82 lines
2.6 KiB
Diff
82 lines
2.6 KiB
Diff
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
|
|
Date: Mon, 17 Oct 2011 11:50:30 +0200
|
|
Subject: [PATCH] cputimer: Cure lock inversion
|
|
|
|
commit bcd5cff7216f9b2de0a148cc355eac199dc6f1cf upstream.
|
|
|
|
There's a lock inversion between the cputimer->lock and rq->lock;
|
|
notably the two callchains involved are:
|
|
|
|
update_rlimit_cpu()
|
|
sighand->siglock
|
|
set_process_cpu_timer()
|
|
cpu_timer_sample_group()
|
|
thread_group_cputimer()
|
|
cputimer->lock
|
|
thread_group_cputime()
|
|
task_sched_runtime()
|
|
->pi_lock
|
|
rq->lock
|
|
|
|
scheduler_tick()
|
|
rq->lock
|
|
task_tick_fair()
|
|
update_curr()
|
|
account_group_exec()
|
|
cputimer->lock
|
|
|
|
Where the first one is enabling a CLOCK_PROCESS_CPUTIME_ID timer, and
|
|
the second one is keeping up-to-date.
|
|
|
|
This problem was introduced by e8abccb7193 ("posix-cpu-timers: Cure
|
|
SMP accounting oddities").
|
|
|
|
Cure the problem by removing the cputimer->lock and rq->lock nesting,
|
|
this leaves concurrent enablers doing duplicate work, but the time
|
|
wasted should be on the same order otherwise wasted spinning on the
|
|
lock and the greater-than assignment filter should ensure we preserve
|
|
monotonicity.
|
|
|
|
Reported-by: Dave Jones <davej@redhat.com>
|
|
Reported-by: Simon Kirby <sim@hostway.ca>
|
|
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
|
|
Cc: stable@kernel.org
|
|
Cc: Linus Torvalds <torvalds@linux-foundation.org>
|
|
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
|
|
Link: http://lkml.kernel.org/r/1318928713.21167.4.camel@twins
|
|
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
|
|
---
|
|
kernel/posix-cpu-timers.c | 7 ++++---
|
|
1 files changed, 4 insertions(+), 3 deletions(-)
|
|
|
|
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
|
|
index c8008dd..640ded8 100644
|
|
--- a/kernel/posix-cpu-timers.c
|
|
+++ b/kernel/posix-cpu-timers.c
|
|
@@ -274,9 +274,7 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
|
|
struct task_cputime sum;
|
|
unsigned long flags;
|
|
|
|
- spin_lock_irqsave(&cputimer->lock, flags);
|
|
if (!cputimer->running) {
|
|
- cputimer->running = 1;
|
|
/*
|
|
* The POSIX timer interface allows for absolute time expiry
|
|
* values through the TIMER_ABSTIME flag, therefore we have
|
|
@@ -284,8 +282,11 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
|
|
* it.
|
|
*/
|
|
thread_group_cputime(tsk, &sum);
|
|
+ spin_lock_irqsave(&cputimer->lock, flags);
|
|
+ cputimer->running = 1;
|
|
update_gt_cputime(&cputimer->cputime, &sum);
|
|
- }
|
|
+ } else
|
|
+ spin_lock_irqsave(&cputimer->lock, flags);
|
|
*times = cputimer->cputime;
|
|
spin_unlock_irqrestore(&cputimer->lock, flags);
|
|
}
|
|
--
|
|
1.7.7
|
|
|