From da0cb6432175854bd0bf3fbaf7c975f484c79db3 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 26 Oct 2020 14:32:30 -0600 Subject: [PATCH] task_work: Use TIF_NOTIFY_SIGNAL if available stable inclusion from stable-v5.10.162 commit eb42e7b3043167d21f90204df75fa21b6d4af3ff category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7P7OH Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=eb42e7b3043167d21f90204df75fa21b6d4af3ff -------------------------------- [ Upstream commit 114518eb6430b832d2f9f5a008043b913ccf0e24 ] If the arch supports TIF_NOTIFY_SIGNAL, then use that for TWA_SIGNAL as it's more efficient than using the signal delivery method. This is especially true on threaded applications, where ->sighand is shared across threads, but it's also lighter weight on non-shared cases. io_uring is a heavy consumer of TWA_SIGNAL based task_work. A test with threads shows a nice improvement running an io_uring based echo server. stock kernel: 0.01% <= 0.1 milliseconds 95.86% <= 0.2 milliseconds 98.27% <= 0.3 milliseconds 99.71% <= 0.4 milliseconds 100.00% <= 0.5 milliseconds 100.00% <= 0.6 milliseconds 100.00% <= 0.7 milliseconds 100.00% <= 0.8 milliseconds 100.00% <= 0.9 milliseconds 100.00% <= 1.0 milliseconds 100.00% <= 1.1 milliseconds 100.00% <= 2 milliseconds 100.00% <= 3 milliseconds 100.00% <= 3 milliseconds 1378930.00 requests per second ~1600% CPU 1.38M requests/second, and all 16 CPUs are maxed out. patched kernel: 0.01% <= 0.1 milliseconds 98.24% <= 0.2 milliseconds 99.47% <= 0.3 milliseconds 99.99% <= 0.4 milliseconds 100.00% <= 0.5 milliseconds 100.00% <= 0.6 milliseconds 100.00% <= 0.7 milliseconds 100.00% <= 0.8 milliseconds 100.00% <= 0.9 milliseconds 100.00% <= 1.2 milliseconds 1666111.38 requests per second ~1450% CPU 1.67M requests/second, and we're no longer just hammering on the sighand lock. The original reporter states: "For 5.7.15 my benchmark achieves 1.6M qps and system cpu is at ~80%. for 5.7.16 or later it achieves only 1M qps and the system cpu is is at ~100%" with the only difference there being that TWA_SIGNAL is used unconditionally in 5.7.16, since it's required to be able to handle the inability to run task_work if the application is waiting in the kernel already on an event that needs task_work run to be satisfied. Also see commit 0ba9c9edcd15. Reported-by: Roman Gershman Signed-off-by: Jens Axboe Signed-off-by: Thomas Gleixner Reviewed-by: Oleg Nesterov Link: https://lore.kernel.org/r/20201026203230.386348-5-axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman Signed-off-by: sanglipeng --- kernel/task_work.c | 41 +++++++++++++++++++++++++++++------------ 1 file changed, 29 insertions(+), 12 deletions(-) diff --git a/kernel/task_work.c b/kernel/task_work.c index eff8f5d3eedd..957b3e8113a5 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -5,6 +5,34 @@ static struct callback_head work_exited; /* all we need is ->next == NULL */ +/* + * TWA_SIGNAL signaling - use TIF_NOTIFY_SIGNAL, if available, as it's faster + * than TIF_SIGPENDING as there's no dependency on ->sighand. The latter is + * shared for threads, and can cause contention on sighand->lock. Even for + * the non-threaded case TIF_NOTIFY_SIGNAL is more efficient, as no locking + * or IRQ disabling is involved for notification (or running) purposes. + */ +static void task_work_notify_signal(struct task_struct *task) +{ +#if defined(TIF_NOTIFY_SIGNAL) + set_notify_signal(task); +#else + unsigned long flags; + + /* + * Only grab the sighand lock if we don't already have some + * task_work pending. This pairs with the smp_store_mb() + * in get_signal(), see comment there. + */ + if (!(READ_ONCE(task->jobctl) & JOBCTL_TASK_WORK) && + lock_task_sighand(task, &flags)) { + task->jobctl |= JOBCTL_TASK_WORK; + signal_wake_up(task, 0); + unlock_task_sighand(task, &flags); + } +#endif +} + /** * task_work_add - ask the @task to execute @work->func() * @task: the task which should run the callback @@ -33,7 +61,6 @@ int task_work_add(struct task_struct *task, struct callback_head *work, enum task_work_notify_mode notify) { struct callback_head *head; - unsigned long flags; do { head = READ_ONCE(task->task_works); @@ -49,17 +76,7 @@ int task_work_add(struct task_struct *task, struct callback_head *work, set_notify_resume(task); break; case TWA_SIGNAL: - /* - * Only grab the sighand lock if we don't already have some - * task_work pending. This pairs with the smp_store_mb() - * in get_signal(), see comment there. - */ - if (!(READ_ONCE(task->jobctl) & JOBCTL_TASK_WORK) && - lock_task_sighand(task, &flags)) { - task->jobctl |= JOBCTL_TASK_WORK; - signal_wake_up(task, 0); - unlock_task_sighand(task, &flags); - } + task_work_notify_signal(task); break; default: WARN_ON_ONCE(1); -- GitLab