X-Git-Url: https://git.tokkee.org/?a=blobdiff_plain;f=sha1_file.c;h=956422ba4a5df5f46caaf85f10e4c85321439272;hb=bd193f46b70fd3f8a55e2a8dcbb1fb2b4eec13d6;hp=28bd9082fc9f4b79519f6bef8204600072c07027;hpb=77f143bf3e218857ec8e5244d7e862e8e0c1a041;p=git.git

diff --git a/sha1_file.c b/sha1_file.c
index 28bd9082f..956422ba4 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -11,8 +11,10 @@
 #include "pack.h"
 #include "blob.h"
 #include "commit.h"
+#include "run-command.h"
 #include "tag.h"
 #include "tree.h"
+#include "tree-walk.h"
 #include "refs.h"
 #include "pack-revindex.h"
 #include "sha1-lookup.h"
@@ -25,69 +27,73 @@
 #endif
 #endif
 
-#ifdef NO_C99_FORMAT
-#define SZ_FMT "lu"
-static unsigned long sz_fmt(size_t s) { return (unsigned long)s; }
-#else
-#define SZ_FMT "zu"
-static size_t sz_fmt(size_t s) { return s; }
-#endif
+#define SZ_FMT PRIuMAX
+static inline uintmax_t sz_fmt(size_t s) { return s; }
 
 const unsigned char null_sha1[20];
 
-const signed char hexval_table[256] = {
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 00-07 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 08-0f */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 10-17 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 18-1f */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 20-27 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 28-2f */
-	  0,  1,  2,  3,  4,  5,  6,  7,		/* 30-37 */
-	  8,  9, -1, -1, -1, -1, -1, -1,		/* 38-3f */
-	 -1, 10, 11, 12, 13, 14, 15, -1,		/* 40-47 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 48-4f */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 50-57 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 58-5f */
-	 -1, 10, 11, 12, 13, 14, 15, -1,		/* 60-67 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 68-67 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 70-77 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 78-7f */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 80-87 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 88-8f */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 90-97 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 98-9f */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* a0-a7 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* a8-af */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* b0-b7 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* b8-bf */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* c0-c7 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* c8-cf */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* d0-d7 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* d8-df */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* e0-e7 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* e8-ef */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* f0-f7 */
-	 -1, -1, -1, -1, -1, -1, -1, -1,		/* f8-ff */
+/*
+ * This is meant to hold a *small* number of objects that you would
+ * want read_sha1_file() to be able to return, but yet you do not want
+ * to write them into the object store (e.g. a browse-only
+ * application).
+ */
+static struct cached_object {
+	unsigned char sha1[20];
+	enum object_type type;
+	void *buf;
+	unsigned long size;
+} *cached_objects;
+static int cached_object_nr, cached_object_alloc;
+
+static struct cached_object empty_tree = {
+	EMPTY_TREE_SHA1_BIN_LITERAL,
+	OBJ_TREE,
+	"",
+	0
 };
 
-int get_sha1_hex(const char *hex, unsigned char *sha1)
+static struct cached_object *find_cached_object(const unsigned char *sha1)
 {
 	int i;
-	for (i = 0; i < 20; i++) {
-		unsigned int val = (hexval(hex[0]) << 4) | hexval(hex[1]);
-		if (val & ~0xff)
-			return -1;
-		*sha1++ = val;
-		hex += 2;
+	struct cached_object *co = cached_objects;
+
+	for (i = 0; i < cached_object_nr; i++, co++) {
+		if (!hashcmp(co->sha1, sha1))
+			return co;
 	}
-	return 0;
+	if (!hashcmp(sha1, empty_tree.sha1))
+		return &empty_tree;
+	return NULL;
 }
 
-static inline int offset_1st_component(const char *path)
+int mkdir_in_gitdir(const char *path)
 {
-	if (has_dos_drive_prefix(path))
-		return 2 + (path[2] == '/');
-	return *path == '/';
+	if (mkdir(path, 0777)) {
+		int saved_errno = errno;
+		struct stat st;
+		struct strbuf sb = STRBUF_INIT;
+
+		if (errno != EEXIST)
+			return -1;
+		/*
+		 * Are we looking at a path in a symlinked worktree
+		 * whose original repository does not yet have it?
+		 * e.g. .git/rr-cache pointing at its original
+		 * repository in which the user hasn't performed any
+		 * conflict resolution yet?
+		 */
+		if (lstat(path, &st) || !S_ISLNK(st.st_mode) ||
+		    strbuf_readlink(&sb, path, st.st_size) ||
+		    !is_absolute_path(sb.buf) ||
+		    mkdir(sb.buf, 0777)) {
+			strbuf_release(&sb);
+			errno = saved_errno;
+			return -1;
+		}
+		strbuf_release(&sb);
+	}
+	return adjust_shared_perm(path);
 }
 
 int safe_create_leading_directories(char *path)
@@ -133,24 +139,6 @@ int safe_create_leading_directories_const(const char *path)
 	return result;
 }
 
-char *sha1_to_hex(const unsigned char *sha1)
-{
-	static int bufno;
-	static char hexbuffer[4][50];
-	static const char hex[] = "0123456789abcdef";
-	char *buffer = hexbuffer[3 & ++bufno], *buf = buffer;
-	int i;
-
-	for (i = 0; i < 20; i++) {
-		unsigned int val = *sha1++;
-		*buf++ = hex[val >> 4];
-		*buf++ = hex[val & 0xf];
-	}
-	*buf = '\0';
-
-	return buffer;
-}
-
 static void fill_sha1_path(char *pathbuf, const unsigned char *sha1)
 {
 	int i;
@@ -175,20 +163,22 @@ static void fill_sha1_path(char *pathbuf, const unsigned char *sha1)
  */
 char *sha1_file_name(const unsigned char *sha1)
 {
-	static char *name, *base;
+	static char buf[PATH_MAX];
+	const char *objdir;
+	int len;
 
-	if (!base) {
-		const char *sha1_file_directory = get_object_directory();
-		int len = strlen(sha1_file_directory);
-		base = xmalloc(len + 60);
-		memcpy(base, sha1_file_directory, len);
-		memset(base+len, 0, 60);
-		base[len] = '/';
-		base[len+3] = '/';
-		name = base + len + 1;
-	}
-	fill_sha1_path(name, sha1);
-	return base;
+	objdir = get_object_directory();
+	len = strlen(objdir);
+
+	/* '/' + 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;
 }
 
 static char *sha1_get_pack_name(const unsigned char *sha1,
@@ -236,6 +226,7 @@ struct alternate_object_database *alt_odb_list;
 static struct alternate_object_database **alt_odb_tail;
 
 static void read_info_alternates(const char * alternates, int depth);
+static int git_open_noatime(const char *name);
 
 /*
  * Prepare alternate object database registry.
@@ -257,27 +248,30 @@ static int link_alt_odb_entry(const char * entry, int len, const char * relative
 	const char *objdir = get_object_directory();
 	struct alternate_object_database *ent;
 	struct alternate_object_database *alt;
-	/* 43 = 40-byte + 2 '/' + terminating NUL */
-	int pfxlen = len;
-	int entlen = pfxlen + 43;
-	int base_len = -1;
+	int pfxlen, entlen;
+	struct strbuf pathbuf = STRBUF_INIT;
 
 	if (!is_absolute_path(entry) && relative_base) {
-		/* Relative alt-odb */
-		if (base_len < 0)
-			base_len = strlen(relative_base) + 1;
-		entlen += base_len;
-		pfxlen += base_len;
+		strbuf_addstr(&pathbuf, real_path(relative_base));
+		strbuf_addch(&pathbuf, '/');
 	}
-	ent = xmalloc(sizeof(*ent) + entlen);
+	strbuf_add(&pathbuf, entry, len);
 
-	if (!is_absolute_path(entry) && relative_base) {
-		memcpy(ent->base, relative_base, base_len - 1);
-		ent->base[base_len - 1] = '/';
-		memcpy(ent->base + base_len, entry, len);
-	}
-	else
-		memcpy(ent->base, entry, pfxlen);
+	normalize_path_copy(pathbuf.buf, pathbuf.buf);
+
+	pfxlen = strlen(pathbuf.buf);
+
+	/*
+	 * 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;
+
+	entlen = pfxlen + 43; /* '/' + 2 hex + '/' + 38 hex + NUL */
+	ent = xmalloc(sizeof(*ent) + entlen);
+	memcpy(ent->base, pathbuf.buf, pfxlen);
+	strbuf_release(&pathbuf);
 
 	ent->name = ent->base + pfxlen + 1;
 	ent->base[pfxlen + 3] = '/';
@@ -369,7 +363,7 @@ static void read_info_alternates(const char * relative_base, int depth)
 	int fd;
 
 	sprintf(path, "%s/%s", relative_base, alt_file_name);
-	fd = open(path, O_RDONLY);
+	fd = git_open_noatime(path);
 	if (fd < 0)
 		return;
 	if (fstat(fd, &st) || (st.st_size == 0)) {
@@ -389,7 +383,7 @@ 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/objects\n", reference);
+	char *alt = mkpath("%s\n", reference);
 	write_or_die(fd, alt, strlen(alt));
 	if (commit_lock_file(lock))
 		die("could not close alternates file");
@@ -451,6 +445,8 @@ static unsigned int pack_used_ctr;
 static unsigned int pack_mmap_calls;
 static unsigned int peak_pack_open_windows;
 static unsigned int pack_open_windows;
+static unsigned int pack_open_fds;
+static unsigned int pack_max_fds;
 static size_t peak_pack_mapped;
 static size_t pack_mapped;
 struct packed_git *packed_git;
@@ -482,7 +478,7 @@ 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 = open(path, O_RDONLY);
+	int fd = git_open_noatime(path);
 	struct stat st;
 
 	if (fd < 0)
@@ -628,8 +624,10 @@ static int unuse_one_window(struct packed_git *current, int keep_fd)
 			lru_l->next = lru_w->next;
 		else {
 			lru_p->windows = lru_w->next;
-			if (!lru_p->windows && lru_p->pack_fd != keep_fd) {
+			if (!lru_p->windows && lru_p->pack_fd != -1
+				&& lru_p->pack_fd != keep_fd) {
 				close(lru_p->pack_fd);
+				pack_open_fds--;
 				lru_p->pack_fd = -1;
 			}
 		}
@@ -647,6 +645,21 @@ void release_pack_memory(size_t need, int fd)
 		; /* nothing */
 }
 
+void *xmmap(void *start, size_t length,
+	int prot, int flags, int fd, off_t offset)
+{
+	void *ret = mmap(start, length, prot, flags, fd, offset);
+	if (ret == MAP_FAILED) {
+		if (!length)
+			return NULL;
+		release_pack_memory(length, fd);
+		ret = mmap(start, length, prot, flags, fd, offset);
+		if (ret == MAP_FAILED)
+			die_errno("Out of memory? mmap failed");
+	}
+	return ret;
+}
+
 void close_pack_windows(struct packed_git *p)
 {
 	while (p->windows) {
@@ -672,6 +685,14 @@ void unuse_pack(struct pack_window **w_cursor)
 	}
 }
 
+void close_pack_index(struct packed_git *p)
+{
+	if (p->index_data) {
+		munmap((void *)p->index_data, p->index_size);
+		p->index_data = NULL;
+	}
+}
+
 /*
  * This is used by git-repack in case a newly created pack happens to
  * contain the same set of objects as an existing one.  In that case
@@ -691,10 +712,11 @@ void free_pack_by_name(const char *pack_name)
 		if (strcmp(pack_name, p->pack_name) == 0) {
 			clear_delta_base_cache();
 			close_pack_windows(p);
-			if (p->pack_fd != -1)
+			if (p->pack_fd != -1) {
 				close(p->pack_fd);
-			if (p->index_data)
-				munmap((void *)p->index_data, p->index_size);
+				pack_open_fds--;
+			}
+			close_pack_index(p);
 			free(p->bad_object_sha1);
 			*pp = p->next;
 			free(p);
@@ -719,9 +741,29 @@ static int open_packed_git_1(struct packed_git *p)
 	if (!p->index_data && open_pack_index(p))
 		return error("packfile %s index unavailable", p->pack_name);
 
-	p->pack_fd = open(p->pack_name, O_RDONLY);
+	if (!pack_max_fds) {
+		struct rlimit lim;
+		unsigned int max_fds;
+
+		if (getrlimit(RLIMIT_NOFILE, &lim))
+			die_errno("cannot get RLIMIT_NOFILE");
+
+		max_fds = lim.rlim_cur;
+
+		/* Save 3 for stdin/stdout/stderr, 22 for work */
+		if (25 < max_fds)
+			pack_max_fds = max_fds - 25;
+		else
+			pack_max_fds = 1;
+	}
+
+	while (pack_max_fds <= pack_open_fds && unuse_one_window(NULL, -1))
+		; /* nothing */
+
+	p->pack_fd = git_open_noatime(p->pack_name);
 	if (p->pack_fd < 0 || fstat(p->pack_fd, &st))
 		return -1;
+	pack_open_fds++;
 
 	/* If we created the struct before we had the pack we lack size. */
 	if (!p->pack_size) {
@@ -773,6 +815,7 @@ static int open_packed_git(struct packed_git *p)
 		return 0;
 	if (p->pack_fd != -1) {
 		close(p->pack_fd);
+		pack_open_fds--;
 		p->pack_fd = -1;
 	}
 	return -1;
@@ -794,18 +837,17 @@ static int in_window(struct pack_window *win, off_t offset)
 unsigned char *use_pack(struct packed_git *p,
 		struct pack_window **w_cursor,
 		off_t offset,
-		unsigned int *left)
+		unsigned long *left)
 {
 	struct pack_window *win = *w_cursor;
 
-	if (p->pack_fd == -1 && open_packed_git(p))
-		die("packfile %s cannot be accessed", p->pack_name);
-
 	/* Since packfiles end in a hash of their content and it's
 	 * pointless to ask for an offset into the middle of that
 	 * hash, and the in_window function above wouldn't match
 	 * don't allow an offset too close to the end of the file.
 	 */
+	if (!p->pack_size && p->pack_fd == -1 && open_packed_git(p))
+		die("packfile %s cannot be accessed", p->pack_name);
 	if (offset > (p->pack_size - 20))
 		die("offset beyond end of packfile (truncated pack?)");
 
@@ -819,6 +861,10 @@ unsigned char *use_pack(struct packed_git *p,
 		if (!win) {
 			size_t window_align = packed_git_window_size / 2;
 			off_t len;
+
+			if (p->pack_fd == -1 && open_packed_git(p))
+				die("packfile %s cannot be accessed", p->pack_name);
+
 			win = xcalloc(1, sizeof(*win));
 			win->offset = (offset / window_align) * window_align;
 			len = p->pack_size - win->offset;
@@ -836,6 +882,12 @@ unsigned char *use_pack(struct packed_git *p,
 				die("packfile %s cannot be mapped: %s",
 					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;
+			}
 			pack_mmap_calls++;
 			pack_open_windows++;
 			if (pack_mapped > peak_pack_mapped)
@@ -865,11 +917,22 @@ static struct packed_git *alloc_packed_git(int extra)
 	return p;
 }
 
+static void try_to_free_pack_memory(size_t size)
+{
+	release_pack_memory(size, -1);
+}
+
 struct packed_git *add_packed_git(const char *path, int 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);
 
+	if (!have_set_try_to_free_routine) {
+		have_set_try_to_free_routine = 1;
+		set_try_to_free_routine(try_to_free_pack_memory);
+	}
+
 	/*
 	 * Make sure a corresponding .pack file exists and that
 	 * the index looks sane.
@@ -902,9 +965,8 @@ struct packed_git *add_packed_git(const char *path, int path_len, int local)
 	return p;
 }
 
-struct packed_git *parse_pack_index(unsigned char *sha1)
+struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path)
 {
-	const char *idx_path = sha1_pack_index_name(sha1);
 	const char *path = sha1_pack_name(sha1);
 	struct packed_git *p = alloc_packed_git(strlen(path) + 1);
 
@@ -920,6 +982,9 @@ struct packed_git *parse_pack_index(unsigned char *sha1)
 
 void install_packed_git(struct packed_git *pack)
 {
+	if (pack->pack_fd != -1)
+		pack_open_fds++;
+
 	pack->next = packed_git;
 	packed_git = pack;
 }
@@ -1064,7 +1129,7 @@ static void mark_bad_packed_object(struct packed_git *p,
 	p->num_bad_objects++;
 }
 
-static int has_packed_and_bad(const unsigned char *sha1)
+static const struct packed_git *has_packed_and_bad(const unsigned char *sha1)
 {
 	struct packed_git *p;
 	unsigned i;
@@ -1072,8 +1137,8 @@ static int has_packed_and_bad(const unsigned char *sha1)
 	for (p = packed_git; p; p = p->next)
 		for (i = 0; i < p->num_bad_objects; i++)
 			if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i))
-				return 1;
-	return 0;
+				return p;
+	return NULL;
 }
 
 int check_sha1_signature(const unsigned char *sha1, void *map, unsigned long size, const char *type)
@@ -1086,15 +1151,20 @@ int check_sha1_signature(const unsigned char *sha1, void *map, unsigned long siz
 static int git_open_noatime(const char *name)
 {
 	static int sha1_file_open_flag = O_NOATIME;
-	int fd = open(name, O_RDONLY | sha1_file_open_flag);
 
-	/* Might the failure be due to O_NOATIME? */
-	if (fd < 0 && errno != ENOENT && sha1_file_open_flag) {
-		fd = open(name, O_RDONLY);
+	for (;;) {
+		int fd = open(name, O_RDONLY | sha1_file_open_flag);
 		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;
+			continue;
+		}
+
+		return -1;
 	}
-	return fd;
 }
 
 static int open_sha1_file(const unsigned char *sha1)
@@ -1119,7 +1189,7 @@ static int open_sha1_file(const unsigned char *sha1)
 	return -1;
 }
 
-static void *map_sha1_file(const unsigned char *sha1, unsigned long *size)
+void *map_sha1_file(const unsigned char *sha1, unsigned long *size)
 {
 	void *map;
 	int fd;
@@ -1138,28 +1208,56 @@ static void *map_sha1_file(const unsigned char *sha1, unsigned long *size)
 	return map;
 }
 
-static int legacy_loose_object(unsigned char *map)
+/*
+ * There used to be a second loose object header format which
+ * was meant to mimic the in-pack format, allowing for direct
+ * copy of the object data.  This format turned up not to be
+ * really worth it and we no longer write loose objects in that
+ * format.
+ */
+static int experimental_loose_object(unsigned char *map)
 {
 	unsigned int word;
 
 	/*
-	 * Is it a zlib-compressed buffer? If so, the first byte
-	 * must be 0x78 (15-bit window size, deflated), and the
-	 * first 16-bit word is evenly divisible by 31
+	 * We must determine if the buffer contains the standard
+	 * zlib-deflated stream or the experimental format based
+	 * on the in-pack object format. Compare the header byte
+	 * for each format:
+	 *
+	 * RFC1950 zlib w/ deflate : 0www1000 : 0 <= www <= 7
+	 * Experimental pack-based : Stttssss : ttt = 1,2,3,4
+	 *
+	 * If bit 7 is clear and bits 0-3 equal 8, the buffer MUST be
+	 * in standard loose-object format, UNLESS it is a Git-pack
+	 * format object *exactly* 8 bytes in size when inflated.
+	 *
+	 * However, RFC1950 also specifies that the 1st 16-bit word
+	 * must be divisible by 31 - this checksum tells us our buffer
+	 * is in the standard format, giving a false positive only if
+	 * the 1st word of the Git-pack format object happens to be
+	 * divisible by 31, ie:
+	 *      ((byte0 * 256) + byte1) % 31 = 0
+	 *   =>        0ttt10000www1000 % 31 = 0
+	 *
+	 * As it happens, this case can only arise for www=3 & ttt=1
+	 * - ie, a Commit object, which would have to be 8 bytes in
+	 * size. As no Commit can be that small, we find that the
+	 * combination of these two criteria (bitmask & checksum)
+	 * can always correctly determine the buffer format.
 	 */
 	word = (map[0] << 8) + map[1];
-	if (map[0] == 0x78 && !(word % 31))
-		return 1;
-	else
+	if ((map[0] & 0x8F) == 0x08 && !(word % 31))
 		return 0;
+	else
+		return 1;
 }
 
 unsigned long unpack_object_header_buffer(const unsigned char *buf,
 		unsigned long len, enum object_type *type, unsigned long *sizep)
 {
 	unsigned shift;
-	unsigned char c;
-	unsigned long size;
+	unsigned long size, c;
 	unsigned long used = 0;
 
 	c = buf[used++];
@@ -1167,9 +1265,10 @@ unsigned long unpack_object_header_buffer(const unsigned char *buf,
 	size = c & 15;
 	shift = 4;
 	while (c & 0x80) {
-		if (len <= used || sizeof(long) * 8 <= shift) {
+		if (len <= used || bitsizeof(long) <= shift) {
 			error("bad object header");
-			return 0;
+			size = used = 0;
+			break;
 		}
 		c = buf[used++];
 		size += (c & 0x7f) << shift;
@@ -1179,7 +1278,7 @@ unsigned long unpack_object_header_buffer(const unsigned char *buf,
 	return used;
 }
 
-static int unpack_sha1_header(z_stream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz)
+int unpack_sha1_header(git_zstream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz)
 {
 	unsigned long size, used;
 	static const char valid_loose_object_type[8] = {
@@ -1196,40 +1295,35 @@ static int unpack_sha1_header(z_stream *stream, unsigned char *map, unsigned lon
 	stream->next_out = buffer;
 	stream->avail_out = bufsiz;
 
-	if (legacy_loose_object(map)) {
-		git_inflate_init(stream);
-		return git_inflate(stream, 0);
-	}
-
+	if (experimental_loose_object(map)) {
+		/*
+		 * The old experimental format we no longer produce;
+		 * we can still read it.
+		 */
+		used = unpack_object_header_buffer(map, mapsize, &type, &size);
+		if (!used || !valid_loose_object_type[type])
+			return -1;
+		map += used;
+		mapsize -= used;
 
-	/*
-	 * There used to be a second loose object header format which
-	 * was meant to mimic the in-pack format, allowing for direct
-	 * copy of the object data.  This format turned up not to be
-	 * really worth it and we don't write it any longer.  But we
-	 * can still read it.
-	 */
-	used = unpack_object_header_buffer(map, mapsize, &type, &size);
-	if (!used || !valid_loose_object_type[type])
-		return -1;
-	map += used;
-	mapsize -= used;
+		/* Set up the stream for the rest.. */
+		stream->next_in = map;
+		stream->avail_in = mapsize;
+		git_inflate_init(stream);
 
-	/* Set up the stream for the rest.. */
-	stream->next_in = map;
-	stream->avail_in = mapsize;
+		/* And generate the fake traditional header */
+		stream->total_out = 1 + snprintf(buffer, bufsiz, "%s %lu",
+						 typename(type), size);
+		return 0;
+	}
 	git_inflate_init(stream);
-
-	/* And generate the fake traditional header */
-	stream->total_out = 1 + snprintf(buffer, bufsiz, "%s %lu",
-					 typename(type), size);
-	return 0;
+	return git_inflate(stream, 0);
 }
 
-static void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size, const unsigned char *sha1)
+static void *unpack_sha1_rest(git_zstream *stream, void *buffer, unsigned long size, const unsigned char *sha1)
 {
 	int bytes = strlen(buffer) + 1;
-	unsigned char *buf = xmalloc(1+size);
+	unsigned char *buf = xmallocz(size);
 	unsigned long n;
 	int status = Z_OK;
 
@@ -1242,7 +1336,7 @@ static void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size
 		/*
 		 * The above condition must be (bytes <= size), not
 		 * (bytes < size).  In other words, even though we
-		 * expect no more output and set avail_out to zer0,
+		 * expect no more output and set avail_out to zero,
 		 * the input zlib stream may have bytes that express
 		 * "this concludes the stream", and we *do* want to
 		 * eat that input.
@@ -1257,7 +1351,6 @@ static void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size
 		while (status == Z_OK)
 			status = git_inflate(stream, Z_FINISH);
 	}
-	buf[size] = 0;
 	if (status == Z_STREAM_END && !stream->avail_in) {
 		git_inflate_end(stream);
 		return buf;
@@ -1277,7 +1370,7 @@ static void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size
  * too permissive for what we want to check. So do an anal
  * object header parse by hand.
  */
-static int parse_sha1_header(const char *hdr, unsigned long *sizep)
+int parse_sha1_header(const char *hdr, unsigned long *sizep)
 {
 	char type[10];
 	int i;
@@ -1326,7 +1419,7 @@ static int parse_sha1_header(const char *hdr, unsigned long *sizep)
 static void *unpack_sha1_file(void *map, unsigned long mapsize, enum object_type *type, unsigned long *size, const unsigned char *sha1)
 {
 	int ret;
-	z_stream stream;
+	git_zstream stream;
 	char hdr[8192];
 
 	ret = unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr));
@@ -1342,7 +1435,7 @@ unsigned long get_size_from_delta(struct packed_git *p,
 {
 	const unsigned char *data;
 	unsigned char delta_head[20], *in;
-	z_stream stream;
+	git_zstream stream;
 	int st;
 
 	memset(&stream, 0, sizeof(stream));
@@ -1416,7 +1509,7 @@ static off_t get_delta_base(struct packed_git *p,
 
 /* forward declaration for a mutually recursive function */
 static int packed_object_info(struct packed_git *p, off_t offset,
-			      unsigned long *sizep);
+			      unsigned long *sizep, int *rtype);
 
 static int packed_delta_info(struct packed_git *p,
 			     struct pack_window **w_curs,
@@ -1430,7 +1523,7 @@ static int packed_delta_info(struct packed_git *p,
 	base_offset = get_delta_base(p, w_curs, &curpos, type, obj_offset);
 	if (!base_offset)
 		return OBJ_BAD;
-	type = packed_object_info(p, base_offset, NULL);
+	type = packed_object_info(p, base_offset, NULL, NULL);
 	if (type <= OBJ_NONE) {
 		struct revindex_entry *revidx;
 		const unsigned char *base_sha1;
@@ -1458,18 +1551,18 @@ static int packed_delta_info(struct packed_git *p,
 	return type;
 }
 
-static int unpack_object_header(struct packed_git *p,
-				struct pack_window **w_curs,
-				off_t *curpos,
-				unsigned long *sizep)
+int unpack_object_header(struct packed_git *p,
+			 struct pack_window **w_curs,
+			 off_t *curpos,
+			 unsigned long *sizep)
 {
 	unsigned char *base;
-	unsigned int left;
+	unsigned long left;
 	unsigned long used;
 	enum object_type type;
 
 	/* use_pack() assures us we have [base, base + 20) available
-	 * as a range that we can look at at.  (Its actually the hash
+	 * as a range that we can look at.  (Its actually the hash
 	 * size that is assured.)  With our object header encoding
 	 * the maximum deflated object size is 2^137, which is just
 	 * insane, so we know won't exceed what we have been given.
@@ -1484,63 +1577,8 @@ static int unpack_object_header(struct packed_git *p,
 	return type;
 }
 
-const char *packed_object_info_detail(struct packed_git *p,
-				      off_t obj_offset,
-				      unsigned long *size,
-				      unsigned long *store_size,
-				      unsigned int *delta_chain_length,
-				      unsigned char *base_sha1)
-{
-	struct pack_window *w_curs = NULL;
-	off_t curpos;
-	unsigned long dummy;
-	unsigned char *next_sha1;
-	enum object_type type;
-	struct revindex_entry *revidx;
-
-	*delta_chain_length = 0;
-	curpos = obj_offset;
-	type = unpack_object_header(p, &w_curs, &curpos, size);
-
-	revidx = find_pack_revindex(p, obj_offset);
-	*store_size = revidx[1].offset - obj_offset;
-
-	for (;;) {
-		switch (type) {
-		default:
-			die("pack %s contains unknown object type %d",
-			    p->pack_name, type);
-		case OBJ_COMMIT:
-		case OBJ_TREE:
-		case OBJ_BLOB:
-		case OBJ_TAG:
-			unuse_pack(&w_curs);
-			return typename(type);
-		case OBJ_OFS_DELTA:
-			obj_offset = get_delta_base(p, &w_curs, &curpos, type, obj_offset);
-			if (!obj_offset)
-				die("pack %s contains bad delta base reference of type %s",
-				    p->pack_name, typename(type));
-			if (*delta_chain_length == 0) {
-				revidx = find_pack_revindex(p, obj_offset);
-				hashcpy(base_sha1, nth_packed_object_sha1(p, revidx->nr));
-			}
-			break;
-		case OBJ_REF_DELTA:
-			next_sha1 = use_pack(p, &w_curs, curpos, NULL);
-			if (*delta_chain_length == 0)
-				hashcpy(base_sha1, next_sha1);
-			obj_offset = find_pack_entry_one(next_sha1, p);
-			break;
-		}
-		(*delta_chain_length)++;
-		curpos = obj_offset;
-		type = unpack_object_header(p, &w_curs, &curpos, &dummy);
-	}
-}
-
 static int packed_object_info(struct packed_git *p, off_t obj_offset,
-			      unsigned long *sizep)
+			      unsigned long *sizep, int *rtype)
 {
 	struct pack_window *w_curs = NULL;
 	unsigned long size;
@@ -1548,6 +1586,8 @@ static int packed_object_info(struct packed_git *p, off_t obj_offset,
 	enum object_type type;
 
 	type = unpack_object_header(p, &w_curs, &curpos, &size);
+	if (rtype)
+		*rtype = type; /* representation type */
 
 	switch (type) {
 	case OBJ_OFS_DELTA:
@@ -1577,20 +1617,21 @@ static void *unpack_compressed_entry(struct packed_git *p,
 				    unsigned long size)
 {
 	int st;
-	z_stream stream;
+	git_zstream stream;
 	unsigned char *buffer, *in;
 
-	buffer = xmalloc(size + 1);
-	buffer[size] = 0;
+	buffer = xmallocz(size);
 	memset(&stream, 0, sizeof(stream));
 	stream.next_out = buffer;
-	stream.avail_out = size;
+	stream.avail_out = size + 1;
 
 	git_inflate_init(&stream);
 	do {
 		in = use_pack(p, w_curs, curpos, &stream.avail_in);
 		stream.next_in = in;
 		st = git_inflate(&stream, Z_FINISH);
+		if (!stream.avail_out)
+			break; /* the payload is larger than it should be */
 		curpos += stream.next_in - in;
 	} while (st == Z_OK || st == Z_BUF_ERROR);
 	git_inflate_end(&stream);
@@ -1629,6 +1670,13 @@ static unsigned long pack_entry_hash(struct packed_git *p, off_t base_offset)
 	return hash % MAX_DELTA_CACHE;
 }
 
+static int in_delta_base_cache(struct packed_git *p, off_t base_offset)
+{
+	unsigned long hash = pack_entry_hash(p, base_offset);
+	struct delta_base_cache_entry *ent = delta_base_cache + hash;
+	return (ent->data && ent->p == p && ent->base_offset == base_offset);
+}
+
 static void *cache_or_unpack_entry(struct packed_git *p, off_t base_offset,
 	unsigned long *base_size, enum object_type *type, int keep_cache)
 {
@@ -1773,6 +1821,24 @@ static void *unpack_delta_entry(struct packed_git *p,
 	return result;
 }
 
+static void write_pack_access_log(struct packed_git *p, off_t obj_offset)
+{
+	static FILE *log_file;
+
+	if (!log_file) {
+		log_file = fopen(log_pack_access, "w");
+		if (!log_file) {
+			error("cannot open pack access log '%s' for writing: %s",
+			      log_pack_access, strerror(errno));
+			log_pack_access = NULL;
+			return;
+		}
+	}
+	fprintf(log_file, "%s %"PRIuMAX"\n",
+		p->pack_name, (uintmax_t)obj_offset);
+	fflush(log_file);
+}
+
 int do_check_packed_object_crc;
 
 void *unpack_entry(struct packed_git *p, off_t obj_offset,
@@ -1782,6 +1848,9 @@ void *unpack_entry(struct packed_git *p, off_t obj_offset,
 	off_t curpos = obj_offset;
 	void *data;
 
+	if (log_pack_access)
+		write_pack_access_log(p, obj_offset);
+
 	if (do_check_packed_object_crc && p->index_version > 1) {
 		struct revindex_entry *revidx = find_pack_revindex(p, obj_offset);
 		unsigned long len = revidx[1].offset - obj_offset;
@@ -1919,6 +1988,27 @@ off_t find_pack_entry_one(const unsigned char *sha1,
 	return 0;
 }
 
+int is_pack_valid(struct packed_git *p)
+{
+	/* An already open pack is known to be valid. */
+	if (p->pack_fd != -1)
+		return 1;
+
+	/* If the pack has one window completely covering the
+	 * file size, the pack is known to be valid even if
+	 * the descriptor is not currently open.
+	 */
+	if (p->windows) {
+		struct pack_window *w = p->windows;
+
+		if (!w->offset && w->len == p->pack_size)
+			return 1;
+	}
+
+	/* Force the pack to open to prove its valid. */
+	return !open_packed_git(p);
+}
+
 static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e)
 {
 	static struct packed_git *last_found = (void *)1;
@@ -1948,8 +2038,8 @@ static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e)
 			 * it may have been deleted since the index
 			 * was loaded!
 			 */
-			if (p->pack_fd == -1 && open_packed_git(p)) {
-				error("packfile %s cannot be accessed", p->pack_name);
+			if (!is_pack_valid(p)) {
+				warning("packfile %s cannot be accessed", p->pack_name);
 				goto next;
 			}
 			e->offset = offset;
@@ -1988,7 +2078,7 @@ static int sha1_loose_object_info(const unsigned char *sha1, unsigned long *size
 	int status;
 	unsigned long mapsize, size;
 	void *map;
-	z_stream stream;
+	git_zstream stream;
 	char hdr[32];
 
 	map = map_sha1_file(sha1, &mapsize);
@@ -2006,16 +2096,28 @@ static int sha1_loose_object_info(const unsigned char *sha1, unsigned long *size
 	return status;
 }
 
-int sha1_object_info(const unsigned char *sha1, unsigned long *sizep)
+/* returns enum object_type or negative */
+int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi)
 {
+	struct cached_object *co;
 	struct pack_entry e;
-	int status;
+	int status, rtype;
+
+	co = find_cached_object(sha1);
+	if (co) {
+		if (oi->sizep)
+			*(oi->sizep) = co->size;
+		oi->whence = OI_CACHED;
+		return co->type;
+	}
 
 	if (!find_pack_entry(sha1, &e)) {
 		/* Most likely it's a loose object. */
-		status = sha1_loose_object_info(sha1, sizep);
-		if (status >= 0)
+		status = sha1_loose_object_info(sha1, oi->sizep);
+		if (status >= 0) {
+			oi->whence = OI_LOOSE;
 			return status;
+		}
 
 		/* Not a loose object; someone else may have just packed it. */
 		reprepare_packed_git();
@@ -2023,15 +2125,31 @@ int sha1_object_info(const unsigned char *sha1, unsigned long *sizep)
 			return status;
 	}
 
-	status = packed_object_info(e.p, e.offset, sizep);
+	status = packed_object_info(e.p, e.offset, oi->sizep, &rtype);
 	if (status < 0) {
 		mark_bad_packed_object(e.p, sha1);
-		status = sha1_object_info(sha1, sizep);
+		status = sha1_object_info_extended(sha1, oi);
+	} else if (in_delta_base_cache(e.p, e.offset)) {
+		oi->whence = OI_DBCACHED;
+	} else {
+		oi->whence = OI_PACKED;
+		oi->u.packed.offset = e.offset;
+		oi->u.packed.pack = e.p;
+		oi->u.packed.is_delta = (rtype == OBJ_REF_DELTA ||
+					 rtype == OBJ_OFS_DELTA);
 	}
 
 	return status;
 }
 
+int sha1_object_info(const unsigned char *sha1, unsigned long *sizep)
+{
+	struct object_info oi;
+
+	oi.sizep = sizep;
+	return sha1_object_info_extended(sha1, &oi);
+}
+
 static void *read_packed_sha1(const unsigned char *sha1,
 			      enum object_type *type, unsigned long *size)
 {
@@ -2056,41 +2174,6 @@ static void *read_packed_sha1(const unsigned char *sha1,
 	return data;
 }
 
-/*
- * This is meant to hold a *small* number of objects that you would
- * want read_sha1_file() to be able to return, but yet you do not want
- * to write them into the object store (e.g. a browse-only
- * application).
- */
-static struct cached_object {
-	unsigned char sha1[20];
-	enum object_type type;
-	void *buf;
-	unsigned long size;
-} *cached_objects;
-static int cached_object_nr, cached_object_alloc;
-
-static struct cached_object empty_tree = {
-	EMPTY_TREE_SHA1_BIN,
-	OBJ_TREE,
-	"",
-	0
-};
-
-static struct cached_object *find_cached_object(const unsigned char *sha1)
-{
-	int i;
-	struct cached_object *co = cached_objects;
-
-	for (i = 0; i < cached_object_nr; i++, co++) {
-		if (!hashcmp(co->sha1, sha1))
-			return co;
-	}
-	if (!hashcmp(sha1, empty_tree.sha1))
-		return &empty_tree;
-	return NULL;
-}
-
 int pretend_sha1_file(void *buf, unsigned long len, enum object_type type,
 		      unsigned char *sha1)
 {
@@ -2141,14 +2224,46 @@ static void *read_object(const unsigned char *sha1, enum object_type *type,
 	return read_packed_sha1(sha1, type, size);
 }
 
-void *read_sha1_file(const unsigned char *sha1, enum object_type *type,
-		     unsigned long *size)
+/*
+ * This function dies on corrupt objects; the callers who want to
+ * deal with them should arrange to call read_object() and give error
+ * messages themselves.
+ */
+void *read_sha1_file_extended(const unsigned char *sha1,
+			      enum object_type *type,
+			      unsigned long *size,
+			      unsigned flag)
 {
-	void *data = read_object(sha1, type, size);
-	/* legacy behavior is to die on corrupted objects */
-	if (!data && (has_loose_object(sha1) || has_packed_and_bad(sha1)))
-		die("object %s is corrupted", sha1_to_hex(sha1));
-	return data;
+	void *data;
+	char *path;
+	const struct packed_git *p;
+	const unsigned char *repl = (flag & READ_SHA1_FILE_REPLACE)
+		? lookup_replace_object(sha1) : sha1;
+
+	errno = 0;
+	data = read_object(repl, type, size);
+	if (data)
+		return data;
+
+	if (errno && errno != ENOENT)
+		die_errno("failed to read object %s", sha1_to_hex(sha1));
+
+	/* die if we replaced an object with one that does not exist */
+	if (repl != sha1)
+		die("replacement %s not found for %s",
+		    sha1_to_hex(repl), sha1_to_hex(sha1));
+
+	if (has_loose_object(repl)) {
+		path = sha1_file_name(sha1);
+		die("loose object %s (stored in %s) is corrupt",
+		    sha1_to_hex(repl), path);
+	}
+
+	if ((p = has_packed_and_bad(repl)) != NULL)
+		die("packed object %s (stored in %s) is corrupt",
+		    sha1_to_hex(repl), p->pack_name);
+
+	return NULL;
 }
 
 void *read_object_with_reference(const unsigned char *sha1,
@@ -2247,7 +2362,7 @@ int move_temp_to_file(const char *tmpfile, const char *filename)
 			goto out;
 		ret = errno;
 	}
-	unlink(tmpfile);
+	unlink_or_warn(tmpfile);
 	if (ret) {
 		if (ret != EEXIST) {
 			return error("unable to write sha1 filename %s: %s\n", filename, strerror(ret));
@@ -2256,7 +2371,7 @@ int move_temp_to_file(const char *tmpfile, const char *filename)
 	}
 
 out:
-	if (set_shared_perm(filename, (S_IFREG|0444)))
+	if (adjust_shared_perm(filename))
 		return error("unable to set permission to '%s'", filename);
 	return 0;
 }
@@ -2283,7 +2398,7 @@ static void close_sha1_file(int fd)
 	if (fsync_object_files)
 		fsync_or_die(fd, "sha1 file");
 	if (close(fd) != 0)
-		die("error when closing sha1 file (%s)", strerror(errno));
+		die_errno("error when closing sha1 file");
 }
 
 /* Size of directory component, including the ending '/' */
@@ -2312,7 +2427,7 @@ static int create_tmpfile(char *buffer, size_t bufsiz, const char *filename)
 	}
 	memcpy(buffer, filename, dirlen);
 	strcpy(buffer + dirlen, "tmp_obj_XXXXXX");
-	fd = mkstemp(buffer);
+	fd = git_mkstemp_mode(buffer, 0444);
 	if (fd < 0 && dirlen && errno == ENOENT) {
 		/* Make sure the directory exists */
 		memcpy(buffer, filename, dirlen);
@@ -2322,18 +2437,19 @@ static int create_tmpfile(char *buffer, size_t bufsiz, const char *filename)
 
 		/* Try again */
 		strcpy(buffer + dirlen - 1, "/tmp_obj_XXXXXX");
-		fd = mkstemp(buffer);
+		fd = git_mkstemp_mode(buffer, 0444);
 	}
 	return fd;
 }
 
 static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen,
-			      void *buf, unsigned long len, time_t mtime)
+			      const void *buf, unsigned long len, time_t mtime)
 {
 	int fd, ret;
-	size_t size;
-	unsigned char *compressed;
-	z_stream stream;
+	unsigned char compressed[4096];
+	git_zstream stream;
+	git_SHA_CTX c;
+	unsigned char parano_sha1[20];
 	char *filename;
 	static char tmpfile[PATH_MAX];
 
@@ -2348,37 +2464,41 @@ static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen,
 
 	/* Set it up */
 	memset(&stream, 0, sizeof(stream));
-	deflateInit(&stream, zlib_compression_level);
-	size = 8 + deflateBound(&stream, len+hdrlen);
-	compressed = xmalloc(size);
-
-	/* Compress it */
+	git_deflate_init(&stream, zlib_compression_level);
 	stream.next_out = compressed;
-	stream.avail_out = size;
+	stream.avail_out = sizeof(compressed);
+	git_SHA1_Init(&c);
 
 	/* First header.. */
 	stream.next_in = (unsigned char *)hdr;
 	stream.avail_in = hdrlen;
-	while (deflate(&stream, 0) == Z_OK)
-		/* nothing */;
+	while (git_deflate(&stream, 0) == Z_OK)
+		; /* nothing */
+	git_SHA1_Update(&c, hdr, hdrlen);
 
 	/* Then the data itself.. */
-	stream.next_in = buf;
+	stream.next_in = (void *)buf;
 	stream.avail_in = len;
-	ret = deflate(&stream, Z_FINISH);
+	do {
+		unsigned char *in0 = stream.next_in;
+		ret = git_deflate(&stream, Z_FINISH);
+		git_SHA1_Update(&c, in0, stream.next_in - in0);
+		if (write_buffer(fd, compressed, stream.next_out - compressed) < 0)
+			die("unable to write sha1 file");
+		stream.next_out = compressed;
+		stream.avail_out = sizeof(compressed);
+	} while (ret == Z_OK);
+
 	if (ret != Z_STREAM_END)
 		die("unable to deflate new object %s (%d)", sha1_to_hex(sha1), ret);
-
-	ret = deflateEnd(&stream);
+	ret = git_deflate_end_gently(&stream);
 	if (ret != Z_OK)
 		die("deflateEnd on object %s failed (%d)", sha1_to_hex(sha1), ret);
+	git_SHA1_Final(parano_sha1, &c);
+	if (hashcmp(sha1, parano_sha1) != 0)
+		die("confused by unstable object source data for %s", sha1_to_hex(sha1));
 
-	size = stream.total_out;
-
-	if (write_buffer(fd, compressed, size) < 0)
-		die("unable to write sha1 file");
 	close_sha1_file(fd);
-	free(compressed);
 
 	if (mtime) {
 		struct utimbuf utb;
@@ -2392,7 +2512,7 @@ static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen,
 	return move_temp_to_file(tmpfile, filename);
 }
 
-int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned char *returnsha1)
+int write_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *returnsha1)
 {
 	unsigned char sha1[20];
 	char hdr[32];
@@ -2438,14 +2558,6 @@ int has_pack_index(const unsigned char *sha1)
 	return 1;
 }
 
-int has_pack_file(const unsigned char *sha1)
-{
-	struct stat st;
-	if (stat(sha1_pack_name(sha1), &st))
-		return 0;
-	return 1;
-}
-
 int has_sha1_pack(const unsigned char *sha1)
 {
 	struct pack_entry e;
@@ -2461,10 +2573,40 @@ int has_sha1_file(const unsigned char *sha1)
 	return has_loose_object(sha1);
 }
 
+static void check_tree(const void *buf, size_t size)
+{
+	struct tree_desc desc;
+	struct name_entry entry;
+
+	init_tree_desc(&desc, buf, size);
+	while (tree_entry(&desc, &entry))
+		/* do nothing
+		 * tree_entry() will die() on malformed entries */
+		;
+}
+
+static void check_commit(const void *buf, size_t size)
+{
+	struct commit c;
+	memset(&c, 0, sizeof(c));
+	if (parse_commit_buffer(&c, buf, size))
+		die("corrupt commit");
+}
+
+static void check_tag(const void *buf, size_t size)
+{
+	struct tag t;
+	memset(&t, 0, sizeof(t));
+	if (parse_tag_buffer(&t, buf, size))
+		die("corrupt tag");
+}
+
 static int index_mem(unsigned char *sha1, void *buf, size_t size,
-		     int write_object, enum object_type type, const char *path)
+		     enum object_type type,
+		     const char *path, unsigned flags)
 {
 	int ret, re_allocated = 0;
+	int write_object = flags & HASH_WRITE_OBJECT;
 
 	if (!type)
 		type = OBJ_BLOB;
@@ -2475,11 +2617,19 @@ static int index_mem(unsigned char *sha1, void *buf, size_t size,
 	if ((type == OBJ_BLOB) && path) {
 		struct strbuf nbuf = STRBUF_INIT;
 		if (convert_to_git(path, buf, size, &nbuf,
-		                   write_object ? safe_crlf : 0)) {
+				   write_object ? safe_crlf : SAFE_CRLF_FALSE)) {
 			buf = strbuf_detach(&nbuf, &size);
 			re_allocated = 1;
 		}
 	}
+	if (flags & HASH_FORMAT_CHECK) {
+		if (type == OBJ_TREE)
+			check_tree(buf, size);
+		if (type == OBJ_COMMIT)
+			check_commit(buf, size);
+		if (type == OBJ_TAG)
+			check_tag(buf, size);
+	}
 
 	if (write_object)
 		ret = write_sha1_file(buf, size, typename(type), sha1);
@@ -2490,31 +2640,141 @@ static int index_mem(unsigned char *sha1, void *buf, size_t size,
 	return ret;
 }
 
-int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object,
-	     enum object_type type, const char *path)
+static int index_pipe(unsigned char *sha1, int fd, enum object_type type,
+		      const char *path, unsigned flags)
 {
+	struct strbuf sbuf = STRBUF_INIT;
 	int ret;
-	size_t size = xsize_t(st->st_size);
 
-	if (!S_ISREG(st->st_mode)) {
-		struct strbuf sbuf = STRBUF_INIT;
-		if (strbuf_read(&sbuf, fd, 4096) >= 0)
-			ret = index_mem(sha1, sbuf.buf, sbuf.len, write_object,
-					type, path);
+	if (strbuf_read(&sbuf, fd, 4096) >= 0)
+		ret = index_mem(sha1, sbuf.buf, sbuf.len, type,	path, flags);
+	else
+		ret = -1;
+	strbuf_release(&sbuf);
+	return ret;
+}
+
+#define SMALL_FILE_SIZE (32*1024)
+
+static int index_core(unsigned char *sha1, int fd, size_t size,
+		      enum object_type type, const char *path,
+		      unsigned flags)
+{
+	int ret;
+
+	if (!size) {
+		ret = index_mem(sha1, NULL, size, type, path, flags);
+	} else if (size <= SMALL_FILE_SIZE) {
+		char *buf = xmalloc(size);
+		if (size == read_in_full(fd, buf, size))
+			ret = index_mem(sha1, buf, size, type, path, flags);
 		else
-			ret = -1;
-		strbuf_release(&sbuf);
-	} else if (size) {
+			ret = error("short read %s", strerror(errno));
+		free(buf);
+	} else {
 		void *buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0);
-		ret = index_mem(sha1, buf, size, write_object, type, path);
+		ret = index_mem(sha1, buf, size, type, path, flags);
 		munmap(buf, size);
-	} else
-		ret = index_mem(sha1, NULL, size, write_object, type, path);
+	}
+	return ret;
+}
+
+/*
+ * This creates one packfile per large blob, because the caller
+ * immediately wants the result sha1, and fast-import can report the
+ * object name via marks mechanism only by closing the created
+ * packfile.
+ *
+ * This also bypasses the usual "convert-to-git" dance, and that is on
+ * purpose. We could write a streaming version of the converting
+ * functions and insert that before feeding the data to fast-import
+ * (or equivalent in-core API described above), but the primary
+ * motivation for trying to stream from the working tree file and to
+ * avoid mmaping it in core is to deal with large binary blobs, and
+ * by definition they do _not_ want to get any conversion.
+ */
+static int index_stream(unsigned char *sha1, int fd, size_t size,
+			enum object_type type, const char *path,
+			unsigned flags)
+{
+	struct child_process fast_import;
+	char export_marks[512];
+	const char *argv[] = { "fast-import", "--quiet", export_marks, NULL };
+	char tmpfile[512];
+	char fast_import_cmd[512];
+	char buf[512];
+	int len, tmpfd;
+
+	strcpy(tmpfile, git_path("hashstream_XXXXXX"));
+	tmpfd = git_mkstemp_mode(tmpfile, 0600);
+	if (tmpfd < 0)
+		die_errno("cannot create tempfile: %s", tmpfile);
+	if (close(tmpfd))
+		die_errno("cannot close tempfile: %s", tmpfile);
+	sprintf(export_marks, "--export-marks=%s", tmpfile);
+
+	memset(&fast_import, 0, sizeof(fast_import));
+	fast_import.in = -1;
+	fast_import.argv = argv;
+	fast_import.git_cmd = 1;
+	if (start_command(&fast_import))
+		die_errno("index-stream: git fast-import failed");
+
+	len = sprintf(fast_import_cmd, "blob\nmark :1\ndata %lu\n",
+		      (unsigned long) size);
+	write_or_whine(fast_import.in, fast_import_cmd, len,
+		       "index-stream: feeding fast-import");
+	while (size) {
+		char buf[10240];
+		size_t sz = size < sizeof(buf) ? size : sizeof(buf);
+		ssize_t actual;
+
+		actual = read_in_full(fd, buf, sz);
+		if (actual < 0)
+			die_errno("index-stream: reading input");
+		if (write_in_full(fast_import.in, buf, actual) != actual)
+			die_errno("index-stream: feeding fast-import");
+		size -= actual;
+	}
+	if (close(fast_import.in))
+		die_errno("index-stream: closing fast-import");
+	if (finish_command(&fast_import))
+		die_errno("index-stream: finishing fast-import");
+
+	tmpfd = open(tmpfile, O_RDONLY);
+	if (tmpfd < 0)
+		die_errno("index-stream: cannot open fast-import mark");
+	len = read(tmpfd, buf, sizeof(buf));
+	if (len < 0)
+		die_errno("index-stream: reading fast-import mark");
+	if (close(tmpfd) < 0)
+		die_errno("index-stream: closing fast-import mark");
+	if (unlink(tmpfile))
+		die_errno("index-stream: unlinking fast-import mark");
+	if (len != 44 ||
+	    memcmp(":1 ", buf, 3) ||
+	    get_sha1_hex(buf + 3, sha1))
+		die_errno("index-stream: unexpected fast-import mark: <%s>", buf);
+	return 0;
+}
+
+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))
+		ret = index_pipe(sha1, fd, type, path, flags);
+	else if (size <= big_file_threshold || type != OBJ_BLOB)
+		ret = index_core(sha1, fd, size, type, path, flags);
+	else
+		ret = index_stream(sha1, fd, size, type, path, flags);
 	close(fd);
 	return ret;
 }
 
-int index_path(unsigned char *sha1, const char *path, struct stat *st, int write_object)
+int index_path(unsigned char *sha1, const char *path, struct stat *st, unsigned flags)
 {
 	int fd;
 	struct strbuf sb = STRBUF_INIT;
@@ -2525,7 +2785,7 @@ int index_path(unsigned char *sha1, const char *path, struct stat *st, int write
 		if (fd < 0)
 			return error("open(\"%s\"): %s", path,
 				     strerror(errno));
-		if (index_fd(sha1, fd, st, write_object, OBJ_BLOB, path) < 0)
+		if (index_fd(sha1, fd, st, OBJ_BLOB, path, flags) < 0)
 			return error("%s: failed to insert into database",
 				     path);
 		break;
@@ -2535,7 +2795,7 @@ int index_path(unsigned char *sha1, const char *path, struct stat *st, int write
 			return error("readlink(\"%s\"): %s", path,
 			             errstr);
 		}
-		if (!write_object)
+		if (!(flags & HASH_WRITE_OBJECT))
 			hash_sha1_file(sb.buf, sb.len, blob_type, sha1);
 		else if (write_sha1_file(sb.buf, sb.len, blob_type, sha1))
 			return error("%s: failed to insert into database",
@@ -2564,3 +2824,13 @@ int read_pack_header(int fd, struct pack_header *header)
 		return PH_ERROR_PROTOCOL;
 	return 0;
 }
+
+void assert_sha1_type(const unsigned char *sha1, enum object_type expect)
+{
+	enum object_type type = sha1_object_info(sha1, NULL);
+	if (type < 0)
+		die("%s is not a valid object", sha1_to_hex(sha1));
+	if (type != expect)
+		die("%s is not a valid '%s' object", sha1_to_hex(sha1),
+		    typename(expect));
+}