release/src/router/nettle/x86_64/ecc-256-redc.asm

   1 C nettle, low-level cryptographics library
   2 C
   3 C Copyright (C) 2013 Niels Möller
   4 C
   5 C The nettle library is free software; you can redistribute it and/or modify
   6 C it under the terms of the GNU Lesser General Public License as published by
   7 C the Free Software Foundation; either version 2.1 of the License, or (at your
   8 C option) any later version.
   9 C
  10 C The nettle library is distributed in the hope that it will be useful, but
  11 C WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
  12 C or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU Lesser General Public
  13 C License for more details.
  14 C
  15 C You should have received a copy of the GNU Lesser General Public License
  16 C along with the nettle library; see the file COPYING.LIB.  If not, write to
  17 C the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
  18 C MA 02111-1301, USA.
  19
  20         .file "ecc-256-redc.asm"
  21
  22 define(<RP>, <%rsi>)
  23 define(<U0>, <%rdi>) C Overlaps unused ecc input
  24 define(<U1>, <%rcx>)
  25 define(<U2>, <%rax>)
  26 define(<U3>, <%rdx>)
  27 define(<U4>, <%r8>)
  28 define(<U5>, <%r9>)
  29 define(<U6>, <%r10>)
  30 define(<F0>, <%r11>)
  31 define(<F1>, <%r12>)
  32 define(<F2>, <%rbx>)
  33 define(<F3>, <%rbp>)
  34
  35 C FOLD(x), sets (F3,F2,F1,F0)  <-- (x << 224) - (x << 128) - (x<<32)
  36 define(<FOLD>, <
  37         mov     $1, F2
  38         mov     $1, F3
  39         shl     <$>32, F2
  40         shr     <$>32, F3
  41         xor     F0,F0
  42         xor     F1,F1
  43         sub     F2, F0
  44         sbb     F3, F1
  45         sbb     $1, F2
  46         sbb     <$>0, F3
  47 >)
  48 PROLOGUE(nettle_ecc_256_redc)
  49         W64_ENTRY(2, 0)
  50         C save all registers that need to be saved
  51         push    %rbx
  52         push    %rbp
  53         push    %r12
  54
  55         mov     (RP), U0
  56         FOLD(U0)
  57         mov     8(RP), U1
  58         mov     16(RP), U2
  59         mov     24(RP), U3
  60         sub     F0, U1
  61         sbb     F1, U2
  62         sbb     F2, U3
  63         sbb     F3, U0          C Add in later
  64
  65         FOLD(U1)
  66         mov     32(RP), U4
  67         sub     F0, U2
  68         sbb     F1, U3
  69         sbb     F2, U4
  70         sbb     F3, U1
  71
  72         FOLD(U2)
  73         mov     40(RP), U5
  74         sub     F0, U3
  75         sbb     F1, U4
  76         sbb     F2, U5
  77         sbb     F3, U2
  78
  79         FOLD(U3)
  80         mov     48(RP), U6
  81         sub     F0, U4
  82         sbb     F1, U5
  83         sbb     F2, U6
  84         sbb     F3, U3
  85
  86         add     U4, U0
  87         adc     U5, U1
  88         adc     U6, U2
  89         adc     56(RP), U3
  90
  91         C If carry, we need to add in
  92         C 2^256 - p = <0xfffffffe, 0xff..ff, 0xffffffff00000000, 1>
  93         sbb     F2, F2
  94         mov     F2, F0
  95         mov     F2, F1
  96         mov     XREG(F2), XREG(F3)
  97         neg     F0
  98         shl     $32, F1
  99         and     $-2, XREG(F3)
 100
 101         add     F0, U0
 102         mov     U0, (RP)
 103         adc     F1, U1
 104         mov     U1, 8(RP)
 105         adc     F2, U2
 106         mov     U2, 16(RP)
 107         adc     F3, U3
 108
 109         mov     U3, 24(RP)
 110
 111         pop     %r12
 112         pop     %rbp
 113         pop     %rbx
 114         W64_EXIT(2, 0)
 115         ret
 116 EPILOGUE(nettle_ecc_256_redc)