propogate_mnt: Handle the first propogated copy being a slave

commit 5ec0811d30378ae104f250bfc9b3640242d81e3f upstream.

When the first propgated copy was a slave the following oops would result:
> BUG: unable to handle kernel NULL pointer dereference at 0000000000000010
> IP: [<ffffffff811fba4e>] propagate_one+0xbe/0x1c0
> PGD bacd4067 PUD bac66067 PMD 0
> Oops: 0000 [#1] SMP
> Modules linked in:
> CPU: 1 PID: 824 Comm: mount Not tainted 4.6.0-rc5userns+ #1523
> Hardware name: Bochs Bochs, BIOS Bochs 01/01/2007
> task: ffff8800bb0a8000 ti: ffff8800bac3c000 task.ti: ffff8800bac3c000
> RIP: 0010:[<ffffffff811fba4e>]  [<ffffffff811fba4e>] propagate_one+0xbe/0x1c0
> RSP: 0018:ffff8800bac3fd38  EFLAGS: 00010283
> RAX: 0000000000000000 RBX: ffff8800bb77ec00 RCX: 0000000000000010
> RDX: 0000000000000000 RSI: ffff8800bb58c000 RDI: ffff8800bb58c480
> RBP: ffff8800bac3fd48 R08: 0000000000000001 R09: 0000000000000000
> R10: 0000000000001ca1 R11: 0000000000001c9d R12: 0000000000000000
> R13: ffff8800ba713800 R14: ffff8800bac3fda0 R15: ffff8800bb77ec00
> FS:  00007f3c0cd9b7e0(0000) GS:ffff8800bfb00000(0000) knlGS:0000000000000000
> CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> CR2: 0000000000000010 CR3: 00000000bb79d000 CR4: 00000000000006e0
> Stack:
>  ffff8800bb77ec00 0000000000000000 ffff8800bac3fd88 ffffffff811fbf85
>  ffff8800bac3fd98 ffff8800bb77f080 ffff8800ba713800 ffff8800bb262b40
>  0000000000000000 0000000000000000 ffff8800bac3fdd8 ffffffff811f1da0
> Call Trace:
>  [<ffffffff811fbf85>] propagate_mnt+0x105/0x140
>  [<ffffffff811f1da0>] attach_recursive_mnt+0x120/0x1e0
>  [<ffffffff811f1ec3>] graft_tree+0x63/0x70
>  [<ffffffff811f1f6b>] do_add_mount+0x9b/0x100
>  [<ffffffff811f2c1a>] do_mount+0x2aa/0xdf0
>  [<ffffffff8117efbe>] ? strndup_user+0x4e/0x70
>  [<ffffffff811f3a45>] SyS_mount+0x75/0xc0
>  [<ffffffff8100242b>] do_syscall_64+0x4b/0xa0
>  [<ffffffff81988f3c>] entry_SYSCALL64_slow_path+0x25/0x25
> Code: 00 00 75 ec 48 89 0d 02 22 22 01 8b 89 10 01 00 00 48 89 05 fd 21 22 01 39 8e 10 01 00 00 0f 84 e0 00 00 00 48 8b 80 d8 00 00 00 <48> 8b 50 10 48 89 05 df 21 22 01 48 89 15 d0 21 22 01 8b 53 30
> RIP  [<ffffffff811fba4e>] propagate_one+0xbe/0x1c0
>  RSP <ffff8800bac3fd38>
> CR2: 0000000000000010
> ---[ end trace 2725ecd95164f217 ]---

This oops happens with the namespace_sem held and can be triggered by
non-root users.  An all around not pleasant experience.

To avoid this scenario when finding the appropriate source mount to
copy stop the walk up the mnt_master chain when the first source mount
is encountered.

Further rewrite the walk up the last_source mnt_master chain so that
it is clear what is going on.

The reason why the first source mount is special is that it it's
mnt_parent is not a mount in the dest_mnt propagation tree, and as
such termination conditions based up on the dest_mnt mount propgation
tree do not make sense.

To avoid other kinds of confusion last_dest is not changed when
computing last_source.  last_dest is only used once in propagate_one
and that is above the point of the code being modified, so changing
the global variable is meaningless and confusing.

fixes: f2ebb3a921c1ca1e2ddd9242e95a1989a50c4c68 ("smarter propagate_mnt()")
Reported-by: Tycho Andersen <tycho.andersen@canonical.com>
Reviewed-by: Seth Forshee <seth.forshee@canonical.com>
Tested-by: Seth Forshee <seth.forshee@canonical.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/fs/pnode.c b/fs/pnode.c
index c524fdddc7fb1f601d6d06ddb46d0affcca89c08..99899705b1055411723c3e5919ecbc1f50139e14 100644 (file)
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -198,7 +198,7 @@ static struct mount *next_group(struct mount *m, struct mount *origin)
 
 /* all accesses are serialized by namespace_sem */
 static struct user_namespace *user_ns;
-static struct mount *last_dest, *last_source, *dest_master;
+static struct mount *last_dest, *first_source, *last_source, *dest_master;
 static struct mountpoint *mp;
 static struct hlist_head *list;
 
@@ -221,20 +221,22 @@ static int propagate_one(struct mount *m)
                type = CL_MAKE_SHARED;
        } else {
                struct mount *n, *p;
+               bool done;
                for (n = m; ; n = p) {
                        p = n->mnt_master;
-                       if (p == dest_master || IS_MNT_MARKED(p)) {
-                               while (last_dest->mnt_master != p) {
-                                       last_source = last_source->mnt_master;
-                                       last_dest = last_source->mnt_parent;
-                               }
-                               if (!peers(n, last_dest)) {
-                                       last_source = last_source->mnt_master;
-                                       last_dest = last_source->mnt_parent;
-                               }
+                       if (p == dest_master || IS_MNT_MARKED(p))
                                break;
-                       }
                }
+               do {
+                       struct mount *parent = last_source->mnt_parent;
+                       if (last_source == first_source)
+                               break;
+                       done = parent->mnt_master == p;
+                       if (done && peers(n, parent))
+                               break;
+                       last_source = last_source->mnt_master;
+               } while (!done);
+
                type = CL_SLAVE;
                /* beginning of peer group among the slaves? */
                if (IS_MNT_SHARED(m))
@@ -286,6 +288,7 @@ int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp,
         */
        user_ns = current->nsproxy->mnt_ns->user_ns;
        last_dest = dest_mnt;
+       first_source = source_mnt;
        last_source = source_mnt;
        mp = dest_mp;
        list = tree_list;