summaryrefslogtreecommitdiff
path: root/kernel/locking
diff options
context:
space:
mode:
authorPeter Zijlstra <peterz@infradead.org>2015-06-05 17:30:23 +0200
committerIngo Molnar <mingo@kernel.org>2015-06-19 10:03:12 +0200
commitb17718d02f54b90978d0e0146368b512b11c3e84 (patch)
treec54ac78b31f90bc79599aed01b8a6269d74c753c /kernel/locking
parent82a0d2762699b95d6ce4114d00dc1865df9b0df3 (diff)
sched/stop_machine: Fix deadlock between multiple stop_two_cpus()
Jiri reported a machine stuck in multi_cpu_stop() with migrate_swap_stop() as function and with the following src,dst cpu pairs: {11, 4} {13, 11} { 4, 13} 4 11 13 cpuM: queue(4 ,13) *Ma cpuN: queue(13,11) *N Na *M Mb cpuO: queue(11, 4) *O Oa *Nb *Ob Where *X denotes the cpu running the queueing of cpu-X and X[ab] denotes the first/second queued work. You'll observe the top of the workqueue for each cpu: 4,11,13 to be work from cpus: M, O, N resp. IOW. deadlock. Do away with the queueing trickery and introduce lg_double_lock() to lock both CPUs and fully serialize the stop_two_cpus() callers instead of the partial (and buggy) serialization we have now. Reported-by: Jiri Olsa <jolsa@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20150605153023.GH19282@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel/locking')
-rw-r--r--kernel/locking/lglock.c22
1 files changed, 22 insertions, 0 deletions
diff --git a/kernel/locking/lglock.c b/kernel/locking/lglock.c
index 86ae2aebf004..951cfcd10b4a 100644
--- a/kernel/locking/lglock.c
+++ b/kernel/locking/lglock.c
@@ -60,6 +60,28 @@ void lg_local_unlock_cpu(struct lglock *lg, int cpu)
}
EXPORT_SYMBOL(lg_local_unlock_cpu);
+void lg_double_lock(struct lglock *lg, int cpu1, int cpu2)
+{
+ BUG_ON(cpu1 == cpu2);
+
+ /* lock in cpu order, just like lg_global_lock */
+ if (cpu2 < cpu1)
+ swap(cpu1, cpu2);
+
+ preempt_disable();
+ lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_);
+ arch_spin_lock(per_cpu_ptr(lg->lock, cpu1));
+ arch_spin_lock(per_cpu_ptr(lg->lock, cpu2));
+}
+
+void lg_double_unlock(struct lglock *lg, int cpu1, int cpu2)
+{
+ lock_release(&lg->lock_dep_map, 1, _RET_IP_);
+ arch_spin_unlock(per_cpu_ptr(lg->lock, cpu1));
+ arch_spin_unlock(per_cpu_ptr(lg->lock, cpu2));
+ preempt_enable();
+}
+
void lg_global_lock(struct lglock *lg)
{
int i;