1 files changed, 116 insertions, 85 deletions

diff --git a/kernel/user.c b/kernel/user.c
index 89e562feb1b..4efa39350e4 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -13,58 +13,104 @@
 #include <linux/slab.h>
 #include <linux/bitops.h>
 #include <linux/key.h>
+#include <linux/interrupt.h>
+#include <linux/export.h>
+#include <linux/user_namespace.h>
+#include <linux/proc_ns.h>
+
+/*
+ * userns count is 1 for root user, 1 for init_uts_ns,
+ * 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,
+		},
+	},
+	.projid_map = {
+		.nr_extents = 1,
+		.extent[0] = {
+			.first = 0,
+			.lower_first = 0,
+			.count = 4294967295U,
+		},
+	},
+	.count = ATOMIC_INIT(3),
+	.owner = GLOBAL_ROOT_UID,
+	.group = GLOBAL_ROOT_GID,
+	.proc_inum = PROC_USER_INIT_INO,
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+	.persistent_keyring_register_sem =
+	__RWSEM_INITIALIZER(init_user_ns.persistent_keyring_register_sem),
+#endif
+};
+EXPORT_SYMBOL_GPL(init_user_ns);
 
 /*
  * UID task count cache, to get fast user lookup in "alloc_uid"
  * when changing user ID's (ie setuid() and friends).
  */
 
-#define UIDHASH_BITS (CONFIG_BASE_SMALL ? 3 : 8)
-#define UIDHASH_SZ		(1 << UIDHASH_BITS)
+#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(uid)	(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];
 
-static kmem_cache_t *uid_cachep;
-static struct list_head uidhash_table[UIDHASH_SZ];
+/*
+ * The uidhash_lock is mostly taken from process context, but it is
+ * occasionally also taken from softirq/tasklet context, when
+ * task-structs get RCU-freed. Hence all locking must be softirq-safe.
+ * But free_uid() is also called with local interrupts disabled, and running
+ * local_bh_enable() with local interrupts disabled is an error - we'll run
+ * softirq callbacks, and they can unconditionally enable interrupts, and
+ * the caller of free_uid() didn't expect that..
+ */
 static DEFINE_SPINLOCK(uidhash_lock);
 
+/* root_user.__count is 1, for init task cred */
 struct user_struct root_user = {
 	.__count	= ATOMIC_INIT(1),
 	.processes	= ATOMIC_INIT(1),
-	.files		= ATOMIC_INIT(0),
 	.sigpending	= ATOMIC_INIT(0),
-	.mq_bytes	= 0,
 	.locked_shm     = 0,
-#ifdef CONFIG_KEYS
-	.uid_keyring	= &root_user_keyring,
-	.session_keyring = &root_session_keyring,
-#endif
+	.uid		= GLOBAL_ROOT_UID,
 };
 
 /*
  * These routines must be called with the uidhash spinlock held!
  */
-static inline void uid_hash_insert(struct user_struct *up, struct list_head *hashent)
+static void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent)
 {
-	list_add(&up->uidhash_list, hashent);
+	hlist_add_head(&up->uidhash_node, hashent);
 }
 
-static inline void uid_hash_remove(struct user_struct *up)
+static void uid_hash_remove(struct user_struct *up)
 {
-	list_del(&up->uidhash_list);
+	hlist_del_init(&up->uidhash_node);
 }
 
-static inline struct user_struct *uid_hash_find(uid_t uid, struct list_head *hashent)
+static struct user_struct *uid_hash_find(kuid_t uid, struct hlist_head *hashent)
 {
-	struct list_head *up;
-
-	list_for_each(up, hashent) {
-		struct user_struct *user;
+	struct user_struct *user;
 
-		user = list_entry(up, struct user_struct, uidhash_list);
-
-		if(user->uid == uid) {
+	hlist_for_each_entry(user, hashent, uidhash_node) {
+		if (uid_eq(user->uid, uid)) {
 			atomic_inc(&user->__count);
 			return user;
 		}
@@ -73,71 +119,73 @@ static inline struct user_struct *uid_hash_find(uid_t uid, struct list_head *has
 	return NULL;
 }
 
+/* IRQs are disabled and uidhash_lock is held upon function entry.
+ * IRQ state (as stored in flags) is restored and uidhash_lock released
+ * upon function exit.
+ */
+static void free_user(struct user_struct *up, unsigned long flags)
+	__releases(&uidhash_lock)
+{
+	uid_hash_remove(up);
+	spin_unlock_irqrestore(&uidhash_lock, flags);
+	key_put(up->uid_keyring);
+	key_put(up->session_keyring);
+	kmem_cache_free(uid_cachep, up);
+}
+
 /*
  * Locate the user_struct for the passed UID.  If found, take a ref on it.  The
  * caller must undo that ref with free_uid().
  *
  * 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;
 
-	spin_lock(&uidhash_lock);
+	spin_lock_irqsave(&uidhash_lock, flags);
 	ret = uid_hash_find(uid, uidhashentry(uid));
-	spin_unlock(&uidhash_lock);
+	spin_unlock_irqrestore(&uidhash_lock, flags);
 	return ret;
 }
 
 void free_uid(struct user_struct *up)
 {
-	if (up && atomic_dec_and_lock(&up->__count, &uidhash_lock)) {
-		uid_hash_remove(up);
-		key_put(up->uid_keyring);
-		key_put(up->session_keyring);
-		kmem_cache_free(uid_cachep, up);
-		spin_unlock(&uidhash_lock);
-	}
+	unsigned long flags;
+
+	if (!up)
+		return;
+
+	local_irq_save(flags);
+	if (atomic_dec_and_lock(&up->__count, &uidhash_lock))
+		free_user(up, flags);
+	else
+		local_irq_restore(flags);
 }
 
-struct user_struct * alloc_uid(uid_t uid)
+struct user_struct *alloc_uid(kuid_t uid)
 {
-	struct list_head *hashent = uidhashentry(uid);
-	struct user_struct *up;
+	struct hlist_head *hashent = uidhashentry(uid);
+	struct user_struct *up, *new;
 
-	spin_lock(&uidhash_lock);
+	spin_lock_irq(&uidhash_lock);
 	up = uid_hash_find(uid, hashent);
-	spin_unlock(&uidhash_lock);
+	spin_unlock_irq(&uidhash_lock);
 
 	if (!up) {
-		struct user_struct *new;
-
-		new = kmem_cache_alloc(uid_cachep, SLAB_KERNEL);
+		new = kmem_cache_zalloc(uid_cachep, GFP_KERNEL);
 		if (!new)
-			return NULL;
+			goto out_unlock;
+
 		new->uid = uid;
 		atomic_set(&new->__count, 1);
-		atomic_set(&new->processes, 0);
-		atomic_set(&new->files, 0);
-		atomic_set(&new->sigpending, 0);
-#ifdef CONFIG_INOTIFY
-		atomic_set(&new->inotify_watches, 0);
-		atomic_set(&new->inotify_devs, 0);
-#endif
-
-		new->mq_bytes = 0;
-		new->locked_shm = 0;
-
-		if (alloc_uid_keyring(new) < 0) {
-			kmem_cache_free(uid_cachep, new);
-			return NULL;
-		}
 
 		/*
 		 * Before adding this, check whether we raced
 		 * on adding the same user already..
 		 */
-		spin_lock(&uidhash_lock);
+		spin_lock_irq(&uidhash_lock);
 		up = uid_hash_find(uid, hashent);
 		if (up) {
 			key_put(new->uid_keyring);
@@ -147,47 +195,30 @@ struct user_struct * alloc_uid(uid_t uid)
 			uid_hash_insert(new, hashent);
 			up = new;
 		}
-		spin_unlock(&uidhash_lock);
-
+		spin_unlock_irq(&uidhash_lock);
 	}
+
 	return up;
-}
 
-void switch_uid(struct user_struct *new_user)
-{
-	struct user_struct *old_user;
-
-	/* What if a process setreuid()'s and this brings the
-	 * new uid over his NPROC rlimit?  We can check this now
-	 * cheaply with the new uid cache, so if it matters
-	 * we should be checking for it.  -DaveM
-	 */
-	old_user = current->user;
-	atomic_inc(&new_user->processes);
-	atomic_dec(&old_user->processes);
-	switch_uid_keyring(new_user);
-	current->user = new_user;
-	free_uid(old_user);
-	suid_keys(current);
+out_unlock:
+	return NULL;
 }
 
-
 static int __init uid_cache_init(void)
 {
 	int n;
 
 	uid_cachep = kmem_cache_create("uid_cache", sizeof(struct user_struct),
-			0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
+			0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
 
 	for(n = 0; n < UIDHASH_SZ; ++n)
-		INIT_LIST_HEAD(uidhash_table + n);
+		INIT_HLIST_HEAD(uidhash_table + n);
 
 	/* Insert the root user immediately (init already runs as root) */
-	spin_lock(&uidhash_lock);
-	uid_hash_insert(&root_user, uidhashentry(0));
-	spin_unlock(&uidhash_lock);
+	spin_lock_irq(&uidhash_lock);
+	uid_hash_insert(&root_user, uidhashentry(GLOBAL_ROOT_UID));
+	spin_unlock_irq(&uidhash_lock);
 
 	return 0;
 }
-
-module_init(uid_cache_init);
+subsys_initcall(uid_cache_init);