[PATCH v2] devpts: Make each mount of devpts an independent filesystem.

From: Eric W. Biederman
Date: Wed Apr 20 2016 - 13:11:40 EST



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@xxxxxxxxxxxx>
---
Documentation/filesystems/devpts.txt | 145 +++----------------------
drivers/tty/Kconfig | 11 --
drivers/tty/pty.c | 41 ++++---
fs/devpts/inode.c | 203 ++++++++++-------------------------
fs/namei.c | 49 +++++++--
include/linux/devpts_fs.h | 31 ++----
include/linux/namei.h | 2 +
7 files changed, 144 insertions(+), 338 deletions(-)

diff --git a/Documentation/filesystems/devpts.txt b/Documentation/filesystems/devpts.txt
index 30d2fcb32f72..9f94fe276dea 100644
--- a/Documentation/filesystems/devpts.txt
+++ b/Documentation/filesystems/devpts.txt
@@ -1,141 +1,26 @@
+Each mount of the devpts filesystem is now distinct such that ptys
+and their indicies allocated in one mount are independent from ptys
+and their indicies in all other mounts.

-To support containers, we now allow multiple instances of devpts filesystem,
-such that indices of ptys allocated in one instance are independent of indices
-allocated in other instances of devpts.
+All mounts of the devpts filesystem now create a /dev/pts/ptmx node
+with permissions 0000.

-To preserve backward compatibility, this support for multiple instances is
-enabled only if:
+To retain backwards compatibility the a ptmx device node (aka any node
+created with "mknod name c 5 2") when opened will look for an instance
+of devpts under the name "pts" in the same directory as the ptmx device
+node.

- - CONFIG_DEVPTS_MULTIPLE_INSTANCES=y, and
- - '-o newinstance' mount option is specified while mounting devpts
-
-IOW, devpts now supports both single-instance and multi-instance semantics.
-
-If CONFIG_DEVPTS_MULTIPLE_INSTANCES=n, there is no change in behavior and
-this referred to as the "legacy" mode. In this mode, the new mount options
-(-o newinstance and -o ptmxmode) will be ignored with a 'bogus option' message
-on console.
-
-If CONFIG_DEVPTS_MULTIPLE_INSTANCES=y and devpts is mounted without the
-'newinstance' option (as in current start-up scripts) the new mount binds
-to the initial kernel mount of devpts. This mode is referred to as the
-'single-instance' mode and the current, single-instance semantics are
-preserved, i.e PTYs are common across the system.
-
-The only difference between this single-instance mode and the legacy mode
-is the presence of new, '/dev/pts/ptmx' node with permissions 0000, which
-can safely be ignored.
-
-If CONFIG_DEVPTS_MULTIPLE_INSTANCES=y and 'newinstance' option is specified,
-the mount is considered to be in the multi-instance mode and a new instance
-of the devpts fs is created. Any ptys created in this instance are independent
-of ptys in other instances of devpts. Like in the single-instance mode, the
-/dev/pts/ptmx node is present. To effectively use the multi-instance mode,
-open of /dev/ptmx must be a redirected to '/dev/pts/ptmx' using a symlink or
-bind-mount.
-
-Eg: A container startup script could do the following:
-
- $ chmod 0666 /dev/pts/ptmx
- $ rm /dev/ptmx
- $ ln -s pts/ptmx /dev/ptmx
- $ ns_exec -cm /bin/bash
-
- # We are now in new container
-
- $ umount /dev/pts
- $ mount -t devpts -o newinstance lxcpts /dev/pts
- $ sshd -p 1234
-
-where 'ns_exec -cm /bin/bash' 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.
+As an option instead of placing a /dev/ptmx device node at /dev/ptmx
+it is possible to place a symlink to /dev/pts/ptmx at /dev/ptmx or
+to bind mount /dev/ptx/ptmx to /dev/ptmx. If you opt for using
+the devpts filesystem in this manner devpts should be mounted with
+the ptmxmode=0666, or chmod 0666 /dev/pts/ptmx should be called.

Total count of pty pairs in all instances is limited by sysctls:
kernel.pty.max = 4096 - global limit
-kernel.pty.reserve = 1024 - reserve for initial instance
+kernel.pty.reserve = 1024 - reserved for filesystems mounted from the initial mount namespace
kernel.pty.nr - current count of ptys

Per-instance limit could be set by adding mount option "max=<count>".
This feature was added in kernel 3.4 together with sysctl kernel.pty.reserve.
In kernels older than 3.4 sysctl kernel.pty.max works as per-instance limit.
-
-User-space changes
-------------------
-
-In multi-instance mode (i.e '-o newinstance' mount option is specified at least
-once), following user-space issues should be noted.
-
-1. If -o newinstance mount option is never used, /dev/pts/ptmx can be ignored
- and no change is needed to system-startup scripts.
-
-2. To effectively use multi-instance mode (i.e -o newinstance is specified)
- administrators or startup scripts should "redirect" open of /dev/ptmx to
- /dev/pts/ptmx using either a bind mount or symlink.
-
- $ mount -t devpts -o newinstance devpts /dev/pts
-
- followed by either
-
- $ rm /dev/ptmx
- $ ln -s pts/ptmx /dev/ptmx
- $ chmod 666 /dev/pts/ptmx
- or
- $ mount -o bind /dev/pts/ptmx /dev/ptmx
-
-3. The '/dev/ptmx -> pts/ptmx' symlink is the preferred method since it
- enables better error-reporting and treats both single-instance and
- multi-instance mounts similarly.
-
- But this method requires that system-startup scripts set the mode of
- /dev/pts/ptmx correctly (default mode is 0000). The scripts can set the
- mode by, either
-
- - adding ptmxmode mount option to devpts entry in /etc/fstab, or
- - using 'chmod 0666 /dev/pts/ptmx'
-
-4. If multi-instance mode mount is needed for containers, but the system
- startup scripts have not yet been updated, container-startup scripts
- should bind mount /dev/ptmx to /dev/pts/ptmx to avoid breaking single-
- instance mounts.
-
- Or, in general, container-startup scripts should use:
-
- mount -t devpts -o newinstance -o ptmxmode=0666 devpts /dev/pts
- if [ ! -L /dev/ptmx ]; then
- mount -o bind /dev/pts/ptmx /dev/ptmx
- fi
-
- When all devpts mounts are multi-instance, /dev/ptmx can permanently be
- a symlink to pts/ptmx and the bind mount can be ignored.
-
-5. A multi-instance mount that is not accompanied by the /dev/ptmx to
- /dev/pts/ptmx redirection would result in an unusable/unreachable pty.
-
- mount -t devpts -o newinstance lxcpts /dev/pts
-
- immediately followed by:
-
- open("/dev/ptmx")
-
- would create a pty, say /dev/pts/7, in the initial kernel mount.
- But /dev/pts/7 would be invisible in the new mount.
-
-6. The permissions for /dev/pts/ptmx node should be specified when mounting
- /dev/pts, using the '-o ptmxmode=%o' mount option (default is 0000).
-
- mount -t devpts -o newinstance -o ptmxmode=0644 devpts /dev/pts
-
- The permissions can be later be changed as usual with 'chmod'.
-
- chmod 666 /dev/pts/ptmx
-
-7. A mount of devpts without the 'newinstance' option results in binding to
- initial kernel mount. This behavior while preserving legacy semantics,
- does not provide strict isolation in a container environment. i.e by
- mounting devpts without the 'newinstance' option, a container could
- get visibility into the 'host' or root container's devpts.
-
- To workaround this and have strict isolation, all mounts of devpts,
- including the mount in the root container, should use the newinstance
- option.
diff --git a/drivers/tty/Kconfig b/drivers/tty/Kconfig
index 82c4d2e45319..95103054c0e4 100644
--- a/drivers/tty/Kconfig
+++ b/drivers/tty/Kconfig
@@ -120,17 +120,6 @@ config UNIX98_PTYS
All modern Linux systems use the Unix98 ptys. Say Y unless
you're on an embedded system and want to conserve memory.

-config DEVPTS_MULTIPLE_INSTANCES
- bool "Support multiple instances of devpts"
- depends on UNIX98_PTYS
- default n
- ---help---
- Enable support for multiple instances of devpts filesystem.
- If you want to have isolated PTY namespaces (eg: in containers),
- say Y here. Otherwise, say N. If enabled, each mount of devpts
- filesystem with the '-o newinstance' option will create an
- independent PTY namespace.
-
config LEGACY_PTYS
bool "Legacy (BSD) PTY support"
default y
diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index e16a49b507ef..6e57eb31e327 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -663,14 +663,14 @@ static int pty_unix98_install(struct tty_driver *driver, struct tty_struct *tty)
/* this is called once with whichever end is closed last */
static void pty_unix98_remove(struct tty_driver *driver, struct tty_struct *tty)
{
- struct inode *ptmx_inode;
+ struct pts_fs_info *fsi;

if (tty->driver->subtype == PTY_TYPE_MASTER)
- ptmx_inode = tty->driver_data;
+ fsi = tty->driver_data;
else
- ptmx_inode = tty->link->driver_data;
- devpts_kill_index(ptmx_inode, tty->index);
- devpts_del_ref(ptmx_inode);
+ fsi = tty->link->driver_data;
+ devpts_kill_index(fsi, tty->index);
+ devpts_release(fsi);
}

static const struct tty_operations ptm_unix98_ops = {
@@ -721,6 +721,7 @@ static const struct tty_operations pty_unix98_ops = {
static int ptmx_open(struct inode *inode, struct file *filp)
{
struct tty_struct *tty;
+ struct pts_fs_info *fsi;
struct inode *slave_inode;
int retval;
int index;
@@ -734,13 +735,19 @@ static int ptmx_open(struct inode *inode, struct file *filp)
if (retval)
return retval;

+ fsi = devpts_acquire(filp);
+ if (IS_ERR(fsi)) {
+ retval = PTR_ERR(fsi);
+ goto err_file;
+ }
+
/* find a device that is not in use. */
mutex_lock(&devpts_mutex);
- index = devpts_new_index(inode);
+ index = devpts_new_index(fsi);
if (index < 0) {
retval = index;
mutex_unlock(&devpts_mutex);
- goto err_file;
+ goto err_fsi;
}

mutex_unlock(&devpts_mutex);
@@ -758,23 +765,11 @@ static int ptmx_open(struct inode *inode, struct file *filp)
mutex_unlock(&tty_mutex);

set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */
- tty->driver_data = inode;
-
- /*
- * In the case where all references to ptmx inode are dropped and we
- * still have /dev/tty opened pointing to the master/slave pair (ptmx
- * is closed/released before /dev/tty), we must make sure that the inode
- * is still valid when we call the final pty_unix98_shutdown, thus we
- * hold an additional reference to the ptmx inode. For the same /dev/tty
- * last close case, we also need to make sure the super_block isn't
- * destroyed (devpts instance unmounted), before /dev/tty is closed and
- * on its release devpts_kill_index is called.
- */
- devpts_add_ref(inode);
+ tty->driver_data = fsi;

tty_add_file(tty, filp);

- slave_inode = devpts_pty_new(inode,
+ slave_inode = devpts_pty_new(fsi,
MKDEV(UNIX98_PTY_SLAVE_MAJOR, index), index,
tty->link);
if (IS_ERR(slave_inode)) {
@@ -797,7 +792,9 @@ err_release:
return retval;
out:
mutex_unlock(&tty_mutex);
- devpts_kill_index(inode, index);
+ devpts_kill_index(fsi, index);
+err_fsi:
+ devpts_release(fsi);
err_file:
tty_free_file(filp);
return retval;
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 655f21f99160..0b8edbc617e4 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;
};

@@ -117,17 +115,16 @@ 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}
};

struct pts_fs_info {
struct ida allocated_ptys;
struct pts_mount_opts mount_opts;
+ struct super_block *sb;
struct dentry *ptmx_dentry;
};

@@ -136,15 +133,43 @@ 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;
+
+ /* Is a devpts filesystem at "pts" in the same directory? */
+ path = filp->f_path;
+ path_get(&path);
+ err = path_pts(&path);
+ if (err) {
+ result = ERR_PTR(err);
+ goto out;
+ }
+
+ /* Is the path the root of a devpts filesystem? */
+ result = ERR_PTR(-ENOENT);
+ 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
@@ -153,9 +178,7 @@ 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).
*/
@@ -173,9 +196,12 @@ 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];
@@ -210,16 +236,12 @@ 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) ||
@@ -227,7 +249,6 @@ 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;
@@ -237,7 +258,6 @@ 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;
@@ -304,12 +324,6 @@ 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)
{
@@ -343,11 +357,9 @@ 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;
}
@@ -358,7 +370,7 @@ static const struct super_operations devpts_sops = {
.show_options = devpts_show_options,
};

-static void *new_pts_fs_info(void)
+static void *new_pts_fs_info(struct super_block *sb)
{
struct pts_fs_info *fsi;

@@ -369,6 +381,7 @@ static void *new_pts_fs_info(void)
ida_init(&fsi->allocated_ptys);
fsi->mount_opts.mode = DEVPTS_DEFAULT_MODE;
fsi->mount_opts.ptmxmode = DEVPTS_DEFAULT_PTMX_MODE;
+ fsi->sb = sb;

return fsi;
}
@@ -384,7 +397,7 @@ devpts_fill_super(struct super_block *s, void *data, int silent)
s->s_op = &devpts_sops;
s->s_time_gran = 1;

- s->s_fs_info = new_pts_fs_info();
+ s->s_fs_info = new_pts_fs_info(s);
if (!s->s_fs_info)
goto fail;

@@ -408,40 +421,11 @@ 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)
@@ -454,18 +438,7 @@ 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);

@@ -489,18 +462,6 @@ 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);
@@ -514,9 +475,7 @@ 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
};

/*
@@ -524,24 +483,18 @@ static struct file_system_type devpts_fs_type = {
* to the System V naming convention
*/

-int devpts_new_index(struct inode *ptmx_inode)
+int devpts_new_index(struct pts_fs_info *fsi)
{
- struct super_block *sb = pts_sb_from_inode(ptmx_inode);
- struct pts_fs_info *fsi;
int index;
int ida_ret;

- if (!sb)
- return -ENODEV;
-
- fsi = DEVPTS_SB(sb);
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;
}
@@ -564,37 +517,14 @@ retry:
return index;
}

-void devpts_kill_index(struct inode *ptmx_inode, int idx)
+void devpts_kill_index(struct pts_fs_info *fsi, int idx)
{
- struct super_block *sb = pts_sb_from_inode(ptmx_inode);
- struct pts_fs_info *fsi = DEVPTS_SB(sb);
-
mutex_lock(&allocated_ptys_lock);
ida_remove(&fsi->allocated_ptys, idx);
pty_count--;
mutex_unlock(&allocated_ptys_lock);
}

-/*
- * pty code needs to hold extra references in case of last /dev/tty close
- */
-
-void devpts_add_ref(struct inode *ptmx_inode)
-{
- struct super_block *sb = pts_sb_from_inode(ptmx_inode);
-
- atomic_inc(&sb->s_active);
- ihold(ptmx_inode);
-}
-
-void devpts_del_ref(struct inode *ptmx_inode)
-{
- struct super_block *sb = pts_sb_from_inode(ptmx_inode);
-
- iput(ptmx_inode);
- deactivate_super(sb);
-}
-
/**
* devpts_pty_new -- create a new inode in /dev/pts/
* @ptmx_inode: inode of the master
@@ -604,22 +534,17 @@ void devpts_del_ref(struct inode *ptmx_inode)
*
* The created inode is returned. Remove it from /dev/pts/ by devpts_pty_kill.
*/
-struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index,
+struct inode *devpts_pty_new(struct pts_fs_info *fsi, dev_t device, int index,
void *priv)
{
struct dentry *dentry;
- struct super_block *sb = pts_sb_from_inode(ptmx_inode);
+ struct super_block *sb = fsi->sb;
struct inode *inode;
struct dentry *root;
- struct pts_fs_info *fsi;
struct pts_mount_opts *opts;
char s[12];

- if (!sb)
- return ERR_PTR(-ENODEV);
-
root = sb->s_root;
- fsi = DEVPTS_SB(sb);
opts = &fsi->mount_opts;

inode = new_inode(sb);
@@ -685,7 +610,7 @@ void *devpts_get_priv(struct inode *pts_inode)
*/
void devpts_pty_kill(struct inode *inode)
{
- struct super_block *sb = pts_sb_from_inode(inode);
+ struct super_block *sb = inode->i_sb;
struct dentry *root = sb->s_root;
struct dentry *dentry;

@@ -706,20 +631,8 @@ void devpts_pty_kill(struct inode *inode)
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 794f81dce766..5c0a38971dbd 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1415,21 +1415,28 @@ 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))
@@ -2374,6 +2381,34 @@ 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)
{
diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h
index e0ee0b3000b2..486f6282b0c6 100644
--- a/include/linux/devpts_fs.h
+++ b/include/linux/devpts_fs.h
@@ -17,36 +17,21 @@

#ifdef CONFIG_UNIX98_PTYS

-int devpts_new_index(struct inode *ptmx_inode);
-void devpts_kill_index(struct inode *ptmx_inode, int idx);
-void devpts_add_ref(struct inode *ptmx_inode);
-void devpts_del_ref(struct inode *ptmx_inode);
+struct pts_fs_info;
+
+struct pts_fs_info *devpts_acquire(struct file *filp);
+void devpts_release(struct pts_fs_info *fsi);
+
+int devpts_new_index(struct pts_fs_info *fsi);
+void devpts_kill_index(struct pts_fs_info *fsi, int idx);
/* mknod in devpts */
-struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index,
+struct inode *devpts_pty_new(struct pts_fs_info *fsi, dev_t device, int index,
void *priv);
/* get private structure */
void *devpts_get_priv(struct inode *pts_inode);
/* unlink */
void devpts_pty_kill(struct inode *inode);

-#else
-
-/* Dummy stubs in the no-pty case */
-static inline int devpts_new_index(struct inode *ptmx_inode) { return -EINVAL; }
-static inline void devpts_kill_index(struct inode *ptmx_inode, int idx) { }
-static inline void devpts_add_ref(struct inode *ptmx_inode) { }
-static inline void devpts_del_ref(struct inode *ptmx_inode) { }
-static inline struct inode *devpts_pty_new(struct inode *ptmx_inode,
- dev_t device, int index, void *priv)
-{
- return ERR_PTR(-EINVAL);
-}
-static inline void *devpts_get_priv(struct inode *pts_inode)
-{
- return NULL;
-}
-static inline void devpts_pty_kill(struct inode *inode) { }
-
#endif


diff --git a/include/linux/namei.h b/include/linux/namei.h
index 77d01700daf7..f29abda31e6d 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -45,6 +45,8 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
#define LOOKUP_ROOT 0x2000
#define LOOKUP_EMPTY 0x4000

+extern int path_pts(struct path *path);
+
extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty);

static inline int user_path_at(int dfd, const char __user *name, unsigned flags,
--
2.8.1