>Subject: Re: [PATCH v5 rdma-next] RDMA/umem: Combine contiguous PAGE_SIZE >regions in SGEs > >On Wed, Apr 03, 2019 at 03:54:42PM -0300, Jason Gunthorpe wrote: >> On Tue, Apr 02, 2019 at 02:52:52PM -0500, Shiraz Saleem wrote: >> > Combine contiguous regions of PAGE_SIZE pages into single scatter >> > list entries while adding to the scatter table. This minimizes the >> > number of the entries in the scatter list and reduces the DMA >> > mapping overhead, particularly with the IOMMU. >> > >> > Set default max_seg_size in core for IB devices to 2G and do not >> > combine if we exceed this limit. >> > >> > Also, purge npages in struct ib_umem as we now DMA map the umem SGL >> > with sg_nents, and update remaining non ODP drivers that use >> > umem->npages. >> > Move npages tracking to ib_umem_odp as ODP drivers still need it. >> > >> > This patch should be applied post >> > https://patchwork.kernel.org/cover/10857607/ >> > >> > Suggested-by: Jason Gunthorpe <jgg@xxxxxxxx> >> > Reviewed-by: Michael J. Ruhl <michael.j.ruhl@xxxxxxxxx> >> > Reviewed-by: Ira Weiny <ira.weiny@xxxxxxxxx> >> > Acked-by: Adit Ranadive <aditr@xxxxxxxxxx> >> > Signed-off-by: Shiraz Saleem <shiraz.saleem@xxxxxxxxx> >> > Tested-by: Gal Pressman <galpress@xxxxxxxxxx> >> > Tested-by: Selvin Xavier <selvin.xavier@xxxxxxxxxxxx> >> >> Okay, lets go with this! >> >> The other patches only impact the two drivers, so lets respin them and >> go ahead too. > >Hm. Shiraz, I just noticed this: > >--- a/drivers/infiniband/core/umem.c >+++ b/drivers/infiniband/core/umem.c >@@ -380,8 +380,8 @@ int ib_umem_copy_from(void *dst, struct ib_umem *umem, >size_t offset, > return -EINVAL; > } > >- ret = sg_pcopy_to_buffer(umem->sg_head.sgl, ib_umem_num_pages(umem), >- dst, length, offset + ib_umem_offset(umem)); >+ ret = sg_pcopy_to_buffer(umem->sg_head.sgl, umem->sg_nents, dst, length, >+ offset + ib_umem_offset(umem)); > > if (ret < 0) > return ret; > >Yes? > Ugh! Yes :( I ll send a patch. Shiraz
