seccomp: add a return code to trap to userspace

This patch introduces a means for syscalls matched in seccomp to notify
some other task that a particular filter has been triggered.

The motivation for this is primarily for use with containers. For example,
if a container does an init_module(), we obviously don't want to load this
untrusted code, which may be compiled for the wrong version of the kernel
anyway. Instead, we could parse the module image, figure out which module
the container is trying to load and load it on the host.

As another example, containers cannot mount() in general since various
filesystems assume a trusted image. However, if an orchestrator knows that
e.g. a particular block device has not been exposed to a container for
writing, it want to allow the container to mount that block device (that
is, handle the mount for it).

This patch adds functionality that is already possible via at least two
other means that I know about, both of which involve ptrace(): first, one
could ptrace attach, and then iterate through syscalls via PTRACE_SYSCALL.
Unfortunately this is slow, so a faster version would be to install a
filter that does SECCOMP_RET_TRACE, which triggers a PTRACE_EVENT_SECCOMP.
Since ptrace allows only one tracer, if the container runtime is that
tracer, users inside the container (or outside) trying to debug it will not
be able to use ptrace, which is annoying. It also means that older
distributions based on Upstart cannot boot inside containers using ptrace,
since upstart itself uses ptrace to monitor services while starting.

The actual implementation of this is fairly small, although getting the
synchronization right was/is slightly complex.

Finally, it's worth noting that the classic seccomp TOCTOU of reading
memory data from the task still applies here, but can be avoided with
careful design of the userspace handler: if the userspace handler reads all
of the task memory that is necessary before applying its security policy,
the tracee's subsequent memory edits will not be read by the tracer.

Signed-off-by: Tycho Andersen <tycho@tycho.ws>
CC: Kees Cook <keescook@chromium.org>
CC: Andy Lutomirski <luto@amacapital.net>
CC: Oleg Nesterov <oleg@redhat.com>
CC: Eric W. Biederman <ebiederm@xmission.com>
CC: "Serge E. Hallyn" <serge@hallyn.com>
Acked-by: Serge Hallyn <serge@hallyn.com>
CC: Christian Brauner <christian@brauner.io>
CC: Tyler Hicks <tyhicks@canonical.com>
CC: Akihiro Suda <suda.akihiro@lab.ntt.co.jp>
Signed-off-by: Kees Cook <keescook@chromium.org>

1 files changed, 446 insertions, 2 deletions

diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 393e029f778a..15b6be97fc09 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -33,12 +33,74 @@
 #endif
 
 #ifdef CONFIG_SECCOMP_FILTER
+#include <linux/file.h>
 #include <linux/filter.h>
 #include <linux/pid.h>
 #include <linux/ptrace.h>
 #include <linux/security.h>
 #include <linux/tracehook.h>
 #include <linux/uaccess.h>
+#include <linux/anon_inodes.h>
+
+enum notify_state {
+	SECCOMP_NOTIFY_INIT,
+	SECCOMP_NOTIFY_SENT,
+	SECCOMP_NOTIFY_REPLIED,
+};
+
+struct seccomp_knotif {
+	/* The struct pid of the task whose filter triggered the notification */
+	struct task_struct *task;
+
+	/* The "cookie" for this request; this is unique for this filter. */
+	u64 id;
+
+	/*
+	 * The seccomp data. This pointer is valid the entire time this
+	 * notification is active, since it comes from __seccomp_filter which
+	 * eclipses the entire lifecycle here.
+	 */
+	const struct seccomp_data *data;
+
+	/*
+	 * Notification states. When SECCOMP_RET_USER_NOTIF is returned, a
+	 * struct seccomp_knotif is created and starts out in INIT. Once the
+	 * handler reads the notification off of an FD, it transitions to SENT.
+	 * If a signal is received the state transitions back to INIT and
+	 * another message is sent. When the userspace handler replies, state
+	 * transitions to REPLIED.
+	 */
+	enum notify_state state;
+
+	/* The return values, only valid when in SECCOMP_NOTIFY_REPLIED */
+	int error;
+	long val;
+
+	/* Signals when this has entered SECCOMP_NOTIFY_REPLIED */
+	struct completion ready;
+
+	struct list_head list;
+};
+
+/**
+ * struct notification - container for seccomp userspace notifications. Since
+ * most seccomp filters will not have notification listeners attached and this
+ * structure is fairly large, we store the notification-specific stuff in a
+ * separate structure.
+ *
+ * @request: A semaphore that users of this notification can wait on for
+ *           changes. Actual reads and writes are still controlled with
+ *           filter->notify_lock.
+ * @next_id: The id of the next request.
+ * @notifications: A list of struct seccomp_knotif elements.
+ * @wqh: A wait queue for poll.
+ */
+struct notification {
+	struct semaphore request;
+	u64 next_id;
+	struct list_head notifications;
+	wait_queue_head_t wqh;
+};
 
 /**
  * struct seccomp_filter - container for seccomp BPF programs
@@ -50,6 +112,8 @@
  * @log: true if all actions except for SECCOMP_RET_ALLOW should be logged
  * @prev: points to a previously installed, or inherited, filter
  * @prog: the BPF program to evaluate
+ * @notif: the struct that holds all notification related information
+ * @notify_lock: A lock for all notification-related accesses.
  *
  * seccomp_filter objects are organized in a tree linked via the @prev
  * pointer.  For any task, it appears to be a singly-linked list starting
@@ -66,6 +130,8 @@ struct seccomp_filter {
 	bool log;
 	struct seccomp_filter *prev;
 	struct bpf_prog *prog;
+	struct notification *notif;
+	struct mutex notify_lock;
 };
 
 /* Limit any path through the tree to 256KB worth of instructions. */
@@ -386,6 +452,7 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog)
 	if (!sfilter)
 		return ERR_PTR(-ENOMEM);
 
+	mutex_init(&sfilter->notify_lock);
 	ret = bpf_prog_create_from_user(&sfilter->prog, fprog,
 					seccomp_check_filter, save_orig);
 	if (ret < 0) {
@@ -479,7 +546,6 @@ static long seccomp_attach_filter(unsigned int flags,
 
 static void __get_seccomp_filter(struct seccomp_filter *filter)
 {
-	/* Reference count is bounded by the number of total processes. */
 	refcount_inc(&filter->usage);
 }
 
@@ -550,11 +616,13 @@ static void seccomp_send_sigsys(int syscall, int reason)
 #define SECCOMP_LOG_TRACE		(1 << 4)
 #define SECCOMP_LOG_LOG			(1 << 5)
 #define SECCOMP_LOG_ALLOW		(1 << 6)
+#define SECCOMP_LOG_USER_NOTIF		(1 << 7)
 
 static u32 seccomp_actions_logged = SECCOMP_LOG_KILL_PROCESS |
 				    SECCOMP_LOG_KILL_THREAD  |
 				    SECCOMP_LOG_TRAP  |
 				    SECCOMP_LOG_ERRNO |
+				    SECCOMP_LOG_USER_NOTIF |
 				    SECCOMP_LOG_TRACE |
 				    SECCOMP_LOG_LOG;
 
@@ -575,6 +643,9 @@ static inline void seccomp_log(unsigned long syscall, long signr, u32 action,
 	case SECCOMP_RET_TRACE:
 		log = requested && seccomp_actions_logged & SECCOMP_LOG_TRACE;
 		break;
+	case SECCOMP_RET_USER_NOTIF:
+		log = requested && seccomp_actions_logged & SECCOMP_LOG_USER_NOTIF;
+		break;
 	case SECCOMP_RET_LOG:
 		log = seccomp_actions_logged & SECCOMP_LOG_LOG;
 		break;
@@ -646,6 +717,68 @@ void secure_computing_strict(int this_syscall)
 #else
 
 #ifdef CONFIG_SECCOMP_FILTER
+static u64 seccomp_next_notify_id(struct seccomp_filter *filter)
+{
+	/*
+	 * Note: overflow is ok here, the id just needs to be unique per
+	 * filter.
+	 */
+	lockdep_assert_held(&filter->notify_lock);
+	return filter->notif->next_id++;
+}
+
+static void seccomp_do_user_notification(int this_syscall,
+					 struct seccomp_filter *match,
+					 const struct seccomp_data *sd)
+{
+	int err;
+	long ret = 0;
+	struct seccomp_knotif n = {};
+
+	mutex_lock(&match->notify_lock);
+	err = -ENOSYS;
+	if (!match->notif)
+		goto out;
+
+	n.task = current;
+	n.state = SECCOMP_NOTIFY_INIT;
+	n.data = sd;
+	n.id = seccomp_next_notify_id(match);
+	init_completion(&n.ready);
+	list_add(&n.list, &match->notif->notifications);
+
+	up(&match->notif->request);
+	wake_up_poll(&match->notif->wqh, EPOLLIN | EPOLLRDNORM);
+	mutex_unlock(&match->notify_lock);
+
+	/*
+	 * This is where we wait for a reply from userspace.
+	 */
+	err = wait_for_completion_interruptible(&n.ready);
+	mutex_lock(&match->notify_lock);
+	if (err == 0) {
+		ret = n.val;
+		err = n.error;
+	}
+
+	/*
+	 * Note that it's possible the listener died in between the time when
+	 * we were notified of a respons (or a signal) and when we were able to
+	 * re-acquire the lock, so only delete from the list if the
+	 * notification actually exists.
+	 *
+	 * Also note that this test is only valid because there's no way to
+	 * *reattach* to a notifier right now. If one is added, we'll need to
+	 * keep track of the notif itself and make sure they match here.
+	 */
+	if (match->notif)
+		list_del(&n.list);
+out:
+	mutex_unlock(&match->notify_lock);
+	syscall_set_return_value(current, task_pt_regs(current),
+				 err, ret);
+}
+
 static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
 			    const bool recheck_after_trace)
 {
@@ -728,6 +861,10 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
 
 		return 0;
 
+	case SECCOMP_RET_USER_NOTIF:
+		seccomp_do_user_notification(this_syscall, match, sd);
+		goto skip;
+
 	case SECCOMP_RET_LOG:
 		seccomp_log(this_syscall, 0, action, true);
 		return 0;
@@ -834,6 +971,263 @@ out:
 }
 
 #ifdef CONFIG_SECCOMP_FILTER
+static int seccomp_notify_release(struct inode *inode, struct file *file)
+{
+	struct seccomp_filter *filter = file->private_data;
+	struct seccomp_knotif *knotif;
+
+	mutex_lock(&filter->notify_lock);
+
+	/*
+	 * If this file is being closed because e.g. the task who owned it
+	 * died, let's wake everyone up who was waiting on us.
+	 */
+	list_for_each_entry(knotif, &filter->notif->notifications, list) {
+		if (knotif->state == SECCOMP_NOTIFY_REPLIED)
+			continue;
+
+		knotif->state = SECCOMP_NOTIFY_REPLIED;
+		knotif->error = -ENOSYS;
+		knotif->val = 0;
+
+		complete(&knotif->ready);
+	}
+
+	kfree(filter->notif);
+	filter->notif = NULL;
+	mutex_unlock(&filter->notify_lock);
+	__put_seccomp_filter(filter);
+	return 0;
+}
+
+static long seccomp_notify_recv(struct seccomp_filter *filter,
+				void __user *buf)
+{
+	struct seccomp_knotif *knotif = NULL, *cur;
+	struct seccomp_notif unotif;
+	ssize_t ret;
+
+	memset(&unotif, 0, sizeof(unotif));
+
+	ret = down_interruptible(&filter->notif->request);
+	if (ret < 0)
+		return ret;
+
+	mutex_lock(&filter->notify_lock);
+	list_for_each_entry(cur, &filter->notif->notifications, list) {
+		if (cur->state == SECCOMP_NOTIFY_INIT) {
+			knotif = cur;
+			break;
+		}
+	}
+
+	/*
+	 * If we didn't find a notification, it could be that the task was
+	 * interrupted by a fatal signal between the time we were woken and
+	 * when we were able to acquire the rw lock.
+	 */
+	if (!knotif) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+	unotif.id = knotif->id;
+	unotif.pid = task_pid_vnr(knotif->task);
+	unotif.data = *(knotif->data);
+
+	knotif->state = SECCOMP_NOTIFY_SENT;
+	wake_up_poll(&filter->notif->wqh, EPOLLOUT | EPOLLWRNORM);
+	ret = 0;
+out:
+	mutex_unlock(&filter->notify_lock);
+
+	if (ret == 0 && copy_to_user(buf, &unotif, sizeof(unotif))) {
+		ret = -EFAULT;
+
+		/*
+		 * Userspace screwed up. To make sure that we keep this
+		 * notification alive, let's reset it back to INIT. It
+		 * may have died when we released the lock, so we need to make
+		 * sure it's still around.
+		 */
+		knotif = NULL;
+		mutex_lock(&filter->notify_lock);
+		list_for_each_entry(cur, &filter->notif->notifications, list) {
+			if (cur->id == unotif.id) {
+				knotif = cur;
+				break;
+			}
+		}
+
+		if (knotif) {
+			knotif->state = SECCOMP_NOTIFY_INIT;
+			up(&filter->notif->request);
+		}
+		mutex_unlock(&filter->notify_lock);
+	}
+
+	return ret;
+}
+
+static long seccomp_notify_send(struct seccomp_filter *filter,
+				void __user *buf)
+{
+	struct seccomp_notif_resp resp = {};
+	struct seccomp_knotif *knotif = NULL, *cur;
+	long ret;
+
+	if (copy_from_user(&resp, buf, sizeof(resp)))
+		return -EFAULT;
+
+	if (resp.flags)
+		return -EINVAL;
+
+	ret = mutex_lock_interruptible(&filter->notify_lock);
+	if (ret < 0)
+		return ret;
+
+	list_for_each_entry(cur, &filter->notif->notifications, list) {
+		if (cur->id == resp.id) {
+			knotif = cur;
+			break;
+		}
+	}
+
+	if (!knotif) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+	/* Allow exactly one reply. */
+	if (knotif->state != SECCOMP_NOTIFY_SENT) {
+		ret = -EINPROGRESS;
+		goto out;
+	}
+
+	ret = 0;
+	knotif->state = SECCOMP_NOTIFY_REPLIED;
+	knotif->error = resp.error;
+	knotif->val = resp.val;
+	complete(&knotif->ready);
+out:
+	mutex_unlock(&filter->notify_lock);
+	return ret;
+}
+
+static long seccomp_notify_id_valid(struct seccomp_filter *filter,
+				    void __user *buf)
+{
+	struct seccomp_knotif *knotif = NULL;
+	u64 id;
+	long ret;
+
+	if (copy_from_user(&id, buf, sizeof(id)))
+		return -EFAULT;
+
+	ret = mutex_lock_interruptible(&filter->notify_lock);
+	if (ret < 0)
+		return ret;
+
+	ret = -ENOENT;
+	list_for_each_entry(knotif, &filter->notif->notifications, list) {
+		if (knotif->id == id) {
+			if (knotif->state == SECCOMP_NOTIFY_SENT)
+				ret = 0;
+			goto out;
+		}
+	}
+
+out:
+	mutex_unlock(&filter->notify_lock);
+	return ret;
+}
+
+static long seccomp_notify_ioctl(struct file *file, unsigned int cmd,
+				 unsigned long arg)
+{
+	struct seccomp_filter *filter = file->private_data;
+	void __user *buf = (void __user *)arg;
+
+	switch (cmd) {
+	case SECCOMP_IOCTL_NOTIF_RECV:
+		return seccomp_notify_recv(filter, buf);
+	case SECCOMP_IOCTL_NOTIF_SEND:
+		return seccomp_notify_send(filter, buf);
+	case SECCOMP_IOCTL_NOTIF_ID_VALID:
+		return seccomp_notify_id_valid(filter, buf);
+	default:
+		return -EINVAL;
+	}
+}
+
+static __poll_t seccomp_notify_poll(struct file *file,
+				    struct poll_table_struct *poll_tab)
+{
+	struct seccomp_filter *filter = file->private_data;
+	__poll_t ret = 0;
+	struct seccomp_knotif *cur;
+
+	poll_wait(file, &filter->notif->wqh, poll_tab);
+
+	ret = mutex_lock_interruptible(&filter->notify_lock);
+	if (ret < 0)
+		return EPOLLERR;
+
+	list_for_each_entry(cur, &filter->notif->notifications, list) {
+		if (cur->state == SECCOMP_NOTIFY_INIT)
+			ret |= EPOLLIN | EPOLLRDNORM;
+		if (cur->state == SECCOMP_NOTIFY_SENT)
+			ret |= EPOLLOUT | EPOLLWRNORM;
+		if ((ret & EPOLLIN) && (ret & EPOLLOUT))
+			break;
+	}
+
+	mutex_unlock(&filter->notify_lock);
+
+	return ret;
+}
+
+static const struct file_operations seccomp_notify_ops = {
+	.poll = seccomp_notify_poll,
+	.release = seccomp_notify_release,
+	.unlocked_ioctl = seccomp_notify_ioctl,
+};
+
+static struct file *init_listener(struct seccomp_filter *filter)
+{
+	struct file *ret = ERR_PTR(-EBUSY);
+	struct seccomp_filter *cur;
+
+	for (cur = current->seccomp.filter; cur; cur = cur->prev) {
+		if (cur->notif)
+			goto out;
+	}
+
+	ret = ERR_PTR(-ENOMEM);
+	filter->notif = kzalloc(sizeof(*(filter->notif)), GFP_KERNEL);
+	if (!filter->notif)
+		goto out;
+
+	sema_init(&filter->notif->request, 0);
+	filter->notif->next_id = get_random_u64();
+	INIT_LIST_HEAD(&filter->notif->notifications);
+	init_waitqueue_head(&filter->notif->wqh);
+
+	ret = anon_inode_getfile("seccomp notify", &seccomp_notify_ops,
+				 filter, O_RDWR);
+	if (IS_ERR(ret))
+		goto out_notif;
+
+	/* The file has a reference to it now */
+	__get_seccomp_filter(filter);
+
+out_notif:
+	if (IS_ERR(ret))
+		kfree(filter->notif);
+out:
+	return ret;
+}
+
 /**
  * seccomp_set_mode_filter: internal function for setting seccomp filter
  * @flags:  flags to change filter behavior
@@ -853,6 +1247,8 @@ static long seccomp_set_mode_filter(unsigned int flags,
 	const unsigned long seccomp_mode = SECCOMP_MODE_FILTER;
 	struct seccomp_filter *prepared = NULL;
 	long ret = -EINVAL;
+	int listener = -1;
+	struct file *listener_f = NULL;
 
 	/* Validate flags. */
 	if (flags & ~SECCOMP_FILTER_FLAG_MASK)
@@ -863,13 +1259,28 @@ static long seccomp_set_mode_filter(unsigned int flags,
 	if (IS_ERR(prepared))
 		return PTR_ERR(prepared);
 
+	if (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) {
+		listener = get_unused_fd_flags(O_CLOEXEC);
+		if (listener < 0) {
+			ret = listener;
+			goto out_free;
+		}
+
+		listener_f = init_listener(prepared);
+		if (IS_ERR(listener_f)) {
+			put_unused_fd(listener);
+			ret = PTR_ERR(listener_f);
+			goto out_free;
+		}
+	}
+
 	/*
 	 * Make sure we cannot change seccomp or nnp state via TSYNC
 	 * while another thread is in the middle of calling exec.
 	 */
 	if (flags & SECCOMP_FILTER_FLAG_TSYNC &&
 	    mutex_lock_killable(&current->signal->cred_guard_mutex))
-		goto out_free;
+		goto out_put_fd;
 
 	spin_lock_irq(&current->sighand->siglock);
 
@@ -887,6 +1298,16 @@ out:
 	spin_unlock_irq(&current->sighand->siglock);
 	if (flags & SECCOMP_FILTER_FLAG_TSYNC)
 		mutex_unlock(&current->signal->cred_guard_mutex);
+out_put_fd:
+	if (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) {
+		if (ret < 0) {
+			fput(listener_f);
+			put_unused_fd(listener);
+		} else {
+			fd_install(listener, listener_f);
+			ret = listener;
+		}
+	}
 out_free:
 	seccomp_filter_free(prepared);
 	return ret;
@@ -911,6 +1332,7 @@ static long seccomp_get_action_avail(const char __user *uaction)
 	case SECCOMP_RET_KILL_THREAD:
 	case SECCOMP_RET_TRAP:
 	case SECCOMP_RET_ERRNO:
+	case SECCOMP_RET_USER_NOTIF:
 	case SECCOMP_RET_TRACE:
 	case SECCOMP_RET_LOG:
 	case SECCOMP_RET_ALLOW:
@@ -922,6 +1344,20 @@ static long seccomp_get_action_avail(const char __user *uaction)
 	return 0;
 }
 
+static long seccomp_get_notif_sizes(void __user *usizes)
+{
+	struct seccomp_notif_sizes sizes = {
+		.seccomp_notif = sizeof(struct seccomp_notif),
+		.seccomp_notif_resp = sizeof(struct seccomp_notif_resp),
+		.seccomp_data = sizeof(struct seccomp_data),
+	};
+
+	if (copy_to_user(usizes, &sizes, sizeof(sizes)))
+		return -EFAULT;
+
+	return 0;
+}
+
 /* Common entry point for both prctl and syscall. */
 static long do_seccomp(unsigned int op, unsigned int flags,
 		       void __user *uargs)
@@ -938,6 +1374,11 @@ static long do_seccomp(unsigned int op, unsigned int flags,
 			return -EINVAL;
 
 		return seccomp_get_action_avail(uargs);
+	case SECCOMP_GET_NOTIF_SIZES:
+		if (flags != 0)
+			return -EINVAL;
+
+		return seccomp_get_notif_sizes(uargs);
 	default:
 		return -EINVAL;
 	}
@@ -1111,6 +1552,7 @@ long seccomp_get_metadata(struct task_struct *task,
 #define SECCOMP_RET_KILL_THREAD_NAME	"kill_thread"
 #define SECCOMP_RET_TRAP_NAME		"trap"
 #define SECCOMP_RET_ERRNO_NAME		"errno"
+#define SECCOMP_RET_USER_NOTIF_NAME	"user_notif"
 #define SECCOMP_RET_TRACE_NAME		"trace"
 #define SECCOMP_RET_LOG_NAME		"log"
 #define SECCOMP_RET_ALLOW_NAME		"allow"
@@ -1120,6 +1562,7 @@ static const char seccomp_actions_avail[] =
 				SECCOMP_RET_KILL_THREAD_NAME	" "
 				SECCOMP_RET_TRAP_NAME		" "
 				SECCOMP_RET_ERRNO_NAME		" "
+				SECCOMP_RET_USER_NOTIF_NAME     " "
 				SECCOMP_RET_TRACE_NAME		" "
 				SECCOMP_RET_LOG_NAME		" "
 				SECCOMP_RET_ALLOW_NAME;
@@ -1134,6 +1577,7 @@ static const struct seccomp_log_name seccomp_log_names[] = {
 	{ SECCOMP_LOG_KILL_THREAD, SECCOMP_RET_KILL_THREAD_NAME },
 	{ SECCOMP_LOG_TRAP, SECCOMP_RET_TRAP_NAME },
 	{ SECCOMP_LOG_ERRNO, SECCOMP_RET_ERRNO_NAME },
+	{ SECCOMP_LOG_USER_NOTIF, SECCOMP_RET_USER_NOTIF_NAME },
 	{ SECCOMP_LOG_TRACE, SECCOMP_RET_TRACE_NAME },
 	{ SECCOMP_LOG_LOG, SECCOMP_RET_LOG_NAME },
 	{ SECCOMP_LOG_ALLOW, SECCOMP_RET_ALLOW_NAME },