Merge tag 'seccomp-v6.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux

Pull seccomp updates from Kees Cook:

 - Provide USER_NOTIFY flag for synchronous mode (Andrei Vagin, Peter
   Oskolkov). This touches the scheduler and perf but has been Acked by
   Peter Zijlstra.

 - Fix regression in syscall skipping and restart tracing on arm32. This
   touches arch/arm/ but has been Acked by Arnd Bergmann.

* tag 'seccomp-v6.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux:
  seccomp: Add missing kerndoc notations
  ARM: ptrace: Restore syscall skipping for tracers
  ARM: ptrace: Restore syscall restart tracing
  selftests/seccomp: Handle arm32 corner cases better
  perf/benchmark: add a new benchmark for seccom_unotify
  selftest/seccomp: add a new test for the sync mode of seccomp_user_notify
  seccomp: add the synchronous mode for seccomp_unotify
  sched: add a few helpers to wake up tasks on the current cpu
  sched: add WF_CURRENT_CPU and externise ttwu
  seccomp: don't use semaphore and wait_queue together

arch/arm/include/asm/syscall.h

@@ -25,6 +25,9 @@ static inline int syscall_get_nr(struct task_struct *task,
 	if (IS_ENABLED(CONFIG_AEABI) && !IS_ENABLED(CONFIG_OABI_COMPAT))
 		return task_thread_info(task)->abi_syscall;
 
+	if (task_thread_info(task)->abi_syscall == -1)
+		return -1;
+
 	return task_thread_info(task)->abi_syscall & __NR_SYSCALL_MASK;
 }
 

arch/arm/kernel/entry-common.S

@@ -90,6 +90,7 @@ slow_work_pending:
 	cmp	r0, #0
 	beq	no_work_pending
 	movlt	scno, #(__NR_restart_syscall - __NR_SYSCALL_BASE)
+	str	scno, [tsk, #TI_ABI_SYSCALL]	@ make sure tracers see update
 	ldmia	sp, {r0 - r6}			@ have to reload r0 - r6
 	b	local_restart			@ ... and off we go
 ENDPROC(ret_fast_syscall)

arch/arm/kernel/ptrace.c

@@ -783,8 +783,9 @@ long arch_ptrace(struct task_struct *child, long request,
 			break;
 
 		case PTRACE_SET_SYSCALL:
-			task_thread_info(child)->abi_syscall = data &
+			if (data != -1)
-							__NR_SYSCALL_MASK;
+				data &= __NR_SYSCALL_MASK;
+			task_thread_info(child)->abi_syscall = data;
 			ret = 0;
 			break;
 

include/linux/completion.h

@@ -116,6 +116,7 @@ extern bool try_wait_for_completion(struct completion *x);
 extern bool completion_done(struct completion *x);
 
 extern void complete(struct completion *);
+extern void complete_on_current_cpu(struct completion *x);
 extern void complete_all(struct completion *);
 
 #endif

include/linux/swait.h

@@ -146,7 +146,7 @@ static inline bool swq_has_sleeper(struct swait_queue_head *wq)
 
 extern void swake_up_one(struct swait_queue_head *q);
 extern void swake_up_all(struct swait_queue_head *q);
-extern void swake_up_locked(struct swait_queue_head *q);
+extern void swake_up_locked(struct swait_queue_head *q, int wake_flags);
 
 extern void prepare_to_swait_exclusive(struct swait_queue_head *q, struct swait_queue *wait, int state);
 extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state);

include/linux/wait.h

@@ -210,6 +210,7 @@ __remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq
 }
 
 int __wake_up(struct wait_queue_head *wq_head, unsigned int mode, int nr, void *key);
+void __wake_up_on_current_cpu(struct wait_queue_head *wq_head, unsigned int mode, void *key);
 void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key);
 void __wake_up_locked_key_bookmark(struct wait_queue_head *wq_head,
 		unsigned int mode, void *key, wait_queue_entry_t *bookmark);
@@ -237,6 +238,8 @@ void __wake_up_pollfree(struct wait_queue_head *wq_head);
 #define key_to_poll(m) ((__force __poll_t)(uintptr_t)(void *)(m))
 #define wake_up_poll(x, m)							\
 	__wake_up(x, TASK_NORMAL, 1, poll_to_key(m))
+#define wake_up_poll_on_current_cpu(x, m)					\
+	__wake_up_on_current_cpu(x, TASK_NORMAL, poll_to_key(m))
 #define wake_up_locked_poll(x, m)						\
 	__wake_up_locked_key((x), TASK_NORMAL, poll_to_key(m))
 #define wake_up_interruptible_poll(x, m)					\

include/uapi/linux/seccomp.h

@@ -115,6 +115,8 @@ struct seccomp_notif_resp {
 	__u32 flags;
 };
 
+#define SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP (1UL << 0)
+
 /* valid flags for seccomp_notif_addfd */
 #define SECCOMP_ADDFD_FLAG_SETFD	(1UL << 0) /* Specify remote fd */
 #define SECCOMP_ADDFD_FLAG_SEND		(1UL << 1) /* Addfd and return it, atomically */
@@ -150,4 +152,6 @@ struct seccomp_notif_addfd {
 #define SECCOMP_IOCTL_NOTIF_ADDFD	SECCOMP_IOW(3, \
 						struct seccomp_notif_addfd)
 
+#define SECCOMP_IOCTL_NOTIF_SET_FLAGS	SECCOMP_IOW(4, __u64)
+
 #endif /* _UAPI_LINUX_SECCOMP_H */

kernel/sched/completion.c

@@ -13,6 +13,23 @@
  * Waiting for completion is a typically sync point, but not an exclusion point.
  */
 
+static void complete_with_flags(struct completion *x, int wake_flags)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&x->wait.lock, flags);
+
+	if (x->done != UINT_MAX)
+		x->done++;
+	swake_up_locked(&x->wait, wake_flags);
+	raw_spin_unlock_irqrestore(&x->wait.lock, flags);
+}
+
+void complete_on_current_cpu(struct completion *x)
+{
+	return complete_with_flags(x, WF_CURRENT_CPU);
+}
+
 /**
  * complete: - signals a single thread waiting on this completion
  * @x:  holds the state of this particular completion
@@ -27,14 +44,7 @@
  */
 void complete(struct completion *x)
 {
-	unsigned long flags;
+	complete_with_flags(x, 0);
-
-	raw_spin_lock_irqsave(&x->wait.lock, flags);
-
-	if (x->done != UINT_MAX)
-		x->done++;
-	swake_up_locked(&x->wait);
-	raw_spin_unlock_irqrestore(&x->wait.lock, flags);
 }
 EXPORT_SYMBOL(complete);
 

kernel/sched/core.c

@@ -4193,8 +4193,7 @@ bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
  * Return: %true if @p->state changes (an actual wakeup was done),
  *	   %false otherwise.
  */
-static int
+int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
-try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 {
 	unsigned long flags;
 	int cpu, success = 0;
@@ -7030,7 +7029,7 @@ asmlinkage __visible void __sched preempt_schedule_irq(void)
 int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags,
 			  void *key)
 {
-	WARN_ON_ONCE(IS_ENABLED(CONFIG_SCHED_DEBUG) && wake_flags & ~WF_SYNC);
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_SCHED_DEBUG) && wake_flags & ~(WF_SYNC|WF_CURRENT_CPU));
 	return try_to_wake_up(curr->private, mode, wake_flags);
 }
 EXPORT_SYMBOL(default_wake_function);

kernel/sched/fair.c

@@ -7741,6 +7741,10 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags)
 	if (wake_flags & WF_TTWU) {
 		record_wakee(p);
 
+		if ((wake_flags & WF_CURRENT_CPU) &&
+		    cpumask_test_cpu(cpu, p->cpus_ptr))
+			return cpu;
+
 		if (sched_energy_enabled()) {
 			new_cpu = find_energy_efficient_cpu(p, prev_cpu);
 			if (new_cpu >= 0)

kernel/sched/sched.h

@@ -2131,12 +2131,13 @@ static inline int task_on_rq_migrating(struct task_struct *p)
 }
 
 /* Wake flags. The first three directly map to some SD flag value */
-#define WF_EXEC     0x02 /* Wakeup after exec; maps to SD_BALANCE_EXEC */
+#define WF_EXEC         0x02 /* Wakeup after exec; maps to SD_BALANCE_EXEC */
-#define WF_FORK     0x04 /* Wakeup after fork; maps to SD_BALANCE_FORK */
+#define WF_FORK         0x04 /* Wakeup after fork; maps to SD_BALANCE_FORK */
-#define WF_TTWU     0x08 /* Wakeup;            maps to SD_BALANCE_WAKE */
+#define WF_TTWU         0x08 /* Wakeup;            maps to SD_BALANCE_WAKE */
 
-#define WF_SYNC     0x10 /* Waker goes to sleep after wakeup */
+#define WF_SYNC         0x10 /* Waker goes to sleep after wakeup */
-#define WF_MIGRATED 0x20 /* Internal use, task got migrated */
+#define WF_MIGRATED     0x20 /* Internal use, task got migrated */
+#define WF_CURRENT_CPU  0x40 /* Prefer to move the wakee to the current CPU. */
 
 #ifdef CONFIG_SMP
 static_assert(WF_EXEC == SD_BALANCE_EXEC);
@@ -3229,6 +3230,8 @@ static inline bool is_per_cpu_kthread(struct task_struct *p)
 extern void swake_up_all_locked(struct swait_queue_head *q);
 extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
 
+extern int try_to_wake_up(struct task_struct *tsk, unsigned int state, int wake_flags);
+
 #ifdef CONFIG_PREEMPT_DYNAMIC
 extern int preempt_dynamic_mode;
 extern int sched_dynamic_mode(const char *str);

kernel/sched/swait.c

@@ -18,7 +18,7 @@ EXPORT_SYMBOL(__init_swait_queue_head);
  * If for some reason it would return 0, that means the previously waiting
  * task is already running, so it will observe condition true (or has already).
  */
-void swake_up_locked(struct swait_queue_head *q)
+void swake_up_locked(struct swait_queue_head *q, int wake_flags)
 {
 	struct swait_queue *curr;
 
@@ -26,7 +26,7 @@ void swake_up_locked(struct swait_queue_head *q)
 		return;
 
 	curr = list_first_entry(&q->task_list, typeof(*curr), task_list);
-	wake_up_process(curr->task);
+	try_to_wake_up(curr->task, TASK_NORMAL, wake_flags);
 	list_del_init(&curr->task_list);
 }
 EXPORT_SYMBOL(swake_up_locked);
@@ -41,7 +41,7 @@ EXPORT_SYMBOL(swake_up_locked);
 void swake_up_all_locked(struct swait_queue_head *q)
 {
 	while (!list_empty(&q->task_list))
-		swake_up_locked(q);
+		swake_up_locked(q, 0);
 }
 
 void swake_up_one(struct swait_queue_head *q)
@@ -49,7 +49,7 @@ void swake_up_one(struct swait_queue_head *q)
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&q->lock, flags);
-	swake_up_locked(q);
+	swake_up_locked(q, 0);
 	raw_spin_unlock_irqrestore(&q->lock, flags);
 }
 EXPORT_SYMBOL(swake_up_one);

kernel/sched/wait.c

@@ -161,6 +161,11 @@ int __wake_up(struct wait_queue_head *wq_head, unsigned int mode,
 }
 EXPORT_SYMBOL(__wake_up);
 
+void __wake_up_on_current_cpu(struct wait_queue_head *wq_head, unsigned int mode, void *key)
+{
+	__wake_up_common_lock(wq_head, mode, 1, WF_CURRENT_CPU, key);
+}
+
 /*
  * Same as __wake_up but called with the spinlock in wait_queue_head_t held.
  */

kernel/seccomp.c

@@ -110,11 +110,13 @@ struct seccomp_knotif {
  * @flags: The flags for the new file descriptor. At the moment, only O_CLOEXEC
  *         is allowed.
  * @ioctl_flags: The flags used for the seccomp_addfd ioctl.
+ * @setfd: whether or not SECCOMP_ADDFD_FLAG_SETFD was set during notify_addfd
  * @ret: The return value of the installing process. It is set to the fd num
  *       upon success (>= 0).
  * @completion: Indicates that the installing process has completed fd
  *              installation, or gone away (either due to successful
  *              reply, or signal)
+ * @list: list_head for chaining seccomp_kaddfd together.
  *
  */
 struct seccomp_kaddfd {
@@ -138,14 +140,17 @@ struct seccomp_kaddfd {
  * 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
+ * @requests: A semaphore that users of this notification can wait on for
- *           changes. Actual reads and writes are still controlled with
+ *            changes. Actual reads and writes are still controlled with
- *           filter->notify_lock.
+ *            filter->notify_lock.
+ * @flags: A set of SECCOMP_USER_NOTIF_FD_* flags.
  * @next_id: The id of the next request.
  * @notifications: A list of struct seccomp_knotif elements.
  */
+
 struct notification {
-	struct semaphore request;
+	atomic_t requests;
+	u32 flags;
 	u64 next_id;
 	struct list_head notifications;
 };
@@ -555,6 +560,8 @@ static void __seccomp_filter_release(struct seccomp_filter *orig)
  *			    drop its reference count, and notify
  *			    about unused filters
  *
+ * @tsk: task the filter should be released from.
+ *
  * This function should only be called when the task is exiting as
  * it detaches it from its filter tree. As such, READ_ONCE() and
  * barriers are not needed here, as would normally be needed.
@@ -574,6 +581,8 @@ void seccomp_filter_release(struct task_struct *tsk)
 /**
  * seccomp_sync_threads: sets all threads to use current's filter
  *
+ * @flags: SECCOMP_FILTER_FLAG_* flags to set during sync.
+ *
  * Expects sighand and cred_guard_mutex locks to be held, and for
  * seccomp_can_sync_threads() to have returned success already
  * without dropping the locks.
@@ -1116,8 +1125,11 @@ static int seccomp_do_user_notification(int this_syscall,
 	list_add_tail(&n.list, &match->notif->notifications);
 	INIT_LIST_HEAD(&n.addfd);
 
-	up(&match->notif->request);
+	atomic_inc(&match->notif->requests);
-	wake_up_poll(&match->wqh, EPOLLIN | EPOLLRDNORM);
+	if (match->notif->flags & SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP)
+		wake_up_poll_on_current_cpu(&match->wqh, EPOLLIN | EPOLLRDNORM);
+	else
+		wake_up_poll(&match->wqh, EPOLLIN | EPOLLRDNORM);
 
 	/*
 	 * This is where we wait for a reply from userspace.
@@ -1450,6 +1462,37 @@ find_notification(struct seccomp_filter *filter, u64 id)
 	return NULL;
 }
 
+static int recv_wake_function(wait_queue_entry_t *wait, unsigned int mode, int sync,
+				  void *key)
+{
+	/* Avoid a wakeup if event not interesting for us. */
+	if (key && !(key_to_poll(key) & (EPOLLIN | EPOLLERR)))
+		return 0;
+	return autoremove_wake_function(wait, mode, sync, key);
+}
+
+static int recv_wait_event(struct seccomp_filter *filter)
+{
+	DEFINE_WAIT_FUNC(wait, recv_wake_function);
+	int ret;
+
+	if (atomic_dec_if_positive(&filter->notif->requests) >= 0)
+		return 0;
+
+	for (;;) {
+		ret = prepare_to_wait_event(&filter->wqh, &wait, TASK_INTERRUPTIBLE);
+
+		if (atomic_dec_if_positive(&filter->notif->requests) >= 0)
+			break;
+
+		if (ret)
+			return ret;
+
+		schedule();
+	}
+	finish_wait(&filter->wqh, &wait);
+	return 0;
+}
 
 static long seccomp_notify_recv(struct seccomp_filter *filter,
 				void __user *buf)
@@ -1467,7 +1510,7 @@ static long seccomp_notify_recv(struct seccomp_filter *filter,
 
 	memset(&unotif, 0, sizeof(unotif));
 
-	ret = down_interruptible(&filter->notif->request);
+	ret = recv_wait_event(filter);
 	if (ret < 0)
 		return ret;
 
@@ -1515,7 +1558,8 @@ out:
 			if (should_sleep_killable(filter, knotif))
 				complete(&knotif->ready);
 			knotif->state = SECCOMP_NOTIFY_INIT;
-			up(&filter->notif->request);
+			atomic_inc(&filter->notif->requests);
+			wake_up_poll(&filter->wqh, EPOLLIN | EPOLLRDNORM);
 		}
 		mutex_unlock(&filter->notify_lock);
 	}
@@ -1561,7 +1605,10 @@ static long seccomp_notify_send(struct seccomp_filter *filter,
 	knotif->error = resp.error;
 	knotif->val = resp.val;
 	knotif->flags = resp.flags;
-	complete(&knotif->ready);
+	if (filter->notif->flags & SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP)
+		complete_on_current_cpu(&knotif->ready);
+	else
+		complete(&knotif->ready);
 out:
 	mutex_unlock(&filter->notify_lock);
 	return ret;
@@ -1591,6 +1638,22 @@ static long seccomp_notify_id_valid(struct seccomp_filter *filter,
 	return ret;
 }
 
+static long seccomp_notify_set_flags(struct seccomp_filter *filter,
+				    unsigned long flags)
+{
+	long ret;
+
+	if (flags & ~SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP)
+		return -EINVAL;
+
+	ret = mutex_lock_interruptible(&filter->notify_lock);
+	if (ret < 0)
+		return ret;
+	filter->notif->flags = flags;
+	mutex_unlock(&filter->notify_lock);
+	return 0;
+}
+
 static long seccomp_notify_addfd(struct seccomp_filter *filter,
 				 struct seccomp_notif_addfd __user *uaddfd,
 				 unsigned int size)
@@ -1720,6 +1783,8 @@ static long seccomp_notify_ioctl(struct file *file, unsigned int cmd,
 	case SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR:
 	case SECCOMP_IOCTL_NOTIF_ID_VALID:
 		return seccomp_notify_id_valid(filter, buf);
+	case SECCOMP_IOCTL_NOTIF_SET_FLAGS:
+		return seccomp_notify_set_flags(filter, arg);
 	}
 
 	/* Extensible Argument ioctls */
@@ -1777,7 +1842,6 @@ static struct file *init_listener(struct seccomp_filter *filter)
 	if (!filter->notif)
 		goto out;
 
-	sema_init(&filter->notif->request, 0);
 	filter->notif->next_id = get_random_u64();
 	INIT_LIST_HEAD(&filter->notif->notifications);
 

tools/arch/x86/include/uapi/asm/unistd_32.h

@@ -26,3 +26,6 @@
 #ifndef __NR_setns
 #define __NR_setns 346
 #endif
+#ifdef __NR_seccomp
+#define __NR_seccomp 354
+#endif

tools/arch/x86/include/uapi/asm/unistd_64.h

@@ -26,3 +26,6 @@
 #ifndef __NR_getcpu
 #define __NR_getcpu 309
 #endif
+#ifndef __NR_seccomp
+#define __NR_seccomp 317
+#endif

tools/perf/bench/Build

@@ -1,5 +1,6 @@
 perf-y += sched-messaging.o
 perf-y += sched-pipe.o
+perf-y += sched-seccomp-notify.o
 perf-y += syscall.o
 perf-y += mem-functions.o
 perf-y += futex-hash.o

tools/perf/bench/bench.h

@@ -21,6 +21,7 @@ extern struct timeval bench__start, bench__end, bench__runtime;
 int bench_numa(int argc, const char **argv);
 int bench_sched_messaging(int argc, const char **argv);
 int bench_sched_pipe(int argc, const char **argv);
+int bench_sched_seccomp_notify(int argc, const char **argv);
 int bench_syscall_basic(int argc, const char **argv);
 int bench_syscall_getpgid(int argc, const char **argv);
 int bench_syscall_fork(int argc, const char **argv);

tools/perf/bench/sched-seccomp-notify.c

@@ -0,0 +1,178 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <subcmd/parse-options.h>
+#include "bench.h"
+
+#include <uapi/linux/filter.h>
+#include <sys/types.h>
+#include <sys/time.h>
+#include <linux/unistd.h>
+#include <sys/syscall.h>
+#include <sys/ioctl.h>
+#include <linux/time64.h>
+#include <linux/seccomp.h>
+#include <sys/prctl.h>
+
+#include <unistd.h>
+#include <limits.h>
+#include <stddef.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <sys/wait.h>
+#include <string.h>
+#include <errno.h>
+#include <err.h>
+#include <inttypes.h>
+
+#define LOOPS_DEFAULT 1000000UL
+static uint64_t loops = LOOPS_DEFAULT;
+static bool sync_mode;
+
+static const struct option options[] = {
+	OPT_U64('l', "loop",	&loops,		"Specify number of loops"),
+	OPT_BOOLEAN('s', "sync-mode", &sync_mode,
+		    "Enable the synchronious mode for seccomp notifications"),
+	OPT_END()
+};
+
+static const char * const bench_seccomp_usage[] = {
+	"perf bench sched secccomp-notify <options>",
+	NULL
+};
+
+static int seccomp(unsigned int op, unsigned int flags, void *args)
+{
+	return syscall(__NR_seccomp, op, flags, args);
+}
+
+static int user_notif_syscall(int nr, unsigned int flags)
+{
+	struct sock_filter filter[] = {
+		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
+			offsetof(struct seccomp_data, nr)),
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, nr, 0, 1),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_USER_NOTIF),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+	};
+
+	struct sock_fprog prog = {
+		.len = (unsigned short)ARRAY_SIZE(filter),
+		.filter = filter,
+	};
+
+	return seccomp(SECCOMP_SET_MODE_FILTER, flags, &prog);
+}
+
+#define USER_NOTIF_MAGIC INT_MAX
+static void user_notification_sync_loop(int listener)
+{
+	struct seccomp_notif_resp resp;
+	struct seccomp_notif req;
+	uint64_t nr;
+
+	for (nr = 0; nr < loops; nr++) {
+		memset(&req, 0, sizeof(req));
+		if (ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req))
+			err(EXIT_FAILURE, "SECCOMP_IOCTL_NOTIF_RECV failed");
+
+		if (req.data.nr != __NR_gettid)
+			errx(EXIT_FAILURE, "unexpected syscall: %d", req.data.nr);
+
+		resp.id = req.id;
+		resp.error = 0;
+		resp.val = USER_NOTIF_MAGIC;
+		resp.flags = 0;
+		if (ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp))
+			err(EXIT_FAILURE, "SECCOMP_IOCTL_NOTIF_SEND failed");
+	}
+}
+
+#ifndef SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP
+#define SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP (1UL << 0)
+#define SECCOMP_IOCTL_NOTIF_SET_FLAGS  SECCOMP_IOW(4, __u64)
+#endif
+int bench_sched_seccomp_notify(int argc, const char **argv)
+{
+	struct timeval start, stop, diff;
+	unsigned long long result_usec = 0;
+	int status, listener;
+	pid_t pid;
+	long ret;
+
+	argc = parse_options(argc, argv, options, bench_seccomp_usage, 0);
+
+	gettimeofday(&start, NULL);
+
+	prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	listener = user_notif_syscall(__NR_gettid,
+				      SECCOMP_FILTER_FLAG_NEW_LISTENER);
+	if (listener < 0)
+		err(EXIT_FAILURE, "can't create a notification descriptor");
+
+	pid = fork();
+	if (pid < 0)
+		err(EXIT_FAILURE, "fork");
+	if (pid == 0) {
+		if (prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0))
+			err(EXIT_FAILURE, "can't set the parent death signal");
+		while (1) {
+			ret = syscall(__NR_gettid);
+			if (ret == USER_NOTIF_MAGIC)
+				continue;
+			break;
+		}
+		_exit(1);
+	}
+
+	if (sync_mode) {
+		if (ioctl(listener, SECCOMP_IOCTL_NOTIF_SET_FLAGS,
+			     SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP, 0))
+			err(EXIT_FAILURE,
+			    "can't set SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP");
+	}
+	user_notification_sync_loop(listener);
+
+	kill(pid, SIGKILL);
+	if (waitpid(pid, &status, 0) != pid)
+		err(EXIT_FAILURE, "waitpid(%d) failed", pid);
+	if (!WIFSIGNALED(status) || WTERMSIG(status) != SIGKILL)
+		errx(EXIT_FAILURE, "unexpected exit code: %d", status);
+
+	gettimeofday(&stop, NULL);
+	timersub(&stop, &start, &diff);
+
+	switch (bench_format) {
+	case BENCH_FORMAT_DEFAULT:
+		printf("# Executed %" PRIu64 " system calls\n\n",
+			loops);
+
+		result_usec = diff.tv_sec * USEC_PER_SEC;
+		result_usec += diff.tv_usec;
+
+		printf(" %14s: %lu.%03lu [sec]\n\n", "Total time",
+		       (unsigned long) diff.tv_sec,
+		       (unsigned long) (diff.tv_usec / USEC_PER_MSEC));
+
+		printf(" %14lf usecs/op\n",
+		       (double)result_usec / (double)loops);
+		printf(" %14d ops/sec\n",
+		       (int)((double)loops /
+			     ((double)result_usec / (double)USEC_PER_SEC)));
+		break;
+
+	case BENCH_FORMAT_SIMPLE:
+		printf("%lu.%03lu\n",
+		       (unsigned long) diff.tv_sec,
+		       (unsigned long) (diff.tv_usec / USEC_PER_MSEC));
+		break;
+
+	default:
+		/* reaching here is something disaster */
+		fprintf(stderr, "Unknown format:%d\n", bench_format);
+		exit(1);
+		break;
+	}
+
+	return 0;
+}

tools/perf/builtin-bench.c

@@ -47,6 +47,7 @@ static struct bench numa_benchmarks[] = {
 static struct bench sched_benchmarks[] = {
 	{ "messaging",	"Benchmark for scheduling and IPC",		bench_sched_messaging	},
 	{ "pipe",	"Benchmark for pipe() between two processes",	bench_sched_pipe	},
+	{ "seccomp-notify",	"Benchmark for seccomp user notify",	bench_sched_seccomp_notify},
 	{ "all",	"Run all scheduler benchmarks",		NULL			},
 	{ NULL,		NULL,						NULL			}
 };

tools/testing/selftests/seccomp/seccomp_bpf.c

@@ -2184,6 +2184,9 @@ FIXTURE_TEARDOWN(TRACE_syscall)
 
 TEST(negative_ENOSYS)
 {
+#if defined(__arm__)
+	SKIP(return, "arm32 does not support calling syscall -1");
+#endif
 	/*
 	 * There should be no difference between an "internal" skip
 	 * and userspace asking for syscall "-1".
@@ -3072,7 +3075,8 @@ TEST(syscall_restart)
 		timeout.tv_sec = 1;
 		errno = 0;
 		EXPECT_EQ(0, nanosleep(&timeout, NULL)) {
-			TH_LOG("Call to nanosleep() failed (errno %d)", errno);
+			TH_LOG("Call to nanosleep() failed (errno %d: %s)",
+				errno, strerror(errno));
 		}
 
 		/* Read final sync from parent. */
@@ -3908,6 +3912,9 @@ TEST(user_notification_filter_empty)
 		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
 	}
 
+	if (__NR_clone3 < 0)
+		SKIP(return, "Test not built with clone3 support");
+
 	pid = sys_clone3(&args, sizeof(args));
 	ASSERT_GE(pid, 0);
 
@@ -3962,6 +3969,9 @@ TEST(user_notification_filter_empty_threaded)
 		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
 	}
 
+	if (__NR_clone3 < 0)
+		SKIP(return, "Test not built with clone3 support");
+
 	pid = sys_clone3(&args, sizeof(args));
 	ASSERT_GE(pid, 0);
 
@@ -4255,6 +4265,61 @@ TEST(user_notification_addfd_rlimit)
 	close(memfd);
 }
 
+#ifndef SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP
+#define SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP (1UL << 0)
+#define SECCOMP_IOCTL_NOTIF_SET_FLAGS  SECCOMP_IOW(4, __u64)
+#endif
+
+TEST(user_notification_sync)
+{
+	struct seccomp_notif req = {};
+	struct seccomp_notif_resp resp = {};
+	int status, listener;
+	pid_t pid;
+	long ret;
+
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
+	}
+
+	listener = user_notif_syscall(__NR_getppid,
+				      SECCOMP_FILTER_FLAG_NEW_LISTENER);
+	ASSERT_GE(listener, 0);
+
+	/* Try to set invalid flags. */
+	EXPECT_SYSCALL_RETURN(-EINVAL,
+		ioctl(listener, SECCOMP_IOCTL_NOTIF_SET_FLAGS, 0xffffffff, 0));
+
+	ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SET_FLAGS,
+			SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP, 0), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0) {
+		ret = syscall(__NR_getppid);
+		ASSERT_EQ(ret, USER_NOTIF_MAGIC) {
+			_exit(1);
+		}
+		_exit(0);
+	}
+
+	req.pid = 0;
+	ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
+
+	ASSERT_EQ(req.data.nr,  __NR_getppid);
+
+	resp.id = req.id;
+	resp.error = 0;
+	resp.val = USER_NOTIF_MAGIC;
+	resp.flags = 0;
+	ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0);
+
+	ASSERT_EQ(waitpid(pid, &status, 0), pid);
+	ASSERT_EQ(status, 0);
+}
+
+
 /* Make sure PTRACE_O_SUSPEND_SECCOMP requires CAP_SYS_ADMIN. */
 FIXTURE(O_SUSPEND_SECCOMP) {
 	pid_t pid;