[tip:sched/core] sched/fair: Robustify CFS-bandwidth timer locking

From: tip-bot for Peter Zijlstra
Date: Mon Jan 21 2019 - 06:37:19 EST


Commit-ID: b733c2d2f2810ec8556d2d711d1b95f491bd7697
Gitweb: https://git.kernel.org/tip/b733c2d2f2810ec8556d2d711d1b95f491bd7697
Author: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
AuthorDate: Mon, 7 Jan 2019 13:52:31 +0100
Committer: Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Mon, 21 Jan 2019 11:27:55 +0100

sched/fair: Robustify CFS-bandwidth timer locking

Traditionally hrtimer callbacks were run with IRQs disabled, but with
the introduction of HRTIMER_MODE_SOFT it is possible they run from
SoftIRQ context, which does _NOT_ have IRQs disabled.

Allow for the CFS bandwidth timers (period_timer and slack_timer) to
be ran from SoftIRQ context; this entails removing the assumption that
IRQs are already disabled from the locking.

While mainline doesn't strictly need this, -RT forces all timers not
explicitly marked with MODE_HARD into MODE_SOFT and trips over this.
And marking these timers as MODE_HARD doesn't make sense as they're
not required for RT operation and can potentially be quite expensive.

Reported-by: Tom Putzeys <tom.putzeys@xxxxxxxxxxxxxxxxx>
Tested-by: Mike Galbraith <efault@xxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Link: https://lkml.kernel.org/r/20190107125231.GE14122@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
kernel/sched/fair.c | 30 ++++++++++++++++--------------
1 file changed, 16 insertions(+), 14 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 385725eb3bd6..90c7a7bf45d3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4565,7 +4565,7 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b,
struct rq *rq = rq_of(cfs_rq);
struct rq_flags rf;

- rq_lock(rq, &rf);
+ rq_lock_irqsave(rq, &rf);
if (!cfs_rq_throttled(cfs_rq))
goto next;

@@ -4582,7 +4582,7 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b,
unthrottle_cfs_rq(cfs_rq);

next:
- rq_unlock(rq, &rf);
+ rq_unlock_irqrestore(rq, &rf);

if (!remaining)
break;
@@ -4598,7 +4598,7 @@ next:
* period the timer is deactivated until scheduling resumes; cfs_b->idle is
* used to track this state.
*/
-static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
+static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, unsigned long flags)
{
u64 runtime, runtime_expires;
int throttled;
@@ -4640,11 +4640,11 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
while (throttled && cfs_b->runtime > 0 && !cfs_b->distribute_running) {
runtime = cfs_b->runtime;
cfs_b->distribute_running = 1;
- raw_spin_unlock(&cfs_b->lock);
+ raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
/* we can't nest cfs_b->lock while distributing bandwidth */
runtime = distribute_cfs_runtime(cfs_b, runtime,
runtime_expires);
- raw_spin_lock(&cfs_b->lock);
+ raw_spin_lock_irqsave(&cfs_b->lock, flags);

cfs_b->distribute_running = 0;
throttled = !list_empty(&cfs_b->throttled_cfs_rq);
@@ -4753,17 +4753,18 @@ static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq)
static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
{
u64 runtime = 0, slice = sched_cfs_bandwidth_slice();
+ unsigned long flags;
u64 expires;

/* confirm we're still not at a refresh boundary */
- raw_spin_lock(&cfs_b->lock);
+ raw_spin_lock_irqsave(&cfs_b->lock, flags);
if (cfs_b->distribute_running) {
- raw_spin_unlock(&cfs_b->lock);
+ raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
return;
}

if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) {
- raw_spin_unlock(&cfs_b->lock);
+ raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
return;
}

@@ -4774,18 +4775,18 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
if (runtime)
cfs_b->distribute_running = 1;

- raw_spin_unlock(&cfs_b->lock);
+ raw_spin_unlock_irqrestore(&cfs_b->lock, flags);

if (!runtime)
return;

runtime = distribute_cfs_runtime(cfs_b, runtime, expires);

- raw_spin_lock(&cfs_b->lock);
+ raw_spin_lock_irqsave(&cfs_b->lock, flags);
if (expires == cfs_b->runtime_expires)
lsub_positive(&cfs_b->runtime, runtime);
cfs_b->distribute_running = 0;
- raw_spin_unlock(&cfs_b->lock);
+ raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
}

/*
@@ -4863,20 +4864,21 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
{
struct cfs_bandwidth *cfs_b =
container_of(timer, struct cfs_bandwidth, period_timer);
+ unsigned long flags;
int overrun;
int idle = 0;

- raw_spin_lock(&cfs_b->lock);
+ raw_spin_lock_irqsave(&cfs_b->lock, flags);
for (;;) {
overrun = hrtimer_forward_now(timer, cfs_b->period);
if (!overrun)
break;

- idle = do_sched_cfs_period_timer(cfs_b, overrun);
+ idle = do_sched_cfs_period_timer(cfs_b, overrun, flags);
}
if (idle)
cfs_b->period_active = 0;
- raw_spin_unlock(&cfs_b->lock);
+ raw_spin_unlock_irqrestore(&cfs_b->lock, flags);

return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
}