1 files changed, 167 insertions, 23 deletions

diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c
index b4cb3fe5cc25..fc8666222399 100644
--- a/tools/perf/util/bpf_lock_contention.c
+++ b/tools/perf/util/bpf_lock_contention.c
@@ -2,6 +2,7 @@
 #include "util/cgroup.h"
 #include "util/debug.h"
 #include "util/evlist.h"
+#include "util/hashmap.h"
 #include "util/machine.h"
 #include "util/map.h"
 #include "util/symbol.h"
@@ -12,17 +13,106 @@
 #include <linux/zalloc.h>
 #include <linux/string.h>
 #include <bpf/bpf.h>
+#include <bpf/btf.h>
 #include <inttypes.h>
 
 #include "bpf_skel/lock_contention.skel.h"
 #include "bpf_skel/lock_data.h"
 
 static struct lock_contention_bpf *skel;
+static bool has_slab_iter;
+static struct hashmap slab_hash;
+
+static size_t slab_cache_hash(long key, void *ctx __maybe_unused)
+{
+	return key;
+}
+
+static bool slab_cache_equal(long key1, long key2, void *ctx __maybe_unused)
+{
+	return key1 == key2;
+}
+
+static void check_slab_cache_iter(struct lock_contention *con)
+{
+	struct btf *btf = btf__load_vmlinux_btf();
+	s32 ret;
+
+	hashmap__init(&slab_hash, slab_cache_hash, slab_cache_equal, /*ctx=*/NULL);
+
+	if (btf == NULL) {
+		pr_debug("BTF loading failed: %s\n", strerror(errno));
+		return;
+	}
+
+	ret = btf__find_by_name_kind(btf, "bpf_iter__kmem_cache", BTF_KIND_STRUCT);
+	if (ret < 0) {
+		bpf_program__set_autoload(skel->progs.slab_cache_iter, false);
+		pr_debug("slab cache iterator is not available: %d\n", ret);
+		goto out;
+	}
+
+	has_slab_iter = true;
+
+	bpf_map__set_max_entries(skel->maps.slab_caches, con->map_nr_entries);
+out:
+	btf__free(btf);
+}
+
+static void run_slab_cache_iter(void)
+{
+	int fd;
+	char buf[256];
+	long key, *prev_key;
+
+	if (!has_slab_iter)
+		return;
+
+	fd = bpf_iter_create(bpf_link__fd(skel->links.slab_cache_iter));
+	if (fd < 0) {
+		pr_debug("cannot create slab cache iter: %d\n", fd);
+		return;
+	}
+
+	/* This will run the bpf program */
+	while (read(fd, buf, sizeof(buf)) > 0)
+		continue;
+
+	close(fd);
+
+	/* Read the slab cache map and build a hash with IDs */
+	fd = bpf_map__fd(skel->maps.slab_caches);
+	prev_key = NULL;
+	while (!bpf_map_get_next_key(fd, prev_key, &key)) {
+		struct slab_cache_data *data;
+
+		data = malloc(sizeof(*data));
+		if (data == NULL)
+			break;
+
+		if (bpf_map_lookup_elem(fd, &key, data) < 0)
+			break;
+
+		hashmap__add(&slab_hash, data->id, data);
+		prev_key = &key;
+	}
+}
+
+static void exit_slab_cache_iter(void)
+{
+	struct hashmap_entry *cur;
+	unsigned bkt;
+
+	hashmap__for_each_entry(&slab_hash, cur, bkt)
+		free(cur->pvalue);
+
+	hashmap__clear(&slab_hash);
+}
 
 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;
 
@@ -46,14 +136,22 @@ int lock_contention_prepare(struct lock_contention *con)
 	else
 		bpf_map__set_max_entries(skel->maps.stacks, 1);
 
-	if (target__has_cpu(target))
+	if (target__has_cpu(target)) {
+		skel->rodata->has_cpu = 1;
 		ncpus = perf_cpu_map__nr(evlist->core.user_requested_cpus);
-	if (target__has_task(target))
+	}
+	if (target__has_task(target)) {
+		skel->rodata->has_task = 1;
 		ntasks = perf_thread_map__nr(evlist->core.threads);
-	if (con->filters->nr_types)
+	}
+	if (con->filters->nr_types) {
+		skel->rodata->has_type = 1;
 		ntypes = con->filters->nr_types;
-	if (con->filters->nr_cgrps)
+	}
+	if (con->filters->nr_cgrps) {
+		skel->rodata->has_cgroup = 1;
 		ncgrps = con->filters->nr_cgrps;
+	}
 
 	/* resolve lock name filters to addr */
 	if (con->filters->nr_syms) {
@@ -82,6 +180,7 @@ int lock_contention_prepare(struct lock_contention *con)
 			con->filters->addrs = addrs;
 		}
 		naddrs = con->filters->nr_addrs;
+		skel->rodata->has_addr = 1;
 	}
 
 	bpf_map__set_max_entries(skel->maps.cpu_filter, ncpus);
@@ -90,6 +189,25 @@ int lock_contention_prepare(struct lock_contention *con)
 	bpf_map__set_max_entries(skel->maps.addr_filter, naddrs);
 	bpf_map__set_max_entries(skel->maps.cgroup_filter, ncgrps);
 
+	skel->rodata->stack_skip = con->stack_skip;
+	skel->rodata->aggr_mode = con->aggr_mode;
+	skel->rodata->needs_callstack = con->save_callstack;
+	skel->rodata->lock_owner = con->owner;
+
+	if (con->aggr_mode == LOCK_AGGR_CGROUP || con->filters->nr_cgrps) {
+		if (cgroup_is_v2("perf_event"))
+			skel->rodata->use_cgroup_v2 = 1;
+	}
+
+	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;
@@ -99,7 +217,6 @@ int lock_contention_prepare(struct lock_contention *con)
 		u32 cpu;
 		u8 val = 1;
 
-		skel->bss->has_cpu = 1;
 		fd = bpf_map__fd(skel->maps.cpu_filter);
 
 		for (i = 0; i < ncpus; i++) {
@@ -112,7 +229,6 @@ int lock_contention_prepare(struct lock_contention *con)
 		u32 pid;
 		u8 val = 1;
 
-		skel->bss->has_task = 1;
 		fd = bpf_map__fd(skel->maps.task_filter);
 
 		for (i = 0; i < ntasks; i++) {
@@ -125,7 +241,6 @@ int lock_contention_prepare(struct lock_contention *con)
 		u32 pid = evlist->workload.pid;
 		u8 val = 1;
 
-		skel->bss->has_task = 1;
 		fd = bpf_map__fd(skel->maps.task_filter);
 		bpf_map_update_elem(fd, &pid, &val, BPF_ANY);
 	}
@@ -133,7 +248,6 @@ int lock_contention_prepare(struct lock_contention *con)
 	if (con->filters->nr_types) {
 		u8 val = 1;
 
-		skel->bss->has_type = 1;
 		fd = bpf_map__fd(skel->maps.type_filter);
 
 		for (i = 0; i < con->filters->nr_types; i++)
@@ -143,7 +257,6 @@ int lock_contention_prepare(struct lock_contention *con)
 	if (con->filters->nr_addrs) {
 		u8 val = 1;
 
-		skel->bss->has_addr = 1;
 		fd = bpf_map__fd(skel->maps.addr_filter);
 
 		for (i = 0; i < con->filters->nr_addrs; i++)
@@ -153,29 +266,48 @@ int lock_contention_prepare(struct lock_contention *con)
 	if (con->filters->nr_cgrps) {
 		u8 val = 1;
 
-		skel->bss->has_cgroup = 1;
 		fd = bpf_map__fd(skel->maps.cgroup_filter);
 
 		for (i = 0; i < con->filters->nr_cgrps; i++)
 			bpf_map_update_elem(fd, &con->filters->cgrps[i], &val, BPF_ANY);
 	}
 
-	/* these don't work well if in the rodata section */
-	skel->bss->stack_skip = con->stack_skip;
-	skel->bss->aggr_mode = con->aggr_mode;
-	skel->bss->needs_callstack = con->save_callstack;
-	skel->bss->lock_owner = con->owner;
-
-	if (con->aggr_mode == LOCK_AGGR_CGROUP) {
-		if (cgroup_is_v2("perf_event"))
-			skel->bss->use_cgroup_v2 = 1;
-
+	if (con->aggr_mode == LOCK_AGGR_CGROUP)
 		read_all_cgroups(&con->cgroups);
-	}
 
 	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;
 }
 
@@ -286,6 +418,9 @@ static void account_end_timestamp(struct lock_contention *con)
 			goto next;
 
 		for (int i = 0; i < total_cpus; i++) {
+			if (cpu_data[i].lock == 0)
+				continue;
+
 			update_lock_stat(stat_fd, -1, end_ts, aggr_mode,
 					 &cpu_data[i]);
 		}
@@ -341,6 +476,7 @@ static const char *lock_contention_get_name(struct lock_contention *con,
 
 	if (con->aggr_mode == LOCK_AGGR_ADDR) {
 		int lock_fd = bpf_map__fd(skel->maps.lock_syms);
+		struct slab_cache_data *slab_data;
 
 		/* per-process locks set upper bits of the flags */
 		if (flags & LCD_F_MMAP_LOCK)
@@ -359,6 +495,12 @@ static const char *lock_contention_get_name(struct lock_contention *con,
 				return "rq_lock";
 		}
 
+		/* look slab_hash for dynamic locks in a slab object */
+		if (hashmap__find(&slab_hash, flags & LCB_F_SLAB_ID_MASK, &slab_data)) {
+			snprintf(name_buf, sizeof(name_buf), "&%s", slab_data->name);
+			return name_buf;
+		}
+
 		return "";
 	}
 
@@ -452,7 +594,7 @@ int lock_contention_read(struct lock_contention *con)
 		if (con->save_callstack) {
 			bpf_map_lookup_elem(stack, &key.stack_id, stack_trace);
 
-			if (!match_callstack_filter(machine, stack_trace)) {
+			if (!match_callstack_filter(machine, stack_trace, con->max_stack)) {
 				con->nr_filtered += data.count;
 				goto next;
 			}
@@ -533,5 +675,7 @@ int lock_contention_finish(struct lock_contention *con)
 		cgroup__put(cgrp);
 	}
 
+	exit_slab_cache_iter();
+
 	return 0;
 }