perf: Add support for event removal on exec

Adds bit perf_event_attr::remove_on_exec, to support removing an event
from a task on exec.

This option supports the case where an event is supposed to be
process-wide only, and should not propagate beyond exec, to limit
monitoring to the original process image only.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Marco Elver <elver@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210408103605.1676875-5-elver@google.com

include/uapi/linux/perf_event.h

@@ -390,7 +390,8 @@ struct perf_event_attr {
 				text_poke      :  1, /* include text poke events */
 				build_id       :  1, /* use build id in mmap2 events */
 				inherit_thread :  1, /* children only inherit if cloned with CLONE_THREAD */
-				__reserved_1   : 28;
+				remove_on_exec :  1, /* event is removed from task on exec */
+				__reserved_1   : 27;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */

kernel/events/core.c

@@ -4248,6 +4248,57 @@ out:
 		put_ctx(clone_ctx);
 }
 
+static void perf_remove_from_owner(struct perf_event *event);
+static void perf_event_exit_event(struct perf_event *event,
+				  struct perf_event_context *ctx);
+
+/*
+ * Removes all events from the current task that have been marked
+ * remove-on-exec, and feeds their values back to parent events.
+ */
+static void perf_event_remove_on_exec(int ctxn)
+{
+	struct perf_event_context *ctx, *clone_ctx = NULL;
+	struct perf_event *event, *next;
+	LIST_HEAD(free_list);
+	unsigned long flags;
+	bool modified = false;
+
+	ctx = perf_pin_task_context(current, ctxn);
+	if (!ctx)
+		return;
+
+	mutex_lock(&ctx->mutex);
+
+	if (WARN_ON_ONCE(ctx->task != current))
+		goto unlock;
+
+	list_for_each_entry_safe(event, next, &ctx->event_list, event_entry) {
+		if (!event->attr.remove_on_exec)
+			continue;
+
+		if (!is_kernel_event(event))
+			perf_remove_from_owner(event);
+
+		modified = true;
+
+		perf_event_exit_event(event, ctx);
+	}
+
+	raw_spin_lock_irqsave(&ctx->lock, flags);
+	if (modified)
+		clone_ctx = unclone_ctx(ctx);
+	--ctx->pin_count;
+	raw_spin_unlock_irqrestore(&ctx->lock, flags);
+
+unlock:
+	mutex_unlock(&ctx->mutex);
+
+	put_ctx(ctx);
+	if (clone_ctx)
+		put_ctx(clone_ctx);
+}
+
 struct perf_read_data {
 	struct perf_event *event;
 	bool group;
@@ -7560,18 +7611,18 @@ void perf_event_exec(void)
 	struct perf_event_context *ctx;
 	int ctxn;
 
-	rcu_read_lock();
 	for_each_task_context_nr(ctxn) {
-		ctx = current->perf_event_ctxp[ctxn];
-		if (!ctx)
-			continue;
-
 		perf_event_enable_on_exec(ctxn);
+		perf_event_remove_on_exec(ctxn);
 
-		perf_iterate_ctx(ctx, perf_event_addr_filters_exec, NULL,
+		rcu_read_lock();
-				   true);
+		ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
+		if (ctx) {
+			perf_iterate_ctx(ctx, perf_event_addr_filters_exec,
+					 NULL, true);
+		}
+		rcu_read_unlock();
 	}
-	rcu_read_unlock();
 }
 
 struct remote_output {
@@ -11656,6 +11707,9 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 	if (!attr->inherit && attr->inherit_thread)
 		return -EINVAL;
 
+	if (attr->remove_on_exec && attr->enable_on_exec)
+		return -EINVAL;
+
 out:
 	return ret;