From mboxrd@z Thu Jan  1 00:00:00 1970
From: ming.lei@redhat.com (Ming Lei)
Date: Tue, 12 Dec 2017 23:12:20 +0800
Subject: [PATCH 4/6] blk-mq: avoid to map CPU into stale hw queue
In-Reply-To: <20171212141243.GA7849@lst.de>
References: <20171212110232.12495-1-ming.lei@redhat.com>
 <20171212110232.12495-5-ming.lei@redhat.com>
 <20171212141243.GA7849@lst.de>
Message-ID: <20171212151219.GB15078@ming.t460p>

On Tue, Dec 12, 2017@03:12:43PM +0100, Christoph Hellwig wrote:
> On Tue, Dec 12, 2017@07:02:30PM +0800, Ming Lei wrote:
> > blk_mq_pci_map_queues() may not map one CPU into any hw queue, but its
> > previous map isn't cleared yet, and may point to one stale hw queue
> > index.
> > 
> > This patch fixes the following issue by clearing the mapping table before
> > setting it up in blk_mq_pci_map_queues().
> 
> This needs to be done in the caller intead of the transport specific
> queue map helpers.

OK, there is such issue on other .map_queues() too, such as virtio, ...

Thanks,
Ming