[PATCH 5.9 432/757] RDMA/umem: Fix ib_umem_find_best_pgsz() for mappings that cross a page boundary

[Greg Kroah-Hartman]

From: Jason Gunthorpe <jgg@xxxxxxxxxx>

[ Upstream commit a40c20dabdf9045270767c75918feb67f0727c89 ]

It is possible for a single SGL to span an aligned boundary, eg if the SGL
is

  61440 -> 90112

Then the length is 28672, which currently limits the block size to
32k. With a 32k page size the two covering blocks will be:

  32768->65536 and 65536->98304

However, the correct answer is a 128K block size which will span the whole
28672 bytes in a single block.

Instead of limiting based on length figure out which high IOVA bits don't
change between the start and end addresses. That is the highest useful
page size.

Fixes: 4a35339958f1 ("RDMA/umem: Add API to find best driver supported page size in an MR")
Link: https://lore.kernel.org/r/1-v2-270386b7e60b+28f4-umem_1_jgg@xxxxxxxxxx
Reviewed-by: Leon Romanovsky <leonro@xxxxxxxxxx>
Reviewed-by: Shiraz Saleem <shiraz.saleem@xxxxxxxxx>
Signed-off-by: Jason Gunthorpe <jgg@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
 drivers/infiniband/core/umem.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 831bff8d52e54..09539dd764ec0 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -156,8 +156,13 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem,
 		return 0;
 
 	va = virt;
-	/* max page size not to exceed MR length */
-	mask = roundup_pow_of_two(umem->length);
+	/* 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.
+	 */
+	mask = pgsz_bitmap &
+	       GENMASK(BITS_PER_LONG - 1,
+		       bits_per((umem->length - 1 + virt) ^ virt));
 	/* offset into first SGL */
 	pgoff = umem->address & ~PAGE_MASK;
 
-- 
2.25.1