linux-kernel - Re: [PATCH v9 4/4] sd: change to auto suspend mode

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20130218032039.GA25348@aaronlu.sh.intel.com>
Date:	Mon, 18 Feb 2013 11:20:39 +0800
From:	Aaron Lu <aaron.lu@...el.com>
To:	Alan Stern <stern@...land.harvard.edu>
Cc:	Jens Axboe <axboe@...nel.dk>, "Rafael J. Wysocki" <rjw@...k.pl>,
	James Bottomley <James.Bottomley@...senpartnership.com>,
	linux-pm@...r.kernel.org, linux-scsi@...r.kernel.org,
	linux-kernel@...r.kernel.org, linux-ide@...r.kernel.org,
	Aaron Lu <aaron.lwe@...il.com>,
	Shane Huang <shane.huang@....com>
Subject: Re: [PATCH v9 4/4] sd: change to auto suspend mode

On Wed, Feb 06, 2013 at 10:51:19AM -0500, Alan Stern wrote:
> On Wed, 6 Feb 2013, Aaron Lu wrote:
> 
> > > The "if (err == -EAGAIN)" test and the call to pm_schedule_suspend seem
> > > to have been dropped since v8 of this series.  It looks like they ought
> > > to be moved into sdev_runtime_suspend.
> > 
> > I thought they were no longer needed...
> 
> You did not mention this in the patch description.

Sorry about that.

> 
> > For sd, we have request based rutime PM and the PM core will always try
> > to autosuspend the device with the timer; and for sr, the poll will
> > trigger suspend constantly.
> 
> What if the poll has been disabled?
> 
> > And for both, we don't return -EAGAIN anyway.
> > So I suppose that code is not necessary?
> 
> You could replace it with WARN_ON(err == -EAGAIN).  That way if some 
> SCSI driver does return -EAGAIN in the future, people will know 
> something is wrong.

Placing a WARN_ON there seems to suggest drivers should not return
-EAGAIN, so I think I'll just add back those dropped code to
sdev_runtime_suspend as you have suggested like this:

static int sdev_runtime_suspend(struct device *dev)
{
	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
	int (*cb)(struct device *) = pm ? pm->runtime_suspend : NULL;
	struct scsi_device *sdev = to_scsi_device(dev);
	int ret;

	if (sdev->request_queue->dev)
		return sdev_blk_runtime_suspend(sdev, cb);

	ret = scsi_dev_type_suspend(dev, cb);
	if (ret == -EAGAIN)
		pm_schedule_suspend(dev, jiffies_to_msecs(
					round_jiffies_up_relative(HZ/10)));
	return ret;
}

Does this look OK?

> 
> > BTW, I'll be on vocation till 02/17, and I don't have access to the
> > internet in my hometown, but please feel free to drop any comments and
> > I'll check them when I get back.
> 
> I'm going on vacation next week too.  Enjoy your trip.

Thanks, the trip was great.

-Aaron

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/