refs.c: allow listing and deleting badly named refs

We currently do not handle badly named refs well:

  $ cp .git/refs/heads/master .git/refs/heads/master.....@\*@\\.
  $ git branch
    fatal: Reference has invalid format: 'refs/heads/master.....@*@\.'
  $ git branch -D master.....@\*@\\.
    error: branch 'master.....@*@\.' not found.

Users cannot recover from a badly named ref without manually finding
and deleting the loose ref file or appropriate line in packed-refs.
Making that easier will make it easier to tweak the ref naming rules
in the future, for example to forbid shell metacharacters like '`'
and '"', without putting people in a state that is hard to get out of.

So allow "branch --list" to show these refs and allow "branch -d/-D"
and "update-ref -d" to delete them.  Other commands (for example to
rename refs) will continue to not handle these refs but can be changed
in later patches.

Details:

In resolving functions, refuse to resolve refs that don't pass the
git-check-ref-format(1) check unless the new RESOLVE_REF_ALLOW_BAD_NAME
flag is passed.  Even with RESOLVE_REF_ALLOW_BAD_NAME, refuse to
resolve refs that escape the refs/ directory and do not match the
pattern [A-Z_]* (think "HEAD" and "MERGE_HEAD").

In locking functions, refuse to act on badly named refs unless they
are being deleted and either are in the refs/ directory or match [A-Z_]*.

Just like other invalid refs, flag resolved, badly named refs with the
REF_ISBROKEN flag, treat them as resolving to null_sha1, and skip them
in all iteration functions except for for_each_rawref.

Flag badly named refs (but not symrefs pointing to badly named refs)
with a REF_BAD_NAME flag to make it easier for future callers to
notice and handle them specially.  For example, in a later patch
for-each-ref will use this flag to detect refs whose names can confuse
callers parsing for-each-ref output.

In the transaction API, refuse to create or update badly named refs,
but allow deleting them (unless they try to escape refs/ and don't match
[A-Z_]*).

Signed-off-by: Ronnie Sahlberg <sahlberg@google.com>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 119 insertions, 29 deletions

diff --git a/refs.c b/refs.c
index fe1352a..e7000f2 100644
--- a/refs.c
+++ b/refs.c
@@ -187,8 +187,8 @@ struct ref_dir {
 
 /*
  * Bit values for ref_entry::flag.  REF_ISSYMREF=0x01,
- * REF_ISPACKED=0x02, and REF_ISBROKEN=0x04 are public values; see
- * refs.h.
+ * REF_ISPACKED=0x02, REF_ISBROKEN=0x04 and REF_BAD_NAME=0x08 are
+ * public values; see refs.h.
  */
 
 /*
@@ -196,16 +196,16 @@ struct ref_dir {
  * the correct peeled value for the reference, which might be
  * null_sha1 if the reference is not a tag or if it is broken.
  */
-#define REF_KNOWS_PEELED 0x08
+#define REF_KNOWS_PEELED 0x10
 
 /* ref_entry represents a directory of references */
-#define REF_DIR 0x10
+#define REF_DIR 0x20
 
 /*
  * Entry has not yet been read from disk (used only for REF_DIR
  * entries representing loose references)
  */
-#define REF_INCOMPLETE 0x20
+#define REF_INCOMPLETE 0x40
 
 /*
  * A ref_entry represents either a reference or a "subdirectory" of
@@ -274,6 +274,39 @@ static struct ref_dir *get_ref_dir(struct ref_entry *entry)
 	return dir;
 }
 
+/*
+ * Check if a refname is safe.
+ * For refs that start with "refs/" we consider it safe as long they do
+ * not try to resolve to outside of refs/.
+ *
+ * For all other refs we only consider them safe iff they only contain
+ * upper case characters and '_' (like "HEAD" AND "MERGE_HEAD", and not like
+ * "config").
+ */
+static int refname_is_safe(const char *refname)
+{
+	if (starts_with(refname, "refs/")) {
+		char *buf;
+		int result;
+
+		buf = xmalloc(strlen(refname) + 1);
+		/*
+		 * Does the refname try to escape refs/?
+		 * For example: refs/foo/../bar is safe but refs/foo/../../bar
+		 * is not.
+		 */
+		result = !normalize_path_copy(buf, refname + strlen("refs/"));
+		free(buf);
+		return result;
+	}
+	while (*refname) {
+		if (!isupper(*refname) && *refname != '_')
+			return 0;
+		refname++;
+	}
+	return 1;
+}
+
 static struct ref_entry *create_ref_entry(const char *refname,
 					  const unsigned char *sha1, int flag,
 					  int check_name)
@@ -284,6 +317,8 @@ static struct ref_entry *create_ref_entry(const char *refname,
 	if (check_name &&
 	    check_refname_format(refname, REFNAME_ALLOW_ONELEVEL))
 		die("Reference has invalid format: '%s'", refname);
+	if (!check_name && !refname_is_safe(refname))
+		die("Reference has invalid name: '%s'", refname);
 	len = strlen(refname) + 1;
 	ref = xmalloc(sizeof(struct ref_entry) + len);
 	hashcpy(ref->u.value.sha1, sha1);
@@ -1111,7 +1146,13 @@ static void read_packed_refs(FILE *f, struct ref_dir *dir)
 
 		refname = parse_ref_line(refline, sha1);
 		if (refname) {
-			last = create_ref_entry(refname, sha1, REF_ISPACKED, 1);
+			int flag = REF_ISPACKED;
+
+			if (check_refname_format(refname, REFNAME_ALLOW_ONELEVEL)) {
+				hashclr(sha1);
+				flag |= REF_BAD_NAME | REF_ISBROKEN;
+			}
+			last = create_ref_entry(refname, sha1, flag, 0);
 			if (peeled == PEELED_FULLY ||
 			    (peeled == PEELED_TAGS && starts_with(refname, "refs/tags/")))
 				last->flag |= REF_KNOWS_PEELED;
@@ -1249,8 +1290,13 @@ static void read_loose_refs(const char *dirname, struct ref_dir *dir)
 				hashclr(sha1);
 				flag |= REF_ISBROKEN;
 			}
+			if (check_refname_format(refname.buf,
+						 REFNAME_ALLOW_ONELEVEL)) {
+				hashclr(sha1);
+				flag |= REF_BAD_NAME | REF_ISBROKEN;
+			}
 			add_entry_to_dir(dir,
-					 create_ref_entry(refname.buf, sha1, flag, 1));
+					 create_ref_entry(refname.buf, sha1, flag, 0));
 		}
 		strbuf_setlen(&refname, dirnamelen);
 	}
@@ -1369,10 +1415,10 @@ static struct ref_entry *get_packed_ref(const char *refname)
  * A loose ref file doesn't exist; check for a packed ref.  The
  * options are forwarded from resolve_safe_unsafe().
  */
-static const char *handle_missing_loose_ref(const char *refname,
-					    int resolve_flags,
-					    unsigned char *sha1,
-					    int *flags)
+static int resolve_missing_loose_ref(const char *refname,
+				     int resolve_flags,
+				     unsigned char *sha1,
+				     int *flags)
 {
 	struct ref_entry *entry;
 
@@ -1385,14 +1431,15 @@ static const char *handle_missing_loose_ref(const char *refname,
 		hashcpy(sha1, entry->u.value.sha1);
 		if (flags)
 			*flags |= REF_ISPACKED;
-		return refname;
+		return 0;
 	}
 	/* The reference is not a packed reference, either. */
 	if (resolve_flags & RESOLVE_REF_READING) {
-		return NULL;
+		errno = ENOENT;
+		return -1;
 	} else {
 		hashclr(sha1);
-		return refname;
+		return 0;
 	}
 }
 
@@ -1403,13 +1450,29 @@ const char *resolve_ref_unsafe(const char *refname, int resolve_flags, unsigned
 	ssize_t len;
 	char buffer[256];
 	static char refname_buffer[256];
+	int bad_name = 0;
 
 	if (flags)
 		*flags = 0;
 
 	if (check_refname_format(refname, REFNAME_ALLOW_ONELEVEL)) {
-		errno = EINVAL;
-		return NULL;
+		if (flags)
+			*flags |= REF_BAD_NAME;
+
+		if (!(resolve_flags & RESOLVE_REF_ALLOW_BAD_NAME) ||
+		    !refname_is_safe(refname)) {
+			errno = EINVAL;
+			return NULL;
+		}
+		/*
+		 * dwim_ref() uses REF_ISBROKEN to distinguish between
+		 * missing refs and refs that were present but invalid,
+		 * to complain about the latter to stderr.
+		 *
+		 * We don't know whether the ref exists, so don't set
+		 * REF_ISBROKEN yet.
+		 */
+		bad_name = 1;
 	}
 	for (;;) {
 		char path[PATH_MAX];
@@ -1435,11 +1498,17 @@ const char *resolve_ref_unsafe(const char *refname, int resolve_flags, unsigned
 		 */
 	stat_ref:
 		if (lstat(path, &st) < 0) {
-			if (errno == ENOENT)
-				return handle_missing_loose_ref(refname,
-						resolve_flags, sha1, flags);
-			else
+			if (errno != ENOENT)
+				return NULL;
+			if (resolve_missing_loose_ref(refname, resolve_flags,
+						      sha1, flags))
 				return NULL;
+			if (bad_name) {
+				hashclr(sha1);
+				if (flags)
+					*flags |= REF_ISBROKEN;
+			}
+			return refname;
 		}
 
 		/* Follow "normalized" - ie "refs/.." symlinks by hand */
@@ -1512,6 +1581,11 @@ const char *resolve_ref_unsafe(const char *refname, int resolve_flags, unsigned
 				errno = EINVAL;
 				return NULL;
 			}
+			if (bad_name) {
+				hashclr(sha1);
+				if (flags)
+					*flags |= REF_ISBROKEN;
+			}
 			return refname;
 		}
 		if (flags)
@@ -1527,8 +1601,13 @@ const char *resolve_ref_unsafe(const char *refname, int resolve_flags, unsigned
 		if (check_refname_format(buf, REFNAME_ALLOW_ONELEVEL)) {
 			if (flags)
 				*flags |= REF_ISBROKEN;
-			errno = EINVAL;
-			return NULL;
+
+			if (!(resolve_flags & RESOLVE_REF_ALLOW_BAD_NAME) ||
+			    !refname_is_safe(buf)) {
+				errno = EINVAL;
+				return NULL;
+			}
+			bad_name = 1;
 		}
 	}
 }
@@ -2160,18 +2239,16 @@ static struct ref_lock *lock_ref_sha1_basic(const char *refname,
 	int missing = 0;
 	int attempts_remaining = 3;
 
-	if (check_refname_format(refname, REFNAME_ALLOW_ONELEVEL)) {
-		errno = EINVAL;
-		return NULL;
-	}
-
 	lock = xcalloc(1, sizeof(struct ref_lock));
 	lock->lock_fd = -1;
 
 	if (mustexist)
 		resolve_flags |= RESOLVE_REF_READING;
-	if (flags & REF_NODEREF && flags & REF_DELETING)
-		resolve_flags |= RESOLVE_REF_NO_RECURSE;
+	if (flags & REF_DELETING) {
+		resolve_flags |= RESOLVE_REF_ALLOW_BAD_NAME;
+		if (flags & REF_NODEREF)
+			resolve_flags |= RESOLVE_REF_NO_RECURSE;
+	}
 
 	refname = resolve_ref_unsafe(refname, resolve_flags,
 				     lock->old_sha1, &type);
@@ -3519,6 +3596,13 @@ int ref_transaction_update(struct ref_transaction *transaction,
 	if (have_old && !old_sha1)
 		die("BUG: have_old is true but old_sha1 is NULL");
 
+	if (!is_null_sha1(new_sha1) &&
+	    check_refname_format(refname, REFNAME_ALLOW_ONELEVEL)) {
+		strbuf_addf(err, "refusing to update ref with bad name %s",
+			    refname);
+		return -1;
+	}
+
 	update = add_update(transaction, refname);
 	hashcpy(update->new_sha1, new_sha1);
 	update->flags = flags;
@@ -3544,6 +3628,12 @@ int ref_transaction_create(struct ref_transaction *transaction,
 	if (!new_sha1 || is_null_sha1(new_sha1))
 		die("BUG: create ref with null new_sha1");
 
+	if (check_refname_format(refname, REFNAME_ALLOW_ONELEVEL)) {
+		strbuf_addf(err, "refusing to create ref with bad name %s",
+			    refname);
+		return -1;
+	}
+
 	update = add_update(transaction, refname);
 
 	hashcpy(update->new_sha1, new_sha1);