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>

1 files changed, 105 insertions, 0 deletions

diff --git a/arch/riscv/lib/strlen.S b/arch/riscv/lib/strlen.S
index 0a3b11853efd..0f9dbf93301a 100644
--- a/arch/riscv/lib/strlen.S
+++ b/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)