RISC-V: improve string-function assembly

Adapt the suggestions for the assembly string functions that Andrew
suggested but that I didn't manage to include into the series that
got applied.

This includes improvements to two comments, removal of unneeded labels
and moving one instruction slightly higher to contradict an
explanatory comment.

Suggested-by: Andrew Jones <[email protected]>
Signed-off-by: Heiko Stuebner <[email protected]>
Reviewed-by: Andrew Jones <[email protected]>
Tested-by: Conor Dooley <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Palmer Dabbelt <[email protected]>

Author: Heiko Stuebner

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

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

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
@@ -114,23 +114,21 @@ 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