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

Pull perf updates from Thomas Gleixner:
 "Mostly updates to the perf tool plus two fixes to the kernel core code:

   - Handle tracepoint filters correctly for inherited events (Peter
     Zijlstra)

   - Prevent a deadlock in perf_lock_task_context (Paul McKenney)

   - Add missing newlines to some pr_err() calls (Arnaldo Carvalho de
     Melo)

   - Print full source file paths when using 'perf annotate --print-line
     --full-paths' (Michael Petlan)

   - Fix 'perf probe -d' when just one out of uprobes and kprobes is
     enabled (Wang Nan)

   - Add compiler.h to list.h to fix 'make perf-tar-src-pkg' generated
     tarballs, i.e. out of tree building (Arnaldo Carvalho de Melo)

   - Add the llvm-src-base.c and llvm-src-kbuild.c files, generated by
     the 'perf test' LLVM entries, when running it in-tree, to
     .gitignore (Yunlong Song)

   - libbpf error reporting improvements, using a strerror interface to
     more precisely tell the user about problems with the provided
     scriptlet, be it in C or as a ready made object file (Wang Nan)

   - Do not be case sensitive when searching for matching 'perf test'
     entries (Arnaldo Carvalho de Melo)

   - Inform the user about objdump failures in 'perf annotate' (Andi
     Kleen)

   - Improve the LLVM 'perf test' entry, introduce a new ones for BPF
     and kbuild tests to check the environment used by clang to compile
     .c scriptlets (Wang Nan)"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (32 commits)
  perf/x86/intel/rapl: Remove the unused RAPL_EVENT_DESC() macro
  tools include: Add compiler.h to list.h
  perf probe: Verify parameters in two functions
  perf session: Add missing newlines to some pr_err() calls
  perf annotate: Support full source file paths for srcline fix
  perf test: Add llvm-src-base.c and llvm-src-kbuild.c to .gitignore
  perf: Fix inherited events vs. tracepoint filters
  perf: Disable IRQs across RCU RS CS that acquires scheduler lock
  perf test: Do not be case sensitive when searching for matching tests
  perf test: Add 'perf test BPF'
  perf test: Enhance the LLVM tests: add kbuild test
  perf test: Enhance the LLVM test: update basic BPF test program
  perf bpf: Improve BPF related error messages
  perf tools: Make fetch_kernel_version() publicly available
  bpf tools: Add new API bpf_object__get_kversion()
  bpf tools: Improve libbpf error reporting
  perf probe: Cleanup find_perf_probe_point_from_map to reduce redundancy
  perf annotate: Inform the user about objdump failures in --stdio
  perf stat: Make stat options global
  perf sched latency: Fix thread pid reuse issue
  ...

1 files changed, 13 insertions, 8 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1a734e0adfa7..36babfd20648 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1050,13 +1050,13 @@ retry:
 	/*
 	 * One of the few rules of preemptible RCU is that one cannot do
 	 * rcu_read_unlock() while holding a scheduler (or nested) lock when
-	 * part of the read side critical section was preemptible -- see
+	 * part of the read side critical section was irqs-enabled -- see
 	 * rcu_read_unlock_special().
 	 *
 	 * Since ctx->lock nests under rq->lock we must ensure the entire read
-	 * side critical section is non-preemptible.
+	 * side critical section has interrupts disabled.
 	 */
-	preempt_disable();
+	local_irq_save(*flags);
 	rcu_read_lock();
 	ctx = rcu_dereference(task->perf_event_ctxp[ctxn]);
 	if (ctx) {
@@ -1070,21 +1070,22 @@ retry:
 		 * if so.  If we locked the right context, then it
 		 * can't get swapped on us any more.
 		 */
-		raw_spin_lock_irqsave(&ctx->lock, *flags);
+		raw_spin_lock(&ctx->lock);
 		if (ctx != rcu_dereference(task->perf_event_ctxp[ctxn])) {
-			raw_spin_unlock_irqrestore(&ctx->lock, *flags);
+			raw_spin_unlock(&ctx->lock);
 			rcu_read_unlock();
-			preempt_enable();
+			local_irq_restore(*flags);
 			goto retry;
 		}
 
 		if (!atomic_inc_not_zero(&ctx->refcount)) {
-			raw_spin_unlock_irqrestore(&ctx->lock, *flags);
+			raw_spin_unlock(&ctx->lock);
 			ctx = NULL;
 		}
 	}
 	rcu_read_unlock();
-	preempt_enable();
+	if (!ctx)
+		local_irq_restore(*flags);
 	return ctx;
 }
 
@@ -6913,6 +6914,10 @@ static int perf_tp_filter_match(struct perf_event *event,
 {
 	void *record = data->raw->data;
 
+	/* only top level events have filters set */
+	if (event->parent)
+		event = event->parent;
+
 	if (likely(!event->filter) || filter_match_preds(event->filter, record))
 		return 1;
 	return 0;