From 4036ac1567834222fc763ab18e3e17df93b4eaaf Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Tue, 24 Jun 2014 07:49:40 +0200 Subject: [PATCH] sched: Fix clock_gettime(CLOCK_[PROCESS/THREAD]_CPUTIME_ID) monotonicity If a task has been dequeued, it has been accounted. Do not project cycles that may or may not ever be accounted to a dequeued task, as that may make clock_gettime() both inaccurate and non-monotonic. Protect update_rq_clock() from slight TSC skew while at it. Signed-off-by: Mike Galbraith Cc: kosaki.motohiro@jp.fujitsu.com Cc: pjt@google.com Cc: Linus Torvalds Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1403588980.29711.11.camel@marge.simpson.net Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 866d840b99ca..e50234ba0b27 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -139,6 +139,8 @@ void update_rq_clock(struct rq *rq) return; delta = sched_clock_cpu(cpu_of(rq)) - rq->clock; + if (delta < 0) + return; rq->clock += delta; update_rq_clock_task(rq, delta); } @@ -2431,7 +2433,12 @@ static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq) { u64 ns = 0; - if (task_current(rq, p)) { + /* + * Must be ->curr _and_ ->on_rq. If dequeued, we would + * project cycles that may never be accounted to this + * thread, breaking clock_gettime(). + */ + if (task_current(rq, p) && p->on_rq) { update_rq_clock(rq); ns = rq_clock_task(rq) - p->se.exec_start; if ((s64)ns < 0) @@ -2474,8 +2481,10 @@ unsigned long long task_sched_runtime(struct task_struct *p) * If we race with it leaving cpu, we'll take a lock. So we're correct. * If we race with it entering cpu, unaccounted time is 0. This is * indistinguishable from the read occurring a few cycles earlier. + * If we see ->on_cpu without ->on_rq, the task is leaving, and has + * been accounted, so we're correct here as well. */ - if (!p->on_cpu) + if (!p->on_cpu || !p->on_rq) return p->se.sum_exec_runtime; #endif