/* \
* 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; \
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); \
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; \
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); \
\
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; \
#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; \
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; \
/* \
* 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; \
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; \
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); \
\
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; \
#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; \
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; \
#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;
/**********************************************************************
1-way camellia