From: Eric Biggers <ebiggers@xxxxxxxxxx> Prefer immediates of -128 to 128, since the former fits in a signed byte, saving 3 bytes per instruction. Also prefer VEX-coded instructions to EVEX where this is easy to do. Signed-off-by: Eric Biggers <ebiggers@xxxxxxxxxx> --- arch/x86/crypto/aes-xts-avx-x86_64.S | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) diff --git a/arch/x86/crypto/aes-xts-avx-x86_64.S b/arch/x86/crypto/aes-xts-avx-x86_64.S index bb3d0dfeca575..a49637f0a729d 100644 --- a/arch/x86/crypto/aes-xts-avx-x86_64.S +++ b/arch/x86/crypto/aes-xts-avx-x86_64.S @@ -186,10 +186,11 @@ .endif // V30-V31 are currently unused. .endm // Move a vector between memory and a register. +// The register operand must be in the first 16 vector registers. .macro _vmovdqu src, dst .if VL < 64 vmovdqu \src, \dst .else vmovdqu8 \src, \dst @@ -206,15 +207,16 @@ vbroadcasti32x4 \src, \dst .endif .endm // XOR two vectors together. +// Any register operands must be in the first 16 vector registers. .macro _vpxor src1, src2, dst -.if USE_AVX10 - vpxord \src1, \src2, \dst -.else +.if VL < 64 vpxor \src1, \src2, \dst +.else + vpxord \src1, \src2, \dst .endif .endm // XOR three vectors together. .macro _xor3 src1, src2, src3_and_dst @@ -559,22 +561,22 @@ _setup_round_keys \enc // Compute the first set of tweaks TWEAK[0-3]. _compute_first_set_of_tweaks - sub $4*VL, LEN + add $-4*VL, LEN // shorter than 'sub 4*VL' when VL=32 jl .Lhandle_remainder\@ .Lmain_loop\@: // This is the main loop, en/decrypting 4*VL bytes per iteration. // XOR each source block with its tweak and the zero-th round key. .if USE_AVX10 - vmovdqu8 0*VL(SRC), V0 - vmovdqu8 1*VL(SRC), V1 - vmovdqu8 2*VL(SRC), V2 - vmovdqu8 3*VL(SRC), V3 + _vmovdqu 0*VL(SRC), V0 + _vmovdqu 1*VL(SRC), V1 + _vmovdqu 2*VL(SRC), V2 + _vmovdqu 3*VL(SRC), V3 vpternlogd $0x96, TWEAK0, KEY0, V0 vpternlogd $0x96, TWEAK1, KEY0, V1 vpternlogd $0x96, TWEAK2, KEY0, V2 vpternlogd $0x96, TWEAK3, KEY0, V3 .else @@ -616,13 +618,13 @@ _vmovdqu V3, 3*VL(DST) // Finish computing the next set of tweaks. _tweak_step 1000 - add $4*VL, SRC - add $4*VL, DST - sub $4*VL, LEN + sub $-4*VL, SRC // shorter than 'add 4*VL' when VL=32 + sub $-4*VL, DST + add $-4*VL, LEN jge .Lmain_loop\@ // Check for the uncommon case where the data length isn't a multiple of // 4*VL. Handle it out-of-line in order to optimize for the common // case. In the common case, just fall through to the ret. -- 2.47.1
