From de9b8f5dcbd94bfb1d249907a635f1fb1968e19c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 13 Aug 2015 23:09:29 +0200 Subject: sched: Fix crash trying to dequeue/enqueue the idle thread Sasha reports that his virtual machine tries to schedule the idle thread since commit 6c37067e2786 ("sched: Change the sched_class::set_cpus_allowed() calling context"). Hit trace shows this happening from idle_thread_get()->init_idle(), which is the _second_ init_idle() invocation on that task_struct, the first being done through idle_init()->fork_idle(). (this code is insane...) Because we call init_idle() twice in a row, its ->sched_class == &idle_sched_class and ->on_rq = TASK_ON_RQ_QUEUED. This means do_set_cpus_allowed() think we're queued and will call dequeue_task(), which is implemented with BUG() for the idle class, seeing how dequeueing the idle task is a daft thing. Aside of the whole insanity of calling init_idle() _twice_, change the code to call set_cpus_allowed_common() instead as this is 'obviously' before the idle task gets ran etc.. Reported-by: Sasha Levin Tested-by: Sasha Levin Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: 6c37067e2786 ("sched: Change the sched_class::set_cpus_allowed() calling context") Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'kernel/sched/core.c') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 97d276ff1edb..f0d043ec0182 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4927,7 +4927,15 @@ void init_idle(struct task_struct *idle, int cpu) idle->state = TASK_RUNNING; idle->se.exec_start = sched_clock(); - do_set_cpus_allowed(idle, cpumask_of(cpu)); +#ifdef CONFIG_SMP + /* + * Its possible that init_idle() gets called multiple times on a task, + * in that case do_set_cpus_allowed() will not do the right thing. + * + * And since this is boot we can forgo the serialization. + */ + set_cpus_allowed_common(idle, cpumask_of(cpu)); +#endif /* * We're having a chicken and egg problem, even though we are * holding rq->lock, the cpu isn't yet set to this cpu so the @@ -4944,7 +4952,7 @@ void init_idle(struct task_struct *idle, int cpu) rq->curr = rq->idle = idle; idle->on_rq = TASK_ON_RQ_QUEUED; -#if defined(CONFIG_SMP) +#ifdef CONFIG_SMP idle->on_cpu = 1; #endif raw_spin_unlock(&rq->lock); @@ -4959,7 +4967,7 @@ void init_idle(struct task_struct *idle, int cpu) idle->sched_class = &idle_sched_class; ftrace_graph_init_idle_task(idle, cpu); vtime_init_idle(idle, cpu); -#if defined(CONFIG_SMP) +#ifdef CONFIG_SMP sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu); #endif } -- cgit v1.2.3 From 00cc1633816de8c95f337608a1ea64e228faf771 Mon Sep 17 00:00:00 2001 From: Dominik Dingel Date: Fri, 18 Sep 2015 11:27:45 +0200 Subject: sched: access local runqueue directly in single_task_running Commit 2ee507c47293 ("sched: Add function single_task_running to let a task check if it is the only task running on a cpu") referenced the current runqueue with the smp_processor_id. When CONFIG_DEBUG_PREEMPT is enabled, that is only allowed if preemption is disabled or the currrent task is bound to the local cpu (e.g. kernel worker). With commit f78195129963 ("kvm: add halt_poll_ns module parameter") KVM calls single_task_running. If CONFIG_DEBUG_PREEMPT is enabled that generates a lot of kernel messages. To avoid adding preemption in that cases, as it would limit the usefulness, we change single_task_running to access directly the cpu local runqueue. Cc: Tim Chen Suggested-by: Peter Zijlstra Acked-by: Peter Zijlstra (Intel) Cc: Fixes: 2ee507c472939db4b146d545352b8a7c79ef47f8 Signed-off-by: Dominik Dingel Signed-off-by: Paolo Bonzini --- kernel/sched/core.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'kernel/sched/core.c') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 3595403921bd..4064f794ab8c 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2666,13 +2666,20 @@ unsigned long nr_running(void) /* * Check if only the current task is running on the cpu. + * + * Caution: this function does not check that the caller has disabled + * preemption, thus the result might have a time-of-check-to-time-of-use + * race. The caller is responsible to use it correctly, for example: + * + * - from a non-preemptable section (of course) + * + * - from a thread that is bound to a single CPU + * + * - in a loop with very short iterations (e.g. a polling loop) */ bool single_task_running(void) { - if (cpu_rq(smp_processor_id())->nr_running == 1) - return true; - else - return false; + return raw_rq()->nr_running == 1; } EXPORT_SYMBOL(single_task_running); -- cgit v1.2.3 From 95913d97914f44db2b81271c2e2ebd4d2ac2df83 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 29 Sep 2015 14:45:09 +0200 Subject: sched/core: Fix TASK_DEAD race in finish_task_switch() So the problem this patch is trying to address is as follows: CPU0 CPU1 context_switch(A, B) ttwu(A) LOCK A->pi_lock A->on_cpu == 0 finish_task_switch(A) prev_state = A->state <-. WMB | A->on_cpu = 0; | UNLOCK rq0->lock | | context_switch(C, A) `-- A->state = TASK_DEAD prev_state == TASK_DEAD put_task_struct(A) context_switch(A, C) finish_task_switch(A) A->state == TASK_DEAD put_task_struct(A) The argument being that the WMB will allow the load of A->state on CPU0 to cross over and observe CPU1's store of A->state, which will then result in a double-drop and use-after-free. Now the comment states (and this was true once upon a long time ago) that we need to observe A->state while holding rq->lock because that will order us against the wakeup; however the wakeup will not in fact acquire (that) rq->lock; it takes A->pi_lock these days. We can obviously fix this by upgrading the WMB to an MB, but that is expensive, so we'd rather avoid that. The alternative this patch takes is: smp_store_release(&A->on_cpu, 0), which avoids the MB on some archs, but not important ones like ARM. Reported-by: Oleg Nesterov Signed-off-by: Peter Zijlstra (Intel) Acked-by: Linus Torvalds Cc: # v3.1+ Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Cc: manfred@colorfullife.com Cc: will.deacon@arm.com Fixes: e4a52bcb9a18 ("sched: Remove rq->lock from the first half of ttwu()") Link: http://lkml.kernel.org/r/20150929124509.GG3816@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 10 +++++----- kernel/sched/sched.h | 5 +++-- 2 files changed, 8 insertions(+), 7 deletions(-) (limited to 'kernel/sched/core.c') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 615953141951..10a8faa1b0d4 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2517,11 +2517,11 @@ static struct rq *finish_task_switch(struct task_struct *prev) * If a task dies, then it sets TASK_DEAD in tsk->state and calls * schedule one last time. The schedule call will never return, and * the scheduled task must drop that reference. - * The test for TASK_DEAD must occur while the runqueue locks are - * still held, otherwise prev could be scheduled on another cpu, die - * there before we look at prev->state, and then the reference would - * be dropped twice. - * Manfred Spraul + * + * We must observe prev->state before clearing prev->on_cpu (in + * finish_lock_switch), otherwise a concurrent wakeup can get prev + * running on another CPU and we could rave with its RUNNING -> DEAD + * transition, resulting in a double drop. */ prev_state = prev->state; vtime_task_switch(prev); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 68cda117574c..6d2a119c7ad9 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1078,9 +1078,10 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) * After ->on_cpu is cleared, the task can be moved to a different CPU. * We must ensure this doesn't happen until the switch is completely * finished. + * + * Pairs with the control dependency and rmb in try_to_wake_up(). */ - smp_wmb(); - prev->on_cpu = 0; + smp_store_release(&prev->on_cpu, 0); #endif #ifdef CONFIG_DEBUG_SPINLOCK /* this is a valid case when another task releases the spinlock */ -- cgit v1.2.3