Re: fix blk-mq for SPI hosts

2014-10-23 Thread Jens Axboe
On 10/23/2014 11:14 AM, Christoph Hellwig wrote: > On Thu, Oct 23, 2014 at 01:49:07PM +0300, Meelis Roos wrote: >>> ping? >> >> Sorry, forgot to reply. Yes, it worked fine, on the initial Ultra 1 and >> additionally on Ultra 2 too. > > Thanks! > > Can I get a review from Jens and some SCSI devel

Re: fix blk-mq for SPI hosts

2014-10-23 Thread Christoph Hellwig
On Thu, Oct 23, 2014 at 01:49:07PM +0300, Meelis Roos wrote: > > ping? > > Sorry, forgot to reply. Yes, it worked fine, on the initial Ultra 1 and > additionally on Ultra 2 too. Thanks! Can I get a review from Jens and some SCSI developers, too? Jens, are you fine taking the blkdev.h revert th

Re: fix blk-mq for SPI hosts

2014-10-23 Thread Meelis Roos
> ping? Sorry, forgot to reply. Yes, it worked fine, on the initial Ultra 1 and additionally on Ultra 2 too. > On Sun, Oct 19, 2014 at 05:13:56PM +0200, Christoph Hellwig wrote: > > Fix the assumption that we can treat all blk-mq requests as tagged. For > > traditional SCSI that's wrong, as bei

Re: fix blk-mq for SPI hosts

2014-10-23 Thread Christoph Hellwig
ping? On Sun, Oct 19, 2014 at 05:13:56PM +0200, Christoph Hellwig wrote: > Fix the assumption that we can treat all blk-mq requests as tagged. For > traditional SCSI that's wrong, as being tagged has a very explicit meaning > on the wire. > > This is a little bit different from the version Meeli

fix blk-mq for SPI hosts

2014-10-19 Thread Christoph Hellwig
Fix the assumption that we can treat all blk-mq requests as tagged. For traditional SCSI that's wrong, as being tagged has a very explicit meaning on the wire. This is a little bit different from the version Meelis tested earlier, but the concept is the same. I didn't want to add a Tested-by tag