From 6e317c32fd39a13e4854a27958d5e35d15d196be Mon Sep 17 00:00:00 2001 From: Alexander Popov Date: Sat, 18 Jan 2020 01:59:00 +0300 Subject: timer: Improve the comment describing schedule_timeout() When working commit 6dcd5d7a7a29c1e, a mistake was noticed by Linus: schedule_timeout() was called without setting the task state to anything particular. It calls the scheduler, but doesn't delay anything, because the task stays runnable. That happens because sched_submit_work() does nothing for tasks in TASK_RUNNING state. That turned out to be the intended behavior. Adding a WARN() is not useful as the task could be woken up right after setting the state and before reaching schedule_timeout(). Improve the comment about schedule_timeout() and describe that more explicitly. Signed-off-by: Alexander Popov Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20200117225900.16340-1-alex.popov@linux.com --- kernel/time/timer.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'kernel/time/timer.c') diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 4820823515e9..cb34fac9d9f7 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1828,21 +1828,23 @@ static void process_timeout(struct timer_list *t) * schedule_timeout - sleep until timeout * @timeout: timeout value in jiffies * - * Make the current task sleep until @timeout jiffies have - * elapsed. The routine will return immediately unless - * the current task state has been set (see set_current_state()). + * Make the current task sleep until @timeout jiffies have elapsed. + * The function behavior depends on the current task state + * (see also set_current_state() description): * - * You can set the task state as follows - + * %TASK_RUNNING - the scheduler is called, but the task does not sleep + * at all. That happens because sched_submit_work() does nothing for + * tasks in %TASK_RUNNING state. * * %TASK_UNINTERRUPTIBLE - at least @timeout jiffies are guaranteed to * pass before the routine returns unless the current task is explicitly - * woken up, (e.g. by wake_up_process())". + * woken up, (e.g. by wake_up_process()). * * %TASK_INTERRUPTIBLE - the routine may return early if a signal is * delivered to the current task or the current task is explicitly woken * up. * - * The current task state is guaranteed to be TASK_RUNNING when this + * The current task state is guaranteed to be %TASK_RUNNING when this * routine returns. * * Specifying a @timeout value of %MAX_SCHEDULE_TIMEOUT will schedule @@ -1850,7 +1852,7 @@ static void process_timeout(struct timer_list *t) * value will be %MAX_SCHEDULE_TIMEOUT. * * Returns 0 when the timer has expired otherwise the remaining time in - * jiffies will be returned. In all cases the return value is guaranteed + * jiffies will be returned. In all cases the return value is guaranteed * to be non-negative. */ signed long __sched schedule_timeout(signed long timeout) -- cgit v1.2.3 From 90c018942c2babab73814648b37808fc3bf2ed1a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 Nov 2019 11:37:38 -0800 Subject: timer: Use hlist_unhashed_lockless() in timer_pending() The timer_pending() function is mostly used in lockless contexts, so Without proper annotations, KCSAN might detect a data-race [1]. Using hlist_unhashed_lockless() instead of hand-coding it seems appropriate (as suggested by Paul E. McKenney). [1] BUG: KCSAN: data-race in del_timer / detach_if_pending write to 0xffff88808697d870 of 8 bytes by task 10 on cpu 0: __hlist_del include/linux/list.h:764 [inline] detach_timer kernel/time/timer.c:815 [inline] detach_if_pending+0xcd/0x2d0 kernel/time/timer.c:832 try_to_del_timer_sync+0x60/0xb0 kernel/time/timer.c:1226 del_timer_sync+0x6b/0xa0 kernel/time/timer.c:1365 schedule_timeout+0x2d2/0x6e0 kernel/time/timer.c:1896 rcu_gp_fqs_loop+0x37c/0x580 kernel/rcu/tree.c:1639 rcu_gp_kthread+0x143/0x230 kernel/rcu/tree.c:1799 kthread+0x1d4/0x200 drivers/block/aoe/aoecmd.c:1253 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:352 read to 0xffff88808697d870 of 8 bytes by task 12060 on cpu 1: del_timer+0x3b/0xb0 kernel/time/timer.c:1198 sk_stop_timer+0x25/0x60 net/core/sock.c:2845 inet_csk_clear_xmit_timers+0x69/0xa0 net/ipv4/inet_connection_sock.c:523 tcp_clear_xmit_timers include/net/tcp.h:606 [inline] tcp_v4_destroy_sock+0xa3/0x3f0 net/ipv4/tcp_ipv4.c:2096 inet_csk_destroy_sock+0xf4/0x250 net/ipv4/inet_connection_sock.c:836 tcp_close+0x6f3/0x970 net/ipv4/tcp.c:2497 inet_release+0x86/0x100 net/ipv4/af_inet.c:427 __sock_release+0x85/0x160 net/socket.c:590 sock_close+0x24/0x30 net/socket.c:1268 __fput+0x1e1/0x520 fs/file_table.c:280 ____fput+0x1f/0x30 fs/file_table.c:313 task_work_run+0xf6/0x130 kernel/task_work.c:113 tracehook_notify_resume include/linux/tracehook.h:188 [inline] exit_to_usermode_loop+0x2b4/0x2c0 arch/x86/entry/common.c:163 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 12060 Comm: syz-executor.5 Not tainted 5.4.0-rc3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, Signed-off-by: Eric Dumazet Cc: Thomas Gleixner [ paulmck: Pulled in Eric's later amendments. ] Signed-off-by: Paul E. McKenney --- kernel/time/timer.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'kernel/time/timer.c') diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 4820823515e9..568564ae3597 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -944,6 +944,7 @@ static struct timer_base *lock_timer_base(struct timer_list *timer, #define MOD_TIMER_PENDING_ONLY 0x01 #define MOD_TIMER_REDUCE 0x02 +#define MOD_TIMER_NOTPENDING 0x04 static inline int __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int options) @@ -960,7 +961,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option * the timer is re-modified to have the same timeout or ends up in the * same array bucket then just return: */ - if (timer_pending(timer)) { + if (!(options & MOD_TIMER_NOTPENDING) && timer_pending(timer)) { /* * The downside of this optimization is that it can result in * larger granularity than you would get from adding a new @@ -1133,7 +1134,7 @@ EXPORT_SYMBOL(timer_reduce); void add_timer(struct timer_list *timer) { BUG_ON(timer_pending(timer)); - mod_timer(timer, timer->expires); + __mod_timer(timer, timer->expires, MOD_TIMER_NOTPENDING); } EXPORT_SYMBOL(add_timer); @@ -1891,7 +1892,7 @@ signed long __sched schedule_timeout(signed long timeout) timer.task = current; timer_setup_on_stack(&timer.timer, process_timeout, 0); - __mod_timer(&timer.timer, expire, 0); + __mod_timer(&timer.timer, expire, MOD_TIMER_NOTPENDING); schedule(); del_singleshot_timer_sync(&timer.timer); -- cgit v1.2.3