2 files changed, 62 insertions, 17 deletions

diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c
index ace0d1011a8e..b7aea79495ba 100644
--- a/tools/testing/selftests/bpf/benchs/bench_trigger.c
+++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c
@@ -1,15 +1,45 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
+#define _GNU_SOURCE
+#include <unistd.h>
 #include "bench.h"
 #include "trigger_bench.skel.h"
 #include "trace_helpers.h"
 
+/* adjust slot shift in inc_hits() if changing */
+#define MAX_BUCKETS 256
+
 /* BPF triggering benchmarks */
 static struct trigger_ctx {
 	struct trigger_bench *skel;
 } ctx;
 
-static struct counter base_hits;
+static struct counter base_hits[MAX_BUCKETS];
+
+static __always_inline void inc_counter(struct counter *counters)
+{
+	static __thread int tid = 0;
+	unsigned slot;
+
+	if (unlikely(tid == 0))
+		tid = gettid();
+
+	/* multiplicative hashing, it's fast */
+	slot = 2654435769U * tid;
+	slot >>= 24;
+
+	atomic_inc(&base_hits[slot].value); /* use highest byte as an index */
+}
+
+static long sum_and_reset_counters(struct counter *counters)
+{
+	int i;
+	long sum = 0;
+
+	for (i = 0; i < MAX_BUCKETS; i++)
+		sum += atomic_swap(&counters[i].value, 0);
+	return sum;
+}
 
 static void trigger_validate(void)
 {
@@ -23,14 +53,14 @@ static void *trigger_base_producer(void *input)
 {
 	while (true) {
 		(void)syscall(__NR_getpgid);
-		atomic_inc(&base_hits.value);
+		inc_counter(base_hits);
 	}
 	return NULL;
 }
 
 static void trigger_base_measure(struct bench_res *res)
 {
-	res->hits = atomic_swap(&base_hits.value, 0);
+	res->hits = sum_and_reset_counters(base_hits);
 }
 
 static void *trigger_producer(void *input)
@@ -42,7 +72,7 @@ static void *trigger_producer(void *input)
 
 static void trigger_measure(struct bench_res *res)
 {
-	res->hits = atomic_swap(&ctx.skel->bss->hits, 0);
+	res->hits = sum_and_reset_counters(ctx.skel->bss->hits);
 }
 
 static void setup_ctx(void)
@@ -164,7 +194,7 @@ static void *uprobe_base_producer(void *input)
 {
 	while (true) {
 		uprobe_target_nop();
-		atomic_inc(&base_hits.value);
+		inc_counter(base_hits);
 	}
 	return NULL;
 }
diff --git a/tools/testing/selftests/bpf/progs/trigger_bench.c b/tools/testing/selftests/bpf/progs/trigger_bench.c
index 5fda43901033..42ec202015ed 100644
--- a/tools/testing/selftests/bpf/progs/trigger_bench.c
+++ b/tools/testing/selftests/bpf/progs/trigger_bench.c
@@ -9,12 +9,27 @@
 
 char _license[] SEC("license") = "GPL";
 
-long hits = 0;
+#define CPU_MASK 255
+#define MAX_CPUS (CPU_MASK + 1) /* should match MAX_BUCKETS in benchs/bench_trigger.c */
+
+/* matches struct counter in bench.h */
+struct counter {
+	long value;
+} __attribute__((aligned(128)));
+
+struct counter hits[MAX_CPUS];
+
+static __always_inline void inc_counter(void)
+{
+	int cpu = bpf_get_smp_processor_id();
+
+	__sync_add_and_fetch(&hits[cpu & CPU_MASK].value, 1);
+}
 
 SEC("tp/syscalls/sys_enter_getpgid")
 int bench_trigger_tp(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
 	return 0;
 }
 
@@ -22,69 +37,69 @@ SEC("raw_tp/sys_enter")
 int BPF_PROG(bench_trigger_raw_tp, struct pt_regs *regs, long id)
 {
 	if (id == __NR_getpgid)
-		__sync_add_and_fetch(&hits, 1);
+		inc_counter();
 	return 0;
 }
 
 SEC("kprobe/" SYS_PREFIX "sys_getpgid")
 int bench_trigger_kprobe(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
 	return 0;
 }
 
 SEC("kretprobe/" SYS_PREFIX "sys_getpgid")
 int bench_trigger_kretprobe(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
 	return 0;
 }
 
 SEC("kprobe.multi/" SYS_PREFIX "sys_getpgid")
 int bench_trigger_kprobe_multi(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
 	return 0;
 }
 
 SEC("kretprobe.multi/" SYS_PREFIX "sys_getpgid")
 int bench_trigger_kretprobe_multi(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
 	return 0;
 }
 
 SEC("fentry/" SYS_PREFIX "sys_getpgid")
 int bench_trigger_fentry(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
 	return 0;
 }
 
 SEC("fexit/" SYS_PREFIX "sys_getpgid")
 int bench_trigger_fexit(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
 	return 0;
 }
 
 SEC("fentry.s/" SYS_PREFIX "sys_getpgid")
 int bench_trigger_fentry_sleep(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
 	return 0;
 }
 
 SEC("fmod_ret/" SYS_PREFIX "sys_getpgid")
 int bench_trigger_fmodret(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
 	return -22;
 }
 
 SEC("uprobe")
 int bench_trigger_uprobe(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
 	return 0;
 }