2.6.29-stable review patch. If anyone has any objections, please let us know. ------------------ From: Jack Morgenstein commit 2ac6bf4ddc87c3b6b609f8fa82f6ebbffeac12f4 upstream. The ConnectX Programmer's Reference Manual states that the "SO" bit must be set when posting Fast Register and Local Invalidate send work requests. When this bit is set, the work request will be executed only after all previous work requests on the send queue have been executed. (If the bit is not set, Fast Register and Local Invalidate WQEs may begin execution too early, which violates the defined semantics for these operations) This fixes the issue with NFS/RDMA reported in Signed-off-by: Jack Morgenstein Signed-off-by: Roland Dreier Signed-off-by: Greg Kroah-Hartman --- drivers/infiniband/hw/mlx4/qp.c | 4 ++++ include/linux/mlx4/qp.h | 1 + 2 files changed, 5 insertions(+) --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -1585,12 +1585,16 @@ int mlx4_ib_post_send(struct ib_qp *ibqp break; case IB_WR_LOCAL_INV: + ctrl->srcrb_flags |= + cpu_to_be32(MLX4_WQE_CTRL_STRONG_ORDER); set_local_inv_seg(wqe, wr->ex.invalidate_rkey); wqe += sizeof (struct mlx4_wqe_local_inval_seg); size += sizeof (struct mlx4_wqe_local_inval_seg) / 16; break; case IB_WR_FAST_REG_MR: + ctrl->srcrb_flags |= + cpu_to_be32(MLX4_WQE_CTRL_STRONG_ORDER); set_fmr_seg(wqe, wr); wqe += sizeof (struct mlx4_wqe_fmr_seg); size += sizeof (struct mlx4_wqe_fmr_seg) / 16; --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -165,6 +165,7 @@ enum { MLX4_WQE_CTRL_IP_CSUM = 1 << 4, MLX4_WQE_CTRL_TCP_UDP_CSUM = 1 << 5, MLX4_WQE_CTRL_INS_VLAN = 1 << 6, + MLX4_WQE_CTRL_STRONG_ORDER = 1 << 7, }; struct mlx4_wqe_ctrl_seg { -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/