1 files changed, 193 insertions, 120 deletions

diff --git a/sha1_file.c b/sha1_file.c
index 472ccb2ff9..5457314e6a 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -25,6 +25,7 @@
 #include "dir.h"
 #include "mru.h"
 #include "list.h"
+#include "mergesort.h"
 
 #ifndef O_NOATIME
 #if defined(__linux__) && (defined(__i386__) || defined(__PPC__))
@@ -171,36 +172,42 @@ enum scld_error safe_create_leading_directories_const(const char *path)
 	return result;
 }
 
-static void fill_sha1_path(char *pathbuf, const unsigned char *sha1)
+static void fill_sha1_path(struct strbuf *buf, const unsigned char *sha1)
 {
 	int i;
 	for (i = 0; i < 20; i++) {
 		static char hex[] = "0123456789abcdef";
 		unsigned int val = sha1[i];
-		char *pos = pathbuf + i*2 + (i > 0);
-		*pos++ = hex[val >> 4];
-		*pos = hex[val & 0xf];
+		strbuf_addch(buf, hex[val >> 4]);
+		strbuf_addch(buf, hex[val & 0xf]);
+		if (!i)
+			strbuf_addch(buf, '/');
 	}
 }
 
 const char *sha1_file_name(const unsigned char *sha1)
 {
-	static char buf[PATH_MAX];
-	const char *objdir;
-	int len;
+	static struct strbuf buf = STRBUF_INIT;
+
+	strbuf_reset(&buf);
+	strbuf_addf(&buf, "%s/", get_object_directory());
 
-	objdir = get_object_directory();
-	len = strlen(objdir);
+	fill_sha1_path(&buf, sha1);
+	return buf.buf;
+}
 
-	/* '/' + sha1(2) + '/' + sha1(38) + '\0' */
-	if (len + 43 > PATH_MAX)
-		die("insanely long object directory %s", objdir);
-	memcpy(buf, objdir, len);
-	buf[len] = '/';
-	buf[len+3] = '/';
-	buf[len+42] = '\0';
-	fill_sha1_path(buf + len + 1, sha1);
-	return buf;
+struct strbuf *alt_scratch_buf(struct alternate_object_database *alt)
+{
+	strbuf_setlen(&alt->scratch, alt->base_len);
+	return &alt->scratch;
+}
+
+static const char *alt_sha1_path(struct alternate_object_database *alt,
+				 const unsigned char *sha1)
+{
+	struct strbuf *buf = alt_scratch_buf(alt);
+	fill_sha1_path(buf, sha1);
+	return buf->buf;
 }
 
 /*
@@ -234,6 +241,35 @@ struct alternate_object_database *alt_odb_list;
 static struct alternate_object_database **alt_odb_tail;
 
 /*
+ * Return non-zero iff the path is usable as an alternate object database.
+ */
+static int alt_odb_usable(struct strbuf *path, const char *normalized_objdir)
+{
+	struct alternate_object_database *alt;
+
+	/* Detect cases where alternate disappeared */
+	if (!is_directory(path->buf)) {
+		error("object directory %s does not exist; "
+		      "check .git/objects/info/alternates.",
+		      path->buf);
+		return 0;
+	}
+
+	/*
+	 * Prevent the common mistake of listing the same
+	 * thing twice, or object directory itself.
+	 */
+	for (alt = alt_odb_list; alt; alt = alt->next) {
+		if (!fspathcmp(path->buf, alt->path))
+			return 0;
+	}
+	if (!fspathcmp(path->buf, normalized_objdir))
+		return 0;
+
+	return 1;
+}
+
+/*
  * Prepare alternate object database registry.
  *
  * The variable alt_odb_list points at the list of struct
@@ -252,8 +288,6 @@ static int link_alt_odb_entry(const char *entry, const char *relative_base,
 	int depth, const char *normalized_objdir)
 {
 	struct alternate_object_database *ent;
-	struct alternate_object_database *alt;
-	size_t pfxlen, entlen;
 	struct strbuf pathbuf = STRBUF_INIT;
 
 	if (!is_absolute_path(entry) && relative_base) {
@@ -262,49 +296,26 @@ static int link_alt_odb_entry(const char *entry, const char *relative_base,
 	}
 	strbuf_addstr(&pathbuf, entry);
 
-	normalize_path_copy(pathbuf.buf, pathbuf.buf);
-
-	pfxlen = strlen(pathbuf.buf);
+	if (strbuf_normalize_path(&pathbuf) < 0) {
+		error("unable to normalize alternate object path: %s",
+		      pathbuf.buf);
+		strbuf_release(&pathbuf);
+		return -1;
+	}
 
 	/*
 	 * The trailing slash after the directory name is given by
 	 * this function at the end. Remove duplicates.
 	 */
-	while (pfxlen && pathbuf.buf[pfxlen-1] == '/')
-		pfxlen -= 1;
+	while (pathbuf.len && pathbuf.buf[pathbuf.len - 1] == '/')
+		strbuf_setlen(&pathbuf, pathbuf.len - 1);
 
-	entlen = st_add(pfxlen, 43); /* '/' + 2 hex + '/' + 38 hex + NUL */
-	ent = xmalloc(st_add(sizeof(*ent), entlen));
-	memcpy(ent->base, pathbuf.buf, pfxlen);
-	strbuf_release(&pathbuf);
-
-	ent->name = ent->base + pfxlen + 1;
-	ent->base[pfxlen + 3] = '/';
-	ent->base[pfxlen] = ent->base[entlen-1] = 0;
-
-	/* Detect cases where alternate disappeared */
-	if (!is_directory(ent->base)) {
-		error("object directory %s does not exist; "
-		      "check .git/objects/info/alternates.",
-		      ent->base);
-		free(ent);
+	if (!alt_odb_usable(&pathbuf, normalized_objdir)) {
+		strbuf_release(&pathbuf);
 		return -1;
 	}
 
-	/* Prevent the common mistake of listing the same
-	 * thing twice, or object directory itself.
-	 */
-	for (alt = alt_odb_list; alt; alt = alt->next) {
-		if (pfxlen == alt->name - alt->base - 1 &&
-		    !memcmp(ent->base, alt->base, pfxlen)) {
-			free(ent);
-			return -1;
-		}
-	}
-	if (!fspathcmp(ent->base, normalized_objdir)) {
-		free(ent);
-		return -1;
-	}
+	ent = alloc_alt_odb(pathbuf.buf);
 
 	/* add the alternate entry */
 	*alt_odb_tail = ent;
@@ -312,10 +323,9 @@ static int link_alt_odb_entry(const char *entry, const char *relative_base,
 	ent->next = NULL;
 
 	/* recursively add alternates */
-	read_info_alternates(ent->base, depth + 1);
-
-	ent->base[pfxlen] = '/';
+	read_info_alternates(pathbuf.buf, depth + 1);
 
+	strbuf_release(&pathbuf);
 	return 0;
 }
 
@@ -334,7 +344,9 @@ static void link_alt_odb_entries(const char *alt, int len, int sep,
 	}
 
 	strbuf_add_absolute_path(&objdirbuf, get_object_directory());
-	normalize_path_copy(objdirbuf.buf, objdirbuf.buf);
+	if (strbuf_normalize_path(&objdirbuf) < 0)
+		die("unable to normalize object directory: %s",
+		    objdirbuf.buf);
 
 	alt_copy = xmemdupz(alt, len);
 	string_list_split_in_place(&entries, alt_copy, sep, -1);
@@ -342,12 +354,7 @@ static void link_alt_odb_entries(const char *alt, int len, int sep,
 		const char *entry = entries.items[i].string;
 		if (entry[0] == '\0' || entry[0] == '#')
 			continue;
-		if (!is_absolute_path(entry) && depth) {
-			error("%s: ignoring relative alternate object store %s",
-					relative_base, entry);
-		} else {
-			link_alt_odb_entry(entry, relative_base, depth, objdirbuf.buf);
-		}
+		link_alt_odb_entry(entry, relative_base, depth, objdirbuf.buf);
 	}
 	string_list_clear(&entries, 0);
 	free(alt_copy);
@@ -363,7 +370,7 @@ void read_info_alternates(const char * relative_base, int depth)
 	int fd;
 
 	path = xstrfmt("%s/info/alternates", relative_base);
-	fd = git_open_noatime(path);
+	fd = git_open(path);
 	free(path);
 	if (fd < 0)
 		return;
@@ -380,6 +387,18 @@ void read_info_alternates(const char * relative_base, int depth)
 	munmap(map, mapsz);
 }
 
+struct alternate_object_database *alloc_alt_odb(const char *dir)
+{
+	struct alternate_object_database *ent;
+
+	FLEX_ALLOC_STR(ent, path, dir);
+	strbuf_init(&ent->scratch, 0);
+	strbuf_addf(&ent->scratch, "%s/", dir);
+	ent->base_len = ent->scratch.len;
+
+	return ent;
+}
+
 void add_to_alternates_file(const char *reference)
 {
 	struct lock_file *lock = xcalloc(1, sizeof(struct lock_file));
@@ -425,6 +444,17 @@ void add_to_alternates_file(const char *reference)
 	free(alts);
 }
 
+void add_to_alternates_memory(const char *reference)
+{
+	/*
+	 * Make sure alternates are initialized, or else our entry may be
+	 * overwritten when they are.
+	 */
+	prepare_alt_odb();
+
+	link_alt_odb_entries(reference, strlen(reference), '\n', NULL, 0);
+}
+
 /*
  * Compute the exact path an alternate is at and returns it. In case of
  * error NULL is returned and the human readable error is added to `err`
@@ -565,8 +595,8 @@ 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 (check_and_freshen_file(alt->base, freshen))
+		const char *path = alt_sha1_path(alt, sha1);
+		if (check_and_freshen_file(path, freshen))
 			return 1;
 	}
 	return 0;
@@ -633,7 +663,7 @@ static int check_packed_git_idx(const char *path, struct packed_git *p)
 	struct pack_idx_header *hdr;
 	size_t idx_size;
 	uint32_t version, nr, i, *index;
-	int fd = git_open_noatime(path);
+	int fd = git_open(path);
 	struct stat st;
 
 	if (fd < 0)
@@ -1039,7 +1069,7 @@ static int open_packed_git_1(struct packed_git *p)
 	while (pack_max_fds <= pack_open_fds && close_one_pack())
 		; /* nothing */
 
-	p->pack_fd = git_open_noatime(p->pack_name);
+	p->pack_fd = git_open(p->pack_name);
 	if (p->pack_fd < 0 || fstat(p->pack_fd, &st))
 		return -1;
 	pack_open_fds++;
@@ -1380,10 +1410,46 @@ static void prepare_packed_git_one(char *objdir, int local)
 	strbuf_release(&path);
 }
 
+static int approximate_object_count_valid;
+
+/*
+ * Give a fast, rough count of the number of objects in the repository. This
+ * ignores loose objects completely. If you have a lot of them, then either
+ * you should repack because your performance will be awful, or they are
+ * all unreachable objects about to be pruned, in which case they're not really
+ * interesting as a measure of repo size in the first place.
+ */
+unsigned long approximate_object_count(void)
+{
+	static unsigned long count;
+	if (!approximate_object_count_valid) {
+		struct packed_git *p;
+
+		prepare_packed_git();
+		count = 0;
+		for (p = packed_git; p; p = p->next) {
+			if (open_pack_index(p))
+				continue;
+			count += p->num_objects;
+		}
+	}
+	return count;
+}
+
+static void *get_next_packed_git(const void *p)
+{
+	return ((const struct packed_git *)p)->next;
+}
+
+static void set_next_packed_git(void *p, void *next)
+{
+	((struct packed_git *)p)->next = next;
+}
+
 static int sort_pack(const void *a_, const void *b_)
 {
-	struct packed_git *a = *((struct packed_git **)a_);
-	struct packed_git *b = *((struct packed_git **)b_);
+	const struct packed_git *a = a_;
+	const struct packed_git *b = b_;
 	int st;
 
 	/*
@@ -1410,28 +1476,8 @@ static int sort_pack(const void *a_, const void *b_)
 
 static void rearrange_packed_git(void)
 {
-	struct packed_git **ary, *p;
-	int i, n;
-
-	for (n = 0, p = packed_git; p; p = p->next)
-		n++;
-	if (n < 2)
-		return;
-
-	/* prepare an array of packed_git for easier sorting */
-	ary = xcalloc(n, sizeof(struct packed_git *));
-	for (n = 0, p = packed_git; p; p = p->next)
-		ary[n++] = p;
-
-	qsort(ary, n, sizeof(struct packed_git *), sort_pack);
-
-	/* link them back again */
-	for (i = 0; i < n - 1; i++)
-		ary[i]->next = ary[i + 1];
-	ary[n - 1]->next = NULL;
-	packed_git = ary[0];
-
-	free(ary);
+	packed_git = llist_mergesort(packed_git, get_next_packed_git,
+				     set_next_packed_git, sort_pack);
 }
 
 static void prepare_packed_git_mru(void)
@@ -1452,11 +1498,8 @@ void prepare_packed_git(void)
 		return;
 	prepare_packed_git_one(get_object_directory(), 1);
 	prepare_alt_odb();
-	for (alt = alt_odb_list; alt; alt = alt->next) {
-		alt->name[-1] = 0;
-		prepare_packed_git_one(alt->base, 0);
-		alt->name[-1] = '/';
-	}
+	for (alt = alt_odb_list; alt; alt = alt->next)
+		prepare_packed_git_one(alt->path, 0);
 	rearrange_packed_git();
 	prepare_packed_git_mru();
 	prepare_packed_git_run_once = 1;
@@ -1464,6 +1507,7 @@ void prepare_packed_git(void)
 
 void reprepare_packed_git(void)
 {
+	approximate_object_count_valid = 0;
 	prepare_packed_git_run_once = 0;
 	prepare_packed_git();
 }
@@ -1542,9 +1586,9 @@ int check_sha1_signature(const unsigned char *sha1, void *map,
 	return hashcmp(sha1, real_sha1) ? -1 : 0;
 }
 
-int git_open_noatime(const char *name)
+int git_open(const char *name)
 {
-	static int sha1_file_open_flag = O_NOATIME;
+	static int sha1_file_open_flag = O_NOATIME | O_CLOEXEC;
 
 	for (;;) {
 		int fd;
@@ -1554,12 +1598,17 @@ int git_open_noatime(const char *name)
 		if (fd >= 0)
 			return fd;
 
-		/* Might the failure be due to O_NOATIME? */
-		if (errno != ENOENT && sha1_file_open_flag) {
-			sha1_file_open_flag = 0;
+		/* Try again w/o O_CLOEXEC: the kernel might not support it */
+		if ((sha1_file_open_flag & O_CLOEXEC) && errno == EINVAL) {
+			sha1_file_open_flag &= ~O_CLOEXEC;
 			continue;
 		}
 
+		/* Might the failure be due to O_NOATIME? */
+		if (errno != ENOENT && (sha1_file_open_flag & O_NOATIME)) {
+			sha1_file_open_flag &= ~O_NOATIME;
+			continue;
+		}
 		return -1;
 	}
 }
@@ -1574,8 +1623,8 @@ static int stat_sha1_file(const unsigned char *sha1, struct stat *st)
 	prepare_alt_odb();
 	errno = ENOENT;
 	for (alt = alt_odb_list; alt; alt = alt->next) {
-		fill_sha1_path(alt->name, sha1);
-		if (!lstat(alt->base, st))
+		const char *path = alt_sha1_path(alt, sha1);
+		if (!lstat(path, st))
 			return 0;
 	}
 
@@ -1588,15 +1637,15 @@ static int open_sha1_file(const unsigned char *sha1)
 	struct alternate_object_database *alt;
 	int most_interesting_errno;
 
-	fd = git_open_noatime(sha1_file_name(sha1));
+	fd = git_open(sha1_file_name(sha1));
 	if (fd >= 0)
 		return fd;
 	most_interesting_errno = errno;
 
 	prepare_alt_odb();
 	for (alt = alt_odb_list; alt; alt = alt->next) {
-		fill_sha1_path(alt->name, sha1);
-		fd = git_open_noatime(alt->base);
+		const char *path = alt_sha1_path(alt, sha1);
+		fd = git_open(path);
 		if (fd >= 0)
 			return fd;
 		if (most_interesting_errno == ENOENT)
@@ -1655,7 +1704,9 @@ unsigned long unpack_object_header_buffer(const unsigned char *buf,
 	return used;
 }
 
-int unpack_sha1_header(git_zstream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz)
+static int unpack_sha1_short_header(git_zstream *stream,
+				    unsigned char *map, unsigned long mapsize,
+				    void *buffer, unsigned long bufsiz)
 {
 	/* Get the data stream */
 	memset(stream, 0, sizeof(*stream));
@@ -1668,13 +1719,31 @@ int unpack_sha1_header(git_zstream *stream, unsigned char *map, unsigned long ma
 	return git_inflate(stream, 0);
 }
 
+int unpack_sha1_header(git_zstream *stream,
+		       unsigned char *map, unsigned long mapsize,
+		       void *buffer, unsigned long bufsiz)
+{
+	int status = unpack_sha1_short_header(stream, map, mapsize,
+					      buffer, bufsiz);
+
+	if (status < Z_OK)
+		return status;
+
+	/* Make sure we have the terminating NUL */
+	if (!memchr(buffer, '\0', stream->next_out - (unsigned char *)buffer))
+		return -1;
+	return 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);
+	status = unpack_sha1_short_header(stream, map, mapsize, buffer, bufsiz);
+	if (status < Z_OK)
+		return -1;
 
 	/*
 	 * Check if entire header is unpacked in the first iteration.
@@ -1765,6 +1834,8 @@ static int parse_sha1_header_extended(const char *hdr, struct object_info *oi,
 	 */
 	for (;;) {
 		char c = *hdr++;
+		if (!c)
+			return -1;
 		if (c == ' ')
 			break;
 		type_len++;
@@ -1813,11 +1884,9 @@ static int parse_sha1_header_extended(const char *hdr, struct object_info *oi,
 
 int parse_sha1_header(const char *hdr, unsigned long *sizep)
 {
-	struct object_info oi;
+	struct object_info oi = OBJECT_INFO_INIT;
 
 	oi.sizep = sizep;
-	oi.typename = NULL;
-	oi.typep = NULL;
 	return parse_sha1_header_extended(hdr, &oi, LOOKUP_REPLACE_OBJECT);
 }
 
@@ -2055,8 +2124,8 @@ unwind:
 	goto out;
 }
 
-static int packed_object_info(struct packed_git *p, off_t obj_offset,
-			      struct object_info *oi)
+int packed_object_info(struct packed_git *p, off_t obj_offset,
+		       struct object_info *oi)
 {
 	struct pack_window *w_curs = NULL;
 	unsigned long size;
@@ -2269,11 +2338,11 @@ static void add_delta_base_cache(struct packed_git *p, off_t base_offset,
 	void *base, unsigned long base_size, enum object_type type)
 {
 	struct delta_base_cache_entry *ent = xmalloc(sizeof(*ent));
-	struct list_head *lru;
+	struct list_head *lru, *tmp;
 
 	delta_base_cached += base_size;
 
-	list_for_each(lru, &delta_base_cache_lru) {
+	list_for_each_safe(lru, tmp, &delta_base_cache_lru) {
 		struct delta_base_cache_entry *f =
 			list_entry(lru, struct delta_base_cache_entry, lru);
 		if (delta_base_cached <= delta_base_cache_limit)
@@ -2827,7 +2896,7 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
 int sha1_object_info(const unsigned char *sha1, unsigned long *sizep)
 {
 	enum object_type type;
-	struct object_info oi = {NULL};
+	struct object_info oi = OBJECT_INFO_INIT;
 
 	oi.typep = &type;
 	oi.sizep = sizep;
@@ -3298,6 +3367,11 @@ int has_object_file(const struct object_id *oid)
 	return has_sha1_file(oid->hash);
 }
 
+int has_object_file_with_flags(const struct object_id *oid, int flags)
+{
+	return has_sha1_file_with_flags(oid->hash, flags);
+}
+
 static void check_tree(const void *buf, size_t size)
 {
 	struct tree_desc desc;
@@ -3637,8 +3711,7 @@ static int loose_from_alt_odb(struct alternate_object_database *alt,
 	struct strbuf buf = STRBUF_INIT;
 	int r;
 
-	/* copy base not including trailing '/' */
-	strbuf_add(&buf, alt->base, alt->name - alt->base - 1);
+	strbuf_addstr(&buf, alt->path);
 	r = for_each_loose_file_in_objdir_buf(&buf,
 					      data->cb, NULL, NULL,
 					      data->data);