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

Pull perf updates from Ingo Molnar:
 "Kernel improvements:

   - watchdog driver improvements by Li Zefan
   - Power7 CPI stack events related improvements by Sukadev Bhattiprolu
   - event multiplexing via hrtimers and other improvements by Stephane
     Eranian
   - kernel stack use optimization by Andrew Hunter
   - AMD IOMMU uncore PMU support by Suravee Suthikulpanit
   - NMI handling rate-limits by Dave Hansen
   - various hw_breakpoint fixes by Oleg Nesterov
   - hw_breakpoint overflow period sampling and related signal handling
     fixes by Jiri Olsa
   - Intel Haswell PMU support by Andi Kleen

  Tooling improvements:

   - Reset SIGTERM handler in workload child process, fix from David
     Ahern.
   - Makefile reorganization, prep work for Kconfig patches, from Jiri
     Olsa.
   - Add automated make test suite, from Jiri Olsa.
   - Add --percent-limit option to 'top' and 'report', from Namhyung
     Kim.
   - Sorting improvements, from Namhyung Kim.
   - Expand definition of sysfs format attribute, from Michael Ellerman.

  Tooling fixes:

   - 'perf tests' fixes from Jiri Olsa.
   - Make Power7 CPI stack events available in sysfs, from Sukadev
     Bhattiprolu.
   - Handle death by SIGTERM in 'perf record', fix from David Ahern.
   - Fix printing of perf_event_paranoid message, from David Ahern.
   - Handle realloc failures in 'perf kvm', from David Ahern.
   - Fix divide by 0 in variance, from David Ahern.
   - Save parent pid in thread struct, from David Ahern.
   - Handle JITed code in shared memory, from Andi Kleen.
   - Fixes for 'perf diff', from Jiri Olsa.
   - Remove some unused struct members, from Jiri Olsa.
   - Add missing liblk.a dependency for python/perf.so, fix from Jiri
     Olsa.
   - Respect CROSS_COMPILE in liblk.a, from Rabin Vincent.
   - No need to do locking when adding hists in perf report, only 'top'
     needs that, from Namhyung Kim.
   - Fix alignment of symbol column in in the hists browser (top,
     report) when -v is given, from NAmhyung Kim.
   - Fix 'perf top' -E option behavior, from Namhyung Kim.
   - Fix bug in isupper() and islower(), from Sukadev Bhattiprolu.
   - Fix compile errors in bp_signal 'perf test', from Sukadev
     Bhattiprolu.

  ... and more things"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (102 commits)
  perf/x86: Disable PEBS-LL in intel_pmu_pebs_disable()
  perf/x86: Fix shared register mutual exclusion enforcement
  perf/x86/intel: Support full width counting
  x86: Add NMI duration tracepoints
  perf: Drop sample rate when sampling is too slow
  x86: Warn when NMI handlers take large amounts of time
  hw_breakpoint: Introduce "struct bp_cpuinfo"
  hw_breakpoint: Simplify *register_wide_hw_breakpoint()
  hw_breakpoint: Introduce cpumask_of_bp()
  hw_breakpoint: Simplify the "weight" usage in toggle_bp_slot() paths
  hw_breakpoint: Simplify list/idx mess in toggle_bp_slot() paths
  perf/x86/intel: Add mem-loads/stores support for Haswell
  perf/x86/intel: Support Haswell/v4 LBR format
  perf/x86/intel: Move NMI clearing to end of PMI handler
  perf/x86/intel: Add Haswell PEBS support
  perf/x86/intel: Add simple Haswell PMU support
  perf/x86/intel: Add Haswell PEBS record support
  perf/x86/intel: Fix sparse warning
  perf/x86/amd: AMD IOMMU Performance Counter PERF uncore PMU implementation
  perf/x86/amd: Add IOMMU Performance Counter resource management
  ...

1 files changed, 42 insertions, 54 deletions

diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 6b32721f829a..b11a6cfdb414 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -70,9 +70,17 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 	int symlen;
 	u16 len;
 
-	if (h->ms.sym)
-		hists__new_col_len(hists, HISTC_SYMBOL, h->ms.sym->namelen + 4);
-	else {
+	/*
+	 * +4 accounts for '[x] ' priv level info
+	 * +2 accounts for 0x prefix on raw addresses
+	 * +3 accounts for ' y ' symtab origin info
+	 */
+	if (h->ms.sym) {
+		symlen = h->ms.sym->namelen + 4;
+		if (verbose)
+			symlen += BITS_PER_LONG / 4 + 2 + 3;
+		hists__new_col_len(hists, HISTC_SYMBOL, symlen);
+	} else {
 		symlen = unresolved_col_width + 4 + 2;
 		hists__new_col_len(hists, HISTC_SYMBOL, symlen);
 		hists__set_unres_dso_col_len(hists, HISTC_DSO);
@@ -91,12 +99,10 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 		hists__new_col_len(hists, HISTC_PARENT, h->parent->namelen);
 
 	if (h->branch_info) {
-		/*
-		 * +4 accounts for '[x] ' priv level info
-		 * +2 account of 0x prefix on raw addresses
-		 */
 		if (h->branch_info->from.sym) {
 			symlen = (int)h->branch_info->from.sym->namelen + 4;
+			if (verbose)
+				symlen += BITS_PER_LONG / 4 + 2 + 3;
 			hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen);
 
 			symlen = dso__name_len(h->branch_info->from.map->dso);
@@ -109,6 +115,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 
 		if (h->branch_info->to.sym) {
 			symlen = (int)h->branch_info->to.sym->namelen + 4;
+			if (verbose)
+				symlen += BITS_PER_LONG / 4 + 2 + 3;
 			hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen);
 
 			symlen = dso__name_len(h->branch_info->to.map->dso);
@@ -121,10 +129,6 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 	}
 
 	if (h->mem_info) {
-		/*
-		 * +4 accounts for '[x] ' priv level info
-		 * +2 account of 0x prefix on raw addresses
-		 */
 		if (h->mem_info->daddr.sym) {
 			symlen = (int)h->mem_info->daddr.sym->namelen + 4
 			       + unresolved_col_width + 2;
@@ -236,8 +240,7 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
 	return he->stat.period == 0;
 }
 
-static void __hists__decay_entries(struct hists *hists, bool zap_user,
-				   bool zap_kernel, bool threaded)
+void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
 {
 	struct rb_node *next = rb_first(&hists->entries);
 	struct hist_entry *n;
@@ -256,7 +259,7 @@ static void __hists__decay_entries(struct hists *hists, bool zap_user,
 		    !n->used) {
 			rb_erase(&n->rb_node, &hists->entries);
 
-			if (sort__need_collapse || threaded)
+			if (sort__need_collapse)
 				rb_erase(&n->rb_node_in, &hists->entries_collapsed);
 
 			hist_entry__free(n);
@@ -265,17 +268,6 @@ static void __hists__decay_entries(struct hists *hists, bool zap_user,
 	}
 }
 
-void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
-{
-	return __hists__decay_entries(hists, zap_user, zap_kernel, false);
-}
-
-void hists__decay_entries_threaded(struct hists *hists,
-				   bool zap_user, bool zap_kernel)
-{
-	return __hists__decay_entries(hists, zap_user, zap_kernel, true);
-}
-
 /*
  * histogram, sorted on item, collects periods
  */
@@ -292,6 +284,20 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template)
 			he->ms.map->referenced = true;
 
 		if (he->branch_info) {
+			/*
+			 * This branch info is (a part of) allocated from
+			 * machine__resolve_bstack() and will be freed after
+			 * adding new entries.  So we need to save a copy.
+			 */
+			he->branch_info = malloc(sizeof(*he->branch_info));
+			if (he->branch_info == NULL) {
+				free(he);
+				return NULL;
+			}
+
+			memcpy(he->branch_info, template->branch_info,
+			       sizeof(*he->branch_info));
+
 			if (he->branch_info->from.map)
 				he->branch_info->from.map->referenced = true;
 			if (he->branch_info->to.map)
@@ -341,8 +347,6 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
 	struct hist_entry *he;
 	int cmp;
 
-	pthread_mutex_lock(&hists->lock);
-
 	p = &hists->entries_in->rb_node;
 
 	while (*p != NULL) {
@@ -360,6 +364,12 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
 		if (!cmp) {
 			he_stat__add_period(&he->stat, period, weight);
 
+			/*
+			 * This mem info was allocated from machine__resolve_mem
+			 * and will not be used anymore.
+			 */
+			free(entry->mem_info);
+
 			/* If the map of an existing hist_entry has
 			 * become out-of-date due to an exec() or
 			 * similar, update it.  Otherwise we will
@@ -382,14 +392,12 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
 
 	he = hist_entry__new(entry);
 	if (!he)
-		goto out_unlock;
+		return NULL;
 
 	rb_link_node(&he->rb_node_in, parent, p);
 	rb_insert_color(&he->rb_node_in, hists->entries_in);
 out:
 	hist_entry__add_cpumode_period(he, al->cpumode, period);
-out_unlock:
-	pthread_mutex_unlock(&hists->lock);
 	return he;
 }
 
@@ -589,13 +597,13 @@ static void hists__apply_filters(struct hists *hists, struct hist_entry *he)
 	hists__filter_entry_by_symbol(hists, he);
 }
 
-static void __hists__collapse_resort(struct hists *hists, bool threaded)
+void hists__collapse_resort(struct hists *hists)
 {
 	struct rb_root *root;
 	struct rb_node *next;
 	struct hist_entry *n;
 
-	if (!sort__need_collapse && !threaded)
+	if (!sort__need_collapse)
 		return;
 
 	root = hists__get_rotate_entries_in(hists);
@@ -617,16 +625,6 @@ static void __hists__collapse_resort(struct hists *hists, bool threaded)
 	}
 }
 
-void hists__collapse_resort(struct hists *hists)
-{
-	return __hists__collapse_resort(hists, false);
-}
-
-void hists__collapse_resort_threaded(struct hists *hists)
-{
-	return __hists__collapse_resort(hists, true);
-}
-
 /*
  * reverse the map, sort on period.
  */
@@ -713,7 +711,7 @@ static void __hists__insert_output_entry(struct rb_root *entries,
 	rb_insert_color(&he->rb_node, entries);
 }
 
-static void __hists__output_resort(struct hists *hists, bool threaded)
+void hists__output_resort(struct hists *hists)
 {
 	struct rb_root *root;
 	struct rb_node *next;
@@ -722,7 +720,7 @@ static void __hists__output_resort(struct hists *hists, bool threaded)
 
 	min_callchain_hits = hists->stats.total_period * (callchain_param.min_percent / 100);
 
-	if (sort__need_collapse || threaded)
+	if (sort__need_collapse)
 		root = &hists->entries_collapsed;
 	else
 		root = hists->entries_in;
@@ -743,16 +741,6 @@ static void __hists__output_resort(struct hists *hists, bool threaded)
 	}
 }
 
-void hists__output_resort(struct hists *hists)
-{
-	return __hists__output_resort(hists, false);
-}
-
-void hists__output_resort_threaded(struct hists *hists)
-{
-	return __hists__output_resort(hists, true);
-}
-
 static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h,
 				       enum hist_filter filter)
 {