RDMA/umem: Split ib_umem_num_pages() into ib_umem_num_dma_blocks()

ib_umem_num_pages() should only be used by things working with the SGL in
CPU pages directly.

Drivers building DMA lists should use the new ib_num_dma_blocks() which
returns the number of blocks rdma_umem_for_each_block() will return.

To make this general for DMA drivers requires a different implementation.
Computing DMA block count based on umem->address only works if the
requested page size is < PAGE_SIZE and/or the IOVA == umem->address.

Instead the number of DMA pages should be computed in the IOVA address
space, not umem->address. Thus the IOVA has to be stored inside the umem
so it can be used for these calculations.

For now set it to umem->address by default and fix it up if
ib_umem_find_best_pgsz() was called. This allows drivers to be converted
to ib_umem_num_dma_blocks() safely.

Link: https://lore.kernel.org/r/6-v2-270386b7e60b+28f4-umem_1_jgg@nvidia.com
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

5 files changed, 11 insertions, 6 deletions

diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index fb7630e7aac3..b57dbb14de83 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -161,7 +161,7 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem,
 	if (WARN_ON(!(pgsz_bitmap & GENMASK(PAGE_SHIFT, 0))))
 		return 0;
 
-	va = virt;
+	umem->iova = va = virt;
 	/* The best result is the smallest page size that results in the minimum
 	 * number of required pages. Compute the largest page size that could
 	 * work based on VA address bits that don't change.
@@ -240,6 +240,11 @@ struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr,
 	umem->ibdev      = device;
 	umem->length     = size;
 	umem->address    = addr;
+	/*
+	 * Drivers should call ib_umem_find_best_pgsz() to set the iova
+	 * correctly.
+	 */
+	umem->iova = addr;
 	umem->writable   = ib_access_writable(access);
 	umem->owning_mm = mm = current->mm;
 	mmgrab(mm);
diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index 82afdb1987ef..22c8f5745047 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -548,7 +548,7 @@ struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 
 	shift = PAGE_SHIFT;
 
-	n = ib_umem_num_pages(mhp->umem);
+	n = ib_umem_num_dma_blocks(mhp->umem, 1 << shift);
 	err = alloc_pbl(mhp, n);
 	if (err)
 		goto err_umem_release;
diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c
index c19ec9fd8a63..13de3d2edd34 100644
--- a/drivers/infiniband/hw/mlx5/mem.c
+++ b/drivers/infiniband/hw/mlx5/mem.c
@@ -169,8 +169,8 @@ void mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
 			  int page_shift, __be64 *pas, int access_flags)
 {
 	return __mlx5_ib_populate_pas(dev, umem, page_shift, 0,
-				      ib_umem_num_pages(umem), pas,
-				      access_flags);
+				      ib_umem_num_dma_blocks(umem, PAGE_SIZE),
+				      pas, access_flags);
 }
 int mlx5_ib_get_buf_offset(u64 addr, int page_shift, u32 *offset)
 {
diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c
index cd8980d51f57..82ee252fe5aa 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.c
+++ b/drivers/infiniband/hw/mthca/mthca_provider.c
@@ -881,7 +881,7 @@ static struct ib_mr *mthca_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 		goto err;
 	}
 
-	n = ib_umem_num_pages(mr->umem);
+	n = ib_umem_num_dma_blocks(mr->umem, PAGE_SIZE);
 
 	mr->mtt = mthca_alloc_mtt(dev, n);
 	if (IS_ERR(mr->mtt)) {
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c
index 91f0957e6115..e80848bfb3bd 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_mr.c
@@ -133,7 +133,7 @@ struct ib_mr *pvrdma_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 		return ERR_CAST(umem);
 	}
 
-	npages = ib_umem_num_pages(umem);
+	npages = ib_umem_num_dma_blocks(umem, PAGE_SIZE);
 	if (npages < 0 || npages > PVRDMA_PAGE_DIR_MAX_PAGES) {
 		dev_warn(&dev->pdev->dev, "overflow %d pages in mem region\n",
 			 npages);