From aebacb7f6ca1926918734faae14d1f0b6fae5cb7 Mon Sep 17 00:00:00 2001 From: Nicolas Saenz Julienne Date: Fri, 9 Jul 2021 16:13:25 +0200 Subject: timers: Fix get_next_timer_interrupt() with no timers pending 31cd0e119d50 ("timers: Recalculate next timer interrupt only when necessary") subtly altered get_next_timer_interrupt()'s behaviour. The function no longer consistently returns KTIME_MAX with no timers pending. In order to decide if there are any timers pending we check whether the next expiry will happen NEXT_TIMER_MAX_DELTA jiffies from now. Unfortunately, the next expiry time and the timer base clock are no longer updated in unison. The former changes upon certain timer operations (enqueue, expire, detach), whereas the latter keeps track of jiffies as they move forward. Ultimately breaking the logic above. A simplified example: - Upon entering get_next_timer_interrupt() with: jiffies = 1 base->clk = 0; base->next_expiry = NEXT_TIMER_MAX_DELTA; 'base->next_expiry == base->clk + NEXT_TIMER_MAX_DELTA', the function returns KTIME_MAX. - 'base->clk' is updated to the jiffies value. - The next time we enter get_next_timer_interrupt(), taking into account no timer operations happened: base->clk = 1; base->next_expiry = NEXT_TIMER_MAX_DELTA; 'base->next_expiry != base->clk + NEXT_TIMER_MAX_DELTA', the function returns a valid expire time, which is incorrect. This ultimately might unnecessarily rearm sched's timer on nohz_full setups, and add latency to the system[1]. So, introduce 'base->timers_pending'[2], update it every time 'base->next_expiry' changes, and use it in get_next_timer_interrupt(). [1] See tick_nohz_stop_tick(). [2] A quick pahole check on x86_64 and arm64 shows it doesn't make 'struct timer_base' any bigger. Fixes: 31cd0e119d50 ("timers: Recalculate next timer interrupt only when necessary") Signed-off-by: Nicolas Saenz Julienne Signed-off-by: Frederic Weisbecker --- kernel/time/timer.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'kernel/time/timer.c') diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 3fadb58fc9d7..9eb11c2209e5 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -207,6 +207,7 @@ struct timer_base { unsigned int cpu; bool next_expiry_recalc; bool is_idle; + bool timers_pending; DECLARE_BITMAP(pending_map, WHEEL_SIZE); struct hlist_head vectors[WHEEL_SIZE]; } ____cacheline_aligned; @@ -595,6 +596,7 @@ static void enqueue_timer(struct timer_base *base, struct timer_list *timer, * can reevaluate the wheel: */ base->next_expiry = bucket_expiry; + base->timers_pending = true; base->next_expiry_recalc = false; trigger_dyntick_cpu(base, timer); } @@ -1582,6 +1584,7 @@ static unsigned long __next_timer_interrupt(struct timer_base *base) } base->next_expiry_recalc = false; + base->timers_pending = !(next == base->clk + NEXT_TIMER_MAX_DELTA); return next; } @@ -1633,7 +1636,6 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); u64 expires = KTIME_MAX; unsigned long nextevt; - bool is_max_delta; /* * Pretend that there is no timer pending if the cpu is offline. @@ -1646,7 +1648,6 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) if (base->next_expiry_recalc) base->next_expiry = __next_timer_interrupt(base); nextevt = base->next_expiry; - is_max_delta = (nextevt == base->clk + NEXT_TIMER_MAX_DELTA); /* * We have a fresh next event. Check whether we can forward the @@ -1664,7 +1665,7 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) expires = basem; base->is_idle = false; } else { - if (!is_max_delta) + if (base->timers_pending) expires = basem + (u64)(nextevt - basej) * TICK_NSEC; /* * If we expect to sleep more than a tick, mark the base idle. @@ -1947,6 +1948,7 @@ int timers_prepare_cpu(unsigned int cpu) base = per_cpu_ptr(&timer_bases[b], cpu); base->clk = jiffies; base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA; + base->timers_pending = false; base->is_idle = false; } return 0; -- cgit v1.3-8-gc7d7 From bb7262b295472eb6858b5c49893954794027cd84 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 6 Dec 2020 22:40:07 +0100 Subject: timers: Move clearing of base::timer_running under base:: Lock syzbot reported KCSAN data races vs. timer_base::timer_running being set to NULL without holding base::lock in expire_timers(). This looks innocent and most reads are clearly not problematic, but Frederic identified an issue which is: int data = 0; void timer_func(struct timer_list *t) { data = 1; } CPU 0 CPU 1 ------------------------------ -------------------------- base = lock_timer_base(timer, &flags); raw_spin_unlock(&base->lock); if (base->running_timer != timer) call_timer_fn(timer, fn, baseclk); ret = detach_if_pending(timer, base, true); base->running_timer = NULL; raw_spin_unlock_irqrestore(&base->lock, flags); raw_spin_lock(&base->lock); x = data; If the timer has previously executed on CPU 1 and then CPU 0 can observe base->running_timer == NULL and returns, assuming the timer has completed, but it's not guaranteed on all architectures. The comment for del_timer_sync() makes that guarantee. Moving the assignment under base->lock prevents this. For non-RT kernel it's performance wise completely irrelevant whether the store happens before or after taking the lock. For an RT kernel moving the store under the lock requires an extra unlock/lock pair in the case that there is a waiter for the timer, but that's not the end of the world. Reported-by: syzbot+aa7c2385d46c5eba0b89@syzkaller.appspotmail.com Reported-by: syzbot+abea4558531bae1ba9fe@syzkaller.appspotmail.com Fixes: 030dcdd197d7 ("timers: Prepare support for PREEMPT_RT") Signed-off-by: Thomas Gleixner Tested-by: Sebastian Andrzej Siewior Link: https://lore.kernel.org/r/87lfea7gw8.fsf@nanos.tec.linutronix.de Cc: stable@vger.kernel.org --- kernel/time/timer.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel/time/timer.c') diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 9eb11c2209e5..e3d2c23c413d 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1265,8 +1265,10 @@ static inline void timer_base_unlock_expiry(struct timer_base *base) static void timer_sync_wait_running(struct timer_base *base) { if (atomic_read(&base->timer_waiters)) { + raw_spin_unlock_irq(&base->lock); spin_unlock(&base->expiry_lock); spin_lock(&base->expiry_lock); + raw_spin_lock_irq(&base->lock); } } @@ -1457,14 +1459,14 @@ static void expire_timers(struct timer_base *base, struct hlist_head *head) if (timer->flags & TIMER_IRQSAFE) { raw_spin_unlock(&base->lock); call_timer_fn(timer, fn, baseclk); - base->running_timer = NULL; raw_spin_lock(&base->lock); + base->running_timer = NULL; } else { raw_spin_unlock_irq(&base->lock); call_timer_fn(timer, fn, baseclk); + raw_spin_lock_irq(&base->lock); base->running_timer = NULL; timer_sync_wait_running(base); - raw_spin_lock_irq(&base->lock); } } } -- cgit v1.3-8-gc7d7