selftests/bpf: Add benchmark for bpf_strncmp() helper

Add benchmark to compare the performance between home-made strncmp()
in bpf program and bpf_strncmp() helper. In summary, the performance
win of bpf_strncmp() under x86-64 is greater than 18% when the compared
string length is greater than 64, and is 179% when the length is 4095.
Under arm64 the performance win is even bigger: 33% when the length
is greater than 64 and 600% when the length is 4095.

The following is the details:

no-helper-X: use home-made strncmp() to compare X-sized string
helper-Y: use bpf_strncmp() to compare Y-sized string

Under x86-64:

no-helper-1          3.504 ± 0.000M/s (drops 0.000 ± 0.000M/s)
helper-1             3.347 ± 0.001M/s (drops 0.000 ± 0.000M/s)

no-helper-8          3.357 ± 0.001M/s (drops 0.000 ± 0.000M/s)
helper-8             3.307 ± 0.001M/s (drops 0.000 ± 0.000M/s)

no-helper-32         3.064 ± 0.000M/s (drops 0.000 ± 0.000M/s)
helper-32            3.253 ± 0.001M/s (drops 0.000 ± 0.000M/s)

no-helper-64         2.563 ± 0.001M/s (drops 0.000 ± 0.000M/s)
helper-64            3.040 ± 0.001M/s (drops 0.000 ± 0.000M/s)

no-helper-128        1.975 ± 0.000M/s (drops 0.000 ± 0.000M/s)
helper-128           2.641 ± 0.000M/s (drops 0.000 ± 0.000M/s)

no-helper-512        0.759 ± 0.000M/s (drops 0.000 ± 0.000M/s)
helper-512           1.574 ± 0.000M/s (drops 0.000 ± 0.000M/s)

no-helper-2048       0.329 ± 0.000M/s (drops 0.000 ± 0.000M/s)
helper-2048          0.602 ± 0.000M/s (drops 0.000 ± 0.000M/s)

no-helper-4095       0.117 ± 0.000M/s (drops 0.000 ± 0.000M/s)
helper-4095          0.327 ± 0.000M/s (drops 0.000 ± 0.000M/s)

Under arm64:

no-helper-1          2.806 ± 0.004M/s (drops 0.000 ± 0.000M/s)
helper-1             2.819 ± 0.002M/s (drops 0.000 ± 0.000M/s)

no-helper-8          2.797 ± 0.109M/s (drops 0.000 ± 0.000M/s)
helper-8             2.786 ± 0.025M/s (drops 0.000 ± 0.000M/s)

no-helper-32         2.399 ± 0.011M/s (drops 0.000 ± 0.000M/s)
helper-32            2.703 ± 0.002M/s (drops 0.000 ± 0.000M/s)

no-helper-64         2.020 ± 0.015M/s (drops 0.000 ± 0.000M/s)
helper-64            2.702 ± 0.073M/s (drops 0.000 ± 0.000M/s)

no-helper-128        1.604 ± 0.001M/s (drops 0.000 ± 0.000M/s)
helper-128           2.516 ± 0.002M/s (drops 0.000 ± 0.000M/s)

no-helper-512        0.699 ± 0.000M/s (drops 0.000 ± 0.000M/s)
helper-512           2.106 ± 0.003M/s (drops 0.000 ± 0.000M/s)

no-helper-2048       0.215 ± 0.000M/s (drops 0.000 ± 0.000M/s)
helper-2048          1.223 ± 0.003M/s (drops 0.000 ± 0.000M/s)

no-helper-4095       0.112 ± 0.000M/s (drops 0.000 ± 0.000M/s)
helper-4095          0.796 ± 0.000M/s (drops 0.000 ± 0.000M/s)

Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211210141652.877186-4-houtao1@huawei.com

1 files changed, 50 insertions, 0 deletions

diff --git a/tools/testing/selftests/bpf/progs/strncmp_bench.c b/tools/testing/selftests/bpf/progs/strncmp_bench.c
new file mode 100644
index 000000000000..18373a7df76e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/strncmp_bench.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021. Huawei Technologies Co., Ltd */
+#include <linux/types.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#define STRNCMP_STR_SZ 4096
+
+/* Will be updated by benchmark before program loading */
+const volatile unsigned int cmp_str_len = 1;
+const char target[STRNCMP_STR_SZ];
+
+long hits = 0;
+char str[STRNCMP_STR_SZ];
+
+char _license[] SEC("license") = "GPL";
+
+static __always_inline int local_strncmp(const char *s1, unsigned int sz,
+					 const char *s2)
+{
+	int ret = 0;
+	unsigned int i;
+
+	for (i = 0; i < sz; i++) {
+		/* E.g. 0xff > 0x31 */
+		ret = (unsigned char)s1[i] - (unsigned char)s2[i];
+		if (ret || !s1[i])
+			break;
+	}
+
+	return ret;
+}
+
+SEC("tp/syscalls/sys_enter_getpgid")
+int strncmp_no_helper(void *ctx)
+{
+	if (local_strncmp(str, cmp_str_len + 1, target) < 0)
+		__sync_add_and_fetch(&hits, 1);
+	return 0;
+}
+
+SEC("tp/syscalls/sys_enter_getpgid")
+int strncmp_helper(void *ctx)
+{
+	if (bpf_strncmp(str, cmp_str_len + 1, target) < 0)
+		__sync_add_and_fetch(&hits, 1);
+	return 0;
+}
+