diff --git a/src/gba/gba.c b/src/gba/gba.c index c02e91be6..b5fd146ef 100644 --- a/src/gba/gba.c +++ b/src/gba/gba.c @@ -400,6 +400,9 @@ void GBALoadBIOS(struct GBA* gba, int fd) { void GBAApplyPatch(struct GBA* gba, struct Patch* patch) { size_t patchedSize = patch->outputSize(patch, gba->memory.romSize); + if (!patchedSize) { + return; + } gba->memory.rom = anonymousMemoryMap(patchedSize); memcpy(gba->memory.rom, gba->pristineRom, gba->memory.romSize > patchedSize ? patchedSize : gba->memory.romSize); if (!patch->applyPatch(patch, gba->memory.rom, patchedSize)) { diff --git a/src/util/crc32.c b/src/util/crc32.c new file mode 100644 index 000000000..fcca744d3 --- /dev/null +++ b/src/util/crc32.c @@ -0,0 +1,104 @@ +/*- + * COPYRIGHT (C) 1986 Gary S. Brown. You may use this program, or + * code or tables extracted from it, as desired without restriction. + * + * First, the polynomial itself and its table of feedback terms. The + * polynomial is + * X^32+X^26+X^23+X^22+X^16+X^12+X^11+X^10+X^8+X^7+X^5+X^4+X^2+X^1+X^0 + * + * Note that we take it "backwards" and put the highest-order term in + * the lowest-order bit. The X^32 term is "implied"; the LSB is the + * X^31 term, etc. The X^0 term (usually shown as "+1") results in + * the MSB being 1 + * + * Note that the usual hardware shift register implementation, which + * is what we're using (we're merely optimizing it by doing eight-bit + * chunks at a time) shifts bits into the lowest-order term. In our + * implementation, that means shifting towards the right. Why do we + * do it this way? Because the calculated CRC must be transmitted in + * order from highest-order term to lowest-order term. UARTs transmit + * characters in order from LSB to MSB. By storing the CRC this way + * we hand it to the UART in the order low-byte to high-byte; the UART + * sends each low-bit to hight-bit; and the result is transmission bit + * by bit from highest- to lowest-order term without requiring any bit + * shuffling on our part. Reception works similarly + * + * The feedback terms table consists of 256, 32-bit entries. Notes + * + * The table can be generated at runtime if desired; code to do so + * is shown later. It might not be obvious, but the feedback + * terms simply represent the results of eight shift/xor opera + * tions for all combinations of data and CRC register values + * + * The values must be right-shifted by eight bits by the "updcrc + * logic; the shift must be unsigned (bring in zeroes). On some + * hardware you could probably optimize the shift in assembler by + * using byte-swap instructions + * polynomial $edb88320 + * + * + * CRC32 code derived from work by Gary S. Brown. + */ + +#include "util/crc32.h" + +static uint32_t crc32Table[] = { + 0x00000000, 0x77073096, 0xee0e612c, 0x990951ba, 0x076dc419, 0x706af48f, + 0xe963a535, 0x9e6495a3, 0x0edb8832, 0x79dcb8a4, 0xe0d5e91e, 0x97d2d988, + 0x09b64c2b, 0x7eb17cbd, 0xe7b82d07, 0x90bf1d91, 0x1db71064, 0x6ab020f2, + 0xf3b97148, 0x84be41de, 0x1adad47d, 0x6ddde4eb, 0xf4d4b551, 0x83d385c7, + 0x136c9856, 0x646ba8c0, 0xfd62f97a, 0x8a65c9ec, 0x14015c4f, 0x63066cd9, + 0xfa0f3d63, 0x8d080df5, 0x3b6e20c8, 0x4c69105e, 0xd56041e4, 0xa2677172, + 0x3c03e4d1, 0x4b04d447, 0xd20d85fd, 0xa50ab56b, 0x35b5a8fa, 0x42b2986c, + 0xdbbbc9d6, 0xacbcf940, 0x32d86ce3, 0x45df5c75, 0xdcd60dcf, 0xabd13d59, + 0x26d930ac, 0x51de003a, 0xc8d75180, 0xbfd06116, 0x21b4f4b5, 0x56b3c423, + 0xcfba9599, 0xb8bda50f, 0x2802b89e, 0x5f058808, 0xc60cd9b2, 0xb10be924, + 0x2f6f7c87, 0x58684c11, 0xc1611dab, 0xb6662d3d, 0x76dc4190, 0x01db7106, + 0x98d220bc, 0xefd5102a, 0x71b18589, 0x06b6b51f, 0x9fbfe4a5, 0xe8b8d433, + 0x7807c9a2, 0x0f00f934, 0x9609a88e, 0xe10e9818, 0x7f6a0dbb, 0x086d3d2d, + 0x91646c97, 0xe6635c01, 0x6b6b51f4, 0x1c6c6162, 0x856530d8, 0xf262004e, + 0x6c0695ed, 0x1b01a57b, 0x8208f4c1, 0xf50fc457, 0x65b0d9c6, 0x12b7e950, + 0x8bbeb8ea, 0xfcb9887c, 0x62dd1ddf, 0x15da2d49, 0x8cd37cf3, 0xfbd44c65, + 0x4db26158, 0x3ab551ce, 0xa3bc0074, 0xd4bb30e2, 0x4adfa541, 0x3dd895d7, + 0xa4d1c46d, 0xd3d6f4fb, 0x4369e96a, 0x346ed9fc, 0xad678846, 0xda60b8d0, + 0x44042d73, 0x33031de5, 0xaa0a4c5f, 0xdd0d7cc9, 0x5005713c, 0x270241aa, + 0xbe0b1010, 0xc90c2086, 0x5768b525, 0x206f85b3, 0xb966d409, 0xce61e49f, + 0x5edef90e, 0x29d9c998, 0xb0d09822, 0xc7d7a8b4, 0x59b33d17, 0x2eb40d81, + 0xb7bd5c3b, 0xc0ba6cad, 0xedb88320, 0x9abfb3b6, 0x03b6e20c, 0x74b1d29a, + 0xead54739, 0x9dd277af, 0x04db2615, 0x73dc1683, 0xe3630b12, 0x94643b84, + 0x0d6d6a3e, 0x7a6a5aa8, 0xe40ecf0b, 0x9309ff9d, 0x0a00ae27, 0x7d079eb1, + 0xf00f9344, 0x8708a3d2, 0x1e01f268, 0x6906c2fe, 0xf762575d, 0x806567cb, + 0x196c3671, 0x6e6b06e7, 0xfed41b76, 0x89d32be0, 0x10da7a5a, 0x67dd4acc, + 0xf9b9df6f, 0x8ebeeff9, 0x17b7be43, 0x60b08ed5, 0xd6d6a3e8, 0xa1d1937e, + 0x38d8c2c4, 0x4fdff252, 0xd1bb67f1, 0xa6bc5767, 0x3fb506dd, 0x48b2364b, + 0xd80d2bda, 0xaf0a1b4c, 0x36034af6, 0x41047a60, 0xdf60efc3, 0xa867df55, + 0x316e8eef, 0x4669be79, 0xcb61b38c, 0xbc66831a, 0x256fd2a0, 0x5268e236, + 0xcc0c7795, 0xbb0b4703, 0x220216b9, 0x5505262f, 0xc5ba3bbe, 0xb2bd0b28, + 0x2bb45a92, 0x5cb36a04, 0xc2d7ffa7, 0xb5d0cf31, 0x2cd99e8b, 0x5bdeae1d, + 0x9b64c2b0, 0xec63f226, 0x756aa39c, 0x026d930a, 0x9c0906a9, 0xeb0e363f, + 0x72076785, 0x05005713, 0x95bf4a82, 0xe2b87a14, 0x7bb12bae, 0x0cb61b38, + 0x92d28e9b, 0xe5d5be0d, 0x7cdcefb7, 0x0bdbdf21, 0x86d3d2d4, 0xf1d4e242, + 0x68ddb3f8, 0x1fda836e, 0x81be16cd, 0xf6b9265b, 0x6fb077e1, 0x18b74777, + 0x88085ae6, 0xff0f6a70, 0x66063bca, 0x11010b5c, 0x8f659eff, 0xf862ae69, + 0x616bffd3, 0x166ccf45, 0xa00ae278, 0xd70dd2ee, 0x4e048354, 0x3903b3c2, + 0xa7672661, 0xd06016f7, 0x4969474d, 0x3e6e77db, 0xaed16a4a, 0xd9d65adc, + 0x40df0b66, 0x37d83bf0, 0xa9bcae53, 0xdebb9ec5, 0x47b2cf7f, 0x30b5ffe9, + 0xbdbdf21c, 0xcabac28a, 0x53b39330, 0x24b4a3a6, 0xbad03605, 0xcdd70693, + 0x54de5729, 0x23d967bf, 0xb3667a2e, 0xc4614ab8, 0x5d681b02, 0x2a6f2b94, + 0xb40bbe37, 0xc30c8ea1, 0x5a05df1b, 0x2d02ef8d +}; + +uint32_t crc32(const void* buf, size_t size) { + updateCrc32(0, buf, size); +} + +uint32_t updateCrc32(uint32_t crc, const void* buf, size_t size) { + const uint8_t* p = buf; + + crc = ~crc; + for (size_t i = 0; i < size; ++i) { + crc = crc32Table[(crc ^ p[i]) & 0xFF] ^ (crc >> 8); + } + + return ~crc; +} diff --git a/src/util/crc32.h b/src/util/crc32.h new file mode 100644 index 000000000..5716e9782 --- /dev/null +++ b/src/util/crc32.h @@ -0,0 +1,10 @@ +#ifndef CRC32_H +#define CRC32_H + +#include +#include + +uint32_t crc32(const void* buf, size_t size); +uint32_t updateCrc32(uint32_t crc, const void* buf, size_t size); + +#endif diff --git a/src/util/patch-ups.c b/src/util/patch-ups.c new file mode 100644 index 000000000..102db6de1 --- /dev/null +++ b/src/util/patch-ups.c @@ -0,0 +1,135 @@ +#include "util/patch-ips.h" + +#include "util/crc32.h" +#include "util/patch.h" + +#include +#include + +enum { + IN_CHECKSUM = -12, + OUT_CHECKSUM = -8, + PATCH_CHECKSUM = -4, + + BUFFER_SIZE = 1024 +}; + +static size_t _UPSOutputSize(struct Patch* patch, size_t inSize); +static int _UPSApplyPatch(struct Patch* patch, void* out, size_t outSize); +static size_t _UPSDecodeLength(int fd); + +int loadPatchUPS(struct Patch* patch) { + lseek(patch->patchfd, 0, SEEK_SET); + + char buffer[BUFFER_SIZE]; + if (read(patch->patchfd, buffer, 4) != 4) { + return 0; + } + + if (memcmp(buffer, "UPS1", 4) != 0) { + return 0; + } + + size_t filesize = lseek(patch->patchfd, 0, SEEK_END); + + uint32_t goodCrc32; + lseek(patch->patchfd, PATCH_CHECKSUM, SEEK_END); + if (read(patch->patchfd, &goodCrc32, 4) != 4) { + return 0; + } + + size_t blocksize; + size_t alreadyRead = 0; + lseek(patch->patchfd, 0, SEEK_SET); + uint32_t crc = 0; + while (alreadyRead < filesize + PATCH_CHECKSUM) { + size_t toRead = sizeof(buffer); + if (toRead + alreadyRead > filesize + PATCH_CHECKSUM) { + toRead = filesize + PATCH_CHECKSUM - alreadyRead; + } + blocksize = read(patch->patchfd, buffer, toRead); + alreadyRead += blocksize; + crc = updateCrc32(crc, buffer, blocksize); + if (blocksize < toRead) { + return 0; + } + } + + if (crc != goodCrc32) { + return 0; + } + + patch->outputSize = _UPSOutputSize; + patch->applyPatch = _UPSApplyPatch; + return 1; +} + +size_t _UPSOutputSize(struct Patch* patch, size_t inSize) { + (void) (inSize); + lseek(patch->patchfd, 4, SEEK_SET); + if (_UPSDecodeLength(patch->patchfd) != inSize) { + return 0; + } + return _UPSDecodeLength(patch->patchfd); +} + +int _UPSApplyPatch(struct Patch* patch, void* out, size_t outSize) { + // TODO: Input checksum + + size_t filesize = lseek(patch->patchfd, 0, SEEK_END); + lseek(patch->patchfd, 4, SEEK_SET); + _UPSDecodeLength(patch->patchfd); // Discard input size + if (_UPSDecodeLength(patch->patchfd) != outSize) { + return 0; + } + + size_t offset = 0; + size_t alreadyRead = 0; + uint8_t* buf = out; + while (alreadyRead < filesize + IN_CHECKSUM) { + offset += _UPSDecodeLength(patch->patchfd); + uint8_t byte; + + while (1) { + if (read(patch->patchfd, &byte, 1) != 1) { + return 0; + } + buf[offset] ^= byte; + ++offset; + if (!byte) { + break; + } + } + alreadyRead = lseek(patch->patchfd, 0, SEEK_CUR); + } + + uint32_t goodCrc32; + lseek(patch->patchfd, OUT_CHECKSUM, SEEK_END); + if (read(patch->patchfd, &goodCrc32, 4) != 4) { + return 0; + } + + lseek(patch->patchfd, 0, SEEK_SET); + if (crc32(out, outSize) != goodCrc32) { + return 0; + } + return 1; +} + +size_t _UPSDecodeLength(int fd) { + size_t shift = 1; + size_t value = 0; + uint8_t byte; + while (1) { + if (read(fd, &byte, 1) != 1) { + break; + } + value += (byte & 0x7f) * shift; + if (byte & 0x80) { + break; + } + shift <<= 7; + value += shift; + } + return value; +} diff --git a/src/util/patch-ups.h b/src/util/patch-ups.h new file mode 100644 index 000000000..80038baf3 --- /dev/null +++ b/src/util/patch-ups.h @@ -0,0 +1,8 @@ +#ifndef PATCH_UPS_H +#define PATCH_UPS_H + +struct Patch; + +int loadPatchUPS(struct Patch* patch); + +#endif diff --git a/src/util/patch.c b/src/util/patch.c index c9e080ecf..189542f7f 100644 --- a/src/util/patch.c +++ b/src/util/patch.c @@ -1,6 +1,7 @@ #include "util/patch.h" #include "util/patch-ips.h" +#include "util/patch-ups.h" int loadPatch(int patchfd, struct Patch* patch) { patch->patchfd = patchfd; @@ -9,6 +10,10 @@ int loadPatch(int patchfd, struct Patch* patch) { return 1; } + if (loadPatchUPS(patch)) { + return 1; + } + patch->outputSize = 0; patch->applyPatch = 0; return 0;