RDMA/hns: Add support for XRC on HIP09

The HIP09 supports XRC transport service, it greatly saves the number of
QPs required to connect all processes in a large cluster.

Link: https://lore.kernel.org/r/1614826558-35423-1-git-send-email-liweihang@huawei.comSigned-off-by: Wenpeng Liang <liangwenpeng@huawei.com>
Signed-off-by: Weihang Li <liweihang@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

drivers/infiniband/hw/hns/hns_roce_alloc.c

@@ -304,6 +304,9 @@ int hns_roce_get_umem_bufs(struct hns_roce_dev *hr_dev, dma_addr_t *bufs,
 
 void hns_roce_cleanup_bitmap(struct hns_roce_dev *hr_dev)
 {
+	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_XRC)
+		hns_roce_cleanup_xrcd_table(hr_dev);
+
 	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_SRQ)
 		hns_roce_cleanup_srq_table(hr_dev);
 	hns_roce_cleanup_qp_table(hr_dev);

drivers/infiniband/hw/hns/hns_roce_device.h

@@ -137,6 +137,7 @@ enum {
 	SERV_TYPE_UC,
 	SERV_TYPE_RD,
 	SERV_TYPE_UD,
+	SERV_TYPE_XRC = 5,
 };
 
 enum hns_roce_qp_state {
@@ -168,6 +169,8 @@ enum hns_roce_event {
 	HNS_ROCE_EVENT_TYPE_DB_OVERFLOW               = 0x12,
 	HNS_ROCE_EVENT_TYPE_MB                        = 0x13,
 	HNS_ROCE_EVENT_TYPE_FLR			      = 0x15,
+	HNS_ROCE_EVENT_TYPE_XRCD_VIOLATION	      = 0x16,
+	HNS_ROCE_EVENT_TYPE_INVALID_XRCETH	      = 0x17,
 };
 
 #define HNS_ROCE_CAP_FLAGS_EX_SHIFT 12
@@ -179,6 +182,7 @@ enum {
 	HNS_ROCE_CAP_FLAG_RECORD_DB		= BIT(3),
 	HNS_ROCE_CAP_FLAG_SQ_RECORD_DB		= BIT(4),
 	HNS_ROCE_CAP_FLAG_SRQ			= BIT(5),
+	HNS_ROCE_CAP_FLAG_XRC			= BIT(6),
 	HNS_ROCE_CAP_FLAG_MW			= BIT(7),
 	HNS_ROCE_CAP_FLAG_FRMR                  = BIT(8),
 	HNS_ROCE_CAP_FLAG_QP_FLOW_CTRL		= BIT(9),
@@ -244,6 +248,11 @@ struct hns_roce_pd {
 	unsigned long		pdn;
 };
 
+struct hns_roce_xrcd {
+	struct ib_xrcd ibxrcd;
+	u32 xrcdn;
+};
+
 struct hns_roce_bitmap {
 	/* Bitmap Traversal last a bit which is 1 */
 	unsigned long		last;
@@ -467,6 +476,7 @@ struct hns_roce_srq {
 	u32			rsv_sge;
 	int			wqe_shift;
 	u32			cqn;
+	u32			xrcdn;
 	void __iomem		*db_reg_l;
 
 	atomic_t		refcount;
@@ -640,6 +650,8 @@ struct hns_roce_qp {
 					 enum hns_roce_event event_type);
 	unsigned long		qpn;
 
+	u32			xrcdn;
+
 	atomic_t		refcount;
 	struct completion	free;
 
@@ -766,6 +778,8 @@ struct hns_roce_caps {
 	int		reserved_uars;
 	int		num_pds;
 	int		reserved_pds;
+	u32		num_xrcds;
+	u32		reserved_xrcds;
 	u32		mtt_entry_sz;
 	u32		cqe_sz;
 	u32		page_size_cap;
@@ -963,6 +977,7 @@ struct hns_roce_dev {
 
 	struct hns_roce_cmdq	cmd;
 	struct hns_roce_bitmap    pd_bitmap;
+	struct hns_roce_bitmap xrcd_bitmap;
 	struct hns_roce_uar_table uar_table;
 	struct hns_roce_mr_table  mr_table;
 	struct hns_roce_cq_table  cq_table;
@@ -1004,6 +1019,11 @@ static inline struct hns_roce_pd *to_hr_pd(struct ib_pd *ibpd)
 	return container_of(ibpd, struct hns_roce_pd, ibpd);
 }
 
+static inline struct hns_roce_xrcd *to_hr_xrcd(struct ib_xrcd *ibxrcd)
+{
+	return container_of(ibxrcd, struct hns_roce_xrcd, ibxrcd);
+}
+
 static inline struct hns_roce_ah *to_hr_ah(struct ib_ah *ibah)
 {
 	return container_of(ibah, struct hns_roce_ah, ibah);
@@ -1136,6 +1156,7 @@ int hns_roce_init_mr_table(struct hns_roce_dev *hr_dev);
 void hns_roce_init_cq_table(struct hns_roce_dev *hr_dev);
 int hns_roce_init_qp_table(struct hns_roce_dev *hr_dev);
 int hns_roce_init_srq_table(struct hns_roce_dev *hr_dev);
+int hns_roce_init_xrcd_table(struct hns_roce_dev *hr_dev);
 
 void hns_roce_cleanup_pd_table(struct hns_roce_dev *hr_dev);
 void hns_roce_cleanup_mr_table(struct hns_roce_dev *hr_dev);
@@ -1143,6 +1164,7 @@ void hns_roce_cleanup_eq_table(struct hns_roce_dev *hr_dev);
 void hns_roce_cleanup_cq_table(struct hns_roce_dev *hr_dev);
 void hns_roce_cleanup_qp_table(struct hns_roce_dev *hr_dev);
 void hns_roce_cleanup_srq_table(struct hns_roce_dev *hr_dev);
+void hns_roce_cleanup_xrcd_table(struct hns_roce_dev *hr_dev);
 
 int hns_roce_bitmap_alloc(struct hns_roce_bitmap *bitmap, unsigned long *obj);
 void hns_roce_bitmap_free(struct hns_roce_bitmap *bitmap, unsigned long obj,
@@ -1207,6 +1229,9 @@ int hns_roce_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *srq_attr,
 			struct ib_udata *udata);
 int hns_roce_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata);
 
+int hns_roce_alloc_xrcd(struct ib_xrcd *ib_xrcd, struct ib_udata *udata);
+int hns_roce_dealloc_xrcd(struct ib_xrcd *ib_xrcd, struct ib_udata *udata);
+
 struct ib_qp *hns_roce_create_qp(struct ib_pd *ib_pd,
 				 struct ib_qp_init_attr *init_attr,
 				 struct ib_udata *udata);

drivers/infiniband/hw/hns/hns_roce_hw_v2.h

@@ -74,6 +74,8 @@
 #define HNS_ROCE_V2_MAX_SRQWQE_SEGS		0x1000000
 #define HNS_ROCE_V2_MAX_IDX_SEGS		0x1000000
 #define HNS_ROCE_V2_MAX_PD_NUM			0x1000000
+#define HNS_ROCE_V2_MAX_XRCD_NUM		0x1000000
+#define HNS_ROCE_V2_RSV_XRCD_NUM		0
 #define HNS_ROCE_V2_MAX_QP_INIT_RDMA		128
 #define HNS_ROCE_V2_MAX_QP_DEST_RDMA		128
 #define HNS_ROCE_V2_MAX_SQ_DESC_SZ		64

drivers/infiniband/hw/hns/hns_roce_main.c

@@ -207,6 +207,9 @@ static int hns_roce_query_device(struct ib_device *ib_dev,
 		props->max_fast_reg_page_list_len = HNS_ROCE_FRMR_MAX_PA;
 	}
 
+	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_XRC)
+		props->device_cap_flags |= IB_DEVICE_XRC;
+
 	return 0;
 }
 
@@ -300,6 +303,7 @@ static int hns_roce_alloc_ucontext(struct ib_ucontext *uctx,
 		return -EAGAIN;
 
 	resp.qp_tab_size = hr_dev->caps.num_qps;
+	resp.srq_tab_size = hr_dev->caps.num_srqs;
 
 	ret = hns_roce_uar_alloc(hr_dev, &context->uar);
 	if (ret)
@@ -461,6 +465,13 @@ static const struct ib_device_ops hns_roce_dev_srq_ops = {
 	INIT_RDMA_OBJ_SIZE(ib_srq, hns_roce_srq, ibsrq),
 };
 
+static const struct ib_device_ops hns_roce_dev_xrcd_ops = {
+	.alloc_xrcd = hns_roce_alloc_xrcd,
+	.dealloc_xrcd = hns_roce_dealloc_xrcd,
+
+	INIT_RDMA_OBJ_SIZE(ib_xrcd, hns_roce_xrcd, ibxrcd),
+};
+
 static int hns_roce_register_device(struct hns_roce_dev *hr_dev)
 {
 	int ret;
@@ -484,20 +495,20 @@ static int hns_roce_register_device(struct hns_roce_dev *hr_dev)
 	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_REREG_MR)
 		ib_set_device_ops(ib_dev, &hns_roce_dev_mr_ops);
 
-	/* MW */
 	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_MW)
 		ib_set_device_ops(ib_dev, &hns_roce_dev_mw_ops);
 
-	/* FRMR */
 	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_FRMR)
 		ib_set_device_ops(ib_dev, &hns_roce_dev_frmr_ops);
 
-	/* SRQ */
 	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_SRQ) {
 		ib_set_device_ops(ib_dev, &hns_roce_dev_srq_ops);
 		ib_set_device_ops(ib_dev, hr_dev->hw->hns_roce_dev_srq_ops);
 	}
 
+	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_XRC)
+		ib_set_device_ops(ib_dev, &hns_roce_dev_xrcd_ops);
+
 	ib_set_device_ops(ib_dev, hr_dev->hw->hns_roce_dev_ops);
 	ib_set_device_ops(ib_dev, &hns_roce_dev_ops);
 	for (i = 0; i < hr_dev->caps.num_ports; i++) {
@@ -727,10 +738,19 @@ static int hns_roce_setup_hca(struct hns_roce_dev *hr_dev)
 		goto err_uar_alloc_free;
 	}
 
+	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_XRC) {
+		ret = hns_roce_init_xrcd_table(hr_dev);
+		if (ret) {
+			dev_err(dev, "failed to init xrcd table, ret = %d.\n",
+				ret);
+			goto err_pd_table_free;
+		}
+	}
+
 	ret = hns_roce_init_mr_table(hr_dev);
 	if (ret) {
 		dev_err(dev, "Failed to init memory region table.\n");
-		goto err_pd_table_free;
+		goto err_xrcd_table_free;
 	}
 
 	hns_roce_init_cq_table(hr_dev);
@@ -759,6 +779,10 @@ static int hns_roce_setup_hca(struct hns_roce_dev *hr_dev)
 	hns_roce_cleanup_cq_table(hr_dev);
 	hns_roce_cleanup_mr_table(hr_dev);
 
+err_xrcd_table_free:
+	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_XRC)
+		hns_roce_cleanup_xrcd_table(hr_dev);
+
 err_pd_table_free:
 	hns_roce_cleanup_pd_table(hr_dev);
 

drivers/infiniband/hw/hns/hns_roce_pd.c

@@ -137,3 +137,54 @@ void hns_roce_cleanup_uar_table(struct hns_roce_dev *hr_dev)
 {
 	hns_roce_bitmap_cleanup(&hr_dev->uar_table.bitmap);
 }
+
+static int hns_roce_xrcd_alloc(struct hns_roce_dev *hr_dev, u32 *xrcdn)
+{
+	return hns_roce_bitmap_alloc(&hr_dev->xrcd_bitmap,
+				     (unsigned long *)xrcdn);
+}
+
+static void hns_roce_xrcd_free(struct hns_roce_dev *hr_dev,
+			       u32 xrcdn)
+{
+	hns_roce_bitmap_free(&hr_dev->xrcd_bitmap, xrcdn, BITMAP_NO_RR);
+}
+
+int hns_roce_init_xrcd_table(struct hns_roce_dev *hr_dev)
+{
+	return hns_roce_bitmap_init(&hr_dev->xrcd_bitmap,
+				    hr_dev->caps.num_xrcds,
+				    hr_dev->caps.num_xrcds - 1,
+				    hr_dev->caps.reserved_xrcds, 0);
+}
+
+void hns_roce_cleanup_xrcd_table(struct hns_roce_dev *hr_dev)
+{
+	hns_roce_bitmap_cleanup(&hr_dev->xrcd_bitmap);
+}
+
+int hns_roce_alloc_xrcd(struct ib_xrcd *ib_xrcd, struct ib_udata *udata)
+{
+	struct hns_roce_dev *hr_dev = to_hr_dev(ib_xrcd->device);
+	struct hns_roce_xrcd *xrcd = to_hr_xrcd(ib_xrcd);
+	int ret;
+
+	if (!(hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_XRC))
+		return -EINVAL;
+
+	ret = hns_roce_xrcd_alloc(hr_dev, &xrcd->xrcdn);
+	if (ret) {
+		dev_err(hr_dev->dev, "failed to alloc xrcdn, ret = %d.\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+int hns_roce_dealloc_xrcd(struct ib_xrcd *ib_xrcd, struct ib_udata *udata)
+{
+	hns_roce_xrcd_free(to_hr_dev(ib_xrcd->device),
+			   to_hr_xrcd(ib_xrcd)->xrcdn);
+
+	return 0;
+}

drivers/infiniband/hw/hns/hns_roce_qp.c

@@ -98,7 +98,9 @@ void hns_roce_qp_event(struct hns_roce_dev *hr_dev, u32 qpn, int event_type)
 	if (hr_dev->hw_rev != HNS_ROCE_HW_VER1 &&
 	    (event_type == HNS_ROCE_EVENT_TYPE_WQ_CATAS_ERROR ||
 	     event_type == HNS_ROCE_EVENT_TYPE_INV_REQ_LOCAL_WQ_ERROR ||
-	     event_type == HNS_ROCE_EVENT_TYPE_LOCAL_WQ_ACCESS_ERROR)) {
+	     event_type == HNS_ROCE_EVENT_TYPE_LOCAL_WQ_ACCESS_ERROR ||
+	     event_type == HNS_ROCE_EVENT_TYPE_XRCD_VIOLATION ||
+	     event_type == HNS_ROCE_EVENT_TYPE_INVALID_XRCETH)) {
 		qp->state = IB_QPS_ERR;
 		if (!test_and_set_bit(HNS_ROCE_FLUSH_FLAG, &qp->flush_flag))
 			init_flush_work(hr_dev, qp);
@@ -142,6 +144,8 @@ static void hns_roce_ib_qp_event(struct hns_roce_qp *hr_qp,
 			event.event = IB_EVENT_QP_REQ_ERR;
 			break;
 		case HNS_ROCE_EVENT_TYPE_LOCAL_WQ_ACCESS_ERROR:
+		case HNS_ROCE_EVENT_TYPE_XRCD_VIOLATION:
+		case HNS_ROCE_EVENT_TYPE_INVALID_XRCETH:
 			event.event = IB_EVENT_QP_ACCESS_ERR;
 			break;
 		default:
@@ -366,8 +370,13 @@ void hns_roce_qp_remove(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp)
 	unsigned long flags;
 
 	list_del(&hr_qp->node);
-	list_del(&hr_qp->sq_node);
-	list_del(&hr_qp->rq_node);
+
+	if (hr_qp->ibqp.qp_type != IB_QPT_XRC_TGT)
+		list_del(&hr_qp->sq_node);
+
+	if (hr_qp->ibqp.qp_type != IB_QPT_XRC_INI &&
+	    hr_qp->ibqp.qp_type != IB_QPT_XRC_TGT)
+		list_del(&hr_qp->rq_node);
 
 	xa_lock_irqsave(xa, flags);
 	__xa_erase(xa, hr_qp->qpn & (hr_dev->caps.num_qps - 1));
@@ -1105,11 +1114,16 @@ static int check_qp_type(struct hns_roce_dev *hr_dev, enum ib_qp_type type,
 			 bool is_user)
 {
 	switch (type) {
+	case IB_QPT_XRC_INI:
+	case IB_QPT_XRC_TGT:
+		if (!(hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_XRC))
+			goto out;
+		break;
 	case IB_QPT_UD:
 		if (hr_dev->pci_dev->revision <= PCI_REVISION_ID_HIP08 &&
 		    is_user)
 			goto out;
-		fallthrough;
+		break;
 	case IB_QPT_RC:
 	case IB_QPT_GSI:
 		break;
@@ -1129,8 +1143,8 @@ struct ib_qp *hns_roce_create_qp(struct ib_pd *pd,
 				 struct ib_qp_init_attr *init_attr,
 				 struct ib_udata *udata)
 {
-	struct hns_roce_dev *hr_dev = to_hr_dev(pd->device);
-	struct ib_device *ibdev = &hr_dev->ib_dev;
+	struct ib_device *ibdev = pd ? pd->device : init_attr->xrcd->device;
+	struct hns_roce_dev *hr_dev = to_hr_dev(ibdev);
 	struct hns_roce_qp *hr_qp;
 	int ret;
 
@@ -1142,6 +1156,15 @@ struct ib_qp *hns_roce_create_qp(struct ib_pd *pd,
 	if (!hr_qp)
 		return ERR_PTR(-ENOMEM);
 
+	if (init_attr->qp_type == IB_QPT_XRC_INI)
+		init_attr->recv_cq = NULL;
+
+	if (init_attr->qp_type == IB_QPT_XRC_TGT) {
+		hr_qp->xrcdn = to_hr_xrcd(init_attr->xrcd)->xrcdn;
+		init_attr->recv_cq = NULL;
+		init_attr->send_cq = NULL;
+	}
+
 	if (init_attr->qp_type == IB_QPT_GSI) {
 		hr_qp->port = init_attr->port_num - 1;
 		hr_qp->phy_port = hr_dev->iboe.phy_port[hr_qp->port];
@@ -1161,20 +1184,20 @@ struct ib_qp *hns_roce_create_qp(struct ib_pd *pd,
 
 int to_hr_qp_type(int qp_type)
 {
-	int transport_type;
-
-	if (qp_type == IB_QPT_RC)
-		transport_type = SERV_TYPE_RC;
-	else if (qp_type == IB_QPT_UC)
-		transport_type = SERV_TYPE_UC;
-	else if (qp_type == IB_QPT_UD)
-		transport_type = SERV_TYPE_UD;
-	else if (qp_type == IB_QPT_GSI)
-		transport_type = SERV_TYPE_UD;
-	else
-		transport_type = -1;
-
-	return transport_type;
+	switch (qp_type) {
+	case IB_QPT_RC:
+		return SERV_TYPE_RC;
+	case IB_QPT_UC:
+		return SERV_TYPE_UC;
+	case IB_QPT_UD:
+	case IB_QPT_GSI:
+		return SERV_TYPE_UD;
+	case IB_QPT_XRC_INI:
+	case IB_QPT_XRC_TGT:
+		return SERV_TYPE_XRC;
+	default:
+		return -1;
+	}
 }
 
 static int check_mtu_validate(struct hns_roce_dev *hr_dev,

drivers/infiniband/hw/hns/hns_roce_srq.c

@@ -314,6 +314,9 @@ static void set_srq_ext_param(struct hns_roce_srq *srq,
 {
 	srq->cqn = ib_srq_has_cq(init_attr->srq_type) ?
 		   to_hr_cq(init_attr->ext.cq)->cqn : 0;
+
+	srq->xrcdn = (init_attr->srq_type == IB_SRQT_XRC) ?
+		     to_hr_xrcd(init_attr->ext.xrc.xrcd)->xrcdn : 0;
 }
 
 static int set_srq_param(struct hns_roce_srq *srq,

include/uapi/rdma/hns-abi.h

@@ -86,6 +86,8 @@ struct hns_roce_ib_create_qp_resp {
 struct hns_roce_ib_alloc_ucontext_resp {
 	__u32	qp_tab_size;
 	__u32	cqe_size;
+	__u32	srq_tab_size;
+	__u32	reserved;
 };
 
 struct hns_roce_ib_alloc_pd_resp {