seccomp: Add wait_killable semantic to seccomp user notifier

This introduces a per-filter flag (SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV)
that makes it so that when notifications are received by the supervisor the
notifying process will transition to wait killable semantics. Although wait
killable isn't a set of semantics formally exposed to userspace, the
concept is searchable. If the notifying process is signaled prior to the
notification being received by the userspace agent, it will be handled as
normal.

One quirk about how this is handled is that the notifying process
only switches to TASK_KILLABLE if it receives a wakeup from either
an addfd or a signal. This is to avoid an unnecessary wakeup of
the notifying task.

The reasons behind switching into wait_killable only after userspace
receives the notification are:
* Avoiding unncessary work - Often, workloads will perform work that they
may abort (request racing comes to mind). This allows for syscalls to be
aborted safely prior to the notification being received by the
supervisor. In this, the supervisor doesn't end up doing work that the
workload does not want to complete anyways.
* Avoiding side effects - We don't want the syscall to be interruptible
once the supervisor starts doing work because it may not be trivial
to reverse the operation. For example, unmounting a file system may
take a long time, and it's hard to rollback, or treat that as
reentrant.
* Avoid breaking runtimes - Various runtimes do not GC when they are
during a syscall (or while running native code that subsequently
calls a syscall). If many notifications are blocked, and not picked
up by the supervisor, this can get the application into a bad state.

Signed-off-by: Sargun Dhillon <[e-mail]>
Signed-off-by: Kees Cook <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]

Documentation/userspace-api/seccomp_filter.rst

···
 respond atomically by using the ``SECCOMP_ADDFD_FLAG_SEND`` flag and the return
 value will be the injected file descriptor number.
 
+The notifying process can be preempted, resulting in the notification being
+aborted. This can be problematic when trying to take actions on behalf of the
+notifying process that are long-running and typically retryable (mounting a
+filesytem). Alternatively, at filter installation time, the
+``SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV`` flag can be set. This flag makes it
+such that when a user notification is received by the supervisor, the notifying
+process will ignore non-fatal signals until the response is sent. Signals that
+are sent prior to the notification being received by userspace are handled
+normally.
+
 It is worth noting that ``struct seccomp_data`` contains the values of register
 arguments to the syscall, but does not contain pointers to memory. The task's
 memory is accessible to suitably privileged traces via ``ptrace()`` or

include/linux/seccomp.h

···
 					 SECCOMP_FILTER_FLAG_LOG | \
 					 SECCOMP_FILTER_FLAG_SPEC_ALLOW | \
 					 SECCOMP_FILTER_FLAG_NEW_LISTENER | \
-					 SECCOMP_FILTER_FLAG_TSYNC_ESRCH)
+					 SECCOMP_FILTER_FLAG_TSYNC_ESRCH | \
+					 SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV)
 
 /* sizeof() the first published struct seccomp_notif_addfd */
 #define SECCOMP_NOTIFY_ADDFD_SIZE_VER0 24

include/uapi/linux/seccomp.h

···
 #define SECCOMP_FILTER_FLAG_SPEC_ALLOW		(1UL << 2)
 #define SECCOMP_FILTER_FLAG_NEW_LISTENER	(1UL << 3)
 #define SECCOMP_FILTER_FLAG_TSYNC_ESRCH		(1UL << 4)
+/* Received notifications wait in killable state (only respond to fatal signals) */
+#define SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV	(1UL << 5)
 
 /*
  * All BPF programs must return a 32-bit value.

kernel/seccomp.c

···
  *	   the filter can be freed.
  * @cache: cache of arch/syscall mappings to actions
  * @log: true if all actions except for SECCOMP_RET_ALLOW should be logged
+ * @wait_killable_recv: Put notifying process in killable state once the
+ *			notification is received by the userspace listener.
  * @prev: points to a previously installed, or inherited, filter
  * @prog: the BPF program to evaluate
  * @notif: the struct that holds all notification related information
···
 	refcount_t refs;
 	refcount_t users;
 	bool log;
+	bool wait_killable_recv;
 	struct action_cache cache;
 	struct seccomp_filter *prev;
 	struct bpf_prog *prog;
···
 	if (flags & SECCOMP_FILTER_FLAG_LOG)
 		filter->log = true;
 
+	/* Set wait killable flag, if present. */
+	if (flags & SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV)
+		filter->wait_killable_recv = true;
+
 	/*
 	 * If there is an existing filter, make it the prev and don't drop its
 	 * task reference.
···
 	complete(&addfd->completion);
 }
 
+static bool should_sleep_killable(struct seccomp_filter *match,
+				  struct seccomp_knotif *n)
+{
+	return match->wait_killable_recv && n->state == SECCOMP_NOTIFY_SENT;
+}
+
 static int seccomp_do_user_notification(int this_syscall,
 					struct seccomp_filter *match,
 					const struct seccomp_data *sd)
···
 	 * This is where we wait for a reply from userspace.
 	 */
 	do {
+		bool wait_killable = should_sleep_killable(match, &n);
+
 		mutex_unlock(&match->notify_lock);
-		err = wait_for_completion_interruptible(&n.ready);
+		if (wait_killable)
+			err = wait_for_completion_killable(&n.ready);
+		else
+			err = wait_for_completion_interruptible(&n.ready);
 		mutex_lock(&match->notify_lock);
-		if (err != 0)
+
+		if (err != 0) {
+			/*
+			 * Check to see if the notifcation got picked up and
+			 * whether we should switch to wait killable.
+			 */
+			if (!wait_killable && should_sleep_killable(match, &n))
+				continue;
+
 			goto interrupted;
+		}
 
 		addfd = list_first_entry_or_null(&n.addfd,
 						 struct seccomp_kaddfd, list);
···
 		mutex_lock(&filter->notify_lock);
 		knotif = find_notification(filter, unotif.id);
 		if (knotif) {
+			/* Reset the process to make sure it's not stuck */
+			if (should_sleep_killable(filter, knotif))
+				complete(&knotif->ready);
 			knotif->state = SECCOMP_NOTIFY_INIT;
 			up(&filter->notif->request);
 		}
···
 	if ((flags & SECCOMP_FILTER_FLAG_TSYNC) &&
 	    (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) &&
 	    ((flags & SECCOMP_FILTER_FLAG_TSYNC_ESRCH) == 0))
+		return -EINVAL;
+
+	/*
+	 * The SECCOMP_FILTER_FLAG_WAIT_KILLABLE_SENT flag doesn't make sense
+	 * without the SECCOMP_FILTER_FLAG_NEW_LISTENER flag.
+	 */
+	if ((flags & SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV) &&
+	    ((flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) == 0))
 		return -EINVAL;
 
 	/* Prepare the new filter before holding any locks. */