Sync with 1.8.1 maintenance track

* maint-1.8.1:
  Start preparing for 1.8.1.6
  git-tag(1): we tag HEAD by default
  Fix revision walk for commits with the same dates
  t2003: work around path mangling issue on Windows
  pack-refs: add fully-peeled trait
  pack-refs: write peeled entry for non-tags
  use parse_object_or_die instead of die("bad object")
  avoid segfaults on parse_object failure
  entry: fix filter lookup
  t2003: modernize style
  name-hash.c: fix endless loop with core.ignorecase=true

Author: gitster

Documentation/RelNotes/1.8.1.6.txt

@@ -0,0 +1,34 @@
+Git 1.8.1.6 Release Notes
+=========================
+
+Fixes since v1.8.1.5
+--------------------
+
+ * The code to keep track of what directory names are known to Git on
+   platforms with case insensitive filesystems can get confused upon a
+   hash collision between these pathnames and looped forever.
+
+ * When the "--prefix" option is used to "checkout-index", the code
+   did not pick the correct output filter based on the attribute
+   setting.
+
+ * Annotated tags outside refs/tags/ hierarchy were not advertised
+   correctly to the ls-remote and fetch with recent version of Git.
+
+ * The logic used by "git diff -M --stat" to shorten the names of
+   files before and after a rename did not work correctly when the
+   common prefix and suffix between the two filenames overlapped.
+
+ * "git update-index -h" did not do the usual "-h(elp)" thing.
+
+ * perl/Git.pm::cat_blob slurped everything in core only to write it
+   out to a file descriptor, which was not a very smart thing to do.
+
+ * The SSL peer verification done by "git imap-send" did not ask for
+   Server Name Indication (RFC 4366), failing to connect SSL/TLS
+   sites that serve multiple hostnames on a single IP.
+
+ * "git bundle verify" did not say "records a complete history" for a
+   bundle that does not have any prerequisites.
+
+Also contains various documentation fixes.

Documentation/git-tag.txt

@@ -126,6 +126,12 @@ This option is only applicable when listing tags without annotation lines.
 	linkgit:git-check-ref-format[1].  Some of these checks
 	may restrict the characters allowed in a tag name.
 
+<commit>::
+<object>::
+	The object that the new tag will refer to, usually a commit.
+	Defaults to HEAD.
+
+
 CONFIGURATION
 -------------
 By default, 'git tag' in sign-with-default mode (-s) will use your

builtin/grep.c

@@ -820,9 +820,7 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 		unsigned char sha1[20];
 		/* Is it a rev? */
 		if (!get_sha1(arg, sha1)) {
-			struct object *object = parse_object(sha1);
-			if (!object)
-				die(_("bad object %s"), arg);
+			struct object *object = parse_object_or_die(sha1, arg);
 			if (!seen_dashdash)
 				verify_non_filename(prefix, arg);
 			add_object_array(object, arg, &list);

builtin/prune.c

@@ -149,9 +149,7 @@ int cmd_prune(int argc, const char **argv, const char *prefix)
 		const char *name = *argv++;
 
 		if (!get_sha1(name, sha1)) {
-			struct object *object = parse_object(sha1);
-			if (!object)
-				die("bad object: %s", name);
+			struct object *object = parse_object_or_die(sha1, name);
 			add_pending_object(&revs, object, "");
 		}
 		else

bundle.c

@@ -279,12 +279,12 @@ int create_bundle(struct bundle_header *header, const char *path,
 		if (buf.len > 0 && buf.buf[0] == '-') {
 			write_or_die(bundle_fd, buf.buf, buf.len);
 			if (!get_sha1_hex(buf.buf + 1, sha1)) {
-				struct object *object = parse_object(sha1);
+				struct object *object = parse_object_or_die(sha1, buf.buf);
 				object->flags |= UNINTERESTING;
 				add_pending_object(&revs, object, xstrdup(buf.buf));
 			}
 		} else if (!get_sha1_hex(buf.buf, sha1)) {
-			struct object *object = parse_object(sha1);
+			struct object *object = parse_object_or_die(sha1, buf.buf);
 			object->flags |= SHOWN;
 		}
 	}
@@ -361,7 +361,7 @@ int create_bundle(struct bundle_header *header, const char *path,
 				 * end up triggering "empty bundle"
 				 * error.
 				 */
-				obj = parse_object(sha1);
+				obj = parse_object_or_die(sha1, e->name);
 				obj->flags |= SHOWN;
 				add_pending_object(&revs, obj, e->name);
 			}

cache.h

@@ -131,7 +131,6 @@ struct cache_entry {
 	unsigned int ce_namelen;
 	unsigned char sha1[20];
 	struct cache_entry *next;
-	struct cache_entry *dir_next;
 	char name[FLEX_ARRAY]; /* more */
 };
 
@@ -267,25 +266,15 @@ struct index_state {
 	unsigned name_hash_initialized : 1,
 		 initialized : 1;
 	struct hash_table name_hash;
+	struct hash_table dir_hash;
 };
 
 extern struct index_state the_index;
 
 /* Name hashing */
 extern void add_name_hash(struct index_state *istate, struct cache_entry *ce);
-/*
- * We don't actually *remove* it, we can just mark it invalid so that
- * we won't find it in lookups.
- *
- * Not only would we have to search the lists (simple enough), but
- * we'd also have to rehash other hash buckets in case this makes the
- * hash bucket empty (common). So it's much better to just mark
- * it.
- */
-static inline void remove_name_hash(struct cache_entry *ce)
-{
-	ce->ce_flags |= CE_UNHASHED;
-}
+extern void remove_name_hash(struct index_state *istate, struct cache_entry *ce);
+extern void free_name_hash(struct index_state *istate);
 
 
 #ifndef NO_THE_INDEX_COMPATIBILITY_MACROS

entry.c

@@ -145,7 +145,7 @@ static int write_entry(struct cache_entry *ce, char *path, const struct checkout
 	struct stat st;
 
 	if (ce_mode_s_ifmt == S_IFREG) {
-		struct stream_filter *filter = get_stream_filter(path, ce->sha1);
+		struct stream_filter *filter = get_stream_filter(ce->name, ce->sha1);
 		if (filter &&
 		    !streaming_write_entry(ce, path, filter,
 					   state, to_tempfile,

name-hash.c

@@ -32,38 +32,96 @@ static unsigned int hash_name(const char *name, int namelen)
 	return hash;
 }
 
-static void hash_index_entry_directories(struct index_state *istate, struct cache_entry *ce)
+struct dir_entry {
+	struct dir_entry *next;
+	struct dir_entry *parent;
+	struct cache_entry *ce;
+	int nr;
+	unsigned int namelen;
+};
+
+static struct dir_entry *find_dir_entry(struct index_state *istate,
+		const char *name, unsigned int namelen)
+{
+	unsigned int hash = hash_name(name, namelen);
+	struct dir_entry *dir;
+
+	for (dir = lookup_hash(hash, &istate->dir_hash); dir; dir = dir->next)
+		if (dir->namelen == namelen &&
+		    !strncasecmp(dir->ce->name, name, namelen))
+			return dir;
+	return NULL;
+}
+
+static struct dir_entry *hash_dir_entry(struct index_state *istate,
+		struct cache_entry *ce, int namelen)
 {
 	/*
 	 * Throw each directory component in the hash for quick lookup
 	 * during a git status. Directory components are stored with their
 	 * closing slash.  Despite submodules being a directory, they never
 	 * reach this point, because they are stored without a closing slash
-	 * in the cache.
+	 * in index_state.name_hash (as ordinary cache_entries).
 	 *
-	 * Note that the cache_entry stored with the directory does not
-	 * represent the directory itself.  It is a pointer to an existing
-	 * filename, and its only purpose is to represent existence of the
-	 * directory in the cache.  It is very possible multiple directory
-	 * hash entries may point to the same cache_entry.
+	 * Note that the cache_entry stored with the dir_entry merely
+	 * supplies the name of the directory (up to dir_entry.namelen). We
+	 * track the number of 'active' files in a directory in dir_entry.nr,
+	 * so we can tell if the directory is still relevant, e.g. for git
+	 * status. However, if cache_entries are removed, we cannot pinpoint
+	 * an exact cache_entry that's still active. It is very possible that
+	 * multiple dir_entries point to the same cache_entry.
 	 */
-	unsigned int hash;
-	void **pos;
+	struct dir_entry *dir;
+
+	/* get length of parent directory */
+	while (namelen > 0 && !is_dir_sep(ce->name[namelen - 1]))
+		namelen--;
+	if (namelen <= 0)
+		return NULL;
+
+	/* lookup existing entry for that directory */
+	dir = find_dir_entry(istate, ce->name, namelen);
+	if (!dir) {
+		/* not found, create it and add to hash table */
+		void **pdir;
+		unsigned int hash = hash_name(ce->name, namelen);
 
-	const char *ptr = ce->name;
-	while (*ptr) {
-		while (*ptr && *ptr != '/')
-			++ptr;
-		if (*ptr == '/') {
-			++ptr;
-			hash = hash_name(ce->name, ptr - ce->name);
-			pos = insert_hash(hash, ce, &istate->name_hash);
-			if (pos) {
-				ce->dir_next = *pos;
-				*pos = ce;
-			}
+		dir = xcalloc(1, sizeof(struct dir_entry));
+		dir->namelen = namelen;
+		dir->ce = ce;
+
+		pdir = insert_hash(hash, dir, &istate->dir_hash);
+		if (pdir) {
+			dir->next = *pdir;
+			*pdir = dir;
 		}
+
+		/* recursively add missing parent directories */
+		dir->parent = hash_dir_entry(istate, ce, namelen - 1);
 	}
+	return dir;
+}
+
+static void add_dir_entry(struct index_state *istate, struct cache_entry *ce)
+{
+	/* Add reference to the directory entry (and parents if 0). */
+	struct dir_entry *dir = hash_dir_entry(istate, ce, ce_namelen(ce));
+	while (dir && !(dir->nr++))
+		dir = dir->parent;
+}
+
+static void remove_dir_entry(struct index_state *istate, struct cache_entry *ce)
+{
+	/*
+	 * Release reference to the directory entry (and parents if 0).
+	 *
+	 * Note: we do not remove / free the entry because there's no
+	 * hash.[ch]::remove_hash and dir->next may point to other entries
+	 * that are still valid, so we must not free the memory.
+	 */
+	struct dir_entry *dir = hash_dir_entry(istate, ce, ce_namelen(ce));
+	while (dir && dir->nr && !(--dir->nr))
+		dir = dir->parent;
 }
 
 static void hash_index_entry(struct index_state *istate, struct cache_entry *ce)
@@ -74,16 +132,16 @@ static void hash_index_entry(struct index_state *istate, struct cache_entry *ce)
 	if (ce->ce_flags & CE_HASHED)
 		return;
 	ce->ce_flags |= CE_HASHED;
-	ce->next = ce->dir_next = NULL;
+	ce->next = NULL;
 	hash = hash_name(ce->name, ce_namelen(ce));
 	pos = insert_hash(hash, ce, &istate->name_hash);
 	if (pos) {
 		ce->next = *pos;
 		*pos = ce;
 	}
 
-	if (ignore_case)
-		hash_index_entry_directories(istate, ce);
+	if (ignore_case && !(ce->ce_flags & CE_UNHASHED))
+		add_dir_entry(istate, ce);
 }
 
 static void lazy_init_name_hash(struct index_state *istate)
@@ -99,11 +157,33 @@ static void lazy_init_name_hash(struct index_state *istate)
 
 void add_name_hash(struct index_state *istate, struct cache_entry *ce)
 {
+	/* if already hashed, add reference to directory entries */
+	if (ignore_case && (ce->ce_flags & CE_STATE_MASK) == CE_STATE_MASK)
+		add_dir_entry(istate, ce);
+
 	ce->ce_flags &= ~CE_UNHASHED;
 	if (istate->name_hash_initialized)
 		hash_index_entry(istate, ce);
 }
 
+/*
+ * We don't actually *remove* it, we can just mark it invalid so that
+ * we won't find it in lookups.
+ *
+ * Not only would we have to search the lists (simple enough), but
+ * we'd also have to rehash other hash buckets in case this makes the
+ * hash bucket empty (common). So it's much better to just mark
+ * it.
+ */
+void remove_name_hash(struct index_state *istate, struct cache_entry *ce)
+{
+	/* if already hashed, release reference to directory entries */
+	if (ignore_case && (ce->ce_flags & CE_STATE_MASK) == CE_HASHED)
+		remove_dir_entry(istate, ce);
+
+	ce->ce_flags |= CE_UNHASHED;
+}
+
 static int slow_same_name(const char *name1, int len1, const char *name2, int len2)
 {
 	if (len1 != len2)
@@ -137,18 +217,7 @@ static int same_name(const struct cache_entry *ce, const char *name, int namelen
 	if (!icase)
 		return 0;
 
-	/*
-	 * If the entry we're comparing is a filename (no trailing slash), then compare
-	 * the lengths exactly.
-	 */
-	if (name[namelen - 1] != '/')
-		return slow_same_name(name, namelen, ce->name, len);
-
-	/*
-	 * For a directory, we point to an arbitrary cache_entry filename.  Just
-	 * make sure the directory portion matches.
-	 */
-	return slow_same_name(name, namelen, ce->name, namelen < len ? namelen : len);
+	return slow_same_name(name, namelen, ce->name, len);
 }
 
 struct cache_entry *index_name_exists(struct index_state *istate, const char *name, int namelen, int icase)
@@ -164,27 +233,54 @@ struct cache_entry *index_name_exists(struct index_state *istate, const char *na
 			if (same_name(ce, name, namelen, icase))
 				return ce;
 		}
-		if (icase && name[namelen - 1] == '/')
-			ce = ce->dir_next;
-		else
-			ce = ce->next;
+		ce = ce->next;
 	}
 
 	/*
-	 * Might be a submodule.  Despite submodules being directories,
+	 * When looking for a directory (trailing '/'), it might be a
+	 * submodule or a directory. Despite submodules being directories,
 	 * they are stored in the name hash without a closing slash.
-	 * When ignore_case is 1, directories are stored in the name hash
-	 * with their closing slash.
+	 * When ignore_case is 1, directories are stored in a separate hash
+	 * table *with* their closing slash.
 	 *
 	 * The side effect of this storage technique is we have need to
+	 * lookup the directory in a separate hash table, and if not found
 	 * remove the slash from name and perform the lookup again without
 	 * the slash.  If a match is made, S_ISGITLINK(ce->mode) will be
 	 * true.
 	 */
 	if (icase && name[namelen - 1] == '/') {
+		struct dir_entry *dir = find_dir_entry(istate, name, namelen);
+		if (dir && dir->nr)
+			return dir->ce;
+
 		ce = index_name_exists(istate, name, namelen - 1, icase);
 		if (ce && S_ISGITLINK(ce->ce_mode))
 			return ce;
 	}
 	return NULL;
 }
+
+static int free_dir_entry(void *entry, void *unused)
+{
+	struct dir_entry *dir = entry;
+	while (dir) {
+		struct dir_entry *next = dir->next;
+		free(dir);
+		dir = next;
+	}
+	return 0;
+}
+
+void free_name_hash(struct index_state *istate)
+{
+	if (!istate->name_hash_initialized)
+		return;
+	istate->name_hash_initialized = 0;
+	if (ignore_case)
+		/* free directory entries */
+		for_each_hash(&istate->dir_hash, free_dir_entry, NULL);
+
+	free_hash(&istate->name_hash);
+	free_hash(&istate->dir_hash);
+}