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>

1 files changed, 12 insertions, 3 deletions

diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index b880512ba95f..cf001d4e0a4f 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -17,6 +17,7 @@ struct ib_umem_odp;
 struct ib_umem {
 	struct ib_device       *ibdev;
 	struct mm_struct       *owning_mm;
+	u64 iova;
 	size_t			length;
 	unsigned long		address;
 	u32 writable : 1;
@@ -33,11 +34,17 @@ static inline int ib_umem_offset(struct ib_umem *umem)
 	return umem->address & ~PAGE_MASK;
 }
 
+static inline size_t ib_umem_num_dma_blocks(struct ib_umem *umem,
+					    unsigned long pgsz)
+{
+	return (size_t)((ALIGN(umem->iova + umem->length, pgsz) -
+			 ALIGN_DOWN(umem->iova, pgsz))) /
+	       pgsz;
+}
+
 static inline size_t ib_umem_num_pages(struct ib_umem *umem)
 {
-	return (ALIGN(umem->address + umem->length, PAGE_SIZE) -
-		ALIGN_DOWN(umem->address, PAGE_SIZE)) >>
-	       PAGE_SHIFT;
+	return ib_umem_num_dma_blocks(umem, PAGE_SIZE);
 }
 
 static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter,
@@ -55,6 +62,8 @@ static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter,
  * pgsz must be <= PAGE_SIZE or computed by ib_umem_find_best_pgsz(). The
  * returned DMA blocks will be aligned to pgsz and span the range:
  * ALIGN_DOWN(umem->address, pgsz) to ALIGN(umem->address + umem->length, pgsz)
+ *
+ * Performs exactly ib_umem_num_dma_blocks() iterations.
  */
 #define rdma_umem_for_each_dma_block(umem, biter, pgsz)                        \
 	for (__rdma_umem_block_iter_start(biter, umem, pgsz);                  \