[PATCH v5 2/2] lib/string_kunit: extend benchmarks and unit test to memcmp()

[Milan Tripkovic]

From: Milan Tripkovic <Milan.Tripkovic at rt-rk.com>

Extend the string benchmarking suite to include memcmp().
Extend the string unit test to include memcmp().

Signed-off-by: Milan Tripkovic <Milan.Tripkovic at rt-rk.com>
---
v5 changes:
    - Removed redundant warm-up from test case
    - Link to v4: https://lore.kernel.org/all/20260518131407.1026049-2-milant2002@gmail.com/

v4 changes:
    - Fixed build error: call to undeclared function 'STRING_BENCH'
    - Link to v3: https://lore.kernel.org/all/20260515141019.1234037-1-milant2002@gmail.com/

v3 changes:
    - Split memcmp benchmark into wrapper (string_bench_memcmp) and worker
      function (do_string_bench_memcmp).
    - Removed all C99 mixed declarations; moved all variable declarations
      to the top of each function.
    - Converted len, iterations and loop counters in the benchmark to u64
      to avoid implicit casts.
    - Cleaned up spacing, indentation and minor style issues.
    - Added #if defined(CONFIG_RISCV_ISA_ZBB)... in  memcmp.S
    - Link to v2: https://lore.kernel.org/all/20260514121359.931999-1-milant2002@gmail.com/

v2 changes:
    - Fixed KUnit build failures for Clang and non-benchmark configs.
    - Link to v1: https://lore.kernel.org/all/20260512141007.1193033-1-milant2002@gmail.com/

 lib/tests/string_kunit.c | 110 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 110 insertions(+)

diff --git a/lib/tests/string_kunit.c b/lib/tests/string_kunit.c
index 0819ace5b..7b14c0052 100644
--- a/lib/tests/string_kunit.c
+++ b/lib/tests/string_kunit.c
@@ -881,6 +881,114 @@ static void string_bench_strrchr(struct kunit *test)
 	STRING_BENCH_BUF(test, buf, len, strrchr, buf, '\0');
 }
 
+static void string_test_memcmp(struct kunit *test)
+{
+	const unsigned int max_offset = 16;
+	const unsigned int max_len = 32;
+	const unsigned int buf_size = max_offset + max_len + 32;
+	u8 *buf1, *buf2;
+	unsigned int i, j, len, k;
+	int res;
+
+	buf1 = kunit_kzalloc(test, buf_size, GFP_KERNEL);
+	buf2 = kunit_kzalloc(test, buf_size, GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buf1);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buf2);
+
+	for (i = 0; i < max_offset; i++) {
+		for (j = 0; j < max_offset; j++) {
+			for (len = 0; len <= max_len; len++) {
+				memset(buf1, 'A', buf_size);
+				memset(buf2, 'A', buf_size);
+				KUNIT_EXPECT_EQ_MSG(test, memcmp(buf1 + i, buf2 + j, len), 0,
+						    "Should be equal: i:%u j:%u len:%u", i, j, len);
+				for (k = 0; k < len; k++) {
+					memset(buf1, 'A', buf_size);
+					memset(buf2, 'A', buf_size);
+					buf2[j + k] = 'B';
+					res = memcmp(buf1 + i, buf2 + j, len);
+					KUNIT_EXPECT_NE_MSG(test, res, 0,
+							    "Should detect difference at k:%u (i:%u j:%u len:%u)",
+						k, i, j, len);
+					if (buf1[i + k] < buf2[j + k])
+						KUNIT_EXPECT_LT(test, res, 0);
+					else
+						KUNIT_EXPECT_GT(test, res, 0);
+				}
+			}
+		}
+	}
+}
+
+#ifndef STRING_BENCH
+#define STRING_BENCH(...) 0
+#endif
+
+static void do_string_bench_memcmp(struct kunit *test)
+{
+	char *buf1 = NULL;
+	char *buf2 = NULL;
+	const u64 lengths[] = { 1, 7, 8, 16, 32, 64, 128, 512, 1024, 4096};
+	const int offsets[] = { 0, 1, 3, 7};
+	const u64 max_len = 4096 + 64;
+	unsigned int o, i;
+	unsigned int off;
+	u64 len;
+	char *p1;
+	char *p2;
+	u64 iterations;
+	u64 elapsed;
+	u64 ns_per_call;
+	u64 mbps;
+
+	buf1 = vmalloc(max_len);
+	buf2 = vmalloc(max_len);
+
+	if (!buf1 || !buf2) {
+		vfree(buf1);
+		vfree(buf2);
+		kunit_err(test, "vmalloc failed\n");
+		return;
+	}
+
+	memset(buf1, 'A', max_len);
+	memset(buf2, 'A', max_len);
+
+	for (o = 0; o < ARRAY_SIZE(offsets); o++) {
+		off = offsets[o];
+
+		for (i = 0; i < ARRAY_SIZE(lengths); i++) {
+			len = lengths[i];
+			p1 = buf1;
+			p2 = buf2 + off;
+			iterations = (len < 512) ? 100000ULL : 10000ULL;
+			elapsed = STRING_BENCH(iterations, memcmp, p1, p2, len);
+			ns_per_call = div_u64(elapsed, iterations);
+			mbps = len ? div_u64(iterations * len * (NSEC_PER_SEC / MEGA), elapsed) : 0;
+
+			if (off == 0) {
+				kunit_info(test, "bench_memcmp_aligned: len=%-4llu: %llu MB/s (%llu ns/call)\n",
+					   len, mbps, ns_per_call);
+			} else {
+				kunit_info(test, "bench_memcmp_unaligned(off=%u): len=%-4llu: %llu MB/s (%llu ns/call)\n",
+					   off, len, mbps, ns_per_call);
+			}
+		}
+	}
+
+	vfree(buf1);
+	vfree(buf2);
+}
+
+static void string_bench_memcmp(struct kunit *test)
+{
+	if (!IS_ENABLED(CONFIG_STRING_KUNIT_BENCH)) {
+		kunit_skip(test, "CONFIG_STRING_KUNIT_BENCH not enabled");
+		return;
+	}
+	do_string_bench_memcmp(test);
+}
+
 static struct kunit_case string_test_cases[] = {
 	KUNIT_CASE(string_test_memset16),
 	KUNIT_CASE(string_test_memset32),
@@ -910,6 +1018,8 @@ static struct kunit_case string_test_cases[] = {
 	KUNIT_CASE(string_bench_strnlen),
 	KUNIT_CASE(string_bench_strchr),
 	KUNIT_CASE(string_bench_strrchr),
+	KUNIT_CASE(string_test_memcmp),
+	KUNIT_CASE_SLOW(string_bench_memcmp),
 	{}
 };
 
-- 
2.43.0