summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorGaurav Kohli <gkohli@codeaurora.org>2018-08-02 14:21:03 +0530
committerThomas Gleixner <tglx@linutronix.de>2018-08-02 12:52:38 +0200
commit363e934d8811d799c88faffc5bfca782fd728334 (patch)
tree21cd33b9bf7ab353bd968ee8b0ebe7ccb0b2048a
parentb2ab472dc159b7f89e2bc2d305fbc52fc2241dd6 (diff)
downloadlinux-363e934d8811d799c88faffc5bfca782fd728334.tar.gz
linux-363e934d8811d799c88faffc5bfca782fd728334.tar.bz2
linux-363e934d8811d799c88faffc5bfca782fd728334.zip
timers: Clear timer_base::must_forward_clk with timer_base::lock held
timer_base::must_forward_clock is indicating that the base clock might be stale due to a long idle sleep. The forwarding of the base clock takes place in the timer softirq or when a timer is enqueued to a base which is idle. If the enqueue of timer to an idle base happens from a remote CPU, then the following race can happen: CPU0 CPU1 run_timer_softirq mod_timer base = lock_timer_base(timer); base->must_forward_clk = false if (base->must_forward_clk) forward(base); -> skipped enqueue_timer(base, timer, idx); -> idx is calculated high due to stale base unlock_timer_base(timer); base = lock_timer_base(timer); forward(base); The root cause is that timer_base::must_forward_clk is cleared outside the timer_base::lock held region, so the remote queuing CPU observes it as cleared, but the base clock is still stale. This can cause large granularity values for timers, i.e. the accuracy of the expiry time suffers. Prevent this by clearing the flag with timer_base::lock held, so that the forwarding takes place before the cleared flag is observable by a remote CPU. Signed-off-by: Gaurav Kohli <gkohli@codeaurora.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: john.stultz@linaro.org Cc: sboyd@kernel.org Cc: linux-arm-msm@vger.kernel.org Link: https://lkml.kernel.org/r/1533199863-22748-1-git-send-email-gkohli@codeaurora.org
-rw-r--r--kernel/time/timer.c29
1 files changed, 16 insertions, 13 deletions
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index baa528a24a73..fa49cd753dea 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1657,6 +1657,22 @@ static inline void __run_timers(struct timer_base *base)
raw_spin_lock_irq(&base->lock);
+ /*
+ * timer_base::must_forward_clk must be cleared before running
+ * timers so that any timer functions that call mod_timer() will
+ * not try to forward the base. Idle tracking / clock forwarding
+ * logic is only used with BASE_STD timers.
+ *
+ * The must_forward_clk flag is cleared unconditionally also for
+ * the deferrable base. The deferrable base is not affected by idle
+ * tracking and never forwarded, so clearing the flag is a NOOP.
+ *
+ * The fact that the deferrable base is never forwarded can cause
+ * large variations in granularity for deferrable timers, but they
+ * can be deferred for long periods due to idle anyway.
+ */
+ base->must_forward_clk = false;
+
while (time_after_eq(jiffies, base->clk)) {
levels = collect_expired_timers(base, heads);
@@ -1676,19 +1692,6 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h)
{
struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
- /*
- * must_forward_clk must be cleared before running timers so that any
- * timer functions that call mod_timer will not try to forward the
- * base. idle trcking / clock forwarding logic is only used with
- * BASE_STD timers.
- *
- * The deferrable base does not do idle tracking at all, so we do
- * not forward it. This can result in very large variations in
- * granularity for deferrable timers, but they can be deferred for
- * long periods due to idle.
- */
- base->must_forward_clk = false;
-
__run_timers(base);
if (IS_ENABLED(CONFIG_NO_HZ_COMMON))
__run_timers(this_cpu_ptr(&timer_bases[BASE_DEF]));