This is a note to let you know that I've just added the patch titled
sched: Sanitize irq accounting madness
to the 3.10-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
sched-sanitize-irq-accounting-madness.patch
and it can be found in the queue-3.10 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From 2d513868e2a33e1d5315490ef4c861ee65babd65 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Date: Fri, 2 May 2014 23:26:24 +0200
Subject: sched: Sanitize irq accounting madness
From: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
commit 2d513868e2a33e1d5315490ef4c861ee65babd65 upstream.
Russell reported, that irqtime_account_idle_ticks() takes ages due to:
for (i = 0; i < ticks; i++)
irqtime_account_process_tick(current, 0, rq);
It's sad, that this code was written way _AFTER_ the NOHZ idle
functionality was available. I charge myself guitly for not paying
attention when that crap got merged with commit abb74cefa ("sched:
Export ns irqtimes through /proc/stat")
So instead of looping nr_ticks times just apply the whole thing at
once.
As a side note: The whole cputime_t vs. u64 business in that context
wants to be cleaned up as well. There is no point in having all these
back and forth conversions. Lets standardise on u64 nsec for all
kernel internal accounting and be done with it. Everything else does
not make sense at all for fine grained accounting. Frederic, can you
please take care of that?
Reported-by: Russell King <rmk+kernel@xxxxxxxxxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Reviewed-by: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Venkatesh Pallipadi <venki@xxxxxxxxxx>
Cc: Shaun Ruffell <sruffell@xxxxxxxxxx>
Link: http://lkml.kernel.org/r/alpine.DEB.2.02.1405022307000.6261@xxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
kernel/sched/cputime.c | 32 ++++++++++++++++----------------
1 file changed, 16 insertions(+), 16 deletions(-)
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -326,50 +326,50 @@ out:
* softirq as those do not count in task exec_runtime any more.
*/
static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
- struct rq *rq)
+ struct rq *rq, int ticks)
{
- cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
+ cputime_t scaled = cputime_to_scaled(cputime_one_jiffy);
+ u64 cputime = (__force u64) cputime_one_jiffy;
u64 *cpustat = kcpustat_this_cpu->cpustat;
if (steal_account_process_tick())
return;
+ cputime *= ticks;
+ scaled *= ticks;
+
if (irqtime_account_hi_update()) {
- cpustat[CPUTIME_IRQ] += (__force u64) cputime_one_jiffy;
+ cpustat[CPUTIME_IRQ] += cputime;
} else if (irqtime_account_si_update()) {
- cpustat[CPUTIME_SOFTIRQ] += (__force u64) cputime_one_jiffy;
+ cpustat[CPUTIME_SOFTIRQ] += cputime;
} else if (this_cpu_ksoftirqd() == p) {
/*
* ksoftirqd time do not get accounted in cpu_softirq_time.
* So, we have to handle it separately here.
* Also, p->stime needs to be updated for ksoftirqd.
*/
- __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
- CPUTIME_SOFTIRQ);
+ __account_system_time(p, cputime, scaled, CPUTIME_SOFTIRQ);
} else if (user_tick) {
- account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
+ account_user_time(p, cputime, scaled);
} else if (p == rq->idle) {
- account_idle_time(cputime_one_jiffy);
+ account_idle_time(cputime);
} else if (p->flags & PF_VCPU) { /* System time or guest time */
- account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled);
+ account_guest_time(p, cputime, scaled);
} else {
- __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
- CPUTIME_SYSTEM);
+ __account_system_time(p, cputime, scaled, CPUTIME_SYSTEM);
}
}
static void irqtime_account_idle_ticks(int ticks)
{
- int i;
struct rq *rq = this_rq();
- for (i = 0; i < ticks; i++)
- irqtime_account_process_tick(current, 0, rq);
+ irqtime_account_process_tick(current, 0, rq, ticks);
}
#else /* CONFIG_IRQ_TIME_ACCOUNTING */
static inline void irqtime_account_idle_ticks(int ticks) {}
static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick,
- struct rq *rq) {}
+ struct rq *rq, int nr_ticks) {}
#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
/*
@@ -464,7 +464,7 @@ void account_process_tick(struct task_st
return;
if (sched_clock_irqtime) {
- irqtime_account_process_tick(p, user_tick, rq);
+ irqtime_account_process_tick(p, user_tick, rq, 1);
return;
}
Patches currently in stable-queue which might be from tglx@xxxxxxxxxxxxx are
queue-3.10/sched-sanitize-irq-accounting-madness.patch
queue-3.10/perf-prevent-false-warning-in-perf_swevent_add.patch
queue-3.10/perf-fix-race-in-removing-an-event.patch
queue-3.10/perf-limit-perf_event_attr-sample_period-to-63-bits.patch
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html