Merge branch 'lt/in-core-index'

* lt/in-core-index:
  lazy index hashing
  Create pathname-based hash-table lookup into index
  read-cache.c: introduce is_racy_timestamp() helper
  read-cache.c: fix a couple more CE_REMOVE conversion
  Also use unpack_trees() in do_diff_cache()
  Make run_diff_index() use unpack_trees(), not read_tree()
  Avoid running lstat(2) on the same cache entry.
  index: be careful when handling long names
  Make on-disk index representation separate from in-core one

builtin-apply.c

@@ -1946,7 +1946,7 @@ static int read_file_or_gitlink(struct cache_entry *ce, struct strbuf *buf)
 	if (!ce)
 		return 0;
 
-	if (S_ISGITLINK(ntohl(ce->ce_mode))) {
+	if (S_ISGITLINK(ce->ce_mode)) {
 		strbuf_grow(buf, 100);
 		strbuf_addf(buf, "Subproject commit %s\n", sha1_to_hex(ce->sha1));
 	} else {
@@ -2023,7 +2023,7 @@ static int check_to_create_blob(const char *new_name, int ok_if_exists)
 
 static int verify_index_match(struct cache_entry *ce, struct stat *st)
 {
-	if (S_ISGITLINK(ntohl(ce->ce_mode))) {
+	if (S_ISGITLINK(ce->ce_mode)) {
 		if (!S_ISDIR(st->st_mode))
 			return -1;
 		return 0;
@@ -2082,12 +2082,12 @@ static int check_patch(struct patch *patch, struct patch *prev_patch)
 				return error("%s: does not match index",
 					     old_name);
 			if (cached)
-				st_mode = ntohl(ce->ce_mode);
+				st_mode = ce->ce_mode;
 		} else if (stat_ret < 0)
 			return error("%s: %s", old_name, strerror(errno));
 
 		if (!cached)
-			st_mode = ntohl(ce_mode_from_stat(ce, st.st_mode));
+			st_mode = ce_mode_from_stat(ce, st.st_mode);
 
 		if (patch->is_new < 0)
 			patch->is_new = 0;
@@ -2388,7 +2388,7 @@ static void add_index_file(const char *path, unsigned mode, void *buf, unsigned
 	ce = xcalloc(1, ce_size);
 	memcpy(ce->name, path, namelen);
 	ce->ce_mode = create_ce_mode(mode);
-	ce->ce_flags = htons(namelen);
+	ce->ce_flags = namelen;
 	if (S_ISGITLINK(mode)) {
 		const char *s = buf;
 

builtin-blame.c

@@ -2092,7 +2092,7 @@ static struct commit *fake_working_tree_commit(const char *path, const char *con
 	if (!mode) {
 		int pos = cache_name_pos(path, len);
 		if (0 <= pos)
-			mode = ntohl(active_cache[pos]->ce_mode);
+			mode = active_cache[pos]->ce_mode;
 		else
 			/* Let's not bother reading from HEAD tree */
 			mode = S_IFREG | 0644;

builtin-commit.c

@@ -160,7 +160,7 @@ static int list_paths(struct path_list *list, const char *with_tree,
 
 	for (i = 0; i < active_nr; i++) {
 		struct cache_entry *ce = active_cache[i];
-		if (ce->ce_flags & htons(CE_UPDATE))
+		if (ce->ce_flags & CE_UPDATE)
 			continue;
 		if (!pathspec_match(pattern, m, ce->name, 0))
 			continue;

builtin-fsck.c

@@ -765,7 +765,7 @@ int cmd_fsck(int argc, const char **argv, const char *prefix)
 			struct blob *blob;
 			struct object *obj;
 
-			mode = ntohl(active_cache[i]->ce_mode);
+			mode = active_cache[i]->ce_mode;
 			if (S_ISGITLINK(mode))
 				continue;
 			blob = lookup_blob(active_cache[i]->sha1);

builtin-grep.c

@@ -331,7 +331,7 @@ static int external_grep(struct grep_opt *opt, const char **paths, int cached)
 		struct cache_entry *ce = active_cache[i];
 		char *name;
 		int kept;
-		if (!S_ISREG(ntohl(ce->ce_mode)))
+		if (!S_ISREG(ce->ce_mode))
 			continue;
 		if (!pathspec_matches(paths, ce->name))
 			continue;
@@ -387,7 +387,7 @@ static int grep_cache(struct grep_opt *opt, const char **paths, int cached)
 
 	for (nr = 0; nr < active_nr; nr++) {
 		struct cache_entry *ce = active_cache[nr];
-		if (!S_ISREG(ntohl(ce->ce_mode)))
+		if (!S_ISREG(ce->ce_mode))
 			continue;
 		if (!pathspec_matches(paths, ce->name))
 			continue;

builtin-ls-files.c

@@ -189,7 +189,7 @@ static void show_ce_entry(const char *tag, struct cache_entry *ce)
 		return;
 
 	if (tag && *tag && show_valid_bit &&
-	    (ce->ce_flags & htons(CE_VALID))) {
+	    (ce->ce_flags & CE_VALID)) {
 		static char alttag[4];
 		memcpy(alttag, tag, 3);
 		if (isalpha(tag[0]))
@@ -210,7 +210,7 @@ static void show_ce_entry(const char *tag, struct cache_entry *ce)
 	} else {
 		printf("%s%06o %s %d\t",
 		       tag,
-		       ntohl(ce->ce_mode),
+		       ce->ce_mode,
 		       abbrev ? find_unique_abbrev(ce->sha1,abbrev)
 				: sha1_to_hex(ce->sha1),
 		       ce_stage(ce));
@@ -242,7 +242,7 @@ static void show_files(struct dir_struct *dir, const char *prefix)
 				continue;
 			if (show_unmerged && !ce_stage(ce))
 				continue;
-			if (ce->ce_flags & htons(CE_UPDATE))
+			if (ce->ce_flags & CE_UPDATE)
 				continue;
 			show_ce_entry(ce_stage(ce) ? tag_unmerged : tag_cached, ce);
 		}
@@ -350,7 +350,7 @@ void overlay_tree_on_cache(const char *tree_name, const char *prefix)
 		struct cache_entry *ce = active_cache[i];
 		if (!ce_stage(ce))
 			continue;
-		ce->ce_flags |= htons(CE_STAGEMASK);
+		ce->ce_flags |= CE_STAGEMASK;
 	}
 
 	if (prefix) {
@@ -379,7 +379,7 @@ void overlay_tree_on_cache(const char *tree_name, const char *prefix)
 			 */
 			if (last_stage0 &&
 			    !strcmp(last_stage0->name, ce->name))
-				ce->ce_flags |= htons(CE_UPDATE);
+				ce->ce_flags |= CE_UPDATE;
 		}
 	}
 }

builtin-read-tree.c

@@ -45,8 +45,7 @@ static int read_cache_unmerged(void)
 				continue;
 			cache_tree_invalidate_path(active_cache_tree, ce->name);
 			last = ce;
-			ce->ce_mode = 0;
-			ce->ce_flags &= ~htons(CE_STAGEMASK);
+			ce->ce_flags |= CE_REMOVE;
 		}
 		*dst++ = ce;
 	}

builtin-rerere.c

@@ -149,8 +149,8 @@ static int find_conflict(struct path_list *conflict)
 		if (ce_stage(e2) == 2 &&
 		    ce_stage(e3) == 3 &&
 		    ce_same_name(e2, e3) &&
-		    S_ISREG(ntohl(e2->ce_mode)) &&
-		    S_ISREG(ntohl(e3->ce_mode))) {
+		    S_ISREG(e2->ce_mode) &&
+		    S_ISREG(e3->ce_mode)) {
 			path_list_insert((const char *)e2->name, conflict);
 			i++; /* skip over both #2 and #3 */
 		}

builtin-update-index.c

@@ -47,10 +47,10 @@ static int mark_valid(const char *path)
 	if (0 <= pos) {
 		switch (mark_valid_only) {
 		case MARK_VALID:
-			active_cache[pos]->ce_flags |= htons(CE_VALID);
+			active_cache[pos]->ce_flags |= CE_VALID;
 			break;
 		case UNMARK_VALID:
-			active_cache[pos]->ce_flags &= ~htons(CE_VALID);
+			active_cache[pos]->ce_flags &= ~CE_VALID;
 			break;
 		}
 		cache_tree_invalidate_path(active_cache_tree, path);
@@ -95,7 +95,7 @@ static int add_one_path(struct cache_entry *old, const char *path, int len, stru
 	size = cache_entry_size(len);
 	ce = xcalloc(1, size);
 	memcpy(ce->name, path, len);
-	ce->ce_flags = htons(len);
+	ce->ce_flags = len;
 	fill_stat_cache_info(ce, st);
 	ce->ce_mode = ce_mode_from_stat(old, st->st_mode);
 
@@ -139,7 +139,7 @@ static int process_directory(const char *path, int len, struct stat *st)
 	/* Exact match: file or existing gitlink */
 	if (pos >= 0) {
 		struct cache_entry *ce = active_cache[pos];
-		if (S_ISGITLINK(ntohl(ce->ce_mode))) {
+		if (S_ISGITLINK(ce->ce_mode)) {
 
 			/* Do nothing to the index if there is no HEAD! */
 			if (resolve_gitlink_ref(path, "HEAD", sha1) < 0)
@@ -183,7 +183,7 @@ static int process_file(const char *path, int len, struct stat *st)
 	int pos = cache_name_pos(path, len);
 	struct cache_entry *ce = pos < 0 ? NULL : active_cache[pos];
 
-	if (ce && S_ISGITLINK(ntohl(ce->ce_mode)))
+	if (ce && S_ISGITLINK(ce->ce_mode))
 		return error("%s is already a gitlink, not replacing", path);
 
 	return add_one_path(ce, path, len, st);
@@ -226,7 +226,7 @@ static int add_cacheinfo(unsigned int mode, const unsigned char *sha1,
 	ce->ce_flags = create_ce_flags(len, stage);
 	ce->ce_mode = create_ce_mode(mode);
 	if (assume_unchanged)
-		ce->ce_flags |= htons(CE_VALID);
+		ce->ce_flags |= CE_VALID;
 	option = allow_add ? ADD_CACHE_OK_TO_ADD : 0;
 	option |= allow_replace ? ADD_CACHE_OK_TO_REPLACE : 0;
 	if (add_cache_entry(ce, option))
@@ -246,14 +246,14 @@ static void chmod_path(int flip, const char *path)
 	if (pos < 0)
 		goto fail;
 	ce = active_cache[pos];
-	mode = ntohl(ce->ce_mode);
+	mode = ce->ce_mode;
 	if (!S_ISREG(mode))
 		goto fail;
 	switch (flip) {
 	case '+':
-		ce->ce_mode |= htonl(0111); break;
+		ce->ce_mode |= 0111; break;
 	case '-':
-		ce->ce_mode &= htonl(~0111); break;
+		ce->ce_mode &= ~0111; break;
 	default:
 		goto fail;
 	}

cache-tree.c

@@ -320,13 +320,13 @@ static int update_one(struct cache_tree *it,
 		}
 		else {
 			sha1 = ce->sha1;
-			mode = ntohl(ce->ce_mode);
+			mode = ce->ce_mode;
 			entlen = pathlen - baselen;
 		}
 		if (mode != S_IFGITLINK && !missing_ok && !has_sha1_file(sha1))
 			return error("invalid object %s", sha1_to_hex(sha1));
 
-		if (!ce->ce_mode)
+		if (ce->ce_flags & CE_REMOVE)
 			continue; /* entry being removed */
 
 		strbuf_grow(&buffer, entlen + 100);

cache.h

@@ -3,6 +3,7 @@
 
 #include "git-compat-util.h"
 #include "strbuf.h"
+#include "hash.h"
 
 #include SHA1_HEADER
 #include <zlib.h>
@@ -94,48 +95,84 @@ struct cache_time {
  * 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;
+	unsigned int dev;
+	unsigned int ino;
+	unsigned int mode;
+	unsigned int uid;
+	unsigned int gid;
+	unsigned int size;
+	unsigned char sha1[20];
+	unsigned short flags;
+	char name[FLEX_ARRAY]; /* more */
+};
+
 struct cache_entry {
-	struct cache_time ce_ctime;
-	struct cache_time ce_mtime;
+	struct cache_entry *next;
+	unsigned int ce_ctime;
+	unsigned int ce_mtime;
 	unsigned int ce_dev;
 	unsigned int ce_ino;
 	unsigned int ce_mode;
 	unsigned int ce_uid;
 	unsigned int ce_gid;
 	unsigned int ce_size;
+	unsigned int ce_flags;
 	unsigned char sha1[20];
-	unsigned short ce_flags;
 	char name[FLEX_ARRAY]; /* more */
 };
 
 #define CE_NAMEMASK  (0x0fff)
 #define CE_STAGEMASK (0x3000)
-#define CE_UPDATE    (0x4000)
 #define CE_VALID     (0x8000)
 #define CE_STAGESHIFT 12
 
-#define create_ce_flags(len, stage) htons((len) | ((stage) << CE_STAGESHIFT))
-#define ce_namelen(ce) (CE_NAMEMASK & ntohs((ce)->ce_flags))
+/* In-memory only */
+#define CE_UPDATE    (0x10000)
+#define CE_REMOVE    (0x20000)
+#define CE_UPTODATE  (0x40000)
+#define CE_UNHASHED  (0x80000)
+
+static inline unsigned create_ce_flags(size_t len, unsigned stage)
+{
+	if (len >= CE_NAMEMASK)
+		len = CE_NAMEMASK;
+	return (len | (stage << CE_STAGESHIFT));
+}
+
+static inline size_t ce_namelen(const struct cache_entry *ce)
+{
+	size_t len = ce->ce_flags & CE_NAMEMASK;
+	if (len < CE_NAMEMASK)
+		return len;
+	return strlen(ce->name + CE_NAMEMASK) + CE_NAMEMASK;
+}
+
 #define ce_size(ce) cache_entry_size(ce_namelen(ce))
-#define ce_stage(ce) ((CE_STAGEMASK & ntohs((ce)->ce_flags)) >> CE_STAGESHIFT)
+#define ondisk_ce_size(ce) ondisk_cache_entry_size(ce_namelen(ce))
+#define ce_stage(ce) ((CE_STAGEMASK & (ce)->ce_flags) >> CE_STAGESHIFT)
+#define ce_uptodate(ce) ((ce)->ce_flags & CE_UPTODATE)
+#define ce_mark_uptodate(ce) ((ce)->ce_flags |= CE_UPTODATE)
 
 #define ce_permissions(mode) (((mode) & 0100) ? 0755 : 0644)
 static inline unsigned int create_ce_mode(unsigned int mode)
 {
 	if (S_ISLNK(mode))
-		return htonl(S_IFLNK);
+		return S_IFLNK;
 	if (S_ISDIR(mode) || S_ISGITLINK(mode))
-		return htonl(S_IFGITLINK);
-	return htonl(S_IFREG | ce_permissions(mode));
+		return S_IFGITLINK;
+	return S_IFREG | ce_permissions(mode);
 }
 static inline unsigned int ce_mode_from_stat(struct cache_entry *ce, unsigned int mode)
 {
 	extern int trust_executable_bit, has_symlinks;
 	if (!has_symlinks && S_ISREG(mode) &&
-	    ce && S_ISLNK(ntohl(ce->ce_mode)))
+	    ce && S_ISLNK(ce->ce_mode))
 		return ce->ce_mode;
 	if (!trust_executable_bit && S_ISREG(mode)) {
-		if (ce && S_ISREG(ntohl(ce->ce_mode)))
+		if (ce && S_ISREG(ce->ce_mode))
 			return ce->ce_mode;
 		return create_ce_mode(0666);
 	}
@@ -146,14 +183,16 @@ static inline unsigned int ce_mode_from_stat(struct cache_entry *ce, unsigned in
 	S_ISLNK(mode) ? S_IFLNK : S_ISDIR(mode) ? S_IFDIR : S_IFGITLINK)
 
 #define cache_entry_size(len) ((offsetof(struct cache_entry,name) + (len) + 8) & ~7)
+#define ondisk_cache_entry_size(len) ((offsetof(struct ondisk_cache_entry,name) + (len) + 8) & ~7)
 
 struct index_state {
 	struct cache_entry **cache;
 	unsigned int cache_nr, cache_alloc, cache_changed;
 	struct cache_tree *cache_tree;
 	time_t timestamp;
-	void *mmap;
-	size_t mmap_size;
+	void *alloc;
+	unsigned name_hash_initialized : 1;
+	struct hash_table name_hash;
 };
 
 extern struct index_state the_index;
@@ -177,6 +216,7 @@ extern struct index_state the_index;
 #define refresh_cache(flags) refresh_index(&the_index, (flags), NULL, NULL)
 #define ce_match_stat(ce, st, options) ie_match_stat(&the_index, (ce), (st), (options))
 #define ce_modified(ce, st, options) ie_modified(&the_index, (ce), (st), (options))
+#define cache_name_exists(name, namelen) index_name_exists(&the_index, (name), (namelen))
 #endif
 
 enum object_type {
@@ -263,6 +303,7 @@ extern int read_index_from(struct index_state *, const char *path);
 extern int write_index(struct index_state *, int newfd);
 extern int discard_index(struct index_state *);
 extern int verify_path(const char *path);
+extern int index_name_exists(struct index_state *istate, const char *name, int namelen);
 extern int index_name_pos(struct index_state *, const char *name, int namelen);
 #define ADD_CACHE_OK_TO_ADD 1		/* Ok to add */
 #define ADD_CACHE_OK_TO_REPLACE 2	/* Ok to replace file/directory */