mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Tejun Heo <tj@kernel.org>
To: torvalds@linux-foundation.org, mingo@elte.hu,
	peterz@infradead.org, awalls@radix.net,
	linux-kernel@vger.kernel.org, jeff@garzik.org,
	akpm@linux-foundation.org, jens.axboe@oracle.com,
	rusty@rustcorp.com.au, cl@linux-foundation.org,
	dhowells@redhat.com, arjan@linux.intel.com, avi@redhat.com,
	johannes@sipsolutions.net, andi@firstfloor.org, oleg@redhat.com
Cc: Tejun Heo <tj@kernel.org>, Jeff Garzik <jgarzik@pobox.com>
Subject: [PATCH 36/43] libata: take advantage of cmwq and remove concurrency limitations
Date: Fri, 26 Feb 2010 21:23:13 +0900	[thread overview]
Message-ID: <1267187000-18791-37-git-send-email-tj@kernel.org> (raw)
In-Reply-To: <1267187000-18791-1-git-send-email-tj@kernel.org>

libata has two concurrency related limitations.

a. ata_wq which is used for polling PIO has single thread per CPU.  If
   there are multiple devices doing polling PIO on the same CPU, they
   can't be executed simultaneously.

b. ata_aux_wq which is used for SCSI probing has single thread.  In
   cases where SCSI probing is stalled for extended period of time
   which is possible for ATAPI devices, this will stall all probing.

#a is solved by increasing maximum concurrency of ata_wq.  Please note
that polling PIO might be used under allocation path and thus needs to
be served by a separate wq with a rescuer.

#b is solved by using the default wq instead and achieving exclusion
via per-port mutex.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Jeff Garzik <jgarzik@pobox.com>
---
 drivers/ata/libata-core.c |   19 ++-----------------
 drivers/ata/libata-eh.c   |    4 ++--
 drivers/ata/libata-scsi.c |   10 ++++++----
 drivers/ata/libata.h      |    1 -
 include/linux/libata.h    |    2 ++
 5 files changed, 12 insertions(+), 24 deletions(-)

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 6728328..389c580 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -97,8 +97,6 @@ static unsigned long ata_dev_blacklisted(const struct ata_device *dev);
 unsigned int ata_print_id = 1;
 static struct workqueue_struct *ata_wq;
 
-struct workqueue_struct *ata_aux_wq;
-
 struct ata_force_param {
 	const char	*name;
 	unsigned int	cbl;
@@ -5705,6 +5703,7 @@ struct ata_port *ata_port_alloc(struct ata_host *host)
 #else
 	INIT_DELAYED_WORK(&ap->port_task, NULL);
 #endif
+	mutex_init(&ap->scsi_scan_mutex);
 	INIT_DELAYED_WORK(&ap->hotplug_task, ata_scsi_hotplug);
 	INIT_WORK(&ap->scsi_rescan_task, ata_scsi_dev_rescan);
 	INIT_LIST_HEAD(&ap->eh_done_q);
@@ -6640,26 +6639,13 @@ static int __init ata_init(void)
 {
 	ata_parse_force_param();
 
-	/*
-	 * FIXME: In UP case, there is only one workqueue thread and if you
-	 * have more than one PIO device, latency is bloody awful, with
-	 * occasional multi-second "hiccups" as one PIO device waits for
-	 * another.  It's an ugly wart that users DO occasionally complain
-	 * about; luckily most users have at most one PIO polled device.
-	 */
-	ata_wq = create_workqueue("ata");
+	ata_wq = __create_workqueue("ata", WQ_RESCUER, WQ_MAX_ACTIVE);
 	if (!ata_wq)
 		goto free_force_tbl;
 
-	ata_aux_wq = create_singlethread_workqueue("ata_aux");
-	if (!ata_aux_wq)
-		goto free_wq;
-
 	printk(KERN_DEBUG "libata version " DRV_VERSION " loaded.\n");
 	return 0;
 
-free_wq:
-	destroy_workqueue(ata_wq);
 free_force_tbl:
 	kfree(ata_force_tbl);
 	return -ENOMEM;
@@ -6669,7 +6655,6 @@ static void __exit ata_exit(void)
 {
 	kfree(ata_force_tbl);
 	destroy_workqueue(ata_wq);
-	destroy_workqueue(ata_aux_wq);
 }
 
 subsys_initcall(ata_init);
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 9f6cfac..a1975a4 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -727,7 +727,7 @@ void ata_scsi_error(struct Scsi_Host *host)
 	if (ap->pflags & ATA_PFLAG_LOADING)
 		ap->pflags &= ~ATA_PFLAG_LOADING;
 	else if (ap->pflags & ATA_PFLAG_SCSI_HOTPLUG)
-		queue_delayed_work(ata_aux_wq, &ap->hotplug_task, 0);
+		schedule_delayed_work(&ap->hotplug_task, 0);
 
 	if (ap->pflags & ATA_PFLAG_RECOVERED)
 		ata_port_printk(ap, KERN_INFO, "EH complete\n");
@@ -2939,7 +2939,7 @@ static int ata_eh_revalidate_and_attach(struct ata_link *link,
 			ehc->i.flags |= ATA_EHI_SETMODE;
 
 			/* schedule the scsi_rescan_device() here */
-			queue_work(ata_aux_wq, &(ap->scsi_rescan_task));
+			schedule_work(&(ap->scsi_rescan_task));
 		} else if (dev->class == ATA_DEV_UNKNOWN &&
 			   ehc->tries[dev->devno] &&
 			   ata_class_enabled(ehc->classes[dev->devno])) {
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index d096fbc..dc1159a 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -3408,7 +3408,7 @@ void ata_scsi_scan_host(struct ata_port *ap, int sync)
 				"                  switching to async\n");
 	}
 
-	queue_delayed_work(ata_aux_wq, &ap->hotplug_task,
+	queue_delayed_work(system_long_wq, &ap->hotplug_task,
 			   round_jiffies_relative(HZ));
 }
 
@@ -3555,6 +3555,7 @@ void ata_scsi_hotplug(struct work_struct *work)
 	}
 
 	DPRINTK("ENTER\n");
+	mutex_lock(&ap->scsi_scan_mutex);
 
 	/* Unplug detached devices.  We cannot use link iterator here
 	 * because PMP links have to be scanned even if PMP is
@@ -3568,6 +3569,7 @@ void ata_scsi_hotplug(struct work_struct *work)
 	/* scan for new ones */
 	ata_scsi_scan_host(ap, 0);
 
+	mutex_unlock(&ap->scsi_scan_mutex);
 	DPRINTK("EXIT\n");
 }
 
@@ -3646,9 +3648,7 @@ static int ata_scsi_user_scan(struct Scsi_Host *shost, unsigned int channel,
  *	@work: Pointer to ATA port to perform scsi_rescan_device()
  *
  *	After ATA pass thru (SAT) commands are executed successfully,
- *	libata need to propagate the changes to SCSI layer.  This
- *	function must be executed from ata_aux_wq such that sdev
- *	attach/detach don't race with rescan.
+ *	libata need to propagate the changes to SCSI layer.
  *
  *	LOCKING:
  *	Kernel thread context (may sleep).
@@ -3661,6 +3661,7 @@ void ata_scsi_dev_rescan(struct work_struct *work)
 	struct ata_device *dev;
 	unsigned long flags;
 
+	mutex_lock(&ap->scsi_scan_mutex);
 	spin_lock_irqsave(ap->lock, flags);
 
 	ata_for_each_link(link, ap, EDGE) {
@@ -3680,6 +3681,7 @@ void ata_scsi_dev_rescan(struct work_struct *work)
 	}
 
 	spin_unlock_irqrestore(ap->lock, flags);
+	mutex_unlock(&ap->scsi_scan_mutex);
 }
 
 /**
diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h
index 823e630..4da2105 100644
--- a/drivers/ata/libata.h
+++ b/drivers/ata/libata.h
@@ -65,7 +65,6 @@ enum {
 };
 
 extern unsigned int ata_print_id;
-extern struct workqueue_struct *ata_aux_wq;
 extern int atapi_passthru16;
 extern int libata_fua;
 extern int libata_noacpi;
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 7311225..29bf1ec 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -752,6 +752,8 @@ struct ata_port {
 
 	void			*port_task_data;
 	struct delayed_work	port_task;
+
+	struct mutex		scsi_scan_mutex;
 	struct delayed_work	hotplug_task;
 	struct work_struct	scsi_rescan_task;
 
-- 
1.6.4.2


  parent reply	other threads:[~2010-02-26 12:15 UTC|newest]

Thread overview: 86+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-02-26 12:22 [PATCHSET] workqueue: concurrency managed workqueue, take#4 Tejun Heo
2010-02-26 12:22 ` [PATCH 01/43] sched: consult online mask instead of active in select_fallback_rq() Tejun Heo
2010-02-26 12:22 ` [PATCH 02/43] sched: rename preempt_notifiers to sched_notifiers and refactor implementation Tejun Heo
2010-02-26 12:22 ` [PATCH 03/43] sched: refactor try_to_wake_up() Tejun Heo
2010-02-26 12:22 ` [PATCH 04/43] sched: implement __set_cpus_allowed() Tejun Heo
2010-02-26 12:22 ` [PATCH 05/43] sched: make sched_notifiers unconditional Tejun Heo
2010-02-26 12:22 ` [PATCH 06/43] sched: add wakeup/sleep sched_notifiers and allow NULL notifier ops Tejun Heo
2010-02-26 12:22 ` [PATCH 07/43] sched: implement try_to_wake_up_local() Tejun Heo
2010-02-28 12:33   ` Oleg Nesterov
2010-03-01 14:22     ` Tejun Heo
2010-02-26 12:22 ` [PATCH 08/43] workqueue: change cancel_work_sync() to clear work->data Tejun Heo
2010-02-26 12:22 ` [PATCH 09/43] acpi: use queue_work_on() instead of binding workqueue worker to cpu0 Tejun Heo
2010-02-26 12:22 ` [PATCH 10/43] stop_machine: reimplement without using workqueue Tejun Heo
2010-02-28 14:11   ` Oleg Nesterov
2010-03-01 15:07     ` Tejun Heo
2010-03-01 15:37       ` Oleg Nesterov
2010-03-01 16:36         ` Tejun Heo
2010-03-01 16:50           ` Oleg Nesterov
2010-03-01 18:02             ` Tejun Heo
2010-02-28 14:34   ` Oleg Nesterov
2010-03-01 15:11     ` Tejun Heo
2010-03-01 15:41       ` Oleg Nesterov
2010-02-26 12:22 ` [PATCH 11/43] workqueue: misc/cosmetic updates Tejun Heo
2010-02-26 12:22 ` [PATCH 12/43] workqueue: merge feature parameters into flags Tejun Heo
2010-02-26 12:22 ` [PATCH 13/43] workqueue: define masks for work flags and conditionalize STATIC flags Tejun Heo
2010-02-26 12:22 ` [PATCH 14/43] workqueue: separate out process_one_work() Tejun Heo
2010-02-26 12:22 ` [PATCH 15/43] workqueue: temporarily disable workqueue tracing Tejun Heo
2010-02-26 12:22 ` [PATCH 16/43] workqueue: kill cpu_populated_map Tejun Heo
2010-02-28 16:00   ` Oleg Nesterov
2010-03-01 15:32     ` Tejun Heo
2010-03-01 15:50       ` Oleg Nesterov
2010-03-01 16:19         ` Tejun Heo
2010-02-26 12:22 ` [PATCH 17/43] workqueue: update cwq alignement Tejun Heo
2010-02-28 17:12   ` Oleg Nesterov
2010-03-01 16:40     ` Tejun Heo
2010-02-26 12:22 ` [PATCH 18/43] workqueue: reimplement workqueue flushing using color coded works Tejun Heo
2010-02-28 20:31   ` Oleg Nesterov
2010-03-01 17:33     ` Tejun Heo
2010-03-01 19:47       ` Oleg Nesterov
2010-02-26 12:22 ` [PATCH 19/43] workqueue: introduce worker Tejun Heo
2010-02-26 12:22 ` [PATCH 20/43] workqueue: reimplement work flushing using linked works Tejun Heo
2010-03-01 14:53   ` Oleg Nesterov
2010-03-01 18:00     ` Tejun Heo
2010-03-01 18:51       ` Oleg Nesterov
2010-02-26 12:22 ` [PATCH 21/43] workqueue: implement per-cwq active work limit Tejun Heo
2010-02-26 12:22 ` [PATCH 22/43] workqueue: reimplement workqueue freeze using max_active Tejun Heo
2010-02-26 12:23 ` [PATCH 23/43] workqueue: introduce global cwq and unify cwq locks Tejun Heo
2010-02-26 12:23 ` [PATCH 24/43] workqueue: implement worker states Tejun Heo
2010-02-26 12:23 ` [PATCH 25/43] workqueue: reimplement CPU hotplugging support using trustee Tejun Heo
2010-02-26 12:23 ` [PATCH 26/43] workqueue: make single thread workqueue shared worker pool friendly Tejun Heo
2010-02-26 12:23 ` [PATCH 27/43] workqueue: add find_worker_executing_work() and track current_cwq Tejun Heo
2010-02-26 12:23 ` [PATCH 28/43] workqueue: carry cpu number in work data once execution starts Tejun Heo
2010-02-28  7:08   ` [PATCH UPDATED " Tejun Heo
2010-02-26 12:23 ` [PATCH 29/43] workqueue: implement WQ_NON_REENTRANT Tejun Heo
2010-02-26 12:23 ` [PATCH 30/43] workqueue: use shared worklist and pool all workers per cpu Tejun Heo
2010-02-26 12:23 ` [PATCH 31/43] workqueue: implement concurrency managed dynamic worker pool Tejun Heo
2010-02-26 12:23 ` [PATCH 32/43] workqueue: increase max_active of keventd and kill current_is_keventd() Tejun Heo
2010-02-26 12:23 ` [PATCH 33/43] workqueue: add system_wq, system_long_wq and system_nrt_wq Tejun Heo
2010-02-26 12:23 ` [PATCH 34/43] workqueue: implement DEBUGFS/workqueue Tejun Heo
2010-02-28  7:13   ` [PATCH UPDATED " Tejun Heo
2010-02-26 12:23 ` [PATCH 35/43] workqueue: implement several utility APIs Tejun Heo
2010-02-28  7:15   ` [PATCH UPDATED " Tejun Heo
2010-02-26 12:23 ` Tejun Heo [this message]
2010-02-26 12:23 ` [PATCH 37/43] async: use workqueue for worker pool Tejun Heo
2010-02-26 12:23 ` [PATCH 38/43] fscache: convert object to use workqueue instead of slow-work Tejun Heo
2010-02-26 12:23 ` [PATCH 39/43] fscache: convert operation " Tejun Heo
2010-02-26 12:23 ` [PATCH 40/43] fscache: drop references to slow-work Tejun Heo
2010-02-26 12:23 ` [PATCH 41/43] cifs: use workqueue instead of slow-work Tejun Heo
2010-02-28  7:09   ` [PATCH UPDATED " Tejun Heo
2010-02-26 12:23 ` [PATCH 42/43] gfs2: " Tejun Heo
2010-02-28  7:10   ` [PATCH UPDATED " Tejun Heo
2010-02-26 12:23 ` [PATCH 43/43] slow-work: kill it Tejun Heo
2010-02-27 22:52 ` [PATCH] workqueue: Fix build on PowerPC Anton Blanchard
2010-02-28  6:08   ` Tejun Heo
2010-02-28  1:00 ` [PATCH] workqueue: Fix a compile warning in work_busy Anton Blanchard
2010-02-28  6:18   ` Tejun Heo
2010-02-28  1:11 ` [PATCHSET] workqueue: concurrency managed workqueue, take#4 Anton Blanchard
2010-02-28  6:32   ` Tejun Heo
2010-03-10 14:52 ` David Howells
2010-03-12  5:03   ` Tejun Heo
2010-03-12 11:23   ` David Howells
2010-03-12 22:55     ` Tejun Heo
2010-03-16 14:38     ` David Howells
2010-03-16 16:03       ` Tejun Heo
2010-03-16 17:18       ` David Howells
2010-04-25  8:09 ` [PATCHSET UPDATED] " 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=1267187000-18791-37-git-send-email-tj@kernel.org \
    --to=tj@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=andi@firstfloor.org \
    --cc=arjan@linux.intel.com \
    --cc=avi@redhat.com \
    --cc=awalls@radix.net \
    --cc=cl@linux-foundation.org \
    --cc=dhowells@redhat.com \
    --cc=jeff@garzik.org \
    --cc=jens.axboe@oracle.com \
    --cc=jgarzik@pobox.com \
    --cc=johannes@sipsolutions.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=oleg@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rusty@rustcorp.com.au \
    --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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

Powered by JetHome