* [PATCH v6 1/2] riscv: lib: add memcmp() implementation
2026-05-20 12:39 [PATCH v6 0/2] riscv: lib: add optimized memcmp() and extend KUnit tests Milan Tripkovic
@ 2026-05-20 12:39 ` Milan Tripkovic
2026-05-20 12:39 ` [PATCH v6 2/2] lib/string_kunit: extend benchmarks and unit test to memcmp() Milan Tripkovic
1 sibling, 0 replies; 4+ messages in thread
From: Milan Tripkovic @ 2026-05-20 12:39 UTC (permalink / raw)
To: pjw, palmer, aou, kees
Cc: alex, andy, linux-riscv, linux-kernel, linux-hardening,
Dusan.Stojkovic, Milan Tripkovic
From: Milan Tripkovic <Milan.Tripkovic@rt-rk.com>
Add an assembly implementation of memcmp() for RISC-V. The implementation
uses word-aligned loads for the generic path and the ZBB extension for
optimized sign resolution, with an assembly fallback for non-ZBB systems.
Benchmark results (QEMU TCG, rv64):
Len | Default |NoALIGN | ALIGN | %NoALIGN | %ALIGN
------|---------|--------|--------|----------|--------
1 B | 20.3 | 21.5 | 20.9 | +5.9% | +3.0%
7 B | 88.9 | 96.9 | 155.7 | +9.0% | +75.1%
8 B | 89.6 | 110.5 | 176.2 | +23.3% | +96.7%
16 B | 134.4 | 172.8 | 334.8 | +28.6% | +149.1%
31 B | 163.5 | 211.9 | 606.2 | +29.6% | +270.8%
64 B | 203.8 | 240.3 | 968.6 | +17.9% | +375.3%
127 B | 224.6 | 269.0 | 1362.8 | +19.8% | +506.8%
512 B | 235.7 | 269.9 | 1913.7 | +14.5% | +711.9%
1024 B| 256.8 | 283.5 | 2123.6 | +10.4% | +726.9%
4096 B| 263.8 | 299.7 | 2290.4 | +13.6% | +768.2%
Signed-off-by: Milan Tripkovic <Milan.Tripkovic@rt-rk.com>
---
v6 changes:
- Fixed build errors kernel test robot noticed.
- Link to v5: https://lore.kernel.org/all/20260519140029.1190381-1-milant2002@gmail.com/
v5 changes:
- Optimized generic memcmp path with word-aligned loads.
- Implemented non-ZBB fallback to byte comparison per review.
- Link to v4: https://lore.kernel.org/all/20260518131407.1026049-2-milant2002@gmail.com/
v2 changes:
- Added alignment checks for buffers to avoid expensive misaligned loads.
- Optimized the loop using end-pointers to reduce per-iteration overhead.
- Implemented word-aligned tail handling using ZBB shifts.
- Removed redundant pointer equality (a0 == a1) check.
- Retained BE support via #ifndef; ZBB rev8 is used for the LE fast-path.
- Link to v1: https://lore.kernel.org/all/20260512141007.1193033-1-milant2002@gmail.com/
arch/riscv/include/asm/string.h | 2 +
arch/riscv/lib/Makefile | 1 +
arch/riscv/lib/memcmp.S | 107 ++++++++++++++++++++++++++++++++
arch/riscv/purgatory/Makefile | 5 +-
4 files changed, 114 insertions(+), 1 deletion(-)
create mode 100644 arch/riscv/lib/memcmp.S
diff --git a/arch/riscv/include/asm/string.h b/arch/riscv/include/asm/string.h
index 764ffe8f6..5c5299678 100644
--- a/arch/riscv/include/asm/string.h
+++ b/arch/riscv/include/asm/string.h
@@ -18,6 +18,8 @@ extern asmlinkage void *__memcpy(void *, const void *, size_t);
#define __HAVE_ARCH_MEMMOVE
extern asmlinkage void *memmove(void *, const void *, size_t);
extern asmlinkage void *__memmove(void *, const void *, size_t);
+#define __HAVE_ARCH_MEMCMP
+extern asmlinkage int memcmp(const void *, const void *, size_t);
#if !(defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS))
#define __HAVE_ARCH_STRCMP
diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile
index 6f767b2a3..b529e1be1 100644
--- a/arch/riscv/lib/Makefile
+++ b/arch/riscv/lib/Makefile
@@ -3,6 +3,7 @@ lib-y += delay.o
lib-y += memcpy.o
lib-y += memset.o
lib-y += memmove.o
+lib-y += memcmp.o
ifeq ($(CONFIG_KASAN_GENERIC)$(CONFIG_KASAN_SW_TAGS),)
lib-y += strcmp.o
lib-y += strlen.o
diff --git a/arch/riscv/lib/memcmp.S b/arch/riscv/lib/memcmp.S
new file mode 100644
index 000000000..bdb92941d
--- /dev/null
+++ b/arch/riscv/lib/memcmp.S
@@ -0,0 +1,107 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include <linux/linkage.h>
+#include <asm/asm.h>
+#include <asm/alternative-macros.h>
+#include <asm/hwcap.h>
+
+#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB)
+.option push
+.option arch,+zbb
+#endif
+
+/* int memcmp(const void *cs, const void *ct, size_t n) */
+SYM_FUNC_START(memcmp)
+/*
+ * Parameters
+ * a0 - Pointer to first memory block (cs), also return value
+ * a1 - Pointer to second memory block (ct)
+ * a2 - Number of bytes to compare (n), decremented during loop
+ *
+ * Returns
+ * a0 - 0 if equal, positive if cs > ct, negative if cs < ct
+ *
+ * Clobbers
+ * t0, t1, t2, t3, t4
+ */
+ add t3, a0, a2
+ or t0, a0, a1
+ andi t0, t0, (SZREG - 1)
+ bnez t0, 5f
+
+ addi t4, t3, -SZREG
+ bltu t4, a0, 7f
+
+1:
+ REG_L t1, 0(a0)
+ REG_L t2, 0(a1)
+ bne t1, t2, 2f
+ addi a0, a0, SZREG
+ addi a1, a1, SZREG
+ bleu a0, t4, 1b
+
+7:
+#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB)
+ __ALTERNATIVE_CFG("j 5f", "nop", 0, RISCV_ISA_EXT_ZBB,
+ IS_ENABLED(CONFIG_RISCV_ISA_ZBB))
+
+ beq a0, t3, 4f
+ REG_L t1, 0(a0)
+ REG_L t2, 0(a1)
+
+ sub t0, t3, a0
+ li t4, SZREG
+ sub t0, t4, t0
+ slli t0, t0, 3
+
+#ifndef CONFIG_CPU_BIG_ENDIAN
+ rev8 t1, t1
+ rev8 t2, t2
+#endif
+ srl t1, t1, t0
+ srl t2, t2, t0
+
+ bne t1, t2, 8f
+ li a0, 0
+ ret
+#else
+ j 5f
+#endif
+5:
+ beq a0, t3, 4f
+6:
+ lbu t1, 0(a0)
+ lbu t2, 0(a1)
+ bne t1, t2, 3f
+ addi a0, a0, 1
+ addi a1, a1, 1
+ bne a0, t3, 6b
+
+4: li a0, 0
+ ret
+2:
+#if !defined(CONFIG_CPU_BIG_ENDIAN) && \
+ defined(CONFIG_TOOLCHAIN_HAS_ZBB) && defined(CONFIG_RISCV_ISA_ZBB)
+ __ALTERNATIVE_CFG("j 5b", "nop", 0, RISCV_ISA_EXT_ZBB, IS_ENABLED(CONFIG_RISCV_ISA_ZBB))
+ rev8 t1, t1
+ rev8 t2, t2
+#elif !defined(CONFIG_CPU_BIG_ENDIAN)
+ j 5b
+#endif
+8:
+ sltu a0, t2, t1
+ sltu t0, t1, t2
+ sub a0, a0, t0
+ ret
+
+3:
+ sub a0, t1, t2
+ ret
+
+SYM_FUNC_END(memcmp)
+SYM_FUNC_ALIAS(__pi_memcmp, memcmp)
+EXPORT_SYMBOL(memcmp)
+
+#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB)
+.option pop
+#endif
diff --git a/arch/riscv/purgatory/Makefile b/arch/riscv/purgatory/Makefile
index b0358a78f..456929971 100644
--- a/arch/riscv/purgatory/Makefile
+++ b/arch/riscv/purgatory/Makefile
@@ -1,6 +1,6 @@
# SPDX-License-Identifier: GPL-2.0
-purgatory-y := purgatory.o sha256.o entry.o string.o ctype.o memcpy.o memset.o
+purgatory-y := purgatory.o sha256.o entry.o string.o ctype.o memcpy.o memset.o memcmp.o
ifeq ($(CONFIG_KASAN_GENERIC)$(CONFIG_KASAN_SW_TAGS),)
purgatory-y += strcmp.o strlen.o strncmp.o strnlen.o strchr.o strrchr.o
endif
@@ -41,6 +41,9 @@ $(obj)/strchr.o: $(srctree)/arch/riscv/lib/strchr.S FORCE
$(obj)/strrchr.o: $(srctree)/arch/riscv/lib/strrchr.S FORCE
$(call if_changed_rule,as_o_S)
+$(obj)/memcmp.o: $(srctree)/arch/riscv/lib/memcmp.S FORCE
+ $(call if_changed_rule,as_o_S)
+
CFLAGS_sha256.o := -D__DISABLE_EXPORTS -D__NO_FORTIFY
CFLAGS_string.o := -D__DISABLE_EXPORTS
CFLAGS_ctype.o := -D__DISABLE_EXPORTS
--
2.43.0
^ permalink raw reply [flat|nested] 4+ messages in thread* [PATCH v6 2/2] lib/string_kunit: extend benchmarks and unit test to memcmp()
2026-05-20 12:39 [PATCH v6 0/2] riscv: lib: add optimized memcmp() and extend KUnit tests Milan Tripkovic
2026-05-20 12:39 ` [PATCH v6 1/2] riscv: lib: add memcmp() implementation Milan Tripkovic
@ 2026-05-20 12:39 ` Milan Tripkovic
2026-08-06 17:56 ` Paul Walmsley
1 sibling, 1 reply; 4+ messages in thread
From: Milan Tripkovic @ 2026-05-20 12:39 UTC (permalink / raw)
To: pjw, palmer, aou, kees
Cc: alex, andy, linux-riscv, linux-kernel, linux-hardening,
Dusan.Stojkovic, Milan Tripkovic
From: Milan Tripkovic <Milan.Tripkovic@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@rt-rk.com>
---
v6 changes:
- Fixed build errors kernel test robot noticed.
- Link to v5: https://lore.kernel.org/all/20260519140029.1190381-1-milant2002@gmail.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 | 106 +++++++++++++++++++++++++++++++++++++++
1 file changed, 106 insertions(+)
diff --git a/lib/tests/string_kunit.c b/lib/tests/string_kunit.c
index 0819ace5b..d395627f7 100644
--- a/lib/tests/string_kunit.c
+++ b/lib/tests/string_kunit.c
@@ -881,6 +881,110 @@ 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;
+ 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];
+ iterations = (len < 512) ? 100000ULL : 10000ULL;
+ elapsed = STRING_BENCH(iterations, memcmp, buf1, buf2 + off, 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 +1014,8 @@ 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
^ permalink raw reply [flat|nested] 4+ messages in thread