Tweeted twitter.com/#!/StackReverseEng/status/598477631705772032
2 Better usage of the wiki syntax
source | link
unsigned int __cdecl newhash(int a1, unsigned int a2, int zero)
{
  int content; // ebx@1
  int v4; // ecx@1
  int v5; // edx@1
  int i; // eax@1
  int v7; // ecx@2
  unsigned int v8; // eax@2
  int v9; // edx@2
  int v10; // ecx@2
  int v11; // eax@2
  int v12; // edx@2
  int v13; // ecx@2
  int v14; // eax@2
  unsigned int v15; // eax@3
  int v16; // edx@15
  int v17; // ecx@15
  int v18; // eax@15
  int v19; // edx@15
  int v20; // ecx@15
  int v21; // eax@15
  int v22; // edx@15
  unsigned int contentLength; // [sp+Ch] [bp-4h]@1

  content = a1;
  contentLength = a2;
  v4 = -1640531527;
  v5 = -1640531527;
  for ( i = zero; contentLength >= 12; contentLength -= 12 )
  {
    v7 = (*(_BYTE *)(content + 7) << 24)
       + (*(_BYTE *)(content + 6) << 16)
       + (*(_BYTE *)(content + 5) << 8)
       + *(_BYTE *)(content + 4)
       + v4;
    v8 = (*(_BYTE *)(content + 11) << 24)
       + (*(_BYTE *)(content + 10) << 16)
       + (*(_BYTE *)(content + 9) << 8)
       + *(_BYTE *)(content + 8)
       + i;
    v9 = (v8 >> 13) ^ ((*(_BYTE *)(content + 3) << 24)
                     + (*(_BYTE *)(content + 2) << 16)
                     + (*(_BYTE *)(content + 1) << 8)
                     + *(_BYTE *)content
                     + v5
                     - v7
                     - v8);
    v10 = (v9 << 8) ^ (v7 - v8 - v9);
    v11 = ((unsigned int)v10 >> 13) ^ (v8 - v9 - v10);
    v12 = ((unsigned int)v11 >> 12) ^ (v9 - v10 - v11);
    v13 = (v12 << 16) ^ (v10 - v11 - v12);
    v14 = ((unsigned int)v13 >> 5) ^ (v11 - v12 - v13);
    v5 = ((unsigned int)v14 >> 3) ^ (v12 - v13 - v14);
    v4 = (v5 << 10) ^ (v13 - v14 - v5);
    i = ((unsigned int)v4 >> 15) ^ (v14 - v5 - v4);
    content += 12;
  }
  v15 = a2 + i;
  switch ( contentLength )
  {
    case 0xBu:
      v15 += *(_BYTE *)(content + 10) << 24;
      goto LABEL_5;
    case 0xAu:
LABEL_5:
      v15 += *(_BYTE *)(content + 9) << 16;
      goto LABEL_6;
    case 9u:
LABEL_6:
      v15 += *(_BYTE *)(content + 8) << 8;
      goto LABEL_7;
    case 8u:
LABEL_7:
      v4 += *(_BYTE *)(content + 7) << 24;
      goto LABEL_8;
    case 7u:
LABEL_8:
      v4 += *(_BYTE *)(content + 6) << 16;
      goto LABEL_9;
    case 6u:
LABEL_9:
      v4 += *(_BYTE *)(content + 5) << 8;
      goto LABEL_10;
    case 5u:
LABEL_10:
      v4 += *(_BYTE *)(content + 4);
      goto LABEL_11;
    case 4u:
LABEL_11:
      v5 += *(_BYTE *)(content + 3) << 24;
      goto LABEL_12;
    case 3u:
LABEL_12:
      v5 += *(_BYTE *)(content + 2) << 16;
      goto LABEL_13;
    case 2u:
LABEL_13:
      v5 += *(_BYTE *)(content + 1) << 8;
      goto LABEL_14;
    case 1u:
LABEL_14:
      v5 += *(_BYTE *)content;
      break;
    default:
      break;
  }
  v16 = (v15 >> 13) ^ (v5 - v4 - v15);
  v17 = (v16 << 8) ^ (v4 - v15 - v16);
  v18 = ((unsigned int)v17 >> 13) ^ (v15 - v16 - v17);
  v19 = ((unsigned int)v18 >> 12) ^ (v16 - v17 - v18);
  v20 = (v19 << 16) ^ (v17 - v18 - v19);
  v21 = ((unsigned int)v20 >> 5) ^ (v18 - v19 - v20);
  v22 = ((unsigned int)v21 >> 3) ^ (v19 - v20 - v21); 

  return (((v22 << 10) ^ 
           (unsigned int)(v20 - v21 - v22)) >> 15) ^ 
           (v21 - v22 - ((v22 << 10) ^ (v20 - v21 - v22)));
}
  1. First and foremost, is this a standard algorithm like CRC or something?
  2. Is there a reason for the v4 and v5 variables to be -1640531527?
  3. What is the purpose of "(*(_BYTE *)(content + 7) << 24)"(*(_BYTE *)(content + 7) << 24) isn't a byte only 8 bits, so won't it be 0 every time? I looked up the order of operations and it seems that the casting is first then the bit operations, so it means it converts it to the 8th byte in the file and bit shifts it 24 bits right? why?
  4. Why are some bits signed and some unsigned, and would it change the outcome if there is a mix?

Thanks!

unsigned int __cdecl newhash(int a1, unsigned int a2, int zero)
{
  int content; // ebx@1
  int v4; // ecx@1
  int v5; // edx@1
  int i; // eax@1
  int v7; // ecx@2
  unsigned int v8; // eax@2
  int v9; // edx@2
  int v10; // ecx@2
  int v11; // eax@2
  int v12; // edx@2
  int v13; // ecx@2
  int v14; // eax@2
  unsigned int v15; // eax@3
  int v16; // edx@15
  int v17; // ecx@15
  int v18; // eax@15
  int v19; // edx@15
  int v20; // ecx@15
  int v21; // eax@15
  int v22; // edx@15
  unsigned int contentLength; // [sp+Ch] [bp-4h]@1

  content = a1;
  contentLength = a2;
  v4 = -1640531527;
  v5 = -1640531527;
  for ( i = zero; contentLength >= 12; contentLength -= 12 )
  {
    v7 = (*(_BYTE *)(content + 7) << 24)
       + (*(_BYTE *)(content + 6) << 16)
       + (*(_BYTE *)(content + 5) << 8)
       + *(_BYTE *)(content + 4)
       + v4;
    v8 = (*(_BYTE *)(content + 11) << 24)
       + (*(_BYTE *)(content + 10) << 16)
       + (*(_BYTE *)(content + 9) << 8)
       + *(_BYTE *)(content + 8)
       + i;
    v9 = (v8 >> 13) ^ ((*(_BYTE *)(content + 3) << 24)
                     + (*(_BYTE *)(content + 2) << 16)
                     + (*(_BYTE *)(content + 1) << 8)
                     + *(_BYTE *)content
                     + v5
                     - v7
                     - v8);
    v10 = (v9 << 8) ^ (v7 - v8 - v9);
    v11 = ((unsigned int)v10 >> 13) ^ (v8 - v9 - v10);
    v12 = ((unsigned int)v11 >> 12) ^ (v9 - v10 - v11);
    v13 = (v12 << 16) ^ (v10 - v11 - v12);
    v14 = ((unsigned int)v13 >> 5) ^ (v11 - v12 - v13);
    v5 = ((unsigned int)v14 >> 3) ^ (v12 - v13 - v14);
    v4 = (v5 << 10) ^ (v13 - v14 - v5);
    i = ((unsigned int)v4 >> 15) ^ (v14 - v5 - v4);
    content += 12;
  }
  v15 = a2 + i;
  switch ( contentLength )
  {
    case 0xBu:
      v15 += *(_BYTE *)(content + 10) << 24;
      goto LABEL_5;
    case 0xAu:
LABEL_5:
      v15 += *(_BYTE *)(content + 9) << 16;
      goto LABEL_6;
    case 9u:
LABEL_6:
      v15 += *(_BYTE *)(content + 8) << 8;
      goto LABEL_7;
    case 8u:
LABEL_7:
      v4 += *(_BYTE *)(content + 7) << 24;
      goto LABEL_8;
    case 7u:
LABEL_8:
      v4 += *(_BYTE *)(content + 6) << 16;
      goto LABEL_9;
    case 6u:
LABEL_9:
      v4 += *(_BYTE *)(content + 5) << 8;
      goto LABEL_10;
    case 5u:
LABEL_10:
      v4 += *(_BYTE *)(content + 4);
      goto LABEL_11;
    case 4u:
LABEL_11:
      v5 += *(_BYTE *)(content + 3) << 24;
      goto LABEL_12;
    case 3u:
LABEL_12:
      v5 += *(_BYTE *)(content + 2) << 16;
      goto LABEL_13;
    case 2u:
LABEL_13:
      v5 += *(_BYTE *)(content + 1) << 8;
      goto LABEL_14;
    case 1u:
LABEL_14:
      v5 += *(_BYTE *)content;
      break;
    default:
      break;
  }
  v16 = (v15 >> 13) ^ (v5 - v4 - v15);
  v17 = (v16 << 8) ^ (v4 - v15 - v16);
  v18 = ((unsigned int)v17 >> 13) ^ (v15 - v16 - v17);
  v19 = ((unsigned int)v18 >> 12) ^ (v16 - v17 - v18);
  v20 = (v19 << 16) ^ (v17 - v18 - v19);
  v21 = ((unsigned int)v20 >> 5) ^ (v18 - v19 - v20);
  v22 = ((unsigned int)v21 >> 3) ^ (v19 - v20 - v21);
  return (((v22 << 10) ^ (unsigned int)(v20 - v21 - v22)) >> 15) ^ (v21 - v22 - ((v22 << 10) ^ (v20 - v21 - v22)));
}
  1. First and foremost, is this a standard algorithm like CRC or something?
  2. Is there a reason for the v4 and v5 variables to be -1640531527?
  3. What is the purpose of "(*(_BYTE *)(content + 7) << 24)" isn't a byte only 8 bits, so won't it be 0 every time? I looked up the order of operations and it seems that the casting is first then the bit operations, so it means it converts it to the 8th byte in the file and bit shifts it 24 bits right? why?
  4. Why are some bits signed and some unsigned, and would it change the outcome if there is a mix?

Thanks!

unsigned int __cdecl newhash(int a1, unsigned int a2, int zero)
{
  int content; // ebx@1
  int v4; // ecx@1
  int v5; // edx@1
  int i; // eax@1
  int v7; // ecx@2
  unsigned int v8; // eax@2
  int v9; // edx@2
  int v10; // ecx@2
  int v11; // eax@2
  int v12; // edx@2
  int v13; // ecx@2
  int v14; // eax@2
  unsigned int v15; // eax@3
  int v16; // edx@15
  int v17; // ecx@15
  int v18; // eax@15
  int v19; // edx@15
  int v20; // ecx@15
  int v21; // eax@15
  int v22; // edx@15
  unsigned int contentLength; // [sp+Ch] [bp-4h]@1

  content = a1;
  contentLength = a2;
  v4 = -1640531527;
  v5 = -1640531527;
  for ( i = zero; contentLength >= 12; contentLength -= 12 )
  {
    v7 = (*(_BYTE *)(content + 7) << 24)
       + (*(_BYTE *)(content + 6) << 16)
       + (*(_BYTE *)(content + 5) << 8)
       + *(_BYTE *)(content + 4)
       + v4;
    v8 = (*(_BYTE *)(content + 11) << 24)
       + (*(_BYTE *)(content + 10) << 16)
       + (*(_BYTE *)(content + 9) << 8)
       + *(_BYTE *)(content + 8)
       + i;
    v9 = (v8 >> 13) ^ ((*(_BYTE *)(content + 3) << 24)
                     + (*(_BYTE *)(content + 2) << 16)
                     + (*(_BYTE *)(content + 1) << 8)
                     + *(_BYTE *)content
                     + v5
                     - v7
                     - v8);
    v10 = (v9 << 8) ^ (v7 - v8 - v9);
    v11 = ((unsigned int)v10 >> 13) ^ (v8 - v9 - v10);
    v12 = ((unsigned int)v11 >> 12) ^ (v9 - v10 - v11);
    v13 = (v12 << 16) ^ (v10 - v11 - v12);
    v14 = ((unsigned int)v13 >> 5) ^ (v11 - v12 - v13);
    v5 = ((unsigned int)v14 >> 3) ^ (v12 - v13 - v14);
    v4 = (v5 << 10) ^ (v13 - v14 - v5);
    i = ((unsigned int)v4 >> 15) ^ (v14 - v5 - v4);
    content += 12;
  }
  v15 = a2 + i;
  switch ( contentLength )
  {
    case 0xBu:
      v15 += *(_BYTE *)(content + 10) << 24;
      goto LABEL_5;
    case 0xAu:
LABEL_5:
      v15 += *(_BYTE *)(content + 9) << 16;
      goto LABEL_6;
    case 9u:
LABEL_6:
      v15 += *(_BYTE *)(content + 8) << 8;
      goto LABEL_7;
    case 8u:
LABEL_7:
      v4 += *(_BYTE *)(content + 7) << 24;
      goto LABEL_8;
    case 7u:
LABEL_8:
      v4 += *(_BYTE *)(content + 6) << 16;
      goto LABEL_9;
    case 6u:
LABEL_9:
      v4 += *(_BYTE *)(content + 5) << 8;
      goto LABEL_10;
    case 5u:
LABEL_10:
      v4 += *(_BYTE *)(content + 4);
      goto LABEL_11;
    case 4u:
LABEL_11:
      v5 += *(_BYTE *)(content + 3) << 24;
      goto LABEL_12;
    case 3u:
LABEL_12:
      v5 += *(_BYTE *)(content + 2) << 16;
      goto LABEL_13;
    case 2u:
LABEL_13:
      v5 += *(_BYTE *)(content + 1) << 8;
      goto LABEL_14;
    case 1u:
LABEL_14:
      v5 += *(_BYTE *)content;
      break;
    default:
      break;
  }
  v16 = (v15 >> 13) ^ (v5 - v4 - v15);
  v17 = (v16 << 8) ^ (v4 - v15 - v16);
  v18 = ((unsigned int)v17 >> 13) ^ (v15 - v16 - v17);
  v19 = ((unsigned int)v18 >> 12) ^ (v16 - v17 - v18);
  v20 = (v19 << 16) ^ (v17 - v18 - v19);
  v21 = ((unsigned int)v20 >> 5) ^ (v18 - v19 - v20);
  v22 = ((unsigned int)v21 >> 3) ^ (v19 - v20 - v21); 

  return (((v22 << 10) ^ 
           (unsigned int)(v20 - v21 - v22)) >> 15) ^ 
           (v21 - v22 - ((v22 << 10) ^ (v20 - v21 - v22)));
}
  1. First and foremost, is this a standard algorithm like CRC or something?
  2. Is there a reason for the v4 and v5 variables to be -1640531527?
  3. What is the purpose of (*(_BYTE *)(content + 7) << 24) isn't a byte only 8 bits, so won't it be 0 every time? I looked up the order of operations and it seems that the casting is first then the bit operations, so it means it converts it to the 8th byte in the file and bit shifts it 24 bits right? why?
  4. Why are some bits signed and some unsigned, and would it change the outcome if there is a mix?
1
source | link

Hash algorithm written in C decompiled with IDA

I have been working on rewriting a program, although it uses a hash to fingerprint the file, I have used IDA to find the function doing the hash and what it is doing to the file before it sends it to the hash function.

I just have a couple questions about what is going on, I know I can simply invoke it as it is in a DLL, but I want to understand what is going on as well.

unsigned int __cdecl newhash(int a1, unsigned int a2, int zero)
{
  int content; // ebx@1
  int v4; // ecx@1
  int v5; // edx@1
  int i; // eax@1
  int v7; // ecx@2
  unsigned int v8; // eax@2
  int v9; // edx@2
  int v10; // ecx@2
  int v11; // eax@2
  int v12; // edx@2
  int v13; // ecx@2
  int v14; // eax@2
  unsigned int v15; // eax@3
  int v16; // edx@15
  int v17; // ecx@15
  int v18; // eax@15
  int v19; // edx@15
  int v20; // ecx@15
  int v21; // eax@15
  int v22; // edx@15
  unsigned int contentLength; // [sp+Ch] [bp-4h]@1

  content = a1;
  contentLength = a2;
  v4 = -1640531527;
  v5 = -1640531527;
  for ( i = zero; contentLength >= 12; contentLength -= 12 )
  {
    v7 = (*(_BYTE *)(content + 7) << 24)
       + (*(_BYTE *)(content + 6) << 16)
       + (*(_BYTE *)(content + 5) << 8)
       + *(_BYTE *)(content + 4)
       + v4;
    v8 = (*(_BYTE *)(content + 11) << 24)
       + (*(_BYTE *)(content + 10) << 16)
       + (*(_BYTE *)(content + 9) << 8)
       + *(_BYTE *)(content + 8)
       + i;
    v9 = (v8 >> 13) ^ ((*(_BYTE *)(content + 3) << 24)
                     + (*(_BYTE *)(content + 2) << 16)
                     + (*(_BYTE *)(content + 1) << 8)
                     + *(_BYTE *)content
                     + v5
                     - v7
                     - v8);
    v10 = (v9 << 8) ^ (v7 - v8 - v9);
    v11 = ((unsigned int)v10 >> 13) ^ (v8 - v9 - v10);
    v12 = ((unsigned int)v11 >> 12) ^ (v9 - v10 - v11);
    v13 = (v12 << 16) ^ (v10 - v11 - v12);
    v14 = ((unsigned int)v13 >> 5) ^ (v11 - v12 - v13);
    v5 = ((unsigned int)v14 >> 3) ^ (v12 - v13 - v14);
    v4 = (v5 << 10) ^ (v13 - v14 - v5);
    i = ((unsigned int)v4 >> 15) ^ (v14 - v5 - v4);
    content += 12;
  }
  v15 = a2 + i;
  switch ( contentLength )
  {
    case 0xBu:
      v15 += *(_BYTE *)(content + 10) << 24;
      goto LABEL_5;
    case 0xAu:
LABEL_5:
      v15 += *(_BYTE *)(content + 9) << 16;
      goto LABEL_6;
    case 9u:
LABEL_6:
      v15 += *(_BYTE *)(content + 8) << 8;
      goto LABEL_7;
    case 8u:
LABEL_7:
      v4 += *(_BYTE *)(content + 7) << 24;
      goto LABEL_8;
    case 7u:
LABEL_8:
      v4 += *(_BYTE *)(content + 6) << 16;
      goto LABEL_9;
    case 6u:
LABEL_9:
      v4 += *(_BYTE *)(content + 5) << 8;
      goto LABEL_10;
    case 5u:
LABEL_10:
      v4 += *(_BYTE *)(content + 4);
      goto LABEL_11;
    case 4u:
LABEL_11:
      v5 += *(_BYTE *)(content + 3) << 24;
      goto LABEL_12;
    case 3u:
LABEL_12:
      v5 += *(_BYTE *)(content + 2) << 16;
      goto LABEL_13;
    case 2u:
LABEL_13:
      v5 += *(_BYTE *)(content + 1) << 8;
      goto LABEL_14;
    case 1u:
LABEL_14:
      v5 += *(_BYTE *)content;
      break;
    default:
      break;
  }
  v16 = (v15 >> 13) ^ (v5 - v4 - v15);
  v17 = (v16 << 8) ^ (v4 - v15 - v16);
  v18 = ((unsigned int)v17 >> 13) ^ (v15 - v16 - v17);
  v19 = ((unsigned int)v18 >> 12) ^ (v16 - v17 - v18);
  v20 = (v19 << 16) ^ (v17 - v18 - v19);
  v21 = ((unsigned int)v20 >> 5) ^ (v18 - v19 - v20);
  v22 = ((unsigned int)v21 >> 3) ^ (v19 - v20 - v21);
  return (((v22 << 10) ^ (unsigned int)(v20 - v21 - v22)) >> 15) ^ (v21 - v22 - ((v22 << 10) ^ (v20 - v21 - v22)));
}

a1 is an address location a2 is the length of the file to hash zero I renamed as it always sends zero for whatever reason.

Now for the questions:

  1. First and foremost, is this a standard algorithm like CRC or something?
  2. Is there a reason for the v4 and v5 variables to be -1640531527?
  3. What is the purpose of "(*(_BYTE *)(content + 7) << 24)" isn't a byte only 8 bits, so won't it be 0 every time? I looked up the order of operations and it seems that the casting is first then the bit operations, so it means it converts it to the 8th byte in the file and bit shifts it 24 bits right? why?
  4. Why are some bits signed and some unsigned, and would it change the outcome if there is a mix?

Those are most of my questions, I understand it is going through all the bytes and getting a total to figure out the "hash" for the file, I understand that the switch case is taking care of the situation of the file not being exactly divisible by 12. I think once I understand the logic behind the bitwise operations then it will be more clear.

Thanks!