perf/core: Fix concurrent sys_perf_event_open() vs. 'move_group' race

Di Shen reported a race between two concurrent sys_perf_event_open()
calls where both try and move the same pre-existing software group
into a hardware context.

The problem is exactly that described in commit:

  7b615c410dda ("perf: Fix event->ctx locking")

... where, while we wait for a ctx->mutex acquisition, the event->ctx
relation can have changed under us.

That very same commit failed to recognise sys_perf_event_context() as an
external access vector to the events and thereby didn't apply the
established locking rules correctly.

So while one sys_perf_event_open() call is stuck waiting on
mutex_lock_double(), the other (which owns said locks) moves the group
about. So by the time the former sys_perf_event_open() acquires the
locks, the context we've acquired is stale (and possibly dead).

Apply the established locking rules as per perf_event_ctx_lock_nested()
to the mutex_lock_double() for the 'move_group' case. This obviously means
we need to validate state after we acquire the locks.

Reported-by: Di Shen (Keen Lab)
Tested-by: John Dias <joaodias@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Min Chong <mchong@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Fixes: 7b615c410dda ("perf: Fix event->ctx locking")
Link: http://lkml.kernel.org/r/20170106131444.GZ3174@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 72ce7d63e561c050e14dfb423a5626efa50bc4cb..cbc5937265da842bc714cbccf8091484caa5f536 100644 (file)
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9529,6 +9529,37 @@ static int perf_event_set_clock(struct perf_event *event, clockid_t clk_id)
        return 0;
 }
 
+/*
+ * Variation on perf_event_ctx_lock_nested(), except we take two context
+ * mutexes.
+ */
+static struct perf_event_context *
+__perf_event_ctx_lock_double(struct perf_event *group_leader,
+                            struct perf_event_context *ctx)
+{
+       struct perf_event_context *gctx;
+
+again:
+       rcu_read_lock();
+       gctx = READ_ONCE(group_leader->ctx);
+       if (!atomic_inc_not_zero(&gctx->refcount)) {
+               rcu_read_unlock();
+               goto again;
+       }
+       rcu_read_unlock();
+
+       mutex_lock_double(&gctx->mutex, &ctx->mutex);
+
+       if (group_leader->ctx != gctx) {
+               mutex_unlock(&ctx->mutex);
+               mutex_unlock(&gctx->mutex);
+               put_ctx(gctx);
+               goto again;
+       }
+
+       return gctx;
+}
+
 /**
  * sys_perf_event_open - open a performance event, associate it to a task/cpu
  *
@@ -9772,12 +9803,31 @@ SYSCALL_DEFINE5(perf_event_open,
        }
 
        if (move_group) {
-               gctx = group_leader->ctx;
-               mutex_lock_double(&gctx->mutex, &ctx->mutex);
+               gctx = __perf_event_ctx_lock_double(group_leader, ctx);
+
                if (gctx->task == TASK_TOMBSTONE) {
                        err = -ESRCH;
                        goto err_locked;
                }
+
+               /*
+                * Check if we raced against another sys_perf_event_open() call
+                * moving the software group underneath us.
+                */
+               if (!(group_leader->group_caps & PERF_EV_CAP_SOFTWARE)) {
+                       /*
+                        * If someone moved the group out from under us, check
+                        * if this new event wound up on the same ctx, if so
+                        * its the regular !move_group case, otherwise fail.
+                        */
+                       if (gctx != ctx) {
+                               err = -EINVAL;
+                               goto err_locked;
+                       } else {
+                               perf_event_ctx_unlock(group_leader, gctx);
+                               move_group = 0;
+                       }
+               }
        } else {
                mutex_lock(&ctx->mutex);
        }
@@ -9879,7 +9929,7 @@ SYSCALL_DEFINE5(perf_event_open,
        perf_unpin_context(ctx);
 
        if (move_group)
-               mutex_unlock(&gctx->mutex);
+               perf_event_ctx_unlock(group_leader, gctx);
        mutex_unlock(&ctx->mutex);
 
        if (task) {
@@ -9905,7 +9955,7 @@ SYSCALL_DEFINE5(perf_event_open,
 
 err_locked:
        if (move_group)
-               mutex_unlock(&gctx->mutex);
+               perf_event_ctx_unlock(group_leader, gctx);
        mutex_unlock(&ctx->mutex);
 /* err_file: */
        fput(event_file);