Merge branch 'kb/lstat-cache'

* kb/lstat-cache:
  lstat_cache(): introduce clear_lstat_cache() function
  lstat_cache(): introduce invalidate_lstat_cache() function
  lstat_cache(): introduce has_dirs_only_path() function
  lstat_cache(): introduce has_symlink_or_noent_leading_path() function
  lstat_cache(): more cache effective symlink/directory detection

4 files changed, 238 insertions, 67 deletions

diff --git a/cache.h b/cache.h
index c96854a0d6..c17fbf58a7 100644
--- a/cache.h
+++ b/cache.h
@@ -721,6 +721,10 @@ struct checkout {
 
 extern int checkout_entry(struct cache_entry *ce, const struct checkout *state, char *topath);
 extern int has_symlink_leading_path(int len, const char *name);
+extern int has_symlink_or_noent_leading_path(int len, const char *name);
+extern int has_dirs_only_path(int len, const char *name, int prefix_len);
+extern void invalidate_lstat_cache(int len, const char *name);
+extern void clear_lstat_cache(void);
 
 extern struct alternate_object_database {
 	struct alternate_object_database *next;
diff --git a/entry.c b/entry.c
index 5f24816eb9..05aa58d348 100644
--- a/entry.c
+++ b/entry.c
@@ -9,35 +9,25 @@ static void create_directories(const char *path, const struct checkout *state)
 	const char *slash = path;
 
 	while ((slash = strchr(slash+1, '/')) != NULL) {
-		struct stat st;
-		int stat_status;
-
 		len = slash - path;
 		memcpy(buf, path, len);
 		buf[len] = 0;
 
-		if (len <= state->base_dir_len)
-			/*
-			 * checkout-index --prefix=<dir>; <dir> is
-			 * allowed to be a symlink to an existing
-			 * directory.
-			 */
-			stat_status = stat(buf, &st);
-		else
-			/*
-			 * if there currently is a symlink, we would
-			 * want to replace it with a real directory.
-			 */
-			stat_status = lstat(buf, &st);
-
-		if (!stat_status && S_ISDIR(st.st_mode))
+		/*
+		 * For 'checkout-index --prefix=<dir>', <dir> is
+		 * allowed to be a symlink to an existing directory,
+		 * and we set 'state->base_dir_len' below, such that
+		 * we test the path components of the prefix with the
+		 * stat() function instead of the lstat() function.
+		 */
+		if (has_dirs_only_path(len, buf, state->base_dir_len))
 			continue; /* ok, it is already a directory. */
 
 		/*
-		 * We know stat_status == 0 means something exists
-		 * there and this mkdir would fail, but that is an
-		 * error codepath; we do not care, as we unlink and
-		 * mkdir again in such a case.
+		 * If this mkdir() would fail, it could be that there
+		 * is already a symlink or something else exists
+		 * there, therefore we then try to unlink it and try
+		 * one more time to create the directory.
 		 */
 		if (mkdir(buf, 0777)) {
 			if (errno == EEXIST && state->force &&
diff --git a/symlinks.c b/symlinks.c
index 5a5e781a15..f262b7c44b 100644
--- a/symlinks.c
+++ b/symlinks.c
@@ -1,64 +1,241 @@
 #include "cache.h"
 
-struct pathname {
+static struct cache_def {
+	char path[PATH_MAX + 1];
 	int len;
-	char path[PATH_MAX];
-};
+	int flags;
+	int track_flags;
+	int prefix_len_stat_func;
+} cache;
 
-/* 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' and the cached path string.
+ */
+static inline int longest_match_lstat_cache(int len, const char *name,
+					    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 < cache.len ? len : cache.len;
+	while (i < max_len && name[i] == cache.path[i]) {
+		if (name[i] == '/') {
+			match_len_prev = match_len;
+			match_len = i;
+		}
+		i++;
+	}
+	/* Is the cached path string a substring of 'name'? */
+	if (i == cache.len && cache.len < len && name[cache.len] == '/') {
+		match_len_prev = match_len;
+		match_len = cache.len;
+	/* Is 'name' a substring of the cached path string? */
+	} else if ((i == len && len < cache.len && cache.path[len] == '/') ||
+		   (i == len && len == cache.len)) {
+		match_len_prev = match_len;
+		match_len = len;
+	}
+	*previous_slash = match_len_prev;
+	return match_len;
 }
 
-static inline void set_pathname(int len, const char *name, struct pathname *match)
+static inline void reset_lstat_cache(int track_flags, int prefix_len_stat_func)
 {
-	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;
+	cache.track_flags = track_flags;
+	cache.prefix_len_stat_func = prefix_len_stat_func;
 }
 
-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(int len, const char *name,
+		       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 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(track_flags, 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_match_lstat_cache(len, name, &previous_slash);
+		match_flags = cache.flags & track_flags & (FL_NOENT|FL_SYMLINK);
+		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(track_flags, prefix_len_stat_func);
+	}
+	return ret_flags;
+}
+
+/*
+ * Invalidate the given 'name' from the cache, if 'name' matches
+ * completely with the cache.
+ */
+void invalidate_lstat_cache(int len, const char *name)
+{
+	int match_len, previous_slash;
+
+	match_len = longest_match_lstat_cache(len, name, &previous_slash);
+	if (len == match_len) {
+		if ((cache.track_flags & FL_DIR) && previous_slash > 0) {
+			cache.path[previous_slash] = '\0';
+			cache.len = previous_slash;
+			cache.flags = FL_DIR;
+		} else
+			reset_lstat_cache(cache.track_flags,
+					  cache.prefix_len_stat_func);
+	}
+}
+
+/*
+ * Completely clear the contents of the cache
+ */
+void clear_lstat_cache(void)
+{
+	reset_lstat_cache(0, 0);
+}
+
+#define USE_ONLY_LSTAT  0
+
+/*
+ * Return non-zero if path 'name' has a leading symlink component
+ */
+int has_symlink_leading_path(int len, const char *name)
+{
+	return lstat_cache(len, name,
+			   FL_SYMLINK|FL_DIR, USE_ONLY_LSTAT) &
+		FL_SYMLINK;
+}
+
+/*
+ * 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(int len, const char *name)
+{
+	return lstat_cache(len, name,
+			   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(int len, const char *name, int prefix_len)
+{
+	return lstat_cache(len, name,
+			   FL_DIR|FL_FULLPATH, prefix_len) &
+		FL_DIR;
 }
diff --git a/unpack-trees.c b/unpack-trees.c
index 15c9ef592b..16bc2ca9eb 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -61,7 +61,7 @@ static void unlink_entry(struct cache_entry *ce)
 	char *cp, *prev;
 	char *name = ce->name;
 
-	if (has_symlink_leading_path(ce_namelen(ce), ce->name))
+	if (has_symlink_or_noent_leading_path(ce_namelen(ce), ce->name))
 		return;
 	if (unlink(name))
 		return;
@@ -580,7 +580,7 @@ static int verify_absent(struct cache_entry *ce, const char *action,
 	if (o->index_only || o->reset || !o->update)
 		return 0;
 
-	if (has_symlink_leading_path(ce_namelen(ce), ce->name))
+	if (has_symlink_or_noent_leading_path(ce_namelen(ce), ce->name))
 		return 0;
 
 	if (!lstat(ce->name, &st)) {