[PATCH 4/6] blk-mq: avoid to map CPU into stale hw queue
Ming Lei
ming.lei at redhat.com
Tue Dec 12 07:12:20 PST 2017
On Tue, Dec 12, 2017 at 03:12:43PM +0100, Christoph Hellwig wrote:
> On Tue, Dec 12, 2017 at 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
More information about the Linux-nvme
mailing list