summaryrefslogtreecommitdiff
path: root/deps/openssl/openssl/crypto/bn/asm/x86_64-mont5.pl
diff options
context:
space:
mode:
Diffstat (limited to 'deps/openssl/openssl/crypto/bn/asm/x86_64-mont5.pl')
-rwxr-xr-xdeps/openssl/openssl/crypto/bn/asm/x86_64-mont5.pl129
1 files changed, 118 insertions, 11 deletions
diff --git a/deps/openssl/openssl/crypto/bn/asm/x86_64-mont5.pl b/deps/openssl/openssl/crypto/bn/asm/x86_64-mont5.pl
index 97d8eee700..ad6e8ada3c 100755
--- a/deps/openssl/openssl/crypto/bn/asm/x86_64-mont5.pl
+++ b/deps/openssl/openssl/crypto/bn/asm/x86_64-mont5.pl
@@ -93,8 +93,10 @@ $code=<<___;
.type bn_mul_mont_gather5,\@function,6
.align 64
bn_mul_mont_gather5:
+.cfi_startproc
mov ${num}d,${num}d
mov %rsp,%rax
+.cfi_def_cfa_register %rax
test \$7,${num}d
jnz .Lmul_enter
___
@@ -108,11 +110,17 @@ $code.=<<___;
.Lmul_enter:
movd `($win64?56:8)`(%rsp),%xmm5 # load 7th argument
push %rbx
+.cfi_push %rbx
push %rbp
+.cfi_push %rbp
push %r12
+.cfi_push %r12
push %r13
+.cfi_push %r13
push %r14
+.cfi_push %r14
push %r15
+.cfi_push %r15
neg $num
mov %rsp,%r11
@@ -145,6 +153,7 @@ $code.=<<___;
lea .Linc(%rip),%r10
mov %rax,8(%rsp,$num,8) # tp[num+1]=%rsp
+.cfi_cfa_expression %rsp+8,$num,8,mul,plus,deref,+8
.Lmul_body:
lea 128($bp),%r12 # reassign $bp (+size optimization)
@@ -410,7 +419,7 @@ $code.=<<___;
mov %rax,($rp,$i,8) # rp[i]=tp[i]-np[i]
mov 8($ap,$i,8),%rax # tp[i+1]
lea 1($i),$i # i++
- dec $j # doesnn't affect CF!
+ dec $j # doesn't affect CF!
jnz .Lsub
sbb \$0,%rax # handle upmost overflow bit
@@ -432,17 +441,26 @@ $code.=<<___;
jnz .Lcopy
mov 8(%rsp,$num,8),%rsi # restore %rsp
+.cfi_def_cfa %rsi,8
mov \$1,%rax
mov -48(%rsi),%r15
+.cfi_restore %r15
mov -40(%rsi),%r14
+.cfi_restore %r14
mov -32(%rsi),%r13
+.cfi_restore %r13
mov -24(%rsi),%r12
+.cfi_restore %r12
mov -16(%rsi),%rbp
+.cfi_restore %rbp
mov -8(%rsi),%rbx
+.cfi_restore %rbx
lea (%rsi),%rsp
+.cfi_def_cfa_register %rsp
.Lmul_epilogue:
ret
+.cfi_endproc
.size bn_mul_mont_gather5,.-bn_mul_mont_gather5
___
{{{
@@ -452,8 +470,10 @@ $code.=<<___;
.type bn_mul4x_mont_gather5,\@function,6
.align 32
bn_mul4x_mont_gather5:
+.cfi_startproc
.byte 0x67
mov %rsp,%rax
+.cfi_def_cfa_register %rax
.Lmul4x_enter:
___
$code.=<<___ if ($addx);
@@ -463,11 +483,17 @@ $code.=<<___ if ($addx);
___
$code.=<<___;
push %rbx
+.cfi_push %rbx
push %rbp
+.cfi_push %rbp
push %r12
+.cfi_push %r12
push %r13
+.cfi_push %r13
push %r14
+.cfi_push %r14
push %r15
+.cfi_push %r15
.Lmul4x_prologue:
.byte 0x67
@@ -523,22 +549,32 @@ $code.=<<___;
neg $num
mov %rax,40(%rsp)
+.cfi_cfa_expression %rsp+40,deref,+8
.Lmul4x_body:
call mul4x_internal
mov 40(%rsp),%rsi # restore %rsp
+.cfi_def_cfa %rsi,8
mov \$1,%rax
mov -48(%rsi),%r15
+.cfi_restore %r15
mov -40(%rsi),%r14
+.cfi_restore %r14
mov -32(%rsi),%r13
+.cfi_restore %r13
mov -24(%rsi),%r12
+.cfi_restore %r12
mov -16(%rsi),%rbp
+.cfi_restore %rbp
mov -8(%rsi),%rbx
+.cfi_restore %rbx
lea (%rsi),%rsp
+.cfi_def_cfa_register %rsp
.Lmul4x_epilogue:
ret
+.cfi_endproc
.size bn_mul4x_mont_gather5,.-bn_mul4x_mont_gather5
.type mul4x_internal,\@abi-omnipotent
@@ -1050,7 +1086,7 @@ my $bptr="%rdx"; # const void *table,
my $nptr="%rcx"; # const BN_ULONG *nptr,
my $n0 ="%r8"; # const BN_ULONG *n0);
my $num ="%r9"; # int num, has to be divisible by 8
- # int pwr
+ # int pwr
my ($i,$j,$tptr)=("%rbp","%rcx",$rptr);
my @A0=("%r10","%r11");
@@ -1062,7 +1098,9 @@ $code.=<<___;
.type bn_power5,\@function,6
.align 32
bn_power5:
+.cfi_startproc
mov %rsp,%rax
+.cfi_def_cfa_register %rax
___
$code.=<<___ if ($addx);
mov OPENSSL_ia32cap_P+8(%rip),%r11d
@@ -1072,11 +1110,17 @@ $code.=<<___ if ($addx);
___
$code.=<<___;
push %rbx
+.cfi_push %rbx
push %rbp
+.cfi_push %rbp
push %r12
+.cfi_push %r12
push %r13
+.cfi_push %r13
push %r14
+.cfi_push %r14
push %r15
+.cfi_push %r15
.Lpower5_prologue:
shl \$3,${num}d # convert $num to bytes
@@ -1127,7 +1171,7 @@ $code.=<<___;
ja .Lpwr_page_walk
.Lpwr_page_walk_done:
- mov $num,%r10
+ mov $num,%r10
neg $num
##############################################################
@@ -1141,6 +1185,7 @@ $code.=<<___;
#
mov $n0, 32(%rsp)
mov %rax, 40(%rsp) # save original %rsp
+.cfi_cfa_expression %rsp+40,deref,+8
.Lpower5_body:
movq $rptr,%xmm1 # save $rptr, used in sqr8x
movq $nptr,%xmm2 # save $nptr
@@ -1167,16 +1212,25 @@ $code.=<<___;
call mul4x_internal
mov 40(%rsp),%rsi # restore %rsp
+.cfi_def_cfa %rsi,8
mov \$1,%rax
mov -48(%rsi),%r15
+.cfi_restore %r15
mov -40(%rsi),%r14
+.cfi_restore %r14
mov -32(%rsi),%r13
+.cfi_restore %r13
mov -24(%rsi),%r12
+.cfi_restore %r12
mov -16(%rsi),%rbp
+.cfi_restore %rbp
mov -8(%rsi),%rbx
+.cfi_restore %rbx
lea (%rsi),%rsp
+.cfi_def_cfa_register %rsp
.Lpower5_epilogue:
ret
+.cfi_endproc
.size bn_power5,.-bn_power5
.globl bn_sqr8x_internal
@@ -2036,7 +2090,7 @@ __bn_post4x_internal:
jnz .Lsqr4x_sub
mov $num,%r10 # prepare for back-to-back call
- neg $num # restore $num
+ neg $num # restore $num
ret
.size __bn_post4x_internal,.-__bn_post4x_internal
___
@@ -2056,14 +2110,22 @@ bn_from_montgomery:
.type bn_from_mont8x,\@function,6
.align 32
bn_from_mont8x:
+.cfi_startproc
.byte 0x67
mov %rsp,%rax
+.cfi_def_cfa_register %rax
push %rbx
+.cfi_push %rbx
push %rbp
+.cfi_push %rbp
push %r12
+.cfi_push %r12
push %r13
+.cfi_push %r13
push %r14
+.cfi_push %r14
push %r15
+.cfi_push %r15
.Lfrom_prologue:
shl \$3,${num}d # convert $num to bytes
@@ -2128,6 +2190,7 @@ bn_from_mont8x:
#
mov $n0, 32(%rsp)
mov %rax, 40(%rsp) # save original %rsp
+.cfi_cfa_expression %rsp+40,deref,+8
.Lfrom_body:
mov $num,%r11
lea 48(%rsp),%rax
@@ -2171,7 +2234,6 @@ $code.=<<___ if ($addx);
pxor %xmm0,%xmm0
lea 48(%rsp),%rax
- mov 40(%rsp),%rsi # restore %rsp
jmp .Lfrom_mont_zero
.align 32
@@ -2183,11 +2245,12 @@ $code.=<<___;
pxor %xmm0,%xmm0
lea 48(%rsp),%rax
- mov 40(%rsp),%rsi # restore %rsp
jmp .Lfrom_mont_zero
.align 32
.Lfrom_mont_zero:
+ mov 40(%rsp),%rsi # restore %rsp
+.cfi_def_cfa %rsi,8
movdqa %xmm0,16*0(%rax)
movdqa %xmm0,16*1(%rax)
movdqa %xmm0,16*2(%rax)
@@ -2198,14 +2261,22 @@ $code.=<<___;
mov \$1,%rax
mov -48(%rsi),%r15
+.cfi_restore %r15
mov -40(%rsi),%r14
+.cfi_restore %r14
mov -32(%rsi),%r13
+.cfi_restore %r13
mov -24(%rsi),%r12
+.cfi_restore %r12
mov -16(%rsi),%rbp
+.cfi_restore %rbp
mov -8(%rsi),%rbx
+.cfi_restore %rbx
lea (%rsi),%rsp
+.cfi_def_cfa_register %rsp
.Lfrom_epilogue:
ret
+.cfi_endproc
.size bn_from_mont8x,.-bn_from_mont8x
___
}
@@ -2218,14 +2289,22 @@ $code.=<<___;
.type bn_mulx4x_mont_gather5,\@function,6
.align 32
bn_mulx4x_mont_gather5:
+.cfi_startproc
mov %rsp,%rax
+.cfi_def_cfa_register %rax
.Lmulx4x_enter:
push %rbx
+.cfi_push %rbx
push %rbp
+.cfi_push %rbp
push %r12
+.cfi_push %r12
push %r13
+.cfi_push %r13
push %r14
+.cfi_push %r14
push %r15
+.cfi_push %r15
.Lmulx4x_prologue:
shl \$3,${num}d # convert $num to bytes
@@ -2259,7 +2338,7 @@ bn_mulx4x_mont_gather5:
mov \$0,%r10
cmovc %r10,%r11
sub %r11,%rbp
-.Lmulx4xsp_done:
+.Lmulx4xsp_done:
and \$-64,%rbp # ensure alignment
mov %rsp,%r11
sub %rbp,%r11
@@ -2291,21 +2370,31 @@ bn_mulx4x_mont_gather5:
#
mov $n0, 32(%rsp) # save *n0
mov %rax,40(%rsp) # save original %rsp
+.cfi_cfa_expression %rsp+40,deref,+8
.Lmulx4x_body:
call mulx4x_internal
mov 40(%rsp),%rsi # restore %rsp
+.cfi_def_cfa %rsi,8
mov \$1,%rax
mov -48(%rsi),%r15
+.cfi_restore %r15
mov -40(%rsi),%r14
+.cfi_restore %r14
mov -32(%rsi),%r13
+.cfi_restore %r13
mov -24(%rsi),%r12
+.cfi_restore %r12
mov -16(%rsi),%rbp
+.cfi_restore %rbp
mov -8(%rsi),%rbx
+.cfi_restore %rbx
lea (%rsi),%rsp
+.cfi_def_cfa_register %rsp
.Lmulx4x_epilogue:
ret
+.cfi_endproc
.size bn_mulx4x_mont_gather5,.-bn_mulx4x_mont_gather5
.type mulx4x_internal,\@abi-omnipotent
@@ -2333,7 +2422,7 @@ my $N=$STRIDE/4; # should match cache line size
$code.=<<___;
movdqa 0(%rax),%xmm0 # 00000001000000010000000000000000
movdqa 16(%rax),%xmm1 # 00000002000000020000000200000002
- lea 88-112(%rsp,%r10),%r10 # place the mask after tp[num+1] (+ICache optimizaton)
+ lea 88-112(%rsp,%r10),%r10 # place the mask after tp[num+1] (+ICache optimization)
lea 128($bp),$bptr # size optimization
pshufd \$0,%xmm5,%xmm5 # broadcast index
@@ -2683,14 +2772,22 @@ $code.=<<___;
.type bn_powerx5,\@function,6
.align 32
bn_powerx5:
+.cfi_startproc
mov %rsp,%rax
+.cfi_def_cfa_register %rax
.Lpowerx5_enter:
push %rbx
+.cfi_push %rbx
push %rbp
+.cfi_push %rbp
push %r12
+.cfi_push %r12
push %r13
+.cfi_push %r13
push %r14
+.cfi_push %r14
push %r15
+.cfi_push %r15
.Lpowerx5_prologue:
shl \$3,${num}d # convert $num to bytes
@@ -2741,7 +2838,7 @@ bn_powerx5:
ja .Lpwrx_page_walk
.Lpwrx_page_walk_done:
- mov $num,%r10
+ mov $num,%r10
neg $num
##############################################################
@@ -2762,6 +2859,7 @@ bn_powerx5:
movq $bptr,%xmm4
mov $n0, 32(%rsp)
mov %rax, 40(%rsp) # save original %rsp
+.cfi_cfa_expression %rsp+40,deref,+8
.Lpowerx5_body:
call __bn_sqrx8x_internal
@@ -2784,17 +2882,26 @@ bn_powerx5:
call mulx4x_internal
mov 40(%rsp),%rsi # restore %rsp
+.cfi_def_cfa %rsi,8
mov \$1,%rax
mov -48(%rsi),%r15
+.cfi_restore %r15
mov -40(%rsi),%r14
+.cfi_restore %r14
mov -32(%rsi),%r13
+.cfi_restore %r13
mov -24(%rsi),%r12
+.cfi_restore %r12
mov -16(%rsi),%rbp
+.cfi_restore %rbp
mov -8(%rsi),%rbx
+.cfi_restore %rbx
lea (%rsi),%rsp
+.cfi_def_cfa_register %rsp
.Lpowerx5_epilogue:
ret
+.cfi_endproc
.size bn_powerx5,.-bn_powerx5
.globl bn_sqrx8x_internal
@@ -3678,8 +3785,8 @@ mul_handler:
jb .Lcommon_seh_tail
mov 4(%r11),%r10d # HandlerData[1]
- lea (%rsi,%r10),%r10 # epilogue label
- cmp %r10,%rbx # context->Rip>=epilogue label
+ lea (%rsi,%r10),%r10 # beginning of body label
+ cmp %r10,%rbx # context->Rip<body label
jb .Lcommon_pop_regs
mov 152($context),%rax # pull context->Rsp
generated by cgit v1.2.3 (git 2.39.1) at 2024-05-12 23:20:32 +0000