[PATCH v6 1/3] perf lock: Fix parse_lock_type which only retrieve one lock flag

[PATCH v6 1/3] perf lock: Fix parse_lock_type which only retrieve one lock flag

[Chun-Tse Shao]

`parse_lock_type` can only add the first lock flag in `lock_type_table`
given input `str`. For example, for `Y rwlock`, it only adds `rwlock:R`
into this perf session. Another example is for `-Y mutex`, it only adds
the mutex without `LCB_F_SPIN` flag. The patch fixes this issue, makes
sure both `rwlock:R` and `rwlock:W` will be added with `-Y rwlock`, and
so on.

Testing:
  $ ./perf lock con -ab -Y mutex,rwlock -- perf bench sched pipe
  # Running 'sched/pipe' benchmark:
  # Executed 1000000 pipe operations between two processes

       Total time: 9.313 [sec]

         9.313976 usecs/op
           107365 ops/sec
   contended   total wait     max wait     avg wait         type   caller

         176      1.65 ms     19.43 us      9.38 us        mutex   pipe_read+0x57
          34    180.14 us     10.93 us      5.30 us        mutex   pipe_write+0x50
           7     77.48 us     16.09 us     11.07 us        mutex   do_epoll_wait+0x24d
           7     74.70 us     13.50 us     10.67 us        mutex   do_epoll_wait+0x24d
           3     35.97 us     14.44 us     11.99 us     rwlock:W   ep_done_scan+0x2d
           3     35.00 us     12.23 us     11.66 us     rwlock:W   do_epoll_wait+0x255
           2     15.88 us     11.96 us      7.94 us     rwlock:W   do_epoll_wait+0x47c
           1     15.23 us     15.23 us     15.23 us     rwlock:W   do_epoll_wait+0x4d0
           1     14.26 us     14.26 us     14.26 us     rwlock:W   ep_done_scan+0x2d
           2     14.00 us      7.99 us      7.00 us        mutex   pipe_read+0x282
           1     12.29 us     12.29 us     12.29 us     rwlock:R   ep_poll_callback+0x35
           1     12.02 us     12.02 us     12.02 us     rwlock:W   do_epoll_ctl+0xb65
           1     10.25 us     10.25 us     10.25 us     rwlock:R   ep_poll_callback+0x35
           1      7.86 us      7.86 us      7.86 us        mutex   do_epoll_ctl+0x6c1
           1      5.04 us      5.04 us      5.04 us        mutex   do_epoll_ctl+0x3d4

Fixes: d783ea8f62c4 ("perf lock contention: Simplify parse_lock_type()")
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Chun-Tse Shao <ctshao@google.com>
---
Note:
  Rebased on tmp.perf-tools-next.
  Added `mutex-spin` based on Namhyung's comment after Reviewed-by tag.

 tools/perf/builtin-lock.c | 65 ++++++++++++++++++++++++---------------
 1 file changed, 40 insertions(+), 25 deletions(-)

diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 208c482daa56..a6203c622967 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -1484,8 +1484,7 @@ static const struct {
 	{ LCB_F_PERCPU | LCB_F_WRITE,	"pcpu-sem:W",	"percpu-rwsem" },
 	{ LCB_F_MUTEX,			"mutex",	"mutex" },
 	{ LCB_F_MUTEX | LCB_F_SPIN,	"mutex",	"mutex" },
-	/* alias for get_type_flag() */
-	{ LCB_F_MUTEX | LCB_F_SPIN,	"mutex-spin",	"mutex" },
+	{ LCB_F_MUTEX | LCB_F_SPIN,	"mutex-spin",	"mutex-spin" },
 };

 static const char *get_type_str(unsigned int flags)
@@ -1510,19 +1509,6 @@ static const char *get_type_name(unsigned int flags)
 	return "unknown";
 }

-static unsigned int get_type_flag(const char *str)
-{
-	for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) {
-		if (!strcmp(lock_type_table[i].name, str))
-			return lock_type_table[i].flags;
-	}
-	for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) {
-		if (!strcmp(lock_type_table[i].str, str))
-			return lock_type_table[i].flags;
-	}
-	return UINT_MAX;
-}
-
 static void lock_filter_finish(void)
 {
 	zfree(&filters.types);
@@ -2249,29 +2235,58 @@ static int parse_lock_type(const struct option *opt __maybe_unused, const char *
 			   int unset __maybe_unused)
 {
 	char *s, *tmp, *tok;
-	int ret = 0;

 	s = strdup(str);
 	if (s == NULL)
 		return -1;

 	for (tok = strtok_r(s, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) {
-		unsigned int flags = get_type_flag(tok);
+		bool found = false;

-		if (flags == -1U) {
-			pr_err("Unknown lock flags: %s\n", tok);
-			ret = -1;
-			break;
+		/* `tok` is `str` in `lock_type_table` if it contains ':'. */
+		if (strchr(tok, ':')) {
+			for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) {
+				if (!strcmp(lock_type_table[i].str, tok) &&
+				    add_lock_type(lock_type_table[i].flags)) {
+					found = true;
+					break;
+				}
+			}
+
+			if (!found) {
+				pr_err("Unknown lock flags name: %s\n", tok);
+				free(s);
+				return -1;
+			}
+
+			continue;
 		}

-		if (!add_lock_type(flags)) {
-			ret = -1;
-			break;
+		/*
+		 * Otherwise `tok` is `name` in `lock_type_table`.
+		 * Single lock name could contain multiple flags.
+		 */
+		for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) {
+			if (!strcmp(lock_type_table[i].name, tok)) {
+				if (add_lock_type(lock_type_table[i].flags)) {
+					found = true;
+				} else {
+					free(s);
+					return -1;
+				}
+			}
 		}
+
+		if (!found) {
+			pr_err("Unknown lock name: %s\n", tok);
+			free(s);
+			return -1;
+		}
+
 	}

 	free(s);
-	return ret;
+	return 0;
 }

 static bool add_lock_addr(unsigned long addr)
--
2.48.0.rc2.279.g1de40edade-goog

[PATCH v6 2/3] perf lock: Add percpu-rwsem for type filter

[Chun-Tse Shao]

percpu-rwsem was missing in man page. And for backward compatibility,
replace `pcpu-sem` with `percpu-rwsem` before parsing lock name.
Tested `./perf lock con -ab -Y pcpu-sem` and `./perf lock con -ab -Y
percpu-rwsem`

Fixes: 4f701063bfa2 ("perf lock contention: Show lock type with address")
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Chun-Tse Shao <ctshao@google.com>
---
Note:
  Rebased on tmp.perf-tools-next

 tools/perf/Documentation/perf-lock.txt | 4 ++--
 tools/perf/builtin-lock.c              | 3 +++
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt
index 57a940399de0..d3793054f7d3 100644
--- a/tools/perf/Documentation/perf-lock.txt
+++ b/tools/perf/Documentation/perf-lock.txt
@@ -187,8 +187,8 @@ CONTENTION OPTIONS
 	Show lock contention only for given lock types (comma separated list).
 	Available values are:
 	  semaphore, spinlock, rwlock, rwlock:R, rwlock:W, rwsem, rwsem:R, rwsem:W,
-	  rtmutex, rwlock-rt, rwlock-rt:R, rwlock-rt:W, pcpu-sem, pcpu-sem:R, pcpu-sem:W,
-	  mutex
+	  rtmutex, rwlock-rt, rwlock-rt:R, rwlock-rt:W, percpu-rwmem, pcpu-sem,
+	  pcpu-sem:R, pcpu-sem:W, mutex

 	Note that RW-variant of locks have :R and :W suffix.  Names without the
 	suffix are shortcuts for the both variants.  Ex) rwsem = rwsem:R + rwsem:W.
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index a6203c622967..258c4ccb96af 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -2265,7 +2265,10 @@ static int parse_lock_type(const struct option *opt __maybe_unused, const char *
 		/*
 		 * Otherwise `tok` is `name` in `lock_type_table`.
 		 * Single lock name could contain multiple flags.
+		 * Replace alias `pcpu-sem` with actual name `percpu-rwsem.
 		 */
+		if (!strcmp(tok, "pcpu-sem"))
+			tok = (char *)"percpu-rwsem";
 		for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) {
 			if (!strcmp(lock_type_table[i].name, tok)) {
 				if (add_lock_type(lock_type_table[i].flags)) {
--
2.48.0.rc2.279.g1de40edade-goog

[PATCH v6 3/3] perf lock: Rename fields in lock_type_table

[Chun-Tse Shao]

`lock_type_table` contains `name` and `str` which can be confusing.
Rename them to `flags_name` and `lock_name` and add descriptions to
enhance understanding.
Tested by building perf for x86.

Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Chun-Tse Shao <ctshao@google.com>
---
Note:
  Rebased on tmp.perf-tools-next

 tools/perf/builtin-lock.c | 33 +++++++++++++++++++--------------
 1 file changed, 19 insertions(+), 14 deletions(-)

diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 258c4ccb96af..ea3a62ba95d4 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -1468,8 +1468,13 @@ static void sort_result(void)

 static const struct {
 	unsigned int flags;
-	const char *str;
-	const char *name;
+	/*
+	 * Name of the lock flags (access), with delimeter ':'.
+	 * For example, rwsem:R of rwsem:W.
+	 */
+	const char *flags_name;
+	/* Name of the lock (type), for example, rwlock or rwsem. */
+	const char *lock_name;
 } lock_type_table[] = {
 	{ 0,				"semaphore",	"semaphore" },
 	{ LCB_F_SPIN,			"spinlock",	"spinlock" },
@@ -1487,24 +1492,24 @@ static const struct {
 	{ LCB_F_MUTEX | LCB_F_SPIN,	"mutex-spin",	"mutex-spin" },
 };

-static const char *get_type_str(unsigned int flags)
+static const char *get_type_flags_name(unsigned int flags)
 {
 	flags &= LCB_F_TYPE_MASK;

 	for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) {
 		if (lock_type_table[i].flags == flags)
-			return lock_type_table[i].str;
+			return lock_type_table[i].flags_name;
 	}
 	return "unknown";
 }

-static const char *get_type_name(unsigned int flags)
+static const char *get_type_lock_name(unsigned int flags)
 {
 	flags &= LCB_F_TYPE_MASK;

 	for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) {
 		if (lock_type_table[i].flags == flags)
-			return lock_type_table[i].name;
+			return lock_type_table[i].lock_name;
 	}
 	return "unknown";
 }
@@ -1617,7 +1622,7 @@ static void print_lock_stat_stdio(struct lock_contention *con, struct lock_stat

 	switch (aggr_mode) {
 	case LOCK_AGGR_CALLER:
-		fprintf(lock_output, "  %10s   %s\n", get_type_str(st->flags), st->name);
+		fprintf(lock_output, "  %10s   %s\n", get_type_flags_name(st->flags), st->name);
 		break;
 	case LOCK_AGGR_TASK:
 		pid = st->addr;
@@ -1627,7 +1632,7 @@ static void print_lock_stat_stdio(struct lock_contention *con, struct lock_stat
 		break;
 	case LOCK_AGGR_ADDR:
 		fprintf(lock_output, "  %016llx   %s (%s)\n", (unsigned long long)st->addr,
-			st->name, get_type_name(st->flags));
+			st->name, get_type_lock_name(st->flags));
 		break;
 	case LOCK_AGGR_CGROUP:
 		fprintf(lock_output, "  %s\n", st->name);
@@ -1668,7 +1673,7 @@ static void print_lock_stat_csv(struct lock_contention *con, struct lock_stat *s

 	switch (aggr_mode) {
 	case LOCK_AGGR_CALLER:
-		fprintf(lock_output, "%s%s %s", get_type_str(st->flags), sep, st->name);
+		fprintf(lock_output, "%s%s %s", get_type_flags_name(st->flags), sep, st->name);
 		if (verbose <= 0)
 			fprintf(lock_output, "\n");
 		break;
@@ -1680,7 +1685,7 @@ static void print_lock_stat_csv(struct lock_contention *con, struct lock_stat *s
 		break;
 	case LOCK_AGGR_ADDR:
 		fprintf(lock_output, "%llx%s %s%s %s\n", (unsigned long long)st->addr, sep,
-			st->name, sep, get_type_name(st->flags));
+			st->name, sep, get_type_lock_name(st->flags));
 		break;
 	case LOCK_AGGR_CGROUP:
 		fprintf(lock_output, "%s\n",st->name);
@@ -2243,10 +2248,10 @@ static int parse_lock_type(const struct option *opt __maybe_unused, const char *
 	for (tok = strtok_r(s, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) {
 		bool found = false;

-		/* `tok` is `str` in `lock_type_table` if it contains ':'. */
+		/* `tok` is a flags name if it contains ':'. */
 		if (strchr(tok, ':')) {
 			for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) {
-				if (!strcmp(lock_type_table[i].str, tok) &&
+				if (!strcmp(lock_type_table[i].flags_name, tok) &&
 				    add_lock_type(lock_type_table[i].flags)) {
 					found = true;
 					break;
@@ -2263,14 +2268,14 @@ static int parse_lock_type(const struct option *opt __maybe_unused, const char *
 		}

 		/*
-		 * Otherwise `tok` is `name` in `lock_type_table`.
+		 * Otherwise `tok` is a lock name.
 		 * Single lock name could contain multiple flags.
 		 * Replace alias `pcpu-sem` with actual name `percpu-rwsem.
 		 */
 		if (!strcmp(tok, "pcpu-sem"))
 			tok = (char *)"percpu-rwsem";
 		for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) {
-			if (!strcmp(lock_type_table[i].name, tok)) {
+			if (!strcmp(lock_type_table[i].lock_name, tok)) {
 				if (add_lock_type(lock_type_table[i].flags)) {
 					found = true;
 				} else {
--
2.48.0.rc2.279.g1de40edade-goog

Re: [PATCH v6 1/3] perf lock: Fix parse_lock_type which only retrieve one lock flag

[Namhyung Kim]

On Thu, 16 Jan 2025 15:58:14 -0800, Chun-Tse Shao wrote:

> `parse_lock_type` can only add the first lock flag in `lock_type_table`
> given input `str`. For example, for `Y rwlock`, it only adds `rwlock:R`
> into this perf session. Another example is for `-Y mutex`, it only adds
> the mutex without `LCB_F_SPIN` flag. The patch fixes this issue, makes
> sure both `rwlock:R` and `rwlock:W` will be added with `-Y rwlock`, and
> so on.
> 
> [...]

Applied to perf-tools-next, thanks!

Best regards,
Namhyung