perf/core: Fix exclusive events' grouping

commit 8a58ddae23796c733c5dfbd717538d89d036c5bd upstream.

So far, we tried to disallow grouping exclusive events for the fear of
complications they would cause with moving between contexts. Specifically,
moving a software group to a hardware context would violate the exclusivity
rules if both groups contain matching exclusive events.

This attempt was, however, unsuccessful: the check that we have in the
perf_event_open() syscall is both wrong (looks at wrong PMU) and
insufficient (group leader may still be exclusive), as can be illustrated
by running:

  $ perf record -e '{intel_pt//,cycles}' uname
  $ perf record -e '{cycles,intel_pt//}' uname

ultimately successfully.

Furthermore, we are completely free to trigger the exclusivity violation
by:

   perf -e '{cycles,intel_pt//}' -e '{intel_pt//,instructions}'

even though the helpful perf record will not allow that, the ABI will.

The warning later in the perf_event_open() path will also not trigger, because
it's also wrong.

Fix all this by validating the original group before moving, getting rid
of broken safeguards and placing a useful one to perf_install_in_context().

Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: <stable@vger.kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.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>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: mathieu.poirier@linaro.org
Cc: will.deacon@arm.com
Fixes: bed5b25ad9c8a ("perf: Add a pmu capability for "exclusive" events")
Link: https://lkml.kernel.org/r/20190701110755.24646-1-alexander.shishkin@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 22 insertions, 12 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 3b61ff40bfe2..6fb9c60eba00 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2541,6 +2541,9 @@ unlock:
 	return ret;
 }
 
+static bool exclusive_event_installable(struct perf_event *event,
+					struct perf_event_context *ctx);
+
 /*
  * Attach a performance event to a context.
  *
@@ -2555,6 +2558,8 @@ perf_install_in_context(struct perf_event_context *ctx,
 
 	lockdep_assert_held(&ctx->mutex);
 
+	WARN_ON_ONCE(!exclusive_event_installable(event, ctx));
+
 	if (event->cpu != -1)
 		event->cpu = cpu;
 
@@ -4341,7 +4346,7 @@ static int exclusive_event_init(struct perf_event *event)
 {
 	struct pmu *pmu = event->pmu;
 
-	if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE))
+	if (!is_exclusive_pmu(pmu))
 		return 0;
 
 	/*
@@ -4372,7 +4377,7 @@ static void exclusive_event_destroy(struct perf_event *event)
 {
 	struct pmu *pmu = event->pmu;
 
-	if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE))
+	if (!is_exclusive_pmu(pmu))
 		return;
 
 	/* see comment in exclusive_event_init() */
@@ -4392,14 +4397,15 @@ static bool exclusive_event_match(struct perf_event *e1, struct perf_event *e2)
 	return false;
 }
 
-/* Called under the same ctx::mutex as perf_install_in_context() */
 static bool exclusive_event_installable(struct perf_event *event,
 					struct perf_event_context *ctx)
 {
 	struct perf_event *iter_event;
 	struct pmu *pmu = event->pmu;
 
-	if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE))
+	lockdep_assert_held(&ctx->mutex);
+
+	if (!is_exclusive_pmu(pmu))
 		return true;
 
 	list_for_each_entry(iter_event, &ctx->event_list, event_entry) {
@@ -10613,11 +10619,6 @@ SYSCALL_DEFINE5(perf_event_open,
 		goto err_alloc;
 	}
 
-	if ((pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE) && group_leader) {
-		err = -EBUSY;
-		goto err_context;
-	}
-
 	/*
 	 * Look up the group leader (we will attach this event to it):
 	 */
@@ -10705,6 +10706,18 @@ SYSCALL_DEFINE5(perf_event_open,
 				move_group = 0;
 			}
 		}
+
+		/*
+		 * Failure to create exclusive events returns -EBUSY.
+		 */
+		err = -EBUSY;
+		if (!exclusive_event_installable(group_leader, ctx))
+			goto err_locked;
+
+		for_each_sibling_event(sibling, group_leader) {
+			if (!exclusive_event_installable(sibling, ctx))
+				goto err_locked;
+		}
 	} else {
 		mutex_lock(&ctx->mutex);
 	}
@@ -10741,9 +10754,6 @@ SYSCALL_DEFINE5(perf_event_open,
 	 * because we need to serialize with concurrent event creation.
 	 */
 	if (!exclusive_event_installable(event, ctx)) {
-		/* exclusive and group stuff are assumed mutually exclusive */
-		WARN_ON_ONCE(move_group);
-
 		err = -EBUSY;
 		goto err_locked;
 	}