Prefer RIP-relative addressing where possible, which removes the need for boot time relocation fixups. Co-developed-by: Thomas Garnier <thgarnie@xxxxxxxxxxxx> Signed-off-by: Thomas Garnier <thgarnie@xxxxxxxxxxxx> Signed-off-by: Ard Biesheuvel <ardb@xxxxxxxxxx> --- arch/x86/crypto/cast5-avx-x86_64-asm_64.S | 38 +++++++++++--------- 1 file changed, 21 insertions(+), 17 deletions(-) diff --git a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S index 0326a01503c3a554..b4e460a87f18ddaa 100644 --- a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S @@ -84,15 +84,19 @@ #define lookup_32bit(src, dst, op1, op2, op3, interleave_op, il_reg) \ movzbl src ## bh, RID1d; \ + leaq s1(%rip), RID2; \ + movl (RID2,RID1,4), dst ## d; \ movzbl src ## bl, RID2d; \ + leaq s2(%rip), RID1; \ + op1 (RID1,RID2,4), dst ## d; \ shrq $16, src; \ - movl s1(, RID1, 4), dst ## d; \ - op1 s2(, RID2, 4), dst ## d; \ movzbl src ## bh, RID1d; \ + leaq s3(%rip), RID2; \ + op2 (RID2,RID1,4), dst ## d; \ movzbl src ## bl, RID2d; \ interleave_op(il_reg); \ - op2 s3(, RID1, 4), dst ## d; \ - op3 s4(, RID2, 4), dst ## d; + leaq s4(%rip), RID1; \ + op3 (RID1,RID2,4), dst ## d; #define dummy(d) /* do nothing */ @@ -151,15 +155,15 @@ subround(l ## 3, r ## 3, l ## 4, r ## 4, f); #define enc_preload_rkr() \ - vbroadcastss .L16_mask, RKR; \ + vbroadcastss .L16_mask(%rip), RKR; \ /* add 16-bit rotation to key rotations (mod 32) */ \ vpxor kr(CTX), RKR, RKR; #define dec_preload_rkr() \ - vbroadcastss .L16_mask, RKR; \ + vbroadcastss .L16_mask(%rip), RKR; \ /* add 16-bit rotation to key rotations (mod 32) */ \ vpxor kr(CTX), RKR, RKR; \ - vpshufb .Lbswap128_mask, RKR, RKR; + vpshufb .Lbswap128_mask(%rip), RKR, RKR; #define transpose_2x4(x0, x1, t0, t1) \ vpunpckldq x1, x0, t0; \ @@ -235,9 +239,9 @@ SYM_FUNC_START_LOCAL(__cast5_enc_blk16) movq %rdi, CTX; - vmovdqa .Lbswap_mask, RKM; - vmovd .Lfirst_mask, R1ST; - vmovd .L32_mask, R32; + vmovdqa .Lbswap_mask(%rip), RKM; + vmovd .Lfirst_mask(%rip), R1ST; + vmovd .L32_mask(%rip), R32; enc_preload_rkr(); inpack_blocks(RL1, RR1, RTMP, RX, RKM); @@ -271,7 +275,7 @@ SYM_FUNC_START_LOCAL(__cast5_enc_blk16) popq %rbx; popq %r15; - vmovdqa .Lbswap_mask, RKM; + vmovdqa .Lbswap_mask(%rip), RKM; outunpack_blocks(RR1, RL1, RTMP, RX, RKM); outunpack_blocks(RR2, RL2, RTMP, RX, RKM); @@ -308,9 +312,9 @@ SYM_FUNC_START_LOCAL(__cast5_dec_blk16) movq %rdi, CTX; - vmovdqa .Lbswap_mask, RKM; - vmovd .Lfirst_mask, R1ST; - vmovd .L32_mask, R32; + vmovdqa .Lbswap_mask(%rip), RKM; + vmovd .Lfirst_mask(%rip), R1ST; + vmovd .L32_mask(%rip), R32; dec_preload_rkr(); inpack_blocks(RL1, RR1, RTMP, RX, RKM); @@ -341,7 +345,7 @@ SYM_FUNC_START_LOCAL(__cast5_dec_blk16) round(RL, RR, 1, 2); round(RR, RL, 0, 1); - vmovdqa .Lbswap_mask, RKM; + vmovdqa .Lbswap_mask(%rip), RKM; popq %rbx; popq %r15; @@ -504,8 +508,8 @@ SYM_FUNC_START(cast5_ctr_16way) vpcmpeqd RKR, RKR, RKR; vpaddq RKR, RKR, RKR; /* low: -2, high: -2 */ - vmovdqa .Lbswap_iv_mask, R1ST; - vmovdqa .Lbswap128_mask, RKM; + vmovdqa .Lbswap_iv_mask(%rip), R1ST; + vmovdqa .Lbswap128_mask(%rip), RKM; /* load IV and byteswap */ vmovq (%rcx), RX; -- 2.39.2
