Merge tag 'threads-v5.8' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux

Pull thread updates from Christian Brauner:
 "We have been discussing using pidfds to attach to namespaces for quite
  a while and the patches have in one form or another already existed
  for about a year. But I wanted to wait to see how the general api
  would be received and adopted.

  This contains the changes to make it possible to use pidfds to attach
  to the namespaces of a process, i.e. they can be passed as the first
  argument to the setns() syscall.

  When only a single namespace type is specified the semantics are
  equivalent to passing an nsfd. That means setns(nsfd, CLONE_NEWNET)
  equals setns(pidfd, CLONE_NEWNET).

  However, when a pidfd is passed, multiple namespace flags can be
  specified in the second setns() argument and setns() will attach the
  caller to all the specified namespaces all at once or to none of them.

  Specifying 0 is not valid together with a pidfd. Here are just two
  obvious examples:

    setns(pidfd, CLONE_NEWPID | CLONE_NEWNS | CLONE_NEWNET);
    setns(pidfd, CLONE_NEWUSER);

  Allowing to also attach subsets of namespaces supports various
  use-cases where callers setns to a subset of namespaces to retain
  privilege, perform an action and then re-attach another subset of
  namespaces.

  Apart from significantly reducing the number of syscalls needed to
  attach to all currently supported namespaces (eight "open+setns"
  sequences vs just a single "setns()"), this also allows atomic setns
  to a set of namespaces, i.e. either attaching to all namespaces
  succeeds or we fail without having changed anything.

  This is centered around a new internal struct nsset which holds all
  information necessary for a task to switch to a new set of namespaces
  atomically. Fwiw, with this change a pidfd becomes the only token
  needed to interact with a container. I'm expecting this to be
  picked-up by util-linux for nsenter rather soon.

  Associated with this change is a shiny new test-suite dedicated to
  setns() (for pidfds and nsfds alike)"

* tag 'threads-v5.8' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux:
  selftests/pidfd: add pidfd setns tests
  nsproxy: attach to namespaces via pidfds
  nsproxy: add struct nsset

6 files changed, 299 insertions, 34 deletions

diff --git a/kernel/cgroup/namespace.c b/kernel/cgroup/namespace.c
index b05f1dd58a62..812a61afd538 100644
--- a/kernel/cgroup/namespace.c
+++ b/kernel/cgroup/namespace.c
@@ -95,11 +95,12 @@ static inline struct cgroup_namespace *to_cg_ns(struct ns_common *ns)
 	return container_of(ns, struct cgroup_namespace, ns);
 }
 
-static int cgroupns_install(struct nsproxy *nsproxy, struct ns_common *ns)
+static int cgroupns_install(struct nsset *nsset, struct ns_common *ns)
 {
+	struct nsproxy *nsproxy = nsset->nsproxy;
 	struct cgroup_namespace *cgroup_ns = to_cg_ns(ns);
 
-	if (!ns_capable(current_user_ns(), CAP_SYS_ADMIN) ||
+	if (!ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN) ||
 	    !ns_capable(cgroup_ns->user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index ed9882108cd2..b03df67621d0 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -19,6 +19,8 @@
 #include <net/net_namespace.h>
 #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>
@@ -257,37 +259,296 @@ void exit_task_namespaces(struct task_struct *p)
 	switch_task_namespaces(p, NULL);
 }
 
-SYSCALL_DEFINE2(setns, int, fd, int, nstype)
+static int check_setns_flags(unsigned long flags)
 {
-	struct task_struct *tsk = current;
-	struct nsproxy *new_nsproxy;
-	struct file *file;
-	struct ns_common *ns;
-	int err;
+	if (!flags || (flags & ~(CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
+				 CLONE_NEWNET | CLONE_NEWUSER | CLONE_NEWPID |
+				 CLONE_NEWCGROUP)))
+		return -EINVAL;
 
-	file = proc_ns_fget(fd);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
+#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
 
-	err = -EINVAL;
-	ns = get_proc_ns(file_inode(file));
-	if (nstype && (ns->ops->type != nstype))
-		goto out;
+	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(unsigned flags, struct nsset *nsset)
+{
+	struct task_struct *me = current;
+
+	nsset->nsproxy = create_new_namespaces(0, me, current_user_ns(), me->fs);
+	if (IS_ERR(nsset->nsproxy))
+		return PTR_ERR(nsset->nsproxy);
 
-	new_nsproxy = create_new_namespaces(0, tsk, current_user_ns(), tsk->fs);
-	if (IS_ERR(new_nsproxy)) {
-		err = PTR_ERR(new_nsproxy);
+	if (flags & CLONE_NEWUSER)
+		nsset->cred = prepare_creds();
+	else
+		nsset->cred = current_cred();
+	if (!nsset->cred)
 		goto out;
+
+	/* 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;
 	}
 
-	err = ns->ops->install(new_nsproxy, ns);
-	if (err) {
-		free_nsproxy(new_nsproxy);
-		goto out;
+	nsset->flags = flags;
+	return 0;
+
+out:
+	put_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
+ * a separate ns_common operation seems unnecessary for now.
+ * Unshare is doing the same thing. If we'll end up needing to do
+ * more in a given namespace or a helper here is ultimately not
+ * exported anymore a simple commit handler for each namespace
+ * should be added to ns_common.
+ */
+static void commit_nsset(struct nsset *nsset)
+{
+	unsigned flags = nsset->flags;
+	struct task_struct *me = current;
+
+#ifdef CONFIG_USER_NS
+	if (flags & CLONE_NEWUSER) {
+		/* transfer ownership */
+		commit_creds(nsset_cred(nsset));
+		nsset->cred = NULL;
+	}
+#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);
 	}
-	switch_task_namespaces(tsk, new_nsproxy);
 
-	perf_event_namespaces(tsk);
+#ifdef CONFIG_IPC_NS
+	if (flags & CLONE_NEWIPC)
+		exit_sem(me);
+#endif
+
+	/* transfer ownership */
+	switch_task_namespaces(me, nsset->nsproxy);
+	nsset->nsproxy = NULL;
+}
+
+SYSCALL_DEFINE2(setns, int, fd, int, flags)
+{
+	struct file *file;
+	struct ns_common *ns = NULL;
+	struct nsset nsset = {};
+	int err = 0;
+
+	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(flags, &nsset);
+	if (err)
+		goto out;
+
+	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);
+	}
+	put_nsset(&nsset);
 out:
 	fput(file);
 	return err;
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 01f8ba32cc0c..11db2bdbb41e 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -378,13 +378,14 @@ static void pidns_put(struct ns_common *ns)
 	put_pid_ns(to_pid_ns(ns));
 }
 
-static int pidns_install(struct nsproxy *nsproxy, struct ns_common *ns)
+static int pidns_install(struct nsset *nsset, struct ns_common *ns)
 {
+	struct nsproxy *nsproxy = nsset->nsproxy;
 	struct pid_namespace *active = task_active_pid_ns(current);
 	struct pid_namespace *ancestor, *new = to_pid_ns(ns);
 
 	if (!ns_capable(new->user_ns, CAP_SYS_ADMIN) ||
-	    !ns_capable(current_user_ns(), CAP_SYS_ADMIN))
+	    !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
 	/*
diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
index 53bce347cd50..5d9fc22d836a 100644
--- a/kernel/time/namespace.c
+++ b/kernel/time/namespace.c
@@ -280,8 +280,9 @@ static void timens_put(struct ns_common *ns)
 	put_time_ns(to_time_ns(ns));
 }
 
-static int timens_install(struct nsproxy *nsproxy, struct ns_common *new)
+static int timens_install(struct nsset *nsset, struct ns_common *new)
 {
+	struct nsproxy *nsproxy = nsset->nsproxy;
 	struct time_namespace *ns = to_time_ns(new);
 	int err;
 
@@ -289,7 +290,7 @@ static int timens_install(struct nsproxy *nsproxy, struct ns_common *new)
 		return -EUSERS;
 
 	if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) ||
-	    !ns_capable(current_user_ns(), CAP_SYS_ADMIN))
+	    !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
 	timens_set_vvar_page(current, ns);
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 8eadadc478f9..87804e0371fe 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -1253,7 +1253,7 @@ static void userns_put(struct ns_common *ns)
 	put_user_ns(to_user_ns(ns));
 }
 
-static int userns_install(struct nsproxy *nsproxy, struct ns_common *ns)
+static int userns_install(struct nsset *nsset, struct ns_common *ns)
 {
 	struct user_namespace *user_ns = to_user_ns(ns);
 	struct cred *cred;
@@ -1274,14 +1274,14 @@ static int userns_install(struct nsproxy *nsproxy, struct ns_common *ns)
 	if (!ns_capable(user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
-	cred = prepare_creds();
+	cred = nsset_cred(nsset);
 	if (!cred)
-		return -ENOMEM;
+		return -EINVAL;
 
 	put_user_ns(cred->user_ns);
 	set_cred_user_ns(cred, get_user_ns(user_ns));
 
-	return commit_creds(cred);
+	return 0;
 }
 
 struct ns_common *ns_get_owner(struct ns_common *ns)
diff --git a/kernel/utsname.c b/kernel/utsname.c
index f0e491193009..e488d0e2ab45 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -140,12 +140,13 @@ static void utsns_put(struct ns_common *ns)
 	put_uts_ns(to_uts_ns(ns));
 }
 
-static int utsns_install(struct nsproxy *nsproxy, struct ns_common *new)
+static int utsns_install(struct nsset *nsset, struct ns_common *new)
 {
+	struct nsproxy *nsproxy = nsset->nsproxy;
 	struct uts_namespace *ns = to_uts_ns(new);
 
 	if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) ||
-	    !ns_capable(current_user_ns(), CAP_SYS_ADMIN))
+	    !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
 	get_uts_ns(ns);