Re: [PATCH v4 2/5] IB/core, RDMA RW API: Do not exceed QP SGE send limit

[Leon Romanovsky <leon-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>]

[-- Attachment #1: Type: text/plain, Size: 1521 bytes --]

On Wed, Jul 27, 2016 at 08:24:32AM -0700, Bart Van Assche wrote:
> On 07/27/2016 05:42 AM, Leon Romanovsky wrote:
> >On Thu, Jul 21, 2016 at 01:03:30PM -0700, Bart Van Assche wrote:
> >> static inline u32 rdma_rw_fr_page_list_len(struct ib_device *dev)
> >> {
> >> 	/* arbitrary limit to avoid allocating gigantic resources */
> >>@@ -186,7 +179,8 @@ static int rdma_rw_init_map_wrs(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
> >> 		u64 remote_addr, u32 rkey, enum dma_data_direction dir)
> >> {
> >> 	struct ib_device *dev = qp->pd->device;
> >>-	u32 max_sge = rdma_rw_max_sge(dev, dir);
> >>+	u32 max_sge = dir == DMA_TO_DEVICE ? qp->max_write_sge :
> >>+		      qp->max_read_sge;
> >
> >Bart,
> >I'm sure that I missed something.
> >
> >Can "dir" be DMA_BIDIRECTIONAL?
> >If yes, mxa_sge will be min(max_write_sge, max_read_sge).
> 
> Hello Leon,
> 
> The RDMA R/W API is intended for target drivers. None of the upstream target
> drivers (ib_isert, ib_srpt, nvmet) that use the RDMA R/W API support bidi
> commands today. And even if such support would be added, these target
> drivers should perform RDMA READs and WRITEs in two phases. So I do not
> expect that "dir" will ever be equal to DMA_BIDIRECTIONAL in the above code.
> 
> Bart.

Thanks Bart.

> --
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 819 bytes --]