Here are some bugfixes for hns driver. v1 -> v2: * Drop patch #2 in v1 because Leon pointed out a problem about mailbox mode, and we plan to handle it in another patchset. * Patch #1: put the atomic length check in set_rc_wqe(), stop processing WQEs and return immediately if there is an error. * Patch #2: use BH workqueue instead of tasklet. Chengchang Tang (5): RDMA/hns: Fix missing pagesize and alignment check in FRMR RDMA/hns: Fix shift-out-bounds when max_inline_data is 0 RDMA/hns: Fix undifined behavior caused by invalid max_sge RDMA/hns: Fix insufficient extend DB for VFs. RDMA/hns: Fix mbx timing out before CMD execution is completed Junxian Huang (3): RDMA/hns: Check atomic wr length RDMA/hns: Fix soft lockup under heavy CEQE load RDMA/hns: Fix unmatch exception handling when init eq table fails drivers/infiniband/hw/hns/hns_roce_device.h | 7 + drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 164 +++++++++++++------- drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 6 + drivers/infiniband/hw/hns/hns_roce_mr.c | 5 + drivers/infiniband/hw/hns/hns_roce_qp.c | 4 +- drivers/infiniband/hw/hns/hns_roce_srq.c | 2 +- 6 files changed, 127 insertions(+), 61 deletions(-) -- 2.33.0