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

Pull perf tooling updates form Ingo Molnar:
 "A final batch of perf tooling changes: mostly fixes and small
  improvements"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (29 commits)
  perf session: Add comment for perf_session__register_idle_thread()
  perf thread-stack: Fix thread stack processing for the idle task
  perf thread-stack: Allocate an array of thread stacks
  perf thread-stack: Factor out thread_stack__init()
  perf thread-stack: Allow for a thread stack array
  perf thread-stack: Avoid direct reference to the thread's stack
  perf thread-stack: Tidy thread_stack__bottom() usage
  perf thread-stack: Simplify some code in thread_stack__process()
  tools gpio: Allow overriding CFLAGS
  tools power turbostat: Override CFLAGS assignments and add LDFLAGS to build command
  tools thermal tmon: Allow overriding CFLAGS assignments
  tools power x86_energy_perf_policy: Override CFLAGS assignments and add LDFLAGS to build command
  perf c2c: Increase the HITM ratio limit for displayed cachelines
  perf c2c: Change the default coalesce setup
  perf trace beauty ioctl: Beautify USBDEVFS_ commands
  perf trace beauty: Export function to get the files for a thread
  perf trace: Wire up ioctl's USBDEBFS_ cmd table generator
  perf beauty ioctl: Add generator for USBDEVFS_ ioctl commands
  tools headers uapi: Grab a copy of usbdevice_fs.h
  perf trace: Store the major number for a file when storing its pathname
  ...

1 files changed, 18 insertions, 3 deletions

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 3728b50e52e2..d079f36d342d 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1073,9 +1073,18 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 
 	/*
 	 * Print final block upto sample
+	 *
+	 * Due to pipeline delays the LBRs might be missing a branch
+	 * or two, which can result in very large or negative blocks
+	 * between final branch and sample. When this happens just
+	 * continue walking after the last TO until we hit a branch.
 	 */
 	start = br->entries[0].to;
 	end = sample->ip;
+	if (end < start) {
+		/* Missing jump. Scan 128 bytes for the next branch */
+		end = start + 128;
+	}
 	len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, true);
 	printed += ip__fprintf_sym(start, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
 	if (len <= 0) {
@@ -1084,7 +1093,6 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 			      machine, thread, &x.is64bit, &x.cpumode, false);
 		if (len <= 0)
 			goto out;
-
 		printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", sample->ip,
 			dump_insn(&x, sample->ip, buffer, len, NULL));
 		if (PRINT_FIELD(SRCCODE))
@@ -1096,6 +1104,13 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 				   dump_insn(&x, start + off, buffer + off, len - off, &ilen));
 		if (ilen == 0)
 			break;
+		if (arch_is_branch(buffer + off, len - off, x.is64bit) && start + off != sample->ip) {
+			/*
+			 * Hit a missing branch. Just stop.
+			 */
+			printed += fprintf(fp, "\t... not reaching sample ...\n");
+			break;
+		}
 		if (PRINT_FIELD(SRCCODE))
 			print_srccode(thread, x.cpumode, start + off);
 	}
@@ -1167,7 +1182,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 					   struct addr_location *al, FILE *fp)
 {
 	struct perf_event_attr *attr = &evsel->attr;
-	size_t depth = thread_stack__depth(thread);
+	size_t depth = thread_stack__depth(thread, sample->cpu);
 	const char *name = NULL;
 	static int spacing;
 	int len = 0;
@@ -1701,7 +1716,7 @@ static bool show_event(struct perf_sample *sample,
 		       struct thread *thread,
 		       struct addr_location *al)
 {
-	int depth = thread_stack__depth(thread);
+	int depth = thread_stack__depth(thread, sample->cpu);
 
 	if (!symbol_conf.graph_function)
 		return true;