perf/core: Fix sideband list-iteration vs. event ordering NULL pointer deference crash

Vegard Nossum reported that perf fuzzing generates a NULL
pointer dereference crash:

> Digging a bit deeper into this, it seems the event itself is getting
> created by perf_event_open() and it gets added to the pmu_event_list
> through:
>
> perf_event_open()
>  - perf_event_alloc()
>     - account_event()
>        - account_pmu_sb_event()
>           - attach_sb_event()
>
> so at this point the event is being attached but its ->ctx is still
> NULL. It seems like ->ctx is set just a bit later in
> perf_event_open(), though.
>
> But before that, __schedule() comes along and creates a stack trace
> similar to the one above:
>
> __schedule()
>  - __perf_event_task_sched_out()
>    - perf_iterate_sb()
>      - perf_iterate_sb_cpu()
>         - event_filter_match()
>           - perf_cgroup_match()
>             - __get_cpu_context()
>               - (dereference ctx which is NULL)
>
> So I guess the question is... should the event be attached (= put on
> the list) before ->ctx gets set? Or should the cgroup code check for a
> NULL ->ctx?

The latter seems like the simplest solution. Moving the list-add later
creates a bit of a mess.

Reported-by: Vegard Nossum <vegard.nossum@gmail.com>
Tested-by: Vegard Nossum <vegard.nossum@gmail.com>
Tested-by: Vince Weaver <vincent.weaver@maine.edu>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: David Carrillo-Cisneros <davidcc@google.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: f2fb6bef9251 ("perf/core: Optimize side-band event delivery")
Link: http://lkml.kernel.org/r/20160804123724.GN6862@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 18 insertions, 5 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index a19550d80ab1..87d02b8cb87e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1716,8 +1716,8 @@ static inline int pmu_filter_match(struct perf_event *event)
 static inline int
 event_filter_match(struct perf_event *event)
 {
-        return (event->cpu == -1 || event->cpu == smp_processor_id())
-            && perf_cgroup_match(event) && pmu_filter_match(event);
+        return (event->cpu == -1 || event->cpu == smp_processor_id()) &&
+               perf_cgroup_match(event) && pmu_filter_match(event);
 }
 
 static void
@@ -1737,8 +1737,8 @@ event_sched_out(struct perf_event *event,
          * maintained, otherwise bogus information is return
          * via read() for time_enabled, time_running:
          */
-        if (event->state == PERF_EVENT_STATE_INACTIVE
-            && !event_filter_match(event)) {
+        if (event->state == PERF_EVENT_STATE_INACTIVE &&
+            !event_filter_match(event)) {
                 delta = tstamp - event->tstamp_stopped;
                 event->tstamp_running += delta;
                 event->tstamp_stopped = tstamp;
@@ -2236,10 +2236,15 @@ perf_install_in_context(struct perf_event_context *ctx,
 
         lockdep_assert_held(&ctx->mutex);
 
-        event->ctx = ctx;
         if (event->cpu != -1)
                 event->cpu = cpu;
 
+        /*
+         * Ensures that if we can observe event->ctx, both the event and ctx
+         * will be 'complete'. See perf_iterate_sb_cpu().
+         */
+        smp_store_release(&event->ctx, ctx);
+
         if (!task) {
                 cpu_function_call(cpu, __perf_install_in_context, event);
                 return;
@@ -5969,6 +5974,14 @@ static void perf_iterate_sb_cpu(perf_iterate_f output, void *data)
         struct perf_event *event;
 
         list_for_each_entry_rcu(event, &pel->list, sb_list) {
+                /*
+                 * Skip events that are not fully formed yet; ensure that
+                 * if we observe event->ctx, both event and ctx will be
+                 * complete enough. See perf_install_in_context().
+                 */
+                if (!smp_load_acquire(&event->ctx))
+                        continue;
+
                 if (event->state < PERF_EVENT_STATE_INACTIVE)
                         continue;
                 if (!event_filter_match(event))