armv8/cache.S: Triple with single instruction

Replace the current 2-instruction 2-step tripling code by a
corresponding single instruction leveraging ARMv8-A's "flexible second
operand as a register with optional shift". This has the added benefit
(albeit arguably negligible) of reducing the final code size.

Fix the comment as the tripled cache level is placed in x12, not x0.

Signed-off-by: Pierre-Clément Tosi <ptosi@google.com>

diff --git a/arch/arm/cpu/armv8/cache.S b/arch/arm/cpu/armv8/cache.S
index eec2958..d1cee23 100644 (file)
--- a/arch/arm/cpu/armv8/cache.S
+++ b/arch/arm/cpu/armv8/cache.S
@@ -80,8 +80,7 @@ ENTRY(__asm_dcache_all)
        /* x15 <- return address */
 
 loop_level:
-       lsl     x12, x0, #1
-       add     x12, x12, x0            /* x0 <- tripled cache level */
+       add     x12, x0, x0, lsl #1     /* x12 <- tripled cache level */
        lsr     x12, x10, x12
        and     x12, x12, #7            /* x12 <- cache type */
        cmp     x12, #2