[PATCH v8 1/4] Create source symlink in perf object dir

[PATCH v8 1/4] Create source symlink in perf object dir

[Andi Kleen]

Create a source symlink to the original source in the objdir.
This is similar to what the main kernel build script does.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/Makefile.perf | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 175e4c7898f0..d46892d8223b 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -163,6 +163,8 @@ ifneq ($(OUTPUT),)
 # for flex/bison parsers.
 VPATH += $(OUTPUT)
 export VPATH
+# create symlink to the original source
+SOURCE := $(shell ln -sf $(srctree)/tools/perf $(OUTPUT)/source)
 endif
 
 ifeq ($(V),1)
-- 
2.45.2

[PATCH v8 2/4] perf test: Support external tests for separate objdir

[Andi Kleen]

Extend the searching for the test files so that it works
when running perf from a separate objdir, and also when
the perf executable is symlinked.

Signed-off-by: Andi Kleen <ak@linux.intel.com>

----

v2: Fix string test (Namhyung)
Handle both in source and out of source builds.
---
 tools/perf/tests/tests-scripts.c | 37 +++++++++++++++++++++++++++++---
 1 file changed, 34 insertions(+), 3 deletions(-)

diff --git a/tools/perf/tests/tests-scripts.c b/tools/perf/tests/tests-scripts.c
index e2042b368269..9f71ffed702c 100644
--- a/tools/perf/tests/tests-scripts.c
+++ b/tools/perf/tests/tests-scripts.c
@@ -29,16 +29,47 @@
 
 static int shell_tests__dir_fd(void)
 {
-	char path[PATH_MAX], *exec_path;
-	static const char * const devel_dirs[] = { "./tools/perf/tests/shell", "./tests/shell", };
+	struct stat st;
+	char path[PATH_MAX], path2[PATH_MAX], *exec_path;
+	static const char * const devel_dirs[] = {
+		"./tools/perf/tests/shell",
+		"./tests/shell",
+		"./source/tests/shell"
+	};
+	int fd;
+	char *p;
 
 	for (size_t i = 0; i < ARRAY_SIZE(devel_dirs); ++i) {
-		int fd = open(devel_dirs[i], O_PATH);
+		fd = open(devel_dirs[i], O_PATH);
 
 		if (fd >= 0)
 			return fd;
 	}
 
+	/* Use directory of executable */
+	if (readlink("/proc/self/exe", path2, sizeof path2) < 0)
+		return -1;
+	/* Follow another level of symlink if there */
+	if (lstat(path2, &st) == 0 && (st.st_mode & S_IFMT) == S_IFLNK) {
+		scnprintf(path, sizeof(path), path2);
+		if (readlink(path, path2, sizeof path2) < 0)
+			return -1;
+	}
+	/* Get directory */
+	p = strrchr(path2, '/');
+	if (p)
+		*p = 0;
+	scnprintf(path, sizeof(path), "%s/tests/shell", path2);
+	fd = open(path, O_PATH);
+	if (fd >= 0)
+		return fd;
+	if (p)
+		*p = 0;
+	scnprintf(path, sizeof(path), "%s/source/tests/shell", path2);
+	fd = open(path, O_PATH);
+	if (fd >= 0)
+		return fd;
+
 	/* Then installed path. */
 	exec_path = get_argv_exec_path();
 	scnprintf(path, sizeof(path), "%s/tests/shell", exec_path);
-- 
2.45.2

[PATCH v8 3/4] perf script: Fix perf script -F +metric

[Andi Kleen]

This fixes a regression with perf script -F +metric originally caused by :

commit 37cc8ad77cf81f3ffd226856c367b0e15333a738
Author: Ian Rogers <irogers@google.com>
Date:   Sun Feb 19 01:28:46 2023 -0800

    perf metric: Directly use counts rather than saved_value

In the perf script environment the evsel wouldn't allocate an aggr
values array, which led to a -1 reference because the metric
evaluation would try to reference NULL - 1 (for aggr_idx)

Give the perf script evsels a single CPU aggr setup. That's
enough because the groups are always contiguous, so no need
to store more than one CPU's worth of values.

Before

% perf record -e '{cycles,instructions}:S' perf bench  mem memcpy
% perf script -F +metric
Segmentation fault (core dumped)

After:

% perf record -e '{cycles,instructions}:S' perf bench  mem memcpy
...
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.028 MB perf.data (90 samples) ]
% perf script -F +metric
       perf-exec 1847557 264658.180789:       3009       cycles:  ffffffff990a579a native_write_msr+0xa ([kernel.kallsyms])
       perf-exec 1847557 264658.180789:        382 instructions:  ffffffff990a579a native_write_msr+0xa ([kernel.kallsyms])
       perf-exec 1847557 264658.180789:         metric:    0.13  insn per cycle
...

Fixes: 37cc8ad77cf8 ("perf metric: Directly use counts rather ...")
Signed-off-by: Andi Kleen <ak@linux.intel.com>

----

v2: Reformat code
v3: Work around bogus warning
v4: Set up aggr map only for metrics case to keep perf stat record
working
v5: Broken version
v6: Only set up limited aggregation mode with -F +metric. Add conflict
checks with perf stat record files.
v7: Remove some unnecessary conflict checks. Fix buffer overflow. Minor cleanups.
v8: Add check for leader sampling. Update some comments.
---
 tools/perf/builtin-script.c | 50 +++++++++++++++++++++++++++++++++----
 1 file changed, 45 insertions(+), 5 deletions(-)

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c16224b1fef3..04378615b2ad 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -335,7 +335,6 @@ struct evsel_script {
        FILE *fp;
        u64  samples;
        /* For metric output */
-       u64  val;
        int  gnum;
 };
 
@@ -2127,18 +2126,30 @@ static void perf_sample__fprint_metric(struct perf_script *script,
 	};
 	struct evsel *ev2;
 	u64 val;
+	static int printed;
 
 	if (!evsel->stats)
 		evlist__alloc_stats(&stat_config, script->session->evlist, /*alloc_raw=*/false);
 	if (evsel_script(leader)->gnum++ == 0)
 		perf_stat__reset_shadow_stats();
-	val = sample->period * evsel->scale;
-	evsel_script(evsel)->val = val;
+	val = sample->period;
+	if (!(evsel->core.attr.sample_type & PERF_SAMPLE_READ)) {
+		if (!printed)
+			fprintf(stderr, "perf script: -F metric requires {}:S for groups leader sampling\n");
+		printed = 1;
+		return;
+	}
+	/*
+	 * Always use the first entry as storage because the leader sampling
+	 * groups are contiguous and there's no need to handle multiple indexes
+	 * for anything.
+	 */
+	evsel->stats->aggr[0].counts.val = val;
 	if (evsel_script(leader)->gnum == leader->core.nr_members) {
 		for_each_group_member (ev2, leader) {
 			perf_stat__print_shadow_stats(&stat_config, ev2,
-						      evsel_script(ev2)->val,
-						      sample->cpu,
+						      evsel->stats->aggr[0].counts.val,
+						      0,
 						      &ctx,
 						      NULL);
 		}
@@ -2325,6 +2336,20 @@ static void process_event(struct perf_script *script,
 		fflush(fp);
 }
 
+static void check_metric_conflict(void)
+{
+	int i;
+	/*
+	 * Avoid conflict with the aggregation mode used for the metric printing.
+	 */
+	for (i = 0; i < OUTPUT_TYPE_MAX; i++) {
+		if (output[i].fields & PERF_OUTPUT_METRIC) {
+			fprintf(stderr, "perf stat record files are not supported with -F metric\n");
+			exit(1);
+		}
+	}
+}
+
 static struct scripting_ops	*scripting_ops;
 
 static void __process_stat(struct evsel *counter, u64 tstamp)
@@ -2334,6 +2359,8 @@ static void __process_stat(struct evsel *counter, u64 tstamp)
 	struct perf_cpu cpu;
 	static int header_printed;
 
+	check_metric_conflict();
+
 	if (!header_printed) {
 		printf("%3s %8s %15s %15s %15s %15s %s\n",
 		       "CPU", "THREAD", "VAL", "ENA", "RUN", "TIME", "EVENT");
@@ -3725,6 +3752,8 @@ static int process_stat_config_event(struct perf_session *session __maybe_unused
 {
 	perf_event__read_stat_config(&stat_config, &event->stat_config);
 
+	check_metric_conflict();
+
 	/*
 	 * Aggregation modes are not used since post-processing scripts are
 	 * supposed to take care of such requirements
@@ -4088,6 +4117,17 @@ 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);
+	for (i = 0; i < OUTPUT_TYPE_MAX; i++) {
+		if (output[i].fields & PERF_OUTPUT_METRIC) {
+			stat_config.aggr_map = cpu_aggr_map__empty_new(1);
+			err = -ENOMEM;
+			if (!stat_config.aggr_map)
+				goto out;
+			err = 0;
+			stat_config.aggr_map->nr = 1;
+			break;
+		}
+	}
 
 	if (symbol_conf.guestmount ||
 	    symbol_conf.default_guest_vmlinux_name ||
-- 
2.45.2

[PATCH v8 4/4] Add a test case for perf script -F +metric

[Andi Kleen]

Just a simple test

Signed-off-by: Andi Kleen <ak@linux.intel.com>

----

v2: Avoid bashisms. Use noploop
v3: Avoid false positive in shellcheck
v4: Use :S in the test (Ian, Namhyung)
---
 tools/perf/tests/shell/script.sh | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/tools/perf/tests/shell/script.sh b/tools/perf/tests/shell/script.sh
index c1a603653662..e69c3548583a 100755
--- a/tools/perf/tests/shell/script.sh
+++ b/tools/perf/tests/shell/script.sh
@@ -7,6 +7,7 @@ set -e
 temp_dir=$(mktemp -d /tmp/perf-test-script.XXXXXXXXXX)
 
 perfdatafile="${temp_dir}/perf.data"
+scriptoutput="${temp_dir}/script"
 db_test="${temp_dir}/db_test.py"
 
 err=0
@@ -88,8 +89,21 @@ test_parallel_perf()
 	echo "parallel-perf test [Success]"
 }
 
+test_metric()
+{
+	echo "script metric test"
+	if ! perf list | grep -q cycles ; then return ; fi
+	if ! perf list | grep -q instructions ; then return ; fi
+	perf record -e '{cycles,instructions}:S' -o "${perfdatafile}" perf test -w noploop
+	perf script -i "${perfdatafile}" -F +metric  > $scriptoutput
+	test "`grep -c metric $scriptoutput`" -gt 5
+	grep metric $scriptoutput | head
+	echo "script metric test [Success]"
+}
+
 test_db
 test_parallel_perf
+test_metric
 
 cleanup
 
-- 
2.45.2

Re: [PATCH v8 2/4] perf test: Support external tests for separate objdir

[Namhyung Kim]

On Thu, Aug 01, 2024 at 02:28:42PM -0700, Andi Kleen wrote:
> Extend the searching for the test files so that it works
> when running perf from a separate objdir, and also when
> the perf executable is symlinked.
> 
> Signed-off-by: Andi Kleen <ak@linux.intel.com>
> 
> ----
> 
> v2: Fix string test (Namhyung)
> Handle both in source and out of source builds.
> ---
>  tools/perf/tests/tests-scripts.c | 37 +++++++++++++++++++++++++++++---
>  1 file changed, 34 insertions(+), 3 deletions(-)
> 
> diff --git a/tools/perf/tests/tests-scripts.c b/tools/perf/tests/tests-scripts.c
> index e2042b368269..9f71ffed702c 100644
> --- a/tools/perf/tests/tests-scripts.c
> +++ b/tools/perf/tests/tests-scripts.c
> @@ -29,16 +29,47 @@
>  
>  static int shell_tests__dir_fd(void)
>  {
> -	char path[PATH_MAX], *exec_path;
> -	static const char * const devel_dirs[] = { "./tools/perf/tests/shell", "./tests/shell", };
> +	struct stat st;
> +	char path[PATH_MAX], path2[PATH_MAX], *exec_path;
> +	static const char * const devel_dirs[] = {
> +		"./tools/perf/tests/shell",
> +		"./tests/shell",
> +		"./source/tests/shell"
> +	};
> +	int fd;
> +	char *p;
>  
>  	for (size_t i = 0; i < ARRAY_SIZE(devel_dirs); ++i) {
> -		int fd = open(devel_dirs[i], O_PATH);
> +		fd = open(devel_dirs[i], O_PATH);
>  
>  		if (fd >= 0)
>  			return fd;
>  	}
>  
> +	/* Use directory of executable */
> +	if (readlink("/proc/self/exe", path2, sizeof path2) < 0)
> +		return -1;
> +	/* Follow another level of symlink if there */
> +	if (lstat(path2, &st) == 0 && (st.st_mode & S_IFMT) == S_IFLNK) {
> +		scnprintf(path, sizeof(path), path2);
> +		if (readlink(path, path2, sizeof path2) < 0)
> +			return -1;
> +	}
> +	/* Get directory */
> +	p = strrchr(path2, '/');
> +	if (p)
> +		*p = 0;
> +	scnprintf(path, sizeof(path), "%s/tests/shell", path2);
> +	fd = open(path, O_PATH);
> +	if (fd >= 0)
> +		return fd;
> +	if (p)
> +		*p = 0;

This part looks unnecessary.

Thanks,
Namhyung


> +	scnprintf(path, sizeof(path), "%s/source/tests/shell", path2);
> +	fd = open(path, O_PATH);
> +	if (fd >= 0)
> +		return fd;
> +
>  	/* Then installed path. */
>  	exec_path = get_argv_exec_path();
>  	scnprintf(path, sizeof(path), "%s/tests/shell", exec_path);
> -- 
> 2.45.2
> 

Re: [PATCH v8 3/4] perf script: Fix perf script -F +metric

[Namhyung Kim]

On Thu, Aug 01, 2024 at 02:28:43PM -0700, Andi Kleen wrote:
> This fixes a regression with perf script -F +metric originally caused by :
> 
> commit 37cc8ad77cf81f3ffd226856c367b0e15333a738
> Author: Ian Rogers <irogers@google.com>
> Date:   Sun Feb 19 01:28:46 2023 -0800
> 
>     perf metric: Directly use counts rather than saved_value
> 
> In the perf script environment the evsel wouldn't allocate an aggr
> values array, which led to a -1 reference because the metric
> evaluation would try to reference NULL - 1 (for aggr_idx)
> 
> Give the perf script evsels a single CPU aggr setup. That's
> enough because the groups are always contiguous, so no need
> to store more than one CPU's worth of values.
> 
> Before
> 
> % perf record -e '{cycles,instructions}:S' perf bench  mem memcpy
> % perf script -F +metric
> Segmentation fault (core dumped)
> 
> After:
> 
> % perf record -e '{cycles,instructions}:S' perf bench  mem memcpy
> ...
> [ perf record: Woken up 1 times to write data ]
> [ perf record: Captured and wrote 0.028 MB perf.data (90 samples) ]
> % perf script -F +metric
>        perf-exec 1847557 264658.180789:       3009       cycles:  ffffffff990a579a native_write_msr+0xa ([kernel.kallsyms])
>        perf-exec 1847557 264658.180789:        382 instructions:  ffffffff990a579a native_write_msr+0xa ([kernel.kallsyms])
>        perf-exec 1847557 264658.180789:         metric:    0.13  insn per cycle
> ...
> 
> Fixes: 37cc8ad77cf8 ("perf metric: Directly use counts rather ...")
> Signed-off-by: Andi Kleen <ak@linux.intel.com>
> 
> ----
> 
> v2: Reformat code
> v3: Work around bogus warning
> v4: Set up aggr map only for metrics case to keep perf stat record
> working
> v5: Broken version
> v6: Only set up limited aggregation mode with -F +metric. Add conflict
> checks with perf stat record files.
> v7: Remove some unnecessary conflict checks. Fix buffer overflow. Minor cleanups.
> v8: Add check for leader sampling. Update some comments.
> ---
>  tools/perf/builtin-script.c | 50 +++++++++++++++++++++++++++++++++----
>  1 file changed, 45 insertions(+), 5 deletions(-)
> 
> diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
> index c16224b1fef3..04378615b2ad 100644
> --- a/tools/perf/builtin-script.c
> +++ b/tools/perf/builtin-script.c
> @@ -335,7 +335,6 @@ struct evsel_script {
>         FILE *fp;
>         u64  samples;
>         /* For metric output */
> -       u64  val;
>         int  gnum;
>  };
>  
> @@ -2127,18 +2126,30 @@ static void perf_sample__fprint_metric(struct perf_script *script,
>  	};
>  	struct evsel *ev2;
>  	u64 val;
> +	static int printed;
>  
>  	if (!evsel->stats)
>  		evlist__alloc_stats(&stat_config, script->session->evlist, /*alloc_raw=*/false);
>  	if (evsel_script(leader)->gnum++ == 0)
>  		perf_stat__reset_shadow_stats();
> -	val = sample->period * evsel->scale;
> -	evsel_script(evsel)->val = val;
> +	val = sample->period;
> +	if (!(evsel->core.attr.sample_type & PERF_SAMPLE_READ)) {

The correct check would need PERF_FORMAT_GROUP in attr.read_format for
the leader event, and no attr.sample_period for member events.  But I
guess practically it's enough to check the leader only.

Thanks,
Namhyung


> +		if (!printed)
> +			fprintf(stderr, "perf script: -F metric requires {}:S for groups leader sampling\n");
> +		printed = 1;
> +		return;
> +	}
> +	/*
> +	 * Always use the first entry as storage because the leader sampling
> +	 * groups are contiguous and there's no need to handle multiple indexes
> +	 * for anything.
> +	 */
> +	evsel->stats->aggr[0].counts.val = val;
>  	if (evsel_script(leader)->gnum == leader->core.nr_members) {
>  		for_each_group_member (ev2, leader) {
>  			perf_stat__print_shadow_stats(&stat_config, ev2,
> -						      evsel_script(ev2)->val,
> -						      sample->cpu,
> +						      evsel->stats->aggr[0].counts.val,
> +						      0,
>  						      &ctx,
>  						      NULL);
>  		}
> @@ -2325,6 +2336,20 @@ static void process_event(struct perf_script *script,
>  		fflush(fp);
>  }
>  
> +static void check_metric_conflict(void)
> +{
> +	int i;
> +	/*
> +	 * Avoid conflict with the aggregation mode used for the metric printing.
> +	 */
> +	for (i = 0; i < OUTPUT_TYPE_MAX; i++) {
> +		if (output[i].fields & PERF_OUTPUT_METRIC) {
> +			fprintf(stderr, "perf stat record files are not supported with -F metric\n");
> +			exit(1);
> +		}
> +	}
> +}
> +
>  static struct scripting_ops	*scripting_ops;
>  
>  static void __process_stat(struct evsel *counter, u64 tstamp)
> @@ -2334,6 +2359,8 @@ static void __process_stat(struct evsel *counter, u64 tstamp)
>  	struct perf_cpu cpu;
>  	static int header_printed;
>  
> +	check_metric_conflict();
> +
>  	if (!header_printed) {
>  		printf("%3s %8s %15s %15s %15s %15s %s\n",
>  		       "CPU", "THREAD", "VAL", "ENA", "RUN", "TIME", "EVENT");
> @@ -3725,6 +3752,8 @@ static int process_stat_config_event(struct perf_session *session __maybe_unused
>  {
>  	perf_event__read_stat_config(&stat_config, &event->stat_config);
>  
> +	check_metric_conflict();
> +
>  	/*
>  	 * Aggregation modes are not used since post-processing scripts are
>  	 * supposed to take care of such requirements
> @@ -4088,6 +4117,17 @@ 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);
> +	for (i = 0; i < OUTPUT_TYPE_MAX; i++) {
> +		if (output[i].fields & PERF_OUTPUT_METRIC) {
> +			stat_config.aggr_map = cpu_aggr_map__empty_new(1);
> +			err = -ENOMEM;
> +			if (!stat_config.aggr_map)
> +				goto out;
> +			err = 0;
> +			stat_config.aggr_map->nr = 1;
> +			break;
> +		}
> +	}
>  
>  	if (symbol_conf.guestmount ||
>  	    symbol_conf.default_guest_vmlinux_name ||
> -- 
> 2.45.2
> 

Re: [PATCH v8 4/4] Add a test case for perf script -F +metric

[Namhyung Kim]

On Thu, Aug 01, 2024 at 02:28:44PM -0700, Andi Kleen wrote:
> Just a simple test

Can you please briefly describe what the test does?  Ideally with an
example output with 'perf test -vv'.

Thanks,
Namhyung

> 
> Signed-off-by: Andi Kleen <ak@linux.intel.com>
> 
> ----
> 
> v2: Avoid bashisms. Use noploop
> v3: Avoid false positive in shellcheck
> v4: Use :S in the test (Ian, Namhyung)
> ---
>  tools/perf/tests/shell/script.sh | 14 ++++++++++++++
>  1 file changed, 14 insertions(+)
> 
> diff --git a/tools/perf/tests/shell/script.sh b/tools/perf/tests/shell/script.sh
> index c1a603653662..e69c3548583a 100755
> --- a/tools/perf/tests/shell/script.sh
> +++ b/tools/perf/tests/shell/script.sh
> @@ -7,6 +7,7 @@ set -e
>  temp_dir=$(mktemp -d /tmp/perf-test-script.XXXXXXXXXX)
>  
>  perfdatafile="${temp_dir}/perf.data"
> +scriptoutput="${temp_dir}/script"
>  db_test="${temp_dir}/db_test.py"
>  
>  err=0
> @@ -88,8 +89,21 @@ test_parallel_perf()
>  	echo "parallel-perf test [Success]"
>  }
>  
> +test_metric()
> +{
> +	echo "script metric test"
> +	if ! perf list | grep -q cycles ; then return ; fi
> +	if ! perf list | grep -q instructions ; then return ; fi
> +	perf record -e '{cycles,instructions}:S' -o "${perfdatafile}" perf test -w noploop
> +	perf script -i "${perfdatafile}" -F +metric  > $scriptoutput
> +	test "`grep -c metric $scriptoutput`" -gt 5
> +	grep metric $scriptoutput | head
> +	echo "script metric test [Success]"
> +}
> +
>  test_db
>  test_parallel_perf
> +test_metric
>  
>  cleanup
>  
> -- 
> 2.45.2
> 

[PATCH v8 1/4] Create source symlink in perf object dir

[Andi Kleen]

Create a source symlink to the original source in the objdir.
This is similar to what the main kernel build script does.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/Makefile.perf | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 175e4c7898f0..d46892d8223b 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -163,6 +163,8 @@ ifneq ($(OUTPUT),)
 # for flex/bison parsers.
 VPATH += $(OUTPUT)
 export VPATH
+# create symlink to the original source
+SOURCE := $(shell ln -sf $(srctree)/tools/perf $(OUTPUT)/source)
 endif
 
 ifeq ($(V),1)
-- 
2.45.2