devpts: Make each mount of devpts an independent filesystem.

The /dev/ptmx device node is changed to lookup the directory entry "pts"
in the same directory as the /dev/ptmx device node was opened in.  If
there is a "pts" entry and that entry is a devpts filesystem /dev/ptmx
uses that filesystem.  Otherwise the open of /dev/ptmx fails.

The DEVPTS_MULTIPLE_INSTANCES configuration option is removed, so that
userspace can now safely depend on each mount of devpts creating a new
instance of the filesystem.

Each mount of devpts is now a separate and equal filesystem.

Reserved ttys are now available to all instances of devpts where the
mounter is in the initial mount namespace.

A new vfs helper path_pts is introduced that finds a directory entry
named "pts" in the directory of the passed in path, and changes the
passed in path to point to it.  The helper path_pts uses a function
path_parent_directory that was factored out of follow_dotdot.

In the implementation of devpts:
 - devpts_mnt is killed as it is no longer meaningful if all mounts of
   devpts are equal.
 - pts_sb_from_inode is replaced by just inode->i_sb as all cached
   inodes in the tty layer are now from the devpts filesystem.
 - devpts_add_ref is rolled into the new function devpts_ptmx.  And the
   unnecessary inode hold is removed.
 - devpts_del_ref is renamed devpts_release and reduced to just a
   deacrivate_super.
 - The newinstance mount option continues to be accepted but is now
   ignored.

In devpts_fs.h definitions for when !CONFIG_UNIX98_PTYS are removed as
they are never used.

Documentation/filesystems/devices.txt is updated to describe the current
situation.

This has been verified to work properly on openwrt-15.05, centos5,
centos6, centos7, debian-6.0.2, debian-7.9, debian-8.2, ubuntu-14.04.3,
ubuntu-15.10, fedora23, magia-5, mint-17.3, opensuse-42.1,
slackware-14.1, gentoo-20151225 (13.0?), archlinux-2015-12-01.  With the
caveat that on centos6 and on slackware-14.1 that there wind up being
two instances of the devpts filesystem mounted on /dev/pts, the lower
copy does not end up getting used.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Greg KH <greg@kroah.com>
Cc: Peter Hurley <peter@hurleysoftware.com>
Cc: Peter Anvin <hpa@zytor.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Serge Hallyn <serge.hallyn@ubuntu.com>
Cc: Willy Tarreau <w@1wt.eu>
Cc: Aurelien Jarno <aurelien@aurel32.net>
Cc: One Thousand Gnomes <gnomes@lxorguk.ukuu.org.uk>
Cc: Jann Horn <jann@thejh.net>
Cc: Jiri Slaby <jslaby@suse.com>
Cc: Florian Weimer <fw@deneb.enyo.de>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 97 insertions, 143 deletions

diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 0b2954d7172d..37c134a132c7 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -95,8 +95,6 @@ static struct ctl_table pty_root_table[] = {
 
 static DEFINE_MUTEX(allocated_ptys_lock);
 
-static struct vfsmount *devpts_mnt;
-
 struct pts_mount_opts {
 	int setuid;
 	int setgid;
@@ -104,7 +102,7 @@ struct pts_mount_opts {
 	kgid_t   gid;
 	umode_t mode;
 	umode_t ptmxmode;
-	int newinstance;
+	int reserve;
 	int max;
 };
 
@@ -117,11 +115,9 @@ static const match_table_t tokens = {
 	{Opt_uid, "uid=%u"},
 	{Opt_gid, "gid=%u"},
 	{Opt_mode, "mode=%o"},
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
 	{Opt_ptmxmode, "ptmxmode=%o"},
 	{Opt_newinstance, "newinstance"},
 	{Opt_max, "max=%d"},
-#endif
 	{Opt_err, NULL}
 };
 
@@ -137,15 +133,48 @@ static inline struct pts_fs_info *DEVPTS_SB(struct super_block *sb)
 	return sb->s_fs_info;
 }
 
-static inline struct super_block *pts_sb_from_inode(struct inode *inode)
+struct pts_fs_info *devpts_acquire(struct file *filp)
 {
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
-	if (inode->i_sb->s_magic == DEVPTS_SUPER_MAGIC)
-		return inode->i_sb;
-#endif
-	if (!devpts_mnt)
-		return NULL;
-	return devpts_mnt->mnt_sb;
+	struct pts_fs_info *result;
+	struct path path;
+	struct super_block *sb;
+	int err;
+
+	path = filp->f_path;
+	path_get(&path);
+
+	/* Has the devpts filesystem already been found? */
+	sb = path.mnt->mnt_sb;
+	if (sb->s_magic != DEVPTS_SUPER_MAGIC) {
+		/* Is a devpts filesystem at "pts" in the same directory? */
+		err = path_pts(&path);
+		if (err) {
+			result = ERR_PTR(err);
+			goto out;
+		}
+
+		/* Is the path the root of a devpts filesystem? */
+		result = ERR_PTR(-ENODEV);
+		sb = path.mnt->mnt_sb;
+		if ((sb->s_magic != DEVPTS_SUPER_MAGIC) ||
+		    (path.mnt->mnt_root != sb->s_root))
+			goto out;
+	}
+
+	/*
+	 * pty code needs to hold extra references in case of last /dev/tty close
+	 */
+	atomic_inc(&sb->s_active);
+	result = DEVPTS_SB(sb);
+
+out:
+	path_put(&path);
+	return result;
+}
+
+void devpts_release(struct pts_fs_info *fsi)
+{
+	deactivate_super(fsi->sb);
 }
 
 #define PARSE_MOUNT	0
@@ -154,9 +183,7 @@ static inline struct super_block *pts_sb_from_inode(struct inode *inode)
 /*
  * parse_mount_options():
  *	Set @opts to mount options specified in @data. If an option is not
- *	specified in @data, set it to its default value. The exception is
- *	'newinstance' option which can only be set/cleared on a mount (i.e.
- *	cannot be changed during remount).
+ *	specified in @data, set it to its default value.
  *
  * Note: @data may be NULL (in which case all options are set to default).
  */
@@ -174,9 +201,12 @@ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts)
 	opts->ptmxmode = DEVPTS_DEFAULT_PTMX_MODE;
 	opts->max     = NR_UNIX98_PTY_MAX;
 
-	/* newinstance makes sense only on initial mount */
+	/* Only allow instances mounted from the initial mount
+	 * namespace to tap the reserve pool of ptys.
+	 */
 	if (op == PARSE_MOUNT)
-		opts->newinstance = 0;
+		opts->reserve =
+			(current->nsproxy->mnt_ns == init_task.nsproxy->mnt_ns);
 
 	while ((p = strsep(&data, ",")) != NULL) {
 		substring_t args[MAX_OPT_ARGS];
@@ -211,16 +241,12 @@ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts)
 				return -EINVAL;
 			opts->mode = option & S_IALLUGO;
 			break;
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
 		case Opt_ptmxmode:
 			if (match_octal(&args[0], &option))
 				return -EINVAL;
 			opts->ptmxmode = option & S_IALLUGO;
 			break;
 		case Opt_newinstance:
-			/* newinstance makes sense only on initial mount */
-			if (op == PARSE_MOUNT)
-				opts->newinstance = 1;
 			break;
 		case Opt_max:
 			if (match_int(&args[0], &option) ||
@@ -228,7 +254,6 @@ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts)
 				return -EINVAL;
 			opts->max = option;
 			break;
-#endif
 		default:
 			pr_err("called with bogus options\n");
 			return -EINVAL;
@@ -238,7 +263,6 @@ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts)
 	return 0;
 }
 
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
 static int mknod_ptmx(struct super_block *sb)
 {
 	int mode;
@@ -305,12 +329,6 @@ static void update_ptmx_mode(struct pts_fs_info *fsi)
 		inode->i_mode = S_IFCHR|fsi->mount_opts.ptmxmode;
 	}
 }
-#else
-static inline void update_ptmx_mode(struct pts_fs_info *fsi)
-{
-	return;
-}
-#endif
 
 static int devpts_remount(struct super_block *sb, int *flags, char *data)
 {
@@ -344,11 +362,9 @@ static int devpts_show_options(struct seq_file *seq, struct dentry *root)
 		seq_printf(seq, ",gid=%u",
 			   from_kgid_munged(&init_user_ns, opts->gid));
 	seq_printf(seq, ",mode=%03o", opts->mode);
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
 	seq_printf(seq, ",ptmxmode=%03o", opts->ptmxmode);
 	if (opts->max < NR_UNIX98_PTY_MAX)
 		seq_printf(seq, ",max=%d", opts->max);
-#endif
 
 	return 0;
 }
@@ -410,40 +426,11 @@ fail:
 	return -ENOMEM;
 }
 
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
-static int compare_init_pts_sb(struct super_block *s, void *p)
-{
-	if (devpts_mnt)
-		return devpts_mnt->mnt_sb == s;
-	return 0;
-}
-
 /*
  * devpts_mount()
  *
- *     If the '-o newinstance' mount option was specified, mount a new
- *     (private) instance of devpts.  PTYs created in this instance are
- *     independent of the PTYs in other devpts instances.
- *
- *     If the '-o newinstance' option was not specified, mount/remount the
- *     initial kernel mount of devpts.  This type of mount gives the
- *     legacy, single-instance semantics.
- *
- *     The 'newinstance' option is needed to support multiple namespace
- *     semantics in devpts while preserving backward compatibility of the
- *     current 'single-namespace' semantics. i.e all mounts of devpts
- *     without the 'newinstance' mount option should bind to the initial
- *     kernel mount, like mount_single().
- *
- *     Mounts with 'newinstance' option create a new, private namespace.
- *
- *     NOTE:
- *
- *     For single-mount semantics, devpts cannot use mount_single(),
- *     because mount_single()/sget() find and use the super-block from
- *     the most recent mount of devpts. But that recent mount may be a
- *     'newinstance' mount and mount_single() would pick the newinstance
- *     super-block instead of the initial super-block.
+ *     Mount a new (private) instance of devpts.  PTYs created in this
+ *     instance are independent of the PTYs in other devpts instances.
  */
 static struct dentry *devpts_mount(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data)
@@ -456,18 +443,7 @@ static struct dentry *devpts_mount(struct file_system_type *fs_type,
 	if (error)
 		return ERR_PTR(error);
 
-	/* Require newinstance for all user namespace mounts to ensure
-	 * the mount options are not changed.
-	 */
-	if ((current_user_ns() != &init_user_ns) && !opts.newinstance)
-		return ERR_PTR(-EINVAL);
-
-	if (opts.newinstance)
-		s = sget(fs_type, NULL, set_anon_super, flags, NULL);
-	else
-		s = sget(fs_type, compare_init_pts_sb, set_anon_super, flags,
-			 NULL);
-
+	s = sget(fs_type, NULL, set_anon_super, flags, NULL);
 	if (IS_ERR(s))
 		return ERR_CAST(s);
 
@@ -491,18 +467,6 @@ out_undo_sget:
 	return ERR_PTR(error);
 }
 
-#else
-/*
- * This supports only the legacy single-instance semantics (no
- * multiple-instance semantics)
- */
-static struct dentry *devpts_mount(struct file_system_type *fs_type, int flags,
-		const char *dev_name, void *data)
-{
-	return mount_single(fs_type, flags, data, devpts_fill_super);
-}
-#endif
-
 static void devpts_kill_sb(struct super_block *sb)
 {
 	struct pts_fs_info *fsi = DEVPTS_SB(sb);
@@ -516,9 +480,7 @@ static struct file_system_type devpts_fs_type = {
 	.name		= "devpts",
 	.mount		= devpts_mount,
 	.kill_sb	= devpts_kill_sb,
-#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
 	.fs_flags	= FS_USERNS_MOUNT | FS_USERNS_DEV_MOUNT,
-#endif
 };
 
 /*
@@ -531,16 +493,13 @@ int devpts_new_index(struct pts_fs_info *fsi)
 	int index;
 	int ida_ret;
 
-	if (!fsi)
-		return -ENODEV;
-
 retry:
 	if (!ida_pre_get(&fsi->allocated_ptys, GFP_KERNEL))
 		return -ENOMEM;
 
 	mutex_lock(&allocated_ptys_lock);
-	if (pty_count >= pty_limit -
-			(fsi->mount_opts.newinstance ? pty_reserve : 0)) {
+	if (pty_count >= (pty_limit -
+			  (fsi->mount_opts.reserve ? 0 : pty_reserve))) {
 		mutex_unlock(&allocated_ptys_lock);
 		return -ENOSPC;
 	}
@@ -571,30 +530,6 @@ void devpts_kill_index(struct pts_fs_info *fsi, int idx)
 	mutex_unlock(&allocated_ptys_lock);
 }
 
-/*
- * pty code needs to hold extra references in case of last /dev/tty close
- */
-struct pts_fs_info *devpts_get_ref(struct inode *ptmx_inode, struct file *file)
-{
-	struct super_block *sb;
-	struct pts_fs_info *fsi;
-
-	sb = pts_sb_from_inode(ptmx_inode);
-	if (!sb)
-		return NULL;
-	fsi = DEVPTS_SB(sb);
-	if (!fsi)
-		return NULL;
-
-	atomic_inc(&sb->s_active);
-	return fsi;
-}
-
-void devpts_put_ref(struct pts_fs_info *fsi)
-{
-	deactivate_super(fsi->sb);
-}
-
 /**
  * devpts_pty_new -- create a new inode in /dev/pts/
  * @ptmx_inode: inode of the master
@@ -607,16 +542,12 @@ void devpts_put_ref(struct pts_fs_info *fsi)
 struct dentry *devpts_pty_new(struct pts_fs_info *fsi, int index, void *priv)
 {
 	struct dentry *dentry;
-	struct super_block *sb;
+	struct super_block *sb = fsi->sb;
 	struct inode *inode;
 	struct dentry *root;
 	struct pts_mount_opts *opts;
 	char s[12];
 
-	if (!fsi)
-		return ERR_PTR(-ENODEV);
-
-	sb = fsi->sb;
 	root = sb->s_root;
 	opts = &fsi->mount_opts;
 
@@ -676,20 +607,8 @@ void devpts_pty_kill(struct dentry *dentry)
 static int __init init_devpts_fs(void)
 {
 	int err = register_filesystem(&devpts_fs_type);
-	struct ctl_table_header *table;
-
 	if (!err) {
-		struct vfsmount *mnt;
-
-		table = register_sysctl_table(pty_root_table);
-		mnt = kern_mount(&devpts_fs_type);
-		if (IS_ERR(mnt)) {
-			err = PTR_ERR(mnt);
-			unregister_filesystem(&devpts_fs_type);
-			unregister_sysctl_table(table);
-		} else {
-			devpts_mnt = mnt;
-		}
+		register_sysctl_table(pty_root_table);
 	}
 	return err;
 }
diff --git a/fs/namei.c b/fs/namei.c
index 4c4f95ac8aa5..6a82fb7e2127 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1416,21 +1416,28 @@ static void follow_mount(struct path *path)
 	}
 }
 
+static int path_parent_directory(struct path *path)
+{
+	struct dentry *old = path->dentry;
+	/* rare case of legitimate dget_parent()... */
+	path->dentry = dget_parent(path->dentry);
+	dput(old);
+	if (unlikely(!path_connected(path)))
+		return -ENOENT;
+	return 0;
+}
+
 static int follow_dotdot(struct nameidata *nd)
 {
 	while(1) {
-		struct dentry *old = nd->path.dentry;
-
 		if (nd->path.dentry == nd->root.dentry &&
 		    nd->path.mnt == nd->root.mnt) {
 			break;
 		}
 		if (nd->path.dentry != nd->path.mnt->mnt_root) {
-			/* rare case of legitimate dget_parent()... */
-			nd->path.dentry = dget_parent(nd->path.dentry);
-			dput(old);
-			if (unlikely(!path_connected(&nd->path)))
-				return -ENOENT;
+			int ret = path_parent_directory(&nd->path);
+			if (ret)
+				return ret;
 			break;
 		}
 		if (!follow_up(&nd->path))
@@ -2514,6 +2521,34 @@ struct dentry *lookup_one_len_unlocked(const char *name,
 }
 EXPORT_SYMBOL(lookup_one_len_unlocked);
 
+#ifdef CONFIG_UNIX98_PTYS
+int path_pts(struct path *path)
+{
+	/* Find something mounted on "pts" in the same directory as
+	 * the input path.
+	 */
+	struct dentry *child, *parent;
+	struct qstr this;
+	int ret;
+
+	ret = path_parent_directory(path);
+	if (ret)
+		return ret;
+
+	parent = path->dentry;
+	this.name = "pts";
+	this.len = 3;
+	child = d_hash_and_lookup(parent, &this);
+	if (!child)
+		return -ENOENT;
+
+	path->dentry = child;
+	dput(parent);
+	follow_mount(path);
+	return 0;
+}
+#endif
+
 int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
 		 struct path *path, int *empty)
 {