From: Xi Wang wangxi11@huawei.com
[ Upstream commit 395f2e8fd340c5bfad026f5968b56ec34cf20dd1 ]
If the hns ROCEE reports a general error CQE (types not specified by the IB General Specifications), it's no need to change the QP state to error, and the driver should just skip it.
Fixes: 7c044adca272 ("RDMA/hns: Simplify the cqe code of poll cq") Link: https://lore.kernel.org/r/1595932941-40613-8-git-send-email-liweihang@huawei... Signed-off-by: Xi Wang wangxi11@huawei.com Signed-off-by: Weihang Li liweihang@huawei.com Signed-off-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 9 +++++++++ drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 1 + 2 files changed, 10 insertions(+)
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 9833ce3e21f9e..eb71b941d21b7 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -3053,6 +3053,7 @@ static void get_cqe_status(struct hns_roce_dev *hr_dev, struct hns_roce_qp *qp, IB_WC_RETRY_EXC_ERR }, { HNS_ROCE_CQE_V2_RNR_RETRY_EXC_ERR, IB_WC_RNR_RETRY_EXC_ERR }, { HNS_ROCE_CQE_V2_REMOTE_ABORT_ERR, IB_WC_REM_ABORT_ERR }, + { HNS_ROCE_CQE_V2_GENERAL_ERR, IB_WC_GENERAL_ERR} };
u32 cqe_status = roce_get_field(cqe->byte_4, V2_CQE_BYTE_4_STATUS_M, @@ -3074,6 +3075,14 @@ static void get_cqe_status(struct hns_roce_dev *hr_dev, struct hns_roce_qp *qp, print_hex_dump(KERN_ERR, "", DUMP_PREFIX_NONE, 16, 4, cqe, sizeof(*cqe), false);
+ /* + * For hns ROCEE, GENERAL_ERR is an error type that is not defined in + * the standard protocol, the driver must ignore it and needn't to set + * the QP to an error state. + */ + if (cqe_status == HNS_ROCE_CQE_V2_GENERAL_ERR) + return; + /* * Hip08 hardware cannot flush the WQEs in SQ/RQ if the QP state gets * into errored mode. Hence, as a workaround to this hardware diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index e176b0aaa4ac2..e6c385ced1872 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -230,6 +230,7 @@ enum { HNS_ROCE_CQE_V2_TRANSPORT_RETRY_EXC_ERR = 0x15, HNS_ROCE_CQE_V2_RNR_RETRY_EXC_ERR = 0x16, HNS_ROCE_CQE_V2_REMOTE_ABORT_ERR = 0x22, + HNS_ROCE_CQE_V2_GENERAL_ERR = 0x23,
HNS_ROCE_V2_CQE_STATUS_MASK = 0xff, };