From mboxrd@z Thu Jan  1 00:00:00 1970
From: guenther@tum.de (Stephan =?utf-8?Q?G=C3=BCnther?=)
Date: Sat, 21 Nov 2015 13:16:11 +0100
Subject: [PATCH 1/1] nvme: temporary fix for Apple NVMe controller reset
In-Reply-To: <20151121082041.GA17935@infradead.org>
References: <6ed9ad799884d9d4bdbfbdf94185c3f2@localhost>
 <20151121082041.GA17935@infradead.org>
Message-ID: <4e6635a1510af922268cd5a6a242f5bb@localhost>

On 2015/November/21 12:20, Christoph Hellwig wrote:
> Hi Stephan,
> 
> > +	/*
> > +	 * Temporary fix for the Apple controller found in the MacBook8,1 and
> > +	 * some MacBook7,1 to avoid controller resets and data loss.
> > +	 */
> > +	if (pdev->vendor == PCI_VENDOR_ID_APPLE && pdev->device == 0x2001)
> > +		dev->q_depth = 2;
> 
> Can you add a dev_warn() here?  A NVMe device with queue depth is going
> to perform bady, and we should tell people that we're applying a crude
> workaround.

I'll resend the patch with an updated commit message and dev_warn().

Interestingly, I cannot really complain about performance with that
patch applied. That little notebook behaves really well. But that queue
depth cannot be the solution of course.

> 
> Otherwise this looks fine to me to get you guys going, but I really hope
> we'll find the root cause soon.

I wish Apple would show any interest in that matter...