RISC-V: add zbb support to string functions

Add handling for ZBB extension and add support for using it as a
variant for optimized string functions.

Support for the Zbb-str-variants is limited to the GNU-assembler
for now, as LLVM has not yet acquired the functionality to
selectively change the arch option in assembler code.
This is still under review at
    https://reviews.llvm.org/D123515

Co-developed-by: Christoph Muellner <christoph.muellner@vrull.eu>
Signed-off-by: Christoph Muellner <christoph.muellner@vrull.eu>
Signed-off-by: Heiko Stuebner <heiko.stuebner@vrull.eu>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20230113212301.3534711-3-heiko@sntech.de
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

Author: Heiko Stuebner

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/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/lib/strcmp.S

@@ -3,9 +3,14 @@
 #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
@@ -33,4 +38,84 @@ SYM_FUNC_START(strcmp)
 	 */
 	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

@@ -3,9 +3,14 @@
 #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
@@ -25,4 +30,104 @@ SYM_FUNC_START(strlen)
 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)