1 files changed, 239 insertions, 69 deletions

diff --git a/object-file.c b/object-file.c
index b5d1d12b68..c1b71c2834 100644
--- a/object-file.c
+++ b/object-file.c
@@ -140,27 +140,32 @@ static void git_hash_sha256_final_oid(struct object_id *oid, git_hash_ctx *ctx)
 	oid->algo = GIT_HASH_SHA256;
 }
 
-static void git_hash_unknown_init(git_hash_ctx *ctx)
+static void git_hash_unknown_init(git_hash_ctx *ctx UNUSED)
 {
 	BUG("trying to init unknown hash");
 }
 
-static void git_hash_unknown_clone(git_hash_ctx *dst, const git_hash_ctx *src)
+static void git_hash_unknown_clone(git_hash_ctx *dst UNUSED,
+				   const git_hash_ctx *src UNUSED)
 {
 	BUG("trying to clone unknown hash");
 }
 
-static void git_hash_unknown_update(git_hash_ctx *ctx, const void *data, size_t len)
+static void git_hash_unknown_update(git_hash_ctx *ctx UNUSED,
+				    const void *data UNUSED,
+				    size_t len UNUSED)
 {
 	BUG("trying to update unknown hash");
 }
 
-static void git_hash_unknown_final(unsigned char *hash, git_hash_ctx *ctx)
+static void git_hash_unknown_final(unsigned char *hash UNUSED,
+				   git_hash_ctx *ctx UNUSED)
 {
 	BUG("trying to finalize unknown hash");
 }
 
-static void git_hash_unknown_final_oid(struct object_id *oid, git_hash_ctx *ctx)
+static void git_hash_unknown_final_oid(struct object_id *oid UNUSED,
+				       git_hash_ctx *ctx UNUSED)
 {
 	BUG("trying to finalize unknown hash");
 }
@@ -503,7 +508,9 @@ static int link_alt_odb_entry(struct repository *r, const struct strbuf *entry,
 {
 	struct object_directory *ent;
 	struct strbuf pathbuf = STRBUF_INIT;
+	struct strbuf tmp = STRBUF_INIT;
 	khiter_t pos;
+	int ret = -1;
 
 	if (!is_absolute_path(entry->buf) && relative_base) {
 		strbuf_realpath(&pathbuf, relative_base, 1);
@@ -511,12 +518,12 @@ static int link_alt_odb_entry(struct repository *r, const struct strbuf *entry,
 	}
 	strbuf_addbuf(&pathbuf, entry);
 
-	if (strbuf_normalize_path(&pathbuf) < 0 && relative_base) {
+	if (!strbuf_realpath(&tmp, pathbuf.buf, 0)) {
 		error(_("unable to normalize alternate object path: %s"),
 		      pathbuf.buf);
-		strbuf_release(&pathbuf);
-		return -1;
+		goto error;
 	}
+	strbuf_swap(&pathbuf, &tmp);
 
 	/*
 	 * The trailing slash after the directory name is given by
@@ -525,10 +532,8 @@ static int link_alt_odb_entry(struct repository *r, const struct strbuf *entry,
 	while (pathbuf.len && pathbuf.buf[pathbuf.len - 1] == '/')
 		strbuf_setlen(&pathbuf, pathbuf.len - 1);
 
-	if (!alt_odb_usable(r->objects, &pathbuf, normalized_objdir, &pos)) {
-		strbuf_release(&pathbuf);
-		return -1;
-	}
+	if (!alt_odb_usable(r->objects, &pathbuf, normalized_objdir, &pos))
+		goto error;
 
 	CALLOC_ARRAY(ent, 1);
 	/* pathbuf.buf is already in r->objects->odb_by_path */
@@ -543,8 +548,11 @@ static int link_alt_odb_entry(struct repository *r, const struct strbuf *entry,
 
 	/* recursively add alternates */
 	read_info_alternates(r, ent->path, depth + 1);
-
-	return 0;
+	ret = 0;
+ error:
+	strbuf_release(&tmp);
+	strbuf_release(&pathbuf);
+	return ret;
 }
 
 static const char *parse_alt_odb_entry(const char *string,
@@ -591,10 +599,7 @@ static void link_alt_odb_entries(struct repository *r, const char *alt,
 		return;
 	}
 
-	strbuf_add_absolute_path(&objdirbuf, r->objects->odb->path);
-	if (strbuf_normalize_path(&objdirbuf) < 0)
-		die(_("unable to normalize object directory: %s"),
-		    objdirbuf.buf);
+	strbuf_realpath(&objdirbuf, r->objects->odb->path, 1);
 
 	while (*alt) {
 		alt = parse_alt_odb_entry(alt, sep, &entry);
@@ -838,7 +843,7 @@ static void fill_alternate_refs_command(struct child_process *cmd,
 		}
 	}
 
-	strvec_pushv(&cmd->env_array, (const char **)local_repo_env);
+	strvec_pushv(&cmd->env, (const char **)local_repo_env);
 	cmd->out = -1;
 }
 
@@ -997,7 +1002,7 @@ int has_loose_object_nonlocal(const struct object_id *oid)
 	return check_and_freshen_nonlocal(oid, 0);
 }
 
-static int has_loose_object(const struct object_id *oid)
+int has_loose_object(const struct object_id *oid)
 {
 	return check_and_freshen(oid, 0);
 }
@@ -1599,10 +1604,6 @@ static int do_oid_object_info_extended(struct repository *r,
 		if (fetch_if_missing && repo_has_promisor_remote(r) &&
 		    !already_retried &&
 		    !(flags & OBJECT_INFO_SKIP_FETCH_OBJECT)) {
-			/*
-			 * TODO Investigate checking promisor_remote_get_direct()
-			 * TODO return value and stopping on error here.
-			 */
 			promisor_remote_get_direct(r, real, 1);
 			already_retried = 1;
 			continue;
@@ -1728,7 +1729,7 @@ void *read_object_file_extended(struct repository *r,
 		die(_("loose object %s (stored in %s) is corrupt"),
 		    oid_to_hex(repl), path);
 
-	if ((p = has_packed_and_bad(r, repl)) != NULL)
+	if ((p = has_packed_and_bad(r, repl)))
 		die(_("packed object %s (stored in %s) is corrupt"),
 		    oid_to_hex(repl), p->pack_name);
 	obj_read_unlock();
@@ -1863,13 +1864,6 @@ out:
 	return 0;
 }
 
-static int write_buffer(int fd, const void *buf, size_t len)
-{
-	if (write_in_full(fd, buf, len) < 0)
-		return error_errno(_("file write error"));
-	return 0;
-}
-
 static void hash_object_file_literally(const struct git_hash_algo *algo,
 				       const void *buf, unsigned long len,
 				       const char *type, struct object_id *oid)
@@ -1893,7 +1887,9 @@ static void close_loose_object(int fd, const char *filename)
 	if (the_repository->objects->odb->will_destroy)
 		goto out;
 
-	if (fsync_object_files > 0)
+	if (batch_fsync_enabled(FSYNC_COMPONENT_LOOSE_OBJECT))
+		fsync_loose_object_bulk_checkin(fd, filename);
+	else if (fsync_object_files > 0)
 		fsync_or_die(fd, filename);
 	else
 		fsync_component_or_die(FSYNC_COMPONENT_LOOSE_OBJECT, fd,
@@ -1949,6 +1945,96 @@ static int create_tmpfile(struct strbuf *tmp, const char *filename)
 	return fd;
 }
 
+/**
+ * Common steps for loose object writers to start writing loose
+ * objects:
+ *
+ * - Create tmpfile for the loose object.
+ * - Setup zlib stream for compression.
+ * - Start to feed header to zlib stream.
+ *
+ * Returns a "fd", which should later be provided to
+ * end_loose_object_common().
+ */
+static int start_loose_object_common(struct strbuf *tmp_file,
+				     const char *filename, unsigned flags,
+				     git_zstream *stream,
+				     unsigned char *buf, size_t buflen,
+				     git_hash_ctx *c,
+				     char *hdr, int hdrlen)
+{
+	int fd;
+
+	fd = create_tmpfile(tmp_file, filename);
+	if (fd < 0) {
+		if (flags & HASH_SILENT)
+			return -1;
+		else if (errno == EACCES)
+			return error(_("insufficient permission for adding "
+				       "an object to repository database %s"),
+				     get_object_directory());
+		else
+			return error_errno(
+				_("unable to create temporary file"));
+	}
+
+	/*  Setup zlib stream for compression */
+	git_deflate_init(stream, zlib_compression_level);
+	stream->next_out = buf;
+	stream->avail_out = buflen;
+	the_hash_algo->init_fn(c);
+
+	/*  Start to feed header to zlib stream */
+	stream->next_in = (unsigned char *)hdr;
+	stream->avail_in = hdrlen;
+	while (git_deflate(stream, 0) == Z_OK)
+		; /* nothing */
+	the_hash_algo->update_fn(c, hdr, hdrlen);
+
+	return fd;
+}
+
+/**
+ * Common steps for the inner git_deflate() loop for writing loose
+ * objects. Returns what git_deflate() returns.
+ */
+static int write_loose_object_common(git_hash_ctx *c,
+				     git_zstream *stream, const int flush,
+				     unsigned char *in0, const int fd,
+				     unsigned char *compressed,
+				     const size_t compressed_len)
+{
+	int ret;
+
+	ret = git_deflate(stream, flush ? Z_FINISH : 0);
+	the_hash_algo->update_fn(c, in0, stream->next_in - in0);
+	if (write_in_full(fd, compressed, stream->next_out - compressed) < 0)
+		die_errno(_("unable to write loose object file"));
+	stream->next_out = compressed;
+	stream->avail_out = compressed_len;
+
+	return ret;
+}
+
+/**
+ * Common steps for loose object writers to end writing loose objects:
+ *
+ * - End the compression of zlib stream.
+ * - Get the calculated oid to "oid".
+ */
+static int end_loose_object_common(git_hash_ctx *c, git_zstream *stream,
+				   struct object_id *oid)
+{
+	int ret;
+
+	ret = git_deflate_end_gently(stream);
+	if (ret != Z_OK)
+		return ret;
+	the_hash_algo->final_oid_fn(oid, c);
+
+	return Z_OK;
+}
+
 static int write_loose_object(const struct object_id *oid, char *hdr,
 			      int hdrlen, const void *buf, unsigned long len,
 			      time_t mtime, unsigned flags)
@@ -1961,52 +2047,34 @@ static int write_loose_object(const struct object_id *oid, char *hdr,
 	static struct strbuf tmp_file = STRBUF_INIT;
 	static struct strbuf filename = STRBUF_INIT;
 
-	loose_object_path(the_repository, &filename, oid);
-
-	fd = create_tmpfile(&tmp_file, filename.buf);
-	if (fd < 0) {
-		if (flags & HASH_SILENT)
-			return -1;
-		else if (errno == EACCES)
-			return error(_("insufficient permission for adding an object to repository database %s"), get_object_directory());
-		else
-			return error_errno(_("unable to create temporary file"));
-	}
+	if (batch_fsync_enabled(FSYNC_COMPONENT_LOOSE_OBJECT))
+		prepare_loose_object_bulk_checkin();
 
-	/* Set it up */
-	git_deflate_init(&stream, zlib_compression_level);
-	stream.next_out = compressed;
-	stream.avail_out = sizeof(compressed);
-	the_hash_algo->init_fn(&c);
+	loose_object_path(the_repository, &filename, oid);
 
-	/* First header.. */
-	stream.next_in = (unsigned char *)hdr;
-	stream.avail_in = hdrlen;
-	while (git_deflate(&stream, 0) == Z_OK)
-		; /* nothing */
-	the_hash_algo->update_fn(&c, hdr, hdrlen);
+	fd = start_loose_object_common(&tmp_file, filename.buf, flags,
+				       &stream, compressed, sizeof(compressed),
+				       &c, hdr, hdrlen);
+	if (fd < 0)
+		return -1;
 
 	/* Then the data itself.. */
 	stream.next_in = (void *)buf;
 	stream.avail_in = len;
 	do {
 		unsigned char *in0 = stream.next_in;
-		ret = git_deflate(&stream, Z_FINISH);
-		the_hash_algo->update_fn(&c, in0, stream.next_in - in0);
-		if (write_buffer(fd, compressed, stream.next_out - compressed) < 0)
-			die(_("unable to write loose object file"));
-		stream.next_out = compressed;
-		stream.avail_out = sizeof(compressed);
+
+		ret = write_loose_object_common(&c, &stream, 1, in0, fd,
+						compressed, sizeof(compressed));
 	} while (ret == Z_OK);
 
 	if (ret != Z_STREAM_END)
 		die(_("unable to deflate new object %s (%d)"), oid_to_hex(oid),
 		    ret);
-	ret = git_deflate_end_gently(&stream);
+	ret = end_loose_object_common(&c, &stream, &parano_oid);
 	if (ret != Z_OK)
 		die(_("deflateEnd on object %s failed (%d)"), oid_to_hex(oid),
 		    ret);
-	the_hash_algo->final_oid_fn(&parano_oid, &c);
 	if (!oideq(oid, &parano_oid))
 		die(_("confused by unstable object source data for %s"),
 		    oid_to_hex(oid));
@@ -2035,6 +2103,8 @@ static int freshen_packed_object(const struct object_id *oid)
 	struct pack_entry e;
 	if (!find_pack_entry(the_repository, oid, &e))
 		return 0;
+	if (e.p->is_cruft)
+		return 0;
 	if (e.p->freshened)
 		return 1;
 	if (!freshen_file(e.p->pack_name))
@@ -2043,6 +2113,110 @@ static int freshen_packed_object(const struct object_id *oid)
 	return 1;
 }
 
+int stream_loose_object(struct input_stream *in_stream, size_t len,
+			struct object_id *oid)
+{
+	int fd, ret, err = 0, flush = 0;
+	unsigned char compressed[4096];
+	git_zstream stream;
+	git_hash_ctx c;
+	struct strbuf tmp_file = STRBUF_INIT;
+	struct strbuf filename = STRBUF_INIT;
+	int dirlen;
+	char hdr[MAX_HEADER_LEN];
+	int hdrlen;
+
+	if (batch_fsync_enabled(FSYNC_COMPONENT_LOOSE_OBJECT))
+		prepare_loose_object_bulk_checkin();
+
+	/* Since oid is not determined, save tmp file to odb path. */
+	strbuf_addf(&filename, "%s/", get_object_directory());
+	hdrlen = format_object_header(hdr, sizeof(hdr), OBJ_BLOB, len);
+
+	/*
+	 * Common steps for write_loose_object and stream_loose_object to
+	 * start writing loose objects:
+	 *
+	 *  - Create tmpfile for the loose object.
+	 *  - Setup zlib stream for compression.
+	 *  - Start to feed header to zlib stream.
+	 */
+	fd = start_loose_object_common(&tmp_file, filename.buf, 0,
+				       &stream, compressed, sizeof(compressed),
+				       &c, hdr, hdrlen);
+	if (fd < 0) {
+		err = -1;
+		goto cleanup;
+	}
+
+	/* Then the data itself.. */
+	do {
+		unsigned char *in0 = stream.next_in;
+
+		if (!stream.avail_in && !in_stream->is_finished) {
+			const void *in = in_stream->read(in_stream, &stream.avail_in);
+			stream.next_in = (void *)in;
+			in0 = (unsigned char *)in;
+			/* All data has been read. */
+			if (in_stream->is_finished)
+				flush = 1;
+		}
+		ret = write_loose_object_common(&c, &stream, flush, in0, fd,
+						compressed, sizeof(compressed));
+		/*
+		 * Unlike write_loose_object(), we do not have the entire
+		 * buffer. If we get Z_BUF_ERROR due to too few input bytes,
+		 * then we'll replenish them in the next input_stream->read()
+		 * call when we loop.
+		 */
+	} while (ret == Z_OK || ret == Z_BUF_ERROR);
+
+	if (stream.total_in != len + hdrlen)
+		die(_("write stream object %ld != %"PRIuMAX), stream.total_in,
+		    (uintmax_t)len + hdrlen);
+
+	/*
+	 * Common steps for write_loose_object and stream_loose_object to
+	 * end writing loose oject:
+	 *
+	 *  - End the compression of zlib stream.
+	 *  - Get the calculated oid.
+	 */
+	if (ret != Z_STREAM_END)
+		die(_("unable to stream deflate new object (%d)"), ret);
+	ret = end_loose_object_common(&c, &stream, oid);
+	if (ret != Z_OK)
+		die(_("deflateEnd on stream object failed (%d)"), ret);
+	close_loose_object(fd, tmp_file.buf);
+
+	if (freshen_packed_object(oid) || freshen_loose_object(oid)) {
+		unlink_or_warn(tmp_file.buf);
+		goto cleanup;
+	}
+
+	loose_object_path(the_repository, &filename, oid);
+
+	/* We finally know the object path, and create the missing dir. */
+	dirlen = directory_size(filename.buf);
+	if (dirlen) {
+		struct strbuf dir = STRBUF_INIT;
+		strbuf_add(&dir, filename.buf, dirlen);
+
+		if (mkdir_in_gitdir(dir.buf) && errno != EEXIST) {
+			err = error_errno(_("unable to create directory %s"), dir.buf);
+			strbuf_release(&dir);
+			goto cleanup;
+		}
+		strbuf_release(&dir);
+	}
+
+	err = finalize_object_file(tmp_file.buf, filename.buf);
+cleanup:
+	strbuf_release(&tmp_file);
+	strbuf_release(&filename);
+	return err;
+}
+
 int write_object_file_flags(const void *buf, unsigned long len,
 			    enum object_type type, struct object_id *oid,
 			    unsigned flags)
@@ -2623,12 +2797,8 @@ int read_loose_object(const char *path,
 		goto out;
 	}
 
-	switch (unpack_loose_header(&stream, map, mapsize, hdr, sizeof(hdr),
-				    NULL)) {
-	case ULHR_OK:
-		break;
-	case ULHR_BAD:
-	case ULHR_TOO_LONG:
+	if (unpack_loose_header(&stream, map, mapsize, hdr, sizeof(hdr),
+				NULL) != ULHR_OK) {
 		error(_("unable to unpack header of %s"), path);
 		goto out;
 	}