Merge branch 'New benchmark for hashmap lookups'

Anton Protopopov says:

====================

Add a new benchmark for hashmap lookups and fix several typos.

In commit 3 I've patched the bench utility so that now command line options
can be reused by different benchmarks.

The benchmark itself is added in the last commit 7. I was using this benchmark
to test map lookup productivity when using a different hash function [1]. When
run with --quiet, the results can be easily plotted [2].  The results provided
by the benchmark look reasonable and match the results of my different
benchmarks (requiring to patch kernel to get actual statistics on map lookups).

Links:
  [1] https://fosdem.org/2023/schedule/event/bpf_hashing/
  [2] https://github.com/aspsk/bpf-bench/tree/master/hashmap-bench

Changes,
v1->v2:
- percpu_times_index[] is of wrong size (Martin)
- use base 0 for strtol (Andrii)
- just use -q without argument (Andrii)
- use less hacks when parsing arguments (Andrii)
====================

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>

14 files changed, 420 insertions, 32 deletions

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 521933bc15fea9..b677dcd0b77af8 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -638,6 +638,7 @@ $(OUTPUT)/bench_strncmp.o: $(OUTPUT)/strncmp_bench.skel.h
 $(OUTPUT)/bench_bpf_hashmap_full_update.o: $(OUTPUT)/bpf_hashmap_full_update_bench.skel.h
 $(OUTPUT)/bench_local_storage.o: $(OUTPUT)/local_storage_bench.skel.h
 $(OUTPUT)/bench_local_storage_rcu_tasks_trace.o: $(OUTPUT)/local_storage_rcu_tasks_trace_bench.skel.h
+$(OUTPUT)/bench_bpf_hashmap_lookup.o: $(OUTPUT)/bpf_hashmap_lookup.skel.h
 $(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ)
 $(OUTPUT)/bench: LDLIBS += -lm
 $(OUTPUT)/bench: $(OUTPUT)/bench.o \
@@ -652,7 +653,9 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \
 		 $(OUTPUT)/bench_strncmp.o \
 		 $(OUTPUT)/bench_bpf_hashmap_full_update.o \
 		 $(OUTPUT)/bench_local_storage.o \
-		 $(OUTPUT)/bench_local_storage_rcu_tasks_trace.o
+		 $(OUTPUT)/bench_local_storage_rcu_tasks_trace.o \
+		 $(OUTPUT)/bench_bpf_hashmap_lookup.o \
+		 #
 	$(call msg,BINARY,,$@)
 	$(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@
 
diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
index c1f20a14746241..0b2a53bb846090 100644
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@@ -16,6 +16,7 @@ struct env env = {
 	.warmup_sec = 1,
 	.duration_sec = 5,
 	.affinity = false,
+	.quiet = false,
 	.consumer_cnt = 1,
 	.producer_cnt = 1,
 };
@@ -262,6 +263,7 @@ static const struct argp_option opts[] = {
 	{ "consumers", 'c', "NUM", 0, "Number of consumer threads"},
 	{ "verbose", 'v', NULL, 0, "Verbose debug output"},
 	{ "affinity", 'a', NULL, 0, "Set consumer/producer thread affinity"},
+	{ "quiet", 'q', NULL, 0, "Be more quiet"},
 	{ "prod-affinity", ARG_PROD_AFFINITY_SET, "CPUSET", 0,
 	  "Set of CPUs for producer threads; implies --affinity"},
 	{ "cons-affinity", ARG_CONS_AFFINITY_SET, "CPUSET", 0,
@@ -275,6 +277,7 @@ extern struct argp bench_bpf_loop_argp;
 extern struct argp bench_local_storage_argp;
 extern struct argp bench_local_storage_rcu_tasks_trace_argp;
 extern struct argp bench_strncmp_argp;
+extern struct argp bench_hashmap_lookup_argp;
 
 static const struct argp_child bench_parsers[] = {
 	{ &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 },
@@ -284,13 +287,15 @@ static const struct argp_child bench_parsers[] = {
 	{ &bench_strncmp_argp, 0, "bpf_strncmp helper benchmark", 0 },
 	{ &bench_local_storage_rcu_tasks_trace_argp, 0,
 		"local_storage RCU Tasks Trace slowdown benchmark", 0 },
+	{ &bench_hashmap_lookup_argp, 0, "Hashmap lookup benchmark", 0 },
 	{},
 };
 
+/* Make pos_args global, so that we can run argp_parse twice, if necessary */
+static int pos_args;
+
 static error_t parse_arg(int key, char *arg, struct argp_state *state)
 {
-	static int pos_args;
-
 	switch (key) {
 	case 'v':
 		env.verbose = true;
@@ -329,6 +334,9 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 	case 'a':
 		env.affinity = true;
 		break;
+	case 'q':
+		env.quiet = true;
+		break;
 	case ARG_PROD_AFFINITY_SET:
 		env.affinity = true;
 		if (parse_num_list(arg, &env.prod_cpus.cpus,
@@ -359,7 +367,7 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 	return 0;
 }
 
-static void parse_cmdline_args(int argc, char **argv)
+static void parse_cmdline_args_init(int argc, char **argv)
 {
 	static const struct argp argp = {
 		.options = opts,
@@ -369,9 +377,25 @@ static void parse_cmdline_args(int argc, char **argv)
 	};
 	if (argp_parse(&argp, argc, argv, 0, NULL, NULL))
 		exit(1);
-	if (!env.list && !env.bench_name) {
-		argp_help(&argp, stderr, ARGP_HELP_DOC, "bench");
-		exit(1);
+}
+
+static void parse_cmdline_args_final(int argc, char **argv)
+{
+	struct argp_child bench_parsers[2] = {};
+	const struct argp argp = {
+		.options = opts,
+		.parser = parse_arg,
+		.doc = argp_program_doc,
+		.children = bench_parsers,
+	};
+
+	/* Parse arguments the second time with the correct set of parsers */
+	if (bench->argp) {
+		bench_parsers[0].argp = bench->argp;
+		bench_parsers[0].header = bench->name;
+		pos_args = 0;
+		if (argp_parse(&argp, argc, argv, 0, NULL, NULL))
+			exit(1);
 	}
 }
 
@@ -490,6 +514,7 @@ extern const struct bench bench_local_storage_cache_seq_get;
 extern const struct bench bench_local_storage_cache_interleaved_get;
 extern const struct bench bench_local_storage_cache_hashmap_control;
 extern const struct bench bench_local_storage_tasks_trace;
+extern const struct bench bench_bpf_hashmap_lookup;
 
 static const struct bench *benchs[] = {
 	&bench_count_global,
@@ -529,17 +554,17 @@ static const struct bench *benchs[] = {
 	&bench_local_storage_cache_interleaved_get,
 	&bench_local_storage_cache_hashmap_control,
 	&bench_local_storage_tasks_trace,
+	&bench_bpf_hashmap_lookup,
 };
 
-static void setup_benchmark()
+static void find_benchmark(void)
 {
-	int i, err;
+	int i;
 
 	if (!env.bench_name) {
 		fprintf(stderr, "benchmark name is not specified\n");
 		exit(1);
 	}
-
 	for (i = 0; i < ARRAY_SIZE(benchs); i++) {
 		if (strcmp(benchs[i]->name, env.bench_name) == 0) {
 			bench = benchs[i];
@@ -550,8 +575,14 @@ static void setup_benchmark()
 		fprintf(stderr, "benchmark '%s' not found\n", env.bench_name);
 		exit(1);
 	}
+}
 
-	printf("Setting up benchmark '%s'...\n", bench->name);
+static void setup_benchmark(void)
+{
+	int i, err;
+
+	if (!env.quiet)
+		printf("Setting up benchmark '%s'...\n", bench->name);
 
 	state.producers = calloc(env.producer_cnt, sizeof(*state.producers));
 	state.consumers = calloc(env.consumer_cnt, sizeof(*state.consumers));
@@ -597,7 +628,8 @@ static void setup_benchmark()
 					    next_cpu(&env.prod_cpus));
 	}
 
-	printf("Benchmark '%s' started.\n", bench->name);
+	if (!env.quiet)
+		printf("Benchmark '%s' started.\n", bench->name);
 }
 
 static pthread_mutex_t bench_done_mtx = PTHREAD_MUTEX_INITIALIZER;
@@ -621,7 +653,7 @@ static void collect_measurements(long delta_ns) {
 
 int main(int argc, char **argv)
 {
-	parse_cmdline_args(argc, argv);
+	parse_cmdline_args_init(argc, argv);
 
 	if (env.list) {
 		int i;
@@ -633,6 +665,9 @@ int main(int argc, char **argv)
 		return 0;
 	}
 
+	find_benchmark();
+	parse_cmdline_args_final(argc, argv);
+
 	setup_benchmark();
 
 	setup_timer();
diff --git a/tools/testing/selftests/bpf/bench.h b/tools/testing/selftests/bpf/bench.h
index d748255877e2d2..402729c6a3ac50 100644
--- a/tools/testing/selftests/bpf/bench.h
+++ b/tools/testing/selftests/bpf/bench.h
@@ -24,6 +24,7 @@ struct env {
 	bool verbose;
 	bool list;
 	bool affinity;
+	bool quiet;
 	int consumer_cnt;
 	int producer_cnt;
 	struct cpu_set prod_cpus;
@@ -47,6 +48,7 @@ struct bench_res {
 
 struct bench {
 	const char *name;
+	const struct argp *argp;
 	void (*validate)(void);
 	void (*setup)(void);
 	void *(*producer_thread)(void *ctx);
diff --git a/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c b/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c
index 5bcb8a8cdeb204..7c8ccc1083138f 100644
--- a/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c
+++ b/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c
@@ -428,6 +428,7 @@ static void *consumer(void *input)
 
 const struct bench bench_bloom_lookup = {
 	.name = "bloom-lookup",
+	.argp = &bench_bloom_map_argp,
 	.validate = validate,
 	.setup = bloom_lookup_setup,
 	.producer_thread = producer,
@@ -439,6 +440,7 @@ const struct bench bench_bloom_lookup = {
 
 const struct bench bench_bloom_update = {
 	.name = "bloom-update",
+	.argp = &bench_bloom_map_argp,
 	.validate = validate,
 	.setup = bloom_update_setup,
 	.producer_thread = producer,
@@ -450,6 +452,7 @@ const struct bench bench_bloom_update = {
 
 const struct bench bench_bloom_false_positive = {
 	.name = "bloom-false-positive",
+	.argp = &bench_bloom_map_argp,
 	.validate = validate,
 	.setup = false_positive_setup,
 	.producer_thread = producer,
@@ -461,6 +464,7 @@ const struct bench bench_bloom_false_positive = {
 
 const struct bench bench_hashmap_without_bloom = {
 	.name = "hashmap-without-bloom",
+	.argp = &bench_bloom_map_argp,
 	.validate = validate,
 	.setup = hashmap_no_bloom_setup,
 	.producer_thread = producer,
@@ -472,6 +476,7 @@ const struct bench bench_hashmap_without_bloom = {
 
 const struct bench bench_hashmap_with_bloom = {
 	.name = "hashmap-with-bloom",
+	.argp = &bench_bloom_map_argp,
 	.validate = validate,
 	.setup = hashmap_with_bloom_setup,
 	.producer_thread = producer,
diff --git a/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_full_update.c b/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_full_update.c
index cec51e0ff4b8a0..75abe8137b6cf0 100644
--- a/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_full_update.c
+++ b/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_full_update.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2022 Bytedance */
 
-#include <argp.h>
 #include "bench.h"
 #include "bpf_hashmap_full_update_bench.skel.h"
 #include "bpf_util.h"
@@ -68,7 +67,7 @@ static void setup(void)
 		bpf_map_update_elem(map_fd, &i, &i, BPF_ANY);
 }
 
-void hashmap_report_final(struct bench_res res[], int res_cnt)
+static void hashmap_report_final(struct bench_res res[], int res_cnt)
 {
 	unsigned int nr_cpus = bpf_num_possible_cpus();
 	int i;
@@ -85,7 +84,7 @@ void hashmap_report_final(struct bench_res res[], int res_cnt)
 }
 
 const struct bench bench_bpf_hashmap_full_update = {
-	.name = "bpf-hashmap-ful-update",
+	.name = "bpf-hashmap-full-update",
 	.validate = validate,
 	.setup = setup,
 	.producer_thread = producer,
diff --git a/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_lookup.c b/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_lookup.c
new file mode 100644
index 00000000000000..8dbb02f75cffc1
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_lookup.c
@@ -0,0 +1,283 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+
+#include <sys/random.h>
+#include <argp.h>
+#include "bench.h"
+#include "bpf_hashmap_lookup.skel.h"
+#include "bpf_util.h"
+
+/* BPF triggering benchmarks */
+static struct ctx {
+	struct bpf_hashmap_lookup *skel;
+} ctx;
+
+/* only available to kernel, so define it here */
+#define BPF_MAX_LOOPS (1<<23)
+
+#define MAX_KEY_SIZE 1024 /* the size of the key map */
+
+static struct {
+	__u32 key_size;
+	__u32 map_flags;
+	__u32 max_entries;
+	__u32 nr_entries;
+	__u32 nr_loops;
+} args = {
+	.key_size = 4,
+	.map_flags = 0,
+	.max_entries = 1000,
+	.nr_entries = 500,
+	.nr_loops = 1000000,
+};
+
+enum {
+	ARG_KEY_SIZE = 8001,
+	ARG_MAP_FLAGS,
+	ARG_MAX_ENTRIES,
+	ARG_NR_ENTRIES,
+	ARG_NR_LOOPS,
+};
+
+static const struct argp_option opts[] = {
+	{ "key_size", ARG_KEY_SIZE, "KEY_SIZE", 0,
+	  "The hashmap key size (max 1024)"},
+	{ "map_flags", ARG_MAP_FLAGS, "MAP_FLAGS", 0,
+	  "The hashmap flags passed to BPF_MAP_CREATE"},
+	{ "max_entries", ARG_MAX_ENTRIES, "MAX_ENTRIES", 0,
+	  "The hashmap max entries"},
+	{ "nr_entries", ARG_NR_ENTRIES, "NR_ENTRIES", 0,
+	  "The number of entries to insert/lookup"},
+	{ "nr_loops", ARG_NR_LOOPS, "NR_LOOPS", 0,
+	  "The number of loops for the benchmark"},
+	{},
+};
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+	long ret;
+
+	switch (key) {
+	case ARG_KEY_SIZE:
+		ret = strtol(arg, NULL, 10);
+		if (ret < 1 || ret > MAX_KEY_SIZE) {
+			fprintf(stderr, "invalid key_size");
+			argp_usage(state);
+		}
+		args.key_size = ret;
+		break;
+	case ARG_MAP_FLAGS:
+		ret = strtol(arg, NULL, 0);
+		if (ret < 0 || ret > UINT_MAX) {
+			fprintf(stderr, "invalid map_flags");
+			argp_usage(state);
+		}
+		args.map_flags = ret;
+		break;
+	case ARG_MAX_ENTRIES:
+		ret = strtol(arg, NULL, 10);
+		if (ret < 1 || ret > UINT_MAX) {
+			fprintf(stderr, "invalid max_entries");
+			argp_usage(state);
+		}
+		args.max_entries = ret;
+		break;
+	case ARG_NR_ENTRIES:
+		ret = strtol(arg, NULL, 10);
+		if (ret < 1 || ret > UINT_MAX) {
+			fprintf(stderr, "invalid nr_entries");
+			argp_usage(state);
+		}
+		args.nr_entries = ret;
+		break;
+	case ARG_NR_LOOPS:
+		ret = strtol(arg, NULL, 10);
+		if (ret < 1 || ret > BPF_MAX_LOOPS) {
+			fprintf(stderr, "invalid nr_loops: %ld (min=1 max=%u)\n",
+				ret, BPF_MAX_LOOPS);
+			argp_usage(state);
+		}
+		args.nr_loops = ret;
+		break;
+	default:
+		return ARGP_ERR_UNKNOWN;
+	}
+
+	return 0;
+}
+
+const struct argp bench_hashmap_lookup_argp = {
+	.options = opts,
+	.parser = parse_arg,
+};
+
+static void validate(void)
+{
+	if (env.consumer_cnt != 1) {
+		fprintf(stderr, "benchmark doesn't support multi-consumer!\n");
+		exit(1);
+	}
+
+	if (args.nr_entries > args.max_entries) {
+		fprintf(stderr, "args.nr_entries is too big! (max %u, got %u)\n",
+			args.max_entries, args.nr_entries);
+		exit(1);
+	}
+}
+
+static void *producer(void *input)
+{
+	while (true) {
+		/* trigger the bpf program */
+		syscall(__NR_getpgid);
+	}
+	return NULL;
+}
+
+static void *consumer(void *input)
+{
+	return NULL;
+}
+
+static void measure(struct bench_res *res)
+{
+}
+
+static inline void patch_key(u32 i, u32 *key)
+{
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	*key = i + 1;
+#else
+	*key = __builtin_bswap32(i + 1);
+#endif
+	/* the rest of key is random */
+}
+
+static void setup(void)
+{
+	struct bpf_link *link;
+	int map_fd;
+	int ret;
+	int i;
+
+	setup_libbpf();
+
+	ctx.skel = bpf_hashmap_lookup__open();
+	if (!ctx.skel) {
+		fprintf(stderr, "failed to open skeleton\n");
+		exit(1);
+	}
+
+	bpf_map__set_max_entries(ctx.skel->maps.hash_map_bench, args.max_entries);
+	bpf_map__set_key_size(ctx.skel->maps.hash_map_bench, args.key_size);
+	bpf_map__set_value_size(ctx.skel->maps.hash_map_bench, 8);
+	bpf_map__set_map_flags(ctx.skel->maps.hash_map_bench, args.map_flags);
+
+	ctx.skel->bss->nr_entries = args.nr_entries;
+	ctx.skel->bss->nr_loops = args.nr_loops / args.nr_entries;
+
+	if (args.key_size > 4) {
+		for (i = 1; i < args.key_size/4; i++)
+			ctx.skel->bss->key[i] = 2654435761 * i;
+	}
+
+	ret = bpf_hashmap_lookup__load(ctx.skel);
+	if (ret) {
+		bpf_hashmap_lookup__destroy(ctx.skel);
+		fprintf(stderr, "failed to load map: %s", strerror(-ret));
+		exit(1);
+	}
+
+	/* fill in the hash_map */
+	map_fd = bpf_map__fd(ctx.skel->maps.hash_map_bench);
+	for (u64 i = 0; i < args.nr_entries; i++) {
+		patch_key(i, ctx.skel->bss->key);
+		bpf_map_update_elem(map_fd, ctx.skel->bss->key, &i, BPF_ANY);
+	}
+
+	link = bpf_program__attach(ctx.skel->progs.benchmark);
+	if (!link) {
+		fprintf(stderr, "failed to attach program!\n");
+		exit(1);
+	}
+}
+
+static inline double events_from_time(u64 time)
+{
+	if (time)
+		return args.nr_loops * 1000000000llu / time / 1000000.0L;
+
+	return 0;
+}
+
+static int compute_events(u64 *times, double *events_mean, double *events_stddev, u64 *mean_time)
+{
+	int i, n = 0;
+
+	*events_mean = 0;
+	*events_stddev = 0;
+	*mean_time = 0;
+
+	for (i = 0; i < 32; i++) {
+		if (!times[i])
+			break;
+		*mean_time += times[i];
+		*events_mean += events_from_time(times[i]);
+		n += 1;
+	}
+	if (!n)
+		return 0;
+
+	*mean_time /= n;
+	*events_mean /= n;
+
+	if (n > 1) {
+		for (i = 0; i < n; i++) {
+			double events_i = *events_mean - events_from_time(times[i]);
+			*events_stddev += events_i * events_i / (n - 1);
+		}
+		*events_stddev = sqrt(*events_stddev);
+	}
+
+	return n;
+}
+
+static void hashmap_report_final(struct bench_res res[], int res_cnt)
+{
+	unsigned int nr_cpus = bpf_num_possible_cpus();
+	double events_mean, events_stddev;
+	u64 mean_time;
+	int i, n;
+
+	for (i = 0; i < nr_cpus; i++) {
+		n = compute_events(ctx.skel->bss->percpu_times[i], &events_mean,
+				   &events_stddev, &mean_time);
+		if (n == 0)
+			continue;
+
+		if (env.quiet) {
+			/* we expect only one cpu to be present */
+			if (env.affinity)
+				printf("%.3lf\n", events_mean);
+			else
+				printf("cpu%02d %.3lf\n", i, events_mean);
+		} else {
+			printf("cpu%02d: lookup %.3lfM ± %.3lfM events/sec"
+			       " (approximated from %d samples of ~%lums)\n",
+			       i, events_mean, 2*events_stddev,
+			       n, mean_time / 1000000);
+		}
+	}
+}
+
+const struct bench bench_bpf_hashmap_lookup = {
+	.name = "bpf-hashmap-lookup",
+	.argp = &bench_hashmap_lookup_argp,
+	.validate = validate,
+	.setup = setup,
+	.producer_thread = producer,
+	.consumer_thread = consumer,
+	.measure = measure,
+	.report_progress = NULL,
+	.report_final = hashmap_report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c b/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c
index d0a6572bfab61d..d8a0394e10b15f 100644
--- a/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c
+++ b/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c
@@ -95,6 +95,7 @@ static void setup(void)
 
 const struct bench bench_bpf_loop = {
 	.name = "bpf-loop",
+	.argp = &bench_bpf_loop_argp,
 	.validate = validate,
 	.setup = setup,
 	.producer_thread = producer,
diff --git a/tools/testing/selftests/bpf/benchs/bench_local_storage.c b/tools/testing/selftests/bpf/benchs/bench_local_storage.c
index 5a378c84e81f64..d4b2817306d42a 100644
--- a/tools/testing/selftests/bpf/benchs/bench_local_storage.c
+++ b/tools/testing/selftests/bpf/benchs/bench_local_storage.c
@@ -255,6 +255,7 @@ static void *producer(void *input)
  */
 const struct bench bench_local_storage_cache_seq_get = {
 	.name = "local-storage-cache-seq-get",
+	.argp = &bench_local_storage_argp,
 	.validate = validate,
 	.setup = local_storage_cache_get_setup,
 	.producer_thread = producer,
@@ -266,6 +267,7 @@ const struct bench bench_local_storage_cache_seq_get = {
 
 const struct bench bench_local_storage_cache_interleaved_get = {
 	.name = "local-storage-cache-int-get",
+	.argp = &bench_local_storage_argp,
 	.validate = validate,
 	.setup = local_storage_cache_get_interleaved_setup,
 	.producer_thread = producer,
@@ -277,6 +279,7 @@ const struct bench bench_local_storage_cache_interleaved_get = {
 
 const struct bench bench_local_storage_cache_hashmap_control = {
 	.name = "local-storage-cache-hashmap-control",
+	.argp = &bench_local_storage_argp,
 	.validate = validate,
 	.setup = hashmap_setup,
 	.producer_thread = producer,
diff --git a/tools/testing/selftests/bpf/benchs/bench_local_storage_rcu_tasks_trace.c b/tools/testing/selftests/bpf/benchs/bench_local_storage_rcu_tasks_trace.c
index 43f109d9313029..d5eb5587f2aa9e 100644
--- a/tools/testing/selftests/bpf/benchs/bench_local_storage_rcu_tasks_trace.c
+++ b/tools/testing/selftests/bpf/benchs/bench_local_storage_rcu_tasks_trace.c
@@ -12,17 +12,14 @@
 static struct {
 	__u32 nr_procs;
 	__u32 kthread_pid;
-	bool quiet;
 } args = {
 	.nr_procs = 1000,
 	.kthread_pid = 0,
-	.quiet = false,
 };
 
 enum {
 	ARG_NR_PROCS = 7000,
 	ARG_KTHREAD_PID = 7001,
-	ARG_QUIET = 7002,
 };
 
 static const struct argp_option opts[] = {
@@ -30,8 +27,6 @@ static const struct argp_option opts[] = {
 		"Set number of user processes to spin up"},
 	{ "kthread_pid", ARG_KTHREAD_PID, "PID", 0,
 		"Pid of rcu_tasks_trace kthread for ticks tracking"},
-	{ "quiet", ARG_QUIET, "{0,1}", 0,
-		"If true, don't report progress"},
 	{},
 };
 
@@ -56,14 +51,6 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 		}
 		args.kthread_pid = ret;
 		break;
-	case ARG_QUIET:
-		ret = strtol(arg, NULL, 10);
-		if (ret < 0 || ret > 1) {
-			fprintf(stderr, "invalid quiet %ld\n", ret);
-			argp_usage(state);
-		}
-		args.quiet = ret;
-		break;
 break;
 	default:
 		return ARGP_ERR_UNKNOWN;
@@ -230,7 +217,7 @@ static void report_progress(int iter, struct bench_res *res, long delta_ns)
 		exit(1);
 	}
 
-	if (args.quiet)
+	if (env.quiet)
 		return;
 
 	printf("Iter %d\t avg tasks_trace grace period latency\t%lf ns\n",
@@ -271,6 +258,7 @@ static void report_final(struct bench_res res[], int res_cnt)
  */
 const struct bench bench_local_storage_tasks_trace = {
 	.name = "local-storage-tasks-trace",
+	.argp = &bench_local_storage_rcu_tasks_trace_argp,
 	.validate = validate,
 	.setup = local_storage_tasks_trace_setup,
 	.producer_thread = producer,
diff --git a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
index c2554f9695ffbb..fc91fdac4faa5e 100644
--- a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
+++ b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
@@ -518,6 +518,7 @@ static void *perfbuf_custom_consumer(void *input)
 
 const struct bench bench_rb_libbpf = {
 	.name = "rb-libbpf",
+	.argp = &bench_ringbufs_argp,
 	.validate = bufs_validate,
 	.setup = ringbuf_libbpf_setup,
 	.producer_thread = bufs_sample_producer,
@@ -529,6 +530,7 @@ const struct bench bench_rb_libbpf = {
 
 const struct bench bench_rb_custom = {
 	.name = "rb-custom",
+	.argp = &bench_ringbufs_argp,
 	.validate = bufs_validate,
 	.setup = ringbuf_custom_setup,
 	.producer_thread = bufs_sample_producer,
@@ -540,6 +542,7 @@ const struct bench bench_rb_custom = {
 
 const struct bench bench_pb_libbpf = {
 	.name = "pb-libbpf",
+	.argp = &bench_ringbufs_argp,
 	.validate = bufs_validate,
 	.setup = perfbuf_libbpf_setup,
 	.producer_thread = bufs_sample_producer,
@@ -551,6 +554,7 @@ const struct bench bench_pb_libbpf = {
 
 const struct bench bench_pb_custom = {
 	.name = "pb-custom",
+	.argp = &bench_ringbufs_argp,
 	.validate = bufs_validate,
 	.setup = perfbuf_libbpf_setup,
 	.producer_thread = bufs_sample_producer,
diff --git a/tools/testing/selftests/bpf/benchs/bench_strncmp.c b/tools/testing/selftests/bpf/benchs/bench_strncmp.c
index 494b591c028970..d3fad2ba6916fd 100644
--- a/tools/testing/selftests/bpf/benchs/bench_strncmp.c
+++ b/tools/testing/selftests/bpf/benchs/bench_strncmp.c
@@ -140,6 +140,7 @@ static void strncmp_measure(struct bench_res *res)
 
 const struct bench bench_strncmp_no_helper = {
 	.name = "strncmp-no-helper",
+	.argp = &bench_strncmp_argp,
 	.validate = strncmp_validate,
 	.setup = strncmp_no_helper_setup,
 	.producer_thread = strncmp_producer,
@@ -151,6 +152,7 @@ const struct bench bench_strncmp_no_helper = {
 
 const struct bench bench_strncmp_helper = {
 	.name = "strncmp-helper",
+	.argp = &bench_strncmp_argp,
 	.validate = strncmp_validate,
 	.setup = strncmp_helper_setup,
 	.producer_thread = strncmp_producer,
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_bpf_hashmap_full_update.sh b/tools/testing/selftests/bpf/benchs/run_bench_bpf_hashmap_full_update.sh
index 1e2de838f9fa9c..cd2efd3fdef3ad 100755
--- a/tools/testing/selftests/bpf/benchs/run_bench_bpf_hashmap_full_update.sh
+++ b/tools/testing/selftests/bpf/benchs/run_bench_bpf_hashmap_full_update.sh
@@ -6,6 +6,6 @@ source ./benchs/run_common.sh
 set -eufo pipefail
 
 nr_threads=`expr $(cat /proc/cpuinfo | grep "processor"| wc -l) - 1`
-summary=$($RUN_BENCH -p $nr_threads bpf-hashmap-ful-update)
+summary=$($RUN_BENCH -p $nr_threads bpf-hashmap-full-update)
 printf "$summary"
 printf "\n"
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_local_storage_rcu_tasks_trace.sh b/tools/testing/selftests/bpf/benchs/run_bench_local_storage_rcu_tasks_trace.sh
index 5dac1f02892cf7..3e8a969f20967d 100755
--- a/tools/testing/selftests/bpf/benchs/run_bench_local_storage_rcu_tasks_trace.sh
+++ b/tools/testing/selftests/bpf/benchs/run_bench_local_storage_rcu_tasks_trace.sh
@@ -8,4 +8,4 @@ if [ -z $kthread_pid ]; then
 	exit 1
 fi
 
-./bench --nr_procs 15000 --kthread_pid $kthread_pid -d 600 --quiet 1 local-storage-tasks-trace
+./bench --nr_procs 15000 --kthread_pid $kthread_pid -d 600 --quiet local-storage-tasks-trace
diff --git a/tools/testing/selftests/bpf/progs/bpf_hashmap_lookup.c b/tools/testing/selftests/bpf/progs/bpf_hashmap_lookup.c
new file mode 100644
index 00000000000000..1eb74ddca41445
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_hashmap_lookup.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+
+#include "vmlinux.h"
+
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+} hash_map_bench SEC(".maps");
+
+/* The number of slots to store times */
+#define NR_SLOTS 32
+#define NR_CPUS 256
+#define CPU_MASK (NR_CPUS-1)
+
+/* Configured by userspace */
+u64 nr_entries;
+u64 nr_loops;
+u32 __attribute__((__aligned__(8))) key[NR_CPUS];
+
+/* Filled by us */
+u64 __attribute__((__aligned__(256))) percpu_times_index[NR_CPUS];
+u64 __attribute__((__aligned__(256))) percpu_times[NR_CPUS][NR_SLOTS];
+
+static inline void patch_key(u32 i)
+{
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	key[0] = i + 1;
+#else
+	key[0] = __builtin_bswap32(i + 1);
+#endif
+	/* the rest of key is random and is configured by userspace */
+}
+
+static int lookup_callback(__u32 index, u32 *unused)
+{
+	patch_key(index);
+	return bpf_map_lookup_elem(&hash_map_bench, key) ? 0 : 1;
+}
+
+static int loop_lookup_callback(__u32 index, u32 *unused)
+{
+	return bpf_loop(nr_entries, lookup_callback, NULL, 0) ? 0 : 1;
+}
+
+SEC("fentry/" SYS_PREFIX "sys_getpgid")
+int benchmark(void *ctx)
+{
+	u32 cpu = bpf_get_smp_processor_id();
+	u32 times_index;
+	u64 start_time;
+
+	times_index = percpu_times_index[cpu & CPU_MASK] % NR_SLOTS;
+	start_time = bpf_ktime_get_ns();
+	bpf_loop(nr_loops, loop_lookup_callback, NULL, 0);
+	percpu_times[cpu & CPU_MASK][times_index] = bpf_ktime_get_ns() - start_time;
+	percpu_times_index[cpu & CPU_MASK] += 1;
+	return 0;
+}