public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Tejun Heo <tj@kernel.org>
To: torvalds@linux-foundation.org, akpm@linux-foundation.org,
	mingo@redhat.com, peterz@infradead.org, axboe@kernel.dk,
	tytso@mit.edu, jack@suse.com, adilger.kernel@dilger.ca
Cc: linux-ext4@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-kernel@vger.kernel.org, kernel-team@fb.com, mingbo@fb.com,
	Tejun Heo <tj@kernel.org>
Subject: [PATCH 2/4] sched: separate out io_schedule_prepare() and io_schedule_finish()
Date: Fri, 28 Oct 2016 12:58:10 -0400	[thread overview]
Message-ID: <1477673892-28940-3-git-send-email-tj@kernel.org> (raw)
In-Reply-To: <1477673892-28940-1-git-send-email-tj@kernel.org>

Now that IO schedule accounting is done inside __schedule(),
io_schedule() can be split into three steps - prep, schedule, and
finish - where the schedule part doesn't need any special annotation.
This allows marking a sleep as iowait by simply wrapping an existing
blocking function with io_schedule_prepare() and io_schedule_finish().

Because task_struct->in_iowait is single bit, the caller of
io_schedule_prepare() needs to record and the pass its state to
io_schedule_finish() to be safe regarding nesting.  While this isn't
the prettiest, these functions are mostly gonna be used by core
functions and we don't want to use more space for ->in_iowait.

While at it, as it's simple to do now, reimplement io_schedule()
without unnecessarily going through io_schedule_timeout().

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Jens Axboe <axboe@kernel.dk>
---
 include/linux/sched.h |  8 +++-----
 kernel/sched/core.c   | 33 ++++++++++++++++++++++++++++-----
 2 files changed, 31 insertions(+), 10 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 348f51b..c025f77 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -441,12 +441,10 @@ extern signed long schedule_timeout_idle(signed long timeout);
 asmlinkage void schedule(void);
 extern void schedule_preempt_disabled(void);
 
+extern int __must_check io_schedule_prepare(void);
+extern void io_schedule_finish(int token);
 extern long io_schedule_timeout(long timeout);
-
-static inline void io_schedule(void)
-{
-	io_schedule_timeout(MAX_SCHEDULE_TIMEOUT);
-}
+extern void io_schedule(void);
 
 void __noreturn do_task_dead(void);
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f6baa38..30d3185 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5067,25 +5067,48 @@ int __sched yield_to(struct task_struct *p, bool preempt)
 }
 EXPORT_SYMBOL_GPL(yield_to);
 
+int io_schedule_prepare(void)
+{
+	int old_iowait = current->in_iowait;
+
+	current->in_iowait = 1;
+	blk_schedule_flush_plug(current);
+
+	return old_iowait;
+}
+
+void io_schedule_finish(int token)
+{
+	current->in_iowait = token;
+}
+
 /*
  * This task is about to go to sleep on IO. Increment rq->nr_iowait so
  * that process accounting knows that this is a task in IO wait state.
  */
 long __sched io_schedule_timeout(long timeout)
 {
-	int old_iowait = current->in_iowait;
+	int token;
 	long ret;
 
-	current->in_iowait = 1;
-	blk_schedule_flush_plug(current);
-
+	token = io_schedule_prepare();
 	ret = schedule_timeout(timeout);
-	current->in_iowait = old_iowait;
+	io_schedule_finish(token);
 
 	return ret;
 }
 EXPORT_SYMBOL(io_schedule_timeout);
 
+void io_schedule(void)
+{
+	int token;
+
+	token = io_schedule_prepare();
+	schedule();
+	io_schedule_finish(token);
+}
+EXPORT_SYMBOL(io_schedule);
+
 /**
  * sys_sched_get_priority_max - return maximum RT priority.
  * @policy: scheduling class.
-- 
2.7.4

  parent reply	other threads:[~2016-10-28 16:59 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-10-28 16:58 [PATCHSET RFC] sched, jbd2: mark sleeps on journal->j_checkpoint_mutex as iowait Tejun Heo
2016-10-28 16:58 ` [PATCH 1/4] sched: move IO scheduling accounting from io_schedule_timeout() to __schedule() Tejun Heo
2016-10-28 18:27   ` Peter Zijlstra
2016-10-28 19:07     ` Peter Zijlstra
2016-10-28 19:12       ` Tejun Heo
2016-10-29  3:21         ` Peter Zijlstra
2016-10-31 16:45           ` Tejun Heo
2016-12-06 21:30             ` Tejun Heo
2016-11-03 15:33   ` Pavan Kondeti
2016-11-08 22:51     ` Tejun Heo
2016-12-06 21:29   ` [PATCH v2 " Tejun Heo
2016-12-07  9:35     ` Peter Zijlstra
2016-12-07 20:48       ` [PATCH v3 1/4] sched: move IO scheduling accounting from io_schedule_timeout() into scheduler Tejun Heo
2017-01-14 12:49         ` [tip:sched/core] sched/core: " tip-bot for Tejun Heo
2016-10-28 16:58 ` Tejun Heo [this message]
2017-01-14 12:49   ` [tip:sched/core] sched/core: Separate out io_schedule_prepare() and io_schedule_finish() tip-bot for Tejun Heo
2016-10-28 16:58 ` [PATCH 3/4] mutex: add mutex_lock_io() Tejun Heo
2017-01-14 12:50   ` [tip:sched/core] locking/mutex, sched/wait: Add mutex_lock_io() tip-bot for Tejun Heo
2017-01-14 14:13     ` Mike Galbraith
2017-01-14 16:10       ` Ingo Molnar
2016-10-28 16:58 ` [PATCH 4/4] jbd2: use mutex_lock_io() for journal->j_checkpoint_mutex Tejun Heo
2017-01-14 12:51   ` [tip:sched/core] fs/jbd2, locking/mutex, sched/wait: Use " tip-bot for Tejun Heo

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=1477673892-28940-3-git-send-email-tj@kernel.org \
    --to=tj@kernel.org \
    --cc=adilger.kernel@dilger.ca \
    --cc=akpm@linux-foundation.org \
    --cc=axboe@kernel.dk \
    --cc=jack@suse.com \
    --cc=kernel-team@fb.com \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingbo@fb.com \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=torvalds@linux-foundation.org \
    --cc=tytso@mit.edu \
    /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