From: Oleg Nesterov <oleg@redhat.com>
To: Peter Zijlstra <peterz@infradead.org>, Al Viro <viro@zeniv.linux.org.uk>
Cc: Dave Jones <davej@redhat.com>,
Linux Kernel <linux-kernel@vger.kernel.org>,
Thomas Gleixner <tglx@linutronix.de>,
rostedt <rostedt@goodmis.org>, dhowells <dhowells@redhat.com>,
Linus Torvalds <torvalds@linux-foundation.org>
Subject: [PATCH 1/4] task_work: make task_work_add() lockless
Date: Sun, 26 Aug 2012 21:12:09 +0200 [thread overview]
Message-ID: <20120826191209.GA4221@redhat.com> (raw)
In-Reply-To: <20120826191132.GA3743@redhat.com>
Change task_works 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.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
---
kernel/task_work.c | 95 ++++++++++++++++++++++++++-------------------------
1 files changed, 48 insertions(+), 47 deletions(-)
diff --git a/kernel/task_work.c b/kernel/task_work.c
index d320d44..f13ec0b 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);
}
}
--
1.5.5.1
next prev parent reply other threads:[~2012-08-26 19:10 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-07-24 20:36 lockdep trace from posix timers Dave Jones
2012-07-27 16:20 ` Dave Jones
2012-08-16 12:54 ` Ming Lei
2012-08-16 14:03 ` Dave Jones
2012-08-16 18:07 ` Peter Zijlstra
2012-08-17 15:14 ` Oleg Nesterov
2012-08-17 15:17 ` Oleg Nesterov
2012-08-17 16:40 ` task_work_add() should not succeed unconditionally (Was: lockdep trace from posix timers) Oleg Nesterov
2012-08-20 7:15 ` lockdep trace from posix timers Peter Zijlstra
2012-08-20 11:44 ` Peter Zijlstra
2012-08-20 11:46 ` Peter Zijlstra
2012-08-20 11:50 ` Peter Zijlstra
2012-08-20 12:19 ` Steven Rostedt
2012-08-20 12:20 ` Peter Zijlstra
2012-08-20 14:59 ` Oleg Nesterov
2012-08-20 15:10 ` Peter Zijlstra
2012-08-20 15:27 ` Peter Zijlstra
2012-08-20 15:32 ` Oleg Nesterov
2012-08-20 15:46 ` Peter Zijlstra
2012-08-20 15:58 ` Oleg Nesterov
2012-08-20 16:03 ` Peter Zijlstra
2012-08-20 15:05 ` Oleg Nesterov
2012-08-20 15:12 ` Peter Zijlstra
2012-08-20 15:41 ` Oleg Nesterov
2012-08-20 15:56 ` Peter Zijlstra
2012-08-20 16:10 ` Oleg Nesterov
2012-08-20 16:19 ` Peter Zijlstra
2012-08-20 16:23 ` Oleg Nesterov
2012-08-21 18:27 ` Oleg Nesterov
2012-08-21 18:34 ` Oleg Nesterov
2012-08-24 18:56 ` Oleg Nesterov
2012-08-26 19:11 ` [PATCH 0/4] (Was: lockdep trace from posix timers) Oleg Nesterov
2012-08-26 19:12 ` Oleg Nesterov [this message]
2012-09-14 6:08 ` [tip:core/urgent] task_work: Make task_work_add() lockless tip-bot for Oleg Nesterov
2012-09-24 19:27 ` [PATCH 1/4] task_work: make " Geert Uytterhoeven
2012-09-24 20:37 ` Oleg Nesterov
2012-08-26 19:12 ` [PATCH 2/4] task_work: task_work_add() should not succeed after exit_task_work() Oleg Nesterov
2012-09-14 6:09 ` [tip:core/urgent] " tip-bot for Oleg Nesterov
2012-08-26 19:12 ` [PATCH 3/4] task_work: revert d35abdb2 "hold task_lock around checks in keyctl" Oleg Nesterov
2012-09-14 6:10 ` [tip:core/urgent] task_work: Revert " hold " tip-bot for Oleg Nesterov
2012-08-26 19:12 ` [PATCH 4/4] task_work: simplify the usage in ptrace_notify() and get_signal_to_deliver() Oleg Nesterov
2012-09-14 6:11 ` [tip:core/urgent] task_work: Simplify " tip-bot for Oleg Nesterov
2012-09-06 18:01 ` [PATCH 0/4] (Was: lockdep trace from posix timers) Oleg Nesterov
2012-09-06 18:35 ` Peter Zijlstra
2012-09-07 13:13 ` Oleg Nesterov
2012-08-28 16:29 ` lockdep trace from posix timers Peter Zijlstra
2012-08-28 17:01 ` Oleg Nesterov
2012-08-28 17:12 ` Oleg Nesterov
2012-08-28 17:28 ` Peter Zijlstra
2012-08-29 15:25 ` Oleg Nesterov
2012-08-20 14:55 ` Oleg Nesterov
2012-08-20 15:43 ` Oleg Nesterov
2012-08-20 15:48 ` Peter Zijlstra
2012-08-20 15:58 ` Oleg Nesterov
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20120826191209.GA4221@redhat.com \
--to=oleg@redhat.com \
--cc=davej@redhat.com \
--cc=dhowells@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
--cc=viro@zeniv.linux.org.uk \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).