[GIT PULL 00/10] perf/core improvements and fixes

[GIT PULL 00/10] perf/core improvements and fixes

[Arnaldo Carvalho de Melo]

From: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>

Hi Ingo,

	Please consider pulling,

- Arnaldo

The following changes since commit caea6cf52139116e43e615d87fcbf9823e197fdf:

  Merge branch 'uprobes/core' of git://git.kernel.org/pub/scm/linux/kernel/git/oleg/misc into perf/core (2013-11-11 09:44:16 +0100)

are available in the git repository at:


  git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux tags/perf-core-for-mingo

for you to fetch changes up to 67c1e4a53b17894e6a24f95057cc374c4be051cb:

  perf tests: Use lower sample_freq in sw clock event period test (2013-11-11 16:43:34 -0300)

----------------------------------------------------------------
perf/core improvements and fixes.

. Prevent condition that all sort keys are elided, fix from Namhyung Kim.

. Synthesize non-exec MMAP records when --data used, allowing the resolution of
  data addresses to symbols (global variables, etc).

. Don't force a refresh during progress update in the TUI, greatly reducing
  startup costs, fix from Patrick Palka.

. Fix sw clock event period test wrt not checking if using > max_sample_freq.

. Code cleanups by David Ahern and Adrian Hunter.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

----------------------------------------------------------------
Adrian Hunter (1):
      perf record: Use correct return type for write()

Arnaldo Carvalho de Melo (6):
      perf evsel: Remove idx parm from constructor
      perf record: Synthesize non-exec MMAP records when --data used
      perf machine: Introduce synthesize_threads method out of open coded equivalent
      perf machine: Simplify synthesize_threads method
      perf tests: Check return of perf_evlist__open sw clock event period test
      perf tests: Use lower sample_freq in sw clock event period test

David Ahern (1):
      perf record: Move existing write_output into helper function

Namhyung Kim (1):
      perf tools: Prevent condition that all sort keys are elided

Patrick Palka (1):
      perf ui tui progress: Don't force a refresh during progress update

 tools/perf/builtin-kvm.c                  | 14 ++-------
 tools/perf/builtin-record.c               | 21 ++++++-------
 tools/perf/builtin-top.c                  | 10 ++-----
 tools/perf/builtin-trace.c                | 24 +++++----------
 tools/perf/tests/code-reading.c           |  2 +-
 tools/perf/tests/evsel-tp-sched.c         |  4 +--
 tools/perf/tests/mmap-basic.c             |  2 +-
 tools/perf/tests/open-syscall-all-cpus.c  |  2 +-
 tools/perf/tests/open-syscall-tp-fields.c |  2 +-
 tools/perf/tests/open-syscall.c           |  2 +-
 tools/perf/tests/sw-clock.c               | 13 ++++++--
 tools/perf/ui/tui/progress.c              |  3 +-
 tools/perf/util/event.c                   | 50 ++++++++++++++++++-------------
 tools/perf/util/event.h                   |  4 +--
 tools/perf/util/evlist.c                  |  9 +++---
 tools/perf/util/evsel.c                   |  4 +--
 tools/perf/util/evsel.h                   | 15 ++++++++--
 tools/perf/util/header.c                  |  4 +--
 tools/perf/util/machine.c                 | 12 ++++++++
 tools/perf/util/machine.h                 | 12 ++++++++
 tools/perf/util/parse-events.c            |  6 ++--
 tools/perf/util/sort.c                    | 13 ++++++++
 22 files changed, 133 insertions(+), 95 deletions(-)

[PATCH 01/10] perf ui tui progress: Don't force a refresh during progress update

[Arnaldo Carvalho de Melo]

From: Patrick Palka <patrick@parcs.ath.cx>

Each call to tui_progress__update() would forcibly refresh the entire
screen.  This is somewhat inefficient and causes noticable flickering
during the startup of perf-report, especially on large/slow terminals.

It looks like the force-refresh in tui_progress__update() serves no
purpose other than to clear the screen so that the progress bar of a
previous operation does not subsume that of a subsequent operation.  But
we can do just that in a much more efficient manner by clearing only the
region that a previous progress bar may have occupied before repainting
the new progress bar.  Then the force-refresh could be removed with no
change in visuals.

This patch disables the slow force-refresh in tui_progress__update() and
instead calls SLsmg_fill_region() on the entire area that the progress
bar may occupy before repainting it.  This change makes the startup of
perf-report much faster and appear much "smoother".

It turns out that this was a big bottleneck in the startup speed of
perf-report -- with this patch, perf-report starts up ~2x faster (1.1s
vs 0.55s) on my machines.  (These numbers were measured by running "time
perf report" on an 8MB perf.data and pressing 'q' immediately.)

Signed-off-by: Patrick Palka <patrick@parcs.ath.cx>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1382747149-9716-1-git-send-email-patrick@parcs.ath.cx
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/ui/tui/progress.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/perf/ui/tui/progress.c b/tools/perf/ui/tui/progress.c
index 3e2d936d7443..c61d14b101e0 100644
--- a/tools/perf/ui/tui/progress.c
+++ b/tools/perf/ui/tui/progress.c
@@ -18,13 +18,14 @@ static void tui_progress__update(struct ui_progress *p)
 	if (p->total == 0)
 		return;
 
-	ui__refresh_dimensions(true);
+	ui__refresh_dimensions(false);
 	pthread_mutex_lock(&ui__lock);
 	y = SLtt_Screen_Rows / 2 - 2;
 	SLsmg_set_color(0);
 	SLsmg_draw_box(y, 0, 3, SLtt_Screen_Cols);
 	SLsmg_gotorc(y++, 1);
 	SLsmg_write_string((char *)p->title);
+	SLsmg_fill_region(y, 1, 1, SLtt_Screen_Cols - 2, ' ');
 	SLsmg_set_color(HE_COLORSET_SELECTED);
 	bar = ((SLtt_Screen_Cols - 2) * p->curr) / p->total;
 	SLsmg_fill_region(y, 1, 1, bar, ' ');
-- 
1.8.1.4

[PATCH 02/10] perf evsel: Remove idx parm from constructor

[Arnaldo Carvalho de Melo]

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

Most uses of the evsel constructor are followed by a call to
perf_evlist__add with an idex of evlist->nr_entries, so make rename
the current constructor to perf_evsel__new_idx and remove the need
for passing the constructor for the common case.

We still need the new_idx variant because the way groups are handled,
with evsel->nr_members holding the number of entries in an evlist,
partitioning the evlist into sublists inside a single linked list.

This asks for a clarifying refactoring, but for now simplify the non
parser cases, so that tool writers don't have to bother with evsel idx
setting.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-zy9tskx6jqm2rmw7468zze2a@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c                | 13 +++++--------
 tools/perf/tests/evsel-tp-sched.c         |  4 ++--
 tools/perf/tests/mmap-basic.c             |  2 +-
 tools/perf/tests/open-syscall-all-cpus.c  |  2 +-
 tools/perf/tests/open-syscall-tp-fields.c |  2 +-
 tools/perf/tests/open-syscall.c           |  2 +-
 tools/perf/tests/sw-clock.c               |  2 +-
 tools/perf/util/evlist.c                  |  9 +++++----
 tools/perf/util/evsel.c                   |  4 ++--
 tools/perf/util/evsel.h                   | 15 +++++++++++++--
 tools/perf/util/header.c                  |  4 ++--
 tools/perf/util/parse-events.c            |  6 +++---
 12 files changed, 37 insertions(+), 28 deletions(-)

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 329b7832b5da..68943cad70d4 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -149,10 +149,9 @@ static void perf_evsel__delete_priv(struct perf_evsel *evsel)
 	perf_evsel__delete(evsel);
 }
 
-static struct perf_evsel *perf_evsel__syscall_newtp(const char *direction,
-						    void *handler, int idx)
+static struct perf_evsel *perf_evsel__syscall_newtp(const char *direction, void *handler)
 {
-	struct perf_evsel *evsel = perf_evsel__newtp("raw_syscalls", direction, idx);
+	struct perf_evsel *evsel = perf_evsel__newtp("raw_syscalls", direction);
 
 	if (evsel) {
 		evsel->priv = malloc(sizeof(struct syscall_tp));
@@ -186,17 +185,16 @@ static int perf_evlist__add_syscall_newtp(struct perf_evlist *evlist,
 					  void *sys_exit_handler)
 {
 	int ret = -1;
-	int idx = evlist->nr_entries;
 	struct perf_evsel *sys_enter, *sys_exit;
 
-	sys_enter = perf_evsel__syscall_newtp("sys_enter", sys_enter_handler, idx++);
+	sys_enter = perf_evsel__syscall_newtp("sys_enter", sys_enter_handler);
 	if (sys_enter == NULL)
 		goto out;
 
 	if (perf_evsel__init_sc_tp_ptr_field(sys_enter, args))
 		goto out_delete_sys_enter;
 
-	sys_exit = perf_evsel__syscall_newtp("sys_exit", sys_exit_handler, idx++);
+	sys_exit = perf_evsel__syscall_newtp("sys_exit", sys_exit_handler);
 	if (sys_exit == NULL)
 		goto out_delete_sys_enter;
 
@@ -1824,8 +1822,7 @@ static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);
 
 static void perf_evlist__add_vfs_getname(struct perf_evlist *evlist)
 {
-	struct perf_evsel *evsel = perf_evsel__newtp("probe", "vfs_getname",
-						     evlist->nr_entries);
+	struct perf_evsel *evsel = perf_evsel__newtp("probe", "vfs_getname");
 	if (evsel == NULL)
 		return;
 
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index 9b98c1554833..4774f7fbb758 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -32,7 +32,7 @@ static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
 
 int test__perf_evsel__tp_sched_test(void)
 {
-	struct perf_evsel *evsel = perf_evsel__newtp("sched", "sched_switch", 0);
+	struct perf_evsel *evsel = perf_evsel__newtp("sched", "sched_switch");
 	int ret = 0;
 
 	if (evsel == NULL) {
@@ -63,7 +63,7 @@ int test__perf_evsel__tp_sched_test(void)
 
 	perf_evsel__delete(evsel);
 
-	evsel = perf_evsel__newtp("sched", "sched_wakeup", 0);
+	evsel = perf_evsel__newtp("sched", "sched_wakeup");
 
 	if (perf_evsel__test_field(evsel, "comm", 16, true))
 		ret = -1;
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index a7232c204eb9..d64ab79c6d35 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -65,7 +65,7 @@ int test__basic_mmap(void)
 		char name[64];
 
 		snprintf(name, sizeof(name), "sys_enter_%s", syscall_names[i]);
-		evsels[i] = perf_evsel__newtp("syscalls", name, i);
+		evsels[i] = perf_evsel__newtp("syscalls", name);
 		if (evsels[i] == NULL) {
 			pr_debug("perf_evsel__new\n");
 			goto out_free_evlist;
diff --git a/tools/perf/tests/open-syscall-all-cpus.c b/tools/perf/tests/open-syscall-all-cpus.c
index b0657a9ccda6..5fecdbd2f5f7 100644
--- a/tools/perf/tests/open-syscall-all-cpus.c
+++ b/tools/perf/tests/open-syscall-all-cpus.c
@@ -26,7 +26,7 @@ int test__open_syscall_event_on_all_cpus(void)
 
 	CPU_ZERO(&cpu_set);
 
-	evsel = perf_evsel__newtp("syscalls", "sys_enter_open", 0);
+	evsel = perf_evsel__newtp("syscalls", "sys_enter_open");
 	if (evsel == NULL) {
 		pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
 		goto out_thread_map_delete;
diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c
index 524b221b829b..41cc0badb74b 100644
--- a/tools/perf/tests/open-syscall-tp-fields.c
+++ b/tools/perf/tests/open-syscall-tp-fields.c
@@ -27,7 +27,7 @@ int test__syscall_open_tp_fields(void)
 		goto out;
 	}
 
-	evsel = perf_evsel__newtp("syscalls", "sys_enter_open", 0);
+	evsel = perf_evsel__newtp("syscalls", "sys_enter_open");
 	if (evsel == NULL) {
 		pr_debug("%s: perf_evsel__newtp\n", __func__);
 		goto out_delete_evlist;
diff --git a/tools/perf/tests/open-syscall.c b/tools/perf/tests/open-syscall.c
index befc0671f95d..c1dc7d25f38c 100644
--- a/tools/perf/tests/open-syscall.c
+++ b/tools/perf/tests/open-syscall.c
@@ -15,7 +15,7 @@ int test__open_syscall_event(void)
 		return -1;
 	}
 
-	evsel = perf_evsel__newtp("syscalls", "sys_enter_open", 0);
+	evsel = perf_evsel__newtp("syscalls", "sys_enter_open");
 	if (evsel == NULL) {
 		pr_debug("is debugfs mounted on /sys/kernel/debug?\n");
 		goto out_thread_map_delete;
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 6e2b44ec0749..73c5c37cb27b 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -42,7 +42,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 		return -1;
 	}
 
-	evsel = perf_evsel__new(&attr, 0);
+	evsel = perf_evsel__new(&attr);
 	if (evsel == NULL) {
 		pr_debug("perf_evsel__new\n");
 		goto out_free_evlist;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index b939221efd8d..99dc58e5dcc3 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -117,6 +117,8 @@ void perf_evlist__delete(struct perf_evlist *evlist)
 void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
 {
 	list_add_tail(&entry->node, &evlist->entries);
+	entry->idx = evlist->nr_entries;
+
 	if (!evlist->nr_entries++)
 		perf_evlist__set_id_pos(evlist);
 }
@@ -165,7 +167,7 @@ int perf_evlist__add_default(struct perf_evlist *evlist)
 
 	event_attr_init(&attr);
 
-	evsel = perf_evsel__new(&attr, 0);
+	evsel = perf_evsel__new(&attr);
 	if (evsel == NULL)
 		goto error;
 
@@ -190,7 +192,7 @@ static int perf_evlist__add_attrs(struct perf_evlist *evlist,
 	size_t i;
 
 	for (i = 0; i < nr_attrs; i++) {
-		evsel = perf_evsel__new(attrs + i, evlist->nr_entries + i);
+		evsel = perf_evsel__new_idx(attrs + i, evlist->nr_entries + i);
 		if (evsel == NULL)
 			goto out_delete_partial_list;
 		list_add_tail(&evsel->node, &head);
@@ -249,9 +251,8 @@ perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist,
 int perf_evlist__add_newtp(struct perf_evlist *evlist,
 			   const char *sys, const char *name, void *handler)
 {
-	struct perf_evsel *evsel;
+	struct perf_evsel *evsel = perf_evsel__newtp(sys, name);
 
-	evsel = perf_evsel__newtp(sys, name, evlist->nr_entries);
 	if (evsel == NULL)
 		return -1;
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 5280820ed389..f95653a639a6 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -168,7 +168,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	perf_evsel__calc_id_pos(evsel);
 }
 
-struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
+struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 {
 	struct perf_evsel *evsel = zalloc(sizeof(*evsel));
 
@@ -219,7 +219,7 @@ out:
 	return format;
 }
 
-struct perf_evsel *perf_evsel__newtp(const char *sys, const char *name, int idx)
+struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx)
 {
 	struct perf_evsel *evsel = zalloc(sizeof(*evsel));
 
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 64ec8e1a7a28..0178233abd64 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -96,8 +96,19 @@ struct thread_map;
 struct perf_evlist;
 struct perf_record_opts;
 
-struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx);
-struct perf_evsel *perf_evsel__newtp(const char *sys, const char *name, int idx);
+struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx);
+
+static inline struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr)
+{
+	return perf_evsel__new_idx(attr, 0);
+}
+
+struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx);
+
+static inline struct perf_evsel *perf_evsel__newtp(const char *sys, const char *name)
+{
+	return perf_evsel__newtp_idx(sys, name, 0);
+}
 
 struct event_format *event_format__new(const char *sys, const char *name);
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 26d9520a0c1b..369c03648f88 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2797,7 +2797,7 @@ int perf_session__read_header(struct perf_session *session)
 			perf_event__attr_swap(&f_attr.attr);
 
 		tmp = lseek(fd, 0, SEEK_CUR);
-		evsel = perf_evsel__new(&f_attr.attr, i);
+		evsel = perf_evsel__new(&f_attr.attr);
 
 		if (evsel == NULL)
 			goto out_delete_evlist;
@@ -2916,7 +2916,7 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
 			return -ENOMEM;
 	}
 
-	evsel = perf_evsel__new(&event->attr.attr, evlist->nr_entries);
+	evsel = perf_evsel__new(&event->attr.attr);
 	if (evsel == NULL)
 		return -ENOMEM;
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index c90e55cf7e82..6de6f89c2a61 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -277,7 +277,7 @@ static int __add_event(struct list_head *list, int *idx,
 
 	event_attr_init(attr);
 
-	evsel = perf_evsel__new(attr, (*idx)++);
+	evsel = perf_evsel__new_idx(attr, (*idx)++);
 	if (!evsel)
 		return -ENOMEM;
 
@@ -378,7 +378,7 @@ static int add_tracepoint(struct list_head *list, int *idx,
 {
 	struct perf_evsel *evsel;
 
-	evsel = perf_evsel__newtp(sys_name, evt_name, (*idx)++);
+	evsel = perf_evsel__newtp_idx(sys_name, evt_name, (*idx)++);
 	if (!evsel)
 		return -ENOMEM;
 
@@ -1097,7 +1097,7 @@ static bool is_event_supported(u8 type, unsigned config)
 		.threads = { 0 },
 	};
 
-	evsel = perf_evsel__new(&attr, 0);
+	evsel = perf_evsel__new(&attr);
 	if (evsel) {
 		ret = perf_evsel__open(evsel, NULL, &tmap.map) >= 0;
 		perf_evsel__delete(evsel);
-- 
1.8.1.4

[PATCH 03/10] perf record: Synthesize non-exec MMAP records when --data used

[Arnaldo Carvalho de Melo]

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

When perf_event_attr.mmap_data is set the kernel will generate
PERF_RECORD_MMAP events when non-exec (data, SysV mem) mmaps are
created, so we need to synthesize from /proc/pid/maps for existing
threads, as we do for exec mmaps.

Right now just 'perf record' does it, but any other tool that uses
perf_event__synthesize_thread(s|map) can request it.

Reported-by: Don Zickus <dzickus@redhat.com>
Tested-by: Don Zickus <dzickus@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Bill Gray <bgray@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Joe Mario <jmario@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Richard Fowles <rfowles@redhat.com>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ihwzraikx23ian9txinogvv2@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-kvm.c        |  4 ++--
 tools/perf/builtin-record.c     |  6 ++---
 tools/perf/builtin-top.c        |  4 ++--
 tools/perf/builtin-trace.c      |  4 ++--
 tools/perf/tests/code-reading.c |  2 +-
 tools/perf/util/event.c         | 50 ++++++++++++++++++++++++-----------------
 tools/perf/util/event.h         |  4 ++--
 7 files changed, 42 insertions(+), 32 deletions(-)

diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index cd9f92078aba..f36e8209c300 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1550,10 +1550,10 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 		perf_event__synthesize_thread_map(&kvm->tool,
 						  kvm->evlist->threads,
 						  perf_event__process,
-						  &kvm->session->machines.host);
+						  &kvm->session->machines.host, false);
 	else
 		perf_event__synthesize_threads(&kvm->tool, perf_event__process,
-					       &kvm->session->machines.host);
+					       &kvm->session->machines.host, false);
 
 
 	err = kvm_live_open_events(kvm);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 15280b5e5574..afb252cf6eca 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -482,11 +482,11 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 
 	if (perf_target__has_task(&opts->target))
 		err = perf_event__synthesize_thread_map(tool, evsel_list->threads,
-						  process_synthesized_event,
-						  machine);
+							process_synthesized_event,
+							machine, opts->sample_address);
 	else if (perf_target__has_cpu(&opts->target))
 		err = perf_event__synthesize_threads(tool, process_synthesized_event,
-					       machine);
+						     machine, opts->sample_address);
 	else /* command specified */
 		err = 0;
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 9acca8856ccb..cc96d753db96 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -953,10 +953,10 @@ static int __cmd_top(struct perf_top *top)
 	if (perf_target__has_task(&opts->target))
 		perf_event__synthesize_thread_map(&top->tool, top->evlist->threads,
 						  perf_event__process,
-						  &top->session->machines.host);
+						  &top->session->machines.host, false);
 	else
 		perf_event__synthesize_threads(&top->tool, perf_event__process,
-					       &top->session->machines.host);
+					       &top->session->machines.host, false);
 
 	ret = perf_top__start_counters(top);
 	if (ret)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 68943cad70d4..277c2367e0cf 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1343,10 +1343,10 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 	if (perf_target__has_task(&trace->opts.target)) {
 		err = perf_event__synthesize_thread_map(&trace->tool, evlist->threads,
 							trace__tool_process,
-							trace->host);
+							trace->host, false);
 	} else {
 		err = perf_event__synthesize_threads(&trace->tool, trace__tool_process,
-						     trace->host);
+						     trace->host, false);
 	}
 
 	if (err)
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 49ccc3b2995e..6d9dc198a200 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -441,7 +441,7 @@ static int do_test_code_reading(bool try_kcore)
 	}
 
 	ret = perf_event__synthesize_thread_map(NULL, threads,
-						perf_event__process, machine);
+						perf_event__process, machine, false);
 	if (ret < 0) {
 		pr_debug("perf_event__synthesize_thread_map failed\n");
 		goto out_err;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index ec9ae1114ed4..6e3a846aed0e 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -170,7 +170,8 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 					      union perf_event *event,
 					      pid_t pid, pid_t tgid,
 					      perf_event__handler_t process,
-					      struct machine *machine)
+					      struct machine *machine,
+					      bool mmap_data)
 {
 	char filename[PATH_MAX];
 	FILE *fp;
@@ -188,10 +189,6 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 	}
 
 	event->header.type = PERF_RECORD_MMAP;
-	/*
-	 * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
-	 */
-	event->header.misc = PERF_RECORD_MISC_USER;
 
 	while (1) {
 		char bf[BUFSIZ];
@@ -215,9 +212,17 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 
 		if (n != 5)
 			continue;
+		/*
+		 * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
+		 */
+		event->header.misc = PERF_RECORD_MISC_USER;
 
-		if (prot[2] != 'x')
-			continue;
+		if (prot[2] != 'x') {
+			if (!mmap_data || prot[0] != 'r')
+				continue;
+
+			event->header.misc |= PERF_RECORD_MISC_MMAP_DATA;
+		}
 
 		if (!strcmp(execname, ""))
 			strcpy(execname, anonstr);
@@ -304,20 +309,21 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 				      pid_t pid, int full,
 					  perf_event__handler_t process,
 				      struct perf_tool *tool,
-				      struct machine *machine)
+				      struct machine *machine, bool mmap_data)
 {
 	pid_t tgid = perf_event__synthesize_comm(tool, comm_event, pid, full,
 						 process, machine);
 	if (tgid == -1)
 		return -1;
 	return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
-						  process, machine);
+						  process, machine, mmap_data);
 }
 
 int perf_event__synthesize_thread_map(struct perf_tool *tool,
 				      struct thread_map *threads,
 				      perf_event__handler_t process,
-				      struct machine *machine)
+				      struct machine *machine,
+				      bool mmap_data)
 {
 	union perf_event *comm_event, *mmap_event;
 	int err = -1, thread, j;
@@ -334,7 +340,8 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 	for (thread = 0; thread < threads->nr; ++thread) {
 		if (__event__synthesize_thread(comm_event, mmap_event,
 					       threads->map[thread], 0,
-					       process, tool, machine)) {
+					       process, tool, machine,
+					       mmap_data)) {
 			err = -1;
 			break;
 		}
@@ -356,10 +363,10 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 
 			/* if not, generate events for it */
 			if (need_leader &&
-			    __event__synthesize_thread(comm_event,
-						      mmap_event,
-						      comm_event->comm.pid, 0,
-						      process, tool, machine)) {
+			    __event__synthesize_thread(comm_event, mmap_event,
+						       comm_event->comm.pid, 0,
+						       process, tool, machine,
+						       mmap_data)) {
 				err = -1;
 				break;
 			}
@@ -374,7 +381,7 @@ out:
 
 int perf_event__synthesize_threads(struct perf_tool *tool,
 				   perf_event__handler_t process,
-				   struct machine *machine)
+				   struct machine *machine, bool mmap_data)
 {
 	DIR *proc;
 	struct dirent dirent, *next;
@@ -404,7 +411,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
  		 * one thread couldn't be synthesized.
  		 */
 		__event__synthesize_thread(comm_event, mmap_event, pid, 1,
-					   process, tool, machine);
+					   process, tool, machine, mmap_data);
 	}
 
 	err = 0;
@@ -528,19 +535,22 @@ int perf_event__process_lost(struct perf_tool *tool __maybe_unused,
 
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
 {
-	return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %s\n",
+	return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n",
 		       event->mmap.pid, event->mmap.tid, event->mmap.start,
-		       event->mmap.len, event->mmap.pgoff, event->mmap.filename);
+		       event->mmap.len, event->mmap.pgoff,
+		       (event->header.misc & PERF_RECORD_MISC_MMAP_DATA) ? 'r' : 'x',
+		       event->mmap.filename);
 }
 
 size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp)
 {
 	return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64
-			   " %02x:%02x %"PRIu64" %"PRIu64"]: %s\n",
+			   " %02x:%02x %"PRIu64" %"PRIu64"]: %c %s\n",
 		       event->mmap2.pid, event->mmap2.tid, event->mmap2.start,
 		       event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj,
 		       event->mmap2.min, event->mmap2.ino,
 		       event->mmap2.ino_generation,
+		       (event->header.misc & PERF_RECORD_MISC_MMAP_DATA) ? 'r' : 'x',
 		       event->mmap2.filename);
 }
 
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index f8d70f3003ab..30fec9901e44 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -208,10 +208,10 @@ typedef int (*perf_event__handler_t)(struct perf_tool *tool,
 int perf_event__synthesize_thread_map(struct perf_tool *tool,
 				      struct thread_map *threads,
 				      perf_event__handler_t process,
-				      struct machine *machine);
+				      struct machine *machine, bool mmap_data);
 int perf_event__synthesize_threads(struct perf_tool *tool,
 				   perf_event__handler_t process,
-				   struct machine *machine);
+				   struct machine *machine, bool mmap_data);
 int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 				       perf_event__handler_t process,
 				       struct machine *machine,
-- 
1.8.1.4

[PATCH 04/10] perf machine: Introduce synthesize_threads method out of open coded equivalent

[Arnaldo Carvalho de Melo]

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

Further simplifications to be done on following patch, as most tools
don't use the callback, using instead just the canned
machine__process_event one.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-r1m0vuuj3cat4bampno9yc8d@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-kvm.c    | 15 +++------------
 tools/perf/builtin-record.c | 12 ++----------
 tools/perf/builtin-top.c    | 11 +++--------
 tools/perf/builtin-trace.c  | 11 ++---------
 tools/perf/util/machine.c   | 12 ++++++++++++
 tools/perf/util/machine.h   |  4 ++++
 6 files changed, 26 insertions(+), 39 deletions(-)

diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index f36e8209c300..f5d2c4bccbec 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1544,18 +1544,9 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	}
 	kvm->session->evlist = kvm->evlist;
 	perf_session__set_id_hdr_size(kvm->session);
-
-
-	if (perf_target__has_task(&kvm->opts.target))
-		perf_event__synthesize_thread_map(&kvm->tool,
-						  kvm->evlist->threads,
-						  perf_event__process,
-						  &kvm->session->machines.host, false);
-	else
-		perf_event__synthesize_threads(&kvm->tool, perf_event__process,
-					       &kvm->session->machines.host, false);
-
-
+	machine__synthesize_threads(&kvm->session->machines.host, &kvm->tool,
+				    &kvm->opts.target, kvm->evlist->threads,
+				    perf_event__process, false);
 	err = kvm_live_open_events(kvm);
 	if (err)
 		goto out;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index afb252cf6eca..41d1f37f5348 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -480,16 +480,8 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 					 perf_event__synthesize_guest_os, tool);
 	}
 
-	if (perf_target__has_task(&opts->target))
-		err = perf_event__synthesize_thread_map(tool, evsel_list->threads,
-							process_synthesized_event,
-							machine, opts->sample_address);
-	else if (perf_target__has_cpu(&opts->target))
-		err = perf_event__synthesize_threads(tool, process_synthesized_event,
-						     machine, opts->sample_address);
-	else /* command specified */
-		err = 0;
-
+	err = machine__synthesize_threads(machine, tool, &opts->target, evsel_list->threads,
+					  process_synthesized_event, opts->sample_address);
 	if (err != 0)
 		goto out_delete_session;
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index cc96d753db96..c3a936ef7688 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -950,14 +950,9 @@ static int __cmd_top(struct perf_top *top)
 	if (ret)
 		goto out_delete;
 
-	if (perf_target__has_task(&opts->target))
-		perf_event__synthesize_thread_map(&top->tool, top->evlist->threads,
-						  perf_event__process,
-						  &top->session->machines.host, false);
-	else
-		perf_event__synthesize_threads(&top->tool, perf_event__process,
-					       &top->session->machines.host, false);
-
+	machine__synthesize_threads(&top->session->machines.host, &top->tool,
+				    &opts->target, top->evlist->threads,
+				    perf_event__process, false);
 	ret = perf_top__start_counters(top);
 	if (ret)
 		goto out_delete;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 277c2367e0cf..7690324824db 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1340,15 +1340,8 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 	if (trace->host == NULL)
 		return -ENOMEM;
 
-	if (perf_target__has_task(&trace->opts.target)) {
-		err = perf_event__synthesize_thread_map(&trace->tool, evlist->threads,
-							trace__tool_process,
-							trace->host, false);
-	} else {
-		err = perf_event__synthesize_threads(&trace->tool, trace__tool_process,
-						     trace->host, false);
-	}
-
+	err = machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
+					  evlist->threads, trace__tool_process, false);
 	if (err)
 		symbol__exit();
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index ce034c183a7e..9f2c61d5a9ed 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1394,3 +1394,15 @@ int machine__for_each_thread(struct machine *machine,
 	}
 	return rc;
 }
+
+int machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
+				struct perf_target *target, struct thread_map *threads,
+				perf_event__handler_t process, bool data_mmap)
+{
+	if (perf_target__has_task(target))
+		return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap);
+	else if (perf_target__has_cpu(target))
+		return perf_event__synthesize_threads(tool, process, machine, data_mmap);
+	/* command specified */
+	return 0;
+}
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 2389ba81fafe..14a89d2aecaf 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -4,6 +4,7 @@
 #include <sys/types.h>
 #include <linux/rbtree.h>
 #include "map.h"
+#include "event.h"
 
 struct addr_location;
 struct branch_stack;
@@ -178,4 +179,7 @@ int machine__for_each_thread(struct machine *machine,
 			     int (*fn)(struct thread *thread, void *p),
 			     void *priv);
 
+int machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
+				struct perf_target *target, struct thread_map *threads,
+				perf_event__handler_t process, bool data_mmap);
 #endif /* __PERF_MACHINE_H */
-- 
1.8.1.4

[PATCH 05/10] perf machine: Simplify synthesize_threads method

[Arnaldo Carvalho de Melo]

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

Several tools (top, kvm) don't need to be called back to process each of
the syntheiszed records, instead relying on the machine__process_event
function to change the per machine data structures that represent
threads and mmaps, so provide a way to ask for this common idiom.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-pusqibp8n3c4ynegd1frn4zd@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-kvm.c    |  5 ++---
 tools/perf/builtin-record.c |  4 ++--
 tools/perf/builtin-top.c    |  5 ++---
 tools/perf/builtin-trace.c  |  4 ++--
 tools/perf/util/machine.c   |  6 +++---
 tools/perf/util/machine.h   | 14 +++++++++++---
 6 files changed, 22 insertions(+), 16 deletions(-)

diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index f5d2c4bccbec..346bb5909e3d 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1544,9 +1544,8 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	}
 	kvm->session->evlist = kvm->evlist;
 	perf_session__set_id_hdr_size(kvm->session);
-	machine__synthesize_threads(&kvm->session->machines.host, &kvm->tool,
-				    &kvm->opts.target, kvm->evlist->threads,
-				    perf_event__process, false);
+	machine__synthesize_threads(&kvm->session->machines.host, &kvm->opts.target,
+				    kvm->evlist->threads, false);
 	err = kvm_live_open_events(kvm);
 	if (err)
 		goto out;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 41d1f37f5348..fc68b26d58f9 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -480,8 +480,8 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 					 perf_event__synthesize_guest_os, tool);
 	}
 
-	err = machine__synthesize_threads(machine, tool, &opts->target, evsel_list->threads,
-					  process_synthesized_event, opts->sample_address);
+	err = __machine__synthesize_threads(machine, tool, &opts->target, evsel_list->threads,
+					    process_synthesized_event, opts->sample_address);
 	if (err != 0)
 		goto out_delete_session;
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index c3a936ef7688..8c520d9fecfc 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -950,9 +950,8 @@ static int __cmd_top(struct perf_top *top)
 	if (ret)
 		goto out_delete;
 
-	machine__synthesize_threads(&top->session->machines.host, &top->tool,
-				    &opts->target, top->evlist->threads,
-				    perf_event__process, false);
+	machine__synthesize_threads(&top->session->machines.host, &opts->target,
+				    top->evlist->threads, false);
 	ret = perf_top__start_counters(top);
 	if (ret)
 		goto out_delete;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 7690324824db..c3008b1c369c 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1340,8 +1340,8 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 	if (trace->host == NULL)
 		return -ENOMEM;
 
-	err = machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
-					  evlist->threads, trace__tool_process, false);
+	err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
+					    evlist->threads, trace__tool_process, false);
 	if (err)
 		symbol__exit();
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 9f2c61d5a9ed..680700b6d779 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1395,9 +1395,9 @@ int machine__for_each_thread(struct machine *machine,
 	return rc;
 }
 
-int machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
-				struct perf_target *target, struct thread_map *threads,
-				perf_event__handler_t process, bool data_mmap)
+int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
+				  struct perf_target *target, struct thread_map *threads,
+				  perf_event__handler_t process, bool data_mmap)
 {
 	if (perf_target__has_task(target))
 		return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap);
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 14a89d2aecaf..fedd1dfaf715 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -179,7 +179,15 @@ int machine__for_each_thread(struct machine *machine,
 			     int (*fn)(struct thread *thread, void *p),
 			     void *priv);
 
-int machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
-				struct perf_target *target, struct thread_map *threads,
-				perf_event__handler_t process, bool data_mmap);
+int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
+				  struct perf_target *target, struct thread_map *threads,
+				  perf_event__handler_t process, bool data_mmap);
+static inline
+int machine__synthesize_threads(struct machine *machine, struct perf_target *target,
+				struct thread_map *threads, bool data_mmap)
+{
+	return __machine__synthesize_threads(machine, NULL, target, threads,
+					     perf_event__process, data_mmap);
+}
+
 #endif /* __PERF_MACHINE_H */
-- 
1.8.1.4

[PATCH 06/10] perf tools: Prevent condition that all sort keys are elided

[Arnaldo Carvalho de Melo]

From: Namhyung Kim <namhyung.kim@lge.com>

If given sort keys are all elided there'll be no output except for the
overhead column - actually the TUI shows a noisy output.  In this case
it'd be better to show up the sort keys rather than elide.

Before:

  $ perf report -s comm -c perf
  (...)
  # Overhead
  # ........
  #
     100.00%

After:

  $ perf report -s comm -c perf
  (...)
  # Overhead  Command
  # ........  .......
  #
     100.00%     perf

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1383900822-14609-1-git-send-email-namhyung@kernel.org
[ Us curly braces around multi-line statements, as requested by Ingo Molnar ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/sort.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 3c1b75c8b9a6..8b0bb1f4494a 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1137,6 +1137,8 @@ static void sort_entry__setup_elide(struct sort_entry *se,
 
 void sort__setup_elide(FILE *output)
 {
+	struct sort_entry *se;
+
 	sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
 				"dso", output);
 	sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list,
@@ -1172,4 +1174,15 @@ void sort__setup_elide(FILE *output)
 					"snoop", output);
 	}
 
+	/*
+	 * It makes no sense to elide all of sort entries.
+	 * Just revert them to show up again.
+	 */
+	list_for_each_entry(se, &hist_entry__sort_list, list) {
+		if (!se->elide)
+			return;
+	}
+
+	list_for_each_entry(se, &hist_entry__sort_list, list)
+		se->elide = false;
 }
-- 
1.8.1.4

[PATCH 07/10] perf record: Use correct return type for write()

[Arnaldo Carvalho de Melo]

From: Adrian Hunter <adrian.hunter@intel.com>

write() returns a 'ssize_t' not an 'int'.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1383906470-21002-1-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-record.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index fc68b26d58f9..8f5af32d6451 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -81,7 +81,7 @@ static int write_output(struct perf_record *rec, void *buf, size_t size)
 	struct perf_data_file *file = &rec->file;
 
 	while (size) {
-		int ret = write(file->fd, buf, size);
+		ssize_t ret = write(file->fd, buf, size);
 
 		if (ret < 0) {
 			pr_err("failed to write perf data, error: %m\n");
-- 
1.8.1.4

[PATCH 08/10] perf record: Move existing write_output into helper function

[Arnaldo Carvalho de Melo]

From: David Ahern <dsahern@gmail.com>

Code move only; no logic changes. In preparation for the mmap based
output option in the next patch.

Signed-off-by: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1383884605-30968-2-git-send-email-dsahern@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-record.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 8f5af32d6451..880227eae20f 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -76,7 +76,7 @@ struct perf_record {
 	long			samples;
 };
 
-static int write_output(struct perf_record *rec, void *buf, size_t size)
+static int do_write_output(struct perf_record *rec, void *buf, size_t size)
 {
 	struct perf_data_file *file = &rec->file;
 
@@ -97,6 +97,11 @@ static int write_output(struct perf_record *rec, void *buf, size_t size)
 	return 0;
 }
 
+static int write_output(struct perf_record *rec, void *buf, size_t size)
+{
+	return do_write_output(rec, buf, size);
+}
+
 static int process_synthesized_event(struct perf_tool *tool,
 				     union perf_event *event,
 				     struct perf_sample *sample __maybe_unused,
-- 
1.8.1.4

[PATCH 09/10] perf tests: Check return of perf_evlist__open sw clock event period test

[Arnaldo Carvalho de Melo]

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

We were not checking if we successfully opened the counters, i.e. if
sys_perf_event_open worked, when it doesn't in this test, we were
continuing anyway and then segfaulting when trying to access the file
descriptor array, that at that point had been freed in perf_evlist__open
error path:

[root@ssdandy ~]# perf test -v 19
19: Test software clock events have valid period values    :
--- start ---
Segmentation fault (core dumped)
[root@ssdandy ~]#

Do the check and bail out instead.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-6qy8ljkn0e9hm7bh7keo5z68@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/sw-clock.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 73c5c37cb27b..ed777728dfe7 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -57,7 +57,11 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 		goto out_delete_maps;
 	}
 
-	perf_evlist__open(evlist);
+	if (perf_evlist__open(evlist)) {
+		err = -errno;
+		pr_debug("Couldn't open evlist: %s\n", strerror(errno));
+		goto out_delete_maps;
+	}
 
 	err = perf_evlist__mmap(evlist, 128, true);
 	if (err < 0) {
-- 
1.8.1.4

[PATCH 10/10] perf tests: Use lower sample_freq in sw clock event period test

[Arnaldo Carvalho de Melo]

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

We were using it at 10 kHz, which doesn't work in machines where somehow
the max freq was auto reduced by the kernel:

[root@ssdandy ~]# perf test 19
19: Test software clock events have valid period values    : FAILED!
[root@ssdandy ~]# perf test -v 19
19: Test software clock events have valid period values    :
--- start ---
Couldn't open evlist: Invalid argument
---- end ----
Test software clock events have valid period values: FAILED!
[root@ssdandy ~]#

[root@ssdandy ~]# cat /proc/sys/kernel/perf_event_max_sample_rate
7000

Reducing it to 500 Hz should be good enough for this test and also
shouldn't affect what it is testing.

But warn the user if it fails, informing the knob and the freq tried.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-548rhj1uo6xbwnxa95kw3hqe@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/sw-clock.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index ed777728dfe7..93a7139ff5f7 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -34,7 +34,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 		.freq = 1,
 	};
 
-	attr.sample_freq = 10000;
+	attr.sample_freq = 500;
 
 	evlist = perf_evlist__new();
 	if (evlist == NULL) {
@@ -58,8 +58,11 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 	}
 
 	if (perf_evlist__open(evlist)) {
+		const char *knob = "/proc/sys/kernel/perf_event_max_sample_rate";
+
 		err = -errno;
-		pr_debug("Couldn't open evlist: %s\n", strerror(errno));
+		pr_debug("Couldn't open evlist: %s\nHint: check %s, using %" PRIu64 " in this test.\n",
+			 strerror(errno), knob, (u64)attr.sample_freq);
 		goto out_delete_maps;
 	}
 
-- 
1.8.1.4

Re: [PATCH 03/10] perf record: Synthesize non-exec MMAP records when --data used

[David Ahern]

[Added Vince]

On 11/11/13, 1:22 PM, Arnaldo Carvalho de Melo wrote:
> When perf_event_attr.mmap_data is set the kernel will generate
> PERF_RECORD_MMAP events when non-exec (data, SysV mem) mmaps are
> created, so we need to synthesize from /proc/pid/maps for existing
> threads

Seems like that should be documented in the man pages:

[dsa@MacBook perf]$ egrep -r mmap_data Documentation/
[dsa@MacBook perf]$

Vince: where are you keeping the man page you are putting together?

David

Re: [PATCH 04/10] perf machine: Introduce synthesize_threads method out of open coded equivalent

[David Ahern]

On 11/11/13, 1:22 PM, Arnaldo Carvalho de Melo wrote:
> +	if (perf_target__has_task(target))
> +		return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap);
> +	else if (perf_target__has_cpu(target))
> +		return perf_event__synthesize_threads(tool, process, machine, data_mmap);


Getting kind of long on the line lengths...

Re: [PATCH 10/10] perf tests: Use lower sample_freq in sw clock event period test

[David Ahern]

On 11/11/13, 1:22 PM, Arnaldo Carvalho de Melo wrote:

> @@ -58,8 +58,11 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
>   	}
>
>   	if (perf_evlist__open(evlist)) {
> +		const char *knob = "/proc/sys/kernel/perf_event_max_sample_rate";
> +
>   		err = -errno;
> -		pr_debug("Couldn't open evlist: %s\n", strerror(errno));
> +		pr_debug("Couldn't open evlist: %s\nHint: check %s, using %" PRIu64 " in this test.\n",
> +			 strerror(errno), knob, (u64)attr.sample_freq);
>   		goto out_delete_maps;
>   	}

Jiri had a patch to drop the sample rate to max. Perhaps re-use that here?

Re: [PATCH 04/10] perf machine: Introduce synthesize_threads method out of open coded equivalent

[Ingo Molnar]

* David Ahern <dsahern@gmail.com> wrote:

> On 11/11/13, 1:22 PM, Arnaldo Carvalho de Melo wrote:
> >+	if (perf_target__has_task(target))
> >+		return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap);
> >+	else if (perf_target__has_cpu(target))
> >+		return perf_event__synthesize_threads(tool, process, machine, data_mmap);
> 
> 
> Getting kind of long on the line lengths...

Maybe we could start losing most of the perf_ prefixes - it's all about 
perf here, so it does not really add much information, does it?

that would turn it into:

	if (target__has_task(target))
		return event__synthesize_thread_map(tool, threads, process, machine, data_mmap);
	else if (target__has_cpu(target))
		return event__synthesize_threads(tool, process, machine, data_mmap);

Another trick would be to combine (tool, machine) into a single helper 
struct (struct context *ctx?), if that is mostly a constant combination 
describing tool environment, which gets passed deep inside the guts of 
functions.

Thanks,

	Ingo

Re: [PATCH 03/10] perf record: Synthesize non-exec MMAP records when --data used

[Vince Weaver]

On Mon, 11 Nov 2013, David Ahern wrote:

> [Added Vince]
> 
> On 11/11/13, 1:22 PM, Arnaldo Carvalho de Melo wrote:
> > When perf_event_attr.mmap_data is set the kernel will generate
> > PERF_RECORD_MMAP events when non-exec (data, SysV mem) mmaps are
> > created, so we need to synthesize from /proc/pid/maps for existing
> > threads
> 
> Seems like that should be documented in the man pages:
> 
> [dsa@MacBook perf]$ egrep -r mmap_data Documentation/
> [dsa@MacBook perf]$
> 
> Vince: where are you keeping the man page you are putting together?

It's in the official linux manpage git tree (perf_event_open.2) and
has been included in the last few manpage releases.  

There is a blurb on PERF_RECORD_MMAP, though it definitely could use a 
bit more elaboration.

Vince

Re: [PATCH 10/10] perf tests: Use lower sample_freq in sw clock event period test

[Adrian Hunter]

On 11/11/13 22:22, Arnaldo Carvalho de Melo wrote:
> From: Arnaldo Carvalho de Melo <acme@redhat.com>
>
> We were using it at 10 kHz, which doesn't work in machines where somehow
> the max freq was auto reduced by the kernel:
>
> [root@ssdandy ~]# perf test 19
> 19: Test software clock events have valid period values    : FAILED!
> [root@ssdandy ~]# perf test -v 19
> 19: Test software clock events have valid period values    :
> --- start ---
> Couldn't open evlist: Invalid argument
> ---- end ----
> Test software clock events have valid period values: FAILED!
> [root@ssdandy ~]#
>
> [root@ssdandy ~]# cat /proc/sys/kernel/perf_event_max_sample_rate
> 7000
>
> Reducing it to 500 Hz should be good enough for this test and also
> shouldn't affect what it is testing.
>
> But warn the user if it fails, informing the knob and the freq tried.

Doesn't work for me:

./perf test -v 19
19: Test software clock events have valid period values    :
--- start ---
mmap size 528384B
mmap size 528384B
All (0) samples have period value of 1!
---- end ----
Test software clock events have valid period values: FAILED!

But this fixes it:

diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 93a7139..6664a7c 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -9,7 +9,7 @@
 #include "util/cpumap.h"
 #include "util/thread_map.h"
 
-#define NR_LOOPS  1000000
+#define NR_LOOPS  10000000
 
 /*
  * This test will open software clock events (cpu-clock, task-clock)


>
> Cc: Adrian Hunter <adrian.hunter@intel.com>
> Cc: David Ahern <dsahern@gmail.com>
> Cc: Frederic Weisbecker <fweisbec@gmail.com>
> Cc: Jiri Olsa <jolsa@redhat.com>
> Cc: Mike Galbraith <efault@gmx.de>
> Cc: Namhyung Kim <namhyung@kernel.org>
> Cc: Paul Mackerras <paulus@samba.org>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Stephane Eranian <eranian@google.com>
> Link: http://lkml.kernel.org/n/tip-548rhj1uo6xbwnxa95kw3hqe@git.kernel.org
> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
> ---
>  tools/perf/tests/sw-clock.c | 7 +++++--
>  1 file changed, 5 insertions(+), 2 deletions(-)
>
> diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
> index ed777728dfe7..93a7139ff5f7 100644
> --- a/tools/perf/tests/sw-clock.c
> +++ b/tools/perf/tests/sw-clock.c
> @@ -34,7 +34,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
>  		.freq = 1,
>  	};
>  
> -	attr.sample_freq = 10000;
> +	attr.sample_freq = 500;
>  
>  	evlist = perf_evlist__new();
>  	if (evlist == NULL) {
> @@ -58,8 +58,11 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
>  	}
>  
>  	if (perf_evlist__open(evlist)) {
> +		const char *knob = "/proc/sys/kernel/perf_event_max_sample_rate";
> +
>  		err = -errno;
> -		pr_debug("Couldn't open evlist: %s\n", strerror(errno));
> +		pr_debug("Couldn't open evlist: %s\nHint: check %s, using %" PRIu64 " in this test.\n",
> +			 strerror(errno), knob, (u64)attr.sample_freq);
>  		goto out_delete_maps;
>  	}
>  

Re: [PATCH 10/10] perf tests: Use lower sample_freq in sw clock event period test

[Namhyung Kim]

Hi Adrian,

On Tue, 12 Nov 2013 09:07:36 +0200, Adrian Hunter wrote:
> On 11/11/13 22:22, Arnaldo Carvalho de Melo wrote:
>> From: Arnaldo Carvalho de Melo <acme@redhat.com>
>>
>> We were using it at 10 kHz, which doesn't work in machines where somehow
>> the max freq was auto reduced by the kernel:
>>
>> [root@ssdandy ~]# perf test 19
>> 19: Test software clock events have valid period values    : FAILED!
>> [root@ssdandy ~]# perf test -v 19
>> 19: Test software clock events have valid period values    :
>> --- start ---
>> Couldn't open evlist: Invalid argument
>> ---- end ----
>> Test software clock events have valid period values: FAILED!
>> [root@ssdandy ~]#
>>
>> [root@ssdandy ~]# cat /proc/sys/kernel/perf_event_max_sample_rate
>> 7000
>>
>> Reducing it to 500 Hz should be good enough for this test and also
>> shouldn't affect what it is testing.
>>
>> But warn the user if it fails, informing the knob and the freq tried.
>
> Doesn't work for me:
>
> ./perf test -v 19
> 19: Test software clock events have valid period values    :
> --- start ---
> mmap size 528384B
> mmap size 528384B
> All (0) samples have period value of 1!
> ---- end ----
> Test software clock events have valid period values: FAILED!
>
> But this fixes it:
>
> diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
> index 93a7139..6664a7c 100644
> --- a/tools/perf/tests/sw-clock.c
> +++ b/tools/perf/tests/sw-clock.c
> @@ -9,7 +9,7 @@
>  #include "util/cpumap.h"
>  #include "util/thread_map.h"
>  
> -#define NR_LOOPS  1000000
> +#define NR_LOOPS  10000000

Or else, why not using the max_sample_rate as the freq value?

Thanks,
Namhyung

Re: [PATCH 04/10] perf machine: Introduce synthesize_threads method out of open coded equivalent

[Arnaldo Carvalho de Melo]

Em Mon, Nov 11, 2013 at 09:50:45PM +0100, Ingo Molnar escreveu:
> * David Ahern <dsahern@gmail.com> wrote:

> > On 11/11/13, 1:22 PM, Arnaldo Carvalho de Melo wrote:
> > >+	if (perf_target__has_task(target))
> > >+		return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap);
> > >+	else if (perf_target__has_cpu(target))
> > >+		return perf_event__synthesize_threads(tool, process, machine, data_mmap);

> > Getting kind of long on the line lengths...

> Maybe we could start losing most of the perf_ prefixes - it's all about 
> perf here, so it does not really add much information, does it?

In some cases that is ok, that is why I didn't call it 'perf_machine',
just 'machine', in others, like 'perf_event', I thought 'event' would be
too general when somebody tries to use this code together with other
libraries.

In some cases, like 'perf_target', probably its ok to move to
'target', perhaps this is ok for this problem domain, i.e.
monitoring/profiling/etc.
 
> that would turn it into:
> 
> 	if (target__has_task(target))
> 		return event__synthesize_thread_map(tool, threads, process, machine, data_mmap);
> 	else if (target__has_cpu(target))
> 		return event__synthesize_threads(tool, process, machine, data_mmap);
> 
> Another trick would be to combine (tool, machine) into a single helper 
> struct (struct context *ctx?), if that is mostly a constant combination 
> describing tool environment, which gets passed deep inside the guts of 
> functions.


Reducing the function signature is something that may help as well, and
was done in this series with machine__synthesize_threads, that avoids
passing the tool and process arguments, since they were constanty
anyway.

What you propose is used in some cases, like with symbol_conf, will try
to work in that direction as time goes by, i.e. doing some refactoring
work of this kind every once in a while, not to disrupt too much the
patch flow.
 
- Arnaldo

Re: [PATCH 10/10] perf tests: Use lower sample_freq in sw clock event period test

[Arnaldo Carvalho de Melo]

Em Tue, Nov 12, 2013 at 05:40:39PM +0900, Namhyung Kim escreveu:
> Hi Adrian,
> 
> On Tue, 12 Nov 2013 09:07:36 +0200, Adrian Hunter wrote:
> > On 11/11/13 22:22, Arnaldo Carvalho de Melo wrote:
> >> From: Arnaldo Carvalho de Melo <acme@redhat.com>
> >>
> >> We were using it at 10 kHz, which doesn't work in machines where somehow
> >> the max freq was auto reduced by the kernel:
> >>
> >> [root@ssdandy ~]# perf test 19
> >> 19: Test software clock events have valid period values    : FAILED!
> >> [root@ssdandy ~]# perf test -v 19
> >> 19: Test software clock events have valid period values    :
> >> --- start ---
> >> Couldn't open evlist: Invalid argument
> >> ---- end ----
> >> Test software clock events have valid period values: FAILED!
> >> [root@ssdandy ~]#
> >>
> >> [root@ssdandy ~]# cat /proc/sys/kernel/perf_event_max_sample_rate
> >> 7000
> >>
> >> Reducing it to 500 Hz should be good enough for this test and also
> >> shouldn't affect what it is testing.
> >>
> >> But warn the user if it fails, informing the knob and the freq tried.
> >
> > Doesn't work for me:
> >
> > ./perf test -v 19
> > 19: Test software clock events have valid period values    :
> > --- start ---
> > mmap size 528384B
> > mmap size 528384B
> > All (0) samples have period value of 1!
> > ---- end ----
> > Test software clock events have valid period values: FAILED!
> >
> > But this fixes it:
> >
> > diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
> > index 93a7139..6664a7c 100644
> > --- a/tools/perf/tests/sw-clock.c
> > +++ b/tools/perf/tests/sw-clock.c
> > @@ -9,7 +9,7 @@
> >  #include "util/cpumap.h"
> >  #include "util/thread_map.h"
> >  
> > -#define NR_LOOPS  1000000
> > +#define NR_LOOPS  10000000
> 
> Or else, why not using the max_sample_rate as the freq value?

Sure, that probably is better, I was just trying the lazy way, as doing
what you suggest entails reworking what Jiri did, since the routine that
reads that max_sample_rate is not exported, needs some massaging, etc.

Using a low enough max_sample_rate and warning the user that anyway
would be better knowing that the sample rate lowered so dramatically
looked quicker/lazy enough ;-)

- Arnaldo

Re: [PATCH 04/10] perf machine: Introduce synthesize_threads method out of open coded equivalent

[Ingo Molnar]

* Arnaldo Carvalho de Melo <acme@ghostprotocols.net> wrote:

> Em Mon, Nov 11, 2013 at 09:50:45PM +0100, Ingo Molnar escreveu:
> > * David Ahern <dsahern@gmail.com> wrote:
> 
> > > On 11/11/13, 1:22 PM, Arnaldo Carvalho de Melo wrote:
> > > >+	if (perf_target__has_task(target))
> > > >+		return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap);
> > > >+	else if (perf_target__has_cpu(target))
> > > >+		return perf_event__synthesize_threads(tool, process, machine, data_mmap);
> 
> > > Getting kind of long on the line lengths...
> 
> > Maybe we could start losing most of the perf_ prefixes - it's all about 
> > perf here, so it does not really add much information, does it?
> 
> In some cases that is ok, that is why I didn't call it 'perf_machine', 
> just 'machine', in others, like 'perf_event', I thought 'event' would be 
> too general when somebody tries to use this code together with other 
> libraries.

I think 'event' as a variable name is generally unused by libraries, 
exactly because so much random code uses it.

The only unfortunate C library land grabs I've run into are 'time' [by 
glibc] and 'y0' [by libm].

What I was suggesting here was more like an event__*() namespace - there 
shouldn't be any collision with public functions from libraries, public 
functions are generally either well established, or prefixed with a 
library name.

These are perf-internal function names, so using event__*() should be fine 
- assuming there are no counter arguments.

Thanks,

	Ingo

Re: [PATCH 10/10] perf tests: Use lower sample_freq in sw clock event period test

[Arnaldo Carvalho de Melo]

Em Tue, Nov 12, 2013 at 09:07:36AM +0200, Adrian Hunter escreveu:
> On 11/11/13 22:22, Arnaldo Carvalho de Melo wrote:
> > We were using it at 10 kHz, which doesn't work in machines where somehow
> > the max freq was auto reduced by the kernel:
> >
> > [root@ssdandy ~]# perf test 19
> > 19: Test software clock events have valid period values    : FAILED!
> > [root@ssdandy ~]# perf test -v 19
> > 19: Test software clock events have valid period values    :
> > --- start ---
> > Couldn't open evlist: Invalid argument
> > ---- end ----
> > Test software clock events have valid period values: FAILED!
> > [root@ssdandy ~]#
> >
> > [root@ssdandy ~]# cat /proc/sys/kernel/perf_event_max_sample_rate
> > 7000
> >
> > Reducing it to 500 Hz should be good enough for this test and also
> > shouldn't affect what it is testing.
> >
> > But warn the user if it fails, informing the knob and the freq tried.
> 
> Doesn't work for me:
> 
> ./perf test -v 19
> 19: Test software clock events have valid period values    :
> --- start ---
> mmap size 528384B
> mmap size 528384B
> All (0) samples have period value of 1!
> ---- end ----
> Test software clock events have valid period values: FAILED!
> 
> But this fixes it:
> 
> diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
> index 93a7139..6664a7c 100644
> --- a/tools/perf/tests/sw-clock.c
> +++ b/tools/perf/tests/sw-clock.c
> @@ -9,7 +9,7 @@
>  #include "util/cpumap.h"
>  #include "util/thread_map.h"
>  
> -#define NR_LOOPS  1000000
> +#define NR_LOOPS  10000000

Lower frequency, need to generate more noise, ugh. Adding that, but I
think this test needs to be reworked, Namhyung?

- Arnaldo

[tip:perf/urgent] perf tests: Compensate lower sample freq with longer test loop

[tip-bot for Adrian Hunter]

Commit-ID:  3fe2130523b2e098085eb4d38cd5b737a97cbee6
Gitweb:     http://git.kernel.org/tip/3fe2130523b2e098085eb4d38cd5b737a97cbee6
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Tue, 12 Nov 2013 11:45:21 -0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Tue, 12 Nov 2013 13:00:37 -0300

perf tests: Compensate lower sample freq with longer test loop

Doesn't work for me:

./perf test -v 19
19: Test software clock events have valid period values    :
--- start ---
mmap size 528384B
mmap size 528384B
All (0) samples have period value of 1!
---- end ----
Test software clock events have valid period values: FAILED!

Compensate the lower freq introduced in 67c1e4a53b17 with a longer loop,

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/5281D3B8.2030104@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/sw-clock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 93a7139..6664a7c 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -9,7 +9,7 @@
 #include "util/cpumap.h"
 #include "util/thread_map.h"
 
-#define NR_LOOPS  1000000
+#define NR_LOOPS  10000000
 
 /*
  * This test will open software clock events (cpu-clock, task-clock)

[tip:perf/urgent] perf target: Shorten perf_target__ to target__

[tip-bot for Arnaldo Carvalho de Melo]

Commit-ID:  602ad878d41ef097cc9aa2def7830d5bb27a15d8
Gitweb:     http://git.kernel.org/tip/602ad878d41ef097cc9aa2def7830d5bb27a15d8
Author:     Arnaldo Carvalho de Melo <acme@redhat.com>
AuthorDate: Tue, 12 Nov 2013 16:46:16 -0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Tue, 12 Nov 2013 16:51:03 -0300

perf target: Shorten perf_target__ to target__

Getting unwieldly long, for this app domain should be descriptive enough
and the use of __ to separate the class from the method names should
help with avoiding clashes with other code bases.

Reported-by: David Ahern <dsahern@gmail.com>
Suggested-by: Ingo Molnar <mingo@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/20131112113427.GA4053@ghostprotocols.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-kvm.c     |  6 ++---
 tools/perf/builtin-record.c  | 14 ++++++------
 tools/perf/builtin-stat.c    | 21 ++++++++---------
 tools/perf/builtin-top.c     | 14 ++++++------
 tools/perf/builtin-trace.c   | 10 ++++----
 tools/perf/perf.h            |  2 +-
 tools/perf/tests/task-exit.c |  2 +-
 tools/perf/util/evlist.c     | 12 ++++------
 tools/perf/util/evlist.h     |  5 ++--
 tools/perf/util/evsel.c      |  9 ++++----
 tools/perf/util/evsel.h      |  3 +--
 tools/perf/util/machine.c    |  6 ++---
 tools/perf/util/machine.h    |  4 ++--
 tools/perf/util/target.c     | 54 +++++++++++++++++++++-----------------------
 tools/perf/util/target.h     | 44 +++++++++++++++++-------------------
 tools/perf/util/top.c        |  2 +-
 16 files changed, 99 insertions(+), 109 deletions(-)

diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 346bb59..f8bf5f2 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1510,13 +1510,13 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	/*
 	 * target related setups
 	 */
-	err = perf_target__validate(&kvm->opts.target);
+	err = target__validate(&kvm->opts.target);
 	if (err) {
-		perf_target__strerror(&kvm->opts.target, err, errbuf, BUFSIZ);
+		target__strerror(&kvm->opts.target, err, errbuf, BUFSIZ);
 		ui__warning("%s", errbuf);
 	}
 
-	if (perf_target__none(&kvm->opts.target))
+	if (target__none(&kvm->opts.target))
 		kvm->opts.target.system_wide = true;
 
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 880227e..4d644fe 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -506,7 +506,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 	 * (apart from group members) have enable_on_exec=1 set,
 	 * so don't spoil it by prematurely enabling them.
 	 */
-	if (!perf_target__none(&opts->target))
+	if (!target__none(&opts->target))
 		perf_evlist__enable(evsel_list);
 
 	/*
@@ -535,7 +535,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 		 * die with the process and we wait for that. Thus no need to
 		 * disable events in this case.
 		 */
-		if (done && !disabled && !perf_target__none(&opts->target)) {
+		if (done && !disabled && !target__none(&opts->target)) {
 			perf_evlist__disable(evsel_list);
 			disabled = true;
 		}
@@ -906,7 +906,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	argc = parse_options(argc, argv, record_options, record_usage,
 			    PARSE_OPT_STOP_AT_NON_OPTION);
-	if (!argc && perf_target__none(&rec->opts.target))
+	if (!argc && target__none(&rec->opts.target))
 		usage_with_options(record_usage, record_options);
 
 	if (nr_cgroups && !rec->opts.target.system_wide) {
@@ -936,17 +936,17 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto out_symbol_exit;
 	}
 
-	err = perf_target__validate(&rec->opts.target);
+	err = target__validate(&rec->opts.target);
 	if (err) {
-		perf_target__strerror(&rec->opts.target, err, errbuf, BUFSIZ);
+		target__strerror(&rec->opts.target, err, errbuf, BUFSIZ);
 		ui__warning("%s", errbuf);
 	}
 
-	err = perf_target__parse_uid(&rec->opts.target);
+	err = target__parse_uid(&rec->opts.target);
 	if (err) {
 		int saved_errno = errno;
 
-		perf_target__strerror(&rec->opts.target, err, errbuf, BUFSIZ);
+		target__strerror(&rec->opts.target, err, errbuf, BUFSIZ);
 		ui__error("%s", errbuf);
 
 		err = -saved_errno;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 0fc1c94..ee0d565 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -108,7 +108,7 @@ enum {
 
 static struct perf_evlist	*evsel_list;
 
-static struct perf_target	target = {
+static struct target target = {
 	.uid	= UINT_MAX,
 };
 
@@ -294,11 +294,10 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
 
 	attr->inherit = !no_inherit;
 
-	if (perf_target__has_cpu(&target))
+	if (target__has_cpu(&target))
 		return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
 
-	if (!perf_target__has_task(&target) &&
-	    perf_evsel__is_group_leader(evsel)) {
+	if (!target__has_task(&target) && perf_evsel__is_group_leader(evsel)) {
 		attr->disabled = 1;
 		if (!initial_delay)
 			attr->enable_on_exec = 1;
@@ -1236,7 +1235,7 @@ static void print_stat(int argc, const char **argv)
 			fprintf(output, "\'system wide");
 		else if (target.cpu_list)
 			fprintf(output, "\'CPU(s) %s", target.cpu_list);
-		else if (!perf_target__has_task(&target)) {
+		else if (!target__has_task(&target)) {
 			fprintf(output, "\'%s", argv[0]);
 			for (i = 1; i < argc; i++)
 				fprintf(output, " %s", argv[i]);
@@ -1667,7 +1666,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	} else if (big_num_opt == 0) /* User passed --no-big-num */
 		big_num = false;
 
-	if (!argc && perf_target__none(&target))
+	if (!argc && target__none(&target))
 		usage_with_options(stat_usage, options);
 
 	if (run_count < 0) {
@@ -1680,8 +1679,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	}
 
 	/* no_aggr, cgroup are for system-wide only */
-	if ((aggr_mode != AGGR_GLOBAL || nr_cgroups)
-	     && !perf_target__has_cpu(&target)) {
+	if ((aggr_mode != AGGR_GLOBAL || nr_cgroups) &&
+	    !target__has_cpu(&target)) {
 		fprintf(stderr, "both cgroup and no-aggregation "
 			"modes only available in system-wide mode\n");
 
@@ -1694,14 +1693,14 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (add_default_attributes())
 		goto out;
 
-	perf_target__validate(&target);
+	target__validate(&target);
 
 	if (perf_evlist__create_maps(evsel_list, &target) < 0) {
-		if (perf_target__has_task(&target)) {
+		if (target__has_task(&target)) {
 			pr_err("Problems finding threads of monitor\n");
 			parse_options_usage(stat_usage, options, "p", 1);
 			parse_options_usage(NULL, options, "t", 1);
-		} else if (perf_target__has_cpu(&target)) {
+		} else if (target__has_cpu(&target)) {
 			perror("failed to parse CPUs map");
 			parse_options_usage(stat_usage, options, "C", 1);
 			parse_options_usage(NULL, options, "a", 1);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 8c520d9..b8f8e29 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -967,7 +967,7 @@ static int __cmd_top(struct perf_top *top)
 	 * XXX 'top' still doesn't start workloads like record, trace, but should,
 	 * so leave the check here.
 	 */
-        if (!perf_target__none(&opts->target))
+        if (!target__none(&opts->target))
                 perf_evlist__enable(top->evlist);
 
 	/* Wait for a minimal set of events before starting the snapshot */
@@ -1053,7 +1053,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 		.sym_pcnt_filter     = 5,
 	};
 	struct perf_record_opts *opts = &top.record_opts;
-	struct perf_target *target = &opts->target;
+	struct target *target = &opts->target;
 	const struct option options[] = {
 	OPT_CALLBACK('e', "event", &top.evlist, "event",
 		     "event selector. use 'perf list' to list available events",
@@ -1169,24 +1169,24 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	setup_browser(false);
 
-	status = perf_target__validate(target);
+	status = target__validate(target);
 	if (status) {
-		perf_target__strerror(target, status, errbuf, BUFSIZ);
+		target__strerror(target, status, errbuf, BUFSIZ);
 		ui__warning("%s", errbuf);
 	}
 
-	status = perf_target__parse_uid(target);
+	status = target__parse_uid(target);
 	if (status) {
 		int saved_errno = errno;
 
-		perf_target__strerror(target, status, errbuf, BUFSIZ);
+		target__strerror(target, status, errbuf, BUFSIZ);
 		ui__error("%s", errbuf);
 
 		status = -saved_errno;
 		goto out_delete_evlist;
 	}
 
-	if (perf_target__none(target))
+	if (target__none(target))
 		target->system_wide = true;
 
 	if (perf_evlist__create_maps(top.evlist, target) < 0)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index aa5702f..6b230af 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2327,21 +2327,21 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		}
 	}
 
-	err = perf_target__validate(&trace.opts.target);
+	err = target__validate(&trace.opts.target);
 	if (err) {
-		perf_target__strerror(&trace.opts.target, err, bf, sizeof(bf));
+		target__strerror(&trace.opts.target, err, bf, sizeof(bf));
 		fprintf(trace.output, "%s", bf);
 		goto out_close;
 	}
 
-	err = perf_target__parse_uid(&trace.opts.target);
+	err = target__parse_uid(&trace.opts.target);
 	if (err) {
-		perf_target__strerror(&trace.opts.target, err, bf, sizeof(bf));
+		target__strerror(&trace.opts.target, err, bf, sizeof(bf));
 		fprintf(trace.output, "%s", bf);
 		goto out_close;
 	}
 
-	if (!argc && perf_target__none(&trace.opts.target))
+	if (!argc && target__none(&trace.opts.target))
 		trace.opts.target.system_wide = true;
 
 	if (input_name)
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 6a587e84..b079304 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -248,7 +248,7 @@ enum perf_call_graph_mode {
 };
 
 struct perf_record_opts {
-	struct perf_target target;
+	struct target target;
 	int	     call_graph;
 	bool	     group;
 	bool	     inherit_stat;
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index c33d95f..d09ab57 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -28,7 +28,7 @@ int test__task_exit(void)
 	union perf_event *event;
 	struct perf_evsel *evsel;
 	struct perf_evlist *evlist;
-	struct perf_target target = {
+	struct target target = {
 		.uid		= UINT_MAX,
 		.uses_mmap	= true,
 	};
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index cb19044..dc6fa3f 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -811,8 +811,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 	return perf_evlist__mmap_per_cpu(evlist, prot, mask);
 }
 
-int perf_evlist__create_maps(struct perf_evlist *evlist,
-			     struct perf_target *target)
+int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 {
 	evlist->threads = thread_map__new_str(target->pid, target->tid,
 					      target->uid);
@@ -820,9 +819,9 @@ int perf_evlist__create_maps(struct perf_evlist *evlist,
 	if (evlist->threads == NULL)
 		return -1;
 
-	if (perf_target__has_task(target))
+	if (target__has_task(target))
 		evlist->cpus = cpu_map__dummy_new();
-	else if (!perf_target__has_cpu(target) && !target->uses_mmap)
+	else if (!target__has_cpu(target) && !target->uses_mmap)
 		evlist->cpus = cpu_map__dummy_new();
 	else
 		evlist->cpus = cpu_map__new(target->cpu_list);
@@ -1031,8 +1030,7 @@ out_err:
 	return err;
 }
 
-int perf_evlist__prepare_workload(struct perf_evlist *evlist,
-				  struct perf_target *target,
+int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *target,
 				  const char *argv[], bool pipe_output,
 				  bool want_signal)
 {
@@ -1084,7 +1082,7 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist,
 		exit(-1);
 	}
 
-	if (perf_target__none(target))
+	if (target__none(target))
 		evlist->threads->map[0] = evlist->workload.pid;
 
 	close(child_ready_pipe[1]);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index ecaa582..649d6ea 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -102,7 +102,7 @@ void perf_evlist__config(struct perf_evlist *evlist,
 int perf_record_opts__config(struct perf_record_opts *opts);
 
 int perf_evlist__prepare_workload(struct perf_evlist *evlist,
-				  struct perf_target *target,
+				  struct target *target,
 				  const char *argv[], bool pipe_output,
 				  bool want_signal);
 int perf_evlist__start_workload(struct perf_evlist *evlist);
@@ -134,8 +134,7 @@ static inline void perf_evlist__set_maps(struct perf_evlist *evlist,
 	evlist->threads	= threads;
 }
 
-int perf_evlist__create_maps(struct perf_evlist *evlist,
-			     struct perf_target *target);
+int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target);
 void perf_evlist__delete_maps(struct perf_evlist *evlist);
 int perf_evlist__apply_filters(struct perf_evlist *evlist);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index f95653a..18f7c18 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -645,7 +645,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
 		}
 	}
 
-	if (perf_target__has_cpu(&opts->target))
+	if (target__has_cpu(&opts->target))
 		perf_evsel__set_sample_bit(evsel, CPU);
 
 	if (opts->period)
@@ -653,7 +653,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
 
 	if (!perf_missing_features.sample_id_all &&
 	    (opts->sample_time || !opts->no_inherit ||
-	     perf_target__has_cpu(&opts->target)))
+	     target__has_cpu(&opts->target)))
 		perf_evsel__set_sample_bit(evsel, TIME);
 
 	if (opts->raw_samples) {
@@ -696,7 +696,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
 	 * Setting enable_on_exec for independent events and
 	 * group leaders for traced executed by perf.
 	 */
-	if (perf_target__none(&opts->target) && perf_evsel__is_group_leader(evsel))
+	if (target__none(&opts->target) && perf_evsel__is_group_leader(evsel))
 		attr->enable_on_exec = 1;
 }
 
@@ -2006,8 +2006,7 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 	return false;
 }
 
-int perf_evsel__open_strerror(struct perf_evsel *evsel,
-			      struct perf_target *target,
+int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 			      int err, char *msg, size_t size)
 {
 	switch (err) {
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 0178233..f502965 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -318,8 +318,7 @@ int perf_evsel__fprintf(struct perf_evsel *evsel,
 
 bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 			  char *msg, size_t msgsize);
-int perf_evsel__open_strerror(struct perf_evsel *evsel,
-			      struct perf_target *target,
+int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 			      int err, char *msg, size_t size);
 
 static inline int perf_evsel__group_idx(struct perf_evsel *evsel)
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 680700b6..0393912 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1396,12 +1396,12 @@ int machine__for_each_thread(struct machine *machine,
 }
 
 int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
-				  struct perf_target *target, struct thread_map *threads,
+				  struct target *target, struct thread_map *threads,
 				  perf_event__handler_t process, bool data_mmap)
 {
-	if (perf_target__has_task(target))
+	if (target__has_task(target))
 		return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap);
-	else if (perf_target__has_cpu(target))
+	else if (target__has_cpu(target))
 		return perf_event__synthesize_threads(tool, process, machine, data_mmap);
 	/* command specified */
 	return 0;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index fedd1df..4771330 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -180,10 +180,10 @@ int machine__for_each_thread(struct machine *machine,
 			     void *priv);
 
 int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
-				  struct perf_target *target, struct thread_map *threads,
+				  struct target *target, struct thread_map *threads,
 				  perf_event__handler_t process, bool data_mmap);
 static inline
-int machine__synthesize_threads(struct machine *machine, struct perf_target *target,
+int machine__synthesize_threads(struct machine *machine, struct target *target,
 				struct thread_map *threads, bool data_mmap)
 {
 	return __machine__synthesize_threads(machine, NULL, target, threads,
diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c
index 065528b..3c778a0 100644
--- a/tools/perf/util/target.c
+++ b/tools/perf/util/target.c
@@ -13,9 +13,9 @@
 #include <string.h>
 
 
-enum perf_target_errno perf_target__validate(struct perf_target *target)
+enum target_errno target__validate(struct target *target)
 {
-	enum perf_target_errno ret = PERF_ERRNO_TARGET__SUCCESS;
+	enum target_errno ret = TARGET_ERRNO__SUCCESS;
 
 	if (target->pid)
 		target->tid = target->pid;
@@ -23,42 +23,42 @@ enum perf_target_errno perf_target__validate(struct perf_target *target)
 	/* CPU and PID are mutually exclusive */
 	if (target->tid && target->cpu_list) {
 		target->cpu_list = NULL;
-		if (ret == PERF_ERRNO_TARGET__SUCCESS)
-			ret = PERF_ERRNO_TARGET__PID_OVERRIDE_CPU;
+		if (ret == TARGET_ERRNO__SUCCESS)
+			ret = TARGET_ERRNO__PID_OVERRIDE_CPU;
 	}
 
 	/* UID and PID are mutually exclusive */
 	if (target->tid && target->uid_str) {
 		target->uid_str = NULL;
-		if (ret == PERF_ERRNO_TARGET__SUCCESS)
-			ret = PERF_ERRNO_TARGET__PID_OVERRIDE_UID;
+		if (ret == TARGET_ERRNO__SUCCESS)
+			ret = TARGET_ERRNO__PID_OVERRIDE_UID;
 	}
 
 	/* UID and CPU are mutually exclusive */
 	if (target->uid_str && target->cpu_list) {
 		target->cpu_list = NULL;
-		if (ret == PERF_ERRNO_TARGET__SUCCESS)
-			ret = PERF_ERRNO_TARGET__UID_OVERRIDE_CPU;
+		if (ret == TARGET_ERRNO__SUCCESS)
+			ret = TARGET_ERRNO__UID_OVERRIDE_CPU;
 	}
 
 	/* PID and SYSTEM are mutually exclusive */
 	if (target->tid && target->system_wide) {
 		target->system_wide = false;
-		if (ret == PERF_ERRNO_TARGET__SUCCESS)
-			ret = PERF_ERRNO_TARGET__PID_OVERRIDE_SYSTEM;
+		if (ret == TARGET_ERRNO__SUCCESS)
+			ret = TARGET_ERRNO__PID_OVERRIDE_SYSTEM;
 	}
 
 	/* UID and SYSTEM are mutually exclusive */
 	if (target->uid_str && target->system_wide) {
 		target->system_wide = false;
-		if (ret == PERF_ERRNO_TARGET__SUCCESS)
-			ret = PERF_ERRNO_TARGET__UID_OVERRIDE_SYSTEM;
+		if (ret == TARGET_ERRNO__SUCCESS)
+			ret = TARGET_ERRNO__UID_OVERRIDE_SYSTEM;
 	}
 
 	return ret;
 }
 
-enum perf_target_errno perf_target__parse_uid(struct perf_target *target)
+enum target_errno target__parse_uid(struct target *target)
 {
 	struct passwd pwd, *result;
 	char buf[1024];
@@ -66,7 +66,7 @@ enum perf_target_errno perf_target__parse_uid(struct perf_target *target)
 
 	target->uid = UINT_MAX;
 	if (str == NULL)
-		return PERF_ERRNO_TARGET__SUCCESS;
+		return TARGET_ERRNO__SUCCESS;
 
 	/* Try user name first */
 	getpwnam_r(str, &pwd, buf, sizeof(buf), &result);
@@ -79,22 +79,22 @@ enum perf_target_errno perf_target__parse_uid(struct perf_target *target)
 		int uid = strtol(str, &endptr, 10);
 
 		if (*endptr != '\0')
-			return PERF_ERRNO_TARGET__INVALID_UID;
+			return TARGET_ERRNO__INVALID_UID;
 
 		getpwuid_r(uid, &pwd, buf, sizeof(buf), &result);
 
 		if (result == NULL)
-			return PERF_ERRNO_TARGET__USER_NOT_FOUND;
+			return TARGET_ERRNO__USER_NOT_FOUND;
 	}
 
 	target->uid = result->pw_uid;
-	return PERF_ERRNO_TARGET__SUCCESS;
+	return TARGET_ERRNO__SUCCESS;
 }
 
 /*
- * This must have a same ordering as the enum perf_target_errno.
+ * This must have a same ordering as the enum target_errno.
  */
-static const char *perf_target__error_str[] = {
+static const char *target__error_str[] = {
 	"PID/TID switch overriding CPU",
 	"PID/TID switch overriding UID",
 	"UID switch overriding CPU",
@@ -104,7 +104,7 @@ static const char *perf_target__error_str[] = {
 	"Problems obtaining information for user %s",
 };
 
-int perf_target__strerror(struct perf_target *target, int errnum,
+int target__strerror(struct target *target, int errnum,
 			  char *buf, size_t buflen)
 {
 	int idx;
@@ -124,21 +124,19 @@ int perf_target__strerror(struct perf_target *target, int errnum,
 		return 0;
 	}
 
-	if (errnum <  __PERF_ERRNO_TARGET__START ||
-	    errnum >= __PERF_ERRNO_TARGET__END)
+	if (errnum <  __TARGET_ERRNO__START || errnum >= __TARGET_ERRNO__END)
 		return -1;
 
-	idx = errnum - __PERF_ERRNO_TARGET__START;
-	msg = perf_target__error_str[idx];
+	idx = errnum - __TARGET_ERRNO__START;
+	msg = target__error_str[idx];
 
 	switch (errnum) {
-	case PERF_ERRNO_TARGET__PID_OVERRIDE_CPU
-	 ... PERF_ERRNO_TARGET__UID_OVERRIDE_SYSTEM:
+	case TARGET_ERRNO__PID_OVERRIDE_CPU ... TARGET_ERRNO__UID_OVERRIDE_SYSTEM:
 		snprintf(buf, buflen, "%s", msg);
 		break;
 
-	case PERF_ERRNO_TARGET__INVALID_UID:
-	case PERF_ERRNO_TARGET__USER_NOT_FOUND:
+	case TARGET_ERRNO__INVALID_UID:
+	case TARGET_ERRNO__USER_NOT_FOUND:
 		snprintf(buf, buflen, msg, target->uid_str);
 		break;
 
diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h
index a4be857..89bab71 100644
--- a/tools/perf/util/target.h
+++ b/tools/perf/util/target.h
@@ -4,7 +4,7 @@
 #include <stdbool.h>
 #include <sys/types.h>
 
-struct perf_target {
+struct target {
 	const char   *pid;
 	const char   *tid;
 	const char   *cpu_list;
@@ -14,8 +14,8 @@ struct perf_target {
 	bool	     uses_mmap;
 };
 
-enum perf_target_errno {
-	PERF_ERRNO_TARGET__SUCCESS		= 0,
+enum target_errno {
+	TARGET_ERRNO__SUCCESS		= 0,
 
 	/*
 	 * Choose an arbitrary negative big number not to clash with standard
@@ -24,42 +24,40 @@ enum perf_target_errno {
 	 *
 	 * http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/errno.h.html
 	 */
-	__PERF_ERRNO_TARGET__START		= -10000,
+	__TARGET_ERRNO__START		= -10000,
 
+	/* for target__validate() */
+	TARGET_ERRNO__PID_OVERRIDE_CPU	= __TARGET_ERRNO__START,
+	TARGET_ERRNO__PID_OVERRIDE_UID,
+	TARGET_ERRNO__UID_OVERRIDE_CPU,
+	TARGET_ERRNO__PID_OVERRIDE_SYSTEM,
+	TARGET_ERRNO__UID_OVERRIDE_SYSTEM,
 
-	/* for perf_target__validate() */
-	PERF_ERRNO_TARGET__PID_OVERRIDE_CPU	= __PERF_ERRNO_TARGET__START,
-	PERF_ERRNO_TARGET__PID_OVERRIDE_UID,
-	PERF_ERRNO_TARGET__UID_OVERRIDE_CPU,
-	PERF_ERRNO_TARGET__PID_OVERRIDE_SYSTEM,
-	PERF_ERRNO_TARGET__UID_OVERRIDE_SYSTEM,
+	/* for target__parse_uid() */
+	TARGET_ERRNO__INVALID_UID,
+	TARGET_ERRNO__USER_NOT_FOUND,
 
-	/* for perf_target__parse_uid() */
-	PERF_ERRNO_TARGET__INVALID_UID,
-	PERF_ERRNO_TARGET__USER_NOT_FOUND,
-
-	__PERF_ERRNO_TARGET__END,
+	__TARGET_ERRNO__END,
 };
 
-enum perf_target_errno perf_target__validate(struct perf_target *target);
-enum perf_target_errno perf_target__parse_uid(struct perf_target *target);
+enum target_errno target__validate(struct target *target);
+enum target_errno target__parse_uid(struct target *target);
 
-int perf_target__strerror(struct perf_target *target, int errnum, char *buf,
-			  size_t buflen);
+int target__strerror(struct target *target, int errnum, char *buf, size_t buflen);
 
-static inline bool perf_target__has_task(struct perf_target *target)
+static inline bool target__has_task(struct target *target)
 {
 	return target->tid || target->pid || target->uid_str;
 }
 
-static inline bool perf_target__has_cpu(struct perf_target *target)
+static inline bool target__has_cpu(struct target *target)
 {
 	return target->system_wide || target->cpu_list;
 }
 
-static inline bool perf_target__none(struct perf_target *target)
+static inline bool target__none(struct target *target)
 {
-	return !perf_target__has_task(target) && !perf_target__has_cpu(target);
+	return !target__has_task(target) && !target__has_cpu(target);
 }
 
 #endif /* _PERF_TARGET_H */
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
index f857b51..ce793c7 100644
--- a/tools/perf/util/top.c
+++ b/tools/perf/util/top.c
@@ -27,7 +27,7 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
 	float ksamples_per_sec;
 	float esamples_percent;
 	struct perf_record_opts *opts = &top->record_opts;
-	struct perf_target *target = &opts->target;
+	struct target *target = &opts->target;
 	size_t ret = 0;
 
 	if (top->samples) {

Re: [PATCH 10/10] perf tests: Use lower sample_freq in sw clock event period test

[Namhyung Kim]

Hi Arnaldo,

On Tue, 12 Nov 2013 11:41:01 -0300, Arnaldo Carvalho de Melo wrote:
> Em Tue, Nov 12, 2013 at 09:07:36AM +0200, Adrian Hunter escreveu:
>> -#define NR_LOOPS  1000000
>> +#define NR_LOOPS  10000000
>
> Lower frequency, need to generate more noise, ugh. Adding that, but I
> think this test needs to be reworked, Namhyung?

Hmm.. We might go back to use the default frequency of 4000 (or 1000)
and make the loop based on time like using alarm or setitimer.

Or we can add an outer loop which doubles the inner loop counter if no
samples are collected.

What do you think?

Thanks,
Namhyung

[tip:perf/core] perf tools: Rename 'perf_record_opts' to ' record_opts

[tip-bot for Arnaldo Carvalho de Melo]

Commit-ID:  b40067964f09a5b4d9e133dec225007ee0a13050
Gitweb:     http://git.kernel.org/tip/b40067964f09a5b4d9e133dec225007ee0a13050
Author:     Arnaldo Carvalho de Melo <acme@redhat.com>
AuthorDate: Thu, 19 Dec 2013 14:43:45 -0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Thu, 19 Dec 2013 14:43:45 -0300

perf tools: Rename 'perf_record_opts' to 'record_opts

Reduce typing, functions use class__method convention, so unlikely to
clash with other libraries.

This actually was discussed in the "Link:" referenced message below.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/20131112113427.GA4053@ghostprotocols.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-kvm.c                  |  2 +-
 tools/perf/builtin-record.c               | 18 +++++++++---------
 tools/perf/builtin-top.c                  |  8 ++++----
 tools/perf/builtin-trace.c                |  2 +-
 tools/perf/perf.h                         |  2 +-
 tools/perf/tests/code-reading.c           |  2 +-
 tools/perf/tests/keep-tracking.c          |  2 +-
 tools/perf/tests/open-syscall-tp-fields.c |  2 +-
 tools/perf/tests/perf-record.c            |  2 +-
 tools/perf/tests/perf-time-to-tsc.c       |  2 +-
 tools/perf/util/callchain.h               |  2 +-
 tools/perf/util/evlist.h                  |  7 +++----
 tools/perf/util/evsel.c                   |  3 +--
 tools/perf/util/evsel.h                   |  4 ++--
 tools/perf/util/record.c                  |  9 ++++-----
 tools/perf/util/top.c                     |  2 +-
 tools/perf/util/top.h                     |  2 +-
 17 files changed, 34 insertions(+), 37 deletions(-)

diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 154b397..5a80da6 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -89,7 +89,7 @@ struct exit_reasons_table {
 
 struct perf_kvm_stat {
 	struct perf_tool    tool;
-	struct perf_record_opts opts;
+	struct record_opts  opts;
 	struct perf_evlist  *evlist;
 	struct perf_session *session;
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f2624d4..6ec0cbc 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -64,7 +64,7 @@ static void __handle_on_exit_funcs(void)
 
 struct record {
 	struct perf_tool	tool;
-	struct perf_record_opts	opts;
+	struct record_opts	opts;
 	u64			bytes_written;
 	struct perf_data_file	file;
 	struct perf_evlist	*evlist;
@@ -178,7 +178,7 @@ static int record__open(struct record *rec)
 	struct perf_evsel *pos;
 	struct perf_evlist *evlist = rec->evlist;
 	struct perf_session *session = rec->session;
-	struct perf_record_opts *opts = &rec->opts;
+	struct record_opts *opts = &rec->opts;
 	int rc = 0;
 
 	perf_evlist__config(evlist, opts);
@@ -348,7 +348,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	const bool forks = argc > 0;
 	struct machine *machine;
 	struct perf_tool *tool = &rec->tool;
-	struct perf_record_opts *opts = &rec->opts;
+	struct record_opts *opts = &rec->opts;
 	struct perf_evlist *evsel_list = rec->evlist;
 	struct perf_data_file *file = &rec->file;
 	struct perf_session *session;
@@ -657,7 +657,7 @@ static int get_stack_size(char *str, unsigned long *_size)
 }
 #endif /* HAVE_LIBUNWIND_SUPPORT */
 
-int record_parse_callchain(const char *arg, struct perf_record_opts *opts)
+int record_parse_callchain(const char *arg, struct record_opts *opts)
 {
 	char *tok, *name, *saveptr = NULL;
 	char *buf;
@@ -713,7 +713,7 @@ int record_parse_callchain(const char *arg, struct perf_record_opts *opts)
 	return ret;
 }
 
-static void callchain_debug(struct perf_record_opts *opts)
+static void callchain_debug(struct record_opts *opts)
 {
 	pr_debug("callchain: type %d\n", opts->call_graph);
 
@@ -726,7 +726,7 @@ int record_parse_callchain_opt(const struct option *opt,
 			       const char *arg,
 			       int unset)
 {
-	struct perf_record_opts *opts = opt->value;
+	struct record_opts *opts = opt->value;
 	int ret;
 
 	/* --no-call-graph */
@@ -747,7 +747,7 @@ int record_callchain_opt(const struct option *opt,
 			 const char *arg __maybe_unused,
 			 int unset __maybe_unused)
 {
-	struct perf_record_opts *opts = opt->value;
+	struct record_opts *opts = opt->value;
 
 	if (opts->call_graph == CALLCHAIN_NONE)
 		opts->call_graph = CALLCHAIN_FP;
@@ -796,7 +796,7 @@ const char record_callchain_help[] = CALLCHAIN_HELP "fp";
 /*
  * XXX Will stay a global variable till we fix builtin-script.c to stop messing
  * with it and switch to use the library functions in perf_evlist that came
- * from builtin-record.c, i.e. use perf_record_opts,
+ * from builtin-record.c, i.e. use record_opts,
  * perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record',
  * using pipes, etc.
  */
@@ -944,7 +944,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (perf_evlist__create_maps(evsel_list, &rec->opts.target) < 0)
 		usage_with_options(record_usage, record_options);
 
-	if (perf_record_opts__config(&rec->opts)) {
+	if (record_opts__config(&rec->opts)) {
 		err = -EINVAL;
 		goto out_free_fd;
 	}
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 2c6cb66..172e91a 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -854,7 +854,7 @@ static int perf_top__start_counters(struct perf_top *top)
 	char msg[512];
 	struct perf_evsel *counter;
 	struct perf_evlist *evlist = top->evlist;
-	struct perf_record_opts *opts = &top->record_opts;
+	struct record_opts *opts = &top->record_opts;
 
 	perf_evlist__config(evlist, opts);
 
@@ -906,7 +906,7 @@ static int perf_top__setup_sample_type(struct perf_top *top __maybe_unused)
 
 static int __cmd_top(struct perf_top *top)
 {
-	struct perf_record_opts *opts = &top->record_opts;
+	struct record_opts *opts = &top->record_opts;
 	pthread_t thread;
 	int ret;
 
@@ -1028,7 +1028,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 		.max_stack	     = PERF_MAX_STACK_DEPTH,
 		.sym_pcnt_filter     = 5,
 	};
-	struct perf_record_opts *opts = &top.record_opts;
+	struct record_opts *opts = &top.record_opts;
 	struct target *target = &opts->target;
 	const struct option options[] = {
 	OPT_CALLBACK('e', "event", &top.evlist, "event",
@@ -1179,7 +1179,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (top.delay_secs < 1)
 		top.delay_secs = 1;
 
-	if (perf_record_opts__config(opts)) {
+	if (record_opts__config(opts)) {
 		status = -EINVAL;
 		goto out_delete_maps;
 	}
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 56bbca5..f64b5b0 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1159,7 +1159,7 @@ struct trace {
 		int		max;
 		struct syscall  *table;
 	} syscalls;
-	struct perf_record_opts opts;
+	struct record_opts	opts;
 	struct machine		*host;
 	u64			base_time;
 	bool			full_time;
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index b23fed5..b1cc84b 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -247,7 +247,7 @@ enum perf_call_graph_mode {
 	CALLCHAIN_DWARF
 };
 
-struct perf_record_opts {
+struct record_opts {
 	struct target target;
 	int	     call_graph;
 	bool	     group;
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 85d4919..4248d1e 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -391,7 +391,7 @@ static int do_test_code_reading(bool try_kcore)
 	struct machines machines;
 	struct machine *machine;
 	struct thread *thread;
-	struct perf_record_opts opts = {
+	struct record_opts opts = {
 		.mmap_pages	     = UINT_MAX,
 		.user_freq	     = UINT_MAX,
 		.user_interval	     = ULLONG_MAX,
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 376c356..27eb751 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -51,7 +51,7 @@ static int find_comm(struct perf_evlist *evlist, const char *comm)
  */
 int test__keep_tracking(void)
 {
-	struct perf_record_opts opts = {
+	struct record_opts opts = {
 		.mmap_pages	     = UINT_MAX,
 		.user_freq	     = UINT_MAX,
 		.user_interval	     = ULLONG_MAX,
diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c
index 41cc0ba..774620a 100644
--- a/tools/perf/tests/open-syscall-tp-fields.c
+++ b/tools/perf/tests/open-syscall-tp-fields.c
@@ -6,7 +6,7 @@
 
 int test__syscall_open_tp_fields(void)
 {
-	struct perf_record_opts opts = {
+	struct record_opts opts = {
 		.target = {
 			.uid = UINT_MAX,
 			.uses_mmap = true,
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 93a62b0..eeba562 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -34,7 +34,7 @@ realloc:
 
 int test__PERF_RECORD(void)
 {
-	struct perf_record_opts opts = {
+	struct record_opts opts = {
 		.target = {
 			.uid = UINT_MAX,
 			.uses_mmap = true,
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index 4ca1b93..c6398b9 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -46,7 +46,7 @@ static u64 rdtsc(void)
  */
 int test__perf_time_to_tsc(void)
 {
-	struct perf_record_opts opts = {
+	struct record_opts opts = {
 		.mmap_pages	     = UINT_MAX,
 		.user_freq	     = UINT_MAX,
 		.user_interval	     = ULLONG_MAX,
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 4f7f989..08b25af 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -146,7 +146,7 @@ static inline void callchain_cursor_advance(struct callchain_cursor *cursor)
 
 struct option;
 
-int record_parse_callchain(const char *arg, struct perf_record_opts *opts);
+int record_parse_callchain(const char *arg, struct record_opts *opts);
 int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset);
 int record_callchain_opt(const struct option *opt, const char *arg, int unset);
 
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 9f64ede..2fe5195 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -12,7 +12,7 @@
 struct pollfd;
 struct thread_map;
 struct cpu_map;
-struct perf_record_opts;
+struct record_opts;
 
 #define PERF_EVLIST__HLIST_BITS 8
 #define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS)
@@ -97,9 +97,8 @@ void perf_evlist__close(struct perf_evlist *evlist);
 
 void perf_evlist__set_id_pos(struct perf_evlist *evlist);
 bool perf_can_sample_identifier(void);
-void perf_evlist__config(struct perf_evlist *evlist,
-			 struct perf_record_opts *opts);
-int perf_record_opts__config(struct perf_record_opts *opts);
+void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts);
+int record_opts__config(struct record_opts *opts);
 
 int perf_evlist__prepare_workload(struct perf_evlist *evlist,
 				  struct target *target,
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 01ff4cf..6874e04 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -528,8 +528,7 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size)
  *     enable/disable events specifically, as there's no
  *     initial traced exec call.
  */
-void perf_evsel__config(struct perf_evsel *evsel,
-			struct perf_record_opts *opts)
+void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 {
 	struct perf_evsel *leader = evsel->leader;
 	struct perf_event_attr *attr = &evsel->attr;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 8120eeb..f1b3256 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -96,7 +96,7 @@ struct perf_evsel {
 struct cpu_map;
 struct thread_map;
 struct perf_evlist;
-struct perf_record_opts;
+struct record_opts;
 
 struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx);
 
@@ -120,7 +120,7 @@ void perf_evsel__exit(struct perf_evsel *evsel);
 void perf_evsel__delete(struct perf_evsel *evsel);
 
 void perf_evsel__config(struct perf_evsel *evsel,
-			struct perf_record_opts *opts);
+			struct record_opts *opts);
 
 int __perf_evsel__sample_size(u64 sample_type);
 void perf_evsel__calc_id_pos(struct perf_evsel *evsel);
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index e510453..104a475 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -74,8 +74,7 @@ bool perf_can_sample_identifier(void)
 	return perf_probe_api(perf_probe_sample_identifier);
 }
 
-void perf_evlist__config(struct perf_evlist *evlist,
-			struct perf_record_opts *opts)
+void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
 {
 	struct perf_evsel *evsel;
 	bool use_sample_identifier = false;
@@ -123,7 +122,7 @@ static int get_max_rate(unsigned int *rate)
 	return filename__read_int(path, (int *) rate);
 }
 
-static int perf_record_opts__config_freq(struct perf_record_opts *opts)
+static int record_opts__config_freq(struct record_opts *opts)
 {
 	bool user_freq = opts->user_freq != UINT_MAX;
 	unsigned int max_rate;
@@ -173,9 +172,9 @@ static int perf_record_opts__config_freq(struct perf_record_opts *opts)
 	return 0;
 }
 
-int perf_record_opts__config(struct perf_record_opts *opts)
+int record_opts__config(struct record_opts *opts)
 {
-	return perf_record_opts__config_freq(opts);
+	return record_opts__config_freq(opts);
 }
 
 bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str)
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
index ce793c7..8e517de 100644
--- a/tools/perf/util/top.c
+++ b/tools/perf/util/top.c
@@ -26,7 +26,7 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
 	float samples_per_sec;
 	float ksamples_per_sec;
 	float esamples_percent;
-	struct perf_record_opts *opts = &top->record_opts;
+	struct record_opts *opts = &top->record_opts;
 	struct target *target = &opts->target;
 	size_t ret = 0;
 
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index 88cfeaf..dab14d0 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -14,7 +14,7 @@ struct perf_session;
 struct perf_top {
 	struct perf_tool   tool;
 	struct perf_evlist *evlist;
-	struct perf_record_opts record_opts;
+	struct record_opts record_opts;
 	/*
 	 * Symbols will be added here in perf_event__process_sample and will
 	 * get out after decayed.

[tip:perf/core] perf report: Rename 'perf_report' to 'report'

[tip-bot for Arnaldo Carvalho de Melo]

Commit-ID:  28b21393fa0472501b5a2a85a0b008b4e3dc154c
Gitweb:     http://git.kernel.org/tip/28b21393fa0472501b5a2a85a0b008b4e3dc154c
Author:     Arnaldo Carvalho de Melo <acme@redhat.com>
AuthorDate: Thu, 19 Dec 2013 14:53:53 -0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Thu, 19 Dec 2013 16:19:01 -0300

perf report: Rename 'perf_report' to 'report'

Reduce typing, functions use class__method convention, so unlikely to
clash with other libraries.

This actually was discussed in the "Link:" referenced message below.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/20131112113427.GA4053@ghostprotocols.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-report.c | 73 +++++++++++++++++++--------------------------
 1 file changed, 31 insertions(+), 42 deletions(-)

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 8424053..da156a4 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -39,7 +39,7 @@
 #include <dlfcn.h>
 #include <linux/bitmap.h>
 
-struct perf_report {
+struct report {
 	struct perf_tool	tool;
 	struct perf_session	*session;
 	bool			force, use_tui, use_gtk, use_stdio;
@@ -60,14 +60,14 @@ struct perf_report {
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
-static int perf_report_config(const char *var, const char *value, void *cb)
+static int report__config(const char *var, const char *value, void *cb)
 {
 	if (!strcmp(var, "report.group")) {
 		symbol_conf.event_group = perf_config_bool(var, value);
 		return 0;
 	}
 	if (!strcmp(var, "report.percent-limit")) {
-		struct perf_report *rep = cb;
+		struct report *rep = cb;
 		rep->min_percent = strtof(value, NULL);
 		return 0;
 	}
@@ -75,7 +75,7 @@ static int perf_report_config(const char *var, const char *value, void *cb)
 	return perf_default_config(var, value, cb);
 }
 
-static int report__resolve_callchain(struct perf_report *rep, struct symbol **parent,
+static int report__resolve_callchain(struct report *rep, struct symbol **parent,
 				     struct perf_evsel *evsel, struct addr_location *al,
 				     struct perf_sample *sample, struct machine *machine)
 {
@@ -93,14 +93,11 @@ static int hist_entry__append_callchain(struct hist_entry *he, struct perf_sampl
 	return callchain_append(he->callchain, &callchain_cursor, sample->period);
 }
 
-static int perf_report__add_mem_hist_entry(struct perf_tool *tool,
-					   struct addr_location *al,
-					   struct perf_sample *sample,
-					   struct perf_evsel *evsel,
-					   struct machine *machine,
-					   union perf_event *event)
+static int report__add_mem_hist_entry(struct perf_tool *tool, struct addr_location *al,
+				      struct perf_sample *sample, struct perf_evsel *evsel,
+				      struct machine *machine, union perf_event *event)
 {
-	struct perf_report *rep = container_of(tool, struct perf_report, tool);
+	struct report *rep = container_of(tool, struct report, tool);
 	struct symbol *parent = NULL;
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	struct hist_entry *he;
@@ -150,13 +147,11 @@ out:
 	return err;
 }
 
-static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
-					struct addr_location *al,
-					struct perf_sample *sample,
-					struct perf_evsel *evsel,
-				      struct machine *machine)
+static int report__add_branch_hist_entry(struct perf_tool *tool, struct addr_location *al,
+					 struct perf_sample *sample, struct perf_evsel *evsel,
+					 struct machine *machine)
 {
-	struct perf_report *rep = container_of(tool, struct perf_report, tool);
+	struct report *rep = container_of(tool, struct report, tool);
 	struct symbol *parent = NULL;
 	unsigned i;
 	struct hist_entry *he;
@@ -208,13 +203,11 @@ out:
 	return err;
 }
 
-static int perf_evsel__add_hist_entry(struct perf_tool *tool,
-				      struct perf_evsel *evsel,
-				      struct addr_location *al,
-				      struct perf_sample *sample,
-				      struct machine *machine)
+static int report__add_hist_entry(struct perf_tool *tool, struct perf_evsel *evsel,
+				  struct addr_location *al, struct perf_sample *sample,
+				  struct machine *machine)
 {
-	struct perf_report *rep = container_of(tool, struct perf_report, tool);
+	struct report *rep = container_of(tool, struct report, tool);
 	struct symbol *parent = NULL;
 	struct hist_entry *he;
 	int err = report__resolve_callchain(rep, &parent, evsel, al, sample, machine);
@@ -246,7 +239,7 @@ static int process_sample_event(struct perf_tool *tool,
 				struct perf_evsel *evsel,
 				struct machine *machine)
 {
-	struct perf_report *rep = container_of(tool, struct perf_report, tool);
+	struct report *rep = container_of(tool, struct report, tool);
 	struct addr_location al;
 	int ret;
 
@@ -263,21 +256,18 @@ static int process_sample_event(struct perf_tool *tool,
 		return 0;
 
 	if (sort__mode == SORT_MODE__BRANCH) {
-		ret = perf_report__add_branch_hist_entry(tool, &al, sample,
-							 evsel, machine);
+		ret = report__add_branch_hist_entry(tool, &al, sample, evsel, machine);
 		if (ret < 0)
 			pr_debug("problem adding lbr entry, skipping event\n");
 	} else if (rep->mem_mode == 1) {
-		ret = perf_report__add_mem_hist_entry(tool, &al, sample,
-						      evsel, machine, event);
+		ret = report__add_mem_hist_entry(tool, &al, sample, evsel, machine, event);
 		if (ret < 0)
 			pr_debug("problem adding mem entry, skipping event\n");
 	} else {
 		if (al.map != NULL)
 			al.map->dso->hit = 1;
 
-		ret = perf_evsel__add_hist_entry(tool, evsel, &al, sample,
-						 machine);
+		ret = report__add_hist_entry(tool, evsel, &al, sample, machine);
 		if (ret < 0)
 			pr_debug("problem incrementing symbol period, skipping event\n");
 	}
@@ -290,7 +280,7 @@ static int process_read_event(struct perf_tool *tool,
 			      struct perf_evsel *evsel,
 			      struct machine *machine __maybe_unused)
 {
-	struct perf_report *rep = container_of(tool, struct perf_report, tool);
+	struct report *rep = container_of(tool, struct report, tool);
 
 	if (rep->show_threads) {
 		const char *name = evsel ? perf_evsel__name(evsel) : "unknown";
@@ -309,7 +299,7 @@ static int process_read_event(struct perf_tool *tool,
 }
 
 /* For pipe mode, sample_type is not currently set */
-static int perf_report__setup_sample_type(struct perf_report *rep)
+static int report__setup_sample_type(struct report *rep)
 {
 	struct perf_session *session = rep->session;
 	u64 sample_type = perf_evlist__combined_sample_type(session->evlist);
@@ -354,8 +344,7 @@ static void sig_handler(int sig __maybe_unused)
 	session_done = 1;
 }
 
-static size_t hists__fprintf_nr_sample_events(struct perf_report *rep,
-					      struct hists *hists,
+static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report *rep,
 					      const char *evname, FILE *fp)
 {
 	size_t ret;
@@ -392,7 +381,7 @@ static size_t hists__fprintf_nr_sample_events(struct perf_report *rep,
 }
 
 static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
-					 struct perf_report *rep,
+					 struct report *rep,
 					 const char *help)
 {
 	struct perf_evsel *pos;
@@ -405,7 +394,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 		    !perf_evsel__is_group_leader(pos))
 			continue;
 
-		hists__fprintf_nr_sample_events(rep, hists, evname, stdout);
+		hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
 		hists__fprintf(hists, true, 0, 0, rep->min_percent, stdout);
 		fprintf(stdout, "\n\n");
 	}
@@ -425,7 +414,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 	return 0;
 }
 
-static int __cmd_report(struct perf_report *rep)
+static int __cmd_report(struct report *rep)
 {
 	int ret = -EINVAL;
 	u64 nr_samples;
@@ -449,7 +438,7 @@ static int __cmd_report(struct perf_report *rep)
 	if (rep->show_threads)
 		perf_read_values_init(&rep->show_threads_values);
 
-	ret = perf_report__setup_sample_type(rep);
+	ret = report__setup_sample_type(rep);
 	if (ret)
 		return ret;
 
@@ -568,7 +557,7 @@ static int __cmd_report(struct perf_report *rep)
 static int
 parse_callchain_opt(const struct option *opt, const char *arg, int unset)
 {
-	struct perf_report *rep = (struct perf_report *)opt->value;
+	struct report *rep = (struct report *)opt->value;
 	char *tok, *tok2;
 	char *endptr;
 
@@ -688,7 +677,7 @@ static int
 parse_percent_limit(const struct option *opt, const char *str,
 		    int unset __maybe_unused)
 {
-	struct perf_report *rep = opt->value;
+	struct report *rep = opt->value;
 
 	rep->min_percent = strtof(str, NULL);
 	return 0;
@@ -706,7 +695,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		"perf report [<options>]",
 		NULL
 	};
-	struct perf_report report = {
+	struct report report = {
 		.tool = {
 			.sample		 = process_sample_event,
 			.mmap		 = perf_event__process_mmap,
@@ -822,7 +811,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		.mode  = PERF_DATA_MODE_READ,
 	};
 
-	perf_config(perf_report_config, &report);
+	perf_config(report__config, &report);
 
 	argc = parse_options(argc, argv, options, report_usage, 0);