diff options
| author | Juri Lelli <juri.lelli@redhat.com> | 2023-05-08 10:58:50 +0300 |
|---|---|---|
| committer | Tejun Heo <tj@kernel.org> | 2023-05-09 02:22:33 +0300 |
| commit | 111cd11bbc54850f24191c52ff217da88a5e639b (patch) | |
| tree | 22ff0fd667dbdfc39b55acf04c921ded13e84d8c /kernel/sched | |
| parent | ad3a557daf6915296a43ef97a3e9c48e076c9dd8 (diff) | |
| download | linux-111cd11bbc54850f24191c52ff217da88a5e639b.tar.xz | |
sched/cpuset: Bring back cpuset_mutex
Turns out percpu_cpuset_rwsem - commit 1243dc518c9d ("cgroup/cpuset:
Convert cpuset_mutex to percpu_rwsem") - wasn't such a brilliant idea,
as it has been reported to cause slowdowns in workloads that need to
change cpuset configuration frequently and it is also not implementing
priority inheritance (which causes troubles with realtime workloads).
Convert percpu_cpuset_rwsem back to regular cpuset_mutex. Also grab it
only for SCHED_DEADLINE tasks (other policies don't care about stable
cpusets anyway).
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Reviewed-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Diffstat (limited to 'kernel/sched')
| -rw-r--r-- | kernel/sched/core.c | 22 |
1 files changed, 15 insertions, 7 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 944c3ae39861..d826bec1c522 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7590,6 +7590,7 @@ static int __sched_setscheduler(struct task_struct *p, int reset_on_fork; int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK; struct rq *rq; + bool cpuset_locked = false; /* The pi code expects interrupts enabled */ BUG_ON(pi && in_interrupt()); @@ -7639,8 +7640,14 @@ recheck: return retval; } - if (pi) - cpuset_read_lock(); + /* + * SCHED_DEADLINE bandwidth accounting relies on stable cpusets + * information. + */ + if (dl_policy(policy) || dl_policy(p->policy)) { + cpuset_locked = true; + cpuset_lock(); + } /* * Make sure no PI-waiters arrive (or leave) while we are @@ -7716,8 +7723,8 @@ change: if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { policy = oldpolicy = -1; task_rq_unlock(rq, p, &rf); - if (pi) - cpuset_read_unlock(); + if (cpuset_locked) + cpuset_unlock(); goto recheck; } @@ -7784,7 +7791,8 @@ change: task_rq_unlock(rq, p, &rf); if (pi) { - cpuset_read_unlock(); + if (cpuset_locked) + cpuset_unlock(); rt_mutex_adjust_pi(p); } @@ -7796,8 +7804,8 @@ change: unlock: task_rq_unlock(rq, p, &rf); - if (pi) - cpuset_read_unlock(); + if (cpuset_locked) + cpuset_unlock(); return retval; } |