[GIT PULL 00/12] perf/core improvements, fixes and cleanups

mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed

* [GIT PULL 00/12] perf/core improvements, fixes and cleanups
@ 2011-03-15 20:04 Arnaldo Carvalho de Melo
  2011-03-15 20:04 ` [PATCH 01/12] perf top: Remove redundant perf_top->sym_counter Arnaldo Carvalho de Melo
                   ` (12 more replies)
  0 siblings, 13 replies; 14+ messages in thread
From: Arnaldo Carvalho de Melo @ 2011-03-15 20:04 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, Arnaldo Carvalho de Melo, David Ahern,
	Frederic Weisbecker, Ingo Molnar, Mike Galbraith, Paul Mackerras,
	Peter Zijlstra, Stephane Eranian, Thomas Gleixner, Tom Zanussi,
	Arnaldo Carvalho de Melo

Hi Ingo,

        Please consider pulling from:

git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux-2.6 perf/core

Regards,

- Arnaldo

Arnaldo Carvalho de Melo (5):
  perf top: Remove redundant perf_top->sym_counter
  perf top: Remove redundant syme->origin field
  perf symbols: Rename dso->origin to dso->symtab_type
  perf symbol: Move sym_entry->skip to symbol->ignore
  perf evlist: New command to list the names of events present in a perf.data file

David Ahern (6):
  perf script: Change process_event prototype
  perf tracing: Remove print_graph_cpu and print_graph_proc from trace-event-parse
  perf script: Move printing of 'common' data from print_event and rename
  perf script: Support custom field selection for output
  perf script: Add support for dumping symbols
  perf script: Add support for H/W and S/W events

Frederic Weisbecker (1):
  perf stat: Provide support for filters

 tools/perf/Documentation/perf-evlist.txt           |   26 ++
 tools/perf/Documentation/perf-script.txt           |   22 ++
 tools/perf/Makefile                                |    1 +
 tools/perf/builtin-evlist.c                        |   54 ++++
 tools/perf/builtin-script.c                        |  300 ++++++++++++++++++--
 tools/perf/builtin-stat.c                          |    8 +
 tools/perf/builtin-top.c                           |   20 +-
 tools/perf/builtin.h                               |    1 +
 tools/perf/command-list.txt                        |    1 +
 tools/perf/perf.c                                  |    1 +
 tools/perf/util/annotate.c                         |    2 +-
 tools/perf/util/parse-events.c                     |   22 ++
 tools/perf/util/parse-events.h                     |    1 +
 .../perf/util/scripting-engines/trace-event-perl.c |   11 +-
 .../util/scripting-engines/trace-event-python.c    |   11 +-
 tools/perf/util/session.c                          |   61 ++++
 tools/perf/util/session.h                          |    4 +
 tools/perf/util/symbol.c                           |   64 ++--
 tools/perf/util/symbol.h                           |   31 ++-
 tools/perf/util/top.c                              |    6 +-
 tools/perf/util/top.h                              |    4 +-
 tools/perf/util/trace-event-parse.c                |  110 +-------
 tools/perf/util/trace-event-scripting.c            |    9 +-
 tools/perf/util/trace-event.h                      |   10 +-
 24 files changed, 580 insertions(+), 200 deletions(-)
 create mode 100644 tools/perf/Documentation/perf-evlist.txt
 create mode 100644 tools/perf/builtin-evlist.c


^ permalink raw reply	[flat|nested] 14+ messages in thread

* [PATCH 01/12] perf top: Remove redundant perf_top->sym_counter
  2011-03-15 20:04 [GIT PULL 00/12] perf/core improvements, fixes and cleanups Arnaldo Carvalho de Melo
@ 2011-03-15 20:04 ` Arnaldo Carvalho de Melo
  2011-03-15 20:04 ` [PATCH 02/12] perf top: Remove redundant syme->origin field Arnaldo Carvalho de Melo
                   ` (11 subsequent siblings)
  12 siblings, 0 replies; 14+ messages in thread
From: Arnaldo Carvalho de Melo @ 2011-03-15 20:04 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Frederic Weisbecker,
	Ingo Molnar, Mike Galbraith, Paul Mackerras, Peter Zijlstra,
	Stephane Eranian, Tom Zanussi

From: Arnaldo Carvalho de Melo <acme@redhat.com>

We can get that counter index from perf_top->sym_evsel->idx instead.

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-top.c |   11 ++++++-----
 tools/perf/util/top.c    |    2 +-
 tools/perf/util/top.h    |    2 +-
 3 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 80c9e06..4bf6e02 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -515,24 +515,25 @@ static void handle_keypress(struct perf_session *session, int c)
 			break;
 		case 'E':
 			if (top.evlist->nr_entries > 1) {
+				int counter;
 				fprintf(stderr, "\nAvailable events:");
 
 				list_for_each_entry(top.sym_evsel, &top.evlist->entries, node)
 					fprintf(stderr, "\n\t%d %s", top.sym_evsel->idx, event_name(top.sym_evsel));
 
-				prompt_integer(&top.sym_counter, "Enter details event counter");
+				prompt_integer(&counter, "Enter details event counter");
 
-				if (top.sym_counter >= top.evlist->nr_entries) {
+				if (counter >= top.evlist->nr_entries) {
 					top.sym_evsel = list_entry(top.evlist->entries.next, struct perf_evsel, node);
-					top.sym_counter = 0;
 					fprintf(stderr, "Sorry, no such event, using %s.\n", event_name(top.sym_evsel));
 					sleep(1);
 					break;
 				}
 				list_for_each_entry(top.sym_evsel, &top.evlist->entries, node)
-					if (top.sym_evsel->idx == top.sym_counter)
+					if (top.sym_evsel->idx == counter)
 						break;
-			} else top.sym_counter = 0;
+			} else
+				top.sym_evsel = list_entry(top.evlist->entries.next, struct perf_evsel, node);
 			break;
 		case 'f':
 			prompt_integer(&top.count_filter, "Enter display event count filter");
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
index 75cfe4d..fcfb777 100644
--- a/tools/perf/util/top.c
+++ b/tools/perf/util/top.c
@@ -171,7 +171,7 @@ float perf_top__decay_samples(struct perf_top *top, struct rb_root *root)
 {
 	struct sym_entry *syme, *n;
 	float sum_ksamples = 0.0;
-	int snap = !top->display_weighted ? top->sym_counter : 0, j;
+	int snap = !top->display_weighted ? top->sym_evsel->idx : 0, j;
 
 	/* Sort the active symbols */
 	pthread_mutex_lock(&top->active_symbols_lock);
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index 96d1cb7..96a7831 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -41,7 +41,7 @@ struct perf_top {
 	u64		   exact_samples;
 	u64		   guest_us_samples, guest_kernel_samples;
 	int		   print_entries, count_filter, delay_secs;
-	int		   display_weighted, freq, rb_entries, sym_counter;
+	int		   display_weighted, freq, rb_entries;
 	pid_t		   target_pid, target_tid;
 	bool		   hide_kernel_symbols, hide_user_symbols, zero;
 	const char	   *cpu_list;
-- 
1.6.2.5


^ permalink raw reply	[flat|nested] 14+ messages in thread

* [PATCH 02/12] perf top: Remove redundant syme->origin field
  2011-03-15 20:04 [GIT PULL 00/12] perf/core improvements, fixes and cleanups Arnaldo Carvalho de Melo
  2011-03-15 20:04 ` [PATCH 01/12] perf top: Remove redundant perf_top->sym_counter Arnaldo Carvalho de Melo
@ 2011-03-15 20:04 ` Arnaldo Carvalho de Melo
  2011-03-15 20:04 ` [PATCH 03/12] perf symbols: Rename dso->origin to dso->symtab_type Arnaldo Carvalho de Melo
                   ` (10 subsequent siblings)
  12 siblings, 0 replies; 14+ messages in thread
From: Arnaldo Carvalho de Melo @ 2011-03-15 20:04 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Frederic Weisbecker,
	Ingo Molnar, Mike Galbraith, Paul Mackerras, Peter Zijlstra,
	Stephane Eranian, Tom Zanussi

From: Arnaldo Carvalho de Melo <acme@redhat.com>

We can get it from syme->map->dso->kernel (that should be renamed to
origin, but leave this for another patch).

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-top.c |    1 -
 tools/perf/util/top.c    |    4 ++--
 tools/perf/util/top.h    |    1 -
 3 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 4bf6e02..4976400 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -782,7 +782,6 @@ static void perf_event__process_sample(const union perf_event *event,
 	if (!syme->skip) {
 		struct perf_evsel *evsel;
 
-		syme->origin = origin;
 		evsel = perf_evlist__id2evsel(top.evlist, sample->id);
 		assert(evsel != NULL);
 		syme->count[evsel->idx]++;
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
index fcfb777..a11f607 100644
--- a/tools/perf/util/top.c
+++ b/tools/perf/util/top.c
@@ -184,9 +184,9 @@ float perf_top__decay_samples(struct perf_top *top, struct rb_root *root)
 		if (syme->snap_count != 0) {
 
 			if ((top->hide_user_symbols &&
-			     syme->origin == PERF_RECORD_MISC_USER) ||
+			     syme->map->dso->kernel == DSO_TYPE_USER) ||
 			    (top->hide_kernel_symbols &&
-			     syme->origin == PERF_RECORD_MISC_KERNEL)) {
+			     syme->map->dso->kernel == DSO_TYPE_KERNEL)) {
 				perf_top__remove_active_sym(top, syme);
 				continue;
 			}
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index 96a7831..ba111b2 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -17,7 +17,6 @@ struct sym_entry {
 	unsigned long		snap_count;
 	double			weight;
 	int			skip;
-	u8			origin;
 	struct map		*map;
 	unsigned long		count[0];
 };
-- 
1.6.2.5


^ permalink raw reply	[flat|nested] 14+ messages in thread

* [PATCH 03/12] perf symbols: Rename dso->origin to dso->symtab_type
  2011-03-15 20:04 [GIT PULL 00/12] perf/core improvements, fixes and cleanups Arnaldo Carvalho de Melo
  2011-03-15 20:04 ` [PATCH 01/12] perf top: Remove redundant perf_top->sym_counter Arnaldo Carvalho de Melo
  2011-03-15 20:04 ` [PATCH 02/12] perf top: Remove redundant syme->origin field Arnaldo Carvalho de Melo
@ 2011-03-15 20:04 ` Arnaldo Carvalho de Melo
  2011-03-15 20:04 ` [PATCH 04/12] perf symbol: Move sym_entry->skip to symbol->ignore Arnaldo Carvalho de Melo
                   ` (9 subsequent siblings)
  12 siblings, 0 replies; 14+ messages in thread
From: Arnaldo Carvalho de Melo @ 2011-03-15 20:04 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Frederic Weisbecker,
	Ingo Molnar, Mike Galbraith, Paul Mackerras, Peter Zijlstra,
	Stephane Eranian, Tom Zanussi

From: Arnaldo Carvalho de Melo <acme@redhat.com>

And the DSO__ORIG_ enum to SYMTAB__, to clarify that this is about from
where the symtab was obtained.

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-top.c   |    4 +-
 tools/perf/util/annotate.c |    2 +-
 tools/perf/util/symbol.c   |   64 ++++++++++++++++++++++----------------------
 tools/perf/util/symbol.h   |   26 +++++++++---------
 4 files changed, 48 insertions(+), 48 deletions(-)

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 4976400..31ea7a6 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -152,7 +152,7 @@ static int parse_source(struct sym_entry *syme)
 	/*
 	 * We can't annotate with just /proc/kallsyms
 	 */
-	if (map->dso->origin == DSO__ORIG_KERNEL) {
+	if (map->dso->symtab_type == SYMTAB__KALLSYMS) {
 		pr_err("Can't annotate %s: No vmlinux file was found in the "
 		       "path\n", sym->name);
 		sleep(1);
@@ -769,7 +769,7 @@ static void perf_event__process_sample(const union perf_event *event,
 			struct symbol *sym = sym_entry__symbol(top.sym_filter_entry);
 
 			pr_err("Can't annotate %s", sym->name);
-			if (top.sym_filter_entry->map->dso->origin == DSO__ORIG_KERNEL) {
+			if (top.sym_filter_entry->map->dso->symtab_type == SYMTAB__KALLSYMS) {
 				pr_err(": No vmlinux file was found in the path:\n");
 				machine__fprintf_vmlinux_path(machine, stderr);
 			} else
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 0d0830c..e01af2b 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -294,7 +294,7 @@ fallback:
 		free_filename = false;
 	}
 
-	if (dso->origin == DSO__ORIG_KERNEL) {
+	if (dso->symtab_type == SYMTAB__KALLSYMS) {
 		char bf[BUILD_ID_SIZE * 2 + 16] = " with build id ";
 		char *build_id_msg = NULL;
 
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 00014e3..651dbfe 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -207,7 +207,7 @@ struct dso *dso__new(const char *name)
 		dso__set_short_name(self, self->name);
 		for (i = 0; i < MAP__NR_TYPES; ++i)
 			self->symbols[i] = self->symbol_names[i] = RB_ROOT;
-		self->origin = DSO__ORIG_NOT_FOUND;
+		self->symtab_type = SYMTAB__NOT_FOUND;
 		self->loaded = 0;
 		self->sorted_by_name = 0;
 		self->has_build_id = 0;
@@ -680,9 +680,9 @@ int dso__load_kallsyms(struct dso *self, const char *filename,
 		return -1;
 
 	if (self->kernel == DSO_TYPE_GUEST_KERNEL)
-		self->origin = DSO__ORIG_GUEST_KERNEL;
+		self->symtab_type = SYMTAB__GUEST_KALLSYMS;
 	else
-		self->origin = DSO__ORIG_KERNEL;
+		self->symtab_type = SYMTAB__KALLSYMS;
 
 	return dso__split_kallsyms(self, map, filter);
 }
@@ -1204,7 +1204,7 @@ static int dso__load_sym(struct dso *self, struct map *map, const char *name,
 				}
 				curr_map->map_ip = identity__map_ip;
 				curr_map->unmap_ip = identity__map_ip;
-				curr_dso->origin = self->origin;
+				curr_dso->symtab_type = self->symtab_type;
 				map_groups__insert(kmap->kmaps, curr_map);
 				dsos__add(&self->node, curr_dso);
 				dso__set_loaded(curr_dso, map->type);
@@ -1430,21 +1430,21 @@ out:
 char dso__symtab_origin(const struct dso *self)
 {
 	static const char origin[] = {
-		[DSO__ORIG_KERNEL] =   'k',
-		[DSO__ORIG_JAVA_JIT] = 'j',
-		[DSO__ORIG_BUILD_ID_CACHE] = 'B',
-		[DSO__ORIG_FEDORA] =   'f',
-		[DSO__ORIG_UBUNTU] =   'u',
-		[DSO__ORIG_BUILDID] =  'b',
-		[DSO__ORIG_DSO] =      'd',
-		[DSO__ORIG_KMODULE] =  'K',
-		[DSO__ORIG_GUEST_KERNEL] =  'g',
-		[DSO__ORIG_GUEST_KMODULE] =  'G',
+		[SYMTAB__KALLSYMS]	      = 'k',
+		[SYMTAB__JAVA_JIT]	      = 'j',
+		[SYMTAB__BUILD_ID_CACHE]      = 'B',
+		[SYMTAB__FEDORA_DEBUGINFO]    = 'f',
+		[SYMTAB__UBUNTU_DEBUGINFO]    = 'u',
+		[SYMTAB__BUILDID_DEBUGINFO]   = 'b',
+		[SYMTAB__SYSTEM_PATH_DSO]     = 'd',
+		[SYMTAB__SYSTEM_PATH_KMODULE] = 'K',
+		[SYMTAB__GUEST_KALLSYMS]      =  'g',
+		[SYMTAB__GUEST_KMODULE]	      =  'G',
 	};
 
-	if (self == NULL || self->origin == DSO__ORIG_NOT_FOUND)
+	if (self == NULL || self->symtab_type == SYMTAB__NOT_FOUND)
 		return '!';
-	return origin[self->origin];
+	return origin[self->symtab_type];
 }
 
 int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
@@ -1477,8 +1477,8 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
 
 	if (strncmp(self->name, "/tmp/perf-", 10) == 0) {
 		ret = dso__load_perf_map(self, map, filter);
-		self->origin = ret > 0 ? DSO__ORIG_JAVA_JIT :
-					 DSO__ORIG_NOT_FOUND;
+		self->symtab_type = ret > 0 ? SYMTAB__JAVA_JIT :
+					      SYMTAB__NOT_FOUND;
 		return ret;
 	}
 
@@ -1486,26 +1486,26 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
 	 * On the first pass, only load images if they have a full symtab.
 	 * Failing that, do a second pass where we accept .dynsym also
 	 */
-	for (self->origin = DSO__ORIG_BUILD_ID_CACHE, want_symtab = 1;
-	     self->origin != DSO__ORIG_NOT_FOUND;
-	     self->origin++) {
-		switch (self->origin) {
-		case DSO__ORIG_BUILD_ID_CACHE:
+	for (self->symtab_type = SYMTAB__BUILD_ID_CACHE, want_symtab = 1;
+	     self->symtab_type != SYMTAB__NOT_FOUND;
+	     self->symtab_type++) {
+		switch (self->symtab_type) {
+		case SYMTAB__BUILD_ID_CACHE:
 			/* skip the locally configured cache if a symfs is given */
 			if (symbol_conf.symfs[0] ||
 			    (dso__build_id_filename(self, name, size) == NULL)) {
 				continue;
 			}
 			break;
-		case DSO__ORIG_FEDORA:
+		case SYMTAB__FEDORA_DEBUGINFO:
 			snprintf(name, size, "%s/usr/lib/debug%s.debug",
 				 symbol_conf.symfs, self->long_name);
 			break;
-		case DSO__ORIG_UBUNTU:
+		case SYMTAB__UBUNTU_DEBUGINFO:
 			snprintf(name, size, "%s/usr/lib/debug%s",
 				 symbol_conf.symfs, self->long_name);
 			break;
-		case DSO__ORIG_BUILDID: {
+		case SYMTAB__BUILDID_DEBUGINFO: {
 			char build_id_hex[BUILD_ID_SIZE * 2 + 1];
 
 			if (!self->has_build_id)
@@ -1519,11 +1519,11 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
 				 symbol_conf.symfs, build_id_hex, build_id_hex + 2);
 			}
 			break;
-		case DSO__ORIG_DSO:
+		case SYMTAB__SYSTEM_PATH_DSO:
 			snprintf(name, size, "%s%s",
 			     symbol_conf.symfs, self->long_name);
 			break;
-		case DSO__ORIG_GUEST_KMODULE:
+		case SYMTAB__GUEST_KMODULE:
 			if (map->groups && machine)
 				root_dir = machine->root_dir;
 			else
@@ -1532,7 +1532,7 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
 				 root_dir, self->long_name);
 			break;
 
-		case DSO__ORIG_KMODULE:
+		case SYMTAB__SYSTEM_PATH_KMODULE:
 			snprintf(name, size, "%s%s", symbol_conf.symfs,
 				 self->long_name);
 			break;
@@ -1544,7 +1544,7 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter)
 			 */
 			if (want_symtab) {
 				want_symtab = 0;
-				self->origin = DSO__ORIG_BUILD_ID_CACHE;
+				self->symtab_type = SYMTAB__BUILD_ID_CACHE;
 			} else
 				continue;
 		}
@@ -1757,9 +1757,9 @@ struct map *machine__new_module(struct machine *self, u64 start,
 		return NULL;
 
 	if (machine__is_host(self))
-		dso->origin = DSO__ORIG_KMODULE;
+		dso->symtab_type = SYMTAB__SYSTEM_PATH_KMODULE;
 	else
-		dso->origin = DSO__ORIG_GUEST_KMODULE;
+		dso->symtab_type = SYMTAB__GUEST_KMODULE;
 	map_groups__insert(&self->kmaps, map);
 	return map;
 }
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 4d7ed09..db39c0c 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -137,7 +137,7 @@ struct dso {
 	u8		 annotate_warned:1;
 	u8		 sname_alloc:1;
 	u8		 lname_alloc:1;
-	unsigned char	 origin;
+	unsigned char	 symtab_type;
 	u8		 sorted_by_name;
 	u8		 loaded;
 	u8		 build_id[BUILD_ID_SIZE];
@@ -188,18 +188,18 @@ size_t dso__fprintf_buildid(struct dso *self, FILE *fp);
 size_t dso__fprintf_symbols_by_name(struct dso *self, enum map_type type, FILE *fp);
 size_t dso__fprintf(struct dso *self, enum map_type type, FILE *fp);
 
-enum dso_origin {
-	DSO__ORIG_KERNEL = 0,
-	DSO__ORIG_GUEST_KERNEL,
-	DSO__ORIG_JAVA_JIT,
-	DSO__ORIG_BUILD_ID_CACHE,
-	DSO__ORIG_FEDORA,
-	DSO__ORIG_UBUNTU,
-	DSO__ORIG_BUILDID,
-	DSO__ORIG_DSO,
-	DSO__ORIG_GUEST_KMODULE,
-	DSO__ORIG_KMODULE,
-	DSO__ORIG_NOT_FOUND,
+enum symtab_type {
+	SYMTAB__KALLSYMS = 0,
+	SYMTAB__GUEST_KALLSYMS,
+	SYMTAB__JAVA_JIT,
+	SYMTAB__BUILD_ID_CACHE,
+	SYMTAB__FEDORA_DEBUGINFO,
+	SYMTAB__UBUNTU_DEBUGINFO,
+	SYMTAB__BUILDID_DEBUGINFO,
+	SYMTAB__SYSTEM_PATH_DSO,
+	SYMTAB__GUEST_KMODULE,
+	SYMTAB__SYSTEM_PATH_KMODULE,
+	SYMTAB__NOT_FOUND,
 };
 
 char dso__symtab_origin(const struct dso *self);
-- 
1.6.2.5


^ permalink raw reply	[flat|nested] 14+ messages in thread

* [PATCH 04/12] perf symbol: Move sym_entry->skip to symbol->ignore
  2011-03-15 20:04 [GIT PULL 00/12] perf/core improvements, fixes and cleanups Arnaldo Carvalho de Melo
                   ` (2 preceding siblings ...)
  2011-03-15 20:04 ` [PATCH 03/12] perf symbols: Rename dso->origin to dso->symtab_type Arnaldo Carvalho de Melo
@ 2011-03-15 20:04 ` Arnaldo Carvalho de Melo
  2011-03-15 20:04 ` [PATCH 05/12] perf stat: Provide support for filters Arnaldo Carvalho de Melo
                   ` (8 subsequent siblings)
  12 siblings, 0 replies; 14+ messages in thread
From: Arnaldo Carvalho de Melo @ 2011-03-15 20:04 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Frederic Weisbecker,
	Ingo Molnar, Mike Galbraith, Paul Mackerras, Peter Zijlstra,
	Stephane Eranian, Tom Zanussi

From: Arnaldo Carvalho de Melo <acme@redhat.com>

While going thru each of the sym_entry fields looking to reduce it to
the set of entries needed when in an active symbols list, 'skip' should
really be in symbol, as we set it when loading the symtab.

And the space used by the basic symbol allocation remains the same as
we had 5 bytes of padding.

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-top.c |    4 ++--
 tools/perf/util/symbol.h |    5 +++++
 tools/perf/util/top.h    |    1 -
 3 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 31ea7a6..70f1075 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -676,7 +676,7 @@ static int symbol_filter(struct map *map, struct symbol *sym)
 
 	for (i = 0; skip_symbols[i]; i++) {
 		if (!strcmp(skip_symbols[i], name)) {
-			syme->skip = 1;
+			sym->ignore = true;
 			break;
 		}
 	}
@@ -779,7 +779,7 @@ static void perf_event__process_sample(const union perf_event *event,
 	}
 
 	syme = symbol__priv(al.sym);
-	if (!syme->skip) {
+	if (!al.sym->ignore) {
 		struct perf_evsel *evsel;
 
 		evsel = perf_evlist__id2evsel(top.evlist, sample->id);
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index db39c0c..713b0b4 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -48,12 +48,17 @@ char *strxfrchar(char *s, char from, char to);
 
 #define BUILD_ID_SIZE 20
 
+/** struct symbol - symtab entry
+ *
+ * @ignore - resolvable but tools ignore it (e.g. idle routines)
+ */
 struct symbol {
 	struct rb_node	rb_node;
 	u64		start;
 	u64		end;
 	u16		namelen;
 	u8		binding;
+	bool		ignore;
 	char		name[0];
 };
 
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index ba111b2..bfbf95b 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -16,7 +16,6 @@ struct sym_entry {
 	struct list_head	node;
 	unsigned long		snap_count;
 	double			weight;
-	int			skip;
 	struct map		*map;
 	unsigned long		count[0];
 };
-- 
1.6.2.5


^ permalink raw reply	[flat|nested] 14+ messages in thread

* [PATCH 05/12] perf stat: Provide support for filters
  2011-03-15 20:04 [GIT PULL 00/12] perf/core improvements, fixes and cleanups Arnaldo Carvalho de Melo
                   ` (3 preceding siblings ...)
  2011-03-15 20:04 ` [PATCH 04/12] perf symbol: Move sym_entry->skip to symbol->ignore Arnaldo Carvalho de Melo
@ 2011-03-15 20:04 ` Arnaldo Carvalho de Melo
  2011-03-15 20:04 ` [PATCH 06/12] perf script: Change process_event prototype Arnaldo Carvalho de Melo
                   ` (7 subsequent siblings)
  12 siblings, 0 replies; 14+ messages in thread
From: Arnaldo Carvalho de Melo @ 2011-03-15 20:04 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, Frederic Weisbecker, Ingo Molnar, Paul Mackerras,
	Peter Zijlstra, Stephane Eranian, Arnaldo Carvalho de Melo

From: Frederic Weisbecker <fweisbec@gmail.com>

Now the --filter option is usable with perf stat too.

Cc: Ingo Molnar <mingo@elte.hu>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
LKML-Reference: <1300117230-8404-1-git-send-email-fweisbec@gmail.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c |    8 ++++++++
 1 files changed, 8 insertions(+), 0 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 21c0252..e2109f9 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -333,6 +333,12 @@ static int run_perf_stat(int argc __used, const char **argv)
 		}
 	}
 
+	if (perf_evlist__set_filters(evsel_list)) {
+		error("failed to set filter with %d (%s)\n", errno,
+			strerror(errno));
+		return -1;
+	}
+
 	/*
 	 * Enable counters and exec the command:
 	 */
@@ -634,6 +640,8 @@ static const struct option options[] = {
 	OPT_CALLBACK('e', "event", &evsel_list, "event",
 		     "event selector. use 'perf list' to list available events",
 		     parse_events),
+	OPT_CALLBACK(0, "filter", &evsel_list, "filter",
+		     "event filter", parse_filter),
 	OPT_BOOLEAN('i', "no-inherit", &no_inherit,
 		    "child tasks do not inherit counters"),
 	OPT_INTEGER('p', "pid", &target_pid,
-- 
1.6.2.5


^ permalink raw reply	[flat|nested] 14+ messages in thread

* [PATCH 06/12] perf script: Change process_event prototype
  2011-03-15 20:04 [GIT PULL 00/12] perf/core improvements, fixes and cleanups Arnaldo Carvalho de Melo
                   ` (4 preceding siblings ...)
  2011-03-15 20:04 ` [PATCH 05/12] perf stat: Provide support for filters Arnaldo Carvalho de Melo
@ 2011-03-15 20:04 ` Arnaldo Carvalho de Melo
  2011-03-15 20:04 ` [PATCH 07/12] perf tracing: Remove print_graph_cpu and print_graph_proc from trace-event-parse Arnaldo Carvalho de Melo
                   ` (6 subsequent siblings)
  12 siblings, 0 replies; 14+ messages in thread
From: Arnaldo Carvalho de Melo @ 2011-03-15 20:04 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, David Ahern, Frederic Weisbecker, Ingo Molnar,
	Paul Mackerras, Peter Zijlstra, Thomas Gleixner,
	Arnaldo Carvalho de Melo

From: David Ahern <daahern@cisco.com>

Prepare for handling of samples for any event type.

Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
LKML-Reference: <1299734608-5223-2-git-send-email-daahern@cisco.com>
Signed-off-by: David Ahern <daahern@cisco.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-script.c                        |   25 ++++++++++++-------
 .../perf/util/scripting-engines/trace-event-perl.c |   11 ++++++--
 .../util/scripting-engines/trace-event-python.c    |   11 ++++++--
 tools/perf/util/trace-event-scripting.c            |    9 +++----
 tools/perf/util/trace-event.h                      |    7 ++++-
 5 files changed, 41 insertions(+), 22 deletions(-)

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 5f40df6..b2bdd55 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -20,6 +20,20 @@ static u64			last_timestamp;
 static u64			nr_unordered;
 extern const struct option	record_options[];
 
+static void process_event(union perf_event *event __unused,
+			  struct perf_sample *sample,
+			  struct perf_session *session __unused,
+			  struct thread *thread)
+{
+	/*
+	 * FIXME: better resolve from pid from the struct trace_entry
+	 * field, although it should be the same than this perf
+	 * event pid
+	 */
+	print_event(sample->cpu, sample->raw_data, sample->raw_size,
+		    sample->time, thread->comm);
+}
+
 static int default_start_script(const char *script __unused,
 				int argc __unused,
 				const char **argv __unused)
@@ -40,7 +54,7 @@ static int default_generate_script(const char *outfile __unused)
 static struct scripting_ops default_scripting_ops = {
 	.start_script		= default_start_script,
 	.stop_script		= default_stop_script,
-	.process_event		= print_event,
+	.process_event		= process_event,
 	.generate_script	= default_generate_script,
 };
 
@@ -86,14 +100,7 @@ static int process_sample_event(union perf_event *event,
 			last_timestamp = sample->time;
 			return 0;
 		}
-		/*
-		 * FIXME: better resolve from pid from the struct trace_entry
-		 * field, although it should be the same than this perf
-		 * event pid
-		 */
-		scripting_ops->process_event(sample->cpu, sample->raw_data,
-					     sample->raw_size,
-					     sample->time, thread->comm);
+		scripting_ops->process_event(event, sample, session, thread);
 	}
 
 	session->hists.stats.total_period += sample->period;
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 9368081..6214272 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -245,9 +245,10 @@ static inline struct event *find_cache_event(int type)
 	return event;
 }
 
-static void perl_process_event(int cpu, void *data,
-			       int size __unused,
-			       unsigned long long nsecs, char *comm)
+static void perl_process_event(union perf_event *pevent __unused,
+			       struct perf_sample *sample,
+			       struct perf_session *session __unused,
+			       struct thread *thread)
 {
 	struct format_field *field;
 	static char handler[256];
@@ -256,6 +257,10 @@ static void perl_process_event(int cpu, void *data,
 	struct event *event;
 	int type;
 	int pid;
+	int cpu = sample->cpu;
+	void *data = sample->raw_data;
+	unsigned long long nsecs = sample->time;
+	char *comm = thread->comm;
 
 	dSP;
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 2040b85..1b85d60 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -204,9 +204,10 @@ static inline struct event *find_cache_event(int type)
 	return event;
 }
 
-static void python_process_event(int cpu, void *data,
-				 int size __unused,
-				 unsigned long long nsecs, char *comm)
+static void python_process_event(union perf_event *pevent __unused,
+				 struct perf_sample *sample,
+				 struct perf_session *session __unused,
+				 struct thread *thread)
 {
 	PyObject *handler, *retval, *context, *t, *obj, *dict = NULL;
 	static char handler_name[256];
@@ -217,6 +218,10 @@ static void python_process_event(int cpu, void *data,
 	unsigned n = 0;
 	int type;
 	int pid;
+	int cpu = sample->cpu;
+	void *data = sample->raw_data;
+	unsigned long long nsecs = sample->time;
+	char *comm = thread->comm;
 
 	t = PyTuple_New(MAX_FIELDS);
 	if (!t)
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index f7af2fc..66f4b78 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -36,11 +36,10 @@ static int stop_script_unsupported(void)
 	return 0;
 }
 
-static void process_event_unsupported(int cpu __unused,
-				      void *data __unused,
-				      int size __unused,
-				      unsigned long long nsecs __unused,
-				      char *comm __unused)
+static void process_event_unsupported(union perf_event *event __unused,
+				      struct perf_sample *sample __unused,
+				      struct perf_session *session __unused,
+				      struct thread *thread __unused)
 {
 }
 
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index b5f12ca..5f7b513 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -3,6 +3,7 @@
 
 #include <stdbool.h>
 #include "parse-events.h"
+#include "session.h"
 
 #define __unused __attribute__((unused))
 
@@ -278,8 +279,10 @@ struct scripting_ops {
 	const char *name;
 	int (*start_script) (const char *script, int argc, const char **argv);
 	int (*stop_script) (void);
-	void (*process_event) (int cpu, void *data, int size,
-			       unsigned long long nsecs, char *comm);
+	void (*process_event) (union perf_event *event,
+			       struct perf_sample *sample,
+			       struct perf_session *session,
+			       struct thread *thread);
 	int (*generate_script) (const char *outfile);
 };
 
-- 
1.6.2.5


^ permalink raw reply	[flat|nested] 14+ messages in thread

* [PATCH 07/12] perf tracing: Remove print_graph_cpu and print_graph_proc from trace-event-parse
  2011-03-15 20:04 [GIT PULL 00/12] perf/core improvements, fixes and cleanups Arnaldo Carvalho de Melo
                   ` (5 preceding siblings ...)
  2011-03-15 20:04 ` [PATCH 06/12] perf script: Change process_event prototype Arnaldo Carvalho de Melo
@ 2011-03-15 20:04 ` Arnaldo Carvalho de Melo
  2011-03-15 20:04 ` [PATCH 08/12] perf script: Move printing of 'common' data from print_event and rename Arnaldo Carvalho de Melo
                   ` (5 subsequent siblings)
  12 siblings, 0 replies; 14+ messages in thread
From: Arnaldo Carvalho de Melo @ 2011-03-15 20:04 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, David Ahern, Frederic Weisbecker, Ingo Molnar,
	Paul Mackerras, Peter Zijlstra, Thomas Gleixner,
	Arnaldo Carvalho de Melo

From: David Ahern <daahern@cisco.com>

Next patch moves printing of 'common' data into perf-script which
removes the need for these functions.

Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
LKML-Reference: <1299734608-5223-3-git-send-email-daahern@cisco.com>
Signed-off-by: David Ahern <daahern@cisco.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/trace-event-parse.c |   65 +---------------------------------
 1 files changed, 2 insertions(+), 63 deletions(-)

diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index d8e622d..dd5f058 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -2648,63 +2648,8 @@ static void print_lat_fmt(void *data, int size __unused)
 		printf("%d", lock_depth);
 }
 
-/* taken from Linux, written by Frederic Weisbecker */
-static void print_graph_cpu(int cpu)
-{
-	int i;
-	int log10_this = log10_cpu(cpu);
-	int log10_all = log10_cpu(cpus);
-
-
-	/*
-	 * Start with a space character - to make it stand out
-	 * to the right a bit when trace output is pasted into
-	 * email:
-	 */
-	printf(" ");
-
-	/*
-	 * Tricky - we space the CPU field according to the max
-	 * number of online CPUs. On a 2-cpu system it would take
-	 * a maximum of 1 digit - on a 128 cpu system it would
-	 * take up to 3 digits:
-	 */
-	for (i = 0; i < log10_all - log10_this; i++)
-		printf(" ");
-
-	printf("%d) ", cpu);
-}
-
-#define TRACE_GRAPH_PROCINFO_LENGTH	14
 #define TRACE_GRAPH_INDENT	2
 
-static void print_graph_proc(int pid, const char *comm)
-{
-	/* sign + log10(MAX_INT) + '\0' */
-	char pid_str[11];
-	int spaces = 0;
-	int len;
-	int i;
-
-	sprintf(pid_str, "%d", pid);
-
-	/* 1 stands for the "-" character */
-	len = strlen(comm) + strlen(pid_str) + 1;
-
-	if (len < TRACE_GRAPH_PROCINFO_LENGTH)
-		spaces = TRACE_GRAPH_PROCINFO_LENGTH - len;
-
-	/* First spaces to align center */
-	for (i = 0; i < spaces / 2; i++)
-		printf(" ");
-
-	printf("%s-%s", comm, pid_str);
-
-	/* Last spaces to align center */
-	for (i = 0; i < spaces - (spaces / 2); i++)
-		printf(" ");
-}
-
 static struct record *
 get_return_for_leaf(int cpu, int cur_pid, unsigned long long cur_func,
 		    struct record *next)
@@ -2876,7 +2821,7 @@ static void print_graph_nested(struct event *event, void *data)
 
 static void
 pretty_print_func_ent(void *data, int size, struct event *event,
-		      int cpu, int pid, const char *comm,
+		      int cpu, int pid, const char *comm __unused,
 		      unsigned long secs, unsigned long usecs)
 {
 	struct format_field *field;
@@ -2886,9 +2831,6 @@ pretty_print_func_ent(void *data, int size, struct event *event,
 
 	printf("%5lu.%06lu |  ", secs, usecs);
 
-	print_graph_cpu(cpu);
-	print_graph_proc(pid, comm);
-
 	printf(" | ");
 
 	if (latency_format) {
@@ -2924,7 +2866,7 @@ out_free:
 
 static void
 pretty_print_func_ret(void *data, int size __unused, struct event *event,
-		      int cpu, int pid, const char *comm,
+		      int cpu __unused, int pid __unused, const char *comm __unused,
 		      unsigned long secs, unsigned long usecs)
 {
 	unsigned long long rettime, calltime;
@@ -2934,9 +2876,6 @@ pretty_print_func_ret(void *data, int size __unused, struct event *event,
 
 	printf("%5lu.%06lu |  ", secs, usecs);
 
-	print_graph_cpu(cpu);
-	print_graph_proc(pid, comm);
-
 	printf(" | ");
 
 	if (latency_format) {
-- 
1.6.2.5


^ permalink raw reply	[flat|nested] 14+ messages in thread

* [PATCH 08/12] perf script: Move printing of 'common' data from print_event and rename
  2011-03-15 20:04 [GIT PULL 00/12] perf/core improvements, fixes and cleanups Arnaldo Carvalho de Melo
                   ` (6 preceding siblings ...)
  2011-03-15 20:04 ` [PATCH 07/12] perf tracing: Remove print_graph_cpu and print_graph_proc from trace-event-parse Arnaldo Carvalho de Melo
@ 2011-03-15 20:04 ` Arnaldo Carvalho de Melo
  2011-03-15 20:04 ` [PATCH 09/12] perf script: Support custom field selection for output Arnaldo Carvalho de Melo
                   ` (4 subsequent siblings)
  12 siblings, 0 replies; 14+ messages in thread
From: Arnaldo Carvalho de Melo @ 2011-03-15 20:04 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, David Ahern, Frederic Weisbecker, Ingo Molnar,
	Paul Mackerras, Peter Zijlstra, Thomas Gleixner,
	Arnaldo Carvalho de Melo

From: David Ahern <daahern@cisco.com>

This change does impact output: latency data is trace specific and is
now printed after the common data - comm, tid, cpu, time and event name.

Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
LKML-Reference: <1299734608-5223-4-git-send-email-daahern@cisco.com>
Signed-off-by: David Ahern <daahern@cisco.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-script.c         |   38 ++++++++++++++++++++++-----
 tools/perf/util/trace-event-parse.c |   49 +++++++---------------------------
 tools/perf/util/trace-event.h       |    3 +-
 3 files changed, 42 insertions(+), 48 deletions(-)

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index b2bdd55..0a79da2 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -20,18 +20,42 @@ static u64			last_timestamp;
 static u64			nr_unordered;
 extern const struct option	record_options[];
 
+static void print_sample_start(struct perf_sample *sample,
+			       struct thread *thread)
+{
+	int type;
+	struct event *event;
+	const char *evname = NULL;
+	unsigned long secs;
+	unsigned long usecs;
+	unsigned long long nsecs = sample->time;
+
+	if (latency_format)
+		printf("%8.8s-%-5d %3d", thread->comm, sample->tid, sample->cpu);
+	else
+		printf("%16s-%-5d [%03d]", thread->comm, sample->tid, sample->cpu);
+
+	secs = nsecs / NSECS_PER_SEC;
+	nsecs -= secs * NSECS_PER_SEC;
+	usecs = nsecs / NSECS_PER_USEC;
+	printf(" %5lu.%06lu: ", secs, usecs);
+
+	type = trace_parse_common_type(sample->raw_data);
+	event = trace_find_event(type);
+	if (event)
+		evname = event->name;
+
+	printf("%s: ", evname ? evname : "(unknown)");
+}
+
 static void process_event(union perf_event *event __unused,
 			  struct perf_sample *sample,
 			  struct perf_session *session __unused,
 			  struct thread *thread)
 {
-	/*
-	 * FIXME: better resolve from pid from the struct trace_entry
-	 * field, although it should be the same than this perf
-	 * event pid
-	 */
-	print_event(sample->cpu, sample->raw_data, sample->raw_size,
-		    sample->time, thread->comm);
+	print_sample_start(sample, thread);
+	print_trace_event(sample->cpu, sample->raw_data, sample->raw_size);
+	printf("\n");
 }
 
 static int default_start_script(const char *script __unused,
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index dd5f058..0a7ed5b 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -2643,9 +2643,9 @@ static void print_lat_fmt(void *data, int size __unused)
 		printf(".");
 
 	if (lock_depth < 0)
-		printf(".");
+		printf(". ");
 	else
-		printf("%d", lock_depth);
+		printf("%d ", lock_depth);
 }
 
 #define TRACE_GRAPH_INDENT	2
@@ -2821,18 +2821,13 @@ static void print_graph_nested(struct event *event, void *data)
 
 static void
 pretty_print_func_ent(void *data, int size, struct event *event,
-		      int cpu, int pid, const char *comm __unused,
-		      unsigned long secs, unsigned long usecs)
+		      int cpu, int pid)
 {
 	struct format_field *field;
 	struct record *rec;
 	void *copy_data;
 	unsigned long val;
 
-	printf("%5lu.%06lu |  ", secs, usecs);
-
-	printf(" | ");
-
 	if (latency_format) {
 		print_lat_fmt(data, size);
 		printf(" | ");
@@ -2865,19 +2860,13 @@ out_free:
 }
 
 static void
-pretty_print_func_ret(void *data, int size __unused, struct event *event,
-		      int cpu __unused, int pid __unused, const char *comm __unused,
-		      unsigned long secs, unsigned long usecs)
+pretty_print_func_ret(void *data, int size __unused, struct event *event)
 {
 	unsigned long long rettime, calltime;
 	unsigned long long duration, depth;
 	struct format_field *field;
 	int i;
 
-	printf("%5lu.%06lu |  ", secs, usecs);
-
-	printf(" | ");
-
 	if (latency_format) {
 		print_lat_fmt(data, size);
 		printf(" | ");
@@ -2915,31 +2904,21 @@ pretty_print_func_ret(void *data, int size __unused, struct event *event,
 
 static void
 pretty_print_func_graph(void *data, int size, struct event *event,
-			int cpu, int pid, const char *comm,
-			unsigned long secs, unsigned long usecs)
+			int cpu, int pid)
 {
 	if (event->flags & EVENT_FL_ISFUNCENT)
-		pretty_print_func_ent(data, size, event,
-				      cpu, pid, comm, secs, usecs);
+		pretty_print_func_ent(data, size, event, cpu, pid);
 	else if (event->flags & EVENT_FL_ISFUNCRET)
-		pretty_print_func_ret(data, size, event,
-				      cpu, pid, comm, secs, usecs);
+		pretty_print_func_ret(data, size, event);
 	printf("\n");
 }
 
-void print_event(int cpu, void *data, int size, unsigned long long nsecs,
-		  char *comm)
+void print_trace_event(int cpu, void *data, int size)
 {
 	struct event *event;
-	unsigned long secs;
-	unsigned long usecs;
 	int type;
 	int pid;
 
-	secs = nsecs / NSECS_PER_SEC;
-	nsecs -= secs * NSECS_PER_SEC;
-	usecs = nsecs / NSECS_PER_USEC;
-
 	type = trace_parse_common_type(data);
 
 	event = trace_find_event(type);
@@ -2951,17 +2930,10 @@ void print_event(int cpu, void *data, int size, unsigned long long nsecs,
 	pid = trace_parse_common_pid(data);
 
 	if (event->flags & (EVENT_FL_ISFUNCENT | EVENT_FL_ISFUNCRET))
-		return pretty_print_func_graph(data, size, event, cpu,
-					       pid, comm, secs, usecs);
+		return pretty_print_func_graph(data, size, event, cpu, pid);
 
-	if (latency_format) {
-		printf("%8.8s-%-5d %3d",
-		       comm, pid, cpu);
+	if (latency_format)
 		print_lat_fmt(data, size);
-	} else
-		printf("%16s-%-5d [%03d]", comm, pid,  cpu);
-
-	printf(" %5lu.%06lu: %s: ", secs, usecs, event->name);
 
 	if (event->flags & EVENT_FL_FAILED) {
 		printf("EVENT '%s' FAILED TO PARSE\n",
@@ -2970,7 +2942,6 @@ void print_event(int cpu, void *data, int size, unsigned long long nsecs,
 	}
 
 	pretty_print(data, size, event);
-	printf("\n");
 }
 
 static void print_fields(struct print_flag_sym *field)
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 5f7b513..b04da57 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -177,8 +177,7 @@ void print_printk(void);
 
 int parse_ftrace_file(char *buf, unsigned long size);
 int parse_event_file(char *buf, unsigned long size, char *sys);
-void print_event(int cpu, void *data, int size, unsigned long long nsecs,
-		  char *comm);
+void print_trace_event(int cpu, void *data, int size);
 
 extern int file_bigendian;
 extern int host_bigendian;
-- 
1.6.2.5


^ permalink raw reply	[flat|nested] 14+ messages in thread

* [PATCH 09/12] perf script: Support custom field selection for output
  2011-03-15 20:04 [GIT PULL 00/12] perf/core improvements, fixes and cleanups Arnaldo Carvalho de Melo
                   ` (7 preceding siblings ...)
  2011-03-15 20:04 ` [PATCH 08/12] perf script: Move printing of 'common' data from print_event and rename Arnaldo Carvalho de Melo
@ 2011-03-15 20:04 ` Arnaldo Carvalho de Melo
  2011-03-15 20:04 ` [PATCH 10/12] perf script: Add support for dumping symbols Arnaldo Carvalho de Melo
                   ` (3 subsequent siblings)
  12 siblings, 0 replies; 14+ messages in thread
From: Arnaldo Carvalho de Melo @ 2011-03-15 20:04 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, David Ahern, Frederic Weisbecker, Ingo Molnar,
	Paul Mackerras, Peter Zijlstra, Thomas Gleixner,
	Arnaldo Carvalho de Melo

From: David Ahern <daahern@cisco.com>

Allow a user to select which fields to print to stdout for event data.
Options include comm (command name), tid (thread id), pid (process id),
time (perf timestamp), cpu, event (for event name), and trace (for
trace data).

Default is set to maintain compatibility with current output; this
feature does alter output format slightly -- no '-' between command
and pid/tid.

Thanks to Frederic Weisbecker for detailed suggestions on this approach.

Examples (output compressed)

1. trace, default format

perf record -ga -e sched:sched_switch
perf script

swapper    0 [000] 537.037184: sched_switch: prev_comm=swapper prev_pid=0...
   sshd 1675 [000] 537.037309: sched_switch: prev_comm=sshd prev_pid=1675...
netstat 1692 [001] 537.038664: sched_switch: prev_comm=netstat prev_pid=1692...

2. trace, custom format

perf record -ga -e sched:sched_switch
perf script -f comm,pid,time,trace     <--- omitting cpu and event name

swapper    0 537.037184: prev_comm=swapper prev_pid=0 prev_prio=120 ...
   sshd 1675 537.037309: prev_comm=sshd prev_pid=1675 prev_prio=120 ...
netstat 1692 537.038664: prev_comm=netstat prev_pid=1692 prev_prio=120 ...

Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
LKML-Reference: <1299734608-5223-5-git-send-email-daahern@cisco.com>
Signed-off-by: David Ahern <daahern@cisco.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-script.txt |    5 +
 tools/perf/builtin-script.c              |  141 ++++++++++++++++++++++++++----
 2 files changed, 130 insertions(+), 16 deletions(-)

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 29ad942..b73cf58 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -112,6 +112,11 @@ OPTIONS
 --debug-mode::
         Do various checks like samples ordering and lost events.
 
+-f::
+--fields
+        Comma separated list of fields to print. Options are:
+        comm, tid, pid, time, cpu, event, trace
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 0a79da2..c046e6e 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -20,6 +20,38 @@ static u64			last_timestamp;
 static u64			nr_unordered;
 extern const struct option	record_options[];
 
+enum perf_output_field {
+	PERF_OUTPUT_COMM            = 1U << 0,
+	PERF_OUTPUT_TID             = 1U << 1,
+	PERF_OUTPUT_PID             = 1U << 2,
+	PERF_OUTPUT_TIME            = 1U << 3,
+	PERF_OUTPUT_CPU             = 1U << 4,
+	PERF_OUTPUT_EVNAME          = 1U << 5,
+	PERF_OUTPUT_TRACE           = 1U << 6,
+};
+
+struct output_option {
+	const char *str;
+	enum perf_output_field field;
+} all_output_options[] = {
+	{.str = "comm",  .field = PERF_OUTPUT_COMM},
+	{.str = "tid",   .field = PERF_OUTPUT_TID},
+	{.str = "pid",   .field = PERF_OUTPUT_PID},
+	{.str = "time",  .field = PERF_OUTPUT_TIME},
+	{.str = "cpu",   .field = PERF_OUTPUT_CPU},
+	{.str = "event", .field = PERF_OUTPUT_EVNAME},
+	{.str = "trace", .field = PERF_OUTPUT_TRACE},
+};
+
+/* default set to maintain compatibility with current format */
+static u64 output_fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | \
+			   PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | \
+			   PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE;
+
+static bool output_set_by_user;
+
+#define PRINT_FIELD(x)  (output_fields & PERF_OUTPUT_##x)
+
 static void print_sample_start(struct perf_sample *sample,
 			       struct thread *thread)
 {
@@ -28,24 +60,45 @@ static void print_sample_start(struct perf_sample *sample,
 	const char *evname = NULL;
 	unsigned long secs;
 	unsigned long usecs;
-	unsigned long long nsecs = sample->time;
+	unsigned long long nsecs;
+
+	if (PRINT_FIELD(COMM)) {
+		if (latency_format)
+			printf("%8.8s ", thread->comm);
+		else
+			printf("%16s ", thread->comm);
+	}
 
-	if (latency_format)
-		printf("%8.8s-%-5d %3d", thread->comm, sample->tid, sample->cpu);
-	else
-		printf("%16s-%-5d [%03d]", thread->comm, sample->tid, sample->cpu);
+	if (PRINT_FIELD(PID) && PRINT_FIELD(TID))
+		printf("%5d/%-5d ", sample->pid, sample->tid);
+	else if (PRINT_FIELD(PID))
+		printf("%5d ", sample->pid);
+	else if (PRINT_FIELD(TID))
+		printf("%5d ", sample->tid);
+
+	if (PRINT_FIELD(CPU)) {
+		if (latency_format)
+			printf("%3d ", sample->cpu);
+		else
+			printf("[%03d] ", sample->cpu);
+	}
 
-	secs = nsecs / NSECS_PER_SEC;
-	nsecs -= secs * NSECS_PER_SEC;
-	usecs = nsecs / NSECS_PER_USEC;
-	printf(" %5lu.%06lu: ", secs, usecs);
+	if (PRINT_FIELD(TIME)) {
+		nsecs = sample->time;
+		secs = nsecs / NSECS_PER_SEC;
+		nsecs -= secs * NSECS_PER_SEC;
+		usecs = nsecs / NSECS_PER_USEC;
+		printf("%5lu.%06lu: ", secs, usecs);
+	}
 
-	type = trace_parse_common_type(sample->raw_data);
-	event = trace_find_event(type);
-	if (event)
-		evname = event->name;
+	if (PRINT_FIELD(EVNAME)) {
+		type = trace_parse_common_type(sample->raw_data);
+		event = trace_find_event(type);
+		if (event)
+			evname = event->name;
 
-	printf("%s: ", evname ? evname : "(unknown)");
+		printf("%s: ", evname ? evname : "(unknown)");
+	}
 }
 
 static void process_event(union perf_event *event __unused,
@@ -54,7 +107,11 @@ static void process_event(union perf_event *event __unused,
 			  struct thread *thread)
 {
 	print_sample_start(sample, thread);
-	print_trace_event(sample->cpu, sample->raw_data, sample->raw_size);
+
+	if (PRINT_FIELD(TRACE))
+		print_trace_event(sample->cpu, sample->raw_data,
+				  sample->raw_size);
+
 	printf("\n");
 }
 
@@ -311,6 +368,48 @@ static int parse_scriptname(const struct option *opt __used,
 	return 0;
 }
 
+static int parse_output_fields(const struct option *opt __used,
+			    const char *arg, int unset __used)
+{
+	char *tok;
+	int i, imax = sizeof(all_output_options) / sizeof(struct output_option);
+	int rc = 0;
+	char *str = strdup(arg);
+
+	if (!str)
+		return -ENOMEM;
+
+	tok = strtok(str, ",");
+	if (!tok) {
+		fprintf(stderr, "Invalid field string.");
+		return -EINVAL;
+	}
+
+	output_fields = 0;
+	while (1) {
+		for (i = 0; i < imax; ++i) {
+			if (strcmp(tok, all_output_options[i].str) == 0) {
+				output_fields |= all_output_options[i].field;
+				break;
+			}
+		}
+		if (i == imax) {
+			fprintf(stderr, "Invalid field requested.");
+			rc = -EINVAL;
+			break;
+		}
+
+		tok = strtok(NULL, ",");
+		if (!tok)
+			break;
+	}
+
+	output_set_by_user = true;
+
+	free(str);
+	return rc;
+}
+
 /* Helper function for filesystems that return a dent->d_type DT_UNKNOWN */
 static int is_directory(const char *base_path, const struct dirent *dent)
 {
@@ -623,6 +722,9 @@ static const struct option options[] = {
 		    "input file name"),
 	OPT_BOOLEAN('d', "debug-mode", &debug_mode,
 		   "do various checks like samples ordering and lost events"),
+	OPT_CALLBACK('f', "fields", NULL, "str",
+		     "comma separated output fields. Options: comm,tid,pid,time,cpu,event,trace",
+		     parse_output_fields),
 
 	OPT_END()
 };
@@ -809,8 +911,15 @@ int cmd_script(int argc, const char **argv, const char *prefix __used)
 
 	if (generate_script_lang) {
 		struct stat perf_stat;
+		int input;
+
+		if (output_set_by_user) {
+			fprintf(stderr,
+				"custom fields not supported for generated scripts");
+			return -1;
+		}
 
-		int input = open(input_name, O_RDONLY);
+		input = open(input_name, O_RDONLY);
 		if (input < 0) {
 			perror("failed to open file");
 			exit(-1);
-- 
1.6.2.5


^ permalink raw reply	[flat|nested] 14+ messages in thread

* [PATCH 10/12] perf script: Add support for dumping symbols
  2011-03-15 20:04 [GIT PULL 00/12] perf/core improvements, fixes and cleanups Arnaldo Carvalho de Melo
                   ` (8 preceding siblings ...)
  2011-03-15 20:04 ` [PATCH 09/12] perf script: Support custom field selection for output Arnaldo Carvalho de Melo
@ 2011-03-15 20:04 ` Arnaldo Carvalho de Melo
  2011-03-15 20:05 ` [PATCH 11/12] perf script: Add support for H/W and S/W events Arnaldo Carvalho de Melo
                   ` (2 subsequent siblings)
  12 siblings, 0 replies; 14+ messages in thread
From: Arnaldo Carvalho de Melo @ 2011-03-15 20:04 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, David Ahern, Frederic Weisbecker, Ingo Molnar,
	Paul Mackerras, Peter Zijlstra, Thomas Gleixner,
	Arnaldo Carvalho de Melo

From: David Ahern <daahern@cisco.com>

Add option to dump symbols found in events.

e.g., perf script -f comm,pid,tid,time,trace,sym

swapper     0/0       537.037184: prev_comm=swapper prev_pid=0 prev_prio=120...
        ffffffff81030350 perf_trace_sched_switch ([kernel.kallsyms])
        ffffffff81382ac5 schedule ([kernel.kallsyms])
        ffffffff8100134a cpu_idle ([kernel.kallsyms])
        ffffffff81370b39 rest_init ([kernel.kallsyms])
        ffffffff81696c23 start_kernel ([kernel.kallsyms].init.text)
        ffffffff816962af x86_64_start_reservations ([kernel.kallsyms].init.text)
        ffffffff816963b9 x86_64_start_kernel ([kernel.kallsyms].init.text)

sshd  1675/1675    537.037309: prev_comm=sshd prev_pid=1675 prev_prio=120...
        ffffffff81030350 perf_trace_sched_switch ([kernel.kallsyms])
        ffffffff81382ac5 schedule ([kernel.kallsyms])
        ffffffff813837aa schedule_hrtimeout_range_clock ([kernel.kallsyms])
        ffffffff81383886 schedule_hrtimeout_range ([kernel.kallsyms])
        ffffffff8110c4f9 poll_schedule_timeout ([kernel.kallsyms])
        ffffffff8110cd20 do_select ([kernel.kallsyms])
        ffffffff8110ced8 core_sys_select ([kernel.kallsyms])
        ffffffff8110d00d sys_select ([kernel.kallsyms])
        ffffffff81002bc2 system_call ([kernel.kallsyms])
            7f1647e56e93 __GI_select (/lib64/libc-2.12.90.so)

netstat  1692/1692    537.038664: prev_comm=netstat prev_pid=1692 prev_prio=...
        ffffffff81030350 perf_trace_sched_switch ([kernel.kallsyms])
        ffffffff81382ac5 schedule ([kernel.kallsyms])
        ffffffff81002c3a sysret_careful ([kernel.kallsyms])
            7f7a6cd1b210 __GI___libc_read (/lib64/libc-2.12.90.so)

Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
LKML-Reference: <1299734608-5223-6-git-send-email-daahern@cisco.com>
Signed-off-by: David Ahern <daahern@cisco.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-script.txt |   16 +++++++-
 tools/perf/builtin-script.c              |   31 +++++++++++++++-
 tools/perf/util/session.c                |   61 ++++++++++++++++++++++++++++++
 tools/perf/util/session.h                |    4 ++
 4 files changed, 110 insertions(+), 2 deletions(-)

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index b73cf58..c64118a 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -115,7 +115,21 @@ OPTIONS
 -f::
 --fields
         Comma separated list of fields to print. Options are:
-        comm, tid, pid, time, cpu, event, trace
+        comm, tid, pid, time, cpu, event, trace, sym
+
+-k::
+--vmlinux=<file>::
+        vmlinux pathname
+
+--kallsyms=<file>::
+        kallsyms pathname
+
+--symfs=<directory>::
+        Look for files with symbols relative to this directory.
+
+-G::
+--hide-call-graph::
+        When printing symbols do not display call chain.
 
 SEE ALSO
 --------
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c046e6e..b45b09c 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -19,6 +19,7 @@ static bool			debug_mode;
 static u64			last_timestamp;
 static u64			nr_unordered;
 extern const struct option	record_options[];
+static bool			no_callchain;
 
 enum perf_output_field {
 	PERF_OUTPUT_COMM            = 1U << 0,
@@ -28,6 +29,7 @@ enum perf_output_field {
 	PERF_OUTPUT_CPU             = 1U << 4,
 	PERF_OUTPUT_EVNAME          = 1U << 5,
 	PERF_OUTPUT_TRACE           = 1U << 6,
+	PERF_OUTPUT_SYM             = 1U << 7,
 };
 
 struct output_option {
@@ -41,6 +43,7 @@ struct output_option {
 	{.str = "cpu",   .field = PERF_OUTPUT_CPU},
 	{.str = "event", .field = PERF_OUTPUT_EVNAME},
 	{.str = "trace", .field = PERF_OUTPUT_TRACE},
+	{.str = "sym",   .field = PERF_OUTPUT_SYM},
 };
 
 /* default set to maintain compatibility with current format */
@@ -65,6 +68,8 @@ static void print_sample_start(struct perf_sample *sample,
 	if (PRINT_FIELD(COMM)) {
 		if (latency_format)
 			printf("%8.8s ", thread->comm);
+		else if (PRINT_FIELD(SYM) && symbol_conf.use_callchain)
+			printf("%s ", thread->comm);
 		else
 			printf("%16s ", thread->comm);
 	}
@@ -112,6 +117,14 @@ static void process_event(union perf_event *event __unused,
 		print_trace_event(sample->cpu, sample->raw_data,
 				  sample->raw_size);
 
+	if (PRINT_FIELD(SYM)) {
+		if (!symbol_conf.use_callchain)
+			printf(" ");
+		else
+			printf("\n");
+		perf_session__print_symbols(event, sample, session);
+	}
+
 	printf("\n");
 }
 
@@ -190,7 +203,10 @@ static int process_sample_event(union perf_event *event,
 
 static struct perf_event_ops event_ops = {
 	.sample		 = process_sample_event,
+	.mmap		 = perf_event__process_mmap,
 	.comm		 = perf_event__process_comm,
+	.exit		 = perf_event__process_task,
+	.fork		 = perf_event__process_task,
 	.attr		 = perf_event__process_attr,
 	.event_type	 = perf_event__process_event_type,
 	.tracing_data	 = perf_event__process_tracing_data,
@@ -722,8 +738,16 @@ static const struct option options[] = {
 		    "input file name"),
 	OPT_BOOLEAN('d', "debug-mode", &debug_mode,
 		   "do various checks like samples ordering and lost events"),
+	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
+		   "file", "vmlinux pathname"),
+	OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name,
+		   "file", "kallsyms pathname"),
+	OPT_BOOLEAN('G', "hide-call-graph", &no_callchain,
+		    "When printing symbols do not display call chain"),
+	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
+		    "Look for files with symbols relative to this directory"),
 	OPT_CALLBACK('f', "fields", NULL, "str",
-		     "comma separated output fields. Options: comm,tid,pid,time,cpu,event,trace",
+		     "comma separated output fields. Options: comm,tid,pid,time,cpu,event,trace,sym",
 		     parse_output_fields),
 
 	OPT_END()
@@ -905,6 +929,11 @@ int cmd_script(int argc, const char **argv, const char *prefix __used)
 	if (session == NULL)
 		return -ENOMEM;
 
+	if (!no_callchain && (session->sample_type & PERF_SAMPLE_CALLCHAIN))
+		symbol_conf.use_callchain = true;
+	else
+		symbol_conf.use_callchain = false;
+
 	if (strcmp(input_name, "-") &&
 	    !perf_session__has_traces(session, "record -R"))
 		return -EINVAL;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index f26639f..c68cf40 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1134,3 +1134,64 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
 
 	return ret;
 }
+
+void perf_session__print_symbols(union perf_event *event,
+				struct perf_sample *sample,
+				struct perf_session *session)
+{
+	struct addr_location al;
+	const char *symname, *dsoname;
+	struct callchain_cursor *cursor = &session->callchain_cursor;
+	struct callchain_cursor_node *node;
+
+	if (perf_event__preprocess_sample(event, session, &al, sample,
+					  NULL) < 0) {
+		error("problem processing %d event, skipping it.\n",
+			event->header.type);
+		return;
+	}
+
+	if (symbol_conf.use_callchain && sample->callchain) {
+
+		if (perf_session__resolve_callchain(session, al.thread,
+						sample->callchain, NULL) != 0) {
+			if (verbose)
+				error("Failed to resolve callchain. Skipping\n");
+			return;
+		}
+		callchain_cursor_commit(cursor);
+
+		while (1) {
+			node = callchain_cursor_current(cursor);
+			if (!node)
+				break;
+
+			if (node->sym && node->sym->name)
+				symname = node->sym->name;
+			else
+				symname = "";
+
+			if (node->map && node->map->dso && node->map->dso->name)
+				dsoname = node->map->dso->name;
+			else
+				dsoname = "";
+
+			printf("\t%16" PRIx64 " %s (%s)\n", node->ip, symname, dsoname);
+
+			callchain_cursor_advance(cursor);
+		}
+
+	} else {
+		if (al.sym && al.sym->name)
+			symname = al.sym->name;
+		else
+			symname = "";
+
+		if (al.map && al.map->dso && al.map->dso->name)
+			dsoname = al.map->dso->name;
+		else
+			dsoname = "";
+
+		printf("%16" PRIx64 " %s (%s)", al.addr, symname, dsoname);
+	}
+}
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index b5b148b..0b3c9af 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -159,4 +159,8 @@ static inline int perf_session__parse_sample(struct perf_session *session,
 					session->sample_id_all, sample);
 }
 
+void perf_session__print_symbols(union perf_event *event,
+				 struct perf_sample *sample,
+				 struct perf_session *session);
+
 #endif /* __PERF_SESSION_H */
-- 
1.6.2.5


^ permalink raw reply	[flat|nested] 14+ messages in thread

* [PATCH 11/12] perf script: Add support for H/W and S/W events
  2011-03-15 20:04 [GIT PULL 00/12] perf/core improvements, fixes and cleanups Arnaldo Carvalho de Melo
                   ` (9 preceding siblings ...)
  2011-03-15 20:04 ` [PATCH 10/12] perf script: Add support for dumping symbols Arnaldo Carvalho de Melo
@ 2011-03-15 20:05 ` Arnaldo Carvalho de Melo
  2011-03-15 20:05 ` [PATCH 12/12] perf evlist: New command to list the names of events present in a perf.data file Arnaldo Carvalho de Melo
  2011-03-16 12:53 ` [GIT PULL 00/12] perf/core improvements, fixes and cleanups Ingo Molnar
  12 siblings, 0 replies; 14+ messages in thread
From: Arnaldo Carvalho de Melo @ 2011-03-15 20:05 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, David Ahern, Frederic Weisbecker, Ingo Molnar,
	Paul Mackerras, Peter Zijlstra, Thomas Gleixner,
	Arnaldo Carvalho de Melo

From: David Ahern <daahern@cisco.com>

Custom fields set for each type by prepending field argument with type.
For file with multiple event types (e.g., trace and S/W) display of an
event type suppressed by setting output fields to "".

e.g.,
perf record -ga -e sched:sched_switch -e cpu-clock -c 10000000 -R -- sleep 1
perf script

openssl 11496 [000]  9711.807107: cpu-clock-msecs:
        ffffffff810c22dc arch_local_irq_restore ([kernel.kallsyms])
        ffffffff810c518c __alloc_pages_nodemask ([kernel.kallsyms])
        ffffffff810297b2 pte_alloc_one ([kernel.kallsyms])
        ffffffff810d8b98 __pte_alloc ([kernel.kallsyms])
        ffffffff810daf07 handle_mm_fault ([kernel.kallsyms])
        ffffffff8138763a do_page_fault ([kernel.kallsyms])
        ffffffff81384a65 page_fault ([kernel.kallsyms])
            7f6130507d70 asn1_check_tlen (/lib64/libcrypto.so.1.0.0c)
                       0  ()

         openssl 11496 [000]  9711.808042: sched_switch: prev_comm=openssl ...
     kworker/0:0     4 [000]  9711.808067: sched_switch: prev_comm=kworker/...
         swapper     0 [001]  9711.808090: sched_switch: prev_comm=kworker/...
            sshd 11451 [001]  9711.808185: sched_switch: prev_comm=sshd pre...
swapper     0 [001]  9711.816155: cpu-clock-msecs:
        ffffffff81023609 native_safe_halt ([kernel.kallsyms])
        ffffffff8100132a cpu_idle ([kernel.kallsyms])
        ffffffff8137cf9b start_secondary ([kernel.kallsyms])

openssl 11496 [000]  9711.817104: cpu-clock-msecs:
            7f61304ad723 AES_cbc_encrypt (/lib64/libcrypto.so.1.0.0c)
            7fff3402f950  ()
        12f0debc9a785634  ()

swapper     0 [001]  9711.826155: cpu-clock-msecs:
        ffffffff81023609 native_safe_halt ([kernel.kallsyms])
        ffffffff8100132a cpu_idle ([kernel.kallsyms])
        ffffffff8137cf9b start_secondary ([kernel.kallsyms])

To suppress trace events within the file and use default output for S/W events:
perf script -f trace:

or to suppress S/W events and do default display for trace events:
perf script -f sw:

Custom field selections:
perf script -f sw:comm,tid,time -f trace:time,trace

         openssl 11496  9711.797162:
         swapper     0  9711.807071:
         openssl 11496  9711.807107:
 9711.808042: prev_comm=openssl prev_pid=11496 prev_prio=120 prev_state=R ...
 9711.808067: prev_comm=kworker/0:0 prev_pid=4 prev_prio=120 prev_state=S ...
 9711.808090: prev_comm=kworker/0:0 prev_pid=0 prev_prio=120 prev_state=R ...
 9711.808185: prev_comm=sshd prev_pid=11451 prev_prio=120 prev_state=S ==>...
         swapper     0  9711.816155:
         openssl 11496  9711.817104:
         swapper     0  9711.826155:

Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
LKML-Reference: <1299734608-5223-7-git-send-email-daahern@cisco.com>
Signed-off-by: David Ahern <daahern@cisco.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-script.txt |    5 +-
 tools/perf/builtin-script.c              |  155 +++++++++++++++++++++++-------
 tools/perf/util/parse-events.c           |   22 ++++
 tools/perf/util/parse-events.h           |    1 +
 4 files changed, 147 insertions(+), 36 deletions(-)

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index c64118a..66f040b 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -115,7 +115,10 @@ OPTIONS
 -f::
 --fields
         Comma separated list of fields to print. Options are:
-        comm, tid, pid, time, cpu, event, trace, sym
+        comm, tid, pid, time, cpu, event, trace, sym. Field
+        list must be prepended with the type, trace, sw or hw,
+        to indicate to which event type the field list applies.
+        e.g., -f sw:comm,tid,time,sym  and -f trace:time,cpu,trace
 
 -k::
 --vmlinux=<file>::
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index b45b09c..9f5fc54 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -12,6 +12,8 @@
 #include "util/trace-event.h"
 #include "util/parse-options.h"
 #include "util/util.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
 
 static char const		*script_name;
 static char const		*generate_script_lang;
@@ -47,16 +49,65 @@ struct output_option {
 };
 
 /* default set to maintain compatibility with current format */
-static u64 output_fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | \
-			   PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | \
-			   PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE;
+static u64 output_fields[PERF_TYPE_MAX] = {
+	[PERF_TYPE_HARDWARE] = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | \
+			       PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | \
+			       PERF_OUTPUT_EVNAME | PERF_OUTPUT_SYM,
+
+	[PERF_TYPE_SOFTWARE] = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | \
+			       PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | \
+			       PERF_OUTPUT_EVNAME | PERF_OUTPUT_SYM,
+
+	[PERF_TYPE_TRACEPOINT] = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | \
+				 PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | \
+				 PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE,
+};
 
 static bool output_set_by_user;
 
-#define PRINT_FIELD(x)  (output_fields & PERF_OUTPUT_##x)
+#define PRINT_FIELD(x)  (output_fields[attr->type] & PERF_OUTPUT_##x)
+
+static int perf_session__check_attr(struct perf_session *session,
+				    struct perf_event_attr *attr)
+{
+	if (PRINT_FIELD(TRACE) &&
+		!perf_session__has_traces(session, "record -R"))
+		return -EINVAL;
+
+	if (PRINT_FIELD(SYM)) {
+		if (!(session->sample_type & PERF_SAMPLE_IP)) {
+			pr_err("Samples do not contain IP data.\n");
+			return -EINVAL;
+		}
+		if (!no_callchain &&
+		    !(session->sample_type & PERF_SAMPLE_CALLCHAIN))
+			symbol_conf.use_callchain = false;
+	}
+
+	if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) &&
+		!(session->sample_type & PERF_SAMPLE_TID)) {
+		pr_err("Samples do not contain TID/PID data.\n");
+		return -EINVAL;
+	}
+
+	if (PRINT_FIELD(TIME) &&
+		!(session->sample_type & PERF_SAMPLE_TIME)) {
+		pr_err("Samples do not contain timestamps.\n");
+		return -EINVAL;
+	}
+
+	if (PRINT_FIELD(CPU) &&
+		!(session->sample_type & PERF_SAMPLE_CPU)) {
+		pr_err("Samples do not contain cpu.\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
 
 static void print_sample_start(struct perf_sample *sample,
-			       struct thread *thread)
+			       struct thread *thread,
+			       struct perf_event_attr *attr)
 {
 	int type;
 	struct event *event;
@@ -97,10 +148,13 @@ static void print_sample_start(struct perf_sample *sample,
 	}
 
 	if (PRINT_FIELD(EVNAME)) {
-		type = trace_parse_common_type(sample->raw_data);
-		event = trace_find_event(type);
-		if (event)
-			evname = event->name;
+		if (attr->type == PERF_TYPE_TRACEPOINT) {
+			type = trace_parse_common_type(sample->raw_data);
+			event = trace_find_event(type);
+			if (event)
+				evname = event->name;
+		} else
+			evname = __event_name(attr->type, attr->config);
 
 		printf("%s: ", evname ? evname : "(unknown)");
 	}
@@ -108,10 +162,27 @@ static void print_sample_start(struct perf_sample *sample,
 
 static void process_event(union perf_event *event __unused,
 			  struct perf_sample *sample,
-			  struct perf_session *session __unused,
+			  struct perf_session *session,
 			  struct thread *thread)
 {
-	print_sample_start(sample, thread);
+	struct perf_event_attr *attr;
+	struct perf_evsel *evsel;
+
+	evsel = perf_evlist__id2evsel(session->evlist, sample->id);
+	if (evsel == NULL) {
+		pr_err("Invalid data. Contains samples with id not in "
+		       "its header!\n");
+		return;
+	}
+	attr = &evsel->attr;
+
+	if (output_fields[attr->type] == 0)
+		return;
+
+	if (perf_session__check_attr(session, attr) < 0)
+		return;
+
+	print_sample_start(sample, thread, attr);
 
 	if (PRINT_FIELD(TRACE))
 		print_trace_event(sample->cpu, sample->raw_data,
@@ -183,19 +254,17 @@ static int process_sample_event(union perf_event *event,
 		return -1;
 	}
 
-	if (session->sample_type & PERF_SAMPLE_RAW) {
-		if (debug_mode) {
-			if (sample->time < last_timestamp) {
-				pr_err("Samples misordered, previous: %" PRIu64
-					" this: %" PRIu64 "\n", last_timestamp,
-					sample->time);
-				nr_unordered++;
-			}
-			last_timestamp = sample->time;
-			return 0;
+	if (debug_mode) {
+		if (sample->time < last_timestamp) {
+			pr_err("Samples misordered, previous: %" PRIu64
+				" this: %" PRIu64 "\n", last_timestamp,
+				sample->time);
+			nr_unordered++;
 		}
-		scripting_ops->process_event(event, sample, session, thread);
+		last_timestamp = sample->time;
+		return 0;
 	}
+	scripting_ops->process_event(event, sample, session, thread);
 
 	session->hists.stats.total_period += sample->period;
 	return 0;
@@ -391,21 +460,40 @@ static int parse_output_fields(const struct option *opt __used,
 	int i, imax = sizeof(all_output_options) / sizeof(struct output_option);
 	int rc = 0;
 	char *str = strdup(arg);
+	int type = -1;
 
 	if (!str)
 		return -ENOMEM;
 
-	tok = strtok(str, ",");
+	tok = strtok(str, ":");
 	if (!tok) {
-		fprintf(stderr, "Invalid field string.");
+		fprintf(stderr,
+			"Invalid field string - not prepended with type.");
+		return -EINVAL;
+	}
+
+	/* first word should state which event type user
+	 * is specifying the fields
+	 */
+	if (!strcmp(tok, "hw"))
+		type = PERF_TYPE_HARDWARE;
+	else if (!strcmp(tok, "sw"))
+		type = PERF_TYPE_SOFTWARE;
+	else if (!strcmp(tok, "trace"))
+		type = PERF_TYPE_TRACEPOINT;
+	else {
+		fprintf(stderr, "Invalid event type in field string.");
 		return -EINVAL;
 	}
 
-	output_fields = 0;
+	output_fields[type] = 0;
 	while (1) {
+		tok = strtok(NULL, ",");
+		if (!tok)
+			break;
 		for (i = 0; i < imax; ++i) {
 			if (strcmp(tok, all_output_options[i].str) == 0) {
-				output_fields |= all_output_options[i].field;
+				output_fields[type] |= all_output_options[i].field;
 				break;
 			}
 		}
@@ -414,10 +502,11 @@ static int parse_output_fields(const struct option *opt __used,
 			rc = -EINVAL;
 			break;
 		}
+	}
 
-		tok = strtok(NULL, ",");
-		if (!tok)
-			break;
+	if (output_fields[type] == 0) {
+		pr_debug("No fields requested for %s type. "
+			 "Events will not be displayed\n", event_type(type));
 	}
 
 	output_set_by_user = true;
@@ -747,7 +836,7 @@ static const struct option options[] = {
 	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
 		    "Look for files with symbols relative to this directory"),
 	OPT_CALLBACK('f', "fields", NULL, "str",
-		     "comma separated output fields. Options: comm,tid,pid,time,cpu,event,trace,sym",
+		     "comma separated output fields prepend with 'type:'. Valid types: hw,sw,trace. Fields: comm,tid,pid,time,cpu,event,trace,sym",
 		     parse_output_fields),
 
 	OPT_END()
@@ -929,15 +1018,11 @@ int cmd_script(int argc, const char **argv, const char *prefix __used)
 	if (session == NULL)
 		return -ENOMEM;
 
-	if (!no_callchain && (session->sample_type & PERF_SAMPLE_CALLCHAIN))
+	if (!no_callchain)
 		symbol_conf.use_callchain = true;
 	else
 		symbol_conf.use_callchain = false;
 
-	if (strcmp(input_name, "-") &&
-	    !perf_session__has_traces(session, "record -R"))
-		return -EINVAL;
-
 	if (generate_script_lang) {
 		struct stat perf_stat;
 		int input;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 54a7e26..952b4ae 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -263,6 +263,28 @@ static char *event_cache_name(u8 cache_type, u8 cache_op, u8 cache_result)
 	return name;
 }
 
+const char *event_type(int type)
+{
+	switch (type) {
+	case PERF_TYPE_HARDWARE:
+		return "hardware";
+
+	case PERF_TYPE_SOFTWARE:
+		return "software";
+
+	case PERF_TYPE_TRACEPOINT:
+		return "tracepoint";
+
+	case PERF_TYPE_HW_CACHE:
+		return "hardware-cache";
+
+	default:
+		break;
+	}
+
+	return "unknown";
+}
+
 const char *event_name(struct perf_evsel *evsel)
 {
 	u64 config = evsel->attr.config;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 212f88e..746d3fc 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -20,6 +20,7 @@ struct tracepoint_path {
 extern struct tracepoint_path *tracepoint_id_to_path(u64 config);
 extern bool have_tracepoints(struct list_head *evlist);
 
+const char *event_type(int type);
 const char *event_name(struct perf_evsel *event);
 extern const char *__event_name(int type, u64 config);
 
-- 
1.6.2.5


^ permalink raw reply	[flat|nested] 14+ messages in thread

* [PATCH 12/12] perf evlist: New command to list the names of events present in a perf.data file
  2011-03-15 20:04 [GIT PULL 00/12] perf/core improvements, fixes and cleanups Arnaldo Carvalho de Melo
                   ` (10 preceding siblings ...)
  2011-03-15 20:05 ` [PATCH 11/12] perf script: Add support for H/W and S/W events Arnaldo Carvalho de Melo
@ 2011-03-15 20:05 ` Arnaldo Carvalho de Melo
  2011-03-16 12:53 ` [GIT PULL 00/12] perf/core improvements, fixes and cleanups Ingo Molnar
  12 siblings, 0 replies; 14+ messages in thread
From: Arnaldo Carvalho de Melo @ 2011-03-15 20:05 UTC (permalink / raw)
  To: Ingo Molnar
  Cc: linux-kernel, Arnaldo Carvalho de Melo, Frederic Weisbecker,
	Ingo Molnar, Mike Galbraith, Paul Mackerras, Peter Zijlstra,
	Stephane Eranian, Tom Zanussi

From: Arnaldo Carvalho de Melo <acme@redhat.com>

[root@emilia ~]# perf record -a -e sched:* -e timer:timer* sleep 5
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.172 MB perf.data (~7530 samples) ]
[root@emilia ~]# perf evlist
sched:sched_kthread_stop
sched:sched_kthread_stop_ret
sched:sched_wakeup
sched:sched_wakeup_new
sched:sched_switch
sched:sched_migrate_task
sched:sched_process_free
sched:sched_process_exit
sched:sched_wait_task
sched:sched_process_wait
sched:sched_process_fork
sched:sched_stat_wait
sched:sched_stat_sleep
sched:sched_stat_iowait
sched:sched_stat_runtime
sched:sched_pi_setprio
timer:timer_init
timer:timer_start
timer:timer_expire_entry
timer:timer_expire_exit
timer:timer_cancel
[root@emilia ~]#

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-evlist.txt |   26 ++++++++++++++
 tools/perf/Makefile                      |    1 +
 tools/perf/builtin-evlist.c              |   54 ++++++++++++++++++++++++++++++
 tools/perf/builtin.h                     |    1 +
 tools/perf/command-list.txt              |    1 +
 tools/perf/perf.c                        |    1 +
 6 files changed, 84 insertions(+), 0 deletions(-)
 create mode 100644 tools/perf/Documentation/perf-evlist.txt
 create mode 100644 tools/perf/builtin-evlist.c

diff --git a/tools/perf/Documentation/perf-evlist.txt b/tools/perf/Documentation/perf-evlist.txt
new file mode 100644
index 0000000..0cada9e
--- /dev/null
+++ b/tools/perf/Documentation/perf-evlist.txt
@@ -0,0 +1,26 @@
+perf-evlist(1)
+==============
+
+NAME
+----
+perf-evlist - List the event names in a perf.data file
+
+SYNOPSIS
+--------
+[verse]
+'perf evlist <options>'
+
+DESCRIPTION
+-----------
+This command displays the names of events sampled in a perf.data file.
+
+OPTIONS
+-------
+-i::
+--input=::
+        Input file name. (default: perf.data)
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-list[1],
+linkperf:perf-report[1]
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 9b84218..158c30e 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -338,6 +338,7 @@ endif
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-diff.o
+BUILTIN_OBJS += $(OUTPUT)builtin-evlist.o
 BUILTIN_OBJS += $(OUTPUT)builtin-help.o
 BUILTIN_OBJS += $(OUTPUT)builtin-sched.o
 BUILTIN_OBJS += $(OUTPUT)builtin-buildid-list.o
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
new file mode 100644
index 0000000..4c5e9e0
--- /dev/null
+++ b/tools/perf/builtin-evlist.c
@@ -0,0 +1,54 @@
+/*
+ * Builtin evlist command: Show the list of event selectors present
+ * in a perf.data file.
+ */
+#include "builtin.h"
+
+#include "util/util.h"
+
+#include <linux/list.h>
+
+#include "perf.h"
+#include "util/evlist.h"
+#include "util/evsel.h"
+#include "util/parse-events.h"
+#include "util/parse-options.h"
+#include "util/session.h"
+
+static char const *input_name = "perf.data";
+
+static int __cmd_evlist(void)
+{
+	struct perf_session *session;
+	struct perf_evsel *pos;
+
+	session = perf_session__new(input_name, O_RDONLY, 0, false, NULL);
+	if (session == NULL)
+		return -ENOMEM;
+
+	list_for_each_entry(pos, &session->evlist->entries, node)
+		printf("%s\n", event_name(pos));
+
+	perf_session__delete(session);
+	return 0;
+}
+
+static const char * const evlist_usage[] = {
+	"perf evlist [<options>]",
+	NULL
+};
+
+static const struct option options[] = {
+	OPT_STRING('i', "input", &input_name, "file",
+		    "input file name"),
+	OPT_END()
+};
+
+int cmd_evlist(int argc, const char **argv, const char *prefix __used)
+{
+	argc = parse_options(argc, argv, options, evlist_usage, 0);
+	if (argc)
+		usage_with_options(evlist_usage, options);
+
+	return __cmd_evlist();
+}
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index c7798c7..4702e24 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -19,6 +19,7 @@ extern int cmd_bench(int argc, const char **argv, const char *prefix);
 extern int cmd_buildid_cache(int argc, const char **argv, const char *prefix);
 extern int cmd_buildid_list(int argc, const char **argv, const char *prefix);
 extern int cmd_diff(int argc, const char **argv, const char *prefix);
+extern int cmd_evlist(int argc, const char **argv, const char *prefix);
 extern int cmd_help(int argc, const char **argv, const char *prefix);
 extern int cmd_sched(int argc, const char **argv, const char *prefix);
 extern int cmd_list(int argc, const char **argv, const char *prefix);
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index 16b5088..d695fe4 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -8,6 +8,7 @@ perf-bench			mainporcelain common
 perf-buildid-cache		mainporcelain common
 perf-buildid-list		mainporcelain common
 perf-diff			mainporcelain common
+perf-evlist			mainporcelain common
 perf-inject			mainporcelain common
 perf-list			mainporcelain common
 perf-sched			mainporcelain common
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 595d0f4..ec635b7 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -313,6 +313,7 @@ static void handle_internal_command(int argc, const char **argv)
 		{ "buildid-cache", cmd_buildid_cache, 0 },
 		{ "buildid-list", cmd_buildid_list, 0 },
 		{ "diff",	cmd_diff,	0 },
+		{ "evlist",	cmd_evlist,	0 },
 		{ "help",	cmd_help,	0 },
 		{ "list",	cmd_list,	0 },
 		{ "record",	cmd_record,	0 },
-- 
1.6.2.5


^ permalink raw reply	[flat|nested] 14+ messages in thread

* Re: [GIT PULL 00/12] perf/core improvements, fixes and cleanups
  2011-03-15 20:04 [GIT PULL 00/12] perf/core improvements, fixes and cleanups Arnaldo Carvalho de Melo
                   ` (11 preceding siblings ...)
  2011-03-15 20:05 ` [PATCH 12/12] perf evlist: New command to list the names of events present in a perf.data file Arnaldo Carvalho de Melo
@ 2011-03-16 12:53 ` Ingo Molnar
  12 siblings, 0 replies; 14+ messages in thread
From: Ingo Molnar @ 2011-03-16 12:53 UTC (permalink / raw)
  To: Arnaldo Carvalho de Melo
  Cc: linux-kernel, David Ahern, Frederic Weisbecker, Mike Galbraith,
	Paul Mackerras, Peter Zijlstra, Stephane Eranian,
	Thomas Gleixner, Tom Zanussi, Arnaldo Carvalho de Melo


* Arnaldo Carvalho de Melo <acme@infradead.org> wrote:

> Hi Ingo,
> 
>         Please consider pulling from:
> 
> git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux-2.6 perf/core
> 
> Regards,
> 
> - Arnaldo
> 
> Arnaldo Carvalho de Melo (5):
>   perf top: Remove redundant perf_top->sym_counter
>   perf top: Remove redundant syme->origin field
>   perf symbols: Rename dso->origin to dso->symtab_type
>   perf symbol: Move sym_entry->skip to symbol->ignore
>   perf evlist: New command to list the names of events present in a perf.data file
> 
> David Ahern (6):
>   perf script: Change process_event prototype
>   perf tracing: Remove print_graph_cpu and print_graph_proc from trace-event-parse
>   perf script: Move printing of 'common' data from print_event and rename
>   perf script: Support custom field selection for output
>   perf script: Add support for dumping symbols
>   perf script: Add support for H/W and S/W events
> 
> Frederic Weisbecker (1):
>   perf stat: Provide support for filters
> 
>  tools/perf/Documentation/perf-evlist.txt           |   26 ++
>  tools/perf/Documentation/perf-script.txt           |   22 ++
>  tools/perf/Makefile                                |    1 +
>  tools/perf/builtin-evlist.c                        |   54 ++++
>  tools/perf/builtin-script.c                        |  300 ++++++++++++++++++--
>  tools/perf/builtin-stat.c                          |    8 +
>  tools/perf/builtin-top.c                           |   20 +-
>  tools/perf/builtin.h                               |    1 +
>  tools/perf/command-list.txt                        |    1 +
>  tools/perf/perf.c                                  |    1 +
>  tools/perf/util/annotate.c                         |    2 +-
>  tools/perf/util/parse-events.c                     |   22 ++
>  tools/perf/util/parse-events.h                     |    1 +
>  .../perf/util/scripting-engines/trace-event-perl.c |   11 +-
>  .../util/scripting-engines/trace-event-python.c    |   11 +-
>  tools/perf/util/session.c                          |   61 ++++
>  tools/perf/util/session.h                          |    4 +
>  tools/perf/util/symbol.c                           |   64 ++--
>  tools/perf/util/symbol.h                           |   31 ++-
>  tools/perf/util/top.c                              |    6 +-
>  tools/perf/util/top.h                              |    4 +-
>  tools/perf/util/trace-event-parse.c                |  110 +-------
>  tools/perf/util/trace-event-scripting.c            |    9 +-
>  tools/perf/util/trace-event.h                      |   10 +-
>  24 files changed, 580 insertions(+), 200 deletions(-)
>  create mode 100644 tools/perf/Documentation/perf-evlist.txt
>  create mode 100644 tools/perf/builtin-evlist.c

Pulled, thanks a lot Arnaldo!

	Ingo

^ permalink raw reply	[flat|nested] 14+ messages in thread

end of thread, other threads:[~2011-03-16 12:53 UTC | newest]

Thread overview: 14+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2011-03-15 20:04 [GIT PULL 00/12] perf/core improvements, fixes and cleanups Arnaldo Carvalho de Melo
2011-03-15 20:04 ` [PATCH 01/12] perf top: Remove redundant perf_top->sym_counter Arnaldo Carvalho de Melo
2011-03-15 20:04 ` [PATCH 02/12] perf top: Remove redundant syme->origin field Arnaldo Carvalho de Melo
2011-03-15 20:04 ` [PATCH 03/12] perf symbols: Rename dso->origin to dso->symtab_type Arnaldo Carvalho de Melo
2011-03-15 20:04 ` [PATCH 04/12] perf symbol: Move sym_entry->skip to symbol->ignore Arnaldo Carvalho de Melo
2011-03-15 20:04 ` [PATCH 05/12] perf stat: Provide support for filters Arnaldo Carvalho de Melo
2011-03-15 20:04 ` [PATCH 06/12] perf script: Change process_event prototype Arnaldo Carvalho de Melo
2011-03-15 20:04 ` [PATCH 07/12] perf tracing: Remove print_graph_cpu and print_graph_proc from trace-event-parse Arnaldo Carvalho de Melo
2011-03-15 20:04 ` [PATCH 08/12] perf script: Move printing of 'common' data from print_event and rename Arnaldo Carvalho de Melo
2011-03-15 20:04 ` [PATCH 09/12] perf script: Support custom field selection for output Arnaldo Carvalho de Melo
2011-03-15 20:04 ` [PATCH 10/12] perf script: Add support for dumping symbols Arnaldo Carvalho de Melo
2011-03-15 20:05 ` [PATCH 11/12] perf script: Add support for H/W and S/W events Arnaldo Carvalho de Melo
2011-03-15 20:05 ` [PATCH 12/12] perf evlist: New command to list the names of events present in a perf.data file Arnaldo Carvalho de Melo
2011-03-16 12:53 ` [GIT PULL 00/12] perf/core improvements, fixes and cleanups Ingo Molnar

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

Powered by JetHome