Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull user namespace enhancements from Eric Biederman:
 "This is a course correction for the user namespace, so that we can
  reach an inexpensive, maintainable, and reasonably complete
  implementation.

  Highlights:
   - Config guards make it impossible to enable the user namespace and
     code that has not been converted to be user namespace safe.

   - Use of the new kuid_t type ensures the if you somehow get past the
     config guards the kernel will encounter type errors if you enable
     user namespaces and attempt to compile in code whose permission
     checks have not been updated to be user namespace safe.

   - All uids from child user namespaces are mapped into the initial
     user namespace before they are processed.  Removing the need to add
     an additional check to see if the user namespace of the compared
     uids remains the same.

   - With the user namespaces compiled out the performance is as good or
     better than it is today.

   - For most operations absolutely nothing changes performance or
     operationally with the user namespace enabled.

   - The worst case performance I could come up with was timing 1
     billion cache cold stat operations with the user namespace code
     enabled.  This went from 156s to 164s on my laptop (or 156ns to
     164ns per stat operation).

   - (uid_t)-1 and (gid_t)-1 are reserved as an internal error value.
     Most uid/gid setting system calls treat these value specially
     anyway so attempting to use -1 as a uid would likely cause
     entertaining failures in userspace.

   - If setuid is called with a uid that can not be mapped setuid fails.
     I have looked at sendmail, login, ssh and every other program I
     could think of that would call setuid and they all check for and
     handle the case where setuid fails.

   - If stat or a similar system call is called from a context in which
     we can not map a uid we lie and return overflowuid.  The LFS
     experience suggests not lying and returning an error code might be
     better, but the historical precedent with uids is different and I
     can not think of anything that would break by lying about a uid we
     can't map.

   - Capabilities are localized to the current user namespace making it
     safe to give the initial user in a user namespace all capabilities.

  My git tree covers all of the modifications needed to convert the core
  kernel and enough changes to make a system bootable to runlevel 1."

Fix up trivial conflicts due to nearby independent changes in fs/stat.c

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (46 commits)
  userns:  Silence silly gcc warning.
  cred: use correct cred accessor with regards to rcu read lock
  userns: Convert the move_pages, and migrate_pages permission checks to use uid_eq
  userns: Convert cgroup permission checks to use uid_eq
  userns: Convert tmpfs to use kuid and kgid where appropriate
  userns: Convert sysfs to use kgid/kuid where appropriate
  userns: Convert sysctl permission checks to use kuid and kgids.
  userns: Convert proc to use kuid/kgid where appropriate
  userns: Convert ext4 to user kuid/kgid where appropriate
  userns: Convert ext3 to use kuid/kgid where appropriate
  userns: Convert ext2 to use kuid/kgid where appropriate.
  userns: Convert devpts to use kuid/kgid where appropriate
  userns: Convert binary formats to use kuid/kgid where appropriate
  userns: Add negative depends on entries to avoid building code that is userns unsafe
  userns: signal remove unnecessary map_cred_ns
  userns: Teach inode_capable to understand inodes whose uids map to other namespaces.
  userns: Fail exec for suid and sgid binaries with ids outside our user namespace.
  userns: Convert stat to return values mapped from kuids and kgids
  userns: Convert user specfied uids and gids in chown into kuids and kgid
  userns: Use uid_eq gid_eq helpers when comparing kuids and kgids in the vfs
  ...

1 files changed, 33 insertions, 18 deletions

diff --git a/kernel/user.c b/kernel/user.c
index 71dd2363ab0f..b815fefbe76f 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -22,10 +22,27 @@
  * and 1 for... ?
  */
 struct user_namespace init_user_ns = {
+	.uid_map = {
+		.nr_extents = 1,
+		.extent[0] = {
+			.first = 0,
+			.lower_first = 0,
+			.count = 4294967295U,
+		},
+	},
+	.gid_map = {
+		.nr_extents = 1,
+		.extent[0] = {
+			.first = 0,
+			.lower_first = 0,
+			.count = 4294967295U,
+		},
+	},
 	.kref = {
 		.refcount	= ATOMIC_INIT(3),
 	},
-	.creator = &root_user,
+	.owner = GLOBAL_ROOT_UID,
+	.group = GLOBAL_ROOT_GID,
 };
 EXPORT_SYMBOL_GPL(init_user_ns);
 
@@ -34,11 +51,14 @@ EXPORT_SYMBOL_GPL(init_user_ns);
  * when changing user ID's (ie setuid() and friends).
  */
 
+#define UIDHASH_BITS	(CONFIG_BASE_SMALL ? 3 : 7)
+#define UIDHASH_SZ	(1 << UIDHASH_BITS)
 #define UIDHASH_MASK		(UIDHASH_SZ - 1)
 #define __uidhashfn(uid)	(((uid >> UIDHASH_BITS) + uid) & UIDHASH_MASK)
-#define uidhashentry(ns, uid)	((ns)->uidhash_table + __uidhashfn((uid)))
+#define uidhashentry(uid)	(uidhash_table + __uidhashfn((__kuid_val(uid))))
 
 static struct kmem_cache *uid_cachep;
+struct hlist_head uidhash_table[UIDHASH_SZ];
 
 /*
  * The uidhash_lock is mostly taken from process context, but it is
@@ -51,14 +71,14 @@ static struct kmem_cache *uid_cachep;
  */
 static DEFINE_SPINLOCK(uidhash_lock);
 
-/* root_user.__count is 2, 1 for init task cred, 1 for init_user_ns->user_ns */
+/* root_user.__count is 1, for init task cred */
 struct user_struct root_user = {
-	.__count	= ATOMIC_INIT(2),
+	.__count	= ATOMIC_INIT(1),
 	.processes	= ATOMIC_INIT(1),
 	.files		= ATOMIC_INIT(0),
 	.sigpending	= ATOMIC_INIT(0),
 	.locked_shm     = 0,
-	.user_ns	= &init_user_ns,
+	.uid		= GLOBAL_ROOT_UID,
 };
 
 /*
@@ -72,16 +92,15 @@ static void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent)
 static void uid_hash_remove(struct user_struct *up)
 {
 	hlist_del_init(&up->uidhash_node);
-	put_user_ns(up->user_ns);
 }
 
-static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent)
+static struct user_struct *uid_hash_find(kuid_t uid, struct hlist_head *hashent)
 {
 	struct user_struct *user;
 	struct hlist_node *h;
 
 	hlist_for_each_entry(user, h, hashent, uidhash_node) {
-		if (user->uid == uid) {
+		if (uid_eq(user->uid, uid)) {
 			atomic_inc(&user->__count);
 			return user;
 		}
@@ -110,14 +129,13 @@ static void free_user(struct user_struct *up, unsigned long flags)
  *
  * If the user_struct could not be found, return NULL.
  */
-struct user_struct *find_user(uid_t uid)
+struct user_struct *find_user(kuid_t uid)
 {
 	struct user_struct *ret;
 	unsigned long flags;
-	struct user_namespace *ns = current_user_ns();
 
 	spin_lock_irqsave(&uidhash_lock, flags);
-	ret = uid_hash_find(uid, uidhashentry(ns, uid));
+	ret = uid_hash_find(uid, uidhashentry(uid));
 	spin_unlock_irqrestore(&uidhash_lock, flags);
 	return ret;
 }
@@ -136,9 +154,9 @@ void free_uid(struct user_struct *up)
 		local_irq_restore(flags);
 }
 
-struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
+struct user_struct *alloc_uid(kuid_t uid)
 {
-	struct hlist_head *hashent = uidhashentry(ns, uid);
+	struct hlist_head *hashent = uidhashentry(uid);
 	struct user_struct *up, *new;
 
 	spin_lock_irq(&uidhash_lock);
@@ -153,8 +171,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
 		new->uid = uid;
 		atomic_set(&new->__count, 1);
 
-		new->user_ns = get_user_ns(ns);
-
 		/*
 		 * Before adding this, check whether we raced
 		 * on adding the same user already..
@@ -162,7 +178,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
 		spin_lock_irq(&uidhash_lock);
 		up = uid_hash_find(uid, hashent);
 		if (up) {
-			put_user_ns(ns);
 			key_put(new->uid_keyring);
 			key_put(new->session_keyring);
 			kmem_cache_free(uid_cachep, new);
@@ -187,11 +202,11 @@ static int __init uid_cache_init(void)
 			0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
 
 	for(n = 0; n < UIDHASH_SZ; ++n)
-		INIT_HLIST_HEAD(init_user_ns.uidhash_table + n);
+		INIT_HLIST_HEAD(uidhash_table + n);
 
 	/* Insert the root user immediately (init already runs as root) */
 	spin_lock_irq(&uidhash_lock);
-	uid_hash_insert(&root_user, uidhashentry(&init_user_ns, 0));
+	uid_hash_insert(&root_user, uidhashentry(GLOBAL_ROOT_UID));
 	spin_unlock_irq(&uidhash_lock);
 
 	return 0;