From ea54b10c7773007e173da31fe7adcc049da33331 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Mon, 28 Jan 2008 10:40:59 +0200 Subject: IB/mlx4: Use multiple WQ blocks to post smaller send WQEs ConnectX HCA supports shrinking WQEs, so that a single work request can be made of multiple units of wqe_shift. This way, WRs can differ in size, and do not have to be a power of 2 in size, saving memory and speeding up send WR posting. Unfortunately, if we do this then the wqe_index field in CQEs can't be used to look up the WR ID anymore, so our implementation does this only if selective signaling is off. Further, on 32-bit platforms, we can't use vmap() to make the QP buffer virtually contigious. Thus we have to use constant-sized WRs to make sure a WR is always fully within a single page-sized chunk. Finally, we use WRs with the NOP opcode to avoid wrapping around the queue buffer in the middle of posting a WR, and we set the NoErrorCompletion bit to avoid getting completions with error for NOP WRs. However, NEC is only supported starting with firmware 2.2.232, so we use constant-sized WRs for older firmware. And, since MLX QPs only support SEND, we use constant-sized WRs in this case. When stamping during NOP posting, do stamping following setting of the NOP WQE valid bit. Signed-off-by: Michael S. Tsirkin Signed-off-by: Jack Morgenstein Signed-off-by: Roland Dreier --- drivers/infiniband/hw/mlx4/cq.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'drivers/infiniband/hw/mlx4/cq.c') diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c index 8ac7b973f87..7360bbafbe8 100644 --- a/drivers/infiniband/hw/mlx4/cq.c +++ b/drivers/infiniband/hw/mlx4/cq.c @@ -326,6 +326,12 @@ static int mlx4_ib_poll_one(struct mlx4_ib_cq *cq, is_error = (cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) == MLX4_CQE_OPCODE_ERROR; + if (unlikely((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) == MLX4_OPCODE_NOP && + is_send)) { + printk(KERN_WARNING "Completion for NOP opcode detected!\n"); + return -EINVAL; + } + if (!*cur_qp || (be32_to_cpu(cqe->my_qpn) & 0xffffff) != (*cur_qp)->mqp.qpn) { /* @@ -348,8 +354,10 @@ static int mlx4_ib_poll_one(struct mlx4_ib_cq *cq, if (is_send) { wq = &(*cur_qp)->sq; - wqe_ctr = be16_to_cpu(cqe->wqe_index); - wq->tail += (u16) (wqe_ctr - (u16) wq->tail); + if (!(*cur_qp)->sq_signal_bits) { + wqe_ctr = be16_to_cpu(cqe->wqe_index); + wq->tail += (u16) (wqe_ctr - (u16) wq->tail); + } wc->wr_id = wq->wrid[wq->tail & (wq->wqe_cnt - 1)]; ++wq->tail; } else if ((*cur_qp)->ibqp.srq) { -- cgit v1.2.3