* [PATCH 0/9] perf tools: Assorted fixes
@ 2017-10-13 8:37 Jiri Olsa
2017-10-13 8:37 ` [PATCH 1/9] perf tools: Fix crash in perf_hpp__reset_output_field Jiri Olsa
` (8 more replies)
0 siblings, 9 replies; 16+ messages in thread
From: Jiri Olsa @ 2017-10-13 8:37 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: lkml, Ingo Molnar, Namhyung Kim, David Ahern, Peter Zijlstra,
Andi Kleen, Jin, Yao, Wangnan (F),
Du, Changbin
hi,
sending few fixes that pilled up.
It's also available at:
git://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf.git perf/fixes
thanks,
jirka
---
Jiri Olsa (9):
perf tools: Fix crash in perf_hpp__reset_output_field
perf tools: Add extra integrity checks to fmt_free
perf tools: Rename struct perf_data_file to perf_data
perf tools: Add struct perf_data_file
perf tools: Add perf_data_file__write function
perf stat: Move the shadow stats scale computation in perf_stat__update_shadow_stats
perf stat: Make --per-thread update shadow stats to show metrics
perf tools: Check wether the eBPF file exists in event parsing
perf tools: Unwind properly location after REJECT
tools/perf/builtin-annotate.c | 10 +++++-----
tools/perf/builtin-buildid-cache.c | 8 ++++----
tools/perf/builtin-buildid-list.c | 16 +++++++++-------
tools/perf/builtin-c2c.c | 10 +++++-----
tools/perf/builtin-diff.c | 18 +++++++++---------
tools/perf/builtin-evlist.c | 12 +++++++-----
tools/perf/builtin-inject.c | 36 +++++++++++++++++++-----------------
tools/perf/builtin-kmem.c | 8 ++++----
tools/perf/builtin-kvm.c | 14 ++++++++------
tools/perf/builtin-lock.c | 12 +++++++-----
tools/perf/builtin-mem.c | 12 +++++++-----
tools/perf/builtin-record.c | 50 +++++++++++++++++++++++++-------------------------
tools/perf/builtin-report.c | 14 +++++++-------
tools/perf/builtin-sched.c | 24 ++++++++++++++----------
tools/perf/builtin-script.c | 20 +++++++++++---------
tools/perf/builtin-stat.c | 35 +++++++++++++++++------------------
tools/perf/builtin-timechart.c | 14 ++++++++------
tools/perf/builtin-trace.c | 12 +++++++-----
tools/perf/tests/topology.c | 22 +++++++++++++---------
tools/perf/ui/hist.c | 9 ++++++++-
tools/perf/util/auxtrace.c | 4 ++--
tools/perf/util/data-convert-bt.c | 12 ++++++------
tools/perf/util/data.c | 94 ++++++++++++++++++++++++++++++++++++++++++++++++++--------------------------------------------
tools/perf/util/data.h | 38 ++++++++++++++++++++++----------------
tools/perf/util/header.c | 20 ++++++++++----------
tools/perf/util/intel-bts.c | 6 +++---
tools/perf/util/intel-pt.c | 6 +++---
tools/perf/util/jit.h | 2 +-
tools/perf/util/jitdump.c | 10 +++++-----
tools/perf/util/parse-events.l | 25 +++++++++++++++++++++----
tools/perf/util/session.c | 44 ++++++++++++++++++++++----------------------
tools/perf/util/session.h | 4 ++--
tools/perf/util/stat-shadow.c | 48 +++++++++++++++++++++++++-----------------------
tools/perf/util/stat.c | 8 ++++----
tools/perf/util/stat.h | 2 +-
35 files changed, 371 insertions(+), 308 deletions(-)
^ permalink raw reply [flat|nested] 16+ messages in thread
* [PATCH 1/9] perf tools: Fix crash in perf_hpp__reset_output_field
2017-10-13 8:37 [PATCH 0/9] perf tools: Assorted fixes Jiri Olsa
@ 2017-10-13 8:37 ` Jiri Olsa
2017-10-20 7:18 ` [tip:perf/urgent] perf hists: Fix crash in perf_hpp__reset_output_field() tip-bot for Jiri Olsa
2017-10-13 8:37 ` [PATCH 2/9] perf tools: Add extra integrity checks to fmt_free Jiri Olsa
` (7 subsequent siblings)
8 siblings, 1 reply; 16+ messages in thread
From: Jiri Olsa @ 2017-10-13 8:37 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: lkml, Ingo Molnar, Namhyung Kim, David Ahern, Peter Zijlstra,
Andi Kleen, Jin, Yao, Wangnan (F),
Du, Changbin
Du Changbin reported crash [1] when calling perf_hpp__reset_output_field
after unregistering field via perf_hpp__column_unregister.
This ends up in calling following list_del* sequence on
the same format:
perf_hpp__column_unregister:
list_del(&format->list);
perf_hpp__reset_output_field:
list_del_init(&fmt->list);
where the later list_del_init might touch already
freed formats.
Fixing this by replacing list_del with list_del_init
in perf_hpp__column_unregister.
[1] http://marc.info/?l=linux-kernel&m=149059595826019&w=2
Reported-by: "Du, Changbin" <changbin.du@intel.com>
Link: http://lkml.kernel.org/n/tip-8umo89ntt3kawmfwsivav43t@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
tools/perf/ui/hist.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index ddb2c6fbdf91..6ee6b36bbc76 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -532,7 +532,7 @@ void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
{
- list_del(&format->list);
+ list_del_init(&format->list);
}
void perf_hpp__cancel_cumulate(void)
--
2.13.6
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH 2/9] perf tools: Add extra integrity checks to fmt_free
2017-10-13 8:37 [PATCH 0/9] perf tools: Assorted fixes Jiri Olsa
2017-10-13 8:37 ` [PATCH 1/9] perf tools: Fix crash in perf_hpp__reset_output_field Jiri Olsa
@ 2017-10-13 8:37 ` Jiri Olsa
2017-10-20 7:19 ` [tip:perf/urgent] perf hists: Add extra integrity checks to fmt_free() tip-bot for Jiri Olsa
2017-10-13 8:37 ` [PATCH 3/9] perf tools: Rename struct perf_data_file to perf_data Jiri Olsa
` (6 subsequent siblings)
8 siblings, 1 reply; 16+ messages in thread
From: Jiri Olsa @ 2017-10-13 8:37 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: lkml, Ingo Molnar, Namhyung Kim, David Ahern, Peter Zijlstra,
Andi Kleen, Jin, Yao, Wangnan (F),
Du, Changbin
Make sure the struct perf_hpp_fmt is properly
unhooked before we free it.
Link: http://lkml.kernel.org/n/tip-8umo89ntt3kawmfwsivav43t@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
tools/perf/ui/hist.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 6ee6b36bbc76..db79017a6e56 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -606,6 +606,13 @@ void perf_hpp__append_sort_keys(struct perf_hpp_list *list)
static void fmt_free(struct perf_hpp_fmt *fmt)
{
+ /*
+ * At this point fmt should be completely
+ * unhooked, if not it's a bug.
+ */
+ BUG_ON(!list_empty(&fmt->list));
+ BUG_ON(!list_empty(&fmt->sort_list));
+
if (fmt->free)
fmt->free(fmt);
}
--
2.13.6
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH 3/9] perf tools: Rename struct perf_data_file to perf_data
2017-10-13 8:37 [PATCH 0/9] perf tools: Assorted fixes Jiri Olsa
2017-10-13 8:37 ` [PATCH 1/9] perf tools: Fix crash in perf_hpp__reset_output_field Jiri Olsa
2017-10-13 8:37 ` [PATCH 2/9] perf tools: Add extra integrity checks to fmt_free Jiri Olsa
@ 2017-10-13 8:37 ` Jiri Olsa
2017-10-13 8:37 ` [PATCH 4/9] perf tools: Add struct perf_data_file Jiri Olsa
` (5 subsequent siblings)
8 siblings, 0 replies; 16+ messages in thread
From: Jiri Olsa @ 2017-10-13 8:37 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: lkml, Ingo Molnar, Namhyung Kim, David Ahern, Peter Zijlstra,
Andi Kleen, Jin, Yao, Wangnan (F),
Du, Changbin
Renaming struct perf_data_file to perf_data, because
we will add the possibility to have multiple files
under perf.data, so the 'perf_data' name fits better.
Link: http://lkml.kernel.org/n/tip-39wn4d77phel3dgkzo3lyan0@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
tools/perf/builtin-annotate.c | 10 ++---
tools/perf/builtin-buildid-cache.c | 8 ++--
tools/perf/builtin-buildid-list.c | 8 ++--
tools/perf/builtin-c2c.c | 10 ++---
tools/perf/builtin-diff.c | 18 ++++----
tools/perf/builtin-evlist.c | 4 +-
tools/perf/builtin-inject.c | 26 +++++------
tools/perf/builtin-kmem.c | 8 ++--
tools/perf/builtin-kvm.c | 6 +--
tools/perf/builtin-lock.c | 4 +-
tools/perf/builtin-mem.c | 4 +-
tools/perf/builtin-record.c | 50 ++++++++++-----------
tools/perf/builtin-report.c | 14 +++---
tools/perf/builtin-sched.c | 8 ++--
tools/perf/builtin-script.c | 14 +++---
tools/perf/builtin-stat.c | 32 ++++++-------
tools/perf/builtin-timechart.c | 6 +--
tools/perf/builtin-trace.c | 4 +-
tools/perf/tests/topology.c | 10 ++---
tools/perf/util/auxtrace.c | 4 +-
tools/perf/util/data-convert-bt.c | 6 +--
tools/perf/util/data.c | 92 +++++++++++++++++++-------------------
tools/perf/util/data.h | 32 ++++++-------
| 20 ++++-----
tools/perf/util/intel-bts.c | 6 +--
tools/perf/util/intel-pt.c | 6 +--
tools/perf/util/jit.h | 2 +-
tools/perf/util/jitdump.c | 10 ++---
tools/perf/util/session.c | 44 +++++++++---------
tools/perf/util/session.h | 4 +-
30 files changed, 235 insertions(+), 235 deletions(-)
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index c38373195c4a..2d06be81a109 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -356,7 +356,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
}
if (total_nr_samples == 0) {
- ui__error("The %s file has no samples!\n", session->file->path);
+ ui__error("The %s file has no samples!\n", session->data->path);
goto out;
}
@@ -400,7 +400,7 @@ int cmd_annotate(int argc, const char **argv)
.ordering_requires_timestamps = true,
},
};
- struct perf_data_file file = {
+ struct perf_data data = {
.mode = PERF_DATA_MODE_READ,
};
struct option options[] = {
@@ -410,7 +410,7 @@ int cmd_annotate(int argc, const char **argv)
"only consider symbols in these dsos"),
OPT_STRING('s', "symbol", &annotate.sym_hist_filter, "symbol",
"symbol to annotate"),
- OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+ OPT_BOOLEAN('f', "force", &data.force, "don't complain, do it"),
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show symbol address, etc)"),
OPT_BOOLEAN('q', "quiet", &quiet, "do now show any message"),
@@ -482,9 +482,9 @@ int cmd_annotate(int argc, const char **argv)
if (quiet)
perf_quiet_option();
- file.path = input_name;
+ data.path = input_name;
- annotate.session = perf_session__new(&file, false, &annotate.tool);
+ annotate.session = perf_session__new(&data, false, &annotate.tool);
if (annotate.session == NULL)
return -1;
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index e3eb6240ced0..9fceae47a02e 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -311,7 +311,7 @@ int cmd_buildid_cache(int argc, const char **argv)
*kcore_filename = NULL;
char sbuf[STRERR_BUFSIZE];
- struct perf_data_file file = {
+ struct perf_data data = {
.mode = PERF_DATA_MODE_READ,
};
struct perf_session *session = NULL;
@@ -352,10 +352,10 @@ int cmd_buildid_cache(int argc, const char **argv)
nsi = nsinfo__new(ns_id);
if (missing_filename) {
- file.path = missing_filename;
- file.force = force;
+ data.path = missing_filename;
+ data.force = force;
- session = perf_session__new(&file, false, NULL);
+ session = perf_session__new(&data, false, NULL);
if (session == NULL)
return -1;
}
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index fdaca16e0c74..72bdc0eba990 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -50,7 +50,7 @@ static bool dso__skip_buildid(struct dso *dso, int with_hits)
static int perf_session__list_build_ids(bool force, bool with_hits)
{
struct perf_session *session;
- struct perf_data_file file = {
+ struct perf_data data = {
.path = input_name,
.mode = PERF_DATA_MODE_READ,
.force = force,
@@ -63,7 +63,7 @@ static int perf_session__list_build_ids(bool force, bool with_hits)
if (filename__fprintf_build_id(input_name, stdout) > 0)
goto out;
- session = perf_session__new(&file, false, &build_id__mark_dso_hit_ops);
+ session = perf_session__new(&data, false, &build_id__mark_dso_hit_ops);
if (session == NULL)
return -1;
@@ -71,7 +71,7 @@ static int perf_session__list_build_ids(bool force, bool with_hits)
* We take all buildids when the file contains AUX area tracing data
* because we do not decode the trace because it would take too long.
*/
- if (!perf_data_file__is_pipe(&file) &&
+ if (!perf_data__is_pipe(&data) &&
perf_header__has_feat(&session->header, HEADER_AUXTRACE))
with_hits = false;
@@ -79,7 +79,7 @@ static int perf_session__list_build_ids(bool force, bool with_hits)
* in pipe-mode, the only way to get the buildids is to parse
* the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID
*/
- if (with_hits || perf_data_file__is_pipe(&file))
+ if (with_hits || perf_data__is_pipe(&data))
perf_session__process_events(session);
perf_session__fprintf_dsos_buildid(session, stdout, dso__skip_buildid, with_hits);
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index bb1ee22bd221..87a52d09da29 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2523,7 +2523,7 @@ static int perf_c2c__report(int argc, const char **argv)
{
struct perf_session *session;
struct ui_progress prog;
- struct perf_data_file file = {
+ struct perf_data data = {
.mode = PERF_DATA_MODE_READ,
};
char callchain_default_opt[] = CALLCHAIN_DEFAULT_OPT;
@@ -2572,8 +2572,8 @@ static int perf_c2c__report(int argc, const char **argv)
if (!input_name || !strlen(input_name))
input_name = "perf.data";
- file.path = input_name;
- file.force = symbol_conf.force;
+ data.path = input_name;
+ data.force = symbol_conf.force;
err = setup_display(display);
if (err)
@@ -2591,7 +2591,7 @@ static int perf_c2c__report(int argc, const char **argv)
goto out;
}
- session = perf_session__new(&file, 0, &c2c.tool);
+ session = perf_session__new(&data, 0, &c2c.tool);
if (session == NULL) {
pr_debug("No memory for session\n");
goto out;
@@ -2611,7 +2611,7 @@ static int perf_c2c__report(int argc, const char **argv)
goto out_session;
/* No pipe support at the moment. */
- if (perf_data_file__is_pipe(session->file)) {
+ if (perf_data__is_pipe(session->data)) {
pr_debug("No pipe support at the moment.\n");
goto out_session;
}
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 0cd4cf6a344b..5292e3d13cec 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -47,7 +47,7 @@ struct diff_hpp_fmt {
struct data__file {
struct perf_session *session;
- struct perf_data_file file;
+ struct perf_data data;
int idx;
struct hists *hists;
struct diff_hpp_fmt fmt[PERF_HPP_DIFF__MAX_INDEX];
@@ -707,7 +707,7 @@ static void data__fprintf(void)
data__for_each_file(i, d)
fprintf(stdout, "# [%d] %s %s\n",
- d->idx, d->file.path,
+ d->idx, d->data.path,
!d->idx ? "(Baseline)" : "");
fprintf(stdout, "#\n");
@@ -776,16 +776,16 @@ static int __cmd_diff(void)
int ret = -EINVAL, i;
data__for_each_file(i, d) {
- d->session = perf_session__new(&d->file, false, &tool);
+ d->session = perf_session__new(&d->data, false, &tool);
if (!d->session) {
- pr_err("Failed to open %s\n", d->file.path);
+ pr_err("Failed to open %s\n", d->data.path);
ret = -1;
goto out_delete;
}
ret = perf_session__process_events(d->session);
if (ret) {
- pr_err("Failed to process %s\n", d->file.path);
+ pr_err("Failed to process %s\n", d->data.path);
goto out_delete;
}
@@ -1286,11 +1286,11 @@ static int data_init(int argc, const char **argv)
return -ENOMEM;
data__for_each_file(i, d) {
- struct perf_data_file *file = &d->file;
+ struct perf_data *data = &d->data;
- file->path = use_default ? defaults[i] : argv[i];
- file->mode = PERF_DATA_MODE_READ,
- file->force = force,
+ data->path = use_default ? defaults[i] : argv[i];
+ data->mode = PERF_DATA_MODE_READ,
+ data->force = force,
d->idx = i;
}
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index 6d210e40d611..cd79c26e16a4 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -21,14 +21,14 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details
{
struct perf_session *session;
struct perf_evsel *pos;
- struct perf_data_file file = {
+ struct perf_data data = {
.path = file_name,
.mode = PERF_DATA_MODE_READ,
.force = details->force,
};
bool has_tracepoint = false;
- session = perf_session__new(&file, 0, NULL);
+ session = perf_session__new(&data, 0, NULL);
if (session == NULL)
return -1;
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 2b8032908fb2..ac7486f6c46f 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -35,7 +35,7 @@ struct perf_inject {
bool strip;
bool jit_mode;
const char *input_name;
- struct perf_data_file output;
+ struct perf_data output;
u64 bytes_written;
u64 aux_id;
struct list_head samples;
@@ -52,7 +52,7 @@ static int output_bytes(struct perf_inject *inject, void *buf, size_t sz)
{
ssize_t size;
- size = perf_data_file__write(&inject->output, buf, sz);
+ size = perf_data__write(&inject->output, buf, sz);
if (size < 0)
return -errno;
@@ -154,11 +154,11 @@ static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
return ret;
}
- if (perf_data_file__is_pipe(session->file) || !session->one_mmap) {
+ if (perf_data__is_pipe(session->data) || !session->one_mmap) {
ret = output_bytes(inject, event, event->header.size);
if (ret < 0)
return ret;
- ret = copy_bytes(inject, perf_data_file__fd(session->file),
+ ret = copy_bytes(inject, perf_data__fd(session->data),
event->auxtrace.size);
} else {
ret = output_bytes(inject, event,
@@ -637,8 +637,8 @@ static int __cmd_inject(struct perf_inject *inject)
{
int ret = -EINVAL;
struct perf_session *session = inject->session;
- struct perf_data_file *file_out = &inject->output;
- int fd = perf_data_file__fd(file_out);
+ struct perf_data *data_out = &inject->output;
+ int fd = perf_data__fd(data_out);
u64 output_data_offset;
signal(SIGINT, sig_handler);
@@ -693,14 +693,14 @@ static int __cmd_inject(struct perf_inject *inject)
if (!inject->itrace_synth_opts.set)
auxtrace_index__free(&session->auxtrace_index);
- if (!file_out->is_pipe)
+ if (!data_out->is_pipe)
lseek(fd, output_data_offset, SEEK_SET);
ret = perf_session__process_events(session);
if (ret)
return ret;
- if (!file_out->is_pipe) {
+ if (!data_out->is_pipe) {
if (inject->build_ids)
perf_header__set_feat(&session->header,
HEADER_BUILD_ID);
@@ -779,7 +779,7 @@ int cmd_inject(int argc, const char **argv)
.mode = PERF_DATA_MODE_WRITE,
},
};
- struct perf_data_file file = {
+ struct perf_data data = {
.mode = PERF_DATA_MODE_READ,
};
int ret;
@@ -801,7 +801,7 @@ int cmd_inject(int argc, const char **argv)
"be more verbose (show build ids, etc)"),
OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, "file",
"kallsyms pathname"),
- OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+ OPT_BOOLEAN('f', "force", &data.force, "don't complain, do it"),
OPT_CALLBACK_OPTARG(0, "itrace", &inject.itrace_synth_opts,
NULL, "opts", "Instruction Tracing options",
itrace_parse_synth_opts),
@@ -829,15 +829,15 @@ int cmd_inject(int argc, const char **argv)
return -1;
}
- if (perf_data_file__open(&inject.output)) {
+ if (perf_data__open(&inject.output)) {
perror("failed to create output file");
return -1;
}
inject.tool.ordered_events = inject.sched_stat;
- file.path = inject.input_name;
- inject.session = perf_session__new(&file, true, &inject.tool);
+ data.path = inject.input_name;
+ inject.session = perf_session__new(&data, true, &inject.tool);
if (inject.session == NULL)
return -1;
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 24ee68ecdd42..e2314bba2a3f 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -1893,7 +1893,7 @@ int cmd_kmem(int argc, const char **argv)
{
const char * const default_slab_sort = "frag,hit,bytes";
const char * const default_page_sort = "bytes,hit";
- struct perf_data_file file = {
+ struct perf_data data = {
.mode = PERF_DATA_MODE_READ,
};
const struct option kmem_options[] = {
@@ -1909,7 +1909,7 @@ int cmd_kmem(int argc, const char **argv)
"page, order, migtype, gfp", parse_sort_opt),
OPT_CALLBACK('l', "line", NULL, "num", "show n lines", parse_line_opt),
OPT_BOOLEAN(0, "raw-ip", &raw_ip, "show raw ip instead of symbol"),
- OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+ OPT_BOOLEAN('f', "force", &data.force, "don't complain, do it"),
OPT_CALLBACK_NOOPT(0, "slab", NULL, NULL, "Analyze slab allocator",
parse_slab_opt),
OPT_CALLBACK_NOOPT(0, "page", NULL, NULL, "Analyze page allocator",
@@ -1949,9 +1949,9 @@ int cmd_kmem(int argc, const char **argv)
return __cmd_record(argc, argv);
}
- file.path = input_name;
+ data.path = input_name;
- kmem_session = session = perf_session__new(&file, false, &perf_kmem);
+ kmem_session = session = perf_session__new(&data, false, &perf_kmem);
if (session == NULL)
return -1;
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 721f4f91291a..4301fc34f23c 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1067,7 +1067,7 @@ static int read_events(struct perf_kvm_stat *kvm)
.namespaces = perf_event__process_namespaces,
.ordered_events = true,
};
- struct perf_data_file file = {
+ struct perf_data file = {
.path = kvm->file_name,
.mode = PERF_DATA_MODE_READ,
.force = kvm->force,
@@ -1358,7 +1358,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
"perf kvm stat live [<options>]",
NULL
};
- struct perf_data_file file = {
+ struct perf_data data = {
.mode = PERF_DATA_MODE_WRITE,
};
@@ -1432,7 +1432,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
/*
* perf session
*/
- kvm->session = perf_session__new(&file, false, &kvm->tool);
+ kvm->session = perf_session__new(&data, false, &kvm->tool);
if (kvm->session == NULL) {
err = -1;
goto out;
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index ff98652484a7..2e281f7b0fca 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -864,13 +864,13 @@ static int __cmd_report(bool display_info)
.namespaces = perf_event__process_namespaces,
.ordered_events = true,
};
- struct perf_data_file file = {
+ struct perf_data data = {
.path = input_name,
.mode = PERF_DATA_MODE_READ,
.force = force,
};
- session = perf_session__new(&file, false, &eops);
+ session = perf_session__new(&data, false, &eops);
if (!session) {
pr_err("Initializing perf session failed\n");
return -1;
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 6940490bc3f9..5a4a6f8e614d 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -236,13 +236,13 @@ static int process_sample_event(struct perf_tool *tool,
static int report_raw_events(struct perf_mem *mem)
{
- struct perf_data_file file = {
+ struct perf_data data = {
.path = input_name,
.mode = PERF_DATA_MODE_READ,
.force = mem->force,
};
int ret;
- struct perf_session *session = perf_session__new(&file, false,
+ struct perf_session *session = perf_session__new(&data, false,
&mem->tool);
if (session == NULL)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index a6cbf1640269..0ab7dd0e4f2b 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -66,7 +66,7 @@ struct record {
struct perf_tool tool;
struct record_opts opts;
u64 bytes_written;
- struct perf_data_file file;
+ struct perf_data data;
struct auxtrace_record *itr;
struct perf_evlist *evlist;
struct perf_session *session;
@@ -107,7 +107,7 @@ static bool switch_output_time(struct record *rec)
static int record__write(struct record *rec, void *bf, size_t size)
{
- if (perf_data_file__write(rec->session->file, bf, size) < 0) {
+ if (perf_data__write(rec->session->data, bf, size) < 0) {
pr_err("failed to write perf data, error: %m\n");
return -1;
}
@@ -173,13 +173,13 @@ static int record__process_auxtrace(struct perf_tool *tool,
size_t len1, void *data2, size_t len2)
{
struct record *rec = container_of(tool, struct record, tool);
- struct perf_data_file *file = &rec->file;
+ struct perf_data *data = &rec->data;
size_t padding;
u8 pad[8] = {0};
- if (!perf_data_file__is_pipe(file)) {
+ if (!perf_data__is_pipe(data)) {
off_t file_offset;
- int fd = perf_data_file__fd(file);
+ int fd = perf_data__fd(data);
int err;
file_offset = lseek(fd, 0, SEEK_CUR);
@@ -398,10 +398,10 @@ static int process_sample_event(struct perf_tool *tool,
static int process_buildids(struct record *rec)
{
- struct perf_data_file *file = &rec->file;
+ struct perf_data *data = &rec->data;
struct perf_session *session = rec->session;
- if (file->size == 0)
+ if (data->size == 0)
return 0;
/*
@@ -544,14 +544,14 @@ static void record__init_features(struct record *rec)
static void
record__finish_output(struct record *rec)
{
- struct perf_data_file *file = &rec->file;
- int fd = perf_data_file__fd(file);
+ struct perf_data *data = &rec->data;
+ int fd = perf_data__fd(data);
- if (file->is_pipe)
+ if (data->is_pipe)
return;
rec->session->header.data_size += rec->bytes_written;
- file->size = lseek(perf_data_file__fd(file), 0, SEEK_CUR);
+ data->size = lseek(perf_data__fd(data), 0, SEEK_CUR);
if (!rec->no_buildid) {
process_buildids(rec);
@@ -590,7 +590,7 @@ static int record__synthesize(struct record *rec, bool tail);
static int
record__switch_output(struct record *rec, bool at_exit)
{
- struct perf_data_file *file = &rec->file;
+ struct perf_data *data = &rec->data;
int fd, err;
/* Same Size: "2015122520103046"*/
@@ -608,7 +608,7 @@ record__switch_output(struct record *rec, bool at_exit)
return -EINVAL;
}
- fd = perf_data_file__switch(file, timestamp,
+ fd = perf_data__switch(data, timestamp,
rec->session->header.data_offset,
at_exit);
if (fd >= 0 && !at_exit) {
@@ -618,7 +618,7 @@ record__switch_output(struct record *rec, bool at_exit)
if (!quiet)
fprintf(stderr, "[ perf record: Dump %s.%s ]\n",
- file->path, timestamp);
+ data->path, timestamp);
/* Output tracking events */
if (!at_exit) {
@@ -693,16 +693,16 @@ static int record__synthesize(struct record *rec, bool tail)
{
struct perf_session *session = rec->session;
struct machine *machine = &session->machines.host;
- struct perf_data_file *file = &rec->file;
+ struct perf_data *data = &rec->data;
struct record_opts *opts = &rec->opts;
struct perf_tool *tool = &rec->tool;
- int fd = perf_data_file__fd(file);
+ int fd = perf_data__fd(data);
int err = 0;
if (rec->opts.tail_synthesize != tail)
return 0;
- if (file->is_pipe) {
+ if (data->is_pipe) {
err = perf_event__synthesize_features(
tool, session, rec->evlist, process_synthesized_event);
if (err < 0) {
@@ -781,7 +781,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
struct machine *machine;
struct perf_tool *tool = &rec->tool;
struct record_opts *opts = &rec->opts;
- struct perf_data_file *file = &rec->file;
+ struct perf_data *data = &rec->data;
struct perf_session *session;
bool disabled = false, draining = false;
int fd;
@@ -807,20 +807,20 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
signal(SIGUSR2, SIG_IGN);
}
- session = perf_session__new(file, false, tool);
+ session = perf_session__new(data, false, tool);
if (session == NULL) {
pr_err("Perf session creation failed.\n");
return -1;
}
- fd = perf_data_file__fd(file);
+ fd = perf_data__fd(data);
rec->session = session;
record__init_features(rec);
if (forks) {
err = perf_evlist__prepare_workload(rec->evlist, &opts->target,
- argv, file->is_pipe,
+ argv, data->is_pipe,
workload_exec_failed_signal);
if (err < 0) {
pr_err("Couldn't run the workload!\n");
@@ -856,7 +856,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
if (!rec->evlist->nr_groups)
perf_header__clear_feat(&session->header, HEADER_GROUP_DESC);
- if (file->is_pipe) {
+ if (data->is_pipe) {
err = perf_header__write_pipe(fd);
if (err < 0)
goto out_child;
@@ -1117,8 +1117,8 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
samples[0] = '\0';
fprintf(stderr, "[ perf record: Captured and wrote %.3f MB %s%s%s ]\n",
- perf_data_file__size(file) / 1024.0 / 1024.0,
- file->path, postfix, samples);
+ perf_data__size(data) / 1024.0 / 1024.0,
+ data->path, postfix, samples);
}
out_delete_session:
@@ -1482,7 +1482,7 @@ static struct option __record_options[] = {
OPT_STRING('C', "cpu", &record.opts.target.cpu_list, "cpu",
"list of cpus to monitor"),
OPT_U64('c', "count", &record.opts.user_interval, "event period to sample"),
- OPT_STRING('o', "output", &record.file.path, "file",
+ OPT_STRING('o', "output", &record.data.path, "file",
"output file name"),
OPT_BOOLEAN_SET('i', "no-inherit", &record.opts.no_inherit,
&record.opts.no_inherit_set,
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index f9dff652dcbd..0dc323772b5e 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -257,7 +257,7 @@ 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);
- bool is_pipe = perf_data_file__is_pipe(session->file);
+ bool is_pipe = perf_data__is_pipe(session->data);
if (session->itrace_synth_opts->callchain ||
(!is_pipe &&
@@ -568,7 +568,7 @@ static int __cmd_report(struct report *rep)
int ret;
struct perf_session *session = rep->session;
struct perf_evsel *pos;
- struct perf_data_file *file = session->file;
+ struct perf_data *data = session->data;
signal(SIGINT, sig_handler);
@@ -637,7 +637,7 @@ static int __cmd_report(struct report *rep)
rep->nr_entries += evsel__hists(pos)->nr_entries;
if (rep->nr_entries == 0) {
- ui__error("The %s file has no samples!\n", file->path);
+ ui__error("The %s file has no samples!\n", data->path);
return 0;
}
@@ -879,7 +879,7 @@ int cmd_report(int argc, const char **argv)
"Show inline function"),
OPT_END()
};
- struct perf_data_file file = {
+ struct perf_data data = {
.mode = PERF_DATA_MODE_READ,
};
int ret = hists__init();
@@ -940,11 +940,11 @@ int cmd_report(int argc, const char **argv)
input_name = "perf.data";
}
- file.path = input_name;
- file.force = symbol_conf.force;
+ data.path = input_name;
+ data.force = symbol_conf.force;
repeat:
- session = perf_session__new(&file, false, &report.tool);
+ session = perf_session__new(&data, false, &report.tool);
if (session == NULL)
return -1;
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index b7e8812ee80c..cb5410511f69 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1700,14 +1700,14 @@ static int perf_sched__read_events(struct perf_sched *sched)
{ "sched:sched_migrate_task", process_sched_migrate_task_event, },
};
struct perf_session *session;
- struct perf_data_file file = {
+ struct perf_data data = {
.path = input_name,
.mode = PERF_DATA_MODE_READ,
.force = sched->force,
};
int rc = -1;
- session = perf_session__new(&file, false, &sched->tool);
+ session = perf_session__new(&data, false, &sched->tool);
if (session == NULL) {
pr_debug("No Memory for session\n");
return -1;
@@ -2902,7 +2902,7 @@ static int perf_sched__timehist(struct perf_sched *sched)
const struct perf_evsel_str_handler migrate_handlers[] = {
{ "sched:sched_migrate_task", timehist_migrate_task_event, },
};
- struct perf_data_file file = {
+ struct perf_data data = {
.path = input_name,
.mode = PERF_DATA_MODE_READ,
.force = sched->force,
@@ -2930,7 +2930,7 @@ static int perf_sched__timehist(struct perf_sched *sched)
symbol_conf.use_callchain = sched->show_callchain;
- session = perf_session__new(&file, false, &sched->tool);
+ session = perf_session__new(&data, false, &sched->tool);
if (session == NULL)
return -ENOMEM;
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 9092de0f7238..8477c41dbbe0 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2446,14 +2446,14 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN];
DIR *scripts_dir, *lang_dir;
struct perf_session *session;
- struct perf_data_file file = {
+ struct perf_data data = {
.path = input_name,
.mode = PERF_DATA_MODE_READ,
};
char *temp;
int i = 0;
- session = perf_session__new(&file, false, NULL);
+ session = perf_session__new(&data, false, NULL);
if (!session)
return -1;
@@ -2731,7 +2731,7 @@ int cmd_script(int argc, const char **argv)
.ordering_requires_timestamps = true,
},
};
- struct perf_data_file file = {
+ struct perf_data data = {
.mode = PERF_DATA_MODE_READ,
};
const struct option options[] = {
@@ -2836,8 +2836,8 @@ int cmd_script(int argc, const char **argv)
argc = parse_options_subcommand(argc, argv, options, script_subcommands, script_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
- file.path = input_name;
- file.force = symbol_conf.force;
+ data.path = input_name;
+ data.force = symbol_conf.force;
if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) {
rec_script_path = get_script_path(argv[1], RECORD_SUFFIX);
@@ -3004,7 +3004,7 @@ int cmd_script(int argc, const char **argv)
if (!script_name)
setup_pager();
- session = perf_session__new(&file, false, &script.tool);
+ session = perf_session__new(&data, false, &script.tool);
if (session == NULL)
return -1;
@@ -3059,7 +3059,7 @@ int cmd_script(int argc, const char **argv)
goto out_delete;
}
- input = open(file.path, O_RDONLY); /* input_name */
+ input = open(data.path, O_RDONLY); /* input_name */
if (input < 0) {
err = -errno;
perror("failed to open file");
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index dd525417880a..6a1ef0941fd2 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -175,7 +175,7 @@ static int print_free_counters_hint;
struct perf_stat {
bool record;
- struct perf_data_file file;
+ struct perf_data data;
struct perf_session *session;
u64 bytes_written;
struct perf_tool tool;
@@ -253,7 +253,7 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
* by attr->sample_type != 0, and we can't run it on
* stat sessions.
*/
- if (!(STAT_RECORD && perf_stat.file.is_pipe))
+ if (!(STAT_RECORD && perf_stat.data.is_pipe))
attr->sample_type = PERF_SAMPLE_IDENTIFIER;
/*
@@ -295,7 +295,7 @@ static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
struct perf_sample *sample __maybe_unused,
struct machine *machine __maybe_unused)
{
- if (perf_data_file__write(&perf_stat.file, event, event->header.size) < 0) {
+ if (perf_data__write(&perf_stat.data, event, event->header.size) < 0) {
pr_err("failed to write perf data, error: %m\n");
return -1;
}
@@ -628,7 +628,7 @@ static int __run_perf_stat(int argc, const char **argv)
size_t l;
int status = 0;
const bool forks = (argc > 0);
- bool is_pipe = STAT_RECORD ? perf_stat.file.is_pipe : false;
+ bool is_pipe = STAT_RECORD ? perf_stat.data.is_pipe : false;
struct perf_evsel_config_term *err_term;
if (interval) {
@@ -719,10 +719,10 @@ static int __run_perf_stat(int argc, const char **argv)
}
if (STAT_RECORD) {
- int err, fd = perf_data_file__fd(&perf_stat.file);
+ int err, fd = perf_data__fd(&perf_stat.data);
if (is_pipe) {
- err = perf_header__write_pipe(perf_data_file__fd(&perf_stat.file));
+ err = perf_header__write_pipe(perf_data__fd(&perf_stat.data));
} else {
err = perf_session__write_header(perf_stat.session, evsel_list,
fd, false);
@@ -1696,7 +1696,7 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
char buf[64], *prefix = NULL;
/* Do not print anything if we record to the pipe. */
- if (STAT_RECORD && perf_stat.file.is_pipe)
+ if (STAT_RECORD && perf_stat.data.is_pipe)
return;
if (interval)
@@ -2406,20 +2406,20 @@ static void init_features(struct perf_session *session)
static int __cmd_record(int argc, const char **argv)
{
struct perf_session *session;
- struct perf_data_file *file = &perf_stat.file;
+ struct perf_data *data = &perf_stat.data;
argc = parse_options(argc, argv, stat_options, stat_record_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
if (output_name)
- file->path = output_name;
+ data->path = output_name;
if (run_count != 1 || forever) {
pr_err("Cannot use -r option with perf stat record.\n");
return -1;
}
- session = perf_session__new(file, false, NULL);
+ session = perf_session__new(data, false, NULL);
if (session == NULL) {
pr_err("Perf session creation failed.\n");
return -1;
@@ -2477,7 +2477,7 @@ int process_stat_config_event(struct perf_tool *tool,
if (st->aggr_mode != AGGR_UNSET)
stat_config.aggr_mode = st->aggr_mode;
- if (perf_stat.file.is_pipe)
+ if (perf_stat.data.is_pipe)
perf_stat_init_aggr_mode();
else
perf_stat_init_aggr_mode_file(st);
@@ -2585,10 +2585,10 @@ static int __cmd_report(int argc, const char **argv)
input_name = "perf.data";
}
- perf_stat.file.path = input_name;
- perf_stat.file.mode = PERF_DATA_MODE_READ;
+ perf_stat.data.path = input_name;
+ perf_stat.data.mode = PERF_DATA_MODE_READ;
- session = perf_session__new(&perf_stat.file, false, &perf_stat.tool);
+ session = perf_session__new(&perf_stat.data, false, &perf_stat.tool);
if (session == NULL)
return -1;
@@ -2859,7 +2859,7 @@ int cmd_stat(int argc, const char **argv)
* records, but the need to suppress the kptr_restrict messages in older
* tools remain -acme
*/
- int fd = perf_data_file__fd(&perf_stat.file);
+ int fd = perf_data__fd(&perf_stat.data);
int err = perf_event__synthesize_kernel_mmap((void *)&perf_stat,
process_synthesized_event,
&perf_stat.session->machines.host);
@@ -2873,7 +2873,7 @@ int cmd_stat(int argc, const char **argv)
pr_err("failed to write stat round event\n");
}
- if (!perf_stat.file.is_pipe) {
+ if (!perf_stat.data.is_pipe) {
perf_stat.session->header.data_size += perf_stat.bytes_written;
perf_session__write_header(perf_stat.session, evsel_list, fd, true);
}
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 01de01ca14f2..0f79ea5e2f0f 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -1601,13 +1601,13 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name)
{ "syscalls:sys_exit_pselect6", process_exit_poll },
{ "syscalls:sys_exit_select", process_exit_poll },
};
- struct perf_data_file file = {
+ struct perf_data data = {
.path = input_name,
.mode = PERF_DATA_MODE_READ,
.force = tchart->force,
};
- struct perf_session *session = perf_session__new(&file, false,
+ struct perf_session *session = perf_session__new(&data, false,
&tchart->tool);
int ret = -EINVAL;
@@ -1617,7 +1617,7 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name)
symbol__init(&session->header.env);
(void)perf_header__process_sections(&session->header,
- perf_data_file__fd(session->file),
+ perf_data__fd(session->data),
tchart,
process_header);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index afef6fe46c45..94beb372d097 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2529,7 +2529,7 @@ static int trace__replay(struct trace *trace)
const struct perf_evsel_str_handler handlers[] = {
{ "probe:vfs_getname", trace__vfs_getname, },
};
- struct perf_data_file file = {
+ struct perf_data data = {
.path = input_name,
.mode = PERF_DATA_MODE_READ,
.force = trace->force,
@@ -2555,7 +2555,7 @@ static int trace__replay(struct trace *trace)
/* add tid to output */
trace->multiple_threads = true;
- session = perf_session__new(&file, false, &trace->tool);
+ session = perf_session__new(&data, false, &trace->tool);
if (session == NULL)
return -1;
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index 19b0561fd6f6..7536782e8495 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -29,12 +29,12 @@ static int get_temp(char *path)
static int session_write_header(char *path)
{
struct perf_session *session;
- struct perf_data_file file = {
+ struct perf_data data = {
.path = path,
.mode = PERF_DATA_MODE_WRITE,
};
- session = perf_session__new(&file, false, NULL);
+ session = perf_session__new(&data, false, NULL);
TEST_ASSERT_VAL("can't get session", session);
session->evlist = perf_evlist__new_default();
@@ -46,7 +46,7 @@ static int session_write_header(char *path)
session->header.data_size += DATA_SIZE;
TEST_ASSERT_VAL("failed to write header",
- !perf_session__write_header(session, session->evlist, file.fd, true));
+ !perf_session__write_header(session, session->evlist, data.fd, true));
perf_session__delete(session);
@@ -56,13 +56,13 @@ static int session_write_header(char *path)
static int check_cpu_topology(char *path, struct cpu_map *map)
{
struct perf_session *session;
- struct perf_data_file file = {
+ struct perf_data data = {
.path = path,
.mode = PERF_DATA_MODE_READ,
};
int i;
- session = perf_session__new(&file, false, NULL);
+ session = perf_session__new(&data, false, NULL);
TEST_ASSERT_VAL("can't get session", session);
for (i = 0; i < session->header.env.nr_cpus_avail; i++) {
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 5547457566a7..a33491416400 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -208,7 +208,7 @@ static int auxtrace_queues__grow(struct auxtrace_queues *queues,
static void *auxtrace_copy_data(u64 size, struct perf_session *session)
{
- int fd = perf_data_file__fd(session->file);
+ int fd = perf_data__fd(session->data);
void *p;
ssize_t ret;
@@ -305,7 +305,7 @@ static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues,
if (session->one_mmap) {
buffer->data = buffer->data_offset - session->one_mmap_offset +
session->one_mmap_addr;
- } else if (perf_data_file__is_pipe(session->file)) {
+ } else if (perf_data__is_pipe(session->data)) {
buffer->data = auxtrace_copy_data(buffer->size, session);
if (!buffer->data)
return -ENOMEM;
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 2346cecb8ea2..9fdae383a58c 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -1577,7 +1577,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
struct perf_data_convert_opts *opts)
{
struct perf_session *session;
- struct perf_data_file file = {
+ struct perf_data data = {
.path = input,
.mode = PERF_DATA_MODE_READ,
.force = opts->force,
@@ -1619,7 +1619,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
err = -1;
/* perf.data session */
- session = perf_session__new(&file, 0, &c.tool);
+ session = perf_session__new(&data, 0, &c.tool);
if (!session)
goto free_writer;
@@ -1650,7 +1650,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
fprintf(stderr,
"[ perf data convert: Converted '%s' into CTF data '%s' ]\n",
- file.path, path);
+ data.path, path);
fprintf(stderr,
"[ perf data convert: Converted and wrote %.3f MB (%" PRIu64 " samples",
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index 1123b30e3033..a6eea3df4c10 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -21,56 +21,56 @@
#endif
#endif
-static bool check_pipe(struct perf_data_file *file)
+static bool check_pipe(struct perf_data *data)
{
struct stat st;
bool is_pipe = false;
- int fd = perf_data_file__is_read(file) ?
+ int fd = perf_data__is_read(data) ?
STDIN_FILENO : STDOUT_FILENO;
- if (!file->path) {
+ if (!data->path) {
if (!fstat(fd, &st) && S_ISFIFO(st.st_mode))
is_pipe = true;
} else {
- if (!strcmp(file->path, "-"))
+ if (!strcmp(data->path, "-"))
is_pipe = true;
}
if (is_pipe)
- file->fd = fd;
+ data->fd = fd;
- return file->is_pipe = is_pipe;
+ return data->is_pipe = is_pipe;
}
-static int check_backup(struct perf_data_file *file)
+static int check_backup(struct perf_data *data)
{
struct stat st;
- if (!stat(file->path, &st) && st.st_size) {
+ if (!stat(data->path, &st) && st.st_size) {
/* TODO check errors properly */
char oldname[PATH_MAX];
snprintf(oldname, sizeof(oldname), "%s.old",
- file->path);
+ data->path);
unlink(oldname);
- rename(file->path, oldname);
+ rename(data->path, oldname);
}
return 0;
}
-static int open_file_read(struct perf_data_file *file)
+static int open_file_read(struct perf_data *data)
{
struct stat st;
int fd;
char sbuf[STRERR_BUFSIZE];
- fd = open(file->path, O_RDONLY);
+ fd = open(data->path, O_RDONLY);
if (fd < 0) {
int err = errno;
- pr_err("failed to open %s: %s", file->path,
+ pr_err("failed to open %s: %s", data->path,
str_error_r(err, sbuf, sizeof(sbuf)));
- if (err == ENOENT && !strcmp(file->path, "perf.data"))
+ if (err == ENOENT && !strcmp(data->path, "perf.data"))
pr_err(" (try 'perf record' first)");
pr_err("\n");
return -err;
@@ -79,19 +79,19 @@ static int open_file_read(struct perf_data_file *file)
if (fstat(fd, &st) < 0)
goto out_close;
- if (!file->force && st.st_uid && (st.st_uid != geteuid())) {
+ if (!data->force && st.st_uid && (st.st_uid != geteuid())) {
pr_err("File %s not owned by current user or root (use -f to override)\n",
- file->path);
+ data->path);
goto out_close;
}
if (!st.st_size) {
- pr_info("zero-sized file (%s), nothing to do!\n",
- file->path);
+ pr_info("zero-sized data (%s), nothing to do!\n",
+ data->path);
goto out_close;
}
- file->size = st.st_size;
+ data->size = st.st_size;
return fd;
out_close:
@@ -99,93 +99,93 @@ static int open_file_read(struct perf_data_file *file)
return -1;
}
-static int open_file_write(struct perf_data_file *file)
+static int open_file_write(struct perf_data *data)
{
int fd;
char sbuf[STRERR_BUFSIZE];
- if (check_backup(file))
+ if (check_backup(data))
return -1;
- fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC|O_CLOEXEC,
+ fd = open(data->path, O_CREAT|O_RDWR|O_TRUNC|O_CLOEXEC,
S_IRUSR|S_IWUSR);
if (fd < 0)
- pr_err("failed to open %s : %s\n", file->path,
+ pr_err("failed to open %s : %s\n", data->path,
str_error_r(errno, sbuf, sizeof(sbuf)));
return fd;
}
-static int open_file(struct perf_data_file *file)
+static int open_file(struct perf_data *data)
{
int fd;
- fd = perf_data_file__is_read(file) ?
- open_file_read(file) : open_file_write(file);
+ fd = perf_data__is_read(data) ?
+ open_file_read(data) : open_file_write(data);
- file->fd = fd;
+ data->fd = fd;
return fd < 0 ? -1 : 0;
}
-int perf_data_file__open(struct perf_data_file *file)
+int perf_data__open(struct perf_data *data)
{
- if (check_pipe(file))
+ if (check_pipe(data))
return 0;
- if (!file->path)
- file->path = "perf.data";
+ if (!data->path)
+ data->path = "perf.data";
- return open_file(file);
+ return open_file(data);
}
-void perf_data_file__close(struct perf_data_file *file)
+void perf_data__close(struct perf_data *data)
{
- close(file->fd);
+ close(data->fd);
}
-ssize_t perf_data_file__write(struct perf_data_file *file,
+ssize_t perf_data__write(struct perf_data *data,
void *buf, size_t size)
{
- return writen(file->fd, buf, size);
+ return writen(data->fd, buf, size);
}
-int perf_data_file__switch(struct perf_data_file *file,
+int perf_data__switch(struct perf_data *data,
const char *postfix,
size_t pos, bool at_exit)
{
char *new_filepath;
int ret;
- if (check_pipe(file))
+ if (check_pipe(data))
return -EINVAL;
- if (perf_data_file__is_read(file))
+ if (perf_data__is_read(data))
return -EINVAL;
- if (asprintf(&new_filepath, "%s.%s", file->path, postfix) < 0)
+ if (asprintf(&new_filepath, "%s.%s", data->path, postfix) < 0)
return -ENOMEM;
/*
* Only fire a warning, don't return error, continue fill
* original file.
*/
- if (rename(file->path, new_filepath))
- pr_warning("Failed to rename %s to %s\n", file->path, new_filepath);
+ if (rename(data->path, new_filepath))
+ pr_warning("Failed to rename %s to %s\n", data->path, new_filepath);
if (!at_exit) {
- close(file->fd);
- ret = perf_data_file__open(file);
+ close(data->fd);
+ ret = perf_data__open(data);
if (ret < 0)
goto out;
- if (lseek(file->fd, pos, SEEK_SET) == (off_t)-1) {
+ if (lseek(data->fd, pos, SEEK_SET) == (off_t)-1) {
ret = -errno;
pr_debug("Failed to lseek to %zu: %s",
pos, strerror(errno));
goto out;
}
}
- ret = file->fd;
+ ret = data->fd;
out:
free(new_filepath);
return ret;
diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h
index ae510ce16cb1..a1f9d70426b1 100644
--- a/tools/perf/util/data.h
+++ b/tools/perf/util/data.h
@@ -8,7 +8,7 @@ enum perf_data_mode {
PERF_DATA_MODE_READ,
};
-struct perf_data_file {
+struct perf_data {
const char *path;
int fd;
bool is_pipe;
@@ -17,43 +17,43 @@ struct perf_data_file {
enum perf_data_mode mode;
};
-static inline bool perf_data_file__is_read(struct perf_data_file *file)
+static inline bool perf_data__is_read(struct perf_data *data)
{
- return file->mode == PERF_DATA_MODE_READ;
+ return data->mode == PERF_DATA_MODE_READ;
}
-static inline bool perf_data_file__is_write(struct perf_data_file *file)
+static inline bool perf_data__is_write(struct perf_data *data)
{
- return file->mode == PERF_DATA_MODE_WRITE;
+ return data->mode == PERF_DATA_MODE_WRITE;
}
-static inline int perf_data_file__is_pipe(struct perf_data_file *file)
+static inline int perf_data__is_pipe(struct perf_data *data)
{
- return file->is_pipe;
+ return data->is_pipe;
}
-static inline int perf_data_file__fd(struct perf_data_file *file)
+static inline int perf_data__fd(struct perf_data *data)
{
- return file->fd;
+ return data->fd;
}
-static inline unsigned long perf_data_file__size(struct perf_data_file *file)
+static inline unsigned long perf_data__size(struct perf_data *data)
{
- return file->size;
+ return data->size;
}
-int perf_data_file__open(struct perf_data_file *file);
-void perf_data_file__close(struct perf_data_file *file);
-ssize_t perf_data_file__write(struct perf_data_file *file,
+int perf_data__open(struct perf_data *data);
+void perf_data__close(struct perf_data *data);
+ssize_t perf_data__write(struct perf_data *data,
void *buf, size_t size);
/*
* If at_exit is set, only rename current perf.data to
- * perf.data.<postfix>, continue write on original file.
+ * perf.data.<postfix>, continue write on original data.
* Set at_exit when flushing the last output.
*
* Return value is fd of new output.
*/
-int perf_data_file__switch(struct perf_data_file *file,
+int perf_data__switch(struct perf_data *data,
const char *postfix,
size_t pos, bool at_exit);
#endif /* __PERF_DATA_H */
--git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 605bbd5404fb..d7be552b21c8 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1762,7 +1762,7 @@ process_event_desc(struct feat_fd *ff, void *data __maybe_unused)
session = container_of(ff->ph, struct perf_session, header);
- if (session->file->is_pipe) {
+ if (session->data->is_pipe) {
/* Save events for reading later by print_event_desc,
* since they can't be read again in pipe mode. */
ff->events = events;
@@ -1771,7 +1771,7 @@ process_event_desc(struct feat_fd *ff, void *data __maybe_unused)
for (evsel = events; evsel->attr.size; evsel++)
perf_evlist__set_event_name(session->evlist, evsel);
- if (!session->file->is_pipe)
+ if (!session->data->is_pipe)
free_event_desc(events);
return 0;
@@ -2248,7 +2248,7 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full)
{
struct header_print_data hd;
struct perf_header *header = &session->header;
- int fd = perf_data_file__fd(session->file);
+ int fd = perf_data__fd(session->data);
struct stat st;
int ret, bit;
@@ -2264,7 +2264,7 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full)
perf_header__process_sections(header, fd, &hd,
perf_file_section__fprintf_info);
- if (session->file->is_pipe)
+ if (session->data->is_pipe)
return 0;
fprintf(fp, "# missing features: ");
@@ -2757,7 +2757,7 @@ static int perf_header__read_pipe(struct perf_session *session)
struct perf_pipe_file_header f_header;
if (perf_file_header__read_pipe(&f_header, header,
- perf_data_file__fd(session->file),
+ perf_data__fd(session->data),
session->repipe) < 0) {
pr_debug("incompatible file format\n");
return -EINVAL;
@@ -2860,13 +2860,13 @@ static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist,
int perf_session__read_header(struct perf_session *session)
{
- struct perf_data_file *file = session->file;
+ struct perf_data *data = session->data;
struct perf_header *header = &session->header;
struct perf_file_header f_header;
struct perf_file_attr f_attr;
u64 f_id;
int nr_attrs, nr_ids, i, j;
- int fd = perf_data_file__fd(file);
+ int fd = perf_data__fd(data);
session->evlist = perf_evlist__new();
if (session->evlist == NULL)
@@ -2874,7 +2874,7 @@ int perf_session__read_header(struct perf_session *session)
session->evlist->env = &header->env;
session->machines.host.env = &header->env;
- if (perf_data_file__is_pipe(file))
+ if (perf_data__is_pipe(data))
return perf_header__read_pipe(session);
if (perf_file_header__read(&f_header, header, fd) < 0)
@@ -2889,7 +2889,7 @@ int perf_session__read_header(struct perf_session *session)
if (f_header.data.size == 0) {
pr_warning("WARNING: The %s file's data size field is 0 which is unexpected.\n"
"Was the 'perf record' command properly terminated?\n",
- file->path);
+ data->path);
}
nr_attrs = f_header.attrs.size / f_header.attr_size;
@@ -3397,7 +3397,7 @@ int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused,
struct perf_session *session)
{
ssize_t size_read, padding, size = event->tracing_data.size;
- int fd = perf_data_file__fd(session->file);
+ int fd = perf_data__fd(session->data);
off_t offset = lseek(fd, 0, SEEK_CUR);
char buf[BUFSIZ];
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 218ee2bac9a5..5325e65f9711 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -500,7 +500,7 @@ static int intel_bts_process_queue(struct intel_bts_queue *btsq, u64 *timestamp)
}
if (!buffer->data) {
- int fd = perf_data_file__fd(btsq->bts->session->file);
+ int fd = perf_data__fd(btsq->bts->session->data);
buffer->data = auxtrace_buffer__get_data(buffer, fd);
if (!buffer->data) {
@@ -664,10 +664,10 @@ static int intel_bts_process_auxtrace_event(struct perf_session *session,
if (!bts->data_queued) {
struct auxtrace_buffer *buffer;
off_t data_offset;
- int fd = perf_data_file__fd(session->file);
+ int fd = perf_data__fd(session->data);
int err;
- if (perf_data_file__is_pipe(session->file)) {
+ if (perf_data__is_pipe(session->data)) {
data_offset = 0;
} else {
data_offset = lseek(fd, 0, SEEK_CUR);
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index b58f9fd1e2ee..23f9ba676df0 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -271,7 +271,7 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
ptq->buffer = buffer;
if (!buffer->data) {
- int fd = perf_data_file__fd(ptq->pt->session->file);
+ int fd = perf_data__fd(ptq->pt->session->data);
buffer->data = auxtrace_buffer__get_data(buffer, fd);
if (!buffer->data)
@@ -2084,10 +2084,10 @@ static int intel_pt_process_auxtrace_event(struct perf_session *session,
if (!pt->data_queued) {
struct auxtrace_buffer *buffer;
off_t data_offset;
- int fd = perf_data_file__fd(session->file);
+ int fd = perf_data__fd(session->data);
int err;
- if (perf_data_file__is_pipe(session->file)) {
+ if (perf_data__is_pipe(session->data)) {
data_offset = 0;
} else {
data_offset = lseek(fd, 0, SEEK_CUR);
diff --git a/tools/perf/util/jit.h b/tools/perf/util/jit.h
index 3f42ee4d2a0b..961e7a8a0e17 100644
--- a/tools/perf/util/jit.h
+++ b/tools/perf/util/jit.h
@@ -3,7 +3,7 @@
#include <data.h>
-int jit_process(struct perf_session *session, struct perf_data_file *output,
+int jit_process(struct perf_session *session, struct perf_data *output,
struct machine *machine, char *filename, pid_t pid, u64 *nbytes);
int jit_inject_record(const char *filename);
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index 9084930e1757..e7645098a323 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -29,7 +29,7 @@
#include "sane_ctype.h"
struct jit_buf_desc {
- struct perf_data_file *output;
+ struct perf_data *output;
struct perf_session *session;
struct machine *machine;
union jr_entry *entry;
@@ -60,8 +60,8 @@ struct debug_line_info {
struct jit_tool {
struct perf_tool tool;
- struct perf_data_file output;
- struct perf_data_file input;
+ struct perf_data output;
+ struct perf_data input;
u64 bytes_written;
};
@@ -356,7 +356,7 @@ jit_inject_event(struct jit_buf_desc *jd, union perf_event *event)
{
ssize_t size;
- size = perf_data_file__write(jd->output, event, event->header.size);
+ size = perf_data__write(jd->output, event, event->header.size);
if (size < 0)
return -1;
@@ -751,7 +751,7 @@ jit_detect(char *mmap_name, pid_t pid)
int
jit_process(struct perf_session *session,
- struct perf_data_file *output,
+ struct perf_data *output,
struct machine *machine,
char *filename,
pid_t pid,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index ceac0848469d..9d135b41a205 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -32,14 +32,14 @@ static int perf_session__deliver_event(struct perf_session *session,
static int perf_session__open(struct perf_session *session)
{
- struct perf_data_file *file = session->file;
+ struct perf_data *data = session->data;
if (perf_session__read_header(session) < 0) {
pr_err("incompatible file format (rerun with -v to learn more)\n");
return -1;
}
- if (perf_data_file__is_pipe(file))
+ if (perf_data__is_pipe(data))
return 0;
if (perf_header__has_feat(&session->header, HEADER_STAT))
@@ -120,7 +120,7 @@ static int ordered_events__deliver_event(struct ordered_events *oe,
session->tool, event->file_offset);
}
-struct perf_session *perf_session__new(struct perf_data_file *file,
+struct perf_session *perf_session__new(struct perf_data *data,
bool repipe, struct perf_tool *tool)
{
struct perf_session *session = zalloc(sizeof(*session));
@@ -134,13 +134,13 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
machines__init(&session->machines);
ordered_events__init(&session->ordered_events, ordered_events__deliver_event);
- if (file) {
- if (perf_data_file__open(file))
+ if (data) {
+ if (perf_data__open(data))
goto out_delete;
- session->file = file;
+ session->data = data;
- if (perf_data_file__is_read(file)) {
+ if (perf_data__is_read(data)) {
if (perf_session__open(session) < 0)
goto out_close;
@@ -148,7 +148,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
* set session attributes that are present in perf.data
* but not in pipe-mode.
*/
- if (!file->is_pipe) {
+ if (!data->is_pipe) {
perf_session__set_id_hdr_size(session);
perf_session__set_comm_exec(session);
}
@@ -157,7 +157,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
session->machines.host.env = &perf_env;
}
- if (!file || perf_data_file__is_write(file)) {
+ if (!data || perf_data__is_write(data)) {
/*
* In O_RDONLY mode this will be performed when reading the
* kernel MMAP event, in perf_event__process_mmap().
@@ -170,7 +170,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
* In pipe-mode, evlist is empty until PERF_RECORD_HEADER_ATTR is
* processed, so perf_evlist__sample_id_all is not meaningful here.
*/
- if ((!file || !file->is_pipe) && tool && tool->ordering_requires_timestamps &&
+ if ((!data || !data->is_pipe) && tool && tool->ordering_requires_timestamps &&
tool->ordered_events && !perf_evlist__sample_id_all(session->evlist)) {
dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
tool->ordered_events = false;
@@ -179,7 +179,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
return session;
out_close:
- perf_data_file__close(file);
+ perf_data__close(data);
out_delete:
perf_session__delete(session);
out:
@@ -201,8 +201,8 @@ void perf_session__delete(struct perf_session *session)
perf_session__delete_threads(session);
perf_env__exit(&session->header.env);
machines__exit(&session->machines);
- if (session->file)
- perf_data_file__close(session->file);
+ if (session->data)
+ perf_data__close(session->data);
free(session);
}
@@ -290,8 +290,8 @@ static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
__maybe_unused)
{
dump_printf(": unhandled!\n");
- if (perf_data_file__is_pipe(session->file))
- skipn(perf_data_file__fd(session->file), event->auxtrace.size);
+ if (perf_data__is_pipe(session->data))
+ skipn(perf_data__fd(session->data), event->auxtrace.size);
return event->auxtrace.size;
}
@@ -1347,7 +1347,7 @@ static s64 perf_session__process_user_event(struct perf_session *session,
{
struct ordered_events *oe = &session->ordered_events;
struct perf_tool *tool = session->tool;
- int fd = perf_data_file__fd(session->file);
+ int fd = perf_data__fd(session->data);
int err;
dump_event(session->evlist, event, file_offset, NULL);
@@ -1447,10 +1447,10 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset,
goto out_parse_sample;
}
- if (perf_data_file__is_pipe(session->file))
+ if (perf_data__is_pipe(session->data))
return -1;
- fd = perf_data_file__fd(session->file);
+ fd = perf_data__fd(session->data);
hdr_sz = sizeof(struct perf_event_header);
if (buf_sz < hdr_sz)
@@ -1685,7 +1685,7 @@ static int __perf_session__process_pipe_events(struct perf_session *session)
{
struct ordered_events *oe = &session->ordered_events;
struct perf_tool *tool = session->tool;
- int fd = perf_data_file__fd(session->file);
+ int fd = perf_data__fd(session->data);
union perf_event *event;
uint32_t size, cur_size = 0;
void *buf = NULL;
@@ -1826,7 +1826,7 @@ static int __perf_session__process_events(struct perf_session *session,
{
struct ordered_events *oe = &session->ordered_events;
struct perf_tool *tool = session->tool;
- int fd = perf_data_file__fd(session->file);
+ int fd = perf_data__fd(session->data);
u64 head, page_offset, file_offset, file_pos, size;
int err, mmap_prot, mmap_flags, map_idx = 0;
size_t mmap_size;
@@ -1943,13 +1943,13 @@ static int __perf_session__process_events(struct perf_session *session,
int perf_session__process_events(struct perf_session *session)
{
- u64 size = perf_data_file__size(session->file);
+ u64 size = perf_data__size(session->data);
int err;
if (perf_session__register_idle_thread(session) < 0)
return -ENOMEM;
- if (!perf_data_file__is_pipe(session->file))
+ if (!perf_data__is_pipe(session->data))
err = __perf_session__process_events(session,
session->header.data_offset,
session->header.data_size, size);
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 47b5e7dbcb18..cc1c5ea53c39 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -32,13 +32,13 @@ struct perf_session {
void *one_mmap_addr;
u64 one_mmap_offset;
struct ordered_events ordered_events;
- struct perf_data_file *file;
+ struct perf_data *data;
struct perf_tool *tool;
};
struct perf_tool;
-struct perf_session *perf_session__new(struct perf_data_file *file,
+struct perf_session *perf_session__new(struct perf_data *data,
bool repipe, struct perf_tool *tool);
void perf_session__delete(struct perf_session *session);
--
2.13.6
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH 4/9] perf tools: Add struct perf_data_file
2017-10-13 8:37 [PATCH 0/9] perf tools: Assorted fixes Jiri Olsa
` (2 preceding siblings ...)
2017-10-13 8:37 ` [PATCH 3/9] perf tools: Rename struct perf_data_file to perf_data Jiri Olsa
@ 2017-10-13 8:37 ` Jiri Olsa
2017-10-13 8:37 ` [PATCH 5/9] perf tools: Add perf_data_file__write function Jiri Olsa
` (4 subsequent siblings)
8 siblings, 0 replies; 16+ messages in thread
From: Jiri Olsa @ 2017-10-13 8:37 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: lkml, Ingo Molnar, Namhyung Kim, David Ahern, Peter Zijlstra,
Andi Kleen, Jin, Yao, Wangnan (F),
Du, Changbin
Adding struct perf_data_file represent single file
within perf_data struct.
Link: http://lkml.kernel.org/n/tip-c3f9p4xzykr845ktqcek6p4t@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
tools/perf/builtin-annotate.c | 4 ++--
tools/perf/builtin-buildid-cache.c | 4 ++--
tools/perf/builtin-buildid-list.c | 8 ++++---
tools/perf/builtin-c2c.c | 4 ++--
tools/perf/builtin-diff.c | 12 +++++-----
tools/perf/builtin-evlist.c | 8 ++++---
tools/perf/builtin-inject.c | 12 ++++++----
tools/perf/builtin-kmem.c | 2 +-
tools/perf/builtin-kvm.c | 8 ++++---
tools/perf/builtin-lock.c | 8 ++++---
tools/perf/builtin-mem.c | 8 ++++---
tools/perf/builtin-record.c | 6 ++---
tools/perf/builtin-report.c | 6 ++---
tools/perf/builtin-sched.c | 16 ++++++++-----
tools/perf/builtin-script.c | 12 ++++++----
tools/perf/builtin-stat.c | 6 ++---
tools/perf/builtin-timechart.c | 8 ++++---
tools/perf/builtin-trace.c | 8 ++++---
tools/perf/tests/topology.c | 14 +++++++----
tools/perf/util/data-convert-bt.c | 8 +++----
tools/perf/util/data.c | 48 +++++++++++++++++++-------------------
tools/perf/util/data.h | 10 +++++---
| 2 +-
23 files changed, 126 insertions(+), 96 deletions(-)
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 2d06be81a109..2d5c87578f83 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -356,7 +356,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
}
if (total_nr_samples == 0) {
- ui__error("The %s file has no samples!\n", session->data->path);
+ ui__error("The %s file has no samples!\n", session->data->file.path);
goto out;
}
@@ -482,7 +482,7 @@ int cmd_annotate(int argc, const char **argv)
if (quiet)
perf_quiet_option();
- data.path = input_name;
+ data.file.path = input_name;
annotate.session = perf_session__new(&data, false, &annotate.tool);
if (annotate.session == NULL)
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 9fceae47a02e..cb2453b29365 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -352,8 +352,8 @@ int cmd_buildid_cache(int argc, const char **argv)
nsi = nsinfo__new(ns_id);
if (missing_filename) {
- data.path = missing_filename;
- data.force = force;
+ data.file.path = missing_filename;
+ data.force = force;
session = perf_session__new(&data, false, NULL);
if (session == NULL)
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index 72bdc0eba990..00099a830b0d 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -51,9 +51,11 @@ static int perf_session__list_build_ids(bool force, bool with_hits)
{
struct perf_session *session;
struct perf_data data = {
- .path = input_name,
- .mode = PERF_DATA_MODE_READ,
- .force = force,
+ .file = {
+ .path = input_name,
+ },
+ .mode = PERF_DATA_MODE_READ,
+ .force = force,
};
symbol__elf_init();
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 87a52d09da29..9590fdcc6484 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2572,8 +2572,8 @@ static int perf_c2c__report(int argc, const char **argv)
if (!input_name || !strlen(input_name))
input_name = "perf.data";
- data.path = input_name;
- data.force = symbol_conf.force;
+ data.file.path = input_name;
+ data.force = symbol_conf.force;
err = setup_display(display);
if (err)
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 5292e3d13cec..67570e6417e5 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -707,7 +707,7 @@ static void data__fprintf(void)
data__for_each_file(i, d)
fprintf(stdout, "# [%d] %s %s\n",
- d->idx, d->data.path,
+ d->idx, d->data.file.path,
!d->idx ? "(Baseline)" : "");
fprintf(stdout, "#\n");
@@ -778,14 +778,14 @@ static int __cmd_diff(void)
data__for_each_file(i, d) {
d->session = perf_session__new(&d->data, false, &tool);
if (!d->session) {
- pr_err("Failed to open %s\n", d->data.path);
+ pr_err("Failed to open %s\n", d->data.file.path);
ret = -1;
goto out_delete;
}
ret = perf_session__process_events(d->session);
if (ret) {
- pr_err("Failed to process %s\n", d->data.path);
+ pr_err("Failed to process %s\n", d->data.file.path);
goto out_delete;
}
@@ -1288,9 +1288,9 @@ static int data_init(int argc, const char **argv)
data__for_each_file(i, d) {
struct perf_data *data = &d->data;
- data->path = use_default ? defaults[i] : argv[i];
- data->mode = PERF_DATA_MODE_READ,
- data->force = force,
+ data->file.path = use_default ? defaults[i] : argv[i];
+ data->mode = PERF_DATA_MODE_READ,
+ data->force = force,
d->idx = i;
}
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index cd79c26e16a4..93b85dc857b6 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -22,9 +22,11 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details
struct perf_session *session;
struct perf_evsel *pos;
struct perf_data data = {
- .path = file_name,
- .mode = PERF_DATA_MODE_READ,
- .force = details->force,
+ .file = {
+ .path = file_name,
+ },
+ .mode = PERF_DATA_MODE_READ,
+ .force = details->force,
};
bool has_tracepoint = false;
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index ac7486f6c46f..91e65093d3c2 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -145,7 +145,7 @@ static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
if (!inject->output.is_pipe) {
off_t offset;
- offset = lseek(inject->output.fd, 0, SEEK_CUR);
+ offset = lseek(inject->output.file.fd, 0, SEEK_CUR);
if (offset == -1)
return -errno;
ret = auxtrace_index__auxtrace_event(&session->auxtrace_index,
@@ -775,8 +775,10 @@ int cmd_inject(int argc, const char **argv)
.input_name = "-",
.samples = LIST_HEAD_INIT(inject.samples),
.output = {
- .path = "-",
- .mode = PERF_DATA_MODE_WRITE,
+ .file = {
+ .path = "-",
+ },
+ .mode = PERF_DATA_MODE_WRITE,
},
};
struct perf_data data = {
@@ -789,7 +791,7 @@ int cmd_inject(int argc, const char **argv)
"Inject build-ids into the output stream"),
OPT_STRING('i', "input", &inject.input_name, "file",
"input file name"),
- OPT_STRING('o', "output", &inject.output.path, "file",
+ OPT_STRING('o', "output", &inject.output.file.path, "file",
"output file name"),
OPT_BOOLEAN('s', "sched-stat", &inject.sched_stat,
"Merge sched-stat and sched-switch for getting events "
@@ -836,7 +838,7 @@ int cmd_inject(int argc, const char **argv)
inject.tool.ordered_events = inject.sched_stat;
- data.path = inject.input_name;
+ data.file.path = inject.input_name;
inject.session = perf_session__new(&data, true, &inject.tool);
if (inject.session == NULL)
return -1;
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index e2314bba2a3f..1c2fc3f29434 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -1949,7 +1949,7 @@ int cmd_kmem(int argc, const char **argv)
return __cmd_record(argc, argv);
}
- data.path = input_name;
+ data.file.path = input_name;
kmem_session = session = perf_session__new(&data, false, &perf_kmem);
if (session == NULL)
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 4301fc34f23c..0af4c092b471 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1068,9 +1068,11 @@ static int read_events(struct perf_kvm_stat *kvm)
.ordered_events = true,
};
struct perf_data file = {
- .path = kvm->file_name,
- .mode = PERF_DATA_MODE_READ,
- .force = kvm->force,
+ .file = {
+ .path = kvm->file_name,
+ },
+ .mode = PERF_DATA_MODE_READ,
+ .force = kvm->force,
};
kvm->tool = eops;
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 2e281f7b0fca..81af29400b64 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -865,9 +865,11 @@ static int __cmd_report(bool display_info)
.ordered_events = true,
};
struct perf_data data = {
- .path = input_name,
- .mode = PERF_DATA_MODE_READ,
- .force = force,
+ .file = {
+ .path = input_name,
+ },
+ .mode = PERF_DATA_MODE_READ,
+ .force = force,
};
session = perf_session__new(&data, false, &eops);
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 5a4a6f8e614d..f09fd1a1b813 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -237,9 +237,11 @@ static int process_sample_event(struct perf_tool *tool,
static int report_raw_events(struct perf_mem *mem)
{
struct perf_data data = {
- .path = input_name,
- .mode = PERF_DATA_MODE_READ,
- .force = mem->force,
+ .file = {
+ .path = input_name,
+ },
+ .mode = PERF_DATA_MODE_READ,
+ .force = mem->force,
};
int ret;
struct perf_session *session = perf_session__new(&data, false,
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0ab7dd0e4f2b..f4d9fc54b382 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -618,7 +618,7 @@ record__switch_output(struct record *rec, bool at_exit)
if (!quiet)
fprintf(stderr, "[ perf record: Dump %s.%s ]\n",
- data->path, timestamp);
+ data->file.path, timestamp);
/* Output tracking events */
if (!at_exit) {
@@ -1118,7 +1118,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
fprintf(stderr, "[ perf record: Captured and wrote %.3f MB %s%s%s ]\n",
perf_data__size(data) / 1024.0 / 1024.0,
- data->path, postfix, samples);
+ data->file.path, postfix, samples);
}
out_delete_session:
@@ -1482,7 +1482,7 @@ static struct option __record_options[] = {
OPT_STRING('C', "cpu", &record.opts.target.cpu_list, "cpu",
"list of cpus to monitor"),
OPT_U64('c', "count", &record.opts.user_interval, "event period to sample"),
- OPT_STRING('o', "output", &record.data.path, "file",
+ OPT_STRING('o', "output", &record.data.file.path, "file",
"output file name"),
OPT_BOOLEAN_SET('i', "no-inherit", &record.opts.no_inherit,
&record.opts.no_inherit_set,
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 0dc323772b5e..3c2d9d4932f3 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -637,7 +637,7 @@ static int __cmd_report(struct report *rep)
rep->nr_entries += evsel__hists(pos)->nr_entries;
if (rep->nr_entries == 0) {
- ui__error("The %s file has no samples!\n", data->path);
+ ui__error("The %s file has no samples!\n", data->file.path);
return 0;
}
@@ -940,8 +940,8 @@ int cmd_report(int argc, const char **argv)
input_name = "perf.data";
}
- data.path = input_name;
- data.force = symbol_conf.force;
+ data.file.path = input_name;
+ data.force = symbol_conf.force;
repeat:
session = perf_session__new(&data, false, &report.tool);
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index cb5410511f69..47e54348b5ed 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1701,9 +1701,11 @@ static int perf_sched__read_events(struct perf_sched *sched)
};
struct perf_session *session;
struct perf_data data = {
- .path = input_name,
- .mode = PERF_DATA_MODE_READ,
- .force = sched->force,
+ .file = {
+ .path = input_name,
+ },
+ .mode = PERF_DATA_MODE_READ,
+ .force = sched->force,
};
int rc = -1;
@@ -2903,9 +2905,11 @@ static int perf_sched__timehist(struct perf_sched *sched)
{ "sched:sched_migrate_task", timehist_migrate_task_event, },
};
struct perf_data data = {
- .path = input_name,
- .mode = PERF_DATA_MODE_READ,
- .force = sched->force,
+ .file = {
+ .path = input_name,
+ },
+ .mode = PERF_DATA_MODE_READ,
+ .force = sched->force,
};
struct perf_session *session;
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 8477c41dbbe0..232a4c3771cf 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2447,8 +2447,10 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
DIR *scripts_dir, *lang_dir;
struct perf_session *session;
struct perf_data data = {
- .path = input_name,
- .mode = PERF_DATA_MODE_READ,
+ .file = {
+ .path = input_name,
+ },
+ .mode = PERF_DATA_MODE_READ,
};
char *temp;
int i = 0;
@@ -2836,8 +2838,8 @@ int cmd_script(int argc, const char **argv)
argc = parse_options_subcommand(argc, argv, options, script_subcommands, script_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
- data.path = input_name;
- data.force = symbol_conf.force;
+ data.file.path = input_name;
+ data.force = symbol_conf.force;
if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) {
rec_script_path = get_script_path(argv[1], RECORD_SUFFIX);
@@ -3059,7 +3061,7 @@ int cmd_script(int argc, const char **argv)
goto out_delete;
}
- input = open(data.path, O_RDONLY); /* input_name */
+ input = open(data.file.path, O_RDONLY); /* input_name */
if (input < 0) {
err = -errno;
perror("failed to open file");
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 6a1ef0941fd2..9f2f07c0237d 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -2412,7 +2412,7 @@ static int __cmd_record(int argc, const char **argv)
PARSE_OPT_STOP_AT_NON_OPTION);
if (output_name)
- data->path = output_name;
+ data->file.path = output_name;
if (run_count != 1 || forever) {
pr_err("Cannot use -r option with perf stat record.\n");
@@ -2585,8 +2585,8 @@ static int __cmd_report(int argc, const char **argv)
input_name = "perf.data";
}
- perf_stat.data.path = input_name;
- perf_stat.data.mode = PERF_DATA_MODE_READ;
+ perf_stat.data.file.path = input_name;
+ perf_stat.data.mode = PERF_DATA_MODE_READ;
session = perf_session__new(&perf_stat.data, false, &perf_stat.tool);
if (session == NULL)
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 0f79ea5e2f0f..813698a9b8c7 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -1602,9 +1602,11 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name)
{ "syscalls:sys_exit_select", process_exit_poll },
};
struct perf_data data = {
- .path = input_name,
- .mode = PERF_DATA_MODE_READ,
- .force = tchart->force,
+ .file = {
+ .path = input_name,
+ },
+ .mode = PERF_DATA_MODE_READ,
+ .force = tchart->force,
};
struct perf_session *session = perf_session__new(&data, false,
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 94beb372d097..f6478c46a759 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2530,9 +2530,11 @@ static int trace__replay(struct trace *trace)
{ "probe:vfs_getname", trace__vfs_getname, },
};
struct perf_data data = {
- .path = input_name,
- .mode = PERF_DATA_MODE_READ,
- .force = trace->force,
+ .file = {
+ .path = input_name,
+ },
+ .mode = PERF_DATA_MODE_READ,
+ .force = trace->force,
};
struct perf_session *session;
struct perf_evsel *evsel;
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index 7536782e8495..9bbfed51f1d6 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -30,8 +30,10 @@ static int session_write_header(char *path)
{
struct perf_session *session;
struct perf_data data = {
- .path = path,
- .mode = PERF_DATA_MODE_WRITE,
+ .file = {
+ .path = path,
+ },
+ .mode = PERF_DATA_MODE_WRITE,
};
session = perf_session__new(&data, false, NULL);
@@ -46,7 +48,7 @@ static int session_write_header(char *path)
session->header.data_size += DATA_SIZE;
TEST_ASSERT_VAL("failed to write header",
- !perf_session__write_header(session, session->evlist, data.fd, true));
+ !perf_session__write_header(session, session->evlist, data.file.fd, true));
perf_session__delete(session);
@@ -57,8 +59,10 @@ static int check_cpu_topology(char *path, struct cpu_map *map)
{
struct perf_session *session;
struct perf_data data = {
- .path = path,
- .mode = PERF_DATA_MODE_READ,
+ .file = {
+ .path = path,
+ },
+ .mode = PERF_DATA_MODE_READ,
};
int i;
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 9fdae383a58c..5744c12641a5 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -1578,9 +1578,9 @@ int bt_convert__perf2ctf(const char *input, const char *path,
{
struct perf_session *session;
struct perf_data data = {
- .path = input,
- .mode = PERF_DATA_MODE_READ,
- .force = opts->force,
+ .file.path = input,
+ .mode = PERF_DATA_MODE_READ,
+ .force = opts->force,
};
struct convert c = {
.tool = {
@@ -1650,7 +1650,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
fprintf(stderr,
"[ perf data convert: Converted '%s' into CTF data '%s' ]\n",
- data.path, path);
+ data.file.path, path);
fprintf(stderr,
"[ perf data convert: Converted and wrote %.3f MB (%" PRIu64 " samples",
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index a6eea3df4c10..07ef56a4123c 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -28,16 +28,16 @@ static bool check_pipe(struct perf_data *data)
int fd = perf_data__is_read(data) ?
STDIN_FILENO : STDOUT_FILENO;
- if (!data->path) {
+ if (!data->file.path) {
if (!fstat(fd, &st) && S_ISFIFO(st.st_mode))
is_pipe = true;
} else {
- if (!strcmp(data->path, "-"))
+ if (!strcmp(data->file.path, "-"))
is_pipe = true;
}
if (is_pipe)
- data->fd = fd;
+ data->file.fd = fd;
return data->is_pipe = is_pipe;
}
@@ -46,13 +46,13 @@ static int check_backup(struct perf_data *data)
{
struct stat st;
- if (!stat(data->path, &st) && st.st_size) {
+ if (!stat(data->file.path, &st) && st.st_size) {
/* TODO check errors properly */
char oldname[PATH_MAX];
snprintf(oldname, sizeof(oldname), "%s.old",
- data->path);
+ data->file.path);
unlink(oldname);
- rename(data->path, oldname);
+ rename(data->file.path, oldname);
}
return 0;
@@ -64,13 +64,13 @@ static int open_file_read(struct perf_data *data)
int fd;
char sbuf[STRERR_BUFSIZE];
- fd = open(data->path, O_RDONLY);
+ fd = open(data->file.path, O_RDONLY);
if (fd < 0) {
int err = errno;
- pr_err("failed to open %s: %s", data->path,
+ pr_err("failed to open %s: %s", data->file.path,
str_error_r(err, sbuf, sizeof(sbuf)));
- if (err == ENOENT && !strcmp(data->path, "perf.data"))
+ if (err == ENOENT && !strcmp(data->file.path, "perf.data"))
pr_err(" (try 'perf record' first)");
pr_err("\n");
return -err;
@@ -81,13 +81,13 @@ static int open_file_read(struct perf_data *data)
if (!data->force && st.st_uid && (st.st_uid != geteuid())) {
pr_err("File %s not owned by current user or root (use -f to override)\n",
- data->path);
+ data->file.path);
goto out_close;
}
if (!st.st_size) {
pr_info("zero-sized data (%s), nothing to do!\n",
- data->path);
+ data->file.path);
goto out_close;
}
@@ -107,11 +107,11 @@ static int open_file_write(struct perf_data *data)
if (check_backup(data))
return -1;
- fd = open(data->path, O_CREAT|O_RDWR|O_TRUNC|O_CLOEXEC,
+ fd = open(data->file.path, O_CREAT|O_RDWR|O_TRUNC|O_CLOEXEC,
S_IRUSR|S_IWUSR);
if (fd < 0)
- pr_err("failed to open %s : %s\n", data->path,
+ pr_err("failed to open %s : %s\n", data->file.path,
str_error_r(errno, sbuf, sizeof(sbuf)));
return fd;
@@ -124,7 +124,7 @@ static int open_file(struct perf_data *data)
fd = perf_data__is_read(data) ?
open_file_read(data) : open_file_write(data);
- data->fd = fd;
+ data->file.fd = fd;
return fd < 0 ? -1 : 0;
}
@@ -133,21 +133,21 @@ int perf_data__open(struct perf_data *data)
if (check_pipe(data))
return 0;
- if (!data->path)
- data->path = "perf.data";
+ if (!data->file.path)
+ data->file.path = "perf.data";
return open_file(data);
}
void perf_data__close(struct perf_data *data)
{
- close(data->fd);
+ close(data->file.fd);
}
ssize_t perf_data__write(struct perf_data *data,
void *buf, size_t size)
{
- return writen(data->fd, buf, size);
+ return writen(data->file.fd, buf, size);
}
int perf_data__switch(struct perf_data *data,
@@ -162,30 +162,30 @@ int perf_data__switch(struct perf_data *data,
if (perf_data__is_read(data))
return -EINVAL;
- if (asprintf(&new_filepath, "%s.%s", data->path, postfix) < 0)
+ if (asprintf(&new_filepath, "%s.%s", data->file.path, postfix) < 0)
return -ENOMEM;
/*
* Only fire a warning, don't return error, continue fill
* original file.
*/
- if (rename(data->path, new_filepath))
- pr_warning("Failed to rename %s to %s\n", data->path, new_filepath);
+ if (rename(data->file.path, new_filepath))
+ pr_warning("Failed to rename %s to %s\n", data->file.path, new_filepath);
if (!at_exit) {
- close(data->fd);
+ close(data->file.fd);
ret = perf_data__open(data);
if (ret < 0)
goto out;
- if (lseek(data->fd, pos, SEEK_SET) == (off_t)-1) {
+ if (lseek(data->file.fd, pos, SEEK_SET) == (off_t)-1) {
ret = -errno;
pr_debug("Failed to lseek to %zu: %s",
pos, strerror(errno));
goto out;
}
}
- ret = data->fd;
+ ret = data->file.fd;
out:
free(new_filepath);
return ret;
diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h
index a1f9d70426b1..1797bed3aa4b 100644
--- a/tools/perf/util/data.h
+++ b/tools/perf/util/data.h
@@ -8,9 +8,13 @@ enum perf_data_mode {
PERF_DATA_MODE_READ,
};
+struct perf_data_file {
+ const char *path;
+ int fd;
+};
+
struct perf_data {
- const char *path;
- int fd;
+ struct perf_data_file file;
bool is_pipe;
bool force;
unsigned long size;
@@ -34,7 +38,7 @@ static inline int perf_data__is_pipe(struct perf_data *data)
static inline int perf_data__fd(struct perf_data *data)
{
- return data->fd;
+ return data->file.fd;
}
static inline unsigned long perf_data__size(struct perf_data *data)
--git a/tools/perf/util/header.c b/tools/perf/util/header.c
index d7be552b21c8..6e59dcca9df2 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2889,7 +2889,7 @@ int perf_session__read_header(struct perf_session *session)
if (f_header.data.size == 0) {
pr_warning("WARNING: The %s file's data size field is 0 which is unexpected.\n"
"Was the 'perf record' command properly terminated?\n",
- data->path);
+ data->file.path);
}
nr_attrs = f_header.attrs.size / f_header.attr_size;
--
2.13.6
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH 5/9] perf tools: Add perf_data_file__write function
2017-10-13 8:37 [PATCH 0/9] perf tools: Assorted fixes Jiri Olsa
` (3 preceding siblings ...)
2017-10-13 8:37 ` [PATCH 4/9] perf tools: Add struct perf_data_file Jiri Olsa
@ 2017-10-13 8:37 ` Jiri Olsa
2017-10-13 8:37 ` [PATCH 6/9] perf stat: Move the shadow stats scale computation in perf_stat__update_shadow_stats Jiri Olsa
` (3 subsequent siblings)
8 siblings, 0 replies; 16+ messages in thread
From: Jiri Olsa @ 2017-10-13 8:37 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: lkml, Ingo Molnar, Namhyung Kim, David Ahern, Peter Zijlstra,
Andi Kleen, Jin, Yao, Wangnan (F),
Du, Changbin
Adding perf_data_file__write function to provide
single file write operation.
Link: http://lkml.kernel.org/n/tip-c3f9p4xzykr845ktqcek6p4t@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
tools/perf/util/data.c | 8 +++++++-
tools/perf/util/data.h | 2 ++
2 files changed, 9 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index 07ef56a4123c..f80a23d031d6 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -144,10 +144,16 @@ void perf_data__close(struct perf_data *data)
close(data->file.fd);
}
+ssize_t perf_data_file__write(struct perf_data_file *file,
+ void *buf, size_t size)
+{
+ return writen(file->fd, buf, size);
+}
+
ssize_t perf_data__write(struct perf_data *data,
void *buf, size_t size)
{
- return writen(data->file.fd, buf, size);
+ return perf_data_file__write(&data->file, buf, size);
}
int perf_data__switch(struct perf_data *data,
diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h
index 1797bed3aa4b..000c43bbb7ac 100644
--- a/tools/perf/util/data.h
+++ b/tools/perf/util/data.h
@@ -50,6 +50,8 @@ int perf_data__open(struct perf_data *data);
void perf_data__close(struct perf_data *data);
ssize_t perf_data__write(struct perf_data *data,
void *buf, size_t size);
+ssize_t perf_data_file__write(struct perf_data_file *file,
+ void *buf, size_t size);
/*
* If at_exit is set, only rename current perf.data to
* perf.data.<postfix>, continue write on original data.
--
2.13.6
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH 6/9] perf stat: Move the shadow stats scale computation in perf_stat__update_shadow_stats
2017-10-13 8:37 [PATCH 0/9] perf tools: Assorted fixes Jiri Olsa
` (4 preceding siblings ...)
2017-10-13 8:37 ` [PATCH 5/9] perf tools: Add perf_data_file__write function Jiri Olsa
@ 2017-10-13 8:37 ` Jiri Olsa
2017-10-13 8:37 ` [PATCH 7/9] perf stat: Make --per-thread update shadow stats to show metrics Jiri Olsa
` (2 subsequent siblings)
8 siblings, 0 replies; 16+ messages in thread
From: Jiri Olsa @ 2017-10-13 8:37 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: lkml, Ingo Molnar, Namhyung Kim, David Ahern, Peter Zijlstra,
Andi Kleen, Jin, Yao, Wangnan (F),
Du, Changbin
Moving the shadow stats scale computation under
perf_stat__update_shadow_stats function, so it's
centralized and we don't forget to do it. It also
saves few lines of code.
Link: http://lkml.kernel.org/n/tip-htg7mmyxv6pcrf57qyo6msid@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
tools/perf/builtin-stat.c | 3 +--
tools/perf/util/stat-shadow.c | 48 ++++++++++++++++++++++---------------------
tools/perf/util/stat.c | 6 ++----
tools/perf/util/stat.h | 2 +-
4 files changed, 29 insertions(+), 30 deletions(-)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 9f2f07c0237d..4e109e6ba341 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1267,8 +1267,7 @@ static void aggr_update_shadow(void)
continue;
val += perf_counts(counter->counts, cpu, 0)->val;
}
- val = val * counter->scale;
- perf_stat__update_shadow_stats(counter, &val,
+ perf_stat__update_shadow_stats(counter, val,
first_shadow_cpu(counter, id));
}
}
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index a2c12d1ef32a..51ad03a799ec 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -178,58 +178,60 @@ void perf_stat__reset_shadow_stats(void)
* more semantic information such as miss/hit ratios,
* instruction rates, etc:
*/
-void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
+void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count,
int cpu)
{
int ctx = evsel_context(counter);
+ count *= counter->scale;
+
if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK) ||
perf_evsel__match(counter, SOFTWARE, SW_CPU_CLOCK))
- update_stats(&runtime_nsecs_stats[cpu], count[0]);
+ update_stats(&runtime_nsecs_stats[cpu], count);
else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
- update_stats(&runtime_cycles_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_cycles_stats[ctx][cpu], count);
else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
- update_stats(&runtime_cycles_in_tx_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_cycles_in_tx_stats[ctx][cpu], count);
else if (perf_stat_evsel__is(counter, TRANSACTION_START))
- update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_transaction_stats[ctx][cpu], count);
else if (perf_stat_evsel__is(counter, ELISION_START))
- update_stats(&runtime_elision_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_elision_stats[ctx][cpu], count);
else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS))
- update_stats(&runtime_topdown_total_slots[ctx][cpu], count[0]);
+ update_stats(&runtime_topdown_total_slots[ctx][cpu], count);
else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED))
- update_stats(&runtime_topdown_slots_issued[ctx][cpu], count[0]);
+ update_stats(&runtime_topdown_slots_issued[ctx][cpu], count);
else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED))
- update_stats(&runtime_topdown_slots_retired[ctx][cpu], count[0]);
+ update_stats(&runtime_topdown_slots_retired[ctx][cpu], count);
else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES))
- update_stats(&runtime_topdown_fetch_bubbles[ctx][cpu],count[0]);
+ update_stats(&runtime_topdown_fetch_bubbles[ctx][cpu], count);
else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES))
- update_stats(&runtime_topdown_recovery_bubbles[ctx][cpu], count[0]);
+ update_stats(&runtime_topdown_recovery_bubbles[ctx][cpu], count);
else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
- update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count);
else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
- update_stats(&runtime_stalled_cycles_back_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_stalled_cycles_back_stats[ctx][cpu], count);
else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
- update_stats(&runtime_branches_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_branches_stats[ctx][cpu], count);
else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
- update_stats(&runtime_cacherefs_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_cacherefs_stats[ctx][cpu], count);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
- update_stats(&runtime_l1_dcache_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_l1_dcache_stats[ctx][cpu], count);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
- update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_ll_cache_stats[ctx][cpu], count);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
- update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_ll_cache_stats[ctx][cpu], count);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
- update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
- update_stats(&runtime_itlb_cache_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_itlb_cache_stats[ctx][cpu], count);
else if (perf_stat_evsel__is(counter, SMI_NUM))
- update_stats(&runtime_smi_num_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_smi_num_stats[ctx][cpu], count);
else if (perf_stat_evsel__is(counter, APERF))
- update_stats(&runtime_aperf_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_aperf_stats[ctx][cpu], count);
if (counter->collect_stat) {
struct saved_value *v = saved_value_lookup(counter, cpu, true);
- update_stats(&v->stats, count[0]);
+ update_stats(&v->stats, count);
}
}
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 35e9848734d6..7a3849851c20 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -277,7 +277,7 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel
perf_evsel__compute_deltas(evsel, cpu, thread, count);
perf_counts_values__scale(count, config->scale, NULL);
if (config->aggr_mode == AGGR_NONE)
- perf_stat__update_shadow_stats(evsel, count->values, cpu);
+ perf_stat__update_shadow_stats(evsel, count->val, cpu);
break;
case AGGR_GLOBAL:
aggr->val += count->val;
@@ -320,7 +320,6 @@ int perf_stat_process_counter(struct perf_stat_config *config,
struct perf_counts_values *aggr = &counter->counts->aggr;
struct perf_stat_evsel *ps = counter->priv;
u64 *count = counter->counts->aggr.values;
- u64 val;
int i, ret;
aggr->val = aggr->ena = aggr->run = 0;
@@ -360,8 +359,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
/*
* Save the full runtime - to allow normalization during printout:
*/
- val = counter->scale * *count;
- perf_stat__update_shadow_stats(counter, &val, 0);
+ perf_stat__update_shadow_stats(counter, *count, 0);
return 0;
}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 47915df346fb..490b78aa7230 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -82,7 +82,7 @@ typedef void (*new_line_t )(void *ctx);
void perf_stat__init_shadow_stats(void);
void perf_stat__reset_shadow_stats(void);
-void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
+void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count,
int cpu);
struct perf_stat_output_ctx {
void *ctx;
--
2.13.6
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH 7/9] perf stat: Make --per-thread update shadow stats to show metrics
2017-10-13 8:37 [PATCH 0/9] perf tools: Assorted fixes Jiri Olsa
` (5 preceding siblings ...)
2017-10-13 8:37 ` [PATCH 6/9] perf stat: Move the shadow stats scale computation in perf_stat__update_shadow_stats Jiri Olsa
@ 2017-10-13 8:37 ` Jiri Olsa
2017-10-13 8:37 ` [PATCH 8/9] perf tools: Check wether the eBPF file exists in event parsing Jiri Olsa
2017-10-13 8:37 ` [PATCH 9/9] perf tools: Unwind properly location after REJECT Jiri Olsa
8 siblings, 0 replies; 16+ messages in thread
From: Jiri Olsa @ 2017-10-13 8:37 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: lkml, Ingo Molnar, Namhyung Kim, David Ahern, Peter Zijlstra,
Andi Kleen, Jin, Yao, Wangnan (F),
Du, Changbin
We should support this because it would allow easily to collect metrics
for different threads in applications.
Original patch from posted by Jin Yao in here [1].
1. Current output, for example:
root@skl:/tmp# perf stat --per-thread -p 21623
^C
Performance counter stats for process id '21623':
vmstat-21623 0.517479 task-clock (msec) # 0.000 CPUs utilized
vmstat-21623 1 context-switches
vmstat-21623 0 cpu-migrations
vmstat-21623 0 page-faults
vmstat-21623 461,306 cycles
vmstat-21623 630,724 instructions
vmstat-21623 136,265 branches
vmstat-21623 2,520 branch-misses
1.444020756 seconds time elapsed
root@skl:/tmp# perf stat --per-thread --metrics ipc -p 21623
^C
Performance counter stats for process id '21623':
vmstat-21623 631,185 inst_retired.any
vmstat-21623 605,893 cpu_clk_unhalted.thread
1.415679293 seconds time elapsed
2. With this patch, the result would be:
root@skl:/tmp# perf stat --per-thread -p 21623
^C
Performance counter stats for process id '21623':
vmstat-21623 0.533759 task-clock (msec) # 0.000 CPUs utilized
vmstat-21623 1 context-switches # 0.002 M/sec
vmstat-21623 0 cpu-migrations # 0.000 K/sec
vmstat-21623 0 page-faults # 0.000 K/sec
vmstat-21623 473,896 cycles # 0.888 GHz
vmstat-21623 631,072 instructions # 1.33 insn per cycle
vmstat-21623 136,307 branches # 255.372 M/sec
vmstat-21623 2,524 branch-misses # 1.85% of all branches
1.544862861 seconds time elapsed
root@skl:/tmp# perf stat --per-thread --metrics ipc -p 21623
^C
Performance counter stats for process id '21623':
vmstat-21623 1,259,104 inst_retired.any # 1.2 IPC
vmstat-21623 1,056,756 cpu_clk_unhalted.thread
2.040954502 seconds time elapsed
[1] https://marc.info/?l=linux-kernel&m=150777054620511&w=2
Link: http://lkml.kernel.org/n/tip-tr8ntktxmy4qc5769ajg5u6c@git.kernel.org
Originally-from: Jin Yao <yao.jin@linux.intel.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
tools/perf/util/stat.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 7a3849851c20..c1cf42d04826 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -278,6 +278,8 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel
perf_counts_values__scale(count, config->scale, NULL);
if (config->aggr_mode == AGGR_NONE)
perf_stat__update_shadow_stats(evsel, count->val, cpu);
+ if (config->aggr_mode == AGGR_THREAD)
+ perf_stat__update_shadow_stats(evsel, count->val, 0);
break;
case AGGR_GLOBAL:
aggr->val += count->val;
--
2.13.6
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH 8/9] perf tools: Check wether the eBPF file exists in event parsing
2017-10-13 8:37 [PATCH 0/9] perf tools: Assorted fixes Jiri Olsa
` (6 preceding siblings ...)
2017-10-13 8:37 ` [PATCH 7/9] perf stat: Make --per-thread update shadow stats to show metrics Jiri Olsa
@ 2017-10-13 8:37 ` Jiri Olsa
2017-10-20 7:19 ` [tip:perf/urgent] " tip-bot for Jiri Olsa
2017-10-13 8:37 ` [PATCH 9/9] perf tools: Unwind properly location after REJECT Jiri Olsa
8 siblings, 1 reply; 16+ messages in thread
From: Jiri Olsa @ 2017-10-13 8:37 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: lkml, Ingo Molnar, Namhyung Kim, David Ahern, Peter Zijlstra,
Andi Kleen, Jin, Yao, Wangnan (F),
Du, Changbin
From: Jiri Olsa <jolsa@redhat.com>
Adding the check wether the eBPF file exists, to consider it
as eBPF input file. This way we can differentiate eBPF events
from events that end up with same suffix as eBPF file.
Before:
$ perf stat -e 'cpu/uops_executed.core/' true
bpf: builtin compilation failed: -95, try external compiler
WARNING: unable to get correct kernel building directory.
Hint: Set correct kbuild directory using 'kbuild-dir' option in [llvm]
section of ~/.perfconfig or set it to "" to suppress kbuild
detection.
event syntax error: 'cpu/uops_executed.core/'
\___ Failed to load cpu/uops_executed.c from source: 'version' section incorrect or lost
After:
$ perf stat -e 'cpu/uops_executed.core/' true
Performance counter stats for 'true':
181,533 cpu/uops_executed.core/:u
0.002795447 seconds time elapsed
If user makes type in the eBPF file, we prioritize the event syntax
and show following warning:
$ perf stat -e 'krava.c//' true
event syntax error: 'krava.c//'
\___ Cannot find PMU `krava.c'. Missing kernel support?
Tested-by: Andi Kleen <ak@linux.intel.com>
Link: http://lkml.kernel.org/n/tip-6qs139pd78ts64yfgk2bmphk@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
tools/perf/util/parse-events.l | 17 +++++++++++++++--
1 file changed, 15 insertions(+), 2 deletions(-)
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index ea2426daf7e8..38a42bdf1492 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -8,6 +8,9 @@
%{
#include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
#include "../perf.h"
#include "parse-events.h"
#include "parse-events-bison.h"
@@ -53,9 +56,8 @@ static int str(yyscan_t scanner, int token)
return token;
}
-static bool isbpf(yyscan_t scanner)
+static bool isbpf_suffix(char *text)
{
- char *text = parse_events_get_text(scanner);
int len = strlen(text);
if (len < 2)
@@ -68,6 +70,17 @@ static bool isbpf(yyscan_t scanner)
return false;
}
+static bool isbpf(yyscan_t scanner)
+{
+ char *text = parse_events_get_text(scanner);
+ struct stat st;
+
+ if (!isbpf_suffix(text))
+ return false;
+
+ return stat(text, &st) == 0;
+}
+
/*
* This function is called when the parser gets two kind of input:
*
--
2.13.6
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH 9/9] perf tools: Unwind properly location after REJECT
2017-10-13 8:37 [PATCH 0/9] perf tools: Assorted fixes Jiri Olsa
` (7 preceding siblings ...)
2017-10-13 8:37 ` [PATCH 8/9] perf tools: Check wether the eBPF file exists in event parsing Jiri Olsa
@ 2017-10-13 8:37 ` Jiri Olsa
2017-10-13 19:50 ` Arnaldo Carvalho de Melo
8 siblings, 1 reply; 16+ messages in thread
From: Jiri Olsa @ 2017-10-13 8:37 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: lkml, Ingo Molnar, Namhyung Kim, David Ahern, Peter Zijlstra,
Andi Kleen, Jin, Yao, Wangnan (F),
Du, Changbin
We have defined YY_USER_ACTION to keep trace of the column
location during events parsing, but we need to clean it up
when we call REJECT.
When REJECT is called, the lexer shrinks the text and re-runs
the matching, so we need to address it in resuming the previous
location value.
Tested-by: Andi Kleen <ak@linux.intel.com>
Link: http://lkml.kernel.org/n/tip-vug2hchlny30jfsfrumbym26@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
tools/perf/util/parse-events.l | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 38a42bdf1492..241396cd059d 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -154,6 +154,10 @@ do { \
yycolumn += yyleng; \
} while (0);
+#define USER_REJECT \
+ yycolumn -= yyleng; \
+ REJECT
+
%}
%x mem
@@ -336,8 +340,8 @@ r{num_raw_hex} { return raw(yyscanner); }
{num_hex} { return value(yyscanner, 16); }
{modifier_event} { return str(yyscanner, PE_MODIFIER_EVENT); }
-{bpf_object} { if (!isbpf(yyscanner)) REJECT; return str(yyscanner, PE_BPF_OBJECT); }
-{bpf_source} { if (!isbpf(yyscanner)) REJECT; return str(yyscanner, PE_BPF_SOURCE); }
+{bpf_object} { if (!isbpf(yyscanner)) USER_REJECT; return str(yyscanner, PE_BPF_OBJECT); }
+{bpf_source} { if (!isbpf(yyscanner)) USER_REJECT; return str(yyscanner, PE_BPF_SOURCE); }
{name} { return pmu_str_check(yyscanner); }
"/" { BEGIN(config); return '/'; }
- { return '-'; }
--
2.13.6
^ permalink raw reply related [flat|nested] 16+ messages in thread
* Re: [PATCH 9/9] perf tools: Unwind properly location after REJECT
2017-10-13 8:37 ` [PATCH 9/9] perf tools: Unwind properly location after REJECT Jiri Olsa
@ 2017-10-13 19:50 ` Arnaldo Carvalho de Melo
2017-10-24 12:51 ` [PATCHv2 " Jiri Olsa
0 siblings, 1 reply; 16+ messages in thread
From: Arnaldo Carvalho de Melo @ 2017-10-13 19:50 UTC (permalink / raw)
To: Jiri Olsa
Cc: lkml, Ingo Molnar, Namhyung Kim, David Ahern, Peter Zijlstra,
Andi Kleen, Jin, Yao, Wangnan (F),
Du, Changbin
Em Fri, Oct 13, 2017 at 10:37:36AM +0200, Jiri Olsa escreveu:
> We have defined YY_USER_ACTION to keep trace of the column
> location during events parsing, but we need to clean it up
> when we call REJECT.
>
> When REJECT is called, the lexer shrinks the text and re-runs
> the matching, so we need to address it in resuming the previous
> location value.
What is this fixing? Please state that, below I show what it is breaking
:-/
Before:
[root@jouet ~]# perf trace --no-syscalls -e ~acme/bpf/sys_read.c/max-stack=5/ sleep 1
bpf: builtin compilation failed: -95, try external compiler
0.000 perf_bpf_probe:func:(ffffffffbb2634e0))
sys_read ([kernel.kallsyms])
entry_SYSCALL_64_fastpath ([kernel.kallsyms])
__read (/usr/lib64/ld-2.25.so)
_dl_map_object (/usr/lib64/ld-2.25.so)
After:
[root@jouet ~]# perf trace --no-syscalls -e ~acme/bpf/sys_read.c/max-stack=5/ sleep 1
event syntax error: '/home/acme/bpf/sys_read.c/max-stack=5/'
\___ parser error
Run 'perf list' for a list of valid events
Usage: perf trace [<options>] [<command>]
or: perf trace [<options>] -- <command> [<options>]
or: perf trace record [<options>] [<command>]
or: perf trace record [<options>] -- <command> [<options>]
-e, --event <event> event/syscall selector. use 'perf list' to list available events
[root@jouet ~]#
^ permalink raw reply [flat|nested] 16+ messages in thread
* [tip:perf/urgent] perf hists: Fix crash in perf_hpp__reset_output_field()
2017-10-13 8:37 ` [PATCH 1/9] perf tools: Fix crash in perf_hpp__reset_output_field Jiri Olsa
@ 2017-10-20 7:18 ` tip-bot for Jiri Olsa
0 siblings, 0 replies; 16+ messages in thread
From: tip-bot for Jiri Olsa @ 2017-10-20 7:18 UTC (permalink / raw)
To: linux-tip-commits
Cc: namhyung, linux-kernel, dsahern, wangnan0, jolsa, acme, tglx,
andi, peterz, yao.jin, hpa, changbin.du, mingo
Commit-ID: 70b01dfd765dd2196d51f33a49df23954416f34a
Gitweb: https://git.kernel.org/tip/70b01dfd765dd2196d51f33a49df23954416f34a
Author: Jiri Olsa <jolsa@kernel.org>
AuthorDate: Fri, 13 Oct 2017 10:37:28 +0200
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Fri, 13 Oct 2017 16:43:33 -0300
perf hists: Fix crash in perf_hpp__reset_output_field()
Du Changbin reported crash [1] when calling perf_hpp__reset_output_field()
after unregistering field via perf_hpp__column_unregister().
This ends up in calling following list_del* sequence on
the same format:
perf_hpp__column_unregister:
list_del(&format->list);
perf_hpp__reset_output_field:
list_del_init(&fmt->list);
where the later list_del_init might touch already freed formats.
Fixing this by replacing list_del() with list_del_init() in
perf_hpp__column_unregister().
[1] http://marc.info/?l=linux-kernel&m=149059595826019&w=2
Reported-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/20171013083736.15037-2-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/ui/hist.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index ddb2c6f..6ee6b36 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -532,7 +532,7 @@ void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
{
- list_del(&format->list);
+ list_del_init(&format->list);
}
void perf_hpp__cancel_cumulate(void)
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [tip:perf/urgent] perf hists: Add extra integrity checks to fmt_free()
2017-10-13 8:37 ` [PATCH 2/9] perf tools: Add extra integrity checks to fmt_free Jiri Olsa
@ 2017-10-20 7:19 ` tip-bot for Jiri Olsa
0 siblings, 0 replies; 16+ messages in thread
From: tip-bot for Jiri Olsa @ 2017-10-20 7:19 UTC (permalink / raw)
To: linux-tip-commits
Cc: peterz, hpa, dsahern, andi, jolsa, mingo, changbin.du,
linux-kernel, namhyung, acme, yao.jin, wangnan0, tglx
Commit-ID: d0e35234f647631ddfa5fa8c8ec66c9bc698f0ab
Gitweb: https://git.kernel.org/tip/d0e35234f647631ddfa5fa8c8ec66c9bc698f0ab
Author: Jiri Olsa <jolsa@kernel.org>
AuthorDate: Fri, 13 Oct 2017 10:37:29 +0200
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Fri, 13 Oct 2017 16:43:42 -0300
perf hists: Add extra integrity checks to fmt_free()
Make sure the struct perf_hpp_fmt is properly unhooked before we free
it.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Changbin Du <changbin.du@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/20171013083736.15037-3-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/ui/hist.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 6ee6b36..db79017 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -606,6 +606,13 @@ next:
static void fmt_free(struct perf_hpp_fmt *fmt)
{
+ /*
+ * At this point fmt should be completely
+ * unhooked, if not it's a bug.
+ */
+ BUG_ON(!list_empty(&fmt->list));
+ BUG_ON(!list_empty(&fmt->sort_list));
+
if (fmt->free)
fmt->free(fmt);
}
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [tip:perf/urgent] perf tools: Check wether the eBPF file exists in event parsing
2017-10-13 8:37 ` [PATCH 8/9] perf tools: Check wether the eBPF file exists in event parsing Jiri Olsa
@ 2017-10-20 7:19 ` tip-bot for Jiri Olsa
0 siblings, 0 replies; 16+ messages in thread
From: tip-bot for Jiri Olsa @ 2017-10-20 7:19 UTC (permalink / raw)
To: linux-tip-commits
Cc: dsahern, changbin.du, jolsa, acme, wangnan0, jolsa, namhyung,
yao.jin, mingo, linux-kernel, tglx, ak, hpa, peterz
Commit-ID: 29479bfe83bafb8aa37f36ca132ee8349d11da0c
Gitweb: https://git.kernel.org/tip/29479bfe83bafb8aa37f36ca132ee8349d11da0c
Author: Jiri Olsa <jolsa@redhat.com>
AuthorDate: Fri, 13 Oct 2017 10:37:35 +0200
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Fri, 13 Oct 2017 16:45:04 -0300
perf tools: Check wether the eBPF file exists in event parsing
Adding the check wether the eBPF file exists, to consider it
as eBPF input file. This way we can differentiate eBPF events
from events that end up with same suffix as eBPF file.
Before:
$ perf stat -e 'cpu/uops_executed.core/' true
bpf: builtin compilation failed: -95, try external compiler
WARNING: unable to get correct kernel building directory.
Hint: Set correct kbuild directory using 'kbuild-dir' option in [llvm]
section of ~/.perfconfig or set it to "" to suppress kbuild
detection.
event syntax error: 'cpu/uops_executed.core/'
\___ Failed to load cpu/uops_executed.c from source: 'version' section incorrect or lost
After:
$ perf stat -e 'cpu/uops_executed.core/' true
Performance counter stats for 'true':
181,533 cpu/uops_executed.core/:u
0.002795447 seconds time elapsed
If user makes type in the eBPF file, we prioritize the event syntax
and show following warning:
$ perf stat -e 'krava.c//' true
event syntax error: 'krava.c//'
\___ Cannot find PMU `krava.c'. Missing kernel support?
Reported-and-Tested-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Changbin Du <changbin.du@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/20171013083736.15037-9-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/parse-events.l | 17 +++++++++++++++--
1 file changed, 15 insertions(+), 2 deletions(-)
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index c42edea..dcfdafd 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -8,6 +8,9 @@
%{
#include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
#include "../perf.h"
#include "parse-events.h"
#include "parse-events-bison.h"
@@ -53,9 +56,8 @@ static int str(yyscan_t scanner, int token)
return token;
}
-static bool isbpf(yyscan_t scanner)
+static bool isbpf_suffix(char *text)
{
- char *text = parse_events_get_text(scanner);
int len = strlen(text);
if (len < 2)
@@ -68,6 +70,17 @@ static bool isbpf(yyscan_t scanner)
return false;
}
+static bool isbpf(yyscan_t scanner)
+{
+ char *text = parse_events_get_text(scanner);
+ struct stat st;
+
+ if (!isbpf_suffix(text))
+ return false;
+
+ return stat(text, &st) == 0;
+}
+
/*
* This function is called when the parser gets two kind of input:
*
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCHv2 9/9] perf tools: Unwind properly location after REJECT
2017-10-13 19:50 ` Arnaldo Carvalho de Melo
@ 2017-10-24 12:51 ` Jiri Olsa
2017-10-25 14:07 ` Jiri Olsa
0 siblings, 1 reply; 16+ messages in thread
From: Jiri Olsa @ 2017-10-24 12:51 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: Jiri Olsa, lkml, Ingo Molnar, Namhyung Kim, David Ahern,
Peter Zijlstra, Andi Kleen, Jin, Yao, Wangnan (F),
Du, Changbin
On Fri, Oct 13, 2017 at 04:50:36PM -0300, Arnaldo Carvalho de Melo wrote:
> Em Fri, Oct 13, 2017 at 10:37:36AM +0200, Jiri Olsa escreveu:
> > We have defined YY_USER_ACTION to keep trace of the column
> > location during events parsing, but we need to clean it up
> > when we call REJECT.
> >
> > When REJECT is called, the lexer shrinks the text and re-runs
> > the matching, so we need to address it in resuming the previous
> > location value.
>
> What is this fixing? Please state that, below I show what it is breaking
> :-/
>
> Before:
>
> [root@jouet ~]# perf trace --no-syscalls -e ~acme/bpf/sys_read.c/max-stack=5/ sleep 1
> bpf: builtin compilation failed: -95, try external compiler
> 0.000 perf_bpf_probe:func:(ffffffffbb2634e0))
> sys_read ([kernel.kallsyms])
> entry_SYSCALL_64_fastpath ([kernel.kallsyms])
> __read (/usr/lib64/ld-2.25.so)
> _dl_map_object (/usr/lib64/ld-2.25.so)
>
> After:
>
> [root@jouet ~]# perf trace --no-syscalls -e ~acme/bpf/sys_read.c/max-stack=5/ sleep 1
> event syntax error: '/home/acme/bpf/sys_read.c/max-stack=5/'
> \___ parser error
> Run 'perf list' for a list of valid events
>
> Usage: perf trace [<options>] [<command>]
> or: perf trace [<options>] -- <command> [<options>]
> or: perf trace record [<options>] [<command>]
> or: perf trace record [<options>] -- <command> [<options>]
>
> -e, --event <event> event/syscall selector. use 'perf list' to list available events
> [root@jouet ~]#
>
v2 with updated changelog attached,
also I rebased the rest of the fixes and pushed
them into perf/fixes branch
thanks,
jirka
---
We have defined YY_USER_ACTION to keep trace of the column
location during events parsing, but we need to clean it up
when we call REJECT.
When REJECT is called, the lexer shrinks the text and re-runs
the matching, so we need to address it in resuming the previous
location value to keep it correct for error display, like:
Before:
$ perf stat -e 'cpu/uops_executed.core,krava/' true
event syntax error: '..38;5;9:mi=01;05;37;41:su=48;5;196;38;5;15:sg=48;5;1\
1;38;5;16:ca=48;5;196;38;5;226:tw=48;5;10;38;5;16:ow=48;5;10;38;5;21:st=48;5;\
21;38;50
�'
\___ unknown term
After:
$ ./perf stat -e 'cpu/uops_executed.core,krava/' true
event syntax error: '..cuted.core,krava/'
\___ unknown term
Tested-by: Andi Kleen <ak@linux.intel.com>
Link: http://lkml.kernel.org/n/tip-vug2hchlny30jfsfrumbym26@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
tools/perf/util/parse-events.l | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 38a42bdf1492..241396cd059d 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -154,6 +154,10 @@ do { \
yycolumn += yyleng; \
} while (0);
+#define USER_REJECT \
+ yycolumn -= yyleng; \
+ REJECT
+
%}
%x mem
@@ -336,8 +340,8 @@ r{num_raw_hex} { return raw(yyscanner); }
{num_hex} { return value(yyscanner, 16); }
{modifier_event} { return str(yyscanner, PE_MODIFIER_EVENT); }
-{bpf_object} { if (!isbpf(yyscanner)) REJECT; return str(yyscanner, PE_BPF_OBJECT); }
-{bpf_source} { if (!isbpf(yyscanner)) REJECT; return str(yyscanner, PE_BPF_SOURCE); }
+{bpf_object} { if (!isbpf(yyscanner)) USER_REJECT; return str(yyscanner, PE_BPF_OBJECT); }
+{bpf_source} { if (!isbpf(yyscanner)) USER_REJECT; return str(yyscanner, PE_BPF_SOURCE); }
{name} { return pmu_str_check(yyscanner); }
"/" { BEGIN(config); return '/'; }
- { return '-'; }
--
2.13.6
^ permalink raw reply related [flat|nested] 16+ messages in thread
* Re: [PATCHv2 9/9] perf tools: Unwind properly location after REJECT
2017-10-24 12:51 ` [PATCHv2 " Jiri Olsa
@ 2017-10-25 14:07 ` Jiri Olsa
0 siblings, 0 replies; 16+ messages in thread
From: Jiri Olsa @ 2017-10-25 14:07 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: Jiri Olsa, lkml, Ingo Molnar, Namhyung Kim, David Ahern,
Peter Zijlstra, Andi Kleen, Jin, Yao, Wangnan (F),
Du, Changbin
On Tue, Oct 24, 2017 at 02:51:21PM +0200, Jiri Olsa wrote:
> On Fri, Oct 13, 2017 at 04:50:36PM -0300, Arnaldo Carvalho de Melo wrote:
> > Em Fri, Oct 13, 2017 at 10:37:36AM +0200, Jiri Olsa escreveu:
> > > We have defined YY_USER_ACTION to keep trace of the column
> > > location during events parsing, but we need to clean it up
> > > when we call REJECT.
> > >
> > > When REJECT is called, the lexer shrinks the text and re-runs
> > > the matching, so we need to address it in resuming the previous
> > > location value.
> >
> > What is this fixing? Please state that, below I show what it is breaking
> > :-/
> >
> > Before:
> >
> > [root@jouet ~]# perf trace --no-syscalls -e ~acme/bpf/sys_read.c/max-stack=5/ sleep 1
> > bpf: builtin compilation failed: -95, try external compiler
> > 0.000 perf_bpf_probe:func:(ffffffffbb2634e0))
> > sys_read ([kernel.kallsyms])
> > entry_SYSCALL_64_fastpath ([kernel.kallsyms])
> > __read (/usr/lib64/ld-2.25.so)
> > _dl_map_object (/usr/lib64/ld-2.25.so)
> >
> > After:
> >
> > [root@jouet ~]# perf trace --no-syscalls -e ~acme/bpf/sys_read.c/max-stack=5/ sleep 1
> > event syntax error: '/home/acme/bpf/sys_read.c/max-stack=5/'
> > \___ parser error
> > Run 'perf list' for a list of valid events
> >
> > Usage: perf trace [<options>] [<command>]
> > or: perf trace [<options>] -- <command> [<options>]
> > or: perf trace record [<options>] [<command>]
> > or: perf trace record [<options>] -- <command> [<options>]
> >
> > -e, --event <event> event/syscall selector. use 'perf list' to list available events
> > [root@jouet ~]#
> >
>
> v2 with updated changelog attached,
>
> also I rebased the rest of the fixes and pushed
> them into perf/fixes branch
and I just rebased/pushed that once again.. we are too fast ;-)
thanks,
jirka
^ permalink raw reply [flat|nested] 16+ messages in thread
end of thread, other threads:[~2017-10-25 14:07 UTC | newest]
Thread overview: 16+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2017-10-13 8:37 [PATCH 0/9] perf tools: Assorted fixes Jiri Olsa
2017-10-13 8:37 ` [PATCH 1/9] perf tools: Fix crash in perf_hpp__reset_output_field Jiri Olsa
2017-10-20 7:18 ` [tip:perf/urgent] perf hists: Fix crash in perf_hpp__reset_output_field() tip-bot for Jiri Olsa
2017-10-13 8:37 ` [PATCH 2/9] perf tools: Add extra integrity checks to fmt_free Jiri Olsa
2017-10-20 7:19 ` [tip:perf/urgent] perf hists: Add extra integrity checks to fmt_free() tip-bot for Jiri Olsa
2017-10-13 8:37 ` [PATCH 3/9] perf tools: Rename struct perf_data_file to perf_data Jiri Olsa
2017-10-13 8:37 ` [PATCH 4/9] perf tools: Add struct perf_data_file Jiri Olsa
2017-10-13 8:37 ` [PATCH 5/9] perf tools: Add perf_data_file__write function Jiri Olsa
2017-10-13 8:37 ` [PATCH 6/9] perf stat: Move the shadow stats scale computation in perf_stat__update_shadow_stats Jiri Olsa
2017-10-13 8:37 ` [PATCH 7/9] perf stat: Make --per-thread update shadow stats to show metrics Jiri Olsa
2017-10-13 8:37 ` [PATCH 8/9] perf tools: Check wether the eBPF file exists in event parsing Jiri Olsa
2017-10-20 7:19 ` [tip:perf/urgent] " tip-bot for Jiri Olsa
2017-10-13 8:37 ` [PATCH 9/9] perf tools: Unwind properly location after REJECT Jiri Olsa
2017-10-13 19:50 ` Arnaldo Carvalho de Melo
2017-10-24 12:51 ` [PATCHv2 " Jiri Olsa
2017-10-25 14:07 ` Jiri Olsa
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.