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

Pull perf events update from Ingo Molnar:
 "On the kernel side there's few changes, the one that stands out is
  PEBS machine state sampling support on x86, by Stephane Eranian.

  On the tooling side:

  User visible tooling changes:

   - Don't open the DWARF info multiple times, keeping instead a dwfl
     handle in struct dso, greatly speeding up 'perf report' on powerpc.
     (Sukadev Bhattiprolu)

   - Introduce PARSE_OPT_DISABLED option flag and use it to avoid
     showing undersired options in tools that provides frontends to
     'perf record', like sched, kvm, etc (Namhyung Kim)

   - Fallback to kallsyms when using the minimal 'ELF' loader (Arnaldo
     Carvalho de Melo)

   - Fix annotation with kcore (Adrian Hunter)

   - Support source line numbers in annotate using a hotkey (Andi Kleen)

   - Callchain improvements including:
     * Enable printing the srcline in the history
     * Make get_srcline fall back to sym+offset (Andi Kleen)

   - TUI hist_entry browser fixes, including showing missing overhead
     value for first level callchain.  Detected comparing the output of
     --stdio/--gui (that matched) with --tui, that had this problem.
     (Namhyung Kim)

   - Support handling complete branch stacks as histograms (Andi Kleen)

  Tooling infrastructure changes:

   - Prep work for supporting per-pkg and snapshot counters in 'perf
     stat' (Jiri Olsa)

   - 'perf stat' refactorings, moving stuff from it to evsel.c to use in
     per-pkg/snapshot format changes (Jiri Olsa)

   - Add per-pkg format file parsing (Matt Fleming)

   - Clean up libelf feature support code (Namhyung Kim)

   - Add gzip decompression support for kernel modules (Namhyung Kim)

   - More prep patches for Intel PT, including a a thread stack and more
     stuff made available via the database export mechanism (Adrian
     Hunter)

   - More Intel PT work, including a facility to export sample data
     (comms, threads, symbol names, etc) in a database friendly way,
     with an script to use this to create a postgresql database.
     (Adrian Hunter)

   - Make sure that thread->mg->machine points to the machine where the
     thread exists (it was being set only for the kmaps kernel modules
     case, do it as well for the mmaps) and use it to shorten function
     signatures (Arnaldo Carvalho de Melo)

  ... and lots of other fixes and smaller improvements"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (91 commits)
  perf report: In branch stack mode use address history sorting
  perf report: Add --branch-history option
  perf callchain: Support handling complete branch stacks as histograms
  perf stat: Add support for snapshot counters
  perf stat: Add support for per-pkg counters
  perf tools: Remove perf_evsel__read interface
  perf stat: Use read_counter in read_counter_aggr
  perf stat: Make read_counter work over the thread dimension
  perf stat: Use perf_evsel__read_cb in read_counter
  perf tools: Add snapshot format file parsing
  perf tools: Add per-pkg format file parsing
  perf evsel: Introduce perf_evsel__read_cb function
  perf evsel: Introduce perf_counts_values__scale function
  perf evsel: Introduce perf_evsel__compute_deltas function
  perf tools: Allow to force redirect pr_debug to stderr.
  perf tools: Fix segfault due to invalid kernel dso access
  perf callchain: Make get_srcline fall back to sym+offset
  perf symbols: Move bfd_demangle stubbing to its only user
  perf callchain: Enable printing the srcline in the history
  perf tools: Collapse first level callchain entry if it has sibling
  ...

1 files changed, 94 insertions, 21 deletions

diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index e243ad962a4d..5c9c4947cfb4 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -163,6 +163,41 @@ error:
 	return -1;
 }
 
+static int
+perf_pmu__parse_per_pkg(struct perf_pmu_alias *alias, char *dir, char *name)
+{
+	char path[PATH_MAX];
+	int fd;
+
+	snprintf(path, PATH_MAX, "%s/%s.per-pkg", dir, name);
+
+	fd = open(path, O_RDONLY);
+	if (fd == -1)
+		return -1;
+
+	close(fd);
+
+	alias->per_pkg = true;
+	return 0;
+}
+
+static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
+				    char *dir, char *name)
+{
+	char path[PATH_MAX];
+	int fd;
+
+	snprintf(path, PATH_MAX, "%s/%s.snapshot", dir, name);
+
+	fd = open(path, O_RDONLY);
+	if (fd == -1)
+		return -1;
+
+	alias->snapshot = true;
+	close(fd);
+	return 0;
+}
+
 static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FILE *file)
 {
 	struct perf_pmu_alias *alias;
@@ -181,6 +216,7 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 	INIT_LIST_HEAD(&alias->terms);
 	alias->scale = 1.0;
 	alias->unit[0] = '\0';
+	alias->per_pkg = false;
 
 	ret = parse_events_terms(&alias->terms, buf);
 	if (ret) {
@@ -194,6 +230,8 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 	 */
 	perf_pmu__parse_unit(alias, dir, name);
 	perf_pmu__parse_scale(alias, dir, name);
+	perf_pmu__parse_per_pkg(alias, dir, name);
+	perf_pmu__parse_snapshot(alias, dir, name);
 
 	list_add_tail(&alias->list, list);
 
@@ -209,6 +247,10 @@ static inline bool pmu_alias_info_file(char *name)
 		return true;
 	if (len > 6 && !strcmp(name + len - 6, ".scale"))
 		return true;
+	if (len > 8 && !strcmp(name + len - 8, ".per-pkg"))
+		return true;
+	if (len > 9 && !strcmp(name + len - 9, ".snapshot"))
+		return true;
 
 	return false;
 }
@@ -617,23 +659,27 @@ static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
 }
 
 
-static int check_unit_scale(struct perf_pmu_alias *alias,
-			    const char **unit, double *scale)
+static int check_info_data(struct perf_pmu_alias *alias,
+			   struct perf_pmu_info *info)
 {
 	/*
 	 * Only one term in event definition can
-	 * define unit and scale, fail if there's
-	 * more than one.
+	 * define unit, scale and snapshot, fail
+	 * if there's more than one.
 	 */
-	if ((*unit && alias->unit) ||
-	    (*scale && alias->scale))
+	if ((info->unit && alias->unit) ||
+	    (info->scale && alias->scale) ||
+	    (info->snapshot && alias->snapshot))
 		return -EINVAL;
 
 	if (alias->unit)
-		*unit = alias->unit;
+		info->unit = alias->unit;
 
 	if (alias->scale)
-		*scale = alias->scale;
+		info->scale = alias->scale;
+
+	if (alias->snapshot)
+		info->snapshot = alias->snapshot;
 
 	return 0;
 }
@@ -649,12 +695,15 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 	struct perf_pmu_alias *alias;
 	int ret;
 
+	info->per_pkg = false;
+
 	/*
 	 * Mark unit and scale as not set
 	 * (different from default values, see below)
 	 */
-	info->unit   = NULL;
-	info->scale  = 0.0;
+	info->unit     = NULL;
+	info->scale    = 0.0;
+	info->snapshot = false;
 
 	list_for_each_entry_safe(term, h, head_terms, list) {
 		alias = pmu_find_alias(pmu, term);
@@ -664,10 +713,13 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 		if (ret)
 			return ret;
 
-		ret = check_unit_scale(alias, &info->unit, &info->scale);
+		ret = check_info_data(alias, info);
 		if (ret)
 			return ret;
 
+		if (alias->per_pkg)
+			info->per_pkg = true;
+
 		list_del(&term->list);
 		free(term);
 	}
@@ -747,15 +799,18 @@ void print_pmu_events(const char *event_glob, bool name_only)
 
 	pmu = NULL;
 	len = 0;
-	while ((pmu = perf_pmu__scan(pmu)) != NULL)
+	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
 		list_for_each_entry(alias, &pmu->aliases, list)
 			len++;
-	aliases = malloc(sizeof(char *) * len);
+		if (pmu->selectable)
+			len++;
+	}
+	aliases = zalloc(sizeof(char *) * len);
 	if (!aliases)
-		return;
+		goto out_enomem;
 	pmu = NULL;
 	j = 0;
-	while ((pmu = perf_pmu__scan(pmu)) != NULL)
+	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
 		list_for_each_entry(alias, &pmu->aliases, list) {
 			char *name = format_alias(buf, sizeof(buf), pmu, alias);
 			bool is_cpu = !strcmp(pmu->name, "cpu");
@@ -765,13 +820,23 @@ void print_pmu_events(const char *event_glob, bool name_only)
 			      (!is_cpu && strglobmatch(alias->name,
 						       event_glob))))
 				continue;
-			aliases[j] = name;
+
 			if (is_cpu && !name_only)
-				aliases[j] = format_alias_or(buf, sizeof(buf),
-							      pmu, alias);
-			aliases[j] = strdup(aliases[j]);
+				name = format_alias_or(buf, sizeof(buf), pmu, alias);
+
+			aliases[j] = strdup(name);
+			if (aliases[j] == NULL)
+				goto out_enomem;
 			j++;
 		}
+		if (pmu->selectable) {
+			char *s;
+			if (asprintf(&s, "%s//", pmu->name) < 0)
+				goto out_enomem;
+			aliases[j] = s;
+			j++;
+		}
+	}
 	len = j;
 	qsort(aliases, len, sizeof(char *), cmp_string);
 	for (j = 0; j < len; j++) {
@@ -780,12 +845,20 @@ void print_pmu_events(const char *event_glob, bool name_only)
 			continue;
 		}
 		printf("  %-50s [Kernel PMU event]\n", aliases[j]);
-		zfree(&aliases[j]);
 		printed++;
 	}
 	if (printed)
 		printf("\n");
-	free(aliases);
+out_free:
+	for (j = 0; j < len; j++)
+		zfree(&aliases[j]);
+	zfree(&aliases);
+	return;
+
+out_enomem:
+	printf("FATAL: not enough memory to print PMU events\n");
+	if (aliases)
+		goto out_free;
 }
 
 bool pmu_have_event(const char *pname, const char *name)