[PATCH mlx5-next v1 1/3] net/mlx5: Add DCS caps & fields support

[PATCH mlx5-next v1 1/3] net/mlx5: Add DCS caps & fields support

[Leon Romanovsky]

From: Lior Nahmanson <liorna@nvidia.com>

This fields will be needed when adding a support for DCS offload

max_dci_stream_channels - maximum DCI stream channels supported per DCI.
max_dci_errored_streams - maximum DCI error stream channels
supported per DCI before a DCI move to error state.

Signed-off-by: Lior Nahmanson <liorna@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 include/linux/mlx5/mlx5_ifc.h | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 6d16eed6850e..48b2529451eb 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1655,7 +1655,13 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         max_geneve_tlv_option_data_len[0x5];
 	u8         reserved_at_570[0x10];
 
-	u8         reserved_at_580[0x33];
+	u8	   reserved_at_580[0xb];
+	u8	   log_max_dci_stream_channels[0x5];
+	u8	   reserved_at_590[0x3];
+	u8	   log_max_dci_errored_streams[0x5];
+	u8	   reserved_at_598[0x8];
+
+	u8         reserved_at_5a0[0x13];
 	u8         log_max_dek[0x5];
 	u8         reserved_at_5b8[0x4];
 	u8         mini_cqe_resp_stride_index[0x1];
@@ -3013,10 +3019,12 @@ struct mlx5_ifc_qpc_bits {
 	u8         reserved_at_3c0[0x8];
 	u8         next_send_psn[0x18];
 
-	u8         reserved_at_3e0[0x8];
+	u8         reserved_at_3e0[0x3];
+	u8	   log_num_dci_stream_channels[0x5];
 	u8         cqn_snd[0x18];
 
-	u8         reserved_at_400[0x8];
+	u8         reserved_at_400[0x3];
+	u8	   log_num_dci_errored_streams[0x5];
 	u8         deth_sqpn[0x18];
 
 	u8         reserved_at_420[0x20];
-- 
2.31.1

[PATCH rdma-next v1 2/3] RDMA/mlx5: Separate DCI QP creation logic

[Leon Romanovsky]

From: Lior Nahmanson <liorna@nvidia.com>

This patch isolates DCI QP creation logic to separate function, so this
change will reduce complexity when adding new features to DCI QP without
interfering with other QP types.

The code was copied from create_user_qp() while taking only DCI relevant bits.

Reviewed-by: Meir Lichtinger <meirl@nvidia.com>
Signed-off-by: Lior Nahmanson <liorna@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/mlx5/qp.c | 157 ++++++++++++++++++++++++++++++++
 1 file changed, 157 insertions(+)

diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 7a5f1eba60e3..65a380543f5a 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -1974,6 +1974,160 @@ static int create_xrc_tgt_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	return 0;
 }
 
+static int create_dci(struct mlx5_ib_dev *dev, struct ib_pd *pd,
+		      struct mlx5_ib_qp *qp,
+		      struct mlx5_create_qp_params *params)
+{
+	struct ib_qp_init_attr *init_attr = params->attr;
+	struct mlx5_ib_create_qp *ucmd = params->ucmd;
+	u32 out[MLX5_ST_SZ_DW(create_qp_out)] = {};
+	struct ib_udata *udata = params->udata;
+	u32 uidx = params->uidx;
+	struct mlx5_ib_resources *devr = &dev->devr;
+	int inlen = MLX5_ST_SZ_BYTES(create_qp_in);
+	struct mlx5_core_dev *mdev = dev->mdev;
+	struct mlx5_ib_cq *send_cq;
+	struct mlx5_ib_cq *recv_cq;
+	unsigned long flags;
+	struct mlx5_ib_qp_base *base;
+	int ts_format;
+	int mlx5_st;
+	void *qpc;
+	u32 *in;
+	int err;
+
+	spin_lock_init(&qp->sq.lock);
+	spin_lock_init(&qp->rq.lock);
+
+	mlx5_st = to_mlx5_st(qp->type);
+	if (mlx5_st < 0)
+		return -EINVAL;
+
+	if (init_attr->sq_sig_type == IB_SIGNAL_ALL_WR)
+		qp->sq_signal_bits = MLX5_WQE_CTRL_CQ_UPDATE;
+
+	base = &qp->trans_qp.base;
+
+	qp->has_rq = qp_has_rq(init_attr);
+	err = set_rq_size(dev, &init_attr->cap, qp->has_rq, qp, ucmd);
+	if (err) {
+		mlx5_ib_dbg(dev, "err %d\n", err);
+		return err;
+	}
+
+	if (ucmd->rq_wqe_shift != qp->rq.wqe_shift ||
+	    ucmd->rq_wqe_count != qp->rq.wqe_cnt)
+		return -EINVAL;
+
+	if (ucmd->sq_wqe_count > (1 << MLX5_CAP_GEN(mdev, log_max_qp_sz)))
+		return -EINVAL;
+
+	ts_format = get_qp_ts_format(dev, to_mcq(init_attr->send_cq),
+				     to_mcq(init_attr->recv_cq));
+
+	if (ts_format < 0)
+		return ts_format;
+
+	err = _create_user_qp(dev, pd, qp, udata, init_attr, &in, &params->resp,
+			      &inlen, base, ucmd);
+	if (err)
+		return err;
+
+	if (MLX5_CAP_GEN(mdev, ece_support))
+		MLX5_SET(create_qp_in, in, ece, ucmd->ece_options);
+	qpc = MLX5_ADDR_OF(create_qp_in, in, qpc);
+
+	MLX5_SET(qpc, qpc, st, mlx5_st);
+	MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED);
+	MLX5_SET(qpc, qpc, pd, to_mpd(pd)->pdn);
+
+	if (qp->flags_en & MLX5_QP_FLAG_SIGNATURE)
+		MLX5_SET(qpc, qpc, wq_signature, 1);
+
+	if (qp->flags & IB_QP_CREATE_CROSS_CHANNEL)
+		MLX5_SET(qpc, qpc, cd_master, 1);
+	if (qp->flags & IB_QP_CREATE_MANAGED_SEND)
+		MLX5_SET(qpc, qpc, cd_slave_send, 1);
+	if (qp->flags_en & MLX5_QP_FLAG_SCATTER_CQE)
+		configure_requester_scat_cqe(dev, qp, init_attr, qpc);
+
+	if (qp->rq.wqe_cnt) {
+		MLX5_SET(qpc, qpc, log_rq_stride, qp->rq.wqe_shift - 4);
+		MLX5_SET(qpc, qpc, log_rq_size, ilog2(qp->rq.wqe_cnt));
+	}
+
+	MLX5_SET(qpc, qpc, ts_format, ts_format);
+	MLX5_SET(qpc, qpc, rq_type, get_rx_type(qp, init_attr));
+
+	MLX5_SET(qpc, qpc, log_sq_size, ilog2(qp->sq.wqe_cnt));
+
+	/* Set default resources */
+	if (init_attr->srq) {
+		MLX5_SET(qpc, qpc, xrcd, devr->xrcdn0);
+		MLX5_SET(qpc, qpc, srqn_rmpn_xrqn,
+			 to_msrq(init_attr->srq)->msrq.srqn);
+	} else {
+		MLX5_SET(qpc, qpc, xrcd, devr->xrcdn1);
+		MLX5_SET(qpc, qpc, srqn_rmpn_xrqn,
+			 to_msrq(devr->s1)->msrq.srqn);
+	}
+
+	if (init_attr->send_cq)
+		MLX5_SET(qpc, qpc, cqn_snd,
+			 to_mcq(init_attr->send_cq)->mcq.cqn);
+
+	if (init_attr->recv_cq)
+		MLX5_SET(qpc, qpc, cqn_rcv,
+			 to_mcq(init_attr->recv_cq)->mcq.cqn);
+
+	MLX5_SET64(qpc, qpc, dbr_addr, qp->db.dma);
+
+	/* 0xffffff means we ask to work with cqe version 0 */
+	if (MLX5_CAP_GEN(mdev, cqe_version) == MLX5_CQE_VERSION_V1)
+		MLX5_SET(qpc, qpc, user_index, uidx);
+
+	if (qp->flags & IB_QP_CREATE_PCI_WRITE_END_PADDING) {
+		MLX5_SET(qpc, qpc, end_padding_mode,
+			 MLX5_WQ_END_PAD_MODE_ALIGN);
+		/* Special case to clean flag */
+		qp->flags &= ~IB_QP_CREATE_PCI_WRITE_END_PADDING;
+	}
+
+	err = mlx5_qpc_create_qp(dev, &base->mqp, in, inlen, out);
+
+	kvfree(in);
+	if (err)
+		goto err_create;
+
+	base->container_mibqp = qp;
+	base->mqp.event = mlx5_ib_qp_event;
+	if (MLX5_CAP_GEN(mdev, ece_support))
+		params->resp.ece_options = MLX5_GET(create_qp_out, out, ece);
+
+	get_cqs(qp->type, init_attr->send_cq, init_attr->recv_cq,
+		&send_cq, &recv_cq);
+	spin_lock_irqsave(&dev->reset_flow_resource_lock, flags);
+	mlx5_ib_lock_cqs(send_cq, recv_cq);
+	/* Maintain device to QPs access, needed for further handling via reset
+	 * flow
+	 */
+	list_add_tail(&qp->qps_list, &dev->qp_list);
+	/* Maintain CQ to QPs access, needed for further handling via reset flow
+	 */
+	if (send_cq)
+		list_add_tail(&qp->cq_send_list, &send_cq->list_send_qp);
+	if (recv_cq)
+		list_add_tail(&qp->cq_recv_list, &recv_cq->list_recv_qp);
+	mlx5_ib_unlock_cqs(send_cq, recv_cq);
+	spin_unlock_irqrestore(&dev->reset_flow_resource_lock, flags);
+
+	return 0;
+
+err_create:
+	destroy_qp(dev, qp, base, udata);
+	return err;
+}
+
 static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 			  struct mlx5_ib_qp *qp,
 			  struct mlx5_create_qp_params *params)
@@ -2840,6 +2994,9 @@ static int create_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 	case MLX5_IB_QPT_DCT:
 		err = create_dct(dev, pd, qp, params);
 		break;
+	case MLX5_IB_QPT_DCI:
+		err = create_dci(dev, pd, qp, params);
+		break;
 	case IB_QPT_XRC_TGT:
 		err = create_xrc_tgt_qp(dev, qp, params);
 		break;
-- 
2.31.1

[PATCH rdma-next v1 3/3] RDMA/mlx5: Add DCS offload support

[Leon Romanovsky]

From: Lior Nahmanson <liorna@mellanox.com>

DCS is an offload to SW load balancing of DC initiator work requests.

A single DCI can be connected to only one target at the time and can't
start new connection until the previous work request is completed.
This limitation will cause to delay when the initiator process needs to
transfer data to multiple targets at the same time.
The SW solution is to use a process that handling and spreading the work
request on many DCIs according to destinations.

This feature is an offload to this process and coming to reduce the load
from the CPU and improve the performance.

Reviewed-by: Meir Lichtinger <meirl@nvidia.com>
Signed-off-by: Lior Nahmanson <liorna@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/mlx5/main.c | 10 ++++++++++
 drivers/infiniband/hw/mlx5/qp.c   | 11 +++++++++++
 include/uapi/rdma/mlx5-abi.h      | 17 +++++++++++++++--
 3 files changed, 36 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index b145e477e3ba..c12517b63a8d 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1174,6 +1174,16 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 				MLX5_IB_TUNNELED_OFFLOADS_MPLS_UDP;
 	}
 
+	if (offsetofend(typeof(resp), dci_streams_caps) <= uhw_outlen) {
+		resp.response_length += sizeof(resp.dci_streams_caps);
+
+		resp.dci_streams_caps.max_log_num_concurent =
+			MLX5_CAP_GEN(mdev, log_max_dci_stream_channels);
+
+		resp.dci_streams_caps.max_log_num_errored =
+			MLX5_CAP_GEN(mdev, log_max_dci_errored_streams);
+	}
+
 	if (uhw_outlen) {
 		err = ib_copy_to_udata(uhw, &resp, resp.response_length);
 
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 65a380543f5a..7b545eac37a3 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -2056,6 +2056,13 @@ static int create_dci(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 		MLX5_SET(qpc, qpc, log_rq_size, ilog2(qp->rq.wqe_cnt));
 	}
 
+	if (qp->flags_en & MLX5_QP_FLAG_DCI_STREAM) {
+		MLX5_SET(qpc, qpc, log_num_dci_stream_channels,
+			 ucmd->dci_streams.log_num_concurent);
+		MLX5_SET(qpc, qpc, log_num_dci_errored_streams,
+			 ucmd->dci_streams.log_num_errored);
+	}
+
 	MLX5_SET(qpc, qpc, ts_format, ts_format);
 	MLX5_SET(qpc, qpc, rq_type, get_rx_type(qp, init_attr));
 
@@ -2799,6 +2806,10 @@ static int process_vendor_flags(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 
 	process_vendor_flag(dev, &flags, MLX5_QP_FLAG_TYPE_DCI, true, qp);
 	process_vendor_flag(dev, &flags, MLX5_QP_FLAG_TYPE_DCT, true, qp);
+	process_vendor_flag(dev, &flags, MLX5_QP_FLAG_DCI_STREAM,
+			    MLX5_CAP_GEN(mdev, log_max_dci_stream_channels) &&
+			    MLX5_CAP_GEN(mdev, log_max_dci_errored_streams),
+			    qp);
 
 	process_vendor_flag(dev, &flags, MLX5_QP_FLAG_SIGNATURE, true, qp);
 	process_vendor_flag(dev, &flags, MLX5_QP_FLAG_SCATTER_CQE,
diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h
index 995faf8f44bd..6f54ab3d99e5 100644
--- a/include/uapi/rdma/mlx5-abi.h
+++ b/include/uapi/rdma/mlx5-abi.h
@@ -50,6 +50,7 @@ enum {
 	MLX5_QP_FLAG_ALLOW_SCATTER_CQE	= 1 << 8,
 	MLX5_QP_FLAG_PACKET_BASED_CREDIT_MODE	= 1 << 9,
 	MLX5_QP_FLAG_UAR_PAGE_INDEX = 1 << 10,
+	MLX5_QP_FLAG_DCI_STREAM	= 1 << 11,
 };
 
 enum {
@@ -237,6 +238,11 @@ struct mlx5_ib_striding_rq_caps {
 	__u32 reserved;
 };
 
+struct mlx5_ib_dci_streams_caps {
+	__u8 max_log_num_concurent;
+	__u8 max_log_num_errored;
+};
+
 enum mlx5_ib_query_dev_resp_flags {
 	/* Support 128B CQE compression */
 	MLX5_IB_QUERY_DEV_RESP_FLAGS_CQE_128B_COMP = 1 << 0,
@@ -265,7 +271,8 @@ struct mlx5_ib_query_device_resp {
 	struct mlx5_ib_sw_parsing_caps sw_parsing_caps;
 	struct mlx5_ib_striding_rq_caps striding_rq_caps;
 	__u32	tunnel_offloads_caps; /* enum mlx5_ib_tunnel_offloads */
-	__u32	reserved;
+	struct  mlx5_ib_dci_streams_caps dci_streams_caps;
+	__u16 reserved;
 };
 
 enum mlx5_ib_create_cq_flags {
@@ -311,6 +318,11 @@ struct mlx5_ib_create_srq_resp {
 	__u32	reserved;
 };
 
+struct mlx5_ib_create_qp_dci_streams {
+	__u8 log_num_concurent;
+	__u8 log_num_errored;
+};
+
 struct mlx5_ib_create_qp {
 	__aligned_u64 buf_addr;
 	__aligned_u64 db_addr;
@@ -325,7 +337,8 @@ struct mlx5_ib_create_qp {
 		__aligned_u64 access_key;
 	};
 	__u32  ece_options;
-	__u32  reserved;
+	struct  mlx5_ib_create_qp_dci_streams dci_streams;
+	__u16 reserved;
 };
 
 /* RX Hash function flags */
-- 
2.31.1

Re: [PATCH rdma-next v1 2/3] RDMA/mlx5: Separate DCI QP creation logic

[Jason Gunthorpe]

On Mon, Jun 21, 2021 at 10:06:15AM +0300, Leon Romanovsky wrote:
> From: Lior Nahmanson <liorna@nvidia.com>
> 
> This patch isolates DCI QP creation logic to separate function, so this
> change will reduce complexity when adding new features to DCI QP without
> interfering with other QP types.
> 
> The code was copied from create_user_qp() while taking only DCI relevant bits.
> 
> Reviewed-by: Meir Lichtinger <meirl@nvidia.com>
> Signed-off-by: Lior Nahmanson <liorna@nvidia.com>
> Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
>  drivers/infiniband/hw/mlx5/qp.c | 157 ++++++++++++++++++++++++++++++++
>  1 file changed, 157 insertions(+)
> 
> diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
> index 7a5f1eba60e3..65a380543f5a 100644
> +++ b/drivers/infiniband/hw/mlx5/qp.c
> @@ -1974,6 +1974,160 @@ static int create_xrc_tgt_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
>  	return 0;
>  }
>  
> +static int create_dci(struct mlx5_ib_dev *dev, struct ib_pd *pd,
> +		      struct mlx5_ib_qp *qp,
> +		      struct mlx5_create_qp_params *params)
> +{

This is a huge amount of copying just to add 4 lines, why?

There must be a better way to do this qp stuff.

Why not put more stuff in _create_user_qp()?

Jason

Re: [PATCH rdma-next v1 2/3] RDMA/mlx5: Separate DCI QP creation logic

[Leon Romanovsky]

On Tue, Jun 22, 2021 at 03:45:56PM -0300, Jason Gunthorpe wrote:
> On Mon, Jun 21, 2021 at 10:06:15AM +0300, Leon Romanovsky wrote:
> > From: Lior Nahmanson <liorna@nvidia.com>
> > 
> > This patch isolates DCI QP creation logic to separate function, so this
> > change will reduce complexity when adding new features to DCI QP without
> > interfering with other QP types.
> > 
> > The code was copied from create_user_qp() while taking only DCI relevant bits.
> > 
> > Reviewed-by: Meir Lichtinger <meirl@nvidia.com>
> > Signed-off-by: Lior Nahmanson <liorna@nvidia.com>
> > Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
> >  drivers/infiniband/hw/mlx5/qp.c | 157 ++++++++++++++++++++++++++++++++
> >  1 file changed, 157 insertions(+)
> > 
> > diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
> > index 7a5f1eba60e3..65a380543f5a 100644
> > +++ b/drivers/infiniband/hw/mlx5/qp.c
> > @@ -1974,6 +1974,160 @@ static int create_xrc_tgt_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
> >  	return 0;
> >  }
> >  
> > +static int create_dci(struct mlx5_ib_dev *dev, struct ib_pd *pd,
> > +		      struct mlx5_ib_qp *qp,
> > +		      struct mlx5_create_qp_params *params)
> > +{
> 
> This is a huge amount of copying just to add 4 lines, why?
> 
> There must be a better way to do this qp stuff.
> 
> Why not put more stuff in _create_user_qp()?

Lior proposed it in original patch, but I didn't like it. It caused to
mix of various QP types and maze of "if () else ()" that are not applicable
one to another.

The huge _create_user_qp() is the reason why create_dci() is not small,
we simply had hard time to understand if specific HW bit is needed or
not in DCI flow.

My goal is to have small per-QP type specific functions that calls
to simple functions for very narrow scope.

Something like that:
static int create_dci(...)
{
  ...
  configure_send_cq(..)
  configure_recv_sq(..)
  configure_srq(...)
  ...
}

static int create_user_qp(...)
{
  ...
  configure_send_cq(..)
  configure_recv_sq(..)
  configure_srq(...)
  ...
}


Thanks

> 
> Jason