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

Pull namespace updates from Eric Biederman:
 "There is a lot here. A lot of these changes result in subtle user
  visible differences in kernel behavior. I don't expect anything will
  care but I will revert/fix things immediately if any regressions show
  up.

  From Seth Forshee there is a continuation of the work to make the vfs
  ready for unpriviled mounts. We had thought the previous changes
  prevented the creation of files outside of s_user_ns of a filesystem,
  but it turns we missed the O_CREAT path. Ooops.

  Pavel Tikhomirov and Oleg Nesterov worked together to fix a long
  standing bug in the implemenation of PR_SET_CHILD_SUBREAPER where only
  children that are forked after the prctl are considered and not
  children forked before the prctl. The only known user of this prctl
  systemd forks all children after the prctl. So no userspace
  regressions will occur. Holding earlier forked children to the same
  rules as later forked children creates a semantic that is sane enough
  to allow checkpoing of processes that use this feature.

  There is a long delayed change by Nikolay Borisov to limit inotify
  instances inside a user namespace.

  Michael Kerrisk extends the API for files used to maniuplate
  namespaces with two new trivial ioctls to allow discovery of the
  hierachy and properties of namespaces.

  Konstantin Khlebnikov with the help of Al Viro adds code that when a
  network namespace exits purges it's sysctl entries from the dcache. As
  in some circumstances this could use a lot of memory.

  Vivek Goyal fixed a bug with stacked filesystems where the permissions
  on the wrong inode were being checked.

  I continue previous work on ptracing across exec. Allowing a file to
  be setuid across exec while being ptraced if the tracer has enough
  credentials in the user namespace, and if the process has CAP_SETUID
  in it's own namespace. Proc files for setuid or otherwise undumpable
  executables are now owned by the root in the user namespace of their
  mm. Allowing debugging of setuid applications in containers to work
  better.

  A bug I introduced with permission checking and automount is now
  fixed. The big change is to mark the mounts that the kernel initiates
  as a result of an automount. This allows the permission checks in sget
  to be safely suppressed for this kind of mount. As the permission
  check happened when the original filesystem was mounted.

  Finally a special case in the mount namespace is removed preventing
  unbounded chains in the mount hash table, and making the semantics
  simpler which benefits CRIU.

  The vfs fix along with related work in ima and evm I believe makes us
  ready to finish developing and merge fully unprivileged mounts of the
  fuse filesystem. The cleanups of the mount namespace makes discussing
  how to fix the worst case complexity of umount. The stacked filesystem
  fixes pave the way for adding multiple mappings for the filesystem
  uids so that efficient and safer containers can be implemented"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
  proc/sysctl: Don't grab i_lock under sysctl_lock.
  vfs: Use upper filesystem inode in bprm_fill_uid()
  proc/sysctl: prune stale dentries during unregistering
  mnt: Tuck mounts under others instead of creating shadow/side mounts.
  prctl: propagate has_child_subreaper flag to every descendant
  introduce the walk_process_tree() helper
  nsfs: Add an ioctl() to return owner UID of a userns
  fs: Better permission checking for submounts
  exit: fix the setns() && PR_SET_CHILD_SUBREAPER interaction
  vfs: open() with O_CREAT should not create inodes with unknown ids
  nsfs: Add an ioctl() to return the namespace type
  proc: Better ownership of files for non-dumpable tasks in user namespaces
  exec: Remove LSM_UNSAFE_PTRACE_CAP
  exec: Test the ptracer's saved cred to see if the tracee can gain caps
  exec: Don't reset euid and egid when the tracee has CAP_SETUID
  inotify: Convert to using per-namespace limits

3 files changed, 36 insertions, 21 deletions

diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h
index a6f5907..7c461fd 100644
--- a/fs/notify/inotify/inotify.h
+++ b/fs/notify/inotify/inotify.h
@@ -30,3 +30,20 @@ extern int inotify_handle_event(struct fsnotify_group *group,
 				const unsigned char *file_name, u32 cookie);
 
 extern const struct fsnotify_ops inotify_fsnotify_ops;
+
+#ifdef CONFIG_INOTIFY_USER
+static inline void dec_inotify_instances(struct ucounts *ucounts)
+{
+	dec_ucount(ucounts, UCOUNT_INOTIFY_INSTANCES);
+}
+
+static inline struct ucounts *inc_inotify_watches(struct ucounts *ucounts)
+{
+	return inc_ucount(ucounts->ns, ucounts->uid, UCOUNT_INOTIFY_WATCHES);
+}
+
+static inline void dec_inotify_watches(struct ucounts *ucounts)
+{
+	dec_ucount(ucounts, UCOUNT_INOTIFY_WATCHES);
+}
+#endif
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index 19e7ec1..f36c293 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -165,10 +165,8 @@ static void inotify_free_group_priv(struct fsnotify_group *group)
 	/* ideally the idr is empty and we won't hit the BUG in the callback */
 	idr_for_each(&group->inotify_data.idr, idr_callback, group);
 	idr_destroy(&group->inotify_data.idr);
-	if (group->inotify_data.user) {
-		atomic_dec(&group->inotify_data.user->inotify_devs);
-		free_uid(group->inotify_data.user);
-	}
+	if (group->inotify_data.ucounts)
+		dec_inotify_instances(group->inotify_data.ucounts);
 }
 
 static void inotify_free_event(struct fsnotify_event *fsn_event)
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 69d1ea3..1cf41c6 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -44,10 +44,8 @@
 
 #include <asm/ioctls.h>
 
-/* these are configurable via /proc/sys/fs/inotify/ */
-static int inotify_max_user_instances __read_mostly;
+/* configurable via /proc/sys/fs/inotify/ */
 static int inotify_max_queued_events __read_mostly;
-static int inotify_max_user_watches __read_mostly;
 
 static struct kmem_cache *inotify_inode_mark_cachep __read_mostly;
 
@@ -60,7 +58,7 @@ static int zero;
 struct ctl_table inotify_table[] = {
 	{
 		.procname	= "max_user_instances",
-		.data		= &inotify_max_user_instances,
+		.data		= &init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES],
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
@@ -68,7 +66,7 @@ struct ctl_table inotify_table[] = {
 	},
 	{
 		.procname	= "max_user_watches",
-		.data		= &inotify_max_user_watches,
+		.data		= &init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES],
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
@@ -500,7 +498,7 @@ void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark,
 	/* remove this mark from the idr */
 	inotify_remove_from_idr(group, i_mark);
 
-	atomic_dec(&group->inotify_data.user->inotify_watches);
+	dec_inotify_watches(group->inotify_data.ucounts);
 }
 
 /* ding dong the mark is dead */
@@ -584,14 +582,17 @@ static int inotify_new_watch(struct fsnotify_group *group,
 	tmp_i_mark->fsn_mark.mask = mask;
 	tmp_i_mark->wd = -1;
 
-	ret = -ENOSPC;
-	if (atomic_read(&group->inotify_data.user->inotify_watches) >= inotify_max_user_watches)
-		goto out_err;
-
 	ret = inotify_add_to_idr(idr, idr_lock, tmp_i_mark);
 	if (ret)
 		goto out_err;
 
+	/* increment the number of watches the user has */
+	if (!inc_inotify_watches(group->inotify_data.ucounts)) {
+		inotify_remove_from_idr(group, tmp_i_mark);
+		ret = -ENOSPC;
+		goto out_err;
+	}
+
 	/* we are on the idr, now get on the inode */
 	ret = fsnotify_add_mark_locked(&tmp_i_mark->fsn_mark, group, inode,
 				       NULL, 0);
@@ -601,8 +602,6 @@ static int inotify_new_watch(struct fsnotify_group *group,
 		goto out_err;
 	}
 
-	/* increment the number of watches the user has */
-	atomic_inc(&group->inotify_data.user->inotify_watches);
 
 	/* return the watch descriptor for this new mark */
 	ret = tmp_i_mark->wd;
@@ -653,10 +652,11 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events)
 
 	spin_lock_init(&group->inotify_data.idr_lock);
 	idr_init(&group->inotify_data.idr);
-	group->inotify_data.user = get_current_user();
+	group->inotify_data.ucounts = inc_ucount(current_user_ns(),
+						 current_euid(),
+						 UCOUNT_INOTIFY_INSTANCES);
 
-	if (atomic_inc_return(&group->inotify_data.user->inotify_devs) >
-	    inotify_max_user_instances) {
+	if (!group->inotify_data.ucounts) {
 		fsnotify_destroy_group(group);
 		return ERR_PTR(-EMFILE);
 	}
@@ -819,8 +819,8 @@ static int __init inotify_user_setup(void)
 	inotify_inode_mark_cachep = KMEM_CACHE(inotify_inode_mark, SLAB_PANIC);
 
 	inotify_max_queued_events = 16384;
-	inotify_max_user_instances = 128;
-	inotify_max_user_watches = 8192;
+	init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES] = 128;
+	init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES] = 8192;
 
 	return 0;
 }