Merge branch 'perf-tools-for-linus' of git://github.com/acmel/linux

* 'perf-tools-for-linus' of git://github.com/acmel/linux:
  perf tools: Add support for disabling -Werror via WERROR=0
  perf top: Fix userspace sample addr map offset
  perf symbols: Fix issue with binaries using 16-bytes buildids (v2)
  perf tool: Fix endianness handling of u32 data in samples
  perf sort: Fix symbol sort output by separating unresolved samples by type
  perf symbols: Synthesize anonymous mmap events
  perf record: Create events initially disabled and enable after init
  perf symbols: Add some heuristics for choosing the best duplicate symbol
  perf symbols: Preserve symbol scope when parsing /proc/kallsyms
  perf symbols: /proc/kallsyms does not sort module symbols
  perf symbols: Fix ppc64 SEGV in dso__load_sym with debuginfo files
  perf probe: Fix regression of variable finder

tools/perf/Makefile

@@ -30,6 +30,8 @@ endif
 # Define EXTRA_CFLAGS=-m64 or EXTRA_CFLAGS=-m32 as appropriate for cross-builds.
 #
 # Define NO_DWARF if you do not want debug-info analysis feature at all.
+#
+# Define WERROR=0 to disable treating any warnings as errors.
 
 $(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
 	@$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
@@ -63,6 +65,11 @@ ifeq ($(ARCH),x86_64)
 	endif
 endif
 
+# Treat warnings as errors unless directed not to
+ifneq ($(WERROR),0)
+	CFLAGS_WERROR := -Werror
+endif
+
 #
 # Include saner warnings here, which can catch bugs:
 #
@@ -95,7 +102,7 @@ ifndef PERF_DEBUG
   CFLAGS_OPTIMIZE = -O6
 endif
 
-CFLAGS = -fno-omit-frame-pointer -ggdb3 -Wall -Wextra -std=gnu99 -Werror $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
+CFLAGS = -fno-omit-frame-pointer -ggdb3 -Wall -Wextra -std=gnu99 $(CFLAGS_WERROR) $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
 EXTLIBS = -lpthread -lrt -lelf -lm
 ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
 ALL_LDFLAGS = $(LDFLAGS)

tools/perf/builtin-record.c

@@ -161,6 +161,7 @@ static void config_attr(struct perf_evsel *evsel, struct perf_evlist *evlist)
 	struct perf_event_attr *attr = &evsel->attr;
 	int track = !evsel->idx; /* only the first counter needs these */
 
+	attr->disabled		= 1;
 	attr->inherit		= !no_inherit;
 	attr->read_format	= PERF_FORMAT_TOTAL_TIME_ENABLED |
 				  PERF_FORMAT_TOTAL_TIME_RUNNING |
@@ -671,6 +672,8 @@ static int __cmd_record(int argc, const char **argv)
 		}
 	}
 
+	perf_evlist__enable(evsel_list);
+
 	/*
 	 * Let the child rip
 	 */

tools/perf/builtin-test.c

@@ -561,7 +561,7 @@ static int test__basic_mmap(void)
 		}
 
 		err = perf_event__parse_sample(event, attr.sample_type, sample_size,
-					       false, &sample);
+					       false, &sample, false);
 		if (err) {
 			pr_err("Can't parse sample, err = %d\n", err);
 			goto out_munmap;

tools/perf/builtin-top.c

@@ -191,7 +191,8 @@ static void __zero_source_counters(struct sym_entry *syme)
 	symbol__annotate_zero_histograms(sym);
 }
 
-static void record_precise_ip(struct sym_entry *syme, int counter, u64 ip)
+static void record_precise_ip(struct sym_entry *syme, struct map *map,
+			      int counter, u64 ip)
 {
 	struct annotation *notes;
 	struct symbol *sym;
@@ -205,8 +206,8 @@ static void record_precise_ip(struct sym_entry *syme, int counter, u64 ip)
 	if (pthread_mutex_trylock(&notes->lock))
 		return;
 
-	ip = syme->map->map_ip(syme->map, ip);
-	symbol__inc_addr_samples(sym, syme->map, counter, ip);
+	ip = map->map_ip(map, ip);
+	symbol__inc_addr_samples(sym, map, counter, ip);
 
 	pthread_mutex_unlock(&notes->lock);
 }
@@ -810,7 +811,7 @@ static void perf_event__process_sample(const union perf_event *event,
 		evsel = perf_evlist__id2evsel(top.evlist, sample->id);
 		assert(evsel != NULL);
 		syme->count[evsel->idx]++;
-		record_precise_ip(syme, evsel->idx, ip);
+		record_precise_ip(syme, al.map, evsel->idx, ip);
 		pthread_mutex_lock(&top.active_symbols_lock);
 		if (list_empty(&syme->node) || !syme->node.next) {
 			static bool first = true;

tools/perf/util/event.c

@@ -169,12 +169,17 @@ static int perf_event__synthesize_mmap_events(union perf_event *event,
 			continue;
 		pbf += n + 3;
 		if (*pbf == 'x') { /* vm_exec */
+			char anonstr[] = "//anon\n";
 			char *execname = strchr(bf, '/');
 
 			/* Catch VDSO */
 			if (execname == NULL)
 				execname = strstr(bf, "[vdso]");
 
+			/* Catch anonymous mmaps */
+			if ((execname == NULL) && !strstr(bf, "["))
+				execname = anonstr;
+
 			if (execname == NULL)
 				continue;
 

tools/perf/util/event.h

@@ -186,6 +186,6 @@ const char *perf_event__name(unsigned int id);
 
 int perf_event__parse_sample(const union perf_event *event, u64 type,
 			     int sample_size, bool sample_id_all,
-			     struct perf_sample *sample);
+			     struct perf_sample *sample, bool swapped);
 
 #endif /* __PERF_RECORD_H */

tools/perf/util/evlist.c

@@ -113,6 +113,19 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 	}
 }
 
+void perf_evlist__enable(struct perf_evlist *evlist)
+{
+	int cpu, thread;
+	struct perf_evsel *pos;
+
+	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+		list_for_each_entry(pos, &evlist->entries, node) {
+			for (thread = 0; thread < evlist->threads->nr; thread++)
+				ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_ENABLE);
+		}
+	}
+}
+
 int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 {
 	int nfds = evlist->cpus->nr * evlist->threads->nr * evlist->nr_entries;

tools/perf/util/evlist.h

@@ -54,6 +54,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite);
 void perf_evlist__munmap(struct perf_evlist *evlist);
 
 void perf_evlist__disable(struct perf_evlist *evlist);
+void perf_evlist__enable(struct perf_evlist *evlist);
 
 static inline void perf_evlist__set_maps(struct perf_evlist *evlist,
 					 struct cpu_map *cpus,

tools/perf/util/evsel.c

@@ -7,6 +7,8 @@
  * Released under the GPL v2. (and only v2, not any later version)
  */
 
+#include <byteswap.h>
+#include "asm/bug.h"
 #include "evsel.h"
 #include "evlist.h"
 #include "util.h"
@@ -342,10 +344,20 @@ static bool sample_overlap(const union perf_event *event,
 
 int perf_event__parse_sample(const union perf_event *event, u64 type,
 			     int sample_size, bool sample_id_all,
-			     struct perf_sample *data)
+			     struct perf_sample *data, bool swapped)
 {
 	const u64 *array;
 
+	/*
+	 * used for cross-endian analysis. See git commit 65014ab3
+	 * for why this goofiness is needed.
+	 */
+	union {
+		u64 val64;
+		u32 val32[2];
+	} u;
+
+
 	data->cpu = data->pid = data->tid = -1;
 	data->stream_id = data->id = data->time = -1ULL;
 
@@ -366,9 +378,16 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 	}
 
 	if (type & PERF_SAMPLE_TID) {
-		u32 *p = (u32 *)array;
-		data->pid = p[0];
-		data->tid = p[1];
+		u.val64 = *array;
+		if (swapped) {
+			/* undo swap of u64, then swap on individual u32s */
+			u.val64 = bswap_64(u.val64);
+			u.val32[0] = bswap_32(u.val32[0]);
+			u.val32[1] = bswap_32(u.val32[1]);
+		}
+
+		data->pid = u.val32[0];
+		data->tid = u.val32[1];
 		array++;
 	}
 
@@ -395,8 +414,15 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 	}
 
 	if (type & PERF_SAMPLE_CPU) {
-		u32 *p = (u32 *)array;
-		data->cpu = *p;
+
+		u.val64 = *array;
+		if (swapped) {
+			/* undo swap of u64, then swap on individual u32s */
+			u.val64 = bswap_64(u.val64);
+			u.val32[0] = bswap_32(u.val32[0]);
+		}
+
+		data->cpu = u.val32[0];
 		array++;
 	}
 
@@ -423,18 +449,24 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 	}
 
 	if (type & PERF_SAMPLE_RAW) {
-		u32 *p = (u32 *)array;
+		u.val64 = *array;
+		if (WARN_ONCE(swapped,
+			      "Endianness of raw data not corrected!\n")) {
+			/* undo swap of u64, then swap on individual u32s */
+			u.val64 = bswap_64(u.val64);
+			u.val32[0] = bswap_32(u.val32[0]);
+			u.val32[1] = bswap_32(u.val32[1]);
+		}
 
 		if (sample_overlap(event, array, sizeof(u32)))
 			return -EFAULT;
 
-		data->raw_size = *p;
-		p++;
+		data->raw_size = u.val32[0];
 
-		if (sample_overlap(event, p, data->raw_size))
+		if (sample_overlap(event, &u.val32[1], data->raw_size))
 			return -EFAULT;
 
-		data->raw_data = p;
+		data->raw_data = &u.val32[1];
 	}
 
 	return 0;

tools/perf/util/probe-finder.c

@@ -659,7 +659,7 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf)
 		if (!die_find_variable_at(&pf->cu_die, pf->pvar->var, 0, &vr_die))
 			ret = -ENOENT;
 	}
-	if (ret == 0)
+	if (ret >= 0)
 		ret = convert_variable(&vr_die, pf);
 
 	if (ret < 0)

tools/perf/util/session.h

@@ -162,7 +162,8 @@ static inline int perf_session__parse_sample(struct perf_session *session,
 {
 	return perf_event__parse_sample(event, session->sample_type,
 					session->sample_size,
-					session->sample_id_all, sample);
+					session->sample_id_all, sample,
+					session->header.needs_swap);
 }
 
 struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,

tools/perf/util/sort.c

@@ -151,11 +151,17 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	u64 ip_l, ip_r;
 
+	if (!left->ms.sym && !right->ms.sym)
+		return right->level - left->level;
+
+	if (!left->ms.sym || !right->ms.sym)
+		return cmp_null(left->ms.sym, right->ms.sym);
+
 	if (left->ms.sym == right->ms.sym)
 		return 0;
 
-	ip_l = left->ms.sym ? left->ms.sym->start : left->ip;
-	ip_r = right->ms.sym ? right->ms.sym->start : right->ip;
+	ip_l = left->ms.sym->start;
+	ip_r = right->ms.sym->start;
 
 	return (int64_t)(ip_r - ip_l);
 }