common/mlx5: fix memory region range calculation
authorDmitry Kozlyuk <dkozlyuk@nvidia.com>
Thu, 31 Mar 2022 14:33:16 +0000 (17:33 +0300)
committerRaslan Darawsheh <rasland@nvidia.com>
Thu, 21 Apr 2022 10:47:37 +0000 (12:47 +0200)
MR end for a mempool chunk may be calculated incorrectly.
For example, for chunk with addr=1.5M and len=1M with 2M page size
the range would be [0, 2M), while the proper result is [0, 4M).
Fix the calculation.

Fixes: 690b2a88c2f7 ("common/mlx5: add mempool registration facilities")
Cc: stable@dpdk.org
Signed-off-by: Dmitry Kozlyuk <dkozlyuk@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
drivers/common/mlx5/mlx5_common_mr.c

index fa27bd9..06e4c8f 100644 (file)
@@ -1289,11 +1289,12 @@ mlx5_range_from_mempool_chunk(struct rte_mempool *mp, void *opaque,
                              unsigned int idx)
 {
        struct mlx5_range *ranges = opaque, *range = &ranges[idx];
+       uintptr_t start = (uintptr_t)memhdr->addr;
        uint64_t page_size = rte_mem_page_size();
 
        RTE_SET_USED(mp);
-       range->start = RTE_ALIGN_FLOOR((uintptr_t)memhdr->addr, page_size);
-       range->end = RTE_ALIGN_CEIL(range->start + memhdr->len, page_size);
+       range->start = RTE_ALIGN_FLOOR(start, page_size);
+       range->end = RTE_ALIGN_CEIL(start + memhdr->len, page_size);
 }
 
 /**