1 files changed, 81 insertions, 20 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4df5b695bf0d..d99fe3fdec8a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1231,6 +1231,10 @@ static void put_ctx(struct perf_event_context *ctx)
  *	      perf_event_context::lock
  *	    perf_event::mmap_mutex
  *	    mmap_sem
+ *
+ *    cpu_hotplug_lock
+ *      pmus_lock
+ *	  cpuctx->mutex / perf_event_context::mutex
  */
 static struct perf_event_context *
 perf_event_ctx_lock_nested(struct perf_event *event, int nesting)
@@ -4196,6 +4200,7 @@ int perf_event_release_kernel(struct perf_event *event)
 {
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_event *child, *tmp;
+	LIST_HEAD(free_list);
 
 	/*
 	 * If we got here through err_file: fput(event_file); we will not have
@@ -4268,8 +4273,7 @@ again:
 					       struct perf_event, child_list);
 		if (tmp == child) {
 			perf_remove_from_context(child, DETACH_GROUP);
-			list_del(&child->child_list);
-			free_event(child);
+			list_move(&child->child_list, &free_list);
 			/*
 			 * This matches the refcount bump in inherit_event();
 			 * this can't be the last reference.
@@ -4284,6 +4288,11 @@ again:
 	}
 	mutex_unlock(&event->child_mutex);
 
+	list_for_each_entry_safe(child, tmp, &free_list, child_list) {
+		list_del(&child->child_list);
+		free_event(child);
+	}
+
 no_ctx:
 	put_event(event); /* Must be the 'last' reference */
 	return 0;
@@ -5815,19 +5824,11 @@ void perf_output_sample(struct perf_output_handle *handle,
 		perf_output_read(handle, event);
 
 	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
-		if (data->callchain) {
-			int size = 1;
-
-			if (data->callchain)
-				size += data->callchain->nr;
-
-			size *= sizeof(u64);
+		int size = 1;
 
-			__output_copy(handle, data->callchain, size);
-		} else {
-			u64 nr = 0;
-			perf_output_put(handle, nr);
-		}
+		size += data->callchain->nr;
+		size *= sizeof(u64);
+		__output_copy(handle, data->callchain, size);
 	}
 
 	if (sample_type & PERF_SAMPLE_RAW) {
@@ -5980,6 +5981,26 @@ static u64 perf_virt_to_phys(u64 virt)
 	return phys_addr;
 }
 
+static struct perf_callchain_entry __empty_callchain = { .nr = 0, };
+
+static struct perf_callchain_entry *
+perf_callchain(struct perf_event *event, struct pt_regs *regs)
+{
+	bool kernel = !event->attr.exclude_callchain_kernel;
+	bool user   = !event->attr.exclude_callchain_user;
+	/* Disallow cross-task user callchains. */
+	bool crosstask = event->ctx->task && event->ctx->task != current;
+	const u32 max_stack = event->attr.sample_max_stack;
+	struct perf_callchain_entry *callchain;
+
+	if (!kernel && !user)
+		return &__empty_callchain;
+
+	callchain = get_perf_callchain(regs, 0, kernel, user,
+				       max_stack, crosstask, true);
+	return callchain ?: &__empty_callchain;
+}
+
 void perf_prepare_sample(struct perf_event_header *header,
 			 struct perf_sample_data *data,
 			 struct perf_event *event,
@@ -6002,9 +6023,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 		int size = 1;
 
 		data->callchain = perf_callchain(event, regs);
-
-		if (data->callchain)
-			size += data->callchain->nr;
+		size += data->callchain->nr;
 
 		header->size += size * sizeof(u64);
 	}
@@ -8516,6 +8535,29 @@ fail_clear_files:
 	return ret;
 }
 
+static int
+perf_tracepoint_set_filter(struct perf_event *event, char *filter_str)
+{
+	struct perf_event_context *ctx = event->ctx;
+	int ret;
+
+	/*
+	 * Beware, here be dragons!!
+	 *
+	 * the tracepoint muck will deadlock against ctx->mutex, but the tracepoint
+	 * stuff does not actually need it. So temporarily drop ctx->mutex. As per
+	 * perf_event_ctx_lock() we already have a reference on ctx.
+	 *
+	 * This can result in event getting moved to a different ctx, but that
+	 * does not affect the tracepoint state.
+	 */
+	mutex_unlock(&ctx->mutex);
+	ret = ftrace_profile_set_filter(event, event->attr.config, filter_str);
+	mutex_lock(&ctx->mutex);
+
+	return ret;
+}
+
 static int perf_event_set_filter(struct perf_event *event, void __user *arg)
 {
 	char *filter_str;
@@ -8532,8 +8574,7 @@ static int perf_event_set_filter(struct perf_event *event, void __user *arg)
 
 	if (IS_ENABLED(CONFIG_EVENT_TRACING) &&
 	    event->attr.type == PERF_TYPE_TRACEPOINT)
-		ret = ftrace_profile_set_filter(event, event->attr.config,
-						filter_str);
+		ret = perf_tracepoint_set_filter(event, filter_str);
 	else if (has_addr_filter(event))
 		ret = perf_event_set_addr_filter(event, filter_str);
 
@@ -9168,7 +9209,13 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
 	if (!try_module_get(pmu->module))
 		return -ENODEV;
 
-	if (event->group_leader != event) {
+	/*
+	 * A number of pmu->event_init() methods iterate the sibling_list to,
+	 * for example, validate if the group fits on the PMU. Therefore,
+	 * if this is a sibling event, acquire the ctx->mutex to protect
+	 * the sibling_list.
+	 */
+	if (event->group_leader != event && pmu->task_ctx_nr != perf_sw_context) {
 		/*
 		 * This ctx->mutex can nest when we're called through
 		 * inheritance. See the perf_event_ctx_lock_nested() comment.
@@ -10703,6 +10750,19 @@ inherit_event(struct perf_event *parent_event,
 	if (IS_ERR(child_event))
 		return child_event;
 
+
+	if ((child_event->attach_state & PERF_ATTACH_TASK_DATA) &&
+	    !child_ctx->task_ctx_data) {
+		struct pmu *pmu = child_event->pmu;
+
+		child_ctx->task_ctx_data = kzalloc(pmu->task_ctx_size,
+						   GFP_KERNEL);
+		if (!child_ctx->task_ctx_data) {
+			free_event(child_event);
+			return NULL;
+		}
+	}
+
 	/*
 	 * is_orphaned_event() and list_add_tail(&parent_event->child_list)
 	 * must be under the same lock in order to serialize against
@@ -10713,6 +10773,7 @@ inherit_event(struct perf_event *parent_event,
 	if (is_orphaned_event(parent_event) ||
 	    !atomic_long_inc_not_zero(&parent_event->refcount)) {
 		mutex_unlock(&parent_event->child_mutex);
+		/* task_ctx_data is freed with child_ctx */
 		free_event(child_event);
 		return NULL;
 	}