diff options
| author | Juri Lelli <juri.lelli@redhat.com> | 2025-06-27 13:51:16 +0200 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2025-08-20 18:41:09 +0200 |
| commit | a9507e0953abfde0eb1e82aee84e775be73a21c1 (patch) | |
| tree | c334afa50725a15de46d76031cfc4783d9e24785 | |
| parent | f81538e646f62e7d267244265639d113141e9974 (diff) | |
sched/deadline: Fix accounting after global limits change
[ Upstream commit 440989c10f4e32620e9e2717ca52c3ed7ae11048 ]
A global limits change (sched_rt_handler() logic) currently leaves stale
and/or incorrect values in variables related to accounting (e.g.
extra_bw).
Properly clean up per runqueue variables before implementing the change
and rebuild scheduling domains (so that accounting is also properly
restored) after such a change is complete.
Reported-by: Marcel Ziswiler <marcel.ziswiler@codethink.co.uk>
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Marcel Ziswiler <marcel.ziswiler@codethink.co.uk> # nuc & rock5b
Link: https://lore.kernel.org/r/20250627115118.438797-4-juri.lelli@redhat.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
| -rw-r--r-- | kernel/sched/deadline.c | 4 | ||||
| -rw-r--r-- | kernel/sched/rt.c | 6 |
2 files changed, 9 insertions, 1 deletions
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 65f3b2cc891d..d86b211f2c14 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -3249,6 +3249,9 @@ void sched_dl_do_global(void) if (global_rt_runtime() != RUNTIME_INF) new_bw = to_ratio(global_rt_period(), global_rt_runtime()); + for_each_possible_cpu(cpu) + init_dl_rq_bw_ratio(&cpu_rq(cpu)->dl); + for_each_possible_cpu(cpu) { rcu_read_lock_sched(); @@ -3264,7 +3267,6 @@ void sched_dl_do_global(void) raw_spin_unlock_irqrestore(&dl_b->lock, flags); rcu_read_unlock_sched(); - init_dl_rq_bw_ratio(&cpu_rq(cpu)->dl); } } diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index e40422c37033..507707653312 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -2951,6 +2951,12 @@ undo: sched_domains_mutex_unlock(); mutex_unlock(&mutex); + /* + * After changing maximum available bandwidth for DEADLINE, we need to + * recompute per root domain and per cpus variables accordingly. + */ + rebuild_sched_domains(); + return ret; } |