1 files changed, 88 insertions, 115 deletions

diff --git a/object-file.c b/object-file.c
index c1b71c2834..939865c1ae 100644
--- a/object-file.c
+++ b/object-file.c
@@ -33,6 +33,7 @@
 #include "object-store.h"
 #include "promisor-remote.h"
 #include "submodule.h"
+#include "fsck.h"
 
 /* The maximum size for an object header. */
 #define MAX_HEADER_LEN 32
@@ -1211,35 +1212,25 @@ static int quick_has_loose(struct repository *r,
 }
 
 /*
- * Map the loose object at "path" if it is not NULL, or the path found by
- * searching for a loose object named "oid".
+ * Map and close the given loose object fd. The path argument is used for
+ * error reporting.
  */
-static void *map_loose_object_1(struct repository *r, const char *path,
-			     const struct object_id *oid, unsigned long *size)
+static void *map_fd(int fd, const char *path, unsigned long *size)
 {
-	void *map;
-	int fd;
-
-	if (path)
-		fd = git_open(path);
-	else
-		fd = open_loose_object(r, oid, &path);
-	map = NULL;
-	if (fd >= 0) {
-		struct stat st;
+	void *map = NULL;
+	struct stat st;
 
-		if (!fstat(fd, &st)) {
-			*size = xsize_t(st.st_size);
-			if (!*size) {
-				/* mmap() is forbidden on empty files */
-				error(_("object file %s is empty"), path);
-				close(fd);
-				return NULL;
-			}
-			map = xmmap(NULL, *size, PROT_READ, MAP_PRIVATE, fd, 0);
+	if (!fstat(fd, &st)) {
+		*size = xsize_t(st.st_size);
+		if (!*size) {
+			/* mmap() is forbidden on empty files */
+			error(_("object file %s is empty"), path);
+			close(fd);
+			return NULL;
 		}
-		close(fd);
+		map = xmmap(NULL, *size, PROT_READ, MAP_PRIVATE, fd, 0);
 	}
+	close(fd);
 	return map;
 }
 
@@ -1247,7 +1238,12 @@ void *map_loose_object(struct repository *r,
 		       const struct object_id *oid,
 		       unsigned long *size)
 {
-	return map_loose_object_1(r, NULL, oid, size);
+	const char *p;
+	int fd = open_loose_object(r, oid, &p);
+
+	if (fd < 0)
+		return NULL;
+	return map_fd(fd, p, size);
 }
 
 enum unpack_loose_header_result unpack_loose_header(git_zstream *stream,
@@ -1427,7 +1423,9 @@ static int loose_object_info(struct repository *r,
 			     struct object_info *oi, int flags)
 {
 	int status = 0;
+	int fd;
 	unsigned long mapsize;
+	const char *path;
 	void *map;
 	git_zstream stream;
 	char hdr[MAX_HEADER_LEN];
@@ -1448,7 +1446,6 @@ static int loose_object_info(struct repository *r,
 	 * object even exists.
 	 */
 	if (!oi->typep && !oi->type_name && !oi->sizep && !oi->contentp) {
-		const char *path;
 		struct stat st;
 		if (!oi->disk_sizep && (flags & OBJECT_INFO_QUICK))
 			return quick_has_loose(r, oid) ? 0 : -1;
@@ -1459,7 +1456,13 @@ static int loose_object_info(struct repository *r,
 		return 0;
 	}
 
-	map = map_loose_object(r, oid, &mapsize);
+	fd = open_loose_object(r, oid, &path);
+	if (fd < 0) {
+		if (errno != ENOENT)
+			error_errno(_("unable to open loose object %s"), oid_to_hex(oid));
+		return -1;
+	}
+	map = map_fd(fd, path, &mapsize);
 	if (!map)
 		return -1;
 
@@ -1497,6 +1500,10 @@ static int loose_object_info(struct repository *r,
 		break;
 	}
 
+	if (status && (flags & OBJECT_INFO_DIE_IF_CORRUPT))
+		die(_("loose object %s (stored in %s) is corrupt"),
+		    oid_to_hex(oid), path);
+
 	git_inflate_end(&stream);
 cleanup:
 	munmap(map, mapsize);
@@ -1575,9 +1582,6 @@ static int do_oid_object_info_extended(struct repository *r,
 		if (find_pack_entry(r, real, &e))
 			break;
 
-		if (flags & OBJECT_INFO_IGNORE_LOOSE)
-			return -1;
-
 		/* Most likely it's a loose object. */
 		if (!loose_object_info(r, real, oi, flags))
 			return 0;
@@ -1609,6 +1613,15 @@ static int do_oid_object_info_extended(struct repository *r,
 			continue;
 		}
 
+		if (flags & OBJECT_INFO_DIE_IF_CORRUPT) {
+			const struct packed_git *p;
+			if ((flags & OBJECT_INFO_LOOKUP_REPLACE) && !oideq(real, oid))
+				die(_("replacement %s not found for %s"),
+				    oid_to_hex(real), oid_to_hex(oid));
+			if ((p = has_packed_and_bad(r, real)))
+				die(_("packed object %s (stored in %s) is corrupt"),
+				    oid_to_hex(real), p->pack_name);
+		}
 		return -1;
 	}
 
@@ -1659,21 +1672,6 @@ int oid_object_info(struct repository *r,
 	return type;
 }
 
-static void *read_object(struct repository *r,
-			 const struct object_id *oid, enum object_type *type,
-			 unsigned long *size)
-{
-	struct object_info oi = OBJECT_INFO_INIT;
-	void *content;
-	oi.typep = type;
-	oi.sizep = size;
-	oi.contentp = &content;
-
-	if (oid_object_info_extended(r, oid, &oi, 0) < 0)
-		return NULL;
-	return content;
-}
-
 int pretend_object_file(void *buf, unsigned long len, enum object_type type,
 			struct object_id *oid)
 {
@@ -1695,46 +1693,25 @@ int pretend_object_file(void *buf, unsigned long len, enum object_type type,
 
 /*
  * 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.
+ * deal with them should arrange to call oid_object_info_extended() and give
+ * error messages themselves.
  */
-void *read_object_file_extended(struct repository *r,
-				const struct object_id *oid,
-				enum object_type *type,
-				unsigned long *size,
-				int lookup_replace)
+void *repo_read_object_file(struct repository *r,
+			    const struct object_id *oid,
+			    enum object_type *type,
+			    unsigned long *size)
 {
+	struct object_info oi = OBJECT_INFO_INIT;
+	unsigned flags = OBJECT_INFO_DIE_IF_CORRUPT | OBJECT_INFO_LOOKUP_REPLACE;
 	void *data;
-	const struct packed_git *p;
-	const char *path;
-	struct stat st;
-	const struct object_id *repl = lookup_replace ?
-		lookup_replace_object(r, oid) : oid;
-
-	errno = 0;
-	data = read_object(r, repl, type, size);
-	if (data)
-		return data;
-
-	obj_read_lock();
-	if (errno && errno != ENOENT)
-		die_errno(_("failed to read object %s"), oid_to_hex(oid));
-
-	/* die if we replaced an object with one that does not exist */
-	if (repl != oid)
-		die(_("replacement %s not found for %s"),
-		    oid_to_hex(repl), oid_to_hex(oid));
 
-	if (!stat_loose_object(r, repl, &st, &path))
-		die(_("loose object %s (stored in %s) is corrupt"),
-		    oid_to_hex(repl), path);
-
-	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();
+	oi.typep = type;
+	oi.sizep = size;
+	oi.contentp = &data;
+	if (oid_object_info_extended(r, oid, &oi, flags))
+		return NULL;
 
-	return NULL;
+	return data;
 }
 
 void *read_object_with_reference(struct repository *r,
@@ -2262,6 +2239,7 @@ int force_object_loose(const struct object_id *oid, time_t mtime)
 {
 	void *buf;
 	unsigned long len;
+	struct object_info oi = OBJECT_INFO_INIT;
 	enum object_type type;
 	char hdr[MAX_HEADER_LEN];
 	int hdrlen;
@@ -2269,8 +2247,10 @@ int force_object_loose(const struct object_id *oid, time_t mtime)
 
 	if (has_loose_object(oid))
 		return 0;
-	buf = read_object(the_repository, oid, &type, &len);
-	if (!buf)
+	oi.typep = &type;
+	oi.sizep = &len;
+	oi.contentp = &buf;
+	if (oid_object_info_extended(the_repository, oid, &oi, 0))
 		return error(_("cannot read object for %s"), oid_to_hex(oid));
 	hdrlen = format_object_header(hdr, sizeof(hdr), type, len);
 	ret = write_loose_object(oid, hdr, hdrlen, buf, len, mtime, 0);
@@ -2305,32 +2285,21 @@ int repo_has_object_file(struct repository *r,
 	return repo_has_object_file_with_flags(r, oid, 0);
 }
 
-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(the_repository, &c, buf, size, 0))
-		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(the_repository, &t, buf, size))
-		die(_("corrupt tag"));
+/*
+ * We can't use the normal fsck_error_function() for index_mem(),
+ * because we don't yet have a valid oid for it to report. Instead,
+ * report the minimal fsck error here, and rely on the caller to
+ * give more context.
+ */
+static int hash_format_check_report(struct fsck_options *opts,
+				     const struct object_id *oid,
+				     enum object_type object_type,
+				     enum fsck_msg_type msg_type,
+				     enum fsck_msg_id msg_id,
+				     const char *message)
+{
+	error(_("object fails fsck: %s"), message);
+	return 1;
 }
 
 static int index_mem(struct index_state *istate,
@@ -2357,12 +2326,13 @@ static int index_mem(struct index_state *istate,
 		}
 	}
 	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);
+		struct fsck_options opts = FSCK_OPTIONS_DEFAULT;
+
+		opts.strict = 1;
+		opts.error_func = hash_format_check_report;
+		if (fsck_buffer(null_oid(), type, buf, size, &opts))
+			die(_("refusing to create malformed object"));
+		fsck_finish(&opts);
 	}
 
 	if (write_object)
@@ -2785,13 +2755,16 @@ int read_loose_object(const char *path,
 		      struct object_info *oi)
 {
 	int ret = -1;
+	int fd;
 	void *map = NULL;
 	unsigned long mapsize;
 	git_zstream stream;
 	char hdr[MAX_HEADER_LEN];
 	unsigned long *size = oi->sizep;
 
-	map = map_loose_object_1(the_repository, path, NULL, &mapsize);
+	fd = git_open(path);
+	if (fd >= 0)
+		map = map_fd(fd, path, &mapsize);
 	if (!map) {
 		error_errno(_("unable to mmap %s"), path);
 		goto out;