diff options
Diffstat (limited to 'read-cache.c')
| -rw-r--r-- | read-cache.c | 1367 |
1 files changed, 994 insertions, 373 deletions
diff --git a/read-cache.c b/read-cache.c index 1bbaf1cffb..723d48dddf 100644 --- a/read-cache.c +++ b/read-cache.c @@ -5,15 +5,26 @@ */ #define NO_THE_INDEX_COMPATIBILITY_MACROS #include "cache.h" +#include "lockfile.h" #include "cache-tree.h" #include "refs.h" #include "dir.h" #include "tree.h" #include "commit.h" -#include "diff.h" -#include "diffcore.h" -#include "revision.h" #include "blob.h" +#include "resolve-undo.h" +#include "strbuf.h" +#include "varint.h" +#include "split-index.h" +#include "sigchain.h" +#include "utf8.h" + +static struct cache_entry *refresh_cache_entry(struct cache_entry *ce, + unsigned int options); + +/* Mask for the name length in ce_flags in the on-disk index */ + +#define CE_NAMEMASK (0x0fff) /* Index extensions. * @@ -26,8 +37,17 @@ #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" */ +#define CACHE_EXT_LINK 0x6c696e6b /* "link" */ +#define CACHE_EXT_UNTRACKED 0x554E5452 /* "UNTR" */ + +/* changes that can be kept in $GIT_DIR/index (basically all extensions) */ +#define EXTMASK (RESOLVE_UNDO_CHANGED | CACHE_TREE_CHANGED | \ + CE_ENTRY_ADDED | CE_ENTRY_REMOVED | CE_ENTRY_CHANGED | \ + SPLIT_INDEX_ORDERED | UNTRACKED_CHANGED) struct index_state the_index; +static const char *alternate_index_output; static void set_index_entry(struct index_state *istate, int nr, struct cache_entry *ce) { @@ -39,9 +59,12 @@ static void replace_index_entry(struct index_state *istate, int nr, struct cache { struct cache_entry *old = istate->cache[nr]; - remove_name_hash(old); + replace_index_entry_in_base(istate, old, ce); + remove_name_hash(istate, old); + free(old); set_index_entry(istate, nr, ce); - istate->cache_changed = 1; + ce->ce_flags |= CE_UPDATE_IN_BASE; + istate->cache_changed |= CE_ENTRY_CHANGED; } void rename_index_entry_at(struct index_state *istate, int nr, const char *new_name) @@ -51,15 +74,72 @@ void rename_index_entry_at(struct index_state *istate, int nr, const char *new_n 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); + new->ce_flags &= ~CE_HASHED; + new->ce_namelen = namelen; + new->index = 0; memcpy(new->name, new_name, namelen + 1); - cache_tree_invalidate_path(istate->cache_tree, old->name); + cache_tree_invalidate_path(istate, old->name); + untracked_cache_remove_from_index(istate, old->name); remove_index_entry_at(istate, nr); add_index_entry(istate, new, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE); } +void fill_stat_data(struct stat_data *sd, struct stat *st) +{ + sd->sd_ctime.sec = (unsigned int)st->st_ctime; + sd->sd_mtime.sec = (unsigned int)st->st_mtime; + sd->sd_ctime.nsec = ST_CTIME_NSEC(*st); + sd->sd_mtime.nsec = ST_MTIME_NSEC(*st); + sd->sd_dev = st->st_dev; + sd->sd_ino = st->st_ino; + sd->sd_uid = st->st_uid; + sd->sd_gid = st->st_gid; + sd->sd_size = st->st_size; +} + +int match_stat_data(const struct stat_data *sd, struct stat *st) +{ + int changed = 0; + + if (sd->sd_mtime.sec != (unsigned int)st->st_mtime) + changed |= MTIME_CHANGED; + if (trust_ctime && check_stat && + sd->sd_ctime.sec != (unsigned int)st->st_ctime) + changed |= CTIME_CHANGED; + +#ifdef USE_NSEC + if (check_stat && sd->sd_mtime.nsec != ST_MTIME_NSEC(*st)) + changed |= MTIME_CHANGED; + if (trust_ctime && check_stat && + sd->sd_ctime.nsec != ST_CTIME_NSEC(*st)) + changed |= CTIME_CHANGED; +#endif + + if (check_stat) { + if (sd->sd_uid != (unsigned int) st->st_uid || + sd->sd_gid != (unsigned int) st->st_gid) + changed |= OWNER_CHANGED; + if (sd->sd_ino != (unsigned int) st->st_ino) + changed |= INODE_CHANGED; + } + +#ifdef USE_STDEV + /* + * st_dev breaks on network filesystems where different + * clients will have different views of what "device" + * the filesystem is on + */ + if (check_stat && sd->sd_dev != (unsigned int) st->st_dev) + changed |= INODE_CHANGED; +#endif + + if (sd->sd_size != (unsigned int) st->st_size) + changed |= DATA_CHANGED; + + return changed; +} + /* * This only updates the "non-critical" parts of the directory * cache, ie the parts that aren't tracked by GIT, and only used @@ -67,15 +147,7 @@ void rename_index_entry_at(struct index_state *istate, int nr, const char *new_n */ void fill_stat_cache_info(struct cache_entry *ce, struct stat *st) { - 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; + fill_stat_data(&ce->ce_stat_data, st); if (assume_unchanged) ce->ce_flags |= CE_VALID; @@ -84,21 +156,21 @@ void fill_stat_cache_info(struct cache_entry *ce, struct stat *st) ce_mark_uptodate(ce); } -static int ce_compare_data(struct cache_entry *ce, struct stat *st) +static int ce_compare_data(const struct cache_entry *ce, struct stat *st) { int match = -1; int fd = open(ce->name, O_RDONLY); 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 */ } return match; } -static int ce_compare_link(struct cache_entry *ce, size_t expected_size) +static int ce_compare_link(const struct cache_entry *ce, size_t expected_size) { int match = -1; void *buffer; @@ -119,7 +191,7 @@ static int ce_compare_link(struct cache_entry *ce, size_t expected_size) return match; } -static int ce_compare_gitlink(struct cache_entry *ce) +static int ce_compare_gitlink(const struct cache_entry *ce) { unsigned char sha1[20]; @@ -136,7 +208,7 @@ static int ce_compare_gitlink(struct cache_entry *ce) return hashcmp(sha1, ce->sha1); } -static int ce_modified_check_fs(struct cache_entry *ce, struct stat *st) +static int ce_modified_check_fs(const struct cache_entry *ce, struct stat *st) { switch (st->st_mode & S_IFMT) { case S_IFREG: @@ -156,17 +228,7 @@ static int ce_modified_check_fs(struct cache_entry *ce, struct stat *st) return 0; } -int is_empty_blob_sha1(const unsigned char *sha1) -{ - static const unsigned char empty_blob_sha1[20] = { - 0xe6,0x9d,0xe2,0x9b,0xb2,0xd1,0xd6,0x43,0x4b,0x8b, - 0x29,0xae,0x77,0x5a,0xd8,0xc2,0xe4,0x8c,0x53,0x91 - }; - - return !hashcmp(sha1, empty_blob_sha1); -} - -static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st) +static int ce_match_stat_basic(const struct cache_entry *ce, struct stat *st) { unsigned int changed = 0; @@ -198,39 +260,11 @@ static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st) default: die("internal error: ce_mode is %o", ce->ce_mode); } - if (ce->ce_mtime.sec != (unsigned int)st->st_mtime) - changed |= MTIME_CHANGED; - if (trust_ctime && ce->ce_ctime.sec != (unsigned int)st->st_ctime) - changed |= CTIME_CHANGED; -#ifdef USE_NSEC - if (ce->ce_mtime.nsec != ST_MTIME_NSEC(*st)) - changed |= MTIME_CHANGED; - if (trust_ctime && ce->ce_ctime.nsec != ST_CTIME_NSEC(*st)) - changed |= CTIME_CHANGED; -#endif - - if (ce->ce_uid != (unsigned int) st->st_uid || - ce->ce_gid != (unsigned int) st->st_gid) - changed |= OWNER_CHANGED; - if (ce->ce_ino != (unsigned int) st->st_ino) - changed |= INODE_CHANGED; - -#ifdef USE_STDEV - /* - * st_dev breaks on network filesystems where different - * clients will have different views of what "device" - * the filesystem is on - */ - if (ce->ce_dev != (unsigned int) st->st_dev) - changed |= INODE_CHANGED; -#endif - - if (ce->ce_size != (unsigned int) st->st_size) - changed |= DATA_CHANGED; + changed |= match_stat_data(&ce->ce_stat_data, st); /* Racily smudged entry? */ - if (!ce->ce_size) { + if (!ce->ce_stat_data.sd_size) { if (!is_empty_blob_sha1(ce->sha1)) changed |= DATA_CHANGED; } @@ -238,33 +272,53 @@ static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st) return changed; } -static int is_racy_timestamp(const struct index_state *istate, struct cache_entry *ce) +static int is_racy_stat(const struct index_state *istate, + const struct stat_data *sd) { - return (!S_ISGITLINK(ce->ce_mode) && - istate->timestamp.sec && + return (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)) + (istate->timestamp.sec < sd->sd_mtime.sec || + (istate->timestamp.sec == sd->sd_mtime.sec && + istate->timestamp.nsec <= sd->sd_mtime.nsec)) #else - istate->timestamp.sec <= ce->ce_mtime.sec + istate->timestamp.sec <= sd->sd_mtime.sec #endif - ); + ); +} + +static int is_racy_timestamp(const struct index_state *istate, + const struct cache_entry *ce) +{ + return (!S_ISGITLINK(ce->ce_mode) && + is_racy_stat(istate, &ce->ce_stat_data)); +} + +int match_stat_data_racy(const struct index_state *istate, + const struct stat_data *sd, struct stat *st) +{ + if (is_racy_stat(istate, sd)) + return MTIME_CHANGED; + return match_stat_data(sd, st); } int ie_match_stat(const struct index_state *istate, - struct cache_entry *ce, struct stat *st, + const struct cache_entry *ce, struct stat *st, unsigned int options) { unsigned int changed; 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_skip_worktree && ce_skip_worktree(ce)) + return 0; if (!ignore_valid && (ce->ce_flags & CE_VALID)) return 0; @@ -305,7 +359,8 @@ int ie_match_stat(const struct index_state *istate, } int ie_modified(const struct index_state *istate, - struct cache_entry *ce, struct stat *st, unsigned int options) + const struct cache_entry *ce, + struct stat *st, unsigned int options) { int changed, changed_fs; @@ -334,7 +389,7 @@ int ie_modified(const struct index_state *istate, * then we know it is. */ if ((changed & DATA_CHANGED) && - (S_ISGITLINK(ce->ce_mode) || ce->ce_size != 0)) + (S_ISGITLINK(ce->ce_mode) || ce->ce_stat_data.sd_size != 0)) return changed; changed_fs = ce_modified_check_fs(ce, st); @@ -397,33 +452,35 @@ int df_name_compare(const char *name1, int len1, int mode1, return c1 - c2; } -int cache_name_compare(const char *name1, int flags1, const char *name2, int flags2) +int name_compare(const char *name1, size_t len1, const char *name2, size_t len2) { - int len1 = flags1 & CE_NAMEMASK; - int len2 = flags2 & CE_NAMEMASK; - int len = len1 < len2 ? len1 : len2; - int cmp; - - cmp = memcmp(name1, name2, len); + size_t min_len = (len1 < len2) ? len1 : len2; + int cmp = memcmp(name1, name2, min_len); if (cmp) return cmp; if (len1 < len2) return -1; if (len1 > len2) return 1; + return 0; +} - /* Compare stages */ - flags1 &= CE_STAGEMASK; - flags2 &= CE_STAGEMASK; +int cache_name_stage_compare(const char *name1, int len1, int stage1, const char *name2, int len2, int stage2) +{ + int cmp; + + cmp = name_compare(name1, len1, name2, len2); + if (cmp) + return cmp; - if (flags1 < flags2) + if (stage1 < stage2) return -1; - if (flags1 > flags2) + if (stage1 > stage2) return 1; return 0; } -int index_name_pos(const struct index_state *istate, const char *name, int namelen) +static int index_name_stage_pos(const struct index_state *istate, const char *name, int namelen, int stage) { int first, last; @@ -432,7 +489,7 @@ int index_name_pos(const struct index_state *istate, const char *name, int namel while (last > first) { int next = (last + first) >> 1; struct cache_entry *ce = istate->cache[next]; - int cmp = cache_name_compare(name, namelen, ce->name, ce->ce_flags); + int cmp = cache_name_stage_compare(name, namelen, stage, ce->name, ce_namelen(ce), ce_stage(ce)); if (!cmp) return next; if (cmp < 0) { @@ -444,13 +501,20 @@ int index_name_pos(const struct index_state *istate, const char *name, int namel return -first-1; } +int index_name_pos(const struct index_state *istate, const char *name, int namelen) +{ + return index_name_stage_pos(istate, name, namelen, 0); +} + /* 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]; - remove_name_hash(ce); - istate->cache_changed = 1; + record_resolve_undo(istate, ce); + remove_name_hash(istate, ce); + save_or_free_index_entry(istate, ce); + istate->cache_changed |= CE_ENTRY_REMOVED; istate->cache_nr--; if (pos >= istate->cache_nr) return 0; @@ -461,7 +525,7 @@ int remove_index_entry_at(struct index_state *istate, int pos) } /* - * Remove all cache ententries marked for removal, that is where + * Remove all cache entries 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. */ @@ -471,12 +535,16 @@ void remove_marked_cache_entries(struct index_state *istate) 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]); + if (ce_array[i]->ce_flags & CE_REMOVE) { + remove_name_hash(istate, ce_array[i]); + save_or_free_index_entry(istate, ce_array[i]); + } else ce_array[j++] = ce_array[i]; } - istate->cache_changed = 1; + if (j == istate->cache_nr) + return; + istate->cache_changed |= CE_ENTRY_REMOVED; istate->cache_nr = j; } @@ -485,7 +553,8 @@ 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); + cache_tree_invalidate_path(istate, path); + untracked_cache_remove_from_index(istate, path); while (pos < istate->cache_nr && !strcmp(istate->cache[pos]->name, path)) remove_index_entry_at(istate, pos); return 0; @@ -534,7 +603,9 @@ static int different_name(struct cache_entry *ce, struct cache_entry *alias) * 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) +static struct cache_entry *create_alias_ce(struct index_state *istate, + struct cache_entry *ce, + struct cache_entry *alias) { int len; struct cache_entry *new; @@ -547,11 +618,11 @@ static struct cache_entry *create_alias_ce(struct cache_entry *ce, struct cache_ new = xcalloc(1, cache_entry_size(len)); memcpy(new->name, alias->name, len); copy_cache_entry(new, ce); - free(ce); + save_or_free_index_entry(istate, ce); return new; } -static void record_intent_to_add(struct cache_entry *ce) +void set_object_name_for_intent_to_add_entry(struct cache_entry *ce) { unsigned char sha1[20]; if (write_sha1_file("", 0, blob_type, sha1)) @@ -564,7 +635,7 @@ int add_to_index(struct index_state *istate, const char *path, struct stat *st, 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_RACY_IS_DIRTY; + 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; @@ -582,7 +653,7 @@ int add_to_index(struct index_state *istate, const char *path, struct stat *st, size = cache_entry_size(namelen); ce = xcalloc(1, size); memcpy(ce->name, path, namelen); - ce->ce_flags = namelen; + ce->ce_namelen = namelen; if (!intent_only) fill_stat_cache_info(ce, st); else @@ -601,22 +672,49 @@ int add_to_index(struct index_state *istate, const char *path, struct stat *st, ce->ce_mode = ce_mode_from_stat(ent, st_mode); } - alias = index_name_exists(istate, ce->name, ce_namelen(ce), ignore_case); + /* 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_dir_exists(istate, ce->name, ptr - ce->name - 1); + if (foundce) { + memcpy((void *)startPtr, foundce->name + (startPtr - ce->name), ptr - startPtr); + startPtr = ptr; + } + } + } + } + + alias = index_file_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); - ce_mark_uptodate(alias); + if (!S_ISGITLINK(alias->ce_mode)) + ce_mark_uptodate(alias); alias->ce_flags |= CE_ADDED; + + free(ce); return 0; } if (!intent_only) { - if (index_path(ce->sha1, path, st, 1)) + if (index_path(ce->sha1, path, st, HASH_WRITE_OBJECT)) { + free(ce); return error("unable to index file %s", path); + } } else - record_intent_to_add(ce); + set_object_name_for_intent_to_add_entry(ce); if (ignore_case && alias && different_name(ce, alias)) - ce = create_alias_ce(ce, alias); + ce = create_alias_ce(istate, ce, alias); ce->ce_flags |= CE_ADDED; /* It was suspected to be racily clean, but it turns out to be Ok */ @@ -626,9 +724,11 @@ int add_to_index(struct index_state *istate, const char *path, struct stat *st, 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); + free(ce); + else if (add_index_entry(istate, ce, add_option)) { + free(ce); + return error("unable to add %s to index", path); + } if (verbose && !was_same) printf("add '%s'\n", path); return 0; @@ -644,10 +744,10 @@ int add_file_to_index(struct index_state *istate, const char *path, int flags) struct cache_entry *make_cache_entry(unsigned int mode, const unsigned char *sha1, const char *path, int stage, - int refresh) + unsigned int refresh_options) { int size, len; - struct cache_entry *ce; + struct cache_entry *ce, *ret; if (!verify_path(path)) { error("Invalid path '%s'", path); @@ -660,47 +760,22 @@ struct cache_entry *make_cache_entry(unsigned int mode, hashcpy(ce->sha1, sha1); memcpy(ce->name, path, len); - ce->ce_flags = create_ce_flags(len, stage); + ce->ce_flags = create_ce_flags(stage); + ce->ce_namelen = len; ce->ce_mode = create_ce_mode(mode); - if (refresh) - return refresh_cache_entry(ce, 0); - - return ce; + ret = refresh_cache_entry(ce, refresh_options); + if (ret != ce) + free(ce); + return ret; } -int ce_same_name(struct cache_entry *a, struct cache_entry *b) +int ce_same_name(const struct cache_entry *a, const 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) -{ - 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; -} - /* * We fundamentally don't like some paths: we don't want * dot or dot-dot anywhere, and for obvious reasons don't @@ -716,24 +791,26 @@ 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. */ case 'g': - if (rest[1] != 'i') + case 'G': + if (rest[1] != 'i' && rest[1] != 'I') break; - if (rest[2] != 't') + if (rest[2] != 't' && rest[2] != 'T') break; rest += 2; /* fallthrough */ case '.': - if (rest[1] == '\0' || rest[1] == '/') + if (rest[1] == '\0' || is_dir_sep(rest[1])) return 0; } return 1; @@ -743,23 +820,23 @@ 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: + if (protect_hfs && is_hfs_dotgit(path)) + return 0; + if (protect_ntfs && is_ntfs_dotgit(path)) + return 0; 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++; } @@ -821,7 +898,7 @@ static int has_dir_name(struct index_state *istate, } len = slash - name; - pos = index_name_pos(istate, name, create_ce_flags(len, stage)); + pos = index_name_stage_pos(istate, name, len, stage); if (pos >= 0) { /* * Found one, but not so fast. This could @@ -910,8 +987,9 @@ static int add_index_entry_with_check(struct index_state *istate, struct cache_e int skip_df_check = option & ADD_CACHE_SKIP_DFCHECK; int new_only = option & ADD_CACHE_NEW_ONLY; - cache_tree_invalidate_path(istate->cache_tree, ce->name); - pos = index_name_pos(istate, ce->name, ce->ce_flags); + if (!(option & ADD_CACHE_KEEP_CACHE_TREE)) + cache_tree_invalidate_path(istate, ce->name); + pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce)); /* existing match? Just replace it. */ if (pos >= 0) { @@ -921,6 +999,8 @@ static int add_index_entry_with_check(struct index_state *istate, struct cache_e } pos = -pos-1; + untracked_cache_add_to_index(istate, ce->name); + /* * Inserting a merged entry ("stage 0") into the index * will always replace all non-merged entries.. @@ -943,7 +1023,7 @@ static int add_index_entry_with_check(struct index_state *istate, struct cache_e 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, ce->ce_flags); + pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce)); pos = -pos-1; } return pos + 1; @@ -964,11 +1044,7 @@ int add_index_entry(struct index_state *istate, struct cache_entry *ce, int opti } /* Make sure the array is big enough .. */ - if (istate->cache_nr == istate->cache_alloc) { - istate->cache_alloc = alloc_nr(istate->cache_alloc); - istate->cache = xrealloc(istate->cache, - istate->cache_alloc * sizeof(struct cache_entry *)); - } + ALLOC_GROW(istate->cache, istate->cache_nr + 1, istate->cache_alloc); /* Add it in.. */ istate->cache_nr++; @@ -977,7 +1053,7 @@ int add_index_entry(struct index_state *istate, struct cache_entry *ce, int opti istate->cache + pos, (istate->cache_nr - pos - 1) * sizeof(ce)); set_index_entry(istate, pos, ce); - istate->cache_changed = 1; + istate->cache_changed |= CE_ENTRY_ADDED; return 0; } @@ -994,32 +1070,53 @@ int add_index_entry(struct index_state *istate, struct cache_entry *ce, int opti */ static struct cache_entry *refresh_cache_ent(struct index_state *istate, struct cache_entry *ce, - unsigned int options, int *err) + unsigned int options, int *err, + int *changed_ret) { struct stat st; struct cache_entry *updated; int changed, size; + int refresh = options & CE_MATCH_REFRESH; int ignore_valid = options & CE_MATCH_IGNORE_VALID; + int ignore_skip_worktree = options & CE_MATCH_IGNORE_SKIP_WORKTREE; + int ignore_missing = options & CE_MATCH_IGNORE_MISSING; - if (ce_uptodate(ce)) + if (!refresh || ce_uptodate(ce)) return ce; /* - * CE_VALID means the user promised us that the change to - * the work tree does not matter and told us not to worry. + * 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 (has_symlink_leading_path(ce->name, ce_namelen(ce))) { + if (ignore_missing) + return ce; + if (err) + *err = ENOENT; + return NULL; + } + if (lstat(ce->name, &st) < 0) { + if (ignore_missing && errno == ENOENT) + return ce; if (err) *err = errno; return NULL; } changed = ie_match_stat(istate, ce, &st, options); + if (changed_ret) + *changed_ret = changed; if (!changed) { /* * The path is unchanged. If we were told to ignore @@ -1037,7 +1134,8 @@ static struct cache_entry *refresh_cache_ent(struct index_state *istate, * because CE_UPTODATE flag is in-core only; * we are not going to write this change out. */ - ce_mark_uptodate(ce); + if (!S_ISGITLINK(ce->ce_mode)) + ce_mark_uptodate(ce); return ce; } } @@ -1062,21 +1160,23 @@ static struct cache_entry *refresh_cache_ent(struct index_state *istate, !(ce->ce_flags & CE_VALID)) updated->ce_flags &= ~CE_VALID; + /* istate->cache_changed is updated in the caller */ return updated; } static void show_file(const char * fmt, const char * name, int in_porcelain, - int * first, char *header_msg) + int * first, const char *header_msg) { if (in_porcelain && *first && header_msg) { printf("%s\n", header_msg); - *first=0; + *first = 0; } printf(fmt, name); } -int refresh_index(struct index_state *istate, unsigned int flags, const char **pathspec, - char *seen, char *header_msg) +int refresh_index(struct index_state *istate, unsigned int flags, + const struct pathspec *pathspec, + char *seen, const char *header_msg) { int i; int has_errors = 0; @@ -1087,20 +1187,33 @@ int refresh_index(struct index_state *istate, unsigned int flags, const char **p 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 *needs_update_fmt; - const char *needs_merge_fmt; - - needs_update_fmt = (in_porcelain ? "M\t%s\n" : "%s: needs update\n"); - needs_merge_fmt = (in_porcelain ? "U\t%s\n" : "%s: needs merge\n"); + unsigned int options = (CE_MATCH_REFRESH | + (really ? CE_MATCH_IGNORE_VALID : 0) | + (not_new ? CE_MATCH_IGNORE_MISSING : 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 && !ce_path_match(ce, pathspec, seen)) + filtered = 1; + if (ce_stage(ce)) { while ((i < istate->cache_nr) && ! strcmp(istate->cache[i]->name, ce->name)) @@ -1108,30 +1221,43 @@ int refresh_index(struct index_state *istate, unsigned int flags, const char **p i--; if (allow_unmerged) continue; - show_file(needs_merge_fmt, ce->name, in_porcelain, &first, header_msg); + 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, options, &cache_errno); + new = refresh_cache_ent(istate, ce, options, &cache_errno, &changed); if (new == ce) continue; if (!new) { - if (not_new && cache_errno == ENOENT) - continue; + const char *fmt; + if (really && cache_errno == EINVAL) { /* If we are doing --really-refresh that * means the index is not valid anymore. */ ce->ce_flags &= ~CE_VALID; - istate->cache_changed = 1; + ce->ce_flags |= CE_UPDATE_IN_BASE; + istate->cache_changed |= CE_ENTRY_CHANGED; } if (quiet) continue; - show_file(needs_update_fmt, ce->name, in_porcelain, &first, header_msg); + + 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; } @@ -1141,20 +1267,108 @@ int refresh_index(struct index_state *istate, unsigned int flags, const char **p 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, + unsigned int options) { - return refresh_cache_ent(&the_index, ce, really, NULL); + return refresh_cache_ent(&the_index, ce, options, NULL, NULL); } + +/***************************************************************** + * Index File I/O + *****************************************************************/ + +#define INDEX_FORMAT_DEFAULT 3 + +static unsigned int get_index_format_default(void) +{ + char *envversion = getenv("GIT_INDEX_VERSION"); + char *endp; + int value; + unsigned int version = INDEX_FORMAT_DEFAULT; + + if (!envversion) { + if (!git_config_get_int("index.version", &value)) + version = value; + if (version < INDEX_FORMAT_LB || INDEX_FORMAT_UB < version) { + warning(_("index.version set, but the value is invalid.\n" + "Using version %i"), INDEX_FORMAT_DEFAULT); + return INDEX_FORMAT_DEFAULT; + } + return version; + } + + version = strtoul(envversion, &endp, 10); + if (*endp || + version < INDEX_FORMAT_LB || INDEX_FORMAT_UB < version) { + warning(_("GIT_INDEX_VERSION set, but the value is invalid.\n" + "Using version %i"), INDEX_FORMAT_DEFAULT); + version = INDEX_FORMAT_DEFAULT; + } + return version; +} + +/* + * 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; + uint32_t dev; + uint32_t ino; + uint32_t mode; + uint32_t uid; + uint32_t gid; + uint32_t size; + unsigned char sha1[20]; + uint16_t 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; + uint32_t dev; + uint32_t ino; + uint32_t mode; + uint32_t uid; + uint32_t gid; + uint32_t size; + unsigned char sha1[20]; + uint16_t flags; + uint16_t 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) { 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) && hdr->hdr_version != htonl(3)) - return error("bad index version"); + hdr_version = ntohl(hdr->hdr_version); + if (hdr_version < INDEX_FORMAT_LB || INDEX_FORMAT_UB < 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); @@ -1170,6 +1384,16 @@ 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; + case CACHE_EXT_LINK: + if (read_link_extension(istate, data, sz)) + return -1; + break; + case CACHE_EXT_UNTRACKED: + istate->untracked = read_untracked_extension(data, sz); + break; default: if (*ext < 'A' || 'Z' < *ext) return error("index uses %.4s extension, which we do not understand", @@ -1180,138 +1404,198 @@ static int read_index_extension(struct index_state *istate, return 0; } +int hold_locked_index(struct lock_file *lk, int die_on_error) +{ + return hold_lock_file_for_update(lk, get_index_file(), + die_on_error + ? LOCK_DIE_ON_ERROR + : 0); +} + int read_index(struct index_state *istate) { return read_index_from(istate, get_index_file()); } -static void convert_from_disk(struct ondisk_cache_entry *ondisk, struct cache_entry *ce) +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_stat_data.sd_ctime.sec = get_be32(&ondisk->ctime.sec); + ce->ce_stat_data.sd_mtime.sec = get_be32(&ondisk->mtime.sec); + ce->ce_stat_data.sd_ctime.nsec = get_be32(&ondisk->ctime.nsec); + ce->ce_stat_data.sd_mtime.nsec = get_be32(&ondisk->mtime.nsec); + ce->ce_stat_data.sd_dev = get_be32(&ondisk->dev); + ce->ce_stat_data.sd_ino = get_be32(&ondisk->ino); + ce->ce_mode = get_be32(&ondisk->mode); + ce->ce_stat_data.sd_uid = get_be32(&ondisk->uid); + ce->ce_stat_data.sd_gid = get_be32(&ondisk->gid); + ce->ce_stat_data.sd_size = get_be32(&ondisk->size); + ce->ce_flags = flags & ~CE_NAMEMASK; + ce->ce_namelen = len; + ce->index = 0; + 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; - ce->ce_ctime.sec = ntohl(ondisk->ctime.sec); - ce->ce_mtime.sec = ntohl(ondisk->mtime.sec); - ce->ce_ctime.nsec = ntohl(ondisk->ctime.nsec); - ce->ce_mtime.nsec = ntohl(ondisk->mtime.nsec); - ce->ce_dev = ntohl(ondisk->dev); - ce->ce_ino = ntohl(ondisk->ino); - ce->ce_mode = ntohl(ondisk->mode); - ce->ce_uid = ntohl(ondisk->uid); - ce->ce_gid = ntohl(ondisk->gid); - ce->ce_size = ntohl(ondisk->size); /* On-disk flags are just 16 bits */ - ce->ce_flags = ntohs(ondisk->flags); - - hashcpy(ce->sha1, ondisk->sha1); - - len = ce->ce_flags & CE_NAMEMASK; + flags = get_be16(&ondisk->flags); + len = flags & CE_NAMEMASK; - if (ce->ce_flags & CE_EXTENDED) { + if (flags & CE_EXTENDED) { struct ondisk_cache_entry_extended *ondisk2; int extended_flags; ondisk2 = (struct ondisk_cache_entry_extended *)ondisk; - extended_flags = ntohs(ondisk2->flags2) << 16; + extended_flags = get_be16(&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); - ce->ce_flags |= extended_flags; + flags |= extended_flags; name = ondisk2->name; } else name = ondisk->name; - if (len == CE_NAMEMASK) - len = strlen(name); - /* - * NEEDSWORK: If the original index is crafted, this copy could - * go unchecked. - */ - memcpy(ce->name, name, len + 1); + 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; } -static inline size_t estimate_cache_size(size_t ondisk_size, unsigned int entries) +static void check_ce_order(struct index_state *istate) { - long per_entry; - - per_entry = sizeof(struct cache_entry) - sizeof(struct ondisk_cache_entry); - - /* - * Alignment can cause differences. This should be "alignof", but - * since that's a gcc'ism, just use the size of a pointer. - */ - per_entry += sizeof(void *); - return ondisk_size + entries*per_entry; + unsigned int i; + + for (i = 1; i < istate->cache_nr; i++) { + struct cache_entry *ce = istate->cache[i - 1]; + struct cache_entry *next_ce = istate->cache[i]; + int name_compare = strcmp(ce->name, next_ce->name); + + if (0 < name_compare) + die("unordered stage entries in index"); + if (!name_compare) { + if (!ce_stage(ce)) + die("multiple stage entries for merged file '%s'", + ce->name); + if (ce_stage(ce) > ce_stage(next_ce)) + die("unordered stage entries for '%s'", + ce->name); + } + } } /* remember to discard_cache() before reading a different cache! */ -int read_index_from(struct index_state *istate, const char *path) +int do_read_index(struct index_state *istate, const char *path, int must_exist) { int fd, i; struct stat st; - unsigned long src_offset, dst_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->initialized) return istate->cache_nr; - errno = ENOENT; istate->timestamp.sec = 0; istate->timestamp.nsec = 0; fd = open(path, O_RDONLY); if (fd < 0) { - if (errno == ENOENT) + if (!must_exist && errno == ENOENT) return 0; - die_errno("index file open failed"); + die_errno("%s: index file open failed", path); } if (fstat(fd, &st)) die_errno("cannot stat the open index"); - errno = EINVAL; mmap_size = xsize_t(st.st_size); if (mmap_size < sizeof(struct cache_header) + 20) die("index file smaller than expected"); 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"); + close(fd); hdr = mmap; if (verify_hdr(hdr, mmap_size) < 0) goto unmap; + hashcpy(istate->sha1, (const unsigned char *)hdr + mmap_size - 20); + 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 *)); - - /* - * The disk format is actually larger than the in-memory format, - * due to space for nsec etc, so even though the in-memory one - * has room for a few more flags, we can allocate using the same - * index size - */ - istate->alloc = xmalloc(estimate_cache_size(mmap_size, istate->cache_nr)); + istate->cache = xcalloc(istate->cache_alloc, sizeof(*istate->cache)); istate->initialized = 1; + if (istate->version == 4) + previous_name = &previous_name_buf; + else + previous_name = NULL; + src_offset = sizeof(*hdr); - dst_offset = 0; 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 = (struct cache_entry *)((char *)istate->alloc + dst_offset); - convert_from_disk(disk_ce, ce); + ce = create_from_disk(disk_ce, &consumed, previous_name); set_index_entry(istate, i, ce); - src_offset += ondisk_ce_size(ce); - dst_offset += ce_size(ce); + src_offset += consumed; } + strbuf_release(&previous_name_buf); istate->timestamp.sec = st.st_mtime; istate->timestamp.nsec = ST_MTIME_NSEC(st); @@ -1322,7 +1606,7 @@ int read_index_from(struct index_state *istate, const char *path) * extension name (4-byte) and section length * in 4-byte network byte order. */ - unsigned long extsize; + uint32_t extsize; memcpy(&extsize, (char *)mmap + src_offset + 4, 4); extsize = ntohl(extsize); if (read_index_extension(istate, @@ -1338,29 +1622,75 @@ int read_index_from(struct index_state *istate, const char *path) unmap: munmap(mmap, mmap_size); - errno = EINVAL; die("index file corrupt"); } +int read_index_from(struct index_state *istate, const char *path) +{ + struct split_index *split_index; + int ret; + + /* istate->initialized covers both .git/index and .git/sharedindex.xxx */ + if (istate->initialized) + return istate->cache_nr; + + ret = do_read_index(istate, path, 0); + split_index = istate->split_index; + if (!split_index || is_null_sha1(split_index->base_sha1)) { + check_ce_order(istate); + return ret; + } + + if (split_index->base) + discard_index(split_index->base); + else + split_index->base = xcalloc(1, sizeof(*split_index->base)); + ret = do_read_index(split_index->base, + git_path("sharedindex.%s", + sha1_to_hex(split_index->base_sha1)), 1); + if (hashcmp(split_index->base_sha1, split_index->base->sha1)) + die("broken index, expect %s in %s, got %s", + sha1_to_hex(split_index->base_sha1), + git_path("sharedindex.%s", + sha1_to_hex(split_index->base_sha1)), + sha1_to_hex(split_index->base->sha1)); + merge_base_index(istate); + check_ce_order(istate); + return ret; +} + int is_index_unborn(struct index_state *istate) { - return (!istate->cache_nr && !istate->alloc && !istate->timestamp.sec); + return (!istate->cache_nr && !istate->timestamp.sec); } int discard_index(struct index_state *istate) { + int i; + + for (i = 0; i < istate->cache_nr; i++) { + if (istate->cache[i]->index && + istate->split_index && + istate->split_index->base && + istate->cache[i]->index <= istate->split_index->base->cache_nr && + istate->cache[i] == istate->split_index->base->cache[istate->cache[i]->index - 1]) + continue; + free(istate->cache[i]); + } + resolve_undo_clear_index(istate); istate->cache_nr = 0; istate->cache_changed = 0; istate->timestamp.sec = 0; istate->timestamp.nsec = 0; - istate->name_hash_initialized = 0; - free_hash(&istate->name_hash); + free_name_hash(istate); cache_tree_free(&(istate->cache_tree)); - free(istate->alloc); - istate->alloc = NULL; istate->initialized = 0; - - /* no need to throw away allocated active_cache */ + free(istate->cache); + istate->cache = NULL; + istate->cache_alloc = 0; + discard_split_index(istate); + free_untracked_cache(istate->untracked); + istate->untracked = NULL; return 0; } @@ -1421,7 +1751,7 @@ static int write_index_ext_header(git_SHA_CTX *context, int fd, (ce_write(context, fd, &sz, 4) < 0)) ? -1 : 0; } -static int ce_flush(git_SHA_CTX *context, int fd) +static int ce_flush(git_SHA_CTX *context, int fd, unsigned char *sha1) { unsigned int left = write_buffer_len; @@ -1439,6 +1769,7 @@ static int ce_flush(git_SHA_CTX *context, int fd) /* Append the SHA1 signature at the end */ git_SHA1_Final(write_buffer + left, context); + hashcpy(sha1, write_buffer + left); left += 20; return (write_in_full(fd, write_buffer, left) != left) ? -1 : 0; } @@ -1449,7 +1780,7 @@ static void ce_smudge_racily_clean_entry(struct cache_entry *ce) * The only thing we care about in this function is to smudge the * 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. + * ce_stat_data.sd_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 @@ -1488,49 +1819,175 @@ 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 = 0; + ce->ce_stat_data.sd_size = 0; } } -static int ce_write_entry(git_SHA_CTX *c, int fd, struct cache_entry *ce) +/* Copy miscellaneous fields but not the name */ +static char *copy_cache_entry_to_ondisk(struct ondisk_cache_entry *ondisk, + struct cache_entry *ce) { - int size = ondisk_ce_size(ce); - struct ondisk_cache_entry *ondisk = xcalloc(1, size); - char *name; - - 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); + short flags; + + ondisk->ctime.sec = htonl(ce->ce_stat_data.sd_ctime.sec); + ondisk->mtime.sec = htonl(ce->ce_stat_data.sd_mtime.sec); + ondisk->ctime.nsec = htonl(ce->ce_stat_data.sd_ctime.nsec); + ondisk->mtime.nsec = htonl(ce->ce_stat_data.sd_mtime.nsec); + ondisk->dev = htonl(ce->ce_stat_data.sd_dev); + ondisk->ino = htonl(ce->ce_stat_data.sd_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); + ondisk->uid = htonl(ce->ce_stat_data.sd_uid); + ondisk->gid = htonl(ce->ce_stat_data.sd_gid); + ondisk->size = htonl(ce->ce_stat_data.sd_size); hashcpy(ondisk->sha1, ce->sha1); - ondisk->flags = htons(ce->ce_flags); + + flags = ce->ce_flags & ~CE_NAMEMASK; + flags |= (ce_namelen(ce) >= CE_NAMEMASK ? CE_NAMEMASK : ce_namelen(ce)); + ondisk->flags = htons(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); - name = ondisk2->name; + return ondisk2->name; } - else - name = ondisk->name; - memcpy(name, ce->name, ce_namelen(ce)); + 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; + int saved_namelen = saved_namelen; /* compiler workaround */ + char *name; + int result; + + if (ce->ce_flags & CE_STRIP_NAME) { + saved_namelen = ce_namelen(ce); + ce->ce_namelen = 0; + } + + 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); + } + if (ce->ce_flags & CE_STRIP_NAME) { + ce->ce_namelen = saved_namelen; + ce->ce_flags &= ~CE_STRIP_NAME; + } + + result = ce_write(c, fd, ondisk, size); + free(ondisk); + return result; +} + +/* + * This function verifies if index_state has the correct sha1 of the + * index file. Don't die if we have any other failure, just return 0. + */ +static int verify_index_from(const struct index_state *istate, const char *path) +{ + int fd; + ssize_t n; + struct stat st; + unsigned char sha1[20]; + + if (!istate->initialized) + return 0; + + fd = open(path, O_RDONLY); + if (fd < 0) + return 0; + + if (fstat(fd, &st)) + goto out; + + if (st.st_size < sizeof(struct cache_header) + 20) + goto out; + + n = pread_in_full(fd, sha1, 20, st.st_size - 20); + if (n != 20) + goto out; + + if (hashcmp(istate->sha1, sha1)) + goto out; - return ce_write(c, fd, ondisk, size); + close(fd); + return 1; + +out: + close(fd); + return 0; } -int write_index(struct index_state *istate, int newfd) +static int verify_index(const struct index_state *istate) +{ + return verify_index_from(istate, get_index_file()); +} + +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; +} + +/* + * Opportunistically 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)) && + verify_index(istate) && + write_locked_index(istate, lockfile, COMMIT_LOCK)) + rollback_lock_file(lockfile); +} + +static int do_write_index(struct index_state *istate, int newfd, + int strip_extensions) { git_SHA_CTX c; struct cache_header hdr; - int i, err, removed, extended; + 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 = extended = 0; i < entries; i++) { if (cache[i]->ce_flags & CE_REMOVE) @@ -1544,27 +2001,62 @@ int write_index(struct index_state *istate, int newfd) } } + if (!istate->version) { + istate->version = get_index_format_default(); + if (getenv("GIT_TEST_SPLIT_INDEX")) + init_split_index(istate); + } + + /* 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); - /* for extended format, increase version so older git won't try to read it */ - hdr.hdr_version = htonl(extended ? 3 : 2); + hdr.hdr_version = htonl(hdr_version); hdr.hdr_entries = htonl(entries - removed); 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_flags & CE_REMOVE) continue; if (!ce_uptodate(ce) && is_racy_timestamp(istate, ce)) ce_smudge_racily_clean_entry(ce); - if (ce_write_entry(&c, newfd, ce) < 0) + if (is_null_sha1(ce->sha1)) { + static const char msg[] = "cache entry has null sha1: %s"; + static int allow = -1; + + if (allow < 0) + allow = git_env_bool("GIT_ALLOW_NULL_SHA1", 0); + if (allow) + warning(msg, ce->name); + else + return error(msg, ce->name); + } + 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) { + if (!strip_extensions && istate->split_index) { + struct strbuf sb = STRBUF_INIT; + + err = write_link_extension(&sb, istate) < 0 || + write_index_ext_header(&c, newfd, CACHE_EXT_LINK, + sb.len) < 0 || + ce_write(&c, newfd, sb.buf, sb.len) < 0; + strbuf_release(&sb); + if (err) + return -1; + } + if (!strip_extensions && istate->cache_tree) { struct strbuf sb = STRBUF_INIT; cache_tree_write(&sb, istate->cache_tree); @@ -1574,14 +2066,155 @@ int write_index(struct index_state *istate, int newfd) if (err) return -1; } + if (!strip_extensions && 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 (!strip_extensions && istate->untracked) { + struct strbuf sb = STRBUF_INIT; - if (ce_flush(&c, newfd) || fstat(newfd, &st)) + write_untracked_extension(&sb, istate->untracked); + err = write_index_ext_header(&c, newfd, CACHE_EXT_UNTRACKED, + sb.len) < 0 || + ce_write(&c, newfd, sb.buf, sb.len) < 0; + strbuf_release(&sb); + if (err) + return -1; + } + + if (ce_flush(&c, newfd, istate->sha1) || fstat(newfd, &st)) return -1; istate->timestamp.sec = (unsigned int)st.st_mtime; istate->timestamp.nsec = ST_MTIME_NSEC(st); return 0; } +void set_alternate_index_output(const char *name) +{ + alternate_index_output = name; +} + +static int commit_locked_index(struct lock_file *lk) +{ + if (alternate_index_output) + return commit_lock_file_to(lk, alternate_index_output); + else + return commit_lock_file(lk); +} + +static int do_write_locked_index(struct index_state *istate, struct lock_file *lock, + unsigned flags) +{ + int ret = do_write_index(istate, lock->fd, 0); + if (ret) + return ret; + assert((flags & (COMMIT_LOCK | CLOSE_LOCK)) != + (COMMIT_LOCK | CLOSE_LOCK)); + if (flags & COMMIT_LOCK) + return commit_locked_index(lock); + else if (flags & CLOSE_LOCK) + return close_lock_file(lock); + else + return ret; +} + +static int write_split_index(struct index_state *istate, + struct lock_file *lock, + unsigned flags) +{ + int ret; + prepare_to_write_split_index(istate); + ret = do_write_locked_index(istate, lock, flags); + finish_writing_split_index(istate); + return ret; +} + +static char *temporary_sharedindex; + +static void remove_temporary_sharedindex(void) +{ + if (temporary_sharedindex) { + unlink_or_warn(temporary_sharedindex); + free(temporary_sharedindex); + temporary_sharedindex = NULL; + } +} + +static void remove_temporary_sharedindex_on_signal(int signo) +{ + remove_temporary_sharedindex(); + sigchain_pop(signo); + raise(signo); +} + +static int write_shared_index(struct index_state *istate, + struct lock_file *lock, unsigned flags) +{ + struct split_index *si = istate->split_index; + static int installed_handler; + int fd, ret; + + temporary_sharedindex = git_pathdup("sharedindex_XXXXXX"); + fd = mkstemp(temporary_sharedindex); + if (fd < 0) { + free(temporary_sharedindex); + temporary_sharedindex = NULL; + hashclr(si->base_sha1); + return do_write_locked_index(istate, lock, flags); + } + if (!installed_handler) { + atexit(remove_temporary_sharedindex); + sigchain_push_common(remove_temporary_sharedindex_on_signal); + } + move_cache_to_base_index(istate); + ret = do_write_index(si->base, fd, 1); + close(fd); + if (ret) { + remove_temporary_sharedindex(); + return ret; + } + ret = rename(temporary_sharedindex, + git_path("sharedindex.%s", sha1_to_hex(si->base->sha1))); + free(temporary_sharedindex); + temporary_sharedindex = NULL; + if (!ret) + hashcpy(si->base_sha1, si->base->sha1); + return ret; +} + +int write_locked_index(struct index_state *istate, struct lock_file *lock, + unsigned flags) +{ + struct split_index *si = istate->split_index; + + if (!si || alternate_index_output || + (istate->cache_changed & ~EXTMASK)) { + if (si) + hashclr(si->base_sha1); + return do_write_locked_index(istate, lock, flags); + } + + if (getenv("GIT_TEST_SPLIT_INDEX")) { + int v = si->base_sha1[0]; + if ((v & 15) < 6) + istate->cache_changed |= SPLIT_INDEX_ORDERED; + } + if (istate->cache_changed & SPLIT_INDEX_ORDERED) { + int ret = write_shared_index(istate, lock, flags); + if (ret) + return ret; + } + + return write_split_index(istate, lock, flags); +} + /* * Read the index file that is potentially unmerged into given * index_state, dropping any unmerged entries. Returns true if @@ -1603,96 +2236,20 @@ int read_index_unmerged(struct index_state *istate) if (!ce_stage(ce)) continue; unmerged = 1; - len = strlen(ce->name); + len = ce_namelen(ce); size = cache_entry_size(len); new_ce = xcalloc(1, size); - hashcpy(new_ce->sha1, ce->sha1); memcpy(new_ce->name, ce->name, len); - new_ce->ce_flags = create_ce_flags(len, 0); + new_ce->ce_flags = create_ce_flags(0) | CE_CONFLICTED; + new_ce->ce_namelen = len; 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); + new_ce->name); } return unmerged; } -struct update_callback_data -{ - int flags; - int add_errors; -}; - -static void update_callback(struct diff_queue_struct *q, - struct diff_options *opt, void *cbdata) -{ - int i; - struct update_callback_data *data = cbdata; - - for (i = 0; i < q->nr; i++) { - struct diff_filepair *p = q->queue[i]; - const char *path = p->one->path; - switch (p->status) { - default: - die("unexpected diff status %c", p->status); - case DIFF_STATUS_UNMERGED: - /* - * ADD_CACHE_IGNORE_REMOVAL is unset if "git - * add -u" is calling us, In such a case, a - * missing work tree file needs to be removed - * if there is an unmerged entry at stage #2, - * but such a diff record is followed by - * another with DIFF_STATUS_DELETED (and if - * there is no stage #2, we won't see DELETED - * nor MODIFIED). We can simply continue - * either way. - */ - if (!(data->flags & ADD_CACHE_IGNORE_REMOVAL)) - continue; - /* - * Otherwise, it is "git add path" is asking - * to explicitly add it; we fall through. A - * missing work tree file is an error and is - * caught by add_file_to_index() in such a - * case. - */ - case DIFF_STATUS_MODIFIED: - case DIFF_STATUS_TYPE_CHANGED: - if (add_file_to_index(&the_index, path, data->flags)) { - if (!(data->flags & ADD_CACHE_IGNORE_ERRORS)) - die("updating files failed"); - data->add_errors++; - } - break; - case DIFF_STATUS_DELETED: - if (data->flags & ADD_CACHE_IGNORE_REMOVAL) - break; - if (!(data->flags & ADD_CACHE_PRETEND)) - remove_file_from_index(&the_index, path); - if (data->flags & (ADD_CACHE_PRETEND|ADD_CACHE_VERBOSE)) - printf("remove '%s'\n", path); - break; - } - } -} - -int add_files_to_cache(const char *prefix, const char **pathspec, int flags) -{ - struct update_callback_data data; - struct rev_info rev; - init_revisions(&rev, prefix); - setup_revisions(0, NULL, &rev, NULL); - rev.prune_data = pathspec; - rev.diffopt.output_format = DIFF_FORMAT_CALLBACK; - rev.diffopt.format_callback = update_callback; - data.flags = flags; - data.add_errors = 0; - rev.diffopt.format_callback_data = &data; - run_diff_files(&rev, DIFF_RACY_IS_MODIFIED); - return !!data.add_errors; -} - /* * 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, @@ -1720,3 +2277,67 @@ int index_name_is_other(const struct index_state *istate, const char *name, } return 1; } + +void *read_blob_data_from_index(struct index_state *istate, const char *path, unsigned long *size) +{ + int pos, len; + unsigned long sz; + enum object_type type; + void *data; + + len = strlen(path); + pos = index_name_pos(istate, path, len); + if (pos < 0) { + /* + * We might be in the middle of a merge, in which + * case we would read stage #2 (ours). + */ + int i; + for (i = -pos - 1; + (pos < 0 && i < istate->cache_nr && + !strcmp(istate->cache[i]->name, path)); + i++) + if (ce_stage(istate->cache[i]) == 2) + pos = i; + } + if (pos < 0) + return NULL; + data = read_sha1_file(istate->cache[pos]->sha1, &type, &sz); + if (!data || type != OBJ_BLOB) { + free(data); + return NULL; + } + if (size) + *size = sz; + return data; +} + +void stat_validity_clear(struct stat_validity *sv) +{ + free(sv->sd); + sv->sd = NULL; +} + +int stat_validity_check(struct stat_validity *sv, const char *path) +{ + struct stat st; + + if (stat(path, &st) < 0) + return sv->sd == NULL; + if (!sv->sd) + return 0; + return S_ISREG(st.st_mode) && !match_stat_data(sv->sd, &st); +} + +void stat_validity_update(struct stat_validity *sv, int fd) +{ + struct stat st; + + if (fstat(fd, &st) < 0 || !S_ISREG(st.st_mode)) + stat_validity_clear(sv); + else { + if (!sv->sd) + sv->sd = xcalloc(1, sizeof(struct stat_data)); + fill_stat_data(sv->sd, &st); + } +} |