Shiraz, Saleem 48b586ac36 RDMA/cxgb4: Use for_each_sg_dma_page iterator on umem SGL
Use the for_each_sg_dma_page iterator variant to walk the umem DMA-mapped
SGL and get the page DMA address. This avoids the extra loop to iterate
pages in the SGE when for_each_sg iterator is used.

Additionally, purge umem->page_shift usage in the driver as its only
relevant for ODP MRs. Use system page size and shift instead.

Signed-off-by: Shiraz, Saleem <shiraz.saleem@intel.com>
Acked-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2019-02-11 15:24:55 -07:00
..
2019-01-26 15:03:43 -08:00
2019-01-20 09:12:50 +12:00
2018-12-31 17:32:35 -08:00
2018-12-29 08:20:44 -07:00
2019-01-25 13:03:34 -10:00
2019-01-09 19:20:31 -05:00
2019-01-11 00:15:04 +01:00
2019-01-26 11:14:25 +01:00
2019-01-15 06:24:36 +12:00
2019-01-30 09:30:03 -08:00
2019-02-01 16:56:30 -08:00
2019-01-05 11:30:37 -08:00
2018-12-28 16:52:18 -08:00
2019-01-26 12:42:41 -08:00
2019-01-31 23:06:17 -08:00
2019-01-05 11:23:17 -08:00
2019-01-25 12:57:09 -10:00
2018-12-29 13:03:29 -08:00
2018-12-24 12:06:56 +01:00
2019-01-01 13:24:31 -08:00
2019-02-02 10:12:53 -08:00
2019-02-02 10:12:53 -08:00
2019-01-22 20:54:00 -05:00
2018-12-31 13:06:30 -08:00
2019-02-02 10:26:14 -08:00
2018-12-28 20:54:57 -08:00
2019-01-18 12:58:20 +01:00
2019-01-28 22:53:09 -08:00
2019-01-25 12:58:40 -10:00
2018-12-29 13:40:29 -08:00