admin/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2025-12-07 20:06:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

sched: Fix migrate_disable_switch() locking

Browse Source 
For some reason migrate_disable_switch() was more complicated than it
needs to be, resulting in mind bending locking of dubious quality.

Recognise that migrate_disable_switch() must be called before a
context switch, but any place before that switch is equally good.
Since the current place results in troubled locking, simply move the
thing before taking rq->lock.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Juri Lelli <juri.lelli@redhat.com>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Vincent Guittot <vincent.guittot@linaro.org>
This commit is contained in:
Peter Zijlstra
2025-09-10 09:46:44 +02:00
parent 6455ad5346
commit 942b8db965
1 changed files with 6 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
kernel/sched/core.c
View File

@@ -2346,10 +2346,10 @@ static void migrate_disable_switch(struct rq *rq, struct task_struct *p)
if (p->cpus_ptr != &p->cpus_mask) if (p->cpus_ptr != &p->cpus_mask)
return; return;
/* scoped_guard (task_rq_lock, p) {
* Violates locking rules! See comment in __do_set_cpus_allowed(). update_rq_clock(scope.rq);
*/ __do_set_cpus_allowed(p, &ac);
__do_set_cpus_allowed(p, &ac); }
} }
void ___migrate_enable(void) void ___migrate_enable(void)
@@ -2667,22 +2667,7 @@ __do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx)
struct rq *rq = task_rq(p); struct rq *rq = task_rq(p);
bool queued, running; bool queued, running;
/* lockdep_assert_held(&p->pi_lock);
* This here violates the locking rules for affinity, since we're only
* supposed to change these variables while holding both rq->lock and
* p->pi_lock.
*
* HOWEVER, it magically works, because ttwu() is the only code that
* accesses these variables under p->pi_lock and only does so after
* smp_cond_load_acquire(&p->on_cpu, !VAL), and we're in __schedule()
* before finish_task().
*
* XXX do further audits, this smells like something putrid.
*/
if (ctx->flags & SCA_MIGRATE_DISABLE)
WARN_ON_ONCE(!p->on_cpu);
else
lockdep_assert_held(&p->pi_lock);
queued = task_on_rq_queued(p); queued = task_on_rq_queued(p);
running = task_current_donor(rq, p); running = task_current_donor(rq, p);
@@ -6781,6 +6766,7 @@ static void __sched notrace __schedule(int sched_mode)
local_irq_disable(); local_irq_disable();
rcu_note_context_switch(preempt); rcu_note_context_switch(preempt);
migrate_disable_switch(rq, prev);
/* /*
* Make sure that signal_pending_state()->signal_pending() below * Make sure that signal_pending_state()->signal_pending() below
@@ -6887,7 +6873,6 @@ keep_resched:
*/ */
++*switch_count; ++*switch_count;
migrate_disable_switch(rq, prev);
psi_account_irqtime(rq, prev, next); psi_account_irqtime(rq, prev, next);
psi_sched_switch(prev, next, !task_on_rq_queued(prev) || psi_sched_switch(prev, next, !task_on_rq_queued(prev) ||
prev->se.sched_delayed); prev->se.sched_delayed);