more conservative S_NOSEC handling

Caching "we have already removed suid/caps" was overenthusiastic as merged.
On network filesystems we might have had suid/caps set on another client,
silently picked by this client on revalidate, all of that *without* clearing
the S_NOSEC flag.

AFAICS, the only reasonably sane way to deal with that is
	* new superblock flag; unless set, S_NOSEC is not going to be set.
	* local block filesystems set it in their ->mount() (more accurately,
mount_bdev() does, so does btrfs ->mount(), users of mount_bdev() other than
local block ones clear it)
	* if any network filesystem (or a cluster one) wants to use S_NOSEC,
it'll need to set MS_NOSEC in sb->s_flags *AND* take care to clear S_NOSEC when
inode attribute changes are picked from other clients.

It's not an earth-shattering hole (anybody that can set suid on another client
will almost certainly be able to write to the file before doing that anyway),
but it's a bug that needs fixing.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

6 files changed, 8 insertions, 5 deletions

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 9b2e7e5bc3ef..d158b672a2d2 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -819,7 +819,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 	} else {
 		char b[BDEVNAME_SIZE];
 
-		s->s_flags = flags;
+		s->s_flags = flags | MS_NOSEC;
 		strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
 		error = btrfs_fill_super(s, fs_devices, data,
 					 flags & MS_SILENT ? 1 : 0);
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index cc6ec4b2f0ff..38f84cd48b67 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -921,6 +921,8 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 	if (sb->s_flags & MS_MANDLOCK)
 		goto err;
 
+	sb->s_flags &= ~MS_NOSEC;
+
 	if (!parse_fuse_opt((char *) data, &d, is_bdev))
 		goto err;
 
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index cdbaf5e97308..56f61027236b 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1072,7 +1072,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 
 	sb->s_magic = OCFS2_SUPER_MAGIC;
 
-	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
+	sb->s_flags = (sb->s_flags & ~(MS_POSIXACL | MS_NOSEC)) |
 		((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
 
 	/* Hard readonly mode only if: bdev_read_only, MS_RDONLY,
diff --git a/fs/super.c b/fs/super.c
index c75593953c52..ab3d672db0de 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -822,7 +822,7 @@ struct dentry *mount_bdev(struct file_system_type *fs_type,
 	} else {
 		char b[BDEVNAME_SIZE];
 
-		s->s_flags = flags;
+		s->s_flags = flags | MS_NOSEC;
 		s->s_mode = mode;
 		strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
 		sb_set_blocksize(s, block_size(bdev));
diff --git a/include/linux/fs.h b/include/linux/fs.h
index c55d6b7cd5d6..646a1836152a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -208,6 +208,7 @@ struct inodes_stat_t {
 #define MS_KERNMOUNT	(1<<22) /* this is a kern_mount call */
 #define MS_I_VERSION	(1<<23) /* Update inode I_version field */
 #define MS_STRICTATIME	(1<<24) /* Always perform atime updates */
+#define MS_NOSEC	(1<<28)
 #define MS_BORN		(1<<29)
 #define MS_ACTIVE	(1<<30)
 #define MS_NOUSER	(1<<31)
@@ -2591,7 +2592,7 @@ static inline int is_sxid(mode_t mode)
 
 static inline void inode_has_no_xattr(struct inode *inode)
 {
-	if (!is_sxid(inode->i_mode))
+	if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & MS_NOSEC))
 		inode->i_flags |= S_NOSEC;
 }
 
diff --git a/mm/filemap.c b/mm/filemap.c
index d7b10578a64b..a8251a8d3457 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2000,7 +2000,7 @@ int file_remove_suid(struct file *file)
 		error = security_inode_killpriv(dentry);
 	if (!error && killsuid)
 		error = __remove_suid(dentry, killsuid);
-	if (!error)
+	if (!error && (inode->i_sb->s_flags & MS_NOSEC))
 		inode->i_flags |= S_NOSEC;
 
 	return error;