diff options
Diffstat (limited to 'read-cache.c')
| -rw-r--r-- | read-cache.c | 1201 |
1 files changed, 968 insertions, 233 deletions
diff --git a/read-cache.c b/read-cache.c index 8b1c94e0e3..2357afaa60 100644 --- a/read-cache.c +++ b/read-cache.c @@ -8,6 +8,14 @@ #include "cache-tree.h" #include "refs.h" #include "dir.h" +#include "tree.h" +#include "commit.h" +#include "blob.h" +#include "resolve-undo.h" +#include "strbuf.h" +#include "varint.h" + +static struct cache_entry *refresh_cache_entry(struct cache_entry *ce, int really); /* Index extensions. * @@ -20,9 +28,41 @@ #define CACHE_EXT(s) ( (s[0]<<24)|(s[1]<<16)|(s[2]<<8)|(s[3]) ) #define CACHE_EXT_TREE 0x54524545 /* "TREE" */ +#define CACHE_EXT_RESOLVE_UNDO 0x52455543 /* "REUC" */ struct index_state the_index; +static void set_index_entry(struct index_state *istate, int nr, struct cache_entry *ce) +{ + istate->cache[nr] = ce; + add_name_hash(istate, ce); +} + +static void replace_index_entry(struct index_state *istate, int nr, struct cache_entry *ce) +{ + struct cache_entry *old = istate->cache[nr]; + + remove_name_hash(old); + set_index_entry(istate, nr, ce); + istate->cache_changed = 1; +} + +void rename_index_entry_at(struct index_state *istate, int nr, const char *new_name) +{ + struct cache_entry *old = istate->cache[nr], *new; + int namelen = strlen(new_name); + + new = xmalloc(cache_entry_size(namelen)); + copy_cache_entry(new, old); + new->ce_flags &= ~(CE_STATE_MASK | CE_NAMEMASK); + new->ce_flags |= (namelen >= CE_NAMEMASK ? CE_NAMEMASK : namelen); + memcpy(new->name, new_name, namelen + 1); + + cache_tree_invalidate_path(istate->cache_tree, old->name); + remove_index_entry_at(istate, nr); + add_index_entry(istate, new, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE); +} + /* * This only updates the "non-critical" parts of the directory * cache, ie the parts that aren't tracked by GIT, and only used @@ -30,20 +70,21 @@ struct index_state the_index; */ void fill_stat_cache_info(struct cache_entry *ce, struct stat *st) { - ce->ce_ctime.sec = htonl(st->st_ctime); - ce->ce_mtime.sec = htonl(st->st_mtime); -#ifdef USE_NSEC - ce->ce_ctime.nsec = htonl(st->st_ctim.tv_nsec); - ce->ce_mtime.nsec = htonl(st->st_mtim.tv_nsec); -#endif - ce->ce_dev = htonl(st->st_dev); - ce->ce_ino = htonl(st->st_ino); - ce->ce_uid = htonl(st->st_uid); - ce->ce_gid = htonl(st->st_gid); - ce->ce_size = htonl(st->st_size); + ce->ce_ctime.sec = (unsigned int)st->st_ctime; + ce->ce_mtime.sec = (unsigned int)st->st_mtime; + ce->ce_ctime.nsec = ST_CTIME_NSEC(*st); + ce->ce_mtime.nsec = ST_MTIME_NSEC(*st); + ce->ce_dev = st->st_dev; + ce->ce_ino = st->st_ino; + ce->ce_uid = st->st_uid; + ce->ce_gid = st->st_gid; + ce->ce_size = st->st_size; if (assume_unchanged) - ce->ce_flags |= htons(CE_VALID); + ce->ce_flags |= CE_VALID; + + if (S_ISREG(st->st_mode)) + ce_mark_uptodate(ce); } static int ce_compare_data(struct cache_entry *ce, struct stat *st) @@ -53,7 +94,7 @@ static int ce_compare_data(struct cache_entry *ce, struct stat *st) if (fd >= 0) { unsigned char sha1[20]; - if (!index_fd(sha1, fd, st, 0, OBJ_BLOB, ce->name)) + if (!index_fd(sha1, fd, st, OBJ_BLOB, ce->name, 0)) match = hashcmp(sha1, ce->sha1); /* index_fd() closed the file descriptor already */ } @@ -63,27 +104,21 @@ static int ce_compare_data(struct cache_entry *ce, struct stat *st) static int ce_compare_link(struct cache_entry *ce, size_t expected_size) { int match = -1; - char *target; void *buffer; unsigned long size; enum object_type type; - int len; + struct strbuf sb = STRBUF_INIT; - target = xmalloc(expected_size); - len = readlink(ce->name, target, expected_size); - if (len != expected_size) { - free(target); + if (strbuf_readlink(&sb, ce->name, expected_size)) return -1; - } + buffer = read_sha1_file(ce->sha1, &type, &size); - if (!buffer) { - free(target); - return -1; + if (buffer) { + if (size == sb.len) + match = memcmp(buffer, sb.buf, size); + free(buffer); } - if (size == expected_size) - match = memcmp(buffer, target, size); - free(buffer); - free(target); + strbuf_release(&sb); return match; } @@ -116,8 +151,8 @@ static int ce_modified_check_fs(struct cache_entry *ce, struct stat *st) return DATA_CHANGED; break; case S_IFDIR: - if (S_ISGITLINK(ntohl(ce->ce_mode))) - return 0; + if (S_ISGITLINK(ce->ce_mode)) + return ce_compare_gitlink(ce) ? DATA_CHANGED : 0; default: return TYPE_CHANGED; } @@ -128,14 +163,17 @@ static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st) { unsigned int changed = 0; - switch (ntohl(ce->ce_mode) & S_IFMT) { + if (ce->ce_flags & CE_REMOVE) + return MODE_CHANGED | DATA_CHANGED | TYPE_CHANGED; + + switch (ce->ce_mode & S_IFMT) { case S_IFREG: changed |= !S_ISREG(st->st_mode) ? TYPE_CHANGED : 0; /* We consider only the owner x bit to be relevant for * "mode changes" */ if (trust_executable_bit && - (0100 & (ntohl(ce->ce_mode) ^ st->st_mode))) + (0100 & (ce->ce_mode ^ st->st_mode))) changed |= MODE_CHANGED; break; case S_IFLNK: @@ -144,35 +182,31 @@ static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st) changed |= TYPE_CHANGED; break; case S_IFGITLINK: + /* We ignore most of the st_xxx fields for gitlinks */ if (!S_ISDIR(st->st_mode)) changed |= TYPE_CHANGED; else if (ce_compare_gitlink(ce)) changed |= DATA_CHANGED; return changed; default: - die("internal error: ce_mode is %o", ntohl(ce->ce_mode)); + die("internal error: ce_mode is %o", ce->ce_mode); } - if (ce->ce_mtime.sec != htonl(st->st_mtime)) + if (ce->ce_mtime.sec != (unsigned int)st->st_mtime) changed |= MTIME_CHANGED; - if (ce->ce_ctime.sec != htonl(st->st_ctime)) + if (trust_ctime && ce->ce_ctime.sec != (unsigned int)st->st_ctime) changed |= CTIME_CHANGED; #ifdef USE_NSEC - /* - * nsec seems unreliable - not all filesystems support it, so - * as long as it is in the inode cache you get right nsec - * but after it gets flushed, you get zero nsec. - */ - if (ce->ce_mtime.nsec != htonl(st->st_mtim.tv_nsec)) + if (ce->ce_mtime.nsec != ST_MTIME_NSEC(*st)) changed |= MTIME_CHANGED; - if (ce->ce_ctime.nsec != htonl(st->st_ctim.tv_nsec)) + if (trust_ctime && ce->ce_ctime.nsec != ST_CTIME_NSEC(*st)) changed |= CTIME_CHANGED; #endif - if (ce->ce_uid != htonl(st->st_uid) || - ce->ce_gid != htonl(st->st_gid)) + if (ce->ce_uid != (unsigned int) st->st_uid || + ce->ce_gid != (unsigned int) st->st_gid) changed |= OWNER_CHANGED; - if (ce->ce_ino != htonl(st->st_ino)) + if (ce->ce_ino != (unsigned int) st->st_ino) changed |= INODE_CHANGED; #ifdef USE_STDEV @@ -181,30 +215,65 @@ static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st) * clients will have different views of what "device" * the filesystem is on */ - if (ce->ce_dev != htonl(st->st_dev)) + if (ce->ce_dev != (unsigned int) st->st_dev) changed |= INODE_CHANGED; #endif - if (ce->ce_size != htonl(st->st_size)) + if (ce->ce_size != (unsigned int) st->st_size) changed |= DATA_CHANGED; + /* Racily smudged entry? */ + if (!ce->ce_size) { + if (!is_empty_blob_sha1(ce->sha1)) + changed |= DATA_CHANGED; + } + return changed; } -int ie_match_stat(struct index_state *istate, - struct cache_entry *ce, struct stat *st, int options) +static int is_racy_timestamp(const struct index_state *istate, struct cache_entry *ce) +{ + return (!S_ISGITLINK(ce->ce_mode) && + istate->timestamp.sec && +#ifdef USE_NSEC + /* nanosecond timestamped files can also be racy! */ + (istate->timestamp.sec < ce->ce_mtime.sec || + (istate->timestamp.sec == ce->ce_mtime.sec && + istate->timestamp.nsec <= ce->ce_mtime.nsec)) +#else + istate->timestamp.sec <= ce->ce_mtime.sec +#endif + ); +} + +int ie_match_stat(const struct index_state *istate, + struct cache_entry *ce, struct stat *st, + unsigned int options) { unsigned int changed; - int ignore_valid = options & 01; - int assume_racy_is_modified = options & 02; + int ignore_valid = options & CE_MATCH_IGNORE_VALID; + int ignore_skip_worktree = options & CE_MATCH_IGNORE_SKIP_WORKTREE; + int assume_racy_is_modified = options & CE_MATCH_RACY_IS_DIRTY; /* * If it's marked as always valid in the index, it's * valid whatever the checked-out copy says. + * + * skip-worktree has the same effect with higher precedence */ - if (!ignore_valid && (ce->ce_flags & htons(CE_VALID))) + if (!ignore_skip_worktree && ce_skip_worktree(ce)) + return 0; + if (!ignore_valid && (ce->ce_flags & CE_VALID)) return 0; + /* + * Intent-to-add entries have not been added, so the index entry + * by definition never matches what is in the work tree until it + * actually gets added. + */ + if (ce->ce_flags & CE_INTENT_TO_ADD) + return DATA_CHANGED | TYPE_CHANGED | MODE_CHANGED; + changed = ce_match_stat_basic(ce, st); /* @@ -223,9 +292,7 @@ int ie_match_stat(struct index_state *istate, * whose mtime are the same as the index file timestamp more * carefully than others. */ - if (!changed && - istate->timestamp && - istate->timestamp <= ntohl(ce->ce_mtime.sec)) { + if (!changed && is_racy_timestamp(istate, ce)) { if (assume_racy_is_modified) changed |= DATA_CHANGED; else @@ -235,11 +302,12 @@ int ie_match_stat(struct index_state *istate, return changed; } -int ie_modified(struct index_state *istate, - struct cache_entry *ce, struct stat *st, int really) +int ie_modified(const struct index_state *istate, + struct cache_entry *ce, struct stat *st, unsigned int options) { int changed, changed_fs; - changed = ie_match_stat(istate, ce, st, really); + + changed = ie_match_stat(istate, ce, st, options); if (!changed) return 0; /* @@ -249,11 +317,22 @@ int ie_modified(struct index_state *istate, if (changed & (MODE_CHANGED | TYPE_CHANGED)) return changed; - /* Immediately after read-tree or update-index --cacheinfo, - * the length field is zero. For other cases the ce_size - * should match the SHA1 recorded in the index entry. + /* + * Immediately after read-tree or update-index --cacheinfo, + * the length field is zero, as we have never even read the + * lstat(2) information once, and we cannot trust DATA_CHANGED + * returned by ie_match_stat() which in turn was returned by + * ce_match_stat_basic() to signal that the filesize of the + * blob changed. We have to actually go to the filesystem to + * see if the contents match, and if so, should answer "unchanged". + * + * The logic does not apply to gitlinks, as ce_match_stat_basic() + * already has checked the actual HEAD from the filesystem in the + * subproject. If ie_match_stat() already said it is different, + * then we know it is. */ - if ((changed & DATA_CHANGED) && ce->ce_size != htonl(0)) + if ((changed & DATA_CHANGED) && + (S_ISGITLINK(ce->ce_mode) || ce->ce_size != 0)) return changed; changed_fs = ce_modified_check_fs(ce, st); @@ -281,12 +360,52 @@ int base_name_compare(const char *name1, int len1, int mode1, return (c1 < c2) ? -1 : (c1 > c2) ? 1 : 0; } +/* + * df_name_compare() is identical to base_name_compare(), except it + * compares conflicting directory/file entries as equal. Note that + * while a directory name compares as equal to a regular file, they + * then individually compare _differently_ to a filename that has + * a dot after the basename (because '\0' < '.' < '/'). + * + * This is used by routines that want to traverse the git namespace + * but then handle conflicting entries together when possible. + */ +int df_name_compare(const char *name1, int len1, int mode1, + const char *name2, int len2, int mode2) +{ + int len = len1 < len2 ? len1 : len2, cmp; + unsigned char c1, c2; + + cmp = memcmp(name1, name2, len); + if (cmp) + return cmp; + /* Directories and files compare equal (same length, same name) */ + if (len1 == len2) + return 0; + c1 = name1[len]; + if (!c1 && S_ISDIR(mode1)) + c1 = '/'; + c2 = name2[len]; + if (!c2 && S_ISDIR(mode2)) + c2 = '/'; + if (c1 == '/' && !c2) + return 0; + if (c2 == '/' && !c1) + return 0; + return c1 - c2; +} + int cache_name_compare(const char *name1, int flags1, const char *name2, int flags2) { - int len1 = flags1 & CE_NAMEMASK; - int len2 = flags2 & CE_NAMEMASK; - int len = len1 < len2 ? len1 : len2; - int cmp; + int len1, len2, len, cmp; + + len1 = flags1 & CE_NAMEMASK; + if (CE_NAMEMASK <= len1) + len1 = strlen(name1 + CE_NAMEMASK) + CE_NAMEMASK; + len2 = flags2 & CE_NAMEMASK; + if (CE_NAMEMASK <= len2) + len2 = strlen(name2 + CE_NAMEMASK) + CE_NAMEMASK; + len = len1 < len2 ? len1 : len2; cmp = memcmp(name1, name2, len); if (cmp) @@ -307,7 +426,7 @@ int cache_name_compare(const char *name1, int flags1, const char *name2, int fla return 0; } -int index_name_pos(struct index_state *istate, const char *name, int namelen) +int index_name_pos(const struct index_state *istate, const char *name, int namelen) { int first, last; @@ -316,7 +435,7 @@ int index_name_pos(struct index_state *istate, const char *name, int namelen) while (last > first) { int next = (last + first) >> 1; struct cache_entry *ce = istate->cache[next]; - int cmp = cache_name_compare(name, namelen, ce->name, ntohs(ce->ce_flags)); + int cmp = cache_name_compare(name, namelen, ce->name, ce->ce_flags); if (!cmp) return next; if (cmp < 0) { @@ -331,6 +450,10 @@ int index_name_pos(struct index_state *istate, const char *name, int namelen) /* Remove entry, return true if there are more entries to go.. */ int remove_index_entry_at(struct index_state *istate, int pos) { + struct cache_entry *ce = istate->cache[pos]; + + record_resolve_undo(istate, ce); + remove_name_hash(ce); istate->cache_changed = 1; istate->cache_nr--; if (pos >= istate->cache_nr) @@ -341,11 +464,32 @@ int remove_index_entry_at(struct index_state *istate, int pos) return 1; } +/* + * Remove all cache ententries marked for removal, that is where + * CE_REMOVE is set in ce_flags. This is much more effective than + * calling remove_index_entry_at() for each entry to be removed. + */ +void remove_marked_cache_entries(struct index_state *istate) +{ + struct cache_entry **ce_array = istate->cache; + unsigned int i, j; + + for (i = j = 0; i < istate->cache_nr; i++) { + if (ce_array[i]->ce_flags & CE_REMOVE) + remove_name_hash(ce_array[i]); + else + ce_array[j++] = ce_array[i]; + } + istate->cache_changed = 1; + istate->cache_nr = j; +} + int remove_file_from_index(struct index_state *istate, const char *path) { int pos = index_name_pos(istate, path, strlen(path)); if (pos < 0) pos = -pos-1; + cache_tree_invalidate_path(istate->cache_tree, path); while (pos < istate->cache_nr && !strcmp(istate->cache[pos]->name, path)) remove_index_entry_at(istate, pos); return 0; @@ -379,31 +523,77 @@ static int index_name_pos_also_unmerged(struct index_state *istate, return pos; } -int add_file_to_index(struct index_state *istate, const char *path, int verbose) +static int different_name(struct cache_entry *ce, struct cache_entry *alias) { - int size, namelen, pos; - struct stat st; - struct cache_entry *ce; + int len = ce_namelen(ce); + return ce_namelen(alias) != len || memcmp(ce->name, alias->name, len); +} - if (lstat(path, &st)) - die("%s: unable to stat (%s)", path, strerror(errno)); +/* + * If we add a filename that aliases in the cache, we will use the + * name that we already have - but we don't want to update the same + * alias twice, because that implies that there were actually two + * different files with aliasing names! + * + * So we use the CE_ADDED flag to verify that the alias was an old + * one before we accept it as + */ +static struct cache_entry *create_alias_ce(struct cache_entry *ce, struct cache_entry *alias) +{ + int len; + struct cache_entry *new; + + if (alias->ce_flags & CE_ADDED) + die("Will not add file alias '%s' ('%s' already exists in index)", ce->name, alias->name); + + /* Ok, create the new entry using the name of the existing alias */ + len = ce_namelen(alias); + new = xcalloc(1, cache_entry_size(len)); + memcpy(new->name, alias->name, len); + copy_cache_entry(new, ce); + free(ce); + return new; +} - if (!S_ISREG(st.st_mode) && !S_ISLNK(st.st_mode) && !S_ISDIR(st.st_mode)) - die("%s: can only add regular files, symbolic links or git-directories", path); +static void record_intent_to_add(struct cache_entry *ce) +{ + unsigned char sha1[20]; + if (write_sha1_file("", 0, blob_type, sha1)) + die("cannot create an empty blob in the object database"); + hashcpy(ce->sha1, sha1); +} + +int add_to_index(struct index_state *istate, const char *path, struct stat *st, int flags) +{ + int size, namelen, was_same; + mode_t st_mode = st->st_mode; + struct cache_entry *ce, *alias; + unsigned ce_option = CE_MATCH_IGNORE_VALID|CE_MATCH_IGNORE_SKIP_WORKTREE|CE_MATCH_RACY_IS_DIRTY; + int verbose = flags & (ADD_CACHE_VERBOSE | ADD_CACHE_PRETEND); + int pretend = flags & ADD_CACHE_PRETEND; + int intent_only = flags & ADD_CACHE_INTENT; + int add_option = (ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE| + (intent_only ? ADD_CACHE_NEW_ONLY : 0)); + + if (!S_ISREG(st_mode) && !S_ISLNK(st_mode) && !S_ISDIR(st_mode)) + return error("%s: can only add regular files, symbolic links or git-directories", path); namelen = strlen(path); - if (S_ISDIR(st.st_mode)) { + if (S_ISDIR(st_mode)) { while (namelen && path[namelen-1] == '/') namelen--; } size = cache_entry_size(namelen); ce = xcalloc(1, size); memcpy(ce->name, path, namelen); - ce->ce_flags = htons(namelen); - fill_stat_cache_info(ce, &st); + ce->ce_flags = namelen; + if (!intent_only) + fill_stat_cache_info(ce, st); + else + ce->ce_flags |= CE_INTENT_TO_ADD; if (trust_executable_bit && has_symlinks) - ce->ce_mode = create_ce_mode(st.st_mode); + ce->ce_mode = create_ce_mode(st_mode); else { /* If there is an existing entry, pick the mode bits and type * from it, otherwise assume unexecutable regular file. @@ -412,58 +602,110 @@ int add_file_to_index(struct index_state *istate, const char *path, int verbose) int pos = index_name_pos_also_unmerged(istate, path, namelen); ent = (0 <= pos) ? istate->cache[pos] : NULL; - ce->ce_mode = ce_mode_from_stat(ent, st.st_mode); + ce->ce_mode = ce_mode_from_stat(ent, st_mode); } - pos = index_name_pos(istate, ce->name, namelen); - if (0 <= pos && - !ce_stage(istate->cache[pos]) && - !ie_modified(istate, istate->cache[pos], &st, 1)) { + /* When core.ignorecase=true, determine if a directory of the same name but differing + * case already exists within the Git repository. If it does, ensure the directory + * case of the file being added to the repository matches (is folded into) the existing + * entry's directory case. + */ + if (ignore_case) { + const char *startPtr = ce->name; + const char *ptr = startPtr; + while (*ptr) { + while (*ptr && *ptr != '/') + ++ptr; + if (*ptr == '/') { + struct cache_entry *foundce; + ++ptr; + foundce = index_name_exists(&the_index, ce->name, ptr - ce->name, ignore_case); + if (foundce) { + memcpy((void *)startPtr, foundce->name + (startPtr - ce->name), ptr - startPtr); + startPtr = ptr; + } + } + } + } + + alias = index_name_exists(istate, ce->name, ce_namelen(ce), ignore_case); + if (alias && !ce_stage(alias) && !ie_match_stat(istate, alias, st, ce_option)) { /* Nothing changed, really */ free(ce); + if (!S_ISGITLINK(alias->ce_mode)) + ce_mark_uptodate(alias); + alias->ce_flags |= CE_ADDED; return 0; } - - if (index_path(ce->sha1, path, &st, 1)) - die("unable to index file %s", path); - if (add_index_entry(istate, ce, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE)) - die("unable to add %s to index",path); - if (verbose) + if (!intent_only) { + if (index_path(ce->sha1, path, st, HASH_WRITE_OBJECT)) + return error("unable to index file %s", path); + } else + record_intent_to_add(ce); + + if (ignore_case && alias && different_name(ce, alias)) + ce = create_alias_ce(ce, alias); + ce->ce_flags |= CE_ADDED; + + /* It was suspected to be racily clean, but it turns out to be Ok */ + was_same = (alias && + !ce_stage(alias) && + !hashcmp(alias->sha1, ce->sha1) && + ce->ce_mode == alias->ce_mode); + + if (pretend) + ; + else if (add_index_entry(istate, ce, add_option)) + return error("unable to add %s to index",path); + if (verbose && !was_same) printf("add '%s'\n", path); - cache_tree_invalidate_path(istate->cache_tree, path); return 0; } +int add_file_to_index(struct index_state *istate, const char *path, int flags) +{ + struct stat st; + if (lstat(path, &st)) + die_errno("unable to stat '%s'", path); + return add_to_index(istate, path, &st, flags); +} + +struct cache_entry *make_cache_entry(unsigned int mode, + const unsigned char *sha1, const char *path, int stage, + int refresh) +{ + int size, len; + struct cache_entry *ce; + + if (!verify_path(path)) { + error("Invalid path '%s'", path); + return NULL; + } + + len = strlen(path); + size = cache_entry_size(len); + ce = xcalloc(1, size); + + hashcpy(ce->sha1, sha1); + memcpy(ce->name, path, len); + ce->ce_flags = create_ce_flags(len, stage); + ce->ce_mode = create_ce_mode(mode); + + if (refresh) + return refresh_cache_entry(ce, 0); + + return ce; +} + int ce_same_name(struct cache_entry *a, struct cache_entry *b) { int len = ce_namelen(a); return ce_namelen(b) == len && !memcmp(a->name, b->name, len); } -int ce_path_match(const struct cache_entry *ce, const char **pathspec) +int ce_path_match(const struct cache_entry *ce, const struct pathspec *pathspec) { - const char *match, *name; - int len; - - if (!pathspec) - return 1; - - len = ce_namelen(ce); - name = ce->name; - while ((match = *pathspec++) != NULL) { - int matchlen = strlen(match); - if (matchlen > len) - continue; - if (memcmp(name, match, matchlen)) - continue; - if (matchlen && name[matchlen-1] == '/') - return 1; - if (name[matchlen] == '/' || !name[matchlen]) - return 1; - if (!matchlen) - return 1; - } - return 0; + return match_pathspec_depth(pathspec, ce->name, ce_namelen(ce), 0, NULL); } /* @@ -481,11 +723,12 @@ static int verify_dotfile(const char *rest) * has already been discarded, we now test * the rest. */ - switch (*rest) { + /* "." is not allowed */ - case '\0': case '/': + if (*rest == '\0' || is_dir_sep(*rest)) return 0; + switch (*rest) { /* * ".git" followed by NUL or slash is bad. This * shares the path end test with the ".." case. @@ -498,7 +741,7 @@ static int verify_dotfile(const char *rest) rest += 2; /* fallthrough */ case '.': - if (rest[1] == '\0' || rest[1] == '/') + if (rest[1] == '\0' || is_dir_sep(rest[1])) return 0; } return 1; @@ -508,23 +751,19 @@ int verify_path(const char *path) { char c; + if (has_dos_drive_prefix(path)) + return 0; + goto inside; for (;;) { if (!c) return 1; - if (c == '/') { + if (is_dir_sep(c)) { inside: c = *path++; - switch (c) { - default: - continue; - case '/': case '\0': - break; - case '.': - if (verify_dotfile(path)) - continue; - } - return 0; + if ((c == '.' && !verify_dotfile(path)) || + is_dir_sep(c) || c == '\0') + return 0; } c = *path++; } @@ -553,7 +792,7 @@ static int has_file_name(struct index_state *istate, continue; if (p->name[len] != '/') continue; - if (!ce_stage(p) && !p->ce_mode) + if (p->ce_flags & CE_REMOVE) continue; retval = -1; if (!ok_to_replace) @@ -586,7 +825,7 @@ static int has_dir_name(struct index_state *istate, } len = slash - name; - pos = index_name_pos(istate, name, ntohs(create_ce_flags(len, stage))); + pos = index_name_pos(istate, name, create_ce_flags(len, stage)); if (pos >= 0) { /* * Found one, but not so fast. This could @@ -596,7 +835,7 @@ static int has_dir_name(struct index_state *istate, * it is Ok to have a directory at the same * path. */ - if (stage || istate->cache[pos]->ce_mode) { + if (!(istate->cache[pos]->ce_flags & CE_REMOVE)) { retval = -1; if (!ok_to_replace) break; @@ -618,8 +857,9 @@ static int has_dir_name(struct index_state *istate, (p->name[len] != '/') || memcmp(p->name, name, len)) break; /* not our subdirectory */ - if (ce_stage(p) == stage && (stage || p->ce_mode)) - /* p is at the same stage as our entry, and + if (ce_stage(p) == stage && !(p->ce_flags & CE_REMOVE)) + /* + * p is at the same stage as our entry, and * is a subdirectory of what we are looking * at, so we cannot have conflicts at our * level or anything shorter. @@ -649,7 +889,7 @@ static int check_file_directory_conflict(struct index_state *istate, /* * When ce is an "I am going away" entry, we allow it to be added */ - if (!ce_stage(ce) && !ce->ce_mode) + if (ce->ce_flags & CE_REMOVE) return 0; /* @@ -672,13 +912,15 @@ static int add_index_entry_with_check(struct index_state *istate, struct cache_e int ok_to_add = option & ADD_CACHE_OK_TO_ADD; int ok_to_replace = option & ADD_CACHE_OK_TO_REPLACE; int skip_df_check = option & ADD_CACHE_SKIP_DFCHECK; + int new_only = option & ADD_CACHE_NEW_ONLY; - pos = index_name_pos(istate, ce->name, ntohs(ce->ce_flags)); + cache_tree_invalidate_path(istate->cache_tree, ce->name); + pos = index_name_pos(istate, ce->name, ce->ce_flags); /* existing match? Just replace it. */ if (pos >= 0) { - istate->cache_changed = 1; - istate->cache[pos] = ce; + if (!new_only) + replace_index_entry(istate, pos, ce); return 0; } pos = -pos-1; @@ -698,14 +940,14 @@ static int add_index_entry_with_check(struct index_state *istate, struct cache_e if (!ok_to_add) return -1; if (!verify_path(ce->name)) - return -1; + return error("Invalid path '%s'", ce->name); if (!skip_df_check && check_file_directory_conflict(istate, ce, pos, ok_to_replace)) { if (!ok_to_replace) return error("'%s' appears as both a file and as a directory", ce->name); - pos = index_name_pos(istate, ce->name, ntohs(ce->ce_flags)); + pos = index_name_pos(istate, ce->name, ce->ce_flags); pos = -pos-1; } return pos + 1; @@ -738,7 +980,7 @@ int add_index_entry(struct index_state *istate, struct cache_entry *ce, int opti memmove(istate->cache + pos + 1, istate->cache + pos, (istate->cache_nr - pos - 1) * sizeof(ce)); - istate->cache[pos] = ce; + set_index_entry(istate, pos, ce); istate->cache_changed = 1; return 0; } @@ -755,11 +997,32 @@ int add_index_entry(struct index_state *istate, struct cache_entry *ce, int opti * to link up the stat cache details with the proper files. */ static struct cache_entry *refresh_cache_ent(struct index_state *istate, - struct cache_entry *ce, int really, int *err) + struct cache_entry *ce, + unsigned int options, int *err, + int *changed_ret) { struct stat st; struct cache_entry *updated; int changed, size; + int ignore_valid = options & CE_MATCH_IGNORE_VALID; + int ignore_skip_worktree = options & CE_MATCH_IGNORE_SKIP_WORKTREE; + + if (ce_uptodate(ce)) + return ce; + + /* + * CE_VALID or CE_SKIP_WORKTREE means the user promised us + * that the change to the work tree does not matter and told + * us not to worry. + */ + if (!ignore_skip_worktree && ce_skip_worktree(ce)) { + ce_mark_uptodate(ce); + return ce; + } + if (!ignore_valid && (ce->ce_flags & CE_VALID)) { + ce_mark_uptodate(ce); + return ce; + } if (lstat(ce->name, &st) < 0) { if (err) @@ -767,16 +1030,33 @@ static struct cache_entry *refresh_cache_ent(struct index_state *istate, return NULL; } - changed = ie_match_stat(istate, ce, &st, really); + changed = ie_match_stat(istate, ce, &st, options); + if (changed_ret) + *changed_ret = changed; if (!changed) { - if (really && assume_unchanged && - !(ce->ce_flags & htons(CE_VALID))) + /* + * The path is unchanged. If we were told to ignore + * valid bit, then we did the actual stat check and + * found that the entry is unmodified. If the entry + * is not marked VALID, this is the place to mark it + * valid again, under "assume unchanged" mode. + */ + if (ignore_valid && assume_unchanged && + !(ce->ce_flags & CE_VALID)) ; /* mark this one VALID again */ - else + else { + /* + * We do not mark the index itself "modified" + * because CE_UPTODATE flag is in-core only; + * we are not going to write this change out. + */ + if (!S_ISGITLINK(ce->ce_mode)) + ce_mark_uptodate(ce); return ce; + } } - if (ie_modified(istate, ce, &st, really)) { + if (ie_modified(istate, ce, &st, options)) { if (err) *err = EINVAL; return NULL; @@ -786,20 +1066,31 @@ static struct cache_entry *refresh_cache_ent(struct index_state *istate, updated = xmalloc(size); memcpy(updated, ce, size); fill_stat_cache_info(updated, &st); - - /* In this case, if really is not set, we should leave - * CE_VALID bit alone. Otherwise, paths marked with - * --no-assume-unchanged (i.e. things to be edited) will - * reacquire CE_VALID bit automatically, which is not - * really what we want. + /* + * If ignore_valid is not set, we should leave CE_VALID bit + * alone. Otherwise, paths marked with --no-assume-unchanged + * (i.e. things to be edited) will reacquire CE_VALID bit + * automatically, which is not really what we want. */ - if (!really && assume_unchanged && !(ce->ce_flags & htons(CE_VALID))) - updated->ce_flags &= ~htons(CE_VALID); + if (!ignore_valid && assume_unchanged && + !(ce->ce_flags & CE_VALID)) + updated->ce_flags &= ~CE_VALID; return updated; } -int refresh_index(struct index_state *istate, unsigned int flags, const char **pathspec, char *seen) +static void show_file(const char * fmt, const char * name, int in_porcelain, + int * first, const char *header_msg) +{ + if (in_porcelain && *first && header_msg) { + printf("%s\n", header_msg); + *first = 0; + } + printf(fmt, name); +} + +int refresh_index(struct index_state *istate, unsigned int flags, const char **pathspec, + char *seen, const char *header_msg) { int i; int has_errors = 0; @@ -807,12 +1098,35 @@ int refresh_index(struct index_state *istate, unsigned int flags, const char **p int allow_unmerged = (flags & REFRESH_UNMERGED) != 0; int quiet = (flags & REFRESH_QUIET) != 0; int not_new = (flags & REFRESH_IGNORE_MISSING) != 0; - + int ignore_submodules = (flags & REFRESH_IGNORE_SUBMODULES) != 0; + int first = 1; + int in_porcelain = (flags & REFRESH_IN_PORCELAIN); + unsigned int options = really ? CE_MATCH_IGNORE_VALID : 0; + const char *modified_fmt; + const char *deleted_fmt; + const char *typechange_fmt; + const char *added_fmt; + const char *unmerged_fmt; + + modified_fmt = (in_porcelain ? "M\t%s\n" : "%s: needs update\n"); + deleted_fmt = (in_porcelain ? "D\t%s\n" : "%s: needs update\n"); + typechange_fmt = (in_porcelain ? "T\t%s\n" : "%s needs update\n"); + added_fmt = (in_porcelain ? "A\t%s\n" : "%s needs update\n"); + unmerged_fmt = (in_porcelain ? "U\t%s\n" : "%s: needs merge\n"); for (i = 0; i < istate->cache_nr; i++) { struct cache_entry *ce, *new; int cache_errno = 0; + int changed = 0; + int filtered = 0; ce = istate->cache[i]; + if (ignore_submodules && S_ISGITLINK(ce->ce_mode)) + continue; + + if (pathspec && + !match_pathspec(pathspec, ce->name, ce_namelen(ce), 0, seen)) + filtered = 1; + if (ce_stage(ce)) { while ((i < istate->cache_nr) && ! strcmp(istate->cache[i]->name, ce->name)) @@ -820,59 +1134,129 @@ int refresh_index(struct index_state *istate, unsigned int flags, const char **p i--; if (allow_unmerged) continue; - printf("%s: needs merge\n", ce->name); + if (!filtered) + show_file(unmerged_fmt, ce->name, in_porcelain, + &first, header_msg); has_errors = 1; continue; } - if (pathspec && !match_pathspec(pathspec, ce->name, strlen(ce->name), 0, seen)) + if (filtered) continue; - new = refresh_cache_ent(istate, ce, really, &cache_errno); + new = refresh_cache_ent(istate, ce, options, &cache_errno, &changed); if (new == ce) continue; if (!new) { + const char *fmt; + if (not_new && cache_errno == ENOENT) continue; if (really && cache_errno == EINVAL) { /* If we are doing --really-refresh that * means the index is not valid anymore. */ - ce->ce_flags &= ~htons(CE_VALID); + ce->ce_flags &= ~CE_VALID; istate->cache_changed = 1; } if (quiet) continue; - printf("%s: needs update\n", ce->name); + + if (cache_errno == ENOENT) + fmt = deleted_fmt; + else if (ce->ce_flags & CE_INTENT_TO_ADD) + fmt = added_fmt; /* must be before other checks */ + else if (changed & TYPE_CHANGED) + fmt = typechange_fmt; + else + fmt = modified_fmt; + show_file(fmt, + ce->name, in_porcelain, &first, header_msg); has_errors = 1; continue; } - istate->cache_changed = 1; - /* You can NOT just free istate->cache[i] here, since it - * might not be necessarily malloc()ed but can also come - * from mmap(). */ - istate->cache[i] = new; + + replace_index_entry(istate, i, new); } return has_errors; } -struct cache_entry *refresh_cache_entry(struct cache_entry *ce, int really) +static struct cache_entry *refresh_cache_entry(struct cache_entry *ce, int really) { - return refresh_cache_ent(&the_index, ce, really, NULL); + return refresh_cache_ent(&the_index, ce, really, NULL, NULL); } + +/***************************************************************** + * Index File I/O + *****************************************************************/ + +#define INDEX_FORMAT_DEFAULT 3 + +/* + * dev/ino/uid/gid/size are also just tracked to the low 32 bits + * Again - this is just a (very strong in practice) heuristic that + * the inode hasn't changed. + * + * We save the fields in big-endian order to allow using the + * index file over NFS transparently. + */ +struct ondisk_cache_entry { + struct cache_time ctime; + struct cache_time mtime; + unsigned int dev; + unsigned int ino; + unsigned int mode; + unsigned int uid; + unsigned int gid; + unsigned int size; + unsigned char sha1[20]; + unsigned short flags; + char name[FLEX_ARRAY]; /* more */ +}; + +/* + * This struct is used when CE_EXTENDED bit is 1 + * The struct must match ondisk_cache_entry exactly from + * ctime till flags + */ +struct ondisk_cache_entry_extended { + struct cache_time ctime; + struct cache_time mtime; + unsigned int dev; + unsigned int ino; + unsigned int mode; + unsigned int uid; + unsigned int gid; + unsigned int size; + unsigned char sha1[20]; + unsigned short flags; + unsigned short flags2; + char name[FLEX_ARRAY]; /* more */ +}; + +/* These are only used for v3 or lower */ +#define align_flex_name(STRUCT,len) ((offsetof(struct STRUCT,name) + (len) + 8) & ~7) +#define ondisk_cache_entry_size(len) align_flex_name(ondisk_cache_entry,len) +#define ondisk_cache_entry_extended_size(len) align_flex_name(ondisk_cache_entry_extended,len) +#define ondisk_ce_size(ce) (((ce)->ce_flags & CE_EXTENDED) ? \ + ondisk_cache_entry_extended_size(ce_namelen(ce)) : \ + ondisk_cache_entry_size(ce_namelen(ce))) + static int verify_hdr(struct cache_header *hdr, unsigned long size) { - SHA_CTX c; + git_SHA_CTX c; unsigned char sha1[20]; + int hdr_version; if (hdr->hdr_signature != htonl(CACHE_SIGNATURE)) return error("bad signature"); - if (hdr->hdr_version != htonl(2)) - return error("bad index version"); - SHA1_Init(&c); - SHA1_Update(&c, hdr, size - 20); - SHA1_Final(sha1, &c); + hdr_version = ntohl(hdr->hdr_version); + if (hdr_version < 2 || 4 < hdr_version) + return error("bad index version %d", hdr_version); + git_SHA1_Init(&c); + git_SHA1_Update(&c, hdr, size - 20); + git_SHA1_Final(sha1, &c); if (hashcmp(sha1, (unsigned char *)hdr + size - 20)) return error("bad index file sha1 signature"); return 0; @@ -885,6 +1269,9 @@ static int read_index_extension(struct index_state *istate, case CACHE_EXT_TREE: istate->cache_tree = cache_tree_read(data, sz); break; + case CACHE_EXT_RESOLVE_UNDO: + istate->resolve_undo = resolve_undo_read(data, sz); + break; default: if (*ext < 'A' || 'Z' < *ext) return error("index uses %.4s extension, which we do not understand", @@ -900,108 +1287,257 @@ int read_index(struct index_state *istate) return read_index_from(istate, get_index_file()); } +#ifndef NEEDS_ALIGNED_ACCESS +#define ntoh_s(var) ntohs(var) +#define ntoh_l(var) ntohl(var) +#else +static inline uint16_t ntoh_s_force_align(void *p) +{ + uint16_t x; + memcpy(&x, p, sizeof(x)); + return ntohs(x); +} +static inline uint32_t ntoh_l_force_align(void *p) +{ + uint32_t x; + memcpy(&x, p, sizeof(x)); + return ntohl(x); +} +#define ntoh_s(var) ntoh_s_force_align(&(var)) +#define ntoh_l(var) ntoh_l_force_align(&(var)) +#endif + +static struct cache_entry *cache_entry_from_ondisk(struct ondisk_cache_entry *ondisk, + unsigned int flags, + const char *name, + size_t len) +{ + struct cache_entry *ce = xmalloc(cache_entry_size(len)); + + ce->ce_ctime.sec = ntoh_l(ondisk->ctime.sec); + ce->ce_mtime.sec = ntoh_l(ondisk->mtime.sec); + ce->ce_ctime.nsec = ntoh_l(ondisk->ctime.nsec); + ce->ce_mtime.nsec = ntoh_l(ondisk->mtime.nsec); + ce->ce_dev = ntoh_l(ondisk->dev); + ce->ce_ino = ntoh_l(ondisk->ino); + ce->ce_mode = ntoh_l(ondisk->mode); + ce->ce_uid = ntoh_l(ondisk->uid); + ce->ce_gid = ntoh_l(ondisk->gid); + ce->ce_size = ntoh_l(ondisk->size); + ce->ce_flags = flags; + hashcpy(ce->sha1, ondisk->sha1); + memcpy(ce->name, name, len); + ce->name[len] = '\0'; + return ce; +} + +/* + * Adjacent cache entries tend to share the leading paths, so it makes + * sense to only store the differences in later entries. In the v4 + * on-disk format of the index, each on-disk cache entry stores the + * number of bytes to be stripped from the end of the previous name, + * and the bytes to append to the result, to come up with its name. + */ +static unsigned long expand_name_field(struct strbuf *name, const char *cp_) +{ + const unsigned char *ep, *cp = (const unsigned char *)cp_; + size_t len = decode_varint(&cp); + + if (name->len < len) + die("malformed name field in the index"); + strbuf_remove(name, name->len - len, len); + for (ep = cp; *ep; ep++) + ; /* find the end */ + strbuf_add(name, cp, ep - cp); + return (const char *)ep + 1 - cp_; +} + +static struct cache_entry *create_from_disk(struct ondisk_cache_entry *ondisk, + unsigned long *ent_size, + struct strbuf *previous_name) +{ + struct cache_entry *ce; + size_t len; + const char *name; + unsigned int flags; + + /* On-disk flags are just 16 bits */ + flags = ntoh_s(ondisk->flags); + len = flags & CE_NAMEMASK; + + if (flags & CE_EXTENDED) { + struct ondisk_cache_entry_extended *ondisk2; + int extended_flags; + ondisk2 = (struct ondisk_cache_entry_extended *)ondisk; + extended_flags = ntoh_s(ondisk2->flags2) << 16; + /* We do not yet understand any bit out of CE_EXTENDED_FLAGS */ + if (extended_flags & ~CE_EXTENDED_FLAGS) + die("Unknown index entry format %08x", extended_flags); + flags |= extended_flags; + name = ondisk2->name; + } + else + name = ondisk->name; + + if (!previous_name) { + /* v3 and earlier */ + if (len == CE_NAMEMASK) + len = strlen(name); + ce = cache_entry_from_ondisk(ondisk, flags, name, len); + + *ent_size = ondisk_ce_size(ce); + } else { + unsigned long consumed; + consumed = expand_name_field(previous_name, name); + ce = cache_entry_from_ondisk(ondisk, flags, + previous_name->buf, + previous_name->len); + + *ent_size = (name - ((char *)ondisk)) + consumed; + } + return ce; +} + /* remember to discard_cache() before reading a different cache! */ int read_index_from(struct index_state *istate, const char *path) { int fd, i; struct stat st; - unsigned long offset; + unsigned long src_offset; struct cache_header *hdr; + void *mmap; + size_t mmap_size; + struct strbuf previous_name_buf = STRBUF_INIT, *previous_name; errno = EBUSY; - if (istate->mmap) + if (istate->initialized) return istate->cache_nr; errno = ENOENT; - istate->timestamp = 0; + istate->timestamp.sec = 0; + istate->timestamp.nsec = 0; fd = open(path, O_RDONLY); if (fd < 0) { if (errno == ENOENT) return 0; - die("index file open failed (%s)", strerror(errno)); + die_errno("index file open failed"); } if (fstat(fd, &st)) - die("cannot stat the open index (%s)", strerror(errno)); + die_errno("cannot stat the open index"); errno = EINVAL; - istate->mmap_size = xsize_t(st.st_size); - if (istate->mmap_size < sizeof(struct cache_header) + 20) + mmap_size = xsize_t(st.st_size); + if (mmap_size < sizeof(struct cache_header) + 20) die("index file smaller than expected"); - istate->mmap = xmmap(NULL, istate->mmap_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); + mmap = xmmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); close(fd); + if (mmap == MAP_FAILED) + die_errno("unable to map index file"); - hdr = istate->mmap; - if (verify_hdr(hdr, istate->mmap_size) < 0) + hdr = mmap; + if (verify_hdr(hdr, mmap_size) < 0) goto unmap; + istate->version = ntohl(hdr->hdr_version); istate->cache_nr = ntohl(hdr->hdr_entries); istate->cache_alloc = alloc_nr(istate->cache_nr); istate->cache = xcalloc(istate->cache_alloc, sizeof(struct cache_entry *)); + istate->initialized = 1; + + if (istate->version == 4) + previous_name = &previous_name_buf; + else + previous_name = NULL; - offset = sizeof(*hdr); + src_offset = sizeof(*hdr); for (i = 0; i < istate->cache_nr; i++) { + struct ondisk_cache_entry *disk_ce; struct cache_entry *ce; + unsigned long consumed; + + disk_ce = (struct ondisk_cache_entry *)((char *)mmap + src_offset); + ce = create_from_disk(disk_ce, &consumed, previous_name); + set_index_entry(istate, i, ce); - ce = (struct cache_entry *)((char *)(istate->mmap) + offset); - offset = offset + ce_size(ce); - istate->cache[i] = ce; + src_offset += consumed; } - istate->timestamp = st.st_mtime; - while (offset <= istate->mmap_size - 20 - 8) { + strbuf_release(&previous_name_buf); + istate->timestamp.sec = st.st_mtime; + istate->timestamp.nsec = ST_MTIME_NSEC(st); + + while (src_offset <= mmap_size - 20 - 8) { /* After an array of active_nr index entries, * there can be arbitrary number of extended * sections, each of which is prefixed with * extension name (4-byte) and section length * in 4-byte network byte order. */ - unsigned long extsize; - memcpy(&extsize, (char *)(istate->mmap) + offset + 4, 4); + uint32_t extsize; + memcpy(&extsize, (char *)mmap + src_offset + 4, 4); extsize = ntohl(extsize); if (read_index_extension(istate, - ((const char *) (istate->mmap)) + offset, - (char *) (istate->mmap) + offset + 8, + (const char *) mmap + src_offset, + (char *) mmap + src_offset + 8, extsize) < 0) goto unmap; - offset += 8; - offset += extsize; + src_offset += 8; + src_offset += extsize; } + munmap(mmap, mmap_size); return istate->cache_nr; unmap: - munmap(istate->mmap, istate->mmap_size); + munmap(mmap, mmap_size); errno = EINVAL; die("index file corrupt"); } +int is_index_unborn(struct index_state *istate) +{ + return (!istate->cache_nr && !istate->timestamp.sec); +} + int discard_index(struct index_state *istate) { - int ret; + int i; + for (i = 0; i < istate->cache_nr; i++) + free(istate->cache[i]); + resolve_undo_clear_index(istate); istate->cache_nr = 0; istate->cache_changed = 0; - istate->timestamp = 0; + istate->timestamp.sec = 0; + istate->timestamp.nsec = 0; + istate->name_hash_initialized = 0; + free_hash(&istate->name_hash); cache_tree_free(&(istate->cache_tree)); - if (istate->mmap == NULL) - return 0; - ret = munmap(istate->mmap, istate->mmap_size); - istate->mmap = NULL; - istate->mmap_size = 0; + istate->initialized = 0; /* no need to throw away allocated active_cache */ - return ret; + return 0; +} + +int unmerged_index(const struct index_state *istate) +{ + int i; + for (i = 0; i < istate->cache_nr; i++) { + if (ce_stage(istate->cache[i])) + return 1; + } + return 0; } #define WRITE_BUFFER_SIZE 8192 static unsigned char write_buffer[WRITE_BUFFER_SIZE]; static unsigned long write_buffer_len; -static int ce_write_flush(SHA_CTX *context, int fd) +static int ce_write_flush(git_SHA_CTX *context, int fd) { unsigned int buffered = write_buffer_len; if (buffered) { - SHA1_Update(context, write_buffer, buffered); + git_SHA1_Update(context, write_buffer, buffered); if (write_in_full(fd, write_buffer, buffered) != buffered) return -1; write_buffer_len = 0; @@ -1009,7 +1545,7 @@ static int ce_write_flush(SHA_CTX *context, int fd) return 0; } -static int ce_write(SHA_CTX *context, int fd, void *data, unsigned int len) +static int ce_write(git_SHA_CTX *context, int fd, void *data, unsigned int len) { while (len) { unsigned int buffered = write_buffer_len; @@ -1031,7 +1567,7 @@ static int ce_write(SHA_CTX *context, int fd, void *data, unsigned int len) return 0; } -static int write_index_ext_header(SHA_CTX *context, int fd, +static int write_index_ext_header(git_SHA_CTX *context, int fd, unsigned int ext, unsigned int sz) { ext = htonl(ext); @@ -1040,13 +1576,13 @@ static int write_index_ext_header(SHA_CTX *context, int fd, (ce_write(context, fd, &sz, 4) < 0)) ? -1 : 0; } -static int ce_flush(SHA_CTX *context, int fd) +static int ce_flush(git_SHA_CTX *context, int fd) { unsigned int left = write_buffer_len; if (left) { write_buffer_len = 0; - SHA1_Update(context, write_buffer, left); + git_SHA1_Update(context, write_buffer, left); } /* Flush first if not enough space for SHA1 signature */ @@ -1057,7 +1593,7 @@ static int ce_flush(SHA_CTX *context, int fd) } /* Append the SHA1 signature at the end */ - SHA1_Final(write_buffer + left, context); + git_SHA1_Final(write_buffer + left, context); left += 20; return (write_in_full(fd, write_buffer, left) != left) ? -1 : 0; } @@ -1069,6 +1605,11 @@ static void ce_smudge_racily_clean_entry(struct cache_entry *ce) * falsely clean entry due to touch-update-touch race, so we leave * everything else as they are. We are called for entries whose * ce_mtime match the index file mtime. + * + * Note that this actually does not do much for gitlinks, for + * which ce_match_stat_basic() always goes to the actual + * contents. The caller checks with is_racy_timestamp() which + * always says "no" for gitlinks, so we are not called for them ;-) */ struct stat st; @@ -1102,53 +1643,247 @@ static void ce_smudge_racily_clean_entry(struct cache_entry *ce) * file, and never calls us, so the cached size information * for "frotz" stays 6 which does not match the filesystem. */ - ce->ce_size = htonl(0); + ce->ce_size = 0; + } +} + +/* Copy miscellaneous fields but not the name */ +static char *copy_cache_entry_to_ondisk(struct ondisk_cache_entry *ondisk, + struct cache_entry *ce) +{ + ondisk->ctime.sec = htonl(ce->ce_ctime.sec); + ondisk->mtime.sec = htonl(ce->ce_mtime.sec); + ondisk->ctime.nsec = htonl(ce->ce_ctime.nsec); + ondisk->mtime.nsec = htonl(ce->ce_mtime.nsec); + ondisk->dev = htonl(ce->ce_dev); + ondisk->ino = htonl(ce->ce_ino); + ondisk->mode = htonl(ce->ce_mode); + ondisk->uid = htonl(ce->ce_uid); + ondisk->gid = htonl(ce->ce_gid); + ondisk->size = htonl(ce->ce_size); + hashcpy(ondisk->sha1, ce->sha1); + ondisk->flags = htons(ce->ce_flags); + if (ce->ce_flags & CE_EXTENDED) { + struct ondisk_cache_entry_extended *ondisk2; + ondisk2 = (struct ondisk_cache_entry_extended *)ondisk; + ondisk2->flags2 = htons((ce->ce_flags & CE_EXTENDED_FLAGS) >> 16); + return ondisk2->name; + } + else { + return ondisk->name; + } +} + +static int ce_write_entry(git_SHA_CTX *c, int fd, struct cache_entry *ce, + struct strbuf *previous_name) +{ + int size; + struct ondisk_cache_entry *ondisk; + char *name; + int result; + + if (!previous_name) { + size = ondisk_ce_size(ce); + ondisk = xcalloc(1, size); + name = copy_cache_entry_to_ondisk(ondisk, ce); + memcpy(name, ce->name, ce_namelen(ce)); + } else { + int common, to_remove, prefix_size; + unsigned char to_remove_vi[16]; + for (common = 0; + (ce->name[common] && + common < previous_name->len && + ce->name[common] == previous_name->buf[common]); + common++) + ; /* still matching */ + to_remove = previous_name->len - common; + prefix_size = encode_varint(to_remove, to_remove_vi); + + if (ce->ce_flags & CE_EXTENDED) + size = offsetof(struct ondisk_cache_entry_extended, name); + else + size = offsetof(struct ondisk_cache_entry, name); + size += prefix_size + (ce_namelen(ce) - common + 1); + + ondisk = xcalloc(1, size); + name = copy_cache_entry_to_ondisk(ondisk, ce); + memcpy(name, to_remove_vi, prefix_size); + memcpy(name + prefix_size, ce->name + common, ce_namelen(ce) - common); + + strbuf_splice(previous_name, common, to_remove, + ce->name + common, ce_namelen(ce) - common); } + + result = ce_write(c, fd, ondisk, size); + free(ondisk); + return result; +} + +static int has_racy_timestamp(struct index_state *istate) +{ + int entries = istate->cache_nr; + int i; + + for (i = 0; i < entries; i++) { + struct cache_entry *ce = istate->cache[i]; + if (is_racy_timestamp(istate, ce)) + return 1; + } + return 0; +} + +/* + * Opportunisticly update the index but do not complain if we can't + */ +void update_index_if_able(struct index_state *istate, struct lock_file *lockfile) +{ + if ((istate->cache_changed || has_racy_timestamp(istate)) && + !write_index(istate, lockfile->fd)) + commit_locked_index(lockfile); + else + rollback_lock_file(lockfile); } int write_index(struct index_state *istate, int newfd) { - SHA_CTX c; + git_SHA_CTX c; struct cache_header hdr; - int i, removed; + int i, err, removed, extended, hdr_version; struct cache_entry **cache = istate->cache; int entries = istate->cache_nr; + struct stat st; + struct strbuf previous_name_buf = STRBUF_INIT, *previous_name; - for (i = removed = 0; i < entries; i++) - if (!cache[i]->ce_mode) + for (i = removed = extended = 0; i < entries; i++) { + if (cache[i]->ce_flags & CE_REMOVE) removed++; + /* reduce extended entries if possible */ + cache[i]->ce_flags &= ~CE_EXTENDED; + if (cache[i]->ce_flags & CE_EXTENDED_FLAGS) { + extended++; + cache[i]->ce_flags |= CE_EXTENDED; + } + } + + if (!istate->version) + istate->version = INDEX_FORMAT_DEFAULT; + + /* demote version 3 to version 2 when the latter suffices */ + if (istate->version == 3 || istate->version == 2) + istate->version = extended ? 3 : 2; + + hdr_version = istate->version; + hdr.hdr_signature = htonl(CACHE_SIGNATURE); - hdr.hdr_version = htonl(2); + hdr.hdr_version = htonl(hdr_version); hdr.hdr_entries = htonl(entries - removed); - SHA1_Init(&c); + git_SHA1_Init(&c); if (ce_write(&c, newfd, &hdr, sizeof(hdr)) < 0) return -1; + previous_name = (hdr_version == 4) ? &previous_name_buf : NULL; for (i = 0; i < entries; i++) { struct cache_entry *ce = cache[i]; - if (!ce->ce_mode) + if (ce->ce_flags & CE_REMOVE) continue; - if (istate->timestamp && - istate->timestamp <= ntohl(ce->ce_mtime.sec)) + if (!ce_uptodate(ce) && is_racy_timestamp(istate, ce)) ce_smudge_racily_clean_entry(ce); - if (ce_write(&c, newfd, ce, ce_size(ce)) < 0) + if (ce_write_entry(&c, newfd, ce, previous_name) < 0) return -1; } + strbuf_release(&previous_name_buf); /* Write extension data here */ if (istate->cache_tree) { - unsigned long sz; - void *data = cache_tree_write(istate->cache_tree, &sz); - if (data && - !write_index_ext_header(&c, newfd, CACHE_EXT_TREE, sz) && - !ce_write(&c, newfd, data, sz)) - free(data); - else { - free(data); + struct strbuf sb = STRBUF_INIT; + + cache_tree_write(&sb, istate->cache_tree); + err = write_index_ext_header(&c, newfd, CACHE_EXT_TREE, sb.len) < 0 + || ce_write(&c, newfd, sb.buf, sb.len) < 0; + strbuf_release(&sb); + if (err) return -1; - } } - return ce_flush(&c, newfd); + if (istate->resolve_undo) { + struct strbuf sb = STRBUF_INIT; + + resolve_undo_write(&sb, istate->resolve_undo); + err = write_index_ext_header(&c, newfd, CACHE_EXT_RESOLVE_UNDO, + sb.len) < 0 + || ce_write(&c, newfd, sb.buf, sb.len) < 0; + strbuf_release(&sb); + if (err) + return -1; + } + + if (ce_flush(&c, newfd) || fstat(newfd, &st)) + return -1; + istate->timestamp.sec = (unsigned int)st.st_mtime; + istate->timestamp.nsec = ST_MTIME_NSEC(st); + return 0; +} + +/* + * Read the index file that is potentially unmerged into given + * index_state, dropping any unmerged entries. Returns true if + * the index is unmerged. Callers who want to refuse to work + * from an unmerged state can call this and check its return value, + * instead of calling read_cache(). + */ +int read_index_unmerged(struct index_state *istate) +{ + int i; + int unmerged = 0; + + read_index(istate); + for (i = 0; i < istate->cache_nr; i++) { + struct cache_entry *ce = istate->cache[i]; + struct cache_entry *new_ce; + int size, len; + + if (!ce_stage(ce)) + continue; + unmerged = 1; + len = ce_namelen(ce); + size = cache_entry_size(len); + new_ce = xcalloc(1, size); + memcpy(new_ce->name, ce->name, len); + new_ce->ce_flags = create_ce_flags(len, 0) | CE_CONFLICTED; + new_ce->ce_mode = ce->ce_mode; + if (add_index_entry(istate, new_ce, 0)) + return error("%s: cannot drop to stage #0", + ce->name); + i = index_name_pos(istate, new_ce->name, len); + } + return unmerged; +} + +/* + * Returns 1 if the path is an "other" path with respect to + * the index; that is, the path is not mentioned in the index at all, + * either as a file, a directory with some files in the index, + * or as an unmerged entry. + * + * We helpfully remove a trailing "/" from directories so that + * the output of read_directory can be used as-is. + */ +int index_name_is_other(const struct index_state *istate, const char *name, + int namelen) +{ + int pos; + if (namelen && name[namelen - 1] == '/') + namelen--; + pos = index_name_pos(istate, name, namelen); + if (0 <= pos) + return 0; /* exact match */ + pos = -pos - 1; + if (pos < istate->cache_nr) { + struct cache_entry *ce = istate->cache[pos]; + if (ce_namelen(ce) == namelen && + !memcmp(ce->name, name, namelen)) + return 0; /* Yup, this one exists unmerged */ + } + return 1; } |