perf: Stop all counters on reboot

Use the reboot notifier to detach all running counters on reboot, this
solves a problem with kexec where the new kernel doesn't expect
running counters (rightly so).

It will however decrease the coverage of the NMI watchdog. Making a
kexec specific reboot notifier callback would be best, however that
would require touching all notifier callback handlers as they are not
properly structured to deal with new state.

As a compromise, place the perf reboot notifier at the very last
position in the list.

Reported-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Jason Wessel <jason.wessel@windriver.com>
Cc: Don Zickus <dzickus@redhat.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 23 insertions, 1 deletions

diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 77ad22c00b9d..f9d2645b5546 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -21,6 +21,7 @@
 #include <linux/dcache.h>
 #include <linux/percpu.h>
 #include <linux/ptrace.h>
+#include <linux/reboot.h>
 #include <linux/vmstat.h>
 #include <linux/vmalloc.h>
 #include <linux/hardirq.h>
@@ -6429,7 +6430,7 @@ static void __cpuinit perf_event_init_cpu(int cpu)
         mutex_unlock(&swhash->hlist_mutex);
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
+#if defined CONFIG_HOTPLUG_CPU || defined CONFIG_KEXEC
 static void perf_pmu_rotate_stop(struct pmu *pmu)
 {
         struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
@@ -6483,6 +6484,26 @@ static void perf_event_exit_cpu(int cpu)
 static inline void perf_event_exit_cpu(int cpu) { }
 #endif
 
+static int
+perf_reboot(struct notifier_block *notifier, unsigned long val, void *v)
+{
+        int cpu;
+
+        for_each_online_cpu(cpu)
+                perf_event_exit_cpu(cpu);
+
+        return NOTIFY_OK;
+}
+
+/*
+ * Run the perf reboot notifier at the very last possible moment so that
+ * the generic watchdog code runs as long as possible.
+ */
+static struct notifier_block perf_reboot_notifier = {
+        .notifier_call = perf_reboot,
+        .priority = INT_MIN,
+};
+
 static int __cpuinit
 perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
 {
@@ -6518,6 +6539,7 @@ void __init perf_event_init(void)
         perf_pmu_register(&perf_task_clock);
         perf_tp_register();
         perf_cpu_notifier(perf_cpu_notify);
+        register_reboot_notifier(&perf_reboot_notifier);
 
         ret = init_hw_breakpoint();
         WARN(ret, "hw_breakpoint initialization failed with: %d", ret);