[PATCH] arm64: save movk instructions in mov_q when the lower 16|32 bits are all zero

[Jisheng Zhang]

Currently mov_q is used to move a constant into a 64-bit register,
when the lower 16 or 32bits of the constant are all zero, the mov_q
emits one or two useless movk instructions. If the mov_q macro is used
in hot code path, we want to save the movk instructions as much as
possible. For example, when CONFIG_ARM64_MTE is 'Y' and
CONFIG_KASAN_HW_TAGS is 'N', the following code in __cpu_setup()
routine is the pontential optimization target:

        /* set the TCR_EL1 bits */
        mov_q   x10, TCR_MTE_FLAGS

Before the patch:
	mov	x10, #0x10000000000000
	movk	x10, #0x40, lsl #32
	movk	x10, #0x0, lsl #16
	movk	x10, #0x0

After the patch:
	mov	x10, #0x10000000000000
	movk	x10, #0x40, lsl #32

Signed-off-by: Jisheng Zhang <jszhang at kernel.org>
---
 arch/arm64/include/asm/assembler.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 8c5a61aeaf8e..09f408424cae 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -568,9 +568,13 @@ alternative_endif
 	movz	\reg, :abs_g3:\val
 	movk	\reg, :abs_g2_nc:\val
 	.endif
+	.if ((((\val) >> 16) & 0xffff) != 0)
 	movk	\reg, :abs_g1_nc:\val
 	.endif
+	.endif
+	.if (((\val) & 0xffff) != 0)
 	movk	\reg, :abs_g0_nc:\val
+	.endif
 	.endm
 
 /*
-- 
2.34.1