diff options
Diffstat (limited to 'kernel/task_work.c')
-rw-r--r-- | kernel/task_work.c | 124 |
1 files changed, 95 insertions, 29 deletions
diff --git a/kernel/task_work.c b/kernel/task_work.c index 0fef395662a6..065e1ef8fc8d 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/spinlock.h> #include <linux/task_work.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> static struct callback_head work_exited; /* all we need is ->next == NULL */ @@ -9,57 +9,89 @@ 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 + * is @TWA_RESUME, @TWA_SIGNAL, or @TWA_SIGNAL_NO_IPI. + * + * @TWA_SIGNAL works like signals, in that the it will interrupt the targeted + * task and run the task_work, regardless of whether the task is currently + * running in the kernel or userspace. + * @TWA_SIGNAL_NO_IPI works like @TWA_SIGNAL, except it doesn't send a + * reschedule IPI to force the targeted task to reschedule and run task_work. + * This can be advantageous if there's no strict requirement that the + * task_work be run as soon as possible, just whenever the task enters the + * kernel anyway. + * @TWA_RESUME work is run only when the task exits the kernel and returns to + * user mode, or before entering guest mode. * - * 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. + * 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, bool notify) +int task_work_add(struct task_struct *task, struct callback_head *work, + enum task_work_notify_mode notify) { struct callback_head *head; + /* record the work call stack in order to print it in KASAN reports */ + kasan_record_aux_stack(work); + + head = READ_ONCE(task->task_works); do { - head = READ_ONCE(task->task_works); if (unlikely(head == &work_exited)) return -ESRCH; work->next = head; - } while (cmpxchg(&task->task_works, head, work) != head); + } while (!try_cmpxchg(&task->task_works, &head, work)); - if (notify) + switch (notify) { + case TWA_NONE: + break; + case TWA_RESUME: set_notify_resume(task); + break; + case TWA_SIGNAL: + set_notify_signal(task); + break; + case TWA_SIGNAL_NO_IPI: + __set_notify_signal(task); + break; + default: + WARN_ON_ONCE(1); + break; + } + return 0; } /** - * task_work_cancel - cancel a pending work added by task_work_add() + * task_work_cancel_match - cancel a pending work added by task_work_add() * @task: the task which should execute the work - * @func: identifies the work to remove - * - * Find the last queued pending work with ->func == @func and remove - * it from queue. + * @match: match function to call * * RETURNS: * The found work or NULL if not found. */ struct callback_head * -task_work_cancel(struct task_struct *task, task_work_func_t func) +task_work_cancel_match(struct task_struct *task, + bool (*match)(struct callback_head *, void *data), + void *data) { struct callback_head **pprev = &task->task_works; struct callback_head *work; unsigned long flags; - if (likely(!task->task_works)) + if (likely(!task_work_pending(task))) return NULL; /* * If cmpxchg() fails we continue without updating pprev. @@ -68,10 +100,12 @@ task_work_cancel(struct task_struct *task, task_work_func_t func) * we raced with task_work_run(), *pprev == NULL/exited. */ raw_spin_lock_irqsave(&task->pi_lock, flags); - while ((work = READ_ONCE(*pprev))) { - if (work->func != func) + work = READ_ONCE(*pprev); + while (work) { + if (!match(work, data)) { pprev = &work->next; - else if (cmpxchg(pprev, work, work->next) == work) + work = READ_ONCE(*pprev); + } else if (try_cmpxchg(pprev, &work, work->next)) break; } raw_spin_unlock_irqrestore(&task->pi_lock, flags); @@ -79,6 +113,28 @@ task_work_cancel(struct task_struct *task, task_work_func_t func) return work; } +static bool task_work_func_match(struct callback_head *cb, void *data) +{ + return cb->func == data; +} + +/** + * task_work_cancel - cancel a pending work added by task_work_add() + * @task: the task which should execute the work + * @func: identifies the work to remove + * + * Find the last queued pending work with ->func == @func and remove + * it from queue. + * + * RETURNS: + * The found work or NULL if not found. + */ +struct callback_head * +task_work_cancel(struct task_struct *task, task_work_func_t func) +{ + return task_work_cancel_match(task, task_work_func_match, func); +} + /** * task_work_run - execute the works added by task_work_add() * @@ -97,16 +153,26 @@ void task_work_run(void) * work->func() can do task_work_add(), do not set * work_exited unless the list is empty. */ - raw_spin_lock_irq(&task->pi_lock); + work = READ_ONCE(task->task_works); do { - work = READ_ONCE(task->task_works); - head = !work && (task->flags & PF_EXITING) ? - &work_exited : NULL; - } while (cmpxchg(&task->task_works, work, head) != work); - raw_spin_unlock_irq(&task->pi_lock); + head = NULL; + if (!work) { + if (task->flags & PF_EXITING) + head = &work_exited; + else + break; + } + } while (!try_cmpxchg(&task->task_works, &work, head)); if (!work) break; + /* + * Synchronize with task_work_cancel(). It can not remove + * the first entry == work, cmpxchg(task_works) must fail. + * But it can remove another entry from the ->next list. + */ + raw_spin_lock_irq(&task->pi_lock); + raw_spin_unlock_irq(&task->pi_lock); do { next = work->next; |