/**********************************************************************
16-way AVX cast5
**********************************************************************/
-#define CTX %rdi
+#define CTX %r15
#define RL1 %xmm0
#define RR1 %xmm1
#define RTMP %xmm15
-#define RID1 %rbp
-#define RID1d %ebp
+#define RID1 %rdi
+#define RID1d %edi
#define RID2 %rsi
#define RID2d %esi
.align 16
__cast5_enc_blk16:
/* input:
- * %rdi: ctx, CTX
+ * %rdi: ctx
* RL1: blocks 1 and 2
* RR1: blocks 3 and 4
* RL2: blocks 5 and 6
* RR4: encrypted blocks 15 and 16
*/
- pushq %rbp;
+ pushq %r15;
pushq %rbx;
+ movq %rdi, CTX;
+
vmovdqa .Lbswap_mask, RKM;
vmovd .Lfirst_mask, R1ST;
vmovd .L32_mask, R32;
.L__skip_enc:
popq %rbx;
- popq %rbp;
+ popq %r15;
vmovdqa .Lbswap_mask, RKM;
.align 16
__cast5_dec_blk16:
/* input:
- * %rdi: ctx, CTX
+ * %rdi: ctx
* RL1: encrypted blocks 1 and 2
* RR1: encrypted blocks 3 and 4
* RL2: encrypted blocks 5 and 6
* RR4: decrypted blocks 15 and 16
*/
- pushq %rbp;
+ pushq %r15;
pushq %rbx;
+ movq %rdi, CTX;
+
vmovdqa .Lbswap_mask, RKM;
vmovd .Lfirst_mask, R1ST;
vmovd .L32_mask, R32;
vmovdqa .Lbswap_mask, RKM;
popq %rbx;
- popq %rbp;
+ popq %r15;
outunpack_blocks(RR1, RL1, RTMP, RX, RKM);
outunpack_blocks(RR2, RL2, RTMP, RX, RKM);
ENTRY(cast5_ecb_enc_16way)
/* input:
- * %rdi: ctx, CTX
+ * %rdi: ctx
* %rsi: dst
* %rdx: src
*/
FRAME_BEGIN
+ pushq %r15;
+ movq %rdi, CTX;
movq %rsi, %r11;
vmovdqu (0*4*4)(%rdx), RL1;
vmovdqu RR4, (6*4*4)(%r11);
vmovdqu RL4, (7*4*4)(%r11);
+ popq %r15;
FRAME_END
ret;
ENDPROC(cast5_ecb_enc_16way)
ENTRY(cast5_ecb_dec_16way)
/* input:
- * %rdi: ctx, CTX
+ * %rdi: ctx
* %rsi: dst
* %rdx: src
*/
FRAME_BEGIN
+ pushq %r15;
+
+ movq %rdi, CTX;
movq %rsi, %r11;
vmovdqu (0*4*4)(%rdx), RL1;
vmovdqu RR4, (6*4*4)(%r11);
vmovdqu RL4, (7*4*4)(%r11);
+ popq %r15;
FRAME_END
ret;
ENDPROC(cast5_ecb_dec_16way)
ENTRY(cast5_cbc_dec_16way)
/* input:
- * %rdi: ctx, CTX
+ * %rdi: ctx
* %rsi: dst
* %rdx: src
*/
FRAME_BEGIN
-
pushq %r12;
+ pushq %r15;
+ movq %rdi, CTX;
movq %rsi, %r11;
movq %rdx, %r12;
vmovdqu RR4, (6*16)(%r11);
vmovdqu RL4, (7*16)(%r11);
+ popq %r15;
popq %r12;
-
FRAME_END
ret;
ENDPROC(cast5_cbc_dec_16way)
ENTRY(cast5_ctr_16way)
/* input:
- * %rdi: ctx, CTX
+ * %rdi: ctx
* %rsi: dst
* %rdx: src
* %rcx: iv (big endian, 64bit)
*/
FRAME_BEGIN
-
pushq %r12;
+ pushq %r15;
+ movq %rdi, CTX;
movq %rsi, %r11;
movq %rdx, %r12;
vmovdqu RR4, (6*16)(%r11);
vmovdqu RL4, (7*16)(%r11);
+ popq %r15;
popq %r12;
-
FRAME_END
ret;
ENDPROC(cast5_ctr_16way)