1 files changed, 600 insertions, 181 deletions

diff --git a/sha1_file.c b/sha1_file.c
index 3f70b1d86a..73ccd49a46 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -8,6 +8,7 @@
  */
 #include "cache.h"
 #include "string-list.h"
+#include "lockfile.h"
 #include "delta.h"
 #include "pack.h"
 #include "blob.h"
@@ -35,6 +36,7 @@
 static inline uintmax_t sz_fmt(size_t s) { return s; }
 
 const unsigned char null_sha1[20];
+const struct object_id null_oid;
 
 /*
  * This is meant to hold a *small* number of objects that you would
@@ -207,44 +209,25 @@ const char *sha1_file_name(const unsigned char *sha1)
  * provided by the caller.  which should be "pack" or "idx".
  */
 static char *sha1_get_pack_name(const unsigned char *sha1,
-				char **name, char **base, const char *which)
+				struct strbuf *buf,
+				const char *which)
 {
-	static const char hex[] = "0123456789abcdef";
-	char *buf;
-	int i;
-
-	if (!*base) {
-		const char *sha1_file_directory = get_object_directory();
-		int len = strlen(sha1_file_directory);
-		*base = xmalloc(len + 60);
-		sprintf(*base, "%s/pack/pack-1234567890123456789012345678901234567890.%s",
-			sha1_file_directory, which);
-		*name = *base + len + 11;
-	}
-
-	buf = *name;
-
-	for (i = 0; i < 20; i++) {
-		unsigned int val = *sha1++;
-		*buf++ = hex[val >> 4];
-		*buf++ = hex[val & 0xf];
-	}
-
-	return *base;
+	strbuf_reset(buf);
+	strbuf_addf(buf, "%s/pack/pack-%s.%s", get_object_directory(),
+		    sha1_to_hex(sha1), which);
+	return buf->buf;
 }
 
 char *sha1_pack_name(const unsigned char *sha1)
 {
-	static char *name, *base;
-
-	return sha1_get_pack_name(sha1, &name, &base, "pack");
+	static struct strbuf buf = STRBUF_INIT;
+	return sha1_get_pack_name(sha1, &buf, "pack");
 }
 
 char *sha1_pack_index_name(const unsigned char *sha1)
 {
-	static char *name, *base;
-
-	return sha1_get_pack_name(sha1, &name, &base, "idx");
+	static struct strbuf buf = STRBUF_INIT;
+	return sha1_get_pack_name(sha1, &buf, "idx");
 }
 
 struct alternate_object_database *alt_odb_list;
@@ -350,7 +333,7 @@ static void link_alt_odb_entries(const char *alt, int len, int sep,
 		return;
 	}
 
-	strbuf_addstr(&objdirbuf, absolute_path(get_object_directory()));
+	strbuf_add_absolute_path(&objdirbuf, get_object_directory());
 	normalize_path_copy(objdirbuf.buf, objdirbuf.buf);
 
 	alt_copy = xmemdupz(alt, len);
@@ -376,15 +359,12 @@ void read_info_alternates(const char * relative_base, int depth)
 	char *map;
 	size_t mapsz;
 	struct stat st;
-	const char alt_file_name[] = "info/alternates";
-	/* Given that relative_base is no longer than PATH_MAX,
-	   ensure that "path" has enough space to append "/", the
-	   file name, "info/alternates", and a trailing NUL.  */
-	char path[PATH_MAX + 1 + sizeof alt_file_name];
+	char *path;
 	int fd;
 
-	sprintf(path, "%s/%s", relative_base, alt_file_name);
+	path = xstrfmt("%s/info/alternates", relative_base);
 	fd = git_open_noatime(path);
+	free(path);
 	if (fd < 0)
 		return;
 	if (fstat(fd, &st) || (st.st_size == 0)) {
@@ -403,23 +383,60 @@ void read_info_alternates(const char * relative_base, int depth)
 void add_to_alternates_file(const char *reference)
 {
 	struct lock_file *lock = xcalloc(1, sizeof(struct lock_file));
-	int fd = hold_lock_file_for_append(lock, git_path("objects/info/alternates"), LOCK_DIE_ON_ERROR);
-	char *alt = mkpath("%s\n", reference);
-	write_or_die(fd, alt, strlen(alt));
-	if (commit_lock_file(lock))
-		die("could not close alternates file");
-	if (alt_odb_tail)
-		link_alt_odb_entries(alt, strlen(alt), '\n', NULL, 0);
+	char *alts = git_pathdup("objects/info/alternates");
+	FILE *in, *out;
+
+	hold_lock_file_for_update(lock, alts, LOCK_DIE_ON_ERROR);
+	out = fdopen_lock_file(lock, "w");
+	if (!out)
+		die_errno("unable to fdopen alternates lockfile");
+
+	in = fopen(alts, "r");
+	if (in) {
+		struct strbuf line = STRBUF_INIT;
+		int found = 0;
+
+		while (strbuf_getline(&line, in, '\n') != EOF) {
+			if (!strcmp(reference, line.buf)) {
+				found = 1;
+				break;
+			}
+			fprintf_or_die(out, "%s\n", line.buf);
+		}
+
+		strbuf_release(&line);
+		fclose(in);
+
+		if (found) {
+			rollback_lock_file(lock);
+			lock = NULL;
+		}
+	}
+	else if (errno != ENOENT)
+		die_errno("unable to read alternates file");
+
+	if (lock) {
+		fprintf_or_die(out, "%s\n", reference);
+		if (commit_lock_file(lock))
+			die_errno("unable to move new alternates file into place");
+		if (alt_odb_tail)
+			link_alt_odb_entries(reference, strlen(reference), '\n', NULL, 0);
+	}
+	free(alts);
 }
 
-void foreach_alt_odb(alt_odb_fn fn, void *cb)
+int foreach_alt_odb(alt_odb_fn fn, void *cb)
 {
 	struct alternate_object_database *ent;
+	int r = 0;
 
 	prepare_alt_odb();
-	for (ent = alt_odb_list; ent; ent = ent->next)
-		if (fn(ent, cb))
-			return;
+	for (ent = alt_odb_list; ent; ent = ent->next) {
+		r = fn(ent, cb);
+		if (r)
+			break;
+	}
+	return r;
 }
 
 void prepare_alt_odb(void)
@@ -438,27 +455,61 @@ void prepare_alt_odb(void)
 	read_info_alternates(get_object_directory(), 0);
 }
 
-static int has_loose_object_local(const unsigned char *sha1)
+/* Returns 1 if we have successfully freshened the file, 0 otherwise. */
+static int freshen_file(const char *fn)
 {
-	return !access(sha1_file_name(sha1), F_OK);
+	struct utimbuf t;
+	t.actime = t.modtime = time(NULL);
+	return !utime(fn, &t);
 }
 
-int has_loose_object_nonlocal(const unsigned char *sha1)
+/*
+ * All of the check_and_freshen functions return 1 if the file exists and was
+ * freshened (if freshening was requested), 0 otherwise. If they return
+ * 0, you should not assume that it is safe to skip a write of the object (it
+ * either does not exist on disk, or has a stale mtime and may be subject to
+ * pruning).
+ */
+static int check_and_freshen_file(const char *fn, int freshen)
+{
+	if (access(fn, F_OK))
+		return 0;
+	if (freshen && !freshen_file(fn))
+		return 0;
+	return 1;
+}
+
+static int check_and_freshen_local(const unsigned char *sha1, int freshen)
+{
+	return check_and_freshen_file(sha1_file_name(sha1), freshen);
+}
+
+static int check_and_freshen_nonlocal(const unsigned char *sha1, int freshen)
 {
 	struct alternate_object_database *alt;
 	prepare_alt_odb();
 	for (alt = alt_odb_list; alt; alt = alt->next) {
 		fill_sha1_path(alt->name, sha1);
-		if (!access(alt->base, F_OK))
+		if (check_and_freshen_file(alt->base, freshen))
 			return 1;
 	}
 	return 0;
 }
 
+static int check_and_freshen(const unsigned char *sha1, int freshen)
+{
+	return check_and_freshen_local(sha1, freshen) ||
+	       check_and_freshen_nonlocal(sha1, freshen);
+}
+
+int has_loose_object_nonlocal(const unsigned char *sha1)
+{
+	return check_and_freshen_nonlocal(sha1, 0);
+}
+
 static int has_loose_object(const unsigned char *sha1)
 {
-	return has_loose_object_local(sha1) ||
-	       has_loose_object_nonlocal(sha1);
+	return check_and_freshen(sha1, 0);
 }
 
 static unsigned int pack_used_ctr;
@@ -602,13 +653,15 @@ static int check_packed_git_idx(const char *path, struct packed_git *p)
 int open_pack_index(struct packed_git *p)
 {
 	char *idx_name;
+	size_t len;
 	int ret;
 
 	if (p->index_data)
 		return 0;
 
-	idx_name = xstrdup(p->pack_name);
-	strcpy(idx_name + strlen(idx_name) - strlen(".pack"), ".idx");
+	if (!strip_suffix(p->pack_name, ".pack", &len))
+		die("BUG: pack_name does not end in .pack");
+	idx_name = xstrfmt("%.*s.idx", (int)len, p->pack_name);
 	ret = check_packed_git_idx(idx_name, p);
 	free(idx_name);
 	return ret;
@@ -663,21 +716,44 @@ void release_pack_memory(size_t need)
 		; /* nothing */
 }
 
-void *xmmap(void *start, size_t length,
-	int prot, int flags, int fd, off_t offset)
+static void mmap_limit_check(size_t length)
+{
+	static size_t limit = 0;
+	if (!limit) {
+		limit = git_env_ulong("GIT_MMAP_LIMIT", 0);
+		if (!limit)
+			limit = SIZE_MAX;
+	}
+	if (length > limit)
+		die("attempting to mmap %"PRIuMAX" over limit %"PRIuMAX,
+		    (uintmax_t)length, (uintmax_t)limit);
+}
+
+void *xmmap_gently(void *start, size_t length,
+		  int prot, int flags, int fd, off_t offset)
 {
-	void *ret = mmap(start, length, prot, flags, fd, offset);
+	void *ret;
+
+	mmap_limit_check(length);
+	ret = mmap(start, length, prot, flags, fd, offset);
 	if (ret == MAP_FAILED) {
 		if (!length)
 			return NULL;
 		release_pack_memory(length);
 		ret = mmap(start, length, prot, flags, fd, offset);
-		if (ret == MAP_FAILED)
-			die_errno("Out of memory? mmap failed");
 	}
 	return ret;
 }
 
+void *xmmap(void *start, size_t length,
+	int prot, int flags, int fd, off_t offset)
+{
+	void *ret = xmmap_gently(start, length, prot, flags, fd, offset);
+	if (ret == MAP_FAILED)
+		die_errno("mmap failed");
+	return ret;
+}
+
 void close_pack_windows(struct packed_git *p)
 {
 	while (p->windows) {
@@ -694,6 +770,37 @@ void close_pack_windows(struct packed_git *p)
 	}
 }
 
+static int close_pack_fd(struct packed_git *p)
+{
+	if (p->pack_fd < 0)
+		return 0;
+
+	close(p->pack_fd);
+	pack_open_fds--;
+	p->pack_fd = -1;
+
+	return 1;
+}
+
+static void close_pack(struct packed_git *p)
+{
+	close_pack_windows(p);
+	close_pack_fd(p);
+	close_pack_index(p);
+}
+
+void close_all_packs(void)
+{
+	struct packed_git *p;
+
+	for (p = packed_git; p; p = p->next)
+		if (p->do_not_close)
+			die("BUG! Want to close pack marked 'do-not-close'");
+		else
+			close_pack(p);
+}
+
+
 /*
  * The LRU pack is the one with the oldest MRU window, preferring packs
  * with no used windows, or the oldest mtime if it has no windows allocated.
@@ -761,12 +868,8 @@ static int close_one_pack(void)
 		find_lru_pack(p, &lru_p, &mru_w, &accept_windows_inuse);
 	}
 
-	if (lru_p) {
-		close(lru_p->pack_fd);
-		pack_open_fds--;
-		lru_p->pack_fd = -1;
-		return 1;
-	}
+	if (lru_p)
+		return close_pack_fd(lru_p);
 
 	return 0;
 }
@@ -806,12 +909,7 @@ void free_pack_by_name(const char *pack_name)
 		p = *pp;
 		if (strcmp(pack_name, p->pack_name) == 0) {
 			clear_delta_base_cache();
-			close_pack_windows(p);
-			if (p->pack_fd != -1) {
-				close(p->pack_fd);
-				pack_open_fds--;
-			}
-			close_pack_index(p);
+			close_pack(p);
 			free(p->bad_object_sha1);
 			*pp = p->next;
 			if (last_found_pack == p)
@@ -945,11 +1043,7 @@ static int open_packed_git(struct packed_git *p)
 {
 	if (!open_packed_git_1(p))
 		return 0;
-	if (p->pack_fd != -1) {
-		close(p->pack_fd);
-		pack_open_fds--;
-		p->pack_fd = -1;
-	}
+	close_pack_fd(p);
 	return -1;
 }
 
@@ -1015,11 +1109,8 @@ unsigned char *use_pack(struct packed_git *p,
 					p->pack_name,
 					strerror(errno));
 			if (!win->offset && win->len == p->pack_size
-				&& !p->do_not_close) {
-				close(p->pack_fd);
-				pack_open_fds--;
-				p->pack_fd = -1;
-			}
+				&& !p->do_not_close)
+				close_pack_fd(p);
 			pack_mmap_calls++;
 			pack_open_windows++;
 			if (pack_mapped > peak_pack_mapped)
@@ -1054,11 +1145,12 @@ static void try_to_free_pack_memory(size_t size)
 	release_pack_memory(size);
 }
 
-struct packed_git *add_packed_git(const char *path, int path_len, int local)
+struct packed_git *add_packed_git(const char *path, size_t path_len, int local)
 {
 	static int have_set_try_to_free_routine;
 	struct stat st;
-	struct packed_git *p = alloc_packed_git(path_len + 2);
+	size_t alloc;
+	struct packed_git *p;
 
 	if (!have_set_try_to_free_routine) {
 		have_set_try_to_free_routine = 1;
@@ -1069,18 +1161,22 @@ struct packed_git *add_packed_git(const char *path, int path_len, int local)
 	 * Make sure a corresponding .pack file exists and that
 	 * the index looks sane.
 	 */
-	path_len -= strlen(".idx");
-	if (path_len < 1) {
-		free(p);
+	if (!strip_suffix_mem(path, &path_len, ".idx"))
 		return NULL;
-	}
+
+	/*
+	 * ".pack" is long enough to hold any suffix we're adding (and
+	 * the use xsnprintf double-checks that)
+	 */
+	alloc = path_len + strlen(".pack") + 1;
+	p = alloc_packed_git(alloc);
 	memcpy(p->pack_name, path, path_len);
 
-	strcpy(p->pack_name + path_len, ".keep");
+	xsnprintf(p->pack_name + path_len, alloc - path_len, ".keep");
 	if (!access(p->pack_name, F_OK))
 		p->pack_keep = 1;
 
-	strcpy(p->pack_name + path_len, ".pack");
+	xsnprintf(p->pack_name + path_len, alloc - path_len, ".pack");
 	if (stat(p->pack_name, &st) || !S_ISREG(st.st_mode)) {
 		free(p);
 		return NULL;
@@ -1100,9 +1196,10 @@ struct packed_git *add_packed_git(const char *path, int path_len, int local)
 struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path)
 {
 	const char *path = sha1_pack_name(sha1);
-	struct packed_git *p = alloc_packed_git(strlen(path) + 1);
+	int alloc = strlen(path) + 1;
+	struct packed_git *p = alloc_packed_git(alloc);
 
-	strcpy(p->pack_name, path);
+	memcpy(p->pack_name, path, alloc); /* includes NUL */
 	hashcpy(p->sha1, sha1);
 	if (check_packed_git_idx(idx_path, p)) {
 		free(p);
@@ -1121,27 +1218,16 @@ void install_packed_git(struct packed_git *pack)
 	packed_git = pack;
 }
 
-void (*report_garbage)(const char *desc, const char *path);
+void (*report_garbage)(unsigned seen_bits, const char *path);
 
 static void report_helper(const struct string_list *list,
 			  int seen_bits, int first, int last)
 {
-	const char *msg;
-	switch (seen_bits) {
-	case 0:
-		msg = "no corresponding .idx or .pack";
-		break;
-	case 1:
-		msg = "no corresponding .idx";
-		break;
-	case 2:
-		msg = "no corresponding .pack";
-		break;
-	default:
+	if (seen_bits == (PACKDIR_FILE_PACK|PACKDIR_FILE_IDX))
 		return;
-	}
+
 	for (; first < last; first++)
-		report_garbage(msg, list->items[first].string);
+		report_garbage(seen_bits, list->items[first].string);
 }
 
 static void report_pack_garbage(struct string_list *list)
@@ -1151,7 +1237,7 @@ static void report_pack_garbage(struct string_list *list)
 	if (!report_garbage)
 		return;
 
-	sort_string_list(list);
+	string_list_sort(list);
 
 	for (i = 0; i < list->nr; i++) {
 		const char *path = list->items[i].string;
@@ -1164,7 +1250,7 @@ static void report_pack_garbage(struct string_list *list)
 		if (baselen == -1) {
 			const char *dot = strrchr(path, '.');
 			if (!dot) {
-				report_garbage("garbage found", path);
+				report_garbage(PACKDIR_FILE_GARBAGE, path);
 				continue;
 			}
 			baselen = dot - path + 1;
@@ -1236,7 +1322,7 @@ static void prepare_packed_git_one(char *objdir, int local)
 		    ends_with(de->d_name, ".keep"))
 			string_list_append(&garbage, path.buf);
 		else
-			report_garbage("garbage found", path.buf);
+			report_garbage(PACKDIR_FILE_GARBAGE, path.buf);
 	}
 	closedir(dir);
 	report_pack_garbage(&garbage);
@@ -1372,7 +1458,7 @@ int check_sha1_signature(const unsigned char *sha1, void *map,
 		return -1;
 
 	/* Generate the header */
-	hdrlen = sprintf(hdr, "%s %lu", typename(obj_type), size) + 1;
+	hdrlen = xsnprintf(hdr, sizeof(hdr), "%s %lu", typename(obj_type), size) + 1;
 
 	/* Sha1.. */
 	git_SHA1_Init(&c);
@@ -1399,7 +1485,10 @@ int git_open_noatime(const char *name)
 	static int sha1_file_open_flag = O_NOATIME;
 
 	for (;;) {
-		int fd = open(name, O_RDONLY | sha1_file_open_flag);
+		int fd;
+
+		errno = 0;
+		fd = open(name, O_RDONLY | sha1_file_open_flag);
 		if (fd >= 0)
 			return fd;
 
@@ -1517,6 +1606,40 @@ int unpack_sha1_header(git_zstream *stream, unsigned char *map, unsigned long ma
 	return git_inflate(stream, 0);
 }
 
+static int unpack_sha1_header_to_strbuf(git_zstream *stream, unsigned char *map,
+					unsigned long mapsize, void *buffer,
+					unsigned long bufsiz, struct strbuf *header)
+{
+	int status;
+
+	status = unpack_sha1_header(stream, map, mapsize, buffer, bufsiz);
+
+	/*
+	 * Check if entire header is unpacked in the first iteration.
+	 */
+	if (memchr(buffer, '\0', stream->next_out - (unsigned char *)buffer))
+		return 0;
+
+	/*
+	 * buffer[0..bufsiz] was not large enough.  Copy the partial
+	 * result out to header, and then append the result of further
+	 * reading the stream.
+	 */
+	strbuf_add(header, buffer, stream->next_out - (unsigned char *)buffer);
+	stream->next_out = buffer;
+	stream->avail_out = bufsiz;
+
+	do {
+		status = git_inflate(stream, 0);
+		strbuf_add(header, buffer, stream->next_out - (unsigned char *)buffer);
+		if (memchr(buffer, '\0', stream->next_out - (unsigned char *)buffer))
+			return 0;
+		stream->next_out = buffer;
+		stream->avail_out = bufsiz;
+	} while (status != Z_STREAM_END);
+	return -1;
+}
+
 static void *unpack_sha1_rest(git_zstream *stream, void *buffer, unsigned long size, const unsigned char *sha1)
 {
 	int bytes = strlen(buffer) + 1;
@@ -1567,27 +1690,38 @@ static void *unpack_sha1_rest(git_zstream *stream, void *buffer, unsigned long s
  * too permissive for what we want to check. So do an anal
  * object header parse by hand.
  */
-int parse_sha1_header(const char *hdr, unsigned long *sizep)
+static int parse_sha1_header_extended(const char *hdr, struct object_info *oi,
+			       unsigned int flags)
 {
-	char type[10];
-	int i;
+	const char *type_buf = hdr;
 	unsigned long size;
+	int type, type_len = 0;
 
 	/*
-	 * The type can be at most ten bytes (including the
-	 * terminating '\0' that we add), and is followed by
+	 * The type can be of any size but is followed by
 	 * a space.
 	 */
-	i = 0;
 	for (;;) {
 		char c = *hdr++;
 		if (c == ' ')
 			break;
-		type[i++] = c;
-		if (i >= sizeof(type))
-			return -1;
+		type_len++;
 	}
-	type[i] = 0;
+
+	type = type_from_string_gently(type_buf, type_len, 1);
+	if (oi->typename)
+		strbuf_add(oi->typename, type_buf, type_len);
+	/*
+	 * Set type to 0 if its an unknown object and
+	 * we're obtaining the type using '--allow-unkown-type'
+	 * option.
+	 */
+	if ((flags & LOOKUP_UNKNOWN_OBJECT) && (type < 0))
+		type = 0;
+	else if (type < 0)
+		die("invalid object type");
+	if (oi->typep)
+		*oi->typep = type;
 
 	/*
 	 * The length must follow immediately, and be in canonical
@@ -1605,12 +1739,24 @@ int parse_sha1_header(const char *hdr, unsigned long *sizep)
 			size = size * 10 + c;
 		}
 	}
-	*sizep = size;
+
+	if (oi->sizep)
+		*oi->sizep = size;
 
 	/*
 	 * The length must be followed by a zero byte
 	 */
-	return *hdr ? -1 : type_from_string(type);
+	return *hdr ? -1 : type;
+}
+
+int parse_sha1_header(const char *hdr, unsigned long *sizep)
+{
+	struct object_info oi;
+
+	oi.sizep = sizep;
+	oi.typename = NULL;
+	oi.typep = NULL;
+	return parse_sha1_header_extended(hdr, &oi, LOOKUP_REPLACE_OBJECT);
 }
 
 static void *unpack_sha1_file(void *map, unsigned long mapsize, enum object_type *type, unsigned long *size, const unsigned char *sha1)
@@ -1923,7 +2069,9 @@ static void *unpack_compressed_entry(struct packed_git *p,
 	git_zstream stream;
 	unsigned char *buffer, *in;
 
-	buffer = xmallocz(size);
+	buffer = xmallocz_gently(size);
+	if (!buffer)
+		return NULL;
 	memset(&stream, 0, sizeof(stream));
 	stream.next_out = buffer;
 	stream.avail_out = size + 1;
@@ -1968,7 +2116,7 @@ static unsigned long pack_entry_hash(struct packed_git *p, off_t base_offset)
 {
 	unsigned long hash;
 
-	hash = (unsigned long)p + (unsigned long)base_offset;
+	hash = (unsigned long)(intptr_t)p + (unsigned long)base_offset;
 	hash += (hash >> 8) + (hash >> 16);
 	return hash % MAX_DELTA_CACHE;
 }
@@ -2424,10 +2572,8 @@ static int fill_pack_entry(const unsigned char *sha1,
 	 * answer, as it may have been deleted since the index was
 	 * loaded!
 	 */
-	if (!is_pack_valid(p)) {
-		warning("packfile %s cannot be accessed", p->pack_name);
+	if (!is_pack_valid(p))
 		return 0;
-	}
 	e->offset = offset;
 	e->p = p;
 	hashcpy(e->sha1, sha1);
@@ -2475,13 +2621,15 @@ struct packed_git *find_sha1_pack(const unsigned char *sha1,
 }
 
 static int sha1_loose_object_info(const unsigned char *sha1,
-				  struct object_info *oi)
+				  struct object_info *oi,
+				  int flags)
 {
-	int status;
-	unsigned long mapsize, size;
+	int status = 0;
+	unsigned long mapsize;
 	void *map;
 	git_zstream stream;
 	char hdr[32];
+	struct strbuf hdrbuf = STRBUF_INIT;
 
 	if (oi->delta_base_sha1)
 		hashclr(oi->delta_base_sha1);
@@ -2494,7 +2642,7 @@ static int sha1_loose_object_info(const unsigned char *sha1,
 	 * return value implicitly indicates whether the
 	 * object even exists.
 	 */
-	if (!oi->typep && !oi->sizep) {
+	if (!oi->typep && !oi->typename && !oi->sizep) {
 		struct stat st;
 		if (stat_sha1_file(sha1, &st) < 0)
 			return -1;
@@ -2508,17 +2656,26 @@ static int sha1_loose_object_info(const unsigned char *sha1,
 		return -1;
 	if (oi->disk_sizep)
 		*oi->disk_sizep = mapsize;
-	if (unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr)) < 0)
+	if ((flags & LOOKUP_UNKNOWN_OBJECT)) {
+		if (unpack_sha1_header_to_strbuf(&stream, map, mapsize, hdr, sizeof(hdr), &hdrbuf) < 0)
+			status = error("unable to unpack %s header with --allow-unknown-type",
+				       sha1_to_hex(sha1));
+	} else if (unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr)) < 0)
 		status = error("unable to unpack %s header",
 			       sha1_to_hex(sha1));
-	else if ((status = parse_sha1_header(hdr, &size)) < 0)
+	if (status < 0)
+		; /* Do nothing */
+	else if (hdrbuf.len) {
+		if ((status = parse_sha1_header_extended(hdrbuf.buf, oi, flags)) < 0)
+			status = error("unable to parse %s header with --allow-unknown-type",
+				       sha1_to_hex(sha1));
+	} else if ((status = parse_sha1_header_extended(hdr, oi, flags)) < 0)
 		status = error("unable to parse %s header", sha1_to_hex(sha1));
-	else if (oi->sizep)
-		*oi->sizep = size;
 	git_inflate_end(&stream);
 	munmap(map, mapsize);
-	if (oi->typep)
+	if (status && oi->typep)
 		*oi->typep = status;
+	strbuf_release(&hdrbuf);
 	return 0;
 }
 
@@ -2527,6 +2684,7 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
 	struct cached_object *co;
 	struct pack_entry e;
 	int rtype;
+	enum object_type real_type;
 	const unsigned char *real = lookup_replace_object_extended(sha1, flags);
 
 	co = find_cached_object(real);
@@ -2539,13 +2697,15 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
 			*(oi->disk_sizep) = 0;
 		if (oi->delta_base_sha1)
 			hashclr(oi->delta_base_sha1);
+		if (oi->typename)
+			strbuf_addstr(oi->typename, typename(co->type));
 		oi->whence = OI_CACHED;
 		return 0;
 	}
 
 	if (!find_pack_entry(real, &e)) {
 		/* Most likely it's a loose object. */
-		if (!sha1_loose_object_info(real, oi)) {
+		if (!sha1_loose_object_info(real, oi, flags)) {
 			oi->whence = OI_LOOSE;
 			return 0;
 		}
@@ -2556,9 +2716,18 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
 			return -1;
 	}
 
+	/*
+	 * packed_object_info() does not follow the delta chain to
+	 * find out the real type, unless it is given oi->typep.
+	 */
+	if (oi->typename && !oi->typep)
+		oi->typep = &real_type;
+
 	rtype = packed_object_info(e.p, e.offset, oi);
 	if (rtype < 0) {
 		mark_bad_packed_object(e.p, real);
+		if (oi->typep == &real_type)
+			oi->typep = NULL;
 		return sha1_object_info_extended(real, oi, 0);
 	} else if (in_delta_base_cache(e.p, e.offset)) {
 		oi->whence = OI_DBCACHED;
@@ -2569,6 +2738,10 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
 		oi->u.packed.is_delta = (rtype == OBJ_REF_DELTA ||
 					 rtype == OBJ_OFS_DELTA);
 	}
+	if (oi->typename)
+		strbuf_addstr(oi->typename, typename(*oi->typep));
+	if (oi->typep == &real_type)
+		oi->typep = NULL;
 
 	return 0;
 }
@@ -2751,7 +2924,7 @@ static void write_sha1_file_prepare(const void *buf, unsigned long len,
 	git_SHA_CTX c;
 
 	/* Generate the header */
-	*hdrlen = sprintf(hdr, "%s %lu", type, len)+1;
+	*hdrlen = xsnprintf(hdr, *hdrlen, "%s %lu", type, len)+1;
 
 	/* Sha1.. */
 	git_SHA1_Init(&c);
@@ -2762,11 +2935,8 @@ static void write_sha1_file_prepare(const void *buf, unsigned long len,
 
 /*
  * Move the just written object into its final resting place.
- * NEEDSWORK: this should be renamed to finalize_temp_file() as
- * "moving" is only a part of what it does, when no patch between
- * master to pu changes the call sites of this function.
  */
-int move_temp_to_file(const char *tmpfile, const char *filename)
+int finalize_object_file(const char *tmpfile, const char *filename)
 {
 	int ret = 0;
 
@@ -2817,7 +2987,7 @@ int hash_sha1_file(const void *buf, unsigned long len, const char *type,
                    unsigned char *sha1)
 {
 	char hdr[32];
-	int hdrlen;
+	int hdrlen = sizeof(hdr);
 	write_sha1_file_prepare(buf, len, type, sha1, hdr, &hdrlen);
 	return 0;
 }
@@ -2847,29 +3017,31 @@ static inline int directory_size(const char *filename)
  * We want to avoid cross-directory filename renames, because those
  * can have problems on various filesystems (FAT, NFS, Coda).
  */
-static int create_tmpfile(char *buffer, size_t bufsiz, const char *filename)
+static int create_tmpfile(struct strbuf *tmp, const char *filename)
 {
 	int fd, dirlen = directory_size(filename);
 
-	if (dirlen + 20 > bufsiz) {
-		errno = ENAMETOOLONG;
-		return -1;
-	}
-	memcpy(buffer, filename, dirlen);
-	strcpy(buffer + dirlen, "tmp_obj_XXXXXX");
-	fd = git_mkstemp_mode(buffer, 0444);
+	strbuf_reset(tmp);
+	strbuf_add(tmp, filename, dirlen);
+	strbuf_addstr(tmp, "tmp_obj_XXXXXX");
+	fd = git_mkstemp_mode(tmp->buf, 0444);
 	if (fd < 0 && dirlen && errno == ENOENT) {
-		/* Make sure the directory exists */
-		memcpy(buffer, filename, dirlen);
-		buffer[dirlen-1] = 0;
-		if (mkdir(buffer, 0777) && errno != EEXIST)
+		/*
+		 * Make sure the directory exists; note that the contents
+		 * of the buffer are undefined after mkstemp returns an
+		 * error, so we have to rewrite the whole buffer from
+		 * scratch.
+		 */
+		strbuf_reset(tmp);
+		strbuf_add(tmp, filename, dirlen - 1);
+		if (mkdir(tmp->buf, 0777) && errno != EEXIST)
 			return -1;
-		if (adjust_shared_perm(buffer))
+		if (adjust_shared_perm(tmp->buf))
 			return -1;
 
 		/* Try again */
-		strcpy(buffer + dirlen - 1, "/tmp_obj_XXXXXX");
-		fd = git_mkstemp_mode(buffer, 0444);
+		strbuf_addstr(tmp, "/tmp_obj_XXXXXX");
+		fd = git_mkstemp_mode(tmp->buf, 0444);
 	}
 	return fd;
 }
@@ -2882,10 +3054,10 @@ static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen,
 	git_zstream stream;
 	git_SHA_CTX c;
 	unsigned char parano_sha1[20];
-	static char tmp_file[PATH_MAX];
+	static struct strbuf tmp_file = STRBUF_INIT;
 	const char *filename = sha1_file_name(sha1);
 
-	fd = create_tmpfile(tmp_file, sizeof(tmp_file), filename);
+	fd = create_tmpfile(&tmp_file, filename);
 	if (fd < 0) {
 		if (errno == EACCES)
 			return error("insufficient permission for adding an object to repository database %s", get_object_directory());
@@ -2894,7 +3066,6 @@ static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen,
 	}
 
 	/* Set it up */
-	memset(&stream, 0, sizeof(stream));
 	git_deflate_init(&stream, zlib_compression_level);
 	stream.next_out = compressed;
 	stream.avail_out = sizeof(compressed);
@@ -2935,31 +3106,68 @@ static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen,
 		struct utimbuf utb;
 		utb.actime = mtime;
 		utb.modtime = mtime;
-		if (utime(tmp_file, &utb) < 0)
+		if (utime(tmp_file.buf, &utb) < 0)
 			warning("failed utime() on %s: %s",
-				tmp_file, strerror(errno));
+				tmp_file.buf, strerror(errno));
 	}
 
-	return move_temp_to_file(tmp_file, filename);
+	return finalize_object_file(tmp_file.buf, filename);
 }
 
-int write_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *returnsha1)
+static int freshen_loose_object(const unsigned char *sha1)
+{
+	return check_and_freshen(sha1, 1);
+}
+
+static int freshen_packed_object(const unsigned char *sha1)
+{
+	struct pack_entry e;
+	if (!find_pack_entry(sha1, &e))
+		return 0;
+	if (e.p->freshened)
+		return 1;
+	if (!freshen_file(e.p->pack_name))
+		return 0;
+	e.p->freshened = 1;
+	return 1;
+}
+
+int write_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *sha1)
 {
-	unsigned char sha1[20];
 	char hdr[32];
-	int hdrlen;
+	int hdrlen = sizeof(hdr);
 
 	/* Normally if we have it in the pack then we do not bother writing
 	 * it out into .git/objects/??/?{38} file.
 	 */
 	write_sha1_file_prepare(buf, len, type, sha1, hdr, &hdrlen);
-	if (returnsha1)
-		hashcpy(returnsha1, sha1);
-	if (has_sha1_file(sha1))
+	if (freshen_packed_object(sha1) || freshen_loose_object(sha1))
 		return 0;
 	return write_loose_object(sha1, hdr, hdrlen, buf, len, 0);
 }
 
+int hash_sha1_file_literally(const void *buf, unsigned long len, const char *type,
+			     unsigned char *sha1, unsigned flags)
+{
+	char *header;
+	int hdrlen, status = 0;
+
+	/* type string, SP, %lu of the length plus NUL must fit this */
+	hdrlen = strlen(type) + 32;
+	header = xmalloc(hdrlen);
+	write_sha1_file_prepare(buf, len, type, sha1, header, &hdrlen);
+
+	if (!(flags & HASH_WRITE_OBJECT))
+		goto cleanup;
+	if (freshen_packed_object(sha1) || freshen_loose_object(sha1))
+		goto cleanup;
+	status = write_loose_object(sha1, header, hdrlen, buf, len, 0);
+
+cleanup:
+	free(header);
+	return status;
+}
+
 int force_object_loose(const unsigned char *sha1, time_t mtime)
 {
 	void *buf;
@@ -2974,7 +3182,7 @@ int force_object_loose(const unsigned char *sha1, time_t mtime)
 	buf = read_packed_sha1(sha1, &type, &len);
 	if (!buf)
 		return error("cannot read sha1_file for %s", sha1_to_hex(sha1));
-	hdrlen = sprintf(hdr, "%s %lu", typename(type), len) + 1;
+	hdrlen = xsnprintf(hdr, sizeof(hdr), "%s %lu", typename(type), len) + 1;
 	ret = write_loose_object(sha1, hdr, hdrlen, buf, len, mtime);
 	free(buf);
 
@@ -2995,7 +3203,7 @@ int has_sha1_pack(const unsigned char *sha1)
 	return find_pack_entry(sha1, &e);
 }
 
-int has_sha1_file(const unsigned char *sha1)
+int has_sha1_file_with_flags(const unsigned char *sha1, int flags)
 {
 	struct pack_entry e;
 
@@ -3003,10 +3211,17 @@ int has_sha1_file(const unsigned char *sha1)
 		return 1;
 	if (has_loose_object(sha1))
 		return 1;
+	if (flags & HAS_SHA1_QUICK)
+		return 0;
 	reprepare_packed_git();
 	return find_pack_entry(sha1, &e);
 }
 
+int has_object_file(const struct object_id *oid)
+{
+	return has_sha1_file(oid->hash);
+}
+
 static void check_tree(const void *buf, size_t size)
 {
 	struct tree_desc desc;
@@ -3074,6 +3289,29 @@ static int index_mem(unsigned char *sha1, void *buf, size_t size,
 	return ret;
 }
 
+static int index_stream_convert_blob(unsigned char *sha1, int fd,
+				     const char *path, unsigned flags)
+{
+	int ret;
+	const int write_object = flags & HASH_WRITE_OBJECT;
+	struct strbuf sbuf = STRBUF_INIT;
+
+	assert(path);
+	assert(would_convert_to_git_filter_fd(path));
+
+	convert_to_git_filter_fd(path, fd, &sbuf,
+				 write_object ? safe_crlf : SAFE_CRLF_FALSE);
+
+	if (write_object)
+		ret = write_sha1_file(sbuf.buf, sbuf.len, typename(OBJ_BLOB),
+				      sha1);
+	else
+		ret = hash_sha1_file(sbuf.buf, sbuf.len, typename(OBJ_BLOB),
+				     sha1);
+	strbuf_release(&sbuf);
+	return ret;
+}
+
 static int index_pipe(unsigned char *sha1, int fd, enum object_type type,
 		      const char *path, unsigned flags)
 {
@@ -3097,7 +3335,7 @@ static int index_core(unsigned char *sha1, int fd, size_t size,
 	int ret;
 
 	if (!size) {
-		ret = index_mem(sha1, NULL, size, type, path, flags);
+		ret = index_mem(sha1, "", size, type, path, flags);
 	} else if (size <= SMALL_FILE_SIZE) {
 		char *buf = xmalloc(size);
 		if (size == read_in_full(fd, buf, size))
@@ -3139,15 +3377,22 @@ int index_fd(unsigned char *sha1, int fd, struct stat *st,
 	     enum object_type type, const char *path, unsigned flags)
 {
 	int ret;
-	size_t size = xsize_t(st->st_size);
 
-	if (!S_ISREG(st->st_mode))
+	/*
+	 * Call xsize_t() only when needed to avoid potentially unnecessary
+	 * die() for large files.
+	 */
+	if (type == OBJ_BLOB && path && would_convert_to_git_filter_fd(path))
+		ret = index_stream_convert_blob(sha1, fd, path, flags);
+	else if (!S_ISREG(st->st_mode))
 		ret = index_pipe(sha1, fd, type, path, flags);
-	else if (size <= big_file_threshold || type != OBJ_BLOB ||
-		 (path && would_convert_to_git(path, NULL, 0, 0)))
-		ret = index_core(sha1, fd, size, type, path, flags);
+	else if (st->st_size <= big_file_threshold || type != OBJ_BLOB ||
+		 (path && would_convert_to_git(path)))
+		ret = index_core(sha1, fd, xsize_t(st->st_size), type, path,
+				 flags);
 	else
-		ret = index_stream(sha1, fd, size, type, path, flags);
+		ret = index_stream(sha1, fd, xsize_t(st->st_size), type, path,
+				   flags);
 	close(fd);
 	return ret;
 }
@@ -3212,3 +3457,177 @@ void assert_sha1_type(const unsigned char *sha1, enum object_type expect)
 		die("%s is not a valid '%s' object", sha1_to_hex(sha1),
 		    typename(expect));
 }
+
+static int for_each_file_in_obj_subdir(int subdir_nr,
+				       struct strbuf *path,
+				       each_loose_object_fn obj_cb,
+				       each_loose_cruft_fn cruft_cb,
+				       each_loose_subdir_fn subdir_cb,
+				       void *data)
+{
+	size_t baselen = path->len;
+	DIR *dir = opendir(path->buf);
+	struct dirent *de;
+	int r = 0;
+
+	if (!dir) {
+		if (errno == ENOENT)
+			return 0;
+		return error("unable to open %s: %s", path->buf, strerror(errno));
+	}
+
+	while ((de = readdir(dir))) {
+		if (is_dot_or_dotdot(de->d_name))
+			continue;
+
+		strbuf_setlen(path, baselen);
+		strbuf_addf(path, "/%s", de->d_name);
+
+		if (strlen(de->d_name) == 38)  {
+			char hex[41];
+			unsigned char sha1[20];
+
+			snprintf(hex, sizeof(hex), "%02x%s",
+				 subdir_nr, de->d_name);
+			if (!get_sha1_hex(hex, sha1)) {
+				if (obj_cb) {
+					r = obj_cb(sha1, path->buf, data);
+					if (r)
+						break;
+				}
+				continue;
+			}
+		}
+
+		if (cruft_cb) {
+			r = cruft_cb(de->d_name, path->buf, data);
+			if (r)
+				break;
+		}
+	}
+	closedir(dir);
+
+	strbuf_setlen(path, baselen);
+	if (!r && subdir_cb)
+		r = subdir_cb(subdir_nr, path->buf, data);
+
+	return r;
+}
+
+int for_each_loose_file_in_objdir_buf(struct strbuf *path,
+			    each_loose_object_fn obj_cb,
+			    each_loose_cruft_fn cruft_cb,
+			    each_loose_subdir_fn subdir_cb,
+			    void *data)
+{
+	size_t baselen = path->len;
+	int r = 0;
+	int i;
+
+	for (i = 0; i < 256; i++) {
+		strbuf_addf(path, "/%02x", i);
+		r = for_each_file_in_obj_subdir(i, path, obj_cb, cruft_cb,
+						subdir_cb, data);
+		strbuf_setlen(path, baselen);
+		if (r)
+			break;
+	}
+
+	return r;
+}
+
+int for_each_loose_file_in_objdir(const char *path,
+				  each_loose_object_fn obj_cb,
+				  each_loose_cruft_fn cruft_cb,
+				  each_loose_subdir_fn subdir_cb,
+				  void *data)
+{
+	struct strbuf buf = STRBUF_INIT;
+	int r;
+
+	strbuf_addstr(&buf, path);
+	r = for_each_loose_file_in_objdir_buf(&buf, obj_cb, cruft_cb,
+					      subdir_cb, data);
+	strbuf_release(&buf);
+
+	return r;
+}
+
+struct loose_alt_odb_data {
+	each_loose_object_fn *cb;
+	void *data;
+};
+
+static int loose_from_alt_odb(struct alternate_object_database *alt,
+			      void *vdata)
+{
+	struct loose_alt_odb_data *data = vdata;
+	struct strbuf buf = STRBUF_INIT;
+	int r;
+
+	/* copy base not including trailing '/' */
+	strbuf_add(&buf, alt->base, alt->name - alt->base - 1);
+	r = for_each_loose_file_in_objdir_buf(&buf,
+					      data->cb, NULL, NULL,
+					      data->data);
+	strbuf_release(&buf);
+	return r;
+}
+
+int for_each_loose_object(each_loose_object_fn cb, void *data, unsigned flags)
+{
+	struct loose_alt_odb_data alt;
+	int r;
+
+	r = for_each_loose_file_in_objdir(get_object_directory(),
+					  cb, NULL, NULL, data);
+	if (r)
+		return r;
+
+	if (flags & FOR_EACH_OBJECT_LOCAL_ONLY)
+		return 0;
+
+	alt.cb = cb;
+	alt.data = data;
+	return foreach_alt_odb(loose_from_alt_odb, &alt);
+}
+
+static int for_each_object_in_pack(struct packed_git *p, each_packed_object_fn cb, void *data)
+{
+	uint32_t i;
+	int r = 0;
+
+	for (i = 0; i < p->num_objects; i++) {
+		const unsigned char *sha1 = nth_packed_object_sha1(p, i);
+
+		if (!sha1)
+			return error("unable to get sha1 of object %u in %s",
+				     i, p->pack_name);
+
+		r = cb(sha1, p, i, data);
+		if (r)
+			break;
+	}
+	return r;
+}
+
+int for_each_packed_object(each_packed_object_fn cb, void *data, unsigned flags)
+{
+	struct packed_git *p;
+	int r = 0;
+	int pack_errors = 0;
+
+	prepare_packed_git();
+	for (p = packed_git; p; p = p->next) {
+		if ((flags & FOR_EACH_OBJECT_LOCAL_ONLY) && !p->pack_local)
+			continue;
+		if (open_pack_index(p)) {
+			pack_errors = 1;
+			continue;
+		}
+		r = for_each_object_in_pack(p, cb, data);
+		if (r)
+			break;
+	}
+	return r ? r : pack_errors;
+}