Fix user namespace exiting OOPs

It turned out, that the user namespace is released during the do_exit() in
exit_task_namespaces(), but the struct user_struct is released only during the
put_task_struct(), i.e.  MUCH later.

On debug kernels with poisoned slabs this will cause the oops in
uid_hash_remove() because the head of the chain, which resides inside the
struct user_namespace, will be already freed and poisoned.

Since the uid hash itself is required only when someone can search it, i.e.
when the namespace is alive, we can safely unhash all the user_struct-s from
it during the namespace exiting.  The subsequent free_uid() will complete the
user_struct destruction.

For example simple program

   #include <sched.h>

   char stack[2 * 1024 * 1024];

   int f(void *foo)
   {
   	return 0;
   }

   int main(void)
   {
   	clone(f, stack + 1 * 1024 * 1024, 0x10000000, 0);
   	return 0;
   }

run on kernel with CONFIG_USER_NS turned on will oops the
kernel immediately.

This was spotted during OpenVZ kernel testing.

Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: Alexey Dobriyan <adobriyan@openvz.org>
Acked-by: "Serge E. Hallyn" <serue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6239bc2c2baa61d4ffef54cbd77fa1f294634534..5445eaec6908625968004c361da46dd3062250df 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1472,6 +1472,7 @@ static inline struct user_struct *get_uid(struct user_struct *u)
 }
 extern void free_uid(struct user_struct *);
 extern void switch_uid(struct user_struct *);
 }
 extern void free_uid(struct user_struct *);
 extern void switch_uid(struct user_struct *);

+extern void release_uids(struct user_namespace *ns);

 
 #include <asm/current.h>
 
 
 #include <asm/current.h>
 

diff --git a/kernel/user.c b/kernel/user.c
index add57c7e4c074237572da1b9beaf4592b4488896..9ca2848fc35676fa8ebac52f20c33f7f056d09ff 100644 (file)
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -62,7 +62,7 @@ static inline void uid_hash_insert(struct user_struct *up, struct hlist_head *ha
 
 static inline void uid_hash_remove(struct user_struct *up)
 {
 
 static inline void uid_hash_remove(struct user_struct *up)
 {

-       hlist_del(&up->uidhash_node);
+       hlist_del_init(&up->uidhash_node);

 }
 
 static inline struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent)
 }
 
 static inline struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent)


@@ -199,6 +199,30 @@ void switch_uid(struct user_struct *new_user)
        suid_keys(current);
 }
 
        suid_keys(current);
 }
 

+void release_uids(struct user_namespace *ns)
+{
+       int i;
+       unsigned long flags;
+       struct hlist_head *head;
+       struct hlist_node *nd;
+
+       spin_lock_irqsave(&uidhash_lock, flags);
+       /*
+        * collapse the chains so that the user_struct-s will
+        * be still alive, but not in hashes. subsequent free_uid()
+        * will free them.
+        */
+       for (i = 0; i < UIDHASH_SZ; i++) {
+               head = ns->uidhash_table + i;
+               while (!hlist_empty(head)) {
+                       nd = head->first;
+                       hlist_del_init(nd);
+               }
+       }
+       spin_unlock_irqrestore(&uidhash_lock, flags);
+
+       free_uid(ns->root_user);
+}

 
 static int __init uid_cache_init(void)
 {
 
 static int __init uid_cache_init(void)
 {

diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index e7ba1bf8457caed4144f2ad10e2f7a1800aec14c..7af90fc4f0fd3d870c1f5dbb3b0771fc16bbc5a4 100644 (file)
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -81,7 +81,7 @@ void free_user_ns(struct kref *kref)
        struct user_namespace *ns;
 
        ns = container_of(kref, struct user_namespace, kref);
        struct user_namespace *ns;
 
        ns = container_of(kref, struct user_namespace, kref);

-       free_uid(ns->root_user);
+       release_uids(ns);

        kfree(ns);
 }
 
        kfree(ns);
 }