Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR.

Conflicts:

drivers/net/ethernet/sfc/tc.c
  fa165e194997 ("sfc: don't unregister flow_indr if it was never registered")
  3bf969e88ada ("sfc: add MAE table machinery for conntrack table")
https://lore.kernel.org/all/20230818112159.7430e9b4@canb.auug.org.au/

No adjacent changes.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

9 files changed, 225 insertions, 116 deletions

diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
index 25fc4120b618..b53420e874ac 100644
--- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h
+++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
@@ -31,6 +31,7 @@ struct mlx5_vdpa_mr {
 	struct list_head head;
 	unsigned long num_directs;
 	unsigned long num_klms;
+	/* state of dvq mr */
 	bool initialized;
 
 	/* serialize mkey creation and destruction */
@@ -121,6 +122,7 @@ int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *io
 int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
 			unsigned int asid);
 void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev);
+void mlx5_vdpa_destroy_mr_asid(struct mlx5_vdpa_dev *mvdev, unsigned int asid);
 
 #define mlx5_vdpa_warn(__dev, format, ...)                                                         \
 	dev_warn((__dev)->mdev->device, "%s:%d:(pid %d) warning: " format, __func__, __LINE__,     \
diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c
index 03e543229791..5a1971fcd87b 100644
--- a/drivers/vdpa/mlx5/core/mr.c
+++ b/drivers/vdpa/mlx5/core/mr.c
@@ -489,60 +489,103 @@ static void destroy_user_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mr
 	}
 }
 
-void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev)
+static void _mlx5_vdpa_destroy_cvq_mr(struct mlx5_vdpa_dev *mvdev, unsigned int asid)
+{
+	if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] != asid)
+		return;
+
+	prune_iotlb(mvdev);
+}
+
+static void _mlx5_vdpa_destroy_dvq_mr(struct mlx5_vdpa_dev *mvdev, unsigned int asid)
 {
 	struct mlx5_vdpa_mr *mr = &mvdev->mr;
 
-	mutex_lock(&mr->mkey_mtx);
+	if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] != asid)
+		return;
+
 	if (!mr->initialized)
-		goto out;
+		return;
 
-	prune_iotlb(mvdev);
 	if (mr->user_mr)
 		destroy_user_mr(mvdev, mr);
 	else
 		destroy_dma_mr(mvdev, mr);
 
 	mr->initialized = false;
-out:
+}
+
+void mlx5_vdpa_destroy_mr_asid(struct mlx5_vdpa_dev *mvdev, unsigned int asid)
+{
+	struct mlx5_vdpa_mr *mr = &mvdev->mr;
+
+	mutex_lock(&mr->mkey_mtx);
+
+	_mlx5_vdpa_destroy_dvq_mr(mvdev, asid);
+	_mlx5_vdpa_destroy_cvq_mr(mvdev, asid);
+
 	mutex_unlock(&mr->mkey_mtx);
 }
 
-static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev,
-				struct vhost_iotlb *iotlb, unsigned int asid)
+void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev)
+{
+	mlx5_vdpa_destroy_mr_asid(mvdev, mvdev->group2asid[MLX5_VDPA_CVQ_GROUP]);
+	mlx5_vdpa_destroy_mr_asid(mvdev, mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP]);
+}
+
+static int _mlx5_vdpa_create_cvq_mr(struct mlx5_vdpa_dev *mvdev,
+				    struct vhost_iotlb *iotlb,
+				    unsigned int asid)
+{
+	if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] != asid)
+		return 0;
+
+	return dup_iotlb(mvdev, iotlb);
+}
+
+static int _mlx5_vdpa_create_dvq_mr(struct mlx5_vdpa_dev *mvdev,
+				    struct vhost_iotlb *iotlb,
+				    unsigned int asid)
 {
 	struct mlx5_vdpa_mr *mr = &mvdev->mr;
 	int err;
 
-	if (mr->initialized)
+	if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] != asid)
 		return 0;
 
-	if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) {
-		if (iotlb)
-			err = create_user_mr(mvdev, iotlb);
-		else
-			err = create_dma_mr(mvdev, mr);
+	if (mr->initialized)
+		return 0;
 
-		if (err)
-			return err;
-	}
+	if (iotlb)
+		err = create_user_mr(mvdev, iotlb);
+	else
+		err = create_dma_mr(mvdev, mr);
 
-	if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] == asid) {
-		err = dup_iotlb(mvdev, iotlb);
-		if (err)
-			goto out_err;
-	}
+	if (err)
+		return err;
 
 	mr->initialized = true;
+
+	return 0;
+}
+
+static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev,
+				struct vhost_iotlb *iotlb, unsigned int asid)
+{
+	int err;
+
+	err = _mlx5_vdpa_create_dvq_mr(mvdev, iotlb, asid);
+	if (err)
+		return err;
+
+	err = _mlx5_vdpa_create_cvq_mr(mvdev, iotlb, asid);
+	if (err)
+		goto out_err;
+
 	return 0;
 
 out_err:
-	if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) {
-		if (iotlb)
-			destroy_user_mr(mvdev, mr);
-		else
-			destroy_dma_mr(mvdev, mr);
-	}
+	_mlx5_vdpa_destroy_dvq_mr(mvdev, asid);
 
 	return err;
 }
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index bece4df7b8dd..40a03b08d7cf 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -2517,7 +2517,15 @@ static int mlx5_vdpa_set_driver_features(struct vdpa_device *vdev, u64 features)
 	else
 		ndev->rqt_size = 1;
 
-	ndev->cur_num_vqs = 2 * ndev->rqt_size;
+	/* Device must start with 1 queue pair, as per VIRTIO v1.2 spec, section
+	 * 5.1.6.5.5 "Device operation in multiqueue mode":
+	 *
+	 * Multiqueue is disabled by default.
+	 * The driver enables multiqueue by sending a command using class
+	 * VIRTIO_NET_CTRL_MQ. The command selects the mode of multiqueue
+	 * operation, as follows: ...
+	 */
+	ndev->cur_num_vqs = 2;
 
 	update_cvq_info(mvdev);
 	return err;
@@ -2636,7 +2644,7 @@ static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev,
 		goto err_mr;
 
 	teardown_driver(ndev);
-	mlx5_vdpa_destroy_mr(mvdev);
+	mlx5_vdpa_destroy_mr_asid(mvdev, asid);
 	err = mlx5_vdpa_create_mr(mvdev, iotlb, asid);
 	if (err)
 		goto err_mr;
@@ -2652,7 +2660,7 @@ static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev,
 	return 0;
 
 err_setup:
-	mlx5_vdpa_destroy_mr(mvdev);
+	mlx5_vdpa_destroy_mr_asid(mvdev, asid);
 err_mr:
 	return err;
 }
@@ -3548,17 +3556,6 @@ static void mlx5v_remove(struct auxiliary_device *adev)
 	kfree(mgtdev);
 }
 
-static void mlx5v_shutdown(struct auxiliary_device *auxdev)
-{
-	struct mlx5_vdpa_mgmtdev *mgtdev;
-	struct mlx5_vdpa_net *ndev;
-
-	mgtdev = auxiliary_get_drvdata(auxdev);
-	ndev = mgtdev->ndev;
-
-	free_irqs(ndev);
-}
-
 static const struct auxiliary_device_id mlx5v_id_table[] = {
 	{ .name = MLX5_ADEV_NAME ".vnet", },
 	{},
@@ -3570,7 +3567,6 @@ static struct auxiliary_driver mlx5v_driver = {
 	.name = "vnet",
 	.probe = mlx5v_probe,
 	.remove = mlx5v_remove,
-	.shutdown = mlx5v_shutdown,
 	.id_table = mlx5v_id_table,
 };
 
diff --git a/drivers/vdpa/pds/Makefile b/drivers/vdpa/pds/Makefile
index 2e22418e3ab3..c2d314d4614d 100644
--- a/drivers/vdpa/pds/Makefile
+++ b/drivers/vdpa/pds/Makefile
@@ -5,6 +5,5 @@ obj-$(CONFIG_PDS_VDPA) := pds_vdpa.o
 
 pds_vdpa-y := aux_drv.o \
 	      cmds.o \
+	      debugfs.o \
 	      vdpa_dev.o
-
-pds_vdpa-$(CONFIG_DEBUG_FS) += debugfs.o
diff --git a/drivers/vdpa/pds/debugfs.c b/drivers/vdpa/pds/debugfs.c
index 21a0dc0cb607..9b04aad6ec35 100644
--- a/drivers/vdpa/pds/debugfs.c
+++ b/drivers/vdpa/pds/debugfs.c
@@ -176,6 +176,7 @@ static int identity_show(struct seq_file *seq, void *v)
 {
 	struct pds_vdpa_aux *vdpa_aux = seq->private;
 	struct vdpa_mgmt_dev *mgmt;
+	u64 hw_features;
 
 	seq_printf(seq, "aux_dev:            %s\n",
 		   dev_name(&vdpa_aux->padev->aux_dev.dev));
@@ -183,8 +184,9 @@ static int identity_show(struct seq_file *seq, void *v)
 	mgmt = &vdpa_aux->vdpa_mdev;
 	seq_printf(seq, "max_vqs:            %d\n", mgmt->max_supported_vqs);
 	seq_printf(seq, "config_attr_mask:   %#llx\n", mgmt->config_attr_mask);
-	seq_printf(seq, "supported_features: %#llx\n", mgmt->supported_features);
-	print_feature_bits_all(seq, mgmt->supported_features);
+	hw_features = le64_to_cpu(vdpa_aux->ident.hw_features);
+	seq_printf(seq, "hw_features:        %#llx\n", hw_features);
+	print_feature_bits_all(seq, hw_features);
 
 	return 0;
 }
@@ -200,7 +202,6 @@ static int config_show(struct seq_file *seq, void *v)
 {
 	struct pds_vdpa_device *pdsv = seq->private;
 	struct virtio_net_config vc;
-	u64 driver_features;
 	u8 status;
 
 	memcpy_fromio(&vc, pdsv->vdpa_aux->vd_mdev.device,
@@ -223,12 +224,8 @@ static int config_show(struct seq_file *seq, void *v)
 	status = vp_modern_get_status(&pdsv->vdpa_aux->vd_mdev);
 	seq_printf(seq, "dev_status:           %#x\n", status);
 	print_status_bits(seq, status);
-
-	seq_printf(seq, "req_features:         %#llx\n", pdsv->req_features);
-	print_feature_bits_all(seq, pdsv->req_features);
-	driver_features = vp_modern_get_driver_features(&pdsv->vdpa_aux->vd_mdev);
-	seq_printf(seq, "driver_features:      %#llx\n", driver_features);
-	print_feature_bits_all(seq, driver_features);
+	seq_printf(seq, "negotiated_features:  %#llx\n", pdsv->negotiated_features);
+	print_feature_bits_all(seq, pdsv->negotiated_features);
 	seq_printf(seq, "vdpa_index:           %d\n", pdsv->vdpa_index);
 	seq_printf(seq, "num_vqs:              %d\n", pdsv->num_vqs);
 
diff --git a/drivers/vdpa/pds/vdpa_dev.c b/drivers/vdpa/pds/vdpa_dev.c
index 5071a4d58f8d..52b2449182ad 100644
--- a/drivers/vdpa/pds/vdpa_dev.c
+++ b/drivers/vdpa/pds/vdpa_dev.c
@@ -126,11 +126,9 @@ static void pds_vdpa_release_irq(struct pds_vdpa_device *pdsv, int qid)
 static void pds_vdpa_set_vq_ready(struct vdpa_device *vdpa_dev, u16 qid, bool ready)
 {
 	struct pds_vdpa_device *pdsv = vdpa_to_pdsv(vdpa_dev);
-	struct pci_dev *pdev = pdsv->vdpa_aux->padev->vf_pdev;
 	struct device *dev = &pdsv->vdpa_dev.dev;
 	u64 driver_features;
 	u16 invert_idx = 0;
-	int irq;
 	int err;
 
 	dev_dbg(dev, "%s: qid %d ready %d => %d\n",
@@ -143,19 +141,6 @@ static void pds_vdpa_set_vq_ready(struct vdpa_device *vdpa_dev, u16 qid, bool re
 		invert_idx = PDS_VDPA_PACKED_INVERT_IDX;
 
 	if (ready) {
-		irq = pci_irq_vector(pdev, qid);
-		snprintf(pdsv->vqs[qid].irq_name, sizeof(pdsv->vqs[qid].irq_name),
-			 "vdpa-%s-%d", dev_name(dev), qid);
-
-		err = request_irq(irq, pds_vdpa_isr, 0,
-				  pdsv->vqs[qid].irq_name, &pdsv->vqs[qid]);
-		if (err) {
-			dev_err(dev, "%s: no irq for qid %d: %pe\n",
-				__func__, qid, ERR_PTR(err));
-			return;
-		}
-		pdsv->vqs[qid].irq = irq;
-
 		/* Pass vq setup info to DSC using adminq to gather up and
 		 * send all info at once so FW can do its full set up in
 		 * one easy operation
@@ -164,7 +149,6 @@ static void pds_vdpa_set_vq_ready(struct vdpa_device *vdpa_dev, u16 qid, bool re
 		if (err) {
 			dev_err(dev, "Failed to init vq %d: %pe\n",
 				qid, ERR_PTR(err));
-			pds_vdpa_release_irq(pdsv, qid);
 			ready = false;
 		}
 	} else {
@@ -172,7 +156,6 @@ static void pds_vdpa_set_vq_ready(struct vdpa_device *vdpa_dev, u16 qid, bool re
 		if (err)
 			dev_err(dev, "%s: reset_vq failed qid %d: %pe\n",
 				__func__, qid, ERR_PTR(err));
-		pds_vdpa_release_irq(pdsv, qid);
 	}
 
 	pdsv->vqs[qid].ready = ready;
@@ -318,6 +301,7 @@ static int pds_vdpa_set_driver_features(struct vdpa_device *vdpa_dev, u64 featur
 	struct device *dev = &pdsv->vdpa_dev.dev;
 	u64 driver_features;
 	u64 nego_features;
+	u64 hw_features;
 	u64 missing;
 
 	if (!(features & BIT_ULL(VIRTIO_F_ACCESS_PLATFORM)) && features) {
@@ -325,21 +309,26 @@ static int pds_vdpa_set_driver_features(struct vdpa_device *vdpa_dev, u64 featur
 		return -EOPNOTSUPP;
 	}
 
-	pdsv->req_features = features;
-
 	/* Check for valid feature bits */
-	nego_features = features & le64_to_cpu(pdsv->vdpa_aux->ident.hw_features);
-	missing = pdsv->req_features & ~nego_features;
+	nego_features = features & pdsv->supported_features;
+	missing = features & ~nego_features;
 	if (missing) {
 		dev_err(dev, "Can't support all requested features in %#llx, missing %#llx features\n",
-			pdsv->req_features, missing);
+			features, missing);
 		return -EOPNOTSUPP;
 	}
 
+	pdsv->negotiated_features = nego_features;
+
 	driver_features = pds_vdpa_get_driver_features(vdpa_dev);
 	dev_dbg(dev, "%s: %#llx => %#llx\n",
 		__func__, driver_features, nego_features);
 
+	/* if we're faking the F_MAC, strip it before writing to device */
+	hw_features = le64_to_cpu(pdsv->vdpa_aux->ident.hw_features);
+	if (!(hw_features & BIT_ULL(VIRTIO_NET_F_MAC)))
+		nego_features &= ~BIT_ULL(VIRTIO_NET_F_MAC);
+
 	if (driver_features == nego_features)
 		return 0;
 
@@ -352,7 +341,7 @@ static u64 pds_vdpa_get_driver_features(struct vdpa_device *vdpa_dev)
 {
 	struct pds_vdpa_device *pdsv = vdpa_to_pdsv(vdpa_dev);
 
-	return vp_modern_get_driver_features(&pdsv->vdpa_aux->vd_mdev);
+	return pdsv->negotiated_features;
 }
 
 static void pds_vdpa_set_config_cb(struct vdpa_device *vdpa_dev,
@@ -389,6 +378,72 @@ static u8 pds_vdpa_get_status(struct vdpa_device *vdpa_dev)
 	return vp_modern_get_status(&pdsv->vdpa_aux->vd_mdev);
 }
 
+static int pds_vdpa_request_irqs(struct pds_vdpa_device *pdsv)
+{
+	struct pci_dev *pdev = pdsv->vdpa_aux->padev->vf_pdev;
+	struct pds_vdpa_aux *vdpa_aux = pdsv->vdpa_aux;
+	struct device *dev = &pdsv->vdpa_dev.dev;
+	int max_vq, nintrs, qid, err;
+
+	max_vq = vdpa_aux->vdpa_mdev.max_supported_vqs;
+
+	nintrs = pci_alloc_irq_vectors(pdev, max_vq, max_vq, PCI_IRQ_MSIX);
+	if (nintrs < 0) {
+		dev_err(dev, "Couldn't get %d msix vectors: %pe\n",
+			max_vq, ERR_PTR(nintrs));
+		return nintrs;
+	}
+
+	for (qid = 0; qid < pdsv->num_vqs; ++qid) {
+		int irq = pci_irq_vector(pdev, qid);
+
+		snprintf(pdsv->vqs[qid].irq_name, sizeof(pdsv->vqs[qid].irq_name),
+			 "vdpa-%s-%d", dev_name(dev), qid);
+
+		err = request_irq(irq, pds_vdpa_isr, 0,
+				  pdsv->vqs[qid].irq_name,
+				  &pdsv->vqs[qid]);
+		if (err) {
+			dev_err(dev, "%s: no irq for qid %d: %pe\n",
+				__func__, qid, ERR_PTR(err));
+			goto err_release;
+		}
+
+		pdsv->vqs[qid].irq = irq;
+	}
+
+	vdpa_aux->nintrs = nintrs;
+
+	return 0;
+
+err_release:
+	while (qid--)
+		pds_vdpa_release_irq(pdsv, qid);
+
+	pci_free_irq_vectors(pdev);
+
+	vdpa_aux->nintrs = 0;
+
+	return err;
+}
+
+static void pds_vdpa_release_irqs(struct pds_vdpa_device *pdsv)
+{
+	struct pci_dev *pdev = pdsv->vdpa_aux->padev->vf_pdev;
+	struct pds_vdpa_aux *vdpa_aux = pdsv->vdpa_aux;
+	int qid;
+
+	if (!vdpa_aux->nintrs)
+		return;
+
+	for (qid = 0; qid < pdsv->num_vqs; qid++)
+		pds_vdpa_release_irq(pdsv, qid);
+
+	pci_free_irq_vectors(pdev);
+
+	vdpa_aux->nintrs = 0;
+}
+
 static void pds_vdpa_set_status(struct vdpa_device *vdpa_dev, u8 status)
 {
 	struct pds_vdpa_device *pdsv = vdpa_to_pdsv(vdpa_dev);
@@ -399,6 +454,11 @@ static void pds_vdpa_set_status(struct vdpa_device *vdpa_dev, u8 status)
 	old_status = pds_vdpa_get_status(vdpa_dev);
 	dev_dbg(dev, "%s: old %#x new %#x\n", __func__, old_status, status);
 
+	if (status & ~old_status & VIRTIO_CONFIG_S_DRIVER_OK) {
+		if (pds_vdpa_request_irqs(pdsv))
+			status = old_status | VIRTIO_CONFIG_S_FAILED;
+	}
+
 	pds_vdpa_cmd_set_status(pdsv, status);
 
 	/* Note: still working with FW on the need for this reset cmd */
@@ -409,6 +469,8 @@ static void pds_vdpa_set_status(struct vdpa_device *vdpa_dev, u8 status)
 			pdsv->vqs[i].avail_idx = 0;
 			pdsv->vqs[i].used_idx = 0;
 		}
+
+		pds_vdpa_cmd_set_mac(pdsv, pdsv->mac);
 	}
 
 	if (status & ~old_status & VIRTIO_CONFIG_S_FEATURES_OK) {
@@ -418,6 +480,20 @@ static void pds_vdpa_set_status(struct vdpa_device *vdpa_dev, u8 status)
 							i, &pdsv->vqs[i].notify_pa);
 		}
 	}
+
+	if (old_status & ~status & VIRTIO_CONFIG_S_DRIVER_OK)
+		pds_vdpa_release_irqs(pdsv);
+}
+
+static void pds_vdpa_init_vqs_entry(struct pds_vdpa_device *pdsv, int qid,
+				    void __iomem *notify)
+{
+	memset(&pdsv->vqs[qid], 0, sizeof(pdsv->vqs[0]));
+	pdsv->vqs[qid].qid = qid;
+	pdsv->vqs[qid].pdsv = pdsv;
+	pdsv->vqs[qid].ready = false;
+	pdsv->vqs[qid].irq = VIRTIO_MSI_NO_VECTOR;
+	pdsv->vqs[qid].notify = notify;
 }
 
 static int pds_vdpa_reset(struct vdpa_device *vdpa_dev)
@@ -441,14 +517,17 @@ static int pds_vdpa_reset(struct vdpa_device *vdpa_dev)
 			if (err)
 				dev_err(dev, "%s: reset_vq failed qid %d: %pe\n",
 					__func__, i, ERR_PTR(err));
-			pds_vdpa_release_irq(pdsv, i);
-			memset(&pdsv->vqs[i], 0, sizeof(pdsv->vqs[0]));
-			pdsv->vqs[i].ready = false;
 		}
 	}
 
 	pds_vdpa_set_status(vdpa_dev, 0);
 
+	if (status & VIRTIO_CONFIG_S_DRIVER_OK) {
+		/* Reset the vq info */
+		for (i = 0; i < pdsv->num_vqs && !err; i++)
+			pds_vdpa_init_vqs_entry(pdsv, i, pdsv->vqs[i].notify);
+	}
+
 	return 0;
 }
 
@@ -532,7 +611,6 @@ static int pds_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name,
 	struct device *dma_dev;
 	struct pci_dev *pdev;
 	struct device *dev;
-	u8 mac[ETH_ALEN];
 	int err;
 	int i;
 
@@ -563,7 +641,7 @@ static int pds_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name,
 
 	if (add_config->mask & BIT_ULL(VDPA_ATTR_DEV_FEATURES)) {
 		u64 unsupp_features =
-			add_config->device_features & ~mgmt->supported_features;
+			add_config->device_features & ~pdsv->supported_features;
 
 		if (unsupp_features) {
 			dev_err(dev, "Unsupported features: %#llx\n", unsupp_features);
@@ -614,29 +692,30 @@ static int pds_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name,
 	}
 
 	/* Set a mac, either from the user config if provided
-	 * or set a random mac if default is 00:..:00
+	 * or use the device's mac if not 00:..:00
+	 * or set a random mac
 	 */
 	if (add_config->mask & BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MACADDR)) {
-		ether_addr_copy(mac, add_config->net.mac);
-		pds_vdpa_cmd_set_mac(pdsv, mac);
+		ether_addr_copy(pdsv->mac, add_config->net.mac);
 	} else {
 		struct virtio_net_config __iomem *vc;
 
 		vc = pdsv->vdpa_aux->vd_mdev.device;
-		memcpy_fromio(mac, vc->mac, sizeof(mac));
-		if (is_zero_ether_addr(mac)) {
-			eth_random_addr(mac);
-			dev_info(dev, "setting random mac %pM\n", mac);
-			pds_vdpa_cmd_set_mac(pdsv, mac);
+		memcpy_fromio(pdsv->mac, vc->mac, sizeof(pdsv->mac));
+		if (is_zero_ether_addr(pdsv->mac) &&
+		    (pdsv->supported_features & BIT_ULL(VIRTIO_NET_F_MAC))) {
+			eth_random_addr(pdsv->mac);
+			dev_info(dev, "setting random mac %pM\n", pdsv->mac);
 		}
 	}
+	pds_vdpa_cmd_set_mac(pdsv, pdsv->mac);
 
 	for (i = 0; i < pdsv->num_vqs; i++) {
-		pdsv->vqs[i].qid = i;
-		pdsv->vqs[i].pdsv = pdsv;
-		pdsv->vqs[i].irq = VIRTIO_MSI_NO_VECTOR;
-		pdsv->vqs[i].notify = vp_modern_map_vq_notify(&pdsv->vdpa_aux->vd_mdev,
-							      i, &pdsv->vqs[i].notify_pa);
+		void __iomem *notify;
+
+		notify = vp_modern_map_vq_notify(&pdsv->vdpa_aux->vd_mdev,
+						 i, &pdsv->vqs[i].notify_pa);
+		pds_vdpa_init_vqs_entry(pdsv, i, notify);
 	}
 
 	pdsv->vdpa_dev.mdev = &vdpa_aux->vdpa_mdev;
@@ -746,24 +825,19 @@ int pds_vdpa_get_mgmt_info(struct pds_vdpa_aux *vdpa_aux)
 
 	max_vqs = min_t(u16, dev_intrs, max_vqs);
 	mgmt->max_supported_vqs = min_t(u16, PDS_VDPA_MAX_QUEUES, max_vqs);
-	vdpa_aux->nintrs = mgmt->max_supported_vqs;
+	vdpa_aux->nintrs = 0;
 
 	mgmt->ops = &pds_vdpa_mgmt_dev_ops;
 	mgmt->id_table = pds_vdpa_id_table;
 	mgmt->device = dev;
 	mgmt->supported_features = le64_to_cpu(vdpa_aux->ident.hw_features);
+
+	/* advertise F_MAC even if the device doesn't */
+	mgmt->supported_features |= BIT_ULL(VIRTIO_NET_F_MAC);
+
 	mgmt->config_attr_mask = BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MACADDR);
 	mgmt->config_attr_mask |= BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MAX_VQP);
 	mgmt->config_attr_mask |= BIT_ULL(VDPA_ATTR_DEV_FEATURES);
 
-	err = pci_alloc_irq_vectors(pdev, vdpa_aux->nintrs, vdpa_aux->nintrs,
-				    PCI_IRQ_MSIX);
-	if (err < 0) {
-		dev_err(dev, "Couldn't get %d msix vectors: %pe\n",
-			vdpa_aux->nintrs, ERR_PTR(err));
-		return err;
-	}
-	vdpa_aux->nintrs = err;
-
 	return 0;
 }
diff --git a/drivers/vdpa/pds/vdpa_dev.h b/drivers/vdpa/pds/vdpa_dev.h
index a1bc37de9537..d984ba24a7da 100644
--- a/drivers/vdpa/pds/vdpa_dev.h
+++ b/drivers/vdpa/pds/vdpa_dev.h
@@ -35,10 +35,11 @@ struct pds_vdpa_device {
 	struct pds_vdpa_aux *vdpa_aux;
 
 	struct pds_vdpa_vq_info vqs[PDS_VDPA_MAX_QUEUES];
-	u64 supported_features;		/* specified device features */
-	u64 req_features;		/* features requested by vdpa */
+	u64 supported_features;		/* supported device features */
+	u64 negotiated_features;	/* negotiated features */
 	u8 vdpa_index;			/* rsvd for future subdevice use */
 	u8 num_vqs;			/* num vqs in use */
+	u8 mac[ETH_ALEN];		/* mac selected when the device was added */
 	struct vdpa_callback config_cb;
 	struct notifier_block nb;
 };
diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index 965e32529eb8..a7612e0783b3 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -1247,44 +1247,41 @@ static const struct nla_policy vdpa_nl_policy[VDPA_ATTR_MAX + 1] = {
 	[VDPA_ATTR_MGMTDEV_DEV_NAME] = { .type = NLA_STRING },
 	[VDPA_ATTR_DEV_NAME] = { .type = NLA_STRING },
 	[VDPA_ATTR_DEV_NET_CFG_MACADDR] = NLA_POLICY_ETH_ADDR,
+	[VDPA_ATTR_DEV_NET_CFG_MAX_VQP] = { .type = NLA_U16 },
 	/* virtio spec 1.1 section 5.1.4.1 for valid MTU range */
 	[VDPA_ATTR_DEV_NET_CFG_MTU] = NLA_POLICY_MIN(NLA_U16, 68),
+	[VDPA_ATTR_DEV_QUEUE_INDEX] = { .type = NLA_U32 },
+	[VDPA_ATTR_DEV_FEATURES] = { .type = NLA_U64 },
 };
 
 static const struct genl_ops vdpa_nl_ops[] = {
 	{
 		.cmd = VDPA_CMD_MGMTDEV_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = vdpa_nl_cmd_mgmtdev_get_doit,
 		.dumpit = vdpa_nl_cmd_mgmtdev_get_dumpit,
 	},
 	{
 		.cmd = VDPA_CMD_DEV_NEW,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = vdpa_nl_cmd_dev_add_set_doit,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = VDPA_CMD_DEV_DEL,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = vdpa_nl_cmd_dev_del_set_doit,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = VDPA_CMD_DEV_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = vdpa_nl_cmd_dev_get_doit,
 		.dumpit = vdpa_nl_cmd_dev_get_dumpit,
 	},
 	{
 		.cmd = VDPA_CMD_DEV_CONFIG_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = vdpa_nl_cmd_dev_config_get_doit,
 		.dumpit = vdpa_nl_cmd_dev_config_get_dumpit,
 	},
 	{
 		.cmd = VDPA_CMD_DEV_VSTATS_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = vdpa_nl_cmd_dev_stats_get_doit,
 		.flags = GENL_ADMIN_PERM,
 	},
diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c
index dc38ed21319d..df7869537ef1 100644
--- a/drivers/vdpa/vdpa_user/vduse_dev.c
+++ b/drivers/vdpa/vdpa_user/vduse_dev.c
@@ -935,10 +935,10 @@ static void vduse_dev_irq_inject(struct work_struct *work)
 {
 	struct vduse_dev *dev = container_of(work, struct vduse_dev, inject);
 
-	spin_lock_irq(&dev->irq_lock);
+	spin_lock_bh(&dev->irq_lock);
 	if (dev->config_cb.callback)
 		dev->config_cb.callback(dev->config_cb.private);
-	spin_unlock_irq(&dev->irq_lock);
+	spin_unlock_bh(&dev->irq_lock);
 }
 
 static void vduse_vq_irq_inject(struct work_struct *work)
@@ -946,10 +946,10 @@ static void vduse_vq_irq_inject(struct work_struct *work)
 	struct vduse_virtqueue *vq = container_of(work,
 					struct vduse_virtqueue, inject);
 
-	spin_lock_irq(&vq->irq_lock);
+	spin_lock_bh(&vq->irq_lock);
 	if (vq->ready && vq->cb.callback)
 		vq->cb.callback(vq->cb.private);
-	spin_unlock_irq(&vq->irq_lock);
+	spin_unlock_bh(&vq->irq_lock);
 }
 
 static bool vduse_vq_signal_irqfd(struct vduse_virtqueue *vq)