#include "dir.h"
#include "progress.h"
#include "streaming.h"
+#include "decorate.h"
#define REACHABLE 0x0001
#define SEEN 0x0002
static int show_unreachable;
static int include_reflogs = 1;
static int check_full = 1;
+static int connectivity_only;
static int check_strict;
static int keep_cache_objects;
+static struct fsck_options fsck_walk_options = FSCK_OPTIONS_DEFAULT;
+static struct fsck_options fsck_obj_options = FSCK_OPTIONS_DEFAULT;
static struct object_id head_oid;
static const char *head_points_at;
static int errors_found;
static int verbose;
static int show_progress = -1;
static int show_dangling = 1;
+static int name_objects;
#define ERROR_OBJECT 01
#define ERROR_REACHABLE 02
#define ERROR_PACK 04
+#define ERROR_REFS 010
-#ifdef NO_D_INO_IN_DIRENT
-#define SORT_DIRENT 0
-#define DIRENT_SORT_HINT(de) 0
-#else
-#define SORT_DIRENT 1
-#define DIRENT_SORT_HINT(de) ((de)->d_ino)
-#endif
+static const char *describe_object(struct object *obj)
+{
+ static struct strbuf buf = STRBUF_INIT;
+ char *name = name_objects ?
+ lookup_decoration(fsck_walk_options.object_names, obj) : NULL;
+
+ strbuf_reset(&buf);
+ strbuf_addstr(&buf, oid_to_hex(&obj->oid));
+ if (name)
+ strbuf_addf(&buf, " (%s)", name);
+
+ return buf.buf;
+}
+
+static const char *printable_type(struct object *obj)
+{
+ const char *ret;
+
+ if (obj->type == OBJ_NONE) {
+ enum object_type type = sha1_object_info(obj->oid.hash, NULL);
+ if (type > 0)
+ object_as_type(obj, type, 0);
+ }
+
+ ret = typename(obj->type);
+ if (!ret)
+ ret = "unknown";
+
+ return ret;
+}
+
+static int fsck_config(const char *var, const char *value, void *cb)
+{
+ if (strcmp(var, "fsck.skiplist") == 0) {
+ const char *path;
+ struct strbuf sb = STRBUF_INIT;
+
+ if (git_config_pathname(&path, var, value))
+ return 1;
+ strbuf_addf(&sb, "skiplist=%s", path);
+ free((char *)path);
+ fsck_set_msg_types(&fsck_obj_options, sb.buf);
+ strbuf_release(&sb);
+ return 0;
+ }
+
+ if (skip_prefix(var, "fsck.", &var)) {
+ fsck_set_msg_type(&fsck_obj_options, var, value);
+ return 0;
+ }
-static void objreport(struct object *obj, const char *severity,
- const char *err, va_list params)
+ return git_default_config(var, value, cb);
+}
+
+static void objreport(struct object *obj, const char *msg_type,
+ const char *err)
{
- fprintf(stderr, "%s in %s %s: ",
- severity, typename(obj->type), sha1_to_hex(obj->sha1));
- vfprintf(stderr, err, params);
- fputs("\n", stderr);
+ fprintf(stderr, "%s in %s %s: %s\n",
+ msg_type, printable_type(obj), describe_object(obj), err);
}
-__attribute__((format (printf, 2, 3)))
-static int objerror(struct object *obj, const char *err, ...)
+static int objerror(struct object *obj, const char *err)
{
- va_list params;
- va_start(params, err);
errors_found |= ERROR_OBJECT;
- objreport(obj, "error", err, params);
- va_end(params);
+ objreport(obj, "error", err);
return -1;
}
-__attribute__((format (printf, 3, 4)))
-static int fsck_error_func(struct object *obj, int type, const char *err, ...)
+static int fsck_error_func(struct fsck_options *o,
+ struct object *obj, int type, const char *message)
{
- va_list params;
- va_start(params, err);
- objreport(obj, (type == FSCK_WARN) ? "warning" : "error", err, params);
- va_end(params);
+ objreport(obj, (type == FSCK_WARN) ? "warning" : "error", message);
return (type == FSCK_WARN) ? 0 : 1;
}
static struct object_array pending;
-static int mark_object(struct object *obj, int type, void *data)
+static int mark_object(struct object *obj, int type, void *data, struct fsck_options *options)
{
struct object *parent = data;
if (!obj) {
/* ... these references to parent->fld are safe here */
printf("broken link from %7s %s\n",
- typename(parent->type), sha1_to_hex(parent->sha1));
+ printable_type(parent), describe_object(parent));
printf("broken link from %7s %s\n",
(type == OBJ_ANY ? "unknown" : typename(type)), "unknown");
errors_found |= ERROR_REACHABLE;
return 0;
obj->flags |= REACHABLE;
if (!(obj->flags & HAS_OBJ)) {
- if (parent && !has_sha1_file(obj->sha1)) {
+ if (parent && !has_object_file(&obj->oid)) {
printf("broken link from %7s %s\n",
- typename(parent->type), sha1_to_hex(parent->sha1));
+ printable_type(parent), describe_object(parent));
printf(" to %7s %s\n",
- typename(obj->type), sha1_to_hex(obj->sha1));
+ printable_type(obj), describe_object(obj));
errors_found |= ERROR_REACHABLE;
}
return 1;
static void mark_object_reachable(struct object *obj)
{
- mark_object(obj, OBJ_ANY, NULL);
+ mark_object(obj, OBJ_ANY, NULL, NULL);
}
static int traverse_one_object(struct object *obj)
if (parse_tree(tree) < 0)
return 1; /* error already displayed */
}
- result = fsck_walk(obj, mark_object, obj);
+ result = fsck_walk(obj, obj, &fsck_walk_options);
if (tree)
free_tree_buffer(tree);
return result;
return !!result;
}
-static int mark_used(struct object *obj, int type, void *data)
+static int mark_used(struct object *obj, int type, void *data, struct fsck_options *options)
{
if (!obj)
return 1;
* do a full fsck
*/
if (!(obj->flags & HAS_OBJ)) {
- if (has_sha1_pack(obj->sha1))
+ if (has_sha1_pack(obj->oid.hash))
return; /* it is in pack - forget about it */
- printf("missing %s %s\n", typename(obj->type), sha1_to_hex(obj->sha1));
+ printf("missing %s %s\n", printable_type(obj),
+ describe_object(obj));
errors_found |= ERROR_REACHABLE;
return;
}
* to complain about it being unreachable (since it does
* not exist).
*/
- if (!obj->parsed)
+ if (!(obj->flags & HAS_OBJ))
return;
/*
* since this is something that is prunable.
*/
if (show_unreachable) {
- printf("unreachable %s %s\n", typename(obj->type), sha1_to_hex(obj->sha1));
+ printf("unreachable %s %s\n", printable_type(obj),
+ describe_object(obj));
return;
}
*/
if (!obj->used) {
if (show_dangling)
- printf("dangling %s %s\n", typename(obj->type),
- sha1_to_hex(obj->sha1));
+ printf("dangling %s %s\n", printable_type(obj),
+ describe_object(obj));
if (write_lost_and_found) {
- const char *filename = git_path("lost-found/%s/%s",
+ char *filename = git_pathdup("lost-found/%s/%s",
obj->type == OBJ_COMMIT ? "commit" : "other",
- sha1_to_hex(obj->sha1));
+ describe_object(obj));
FILE *f;
if (safe_create_leading_directories_const(filename)) {
error("Could not create lost-found");
+ free(filename);
return;
}
if (!(f = fopen(filename, "w")))
die_errno("Could not open '%s'", filename);
if (obj->type == OBJ_BLOB) {
- if (stream_blob_to_fd(fileno(f), obj->sha1, NULL, 1))
+ if (stream_blob_to_fd(fileno(f), &obj->oid, NULL, 1))
die_errno("Could not write '%s'", filename);
} else
- fprintf(f, "%s\n", sha1_to_hex(obj->sha1));
+ fprintf(f, "%s\n", describe_object(obj));
if (fclose(f))
die_errno("Could not finish '%s'",
filename);
+ free(filename);
}
return;
}
static void check_object(struct object *obj)
{
if (verbose)
- fprintf(stderr, "Checking %s\n", sha1_to_hex(obj->sha1));
+ fprintf(stderr, "Checking %s\n", describe_object(obj));
if (obj->flags & REACHABLE)
check_reachable_object(obj);
if (verbose)
fprintf(stderr, "Checking %s %s\n",
- typename(obj->type), sha1_to_hex(obj->sha1));
+ printable_type(obj), describe_object(obj));
- if (fsck_walk(obj, mark_used, NULL))
+ if (fsck_walk(obj, NULL, &fsck_obj_options))
objerror(obj, "broken links");
- if (fsck_object(obj, NULL, 0, check_strict, fsck_error_func))
+ if (fsck_object(obj, NULL, 0, &fsck_obj_options))
return -1;
if (obj->type == OBJ_TREE) {
free_commit_buffer(commit);
if (!commit->parents && show_root)
- printf("root %s\n", sha1_to_hex(commit->object.sha1));
+ printf("root %s\n", describe_object(&commit->object));
}
if (obj->type == OBJ_TAG) {
struct tag *tag = (struct tag *) obj;
if (show_tags && tag->tagged) {
- printf("tagged %s %s", typename(tag->tagged->type), sha1_to_hex(tag->tagged->sha1));
- printf(" (%s) in %s\n", tag->tag, sha1_to_hex(tag->object.sha1));
+ printf("tagged %s %s", printable_type(tag->tagged),
+ describe_object(tag->tagged));
+ printf(" (%s) in %s\n", tag->tag,
+ describe_object(&tag->object));
}
}
return 0;
}
-static int fsck_sha1(const unsigned char *sha1)
-{
- struct object *obj = parse_object(sha1);
- if (!obj) {
- errors_found |= ERROR_OBJECT;
- return error("%s: object corrupt or missing",
- sha1_to_hex(sha1));
- }
- obj->flags |= HAS_OBJ;
- return fsck_obj(obj);
-}
-
static int fsck_obj_buffer(const unsigned char *sha1, enum object_type type,
unsigned long size, void *buffer, int *eaten)
{
+ /*
+ * Note, buffer may be NULL if type is OBJ_BLOB. See
+ * verify_packfile(), data_valid variable for details.
+ */
struct object *obj;
obj = parse_object_buffer(sha1, type, size, buffer, eaten);
if (!obj) {
return fsck_obj(obj);
}
-/*
- * This is the sorting chunk size: make it reasonably
- * big so that we can sort well..
- */
-#define MAX_SHA1_ENTRIES (1024)
-
-struct sha1_entry {
- unsigned long ino;
- unsigned char sha1[20];
-};
-
-static struct {
- unsigned long nr;
- struct sha1_entry *entry[MAX_SHA1_ENTRIES];
-} sha1_list;
-
-static int ino_compare(const void *_a, const void *_b)
-{
- const struct sha1_entry *a = _a, *b = _b;
- unsigned long ino1 = a->ino, ino2 = b->ino;
- return ino1 < ino2 ? -1 : ino1 > ino2 ? 1 : 0;
-}
-
-static void fsck_sha1_list(void)
-{
- int i, nr = sha1_list.nr;
-
- if (SORT_DIRENT)
- qsort(sha1_list.entry, nr,
- sizeof(struct sha1_entry *), ino_compare);
- for (i = 0; i < nr; i++) {
- struct sha1_entry *entry = sha1_list.entry[i];
- unsigned char *sha1 = entry->sha1;
-
- sha1_list.entry[i] = NULL;
- if (fsck_sha1(sha1))
- errors_found |= ERROR_OBJECT;
- free(entry);
- }
- sha1_list.nr = 0;
-}
-
-static void add_sha1_list(unsigned char *sha1, unsigned long ino)
-{
- struct sha1_entry *entry = xmalloc(sizeof(*entry));
- int nr;
-
- entry->ino = ino;
- hashcpy(entry->sha1, sha1);
- nr = sha1_list.nr;
- if (nr == MAX_SHA1_ENTRIES) {
- fsck_sha1_list();
- nr = 0;
- }
- sha1_list.entry[nr] = entry;
- sha1_list.nr = ++nr;
-}
-
-static inline int is_loose_object_file(struct dirent *de,
- char *name, unsigned char *sha1)
-{
- if (strlen(de->d_name) != 38)
- return 0;
- memcpy(name + 2, de->d_name, 39);
- return !get_sha1_hex(name, sha1);
-}
-
-static void fsck_dir(int i, char *path)
-{
- DIR *dir = opendir(path);
- struct dirent *de;
- char name[100];
-
- if (!dir)
- return;
-
- if (verbose)
- fprintf(stderr, "Checking directory %s\n", path);
-
- sprintf(name, "%02x", i);
- while ((de = readdir(dir)) != NULL) {
- unsigned char sha1[20];
-
- if (is_dot_or_dotdot(de->d_name))
- continue;
- if (is_loose_object_file(de, name, sha1)) {
- add_sha1_list(sha1, DIRENT_SORT_HINT(de));
- continue;
- }
- if (starts_with(de->d_name, "tmp_obj_"))
- continue;
- fprintf(stderr, "bad sha1 file: %s/%s\n", path, de->d_name);
- }
- closedir(dir);
-}
-
static int default_refs;
-static void fsck_handle_reflog_sha1(const char *refname, unsigned char *sha1)
+static void fsck_handle_reflog_oid(const char *refname, struct object_id *oid,
+ timestamp_t timestamp)
{
struct object *obj;
- if (!is_null_sha1(sha1)) {
- obj = lookup_object(sha1);
- if (obj) {
+ if (!is_null_oid(oid)) {
+ obj = lookup_object(oid->hash);
+ if (obj && (obj->flags & HAS_OBJ)) {
+ if (timestamp && name_objects)
+ add_decoration(fsck_walk_options.object_names,
+ obj,
+ xstrfmt("%s@{%"PRItime"}", refname, timestamp));
obj->used = 1;
mark_object_reachable(obj);
} else {
- error("%s: invalid reflog entry %s", refname, sha1_to_hex(sha1));
+ error("%s: invalid reflog entry %s", refname, oid_to_hex(oid));
errors_found |= ERROR_REACHABLE;
}
}
}
-static int fsck_handle_reflog_ent(unsigned char *osha1, unsigned char *nsha1,
- const char *email, unsigned long timestamp, int tz,
+static int fsck_handle_reflog_ent(struct object_id *ooid, struct object_id *noid,
+ const char *email, timestamp_t timestamp, int tz,
const char *message, void *cb_data)
{
const char *refname = cb_data;
if (verbose)
fprintf(stderr, "Checking reflog %s->%s\n",
- sha1_to_hex(osha1), sha1_to_hex(nsha1));
+ oid_to_hex(ooid), oid_to_hex(noid));
- fsck_handle_reflog_sha1(refname, osha1);
- fsck_handle_reflog_sha1(refname, nsha1);
+ fsck_handle_reflog_oid(refname, ooid, 0);
+ fsck_handle_reflog_oid(refname, noid, timestamp);
return 0;
}
/* We'll continue with the rest despite the error.. */
return 0;
}
- if (obj->type != OBJ_COMMIT && is_branch(refname))
+ if (obj->type != OBJ_COMMIT && is_branch(refname)) {
error("%s: not a commit", refname);
+ errors_found |= ERROR_REFS;
+ }
default_refs++;
obj->used = 1;
+ if (name_objects)
+ add_decoration(fsck_walk_options.object_names,
+ obj, xstrdup(refname));
mark_object_reachable(obj);
return 0;
}
}
+static struct object *parse_loose_object(const struct object_id *oid,
+ const char *path)
+{
+ struct object *obj;
+ void *contents;
+ enum object_type type;
+ unsigned long size;
+ int eaten;
+
+ if (read_loose_object(path, oid->hash, &type, &size, &contents) < 0)
+ return NULL;
+
+ if (!contents && type != OBJ_BLOB)
+ die("BUG: read_loose_object streamed a non-blob");
+
+ obj = parse_object_buffer(oid->hash, type, size, contents, &eaten);
+
+ if (!eaten)
+ free(contents);
+ return obj;
+}
+
+static int fsck_loose(const struct object_id *oid, const char *path, void *data)
+{
+ struct object *obj = parse_loose_object(oid, path);
+
+ if (!obj) {
+ errors_found |= ERROR_OBJECT;
+ error("%s: object corrupt or missing: %s",
+ oid_to_hex(oid), path);
+ return 0; /* keep checking other objects */
+ }
+
+ obj->flags = HAS_OBJ;
+ if (fsck_obj(obj))
+ errors_found |= ERROR_OBJECT;
+ return 0;
+}
+
+static int fsck_cruft(const char *basename, const char *path, void *data)
+{
+ if (!starts_with(basename, "tmp_obj_"))
+ fprintf(stderr, "bad sha1 file: %s\n", path);
+ return 0;
+}
+
+static int fsck_subdir(int nr, const char *path, void *progress)
+{
+ display_progress(progress, nr + 1);
+ return 0;
+}
+
static void fsck_object_dir(const char *path)
{
- int i;
struct progress *progress = NULL;
if (verbose)
if (show_progress)
progress = start_progress(_("Checking object directories"), 256);
- for (i = 0; i < 256; i++) {
- static char dir[4096];
- sprintf(dir, "%s/%02x", path, i);
- fsck_dir(i, dir);
- display_progress(progress, i+1);
- }
+
+ for_each_loose_file_in_objdir(path, fsck_loose, fsck_cruft, fsck_subdir,
+ progress);
+ display_progress(progress, 256);
stop_progress(&progress);
- fsck_sha1_list();
}
static int fsck_head_link(void)
{
- int flag;
int null_is_error = 0;
if (verbose)
fprintf(stderr, "Checking HEAD link\n");
- head_points_at = resolve_ref_unsafe("HEAD", 0, head_oid.hash, &flag);
- if (!head_points_at)
+ head_points_at = resolve_ref_unsafe("HEAD", 0, head_oid.hash, NULL);
+ if (!head_points_at) {
+ errors_found |= ERROR_REFS;
return error("Invalid HEAD");
+ }
if (!strcmp(head_points_at, "HEAD"))
/* detached HEAD */
null_is_error = 1;
- else if (!starts_with(head_points_at, "refs/heads/"))
+ else if (!starts_with(head_points_at, "refs/heads/")) {
+ errors_found |= ERROR_REFS;
return error("HEAD points to something strange (%s)",
head_points_at);
+ }
if (is_null_oid(&head_oid)) {
- if (null_is_error)
+ if (null_is_error) {
+ errors_found |= ERROR_REFS;
return error("HEAD: detached HEAD points at nothing");
+ }
fprintf(stderr, "notice: HEAD points to an unborn branch (%s)\n",
head_points_at + 11);
}
if (!obj) {
error("%s: invalid sha1 pointer in cache-tree",
sha1_to_hex(it->sha1));
+ errors_found |= ERROR_REFS;
return 1;
}
obj->used = 1;
+ if (name_objects)
+ add_decoration(fsck_walk_options.object_names,
+ obj, xstrdup(":"));
mark_object_reachable(obj);
if (obj->type != OBJ_TREE)
err |= objerror(obj, "non-tree in cache-tree");
return err;
}
+static void mark_object_for_connectivity(const struct object_id *oid)
+{
+ struct object *obj = lookup_unknown_object(oid->hash);
+ obj->flags |= HAS_OBJ;
+}
+
+static int mark_loose_for_connectivity(const struct object_id *oid,
+ const char *path,
+ void *data)
+{
+ mark_object_for_connectivity(oid);
+ return 0;
+}
+
+static int mark_packed_for_connectivity(const struct object_id *oid,
+ struct packed_git *pack,
+ uint32_t pos,
+ void *data)
+{
+ mark_object_for_connectivity(oid);
+ return 0;
+}
+
static char const * const fsck_usage[] = {
N_("git fsck [<options>] [<object>...]"),
NULL
OPT_BOOL(0, "cache", &keep_cache_objects, N_("make index objects head nodes")),
OPT_BOOL(0, "reflogs", &include_reflogs, N_("make reflogs head nodes (default)")),
OPT_BOOL(0, "full", &check_full, N_("also consider packs and alternate objects")),
+ OPT_BOOL(0, "connectivity-only", &connectivity_only, N_("check only connectivity")),
OPT_BOOL(0, "strict", &check_strict, N_("enable more strict checking")),
OPT_BOOL(0, "lost-found", &write_lost_and_found,
N_("write dangling objects in .git/lost-found")),
OPT_BOOL(0, "progress", &show_progress, N_("show progress")),
+ OPT_BOOL(0, "name-objects", &name_objects, N_("show verbose names for reachable objects")),
OPT_END(),
};
argc = parse_options(argc, argv, prefix, fsck_opts, fsck_usage, 0);
+ fsck_walk_options.walk = mark_object;
+ fsck_obj_options.walk = mark_used;
+ fsck_obj_options.error_func = fsck_error_func;
+ if (check_strict)
+ fsck_obj_options.strict = 1;
+
if (show_progress == -1)
show_progress = isatty(2);
if (verbose)
include_reflogs = 0;
}
- fsck_head_link();
- fsck_object_dir(get_object_directory());
-
- prepare_alt_odb();
- for (alt = alt_odb_list; alt; alt = alt->next) {
- char namebuf[PATH_MAX];
- int namelen = alt->name - alt->base;
- memcpy(namebuf, alt->base, namelen);
- namebuf[namelen - 1] = 0;
- fsck_object_dir(namebuf);
- }
+ if (name_objects)
+ fsck_walk_options.object_names =
+ xcalloc(1, sizeof(struct decoration));
- if (check_full) {
- struct packed_git *p;
- uint32_t total = 0, count = 0;
- struct progress *progress = NULL;
+ git_config(fsck_config, NULL);
- prepare_packed_git();
-
- if (show_progress) {
+ fsck_head_link();
+ if (connectivity_only) {
+ for_each_loose_object(mark_loose_for_connectivity, NULL, 0);
+ for_each_packed_object(mark_packed_for_connectivity, NULL, 0);
+ } else {
+ fsck_object_dir(get_object_directory());
+
+ prepare_alt_odb();
+ for (alt = alt_odb_list; alt; alt = alt->next)
+ fsck_object_dir(alt->path);
+
+ if (check_full) {
+ struct packed_git *p;
+ uint32_t total = 0, count = 0;
+ struct progress *progress = NULL;
+
+ prepare_packed_git();
+
+ if (show_progress) {
+ for (p = packed_git; p; p = p->next) {
+ if (open_pack_index(p))
+ continue;
+ total += p->num_objects;
+ }
+
+ progress = start_progress(_("Checking objects"), total);
+ }
for (p = packed_git; p; p = p->next) {
- if (open_pack_index(p))
- continue;
- total += p->num_objects;
+ /* verify gives error messages itself */
+ if (verify_pack(p, fsck_obj_buffer,
+ progress, count))
+ errors_found |= ERROR_PACK;
+ count += p->num_objects;
}
-
- progress = start_progress(_("Checking objects"), total);
+ stop_progress(&progress);
}
- for (p = packed_git; p; p = p->next) {
- /* verify gives error messages itself */
- if (verify_pack(p, fsck_obj_buffer,
- progress, count))
- errors_found |= ERROR_PACK;
- count += p->num_objects;
- }
- stop_progress(&progress);
}
heads = 0;
if (!get_sha1(arg, sha1)) {
struct object *obj = lookup_object(sha1);
- /* Error is printed by lookup_object(). */
- if (!obj)
+ if (!obj || !(obj->flags & HAS_OBJ)) {
+ error("%s: object missing", sha1_to_hex(sha1));
+ errors_found |= ERROR_OBJECT;
continue;
+ }
obj->used = 1;
+ if (name_objects)
+ add_decoration(fsck_walk_options.object_names,
+ obj, xstrdup(arg));
mark_object_reachable(obj);
heads++;
continue;
}
error("invalid parameter: expected sha1, got '%s'", arg);
+ errors_found |= ERROR_OBJECT;
}
/*
* default ones from .git/refs. We also consider the index file
* in this case (ie this implies --cache).
*/
- if (!heads) {
+ if (!argc) {
get_default_heads();
keep_cache_objects = 1;
}
if (keep_cache_objects) {
+ verify_index_checksum = 1;
read_cache();
for (i = 0; i < active_nr; i++) {
unsigned int mode;
mode = active_cache[i]->ce_mode;
if (S_ISGITLINK(mode))
continue;
- blob = lookup_blob(active_cache[i]->sha1);
+ blob = lookup_blob(active_cache[i]->oid.hash);
if (!blob)
continue;
obj = &blob->object;
obj->used = 1;
+ if (name_objects)
+ add_decoration(fsck_walk_options.object_names,
+ obj,
+ xstrfmt(":%s", active_cache[i]->name));
mark_object_reachable(obj);
}
if (active_cache_tree)