From: Prathamesh Deshpande Date: Sun, 26 Apr 2026 13:23:41 +0000 (+0100) Subject: RDMA/mlx5: Fix UMR XLT cleanup on ODP populate failure X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=1eae35b37923cb71b0cb5136d00671440d488b9f;p=thirdparty%2Fkernel%2Flinux.git RDMA/mlx5: Fix UMR XLT cleanup on ODP populate failure mlx5r_umr_update_xlt() allocates and DMA maps an XLT buffer with mlx5r_umr_create_xlt(). The buffer is released by the common cleanup path through mlx5r_umr_unmap_free_xlt(). After mlx5_odp_populate_xlt() became fallible, its error path returned directly and skipped that cleanup. This leaks the XLT DMA mapping and buffer. If the emergency XLT page was used, it also leaves xlt_emergency_page_mutex locked. Break out of the loop so execution falls through the existing cleanup path. Fixes: 1efe8c0670d6 ("RDMA/core: Convert UMEM ODP DMA mapping to caching IOVA and page linkage") Signed-off-by: Prathamesh Deshpande Link: https://patch.msgid.link/20260426132356.22264-1-prathameshdeshpande7@gmail.com Signed-off-by: Leon Romanovsky --- diff --git a/drivers/infiniband/hw/mlx5/umr.c b/drivers/infiniband/hw/mlx5/umr.c index 29488fba21a03..71f331ce6d894 100644 --- a/drivers/infiniband/hw/mlx5/umr.c +++ b/drivers/infiniband/hw/mlx5/umr.c @@ -915,7 +915,7 @@ int mlx5r_umr_update_xlt(struct mlx5_ib_mr *mr, u64 idx, int npages, */ err = mlx5_odp_populate_xlt(xlt, idx, npages, mr, flags); if (err) - return err; + break; dma_sync_single_for_device(ddev, sg.addr, sg.length, DMA_TO_DEVICE); sg.length = ALIGN(size_to_map, MLX5_UMR_FLEX_ALIGNMENT);