[PATCH v3 4/4] perf lock contention: Handle slab objects in -L/--lock-filter option
From: Namhyung Kim
Date: Fri Dec 20 2024 - 01:02:26 EST
This is to filter lock contention from specific slab objects only.
Like in the lock symbol output, we can use '&' prefix to filter slab
object names.
root@virtme-ng:/home/namhyung/project/linux# tools/perf/perf lock con -abl sleep 1
contended total wait max wait avg wait address symbol
3 14.99 us 14.44 us 5.00 us ffffffff851c0940 pack_mutex (mutex)
2 2.75 us 2.56 us 1.38 us ffff98d7031fb498 &task_struct (mutex)
4 1.42 us 557 ns 355 ns ffff98d706311400 &kmalloc-cg-512 (mutex)
2 953 ns 714 ns 476 ns ffffffff851c3620 delayed_uprobe_lock (mutex)
1 929 ns 929 ns 929 ns ffff98d7031fb538 &task_struct (mutex)
3 561 ns 210 ns 187 ns ffffffff84a8b3a0 text_mutex (mutex)
1 479 ns 479 ns 479 ns ffffffff851b4cf8 tracepoint_srcu_srcu_usage (mutex)
2 320 ns 195 ns 160 ns ffffffff851cf840 pcpu_alloc_mutex (mutex)
1 212 ns 212 ns 212 ns ffff98d7031784d8 &signal_cache (mutex)
1 177 ns 177 ns 177 ns ffffffff851b4c28 tracepoint_srcu_srcu_usage (mutex)
With the filter, it can show contentions from the task_struct only.
root@virtme-ng:/home/namhyung/project/linux# tools/perf/perf lock con -abl -L '&task_struct' sleep 1
contended total wait max wait avg wait address symbol
2 1.97 us 1.71 us 987 ns ffff98d7032fd658 &task_struct (mutex)
1 1.20 us 1.20 us 1.20 us ffff98d7032fd6f8 &task_struct (mutex)
It can work with other aggregation mode:
root@virtme-ng:/home/namhyung/project/linux# tools/perf/perf lock con -ab -L '&task_struct' sleep 1
contended total wait max wait avg wait type caller
1 25.10 us 25.10 us 25.10 us mutex perf_event_exit_task+0x39
1 21.60 us 21.60 us 21.60 us mutex futex_exit_release+0x21
1 5.56 us 5.56 us 5.56 us mutex futex_exec_release+0x21
Acked-by: Ian Rogers <irogers@xxxxxxxxxx>
Signed-off-by: Namhyung Kim <namhyung@xxxxxxxxxx>
---
tools/perf/builtin-lock.c | 35 ++++++++++++++++
tools/perf/util/bpf_lock_contention.c | 40 ++++++++++++++++++-
.../perf/util/bpf_skel/lock_contention.bpf.c | 21 +++++++++-
tools/perf/util/lock-contention.h | 2 +
4 files changed, 95 insertions(+), 3 deletions(-)
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index d9f3477d2b02b612..208c482daa56ef93 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -1539,6 +1539,12 @@ static void lock_filter_finish(void)
zfree(&filters.cgrps);
filters.nr_cgrps = 0;
+
+ for (int i = 0; i < filters.nr_slabs; i++)
+ free(filters.slabs[i]);
+
+ zfree(&filters.slabs);
+ filters.nr_slabs = 0;
}
static void sort_contention_result(void)
@@ -2305,6 +2311,27 @@ static bool add_lock_sym(char *name)
return true;
}
+static bool add_lock_slab(char *name)
+{
+ char **tmp;
+ char *sym = strdup(name);
+
+ if (sym == NULL) {
+ pr_err("Memory allocation failure\n");
+ return false;
+ }
+
+ tmp = realloc(filters.slabs, (filters.nr_slabs + 1) * sizeof(*filters.slabs));
+ if (tmp == NULL) {
+ pr_err("Memory allocation failure\n");
+ return false;
+ }
+
+ tmp[filters.nr_slabs++] = sym;
+ filters.slabs = tmp;
+ return true;
+}
+
static int parse_lock_addr(const struct option *opt __maybe_unused, const char *str,
int unset __maybe_unused)
{
@@ -2328,6 +2355,14 @@ static int parse_lock_addr(const struct option *opt __maybe_unused, const char *
continue;
}
+ if (*tok == '&') {
+ if (!add_lock_slab(tok + 1)) {
+ ret = -1;
+ break;
+ }
+ continue;
+ }
+
/*
* At this moment, we don't have kernel symbols. Save the symbols
* in a separate list and resolve them to addresses later.
diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c
index a31ace04cb5e7a8f..fc8666222399c995 100644
--- a/tools/perf/util/bpf_lock_contention.c
+++ b/tools/perf/util/bpf_lock_contention.c
@@ -112,7 +112,7 @@ static void exit_slab_cache_iter(void)
int lock_contention_prepare(struct lock_contention *con)
{
int i, fd;
- int ncpus = 1, ntasks = 1, ntypes = 1, naddrs = 1, ncgrps = 1;
+ int ncpus = 1, ntasks = 1, ntypes = 1, naddrs = 1, ncgrps = 1, nslabs = 1;
struct evlist *evlist = con->evlist;
struct target *target = con->target;
@@ -201,6 +201,13 @@ int lock_contention_prepare(struct lock_contention *con)
check_slab_cache_iter(con);
+ if (con->filters->nr_slabs && has_slab_iter) {
+ skel->rodata->has_slab = 1;
+ nslabs = con->filters->nr_slabs;
+ }
+
+ bpf_map__set_max_entries(skel->maps.slab_filter, nslabs);
+
if (lock_contention_bpf__load(skel) < 0) {
pr_err("Failed to load lock-contention BPF skeleton\n");
return -1;
@@ -271,6 +278,36 @@ int lock_contention_prepare(struct lock_contention *con)
bpf_program__set_autoload(skel->progs.collect_lock_syms, false);
lock_contention_bpf__attach(skel);
+
+ /* run the slab iterator after attaching */
+ run_slab_cache_iter();
+
+ if (con->filters->nr_slabs) {
+ u8 val = 1;
+ int cache_fd;
+ long key, *prev_key;
+
+ fd = bpf_map__fd(skel->maps.slab_filter);
+
+ /* Read the slab cache map and build a hash with its address */
+ cache_fd = bpf_map__fd(skel->maps.slab_caches);
+ prev_key = NULL;
+ while (!bpf_map_get_next_key(cache_fd, prev_key, &key)) {
+ struct slab_cache_data data;
+
+ if (bpf_map_lookup_elem(cache_fd, &key, &data) < 0)
+ break;
+
+ for (i = 0; i < con->filters->nr_slabs; i++) {
+ if (!strcmp(con->filters->slabs[i], data.name)) {
+ bpf_map_update_elem(fd, &key, &val, BPF_ANY);
+ break;
+ }
+ }
+ prev_key = &key;
+ }
+ }
+
return 0;
}
@@ -396,7 +433,6 @@ static void account_end_timestamp(struct lock_contention *con)
int lock_contention_start(void)
{
- run_slab_cache_iter();
skel->bss->enabled = 1;
return 0;
}
diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c
index 7182eb559496e34e..6c771ef751d83b43 100644
--- a/tools/perf/util/bpf_skel/lock_contention.bpf.c
+++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c
@@ -100,6 +100,13 @@ struct {
__uint(max_entries, 1);
} cgroup_filter SEC(".maps");
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(key_size, sizeof(long));
+ __uint(value_size, sizeof(__u8));
+ __uint(max_entries, 1);
+} slab_filter SEC(".maps");
+
struct {
__uint(type, BPF_MAP_TYPE_HASH);
__uint(key_size, sizeof(long));
@@ -131,6 +138,7 @@ const volatile int has_task;
const volatile int has_type;
const volatile int has_addr;
const volatile int has_cgroup;
+const volatile int has_slab;
const volatile int needs_callstack;
const volatile int stack_skip;
const volatile int lock_owner;
@@ -213,7 +221,7 @@ static inline int can_record(u64 *ctx)
__u64 addr = ctx[0];
ok = bpf_map_lookup_elem(&addr_filter, &addr);
- if (!ok)
+ if (!ok && !has_slab)
return 0;
}
@@ -226,6 +234,17 @@ static inline int can_record(u64 *ctx)
return 0;
}
+ if (has_slab && bpf_get_kmem_cache) {
+ __u8 *ok;
+ __u64 addr = ctx[0];
+ long kmem_cache_addr;
+
+ kmem_cache_addr = (long)bpf_get_kmem_cache(addr);
+ ok = bpf_map_lookup_elem(&slab_filter, &kmem_cache_addr);
+ if (!ok)
+ return 0;
+ }
+
return 1;
}
diff --git a/tools/perf/util/lock-contention.h b/tools/perf/util/lock-contention.h
index bd71fb73825aa8e1..a09f7fe877df8184 100644
--- a/tools/perf/util/lock-contention.h
+++ b/tools/perf/util/lock-contention.h
@@ -10,10 +10,12 @@ struct lock_filter {
int nr_addrs;
int nr_syms;
int nr_cgrps;
+ int nr_slabs;
unsigned int *types;
unsigned long *addrs;
char **syms;
u64 *cgrps;
+ char **slabs;
};
struct lock_stat {
--
2.47.1.613.gc27f4b7a9f-goog