summaryrefslogtreecommitdiff
path: root/fsck.c
diff options
context:
space:
mode:
Diffstat (limited to 'fsck.c')
-rw-r--r--fsck.c681
1 files changed, 425 insertions, 256 deletions
diff --git a/fsck.c b/fsck.c
index a0cee0be59..f82e2fe9e3 100644
--- a/fsck.c
+++ b/fsck.c
@@ -9,13 +9,14 @@
#include "tag.h"
#include "fsck.h"
#include "refs.h"
+#include "url.h"
#include "utf8.h"
-#include "sha1-array.h"
#include "decorate.h"
#include "oidset.h"
#include "packfile.h"
#include "submodule-config.h"
#include "config.h"
+#include "credential.h"
#include "help.h"
static struct oidset gitmodules_found = OIDSET_INIT;
@@ -44,21 +45,17 @@ static struct oidset gitmodules_done = OIDSET_INIT;
FUNC(MISSING_AUTHOR, ERROR) \
FUNC(MISSING_COMMITTER, ERROR) \
FUNC(MISSING_EMAIL, ERROR) \
- FUNC(MISSING_GRAFT, ERROR) \
FUNC(MISSING_NAME_BEFORE_EMAIL, ERROR) \
FUNC(MISSING_OBJECT, ERROR) \
- FUNC(MISSING_PARENT, ERROR) \
FUNC(MISSING_SPACE_BEFORE_DATE, ERROR) \
FUNC(MISSING_SPACE_BEFORE_EMAIL, ERROR) \
FUNC(MISSING_TAG, ERROR) \
FUNC(MISSING_TAG_ENTRY, ERROR) \
- FUNC(MISSING_TAG_OBJECT, ERROR) \
FUNC(MISSING_TREE, ERROR) \
FUNC(MISSING_TREE_OBJECT, ERROR) \
FUNC(MISSING_TYPE, ERROR) \
FUNC(MISSING_TYPE_ENTRY, ERROR) \
FUNC(MULTIPLE_AUTHORS, ERROR) \
- FUNC(TAG_OBJECT_NOT_TAG, ERROR) \
FUNC(TREE_NOT_SORTED, ERROR) \
FUNC(UNKNOWN_TYPE, ERROR) \
FUNC(ZERO_PADDED_DATE, ERROR) \
@@ -67,6 +64,9 @@ static struct oidset gitmodules_done = OIDSET_INIT;
FUNC(GITMODULES_LARGE, ERROR) \
FUNC(GITMODULES_NAME, ERROR) \
FUNC(GITMODULES_SYMLINK, ERROR) \
+ FUNC(GITMODULES_URL, ERROR) \
+ FUNC(GITMODULES_PATH, ERROR) \
+ FUNC(GITMODULES_UPDATE, ERROR) \
/* warnings */ \
FUNC(BAD_FILEMODE, WARN) \
FUNC(EMPTY_NAME, WARN) \
@@ -180,44 +180,6 @@ static int fsck_msg_type(enum fsck_msg_id msg_id,
return msg_type;
}
-static void init_skiplist(struct fsck_options *options, const char *path)
-{
- static struct oid_array skiplist = OID_ARRAY_INIT;
- int sorted, fd;
- char buffer[GIT_MAX_HEXSZ + 1];
- struct object_id oid;
-
- if (options->skiplist)
- sorted = options->skiplist->sorted;
- else {
- sorted = 1;
- options->skiplist = &skiplist;
- }
-
- fd = open(path, O_RDONLY);
- if (fd < 0)
- die("Could not open skip list: %s", path);
- for (;;) {
- const char *p;
- int result = read_in_full(fd, buffer, sizeof(buffer));
- if (result < 0)
- die_errno("Could not read '%s'", path);
- if (!result)
- break;
- if (parse_oid_hex(buffer, &oid, &p) || *p != '\n')
- die("Invalid SHA-1: %s", buffer);
- oid_array_append(&skiplist, &oid);
- if (sorted && skiplist.nr > 1 &&
- oidcmp(&skiplist.oid[skiplist.nr - 2],
- &oid) > 0)
- sorted = 0;
- }
- close(fd);
-
- if (sorted)
- skiplist.sorted = 1;
-}
-
static int parse_msg_type(const char *str)
{
if (!strcmp(str, "error"))
@@ -286,7 +248,7 @@ void fsck_set_msg_types(struct fsck_options *options, const char *values)
if (!strcmp(buf, "skiplist")) {
if (equal == len)
die("skiplist requires a path");
- init_skiplist(options, buf + equal + 1);
+ oidset_parse_file(&options->skiplist, buf + equal + 1);
buf += len + 1;
continue;
}
@@ -318,16 +280,16 @@ static void append_msg_id(struct strbuf *sb, const char *msg_id)
strbuf_addstr(sb, ": ");
}
-static int object_on_skiplist(struct fsck_options *opts, struct object *obj)
+static int object_on_skiplist(struct fsck_options *opts,
+ const struct object_id *oid)
{
- if (opts && opts->skiplist && obj)
- return oid_array_lookup(opts->skiplist, &obj->oid) >= 0;
- return 0;
+ return opts && oid && oidset_contains(&opts->skiplist, oid);
}
-__attribute__((format (printf, 4, 5)))
-static int report(struct fsck_options *options, struct object *object,
- enum fsck_msg_id id, const char *fmt, ...)
+__attribute__((format (printf, 5, 6)))
+static int report(struct fsck_options *options,
+ const struct object_id *oid, enum object_type object_type,
+ enum fsck_msg_id id, const char *fmt, ...)
{
va_list ap;
struct strbuf sb = STRBUF_INIT;
@@ -336,7 +298,7 @@ static int report(struct fsck_options *options, struct object *object,
if (msg_type == FSCK_IGNORE)
return 0;
- if (object_on_skiplist(options, object))
+ if (object_on_skiplist(options, oid))
return 0;
if (msg_type == FSCK_FATAL)
@@ -348,49 +310,71 @@ static int report(struct fsck_options *options, struct object *object,
va_start(ap, fmt);
strbuf_vaddf(&sb, fmt, ap);
- result = options->error_func(options, object, msg_type, sb.buf);
+ result = options->error_func(options, oid, object_type,
+ msg_type, sb.buf);
strbuf_release(&sb);
va_end(ap);
return result;
}
-static char *get_object_name(struct fsck_options *options, struct object *obj)
+void fsck_enable_object_names(struct fsck_options *options)
+{
+ if (!options->object_names)
+ options->object_names = kh_init_oid_map();
+}
+
+const char *fsck_get_object_name(struct fsck_options *options,
+ const struct object_id *oid)
{
+ khiter_t pos;
if (!options->object_names)
return NULL;
- return lookup_decoration(options->object_names, obj);
+ pos = kh_get_oid_map(options->object_names, *oid);
+ if (pos >= kh_end(options->object_names))
+ return NULL;
+ return kh_value(options->object_names, pos);
}
-static void put_object_name(struct fsck_options *options, struct object *obj,
- const char *fmt, ...)
+void fsck_put_object_name(struct fsck_options *options,
+ const struct object_id *oid,
+ const char *fmt, ...)
{
va_list ap;
struct strbuf buf = STRBUF_INIT;
- char *existing;
+ khiter_t pos;
+ int hashret;
if (!options->object_names)
return;
- existing = lookup_decoration(options->object_names, obj);
- if (existing)
+
+ pos = kh_put_oid_map(options->object_names, *oid, &hashret);
+ if (!hashret)
return;
va_start(ap, fmt);
strbuf_vaddf(&buf, fmt, ap);
- add_decoration(options->object_names, obj, strbuf_detach(&buf, NULL));
+ kh_value(options->object_names, pos) = strbuf_detach(&buf, NULL);
va_end(ap);
}
-static const char *describe_object(struct fsck_options *o, struct object *obj)
+const char *fsck_describe_object(struct fsck_options *options,
+ const struct object_id *oid)
{
- static struct strbuf buf = STRBUF_INIT;
- char *name;
-
- strbuf_reset(&buf);
- strbuf_addstr(&buf, oid_to_hex(&obj->oid));
- if (o->object_names && (name = lookup_decoration(o->object_names, obj)))
- strbuf_addf(&buf, " (%s)", name);
+ static struct strbuf bufs[] = {
+ STRBUF_INIT, STRBUF_INIT, STRBUF_INIT, STRBUF_INIT
+ };
+ static int b = 0;
+ struct strbuf *buf;
+ const char *name = fsck_get_object_name(options, oid);
+
+ buf = bufs + b;
+ b = (b + 1) % ARRAY_SIZE(bufs);
+ strbuf_reset(buf);
+ strbuf_addstr(buf, oid_to_hex(oid));
+ if (name)
+ strbuf_addf(buf, " (%s)", name);
- return buf.buf;
+ return buf->buf;
}
static int fsck_walk_tree(struct tree *tree, void *data, struct fsck_options *options)
@@ -403,7 +387,7 @@ static int fsck_walk_tree(struct tree *tree, void *data, struct fsck_options *op
if (parse_tree(tree))
return -1;
- name = get_object_name(options, &tree->object);
+ name = fsck_get_object_name(options, &tree->object.oid);
if (init_tree_desc_gently(&desc, tree->buffer, tree->size))
return -1;
while (tree_entry_gently(&desc, &entry)) {
@@ -414,22 +398,23 @@ static int fsck_walk_tree(struct tree *tree, void *data, struct fsck_options *op
continue;
if (S_ISDIR(entry.mode)) {
- obj = (struct object *)lookup_tree(the_repository, entry.oid);
+ obj = (struct object *)lookup_tree(the_repository, &entry.oid);
if (name && obj)
- put_object_name(options, obj, "%s%s/", name,
- entry.path);
+ fsck_put_object_name(options, &entry.oid, "%s%s/",
+ name, entry.path);
result = options->walk(obj, OBJ_TREE, data, options);
}
else if (S_ISREG(entry.mode) || S_ISLNK(entry.mode)) {
- obj = (struct object *)lookup_blob(the_repository, entry.oid);
+ obj = (struct object *)lookup_blob(the_repository, &entry.oid);
if (name && obj)
- put_object_name(options, obj, "%s%s", name,
- entry.path);
+ fsck_put_object_name(options, &entry.oid, "%s%s",
+ name, entry.path);
result = options->walk(obj, OBJ_BLOB, data, options);
}
else {
result = error("in tree %s: entry %s has bad mode %.6o",
- describe_object(options, &tree->object), entry.path, entry.mode);
+ fsck_describe_object(options, &tree->object.oid),
+ entry.path, entry.mode);
}
if (result < 0)
return result;
@@ -450,10 +435,10 @@ static int fsck_walk_commit(struct commit *commit, void *data, struct fsck_optio
if (parse_commit(commit))
return -1;
- name = get_object_name(options, &commit->object);
+ name = fsck_get_object_name(options, &commit->object.oid);
if (name)
- put_object_name(options, &get_commit_tree(commit)->object,
- "%s:", name);
+ fsck_put_object_name(options, get_commit_tree_oid(commit),
+ "%s:", name);
result = options->walk((struct object *)get_commit_tree(commit),
OBJ_TREE, data, options);
@@ -481,16 +466,17 @@ static int fsck_walk_commit(struct commit *commit, void *data, struct fsck_optio
while (parents) {
if (name) {
- struct object *obj = &parents->item->object;
+ struct object_id *oid = &parents->item->object.oid;
- if (++counter > 1)
- put_object_name(options, obj, "%s^%d",
- name, counter);
+ if (counter++)
+ fsck_put_object_name(options, oid, "%s^%d",
+ name, counter);
else if (generation > 0)
- put_object_name(options, obj, "%.*s~%d",
- name_prefix_len, name, generation + 1);
+ fsck_put_object_name(options, oid, "%.*s~%d",
+ name_prefix_len, name,
+ generation + 1);
else
- put_object_name(options, obj, "%s^", name);
+ fsck_put_object_name(options, oid, "%s^", name);
}
result = options->walk((struct object *)parents->item, OBJ_COMMIT, data, options);
if (result < 0)
@@ -504,12 +490,12 @@ static int fsck_walk_commit(struct commit *commit, void *data, struct fsck_optio
static int fsck_walk_tag(struct tag *tag, void *data, struct fsck_options *options)
{
- char *name = get_object_name(options, &tag->object);
+ const char *name = fsck_get_object_name(options, &tag->object.oid);
if (parse_tag(tag))
return -1;
if (name)
- put_object_name(options, tag->tagged, "%s", name);
+ fsck_put_object_name(options, &tag->tagged->oid, "%s", name);
return options->walk(tag->tagged, OBJ_ANY, data, options);
}
@@ -531,11 +517,34 @@ int fsck_walk(struct object *obj, void *data, struct fsck_options *options)
case OBJ_TAG:
return fsck_walk_tag((struct tag *)obj, data, options);
default:
- error("Unknown object type for %s", describe_object(options, obj));
+ error("Unknown object type for %s",
+ fsck_describe_object(options, &obj->oid));
return -1;
}
}
+struct name_stack {
+ const char **names;
+ size_t nr, alloc;
+};
+
+static void name_stack_push(struct name_stack *stack, const char *name)
+{
+ ALLOC_GROW(stack->names, stack->nr + 1, stack->alloc);
+ stack->names[stack->nr++] = name;
+}
+
+static const char *name_stack_pop(struct name_stack *stack)
+{
+ return stack->nr ? stack->names[--stack->nr] : NULL;
+}
+
+static void name_stack_clear(struct name_stack *stack)
+{
+ FREE_AND_NULL(stack->names);
+ stack->nr = stack->alloc = 0;
+}
+
/*
* The entries in a tree are ordered in the _path_ order,
* which means that a directory entry is ordered by adding
@@ -547,7 +556,14 @@ int fsck_walk(struct object *obj, void *data, struct fsck_options *options)
#define TREE_UNORDERED (-1)
#define TREE_HAS_DUPS (-2)
-static int verify_ordered(unsigned mode1, const char *name1, unsigned mode2, const char *name2)
+static int is_less_than_slash(unsigned char c)
+{
+ return '\0' < c && c < '/';
+}
+
+static int verify_ordered(unsigned mode1, const char *name1,
+ unsigned mode2, const char *name2,
+ struct name_stack *candidates)
{
int len1 = strlen(name1);
int len2 = strlen(name2);
@@ -579,10 +595,47 @@ static int verify_ordered(unsigned mode1, const char *name1, unsigned mode2, con
c1 = '/';
if (!c2 && S_ISDIR(mode2))
c2 = '/';
+
+ /*
+ * There can be non-consecutive duplicates due to the implicitly
+ * added slash, e.g.:
+ *
+ * foo
+ * foo.bar
+ * foo.bar.baz
+ * foo.bar/
+ * foo/
+ *
+ * Record non-directory candidates (like "foo" and "foo.bar" in
+ * the example) on a stack and check directory candidates (like
+ * foo/" and "foo.bar/") against that stack.
+ */
+ if (!c1 && is_less_than_slash(c2)) {
+ name_stack_push(candidates, name1);
+ } else if (c2 == '/' && is_less_than_slash(c1)) {
+ for (;;) {
+ const char *p;
+ const char *f_name = name_stack_pop(candidates);
+
+ if (!f_name)
+ break;
+ if (!skip_prefix(name2, f_name, &p))
+ continue;
+ if (!*p)
+ return TREE_HAS_DUPS;
+ if (is_less_than_slash(*p)) {
+ name_stack_push(candidates, f_name);
+ break;
+ }
+ }
+ }
+
return c1 < c2 ? 0 : TREE_UNORDERED;
}
-static int fsck_tree(struct tree *item, struct fsck_options *options)
+static int fsck_tree(const struct object_id *oid,
+ const char *buffer, unsigned long size,
+ struct fsck_options *options)
{
int retval = 0;
int has_null_sha1 = 0;
@@ -598,9 +651,10 @@ static int fsck_tree(struct tree *item, struct fsck_options *options)
struct tree_desc desc;
unsigned o_mode;
const char *o_name;
+ struct name_stack df_dup_candidates = { NULL };
- if (init_tree_desc_gently(&desc, item->buffer, item->size)) {
- retval += report(options, &item->object, FSCK_MSG_BAD_TREE, "cannot be parsed as a tree");
+ if (init_tree_desc_gently(&desc, buffer, size)) {
+ retval += report(options, oid, OBJ_TREE, FSCK_MSG_BAD_TREE, "cannot be parsed as a tree");
return retval;
}
@@ -608,8 +662,8 @@ static int fsck_tree(struct tree *item, struct fsck_options *options)
o_name = NULL;
while (desc.size) {
- unsigned mode;
- const char *name;
+ unsigned short mode;
+ const char *name, *backslash;
const struct object_id *oid;
oid = tree_entry_extract(&desc, &name, &mode);
@@ -626,13 +680,30 @@ static int fsck_tree(struct tree *item, struct fsck_options *options)
if (!S_ISLNK(mode))
oidset_insert(&gitmodules_found, oid);
else
- retval += report(options, &item->object,
+ retval += report(options,
+ oid, OBJ_TREE,
FSCK_MSG_GITMODULES_SYMLINK,
".gitmodules is a symbolic link");
}
+ if ((backslash = strchr(name, '\\'))) {
+ while (backslash) {
+ backslash++;
+ has_dotgit |= is_ntfs_dotgit(backslash);
+ if (is_ntfs_dotgitmodules(backslash)) {
+ if (!S_ISLNK(mode))
+ oidset_insert(&gitmodules_found, oid);
+ else
+ retval += report(options, oid, OBJ_TREE,
+ FSCK_MSG_GITMODULES_SYMLINK,
+ ".gitmodules is a symbolic link");
+ }
+ backslash = strchr(backslash, '\\');
+ }
+ }
+
if (update_tree_entry_gently(&desc)) {
- retval += report(options, &item->object, FSCK_MSG_BAD_TREE, "cannot be parsed as a tree");
+ retval += report(options, oid, OBJ_TREE, FSCK_MSG_BAD_TREE, "cannot be parsed as a tree");
break;
}
@@ -660,7 +731,8 @@ static int fsck_tree(struct tree *item, struct fsck_options *options)
}
if (o_name) {
- switch (verify_ordered(o_mode, o_name, mode, name)) {
+ switch (verify_ordered(o_mode, o_name, mode, name,
+ &df_dup_candidates)) {
case TREE_UNORDERED:
not_properly_sorted = 1;
break;
@@ -676,31 +748,34 @@ static int fsck_tree(struct tree *item, struct fsck_options *options)
o_name = name;
}
+ name_stack_clear(&df_dup_candidates);
+
if (has_null_sha1)
- retval += report(options, &item->object, FSCK_MSG_NULL_SHA1, "contains entries pointing to null sha1");
+ retval += report(options, oid, OBJ_TREE, FSCK_MSG_NULL_SHA1, "contains entries pointing to null sha1");
if (has_full_path)
- retval += report(options, &item->object, FSCK_MSG_FULL_PATHNAME, "contains full pathnames");
+ retval += report(options, oid, OBJ_TREE, FSCK_MSG_FULL_PATHNAME, "contains full pathnames");
if (has_empty_name)
- retval += report(options, &item->object, FSCK_MSG_EMPTY_NAME, "contains empty pathname");
+ retval += report(options, oid, OBJ_TREE, FSCK_MSG_EMPTY_NAME, "contains empty pathname");
if (has_dot)
- retval += report(options, &item->object, FSCK_MSG_HAS_DOT, "contains '.'");
+ retval += report(options, oid, OBJ_TREE, FSCK_MSG_HAS_DOT, "contains '.'");
if (has_dotdot)
- retval += report(options, &item->object, FSCK_MSG_HAS_DOTDOT, "contains '..'");
+ retval += report(options, oid, OBJ_TREE, FSCK_MSG_HAS_DOTDOT, "contains '..'");
if (has_dotgit)
- retval += report(options, &item->object, FSCK_MSG_HAS_DOTGIT, "contains '.git'");
+ retval += report(options, oid, OBJ_TREE, FSCK_MSG_HAS_DOTGIT, "contains '.git'");
if (has_zero_pad)
- retval += report(options, &item->object, FSCK_MSG_ZERO_PADDED_FILEMODE, "contains zero-padded file modes");
+ retval += report(options, oid, OBJ_TREE, FSCK_MSG_ZERO_PADDED_FILEMODE, "contains zero-padded file modes");
if (has_bad_modes)
- retval += report(options, &item->object, FSCK_MSG_BAD_FILEMODE, "contains bad file modes");
+ retval += report(options, oid, OBJ_TREE, FSCK_MSG_BAD_FILEMODE, "contains bad file modes");
if (has_dup_entries)
- retval += report(options, &item->object, FSCK_MSG_DUPLICATE_ENTRIES, "contains duplicate file entries");
+ retval += report(options, oid, OBJ_TREE, FSCK_MSG_DUPLICATE_ENTRIES, "contains duplicate file entries");
if (not_properly_sorted)
- retval += report(options, &item->object, FSCK_MSG_TREE_NOT_SORTED, "not properly sorted");
+ retval += report(options, oid, OBJ_TREE, FSCK_MSG_TREE_NOT_SORTED, "not properly sorted");
return retval;
}
static int verify_headers(const void *data, unsigned long size,
- struct object *obj, struct fsck_options *options)
+ const struct object_id *oid, enum object_type type,
+ struct fsck_options *options)
{
const char *buffer = (const char *)data;
unsigned long i;
@@ -708,7 +783,7 @@ static int verify_headers(const void *data, unsigned long size,
for (i = 0; i < size; i++) {
switch (buffer[i]) {
case '\0':
- return report(options, obj,
+ return report(options, oid, type,
FSCK_MSG_NUL_IN_HEADER,
"unterminated header: NUL at offset %ld", i);
case '\n':
@@ -726,11 +801,13 @@ static int verify_headers(const void *data, unsigned long size,
if (size && buffer[size - 1] == '\n')
return 0;
- return report(options, obj,
+ return report(options, oid, type,
FSCK_MSG_UNTERMINATED_HEADER, "unterminated header");
}
-static int fsck_ident(const char **ident, struct object *obj, struct fsck_options *options)
+static int fsck_ident(const char **ident,
+ const struct object_id *oid, enum object_type type,
+ struct fsck_options *options)
{
const char *p = *ident;
char *end;
@@ -740,28 +817,28 @@ static int fsck_ident(const char **ident, struct object *obj, struct fsck_option
(*ident)++;
if (*p == '<')
- return report(options, obj, FSCK_MSG_MISSING_NAME_BEFORE_EMAIL, "invalid author/committer line - missing space before email");
+ return report(options, oid, type, FSCK_MSG_MISSING_NAME_BEFORE_EMAIL, "invalid author/committer line - missing space before email");
p += strcspn(p, "<>\n");
if (*p == '>')
- return report(options, obj, FSCK_MSG_BAD_NAME, "invalid author/committer line - bad name");
+ return report(options, oid, type, FSCK_MSG_BAD_NAME, "invalid author/committer line - bad name");
if (*p != '<')
- return report(options, obj, FSCK_MSG_MISSING_EMAIL, "invalid author/committer line - missing email");
+ return report(options, oid, type, FSCK_MSG_MISSING_EMAIL, "invalid author/committer line - missing email");
if (p[-1] != ' ')
- return report(options, obj, FSCK_MSG_MISSING_SPACE_BEFORE_EMAIL, "invalid author/committer line - missing space before email");
+ return report(options, oid, type, FSCK_MSG_MISSING_SPACE_BEFORE_EMAIL, "invalid author/committer line - missing space before email");
p++;
p += strcspn(p, "<>\n");
if (*p != '>')
- return report(options, obj, FSCK_MSG_BAD_EMAIL, "invalid author/committer line - bad email");
+ return report(options, oid, type, FSCK_MSG_BAD_EMAIL, "invalid author/committer line - bad email");
p++;
if (*p != ' ')
- return report(options, obj, FSCK_MSG_MISSING_SPACE_BEFORE_DATE, "invalid author/committer line - missing space before date");
+ return report(options, oid, type, FSCK_MSG_MISSING_SPACE_BEFORE_DATE, "invalid author/committer line - missing space before date");
p++;
if (*p == '0' && p[1] != ' ')
- return report(options, obj, FSCK_MSG_ZERO_PADDED_DATE, "invalid author/committer line - zero-padded date");
+ return report(options, oid, type, FSCK_MSG_ZERO_PADDED_DATE, "invalid author/committer line - zero-padded date");
if (date_overflows(parse_timestamp(p, &end, 10)))
- return report(options, obj, FSCK_MSG_BAD_DATE_OVERFLOW, "invalid author/committer line - date causes integer overflow");
+ return report(options, oid, type, FSCK_MSG_BAD_DATE_OVERFLOW, "invalid author/committer line - date causes integer overflow");
if ((end == p || *end != ' '))
- return report(options, obj, FSCK_MSG_BAD_DATE, "invalid author/committer line - bad date");
+ return report(options, oid, type, FSCK_MSG_BAD_DATE, "invalid author/committer line - bad date");
p = end + 1;
if ((*p != '+' && *p != '-') ||
!isdigit(p[1]) ||
@@ -769,83 +846,60 @@ static int fsck_ident(const char **ident, struct object *obj, struct fsck_option
!isdigit(p[3]) ||
!isdigit(p[4]) ||
(p[5] != '\n'))
- return report(options, obj, FSCK_MSG_BAD_TIMEZONE, "invalid author/committer line - bad time zone");
+ return report(options, oid, type, FSCK_MSG_BAD_TIMEZONE, "invalid author/committer line - bad time zone");
p += 6;
return 0;
}
-static int fsck_commit_buffer(struct commit *commit, const char *buffer,
- unsigned long size, struct fsck_options *options)
+static int fsck_commit(const struct object_id *oid,
+ const char *buffer, unsigned long size,
+ struct fsck_options *options)
{
- struct object_id tree_oid, oid;
- struct commit_graft *graft;
- unsigned parent_count, parent_line_count = 0, author_count;
+ struct object_id tree_oid, parent_oid;
+ unsigned author_count;
int err;
const char *buffer_begin = buffer;
const char *p;
- if (verify_headers(buffer, size, &commit->object, options))
+ if (verify_headers(buffer, size, oid, OBJ_COMMIT, options))
return -1;
if (!skip_prefix(buffer, "tree ", &buffer))
- return report(options, &commit->object, FSCK_MSG_MISSING_TREE, "invalid format - expected 'tree' line");
+ return report(options, oid, OBJ_COMMIT, FSCK_MSG_MISSING_TREE, "invalid format - expected 'tree' line");
if (parse_oid_hex(buffer, &tree_oid, &p) || *p != '\n') {
- err = report(options, &commit->object, FSCK_MSG_BAD_TREE_SHA1, "invalid 'tree' line format - bad sha1");
+ err = report(options, oid, OBJ_COMMIT, FSCK_MSG_BAD_TREE_SHA1, "invalid 'tree' line format - bad sha1");
if (err)
return err;
}
buffer = p + 1;
while (skip_prefix(buffer, "parent ", &buffer)) {
- if (parse_oid_hex(buffer, &oid, &p) || *p != '\n') {
- err = report(options, &commit->object, FSCK_MSG_BAD_PARENT_SHA1, "invalid 'parent' line format - bad sha1");
+ if (parse_oid_hex(buffer, &parent_oid, &p) || *p != '\n') {
+ err = report(options, oid, OBJ_COMMIT, FSCK_MSG_BAD_PARENT_SHA1, "invalid 'parent' line format - bad sha1");
if (err)
return err;
}
buffer = p + 1;
- parent_line_count++;
- }
- graft = lookup_commit_graft(the_repository, &commit->object.oid);
- parent_count = commit_list_count(commit->parents);
- if (graft) {
- if (graft->nr_parent == -1 && !parent_count)
- ; /* shallow commit */
- else if (graft->nr_parent != parent_count) {
- err = report(options, &commit->object, FSCK_MSG_MISSING_GRAFT, "graft objects missing");
- if (err)
- return err;
- }
- } else {
- if (parent_count != parent_line_count) {
- err = report(options, &commit->object, FSCK_MSG_MISSING_PARENT, "parent objects missing");
- if (err)
- return err;
- }
}
author_count = 0;
while (skip_prefix(buffer, "author ", &buffer)) {
author_count++;
- err = fsck_ident(&buffer, &commit->object, options);
+ err = fsck_ident(&buffer, oid, OBJ_COMMIT, options);
if (err)
return err;
}
if (author_count < 1)
- err = report(options, &commit->object, FSCK_MSG_MISSING_AUTHOR, "invalid format - expected 'author' line");
+ err = report(options, oid, OBJ_COMMIT, FSCK_MSG_MISSING_AUTHOR, "invalid format - expected 'author' line");
else if (author_count > 1)
- err = report(options, &commit->object, FSCK_MSG_MULTIPLE_AUTHORS, "invalid format - multiple 'author' lines");
+ err = report(options, oid, OBJ_COMMIT, FSCK_MSG_MULTIPLE_AUTHORS, "invalid format - multiple 'author' lines");
if (err)
return err;
if (!skip_prefix(buffer, "committer ", &buffer))
- return report(options, &commit->object, FSCK_MSG_MISSING_COMMITTER, "invalid format - expected 'committer' line");
- err = fsck_ident(&buffer, &commit->object, options);
+ return report(options, oid, OBJ_COMMIT, FSCK_MSG_MISSING_COMMITTER, "invalid format - expected 'committer' line");
+ err = fsck_ident(&buffer, oid, OBJ_COMMIT, options);
if (err)
return err;
- if (!get_commit_tree(commit)) {
- err = report(options, &commit->object, FSCK_MSG_BAD_TREE, "could not load commit's tree %s", oid_to_hex(&tree_oid));
- if (err)
- return err;
- }
if (memchr(buffer_begin, '\0', size)) {
- err = report(options, &commit->object, FSCK_MSG_NUL_IN_COMMIT,
+ err = report(options, oid, OBJ_COMMIT, FSCK_MSG_NUL_IN_COMMIT,
"NUL byte in the commit object body");
if (err)
return err;
@@ -853,91 +907,60 @@ static int fsck_commit_buffer(struct commit *commit, const char *buffer,
return 0;
}
-static int fsck_commit(struct commit *commit, const char *data,
- unsigned long size, struct fsck_options *options)
-{
- const char *buffer = data ? data : get_commit_buffer(commit, &size);
- int ret = fsck_commit_buffer(commit, buffer, size, options);
- if (!data)
- unuse_commit_buffer(commit, buffer);
- return ret;
-}
-
-static int fsck_tag_buffer(struct tag *tag, const char *data,
- unsigned long size, struct fsck_options *options)
+static int fsck_tag(const struct object_id *oid, const char *buffer,
+ unsigned long size, struct fsck_options *options)
{
- struct object_id oid;
+ struct object_id tagged_oid;
int ret = 0;
- const char *buffer;
- char *to_free = NULL, *eol;
+ char *eol;
struct strbuf sb = STRBUF_INIT;
const char *p;
- if (data)
- buffer = data;
- else {
- enum object_type type;
-
- buffer = to_free =
- read_object_file(&tag->object.oid, &type, &size);
- if (!buffer)
- return report(options, &tag->object,
- FSCK_MSG_MISSING_TAG_OBJECT,
- "cannot read tag object");
-
- if (type != OBJ_TAG) {
- ret = report(options, &tag->object,
- FSCK_MSG_TAG_OBJECT_NOT_TAG,
- "expected tag got %s",
- type_name(type));
- goto done;
- }
- }
-
- ret = verify_headers(buffer, size, &tag->object, options);
+ ret = verify_headers(buffer, size, oid, OBJ_TAG, options);
if (ret)
goto done;
if (!skip_prefix(buffer, "object ", &buffer)) {
- ret = report(options, &tag->object, FSCK_MSG_MISSING_OBJECT, "invalid format - expected 'object' line");
+ ret = report(options, oid, OBJ_TAG, FSCK_MSG_MISSING_OBJECT, "invalid format - expected 'object' line");
goto done;
}
- if (parse_oid_hex(buffer, &oid, &p) || *p != '\n') {
- ret = report(options, &tag->object, FSCK_MSG_BAD_OBJECT_SHA1, "invalid 'object' line format - bad sha1");
+ if (parse_oid_hex(buffer, &tagged_oid, &p) || *p != '\n') {
+ ret = report(options, oid, OBJ_TAG, FSCK_MSG_BAD_OBJECT_SHA1, "invalid 'object' line format - bad sha1");
if (ret)
goto done;
}
buffer = p + 1;
if (!skip_prefix(buffer, "type ", &buffer)) {
- ret = report(options, &tag->object, FSCK_MSG_MISSING_TYPE_ENTRY, "invalid format - expected 'type' line");
+ ret = report(options, oid, OBJ_TAG, FSCK_MSG_MISSING_TYPE_ENTRY, "invalid format - expected 'type' line");
goto done;
}
eol = strchr(buffer, '\n');
if (!eol) {
- ret = report(options, &tag->object, FSCK_MSG_MISSING_TYPE, "invalid format - unexpected end after 'type' line");
+ ret = report(options, oid, OBJ_TAG, FSCK_MSG_MISSING_TYPE, "invalid format - unexpected end after 'type' line");
goto done;
}
if (type_from_string_gently(buffer, eol - buffer, 1) < 0)
- ret = report(options, &tag->object, FSCK_MSG_BAD_TYPE, "invalid 'type' value");
+ ret = report(options, oid, OBJ_TAG, FSCK_MSG_BAD_TYPE, "invalid 'type' value");
if (ret)
goto done;
buffer = eol + 1;
if (!skip_prefix(buffer, "tag ", &buffer)) {
- ret = report(options, &tag->object, FSCK_MSG_MISSING_TAG_ENTRY, "invalid format - expected 'tag' line");
+ ret = report(options, oid, OBJ_TAG, FSCK_MSG_MISSING_TAG_ENTRY, "invalid format - expected 'tag' line");
goto done;
}
eol = strchr(buffer, '\n');
if (!eol) {
- ret = report(options, &tag->object, FSCK_MSG_MISSING_TAG, "invalid format - unexpected end after 'type' line");
+ ret = report(options, oid, OBJ_TAG, FSCK_MSG_MISSING_TAG, "invalid format - unexpected end after 'type' line");
goto done;
}
strbuf_addf(&sb, "refs/tags/%.*s", (int)(eol - buffer), buffer);
if (check_refname_format(sb.buf, 0)) {
- ret = report(options, &tag->object, FSCK_MSG_BAD_TAG_NAME,
- "invalid 'tag' name: %.*s",
- (int)(eol - buffer), buffer);
+ ret = report(options, oid, OBJ_TAG,
+ FSCK_MSG_BAD_TAG_NAME,
+ "invalid 'tag' name: %.*s",
+ (int)(eol - buffer), buffer);
if (ret)
goto done;
}
@@ -945,32 +968,163 @@ static int fsck_tag_buffer(struct tag *tag, const char *data,
if (!skip_prefix(buffer, "tagger ", &buffer)) {
/* early tags do not contain 'tagger' lines; warn only */
- ret = report(options, &tag->object, FSCK_MSG_MISSING_TAGGER_ENTRY, "invalid format - expected 'tagger' line");
+ ret = report(options, oid, OBJ_TAG, FSCK_MSG_MISSING_TAGGER_ENTRY, "invalid format - expected 'tagger' line");
if (ret)
goto done;
}
else
- ret = fsck_ident(&buffer, &tag->object, options);
+ ret = fsck_ident(&buffer, oid, OBJ_TAG, options);
done:
strbuf_release(&sb);
- free(to_free);
return ret;
}
-static int fsck_tag(struct tag *tag, const char *data,
- unsigned long size, struct fsck_options *options)
+/*
+ * Like builtin/submodule--helper.c's starts_with_dot_slash, but without
+ * relying on the platform-dependent is_dir_sep helper.
+ *
+ * This is for use in checking whether a submodule URL is interpreted as
+ * relative to the current directory on any platform, since \ is a
+ * directory separator on Windows but not on other platforms.
+ */
+static int starts_with_dot_slash(const char *str)
{
- struct object *tagged = tag->tagged;
+ return str[0] == '.' && (str[1] == '/' || str[1] == '\\');
+}
- if (!tagged)
- return report(options, &tag->object, FSCK_MSG_BAD_TAG_OBJECT, "could not load tagged object");
+/*
+ * Like starts_with_dot_slash, this is a variant of submodule--helper's
+ * helper of the same name with the twist that it accepts backslash as a
+ * directory separator even on non-Windows platforms.
+ */
+static int starts_with_dot_dot_slash(const char *str)
+{
+ return str[0] == '.' && starts_with_dot_slash(str + 1);
+}
- return fsck_tag_buffer(tag, data, size, options);
+static int submodule_url_is_relative(const char *url)
+{
+ return starts_with_dot_slash(url) || starts_with_dot_dot_slash(url);
+}
+
+/*
+ * Count directory components that a relative submodule URL should chop
+ * from the remote_url it is to be resolved against.
+ *
+ * In other words, this counts "../" components at the start of a
+ * submodule URL.
+ *
+ * Returns the number of directory components to chop and writes a
+ * pointer to the next character of url after all leading "./" and
+ * "../" components to out.
+ */
+static int count_leading_dotdots(const char *url, const char **out)
+{
+ int result = 0;
+ while (1) {
+ if (starts_with_dot_dot_slash(url)) {
+ result++;
+ url += strlen("../");
+ continue;
+ }
+ if (starts_with_dot_slash(url)) {
+ url += strlen("./");
+ continue;
+ }
+ *out = url;
+ return result;
+ }
+}
+/*
+ * Check whether a transport is implemented by git-remote-curl.
+ *
+ * If it is, returns 1 and writes the URL that would be passed to
+ * git-remote-curl to the "out" parameter.
+ *
+ * Otherwise, returns 0 and leaves "out" untouched.
+ *
+ * Examples:
+ * http::https://example.com/repo.git -> 1, https://example.com/repo.git
+ * https://example.com/repo.git -> 1, https://example.com/repo.git
+ * git://example.com/repo.git -> 0
+ *
+ * This is for use in checking for previously exploitable bugs that
+ * required a submodule URL to be passed to git-remote-curl.
+ */
+static int url_to_curl_url(const char *url, const char **out)
+{
+ /*
+ * We don't need to check for case-aliases, "http.exe", and so
+ * on because in the default configuration, is_transport_allowed
+ * prevents URLs with those schemes from being cloned
+ * automatically.
+ */
+ if (skip_prefix(url, "http::", out) ||
+ skip_prefix(url, "https::", out) ||
+ skip_prefix(url, "ftp::", out) ||
+ skip_prefix(url, "ftps::", out))
+ return 1;
+ if (starts_with(url, "http://") ||
+ starts_with(url, "https://") ||
+ starts_with(url, "ftp://") ||
+ starts_with(url, "ftps://")) {
+ *out = url;
+ return 1;
+ }
+ return 0;
+}
+
+static int check_submodule_url(const char *url)
+{
+ const char *curl_url;
+
+ if (looks_like_command_line_option(url))
+ return -1;
+
+ if (submodule_url_is_relative(url)) {
+ char *decoded;
+ const char *next;
+ int has_nl;
+
+ /*
+ * This could be appended to an http URL and url-decoded;
+ * check for malicious characters.
+ */
+ decoded = url_decode(url);
+ has_nl = !!strchr(decoded, '\n');
+
+ free(decoded);
+ if (has_nl)
+ return -1;
+
+ /*
+ * URLs which escape their root via "../" can overwrite
+ * the host field and previous components, resolving to
+ * URLs like https::example.com/submodule.git and
+ * https:///example.com/submodule.git that were
+ * susceptible to CVE-2020-11008.
+ */
+ if (count_leading_dotdots(url, &next) > 0 &&
+ (*next == ':' || *next == '/'))
+ return -1;
+ }
+
+ else if (url_to_curl_url(url, &curl_url)) {
+ struct credential c = CREDENTIAL_INIT;
+ int ret = 0;
+ if (credential_from_url_gently(&c, curl_url, 1) ||
+ !*c.host)
+ ret = -1;
+ credential_clear(&c);
+ return ret;
+ }
+
+ return 0;
}
struct fsck_gitmodules_data {
- struct object *obj;
+ const struct object_id *oid;
struct fsck_options *options;
int ret;
};
@@ -979,7 +1133,7 @@ static int fsck_gitmodules_fn(const char *var, const char *value, void *vdata)
{
struct fsck_gitmodules_data *data = vdata;
const char *subsection, *key;
- int subsection_len;
+ size_t subsection_len;
char *name;
if (parse_config_key(var, "submodule", &subsection, &subsection_len, &key) < 0 ||
@@ -988,26 +1142,47 @@ static int fsck_gitmodules_fn(const char *var, const char *value, void *vdata)
name = xmemdupz(subsection, subsection_len);
if (check_submodule_name(name) < 0)
- data->ret |= report(data->options, data->obj,
+ data->ret |= report(data->options,
+ data->oid, OBJ_BLOB,
FSCK_MSG_GITMODULES_NAME,
"disallowed submodule name: %s",
name);
+ if (!strcmp(key, "url") && value &&
+ check_submodule_url(value) < 0)
+ data->ret |= report(data->options,
+ data->oid, OBJ_BLOB,
+ FSCK_MSG_GITMODULES_URL,
+ "disallowed submodule url: %s",
+ value);
+ if (!strcmp(key, "path") && value &&
+ looks_like_command_line_option(value))
+ data->ret |= report(data->options,
+ data->oid, OBJ_BLOB,
+ FSCK_MSG_GITMODULES_PATH,
+ "disallowed submodule path: %s",
+ value);
+ if (!strcmp(key, "update") && value &&
+ parse_submodule_update_type(value) == SM_UPDATE_COMMAND)
+ data->ret |= report(data->options, data->oid, OBJ_BLOB,
+ FSCK_MSG_GITMODULES_UPDATE,
+ "disallowed submodule update setting: %s",
+ value);
free(name);
return 0;
}
-static int fsck_blob(struct blob *blob, const char *buf,
+static int fsck_blob(const struct object_id *oid, const char *buf,
unsigned long size, struct fsck_options *options)
{
struct fsck_gitmodules_data data;
struct config_options config_opts = { 0 };
- if (!oidset_contains(&gitmodules_found, &blob->object.oid))
+ if (!oidset_contains(&gitmodules_found, oid))
return 0;
- oidset_insert(&gitmodules_done, &blob->object.oid);
+ oidset_insert(&gitmodules_done, oid);
- if (object_on_skiplist(options, &blob->object))
+ if (object_on_skiplist(options, oid))
return 0;
if (!buf) {
@@ -1016,18 +1191,18 @@ static int fsck_blob(struct blob *blob, const char *buf,
* blob too gigantic to load into memory. Let's just consider
* that an error.
*/
- return report(options, &blob->object,
+ return report(options, oid, OBJ_BLOB,
FSCK_MSG_GITMODULES_LARGE,
".gitmodules too large to parse");
}
- data.obj = &blob->object;
+ data.oid = oid;
data.options = options;
data.ret = 0;
config_opts.error_action = CONFIG_ERROR_SILENT;
if (git_config_from_mem(fsck_gitmodules_fn, CONFIG_ORIGIN_BLOB,
".gitmodules", buf, size, &data, &config_opts))
- data.ret |= report(options, &blob->object,
+ data.ret |= report(options, oid, OBJ_BLOB,
FSCK_MSG_GITMODULES_PARSE,
"could not parse gitmodules blob");
@@ -1038,31 +1213,33 @@ int fsck_object(struct object *obj, void *data, unsigned long size,
struct fsck_options *options)
{
if (!obj)
- return report(options, obj, FSCK_MSG_BAD_OBJECT_SHA1, "no valid object to fsck");
+ return report(options, NULL, OBJ_NONE, FSCK_MSG_BAD_OBJECT_SHA1, "no valid object to fsck");
if (obj->type == OBJ_BLOB)
- return fsck_blob((struct blob *)obj, data, size, options);
+ return fsck_blob(&obj->oid, data, size, options);
if (obj->type == OBJ_TREE)
- return fsck_tree((struct tree *) obj, options);
+ return fsck_tree(&obj->oid, data, size, options);
if (obj->type == OBJ_COMMIT)
- return fsck_commit((struct commit *) obj, (const char *) data,
- size, options);
+ return fsck_commit(&obj->oid, data, size, options);
if (obj->type == OBJ_TAG)
- return fsck_tag((struct tag *) obj, (const char *) data,
- size, options);
+ return fsck_tag(&obj->oid, data, size, options);
- return report(options, obj, FSCK_MSG_UNKNOWN_TYPE, "unknown type '%d' (internal fsck error)",
- obj->type);
+ return report(options, &obj->oid, obj->type,
+ FSCK_MSG_UNKNOWN_TYPE,
+ "unknown type '%d' (internal fsck error)",
+ obj->type);
}
int fsck_error_function(struct fsck_options *o,
- struct object *obj, int msg_type, const char *message)
+ const struct object_id *oid,
+ enum object_type object_type,
+ int msg_type, const char *message)
{
if (msg_type == FSCK_WARN) {
- warning("object %s: %s", describe_object(o, obj), message);
+ warning("object %s: %s", fsck_describe_object(o, oid), message);
return 0;
}
- error("object %s: %s", describe_object(o, obj), message);
+ error("object %s: %s", fsck_describe_object(o, oid), message);
return 1;
}
@@ -1074,7 +1251,6 @@ int fsck_finish(struct fsck_options *options)
oidset_iter_init(&gitmodules_found, &iter);
while ((oid = oidset_iter_next(&iter))) {
- struct blob *blob;
enum object_type type;
unsigned long size;
char *buf;
@@ -1082,29 +1258,22 @@ int fsck_finish(struct fsck_options *options)
if (oidset_contains(&gitmodules_done, oid))
continue;
- blob = lookup_blob(the_repository, oid);
- if (!blob) {
- struct object *obj = lookup_unknown_object(oid->hash);
- ret |= report(options, obj,
- FSCK_MSG_GITMODULES_BLOB,
- "non-blob found at .gitmodules");
- continue;
- }
-
buf = read_object_file(oid, &type, &size);
if (!buf) {
- if (is_promisor_object(&blob->object.oid))
+ if (is_promisor_object(oid))
continue;
- ret |= report(options, &blob->object,
+ ret |= report(options,
+ oid, OBJ_BLOB,
FSCK_MSG_GITMODULES_MISSING,
"unable to read .gitmodules blob");
continue;
}
if (type == OBJ_BLOB)
- ret |= fsck_blob(blob, buf, size, options);
+ ret |= fsck_blob(oid, buf, size, options);
else
- ret |= report(options, &blob->object,
+ ret |= report(options,
+ oid, type,
FSCK_MSG_GITMODULES_BLOB,
"non-blob found at .gitmodules");
free(buf);