linux/fs/nsfs.c

259 lines
5.6 KiB
C
Raw Normal View History

#include <linux/mount.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/proc_ns.h>
#include <linux/magic.h>
#include <linux/ktime.h>
#include <linux/seq_file.h>
#include <linux/user_namespace.h>
#include <linux/nsfs.h>
#include <linux/uaccess.h>
static struct vfsmount *nsfs_mnt;
static long ns_ioctl(struct file *filp, unsigned int ioctl,
unsigned long arg);
static const struct file_operations ns_file_operations = {
.llseek = no_llseek,
.unlocked_ioctl = ns_ioctl,
};
static char *ns_dname(struct dentry *dentry, char *buffer, int buflen)
{
struct inode *inode = d_inode(dentry);
const struct proc_ns_operations *ns_ops = dentry->d_fsdata;
return dynamic_dname(dentry, buffer, buflen, "%s:[%lu]",
ns_ops->name, inode->i_ino);
}
static void ns_prune_dentry(struct dentry *dentry)
{
struct inode *inode = d_inode(dentry);
if (inode) {
struct ns_common *ns = inode->i_private;
atomic_long_set(&ns->stashed, 0);
}
}
const struct dentry_operations ns_dentry_operations =
{
.d_prune = ns_prune_dentry,
.d_delete = always_delete_dentry,
.d_dname = ns_dname,
};
static void nsfs_evict(struct inode *inode)
{
struct ns_common *ns = inode->i_private;
clear_inode(inode);
ns->ops->put(ns);
}
static void *__ns_get_path(struct path *path, struct ns_common *ns)
{
struct vfsmount *mnt = nsfs_mnt;
struct dentry *dentry;
struct inode *inode;
unsigned long d;
rcu_read_lock();
d = atomic_long_read(&ns->stashed);
if (!d)
goto slow;
dentry = (struct dentry *)d;
if (!lockref_get_not_dead(&dentry->d_lockref))
goto slow;
rcu_read_unlock();
ns->ops->put(ns);
got_it:
path->mnt = mntget(mnt);
path->dentry = dentry;
return NULL;
slow:
rcu_read_unlock();
inode = new_inode_pseudo(mnt->mnt_sb);
if (!inode) {
ns->ops->put(ns);
return ERR_PTR(-ENOMEM);
}
inode->i_ino = ns->inum;
inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
inode->i_flags |= S_IMMUTABLE;
inode->i_mode = S_IFREG | S_IRUGO;
inode->i_fop = &ns_file_operations;
inode->i_private = ns;
dentry = d_alloc_pseudo(mnt->mnt_sb, &empty_name);
if (!dentry) {
iput(inode);
return ERR_PTR(-ENOMEM);
}
d_instantiate(dentry, inode);
dentry->d_flags |= DCACHE_RCUACCESS;
dentry->d_fsdata = (void *)ns->ops;
d = atomic_long_cmpxchg(&ns->stashed, 0, (unsigned long)dentry);
if (d) {
d_delete(dentry); /* make sure ->d_prune() does nothing */
dput(dentry);
cpu_relax();
return ERR_PTR(-EAGAIN);
}
goto got_it;
}
void *ns_get_path(struct path *path, struct task_struct *task,
const struct proc_ns_operations *ns_ops)
{
struct ns_common *ns;
void *ret;
again:
ns = ns_ops->get(task);
if (!ns)
return ERR_PTR(-ENOENT);
ret = __ns_get_path(path, ns);
if (IS_ERR(ret) && PTR_ERR(ret) == -EAGAIN)
goto again;
return ret;
}
int open_related_ns(struct ns_common *ns,
struct ns_common *(*get_ns)(struct ns_common *ns))
{
struct path path = {};
struct file *f;
void *err;
int fd;
fd = get_unused_fd_flags(O_CLOEXEC);
if (fd < 0)
return fd;
while (1) {
struct ns_common *relative;
relative = get_ns(ns);
if (IS_ERR(relative)) {
put_unused_fd(fd);
return PTR_ERR(relative);
}
err = __ns_get_path(&path, relative);
if (IS_ERR(err) && PTR_ERR(err) == -EAGAIN)
continue;
break;
}
if (IS_ERR(err)) {
put_unused_fd(fd);
return PTR_ERR(err);
}
f = dentry_open(&path, O_RDONLY, current_cred());
path_put(&path);
if (IS_ERR(f)) {
put_unused_fd(fd);
fd = PTR_ERR(f);
} else
fd_install(fd, f);
return fd;
}
static long ns_ioctl(struct file *filp, unsigned int ioctl,
unsigned long arg)
{
struct user_namespace *user_ns;
struct ns_common *ns = get_proc_ns(file_inode(filp));
uid_t __user *argp;
uid_t uid;
switch (ioctl) {
case NS_GET_USERNS:
return open_related_ns(ns, ns_get_owner);
case NS_GET_PARENT:
if (!ns->ops->get_parent)
return -EINVAL;
return open_related_ns(ns, ns->ops->get_parent);
nsfs: Add an ioctl() to return the namespace type Linux 4.9 added two ioctl() operations that can be used to discover: * the parental relationships for hierarchical namespaces (user and PID) [NS_GET_PARENT] * the user namespaces that owns a specified non-user-namespace [NS_GET_USERNS] For no good reason that I can glean, NS_GET_USERNS was made synonymous with NS_GET_PARENT for user namespaces. It might have been better if NS_GET_USERNS had returned an error if the supplied file descriptor referred to a user namespace, since it suggests that the caller may be confused. More particularly, if it had generated an error, then I wouldn't need the new ioctl() operation proposed here. (On the other hand, what I propose here may be more generally useful.) I would like to write code that discovers namespace relationships for the purpose of understanding the namespace setup on a running system. In particular, given a file descriptor (or pathname) for a namespace, N, I'd like to obtain the corresponding user namespace. Namespace N might be a user namespace (in which case my code would just use N) or a non-user namespace (in which case my code will use NS_GET_USERNS to get the user namespace associated with N). The problem is that there is no way to tell the difference by looking at the file descriptor (and if I try to use NS_GET_USERNS on an N that is a user namespace, I get the parent user namespace of N, which is not what I want). This patch therefore adds a new ioctl(), NS_GET_NSTYPE, which, given a file descriptor that refers to a user namespace, returns the namespace type (one of the CLONE_NEW* constants). Signed-off-by: Michael Kerrisk <mtk-manpages@gmail.com> Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2017-01-25 01:03:36 +00:00
case NS_GET_NSTYPE:
return ns->ops->type;
case NS_GET_OWNER_UID:
if (ns->ops->type != CLONE_NEWUSER)
return -EINVAL;
user_ns = container_of(ns, struct user_namespace, ns);
argp = (uid_t __user *) arg;
uid = from_kuid_munged(current_user_ns(), user_ns->owner);
return put_user(uid, argp);
default:
return -ENOTTY;
}
}
int ns_get_name(char *buf, size_t size, struct task_struct *task,
const struct proc_ns_operations *ns_ops)
{
struct ns_common *ns;
int res = -ENOENT;
ns: allow ns_entries to have custom symlink content Patch series "Expose task pid_ns_for_children to userspace". pid_ns_for_children set by a task is known only to the task itself, and it's impossible to identify it from outside. It's a big problem for checkpoint/restore software like CRIU, because it can't correctly handle tasks, that do setns(CLONE_NEWPID) in proccess of their work. If they have a custom pid_ns_for_children before dump, they must have the same ns after restore. Otherwise, restored task bumped into enviroment it does not expect. This patchset solves the problem. It exposes pid_ns_for_children to ns directory in standard way with the name "pid_for_children": ~# ls /proc/5531/ns -l | grep pid lrwxrwxrwx 1 root root 0 Jan 14 16:38 pid -> pid:[4026531836] lrwxrwxrwx 1 root root 0 Jan 14 16:38 pid_for_children -> pid:[4026532286] This patch (of 2): Make possible to have link content prefix yyy different from the link name xxx: $ readlink /proc/[pid]/ns/xxx yyy:[4026531838] This will be used in next patch. Link: http://lkml.kernel.org/r/149201120318.6007.7362655181033883000.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com> Reviewed-by: Cyrill Gorcunov <gorcunov@openvz.org> Acked-by: Andrei Vagin <avagin@virtuozzo.com> Cc: Andreas Gruenbacher <agruenba@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Michael Kerrisk <mtk.manpages@googlemail.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Paul Moore <paul@paul-moore.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Ingo Molnar <mingo@kernel.org> Cc: Serge Hallyn <serge@hallyn.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-08 22:56:38 +00:00
const char *name;
ns = ns_ops->get(task);
if (ns) {
ns: allow ns_entries to have custom symlink content Patch series "Expose task pid_ns_for_children to userspace". pid_ns_for_children set by a task is known only to the task itself, and it's impossible to identify it from outside. It's a big problem for checkpoint/restore software like CRIU, because it can't correctly handle tasks, that do setns(CLONE_NEWPID) in proccess of their work. If they have a custom pid_ns_for_children before dump, they must have the same ns after restore. Otherwise, restored task bumped into enviroment it does not expect. This patchset solves the problem. It exposes pid_ns_for_children to ns directory in standard way with the name "pid_for_children": ~# ls /proc/5531/ns -l | grep pid lrwxrwxrwx 1 root root 0 Jan 14 16:38 pid -> pid:[4026531836] lrwxrwxrwx 1 root root 0 Jan 14 16:38 pid_for_children -> pid:[4026532286] This patch (of 2): Make possible to have link content prefix yyy different from the link name xxx: $ readlink /proc/[pid]/ns/xxx yyy:[4026531838] This will be used in next patch. Link: http://lkml.kernel.org/r/149201120318.6007.7362655181033883000.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com> Reviewed-by: Cyrill Gorcunov <gorcunov@openvz.org> Acked-by: Andrei Vagin <avagin@virtuozzo.com> Cc: Andreas Gruenbacher <agruenba@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Michael Kerrisk <mtk.manpages@googlemail.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Paul Moore <paul@paul-moore.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Ingo Molnar <mingo@kernel.org> Cc: Serge Hallyn <serge@hallyn.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-08 22:56:38 +00:00
name = ns_ops->real_ns_name ? : ns_ops->name;
res = snprintf(buf, size, "%s:[%u]", name, ns->inum);
ns_ops->put(ns);
}
return res;
}
struct file *proc_ns_fget(int fd)
{
struct file *file;
file = fget(fd);
if (!file)
return ERR_PTR(-EBADF);
if (file->f_op != &ns_file_operations)
goto out_invalid;
return file;
out_invalid:
fput(file);
return ERR_PTR(-EINVAL);
}
static int nsfs_show_path(struct seq_file *seq, struct dentry *dentry)
{
struct inode *inode = d_inode(dentry);
const struct proc_ns_operations *ns_ops = dentry->d_fsdata;
seq_printf(seq, "%s:[%lu]", ns_ops->name, inode->i_ino);
return 0;
}
static const struct super_operations nsfs_ops = {
.statfs = simple_statfs,
.evict_inode = nsfs_evict,
.show_path = nsfs_show_path,
};
static struct dentry *nsfs_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
return mount_pseudo(fs_type, "nsfs:", &nsfs_ops,
&ns_dentry_operations, NSFS_MAGIC);
}
static struct file_system_type nsfs = {
.name = "nsfs",
.mount = nsfs_mount,
.kill_sb = kill_anon_super,
};
void __init nsfs_init(void)
{
nsfs_mnt = kern_mount(&nsfs);
if (IS_ERR(nsfs_mnt))
panic("can't set nsfs up\n");
nsfs_mnt->mnt_sb->s_flags &= ~MS_NOUSER;
}