diff options
| author |   Peter Zijlstra <peterz@infradead.org> | 2020-07-22 10:22:02 +0200 |
|---|---|---|
| committer | Peter Zijlstra <peterz@infradead.org> | 2020-07-22 10:22:02 +0200 |
| commit | 015dc08918785201199ed3450c22bb8939f09dfe (patch) | |
| tree | 7ba52e0b1e518fa750aaac0c1da8dd70c3eca1eb /kernel/sched | |
| parent | sched: Add a tracepoint to track rq->nr_running (diff) | |
| parent | sched: Fix race against ptrace_freeze_trace() (diff) | |
| download | wireguard-linux-015dc08918785201199ed3450c22bb8939f09dfe.tar.xz wireguard-linux-015dc08918785201199ed3450c22bb8939f09dfe.zip | |
Merge branch 'sched/urgent'
Diffstat (limited to 'kernel/sched')
| -rw-r--r-- | kernel/sched/core.c | 24 | ||||
| -rw-r--r-- | kernel/sched/fair.c | 15 |
2 files changed, 27 insertions, 12 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c index ff0519551188..08d02ce26b71 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4193,9 +4193,6 @@ static void __sched notrace __schedule(bool preempt) local_irq_disable(); rcu_note_context_switch(preempt); - /* See deactivate_task() below. */ - prev_state = prev->state; - /* * Make sure that signal_pending_state()->signal_pending() below * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE) @@ -4219,11 +4216,16 @@ static void __sched notrace __schedule(bool preempt) update_rq_clock(rq); switch_count = &prev->nivcsw; + /* - * We must re-load prev->state in case ttwu_remote() changed it - * before we acquired rq->lock. + * We must load prev->state once (task_struct::state is volatile), such + * that: + * + * - we form a control dependency vs deactivate_task() below. + * - ptrace_{,un}freeze_traced() can change ->state underneath us. */ - if (!preempt && prev_state && prev_state == prev->state) { + prev_state = prev->state; + if (!preempt && prev_state) { if (signal_pending_state(prev_state, prev)) { prev->state = TASK_RUNNING; } else { @@ -4237,10 +4239,12 @@ static void __sched notrace __schedule(bool preempt) /* * __schedule() ttwu() - * prev_state = prev->state; if (READ_ONCE(p->on_rq) && ...) - * LOCK rq->lock goto out; - * smp_mb__after_spinlock(); smp_acquire__after_ctrl_dep(); - * p->on_rq = 0; p->state = TASK_WAKING; + * prev_state = prev->state; if (p->on_rq && ...) + * if (prev_state) goto out; + * p->on_rq = 0; smp_acquire__after_ctrl_dep(); + * p->state = TASK_WAKING + * + * Where __schedule() and ttwu() have matching control dependencies. * * After this, schedule() must not care about p->state any more. */ diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 3213cb247aff..98a53a2fe354 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4047,7 +4047,11 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq) return; } - rq->misfit_task_load = task_h_load(p); + /* + * Make sure that misfit_task_load will not be null even if + * task_h_load() returns 0. + */ + rq->misfit_task_load = max_t(unsigned long, task_h_load(p), 1); } #else /* CONFIG_SMP */ @@ -7646,7 +7650,14 @@ static int detach_tasks(struct lb_env *env) switch (env->migration_type) { case migrate_load: - load = task_h_load(p); + /* + * Depending of the number of CPUs and tasks and the + * cgroup hierarchy, task_h_load() can return a null + * value. Make sure that env->imbalance decreases + * otherwise detach_tasks() will stop only after + * detaching up to loop_max tasks. + */ + load = max_t(unsigned long, task_h_load(p), 1); if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed) |