mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-26 10:49:33 +00:00
![Linus Torvalds](/assets/img/avatar_default.png)
Pull vfs pile (part one) from Al Viro: "Assorted stuff - cleaning namei.c up a bit, fixing ->d_name/->d_parent locking violations, etc. The most visible changes here are death of FS_REVAL_DOT (replaced with "has ->d_weak_revalidate()") and a new helper getting from struct file to inode. Some bits of preparation to xattr method interface changes. Misc patches by various people sent this cycle *and* ocfs2 fixes from several cycles ago that should've been upstream right then. PS: the next vfs pile will be xattr stuff." * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (46 commits) saner proc_get_inode() calling conventions proc: avoid extra pde_put() in proc_fill_super() fs: change return values from -EACCES to -EPERM fs/exec.c: make bprm_mm_init() static ocfs2/dlm: use GFP_ATOMIC inside a spin_lock ocfs2: fix possible use-after-free with AIO ocfs2: Fix oops in ocfs2_fast_symlink_readpage() code path get_empty_filp()/alloc_file() leave both ->f_pos and ->f_version zero target: writev() on single-element vector is pointless export kernel_write(), convert open-coded instances fs: encode_fh: return FILEID_INVALID if invalid fid_type kill f_vfsmnt vfs: kill FS_REVAL_DOT by adding a d_weak_revalidate dentry op nfsd: handle vfs_getattr errors in acl protocol switch vfs_getattr() to struct path default SET_PERSONALITY() in linux/elf.h ceph: prepopulate inodes only when request is aborted d_hash_and_lookup(): export, switch open-coded instances 9p: switch v9fs_set_create_acl() to inode+fid, do it before d_instantiate() 9p: split dropping the acls from v9fs_set_create_acl() ...
279 lines
6.2 KiB
C
279 lines
6.2 KiB
C
/*
|
|
* Copyright (C) 2006 IBM Corporation
|
|
*
|
|
* Author: Serge Hallyn <serue@us.ibm.com>
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License as
|
|
* published by the Free Software Foundation, version 2 of the
|
|
* License.
|
|
*
|
|
* Jun 2006 - namespaces support
|
|
* OpenVZ, SWsoft Inc.
|
|
* Pavel Emelianov <xemul@openvz.org>
|
|
*/
|
|
|
|
#include <linux/slab.h>
|
|
#include <linux/export.h>
|
|
#include <linux/nsproxy.h>
|
|
#include <linux/init_task.h>
|
|
#include <linux/mnt_namespace.h>
|
|
#include <linux/utsname.h>
|
|
#include <linux/pid_namespace.h>
|
|
#include <net/net_namespace.h>
|
|
#include <linux/ipc_namespace.h>
|
|
#include <linux/proc_fs.h>
|
|
#include <linux/file.h>
|
|
#include <linux/syscalls.h>
|
|
|
|
static struct kmem_cache *nsproxy_cachep;
|
|
|
|
struct nsproxy init_nsproxy = {
|
|
.count = ATOMIC_INIT(1),
|
|
.uts_ns = &init_uts_ns,
|
|
#if defined(CONFIG_POSIX_MQUEUE) || defined(CONFIG_SYSVIPC)
|
|
.ipc_ns = &init_ipc_ns,
|
|
#endif
|
|
.mnt_ns = NULL,
|
|
.pid_ns = &init_pid_ns,
|
|
#ifdef CONFIG_NET
|
|
.net_ns = &init_net,
|
|
#endif
|
|
};
|
|
|
|
static inline struct nsproxy *create_nsproxy(void)
|
|
{
|
|
struct nsproxy *nsproxy;
|
|
|
|
nsproxy = kmem_cache_alloc(nsproxy_cachep, GFP_KERNEL);
|
|
if (nsproxy)
|
|
atomic_set(&nsproxy->count, 1);
|
|
return nsproxy;
|
|
}
|
|
|
|
/*
|
|
* Create new nsproxy and all of its the associated namespaces.
|
|
* Return the newly created nsproxy. Do not attach this to the task,
|
|
* leave it to the caller to do proper locking and attach it to task.
|
|
*/
|
|
static struct nsproxy *create_new_namespaces(unsigned long flags,
|
|
struct task_struct *tsk, struct user_namespace *user_ns,
|
|
struct fs_struct *new_fs)
|
|
{
|
|
struct nsproxy *new_nsp;
|
|
int err;
|
|
|
|
new_nsp = create_nsproxy();
|
|
if (!new_nsp)
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
new_nsp->mnt_ns = copy_mnt_ns(flags, tsk->nsproxy->mnt_ns, user_ns, new_fs);
|
|
if (IS_ERR(new_nsp->mnt_ns)) {
|
|
err = PTR_ERR(new_nsp->mnt_ns);
|
|
goto out_ns;
|
|
}
|
|
|
|
new_nsp->uts_ns = copy_utsname(flags, user_ns, tsk->nsproxy->uts_ns);
|
|
if (IS_ERR(new_nsp->uts_ns)) {
|
|
err = PTR_ERR(new_nsp->uts_ns);
|
|
goto out_uts;
|
|
}
|
|
|
|
new_nsp->ipc_ns = copy_ipcs(flags, user_ns, tsk->nsproxy->ipc_ns);
|
|
if (IS_ERR(new_nsp->ipc_ns)) {
|
|
err = PTR_ERR(new_nsp->ipc_ns);
|
|
goto out_ipc;
|
|
}
|
|
|
|
new_nsp->pid_ns = copy_pid_ns(flags, user_ns, tsk->nsproxy->pid_ns);
|
|
if (IS_ERR(new_nsp->pid_ns)) {
|
|
err = PTR_ERR(new_nsp->pid_ns);
|
|
goto out_pid;
|
|
}
|
|
|
|
new_nsp->net_ns = copy_net_ns(flags, user_ns, tsk->nsproxy->net_ns);
|
|
if (IS_ERR(new_nsp->net_ns)) {
|
|
err = PTR_ERR(new_nsp->net_ns);
|
|
goto out_net;
|
|
}
|
|
|
|
return new_nsp;
|
|
|
|
out_net:
|
|
if (new_nsp->pid_ns)
|
|
put_pid_ns(new_nsp->pid_ns);
|
|
out_pid:
|
|
if (new_nsp->ipc_ns)
|
|
put_ipc_ns(new_nsp->ipc_ns);
|
|
out_ipc:
|
|
if (new_nsp->uts_ns)
|
|
put_uts_ns(new_nsp->uts_ns);
|
|
out_uts:
|
|
if (new_nsp->mnt_ns)
|
|
put_mnt_ns(new_nsp->mnt_ns);
|
|
out_ns:
|
|
kmem_cache_free(nsproxy_cachep, new_nsp);
|
|
return ERR_PTR(err);
|
|
}
|
|
|
|
/*
|
|
* called from clone. This now handles copy for nsproxy and all
|
|
* namespaces therein.
|
|
*/
|
|
int copy_namespaces(unsigned long flags, struct task_struct *tsk)
|
|
{
|
|
struct nsproxy *old_ns = tsk->nsproxy;
|
|
struct user_namespace *user_ns = task_cred_xxx(tsk, user_ns);
|
|
struct nsproxy *new_ns;
|
|
int err = 0;
|
|
|
|
if (!old_ns)
|
|
return 0;
|
|
|
|
get_nsproxy(old_ns);
|
|
|
|
if (!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
|
|
CLONE_NEWPID | CLONE_NEWNET)))
|
|
return 0;
|
|
|
|
if (!ns_capable(user_ns, CAP_SYS_ADMIN)) {
|
|
err = -EPERM;
|
|
goto out;
|
|
}
|
|
|
|
/*
|
|
* CLONE_NEWIPC must detach from the undolist: after switching
|
|
* to a new ipc namespace, the semaphore arrays from the old
|
|
* namespace are unreachable. In clone parlance, CLONE_SYSVSEM
|
|
* means share undolist with parent, so we must forbid using
|
|
* it along with CLONE_NEWIPC.
|
|
*/
|
|
if ((flags & CLONE_NEWIPC) && (flags & CLONE_SYSVSEM)) {
|
|
err = -EINVAL;
|
|
goto out;
|
|
}
|
|
|
|
new_ns = create_new_namespaces(flags, tsk, user_ns, tsk->fs);
|
|
if (IS_ERR(new_ns)) {
|
|
err = PTR_ERR(new_ns);
|
|
goto out;
|
|
}
|
|
|
|
tsk->nsproxy = new_ns;
|
|
|
|
out:
|
|
put_nsproxy(old_ns);
|
|
return err;
|
|
}
|
|
|
|
void free_nsproxy(struct nsproxy *ns)
|
|
{
|
|
if (ns->mnt_ns)
|
|
put_mnt_ns(ns->mnt_ns);
|
|
if (ns->uts_ns)
|
|
put_uts_ns(ns->uts_ns);
|
|
if (ns->ipc_ns)
|
|
put_ipc_ns(ns->ipc_ns);
|
|
if (ns->pid_ns)
|
|
put_pid_ns(ns->pid_ns);
|
|
put_net(ns->net_ns);
|
|
kmem_cache_free(nsproxy_cachep, ns);
|
|
}
|
|
|
|
/*
|
|
* Called from unshare. Unshare all the namespaces part of nsproxy.
|
|
* On success, returns the new nsproxy.
|
|
*/
|
|
int unshare_nsproxy_namespaces(unsigned long unshare_flags,
|
|
struct nsproxy **new_nsp, struct cred *new_cred, struct fs_struct *new_fs)
|
|
{
|
|
struct user_namespace *user_ns;
|
|
int err = 0;
|
|
|
|
if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
|
|
CLONE_NEWNET | CLONE_NEWPID)))
|
|
return 0;
|
|
|
|
user_ns = new_cred ? new_cred->user_ns : current_user_ns();
|
|
if (!ns_capable(user_ns, CAP_SYS_ADMIN))
|
|
return -EPERM;
|
|
|
|
*new_nsp = create_new_namespaces(unshare_flags, current, user_ns,
|
|
new_fs ? new_fs : current->fs);
|
|
if (IS_ERR(*new_nsp)) {
|
|
err = PTR_ERR(*new_nsp);
|
|
goto out;
|
|
}
|
|
|
|
out:
|
|
return err;
|
|
}
|
|
|
|
void switch_task_namespaces(struct task_struct *p, struct nsproxy *new)
|
|
{
|
|
struct nsproxy *ns;
|
|
|
|
might_sleep();
|
|
|
|
ns = p->nsproxy;
|
|
|
|
rcu_assign_pointer(p->nsproxy, new);
|
|
|
|
if (ns && atomic_dec_and_test(&ns->count)) {
|
|
/*
|
|
* wait for others to get what they want from this nsproxy.
|
|
*
|
|
* cannot release this nsproxy via the call_rcu() since
|
|
* put_mnt_ns() will want to sleep
|
|
*/
|
|
synchronize_rcu();
|
|
free_nsproxy(ns);
|
|
}
|
|
}
|
|
|
|
void exit_task_namespaces(struct task_struct *p)
|
|
{
|
|
switch_task_namespaces(p, NULL);
|
|
}
|
|
|
|
SYSCALL_DEFINE2(setns, int, fd, int, nstype)
|
|
{
|
|
const struct proc_ns_operations *ops;
|
|
struct task_struct *tsk = current;
|
|
struct nsproxy *new_nsproxy;
|
|
struct proc_inode *ei;
|
|
struct file *file;
|
|
int err;
|
|
|
|
file = proc_ns_fget(fd);
|
|
if (IS_ERR(file))
|
|
return PTR_ERR(file);
|
|
|
|
err = -EINVAL;
|
|
ei = PROC_I(file_inode(file));
|
|
ops = ei->ns_ops;
|
|
if (nstype && (ops->type != nstype))
|
|
goto out;
|
|
|
|
new_nsproxy = create_new_namespaces(0, tsk, current_user_ns(), tsk->fs);
|
|
if (IS_ERR(new_nsproxy)) {
|
|
err = PTR_ERR(new_nsproxy);
|
|
goto out;
|
|
}
|
|
|
|
err = ops->install(new_nsproxy, ei->ns);
|
|
if (err) {
|
|
free_nsproxy(new_nsproxy);
|
|
goto out;
|
|
}
|
|
switch_task_namespaces(tsk, new_nsproxy);
|
|
out:
|
|
fput(file);
|
|
return err;
|
|
}
|
|
|
|
int __init nsproxy_cache_init(void)
|
|
{
|
|
nsproxy_cachep = KMEM_CACHE(nsproxy, SLAB_PANIC);
|
|
return 0;
|
|
}
|