@@ -201,8 +201,8 @@ SYM_FUNC_START(crypto_aegis128_aesni_init)
movdqa KEY, STATE4
/* load the constants: */
- movdqa .Laegis128_const_0, STATE2
- movdqa .Laegis128_const_1, STATE1
+ movdqa .Laegis128_const_0(%rip), STATE2
+ movdqa .Laegis128_const_1(%rip), STATE1
pxor STATE2, STATE3
pxor STATE1, STATE4
@@ -682,7 +682,7 @@ SYM_TYPED_FUNC_START(crypto_aegis128_aesni_dec_tail)
punpcklbw T0, T0
punpcklbw T0, T0
punpcklbw T0, T0
- movdqa .Laegis128_counter, T1
+ movdqa .Laegis128_counter(%rip), T1
pcmpgtb T1, T0
pand T0, MSG
@@ -2717,7 +2717,7 @@ SYM_FUNC_END(aesni_cts_cbc_dec)
* BSWAP_MASK == endian swapping mask
*/
SYM_FUNC_START_LOCAL(_aesni_inc_init)
- movaps .Lbswap_mask, BSWAP_MASK
+ movaps .Lbswap_mask(%rip), BSWAP_MASK
movaps IV, CTR
pshufb BSWAP_MASK, CTR
mov $1, TCTR_LOW
@@ -649,7 +649,8 @@ _get_AAD_rest0\@:
vpshufb and an array of shuffle masks */
movq %r12, %r11
salq $4, %r11
- vmovdqu aad_shift_arr(%r11), \T1
+ leaq aad_shift_arr(%rip), %rax
+ vmovdqu (%rax,%r11,), \T1
vpshufb \T1, \T7, \T7
_get_AAD_rest_final\@:
vpshufb SHUF_MASK(%rip), \T7, \T7
@@ -80,7 +80,7 @@
transpose_4x4(c0, c1, c2, c3, a0, a1); \
transpose_4x4(d0, d1, d2, d3, a0, a1); \
\
- vmovdqu .Lshufb_16x16b, a0; \
+ vmovdqu .Lshufb_16x16b(%rip), a0; \
vmovdqu st1, a1; \
vpshufb a0, a2, a2; \
vpshufb a0, a3, a3; \
@@ -132,7 +132,7 @@
transpose_4x4(c0, c1, c2, c3, a0, a1); \
transpose_4x4(d0, d1, d2, d3, a0, a1); \
\
- vmovdqu .Lshufb_16x16b, a0; \
+ vmovdqu .Lshufb_16x16b(%rip), a0; \
vmovdqu st1, a1; \
vpshufb a0, a2, a2; \
vpshufb a0, a3, a3; \
@@ -300,11 +300,11 @@
x4, x5, x6, x7, \
t0, t1, t2, t3, \
t4, t5, t6, t7) \
- vmovdqa .Ltf_s2_bitmatrix, t0; \
- vmovdqa .Ltf_inv_bitmatrix, t1; \
- vmovdqa .Ltf_id_bitmatrix, t2; \
- vmovdqa .Ltf_aff_bitmatrix, t3; \
- vmovdqa .Ltf_x2_bitmatrix, t4; \
+ vmovdqa .Ltf_s2_bitmatrix(%rip), t0; \
+ vmovdqa .Ltf_inv_bitmatrix(%rip), t1; \
+ vmovdqa .Ltf_id_bitmatrix(%rip), t2; \
+ vmovdqa .Ltf_aff_bitmatrix(%rip), t3; \
+ vmovdqa .Ltf_x2_bitmatrix(%rip), t4; \
vgf2p8affineinvqb $(tf_s2_const), t0, x1, x1; \
vgf2p8affineinvqb $(tf_s2_const), t0, x5, x5; \
vgf2p8affineqb $(tf_inv_const), t1, x2, x2; \
@@ -324,13 +324,13 @@
x4, x5, x6, x7, \
t0, t1, t2, t3, \
t4, t5, t6, t7) \
- vmovdqa .Linv_shift_row, t0; \
- vmovdqa .Lshift_row, t1; \
- vbroadcastss .L0f0f0f0f, t6; \
- vmovdqa .Ltf_lo__inv_aff__and__s2, t2; \
- vmovdqa .Ltf_hi__inv_aff__and__s2, t3; \
- vmovdqa .Ltf_lo__x2__and__fwd_aff, t4; \
- vmovdqa .Ltf_hi__x2__and__fwd_aff, t5; \
+ vmovdqa .Linv_shift_row(%rip), t0; \
+ vmovdqa .Lshift_row(%rip), t1; \
+ vpbroadcastd .L0f0f0f0f(%rip), t6; \
+ vmovdqa .Ltf_lo__inv_aff__and__s2(%rip), t2; \
+ vmovdqa .Ltf_hi__inv_aff__and__s2(%rip), t3; \
+ vmovdqa .Ltf_lo__x2__and__fwd_aff(%rip), t4; \
+ vmovdqa .Ltf_hi__x2__and__fwd_aff(%rip), t5; \
\
vaesenclast t7, x0, x0; \
vaesenclast t7, x4, x4; \
@@ -1035,7 +1035,7 @@ SYM_FUNC_START_LOCAL(__aria_aesni_avx_ctr_gen_keystream_16way)
/* load IV and byteswap */
vmovdqu (%r8), %xmm8;
- vmovdqa .Lbswap128_mask (%rip), %xmm1;
+ vmovdqa .Lbswap128_mask(%rip), %xmm1;
vpshufb %xmm1, %xmm8, %xmm3; /* be => le */
vpcmpeqd %xmm0, %xmm0, %xmm0;
@@ -52,10 +52,10 @@
/* \
* S-function with AES subbytes \
*/ \
- vmovdqa .Linv_shift_row, t4; \
- vbroadcastss .L0f0f0f0f, t7; \
- vmovdqa .Lpre_tf_lo_s1, t0; \
- vmovdqa .Lpre_tf_hi_s1, t1; \
+ vmovdqa .Linv_shift_row(%rip), t4; \
+ vbroadcastss .L0f0f0f0f(%rip), t7; \
+ vmovdqa .Lpre_tf_lo_s1(%rip), t0; \
+ vmovdqa .Lpre_tf_hi_s1(%rip), t1; \
\
/* AES inverse shift rows */ \
vpshufb t4, x0, x0; \
@@ -68,8 +68,8 @@
vpshufb t4, x6, x6; \
\
/* prefilter sboxes 1, 2 and 3 */ \
- vmovdqa .Lpre_tf_lo_s4, t2; \
- vmovdqa .Lpre_tf_hi_s4, t3; \
+ vmovdqa .Lpre_tf_lo_s4(%rip), t2; \
+ vmovdqa .Lpre_tf_hi_s4(%rip), t3; \
filter_8bit(x0, t0, t1, t7, t6); \
filter_8bit(x7, t0, t1, t7, t6); \
filter_8bit(x1, t0, t1, t7, t6); \
@@ -83,8 +83,8 @@
filter_8bit(x6, t2, t3, t7, t6); \
\
/* AES subbytes + AES shift rows */ \
- vmovdqa .Lpost_tf_lo_s1, t0; \
- vmovdqa .Lpost_tf_hi_s1, t1; \
+ vmovdqa .Lpost_tf_lo_s1(%rip), t0; \
+ vmovdqa .Lpost_tf_hi_s1(%rip), t1; \
vaesenclast t4, x0, x0; \
vaesenclast t4, x7, x7; \
vaesenclast t4, x1, x1; \
@@ -95,16 +95,16 @@
vaesenclast t4, x6, x6; \
\
/* postfilter sboxes 1 and 4 */ \
- vmovdqa .Lpost_tf_lo_s3, t2; \
- vmovdqa .Lpost_tf_hi_s3, t3; \
+ vmovdqa .Lpost_tf_lo_s3(%rip), t2; \
+ vmovdqa .Lpost_tf_hi_s3(%rip), t3; \
filter_8bit(x0, t0, t1, t7, t6); \
filter_8bit(x7, t0, t1, t7, t6); \
filter_8bit(x3, t0, t1, t7, t6); \
filter_8bit(x6, t0, t1, t7, t6); \
\
/* postfilter sbox 3 */ \
- vmovdqa .Lpost_tf_lo_s2, t4; \
- vmovdqa .Lpost_tf_hi_s2, t5; \
+ vmovdqa .Lpost_tf_lo_s2(%rip), t4; \
+ vmovdqa .Lpost_tf_hi_s2(%rip), t5; \
filter_8bit(x2, t2, t3, t7, t6); \
filter_8bit(x5, t2, t3, t7, t6); \
\
@@ -443,7 +443,7 @@ SYM_FUNC_END(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
transpose_4x4(c0, c1, c2, c3, a0, a1); \
transpose_4x4(d0, d1, d2, d3, a0, a1); \
\
- vmovdqu .Lshufb_16x16b, a0; \
+ vmovdqu .Lshufb_16x16b(%rip), a0; \
vmovdqu st1, a1; \
vpshufb a0, a2, a2; \
vpshufb a0, a3, a3; \
@@ -482,7 +482,7 @@ SYM_FUNC_END(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
#define inpack16_pre(x0, x1, x2, x3, x4, x5, x6, x7, y0, y1, y2, y3, y4, y5, \
y6, y7, rio, key) \
vmovq key, x0; \
- vpshufb .Lpack_bswap, x0, x0; \
+ vpshufb .Lpack_bswap(%rip), x0, x0; \
\
vpxor 0 * 16(rio), x0, y7; \
vpxor 1 * 16(rio), x0, y6; \
@@ -533,7 +533,7 @@ SYM_FUNC_END(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
vmovdqu x0, stack_tmp0; \
\
vmovq key, x0; \
- vpshufb .Lpack_bswap, x0, x0; \
+ vpshufb .Lpack_bswap(%rip), x0, x0; \
\
vpxor x0, y7, y7; \
vpxor x0, y6, y6; \
@@ -64,12 +64,12 @@
/* \
* S-function with AES subbytes \
*/ \
- vbroadcasti128 .Linv_shift_row, t4; \
- vpbroadcastd .L0f0f0f0f, t7; \
- vbroadcasti128 .Lpre_tf_lo_s1, t5; \
- vbroadcasti128 .Lpre_tf_hi_s1, t6; \
- vbroadcasti128 .Lpre_tf_lo_s4, t2; \
- vbroadcasti128 .Lpre_tf_hi_s4, t3; \
+ vbroadcasti128 .Linv_shift_row(%rip), t4; \
+ vpbroadcastd .L0f0f0f0f(%rip), t7; \
+ vbroadcasti128 .Lpre_tf_lo_s1(%rip), t5; \
+ vbroadcasti128 .Lpre_tf_hi_s1(%rip), t6; \
+ vbroadcasti128 .Lpre_tf_lo_s4(%rip), t2; \
+ vbroadcasti128 .Lpre_tf_hi_s4(%rip), t3; \
\
/* AES inverse shift rows */ \
vpshufb t4, x0, x0; \
@@ -115,8 +115,8 @@
vinserti128 $1, t2##_x, x6, x6; \
vextracti128 $1, x1, t3##_x; \
vextracti128 $1, x4, t2##_x; \
- vbroadcasti128 .Lpost_tf_lo_s1, t0; \
- vbroadcasti128 .Lpost_tf_hi_s1, t1; \
+ vbroadcasti128 .Lpost_tf_lo_s1(%rip), t0; \
+ vbroadcasti128 .Lpost_tf_hi_s1(%rip), t1; \
vaesenclast t4##_x, x2##_x, x2##_x; \
vaesenclast t4##_x, t6##_x, t6##_x; \
vinserti128 $1, t6##_x, x2, x2; \
@@ -131,16 +131,16 @@
vinserti128 $1, t2##_x, x4, x4; \
\
/* postfilter sboxes 1 and 4 */ \
- vbroadcasti128 .Lpost_tf_lo_s3, t2; \
- vbroadcasti128 .Lpost_tf_hi_s3, t3; \
+ vbroadcasti128 .Lpost_tf_lo_s3(%rip), t2; \
+ vbroadcasti128 .Lpost_tf_hi_s3(%rip), t3; \
filter_8bit(x0, t0, t1, t7, t6); \
filter_8bit(x7, t0, t1, t7, t6); \
filter_8bit(x3, t0, t1, t7, t6); \
filter_8bit(x6, t0, t1, t7, t6); \
\
/* postfilter sbox 3 */ \
- vbroadcasti128 .Lpost_tf_lo_s2, t4; \
- vbroadcasti128 .Lpost_tf_hi_s2, t5; \
+ vbroadcasti128 .Lpost_tf_lo_s2(%rip), t4; \
+ vbroadcasti128 .Lpost_tf_hi_s2(%rip), t5; \
filter_8bit(x2, t2, t3, t7, t6); \
filter_8bit(x5, t2, t3, t7, t6); \
\
@@ -475,7 +475,7 @@ SYM_FUNC_END(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
transpose_4x4(c0, c1, c2, c3, a0, a1); \
transpose_4x4(d0, d1, d2, d3, a0, a1); \
\
- vbroadcasti128 .Lshufb_16x16b, a0; \
+ vbroadcasti128 .Lshufb_16x16b(%rip), a0; \
vmovdqu st1, a1; \
vpshufb a0, a2, a2; \
vpshufb a0, a3, a3; \
@@ -514,7 +514,7 @@ SYM_FUNC_END(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
#define inpack32_pre(x0, x1, x2, x3, x4, x5, x6, x7, y0, y1, y2, y3, y4, y5, \
y6, y7, rio, key) \
vpbroadcastq key, x0; \
- vpshufb .Lpack_bswap, x0, x0; \
+ vpshufb .Lpack_bswap(%rip), x0, x0; \
\
vpxor 0 * 32(rio), x0, y7; \
vpxor 1 * 32(rio), x0, y6; \
@@ -565,7 +565,7 @@ SYM_FUNC_END(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
vmovdqu x0, stack_tmp0; \
\
vpbroadcastq key, x0; \
- vpshufb .Lpack_bswap, x0, x0; \
+ vpshufb .Lpack_bswap(%rip), x0, x0; \
\
vpxor x0, y7, y7; \
vpxor x0, y6, y6; \
@@ -77,11 +77,13 @@
#define RXORbl %r9b
#define xor2ror16(T0, T1, tmp1, tmp2, ab, dst) \
+ leaq T0(%rip), tmp1; \
movzbl ab ## bl, tmp2 ## d; \
+ xorq (tmp1, tmp2, 8), dst; \
+ leaq T1(%rip), tmp2; \
movzbl ab ## bh, tmp1 ## d; \
- rorq $16, ab; \
- xorq T0(, tmp2, 8), dst; \
- xorq T1(, tmp1, 8), dst;
+ xorq (tmp2, tmp1, 8), dst; \
+ rorq $16, ab;
/**********************************************************************
1-way camellia
@@ -83,16 +83,20 @@
#define lookup_32bit(src, dst, op1, op2, op3, interleave_op, il_reg) \
- movzbl src ## bh, RID1d; \
- movzbl src ## bl, RID2d; \
- shrq $16, src; \
- movl s1(, RID1, 4), dst ## d; \
- op1 s2(, RID2, 4), dst ## d; \
- movzbl src ## bh, RID1d; \
- movzbl src ## bl, RID2d; \
- interleave_op(il_reg); \
- op2 s3(, RID1, 4), dst ## d; \
- op3 s4(, RID2, 4), dst ## d;
+ 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; \
+ movzbl src ## bh, RID1d; \
+ leaq s3(%rip), RID2; \
+ op2 (RID2, RID1, 4), dst ## d; \
+ movzbl src ## bl, RID2d; \
+ leaq s4(%rip), RID1; \
+ op3 (RID1, RID2, 4), dst ## d; \
+ interleave_op(il_reg);
#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;
@@ -83,16 +83,20 @@
#define lookup_32bit(src, dst, op1, op2, op3, interleave_op, il_reg) \
- movzbl src ## bh, RID1d; \
- movzbl src ## bl, RID2d; \
- shrq $16, src; \
- movl s1(, RID1, 4), dst ## d; \
- op1 s2(, RID2, 4), dst ## d; \
- movzbl src ## bh, RID1d; \
- movzbl src ## bl, RID2d; \
- interleave_op(il_reg); \
- op2 s3(, RID1, 4), dst ## d; \
- op3 s4(, RID2, 4), dst ## d;
+ 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; \
+ movzbl src ## bh, RID1d; \
+ leaq s3(%rip), RID2; \
+ op2 (RID2, RID1, 4), dst ## d; \
+ movzbl src ## bl, RID2d; \
+ leaq s4(%rip), RID1; \
+ op3 (RID1, RID2, 4), dst ## d; \
+ interleave_op(il_reg);
#define dummy(d) /* do nothing */
@@ -175,10 +179,10 @@
qop(RD, RC, 1);
#define shuffle(mask) \
- vpshufb mask, RKR, RKR;
+ vpshufb mask(%rip), RKR, RKR;
#define preload_rkr(n, do_mask, mask) \
- vbroadcastss .L16_mask, RKR; \
+ vbroadcastss .L16_mask(%rip), RKR; \
/* add 16-bit rotation to key rotations (mod 32) */ \
vpxor (kr+n*16)(CTX), RKR, RKR; \
do_mask(mask);
@@ -258,9 +262,9 @@ SYM_FUNC_START_LOCAL(__cast6_enc_blk8)
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;
inpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
inpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
@@ -284,7 +288,7 @@ SYM_FUNC_START_LOCAL(__cast6_enc_blk8)
popq %rbx;
popq %r15;
- vmovdqa .Lbswap_mask, RKM;
+ vmovdqa .Lbswap_mask(%rip), RKM;
outunpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
@@ -306,9 +310,9 @@ SYM_FUNC_START_LOCAL(__cast6_dec_blk8)
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;
inpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
inpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
@@ -332,7 +336,7 @@ SYM_FUNC_START_LOCAL(__cast6_dec_blk8)
popq %rbx;
popq %r15;
- vmovdqa .Lbswap_mask, RKM;
+ vmovdqa .Lbswap_mask(%rip), RKM;
outunpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
@@ -168,7 +168,8 @@ continue_block:
xor crc2, crc2
## branch into array
- mov jump_table(,%rax,8), %bufp
+ leaq jump_table(%rip), %bufp
+ mov (%bufp,%rax,8), %bufp
JMP_NOSPEC bufp
################################################################
@@ -129,21 +129,29 @@
movzbl RW0bl, RT2d; \
movzbl RW0bh, RT3d; \
shrq $16, RW0; \
- movq s8(, RT0, 8), RT0; \
- xorq s6(, RT1, 8), to; \
+ leaq s8(%rip), RW1; \
+ movq (RW1, RT0, 8), RT0; \
+ leaq s6(%rip), RW1; \
+ xorq (RW1, RT1, 8), to; \
movzbl RW0bl, RL1d; \
movzbl RW0bh, RT1d; \
shrl $16, RW0d; \
- xorq s4(, RT2, 8), RT0; \
- xorq s2(, RT3, 8), to; \
+ leaq s4(%rip), RW1; \
+ xorq (RW1, RT2, 8), RT0; \
+ leaq s2(%rip), RW1; \
+ xorq (RW1, RT3, 8), to; \
movzbl RW0bl, RT2d; \
movzbl RW0bh, RT3d; \
- xorq s7(, RL1, 8), RT0; \
- xorq s5(, RT1, 8), to; \
- xorq s3(, RT2, 8), RT0; \
+ leaq s7(%rip), RW1; \
+ xorq (RW1, RL1, 8), RT0; \
+ leaq s5(%rip), RW1; \
+ xorq (RW1, RT1, 8), to; \
+ leaq s3(%rip), RW1; \
+ xorq (RW1, RT2, 8), RT0; \
load_next_key(n, RW0); \
xorq RT0, to; \
- xorq s1(, RT3, 8), to; \
+ leaq s1(%rip), RW1; \
+ xorq (RW1, RT3, 8), to; \
#define load_next_key(n, RWx) \
movq (((n) + 1) * 8)(CTX), RWx;
@@ -355,65 +363,89 @@ SYM_FUNC_END(des3_ede_x86_64_crypt_blk)
movzbl RW0bl, RT3d; \
movzbl RW0bh, RT1d; \
shrq $16, RW0; \
- xorq s8(, RT3, 8), to##0; \
- xorq s6(, RT1, 8), to##0; \
+ leaq s8(%rip), RT2; \
+ xorq (RT2, RT3, 8), to##0; \
+ leaq s6(%rip), RT2; \
+ xorq (RT2, RT1, 8), to##0; \
movzbl RW0bl, RT3d; \
movzbl RW0bh, RT1d; \
shrq $16, RW0; \
- xorq s4(, RT3, 8), to##0; \
- xorq s2(, RT1, 8), to##0; \
+ leaq s4(%rip), RT2; \
+ xorq (RT2, RT3, 8), to##0; \
+ leaq s2(%rip), RT2; \
+ xorq (RT2, RT1, 8), to##0; \
movzbl RW0bl, RT3d; \
movzbl RW0bh, RT1d; \
shrl $16, RW0d; \
- xorq s7(, RT3, 8), to##0; \
- xorq s5(, RT1, 8), to##0; \
+ leaq s7(%rip), RT2; \
+ xorq (RT2, RT3, 8), to##0; \
+ leaq s5(%rip), RT2; \
+ xorq (RT2, RT1, 8), to##0; \
movzbl RW0bl, RT3d; \
movzbl RW0bh, RT1d; \
load_next_key(n, RW0); \
- xorq s3(, RT3, 8), to##0; \
- xorq s1(, RT1, 8), to##0; \
+ leaq s3(%rip), RT2; \
+ xorq (RT2, RT3, 8), to##0; \
+ leaq s1(%rip), RT2; \
+ xorq (RT2, RT1, 8), to##0; \
xorq from##1, RW1; \
movzbl RW1bl, RT3d; \
movzbl RW1bh, RT1d; \
shrq $16, RW1; \
- xorq s8(, RT3, 8), to##1; \
- xorq s6(, RT1, 8), to##1; \
+ leaq s8(%rip), RT2; \
+ xorq (RT2, RT3, 8), to##1; \
+ leaq s6(%rip), RT2; \
+ xorq (RT2, RT1, 8), to##1; \
movzbl RW1bl, RT3d; \
movzbl RW1bh, RT1d; \
shrq $16, RW1; \
- xorq s4(, RT3, 8), to##1; \
- xorq s2(, RT1, 8), to##1; \
+ leaq s4(%rip), RT2; \
+ xorq (RT2, RT3, 8), to##1; \
+ leaq s2(%rip), RT2; \
+ xorq (RT2, RT1, 8), to##1; \
movzbl RW1bl, RT3d; \
movzbl RW1bh, RT1d; \
shrl $16, RW1d; \
- xorq s7(, RT3, 8), to##1; \
- xorq s5(, RT1, 8), to##1; \
+ leaq s7(%rip), RT2; \
+ xorq (RT2, RT3, 8), to##1; \
+ leaq s5(%rip), RT2; \
+ xorq (RT2, RT1, 8), to##1; \
movzbl RW1bl, RT3d; \
movzbl RW1bh, RT1d; \
do_movq(RW0, RW1); \
- xorq s3(, RT3, 8), to##1; \
- xorq s1(, RT1, 8), to##1; \
+ leaq s3(%rip), RT2; \
+ xorq (RT2, RT3, 8), to##1; \
+ leaq s1(%rip), RT2; \
+ xorq (RT2, RT1, 8), to##1; \
xorq from##2, RW2; \
movzbl RW2bl, RT3d; \
movzbl RW2bh, RT1d; \
shrq $16, RW2; \
- xorq s8(, RT3, 8), to##2; \
- xorq s6(, RT1, 8), to##2; \
+ leaq s8(%rip), RT2; \
+ xorq (RT2, RT3, 8), to##2; \
+ leaq s6(%rip), RT2; \
+ xorq (RT2, RT1, 8), to##2; \
movzbl RW2bl, RT3d; \
movzbl RW2bh, RT1d; \
shrq $16, RW2; \
- xorq s4(, RT3, 8), to##2; \
- xorq s2(, RT1, 8), to##2; \
+ leaq s4(%rip), RT2; \
+ xorq (RT2, RT3, 8), to##2; \
+ leaq s2(%rip), RT2; \
+ xorq (RT2, RT1, 8), to##2; \
movzbl RW2bl, RT3d; \
movzbl RW2bh, RT1d; \
shrl $16, RW2d; \
- xorq s7(, RT3, 8), to##2; \
- xorq s5(, RT1, 8), to##2; \
+ leaq s7(%rip), RT2; \
+ xorq (RT2, RT3, 8), to##2; \
+ leaq s5(%rip), RT2; \
+ xorq (RT2, RT1, 8), to##2; \
movzbl RW2bl, RT3d; \
movzbl RW2bh, RT1d; \
do_movq(RW0, RW2); \
- xorq s3(, RT3, 8), to##2; \
- xorq s1(, RT1, 8), to##2;
+ leaq s3(%rip), RT2; \
+ xorq (RT2, RT3, 8), to##2; \
+ leaq s1(%rip), RT2; \
+ xorq (RT2, RT1, 8), to##2;
#define __movq(src, dst) \
movq src, dst;
@@ -93,7 +93,7 @@ SYM_FUNC_START(clmul_ghash_mul)
FRAME_BEGIN
movups (%rdi), DATA
movups (%rsi), SHASH
- movaps .Lbswap_mask, BSWAP
+ movaps .Lbswap_mask(%rip), BSWAP
pshufb BSWAP, DATA
call __clmul_gf128mul_ble
pshufb BSWAP, DATA
@@ -110,7 +110,7 @@ SYM_FUNC_START(clmul_ghash_update)
FRAME_BEGIN
cmp $16, %rdx
jb .Lupdate_just_ret # check length
- movaps .Lbswap_mask, BSWAP
+ movaps .Lbswap_mask(%rip), BSWAP
movups (%rdi), DATA
movups (%rcx), SHASH
pshufb BSWAP, DATA
@@ -589,19 +589,23 @@ last_block_enter:
.align 16
loop1:
- vpaddd K256+0*32(SRND), X0, XFER
+ leaq K256(%rip), INP
+ vpaddd 0*32(INP, SRND), X0, XFER
vmovdqa XFER, 0*32+_XFER(%rsp, SRND)
FOUR_ROUNDS_AND_SCHED _XFER + 0*32
- vpaddd K256+1*32(SRND), X0, XFER
+ leaq K256(%rip), INP
+ vpaddd 1*32(INP, SRND), X0, XFER
vmovdqa XFER, 1*32+_XFER(%rsp, SRND)
FOUR_ROUNDS_AND_SCHED _XFER + 1*32
- vpaddd K256+2*32(SRND), X0, XFER
+ leaq K256(%rip), INP
+ vpaddd 2*32(INP, SRND), X0, XFER
vmovdqa XFER, 2*32+_XFER(%rsp, SRND)
FOUR_ROUNDS_AND_SCHED _XFER + 2*32
- vpaddd K256+3*32(SRND), X0, XFER
+ leaq K256(%rip), INP
+ vpaddd 3*32(INP, SRND), X0, XFER
vmovdqa XFER, 3*32+_XFER(%rsp, SRND)
FOUR_ROUNDS_AND_SCHED _XFER + 3*32
@@ -611,11 +615,13 @@ loop1:
loop2:
## Do last 16 rounds with no scheduling
- vpaddd K256+0*32(SRND), X0, XFER
+ leaq K256(%rip), INP
+ vpaddd 0*32(INP, SRND), X0, XFER
vmovdqa XFER, 0*32+_XFER(%rsp, SRND)
DO_4ROUNDS _XFER + 0*32
- vpaddd K256+1*32(SRND), X1, XFER
+ leaq K256(%rip), INP
+ vpaddd 1*32(INP, SRND), X1, XFER
vmovdqa XFER, 1*32+_XFER(%rsp, SRND)
DO_4ROUNDS _XFER + 1*32
add $2*32, SRND