[PATCH v8 1/5] RDMA/umem: Support importing dma-buf as user memory region

[Xiong, Jianxin]

> -----Original Message-----
> From: Jason Gunthorpe <jgg at ziepe.ca>
> Sent: Friday, November 06, 2020 8:40 AM
> To: Xiong, Jianxin <jianxin.xiong at intel.com>
> Cc: linux-rdma at vger.kernel.org; dri-devel at lists.freedesktop.org; Doug Ledford <dledford at redhat.com>; Leon Romanovsky
> <leon at kernel.org>; Sumit Semwal <sumit.semwal at linaro.org>; Christian Koenig <christian.koenig at amd.com>; Vetter, Daniel
> <daniel.vetter at intel.com>
> Subject: Re: [PATCH v8 1/5] RDMA/umem: Support importing dma-buf as user memory region
> 
> On Fri, Nov 06, 2020 at 04:34:07PM +0000, Xiong, Jianxin wrote:
> 
> > > The user could specify a length that is beyond the dma buf, can the
> > > dma buf length be checked during get?
> >
> > In order to check the length, the buffer needs to be mapped. That can be done.
> 
> Do DMA bufs even have definitate immutable lengths? Going to be a probelm if they can shrink

Good question. The buffer itself has fixed size. If for whatever reason the mapping
is not full it must be temporary. If that does happen ib_umem_dmabuf_map_pages
will undo the mapping and return error. It will be retried later via the pagefault handler.

> 
> > > Also page_size can be 0 because iova is not OK. iova should be
> > > checked for alignment during get as well:
> > >
> > >   iova & (PAGE_SIZE-1) == umem->addr & (PAGE_SIZE-1)
> >
> > If ib_umem_dmabuf_map_pages is called during get this error is automatically caught.
> 
> The ib_umem_find_best_pgsz() checks this equation, yes.
> 
> So you'd map the sgl before allocating the mkey? This then checks the length and iova?

Yes

> 
> Jason