From mboxrd@z Thu Jan  1 00:00:00 1970
From: hch@infradead.org (Christoph Hellwig)
Date: Thu, 17 May 2018 08:35:05 -0700
Subject: [PATCH] nvme: handle completions outside of the queue lock
In-Reply-To: <6df24c77-bdc8-4265-30ea-8140eedc1fbd@kernel.dk>
References: <da619fe4-a9ea-57e9-a731-e59a9043970e@kernel.dk>
 <20180517034750.GA22063@localhost.localdomain>
 <20180517071651.GC30079@infradead.org>
 <20180517142159.GC22063@localhost.localdomain>
 <39c39949-1aea-4892-1d80-5ea58d1ced24@kernel.dk>
 <20180517153007.GB19042@infradead.org>
 <6df24c77-bdc8-4265-30ea-8140eedc1fbd@kernel.dk>
Message-ID: <20180517153505.GA28489@infradead.org>

On Thu, May 17, 2018@09:33:34AM -0600, Jens Axboe wrote:
> The poll issue is almost moot imho, unless you have a ton of other
> IO on the same hardware queue while you poll. It'll work fine, the
> testing I ran didn't find anything. Agree the volatile should have
> been a prep, but again not really a major thing.

But it's not a whole lot of work to redo it either.  I'll volunteer
doing it while spending time on a call :)