summaryrefslogtreecommitdiffstats
path: root/kernel/sched
diff options
context:
space:
mode:
authorRik van Riel <riel@redhat.com>2014-08-16 13:40:10 -0400
committerIngo Molnar <mingo@kernel.org>2014-09-08 08:17:01 +0200
commite78c3496790ee8a36522a838b59b388e8a709e65 (patch)
tree0473b9ea676754d50b19eb1a862ac16fdffacbeb /kernel/sched
parent90ed9cbe765ad358b3151a12b8bf889a3cbcd573 (diff)
downloadop-kernel-dev-e78c3496790ee8a36522a838b59b388e8a709e65.zip
op-kernel-dev-e78c3496790ee8a36522a838b59b388e8a709e65.tar.gz
time, signal: Protect resource use statistics with seqlock
Both times() and clock_gettime(CLOCK_PROCESS_CPUTIME_ID) have scalability issues on large systems, due to both functions being serialized with a lock. The lock protects against reporting a wrong value, due to a thread in the task group exiting, its statistics reporting up to the signal struct, and that exited task's statistics being counted twice (or not at all). Protecting that with a lock results in times() and clock_gettime() being completely serialized on large systems. This can be fixed by using a seqlock around the events that gather and propagate statistics. As an additional benefit, the protection code can be moved into thread_group_cputime(), slightly simplifying the calling functions. In the case of posix_cpu_clock_get_task() things can be simplified a lot, because the calling function already ensures that the task sticks around, and the rest is now taken care of in thread_group_cputime(). This way the statistics reporting code can run lockless. Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Alex Thorlton <athorlton@sgi.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Daeseok Youn <daeseok.youn@gmail.com> Cc: David Rientjes <rientjes@google.com> Cc: Dongsheng Yang <yangds.fnst@cn.fujitsu.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Guillaume Morin <guillaume@morinfr.org> Cc: Ionut Alexa <ionut.m.alexa@gmail.com> Cc: Kees Cook <keescook@chromium.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Li Zefan <lizefan@huawei.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Michal Schmidt <mschmidt@redhat.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Vladimir Davydov <vdavydov@parallels.com> Cc: umgwanakikbuti@gmail.com Cc: fweisbec@gmail.com Cc: srao@redhat.com Cc: lwoodman@redhat.com Cc: atheurer@redhat.com Link: http://lkml.kernel.org/r/20140816134010.26a9b572@annuminas.surriel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel/sched')
-rw-r--r--kernel/sched/cputime.c33
1 files changed, 20 insertions, 13 deletions
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 3e52836..49b7cfe 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -288,18 +288,28 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
struct signal_struct *sig = tsk->signal;
cputime_t utime, stime;
struct task_struct *t;
-
- times->utime = sig->utime;
- times->stime = sig->stime;
- times->sum_exec_runtime = sig->sum_sched_runtime;
+ unsigned int seq, nextseq;
rcu_read_lock();
- for_each_thread(tsk, t) {
- task_cputime(t, &utime, &stime);
- times->utime += utime;
- times->stime += stime;
- times->sum_exec_runtime += task_sched_runtime(t);
- }
+ /* Attempt a lockless read on the first round. */
+ nextseq = 0;
+ do {
+ seq = nextseq;
+ read_seqbegin_or_lock(&sig->stats_lock, &seq);
+ times->utime = sig->utime;
+ times->stime = sig->stime;
+ times->sum_exec_runtime = sig->sum_sched_runtime;
+
+ for_each_thread(tsk, t) {
+ task_cputime(t, &utime, &stime);
+ times->utime += utime;
+ times->stime += stime;
+ times->sum_exec_runtime += task_sched_runtime(t);
+ }
+ /* If lockless access failed, take the lock. */
+ nextseq = 1;
+ } while (need_seqretry(&sig->stats_lock, seq));
+ done_seqretry(&sig->stats_lock, seq);
rcu_read_unlock();
}
@@ -611,9 +621,6 @@ void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
cputime_adjust(&cputime, &p->prev_cputime, ut, st);
}
-/*
- * Must be called with siglock held.
- */
void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
{
struct task_cputime cputime;
OpenPOWER on IntegriCloud