riscv: lib: optimize strlen loop efficiency

Optimize the generic strlen implementation by using a pre-decrement
pointer. This reduces the loop body from 4 instructions to 3 and
eliminates the unconditional jump ('j').

Old loop (4 instructions, 2 branches):
  1: lbu t0, 0(t1); beqz t0, 2f; addi t1, t1, 1; j 1b

New loop (3 instructions, 1 branch):
  1: addi t1, t1, 1; lbu t0, 0(t1); bnez t0, 1b

This change improves execution efficiency and reduces branch pressure
for systems without the Zbb extension.

Signed-off-by: Feng Jiang <jiangfeng@kylinos.cn>
Link: https://patch.msgid.link/20251218032614.57356-1-jiangfeng@kylinos.cn
Signed-off-by: Paul Walmsley <pjw@kernel.org>

diff --git a/arch/riscv/lib/strlen.S b/arch/riscv/lib/strlen.S
index eb4d2b7ed22b6418ee32c8a29218d2e901de5f54..e7736ccda5141adbfa5671d978cf94b0769091d9 100644 (file)
--- a/arch/riscv/lib/strlen.S
+++ b/arch/riscv/lib/strlen.S
@@ -21,13 +21,11 @@ SYM_FUNC_START(strlen)
         * Clobbers:
         *   t0, t1
         */
-       mv      t1, a0
+       addi    t1, a0, -1
 1:
-       lbu     t0, 0(t1)
-       beqz    t0, 2f
        addi    t1, t1, 1
-       j       1b
-2:
+       lbu     t0, 0(t1)
+       bnez    t0, 1b
        sub     a0, t1, a0
        ret