Merge tag 'seccomp-v5.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux

Pull seccomp updates from Kees Cook:

 - Rework USER_NOTIF notification ordering and kill logic (Sargun
   Dhillon)

 - Improved PTRACE_O_SUSPEND_SECCOMP selftest (Jann Horn)

 - Gracefully handle failed unshare() in selftests (Yang Guang)

 - Spelling fix (Colin Ian King)

* tag 'seccomp-v5.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux:
  selftests/seccomp: Fix spelling mistake "Coud" -> "Could"
  selftests/seccomp: Add test for wait killable notifier
  selftests/seccomp: Refactor get_proc_stat to split out file reading code
  seccomp: Add wait_killable semantic to seccomp user notifier
  selftests/seccomp: Ensure that notifications come in FIFO order
  seccomp: Use FIFO semantics to order notifications
  selftests/seccomp: Add SKIP for failed unshare()
  selftests/seccomp: Test PTRACE_O_SUSPEND_SECCOMP without CAP_SYS_ADMIN

Documentation/userspace-api/seccomp_filter.rst

@@ -271,6 +271,16 @@ notifying process it will be replaced. The supervisor can also add an FD, and
 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

@@ -8,7 +8,8 @@
 					 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

@@ -23,6 +23,8 @@
 #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

@@ -200,6 +200,8 @@ static inline void seccomp_cache_prepare(struct seccomp_filter *sfilter)
  *	   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
@@ -220,6 +222,7 @@ struct seccomp_filter {
 	refcount_t refs;
 	refcount_t users;
 	bool log;
+	bool wait_killable_recv;
 	struct action_cache cache;
 	struct seccomp_filter *prev;
 	struct bpf_prog *prog;
@@ -893,6 +896,10 @@ static long seccomp_attach_filter(unsigned int flags,
 	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.
@@ -1080,6 +1087,12 @@ static void seccomp_handle_addfd(struct seccomp_kaddfd *addfd, struct seccomp_kn
 	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)
@@ -1100,7 +1113,7 @@ static int seccomp_do_user_notification(int this_syscall,
 	n.data = sd;
 	n.id = seccomp_next_notify_id(match);
 	init_completion(&n.ready);
-	list_add(&n.list, &match->notif->notifications);
+	list_add_tail(&n.list, &match->notif->notifications);
 	INIT_LIST_HEAD(&n.addfd);
 
 	up(&match->notif->request);
@@ -1110,11 +1123,25 @@ static int seccomp_do_user_notification(int this_syscall,
 	 * This is where we wait for a reply from userspace.
 	 */
 	do {
+		bool wait_killable = should_sleep_killable(match, &n);
+
 		mutex_unlock(&match->notify_lock);
+		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);
@@ -1484,6 +1511,9 @@ static long seccomp_notify_recv(struct seccomp_filter *filter,
 		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);
 		}
@@ -1829,6 +1859,14 @@ static long seccomp_set_mode_filter(unsigned int flags,
 	    ((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. */
 	prepared = seccomp_prepare_user_filter(filter);
 	if (IS_ERR(prepared))

tools/testing/selftests/seccomp/Makefile

 # SPDX-License-Identifier: GPL-2.0
 CFLAGS += -Wl,-no-as-needed -Wall -isystem ../../../../usr/include/
 LDFLAGS += -lpthread
+LDLIBS += -lcap
 
 TEST_GEN_PROGS := seccomp_bpf seccomp_benchmark
 include ../lib.mk