[PATCH 1/7] fs: Add user namesapace member to struct super_block

[Seth Forshee <seth.forshee@canonical.com>]

Initially this will be used to eliminate the implicit MNT_NODEV
flag for mounts from user namespaces. In the future it will also
be used for translating ids and checking capabilities for
filesystems mounted from user namespaces.

s_user_ns is initialized in alloc_super() and is generally set to
current_user_ns(). To avoid security and corruption issues, two
additional mount checks are also added:

 - do_new_mount() gains a check that the user has CAP_SYS_ADMIN
   in current_user_ns().

 - sget() will fail with EBUSY when the filesystem it's looking
   for is already mounted from another user namespace.

proc needs some special handling here. The user namespace of
current isn't appropriate when forking as a result of clone (2)
with CLONE_NEWPID|CLONE_NEWUSER, as it will make proc unmountable
from within the new user namespace. Instead, the user namespace
which owns the new pid namespace should be used. sget_userns() is
added to allow passing of a user namespace other than that of
current, and this is used by proc_mount(). sget() becomes a
wrapper around sget_userns() which passes current_user_ns().

Signed-off-by: Seth Forshee <seth.forshee@canonical.com>
---
 fs/namespace.c     |  3 +++
 fs/proc/root.c     |  3 ++-
 fs/super.c         | 38 +++++++++++++++++++++++++++++++++-----
 include/linux/fs.h |  8 ++++++++
 4 files changed, 46 insertions(+), 6 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index ce428cadd41f..f1f67d663d49 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2357,6 +2357,9 @@ static int do_new_mount(struct path *path, const char *fstype, int flags,
 	struct vfsmount *mnt;
 	int err;
 
+	if (!ns_capable(current_user_ns(), CAP_SYS_ADMIN))
+		return -EPERM;
+
 	if (!fstype)
 		return -EINVAL;
 
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 361ab4ee42fc..4b302cbf13f9 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -117,7 +117,8 @@ static struct dentry *proc_mount(struct file_system_type *fs_type,
 			return ERR_PTR(-EPERM);
 	}
 
-	sb = sget(fs_type, proc_test_super, proc_set_super, flags, ns);
+	sb = sget_userns(fs_type, proc_test_super, proc_set_super, flags,
+			 ns->user_ns, ns);
 	if (IS_ERR(sb))
 		return ERR_CAST(sb);
 
diff --git a/fs/super.c b/fs/super.c
index b61372354f2b..b5f171aadbf7 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -33,6 +33,7 @@
 #include <linux/cleancache.h>
 #include <linux/fsnotify.h>
 #include <linux/lockdep.h>
+#include <linux/user_namespace.h>
 #include "internal.h"
 
 
@@ -148,6 +149,7 @@ static void destroy_super(struct super_block *s)
 	list_lru_destroy(&s->s_inode_lru);
 	for (i = 0; i < SB_FREEZE_LEVELS; i++)
 		percpu_counter_destroy(&s->s_writers.counter[i]);
+	put_user_ns(s->s_user_ns);
 	security_sb_free(s);
 	WARN_ON(!list_empty(&s->s_mounts));
 	kfree(s->s_subtype);
@@ -163,7 +165,8 @@ static void destroy_super(struct super_block *s)
  *	Allocates and initializes a new &struct super_block.  alloc_super()
  *	returns a pointer new superblock or %NULL if allocation had failed.
  */
-static struct super_block *alloc_super(struct file_system_type *type, int flags)
+static struct super_block *alloc_super(struct file_system_type *type, int flags,
+				       struct user_namespace *user_ns)
 {
 	struct super_block *s = kzalloc(sizeof(struct super_block),  GFP_USER);
 	static const struct super_operations default_op;
@@ -231,6 +234,8 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 	s->s_shrink.count_objects = super_cache_count;
 	s->s_shrink.batch = 1024;
 	s->s_shrink.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE;
+
+	s->s_user_ns = get_user_ns(user_ns);
 	return s;
 
 fail:
@@ -427,17 +432,17 @@ void generic_shutdown_super(struct super_block *sb)
 EXPORT_SYMBOL(generic_shutdown_super);
 
 /**
- *	sget	-	find or create a superblock
+ *	sget_userns -	find or create a superblock
  *	@type:	filesystem type superblock should belong to
  *	@test:	comparison callback
  *	@set:	setup callback
  *	@flags:	mount flags
  *	@data:	argument to each of them
  */
-struct super_block *sget(struct file_system_type *type,
+struct super_block *sget_userns(struct file_system_type *type,
 			int (*test)(struct super_block *,void *),
 			int (*set)(struct super_block *,void *),
-			int flags,
+			int flags, struct user_namespace *user_ns,
 			void *data)
 {
 	struct super_block *s = NULL;
@@ -450,6 +455,10 @@ retry:
 		hlist_for_each_entry(old, &type->fs_supers, s_instances) {
 			if (!test(old, data))
 				continue;
+			if (user_ns != old->s_user_ns) {
+				spin_unlock(&sb_lock);
+				return ERR_PTR(-EBUSY);
+			}
 			if (!grab_super(old))
 				goto retry;
 			if (s) {
@@ -462,7 +471,7 @@ retry:
 	}
 	if (!s) {
 		spin_unlock(&sb_lock);
-		s = alloc_super(type, flags);
+		s = alloc_super(type, flags, user_ns);
 		if (!s)
 			return ERR_PTR(-ENOMEM);
 		goto retry;
@@ -485,6 +494,25 @@ retry:
 	return s;
 }
 
+EXPORT_SYMBOL(sget_userns);
+
+/**
+ *	sget	-	find or create a superblock
+ *	@type:	  filesystem type superblock should belong to
+ *	@test:	  comparison callback
+ *	@set:	  setup callback
+ *	@flags:	  mount flags
+ *	@data:	  argument to each of them
+ */
+struct super_block *sget(struct file_system_type *type,
+			int (*test)(struct super_block *,void *),
+			int (*set)(struct super_block *,void *),
+			int flags,
+			void *data)
+{
+	return sget_userns(type, test, set, flags, current_user_ns(), data);
+}
+
 EXPORT_SYMBOL(sget);
 
 void drop_super(struct super_block *sb)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 42912f8d286e..1876477ac9f8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -30,6 +30,7 @@
 #include <linux/lockdep.h>
 #include <linux/percpu-rwsem.h>
 #include <linux/blk_types.h>
+#include <linux/user_namespace.h>
 
 #include <asm/byteorder.h>
 #include <uapi/linux/fs.h>
@@ -1353,6 +1354,8 @@ struct super_block {
 	struct workqueue_struct *s_dio_done_wq;
 	struct hlist_head s_pins;
 
+	struct user_namespace *s_user_ns;
+
 	/*
 	 * Keep the lru lists last in the structure so they always sit on their
 	 * own individual cachelines.
@@ -1959,6 +1962,11 @@ void deactivate_locked_super(struct super_block *sb);
 int set_anon_super(struct super_block *s, void *data);
 int get_anon_bdev(dev_t *);
 void free_anon_bdev(dev_t);
+struct super_block *sget_userns(struct file_system_type *type,
+			int (*test)(struct super_block *,void *),
+			int (*set)(struct super_block *,void *),
+			int flags, struct user_namespace *user_ns,
+			void *data);
 struct super_block *sget(struct file_system_type *type,
 			int (*test)(struct super_block *,void *),
 			int (*set)(struct super_block *,void *),
-- 
1.9.1