* [PATCH] perf lock: Fix parse_lock_type which only retrieve one lock flag
@ 2024-11-21 4:45 Chun-Tse Shao
2024-11-21 7:18 ` Namhyung Kim
0 siblings, 1 reply; 3+ messages in thread
From: Chun-Tse Shao @ 2024-11-21 4:45 UTC (permalink / raw)
To: linux-kernel
Cc: Chun-Tse Shao, Peter Zijlstra, Ingo Molnar,
Arnaldo Carvalho de Melo, Mark Rutland, Alexander Shishkin,
Jiri Olsa, Namhyung Kim
`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 rwlock,mutex -- perf bench sched pipe
# Running 'sched/pipe' benchmark:
# Executed 1000000 pipe operations between two processes
Total time: 7.870 [sec]
7.870224 usecs/op
127061 ops/sec
contended total wait max wait avg wait type caller
122 1.01 ms 18.73 us 8.32 us mutex pipe_read+0x57
33 149.06 us 8.88 us 4.52 us mutex pipe_write+0x50
5 56.06 us 15.07 us 11.21 us mutex do_epoll_wait+0x24d
2 26.43 us 14.62 us 13.22 us mutex do_epoll_wait+0x24d
2 21.51 us 15.68 us 10.76 us mutex pipe_read+0x282
2 20.57 us 10.74 us 10.29 us mutex do_epoll_ctl+0x3d4
1 8.58 us 8.58 us 8.58 us rwlock:W do_epoll_wait+0x255
1 8.38 us 8.38 us 8.38 us rwlock:W do_epoll_ctl+0xb65
1 8.11 us 8.11 us 8.11 us rwlock:R ep_poll_callback+0x35
1 5.49 us 5.49 us 5.49 us mutex do_epoll_ctl+0x6c1
Signed-off-by: Chun-Tse Shao <ctshao@google.com>
---
tools/perf/builtin-lock.c | 118 +++++++++++++++++++++++---------------
1 file changed, 71 insertions(+), 47 deletions(-)
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 062e2b56a2ab..2692b8e9eb9a 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -1575,61 +1575,57 @@ static void sort_result(void)
static const struct {
unsigned int flags;
- const char *str;
+ /* Name of the lock, it is unique and 1-1 mapping to flags */
const char *name;
+ /*
+ * Name of the group this lock belongs to.
+ * For example, both rwlock:R and rwlock:W belong to rwlock.
+ * This is used for reverse parsing while user specify the group name (ex. mutex/rwlock),
+ * And for symbol name in LOCK_AGGR_ADDR mode.
+ */
+ const char *affiliated_group_name;
+ /*
+ * This is used for caller type in LOCK_AGGR_CALLER mode.
+ */
+ const char *caller_type;
} lock_type_table[] = {
- { 0, "semaphore", "semaphore" },
- { LCB_F_SPIN, "spinlock", "spinlock" },
- { LCB_F_SPIN | LCB_F_READ, "rwlock:R", "rwlock" },
- { LCB_F_SPIN | LCB_F_WRITE, "rwlock:W", "rwlock" },
- { LCB_F_READ, "rwsem:R", "rwsem" },
- { LCB_F_WRITE, "rwsem:W", "rwsem" },
- { LCB_F_RT, "rt-mutex", "rt-mutex" },
- { LCB_F_RT | LCB_F_READ, "rwlock-rt:R", "rwlock-rt" },
- { LCB_F_RT | LCB_F_WRITE, "rwlock-rt:W", "rwlock-rt" },
- { LCB_F_PERCPU | LCB_F_READ, "pcpu-sem:R", "percpu-rwsem" },
- { 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" },
+ { 0, "semaphore", "semaphore", "semaphore" },
+ { LCB_F_SPIN, "spinlock", "spinlock", "spinlock" },
+ { LCB_F_SPIN | LCB_F_READ, "rwlock:R", "rwlock", "rwlock:R" },
+ { LCB_F_SPIN | LCB_F_WRITE, "rwlock:W", "rwlock", "rwlock:W" },
+ { LCB_F_READ, "rwsem:R", "rwsem", "rwsem:R" },
+ { LCB_F_WRITE, "rwsem:W", "rwsem", "rwsem:W" },
+ { LCB_F_RT, "rt-mutex", "rt-mutex", "rt-mutex" },
+ { LCB_F_RT | LCB_F_READ, "rwlock-rt:R", "rwlock-rt", "rwlock-rt:R" },
+ { LCB_F_RT | LCB_F_WRITE, "rwlock-rt:W", "rwlock-rt", "rwlock-rt:W" },
+ { LCB_F_PERCPU | LCB_F_READ, "pcpu-sem:R", "percpu-rwsem", "pcpu-sem:R" },
+ { LCB_F_PERCPU | LCB_F_WRITE, "pcpu-sem:W", "percpu-rwsem", "pcpu-sem:W" },
+ { LCB_F_MUTEX, "mutex-nospin", "mutex", "mutex" },
+ { LCB_F_MUTEX | LCB_F_SPIN, "mutex-spin", "mutex", "mutex" },
};
-static const char *get_type_str(unsigned int flags)
+static const char *get_lock_caller_type(unsigned int flags)
{
flags &= LCB_F_MAX_FLAGS - 1;
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].caller_type;
}
return "unknown";
}
-static const char *get_type_name(unsigned int flags)
+static const char *get_lock_affiliated_group_name(unsigned int flags)
{
flags &= LCB_F_MAX_FLAGS - 1;
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].affiliated_group_name;
}
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);
@@ -1732,7 +1728,8 @@ 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_lock_caller_type(st->flags), st->name);
break;
case LOCK_AGGR_TASK:
pid = st->addr;
@@ -1742,7 +1739,7 @@ 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_lock_affiliated_group_name(st->flags));
break;
case LOCK_AGGR_CGROUP:
fprintf(lock_output, " %s\n", st->name);
@@ -1783,7 +1780,8 @@ 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_lock_caller_type(st->flags), sep, st->name);
if (verbose <= 0)
fprintf(lock_output, "\n");
break;
@@ -1795,7 +1793,7 @@ 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_lock_affiliated_group_name(st->flags));
break;
case LOCK_AGGR_CGROUP:
fprintf(lock_output, "%s\n",st->name);
@@ -2333,6 +2331,7 @@ static int parse_max_stack(const struct option *opt, const char *str,
return 0;
}
+
static bool add_lock_type(unsigned int flags)
{
unsigned int *tmp;
@@ -2350,29 +2349,54 @@ 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;
+ /* Traverse lock name first. */
+ 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;
+ break;
+ }
+ pr_err("Failed to alloc lock: %s\n", tok);
+ free(s);
+ return -1;
+ }
}
+ if (found)
+ continue;
- if (!add_lock_type(flags)) {
- ret = -1;
- break;
+ /*
+ * If `tok` can not be found in lock name, look up the lock affiliated group
+ * instead. A group would contain more than one lock flag.
+ */
+ for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) {
+ if (!strcmp(lock_type_table[i].affiliated_group_name, tok)) {
+ if (add_lock_type(lock_type_table[i].flags)) {
+ found = true;
+ } else {
+ pr_err("Failed to alloc lock: %s\n", tok);
+ free(s);
+ return -1;
+ }
+ }
+ }
+
+ if (!found) {
+ pr_err("Unknown lock flags: %s\n", tok);
+ free(s);
+ return -1;
}
}
free(s);
- return ret;
+ return 0;
}
static bool add_lock_addr(unsigned long addr)
--
2.47.0.371.ga323438b13-goog
^ permalink raw reply related [flat|nested] 3+ messages in thread* Re: [PATCH] perf lock: Fix parse_lock_type which only retrieve one lock flag 2024-11-21 4:45 [PATCH] perf lock: Fix parse_lock_type which only retrieve one lock flag Chun-Tse Shao @ 2024-11-21 7:18 ` Namhyung Kim 2024-11-22 0:34 ` Chun-Tse Shao 0 siblings, 1 reply; 3+ messages in thread From: Namhyung Kim @ 2024-11-21 7:18 UTC (permalink / raw) To: Chun-Tse Shao Cc: linux-kernel, Peter Zijlstra, Ingo Molnar, Arnaldo Carvalho de Melo, Mark Rutland, Alexander Shishkin, Jiri Olsa Hi CT, On Thu, Nov 21, 2024 at 04:45:51AM +0000, 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. Thanks for working on this. I think I broke it at some point. > > Testing: > $ ./perf lock con -ab -Y rwlock,mutex -- perf bench sched pipe > # Running 'sched/pipe' benchmark: > # Executed 1000000 pipe operations between two processes > > Total time: 7.870 [sec] > > 7.870224 usecs/op > 127061 ops/sec > contended total wait max wait avg wait type caller > > 122 1.01 ms 18.73 us 8.32 us mutex pipe_read+0x57 > 33 149.06 us 8.88 us 4.52 us mutex pipe_write+0x50 > 5 56.06 us 15.07 us 11.21 us mutex do_epoll_wait+0x24d > 2 26.43 us 14.62 us 13.22 us mutex do_epoll_wait+0x24d > 2 21.51 us 15.68 us 10.76 us mutex pipe_read+0x282 > 2 20.57 us 10.74 us 10.29 us mutex do_epoll_ctl+0x3d4 > 1 8.58 us 8.58 us 8.58 us rwlock:W do_epoll_wait+0x255 > 1 8.38 us 8.38 us 8.38 us rwlock:W do_epoll_ctl+0xb65 > 1 8.11 us 8.11 us 8.11 us rwlock:R ep_poll_callback+0x35 > 1 5.49 us 5.49 us 5.49 us mutex do_epoll_ctl+0x6c1 It should have Fixes: d783ea8f62c4 ("perf lock contention: Simplify parse_lock_type()") > > Signed-off-by: Chun-Tse Shao <ctshao@google.com> > --- > tools/perf/builtin-lock.c | 118 +++++++++++++++++++++++--------------- > 1 file changed, 71 insertions(+), 47 deletions(-) > > diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c > index 062e2b56a2ab..2692b8e9eb9a 100644 > --- a/tools/perf/builtin-lock.c > +++ b/tools/perf/builtin-lock.c > @@ -1575,61 +1575,57 @@ static void sort_result(void) > > static const struct { > unsigned int flags; > - const char *str; > + /* Name of the lock, it is unique and 1-1 mapping to flags */ > const char *name; > + /* > + * Name of the group this lock belongs to. > + * For example, both rwlock:R and rwlock:W belong to rwlock. > + * This is used for reverse parsing while user specify the group name (ex. mutex/rwlock), > + * And for symbol name in LOCK_AGGR_ADDR mode. > + */ > + const char *affiliated_group_name; > + /* > + * This is used for caller type in LOCK_AGGR_CALLER mode. > + */ > + const char *caller_type; I admit that the 'str' and 'name' are not good but I'm not sure if we need those 3 different names because they are mostly the same. Maybe we have rename the original fields to 'name' and 'group'? > } lock_type_table[] = { > - { 0, "semaphore", "semaphore" }, > - { LCB_F_SPIN, "spinlock", "spinlock" }, > - { LCB_F_SPIN | LCB_F_READ, "rwlock:R", "rwlock" }, > - { LCB_F_SPIN | LCB_F_WRITE, "rwlock:W", "rwlock" }, > - { LCB_F_READ, "rwsem:R", "rwsem" }, > - { LCB_F_WRITE, "rwsem:W", "rwsem" }, > - { LCB_F_RT, "rt-mutex", "rt-mutex" }, > - { LCB_F_RT | LCB_F_READ, "rwlock-rt:R", "rwlock-rt" }, > - { LCB_F_RT | LCB_F_WRITE, "rwlock-rt:W", "rwlock-rt" }, > - { LCB_F_PERCPU | LCB_F_READ, "pcpu-sem:R", "percpu-rwsem" }, > - { 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" }, > + { 0, "semaphore", "semaphore", "semaphore" }, > + { LCB_F_SPIN, "spinlock", "spinlock", "spinlock" }, > + { LCB_F_SPIN | LCB_F_READ, "rwlock:R", "rwlock", "rwlock:R" }, > + { LCB_F_SPIN | LCB_F_WRITE, "rwlock:W", "rwlock", "rwlock:W" }, > + { LCB_F_READ, "rwsem:R", "rwsem", "rwsem:R" }, > + { LCB_F_WRITE, "rwsem:W", "rwsem", "rwsem:W" }, > + { LCB_F_RT, "rt-mutex", "rt-mutex", "rt-mutex" }, > + { LCB_F_RT | LCB_F_READ, "rwlock-rt:R", "rwlock-rt", "rwlock-rt:R" }, > + { LCB_F_RT | LCB_F_WRITE, "rwlock-rt:W", "rwlock-rt", "rwlock-rt:W" }, > + { LCB_F_PERCPU | LCB_F_READ, "pcpu-sem:R", "percpu-rwsem", "pcpu-sem:R" }, > + { LCB_F_PERCPU | LCB_F_WRITE, "pcpu-sem:W", "percpu-rwsem", "pcpu-sem:W" }, I've realized that it doesn't match with the documentation. It should match with 'pcpu-sem'. Maybe we can replace the 'pcpu-sem' string in the parse_lock_type() to 'percpu-rwsem'. > + { LCB_F_MUTEX, "mutex-nospin", "mutex", "mutex" }, > + { LCB_F_MUTEX | LCB_F_SPIN, "mutex-spin", "mutex", "mutex" }, These are not for users and we don't track mutex-spinning precisely (yet). So I think we can name both of them simply as "mutex". { LCB_F_MUTEX, "mutex", "mutex" }, { LCB_F_MUTEX | LCB_F_SPIN "mutex", "mutex" }, And remove the last alias entry. > }; > > -static const char *get_type_str(unsigned int flags) > +static const char *get_lock_caller_type(unsigned int flags) > { > flags &= LCB_F_MAX_FLAGS - 1; > > 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].caller_type; > } > return "unknown"; > } > > -static const char *get_type_name(unsigned int flags) > +static const char *get_lock_affiliated_group_name(unsigned int flags) > { > flags &= LCB_F_MAX_FLAGS - 1; > > 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].affiliated_group_name; > } > 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); > @@ -1732,7 +1728,8 @@ 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_lock_caller_type(st->flags), st->name); > break; > case LOCK_AGGR_TASK: > pid = st->addr; > @@ -1742,7 +1739,7 @@ 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_lock_affiliated_group_name(st->flags)); > break; > case LOCK_AGGR_CGROUP: > fprintf(lock_output, " %s\n", st->name); > @@ -1783,7 +1780,8 @@ 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_lock_caller_type(st->flags), sep, st->name); > if (verbose <= 0) > fprintf(lock_output, "\n"); > break; > @@ -1795,7 +1793,7 @@ 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_lock_affiliated_group_name(st->flags)); > break; > case LOCK_AGGR_CGROUP: > fprintf(lock_output, "%s\n",st->name); > @@ -2333,6 +2331,7 @@ static int parse_max_stack(const struct option *opt, const char *str, > return 0; > } > > + > static bool add_lock_type(unsigned int flags) > { > unsigned int *tmp; > @@ -2350,29 +2349,54 @@ 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; > + /* Traverse lock name first. */ > + 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; > + break; > + } > + pr_err("Failed to alloc lock: %s\n", tok); > + free(s); > + return -1; > + } > } > + if (found) > + continue; Then I think the logic can be like this. if (strchr(tok, ':')) { flags = get_type_flag(tok); add_lock_type(flag); continue; } if (!strcmp(tok, "pcpu-sem")) tok = "percpu-rwsem"; for (i = 0; i < ARRAY_SIZE(lock_type_table); i++) { if (!strcmp(lock_type_table[i].group, tok)) add_lock_type(...); } Thanks, Namhyung > > - if (!add_lock_type(flags)) { > - ret = -1; > - break; > + /* > + * If `tok` can not be found in lock name, look up the lock affiliated group > + * instead. A group would contain more than one lock flag. > + */ > + for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) { > + if (!strcmp(lock_type_table[i].affiliated_group_name, tok)) { > + if (add_lock_type(lock_type_table[i].flags)) { > + found = true; > + } else { > + pr_err("Failed to alloc lock: %s\n", tok); > + free(s); > + return -1; > + } > + } > + } > + > + if (!found) { > + pr_err("Unknown lock flags: %s\n", tok); > + free(s); > + return -1; > } > } > > free(s); > - return ret; > + return 0; > } > > static bool add_lock_addr(unsigned long addr) > -- > 2.47.0.371.ga323438b13-goog > ^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH] perf lock: Fix parse_lock_type which only retrieve one lock flag 2024-11-21 7:18 ` Namhyung Kim @ 2024-11-22 0:34 ` Chun-Tse Shao 0 siblings, 0 replies; 3+ messages in thread From: Chun-Tse Shao @ 2024-11-22 0:34 UTC (permalink / raw) To: Namhyung Kim Cc: linux-kernel, Peter Zijlstra, Ingo Molnar, Arnaldo Carvalho de Melo, Mark Rutland, Alexander Shishkin, Jiri Olsa Thank you Namhyung! please check my patch v2: https://lore.kernel.org/all/20241122002752.4179915-1-ctshao@google.com On Wed, Nov 20, 2024 at 11:18 PM Namhyung Kim <namhyung@kernel.org> wrote: > > Hi CT, > > On Thu, Nov 21, 2024 at 04:45:51AM +0000, 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. > > Thanks for working on this. I think I broke it at some point. > > > > > Testing: > > $ ./perf lock con -ab -Y rwlock,mutex -- perf bench sched pipe > > # Running 'sched/pipe' benchmark: > > # Executed 1000000 pipe operations between two processes > > > > Total time: 7.870 [sec] > > > > 7.870224 usecs/op > > 127061 ops/sec > > contended total wait max wait avg wait type caller > > > > 122 1.01 ms 18.73 us 8.32 us mutex pipe_read+0x57 > > 33 149.06 us 8.88 us 4.52 us mutex pipe_write+0x50 > > 5 56.06 us 15.07 us 11.21 us mutex do_epoll_wait+0x24d > > 2 26.43 us 14.62 us 13.22 us mutex do_epoll_wait+0x24d > > 2 21.51 us 15.68 us 10.76 us mutex pipe_read+0x282 > > 2 20.57 us 10.74 us 10.29 us mutex do_epoll_ctl+0x3d4 > > 1 8.58 us 8.58 us 8.58 us rwlock:W do_epoll_wait+0x255 > > 1 8.38 us 8.38 us 8.38 us rwlock:W do_epoll_ctl+0xb65 > > 1 8.11 us 8.11 us 8.11 us rwlock:R ep_poll_callback+0x35 > > 1 5.49 us 5.49 us 5.49 us mutex do_epoll_ctl+0x6c1 > > It should have > > Fixes: d783ea8f62c4 ("perf lock contention: Simplify parse_lock_type()") Done. > > > > > Signed-off-by: Chun-Tse Shao <ctshao@google.com> > > --- > > tools/perf/builtin-lock.c | 118 +++++++++++++++++++++++--------------- > > 1 file changed, 71 insertions(+), 47 deletions(-) > > > > diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c > > index 062e2b56a2ab..2692b8e9eb9a 100644 > > --- a/tools/perf/builtin-lock.c > > +++ b/tools/perf/builtin-lock.c > > @@ -1575,61 +1575,57 @@ static void sort_result(void) > > > > static const struct { > > unsigned int flags; > > - const char *str; > > + /* Name of the lock, it is unique and 1-1 mapping to flags */ > > const char *name; > > + /* > > + * Name of the group this lock belongs to. > > + * For example, both rwlock:R and rwlock:W belong to rwlock. > > + * This is used for reverse parsing while user specify the group name (ex. mutex/rwlock), > > + * And for symbol name in LOCK_AGGR_ADDR mode. > > + */ > > + const char *affiliated_group_name; > > + /* > > + * This is used for caller type in LOCK_AGGR_CALLER mode. > > + */ > > + const char *caller_type; > > I admit that the 'str' and 'name' are not good but I'm not sure if we > need those 3 different names because they are mostly the same. Maybe we > have rename the original fields to 'name' and 'group'? Done. > > > > } lock_type_table[] = { > > - { 0, "semaphore", "semaphore" }, > > - { LCB_F_SPIN, "spinlock", "spinlock" }, > > - { LCB_F_SPIN | LCB_F_READ, "rwlock:R", "rwlock" }, > > - { LCB_F_SPIN | LCB_F_WRITE, "rwlock:W", "rwlock" }, > > - { LCB_F_READ, "rwsem:R", "rwsem" }, > > - { LCB_F_WRITE, "rwsem:W", "rwsem" }, > > - { LCB_F_RT, "rt-mutex", "rt-mutex" }, > > - { LCB_F_RT | LCB_F_READ, "rwlock-rt:R", "rwlock-rt" }, > > - { LCB_F_RT | LCB_F_WRITE, "rwlock-rt:W", "rwlock-rt" }, > > - { LCB_F_PERCPU | LCB_F_READ, "pcpu-sem:R", "percpu-rwsem" }, > > - { 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" }, > > + { 0, "semaphore", "semaphore", "semaphore" }, > > + { LCB_F_SPIN, "spinlock", "spinlock", "spinlock" }, > > + { LCB_F_SPIN | LCB_F_READ, "rwlock:R", "rwlock", "rwlock:R" }, > > + { LCB_F_SPIN | LCB_F_WRITE, "rwlock:W", "rwlock", "rwlock:W" }, > > + { LCB_F_READ, "rwsem:R", "rwsem", "rwsem:R" }, > > + { LCB_F_WRITE, "rwsem:W", "rwsem", "rwsem:W" }, > > + { LCB_F_RT, "rt-mutex", "rt-mutex", "rt-mutex" }, > > + { LCB_F_RT | LCB_F_READ, "rwlock-rt:R", "rwlock-rt", "rwlock-rt:R" }, > > + { LCB_F_RT | LCB_F_WRITE, "rwlock-rt:W", "rwlock-rt", "rwlock-rt:W" }, > > + { LCB_F_PERCPU | LCB_F_READ, "pcpu-sem:R", "percpu-rwsem", "pcpu-sem:R" }, > > + { LCB_F_PERCPU | LCB_F_WRITE, "pcpu-sem:W", "percpu-rwsem", "pcpu-sem:W" }, > > I've realized that it doesn't match with the documentation. It should > match with 'pcpu-sem'. Maybe we can replace the 'pcpu-sem' string in > the parse_lock_type() to 'percpu-rwsem'. Done. > > > + { LCB_F_MUTEX, "mutex-nospin", "mutex", "mutex" }, > > + { LCB_F_MUTEX | LCB_F_SPIN, "mutex-spin", "mutex", "mutex" }, > > These are not for users and we don't track mutex-spinning precisely > (yet). So I think we can name both of them simply as "mutex". > > { LCB_F_MUTEX, "mutex", "mutex" }, > { LCB_F_MUTEX | LCB_F_SPIN "mutex", "mutex" }, > > And remove the last alias entry. Done. > > > }; > > > > -static const char *get_type_str(unsigned int flags) > > +static const char *get_lock_caller_type(unsigned int flags) > > { > > flags &= LCB_F_MAX_FLAGS - 1; > > > > 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].caller_type; > > } > > return "unknown"; > > } > > > > -static const char *get_type_name(unsigned int flags) > > +static const char *get_lock_affiliated_group_name(unsigned int flags) > > { > > flags &= LCB_F_MAX_FLAGS - 1; > > > > 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].affiliated_group_name; > > } > > 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); > > @@ -1732,7 +1728,8 @@ 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_lock_caller_type(st->flags), st->name); > > break; > > case LOCK_AGGR_TASK: > > pid = st->addr; > > @@ -1742,7 +1739,7 @@ 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_lock_affiliated_group_name(st->flags)); > > break; > > case LOCK_AGGR_CGROUP: > > fprintf(lock_output, " %s\n", st->name); > > @@ -1783,7 +1780,8 @@ 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_lock_caller_type(st->flags), sep, st->name); > > if (verbose <= 0) > > fprintf(lock_output, "\n"); > > break; > > @@ -1795,7 +1793,7 @@ 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_lock_affiliated_group_name(st->flags)); > > break; > > case LOCK_AGGR_CGROUP: > > fprintf(lock_output, "%s\n",st->name); > > @@ -2333,6 +2331,7 @@ static int parse_max_stack(const struct option *opt, const char *str, > > return 0; > > } > > > > + > > static bool add_lock_type(unsigned int flags) > > { > > unsigned int *tmp; > > @@ -2350,29 +2349,54 @@ 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; > > + /* Traverse lock name first. */ > > + 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; > > + break; > > + } > > + pr_err("Failed to alloc lock: %s\n", tok); > > + free(s); > > + return -1; > > + } > > } > > + if (found) > > + continue; > > Then I think the logic can be like this. > > if (strchr(tok, ':')) { > flags = get_type_flag(tok); > add_lock_type(flag); > continue; > } > > if (!strcmp(tok, "pcpu-sem")) > tok = "percpu-rwsem"; > > for (i = 0; i < ARRAY_SIZE(lock_type_table); i++) { > if (!strcmp(lock_type_table[i].group, tok)) > add_lock_type(...); > } Done. I think `get_type_flag` would be unnecessary since it's only called once. > > Thanks, > Namhyung > > > > > - if (!add_lock_type(flags)) { > > - ret = -1; > > - break; > > + /* > > + * If `tok` can not be found in lock name, look up the lock affiliated group > > + * instead. A group would contain more than one lock flag. > > + */ > > + for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) { > > + if (!strcmp(lock_type_table[i].affiliated_group_name, tok)) { > > + if (add_lock_type(lock_type_table[i].flags)) { > > + found = true; > > + } else { > > + pr_err("Failed to alloc lock: %s\n", tok); > > + free(s); > > + return -1; > > + } > > + } > > + } > > + > > + if (!found) { > > + pr_err("Unknown lock flags: %s\n", tok); > > + free(s); > > + return -1; > > } > > } > > > > free(s); > > - return ret; > > + return 0; > > } > > > > static bool add_lock_addr(unsigned long addr) > > -- > > 2.47.0.371.ga323438b13-goog > > ^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2024-11-22 0:34 UTC | newest] Thread overview: 3+ messages (download: mbox.gz follow: Atom feed -- links below jump to the message on this page -- 2024-11-21 4:45 [PATCH] perf lock: Fix parse_lock_type which only retrieve one lock flag Chun-Tse Shao 2024-11-21 7:18 ` Namhyung Kim 2024-11-22 0:34 ` Chun-Tse Shao
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox