Fix typo in x86_64-mont5.pl CFI directives

[openssl.git] / crypto / bn / asm / x86_64-mont5.pl

diff --git a/crypto/bn/asm/x86_64-mont5.pl b/crypto/bn/asm/x86_64-mont5.pl
index 3278dc60568ba4cd04dc473bf536083815095249..9c77642b71d0c822b1d37cff0235f0dd91ee571e 100755 (executable)
--- a/crypto/bn/asm/x86_64-mont5.pl
+++ b/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)
@@ -431,17 +440,26 @@ $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
 ___
 {{{
@@ -451,8 +469,10 @@ $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);
@@ -462,11 +482,17 @@ $code.=<<___ if ($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
@@ -522,22 +548,32 @@ $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
@@ -1049,7 +1085,7 @@ 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");
@@ -1061,7 +1097,9 @@ $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
@@ -1071,11 +1109,17 @@ $code.=<<___ if ($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
@@ -1126,7 +1170,7 @@ $code.=<<___;
        ja      .Lpwr_page_walk
 .Lpwr_page_walk_done:
 
-       mov     $num,%r10       
+       mov     $num,%r10
        neg     $num
 
        ##############################################################
@@ -1140,6 +1184,7 @@ $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
@@ -1166,16 +1211,25 @@ $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
@@ -1934,6 +1988,7 @@ __bn_sqr8x_reduction:
 
 .align 32
 .L8x_tail_done:
+       xor     %rax,%rax
        add     (%rdx),%r8              # can this overflow?
        adc     \$0,%r9
        adc     \$0,%r10
@@ -1941,10 +1996,8 @@ __bn_sqr8x_reduction:
        adc     \$0,%r12
        adc     \$0,%r13
        adc     \$0,%r14
-       adc     \$0,%r15                # can't overflow, because we
-                                       # started with "overhung" part
-                                       # of multiplication
-       xor     %rax,%rax
+       adc     \$0,%r15
+       adc     \$0,%rax
 
        neg     $carry
 .L8x_no_tail:
@@ -2036,7 +2089,7 @@ __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 +2109,22 @@ 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 +2189,7 @@ 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 +2233,6 @@ $code.=<<___ if ($addx);
 
        pxor    %xmm0,%xmm0
        lea     48(%rsp),%rax
-       mov     40(%rsp),%rsi           # restore %rsp
        jmp     .Lfrom_mont_zero
 
 .align 32
@@ -2183,11 +2244,12 @@ $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 +2260,22 @@ $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 +2288,22 @@ $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 +2337,7 @@ 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 +2369,31 @@ 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
@@ -2683,14 +2771,22 @@ $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 +2837,7 @@ bn_powerx5:
        ja      .Lpwrx_page_walk
 .Lpwrx_page_walk_done:
 
-       mov     $num,%r10       
+       mov     $num,%r10
        neg     $num
 
        ##############################################################
@@ -2762,6 +2858,7 @@ 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 +2881,26 @@ 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
@@ -3384,6 +3490,7 @@ __bn_sqrx8x_reduction:
 
 .align 32
 .Lsqrx8x_tail_done:
+       xor     %rax,%rax
        add     24+8(%rsp),%r8          # can this overflow?
        adc     \$0,%r9
        adc     \$0,%r10
@@ -3391,10 +3498,8 @@ __bn_sqrx8x_reduction:
        adc     \$0,%r12
        adc     \$0,%r13
        adc     \$0,%r14
-       adc     \$0,%r15                # can't overflow, because we
-                                       # started with "overhung" part
-                                       # of multiplication
-       mov     $carry,%rax             # xor   %rax,%rax
+       adc     \$0,%r15
+       adc     \$0,%rax
 
        sub     16+8(%rsp),$carry       # mov 16(%rsp),%cf
 .Lsqrx8x_no_tail:                      # %cf is 0 if jumped here
@@ -3409,7 +3514,7 @@ __bn_sqrx8x_reduction:
        adc     8*5($tptr),%r13
        adc     8*6($tptr),%r14
        adc     8*7($tptr),%r15
-       adc     %rax,%rax               # top-most carry
+       adc     \$0,%rax                # top-most carry
 
        mov     32+8(%rsp),%rbx         # n0
        mov     8*8($tptr,%rcx),%rdx    # modulo-scheduled "%r8"
@@ -3671,8 +3776,8 @@ 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