Merge branch 'for-next/seccomp' of git://git.kernel.org/pub/scm/linux…

…/kernel/git/kees/linux.git

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;
-
-	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);
 

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;
@@ -7032,7 +7031,7 @@ 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

@@ -7821,6 +7821,10 @@ 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

@@ -2135,12 +2135,13 @@ 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);
@@ -3232,6 +3233,8 @@ 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

@@ -18,15 +18,15 @@ 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;
 
 	if (list_empty(&q->task_list))
 		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);
@@ -41,15 +41,15 @@ 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)
 {
 	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

@@ -143,9 +143,12 @@ struct seccomp_kaddfd {
  *           filter->notify_lock.
  * @next_id: The id of the next request.
  * @notifications: A list of struct seccomp_knotif elements.
+ * @flags: A set of SECCOMP_USER_NOTIF_FD_* flags.
  */
+
 struct notification {
-	struct semaphore request;
+	atomic_t requests;
+	u32 flags;
 	u64 next_id;
 	struct list_head notifications;
 };
@@ -1116,8 +1119,11 @@ 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 +1456,37 @@ 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 +1504,7 @@ 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 +1552,8 @@ static long seccomp_notify_recv(struct seccomp_filter *filter,
 			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 +1599,10 @@ 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 +1632,22 @@ 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 +1777,8 @@ 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 +1836,6 @@ 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);