Merge: Rebase HyperV MANA driver to upstream kernel v6.11-rc3

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/5023


This pull request rebases MANA driver to kernel v6.11-rc3

JIRA: https://issues.redhat.com/browse/RHEL-54330

Tested: compile tested only

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>

Approved-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Approved-by: Wander Lairson Costa <wander@redhat.com>
Approved-by: Chris von Recklinghausen <crecklin@redhat.com>
Approved-by: Izabela Bakollari <ibakolla@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Rado Vrbovsky <rvrbovsk@redhat.com>

Author: emmil

drivers/infiniband/hw/mana/cq.c

@@ -9,66 +9,78 @@ int mana_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		      struct ib_udata *udata)
 {
 	struct mana_ib_cq *cq = container_of(ibcq, struct mana_ib_cq, ibcq);
+	struct mana_ib_create_cq_resp resp = {};
+	struct mana_ib_ucontext *mana_ucontext;
 	struct ib_device *ibdev = ibcq->device;
 	struct mana_ib_create_cq ucmd = {};
 	struct mana_ib_dev *mdev;
-	struct gdma_context *gc;
+	bool is_rnic_cq;
+	u32 doorbell;
 	int err;
 
 	mdev = container_of(ibdev, struct mana_ib_dev, ib_dev);
-	gc = mdev->gdma_dev->gdma_context;
 
-	if (udata->inlen < sizeof(ucmd))
-		return -EINVAL;
+	cq->comp_vector = attr->comp_vector % ibdev->num_comp_vectors;
+	cq->cq_handle = INVALID_MANA_HANDLE;
 
-	if (attr->comp_vector > gc->max_num_queues)
+	if (udata->inlen < offsetof(struct mana_ib_create_cq, flags))
 		return -EINVAL;
 
-	cq->comp_vector = attr->comp_vector;
-
 	err = ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata->inlen));
 	if (err) {
 		ibdev_dbg(ibdev,
 			  "Failed to copy from udata for create cq, %d\n", err);
 		return err;
 	}
 
-	if (attr->cqe > mdev->adapter_caps.max_qp_wr) {
+	is_rnic_cq = !!(ucmd.flags & MANA_IB_CREATE_RNIC_CQ);
+
+	if (!is_rnic_cq && attr->cqe > mdev->adapter_caps.max_qp_wr) {
 		ibdev_dbg(ibdev, "CQE %d exceeding limit\n", attr->cqe);
 		return -EINVAL;
 	}
 
 	cq->cqe = attr->cqe;
-	cq->umem = ib_umem_get(ibdev, ucmd.buf_addr, cq->cqe * COMP_ENTRY_SIZE,
-			       IB_ACCESS_LOCAL_WRITE);
-	if (IS_ERR(cq->umem)) {
-		err = PTR_ERR(cq->umem);
-		ibdev_dbg(ibdev, "Failed to get umem for create cq, err %d\n",
-			  err);
+	err = mana_ib_create_queue(mdev, ucmd.buf_addr, cq->cqe * COMP_ENTRY_SIZE, &cq->queue);
+	if (err) {
+		ibdev_dbg(ibdev, "Failed to create queue for create cq, %d\n", err);
 		return err;
 	}
 
-	err = mana_ib_gd_create_dma_region(mdev, cq->umem, &cq->gdma_region);
-	if (err) {
-		ibdev_dbg(ibdev,
-			  "Failed to create dma region for create cq, %d\n",
-			  err);
-		goto err_release_umem;
+	mana_ucontext = rdma_udata_to_drv_context(udata, struct mana_ib_ucontext,
+						  ibucontext);
+	doorbell = mana_ucontext->doorbell;
+
+	if (is_rnic_cq) {
+		err = mana_ib_gd_create_cq(mdev, cq, doorbell);
+		if (err) {
+			ibdev_dbg(ibdev, "Failed to create RNIC cq, %d\n", err);
+			goto err_destroy_queue;
+		}
+
+		err = mana_ib_install_cq_cb(mdev, cq);
+		if (err) {
+			ibdev_dbg(ibdev, "Failed to install cq callback, %d\n", err);
+			goto err_destroy_rnic_cq;
+		}
 	}
 
-	ibdev_dbg(ibdev,
-		  "mana_ib_gd_create_dma_region ret %d gdma_region 0x%llx\n",
-		  err, cq->gdma_region);
-
-	/*
-	 * The CQ ID is not known at this time. The ID is generated at create_qp
-	 */
-	cq->id = INVALID_QUEUE_ID;
+	resp.cqid = cq->queue.id;
+	err = ib_copy_to_udata(udata, &resp, min(sizeof(resp), udata->outlen));
+	if (err) {
+		ibdev_dbg(&mdev->ib_dev, "Failed to copy to udata, %d\n", err);
+		goto err_remove_cq_cb;
+	}
 
 	return 0;
 
-err_release_umem:
-	ib_umem_release(cq->umem);
+err_remove_cq_cb:
+	mana_ib_remove_cq_cb(mdev, cq);
+err_destroy_rnic_cq:
+	mana_ib_gd_destroy_cq(mdev, cq);
+err_destroy_queue:
+	mana_ib_destroy_queue(mdev, &cq->queue);
+
 	return err;
 }
 
@@ -77,33 +89,57 @@ int mana_ib_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata)
 	struct mana_ib_cq *cq = container_of(ibcq, struct mana_ib_cq, ibcq);
 	struct ib_device *ibdev = ibcq->device;
 	struct mana_ib_dev *mdev;
-	struct gdma_context *gc;
-	int err;
 
 	mdev = container_of(ibdev, struct mana_ib_dev, ib_dev);
-	gc = mdev->gdma_dev->gdma_context;
 
-	err = mana_ib_gd_destroy_dma_region(mdev, cq->gdma_region);
-	if (err) {
-		ibdev_dbg(ibdev,
-			  "Failed to destroy dma region, %d\n", err);
-		return err;
-	}
+	mana_ib_remove_cq_cb(mdev, cq);
 
-	if (cq->id != INVALID_QUEUE_ID) {
-		kfree(gc->cq_table[cq->id]);
-		gc->cq_table[cq->id] = NULL;
-	}
+	/* Ignore return code as there is not much we can do about it.
+	 * The error message is printed inside.
+	 */
+	mana_ib_gd_destroy_cq(mdev, cq);
 
-	ib_umem_release(cq->umem);
+	mana_ib_destroy_queue(mdev, &cq->queue);
 
 	return 0;
 }
 
-void mana_ib_cq_handler(void *ctx, struct gdma_queue *gdma_cq)
+static void mana_ib_cq_handler(void *ctx, struct gdma_queue *gdma_cq)
 {
 	struct mana_ib_cq *cq = ctx;
 
 	if (cq->ibcq.comp_handler)
 		cq->ibcq.comp_handler(&cq->ibcq, cq->ibcq.cq_context);
 }
+
+int mana_ib_install_cq_cb(struct mana_ib_dev *mdev, struct mana_ib_cq *cq)
+{
+	struct gdma_context *gc = mdev_to_gc(mdev);
+	struct gdma_queue *gdma_cq;
+
+	if (cq->queue.id >= gc->max_num_cqs)
+		return -EINVAL;
+	/* Create CQ table entry */
+	WARN_ON(gc->cq_table[cq->queue.id]);
+	gdma_cq = kzalloc(sizeof(*gdma_cq), GFP_KERNEL);
+	if (!gdma_cq)
+		return -ENOMEM;
+
+	gdma_cq->cq.context = cq;
+	gdma_cq->type = GDMA_CQ;
+	gdma_cq->cq.callback = mana_ib_cq_handler;
+	gdma_cq->id = cq->queue.id;
+	gc->cq_table[cq->queue.id] = gdma_cq;
+	return 0;
+}
+
+void mana_ib_remove_cq_cb(struct mana_ib_dev *mdev, struct mana_ib_cq *cq)
+{
+	struct gdma_context *gc = mdev_to_gc(mdev);
+
+	if (cq->queue.id >= gc->max_num_cqs || cq->queue.id == INVALID_QUEUE_ID)
+		return;
+
+	kfree(gc->cq_table[cq->queue.id]);
+	gc->cq_table[cq->queue.id] = NULL;
+}

drivers/infiniband/hw/mana/device.c

@@ -5,6 +5,8 @@
 
 #include "mana_ib.h"
 #include <net/mana/mana_auxiliary.h>
+#include <linux/etherdevice.h>
+#include <net/addrconf.h>
 
 MODULE_DESCRIPTION("Microsoft Azure Network Adapter IB driver");
 MODULE_LICENSE("GPL");
@@ -15,6 +17,7 @@ static const struct ib_device_ops mana_ib_dev_ops = {
 	.driver_id = RDMA_DRIVER_MANA,
 	.uverbs_abi_ver = MANA_IB_UVERBS_ABI_VERSION,
 
+	.add_gid = mana_ib_gd_add_gid,
 	.alloc_pd = mana_ib_alloc_pd,
 	.alloc_ucontext = mana_ib_alloc_ucontext,
 	.create_cq = mana_ib_create_cq,
@@ -23,18 +26,21 @@ static const struct ib_device_ops mana_ib_dev_ops = {
 	.create_wq = mana_ib_create_wq,
 	.dealloc_pd = mana_ib_dealloc_pd,
 	.dealloc_ucontext = mana_ib_dealloc_ucontext,
+	.del_gid = mana_ib_gd_del_gid,
 	.dereg_mr = mana_ib_dereg_mr,
 	.destroy_cq = mana_ib_destroy_cq,
 	.destroy_qp = mana_ib_destroy_qp,
 	.destroy_rwq_ind_table = mana_ib_destroy_rwq_ind_table,
 	.destroy_wq = mana_ib_destroy_wq,
 	.disassociate_ucontext = mana_ib_disassociate_ucontext,
+	.get_link_layer = mana_ib_get_link_layer,
 	.get_port_immutable = mana_ib_get_port_immutable,
 	.mmap = mana_ib_mmap,
 	.modify_qp = mana_ib_modify_qp,
 	.modify_wq = mana_ib_modify_wq,
 	.query_device = mana_ib_query_device,
 	.query_gid = mana_ib_query_gid,
+	.query_pkey = mana_ib_query_pkey,
 	.query_port = mana_ib_query_port,
 	.reg_user_mr = mana_ib_reg_user_mr,
 
@@ -51,8 +57,10 @@ static int mana_ib_probe(struct auxiliary_device *adev,
 {
 	struct mana_adev *madev = container_of(adev, struct mana_adev, adev);
 	struct gdma_dev *mdev = madev->mdev;
+	struct net_device *ndev;
 	struct mana_context *mc;
 	struct mana_ib_dev *dev;
+	u8 mac_addr[ETH_ALEN];
 	int ret;
 
 	mc = mdev->driver_data;
@@ -74,9 +82,26 @@ static int mana_ib_probe(struct auxiliary_device *adev,
 	 * num_comp_vectors needs to set to the max MSIX index
 	 * when interrupts and event queues are implemented
 	 */
-	dev->ib_dev.num_comp_vectors = 1;
+	dev->ib_dev.num_comp_vectors = mdev->gdma_context->max_num_queues;
 	dev->ib_dev.dev.parent = mdev->gdma_context->dev;
 
+	rcu_read_lock(); /* required to get primary netdev */
+	ndev = mana_get_primary_netdev_rcu(mc, 0);
+	if (!ndev) {
+		rcu_read_unlock();
+		ret = -ENODEV;
+		ibdev_err(&dev->ib_dev, "Failed to get netdev for IB port 1");
+		goto free_ib_device;
+	}
+	ether_addr_copy(mac_addr, ndev->dev_addr);
+	addrconf_addr_eui48((u8 *)&dev->ib_dev.node_guid, ndev->dev_addr);
+	ret = ib_device_set_netdev(&dev->ib_dev, ndev, 1);
+	rcu_read_unlock();
+	if (ret) {
+		ibdev_err(&dev->ib_dev, "Failed to set ib netdev, ret %d", ret);
+		goto free_ib_device;
+	}
+
 	ret = mana_gd_register_device(&mdev->gdma_context->mana_ib);
 	if (ret) {
 		ibdev_err(&dev->ib_dev, "Failed to register device, ret %d",
@@ -92,15 +117,38 @@ static int mana_ib_probe(struct auxiliary_device *adev,
 		goto deregister_device;
 	}
 
+	ret = mana_ib_create_eqs(dev);
+	if (ret) {
+		ibdev_err(&dev->ib_dev, "Failed to create EQs, ret %d", ret);
+		goto deregister_device;
+	}
+
+	ret = mana_ib_gd_create_rnic_adapter(dev);
+	if (ret)
+		goto destroy_eqs;
+
+	xa_init_flags(&dev->qp_table_wq, XA_FLAGS_LOCK_IRQ);
+	ret = mana_ib_gd_config_mac(dev, ADDR_OP_ADD, mac_addr);
+	if (ret) {
+		ibdev_err(&dev->ib_dev, "Failed to add Mac address, ret %d",
+			  ret);
+		goto destroy_rnic;
+	}
+
 	ret = ib_register_device(&dev->ib_dev, "mana_%d",
 				 mdev->gdma_context->dev);
 	if (ret)
-		goto deregister_device;
+		goto destroy_rnic;
 
 	dev_set_drvdata(&adev->dev, dev);
 
 	return 0;
 
+destroy_rnic:
+	xa_destroy(&dev->qp_table_wq);
+	mana_ib_gd_destroy_rnic_adapter(dev);
+destroy_eqs:
+	mana_ib_destroy_eqs(dev);
 deregister_device:
 	mana_gd_deregister_device(dev->gdma_dev);
 free_ib_device:
@@ -113,9 +161,10 @@ static void mana_ib_remove(struct auxiliary_device *adev)
 	struct mana_ib_dev *dev = dev_get_drvdata(&adev->dev);
 
 	ib_unregister_device(&dev->ib_dev);
-
+	xa_destroy(&dev->qp_table_wq);
+	mana_ib_gd_destroy_rnic_adapter(dev);
+	mana_ib_destroy_eqs(dev);
 	mana_gd_deregister_device(dev->gdma_dev);
-
 	ib_dealloc_device(&dev->ib_dev);
 }