All of lore.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: linux-kernel@vger.kernel.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
	Ingo Molnar <mingo@elte.hu>, Thomas Gleixner <tglx@linutronix.de>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Tejun Heo <tj@kernel.org>, Jens Axboe <jaxboe@fusionio.com>
Subject: [RFC][PATCH 3/3] block: Break long IRQ disabled region
Date: Wed, 22 Jun 2011 01:34:47 +0200	[thread overview]
Message-ID: <20110621233648.914681513@chello.nl> (raw)
In-Reply-To: 20110621233444.094372367@chello.nl

[-- Attachment #1: tglx3 --]
[-- Type: text/plain, Size: 1470 bytes --]

Keeping IRQs disabled for long is not a feature.

Cc: Jens Axboe <jaxboe@fusionio.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 block/blk-core.c |   11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

Index: linux-2.6/block/blk-core.c
===================================================================
--- linux-2.6.orig/block/blk-core.c
+++ linux-2.6/block/blk-core.c
@@ -2661,7 +2661,7 @@ static void queue_unplugged(struct reque
 	trace_block_unplug(q, depth, true);
 
 	__blk_run_queue(q);
-	spin_unlock(q->queue_lock);
+	spin_unlock_irq(q->queue_lock);
 }
 
 static void flush_plug_callbacks(struct blk_plug *plug)
@@ -2706,11 +2706,6 @@ void blk_flush_plug_list(struct blk_plug
 	q = NULL;
 	depth = 0;
 
-	/*
-	 * Save and disable interrupts here, to avoid doing it for every
-	 * queue lock we have to take.
-	 */
-	local_irq_save(flags);
 	while (!list_empty(&list)) {
 		rq = list_entry_rq(list.next);
 		list_del_init(&rq->queuelist);
@@ -2723,7 +2718,7 @@ void blk_flush_plug_list(struct blk_plug
 				queue_unplugged(q, depth);
 			q = rq->q;
 			depth = 0;
-			spin_lock(q->queue_lock);
+			spin_lock_irq(q->queue_lock);
 		}
 		/*
 		 * rq is already accounted, so use raw insert
@@ -2741,8 +2736,6 @@ void blk_flush_plug_list(struct blk_plug
 	 */
 	if (q)
 		queue_unplugged(q, depth);
-
-	local_irq_restore(flags);
 }
 
 void blk_finish_plug(struct blk_plug *plug)



  parent reply	other threads:[~2011-06-21 23:46 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-06-21 23:34 [RFC][PATCH 0/3] Move WQ,unplug scheduler hooks Peter Zijlstra
2011-06-21 23:34 ` [RFC][PATCH 1/3] sched, block: Move unplug Peter Zijlstra
2011-06-22  7:01   ` Jens Axboe
2011-06-22 13:53     ` Thomas Gleixner
2011-06-22 14:01       ` Jens Axboe
2011-06-22 14:30         ` Thomas Gleixner
2011-06-22 14:38           ` Peter Zijlstra
2011-06-22 15:08             ` Vivek Goyal
2011-06-22 16:04               ` Jens Axboe
2011-06-21 23:34 ` [RFC][PATCH 2/3] sched, workqueue: Move WQ-sleeper wakeup Peter Zijlstra
2011-06-22  9:24   ` Tejun Heo
2011-06-22  9:27     ` Peter Zijlstra
2011-06-22  9:37       ` Tejun Heo
2011-06-22 13:47     ` Thomas Gleixner
2011-06-21 23:34 ` Peter Zijlstra [this message]
2011-06-22  7:03   ` [RFC][PATCH 3/3] block: Break long IRQ disabled region Jens Axboe

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=20110621233648.914681513@chello.nl \
    --to=a.p.zijlstra@chello.nl \
    --cc=jaxboe@fusionio.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=tglx@linutronix.de \
    --cc=tj@kernel.org \
    --cc=torvalds@linux-foundation.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.