IB/mlx4: Add strong ordering to local inval and fast reg work requests
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 <http://lists.openfabrics.org/pipermail/general/2009-April/059253.html> Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il> Cc: <stable@kernel.org> Signed-off-by: Roland Dreier <rolandd@cisco.com>
This commit is contained in:
parent
ab6bf42e23
commit
2ac6bf4ddc
|
@ -1585,12 +1585,16 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
|
|||
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;
|
||||
|
|
|
@ -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 {
|
||||
|
|
Loading…
Reference in New Issue