On Wed, Sep 04, 2019 at 02:54:26PM +0200, Thomas HellstrÃm (VMware) wrote:
On 9/4/19 2:17 PM, Christoph Hellwig wrote:You are supposed to return SCSI_MLQUEUE_HOST_BUSY in that case,
A call to dma_max_mapping_size() to limit the maximum I/O size solvesHmm, OK. I guess with a sufficient queue depth and many mappings waiting for
that problem. With the latest kernel that should actually be done
automatically by the SCSI midlayer for you.
DMA completion, the SWIOTLB may fill up anyway...
I'll see if I can come up with something.
which means that the kernel won't send more commands until another