Merge tag 'arch-cleanup-2020-10-22' of git://git.kernel.dk/linux-block

Pull arch task_work cleanups from Jens Axboe:
 "Two cleanups that don't fit other categories:

   - Finally get the task_work_add() cleanup done properly, so we don't
     have random 0/1/false/true/TWA_SIGNAL confusing use cases. Updates
     all callers, and also fixes up the documentation for
     task_work_add().

   - While working on some TIF related changes for 5.11, this
     TIF_NOTIFY_RESUME cleanup fell out of that. Remove some arch
     duplication for how that is handled"

* tag 'arch-cleanup-2020-10-22' of git://git.kernel.dk/linux-block:
  task_work: cleanup notification modes
  tracehook: clear TIF_NOTIFY_RESUME in tracehook_notify_resume()

arch/alpha/kernel/signal.c

@@ -531,7 +531,6 @@ do_work_pending(struct pt_regs *regs, unsigned long thread_flags,
 				do_signal(regs, r0, r19);
 				r0 = 0;
 			} else {
-				clear_thread_flag(TIF_NOTIFY_RESUME);
 				tracehook_notify_resume(regs);
 			}
 		}

arch/arc/kernel/signal.c

@@ -394,6 +394,6 @@ void do_notify_resume(struct pt_regs *regs)
 	 * ASM glue gaurantees that this is only called when returning to
 	 * user mode
 	 */
-	if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME))
+	if (test_thread_flag(TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
 }

arch/arm/kernel/signal.c

@@ -669,7 +669,6 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
 			} else if (thread_flags & _TIF_UPROBE) {
 				uprobe_notify_resume(regs);
 			} else {
-				clear_thread_flag(TIF_NOTIFY_RESUME);
 				tracehook_notify_resume(regs);
 				rseq_handle_notify_resume(NULL, regs);
 			}

arch/arm64/kernel/signal.c

@@ -946,7 +946,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 				do_signal(regs);
 
 			if (thread_flags & _TIF_NOTIFY_RESUME) {
-				clear_thread_flag(TIF_NOTIFY_RESUME);
 				tracehook_notify_resume(regs);
 				rseq_handle_notify_resume(NULL, regs);
 			}

arch/c6x/kernel/signal.c

@@ -316,8 +316,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, u32 thread_info_flags,
 	if (thread_info_flags & (1 << TIF_SIGPENDING))
 		do_signal(regs, syscall);
 
-	if (thread_info_flags & (1 << TIF_NOTIFY_RESUME)) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
+	if (thread_info_flags & (1 << TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
-	}
 }

arch/csky/kernel/signal.c

@@ -261,7 +261,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 		do_signal(regs);
 
 	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
 		rseq_handle_notify_resume(NULL, regs);
 	}

arch/h8300/kernel/signal.c

@@ -282,8 +282,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, u32 thread_info_flags)
 	if (thread_info_flags & _TIF_SIGPENDING)
 		do_signal(regs);
 
-	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
+	if (thread_info_flags & _TIF_NOTIFY_RESUME)
 		tracehook_notify_resume(regs);
-	}
 }

arch/hexagon/kernel/process.c

@@ -180,7 +180,6 @@ int do_work_pending(struct pt_regs *regs, u32 thread_info_flags)
 	}
 
 	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
 		return 1;
 	}

arch/ia64/kernel/process.c

@@ -176,7 +176,7 @@ do_notify_resume_user(sigset_t *unused, struct sigscratch *scr, long in_syscall)
 		ia64_do_signal(scr, in_syscall);
 	}
 
-	if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME)) {
+	if (test_thread_flag(TIF_NOTIFY_RESUME)) {
 		local_irq_enable();	/* force interrupt enable */
 		tracehook_notify_resume(&scr->pt);
 	}

arch/m68k/kernel/signal.c

@@ -1136,6 +1136,6 @@ void do_notify_resume(struct pt_regs *regs)
 	if (test_thread_flag(TIF_SIGPENDING))
 		do_signal(regs);
 
-	if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME))
+	if (test_thread_flag(TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
 }

arch/microblaze/kernel/signal.c

@@ -316,6 +316,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, int in_syscall)
 	if (test_thread_flag(TIF_SIGPENDING))
 		do_signal(regs, in_syscall);
 
-	if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME))
+	if (test_thread_flag(TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
 }

arch/mips/kernel/signal.c

@@ -907,7 +907,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, void *unused,
 		do_signal(regs);
 
 	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
 		rseq_handle_notify_resume(NULL, regs);
 	}

arch/nds32/kernel/signal.c

@@ -379,8 +379,6 @@ do_notify_resume(struct pt_regs *regs, unsigned int thread_flags)
 	if (thread_flags & _TIF_SIGPENDING)
 		do_signal(regs);
 
-	if (thread_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
+	if (thread_flags & _TIF_NOTIFY_RESUME)
 		tracehook_notify_resume(regs);
-	}
 }

arch/nios2/kernel/signal.c

@@ -317,7 +317,7 @@ asmlinkage int do_notify_resume(struct pt_regs *regs)
 			 */
 			return restart;
 		}
-	} else if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME))
+	} else if (test_thread_flag(TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
 
 	return 0;

arch/openrisc/kernel/signal.c

@@ -311,7 +311,6 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
 				}
 				syscall = 0;
 			} else {
-				clear_thread_flag(TIF_NOTIFY_RESUME);
 				tracehook_notify_resume(regs);
 			}
 		}

arch/parisc/kernel/signal.c

@@ -606,8 +606,6 @@ void do_notify_resume(struct pt_regs *regs, long in_syscall)
 	if (test_thread_flag(TIF_SIGPENDING))
 		do_signal(regs, in_syscall);
 
-	if (test_thread_flag(TIF_NOTIFY_RESUME)) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
+	if (test_thread_flag(TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
-	}
 }

arch/powerpc/kernel/signal.c

@@ -324,7 +324,6 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
 	}
 
 	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
 		tracehook_notify_resume(regs);
 		rseq_handle_notify_resume(NULL, regs);
 	}

arch/riscv/kernel/signal.c

@@ -313,8 +313,6 @@ asmlinkage __visible void do_notify_resume(struct pt_regs *regs,
 	if (thread_info_flags & _TIF_SIGPENDING)
 		do_signal(regs);
 
-	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
+	if (thread_info_flags & _TIF_NOTIFY_RESUME)
 		tracehook_notify_resume(regs);
-	}
 }

arch/s390/kernel/signal.c

@@ -535,7 +535,6 @@ void do_signal(struct pt_regs *regs)
 
 void do_notify_resume(struct pt_regs *regs)
 {
-	clear_thread_flag(TIF_NOTIFY_RESUME);
 	tracehook_notify_resume(regs);
 	rseq_handle_notify_resume(NULL, regs);
 }

arch/sh/kernel/signal_32.c

@@ -502,8 +502,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, unsigned int save_r0,
 	if (thread_info_flags & _TIF_SIGPENDING)
 		do_signal(regs, save_r0);
 
-	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
+	if (thread_info_flags & _TIF_NOTIFY_RESUME)
 		tracehook_notify_resume(regs);
-	}
 }

arch/sparc/kernel/signal_32.c

@@ -523,10 +523,8 @@ void do_notify_resume(struct pt_regs *regs, unsigned long orig_i0,
 {
 	if (thread_info_flags & _TIF_SIGPENDING)
 		do_signal(regs, orig_i0);
-	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
+	if (thread_info_flags & _TIF_NOTIFY_RESUME)
 		tracehook_notify_resume(regs);
-	}
 }
 
 asmlinkage int do_sys_sigstack(struct sigstack __user *ssptr,

arch/sparc/kernel/signal_64.c

@@ -551,10 +551,8 @@ void do_notify_resume(struct pt_regs *regs, unsigned long orig_i0, unsigned long
 		uprobe_notify_resume(regs);
 	if (thread_info_flags & _TIF_SIGPENDING)
 		do_signal(regs, orig_i0);
-	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
+	if (thread_info_flags & _TIF_NOTIFY_RESUME)
 		tracehook_notify_resume(regs);
-	}
 	user_enter();
 }
 

arch/um/kernel/process.c

@@ -101,7 +101,7 @@ void interrupt_end(void)
 		schedule();
 	if (test_thread_flag(TIF_SIGPENDING))
 		do_signal(regs);
-	if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME))
+	if (test_thread_flag(TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
 }
 

arch/x86/kernel/cpu/mce/core.c

@@ -1277,7 +1277,7 @@ static void queue_task_work(struct mce *m, int kill_it)
 	else
 		current->mce_kill_me.func = kill_me_maybe;
 
-	task_work_add(current, &current->mce_kill_me, true);
+	task_work_add(current, &current->mce_kill_me, TWA_RESUME);
 }
 
 /*

arch/x86/kernel/cpu/resctrl/rdtgroup.c

@@ -561,7 +561,7 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
 	 * callback has been invoked.
 	 */
 	atomic_inc(&rdtgrp->waitcount);
-	ret = task_work_add(tsk, &callback->work, true);
+	ret = task_work_add(tsk, &callback->work, TWA_RESUME);
 	if (ret) {
 		/*
 		 * Task is exiting. Drop the refcount and free the callback.

arch/xtensa/kernel/signal.c

@@ -501,6 +501,6 @@ void do_notify_resume(struct pt_regs *regs)
 	if (test_thread_flag(TIF_SIGPENDING))
 		do_signal(regs);
 
-	if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME))
+	if (test_thread_flag(TIF_NOTIFY_RESUME))
 		tracehook_notify_resume(regs);
 }

drivers/acpi/apei/ghes.c

@@ -942,7 +942,7 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
 			estatus_node->task_work.func = ghes_kick_task_work;
 			estatus_node->task_work_cpu = smp_processor_id();
 			ret = task_work_add(current, &estatus_node->task_work,
-					    true);
+					    TWA_RESUME);
 			if (ret)
 				estatus_node->task_work.func = NULL;
 		}

drivers/android/binder.c

@@ -2229,7 +2229,7 @@ static void binder_deferred_fd_close(int fd)
 	__close_fd_get_file(fd, &twcb->file);
 	if (twcb->file) {
 		filp_close(twcb->file, current->files);
-		task_work_add(current, &twcb->twork, true);
+		task_work_add(current, &twcb->twork, TWA_RESUME);
 	} else {
 		kfree(twcb);
 	}

fs/file_table.c

@@ -339,7 +339,7 @@ void fput_many(struct file *file, unsigned int refs)
 
 		if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {
 			init_task_work(&file->f_u.fu_rcuhead, ____fput);
-			if (!task_work_add(task, &file->f_u.fu_rcuhead, true))
+			if (!task_work_add(task, &file->f_u.fu_rcuhead, TWA_RESUME))
 				return;
 			/*
 			 * After this task has run exit_task_work(),

fs/io_uring.c

@@ -1976,7 +1976,8 @@ static int io_req_task_work_add(struct io_kiocb *req, bool twa_signal_ok)
 {
 	struct task_struct *tsk = req->task;
 	struct io_ring_ctx *ctx = req->ctx;
-	int ret, notify;
+	enum task_work_notify_mode notify;
+	int ret;
 
 	if (tsk->flags & PF_EXITING)
 		return -ESRCH;
@@ -1987,7 +1988,7 @@ static int io_req_task_work_add(struct io_kiocb *req, bool twa_signal_ok)
 	 * processing task_work. There's no reliable way to tell if TWA_RESUME
 	 * will do the job.
 	 */
-	notify = 0;
+	notify = TWA_NONE;
 	if (!(ctx->flags & IORING_SETUP_SQPOLL) && twa_signal_ok)
 		notify = TWA_SIGNAL;
 
@@ -2056,7 +2057,7 @@ static void io_req_task_queue(struct io_kiocb *req)
 
 		init_task_work(&req->task_work, io_req_task_cancel);
 		tsk = io_wq_get_task(req->ctx->io_wq);
-		task_work_add(tsk, &req->task_work, 0);
+		task_work_add(tsk, &req->task_work, TWA_NONE);
 		wake_up_process(tsk);
 	}
 }
@@ -2177,7 +2178,7 @@ static void io_free_req_deferred(struct io_kiocb *req)
 		struct task_struct *tsk;
 
 		tsk = io_wq_get_task(req->ctx->io_wq);
-		task_work_add(tsk, &req->task_work, 0);
+		task_work_add(tsk, &req->task_work, TWA_NONE);
 		wake_up_process(tsk);
 	}
 }
@@ -3291,7 +3292,7 @@ static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode,
 		/* queue just for cancelation */
 		init_task_work(&req->task_work, io_req_task_cancel);
 		tsk = io_wq_get_task(req->ctx->io_wq);
-		task_work_add(tsk, &req->task_work, 0);
+		task_work_add(tsk, &req->task_work, TWA_NONE);
 		wake_up_process(tsk);
 	}
 	return 1;
@@ -4857,7 +4858,7 @@ static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll,
 
 		WRITE_ONCE(poll->canceled, true);
 		tsk = io_wq_get_task(req->ctx->io_wq);
-		task_work_add(tsk, &req->task_work, 0);
+		task_work_add(tsk, &req->task_work, TWA_NONE);
 		wake_up_process(tsk);
 	}
 	return 1;

fs/namespace.c

@@ -1191,7 +1191,7 @@ static void mntput_no_expire(struct mount *mnt)
 		struct task_struct *task = current;
 		if (likely(!(task->flags & PF_KTHREAD))) {
 			init_task_work(&mnt->mnt_rcu, __cleanup_mnt);
-			if (!task_work_add(task, &mnt->mnt_rcu, true))
+			if (!task_work_add(task, &mnt->mnt_rcu, TWA_RESUME))
 				return;
 		}
 		if (llist_add(&mnt->mnt_llist, &delayed_mntput_list))

include/linux/task_work.h

@@ -13,9 +13,14 @@ init_task_work(struct callback_head *twork, task_work_func_t func)
 	twork->func = func;
 }
 
-#define TWA_RESUME	1
-#define TWA_SIGNAL	2
-int task_work_add(struct task_struct *task, struct callback_head *twork, int);
+enum task_work_notify_mode {
+	TWA_NONE,
+	TWA_RESUME,
+	TWA_SIGNAL,
+};
+
+int task_work_add(struct task_struct *task, struct callback_head *twork,
+			enum task_work_notify_mode mode);
 
 struct callback_head *task_work_cancel(struct task_struct *, task_work_func_t);
 void task_work_run(void);

include/linux/tracehook.h

@@ -178,9 +178,9 @@ static inline void set_notify_resume(struct task_struct *task)
  */
 static inline void tracehook_notify_resume(struct pt_regs *regs)
 {
+	clear_thread_flag(TIF_NOTIFY_RESUME);
 	/*
-	 * The caller just cleared TIF_NOTIFY_RESUME. This barrier
-	 * pairs with task_work_add()->set_notify_resume() after
+	 * This barrier pairs with task_work_add()->set_notify_resume() after
 	 * hlist_add_head(task->task_works);
 	 */
 	smp_mb__after_atomic();

kernel/entry/common.c

@@ -161,7 +161,6 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 			arch_do_signal(regs);
 
 		if (ti_work & _TIF_NOTIFY_RESUME) {
-			clear_thread_flag(TIF_NOTIFY_RESUME);
 			tracehook_notify_resume(regs);
 			rseq_handle_notify_resume(NULL, regs);
 		}

kernel/entry/kvm.c

@@ -16,10 +16,8 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work)
 		if (ti_work & _TIF_NEED_RESCHED)
 			schedule();
 
-		if (ti_work & _TIF_NOTIFY_RESUME) {
-			clear_thread_flag(TIF_NOTIFY_RESUME);
+		if (ti_work & _TIF_NOTIFY_RESUME)
 			tracehook_notify_resume(NULL);
-		}
 
 		ret = arch_xfer_to_guest_mode_handle_work(vcpu, ti_work);
 		if (ret)

kernel/events/uprobes.c

@@ -1823,7 +1823,7 @@ void uprobe_copy_process(struct task_struct *t, unsigned long flags)
 
 	t->utask->dup_xol_addr = area->vaddr;
 	init_task_work(&t->utask->dup_xol_work, dup_xol_work);
-	task_work_add(t, &t->utask->dup_xol_work, true);
+	task_work_add(t, &t->utask->dup_xol_work, TWA_RESUME);
 }
 
 /*

kernel/irq/manage.c

@@ -1162,7 +1162,7 @@ static int irq_thread(void *data)
 		handler_fn = irq_thread_fn;
 
 	init_task_work(&on_exit_work, irq_thread_dtor);
-	task_work_add(current, &on_exit_work, false);
+	task_work_add(current, &on_exit_work, TWA_NONE);
 
 	irq_thread_check_affinity(desc, action);
 

kernel/sched/fair.c

@@ -2928,7 +2928,7 @@ static void task_tick_numa(struct rq *rq, struct task_struct *curr)
 		curr->node_stamp += period;
 
 		if (!time_before(jiffies, curr->mm->numa_next_scan))
-			task_work_add(curr, work, true);
+			task_work_add(curr, work, TWA_RESUME);
 	}
 }
 

kernel/task_work.c

@@ -9,23 +9,28 @@ static struct callback_head work_exited; /* all we need is ->next == NULL */
  * task_work_add - ask the @task to execute @work->func()
  * @task: the task which should run the callback
  * @work: the callback to run
- * @notify: send the notification if true
+ * @notify: how to notify the targeted task
  *
- * Queue @work for task_work_run() below and notify the @task if @notify.
- * Fails if the @task is exiting/exited and thus it can't process this @work.
- * Otherwise @work->func() will be called when the @task returns from kernel
- * mode or exits.
+ * Queue @work for task_work_run() below and notify the @task if @notify
+ * is @TWA_RESUME or @TWA_SIGNAL. @TWA_SIGNAL works like signals, in that the
+ * it will interrupt the targeted task and run the task_work. @TWA_RESUME
+ * work is run only when the task exits the kernel and returns to user mode,
+ * or before entering guest mode. Fails if the @task is exiting/exited and thus
+ * it can't process this @work. Otherwise @work->func() will be called when the
+ * @task goes through one of the aforementioned transitions, or exits.
  *
- * This is like the signal handler which runs in kernel mode, but it doesn't
- * try to wake up the @task.
+ * If the targeted task is exiting, then an error is returned and the work item
+ * is not queued. It's up to the caller to arrange for an alternative mechanism
+ * in that case.
  *
- * Note: there is no ordering guarantee on works queued here.
+ * Note: there is no ordering guarantee on works queued here. The task_work
+ * list is LIFO.
  *
  * RETURNS:
  * 0 if succeeds or -ESRCH.
  */
-int
-task_work_add(struct task_struct *task, struct callback_head *work, int notify)
+int task_work_add(struct task_struct *task, struct callback_head *work,
+		  enum task_work_notify_mode notify)
 {
 	struct callback_head *head;
 	unsigned long flags;
@@ -38,6 +43,8 @@ task_work_add(struct task_struct *task, struct callback_head *work, int notify)
 	} while (cmpxchg(&task->task_works, head, work) != head);
 
 	switch (notify) {
+	case TWA_NONE:
+		break;
 	case TWA_RESUME:
 		set_notify_resume(task);
 		break;
@@ -54,6 +61,9 @@ task_work_add(struct task_struct *task, struct callback_head *work, int notify)
 			unlock_task_sighand(task, &flags);
 		}
 		break;
+	default:
+		WARN_ON_ONCE(1);
+		break;
 	}
 
 	return 0;

security/keys/keyctl.c

@@ -1693,7 +1693,7 @@ long keyctl_session_to_parent(void)
 
 	/* the replacement session keyring is applied just prior to userspace
 	 * restarting */
-	ret = task_work_add(parent, newwork, true);
+	ret = task_work_add(parent, newwork, TWA_RESUME);
 	if (!ret)
 		newwork = NULL;
 unlock:

security/yama/yama_lsm.c

@@ -99,7 +99,7 @@ static void report_access(const char *access, struct task_struct *target,
 	info->access = access;
 	info->target = target;
 	info->agent = agent;
-	if (task_work_add(current, &info->work, true) == 0)
+	if (task_work_add(current, &info->work, TWA_RESUME) == 0)
 		return; /* success */
 
 	WARN(1, "report_access called from exiting task");