efivarfs_d_ops; sb->s_time_gran = 1; - inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0); + inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0, true); if (!inode) return -ENOMEM; inode->i_op = &efivarfs_dir_inode_operations; diff --git a/include/linux/efi.h b/include/linux/efi.h index 16ca611aabc8..47be3ad7d3e5 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1201,6 +1201,8 @@ struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid, bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data, unsigned long data_size); +bool efivar_variable_is_removable(efi_guid_t vendor, const char *name, + size_t len); extern struct work_struct efivar_work; void efivar_run_worker(void); diff --git a/tools/testing/selftests/efivarfs/efivarfs.sh b/tools/testing/selftests/efivarfs/efivarfs.sh index 77edcdcc016b..057278448515 100755 --- a/tools/testing/selftests/efivarfs/efivarfs.sh +++ b/tools/testing/selftests/efivarfs/efivarfs.sh @@ -88,7 +88,11 @@ test_delete() exit 1 fi - rm $file + rm $file 2>/dev/null + if [ $? -ne 0 ]; then + chattr -i $file + rm $file + fi if [ -e $file ]; then echo "$file couldn't be deleted" >&2 @@ -111,6 +115,7 @@ test_zero_size_delete() exit 1 fi + chattr -i $file printf "$attrs" > $file if [ -e $file ]; then @@ -141,7 +146,11 @@ test_valid_filenames() echo "$file could not be created" >&2 ret=1 else - rm $file + rm $file 2>/dev/null + if [ $? -ne 0 ]; then + chattr -i $file + rm $file + fi fi done @@ -174,7 +183,11 @@ test_invalid_filenames() if [ -e $file ]; then echo "Creating $file should have failed" >&2 - rm $file + rm $file 2>/dev/null + if [ $? -ne 0 ]; then + chattr -i $file + rm $file + fi ret=1 fi done diff --git a/tools/testing/selftests/efivarfs/open-unlink.c b/tools/testing/selftests/efivarfs/open-unlink.c index 8c0764407b3c..4af74f733036 100644 --- a/tools/testing/selftests/efivarfs/open-unlink.c +++ b/tools/testing/selftests/efivarfs/open-unlink.c @@ -1,10 +1,68 @@ +#include #include #include #include #include +#include #include #include #include +#include + +static int set_immutable(const char *path, int immutable) +{ + unsigned int flags; + int fd; + int rc; + int error; + + fd = open(path, O_RDONLY); + if (fd < 0) + return fd; + + rc = ioctl(fd, FS_IOC_GETFLAGS, &flags); + if (rc < 0) { + error = errno; + close(fd); + errno = error; + return rc; + } + + if (immutable) + flags |= FS_IMMUTABLE_FL; + else + flags &= ~FS_IMMUTABLE_FL; + + rc = ioctl(fd, FS_IOC_SETFLAGS, &flags); + error = errno; + close(fd); + errno = error; + return rc; +} + +static int get_immutable(const char *path) +{ + unsigned int flags; + int fd; + int rc; + int error; + + fd = open(path, O_RDONLY); + if (fd < 0) + return fd; + + rc = ioctl(fd, FS_IOC_GETFLAGS, &flags); + if (rc < 0) { + error = errno; + close(fd); + errno = error; + return rc; + } + close(fd); + if (flags & FS_IMMUTABLE_FL) + return 1; + return 0; +} int main(int argc, char **argv) { @@ -27,7 +85,7 @@ int main(int argc, char **argv) buf[4] = 0; /* create a test variable */ - fd = open(path, O_WRONLY | O_CREAT); + fd = open(path, O_WRONLY | O_CREAT, 0600); if (fd < 0) { perror("open(O_WRONLY)"); return EXIT_FAILURE; @@ -41,6 +99,18 @@ int main(int argc, char **argv) close(fd); + rc = get_immutable(path); + if (rc < 0) { + perror("ioctl(FS_IOC_GETFLAGS)"); + return EXIT_FAILURE; + } else if (rc) { + rc = set_immutable(path, 0); + if (rc < 0) { + perror("ioctl(FS_IOC_SETFLAGS)"); + return EXIT_FAILURE; + } + } + fd = open(path, O_RDONLY); if (fd < 0) { perror("open"); -- cgit v1.2.3 From 4a389810bc3cb0e73443104f0827e81e23cb1e12 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 11 Feb 2016 16:13:14 -0800 Subject: kernel/locking/lockdep.c: convert hash tables to hlists Mike said: : CONFIG_UBSAN_ALIGNMENT breaks x86-64 kernel with lockdep enabled, i. e : kernel with CONFIG_UBSAN_ALIGNMENT fails to load without even any error : message. : : The problem is that ubsan callbacks use spinlocks and might be called : before lockdep is initialized. Particularly this line in the : reserve_ebda_region function causes problem: : : lowmem = *(unsigned short *)__va(BIOS_LOWMEM_KILOBYTES); : : If i put lockdep_init() before reserve_ebda_region call in : x86_64_start_reservations kernel loads well. Fix this ordering issue permanently: change lockdep so that it uses hlists for the hash tables. Unlike a list_head, an hlist_head is in its initialized state when it is all-zeroes, so lockdep is ready for operation immediately upon boot - lockdep_init() need not have run. The patch will also save some memory. lockdep_init() and lockdep_initialized can be done away with now - a 4.6 patch has been prepared to do this. Reported-by: Mike Krinkin Suggested-by: Mike Krinkin Cc: Andrey Ryabinin Cc: Ingo Molnar Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/lockdep.h | 4 ++-- kernel/locking/lockdep.c | 42 +++++++++++++++++++----------------------- 2 files changed, 21 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index c57e424d914b..4dca42fd32f5 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -66,7 +66,7 @@ struct lock_class { /* * class-hash: */ - struct list_head hash_entry; + struct hlist_node hash_entry; /* * global list of all lock-classes: @@ -199,7 +199,7 @@ struct lock_chain { u8 irq_context; u8 depth; u16 base; - struct list_head entry; + struct hlist_node entry; u64 chain_key; }; diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 60ace56618f6..7537e568dabe 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -292,7 +292,7 @@ LIST_HEAD(all_lock_classes); #define __classhashfn(key) hash_long((unsigned long)key, CLASSHASH_BITS) #define classhashentry(key) (classhash_table + __classhashfn((key))) -static struct list_head classhash_table[CLASSHASH_SIZE]; +static struct hlist_head classhash_table[CLASSHASH_SIZE]; /* * We put the lock dependency chains into a hash-table as well, to cache @@ -303,7 +303,7 @@ static struct list_head classhash_table[CLASSHASH_SIZE]; #define __chainhashfn(chain) hash_long(chain, CHAINHASH_BITS) #define chainhashentry(chain) (chainhash_table + __chainhashfn((chain))) -static struct list_head chainhash_table[CHAINHASH_SIZE]; +static struct hlist_head chainhash_table[CHAINHASH_SIZE]; /* * The hash key of the lock dependency chains is a hash itself too: @@ -666,7 +666,7 @@ static inline struct lock_class * look_up_lock_class(struct lockdep_map *lock, unsigned int subclass) { struct lockdep_subclass_key *key; - struct list_head *hash_head; + struct hlist_head *hash_head; struct lock_class *class; #ifdef CONFIG_DEBUG_LOCKDEP @@ -719,7 +719,7 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass) if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) return NULL; - list_for_each_entry_rcu(class, hash_head, hash_entry) { + hlist_for_each_entry_rcu(class, hash_head, hash_entry) { if (class->key == key) { /* * Huh! same key, different name? Did someone trample @@ -742,7 +742,7 @@ static inline struct lock_class * register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) { struct lockdep_subclass_key *key; - struct list_head *hash_head; + struct hlist_head *hash_head; struct lock_class *class; DEBUG_LOCKS_WARN_ON(!irqs_disabled()); @@ -774,7 +774,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) * We have to do the hash-walk again, to avoid races * with another CPU: */ - list_for_each_entry_rcu(class, hash_head, hash_entry) { + hlist_for_each_entry_rcu(class, hash_head, hash_entry) { if (class->key == key) goto out_unlock_set; } @@ -805,7 +805,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) * We use RCU's safe list-add method to make * parallel walking of the hash-list safe: */ - list_add_tail_rcu(&class->hash_entry, hash_head); + hlist_add_head_rcu(&class->hash_entry, hash_head); /* * Add it to the global list of classes: */ @@ -2017,7 +2017,7 @@ static inline int lookup_chain_cache(struct task_struct *curr, u64 chain_key) { struct lock_class *class = hlock_class(hlock); - struct list_head *hash_head = chainhashentry(chain_key); + struct hlist_head *hash_head = chainhashentry(chain_key); struct lock_chain *chain; struct held_lock *hlock_curr; int i, j; @@ -2033,7 +2033,7 @@ static inline int lookup_chain_cache(struct task_struct *curr, * We can walk it lock-free, because entries only get added * to the hash: */ - list_for_each_entry_rcu(chain, hash_head, entry) { + hlist_for_each_entry_rcu(chain, hash_head, entry) { if (chain->chain_key == chain_key) { cache_hit: debug_atomic_inc(chain_lookup_hits); @@ -2057,7 +2057,7 @@ cache_hit: /* * We have to walk the chain again locked - to avoid duplicates: */ - list_for_each_entry(chain, hash_head, entry) { + hlist_for_each_entry(chain, hash_head, entry) { if (chain->chain_key == chain_key) { graph_unlock(); goto cache_hit; @@ -2091,7 +2091,7 @@ cache_hit: } chain_hlocks[chain->base + j] = class - lock_classes; } - list_add_tail_rcu(&chain->entry, hash_head); + hlist_add_head_rcu(&chain->entry, hash_head); debug_atomic_inc(chain_lookup_misses); inc_chains(); @@ -3875,7 +3875,7 @@ void lockdep_reset(void) nr_process_chains = 0; debug_locks = 1; for (i = 0; i < CHAINHASH_SIZE; i++) - INIT_LIST_HEAD(chainhash_table + i); + INIT_HLIST_HEAD(chainhash_table + i); raw_local_irq_restore(flags); } @@ -3894,7 +3894,7 @@ static void zap_class(struct lock_class *class) /* * Unhash the class and remove it from the all_lock_classes list: */ - list_del_rcu(&class->hash_entry); + hlist_del_rcu(&class->hash_entry); list_del_rcu(&class->lock_entry); RCU_INIT_POINTER(class->key, NULL); @@ -3917,7 +3917,7 @@ static inline int within(const void *addr, void *start, unsigned long size) void lockdep_free_key_range(void *start, unsigned long size) { struct lock_class *class; - struct list_head *head; + struct hlist_head *head; unsigned long flags; int i; int locked; @@ -3930,9 +3930,7 @@ void lockdep_free_key_range(void *start, unsigned long size) */ for (i = 0; i < CLASSHASH_SIZE; i++) { head = classhash_table + i; - if (list_empty(head)) - continue; - list_for_each_entry_rcu(class, head, hash_entry) { + hlist_for_each_entry_rcu(class, head, hash_entry) { if (within(class->key, start, size)) zap_class(class); else if (within(class->name, start, size)) @@ -3962,7 +3960,7 @@ void lockdep_free_key_range(void *start, unsigned long size) void lockdep_reset_lock(struct lockdep_map *lock) { struct lock_class *class; - struct list_head *head; + struct hlist_head *head; unsigned long flags; int i, j; int locked; @@ -3987,9 +3985,7 @@ void lockdep_reset_lock(struct lockdep_map *lock) locked = graph_lock(); for (i = 0; i < CLASSHASH_SIZE; i++) { head = classhash_table + i; - if (list_empty(head)) - continue; - list_for_each_entry_rcu(class, head, hash_entry) { + hlist_for_each_entry_rcu(class, head, hash_entry) { int match = 0; for (j = 0; j < NR_LOCKDEP_CACHING_CLASSES; j++) @@ -4027,10 +4023,10 @@ void lockdep_init(void) return; for (i = 0; i < CLASSHASH_SIZE; i++) - INIT_LIST_HEAD(classhash_table + i); + INIT_HLIST_HEAD(classhash_table + i); for (i = 0; i < CHAINHASH_SIZE; i++) - INIT_LIST_HEAD(chainhash_table + i); + INIT_HLIST_HEAD(chainhash_table + i); lockdep_initialized = 1; } -- cgit v1.2.3 From db78c22230d0bcc8b27b81f05b39f104f08232c5 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 11 Feb 2016 16:13:17 -0800 Subject: mm: fix pfn_t vs highmem The pfn_t type uses an unsigned long to store a pfn + flags value. On a 64-bit platform the upper 12 bits of an unsigned long are never used for storing the value of a pfn. However, this is not true on highmem platforms, all 32-bits of a pfn value are used to address a 44-bit physical address space. A pfn_t needs to store a 64-bit value. Link: https://bugzilla.kernel.org/show_bug.cgi?id=112211 Fixes: 01c8f1c44b83 ("mm, dax, gpu: convert vm_insert_mixed to pfn_t") Signed-off-by: Dan Williams Reported-by: Stuart Foster Reported-by: Julian Margetson Tested-by: Julian Margetson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pfn.h | 2 +- include/linux/pfn_t.h | 19 +++++++++---------- kernel/memremap.c | 2 +- 3 files changed, 11 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pfn.h b/include/linux/pfn.h index 2d8e49711b63..1132953235c0 100644 --- a/include/linux/pfn.h +++ b/include/linux/pfn.h @@ -10,7 +10,7 @@ * backing is indicated by flags in the high bits of the value. */ typedef struct { - unsigned long val; + u64 val; } pfn_t; #endif diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h index 37448ab5fb5c..94994810c7c0 100644 --- a/include/linux/pfn_t.h +++ b/include/linux/pfn_t.h @@ -9,14 +9,13 @@ * PFN_DEV - pfn is not covered by system memmap by default * PFN_MAP - pfn has a dynamic page mapping established by a device driver */ -#define PFN_FLAGS_MASK (((unsigned long) ~PAGE_MASK) \ - << (BITS_PER_LONG - PAGE_SHIFT)) -#define PFN_SG_CHAIN (1UL << (BITS_PER_LONG - 1)) -#define PFN_SG_LAST (1UL << (BITS_PER_LONG - 2)) -#define PFN_DEV (1UL << (BITS_PER_LONG - 3)) -#define PFN_MAP (1UL << (BITS_PER_LONG - 4)) - -static inline pfn_t __pfn_to_pfn_t(unsigned long pfn, unsigned long flags) +#define PFN_FLAGS_MASK (((u64) ~PAGE_MASK) << (BITS_PER_LONG_LONG - PAGE_SHIFT)) +#define PFN_SG_CHAIN (1ULL << (BITS_PER_LONG_LONG - 1)) +#define PFN_SG_LAST (1ULL << (BITS_PER_LONG_LONG - 2)) +#define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3)) +#define PFN_MAP (1ULL << (BITS_PER_LONG_LONG - 4)) + +static inline pfn_t __pfn_to_pfn_t(unsigned long pfn, u64 flags) { pfn_t pfn_t = { .val = pfn | (flags & PFN_FLAGS_MASK), }; @@ -29,7 +28,7 @@ static inline pfn_t pfn_to_pfn_t(unsigned long pfn) return __pfn_to_pfn_t(pfn, 0); } -extern pfn_t phys_to_pfn_t(phys_addr_t addr, unsigned long flags); +extern pfn_t phys_to_pfn_t(phys_addr_t addr, u64 flags); static inline bool pfn_t_has_page(pfn_t pfn) { @@ -87,7 +86,7 @@ static inline pmd_t pfn_t_pmd(pfn_t pfn, pgprot_t pgprot) #ifdef __HAVE_ARCH_PTE_DEVMAP static inline bool pfn_t_devmap(pfn_t pfn) { - const unsigned long flags = PFN_DEV|PFN_MAP; + const u64 flags = PFN_DEV|PFN_MAP; return (pfn.val & flags) == flags; } diff --git a/kernel/memremap.c b/kernel/memremap.c index 70ee3775de24..2c468dea60bc 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -150,7 +150,7 @@ void devm_memunmap(struct device *dev, void *addr) } EXPORT_SYMBOL(devm_memunmap); -pfn_t phys_to_pfn_t(phys_addr_t addr, unsigned long flags) +pfn_t phys_to_pfn_t(phys_addr_t addr, u64 flags) { return __pfn_to_pfn_t(addr >> PAGE_SHIFT, flags); } -- cgit v1.2.3 From 46924008273ed03bd11dbb32136e3da4cfe056e1 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Mon, 15 Feb 2016 12:42:38 +0000 Subject: iommu/vt-d: Clear PPR bit to ensure we get more page request interrupts According to the VT-d specification we need to clear the PPR bit in the Page Request Status register when handling page requests, or the hardware won't generate any more interrupts. This wasn't actually necessary on SKL/KBL (which may well be the subject of a hardware erratum, although it's harmless enough). But other implementations do appear to get it right, and we only ever get one interrupt unless we clear the PPR bit. Reported-by: CQ Tang Signed-off-by: David Woodhouse Cc: stable@vger.kernel.org --- drivers/iommu/intel-svm.c | 4 ++++ include/linux/intel-iommu.h | 3 +++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c index 97a818992d6d..d9939fa9b588 100644 --- a/drivers/iommu/intel-svm.c +++ b/drivers/iommu/intel-svm.c @@ -524,6 +524,10 @@ static irqreturn_t prq_event_thread(int irq, void *d) struct intel_svm *svm = NULL; int head, tail, handled = 0; + /* Clear PPR bit before reading head/tail registers, to + * ensure that we get a new interrupt if needed. */ + writel(DMA_PRS_PPR, iommu->reg + DMAR_PRS_REG); + tail = dmar_readq(iommu->reg + DMAR_PQT_REG) & PRQ_RING_MASK; head = dmar_readq(iommu->reg + DMAR_PQH_REG) & PRQ_RING_MASK; while (head != tail) { diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 821273ca4873..2d9b650047a5 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -235,6 +235,9 @@ static inline void dmar_writeq(void __iomem *addr, u64 val) /* low 64 bit */ #define dma_frcd_page_addr(d) (d & (((u64)-1) << PAGE_SHIFT)) +/* PRS_REG */ +#define DMA_PRS_PPR ((u32)1) + #define IOMMU_WAIT_OP(iommu, offset, op, cond, sts) \ do { \ cycles_t start_time = get_cycles(); \ -- cgit v1.2.3 From f37755490fe9bf76f6ba1d8c6591745d3574a6a6 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Mon, 15 Feb 2016 12:36:14 -0500 Subject: tracepoints: Do not trace when cpu is offline The tracepoint infrastructure uses RCU sched protection to enable and disable tracepoints safely. There are some instances where tracepoints are used in infrastructure code (like kfree()) that get called after a CPU is going offline, and perhaps when it is coming back online but hasn't been registered yet. This can probuce the following warning: [ INFO: suspicious RCU usage. ] 4.4.0-00006-g0fe53e8-dirty #34 Tainted: G S ------------------------------- include/trace/events/kmem.h:141 suspicious rcu_dereference_check() usage! other info that might help us debug this: RCU used illegally from offline CPU! rcu_scheduler_active = 1, debug_locks = 1 no locks held by swapper/8/0. stack backtrace: CPU: 8 PID: 0 Comm: swapper/8 Tainted: G S 4.4.0-00006-g0fe53e8-dirty #34 Call Trace: [c0000005b76c78d0] [c0000000008b9540] .dump_stack+0x98/0xd4 (unreliable) [c0000005b76c7950] [c00000000010c898] .lockdep_rcu_suspicious+0x108/0x170 [c0000005b76c79e0] [c00000000029adc0] .kfree+0x390/0x440 [c0000005b76c7a80] [c000000000055f74] .destroy_context+0x44/0x100 [c0000005b76c7b00] [c0000000000934a0] .__mmdrop+0x60/0x150 [c0000005b76c7b90] [c0000000000e3ff0] .idle_task_exit+0x130/0x140 [c0000005b76c7c20] [c000000000075804] .pseries_mach_cpu_die+0x64/0x310 [c0000005b76c7cd0] [c000000000043e7c] .cpu_die+0x3c/0x60 [c0000005b76c7d40] [c0000000000188d8] .arch_cpu_idle_dead+0x28/0x40 [c0000005b76c7db0] [c000000000101e6c] .cpu_startup_entry+0x50c/0x560 [c0000005b76c7ed0] [c000000000043bd8] .start_secondary+0x328/0x360 [c0000005b76c7f90] [c000000000008a6c] start_secondary_prolog+0x10/0x14 This warning is not a false positive either. RCU is not protecting code that is being executed while the CPU is offline. Instead of playing "whack-a-mole(TM)" and adding conditional statements to the tracepoints we find that are used in this instance, simply add a cpu_online() test to the tracepoint code where the tracepoint will be ignored if the CPU is offline. Use of raw_smp_processor_id() is fine, as there should never be a case where the tracepoint code goes from running on a CPU that is online and suddenly gets migrated to a CPU that is offline. Link: http://lkml.kernel.org/r/1455387773-4245-1-git-send-email-kda@linux-powerpc.org Reported-by: Denis Kirjanov Fixes: 97e1c18e8d17b ("tracing: Kernel Tracepoints") Cc: stable@vger.kernel.org # v2.6.28+ Signed-off-by: Steven Rostedt --- include/linux/tracepoint.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index acd522a91539..acfdbf353a0b 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -14,8 +14,10 @@ * See the file COPYING for more details. */ +#include #include #include +#include #include #include @@ -132,6 +134,9 @@ extern void syscall_unregfunc(void); void *it_func; \ void *__data; \ \ + if (!cpu_online(raw_smp_processor_id())) \ + return; \ + \ if (!(cond)) \ return; \ prercu; \ -- cgit v1.2.3 From b33c8ff4431a343561e2319f17c14286f2aa52e2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 12 Feb 2016 22:26:42 +0100 Subject: tracing: Fix freak link error caused by branch tracer In my randconfig tests, I came across a bug that involves several components: * gcc-4.9 through at least 5.3 * CONFIG_GCOV_PROFILE_ALL enabling -fprofile-arcs for all files * CONFIG_PROFILE_ALL_BRANCHES overriding every if() * The optimized implementation of do_div() that tries to replace a library call with an division by multiplication * code in drivers/media/dvb-frontends/zl10353.c doing u32 adc_clock = 450560; /* 45.056 MHz */ if (state->config.adc_clock) adc_clock = state->config.adc_clock; do_div(value, adc_clock); In this case, gcc fails to determine whether the divisor in do_div() is __builtin_constant_p(). In particular, it concludes that __builtin_constant_p(adc_clock) is false, while __builtin_constant_p(!!adc_clock) is true. That in turn throws off the logic in do_div() that also uses __builtin_constant_p(), and instead of picking either the constant- optimized division, and the code in ilog2() that uses __builtin_constant_p() to figure out whether it knows the answer at compile time. The result is a link error from failing to find multiple symbols that should never have been called based on the __builtin_constant_p(): dvb-frontends/zl10353.c:138: undefined reference to `____ilog2_NaN' dvb-frontends/zl10353.c:138: undefined reference to `__aeabi_uldivmod' ERROR: "____ilog2_NaN" [drivers/media/dvb-frontends/zl10353.ko] undefined! ERROR: "__aeabi_uldivmod" [drivers/media/dvb-frontends/zl10353.ko] undefined! This patch avoids the problem by changing __trace_if() to check whether the condition is known at compile-time to be nonzero, rather than checking whether it is actually a constant. I see this one link error in roughly one out of 1600 randconfig builds on ARM, and the patch fixes all known instances. Link: http://lkml.kernel.org/r/1455312410-1058841-1-git-send-email-arnd@arndb.de Acked-by: Nicolas Pitre Fixes: ab3c9c686e22 ("branch tracer, intel-iommu: fix build with CONFIG_BRANCH_TRACER=y") Cc: stable@vger.kernel.org # v2.6.30+ Signed-off-by: Arnd Bergmann Signed-off-by: Steven Rostedt --- include/linux/compiler.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 00b042c49ccd..48f5aab117ae 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -144,7 +144,7 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); */ #define if(cond, ...) __trace_if( (cond , ## __VA_ARGS__) ) #define __trace_if(cond) \ - if (__builtin_constant_p((cond)) ? !!(cond) : \ + if (__builtin_constant_p(!!(cond)) ? !!(cond) : \ ({ \ int ______r; \ static struct ftrace_branch_data \ -- cgit v1.2.3 From b4ff3a36d3e409d365a09b6b783ff895063ff4ef Mon Sep 17 00:00:00 2001 From: Matan Barak Date: Tue, 9 Feb 2016 14:57:42 +0200 Subject: net/mlx5: Use offset based reserved field names in the IFC header file mlx5_ifc.h is a header file representing the API and ABI between the driver to the firmware and hardware. This file is used from both the mlx5_ib and mlx5_core drivers. Previously, this file used incrementing counter to indicate reserved fields, for example: struct mlx5_ifc_odp_per_transport_service_cap_bits { u8 send[0x1]; u8 receive[0x1]; u8 write[0x1]; u8 read[0x1]; u8 reserved_0[0x1]; u8 srq_receive[0x1]; u8 reserved_1[0x1a]; }; If one developer implements through net-next feature A that uses reserved_0, they replace it with featureA and renames reserved_1 to reserved_0. In the same kernel cycle, a 2nd developer could implement feature B through the rdma tree, that uses reserved_1 and split it to featureB and a smaller reserved_1 field. This will cause a conflict when the two trees are merged. The source of this conflict is that the 1st developer changed *all* reserved fields. As Linus suggested, we change the layout of structs to: struct mlx5_ifc_odp_per_transport_service_cap_bits { u8 send[0x1]; u8 receive[0x1]; u8 write[0x1]; u8 read[0x1]; u8 reserved_at_4[0x1]; u8 srq_receive[0x1]; u8 reserved_at_6[0x1a]; }; This makes the conflicts much more rare and preserves the locality of changes. Signed-off-by: Matan Barak Signed-off-by: Alaa Hleihel Reported-by: Linus Torvalds Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/mlx5_ifc.h | 2968 ++++++++++++++++++++--------------------- 1 file changed, 1484 insertions(+), 1484 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 231ab6bcea76..51f1e540fc2b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -207,15 +207,15 @@ struct mlx5_ifc_flow_table_fields_supported_bits { u8 outer_dmac[0x1]; u8 outer_smac[0x1]; u8 outer_ether_type[0x1]; - u8 reserved_0[0x1]; + u8 reserved_at_3[0x1]; u8 outer_first_prio[0x1]; u8 outer_first_cfi[0x1]; u8 outer_first_vid[0x1]; - u8 reserved_1[0x1]; + u8 reserved_at_7[0x1]; u8 outer_second_prio[0x1]; u8 outer_second_cfi[0x1]; u8 outer_second_vid[0x1]; - u8 reserved_2[0x1]; + u8 reserved_at_b[0x1]; u8 outer_sip[0x1]; u8 outer_dip[0x1]; u8 outer_frag[0x1]; @@ -230,21 +230,21 @@ struct mlx5_ifc_flow_table_fields_supported_bits { u8 outer_gre_protocol[0x1]; u8 outer_gre_key[0x1]; u8 outer_vxlan_vni[0x1]; - u8 reserved_3[0x5]; + u8 reserved_at_1a[0x5]; u8 source_eswitch_port[0x1]; u8 inner_dmac[0x1]; u8 inner_smac[0x1]; u8 inner_ether_type[0x1]; - u8 reserved_4[0x1]; + u8 reserved_at_23[0x1]; u8 inner_first_prio[0x1]; u8 inner_first_cfi[0x1]; u8 inner_first_vid[0x1]; - u8 reserved_5[0x1]; + u8 reserved_at_27[0x1]; u8 inner_second_prio[0x1]; u8 inner_second_cfi[0x1]; u8 inner_second_vid[0x1]; - u8 reserved_6[0x1]; + u8 reserved_at_2b[0x1]; u8 inner_sip[0x1]; u8 inner_dip[0x1]; u8 inner_frag[0x1]; @@ -256,37 +256,37 @@ struct mlx5_ifc_flow_table_fields_supported_bits { u8 inner_tcp_sport[0x1]; u8 inner_tcp_dport[0x1]; u8 inner_tcp_flags[0x1]; - u8 reserved_7[0x9]; + u8 reserved_at_37[0x9]; - u8 reserved_8[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_flow_table_prop_layout_bits { u8 ft_support[0x1]; - u8 reserved_0[0x2]; + u8 reserved_at_1[0x2]; u8 flow_modify_en[0x1]; u8 modify_root[0x1]; u8 identified_miss_table_mode[0x1]; u8 flow_table_modify[0x1]; - u8 reserved_1[0x19]; + u8 reserved_at_7[0x19]; - u8 reserved_2[0x2]; + u8 reserved_at_20[0x2]; u8 log_max_ft_size[0x6]; - u8 reserved_3[0x10]; + u8 reserved_at_28[0x10]; u8 max_ft_level[0x8]; - u8 reserved_4[0x20]; + u8 reserved_at_40[0x20]; - u8 reserved_5[0x18]; + u8 reserved_at_60[0x18]; u8 log_max_ft_num[0x8]; - u8 reserved_6[0x18]; + u8 reserved_at_80[0x18]; u8 log_max_destination[0x8]; - u8 reserved_7[0x18]; + u8 reserved_at_a0[0x18]; u8 log_max_flow[0x8]; - u8 reserved_8[0x40]; + u8 reserved_at_c0[0x40]; struct mlx5_ifc_flow_table_fields_supported_bits ft_field_support; @@ -298,13 +298,13 @@ struct mlx5_ifc_odp_per_transport_service_cap_bits { u8 receive[0x1]; u8 write[0x1]; u8 read[0x1]; - u8 reserved_0[0x1]; + u8 reserved_at_4[0x1]; u8 srq_receive[0x1]; - u8 reserved_1[0x1a]; + u8 reserved_at_6[0x1a]; }; struct mlx5_ifc_ipv4_layout_bits { - u8 reserved_0[0x60]; + u8 reserved_at_0[0x60]; u8 ipv4[0x20]; }; @@ -316,7 +316,7 @@ struct mlx5_ifc_ipv6_layout_bits { union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits { struct mlx5_ifc_ipv6_layout_bits ipv6_layout; struct mlx5_ifc_ipv4_layout_bits ipv4_layout; - u8 reserved_0[0x80]; + u8 reserved_at_0[0x80]; }; struct mlx5_ifc_fte_match_set_lyr_2_4_bits { @@ -336,15 +336,15 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits { u8 ip_dscp[0x6]; u8 ip_ecn[0x2]; u8 vlan_tag[0x1]; - u8 reserved_0[0x1]; + u8 reserved_at_91[0x1]; u8 frag[0x1]; - u8 reserved_1[0x4]; + u8 reserved_at_93[0x4]; u8 tcp_flags[0x9]; u8 tcp_sport[0x10]; u8 tcp_dport[0x10]; - u8 reserved_2[0x20]; + u8 reserved_at_c0[0x20]; u8 udp_sport[0x10]; u8 udp_dport[0x10]; @@ -355,9 +355,9 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits { }; struct mlx5_ifc_fte_match_set_misc_bits { - u8 reserved_0[0x20]; + u8 reserved_at_0[0x20]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 source_port[0x10]; u8 outer_second_prio[0x3]; @@ -369,31 +369,31 @@ struct mlx5_ifc_fte_match_set_misc_bits { u8 outer_second_vlan_tag[0x1]; u8 inner_second_vlan_tag[0x1]; - u8 reserved_2[0xe]; + u8 reserved_at_62[0xe]; u8 gre_protocol[0x10]; u8 gre_key_h[0x18]; u8 gre_key_l[0x8]; u8 vxlan_vni[0x18]; - u8 reserved_3[0x8]; + u8 reserved_at_b8[0x8]; - u8 reserved_4[0x20]; + u8 reserved_at_c0[0x20]; - u8 reserved_5[0xc]; + u8 reserved_at_e0[0xc]; u8 outer_ipv6_flow_label[0x14]; - u8 reserved_6[0xc]; + u8 reserved_at_100[0xc]; u8 inner_ipv6_flow_label[0x14]; - u8 reserved_7[0xe0]; + u8 reserved_at_120[0xe0]; }; struct mlx5_ifc_cmd_pas_bits { u8 pa_h[0x20]; u8 pa_l[0x14]; - u8 reserved_0[0xc]; + u8 reserved_at_34[0xc]; }; struct mlx5_ifc_uint64_bits { @@ -418,31 +418,31 @@ enum { struct mlx5_ifc_ads_bits { u8 fl[0x1]; u8 free_ar[0x1]; - u8 reserved_0[0xe]; + u8 reserved_at_2[0xe]; u8 pkey_index[0x10]; - u8 reserved_1[0x8]; + u8 reserved_at_20[0x8]; u8 grh[0x1]; u8 mlid[0x7]; u8 rlid[0x10]; u8 ack_timeout[0x5]; - u8 reserved_2[0x3]; + u8 reserved_at_45[0x3]; u8 src_addr_index[0x8]; - u8 reserved_3[0x4]; + u8 reserved_at_50[0x4]; u8 stat_rate[0x4]; u8 hop_limit[0x8]; - u8 reserved_4[0x4]; + u8 reserved_at_60[0x4]; u8 tclass[0x8]; u8 flow_label[0x14]; u8 rgid_rip[16][0x8]; - u8 reserved_5[0x4]; + u8 reserved_at_100[0x4]; u8 f_dscp[0x1]; u8 f_ecn[0x1]; - u8 reserved_6[0x1]; + u8 reserved_at_106[0x1]; u8 f_eth_prio[0x1]; u8 ecn[0x2]; u8 dscp[0x6]; @@ -458,25 +458,25 @@ struct mlx5_ifc_ads_bits { }; struct mlx5_ifc_flow_table_nic_cap_bits { - u8 reserved_0[0x200]; + u8 reserved_at_0[0x200]; struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive; - u8 reserved_1[0x200]; + u8 reserved_at_400[0x200]; struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive_sniffer; struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_transmit; - u8 reserved_2[0x200]; + u8 reserved_at_a00[0x200]; struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_transmit_sniffer; - u8 reserved_3[0x7200]; + u8 reserved_at_e00[0x7200]; }; struct mlx5_ifc_flow_table_eswitch_cap_bits { - u8 reserved_0[0x200]; + u8 reserved_at_0[0x200]; struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_esw_fdb; @@ -484,7 +484,7 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits { struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_esw_acl_egress; - u8 reserved_1[0x7800]; + u8 reserved_at_800[0x7800]; }; struct mlx5_ifc_e_switch_cap_bits { @@ -493,9 +493,9 @@ struct mlx5_ifc_e_switch_cap_bits { u8 vport_svlan_insert[0x1]; u8 vport_cvlan_insert_if_not_exist[0x1]; u8 vport_cvlan_insert_overwrite[0x1]; - u8 reserved_0[0x1b]; + u8 reserved_at_5[0x1b]; - u8 reserved_1[0x7e0]; + u8 reserved_at_20[0x7e0]; }; struct mlx5_ifc_per_protocol_networking_offload_caps_bits { @@ -504,51 +504,51 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 lro_cap[0x1]; u8 lro_psh_flag[0x1]; u8 lro_time_stamp[0x1]; - u8 reserved_0[0x3]; + u8 reserved_at_5[0x3]; u8 self_lb_en_modifiable[0x1]; - u8 reserved_1[0x2]; + u8 reserved_at_9[0x2]; u8 max_lso_cap[0x5]; - u8 reserved_2[0x4]; + u8 reserved_at_10[0x4]; u8 rss_ind_tbl_cap[0x4]; - u8 reserved_3[0x3]; + u8 reserved_at_18[0x3]; u8 tunnel_lso_const_out_ip_id[0x1]; - u8 reserved_4[0x2]; + u8 reserved_at_1c[0x2]; u8 tunnel_statless_gre[0x1]; u8 tunnel_stateless_vxlan[0x1]; - u8 reserved_5[0x20]; + u8 reserved_at_20[0x20]; - u8 reserved_6[0x10]; + u8 reserved_at_40[0x10]; u8 lro_min_mss_size[0x10]; - u8 reserved_7[0x120]; + u8 reserved_at_60[0x120]; u8 lro_timer_supported_periods[4][0x20]; - u8 reserved_8[0x600]; + u8 reserved_at_200[0x600]; }; struct mlx5_ifc_roce_cap_bits { u8 roce_apm[0x1]; - u8 reserved_0[0x1f]; + u8 reserved_at_1[0x1f]; - u8 reserved_1[0x60]; + u8 reserved_at_20[0x60]; - u8 reserved_2[0xc]; + u8 reserved_at_80[0xc]; u8 l3_type[0x4]; - u8 reserved_3[0x8]; + u8 reserved_at_90[0x8]; u8 roce_version[0x8]; - u8 reserved_4[0x10]; + u8 reserved_at_a0[0x10]; u8 r_roce_dest_udp_port[0x10]; u8 r_roce_max_src_udp_port[0x10]; u8 r_roce_min_src_udp_port[0x10]; - u8 reserved_5[0x10]; + u8 reserved_at_e0[0x10]; u8 roce_address_table_size[0x10]; - u8 reserved_6[0x700]; + u8 reserved_at_100[0x700]; }; enum { @@ -576,35 +576,35 @@ enum { }; struct mlx5_ifc_atomic_caps_bits { - u8 reserved_0[0x40]; + u8 reserved_at_0[0x40]; u8 atomic_req_8B_endianess_mode[0x2]; - u8 reserved_1[0x4]; + u8 reserved_at_42[0x4]; u8 supported_atomic_req_8B_endianess_mode_1[0x1]; - u8 reserved_2[0x19]; + u8 reserved_at_47[0x19]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; - u8 reserved_4[0x10]; + u8 reserved_at_80[0x10]; u8 atomic_operations[0x10]; - u8 reserved_5[0x10]; + u8 reserved_at_a0[0x10]; u8 atomic_size_qp[0x10]; - u8 reserved_6[0x10]; + u8 reserved_at_c0[0x10]; u8 atomic_size_dc[0x10]; - u8 reserved_7[0x720]; + u8 reserved_at_e0[0x720]; }; struct mlx5_ifc_odp_cap_bits { - u8 reserved_0[0x40]; + u8 reserved_at_0[0x40]; u8 sig[0x1]; - u8 reserved_1[0x1f]; + u8 reserved_at_41[0x1f]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; struct mlx5_ifc_odp_per_transport_service_cap_bits rc_odp_caps; @@ -612,7 +612,7 @@ struct mlx5_ifc_odp_cap_bits { struct mlx5_ifc_odp_per_transport_service_cap_bits ud_odp_caps; - u8 reserved_3[0x720]; + u8 reserved_at_e0[0x720]; }; enum { @@ -660,55 +660,55 @@ enum { }; struct mlx5_ifc_cmd_hca_cap_bits { - u8 reserved_0[0x80]; + u8 reserved_at_0[0x80]; u8 log_max_srq_sz[0x8]; u8 log_max_qp_sz[0x8]; - u8 reserved_1[0xb]; + u8 reserved_at_90[0xb]; u8 log_max_qp[0x5]; - u8 reserved_2[0xb]; + u8 reserved_at_a0[0xb]; u8 log_max_srq[0x5]; - u8 reserved_3[0x10]; + u8 reserved_at_b0[0x10]; - u8 reserved_4[0x8]; + u8 reserved_at_c0[0x8]; u8 log_max_cq_sz[0x8]; - u8 reserved_5[0xb]; + u8 reserved_at_d0[0xb]; u8 log_max_cq[0x5]; u8 log_max_eq_sz[0x8]; - u8 reserved_6[0x2]; + u8 reserved_at_e8[0x2]; u8 log_max_mkey[0x6]; - u8 reserved_7[0xc]; + u8 reserved_at_f0[0xc]; u8 log_max_eq[0x4]; u8 max_indirection[0x8]; - u8 reserved_8[0x1]; + u8 reserved_at_108[0x1]; u8 log_max_mrw_sz[0x7]; - u8 reserved_9[0x2]; + u8 reserved_at_110[0x2]; u8 log_max_bsf_list_size[0x6]; - u8 reserved_10[0x2]; + u8 reserved_at_118[0x2]; u8 log_max_klm_list_size[0x6]; - u8 reserved_11[0xa]; + u8 reserved_at_120[0xa]; u8 log_max_ra_req_dc[0x6]; - u8 reserved_12[0xa]; + u8 reserved_at_130[0xa]; u8 log_max_ra_res_dc[0x6]; - u8 reserved_13[0xa]; + u8 reserved_at_140[0xa]; u8 log_max_ra_req_qp[0x6]; - u8 reserved_14[0xa]; + u8 reserved_at_150[0xa]; u8 log_max_ra_res_qp[0x6]; u8 pad_cap[0x1]; u8 cc_query_allowed[0x1]; u8 cc_modify_allowed[0x1]; - u8 reserved_15[0xd]; + u8 reserved_at_163[0xd]; u8 gid_table_size[0x10]; u8 out_of_seq_cnt[0x1]; u8 vport_counters[0x1]; - u8 reserved_16[0x4]; + u8 reserved_at_182[0x4]; u8 max_qp_cnt[0xa]; u8 pkey_table_size[0x10]; @@ -716,158 +716,158 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 vhca_group_manager[0x1]; u8 ib_virt[0x1]; u8 eth_virt[0x1]; - u8 reserved_17[0x1]; + u8 reserved_at_1a4[0x1]; u8 ets[0x1]; u8 nic_flow_table[0x1]; u8 eswitch_flow_table[0x1]; u8 early_vf_enable; - u8 reserved_18[0x2]; + u8 reserved_at_1a8[0x2]; u8 local_ca_ack_delay[0x5]; - u8 reserved_19[0x6]; + u8 reserved_at_1af[0x6]; u8 port_type[0x2]; u8 num_ports[0x8]; - u8 reserved_20[0x3]; + u8 reserved_at_1bf[0x3]; u8 log_max_msg[0x5]; - u8 reserved_21[0x18]; + u8 reserved_at_1c7[0x18]; u8 stat_rate_support[0x10]; - u8 reserved_22[0xc]; + u8 reserved_at_1ef[0xc]; u8 cqe_version[0x4]; u8 compact_address_vector[0x1]; - u8 reserved_23[0xe]; + u8 reserved_at_200[0xe]; u8 drain_sigerr[0x1]; u8 cmdif_checksum[0x2]; u8 sigerr_cqe[0x1]; - u8 reserved_24[0x1]; + u8 reserved_at_212[0x1]; u8 wq_signature[0x1]; u8 sctr_data_cqe[0x1]; - u8 reserved_25[0x1]; + u8 reserved_at_215[0x1]; u8 sho[0x1]; u8 tph[0x1]; u8 rf[0x1]; u8 dct[0x1]; - u8 reserved_26[0x1]; + u8 reserved_at_21a[0x1]; u8 eth_net_offloads[0x1]; u8 roce[0x1]; u8 atomic[0x1]; - u8 reserved_27[0x1]; + u8 reserved_at_21e[0x1]; u8 cq_oi[0x1]; u8 cq_resize[0x1]; u8 cq_moderation[0x1]; - u8 reserved_28[0x3]; + u8 reserved_at_222[0x3]; u8 cq_eq_remap[0x1]; u8 pg[0x1]; u8 block_lb_mc[0x1]; - u8 reserved_29[0x1]; + u8 reserved_at_228[0x1]; u8 scqe_break_moderation[0x1]; - u8 reserved_30[0x1]; + u8 reserved_at_22a[0x1]; u8 cd[0x1]; - u8 reserved_31[0x1]; + u8 reserved_at_22c[0x1]; u8 apm[0x1]; - u8 reserved_32[0x7]; + u8 reserved_at_22e[0x7]; u8 qkv[0x1]; u8 pkv[0x1]; - u8 reserved_33[0x4]; + u8 reserved_at_237[0x4]; u8 xrc[0x1]; u8 ud[0x1]; u8 uc[0x1]; u8 rc[0x1]; - u8 reserved_34[0xa]; + u8 reserved_at_23f[0xa]; u8 uar_sz[0x6]; - u8 reserved_35[0x8]; + u8 reserved_at_24f[0x8]; u8 log_pg_sz[0x8]; u8 bf[0x1]; - u8 reserved_36[0x1]; + u8 reserved_at_260[0x1]; u8 pad_tx_eth_packet[0x1]; - u8 reserved_37[0x8]; + u8 reserved_at_262[0x8]; u8 log_bf_reg_size[0x5]; - u8 reserved_38[0x10]; + u8 reserved_at_26f[0x10]; - u8 reserved_39[0x10]; + u8 reserved_at_27f[0x10]; u8 max_wqe_sz_sq[0x10]; - u8 reserved_40[0x10]; + u8 reserved_at_29f[0x10]; u8 max_wqe_sz_rq[0x10]; - u8 reserved_41[0x10]; + u8 reserved_at_2bf[0x10]; u8 max_wqe_sz_sq_dc[0x10]; - u8 reserved_42[0x7]; + u8 reserved_at_2df[0x7]; u8 max_qp_mcg[0x19]; - u8 reserved_43[0x18]; + u8 reserved_at_2ff[0x18]; u8 log_max_mcg[0x8]; - u8 reserved_44[0x3]; + u8 reserved_at_31f[0x3]; u8 log_max_transport_domain[0x5]; - u8 reserved_45[0x3]; + u8 reserved_at_327[0x3]; u8 log_max_pd[0x5]; - u8 reserved_46[0xb]; + u8 reserved_at_32f[0xb]; u8 log_max_xrcd[0x5]; - u8 reserved_47[0x20]; + u8 reserved_at_33f[0x20]; - u8 reserved_48[0x3]; + u8 reserved_at_35f[0x3]; u8 log_max_rq[0x5]; - u8 reserved_49[0x3]; + u8 reserved_at_367[0x3]; u8 log_max_sq[0x5]; - u8 reserved_50[0x3]; + u8 reserved_at_36f[0x3]; u8 log_max_tir[0x5]; - u8 reserved_51[0x3]; + u8 reserved_at_377[0x3]; u8 log_max_tis[0x5]; u8 basic_cyclic_rcv_wqe[0x1]; - u8 reserved_52[0x2]; + u8 reserved_at_380[0x2]; u8 log_max_rmp[0x5]; - u8 reserved_53[0x3]; + u8 reserved_at_387[0x3]; u8 log_max_rqt[0x5]; - u8 reserved_54[0x3]; + u8 reserved_at_38f[0x3]; u8 log_max_rqt_size[0x5]; - u8 reserved_55[0x3]; + u8 reserved_at_397[0x3]; u8 log_max_tis_per_sq[0x5]; - u8 reserved_56[0x3]; + u8 reserved_at_39f[0x3]; u8 log_max_stride_sz_rq[0x5]; - u8 reserved_57[0x3]; + u8 reserved_at_3a7[0x3]; u8 log_min_stride_sz_rq[0x5]; - u8 reserved_58[0x3]; + u8 reserved_at_3af[0x3]; u8 log_max_stride_sz_sq[0x5]; - u8 reserved_59[0x3]; + u8 reserved_at_3b7[0x3]; u8 log_min_stride_sz_sq[0x5]; - u8 reserved_60[0x1b]; + u8 reserved_at_3bf[0x1b]; u8 log_max_wq_sz[0x5]; u8 nic_vport_change_event[0x1]; - u8 reserved_61[0xa]; + u8 reserved_at_3e0[0xa]; u8 log_max_vlan_list[0x5]; - u8 reserved_62[0x3]; + u8 reserved_at_3ef[0x3]; u8 log_max_current_mc_list[0x5]; - u8 reserved_63[0x3]; + u8 reserved_at_3f7[0x3]; u8 log_max_current_uc_list[0x5]; - u8 reserved_64[0x80]; + u8 reserved_at_3ff[0x80]; - u8 reserved_65[0x3]; + u8 reserved_at_47f[0x3]; u8 log_max_l2_table[0x5]; - u8 reserved_66[0x8]; + u8 reserved_at_487[0x8]; u8 log_uar_page_sz[0x10]; - u8 reserved_67[0x20]; + u8 reserved_at_49f[0x20]; u8 device_frequency_mhz[0x20]; u8 device_frequency_khz[0x20]; - u8 reserved_68[0x5f]; + u8 reserved_at_4ff[0x5f]; u8 cqe_zip[0x1]; u8 cqe_zip_timeout[0x10]; u8 cqe_zip_max_num[0x10]; - u8 reserved_69[0x220]; + u8 reserved_at_57f[0x220]; }; enum mlx5_flow_destination_type { @@ -880,7 +880,7 @@ struct mlx5_ifc_dest_format_struct_bits { u8 destination_type[0x8]; u8 destination_id[0x18]; - u8 reserved_0[0x20]; + u8 reserved_at_20[0x20]; }; struct mlx5_ifc_fte_match_param_bits { @@ -890,7 +890,7 @@ struct mlx5_ifc_fte_match_param_bits { struct mlx5_ifc_fte_match_set_lyr_2_4_bits inner_headers; - u8 reserved_0[0xa00]; + u8 reserved_at_600[0xa00]; }; enum { @@ -922,18 +922,18 @@ struct mlx5_ifc_wq_bits { u8 wq_signature[0x1]; u8 end_padding_mode[0x2]; u8 cd_slave[0x1]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 hds_skip_first_sge[0x1]; u8 log2_hds_buf_size[0x3]; - u8 reserved_1[0x7]; + u8 reserved_at_24[0x7]; u8 page_offset[0x5]; u8 lwm[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 pd[0x18]; - u8 reserved_3[0x8]; + u8 reserved_at_60[0x8]; u8 uar_page[0x18]; u8 dbr_addr[0x40]; @@ -942,60 +942,60 @@ struct mlx5_ifc_wq_bits { u8 sw_counter[0x20]; - u8 reserved_4[0xc]; + u8 reserved_at_100[0xc]; u8 log_wq_stride[0x4]; - u8 reserved_5[0x3]; + u8 reserved_at_110[0x3]; u8 log_wq_pg_sz[0x5]; - u8 reserved_6[0x3]; + u8 reserved_at_118[0x3]; u8 log_wq_sz[0x5]; - u8 reserved_7[0x4e0]; + u8 reserved_at_120[0x4e0]; struct mlx5_ifc_cmd_pas_bits pas[0]; }; struct mlx5_ifc_rq_num_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 rq_num[0x18]; }; struct mlx5_ifc_mac_address_layout_bits { - u8 reserved_0[0x10]; + u8 reserved_at_0[0x10]; u8 mac_addr_47_32[0x10]; u8 mac_addr_31_0[0x20]; }; struct mlx5_ifc_vlan_layout_bits { - u8 reserved_0[0x14]; + u8 reserved_at_0[0x14]; u8 vlan[0x0c]; - u8 reserved_1[0x20]; + u8 reserved_at_20[0x20]; }; struct mlx5_ifc_cong_control_r_roce_ecn_np_bits { - u8 reserved_0[0xa0]; + u8 reserved_at_0[0xa0]; u8 min_time_between_cnps[0x20]; - u8 reserved_1[0x12]; + u8 reserved_at_c0[0x12]; u8 cnp_dscp[0x6]; - u8 reserved_2[0x5]; + u8 reserved_at_d8[0x5]; u8 cnp_802p_prio[0x3]; - u8 reserved_3[0x720]; + u8 reserved_at_e0[0x720]; }; struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits { - u8 reserved_0[0x60]; + u8 reserved_at_0[0x60]; - u8 reserved_1[0x4]; + u8 reserved_at_60[0x4]; u8 clamp_tgt_rate[0x1]; - u8 reserved_2[0x3]; + u8 reserved_at_65[0x3]; u8 clamp_tgt_rate_after_time_inc[0x1]; - u8 reserved_3[0x17]; + u8 reserved_at_69[0x17]; - u8 reserved_4[0x20]; + u8 reserved_at_80[0x20]; u8 rpg_time_reset[0x20]; @@ -1015,7 +1015,7 @@ struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits { u8 rpg_min_rate[0x20]; - u8 reserved_5[0xe0]; + u8 reserved_at_1c0[0xe0]; u8 rate_to_set_on_first_cnp[0x20]; @@ -1025,15 +1025,15 @@ struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits { u8 rate_reduce_monitor_period[0x20]; - u8 reserved_6[0x20]; + u8 reserved_at_320[0x20]; u8 initial_alpha_value[0x20]; - u8 reserved_7[0x4a0]; + u8 reserved_at_360[0x4a0]; }; struct mlx5_ifc_cong_control_802_1qau_rp_bits { - u8 reserved_0[0x80]; + u8 reserved_at_0[0x80]; u8 rppp_max_rps[0x20]; @@ -1055,7 +1055,7 @@ struct mlx5_ifc_cong_control_802_1qau_rp_bits { u8 rpg_min_rate[0x20]; - u8 reserved_1[0x640]; + u8 reserved_at_1c0[0x640]; }; enum { @@ -1205,7 +1205,7 @@ struct mlx5_ifc_phys_layer_cntrs_bits { u8 successful_recovery_events[0x20]; - u8 reserved_0[0x180]; + u8 reserved_at_640[0x180]; }; struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits { @@ -1213,7 +1213,7 @@ struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits { u8 transmit_queue_low[0x20]; - u8 reserved_0[0x780]; + u8 reserved_at_40[0x780]; }; struct mlx5_ifc_eth_per_prio_grp_data_layout_bits { @@ -1221,7 +1221,7 @@ struct mlx5_ifc_eth_per_prio_grp_data_layout_bits { u8 rx_octets_low[0x20]; - u8 reserved_0[0xc0]; + u8 reserved_at_40[0xc0]; u8 rx_frames_high[0x20]; @@ -1231,7 +1231,7 @@ struct mlx5_ifc_eth_per_prio_grp_data_layout_bits { u8 tx_octets_low[0x20]; - u8 reserved_1[0xc0]; + u8 reserved_at_180[0xc0]; u8 tx_frames_high[0x20]; @@ -1257,7 +1257,7 @@ struct mlx5_ifc_eth_per_prio_grp_data_layout_bits { u8 rx_pause_transition_low[0x20]; - u8 reserved_2[0x400]; + u8 reserved_at_3c0[0x400]; }; struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits { @@ -1265,7 +1265,7 @@ struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits { u8 port_transmit_wait_low[0x20]; - u8 reserved_0[0x780]; + u8 reserved_at_40[0x780]; }; struct mlx5_ifc_eth_3635_cntrs_grp_data_layout_bits { @@ -1333,7 +1333,7 @@ struct mlx5_ifc_eth_3635_cntrs_grp_data_layout_bits { u8 dot3out_pause_frames_low[0x20]; - u8 reserved_0[0x3c0]; + u8 reserved_at_400[0x3c0]; }; struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits { @@ -1421,7 +1421,7 @@ struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits { u8 ether_stats_pkts8192to10239octets_low[0x20]; - u8 reserved_0[0x280]; + u8 reserved_at_540[0x280]; }; struct mlx5_ifc_eth_2863_cntrs_grp_data_layout_bits { @@ -1477,7 +1477,7 @@ struct mlx5_ifc_eth_2863_cntrs_grp_data_layout_bits { u8 if_out_broadcast_pkts_low[0x20]; - u8 reserved_0[0x480]; + u8 reserved_at_340[0x480]; }; struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits { @@ -1557,54 +1557,54 @@ struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits { u8 a_pause_mac_ctrl_frames_transmitted_low[0x20]; - u8 reserved_0[0x300]; + u8 reserved_at_4c0[0x300]; }; struct mlx5_ifc_cmd_inter_comp_event_bits { u8 command_completion_vector[0x20]; - u8 reserved_0[0xc0]; + u8 reserved_at_20[0xc0]; }; struct mlx5_ifc_stall_vl_event_bits { - u8 reserved_0[0x18]; + u8 reserved_at_0[0x18]; u8 port_num[0x1]; - u8 reserved_1[0x3]; + u8 reserved_at_19[0x3]; u8 vl[0x4]; - u8 reserved_2[0xa0]; + u8 reserved_at_20[0xa0]; }; struct mlx5_ifc_db_bf_congestion_event_bits { u8 event_subtype[0x8]; - u8 reserved_0[0x8]; + u8 reserved_at_8[0x8]; u8 congestion_level[0x8]; - u8 reserved_1[0x8]; + u8 reserved_at_18[0x8]; - u8 reserved_2[0xa0]; + u8 reserved_at_20[0xa0]; }; struct mlx5_ifc_gpio_event_bits { - u8 reserved_0[0x60]; + u8 reserved_at_0[0x60]; u8 gpio_event_hi[0x20]; u8 gpio_event_lo[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_a0[0x40]; }; struct mlx5_ifc_port_state_change_event_bits { - u8 reserved_0[0x40]; + u8 reserved_at_0[0x40]; u8 port_num[0x4]; - u8 reserved_1[0x1c]; + u8 reserved_at_44[0x1c]; - u8 reserved_2[0x80]; + u8 reserved_at_60[0x80]; }; struct mlx5_ifc_dropped_packet_logged_bits { - u8 reserved_0[0xe0]; + u8 reserved_at_0[0xe0]; }; enum { @@ -1613,15 +1613,15 @@ enum { }; struct mlx5_ifc_cq_error_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 cqn[0x18]; - u8 reserved_1[0x20]; + u8 reserved_at_20[0x20]; - u8 reserved_2[0x18]; + u8 reserved_at_40[0x18]; u8 syndrome[0x8]; - u8 reserved_3[0x80]; + u8 reserved_at_60[0x80]; }; struct mlx5_ifc_rdma_page_fault_event_bits { @@ -1629,14 +1629,14 @@ struct mlx5_ifc_rdma_page_fault_event_bits { u8 r_key[0x20]; - u8 reserved_0[0x10]; + u8 reserved_at_40[0x10]; u8 packet_len[0x10]; u8 rdma_op_len[0x20]; u8 rdma_va[0x40]; - u8 reserved_1[0x5]; + u8 reserved_at_c0[0x5]; u8 rdma[0x1]; u8 write[0x1]; u8 requestor[0x1]; @@ -1646,15 +1646,15 @@ struct mlx5_ifc_rdma_page_fault_event_bits { struct mlx5_ifc_wqe_associated_page_fault_event_bits { u8 bytes_committed[0x20]; - u8 reserved_0[0x10]; + u8 reserved_at_20[0x10]; u8 wqe_index[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_40[0x10]; u8 len[0x10]; - u8 reserved_2[0x60]; + u8 reserved_at_60[0x60]; - u8 reserved_3[0x5]; + u8 reserved_at_c0[0x5]; u8 rdma[0x1]; u8 write_read[0x1]; u8 requestor[0x1]; @@ -1662,26 +1662,26 @@ struct mlx5_ifc_wqe_associated_page_fault_event_bits { }; struct mlx5_ifc_qp_events_bits { - u8 reserved_0[0xa0]; + u8 reserved_at_0[0xa0]; u8 type[0x8]; - u8 reserved_1[0x18]; + u8 reserved_at_a8[0x18]; - u8 reserved_2[0x8]; + u8 reserved_at_c0[0x8]; u8 qpn_rqn_sqn[0x18]; }; struct mlx5_ifc_dct_events_bits { - u8 reserved_0[0xc0]; + u8 reserved_at_0[0xc0]; - u8 reserved_1[0x8]; + u8 reserved_at_c0[0x8]; u8 dct_number[0x18]; }; struct mlx5_ifc_comp_event_bits { - u8 reserved_0[0xc0]; + u8 reserved_at_0[0xc0]; - u8 reserved_1[0x8]; + u8 reserved_at_c0[0x8]; u8 cq_number[0x18]; }; @@ -1754,41 +1754,41 @@ enum { struct mlx5_ifc_qpc_bits { u8 state[0x4]; - u8 reserved_0[0x4]; + u8 reserved_at_4[0x4]; u8 st[0x8]; - u8 reserved_1[0x3]; + u8 reserved_at_10[0x3]; u8 pm_state[0x2]; - u8 reserved_2[0x7]; + u8 reserved_at_15[0x7]; u8 end_padding_mode[0x2]; - u8 reserved_3[0x2]; + u8 reserved_at_1e[0x2]; u8 wq_signature[0x1]; u8 block_lb_mc[0x1]; u8 atomic_like_write_en[0x1]; u8 latency_sensitive[0x1]; - u8 reserved_4[0x1]; + u8 reserved_at_24[0x1]; u8 drain_sigerr[0x1]; - u8 reserved_5[0x2]; + u8 reserved_at_26[0x2]; u8 pd[0x18]; u8 mtu[0x3]; u8 log_msg_max[0x5]; - u8 reserved_6[0x1]; + u8 reserved_at_48[0x1]; u8 log_rq_size[0x4]; u8 log_rq_stride[0x3]; u8 no_sq[0x1]; u8 log_sq_size[0x4]; - u8 reserved_7[0x6]; + u8 reserved_at_55[0x6]; u8 rlky[0x1]; - u8 reserved_8[0x4]; + u8 reserved_at_5c[0x4]; u8 counter_set_id[0x8]; u8 uar_page[0x18]; - u8 reserved_9[0x8]; + u8 reserved_at_80[0x8]; u8 user_index[0x18]; - u8 reserved_10[0x3]; + u8 reserved_at_a0[0x3]; u8 log_page_size[0x5]; u8 remote_qpn[0x18]; @@ -1797,66 +1797,66 @@ struct mlx5_ifc_qpc_bits { struct mlx5_ifc_ads_bits secondary_address_path; u8 log_ack_req_freq[0x4]; - u8 reserved_11[0x4]; + u8 reserved_at_384[0x4]; u8 log_sra_max[0x3]; - u8 reserved_12[0x2]; + u8 reserved_at_38b[0x2]; u8 retry_count[0x3]; u8 rnr_retry[0x3]; - u8 reserved_13[0x1]; + u8 reserved_at_393[0x1]; u8 fre[0x1]; u8 cur_rnr_retry[0x3]; u8 cur_retry_count[0x3]; - u8 reserved_14[0x5]; + u8 reserved_at_39b[0x5]; - u8 reserved_15[0x20]; + u8 reserved_at_3a0[0x20]; - u8 reserved_16[0x8]; + u8 reserved_at_3c0[0x8]; u8 next_send_psn[0x18]; - u8 reserved_17[0x8]; + u8 reserved_at_3e0[0x8]; u8 cqn_snd[0x18]; - u8 reserved_18[0x40]; + u8 reserved_at_400[0x40]; - u8 reserved_19[0x8]; + u8 reserved_at_440[0x8]; u8 last_acked_psn[0x18]; - u8 reserved_20[0x8]; + u8 reserved_at_460[0x8]; u8 ssn[0x18]; - u8 reserved_21[0x8]; + u8 reserved_at_480[0x8]; u8 log_rra_max[0x3]; - u8 reserved_22[0x1]; + u8 reserved_at_48b[0x1]; u8 atomic_mode[0x4]; u8 rre[0x1]; u8 rwe[0x1]; u8 rae[0x1]; - u8 reserved_23[0x1]; + u8 reserved_at_493[0x1]; u8 page_offset[0x6]; - u8 reserved_24[0x3]; + u8 reserved_at_49a[0x3]; u8 cd_slave_receive[0x1]; u8 cd_slave_send[0x1]; u8 cd_master[0x1]; - u8 reserved_25[0x3]; + u8 reserved_at_4a0[0x3]; u8 min_rnr_nak[0x5]; u8 next_rcv_psn[0x18]; - u8 reserved_26[0x8]; + u8 reserved_at_4c0[0x8]; u8 xrcd[0x18]; - u8 reserved_27[0x8]; + u8 reserved_at_4e0[0x8]; u8 cqn_rcv[0x18]; u8 dbr_addr[0x40]; u8 q_key[0x20]; - u8 reserved_28[0x5]; + u8 reserved_at_560[0x5]; u8 rq_type[0x3]; u8 srqn_rmpn[0x18]; - u8 reserved_29[0x8]; + u8 reserved_at_580[0x8]; u8 rmsn[0x18]; u8 hw_sq_wqebb_counter[0x10]; @@ -1866,33 +1866,33 @@ struct mlx5_ifc_qpc_bits { u8 sw_rq_counter[0x20]; - u8 reserved_30[0x20]; + u8 reserved_at_600[0x20]; - u8 reserved_31[0xf]; + u8 reserved_at_620[0xf]; u8 cgs[0x1]; u8 cs_req[0x8]; u8 cs_res[0x8]; u8 dc_access_key[0x40]; - u8 reserved_32[0xc0]; + u8 reserved_at_680[0xc0]; }; struct mlx5_ifc_roce_addr_layout_bits { u8 source_l3_address[16][0x8]; - u8 reserved_0[0x3]; + u8 reserved_at_80[0x3]; u8 vlan_valid[0x1]; u8 vlan_id[0xc]; u8 source_mac_47_32[0x10]; u8 source_mac_31_0[0x20]; - u8 reserved_1[0x14]; + u8 reserved_at_c0[0x14]; u8 roce_l3_type[0x4]; u8 roce_version[0x8]; - u8 reserved_2[0x20]; + u8 reserved_at_e0[0x20]; }; union mlx5_ifc_hca_cap_union_bits { @@ -1904,7 +1904,7 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_flow_table_nic_cap_bits flow_table_nic_cap; struct mlx5_ifc_flow_table_eswitch_cap_bits flow_table_eswitch_cap; struct mlx5_ifc_e_switch_cap_bits e_switch_cap; - u8 reserved_0[0x8000]; + u8 reserved_at_0[0x8000]; }; enum { @@ -1914,24 +1914,24 @@ enum { }; struct mlx5_ifc_flow_context_bits { - u8 reserved_0[0x20]; + u8 reserved_at_0[0x20]; u8 group_id[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 flow_tag[0x18]; - u8 reserved_2[0x10]; + u8 reserved_at_60[0x10]; u8 action[0x10]; - u8 reserved_3[0x8]; + u8 reserved_at_80[0x8]; u8 destination_list_size[0x18]; - u8 reserved_4[0x160]; + u8 reserved_at_a0[0x160]; struct mlx5_ifc_fte_match_param_bits match_value; - u8 reserved_5[0x600]; + u8 reserved_at_1200[0x600]; struct mlx5_ifc_dest_format_struct_bits destination[0]; }; @@ -1944,43 +1944,43 @@ enum { struct mlx5_ifc_xrc_srqc_bits { u8 state[0x4]; u8 log_xrc_srq_size[0x4]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 wq_signature[0x1]; u8 cont_srq[0x1]; - u8 reserved_1[0x1]; + u8 reserved_at_22[0x1]; u8 rlky[0x1]; u8 basic_cyclic_rcv_wqe[0x1]; u8 log_rq_stride[0x3]; u8 xrcd[0x18]; u8 page_offset[0x6]; - u8 reserved_2[0x2]; + u8 reserved_at_46[0x2]; u8 cqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 user_index_equal_xrc_srqn[0x1]; - u8 reserved_4[0x1]; + u8 reserved_at_81[0x1]; u8 log_page_size[0x6]; u8 user_index[0x18]; - u8 reserved_5[0x20]; + u8 reserved_at_a0[0x20]; - u8 reserved_6[0x8]; + u8 reserved_at_c0[0x8]; u8 pd[0x18]; u8 lwm[0x10]; u8 wqe_cnt[0x10]; - u8 reserved_7[0x40]; + u8 reserved_at_100[0x40]; u8 db_record_addr_h[0x20]; u8 db_record_addr_l[0x1e]; - u8 reserved_8[0x2]; + u8 reserved_at_17e[0x2]; - u8 reserved_9[0x80]; + u8 reserved_at_180[0x80]; }; struct mlx5_ifc_traffic_counter_bits { @@ -1990,16 +1990,16 @@ struct mlx5_ifc_traffic_counter_bits { }; struct mlx5_ifc_tisc_bits { - u8 reserved_0[0xc]; + u8 reserved_at_0[0xc]; u8 prio[0x4]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_2[0x100]; + u8 reserved_at_20[0x100]; - u8 reserved_3[0x8]; + u8 reserved_at_120[0x8]; u8 transport_domain[0x18]; - u8 reserved_4[0x3c0]; + u8 reserved_at_140[0x3c0]; }; enum { @@ -2024,31 +2024,31 @@ enum { }; struct mlx5_ifc_tirc_bits { - u8 reserved_0[0x20]; + u8 reserved_at_0[0x20]; u8 disp_type[0x4]; - u8 reserved_1[0x1c]; + u8 reserved_at_24[0x1c]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; - u8 reserved_3[0x4]; + u8 reserved_at_80[0x4]; u8 lro_timeout_period_usecs[0x10]; u8 lro_enable_mask[0x4]; u8 lro_max_ip_payload_size[0x8]; - u8 reserved_4[0x40]; + u8 reserved_at_a0[0x40]; - u8 reserved_5[0x8]; + u8 reserved_at_e0[0x8]; u8 inline_rqn[0x18]; u8 rx_hash_symmetric[0x1]; - u8 reserved_6[0x1]; + u8 reserved_at_101[0x1]; u8 tunneled_offload_en[0x1]; - u8 reserved_7[0x5]; + u8 reserved_at_103[0x5]; u8 indirect_table[0x18]; u8 rx_hash_fn[0x4]; - u8 reserved_8[0x2]; + u8 reserved_at_124[0x2]; u8 self_lb_block[0x2]; u8 transport_domain[0x18]; @@ -2058,7 +2058,7 @@ struct mlx5_ifc_tirc_bits { struct mlx5_ifc_rx_hash_field_select_bits rx_hash_field_selector_inner; - u8 reserved_9[0x4c0]; + u8 reserved_at_2c0[0x4c0]; }; enum { @@ -2069,39 +2069,39 @@ enum { struct mlx5_ifc_srqc_bits { u8 state[0x4]; u8 log_srq_size[0x4]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 wq_signature[0x1]; u8 cont_srq[0x1]; - u8 reserved_1[0x1]; + u8 reserved_at_22[0x1]; u8 rlky[0x1]; - u8 reserved_2[0x1]; + u8 reserved_at_24[0x1]; u8 log_rq_stride[0x3]; u8 xrcd[0x18]; u8 page_offset[0x6]; - u8 reserved_3[0x2]; + u8 reserved_at_46[0x2]; u8 cqn[0x18]; - u8 reserved_4[0x20]; + u8 reserved_at_60[0x20]; - u8 reserved_5[0x2]; + u8 reserved_at_80[0x2]; u8 log_page_size[0x6]; - u8 reserved_6[0x18]; + u8 reserved_at_88[0x18]; - u8 reserved_7[0x20]; + u8 reserved_at_a0[0x20]; - u8 reserved_8[0x8]; + u8 reserved_at_c0[0x8]; u8 pd[0x18]; u8 lwm[0x10]; u8 wqe_cnt[0x10]; - u8 reserved_9[0x40]; + u8 reserved_at_100[0x40]; u8 dbr_addr[0x40]; - u8 reserved_10[0x80]; + u8 reserved_at_180[0x80]; }; enum { @@ -2115,39 +2115,39 @@ struct mlx5_ifc_sqc_bits { u8 cd_master[0x1]; u8 fre[0x1]; u8 flush_in_error_en[0x1]; - u8 reserved_0[0x4]; + u8 reserved_at_4[0x4]; u8 state[0x4]; - u8 reserved_1[0x14]; + u8 reserved_at_c[0x14]; - u8 reserved_2[0x8]; + u8 reserved_at_20[0x8]; u8 user_index[0x18]; - u8 reserved_3[0x8]; + u8 reserved_at_40[0x8]; u8 cqn[0x18]; - u8 reserved_4[0xa0]; + u8 reserved_at_60[0xa0]; u8 tis_lst_sz[0x10]; - u8 reserved_5[0x10]; + u8 reserved_at_110[0x10]; - u8 reserved_6[0x40]; + u8 reserved_at_120[0x40]; - u8 reserved_7[0x8]; + u8 reserved_at_160[0x8]; u8 tis_num_0[0x18]; struct mlx5_ifc_wq_bits wq; }; struct mlx5_ifc_rqtc_bits { - u8 reserved_0[0xa0]; + u8 reserved_at_0[0xa0]; - u8 reserved_1[0x10]; + u8 reserved_at_a0[0x10]; u8 rqt_max_size[0x10]; - u8 reserved_2[0x10]; + u8 reserved_at_c0[0x10]; u8 rqt_actual_size[0x10]; - u8 reserved_3[0x6a0]; + u8 reserved_at_e0[0x6a0]; struct mlx5_ifc_rq_num_bits rq_num[0]; }; @@ -2165,27 +2165,27 @@ enum { struct mlx5_ifc_rqc_bits { u8 rlky[0x1]; - u8 reserved_0[0x2]; + u8 reserved_at_1[0x2]; u8 vsd[0x1]; u8 mem_rq_type[0x4]; u8 state[0x4]; - u8 reserved_1[0x1]; + u8 reserved_at_c[0x1]; u8 flush_in_error_en[0x1]; - u8 reserved_2[0x12]; + u8 reserved_at_e[0x12]; - u8 reserved_3[0x8]; + u8 reserved_at_20[0x8]; u8 user_index[0x18]; - u8 reserved_4[0x8]; + u8 reserved_at_40[0x8]; u8 cqn[0x18]; u8 counter_set_id[0x8]; - u8 reserved_5[0x18]; + u8 reserved_at_68[0x18]; - u8 reserved_6[0x8]; + u8 reserved_at_80[0x8]; u8 rmpn[0x18]; - u8 reserved_7[0xe0]; + u8 reserved_at_a0[0xe0]; struct mlx5_ifc_wq_bits wq; }; @@ -2196,31 +2196,31 @@ enum { }; struct mlx5_ifc_rmpc_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 state[0x4]; - u8 reserved_1[0x14]; + u8 reserved_at_c[0x14]; u8 basic_cyclic_rcv_wqe[0x1]; - u8 reserved_2[0x1f]; + u8 reserved_at_21[0x1f]; - u8 reserved_3[0x140]; + u8 reserved_at_40[0x140]; struct mlx5_ifc_wq_bits wq; }; struct mlx5_ifc_nic_vport_context_bits { - u8 reserved_0[0x1f]; + u8 reserved_at_0[0x1f]; u8 roce_en[0x1]; u8 arm_change_event[0x1]; - u8 reserved_1[0x1a]; + u8 reserved_at_21[0x1a]; u8 event_on_mtu[0x1]; u8 event_on_promisc_change[0x1]; u8 event_on_vlan_change[0x1]; u8 event_on_mc_address_change[0x1]; u8 event_on_uc_address_change[0x1]; - u8 reserved_2[0xf0]; + u8 reserved_at_40[0xf0]; u8 mtu[0x10]; @@ -2228,21 +2228,21 @@ struct mlx5_ifc_nic_vport_context_bits { u8 port_guid[0x40]; u8 node_guid[0x40]; - u8 reserved_3[0x140]; + u8 reserved_at_200[0x140]; u8 qkey_violation_counter[0x10]; - u8 reserved_4[0x430]; + u8 reserved_at_350[0x430]; u8 promisc_uc[0x1]; u8 promisc_mc[0x1]; u8 promisc_all[0x1]; - u8 reserved_5[0x2]; + u8 reserved_at_783[0x2]; u8 allowed_list_type[0x3]; - u8 reserved_6[0xc]; + u8 reserved_at_788[0xc]; u8 allowed_list_size[0xc]; struct mlx5_ifc_mac_address_layout_bits permanent_address; - u8 reserved_7[0x20]; + u8 reserved_at_7e0[0x20]; u8 current_uc_mac_address[0][0x40]; }; @@ -2254,9 +2254,9 @@ enum { }; struct mlx5_ifc_mkc_bits { - u8 reserved_0[0x1]; + u8 reserved_at_0[0x1]; u8 free[0x1]; - u8 reserved_1[0xd]; + u8 reserved_at_2[0xd]; u8 small_fence_on_rdma_read_response[0x1]; u8 umr_en[0x1]; u8 a[0x1]; @@ -2265,19 +2265,19 @@ struct mlx5_ifc_mkc_bits { u8 lw[0x1]; u8 lr[0x1]; u8 access_mode[0x2]; - u8 reserved_2[0x8]; + u8 reserved_at_18[0x8]; u8 qpn[0x18]; u8 mkey_7_0[0x8]; - u8 reserved_3[0x20]; + u8 reserved_at_40[0x20]; u8 length64[0x1]; u8 bsf_en[0x1]; u8 sync_umr[0x1]; - u8 reserved_4[0x2]; + u8 reserved_at_63[0x2]; u8 expected_sigerr_count[0x1]; - u8 reserved_5[0x1]; + u8 reserved_at_66[0x1]; u8 en_rinval[0x1]; u8 pd[0x18]; @@ -2287,18 +2287,18 @@ struct mlx5_ifc_mkc_bits { u8 bsf_octword_size[0x20]; - u8 reserved_6[0x80]; + u8 reserved_at_120[0x80]; u8 translations_octword_size[0x20]; - u8 reserved_7[0x1b]; + u8 reserved_at_1c0[0x1b]; u8 log_page_size[0x5]; - u8 reserved_8[0x20]; + u8 reserved_at_1e0[0x20]; }; struct mlx5_ifc_pkey_bits { - u8 reserved_0[0x10]; + u8 reserved_at_0[0x10]; u8 pkey[0x10]; }; @@ -2309,19 +2309,19 @@ struct mlx5_ifc_array128_auto_bits { struct mlx5_ifc_hca_vport_context_bits { u8 field_select[0x20]; - u8 reserved_0[0xe0]; + u8 reserved_at_20[0xe0]; u8 sm_virt_aware[0x1]; u8 has_smi[0x1]; u8 has_raw[0x1]; u8 grh_required[0x1]; - u8 reserved_1[0xc]; + u8 reserved_at_104[0xc]; u8 port_physical_state[0x4]; u8 vport_state_policy[0x4]; u8 port_state[0x4]; u8 vport_state[0x4]; - u8 reserved_2[0x20]; + u8 reserved_at_120[0x20]; u8 system_image_guid[0x40]; @@ -2337,33 +2337,33 @@ struct mlx5_ifc_hca_vport_context_bits { u8 cap_mask2_field_select[0x20]; - u8 reserved_3[0x80]; + u8 reserved_at_280[0x80]; u8 lid[0x10]; - u8 reserved_4[0x4]; + u8 reserved_at_310[0x4]; u8 init_type_reply[0x4]; u8 lmc[0x3]; u8 subnet_timeout[0x5]; u8 sm_lid[0x10]; u8 sm_sl[0x4]; - u8 reserved_5[0xc]; + u8 reserved_at_334[0xc]; u8 qkey_violation_counter[0x10]; u8 pkey_violation_counter[0x10]; - u8 reserved_6[0xca0]; + u8 reserved_at_360[0xca0]; }; struct mlx5_ifc_esw_vport_context_bits { - u8 reserved_0[0x3]; + u8 reserved_at_0[0x3]; u8 vport_svlan_strip[0x1]; u8 vport_cvlan_strip[0x1]; u8 vport_svlan_insert[0x1]; u8 vport_cvlan_insert[0x2]; - u8 reserved_1[0x18]; + u8 reserved_at_8[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_20[0x20]; u8 svlan_cfi[0x1]; u8 svlan_pcp[0x3]; @@ -2372,7 +2372,7 @@ struct mlx5_ifc_esw_vport_context_bits { u8 cvlan_pcp[0x3]; u8 cvlan_id[0xc]; - u8 reserved_3[0x7a0]; + u8 reserved_at_60[0x7a0]; }; enum { @@ -2387,41 +2387,41 @@ enum { struct mlx5_ifc_eqc_bits { u8 status[0x4]; - u8 reserved_0[0x9]; + u8 reserved_at_4[0x9]; u8 ec[0x1]; u8 oi[0x1]; - u8 reserved_1[0x5]; + u8 reserved_at_f[0x5]; u8 st[0x4]; - u8 reserved_2[0x8]; + u8 reserved_at_18[0x8]; - u8 reserved_3[0x20]; + u8 reserved_at_20[0x20]; - u8 reserved_4[0x14]; + u8 reserved_at_40[0x14]; u8 page_offset[0x6]; - u8 reserved_5[0x6]; + u8 reserved_at_5a[0x6]; - u8 reserved_6[0x3]; + u8 reserved_at_60[0x3]; u8 log_eq_size[0x5]; u8 uar_page[0x18]; - u8 reserved_7[0x20]; + u8 reserved_at_80[0x20]; - u8 reserved_8[0x18]; + u8 reserved_at_a0[0x18]; u8 intr[0x8]; - u8 reserved_9[0x3]; + u8 reserved_at_c0[0x3]; u8 log_page_size[0x5]; - u8 reserved_10[0x18]; + u8 reserved_at_c8[0x18]; - u8 reserved_11[0x60]; + u8 reserved_at_e0[0x60]; - u8 reserved_12[0x8]; + u8 reserved_at_140[0x8]; u8 consumer_counter[0x18]; - u8 reserved_13[0x8]; + u8 reserved_at_160[0x8]; u8 producer_counter[0x18]; - u8 reserved_14[0x80]; + u8 reserved_at_180[0x80]; }; enum { @@ -2445,14 +2445,14 @@ enum { }; struct mlx5_ifc_dctc_bits { - u8 reserved_0[0x4]; + u8 reserved_at_0[0x4]; u8 state[0x4]; - u8 reserved_1[0x18]; + u8 reserved_at_8[0x18]; - u8 reserved_2[0x8]; + u8 reserved_at_20[0x8]; u8 user_index[0x18]; - u8 reserved_3[0x8]; + u8 reserved_at_40[0x8]; u8 cqn[0x18]; u8 counter_set_id[0x8]; @@ -2464,45 +2464,45 @@ struct mlx5_ifc_dctc_bits { u8 latency_sensitive[0x1]; u8 rlky[0x1]; u8 free_ar[0x1]; - u8 reserved_4[0xd]; + u8 reserved_at_73[0xd]; - u8 reserved_5[0x8]; + u8 reserved_at_80[0x8]; u8 cs_res[0x8]; - u8 reserved_6[0x3]; + u8 reserved_at_90[0x3]; u8 min_rnr_nak[0x5]; - u8 reserved_7[0x8]; + u8 reserved_at_98[0x8]; - u8 reserved_8[0x8]; + u8 reserved_at_a0[0x8]; u8 srqn[0x18]; - u8 reserved_9[0x8]; + u8 reserved_at_c0[0x8]; u8 pd[0x18]; u8 tclass[0x8]; - u8 reserved_10[0x4]; + u8 reserved_at_e8[0x4]; u8 flow_label[0x14]; u8 dc_access_key[0x40]; - u8 reserved_11[0x5]; + u8 reserved_at_140[0x5]; u8 mtu[0x3]; u8 port[0x8]; u8 pkey_index[0x10]; - u8 reserved_12[0x8]; + u8 reserved_at_160[0x8]; u8 my_addr_index[0x8]; - u8 reserved_13[0x8]; + u8 reserved_at_170[0x8]; u8 hop_limit[0x8]; u8 dc_access_key_violation_count[0x20]; - u8 reserved_14[0x14]; + u8 reserved_at_1a0[0x14]; u8 dei_cfi[0x1]; u8 eth_prio[0x3]; u8 ecn[0x2]; u8 dscp[0x6]; - u8 reserved_15[0x40]; + u8 reserved_at_1c0[0x40]; }; enum { @@ -2524,54 +2524,54 @@ enum { struct mlx5_ifc_cqc_bits { u8 status[0x4]; - u8 reserved_0[0x4]; + u8 reserved_at_4[0x4]; u8 cqe_sz[0x3]; u8 cc[0x1]; - u8 reserved_1[0x1]; + u8 reserved_at_c[0x1]; u8 scqe_break_moderation_en[0x1]; u8 oi[0x1]; - u8 reserved_2[0x2]; + u8 reserved_at_f[0x2]; u8 cqe_zip_en[0x1]; u8 mini_cqe_res_format[0x2]; u8 st[0x4]; - u8 reserved_3[0x8]; + u8 reserved_at_18[0x8]; - u8 reserved_4[0x20]; + u8 reserved_at_20[0x20]; - u8 reserved_5[0x14]; + u8 reserved_at_40[0x14]; u8 page_offset[0x6]; - u8 reserved_6[0x6]; + u8 reserved_at_5a[0x6]; - u8 reserved_7[0x3]; + u8 reserved_at_60[0x3]; u8 log_cq_size[0x5]; u8 uar_page[0x18]; - u8 reserved_8[0x4]; + u8 reserved_at_80[0x4]; u8 cq_period[0xc]; u8 cq_max_count[0x10]; - u8 reserved_9[0x18]; + u8 reserved_at_a0[0x18]; u8 c_eqn[0x8]; - u8 reserved_10[0x3]; + u8 reserved_at_c0[0x3]; u8 log_page_size[0x5]; - u8 reserved_11[0x18]; + u8 reserved_at_c8[0x18]; - u8 reserved_12[0x20]; + u8 reserved_at_e0[0x20]; - u8 reserved_13[0x8]; + u8 reserved_at_100[0x8]; u8 last_notified_index[0x18]; - u8 reserved_14[0x8]; + u8 reserved_at_120[0x8]; u8 last_solicit_index[0x18]; - u8 reserved_15[0x8]; + u8 reserved_at_140[0x8]; u8 consumer_counter[0x18]; - u8 reserved_16[0x8]; + u8 reserved_at_160[0x8]; u8 producer_counter[0x18]; - u8 reserved_17[0x40]; + u8 reserved_at_180[0x40]; u8 dbr_addr[0x40]; }; @@ -2580,16 +2580,16 @@ union mlx5_ifc_cong_control_roce_ecn_auto_bits { struct mlx5_ifc_cong_control_802_1qau_rp_bits cong_control_802_1qau_rp; struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits cong_control_r_roce_ecn_rp; struct mlx5_ifc_cong_control_r_roce_ecn_np_bits cong_control_r_roce_ecn_np; - u8 reserved_0[0x800]; + u8 reserved_at_0[0x800]; }; struct mlx5_ifc_query_adapter_param_block_bits { - u8 reserved_0[0xc0]; + u8 reserved_at_0[0xc0]; - u8 reserved_1[0x8]; + u8 reserved_at_c0[0x8]; u8 ieee_vendor_id[0x18]; - u8 reserved_2[0x10]; + u8 reserved_at_e0[0x10]; u8 vsd_vendor_id[0x10]; u8 vsd[208][0x8]; @@ -2600,14 +2600,14 @@ struct mlx5_ifc_query_adapter_param_block_bits { union mlx5_ifc_modify_field_select_resize_field_select_auto_bits { struct mlx5_ifc_modify_field_select_bits modify_field_select; struct mlx5_ifc_resize_field_select_bits resize_field_select; - u8 reserved_0[0x20]; + u8 reserved_at_0[0x20]; }; union mlx5_ifc_field_select_802_1_r_roce_auto_bits { struct mlx5_ifc_field_select_802_1qau_rp_bits field_select_802_1qau_rp; struct mlx5_ifc_field_select_r_roce_rp_bits field_select_r_roce_rp; struct mlx5_ifc_field_select_r_roce_np_bits field_select_r_roce_np; - u8 reserved_0[0x20]; + u8 reserved_at_0[0x20]; }; union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits { @@ -2619,7 +2619,7 @@ union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits { struct mlx5_ifc_eth_per_prio_grp_data_layout_bits eth_per_prio_grp_data_layout; struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits eth_per_traffic_grp_data_layout; struct mlx5_ifc_phys_layer_cntrs_bits phys_layer_cntrs; - u8 reserved_0[0x7c0]; + u8 reserved_at_0[0x7c0]; }; union mlx5_ifc_event_auto_bits { @@ -2635,23 +2635,23 @@ union mlx5_ifc_event_auto_bits { struct mlx5_ifc_db_bf_congestion_event_bits db_bf_congestion_event; struct mlx5_ifc_stall_vl_event_bits stall_vl_event; struct mlx5_ifc_cmd_inter_comp_event_bits cmd_inter_comp_event; - u8 reserved_0[0xe0]; + u8 reserved_at_0[0xe0]; }; struct mlx5_ifc_health_buffer_bits { - u8 reserved_0[0x100]; + u8 reserved_at_0[0x100]; u8 assert_existptr[0x20]; u8 assert_callra[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_140[0x40]; u8 fw_version[0x20]; u8 hw_id[0x20]; - u8 reserved_2[0x20]; + u8 reserved_at_1c0[0x20]; u8 irisc_index[0x8]; u8 synd[0x8]; @@ -2660,20 +2660,20 @@ struct mlx5_ifc_health_buffer_bits { struct mlx5_ifc_register_loopback_control_bits { u8 no_lb[0x1]; - u8 reserved_0[0x7]; + u8 reserved_at_1[0x7]; u8 port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_2[0x60]; + u8 reserved_at_20[0x60]; }; struct mlx5_ifc_teardown_hca_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; enum { @@ -2683,108 +2683,108 @@ enum { struct mlx5_ifc_teardown_hca_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x10]; + u8 reserved_at_40[0x10]; u8 profile[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_sqerr2rts_qp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_sqerr2rts_qp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 opt_param_mask[0x20]; - u8 reserved_4[0x20]; + u8 reserved_at_a0[0x20]; struct mlx5_ifc_qpc_bits qpc; - u8 reserved_5[0x80]; + u8 reserved_at_800[0x80]; }; struct mlx5_ifc_sqd2rts_qp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_sqd2rts_qp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 opt_param_mask[0x20]; - u8 reserved_4[0x20]; + u8 reserved_at_a0[0x20]; struct mlx5_ifc_qpc_bits qpc; - u8 reserved_5[0x80]; + u8 reserved_at_800[0x80]; }; struct mlx5_ifc_set_roce_address_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_set_roce_address_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 roce_address_index[0x10]; - u8 reserved_2[0x10]; + u8 reserved_at_50[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; struct mlx5_ifc_roce_addr_layout_bits roce_address; }; struct mlx5_ifc_set_mad_demux_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; enum { @@ -2794,89 +2794,89 @@ enum { struct mlx5_ifc_set_mad_demux_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x20]; + u8 reserved_at_40[0x20]; - u8 reserved_3[0x6]; + u8 reserved_at_60[0x6]; u8 demux_mode[0x2]; - u8 reserved_4[0x18]; + u8 reserved_at_68[0x18]; }; struct mlx5_ifc_set_l2_table_entry_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_set_l2_table_entry_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x60]; + u8 reserved_at_40[0x60]; - u8 reserved_3[0x8]; + u8 reserved_at_a0[0x8]; u8 table_index[0x18]; - u8 reserved_4[0x20]; + u8 reserved_at_c0[0x20]; - u8 reserved_5[0x13]; + u8 reserved_at_e0[0x13]; u8 vlan_valid[0x1]; u8 vlan[0xc]; struct mlx5_ifc_mac_address_layout_bits mac_address; - u8 reserved_6[0xc0]; + u8 reserved_at_140[0xc0]; }; struct mlx5_ifc_set_issi_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_set_issi_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x10]; + u8 reserved_at_40[0x10]; u8 current_issi[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_set_hca_cap_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_set_hca_cap_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; union mlx5_ifc_hca_cap_union_bits capability; }; @@ -2890,156 +2890,156 @@ enum { struct mlx5_ifc_set_fte_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_set_fte_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; u8 table_type[0x8]; - u8 reserved_3[0x18]; + u8 reserved_at_88[0x18]; - u8 reserved_4[0x8]; + u8 reserved_at_a0[0x8]; u8 table_id[0x18]; - u8 reserved_5[0x18]; + u8 reserved_at_c0[0x18]; u8 modify_enable_mask[0x8]; - u8 reserved_6[0x20]; + u8 reserved_at_e0[0x20]; u8 flow_index[0x20]; - u8 reserved_7[0xe0]; + u8 reserved_at_120[0xe0]; struct mlx5_ifc_flow_context_bits flow_context; }; struct mlx5_ifc_rts2rts_qp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_rts2rts_qp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 opt_param_mask[0x20]; - u8 reserved_4[0x20]; + u8 reserved_at_a0[0x20]; struct mlx5_ifc_qpc_bits qpc; - u8 reserved_5[0x80]; + u8 reserved_at_800[0x80]; }; struct mlx5_ifc_rtr2rts_qp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_rtr2rts_qp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 opt_param_mask[0x20]; - u8 reserved_4[0x20]; + u8 reserved_at_a0[0x20]; struct mlx5_ifc_qpc_bits qpc; - u8 reserved_5[0x80]; + u8 reserved_at_800[0x80]; }; struct mlx5_ifc_rst2init_qp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_rst2init_qp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 opt_param_mask[0x20]; - u8 reserved_4[0x20]; + u8 reserved_at_a0[0x20]; struct mlx5_ifc_qpc_bits qpc; - u8 reserved_5[0x80]; + u8 reserved_at_800[0x80]; }; struct mlx5_ifc_query_xrc_srq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry; - u8 reserved_2[0x600]; + u8 reserved_at_280[0x600]; u8 pas[0][0x40]; }; struct mlx5_ifc_query_xrc_srq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 xrc_srqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; enum { @@ -3049,13 +3049,13 @@ enum { struct mlx5_ifc_query_vport_state_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x20]; + u8 reserved_at_40[0x20]; - u8 reserved_2[0x18]; + u8 reserved_at_60[0x18]; u8 admin_state[0x4]; u8 state[0x4]; }; @@ -3067,25 +3067,25 @@ enum { struct mlx5_ifc_query_vport_state_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_2[0xf]; + u8 reserved_at_41[0xf]; u8 vport_number[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_vport_counter_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_traffic_counter_bits received_errors; @@ -3111,7 +3111,7 @@ struct mlx5_ifc_query_vport_counter_out_bits { struct mlx5_ifc_traffic_counter_bits transmitted_eth_multicast; - u8 reserved_2[0xa00]; + u8 reserved_at_680[0xa00]; }; enum { @@ -3120,328 +3120,328 @@ enum { struct mlx5_ifc_query_vport_counter_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_2[0xf]; + u8 reserved_at_41[0xf]; u8 vport_number[0x10]; - u8 reserved_3[0x60]; + u8 reserved_at_60[0x60]; u8 clear[0x1]; - u8 reserved_4[0x1f]; + u8 reserved_at_c1[0x1f]; - u8 reserved_5[0x20]; + u8 reserved_at_e0[0x20]; }; struct mlx5_ifc_query_tis_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_tisc_bits tis_context; }; struct mlx5_ifc_query_tis_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 tisn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_tir_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0xc0]; + u8 reserved_at_40[0xc0]; struct mlx5_ifc_tirc_bits tir_context; }; struct mlx5_ifc_query_tir_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 tirn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_srq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_srqc_bits srq_context_entry; - u8 reserved_2[0x600]; + u8 reserved_at_280[0x600]; u8 pas[0][0x40]; }; struct mlx5_ifc_query_srq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 srqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_sq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0xc0]; + u8 reserved_at_40[0xc0]; struct mlx5_ifc_sqc_bits sq_context; }; struct mlx5_ifc_query_sq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 sqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_special_contexts_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x20]; + u8 reserved_at_40[0x20]; u8 resd_lkey[0x20]; }; struct mlx5_ifc_query_special_contexts_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_query_rqt_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0xc0]; + u8 reserved_at_40[0xc0]; struct mlx5_ifc_rqtc_bits rqt_context; }; struct mlx5_ifc_query_rqt_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 rqtn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_rq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0xc0]; + u8 reserved_at_40[0xc0]; struct mlx5_ifc_rqc_bits rq_context; }; struct mlx5_ifc_query_rq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 rqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_roce_address_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_roce_addr_layout_bits roce_address; }; struct mlx5_ifc_query_roce_address_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 roce_address_index[0x10]; - u8 reserved_2[0x10]; + u8 reserved_at_50[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_rmp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0xc0]; + u8 reserved_at_40[0xc0]; struct mlx5_ifc_rmpc_bits rmp_context; }; struct mlx5_ifc_query_rmp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 rmpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_qp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; u8 opt_param_mask[0x20]; - u8 reserved_2[0x20]; + u8 reserved_at_a0[0x20]; struct mlx5_ifc_qpc_bits qpc; - u8 reserved_3[0x80]; + u8 reserved_at_800[0x80]; u8 pas[0][0x40]; }; struct mlx5_ifc_query_qp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_q_counter_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; u8 rx_write_requests[0x20]; - u8 reserved_2[0x20]; + u8 reserved_at_a0[0x20]; u8 rx_read_requests[0x20]; - u8 reserved_3[0x20]; + u8 reserved_at_e0[0x20]; u8 rx_atomic_requests[0x20]; - u8 reserved_4[0x20]; + u8 reserved_at_120[0x20]; u8 rx_dct_connect[0x20]; - u8 reserved_5[0x20]; + u8 reserved_at_160[0x20]; u8 out_of_buffer[0x20]; - u8 reserved_6[0x20]; + u8 reserved_at_1a0[0x20]; u8 out_of_sequence[0x20]; - u8 reserved_7[0x620]; + u8 reserved_at_1e0[0x620]; }; struct mlx5_ifc_query_q_counter_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x80]; + u8 reserved_at_40[0x80]; u8 clear[0x1]; - u8 reserved_3[0x1f]; + u8 reserved_at_c1[0x1f]; - u8 reserved_4[0x18]; + u8 reserved_at_e0[0x18]; u8 counter_set_id[0x8]; }; struct mlx5_ifc_query_pages_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x10]; + u8 reserved_at_40[0x10]; u8 function_id[0x10]; u8 num_pages[0x20]; @@ -3455,55 +3455,55 @@ enum { struct mlx5_ifc_query_pages_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x10]; + u8 reserved_at_40[0x10]; u8 function_id[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_nic_vport_context_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_nic_vport_context_bits nic_vport_context; }; struct mlx5_ifc_query_nic_vport_context_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_2[0xf]; + u8 reserved_at_41[0xf]; u8 vport_number[0x10]; - u8 reserved_3[0x5]; + u8 reserved_at_60[0x5]; u8 allowed_list_type[0x3]; - u8 reserved_4[0x18]; + u8 reserved_at_68[0x18]; }; struct mlx5_ifc_query_mkey_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_mkc_bits memory_key_mkey_entry; - u8 reserved_2[0x600]; + u8 reserved_at_280[0x600]; u8 bsf0_klm0_pas_mtt0_1[16][0x8]; @@ -3512,265 +3512,265 @@ struct mlx5_ifc_query_mkey_out_bits { struct mlx5_ifc_query_mkey_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 mkey_index[0x18]; u8 pg_access[0x1]; - u8 reserved_3[0x1f]; + u8 reserved_at_61[0x1f]; }; struct mlx5_ifc_query_mad_demux_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; u8 mad_dumux_parameters_block[0x20]; }; struct mlx5_ifc_query_mad_demux_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_query_l2_table_entry_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0xa0]; + u8 reserved_at_40[0xa0]; - u8 reserved_2[0x13]; + u8 reserved_at_e0[0x13]; u8 vlan_valid[0x1]; u8 vlan[0xc]; struct mlx5_ifc_mac_address_layout_bits mac_address; - u8 reserved_3[0xc0]; + u8 reserved_at_140[0xc0]; }; struct mlx5_ifc_query_l2_table_entry_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x60]; + u8 reserved_at_40[0x60]; - u8 reserved_3[0x8]; + u8 reserved_at_a0[0x8]; u8 table_index[0x18]; - u8 reserved_4[0x140]; + u8 reserved_at_c0[0x140]; }; struct mlx5_ifc_query_issi_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x10]; + u8 reserved_at_40[0x10]; u8 current_issi[0x10]; - u8 reserved_2[0xa0]; + u8 reserved_at_60[0xa0]; - u8 supported_issi_reserved[76][0x8]; + u8 reserved_at_100[76][0x8]; u8 supported_issi_dw0[0x20]; }; struct mlx5_ifc_query_issi_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_query_hca_vport_pkey_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_pkey_bits pkey[0]; }; struct mlx5_ifc_query_hca_vport_pkey_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_2[0xb]; + u8 reserved_at_41[0xb]; u8 port_num[0x4]; u8 vport_number[0x10]; - u8 reserved_3[0x10]; + u8 reserved_at_60[0x10]; u8 pkey_index[0x10]; }; struct mlx5_ifc_query_hca_vport_gid_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x20]; + u8 reserved_at_40[0x20]; u8 gids_num[0x10]; - u8 reserved_2[0x10]; + u8 reserved_at_70[0x10]; struct mlx5_ifc_array128_auto_bits gid[0]; }; struct mlx5_ifc_query_hca_vport_gid_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_2[0xb]; + u8 reserved_at_41[0xb]; u8 port_num[0x4]; u8 vport_number[0x10]; - u8 reserved_3[0x10]; + u8 reserved_at_60[0x10]; u8 gid_index[0x10]; }; struct mlx5_ifc_query_hca_vport_context_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_hca_vport_context_bits hca_vport_context; }; struct mlx5_ifc_query_hca_vport_context_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_2[0xb]; + u8 reserved_at_41[0xb]; u8 port_num[0x4]; u8 vport_number[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_hca_cap_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; union mlx5_ifc_hca_cap_union_bits capability; }; struct mlx5_ifc_query_hca_cap_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_query_flow_table_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x80]; + u8 reserved_at_40[0x80]; - u8 reserved_2[0x8]; + u8 reserved_at_c0[0x8]; u8 level[0x8]; - u8 reserved_3[0x8]; + u8 reserved_at_d0[0x8]; u8 log_size[0x8]; - u8 reserved_4[0x120]; + u8 reserved_at_e0[0x120]; }; struct mlx5_ifc_query_flow_table_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; u8 table_type[0x8]; - u8 reserved_3[0x18]; + u8 reserved_at_88[0x18]; - u8 reserved_4[0x8]; + u8 reserved_at_a0[0x8]; u8 table_id[0x18]; - u8 reserved_5[0x140]; + u8 reserved_at_c0[0x140]; }; struct mlx5_ifc_query_fte_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x1c0]; + u8 reserved_at_40[0x1c0]; struct mlx5_ifc_flow_context_bits flow_context; }; struct mlx5_ifc_query_fte_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; u8 table_type[0x8]; - u8 reserved_3[0x18]; + u8 reserved_at_88[0x18]; - u8 reserved_4[0x8]; + u8 reserved_at_a0[0x8]; u8 table_id[0x18]; - u8 reserved_5[0x40]; + u8 reserved_at_c0[0x40]; u8 flow_index[0x20]; - u8 reserved_6[0xe0]; + u8 reserved_at_120[0xe0]; }; enum { @@ -3781,84 +3781,84 @@ enum { struct mlx5_ifc_query_flow_group_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0xa0]; + u8 reserved_at_40[0xa0]; u8 start_flow_index[0x20]; - u8 reserved_2[0x20]; + u8 reserved_at_100[0x20]; u8 end_flow_index[0x20]; - u8 reserved_3[0xa0]; + u8 reserved_at_140[0xa0]; - u8 reserved_4[0x18]; + u8 reserved_at_1e0[0x18]; u8 match_criteria_enable[0x8]; struct mlx5_ifc_fte_match_param_bits match_criteria; - u8 reserved_5[0xe00]; + u8 reserved_at_1200[0xe00]; }; struct mlx5_ifc_query_flow_group_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; u8 table_type[0x8]; - u8 reserved_3[0x18]; + u8 reserved_at_88[0x18]; - u8 reserved_4[0x8]; + u8 reserved_at_a0[0x8]; u8 table_id[0x18]; u8 group_id[0x20]; - u8 reserved_5[0x120]; + u8 reserved_at_e0[0x120]; }; struct mlx5_ifc_query_esw_vport_context_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_esw_vport_context_bits esw_vport_context; }; struct mlx5_ifc_query_esw_vport_context_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_2[0xf]; + u8 reserved_at_41[0xf]; u8 vport_number[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_modify_esw_vport_context_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_esw_vport_context_fields_select_bits { - u8 reserved[0x1c]; + u8 reserved_at_0[0x1c]; u8 vport_cvlan_insert[0x1]; u8 vport_svlan_insert[0x1]; u8 vport_cvlan_strip[0x1]; @@ -3867,13 +3867,13 @@ struct mlx5_ifc_esw_vport_context_fields_select_bits { struct mlx5_ifc_modify_esw_vport_context_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_2[0xf]; + u8 reserved_at_41[0xf]; u8 vport_number[0x10]; struct mlx5_ifc_esw_vport_context_fields_select_bits field_select; @@ -3883,124 +3883,124 @@ struct mlx5_ifc_modify_esw_vport_context_in_bits { struct mlx5_ifc_query_eq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_eqc_bits eq_context_entry; - u8 reserved_2[0x40]; + u8 reserved_at_280[0x40]; u8 event_bitmask[0x40]; - u8 reserved_3[0x580]; + u8 reserved_at_300[0x580]; u8 pas[0][0x40]; }; struct mlx5_ifc_query_eq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x18]; + u8 reserved_at_40[0x18]; u8 eq_number[0x8]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_dct_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_dctc_bits dct_context_entry; - u8 reserved_2[0x180]; + u8 reserved_at_280[0x180]; }; struct mlx5_ifc_query_dct_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 dctn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_cq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_cqc_bits cq_context; - u8 reserved_2[0x600]; + u8 reserved_at_280[0x600]; u8 pas[0][0x40]; }; struct mlx5_ifc_query_cq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 cqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_cong_status_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x20]; + u8 reserved_at_40[0x20]; u8 enable[0x1]; u8 tag_enable[0x1]; - u8 reserved_2[0x1e]; + u8 reserved_at_62[0x1e]; }; struct mlx5_ifc_query_cong_status_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x18]; + u8 reserved_at_40[0x18]; u8 priority[0x4]; u8 cong_protocol[0x4]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_cong_statistics_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; u8 cur_flows[0x20]; @@ -4014,7 +4014,7 @@ struct mlx5_ifc_query_cong_statistics_out_bits { u8 cnp_handled_low[0x20]; - u8 reserved_2[0x100]; + u8 reserved_at_140[0x100]; u8 time_stamp_high[0x20]; @@ -4030,453 +4030,453 @@ struct mlx5_ifc_query_cong_statistics_out_bits { u8 cnps_sent_low[0x20]; - u8 reserved_3[0x560]; + u8 reserved_at_320[0x560]; }; struct mlx5_ifc_query_cong_statistics_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 clear[0x1]; - u8 reserved_2[0x1f]; + u8 reserved_at_41[0x1f]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_cong_params_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; union mlx5_ifc_cong_control_roce_ecn_auto_bits congestion_parameters; }; struct mlx5_ifc_query_cong_params_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x1c]; + u8 reserved_at_40[0x1c]; u8 cong_protocol[0x4]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_adapter_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_query_adapter_param_block_bits query_adapter_struct; }; struct mlx5_ifc_query_adapter_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_qp_2rst_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_qp_2rst_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_qp_2err_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_qp_2err_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_page_fault_resume_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_page_fault_resume_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 error[0x1]; - u8 reserved_2[0x4]; + u8 reserved_at_41[0x4]; u8 rdma[0x1]; u8 read_write[0x1]; u8 req_res[0x1]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_nop_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_nop_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_modify_vport_state_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_modify_vport_state_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_2[0xf]; + u8 reserved_at_41[0xf]; u8 vport_number[0x10]; - u8 reserved_3[0x18]; + u8 reserved_at_60[0x18]; u8 admin_state[0x4]; - u8 reserved_4[0x4]; + u8 reserved_at_7c[0x4]; }; struct mlx5_ifc_modify_tis_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_modify_tis_bitmask_bits { - u8 reserved_0[0x20]; + u8 reserved_at_0[0x20]; - u8 reserved_1[0x1f]; + u8 reserved_at_20[0x1f]; u8 prio[0x1]; }; struct mlx5_ifc_modify_tis_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 tisn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; struct mlx5_ifc_modify_tis_bitmask_bits bitmask; - u8 reserved_4[0x40]; + u8 reserved_at_c0[0x40]; struct mlx5_ifc_tisc_bits ctx; }; struct mlx5_ifc_modify_tir_bitmask_bits { - u8 reserved_0[0x20]; + u8 reserved_at_0[0x20]; - u8 reserved_1[0x1b]; + u8 reserved_at_20[0x1b]; u8 self_lb_en[0x1]; - u8 reserved_2[0x3]; + u8 reserved_at_3c[0x3]; u8 lro[0x1]; }; struct mlx5_ifc_modify_tir_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_modify_tir_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 tirn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; struct mlx5_ifc_modify_tir_bitmask_bits bitmask; - u8 reserved_4[0x40]; + u8 reserved_at_c0[0x40]; struct mlx5_ifc_tirc_bits ctx; }; struct mlx5_ifc_modify_sq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_modify_sq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 sq_state[0x4]; - u8 reserved_2[0x4]; + u8 reserved_at_44[0x4]; u8 sqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 modify_bitmask[0x40]; - u8 reserved_4[0x40]; + u8 reserved_at_c0[0x40]; struct mlx5_ifc_sqc_bits ctx; }; struct mlx5_ifc_modify_rqt_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_rqt_bitmask_bits { - u8 reserved[0x20]; + u8 reserved_at_0[0x20]; - u8 reserved1[0x1f]; + u8 reserved_at_20[0x1f]; u8 rqn_list[0x1]; }; struct mlx5_ifc_modify_rqt_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 rqtn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; struct mlx5_ifc_rqt_bitmask_bits bitmask; - u8 reserved_4[0x40]; + u8 reserved_at_c0[0x40]; struct mlx5_ifc_rqtc_bits ctx; }; struct mlx5_ifc_modify_rq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_modify_rq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 rq_state[0x4]; - u8 reserved_2[0x4]; + u8 reserved_at_44[0x4]; u8 rqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 modify_bitmask[0x40]; - u8 reserved_4[0x40]; + u8 reserved_at_c0[0x40]; struct mlx5_ifc_rqc_bits ctx; }; struct mlx5_ifc_modify_rmp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_rmp_bitmask_bits { - u8 reserved[0x20]; + u8 reserved_at_0[0x20]; - u8 reserved1[0x1f]; + u8 reserved_at_20[0x1f]; u8 lwm[0x1]; }; struct mlx5_ifc_modify_rmp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 rmp_state[0x4]; - u8 reserved_2[0x4]; + u8 reserved_at_44[0x4]; u8 rmpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; struct mlx5_ifc_rmp_bitmask_bits bitmask; - u8 reserved_4[0x40]; + u8 reserved_at_c0[0x40]; struct mlx5_ifc_rmpc_bits ctx; }; struct mlx5_ifc_modify_nic_vport_context_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_modify_nic_vport_field_select_bits { - u8 reserved_0[0x19]; + u8 reserved_at_0[0x19]; u8 mtu[0x1]; u8 change_event[0x1]; u8 promisc[0x1]; u8 permanent_address[0x1]; u8 addresses_list[0x1]; u8 roce_en[0x1]; - u8 reserved_1[0x1]; + u8 reserved_at_1f[0x1]; }; struct mlx5_ifc_modify_nic_vport_context_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_2[0xf]; + u8 reserved_at_41[0xf]; u8 vport_number[0x10]; struct mlx5_ifc_modify_nic_vport_field_select_bits field_select; - u8 reserved_3[0x780]; + u8 reserved_at_80[0x780]; struct mlx5_ifc_nic_vport_context_bits nic_vport_context; }; struct mlx5_ifc_modify_hca_vport_context_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_modify_hca_vport_context_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_2[0xb]; + u8 reserved_at_41[0xb]; u8 port_num[0x4]; u8 vport_number[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; struct mlx5_ifc_hca_vport_context_bits hca_vport_context; }; struct mlx5_ifc_modify_cq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; enum { @@ -4486,83 +4486,83 @@ enum { struct mlx5_ifc_modify_cq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 cqn[0x18]; union mlx5_ifc_modify_field_select_resize_field_select_auto_bits modify_field_select_resize_field_select; struct mlx5_ifc_cqc_bits cq_context; - u8 reserved_3[0x600]; + u8 reserved_at_280[0x600]; u8 pas[0][0x40]; }; struct mlx5_ifc_modify_cong_status_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_modify_cong_status_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x18]; + u8 reserved_at_40[0x18]; u8 priority[0x4]; u8 cong_protocol[0x4]; u8 enable[0x1]; u8 tag_enable[0x1]; - u8 reserved_3[0x1e]; + u8 reserved_at_62[0x1e]; }; struct mlx5_ifc_modify_cong_params_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_modify_cong_params_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x1c]; + u8 reserved_at_40[0x1c]; u8 cong_protocol[0x4]; union mlx5_ifc_field_select_802_1_r_roce_auto_bits field_select; - u8 reserved_3[0x80]; + u8 reserved_at_80[0x80]; union mlx5_ifc_cong_control_roce_ecn_auto_bits congestion_parameters; }; struct mlx5_ifc_manage_pages_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; u8 output_num_entries[0x20]; - u8 reserved_1[0x20]; + u8 reserved_at_60[0x20]; u8 pas[0][0x40]; }; @@ -4575,12 +4575,12 @@ enum { struct mlx5_ifc_manage_pages_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x10]; + u8 reserved_at_40[0x10]; u8 function_id[0x10]; u8 input_num_entries[0x20]; @@ -4590,117 +4590,117 @@ struct mlx5_ifc_manage_pages_in_bits { struct mlx5_ifc_mad_ifc_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; u8 response_mad_packet[256][0x8]; }; struct mlx5_ifc_mad_ifc_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 remote_lid[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_50[0x8]; u8 port[0x8]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 mad[256][0x8]; }; struct mlx5_ifc_init_hca_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_init_hca_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_init2rtr_qp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_init2rtr_qp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 opt_param_mask[0x20]; - u8 reserved_4[0x20]; + u8 reserved_at_a0[0x20]; struct mlx5_ifc_qpc_bits qpc; - u8 reserved_5[0x80]; + u8 reserved_at_800[0x80]; }; struct mlx5_ifc_init2init_qp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_init2init_qp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 opt_param_mask[0x20]; - u8 reserved_4[0x20]; + u8 reserved_at_a0[0x20]; struct mlx5_ifc_qpc_bits qpc; - u8 reserved_5[0x80]; + u8 reserved_at_800[0x80]; }; struct mlx5_ifc_get_dropped_packet_log_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; u8 packet_headers_log[128][0x8]; @@ -4709,1029 +4709,1029 @@ struct mlx5_ifc_get_dropped_packet_log_out_bits { struct mlx5_ifc_get_dropped_packet_log_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_gen_eqe_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x18]; + u8 reserved_at_40[0x18]; u8 eq_number[0x8]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 eqe[64][0x8]; }; struct mlx5_ifc_gen_eq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_enable_hca_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x20]; + u8 reserved_at_40[0x20]; }; struct mlx5_ifc_enable_hca_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x10]; + u8 reserved_at_40[0x10]; u8 function_id[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_drain_dct_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_drain_dct_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 dctn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_disable_hca_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x20]; + u8 reserved_at_40[0x20]; }; struct mlx5_ifc_disable_hca_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x10]; + u8 reserved_at_40[0x10]; u8 function_id[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_detach_from_mcg_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_detach_from_mcg_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 multicast_gid[16][0x8]; }; struct mlx5_ifc_destroy_xrc_srq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_xrc_srq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 xrc_srqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_tis_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_tis_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 tisn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_tir_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_tir_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 tirn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_srq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_srq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 srqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_sq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_sq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 sqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_rqt_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_rqt_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 rqtn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_rq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_rq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 rqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_rmp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_rmp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 rmpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_qp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_qp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_psv_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_psv_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 psvn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_mkey_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_mkey_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 mkey_index[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_flow_table_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_flow_table_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; u8 table_type[0x8]; - u8 reserved_3[0x18]; + u8 reserved_at_88[0x18]; - u8 reserved_4[0x8]; + u8 reserved_at_a0[0x8]; u8 table_id[0x18]; - u8 reserved_5[0x140]; + u8 reserved_at_c0[0x140]; }; struct mlx5_ifc_destroy_flow_group_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_flow_group_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; u8 table_type[0x8]; - u8 reserved_3[0x18]; + u8 reserved_at_88[0x18]; - u8 reserved_4[0x8]; + u8 reserved_at_a0[0x8]; u8 table_id[0x18]; u8 group_id[0x20]; - u8 reserved_5[0x120]; + u8 reserved_at_e0[0x120]; }; struct mlx5_ifc_destroy_eq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_eq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x18]; + u8 reserved_at_40[0x18]; u8 eq_number[0x8]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_dct_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_dct_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 dctn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_cq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_cq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 cqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_delete_vxlan_udp_dport_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_delete_vxlan_udp_dport_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x20]; + u8 reserved_at_40[0x20]; - u8 reserved_3[0x10]; + u8 reserved_at_60[0x10]; u8 vxlan_udp_port[0x10]; }; struct mlx5_ifc_delete_l2_table_entry_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_delete_l2_table_entry_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x60]; + u8 reserved_at_40[0x60]; - u8 reserved_3[0x8]; + u8 reserved_at_a0[0x8]; u8 table_index[0x18]; - u8 reserved_4[0x140]; + u8 reserved_at_c0[0x140]; }; struct mlx5_ifc_delete_fte_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_delete_fte_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; u8 table_type[0x8]; - u8 reserved_3[0x18]; + u8 reserved_at_88[0x18]; - u8 reserved_4[0x8]; + u8 reserved_at_a0[0x8]; u8 table_id[0x18]; - u8 reserved_5[0x40]; + u8 reserved_at_c0[0x40]; u8 flow_index[0x20]; - u8 reserved_6[0xe0]; + u8 reserved_at_120[0xe0]; }; struct mlx5_ifc_dealloc_xrcd_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_dealloc_xrcd_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 xrcd[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_dealloc_uar_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_dealloc_uar_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 uar[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_dealloc_transport_domain_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_dealloc_transport_domain_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 transport_domain[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_dealloc_q_counter_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_dealloc_q_counter_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x18]; + u8 reserved_at_40[0x18]; u8 counter_set_id[0x8]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_dealloc_pd_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_dealloc_pd_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 pd[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_xrc_srq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 xrc_srqn[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_xrc_srq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry; - u8 reserved_3[0x600]; + u8 reserved_at_280[0x600]; u8 pas[0][0x40]; }; struct mlx5_ifc_create_tis_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 tisn[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_tis_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0xc0]; + u8 reserved_at_40[0xc0]; struct mlx5_ifc_tisc_bits ctx; }; struct mlx5_ifc_create_tir_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 tirn[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_tir_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0xc0]; + u8 reserved_at_40[0xc0]; struct mlx5_ifc_tirc_bits ctx; }; struct mlx5_ifc_create_srq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 srqn[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_srq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_srqc_bits srq_context_entry; - u8 reserved_3[0x600]; + u8 reserved_at_280[0x600]; u8 pas[0][0x40]; }; struct mlx5_ifc_create_sq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 sqn[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_sq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0xc0]; + u8 reserved_at_40[0xc0]; struct mlx5_ifc_sqc_bits ctx; }; struct mlx5_ifc_create_rqt_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 rqtn[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_rqt_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0xc0]; + u8 reserved_at_40[0xc0]; struct mlx5_ifc_rqtc_bits rqt_context; }; struct mlx5_ifc_create_rq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 rqn[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_rq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0xc0]; + u8 reserved_at_40[0xc0]; struct mlx5_ifc_rqc_bits ctx; }; struct mlx5_ifc_create_rmp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 rmpn[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_rmp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0xc0]; + u8 reserved_at_40[0xc0]; struct mlx5_ifc_rmpc_bits ctx; }; struct mlx5_ifc_create_qp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_qp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; u8 opt_param_mask[0x20]; - u8 reserved_3[0x20]; + u8 reserved_at_a0[0x20]; struct mlx5_ifc_qpc_bits qpc; - u8 reserved_4[0x80]; + u8 reserved_at_800[0x80]; u8 pas[0][0x40]; }; struct mlx5_ifc_create_psv_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; - u8 reserved_2[0x8]; + u8 reserved_at_80[0x8]; u8 psv0_index[0x18]; - u8 reserved_3[0x8]; + u8 reserved_at_a0[0x8]; u8 psv1_index[0x18]; - u8 reserved_4[0x8]; + u8 reserved_at_c0[0x8]; u8 psv2_index[0x18]; - u8 reserved_5[0x8]; + u8 reserved_at_e0[0x8]; u8 psv3_index[0x18]; }; struct mlx5_ifc_create_psv_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 num_psv[0x4]; - u8 reserved_2[0x4]; + u8 reserved_at_44[0x4]; u8 pd[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_mkey_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 mkey_index[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_mkey_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x20]; + u8 reserved_at_40[0x20]; u8 pg_access[0x1]; - u8 reserved_3[0x1f]; + u8 reserved_at_61[0x1f]; struct mlx5_ifc_mkc_bits memory_key_mkey_entry; - u8 reserved_4[0x80]; + u8 reserved_at_280[0x80]; u8 translations_octword_actual_size[0x20]; - u8 reserved_5[0x560]; + u8 reserved_at_320[0x560]; u8 klm_pas_mtt[0][0x20]; }; struct mlx5_ifc_create_flow_table_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 table_id[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_flow_table_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; u8 table_type[0x8]; - u8 reserved_3[0x18]; + u8 reserved_at_88[0x18]; - u8 reserved_4[0x20]; + u8 reserved_at_a0[0x20]; - u8 reserved_5[0x4]; + u8 reserved_at_c0[0x4]; u8 table_miss_mode[0x4]; u8 level[0x8]; - u8 reserved_6[0x8]; + u8 reserved_at_d0[0x8]; u8 log_size[0x8]; - u8 reserved_7[0x8]; + u8 reserved_at_e0[0x8]; u8 table_miss_id[0x18]; - u8 reserved_8[0x100]; + u8 reserved_at_100[0x100]; }; struct mlx5_ifc_create_flow_group_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 group_id[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; enum { @@ -5742,134 +5742,134 @@ enum { struct mlx5_ifc_create_flow_group_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; u8 table_type[0x8]; - u8 reserved_3[0x18]; + u8 reserved_at_88[0x18]; - u8 reserved_4[0x8]; + u8 reserved_at_a0[0x8]; u8 table_id[0x18]; - u8 reserved_5[0x20]; + u8 reserved_at_c0[0x20]; u8 start_flow_index[0x20]; - u8 reserved_6[0x20]; + u8 reserved_at_100[0x20]; u8 end_flow_index[0x20]; - u8 reserved_7[0xa0]; + u8 reserved_at_140[0xa0]; - u8 reserved_8[0x18]; + u8 reserved_at_1e0[0x18]; u8 match_criteria_enable[0x8]; struct mlx5_ifc_fte_match_param_bits match_criteria; - u8 reserved_9[0xe00]; + u8 reserved_at_1200[0xe00]; }; struct mlx5_ifc_create_eq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x18]; + u8 reserved_at_40[0x18]; u8 eq_number[0x8]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_eq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_eqc_bits eq_context_entry; - u8 reserved_3[0x40]; + u8 reserved_at_280[0x40]; u8 event_bitmask[0x40]; - u8 reserved_4[0x580]; + u8 reserved_at_300[0x580]; u8 pas[0][0x40]; }; struct mlx5_ifc_create_dct_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 dctn[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_dct_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_dctc_bits dct_context_entry; - u8 reserved_3[0x180]; + u8 reserved_at_280[0x180]; }; struct mlx5_ifc_create_cq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 cqn[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_cq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_cqc_bits cq_context; - u8 reserved_3[0x600]; + u8 reserved_at_280[0x600]; u8 pas[0][0x40]; }; struct mlx5_ifc_config_int_moderation_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x4]; + u8 reserved_at_40[0x4]; u8 min_delay[0xc]; u8 int_vector[0x10]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; enum { @@ -5879,49 +5879,49 @@ enum { struct mlx5_ifc_config_int_moderation_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x4]; + u8 reserved_at_40[0x4]; u8 min_delay[0xc]; u8 int_vector[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_attach_to_mcg_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_attach_to_mcg_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 multicast_gid[16][0x8]; }; struct mlx5_ifc_arm_xrc_srq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; enum { @@ -5930,25 +5930,25 @@ enum { struct mlx5_ifc_arm_xrc_srq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 xrc_srqn[0x18]; - u8 reserved_3[0x10]; + u8 reserved_at_60[0x10]; u8 lwm[0x10]; }; struct mlx5_ifc_arm_rq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; enum { @@ -5957,179 +5957,179 @@ enum { struct mlx5_ifc_arm_rq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 srq_number[0x18]; - u8 reserved_3[0x10]; + u8 reserved_at_60[0x10]; u8 lwm[0x10]; }; struct mlx5_ifc_arm_dct_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_arm_dct_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 dct_number[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_alloc_xrcd_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 xrcd[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_alloc_xrcd_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_alloc_uar_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 uar[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_alloc_uar_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_alloc_transport_domain_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 transport_domain[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_alloc_transport_domain_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_alloc_q_counter_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x18]; + u8 reserved_at_40[0x18]; u8 counter_set_id[0x8]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_alloc_q_counter_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_alloc_pd_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 pd[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_alloc_pd_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_add_vxlan_udp_dport_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_add_vxlan_udp_dport_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x20]; + u8 reserved_at_40[0x20]; - u8 reserved_3[0x10]; + u8 reserved_at_60[0x10]; u8 vxlan_udp_port[0x10]; }; struct mlx5_ifc_access_register_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; u8 register_data[0][0x20]; }; @@ -6141,12 +6141,12 @@ enum { struct mlx5_ifc_access_register_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x10]; + u8 reserved_at_40[0x10]; u8 register_id[0x10]; u8 argument[0x20]; @@ -6159,24 +6159,24 @@ struct mlx5_ifc_sltp_reg_bits { u8 version[0x4]; u8 local_port[0x8]; u8 pnat[0x2]; - u8 reserved_0[0x2]; + u8 reserved_at_12[0x2]; u8 lane[0x4]; - u8 reserved_1[0x8]; + u8 reserved_at_18[0x8]; - u8 reserved_2[0x20]; + u8 reserved_at_20[0x20]; - u8 reserved_3[0x7]; + u8 reserved_at_40[0x7]; u8 polarity[0x1]; u8 ob_tap0[0x8]; u8 ob_tap1[0x8]; u8 ob_tap2[0x8]; - u8 reserved_4[0xc]; + u8 reserved_at_60[0xc]; u8 ob_preemp_mode[0x4]; u8 ob_reg[0x8]; u8 ob_bias[0x8]; - u8 reserved_5[0x20]; + u8 reserved_at_80[0x20]; }; struct mlx5_ifc_slrg_reg_bits { @@ -6184,36 +6184,36 @@ struct mlx5_ifc_slrg_reg_bits { u8 version[0x4]; u8 local_port[0x8]; u8 pnat[0x2]; - u8 reserved_0[0x2]; + u8 reserved_at_12[0x2]; u8 lane[0x4]; - u8 reserved_1[0x8]; + u8 reserved_at_18[0x8]; u8 time_to_link_up[0x10]; - u8 reserved_2[0xc]; + u8 reserved_at_30[0xc]; u8 grade_lane_speed[0x4]; u8 grade_version[0x8]; u8 grade[0x18]; - u8 reserved_3[0x4]; + u8 reserved_at_60[0x4]; u8 height_grade_type[0x4]; u8 height_grade[0x18]; u8 height_dz[0x10]; u8 height_dv[0x10]; - u8 reserved_4[0x10]; + u8 reserved_at_a0[0x10]; u8 height_sigma[0x10]; - u8 reserved_5[0x20]; + u8 reserved_at_c0[0x20]; - u8 reserved_6[0x4]; + u8 reserved_at_e0[0x4]; u8 phase_grade_type[0x4]; u8 phase_grade[0x18]; - u8 reserved_7[0x8]; + u8 reserved_at_100[0x8]; u8 phase_eo_pos[0x8]; - u8 reserved_8[0x8]; + u8 reserved_at_110[0x8]; u8 phase_eo_neg[0x8]; u8 ffe_set_tested[0x10]; @@ -6221,70 +6221,70 @@ struct mlx5_ifc_slrg_reg_bits { }; struct mlx5_ifc_pvlc_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_2[0x1c]; + u8 reserved_at_20[0x1c]; u8 vl_hw_cap[0x4]; - u8 reserved_3[0x1c]; + u8 reserved_at_40[0x1c]; u8 vl_admin[0x4]; - u8 reserved_4[0x1c]; + u8 reserved_at_60[0x1c]; u8 vl_operational[0x4]; }; struct mlx5_ifc_pude_reg_bits { u8 swid[0x8]; u8 local_port[0x8]; - u8 reserved_0[0x4]; + u8 reserved_at_10[0x4]; u8 admin_status[0x4]; - u8 reserved_1[0x4]; + u8 reserved_at_18[0x4]; u8 oper_status[0x4]; - u8 reserved_2[0x60]; + u8 reserved_at_20[0x60]; }; struct mlx5_ifc_ptys_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0xd]; + u8 reserved_at_10[0xd]; u8 proto_mask[0x3]; - u8 reserved_2[0x40]; + u8 reserved_at_20[0x40]; u8 eth_proto_capability[0x20]; u8 ib_link_width_capability[0x10]; u8 ib_proto_capability[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_a0[0x20]; u8 eth_proto_admin[0x20]; u8 ib_link_width_admin[0x10]; u8 ib_proto_admin[0x10]; - u8 reserved_4[0x20]; + u8 reserved_at_100[0x20]; u8 eth_proto_oper[0x20]; u8 ib_link_width_oper[0x10]; u8 ib_proto_oper[0x10]; - u8 reserved_5[0x20]; + u8 reserved_at_160[0x20]; u8 eth_proto_lp_advertise[0x20]; - u8 reserved_6[0x60]; + u8 reserved_at_1a0[0x60]; }; struct mlx5_ifc_ptas_reg_bits { - u8 reserved_0[0x20]; + u8 reserved_at_0[0x20]; u8 algorithm_options[0x10]; - u8 reserved_1[0x4]; + u8 reserved_at_30[0x4]; u8 repetitions_mode[0x4]; u8 num_of_repetitions[0x8]; @@ -6310,13 +6310,13 @@ struct mlx5_ifc_ptas_reg_bits { u8 ndeo_error_threshold[0x10]; u8 mixer_offset_step_size[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_110[0x8]; u8 mix90_phase_for_voltage_bath[0x8]; u8 mixer_offset_start[0x10]; u8 mixer_offset_end[0x10]; - u8 reserved_3[0x15]; + u8 reserved_at_140[0x15]; u8 ber_test_time[0xb]; }; @@ -6324,154 +6324,154 @@ struct mlx5_ifc_pspa_reg_bits { u8 swid[0x8]; u8 local_port[0x8]; u8 sub_port[0x8]; - u8 reserved_0[0x8]; + u8 reserved_at_18[0x8]; - u8 reserved_1[0x20]; + u8 reserved_at_20[0x20]; }; struct mlx5_ifc_pqdr_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0x5]; + u8 reserved_at_10[0x5]; u8 prio[0x3]; - u8 reserved_2[0x6]; + u8 reserved_at_18[0x6]; u8 mode[0x2]; - u8 reserved_3[0x20]; + u8 reserved_at_20[0x20]; - u8 reserved_4[0x10]; + u8 reserved_at_40[0x10]; u8 min_threshold[0x10]; - u8 reserved_5[0x10]; + u8 reserved_at_60[0x10]; u8 max_threshold[0x10]; - u8 reserved_6[0x10]; + u8 reserved_at_80[0x10]; u8 mark_probability_denominator[0x10]; - u8 reserved_7[0x60]; + u8 reserved_at_a0[0x60]; }; struct mlx5_ifc_ppsc_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_2[0x60]; + u8 reserved_at_20[0x60]; - u8 reserved_3[0x1c]; + u8 reserved_at_80[0x1c]; u8 wrps_admin[0x4]; - u8 reserved_4[0x1c]; + u8 reserved_at_a0[0x1c]; u8 wrps_status[0x4]; - u8 reserved_5[0x8]; + u8 reserved_at_c0[0x8]; u8 up_threshold[0x8]; - u8 reserved_6[0x8]; + u8 reserved_at_d0[0x8]; u8 down_threshold[0x8]; - u8 reserved_7[0x20]; + u8 reserved_at_e0[0x20]; - u8 reserved_8[0x1c]; + u8 reserved_at_100[0x1c]; u8 srps_admin[0x4]; - u8 reserved_9[0x1c]; + u8 reserved_at_120[0x1c]; u8 srps_status[0x4]; - u8 reserved_10[0x40]; + u8 reserved_at_140[0x40]; }; struct mlx5_ifc_pplr_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_20[0x8]; u8 lb_cap[0x8]; - u8 reserved_3[0x8]; + u8 reserved_at_30[0x8]; u8 lb_en[0x8]; }; struct mlx5_ifc_pplm_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_2[0x20]; + u8 reserved_at_20[0x20]; u8 port_profile_mode[0x8]; u8 static_port_profile[0x8]; u8 active_port_profile[0x8]; - u8 reserved_3[0x8]; + u8 reserved_at_58[0x8]; u8 retransmission_active[0x8]; u8 fec_mode_active[0x18]; - u8 reserved_4[0x20]; + u8 reserved_at_80[0x20]; }; struct mlx5_ifc_ppcnt_reg_bits { u8 swid[0x8]; u8 local_port[0x8]; u8 pnat[0x2]; - u8 reserved_0[0x8]; + u8 reserved_at_12[0x8]; u8 grp[0x6]; u8 clr[0x1]; - u8 reserved_1[0x1c]; + u8 reserved_at_21[0x1c]; u8 prio_tc[0x3]; union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits counter_set; }; struct mlx5_ifc_ppad_reg_bits { - u8 reserved_0[0x3]; + u8 reserved_at_0[0x3]; u8 single_mac[0x1]; - u8 reserved_1[0x4]; + u8 reserved_at_4[0x4]; u8 local_port[0x8]; u8 mac_47_32[0x10]; u8 mac_31_0[0x20]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_pmtu_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; u8 max_mtu[0x10]; - u8 reserved_2[0x10]; + u8 reserved_at_30[0x10]; u8 admin_mtu[0x10]; - u8 reserved_3[0x10]; + u8 reserved_at_50[0x10]; u8 oper_mtu[0x10]; - u8 reserved_4[0x10]; + u8 reserved_at_70[0x10]; }; struct mlx5_ifc_pmpr_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 module[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_2[0x18]; + u8 reserved_at_20[0x18]; u8 attenuation_5g[0x8]; - u8 reserved_3[0x18]; + u8 reserved_at_40[0x18]; u8 attenuation_7g[0x8]; - u8 reserved_4[0x18]; + u8 reserved_at_60[0x18]; u8 attenuation_12g[0x8]; }; struct mlx5_ifc_pmpe_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 module[0x8]; - u8 reserved_1[0xc]; + u8 reserved_at_10[0xc]; u8 module_status[0x4]; - u8 reserved_2[0x60]; + u8 reserved_at_20[0x60]; }; struct mlx5_ifc_pmpc_reg_bits { @@ -6479,20 +6479,20 @@ struct mlx5_ifc_pmpc_reg_bits { }; struct mlx5_ifc_pmlpn_reg_bits { - u8 reserved_0[0x4]; + u8 reserved_at_0[0x4]; u8 mlpn_status[0x4]; u8 local_port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; u8 e[0x1]; - u8 reserved_2[0x1f]; + u8 reserved_at_21[0x1f]; }; struct mlx5_ifc_pmlp_reg_bits { u8 rxtx[0x1]; - u8 reserved_0[0x7]; + u8 reserved_at_1[0x7]; u8 local_port[0x8]; - u8 reserved_1[0x8]; + u8 reserved_at_10[0x8]; u8 width[0x8]; u8 lane0_module_mapping[0x20]; @@ -6503,36 +6503,36 @@ struct mlx5_ifc_pmlp_reg_bits { u8 lane3_module_mapping[0x20]; - u8 reserved_2[0x160]; + u8 reserved_at_a0[0x160]; }; struct mlx5_ifc_pmaos_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 module[0x8]; - u8 reserved_1[0x4]; + u8 reserved_at_10[0x4]; u8 admin_status[0x4]; - u8 reserved_2[0x4]; + u8 reserved_at_18[0x4]; u8 oper_status[0x4]; u8 ase[0x1]; u8 ee[0x1]; - u8 reserved_3[0x1c]; + u8 reserved_at_22[0x1c]; u8 e[0x2]; - u8 reserved_4[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_plpc_reg_bits { - u8 reserved_0[0x4]; + u8 reserved_at_0[0x4]; u8 profile_id[0xc]; - u8 reserved_1[0x4]; + u8 reserved_at_10[0x4]; u8 proto_mask[0x4]; - u8 reserved_2[0x8]; + u8 reserved_at_18[0x8]; - u8 reserved_3[0x10]; + u8 reserved_at_20[0x10]; u8 lane_speed[0x10]; - u8 reserved_4[0x17]; + u8 reserved_at_40[0x17]; u8 lpbf[0x1]; u8 fec_mode_policy[0x8]; @@ -6545,44 +6545,44 @@ struct mlx5_ifc_plpc_reg_bits { u8 retransmission_request_admin[0x8]; u8 fec_mode_request_admin[0x18]; - u8 reserved_5[0x80]; + u8 reserved_at_c0[0x80]; }; struct mlx5_ifc_plib_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0x8]; + u8 reserved_at_10[0x8]; u8 ib_port[0x8]; - u8 reserved_2[0x60]; + u8 reserved_at_20[0x60]; }; struct mlx5_ifc_plbf_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0xd]; + u8 reserved_at_10[0xd]; u8 lbf_mode[0x3]; - u8 reserved_2[0x20]; + u8 reserved_at_20[0x20]; }; struct mlx5_ifc_pipg_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; u8 dic[0x1]; - u8 reserved_2[0x19]; + u8 reserved_at_21[0x19]; u8 ipg[0x4]; - u8 reserved_3[0x2]; + u8 reserved_at_3e[0x2]; }; struct mlx5_ifc_pifr_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_2[0xe0]; + u8 reserved_at_20[0xe0]; u8 port_filter[8][0x20]; @@ -6590,36 +6590,36 @@ struct mlx5_ifc_pifr_reg_bits { }; struct mlx5_ifc_pfcc_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; u8 ppan[0x4]; - u8 reserved_2[0x4]; + u8 reserved_at_24[0x4]; u8 prio_mask_tx[0x8]; - u8 reserved_3[0x8]; + u8 reserved_at_30[0x8]; u8 prio_mask_rx[0x8]; u8 pptx[0x1]; u8 aptx[0x1]; - u8 reserved_4[0x6]; + u8 reserved_at_42[0x6]; u8 pfctx[0x8]; - u8 reserved_5[0x10]; + u8 reserved_at_50[0x10]; u8 pprx[0x1]; u8 aprx[0x1]; - u8 reserved_6[0x6]; + u8 reserved_at_62[0x6]; u8 pfcrx[0x8]; - u8 reserved_7[0x10]; + u8 reserved_at_70[0x10]; - u8 reserved_8[0x80]; + u8 reserved_at_80[0x80]; }; struct mlx5_ifc_pelc_reg_bits { u8 op[0x4]; - u8 reserved_0[0x4]; + u8 reserved_at_4[0x4]; u8 local_port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; u8 op_admin[0x8]; u8 op_capability[0x8]; @@ -6634,28 +6634,28 @@ struct mlx5_ifc_pelc_reg_bits { u8 active[0x40]; - u8 reserved_2[0x80]; + u8 reserved_at_140[0x80]; }; struct mlx5_ifc_peir_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_2[0xc]; + u8 reserved_at_20[0xc]; u8 error_count[0x4]; - u8 reserved_3[0x10]; + u8 reserved_at_30[0x10]; - u8 reserved_4[0xc]; + u8 reserved_at_40[0xc]; u8 lane[0x4]; - u8 reserved_5[0x8]; + u8 reserved_at_50[0x8]; u8 error_type[0x8]; }; struct mlx5_ifc_pcap_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; u8 port_capability_mask[4][0x20]; }; @@ -6663,46 +6663,46 @@ struct mlx5_ifc_pcap_reg_bits { struct mlx5_ifc_paos_reg_bits { u8 swid[0x8]; u8 local_port[0x8]; - u8 reserved_0[0x4]; + u8 reserved_at_10[0x4]; u8 admin_status[0x4]; - u8 reserved_1[0x4]; + u8 reserved_at_18[0x4]; u8 oper_status[0x4]; u8 ase[0x1]; u8 ee[0x1]; - u8 reserved_2[0x1c]; + u8 reserved_at_22[0x1c]; u8 e[0x2]; - u8 reserved_3[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_pamp_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 opamp_group[0x8]; - u8 reserved_1[0xc]; + u8 reserved_at_10[0xc]; u8 opamp_group_type[0x4]; u8 start_index[0x10]; - u8 reserved_2[0x4]; + u8 reserved_at_30[0x4]; u8 num_of_indices[0xc]; u8 index_data[18][0x10]; }; struct mlx5_ifc_lane_2_module_mapping_bits { - u8 reserved_0[0x6]; + u8 reserved_at_0[0x6]; u8 rx_lane[0x2]; - u8 reserved_1[0x6]; + u8 reserved_at_8[0x6]; u8 tx_lane[0x2]; - u8 reserved_2[0x8]; + u8 reserved_at_10[0x8]; u8 module[0x8]; }; struct mlx5_ifc_bufferx_reg_bits { - u8 reserved_0[0x6]; + u8 reserved_at_0[0x6]; u8 lossy[0x1]; u8 epsb[0x1]; - u8 reserved_1[0xc]; + u8 reserved_at_8[0xc]; u8 size[0xc]; u8 xoff_threshold[0x10]; @@ -6714,21 +6714,21 @@ struct mlx5_ifc_set_node_in_bits { }; struct mlx5_ifc_register_power_settings_bits { - u8 reserved_0[0x18]; + u8 reserved_at_0[0x18]; u8 power_settings_level[0x8]; - u8 reserved_1[0x60]; + u8 reserved_at_20[0x60]; }; struct mlx5_ifc_register_host_endianness_bits { u8 he[0x1]; - u8 reserved_0[0x1f]; + u8 reserved_at_1[0x1f]; - u8 reserved_1[0x60]; + u8 reserved_at_20[0x60]; }; struct mlx5_ifc_umr_pointer_desc_argument_bits { - u8 reserved_0[0x20]; + u8 reserved_at_0[0x20]; u8 mkey[0x20]; @@ -6741,7 +6741,7 @@ struct mlx5_ifc_ud_adrs_vector_bits { u8 dc_key[0x40]; u8 ext[0x1]; - u8 reserved_0[0x7]; + u8 reserved_at_41[0x7]; u8 destination_qp_dct[0x18]; u8 static_rate[0x4]; @@ -6750,7 +6750,7 @@ struct mlx5_ifc_ud_adrs_vector_bits { u8 mlid[0x7]; u8 rlid_udp_sport[0x10]; - u8 reserved_1[0x20]; + u8 reserved_at_80[0x20]; u8 rmac_47_16[0x20]; @@ -6758,9 +6758,9 @@ struct mlx5_ifc_ud_adrs_vector_bits { u8 tclass[0x8]; u8 hop_limit[0x8]; - u8 reserved_2[0x1]; + u8 reserved_at_e0[0x1]; u8 grh[0x1]; - u8 reserved_3[0x2]; + u8 reserved_at_e2[0x2]; u8 src_addr_index[0x8]; u8 flow_label[0x14]; @@ -6768,27 +6768,27 @@ struct mlx5_ifc_ud_adrs_vector_bits { }; struct mlx5_ifc_pages_req_event_bits { - u8 reserved_0[0x10]; + u8 reserved_at_0[0x10]; u8 function_id[0x10]; u8 num_pages[0x20]; - u8 reserved_1[0xa0]; + u8 reserved_at_40[0xa0]; }; struct mlx5_ifc_eqe_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 event_type[0x8]; - u8 reserved_1[0x8]; + u8 reserved_at_10[0x8]; u8 event_sub_type[0x8]; - u8 reserved_2[0xe0]; + u8 reserved_at_20[0xe0]; union mlx5_ifc_event_auto_bits event_data; - u8 reserved_3[0x10]; + u8 reserved_at_1e0[0x10]; u8 signature[0x8]; - u8 reserved_4[0x7]; + u8 reserved_at_1f8[0x7]; u8 owner[0x1]; }; @@ -6798,14 +6798,14 @@ enum { struct mlx5_ifc_cmd_queue_entry_bits { u8 type[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 input_length[0x20]; u8 input_mailbox_pointer_63_32[0x20]; u8 input_mailbox_pointer_31_9[0x17]; - u8 reserved_1[0x9]; + u8 reserved_at_77[0x9]; u8 command_input_inline_data[16][0x8]; @@ -6814,20 +6814,20 @@ struct mlx5_ifc_cmd_queue_entry_bits { u8 output_mailbox_pointer_63_32[0x20]; u8 output_mailbox_pointer_31_9[0x17]; - u8 reserved_2[0x9]; + u8 reserved_at_1b7[0x9]; u8 output_length[0x20]; u8 token[0x8]; u8 signature[0x8]; - u8 reserved_3[0x8]; + u8 reserved_at_1f0[0x8]; u8 status[0x7]; u8 ownership[0x1]; }; struct mlx5_ifc_cmd_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; @@ -6836,9 +6836,9 @@ struct mlx5_ifc_cmd_out_bits { struct mlx5_ifc_cmd_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 command[0][0x20]; @@ -6847,16 +6847,16 @@ struct mlx5_ifc_cmd_in_bits { struct mlx5_ifc_cmd_if_box_bits { u8 mailbox_data[512][0x8]; - u8 reserved_0[0x180]; + u8 reserved_at_1000[0x180]; u8 next_pointer_63_32[0x20]; u8 next_pointer_31_10[0x16]; - u8 reserved_1[0xa]; + u8 reserved_at_11b6[0xa]; u8 block_number[0x20]; - u8 reserved_2[0x8]; + u8 reserved_at_11e0[0x8]; u8 token[0x8]; u8 ctrl_signature[0x8]; u8 signature[0x8]; @@ -6866,7 +6866,7 @@ struct mlx5_ifc_mtt_bits { u8 ptag_63_32[0x20]; u8 ptag_31_8[0x18]; - u8 reserved_0[0x6]; + u8 reserved_at_38[0x6]; u8 wr_en[0x1]; u8 rd_en[0x1]; }; @@ -6904,38 +6904,38 @@ struct mlx5_ifc_initial_seg_bits { u8 cmd_interface_rev[0x10]; u8 fw_rev_subminor[0x10]; - u8 reserved_0[0x40]; + u8 reserved_at_40[0x40]; u8 cmdq_phy_addr_63_32[0x20]; u8 cmdq_phy_addr_31_12[0x14]; - u8 reserved_1[0x2]; + u8 reserved_at_b4[0x2]; u8 nic_interface[0x2]; u8 log_cmdq_size[0x4]; u8 log_cmdq_stride[0x4]; u8 command_doorbell_vector[0x20]; - u8 reserved_2[0xf00]; + u8 reserved_at_e0[0xf00]; u8 initializing[0x1]; - u8 reserved_3[0x4]; + u8 reserved_at_fe1[0x4]; u8 nic_interface_supported[0x3]; - u8 reserved_4[0x18]; + u8 reserved_at_fe8[0x18]; struct mlx5_ifc_health_buffer_bits health_buffer; u8 no_dram_nic_offset[0x20]; - u8 reserved_5[0x6e40]; + u8 reserved_at_1220[0x6e40]; - u8 reserved_6[0x1f]; + u8 reserved_at_8060[0x1f]; u8 clear_int[0x1]; u8 health_syndrome[0x8]; u8 health_counter[0x18]; - u8 reserved_7[0x17fc0]; + u8 reserved_at_80a0[0x17fc0]; }; union mlx5_ifc_ports_control_registers_document_bits { @@ -6980,44 +6980,44 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_pvlc_reg_bits pvlc_reg; struct mlx5_ifc_slrg_reg_bits slrg_reg; struct mlx5_ifc_sltp_reg_bits sltp_reg; - u8 reserved_0[0x60e0]; + u8 reserved_at_0[0x60e0]; }; union mlx5_ifc_debug_enhancements_document_bits { struct mlx5_ifc_health_buffer_bits health_buffer; - u8 reserved_0[0x200]; + u8 reserved_at_0[0x200]; }; union mlx5_ifc_uplink_pci_interface_document_bits { struct mlx5_ifc_initial_seg_bits initial_seg; - u8 reserved_0[0x20060]; + u8 reserved_at_0[0x20060]; }; struct mlx5_ifc_set_flow_table_root_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_set_flow_table_root_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; u8 table_type[0x8]; - u8 reserved_3[0x18]; + u8 reserved_at_88[0x18]; - u8 reserved_4[0x8]; + u8 reserved_at_a0[0x8]; u8 table_id[0x18]; - u8 reserved_5[0x140]; + u8 reserved_at_c0[0x140]; }; enum { @@ -7026,39 +7026,39 @@ enum { struct mlx5_ifc_modify_flow_table_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_modify_flow_table_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x20]; + u8 reserved_at_40[0x20]; - u8 reserved_3[0x10]; + u8 reserved_at_60[0x10]; u8 modify_field_select[0x10]; u8 table_type[0x8]; - u8 reserved_4[0x18]; + u8 reserved_at_88[0x18]; - u8 reserved_5[0x8]; + u8 reserved_at_a0[0x8]; u8 table_id[0x18]; - u8 reserved_6[0x4]; + u8 reserved_at_c0[0x4]; u8 table_miss_mode[0x4]; - u8 reserved_7[0x18]; + u8 reserved_at_c8[0x18]; - u8 reserved_8[0x8]; + u8 reserved_at_e0[0x8]; u8 table_miss_id[0x18]; - u8 reserved_9[0x100]; + u8 reserved_at_100[0x100]; }; #endif /* MLX5_IFC_H */ -- cgit v1.2.3 From 85743f1eb34548ba4b056d2f184a3d107a3b8917 Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Wed, 17 Feb 2016 17:24:26 +0200 Subject: net/mlx4_core: Set UAR page size to 4KB regardless of system page size problem description: The current code sets UAR page size equal to system page size. The ConnectX-3 and ConnectX-3 Pro HWs require minimum 128 UAR pages. The mlx4 kernel drivers are not loaded if there is less than 128 UAR pages. solution: Always set UAR page to 4KB. This allows more UAR pages if the OS has PAGE_SIZE larger than 4KB. For example, PowerPC kernel use 64KB system page size, with 4MB uar region, there are 4MB/2/64KB = 32 uars (half for uar, half for blueflame). This does not meet minimum 128 UAR pages requirement. With 4KB UAR page, there are 4MB/2/4KB = 512 uars which meet the minimum requirement. Note that only codes in mlx4_core that deal with firmware know that uar page size is 4KB. Codes that deal with usr page in cq and qp context (mlx4_ib, mlx4_en and part of mlx4_core) still have the same assumption that uar page size equals to system page size. Note that with this implementation, on 64KB system page size kernel, there are 16 uars per system page but only one uars is used. The other 15 uars are ignored because of the above assumption. Regarding SR-IOV, mlx4_core in hypervisor will set the uar page size to 4KB and mlx4_core code in virtual OS will obtain the uar page size from firmware. Regarding backward compatibility in SR-IOV, if hypervisor has this new code, the virtual OS must be updated. If hypervisor has old code, and the virtual OS has this new code, the new code will be backward compatible with the old code. If the uar size is big enough, this new code in VF continues to work with 64 KB uar page size (on PowerPc kernel). If the uar size does not meet 128 uars requirement, this new code not loaded in VF and print the same error message as the old code in Hypervisor. Signed-off-by: Huy Nguyen Reviewed-by: Yishai Hadas Signed-off-by: David S. Miller --- drivers/infiniband/hw/mlx4/qp.c | 7 ++- drivers/net/ethernet/mellanox/mlx4/cq.c | 4 +- drivers/net/ethernet/mellanox/mlx4/en_resources.c | 3 +- drivers/net/ethernet/mellanox/mlx4/en_tx.c | 4 +- drivers/net/ethernet/mellanox/mlx4/eq.c | 7 +-- drivers/net/ethernet/mellanox/mlx4/main.c | 56 ++++++++++++++++++----- drivers/net/ethernet/mellanox/mlx4/pd.c | 12 +++-- include/linux/mlx4/device.h | 13 ++++++ 8 files changed, 84 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index bc5536f00b6c..fd97534762b8 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -1681,9 +1681,12 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, } if (qp->ibqp.uobject) - context->usr_page = cpu_to_be32(to_mucontext(ibqp->uobject->context)->uar.index); + context->usr_page = cpu_to_be32( + mlx4_to_hw_uar_index(dev->dev, + to_mucontext(ibqp->uobject->context)->uar.index)); else - context->usr_page = cpu_to_be32(dev->priv_uar.index); + context->usr_page = cpu_to_be32( + mlx4_to_hw_uar_index(dev->dev, dev->priv_uar.index)); if (attr_mask & IB_QP_DEST_QPN) context->remote_qpn = cpu_to_be32(attr->dest_qp_num); diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c index 3348e646db70..a849da92f857 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/cq.c @@ -318,7 +318,9 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, if (timestamp_en) cq_context->flags |= cpu_to_be32(1 << 19); - cq_context->logsize_usrpage = cpu_to_be32((ilog2(nent) << 24) | uar->index); + cq_context->logsize_usrpage = + cpu_to_be32((ilog2(nent) << 24) | + mlx4_to_hw_uar_index(dev, uar->index)); cq_context->comp_eqn = priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(vector)].eqn; cq_context->log_page_size = mtt->page_shift - MLX4_ICM_PAGE_SHIFT; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_resources.c b/drivers/net/ethernet/mellanox/mlx4/en_resources.c index 12aab5a659d3..02e925d6f734 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_resources.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_resources.c @@ -58,7 +58,8 @@ void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride, } else { context->sq_size_stride = ilog2(TXBB_SIZE) - 4; } - context->usr_page = cpu_to_be32(mdev->priv_uar.index); + context->usr_page = cpu_to_be32(mlx4_to_hw_uar_index(mdev->dev, + mdev->priv_uar.index)); context->local_qpn = cpu_to_be32(qpn); context->pri_path.ackto = 1 & 0x07; context->pri_path.sched_queue = 0x83 | (priv->port - 1) << 6; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 4421bf5463f6..e0946ab22010 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -213,7 +213,9 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv, mlx4_en_fill_qp_context(priv, ring->size, ring->stride, 1, 0, ring->qpn, ring->cqn, user_prio, &ring->context); if (ring->bf_alloced) - ring->context.usr_page = cpu_to_be32(ring->bf.uar->index); + ring->context.usr_page = + cpu_to_be32(mlx4_to_hw_uar_index(mdev->dev, + ring->bf.uar->index)); err = mlx4_qp_to_ready(mdev->dev, &ring->wqres.mtt, &ring->context, &ring->qp, &ring->qp_state); diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index 4696053165f8..f613977455e0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -940,9 +940,10 @@ static void __iomem *mlx4_get_eq_uar(struct mlx4_dev *dev, struct mlx4_eq *eq) if (!priv->eq_table.uar_map[index]) { priv->eq_table.uar_map[index] = - ioremap(pci_resource_start(dev->persist->pdev, 2) + - ((eq->eqn / 4) << PAGE_SHIFT), - PAGE_SIZE); + ioremap( + pci_resource_start(dev->persist->pdev, 2) + + ((eq->eqn / 4) << (dev->uar_page_shift)), + (1 << (dev->uar_page_shift))); if (!priv->eq_table.uar_map[index]) { mlx4_err(dev, "Couldn't map EQ doorbell for EQN 0x%06x\n", eq->eqn); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index f1b6d219e445..2cc3c626c3fe 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -168,6 +168,20 @@ struct mlx4_port_config { static atomic_t pf_loading = ATOMIC_INIT(0); +static inline void mlx4_set_num_reserved_uars(struct mlx4_dev *dev, + struct mlx4_dev_cap *dev_cap) +{ + /* The reserved_uars is calculated by system page size unit. + * Therefore, adjustment is added when the uar page size is less + * than the system page size + */ + dev->caps.reserved_uars = + max_t(int, + mlx4_get_num_reserved_uar(dev), + dev_cap->reserved_uars / + (1 << (PAGE_SHIFT - dev->uar_page_shift))); +} + int mlx4_check_port_params(struct mlx4_dev *dev, enum mlx4_port_type *port_type) { @@ -386,8 +400,6 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev->caps.reserved_mtts = dev_cap->reserved_mtts; dev->caps.reserved_mrws = dev_cap->reserved_mrws; - /* The first 128 UARs are used for EQ doorbells */ - dev->caps.reserved_uars = max_t(int, 128, dev_cap->reserved_uars); dev->caps.reserved_pds = dev_cap->reserved_pds; dev->caps.reserved_xrcds = (dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC) ? dev_cap->reserved_xrcds : 0; @@ -405,6 +417,15 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev->caps.max_gso_sz = dev_cap->max_gso_sz; dev->caps.max_rss_tbl_sz = dev_cap->max_rss_tbl_sz; + /* Save uar page shift */ + if (!mlx4_is_slave(dev)) { + /* Virtual PCI function needs to determine UAR page size from + * firmware. Only master PCI function can set the uar page size + */ + dev->uar_page_shift = DEFAULT_UAR_PAGE_SHIFT; + mlx4_set_num_reserved_uars(dev, dev_cap); + } + if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PHV_EN) { struct mlx4_init_hca_param hca_param; @@ -815,16 +836,25 @@ static int mlx4_slave_cap(struct mlx4_dev *dev) return -ENODEV; } - /* slave gets uar page size from QUERY_HCA fw command */ - dev->caps.uar_page_size = 1 << (hca_param.uar_page_sz + 12); + /* Set uar_page_shift for VF */ + dev->uar_page_shift = hca_param.uar_page_sz + 12; - /* TODO: relax this assumption */ - if (dev->caps.uar_page_size != PAGE_SIZE) { - mlx4_err(dev, "UAR size:%d != kernel PAGE_SIZE of %ld\n", - dev->caps.uar_page_size, PAGE_SIZE); - return -ENODEV; + /* Make sure the master uar page size is valid */ + if (dev->uar_page_shift > PAGE_SHIFT) { + mlx4_err(dev, + "Invalid configuration: uar page size is larger than system page size\n"); + return -ENODEV; } + /* Set reserved_uars based on the uar_page_shift */ + mlx4_set_num_reserved_uars(dev, &dev_cap); + + /* Although uar page size in FW differs from system page size, + * upper software layers (mlx4_ib, mlx4_en and part of mlx4_core) + * still works with assumption that uar page size == system page size + */ + dev->caps.uar_page_size = PAGE_SIZE; + memset(&func_cap, 0, sizeof(func_cap)); err = mlx4_QUERY_FUNC_CAP(dev, 0, &func_cap); if (err) { @@ -2179,8 +2209,12 @@ static int mlx4_init_hca(struct mlx4_dev *dev) dev->caps.max_fmr_maps = (1 << (32 - ilog2(dev->caps.num_mpts))) - 1; - init_hca.log_uar_sz = ilog2(dev->caps.num_uars); - init_hca.uar_page_sz = PAGE_SHIFT - 12; + /* Always set UAR page size 4KB, set log_uar_sz accordingly */ + init_hca.log_uar_sz = ilog2(dev->caps.num_uars) + + PAGE_SHIFT - + DEFAULT_UAR_PAGE_SHIFT; + init_hca.uar_page_sz = DEFAULT_UAR_PAGE_SHIFT - 12; + init_hca.mw_enabled = 0; if (dev->caps.flags & MLX4_DEV_CAP_FLAG_MEM_WINDOW || dev->caps.bmme_flags & MLX4_BMME_FLAG_TYPE_2_WIN) diff --git a/drivers/net/ethernet/mellanox/mlx4/pd.c b/drivers/net/ethernet/mellanox/mlx4/pd.c index 609c59dc854e..b3cc3ab63799 100644 --- a/drivers/net/ethernet/mellanox/mlx4/pd.c +++ b/drivers/net/ethernet/mellanox/mlx4/pd.c @@ -269,9 +269,15 @@ EXPORT_SYMBOL_GPL(mlx4_bf_free); int mlx4_init_uar_table(struct mlx4_dev *dev) { - if (dev->caps.num_uars <= 128) { - mlx4_err(dev, "Only %d UAR pages (need more than 128)\n", - dev->caps.num_uars); + int num_reserved_uar = mlx4_get_num_reserved_uar(dev); + + mlx4_dbg(dev, "uar_page_shift = %d", dev->uar_page_shift); + mlx4_dbg(dev, "Effective reserved_uars=%d", dev->caps.reserved_uars); + + if (dev->caps.num_uars <= num_reserved_uar) { + mlx4_err( + dev, "Only %d UAR pages (need more than %d)\n", + dev->caps.num_uars, num_reserved_uar); mlx4_err(dev, "Increase firmware log2_uar_bar_megabytes?\n"); return -ENODEV; } diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 430a929f048b..a0e8cc8dcc67 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -44,6 +44,8 @@ #include +#define DEFAULT_UAR_PAGE_SHIFT 12 + #define MAX_MSIX_P_PORT 17 #define MAX_MSIX 64 #define MIN_MSIX_P_PORT 5 @@ -856,6 +858,7 @@ struct mlx4_dev { u64 regid_promisc_array[MLX4_MAX_PORTS + 1]; u64 regid_allmulti_array[MLX4_MAX_PORTS + 1]; struct mlx4_vf_dev *dev_vfs; + u8 uar_page_shift; }; struct mlx4_clock_params { @@ -1528,4 +1531,14 @@ int mlx4_ACCESS_PTYS_REG(struct mlx4_dev *dev, int mlx4_get_internal_clock_params(struct mlx4_dev *dev, struct mlx4_clock_params *params); +static inline int mlx4_to_hw_uar_index(struct mlx4_dev *dev, int index) +{ + return (index << (PAGE_SHIFT - dev->uar_page_shift)); +} + +static inline int mlx4_get_num_reserved_uar(struct mlx4_dev *dev) +{ + /* The first 128 UARs are used for EQ doorbells */ + return (128 >> (PAGE_SHIFT - dev->uar_page_shift)); +} #endif /* MLX4_DEVICE_H */ -- cgit v1.2.3 From 7dcd182bec271ab341b05b66b6006995795fc0e7 Mon Sep 17 00:00:00 2001 From: Jessica Yu Date: Tue, 16 Feb 2016 17:32:33 -0500 Subject: ftrace/module: remove ftrace module notifier Remove the ftrace module notifier in favor of directly calling ftrace_module_enable() and ftrace_release_mod() in the module loader. Hard-coding the function calls directly in the module loader removes dependence on the module notifier call chain and provides better visibility and control over what gets called when, which is important to kernel utilities such as livepatch. This fixes a notifier ordering issue in which the ftrace module notifier (and hence ftrace_module_enable()) for coming modules was being called after klp_module_notify(), which caused livepatch modules to initialize incorrectly. This patch removes dependence on the module notifier call chain in favor of hard coding the corresponding function calls in the module loader. This ensures that ftrace and livepatch code get called in the correct order on patch module load and unload. Fixes: 5156dca34a3e ("ftrace: Fix the race between ftrace and insmod") Signed-off-by: Jessica Yu Reviewed-by: Steven Rostedt Reviewed-by: Petr Mladek Acked-by: Rusty Russell Reviewed-by: Josh Poimboeuf Reviewed-by: Miroslav Benes Signed-off-by: Jiri Kosina --- include/linux/ftrace.h | 6 ++++-- kernel/module.c | 4 ++++ kernel/trace/ftrace.c | 36 +----------------------------------- 3 files changed, 9 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 0639dcc98195..76dc15e171eb 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -604,6 +604,7 @@ extern int ftrace_arch_read_dyn_info(char *buf, int size); extern int skip_trace(unsigned long ip); extern void ftrace_module_init(struct module *mod); +extern void ftrace_module_enable(struct module *mod); extern void ftrace_release_mod(struct module *mod); extern void ftrace_disable_daemon(void); @@ -613,8 +614,9 @@ static inline int skip_trace(unsigned long ip) { return 0; } static inline int ftrace_force_update(void) { return 0; } static inline void ftrace_disable_daemon(void) { } static inline void ftrace_enable_daemon(void) { } -static inline void ftrace_release_mod(struct module *mod) {} -static inline void ftrace_module_init(struct module *mod) {} +static inline void ftrace_module_init(struct module *mod) { } +static inline void ftrace_module_enable(struct module *mod) { } +static inline void ftrace_release_mod(struct module *mod) { } static inline __init int register_ftrace_command(struct ftrace_func_command *cmd) { return -EINVAL; diff --git a/kernel/module.c b/kernel/module.c index 8358f4697c0c..b05d466cfa02 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -981,6 +981,8 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, mod->exit(); blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_GOING, mod); + ftrace_release_mod(mod); + async_synchronize_full(); /* Store the name of the last unloaded module for diagnostic purposes */ @@ -3295,6 +3297,7 @@ fail: module_put(mod); blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_GOING, mod); + ftrace_release_mod(mod); free_module(mod); wake_up_all(&module_wq); return ret; @@ -3371,6 +3374,7 @@ static int complete_formation(struct module *mod, struct load_info *info) mod->state = MODULE_STATE_COMING; mutex_unlock(&module_mutex); + ftrace_module_enable(mod); blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_COMING, mod); return 0; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index eca592f977b2..57a6eea84694 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4961,7 +4961,7 @@ void ftrace_release_mod(struct module *mod) mutex_unlock(&ftrace_lock); } -static void ftrace_module_enable(struct module *mod) +void ftrace_module_enable(struct module *mod) { struct dyn_ftrace *rec; struct ftrace_page *pg; @@ -5038,38 +5038,8 @@ void ftrace_module_init(struct module *mod) ftrace_process_locs(mod, mod->ftrace_callsites, mod->ftrace_callsites + mod->num_ftrace_callsites); } - -static int ftrace_module_notify(struct notifier_block *self, - unsigned long val, void *data) -{ - struct module *mod = data; - - switch (val) { - case MODULE_STATE_COMING: - ftrace_module_enable(mod); - break; - case MODULE_STATE_GOING: - ftrace_release_mod(mod); - break; - default: - break; - } - - return 0; -} -#else -static int ftrace_module_notify(struct notifier_block *self, - unsigned long val, void *data) -{ - return 0; -} #endif /* CONFIG_MODULES */ -struct notifier_block ftrace_module_nb = { - .notifier_call = ftrace_module_notify, - .priority = INT_MIN, /* Run after anything that can remove kprobes */ -}; - void __init ftrace_init(void) { extern unsigned long __start_mcount_loc[]; @@ -5098,10 +5068,6 @@ void __init ftrace_init(void) __start_mcount_loc, __stop_mcount_loc); - ret = register_module_notifier(&ftrace_module_nb); - if (ret) - pr_warning("Failed to register trace ftrace module exit notifier\n"); - set_ftrace_early_filters(); return; -- cgit v1.2.3 From 13d34ac6e55b8284c592c67e166ac614b3c4c1d7 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 17 Feb 2016 13:11:18 -0800 Subject: Revert "fsnotify: destroy marks with call_srcu instead of dedicated thread" This reverts commit c510eff6beba ("fsnotify: destroy marks with call_srcu instead of dedicated thread"). Eryu reported that he was seeing some OOM kills kick in when running a testcase that adds and removes inotify marks on a file in a tight loop. The above commit changed the code to use call_srcu to clean up the marks. While that does (in principle) work, the srcu callback job is limited to cleaning up entries in small batches and only once per jiffy. It's easily possible to overwhelm that machinery with too many call_srcu callbacks, and Eryu's reproduer did just that. There's also another potential problem with using call_srcu here. While you can obviously sleep while holding the srcu_read_lock, the callbacks run under local_bh_disable, so you can't sleep there. It's possible when putting the last reference to the fsnotify_mark that we'll end up putting a chain of references including the fsnotify_group, uid, and associated keys. While I don't see any obvious ways that that could occurs, it's probably still best to avoid using call_srcu here after all. This patch reverts the above patch. A later patch will take a different approach to eliminated the dedicated thread here. Signed-off-by: Jeff Layton Reported-by: Eryu Guan Tested-by: Eryu Guan Cc: Jan Kara Cc: Eric Paris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/notify/mark.c | 66 +++++++++++++++++++++++++++++++--------- include/linux/fsnotify_backend.h | 5 +-- 2 files changed, 53 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/mark.c b/fs/notify/mark.c index cfcbf114676e..fc0df4442f7b 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -92,6 +92,9 @@ #include "fsnotify.h" struct srcu_struct fsnotify_mark_srcu; +static DEFINE_SPINLOCK(destroy_lock); +static LIST_HEAD(destroy_list); +static DECLARE_WAIT_QUEUE_HEAD(destroy_waitq); void fsnotify_get_mark(struct fsnotify_mark *mark) { @@ -165,19 +168,10 @@ void fsnotify_detach_mark(struct fsnotify_mark *mark) atomic_dec(&group->num_marks); } -static void -fsnotify_mark_free_rcu(struct rcu_head *rcu) -{ - struct fsnotify_mark *mark; - - mark = container_of(rcu, struct fsnotify_mark, g_rcu); - fsnotify_put_mark(mark); -} - /* - * Free fsnotify mark. The freeing is actually happening from a call_srcu - * callback. Caller must have a reference to the mark or be protected by - * fsnotify_mark_srcu. + * Free fsnotify mark. The freeing is actually happening from a kthread which + * first waits for srcu period end. Caller must have a reference to the mark + * or be protected by fsnotify_mark_srcu. */ void fsnotify_free_mark(struct fsnotify_mark *mark) { @@ -192,7 +186,10 @@ void fsnotify_free_mark(struct fsnotify_mark *mark) mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE; spin_unlock(&mark->lock); - call_srcu(&fsnotify_mark_srcu, &mark->g_rcu, fsnotify_mark_free_rcu); + spin_lock(&destroy_lock); + list_add(&mark->g_list, &destroy_list); + spin_unlock(&destroy_lock); + wake_up(&destroy_waitq); /* * Some groups like to know that marks are being freed. This is a @@ -388,7 +385,11 @@ err: spin_unlock(&mark->lock); - call_srcu(&fsnotify_mark_srcu, &mark->g_rcu, fsnotify_mark_free_rcu); + spin_lock(&destroy_lock); + list_add(&mark->g_list, &destroy_list); + spin_unlock(&destroy_lock); + wake_up(&destroy_waitq); + return ret; } @@ -491,3 +492,40 @@ void fsnotify_init_mark(struct fsnotify_mark *mark, atomic_set(&mark->refcnt, 1); mark->free_mark = free_mark; } + +static int fsnotify_mark_destroy(void *ignored) +{ + struct fsnotify_mark *mark, *next; + struct list_head private_destroy_list; + + for (;;) { + spin_lock(&destroy_lock); + /* exchange the list head */ + list_replace_init(&destroy_list, &private_destroy_list); + spin_unlock(&destroy_lock); + + synchronize_srcu(&fsnotify_mark_srcu); + + list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) { + list_del_init(&mark->g_list); + fsnotify_put_mark(mark); + } + + wait_event_interruptible(destroy_waitq, !list_empty(&destroy_list)); + } + + return 0; +} + +static int __init fsnotify_mark_init(void) +{ + struct task_struct *thread; + + thread = kthread_run(fsnotify_mark_destroy, NULL, + "fsnotify_mark"); + if (IS_ERR(thread)) + panic("unable to start fsnotify mark destruction thread."); + + return 0; +} +device_initcall(fsnotify_mark_init); diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 6b7e89f45aa4..533c4408529a 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -220,10 +220,7 @@ struct fsnotify_mark { /* List of marks by group->i_fsnotify_marks. Also reused for queueing * mark into destroy_list when it's waiting for the end of SRCU period * before it can be freed. [group->mark_mutex] */ - union { - struct list_head g_list; - struct rcu_head g_rcu; - }; + struct list_head g_list; /* Protects inode / mnt pointers, flags, masks */ spinlock_t lock; /* List of marks for inode / vfsmount [obj_lock] */ -- cgit v1.2.3 From cfdd28beb3205dbd1e91571516807199c8ab84ca Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 17 Feb 2016 18:00:31 +0100 Subject: net: make netdev_for_each_lower_dev safe for device removal When I used netdev_for_each_lower_dev in commit bad531623253 ("vrf: remove slave queue and private slave struct") I thought that it acts like netdev_for_each_lower_private and can be used to remove the current device from the list while walking, but unfortunately it acts more like netdev_for_each_lower_private_rcu and doesn't allow it. The difference is where the "iter" points to, right now it points to the current element and that makes it impossible to remove it. Change the logic to be similar to netdev_for_each_lower_private and make it point to the "next" element so we can safely delete the current one. VRF is the only such user right now, there's no change for the read-only users. Here's what can happen now: [98423.249858] general protection fault: 0000 [#1] SMP [98423.250175] Modules linked in: vrf bridge(O) stp llc nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace sunrpc crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel jitterentropy_rng sha256_generic hmac drbg ppdev aesni_intel aes_x86_64 glue_helper lrw gf128mul ablk_helper cryptd evdev serio_raw pcspkr virtio_balloon parport_pc parport i2c_piix4 i2c_core virtio_console acpi_cpufreq button 9pnet_virtio 9p 9pnet fscache ipv6 autofs4 ext4 crc16 mbcache jbd2 sg virtio_blk virtio_net sr_mod cdrom e1000 ata_generic ehci_pci uhci_hcd ehci_hcd usbcore usb_common virtio_pci ata_piix libata floppy virtio_ring virtio scsi_mod [last unloaded: bridge] [98423.255040] CPU: 1 PID: 14173 Comm: ip Tainted: G O 4.5.0-rc2+ #81 [98423.255386] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.8.1-20150318_183358- 04/01/2014 [98423.255777] task: ffff8800547f5540 ti: ffff88003428c000 task.ti: ffff88003428c000 [98423.256123] RIP: 0010:[] [] netdev_lower_get_next+0x1e/0x30 [98423.256534] RSP: 0018:ffff88003428f940 EFLAGS: 00010207 [98423.256766] RAX: 0002000100000004 RBX: ffff880054ff9000 RCX: 0000000000000000 [98423.257039] RDX: ffff88003428f8b8 RSI: ffff88003428f950 RDI: ffff880054ff90c0 [98423.257287] RBP: ffff88003428f940 R08: 0000000000000000 R09: 0000000000000000 [98423.257537] R10: 0000000000000001 R11: 0000000000000000 R12: ffff88003428f9e0 [98423.257802] R13: ffff880054a5fd00 R14: ffff88003428f970 R15: 0000000000000001 [98423.258055] FS: 00007f3d76881700(0000) GS:ffff88005d000000(0000) knlGS:0000000000000000 [98423.258418] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [98423.258650] CR2: 00007ffe5951ffa8 CR3: 0000000052077000 CR4: 00000000000406e0 [98423.258902] Stack: [98423.259075] ffff88003428f960 ffffffffa0442636 0002000100000004 ffff880054ff9000 [98423.259647] ffff88003428f9b0 ffffffff81518205 ffff880054ff9000 ffff88003428f978 [98423.260208] ffff88003428f978 ffff88003428f9e0 ffff88003428f9e0 ffff880035b35f00 [98423.260739] Call Trace: [98423.260920] [] vrf_dev_uninit+0x76/0xa0 [vrf] [98423.261156] [] rollback_registered_many+0x205/0x390 [98423.261401] [] unregister_netdevice_many+0x1c/0x70 [98423.261641] [] rtnl_delete_link+0x3c/0x50 [98423.271557] [] rtnl_dellink+0xcb/0x1d0 [98423.271800] [] ? __inc_zone_state+0x4a/0x90 [98423.272049] [] rtnetlink_rcv_msg+0x84/0x200 [98423.272279] [] ? trace_hardirqs_on+0xd/0x10 [98423.272513] [] ? rtnetlink_rcv+0x1b/0x40 [98423.272755] [] ? rtnetlink_rcv+0x40/0x40 [98423.272983] [] netlink_rcv_skb+0x97/0xb0 [98423.273209] [] rtnetlink_rcv+0x2a/0x40 [98423.273476] [] netlink_unicast+0x11b/0x1a0 [98423.273710] [] netlink_sendmsg+0x3e1/0x610 [98423.273947] [] sock_sendmsg+0x38/0x70 [98423.274175] [] ___sys_sendmsg+0x2e3/0x2f0 [98423.274416] [] ? do_raw_spin_unlock+0xbe/0x140 [98423.274658] [] ? handle_mm_fault+0x26c/0x2210 [98423.274894] [] ? handle_mm_fault+0x4d/0x2210 [98423.275130] [] ? __fget_light+0x91/0xb0 [98423.275365] [] __sys_sendmsg+0x42/0x80 [98423.275595] [] SyS_sendmsg+0x12/0x20 [98423.275827] [] entry_SYSCALL_64_fastpath+0x16/0x7a [98423.276073] Code: c3 31 c0 5d c3 0f 1f 84 00 00 00 00 00 66 66 66 66 90 48 8b 06 55 48 81 c7 c0 00 00 00 48 89 e5 48 8b 00 48 39 f8 74 09 48 89 06 <48> 8b 40 e8 5d c3 31 c0 5d c3 0f 1f 84 00 00 00 00 00 66 66 66 [98423.279639] RIP [] netdev_lower_get_next+0x1e/0x30 [98423.279920] RSP CC: David Ahern CC: David S. Miller CC: Roopa Prabhu CC: Vlad Yasevich Fixes: bad531623253 ("vrf: remove slave queue and private slave struct") Signed-off-by: Nikolay Aleksandrov Reviewed-by: David Ahern Tested-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- net/core/dev.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 289c2314d766..5440b7b705eb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3718,7 +3718,7 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev, void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter); #define netdev_for_each_lower_dev(dev, ldev, iter) \ - for (iter = &(dev)->adj_list.lower, \ + for (iter = (dev)->adj_list.lower.next, \ ldev = netdev_lower_get_next(dev, &(iter)); \ ldev; \ ldev = netdev_lower_get_next(dev, &(iter))) diff --git a/net/core/dev.c b/net/core/dev.c index e15e6e6a7a8a..0ef061b2badc 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5379,12 +5379,12 @@ void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; - lower = list_entry((*iter)->next, struct netdev_adjacent, list); + lower = list_entry(*iter, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; - *iter = &lower->list; + *iter = lower->list.next; return lower->dev; } -- cgit v1.2.3 From e52bc7c28ac9f54db6f86b19ed65c599def18c98 Mon Sep 17 00:00:00 2001 From: David Decotigny Date: Fri, 19 Feb 2016 09:23:59 -0500 Subject: lib/bitmap.c: conversion routines to/from u32 array Aimed at transferring bitmaps to/from user-space in a 32/64-bit agnostic way. Tested: unit tests (next patch) on qemu i386, x86_64, ppc, ppc64 BE and LE, ARM. Signed-off-by: David Decotigny Reviewed-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/bitmap.h | 10 ++++++ lib/bitmap.c | 89 ++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 99 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 9653fdb76a42..e9b0b9ab07e5 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -59,6 +59,8 @@ * bitmap_find_free_region(bitmap, bits, order) Find and allocate bit region * bitmap_release_region(bitmap, pos, order) Free specified bit region * bitmap_allocate_region(bitmap, pos, order) Allocate specified bit region + * bitmap_from_u32array(dst, nbits, buf, nwords) *dst = *buf (nwords 32b words) + * bitmap_to_u32array(buf, nwords, src, nbits) *buf = *dst (nwords 32b words) */ /* @@ -163,6 +165,14 @@ extern void bitmap_fold(unsigned long *dst, const unsigned long *orig, extern int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order); extern void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order); extern int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order); +extern unsigned int bitmap_from_u32array(unsigned long *bitmap, + unsigned int nbits, + const u32 *buf, + unsigned int nwords); +extern unsigned int bitmap_to_u32array(u32 *buf, + unsigned int nwords, + const unsigned long *bitmap, + unsigned int nbits); #ifdef __BIG_ENDIAN extern void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int nbits); #else diff --git a/lib/bitmap.c b/lib/bitmap.c index 814814397cce..c66da508cbf7 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -12,6 +12,8 @@ #include #include #include +#include +#include #include #include @@ -1059,6 +1061,93 @@ int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order) } EXPORT_SYMBOL(bitmap_allocate_region); +/** + * bitmap_from_u32array - copy the contents of a u32 array of bits to bitmap + * @bitmap: array of unsigned longs, the destination bitmap, non NULL + * @nbits: number of bits in @bitmap + * @buf: array of u32 (in host byte order), the source bitmap, non NULL + * @nwords: number of u32 words in @buf + * + * copy min(nbits, 32*nwords) bits from @buf to @bitmap, remaining + * bits between nword and nbits in @bitmap (if any) are cleared. In + * last word of @bitmap, the bits beyond nbits (if any) are kept + * unchanged. + * + * Return the number of bits effectively copied. + */ +unsigned int +bitmap_from_u32array(unsigned long *bitmap, unsigned int nbits, + const u32 *buf, unsigned int nwords) +{ + unsigned int dst_idx, src_idx; + + for (src_idx = dst_idx = 0; dst_idx < BITS_TO_LONGS(nbits); ++dst_idx) { + unsigned long part = 0; + + if (src_idx < nwords) + part = buf[src_idx++]; + +#if BITS_PER_LONG == 64 + if (src_idx < nwords) + part |= ((unsigned long) buf[src_idx++]) << 32; +#endif + + if (dst_idx < nbits/BITS_PER_LONG) + bitmap[dst_idx] = part; + else { + unsigned long mask = BITMAP_LAST_WORD_MASK(nbits); + + bitmap[dst_idx] = (bitmap[dst_idx] & ~mask) + | (part & mask); + } + } + + return min_t(unsigned int, nbits, 32*nwords); +} +EXPORT_SYMBOL(bitmap_from_u32array); + +/** + * bitmap_to_u32array - copy the contents of bitmap to a u32 array of bits + * @buf: array of u32 (in host byte order), the dest bitmap, non NULL + * @nwords: number of u32 words in @buf + * @bitmap: array of unsigned longs, the source bitmap, non NULL + * @nbits: number of bits in @bitmap + * + * copy min(nbits, 32*nwords) bits from @bitmap to @buf. Remaining + * bits after nbits in @buf (if any) are cleared. + * + * Return the number of bits effectively copied. + */ +unsigned int +bitmap_to_u32array(u32 *buf, unsigned int nwords, + const unsigned long *bitmap, unsigned int nbits) +{ + unsigned int dst_idx = 0, src_idx = 0; + + while (dst_idx < nwords) { + unsigned long part = 0; + + if (src_idx < BITS_TO_LONGS(nbits)) { + part = bitmap[src_idx]; + if (src_idx >= nbits/BITS_PER_LONG) + part &= BITMAP_LAST_WORD_MASK(nbits); + src_idx++; + } + + buf[dst_idx++] = part & 0xffffffffUL; + +#if BITS_PER_LONG == 64 + if (dst_idx < nwords) { + part >>= 32; + buf[dst_idx++] = part & 0xffffffffUL; + } +#endif + } + + return min_t(unsigned int, nbits, 32*nwords); +} +EXPORT_SYMBOL(bitmap_to_u32array); + /** * bitmap_copy_le - copy a bitmap, putting the bits into little-endian order. * @dst: destination buffer -- cgit v1.2.3 From 421797b1aa363cb897f29f7d365e068dc9d9db81 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 19 Feb 2016 09:24:02 -0500 Subject: net/ethtool: support get coalesce per queue This patch implements sub command ETHTOOL_GCOALESCE for ioctl ETHTOOL_PERQUEUE. It introduces an interface get_per_queue_coalesce to get coalesce of each masked queue from device driver. Then the interrupt coalescing parameters will be copied back to user space one by one. Signed-off-by: Kan Liang Reviewed-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/ethtool.h | 8 +++++++- net/core/ethtool.c | 35 ++++++++++++++++++++++++++++++++++- 2 files changed, 41 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 653dc9c4ebac..de56600023a7 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -201,6 +201,11 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) * @get_module_eeprom: Get the eeprom information from the plug-in module * @get_eee: Get Energy-Efficient (EEE) supported and status. * @set_eee: Set EEE status (enable/disable) as well as LPI timers. + * @get_per_queue_coalesce: Get interrupt coalescing parameters per queue. + * It must check that the given queue number is valid. If neither a RX nor + * a TX queue has this number, return -EINVAL. If only a RX queue or a TX + * queue has this number, set the inapplicable fields to ~0 and return 0. + * Returns a negative error code or zero. * * All operations are optional (i.e. the function pointer may be set * to %NULL) and callers must take this into account. Callers must @@ -279,7 +284,8 @@ struct ethtool_ops { const struct ethtool_tunable *, void *); int (*set_tunable)(struct net_device *, const struct ethtool_tunable *, const void *); - + int (*get_per_queue_coalesce)(struct net_device *, u32, + struct ethtool_coalesce *); }; #endif /* _LINUX_ETHTOOL_H */ diff --git a/net/core/ethtool.c b/net/core/ethtool.c index d640ecf71e74..2a6c3a26f63f 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1888,6 +1888,38 @@ out: return ret; } +static int ethtool_get_per_queue_coalesce(struct net_device *dev, + void __user *useraddr, + struct ethtool_per_queue_op *per_queue_opt) +{ + u32 bit; + int ret; + DECLARE_BITMAP(queue_mask, MAX_NUM_QUEUE); + + if (!dev->ethtool_ops->get_per_queue_coalesce) + return -EOPNOTSUPP; + + useraddr += sizeof(*per_queue_opt); + + bitmap_from_u32array(queue_mask, + MAX_NUM_QUEUE, + per_queue_opt->queue_mask, + DIV_ROUND_UP(MAX_NUM_QUEUE, 32)); + + for_each_set_bit(bit, queue_mask, MAX_NUM_QUEUE) { + struct ethtool_coalesce coalesce = { .cmd = ETHTOOL_GCOALESCE }; + + ret = dev->ethtool_ops->get_per_queue_coalesce(dev, bit, &coalesce); + if (ret != 0) + return ret; + if (copy_to_user(useraddr, &coalesce, sizeof(coalesce))) + return -EFAULT; + useraddr += sizeof(coalesce); + } + + return 0; +} + static int ethtool_set_per_queue(struct net_device *dev, void __user *useraddr) { struct ethtool_per_queue_op per_queue_opt; @@ -1896,7 +1928,8 @@ static int ethtool_set_per_queue(struct net_device *dev, void __user *useraddr) return -EFAULT; switch (per_queue_opt.sub_command) { - + case ETHTOOL_GCOALESCE: + return ethtool_get_per_queue_coalesce(dev, useraddr, &per_queue_opt); default: return -EOPNOTSUPP; }; -- cgit v1.2.3 From f38d138a7da6510a1184e3bc5f425deb187c3265 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 19 Feb 2016 09:24:03 -0500 Subject: net/ethtool: support set coalesce per queue This patch implements sub command ETHTOOL_SCOALESCE for ioctl ETHTOOL_PERQUEUE. It introduces an interface set_per_queue_coalesce to set coalesce of each masked queue to device driver. The wanted coalesce information are stored in "data" for each masked queue, which can copy from userspace. If it fails to set coalesce to device driver, the value which already set to specific queue will be tried to rollback. Signed-off-by: Kan Liang Reviewed-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/ethtool.h | 7 ++++++ net/core/ethtool.c | 61 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 68 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index de56600023a7..472d7d7b01c2 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -206,6 +206,11 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) * a TX queue has this number, return -EINVAL. If only a RX queue or a TX * queue has this number, set the inapplicable fields to ~0 and return 0. * Returns a negative error code or zero. + * @set_per_queue_coalesce: Set interrupt coalescing parameters per queue. + * It must check that the given queue number is valid. If neither a RX nor + * a TX queue has this number, return -EINVAL. If only a RX queue or a TX + * queue has this number, ignore the inapplicable fields. + * Returns a negative error code or zero. * * All operations are optional (i.e. the function pointer may be set * to %NULL) and callers must take this into account. Callers must @@ -286,6 +291,8 @@ struct ethtool_ops { const struct ethtool_tunable *, const void *); int (*get_per_queue_coalesce)(struct net_device *, u32, struct ethtool_coalesce *); + int (*set_per_queue_coalesce)(struct net_device *, u32, + struct ethtool_coalesce *); }; #endif /* _LINUX_ETHTOOL_H */ diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 2a6c3a26f63f..2406101002b1 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1920,6 +1920,65 @@ static int ethtool_get_per_queue_coalesce(struct net_device *dev, return 0; } +static int ethtool_set_per_queue_coalesce(struct net_device *dev, + void __user *useraddr, + struct ethtool_per_queue_op *per_queue_opt) +{ + u32 bit; + int i, ret = 0; + int n_queue; + struct ethtool_coalesce *backup = NULL, *tmp = NULL; + DECLARE_BITMAP(queue_mask, MAX_NUM_QUEUE); + + if ((!dev->ethtool_ops->set_per_queue_coalesce) || + (!dev->ethtool_ops->get_per_queue_coalesce)) + return -EOPNOTSUPP; + + useraddr += sizeof(*per_queue_opt); + + bitmap_from_u32array(queue_mask, + MAX_NUM_QUEUE, + per_queue_opt->queue_mask, + DIV_ROUND_UP(MAX_NUM_QUEUE, 32)); + n_queue = bitmap_weight(queue_mask, MAX_NUM_QUEUE); + tmp = backup = kmalloc_array(n_queue, sizeof(*backup), GFP_KERNEL); + if (!backup) + return -ENOMEM; + + for_each_set_bit(bit, queue_mask, MAX_NUM_QUEUE) { + struct ethtool_coalesce coalesce; + + ret = dev->ethtool_ops->get_per_queue_coalesce(dev, bit, tmp); + if (ret != 0) + goto roll_back; + + tmp++; + + if (copy_from_user(&coalesce, useraddr, sizeof(coalesce))) { + ret = -EFAULT; + goto roll_back; + } + + ret = dev->ethtool_ops->set_per_queue_coalesce(dev, bit, &coalesce); + if (ret != 0) + goto roll_back; + + useraddr += sizeof(coalesce); + } + +roll_back: + if (ret != 0) { + tmp = backup; + for_each_set_bit(i, queue_mask, bit) { + dev->ethtool_ops->set_per_queue_coalesce(dev, i, tmp); + tmp++; + } + } + kfree(backup); + + return ret; +} + static int ethtool_set_per_queue(struct net_device *dev, void __user *useraddr) { struct ethtool_per_queue_op per_queue_opt; @@ -1930,6 +1989,8 @@ static int ethtool_set_per_queue(struct net_device *dev, void __user *useraddr) switch (per_queue_opt.sub_command) { case ETHTOOL_GCOALESCE: return ethtool_get_per_queue_coalesce(dev, useraddr, &per_queue_opt); + case ETHTOOL_SCOALESCE: + return ethtool_set_per_queue_coalesce(dev, useraddr, &per_queue_opt); default: return -EOPNOTSUPP; }; -- cgit v1.2.3 From 568b329a02f75ed3aaae5eb2cca384cb9e09cb29 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 17 Feb 2016 19:58:57 -0800 Subject: perf: generalize perf_callchain . avoid walking the stack when there is no room left in the buffer . generalize get_perf_callchain() to be called from bpf helper Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- arch/x86/include/asm/stacktrace.h | 2 +- arch/x86/kernel/cpu/perf_event.c | 4 ++-- arch/x86/kernel/dumpstack.c | 6 ++++-- arch/x86/kernel/stacktrace.c | 18 +++++++++++------- arch/x86/oprofile/backtrace.c | 3 ++- include/linux/perf_event.h | 13 +++++++++++-- kernel/events/callchain.c | 32 ++++++++++++++++++++------------ kernel/events/internal.h | 2 -- 8 files changed, 51 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 70bbe39043a9..7c247e7404be 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -37,7 +37,7 @@ print_context_stack_bp(struct thread_info *tinfo, /* Generic stack tracer with callbacks */ struct stacktrace_ops { - void (*address)(void *data, unsigned long address, int reliable); + int (*address)(void *data, unsigned long address, int reliable); /* On negative return stop dumping */ int (*stack)(void *data, char *name); walk_stack_t walk_stack; diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 1b443db2db50..d276b31ca473 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -2180,11 +2180,11 @@ static int backtrace_stack(void *data, char *name) return 0; } -static void backtrace_address(void *data, unsigned long addr, int reliable) +static int backtrace_address(void *data, unsigned long addr, int reliable) { struct perf_callchain_entry *entry = data; - perf_callchain_store(entry, addr); + return perf_callchain_store(entry, addr); } static const struct stacktrace_ops backtrace_ops = { diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 9c30acfadae2..0d1ff4b407d4 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -135,7 +135,8 @@ print_context_stack_bp(struct thread_info *tinfo, if (!__kernel_text_address(addr)) break; - ops->address(data, addr, 1); + if (ops->address(data, addr, 1)) + break; frame = frame->next_frame; ret_addr = &frame->return_address; print_ftrace_graph_addr(addr, data, ops, tinfo, graph); @@ -154,10 +155,11 @@ static int print_trace_stack(void *data, char *name) /* * Print one address/symbol entries per line. */ -static void print_trace_address(void *data, unsigned long addr, int reliable) +static int print_trace_address(void *data, unsigned long addr, int reliable) { touch_nmi_watchdog(); printk_stack_address(addr, reliable, data); + return 0; } static const struct stacktrace_ops print_trace_ops = { diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index fdd0c6430e5a..9ee98eefc44d 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -14,30 +14,34 @@ static int save_stack_stack(void *data, char *name) return 0; } -static void +static int __save_stack_address(void *data, unsigned long addr, bool reliable, bool nosched) { struct stack_trace *trace = data; #ifdef CONFIG_FRAME_POINTER if (!reliable) - return; + return 0; #endif if (nosched && in_sched_functions(addr)) - return; + return 0; if (trace->skip > 0) { trace->skip--; - return; + return 0; } - if (trace->nr_entries < trace->max_entries) + if (trace->nr_entries < trace->max_entries) { trace->entries[trace->nr_entries++] = addr; + return 0; + } else { + return -1; /* no more room, stop walking the stack */ + } } -static void save_stack_address(void *data, unsigned long addr, int reliable) +static int save_stack_address(void *data, unsigned long addr, int reliable) { return __save_stack_address(data, addr, reliable, false); } -static void +static int save_stack_address_nosched(void *data, unsigned long addr, int reliable) { return __save_stack_address(data, addr, reliable, true); diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c index 4e664bdb535a..cb31a4440e58 100644 --- a/arch/x86/oprofile/backtrace.c +++ b/arch/x86/oprofile/backtrace.c @@ -23,12 +23,13 @@ static int backtrace_stack(void *data, char *name) return 0; } -static void backtrace_address(void *data, unsigned long addr, int reliable) +static int backtrace_address(void *data, unsigned long addr, int reliable) { unsigned int *depth = data; if ((*depth)--) oprofile_add_trace(addr); + return 0; } static struct stacktrace_ops backtrace_ops = { diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index b35a61a481fa..7da3c25999df 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -964,11 +964,20 @@ DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry); extern void perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs); extern void perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs); +extern struct perf_callchain_entry * +get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, + bool crosstask, bool add_mark); +extern int get_callchain_buffers(void); +extern void put_callchain_buffers(void); -static inline void perf_callchain_store(struct perf_callchain_entry *entry, u64 ip) +static inline int perf_callchain_store(struct perf_callchain_entry *entry, u64 ip) { - if (entry->nr < PERF_MAX_STACK_DEPTH) + if (entry->nr < PERF_MAX_STACK_DEPTH) { entry->ip[entry->nr++] = ip; + return 0; + } else { + return -1; /* no more room, stop walking the stack */ + } } extern int sysctl_perf_event_paranoid; diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index 9c418002b8c1..343c22f5e867 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -159,15 +159,24 @@ put_callchain_entry(int rctx) struct perf_callchain_entry * perf_callchain(struct perf_event *event, struct pt_regs *regs) { - int rctx; - struct perf_callchain_entry *entry; - - int kernel = !event->attr.exclude_callchain_kernel; - int user = !event->attr.exclude_callchain_user; + bool kernel = !event->attr.exclude_callchain_kernel; + bool user = !event->attr.exclude_callchain_user; + /* Disallow cross-task user callchains. */ + bool crosstask = event->ctx->task && event->ctx->task != current; if (!kernel && !user) return NULL; + return get_perf_callchain(regs, 0, kernel, user, crosstask, true); +} + +struct perf_callchain_entry * +get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, + bool crosstask, bool add_mark) +{ + struct perf_callchain_entry *entry; + int rctx; + entry = get_callchain_entry(&rctx); if (rctx == -1) return NULL; @@ -175,10 +184,11 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs) if (!entry) goto exit_put; - entry->nr = 0; + entry->nr = init_nr; if (kernel && !user_mode(regs)) { - perf_callchain_store(entry, PERF_CONTEXT_KERNEL); + if (add_mark) + perf_callchain_store(entry, PERF_CONTEXT_KERNEL); perf_callchain_kernel(entry, regs); } @@ -191,13 +201,11 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs) } if (regs) { - /* - * Disallow cross-task user callchains. - */ - if (event->ctx->task && event->ctx->task != current) + if (crosstask) goto exit_put; - perf_callchain_store(entry, PERF_CONTEXT_USER); + if (add_mark) + perf_callchain_store(entry, PERF_CONTEXT_USER); perf_callchain_user(entry, regs); } } diff --git a/kernel/events/internal.h b/kernel/events/internal.h index 2bbad9c1274c..4199b6d193f5 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -182,8 +182,6 @@ DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user) /* Callchain handling */ extern struct perf_callchain_entry * perf_callchain(struct perf_event *event, struct pt_regs *regs); -extern int get_callchain_buffers(void); -extern void put_callchain_buffers(void); static inline int get_recursion_context(int *recursion) { -- cgit v1.2.3 From d5a3b1f691865be576c2bffa708549b8cdccda19 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 17 Feb 2016 19:58:58 -0800 Subject: bpf: introduce BPF_MAP_TYPE_STACK_TRACE add new map type to store stack traces and corresponding helper bpf_get_stackid(ctx, map, flags) - walk user or kernel stack and return id @ctx: struct pt_regs* @map: pointer to stack_trace map @flags: bits 0-7 - numer of stack frames to skip bit 8 - collect user stack instead of kernel bit 9 - compare stacks by hash only bit 10 - if two different stacks hash into the same stackid discard old other bits - reserved Return: >= 0 stackid on success or negative error stackid is a 32-bit integer handle that can be further combined with other data (including other stackid) and used as a key into maps. Userspace will access stackmap using standard lookup/delete syscall commands to retrieve full stack trace for given stackid. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 21 +++++ kernel/bpf/Makefile | 3 + kernel/bpf/stackmap.c | 237 +++++++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/verifier.c | 6 +- kernel/trace/bpf_trace.c | 2 + 6 files changed, 269 insertions(+), 1 deletion(-) create mode 100644 kernel/bpf/stackmap.c (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 90ee6ab24bc5..0cadbb7456c0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -237,6 +237,7 @@ extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; extern const struct bpf_func_proto bpf_skb_vlan_push_proto; extern const struct bpf_func_proto bpf_skb_vlan_pop_proto; +extern const struct bpf_func_proto bpf_get_stackid_proto; /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2ee0fde1bf96..d3e77da8e9e8 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -83,6 +83,7 @@ enum bpf_map_type { BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_MAP_TYPE_PERCPU_HASH, BPF_MAP_TYPE_PERCPU_ARRAY, + BPF_MAP_TYPE_STACK_TRACE, }; enum bpf_prog_type { @@ -272,6 +273,20 @@ enum bpf_func_id { */ BPF_FUNC_perf_event_output, BPF_FUNC_skb_load_bytes, + + /** + * bpf_get_stackid(ctx, map, flags) - walk user or kernel stack and return id + * @ctx: struct pt_regs* + * @map: pointer to stack_trace map + * @flags: bits 0-7 - numer of stack frames to skip + * bit 8 - collect user stack instead of kernel + * bit 9 - compare stacks by hash only + * bit 10 - if two different stacks hash into the same stackid + * discard old + * other bits - reserved + * Return: >= 0 stackid on success or negative error + */ + BPF_FUNC_get_stackid, __BPF_FUNC_MAX_ID, }; @@ -294,6 +309,12 @@ enum bpf_func_id { /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ #define BPF_F_TUNINFO_IPV6 (1ULL << 0) +/* BPF_FUNC_get_stackid flags. */ +#define BPF_F_SKIP_FIELD_MASK 0xffULL +#define BPF_F_USER_STACK (1ULL << 8) +#define BPF_F_FAST_STACK_CMP (1ULL << 9) +#define BPF_F_REUSE_STACKID (1ULL << 10) + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 13272582eee0..8a932d079c24 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -2,3 +2,6 @@ obj-y := core.o obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o +ifeq ($(CONFIG_PERF_EVENTS),y) +obj-$(CONFIG_BPF_SYSCALL) += stackmap.o +endif diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c new file mode 100644 index 000000000000..8a60ee14a977 --- /dev/null +++ b/kernel/bpf/stackmap.c @@ -0,0 +1,237 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include +#include +#include +#include +#include +#include + +struct stack_map_bucket { + struct rcu_head rcu; + u32 hash; + u32 nr; + u64 ip[]; +}; + +struct bpf_stack_map { + struct bpf_map map; + u32 n_buckets; + struct stack_map_bucket __rcu *buckets[]; +}; + +/* Called from syscall */ +static struct bpf_map *stack_map_alloc(union bpf_attr *attr) +{ + u32 value_size = attr->value_size; + struct bpf_stack_map *smap; + u64 cost, n_buckets; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + + /* check sanity of attributes */ + if (attr->max_entries == 0 || attr->key_size != 4 || + value_size < 8 || value_size % 8 || + value_size / 8 > PERF_MAX_STACK_DEPTH) + return ERR_PTR(-EINVAL); + + /* hash table size must be power of 2 */ + n_buckets = roundup_pow_of_two(attr->max_entries); + + cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap); + if (cost >= U32_MAX - PAGE_SIZE) + return ERR_PTR(-E2BIG); + + smap = kzalloc(cost, GFP_USER | __GFP_NOWARN); + if (!smap) { + smap = vzalloc(cost); + if (!smap) + return ERR_PTR(-ENOMEM); + } + + err = -E2BIG; + cost += n_buckets * (value_size + sizeof(struct stack_map_bucket)); + if (cost >= U32_MAX - PAGE_SIZE) + goto free_smap; + + smap->map.map_type = attr->map_type; + smap->map.key_size = attr->key_size; + smap->map.value_size = value_size; + smap->map.max_entries = attr->max_entries; + smap->n_buckets = n_buckets; + smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + err = get_callchain_buffers(); + if (err) + goto free_smap; + + return &smap->map; + +free_smap: + kvfree(smap); + return ERR_PTR(err); +} + +static u64 bpf_get_stackid(u64 r1, u64 r2, u64 flags, u64 r4, u64 r5) +{ + struct pt_regs *regs = (struct pt_regs *) (long) r1; + struct bpf_map *map = (struct bpf_map *) (long) r2; + struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); + struct perf_callchain_entry *trace; + struct stack_map_bucket *bucket, *new_bucket, *old_bucket; + u32 max_depth = map->value_size / 8; + /* stack_map_alloc() checks that max_depth <= PERF_MAX_STACK_DEPTH */ + u32 init_nr = PERF_MAX_STACK_DEPTH - max_depth; + u32 skip = flags & BPF_F_SKIP_FIELD_MASK; + u32 hash, id, trace_nr, trace_len; + bool user = flags & BPF_F_USER_STACK; + bool kernel = !user; + u64 *ips; + + if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | + BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID))) + return -EINVAL; + + trace = get_perf_callchain(regs, init_nr, kernel, user, false, false); + + if (unlikely(!trace)) + /* couldn't fetch the stack trace */ + return -EFAULT; + + /* get_perf_callchain() guarantees that trace->nr >= init_nr + * and trace-nr <= PERF_MAX_STACK_DEPTH, so trace_nr <= max_depth + */ + trace_nr = trace->nr - init_nr; + + if (trace_nr <= skip) + /* skipping more than usable stack trace */ + return -EFAULT; + + trace_nr -= skip; + trace_len = trace_nr * sizeof(u64); + ips = trace->ip + skip + init_nr; + hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0); + id = hash & (smap->n_buckets - 1); + bucket = rcu_dereference(smap->buckets[id]); + + if (bucket && bucket->hash == hash) { + if (flags & BPF_F_FAST_STACK_CMP) + return id; + if (bucket->nr == trace_nr && + memcmp(bucket->ip, ips, trace_len) == 0) + return id; + } + + /* this call stack is not in the map, try to add it */ + if (bucket && !(flags & BPF_F_REUSE_STACKID)) + return -EEXIST; + + new_bucket = kmalloc(sizeof(struct stack_map_bucket) + map->value_size, + GFP_ATOMIC | __GFP_NOWARN); + if (unlikely(!new_bucket)) + return -ENOMEM; + + memcpy(new_bucket->ip, ips, trace_len); + memset(new_bucket->ip + trace_len / 8, 0, map->value_size - trace_len); + new_bucket->hash = hash; + new_bucket->nr = trace_nr; + + old_bucket = xchg(&smap->buckets[id], new_bucket); + if (old_bucket) + kfree_rcu(old_bucket, rcu); + return id; +} + +const struct bpf_func_proto bpf_get_stackid_proto = { + .func = bpf_get_stackid, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_ANYTHING, +}; + +/* Called from syscall or from eBPF program */ +static void *stack_map_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); + struct stack_map_bucket *bucket; + u32 id = *(u32 *)key; + + if (unlikely(id >= smap->n_buckets)) + return NULL; + bucket = rcu_dereference(smap->buckets[id]); + return bucket ? bucket->ip : NULL; +} + +static int stack_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + return -EINVAL; +} + +static int stack_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + return -EINVAL; +} + +/* Called from syscall or from eBPF program */ +static int stack_map_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); + struct stack_map_bucket *old_bucket; + u32 id = *(u32 *)key; + + if (unlikely(id >= smap->n_buckets)) + return -E2BIG; + + old_bucket = xchg(&smap->buckets[id], NULL); + if (old_bucket) { + kfree_rcu(old_bucket, rcu); + return 0; + } else { + return -ENOENT; + } +} + +/* Called when map->refcnt goes to zero, either from workqueue or from syscall */ +static void stack_map_free(struct bpf_map *map) +{ + struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); + int i; + + synchronize_rcu(); + + for (i = 0; i < smap->n_buckets; i++) + if (smap->buckets[i]) + kfree_rcu(smap->buckets[i], rcu); + kvfree(smap); + put_callchain_buffers(); +} + +static const struct bpf_map_ops stack_map_ops = { + .map_alloc = stack_map_alloc, + .map_free = stack_map_free, + .map_get_next_key = stack_map_get_next_key, + .map_lookup_elem = stack_map_lookup_elem, + .map_update_elem = stack_map_update_elem, + .map_delete_elem = stack_map_delete_elem, +}; + +static struct bpf_map_type_list stack_map_type __read_mostly = { + .ops = &stack_map_ops, + .type = BPF_MAP_TYPE_STACK_TRACE, +}; + +static int __init register_stack_map(void) +{ + bpf_register_map_type(&stack_map_type); + return 0; +} +late_initcall(register_stack_map); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d1d3e8f57de9..42ba4ccc020b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -246,6 +246,7 @@ static const struct { {BPF_MAP_TYPE_PROG_ARRAY, BPF_FUNC_tail_call}, {BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_read}, {BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_output}, + {BPF_MAP_TYPE_STACK_TRACE, BPF_FUNC_get_stackid}, }; static void print_verifier_state(struct verifier_env *env) @@ -911,8 +912,11 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) * don't allow any other map type to be passed into * the special func; */ - if (bool_func && bool_map != bool_func) + if (bool_func && bool_map != bool_func) { + verbose("cannot pass map_type %d into func %d\n", + map->map_type, func_id); return -EINVAL; + } } return 0; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 326a75e884db..4b8caa392b86 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -299,6 +299,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func return &bpf_perf_event_read_proto; case BPF_FUNC_perf_event_output: return &bpf_perf_event_output_proto; + case BPF_FUNC_get_stackid: + return &bpf_get_stackid_proto; default: return NULL; } -- cgit v1.2.3 From b1cb86ae0e5951e9747ec7a5b33d1c1217791b75 Mon Sep 17 00:00:00 2001 From: "Karicheri, Muralidharan" Date: Fri, 19 Feb 2016 12:58:43 -0500 Subject: soc: ti: knav_dma: rename pad in struct knav_dma_desc to sw_data Rename the pad to sw_data as per description of this field in the hardware spec(refer sprugr9 from www.ti.com). Latest version of the document is at http://www.ti.com/lit/ug/sprugr9h/sprugr9h.pdf and section 3.1 Host Packet Descriptor describes this field. Define and use a constant for the size of sw_data field similar to other fields in the struct for desc and document the sw_data field in the header. As the sw_data is not touched by hw, it's type can be changed to u32. Rename the helpers to match with the updated dma desc field sw_data. Cc: Wingman Kwok Cc: Mugunthan V N CC: Arnd Bergmann CC: Grygorii Strashko CC: David Laight Signed-off-by: Murali Karicheri Acked-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/netcp_core.c | 40 +++++++++++++++++++----------------- include/linux/soc/ti/knav_dma.h | 4 +++- 2 files changed, 24 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 0b26e5209413..84bab29995fd 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -117,10 +117,11 @@ static void get_pkt_info(dma_addr_t *buff, u32 *buff_len, dma_addr_t *ndesc, *ndesc = le32_to_cpu(desc->next_desc); } -static void get_pad_info(u32 *pad0, u32 *pad1, struct knav_dma_desc *desc) +static void get_sw_data(u32 *data0, u32 *data1, struct knav_dma_desc *desc) { - *pad0 = le32_to_cpu(desc->pad[0]); - *pad1 = le32_to_cpu(desc->pad[1]); + /* No Endian conversion needed as this data is untouched by hw */ + *data0 = desc->sw_data[0]; + *data1 = desc->sw_data[1]; } static void get_org_pkt_info(dma_addr_t *buff, u32 *buff_len, @@ -153,10 +154,11 @@ static void set_desc_info(u32 desc_info, u32 pkt_info, desc->packet_info = cpu_to_le32(pkt_info); } -static void set_pad_info(u32 pad0, u32 pad1, struct knav_dma_desc *desc) +static void set_sw_data(u32 data0, u32 data1, struct knav_dma_desc *desc) { - desc->pad[0] = cpu_to_le32(pad0); - desc->pad[1] = cpu_to_le32(pad1); + /* No Endian conversion needed as this data is untouched by hw */ + desc->sw_data[0] = data0; + desc->sw_data[1] = data1; } static void set_org_pkt_info(dma_addr_t buff, u32 buff_len, @@ -581,12 +583,12 @@ static void netcp_free_rx_desc_chain(struct netcp_intf *netcp, break; } get_pkt_info(&dma_buf, &tmp, &dma_desc, ndesc); - get_pad_info((u32 *)&buf_ptr, &buf_len, ndesc); + get_sw_data((u32 *)&buf_ptr, &buf_len, ndesc); dma_unmap_page(netcp->dev, dma_buf, PAGE_SIZE, DMA_FROM_DEVICE); __free_page(buf_ptr); knav_pool_desc_put(netcp->rx_pool, desc); } - get_pad_info((u32 *)&buf_ptr, &buf_len, desc); + get_sw_data((u32 *)&buf_ptr, &buf_len, desc); if (buf_ptr) netcp_frag_free(buf_len <= PAGE_SIZE, buf_ptr); @@ -639,7 +641,7 @@ static int netcp_process_one_rx_packet(struct netcp_intf *netcp) } get_pkt_info(&dma_buff, &buf_len, &dma_desc, desc); - get_pad_info((u32 *)&org_buf_ptr, &org_buf_len, desc); + get_sw_data((u32 *)&org_buf_ptr, &org_buf_len, desc); if (unlikely(!org_buf_ptr)) { dev_err(netcp->ndev_dev, "NULL bufptr in desc\n"); @@ -672,7 +674,7 @@ static int netcp_process_one_rx_packet(struct netcp_intf *netcp) } get_pkt_info(&dma_buff, &buf_len, &dma_desc, ndesc); - get_pad_info((u32 *)&page, &tmp, ndesc); + get_sw_data((u32 *)&page, &tmp, ndesc); if (likely(dma_buff && buf_len && page)) { dma_unmap_page(netcp->dev, dma_buff, PAGE_SIZE, @@ -761,7 +763,7 @@ static void netcp_free_rx_buf(struct netcp_intf *netcp, int fdq) } get_org_pkt_info(&dma, &buf_len, desc); - get_pad_info((u32 *)&buf_ptr, &tmp, desc); + get_sw_data((u32 *)&buf_ptr, &tmp, desc); if (unlikely(!dma)) { dev_err(netcp->ndev_dev, "NULL orig_buff in desc\n"); @@ -813,7 +815,7 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) struct page *page; dma_addr_t dma; void *bufptr; - u32 pad[2]; + u32 sw_data[2]; /* Allocate descriptor */ hwdesc = knav_pool_desc_get(netcp->rx_pool); @@ -830,7 +832,7 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); bufptr = netdev_alloc_frag(primary_buf_len); - pad[1] = primary_buf_len; + sw_data[1] = primary_buf_len; if (unlikely(!bufptr)) { dev_warn_ratelimited(netcp->ndev_dev, @@ -842,7 +844,7 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) if (unlikely(dma_mapping_error(netcp->dev, dma))) goto fail; - pad[0] = (u32)bufptr; + sw_data[0] = (u32)bufptr; } else { /* Allocate a secondary receive queue entry */ page = alloc_page(GFP_ATOMIC | GFP_DMA | __GFP_COLD); @@ -852,8 +854,8 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) } buf_len = PAGE_SIZE; dma = dma_map_page(netcp->dev, page, 0, buf_len, DMA_TO_DEVICE); - pad[0] = (u32)page; - pad[1] = 0; + sw_data[0] = (u32)page; + sw_data[1] = 0; } desc_info = KNAV_DMA_DESC_PS_INFO_IN_DESC; @@ -863,7 +865,7 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) pkt_info |= (netcp->rx_queue_id & KNAV_DMA_DESC_RETQ_MASK) << KNAV_DMA_DESC_RETQ_SHIFT; set_org_pkt_info(dma, buf_len, hwdesc); - set_pad_info(pad[0], pad[1], hwdesc); + set_sw_data(sw_data[0], sw_data[1], hwdesc); set_desc_info(desc_info, pkt_info, hwdesc); /* Push to FDQs */ @@ -969,7 +971,7 @@ static int netcp_process_tx_compl_packets(struct netcp_intf *netcp, continue; } - get_pad_info((u32 *)&skb, &tmp, desc); + get_sw_data((u32 *)&skb, &tmp, desc); netcp_free_tx_desc_chain(netcp, desc, dma_sz); if (!skb) { dev_err(netcp->ndev_dev, "No skb in Tx desc\n"); @@ -1174,7 +1176,7 @@ static int netcp_tx_submit_skb(struct netcp_intf *netcp, } set_words(&tmp, 1, &desc->packet_info); - set_words((u32 *)&skb, 1, &desc->pad[0]); + set_sw_data((u32)skb, 0, desc); if (tx_pipe->flags & SWITCH_TO_PORT_IN_TAGINFO) { tmp = tx_pipe->switch_to_port; diff --git a/include/linux/soc/ti/knav_dma.h b/include/linux/soc/ti/knav_dma.h index 343c13ac4f71..35cb9264e0d5 100644 --- a/include/linux/soc/ti/knav_dma.h +++ b/include/linux/soc/ti/knav_dma.h @@ -44,6 +44,7 @@ #define KNAV_DMA_NUM_EPIB_WORDS 4 #define KNAV_DMA_NUM_PS_WORDS 16 +#define KNAV_DMA_NUM_SW_DATA_WORDS 4 #define KNAV_DMA_FDQ_PER_CHAN 4 /* Tx channel scheduling priority */ @@ -142,6 +143,7 @@ struct knav_dma_cfg { * @orig_buff: buff pointer since 'buff' can be overwritten * @epib: Extended packet info block * @psdata: Protocol specific + * @sw_data: Software private data not touched by h/w */ struct knav_dma_desc { __le32 desc_info; @@ -154,7 +156,7 @@ struct knav_dma_desc { __le32 orig_buff; __le32 epib[KNAV_DMA_NUM_EPIB_WORDS]; __le32 psdata[KNAV_DMA_NUM_PS_WORDS]; - __le32 pad[4]; + u32 sw_data[KNAV_DMA_NUM_SW_DATA_WORDS]; } ____cacheline_aligned; #if IS_ENABLED(CONFIG_KEYSTONE_NAVIGATOR_DMA) -- cgit v1.2.3 From 8e2fe1d9f1a20924f98ea46931a1d7fb092aa876 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 19 Feb 2016 23:05:22 +0100 Subject: bpf: add new arg_type that allows for 0 sized stack buffer Currently, when we pass a buffer from the eBPF stack into a helper function, the function proto indicates argument types as ARG_PTR_TO_STACK and ARG_CONST_STACK_SIZE pair. If R contains the former, then R must be of the latter type. Then, verifier checks whether the buffer points into eBPF stack, is initialized, etc. The verifier also guarantees that the constant value passed in R is greater than 0, so helper functions don't need to test for it and can always assume a non-NULL initialized buffer as well as non-0 buffer size. This patch adds a new argument types ARG_CONST_STACK_SIZE_OR_ZERO that allows to also pass NULL as R and 0 as R into the helper function. Such helper functions, of course, need to be able to handle these cases internally then. Verifier guarantees that either R == NULL && R == 0 or R != NULL && R != 0 (like the case of ARG_CONST_STACK_SIZE), any other combinations are not possible to load. I went through various options of extending the verifier, and introducing the type ARG_CONST_STACK_SIZE_OR_ZERO seems to have most minimal changes needed to the verifier. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + kernel/bpf/verifier.c | 42 ++++++++++++++++++++++++++++++++---------- 2 files changed, 33 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0cadbb7456c0..51e498e5470e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -65,6 +65,7 @@ enum bpf_arg_type { */ ARG_PTR_TO_STACK, /* any pointer to eBPF program stack */ ARG_CONST_STACK_SIZE, /* number of bytes accessed from stack */ + ARG_CONST_STACK_SIZE_OR_ZERO, /* number of bytes accessed from stack or 0 */ ARG_PTR_TO_CTX, /* pointer to context */ ARG_ANYTHING, /* any (initialized) argument is ok */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 42ba4ccc020b..36dc497deaa3 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -779,15 +779,24 @@ static int check_xadd(struct verifier_env *env, struct bpf_insn *insn) * bytes from that pointer, make sure that it's within stack boundary * and all elements of stack are initialized */ -static int check_stack_boundary(struct verifier_env *env, - int regno, int access_size) +static int check_stack_boundary(struct verifier_env *env, int regno, + int access_size, bool zero_size_allowed) { struct verifier_state *state = &env->cur_state; struct reg_state *regs = state->regs; int off, i; - if (regs[regno].type != PTR_TO_STACK) + if (regs[regno].type != PTR_TO_STACK) { + if (zero_size_allowed && access_size == 0 && + regs[regno].type == CONST_IMM && + regs[regno].imm == 0) + return 0; + + verbose("R%d type=%s expected=%s\n", regno, + reg_type_str[regs[regno].type], + reg_type_str[PTR_TO_STACK]); return -EACCES; + } off = regs[regno].imm; if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 || @@ -830,15 +839,24 @@ static int check_func_arg(struct verifier_env *env, u32 regno, return 0; } - if (arg_type == ARG_PTR_TO_STACK || arg_type == ARG_PTR_TO_MAP_KEY || + if (arg_type == ARG_PTR_TO_MAP_KEY || arg_type == ARG_PTR_TO_MAP_VALUE) { expected_type = PTR_TO_STACK; - } else if (arg_type == ARG_CONST_STACK_SIZE) { + } else if (arg_type == ARG_CONST_STACK_SIZE || + arg_type == ARG_CONST_STACK_SIZE_OR_ZERO) { expected_type = CONST_IMM; } else if (arg_type == ARG_CONST_MAP_PTR) { expected_type = CONST_PTR_TO_MAP; } else if (arg_type == ARG_PTR_TO_CTX) { expected_type = PTR_TO_CTX; + } else if (arg_type == ARG_PTR_TO_STACK) { + expected_type = PTR_TO_STACK; + /* One exception here. In case function allows for NULL to be + * passed in as argument, it's a CONST_IMM type. Final test + * happens during stack boundary checking. + */ + if (reg->type == CONST_IMM && reg->imm == 0) + expected_type = CONST_IMM; } else { verbose("unsupported arg_type %d\n", arg_type); return -EFAULT; @@ -868,8 +886,8 @@ static int check_func_arg(struct verifier_env *env, u32 regno, verbose("invalid map_ptr to access map->key\n"); return -EACCES; } - err = check_stack_boundary(env, regno, (*mapp)->key_size); - + err = check_stack_boundary(env, regno, (*mapp)->key_size, + false); } else if (arg_type == ARG_PTR_TO_MAP_VALUE) { /* bpf_map_xxx(..., map_ptr, ..., value) call: * check [value, value + map->value_size) validity @@ -879,9 +897,12 @@ static int check_func_arg(struct verifier_env *env, u32 regno, verbose("invalid map_ptr to access map->value\n"); return -EACCES; } - err = check_stack_boundary(env, regno, (*mapp)->value_size); + err = check_stack_boundary(env, regno, (*mapp)->value_size, + false); + } else if (arg_type == ARG_CONST_STACK_SIZE || + arg_type == ARG_CONST_STACK_SIZE_OR_ZERO) { + bool zero_size_allowed = (arg_type == ARG_CONST_STACK_SIZE_OR_ZERO); - } else if (arg_type == ARG_CONST_STACK_SIZE) { /* bpf_xxx(..., buf, len) call will access 'len' bytes * from stack pointer 'buf'. Check it * note: regno == len, regno - 1 == buf @@ -891,7 +912,8 @@ static int check_func_arg(struct verifier_env *env, u32 regno, verbose("ARG_CONST_STACK_SIZE cannot be first argument\n"); return -EACCES; } - err = check_stack_boundary(env, regno - 1, reg->imm); + err = check_stack_boundary(env, regno - 1, reg->imm, + zero_size_allowed); } return err; -- cgit v1.2.3 From 3697649ff29e0f647565eed04b27a7779c646a22 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 19 Feb 2016 23:05:25 +0100 Subject: bpf: try harder on clones when writing into skb When we're dealing with clones and the area is not writeable, try harder and get a copy via pskb_expand_head(). Replace also other occurences in tc actions with the new skb_try_make_writable(). Reported-by: Ashhad Sheikh Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/skbuff.h | 7 +++++++ net/core/filter.c | 19 ++++++++++--------- net/sched/act_csum.c | 8 ++------ net/sched/act_nat.c | 18 +++++------------- 4 files changed, 24 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 89b536796e53..6a57757a86cf 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2630,6 +2630,13 @@ static inline int skb_clone_writable(const struct sk_buff *skb, unsigned int len skb_headroom(skb) + len <= skb->hdr_len; } +static inline int skb_try_make_writable(struct sk_buff *skb, + unsigned int write_len) +{ + return skb_cloned(skb) && !skb_clone_writable(skb, write_len) && + pskb_expand_head(skb, 0, 0, GFP_ATOMIC); +} + static inline int __skb_cow(struct sk_buff *skb, unsigned int headroom, int cloned) { diff --git a/net/core/filter.c b/net/core/filter.c index ea391e6be7fa..f031b82128f3 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1364,9 +1364,7 @@ static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) */ if (unlikely((u32) offset > 0xffff || len > sizeof(sp->buff))) return -EFAULT; - - if (unlikely(skb_cloned(skb) && - !skb_clone_writable(skb, offset + len))) + if (unlikely(skb_try_make_writable(skb, offset + len))) return -EFAULT; ptr = skb_header_pointer(skb, offset, len, sp->buff); @@ -1439,9 +1437,7 @@ static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) return -EINVAL; if (unlikely((u32) offset > 0xffff)) return -EFAULT; - - if (unlikely(skb_cloned(skb) && - !skb_clone_writable(skb, offset + sizeof(sum)))) + if (unlikely(skb_try_make_writable(skb, offset + sizeof(sum)))) return -EFAULT; ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum); @@ -1488,9 +1484,7 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) return -EINVAL; if (unlikely((u32) offset > 0xffff)) return -EFAULT; - - if (unlikely(skb_cloned(skb) && - !skb_clone_writable(skb, offset + sizeof(sum)))) + if (unlikely(skb_try_make_writable(skb, offset + sizeof(sum)))) return -EFAULT; ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum); @@ -1734,6 +1728,13 @@ bool bpf_helper_changes_skb_data(void *func) return true; if (func == bpf_skb_vlan_pop) return true; + if (func == bpf_skb_store_bytes) + return true; + if (func == bpf_l3_csum_replace) + return true; + if (func == bpf_l4_csum_replace) + return true; + return false; } diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index b07c535ba8e7..eeb3eb3ea9eb 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -105,9 +105,7 @@ static void *tcf_csum_skb_nextlayer(struct sk_buff *skb, int hl = ihl + jhl; if (!pskb_may_pull(skb, ipl + ntkoff) || (ipl < hl) || - (skb_cloned(skb) && - !skb_clone_writable(skb, hl + ntkoff) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) + skb_try_make_writable(skb, hl + ntkoff)) return NULL; else return (void *)(skb_network_header(skb) + ihl); @@ -365,9 +363,7 @@ static int tcf_csum_ipv4(struct sk_buff *skb, u32 update_flags) } if (update_flags & TCA_CSUM_UPDATE_FLAG_IPV4HDR) { - if (skb_cloned(skb) && - !skb_clone_writable(skb, sizeof(*iph) + ntkoff) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_try_make_writable(skb, sizeof(*iph) + ntkoff)) goto fail; ip_send_check(ip_hdr(skb)); diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index b7c4ead8b5a8..27607b863aba 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -126,9 +126,7 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a, addr = iph->daddr; if (!((old_addr ^ addr) & mask)) { - if (skb_cloned(skb) && - !skb_clone_writable(skb, sizeof(*iph) + noff) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_try_make_writable(skb, sizeof(*iph) + noff)) goto drop; new_addr &= mask; @@ -156,9 +154,7 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a, struct tcphdr *tcph; if (!pskb_may_pull(skb, ihl + sizeof(*tcph) + noff) || - (skb_cloned(skb) && - !skb_clone_writable(skb, ihl + sizeof(*tcph) + noff) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) + skb_try_make_writable(skb, ihl + sizeof(*tcph) + noff)) goto drop; tcph = (void *)(skb_network_header(skb) + ihl); @@ -171,9 +167,7 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a, struct udphdr *udph; if (!pskb_may_pull(skb, ihl + sizeof(*udph) + noff) || - (skb_cloned(skb) && - !skb_clone_writable(skb, ihl + sizeof(*udph) + noff) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) + skb_try_make_writable(skb, ihl + sizeof(*udph) + noff)) goto drop; udph = (void *)(skb_network_header(skb) + ihl); @@ -213,10 +207,8 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a, if ((old_addr ^ addr) & mask) break; - if (skb_cloned(skb) && - !skb_clone_writable(skb, ihl + sizeof(*icmph) + - sizeof(*iph) + noff) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_try_make_writable(skb, ihl + sizeof(*icmph) + + sizeof(*iph) + noff)) goto drop; icmph = (void *)(skb_network_header(skb) + ihl); -- cgit v1.2.3 From 944945986f125bdbbeaa78dac0c0eadb963eb34a Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Sun, 21 Feb 2016 11:40:10 +0200 Subject: qed: Introduce DMA_REGPAIR_LE FW hsi contains regpairs, mostly for 64-bit address representations. Since same paradigm is applied each time a regpair is filled, this introduces a new utility macro for setting such regpairs. Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_l2.c | 9 +++------ drivers/net/ethernet/qlogic/qed/qed_sp_commands.c | 12 ++++-------- drivers/net/ethernet/qlogic/qed/qed_spq.c | 9 +++------ include/linux/qed/qed_chain.h | 4 ++++ 4 files changed, 14 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 8d1bc7e7e996..bba59c51f72c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -557,12 +557,10 @@ qed_sp_eth_rxq_start_ramrod(struct qed_hwfn *p_hwfn, p_ramrod->complete_event_flg = 1; p_ramrod->bd_max_bytes = cpu_to_le16(bd_max_bytes); - p_ramrod->bd_base.hi = DMA_HI_LE(bd_chain_phys_addr); - p_ramrod->bd_base.lo = DMA_LO_LE(bd_chain_phys_addr); + DMA_REGPAIR_LE(p_ramrod->bd_base, bd_chain_phys_addr); p_ramrod->num_of_pbl_pages = cpu_to_le16(cqe_pbl_size); - p_ramrod->cqe_pbl_addr.hi = DMA_HI_LE(cqe_pbl_addr); - p_ramrod->cqe_pbl_addr.lo = DMA_LO_LE(cqe_pbl_addr); + DMA_REGPAIR_LE(p_ramrod->cqe_pbl_addr, cqe_pbl_addr); rc = qed_spq_post(p_hwfn, p_ent, NULL); @@ -721,8 +719,7 @@ qed_sp_eth_txq_start_ramrod(struct qed_hwfn *p_hwfn, p_ramrod->stats_counter_id = stats_id; p_ramrod->pbl_size = cpu_to_le16(pbl_size); - p_ramrod->pbl_base_addr.hi = DMA_HI_LE(pbl_addr); - p_ramrod->pbl_base_addr.lo = DMA_LO_LE(pbl_addr); + DMA_REGPAIR_LE(p_ramrod->pbl_base_addr, pbl_addr); pq_id = qed_get_qm_pq(p_hwfn, PROTOCOLID_ETH, diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c index e271ef95745c..1c06c37d4c3d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c @@ -136,16 +136,12 @@ int qed_sp_pf_start(struct qed_hwfn *p_hwfn, p_ramrod->outer_tag = p_hwfn->hw_info.ovlan; /* Place EQ address in RAMROD */ - p_ramrod->event_ring_pbl_addr.hi = - DMA_HI_LE(p_hwfn->p_eq->chain.pbl.p_phys_table); - p_ramrod->event_ring_pbl_addr.lo = - DMA_LO_LE(p_hwfn->p_eq->chain.pbl.p_phys_table); + DMA_REGPAIR_LE(p_ramrod->event_ring_pbl_addr, + p_hwfn->p_eq->chain.pbl.p_phys_table); p_ramrod->event_ring_num_pages = (u8)p_hwfn->p_eq->chain.page_cnt; - p_ramrod->consolid_q_pbl_addr.hi = - DMA_HI_LE(p_hwfn->p_consq->chain.pbl.p_phys_table); - p_ramrod->consolid_q_pbl_addr.lo = - DMA_LO_LE(p_hwfn->p_consq->chain.pbl.p_phys_table); + DMA_REGPAIR_LE(p_ramrod->consolid_q_pbl_addr, + p_hwfn->p_consq->chain.pbl.p_phys_table); p_hwfn->hw_info.personality = PERSONALITY_ETH; diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index f6c6c21601d7..89469d5aae25 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -183,10 +183,8 @@ static void qed_spq_hw_initialize(struct qed_hwfn *p_hwfn, p_cxt->xstorm_st_context.spq_base_hi = DMA_HI_LE(p_spq->chain.p_phys_addr); - p_cxt->xstorm_st_context.consolid_base_addr.lo = - DMA_LO_LE(p_hwfn->p_consq->chain.p_phys_addr); - p_cxt->xstorm_st_context.consolid_base_addr.hi = - DMA_HI_LE(p_hwfn->p_consq->chain.p_phys_addr); + DMA_REGPAIR_LE(p_cxt->xstorm_st_context.consolid_base_addr, + p_hwfn->p_consq->chain.p_phys_addr); } static int qed_spq_hw_post(struct qed_hwfn *p_hwfn, @@ -423,8 +421,7 @@ void qed_spq_setup(struct qed_hwfn *p_hwfn) p_virt = p_spq->p_virt; for (i = 0; i < p_spq->chain.capacity; i++) { - p_virt->elem.data_ptr.hi = DMA_HI_LE(p_phys); - p_virt->elem.data_ptr.lo = DMA_LO_LE(p_phys); + DMA_REGPAIR_LE(p_virt->elem.data_ptr, p_phys); list_add_tail(&p_virt->list, &p_spq->free_pool); diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 41b9049b57e2..5f8fcaaa6504 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -19,6 +19,10 @@ /* dma_addr_t manip */ #define DMA_LO_LE(x) cpu_to_le32(lower_32_bits(x)) #define DMA_HI_LE(x) cpu_to_le32(upper_32_bits(x)) +#define DMA_REGPAIR_LE(x, val) do { \ + (x).hi = DMA_HI_LE((val)); \ + (x).lo = DMA_LO_LE((val)); \ + } while (0) #define HILO_GEN(hi, lo, type) ((((type)(hi)) << 32) + (lo)) #define HILO_DMA(hi, lo) HILO_GEN(hi, lo, dma_addr_t) -- cgit v1.2.3 From 506bcfa8abebdbcebdc17b03e96e38dc0b8ce765 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Sun, 13 Dec 2015 15:41:05 +0200 Subject: mac80211: limit the A-MSDU Tx based on peer's capabilities In VHT, the specification allows to limit the number of MSDUs in an A-MSDU in the Extended Capabilities IE. There is also a limitation on the byte size in the VHT IE. In HT, the only limitation is on the byte size. Parse the capabilities from the peer and make them available to the driver. In HT, there is another limitation when a BA agreement is active: the byte size can't be greater than 4095. This is not enforced here. Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 19 +++++++++++++++++++ include/net/mac80211.h | 14 ++++++++++++++ net/mac80211/cfg.c | 29 +++++++++++++++++++++++++++++ net/mac80211/ht.c | 5 +++++ net/mac80211/vht.c | 17 +++++++++++++++++ 5 files changed, 84 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index d9ddb89533a7..3b1f6cef9513 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -163,6 +163,14 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) /* 30 byte 4 addr hdr, 2 byte QoS, 2304 byte MSDU, 12 byte crypt, 4 byte FCS */ #define IEEE80211_MAX_FRAME_LEN 2352 +/* Maximal size of an A-MSDU */ +#define IEEE80211_MAX_MPDU_LEN_HT_3839 3839 +#define IEEE80211_MAX_MPDU_LEN_HT_7935 7935 + +#define IEEE80211_MAX_MPDU_LEN_VHT_3895 3895 +#define IEEE80211_MAX_MPDU_LEN_VHT_7991 7991 +#define IEEE80211_MAX_MPDU_LEN_VHT_11454 11454 + #define IEEE80211_MAX_SSID_LEN 32 #define IEEE80211_MAX_MESH_ID_LEN 32 @@ -1505,6 +1513,7 @@ struct ieee80211_vht_operation { #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 0x00000000 #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 0x00000001 #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 0x00000002 +#define IEEE80211_VHT_CAP_MAX_MPDU_MASK 0x00000003 #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ 0x00000004 #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ 0x00000008 #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK 0x0000000C @@ -2086,6 +2095,16 @@ enum ieee80211_tdls_actioncode { #define WLAN_EXT_CAPA8_TDLS_WIDE_BW_ENABLED BIT(5) #define WLAN_EXT_CAPA8_OPMODE_NOTIF BIT(6) +/* Defines the maximal number of MSDUs in an A-MSDU. */ +#define WLAN_EXT_CAPA8_MAX_MSDU_IN_AMSDU_LSB BIT(7) +#define WLAN_EXT_CAPA9_MAX_MSDU_IN_AMSDU_MSB BIT(0) + +/* + * Fine Timing Measurement Initiator - bit 71 of @WLAN_EID_EXT_CAPABILITY + * information element + */ +#define WLAN_EXT_CAPA9_FTM_INITIATOR BIT(7) + /* TDLS specific payload type in the LLC/SNAP header */ #define WLAN_TDLS_SNAP_RFTYPE 0x2 diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 5910085af9e6..df5698ed8052 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1714,6 +1714,18 @@ struct ieee80211_sta_rates { * @tdls_initiator: indicates the STA is an initiator of the TDLS link. Only * valid if the STA is a TDLS peer in the first place. * @mfp: indicates whether the STA uses management frame protection or not. + * @max_amsdu_subframes: indicates the maximal number of MSDUs in a single + * A-MSDU. Taken from the Extended Capabilities element. 0 means + * unlimited. + * @max_amsdu_len: indicates the maximal length of an A-MSDU in bytes. This + * field is always valid for packets with a VHT preamble. For packets + * with a HT preamble, additional limits apply: + * + If the skb is transmitted as part of a BA agreement, the + * A-MSDU maximal size is min(max_amsdu_len, 4065) bytes. + * + If the skb is not part of a BA aggreement, the A-MSDU maximal + * size is min(max_amsdu_len, 7935) bytes. + * Both additional HT limits must be enforced by the low level driver. + * This is defined by the spec (IEEE 802.11-2012 section 8.3.2.2 NOTE 2). * @txq: per-TID data TX queues (if driver uses the TXQ abstraction) */ struct ieee80211_sta { @@ -1732,6 +1744,8 @@ struct ieee80211_sta { bool tdls; bool tdls_initiator; bool mfp; + u8 max_amsdu_subframes; + u16 max_amsdu_len; struct ieee80211_txq *txq[IEEE80211_NUM_TIDS]; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 166a29fe6c35..66d22de93c8d 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1131,6 +1131,34 @@ static int sta_apply_parameters(struct ieee80211_local *local, sta->sta.max_sp = params->max_sp; } + /* The sender might not have sent the last bit, consider it to be 0 */ + if (params->ext_capab_len >= 8) { + u8 val = (params->ext_capab[7] & + WLAN_EXT_CAPA8_MAX_MSDU_IN_AMSDU_LSB) >> 7; + + /* we did get all the bits, take the MSB as well */ + if (params->ext_capab_len >= 9) { + u8 val_msb = params->ext_capab[8] & + WLAN_EXT_CAPA9_MAX_MSDU_IN_AMSDU_MSB; + val_msb <<= 1; + val |= val_msb; + } + + switch (val) { + case 1: + sta->sta.max_amsdu_subframes = 32; + break; + case 2: + sta->sta.max_amsdu_subframes = 16; + break; + case 3: + sta->sta.max_amsdu_subframes = 8; + break; + default: + sta->sta.max_amsdu_subframes = 0; + } + } + /* * cfg80211 validates this (1-2007) and allows setting the AID * only when creating a new station entry @@ -1160,6 +1188,7 @@ static int sta_apply_parameters(struct ieee80211_local *local, ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband, params->ht_capa, sta); + /* VHT can override some HT caps such as the A-MSDU max length */ if (params->vht_capa) ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, params->vht_capa, sta); diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 7a76ce639d58..f4a528773563 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -230,6 +230,11 @@ bool ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata, /* set Rx highest rate */ ht_cap.mcs.rx_highest = ht_cap_ie->mcs.rx_highest; + if (ht_cap.cap & IEEE80211_HT_CAP_MAX_AMSDU) + sta->sta.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_HT_7935; + else + sta->sta.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_HT_3839; + apply: changed = memcmp(&sta->sta.ht_cap, &ht_cap, sizeof(ht_cap)); diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index 050de08bf82e..204cf9ad3019 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -281,6 +281,23 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, } sta->sta.bandwidth = ieee80211_sta_cur_vht_bw(sta); + + /* If HT IE reported 3839 bytes only, stay with that size. */ + if (sta->sta.max_amsdu_len == IEEE80211_MAX_MPDU_LEN_HT_3839) + return; + + switch (vht_cap->cap & IEEE80211_VHT_CAP_MAX_MPDU_MASK) { + case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454: + sta->sta.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_VHT_11454; + break; + case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991: + sta->sta.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_VHT_7991; + break; + case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895: + default: + sta->sta.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_VHT_3895; + break; + } } enum ieee80211_sta_rx_bandwidth ieee80211_sta_cap_rx_bw(struct sta_info *sta) -- cgit v1.2.3 From dd21dfc645d5dce0657af78761b3fa11a3a95398 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 20 Jan 2016 10:39:23 +0100 Subject: rfkill: disentangle polling pause and suspend When suspended while polling is paused, polling will erroneously resume at resume time. Fix this by tracking pause and suspend in separate state variable and adding the necessary checks. Clarify the documentation on this as well. Signed-off-by: Johannes Berg --- include/linux/rfkill.h | 3 ++- net/rfkill/core.c | 17 +++++++++++++++-- 2 files changed, 17 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h index d9010789b4e8..7af625f6d226 100644 --- a/include/linux/rfkill.h +++ b/include/linux/rfkill.h @@ -104,7 +104,8 @@ int __must_check rfkill_register(struct rfkill *rfkill); * * Pause polling -- say transmitter is off for other reasons. * NOTE: not necessary for suspend/resume -- in that case the - * core stops polling anyway + * core stops polling anyway (but will also correctly handle + * the case of polling having been paused before suspend.) */ void rfkill_pause_polling(struct rfkill *rfkill); diff --git a/net/rfkill/core.c b/net/rfkill/core.c index f53bf3b6558b..166439995f34 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -57,6 +57,8 @@ struct rfkill { bool registered; bool persistent; + bool polling_paused; + bool suspended; const struct rfkill_ops *ops; void *data; @@ -786,6 +788,7 @@ void rfkill_pause_polling(struct rfkill *rfkill) if (!rfkill->ops->poll) return; + rfkill->polling_paused = true; cancel_delayed_work_sync(&rfkill->poll_work); } EXPORT_SYMBOL(rfkill_pause_polling); @@ -797,6 +800,11 @@ void rfkill_resume_polling(struct rfkill *rfkill) if (!rfkill->ops->poll) return; + rfkill->polling_paused = false; + + if (rfkill->suspended) + return; + queue_delayed_work(system_power_efficient_wq, &rfkill->poll_work, 0); } @@ -807,7 +815,8 @@ static int rfkill_suspend(struct device *dev) { struct rfkill *rfkill = to_rfkill(dev); - rfkill_pause_polling(rfkill); + rfkill->suspended = true; + cancel_delayed_work_sync(&rfkill->poll_work); return 0; } @@ -817,12 +826,16 @@ static int rfkill_resume(struct device *dev) struct rfkill *rfkill = to_rfkill(dev); bool cur; + rfkill->suspended = false; + if (!rfkill->persistent) { cur = !!(rfkill->state & RFKILL_BLOCK_SW); rfkill_set_block(rfkill, cur); } - rfkill_resume_polling(rfkill); + if (rfkill->ops->poll && !rfkill->polling_paused) + queue_delayed_work(system_power_efficient_wq, + &rfkill->poll_work, 0); return 0; } -- cgit v1.2.3 From 648b50dd6abf8e6e5b589bb8e6873a4596389dbe Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Mon, 25 Jan 2016 12:03:46 +0300 Subject: net: rfkill: add rfkill_find_type function Helper for finding the type based on name. Useful if the type needs to be determined based on device property. Signed-off-by: Heikki Krogerus [modify rfkill_types array and BUILD_BUG_ON to not cause errors] Signed-off-by: Johannes Berg --- include/linux/rfkill.h | 15 +++++++++++++ net/rfkill/core.c | 58 ++++++++++++++++++++++++++------------------------ 2 files changed, 45 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h index 7af625f6d226..e6a0031d1b1f 100644 --- a/include/linux/rfkill.h +++ b/include/linux/rfkill.h @@ -213,6 +213,15 @@ void rfkill_set_states(struct rfkill *rfkill, bool sw, bool hw); * @rfkill: rfkill struct to query */ bool rfkill_blocked(struct rfkill *rfkill); + +/** + * rfkill_find_type - Helpper for finding rfkill type by name + * @name: the name of the type + * + * Returns enum rfkill_type that conrresponds the name. + */ +enum rfkill_type rfkill_find_type(const char *name); + #else /* !RFKILL */ static inline struct rfkill * __must_check rfkill_alloc(const char *name, @@ -269,6 +278,12 @@ static inline bool rfkill_blocked(struct rfkill *rfkill) { return false; } + +static inline enum rfkill_type rfkill_find_type(const char *name) +{ + return RFKILL_TYPE_ALL; +} + #endif /* RFKILL || RFKILL_MODULE */ diff --git a/net/rfkill/core.c b/net/rfkill/core.c index a805831d5d9b..2a23479a49f2 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -572,6 +572,34 @@ void rfkill_set_states(struct rfkill *rfkill, bool sw, bool hw) } EXPORT_SYMBOL(rfkill_set_states); +static const char * const rfkill_types[] = { + NULL, /* RFKILL_TYPE_ALL */ + "wlan", + "bluetooth", + "ultrawideband", + "wimax", + "wwan", + "gps", + "fm", + "nfc", +}; + +enum rfkill_type rfkill_find_type(const char *name) +{ + int i; + + BUILD_BUG_ON(ARRAY_SIZE(rfkill_types) != NUM_RFKILL_TYPES); + + if (!name) + return RFKILL_TYPE_ALL; + + for (i = 1; i < NUM_RFKILL_TYPES; i++) + if (!strcmp(name, rfkill_types[i])) + return i; + return RFKILL_TYPE_ALL; +} +EXPORT_SYMBOL(rfkill_find_type); + static ssize_t name_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -581,38 +609,12 @@ static ssize_t name_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RO(name); -static const char *rfkill_get_type_str(enum rfkill_type type) -{ - BUILD_BUG_ON(NUM_RFKILL_TYPES != RFKILL_TYPE_NFC + 1); - - switch (type) { - case RFKILL_TYPE_WLAN: - return "wlan"; - case RFKILL_TYPE_BLUETOOTH: - return "bluetooth"; - case RFKILL_TYPE_UWB: - return "ultrawideband"; - case RFKILL_TYPE_WIMAX: - return "wimax"; - case RFKILL_TYPE_WWAN: - return "wwan"; - case RFKILL_TYPE_GPS: - return "gps"; - case RFKILL_TYPE_FM: - return "fm"; - case RFKILL_TYPE_NFC: - return "nfc"; - default: - BUG(); - } -} - static ssize_t type_show(struct device *dev, struct device_attribute *attr, char *buf) { struct rfkill *rfkill = to_rfkill(dev); - return sprintf(buf, "%s\n", rfkill_get_type_str(rfkill->type)); + return sprintf(buf, "%s\n", rfkill_types[rfkill->type]); } static DEVICE_ATTR_RO(type); @@ -750,7 +752,7 @@ static int rfkill_dev_uevent(struct device *dev, struct kobj_uevent_env *env) if (error) return error; error = add_uevent_var(env, "RFKILL_TYPE=%s", - rfkill_get_type_str(rfkill->type)); + rfkill_types[rfkill->type]); if (error) return error; spin_lock_irqsave(&rfkill->lock, flags); -- cgit v1.2.3 From fb2e6b7b7b02ab35a9d5355a69097a6f60c69d38 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Mon, 25 Jan 2016 12:03:49 +0300 Subject: net: rfkill: gpio: remove rfkill_gpio_platform_data No more users for it. Signed-off-by: Heikki Krogerus Signed-off-by: Johannes Berg --- include/linux/rfkill-gpio.h | 37 ------------------------------------- net/rfkill/Kconfig | 3 +-- net/rfkill/rfkill-gpio.c | 8 -------- 3 files changed, 1 insertion(+), 47 deletions(-) delete mode 100644 include/linux/rfkill-gpio.h (limited to 'include/linux') diff --git a/include/linux/rfkill-gpio.h b/include/linux/rfkill-gpio.h deleted file mode 100644 index 20bcb55498cd..000000000000 --- a/include/linux/rfkill-gpio.h +++ /dev/null @@ -1,37 +0,0 @@ -/* - * Copyright (c) 2011, NVIDIA Corporation. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - */ - - -#ifndef __RFKILL_GPIO_H -#define __RFKILL_GPIO_H - -#include -#include - -/** - * struct rfkill_gpio_platform_data - platform data for rfkill gpio device. - * for unused gpio's, the expected value is -1. - * @name: name for the gpio rf kill instance - */ - -struct rfkill_gpio_platform_data { - char *name; - enum rfkill_type type; -}; - -#endif /* __RFKILL_GPIO_H */ diff --git a/net/rfkill/Kconfig b/net/rfkill/Kconfig index 598d374f6a35..868f1ad0415a 100644 --- a/net/rfkill/Kconfig +++ b/net/rfkill/Kconfig @@ -41,5 +41,4 @@ config RFKILL_GPIO default n help If you say yes here you get support of a generic gpio RFKILL - driver. The platform should fill in the appropriate fields in the - rfkill_gpio_platform_data structure and pass that to the driver. + driver. diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index 1a9c0316aad1..76c01cbd56e3 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -27,8 +27,6 @@ #include #include -#include - struct rfkill_gpio_data { const char *name; enum rfkill_type type; @@ -89,7 +87,6 @@ static int rfkill_gpio_acpi_probe(struct device *dev, static int rfkill_gpio_probe(struct platform_device *pdev) { - struct rfkill_gpio_platform_data *pdata = pdev->dev.platform_data; struct rfkill_gpio_data *rfkill; struct gpio_desc *gpio; const char *type_name; @@ -111,11 +108,6 @@ static int rfkill_gpio_probe(struct platform_device *pdev) ret = rfkill_gpio_acpi_probe(&pdev->dev, rfkill); if (ret) return ret; - } else if (pdata) { - rfkill->name = pdata->name; - rfkill->type = pdata->type; - } else { - return -ENODEV; } rfkill->clk = devm_clk_get(&pdev->dev, NULL); -- cgit v1.2.3 From ada68c31ba9c02d7aabdd87db979fe670b499d54 Mon Sep 17 00:00:00 2001 From: Achiad Shochat Date: Mon, 22 Feb 2016 18:17:23 +0200 Subject: net/mlx5: Introduce a new header file for physical port functions All the device physical port access functions are implemented in the port.c file. We just extract the exposure of these functions from driver.h into a dedicated header file called port.h. Signed-off-by: Achiad Shochat Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/infiniband/hw/mlx5/main.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/en.h | 1 + drivers/net/ethernet/mellanox/mlx5/core/port.c | 1 + include/linux/mlx5/driver.h | 31 ------------ include/linux/mlx5/port.h | 69 ++++++++++++++++++++++++++ 5 files changed, 72 insertions(+), 31 deletions(-) create mode 100644 include/linux/mlx5/port.h (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 03c418ccbc98..e1cea4415704 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index aac071a7e830..15f6cdb842d5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -38,6 +38,7 @@ #include #include #include +#include #include #include #include "wq.h" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index a87e773e93f3..1e863216ac4a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -32,6 +32,7 @@ #include #include +#include #include #include "mlx5_core.h" diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 1e3006dcf35d..02adc67720ce 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -794,37 +794,6 @@ int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in, int size_in, void *data_out, int size_out, u16 reg_num, int arg, int write); -int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps); -int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys, - int ptys_size, int proto_mask, u8 local_port); -int mlx5_query_port_proto_cap(struct mlx5_core_dev *dev, - u32 *proto_cap, int proto_mask); -int mlx5_query_port_proto_admin(struct mlx5_core_dev *dev, - u32 *proto_admin, int proto_mask); -int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev, - u8 *link_width_oper, u8 local_port); -int mlx5_query_port_proto_oper(struct mlx5_core_dev *dev, - u8 *proto_oper, int proto_mask, - u8 local_port); -int mlx5_set_port_proto(struct mlx5_core_dev *dev, u32 proto_admin, - int proto_mask); -int mlx5_set_port_admin_status(struct mlx5_core_dev *dev, - enum mlx5_port_status status); -int mlx5_query_port_admin_status(struct mlx5_core_dev *dev, - enum mlx5_port_status *status); - -int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port); -void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu, u8 port); -void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu, - u8 port); - -int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev, - u8 *vl_hw_cap, u8 local_port); - -int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause); -int mlx5_query_port_pause(struct mlx5_core_dev *dev, - u32 *rx_pause, u32 *tx_pause); - int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq); void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq); int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq, diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h new file mode 100644 index 000000000000..7accd4a65da5 --- /dev/null +++ b/include/linux/mlx5/port.h @@ -0,0 +1,69 @@ +/* + * Copyright (c) 2016, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef __MLX5_PORT_H__ +#define __MLX5_PORT_H__ + +#include + +int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps); +int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys, + int ptys_size, int proto_mask, u8 local_port); +int mlx5_query_port_proto_cap(struct mlx5_core_dev *dev, + u32 *proto_cap, int proto_mask); +int mlx5_query_port_proto_admin(struct mlx5_core_dev *dev, + u32 *proto_admin, int proto_mask); +int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev, + u8 *link_width_oper, u8 local_port); +int mlx5_query_port_proto_oper(struct mlx5_core_dev *dev, + u8 *proto_oper, int proto_mask, + u8 local_port); +int mlx5_set_port_proto(struct mlx5_core_dev *dev, u32 proto_admin, + int proto_mask); +int mlx5_set_port_admin_status(struct mlx5_core_dev *dev, + enum mlx5_port_status status); +int mlx5_query_port_admin_status(struct mlx5_core_dev *dev, + enum mlx5_port_status *status); + +int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port); +void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu, u8 port); +void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu, + u8 port); + +int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev, + u8 *vl_hw_cap, u8 local_port); + +int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause); +int mlx5_query_port_pause(struct mlx5_core_dev *dev, + u32 *rx_pause, u32 *tx_pause); + +#endif /* __MLX5_PORT_H__ */ -- cgit v1.2.3 From ad909eb064219a64fd10e9c7d9f39a3042760025 Mon Sep 17 00:00:00 2001 From: Achiad Shochat Date: Mon, 22 Feb 2016 18:17:24 +0200 Subject: net/mlx5: Introduce physical port PFC access functions Add access functions to set and query a physical port PFC (Priority Flow Control) parameters. Signed-off-by: Achiad Shochat Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/port.c | 41 ++++++++++++++++++++++++++ include/linux/mlx5/port.h | 4 +++ 2 files changed, 45 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 1e863216ac4a..dae70500b6a9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -364,3 +364,44 @@ int mlx5_query_port_pause(struct mlx5_core_dev *dev, return 0; } EXPORT_SYMBOL_GPL(mlx5_query_port_pause); + +int mlx5_set_port_pfc(struct mlx5_core_dev *dev, u8 pfc_en_tx, u8 pfc_en_rx) +{ + u32 in[MLX5_ST_SZ_DW(pfcc_reg)]; + u32 out[MLX5_ST_SZ_DW(pfcc_reg)]; + + memset(in, 0, sizeof(in)); + MLX5_SET(pfcc_reg, in, local_port, 1); + MLX5_SET(pfcc_reg, in, pfctx, pfc_en_tx); + MLX5_SET(pfcc_reg, in, pfcrx, pfc_en_rx); + MLX5_SET_TO_ONES(pfcc_reg, in, prio_mask_tx); + MLX5_SET_TO_ONES(pfcc_reg, in, prio_mask_rx); + + return mlx5_core_access_reg(dev, in, sizeof(in), out, + sizeof(out), MLX5_REG_PFCC, 0, 1); +} +EXPORT_SYMBOL_GPL(mlx5_set_port_pfc); + +int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, u8 *pfc_en_rx) +{ + u32 in[MLX5_ST_SZ_DW(pfcc_reg)]; + u32 out[MLX5_ST_SZ_DW(pfcc_reg)]; + int err; + + memset(in, 0, sizeof(in)); + MLX5_SET(pfcc_reg, in, local_port, 1); + + err = mlx5_core_access_reg(dev, in, sizeof(in), out, + sizeof(out), MLX5_REG_PFCC, 0, 0); + if (err) + return err; + + if (pfc_en_tx) + *pfc_en_tx = MLX5_GET(pfcc_reg, out, pfctx); + + if (pfc_en_rx) + *pfc_en_rx = MLX5_GET(pfcc_reg, out, pfcrx); + + return 0; +} +EXPORT_SYMBOL_GPL(mlx5_query_port_pfc); diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 7accd4a65da5..4b3644caa936 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -66,4 +66,8 @@ int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause); int mlx5_query_port_pause(struct mlx5_core_dev *dev, u32 *rx_pause, u32 *tx_pause); +int mlx5_set_port_pfc(struct mlx5_core_dev *dev, u8 pfc_en_tx, u8 pfc_en_rx); +int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, + u8 *pfc_en_rx); + #endif /* __MLX5_PORT_H__ */ -- cgit v1.2.3 From 4f3961eeafe0aca8f6b0933899ef0d91f561352d Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 22 Feb 2016 18:17:25 +0200 Subject: net/mlx5: Introduce physical port TC/prio access functions Add access functions to set and query a physical port TC groups and prio parameters. Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/port.c | 76 ++++++++++++++++++++++++++ include/linux/mlx5/driver.h | 2 + include/linux/mlx5/mlx5_ifc.h | 49 ++++++++++++++++- include/linux/mlx5/port.h | 6 ++ 4 files changed, 132 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index dae70500b6a9..569100d3f57b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -405,3 +405,79 @@ int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, u8 *pfc_en_rx) return 0; } EXPORT_SYMBOL_GPL(mlx5_query_port_pfc); + +int mlx5_max_tc(struct mlx5_core_dev *mdev) +{ + u8 num_tc = MLX5_CAP_GEN(mdev, max_tc) ? : 8; + + return num_tc - 1; +} + +int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc) +{ + u32 in[MLX5_ST_SZ_DW(qtct_reg)]; + u32 out[MLX5_ST_SZ_DW(qtct_reg)]; + int err; + int i; + + memset(in, 0, sizeof(in)); + for (i = 0; i < 8; i++) { + if (prio_tc[i] > mlx5_max_tc(mdev)) + return -EINVAL; + + MLX5_SET(qtct_reg, in, prio, i); + MLX5_SET(qtct_reg, in, tclass, prio_tc[i]); + + err = mlx5_core_access_reg(mdev, in, sizeof(in), out, + sizeof(out), MLX5_REG_QTCT, 0, 1); + if (err) + return err; + } + + return 0; +} +EXPORT_SYMBOL_GPL(mlx5_set_port_prio_tc); + +static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in, + int inlen) +{ + u32 out[MLX5_ST_SZ_DW(qtct_reg)]; + + if (!MLX5_CAP_GEN(mdev, ets)) + return -ENOTSUPP; + + return mlx5_core_access_reg(mdev, in, inlen, out, sizeof(out), + MLX5_REG_QETCR, 0, 1); +} + +int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group) +{ + u32 in[MLX5_ST_SZ_DW(qetc_reg)]; + int i; + + memset(in, 0, sizeof(in)); + + for (i = 0; i <= mlx5_max_tc(mdev); i++) { + MLX5_SET(qetc_reg, in, tc_configuration[i].g, 1); + MLX5_SET(qetc_reg, in, tc_configuration[i].group, tc_group[i]); + } + + return mlx5_set_port_qetcr_reg(mdev, in, sizeof(in)); +} +EXPORT_SYMBOL_GPL(mlx5_set_port_tc_group); + +int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw) +{ + u32 in[MLX5_ST_SZ_DW(qetc_reg)]; + int i; + + memset(in, 0, sizeof(in)); + + for (i = 0; i <= mlx5_max_tc(mdev); i++) { + MLX5_SET(qetc_reg, in, tc_configuration[i].b, 1); + MLX5_SET(qetc_reg, in, tc_configuration[i].bw_allocation, tc_bw[i]); + } + + return mlx5_set_port_qetcr_reg(mdev, in, sizeof(in)); +} +EXPORT_SYMBOL_GPL(mlx5_set_port_tc_bw_alloc); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 02adc67720ce..a815da92d4eb 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -99,6 +99,8 @@ enum { }; enum { + MLX5_REG_QETCR = 0x4005, + MLX5_REG_QTCT = 0x400a, MLX5_REG_PCAP = 0x5001, MLX5_REG_PMTU = 0x5003, MLX5_REG_PTYS = 0x5004, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 51f1e540fc2b..ec957e059de8 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -729,7 +729,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_1bf[0x3]; u8 log_max_msg[0x5]; - u8 reserved_at_1c7[0x18]; + u8 reserved_at_1c7[0x4]; + u8 max_tc[0x4]; + u8 reserved_at_1cf[0x10]; u8 stat_rate_support[0x10]; u8 reserved_at_1ef[0xc]; @@ -7061,4 +7063,49 @@ struct mlx5_ifc_modify_flow_table_in_bits { u8 reserved_at_100[0x100]; }; +struct mlx5_ifc_ets_tcn_config_reg_bits { + u8 g[0x1]; + u8 b[0x1]; + u8 r[0x1]; + u8 reserved_at_3[0x9]; + u8 group[0x4]; + u8 reserved_at_10[0x9]; + u8 bw_allocation[0x7]; + + u8 reserved_at_20[0xc]; + u8 max_bw_units[0x4]; + u8 reserved_at_30[0x8]; + u8 max_bw_value[0x8]; +}; + +struct mlx5_ifc_ets_global_config_reg_bits { + u8 reserved_at_0[0x2]; + u8 r[0x1]; + u8 reserved_at_3[0x1d]; + + u8 reserved_at_20[0xc]; + u8 max_bw_units[0x4]; + u8 reserved_at_30[0x8]; + u8 max_bw_value[0x8]; +}; + +struct mlx5_ifc_qetc_reg_bits { + u8 reserved_at_0[0x8]; + u8 port_number[0x8]; + u8 reserved_at_10[0x30]; + + struct mlx5_ifc_ets_tcn_config_reg_bits tc_configuration[0x8]; + struct mlx5_ifc_ets_global_config_reg_bits global_configuration; +}; + +struct mlx5_ifc_qtct_reg_bits { + u8 reserved_at_0[0x8]; + u8 port_number[0x8]; + u8 reserved_at_10[0xd]; + u8 prio[0x3]; + + u8 reserved_at_20[0x1d]; + u8 tclass[0x3]; +}; + #endif /* MLX5_IFC_H */ diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 4b3644caa936..0c67e699d017 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -70,4 +70,10 @@ int mlx5_set_port_pfc(struct mlx5_core_dev *dev, u8 pfc_en_tx, u8 pfc_en_rx); int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, u8 *pfc_en_rx); +int mlx5_max_tc(struct mlx5_core_dev *mdev); + +int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc); +int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group); +int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw); + #endif /* __MLX5_PORT_H__ */ -- cgit v1.2.3 From d8880795dabf2381ed1e98348f6d9c7ea6fab950 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 22 Feb 2016 18:17:28 +0200 Subject: net/mlx5e: Implement DCBNL IEEE max rate Add support for DCBNL IEEE get/set max rate. Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c | 73 ++++++++++++++++++++++ drivers/net/ethernet/mellanox/mlx5/core/port.c | 65 +++++++++++++++++++ include/linux/mlx5/device.h | 6 ++ include/linux/mlx5/port.h | 6 ++ 4 files changed, 150 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 39d8069ba9e3..3036f279a8fd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -35,6 +35,9 @@ #define MLX5E_MAX_PRIORITY 8 +#define MLX5E_100MB (100000) +#define MLX5E_1GB (1000000) + static int mlx5e_dcbnl_ieee_getets(struct net_device *netdev, struct ieee_ets *ets) { @@ -219,9 +222,79 @@ static u8 mlx5e_dcbnl_setdcbx(struct net_device *dev, u8 mode) return 0; } +static int mlx5e_dcbnl_ieee_getmaxrate(struct net_device *netdev, + struct ieee_maxrate *maxrate) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + u8 max_bw_value[IEEE_8021QAZ_MAX_TCS]; + u8 max_bw_unit[IEEE_8021QAZ_MAX_TCS]; + int err; + int i; + + err = mlx5_query_port_ets_rate_limit(mdev, max_bw_value, max_bw_unit); + if (err) + return err; + + memset(maxrate->tc_maxrate, 0, sizeof(maxrate->tc_maxrate)); + + for (i = 0; i <= mlx5_max_tc(mdev); i++) { + switch (max_bw_unit[i]) { + case MLX5_100_MBPS_UNIT: + maxrate->tc_maxrate[i] = max_bw_value[i] * MLX5E_100MB; + break; + case MLX5_GBPS_UNIT: + maxrate->tc_maxrate[i] = max_bw_value[i] * MLX5E_1GB; + break; + case MLX5_BW_NO_LIMIT: + break; + default: + WARN(true, "non-supported BW unit"); + break; + } + } + + return 0; +} + +static int mlx5e_dcbnl_ieee_setmaxrate(struct net_device *netdev, + struct ieee_maxrate *maxrate) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + u8 max_bw_value[IEEE_8021QAZ_MAX_TCS]; + u8 max_bw_unit[IEEE_8021QAZ_MAX_TCS]; + __u64 upper_limit_mbps = roundup(255 * MLX5E_100MB, MLX5E_1GB); + int i; + + memset(max_bw_value, 0, sizeof(max_bw_value)); + memset(max_bw_unit, 0, sizeof(max_bw_unit)); + + for (i = 0; i <= mlx5_max_tc(mdev); i++) { + if (!maxrate->tc_maxrate[i]) { + max_bw_unit[i] = MLX5_BW_NO_LIMIT; + continue; + } + if (maxrate->tc_maxrate[i] < upper_limit_mbps) { + max_bw_value[i] = div_u64(maxrate->tc_maxrate[i], + MLX5E_100MB); + max_bw_value[i] = max_bw_value[i] ? max_bw_value[i] : 1; + max_bw_unit[i] = MLX5_100_MBPS_UNIT; + } else { + max_bw_value[i] = div_u64(maxrate->tc_maxrate[i], + MLX5E_1GB); + max_bw_unit[i] = MLX5_GBPS_UNIT; + } + } + + return mlx5_modify_port_ets_rate_limit(mdev, max_bw_value, max_bw_unit); +} + const struct dcbnl_rtnl_ops mlx5e_dcbnl_ops = { .ieee_getets = mlx5e_dcbnl_ieee_getets, .ieee_setets = mlx5e_dcbnl_ieee_setets, + .ieee_getmaxrate = mlx5e_dcbnl_ieee_getmaxrate, + .ieee_setmaxrate = mlx5e_dcbnl_ieee_setmaxrate, .ieee_getpfc = mlx5e_dcbnl_ieee_getpfc, .ieee_setpfc = mlx5e_dcbnl_ieee_setpfc, .getdcbx = mlx5e_dcbnl_getdcbx, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 569100d3f57b..d97605ef3efd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -450,6 +450,19 @@ static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in, MLX5_REG_QETCR, 0, 1); } +static int mlx5_query_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *out, + int outlen) +{ + u32 in[MLX5_ST_SZ_DW(qtct_reg)]; + + if (!MLX5_CAP_GEN(mdev, ets)) + return -ENOTSUPP; + + memset(in, 0, sizeof(in)); + return mlx5_core_access_reg(mdev, in, sizeof(in), out, outlen, + MLX5_REG_QETCR, 0, 0); +} + int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group) { u32 in[MLX5_ST_SZ_DW(qetc_reg)]; @@ -481,3 +494,55 @@ int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw) return mlx5_set_port_qetcr_reg(mdev, in, sizeof(in)); } EXPORT_SYMBOL_GPL(mlx5_set_port_tc_bw_alloc); + +int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev, + u8 *max_bw_value, + u8 *max_bw_units) +{ + u32 in[MLX5_ST_SZ_DW(qetc_reg)]; + void *ets_tcn_conf; + int i; + + memset(in, 0, sizeof(in)); + + MLX5_SET(qetc_reg, in, port_number, 1); + + for (i = 0; i <= mlx5_max_tc(mdev); i++) { + ets_tcn_conf = MLX5_ADDR_OF(qetc_reg, in, tc_configuration[i]); + + MLX5_SET(ets_tcn_config_reg, ets_tcn_conf, r, 1); + MLX5_SET(ets_tcn_config_reg, ets_tcn_conf, max_bw_units, + max_bw_units[i]); + MLX5_SET(ets_tcn_config_reg, ets_tcn_conf, max_bw_value, + max_bw_value[i]); + } + + return mlx5_set_port_qetcr_reg(mdev, in, sizeof(in)); +} +EXPORT_SYMBOL_GPL(mlx5_modify_port_ets_rate_limit); + +int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev, + u8 *max_bw_value, + u8 *max_bw_units) +{ + u32 out[MLX5_ST_SZ_DW(qetc_reg)]; + void *ets_tcn_conf; + int err; + int i; + + err = mlx5_query_port_qetcr_reg(mdev, out, sizeof(out)); + if (err) + return err; + + for (i = 0; i <= mlx5_max_tc(mdev); i++) { + ets_tcn_conf = MLX5_ADDR_OF(qetc_reg, out, tc_configuration[i]); + + max_bw_value[i] = MLX5_GET(ets_tcn_config_reg, ets_tcn_conf, + max_bw_value); + max_bw_units[i] = MLX5_GET(ets_tcn_config_reg, ets_tcn_conf, + max_bw_units); + } + + return 0; +} +EXPORT_SYMBOL_GPL(mlx5_query_port_ets_rate_limit); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 987764afa65c..bfc1ab0552d3 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -350,6 +350,12 @@ enum { MLX5_SET_PORT_PKEY_TABLE = 20, }; +enum { + MLX5_BW_NO_LIMIT = 0, + MLX5_100_MBPS_UNIT = 3, + MLX5_GBPS_UNIT = 4, +}; + enum { MLX5_MAX_PAGE_SHIFT = 31 }; diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 0c67e699d017..595c7b2d9bfa 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -75,5 +75,11 @@ int mlx5_max_tc(struct mlx5_core_dev *mdev); int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc); int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group); int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw); +int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev, + u8 *max_bw_value, + u8 *max_bw_unit); +int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev, + u8 *max_bw_value, + u8 *max_bw_unit); #endif /* __MLX5_PORT_H__ */ -- cgit v1.2.3 From 928cfe8745a62e60c1e8e06676a74724e7786024 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 22 Feb 2016 18:17:29 +0200 Subject: net/mlx5e: Wake On LAN support Implement set/get WOL by ethtool and added the needed device commands and structures to mlx5_ifc. Signed-off-by: Tariq Toukan Signed-off-by: Rana Shahout Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 6 + .../net/ethernet/mellanox/mlx5/core/en_ethtool.c | 125 +++++++++++++++++++++ drivers/net/ethernet/mellanox/mlx5/core/port.c | 38 +++++++ include/linux/mlx5/device.h | 11 ++ include/linux/mlx5/mlx5_ifc.h | 62 +++++++++- include/linux/mlx5/port.h | 2 + 6 files changed, 243 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 037fc4cdf5af..9ce87c624450 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -560,6 +560,12 @@ const char *mlx5_command_str(int command) case MLX5_CMD_OP_ACCESS_REG: return "MLX5_CMD_OP_ACCESS_REG"; + case MLX5_CMD_OP_SET_WOL_ROL: + return "SET_WOL_ROL"; + + case MLX5_CMD_OP_QUERY_WOL_ROL: + return "QUERY_WOL_ROL"; + default: return "unknown command opcode"; } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 65624ac65b4c..e9760f895744 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -884,6 +884,129 @@ static int mlx5e_get_ts_info(struct net_device *dev, return 0; } +static __u32 mlx5e_get_wol_supported(struct mlx5_core_dev *mdev) +{ + __u32 ret = 0; + + if (MLX5_CAP_GEN(mdev, wol_g)) + ret |= WAKE_MAGIC; + + if (MLX5_CAP_GEN(mdev, wol_s)) + ret |= WAKE_MAGICSECURE; + + if (MLX5_CAP_GEN(mdev, wol_a)) + ret |= WAKE_ARP; + + if (MLX5_CAP_GEN(mdev, wol_b)) + ret |= WAKE_BCAST; + + if (MLX5_CAP_GEN(mdev, wol_m)) + ret |= WAKE_MCAST; + + if (MLX5_CAP_GEN(mdev, wol_u)) + ret |= WAKE_UCAST; + + if (MLX5_CAP_GEN(mdev, wol_p)) + ret |= WAKE_PHY; + + return ret; +} + +static __u32 mlx5e_refomrat_wol_mode_mlx5_to_linux(u8 mode) +{ + __u32 ret = 0; + + if (mode & MLX5_WOL_MAGIC) + ret |= WAKE_MAGIC; + + if (mode & MLX5_WOL_SECURED_MAGIC) + ret |= WAKE_MAGICSECURE; + + if (mode & MLX5_WOL_ARP) + ret |= WAKE_ARP; + + if (mode & MLX5_WOL_BROADCAST) + ret |= WAKE_BCAST; + + if (mode & MLX5_WOL_MULTICAST) + ret |= WAKE_MCAST; + + if (mode & MLX5_WOL_UNICAST) + ret |= WAKE_UCAST; + + if (mode & MLX5_WOL_PHY_ACTIVITY) + ret |= WAKE_PHY; + + return ret; +} + +static u8 mlx5e_refomrat_wol_mode_linux_to_mlx5(__u32 mode) +{ + u8 ret = 0; + + if (mode & WAKE_MAGIC) + ret |= MLX5_WOL_MAGIC; + + if (mode & WAKE_MAGICSECURE) + ret |= MLX5_WOL_SECURED_MAGIC; + + if (mode & WAKE_ARP) + ret |= MLX5_WOL_ARP; + + if (mode & WAKE_BCAST) + ret |= MLX5_WOL_BROADCAST; + + if (mode & WAKE_MCAST) + ret |= MLX5_WOL_MULTICAST; + + if (mode & WAKE_UCAST) + ret |= MLX5_WOL_UNICAST; + + if (mode & WAKE_PHY) + ret |= MLX5_WOL_PHY_ACTIVITY; + + return ret; +} + +static void mlx5e_get_wol(struct net_device *netdev, + struct ethtool_wolinfo *wol) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + u8 mlx5_wol_mode; + int err; + + memset(wol, 0, sizeof(*wol)); + + wol->supported = mlx5e_get_wol_supported(mdev); + if (!wol->supported) + return; + + err = mlx5_query_port_wol(mdev, &mlx5_wol_mode); + if (err) + return; + + wol->wolopts = mlx5e_refomrat_wol_mode_mlx5_to_linux(mlx5_wol_mode); +} + +static int mlx5e_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + __u32 wol_supported = mlx5e_get_wol_supported(mdev); + u32 mlx5_wol_mode; + + if (!wol_supported) + return -ENOTSUPP; + + if (wol->wolopts & ~wol_supported) + return -EINVAL; + + mlx5_wol_mode = mlx5e_refomrat_wol_mode_linux_to_mlx5(wol->wolopts); + + return mlx5_set_port_wol(mdev, mlx5_wol_mode); +} + const struct ethtool_ops mlx5e_ethtool_ops = { .get_drvinfo = mlx5e_get_drvinfo, .get_link = ethtool_op_get_link, @@ -908,4 +1031,6 @@ const struct ethtool_ops mlx5e_ethtool_ops = { .get_pauseparam = mlx5e_get_pauseparam, .set_pauseparam = mlx5e_set_pauseparam, .get_ts_info = mlx5e_get_ts_info, + .get_wol = mlx5e_get_wol, + .set_wol = mlx5e_set_wol, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index d97605ef3efd..e1f2e1059cfd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -546,3 +546,41 @@ int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev, return 0; } EXPORT_SYMBOL_GPL(mlx5_query_port_ets_rate_limit); + +int mlx5_set_port_wol(struct mlx5_core_dev *mdev, u8 wol_mode) +{ + u32 in[MLX5_ST_SZ_DW(set_wol_rol_in)]; + u32 out[MLX5_ST_SZ_DW(set_wol_rol_out)]; + + memset(in, 0, sizeof(in)); + memset(out, 0, sizeof(out)); + + MLX5_SET(set_wol_rol_in, in, opcode, MLX5_CMD_OP_SET_WOL_ROL); + MLX5_SET(set_wol_rol_in, in, wol_mode_valid, 1); + MLX5_SET(set_wol_rol_in, in, wol_mode, wol_mode); + + return mlx5_cmd_exec_check_status(mdev, in, sizeof(in), + out, sizeof(out)); +} +EXPORT_SYMBOL_GPL(mlx5_set_port_wol); + +int mlx5_query_port_wol(struct mlx5_core_dev *mdev, u8 *wol_mode) +{ + u32 in[MLX5_ST_SZ_DW(query_wol_rol_in)]; + u32 out[MLX5_ST_SZ_DW(query_wol_rol_out)]; + int err; + + memset(in, 0, sizeof(in)); + memset(out, 0, sizeof(out)); + + MLX5_SET(query_wol_rol_in, in, opcode, MLX5_CMD_OP_QUERY_WOL_ROL); + + err = mlx5_cmd_exec_check_status(mdev, in, sizeof(in), + out, sizeof(out)); + + if (!err) + *wol_mode = MLX5_GET(query_wol_rol_out, out, wol_mode); + + return err; +} +EXPORT_SYMBOL_GPL(mlx5_query_port_wol); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index bfc1ab0552d3..68a56bc37df2 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1183,6 +1183,17 @@ enum { MLX5_RQC_RQ_TYPE_MEMORY_RQ_RPM = 0x1, }; +enum mlx5_wol_mode { + MLX5_WOL_DISABLE = 0, + MLX5_WOL_SECURED_MAGIC = 1 << 1, + MLX5_WOL_MAGIC = 1 << 2, + MLX5_WOL_ARP = 1 << 3, + MLX5_WOL_BROADCAST = 1 << 4, + MLX5_WOL_MULTICAST = 1 << 5, + MLX5_WOL_UNICAST = 1 << 6, + MLX5_WOL_PHY_ACTIVITY = 1 << 7, +}; + /* MLX5 DEV CAPs */ /* TODO: EAT.ME */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index ec957e059de8..03ffe9530365 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -166,6 +166,8 @@ enum { MLX5_CMD_OP_SET_L2_TABLE_ENTRY = 0x829, MLX5_CMD_OP_QUERY_L2_TABLE_ENTRY = 0x82a, MLX5_CMD_OP_DELETE_L2_TABLE_ENTRY = 0x82b, + MLX5_CMD_OP_SET_WOL_ROL = 0x830, + MLX5_CMD_OP_QUERY_WOL_ROL = 0x831, MLX5_CMD_OP_CREATE_TIR = 0x900, MLX5_CMD_OP_MODIFY_TIR = 0x901, MLX5_CMD_OP_DESTROY_TIR = 0x902, @@ -731,7 +733,17 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_msg[0x5]; u8 reserved_at_1c7[0x4]; u8 max_tc[0x4]; - u8 reserved_at_1cf[0x10]; + u8 reserved_at_1cf[0x6]; + u8 rol_s[0x1]; + u8 rol_g[0x1]; + u8 reserved_at_1d7[0x1]; + u8 wol_s[0x1]; + u8 wol_g[0x1]; + u8 wol_a[0x1]; + u8 wol_b[0x1]; + u8 wol_m[0x1]; + u8 wol_u[0x1]; + u8 wol_p[0x1]; u8 stat_rate_support[0x10]; u8 reserved_at_1ef[0xc]; @@ -6873,6 +6885,54 @@ struct mlx5_ifc_mtt_bits { u8 rd_en[0x1]; }; +struct mlx5_ifc_query_wol_rol_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x10]; + u8 rol_mode[0x8]; + u8 wol_mode[0x8]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_query_wol_rol_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_set_wol_rol_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_set_wol_rol_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 rol_mode_valid[0x1]; + u8 wol_mode_valid[0x1]; + u8 reserved_at_42[0xe]; + u8 rol_mode[0x8]; + u8 wol_mode[0x8]; + + u8 reserved_at_60[0x20]; +}; + enum { MLX5_INITIAL_SEG_NIC_INTERFACE_FULL_DRIVER = 0x0, MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED = 0x1, diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 595c7b2d9bfa..a1d145abd4eb 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -81,5 +81,7 @@ int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev, int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev, u8 *max_bw_value, u8 *max_bw_unit); +int mlx5_set_port_wol(struct mlx5_core_dev *mdev, u8 wol_mode); +int mlx5_query_port_wol(struct mlx5_core_dev *mdev, u8 *wol_mode); #endif /* __MLX5_PORT_H__ */ -- cgit v1.2.3 From f1705ec197e705b79ea40fe7a2cc5acfa1d3bfac Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 24 Feb 2016 09:25:37 -0800 Subject: net: ipv6: Make address flushing on ifdown optional Currently, all ipv6 addresses are flushed when the interface is configured down, including global, static addresses: $ ip -6 addr show dev eth1 3: eth1: mtu 1500 state UP qlen 1000 inet6 2100:1::2/120 scope global valid_lft forever preferred_lft forever inet6 fe80::e0:f9ff:fe79:34bd/64 scope link valid_lft forever preferred_lft forever $ ip link set dev eth1 down $ ip -6 addr show dev eth1 << nothing; all addresses have been flushed>> Add a new sysctl to make this behavior optional. The new setting defaults to flush all addresses to maintain backwards compatibility. When the set global addresses with no expire times are not flushed on an admin down. The sysctl is per-interface or system-wide for all interfaces $ sysctl -w net.ipv6.conf.eth1.keep_addr_on_down=1 or $ sysctl -w net.ipv6.conf.all.keep_addr_on_down=1 Will keep addresses on eth1 on an admin down. $ ip -6 addr show dev eth1 3: eth1: mtu 1500 state UP qlen 1000 inet6 2100:1::2/120 scope global valid_lft forever preferred_lft forever inet6 fe80::e0:f9ff:fe79:34bd/64 scope link valid_lft forever preferred_lft forever $ ip link set dev eth1 down $ ip -6 addr show dev eth1 3: eth1: mtu 1500 state DOWN qlen 1000 inet6 2100:1::2/120 scope global tentative valid_lft forever preferred_lft forever inet6 fe80::e0:f9ff:fe79:34bd/64 scope link tentative valid_lft forever preferred_lft forever Signed-off-by: David Ahern Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 9 +++ include/linux/ipv6.h | 1 + include/uapi/linux/ipv6.h | 1 + net/ipv6/addrconf.c | 136 +++++++++++++++++++++++++++++---- 4 files changed, 132 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 24ce97f42d35..d5df40c75aa4 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -1563,6 +1563,15 @@ temp_prefered_lft - INTEGER Preferred lifetime (in seconds) for temporary addresses. Default: 86400 (1 day) +keep_addr_on_down - INTEGER + Keep all IPv6 addresses on an interface down event. If set static + global addresses with no expiration time are not flushed. + >0 : enabled + 0 : system default + <0 : disabled + + Default: 0 (addresses are removed) + max_desync_factor - INTEGER Maximum value for DESYNC_FACTOR, which is a random value that ensures that clients don't synchronize with each diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 4b2267e1b7c3..7edc14fb66b6 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -62,6 +62,7 @@ struct ipv6_devconf { struct in6_addr secret; } stable_secret; __s32 use_oif_addrs_only; + __s32 keep_addr_on_down; void *sysctl; }; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index ec117b65d5a5..395876060f50 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -176,6 +176,7 @@ enum { DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN, DEVCONF_DROP_UNICAST_IN_L2_MULTICAST, DEVCONF_DROP_UNSOLICITED_NA, + DEVCONF_KEEP_ADDR_ON_DOWN, DEVCONF_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 4751f8922362..a2d6f6c242af 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -216,6 +216,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { }, .use_oif_addrs_only = 0, .ignore_routes_with_linkdown = 0, + .keep_addr_on_down = 0, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -260,6 +261,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { }, .use_oif_addrs_only = 0, .ignore_routes_with_linkdown = 0, + .keep_addr_on_down = 0, }; /* Check if a valid qdisc is available */ @@ -3168,6 +3170,55 @@ static void addrconf_gre_config(struct net_device *dev) } #endif +static int fixup_permanent_addr(struct inet6_dev *idev, + struct inet6_ifaddr *ifp) +{ + if (!ifp->rt) { + struct rt6_info *rt; + + rt = addrconf_dst_alloc(idev, &ifp->addr, false); + if (unlikely(IS_ERR(rt))) + return PTR_ERR(rt); + + ifp->rt = rt; + } + + if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) { + addrconf_prefix_route(&ifp->addr, ifp->prefix_len, + idev->dev, 0, 0); + } + + addrconf_dad_start(ifp); + + return 0; +} + +static void addrconf_permanent_addr(struct net_device *dev) +{ + struct inet6_ifaddr *ifp, *tmp; + struct inet6_dev *idev; + + idev = __in6_dev_get(dev); + if (!idev) + return; + + write_lock_bh(&idev->lock); + + list_for_each_entry_safe(ifp, tmp, &idev->addr_list, if_list) { + if ((ifp->flags & IFA_F_PERMANENT) && + fixup_permanent_addr(idev, ifp) < 0) { + write_unlock_bh(&idev->lock); + ipv6_del_addr(ifp); + write_lock_bh(&idev->lock); + + net_info_ratelimited("%s: Failed to add prefix route for address %pI6c; dropping\n", + idev->dev->name, &ifp->addr); + } + } + + write_unlock_bh(&idev->lock); +} + static int addrconf_notify(struct notifier_block *this, unsigned long event, void *ptr) { @@ -3253,6 +3304,9 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, run_pending = 1; } + /* restore routes for permanent addresses */ + addrconf_permanent_addr(dev); + switch (dev->type) { #if IS_ENABLED(CONFIG_IPV6_SIT) case ARPHRD_SIT: @@ -3356,7 +3410,10 @@ static int addrconf_ifdown(struct net_device *dev, int how) { struct net *net = dev_net(dev); struct inet6_dev *idev; - struct inet6_ifaddr *ifa; + struct inet6_ifaddr *ifa, *tmp; + struct list_head del_list; + int _keep_addr; + bool keep_addr; int state, i; ASSERT_RTNL(); @@ -3383,6 +3440,16 @@ static int addrconf_ifdown(struct net_device *dev, int how) } + /* aggregate the system setting and interface setting */ + _keep_addr = net->ipv6.devconf_all->keep_addr_on_down; + if (!_keep_addr) + _keep_addr = idev->cnf.keep_addr_on_down; + + /* combine the user config with event to determine if permanent + * addresses are to be removed from address hash table + */ + keep_addr = !(how || _keep_addr <= 0); + /* Step 2: clear hash table */ for (i = 0; i < IN6_ADDR_HSIZE; i++) { struct hlist_head *h = &inet6_addr_lst[i]; @@ -3391,9 +3458,15 @@ static int addrconf_ifdown(struct net_device *dev, int how) restart: hlist_for_each_entry_rcu(ifa, h, addr_lst) { if (ifa->idev == idev) { - hlist_del_init_rcu(&ifa->addr_lst); addrconf_del_dad_work(ifa); - goto restart; + /* combined flag + permanent flag decide if + * address is retained on a down event + */ + if (!keep_addr || + !(ifa->flags & IFA_F_PERMANENT)) { + hlist_del_init_rcu(&ifa->addr_lst); + goto restart; + } } } spin_unlock_bh(&addrconf_hash_lock); @@ -3427,31 +3500,53 @@ restart: write_lock_bh(&idev->lock); } - while (!list_empty(&idev->addr_list)) { - ifa = list_first_entry(&idev->addr_list, - struct inet6_ifaddr, if_list); - addrconf_del_dad_work(ifa); + /* re-combine the user config with event to determine if permanent + * addresses are to be removed from the interface list + */ + keep_addr = (!how && _keep_addr > 0); - list_del(&ifa->if_list); + INIT_LIST_HEAD(&del_list); + list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) { + addrconf_del_dad_work(ifa); write_unlock_bh(&idev->lock); - spin_lock_bh(&ifa->lock); - state = ifa->state; - ifa->state = INET6_IFADDR_STATE_DEAD; + + if (keep_addr && (ifa->flags & IFA_F_PERMANENT)) { + /* set state to skip the notifier below */ + state = INET6_IFADDR_STATE_DEAD; + ifa->state = 0; + if (!(ifa->flags & IFA_F_NODAD)) + ifa->flags |= IFA_F_TENTATIVE; + } else { + state = ifa->state; + ifa->state = INET6_IFADDR_STATE_DEAD; + + list_del(&ifa->if_list); + list_add(&ifa->if_list, &del_list); + } + spin_unlock_bh(&ifa->lock); if (state != INET6_IFADDR_STATE_DEAD) { __ipv6_ifa_notify(RTM_DELADDR, ifa); inet6addr_notifier_call_chain(NETDEV_DOWN, ifa); } - in6_ifa_put(ifa); write_lock_bh(&idev->lock); } write_unlock_bh(&idev->lock); + /* now clean up addresses to be removed */ + while (!list_empty(&del_list)) { + ifa = list_first_entry(&del_list, + struct inet6_ifaddr, if_list); + list_del(&ifa->if_list); + + in6_ifa_put(ifa); + } + /* Step 5: Discard anycast and multicast list */ if (how) { ipv6_ac_destroy_dev(idev); @@ -4716,6 +4811,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_USE_OIF_ADDRS_ONLY] = cnf->use_oif_addrs_only; array[DEVCONF_DROP_UNICAST_IN_L2_MULTICAST] = cnf->drop_unicast_in_l2_multicast; array[DEVCONF_DROP_UNSOLICITED_NA] = cnf->drop_unsolicited_na; + array[DEVCONF_KEEP_ADDR_ON_DOWN] = cnf->keep_addr_on_down; } static inline size_t inet6_ifla6_size(void) @@ -5197,10 +5293,12 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) if (rt) ip6_del_rt(rt); } - dst_hold(&ifp->rt->dst); - - ip6_del_rt(ifp->rt); + if (ifp->rt) { + dst_hold(&ifp->rt->dst); + ip6_del_rt(ifp->rt); + ifp->rt = NULL; + } rt_genid_bump_ipv6(net); break; } @@ -5803,6 +5901,14 @@ static struct addrconf_sysctl_table .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "keep_addr_on_down", + .data = &ipv6_devconf.keep_addr_on_down, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + + }, { /* sentinel */ } -- cgit v1.2.3 From 3f1ac7a700d039c61d8d8b99f28d605d489a60cf Mon Sep 17 00:00:00 2001 From: David Decotigny Date: Wed, 24 Feb 2016 10:57:59 -0800 Subject: net: ethtool: add new ETHTOOL_xLINKSETTINGS API This patch defines a new ETHTOOL_GLINKSETTINGS/SLINKSETTINGS API, handled by the new get_link_ksettings/set_link_ksettings callbacks. This API provides support for most legacy ethtool_cmd fields, adds support for larger link mode masks (up to 4064 bits, variable length), and removes ethtool_cmd deprecated fields (transceiver/maxrxpkt/maxtxpkt). This API is deprecating the legacy ETHTOOL_GSET/SSET API and provides the following backward compatibility properties: - legacy ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks. - legacy ethtool with new get/set_link_ksettings drivers: the new driver callbacks are used, data internally converted to legacy ethtool_cmd. ETHTOOL_GSET will return only the 1st 32b of each link mode mask. ETHTOOL_SSET will fail if user tries to set the ethtool_cmd deprecated fields to non-0 (transceiver/maxrxpkt/maxtxpkt). A kernel warning is logged if driver sets higher bits. - future ethtool with legacy drivers: no change, still using the get_settings/set_settings callbacks, internally converted to new data structure. Deprecated fields (transceiver/maxrxpkt/maxtxpkt) will be ignored and seen as 0 from user space. Note that that "future" ethtool tool will not allow changes to these deprecated fields. - future ethtool with new drivers: direct call to the new callbacks. By "future" ethtool, what is meant is: - query: first try ETHTOOL_GLINKSETTINGS, and revert to ETHTOOL_GSET if fails - set: query first and remember which of ETHTOOL_GLINKSETTINGS or ETHTOOL_GSET was successful + if ETHTOOL_GLINKSETTINGS was successful, then change config with ETHTOOL_SLINKSETTINGS. A failure there is final (do not try ETHTOOL_SSET). + otherwise ETHTOOL_GSET was successful, change config with ETHTOOL_SSET. A failure there is final (do not try ETHTOOL_SLINKSETTINGS). The interaction user/kernel via the new API requires a small ETHTOOL_GLINKSETTINGS handshake first to agree on the length of the link mode bitmaps. If kernel doesn't agree with user, it returns the bitmap length it is expecting from user as a negative length (and cmd field is 0). When kernel and user agree, kernel returns valid info in all fields (ie. link mode length > 0 and cmd is ETHTOOL_GLINKSETTINGS). Data structure crossing user/kernel boundary is 32/64-bit agnostic. Converted internally to a legal kernel bitmap. The internal __ethtool_get_settings kernel helper will gradually be replaced by __ethtool_get_link_ksettings by the time the first "link_settings" drivers start to appear. So this patch doesn't change it, it will be removed before it needs to be changed. Signed-off-by: David Decotigny Signed-off-by: David S. Miller --- include/linux/ethtool.h | 91 ++++++++- include/uapi/linux/ethtool.h | 322 +++++++++++++++++++++++------- net/core/ethtool.c | 453 ++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 786 insertions(+), 80 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 472d7d7b01c2..8a400a54c92e 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -12,6 +12,7 @@ #ifndef _LINUX_ETHTOOL_H #define _LINUX_ETHTOOL_H +#include #include #include @@ -40,9 +41,6 @@ struct compat_ethtool_rxnfc { #include -extern int __ethtool_get_settings(struct net_device *dev, - struct ethtool_cmd *cmd); - /** * enum ethtool_phys_id_state - indicator state for physical identification * @ETHTOOL_ID_INACTIVE: Physical ID indicator should be deactivated @@ -97,13 +95,74 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) return index % n_rx_rings; } +/* number of link mode bits/ulongs handled internally by kernel */ +#define __ETHTOOL_LINK_MODE_MASK_NBITS \ + (__ETHTOOL_LINK_MODE_LAST + 1) + +/* declare a link mode bitmap */ +#define __ETHTOOL_DECLARE_LINK_MODE_MASK(name) \ + DECLARE_BITMAP(name, __ETHTOOL_LINK_MODE_MASK_NBITS) + +/* drivers must ignore base.cmd and base.link_mode_masks_nwords + * fields, but they are allowed to overwrite them (will be ignored). + */ +struct ethtool_link_ksettings { + struct ethtool_link_settings base; + struct { + __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); + __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); + __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); + } link_modes; +}; + +/** + * ethtool_link_ksettings_zero_link_mode - clear link_ksettings link mode mask + * @ptr : pointer to struct ethtool_link_ksettings + * @name : one of supported/advertising/lp_advertising + */ +#define ethtool_link_ksettings_zero_link_mode(ptr, name) \ + bitmap_zero((ptr)->link_modes.name, __ETHTOOL_LINK_MODE_MASK_NBITS) + +/** + * ethtool_link_ksettings_add_link_mode - set bit in link_ksettings + * link mode mask + * @ptr : pointer to struct ethtool_link_ksettings + * @name : one of supported/advertising/lp_advertising + * @mode : one of the ETHTOOL_LINK_MODE_*_BIT + * (not atomic, no bound checking) + */ +#define ethtool_link_ksettings_add_link_mode(ptr, name, mode) \ + __set_bit(ETHTOOL_LINK_MODE_ ## mode ## _BIT, (ptr)->link_modes.name) + +/** + * ethtool_link_ksettings_test_link_mode - test bit in ksettings link mode mask + * @ptr : pointer to struct ethtool_link_ksettings + * @name : one of supported/advertising/lp_advertising + * @mode : one of the ETHTOOL_LINK_MODE_*_BIT + * (not atomic, no bound checking) + * + * Returns true/false. + */ +#define ethtool_link_ksettings_test_link_mode(ptr, name, mode) \ + test_bit(ETHTOOL_LINK_MODE_ ## mode ## _BIT, (ptr)->link_modes.name) + +extern int +__ethtool_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *link_ksettings); + +/* DEPRECATED, use __ethtool_get_link_ksettings */ +extern int __ethtool_get_settings(struct net_device *dev, + struct ethtool_cmd *cmd); + /** * struct ethtool_ops - optional netdev operations - * @get_settings: Get various device settings including Ethernet link + * @get_settings: DEPRECATED, use %get_link_ksettings/%set_link_ksettings + * API. Get various device settings including Ethernet link * settings. The @cmd parameter is expected to have been cleared - * before get_settings is called. Returns a negative error code or - * zero. - * @set_settings: Set various device settings including Ethernet link + * before get_settings is called. Returns a negative error code + * or zero. + * @set_settings: DEPRECATED, use %get_link_ksettings/%set_link_ksettings + * API. Set various device settings including Ethernet link * settings. Returns a negative error code or zero. * @get_drvinfo: Report driver/device information. Should only set the * @driver, @version, @fw_version and @bus_info fields. If not @@ -211,6 +270,19 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) * a TX queue has this number, return -EINVAL. If only a RX queue or a TX * queue has this number, ignore the inapplicable fields. * Returns a negative error code or zero. + * @get_link_ksettings: When defined, takes precedence over the + * %get_settings method. Get various device settings + * including Ethernet link settings. The %cmd and + * %link_mode_masks_nwords fields should be ignored (use + * %__ETHTOOL_LINK_MODE_MASK_NBITS instead of the latter), any + * change to them will be overwritten by kernel. Returns a + * negative error code or zero. + * @set_link_ksettings: When defined, takes precedence over the + * %set_settings method. Set various device settings including + * Ethernet link settings. The %cmd and %link_mode_masks_nwords + * fields should be ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS + * instead of the latter), any change to them will be overwritten + * by kernel. Returns a negative error code or zero. * * All operations are optional (i.e. the function pointer may be set * to %NULL) and callers must take this into account. Callers must @@ -293,6 +365,9 @@ struct ethtool_ops { struct ethtool_coalesce *); int (*set_per_queue_coalesce)(struct net_device *, u32, struct ethtool_coalesce *); - + int (*get_link_ksettings)(struct net_device *, + struct ethtool_link_ksettings *); + int (*set_link_ksettings)(struct net_device *, + const struct ethtool_link_ksettings *); }; #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index f15ae02621a1..37fd6dc33de4 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -21,7 +21,8 @@ */ /** - * struct ethtool_cmd - link control and status + * struct ethtool_cmd - DEPRECATED, link control and status + * This structure is DEPRECATED, please use struct ethtool_link_settings. * @cmd: Command number = %ETHTOOL_GSET or %ETHTOOL_SSET * @supported: Bitmask of %SUPPORTED_* flags for the link modes, * physical connectors and other link features for which the @@ -1219,8 +1220,12 @@ struct ethtool_per_queue_op { }; /* CMDs currently supported */ -#define ETHTOOL_GSET 0x00000001 /* Get settings. */ -#define ETHTOOL_SSET 0x00000002 /* Set settings. */ +#define ETHTOOL_GSET 0x00000001 /* DEPRECATED, Get settings. + * Please use ETHTOOL_GLINKSETTINGS + */ +#define ETHTOOL_SSET 0x00000002 /* DEPRECATED, Set settings. + * Please use ETHTOOL_SLINKSETTINGS + */ #define ETHTOOL_GDRVINFO 0x00000003 /* Get driver info. */ #define ETHTOOL_GREGS 0x00000004 /* Get NIC registers. */ #define ETHTOOL_GWOL 0x00000005 /* Get wake-on-lan options. */ @@ -1302,73 +1307,139 @@ struct ethtool_per_queue_op { #define ETHTOOL_PERQUEUE 0x0000004b /* Set per queue options */ +#define ETHTOOL_GLINKSETTINGS 0x0000004c /* Get ethtool_link_settings */ +#define ETHTOOL_SLINKSETTINGS 0x0000004d /* Set ethtool_link_settings */ + + /* compatibility with older code */ #define SPARC_ETH_GSET ETHTOOL_GSET #define SPARC_ETH_SSET ETHTOOL_SSET -#define SUPPORTED_10baseT_Half (1 << 0) -#define SUPPORTED_10baseT_Full (1 << 1) -#define SUPPORTED_100baseT_Half (1 << 2) -#define SUPPORTED_100baseT_Full (1 << 3) -#define SUPPORTED_1000baseT_Half (1 << 4) -#define SUPPORTED_1000baseT_Full (1 << 5) -#define SUPPORTED_Autoneg (1 << 6) -#define SUPPORTED_TP (1 << 7) -#define SUPPORTED_AUI (1 << 8) -#define SUPPORTED_MII (1 << 9) -#define SUPPORTED_FIBRE (1 << 10) -#define SUPPORTED_BNC (1 << 11) -#define SUPPORTED_10000baseT_Full (1 << 12) -#define SUPPORTED_Pause (1 << 13) -#define SUPPORTED_Asym_Pause (1 << 14) -#define SUPPORTED_2500baseX_Full (1 << 15) -#define SUPPORTED_Backplane (1 << 16) -#define SUPPORTED_1000baseKX_Full (1 << 17) -#define SUPPORTED_10000baseKX4_Full (1 << 18) -#define SUPPORTED_10000baseKR_Full (1 << 19) -#define SUPPORTED_10000baseR_FEC (1 << 20) -#define SUPPORTED_20000baseMLD2_Full (1 << 21) -#define SUPPORTED_20000baseKR2_Full (1 << 22) -#define SUPPORTED_40000baseKR4_Full (1 << 23) -#define SUPPORTED_40000baseCR4_Full (1 << 24) -#define SUPPORTED_40000baseSR4_Full (1 << 25) -#define SUPPORTED_40000baseLR4_Full (1 << 26) -#define SUPPORTED_56000baseKR4_Full (1 << 27) -#define SUPPORTED_56000baseCR4_Full (1 << 28) -#define SUPPORTED_56000baseSR4_Full (1 << 29) -#define SUPPORTED_56000baseLR4_Full (1 << 30) - -#define ADVERTISED_10baseT_Half (1 << 0) -#define ADVERTISED_10baseT_Full (1 << 1) -#define ADVERTISED_100baseT_Half (1 << 2) -#define ADVERTISED_100baseT_Full (1 << 3) -#define ADVERTISED_1000baseT_Half (1 << 4) -#define ADVERTISED_1000baseT_Full (1 << 5) -#define ADVERTISED_Autoneg (1 << 6) -#define ADVERTISED_TP (1 << 7) -#define ADVERTISED_AUI (1 << 8) -#define ADVERTISED_MII (1 << 9) -#define ADVERTISED_FIBRE (1 << 10) -#define ADVERTISED_BNC (1 << 11) -#define ADVERTISED_10000baseT_Full (1 << 12) -#define ADVERTISED_Pause (1 << 13) -#define ADVERTISED_Asym_Pause (1 << 14) -#define ADVERTISED_2500baseX_Full (1 << 15) -#define ADVERTISED_Backplane (1 << 16) -#define ADVERTISED_1000baseKX_Full (1 << 17) -#define ADVERTISED_10000baseKX4_Full (1 << 18) -#define ADVERTISED_10000baseKR_Full (1 << 19) -#define ADVERTISED_10000baseR_FEC (1 << 20) -#define ADVERTISED_20000baseMLD2_Full (1 << 21) -#define ADVERTISED_20000baseKR2_Full (1 << 22) -#define ADVERTISED_40000baseKR4_Full (1 << 23) -#define ADVERTISED_40000baseCR4_Full (1 << 24) -#define ADVERTISED_40000baseSR4_Full (1 << 25) -#define ADVERTISED_40000baseLR4_Full (1 << 26) -#define ADVERTISED_56000baseKR4_Full (1 << 27) -#define ADVERTISED_56000baseCR4_Full (1 << 28) -#define ADVERTISED_56000baseSR4_Full (1 << 29) -#define ADVERTISED_56000baseLR4_Full (1 << 30) +/* Link mode bit indices */ +enum ethtool_link_mode_bit_indices { + ETHTOOL_LINK_MODE_10baseT_Half_BIT = 0, + ETHTOOL_LINK_MODE_10baseT_Full_BIT = 1, + ETHTOOL_LINK_MODE_100baseT_Half_BIT = 2, + ETHTOOL_LINK_MODE_100baseT_Full_BIT = 3, + ETHTOOL_LINK_MODE_1000baseT_Half_BIT = 4, + ETHTOOL_LINK_MODE_1000baseT_Full_BIT = 5, + ETHTOOL_LINK_MODE_Autoneg_BIT = 6, + ETHTOOL_LINK_MODE_TP_BIT = 7, + ETHTOOL_LINK_MODE_AUI_BIT = 8, + ETHTOOL_LINK_MODE_MII_BIT = 9, + ETHTOOL_LINK_MODE_FIBRE_BIT = 10, + ETHTOOL_LINK_MODE_BNC_BIT = 11, + ETHTOOL_LINK_MODE_10000baseT_Full_BIT = 12, + ETHTOOL_LINK_MODE_Pause_BIT = 13, + ETHTOOL_LINK_MODE_Asym_Pause_BIT = 14, + ETHTOOL_LINK_MODE_2500baseX_Full_BIT = 15, + ETHTOOL_LINK_MODE_Backplane_BIT = 16, + ETHTOOL_LINK_MODE_1000baseKX_Full_BIT = 17, + ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT = 18, + ETHTOOL_LINK_MODE_10000baseKR_Full_BIT = 19, + ETHTOOL_LINK_MODE_10000baseR_FEC_BIT = 20, + ETHTOOL_LINK_MODE_20000baseMLD2_Full_BIT = 21, + ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT = 22, + ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT = 23, + ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT = 24, + ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT = 25, + ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT = 26, + ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT = 27, + ETHTOOL_LINK_MODE_56000baseCR4_Full_BIT = 28, + ETHTOOL_LINK_MODE_56000baseSR4_Full_BIT = 29, + ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT = 30, + + /* Last allowed bit for __ETHTOOL_LINK_MODE_LEGACY_MASK is bit + * 31. Please do NOT define any SUPPORTED_* or ADVERTISED_* + * macro for bits > 31. The only way to use indices > 31 is to + * use the new ETHTOOL_GLINKSETTINGS/ETHTOOL_SLINKSETTINGS API. + */ + + __ETHTOOL_LINK_MODE_LAST + = ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT, +}; + +#define __ETHTOOL_LINK_MODE_LEGACY_MASK(base_name) \ + (1UL << (ETHTOOL_LINK_MODE_ ## base_name ## _BIT)) + +/* DEPRECATED macros. Please migrate to + * ETHTOOL_GLINKSETTINGS/ETHTOOL_SLINKSETTINGS API. Please do NOT + * define any new SUPPORTED_* macro for bits > 31. + */ +#define SUPPORTED_10baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Half) +#define SUPPORTED_10baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Full) +#define SUPPORTED_100baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Half) +#define SUPPORTED_100baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Full) +#define SUPPORTED_1000baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Half) +#define SUPPORTED_1000baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Full) +#define SUPPORTED_Autoneg __ETHTOOL_LINK_MODE_LEGACY_MASK(Autoneg) +#define SUPPORTED_TP __ETHTOOL_LINK_MODE_LEGACY_MASK(TP) +#define SUPPORTED_AUI __ETHTOOL_LINK_MODE_LEGACY_MASK(AUI) +#define SUPPORTED_MII __ETHTOOL_LINK_MODE_LEGACY_MASK(MII) +#define SUPPORTED_FIBRE __ETHTOOL_LINK_MODE_LEGACY_MASK(FIBRE) +#define SUPPORTED_BNC __ETHTOOL_LINK_MODE_LEGACY_MASK(BNC) +#define SUPPORTED_10000baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseT_Full) +#define SUPPORTED_Pause __ETHTOOL_LINK_MODE_LEGACY_MASK(Pause) +#define SUPPORTED_Asym_Pause __ETHTOOL_LINK_MODE_LEGACY_MASK(Asym_Pause) +#define SUPPORTED_2500baseX_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(2500baseX_Full) +#define SUPPORTED_Backplane __ETHTOOL_LINK_MODE_LEGACY_MASK(Backplane) +#define SUPPORTED_1000baseKX_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseKX_Full) +#define SUPPORTED_10000baseKX4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKX4_Full) +#define SUPPORTED_10000baseKR_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKR_Full) +#define SUPPORTED_10000baseR_FEC __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseR_FEC) +#define SUPPORTED_20000baseMLD2_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseMLD2_Full) +#define SUPPORTED_20000baseKR2_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseKR2_Full) +#define SUPPORTED_40000baseKR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseKR4_Full) +#define SUPPORTED_40000baseCR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseCR4_Full) +#define SUPPORTED_40000baseSR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseSR4_Full) +#define SUPPORTED_40000baseLR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseLR4_Full) +#define SUPPORTED_56000baseKR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseKR4_Full) +#define SUPPORTED_56000baseCR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseCR4_Full) +#define SUPPORTED_56000baseSR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseSR4_Full) +#define SUPPORTED_56000baseLR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseLR4_Full) +/* Please do not define any new SUPPORTED_* macro for bits > 31, see + * notice above. + */ + +/* + * DEPRECATED macros. Please migrate to + * ETHTOOL_GLINKSETTINGS/ETHTOOL_SLINKSETTINGS API. Please do NOT + * define any new ADERTISE_* macro for bits > 31. + */ +#define ADVERTISED_10baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Half) +#define ADVERTISED_10baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10baseT_Full) +#define ADVERTISED_100baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Half) +#define ADVERTISED_100baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(100baseT_Full) +#define ADVERTISED_1000baseT_Half __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Half) +#define ADVERTISED_1000baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseT_Full) +#define ADVERTISED_Autoneg __ETHTOOL_LINK_MODE_LEGACY_MASK(Autoneg) +#define ADVERTISED_TP __ETHTOOL_LINK_MODE_LEGACY_MASK(TP) +#define ADVERTISED_AUI __ETHTOOL_LINK_MODE_LEGACY_MASK(AUI) +#define ADVERTISED_MII __ETHTOOL_LINK_MODE_LEGACY_MASK(MII) +#define ADVERTISED_FIBRE __ETHTOOL_LINK_MODE_LEGACY_MASK(FIBRE) +#define ADVERTISED_BNC __ETHTOOL_LINK_MODE_LEGACY_MASK(BNC) +#define ADVERTISED_10000baseT_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseT_Full) +#define ADVERTISED_Pause __ETHTOOL_LINK_MODE_LEGACY_MASK(Pause) +#define ADVERTISED_Asym_Pause __ETHTOOL_LINK_MODE_LEGACY_MASK(Asym_Pause) +#define ADVERTISED_2500baseX_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(2500baseX_Full) +#define ADVERTISED_Backplane __ETHTOOL_LINK_MODE_LEGACY_MASK(Backplane) +#define ADVERTISED_1000baseKX_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(1000baseKX_Full) +#define ADVERTISED_10000baseKX4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKX4_Full) +#define ADVERTISED_10000baseKR_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseKR_Full) +#define ADVERTISED_10000baseR_FEC __ETHTOOL_LINK_MODE_LEGACY_MASK(10000baseR_FEC) +#define ADVERTISED_20000baseMLD2_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseMLD2_Full) +#define ADVERTISED_20000baseKR2_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(20000baseKR2_Full) +#define ADVERTISED_40000baseKR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseKR4_Full) +#define ADVERTISED_40000baseCR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseCR4_Full) +#define ADVERTISED_40000baseSR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseSR4_Full) +#define ADVERTISED_40000baseLR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(40000baseLR4_Full) +#define ADVERTISED_56000baseKR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseKR4_Full) +#define ADVERTISED_56000baseCR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseCR4_Full) +#define ADVERTISED_56000baseSR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseSR4_Full) +#define ADVERTISED_56000baseLR4_Full __ETHTOOL_LINK_MODE_LEGACY_MASK(56000baseLR4_Full) +/* Please do not define any new ADVERTISED_* macro for bits > 31, see + * notice above. + */ /* The following are all involved in forcing a particular link * mode for the device for setting things. When getting the @@ -1533,4 +1604,123 @@ enum ethtool_reset_flags { }; #define ETH_RESET_SHARED_SHIFT 16 + +/** + * struct ethtool_link_settings - link control and status + * + * IMPORTANT, Backward compatibility notice: When implementing new + * user-space tools, please first try %ETHTOOL_GLINKSETTINGS, and + * if it succeeds use %ETHTOOL_SLINKSETTINGS to change link + * settings; do not use %ETHTOOL_SSET if %ETHTOOL_GLINKSETTINGS + * succeeded: stick to %ETHTOOL_GLINKSETTINGS/%SLINKSETTINGS in + * that case. Conversely, if %ETHTOOL_GLINKSETTINGS fails, use + * %ETHTOOL_GSET to query and %ETHTOOL_SSET to change link + * settings; do not use %ETHTOOL_SLINKSETTINGS if + * %ETHTOOL_GLINKSETTINGS failed: stick to + * %ETHTOOL_GSET/%ETHTOOL_SSET in that case. + * + * @cmd: Command number = %ETHTOOL_GLINKSETTINGS or %ETHTOOL_SLINKSETTINGS + * @speed: Link speed (Mbps) + * @duplex: Duplex mode; one of %DUPLEX_* + * @port: Physical connector type; one of %PORT_* + * @phy_address: MDIO address of PHY (transceiver); 0 or 255 if not + * applicable. For clause 45 PHYs this is the PRTAD. + * @autoneg: Enable/disable autonegotiation and auto-detection; + * either %AUTONEG_DISABLE or %AUTONEG_ENABLE + * @mdio_support: Bitmask of %ETH_MDIO_SUPPORTS_* flags for the MDIO + * protocols supported by the interface; 0 if unknown. + * Read-only. + * @eth_tp_mdix: Ethernet twisted-pair MDI(-X) status; one of + * %ETH_TP_MDI_*. If the status is unknown or not applicable, the + * value will be %ETH_TP_MDI_INVALID. Read-only. + * @eth_tp_mdix_ctrl: Ethernet twisted pair MDI(-X) control; one of + * %ETH_TP_MDI_*. If MDI(-X) control is not implemented, reads + * yield %ETH_TP_MDI_INVALID and writes may be ignored or rejected. + * When written successfully, the link should be renegotiated if + * necessary. + * @link_mode_masks_nwords: Number of 32-bit words for each of the + * supported, advertising, lp_advertising link mode bitmaps. For + * %ETHTOOL_GLINKSETTINGS: on entry, number of words passed by user + * (>= 0); on return, if handshake in progress, negative if + * request size unsupported by kernel: absolute value indicates + * kernel recommended size and cmd field is 0, as well as all the + * other fields; otherwise (handshake completed), strictly + * positive to indicate size used by kernel and cmd field is + * %ETHTOOL_GLINKSETTINGS, all other fields populated by driver. For + * %ETHTOOL_SLINKSETTINGS: must be valid on entry, ie. a positive + * value returned previously by %ETHTOOL_GLINKSETTINGS, otherwise + * refused. For drivers: ignore this field (use kernel's + * __ETHTOOL_LINK_MODE_MASK_NBITS instead), any change to it will + * be overwritten by kernel. + * @supported: Bitmap with each bit meaning given by + * %ethtool_link_mode_bit_indices for the link modes, physical + * connectors and other link features for which the interface + * supports autonegotiation or auto-detection. Read-only. + * @advertising: Bitmap with each bit meaning given by + * %ethtool_link_mode_bit_indices for the link modes, physical + * connectors and other link features that are advertised through + * autonegotiation or enabled for auto-detection. + * @lp_advertising: Bitmap with each bit meaning given by + * %ethtool_link_mode_bit_indices for the link modes, and other + * link features that the link partner advertised through + * autonegotiation; 0 if unknown or not applicable. Read-only. + * + * If autonegotiation is disabled, the speed and @duplex represent the + * fixed link mode and are writable if the driver supports multiple + * link modes. If it is enabled then they are read-only; if the link + * is up they represent the negotiated link mode; if the link is down, + * the speed is 0, %SPEED_UNKNOWN or the highest enabled speed and + * @duplex is %DUPLEX_UNKNOWN or the best enabled duplex mode. + * + * Some hardware interfaces may have multiple PHYs and/or physical + * connectors fitted or do not allow the driver to detect which are + * fitted. For these interfaces @port and/or @phy_address may be + * writable, possibly dependent on @autoneg being %AUTONEG_DISABLE. + * Otherwise, attempts to write different values may be ignored or + * rejected. + * + * Deprecated %ethtool_cmd fields transceiver, maxtxpkt and maxrxpkt + * are not available in %ethtool_link_settings. Until all drivers are + * converted to ignore them or to the new %ethtool_link_settings API, + * for both queries and changes, users should always try + * %ETHTOOL_GLINKSETTINGS first, and if it fails with -ENOTSUPP stick + * only to %ETHTOOL_GSET and %ETHTOOL_SSET consistently. If it + * succeeds, then users should stick to %ETHTOOL_GLINKSETTINGS and + * %ETHTOOL_SLINKSETTINGS (which would support drivers implementing + * either %ethtool_cmd or %ethtool_link_settings). + * + * Users should assume that all fields not marked read-only are + * writable and subject to validation by the driver. They should use + * %ETHTOOL_GLINKSETTINGS to get the current values before making specific + * changes and then applying them with %ETHTOOL_SLINKSETTINGS. + * + * Drivers that implement %get_link_ksettings and/or + * %set_link_ksettings should ignore the @cmd + * and @link_mode_masks_nwords fields (any change to them overwritten + * by kernel), and rely only on kernel's internal + * %__ETHTOOL_LINK_MODE_MASK_NBITS and + * %ethtool_link_mode_mask_t. Drivers that implement + * %set_link_ksettings() should validate all fields other than @cmd + * and @link_mode_masks_nwords that are not described as read-only or + * deprecated, and must ignore all fields described as read-only. + */ +struct ethtool_link_settings { + __u32 cmd; + __u32 speed; + __u8 duplex; + __u8 port; + __u8 phy_address; + __u8 autoneg; + __u8 mdio_support; + __u8 eth_tp_mdix; + __u8 eth_tp_mdix_ctrl; + __s8 link_mode_masks_nwords; + __u32 reserved[8]; + __u32 link_mode_masks[0]; + /* layout of link_mode_masks fields: + * __u32 map_supported[link_mode_masks_nwords]; + * __u32 map_advertising[link_mode_masks_nwords]; + * __u32 map_lp_advertising[link_mode_masks_nwords]; + */ +}; #endif /* _UAPI_LINUX_ETHTOOL_H */ diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 2406101002b1..edcec56ed228 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -387,6 +387,359 @@ static int __ethtool_set_flags(struct net_device *dev, u32 data) return 0; } +static void convert_legacy_u32_to_link_mode(unsigned long *dst, u32 legacy_u32) +{ + bitmap_zero(dst, __ETHTOOL_LINK_MODE_MASK_NBITS); + dst[0] = legacy_u32; +} + +/* return false if src had higher bits set. lower bits always updated. */ +static bool convert_link_mode_to_legacy_u32(u32 *legacy_u32, + const unsigned long *src) +{ + bool retval = true; + + /* TODO: following test will soon always be true */ + if (__ETHTOOL_LINK_MODE_MASK_NBITS > 32) { + __ETHTOOL_DECLARE_LINK_MODE_MASK(ext); + + bitmap_zero(ext, __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_fill(ext, 32); + bitmap_complement(ext, ext, __ETHTOOL_LINK_MODE_MASK_NBITS); + if (bitmap_intersects(ext, src, + __ETHTOOL_LINK_MODE_MASK_NBITS)) { + /* src mask goes beyond bit 31 */ + retval = false; + } + } + *legacy_u32 = src[0]; + return retval; +} + +/* return false if legacy contained non-0 deprecated fields + * transceiver/maxtxpkt/maxrxpkt. rest of ksettings always updated + */ +static bool +convert_legacy_settings_to_link_ksettings( + struct ethtool_link_ksettings *link_ksettings, + const struct ethtool_cmd *legacy_settings) +{ + bool retval = true; + + memset(link_ksettings, 0, sizeof(*link_ksettings)); + + /* This is used to tell users that driver is still using these + * deprecated legacy fields, and they should not use + * %ETHTOOL_GLINKSETTINGS/%ETHTOOL_SLINKSETTINGS + */ + if (legacy_settings->transceiver || + legacy_settings->maxtxpkt || + legacy_settings->maxrxpkt) + retval = false; + + convert_legacy_u32_to_link_mode( + link_ksettings->link_modes.supported, + legacy_settings->supported); + convert_legacy_u32_to_link_mode( + link_ksettings->link_modes.advertising, + legacy_settings->advertising); + convert_legacy_u32_to_link_mode( + link_ksettings->link_modes.lp_advertising, + legacy_settings->lp_advertising); + link_ksettings->base.speed + = ethtool_cmd_speed(legacy_settings); + link_ksettings->base.duplex + = legacy_settings->duplex; + link_ksettings->base.port + = legacy_settings->port; + link_ksettings->base.phy_address + = legacy_settings->phy_address; + link_ksettings->base.autoneg + = legacy_settings->autoneg; + link_ksettings->base.mdio_support + = legacy_settings->mdio_support; + link_ksettings->base.eth_tp_mdix + = legacy_settings->eth_tp_mdix; + link_ksettings->base.eth_tp_mdix_ctrl + = legacy_settings->eth_tp_mdix_ctrl; + return retval; +} + +/* return false if ksettings link modes had higher bits + * set. legacy_settings always updated (best effort) + */ +static bool +convert_link_ksettings_to_legacy_settings( + struct ethtool_cmd *legacy_settings, + const struct ethtool_link_ksettings *link_ksettings) +{ + bool retval = true; + + memset(legacy_settings, 0, sizeof(*legacy_settings)); + /* this also clears the deprecated fields in legacy structure: + * __u8 transceiver; + * __u32 maxtxpkt; + * __u32 maxrxpkt; + */ + + retval &= convert_link_mode_to_legacy_u32( + &legacy_settings->supported, + link_ksettings->link_modes.supported); + retval &= convert_link_mode_to_legacy_u32( + &legacy_settings->advertising, + link_ksettings->link_modes.advertising); + retval &= convert_link_mode_to_legacy_u32( + &legacy_settings->lp_advertising, + link_ksettings->link_modes.lp_advertising); + ethtool_cmd_speed_set(legacy_settings, link_ksettings->base.speed); + legacy_settings->duplex + = link_ksettings->base.duplex; + legacy_settings->port + = link_ksettings->base.port; + legacy_settings->phy_address + = link_ksettings->base.phy_address; + legacy_settings->autoneg + = link_ksettings->base.autoneg; + legacy_settings->mdio_support + = link_ksettings->base.mdio_support; + legacy_settings->eth_tp_mdix + = link_ksettings->base.eth_tp_mdix; + legacy_settings->eth_tp_mdix_ctrl + = link_ksettings->base.eth_tp_mdix_ctrl; + return retval; +} + +/* number of 32-bit words to store the user's link mode bitmaps */ +#define __ETHTOOL_LINK_MODE_MASK_NU32 \ + DIV_ROUND_UP(__ETHTOOL_LINK_MODE_MASK_NBITS, 32) + +/* layout of the struct passed from/to userland */ +struct ethtool_link_usettings { + struct ethtool_link_settings base; + struct { + __u32 supported[__ETHTOOL_LINK_MODE_MASK_NU32]; + __u32 advertising[__ETHTOOL_LINK_MODE_MASK_NU32]; + __u32 lp_advertising[__ETHTOOL_LINK_MODE_MASK_NU32]; + } link_modes; +}; + +/* Internal kernel helper to query a device ethtool_link_settings. + * + * Backward compatibility note: for compatibility with legacy drivers + * that implement only the ethtool_cmd API, this has to work with both + * drivers implementing get_link_ksettings API and drivers + * implementing get_settings API. When drivers implement get_settings + * and report ethtool_cmd deprecated fields + * (transceiver/maxrxpkt/maxtxpkt), these fields are silently ignored + * because the resulting struct ethtool_link_settings does not report them. + */ +int __ethtool_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *link_ksettings) +{ + int err; + struct ethtool_cmd cmd; + + ASSERT_RTNL(); + + if (dev->ethtool_ops->get_link_ksettings) { + memset(link_ksettings, 0, sizeof(*link_ksettings)); + return dev->ethtool_ops->get_link_ksettings(dev, + link_ksettings); + } + + /* driver doesn't support %ethtool_link_ksettings API. revert to + * legacy %ethtool_cmd API, unless it's not supported either. + * TODO: remove when ethtool_ops::get_settings disappears internally + */ + err = __ethtool_get_settings(dev, &cmd); + if (err < 0) + return err; + + /* we ignore deprecated fields transceiver/maxrxpkt/maxtxpkt + */ + convert_legacy_settings_to_link_ksettings(link_ksettings, &cmd); + return err; +} +EXPORT_SYMBOL(__ethtool_get_link_ksettings); + +/* convert ethtool_link_usettings in user space to a kernel internal + * ethtool_link_ksettings. return 0 on success, errno on error. + */ +static int load_link_ksettings_from_user(struct ethtool_link_ksettings *to, + const void __user *from) +{ + struct ethtool_link_usettings link_usettings; + + if (copy_from_user(&link_usettings, from, sizeof(link_usettings))) + return -EFAULT; + + memcpy(&to->base, &link_usettings.base, sizeof(to->base)); + bitmap_from_u32array(to->link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NBITS, + link_usettings.link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NU32); + bitmap_from_u32array(to->link_modes.advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS, + link_usettings.link_modes.advertising, + __ETHTOOL_LINK_MODE_MASK_NU32); + bitmap_from_u32array(to->link_modes.lp_advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS, + link_usettings.link_modes.lp_advertising, + __ETHTOOL_LINK_MODE_MASK_NU32); + + return 0; +} + +/* convert a kernel internal ethtool_link_ksettings to + * ethtool_link_usettings in user space. return 0 on success, errno on + * error. + */ +static int +store_link_ksettings_for_user(void __user *to, + const struct ethtool_link_ksettings *from) +{ + struct ethtool_link_usettings link_usettings; + + memcpy(&link_usettings.base, &from->base, sizeof(link_usettings)); + bitmap_to_u32array(link_usettings.link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NU32, + from->link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_to_u32array(link_usettings.link_modes.advertising, + __ETHTOOL_LINK_MODE_MASK_NU32, + from->link_modes.advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_to_u32array(link_usettings.link_modes.lp_advertising, + __ETHTOOL_LINK_MODE_MASK_NU32, + from->link_modes.lp_advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS); + + if (copy_to_user(to, &link_usettings, sizeof(link_usettings))) + return -EFAULT; + + return 0; +} + +/* Query device for its ethtool_link_settings. + * + * Backward compatibility note: this function must fail when driver + * does not implement ethtool::get_link_ksettings, even if legacy + * ethtool_ops::get_settings is implemented. This tells new versions + * of ethtool that they should use the legacy API %ETHTOOL_GSET for + * this driver, so that they can correctly access the ethtool_cmd + * deprecated fields (transceiver/maxrxpkt/maxtxpkt), until no driver + * implements ethtool_ops::get_settings anymore. + */ +static int ethtool_get_link_ksettings(struct net_device *dev, + void __user *useraddr) +{ + int err = 0; + struct ethtool_link_ksettings link_ksettings; + + ASSERT_RTNL(); + + if (!dev->ethtool_ops->get_link_ksettings) + return -EOPNOTSUPP; + + /* handle bitmap nbits handshake */ + if (copy_from_user(&link_ksettings.base, useraddr, + sizeof(link_ksettings.base))) + return -EFAULT; + + if (__ETHTOOL_LINK_MODE_MASK_NU32 + != link_ksettings.base.link_mode_masks_nwords) { + /* wrong link mode nbits requested */ + memset(&link_ksettings, 0, sizeof(link_ksettings)); + /* keep cmd field reset to 0 */ + /* send back number of words required as negative val */ + compiletime_assert(__ETHTOOL_LINK_MODE_MASK_NU32 <= S8_MAX, + "need too many bits for link modes!"); + link_ksettings.base.link_mode_masks_nwords + = -((s8)__ETHTOOL_LINK_MODE_MASK_NU32); + + /* copy the base fields back to user, not the link + * mode bitmaps + */ + if (copy_to_user(useraddr, &link_ksettings.base, + sizeof(link_ksettings.base))) + return -EFAULT; + + return 0; + } + + /* handshake successful: user/kernel agree on + * link_mode_masks_nwords + */ + + memset(&link_ksettings, 0, sizeof(link_ksettings)); + err = dev->ethtool_ops->get_link_ksettings(dev, &link_ksettings); + if (err < 0) + return err; + + /* make sure we tell the right values to user */ + link_ksettings.base.cmd = ETHTOOL_GLINKSETTINGS; + link_ksettings.base.link_mode_masks_nwords + = __ETHTOOL_LINK_MODE_MASK_NU32; + + return store_link_ksettings_for_user(useraddr, &link_ksettings); +} + +/* Update device ethtool_link_settings. + * + * Backward compatibility note: this function must fail when driver + * does not implement ethtool::set_link_ksettings, even if legacy + * ethtool_ops::set_settings is implemented. This tells new versions + * of ethtool that they should use the legacy API %ETHTOOL_SSET for + * this driver, so that they can correctly update the ethtool_cmd + * deprecated fields (transceiver/maxrxpkt/maxtxpkt), until no driver + * implements ethtool_ops::get_settings anymore. + */ +static int ethtool_set_link_ksettings(struct net_device *dev, + void __user *useraddr) +{ + int err; + struct ethtool_link_ksettings link_ksettings; + + ASSERT_RTNL(); + + if (!dev->ethtool_ops->set_link_ksettings) + return -EOPNOTSUPP; + + /* make sure nbits field has expected value */ + if (copy_from_user(&link_ksettings.base, useraddr, + sizeof(link_ksettings.base))) + return -EFAULT; + + if (__ETHTOOL_LINK_MODE_MASK_NU32 + != link_ksettings.base.link_mode_masks_nwords) + return -EINVAL; + + /* copy the whole structure, now that we know it has expected + * format + */ + err = load_link_ksettings_from_user(&link_ksettings, useraddr); + if (err) + return err; + + /* re-check nwords field, just in case */ + if (__ETHTOOL_LINK_MODE_MASK_NU32 + != link_ksettings.base.link_mode_masks_nwords) + return -EINVAL; + + return dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings); +} + +/* Internal kernel helper to query a device ethtool_cmd settings. + * + * Note about transition to ethtool_link_settings API: We do not need + * (or want) this function to support "dev" instances that implement + * the ethtool_link_settings API as we will update the drivers calling + * this function to call __ethtool_get_link_ksettings instead, before + * the first drivers implement ethtool_ops::get_link_ksettings. + * + * TODO 1: at least make this function static when no driver is using it + * TODO 2: remove when ethtool_ops::get_settings disappears internally + */ int __ethtool_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) { ASSERT_RTNL(); @@ -400,30 +753,112 @@ int __ethtool_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) } EXPORT_SYMBOL(__ethtool_get_settings); +static void +warn_incomplete_ethtool_legacy_settings_conversion(const char *details) +{ + char name[sizeof(current->comm)]; + + pr_info_once("warning: `%s' uses legacy ethtool link settings API, %s\n", + get_task_comm(name, current), details); +} + +/* Query device for its ethtool_cmd settings. + * + * Backward compatibility note: for compatibility with legacy ethtool, + * this has to work with both drivers implementing get_link_ksettings + * API and drivers implementing get_settings API. When drivers + * implement get_link_ksettings and report higher link mode bits, a + * kernel warning is logged once (with name of 1st driver/device) to + * recommend user to upgrade ethtool, but the command is successful + * (only the lower link mode bits reported back to user). + */ static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) { - int err; struct ethtool_cmd cmd; - err = __ethtool_get_settings(dev, &cmd); - if (err < 0) - return err; + ASSERT_RTNL(); + + if (dev->ethtool_ops->get_link_ksettings) { + /* First, use link_ksettings API if it is supported */ + int err; + struct ethtool_link_ksettings link_ksettings; + + memset(&link_ksettings, 0, sizeof(link_ksettings)); + err = dev->ethtool_ops->get_link_ksettings(dev, + &link_ksettings); + if (err < 0) + return err; + if (!convert_link_ksettings_to_legacy_settings(&cmd, + &link_ksettings)) + warn_incomplete_ethtool_legacy_settings_conversion( + "link modes are only partially reported"); + + /* send a sensible cmd tag back to user */ + cmd.cmd = ETHTOOL_GSET; + } else { + int err; + /* TODO: return -EOPNOTSUPP when + * ethtool_ops::get_settings disappears internally + */ + + /* driver doesn't support %ethtool_link_ksettings + * API. revert to legacy %ethtool_cmd API, unless it's + * not supported either. + */ + err = __ethtool_get_settings(dev, &cmd); + if (err < 0) + return err; + } if (copy_to_user(useraddr, &cmd, sizeof(cmd))) return -EFAULT; + return 0; } +/* Update device link settings with given ethtool_cmd. + * + * Backward compatibility note: for compatibility with legacy ethtool, + * this has to work with both drivers implementing set_link_ksettings + * API and drivers implementing set_settings API. When drivers + * implement set_link_ksettings and user's request updates deprecated + * ethtool_cmd fields (transceiver/maxrxpkt/maxtxpkt), a kernel + * warning is logged once (with name of 1st driver/device) to + * recommend user to upgrade ethtool, and the request is rejected. + */ static int ethtool_set_settings(struct net_device *dev, void __user *useraddr) { struct ethtool_cmd cmd; - if (!dev->ethtool_ops->set_settings) - return -EOPNOTSUPP; + ASSERT_RTNL(); if (copy_from_user(&cmd, useraddr, sizeof(cmd))) return -EFAULT; + /* first, try new %ethtool_link_ksettings API. */ + if (dev->ethtool_ops->set_link_ksettings) { + struct ethtool_link_ksettings link_ksettings; + + if (!convert_legacy_settings_to_link_ksettings(&link_ksettings, + &cmd)) + return -EINVAL; + + link_ksettings.base.cmd = ETHTOOL_SLINKSETTINGS; + link_ksettings.base.link_mode_masks_nwords + = __ETHTOOL_LINK_MODE_MASK_NU32; + return dev->ethtool_ops->set_link_ksettings(dev, + &link_ksettings); + } + + /* legacy %ethtool_cmd API */ + + /* TODO: return -EOPNOTSUPP when ethtool_ops::get_settings + * disappears internally + */ + + if (!dev->ethtool_ops->set_settings) + return -EOPNOTSUPP; + return dev->ethtool_ops->set_settings(dev, &cmd); } @@ -2252,6 +2687,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_PERQUEUE: rc = ethtool_set_per_queue(dev, useraddr); break; + case ETHTOOL_GLINKSETTINGS: + rc = ethtool_get_link_ksettings(dev, useraddr); + break; + case ETHTOOL_SLINKSETTINGS: + rc = ethtool_set_link_ksettings(dev, useraddr); + break; default: rc = -EOPNOTSUPP; } -- cgit v1.2.3 From 3237fc63a3297d472a8cec33cb914f20570cfc23 Mon Sep 17 00:00:00 2001 From: David Decotigny Date: Wed, 24 Feb 2016 10:58:11 -0800 Subject: net: ethtool: remove unused __ethtool_get_settings replaced by __ethtool_get_link_ksettings. Signed-off-by: David Decotigny Signed-off-by: David S. Miller --- include/linux/ethtool.h | 4 ---- net/core/ethtool.c | 45 ++++++++++++++------------------------------- 2 files changed, 14 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 8a400a54c92e..e2b7bf27c03e 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -150,10 +150,6 @@ extern int __ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *link_ksettings); -/* DEPRECATED, use __ethtool_get_link_ksettings */ -extern int __ethtool_get_settings(struct net_device *dev, - struct ethtool_cmd *cmd); - /** * struct ethtool_ops - optional netdev operations * @get_settings: DEPRECATED, use %get_link_ksettings/%set_link_ksettings diff --git a/net/core/ethtool.c b/net/core/ethtool.c index edcec56ed228..2966cd0d7c93 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -551,7 +551,12 @@ int __ethtool_get_link_ksettings(struct net_device *dev, * legacy %ethtool_cmd API, unless it's not supported either. * TODO: remove when ethtool_ops::get_settings disappears internally */ - err = __ethtool_get_settings(dev, &cmd); + if (!dev->ethtool_ops->get_settings) + return -EOPNOTSUPP; + + memset(&cmd, 0, sizeof(cmd)); + cmd.cmd = ETHTOOL_GSET; + err = dev->ethtool_ops->get_settings(dev, &cmd); if (err < 0) return err; @@ -729,30 +734,6 @@ static int ethtool_set_link_ksettings(struct net_device *dev, return dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings); } -/* Internal kernel helper to query a device ethtool_cmd settings. - * - * Note about transition to ethtool_link_settings API: We do not need - * (or want) this function to support "dev" instances that implement - * the ethtool_link_settings API as we will update the drivers calling - * this function to call __ethtool_get_link_ksettings instead, before - * the first drivers implement ethtool_ops::get_link_ksettings. - * - * TODO 1: at least make this function static when no driver is using it - * TODO 2: remove when ethtool_ops::get_settings disappears internally - */ -int __ethtool_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) -{ - ASSERT_RTNL(); - - if (!dev->ethtool_ops->get_settings) - return -EOPNOTSUPP; - - memset(cmd, 0, sizeof(struct ethtool_cmd)); - cmd->cmd = ETHTOOL_GSET; - return dev->ethtool_ops->get_settings(dev, cmd); -} -EXPORT_SYMBOL(__ethtool_get_settings); - static void warn_incomplete_ethtool_legacy_settings_conversion(const char *details) { @@ -796,16 +777,18 @@ static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) /* send a sensible cmd tag back to user */ cmd.cmd = ETHTOOL_GSET; } else { - int err; - /* TODO: return -EOPNOTSUPP when - * ethtool_ops::get_settings disappears internally - */ - /* driver doesn't support %ethtool_link_ksettings * API. revert to legacy %ethtool_cmd API, unless it's * not supported either. */ - err = __ethtool_get_settings(dev, &cmd); + int err; + + if (!dev->ethtool_ops->get_settings) + return -EOPNOTSUPP; + + memset(&cmd, 0, sizeof(cmd)); + cmd.cmd = ETHTOOL_GSET; + err = dev->ethtool_ops->get_settings(dev, &cmd); if (err < 0) return err; } -- cgit v1.2.3 From 871b642adebe300be2e50aa5f65a418510f636ec Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 26 Feb 2016 10:45:37 +0100 Subject: netdev: introduce ndo_set_rx_headroom This method allows the controlling device (i.e. the bridge) to specify additional headroom to be allocated for skb head on frame reception. Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/netdevice.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e52077ffe5ed..efe7cec111fa 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1093,6 +1093,12 @@ struct tc_to_netdev { * This function is used to get egress tunnel information for given skb. * This is useful for retrieving outer tunnel header parameters while * sampling packet. + * void (*ndo_set_rx_headroom)(struct net_device *dev, int needed_headroom); + * This function is used to specify the headroom that the skb must + * consider when allocation skb during packet reception. Setting + * appropriate rx headroom value allows avoiding skb head copy on + * forward. Setting a negative value reset the rx headroom to the + * default value. * */ struct net_device_ops { @@ -1278,6 +1284,8 @@ struct net_device_ops { bool proto_down); int (*ndo_fill_metadata_dst)(struct net_device *dev, struct sk_buff *skb); + void (*ndo_set_rx_headroom)(struct net_device *dev, + int needed_headroom); }; /** @@ -1315,6 +1323,8 @@ struct net_device_ops { * @IFF_L3MDEV_SLAVE: device is enslaved to an L3 master device * @IFF_TEAM: device is a team device * @IFF_RXFH_CONFIGURED: device has had Rx Flow indirection table configured + * @IFF_PHONY_HEADROOM: the headroom value is controlled by an external + * entity (i.e. the master device for bridged veth) */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1343,6 +1353,7 @@ enum netdev_priv_flags { IFF_L3MDEV_SLAVE = 1<<23, IFF_TEAM = 1<<24, IFF_RXFH_CONFIGURED = 1<<25, + IFF_PHONY_HEADROOM = 1<<26, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1937,6 +1948,26 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, void *accel_priv); +/* returns the headroom that the master device needs to take in account + * when forwarding to this dev + */ +static inline unsigned netdev_get_fwd_headroom(struct net_device *dev) +{ + return dev->priv_flags & IFF_PHONY_HEADROOM ? 0 : dev->needed_headroom; +} + +static inline void netdev_set_rx_headroom(struct net_device *dev, int new_hr) +{ + if (dev->netdev_ops->ndo_set_rx_headroom) + dev->netdev_ops->ndo_set_rx_headroom(dev, new_hr); +} + +/* set the device rx headroom to the dev's default */ +static inline void netdev_reset_rx_headroom(struct net_device *dev) +{ + netdev_set_rx_headroom(dev, -1); +} + /* * Net namespace inlines */ -- cgit v1.2.3 From 09d4d087cd4869859fcc5dfc692f0830550a1b48 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 26 Feb 2016 17:32:24 +0100 Subject: mlx4: Implement devlink interface Implement newly introduced devlink interface. Add devlink port instances for every port and set the port types accordingly. Signed-off-by: Jiri Pirko v2->v3: -add dev param to devlink_register (api change) Signed-off-by: David S. Miller --- drivers/infiniband/hw/mlx4/main.c | 7 ++++ drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 8 ++++- drivers/net/ethernet/mellanox/mlx4/intf.c | 9 ++++++ drivers/net/ethernet/mellanox/mlx4/main.c | 44 +++++++++++++++++++------- drivers/net/ethernet/mellanox/mlx4/mlx4.h | 2 ++ include/linux/mlx4/driver.h | 3 ++ 6 files changed, 60 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 1c7ab6cabbb8..a15a7b37d386 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -41,6 +41,7 @@ #include #include #include +#include #include #include @@ -2519,6 +2520,9 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) } ibdev->ib_active = true; + mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB) + devlink_port_type_ib_set(mlx4_get_devlink_port(dev, i), + &ibdev->ib_dev); if (mlx4_is_mfunc(ibdev->dev)) init_pkeys(ibdev); @@ -2643,7 +2647,10 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr) { struct mlx4_ib_dev *ibdev = ibdev_ptr; int p; + int i; + mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB) + devlink_port_type_clear(mlx4_get_devlink_port(dev, i)); ibdev->ib_active = false; flush_workqueue(wq); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 96d95cb36c52..e26b110e27da 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -40,6 +40,7 @@ #include #include #include +#include #include #include @@ -2033,8 +2034,11 @@ void mlx4_en_destroy_netdev(struct net_device *dev) en_dbg(DRV, priv, "Destroying netdev on port:%d\n", priv->port); /* Unregister device - this will close the port if it was up */ - if (priv->registered) + if (priv->registered) { + devlink_port_type_clear(mlx4_get_devlink_port(mdev->dev, + priv->port)); unregister_netdev(dev); + } if (priv->allocated) mlx4_free_hwq_res(mdev->dev, &priv->res, MLX4_EN_PAGE_SIZE); @@ -3051,6 +3055,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, } priv->registered = 1; + devlink_port_type_eth_set(mlx4_get_devlink_port(mdev->dev, priv->port), + dev); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c index 0472941af820..dec77d6f0ac9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/intf.c +++ b/drivers/net/ethernet/mellanox/mlx4/intf.c @@ -34,6 +34,7 @@ #include #include #include +#include #include "mlx4.h" @@ -249,3 +250,11 @@ void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int return result; } EXPORT_SYMBOL_GPL(mlx4_get_protocol_dev); + +struct devlink_port *mlx4_get_devlink_port(struct mlx4_dev *dev, int port) +{ + struct mlx4_port_info *info = &mlx4_priv(dev)->port[port]; + + return &info->devlink_port; +} +EXPORT_SYMBOL_GPL(mlx4_get_devlink_port); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 2cc3c626c3fe..4f5cfe4989ce 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include @@ -2881,8 +2882,13 @@ no_msi: static int mlx4_init_port_info(struct mlx4_dev *dev, int port) { + struct devlink *devlink = priv_to_devlink(mlx4_priv(dev)); struct mlx4_port_info *info = &mlx4_priv(dev)->port[port]; - int err = 0; + int err; + + err = devlink_port_register(devlink, &info->devlink_port, port); + if (err) + return err; info->dev = dev; info->port = port; @@ -2907,6 +2913,7 @@ static int mlx4_init_port_info(struct mlx4_dev *dev, int port) err = device_create_file(&dev->persist->pdev->dev, &info->port_attr); if (err) { mlx4_err(dev, "Failed to create file for port %d\n", port); + devlink_port_unregister(&info->devlink_port); info->port = -1; } @@ -3680,21 +3687,23 @@ err_disable_pdev: static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) { + struct devlink *devlink; struct mlx4_priv *priv; struct mlx4_dev *dev; int ret; printk_once(KERN_INFO "%s", mlx4_version); - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (!priv) + devlink = devlink_alloc(NULL, sizeof(*priv)); + if (!devlink) return -ENOMEM; + priv = devlink_priv(devlink); dev = &priv->dev; dev->persist = kzalloc(sizeof(*dev->persist), GFP_KERNEL); if (!dev->persist) { - kfree(priv); - return -ENOMEM; + ret = -ENOMEM; + goto err_devlink_free; } dev->persist->pdev = pdev; dev->persist->dev = dev; @@ -3703,14 +3712,23 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) mutex_init(&dev->persist->device_state_mutex); mutex_init(&dev->persist->interface_state_mutex); + ret = devlink_register(devlink, &pdev->dev); + if (ret) + goto err_persist_free; + ret = __mlx4_init_one(pdev, id->driver_data, priv); - if (ret) { - kfree(dev->persist); - kfree(priv); - } else { - pci_save_state(pdev); - } + if (ret) + goto err_devlink_unregister; + pci_save_state(pdev); + return 0; + +err_devlink_unregister: + devlink_unregister(devlink); +err_persist_free: + kfree(dev->persist); +err_devlink_free: + devlink_free(devlink); return ret; } @@ -3811,6 +3829,7 @@ static void mlx4_remove_one(struct pci_dev *pdev) struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev); struct mlx4_dev *dev = persist->dev; struct mlx4_priv *priv = mlx4_priv(dev); + struct devlink *devlink = priv_to_devlink(priv); int active_vfs = 0; mutex_lock(&persist->interface_state_mutex); @@ -3841,8 +3860,9 @@ static void mlx4_remove_one(struct pci_dev *pdev) pci_release_regions(pdev); pci_disable_device(pdev); + devlink_unregister(devlink); kfree(dev->persist); - kfree(priv); + devlink_free(devlink); pci_set_drvdata(pdev, NULL); } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 7baef52db6b7..ef9683101ead 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -45,6 +45,7 @@ #include #include #include +#include #include #include @@ -828,6 +829,7 @@ struct mlx4_port_info { struct mlx4_roce_gid_table gid_table; int base_qpn; struct cpu_rmap *rmap; + struct devlink_port devlink_port; }; struct mlx4_sense { diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index 2e8af001c5da..bd0e7075ea6d 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -33,6 +33,7 @@ #ifndef MLX4_DRIVER_H #define MLX4_DRIVER_H +#include #include struct mlx4_dev; @@ -89,6 +90,8 @@ int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p); void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int port); +struct devlink_port *mlx4_get_devlink_port(struct mlx4_dev *dev, int port); + static inline u64 mlx4_mac_to_u64(u8 *addr) { u64 mac = 0; -- cgit v1.2.3 From 6b6c07bdcdc97ccac2596063bfc32a5faddfe884 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Wed, 2 Mar 2016 00:13:39 +0200 Subject: net/mlx5: Make command timeout way shorter The command timeout is terribly long, whole two hours. Make it 60s so if things do go wrong, the user gets feedback in relatively short time, so they can take corrective actions and/or investigate using tools and such. Fixes: e126ba97dba9 ('mlx5: Add driver for Mellanox Connect-IB adapters') Signed-off-by: Or Gerlitz Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index a815da92d4eb..3388a43b78f6 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -54,7 +54,7 @@ enum { /* one minute for the sake of bringup. Generally, commands must always * complete and we may need to increase this timeout value */ - MLX5_CMD_TIMEOUT_MSEC = 7200 * 1000, + MLX5_CMD_TIMEOUT_MSEC = 60 * 1000, MLX5_CMD_WQ_MAX_NAME = 32, }; -- cgit v1.2.3 From 0ba422410bbf7081c3c7d7b2dcc10e9eb5cb46f7 Mon Sep 17 00:00:00 2001 From: Moshe Lazer Date: Wed, 2 Mar 2016 00:13:40 +0200 Subject: net/mlx5: Fix global UAR mapping Avoid double mapping of io mapped memory, Device page may be mapped to non-cached(NC) or to write-combining(WC). The code before this fix tries to map it both to WC and NC contrary to what stated in Intel's software developer manual. Here we remove the global WC mapping of all UARS "dev->priv.bf_mapping", since UAR mapping should be decided per UAR (e.g we want different mappings for EQs, CQs vs QPs). Caller will now have to choose whether to map via write-combining API or not. mlx5e SQs will choose write-combining in order to perform BlueFlame writes. Fixes: 88a85f99e51f ('TX latency optimization to save DMA reads') Signed-off-by: Moshe Lazer Reviewed-by: Achiad Shochat Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 16 +++++-------- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 12 ++++++---- drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/main.c | 28 +--------------------- drivers/net/ethernet/mellanox/mlx5/core/uar.c | 29 ++++++++++++++--------- include/linux/mlx5/driver.h | 5 ++-- 6 files changed, 36 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index b289660568cf..9c0e80e64b43 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -388,6 +388,7 @@ struct mlx5e_sq_dma { enum { MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, + MLX5E_SQ_STATE_BF_ENABLE, }; struct mlx5e_sq { @@ -416,7 +417,6 @@ struct mlx5e_sq { struct mlx5_wq_cyc wq; u32 dma_fifo_mask; void __iomem *uar_map; - void __iomem *uar_bf_map; struct netdev_queue *txq; u32 sqn; u16 bf_buf_size; @@ -664,16 +664,12 @@ static inline void mlx5e_tx_notify_hw(struct mlx5e_sq *sq, * doorbell */ wmb(); - - if (bf_sz) { - __iowrite64_copy(sq->uar_bf_map + ofst, &wqe->ctrl, bf_sz); - - /* flush the write-combining mapped buffer */ - wmb(); - - } else { + if (bf_sz) + __iowrite64_copy(sq->uar_map + ofst, &wqe->ctrl, bf_sz); + else mlx5_write64((__be32 *)&wqe->ctrl, sq->uar_map + ofst, NULL); - } + /* flush the write-combining mapped buffer */ + wmb(); sq->bf_offset ^= sq->bf_buf_size; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index b20a35bd1d4f..5063c0e0f8ac 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -548,7 +548,7 @@ static int mlx5e_create_sq(struct mlx5e_channel *c, int txq_ix; int err; - err = mlx5_alloc_map_uar(mdev, &sq->uar); + err = mlx5_alloc_map_uar(mdev, &sq->uar, true); if (err) return err; @@ -560,8 +560,12 @@ static int mlx5e_create_sq(struct mlx5e_channel *c, goto err_unmap_free_uar; sq->wq.db = &sq->wq.db[MLX5_SND_DBR]; - sq->uar_map = sq->uar.map; - sq->uar_bf_map = sq->uar.bf_map; + if (sq->uar.bf_map) { + set_bit(MLX5E_SQ_STATE_BF_ENABLE, &sq->state); + sq->uar_map = sq->uar.bf_map; + } else { + sq->uar_map = sq->uar.map; + } sq->bf_buf_size = (1 << MLX5_CAP_GEN(mdev, log_bf_reg_size)) / 2; sq->max_inline = param->max_inline; @@ -2418,7 +2422,7 @@ static void *mlx5e_create_netdev(struct mlx5_core_dev *mdev) priv = netdev_priv(netdev); - err = mlx5_alloc_map_uar(mdev, &priv->cq_uar); + err = mlx5_alloc_map_uar(mdev, &priv->cq_uar, false); if (err) { mlx5_core_err(mdev, "alloc_map uar failed, %d\n", err); goto err_free_netdev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index a05c070cbc2f..c34f4f3e9537 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -303,7 +303,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) if (!skb->xmit_more || netif_xmit_stopped(sq->txq)) { int bf_sz = 0; - if (bf && sq->uar_bf_map) + if (bf && test_bit(MLX5E_SQ_STATE_BF_ENABLE, &sq->state)) bf_sz = wi->num_wqebbs << 3; cseg->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 1545a944c309..8b7133de498e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -767,22 +767,6 @@ static int mlx5_core_set_issi(struct mlx5_core_dev *dev) return -ENOTSUPP; } -static int map_bf_area(struct mlx5_core_dev *dev) -{ - resource_size_t bf_start = pci_resource_start(dev->pdev, 0); - resource_size_t bf_len = pci_resource_len(dev->pdev, 0); - - dev->priv.bf_mapping = io_mapping_create_wc(bf_start, bf_len); - - return dev->priv.bf_mapping ? 0 : -ENOMEM; -} - -static void unmap_bf_area(struct mlx5_core_dev *dev) -{ - if (dev->priv.bf_mapping) - io_mapping_free(dev->priv.bf_mapping); -} - static void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv) { struct mlx5_device_context *dev_ctx; @@ -1103,14 +1087,9 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) goto err_stop_eqs; } - if (map_bf_area(dev)) - dev_err(&pdev->dev, "Failed to map blue flame area\n"); - err = mlx5_irq_set_affinity_hints(dev); - if (err) { + if (err) dev_err(&pdev->dev, "Failed to alloc affinity hint cpumask\n"); - goto err_unmap_bf_area; - } MLX5_INIT_DOORBELL_LOCK(&priv->cq_uar_lock); @@ -1169,10 +1148,6 @@ err_fs: mlx5_cleanup_qp_table(dev); mlx5_cleanup_cq_table(dev); mlx5_irq_clear_affinity_hints(dev); - -err_unmap_bf_area: - unmap_bf_area(dev); - free_comp_eqs(dev); err_stop_eqs: @@ -1242,7 +1217,6 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) mlx5_cleanup_qp_table(dev); mlx5_cleanup_cq_table(dev); mlx5_irq_clear_affinity_hints(dev); - unmap_bf_area(dev); free_comp_eqs(dev); mlx5_stop_eqs(dev); mlx5_free_uuars(dev, &priv->uuari); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c index eb05c845ece9..8ba080e441a1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c @@ -226,7 +226,8 @@ int mlx5_free_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari) return 0; } -int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar) +int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar, + bool map_wc) { phys_addr_t pfn; phys_addr_t uar_bar_start; @@ -240,20 +241,26 @@ int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar) uar_bar_start = pci_resource_start(mdev->pdev, 0); pfn = (uar_bar_start >> PAGE_SHIFT) + uar->index; - uar->map = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE); - if (!uar->map) { - mlx5_core_warn(mdev, "ioremap() failed, %d\n", err); - err = -ENOMEM; - goto err_free_uar; - } - if (mdev->priv.bf_mapping) - uar->bf_map = io_mapping_map_wc(mdev->priv.bf_mapping, - uar->index << PAGE_SHIFT); + if (map_wc) { + uar->bf_map = ioremap_wc(pfn << PAGE_SHIFT, PAGE_SIZE); + if (!uar->bf_map) { + mlx5_core_warn(mdev, "ioremap_wc() failed\n"); + uar->map = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE); + if (!uar->map) + goto err_free_uar; + } + } else { + uar->map = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE); + if (!uar->map) + goto err_free_uar; + } return 0; err_free_uar: + mlx5_core_warn(mdev, "ioremap() failed\n"); + err = -ENOMEM; mlx5_cmd_free_uar(mdev, uar->index); return err; @@ -262,8 +269,8 @@ EXPORT_SYMBOL(mlx5_alloc_map_uar); void mlx5_unmap_free_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar) { - io_mapping_unmap(uar->bf_map); iounmap(uar->map); + iounmap(uar->bf_map); mlx5_cmd_free_uar(mdev, uar->index); } EXPORT_SYMBOL(mlx5_unmap_free_uar); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 3388a43b78f6..bb1a880a5bc5 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -460,8 +460,6 @@ struct mlx5_priv { struct mlx5_uuar_info uuari; MLX5_DECLARE_DOORBELL_LOCK(cq_uar_lock); - struct io_mapping *bf_mapping; - /* pages stuff */ struct workqueue_struct *pg_wq; struct rb_root page_root; @@ -719,7 +717,8 @@ int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn); int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn); int mlx5_alloc_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari); int mlx5_free_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari); -int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar); +int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar, + bool map_wc); void mlx5_unmap_free_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar); void mlx5_health_cleanup(struct mlx5_core_dev *dev); int mlx5_health_init(struct mlx5_core_dev *dev); -- cgit v1.2.3 From 64d4e3431e686dc37ce388ba531c4c4e866fb141 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Sat, 27 Feb 2016 20:19:54 -0800 Subject: net: remove skb_sender_cpu_clear() After commit 52bd2d62ce67 ("net: better skb->sender_cpu and skb->napi_id cohabitation") skb_sender_cpu_clear() becomes empty and can be removed. Cc: Eric Dumazet Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ---- net/bridge/br_forward.c | 1 - net/core/filter.c | 2 -- net/core/skbuff.c | 1 - net/ipv4/ip_forward.c | 1 - net/ipv6/ip6_output.c | 1 - net/netfilter/ipvs/ip_vs_xmit.c | 6 ------ net/netfilter/nf_dup_netdev.c | 1 - net/sched/act_mirred.c | 1 - 9 files changed, 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index eab4f8fbed58..797cefb888fb 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1161,10 +1161,6 @@ static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) to->l4_hash = from->l4_hash; }; -static inline void skb_sender_cpu_clear(struct sk_buff *skb) -{ -} - #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index fcdb86dd5a23..f47759f05b6d 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -44,7 +44,6 @@ int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb skb_push(skb, ETH_HLEN); br_drop_fake_rtable(skb); - skb_sender_cpu_clear(skb); if (skb->ip_summed == CHECKSUM_PARTIAL && (skb->protocol == htons(ETH_P_8021Q) || diff --git a/net/core/filter.c b/net/core/filter.c index a3aba15a8025..5e2a3b5e5196 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1597,7 +1597,6 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5) } skb2->dev = dev; - skb_sender_cpu_clear(skb2); return dev_queue_xmit(skb2); } @@ -1650,7 +1649,6 @@ int skb_do_redirect(struct sk_buff *skb) } skb->dev = dev; - skb_sender_cpu_clear(skb); return dev_queue_xmit(skb); } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 488566b09c6d..7af7ec635d90 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4302,7 +4302,6 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) skb->skb_iif = 0; skb->ignore_df = 0; skb_dst_drop(skb); - skb_sender_cpu_clear(skb); secpath_reset(skb); nf_reset(skb); nf_reset_trace(skb); diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index da0d7ce85844..af18f1e4889e 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -71,7 +71,6 @@ static int ip_forward_finish(struct net *net, struct sock *sk, struct sk_buff *s if (unlikely(opt->optlen)) ip_forward_options(skb); - skb_sender_cpu_clear(skb); return dst_output(net, sk, skb); } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a163102f1803..9428345d3a07 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -332,7 +332,6 @@ static int ip6_forward_proxy_check(struct sk_buff *skb) static inline int ip6_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { - skb_sender_cpu_clear(skb); return dst_output(net, sk, skb); } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index a3f5cd9b3c4c..dc196a0f501d 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -531,8 +531,6 @@ static inline int ip_vs_tunnel_xmit_prepare(struct sk_buff *skb, if (ret == NF_ACCEPT) { nf_reset(skb); skb_forward_csum(skb); - if (!skb->sk) - skb_sender_cpu_clear(skb); } return ret; } @@ -573,8 +571,6 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb, if (!local) { skb_forward_csum(skb); - if (!skb->sk) - skb_sender_cpu_clear(skb); NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb, NULL, skb_dst(skb)->dev, dst_output); } else @@ -595,8 +591,6 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb, if (!local) { ip_vs_drop_early_demux_sk(skb); skb_forward_csum(skb); - if (!skb->sk) - skb_sender_cpu_clear(skb); NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb, NULL, skb_dst(skb)->dev, dst_output); } else diff --git a/net/netfilter/nf_dup_netdev.c b/net/netfilter/nf_dup_netdev.c index 8414ee1a0319..7ec69723940f 100644 --- a/net/netfilter/nf_dup_netdev.c +++ b/net/netfilter/nf_dup_netdev.c @@ -31,7 +31,6 @@ void nf_dup_netdev_egress(const struct nft_pktinfo *pkt, int oif) skb_push(skb, skb->mac_len); skb->dev = dev; - skb_sender_cpu_clear(skb); dev_queue_xmit(skb); } EXPORT_SYMBOL_GPL(nf_dup_netdev_egress); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 6b284d991e0b..e8a760cf7775 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -182,7 +182,6 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, skb2->skb_iif = skb->dev->ifindex; skb2->dev = dev; - skb_sender_cpu_clear(skb2); err = dev_queue_xmit(skb2); if (err) { -- cgit v1.2.3 From 4ac801b77e6f06e6b12c069fd29216a4102065fb Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Sun, 28 Feb 2016 12:26:52 +0200 Subject: qed: Semantic refactoring of interrupt code Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_dev.c | 6 +- drivers/net/ethernet/qlogic/qed/qed_int.c | 155 ++++++++++++++++------------- drivers/net/ethernet/qlogic/qed/qed_int.h | 6 +- drivers/net/ethernet/qlogic/qed/qed_main.c | 15 +-- include/linux/qed/qed_if.h | 6 ++ 5 files changed, 111 insertions(+), 77 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index acfe7be49a58..d9a5175ebd04 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -1011,13 +1011,17 @@ static void qed_hw_get_resc(struct qed_hwfn *p_hwfn) { u32 *resc_start = p_hwfn->hw_info.resc_start; u32 *resc_num = p_hwfn->hw_info.resc_num; + struct qed_sb_cnt_info sb_cnt_info; int num_funcs, i; num_funcs = MAX_NUM_PFS_BB; + memset(&sb_cnt_info, 0, sizeof(sb_cnt_info)); + qed_int_get_num_sbs(p_hwfn, &sb_cnt_info); + resc_num[QED_SB] = min_t(u32, (MAX_SB_PER_PATH_BB / num_funcs), - qed_int_get_num_sbs(p_hwfn, NULL)); + sb_cnt_info.sb_cnt); resc_num[QED_L2_QUEUE] = MAX_NUM_L2_QUEUES_BB / num_funcs; resc_num[QED_VPORT] = MAX_NUM_VPORTS_BB / num_funcs; resc_num[QED_RSS_ENG] = ETH_RSS_ENGINE_NUM_BB / num_funcs; diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c index fa73daa94655..7fd1be61de5c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.c +++ b/drivers/net/ethernet/qlogic/qed/qed_int.c @@ -343,17 +343,17 @@ void qed_int_sp_dpc(unsigned long hwfn_cookie) static void qed_int_sb_attn_free(struct qed_hwfn *p_hwfn) { - struct qed_dev *cdev = p_hwfn->cdev; - struct qed_sb_attn_info *p_sb = p_hwfn->p_sb_attn; - - if (p_sb) { - if (p_sb->sb_attn) - dma_free_coherent(&cdev->pdev->dev, - SB_ATTN_ALIGNED_SIZE(p_hwfn), - p_sb->sb_attn, - p_sb->sb_phys); - kfree(p_sb); - } + struct qed_sb_attn_info *p_sb = p_hwfn->p_sb_attn; + + if (!p_sb) + return; + + if (p_sb->sb_attn) + dma_free_coherent(&p_hwfn->cdev->pdev->dev, + SB_ATTN_ALIGNED_SIZE(p_hwfn), + p_sb->sb_attn, + p_sb->sb_phys); + kfree(p_sb); } static void qed_int_sb_attn_setup(struct qed_hwfn *p_hwfn, @@ -433,6 +433,7 @@ void qed_init_cau_sb_entry(struct qed_hwfn *p_hwfn, u16 vf_number, u8 vf_valid) { + struct qed_dev *cdev = p_hwfn->cdev; u32 cau_state; memset(p_sb_entry, 0, sizeof(*p_sb_entry)); @@ -451,14 +452,12 @@ void qed_init_cau_sb_entry(struct qed_hwfn *p_hwfn, cau_state = CAU_HC_DISABLE_STATE; - if (p_hwfn->cdev->int_coalescing_mode == QED_COAL_MODE_ENABLE) { + if (cdev->int_coalescing_mode == QED_COAL_MODE_ENABLE) { cau_state = CAU_HC_ENABLE_STATE; - if (!p_hwfn->cdev->rx_coalesce_usecs) - p_hwfn->cdev->rx_coalesce_usecs = - QED_CAU_DEF_RX_USECS; - if (!p_hwfn->cdev->tx_coalesce_usecs) - p_hwfn->cdev->tx_coalesce_usecs = - QED_CAU_DEF_TX_USECS; + if (!cdev->rx_coalesce_usecs) + cdev->rx_coalesce_usecs = QED_CAU_DEF_RX_USECS; + if (!cdev->tx_coalesce_usecs) + cdev->tx_coalesce_usecs = QED_CAU_DEF_TX_USECS; } SET_FIELD(p_sb_entry->data, CAU_SB_ENTRY_STATE0, cau_state); @@ -638,8 +637,10 @@ int qed_int_sb_release(struct qed_hwfn *p_hwfn, sb_info->sb_ack = 0; memset(sb_info->sb_virt, 0, sizeof(*sb_info->sb_virt)); - p_hwfn->sbs_info[sb_id] = NULL; - p_hwfn->num_sbs--; + if (p_hwfn->sbs_info[sb_id] != NULL) { + p_hwfn->sbs_info[sb_id] = NULL; + p_hwfn->num_sbs--; + } return 0; } @@ -648,14 +649,15 @@ static void qed_int_sp_sb_free(struct qed_hwfn *p_hwfn) { struct qed_sb_sp_info *p_sb = p_hwfn->p_sp_sb; - if (p_sb) { - if (p_sb->sb_info.sb_virt) - dma_free_coherent(&p_hwfn->cdev->pdev->dev, - SB_ALIGNED_SIZE(p_hwfn), - p_sb->sb_info.sb_virt, - p_sb->sb_info.sb_phys); - kfree(p_sb); - } + if (!p_sb) + return; + + if (p_sb->sb_info.sb_virt) + dma_free_coherent(&p_hwfn->cdev->pdev->dev, + SB_ALIGNED_SIZE(p_hwfn), + p_sb->sb_info.sb_virt, + p_sb->sb_info.sb_phys); + kfree(p_sb); } static int qed_int_sp_sb_alloc(struct qed_hwfn *p_hwfn, @@ -718,36 +720,36 @@ int qed_int_register_cb(struct qed_hwfn *p_hwfn, __le16 **p_fw_cons) { struct qed_sb_sp_info *p_sp_sb = p_hwfn->p_sp_sb; - int qed_status = -ENOMEM; + int rc = -ENOMEM; u8 pi; /* Look for a free index */ for (pi = 0; pi < ARRAY_SIZE(p_sp_sb->pi_info_arr); pi++) { - if (!p_sp_sb->pi_info_arr[pi].comp_cb) { - p_sp_sb->pi_info_arr[pi].comp_cb = comp_cb; - p_sp_sb->pi_info_arr[pi].cookie = cookie; - *sb_idx = pi; - *p_fw_cons = &p_sp_sb->sb_info.sb_virt->pi_array[pi]; - qed_status = 0; - break; - } + if (p_sp_sb->pi_info_arr[pi].comp_cb) + continue; + + p_sp_sb->pi_info_arr[pi].comp_cb = comp_cb; + p_sp_sb->pi_info_arr[pi].cookie = cookie; + *sb_idx = pi; + *p_fw_cons = &p_sp_sb->sb_info.sb_virt->pi_array[pi]; + rc = 0; + break; } - return qed_status; + return rc; } int qed_int_unregister_cb(struct qed_hwfn *p_hwfn, u8 pi) { struct qed_sb_sp_info *p_sp_sb = p_hwfn->p_sp_sb; - int qed_status = -ENOMEM; - if (p_sp_sb->pi_info_arr[pi].comp_cb) { - p_sp_sb->pi_info_arr[pi].comp_cb = NULL; - p_sp_sb->pi_info_arr[pi].cookie = NULL; - qed_status = 0; - } + if (p_sp_sb->pi_info_arr[pi].comp_cb == NULL) + return -ENOMEM; - return qed_status; + p_sp_sb->pi_info_arr[pi].comp_cb = NULL; + p_sp_sb->pi_info_arr[pi].cookie = NULL; + + return 0; } u16 qed_int_get_sp_sb_id(struct qed_hwfn *p_hwfn) @@ -937,6 +939,39 @@ void qed_int_igu_init_pure_rt(struct qed_hwfn *p_hwfn, } } +static u32 qed_int_igu_read_cam_block(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u16 sb_id) +{ + u32 val = qed_rd(p_hwfn, p_ptt, + IGU_REG_MAPPING_MEMORY + + sizeof(u32) * sb_id); + struct qed_igu_block *p_block; + + p_block = &p_hwfn->hw_info.p_igu_info->igu_map.igu_blocks[sb_id]; + + /* stop scanning when hit first invalid PF entry */ + if (!GET_FIELD(val, IGU_MAPPING_LINE_VALID) && + GET_FIELD(val, IGU_MAPPING_LINE_PF_VALID)) + goto out; + + /* Fill the block information */ + p_block->status = QED_IGU_STATUS_VALID; + p_block->function_id = GET_FIELD(val, + IGU_MAPPING_LINE_FUNCTION_NUMBER); + p_block->is_pf = GET_FIELD(val, IGU_MAPPING_LINE_PF_VALID); + p_block->vector_number = GET_FIELD(val, + IGU_MAPPING_LINE_VECTOR_NUMBER); + + DP_VERBOSE(p_hwfn, NETIF_MSG_INTR, + "IGU_BLOCK: [SB 0x%04x, Value in CAM 0x%08x] func_id = %d is_pf = %d vector_num = 0x%x\n", + sb_id, val, p_block->function_id, + p_block->is_pf, p_block->vector_number); + +out: + return val; +} + int qed_int_igu_read_cam(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { @@ -963,26 +998,13 @@ int qed_int_igu_read_cam(struct qed_hwfn *p_hwfn, sb_id++) { blk = &p_igu_info->igu_map.igu_blocks[sb_id]; - val = qed_rd(p_hwfn, p_ptt, - IGU_REG_MAPPING_MEMORY + sizeof(u32) * sb_id); + val = qed_int_igu_read_cam_block(p_hwfn, p_ptt, sb_id); /* stop scanning when hit first invalid PF entry */ if (!GET_FIELD(val, IGU_MAPPING_LINE_VALID) && GET_FIELD(val, IGU_MAPPING_LINE_PF_VALID)) break; - blk->status = QED_IGU_STATUS_VALID; - blk->function_id = GET_FIELD(val, - IGU_MAPPING_LINE_FUNCTION_NUMBER); - blk->is_pf = GET_FIELD(val, IGU_MAPPING_LINE_PF_VALID); - blk->vector_number = GET_FIELD(val, - IGU_MAPPING_LINE_VECTOR_NUMBER); - - DP_VERBOSE(p_hwfn, NETIF_MSG_INTR, - "IGU_BLOCK[sb_id]:%x:func_id = %d is_pf = %d vector_num = 0x%x\n", - val, blk->function_id, blk->is_pf, - blk->vector_number); - if (blk->is_pf) { if (blk->function_id == p_hwfn->rel_pf_id) { blk->status |= QED_IGU_STATUS_PF; @@ -1121,18 +1143,17 @@ void qed_int_setup(struct qed_hwfn *p_hwfn, qed_int_sp_dpc_setup(p_hwfn); } -int qed_int_get_num_sbs(struct qed_hwfn *p_hwfn, - int *p_iov_blks) +void qed_int_get_num_sbs(struct qed_hwfn *p_hwfn, + struct qed_sb_cnt_info *p_sb_cnt_info) { struct qed_igu_info *info = p_hwfn->hw_info.p_igu_info; - if (!info) - return 0; - - if (p_iov_blks) - *p_iov_blks = info->free_blks; + if (!info || !p_sb_cnt_info) + return; - return info->igu_sb_cnt; + p_sb_cnt_info->sb_cnt = info->igu_sb_cnt; + p_sb_cnt_info->sb_iov_cnt = info->igu_sb_cnt_iov; + p_sb_cnt_info->sb_free_blk = info->free_blks; } void qed_int_disable_post_isr_release(struct qed_dev *cdev) diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.h b/drivers/net/ethernet/qlogic/qed/qed_int.h index 51e0b09a7f47..c57f2e680770 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.h +++ b/drivers/net/ethernet/qlogic/qed/qed_int.h @@ -161,12 +161,12 @@ void qed_int_sp_dpc(unsigned long hwfn_cookie); * blocks configured for this funciton in the igu. * * @param p_hwfn - * @param p_iov_blks - configured free blks for vfs + * @param p_sb_cnt_info * * @return int - number of status blocks configured */ -int qed_int_get_num_sbs(struct qed_hwfn *p_hwfn, - int *p_iov_blks); +void qed_int_get_num_sbs(struct qed_hwfn *p_hwfn, + struct qed_sb_cnt_info *p_sb_cnt_info); /** * @brief qed_int_disable_post_isr_release - performs the cleanup post ISR diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 25d6e91335ea..caa689e6575c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -634,15 +634,18 @@ static int qed_get_int_fp(struct qed_dev *cdev, struct qed_int_info *info) static int qed_slowpath_setup_int(struct qed_dev *cdev, enum qed_int_mode int_mode) { - int rc, i; - u8 num_vectors = 0; - + struct qed_sb_cnt_info sb_cnt_info; + int rc; + int i; memset(&cdev->int_params, 0, sizeof(struct qed_int_params)); cdev->int_params.in.int_mode = int_mode; - for_each_hwfn(cdev, i) - num_vectors += qed_int_get_num_sbs(&cdev->hwfns[i], NULL) + 1; - cdev->int_params.in.num_vectors = num_vectors; + for_each_hwfn(cdev, i) { + memset(&sb_cnt_info, 0, sizeof(sb_cnt_info)); + qed_int_get_num_sbs(&cdev->hwfns[i], &sb_cnt_info); + cdev->int_params.in.num_vectors += sb_cnt_info.sb_cnt; + cdev->int_params.in.num_vectors++; /* slowpath */ + } /* We want a minimum of one slowpath and one fastpath vector per hwfn */ cdev->int_params.in.min_msix_cnt = cdev->num_hwfns * 2; diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 3d43c1d4ecef..1f7599c77cd4 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -446,6 +446,12 @@ struct qed_eth_stats { #define RX_PI 0 #define TX_PI(tc) (RX_PI + 1 + tc) +struct qed_sb_cnt_info { + int sb_cnt; + int sb_iov_cnt; + int sb_free_blk; +}; + static inline u16 qed_sb_update_sb_idx(struct qed_sb_info *sb_info) { u32 prod = 0; -- cgit v1.2.3 From afea03656add70a0e00f5b0039f87288c7af8b9f Mon Sep 17 00:00:00 2001 From: Giuseppe Cavallaro Date: Mon, 29 Feb 2016 14:27:28 +0100 Subject: stmmac: rework DMA bus setting and introduce new platform AXI structure This patch restructures the DMA bus settings and this is done by introducing a new platform structure used for programming the AXI Bus Mode Register inside the DMA module. This structure can be populated from device-tree as documented in the binding txt file. After initializing the DMA, the AXI register can be optionally tuned for platform drivers based. This patch also reworks some parameters to make coherent the DMA configuration now that AXI register is introduced. For example, the burst_len is managed by using the mentioned axi support above; so the snps,burst-len parameter has been removed. It makes sense to provide the AAL parameter from DT to Address-Aligned Beats inside the Register0 and review the PBL settings when initialize the engine. For PCI glue, rebuilding the story of this setting, it was added to align a configuration so not for fixing some known problem. No issue raised after this patch. It is safe to use the default burst length instead of tuning it to the maximum value Signed-off-by: Giuseppe Cavallaro Signed-off-by: Alexandre TORGUE Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/stmmac.txt | 54 ++++++++---- drivers/net/ethernet/stmicro/stmmac/common.h | 5 +- drivers/net/ethernet/stmicro/stmmac/dwmac1000.h | 2 +- .../net/ethernet/stmicro/stmmac/dwmac1000_dma.c | 99 +++++++++++++++------- drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h | 34 +++++++- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 12 ++- drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c | 4 +- .../net/ethernet/stmicro/stmmac/stmmac_platform.c | 42 ++++++++- include/linux/stmmac.h | 17 +++- 10 files changed, 209 insertions(+), 62 deletions(-) (limited to 'include/linux') diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt index e862a922bd3f..6605d19601c2 100644 --- a/Documentation/devicetree/bindings/net/stmmac.txt +++ b/Documentation/devicetree/bindings/net/stmmac.txt @@ -17,7 +17,25 @@ Required properties: The 1st cell is reset pre-delay in micro seconds. The 2nd cell is reset pulse in micro seconds. The 3rd cell is reset post-delay in micro seconds. + +Optional properties: +- resets: Should contain a phandle to the STMMAC reset signal, if any +- reset-names: Should contain the reset signal name "stmmaceth", if a + reset phandle is given +- max-frame-size: See ethernet.txt file in the same directory +- clocks: If present, the first clock should be the GMAC main clock and + the second clock should be peripheral's register interface clock. Further + clocks may be specified in derived bindings. +- clock-names: One name for each entry in the clocks property, the + first one should be "stmmaceth" and the second one should be "pclk". +- clk_ptp_ref: this is the PTP reference clock; in case of the PTP is + available this clock is used for programming the Timestamp Addend Register. + If not passed then the system clock will be used and this is fine on some + platforms. +- tx-fifo-depth: See ethernet.txt file in the same directory +- rx-fifo-depth: See ethernet.txt file in the same directory - snps,pbl Programmable Burst Length +- snps,aal Address-Aligned Beats - snps,fixed-burst Program the DMA to use the fixed burst mode - snps,mixed-burst Program the DMA to use the mixed burst mode - snps,force_thresh_dma_mode Force DMA to use the threshold mode for @@ -29,27 +47,28 @@ Required properties: supported by this device instance - snps,perfect-filter-entries: Number of perfect filter entries supported by this device instance - -Optional properties: -- resets: Should contain a phandle to the STMMAC reset signal, if any -- reset-names: Should contain the reset signal name "stmmaceth", if a - reset phandle is given -- max-frame-size: See ethernet.txt file in the same directory -- clocks: If present, the first clock should be the GMAC main clock - The optional second clock should be peripheral's register interface clock. - The third optional clock should be the ptp reference clock. - Further clocks may be specified in derived bindings. -- clock-names: One name for each entry in the clocks property. - The first one should be "stmmaceth". - The optional second one should be "pclk". - The optional third one should be "clk_ptp_ref". -- snps,burst_len: The AXI burst lenth value of the AXI BUS MODE register. -- tx-fifo-depth: See ethernet.txt file in the same directory -- rx-fifo-depth: See ethernet.txt file in the same directory +- AXI BUS Mode parameters: below the list of all the parameters to program the + AXI register inside the DMA module: + - snps,lpi_en: enable Low Power Interface + - snps,xit_frm: unlock on WoL + - snps,wr_osr_lmt: max write oustanding req. limit + - snps,rd_osr_lmt: max read oustanding req. limit + - snps,kbbe: do not cross 1KiB boundary. + - snps,axi_all: align address + - snps,blen: this is a vector of supported burst length. + - snps,fb: fixed-burst + - snps,mb: mixed-burst + - snps,rb: rebuild INCRx Burst - mdio: with compatible = "snps,dwmac-mdio", create and register mdio bus. Examples: + stmmac_axi_setup: stmmac-axi-config { + snps,wr_osr_lmt = <0xf>; + snps,rd_osr_lmt = <0xf>; + snps,blen = <256 128 64 32 0 0 0>; + }; + gmac0: ethernet@e0800000 { compatible = "st,spear600-gmac"; reg = <0xe0800000 0x8000>; @@ -65,6 +84,7 @@ Examples: tx-fifo-depth = <16384>; clocks = <&clock>; clock-names = "stmmaceth"; + snps,axi-config = <&stmmac_axi_setup>; mdio0 { #address-cells = <1>; #size-cells = <0>; diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index bac0e44d7634..586a33624dd2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -27,6 +27,7 @@ #include #include +#include #include #include #if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) @@ -378,7 +379,9 @@ struct stmmac_dma_ops { /* DMA core initialization */ int (*reset)(void __iomem *ioaddr); void (*init)(void __iomem *ioaddr, int pbl, int fb, int mb, - int burst_len, u32 dma_tx, u32 dma_rx, int atds); + int aal, u32 dma_tx, u32 dma_rx, int atds); + /* Configure the AXI Bus Mode Register */ + void (*axi)(void __iomem *ioaddr, struct stmmac_axi *axi); /* Dump DMA registers */ void (*dump_regs) (void __iomem *ioaddr); /* Set tx/rx threshold in the csr6 register diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h index 9d36ae788429..b0593a4268ee 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h @@ -240,7 +240,7 @@ enum rx_tx_priority_ratio { #define DMA_BUS_MODE_RPBL_MASK 0x003e0000 /* Rx-Programmable Burst Len */ #define DMA_BUS_MODE_RPBL_SHIFT 17 #define DMA_BUS_MODE_USP 0x00800000 -#define DMA_BUS_MODE_PBL 0x01000000 +#define DMA_BUS_MODE_MAXPBL 0x01000000 #define DMA_BUS_MODE_AAL 0x02000000 /* DMA CRS Control and Status Register Mapping */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c index 5f0aea56b298..da32d6037e3e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c @@ -30,24 +30,76 @@ #include "dwmac1000.h" #include "dwmac_dma.h" +static void dwmac1000_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi) +{ + u32 value = readl(ioaddr + DMA_AXI_BUS_MODE); + int i; + + pr_info("dwmac1000: Master AXI performs %s burst length\n", + !(value & DMA_AXI_UNDEF) ? "fixed" : "any"); + + if (axi->axi_lpi_en) + value |= DMA_AXI_EN_LPI; + if (axi->axi_xit_frm) + value |= DMA_AXI_LPI_XIT_FRM; + + value |= (axi->axi_wr_osr_lmt & DMA_AXI_WR_OSR_LMT_MASK) << + DMA_AXI_WR_OSR_LMT_SHIFT; + + value |= (axi->axi_rd_osr_lmt & DMA_AXI_RD_OSR_LMT_MASK) << + DMA_AXI_RD_OSR_LMT_SHIFT; + + /* Depending on the UNDEF bit the Master AXI will perform any burst + * length according to the BLEN programmed (by default all BLEN are + * set). + */ + for (i = 0; i < AXI_BLEN; i++) { + switch (axi->axi_blen[i]) { + case 256: + value |= DMA_AXI_BLEN256; + break; + case 128: + value |= DMA_AXI_BLEN128; + break; + case 64: + value |= DMA_AXI_BLEN64; + break; + case 32: + value |= DMA_AXI_BLEN32; + break; + case 16: + value |= DMA_AXI_BLEN16; + break; + case 8: + value |= DMA_AXI_BLEN8; + break; + case 4: + value |= DMA_AXI_BLEN4; + break; + } + } + + writel(value, ioaddr + DMA_AXI_BUS_MODE); +} + static void dwmac1000_dma_init(void __iomem *ioaddr, int pbl, int fb, int mb, - int burst_len, u32 dma_tx, u32 dma_rx, int atds) + int aal, u32 dma_tx, u32 dma_rx, int atds) { - u32 value; + u32 value = readl(ioaddr + DMA_BUS_MODE); /* - * Set the DMA PBL (Programmable Burst Length) mode - * Before stmmac core 3.50 this mode bit was 4xPBL, and + * Set the DMA PBL (Programmable Burst Length) mode. + * + * Note: before stmmac core 3.50 this mode bit was 4xPBL, and * post 3.5 mode bit acts as 8*PBL. - * For core rev < 3.5, when the core is set for 4xPBL mode, the - * DMA transfers the data in 4, 8, 16, 32, 64 & 128 beats - * depending on pbl value. - * For core rev > 3.5, when the core is set for 8xPBL mode, the - * DMA transfers the data in 8, 16, 32, 64, 128 & 256 beats - * depending on pbl value. + * + * This configuration doesn't take care about the Separate PBL + * so only the bits: 13-8 are programmed with the PBL passed from the + * platform. */ - value = DMA_BUS_MODE_PBL | ((pbl << DMA_BUS_MODE_PBL_SHIFT) | - (pbl << DMA_BUS_MODE_RPBL_SHIFT)); + value |= DMA_BUS_MODE_MAXPBL; + value &= ~DMA_BUS_MODE_PBL_MASK; + value |= (pbl << DMA_BUS_MODE_PBL_SHIFT); /* Set the Fixed burst mode */ if (fb) @@ -60,26 +112,10 @@ static void dwmac1000_dma_init(void __iomem *ioaddr, int pbl, int fb, int mb, if (atds) value |= DMA_BUS_MODE_ATDS; - writel(value, ioaddr + DMA_BUS_MODE); + if (aal) + value |= DMA_BUS_MODE_AAL; - /* In case of GMAC AXI configuration, program the DMA_AXI_BUS_MODE - * for supported bursts. - * - * Note: This is applicable only for revision GMACv3.61a. For - * older version this register is reserved and shall have no - * effect. - * - * Note: - * For Fixed Burst Mode: if we directly write 0xFF to this - * register using the configurations pass from platform code, - * this would ensure that all bursts supported by core are set - * and those which are not supported would remain ineffective. - * - * For Non Fixed Burst Mode: provide the maximum value of the - * burst length. Any burst equal or below the provided burst - * length would be allowed to perform. - */ - writel(burst_len, ioaddr + DMA_AXI_BUS_MODE); + writel(value, ioaddr + DMA_BUS_MODE); /* Mask interrupts by writing to CSR7 */ writel(DMA_INTR_DEFAULT_MASK, ioaddr + DMA_INTR_ENA); @@ -192,6 +228,7 @@ static void dwmac1000_rx_watchdog(void __iomem *ioaddr, u32 riwt) const struct stmmac_dma_ops dwmac1000_dma_ops = { .reset = dwmac_dma_reset, .init = dwmac1000_dma_init, + .axi = dwmac1000_dma_axi, .dump_regs = dwmac1000_dump_dma_regs, .dma_mode = dwmac1000_dma_operation_mode, .enable_dma_transmission = dwmac_enable_dma_transmission, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c index c40582a938a4..61f54c99a7de 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c @@ -33,7 +33,7 @@ #include "dwmac_dma.h" static void dwmac100_dma_init(void __iomem *ioaddr, int pbl, int fb, int mb, - int burst_len, u32 dma_tx, u32 dma_rx, int atds) + int aal, u32 dma_tx, u32 dma_rx, int atds) { /* Enable Application Access by writing to DMA CSR0 */ writel(DMA_BUS_MODE_DEFAULT | (pbl << DMA_BUS_MODE_PBL_SHIFT), diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h index 13ca90e23479..726d9d9aaf83 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h @@ -41,8 +41,40 @@ /* Rx watchdog register */ #define DMA_RX_WATCHDOG 0x00001024 -/* AXI Bus Mode */ + +/* AXI Master Bus Mode */ #define DMA_AXI_BUS_MODE 0x00001028 + +#define DMA_AXI_EN_LPI BIT(31) +#define DMA_AXI_LPI_XIT_FRM BIT(30) +#define DMA_AXI_WR_OSR_LMT GENMASK(23, 20) +#define DMA_AXI_WR_OSR_LMT_SHIFT 20 +#define DMA_AXI_WR_OSR_LMT_MASK 0xf +#define DMA_AXI_RD_OSR_LMT GENMASK(19, 16) +#define DMA_AXI_RD_OSR_LMT_SHIFT 16 +#define DMA_AXI_RD_OSR_LMT_MASK 0xf + +#define DMA_AXI_OSR_MAX 0xf +#define DMA_AXI_MAX_OSR_LIMIT ((DMA_AXI_OSR_MAX << DMA_AXI_WR_OSR_LMT_SHIFT) | \ + (DMA_AXI_OSR_MAX << DMA_AXI_RD_OSR_LMT_SHIFT)) +#define DMA_AXI_1KBBE BIT(13) +#define DMA_AXI_AAL BIT(12) +#define DMA_AXI_BLEN256 BIT(7) +#define DMA_AXI_BLEN128 BIT(6) +#define DMA_AXI_BLEN64 BIT(5) +#define DMA_AXI_BLEN32 BIT(4) +#define DMA_AXI_BLEN16 BIT(3) +#define DMA_AXI_BLEN8 BIT(2) +#define DMA_AXI_BLEN4 BIT(1) +#define DMA_BURST_LEN_DEFAULT (DMA_AXI_BLEN256 | DMA_AXI_BLEN128 | \ + DMA_AXI_BLEN64 | DMA_AXI_BLEN32 | \ + DMA_AXI_BLEN16 | DMA_AXI_BLEN8 | \ + DMA_AXI_BLEN4) + +#define DMA_AXI_UNDEF BIT(0) + +#define DMA_AXI_BURST_LEN_MASK 0x000000FE + #define DMA_CUR_TX_BUF_ADDR 0x00001050 /* Current Host Tx Buffer */ #define DMA_CUR_RX_BUF_ADDR 0x00001054 /* Current Host Rx Buffer */ #define DMA_HW_FEATURE 0x00001058 /* HW Feature Register */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 13752e933e43..89c26268822e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1635,7 +1635,7 @@ static void stmmac_check_ether_addr(struct stmmac_priv *priv) */ static int stmmac_init_dma_engine(struct stmmac_priv *priv) { - int pbl = DEFAULT_DMA_PBL, fixed_burst = 0, burst_len = 0; + int pbl = DEFAULT_DMA_PBL, fixed_burst = 0, aal = 0; int mixed_burst = 0; int atds = 0; int ret = 0; @@ -1644,7 +1644,7 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) pbl = priv->plat->dma_cfg->pbl; fixed_burst = priv->plat->dma_cfg->fixed_burst; mixed_burst = priv->plat->dma_cfg->mixed_burst; - burst_len = priv->plat->dma_cfg->burst_len; + aal = priv->plat->dma_cfg->aal; } if (priv->extend_desc && (priv->mode == STMMAC_RING_MODE)) @@ -1657,8 +1657,12 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) } priv->hw->dma->init(priv->ioaddr, pbl, fixed_burst, mixed_burst, - burst_len, priv->dma_tx_phy, - priv->dma_rx_phy, atds); + aal, priv->dma_tx_phy, priv->dma_rx_phy, atds); + + if ((priv->synopsys_id >= DWMAC_CORE_3_50) && + (priv->plat->axi && priv->hw->dma->axi)) + priv->hw->dma->axi(priv->ioaddr, priv->plat->axi); + return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index d71a721ea61c..ae4388735b7f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -81,7 +81,7 @@ static void stmmac_default_data(struct plat_stmmacenet_data *plat) plat->mdio_bus_data->phy_mask = 0; plat->dma_cfg->pbl = 32; - plat->dma_cfg->burst_len = DMA_AXI_BLEN_256; + /* TODO: AXI */ /* Set default value for multicast hash bins */ plat->multicast_filter_bins = HASH_TABLE_SIZE; @@ -115,8 +115,8 @@ static int quark_default_data(struct plat_stmmacenet_data *plat, plat->mdio_bus_data->phy_mask = 0; plat->dma_cfg->pbl = 16; - plat->dma_cfg->burst_len = DMA_AXI_BLEN_256; plat->dma_cfg->fixed_burst = 1; + /* AXI (TODO) */ /* Set default value for multicast hash bins */ plat->multicast_filter_bins = HASH_TABLE_SIZE; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 6a52fa18cbf2..69ccf486d4fa 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -95,6 +95,42 @@ static int dwmac1000_validate_ucast_entries(int ucast_entries) return x; } +/** + * stmmac_axi_setup - parse DT parameters for programming the AXI register + * @pdev: platform device + * @priv: driver private struct. + * Description: + * if required, from device-tree the AXI internal register can be tuned + * by using platform parameters. + */ +static struct stmmac_axi *stmmac_axi_setup(struct platform_device *pdev) +{ + struct device_node *np; + struct stmmac_axi *axi; + + np = of_parse_phandle(pdev->dev.of_node, "snps,axi-config", 0); + if (!np) + return NULL; + + axi = kzalloc(sizeof(axi), GFP_KERNEL); + if (!axi) + return ERR_PTR(-ENOMEM); + + axi->axi_lpi_en = of_property_read_bool(np, "snps,lpi_en"); + axi->axi_xit_frm = of_property_read_bool(np, "snps,xit_frm"); + axi->axi_kbbe = of_property_read_bool(np, "snps,axi_kbbe"); + axi->axi_axi_all = of_property_read_bool(np, "snps,axi_all"); + axi->axi_fb = of_property_read_bool(np, "snps,axi_fb"); + axi->axi_mb = of_property_read_bool(np, "snps,axi_mb"); + axi->axi_rb = of_property_read_bool(np, "snps,axi_rb"); + + of_property_read_u32(np, "snps,wr_osr_lmt", &axi->axi_wr_osr_lmt); + of_property_read_u32(np, "snps,rd_osr_lmt", &axi->axi_rd_osr_lmt); + of_property_read_u32_array(np, "snps,blen", axi->axi_blen, AXI_BLEN); + + return axi; +} + /** * stmmac_probe_config_dt - parse device-tree driver parameters * @pdev: platform_device structure @@ -216,13 +252,11 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) } plat->dma_cfg = dma_cfg; of_property_read_u32(np, "snps,pbl", &dma_cfg->pbl); + dma_cfg->aal = of_property_read_bool(np, "snps,aal"); dma_cfg->fixed_burst = of_property_read_bool(np, "snps,fixed-burst"); dma_cfg->mixed_burst = of_property_read_bool(np, "snps,mixed-burst"); - of_property_read_u32(np, "snps,burst_len", &dma_cfg->burst_len); - if (dma_cfg->burst_len < 0 || dma_cfg->burst_len > 256) - dma_cfg->burst_len = 0; } plat->force_thresh_dma_mode = of_property_read_bool(np, "snps,force_thresh_dma_mode"); if (plat->force_thresh_dma_mode) { @@ -230,6 +264,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) pr_warn("force_sf_dma_mode is ignored if force_thresh_dma_mode is set."); } + plat->axi = stmmac_axi_setup(pdev); + return plat; } #else diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index eead8ab93c0a..6e53fa8942a4 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -90,7 +90,21 @@ struct stmmac_dma_cfg { int pbl; int fixed_burst; int mixed_burst; - int burst_len; + bool aal; +}; + +#define AXI_BLEN 7 +struct stmmac_axi { + bool axi_lpi_en; + bool axi_xit_frm; + u32 axi_wr_osr_lmt; + u32 axi_rd_osr_lmt; + bool axi_kbbe; + bool axi_axi_all; + u32 axi_blen[AXI_BLEN]; + bool axi_fb; + bool axi_mb; + bool axi_rb; }; struct plat_stmmacenet_data { @@ -122,5 +136,6 @@ struct plat_stmmacenet_data { int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); void *bsp_priv; + struct stmmac_axi *axi; }; #endif -- cgit v1.2.3 From b5d3755a22e0cc4c369c0985aef0c52c2477c1e7 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Fri, 4 Mar 2016 11:52:16 +0100 Subject: uapi: define DIV_ROUND_UP for userland DIV_ROUND_UP is defined in linux/kernel.h only for the kernel. When ethtool.h is included by a userland app, we got the following error: include/linux/ethtool.h:1218:8: error: variably modified 'queue_mask' at file scope __u32 queue_mask[DIV_ROUND_UP(MAX_NUM_QUEUE, 32)]; ^ Let's add a common definition in uapi and use it everywhere. Fixes: ac2c7ad0e5d6 ("net/ethtool: introduce a new ioctl for per queue setting") CC: Kan Liang Suggested-by: Ben Hutchings Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/linux/kernel.h | 2 +- include/uapi/linux/ethtool.h | 3 ++- include/uapi/linux/kernel.h | 1 + include/uapi/linux/mroute6.h | 9 ++------- 4 files changed, 6 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index f31638c6e873..ac1923957236 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -64,7 +64,7 @@ #define round_down(x, y) ((x) & ~__round_mask(x, y)) #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) -#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) +#define DIV_ROUND_UP __KERNEL_DIV_ROUND_UP #define DIV_ROUND_UP_ULL(ll,d) \ ({ unsigned long long _tmp = (ll)+(d)-1; do_div(_tmp, d); _tmp; }) diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 37fd6dc33de4..9c22249ebf35 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -13,6 +13,7 @@ #ifndef _UAPI_LINUX_ETHTOOL_H #define _UAPI_LINUX_ETHTOOL_H +#include #include #include @@ -1215,7 +1216,7 @@ enum ethtool_sfeatures_retval_bits { struct ethtool_per_queue_op { __u32 cmd; __u32 sub_command; - __u32 queue_mask[DIV_ROUND_UP(MAX_NUM_QUEUE, 32)]; + __u32 queue_mask[__KERNEL_DIV_ROUND_UP(MAX_NUM_QUEUE, 32)]; char data[]; }; diff --git a/include/uapi/linux/kernel.h b/include/uapi/linux/kernel.h index 321e399457f5..466073f0ce46 100644 --- a/include/uapi/linux/kernel.h +++ b/include/uapi/linux/kernel.h @@ -9,5 +9,6 @@ #define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) +#define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) #endif /* _UAPI_LINUX_KERNEL_H */ diff --git a/include/uapi/linux/mroute6.h b/include/uapi/linux/mroute6.h index ce91215cf7e6..5062fb5751e1 100644 --- a/include/uapi/linux/mroute6.h +++ b/include/uapi/linux/mroute6.h @@ -1,6 +1,7 @@ #ifndef _UAPI__LINUX_MROUTE6_H #define _UAPI__LINUX_MROUTE6_H +#include #include #include @@ -46,14 +47,8 @@ typedef unsigned short mifi_t; typedef __u32 if_mask; #define NIFBITS (sizeof(if_mask) * 8) /* bits per mask */ -#if !defined(__KERNEL__) -#if !defined(DIV_ROUND_UP) -#define DIV_ROUND_UP(x,y) (((x) + ((y) - 1)) / (y)) -#endif -#endif - typedef struct if_set { - if_mask ifs_bits[DIV_ROUND_UP(IF_SETSIZE, NIFBITS)]; + if_mask ifs_bits[__KERNEL_DIV_ROUND_UP(IF_SETSIZE, NIFBITS)]; } if_set; #define IF_SET(n, p) ((p)->ifs_bits[(n)/NIFBITS] |= (1 << ((n) % NIFBITS))) -- cgit v1.2.3