perf/core improvements and fixes

index 80a50fdb6d8a..78032d887c1a 100644
@@ -25,12 +25,6 @@
 extern int parse_events_debug;
 #endif
 int parse_events_parse(void *data, void *scanner);
-int parse_events_term__num(struct parse_events_term **term,
-			   int type_term, char *config, u64 num,
-			   YYLTYPE *loc_term, YYLTYPE *loc_val);
-int parse_events_term__str(struct parse_events_term **term,
-			   int type_term, char *config, char *str,
-			   YYLTYPE *loc_term, YYLTYPE *loc_val);
 
 static struct perf_pmu_event_symbol *perf_pmu_events_list;
 /*

@@ -1601,8 +1595,11 @@ static int new_term(struct parse_events_term **_term, int type_val,
 
 int parse_events_term__num(struct parse_events_term **term,
 			   int type_term, char *config, u64 num,
-			   YYLTYPE *loc_term, YYLTYPE *loc_val)
+			   void *loc_term_, void *loc_val_)
 {
+	YYLTYPE *loc_term = loc_term_;
+	YYLTYPE *loc_val = loc_val_;
+
 	return new_term(term, PARSE_EVENTS__TERM_TYPE_NUM, type_term,
 			config, NULL, num,
 			loc_term ? loc_term->first_column : 0,

@@ -1611,8 +1608,11 @@ int parse_events_term__num(struct parse_events_term **term,
 
 int parse_events_term__str(struct parse_events_term **term,
 			   int type_term, char *config, char *str,
-			   YYLTYPE *loc_term, YYLTYPE *loc_val)
+			   void *loc_term_, void *loc_val_)
 {
+	YYLTYPE *loc_term = loc_term_;
+	YYLTYPE *loc_val = loc_val_;
+
 	return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, type_term,
 			config, str, 0,
 			loc_term ? loc_term->first_column : 0,

index e236f1b6ac6f..131f29b2f132 100644
@@ -98,6 +98,12 @@ struct parse_events_terms {
 };
 
 int parse_events__is_hardcoded_term(struct parse_events_term *term);
+int parse_events_term__num(struct parse_events_term **term,
+			   int type_term, char *config, u64 num,
+			   void *loc_term, void *loc_val);
+int parse_events_term__str(struct parse_events_term **term,
+			   int type_term, char *config, char *str,
+			   void *loc_term, void *loc_val);
 int parse_events_term__sym_hw(struct parse_events_term **term,
 			      char *config, unsigned idx);
 int parse_events_term__clone(struct parse_events_term **new,

index 78032d887c1a..2a4d1ec02846 100644
@@ -1659,6 +1659,8 @@ void parse_events_evlist_error(struct parse_events_evlist *data,
 {
 	struct parse_events_error *err = data->error;
 
+	if (!err)
+		return;
 	err->idx = idx;
 	err->str = strdup(str);
 	WARN_ONCE(!err->str, "WARNING: failed to allocate error string");

index e722107f932a..39fe09d5a87e 100644
@@ -1182,7 +1182,7 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset,
 		return -1;
 
 	if (lseek(fd, file_offset, SEEK_SET) == (off_t)-1 ||
-	    readn(fd, &buf, hdr_sz) != (ssize_t)hdr_sz)
+	    readn(fd, buf, hdr_sz) != (ssize_t)hdr_sz)
 		return -1;
 
 	event = (union perf_event *)buf;

@@ -1190,12 +1190,12 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset,
 	if (session->header.needs_swap)
 		perf_event_header__bswap(&event->header);
 
-	if (event->header.size < hdr_sz)
+	if (event->header.size < hdr_sz || event->header.size > buf_sz)
 		return -1;
 
 	rest = event->header.size - hdr_sz;
 
-	if (readn(fd, &buf, rest) != (ssize_t)rest)
+	if (readn(fd, buf, rest) != (ssize_t)rest)
 		return -1;
 
 	if (session->header.needs_swap)

index 92fca2157e5e..56025d90622f 100644
@@ -139,8 +139,10 @@ static int process_sample_event(struct perf_tool *tool,
 	struct report *rep = container_of(tool, struct report, tool);
 	struct addr_location al;
 	struct hist_entry_iter iter = {
-		.hide_unresolved = rep->hide_unresolved,
-		.add_entry_cb = hist_iter__report_callback,
+		.evsel 			= evsel,
+		.sample 		= sample,
+		.hide_unresolved 	= rep->hide_unresolved,
+		.add_entry_cb 		= hist_iter__report_callback,
 	};
 	int ret = 0;
 

@@ -168,8 +170,7 @@ static int process_sample_event(struct perf_tool *tool,
 	if (al.map != NULL)
 		al.map->dso->hit = 1;
 
-	ret = hist_entry_iter__add(&iter, &al, evsel, sample, rep->max_stack,
-				   rep);
+	ret = hist_entry_iter__add(&iter, &al, rep->max_stack, rep);
 	if (ret < 0)
 		pr_debug("problem adding hist entry, skipping event\n");
 out_put:

index a19351728f0f..6b987424d015 100644
@@ -775,7 +775,9 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	if (al.sym == NULL || !al.sym->ignore) {
 		struct hists *hists = evsel__hists(evsel);
 		struct hist_entry_iter iter = {
-			.add_entry_cb = hist_iter__top_callback,
+			.evsel		= evsel,
+			.sample 	= sample,
+			.add_entry_cb 	= hist_iter__top_callback,
 		};
 
 		if (symbol_conf.cumulate_callchain)

@@ -785,8 +787,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 
 		pthread_mutex_lock(&hists->lock);
 
-		err = hist_entry_iter__add(&iter, &al, evsel, sample,
-					   top->max_stack, top);
+		err = hist_entry_iter__add(&iter, &al, top->max_stack, top);
 		if (err < 0)
 			pr_err("Problem incrementing symbol period, skipping event\n");
 

index 620f626e5b35..7d82c8be5e36 100644
@@ -87,6 +87,8 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 			},
 		};
 		struct hist_entry_iter iter = {
+			.evsel = evsel,
+			.sample	= &sample,
 			.hide_unresolved = false,
 		};
 

@@ -104,8 +106,8 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 						  &sample) < 0)
 			goto out;
 
-		if (hist_entry_iter__add(&iter, &al, evsel, &sample,
-					 PERF_MAX_STACK_DEPTH, NULL) < 0) {
+		if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH,
+					 NULL) < 0) {
 			addr_location__put(&al);
 			goto out;
 		}

index 82e1ee52e024..ce48775e6ada 100644
@@ -63,6 +63,8 @@ static int add_hist_entries(struct perf_evlist *evlist,
 				},
 			};
 			struct hist_entry_iter iter = {
+				.evsel = evsel,
+				.sample = &sample,
 				.ops = &hist_iter_normal,
 				.hide_unresolved = false,
 			};

@@ -81,7 +83,7 @@ static int add_hist_entries(struct perf_evlist *evlist,
 							  &sample) < 0)
 				goto out;
 
-			if (hist_entry_iter__add(&iter, &al, evsel, &sample,
+			if (hist_entry_iter__add(&iter, &al,
 						 PERF_MAX_STACK_DEPTH, NULL) < 0) {
 				addr_location__put(&al);
 				goto out;

index fd7ec4f9aeb4..adbebc852cc8 100644
@@ -57,6 +57,8 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 			},
 		};
 		struct hist_entry_iter iter = {
+			.evsel = evsel,
+			.sample = &sample,
 			.ops = &hist_iter_normal,
 			.hide_unresolved = false,
 		};

@@ -70,8 +72,8 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 						  &sample) < 0)
 			goto out;
 
-		if (hist_entry_iter__add(&iter, &al, evsel, &sample,
-					 PERF_MAX_STACK_DEPTH, NULL) < 0) {
+		if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH,
+					 NULL) < 0) {
 			addr_location__put(&al);
 			goto out;
 		}

index 338770679863..2504b5b1a308 100644
@@ -851,19 +851,15 @@ const struct hist_iter_ops hist_iter_cumulative = {
 };
 
 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
-			 struct perf_evsel *evsel, struct perf_sample *sample,
 			 int max_stack_depth, void *arg)
 {
 	int err, err2;
 
-	err = sample__resolve_callchain(sample, &iter->parent, evsel, al,
-					max_stack_depth);
+	err = sample__resolve_callchain(iter->sample, &iter->parent,
+					iter->evsel, al, max_stack_depth);
 	if (err)
 		return err;
 
-	iter->evsel = evsel;
-	iter->sample = sample;
-
 	err = iter->ops->prepare_entry(iter, al);
 	if (err)
 		goto out;

index 9f31b89a527a..5ed8d9c22981 100644
@@ -111,7 +111,6 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 				      u64 weight, u64 transaction,
 				      bool sample_self);
 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
-			 struct perf_evsel *evsel, struct perf_sample *sample,
 			 int max_stack_depth, void *arg);
 
 int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right);

index 2504b5b1a308..f53d017c7c22 100644
@@ -362,10 +362,10 @@ static u8 symbol__parent_filter(const struct symbol *parent)
 	return 0;
 }
 
-static struct hist_entry *add_hist_entry(struct hists *hists,
-					 struct hist_entry *entry,
-					 struct addr_location *al,
-					 bool sample_self)
+static struct hist_entry *hists__findnew_entry(struct hists *hists,
+					       struct hist_entry *entry,
+					       struct addr_location *al,
+					       bool sample_self)
 {
 	struct rb_node **p;
 	struct rb_node *parent = NULL;

@@ -468,7 +468,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 		.transaction = transaction,
 	};
 
-	return add_hist_entry(hists, &entry, al, sample_self);
+	return hists__findnew_entry(hists, &entry, al, sample_self);
 }
 
 static int

@@ -548,9 +548,9 @@ iter_finish_mem_entry(struct hist_entry_iter *iter,
 
 out:
 	/*
-	 * We don't need to free iter->priv (mem_info) here since
-	 * the mem info was either already freed in add_hist_entry() or
-	 * passed to a new hist entry by hist_entry__new().
+	 * We don't need to free iter->priv (mem_info) here since the mem info
+	 * was either already freed in hists__findnew_entry() or passed to a
+	 * new hist entry by hist_entry__new().
 	 */
 	iter->priv = NULL;
 

index b2bb59df65e1..21b7ff382c3f 100644
@@ -2,24 +2,27 @@
 #include "util.h"
 #include <stdlib.h>
 #include <stdio.h>
+#include <linux/atomic.h>
 
 struct comm_str {
 	char *str;
 	struct rb_node rb_node;
-	int ref;
+	atomic_t refcnt;
 };
 
 /* Should perhaps be moved to struct machine */
 static struct rb_root comm_str_root;
 
-static void comm_str__get(struct comm_str *cs)
+static struct comm_str *comm_str__get(struct comm_str *cs)
 {
-	cs->ref++;
+	if (cs)
+		atomic_inc(&cs->refcnt);
+	return cs;
 }
 
 static void comm_str__put(struct comm_str *cs)
 {
-	if (!--cs->ref) {
+	if (cs && atomic_dec_and_test(&cs->refcnt)) {
 		rb_erase(&cs->rb_node, &comm_str_root);
 		zfree(&cs->str);
 		free(cs);

@@ -40,6 +43,8 @@ static struct comm_str *comm_str__alloc(const char *str)
 		return NULL;
 	}
 
+	atomic_set(&cs->refcnt, 0);
+
 	return cs;
 }
 

index daa55910ff28..7ec3188d3cb3 100644
@@ -333,7 +333,7 @@ static void machine__update_thread_pid(struct machine *machine,
 		if (!map_groups__empty(th->mg))
 			pr_err("Discarding thread maps for %d:%d\n",
 			       th->pid_, th->tid);
-		map_groups__delete(th->mg);
+		map_groups__put(th->mg);
 	}
 
 	th->mg = map_groups__get(leader->mg);

index 1b96c8d18435..516e0c25ea16 100644
@@ -440,15 +440,7 @@ void dso__data_close(struct dso *dso)
 	pthread_mutex_unlock(&dso__data_open_lock);
 }
 
-/**
- * dso__data_fd - Get dso's data file descriptor
- * @dso: dso object
- * @machine: machine object
- *
- * External interface to find dso's file, open it and
- * returns file descriptor.
- */
-int dso__data_fd(struct dso *dso, struct machine *machine)
+static void try_to_open_dso(struct dso *dso, struct machine *machine)
 {
 	enum dso_binary_type binary_type_data[] = {
 		DSO_BINARY_TYPE__BUILD_ID_CACHE,

@@ -457,13 +449,8 @@ int dso__data_fd(struct dso *dso, struct machine *machine)
 	};
 	int i = 0;
 
-	if (dso->data.status == DSO_DATA_STATUS_ERROR)
-		return -1;
-
-	pthread_mutex_lock(&dso__data_open_lock);
-
 	if (dso->data.fd >= 0)
-		goto out;
+		return;
 
 	if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) {
 		dso->data.fd = open_dso(dso, machine);

@@ -483,8 +470,25 @@ out:
 		dso->data.status = DSO_DATA_STATUS_OK;
 	else
 		dso->data.status = DSO_DATA_STATUS_ERROR;
+}
+
+/**
+ * dso__data_fd - Get dso's data file descriptor
+ * @dso: dso object
+ * @machine: machine object
+ *
+ * External interface to find dso's file, open it and
+ * returns file descriptor.
+ */
+int dso__data_fd(struct dso *dso, struct machine *machine)
+{
+	if (dso->data.status == DSO_DATA_STATUS_ERROR)
+		return -1;
 
+	pthread_mutex_lock(&dso__data_open_lock);
+	try_to_open_dso(dso, machine);
 	pthread_mutex_unlock(&dso__data_open_lock);
+
 	return dso->data.fd;
 }
 

@@ -609,13 +613,12 @@ dso_cache__read(struct dso *dso, struct machine *machine,
 		 * dso->data.fd might be closed if other thread opened another
 		 * file (dso) due to open file limit (RLIMIT_NOFILE).
 		 */
+		try_to_open_dso(dso, machine);
+
 		if (dso->data.fd < 0) {
-			dso->data.fd = open_dso(dso, machine);
-			if (dso->data.fd < 0) {
-				ret = -errno;
-				dso->data.status = DSO_DATA_STATUS_ERROR;
-				break;
-			}
+			ret = -errno;
+			dso->data.status = DSO_DATA_STATUS_ERROR;
+			break;
 		}
 
 		cache_offset = offset & DSO__DATA_CACHE_MASK;

@@ -702,19 +705,21 @@ static int data_file_size(struct dso *dso, struct machine *machine)
 	if (dso->data.file_size)
 		return 0;
 
+	if (dso->data.status == DSO_DATA_STATUS_ERROR)
+		return -1;
+
 	pthread_mutex_lock(&dso__data_open_lock);
 
 	/*
 	 * dso->data.fd might be closed if other thread opened another
 	 * file (dso) due to open file limit (RLIMIT_NOFILE).
 	 */
+	try_to_open_dso(dso, machine);
+
 	if (dso->data.fd < 0) {
-		dso->data.fd = open_dso(dso, machine);
-		if (dso->data.fd < 0) {
-			ret = -errno;
-			dso->data.status = DSO_DATA_STATUS_ERROR;
-			goto out;
-		}
+		ret = -errno;
+		dso->data.status = DSO_DATA_STATUS_ERROR;
+		goto out;
 	}
 
 	if (fstat(dso->data.fd, &st) < 0) {

index 516e0c25ea16..e95e850dd832 100644
@@ -745,12 +745,6 @@ out:
  */
 off_t dso__data_size(struct dso *dso, struct machine *machine)
 {
-	int fd;
-
-	fd = dso__data_fd(dso, machine);
-	if (fd < 0)
-		return fd;
-
 	if (data_file_size(dso, machine))
 		return -1;
 

index 513e5febbe5a..3e41c61bd861 100644
@@ -99,6 +99,17 @@ struct test_data_offset offsets[] = {
 	},
 };
 
+/* move it from util/dso.c for compatibility */
+static int dso__data_fd(struct dso *dso, struct machine *machine)
+{
+	int fd = dso__data_get_fd(dso, machine);
+
+	if (fd >= 0)
+		dso__data_put_fd(dso);
+
+	return fd;
+}
+
 int test__dso_data(void)
 {
 	struct machine machine;

index e95e850dd832..7e11a700303f 100644
@@ -473,25 +473,35 @@ out:
 }
 
 /**
- * dso__data_fd - Get dso's data file descriptor
+ * dso__data_get_fd - Get dso's data file descriptor
  * @dso: dso object
  * @machine: machine object
  *
  * External interface to find dso's file, open it and
- * returns file descriptor.
+ * returns file descriptor.  It should be paired with
+ * dso__data_put_fd() if it returns non-negative value.
  */
-int dso__data_fd(struct dso *dso, struct machine *machine)
+int dso__data_get_fd(struct dso *dso, struct machine *machine)
 {
 	if (dso->data.status == DSO_DATA_STATUS_ERROR)
 		return -1;
 
-	pthread_mutex_lock(&dso__data_open_lock);
+	if (pthread_mutex_lock(&dso__data_open_lock) < 0)
+		return -1;
+
 	try_to_open_dso(dso, machine);
-	pthread_mutex_unlock(&dso__data_open_lock);
+
+	if (dso->data.fd < 0)
+		pthread_mutex_unlock(&dso__data_open_lock);
 
 	return dso->data.fd;
 }
 
+void dso__data_put_fd(struct dso *dso __maybe_unused)
+{
+	pthread_mutex_unlock(&dso__data_open_lock);
+}
+
 bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by)
 {
 	u32 flag = 1 << by;

@@ -1199,12 +1209,15 @@ size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp)
 enum dso_type dso__type(struct dso *dso, struct machine *machine)
 {
 	int fd;
+	enum dso_type type = DSO__TYPE_UNKNOWN;
 
-	fd = dso__data_fd(dso, machine);
-	if (fd < 0)
-		return DSO__TYPE_UNKNOWN;
+	fd = dso__data_get_fd(dso, machine);
+	if (fd >= 0) {
+		type = dso__type_fd(fd);
+		dso__data_put_fd(dso);
+	}
 
-	return dso__type_fd(fd);
+	return type;
 }
 
 int dso__strerror_load(struct dso *dso, char *buf, size_t buflen)

index b26ec3ab1336..bcec06ad73a2 100644
@@ -240,7 +240,8 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
 
 /*
  * The dso__data_* external interface provides following functions:
- *   dso__data_fd
+ *   dso__data_get_fd
+ *   dso__data_put_fd
  *   dso__data_close
  *   dso__data_size
  *   dso__data_read_offset

@@ -257,8 +258,11 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
  * The current usage of the dso__data_* interface is as follows:
  *
  * Get DSO's fd:
- *   int fd = dso__data_fd(dso, machine);
- *   USE 'fd' SOMEHOW
+ *   int fd = dso__data_get_fd(dso, machine);
+ *   if (fd >= 0) {
+ *       USE 'fd' SOMEHOW
+ *       dso__data_put_fd(dso);
+ *   }
  *
  * Read DSO's data:
  *   n = dso__data_read_offset(dso_0, &machine, 0, buf, BUFSIZE);

@@ -277,7 +281,8 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
  *
  * TODO
 */
-int dso__data_fd(struct dso *dso, struct machine *machine);
+int dso__data_get_fd(struct dso *dso, struct machine *machine);
+void dso__data_put_fd(struct dso *dso __maybe_unused);
 void dso__data_close(struct dso *dso);
 
 off_t dso__data_size(struct dso *dso, struct machine *machine);

index 7b09a443a280..f079b63f0b7f 100644
@@ -269,13 +269,14 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine,
 	u64 offset = dso->data.eh_frame_hdr_offset;
 
 	if (offset == 0) {
-		fd = dso__data_fd(dso, machine);
+		fd = dso__data_get_fd(dso, machine);
 		if (fd < 0)
 			return -EINVAL;
 
 		/* Check the .eh_frame section for unwinding info */
 		offset = elf_section_offset(fd, ".eh_frame_hdr");
 		dso->data.eh_frame_hdr_offset = offset;
+		dso__data_put_fd(dso);
 	}
 
 	if (offset)

@@ -294,13 +295,14 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
 	u64 ofs = dso->data.debug_frame_offset;
 
 	if (ofs == 0) {
-		fd = dso__data_fd(dso, machine);
+		fd = dso__data_get_fd(dso, machine);
 		if (fd < 0)
 			return -EINVAL;
 
 		/* Check the .debug_frame section for unwinding info */
 		ofs = elf_section_offset(fd, ".debug_frame");
 		dso->data.debug_frame_offset = ofs;
+		dso__data_put_fd(dso);
 	}
 
 	*offset = ofs;

@@ -353,10 +355,13 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
 #ifndef NO_LIBUNWIND_DEBUG_FRAME
 	/* Check the .debug_frame section for unwinding info */
 	if (!read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) {
-		int fd = dso__data_fd(map->dso, ui->machine);
+		int fd = dso__data_get_fd(map->dso, ui->machine);
 		int is_exec = elf_is_exec(fd, map->dso->name);
 		unw_word_t base = is_exec ? 0 : map->start;
 
+		if (fd >= 0)
+			dso__data_put_fd(dso);
+
 		memset(&di, 0, sizeof(di));
 		if (dwarf_find_debug_frame(0, &di, ip, base, map->dso->name,
 					   map->start, map->end))

index 2d20c5ff8653..09a62731e035 100644
@@ -775,7 +775,7 @@ struct map *maps__first(struct rb_root *maps)
 	return NULL;
 }
 
-struct map *maps__next(struct map *map)
+struct map *map__next(struct map *map)
 {
 	struct rb_node *next = rb_next(&map->rb_node);
 

index 7f39217d29bf..aba9569165ea 100644
@@ -166,7 +166,7 @@ void maps__insert(struct rb_root *maps, struct map *map);
 void maps__remove(struct rb_root *maps, struct map *map);
 struct map *maps__find(struct rb_root *maps, u64 addr);
 struct map *maps__first(struct rb_root *maps);
-struct map *maps__next(struct map *map);
+struct map *map__next(struct map *map);
 void map_groups__init(struct map_groups *mg, struct machine *machine);
 void map_groups__exit(struct map_groups *mg);
 int map_groups__clone(struct map_groups *mg,

@@ -201,7 +201,7 @@ static inline struct map *map_groups__first(struct map_groups *mg,
 
 static inline struct map *map_groups__next(struct map *map)
 {
-	return maps__next(map);
+	return map__next(map);
 }
 
 struct symbol *map_groups__find_symbol(struct map_groups *mg,

index 16c28a37a9e4..28c4b746baa1 100644
@@ -54,7 +54,6 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 
 		list_add(&comm->list, &thread->comm_list);
 		atomic_set(&thread->refcnt, 0);
-		INIT_LIST_HEAD(&thread->node);
 		RB_CLEAR_NODE(&thread->rb_node);
 	}
 

@@ -70,7 +69,6 @@ void thread__delete(struct thread *thread)
 	struct comm *comm, *tmp;
 
 	BUG_ON(!RB_EMPTY_NODE(&thread->rb_node));
-	BUG_ON(!list_empty(&thread->node));
 
 	thread_stack__free(thread);
 

index 09a62731e035..c1bfd0a12a94 100644
@@ -498,28 +498,6 @@ void map_groups__put(struct map_groups *mg)
 		map_groups__delete(mg);
 }
 
-void map_groups__flush(struct map_groups *mg)
-{
-	int type;
-
-	for (type = 0; type < MAP__NR_TYPES; type++) {
-		struct rb_root *root = &mg->maps[type];
-		struct rb_node *next = rb_first(root);
-
-		while (next) {
-			struct map *pos = rb_entry(next, struct map, rb_node);
-			next = rb_next(&pos->rb_node);
-			rb_erase(&pos->rb_node, root);
-			/*
-			 * We may have references to this map, for
-			 * instance in some hist_entry instances, so
-			 * just move them to a separate list.
-			 */
-			list_add_tail(&pos->node, &mg->removed_maps[pos->type]);
-		}
-	}
-}
-
 struct symbol *map_groups__find_symbol(struct map_groups *mg,
 				       enum map_type type, u64 addr,
 				       struct map **mapp,

index aba9569165ea..f2b27566d986 100644
@@ -233,6 +233,4 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 struct map *map_groups__find_by_name(struct map_groups *mg,
 				     enum map_type type, const char *name);
 
-void map_groups__flush(struct map_groups *mg);
-
 #endif /* __PERF_MAP_H */

index 2a030c5af3aa..f06d89f0b867 100644
@@ -1,2 +1,16 @@
+#ifndef __TOOLS_LINUX_PERF_RBTREE_H
+#define __TOOLS_LINUX_PERF_RBTREE_H
 #include <stdbool.h>
 #include "../../../../include/linux/rbtree.h"
+
+/*
+ * Handy for checking that we are not deleting an entry that is
+ * already in a list, found in block/{blk-throttle,cfq-iosched}.c,
+ * probably should be moved to lib/rbtree.c...
+ */
+static inline void rb_erase_init(struct rb_node *n, struct rb_root *root)
+{
+	rb_erase(n, root);
+	RB_CLEAR_NODE(n);
+}
+#endif /* __TOOLS_LINUX_PERF_RBTREE_H */

index 7ec3188d3cb3..6bf845758ae3 100644
@@ -400,7 +400,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 		 * leader and that would screwed the rb tree.
 		 */
 		if (thread__init_map_groups(th, machine)) {
-			rb_erase(&th->rb_node, &machine->threads);
+			rb_erase_init(&th->rb_node, &machine->threads);
 			RB_CLEAR_NODE(&th->rb_node);
 			thread__delete(th);
 			return NULL;

@@ -1314,7 +1314,7 @@ static void __machine__remove_thread(struct machine *machine, struct thread *th,
 	BUG_ON(atomic_read(&th->refcnt) == 0);
 	if (lock)
 		pthread_rwlock_wrlock(&machine->threads_lock);
-	rb_erase(&th->rb_node, &machine->threads);
+	rb_erase_init(&th->rb_node, &machine->threads);
 	RB_CLEAR_NODE(&th->rb_node);
 	/*
 	 * Move it first to the dead_threads list, then drop the reference,

index 1faa1e67398b..db6021834e8f 100644
@@ -195,7 +195,6 @@ static void put_target_map(struct map *map, bool user)
 {
 	if (map && user) {
 		/* Only the user map needs to be released */
-		dso__delete(map->dso);
 		map__delete(map);
 	}
 }

@@ -1791,7 +1790,6 @@ static int find_perf_probe_point_from_map(struct probe_trace_point *tp,
 
 out:
 	if (map && !is_kprobe) {
-		dso__delete(map->dso);
 		map__delete(map);
 	}
 

@@ -2884,7 +2882,6 @@ int show_available_funcs(const char *target, struct strfilter *_filter,
 	dso__fprintf_symbols_by_name(map->dso, map->type, stdout);
 end:
 	if (user) {
-		dso__delete(map->dso);
 		map__delete(map);
 	}
 	exit_symbol_maps();

index 3d9088003a5b..94ac6924df65 100644
@@ -23,9 +23,10 @@ int test__vmlinux_matches_kallsyms(void)
 	int err = -1;
 	struct rb_node *nd;
 	struct symbol *sym;
-	struct map *kallsyms_map, *vmlinux_map;
+	struct map *kallsyms_map, *vmlinux_map, *map;
 	struct machine kallsyms, vmlinux;
 	enum map_type type = MAP__FUNCTION;
+	struct rb_root *maps = &vmlinux.kmaps.maps[type];
 	u64 mem_start, mem_end;
 
 	/*

@@ -184,8 +185,8 @@ detour:
 
 	pr_info("Maps only in vmlinux:\n");
 
-	for (nd = rb_first(&vmlinux.kmaps.maps[type]); nd; nd = rb_next(nd)) {
-		struct map *pos = rb_entry(nd, struct map, rb_node), *pair;
+	for (map = maps__first(maps); map; map = map__next(map)) {
+		struct map *
 		/*
 		 * If it is the kernel, kallsyms is always "[kernel.kallsyms]", while
 		 * the kernel will have the path for the vmlinux file being used,

@@ -193,22 +194,22 @@ detour:
 		 * both cases.
 		 */
 		pair = map_groups__find_by_name(&kallsyms.kmaps, type,
-						(pos->dso->kernel ?
-							pos->dso->short_name :
-							pos->dso->name));
+						(map->dso->kernel ?
+							map->dso->short_name :
+							map->dso->name));
 		if (pair)
 			pair->priv = 1;
 		else
-			map__fprintf(pos, stderr);
+			map__fprintf(map, stderr);
 	}
 
 	pr_info("Maps in vmlinux with a different name in kallsyms:\n");
 
-	for (nd = rb_first(&vmlinux.kmaps.maps[type]); nd; nd = rb_next(nd)) {
-		struct map *pos = rb_entry(nd, struct map, rb_node), *pair;
+	for (map = maps__first(maps); map; map = map__next(map)) {
+		struct map *pair;
 
-		mem_start = vmlinux_map->unmap_ip(vmlinux_map, pos->start);
-		mem_end = vmlinux_map->unmap_ip(vmlinux_map, pos->end);
+		mem_start = vmlinux_map->unmap_ip(vmlinux_map, map->start);
+		mem_end = vmlinux_map->unmap_ip(vmlinux_map, map->end);
 
 		pair = map_groups__find(&kallsyms.kmaps, type, mem_start);
 		if (pair == NULL || pair->priv)

@@ -217,7 +218,7 @@ detour:
 		if (pair->start == mem_start) {
 			pair->priv = 1;
 			pr_info(" %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as",
-				pos->start, pos->end, pos->pgoff, pos->dso->name);
+				map->start, map->end, map->pgoff, map->dso->name);
 			if (mem_end != pair->end)
 				pr_info(":\n*%" PRIx64 "-%" PRIx64 " %" PRIx64,
 					pair->start, pair->end, pair->pgoff);

@@ -228,12 +229,11 @@ detour:
 
 	pr_info("Maps only in kallsyms:\n");
 
-	for (nd = rb_first(&kallsyms.kmaps.maps[type]);
-	     nd; nd = rb_next(nd)) {
-		struct map *pos = rb_entry(nd, struct map, rb_node);
+	maps = &kallsyms.kmaps.maps[type];
 
-		if (!pos->priv)
-			map__fprintf(pos, stderr);
+	for (map = maps__first(maps); map; map = map__next(map)) {
+		if (!map->priv)
+			map__fprintf(map, stderr);
 	}
 out:
 	machine__exit(&kallsyms);

index a513a51f7330..9d3bba175423 100644
@@ -329,8 +329,9 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 				   struct machine *machine)
 {
 	int rc = 0;
-	struct rb_node *nd;
+	struct map *pos;
 	struct map_groups *kmaps = &machine->kmaps;
+	struct rb_root *maps = &kmaps->maps[MAP__FUNCTION];
 	union perf_event *event = zalloc((sizeof(event->mmap) +
 					  machine->id_hdr_size));
 	if (event == NULL) {

@@ -350,10 +351,8 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 	else
 		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
 
-	for (nd = rb_first(&kmaps->maps[MAP__FUNCTION]);
-	     nd; nd = rb_next(nd)) {
+	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
 		size_t size;
-		struct map *pos = rb_entry(nd, struct map, rb_node);
 
 		if (pos->dso->kernel)
 			continue;

index c1bfd0a12a94..898ab92a98dd 100644
@@ -688,9 +688,10 @@ move_map:
 int map_groups__clone(struct map_groups *mg,
 		      struct map_groups *parent, enum map_type type)
 {
-	struct rb_node *nd;
-	for (nd = rb_first(&parent->maps[type]); nd; nd = rb_next(nd)) {
-		struct map *map = rb_entry(nd, struct map, rb_node);
+	struct map *map;
+	struct rb_root *maps = &parent->maps[type];
+
+	for (map = maps__first(maps); map; map = map__next(map)) {
 		struct map *new = map__clone(map);
 		if (new == NULL)
 			return -ENOMEM;

index db6021834e8f..092256516262 100644
@@ -162,8 +162,9 @@ static u64 kernel_get_symbol_address_by_name(const char *name, bool reloc)
 
 static struct map *kernel_get_module_map(const char *module)
 {
-	struct rb_node *nd;
 	struct map_groups *grp = &host_machine->kmaps;
+	struct rb_root *maps = &grp->maps[MAP__FUNCTION];
+	struct map *pos;
 
 	/* A file path -- this is an offline module */
 	if (module && strchr(module, '/'))

@@ -172,8 +173,7 @@ static struct map *kernel_get_module_map(const char *module)
 	if (!module)
 		module = "kernel";
 
-	for (nd = rb_first(&grp->maps[MAP__FUNCTION]); nd; nd = rb_next(nd)) {
-		struct map *pos = rb_entry(nd, struct map, rb_node);
+	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
 		if (strncmp(pos->dso->short_name + 1, module,
 			    pos->dso->short_name_len - 2) == 0) {
 			return pos;

index 82a31fd0fcf5..00b6b17e74a7 100644
@@ -202,18 +202,16 @@ void symbols__fixup_end(struct rb_root *symbols)
 
 void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
 {
-	struct map *prev, *curr;
-	struct rb_node *nd, *prevnd = rb_first(&mg->maps[type]);
+	struct rb_root *maps = &mg->maps[type];
+	struct map *next, *curr;
 
-	if (prevnd == NULL)
+	curr = maps__first(maps);
+	if (curr == NULL)
 		return;
 
-	curr = rb_entry(prevnd, struct map, rb_node);
-
-	for (nd = rb_next(prevnd); nd; nd = rb_next(nd)) {
-		prev = curr;
-		curr = rb_entry(nd, struct map, rb_node);
-		prev->end = curr->start;
+	for (next = map__next(curr); next; next = map__next(curr)) {
+		curr->end = next->start;
+		curr = next;
 	}
 
 	/*

@@ -1522,11 +1520,10 @@ out:
 struct map *map_groups__find_by_name(struct map_groups *mg,
 				     enum map_type type, const char *name)
 {
-	struct rb_node *nd;
-
-	for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) {
-		struct map *map = rb_entry(nd, struct map, rb_node);
+	struct rb_root *maps = &mg->maps[type];
+	struct map *map;
 
+	for (map = maps__first(maps); map; map = map__next(map)) {
 		if (map->dso && strcmp(map->dso->short_name, name) == 0)
 			return map;
 	}

index 49776f190abf..b7bb42c44694 100644
@@ -61,7 +61,7 @@ const char *const mips_triplets[] = {
 static bool lookup_path(char *name)
 {
 	bool found = false;
-	char *path, *tmp;
+	char *path, *tmp = NULL;
 	char buf[PATH_MAX];
 	char *env = getenv("PATH");
 

index 00b6b17e74a7..b9e3eb581884 100644
@@ -398,7 +398,7 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
 					    const char *name)
 {
 	struct rb_node *n;
-	struct symbol_name_rb_node *s;
+	struct symbol_name_rb_node *s = NULL;
 
 	if (symbols == NULL)
 		return NULL;

index 25d6c737be3e..d4957418657e 100644
@@ -173,7 +173,7 @@ void parse_ftrace_printk(struct pevent *pevent,
 	char *line;
 	char *next = NULL;
 	char *addr_str;
-	char *fmt;
+	char *fmt = NULL;
 
 	line = strtok_r(file, "\n", &next);
 	while (line) {

index 79273ecf92eb..33962612a5e9 100644
@@ -95,6 +95,7 @@ struct work_atoms {
 	u64			total_lat;
 	u64			nb_atoms;
 	u64			total_runtime;
+	int			num_merged;
 };
 
 typedef int (*sort_fn_t)(struct work_atoms *, struct work_atoms *);

@@ -168,9 +169,10 @@ struct perf_sched {
 	u64		 all_runtime;
 	u64		 all_count;
 	u64		 cpu_last_switched[MAX_CPUS];
-	struct rb_root	 atom_root, sorted_atom_root;
+	struct rb_root	 atom_root, sorted_atom_root, merged_atom_root;
 	struct list_head sort_list, cmp_pid;
 	bool force;
+	bool skip_merge;
 };
 
 static u64 get_nsecs(void)

@@ -1182,7 +1184,10 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_
 	sched->all_runtime += work_list->total_runtime;
 	sched->all_count   += work_list->nb_atoms;
 
-	ret = printf("  %s:%d ", thread__comm_str(work_list->thread), work_list->thread->tid);
+	if (work_list->num_merged > 1)
+		ret = printf("  %s:(%d) ", thread__comm_str(work_list->thread), work_list->num_merged);
+	else
+		ret = printf("  %s:%d ", thread__comm_str(work_list->thread), work_list->thread->tid);
 
 	for (i = 0; i < 24 - ret; i++)
 		printf(" ");

@@ -1302,17 +1307,22 @@ static int sort_dimension__add(const char *tok, struct list_head *list)
 static void perf_sched__sort_lat(struct perf_sched *sched)
 {
 	struct rb_node *node;
-
+	struct rb_root *root = &sched->atom_root;
+again:
 	for (;;) {
 		struct work_atoms *data;
-		node = rb_first(&sched->atom_root);
+		node = rb_first(root);
 		if (!node)
 			break;
 
-		rb_erase(node, &sched->atom_root);
+		rb_erase(node, root);
 		data = rb_entry(node, struct work_atoms, node);
 		__thread_latency_insert(&sched->sorted_atom_root, data, &sched->sort_list);
 	}
+	if (root == &sched->atom_root) {
+		root = &sched->merged_atom_root;
+		goto again;
+	}
 }
 
 static int process_sched_wakeup_event(struct perf_tool *tool,

@@ -1572,6 +1582,59 @@ static void print_bad_events(struct perf_sched *sched)
 	}
 }
 
+static void __merge_work_atoms(struct rb_root *root, struct work_atoms *data)
+{
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+	struct work_atoms *this;
+	const char *comm = thread__comm_str(data->thread), *this_comm;
+
+	while (*new) {
+		int cmp;
+
+		this = container_of(*new, struct work_atoms, node);
+		parent = *new;
+
+		this_comm = thread__comm_str(this->thread);
+		cmp = strcmp(comm, this_comm);
+		if (cmp > 0) {
+			new = &((*new)->rb_left);
+		} else if (cmp < 0) {
+			new = &((*new)->rb_right);
+		} else {
+			this->num_merged++;
+			this->total_runtime += data->total_runtime;
+			this->nb_atoms += data->nb_atoms;
+			this->total_lat += data->total_lat;
+			list_splice(&data->work_list, &this->work_list);
+			if (this->max_lat < data->max_lat) {
+				this->max_lat = data->max_lat;
+				this->max_lat_at = data->max_lat_at;
+			}
+			zfree(&data);
+			return;
+		}
+	}
+
+	data->num_merged++;
+	rb_link_node(&data->node, parent, new);
+	rb_insert_color(&data->node, root);
+}
+
+static void perf_sched__merge_lat(struct perf_sched *sched)
+{
+	struct work_atoms *data;
+	struct rb_node *node;
+
+	if (sched->skip_merge)
+		return;
+
+	while ((node = rb_first(&sched->atom_root))) {
+		rb_erase(node, &sched->atom_root);
+		data = rb_entry(node, struct work_atoms, node);
+		__merge_work_atoms(&sched->merged_atom_root, data);
+	}
+}
+
 static int perf_sched__lat(struct perf_sched *sched)
 {
 	struct rb_node *next;

@@ -1581,6 +1644,7 @@ static int perf_sched__lat(struct perf_sched *sched)
 	if (perf_sched__read_events(sched))
 		return -1;
 
+	perf_sched__merge_lat(sched);
 	perf_sched__sort_lat(sched);
 
 	printf("\n -----------------------------------------------------------------------------------------------------------------\n");

@@ -1732,6 +1796,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 		.profile_cpu	      = -1,
 		.next_shortname1      = 'A',
 		.next_shortname2      = '0',
+		.skip_merge           = 0,
 	};
 	const struct option latency_options[] = {
 	OPT_STRING('s', "sort", &sched.sort_order, "key[,key2...]",

@@ -1742,6 +1807,8 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "CPU to profile on"),
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
 		    "dump raw trace in ASCII"),
+	OPT_BOOLEAN('p', "pids", &sched.skip_merge,
+		    "latency stats per pid instead of per comm"),
 	OPT_END()
 	};
 	const struct option replay_options[] = {

index 244c66f89891..5d3ab7c8ceaf 100644
@@ -442,6 +442,10 @@ static struct perf_pmu *pmu_lookup(const char *name)
 	LIST_HEAD(aliases);
 	__u32 type;
 
+	/* No support for intel_bts or intel_pt so disallow them */
+	if (!strcmp(name, "intel_bts") || !strcmp(name, "intel_pt"))
+		return NULL;
+
 	/*
 	 * The pmu data we store & need consists of the pmu
 	 * type value and format definitions. Load both right

index df66966cfde7..734c4d2a9208 100644
@@ -884,6 +884,7 @@ int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
 		fprintf(stdout, " type: %u\n", type);
 
 	switch (type) {
+	case PERF_AUXTRACE_INTEL_PT:
 	case PERF_AUXTRACE_UNKNOWN:
 	default:
 		return -EINVAL;

index a171abbe7301..ed9874303b83 100644
@@ -39,6 +39,7 @@ struct events_stats;
 
 enum auxtrace_type {
 	PERF_AUXTRACE_UNKNOWN,
+	PERF_AUXTRACE_INTEL_PT,
 };
 
 enum itrace_period_type {

400 lines not on this page · raw message

64 lines not on this page · raw message

246 lines not on this page · raw message

65 lines not on this page · raw message

155 lines not on this page · raw message

52 lines not on this page · raw message

1,758 lines not on this page · raw message

102 lines not on this page · raw message

752 lines not on this page · raw message

1,889 lines not on this page · raw message

51 lines not on this page · raw message

new file mode 100644
index 000000000000..e7654b506312
@@ -0,0 +1,38 @@
+/*
+ * auxtrace.c: AUX area tracing support
+ * Copyright (c) 2013-2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include "../../util/header.h"
+#include "../../util/auxtrace.h"
+#include "../../util/intel-pt.h"
+
+struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist __maybe_unused,
+					      int *err)
+{
+	char buffer[64];
+	int ret;
+
+	*err = 0;
+
+	ret = get_cpuid(buffer, sizeof(buffer));
+	if (ret) {
+		*err = ret;
+		return NULL;
+	}
+
+	if (!strncmp(buffer, "GenuineIntel,", 13))
+		return intel_pt_recording_init(err);
+
+	return NULL;
+}

new file mode 100644
index 000000000000..fd11cc3ce780
@@ -0,0 +1,15 @@
+#include <string.h>
+
+#include <linux/perf_event.h>
+
+#include "../../util/intel-pt.h"
+#include "../../util/pmu.h"
+
+struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)
+{
+#ifdef HAVE_AUXTRACE_SUPPORT
+	if (!strcmp(pmu->name, INTEL_PT_PMU_NAME))
+		return intel_pt_pmu_default_config(pmu);
+#endif
+	return NULL;
+}

index 734c4d2a9208..8b7d59a7cc9e 100644
@@ -47,6 +47,8 @@
 #include "debug.h"
 #include "parse-options.h"
 
+#include "intel-pt.h"
+
 int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
 			struct auxtrace_mmap_params *mp,
 			void *userpg, int fd)

@@ -876,7 +878,7 @@ static bool auxtrace__dont_decode(struct perf_session *session)
 
 int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
 				      union perf_event *event,
-				      struct perf_session *session __maybe_unused)
+				      struct perf_session *session)
 {
 	enum auxtrace_type type = event->auxtrace_info.type;
 

@@ -885,6 +887,7 @@ int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
 
 	switch (type) {
 	case PERF_AUXTRACE_INTEL_PT:
+		return intel_pt_process_auxtrace_info(event, session);
 	case PERF_AUXTRACE_UNKNOWN:
 	default:
 		return -EINVAL;

index 5d3ab7c8ceaf..fddad8ba4b39 100644
@@ -442,8 +442,8 @@ static struct perf_pmu *pmu_lookup(const char *name)
 	LIST_HEAD(aliases);
 	__u32 type;
 
-	/* No support for intel_bts or intel_pt so disallow them */
-	if (!strcmp(name, "intel_bts") || !strcmp(name, "intel_pt"))
+	/* No support for intel_bts so disallow it */
+	if (!strcmp(name, "intel_bts"))
 		return NULL;
 
 	/*

index 8b7d59a7cc9e..2d57759d5b69 100644
@@ -1186,6 +1186,13 @@ static int __auxtrace_mmap__read(struct auxtrace_mmap *mm,
 		data2 = NULL;
 	}
 
+	if (itr->alignment) {
+		unsigned int unwanted = len1 % itr->alignment;
+
+		len1 -= unwanted;
+		size -= unwanted;
+	}
+
 	/* padding must be written by fn() e.g. record__process_auxtrace() */
 	padding = size & 7;
 	if (padding)

index ed9874303b83..7d12f33a3a06 100644
@@ -304,6 +304,7 @@ struct auxtrace_record {
 				      const char *str);
 	u64 (*reference)(struct auxtrace_record *itr);
 	int (*read_finish)(struct auxtrace_record *itr, int idx);
+	unsigned int alignment;
 };
 
 #ifdef HAVE_AUXTRACE_SUPPORT

65 lines not on this page · raw message

458 lines not on this page · raw message

index fd11cc3ce780..79fe07158d00 100644
@@ -3,6 +3,7 @@
 #include <linux/perf_event.h>
 
 #include "../../util/intel-pt.h"
+#include "../../util/intel-bts.h"
 #include "../../util/pmu.h"
 
 struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused)

@@ -10,6 +11,8 @@ struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __mayb
 #ifdef HAVE_AUXTRACE_SUPPORT
 	if (!strcmp(pmu->name, INTEL_PT_PMU_NAME))
 		return intel_pt_pmu_default_config(pmu);
+	if (!strcmp(pmu->name, INTEL_BTS_PMU_NAME))
+		pmu->selectable = true;
 #endif
 	return NULL;
 }

index 2d57759d5b69..aa93ab1ce63a 100644
@@ -48,6 +48,7 @@
 #include "parse-options.h"
 
 #include "intel-pt.h"
+#include "intel-bts.h"
 
 int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
 			struct auxtrace_mmap_params *mp,

@@ -888,6 +889,8 @@ int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
 	switch (type) {
 	case PERF_AUXTRACE_INTEL_PT:
 		return intel_pt_process_auxtrace_info(event, session);
+	case PERF_AUXTRACE_INTEL_BTS:
+		return intel_bts_process_auxtrace_info(event, session);
 	case PERF_AUXTRACE_UNKNOWN:
 	default:
 		return -EINVAL;

index 7d12f33a3a06..bf72b77a588a 100644
@@ -40,6 +40,7 @@ struct events_stats;
 enum auxtrace_type {
 	PERF_AUXTRACE_UNKNOWN,
 	PERF_AUXTRACE_INTEL_PT,
+	PERF_AUXTRACE_INTEL_BTS,
 };
 
 enum itrace_period_type {

793 lines not on this page · raw message

43 lines not on this page · raw message

index fddad8ba4b39..244c66f89891 100644
@@ -442,10 +442,6 @@ static struct perf_pmu *pmu_lookup(const char *name)
 	LIST_HEAD(aliases);
 	__u32 type;
 
-	/* No support for intel_bts so disallow it */
-	if (!strcmp(name, "intel_bts"))
-		return NULL;
-
 	/*
 	 * The pmu data we store & need consists of the pmu
 	 * type value and format definitions. Load both right

index 6d66879e1e33..9c25bfadb4f3 100644
@@ -876,6 +876,8 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
 	sample.stream_id = ptq->pt->branches_id;
 	sample.period = 1;
 	sample.cpu = ptq->cpu;
+	sample.flags = ptq->flags;
+	sample.insn_len = ptq->insn_len;
 
 	if (pt->branches_filter && !(pt->branches_filter & ptq->flags))
 		return 0;

@@ -918,6 +920,8 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
 	sample.stream_id = ptq->pt->instructions_id;
 	sample.period = ptq->pt->instructions_sample_period;
 	sample.cpu = ptq->cpu;
+	sample.flags = ptq->flags;
+	sample.insn_len = ptq->insn_len;
 
 	if (pt->synth_opts.callchain) {
 		thread_stack__sample(ptq->thread, ptq->chain,

index 48bcbd607ef7..b068860d4940 100644
@@ -30,6 +30,7 @@
 #include "debug.h"
 #include "tsc.h"
 #include "auxtrace.h"
+#include "intel-pt-decoder/intel-pt-insn-decoder.h"
 #include "intel-bts.h"
 
 #define MAX_TIMESTAMP (~0ULL)

@@ -58,6 +59,7 @@ struct intel_bts {
 	bool				cap_user_time_zero;
 	struct itrace_synth_opts	synth_opts;
 	bool				sample_branches;
+	u32				branches_filter;
 	u64				branches_sample_type;
 	u64				branches_id;
 	size_t				branches_event_size;

@@ -74,6 +76,8 @@ struct intel_bts_queue {
 	pid_t			tid;
 	int			cpu;
 	u64			time;
+	struct intel_pt_insn	intel_pt_insn;
+	u32			sample_flags;
 };
 
 struct branch {

@@ -281,6 +285,8 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 	sample.stream_id = btsq->bts->branches_id;
 	sample.period = 1;
 	sample.cpu = btsq->cpu;
+	sample.flags = btsq->sample_flags;
+	sample.insn_len = btsq->intel_pt_insn.length;
 
 	if (bts->synth_opts.inject) {
 		event.sample.header.size = bts->branches_event_size;

@@ -300,11 +306,115 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 	return ret;
 }
 
+static int intel_bts_get_next_insn(struct intel_bts_queue *btsq, u64 ip)
+{
+	struct machine *machine = btsq->bts->machine;
+	struct thread *thread;
+	struct addr_location al;
+	unsigned char buf[1024];
+	size_t bufsz;
+	ssize_t len;
+	int x86_64;
+	uint8_t cpumode;
+
+	bufsz = intel_pt_insn_max_size();
+
+	if (machine__kernel_ip(machine, ip))
+		cpumode = PERF_RECORD_MISC_KERNEL;
+	else
+		cpumode = PERF_RECORD_MISC_USER;
+
+	thread = machine__find_thread(machine, -1, btsq->tid);
+	if (!thread)
+		return -1;
+
+	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, ip, &al);
+	if (!al.map || !al.map->dso)
+		return -1;
+
+	len = dso__data_read_addr(al.map->dso, al.map, machine, ip, buf, bufsz);
+	if (len <= 0)
+		return -1;
+
+	/* Load maps to ensure dso->is_64_bit has been updated */
+	map__load(al.map, machine->symbol_filter);
+
+	x86_64 = al.map->dso->is_64_bit;
+
+	if (intel_pt_get_insn(buf, len, x86_64, &btsq->intel_pt_insn))
+		return -1;
+
+	return 0;
+}
+
+static int intel_bts_synth_error(struct intel_bts *bts, int cpu, pid_t pid,
+				 pid_t tid, u64 ip)
+{
+	union perf_event event;
+	int err;
+
+	auxtrace_synth_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE,
+			     INTEL_BTS_ERR_NOINSN, cpu, pid, tid, ip,
+			     "Failed to get instruction");
+
+	err = perf_session__deliver_synth_event(bts->session, &event, NULL);
+	if (err)
+		pr_err("Intel BTS: failed to deliver error event, error %d\n",
+		       err);
+
+	return err;
+}
+
+static int intel_bts_get_branch_type(struct intel_bts_queue *btsq,
+				     struct branch *branch)
+{
+	int err;
+
+	if (!branch->from) {
+		if (branch->to)
+			btsq->sample_flags = PERF_IP_FLAG_BRANCH |
+					     PERF_IP_FLAG_TRACE_BEGIN;
+		else
+			btsq->sample_flags = 0;
+		btsq->intel_pt_insn.length = 0;
+	} else if (!branch->to) {
+		btsq->sample_flags = PERF_IP_FLAG_BRANCH |
+				     PERF_IP_FLAG_TRACE_END;
+		btsq->intel_pt_insn.length = 0;
+	} else {
+		err = intel_bts_get_next_insn(btsq, branch->from);
+		if (err) {
+			btsq->sample_flags = 0;
+			btsq->intel_pt_insn.length = 0;
+			if (!btsq->bts->synth_opts.errors)
+				return 0;
+			err = intel_bts_synth_error(btsq->bts, btsq->cpu,
+						    btsq->pid, btsq->tid,
+						    branch->from);
+			return err;
+		}
+		btsq->sample_flags = intel_pt_insn_type(btsq->intel_pt_insn.op);
+		/* Check for an async branch into the kernel */
+		if (!machine__kernel_ip(btsq->bts->machine, branch->from) &&
+		    machine__kernel_ip(btsq->bts->machine, branch->to) &&
+		    btsq->sample_flags != (PERF_IP_FLAG_BRANCH |
+					   PERF_IP_FLAG_CALL |
+					   PERF_IP_FLAG_SYSCALLRET))
+			btsq->sample_flags = PERF_IP_FLAG_BRANCH |
+					     PERF_IP_FLAG_CALL |
+					     PERF_IP_FLAG_ASYNC |
+					     PERF_IP_FLAG_INTERRUPT;
+	}
+
+	return 0;
+}
+
 static int intel_bts_process_buffer(struct intel_bts_queue *btsq,
 				    struct auxtrace_buffer *buffer)
 {
 	struct branch *branch;
-	size_t sz;
+	size_t sz, bsz = sizeof(struct branch);
+	u32 filter = btsq->bts->branches_filter;
 	int err = 0;
 
 	if (buffer->use_data) {

@@ -318,14 +428,15 @@ static int intel_bts_process_buffer(struct intel_bts_queue *btsq,
 	if (!btsq->bts->sample_branches)
 		return 0;
 
-	while (sz > sizeof(struct branch)) {
+	for (; sz > bsz; branch += 1, sz -= bsz) {
 		if (!branch->from && !branch->to)
 			continue;
+		intel_bts_get_branch_type(btsq, branch);
+		if (filter && !(filter & btsq->sample_flags))
+			continue;
 		err = intel_bts_synth_branch_sample(btsq, branch);
 		if (err)
 			break;
-		branch += 1;
-		sz -= sizeof(struct branch);
 	}
 	return err;
 }

@@ -771,6 +882,13 @@ int intel_bts_process_auxtrace_info(union perf_event *event,
 	else
 		itrace_synth_opts__set_default(&bts->synth_opts);
 
+	if (bts->synth_opts.calls)
+		bts->branches_filter |= PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC |
+					PERF_IP_FLAG_TRACE_END;
+	if (bts->synth_opts.returns)
+		bts->branches_filter |= PERF_IP_FLAG_RETURN |
+					PERF_IP_FLAG_TRACE_BEGIN;
+
 	err = intel_bts_synth_events(bts, session);
 	if (err)
 		goto err_free_queues;

index 9c25bfadb4f3..5a59fd8e79ae 100644
@@ -265,7 +265,7 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
 	if (!old_buffer || ptq->pt->sampling_mode || (ptq->pt->snapshot_mode &&
 						      !buffer->consecutive)) {
 		b->consecutive = false;
-		b->trace_nr = buffer->buffer_nr;
+		b->trace_nr = buffer->buffer_nr + 1;
 	} else {
 		b->consecutive = true;
 	}

@@ -1075,6 +1075,8 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 		thread_stack__event(ptq->thread, ptq->flags, state->from_ip,
 				    state->to_ip, ptq->insn_len,
 				    state->trace_nr);
+	else
+		thread_stack__set_trace_nr(ptq->thread, state->trace_nr);
 
 	if (pt->sample_branches) {
 		err = intel_pt_synth_branch_sample(ptq);

index b068860d4940..cd7bde33b635 100644
@@ -27,6 +27,8 @@
 #include "machine.h"
 #include "session.h"
 #include "util.h"
+#include "thread.h"
+#include "thread-stack.h"
 #include "debug.h"
 #include "tsc.h"
 #include "auxtrace.h"

@@ -443,19 +445,22 @@ static int intel_bts_process_buffer(struct intel_bts_queue *btsq,
 
 static int intel_bts_process_queue(struct intel_bts_queue *btsq, u64 *timestamp)
 {
-	struct auxtrace_buffer *buffer = btsq->buffer;
+	struct auxtrace_buffer *buffer = btsq->buffer, *old_buffer = buffer;
 	struct auxtrace_queue *queue;
+	struct thread *thread;
 	int err;
 
 	if (btsq->done)
 		return 1;
 
 	if (btsq->pid == -1) {
-		struct thread *thread;
-
-		thread = machine__find_thread(btsq->bts->machine, -1, btsq->tid);
+		thread = machine__find_thread(btsq->bts->machine, -1,
+					      btsq->tid);
 		if (thread)
 			btsq->pid = thread->pid_;
+	} else {
+		thread = machine__findnew_thread(btsq->bts->machine, btsq->pid,
+						 btsq->tid);
 	}
 
 	queue = &btsq->bts->queues.queue_array[btsq->queue_nr];

@@ -485,6 +490,11 @@ static int intel_bts_process_queue(struct intel_bts_queue *btsq, u64 *timestamp)
 	    intel_bts_do_fix_overlap(queue, buffer))
 		return -ENOMEM;
 
+	if (!btsq->bts->synth_opts.callchain && thread &&
+	    (!old_buffer || btsq->bts->sampling_mode ||
+	     (btsq->bts->snapshot_mode && !buffer->consecutive)))
+		thread_stack__set_trace_nr(thread, buffer->buffer_nr + 1);
+
 	err = intel_bts_process_buffer(btsq, buffer);
 
 	auxtrace_buffer__drop_data(buffer);