From mboxrd@z Thu Jan  1 00:00:00 1970
From: Jens Axboe <axboe@kernel.dk>
Subject: Re: blk-mq request allocation stalls
Date: Tue, 13 Jan 2015 07:59:58 -0700
Message-ID: <54B532EE.20700@kernel.dk>
References: <alpine.LNX.2.00.1501071755110.4026@localhost.lm.intel.com>
	<20150109194955.GA32641@redhat.com>
	<54B042FE.2000205@kernel.dk> <54B043FC.8000902@kernel.dk>
	<20150109214015.GA1032@redhat.com> <54B04E94.3010403@kernel.dk>
	<20150109222543.GA1190@redhat.com> <54B071DC.9000307@kernel.dk>
	<20150110014811.GA2384@redhat.com> <54B08779.2080705@kernel.dk>
	<20150110031057.GA2823@redhat.com>
	<54B3DE54.7090909@sandisk.com> <54B3EB4A.9090404@kernel.dk>
	<54B3F255.5080802@sandisk.com> <54B3F78D.2020704@kernel.dk>
	<54B3FE89.200@sandisk.com> <54B3FFAE.4070609@kernel.dk>
	<alpine.LNX.2.00.1501121738000.4026@localhost.lm.intel.com>
	<54B40E8A.6010005@kernel.dk>
	<alpine.LNX.2.00.1501121818510.4026@localhost.lm.intel.com>
	<alpine.LNX.2.00.1501121830010.4026@localhost.lm.intel.com>
Reply-To: device-mapper development <dm-devel@redhat.com>
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"; Format="flowed"
Content-Transfer-Encoding: 7bit
Return-path: <dm-devel-bounces@redhat.com>
In-Reply-To: <alpine.LNX.2.00.1501121830010.4026@localhost.lm.intel.com>
List-Unsubscribe: <https://www.redhat.com/mailman/options/dm-devel>,
	<mailto:dm-devel-request@redhat.com?subject=unsubscribe>
List-Archive: <https://www.redhat.com/archives/dm-devel>
List-Post: <mailto:dm-devel@redhat.com>
List-Help: <mailto:dm-devel-request@redhat.com?subject=help>
List-Subscribe: <https://www.redhat.com/mailman/listinfo/dm-devel>,
	<mailto:dm-devel-request@redhat.com?subject=subscribe>
Sender: dm-devel-bounces@redhat.com
Errors-To: dm-devel-bounces@redhat.com
To: Keith Busch <keith.busch@intel.com>
Cc: Christoph Hellwig <hch@infradead.org>, Bart Van Assche <bart.vanassche@sandisk.com>, device-mapper development <dm-devel@redhat.com>, Jun'ichi Nomura <j-nomura@ce.jp.nec.com>, Mike Snitzer <snitzer@redhat.com>
List-Id: dm-devel.ids

On 01/12/2015 11:35 AM, Keith Busch wrote:
> On Mon, 12 Jan 2015, Keith Busch wrote:
>> Oh, let's look at "__blk_rq_prep_clone". dm calls that after
>> blk_get_request() for the blk-mq based multipath types and overrides the
>> destinations cmd_flags with the source's even though the source was not
>> allocated from a blk-mq based queue, much less a shared tag.
>
> Untested patch. This will also preserve the failfast cmd_flag dm-mpath
> set after allocating.
>
> ---
> diff --git a/block/blk-core.c b/block/blk-core.c
> index 7e78931..6201090 100644
> --- a/block/blk-core.c
> +++ b/block/blk-core.c
> @@ -2895,7 +2895,10 @@ EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
>   static void __blk_rq_prep_clone(struct request *dst, struct request *src)
>   {
>       dst->cpu = src->cpu;
> -    dst->cmd_flags = (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE;
> +    if (dst->q->mq_ops)
> +        dst->cmd_flags |= (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE;
> +    else
> +        dst->cmd_flags = (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE;

Making the two cases different is a bit... nonsensical. We should do 
this for both cases, if safe, or move the MQ_INFLIGHT flag and expand 
the CLONE_MASK.

-- 
Jens Axboe