diff options
Diffstat (limited to 'Documentation/howto')
| -rw-r--r-- | Documentation/howto/new-command.txt | 6 | ||||
| -rw-r--r-- | Documentation/howto/recover-corrupted-object-harder.txt | 237 | ||||
| -rw-r--r-- | Documentation/howto/revert-a-faulty-merge.txt | 16 |
3 files changed, 249 insertions, 10 deletions
diff --git a/Documentation/howto/new-command.txt b/Documentation/howto/new-command.txt index d7de5a3e9e..15a4c8031f 100644 --- a/Documentation/howto/new-command.txt +++ b/Documentation/howto/new-command.txt @@ -94,8 +94,10 @@ your language, document it in the INSTALL file. 6. There is a file command-list.txt in the distribution main directory that categorizes commands by type, so they can be listed in appropriate subsections in the documentation's summary command list. Add an entry -for yours. To understand the categories, look at git-commands.txt -in the main directory. +for yours. To understand the categories, look at command-list.txt +in the main directory. If the new command is part of the typical Git +workflow and you believe it common enough to be mentioned in 'git help', +map this command to a common group in the column [common]. 7. Give the maintainer one paragraph to include in the RelNotes file to describe the new feature; a good place to do so is in the cover diff --git a/Documentation/howto/recover-corrupted-object-harder.txt b/Documentation/howto/recover-corrupted-object-harder.txt index 23e685d8ca..9c4cd0915f 100644 --- a/Documentation/howto/recover-corrupted-object-harder.txt +++ b/Documentation/howto/recover-corrupted-object-harder.txt @@ -240,3 +240,240 @@ But more importantly, git's hashing and checksumming noticed a problem that easily could have gone undetected in another system. The result still compiled, but would have caused an interesting bug (that would have been blamed on some random commit). + + +The adventure continues... +-------------------------- + +I ended up doing this again! Same entity, new hardware. The assumption +at this point is that the old disk corrupted the packfile, and then the +corruption was migrated to the new hardware (because it was done by +rsync or similar, and no fsck was done at the time of migration). + +This time, the affected blob was over 20 megabytes, which was far too +large to do a brute-force on. I followed the instructions above to +create the `zlib` file. I then used the `inflate` program below to pull +the corrupted data from that. Examining that output gave me a hint about +where in the file the corruption was. But now I was working with the +file itself, not the zlib contents. So knowing the sha1 of the object +and the approximate area of the corruption, I used the `sha1-munge` +program below to brute-force the correct byte. + +Here's the inflate program (it's essentially `gunzip` but without the +`.gz` header processing): + +-------------------------- +#include <stdio.h> +#include <string.h> +#include <zlib.h> +#include <stdlib.h> + +int main(int argc, char **argv) +{ + /* + * oversized so we can read the whole buffer in; + * this could actually be switched to streaming + * to avoid any memory limitations + */ + static unsigned char buf[25 * 1024 * 1024]; + static unsigned char out[25 * 1024 * 1024]; + int len; + z_stream z; + int ret; + + len = read(0, buf, sizeof(buf)); + memset(&z, 0, sizeof(z)); + inflateInit(&z); + + z.next_in = buf; + z.avail_in = len; + z.next_out = out; + z.avail_out = sizeof(out); + + ret = inflate(&z, 0); + if (ret != Z_OK && ret != Z_STREAM_END) + fprintf(stderr, "initial inflate failed (%d)\n", ret); + + fprintf(stderr, "outputting %lu bytes", z.total_out); + fwrite(out, 1, z.total_out, stdout); + return 0; +} +-------------------------- + +And here is the `sha1-munge` program: + +-------------------------- +#include <stdio.h> +#include <unistd.h> +#include <string.h> +#include <signal.h> +#include <openssl/sha.h> +#include <stdlib.h> + +/* eye candy */ +static int counter = 0; +static void progress(int sig) +{ + fprintf(stderr, "\r%d", counter); + alarm(1); +} + +static const signed char hexval_table[256] = { + -1, -1, -1, -1, -1, -1, -1, -1, /* 00-07 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 08-0f */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 10-17 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 18-1f */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 20-27 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 28-2f */ + 0, 1, 2, 3, 4, 5, 6, 7, /* 30-37 */ + 8, 9, -1, -1, -1, -1, -1, -1, /* 38-3f */ + -1, 10, 11, 12, 13, 14, 15, -1, /* 40-47 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 48-4f */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 50-57 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 58-5f */ + -1, 10, 11, 12, 13, 14, 15, -1, /* 60-67 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 68-67 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 70-77 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 78-7f */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 80-87 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 88-8f */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 90-97 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* 98-9f */ + -1, -1, -1, -1, -1, -1, -1, -1, /* a0-a7 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* a8-af */ + -1, -1, -1, -1, -1, -1, -1, -1, /* b0-b7 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* b8-bf */ + -1, -1, -1, -1, -1, -1, -1, -1, /* c0-c7 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* c8-cf */ + -1, -1, -1, -1, -1, -1, -1, -1, /* d0-d7 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* d8-df */ + -1, -1, -1, -1, -1, -1, -1, -1, /* e0-e7 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* e8-ef */ + -1, -1, -1, -1, -1, -1, -1, -1, /* f0-f7 */ + -1, -1, -1, -1, -1, -1, -1, -1, /* f8-ff */ +}; + +static inline unsigned int hexval(unsigned char c) +{ +return hexval_table[c]; +} + +static int get_sha1_hex(const char *hex, unsigned char *sha1) +{ + int i; + for (i = 0; i < 20; i++) { + unsigned int val; + /* + * hex[1]=='\0' is caught when val is checked below, + * but if hex[0] is NUL we have to avoid reading + * past the end of the string: + */ + if (!hex[0]) + return -1; + val = (hexval(hex[0]) << 4) | hexval(hex[1]); + if (val & ~0xff) + return -1; + *sha1++ = val; + hex += 2; + } + return 0; +} + +int main(int argc, char **argv) +{ + /* oversized so we can read the whole buffer in */ + static unsigned char buf[25 * 1024 * 1024]; + char header[32]; + int header_len; + unsigned char have[20], want[20]; + int start, len; + SHA_CTX orig; + unsigned i, j; + + if (!argv[1] || get_sha1_hex(argv[1], want)) { + fprintf(stderr, "usage: sha1-munge <sha1> [start] <file.in\n"); + return 1; + } + + if (argv[2]) + start = atoi(argv[2]); + else + start = 0; + + len = read(0, buf, sizeof(buf)); + header_len = sprintf(header, "blob %d", len) + 1; + fprintf(stderr, "using header: %s\n", header); + + /* + * We keep a running sha1 so that if you are munging + * near the end of the file, we do not have to re-sha1 + * the unchanged earlier bytes + */ + SHA1_Init(&orig); + SHA1_Update(&orig, header, header_len); + if (start) + SHA1_Update(&orig, buf, start); + + signal(SIGALRM, progress); + alarm(1); + + for (i = start; i < len; i++) { + unsigned char c; + SHA_CTX x; + +#if 0 + /* + * deletion -- this would not actually work in practice, + * I think, because we've already committed to a + * particular size in the header. Ditto for addition + * below. In those cases, you'd have to do the whole + * sha1 from scratch, or possibly keep three running + * "orig" sha1 computations going. + */ + memcpy(&x, &orig, sizeof(x)); + SHA1_Update(&x, buf + i + 1, len - i - 1); + SHA1_Final(have, &x); + if (!memcmp(have, want, 20)) + printf("i=%d, deletion\n", i); +#endif + + /* + * replacement -- note that this tries each of the 256 + * possible bytes. If you suspect a single-bit flip, + * it would be much shorter to just try the 8 + * bit-flipped variants. + */ + c = buf[i]; + for (j = 0; j <= 0xff; j++) { + buf[i] = j; + + memcpy(&x, &orig, sizeof(x)); + SHA1_Update(&x, buf + i, len - i); + SHA1_Final(have, &x); + if (!memcmp(have, want, 20)) + printf("i=%d, j=%02x\n", i, j); + } + buf[i] = c; + +#if 0 + /* addition */ + for (j = 0; j <= 0xff; j++) { + unsigned char extra = j; + memcpy(&x, &orig, sizeof(x)); + SHA1_Update(&x, &extra, 1); + SHA1_Update(&x, buf + i, len - i); + SHA1_Final(have, &x); + if (!memcmp(have, want, 20)) + printf("i=%d, addition=%02x", i, j); + } +#endif + + SHA1_Update(&orig, buf + i, 1); + counter++; + } + + alarm(0); + fprintf(stderr, "\r%d\n", counter); + return 0; +} +-------------------------- diff --git a/Documentation/howto/revert-a-faulty-merge.txt b/Documentation/howto/revert-a-faulty-merge.txt index 462255ed5d..19f59cc888 100644 --- a/Documentation/howto/revert-a-faulty-merge.txt +++ b/Documentation/howto/revert-a-faulty-merge.txt @@ -30,7 +30,7 @@ The history immediately after the "revert of the merge" would look like this: ---o---o---o---M---x---x---W - / + / ---A---B where A and B are on the side development that was not so good, M is the @@ -47,7 +47,7 @@ After the developers of the side branch fix their mistakes, the history may look like this: ---o---o---o---M---x---x---W---x - / + / ---A---B-------------------C---D where C and D are to fix what was broken in A and B, and you may already @@ -81,7 +81,7 @@ In such a situation, you would want to first revert the previous revert, which would make the history look like this: ---o---o---o---M---x---x---W---x---Y - / + / ---A---B-------------------C---D where Y is the revert of W. Such a "revert of the revert" can be done @@ -93,14 +93,14 @@ This history would (ignoring possible conflicts between what W and W..Y changed) be equivalent to not having W or Y at all in the history: ---o---o---o---M---x---x-------x---- - / + / ---A---B-------------------C---D and merging the side branch again will not have conflict arising from an earlier revert and revert of the revert. ---o---o---o---M---x---x-------x-------* - / / + / / ---A---B-------------------C---D Of course the changes made in C and D still can conflict with what was @@ -111,13 +111,13 @@ faulty A and B, and redone the changes on top of the updated mainline after the revert, the history would have looked like this: ---o---o---o---M---x---x---W---x---x - / \ + / \ ---A---B A'--B'--C' If you reverted the revert in such a case as in the previous example: ---o---o---o---M---x---x---W---x---x---Y---* - / \ / + / \ / ---A---B A'--B'--C' where Y is the revert of W, A' and B' are rerolled A and B, and there may @@ -129,7 +129,7 @@ lot of overlapping changes that result in conflicts. So do not do "revert of revert" blindly without thinking.. ---o---o---o---M---x---x---W---x---x - / \ + / \ ---A---B A'--B'--C' In the history with rebased side branch, W (and M) are behind the merge |