1 files changed, 262 insertions, 45 deletions

diff --git a/symlinks.c b/symlinks.c
index 5a5e781a15..8860120011 100644
--- a/symlinks.c
+++ b/symlinks.c
@@ -1,64 +1,281 @@
 #include "cache.h"
 
-struct pathname {
-	int len;
-	char path[PATH_MAX];
-};
-
-/* Return matching pathname prefix length, or zero if not matching */
-static inline int match_pathname(int len, const char *name, struct pathname *match)
+/*
+ * Returns the length (on a path component basis) of the longest
+ * common prefix match of 'name_a' and 'name_b'.
+ */
+static int longest_path_match(const char *name_a, int len_a,
+			      const char *name_b, int len_b,
+			      int *previous_slash)
 {
-	int match_len = match->len;
-	return (len > match_len &&
-		name[match_len] == '/' &&
-		!memcmp(name, match->path, match_len)) ? match_len : 0;
+	int max_len, match_len = 0, match_len_prev = 0, i = 0;
+
+	max_len = len_a < len_b ? len_a : len_b;
+	while (i < max_len && name_a[i] == name_b[i]) {
+		if (name_a[i] == '/') {
+			match_len_prev = match_len;
+			match_len = i;
+		}
+		i++;
+	}
+	/*
+	 * Is 'name_b' a substring of 'name_a', the other way around,
+	 * or is 'name_a' and 'name_b' the exact same string?
+	 */
+	if (i >= max_len && ((len_a > len_b && name_a[len_b] == '/') ||
+			     (len_a < len_b && name_b[len_a] == '/') ||
+			     (len_a == len_b))) {
+		match_len_prev = match_len;
+		match_len = i;
+	}
+	*previous_slash = match_len_prev;
+	return match_len;
 }
 
-static inline void set_pathname(int len, const char *name, struct pathname *match)
+static struct cache_def default_cache;
+
+static inline void reset_lstat_cache(struct cache_def *cache)
 {
-	if (len < PATH_MAX) {
-		match->len = len;
-		memcpy(match->path, name, len);
-		match->path[len] = 0;
-	}
+	cache->path[0] = '\0';
+	cache->len = 0;
+	cache->flags = 0;
+	/*
+	 * The track_flags and prefix_len_stat_func members is only
+	 * set by the safeguard rule inside lstat_cache()
+	 */
 }
 
-int has_symlink_leading_path(int len, const char *name)
+#define FL_DIR      (1 << 0)
+#define FL_NOENT    (1 << 1)
+#define FL_SYMLINK  (1 << 2)
+#define FL_LSTATERR (1 << 3)
+#define FL_ERR      (1 << 4)
+#define FL_FULLPATH (1 << 5)
+
+/*
+ * Check if name 'name' of length 'len' has a symlink leading
+ * component, or if the directory exists and is real, or not.
+ *
+ * To speed up the check, some information is allowed to be cached.
+ * This can be indicated by the 'track_flags' argument, which also can
+ * be used to indicate that we should check the full path.
+ *
+ * The 'prefix_len_stat_func' parameter can be used to set the length
+ * of the prefix, where the cache should use the stat() function
+ * instead of the lstat() function to test each path component.
+ */
+static int lstat_cache(struct cache_def *cache, const char *name, int len,
+		       int track_flags, int prefix_len_stat_func)
 {
-	static struct pathname link, nonlink;
-	char path[PATH_MAX];
+	int match_len, last_slash, last_slash_dir, previous_slash;
+	int match_flags, ret_flags, save_flags, max_len, ret;
 	struct stat st;
-	char *sp;
-	int known_dir;
 
-	/*
-	 * See if the last known symlink cache matches.
-	 */
-	if (match_pathname(len, name, &link))
-		return 1;
+	if (cache->track_flags != track_flags ||
+	    cache->prefix_len_stat_func != prefix_len_stat_func) {
+		/*
+		 * As a safeguard rule we clear the cache if the
+		 * values of track_flags and/or prefix_len_stat_func
+		 * does not match with the last supplied values.
+		 */
+		reset_lstat_cache(cache);
+		cache->track_flags = track_flags;
+		cache->prefix_len_stat_func = prefix_len_stat_func;
+		match_len = last_slash = 0;
+	} else {
+		/*
+		 * Check to see if we have a match from the cache for
+		 * the 2 "excluding" path types.
+		 */
+		match_len = last_slash =
+			longest_path_match(name, len, cache->path, cache->len,
+					   &previous_slash);
+		match_flags = cache->flags & track_flags & (FL_NOENT|FL_SYMLINK);
+
+		if (!(track_flags & FL_FULLPATH) && match_len == len)
+			match_len = last_slash = previous_slash;
+
+		if (match_flags && match_len == cache->len)
+			return match_flags;
+		/*
+		 * If we now have match_len > 0, we would know that
+		 * the matched part will always be a directory.
+		 *
+		 * Also, if we are tracking directories and 'name' is
+		 * a substring of the cache on a path component basis,
+		 * we can return immediately.
+		 */
+		match_flags = track_flags & FL_DIR;
+		if (match_flags && len == match_len)
+			return match_flags;
+	}
 
 	/*
-	 * Get rid of the last known directory part
+	 * Okay, no match from the cache so far, so now we have to
+	 * check the rest of the path components.
 	 */
-	known_dir = match_pathname(len, name, &nonlink);
-
-	while ((sp = strchr(name + known_dir + 1, '/')) != NULL) {
-		int thislen = sp - name ;
-		memcpy(path, name, thislen);
-		path[thislen] = 0;
-
-		if (lstat(path, &st))
-			return 0;
-		if (S_ISDIR(st.st_mode)) {
-			set_pathname(thislen, path, &nonlink);
-			known_dir = thislen;
+	ret_flags = FL_DIR;
+	last_slash_dir = last_slash;
+	max_len = len < PATH_MAX ? len : PATH_MAX;
+	while (match_len < max_len) {
+		do {
+			cache->path[match_len] = name[match_len];
+			match_len++;
+		} while (match_len < max_len && name[match_len] != '/');
+		if (match_len >= max_len && !(track_flags & FL_FULLPATH))
+			break;
+		last_slash = match_len;
+		cache->path[last_slash] = '\0';
+
+		if (last_slash <= prefix_len_stat_func)
+			ret = stat(cache->path, &st);
+		else
+			ret = lstat(cache->path, &st);
+
+		if (ret) {
+			ret_flags = FL_LSTATERR;
+			if (errno == ENOENT)
+				ret_flags |= FL_NOENT;
+		} else if (S_ISDIR(st.st_mode)) {
+			last_slash_dir = last_slash;
 			continue;
-		}
-		if (S_ISLNK(st.st_mode)) {
-			set_pathname(thislen, path, &link);
-			return 1;
+		} else if (S_ISLNK(st.st_mode)) {
+			ret_flags = FL_SYMLINK;
+		} else {
+			ret_flags = FL_ERR;
 		}
 		break;
 	}
-	return 0;
+
+	/*
+	 * At the end update the cache.  Note that max 3 different
+	 * path types, FL_NOENT, FL_SYMLINK and FL_DIR, can be cached
+	 * for the moment!
+	 */
+	save_flags = ret_flags & track_flags & (FL_NOENT|FL_SYMLINK);
+	if (save_flags && last_slash > 0 && last_slash <= PATH_MAX) {
+		cache->path[last_slash] = '\0';
+		cache->len = last_slash;
+		cache->flags = save_flags;
+	} else if ((track_flags & FL_DIR) &&
+		   last_slash_dir > 0 && last_slash_dir <= PATH_MAX) {
+		/*
+		 * We have a separate test for the directory case,
+		 * since it could be that we have found a symlink or a
+		 * non-existing directory and the track_flags says
+		 * that we cannot cache this fact, so the cache would
+		 * then have been left empty in this case.
+		 *
+		 * But if we are allowed to track real directories, we
+		 * can still cache the path components before the last
+		 * one (the found symlink or non-existing component).
+		 */
+		cache->path[last_slash_dir] = '\0';
+		cache->len = last_slash_dir;
+		cache->flags = FL_DIR;
+	} else {
+		reset_lstat_cache(cache);
+	}
+	return ret_flags;
+}
+
+#define USE_ONLY_LSTAT  0
+
+/*
+ * Return non-zero if path 'name' has a leading symlink component
+ */
+int threaded_has_symlink_leading_path(struct cache_def *cache, const char *name, int len)
+{
+	return lstat_cache(cache, name, len, FL_SYMLINK|FL_DIR, USE_ONLY_LSTAT) & FL_SYMLINK;
+}
+
+/*
+ * Return non-zero if path 'name' has a leading symlink component
+ */
+int has_symlink_leading_path(const char *name, int len)
+{
+	return threaded_has_symlink_leading_path(&default_cache, name, len);
+}
+
+/*
+ * Return non-zero if path 'name' has a leading symlink component or
+ * if some leading path component does not exists.
+ */
+int has_symlink_or_noent_leading_path(const char *name, int len)
+{
+	struct cache_def *cache = &default_cache;	/* FIXME */
+	return lstat_cache(cache, name, len,
+			   FL_SYMLINK|FL_NOENT|FL_DIR, USE_ONLY_LSTAT) &
+		(FL_SYMLINK|FL_NOENT);
+}
+
+/*
+ * Return non-zero if all path components of 'name' exists as a
+ * directory.  If prefix_len > 0, we will test with the stat()
+ * function instead of the lstat() function for a prefix length of
+ * 'prefix_len', thus we then allow for symlinks in the prefix part as
+ * long as those points to real existing directories.
+ */
+int has_dirs_only_path(const char *name, int len, int prefix_len)
+{
+	struct cache_def *cache = &default_cache;	/* FIXME */
+	return lstat_cache(cache, name, len,
+			   FL_DIR|FL_FULLPATH, prefix_len) &
+		FL_DIR;
+}
+
+static struct removal_def {
+	char path[PATH_MAX];
+	int len;
+} removal;
+
+static void do_remove_scheduled_dirs(int new_len)
+{
+	while (removal.len > new_len) {
+		removal.path[removal.len] = '\0';
+		if (rmdir(removal.path))
+			break;
+		do {
+			removal.len--;
+		} while (removal.len > new_len &&
+			 removal.path[removal.len] != '/');
+	}
+	removal.len = new_len;
+}
+
+void schedule_dir_for_removal(const char *name, int len)
+{
+	int match_len, last_slash, i, previous_slash;
+
+	match_len = last_slash = i =
+		longest_path_match(name, len, removal.path, removal.len,
+				   &previous_slash);
+	/* Find last slash inside 'name' */
+	while (i < len) {
+		if (name[i] == '/')
+			last_slash = i;
+		i++;
+	}
+
+	/*
+	 * If we are about to go down the directory tree, we check if
+	 * we must first go upwards the tree, such that we then can
+	 * remove possible empty directories as we go upwards.
+	 */
+	if (match_len < last_slash && match_len < removal.len)
+		do_remove_scheduled_dirs(match_len);
+	/*
+	 * If we go deeper down the directory tree, we only need to
+	 * save the new path components as we go down.
+	 */
+	if (match_len < last_slash) {
+		memcpy(&removal.path[match_len], &name[match_len],
+		       last_slash - match_len);
+		removal.len = last_slash;
+	}
+}
+
+void remove_scheduled_dirs(void)
+{
+	do_remove_scheduled_dirs(0);
 }