keys: Namespace keyring names

Keyring names are held in a single global list that any process can pick
from by means of keyctl_join_session_keyring (provided the keyring grants
Search permission).  This isn't very container friendly, however.

Make the following changes:

 (1) Make default session, process and thread keyring names begin with a
     '.' instead of '_'.

 (2) Keyrings whose names begin with a '.' aren't added to the list.  Such
     keyrings are system specials.

 (3) Replace the global list with per-user_namespace lists.  A keyring adds
     its name to the list for the user_namespace that it is currently in.

 (4) When a user_namespace is deleted, it just removes itself from the
     keyring name list.

The global keyring_name_lock is retained for accessing the name lists.
This allows (4) to work.

This can be tested by:

	# keyctl newring foo @s
	995906392
	# unshare -U
	$ keyctl show
	...
	 995906392 --alswrv  65534 65534   \_ keyring: foo
	...
	$ keyctl session foo
	Joined session keyring: 935622349

As can be seen, a new session keyring was created.

The capability bit KEYCTL_CAPS1_NS_KEYRING_NAME is set if the kernel is
employing this feature.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Eric W. Biederman <ebiederm@xmission.com>

include/linux/key.h

@@ -361,6 +361,7 @@ extern void key_set_timeout(struct key *, unsigned);
 
 extern key_ref_t lookup_user_key(key_serial_t id, unsigned long flags,
 				 key_perm_t perm);
+extern void key_free_user_ns(struct user_namespace *);
 
 /*
  * The permissions required on a key that we're looking up.
@@ -434,6 +435,7 @@ extern void key_init(void);
 #define key_fsuid_changed(c)		do { } while(0)
 #define key_fsgid_changed(c)		do { } while(0)
 #define key_init()			do { } while(0)
+#define key_free_user_ns(ns)		do { } while(0)
 
 #endif /* CONFIG_KEYS */
 #endif /* __KERNEL__ */

include/linux/user_namespace.h

@@ -64,6 +64,11 @@ struct user_namespace {
 	struct ns_common	ns;
 	unsigned long		flags;
 
+#ifdef CONFIG_KEYS
+	/* List of joinable keyrings in this namespace */
+	struct list_head	keyring_name_list;
+#endif
+
 	/* Register of per-UID persistent keyrings for this namespace */
 #ifdef CONFIG_PERSISTENT_KEYRINGS
 	struct key		*persistent_keyring_register;

include/uapi/linux/keyctl.h

@@ -128,5 +128,6 @@ struct keyctl_pkey_params {
 #define KEYCTL_CAPS0_INVALIDATE		0x20 /* KEYCTL_INVALIDATE supported */
 #define KEYCTL_CAPS0_RESTRICT_KEYRING	0x40 /* KEYCTL_RESTRICT_KEYRING supported */
 #define KEYCTL_CAPS0_MOVE		0x80 /* KEYCTL_MOVE supported */
+#define KEYCTL_CAPS1_NS_KEYRING_NAME	0x01 /* Keyring names are per-user_namespace */
 
 #endif /*  _LINUX_KEYCTL_H */

kernel/user.c

@@ -62,6 +62,9 @@ struct user_namespace init_user_ns = {
 	.ns.ops = &userns_operations,
 #endif
 	.flags = USERNS_INIT_FLAGS,
+#ifdef CONFIG_KEYS
+	.keyring_name_list = LIST_HEAD_INIT(init_user_ns.keyring_name_list),
+#endif
 #ifdef CONFIG_PERSISTENT_KEYRINGS
 	.persistent_keyring_register_sem =
 	__RWSEM_INITIALIZER(init_user_ns.persistent_keyring_register_sem),

kernel/user_namespace.c

@@ -133,6 +133,9 @@ int create_user_ns(struct cred *new)
 	ns->flags = parent_ns->flags;
 	mutex_unlock(&userns_state_mutex);
 
+#ifdef CONFIG_KEYS
+	INIT_LIST_HEAD(&ns->keyring_name_list);
+#endif
 #ifdef CONFIG_PERSISTENT_KEYRINGS
 	init_rwsem(&ns->persistent_keyring_register_sem);
 #endif
@@ -196,9 +199,7 @@ static void free_user_ns(struct work_struct *work)
 			kfree(ns->projid_map.reverse);
 		}
 		retire_userns_sysctls(ns);
-#ifdef CONFIG_PERSISTENT_KEYRINGS
-		key_put(ns->persistent_keyring_register);
-#endif
+		key_free_user_ns(ns);
 		ns_free_inum(&ns->ns);
 		kmem_cache_free(user_ns_cachep, ns);
 		dec_user_namespaces(ucounts);

security/keys/keyctl.c

@@ -30,7 +30,7 @@
 
 #define KEY_MAX_DESC_SIZE 4096
 
-static const unsigned char keyrings_capabilities[1] = {
+static const unsigned char keyrings_capabilities[2] = {
 	[0] = (KEYCTL_CAPS0_CAPABILITIES |
 	       (IS_ENABLED(CONFIG_PERSISTENT_KEYRINGS)	? KEYCTL_CAPS0_PERSISTENT_KEYRINGS : 0) |
 	       (IS_ENABLED(CONFIG_KEY_DH_OPERATIONS)	? KEYCTL_CAPS0_DIFFIE_HELLMAN : 0) |
@@ -40,6 +40,7 @@ static const unsigned char keyrings_capabilities[1] = {
 	       KEYCTL_CAPS0_RESTRICT_KEYRING |
 	       KEYCTL_CAPS0_MOVE
 	       ),
+	[1] = (KEYCTL_CAPS1_NS_KEYRING_NAME),
 };
 
 static int key_get_type_from_user(char *type,

security/keys/keyring.c

@@ -16,6 +16,7 @@
 #include <linux/security.h>
 #include <linux/seq_file.h>
 #include <linux/err.h>
+#include <linux/user_namespace.h>
 #include <keys/keyring-type.h>
 #include <keys/user-type.h>
 #include <linux/assoc_array_priv.h>
@@ -28,11 +29,6 @@
  */
 #define KEYRING_SEARCH_MAX_DEPTH 6
 
-/*
- * We keep all named keyrings in a hash to speed looking them up.
- */
-#define KEYRING_NAME_HASH_SIZE	(1 << 5)
-
 /*
  * We mark pointers we pass to the associative array with bit 1 set if
  * they're keyrings and clear otherwise.
@@ -55,17 +51,20 @@ static inline void *keyring_key_to_ptr(struct key *key)
 	return key;
 }
 
-static struct list_head	keyring_name_hash[KEYRING_NAME_HASH_SIZE];
 static DEFINE_RWLOCK(keyring_name_lock);
 
-static inline unsigned keyring_hash(const char *desc)
+/*
+ * Clean up the bits of user_namespace that belong to us.
+ */
+void key_free_user_ns(struct user_namespace *ns)
 {
-	unsigned bucket = 0;
+	write_lock(&keyring_name_lock);
+	list_del_init(&ns->keyring_name_list);
+	write_unlock(&keyring_name_lock);
 
-	for (; *desc; desc++)
-		bucket += (unsigned char)*desc;
-
-	return bucket & (KEYRING_NAME_HASH_SIZE - 1);
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+	key_put(ns->persistent_keyring_register);
+#endif
 }
 
 /*
@@ -104,23 +103,17 @@ static DEFINE_MUTEX(keyring_serialise_link_lock);
 
 /*
  * Publish the name of a keyring so that it can be found by name (if it has
- * one).
+ * one and it doesn't begin with a dot).
  */
 static void keyring_publish_name(struct key *keyring)
 {
-	int bucket;
-
-	if (keyring->description) {
-		bucket = keyring_hash(keyring->description);
+	struct user_namespace *ns = current_user_ns();
 
+	if (keyring->description &&
+	    keyring->description[0] &&
+	    keyring->description[0] != '.') {
 		write_lock(&keyring_name_lock);
-
-		if (!keyring_name_hash[bucket].next)
-			INIT_LIST_HEAD(&keyring_name_hash[bucket]);
-
-		list_add_tail(&keyring->name_link,
-			      &keyring_name_hash[bucket]);
-
+		list_add_tail(&keyring->name_link, &ns->keyring_name_list);
 		write_unlock(&keyring_name_lock);
 	}
 }
@@ -1097,24 +1090,19 @@ found:
  */
 struct key *find_keyring_by_name(const char *name, bool uid_keyring)
 {
+	struct user_namespace *ns = current_user_ns();
 	struct key *keyring;
-	int bucket;
 
 	if (!name)
 		return ERR_PTR(-EINVAL);
 
-	bucket = keyring_hash(name);
-
 	read_lock(&keyring_name_lock);
 
-	if (keyring_name_hash[bucket].next) {
-		/* search this hash bucket for a keyring with a matching name
-		 * that's readable and that hasn't been revoked */
-		list_for_each_entry(keyring,
-				    &keyring_name_hash[bucket],
-				    name_link
-				    ) {
-			if (!kuid_has_mapping(current_user_ns(), keyring->user->uid))
+	/* Search this hash bucket for a keyring with a matching name that
+	 * grants Search permission and that hasn't been revoked
+	 */
+	list_for_each_entry(keyring, &ns->keyring_name_list, name_link) {
+		if (!kuid_has_mapping(ns, keyring->user->uid))
 			continue;
 
 		if (test_bit(KEY_FLAG_REVOKED, &keyring->flags))
@@ -1141,7 +1129,6 @@ struct key *find_keyring_by_name(const char *name, bool uid_keyring)
 		keyring->last_used_at = ktime_get_real_seconds();
 		goto out;
 	}
-	}
 
 	keyring = ERR_PTR(-ENOKEY);
 out: