void __mlx4_ib_cq_clean(struct mlx4_ib_cq *cq, u32 qpn, struct mlx4_ib_srq *srq)
{
u32 prod_index;
int nfreed = 0;
struct mlx4_cqe *cqe, *dest;
u8 owner_bit;
/*
* First we need to find the current producer index, so we
* know where to start cleaning from. It doesn't matter if HW
* adds new entries after this loop -- the QP we're worried
* about is already in RESET, so the new entries won't come
* from our QP and therefore don't need to be checked.
*/
for (prod_index = cq->mcq.cons_index; get_sw_cqe(cq, prod_index); ++prod_index)
if (prod_index == cq->mcq.cons_index + cq->ibcq.cqe)
break;
/*
* Now sweep backwards through the CQ, removing CQ entries
* that match our QP by copying older entries on top of them.
*/
while ((int) --prod_index - (int) cq->mcq.cons_index >= 0) {
cqe = get_cqe(cq, prod_index & cq->ibcq.cqe);
if ((be32_to_cpu(cqe->vlan_my_qpn) & MLX4_CQE_QPN_MASK) == qpn) {
if (srq && !(cqe->owner_sr_opcode & MLX4_CQE_IS_SEND_MASK))
mlx4_ib_free_srq_wqe(srq, be16_to_cpu(cqe->wqe_index));
++nfreed;
} else if (nfreed) {
dest = get_cqe(cq, (prod_index + nfreed) & cq->ibcq.cqe);
owner_bit = dest->owner_sr_opcode & MLX4_CQE_OWNER_MASK;
memcpy(dest, cqe, sizeof *cqe);
dest->owner_sr_opcode = owner_bit |
(dest->owner_sr_opcode & ~MLX4_CQE_OWNER_MASK);
}
}
if (nfreed) {
cq->mcq.cons_index += nfreed;
/*
* Make sure update of buffer contents is done before
* updating consumer index.
*/
wmb();
mlx4_cq_set_ci(&cq->mcq);
}
}
static int mlx4_ib_poll_one(struct mlx4_ib_cq *cq,
struct mlx4_ib_qp **cur_qp,
struct ib_wc *wc)
{
struct mlx4_cqe *cqe;
struct mlx4_qp *mqp;
struct mlx4_ib_wq *wq;
struct mlx4_ib_srq *srq;
int is_send;
int is_error;
u32 g_mlpath_rqpn;
u16 wqe_ctr;
repoll:
cqe = next_cqe_sw(cq);
if (!cqe)
return -EAGAIN;
++cq->mcq.cons_index;
/*
* Make sure we read CQ entry contents after we've checked the
* ownership bit.
*/
rmb();
is_send = cqe->owner_sr_opcode & MLX4_CQE_IS_SEND_MASK;
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;
}
/* Resize CQ in progress */
if (unlikely((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) == MLX4_CQE_OPCODE_RESIZE)) {
if (cq->resize_buf) {
struct mlx4_ib_dev *dev = to_mdev(cq->ibcq.device);
mlx4_ib_free_cq_buf(dev, &cq->buf, cq->ibcq.cqe);
cq->buf = cq->resize_buf->buf;
cq->ibcq.cqe = cq->resize_buf->cqe;
kfree(cq->resize_buf);
cq->resize_buf = NULL;
}
goto repoll;
}
if (!*cur_qp ||
(be32_to_cpu(cqe->vlan_my_qpn) & MLX4_CQE_QPN_MASK) != (*cur_qp)->mqp.qpn) {
/*
* We do not have to take the QP table lock here,
* because CQs will be locked while QPs are removed
* from the table.
*/
mqp = __mlx4_qp_lookup(to_mdev(cq->ibcq.device)->dev,
be32_to_cpu(cqe->vlan_my_qpn));
if (unlikely(!mqp)) {
printk(KERN_WARNING "CQ %06x with entry for unknown QPN %06x\n",
cq->mcq.cqn, be32_to_cpu(cqe->vlan_my_qpn) & MLX4_CQE_QPN_MASK);
return -EINVAL;
}
*cur_qp = to_mibqp(mqp);
}
wc->qp = &(*cur_qp)->ibqp;
if (is_send) {
wq = &(*cur_qp)->sq;
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) {
srq = to_msrq((*cur_qp)->ibqp.srq);
wqe_ctr = be16_to_cpu(cqe->wqe_index);
wc->wr_id = srq->wrid[wqe_ctr];
mlx4_ib_free_srq_wqe(srq, wqe_ctr);
} else {
wq = &(*cur_qp)->rq;
wc->wr_id = wq->wrid[wq->tail & (wq->wqe_cnt - 1)];
++wq->tail;
}
if (unlikely(is_error)) {
mlx4_ib_handle_error_cqe((struct mlx4_err_cqe *) cqe, wc);
return 0;
}
wc->status = IB_WC_SUCCESS;
if (is_send) {
wc->wc_flags = 0;
switch (cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) {
case MLX4_OPCODE_RDMA_WRITE_IMM:
wc->wc_flags |= IB_WC_WITH_IMM;
case MLX4_OPCODE_RDMA_WRITE:
wc->opcode = IB_WC_RDMA_WRITE;
break;
case MLX4_OPCODE_SEND_IMM:
wc->wc_flags |= IB_WC_WITH_IMM;
case MLX4_OPCODE_SEND:
case MLX4_OPCODE_SEND_INVAL:
wc->opcode = IB_WC_SEND;
break;
case MLX4_OPCODE_RDMA_READ:
wc->opcode = IB_WC_RDMA_READ;
wc->byte_len = be32_to_cpu(cqe->byte_cnt);
break;
case MLX4_OPCODE_ATOMIC_CS:
wc->opcode = IB_WC_COMP_SWAP;
wc->byte_len = 8;
break;
case MLX4_OPCODE_ATOMIC_FA:
wc->opcode = IB_WC_FETCH_ADD;
wc->byte_len = 8;
break;
case MLX4_OPCODE_MASKED_ATOMIC_CS:
wc->opcode = IB_WC_MASKED_COMP_SWAP;
wc->byte_len = 8;
break;
case MLX4_OPCODE_MASKED_ATOMIC_FA:
wc->opcode = IB_WC_MASKED_FETCH_ADD;
wc->byte_len = 8;
break;
case MLX4_OPCODE_BIND_MW:
wc->opcode = IB_WC_BIND_MW;
break;
case MLX4_OPCODE_LSO:
wc->opcode = IB_WC_LSO;
break;
case MLX4_OPCODE_FMR:
wc->opcode = IB_WC_FAST_REG_MR;
break;
case MLX4_OPCODE_LOCAL_INVAL:
wc->opcode = IB_WC_LOCAL_INV;
break;
}
} else {
wc->byte_len = be32_to_cpu(cqe->byte_cnt);
switch (cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) {
case MLX4_RECV_OPCODE_RDMA_WRITE_IMM:
wc->opcode = IB_WC_RECV_RDMA_WITH_IMM;
wc->wc_flags = IB_WC_WITH_IMM;
wc->ex.imm_data = cqe->immed_rss_invalid;
break;
case MLX4_RECV_OPCODE_SEND_INVAL:
wc->opcode = IB_WC_RECV;
wc->wc_flags = IB_WC_WITH_INVALIDATE;
wc->ex.invalidate_rkey = be32_to_cpu(cqe->immed_rss_invalid);
break;
case MLX4_RECV_OPCODE_SEND:
wc->opcode = IB_WC_RECV;
wc->wc_flags = 0;
break;
case MLX4_RECV_OPCODE_SEND_IMM:
wc->opcode = IB_WC_RECV;
wc->wc_flags = IB_WC_WITH_IMM;
wc->ex.imm_data = cqe->immed_rss_invalid;
break;
}
wc->slid = be16_to_cpu(cqe->rlid);
g_mlpath_rqpn = be32_to_cpu(cqe->g_mlpath_rqpn);
wc->src_qp = g_mlpath_rqpn & 0xffffff;
wc->dlid_path_bits = (g_mlpath_rqpn >> 24) & 0x7f;
wc->wc_flags |= g_mlpath_rqpn & 0x80000000 ? IB_WC_GRH : 0;
wc->pkey_index = be32_to_cpu(cqe->immed_rss_invalid) & 0x7f;
wc->csum_ok = mlx4_ib_ipoib_csum_ok(cqe->status, cqe->checksum);
if (rdma_port_get_link_layer(wc->qp->device,
(*cur_qp)->port) == IB_LINK_LAYER_ETHERNET)
wc->sl = be16_to_cpu(cqe->sl_vid) >> 13;
else
wc->sl = be16_to_cpu(cqe->sl_vid) >> 12;
}