summaryrefslogtreecommitdiffstats
path: root/kernel/task_work.c
diff options
context:
space:
mode:
authorOleg Nesterov <oleg@redhat.com>2012-08-26 21:12:09 +0200
committerIngo Molnar <mingo@kernel.org>2012-09-13 16:47:33 +0200
commitac3d0da8f3290b3d394cdb7f50604424a7cd6092 (patch)
treec1a126ac8ab3d87f22baaa51fd786f3c56c22327 /kernel/task_work.c
parent15674868d6c5985466835c56dd89d39235f16302 (diff)
downloadlinux-ac3d0da8f3290b3d394cdb7f50604424a7cd6092.tar.gz
linux-ac3d0da8f3290b3d394cdb7f50604424a7cd6092.tar.bz2
linux-ac3d0da8f3290b3d394cdb7f50604424a7cd6092.zip
task_work: Make task_work_add() lockless
Change task_work's to use llist-like code to avoid pi_lock in task_work_add(), this makes it useable under rq->lock. task_work_cancel() and task_work_run() still use pi_lock to synchronize with each other. (This is in preparation for a deadlock fix.) Suggested-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20120826191209.GA4221@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel/task_work.c')
-rw-r--r--kernel/task_work.c95
1 files changed, 48 insertions, 47 deletions
diff --git a/kernel/task_work.c b/kernel/task_work.c
index d320d44903bd..f13ec0bda1d5 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -3,25 +3,18 @@
#include <linux/tracehook.h>
int
-task_work_add(struct task_struct *task, struct callback_head *twork, bool notify)
+task_work_add(struct task_struct *task, struct callback_head *work, bool notify)
{
- struct callback_head *last, *first;
- unsigned long flags;
-
+ struct callback_head *head;
/*
* Not inserting the new work if the task has already passed
* exit_task_work() is the responisbility of callers.
*/
- raw_spin_lock_irqsave(&task->pi_lock, flags);
- last = task->task_works;
- first = last ? last->next : twork;
- twork->next = first;
- if (last)
- last->next = twork;
- task->task_works = twork;
- raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ do {
+ head = ACCESS_ONCE(task->task_works);
+ work->next = head;
+ } while (cmpxchg(&task->task_works, head, work) != head);
- /* test_and_set_bit() implies mb(), see tracehook_notify_resume(). */
if (notify)
set_notify_resume(task);
return 0;
@@ -30,52 +23,60 @@ task_work_add(struct task_struct *task, struct callback_head *twork, bool notify
struct callback_head *
task_work_cancel(struct task_struct *task, task_work_func_t func)
{
+ struct callback_head **pprev = &task->task_works;
+ struct callback_head *work = NULL;
unsigned long flags;
- struct callback_head *last, *res = NULL;
-
+ /*
+ * If cmpxchg() fails we continue without updating pprev.
+ * Either we raced with task_work_add() which added the
+ * new entry before this work, we will find it again. Or
+ * we raced with task_work_run(), *pprev == NULL.
+ */
raw_spin_lock_irqsave(&task->pi_lock, flags);
- last = task->task_works;
- if (last) {
- struct callback_head *q = last, *p = q->next;
- while (1) {
- if (p->func == func) {
- q->next = p->next;
- if (p == last)
- task->task_works = q == p ? NULL : q;
- res = p;
- break;
- }
- if (p == last)
- break;
- q = p;
- p = q->next;
- }
+ while ((work = ACCESS_ONCE(*pprev))) {
+ read_barrier_depends();
+ if (work->func != func)
+ pprev = &work->next;
+ else if (cmpxchg(pprev, work, work->next) == work)
+ break;
}
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
- return res;
+
+ return work;
}
void task_work_run(void)
{
struct task_struct *task = current;
- struct callback_head *p, *q;
+ struct callback_head *work, *head, *next;
- while (1) {
- raw_spin_lock_irq(&task->pi_lock);
- p = task->task_works;
- task->task_works = NULL;
- raw_spin_unlock_irq(&task->pi_lock);
+ for (;;) {
+ work = xchg(&task->task_works, NULL);
+ if (!work)
+ break;
+ /*
+ * Synchronize with task_work_cancel(). It can't remove
+ * the first entry == work, cmpxchg(task_works) should
+ * fail, but it can play with *work and other entries.
+ */
+ raw_spin_unlock_wait(&task->pi_lock);
+ smp_mb();
- if (unlikely(!p))
- return;
+ /* Reverse the list to run the works in fifo order */
+ head = NULL;
+ do {
+ next = work->next;
+ work->next = head;
+ head = work;
+ work = next;
+ } while (work);
- q = p->next; /* head */
- p->next = NULL; /* cut it */
- while (q) {
- p = q->next;
- q->func(q);
- q = p;
+ work = head;
+ do {
+ next = work->next;
+ work->func(work);
+ work = next;
cond_resched();
- }
+ } while (work);
}
}