riscv: lib: add strnlen() implementation

Add an optimized strnlen() implementation for RISC-V. This version
includes a generic optimization and a Zbb-powered optimization using
the 'orc.b' instruction, derived from the strlen() implementation.

Benchmark results (QEMU TCG, rv64):
  Length | Original (MB/s) | Optimized (MB/s) | Improvement
  -------|-----------------|------------------|------------
  16 B   | 179             | 309              | +72.6%
  512 B  | 347             | 1562             | +350.1%
  4096 B | 356             | 1878             | +427.5%

Suggested-by: Qingfang Deng <dqfext@gmail.com>
Signed-off-by: Feng Jiang <jiangfeng@kylinos.cn>
Link: https://patch.msgid.link/20260130025018.172925-7-jiangfeng@kylinos.cn
Signed-off-by: Paul Walmsley <pjw@kernel.org>

arch/riscv/include/asm/string.h

@@ -28,6 +28,9 @@ extern asmlinkage __kernel_size_t strlen(const char *);
 
 #define __HAVE_ARCH_STRNCMP
 extern asmlinkage int strncmp(const char *cs, const char *ct, size_t count);
+
+#define __HAVE_ARCH_STRNLEN
+extern asmlinkage __kernel_size_t strnlen(const char *, size_t);
 #endif
 
 /* For those files which don't want to check by kasan. */

arch/riscv/lib/Makefile

@@ -7,6 +7,7 @@ ifeq ($(CONFIG_KASAN_GENERIC)$(CONFIG_KASAN_SW_TAGS),)
 lib-y			+= strcmp.o
 lib-y			+= strlen.o
 lib-y			+= strncmp.o
+lib-y			+= strnlen.o
 endif
 lib-y			+= csum.o
 ifeq ($(CONFIG_MMU), y)

arch/riscv/lib/strnlen.S

@@ -0,0 +1,164 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+/*
+ * Base on arch/riscv/lib/strlen.S
+ *
+ * Copyright (C) Feng Jiang <jiangfeng@kylinos.cn>
+ */
+
+#include <linux/linkage.h>
+#include <asm/asm.h>
+#include <asm/alternative-macros.h>
+#include <asm/hwcap.h>
+
+/* size_t strnlen(const char *s, size_t count) */
+SYM_FUNC_START(strnlen)
+
+	__ALTERNATIVE_CFG("nop", "j strnlen_zbb", 0, RISCV_ISA_EXT_ZBB,
+		IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB))
+
+
+	/*
+	 * Returns
+	 *   a0 - String length
+	 *
+	 * Parameters
+	 *   a0 - String to measure
+	 *   a1 - Max length of string
+	 *
+	 * Clobbers
+	 *   t0, t1, t2
+	 */
+	addi	t1, a0, -1
+	add	t2, a0, a1
+1:
+	addi	t1, t1, 1
+	beq	t1, t2, 2f
+	lbu	t0, 0(t1)
+	bnez	t0, 1b
+2:
+	sub	a0, t1, a0
+	ret
+
+
+/*
+ * Variant of strnlen using the ZBB extension if available
+ */
+#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB)
+strnlen_zbb:
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+# define CZ	clz
+# define SHIFT	sll
+#else
+# define CZ	ctz
+# define SHIFT	srl
+#endif
+
+.option push
+.option arch,+zbb
+
+	/*
+	 * Returns
+	 *   a0 - String length
+	 *
+	 * Parameters
+	 *   a0 - String to measure
+	 *   a1 - Max length of string
+	 *
+	 * Clobbers
+	 *   t0, t1, t2, t3, t4
+	 */
+
+	/* If maxlen is 0, return 0. */
+	beqz	a1, 3f
+
+	/* Number of irrelevant bytes in the first word. */
+	andi	t2, a0, SZREG-1
+
+	/* Align pointer. */
+	andi	t0, a0, -SZREG
+
+	li	t3, SZREG
+	sub	t3, t3, t2
+	slli	t2, t2, 3
+
+	/* Aligned boundary. */
+	add	t4, a0, a1
+	andi	t4, t4, -SZREG
+
+	/* Get the first word.  */
+	REG_L	t1, 0(t0)
+
+	/*
+	 * Shift away the partial data we loaded to remove the irrelevant bytes
+	 * preceding the string with the effect of adding NUL bytes at the
+	 * end of the string's first word.
+	 */
+	SHIFT	t1, t1, t2
+
+	/* Convert non-NUL into 0xff and NUL into 0x00. */
+	orc.b	t1, t1
+
+	/* Convert non-NUL into 0x00 and NUL into 0xff. */
+	not	t1, t1
+
+	/*
+	 * Search for the first set bit (corresponding to a NUL byte in the
+	 * original chunk).
+	 */
+	CZ	t1, t1
+
+	/*
+	 * The first chunk is special: compare against the number
+	 * of valid bytes in this chunk.
+	 */
+	srli	a0, t1, 3
+
+	/* Limit the result by maxlen. */
+	minu	a0, a0, a1
+
+	bgtu	t3, a0, 2f
+
+	/* Prepare for the word comparison loop. */
+	addi	t2, t0, SZREG
+	li	t3, -1
+
+	/*
+	 * Our critical loop is 4 instructions and processes data in
+	 * 4 byte or 8 byte chunks.
+	 */
+	.p2align 3
+1:
+	REG_L	t1, SZREG(t0)
+	addi	t0, t0, SZREG
+	orc.b	t1, t1
+	bgeu	t0, t4, 4f
+	beq	t1, t3, 1b
+4:
+	not	t1, t1
+	CZ	t1, t1
+	srli	t1, t1, 3
+
+	/* Get number of processed bytes. */
+	sub	t2, t0, t2
+
+	/* Add number of characters in the first word.  */
+	add	a0, a0, t2
+
+	/* Add number of characters in the last word.  */
+	add	a0, a0, t1
+
+	/* Ensure the final result does not exceed maxlen. */
+	minu	a0, a0, a1
+2:
+	ret
+3:
+	mv	a0, a1
+	ret
+
+.option pop
+#endif
+SYM_FUNC_END(strnlen)
+SYM_FUNC_ALIAS(__pi_strnlen, strnlen)
+EXPORT_SYMBOL(strnlen)

arch/riscv/purgatory/Makefile

@@ -2,7 +2,7 @@
 
 purgatory-y := purgatory.o sha256.o entry.o string.o ctype.o memcpy.o memset.o
 ifeq ($(CONFIG_KASAN_GENERIC)$(CONFIG_KASAN_SW_TAGS),)
-purgatory-y += strcmp.o strlen.o strncmp.o
+purgatory-y += strcmp.o strlen.o strncmp.o strnlen.o
 endif
 
 targets += $(purgatory-y)
@@ -32,6 +32,9 @@ $(obj)/strncmp.o: $(srctree)/arch/riscv/lib/strncmp.S FORCE
 $(obj)/sha256.o: $(srctree)/lib/crypto/sha256.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
+$(obj)/strnlen.o: $(srctree)/arch/riscv/lib/strnlen.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