RDMA/irdma: Introduce GEN3 vPort driver support

In the IPU model, a function can host one or more logical network
endpoints called vPorts. Each vPort may be associated with either a
physical or an internal communication port, and can be RDMA capable. A
vPort features a netdev and, if RDMA capable, must have an associated
ib_dev.

This change introduces a GEN3 auxiliary vPort driver responsible for
registering a verbs device for every RDMA-capable vPort. Additionally,
the UAPI is updated to prevent the binding of GEN3 devices to older
user-space providers.

Signed-off-by: Mustafa Ismail <mustafa.ismail@intel.com>
Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Link: https://patch.msgid.link/20250827152545.2056-8-tatyana.e.nikolova@intel.com
Tested-by: Jacob Moroni <jmoroni@google.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>

4 files changed, 132 insertions, 1 deletions

diff --git a/drivers/infiniband/hw/irdma/main.c b/drivers/infiniband/hw/irdma/main.c
index 162f1fab32b5..95957d52883d 100644
--- a/drivers/infiniband/hw/irdma/main.c
+++ b/drivers/infiniband/hw/irdma/main.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 /* Copyright (c) 2015 - 2021 Intel Corporation */
 #include "main.h"
+#include <linux/net/intel/iidc_rdma_idpf.h>
 
 MODULE_ALIAS("i40iw");
 MODULE_DESCRIPTION("Intel(R) Ethernet Protocol Driver for RDMA");
@@ -46,6 +47,113 @@ void irdma_log_invalid_mtu(u16 mtu, struct irdma_sc_dev *dev)
 		ibdev_warn(to_ibdev(dev), "MTU setting [%d] too low for RDMA traffic. Minimum MTU is 1280 for IPv6\\n", mtu);
 }
 
+static void ig3rdma_idc_vport_event_handler(struct iidc_rdma_vport_dev_info *cdev_info,
+					    struct iidc_rdma_event *event)
+{
+	struct irdma_device *iwdev = auxiliary_get_drvdata(cdev_info->adev);
+	struct irdma_l2params l2params = {};
+
+	if (*event->type & BIT(IIDC_RDMA_EVENT_AFTER_MTU_CHANGE)) {
+		ibdev_dbg(&iwdev->ibdev, "CLNT: new MTU = %d\n", iwdev->netdev->mtu);
+		if (iwdev->vsi.mtu != iwdev->netdev->mtu) {
+			l2params.mtu = iwdev->netdev->mtu;
+			l2params.mtu_changed = true;
+			irdma_log_invalid_mtu(l2params.mtu, &iwdev->rf->sc_dev);
+			irdma_change_l2params(&iwdev->vsi, &l2params);
+		}
+	}
+}
+
+static int ig3rdma_vport_probe(struct auxiliary_device *aux_dev,
+			       const struct auxiliary_device_id *id)
+{
+	struct iidc_rdma_vport_auxiliary_dev *idc_adev =
+		container_of(aux_dev, struct iidc_rdma_vport_auxiliary_dev, adev);
+	struct auxiliary_device *aux_core_dev = idc_adev->vdev_info->core_adev;
+	struct irdma_pci_f *rf = auxiliary_get_drvdata(aux_core_dev);
+	struct irdma_l2params l2params = {};
+	struct irdma_device *iwdev;
+	int err;
+
+	if (!rf) {
+		WARN_ON_ONCE(1);
+		return -ENOMEM;
+	}
+	iwdev = ib_alloc_device(irdma_device, ibdev);
+	/* Fill iwdev info */
+	iwdev->is_vport = true;
+	iwdev->rf = rf;
+	iwdev->vport_id = idc_adev->vdev_info->vport_id;
+	iwdev->netdev = idc_adev->vdev_info->netdev;
+	iwdev->init_state = INITIAL_STATE;
+	iwdev->roce_cwnd = IRDMA_ROCE_CWND_DEFAULT;
+	iwdev->roce_ackcreds = IRDMA_ROCE_ACKCREDS_DEFAULT;
+	iwdev->rcv_wnd = IRDMA_CM_DEFAULT_RCV_WND_SCALED;
+	iwdev->rcv_wscale = IRDMA_CM_DEFAULT_RCV_WND_SCALE;
+	iwdev->roce_mode = true;
+	iwdev->push_mode = false;
+
+	l2params.mtu = iwdev->netdev->mtu;
+
+	err = irdma_rt_init_hw(iwdev, &l2params);
+	if (err)
+		goto err_rt_init;
+
+	err = irdma_ib_register_device(iwdev);
+	if (err)
+		goto err_ibreg;
+
+	auxiliary_set_drvdata(aux_dev, iwdev);
+
+	ibdev_dbg(&iwdev->ibdev,
+		  "INIT: Gen[%d] vport[%d] probe success. dev_name = %s, core_dev_name = %s, netdev=%s\n",
+		  rf->rdma_ver, idc_adev->vdev_info->vport_id,
+		  dev_name(&aux_dev->dev),
+		  dev_name(&idc_adev->vdev_info->core_adev->dev),
+		  netdev_name(idc_adev->vdev_info->netdev));
+
+	return 0;
+err_ibreg:
+	irdma_rt_deinit_hw(iwdev);
+err_rt_init:
+	ib_dealloc_device(&iwdev->ibdev);
+
+	return err;
+}
+
+static void ig3rdma_vport_remove(struct auxiliary_device *aux_dev)
+{
+	struct iidc_rdma_vport_auxiliary_dev *idc_adev =
+		container_of(aux_dev, struct iidc_rdma_vport_auxiliary_dev, adev);
+	struct irdma_device *iwdev = auxiliary_get_drvdata(aux_dev);
+
+	ibdev_dbg(&iwdev->ibdev,
+		  "INIT: Gen[%d] dev_name = %s, core_dev_name = %s, netdev=%s\n",
+		  iwdev->rf->rdma_ver, dev_name(&aux_dev->dev),
+		  dev_name(&idc_adev->vdev_info->core_adev->dev),
+		  netdev_name(idc_adev->vdev_info->netdev));
+
+	irdma_ib_unregister_device(iwdev);
+}
+
+static const struct auxiliary_device_id ig3rdma_vport_auxiliary_id_table[] = {
+	{.name = "idpf.8086.rdma.vdev", },
+	{},
+};
+
+MODULE_DEVICE_TABLE(auxiliary, ig3rdma_vport_auxiliary_id_table);
+
+static struct iidc_rdma_vport_auxiliary_drv ig3rdma_vport_auxiliary_drv = {
+	.adrv = {
+		.name = "vdev",
+		.id_table = ig3rdma_vport_auxiliary_id_table,
+		.probe = ig3rdma_vport_probe,
+		.remove = ig3rdma_vport_remove,
+	},
+	.event_handler = ig3rdma_idc_vport_event_handler,
+};
+
+
 static int __init irdma_init_module(void)
 {
 	int ret;
@@ -74,6 +182,17 @@ static int __init irdma_init_module(void)
 
 		return ret;
 	}
+
+	ret = auxiliary_driver_register(&ig3rdma_vport_auxiliary_drv.adrv);
+	if (ret) {
+		auxiliary_driver_unregister(&ig3rdma_core_auxiliary_drv.adrv);
+		auxiliary_driver_unregister(&icrdma_core_auxiliary_drv.adrv);
+		auxiliary_driver_unregister(&i40iw_auxiliary_drv);
+		pr_err("Failed ig3rdma vport auxiliary_driver_register() ret=%d\n",
+		       ret);
+
+		return ret;
+	}
 	irdma_register_notifiers();
 
 	return 0;
@@ -85,6 +204,7 @@ static void __exit irdma_exit_module(void)
 	auxiliary_driver_unregister(&icrdma_core_auxiliary_drv.adrv);
 	auxiliary_driver_unregister(&i40iw_auxiliary_drv);
 	auxiliary_driver_unregister(&ig3rdma_core_auxiliary_drv.adrv);
+	auxiliary_driver_unregister(&ig3rdma_vport_auxiliary_drv.adrv);
 }
 
 module_init(irdma_init_module);
diff --git a/drivers/infiniband/hw/irdma/main.h b/drivers/infiniband/hw/irdma/main.h
index 7300f8ab49ca..c64d772dc644 100644
--- a/drivers/infiniband/hw/irdma/main.h
+++ b/drivers/infiniband/hw/irdma/main.h
@@ -354,12 +354,14 @@ struct irdma_device {
 	u32 rcv_wnd;
 	u16 mac_ip_table_idx;
 	u16 vsi_num;
+	u16 vport_id;
 	u8 rcv_wscale;
 	u8 iw_status;
 	bool roce_mode:1;
 	bool roce_dcqcn_en:1;
 	bool dcb_vlan_mode:1;
 	bool iw_ooo:1;
+	bool is_vport:1;
 	enum init_completion_state init_state;
 
 	wait_queue_head_t suspend_wq;
diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
index 894c1f7bcb43..7f59bdd85da0 100644
--- a/drivers/infiniband/hw/irdma/verbs.c
+++ b/drivers/infiniband/hw/irdma/verbs.c
@@ -292,6 +292,10 @@ static int irdma_alloc_ucontext(struct ib_ucontext *uctx,
 	ucontext->iwdev = iwdev;
 	ucontext->abi_ver = req.userspace_ver;
 
+	if (!(req.comp_mask & IRDMA_SUPPORT_WQE_FORMAT_V2) &&
+	    uk_attrs->hw_rev >= IRDMA_GEN_3)
+		return -EOPNOTSUPP;
+
 	if (req.comp_mask & IRDMA_ALLOC_UCTX_USE_RAW_ATTR)
 		ucontext->use_raw_attrs = true;
 
@@ -4891,5 +4895,9 @@ void irdma_ib_dealloc_device(struct ib_device *ibdev)
 	struct irdma_device *iwdev = to_iwdev(ibdev);
 
 	irdma_rt_deinit_hw(iwdev);
-	irdma_ctrl_deinit_hw(iwdev->rf);
+	if (!iwdev->is_vport) {
+		irdma_ctrl_deinit_hw(iwdev->rf);
+		if (iwdev->rf->vchnl_wq)
+			destroy_workqueue(iwdev->rf->vchnl_wq);
+	}
 }
diff --git a/include/uapi/rdma/irdma-abi.h b/include/uapi/rdma/irdma-abi.h
index bb18f15489e3..4e42054cca33 100644
--- a/include/uapi/rdma/irdma-abi.h
+++ b/include/uapi/rdma/irdma-abi.h
@@ -25,6 +25,7 @@ enum irdma_memreg_type {
 enum {
 	IRDMA_ALLOC_UCTX_USE_RAW_ATTR = 1 << 0,
 	IRDMA_ALLOC_UCTX_MIN_HW_WQ_SIZE = 1 << 1,
+	IRDMA_SUPPORT_WQE_FORMAT_V2 = 1 << 3,
 };
 
 struct irdma_alloc_ucontext_req {