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

Author: torvalds

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 &
-							__NR_SYSCALL_MASK;
+			if (data != -1)
+				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;
-
-	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;
@@ -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)