Merge tag 'riscv-for-linus-6.3-mw2' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull more RISC-V updates from Palmer Dabbelt:

 - Some cleanups and fixes for the Zbb-optimized string routines

 - Support for custom (vendor or implementation defined) perf events

 - COMMAND_LINE_SIZE has been increased to 1024

* tag 'riscv-for-linus-6.3-mw2' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux:
  riscv: Bump COMMAND_LINE_SIZE value to 1024
  drivers/perf: RISC-V: Allow programming custom firmware events
  riscv, lib: Fix Zbb strncmp
  RISC-V: improve string-function assembly

4 files changed, 27 insertions, 17 deletions

diff --git a/arch/riscv/include/uapi/asm/setup.h b/arch/riscv/include/uapi/asm/setup.h
new file mode 100644
index 000000000000..66b13a522880
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/setup.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+
+#ifndef _UAPI_ASM_RISCV_SETUP_H
+#define _UAPI_ASM_RISCV_SETUP_H
+
+#define COMMAND_LINE_SIZE	1024
+
+#endif /* _UAPI_ASM_RISCV_SETUP_H */
diff --git a/arch/riscv/lib/strcmp.S b/arch/riscv/lib/strcmp.S
index 986ab23fe787..c42a8412547f 100644
--- a/arch/riscv/lib/strcmp.S
+++ b/arch/riscv/lib/strcmp.S
@@ -40,7 +40,9 @@ SYM_FUNC_START(strcmp)
 	ret
 
 /*
- * Variant of strcmp using the ZBB extension if available
+ * Variant of strcmp using the ZBB extension if available.
+ * The code was published as part of the bitmanip manual
+ * in Appendix A.
  */
 #ifdef CONFIG_RISCV_ISA_ZBB
 strcmp_zbb:
@@ -57,7 +59,7 @@ strcmp_zbb:
 	 *   a1 - string2
 	 *
 	 * Clobbers
-	 *   t0, t1, t2, t3, t4, t5
+	 *   t0, t1, t2, t3, t4
 	 */
 
 	or	t2, a0, a1
diff --git a/arch/riscv/lib/strlen.S b/arch/riscv/lib/strlen.S
index 8345ceeee3f6..15bb8f3aa959 100644
--- a/arch/riscv/lib/strlen.S
+++ b/arch/riscv/lib/strlen.S
@@ -96,7 +96,7 @@ strlen_zbb:
 	 * of valid bytes in this chunk.
 	 */
 	srli	a0, t1, 3
-	bgtu	t3, a0, 3f
+	bgtu	t3, a0, 2f
 
 	/* Prepare for the word comparison loop. */
 	addi	t2, t0, SZREG
@@ -112,20 +112,20 @@ strlen_zbb:
 	addi	t0, t0, SZREG
 	orc.b	t1, t1
 	beq	t1, t3, 1b
-2:
+
 	not	t1, t1
 	CZ	t1, t1
+	srli	t1, t1, 3
 
-	/* Get number of processed words.  */
+	/* Get number of processed bytes. */
 	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:
+2:
 	ret
 
 .option pop
diff --git a/arch/riscv/lib/strncmp.S b/arch/riscv/lib/strncmp.S
index ee49595075be..7ac2f667285a 100644
--- a/arch/riscv/lib/strncmp.S
+++ b/arch/riscv/lib/strncmp.S
@@ -70,7 +70,7 @@ strncmp_zbb:
 	li	t5, -1
 	and	t2, t2, SZREG-1
 	add	t4, a0, a2
-	bnez	t2, 4f
+	bnez	t2, 3f
 
 	/* Adjust limit for fast-path.  */
 	andi	t6, t4, -SZREG
@@ -78,11 +78,13 @@ strncmp_zbb:
 	/* Main loop for aligned string.  */
 	.p2align 3
 1:
-	bgt	a0, t6, 3f
+	bge	a0, t6, 3f
 	REG_L	t0, 0(a0)
 	REG_L	t1, 0(a1)
 	orc.b	t3, t0
 	bne	t3, t5, 2f
+	orc.b	t3, t1
+	bne	t3, t5, 2f
 	addi	a0, a0, SZREG
 	addi	a1, a1, SZREG
 	beq	t0, t1, 1b
@@ -114,23 +116,21 @@ strncmp_zbb:
 	ret
 
 	/* Simple loop for misaligned strings.  */
-3:
-	/* Restore limit for slow-path.  */
 	.p2align 3
-4:
-	bge	a0, t4, 6f
+3:
+	bge	a0, t4, 5f
 	lbu	t0, 0(a0)
 	lbu	t1, 0(a1)
 	addi	a0, a0, 1
 	addi	a1, a1, 1
-	bne	t0, t1, 5f
-	bnez	t0, 4b
+	bne	t0, t1, 4f
+	bnez	t0, 3b
 
-5:
+4:
 	sub	a0, t0, t1
 	ret
 
-6:
+5:
 	li	a0, 0
 	ret