diff options
Diffstat (limited to 'cputimer-cure-lock-inversion.patch')
| -rw-r--r-- | cputimer-cure-lock-inversion.patch | 73 |
1 files changed, 73 insertions, 0 deletions
diff --git a/cputimer-cure-lock-inversion.patch b/cputimer-cure-lock-inversion.patch new file mode 100644 index 000000000..cebb775bf --- /dev/null +++ b/cputimer-cure-lock-inversion.patch @@ -0,0 +1,73 @@ +Subject: cputimer: Cure lock inversion +From: Peter Zijlstra <a.p.zijlstra@chello.nl> +Date: Mon Oct 17 11:50:30 CEST 2011 + +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> +Cc: stable@kernel.org +Cc: Thomas Gleixner <tglx@linutronix.de> +Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> +--- + kernel/posix-cpu-timers.c | 7 ++++--- + 1 file changed, 4 insertions(+), 3 deletions(-) +Index: linux-2.6/kernel/posix-cpu-timers.c +=================================================================== +--- linux-2.6.orig/kernel/posix-cpu-timers.c ++++ linux-2.6/kernel/posix-cpu-timers.c +@@ -274,9 +274,7 @@ void thread_group_cputimer(struct task_s + 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_s + * 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); + } + |