From a7ad9ddeb528b91de03cedeef34532dc0ba77bfd Mon Sep 17 00:00:00 2001 From: Dust Li Date: Mon, 27 Dec 2021 20:38:06 +0800 Subject: RDMA/mlx5: Print wc status on CQE error and dump needed mlx5_handle_error_cqe() only dump the content of the CQE which is raw hex data, and not straighforward for debug. Print WC status message when we got CQE error and dump is need. Here is an example of how the dmesg log looks like with this: infiniband mlx5_0: mlx5_handle_error_cqe:333:(pid 0): WC error: 10, message: remote access error infiniband mlx5_0: dump_cqe:272:(pid 0): dump error cqe 00000000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00000010: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00000020: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00000030: 00 00 00 00 00 00 88 13 08 03 61 b3 1e a1 42 d3 Link: https://lore.kernel.org/r/20211227123806.47530-1-dust.li@linux.alibaba.com Signed-off-by: Dust Li Acked-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/cq.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'drivers/infiniband') diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index a190fb581591..08371a80fdc2 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -328,8 +328,11 @@ static void mlx5_handle_error_cqe(struct mlx5_ib_dev *dev, } wc->vendor_err = cqe->vendor_err_synd; - if (dump) + if (dump) { + mlx5_ib_warn(dev, "WC error: %d, Message: %s\n", wc->status, + ib_wc_status_msg(wc->status)); dump_cqe(dev, cqe); + } } static void handle_atomics(struct mlx5_ib_qp *qp, struct mlx5_cqe64 *cqe64, -- cgit v1.2.3