Merge patch series "Zbb string optimizations"

Heiko Stuebner <heiko@sntech.de> says:

From: Heiko Stuebner <heiko.stuebner@vrull.eu>

This series still tries to allow optimized string functions for specific
extensions. The last approach of using an inline base function to hold
the alternative calls did cause some issues in a number of places

So instead of that we're now just using an alternative j at the beginning
of the generic function to jump to a separate place inside the function
itself.

* b4-shazam-merge:
  RISC-V: add zbb support to string functions
  RISC-V: add infrastructure to allow different str* implementations

Link: https://lore.kernel.org/r/20230113212301.3534711-1-heiko@sntech.de
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

arch/riscv/Kconfig

@@ -416,6 +416,30 @@ config RISCV_ISA_SVPBMT
 
 	   If you don't know what to do here, say Y.
 
+config TOOLCHAIN_HAS_ZBB
+	bool
+	default y
+	depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zbb)
+	depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zbb)
+	depends on LLD_VERSION >= 150000 || LD_VERSION >= 23900
+	depends on AS_IS_GNU
+
+config RISCV_ISA_ZBB
+	bool "Zbb extension support for bit manipulation instructions"
+	depends on TOOLCHAIN_HAS_ZBB
+	depends on !XIP_KERNEL && MMU
+	select RISCV_ALTERNATIVE
+	default y
+	help
+	   Adds support to dynamically detect the presence of the ZBB
+	   extension (basic bit manipulation) and enable its usage.
+
+	   The Zbb extension provides instructions to accelerate a number
+	   of bit-specific operations (count bit population, sign extending,
+	   bitrotation, etc).
+
+	   If you don't know what to do here, say Y.
+
 config TOOLCHAIN_HAS_ZICBOM
 	bool
 	default y

arch/riscv/include/asm/errata_list.h

@@ -24,7 +24,8 @@
 
 #define	CPUFEATURE_SVPBMT 0
 #define	CPUFEATURE_ZICBOM 1
-#define	CPUFEATURE_NUMBER 2
+#define	CPUFEATURE_ZBB 2
+#define	CPUFEATURE_NUMBER 3
 
 #ifdef __ASSEMBLY__
 

arch/riscv/include/asm/hwcap.h

@@ -58,6 +58,7 @@ enum riscv_isa_ext_id {
 	RISCV_ISA_EXT_SSTC,
 	RISCV_ISA_EXT_SVINVAL,
 	RISCV_ISA_EXT_SVPBMT,
+	RISCV_ISA_EXT_ZBB,
 	RISCV_ISA_EXT_ZICBOM,
 	RISCV_ISA_EXT_ZIHINTPAUSE,
 	RISCV_ISA_EXT_ID_MAX

arch/riscv/include/asm/string.h

@@ -18,6 +18,16 @@ 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_STRCMP
+extern asmlinkage int strcmp(const char *cs, const char *ct);
+
+#define __HAVE_ARCH_STRLEN
+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);
+
 /* For those files which don't want to check by kasan. */
 #if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)
 #define memcpy(dst, src, len) __memcpy(dst, src, len)

arch/riscv/kernel/cpu.c

@@ -185,6 +185,7 @@ arch_initcall(riscv_cpuinfo_init);
  * New entries to this struct should follow the ordering rules described above.
  */
 static struct riscv_isa_ext_data isa_ext_arr[] = {
+	__RISCV_ISA_EXT_DATA(zbb, RISCV_ISA_EXT_ZBB),
 	__RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM),
 	__RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE),
 	__RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF),

arch/riscv/kernel/cpufeature.c

@@ -227,6 +227,7 @@ void __init riscv_fill_hwcap(void)
 				SET_ISA_EXT_MAP("sstc", RISCV_ISA_EXT_SSTC);
 				SET_ISA_EXT_MAP("svinval", RISCV_ISA_EXT_SVINVAL);
 				SET_ISA_EXT_MAP("svpbmt", RISCV_ISA_EXT_SVPBMT);
+				SET_ISA_EXT_MAP("zbb", RISCV_ISA_EXT_ZBB);
 				SET_ISA_EXT_MAP("zicbom", RISCV_ISA_EXT_ZICBOM);
 				SET_ISA_EXT_MAP("zihintpause", RISCV_ISA_EXT_ZIHINTPAUSE);
 			}
@@ -302,6 +303,20 @@ static bool __init_or_module cpufeature_probe_zicbom(unsigned int stage)
 	return true;
 }
 
+static bool __init_or_module cpufeature_probe_zbb(unsigned int stage)
+{
+	if (!IS_ENABLED(CONFIG_RISCV_ISA_ZBB))
+		return false;
+
+	if (stage == RISCV_ALTERNATIVES_EARLY_BOOT)
+		return false;
+
+	if (!riscv_isa_extension_available(NULL, ZBB))
+		return false;
+
+	return true;
+}
+
 /*
  * Probe presence of individual extensions.
  *
@@ -320,6 +335,9 @@ static u32 __init_or_module cpufeature_probe(unsigned int stage)
 	if (cpufeature_probe_zicbom(stage))
 		cpu_req_feature |= BIT(CPUFEATURE_ZICBOM);
 
+	if (cpufeature_probe_zbb(stage))
+		cpu_req_feature |= BIT(CPUFEATURE_ZBB);
+
 	return cpu_req_feature;
 }
 

arch/riscv/kernel/riscv_ksyms.c

@@ -12,6 +12,9 @@
 EXPORT_SYMBOL(memset);
 EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(memmove);
+EXPORT_SYMBOL(strcmp);
+EXPORT_SYMBOL(strlen);
+EXPORT_SYMBOL(strncmp);
 EXPORT_SYMBOL(__memset);
 EXPORT_SYMBOL(__memcpy);
 EXPORT_SYMBOL(__memmove);

arch/riscv/lib/Makefile

@@ -3,6 +3,9 @@ lib-y			+= delay.o
 lib-y			+= memcpy.o
 lib-y			+= memset.o
 lib-y			+= memmove.o
+lib-y			+= strcmp.o
+lib-y			+= strlen.o
+lib-y			+= strncmp.o
 lib-$(CONFIG_MMU)	+= uaccess.o
 lib-$(CONFIG_64BIT)	+= tishift.o
 

arch/riscv/lib/strcmp.S

@@ -0,0 +1,121 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include <linux/linkage.h>
+#include <asm/asm.h>
+#include <asm-generic/export.h>
+#include <asm/alternative-macros.h>
+#include <asm/errata_list.h>
+
+/* int strcmp(const char *cs, const char *ct) */
+SYM_FUNC_START(strcmp)
+
+	ALTERNATIVE("nop", "j strcmp_zbb", 0, CPUFEATURE_ZBB, CONFIG_RISCV_ISA_ZBB)
+
+	/*
+	 * Returns
+	 *   a0 - comparison result, value like strcmp
+	 *
+	 * Parameters
+	 *   a0 - string1
+	 *   a1 - string2
+	 *
+	 * Clobbers
+	 *   t0, t1
+	 */
+1:
+	lbu	t0, 0(a0)
+	lbu	t1, 0(a1)
+	addi	a0, a0, 1
+	addi	a1, a1, 1
+	bne	t0, t1, 2f
+	bnez	t0, 1b
+	li	a0, 0
+	ret
+2:
+	/*
+	 * strcmp only needs to return (< 0, 0, > 0) values
+	 * not necessarily -1, 0, +1
+	 */
+	sub	a0, t0, t1
+	ret
+
+/*
+ * Variant of strcmp using the ZBB extension if available
+ */
+#ifdef CONFIG_RISCV_ISA_ZBB
+strcmp_zbb:
+
+.option push
+.option arch,+zbb
+
+	/*
+	 * Returns
+	 *   a0 - comparison result, value like strcmp
+	 *
+	 * Parameters
+	 *   a0 - string1
+	 *   a1 - string2
+	 *
+	 * Clobbers
+	 *   t0, t1, t2, t3, t4, t5
+	 */
+
+	or	t2, a0, a1
+	li	t4, -1
+	and	t2, t2, SZREG-1
+	bnez	t2, 3f
+
+	/* Main loop for aligned string.  */
+	.p2align 3
+1:
+	REG_L	t0, 0(a0)
+	REG_L	t1, 0(a1)
+	orc.b	t3, t0
+	bne	t3, t4, 2f
+	addi	a0, a0, SZREG
+	addi	a1, a1, SZREG
+	beq	t0, t1, 1b
+
+	/*
+	 * Words don't match, and no null byte in the first
+	 * word. Get bytes in big-endian order and compare.
+	 */
+#ifndef CONFIG_CPU_BIG_ENDIAN
+	rev8	t0, t0
+	rev8	t1, t1
+#endif
+
+	/* Synthesize (t0 >= t1) ? 1 : -1 in a branchless sequence. */
+	sltu	a0, t0, t1
+	neg	a0, a0
+	ori	a0, a0, 1
+	ret
+
+2:
+	/*
+	 * Found a null byte.
+	 * If words don't match, fall back to simple loop.
+	 */
+	bne	t0, t1, 3f
+
+	/* Otherwise, strings are equal. */
+	li	a0, 0
+	ret
+
+	/* Simple loop for misaligned strings. */
+	.p2align 3
+3:
+	lbu	t0, 0(a0)
+	lbu	t1, 0(a1)
+	addi	a0, a0, 1
+	addi	a1, a1, 1
+	bne	t0, t1, 4f
+	bnez	t0, 3b
+
+4:
+	sub	a0, t0, t1
+	ret
+
+.option pop
+#endif
+SYM_FUNC_END(strcmp)

arch/riscv/lib/strlen.S

@@ -0,0 +1,133 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include <linux/linkage.h>
+#include <asm/asm.h>
+#include <asm-generic/export.h>
+#include <asm/alternative-macros.h>
+#include <asm/errata_list.h>
+
+/* int strlen(const char *s) */
+SYM_FUNC_START(strlen)
+
+	ALTERNATIVE("nop", "j strlen_zbb", 0, CPUFEATURE_ZBB, CONFIG_RISCV_ISA_ZBB)
+
+	/*
+	 * Returns
+	 *   a0 - string length
+	 *
+	 * Parameters
+	 *   a0 - String to measure
+	 *
+	 * Clobbers:
+	 *   t0, t1
+	 */
+	mv	t1, a0
+1:
+	lbu	t0, 0(t1)
+	beqz	t0, 2f
+	addi	t1, t1, 1
+	j	1b
+2:
+	sub	a0, t1, a0
+	ret
+
+/*
+ * Variant of strlen using the ZBB extension if available
+ */
+#ifdef CONFIG_RISCV_ISA_ZBB
+strlen_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
+	 *
+	 * Clobbers
+	 *   t0, t1, t2, t3
+	 */
+
+	/* 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
+
+	/* 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
+	bgtu	t3, a0, 3f
+
+	/* 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
+	beq	t1, t3, 1b
+2:
+	not	t1, t1
+	CZ	t1, t1
+
+	/* Get number of processed words.  */
+	sub	t2, t0, t2
+
+	/* Add number of characters in the first word.  */
+	add	a0, a0, t2
+	srli	t1, t1, 3
+
+	/* Add number of characters in the last word.  */
+	add	a0, a0, t1
+3:
+	ret
+
+.option pop
+#endif
+SYM_FUNC_END(strlen)

arch/riscv/lib/strncmp.S

@@ -0,0 +1,139 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include <linux/linkage.h>
+#include <asm/asm.h>
+#include <asm-generic/export.h>
+#include <asm/alternative-macros.h>
+#include <asm/errata_list.h>
+
+/* int strncmp(const char *cs, const char *ct, size_t count) */
+SYM_FUNC_START(strncmp)
+
+	ALTERNATIVE("nop", "j strncmp_zbb", 0, CPUFEATURE_ZBB, CONFIG_RISCV_ISA_ZBB)
+
+	/*
+	 * Returns
+	 *   a0 - comparison result, value like strncmp
+	 *
+	 * Parameters
+	 *   a0 - string1
+	 *   a1 - string2
+	 *   a2 - number of characters to compare
+	 *
+	 * Clobbers
+	 *   t0, t1, t2
+	 */
+	li	t2, 0
+1:
+	beq	a2, t2, 2f
+	lbu	t0, 0(a0)
+	lbu	t1, 0(a1)
+	addi	a0, a0, 1
+	addi	a1, a1, 1
+	bne	t0, t1, 3f
+	addi	t2, t2, 1
+	bnez	t0, 1b
+2:
+	li	a0, 0
+	ret
+3:
+	/*
+	 * strncmp only needs to return (< 0, 0, > 0) values
+	 * not necessarily -1, 0, +1
+	 */
+	sub	a0, t0, t1
+	ret
+
+/*
+ * Variant of strncmp using the ZBB extension if available
+ */
+#ifdef CONFIG_RISCV_ISA_ZBB
+strncmp_zbb:
+
+.option push
+.option arch,+zbb
+
+	/*
+	 * Returns
+	 *   a0 - comparison result, like strncmp
+	 *
+	 * Parameters
+	 *   a0 - string1
+	 *   a1 - string2
+	 *   a2 - number of characters to compare
+	 *
+	 * Clobbers
+	 *   t0, t1, t2, t3, t4, t5, t6
+	 */
+
+	or	t2, a0, a1
+	li	t5, -1
+	and	t2, t2, SZREG-1
+	add	t4, a0, a2
+	bnez	t2, 4f
+
+	/* Adjust limit for fast-path.  */
+	andi	t6, t4, -SZREG
+
+	/* Main loop for aligned string.  */
+	.p2align 3
+1:
+	bgt	a0, t6, 3f
+	REG_L	t0, 0(a0)
+	REG_L	t1, 0(a1)
+	orc.b	t3, t0
+	bne	t3, t5, 2f
+	addi	a0, a0, SZREG
+	addi	a1, a1, SZREG
+	beq	t0, t1, 1b
+
+	/*
+	 * Words don't match, and no null byte in the first
+	 * word. Get bytes in big-endian order and compare.
+	 */
+#ifndef CONFIG_CPU_BIG_ENDIAN
+	rev8	t0, t0
+	rev8	t1, t1
+#endif
+
+	/* Synthesize (t0 >= t1) ? 1 : -1 in a branchless sequence.  */
+	sltu	a0, t0, t1
+	neg	a0, a0
+	ori	a0, a0, 1
+	ret
+
+2:
+	/*
+	 * Found a null byte.
+	 * If words don't match, fall back to simple loop.
+	 */
+	bne	t0, t1, 3f
+
+	/* Otherwise, strings are equal.  */
+	li	a0, 0
+	ret
+
+	/* Simple loop for misaligned strings.  */
+3:
+	/* Restore limit for slow-path.  */
+	.p2align 3
+4:
+	bge	a0, t4, 6f
+	lbu	t0, 0(a0)
+	lbu	t1, 0(a1)
+	addi	a0, a0, 1
+	addi	a1, a1, 1
+	bne	t0, t1, 5f
+	bnez	t0, 4b
+
+5:
+	sub	a0, t0, t1
+	ret
+
+6:
+	li	a0, 0
+	ret
+
+.option pop
+#endif
+SYM_FUNC_END(strncmp)

arch/riscv/purgatory/Makefile

@@ -2,6 +2,7 @@
 OBJECT_FILES_NON_STANDARD := y
 
 purgatory-y := purgatory.o sha256.o entry.o string.o ctype.o memcpy.o memset.o
+purgatory-y += strcmp.o strlen.o strncmp.o
 
 targets += $(purgatory-y)
 PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
@@ -18,6 +19,15 @@ $(obj)/memcpy.o: $(srctree)/arch/riscv/lib/memcpy.S FORCE
 $(obj)/memset.o: $(srctree)/arch/riscv/lib/memset.S FORCE
 	$(call if_changed_rule,as_o_S)
 
+$(obj)/strcmp.o: $(srctree)/arch/riscv/lib/strcmp.S FORCE
+	$(call if_changed_rule,as_o_S)
+
+$(obj)/strlen.o: $(srctree)/arch/riscv/lib/strlen.S FORCE
+	$(call if_changed_rule,as_o_S)
+
+$(obj)/strncmp.o: $(srctree)/arch/riscv/lib/strncmp.S FORCE
+	$(call if_changed_rule,as_o_S)
+
 $(obj)/sha256.o: $(srctree)/lib/crypto/sha256.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
@@ -77,6 +87,9 @@ CFLAGS_ctype.o			+= $(PURGATORY_CFLAGS)
 AFLAGS_REMOVE_entry.o		+= -Wa,-gdwarf-2
 AFLAGS_REMOVE_memcpy.o		+= -Wa,-gdwarf-2
 AFLAGS_REMOVE_memset.o		+= -Wa,-gdwarf-2
+AFLAGS_REMOVE_strcmp.o		+= -Wa,-gdwarf-2
+AFLAGS_REMOVE_strlen.o		+= -Wa,-gdwarf-2
+AFLAGS_REMOVE_strncmp.o		+= -Wa,-gdwarf-2
 
 $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
 		$(call if_changed,ld)