timer fix
Ingo Molnar
maintainerLinus,
Please pull the latest timers-urgent-for-linus git tree from:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers-urgent-for-linus
# HEAD: b9023b91dd020ad7e093baa5122b6968c48cc9e0 tick: broadcast-hrtimer: Fix a race in bc_set_next
Fix a broadcast-timer handling race that can result in spuriously and indefinitely delayed hrtimers and even RCU stalls if the system is otherwise quiet.
Thanks,
Ingo
------------------>
Balasubramani Vivekanandan (1):
tick: broadcast-hrtimer: Fix a race in bc_set_next
kernel/time/tick-broadcast-hrtimer.c | 62 +++++++++++++++++------------------- 1 file changed, 29 insertions(+), 33 deletions(-)
kernel/time/tick-broadcast-hrtimer.c +29 -33
@@ -42,39 +42,39 @@ static int bc_shutdown(struct clock_event_device *evt)*/ static int bc_set_next (ktime_t expires,struct clock_event_device *bc) { -int bc_moved;/* -* We try to cancel the timer first. If the callback is on -* flight on some other cpu then we let it handle it. If we -* were able to cancel the timer nothing can rearm it as we -* own broadcast_lock. +* This is called either from enter/exit idle code or from the +* broadcast handler. In all cases tick_broadcast_lock is held. * -* However we can also be called from the event handler of -* ce_broadcast_hrtimer itself when it expires. We cannot -* restart the timer because we are in the callback, but we -* can set the expiry time and let the callback return -* HRTIMER_RESTART. +* hrtimer_cancel() cannot be called here neither from the +* broadcast handler nor from the enter/exit idle code. The idle +* code can run into the problem described in bc_shutdown() and the +* broadcast handler cannot wait for itself to complete for obvious +* reasons. * -* Since we are in the idle loop at this point and because -* hrtimer_{start/cancel} functions call into tracing, -* calls to these functions must be bound within RCU_NONIDLE. +* Each caller tries to arm the hrtimer on its own CPU, but if the +* hrtimer callbback function is currently running, then +* hrtimer_start() cannot move it and the timer stays on the CPU on +* which it is assigned at the moment. +* +* As this can be called from idle code, the hrtimer_start() +* invocation has to be wrapped with RCU_NONIDLE() as +* hrtimer_start() can call into tracing. */ -RCU_NONIDLE ( - { - bc_moved =hrtimer_try_to_cancel (&bctimer) >=0 ; -if (bc_moved) { -hrtimer_start (&bctimer, expires, -HRTIMER_MODE_ABS_PINNED_HARD ); - } - } - ); - -if (bc_moved) { -/* Bind the "device" to the cpu */ - bc->bound_on =smp_processor_id (); - }else if (bc->bound_on ==smp_processor_id ()) { -hrtimer_set_expires (&bctimer, expires); - } +RCU_NONIDLE ( { +hrtimer_start (&bctimer, expires,HRTIMER_MODE_ABS_PINNED_HARD ); +/* +* The core tick broadcast mode expects bc->bound_on to be set +* correctly to prevent a CPU which has the broadcast hrtimer +* armed from going deep idle. +* +* As tick_broadcast_lock is held, nothing can change the cpu +* base which was just established in hrtimer_start() above. So +* the below access is safe even without holding the hrtimer +* base lock. +*/ + bc->bound_on = bctimer.base->cpu_base->cpu; + } );return 0 ; }
@@ -100,10 +100,6 @@ static enum hrtimer_restart bc_handler(struct hrtimer *t) { ce_broadcast_hrtimer.event_handler (&ce_broadcast_hrtimer); -if (clockevent_state_oneshot (&ce_broadcast_hrtimer)) -if (ce_broadcast_hrtimer.next_event !=KTIME_MAX ) -return HRTIMER_RESTART ; -return HRTIMER_NORESTART ; }
The pull request you sent on Thu, 3 Oct 2019 00:06:07 +0200:
The pull request you sent on Thu, 3 Oct 2019 00:06:07 +0200:
Quoted 1 line
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.gittimers-urgent-for-linus
has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/5021b9182ee805603e3b180220a929af7bd4b960
Thank you!
Signature · 2 lines
Deet-doot-dot, I am a bot. https://korg.wiki.kernel.org/userdoc/prtracker