Merge branch 'jc/nostat'

* jc/nostat:
  cache_name_compare() compares name and stage, nothing else.
  "assume unchanged" git: documentation.
  ls-files: split "show-valid-bit" into a different option.
  "Assume unchanged" git: --really-refresh fix.
  ls-files: debugging aid for CE_VALID changes.
  "Assume unchanged" git: do not set CE_VALID with --refresh
  "Assume unchanged" git

Documentation/git-ls-files.txt

@@ -8,7 +8,8 @@ git-ls-files - Information about files in the index/working directory
 
 SYNOPSIS
 --------
-'git-ls-files' [-z] [-t]
+[verse]
+'git-ls-files' [-z] [-t] [-v]
 		(--[cached|deleted|others|ignored|stage|unmerged|killed|modified])\*
 		(-[c|d|o|i|s|u|k|m])\*
 		[-x <pattern>|--exclude=<pattern>]
@@ -87,6 +88,10 @@ OPTIONS
 	K::	to be killed
 	?::	other
 
+-v::
+	Similar to `-t`, but use lowercase letters for files
+	that are marked as 'always matching index'.
+
 --full-name::
 	When run from a subdirectory, the command usually
 	outputs paths relative to the current directory.  This

Documentation/git-update-index.txt

@@ -8,11 +8,14 @@ git-update-index - Modifies the index or directory cache
 
 SYNOPSIS
 --------
+[verse]
 'git-update-index'
 	     [--add] [--remove | --force-remove] [--replace] 
 	     [--refresh [-q] [--unmerged] [--ignore-missing]]
 	     [--cacheinfo <mode> <object> <file>]\*
 	     [--chmod=(+|-)x]
+	     [--assume-unchanged | --no-assume-unchanged]
+	     [--really-refresh]
 	     [--info-only] [--index-info]
 	     [-z] [--stdin]
 	     [--verbose]
@@ -65,6 +68,18 @@ OPTIONS
 --chmod=(+|-)x::
         Set the execute permissions on the updated files.        
 
+--assume-unchanged, --no-assume-unchanged::
+	When these flags are specified, the object name recorded
+	for the paths are not updated.  Instead, these options
+	sets and unsets the "assume unchanged" bit for the
+	paths.  When the "assume unchanged" bit is on, git stops
+	checking the working tree files for possible
+	modifications, so you need to manually unset the bit to
+	tell git when you change the working tree file. This is
+	sometimes helpful when working with a big project on a
+	filesystem that has very slow lstat(2) system call
+	(e.g. cifs).
+
 --info-only::
 	Do not create objects in the object database for all
 	<file> arguments that follow this flag; just insert
@@ -193,6 +208,37 @@ $ git ls-files -s
 ------------
 
 
+Using "assume unchanged" bit
+----------------------------
+
+Many operations in git depend on your filesystem to have an
+efficient `lstat(2)` implementation, so that `st_mtime`
+information for working tree files can be cheaply checked to see
+if the file contents have changed from the version recorded in
+the index file.  Unfortunately, some filesystems have
+inefficient `lstat(2)`.  If your filesystem is one of them, you
+can set "assume unchanged" bit to paths you have not changed to
+cause git not to do this check.  Note that setting this bit on a
+path does not mean git will check the contents of the file to
+see if it has changed -- it makes git to omit any checking and
+assume it has *not* changed.  When you make changes to working
+tree files, you have to explicitly tell git about it by dropping
+"assume unchanged" bit, either before or after you modify them.
+
+In order to set "assume unchanged" bit, use `--assume-unchanged`
+option.  To unset, use `--no-assume-unchanged`.
+
+The command looks at `core.ignorestat` configuration variable.  When
+this is true, paths updated with `git-update-index paths...` and
+paths updated with other git commands that update both index and
+working tree (e.g. `git-apply --index`, `git-checkout-index -u`,
+and `git-read-tree -u`) are automatically marked as "assume
+unchanged".  Note that "assume unchanged" bit is *not* set if
+`git-update-index --refresh` finds the working tree file matches
+the index (use `git-update-index --really-refresh` if you want
+to mark them as "assume unchanged").
+
+
 Examples
 --------
 To update and refresh only the files already checked out:
@@ -201,6 +247,35 @@ To update and refresh only the files already checked out:
 $ git-checkout-index -n -f -a && git-update-index --ignore-missing --refresh
 ----------------
 
+On an inefficient filesystem with `core.ignorestat` set:
+
+------------
+$ git update-index --really-refresh <1>
+$ git update-index --no-assume-unchanged foo.c <2>
+$ git diff --name-only <3>
+$ edit foo.c
+$ git diff --name-only <4>
+M foo.c
+$ git update-index foo.c <5>
+$ git diff --name-only <6>
+$ edit foo.c
+$ git diff --name-only <7>
+$ git update-index --no-assume-unchanged foo.c <8>
+$ git diff --name-only <9>
+M foo.c
+
+<1> forces lstat(2) to set "assume unchanged" bits for paths
+    that match index.
+<2> mark the path to be edited.
+<3> this does lstat(2) and finds index matches the path.
+<4> this does lstat(2) and finds index does not match the path.
+<5> registering the new version to index sets "assume unchanged" bit.
+<6> and it is assumed unchanged.
+<7> even after you edit it.
+<8> you can tell about the change after the fact.
+<9> now it checks with lstat(2) and finds it has been changed.
+------------
+
 
 Configuration
 -------------
@@ -213,6 +288,9 @@ in the index and the file mode on the filesystem if they differ only on
 executable bit.   On such an unfortunate filesystem, you may
 need to use `git-update-index --chmod=`.
 
+The command looks at `core.ignorestat` configuration variable.  See
+'Using "assume unchanged" bit' section above.
+
 
 See Also
 --------

apply.c

@@ -1317,7 +1317,7 @@ static int check_patch(struct patch *patch)
 					return -1;
 			}
 
-			changed = ce_match_stat(active_cache[pos], &st);
+			changed = ce_match_stat(active_cache[pos], &st, 1);
 			if (changed)
 				return error("%s: does not match index",
 					     old_name);

cache.h

@@ -91,6 +91,7 @@ struct cache_entry {
 #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))
@@ -144,8 +145,8 @@ extern int add_cache_entry(struct cache_entry *ce, int option);
 extern int remove_cache_entry_at(int pos);
 extern int remove_file_from_cache(const char *path);
 extern int ce_same_name(struct cache_entry *a, struct cache_entry *b);
-extern int ce_match_stat(struct cache_entry *ce, struct stat *st);
-extern int ce_modified(struct cache_entry *ce, struct stat *st);
+extern int ce_match_stat(struct cache_entry *ce, struct stat *st, int);
+extern int ce_modified(struct cache_entry *ce, struct stat *st, int);
 extern int ce_path_match(const struct cache_entry *ce, const char **pathspec);
 extern int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, const char *type);
 extern int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object);
@@ -161,6 +162,7 @@ extern int commit_index_file(struct cache_file *);
 extern void rollback_index_file(struct cache_file *);
 
 extern int trust_executable_bit;
+extern int assume_unchanged;
 extern int only_use_symrefs;
 extern int diff_rename_limit_default;
 extern int shared_repository;

checkout-index.c

@@ -116,6 +116,7 @@ int main(int argc, char **argv)
 	int all = 0;
 
 	prefix = setup_git_directory();
+	git_config(git_default_config);
 	prefix_length = prefix ? strlen(prefix) : 0;
 
 	if (read_cache() < 0) {

config.c

@@ -222,6 +222,11 @@ int git_default_config(const char *var, const char *value)
 		return 0;
 	}
 
+	if (!strcmp(var, "core.ignorestat")) {
+		assume_unchanged = git_config_bool(var, value);
+		return 0;
+	}
+
 	if (!strcmp(var, "core.symrefsonly")) {
 		only_use_symrefs = git_config_bool(var, value);
 		return 0;

diff-files.c

@@ -193,7 +193,7 @@ int main(int argc, const char **argv)
 			show_file('-', ce);
 			continue;
 		}
-		changed = ce_match_stat(ce, &st);
+		changed = ce_match_stat(ce, &st, 0);
 		if (!changed && !diff_options.find_copies_harder)
 			continue;
 		oldmode = ntohl(ce->ce_mode);

diff-index.c

@@ -33,7 +33,7 @@ static int get_stat_data(struct cache_entry *ce,
 			}
 			return -1;
 		}
-		changed = ce_match_stat(ce, &st);
+		changed = ce_match_stat(ce, &st, 0);
 		if (changed) {
 			mode = create_ce_mode(st.st_mode);
 			if (!trust_executable_bit &&

diff.c

@@ -311,7 +311,7 @@ static int work_tree_matches(const char *name, const unsigned char *sha1)
 	ce = active_cache[pos];
 	if ((lstat(name, &st) < 0) ||
 	    !S_ISREG(st.st_mode) || /* careful! */
-	    ce_match_stat(ce, &st) ||
+	    ce_match_stat(ce, &st, 0) ||
 	    memcmp(sha1, ce->sha1, 20))
 		return 0;
 	/* we return 1 only when we can stat, it is a regular file,

entry.c

@@ -123,7 +123,7 @@ int checkout_entry(struct cache_entry *ce, struct checkout *state)
 	strcpy(path + len, ce->name);
 
 	if (!lstat(path, &st)) {
-		unsigned changed = ce_match_stat(ce, &st);
+		unsigned changed = ce_match_stat(ce, &st, 1);
 		if (!changed)
 			return 0;
 		if (!state->force) {

environment.c

@@ -12,6 +12,7 @@
 char git_default_email[MAX_GITNAME];
 char git_default_name[MAX_GITNAME];
 int trust_executable_bit = 1;
+int assume_unchanged = 0;
 int only_use_symrefs = 0;
 int repository_format_version = 0;
 char git_commit_encoding[MAX_ENCODING_LENGTH] = "utf-8";

ls-files.c

@@ -20,6 +20,7 @@ static int show_unmerged = 0;
 static int show_modified = 0;
 static int show_killed = 0;
 static int show_other_directories = 0;
+static int show_valid_bit = 0;
 static int line_terminator = '\n';
 
 static int prefix_len = 0, prefix_offset = 0;
@@ -457,6 +458,23 @@ static void show_ce_entry(const char *tag, struct cache_entry *ce)
 	if (pathspec && !match(pathspec, ps_matched, ce->name, len))
 		return;
 
+	if (tag && *tag && show_valid_bit &&
+	    (ce->ce_flags & htons(CE_VALID))) {
+		static char alttag[4];
+		memcpy(alttag, tag, 3);
+		if (isalpha(tag[0]))
+			alttag[0] = tolower(tag[0]);
+		else if (tag[0] == '?')
+			alttag[0] = '!';
+		else {
+			alttag[0] = 'v';
+			alttag[1] = tag[0];
+			alttag[2] = ' ';
+			alttag[3] = 0;
+		}
+		tag = alttag;
+	}
+
 	if (!show_stage) {
 		fputs(tag, stdout);
 		write_name_quoted("", 0, ce->name + offset,
@@ -533,7 +551,7 @@ static void show_files(void)
 			err = lstat(ce->name, &st);
 			if (show_deleted && err)
 				show_ce_entry(tag_removed, ce);
-			if (show_modified && ce_modified(ce, &st))
+			if (show_modified && ce_modified(ce, &st, 0))
 				show_ce_entry(tag_modified, ce);
 		}
 	}
@@ -606,7 +624,7 @@ static void verify_pathspec(void)
 }
 
 static const char ls_files_usage[] =
-	"git-ls-files [-z] [-t] (--[cached|deleted|others|stage|unmerged|killed|modified])* "
+	"git-ls-files [-z] [-t] [-v] (--[cached|deleted|others|stage|unmerged|killed|modified])* "
 	"[ --ignored ] [--exclude=<pattern>] [--exclude-from=<file>] "
 	"[ --exclude-per-directory=<filename> ] [--full-name] [--] [<file>]*";
 
@@ -631,13 +649,15 @@ int main(int argc, const char **argv)
 			line_terminator = 0;
 			continue;
 		}
-		if (!strcmp(arg, "-t")) {
+		if (!strcmp(arg, "-t") || !strcmp(arg, "-v")) {
 			tag_cached = "H ";
 			tag_unmerged = "M ";
 			tag_removed = "R ";
 			tag_modified = "C ";
 			tag_other = "? ";
 			tag_killed = "K ";
+			if (arg[1] == 'v')
+				show_valid_bit = 1;
 			continue;
 		}
 		if (!strcmp(arg, "-c") || !strcmp(arg, "--cached")) {

read-cache.c

@@ -27,6 +27,9 @@ void fill_stat_cache_info(struct cache_entry *ce, struct stat *st)
 	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)
@@ -146,9 +149,18 @@ static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st)
 	return changed;
 }
 
-int ce_match_stat(struct cache_entry *ce, struct stat *st)
+int ce_match_stat(struct cache_entry *ce, struct stat *st, int ignore_valid)
 {
-	unsigned int changed = ce_match_stat_basic(ce, st);
+	unsigned int changed;
+
+	/*
+	 * 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;
+
+	changed = ce_match_stat_basic(ce, st);
 
 	/*
 	 * Within 1 second of this sequence:
@@ -164,7 +176,7 @@ int ce_match_stat(struct cache_entry *ce, struct stat *st)
 	 * 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
-	 * careful than others.
+	 * carefully than others.
 	 */
 	if (!changed &&
 	    index_file_timestamp &&
@@ -174,10 +186,10 @@ int ce_match_stat(struct cache_entry *ce, struct stat *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_fs;
-	changed = ce_match_stat(ce, st);
+	changed = ce_match_stat(ce, st, really);
 	if (!changed)
 		return 0;
 	/*
@@ -233,6 +245,11 @@ int cache_name_compare(const char *name1, int flags1, const char *name2, int fla
 		return -1;
 	if (len1 > len2)
 		return 1;
+
+	/* Compare stages  */
+	flags1 &= CE_STAGEMASK;
+	flags2 &= CE_STAGEMASK;
+
 	if (flags1 < flags2)
 		return -1;
 	if (flags1 > flags2)
@@ -430,6 +447,7 @@ int add_cache_entry(struct cache_entry *ce, int option)
 	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. */

read-tree.c

@@ -349,7 +349,7 @@ static void verify_uptodate(struct cache_entry *ce)
 		return;
 
 	if (!lstat(ce->name, &st)) {
-		unsigned changed = ce_match_stat(ce, &st);
+		unsigned changed = ce_match_stat(ce, &st, 1);
 		if (!changed)
 			return;
 		errno = 0;

update-index.c

@@ -23,6 +23,10 @@ static int quiet; /* --refresh needing update is not error */
 static int info_only;
 static int force_remove;
 static int verbose;
+static int mark_valid_only = 0;
+#define MARK_VALID 1
+#define UNMARK_VALID 2
+
 
 /* Three functions to allow overloaded pointer return; see linux/err.h */
 static inline void *ERR_PTR(long error)
@@ -53,6 +57,25 @@ static void report(const char *fmt, ...)
 	va_end(vp);
 }
 
+static int mark_valid(const char *path)
+{
+	int namelen = strlen(path);
+	int pos = cache_name_pos(path, namelen);
+	if (0 <= pos) {
+		switch (mark_valid_only) {
+		case MARK_VALID:
+			active_cache[pos]->ce_flags |= htons(CE_VALID);
+			break;
+		case UNMARK_VALID:
+			active_cache[pos]->ce_flags &= ~htons(CE_VALID);
+			break;
+		}
+		active_cache_changed = 1;
+		return 0;
+	}
+	return -1;
+}
+
 static int add_file_to_cache(const char *path)
 {
 	int size, namelen, option, status;
@@ -94,6 +117,7 @@ static int add_file_to_cache(const char *path)
 	ce = xmalloc(size);
 	memset(ce, 0, size);
 	memcpy(ce->name, path, namelen);
+	ce->ce_flags = htons(namelen);
 	fill_stat_cache_info(ce, &st);
 
 	ce->ce_mode = create_ce_mode(st.st_mode);
@@ -105,7 +129,6 @@ static int add_file_to_cache(const char *path)
 		if (0 <= pos)
 			ce->ce_mode = active_cache[pos]->ce_mode;
 	}
-	ce->ce_flags = htons(namelen);
 
 	if (index_path(ce->sha1, path, &st, !info_only))
 		return -1;
@@ -128,7 +151,7 @@ static int add_file_to_cache(const char *path)
  * 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)
+static struct cache_entry *refresh_entry(struct cache_entry *ce, int really)
 {
 	struct stat st;
 	struct cache_entry *updated;
@@ -137,21 +160,36 @@ static struct cache_entry *refresh_entry(struct cache_entry *ce)
 	if (lstat(ce->name, &st) < 0)
 		return ERR_PTR(-errno);
 
-	changed = ce_match_stat(ce, &st);
-	if (!changed)
-		return NULL;
+	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))
+	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;
 }
 
-static int refresh_cache(void)
+static int refresh_cache(int really)
 {
 	int i;
 	int has_errors = 0;
@@ -171,12 +209,19 @@ static int refresh_cache(void)
 			continue;
 		}
 
-		new = refresh_entry(ce);
+		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);
@@ -274,6 +319,8 @@ static int add_cacheinfo(unsigned int mode, const unsigned char *sha1,
 	memcpy(ce->name, path, len);
 	ce->ce_flags = create_ce_flags(len, stage);
 	ce->ce_mode = create_ce_mode(mode);
+	if (assume_unchanged)
+		ce->ce_flags |= htons(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))
@@ -317,6 +364,12 @@ static void update_one(const char *path, const char *prefix, int prefix_length)
 		fprintf(stderr, "Ignoring path %s\n", path);
 		return;
 	}
+	if (mark_valid_only) {
+		if (mark_valid(p))
+			die("Unable to mark file %s", path);
+		return;
+	}
+
 	if (force_remove) {
 		if (remove_file_from_cache(p))
 			die("git-update-index: unable to remove %s", path);
@@ -467,7 +520,11 @@ int main(int argc, const char **argv)
 				continue;
 			}
 			if (!strcmp(path, "--refresh")) {
-				has_errors |= refresh_cache();
+				has_errors |= refresh_cache(0);
+				continue;
+			}
+			if (!strcmp(path, "--really-refresh")) {
+				has_errors |= refresh_cache(1);
 				continue;
 			}
 			if (!strcmp(path, "--cacheinfo")) {
@@ -493,6 +550,14 @@ int main(int argc, const char **argv)
 					die("git-update-index: %s cannot chmod %s", path, argv[i]);
 				continue;
 			}
+			if (!strcmp(path, "--assume-unchanged")) {
+				mark_valid_only = MARK_VALID;
+				continue;
+			}
+			if (!strcmp(path, "--no-assume-unchanged")) {
+				mark_valid_only = UNMARK_VALID;
+				continue;
+			}
 			if (!strcmp(path, "--info-only")) {
 				info_only = 1;
 				continue;

write-tree.c

@@ -111,7 +111,7 @@ int main(int argc, char **argv)
 	funny = 0;
 	for (i = 0; i < entries; i++) {
 		struct cache_entry *ce = active_cache[i];
-		if (ntohs(ce->ce_flags) & ~CE_NAMEMASK) {
+		if (ce_stage(ce)) {
 			if (10 < ++funny) {
 				fprintf(stderr, "...\n");
 				break;