From 60e69eed85bb7b5198ef70643b5895c26ad76ef7 Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Mon, 7 Apr 2014 10:55:15 +0200 Subject: sched/numa: Fix task_numa_free() lockdep splat Sasha reported that lockdep claims that the following commit: made numa_group.lock interrupt unsafe: 156654f491dd ("sched/numa: Move task_numa_free() to __put_task_struct()") While I don't see how that could be, given the commit in question moved task_numa_free() from one irq enabled region to another, the below does make both gripes and lockups upon gripe with numa=fake=4 go away. Reported-by: Sasha Levin Fixes: 156654f491dd ("sched/numa: Move task_numa_free() to __put_task_struct()") Signed-off-by: Mike Galbraith Signed-off-by: Peter Zijlstra Cc: torvalds@linux-foundation.org Cc: mgorman@suse.com Cc: akpm@linux-foundation.org Cc: Dave Jones Link: http://lkml.kernel.org/r/1396860915.5170.5.camel@marge.simpson.net Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 13 +++++++------ kernel/sched/sched.h | 9 +++++++++ 2 files changed, 16 insertions(+), 6 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 7e9bd0b1fa9e..4f14a656a720 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1497,7 +1497,7 @@ static void task_numa_placement(struct task_struct *p) /* If the task is part of a group prevent parallel updates to group stats */ if (p->numa_group) { group_lock = &p->numa_group->lock; - spin_lock(group_lock); + spin_lock_irq(group_lock); } /* Find the node with the highest number of faults */ @@ -1572,7 +1572,7 @@ static void task_numa_placement(struct task_struct *p) } } - spin_unlock(group_lock); + spin_unlock_irq(group_lock); } /* Preferred node as the node with the most faults */ @@ -1677,7 +1677,8 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, if (!join) return; - double_lock(&my_grp->lock, &grp->lock); + BUG_ON(irqs_disabled()); + double_lock_irq(&my_grp->lock, &grp->lock); for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) { my_grp->faults[i] -= p->numa_faults_memory[i]; @@ -1691,7 +1692,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, grp->nr_tasks++; spin_unlock(&my_grp->lock); - spin_unlock(&grp->lock); + spin_unlock_irq(&grp->lock); rcu_assign_pointer(p->numa_group, grp); @@ -1710,14 +1711,14 @@ void task_numa_free(struct task_struct *p) void *numa_faults = p->numa_faults_memory; if (grp) { - spin_lock(&grp->lock); + spin_lock_irq(&grp->lock); for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) grp->faults[i] -= p->numa_faults_memory[i]; grp->total_faults -= p->total_numa_faults; list_del(&p->numa_entry); grp->nr_tasks--; - spin_unlock(&grp->lock); + spin_unlock_irq(&grp->lock); rcu_assign_pointer(p->numa_group, NULL); put_numa_group(grp); } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index c9007f28d3a2..456e492a3dca 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1385,6 +1385,15 @@ static inline void double_lock(spinlock_t *l1, spinlock_t *l2) spin_lock_nested(l2, SINGLE_DEPTH_NESTING); } +static inline void double_lock_irq(spinlock_t *l1, spinlock_t *l2) +{ + if (l1 > l2) + swap(l1, l2); + + spin_lock_irq(l1); + spin_lock_nested(l2, SINGLE_DEPTH_NESTING); +} + static inline void double_raw_lock(raw_spinlock_t *l1, raw_spinlock_t *l2) { if (l1 > l2) -- cgit v1.2.3 From a1d9a3231eac4117cadaf4b6bba5b2902c15a33e Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Thu, 10 Apr 2014 17:38:36 +0400 Subject: sched: Check for stop task appearance when balancing happens We need to do it like we do for the other higher priority classes.. Signed-off-by: Kirill Tkhai Cc: Michael wang Cc: Sasha Levin Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/336561397137116@web27h.yandex.ru Signed-off-by: Ingo Molnar --- kernel/sched/deadline.c | 11 ++++++++++- kernel/sched/fair.c | 3 ++- kernel/sched/rt.c | 7 ++++--- 3 files changed, 16 insertions(+), 5 deletions(-) diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 27ef40925525..b08095786cb8 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1021,8 +1021,17 @@ struct task_struct *pick_next_task_dl(struct rq *rq, struct task_struct *prev) dl_rq = &rq->dl; - if (need_pull_dl_task(rq, prev)) + if (need_pull_dl_task(rq, prev)) { pull_dl_task(rq); + /* + * pull_rt_task() can drop (and re-acquire) rq->lock; this + * means a stop task can slip in, in which case we need to + * re-start task selection. + */ + if (rq->stop && rq->stop->on_rq) + return RETRY_TASK; + } + /* * When prev is DL, we may throttle it in put_prev_task(). * So, we update time before we check for dl_nr_running. diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 4f14a656a720..7570dd969c28 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6728,7 +6728,8 @@ static int idle_balance(struct rq *this_rq) out: /* Is there a task of a high priority class? */ if (this_rq->nr_running != this_rq->cfs.h_nr_running && - (this_rq->dl.dl_nr_running || + ((this_rq->stop && this_rq->stop->on_rq) || + this_rq->dl.dl_nr_running || (this_rq->rt.rt_nr_running && !rt_rq_throttled(&this_rq->rt)))) pulled_task = -1; diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index d8cdf1618551..bd2267ad404f 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1362,10 +1362,11 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev) pull_rt_task(rq); /* * pull_rt_task() can drop (and re-acquire) rq->lock; this - * means a dl task can slip in, in which case we need to - * re-start task selection. + * means a dl or stop task can slip in, in which case we need + * to re-start task selection. */ - if (unlikely(rq->dl.dl_nr_running)) + if (unlikely((rq->stop && rq->stop->on_rq) || + rq->dl.dl_nr_running)) return RETRY_TASK; } -- cgit v1.2.3