RDMA/mlx5: Split mlx5_ib_update_xlt() into ODP and non-ODP cases

Mixing these together is just a mess, make a dedicated version,
mlx5_ib_update_mr_pas(), which directly loads the whole MTT for a non-ODP
MR.

The split out version can trivially use a simple loop with
rdma_for_each_block() which allows using the core code to compute the MR
pages and avoids seeking in the SGL list after each chunk as the
__mlx5_ib_populate_pas() call required.

Significantly speeds loading large MTTs.

Link: https://lore.kernel.org/r/20201026132314.1336717-5-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

1 files changed, 0 insertions, 64 deletions

diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c
index 779c4a040d8b..92e7621ec858 100644
--- a/drivers/infiniband/hw/mlx5/mem.c
+++ b/drivers/infiniband/hw/mlx5/mem.c
@@ -92,70 +92,6 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr,
 }
 
 /*
- * Populate the given array with bus addresses from the umem.
- *
- * dev - mlx5_ib device
- * umem - umem to use to fill the pages
- * page_shift - determines the page size used in the resulting array
- * offset - offset into the umem to start from,
- *          only implemented for ODP umems
- * num_pages - total number of pages to fill
- * pas - bus addresses array to fill
- * access_flags - access flags to set on all present pages.
-		  use enum mlx5_ib_mtt_access_flags for this.
- */
-void __mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
-			    int page_shift, size_t offset, size_t num_pages,
-			    __be64 *pas, int access_flags)
-{
-	int shift = page_shift - PAGE_SHIFT;
-	int mask = (1 << shift) - 1;
-	int i, k, idx;
-	u64 cur = 0;
-	u64 base;
-	int len;
-	struct scatterlist *sg;
-	int entry;
-
-	i = 0;
-	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
-		len = sg_dma_len(sg) >> PAGE_SHIFT;
-		base = sg_dma_address(sg);
-
-		/* Skip elements below offset */
-		if (i + len < offset << shift) {
-			i += len;
-			continue;
-		}
-
-		/* Skip pages below offset */
-		if (i < offset << shift) {
-			k = (offset << shift) - i;
-			i = offset << shift;
-		} else {
-			k = 0;
-		}
-
-		for (; k < len; k++) {
-			if (!(i & mask)) {
-				cur = base + (k << PAGE_SHIFT);
-				cur |= access_flags;
-				idx = (i >> shift) - offset;
-
-				pas[idx] = cpu_to_be64(cur);
-				mlx5_ib_dbg(dev, "pas[%d] 0x%llx\n",
-					    i >> shift, be64_to_cpu(pas[idx]));
-			}
-			i++;
-
-			/* Stop after num_pages reached */
-			if (i >> shift >= offset + num_pages)
-				return;
-		}
-	}
-}
-
-/*
  * Fill in a physical address list. ib_umem_num_dma_blocks() entries will be
  * filled in the pas array.
  */