Hakase/openssl-custom
1
0 Fork 0
Code Issues Pull Requests Releases Wiki Activity

Latest update.

Browse Source
This commit is contained in:
Hakase
2020-01-17 19:45:12 +09:00
parent 016df9f433
commit 0f7abb4eb6
1100 changed files with 47785 additions and 16292 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crypto/ec/asm/ecp_nistz256-armv4.pl
+33 -46
View File
@@ -1398,7 +1398,7 @@ my ($Z1sqr, $Z2sqr) = ($Hsqr, $Rsqr);
# 256-bit vectors on top. Then note that we push
# starting from r0, which means that we have copy of
# input arguments just below these temporary vectors.
# We use three of them for !in1infty, !in2intfy and
# We use three of them for ~in1infty, ~in2infty and
# result of check for zero.
$code.=<<___;
@@ -1428,7 +1428,7 @@ ecp_nistz256_point_add:
#endif
movne r12,#-1
stmia r3,{r4-r11}
str r12,[sp,#32*18+8] @ !in2infty
str r12,[sp,#32*18+8] @ ~in2infty
ldmia $a_ptr!,{r4-r11} @ copy in1_x
add r3,sp,#$in1_x
@@ -1449,7 +1449,7 @@ ecp_nistz256_point_add:
#endif
movne r12,#-1
stmia r3,{r4-r11}
str r12,[sp,#32*18+4] @ !in1infty
str r12,[sp,#32*18+4] @ ~in1infty
add $a_ptr,sp,#$in2_z
add $b_ptr,sp,#$in2_z
@@ -1514,33 +1514,20 @@ ecp_nistz256_point_add:
orr $a0,$a0,$a2
orr $a4,$a4,$a6
orr $a0,$a0,$a7
orrs $a0,$a0,$a4
orr $a0,$a0,$a4 @ ~is_equal(U1,U2)
bne .Ladd_proceed @ is_equal(U1,U2)?
ldr $t0,[sp,#32*18+4] @ ~in1infty
ldr $t1,[sp,#32*18+8] @ ~in2infty
ldr $t2,[sp,#32*18+12] @ ~is_equal(S1,S2)
mvn $t0,$t0 @ -1/0 -> 0/-1
mvn $t1,$t1 @ -1/0 -> 0/-1
orr $a0,$t0
orr $a0,$t1
orrs $a0,$t2 @ set flags
ldr $t0,[sp,#32*18+4]
ldr $t1,[sp,#32*18+8]
ldr $t2,[sp,#32*18+12]
tst $t0,$t1
beq .Ladd_proceed @ (in1infty || in2infty)?
tst $t2,$t2
beq .Ladd_double @ is_equal(S1,S2)?
@ if(~is_equal(U1,U2) | in1infty | in2infty | ~is_equal(S1,S2))
bne .Ladd_proceed
ldr $r_ptr,[sp,#32*18+16]
eor r4,r4,r4
eor r5,r5,r5
eor r6,r6,r6
eor r7,r7,r7
eor r8,r8,r8
eor r9,r9,r9
eor r10,r10,r10
eor r11,r11,r11
stmia $r_ptr!,{r4-r11}
stmia $r_ptr!,{r4-r11}
stmia $r_ptr!,{r4-r11}
b .Ladd_done
.align 4
.Ladd_double:
ldr $a_ptr,[sp,#32*18+20]
add sp,sp,#32*(18-5)+16 @ difference in frame sizes
@@ -1605,15 +1592,15 @@ ecp_nistz256_point_add:
add $b_ptr,sp,#$S2
bl __ecp_nistz256_sub_from @ p256_sub(res_y, res_y, S2);
ldr r11,[sp,#32*18+4] @ !in1intfy
ldr r12,[sp,#32*18+8] @ !in2intfy
ldr r11,[sp,#32*18+4] @ ~in1infty
ldr r12,[sp,#32*18+8] @ ~in2infty
add r1,sp,#$res_x
add r2,sp,#$in2_x
and r10,r11,r12
and r10,r11,r12 @ ~in1infty & ~in2infty
mvn r11,r11
add r3,sp,#$in1_x
and r11,r11,r12
mvn r12,r12
and r11,r11,r12 @ in1infty & ~in2infty
mvn r12,r12 @ in2infty
ldr $r_ptr,[sp,#32*18+16]
___
for($i=0;$i<96;$i+=8) { # conditional moves
@@ -1621,11 +1608,11 @@ $code.=<<___;
ldmia r1!,{r4-r5} @ res_x
ldmia r2!,{r6-r7} @ in2_x
ldmia r3!,{r8-r9} @ in1_x
and r4,r4,r10
and r4,r4,r10 @ ~in1infty & ~in2infty
and r5,r5,r10
and r6,r6,r11
and r6,r6,r11 @ in1infty & ~in2infty
and r7,r7,r11
and r8,r8,r12
and r8,r8,r12 @ in2infty
and r9,r9,r12
orr r4,r4,r6
orr r5,r5,r7
@@ -1660,7 +1647,7 @@ my $Z1sqr = $S2;
# 256-bit vectors on top. Then note that we push
# starting from r0, which means that we have copy of
# input arguments just below these temporary vectors.
# We use two of them for !in1infty, !in2intfy.
# We use two of them for ~in1infty, ~in2infty.
my @ONE_mont=(1,0,0,-1,-1,-1,-2,0);
@@ -1691,7 +1678,7 @@ ecp_nistz256_point_add_affine:
#endif
movne r12,#-1
stmia r3,{r4-r11}
str r12,[sp,#32*15+4] @ !in1infty
str r12,[sp,#32*15+4] @ ~in1infty
ldmia $b_ptr!,{r4-r11} @ copy in2_x
add r3,sp,#$in2_x
@@ -1718,7 +1705,7 @@ ecp_nistz256_point_add_affine:
it ne
#endif
movne r12,#-1
str r12,[sp,#32*15+8] @ !in2infty
str r12,[sp,#32*15+8] @ ~in2infty
add $a_ptr,sp,#$in1_z
add $b_ptr,sp,#$in1_z
@@ -1800,15 +1787,15 @@ ecp_nistz256_point_add_affine:
add $b_ptr,sp,#$S2
bl __ecp_nistz256_sub_from @ p256_sub(res_y, res_y, S2);
ldr r11,[sp,#32*15+4] @ !in1intfy
ldr r12,[sp,#32*15+8] @ !in2intfy
ldr r11,[sp,#32*15+4] @ ~in1infty
ldr r12,[sp,#32*15+8] @ ~in2infty
add r1,sp,#$res_x
add r2,sp,#$in2_x
and r10,r11,r12
and r10,r11,r12 @ ~in1infty & ~in2infty
mvn r11,r11
add r3,sp,#$in1_x
and r11,r11,r12
mvn r12,r12
and r11,r11,r12 @ in1infty & ~in2infty
mvn r12,r12 @ in2infty
ldr $r_ptr,[sp,#32*15]
___
for($i=0;$i<64;$i+=8) { # conditional moves
@@ -1816,11 +1803,11 @@ $code.=<<___;
ldmia r1!,{r4-r5} @ res_x
ldmia r2!,{r6-r7} @ in2_x
ldmia r3!,{r8-r9} @ in1_x
and r4,r4,r10
and r4,r4,r10 @ ~in1infty & ~in2infty
and r5,r5,r10
and r6,r6,r11
and r6,r6,r11 @ in1infty & ~in2infty
and r7,r7,r11
and r8,r8,r12
and r8,r8,r12 @ in2infty
and r9,r9,r12
orr r4,r4,r6
orr r5,r5,r7