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

Pull namespace updates from Eric Biederman:
 "This is a bunch of small changes built against 3.16-rc6.  The most
  significant change for users is the first patch which makes setns
  drmatically faster by removing unneded rcu handling.

  The next chunk of changes are so that "mount -o remount,.." will not
  allow the user namespace root to drop flags on a mount set by the
  system wide root.  Aks this forces read-only mounts to stay read-only,
  no-dev mounts to stay no-dev, no-suid mounts to stay no-suid, no-exec
  mounts to stay no exec and it prevents unprivileged users from messing
  with a mounts atime settings.  I have included my test case as the
  last patch in this series so people performing backports can verify
  this change works correctly.

  The next change fixes a bug in NFS that was discovered while auditing
  nsproxy users for the first optimization.  Today you can oops the
  kernel by reading /proc/fs/nfsfs/{servers,volumes} if you are clever
  with pid namespaces.  I rebased and fixed the build of the
  !CONFIG_NFS_FS case yesterday when a build bot caught my typo.  Given
  that no one to my knowledge bases anything on my tree fixing the typo
  in place seems more responsible that requiring a typo-fix to be
  backported as well.

  The last change is a small semantic cleanup introducing
  /proc/thread-self and pointing /proc/mounts and /proc/net at it.  This
  prevents several kinds of problemantic corner cases.  It is a
  user-visible change so it has a minute chance of causing regressions
  so the change to /proc/mounts and /proc/net are individual one line
  commits that can be trivially reverted.  Unfortunately I lost and
  could not find the email of the original reporter so he is not
  credited.  From at least one perspective this change to /proc/net is a
  refgression fix to allow pthread /proc/net uses that were broken by
  the introduction of the network namespace"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
  proc: Point /proc/mounts at /proc/thread-self/mounts instead of /proc/self/mounts
  proc: Point /proc/net at /proc/thread-self/net instead of /proc/self/net
  proc: Implement /proc/thread-self to point at the directory of the current thread
  proc: Have net show up under /proc/<tgid>/task/<tid>
  NFS: Fix /proc/fs/nfsfs/servers and /proc/fs/nfsfs/volumes
  mnt: Add tests for unprivileged remount cases that have found to be faulty
  mnt: Change the default remount atime from relatime to the existing value
  mnt: Correct permission checks in do_remount
  mnt: Move the test for MNT_LOCK_READONLY from change_mount_flags into do_remount
  mnt: Only change user settable mount flags in remount
  namespaces: Use task_lock and not rcu to protect nsproxy

1 files changed, 55 insertions, 10 deletions

diff --git a/fs/namespace.c b/fs/namespace.c
index 2a1447c946e7..0acabea58319 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -890,8 +890,21 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 
         mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~(MNT_WRITE_HOLD|MNT_MARKED);
         /* Don't allow unprivileged users to change mount flags */
-        if ((flag & CL_UNPRIVILEGED) && (mnt->mnt.mnt_flags & MNT_READONLY))
-                mnt->mnt.mnt_flags |= MNT_LOCK_READONLY;
+        if (flag & CL_UNPRIVILEGED) {
+                mnt->mnt.mnt_flags |= MNT_LOCK_ATIME;
+
+                if (mnt->mnt.mnt_flags & MNT_READONLY)
+                        mnt->mnt.mnt_flags |= MNT_LOCK_READONLY;
+
+                if (mnt->mnt.mnt_flags & MNT_NODEV)
+                        mnt->mnt.mnt_flags |= MNT_LOCK_NODEV;
+
+                if (mnt->mnt.mnt_flags & MNT_NOSUID)
+                        mnt->mnt.mnt_flags |= MNT_LOCK_NOSUID;
+
+                if (mnt->mnt.mnt_flags & MNT_NOEXEC)
+                        mnt->mnt.mnt_flags |= MNT_LOCK_NOEXEC;
+        }
 
         /* Don't allow unprivileged users to reveal what is under a mount */
         if ((flag & CL_UNPRIVILEGED) && list_empty(&old->mnt_expire))
@@ -1896,9 +1909,6 @@ static int change_mount_flags(struct vfsmount *mnt, int ms_flags)
         if (readonly_request == __mnt_is_readonly(mnt))
                 return 0;
 
-        if (mnt->mnt_flags & MNT_LOCK_READONLY)
-                return -EPERM;
-
         if (readonly_request)
                 error = mnt_make_readonly(real_mount(mnt));
         else
@@ -1924,6 +1934,33 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
         if (path->dentry != path->mnt->mnt_root)
                 return -EINVAL;
 
+        /* Don't allow changing of locked mnt flags.
+         *
+         * No locks need to be held here while testing the various
+         * MNT_LOCK flags because those flags can never be cleared
+         * once they are set.
+         */
+        if ((mnt->mnt.mnt_flags & MNT_LOCK_READONLY) &&
+            !(mnt_flags & MNT_READONLY)) {
+                return -EPERM;
+        }
+        if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) &&
+            !(mnt_flags & MNT_NODEV)) {
+                return -EPERM;
+        }
+        if ((mnt->mnt.mnt_flags & MNT_LOCK_NOSUID) &&
+            !(mnt_flags & MNT_NOSUID)) {
+                return -EPERM;
+        }
+        if ((mnt->mnt.mnt_flags & MNT_LOCK_NOEXEC) &&
+            !(mnt_flags & MNT_NOEXEC)) {
+                return -EPERM;
+        }
+        if ((mnt->mnt.mnt_flags & MNT_LOCK_ATIME) &&
+            ((mnt->mnt.mnt_flags & MNT_ATIME_MASK) != (mnt_flags & MNT_ATIME_MASK))) {
+                return -EPERM;
+        }
+
         err = security_sb_remount(sb, data);
         if (err)
                 return err;
@@ -1937,7 +1974,7 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
                 err = do_remount_sb(sb, flags, data, 0);
         if (!err) {
                 lock_mount_hash();
-                mnt_flags |= mnt->mnt.mnt_flags & MNT_PROPAGATION_MASK;
+                mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK;
                 mnt->mnt.mnt_flags = mnt_flags;
                 touch_mnt_namespace(mnt->mnt_ns);
                 unlock_mount_hash();
@@ -2122,7 +2159,7 @@ static int do_new_mount(struct path *path, const char *fstype, int flags,
                  */
                 if (!(type->fs_flags & FS_USERNS_DEV_MOUNT)) {
                         flags |= MS_NODEV;
-                        mnt_flags |= MNT_NODEV;
+                        mnt_flags |= MNT_NODEV | MNT_LOCK_NODEV;
                 }
         }
 
@@ -2436,6 +2473,14 @@ long do_mount(const char *dev_name, const char *dir_name,
         if (flags & MS_RDONLY)
                 mnt_flags |= MNT_READONLY;
 
+        /* The default atime for remount is preservation */
+        if ((flags & MS_REMOUNT) &&
+            ((flags & (MS_NOATIME | MS_NODIRATIME | MS_RELATIME |
+                       MS_STRICTATIME)) == 0)) {
+                mnt_flags &= ~MNT_ATIME_MASK;
+                mnt_flags |= path.mnt->mnt_flags & MNT_ATIME_MASK;
+        }
+
         flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN |
                    MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT |
                    MS_STRICTATIME);
@@ -2972,13 +3017,13 @@ static void *mntns_get(struct task_struct *task)
         struct mnt_namespace *ns = NULL;
         struct nsproxy *nsproxy;
 
-        rcu_read_lock();
-        nsproxy = task_nsproxy(task);
+        task_lock(task);
+        nsproxy = task->nsproxy;
         if (nsproxy) {
                 ns = nsproxy->mnt_ns;
                 get_mnt_ns(ns);
         }
-        rcu_read_unlock();
+        task_unlock(task);
 
         return ns;
 }