case IB_QPT_GSI:
return sizeof (struct mlx4_wqe_ctrl_seg) +
ALIGN(MLX4_IB_UD_HEADER_SIZE +
+ DIV_ROUND_UP(MLX4_IB_UD_HEADER_SIZE,
+ MLX4_INLINE_ALIGN) *
sizeof (struct mlx4_wqe_inline_seg),
sizeof (struct mlx4_wqe_data_seg)) +
ALIGN(4 +
return 0;
}
-static void init_port(struct mlx4_ib_dev *dev, int port)
-{
- struct mlx4_init_port_param param;
- int err;
-
- memset(¶m, 0, sizeof param);
-
- param.port_width_cap = dev->dev->caps.port_width_cap;
- param.vl_cap = dev->dev->caps.vl_cap;
- param.mtu = ib_mtu_enum_to_int(dev->dev->caps.mtu_cap);
- param.max_gid = dev->dev->caps.gid_table_len;
- param.max_pkey = dev->dev->caps.pkey_table_len;
-
- err = mlx4_INIT_PORT(dev->dev, ¶m, port);
- if (err)
- printk(KERN_WARNING "INIT_PORT failed, return code %d.\n", err);
-}
-
static int to_mlx4_st(enum ib_qp_type type)
{
switch (type) {
path->counter_index = 0xff;
if (ah->ah_flags & IB_AH_GRH) {
- if (ah->grh.sgid_index >= dev->dev->caps.gid_table_len) {
+ if (ah->grh.sgid_index >= dev->dev->caps.gid_table_len[port]) {
printk(KERN_ERR "sgid_index (%u) too large. max is %d\n",
- ah->grh.sgid_index, dev->dev->caps.gid_table_len - 1);
+ ah->grh.sgid_index, dev->dev->caps.gid_table_len[port] - 1);
return -1;
}
}
if (attr_mask & IB_QP_ALT_PATH) {
- if (attr->alt_pkey_index >= dev->dev->caps.pkey_table_len)
- return -EINVAL;
-
if (attr->alt_port_num == 0 ||
attr->alt_port_num > dev->dev->caps.num_ports)
return -EINVAL;
+ if (attr->alt_pkey_index >=
+ dev->dev->caps.pkey_table_len[attr->alt_port_num])
+ return -EINVAL;
+
if (mlx4_set_path(dev, &attr->alt_ah_attr, &context->alt_path,
attr->alt_port_num))
return -EINVAL;
*/
if (is_qp0(dev, qp)) {
if (cur_state != IB_QPS_RTR && new_state == IB_QPS_RTR)
- init_port(dev, qp->port);
+ if (mlx4_INIT_PORT(dev->dev, qp->port))
+ printk(KERN_WARNING "INIT_PORT failed for port %d\n",
+ qp->port);
if (cur_state != IB_QPS_RESET && cur_state != IB_QPS_ERR &&
(new_state == IB_QPS_RESET || new_state == IB_QPS_ERR))
if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type, attr_mask))
goto out;
- if ((attr_mask & IB_QP_PKEY_INDEX) &&
- attr->pkey_index >= dev->dev->caps.pkey_table_len) {
- goto out;
- }
-
if ((attr_mask & IB_QP_PORT) &&
(attr->port_num == 0 || attr->port_num > dev->dev->caps.num_ports)) {
goto out;
}
+ if (attr_mask & IB_QP_PKEY_INDEX) {
+ int p = attr_mask & IB_QP_PORT ? attr->port_num : qp->port;
+ if (attr->pkey_index >= dev->dev->caps.pkey_table_len[p])
+ goto out;
+ }
+
if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC &&
attr->max_rd_atomic > dev->dev->caps.max_qp_init_rdma) {
goto out;
u16 pkey;
int send_size;
int header_size;
+ int spc;
int i;
send_size = 0;
printk("\n");
}
- inl->byte_count = cpu_to_be32(1 << 31 | header_size);
- memcpy(inl + 1, sqp->header_buf, header_size);
+ /*
+ * Inline data segments may not cross a 64 byte boundary. If
+ * our UD header is bigger than the space available up to the
+ * next 64 byte boundary in the WQE, use two inline data
+ * segments to hold the UD header.
+ */
+ spc = MLX4_INLINE_ALIGN -
+ ((unsigned long) (inl + 1) & (MLX4_INLINE_ALIGN - 1));
+ if (header_size <= spc) {
+ inl->byte_count = cpu_to_be32(1 << 31 | header_size);
+ memcpy(inl + 1, sqp->header_buf, header_size);
+ i = 1;
+ } else {
+ inl->byte_count = cpu_to_be32(1 << 31 | spc);
+ memcpy(inl + 1, sqp->header_buf, spc);
- return ALIGN(sizeof (struct mlx4_wqe_inline_seg) + header_size, 16);
+ inl = (void *) (inl + 1) + spc;
+ memcpy(inl + 1, sqp->header_buf + spc, header_size - spc);
+ /*
+ * Need a barrier here to make sure all the data is
+ * visible before the byte_count field is set.
+ * Otherwise the HCA prefetcher could grab the 64-byte
+ * chunk with this inline segment and get a valid (!=
+ * 0xffffffff) byte count but stale data, and end up
+ * generating a packet with bad headers.
+ *
+ * The first inline segment's byte_count field doesn't
+ * need a barrier, because it comes after a
+ * control/MLX segment and therefore is at an offset
+ * of 16 mod 64.
+ */
+ wmb();
+ inl->byte_count = cpu_to_be32(1 << 31 | (header_size - spc));
+ i = 2;
+ }
+
+ return ALIGN(i * sizeof (struct mlx4_wqe_inline_seg) + header_size, 16);
}
static int mlx4_wq_overflow(struct mlx4_ib_wq *wq, int nreq, struct ib_cq *ib_cq)
return err;
}
+
+static inline enum ib_qp_state to_ib_qp_state(enum mlx4_qp_state mlx4_state)
+{
+ switch (mlx4_state) {
+ case MLX4_QP_STATE_RST: return IB_QPS_RESET;
+ case MLX4_QP_STATE_INIT: return IB_QPS_INIT;
+ case MLX4_QP_STATE_RTR: return IB_QPS_RTR;
+ case MLX4_QP_STATE_RTS: return IB_QPS_RTS;
+ case MLX4_QP_STATE_SQ_DRAINING:
+ case MLX4_QP_STATE_SQD: return IB_QPS_SQD;
+ case MLX4_QP_STATE_SQER: return IB_QPS_SQE;
+ case MLX4_QP_STATE_ERR: return IB_QPS_ERR;
+ default: return -1;
+ }
+}
+
+static inline enum ib_mig_state to_ib_mig_state(int mlx4_mig_state)
+{
+ switch (mlx4_mig_state) {
+ case MLX4_QP_PM_ARMED: return IB_MIG_ARMED;
+ case MLX4_QP_PM_REARM: return IB_MIG_REARM;
+ case MLX4_QP_PM_MIGRATED: return IB_MIG_MIGRATED;
+ default: return -1;
+ }
+}
+
+static int to_ib_qp_access_flags(int mlx4_flags)
+{
+ int ib_flags = 0;
+
+ if (mlx4_flags & MLX4_QP_BIT_RRE)
+ ib_flags |= IB_ACCESS_REMOTE_READ;
+ if (mlx4_flags & MLX4_QP_BIT_RWE)
+ ib_flags |= IB_ACCESS_REMOTE_WRITE;
+ if (mlx4_flags & MLX4_QP_BIT_RAE)
+ ib_flags |= IB_ACCESS_REMOTE_ATOMIC;
+
+ return ib_flags;
+}
+
+static void to_ib_ah_attr(struct mlx4_dev *dev, struct ib_ah_attr *ib_ah_attr,
+ struct mlx4_qp_path *path)
+{
+ memset(ib_ah_attr, 0, sizeof *path);
+ ib_ah_attr->port_num = path->sched_queue & 0x40 ? 2 : 1;
+
+ if (ib_ah_attr->port_num == 0 || ib_ah_attr->port_num > dev->caps.num_ports)
+ return;
+
+ ib_ah_attr->dlid = be16_to_cpu(path->rlid);
+ ib_ah_attr->sl = (path->sched_queue >> 2) & 0xf;
+ ib_ah_attr->src_path_bits = path->grh_mylmc & 0x7f;
+ ib_ah_attr->static_rate = path->static_rate ? path->static_rate - 5 : 0;
+ ib_ah_attr->ah_flags = (path->grh_mylmc & (1 << 7)) ? IB_AH_GRH : 0;
+ if (ib_ah_attr->ah_flags) {
+ ib_ah_attr->grh.sgid_index = path->mgid_index;
+ ib_ah_attr->grh.hop_limit = path->hop_limit;
+ ib_ah_attr->grh.traffic_class =
+ (be32_to_cpu(path->tclass_flowlabel) >> 20) & 0xff;
+ ib_ah_attr->grh.flow_label =
+ be32_to_cpu(path->tclass_flowlabel) & 0xffffff;
+ memcpy(ib_ah_attr->grh.dgid.raw,
+ path->rgid, sizeof ib_ah_attr->grh.dgid.raw);
+ }
+}
+
+int mlx4_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr_mask,
+ struct ib_qp_init_attr *qp_init_attr)
+{
+ struct mlx4_ib_dev *dev = to_mdev(ibqp->device);
+ struct mlx4_ib_qp *qp = to_mqp(ibqp);
+ struct mlx4_qp_context context;
+ int mlx4_state;
+ int err;
+
+ if (qp->state == IB_QPS_RESET) {
+ qp_attr->qp_state = IB_QPS_RESET;
+ goto done;
+ }
+
+ err = mlx4_qp_query(dev->dev, &qp->mqp, &context);
+ if (err)
+ return -EINVAL;
+
+ mlx4_state = be32_to_cpu(context.flags) >> 28;
+
+ qp_attr->qp_state = to_ib_qp_state(mlx4_state);
+ qp_attr->path_mtu = context.mtu_msgmax >> 5;
+ qp_attr->path_mig_state =
+ to_ib_mig_state((be32_to_cpu(context.flags) >> 11) & 0x3);
+ qp_attr->qkey = be32_to_cpu(context.qkey);
+ qp_attr->rq_psn = be32_to_cpu(context.rnr_nextrecvpsn) & 0xffffff;
+ qp_attr->sq_psn = be32_to_cpu(context.next_send_psn) & 0xffffff;
+ qp_attr->dest_qp_num = be32_to_cpu(context.remote_qpn) & 0xffffff;
+ qp_attr->qp_access_flags =
+ to_ib_qp_access_flags(be32_to_cpu(context.params2));
+
+ if (qp->ibqp.qp_type == IB_QPT_RC || qp->ibqp.qp_type == IB_QPT_UC) {
+ to_ib_ah_attr(dev->dev, &qp_attr->ah_attr, &context.pri_path);
+ to_ib_ah_attr(dev->dev, &qp_attr->alt_ah_attr, &context.alt_path);
+ qp_attr->alt_pkey_index = context.alt_path.pkey_index & 0x7f;
+ qp_attr->alt_port_num = qp_attr->alt_ah_attr.port_num;
+ }
+
+ qp_attr->pkey_index = context.pri_path.pkey_index & 0x7f;
+ qp_attr->port_num = context.pri_path.sched_queue & 0x40 ? 2 : 1;
+
+ /* qp_attr->en_sqd_async_notify is only applicable in modify qp */
+ qp_attr->sq_draining = mlx4_state == MLX4_QP_STATE_SQ_DRAINING;
+
+ qp_attr->max_rd_atomic = 1 << ((be32_to_cpu(context.params1) >> 21) & 0x7);
+
+ qp_attr->max_dest_rd_atomic =
+ 1 << ((be32_to_cpu(context.params2) >> 21) & 0x7);
+ qp_attr->min_rnr_timer =
+ (be32_to_cpu(context.rnr_nextrecvpsn) >> 24) & 0x1f;
+ qp_attr->timeout = context.pri_path.ackto >> 3;
+ qp_attr->retry_cnt = (be32_to_cpu(context.params1) >> 16) & 0x7;
+ qp_attr->rnr_retry = (be32_to_cpu(context.params1) >> 13) & 0x7;
+ qp_attr->alt_timeout = context.alt_path.ackto >> 3;
+
+done:
+ qp_attr->cur_qp_state = qp_attr->qp_state;
+ if (!ibqp->uobject) {
+ qp_attr->cap.max_send_wr = qp->sq.wqe_cnt;
+ qp_attr->cap.max_recv_wr = qp->rq.wqe_cnt;
+ qp_attr->cap.max_send_sge = qp->sq.max_gs;
+ qp_attr->cap.max_recv_sge = qp->rq.max_gs;
+ qp_attr->cap.max_inline_data = (1 << qp->sq.wqe_shift) -
+ send_wqe_overhead(qp->ibqp.qp_type) -
+ sizeof (struct mlx4_wqe_inline_seg);
+ qp_init_attr->cap = qp_attr->cap;
+ }
+
+ return 0;
+}
+