* Copyright (C) Linus Torvalds, 2005
*/
#include "cache.h"
+#include "cache-tree.h"
+
+/* Index extensions.
+ *
+ * The first letter should be 'A'..'Z' for extensions that are not
+ * necessary for a correct operation (i.e. optimization data).
+ * When new extensions are added that _needs_ to be understood in
+ * order to correctly interpret the index file, pick character that
+ * is outside the range, to cause the reader to abort.
+ */
+
+#define CACHE_EXT(s) ( (s[0]<<24)|(s[1]<<16)|(s[2]<<8)|(s[3]) )
+#define CACHE_EXT_TREE 0x54524545 /* "TREE" */
struct cache_entry **active_cache = NULL;
+static time_t index_file_timestamp;
unsigned int active_nr = 0, active_alloc = 0, active_cache_changed = 0;
+struct cache_tree *active_cache_tree = NULL;
+
/*
* This only updates the "non-critical" parts of the directory
* cache, ie the parts that aren't tracked by GIT, and only used
ce->ce_uid = htonl(st->st_uid);
ce->ce_gid = htonl(st->st_gid);
ce->ce_size = htonl(st->st_size);
+
+ if (assume_unchanged)
+ ce->ce_flags |= htons(CE_VALID);
+}
+
+static int ce_compare_data(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, NULL))
+ match = memcmp(sha1, ce->sha1, 20);
+ close(fd);
+ }
+ return match;
+}
+
+static int ce_compare_link(struct cache_entry *ce, unsigned long expected_size)
+{
+ int match = -1;
+ char *target;
+ void *buffer;
+ unsigned long size;
+ char type[10];
+ int len;
+
+ target = xmalloc(expected_size);
+ len = readlink(ce->name, target, expected_size);
+ if (len != expected_size) {
+ free(target);
+ return -1;
+ }
+ buffer = read_sha1_file(ce->sha1, type, &size);
+ if (!buffer) {
+ free(target);
+ return -1;
+ }
+ if (size == expected_size)
+ match = memcmp(buffer, target, size);
+ free(buffer);
+ free(target);
+ return match;
+}
+
+static int ce_modified_check_fs(struct cache_entry *ce, struct stat *st)
+{
+ switch (st->st_mode & S_IFMT) {
+ case S_IFREG:
+ if (ce_compare_data(ce, st))
+ return DATA_CHANGED;
+ break;
+ case S_IFLNK:
+ if (ce_compare_link(ce, st->st_size))
+ return DATA_CHANGED;
+ break;
+ default:
+ return TYPE_CHANGED;
+ }
+ return 0;
}
-int ce_match_stat(struct cache_entry *ce, struct stat *st)
+static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st)
{
unsigned int changed = 0;
if (ce->ce_size != htonl(st->st_size))
changed |= DATA_CHANGED;
+
return changed;
}
-static int ce_compare_data(struct cache_entry *ce, struct stat *st)
+int ce_match_stat(struct cache_entry *ce, struct stat *st, int ignore_valid)
{
- int match = -1;
- int fd = open(ce->name, O_RDONLY);
+ unsigned int changed;
- if (fd >= 0) {
- unsigned char sha1[20];
- if (!index_fd(sha1, fd, st, 0, NULL))
- match = memcmp(sha1, ce->sha1, 20);
- close(fd);
- }
- return match;
-}
+ /*
+ * If it's marked as always valid in the index, it's
+ * valid whatever the checked-out copy says.
+ */
+ if (!ignore_valid && (ce->ce_flags & htons(CE_VALID)))
+ return 0;
-static int ce_compare_link(struct cache_entry *ce, unsigned long expected_size)
-{
- int match = -1;
- char *target;
- void *buffer;
- unsigned long size;
- char type[10];
- int len;
+ changed = ce_match_stat_basic(ce, st);
- target = xmalloc(expected_size);
- len = readlink(ce->name, target, expected_size);
- if (len != expected_size) {
- free(target);
- return -1;
- }
- buffer = read_sha1_file(ce->sha1, type, &size);
- if (!buffer) {
- free(target);
- return -1;
- }
- if (size == expected_size)
- match = memcmp(buffer, target, size);
- free(buffer);
- free(target);
- return match;
+ /*
+ * Within 1 second of this sequence:
+ * echo xyzzy >file && git-update-index --add file
+ * running this command:
+ * echo frotz >file
+ * would give a falsely clean cache entry. The mtime and
+ * length match the cache, and other stat fields do not change.
+ *
+ * We could detect this at update-index time (the cache entry
+ * being registered/updated records the same time as "now")
+ * and delay the return from git-update-index, but that would
+ * effectively mean we can make at most one commit per second,
+ * which is not acceptable. Instead, we check cache entries
+ * whose mtime are the same as the index file timestamp more
+ * carefully than others.
+ */
+ if (!changed &&
+ index_file_timestamp &&
+ index_file_timestamp <= ntohl(ce->ce_mtime.sec))
+ changed |= ce_modified_check_fs(ce, st);
+
+ return changed;
}
-int ce_modified(struct cache_entry *ce, struct stat *st)
+int ce_modified(struct cache_entry *ce, struct stat *st, int really)
{
- int changed;
- changed = ce_match_stat(ce, st);
+ int changed, changed_fs;
+ changed = ce_match_stat(ce, st, really);
if (!changed)
return 0;
-
/*
* If the mode or type has changed, there's no point in trying
* to refresh the entry - it's not going to match
if ((changed & DATA_CHANGED) && ce->ce_size != htonl(0))
return changed;
- switch (st->st_mode & S_IFMT) {
- case S_IFREG:
- if (ce_compare_data(ce, st))
- return changed | DATA_CHANGED;
- break;
- case S_IFLNK:
- if (ce_compare_link(ce, st->st_size))
- return changed | DATA_CHANGED;
- break;
- default:
- return changed | TYPE_CHANGED;
- }
+ changed_fs = ce_modified_check_fs(ce, st);
+ if (changed_fs)
+ return changed | changed_fs;
return 0;
}
return -1;
if (len1 > len2)
return 1;
+
+ /* Compare stages */
+ flags1 &= CE_STAGEMASK;
+ flags2 &= CE_STAGEMASK;
+
if (flags1 < flags2)
return -1;
if (flags1 > flags2)
return 0;
}
+/*
+ * We fundamentally don't like some paths: we don't want
+ * dot or dot-dot anywhere, and for obvious reasons don't
+ * want to recurse into ".git" either.
+ *
+ * Also, we don't want double slashes or slashes at the
+ * end that can make pathnames ambiguous.
+ */
+static int verify_dotfile(const char *rest)
+{
+ /*
+ * The first character was '.', but that
+ * has already been discarded, we now test
+ * the rest.
+ */
+ switch (*rest) {
+ /* "." is not allowed */
+ case '\0': case '/':
+ return 0;
+
+ /*
+ * ".git" followed by NUL or slash is bad. This
+ * shares the path end test with the ".." case.
+ */
+ case 'g':
+ if (rest[1] != 'i')
+ break;
+ if (rest[2] != 't')
+ break;
+ rest += 2;
+ /* fallthrough */
+ case '.':
+ if (rest[1] == '\0' || rest[1] == '/')
+ return 0;
+ }
+ return 1;
+}
+
+int verify_path(const char *path)
+{
+ char c;
+
+ goto inside;
+ for (;;) {
+ if (!c)
+ return 1;
+ if (c == '/') {
+inside:
+ c = *path++;
+ switch (c) {
+ default:
+ continue;
+ case '/': case '\0':
+ break;
+ case '.':
+ if (verify_dotfile(path))
+ continue;
+ }
+ return 0;
+ }
+ c = *path++;
+ }
+}
+
/*
* Do we have another file that has the beginning components being a
* proper superset of the name we're trying to add?
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;
+
pos = cache_name_pos(ce->name, ntohs(ce->ce_flags));
/* existing match? Just replace it. */
if (!ok_to_add)
return -1;
+ if (!verify_path(ce->name))
+ return -1;
if (!skip_df_check &&
check_file_directory_conflict(ce, pos, ok_to_replace)) {
return 0;
}
+/* Three functions to allow overloaded pointer return; see linux/err.h */
+static inline void *ERR_PTR(long error)
+{
+ return (void *) error;
+}
+
+static inline long PTR_ERR(const void *ptr)
+{
+ return (long) ptr;
+}
+
+static inline long IS_ERR(const void *ptr)
+{
+ return (unsigned long)ptr > (unsigned long)-1000L;
+}
+
+/*
+ * "refresh" does not calculate a new sha1 file or bring the
+ * cache up-to-date for mode/content changes. But what it
+ * _does_ do is to "re-match" the stat information of a file
+ * with the cache, so that you can refresh the cache for a
+ * file that hasn't been changed but where the stat entry is
+ * out of date.
+ *
+ * For example, you'd want to do this after doing a "git-read-tree",
+ * to link up the stat cache details with the proper files.
+ */
+static struct cache_entry *refresh_entry(struct cache_entry *ce, int really)
+{
+ struct stat st;
+ struct cache_entry *updated;
+ int changed, size;
+
+ if (lstat(ce->name, &st) < 0)
+ return ERR_PTR(-errno);
+
+ changed = ce_match_stat(ce, &st, really);
+ if (!changed) {
+ if (really && assume_unchanged &&
+ !(ce->ce_flags & htons(CE_VALID)))
+ ; /* mark this one VALID again */
+ else
+ return NULL;
+ }
+
+ if (ce_modified(ce, &st, really))
+ return ERR_PTR(-EINVAL);
+
+ size = ce_size(ce);
+ 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 (!really && assume_unchanged && !(ce->ce_flags & htons(CE_VALID)))
+ updated->ce_flags &= ~htons(CE_VALID);
+
+ return updated;
+}
+
+int refresh_cache(unsigned int flags)
+{
+ int i;
+ int has_errors = 0;
+ int really = (flags & REFRESH_REALLY) != 0;
+ int allow_unmerged = (flags & REFRESH_UNMERGED) != 0;
+ int quiet = (flags & REFRESH_QUIET) != 0;
+ int not_new = (flags & REFRESH_IGNORE_MISSING) != 0;
+
+ for (i = 0; i < active_nr; i++) {
+ struct cache_entry *ce, *new;
+ ce = active_cache[i];
+ if (ce_stage(ce)) {
+ while ((i < active_nr) &&
+ ! strcmp(active_cache[i]->name, ce->name))
+ i++;
+ i--;
+ if (allow_unmerged)
+ continue;
+ printf("%s: needs merge\n", ce->name);
+ has_errors = 1;
+ continue;
+ }
+
+ new = refresh_entry(ce, really);
+ if (!new)
+ continue;
+ if (IS_ERR(new)) {
+ if (not_new && PTR_ERR(new) == -ENOENT)
+ continue;
+ if (really && PTR_ERR(new) == -EINVAL) {
+ /* If we are doing --really-refresh that
+ * means the index is not valid anymore.
+ */
+ ce->ce_flags &= ~htons(CE_VALID);
+ active_cache_changed = 1;
+ }
+ if (quiet)
+ continue;
+ printf("%s: needs update\n", ce->name);
+ has_errors = 1;
+ continue;
+ }
+ active_cache_changed = 1;
+ /* You can NOT just free active_cache[i] here, since it
+ * might not be necessarily malloc()ed but can also come
+ * from mmap(). */
+ active_cache[i] = new;
+ }
+ return has_errors;
+}
+
static int verify_hdr(struct cache_header *hdr, unsigned long size)
{
SHA_CTX c;
return 0;
}
+static int read_index_extension(const char *ext, void *data, unsigned long sz)
+{
+ switch (CACHE_EXT(ext)) {
+ case CACHE_EXT_TREE:
+ active_cache_tree = cache_tree_read(data, sz);
+ break;
+ default:
+ if (*ext < 'A' || 'Z' < *ext)
+ return error("index uses %.4s extension, which we do not understand",
+ ext);
+ fprintf(stderr, "ignoring %.4s extension\n", ext);
+ break;
+ }
+ return 0;
+}
+
int read_cache(void)
{
int fd, i;
return active_nr;
errno = ENOENT;
+ index_file_timestamp = 0;
fd = open(get_index_file(), O_RDONLY);
if (fd < 0) {
if (errno == ENOENT)
active_nr = ntohl(hdr->hdr_entries);
active_alloc = alloc_nr(active_nr);
- active_cache = calloc(active_alloc, sizeof(struct cache_entry *));
+ active_cache = xcalloc(active_alloc, sizeof(struct cache_entry *));
offset = sizeof(*hdr);
for (i = 0; i < active_nr; i++) {
offset = offset + ce_size(ce);
active_cache[i] = ce;
}
+ index_file_timestamp = st.st_mtime;
+ while (offset <= 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, map + offset + 4, 4);
+ extsize = ntohl(extsize);
+ if (read_index_extension(map + offset,
+ map + offset + 8, extsize) < 0)
+ goto unmap;
+ offset += 8;
+ offset += extsize;
+ }
return active_nr;
unmap:
return 0;
}
+static int write_index_ext_header(SHA_CTX *context, int fd,
+ unsigned int ext, unsigned int sz)
+{
+ ext = htonl(ext);
+ sz = htonl(sz);
+ if ((ce_write(context, fd, &ext, 4) < 0) ||
+ (ce_write(context, fd, &sz, 4) < 0))
+ return -1;
+ return 0;
+}
+
static int ce_flush(SHA_CTX *context, int fd)
{
unsigned int left = write_buffer_len;
return 0;
}
+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.
+ */
+ struct stat st;
+
+ if (lstat(ce->name, &st) < 0)
+ return;
+ if (ce_match_stat_basic(ce, &st))
+ return;
+ if (ce_modified_check_fs(ce, &st)) {
+ /* This is "racily clean"; smudge it. Note that this
+ * is a tricky code. At first glance, it may appear
+ * that it can break with this sequence:
+ *
+ * $ echo xyzzy >frotz
+ * $ git-update-index --add frotz
+ * $ : >frotz
+ * $ sleep 3
+ * $ echo filfre >nitfol
+ * $ git-update-index --add nitfol
+ *
+ * but it does not. Whe the second update-index runs,
+ * it notices that the entry "frotz" has the same timestamp
+ * as index, and if we were to smudge it by resetting its
+ * size to zero here, then the object name recorded
+ * in index is the 6-byte file but the cached stat information
+ * becomes zero --- which would then match what we would
+ * obtain from the filesystem next time we stat("frotz").
+ *
+ * However, the second update-index, before calling
+ * this function, notices that the cached size is 6
+ * bytes and what is on the filesystem is an empty
+ * 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);
+ }
+}
+
int write_cache(int newfd, struct cache_entry **cache, int entries)
{
SHA_CTX c;
struct cache_entry *ce = cache[i];
if (!ce->ce_mode)
continue;
+ if (index_file_timestamp &&
+ index_file_timestamp <= ntohl(ce->ce_mtime.sec))
+ ce_smudge_racily_clean_entry(ce);
if (ce_write(&c, newfd, ce, ce_size(ce)) < 0)
return -1;
}
+
+ /* Write extension data here */
+ if (active_cache_tree) {
+ unsigned long sz;
+ void *data = cache_tree_write(active_cache_tree, &sz);
+ if (data &&
+ !write_index_ext_header(&c, newfd, CACHE_EXT_TREE, sz) &&
+ !ce_write(&c, newfd, data, sz))
+ ;
+ else {
+ free(data);
+ return -1;
+ }
+ }
return ce_flush(&c, newfd);
}