summaryrefslogtreecommitdiff
path: root/kernel/watchdog_hld.c
diff options
context:
space:
mode:
authorThomas Gleixner <tglx@linutronix.de>2017-09-12 22:37:04 +0300
committerIngo Molnar <mingo@kernel.org>2017-09-14 12:41:05 +0300
commit941154bd6937a710ae9193a3c733c0029e5ae7b8 (patch)
treedede6edfb0306f0ae368d892edbf32f06f24e30b /kernel/watchdog_hld.c
parent20d853fd0703b1d73c35a22024c0d4fcbcc57c8c (diff)
downloadlinux-941154bd6937a710ae9193a3c733c0029e5ae7b8.tar.xz
watchdog/hardlockup/perf: Prevent CPU hotplug deadlock
The following deadlock is possible in the watchdog hotplug code: cpus_write_lock() ... takedown_cpu() smpboot_park_threads() smpboot_park_thread() kthread_park() ->park() := watchdog_disable() watchdog_nmi_disable() perf_event_release_kernel(); put_event() _free_event() ->destroy() := hw_perf_event_destroy() x86_release_hardware() release_ds_buffers() get_online_cpus() when a per cpu watchdog perf event is destroyed which drops the last reference to the PMU hardware. The cleanup code there invokes get_online_cpus() which instantly deadlocks because the hotplug percpu rwsem is write locked. To solve this add a deferring mechanism: cpus_write_lock() kthread_park() watchdog_nmi_disable(deferred) perf_event_disable(event); move_event_to_deferred(event); .... cpus_write_unlock() cleaup_deferred_events() perf_event_release_kernel() This is still properly serialized against concurrent hotplug via the cpu_add_remove_lock, which is held by the task which initiated the hotplug event. This is also used to handle event destruction when the watchdog threads are parked via other mechanisms than CPU hotplug. Analyzed-by: Peter Zijlstra <peterz@infradead.org> Reported-by: Borislav Petkov <bp@alien8.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Don Zickus <dzickus@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sebastian Siewior <bigeasy@linutronix.de> Cc: Ulrich Obergfell <uobergfe@redhat.com> Link: http://lkml.kernel.org/r/20170912194146.884469246@linutronix.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel/watchdog_hld.c')
-rw-r--r--kernel/watchdog_hld.c34
1 files changed, 28 insertions, 6 deletions
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index 7b602714ea53..94111ccb09b5 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -21,6 +21,8 @@
static DEFINE_PER_CPU(bool, hard_watchdog_warn);
static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
+static DEFINE_PER_CPU(struct perf_event *, dead_event);
+static struct cpumask dead_events_mask;
static unsigned long hardlockup_allcpu_dumped;
static bool hardlockup_detector_disabled;
@@ -239,16 +241,18 @@ out:
return 0;
}
-void watchdog_nmi_disable(unsigned int cpu)
+/**
+ * hardlockup_detector_perf_disable - Disable the local event
+ */
+void hardlockup_detector_perf_disable(void)
{
- struct perf_event *event = per_cpu(watchdog_ev, cpu);
+ struct perf_event *event = this_cpu_read(watchdog_ev);
if (event) {
perf_event_disable(event);
- per_cpu(watchdog_ev, cpu) = NULL;
-
- /* should be in cleanup, but blocks oprofile */
- perf_event_release_kernel(event);
+ this_cpu_write(watchdog_ev, NULL);
+ this_cpu_write(dead_event, event);
+ cpumask_set_cpu(smp_processor_id(), &dead_events_mask);
/* watchdog_nmi_enable() expects this to be zero initially. */
if (atomic_dec_and_test(&watchdog_cpus))
@@ -257,6 +261,24 @@ void watchdog_nmi_disable(unsigned int cpu)
}
/**
+ * hardlockup_detector_perf_cleanup - Cleanup disabled events and destroy them
+ *
+ * Called from lockup_detector_cleanup(). Serialized by the caller.
+ */
+void hardlockup_detector_perf_cleanup(void)
+{
+ int cpu;
+
+ for_each_cpu(cpu, &dead_events_mask) {
+ struct perf_event *event = per_cpu(dead_event, cpu);
+
+ per_cpu(dead_event, cpu) = NULL;
+ perf_event_release_kernel(event);
+ }
+ cpumask_clear(&dead_events_mask);
+}
+
+/**
* hardlockup_detector_perf_stop - Globally stop watchdog events
*
* Special interface for x86 to handle the perf HT bug.