This is what M1-type NAOMI cart looks like:
And that is what it took to figure out how the FPGA handles the protected data:
Cracking this nut took plenty of time and hard work. Originally I planned on explaining this in great detail, with photos and screenshots, but in the end decided not to. Sadly, most people couldn't care less (as long as they get to play "free" games) and/or consider this black magic that is best left to nerds and otherwise smelly people. So, I'm going to post the source code. Those of you that can parse C should find it somewhat interesting, those that can't are probably reading wrong blog.
/*
This is a concept version of M1 decoder. It's fully functional, except for
clarity it doesn't handle cases where the data stream ends and you want to
keep reading - to add that functionality just move input buffer cursor to next
4-byte boundary and restart decoding (by re-reading dictionary again).
The source includes a brute-force exhaustive cracker (takes about an hour
for a decent CPU). Pattern compare with just 4 bytes might return some very
close but not correct XOR masks so I decided on 6. Due to the simplification
I explained above it's theoreticaly possible for the cracker to fail (if there
is EOS symbol in the first 6 decoded bytes), but that is highly unlikely.
D.
*/
#include
#include
#include
#include
#define CRACKER
uint8_t ReadByte ();
void StoreByte (uint8_t b);
void ShiftIn ();
void Decode (uint32_t mask);
//-------------------------------------------------------------------------
int s_in_len, s_in_pos;
uint8_t* s_input;
uint8_t s_xor [4];
uint8_t s_dict [111];
int s_subst;
int s_out_len, s_out_cnt;
uint8_t* s_output;
int s_shift, s_bits;
//-------------------------------------------------------------------------
uint8_t ReadByte ()
{
uint8_t v;
switch (s_in_pos & 3)
{
case 0:
v = s_input [s_in_pos + 3];
v ^= s_input [s_in_pos + 1];
break;
case 1:
v = s_input [s_in_pos + 1];
v ^= s_input [s_in_pos - 1];
break;
case 2:
v = s_input [s_in_pos - 1];
break;
case 3:
v = s_input [s_in_pos - 3];
break;
}
v ^= s_xor [s_in_pos & 3];
s_in_pos++;
return v;
}
//-------------------------------------------------------------------------
void StoreByte (uint8_t b)
{
if (s_subst && s_out_cnt >= 2)
b = s_output [s_out_cnt - 2] - b;
s_output [s_out_cnt] = b;
s_out_cnt++;
}
//-------------------------------------------------------------------------
void ShiftIn ()
{
s_shift <<= 8;
s_shift |= ReadByte ();
s_bits += 8;
}
//-------------------------------------------------------------------------
void Decode (uint32_t mask)
{
int i, eos;
s_xor [0] = (uint8_t)mask;
s_xor [1] = (uint8_t)(mask >> 8);
s_xor [2] = (uint8_t)(mask >> 16);
s_xor [3] = (uint8_t)(mask >> 24);
// byte dictionary
s_in_pos = 0;
for (i = 0; i < 111; i++)
s_dict [i] = ReadByte ();
// control bits
s_subst = (s_dict [0] & 64) ? 1 : 0;
// command stream
s_out_cnt = 0, eos = 0;
s_shift = 0, s_bits = 0;
while (!eos && s_in_pos < s_in_len)
{
int code, addr, t;
if (s_bits < 2)
ShiftIn ();
code = (s_shift >> (s_bits - 2)) & 3;
switch (code)
{
case 0:
// 00-aa
if (s_bits < 4)
ShiftIn ();
addr = (s_shift >> (s_bits - 4)) & 3;
s_bits -= 4;
if (addr == 0)
{
// quotation
if (s_bits < 8)
ShiftIn ();
t = (s_shift >> (s_bits - 8)) & 255;
s_bits -= 8;
StoreByte (t);
break;
}
StoreByte (s_dict [addr]);
break;
case 1:
if (s_bits < 5)
ShiftIn ();
t = (s_shift >> (s_bits - 3)) & 1;
if (t == 0)
{
// 010-aa
addr = (s_shift >> (s_bits - 5)) & 3;
addr += 4;
s_bits -= 5;
}
else
{
// 011-aaa
if (s_bits < 6)
ShiftIn ();
addr = (s_shift >> (s_bits - 6)) & 7;
addr += 8;
s_bits -= 6;
}
StoreByte (s_dict [addr]);
break;
case 2:
if (s_bits < 7)
ShiftIn ();
// 10-aaaaa
addr = (s_shift >> (s_bits - 7)) & 31;
addr += 16;
s_bits -= 7;
StoreByte (s_dict [addr]);
break;
case 3:
if (s_bits < 8)
ShiftIn ();
// 11-aaaaaa
addr = (s_shift >> (s_bits - 8)) & 63;
addr += 48;
s_bits -= 8;
if (addr == 111)
// end of stream
eos = 1;
else
StoreByte (s_dict [addr]);
break;
}
}
}
//-------------------------------------------------------------------------
int main (int ia, char *ta [])
{
char* name;
FILE* f;
uint32_t m, x;
time_t t1, t2;
uint8_t pattern [6];
int t;
name = (ia < 2) ? (char*)"input.bin" : ta [1];
f = fopen (name, "rb");
if (f == NULL)
{
printf ("File open error: %s\n", name);
return 1;
}
fseek (f, 0, SEEK_END);
s_in_len = ftell (f);
if (s_in_len < 112)
{
printf ("File too short: %s\n", name);
return 1;
}
s_input = new uint8_t [s_in_len];
fseek (f, 0, SEEK_SET);
fread (s_input, 1, s_in_len, f);
fclose (f);
s_out_len = (s_in_len - 111) * 2;
s_output = new uint8_t [s_out_len];
name = (ia < 3) ? (char*)"pattern.bin" : ta [2];
f = fopen (name, "rb");
if (f == NULL)
{
printf ("File open error: %s\n", name);
return 1;
}
if (fread (pattern, 1, 6, f) < 6)
{
printf ("File too short: %s\n", name);
return 1;
}
fclose (f);
// 840-0030 / AH! MY GODDESS QUIZ GAME: 0xCD9B4896
// 840-0039 / Giant Gram 2000: 0x7F805C3F
// 840-0084 / Virtua Tennis 2: 0x2D2D4743
// 840-0098 / Shootout Pool: 0xA0F37CA7
// 840-0106 / Virtua Fighter 4 Evolution: 0x1E5BB0CD
// 840-0128 / Shootout Pool Prize: 0x9DBDE9CD
// 840-0136 / Shootout Pool Medal: 0x9DBDE9CD
// 840-0140 / Kick'4'Cash: 0x820857C9
// 840-0150 / MKG TKOB 2K3 2ND VER1.003-: 0x3892FB3A
// 841-0007 / Marvel vs. Capcom 2: 0xC18B6E7C
#ifdef CRACKER
x = 0, time (&t1);
t = s_in_len;
s_in_len = 0x88;
for (m = ~0; m != 0; m--)
#else
m = 0xCD9B4896;
#endif
{
Decode (m);
#ifdef CRACKER
if (memcmp (s_output, pattern, 6) == 0)
{
printf ("XOR mask: 0x%08X\n", m);
break;
}
if (x - m > 1024)
{
x = m;
time (&t2);
if (t1 != t2)
{
t1 = t2;
printf ("0x%08X...\n", m);
fflush (stdout);
}
}
#endif
}
#ifdef CRACKER
s_in_len = t;
Decode (m);
#endif
f = fopen ("output.bin", "wb");
if (f == NULL)
return 1;
fwrite (s_output, 1, s_out_cnt, f);
fclose (f);
return 0;
}
Also, NAOMI Test 12/7. I don't have time to work on T13 lately and I'm not going to rush it, so you get this instead. I experimented a lot on this code - it might be actually less stable than the previous version. On the bright side, Power Stone is playable now. Should be, anyway :) |
0 Comments
Post a Comment