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

7 files changed, 115 insertions, 30 deletions

diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index d57a5c1c1cd9..3561ab533dd4 100644
--- a/kernel/sched/completion.c
+++ b/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;
-
-	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);
+	complete_with_flags(x, 0);
 }
 EXPORT_SYMBOL(complete);
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c52c2eba7c73..4d63e063608a 100644
--- a/kernel/sched/core.c
+++ b/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
-try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
+int 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);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b3e25be58e2b..ceb5d4c4738e 100644
--- a/kernel/sched/fair.c
+++ b/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)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index e93e006a942b..48d0be005f08 100644
--- a/kernel/sched/sched.h
+++ b/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_FORK     0x04 /* Wakeup after fork; maps to SD_BALANCE_FORK */
-#define WF_TTWU     0x08 /* Wakeup;            maps to SD_BALANCE_WAKE */
+#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_TTWU         0x08 /* Wakeup;            maps to SD_BALANCE_WAKE */
 
-#define WF_SYNC     0x10 /* Waker goes to sleep after wakeup */
-#define WF_MIGRATED 0x20 /* Internal use, task got migrated */
+#define WF_SYNC         0x10 /* Waker goes to sleep after wakeup */
+#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);
diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c
index 76b9b796e695..72505cd3b60a 100644
--- a/kernel/sched/swait.c
+++ b/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);
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 48c53e4739ea..802d98cf2de3 100644
--- a/kernel/sched/wait.c
+++ b/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.
  */
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index d3e584065c7f..255999ba9190 100644
--- a/kernel/seccomp.c
+++ b/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
- *           changes. Actual reads and writes are still controlled with
- *           filter->notify_lock.
+ * @requests: A semaphore that users of this notification can wait on for
+ *            changes. Actual reads and writes are still controlled with
+ *            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);
-	wake_up_poll(&match->wqh, EPOLLIN | EPOLLRDNORM);
+	atomic_inc(&match->notif->requests);
+	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);