diff --git a/fs/namespace.c b/fs/namespace.c
index 62899fad4a04046f33ae7cdd1479d81a4c554da1..be99e80e3c7c4e4ea24855b05bff2ecb3bae209c 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1733,6 +1733,11 @@ static struct mnt_namespace *to_mnt_ns(struct ns_common *ns)
return container_of(ns, struct mnt_namespace, ns);
}
+struct ns_common *from_mnt_ns(struct mnt_namespace *mnt)
+{
+ return &mnt->ns;
+}
+
static bool mnt_ns_loop(struct dentry *dentry)
{
/* Could bind mounting the mount namespace inode cause a
diff --git a/fs/nsfs.c b/fs/nsfs.c
index 4f1205725cfef03ebf82e327c08f9737bc20ae42..800c1d0eb0d026e40604e465df209cc11051e79f 100644
--- a/fs/nsfs.c
+++ b/fs/nsfs.c
@@ -229,6 +229,11 @@ int ns_get_name(char *buf, size_t size, struct task_struct *task,
return res;
}
+bool proc_ns_file(const struct file *file)
+{
+ return file->f_op == &ns_file_operations;
+}
+
struct file *proc_ns_fget(int fd)
{
struct file *file;
diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h
index 007cfa52efb23093af98b55078f2c160faec17c2..8f882f5881e8797d72bd38c9e693899cc25d1d22 100644
--- a/include/linux/mnt_namespace.h
+++ b/include/linux/mnt_namespace.h
@@ -11,6 +11,7 @@ struct ns_common;
extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *,
struct user_namespace *, struct fs_struct *);
extern void put_mnt_ns(struct mnt_namespace *ns);
+extern struct ns_common *from_mnt_ns(struct mnt_namespace *);
extern const struct file_operations proc_mounts_operations;
extern const struct file_operations proc_mountinfo_operations;
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 45c05fd9c99dc67bfacd75560fc2499b3cc4f1ca..0cfc44d7ac743ed853d660bc92e29707904a604e 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -179,4 +179,6 @@ static inline struct pid_namespace *proc_pid_ns(const struct inode *inode)
return inode->i_sb->s_fs_info;
}
+bool proc_ns_file(const struct file *file);
+
#endif /* _LINUX_PROC_FS_H */
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index b7954fd604753863d296e4063c2b8159a68c9e41..b03df67621d01fd6400722c608185a41effbf716 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -20,6 +20,7 @@
#include <linux/ipc_namespace.h>
#include <linux/time_namespace.h>
#include <linux/fs_struct.h>
+#include <linux/proc_fs.h>
#include <linux/proc_ns.h>
#include <linux/file.h>
#include <linux/syscalls.h>
@@ -258,17 +259,58 @@ void exit_task_namespaces(struct task_struct *p)
switch_task_namespaces(p, NULL);
}
+static int check_setns_flags(unsigned long flags)
+{
+ if (!flags || (flags & ~(CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
+ CLONE_NEWNET | CLONE_NEWUSER | CLONE_NEWPID |
+ CLONE_NEWCGROUP)))
+ return -EINVAL;
+
+#ifndef CONFIG_USER_NS
+ if (flags & CLONE_NEWUSER)
+ return -EINVAL;
+#endif
+#ifndef CONFIG_PID_NS
+ if (flags & CLONE_NEWPID)
+ return -EINVAL;
+#endif
+#ifndef CONFIG_UTS_NS
+ if (flags & CLONE_NEWUTS)
+ return -EINVAL;
+#endif
+#ifndef CONFIG_IPC_NS
+ if (flags & CLONE_NEWIPC)
+ return -EINVAL;
+#endif
+#ifndef CONFIG_CGROUPS
+ if (flags & CLONE_NEWCGROUP)
+ return -EINVAL;
+#endif
+#ifndef CONFIG_NET_NS
+ if (flags & CLONE_NEWNET)
+ return -EINVAL;
+#endif
+
+ return 0;
+}
+
static void put_nsset(struct nsset *nsset)
{
unsigned flags = nsset->flags;
if (flags & CLONE_NEWUSER)
put_cred(nsset_cred(nsset));
+ /*
+ * We only created a temporary copy if we attached to more than just
+ * the mount namespace.
+ */
+ if (nsset->fs && (flags & CLONE_NEWNS) && (flags & ~CLONE_NEWNS))
+ free_fs_struct(nsset->fs);
if (nsset->nsproxy)
free_nsproxy(nsset->nsproxy);
}
-static int prepare_nsset(int nstype, struct nsset *nsset)
+static int prepare_nsset(unsigned flags, struct nsset *nsset)
{
struct task_struct *me = current;
@@ -276,17 +318,23 @@ static int prepare_nsset(int nstype, struct nsset *nsset)
if (IS_ERR(nsset->nsproxy))
return PTR_ERR(nsset->nsproxy);
- if (nstype == CLONE_NEWUSER)
+ if (flags & CLONE_NEWUSER)
nsset->cred = prepare_creds();
else
nsset->cred = current_cred();
if (!nsset->cred)
goto out;
- if (nstype == CLONE_NEWNS)
+ /* Only create a temporary copy of fs_struct if we really need to. */
+ if (flags == CLONE_NEWNS) {
nsset->fs = me->fs;
+ } else if (flags & CLONE_NEWNS) {
+ nsset->fs = copy_fs_struct(me->fs);
+ if (!nsset->fs)
+ goto out;
+ }
- nsset->flags = nstype;
+ nsset->flags = flags;
return 0;
out:
@@ -294,6 +342,138 @@ static int prepare_nsset(int nstype, struct nsset *nsset)
return -ENOMEM;
}
+static inline int validate_ns(struct nsset *nsset, struct ns_common *ns)
+{
+ return ns->ops->install(nsset, ns);
+}
+
+/*
+ * This is the inverse operation to unshare().
+ * Ordering is equivalent to the standard ordering used everywhere else
+ * during unshare and process creation. The switch to the new set of
+ * namespaces occurs at the point of no return after installation of
+ * all requested namespaces was successful in commit_nsset().
+ */
+static int validate_nsset(struct nsset *nsset, struct pid *pid)
+{
+ int ret = 0;
+ unsigned flags = nsset->flags;
+ struct user_namespace *user_ns = NULL;
+ struct pid_namespace *pid_ns = NULL;
+ struct nsproxy *nsp;
+ struct task_struct *tsk;
+
+ /* Take a "snapshot" of the target task's namespaces. */
+ rcu_read_lock();
+ tsk = pid_task(pid, PIDTYPE_PID);
+ if (!tsk) {
+ rcu_read_unlock();
+ return -ESRCH;
+ }
+
+ if (!ptrace_may_access(tsk, PTRACE_MODE_READ_REALCREDS)) {
+ rcu_read_unlock();
+ return -EPERM;
+ }
+
+ task_lock(tsk);
+ nsp = tsk->nsproxy;
+ if (nsp)
+ get_nsproxy(nsp);
+ task_unlock(tsk);
+ if (!nsp) {
+ rcu_read_unlock();
+ return -ESRCH;
+ }
+
+#ifdef CONFIG_PID_NS
+ if (flags & CLONE_NEWPID) {
+ pid_ns = task_active_pid_ns(tsk);
+ if (unlikely(!pid_ns)) {
+ rcu_read_unlock();
+ ret = -ESRCH;
+ goto out;
+ }
+ get_pid_ns(pid_ns);
+ }
+#endif
+
+#ifdef CONFIG_USER_NS
+ if (flags & CLONE_NEWUSER)
+ user_ns = get_user_ns(__task_cred(tsk)->user_ns);
+#endif
+ rcu_read_unlock();
+
+ /*
+ * Install requested namespaces. The caller will have
+ * verified earlier that the requested namespaces are
+ * supported on this kernel. We don't report errors here
+ * if a namespace is requested that isn't supported.
+ */
+#ifdef CONFIG_USER_NS
+ if (flags & CLONE_NEWUSER) {
+ ret = validate_ns(nsset, &user_ns->ns);
+ if (ret)
+ goto out;
+ }
+#endif
+
+ if (flags & CLONE_NEWNS) {
+ ret = validate_ns(nsset, from_mnt_ns(nsp->mnt_ns));
+ if (ret)
+ goto out;
+ }
+
+#ifdef CONFIG_UTS_NS
+ if (flags & CLONE_NEWUTS) {
+ ret = validate_ns(nsset, &nsp->uts_ns->ns);
+ if (ret)
+ goto out;
+ }
+#endif
+
+#ifdef CONFIG_IPC_NS
+ if (flags & CLONE_NEWIPC) {
+ ret = validate_ns(nsset, &nsp->ipc_ns->ns);
+ if (ret)
+ goto out;
+ }
+#endif
+
+#ifdef CONFIG_PID_NS
+ if (flags & CLONE_NEWPID) {
+ ret = validate_ns(nsset, &pid_ns->ns);
+ if (ret)
+ goto out;
+ }
+#endif
+
+#ifdef CONFIG_CGROUPS
+ if (flags & CLONE_NEWCGROUP) {
+ ret = validate_ns(nsset, &nsp->cgroup_ns->ns);
+ if (ret)
+ goto out;
+ }
+#endif
+
+#ifdef CONFIG_NET_NS
+ if (flags & CLONE_NEWNET) {
+ ret = validate_ns(nsset, &nsp->net_ns->ns);
+ if (ret)
+ goto out;
+ }
+#endif
+
+out:
+ if (pid_ns)
+ put_pid_ns(pid_ns);
+ if (nsp)
+ put_nsproxy(nsp);
+ put_user_ns(user_ns);
+
+ return ret;
+}
+
/*
* This is the point of no return. There are just a few namespaces
* that do some actual work here and it's sufficiently minimal that
@@ -316,6 +496,12 @@ static void commit_nsset(struct nsset *nsset)
}
#endif
+ /* We only need to commit if we have used a temporary fs_struct. */
+ if ((flags & CLONE_NEWNS) && (flags & ~CLONE_NEWNS)) {
+ set_fs_root(me->fs, &nsset->fs->root);
+ set_fs_pwd(me->fs, &nsset->fs->pwd);
+ }
+
#ifdef CONFIG_IPC_NS
if (flags & CLONE_NEWIPC)
exit_sem(me);
@@ -326,27 +512,38 @@ static void commit_nsset(struct nsset *nsset)
nsset->nsproxy = NULL;
}
-SYSCALL_DEFINE2(setns, int, fd, int, nstype)
+SYSCALL_DEFINE2(setns, int, fd, int, flags)
{
struct file *file;
- struct ns_common *ns;
+ struct ns_common *ns = NULL;
struct nsset nsset = {};
- int err;
-
- file = proc_ns_fget(fd);
- if (IS_ERR(file))
- return PTR_ERR(file);
+ int err = 0;
- err = -EINVAL;
- ns = get_proc_ns(file_inode(file));
- if (nstype && (ns->ops->type != nstype))
+ file = fget(fd);
+ if (!file)
+ return -EBADF;
+
+ if (proc_ns_file(file)) {
+ ns = get_proc_ns(file_inode(file));
+ if (flags && (ns->ops->type != flags))
+ err = -EINVAL;
+ flags = ns->ops->type;
+ } else if (!IS_ERR(pidfd_pid(file))) {
+ err = check_setns_flags(flags);
+ } else {
+ err = -EBADF;
+ }
+ if (err)
goto out;
- err = prepare_nsset(ns->ops->type, &nsset);
+ err = prepare_nsset(flags, &nsset);
if (err)
goto out;
- err = ns->ops->install(&nsset, ns);
+ if (proc_ns_file(file))
+ err = validate_ns(&nsset, ns);
+ else
+ err = validate_nsset(&nsset, file->private_data);
if (!err) {
commit_nsset(&nsset);
perf_event_namespaces(current);