mirror of
https://github.com/torvalds/linux.git
synced 2026-05-29 17:43:52 +02:00
perf lock contention: Handle slab objects in -L/--lock-filter option
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
Committer testing:
root@number:~# perf lock con -abl sleep 1
contended total wait max wait avg wait address symbol
1 20.80 us 20.80 us 20.80 us ffff9d417fbd65d0 (spinlock)
8 12.85 us 2.41 us 1.61 us ffff9d415eeb6a40 rq_lock (spinlock)
1 2.55 us 2.55 us 2.55 us ffff9d415f636a40 rq_lock (spinlock)
7 1.92 us 840 ns 274 ns ffff9d39c2cbc8c4 (spinlock)
1 1.23 us 1.23 us 1.23 us ffff9d415fb36a40 rq_lock (spinlock)
2 928 ns 738 ns 464 ns ffff9d39c1fa6660 &kmalloc-rnd-14-192 (rwlock)
4 788 ns 252 ns 197 ns ffffffffb8608a80 jiffies_lock (spinlock)
1 304 ns 304 ns 304 ns ffff9d39c2c979c4 (spinlock)
1 216 ns 216 ns 216 ns ffff9d3a0225c660 &kmalloc-rnd-14-192 (rwlock)
1 89 ns 89 ns 89 ns ffff9d3a0adbf3e0 &kmalloc-rnd-14-192 (rwlock)
1 61 ns 61 ns 61 ns ffff9d415f9b6a40 rq_lock (spinlock)
root@number:~# uname -r
6.13.0-rc2
root@number:~#
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Chun-Tse Shao <ctshao@google.com>
Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Kees Cook <kees@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Song Liu <song@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Link: https://lore.kernel.org/r/20241220060009.507297-5-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
Namhyung Kim
Arnaldo Carvalho de Melo
parent
0c631ef07c
commit
91a5bffa56
|
|
@ -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.
|
||||
|
|
|
|||
|
|
@ -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;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -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;
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -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 {
|
||||
|
|
|
|||
Loading…
Reference in New Issue
Block a user