On Fri, Jul 21, 2017 at 01:46:10PM +0200, Christoph Hellwig wrote:
> The blk-mq code lacks support for looking at the rpm_status field, tracking
> active requests and the RQF_PM flag.
>
> Due to the default switch to blk-mq for scsi people start to run into
> suspend / resume issue due to this fact, so make sure we disable the runtime
> PM functionality until it is properly implemented.
>
> Signed-off-by: Christoph Hellwig <hch@xxxxxx>
> ---
> block/blk-core.c | 4 ++++
> 1 file changed, 4 insertions(+)
>
> diff --git a/block/blk-core.c b/block/blk-core.c
> index 970b9c9638c5..dbecbf4a64e0 100644
> --- a/block/blk-core.c
> +++ b/block/blk-core.c
> @@ -3421,6 +3421,10 @@ EXPORT_SYMBOL(blk_finish_plug);
> */
> void blk_pm_runtime_init(struct request_queue *q, struct device *dev)
> {
> + /* not support for RQF_PM and ->rpm_status in blk-mq yet */
The big problem should be that the SCSI device can be runtime suspended,
but never to get back in case of blk-mq.
> + if (q->mq_ops)
> + return;
> +
> q->dev = dev;
> q->rpm_status = RPM_ACTIVE;
> pm_runtime_set_autosuspend_delay(q->dev, -1);
> --
> 2.11.0
>
Either blk-mq or scsi-mq isn't ready for runtime PM, so
we can't enable runtime PM until both are ready.
Reviewed-by: Ming Lei <ming.lei@xxxxxxxxxx>
--
Ming
