From: Milan Tripkovic <[email protected]> Add an assembly implementation of memcmp() for RISC-V. The implementation uses the ZBB extension for word-at-a-time comparison and an assembly fallback for non-ZBB systems.
Benchmark results (QEMU TCG, rv64, Aligned): Len | Default | NoZBB | ZBB | %NoZBB | %ZBB ------|---------|--------|--------|--------|------- 1 B | 20.3 | 25.0 | 20.9 | +23.2% | +3.0% 7 B | 88.9 | 107.5 | 155.7 | +20.9% | +75.1% 8 B | 89.6 | 110.9 | 176.2 | +23.8% | +96.7% 16 B | 134.4 | 172.4 | 334.8 | +28.3% | +149.1% 31 B | 163.5 | 220.5 | 606.2 | +34.9% | +270.8% 64 B | 203.8 | 235.9 | 968.6 | +15.8% | +375.3% 127 B | 224.6 | 268.7 | 1362.8 | +19.6% | +506.8% 512 B | 235.7 | 271.1 | 1913.7 | +15.0% | +711.9% 1024 B| 256.8 | 290.6 | 2123.6 | +13.2% | +726.9% 4096 B| 263.8 | 302.9 | 2290.4 | +14.8% | +768.2% Benchmark results (QEMU TCG, rv64, Unaligned - Offset 3): Len | Default | NoZBB | ZBB | %NoZBB | %ZBB ------|---------|--------|--------|--------|------- 1 B | 20.7 | 21.7 | 21.5 | +4.8% | +3.9% 7 B | 96.2 | 99.1 | 96.9 | +3.0% | +0.7% 8 B | 97.5 | 118.5 | 110.5 | +21.5% | +13.3% 16 B | 136.7 | 166.6 | 172.8 | +21.9% | +26.4% 31 B | 167.6 | 206.5 | 211.9 | +23.2% | +26.4% 64 B | 204.4 | 229.9 | 240.3 | +12.5% | +17.6% 127 B | 229.6 | 261.7 | 269.0 | +14.0% | +17.2% 512 B | 245.5 | 260.8 | 269.9 | +6.2% | +9.9% 1024 B| 246.9 | 261.2 | 283.5 | +5.8% | +14.8% 4096 B| 250.7 | 295.8 | 299.7 | +18.0% | +19.5% Signed-off-by: Milan Tripkovic <[email protected]> --- arch/riscv/include/asm/string.h | 2 + arch/riscv/lib/Makefile | 1 + arch/riscv/lib/memcmp.S | 124 ++++++++++++++++++++++++++++++++ arch/riscv/purgatory/Makefile | 5 +- 4 files changed, 131 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 764ffe8f6479..5c5299678c66 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 6f767b2a349d..b529e1be18b2 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 000000000000..f7d0eaa08880 --- /dev/null +++ b/arch/riscv/lib/memcmp.S @@ -0,0 +1,124 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include <linux/linkage.h> +#include <asm/asm.h> +#include <asm/alternative-macros.h> +#include <asm/hwcap.h> + +/* int memcmp(const void *cs, const void *ct, size_t n) */ +SYM_FUNC_START(memcmp) + + __ALTERNATIVE_CFG("nop", "j memcmp_zbb", 0, RISCV_ISA_EXT_ZBB, + IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) +/* + * 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), transformed to end pointer (a0 + n) + * + * Returns + * a0 - 0 if equal, positive if cs > ct, negative if cs < ct + * + * Clobbers + * t0, t1 + */ + beqz a2, 2f + add a2, a0, a2 +1: + lbu t0, 0(a0) + lbu t1, 0(a1) + bne t0, t1, 3f + addi a0, a0, 1 + addi a1, a1, 1 + bne a0, a2, 1b +2: + li a0, 0 + ret +3: + sub a0, t0, t1 + ret + + +memcmp_zbb: +.option push +.option arch,+zbb +/* + * 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: + 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 +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: +#ifndef CONFIG_CPU_BIG_ENDIAN + rev8 t1, t1 + rev8 t2, t2 +#endif +8: + sltu a0, t2, t1 + sltu t0, t1, t2 + sub a0, a0, t0 + ret + +3: + sub a0, t1, t2 + ret + +.option pop + +SYM_FUNC_END(memcmp) +SYM_FUNC_ALIAS(__pi_memcmp, memcmp) +EXPORT_SYMBOL(memcmp) diff --git a/arch/riscv/purgatory/Makefile b/arch/riscv/purgatory/Makefile index b0358a78f11a..456929971da7 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
