Christoph, [CC'ing also Anton, he improved the old driver a lot.] Anton, this patch is based on: https://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git/?h=mq-conversions Am Montag, 15. Oktober 2018, 08:56:37 CEST schrieb Christoph Hellwig: > There is no good reason to create a scatterlist in the ubd driver, > it can just iterate the request directly. > > Signed-off-by: Christoph Hellwig <hch@xxxxxx> > --- > > Now that we have the blk-mq conversion something like the patch below > should help to simplify the driver even further. hm, this breaks UML. Every filesystem fails to mount. I did some very rough tests, it seems that the driver fails to read data correctly as soon the upper layer tries to get more than 4096 bytes at once out of the block device. IOW: dd if=/dev/ubda bs=4096 count=1 skip=0 2>/dev/null| md5sum - is good. As soon I set bs to something greater it returns garbage. Later this day I might have some cycles left to debug further. Thanks, //richard
