[openib-general] Re: [PATCH 5/6] [RFC] iser handling of memory for RDMA

[Michael S. Tsirkin]

Quoting r. Christoph Hellwig <hch at lst.de>:
> Subject: Re: [PATCH 5/6] [RFC] iser handling of memory for RDMA
> 
> > use kmap_atomic instead of page_address in the code copying from/to SG
> > which is unaligned for rdma
> 
> this isn't entirely correct I think.  iser_finalize_rdma_unaligned_sg
> is called from a tasklist, which is softirq context, so you can't use
> KM_USER0 there. KM_SOFTIRQ0 should probably work.  Otoh tasklets are not
> very scalable because tasklets of a type a serialized against running
> at multiple cpus, so maybe you should switch to a different mechanisms.

You could just switch to using a workqueue - its already per cpu and
KM_USER0 is legal there.

-- 
Michael S. Tsirkin
Staff Engineer, Mellanox Technologies