summaryrefslogtreecommitdiffstats
path: root/kernel/sched
diff options
context:
space:
mode:
authorWanpeng Li <wanpeng.li@hotmail.com>2015-08-28 14:55:56 +0800
committerIngo Molnar <mingo@kernel.org>2015-09-11 07:57:50 +0200
commit5473e0cc37c03c576adbda7591a6cc8e37c1bb7f (patch)
tree3e4996bd02962f27c96dca440f036a571240ca67 /kernel/sched
parent7c8bb6cb95061b3143759459ed6c6b0c73bcfecb (diff)
downloadlinux-5473e0cc37c03c576adbda7591a6cc8e37c1bb7f.tar.bz2
sched: 'Annotate' migrate_tasks()
Kernel testing triggered this warning: | WARNING: CPU: 0 PID: 13 at kernel/sched/core.c:1156 do_set_cpus_allowed+0x7e/0x80() | Modules linked in: | CPU: 0 PID: 13 Comm: migration/0 Not tainted 4.2.0-rc1-00049-g25834c7 #2 | Call Trace: | dump_stack+0x4b/0x75 | warn_slowpath_common+0x8b/0xc0 | warn_slowpath_null+0x22/0x30 | do_set_cpus_allowed+0x7e/0x80 | cpuset_cpus_allowed_fallback+0x7c/0x170 | select_fallback_rq+0x221/0x280 | migration_call+0xe3/0x250 | notifier_call_chain+0x53/0x70 | __raw_notifier_call_chain+0x1e/0x30 | cpu_notify+0x28/0x50 | take_cpu_down+0x22/0x40 | multi_cpu_stop+0xd5/0x140 | cpu_stopper_thread+0xbc/0x170 | smpboot_thread_fn+0x174/0x2f0 | kthread+0xc4/0xe0 | ret_from_kernel_thread+0x21/0x30 As Peterz pointed out: | So the normal rules for changing task_struct::cpus_allowed are holding | both pi_lock and rq->lock, such that holding either stabilizes the mask. | | This is so that wakeup can happen without rq->lock and load-balance | without pi_lock. | | From this we already get the relaxation that we can omit acquiring | rq->lock if the task is not on the rq, because in that case | load-balancing will not apply to it. | | ** these are the rules currently tested in do_set_cpus_allowed() ** | | Now, since __set_cpus_allowed_ptr() uses task_rq_lock() which | unconditionally acquires both locks, we could get away with holding just | rq->lock when on_rq for modification because that'd still exclude | __set_cpus_allowed_ptr(), it would also work against | __kthread_bind_mask() because that assumes !on_rq. | | That said, this is all somewhat fragile. | | Now, I don't think dropping rq->lock is quite as disastrous as it | usually is because !cpu_active at this point, which means load-balance | will not interfere, but that too is somewhat fragile. | | So we end up with a choice of two fragile.. This patch fixes it by following the rules for changing task_struct::cpus_allowed with both pi_lock and rq->lock held. Reported-by: kernel test robot <ying.huang@intel.com> Reported-by: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com> [ Modified changelog and patch. ] Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/BLU436-SMTP1660820490DE202E3934ED3806E0@phx.gbl Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel/sched')
-rw-r--r--kernel/sched/core.c29
1 files changed, 26 insertions, 3 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0902e4d72671..9b786704d34b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5183,24 +5183,47 @@ static void migrate_tasks(struct rq *dead_rq)
break;
/*
- * Ensure rq->lock covers the entire task selection
- * until the migration.
+ * pick_next_task assumes pinned rq->lock.
*/
lockdep_pin_lock(&rq->lock);
next = pick_next_task(rq, &fake_task);
BUG_ON(!next);
next->sched_class->put_prev_task(rq, next);
+ /*
+ * Rules for changing task_struct::cpus_allowed are holding
+ * both pi_lock and rq->lock, such that holding either
+ * stabilizes the mask.
+ *
+ * Drop rq->lock is not quite as disastrous as it usually is
+ * because !cpu_active at this point, which means load-balance
+ * will not interfere. Also, stop-machine.
+ */
+ lockdep_unpin_lock(&rq->lock);
+ raw_spin_unlock(&rq->lock);
+ raw_spin_lock(&next->pi_lock);
+ raw_spin_lock(&rq->lock);
+
+ /*
+ * Since we're inside stop-machine, _nothing_ should have
+ * changed the task, WARN if weird stuff happened, because in
+ * that case the above rq->lock drop is a fail too.
+ */
+ if (WARN_ON(task_rq(next) != rq || !task_on_rq_queued(next))) {
+ raw_spin_unlock(&next->pi_lock);
+ continue;
+ }
+
/* Find suitable destination for @next, with force if needed. */
dest_cpu = select_fallback_rq(dead_rq->cpu, next);
- lockdep_unpin_lock(&rq->lock);
rq = __migrate_task(rq, next, dest_cpu);
if (rq != dead_rq) {
raw_spin_unlock(&rq->lock);
rq = dead_rq;
raw_spin_lock(&rq->lock);
}
+ raw_spin_unlock(&next->pi_lock);
}
rq->stop = stop;