Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf fixes from Ingo Molnar:
 "A number of PMU driver corner case fixes, a race fix, an event
  grouping fix, plus a bunch of tooling fixes/updates"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (30 commits)
  perf/x86/intel: Fix spurious NMI on fixed counter
  perf/core: Fix exclusive events' grouping
  perf/x86/amd/uncore: Set the thread mask for F17h L3 PMCs
  perf/x86/amd/uncore: Do not set 'ThreadMask' and 'SliceMask' for non-L3 PMCs
  perf/core: Fix race between close() and fork()
  perf intel-pt: Fix potential NULL pointer dereference found by the smatch tool
  perf intel-bts: Fix potential NULL pointer dereference found by the smatch tool
  perf script: Assume native_arch for pipe mode
  perf scripts python: export-to-sqlite.py: Fix DROP VIEW power_events_view
  perf scripts python: export-to-postgresql.py: Fix DROP VIEW power_events_view
  perf hists browser: Fix potential NULL pointer dereference found by the smatch tool
  perf cs-etm: Fix potential NULL pointer dereference found by the smatch tool
  perf parse-events: Remove unused variable: error
  perf parse-events: Remove unused variable 'i'
  perf metricgroup: Add missing list_del_init() when flushing egroups list
  perf tools: Use list_del_init() more thorougly
  perf tools: Use zfree() where applicable
  tools lib: Adopt zalloc()/zfree() from tools/perf
  perf tools: Move get_current_dir_name() cond prototype out of util.h
  perf namespaces: Move the conditional setns() prototype to namespaces.h
  ...

1 files changed, 63 insertions, 20 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 785d708f8553..eea9d52b010c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2553,6 +2553,9 @@ unlock:
 	return ret;
 }
 
+static bool exclusive_event_installable(struct perf_event *event,
+					struct perf_event_context *ctx);
+
 /*
  * Attach a performance event to a context.
  *
@@ -2567,6 +2570,8 @@ 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;
 
@@ -4360,7 +4365,7 @@ 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;
 
 	/*
@@ -4391,7 +4396,7 @@ 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() */
@@ -4411,14 +4416,15 @@ 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) {
@@ -4465,12 +4471,20 @@ static void _free_event(struct perf_event *event)
 	if (event->destroy)
 		event->destroy(event);
 
-	if (event->ctx)
-		put_ctx(event->ctx);
-
+	/*
+	 * Must be after ->destroy(), due to uprobe_perf_close() using
+	 * hw.target.
+	 */
 	if (event->hw.target)
 		put_task_struct(event->hw.target);
 
+	/*
+	 * perf_event_free_task() relies on put_ctx() being 'last', in particular
+	 * all task references must be cleaned up.
+	 */
+	if (event->ctx)
+		put_ctx(event->ctx);
+
 	exclusive_event_destroy(event);
 	module_put(event->pmu->module);
 
@@ -4650,8 +4664,17 @@ again:
 	mutex_unlock(&event->child_mutex);
 
 	list_for_each_entry_safe(child, tmp, &free_list, child_list) {
+		void *var = &child->ctx->refcount;
+
 		list_del(&child->child_list);
 		free_event(child);
+
+		/*
+		 * Wake any perf_event_free_task() waiting for this event to be
+		 * freed.
+		 */
+		smp_mb(); /* pairs with wait_var_event() */
+		wake_up_var(var);
 	}
 
 no_ctx:
@@ -10930,11 +10953,6 @@ 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):
 	 */
@@ -11022,6 +11040,18 @@ 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);
 	}
@@ -11058,9 +11088,6 @@ 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;
 	}
@@ -11527,11 +11554,11 @@ static void perf_free_event(struct perf_event *event,
 }
 
 /*
- * Free an unexposed, unused context as created by inheritance by
- * perf_event_init_task below, used by fork() in case of fail.
+ * Free a context as created by inheritance by perf_event_init_task() below,
+ * used by fork() in case of fail.
  *
- * Not all locks are strictly required, but take them anyway to be nice and
- * help out with the lockdep assertions.
+ * Even though the task has never lived, the context and events have been
+ * exposed through the child_list, so we must take care tearing it all down.
  */
 void perf_event_free_task(struct task_struct *task)
 {
@@ -11561,7 +11588,23 @@ void perf_event_free_task(struct task_struct *task)
 			perf_free_event(event, ctx);
 
 		mutex_unlock(&ctx->mutex);
-		put_ctx(ctx);
+
+		/*
+		 * perf_event_release_kernel() could've stolen some of our
+		 * child events and still have them on its free_list. In that
+		 * case we must wait for these events to have been freed (in
+		 * particular all their references to this task must've been
+		 * dropped).
+		 *
+		 * Without this copy_process() will unconditionally free this
+		 * task (irrespective of its reference count) and
+		 * _free_event()'s put_task_struct(event->hw.target) will be a
+		 * use-after-free.
+		 *
+		 * Wait for all events to drop their context reference.
+		 */
+		wait_var_event(&ctx->refcount, refcount_read(&ctx->refcount) == 1);
+		put_ctx(ctx); /* must be last */
 	}
 }