Enable multiple instances of devpts

To support containers, allow multiple instances of devpts filesystem, such
that indices of ptys allocated in one instance are independent of ptys
allocated in other instances of devpts.

But to preserve backward compatibility, enable this support for multiple
instances only if:

	- CONFIG_DEVPTS_MULTIPLE_INSTANCES is set to Y, and
	- '-o newinstance' mount option is specified while mounting devpts

To use multi-instance mount, a container startup script could:

	$ ns_exec -cm /bin/bash
	$ umount /dev/pts
	$ mount -t devpts -o newinstance lxcpts /dev/pts
	$ mount -o bind /dev/pts/ptmx /dev/ptmx
	$ /usr/sbin/sshd -p 1234

where 'ns_exec -cm /bin/bash' is calls clone() with CLONE_NEWNS flag and execs
/bin/bash in the child process. A pty created by the sshd is not visible in
the original mount of /dev/pts.

USER-SPACE-IMPACT:
	- See Documentation/fs/devpts.txt (included in next patch) for user-
	  space impact in multi-instance and mixed-mode operation.
TODO:
	- Update mount(8), pts(4) man pages. Highlight impact of not
	  redirecting /dev/ptmx to /dev/pts/ptmx after a multi-instance mount.

Changelog[v6]:
	- [Dave Hansen] Use new get_init_pts_sb() interface
	- [Serge Hallyn] Don't bother displaying 'newinstance' in show_options
	- [Serge Hallyn] Use macros (PARSE_REMOUNT/PARSE_MOUNT) instead of 0/1.
	- [Serge Hallyn] Check error return from get_sb_single() (now
	  get_init_pts_sb())
	- devpts_pty_kill(): don't dput error dentries

Changelog[v5]:
	- Move get_sb_ref() definition to earlier patch
	- Move usage info to Documentation/filesystems/devpts.txt (next patch)
	- Make ptmx node even in init_pts_ns, now that default mode is 0000
	  (defined in earlier patch, enabled here).
	- Cache ptmx dentry and use to update mode during remount
	  (defined in earlier patch, enabled here).
	- Bugfix: explicitly ignore newinstance on remount (if newinstance was
	  specified on remount of initial mount, it would be ignored but
	  /proc/mounts would imply that the option was set)

Changelog[v4]:

	- Update patch description to address H. Peter Anvin's comments
	- Consolidate multi-instance mode code under new config token,
	  CONFIG_DEVPTS_MULTIPLE_INSTANCE.
	- Move usage-details from patch description to
	  Documentation/fs/devpts.txt

Changelog[v3]:
	- Rename new mount option to 'newinstance'
	- Create ptmx nodes only in 'newinstance' mounts
	- Bugfix: parse_mount_options() modifies @data but since we need to
	  parse the @data twice (once in devpts_get_sb() and once during
	  do_remount_sb()), parse a local copy of @data in devpts_get_sb().
	  (restructured code in devpts_get_sb() to fix this)

Changelog[v2]:
	- Support both single-mount and multiple-mount semantics and
	  provide '-onewmnt' option to select the semantics.

Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Signed-off-by: Alan Cox <alan@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 2d0eb2cf99e619706cb61313ba8f0745a50e5b0c..b4a89fa21673ae98fd44a9de6ecd74fe4b8e8c34 100644 (file)
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -48,10 +48,11 @@ struct pts_mount_opts {
        gid_t   gid;
        umode_t mode;
        umode_t ptmxmode;
+       int newinstance;
 };
 
 enum {
-       Opt_uid, Opt_gid, Opt_mode, Opt_ptmxmode,
+       Opt_uid, Opt_gid, Opt_mode, Opt_ptmxmode, Opt_newinstance,
        Opt_err
 };
 
@@ -61,6 +62,7 @@ static const match_table_t tokens = {
        {Opt_mode, "mode=%o"},
 #ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
        {Opt_ptmxmode, "ptmxmode=%o"},
+       {Opt_newinstance, "newinstance"},
 #endif
        {Opt_err, NULL}
 };
@@ -78,13 +80,17 @@ static inline struct pts_fs_info *DEVPTS_SB(struct super_block *sb)
 
 static inline struct super_block *pts_sb_from_inode(struct inode *inode)
 {
+#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
        if (inode->i_sb->s_magic == DEVPTS_SUPER_MAGIC)
                return inode->i_sb;
-
+#endif
        return devpts_mnt->mnt_sb;
 }
 
-static int parse_mount_options(char *data, struct pts_mount_opts *opts)
+#define PARSE_MOUNT    0
+#define PARSE_REMOUNT  1
+
+static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts)
 {
        char *p;
 
@@ -95,6 +101,10 @@ static int parse_mount_options(char *data, struct pts_mount_opts *opts)
        opts->mode    = DEVPTS_DEFAULT_MODE;
        opts->ptmxmode = DEVPTS_DEFAULT_PTMX_MODE;
 
+       /* newinstance makes sense only on initial mount */
+       if (op == PARSE_MOUNT)
+               opts->newinstance = 0;
+
        while ((p = strsep(&data, ",")) != NULL) {
                substring_t args[MAX_OPT_ARGS];
                int token;
@@ -128,6 +138,11 @@ static int parse_mount_options(char *data, struct pts_mount_opts *opts)
                                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;
 #endif
                default:
                        printk(KERN_ERR "devpts: called with bogus options\n");
@@ -214,7 +229,7 @@ static int devpts_remount(struct super_block *sb, int *flags, char *data)
        struct pts_fs_info *fsi = DEVPTS_SB(sb);
        struct pts_mount_opts *opts = &fsi->mount_opts;
 
-       err = parse_mount_options(data, opts);
+       err = parse_mount_options(data, PARSE_REMOUNT, opts);
 
        /*
         * parse_mount_options() restores options to default values
@@ -309,8 +324,100 @@ static int compare_init_pts_sb(struct super_block *s, void *p)
 {
        if (devpts_mnt)
                return devpts_mnt->mnt_sb == s;
+       return 0;
+}
+
+#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
+/*
+ * Safely parse the mount options in @data and update @opts.
+ *
+ * devpts ends up parsing options two times during mount, due to the
+ * two modes of operation it supports. The first parse occurs in
+ * devpts_get_sb() when determining the mode (single-instance or
+ * multi-instance mode). The second parse happens in devpts_remount()
+ * or new_pts_mount() depending on the mode.
+ *
+ * Parsing of options modifies the @data making subsequent parsing
+ * incorrect. So make a local copy of @data and parse it.
+ *
+ * Return: 0 On success, -errno on error
+ */
+static int safe_parse_mount_options(void *data, struct pts_mount_opts *opts)
+{
+       int rc;
+       void *datacp;
+
+       if (!data)
+               return 0;
+
+       /* Use kstrdup() ?  */
+       datacp = kmalloc(PAGE_SIZE, GFP_KERNEL);
+       if (!datacp)
+               return -ENOMEM;
+
+       memcpy(datacp, data, PAGE_SIZE);
+       rc = parse_mount_options((char *)datacp, PARSE_MOUNT, opts);
+       kfree(datacp);
+
+       return rc;
+}
+
+/*
+ * Mount a new (private) instance of devpts.  PTYs created in this
+ * instance are independent of the PTYs in other devpts instances.
+ */
+static int new_pts_mount(struct file_system_type *fs_type, int flags,
+               void *data, struct vfsmount *mnt)
+{
+       int err;
+       struct pts_fs_info *fsi;
+       struct pts_mount_opts *opts;
+
+       printk(KERN_NOTICE "devpts: newinstance mount\n");
+
+       err = get_sb_nodev(fs_type, flags, data, devpts_fill_super, mnt);
+       if (err)
+               return err;
+
+       fsi = DEVPTS_SB(mnt->mnt_sb);
+       opts = &fsi->mount_opts;
+
+       err = parse_mount_options(data, PARSE_MOUNT, opts);
+       if (err)
+               goto fail;
+
+       err = mknod_ptmx(mnt->mnt_sb);
+       if (err)
+               goto fail;
 
        return 0;
+
+fail:
+       dput(mnt->mnt_sb->s_root);
+       deactivate_super(mnt->mnt_sb);
+       return err;
+}
+
+/*
+ * Check if 'newinstance' mount option was specified in @data.
+ *
+ * Return: -errno      on error (eg: invalid mount options specified)
+ *      : 1            if 'newinstance' mount option was specified
+ *      : 0            if 'newinstance' mount option was NOT specified
+ */
+static int is_new_instance_mount(void *data)
+{
+       int rc;
+       struct pts_mount_opts opts;
+
+       if (!data)
+               return 0;
+
+       rc = safe_parse_mount_options(data, &opts);
+       if (!rc)
+               rc = opts.newinstance;
+
+       return rc;
 }
 
 /*
@@ -358,11 +465,54 @@ static int get_init_pts_sb(struct file_system_type *fs_type, int flags,
         return simple_set_mnt(mnt, s);
 }
 
+/*
+ * Mount or remount the initial kernel mount of devpts. This type of
+ * mount maintains the legacy, single-instance semantics, while the
+ * kernel still allows multiple-instances.
+ */
+static int init_pts_mount(struct file_system_type *fs_type, int flags,
+               void *data, struct vfsmount *mnt)
+{
+       int err;
+
+       err = get_init_pts_sb(fs_type, flags, data, mnt);
+       if (err)
+                return err;
+
+       err = mknod_ptmx(mnt->mnt_sb);
+       if (err) {
+               dput(mnt->mnt_sb->s_root);
+               deactivate_super(mnt->mnt_sb);
+       }
+
+       return err;
+}
+
 static int devpts_get_sb(struct file_system_type *fs_type,
        int flags, const char *dev_name, void *data, struct vfsmount *mnt)
 {
-       return get_init_pts_sb(fs_type, flags, data, mnt);
+       int new;
+
+       new = is_new_instance_mount(data);
+       if (new < 0)
+               return new;
+
+       if (new)
+               return new_pts_mount(fs_type, flags, data, mnt);
+
+       return init_pts_mount(fs_type, flags, data, mnt);
 }
+#else
+/*
+ * This supports only the legacy single-instance semantics (no
+ * multiple-instance semantics)
+ */
+static int devpts_get_sb(struct file_system_type *fs_type, int flags,
+               const char *dev_name, void *data, struct vfsmount *mnt)
+{
+       return get_sb_single(fs_type, flags, data, devpts_fill_super, mnt);
+}
+#endif
 
 static void devpts_kill_sb(struct super_block *sb)
 {
@@ -488,12 +638,18 @@ void devpts_pty_kill(struct tty_struct *tty)
        mutex_lock(&root->d_inode->i_mutex);
 
        dentry = d_find_alias(inode);
-       if (dentry && !IS_ERR(dentry)) {
+       if (IS_ERR(dentry))
+               goto out;
+
+       if (dentry) {
                inode->i_nlink--;
                d_delete(dentry);
-               dput(dentry);
+               dput(dentry);   // d_alloc_name() in devpts_pty_new()
        }
 
+       dput(dentry);           // d_find_alias above
+
+out:
        mutex_unlock(&root->d_inode->i_mutex);
 }