.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,${num}d
jnz .Lmul_enter
___
.Lmul_enter:
movd `($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 %r14
neg $num
mov %rsp,%r11
lea .Linc(%rip),%r10
mov %rax,8(%rsp,$num,8) # tp[num+1]=%rsp
+.cfi_cfa_expression %rsp+8,$num,8,mul,plus,deref,+8
.Lmul_body:
lea 128($bp),%r12 # reassign $bp (+size optimization)
jnz .Lcopy
mov 8(%rsp,$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 %r15
mov -32(%rsi),%r13
+.cfi_restore %r15
mov -24(%rsi),%r12
+.cfi_restore %r15
mov -16(%rsi),%rbp
+.cfi_restore %r15
mov -8(%rsi),%rbx
+.cfi_restore %r15
lea (%rsi),%rsp
+.cfi_def_cfa_register %rsp
.Lmul_epilogue:
ret
+.cfi_endproc
.size bn_mul_mont_gather5,.-bn_mul_mont_gather5
___
{{{
.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);
___
$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
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
.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
___
$code.=<<___;
push %rbx
+.cfi_push %rbx
push %rbp
+.cfi_push %rbp
push %r12
+.cfi_push %r12
push %r13
+.cfi_push %r13
push %r14
+.cfi_push %r14
push %r15
+.cfi_push %r15
.Lpower5_prologue:
shl \$3,${num}d # convert $num to bytes
#
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 $nptr
call mul4x_internal
mov 40(%rsp),%rsi # restore %rsp
+.cfi_def_cfa %rsi,8
mov \$1,%rax
mov -48(%rsi),%r15
+.cfi_restore %r15
mov -40(%rsi),%r14
+.cfi_restore %r14
mov -32(%rsi),%r13
+.cfi_restore %r13
mov -24(%rsi),%r12
+.cfi_restore %r12
mov -16(%rsi),%rbp
+.cfi_restore %rbp
mov -8(%rsi),%rbx
+.cfi_restore %rbx
lea (%rsi),%rsp
+.cfi_def_cfa_register %rsp
.Lpower5_epilogue:
ret
+.cfi_endproc
.size bn_power5,.-bn_power5
.globl bn_sqr8x_internal
.type bn_from_mont8x,\@function,6
.align 32
bn_from_mont8x:
+.cfi_startproc
.byte 0x67
mov %rsp,%rax
+.cfi_def_cfa_register %rax
push %rbx
+.cfi_push %rbx
push %rbp
+.cfi_push %rbp
push %r12
+.cfi_push %r12
push %r13
+.cfi_push %r13
push %r14
+.cfi_push %r14
push %r15
+.cfi_push %r15
.Lfrom_prologue:
shl \$3,${num}d # convert $num to bytes
#
mov $n0, 32(%rsp)
mov %rax, 40(%rsp) # save original %rsp
+.cfi_cfa_expression %rsp+40,deref,+8
.Lfrom_body:
mov $num,%r11
lea 48(%rsp),%rax
pxor %xmm0,%xmm0
lea 48(%rsp),%rax
- mov 40(%rsp),%rsi # restore %rsp
jmp .Lfrom_mont_zero
.align 32
pxor %xmm0,%xmm0
lea 48(%rsp),%rax
- mov 40(%rsp),%rsi # restore %rsp
jmp .Lfrom_mont_zero
.align 32
.Lfrom_mont_zero:
+ mov 40(%rsp),%rsi # restore %rsp
+.cfi_def_cfa %rsi,8
movdqa %xmm0,16*0(%rax)
movdqa %xmm0,16*1(%rax)
movdqa %xmm0,16*2(%rax)
mov \$1,%rax
mov -48(%rsi),%r15
+.cfi_restore %r15
mov -40(%rsi),%r14
+.cfi_restore %r14
mov -32(%rsi),%r13
+.cfi_restore %r13
mov -24(%rsi),%r12
+.cfi_restore %r12
mov -16(%rsi),%rbp
+.cfi_restore %rbp
mov -8(%rsi),%rbx
+.cfi_restore %rbx
lea (%rsi),%rsp
+.cfi_def_cfa_register %rsp
.Lfrom_epilogue:
ret
+.cfi_endproc
.size bn_from_mont8x,.-bn_from_mont8x
___
}
.type bn_mulx4x_mont_gather5,\@function,6
.align 32
bn_mulx4x_mont_gather5:
+.cfi_startproc
mov %rsp,%rax
+.cfi_def_cfa_register %rax
.Lmulx4x_enter:
push %rbx
+.cfi_push %rbx
push %rbp
+.cfi_push %rbp
push %r12
+.cfi_push %r12
push %r13
+.cfi_push %r13
push %r14
+.cfi_push %r14
push %r15
+.cfi_push %r15
.Lmulx4x_prologue:
shl \$3,${num}d # convert $num to bytes
#
mov $n0, 32(%rsp) # save *n0
mov %rax,40(%rsp) # save original %rsp
+.cfi_cfa_expression %rsp+40,deref,+8
.Lmulx4x_body:
call mulx4x_internal
mov 40(%rsp),%rsi # restore %rsp
+.cfi_def_cfa %rsi,8
mov \$1,%rax
mov -48(%rsi),%r15
+.cfi_restore %r15
mov -40(%rsi),%r14
+.cfi_restore %r14
mov -32(%rsi),%r13
+.cfi_restore %r13
mov -24(%rsi),%r12
+.cfi_restore %r12
mov -16(%rsi),%rbp
+.cfi_restore %rbp
mov -8(%rsi),%rbx
+.cfi_restore %rbx
lea (%rsi),%rsp
+.cfi_def_cfa_register %rsp
.Lmulx4x_epilogue:
ret
+.cfi_endproc
.size bn_mulx4x_mont_gather5,.-bn_mulx4x_mont_gather5
.type mulx4x_internal,\@abi-omnipotent
.type bn_powerx5,\@function,6
.align 32
bn_powerx5:
+.cfi_startproc
mov %rsp,%rax
+.cfi_def_cfa_register %rax
.Lpowerx5_enter:
push %rbx
+.cfi_push %rbx
push %rbp
+.cfi_push %rbp
push %r12
+.cfi_push %r12
push %r13
+.cfi_push %r13
push %r14
+.cfi_push %r14
push %r15
+.cfi_push %r15
.Lpowerx5_prologue:
shl \$3,${num}d # convert $num to bytes
movq $bptr,%xmm4
mov $n0, 32(%rsp)
mov %rax, 40(%rsp) # save original %rsp
+.cfi_cfa_expression %rsp+40,deref,+8
.Lpowerx5_body:
call __bn_sqrx8x_internal
call mulx4x_internal
mov 40(%rsp),%rsi # restore %rsp
+.cfi_def_cfa %rsi,8
mov \$1,%rax
mov -48(%rsi),%r15
+.cfi_restore %r15
mov -40(%rsi),%r14
+.cfi_restore %r14
mov -32(%rsi),%r13
+.cfi_restore %r13
mov -24(%rsi),%r12
+.cfi_restore %r12
mov -16(%rsi),%rbp
+.cfi_restore %rbp
mov -8(%rsi),%rbx
+.cfi_restore %rbx
lea (%rsi),%rsp
+.cfi_def_cfa_register %rsp
.Lpowerx5_epilogue:
ret
+.cfi_endproc
.size bn_powerx5,.-bn_powerx5
.globl bn_sqrx8x_internal
jb .Lcommon_seh_tail
mov 4(%r11),%r10d # HandlerData[1]
- lea (%rsi,%r10),%r10 # epilogue label
- cmp %r10,%rbx # context->Rip>=epilogue label
+ lea (%rsi,%r10),%r10 # beginning of body label
+ cmp %r10,%rbx # context->Rip<body label
jb .Lcommon_pop_regs
mov 152($context),%rax # pull context->Rsp