perf/core: Fix another perf,trace,cpuhp lock inversion

Lockdep noticed the following 3-way lockup race:

        perf_trace_init()
 #0       mutex_lock(&event_mutex)
          perf_trace_event_init()
            perf_trace_event_reg()
              tp_event->class->reg() := tracepoint_probe_register
 #1              mutex_lock(&tracepoints_mutex)
                  trace_point_add_func()
 #2                  static_key_enable()

 #2	do_cpu_up()
	  perf_event_init_cpu()
 #3	    mutex_lock(&pmus_lock)
 #4	    mutex_lock(&ctx->mutex)

	perf_ioctl()
 #4	  ctx = perf_event_ctx_lock()
	  _perf_iotcl()
	    ftrace_profile_set_filter()
 #0	      mutex_lock(&event_mutex)

Fudge it for now by noting that the tracepoint state does not depend
on the event <-> context relation. Ugly though :/

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 24 insertions, 2 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2d80824298a7..816f83d70fc6 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8525,6 +8525,29 @@ 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;
@@ -8541,8 +8564,7 @@ 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);